0 files changed, 0 insertions, 0 deletions
diff --git a/CREDITS b/CREDITS
index 40cc4bfb34db..4df764ebe217 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3219,11 +3219,6 @@ N: Dipankar Sarma
 E: dipankar@in.ibm.com
 D: RCU
 
-N: Yoshinori Sato
-E: ysato@users.sourceforge.jp
-D: uClinux for Renesas H8/300 (H8300)
-D: http://uclinux-h8.sourceforge.jp/
-
 N: Hannu Savolainen
 E: hannu@opensound.com
 D: Maintainer of the sound drivers until 2.1.x days.
@@ -3709,6 +3704,13 @@ N: Dirk Verworner
 D: Co-author of German book ``Linux-Kernel-Programmierung''
 D: Co-founder of Berlin Linux User Group
 
+N: Andrew Victor
+E: linux@maxim.org.za
+W: http://maxim.org.za/at91_26.html
+D: First maintainer of Atmel ARM-based SoC, aka AT91
+D: Introduced support for at91rm9200, the first chip of AT91 family
+S: South Africa
+
 N: Riku Voipio
 E: riku.voipio@iki.fi
 D: Author of PCA9532 LED and Fintek f75375s hwmon driver
diff --git a/Documentation/ABI/testing/sysfs-bus-fcoe b/Documentation/ABI/testing/sysfs-bus-fcoe
index 21640eaad371..657df13b100d 100644
--- a/Documentation/ABI/testing/sysfs-bus-fcoe
+++ b/Documentation/ABI/testing/sysfs-bus-fcoe
@@ -32,7 +32,7 @@ Description:	'FCoE Controller' instances on the fcoe bus.
 
 Attributes:
 
-	fcf_dev_loss_tmo: Device loss timeout peroid (see below). Changing
+	fcf_dev_loss_tmo: Device loss timeout period (see below). Changing
 			  this value will change the dev_loss_tmo for all
 			  FCFs discovered by this controller.
 
@@ -61,7 +61,7 @@ Attributes:
 	lesb/err_block:   Link Error Status Block (LESB) block error count.
 
 	lesb/fcs_error:   Link Error Status Block (LESB) Fibre Channel
-			  Serivces error count.
+			  Services error count.
 
 Notes: ctlr_X (global increment starting at 0)
 
@@ -85,7 +85,7 @@ Attributes:
 		     fabric.
 
 	selected:    1 indicates that the switch has been selected for use;
-		     0 indicates that the swich will not be used.
+		     0 indicates that the switch will not be used.
 
 	fc_map:      The Fibre Channel MAP
 
@@ -93,7 +93,7 @@ Attributes:
 
 	mac:         The FCF's MAC address
 
-	fka_peroid:  The FIP Keep-Alive peroid
+	fka_period:  The FIP Keep-Alive period
 
 	fabric_state: The internal kernel state
 		      "Unknown" - Initialization value
@@ -101,9 +101,9 @@ Attributes:
 		      "Connected" - Host is connected to the FCF
 		      "Deleted" - FCF is being removed from the system
 
-	dev_loss_tmo: The device loss timeout peroid for this FCF.
+	dev_loss_tmo: The device loss timeout period for this FCF.
 
-Notes: A device loss infrastructre similar to the FC Transport's
+Notes: A device loss infrastructure similar to the FC Transport's
        is present in fcoe_sysfs. It is nice to have so that a
        link flapping adapter doesn't continually advance the count
        used to identify the discovered FCF. FCFs will exist in a
diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-janz-cmodio b/Documentation/ABI/testing/sysfs-bus-pci-drivers-janz-cmodio
new file mode 100644
index 000000000000..4d08f28dc871
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-janz-cmodio
@@ -0,0 +1,8 @@
+What:		/sys/bus/pci/drivers/janz-cmodio/.../modulbus_number
+Date:		May 2010
+KernelVersion:	2.6.35
+Contact:	Ira W. Snyder <ira.snyder@gmail.com>
+Description:
+		Value representing the HEX switch S2 of the janz carrier board CMOD-IO or CAN-PCI2
+
+		Read-only: value of the configuration switch (0..15)
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index d46bba801aac..acfe9df83139 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -6,6 +6,17 @@ Example: The real path of the attribute /sys/class/cxl/afu0.0s/irqs_max is
 
 Slave contexts (eg. /sys/class/cxl/afu0.0s):
 
+What:           /sys/class/cxl/<afu>/afu_err_buf
+Date:           September 2014
+Contact:        linuxppc-dev@lists.ozlabs.org
+Description:    read only
+                AFU Error Buffer contents. The contents of this file are
+		application specific and depends on the AFU being used.
+		Applications interacting with the AFU can use this attribute
+		to know about the current error condition and take appropriate
+		action like logging the event etc.
+
+
 What:           /sys/class/cxl/<afu>/irqs_max
 Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
@@ -15,6 +26,7 @@ Description:    read/write
                 that hardware can support (eg. 2037). Write values will limit
                 userspace applications to that many userspace interrupts. Must
                 be >= irqs_min.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/irqs_min
 Date:           September 2014
@@ -24,6 +36,7 @@ Description:    read only
                 userspace must request on a CXL_START_WORK ioctl. Userspace may
                 omit the num_interrupts field in the START_WORK IOCTL to get
                 this minimum automatically.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/mmio_size
 Date:           September 2014
@@ -31,6 +44,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the size of the MMIO space that may be mmaped
                 by userspace.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/modes_supported
 Date:           September 2014
@@ -38,6 +52,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 List of the modes this AFU supports. One per line.
                 Valid entries are: "dedicated_process" and "afu_directed"
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/mode
 Date:           September 2014
@@ -46,6 +61,7 @@ Description:    read/write
                 The current mode the AFU is using. Will be one of the modes
                 given in modes_supported. Writing will change the mode
                 provided that no user contexts are attached.
+Users:		https://github.com/ibm-capi/libcxl
 
 
 What:           /sys/class/cxl/<afu>/prefault_mode
@@ -59,6 +75,7 @@ Description:    read/write
                                  descriptor as an effective address and
                                  prefault what it points to.
                         all: all segments process calling START_WORK maps.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/reset
 Date:           September 2014
@@ -66,12 +83,14 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    write only
                 Writing 1 here will reset the AFU provided there are not
                 contexts active on the AFU.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/api_version
 Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the current version of the kernel/user API.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/api_version_compatible
 Date:           September 2014
@@ -79,6 +98,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the the lowest version of the userspace API
                 this this kernel supports.
+Users:		https://github.com/ibm-capi/libcxl
 
 
 AFU configuration records (eg. /sys/class/cxl/afu0.0/cr0):
@@ -92,6 +112,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
 		Hexadecimal value of the vendor ID found in this AFU
 		configuration record.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/cr<config num>/device
 Date:           February 2015
@@ -99,6 +120,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
 		Hexadecimal value of the device ID found in this AFU
 		configuration record.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/cr<config num>/class
 Date:           February 2015
@@ -106,6 +128,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
 		Hexadecimal value of the class code found in this AFU
 		configuration record.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>/cr<config num>/config
 Date:           February 2015
@@ -115,6 +138,7 @@ Description:    read only
 		record. The format is expected to match the either the standard
 		or extended configuration space defined by the PCIe
 		specification.
+Users:		https://github.com/ibm-capi/libcxl
 
 
 
@@ -126,18 +150,21 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the size of the MMIO space that may be mmaped
                 by userspace. This includes all slave contexts space also.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>m/pp_mmio_len
 Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the Per Process MMIO space length.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<afu>m/pp_mmio_off
 Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Decimal value of the Per Process MMIO space offset.
+Users:		https://github.com/ibm-capi/libcxl
 
 
 Card info (eg. /sys/class/cxl/card0)
@@ -147,12 +174,14 @@ Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Identifies the CAIA Version the card implements.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/psl_revision
 Date:           September 2014
 Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Identifies the revision level of the PSL.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/base_image
 Date:           September 2014
@@ -162,6 +191,7 @@ Description:    read only
                 that support loadable PSLs. For FPGAs this field identifies
                 the image contained in the on-adapter flash which is loaded
                 during the initial program load.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/image_loaded
 Date:           September 2014
@@ -169,6 +199,7 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    read only
                 Will return "user" or "factory" depending on the image loaded
                 onto the card.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/load_image_on_perst
 Date:           December 2014
@@ -183,6 +214,7 @@ Description:    read/write
                 user or factory image to be loaded.
                 Default is to reload on PERST whichever image the card has
                 loaded.
+Users:		https://github.com/ibm-capi/libcxl
 
 What:           /sys/class/cxl/<card>/reset
 Date:           October 2014
@@ -190,3 +222,4 @@ Contact:        linuxppc-dev@lists.ozlabs.org
 Description:    write only
                 Writing 1 will issue a PERST to card which may cause the card
                 to reload the FPGA depending on load_image_on_perst.
+Users:		https://github.com/ibm-capi/libcxl
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index 5ecfd72ba684..668604fc8e06 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -39,6 +39,25 @@ Description:
 		Format is a string, e.g: 00:11:22:33:44:55 for an Ethernet MAC
 		address.
 
+What:		/sys/class/net/<bridge iface>/bridge/group_fwd_mask
+Date:		January 2012
+KernelVersion:	3.2
+Contact:	netdev@vger.kernel.org
+Description:
+		Bitmask to allow forwarding of link local frames with address
+		01-80-C2-00-00-0X on a bridge device. Only values that set bits
+		not matching BR_GROUPFWD_RESTRICTED in net/bridge/br_private.h
+		allowed.
+		Default value 0 does not forward any link local frames.
+
+		Restricted bits:
+		0: 01-80-C2-00-00-00 Bridge Group Address used for STP
+		1: 01-80-C2-00-00-01 (MAC Control) 802.3 used for MAC PAUSE
+		2: 01-80-C2-00-00-02 (Link Aggregation) 802.3ad
+
+		Any values not setting these bits can be used. Take special
+		care when forwarding control frames e.g. 802.1X-PAE or LLDP.
+
 What:		/sys/class/net/<iface>/broadcast
 Date:		April 2005
 KernelVersion:	2.6.12
diff --git a/Documentation/ABI/testing/sysfs-class-net-janz-ican3 b/Documentation/ABI/testing/sysfs-class-net-janz-ican3
new file mode 100644
index 000000000000..fdbc03a2b8f8
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-janz-ican3
@@ -0,0 +1,19 @@
+What:		/sys/class/net/<iface>/termination
+Date:		May 2010
+KernelVersion:	2.6.35
+Contact:	Ira W. Snyder <ira.snyder@gmail.com>
+Description:
+		Value representing the can bus termination
+
+		Default: 1 (termination active)
+		Reading: get actual termination state
+		Writing: set actual termination state (0=no termination, 1=termination active)
+
+What:		/sys/class/net/<iface>/fwinfo
+Date:		May 2015
+KernelVersion:	3.19
+Contact:	Andreas Gröger <andreas24groeger@gmail.com>
+Description:
+		Firmware stamp of ican3 module
+		Read-only: 32 byte string identification of the ICAN3 module
+		(known values: "JANZ-ICAN3 ICANOS 1.xx", "JANZ-ICAN3 CAL/CANopen 1.xx")
diff --git a/Documentation/ABI/testing/sysfs-class-scsi_tape b/Documentation/ABI/testing/sysfs-class-scsi_tape
new file mode 100644
index 000000000000..9be398b87ee9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-scsi_tape
@@ -0,0 +1,109 @@
+What:           /sys/class/scsi_tape/*/stats/in_flight
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Show the number of I/Os currently in-flight between the st
+		module and the SCSI mid-layer.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/io_ns
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total amount of time spent waiting for all I/O
+                to and from the tape drive to complete. This includes all
+                reads, writes, and other SCSI commands issued to the tape
+                drive. An example of other SCSI commands would be tape
+                movement such as a rewind when a rewind tape device is
+                closed. This item is measured in nanoseconds.
+
+                To determine the amount of time spent waiting for other I/O
+                to complete subtract read_ns and write_ns from this value.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/other_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		The number of I/O requests issued to the tape drive other
+		than SCSI read/write requests.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/read_byte_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total number of bytes requested from the tape drive.
+		This value is presented in bytes because tape drives support
+		variable length block sizes.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/read_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total number of read requests issued to the tape
+		drive.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/read_ns
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total amount of time in nanoseconds waiting for
+		read I/O requests to complete.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/write_byte_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total number of bytes written to the tape drive.
+		This value is presented in bytes because tape drives support
+		variable length block sizes.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/write_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total number of write requests issued to the tape
+		drive.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/write_ms
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the total amount of time in nanoseconds waiting for
+		write I/O requests to complete.
+Users:
+
+
+What:           /sys/class/scsi_tape/*/stats/resid_cnt
+Date:           Apr 2015
+KernelVersion:  4.2
+Contact:        Shane Seymour <shane.seymour@hp.com>
+Description:
+		Shows the number of times we found that a residual >0
+		was found when the SCSI midlayer indicated that there was
+		an error. For reads this may be a case of someone issuing
+		reads greater than the block size.
+Users:
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 99983e67c13c..da95513571ea 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -162,7 +162,7 @@ Description:	Discover CPUs in the same CPU frequency coordination domain
 What:		/sys/devices/system/cpu/cpu*/cache/index3/cache_disable_{0,1}
 Date:		August 2008
 KernelVersion:	2.6.27
-Contact:	discuss@x86-64.org
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Disable L3 cache indices
 
 		These files exist in every CPU's cache/index3 directory. Each
diff --git a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
index b3f6a2ac5007..db197a879580 100644
--- a/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
+++ b/Documentation/ABI/testing/sysfs-driver-hid-logitech-lg4ff
@@ -1,7 +1,7 @@
-What:		/sys/module/hid_logitech/drivers/hid:logitech/<dev>/range.
+What:		/sys/bus/hid/drivers/logitech/<dev>/range
 Date:		July 2011
 KernelVersion:	3.2
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Display minimum, maximum and current range of the steering
 		wheel. Writing a value within min and max boundaries sets the
 		range of the wheel.
@@ -9,7 +9,7 @@ Description:	Display minimum, maximum and current range of the steering
 What:		/sys/bus/hid/drivers/logitech/<dev>/alternate_modes
 Date:		Feb 2015
 KernelVersion:	4.1
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Displays a set of alternate modes supported by a wheel. Each
 		mode is listed as follows:
 		  Tag: Mode Name
@@ -45,7 +45,7 @@ Description:	Displays a set of alternate modes supported by a wheel. Each
 What:		/sys/bus/hid/drivers/logitech/<dev>/real_id
 Date:		Feb 2015
 KernelVersion:	4.1
-Contact:	Michal Malý <madcatxster@gmail.com>
+Contact:	Michal Malý <madcatxster@devoid-pointer.net>
 Description:	Displays the real model of the wheel regardless of any
 		alternate mode the wheel might be switched to.
 		It is a read-only value.
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
index 05874da7ce80..e794eac32a90 100644
--- a/Documentation/ABI/testing/sysfs-firmware-efi
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -18,3 +18,13 @@ Contact:	Dave Young <dyoung@redhat.com>
 Description:	It shows the physical address of config table entry in the EFI
 		system table.
 Users:		Kexec
+
+What:		/sys/firmware/efi/systab
+Date:		April 2005
+Contact:	linux-efi@vger.kernel.org
+Description:	Displays the physical addresses of all EFI Configuration
+		Tables found via the EFI System Table. The order in
+		which the tables are printed forms an ABI and newer
+		versions are always printed first, i.e. ACPI20 comes
+		before ACPI.
+Users:		dmidecode
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-esrt b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
new file mode 100644
index 000000000000..6e431d1a4e79
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-esrt
@@ -0,0 +1,81 @@
+What:		/sys/firmware/efi/esrt/
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Provides userland access to read the EFI System Resource Table
+		(ESRT), a catalog of firmware for which can be updated with
+		the UEFI UpdateCapsule mechanism described in section 7.5 of
+		the UEFI Standard.
+Users:		fwupdate - https://github.com/rhinstaller/fwupdate
+
+What:		/sys/firmware/efi/esrt/fw_resource_count
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The number of entries in the ESRT
+
+What:		/sys/firmware/efi/esrt/fw_resource_count_max
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The maximum number of entries that /could/ be registered
+		in the allocation the table is currently in.  This is
+		really only useful to the system firmware itself.
+
+What:		/sys/firmware/efi/esrt/fw_resource_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The version of the ESRT structure provided by the firmware.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Each ESRT entry is identified by a GUID, and each gets a
+		subdirectory under entries/ .
+		example: /sys/firmware/efi/esrt/entries/entry0/
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_type
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	What kind of firmware entry this is:
+		0 - Unknown
+		1 - System Firmware
+		2 - Device Firmware
+		3 - UEFI Driver
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_class
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	This is the entry's guid, and will match the directory name.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/fw_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The version of the firmware currently installed.  This is a
+		32-bit unsigned integer.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/lowest_supported_fw_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The lowest version of the firmware that can be installed.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/capsule_flags
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	Flags that must be passed to UpdateCapsule()
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/last_attempt_version
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The last firmware version for which an update was attempted.
+
+What:		/sys/firmware/efi/esrt/entries/entry$N/last_attempt_status
+Date:		February 2015
+Contact:	Peter Jones <pjones@redhat.com>
+Description:	The result of the last firmware update attempt for the
+		firmware resource entry.
+		0 - Success
+		1 - Insufficient resources
+		2 - Incorrect version
+		3 - Invalid format
+		4 - Authentication error
+		5 - AC power event
+		6 - Battery power event
+
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index f4b78eafd92a..b713c35f8543 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -670,7 +670,7 @@ functions:
 	typeof(x) ret;			\
 	ret = calc_ret(x);		\
 	(ret);				\
-)}
+})
 
 ret is a common name for a local variable - __foo_ret is less likely
 to collide with an existing variable.
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 0f7afb2bb442..55b70b903ead 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -25,13 +25,18 @@ physical addresses.  These are the addresses in /proc/iomem.  The physical
 address is not directly useful to a driver; it must use ioremap() to map
 the space and produce a virtual address.
 
-I/O devices use a third kind of address: a "bus address" or "DMA address".
-If a device has registers at an MMIO address, or if it performs DMA to read
-or write system memory, the addresses used by the device are bus addresses.
-In some systems, bus addresses are identical to CPU physical addresses, but
-in general they are not.  IOMMUs and host bridges can produce arbitrary
+I/O devices use a third kind of address: a "bus address".  If a device has
+registers at an MMIO address, or if it performs DMA to read or write system
+memory, the addresses used by the device are bus addresses.  In some
+systems, bus addresses are identical to CPU physical addresses, but in
+general they are not.  IOMMUs and host bridges can produce arbitrary
 mappings between physical and bus addresses.
 
+From a device's point of view, DMA uses the bus address space, but it may
+be restricted to a subset of that space.  For example, even if a system
+supports 64-bit addresses for main memory and PCI BARs, it may use an IOMMU
+so devices only need to use 32-bit DMA addresses.
+
 Here's a picture and some examples:
 
                CPU                  CPU                  Bus
@@ -72,11 +77,11 @@ can use virtual address X to access the buffer, but the device itself
 cannot because DMA doesn't go through the CPU virtual memory system.
 
 In some simple systems, the device can do DMA directly to physical address
-Y.  But in many others, there is IOMMU hardware that translates bus
+Y.  But in many others, there is IOMMU hardware that translates DMA
 addresses to physical addresses, e.g., it translates Z to Y.  This is part
 of the reason for the DMA API: the driver can give a virtual address X to
 an interface like dma_map_single(), which sets up any required IOMMU
-mapping and returns the bus address Z.  The driver then tells the device to
+mapping and returns the DMA address Z.  The driver then tells the device to
 do DMA to Z, and the IOMMU maps it to the buffer at address Y in system
 RAM.
 
@@ -98,7 +103,7 @@ First of all, you should make sure
 #include <linux/dma-mapping.h>
 
 is in your driver, which provides the definition of dma_addr_t.  This type
-can hold any valid DMA or bus address for the platform and should be used
+can hold any valid DMA address for the platform and should be used
 everywhere you hold a DMA address returned from the DMA mapping functions.
 
 			 What memory is DMA'able?
@@ -240,7 +245,7 @@ the case would look like this:
 
 	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
-	   	consistent_using_dac = 1;
+		consistent_using_dac = 1;
 	} else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
@@ -316,7 +321,7 @@ There are two types of DMA mappings:
   Think of "consistent" as "synchronous" or "coherent".
 
   The current default is to return consistent memory in the low 32
-  bits of the bus space.  However, for future compatibility you should
+  bits of the DMA space.  However, for future compatibility you should
   set the consistent mask even if this default is fine for your
   driver.
 
@@ -353,7 +358,7 @@ There are two types of DMA mappings:
   transfer, unmapped right after it (unless you use dma_sync_* below)
   and for which hardware can optimize for sequential accesses.
 
-  This of "streaming" as "asynchronous" or "outside the coherency
+  Think of "streaming" as "asynchronous" or "outside the coherency
   domain".
 
   Good examples of what to use streaming mappings for are:
@@ -403,7 +408,7 @@ dma_alloc_coherent() returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the
 card.
 
-The CPU virtual address and the DMA bus address are both
+The CPU virtual address and the DMA address are both
 guaranteed to be aligned to the smallest PAGE_SIZE order which
 is greater than or equal to the requested size.  This invariant
 exists (for example) to guarantee that if you allocate a chunk
@@ -645,8 +650,8 @@ PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
               dma_map_sg call.
 
 Every dma_map_{single,sg}() call should have its dma_unmap_{single,sg}()
-counterpart, because the bus address space is a shared resource and
-you could render the machine unusable by consuming all bus addresses.
+counterpart, because the DMA address space is a shared resource and
+you could render the machine unusable by consuming all DMA addresses.
 
 If you need to use the same streaming DMA region multiple times and touch
 the data in between the DMA transfers, the buffer needs to be synced
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 52088408668a..7eba542eff7c 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -18,10 +18,10 @@ Part I - dma_ API
 To get the dma_ API, you must #include <linux/dma-mapping.h>.  This
 provides dma_addr_t and the interfaces described below.
 
-A dma_addr_t can hold any valid DMA or bus address for the platform.  It
-can be given to a device to use as a DMA source or target.  A CPU cannot
-reference a dma_addr_t directly because there may be translation between
-its physical address space and the bus address space.
+A dma_addr_t can hold any valid DMA address for the platform.  It can be
+given to a device to use as a DMA source or target.  A CPU cannot reference
+a dma_addr_t directly because there may be translation between its physical
+address space and the DMA address space.
 
 Part Ia - Using large DMA-coherent buffers
 ------------------------------------------
@@ -42,7 +42,7 @@ It returns a pointer to the allocated region (in the processor's virtual
 address space) or NULL if the allocation failed.
 
 It also returns a <dma_handle> which may be cast to an unsigned integer the
-same width as the bus and given to the device as the bus address base of
+same width as the bus and given to the device as the DMA address base of
 the region.
 
 Note: consistent memory can be expensive on some platforms, and the
@@ -193,7 +193,7 @@ dma_map_single(struct device *dev, void *cpu_addr, size_t size,
 		      enum dma_data_direction direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
-device and returns the bus address of the memory.
+device and returns the DMA address of the memory.
 
 The direction for both APIs may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
@@ -212,20 +212,20 @@ contiguous piece of memory.  For this reason, memory to be mapped by
 this API should be obtained from sources which guarantee it to be
 physically contiguous (like kmalloc).
 
-Further, the bus address of the memory must be within the
+Further, the DMA address of the memory must be within the
 dma_mask of the device (the dma_mask is a bit mask of the
-addressable region for the device, i.e., if the bus address of
-the memory ANDed with the dma_mask is still equal to the bus
+addressable region for the device, i.e., if the DMA address of
+the memory ANDed with the dma_mask is still equal to the DMA
 address, then the device can perform DMA to the memory).  To
 ensure that the memory allocated by kmalloc is within the dma_mask,
 the driver may specify various platform-dependent flags to restrict
-the bus address range of the allocation (e.g., on x86, GFP_DMA
-guarantees to be within the first 16MB of available bus addresses,
+the DMA address range of the allocation (e.g., on x86, GFP_DMA
+guarantees to be within the first 16MB of available DMA addresses,
 as required by ISA devices).
 
 Note also that the above constraints on physical contiguity and
 dma_mask may not apply if the platform has an IOMMU (a device which
-maps an I/O bus address to a physical memory address).  However, to be
+maps an I/O DMA address to a physical memory address).  However, to be
 portable, device driver writers may *not* assume that such an IOMMU
 exists.
 
@@ -296,7 +296,7 @@ reduce current DMA mapping usage or delay and try again later).
 	dma_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction direction)
 
-Returns: the number of bus address segments mapped (this may be shorter
+Returns: the number of DMA address segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
 physically or virtually adjacent and an IOMMU maps them with a single
 entry).
@@ -340,7 +340,7 @@ must be the same as those and passed in to the scatter/gather mapping
 API.
 
 Note: <nents> must be the number you passed in, *not* the number of
-bus address entries returned.
+DMA address entries returned.
 
 void
 dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
@@ -507,7 +507,7 @@ it's asked for coherent memory for this device.
 phys_addr is the CPU physical address to which the memory is currently
 assigned (this will be ioremapped so the CPU can access the region).
 
-device_addr is the bus address the device needs to be programmed
+device_addr is the DMA address the device needs to be programmed
 with to actually address this memory (this will be handed out as the
 dma_addr_t in dma_alloc_coherent()).
 
diff --git a/Documentation/DocBook/crypto-API.tmpl b/Documentation/DocBook/crypto-API.tmpl
index efc8d90a9a3f..0992531ffefb 100644
--- a/Documentation/DocBook/crypto-API.tmpl
+++ b/Documentation/DocBook/crypto-API.tmpl
@@ -119,7 +119,7 @@
 
     <para>
      Note: The terms "transformation" and cipher algorithm are used
-     interchangably.
+     interchangeably.
     </para>
    </sect1>
 
@@ -536,8 +536,8 @@
 
      <para>
       For other use cases of AEAD ciphers, the ASCII art applies as
-      well, but the caller may not use the GIVCIPHER interface. In
-      this case, the caller must generate the IV.
+      well, but the caller may not use the AEAD cipher with a separate
+      IV generator. In this case, the caller must generate the IV.
      </para>
 
      <para>
@@ -584,8 +584,8 @@ kernel crypto API                                |   IPSEC Layer
                                                  |
 +-----------+                                    |
 |           |            (1)
-| givcipher | <-----------------------------------  esp_output
-|  (seqiv)  | ---+
+|   aead    | <-----------------------------------  esp_output
+| (seqniv)  | ---+
 +-----------+    |
                  | (2)
 +-----------+    |
@@ -620,8 +620,8 @@ kernel crypto API                                |   IPSEC Layer
      <orderedlist>
       <listitem>
        <para>
-        esp_output() invokes crypto_aead_givencrypt() to trigger an encryption
-        operation of the GIVCIPHER implementation.
+        esp_output() invokes crypto_aead_encrypt() to trigger an encryption
+        operation of the AEAD cipher with IV generator.
        </para>
 
        <para>
@@ -1563,7 +1563,7 @@ struct sockaddr_alg sa = {
 
    <sect1><title>Zero-Copy Interface</title>
     <para>
-     In addition to the send/write/read/recv system call familty, the AF_ALG
+     In addition to the send/write/read/recv system call family, the AF_ALG
      interface can be accessed with the zero-copy interface of splice/vmsplice.
      As the name indicates, the kernel tries to avoid a copy operation into
      kernel space.
@@ -1669,9 +1669,19 @@ read(opfd, out, outlen);
   </chapter>
 
   <chapter id="API"><title>Programming Interface</title>
+   <para>
+    Please note that the kernel crypto API contains the AEAD givcrypt
+    API (crypto_aead_giv* and aead_givcrypt_* function calls in
+    include/crypto/aead.h). This API is obsolete and will be removed
+    in the future. To obtain the functionality of an AEAD cipher with
+    internal IV generation, use the IV generator as a regular cipher.
+    For example, rfc4106(gcm(aes)) is the AEAD cipher with external
+    IV generation and seqniv(rfc4106(gcm(aes))) implies that the kernel
+    crypto API generates the IV. Different IV generators are available.
+   </para>
    <sect1><title>Block Cipher Context Data Structures</title>
 !Pinclude/linux/crypto.h Block Cipher Context Data Structures
-!Finclude/linux/crypto.h aead_request
+!Finclude/crypto/aead.h aead_request
    </sect1>
    <sect1><title>Block Cipher Algorithm Definitions</title>
 !Pinclude/linux/crypto.h Block Cipher Algorithm Definitions
@@ -1680,7 +1690,7 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h aead_alg
 !Finclude/linux/crypto.h blkcipher_alg
 !Finclude/linux/crypto.h cipher_alg
-!Finclude/linux/crypto.h rng_alg
+!Finclude/crypto/rng.h rng_alg
    </sect1>
    <sect1><title>Asynchronous Block Cipher API</title>
 !Pinclude/linux/crypto.h Asynchronous Block Cipher API
@@ -1704,26 +1714,27 @@ read(opfd, out, outlen);
 !Finclude/linux/crypto.h ablkcipher_request_set_crypt
    </sect1>
    <sect1><title>Authenticated Encryption With Associated Data (AEAD) Cipher API</title>
-!Pinclude/linux/crypto.h Authenticated Encryption With Associated Data (AEAD) Cipher API
-!Finclude/linux/crypto.h crypto_alloc_aead
-!Finclude/linux/crypto.h crypto_free_aead
-!Finclude/linux/crypto.h crypto_aead_ivsize
-!Finclude/linux/crypto.h crypto_aead_authsize
-!Finclude/linux/crypto.h crypto_aead_blocksize
-!Finclude/linux/crypto.h crypto_aead_setkey
-!Finclude/linux/crypto.h crypto_aead_setauthsize
-!Finclude/linux/crypto.h crypto_aead_encrypt
-!Finclude/linux/crypto.h crypto_aead_decrypt
+!Pinclude/crypto/aead.h Authenticated Encryption With Associated Data (AEAD) Cipher API
+!Finclude/crypto/aead.h crypto_alloc_aead
+!Finclude/crypto/aead.h crypto_free_aead
+!Finclude/crypto/aead.h crypto_aead_ivsize
+!Finclude/crypto/aead.h crypto_aead_authsize
+!Finclude/crypto/aead.h crypto_aead_blocksize
+!Finclude/crypto/aead.h crypto_aead_setkey
+!Finclude/crypto/aead.h crypto_aead_setauthsize
+!Finclude/crypto/aead.h crypto_aead_encrypt
+!Finclude/crypto/aead.h crypto_aead_decrypt
    </sect1>
    <sect1><title>Asynchronous AEAD Request Handle</title>
-!Pinclude/linux/crypto.h Asynchronous AEAD Request Handle
-!Finclude/linux/crypto.h crypto_aead_reqsize
-!Finclude/linux/crypto.h aead_request_set_tfm
-!Finclude/linux/crypto.h aead_request_alloc
-!Finclude/linux/crypto.h aead_request_free
-!Finclude/linux/crypto.h aead_request_set_callback
-!Finclude/linux/crypto.h aead_request_set_crypt
-!Finclude/linux/crypto.h aead_request_set_assoc
+!Pinclude/crypto/aead.h Asynchronous AEAD Request Handle
+!Finclude/crypto/aead.h crypto_aead_reqsize
+!Finclude/crypto/aead.h aead_request_set_tfm
+!Finclude/crypto/aead.h aead_request_alloc
+!Finclude/crypto/aead.h aead_request_free
+!Finclude/crypto/aead.h aead_request_set_callback
+!Finclude/crypto/aead.h aead_request_set_crypt
+!Finclude/crypto/aead.h aead_request_set_assoc
+!Finclude/crypto/aead.h aead_request_set_ad
    </sect1>
    <sect1><title>Synchronous Block Cipher API</title>
 !Pinclude/linux/crypto.h Synchronous Block Cipher API
diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl
index e84f09467cd7..589b40cc5eb5 100644
--- a/Documentation/DocBook/kernel-hacking.tmpl
+++ b/Documentation/DocBook/kernel-hacking.tmpl
@@ -954,6 +954,8 @@ printk(KERN_INFO "my ip: %pI4\n", &amp;ipaddress);
     <function>MODULE_LICENSE()</function> that specifies a GPL
     compatible license.  It implies that the function is considered
     an internal implementation issue, and not really an interface.
+    Some maintainers and developers may however
+    require EXPORT_SYMBOL_GPL() when adding any new APIs or functionality.
    </para>
   </sect1>
  </chapter>
diff --git a/Documentation/DocBook/scsi.tmpl b/Documentation/DocBook/scsi.tmpl
index 324b53494f08..4b9b9b286cea 100644
--- a/Documentation/DocBook/scsi.tmpl
+++ b/Documentation/DocBook/scsi.tmpl
@@ -81,7 +81,7 @@
         SAS, Fibre Channel, FireWire, and ATAPI devices.  SCSI packets are
         also commonly exchanged over Infiniband,
         <ulink url='http://i2o.shadowconnect.com/faq.php'>I20</ulink>, TCP/IP
-        (<ulink url='http://en.wikipedia.org/wiki/ISCSI'>iSCSI</ulink>), even
+        (<ulink url='https://en.wikipedia.org/wiki/ISCSI'>iSCSI</ulink>), even
         <ulink url='http://cyberelk.net/tim/parport/parscsi.html'>Parallel
         ports</ulink>.
       </para>
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index 653d5d739d7f..31d1d658827f 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -505,7 +505,10 @@ at module load time (for a module) with:
 
 The addresses are normal I2C addresses.  The adapter is the string
 name of the adapter, as shown in /sys/class/i2c-adapter/i2c-<n>/name.
-It is *NOT* i2c-<n> itself.
+It is *NOT* i2c-<n> itself.  Also, the comparison is done ignoring
+spaces, so if the name is "This is an I2C chip" you can say
+adapter_name=ThisisanI2cchip.  This is because it's hard to pass in
+spaces in kernel parameters.
 
 The debug flags are bit flags for each BMC found, they are:
 IPMI messages: 1, driver state: 2, timing: 4, I2C probe: 8
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index f29bcbc463e7..370ca006db7a 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -1496,7 +1496,7 @@ Canis Rufus and Zoicon5 and Anome and Hal Eisen"
 ,month="July"
 ,day="8"
 ,year="2006"
-,note="\url{http://en.wikipedia.org/wiki/Read-copy-update}"
+,note="\url{https://en.wikipedia.org/wiki/Read-copy-update}"
 ,annotation={
 	Wikipedia RCU page as of July 8 2006.
 	[Viewed August 21, 2006]
diff --git a/Documentation/RCU/arrayRCU.txt b/Documentation/RCU/arrayRCU.txt
index 453ebe6953ee..f05a9afb2c39 100644
--- a/Documentation/RCU/arrayRCU.txt
+++ b/Documentation/RCU/arrayRCU.txt
@@ -10,7 +10,19 @@ also be used to protect arrays.  Three situations are as follows:
 
 3.  Resizeable Arrays
 
-Each of these situations are discussed below.
+Each of these three situations involves an RCU-protected pointer to an
+array that is separately indexed.  It might be tempting to consider use
+of RCU to instead protect the index into an array, however, this use
+case is -not- supported.  The problem with RCU-protected indexes into
+arrays is that compilers can play way too many optimization games with
+integers, which means that the rules governing handling of these indexes
+are far more trouble than they are worth.  If RCU-protected indexes into
+arrays prove to be particularly valuable (which they have not thus far),
+explicit cooperation from the compiler will be required to permit them
+to be safely used.
+
+That aside, each of the three RCU-protected pointer situations are
+described in the following sections.
 
 
 Situation 1: Hash Tables
@@ -36,9 +48,9 @@ Quick Quiz:  Why is it so important that updates be rare when
 Situation 3: Resizeable Arrays
 
 Use of RCU for resizeable arrays is demonstrated by the grow_ary()
-function used by the System V IPC code.  The array is used to map from
-semaphore, message-queue, and shared-memory IDs to the data structure
-that represents the corresponding IPC construct.  The grow_ary()
+function formerly used by the System V IPC code.  The array is used
+to map from semaphore, message-queue, and shared-memory IDs to the data
+structure that represents the corresponding IPC construct.  The grow_ary()
 function does not acquire any locks; instead its caller must hold the
 ids->sem semaphore.
 
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
index cd83d2348fef..da51d3068850 100644
--- a/Documentation/RCU/lockdep.txt
+++ b/Documentation/RCU/lockdep.txt
@@ -47,11 +47,6 @@ checking of rcu_dereference() primitives:
 		Use explicit check expression "c" along with
 		srcu_read_lock_held()().  This is useful in code that
 		is invoked by both SRCU readers and updaters.
-	rcu_dereference_index_check(p, c):
-		Use explicit check expression "c", but the caller
-		must supply one of the rcu_read_lock_held() functions.
-		This is useful in code that uses RCU-protected arrays
-		that is invoked by both RCU readers and updaters.
 	rcu_dereference_raw(p):
 		Don't check.  (Use sparingly, if at all.)
 	rcu_dereference_protected(p, c):
@@ -64,11 +59,6 @@ checking of rcu_dereference() primitives:
 		but retain the compiler constraints that prevent duplicating
 		or coalescsing.  This is useful when when testing the
 		value of the pointer itself, for example, against NULL.
-	rcu_access_index(idx):
-		Return the value of the index and omit all barriers, but
-		retain the compiler constraints that prevent duplicating
-		or coalescsing.  This is useful when when testing the
-		value of the index itself, for example, against -1.
 
 The rcu_dereference_check() check expression can be any boolean
 expression, but would normally include a lockdep expression.  However,
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index ceb05da5a5ac..1e6c0da994f5 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -25,17 +25,6 @@ o	You must use one of the rcu_dereference() family of primitives
 	for an example where the compiler can in fact deduce the exact
 	value of the pointer, and thus cause misordering.
 
-o	Do not use single-element RCU-protected arrays.  The compiler
-	is within its right to assume that the value of an index into
-	such an array must necessarily evaluate to zero.  The compiler
-	could then substitute the constant zero for the computation, so
-	that the array index no longer depended on the value returned
-	by rcu_dereference().  If the array index no longer depends
-	on rcu_dereference(), then both the compiler and the CPU
-	are within their rights to order the array access before the
-	rcu_dereference(), which can cause the array access to return
-	garbage.
-
 o	Avoid cancellation when using the "+" and "-" infix arithmetic
 	operators.  For example, for a given variable "x", avoid
 	"(x-x)".  There are similar arithmetic pitfalls from other
@@ -76,14 +65,15 @@ o	Do not use the results from the boolean "&&" and "||" when
 	dereferencing.	For example, the following (rather improbable)
 	code is buggy:
 
-		int a[2];
-		int index;
-		int force_zero_index = 1;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 && force_zero_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p != &oom_p1 && p != &oom_p2;
+		r1 = *q;  /* BUGGY!!! */
 
 	The reason this is buggy is that "&&" and "||" are often compiled
 	using branches.  While weak-memory machines such as ARM or PowerPC
@@ -94,14 +84,15 @@ o	Do not use the results from relational operators ("==", "!=",
 	">", ">=", "<", or "<=") when dereferencing.  For example,
 	the following (quite strange) code is buggy:
 
-		int a[2];
-		int index;
-		int flip_index = 0;
+		int *p;
+		int *q;
 
 		...
 
-		r1 = rcu_dereference(i1)
-		r2 = a[r1 != flip_index];  /* BUGGY!!! */
+		p = rcu_dereference(gp)
+		q = &global_q;
+		q += p > &oom_p;
+		r1 = *q;  /* BUGGY!!! */
 
 	As before, the reason this is buggy is that relational operators
 	are often compiled using branches.  And as before, although
@@ -193,6 +184,11 @@ o	Be very careful about comparing pointers obtained from
 		pointer.  Note that the volatile cast in rcu_dereference()
 		will normally prevent the compiler from knowing too much.
 
+		However, please note that if the compiler knows that the
+		pointer takes on only one of two values, a not-equal
+		comparison will provide exactly the information that the
+		compiler needs to deduce the value of the pointer.
+
 o	Disable any value-speculation optimizations that your compiler
 	might provide, especially if you are making use of feedback-based
 	optimizations that take data collected from prior runs.  Such
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 88dfce182f66..5746b0c77f3e 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -256,7 +256,9 @@ rcu_dereference()
 	If you are going to be fetching multiple fields from the
 	RCU-protected structure, using the local variable is of
 	course preferred.  Repeated rcu_dereference() calls look
-	ugly and incur unnecessary overhead on Alpha CPUs.
+	ugly, do not guarantee that the same pointer will be returned
+	if an update happened while in the critical section, and incur
+	unnecessary overhead on Alpha CPUs.
 
 	Note that the value returned by rcu_dereference() is valid
 	only within the enclosing RCU read-side critical section.
@@ -879,9 +881,7 @@ SRCU:	Initialization/cleanup
 
 All:  lockdep-checked RCU-protected pointer access
 
-	rcu_access_index
 	rcu_access_pointer
-	rcu_dereference_index_check
 	rcu_dereference_raw
 	rcu_lockdep_assert
 	rcu_sleep_check
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index b03a832a08e2..27e7e5edeca8 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -299,7 +299,9 @@ toward the stable maintainers by putting a line like this:
 
   Cc: stable@vger.kernel.org
 
-into your patch.
+into the sign-off area of your patch (note, NOT an email recipient).  You
+should also read Documentation/stable_kernel_rules.txt in addition to this
+file.
 
 Note, however, that some subsystem maintainers want to come to their own
 conclusions on which patches should go to the stable trees.  The networking
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index 750401f91341..b731b292e812 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -42,7 +42,7 @@ Adding ACPI support for an existing driver should be pretty
 straightforward. Here is the simplest example:
 
 	#ifdef CONFIG_ACPI
-	static struct acpi_device_id mydrv_acpi_match[] = {
+	static const struct acpi_device_id mydrv_acpi_match[] = {
 		/* ACPI IDs here */
 		{ }
 	};
@@ -166,7 +166,7 @@ the platform device drivers. Below is an example where we add ACPI support
 to at25 SPI eeprom driver (this is meant for the above ACPI snippet):
 
 	#ifdef CONFIG_ACPI
-	static struct acpi_device_id at25_acpi_match[] = {
+	static const struct acpi_device_id at25_acpi_match[] = {
 		{ "AT25", 0 },
 		{ },
 	};
@@ -230,7 +230,7 @@ Below is an example of how to add ACPI support to the existing mpu3050
 input driver:
 
 	#ifdef CONFIG_ACPI
-	static struct acpi_device_id mpu3050_acpi_match[] = {
+	static const struct acpi_device_id mpu3050_acpi_match[] = {
 		{ "MPU3050", 0 },
 		{ },
 	};
@@ -253,7 +253,7 @@ input driver:
 GPIO support
 ~~~~~~~~~~~~
 ACPI 5 introduced two new resources to describe GPIO connections: GpioIo
-and GpioInt. These resources are used be used to pass GPIO numbers used by
+and GpioInt. These resources can be used to pass GPIO numbers used by
 the device to the driver. ACPI 5.1 extended this with _DSD (Device
 Specific Data) which made it possible to name the GPIOs among other things.
 
@@ -359,3 +359,54 @@ the id should be set like:
 The ACPI id "XYZ0001" is then used to lookup an ACPI device directly under
 the MFD device and if found, that ACPI companion device is bound to the
 resulting child platform device.
+
+Device Tree namespace link device ID
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The Device Tree protocol uses device indentification based on the "compatible"
+property whose value is a string or an array of strings recognized as device
+identifiers by drivers and the driver core.  The set of all those strings may be
+regarded as a device indentification namespace analogous to the ACPI/PNP device
+ID namespace.  Consequently, in principle it should not be necessary to allocate
+a new (and arguably redundant) ACPI/PNP device ID for a devices with an existing
+identification string in the Device Tree (DT) namespace, especially if that ID
+is only needed to indicate that a given device is compatible with another one,
+presumably having a matching driver in the kernel already.
+
+In ACPI, the device identification object called _CID (Compatible ID) is used to
+list the IDs of devices the given one is compatible with, but those IDs must
+belong to one of the namespaces prescribed by the ACPI specification (see
+Section 6.1.2 of ACPI 6.0 for details) and the DT namespace is not one of them.
+Moreover, the specification mandates that either a _HID or an _ADR identificaion
+object be present for all ACPI objects representing devices (Section 6.1 of ACPI
+6.0).  For non-enumerable bus types that object must be _HID and its value must
+be a device ID from one of the namespaces prescribed by the specification too.
+
+The special DT namespace link device ID, PRP0001, provides a means to use the
+existing DT-compatible device identification in ACPI and to satisfy the above
+requirements following from the ACPI specification at the same time.  Namely,
+if PRP0001 is returned by _HID, the ACPI subsystem will look for the
+"compatible" property in the device object's _DSD and will use the value of that
+property to identify the corresponding device in analogy with the original DT
+device identification algorithm.  If the "compatible" property is not present
+or its value is not valid, the device will not be enumerated by the ACPI
+subsystem.  Otherwise, it will be enumerated automatically as a platform device
+(except when an I2C or SPI link from the device to its parent is present, in
+which case the ACPI core will leave the device enumeration to the parent's
+driver) and the identification strings from the "compatible" property value will
+be used to find a driver for the device along with the device IDs listed by _CID
+(if present).
+
+Analogously, if PRP0001 is present in the list of device IDs returned by _CID,
+the identification strings listed by the "compatible" property value (if present
+and valid) will be used to look for a driver matching the device, but in that
+case their relative priority with respect to the other device IDs listed by
+_HID and _CID depends on the position of PRP0001 in the _CID return package.
+Specifically, the device IDs returned by _HID and preceding PRP0001 in the _CID
+return package will be checked first.  Also in that case the bus type the device
+will be enumerated to depends on the device ID returned by _HID.
+
+It is valid to define device objects with a _HID returning PRP0001 and without
+the "compatible" property in the _DSD or a _CID as long as one of their
+ancestors provides a _DSD with a valid "compatible" property.  Such device
+objects are then simply regarded as additional "blocks" providing hierarchical
+configuration information to the driver of the composite ancestor device.
diff --git a/Documentation/acpi/gpio-properties.txt b/Documentation/acpi/gpio-properties.txt
index ae36fcf86dc7..f35dad11f0de 100644
--- a/Documentation/acpi/gpio-properties.txt
+++ b/Documentation/acpi/gpio-properties.txt
@@ -1,9 +1,9 @@
 _DSD Device Properties Related to GPIO
 --------------------------------------
 
-With the release of ACPI 5.1 and the _DSD configuration objecte names
-can finally be given to GPIOs (and other things as well) returned by
-_CRS.  Previously, we were only able to use an integer index to find
+With the release of ACPI 5.1, the _DSD configuration object finally
+allows names to be given to GPIOs (and other things as well) returned
+by _CRS.  Previously, we were only able to use an integer index to find
 the corresponding GPIO, which is pretty error prone (it depends on
 the _CRS output ordering, for example).
 
diff --git a/Documentation/arm/Samsung/Bootloader-interface.txt b/Documentation/arm/Samsung/Bootloader-interface.txt
new file mode 100644
index 000000000000..b96ead9a6919
--- /dev/null
+++ b/Documentation/arm/Samsung/Bootloader-interface.txt
@@ -0,0 +1,53 @@
+      Interface between kernel and boot loaders on Exynos boards
+      ==========================================================
+
+Author: Krzysztof Kozlowski
+Date  : 6 June 2015
+
+The document tries to describe currently used interface between Linux kernel
+and boot loaders on Samsung Exynos based boards. This is not a definition
+of interface but rather a description of existing state, a reference
+for information purpose only.
+
+In the document "boot loader" means any of following: U-boot, proprietary
+SBOOT or any other firmware for ARMv7 and ARMv8 initializing the board before
+executing kernel.
+
+
+1. Non-Secure mode
+Address:      sysram_ns_base_addr
+Offset        Value                                        Purpose
+=============================================================================
+0x08          exynos_cpu_resume_ns                         System suspend
+0x0c          0x00000bad (Magic cookie)                    System suspend
+0x1c          exynos4_secondary_startup                    Secondary CPU boot
+0x1c + 4*cpu  exynos4_secondary_startup (Exynos4412)       Secondary CPU boot
+0x20          0xfcba0d10 (Magic cookie)                    AFTR
+0x24          exynos_cpu_resume_ns                         AFTR
+0x28 + 4*cpu  0x8 (Magic cookie, Exynos3250)               AFTR
+
+
+2. Secure mode
+Address:      sysram_base_addr
+Offset        Value                                        Purpose
+=============================================================================
+0x00          exynos4_secondary_startup                    Secondary CPU boot
+0x04          exynos4_secondary_startup (Exynos542x)       Secondary CPU boot
+4*cpu         exynos4_secondary_startup (Exynos4412)       Secondary CPU boot
+0x20          exynos_cpu_resume (Exynos4210 r1.0)          AFTR
+0x24          0xfcba0d10 (Magic cookie, Exynos4210 r1.0)   AFTR
+
+Address:      pmu_base_addr
+Offset        Value                                        Purpose
+=============================================================================
+0x0800        exynos_cpu_resume                            AFTR
+0x0814        exynos4_secondary_startup (Exynos4210 r1.1)  Secondary CPU boot
+0x0818        0xfcba0d10 (Magic cookie, Exynos4210 r1.1)   AFTR
+0x081C        exynos_cpu_resume (Exynos4210 r1.1)          AFTR
+
+
+3. Other (regardless of secure/non-secure mode)
+Address:      pmu_base_addr
+Offset        Value                           Purpose
+=============================================================================
+0x0908        Non-zero (only Exynos3250)      Secondary CPU boot up indicator
diff --git a/Documentation/arm/vlocks.txt b/Documentation/arm/vlocks.txt
index 415960a9bab0..45731672c564 100644
--- a/Documentation/arm/vlocks.txt
+++ b/Documentation/arm/vlocks.txt
@@ -206,6 +206,6 @@ References
 [1] Lamport, L. "A New Solution of Dijkstra's Concurrent Programming
     Problem", Communications of the ACM 17, 8 (August 1974), 453-455.
 
-    http://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm
+    https://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm
 
 [2] linux/arch/arm/common/vlock.S, www.kernel.org.
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index f3c05b5f9f08..1690350f16e7 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -45,11 +45,13 @@ sees fit.)
 
 Requirement: MANDATORY
 
-The device tree blob (dtb) must be placed on an 8-byte boundary within
-the first 512 megabytes from the start of the kernel image and must not
-cross a 2-megabyte boundary. This is to allow the kernel to map the
-blob using a single section mapping in the initial page tables.
+The device tree blob (dtb) must be placed on an 8-byte boundary and must
+not exceed 2 megabytes in size. Since the dtb will be mapped cacheable
+using blocks of up to 2 megabytes in size, it must not be placed within
+any 2M region which must be mapped with any specific attributes.
 
+NOTE: versions prior to v4.2 also require that the DTB be placed within
+the 512 MB region starting at text_offset bytes below the kernel Image.
 
 3. Decompress the kernel image
 ------------------------------
diff --git a/Documentation/blackfin/gptimers-example.c b/Documentation/blackfin/gptimers-example.c
index b1bd6340e748..283eba993d9d 100644
--- a/Documentation/blackfin/gptimers-example.c
+++ b/Documentation/blackfin/gptimers-example.c
@@ -17,6 +17,12 @@
 
 #define DRIVER_NAME "gptimer_example"
 
+#ifdef IRQ_TIMER5
+#define SAMPLE_IRQ_TIMER IRQ_TIMER5
+#else
+#define SAMPLE_IRQ_TIMER IRQ_TIMER2
+#endif
+
 struct gptimer_data {
 	uint32_t period, width;
 };
@@ -57,7 +63,8 @@ static int __init gptimer_example_init(void)
 	}
 
 	/* grab the IRQ for the timer */
-	ret = request_irq(IRQ_TIMER5, gptimer_example_irq, IRQF_SHARED, DRIVER_NAME, &data);
+	ret = request_irq(SAMPLE_IRQ_TIMER, gptimer_example_irq,
+			IRQF_SHARED, DRIVER_NAME, &data);
 	if (ret) {
 		printk(KERN_NOTICE DRIVER_NAME ": IRQ request failed\n");
 		peripheral_free(P_TMR5);
@@ -65,7 +72,8 @@ static int __init gptimer_example_init(void)
 	}
 
 	/* setup the timer and enable it */
-	set_gptimer_config(TIMER5_id, WDTH_CAP | PULSE_HI | PERIOD_CNT | IRQ_ENA);
+	set_gptimer_config(TIMER5_id,
+			WDTH_CAP | PULSE_HI | PERIOD_CNT | IRQ_ENA);
 	enable_gptimers(TIMER5bit);
 
 	return 0;
@@ -75,7 +83,7 @@ module_init(gptimer_example_init);
 static void __exit gptimer_example_exit(void)
 {
 	disable_gptimers(TIMER5bit);
-	free_irq(IRQ_TIMER5, &data);
+	free_irq(SAMPLE_IRQ_TIMER, &data);
 	peripheral_free(P_TMR5);
 }
 module_exit(gptimer_example_exit);
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index 77ec21574fb1..c15aa75f5227 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -36,7 +36,7 @@ Contents:
 1. What Is A CPUFreq Governor?
 ==============================
 
-Most cpufreq drivers (in fact, all except one, longrun) or even most
+Most cpufreq drivers (except the intel_pstate and longrun) or even most
 cpu frequency scaling algorithms only offer the CPU to be set to one
 frequency. In order to offer dynamic frequency scaling, the cpufreq
 core must be able to tell these drivers of a "target frequency". So
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index 655750743fb0..be8d4006bf76 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -3,24 +3,25 @@ Intel P-state driver
 
 This driver provides an interface to control the P state selection for
 SandyBridge+ Intel processors.  The driver can operate two different
-modes based on the processor model legacy and Hardware P state (HWP)
+modes based on the processor model, legacy mode and Hardware P state (HWP)
 mode.
 
-In legacy mode the driver implements a scaling driver with an internal
-governor for Intel Core processors.  The driver follows the same model
-as the Transmeta scaling driver (longrun.c) and implements the
-setpolicy() instead of target().  Scaling drivers that implement
-setpolicy() are assumed to implement internal governors by the cpufreq
-core. All the logic for selecting the current P state is contained
-within the driver; no external governor is used by the cpufreq core.
+In legacy mode, the Intel P-state implements two internal governors,
+performance and powersave, that differ from the general cpufreq governors of
+the same name (the general cpufreq governors implement target(), whereas the
+internal Intel P-state governors implement setpolicy()).  The internal
+performance governor sets the max_perf_pct and min_perf_pct to 100; that is,
+the governor selects the highest available P state to maximize the performance
+of the core.  The internal powersave governor selects the appropriate P state
+based on the current load on the CPU.
 
 In HWP mode P state selection is implemented in the processor
 itself. The driver provides the interfaces between the cpufreq core and
 the processor to control P state selection based on user preferences
 and reporting frequency to the cpufreq core.  In this mode the
-internal governor code is disabled.
+internal Intel P-state governor code is disabled.
 
-In addtion to the interfaces provided by the cpufreq core for
+In addition to the interfaces provided by the cpufreq core for
 controlling frequency the driver provides sysfs files for
 controlling P state selection. These files have been added to
 /sys/devices/system/cpu/intel_pstate/
diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index ff2f28332cc4..109e97bbab77 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -196,8 +196,6 @@ affected_cpus :			List of Online CPUs that require software
 related_cpus :			List of Online + Offline CPUs that need software
 				coordination of frequency.
 
-scaling_driver :		Hardware driver for cpufreq.
-
 scaling_cur_freq :		Current frequency of the CPU as determined by
 				the governor and cpufreq core, in KHz. This is
 				the frequency the kernel thinks the CPU runs
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 0aad6deb2d96..12b1b25b4da9 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -1,6 +1,6 @@
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo.
+to /proc/cpuinfo output of some architectures:
 
 1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
 
@@ -23,20 +23,35 @@ to /proc/cpuinfo.
 4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
-	core as cpuX
+	core as cpuX.
 
-5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	core as cpuX.
+
+6) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+7) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
+8) /sys/devices/system/cpu/cpuX/topology/book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
+9) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+drivers/base/topology.c, is to export the 6 or 9 attributes. The three book
 related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
@@ -44,20 +59,22 @@ these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
 #define topology_book_id(cpu)
-#define topology_thread_cpumask(cpu)
+#define topology_sibling_cpumask(cpu)
 #define topology_core_cpumask(cpu)
 #define topology_book_cpumask(cpu)
 
-The type of **_id is int.
-The type of siblings is (const) struct cpumask *.
+The type of **_id macros is int.
+The type of **_cpumask macros is (const) struct cpumask *. The latter
+correspond with appropriate **_siblings sysfs attributes (except for
+topology_sibling_cpumask() which corresponds with thread_siblings).
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 1) physical_package_id: -1
 2) core_id: 0
-3) thread_siblings: just the given CPU
-4) core_siblings: just the given CPU
+3) sibling_cpumask: just the given CPU
+4) core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index 5c9a567b3fac..03703afc4d30 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -181,4 +181,4 @@ Notes
 Documentation and specifications: http://halobates.de/firewire/
 
 FireWire is a trademark of Apple Inc. - for more information please refer to:
-http://en.wikipedia.org/wiki/FireWire
+https://en.wikipedia.org/wiki/FireWire
diff --git a/Documentation/devicetree/bindings/arm/altera/socfpga-sdram-edac.txt b/Documentation/devicetree/bindings/arm/altera/socfpga-sdram-edac.txt
index d0ce01da5c59..f5ad0ff69fae 100644
--- a/Documentation/devicetree/bindings/arm/altera/socfpga-sdram-edac.txt
+++ b/Documentation/devicetree/bindings/arm/altera/socfpga-sdram-edac.txt
@@ -2,7 +2,7 @@ Altera SOCFPGA SDRAM Error Detection & Correction [EDAC]
 The EDAC accesses a range of registers in the SDRAM controller.
 
 Required properties:
-- compatible : should contain "altr,sdram-edac";
+- compatible : should contain "altr,sdram-edac" or "altr,sdram-edac-a10"
 - altr,sdr-syscon : phandle of the sdr module
 - interrupts : Should contain the SDRAM ECC IRQ in the
 	appropriate format for the IRQ controller.
diff --git a/Documentation/devicetree/bindings/arm/armv7m_systick.txt b/Documentation/devicetree/bindings/arm/armv7m_systick.txt
new file mode 100644
index 000000000000..7cf4a24601eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/armv7m_systick.txt
@@ -0,0 +1,26 @@
+* ARMv7M System Timer
+
+ARMv7-M includes a system timer, known as SysTick. Current driver only
+implements the clocksource feature.
+
+Required properties:
+- compatible	  : Should be "arm,armv7m-systick"
+- reg		  : The address range of the timer
+
+Required clocking property, have to be one of:
+- clocks	  : The input clock of the timer
+- clock-frequency : The rate in HZ in input of the ARM SysTick
+
+Examples:
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clocks = <&clk_systick>;
+};
+
+systick: timer@e000e010 {
+	compatible = "arm,armv7m-systick";
+	reg = <0xe000e010 0x10>;
+	clock-frequency = <90000000>;
+};
diff --git a/Documentation/devicetree/bindings/arm/omap/l3-noc.txt b/Documentation/devicetree/bindings/arm/omap/l3-noc.txt
index 974624ea68f6..161448da959d 100644
--- a/Documentation/devicetree/bindings/arm/omap/l3-noc.txt
+++ b/Documentation/devicetree/bindings/arm/omap/l3-noc.txt
@@ -6,6 +6,7 @@ provided by Arteris.
 Required properties:
 - compatible : Should be "ti,omap3-l3-smx" for OMAP3 family
                Should be "ti,omap4-l3-noc" for OMAP4 family
+               Should be "ti,omap5-l3-noc" for OMAP5 family
 	       Should be "ti,dra7-l3-noc" for DRA7 family
                Should be "ti,am4372-l3-noc" for AM43 family
 - reg:	Contains L3 register address range for each noc domain.
diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index 7a4d4926f44e..5ba6450693b9 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -248,7 +248,7 @@ Required properties for peripheral clocks:
 - #address-cells : shall be 1 (reg is used to encode clk id).
 - clocks : shall be the master clock phandle.
 	e.g. clocks = <&mck>;
-- name: device tree node describing a specific system clock.
+- name: device tree node describing a specific peripheral clock.
 	* #clock-cells : from common clock binding; shall be set to 0.
 	* reg: peripheral id. See Atmel's datasheets to get a full
 	  list of peripheral ids.
diff --git a/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt b/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt
new file mode 100644
index 000000000000..36c2b528245c
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/renesas,h8300-div-clock.txt
@@ -0,0 +1,24 @@
+* Renesas H8/300 divider clock
+
+Required Properties:
+
+  - compatible: Must be "renesas,sh73a0-h8300-div-clock"
+
+  - clocks: Reference to the parent clocks ("extal1" and "extal2")
+
+  - #clock-cells: Must be 1
+
+  - reg: Base address and length of the divide rate selector
+
+  - renesas,width: bit width of selector
+
+Example
+-------
+
+		cclk: cclk {
+			compatible = "renesas,h8300-div-clock";
+			clocks = <&xclk>;
+			#clock-cells = <0>;
+			reg = <0xfee01b 2>;
+			renesas,width = <2>;
+		};
diff --git a/Documentation/devicetree/bindings/clock/renesas,h8s2678-pll-clock.txt b/Documentation/devicetree/bindings/clock/renesas,h8s2678-pll-clock.txt
new file mode 100644
index 000000000000..500cdadbceb7
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/renesas,h8s2678-pll-clock.txt
@@ -0,0 +1,23 @@
+Renesas H8S2678 PLL clock
+
+This device is Clock multiplyer
+
+Required Properties:
+
+  - compatible: Must be "renesas,h8s2678-pll-clock"
+
+  - clocks: Reference to the parent clocks
+
+  - #clock-cells: Must be 0
+
+  - reg: Two rate selector (Multiply / Divide) register address
+
+Example
+-------
+
+		pllclk: pllclk {
+			compatible = "renesas,h8s2678-pll-clock";
+			clocks = <&xclk>;
+			#clock-cells = <0>;
+			reg = <0xfee03b 2>, <0xfee045 2>;
+		};
diff --git a/Documentation/devicetree/bindings/clock/silabs,si5351.txt b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
index c40711e8e8f7..28b28309f535 100644
--- a/Documentation/devicetree/bindings/clock/silabs,si5351.txt
+++ b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
@@ -17,7 +17,8 @@ Required properties:
 - #clock-cells: from common clock binding; shall be set to 1.
 - clocks: from common clock binding; list of parent clock
   handles, shall be xtal reference clock or xtal and clkin for
-  si5351c only.
+  si5351c only. Corresponding clock input names are "xtal" and
+  "clkin" respectively.
 - #address-cells: shall be set to 1.
 - #size-cells: shall be set to 0.
 
@@ -71,6 +72,7 @@ i2c-master-node {
 
 		/* connect xtal input to 25MHz reference */
 		clocks = <&ref25>;
+		clock-names = "xtal";
 
 		/* connect xtal input as source of pll0 and pll1 */
 		silabs,pll-source = <0 0>, <1 0>;
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
index 38988ef1336b..f0d926bf9f36 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
@@ -1,9 +1,11 @@
-Freescale SoC SEC Security Engines versions 2.x-3.x
+Freescale SoC SEC Security Engines versions 1.x-2.x-3.x
 
 Required properties:
 
 - compatible : Should contain entries for this and backward compatible
-  SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0"
+  SEC versions, high to low, e.g., "fsl,sec2.1", "fsl,sec2.0" (SEC2/3)
+                             e.g., "fsl,sec1.2", "fsl,sec1.0" (SEC1)
+    warning: SEC1 and SEC2 are mutually exclusive
 - reg : Offset and length of the register set for the device
 - interrupts : the SEC's interrupt number
 - fsl,num-channels : An integer representing the number of channels
diff --git a/Documentation/devicetree/bindings/crypto/marvell-cesa.txt b/Documentation/devicetree/bindings/crypto/marvell-cesa.txt
new file mode 100644
index 000000000000..c6c6a4a045bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/marvell-cesa.txt
@@ -0,0 +1,45 @@
+Marvell Cryptographic Engines And Security Accelerator
+
+Required properties:
+- compatible: should be one of the following string
+	      "marvell,orion-crypto"
+	      "marvell,kirkwood-crypto"
+	      "marvell,dove-crypto"
+	      "marvell,armada-370-crypto"
+	      "marvell,armada-xp-crypto"
+	      "marvell,armada-375-crypto"
+	      "marvell,armada-38x-crypto"
+- reg: base physical address of the engine and length of memory mapped
+       region. Can also contain an entry for the SRAM attached to the CESA,
+       but this representation is deprecated and marvell,crypto-srams should
+       be used instead
+- reg-names: "regs". Can contain an "sram" entry, but this representation
+	     is deprecated and marvell,crypto-srams should be used instead
+- interrupts: interrupt number
+- clocks: reference to the crypto engines clocks. This property is not
+	  required for orion and kirkwood platforms
+- clock-names: "cesaX" and "cesazX", X should be replaced by the crypto engine
+	       id.
+	       This property is not required for the orion and kirkwoord
+	       platforms.
+	       "cesazX" clocks are not required on armada-370 platforms
+- marvell,crypto-srams: phandle to crypto SRAM definitions
+
+Optional properties:
+- marvell,crypto-sram-size: SRAM size reserved for crypto operations, if not
+			    specified the whole SRAM is used (2KB)
+
+
+Examples:
+
+	crypto@90000 {
+		compatible = "marvell,armada-xp-crypto";
+		reg = <0x90000 0x10000>;
+		reg-names = "regs";
+		interrupts = <48>, <49>;
+		clocks = <&gateclk 23>, <&gateclk 23>;
+		clock-names = "cesa0", "cesa1";
+		marvell,crypto-srams = <&crypto_sram0>, <&crypto_sram1>;
+		marvell,crypto-sram-size = <0x600>;
+		status = "okay";
+	};
diff --git a/Documentation/devicetree/bindings/crypto/mv_cesa.txt b/Documentation/devicetree/bindings/crypto/mv_cesa.txt
index 47229b1a594b..c0c35f00335b 100644
--- a/Documentation/devicetree/bindings/crypto/mv_cesa.txt
+++ b/Documentation/devicetree/bindings/crypto/mv_cesa.txt
@@ -1,20 +1,33 @@
 Marvell Cryptographic Engines And Security Accelerator
 
 Required properties:
-- compatible : should be "marvell,orion-crypto"
-- reg : base physical address of the engine and length of memory mapped
-        region, followed by base physical address of sram and its memory
-        length
-- reg-names : "regs" , "sram";
-- interrupts : interrupt number
+- compatible: should be one of the following string
+	      "marvell,orion-crypto"
+	      "marvell,kirkwood-crypto"
+	      "marvell,dove-crypto"
+- reg: base physical address of the engine and length of memory mapped
+       region. Can also contain an entry for the SRAM attached to the CESA,
+       but this representation is deprecated and marvell,crypto-srams should
+       be used instead
+- reg-names: "regs". Can contain an "sram" entry, but this representation
+	     is deprecated and marvell,crypto-srams should be used instead
+- interrupts: interrupt number
+- clocks: reference to the crypto engines clocks. This property is only
+	  required for Dove platforms
+- marvell,crypto-srams: phandle to crypto SRAM definitions
+
+Optional properties:
+- marvell,crypto-sram-size: SRAM size reserved for crypto operations, if not
+			    specified the whole SRAM is used (2KB)
 
 Examples:
 
 	crypto@30000 {
 		compatible = "marvell,orion-crypto";
-		reg = <0x30000 0x10000>,
-		      <0x4000000 0x800>;
-		reg-names = "regs" , "sram";
+		reg = <0x30000 0x10000>;
+		reg-names = "regs";
 		interrupts = <22>;
+		marvell,crypto-srams = <&crypto_sram>;
+		marvell,crypto-sram-size = <0x600>;
 		status = "okay";
 	};
diff --git a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
index a4873e5e3e36..e30e184f50c7 100644
--- a/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
+++ b/Documentation/devicetree/bindings/dma/fsl-mxs-dma.txt
@@ -38,7 +38,7 @@ dma_apbx: dma-apbx@80024000 {
 		      80 81 68 69
 		      70 71 72 73
 		      74 75 76 77>;
-	interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+	interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
 			  "saif0", "saif1", "i2c0", "i2c1",
 			  "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
 			  "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
diff --git a/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt b/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
new file mode 100644
index 000000000000..78edb80002c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
@@ -0,0 +1,79 @@
+* APM X-Gene SoC EDAC node
+
+EDAC node is defined to describe on-chip error detection and correction.
+The follow error types are supported:
+
+  memory controller	- Memory controller
+  PMD (L1/L2)		- Processor module unit (PMD) L1/L2 cache
+
+The following section describes the EDAC DT node binding.
+
+Required properties:
+- compatible		: Shall be "apm,xgene-edac".
+- regmap-csw		: Regmap of the CPU switch fabric (CSW) resource.
+- regmap-mcba		: Regmap of the MCB-A (memory bridge) resource.
+- regmap-mcbb		: Regmap of the MCB-B (memory bridge) resource.
+- regmap-efuse		: Regmap of the PMD efuse resource.
+- reg			: First resource shall be the CPU bus (PCP) resource.
+- interrupts            : Interrupt-specifier for MCU, PMD, L3, or SoC error
+			  IRQ(s).
+
+Required properties for memory controller subnode:
+- compatible		: Shall be "apm,xgene-edac-mc".
+- reg			: First resource shall be the memory controller unit
+                          (MCU) resource.
+- memory-controller	: Instance number of the memory controller.
+
+Required properties for PMD subnode:
+- compatible		: Shall be "apm,xgene-edac-pmd" or
+                          "apm,xgene-edac-pmd-v2".
+- reg			: First resource shall be the PMD resource.
+- pmd-controller	: Instance number of the PMD controller.
+
+Example:
+	csw: csw@7e200000 {
+		compatible = "apm,xgene-csw", "syscon";
+		reg = <0x0 0x7e200000 0x0 0x1000>;
+	};
+
+	mcba: mcba@7e700000 {
+		compatible = "apm,xgene-mcb", "syscon";
+		reg = <0x0 0x7e700000 0x0 0x1000>;
+	};
+
+	mcbb: mcbb@7e720000 {
+		compatible = "apm,xgene-mcb", "syscon";
+		reg = <0x0 0x7e720000 0x0 0x1000>;
+	};
+
+	efuse: efuse@1054a000 {
+		compatible = "apm,xgene-efuse", "syscon";
+		reg = <0x0 0x1054a000 0x0 0x20>;
+	};
+
+	edac@78800000 {
+		compatible = "apm,xgene-edac";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		regmap-csw = <&csw>;
+		regmap-mcba = <&mcba>;
+		regmap-mcbb = <&mcbb>;
+		regmap-efuse = <&efuse>;
+		reg = <0x0 0x78800000 0x0 0x100>;
+		interrupts = <0x0 0x20 0x4>,
+			     <0x0 0x21 0x4>,
+			     <0x0 0x27 0x4>;
+
+		edacmc@7e800000 {
+			compatible = "apm,xgene-edac-mc";
+			reg = <0x0 0x7e800000 0x0 0x1000>;
+			memory-controller = <0>;
+		};
+
+		edacpmd@7c000000 {
+			compatible = "apm,xgene-edac-pmd";
+			reg = <0x0 0x7c000000 0x0 0x200000>;
+			pmd-controller = <0>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
new file mode 100644
index 000000000000..435f1bcca341
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
@@ -0,0 +1,65 @@
+Broadcom STB "UPG GIO" GPIO controller
+
+The controller's registers are organized as sets of eight 32-bit
+registers with each set controlling a bank of up to 32 pins.  A single
+interrupt is shared for all of the banks handled by the controller.
+
+Required properties:
+
+- compatible:
+    Must be "brcm,brcmstb-gpio"
+
+- reg:
+    Define the base and range of the I/O address space containing
+    the brcmstb GPIO controller registers
+
+- #gpio-cells:
+    Should be <2>.  The first cell is the pin number (within the controller's
+    pin space), and the second is used for the following:
+    bit[0]: polarity (0 for active-high, 1 for active-low)
+
+- gpio-controller:
+    Specifies that the node is a GPIO controller.
+
+- brcm,gpio-bank-widths:
+    Number of GPIO lines for each bank.  Number of elements must
+    correspond to number of banks suggested by the 'reg' property.
+
+Optional properties:
+
+- interrupts:
+    The interrupt shared by all GPIO lines for this controller.
+
+- interrupt-parent:
+    phandle of the parent interrupt controller
+
+- #interrupt-cells:
+    Should be <2>.  The first cell is the GPIO number, the second should specify
+    flags.  The following subset of flags is supported:
+    - bits[3:0] trigger type and level flags
+        1 = low-to-high edge triggered
+        2 = high-to-low edge triggered
+        4 = active high level-sensitive
+        8 = active low level-sensitive
+      Valid combinations are 1, 2, 3, 4, 8.
+    See also Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+
+- interrupt-controller:
+    Marks the device node as an interrupt controller
+
+- interrupt-names:
+    The name of the IRQ resource used by this controller
+
+Example:
+	upg_gio: gpio@f040a700 {
+		#gpio-cells = <0x2>;
+		#interrupt-cells = <0x2>;
+		compatible = "brcm,bcm7445-gpio", "brcm,brcmstb-gpio";
+		gpio-controller;
+		interrupt-controller;
+		reg = <0xf040a700 0x80>;
+		interrupt-parent = <0xf>;
+		interrupts = <0x6>;
+		interrupt-names = "upg_gio";
+		brcm,gpio-bank-widths = <0x20 0x20 0x20 0x18>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-atlas7.txt b/Documentation/devicetree/bindings/gpio/gpio-atlas7.txt
new file mode 100644
index 000000000000..d7e123fc90b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-atlas7.txt
@@ -0,0 +1,50 @@
+CSR SiRFatlas7 GPIO controller bindings
+
+Required properties:
+- compatible	: "sirf,atlas7-gpio"
+- reg		: Address range of the pinctrl registers
+- interrupts	: Interrupts used by every GPIO group
+- gpio-banks	: How many gpio banks on this controller
+- gpio-controller : Indicates this device is a GPIO controller
+- interrupt-controller  : Marks the device node as an interrupt controller
+
+The GPIO controller also acts as an interrupt controller. It uses the default
+two cells specifier as described in Documentation/devicetree/bindings/
+interrupt-controller/interrupts.txt.
+
+Example:
+
+	gpio_0: gpio_mediam@17040000 {
+		compatible = "sirf,atlas7-gpio";
+		reg = <0x17040000 0x1000>;
+		interrupts = <0 13 0>, <0 14 0>;
+
+		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
+
+		gpio-controller;
+		interrupt-controller;
+
+		gpio-banks = <2>;
+		gpio-ranges = <&pinctrl 0 0 0>,
+				<&pinctrl 32 0 0>;
+		gpio-ranges-group-names = "lvds_gpio_grp",
+					"uart_nand_gpio_grp";
+	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		led1 {
+			gpios = <&gpio_1 15 0>;
+			...
+		};
+
+		led2 {
+			gpios = <&gpio_2 34 0>;
+			...
+		};
+	};
+
+Please refer to gpio.txt in this directory for details of the common
+gpio properties used by devices.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
new file mode 100644
index 000000000000..abf4db736c6e
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-etraxfs.txt
@@ -0,0 +1,21 @@
+Axis ETRAX FS General I/O controller bindings
+
+Required properties:
+
+- compatible:
+  - "axis,etraxfs-gio"
+- reg: Physical base address and length of the controller's registers.
+- #gpio-cells: Should be 3
+  - The first cell is the gpio offset number.
+  - The second cell is reserved and is currently unused.
+  - The third cell is the port number (hex).
+- gpio-controller: Marks the device node as a GPIO controller.
+
+Example:
+
+	gio: gpio@b001a000 {
+		compatible = "axis,etraxfs-gio";
+		reg = <0xb001a000 0x1000>;
+		gpio-controller;
+		#gpio-cells = <3>;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
new file mode 100644
index 000000000000..262ee4ddf2cb
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
@@ -0,0 +1,47 @@
+Netlogic XLP Family GPIO
+========================
+
+This GPIO driver is used for following Netlogic XLP SoCs:
+	XLP832, XLP316, XLP208, XLP980, XLP532
+
+Required properties:
+-------------------
+
+- compatible: Should be one of the following:
+  - "netlogic,xlp832-gpio": For Netlogic XLP832
+  - "netlogic,xlp316-gpio": For Netlogic XLP316
+  - "netlogic,xlp208-gpio": For Netlogic XLP208
+  - "netlogic,xlp980-gpio": For Netlogic XLP980
+  - "netlogic,xlp532-gpio": For Netlogic XLP532
+- reg: Physical base address and length of the controller's registers.
+- #gpio-cells: Should be two. The first cell is the pin number and the second
+  cell is used to specify optional parameters (currently unused).
+- gpio-controller: Marks the device node as a GPIO controller.
+- nr-gpios: Number of GPIO pins supported by the controller.
+- interrupt-cells: Should be two. The first cell is the GPIO Number. The
+  second cell is used to specify flags. The following subset of flags is
+  supported:
+  - trigger type:
+	1 = low to high edge triggered.
+	2 = high to low edge triggered.
+	4 = active high level-sensitive.
+	8 = active low level-sensitive.
+- interrupts: Interrupt number for this device.
+- interrupt-parent: phandle of the parent interrupt controller.
+- interrupt-controller: Identifies the node as an interrupt controller.
+
+Example:
+
+	gpio: xlp_gpio@34000 {
+		compatible = "netlogic,xlp316-gpio";
+		reg = <0 0x34100 0x1000
+		       0 0x35100 0x1000>;
+		#gpio-cells = <2>;
+		gpio-controller;
+		nr-gpios = <57>;
+
+		#interrupt-cells = <2>;
+		interrupt-parent = <&pic>;
+		interrupts = <39>;
+		interrupt-controller;
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
index 986371a4be2c..db4c6a663c03 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
@@ -6,7 +6,7 @@ Required properties:
 			  - First cell is the GPIO line number
 			  - Second cell is used to specify optional
 			    parameters (unused)
-- compatible		: Should be "xlnx,zynq-gpio-1.0"
+- compatible		: Should be "xlnx,zynq-gpio-1.0" or "xlnx,zynqmp-gpio-1.0"
 - clocks		: Clock specifier (see clock bindings for details)
 - gpio-controller	: Marks the device node as a GPIO controller.
 - interrupts		: Interrupt specifier (see interrupt bindings for
diff --git a/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt b/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt
new file mode 100644
index 000000000000..eb7cdd69e10b
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/nxp,lpc1850-gpio.txt
@@ -0,0 +1,39 @@
+NXP LPC18xx/43xx GPIO controller Device Tree Bindings
+-----------------------------------------------------
+
+Required properties:
+- compatible		: Should be "nxp,lpc1850-gpio"
+- reg			: Address and length of the register set for the device
+- clocks		: Clock specifier (see clock bindings for details)
+- gpio-controller	: Marks the device node as a GPIO controller.
+- #gpio-cells 		: Should be two
+			  - First cell is the GPIO line number
+			  - Second cell is used to specify polarity
+
+Optional properties:
+- gpio-ranges		: Mapping between GPIO and pinctrl
+
+Example:
+#define LPC_GPIO(port, pin)	(port * 32 + pin)
+#define LPC_PIN(port, pin)	(0x##port * 32 + pin)
+
+gpio: gpio@400f4000 {
+	compatible = "nxp,lpc1850-gpio";
+	reg = <0x400f4000 0x4000>;
+	clocks = <&ccu1 CLK_CPU_GPIO>;
+	gpio-controller;
+	#gpio-cells = <2>;
+	gpio-ranges =	<&pinctrl LPC_GPIO(0,0)  LPC_PIN(0,0)  2>,
+			...
+			<&pinctrl LPC_GPIO(7,19) LPC_PIN(f,5)  7>;
+};
+
+gpio_joystick {
+	compatible = "gpio-keys-polled";
+	...
+
+	button@0 {
+		...
+		gpios = <&gpio LPC_GPIO(4,8) GPIO_ACTIVE_LOW>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/h8300/cpu.txt b/Documentation/devicetree/bindings/h8300/cpu.txt
new file mode 100644
index 000000000000..70cd58608f4b
--- /dev/null
+++ b/Documentation/devicetree/bindings/h8300/cpu.txt
@@ -0,0 +1,13 @@
+* H8/300 CPU bindings
+
+Required properties:
+
+- compatible: Compatible property value should be "renesas,h8300".
+- clock-frequency: Contains the clock frequency for CPU, in Hz.
+
+Example:
+
+		cpu@0 {
+			compatible = "renesas,h8300";
+			clock-frequency = <20000000>;
+		};
diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index fcca8e744f41..a04a80f9cc70 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -9,6 +9,7 @@ Requires node properties:
 	"murata,ncp21wb473"
 	"murata,ncp03wb473"
 	"murata,ncp15wl333"
+	"murata,ncp03wf104"
 
 /* Usage of vendor name "ntc" is deprecated */
 <DEPRECATED>	"ntc,ncp15wb473"
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index ad0c4ac916dd..00f8652e193a 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -19,8 +19,7 @@ adi,adt7475		+/-1C TDM Extended Temp Range I.C
 adi,adt7476		+/-1C TDM Extended Temp Range I.C
 adi,adt7490		+/-1C TDM Extended Temp Range I.C
 adi,adxl345		Three-Axis Digital Accelerometer
-adi,adxl346		Three-Axis Digital Accelerometer
-adi,adxl34x		Three-Axis Digital Accelerometer
+adi,adxl346		Three-Axis Digital Accelerometer (backward-compatibility value "adi,adxl345" must be listed too)
 at,24c08		i2c serial eeprom  (24cxx)
 atmel,24c00		i2c serial eeprom  (24cxx)
 atmel,24c01		i2c serial eeprom  (24cxx)
diff --git a/Documentation/devicetree/bindings/input/ti,drv2665.txt b/Documentation/devicetree/bindings/input/ti,drv2665.txt
new file mode 100644
index 000000000000..1ba97ac04305
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/ti,drv2665.txt
@@ -0,0 +1,17 @@
+* Texas Instruments - drv2665 Haptics driver
+
+Required properties:
+	- compatible - "ti,drv2665" - DRV2665
+	- reg -  I2C slave address
+	- vbat-supply - Required supply regulator
+
+Example:
+
+haptics: haptics@59 {
+	compatible = "ti,drv2665";
+	reg = <0x59>;
+	vbat-supply = <&vbat>;
+};
+
+For more product information please see the link below:
+http://www.ti.com/product/drv2665
diff --git a/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt b/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
index 4b641c7bf1c2..09089a6d69ed 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
@@ -32,8 +32,8 @@ Example:
 		touchscreen-fuzz-x = <4>;
 		touchscreen-fuzz-y = <7>;
 		touchscreen-fuzz-pressure = <2>;
-		touchscreen-max-x = <4096>;
-		touchscreen-max-y = <4096>;
+		touchscreen-size-x = <4096>;
+		touchscreen-size-y = <4096>;
 		touchscreen-max-pressure = <2048>;
 
 		ti,x-plate-ohms = <280>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index f292917fa00d..0e9f09a6a2fe 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -2,7 +2,7 @@
 
 Required properties:
 - compatible: Should be "atmel,<chip>-aic"
-  <chip> can be "at91rm9200", "sama5d3" or "sama5d4"
+  <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
 - interrupt-controller: Identifies the node as an interrupt controller.
 - interrupt-parent: For single AIC system, it is an empty property.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,h8300h-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,h8300h-intc.txt
new file mode 100644
index 000000000000..56e8d82aff34
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,h8300h-intc.txt
@@ -0,0 +1,22 @@
+* H8/300H Interrupt controller
+
+Required properties:
+
+- compatible: has to be "renesas,h8300h-intc", "renesas,h8300-intc" as fallback.
+- #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
+  interrupts.txt in this directory
+- regs: Base address of interrupt controller registers.
+
+Optional properties:
+
+- any properties, listed in interrupts.txt, and any standard resource allocation
+  properties
+
+Example:
+
+	h8intc: interrupt-controller@fee012 {
+		compatible = "renesas,h8300h-intc", "renesas,h8300-intc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xfee012 7>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,h8s-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,h8s-intc.txt
new file mode 100644
index 000000000000..faded2b1559b
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,h8s-intc.txt
@@ -0,0 +1,22 @@
+* H8S Interrupt controller
+
+Required properties:
+
+- compatible: has to be "renesas,h8s-intc", "renesas,h8300-intc" as fallback.
+- #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
+  interrupts.txt in this directory
+- regs: Base address of interrupt controller registers.
+
+Optional properties:
+
+- any properties, listed in interrupts.txt, and any standard resource allocation
+  properties
+
+Example:
+
+	h8intc: interrupt-controller@fffe00 {
+		compatible = "renesas,h8s-intc", "renesas,h8300-intc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xfffe00 24>;
+	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
index 4f7946ae8adc..772c550d3b4b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,intc-irqpin.txt
@@ -13,9 +13,12 @@ Required properties:
 - reg: Base address and length of each register bank used by the external
   IRQ pins driven by the interrupt controller hardware module. The base
   addresses, length and number of required register banks varies with soctype.
-
+- interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
-  interrupts.txt in this directory
+  interrupts.txt in this directory.
+- interrupts: Must contain a list of interrupt specifiers. For each interrupt
+  provided by this irqpin controller instance, there must be one entry,
+  referring to the corresponding parent interrupt.
 
 Optional properties:
 
@@ -25,3 +28,35 @@ Optional properties:
   if different from the default 4 bits
 - control-parent: disable and enable interrupts on the parent interrupt
   controller, needed for some broken implementations
+- clocks: Must contain a reference to the functional clock.  This property is
+  mandatory if the hardware implements a controllable functional clock for
+  the irqpin controller instance.
+- power-domains: Must contain a reference to the power domain. This property is
+  mandatory if the irqpin controller instance is part of a controllable power
+  domain.
+
+
+Example
+-------
+
+	irqpin1: interrupt-controller@e6900004 {
+		compatible = "renesas,intc-irqpin-r8a7740",
+			     "renesas,intc-irqpin";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xe6900004 4>,
+			<0xe6900014 4>,
+			<0xe6900024 1>,
+			<0xe6900044 1>,
+			<0xe6900064 1>;
+		interrupts = <0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH
+			      0 149 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp2_clks R8A7740_CLK_INTCA>;
+		power-domains = <&pd_a4s>;
+	};
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
new file mode 100644
index 000000000000..c03eec116872
--- /dev/null
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
@@ -0,0 +1,37 @@
+* ARM SMMUv3 Architecture Implementation
+
+The SMMUv3 architecture is a significant deparature from previous
+revisions, replacing the MMIO register interface with in-memory command
+and event queues and adding support for the ATS and PRI components of
+the PCIe specification.
+
+** SMMUv3 required properties:
+
+- compatible        : Should include:
+
+                      * "arm,smmu-v3" for any SMMUv3 compliant
+                        implementation. This entry should be last in the
+                        compatible list.
+
+- reg               : Base address and size of the SMMU.
+
+- interrupts        : Non-secure interrupt list describing the wired
+                      interrupt sources corresponding to entries in
+                      interrupt-names. If no wired interrupts are
+                      present then this property may be omitted.
+
+- interrupt-names   : When the interrupts property is present, should
+                      include the following:
+                      * "eventq"    - Event Queue not empty
+                      * "priq"      - PRI Queue not empty
+                      * "cmdq-sync" - CMD_SYNC complete
+                      * "gerror"    - Global Error activated
+
+** SMMUv3 optional properties:
+
+- dma-coherent      : Present if DMA operations made by the SMMU (page
+                      table walks, stream table accesses etc) are cache
+                      coherent with the CPU.
+
+                      NOTE: this only applies to the SMMU itself, not
+                      masters connected upstream of the SMMU.
diff --git a/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.txt b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.txt
new file mode 100644
index 000000000000..cdf406c902e2
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/renesas,h8300-bsc.txt
@@ -0,0 +1,12 @@
+* H8/300 bus controller
+
+Required properties:
+  - compatible: Must be "renesas,h8300-bsc".
+  - reg: Base address and length of BSC registers.
+
+Example.
+	bsc: memory-controller@fee01e {
+		compatible = "renesas,h8300h-bsc", "renesas,h8300-bsc";
+		reg = <0xfee01e 8>;
+	};
+
diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt
index 7665aa95979f..64fa3b2de6cd 100644
--- a/Documentation/devicetree/bindings/mfd/arizona.txt
+++ b/Documentation/devicetree/bindings/mfd/arizona.txt
@@ -10,6 +10,9 @@ Required properties:
         "wlf,wm5110"
         "wlf,wm8280"
         "wlf,wm8997"
+        "wlf,wm8998"
+        "wlf,wm1814"
+
   - reg : I2C slave address when connected using I2C, chip select number when
     using SPI.
 
@@ -31,10 +34,10 @@ Required properties:
     as covered in Documentation/devicetree/bindings/regulator/regulator.txt
 
   - DBVDD2-supply, DBVDD3-supply : Additional databus power supplies (wm5102,
-    wm5110, wm8280)
+    wm5110, wm8280, wm8998, wm1814)
 
   - SPKVDDL-supply, SPKVDDR-supply : Speaker driver power supplies (wm5102,
-    wm5110, wm8280)
+    wm5110, wm8280, wm8998, wm1814)
 
   - SPKVDD-supply : Speaker driver power supply (wm8997)
 
@@ -53,8 +56,10 @@ Optional properties:
     of input signals. Valid values are 0 (Differential), 1 (Single-ended) and
     2 (Digital Microphone). If absent, INn_MODE registers set to 0 by default.
     If present, values must be specified less than or equal to the number of
-    input singals. If values less than the number of input signals, elements
-    that has not been specifed are set to 0 by default.
+    input signals. If values less than the number of input signals, elements
+    that have not been specified are set to 0 by default. Entries are:
+    <IN1, IN2, IN3, IN4> (wm5102, wm5110, wm8280, wm8997)
+    <IN1A, IN2A, IN1B, IN2B> (wm8998, wm1814)
 
   - wlf,dmic-ref : DMIC reference voltage source for each input, can be
     selected from either MICVDD or one of the MICBIAS's, defines
diff --git a/Documentation/devicetree/bindings/mfd/axp20x.txt b/Documentation/devicetree/bindings/mfd/axp20x.txt
index 98685f291a72..753f14f46e85 100644
--- a/Documentation/devicetree/bindings/mfd/axp20x.txt
+++ b/Documentation/devicetree/bindings/mfd/axp20x.txt
@@ -1,15 +1,16 @@
-AXP202/AXP209 device tree bindings
+AXP family PMIC device tree bindings
 
 The axp20x family current members :
 axp202 (X-Powers)
 axp209 (X-Powers)
+axp221 (X-Powers)
 
 Required properties:
-- compatible: "x-powers,axp202" or "x-powers,axp209"
+- compatible: "x-powers,axp202", "x-powers,axp209", "x-powers,axp221"
 - reg: The I2C slave address for the AXP chip
 - interrupt-parent: The parent interrupt controller
 - interrupts: SoC NMI / GPIO interrupt connected to the PMIC's IRQ pin
-- interrupt-controller: axp20x has its own internal IRQs
+- interrupt-controller: The PMIC has its own internal IRQs
 - #interrupt-cells: Should be set to 1
 
 Optional properties:
@@ -48,6 +49,31 @@ LDO3		: LDO		: ldo3in-supply
 LDO4		: LDO		: ldo24in-supply	: shared supply
 LDO5		: LDO		: ldo5in-supply
 
+AXP221 regulators, type, and corresponding input supply names:
+
+Regulator	  Type		  Supply Name		  Notes
+---------	  ----		  -----------		  -----
+DCDC1		: DC-DC buck	: vin1-supply
+DCDC2		: DC-DC buck	: vin2-supply
+DCDC3		: DC-DC	buck	: vin3-supply
+DCDC4		: DC-DC	buck	: vin4-supply
+DCDC5		: DC-DC	buck	: vin5-supply
+DC1SW		: On/Off Switch	: dcdc1-supply		: DCDC1 secondary output
+DC5LDO		: LDO		: dcdc5-supply		: input from DCDC5
+ALDO1		: LDO		: aldoin-supply		: shared supply
+ALDO2		: LDO		: aldoin-supply		: shared supply
+ALDO3		: LDO		: aldoin-supply		: shared supply
+DLDO1		: LDO		: dldoin-supply		: shared supply
+DLDO2		: LDO		: dldoin-supply		: shared supply
+DLDO3		: LDO		: dldoin-supply		: shared supply
+DLDO4		: LDO		: dldoin-supply		: shared supply
+ELDO1		: LDO		: eldoin-supply		: shared supply
+ELDO2		: LDO		: eldoin-supply		: shared supply
+ELDO3		: LDO		: eldoin-supply		: shared supply
+LDO_IO0		: LDO		: ips-supply		: GPIO 0
+LDO_IO1		: LDO		: ips-supply		: GPIO 1
+RTC_LDO		: LDO		: ips-supply		: always on
+
 Example:
 
 axp209: pmic@34 {
diff --git a/Documentation/devicetree/bindings/mfd/cros-ec.txt b/Documentation/devicetree/bindings/mfd/cros-ec.txt
index 8009c3d87f33..1777916e9e28 100644
--- a/Documentation/devicetree/bindings/mfd/cros-ec.txt
+++ b/Documentation/devicetree/bindings/mfd/cros-ec.txt
@@ -18,6 +18,10 @@ Required properties (SPI):
 - reg: SPI chip select
 
 Optional properties (SPI):
+- google,cros-ec-spi-pre-delay: Some implementations of the EC need a little
+  time to wake up from sleep before they can receive SPI transfers at a high
+  clock rate. This property specifies the delay, in usecs, between the
+  assertion of the CS to the start of the first clock pulse.
 - google,cros-ec-spi-msg-delay: Some implementations of the EC require some
   additional processing time in order to accept new transactions. If the delay
   between transactions is not long enough the EC may not be able to respond
diff --git a/Documentation/devicetree/bindings/mfd/da9063.txt b/Documentation/devicetree/bindings/mfd/da9063.txt
index 42c6fa6f1c9a..05b21bcb8543 100644
--- a/Documentation/devicetree/bindings/mfd/da9063.txt
+++ b/Documentation/devicetree/bindings/mfd/da9063.txt
@@ -5,6 +5,7 @@ DA9093 consists of a large and varied group of sub-devices (I2C Only):
 Device                   Supply Names    Description
 ------                   ------------    -----------
 da9063-regulator        :               : LDOs & BUCKs
+da9063-onkey            :               : On Key
 da9063-rtc              :               : Real-Time Clock
 da9063-watchdog         :               : Watchdog
 
@@ -51,6 +52,18 @@ Sub-nodes:
   the DA9063. There are currently no entries in this binding, however
   compatible = "dlg,da9063-rtc" should be added if a node is created.
 
+- onkey : This node defines the OnKey settings for controlling the key
+  functionality of the device. The node should contain the compatible property
+  with the value "dlg,da9063-onkey".
+
+  Optional onkey properties:
+
+  - dlg,disable-key-power : Disable power-down using a long key-press. If this
+    entry exists the OnKey driver will remove support for the KEY_POWER key
+    press. If this entry does not exist then by default the key-press
+    triggered power down is enabled and the OnKey will support both KEY_POWER
+    and KEY_SLEEP.
+
 - watchdog : This node defines settings for the Watchdog timer associated
   with the DA9063. There are currently no entries in this binding, however
   compatible = "dlg,da9063-watchdog" should be added if a node is created.
@@ -73,6 +86,11 @@ Example:
 			compatible = "dlg,da9063-watchdog";
 		};
 
+		onkey {
+			compatible = "dlg,da9063-onkey";
+			dlg,disable-key-power;
+		};
+
 		regulators {
 			DA9063_BCORE1: bcore1 {
 				regulator-name = "BCORE1";
diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt
index e39f0bc1f55e..163bd81a4607 100644
--- a/Documentation/devicetree/bindings/mfd/max77686.txt
+++ b/Documentation/devicetree/bindings/mfd/max77686.txt
@@ -1,6 +1,6 @@
 Maxim MAX77686 multi-function device
 
-MAX77686 is a Mulitifunction device with PMIC, RTC and Charger on chip. It is
+MAX77686 is a Multifunction device with PMIC, RTC and Charger on chip. It is
 interfaced to host controller using i2c interface. PMIC and Charger submodules
 are addressed using same i2c slave address whereas RTC submodule uses
 different i2c slave address,presently for which we are statically creating i2c
diff --git a/Documentation/devicetree/bindings/mfd/max77693.txt b/Documentation/devicetree/bindings/mfd/max77693.txt
index 38e64405e98d..d3425846aa5b 100644
--- a/Documentation/devicetree/bindings/mfd/max77693.txt
+++ b/Documentation/devicetree/bindings/mfd/max77693.txt
@@ -76,7 +76,60 @@ Optional properties:
     Valid values: 4300000, 4700000, 4800000, 4900000
     Default: 4300000
 
+- led : the LED submodule device node
+
+There are two LED outputs available - FLED1 and FLED2. Each of them can
+control a separate LED or they can be connected together to double
+the maximum current for a single connected LED. One LED is represented
+by one child node.
+
+Required properties:
+- compatible : Must be "maxim,max77693-led".
+
+Optional properties:
+- maxim,boost-mode :
+	In boost mode the device can produce up to 1.2A of total current
+	on both outputs. The maximum current on each output is reduced
+	to 625mA then. If not enabled explicitly, boost setting defaults to
+	LEDS_BOOST_FIXED in case both current sources are used.
+	Possible values:
+		LEDS_BOOST_OFF (0) - no boost,
+		LEDS_BOOST_ADAPTIVE (1) - adaptive mode,
+		LEDS_BOOST_FIXED (2) - fixed mode.
+- maxim,boost-mvout : Output voltage of the boost module in millivolts.
+	Valid values: 3300 - 5500, step by 25 (rounded down)
+	Default: 3300
+- maxim,mvsys-min : Low input voltage level in millivolts. Flash is not fired
+	if chip estimates that system voltage could drop below this level due
+	to flash power consumption.
+	Valid values: 2400 - 3400, step by 33 (rounded down)
+	Default: 2400
+
+Required properties for the LED child node:
+- led-sources : see Documentation/devicetree/bindings/leds/common.txt;
+		device current output identifiers: 0 - FLED1, 1 - FLED2
+- led-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
+	Valid values for a LED connected to one FLED output:
+		15625 - 250000, step by 15625 (rounded down)
+	Valid values for a LED connected to both FLED outputs:
+		15625 - 500000, step by 15625 (rounded down)
+- flash-max-microamp : see Documentation/devicetree/bindings/leds/common.txt
+	Valid values for a single LED connected to one FLED output
+	(boost mode must be turned off):
+		15625 - 1000000, step by 15625 (rounded down)
+	Valid values for a single LED connected to both FLED outputs:
+		15625 - 1250000, step by 15625 (rounded down)
+	Valid values for two LEDs case:
+		15625 - 625000, step by 15625 (rounded down)
+- flash-max-timeout-us : see Documentation/devicetree/bindings/leds/common.txt
+	Valid values: 62500 - 1000000, step by 62500 (rounded down)
+
+Optional properties for the LED child node:
+- label : see Documentation/devicetree/bindings/leds/common.txt
+
 Example:
+#include <dt-bindings/leds/common.h>
+
 	max77693@66 {
 		compatible = "maxim,max77693";
 		reg = <0x66>;
@@ -117,5 +170,19 @@ Example:
 			maxim,thermal-regulation-celsius = <75>;
 			maxim,battery-overcurrent-microamp = <3000000>;
 			maxim,charge-input-threshold-microvolt = <4300000>;
+
+		led {
+			compatible = "maxim,max77693-led";
+			maxim,boost-mode = <LEDS_BOOST_FIXED>;
+			maxim,boost-mvout = <5000>;
+			maxim,mvsys-min = <2400>;
+
+			camera_flash: flash-led {
+				label = "max77693-flash";
+				led-sources = <0>, <1>;
+				led-max-microamp = <500000>;
+				flash-max-microamp = <1250000>;
+				flash-max-timeout-us = <1000000>;
+			};
 		};
 	};
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
index 98ee2abbe138..7e9490313d5a 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
@@ -8,7 +8,8 @@ Device Tree Bindings for the Arasan SDHCI Controller
   [3] Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 Required Properties:
-  - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a'
+  - compatible: Compatibility string. Must be 'arasan,sdhci-8.9a' or
+                'arasan,sdhci-4.9a'
   - reg: From mmc bindings: Register location and length.
   - clocks: From clock bindings: Handles to clock inputs.
   - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb"
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 415c5575cbf7..5d0376b8f202 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -7,7 +7,14 @@ This file documents differences between the core properties described
 by mmc.txt and the properties used by the sdhci-esdhc-imx driver.
 
 Required properties:
-- compatible : Should be "fsl,<chip>-esdhc"
+- compatible : Should be "fsl,<chip>-esdhc", the supported chips include
+	       "fsl,imx25-esdhc"
+	       "fsl,imx35-esdhc"
+	       "fsl,imx51-esdhc"
+	       "fsl,imx53-esdhc"
+	       "fsl,imx6q-usdhc"
+	       "fsl,imx6sl-usdhc"
+	       "fsl,imx6sx-usdhc"
 
 Optional properties:
 - fsl,cd-controller : Indicate to use controller internal card detection
diff --git a/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
index 3b3544931437..df370585cbcc 100644
--- a/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/k3-dw-mshc.txt
@@ -13,6 +13,10 @@ Required Properties:
 
 * compatible: should be one of the following.
   - "hisilicon,hi4511-dw-mshc": for controllers with hi4511 specific extensions.
+  - "hisilicon,hi6220-dw-mshc": for controllers with hi6220 specific extensions.
+
+Optional Properties:
+- hisilicon,peripheral-syscon: phandle of syscon used to control peripheral.
 
 Example:
 
@@ -42,3 +46,27 @@ Example:
 		cap-mmc-highspeed;
 		cap-sd-highspeed;
 	};
+
+	/* for Hi6220 */
+
+	dwmmc_1: dwmmc1@f723e000 {
+		compatible = "hisilicon,hi6220-dw-mshc";
+		num-slots = <0x1>;
+		bus-width = <0x4>;
+		disable-wp;
+		cap-sd-highspeed;
+		sd-uhs-sdr12;
+		sd-uhs-sdr25;
+		card-detect-delay = <200>;
+		hisilicon,peripheral-syscon = <&ao_ctrl>;
+		reg = <0x0 0xf723e000 0x0 0x1000>;
+		interrupts = <0x0 0x49 0x4>;
+		clocks = <&clock_sys HI6220_MMC1_CIUCLK>, <&clock_sys HI6220_MMC1_CLK>;
+		clock-names = "ciu", "biu";
+		cd-gpios = <&gpio1 0 1>;
+		pinctrl-names = "default", "idle";
+		pinctrl-0 = <&sd_pmx_func &sd_clk_cfg_func &sd_cfg_func>;
+		pinctrl-1 = <&sd_pmx_idle &sd_clk_cfg_idle &sd_cfg_idle>;
+		vqmmc-supply = <&ldo7>;
+		vmmc-supply = <&ldo10>;
+	};
diff --git a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
index a462c50f19a8..ce0e76749671 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-simple.txt
@@ -21,5 +21,7 @@ Example:
 
 	sdhci0_pwrseq {
 		compatible = "mmc-pwrseq-simple";
-		reset-gpios = <&gpio1 12 0>;
+		reset-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
+		clocks = <&clk_32768_ck>;
+		clock-names = "ext_clock";
 	}
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 438899e8829b..0384fc3f64e8 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -21,6 +21,11 @@ Optional properties:
   below for the case, when a GPIO is used for the CD line
 - wp-inverted: when present, polarity on the WP line is inverted. See the note
   below for the case, when a GPIO is used for the WP line
+- disable-wp: When set no physical WP line is present. This property should
+  only be specified when the controller has a dedicated write-protect
+  detection logic. If a GPIO is always used for the write-protect detection
+  logic it is sufficient to not specify wp-gpios property in the absence of a WP
+  line.
 - max-frequency: maximum operating clock frequency
 - no-1-8-v: when present, denotes that 1.8v card voltage is not supported on
   this system, even if the controller claims it is.
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
new file mode 100644
index 000000000000..a1adfa495ad3
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -0,0 +1,32 @@
+* MTK MMC controller
+
+The MTK  MSDC can act as a MMC controller
+to support MMC, SD, and SDIO types of memory cards.
+
+This file documents differences between the core properties in mmc.txt
+and the properties used by the msdc driver.
+
+Required properties:
+- compatible: Should be "mediatek,mt8173-mmc","mediatek,mt8135-mmc"
+- interrupts: Should contain MSDC interrupt number
+- clocks: MSDC source clock, HCLK
+- clock-names: "source", "hclk"
+- pinctrl-names: should be "default", "state_uhs"
+- pinctrl-0: should contain default/high speed pin ctrl
+- pinctrl-1: should contain uhs mode pin ctrl
+- vmmc-supply: power to the Core
+- vqmmc-supply: power to the IO
+
+Examples:
+mmc0: mmc@11230000 {
+	compatible = "mediatek,mt8173-mmc", "mediatek,mt8135-mmc";
+	reg = <0 0x11230000 0 0x108>;
+	interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_LOW>;
+	vmmc-supply = <&mt6397_vemc_3v3_reg>;
+	vqmmc-supply = <&mt6397_vio18_reg>;
+	clocks = <&pericfg CLK_PERI_MSDC30_0>, <&topckgen CLK_TOP_MSDC50_0_H_SEL>;
+	clock-names = "source", "hclk";
+	pinctrl-names = "default", "state_uhs";
+	pinctrl-0 = <&mmc0_pins_default>;
+	pinctrl-1 = <&mmc0_pins_uhs>;
+};
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index 299081f94abd..d38942f6c5ae 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -18,6 +18,8 @@ Required properties:
   dma-names property.
 - dma-names: must contain "tx" for the transmit DMA channel and "rx" for the
   receive DMA channel.
+- max-frequency: Maximum operating clock frequency, driver uses default clock
+  frequency if it is not set.
 
 
 Example: R8A7790 (R-Car H2) MMCIF0
@@ -29,4 +31,5 @@ Example: R8A7790 (R-Car H2) MMCIF0
 		clocks = <&mstp3_clks R8A7790_CLK_MMCIF0>;
 		dmas = <&dmac0 0xd1>, <&dmac0 0xd2>;
 		dma-names = "tx", "rx";
+		max-frequency = <97500000>;
 	};
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
new file mode 100644
index 000000000000..4ff7128ee3b2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -0,0 +1,150 @@
+* Broadcom STB NAND Controller
+
+The Broadcom Set-Top Box NAND controller supports low-level access to raw NAND
+flash chips. It has a memory-mapped register interface for both control
+registers and for its data input/output buffer. On some SoCs, this controller is
+paired with a custom DMA engine (inventively named "Flash DMA") which supports
+basic PROGRAM and READ functions, among other features.
+
+This controller was originally designed for STB SoCs (BCM7xxx) but is now
+available on a variety of Broadcom SoCs, including some BCM3xxx, BCM63xx, and
+iProc/Cygnus. Its history includes several similar (but not fully register
+compatible) versions.
+
+Required properties:
+- compatible       : May contain an SoC-specific compatibility string (see below)
+                     to account for any SoC-specific hardware bits that may be
+                     added on top of the base core controller.
+                     In addition, must contain compatibility information about
+                     the core NAND controller, of the following form:
+                     "brcm,brcmnand" and an appropriate version compatibility
+                     string, like "brcm,brcmnand-v7.0"
+                     Possible values:
+                         brcm,brcmnand-v4.0
+                         brcm,brcmnand-v5.0
+                         brcm,brcmnand-v6.0
+                         brcm,brcmnand-v6.1
+                         brcm,brcmnand-v7.0
+                         brcm,brcmnand-v7.1
+                         brcm,brcmnand
+- reg              : the register start and length for NAND register region.
+                     (optional) Flash DMA register range (if present)
+                     (optional) NAND flash cache range (if at non-standard offset)
+- reg-names        : a list of the names corresponding to the previous register
+                     ranges. Should contain "nand" and (optionally)
+                     "flash-dma" and/or "nand-cache".
+- interrupts       : The NAND CTLRDY interrupt and (if Flash DMA is available)
+                     FLASH_DMA_DONE
+- interrupt-names  : May be "nand_ctlrdy" or "flash_dma_done", if broken out as
+                     individual interrupts.
+                     May be "nand", if the SoC has the individual NAND
+                     interrupts multiplexed behind another custom piece of
+                     hardware
+- interrupt-parent : See standard interrupt bindings
+- #address-cells   : <1> - subnodes give the chip-select number
+- #size-cells      : <0>
+
+Optional properties:
+- brcm,nand-has-wp          : Some versions of this IP include a write-protect
+                              (WP) control bit. It is always available on >=
+                              v7.0. Use this property to describe the rare
+                              earlier versions of this core that include WP
+
+ -- Additonal SoC-specific NAND controller properties --
+
+The NAND controller is integrated differently on the variety of SoCs on which it
+is found. Part of this integration involves providing status and enable bits
+with which to control the 8 exposed NAND interrupts, as well as hardware for
+configuring the endianness of the data bus. On some SoCs, these features are
+handled via standard, modular components (e.g., their interrupts look like a
+normal IRQ chip), but on others, they are controlled in unique and interesting
+ways, sometimes with registers that lump multiple NAND-related functions
+together. The former case can be described simply by the standard interrupts
+properties in the main controller node. But for the latter exceptional cases,
+we define additional 'compatible' properties and associated register resources within the NAND controller node above.
+
+ - compatible: Can be one of several SoC-specific strings. Each SoC may have
+   different requirements for its additional properties, as described below each
+   bullet point below.
+
+   * "brcm,nand-bcm63138"
+     - reg: (required) the 'NAND_INT_BASE' register range, with separate status
+       and enable registers
+     - reg-names: (required) "nand-int-base"
+
+   * "brcm,nand-iproc"
+     - reg: (required) the "IDM" register range, for interrupt enable and APB
+       bus access endianness configuration, and the "EXT" register range,
+       for interrupt status/ack.
+     - reg-names: (required) a list of the names corresponding to the previous
+       register ranges. Should contain "iproc-idm" and "iproc-ext".
+
+
+* NAND chip-select
+
+Each controller (compatible: "brcm,brcmnand") may contain one or more subnodes
+to represent enabled chip-selects which (may) contain NAND flash chips. Their
+properties are as follows.
+
+Required properties:
+- compatible                : should contain "brcm,nandcs"
+- reg                       : a single integer representing the chip-select
+                              number (e.g., 0, 1, 2, etc.)
+- #address-cells            : see partition.txt
+- #size-cells               : see partition.txt
+- nand-ecc-strength         : see nand.txt
+- nand-ecc-step-size        : must be 512 or 1024. See nand.txt
+
+Optional properties:
+- nand-on-flash-bbt         : boolean, to enable the on-flash BBT for this
+                              chip-select. See nand.txt
+- brcm,nand-oob-sector-size : integer, to denote the spare area sector size
+                              expected for the ECC layout in use. This size, in
+                              addition to the strength and step-size,
+                              determines how the hardware BCH engine will lay
+                              out the parity bytes it stores on the flash.
+                              This property can be automatically determined by
+                              the flash geometry (particularly the NAND page
+                              and OOB size) in many cases, but when booting
+                              from NAND, the boot controller has only a limited
+                              number of available options for its default ECC
+                              layout.
+
+Each nandcs device node may optionally contain sub-nodes describing the flash
+partition mapping. See partition.txt for more detail.
+
+
+Example:
+
+nand@f0442800 {
+	compatible = "brcm,brcmnand-v7.0", "brcm,brcmnand";
+	reg = <0xF0442800 0x600>,
+	      <0xF0443000 0x100>;
+	reg-names = "nand", "flash-dma";
+	interrupt-parent = <&hif_intr2_intc>;
+	interrupts = <24>, <4>;
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	nandcs@1 {
+		compatible = "brcm,nandcs";
+		reg = <1>; // Chip select 1
+		nand-on-flash-bbt;
+		nand-ecc-strength = <12>;
+		nand-ecc-step-size = <512>;
+
+		// Partitions
+		#address-cells = <1>;  // <2>, for 64-bit offset
+		#size-cells = <1>;     // <2>, for 64-bit length
+		flash0.rootfs@0 {
+			reg = <0 0x10000000>;
+		};
+		flash0@0 {
+			reg = <0 0>; // MTDPART_SIZ_FULL
+		};
+		flash0.kernel@10000000 {
+			reg = <0x10000000 0x400000>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/m25p80.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index f20b111b502a..2bee68103b01 100644
--- a/Documentation/devicetree/bindings/mtd/m25p80.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -8,8 +8,8 @@ Required properties:
                is not Linux-only, but in case of Linux, see the "m25p_ids"
                table in drivers/mtd/devices/m25p80.c for the list of supported
                chips.
-               Must also include "nor-jedec" for any SPI NOR flash that can be
-               identified by the JEDEC READ ID opcode (0x9F).
+               Must also include "jedec,spi-nor" for any SPI NOR flash that can
+               be identified by the JEDEC READ ID opcode (0x9F).
 - reg : Chip-Select number
 - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at
 
@@ -25,7 +25,7 @@ Example:
 	flash: m25p80@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "spansion,m25p80", "nor-jedec";
+		compatible = "spansion,m25p80", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <40000000>;
 		m25p,fast-read;
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
deleted file mode 100644
index 8db32384a486..000000000000
--- a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
+++ /dev/null
@@ -1,48 +0,0 @@
-* AMD 10GbE PHY driver (amd-xgbe-phy)
-
-Required properties:
-- compatible: Should be "amd,xgbe-phy-seattle-v1a" and
-  "ethernet-phy-ieee802.3-c45"
-- reg: Address and length of the register sets for the device
-   - SerDes Rx/Tx registers
-   - SerDes integration registers (1/2)
-   - SerDes integration registers (2/2)
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
-- interrupts: Should contain the amd-xgbe-phy interrupt.
-
-Optional properties:
-- amd,speed-set: Speed capabilities of the device
-    0 - 1GbE and 10GbE (default)
-    1 - 2.5GbE and 10GbE
-
-The following optional properties are represented by an array with each
-value corresponding to a particular speed. The first array value represents
-the setting for the 1GbE speed, the second value for the 2.5GbE speed and
-the third value for the 10GbE speed.  All three values are required if the
-property is used.
-- amd,serdes-blwc: Baseline wandering correction enablement
-    0 - Off
-    1 - On
-- amd,serdes-cdr-rate: CDR rate speed selection
-- amd,serdes-pq-skew: PQ (data sampling) skew
-- amd,serdes-tx-amp: TX amplitude boost
-- amd,serdes-dfe-tap-config: DFE taps available to run
-- amd,serdes-dfe-tap-enable: DFE taps to enable
-
-Example:
-	xgbe_phy@e1240800 {
-		compatible = "amd,xgbe-phy-seattle-v1a", "ethernet-phy-ieee802.3-c45";
-		reg = <0 0xe1240800 0 0x00400>,
-		      <0 0xe1250000 0 0x00060>,
-		      <0 0xe1250080 0 0x00004>;
-		interrupt-parent = <&gic>;
-		interrupts = <0 323 4>;
-		amd,speed-set = <0>;
-		amd,serdes-blwc = <1>, <1>, <0>;
-		amd,serdes-cdr-rate = <2>, <2>, <7>;
-		amd,serdes-pq-skew = <10>, <10>, <30>;
-		amd,serdes-tx-amp = <15>, <15>, <10>;
-		amd,serdes-dfe-tap-config = <3>, <3>, <1>;
-		amd,serdes-dfe-tap-enable = <0>, <0>, <127>;
-	};
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt
index 26efd526d16c..4bb624a73b54 100644
--- a/Documentation/devicetree/bindings/net/amd-xgbe.txt
+++ b/Documentation/devicetree/bindings/net/amd-xgbe.txt
@@ -5,12 +5,16 @@ Required properties:
 - reg: Address and length of the register sets for the device
    - MAC registers
    - PCS registers
+   - SerDes Rx/Tx registers
+   - SerDes integration registers (1/2)
+   - SerDes integration registers (2/2)
 - interrupt-parent: Should be the phandle for the interrupt controller
   that services interrupts for this device
 - interrupts: Should contain the amd-xgbe interrupt(s). The first interrupt
   listed is required and is the general device interrupt. If the optional
   amd,per-channel-interrupt property is specified, then one additional
-  interrupt for each DMA channel supported by the device should be specified
+  interrupt for each DMA channel supported by the device should be specified.
+  The last interrupt listed should be the PCS auto-negotiation interrupt.
 - clocks:
    - DMA clock for the amd-xgbe device (used for calculating the
      correct Rx interrupt watchdog timer value on a DMA channel
@@ -19,7 +23,6 @@ Required properties:
 - clock-names: Should be the names of the clocks
    - "dma_clk" for the DMA clock
    - "ptp_clk" for the PTP clock
-- phy-handle: See ethernet.txt file in the same directory
 - phy-mode: See ethernet.txt file in the same directory
 
 Optional properties:
@@ -29,19 +32,46 @@ Optional properties:
 - amd,per-channel-interrupt: Indicates that Rx and Tx complete will generate
   a unique interrupt for each DMA channel - this requires an additional
   interrupt be configured for each DMA channel
+- amd,speed-set: Speed capabilities of the device
+    0 - 1GbE and 10GbE (default)
+    1 - 2.5GbE and 10GbE
+
+The following optional properties are represented by an array with each
+value corresponding to a particular speed. The first array value represents
+the setting for the 1GbE speed, the second value for the 2.5GbE speed and
+the third value for the 10GbE speed.  All three values are required if the
+property is used.
+- amd,serdes-blwc: Baseline wandering correction enablement
+    0 - Off
+    1 - On
+- amd,serdes-cdr-rate: CDR rate speed selection
+- amd,serdes-pq-skew: PQ (data sampling) skew
+- amd,serdes-tx-amp: TX amplitude boost
+- amd,serdes-dfe-tap-config: DFE taps available to run
+- amd,serdes-dfe-tap-enable: DFE taps to enable
 
 Example:
 	xgbe@e0700000 {
 		compatible = "amd,xgbe-seattle-v1a";
 		reg = <0 0xe0700000 0 0x80000>,
-		      <0 0xe0780000 0 0x80000>;
+		      <0 0xe0780000 0 0x80000>,
+		      <0 0xe1240800 0 0x00400>,
+		      <0 0xe1250000 0 0x00060>,
+		      <0 0xe1250080 0 0x00004>;
 		interrupt-parent = <&gic>;
 		interrupts = <0 325 4>,
-			     <0 326 1>, <0 327 1>, <0 328 1>, <0 329 1>;
+			     <0 326 1>, <0 327 1>, <0 328 1>, <0 329 1>,
+			     <0 323 4>;
 		amd,per-channel-interrupt;
 		clocks = <&xgbe_dma_clk>, <&xgbe_ptp_clk>;
 		clock-names = "dma_clk", "ptp_clk";
-		phy-handle = <&phy>;
 		phy-mode = "xgmii";
 		mac-address = [ 02 a1 a2 a3 a4 a5 ];
+		amd,speed-set = <0>;
+		amd,serdes-blwc = <1>, <1>, <0>;
+		amd,serdes-cdr-rate = <2>, <2>, <7>;
+		amd,serdes-pq-skew = <10>, <10>, <30>;
+		amd,serdes-tx-amp = <15>, <15>, <10>;
+		amd,serdes-dfe-tap-config = <3>, <3>, <1>;
+		amd,serdes-dfe-tap-enable = <0>, <0>, <127>;
 	};
diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt
index abd67c13d344..4451ee973223 100644
--- a/Documentation/devicetree/bindings/net/cdns-emac.txt
+++ b/Documentation/devicetree/bindings/net/cdns-emac.txt
@@ -3,7 +3,8 @@
 Required properties:
 - compatible: Should be "cdns,[<chip>-]{emac}"
   Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC.
-  or the generic form: "cdns,emac".
+  Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.
+  Or the generic form: "cdns,emac".
 - reg: Address and length of the register set for the device
 - interrupts: Should contain macb interrupt
 - phy-mode: see ethernet.txt file in the same directory.
diff --git a/Documentation/devicetree/bindings/net/ezchip_enet.txt b/Documentation/devicetree/bindings/net/ezchip_enet.txt
new file mode 100644
index 000000000000..4e29b2b82873
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ezchip_enet.txt
@@ -0,0 +1,15 @@
+* EZchip NPS Management Ethernet port driver
+
+Required properties:
+- compatible: Should be "ezchip,nps-mgt-enet"
+- reg: Address and length of the register set for the device
+- interrupts: Should contain the ENET interrupt
+
+Examples:
+
+	ethernet@f0003000 {
+		compatible = "ezchip,nps-mgt-enet";
+		reg = <0xf0003000 0x44>;
+		interrupts = <7>;
+		mac-address = [ 00 11 22 33 44 55 ];
+	};
diff --git a/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt b/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt
new file mode 100644
index 000000000000..6d7ab4e524d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ipq806x-dwmac.txt
@@ -0,0 +1,35 @@
+* IPQ806x DWMAC Ethernet controller
+
+The device inherits all the properties of the dwmac/stmmac devices
+described in the file net/stmmac.txt with the following changes.
+
+Required properties:
+
+- compatible: should be "qcom,ipq806x-gmac" along with "snps,dwmac"
+	      and any applicable more detailed version number
+	      described in net/stmmac.txt
+
+- qcom,nss-common: should contain a phandle to a syscon device mapping the
+		   nss-common registers.
+
+- qcom,qsgmii-csr: should contain a phandle to a syscon device mapping the
+		   qsgmii-csr registers.
+
+Example:
+
+	gmac: ethernet@37000000 {
+		device_type = "network";
+		compatible = "qcom,ipq806x-gmac";
+		reg = <0x37000000 0x200000>;
+		interrupts = <GIC_SPI 220 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "macirq";
+
+		qcom,nss-common = <&nss_common>;
+		qcom,qsgmii-csr = <&qsgmii_csr>;
+
+		clocks = <&gcc GMAC_CORE1_CLK>;
+		clock-names = "stmmaceth";
+
+		resets = <&gcc GMAC_CORE1_RESET>;
+		reset-names = "stmmaceth";
+	};
diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt
index ba19d671e808..b5d79761ac97 100644
--- a/Documentation/devicetree/bindings/net/macb.txt
+++ b/Documentation/devicetree/bindings/net/macb.txt
@@ -7,8 +7,10 @@ Required properties:
   Use "cdns,at32ap7000-macb" for other 10/100 usage or use the generic form: "cdns,macb".
   Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on
   the Cadence GEM, or the generic form: "cdns,gem".
-  Use "cdns,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs.
-  Use "cdns,sama5d4-gem" for the Gigabit IP available on Atmel sama5d4 SoCs.
+  Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs.
+  Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs.
+  Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs.
+  Use "cdns,zynqmp-gem" for Zynq Ultrascale+ MPSoC.
 - reg: Address and length of the register set for the device
 - interrupts: Should contain macb interrupt
 - phy-mode: See ethernet.txt file in the same directory.
diff --git a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt
new file mode 100644
index 000000000000..7c4a0cc370cf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt
@@ -0,0 +1,29 @@
+* Marvell International Ltd. NCI NFC Controller
+
+Required properties:
+- compatible: Should be "mrvl,nfc-uart".
+
+Optional SoC specific properties:
+- pinctrl-names: Contains only one value - "default".
+- pintctrl-0: Specifies the pin control groups used for this controller.
+- reset-n-io: Output GPIO pin used to reset the chip (active low).
+- hci-muxed: Specifies that the chip is muxing NCI over HCI frames.
+
+Optional UART-based chip specific properties:
+- flow-control: Specifies that the chip is using RTS/CTS.
+- break-control: Specifies that the chip needs specific break management.
+
+Example (for ARM-based BeagleBoard Black with 88W8887 on UART5):
+
+&uart5 {
+	status = "okay";
+
+	nfcmrvluart: nfcmrvluart@5 {
+		compatible = "mrvl,nfc-uart";
+
+		reset-n-io = <&gpio3 16 0>;
+
+		hci-muxed;
+		flow-control;
+        }
+};
diff --git a/Documentation/devicetree/bindings/net/nfc/st21nfcb.txt b/Documentation/devicetree/bindings/net/nfc/st-nci.txt
index bb237072dbe9..d707588ed734 100644
--- a/Documentation/devicetree/bindings/net/nfc/st21nfcb.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci.txt
@@ -1,7 +1,7 @@
-* STMicroelectronics SAS. ST21NFCB NFC Controller
+* STMicroelectronics SAS. ST NCI NFC Controller
 
 Required properties:
-- compatible: Should be "st,st21nfcb-i2c".
+- compatible: Should be "st,st21nfcb-i2c" or "st,st21nfcc-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
 - interrupt-parent: phandle for the interrupt gpio controller
diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
index 7c89ca290ced..32b35a07abe4 100644
--- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
+++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
@@ -18,6 +18,9 @@ Optional SoC Specific Properties:
   "IRQ Status Read" erratum.
 - en2-rf-quirk: Specify that the trf7970a being used has the "EN2 RF"
   erratum.
+- t5t-rmb-extra-byte-quirk: Specify that the trf7970a has the erratum
+  where an extra byte is returned by Read Multiple Block commands issued
+  to Type 5 tags.
 
 Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 
@@ -39,6 +42,7 @@ Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 		autosuspend-delay = <30000>;
 		irq-status-read-quirk;
 		en2-rf-quirk;
+		t5t-rmb-extra-byte-quirk;
 		status = "okay";
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt b/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt
new file mode 100644
index 000000000000..7edba1264f6f
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nxp,lpc1850-dwmac.txt
@@ -0,0 +1,20 @@
+* NXP LPC1850 GMAC ethernet controller
+
+This device is a platform glue layer for stmmac.
+Please see stmmac.txt for the other unchanged properties.
+
+Required properties:
+ - compatible:  Should contain "nxp,lpc1850-dwmac"
+
+Examples:
+
+mac: ethernet@40010000 {
+	compatible = "nxp,lpc1850-dwmac", "snps,dwmac-3.611", "snps,dwmac";
+	reg = <0x40010000 0x2000>;
+	interrupts = <5>;
+	interrupt-names = "macirq";
+	clocks = <&ccu1 CLK_CPU_ETHERNET>;
+	clock-names = "stmmaceth";
+	resets = <&rgu 22>;
+	reset-names = "stmmaceth";
+}
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index 40831fbaff72..525e1658f2da 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -30,6 +30,9 @@ Optional Properties:
 
 - max-speed: Maximum PHY supported speed (10, 100, 1000...)
 
+- broken-turn-around: If set, indicates the PHY device does not correctly
+  release the turn around line low at the end of a MDIO transaction.
+
 Example:
 
 ethernet-phy@0 {
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
new file mode 100644
index 000000000000..1fd8831437bf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -0,0 +1,48 @@
+* Renesas Electronics Ethernet AVB
+
+This file provides information on what the device node for the Ethernet AVB
+interface contains.
+
+Required properties:
+- compatible: "renesas,etheravb-r8a7790" if the device is a part of R8A7790 SoC.
+	      "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC.
+- reg: offset and length of (1) the register block and (2) the stream buffer.
+- interrupts: interrupt specifier for the sole interrupt.
+- phy-mode: see ethernet.txt file in the same directory.
+- phy-handle: see ethernet.txt file in the same directory.
+- #address-cells: number of address cells for the MDIO bus, must be equal to 1.
+- #size-cells: number of size cells on the MDIO bus, must be equal to 0.
+- clocks: clock phandle and specifier pair.
+- pinctrl-0: phandle, referring to a default pin configuration node.
+
+Optional properties:
+- interrupt-parent: the phandle for the interrupt controller that services
+		    interrupts for this device.
+- pinctrl-names: pin configuration state name ("default").
+- renesas,no-ether-link: boolean, specify when a board does not provide a proper
+			 AVB_LINK signal.
+- renesas,ether-link-active-low: boolean, specify when the AVB_LINK signal is
+				 active-low instead of normal active-high.
+
+Example:
+
+	ethernet@e6800000 {
+		compatible = "renesas,etheravb-r8a7790";
+		reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 163 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&mstp8_clks R8A7790_CLK_ETHERAVB>;
+		phy-mode = "rmii";
+		phy-handle = <&phy0>;
+		pinctrl-0 = <&ether_pins>;
+		pinctrl-names = "default";
+		renesas,no-ether-link;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: ethernet-phy@0 {
+			reg = <0>;
+			interrupt-parent = <&gpio2>;
+			interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
index 21fd199e89b5..93eac7ce1446 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -3,7 +3,7 @@ Rockchip SoC RK3288 10/100/1000 Ethernet driver(GMAC)
 The device node has following properties.
 
 Required properties:
- - compatible: Can be "rockchip,rk3288-gmac".
+ - compatible: Can be one of "rockchip,rk3288-gmac", "rockchip,rk3368-gmac"
  - reg: addresses and length of the register sets for the device.
  - interrupts: Should contain the GMAC interrupts.
  - interrupt-names: Should contain the interrupt names "macirq".
diff --git a/Documentation/devicetree/bindings/net/ti,dp83867.txt b/Documentation/devicetree/bindings/net/ti,dp83867.txt
new file mode 100644
index 000000000000..58d935b58598
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ti,dp83867.txt
@@ -0,0 +1,25 @@
+* Texas Instruments - dp83867 Giga bit ethernet phy
+
+Required properties:
+	- reg - The ID number for the phy, usually a small integer
+	- ti,rx-internal-delay - RGMII Recieve Clock Delay - see dt-bindings/net/ti-dp83867.h
+		for applicable values
+	- ti,tx-internal-delay - RGMII Transmit Clock Delay - see dt-bindings/net/ti-dp83867.h
+		for applicable values
+	- ti,fifo-depth - Transmitt FIFO depth- see dt-bindings/net/ti-dp83867.h
+		for applicable values
+
+Default child nodes are standard Ethernet PHY device
+nodes as described in Documentation/devicetree/bindings/net/phy.txt
+
+Example:
+
+	ethernet-phy@0 {
+		reg = <0>;
+		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
+		ti,tx-internal-delay = <DP83867_RGMIIDCTL_2_75_NS>;
+		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_4_B_NIB>;
+	};
+
+Datasheet can be found:
+http://www.ti.com/product/DP83867IR/datasheet
diff --git a/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt b/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
new file mode 100644
index 000000000000..36d881c8e6d4
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
@@ -0,0 +1,68 @@
+* AppliedMicro X-Gene v1 PCIe MSI controller
+
+Required properties:
+
+- compatible: should be "apm,xgene1-msi" to identify
+	      X-Gene v1 PCIe MSI controller block.
+- msi-controller: indicates that this is X-Gene v1 PCIe MSI controller node
+- reg: physical base address (0x79000000) and length (0x900000) for controller
+       registers. These registers include the MSI termination address and data
+       registers as well as the MSI interrupt status registers.
+- reg-names: not required
+- interrupts: A list of 16 interrupt outputs of the controller, starting from
+	      interrupt number 0x10 to 0x1f.
+- interrupt-names: not required
+
+Each PCIe node needs to have property msi-parent that points to msi controller node
+
+Examples:
+
+SoC DTSI:
+
+	+ MSI node:
+	msi@79000000 {
+		compatible = "apm,xgene1-msi";
+		msi-controller;
+		reg = <0x00 0x79000000 0x0 0x900000>;
+		interrupts = 	<0x0 0x10 0x4>
+				<0x0 0x11 0x4>
+				<0x0 0x12 0x4>
+				<0x0 0x13 0x4>
+				<0x0 0x14 0x4>
+				<0x0 0x15 0x4>
+				<0x0 0x16 0x4>
+				<0x0 0x17 0x4>
+				<0x0 0x18 0x4>
+				<0x0 0x19 0x4>
+				<0x0 0x1a 0x4>
+				<0x0 0x1b 0x4>
+				<0x0 0x1c 0x4>
+				<0x0 0x1d 0x4>
+				<0x0 0x1e 0x4>
+				<0x0 0x1f 0x4>;
+	};
+
+	+ PCIe controller node with msi-parent property pointing to MSI node:
+	pcie0: pcie@1f2b0000 {
+		status = "disabled";
+		device_type = "pci";
+		compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+			0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+		reg-names = "csr", "cfg";
+		ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
+			  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+		dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+			      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+		interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+				 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+				 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+				 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+		dma-coherent;
+		clocks = <&pcie0clk 0>;
+		msi-parent= <&msi>;
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
index fdd8046e650a..9462ab7ddd1f 100644
--- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt
@@ -16,6 +16,8 @@ Required properties:
   "allwinner,sun7i-a20-pinctrl"
   "allwinner,sun8i-a23-pinctrl"
   "allwinner,sun8i-a23-r-pinctrl"
+  "allwinner,sun8i-a33-pinctrl"
+
 - reg: Should contain the register physical address and length for the
   pin controller.
 
diff --git a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
new file mode 100644
index 000000000000..08a4a32c8eb0
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt
@@ -0,0 +1,217 @@
+Imagination Technologies Pistachio SoC pin controllers
+======================================================
+
+The pin controllers on Pistachio are a combined GPIO controller, (GPIO)
+interrupt controller, and pinmux + pinconf device. The system ("east") pin
+controller on Pistachio has 99 pins, 90 of which are MFIOs which can be
+configured as GPIOs. The 90 GPIOs are divided into 6 banks of up to 16 GPIOs
+each. The GPIO banks are represented as sub-nodes of the pad controller node.
+
+Please refer to pinctrl-bindings.txt, ../gpio/gpio.txt, and
+../interrupt-controller/interrupts.txt for generic information regarding
+pin controller, GPIO, and interrupt bindings.
+
+Required properties for pin controller node:
+--------------------------------------------
+ - compatible: "img,pistachio-system-pinctrl".
+ - reg: Address range of the pinctrl registers.
+
+Required properties for GPIO bank sub-nodes:
+--------------------------------------------
+ - interrupts: Interrupt line for the GPIO bank.
+ - gpio-controller: Indicates the device is a GPIO controller.
+ - #gpio-cells: Must be two. The first cell is the GPIO pin number and the
+   second cell indicates the polarity. See <dt-bindings/gpio/gpio.h> for
+   a list of possible values.
+ - interrupt-controller: Indicates the device is an interrupt controller.
+ - #interrupt-cells: Must be two. The first cell is the GPIO pin number and
+   the second cell encodes the interrupt flags. See
+   <dt-bindings/interrupt-controller/irq.h> for a list of valid flags.
+
+Note that the N GPIO bank sub-nodes *must* be named gpio0, gpio1, ... gpioN-1.
+
+Required properties for pin configuration sub-nodes:
+----------------------------------------------------
+ - pins: List of pins to which the configuration applies. See below for a
+   list of possible pins.
+
+Optional properties for pin configuration sub-nodes:
+----------------------------------------------------
+ - function: Mux function for the specified pins. This is not applicable for
+   non-MFIO pins. See below for a list of valid functions for each pin.
+ - bias-high-impedance: Enable high-impedance mode.
+ - bias-pull-up: Enable weak pull-up.
+ - bias-pull-down: Enable weak pull-down.
+ - bias-bus-hold: Enable bus-keeper mode.
+ - drive-strength: Drive strength in mA. Supported values: 2, 4, 8, 12.
+ - input-schmitt-enable: Enable Schmitt trigger.
+ - input-schmitt-disable: Disable Schmitt trigger.
+ - slew-rate: Slew rate control. 0 for slow, 1 for fast.
+
+Pin		Functions
+---		---------
+mfio0		spim1
+mfio1		spim1, spim0, uart1
+mfio2		spim1, spim0, uart1
+mfio3		spim1
+mfio4		spim1
+mfio5		spim1
+mfio6		spim1
+mfio7		spim1
+mfio8		spim0
+mfio9		spim0
+mfio10		spim0
+mfio11		spis
+mfio12		spis
+mfio13		spis
+mfio14		spis
+mfio15		sdhost, mips_trace_clk, mips_trace_data
+mfio16		sdhost, mips_trace_dint, mips_trace_data
+mfio17		sdhost, mips_trace_trigout, mips_trace_data
+mfio18		sdhost, mips_trace_trigin, mips_trace_data
+mfio19		sdhost, mips_trace_dm, mips_trace_data
+mfio20		sdhost, mips_trace_probe_n, mips_trace_data
+mfio21		sdhost, mips_trace_data
+mfio22		sdhost, mips_trace_data
+mfio23		sdhost
+mfio24		sdhost
+mfio25		sdhost
+mfio26		sdhost
+mfio27		sdhost
+mfio28		i2c0, spim0
+mfio29		i2c0, spim0
+mfio30		i2c1, spim0
+mfio31		i2c1, spim1
+mfio32		i2c2
+mfio33		i2c2
+mfio34		i2c3
+mfio35		i2c3
+mfio36		i2s_out, audio_clk_in
+mfio37		i2s_out, debug_raw_cca_ind
+mfio38		i2s_out, debug_ed_sec20_cca_ind
+mfio39		i2s_out, debug_ed_sec40_cca_ind
+mfio40		i2s_out, debug_agc_done_0
+mfio41		i2s_out, debug_agc_done_1
+mfio42		i2s_out, debug_ed_cca_ind
+mfio43		i2s_out, debug_s2l_done
+mfio44		i2s_out
+mfio45		i2s_dac_clk, audio_sync
+mfio46		audio_trigger
+mfio47		i2s_in
+mfio48		i2s_in
+mfio49		i2s_in
+mfio50		i2s_in
+mfio51		i2s_in
+mfio52		i2s_in
+mfio53		i2s_in
+mfio54		i2s_in, spdif_in
+mfio55		uart0, spim0, spim1
+mfio56		uart0, spim0, spim1
+mfio57		uart0, spim0, spim1
+mfio58		uart0, spim1
+mfio59		uart1
+mfio60		uart1
+mfio61		spdif_out
+mfio62		spdif_in
+mfio63		eth, mips_trace_clk, mips_trace_data
+mfio64		eth, mips_trace_dint, mips_trace_data
+mfio65		eth, mips_trace_trigout, mips_trace_data
+mfio66		eth, mips_trace_trigin, mips_trace_data
+mfio67		eth, mips_trace_dm, mips_trace_data
+mfio68		eth, mips_trace_probe_n, mips_trace_data
+mfio69		eth, mips_trace_data
+mfio70		eth, mips_trace_data
+mfio71		eth
+mfio72		ir
+mfio73		pwmpdm, mips_trace_clk, sram_debug
+mfio74		pwmpdm, mips_trace_dint, sram_debug
+mfio75		pwmpdm, mips_trace_trigout, rom_debug
+mfio76		pwmpdm, mips_trace_trigin, rom_debug
+mfio77		mdc_debug, mips_trace_dm, rpu_debug
+mfio78		mdc_debug, mips_trace_probe_n, rpu_debug
+mfio79		ddr_debug, mips_trace_data, mips_debug
+mfio80		ddr_debug, mips_trace_data, mips_debug
+mfio81		dreq0, mips_trace_data, eth_debug
+mfio82		dreq1, mips_trace_data, eth_debug
+mfio83		mips_pll_lock, mips_trace_data, usb_debug
+mfio84		sys_pll_lock, mips_trace_data, usb_debug
+mfio85		wifi_pll_lock, mips_trace_data, sdhost_debug
+mfio86		bt_pll_lock, mips_trace_data, sdhost_debug
+mfio87		rpu_v_pll_lock, dreq2, socif_debug
+mfio88		rpu_l_pll_lock, dreq3, socif_debug
+mfio89		audio_pll_lock, dreq4, dreq5
+tck
+trstn
+tdi
+tms
+tdo
+jtag_comply
+safe_mode
+por_disable
+resetn
+
+Example:
+--------
+pinctrl@18101C00 {
+	compatible = "img,pistachio-system-pinctrl";
+	reg = <0x18101C00 0x400>;
+
+	gpio0: gpio0 {
+		interrupts = <GIC_SHARED 71 IRQ_TYPE_LEVEL_HIGH>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	...
+
+	gpio5: gpio5 {
+		interrupts = <GIC_SHARED 76 IRQ_TYPE_LEVEL_HIGH>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+
+		interrupt-controller;
+		#interrupt-cells = <2>;
+	};
+
+	...
+
+	uart0_xfer: uart0-xfer {
+		uart0-rxd {
+			pins = "mfio55";
+			function = "uart0";
+		};
+		uart0-txd {
+			pins = "mfio56";
+			function = "uart0";
+		};
+	};
+
+	uart0_rts_cts: uart0-rts-cts {
+		uart0-rts {
+			  pins = "mfio57";
+			  function = "uart0";
+		};
+		uart0-cts {
+			  pins = "mfio58";
+			  function = "uart0";
+		};
+	};
+};
+
+uart@... {
+	...
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_xfer>, <&uart0_rts_cts>;
+	...
+};
+
+usb_vbus: fixed-regulator {
+	...
+	gpio = <&gpio5 6 GPIO_ACTIVE_HIGH>;
+	...
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
index adda2a8d1d52..add7c38ec7d8 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-370-pinctrl.txt
@@ -17,10 +17,10 @@ mpp0          0        gpio, uart0(rxd)
 mpp1          1        gpo, uart0(txd)
 mpp2          2        gpio, i2c0(sck), uart0(txd)
 mpp3          3        gpio, i2c0(sda), uart0(rxd)
-mpp4          4        gpio, cpu_pd(vdd)
-mpp5          5        gpo, ge0(txclko), uart1(txd), spi1(clk), audio(mclk)
+mpp4          4        gpio, vdd(cpu-pd)
+mpp5          5        gpo, ge0(txclkout), uart1(txd), spi1(sck), audio(mclk)
 mpp6          6        gpio, ge0(txd0), sata0(prsnt), tdm(rst), audio(sdo)
-mpp7          7        gpo, ge0(txd1), tdm(tdx), audio(lrclk)
+mpp7          7        gpo, ge0(txd1), tdm(dtx), audio(lrclk)
 mpp8          8        gpio, ge0(txd2), uart0(rts), tdm(drx), audio(bclk)
 mpp9          9        gpo, ge0(txd3), uart1(txd), sd0(clk), audio(spdifo)
 mpp10         10       gpio, ge0(txctl), uart0(cts), tdm(fsync), audio(sdi)
@@ -52,8 +52,8 @@ mpp30         30       gpio, ge0(rxd7), ge1(rxclk), i2c1(sck)
 mpp31         31       gpio, tclk, ge0(txerr)
 mpp32         32       gpio, spi0(cs0)
 mpp33         33       gpio, dev(bootcs), spi0(cs0)
-mpp34         34       gpo, dev(wen0), spi0(mosi)
-mpp35         35       gpo, dev(oen), spi0(sck)
+mpp34         34       gpo, dev(we0), spi0(mosi)
+mpp35         35       gpo, dev(oe), spi0(sck)
 mpp36         36       gpo, dev(a1), spi0(miso)
 mpp37         37       gpo, dev(a0), sata0(prsnt)
 mpp38         38       gpio, dev(ready), uart1(cts), uart0(cts)
@@ -86,11 +86,11 @@ mpp57         57       gpio, dev(cs3), uart1(rxd), tdm(fsync), sata0(prsnt),
 mpp58         58       gpio, dev(cs0), uart1(rts), tdm(int), audio(extclk),
                        uart0(rts)
 mpp59         59       gpo, dev(ale0), uart1(rts), uart0(rts), audio(bclk)
-mpp60         60       gpio, dev(ale1), uart1(rxd), sata0(prsnt), pcie(rst-out),
+mpp60         60       gpio, dev(ale1), uart1(rxd), sata0(prsnt), pcie(rstout),
                        audio(sdi)
-mpp61         61       gpo, dev(wen1), uart1(txd), audio(rclk)
+mpp61         61       gpo, dev(we1), uart1(txd), audio(lrclk)
 mpp62         62       gpio, dev(a2), uart1(cts), tdm(drx), pcie(clkreq0),
                        audio(mclk), uart0(cts)
 mpp63         63       gpo, spi0(sck), tclk
-mpp64         64       gpio, spi0(miso), spi0-1(cs1)
-mpp65         65       gpio, spi0(mosi), spi0-1(cs2)
+mpp64         64       gpio, spi0(miso), spi0(cs1)
+mpp65         65       gpio, spi0(mosi), spi0(cs2)
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
index 7de0cda4a379..06e5bb0367f5 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-375-pinctrl.txt
@@ -15,24 +15,24 @@ name          pins     functions
 ================================================================================
 mpp0          0        gpio, dev(ad2), spi0(cs1), spi1(cs1)
 mpp1          1        gpio, dev(ad3), spi0(mosi), spi1(mosi)
-mpp2          2        gpio, dev(ad4), ptp(eventreq), led(c0), audio(sdi)
-mpp3          3        gpio, dev(ad5), ptp(triggen), led(p3), audio(mclk)
+mpp2          2        gpio, dev(ad4), ptp(evreq), led(c0), audio(sdi)
+mpp3          3        gpio, dev(ad5), ptp(trig), led(p3), audio(mclk)
 mpp4          4        gpio, dev(ad6), spi0(miso), spi1(miso)
 mpp5          5        gpio, dev(ad7), spi0(cs2), spi1(cs2)
-mpp6          6        gpio, dev(ad0), led(p1), audio(rclk)
+mpp6          6        gpio, dev(ad0), led(p1), audio(lrclk)
 mpp7          7        gpio, dev(ad1), ptp(clk), led(p2), audio(extclk)
 mpp8          8        gpio, dev (bootcs), spi0(cs0), spi1(cs0)
-mpp9          9        gpio, nf(wen), spi0(sck), spi1(sck)
-mpp10        10        gpio, nf(ren), dram(vttctrl), led(c1)
+mpp9          9        gpio, spi0(sck), spi1(sck), nand(we)
+mpp10        10        gpio, dram(vttctrl), led(c1), nand(re)
 mpp11        11        gpio, dev(a0), led(c2), audio(sdo)
 mpp12        12        gpio, dev(a1), audio(bclk)
-mpp13        13        gpio, dev(readyn), pcie0(rstoutn), pcie1(rstoutn)
+mpp13        13        gpio, dev(ready), pcie0(rstout), pcie1(rstout)
 mpp14        14        gpio, i2c0(sda), uart1(txd)
 mpp15        15        gpio, i2c0(sck), uart1(rxd)
 mpp16        16        gpio, uart0(txd)
 mpp17        17        gpio, uart0(rxd)
-mpp18        18        gpio, tdm(intn)
-mpp19        19        gpio, tdm(rstn)
+mpp18        18        gpio, tdm(int)
+mpp19        19        gpio, tdm(rst)
 mpp20        20        gpio, tdm(pclk)
 mpp21        21        gpio, tdm(fsync)
 mpp22        22        gpio, tdm(drx)
@@ -45,12 +45,12 @@ mpp28        28        gpio, led(p3), ge1(txctl), sd(clk)
 mpp29        29        gpio, pcie1(clkreq), ge1(rxclk), sd(d3)
 mpp30        30        gpio, ge1(txd0), spi1(cs0)
 mpp31        31        gpio, ge1(txd1), spi1(mosi)
-mpp32        32        gpio, ge1(txd2), spi1(sck), ptp(triggen)
+mpp32        32        gpio, ge1(txd2), spi1(sck), ptp(trig)
 mpp33        33        gpio, ge1(txd3), spi1(miso)
 mpp34        34        gpio, ge1(txclkout), spi1(sck)
 mpp35        35        gpio, ge1(rxctl), spi1(cs1), spi0(cs2)
 mpp36        36        gpio, pcie0(clkreq)
-mpp37        37        gpio, pcie0(clkreq), tdm(intn), ge(mdc)
+mpp37        37        gpio, pcie0(clkreq), tdm(int), ge(mdc)
 mpp38        38        gpio, pcie1(clkreq), ge(mdio)
 mpp39        39        gpio, ref(clkout)
 mpp40        40        gpio, uart1(txd)
@@ -58,25 +58,25 @@ mpp41        41        gpio, uart1(rxd)
 mpp42        42        gpio, spi1(cs2), led(c0)
 mpp43        43        gpio, sata0(prsnt), dram(vttctrl)
 mpp44        44        gpio, sata0(prsnt)
-mpp45        45        gpio, spi0(cs2), pcie0(rstoutn)
-mpp46        46        gpio, led(p0), ge0(txd0), ge1(txd0)
+mpp45        45        gpio, spi0(cs2), pcie0(rstout)
+mpp46        46        gpio, led(p0), ge0(txd0), ge1(txd0), dev(we1)
 mpp47        47        gpio, led(p1), ge0(txd1), ge1(txd1)
 mpp48        48        gpio, led(p2), ge0(txd2), ge1(txd2)
 mpp49        49        gpio, led(p3), ge0(txd3), ge1(txd3)
 mpp50        50        gpio, led(c0), ge0(rxd0), ge1(rxd0)
 mpp51        51        gpio, led(c1), ge0(rxd1), ge1(rxd1)
 mpp52        52        gpio, led(c2), ge0(rxd2), ge1(rxd2)
-mpp53        53        gpio, pcie1(rstoutn), ge0(rxd3), ge1(rxd3)
-mpp54        54        gpio, pcie0(rstoutn), ge0(rxctl), ge1(rxctl)
+mpp53        53        gpio, pcie1(rstout), ge0(rxd3), ge1(rxd3)
+mpp54        54        gpio, pcie0(rstout), ge0(rxctl), ge1(rxctl)
 mpp55        55        gpio, ge0(rxclk), ge1(rxclk)
 mpp56        56        gpio, ge0(txclkout), ge1(txclkout)
-mpp57        57        gpio, ge0(txctl), ge1(txctl)
+mpp57        57        gpio, ge0(txctl), ge1(txctl), dev(we0)
 mpp58        58        gpio, led(c0)
 mpp59        59        gpio, led(c1)
 mpp60        60        gpio, uart1(txd), led(c2)
 mpp61        61        gpio, i2c1(sda), uart1(rxd), spi1(cs2), led(p0)
 mpp62        62        gpio, i2c1(sck), led(p1)
-mpp63        63        gpio, ptp(triggen), led(p2)
+mpp63        63        gpio, ptp(trig), led(p2), dev(burst/last)
 mpp64        64        gpio, dram(vttctrl), led(p3)
 mpp65        65        gpio, sata1(prsnt)
-mpp66        66        gpio, ptp(eventreq), spi1(cs3)
+mpp66        66        gpio, ptp(evreq), spi1(cs3)
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
index b17c96849fc9..54ec4c0a0d0e 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-38x-pinctrl.txt
@@ -27,16 +27,16 @@ mpp8          8        gpio, ge0(txd1), dev(ad10)
 mpp9          9        gpio, ge0(txd2), dev(ad11)
 mpp10         10       gpio, ge0(txd3), dev(ad12)
 mpp11         11       gpio, ge0(txctl), dev(ad13)
-mpp12         12       gpio, ge0(rxd0), pcie0(rstout), pcie1(rstout) [1], spi0(cs1), dev(ad14)
-mpp13         13       gpio, ge0(rxd1), pcie0(clkreq), pcie1(clkreq) [1], spi0(cs2), dev(ad15)
-mpp14         14       gpio, ge0(rxd2), ptp(clk), m(vtt_ctrl), spi0(cs3), dev(wen1)
-mpp15         15       gpio, ge0(rxd3), ge(mdc slave), pcie0(rstout), spi0(mosi), pcie1(rstout) [1]
-mpp16         16       gpio, ge0(rxctl), ge(mdio slave), m(decc_err), spi0(miso), pcie0(clkreq)
-mpp17         17       gpio, ge0(rxclk), ptp(clk), ua1(rxd), spi0(sck), sata1(prsnt)
-mpp18         18       gpio, ge0(rxerr), ptp(trig_gen), ua1(txd), spi0(cs0), pcie1(rstout) [1]
-mpp19         19       gpio, ge0(col), ptp(event_req), pcie0(clkreq), sata1(prsnt), ua0(cts)
-mpp20         20       gpio, ge0(txclk), ptp(clk), pcie1(rstout) [1], sata0(prsnt), ua0(rts)
-mpp21         21       gpio, spi0(cs1), ge1(rxd0), sata0(prsnt), sd0(cmd), dev(bootcs)
+mpp12         12       gpio, ge0(rxd0), pcie0(rstout), spi0(cs1), dev(ad14), pcie3(clkreq)
+mpp13         13       gpio, ge0(rxd1), pcie0(clkreq), pcie1(clkreq) [1], spi0(cs2), dev(ad15), pcie2(clkreq)
+mpp14         14       gpio, ge0(rxd2), ptp(clk), dram(vttctrl), spi0(cs3), dev(we1), pcie3(clkreq)
+mpp15         15       gpio, ge0(rxd3), ge(mdc slave), pcie0(rstout), spi0(mosi)
+mpp16         16       gpio, ge0(rxctl), ge(mdio slave), dram(deccerr), spi0(miso), pcie0(clkreq), pcie1(clkreq) [1]
+mpp17         17       gpio, ge0(rxclk), ptp(clk), ua1(rxd), spi0(sck), sata1(prsnt), sata0(prsnt)
+mpp18         18       gpio, ge0(rxerr), ptp(trig), ua1(txd), spi0(cs0)
+mpp19         19       gpio, ge0(col), ptp(evreq), ge0(txerr), sata1(prsnt), ua0(cts)
+mpp20         20       gpio, ge0(txclk), ptp(clk), sata0(prsnt), ua0(rts)
+mpp21         21       gpio, spi0(cs1), ge1(rxd0), sata0(prsnt), sd0(cmd), dev(bootcs), sata1(prsnt)
 mpp22         22       gpio, spi0(mosi), dev(ad0)
 mpp23         23       gpio, spi0(sck), dev(ad2)
 mpp24         24       gpio, spi0(miso), ua0(cts), ua1(rxd), sd0(d4), dev(ready)
@@ -45,36 +45,36 @@ mpp26         26       gpio, spi0(cs2), i2c1(sck), sd0(d6), dev(cs1)
 mpp27         27       gpio, spi0(cs3), ge1(txclkout), i2c1(sda), sd0(d7), dev(cs2)
 mpp28         28       gpio, ge1(txd0), sd0(clk), dev(ad5)
 mpp29         29       gpio, ge1(txd1), dev(ale0)
-mpp30         30       gpio, ge1(txd2), dev(oen)
+mpp30         30       gpio, ge1(txd2), dev(oe)
 mpp31         31       gpio, ge1(txd3), dev(ale1)
-mpp32         32       gpio, ge1(txctl), dev(wen0)
-mpp33         33       gpio, m(decc_err), dev(ad3)
+mpp32         32       gpio, ge1(txctl), dev(we0)
+mpp33         33       gpio, dram(deccerr), dev(ad3)
 mpp34         34       gpio, dev(ad1)
 mpp35         35       gpio, ref(clk_out1), dev(a1)
-mpp36         36       gpio, ptp(trig_gen), dev(a0)
+mpp36         36       gpio, ptp(trig), dev(a0)
 mpp37         37       gpio, ptp(clk), ge1(rxclk), sd0(d3), dev(ad8)
-mpp38         38       gpio, ptp(event_req), ge1(rxd1), ref(clk_out0), sd0(d0), dev(ad4)
+mpp38         38       gpio, ptp(evreq), ge1(rxd1), ref(clk_out0), sd0(d0), dev(ad4)
 mpp39         39       gpio, i2c1(sck), ge1(rxd2), ua0(cts), sd0(d1), dev(a2)
 mpp40         40       gpio, i2c1(sda), ge1(rxd3), ua0(rts), sd0(d2), dev(ad6)
-mpp41         41       gpio, ua1(rxd), ge1(rxctl), ua0(cts), spi1(cs3), dev(burst/last)
+mpp41         41       gpio, ua1(rxd), ge1(rxctl), ua0(cts), spi1(cs3), dev(burst/last), nand(rb0)
 mpp42         42       gpio, ua1(txd), ua0(rts), dev(ad7)
-mpp43         43       gpio, pcie0(clkreq), m(vtt_ctrl), m(decc_err), pcie0(rstout), dev(clkout)
-mpp44         44       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [3], pcie0(rstout)
-mpp45         45       gpio, ref(clk_out0), pcie0(rstout), pcie1(rstout) [1], pcie2(rstout), pcie3(rstout)
-mpp46         46       gpio, ref(clk_out1), pcie0(rstout), pcie1(rstout) [1], pcie2(rstout), pcie3(rstout)
-mpp47         47       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], spi1(cs2), sata3(prsnt) [2]
-mpp48         48       gpio, sata0(prsnt), m(vtt_ctrl), tdm2c(pclk), audio(mclk), sd0(d4)
-mpp49         49       gpio, sata2(prsnt) [2], sata3(prsnt) [2], tdm2c(fsync), audio(lrclk), sd0(d5)
-mpp50         50       gpio, pcie0(rstout), pcie1(rstout) [1], tdm2c(drx), audio(extclk), sd0(cmd)
-mpp51         51       gpio, tdm2c(dtx), audio(sdo), m(decc_err)
-mpp52         52       gpio, pcie0(rstout), pcie1(rstout) [1], tdm2c(intn), audio(sdi), sd0(d6)
-mpp53         53       gpio, sata1(prsnt), sata0(prsnt), tdm2c(rstn), audio(bclk), sd0(d7)
-mpp54         54       gpio, sata0(prsnt), sata1(prsnt), pcie0(rstout), pcie1(rstout) [1], sd0(d3)
-mpp55         55       gpio, ua1(cts), ge(mdio), pcie1(clkreq) [1], spi1(cs1), sd0(d0)
-mpp56         56       gpio, ua1(rts), ge(mdc), m(decc_err), spi1(mosi)
-mpp57         57       gpio, spi1(sck), sd0(clk)
-mpp58         58       gpio, pcie1(clkreq) [1], i2c1(sck), pcie2(clkreq), spi1(miso), sd0(d1)
-mpp59         59       gpio, pcie0(rstout), i2c1(sda), pcie1(rstout) [1], spi1(cs0), sd0(d2)
+mpp43         43       gpio, pcie0(clkreq), dram(vttctrl), dram(deccerr), spi1(cs2), dev(clkout), nand(rb1)
+mpp44         44       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [3]
+mpp45         45       gpio, ref(clk_out0), pcie0(rstout), ua1(rxd)
+mpp46         46       gpio, ref(clk_out1), pcie0(rstout), ua1(txd)
+mpp47         47       gpio, sata0(prsnt), sata1(prsnt), sata2(prsnt) [2], sata3(prsnt) [2]
+mpp48         48       gpio, sata0(prsnt), dram(vttctrl), tdm(pclk), audio(mclk), sd0(d4), pcie0(clkreq)
+mpp49         49       gpio, sata2(prsnt) [2], sata3(prsnt) [2], tdm(fsync), audio(lrclk), sd0(d5), pcie1(clkreq)
+mpp50         50       gpio, pcie0(rstout), tdm(drx), audio(extclk), sd0(cmd)
+mpp51         51       gpio, tdm(dtx), audio(sdo), dram(deccerr), ptp(trig)
+mpp52         52       gpio, pcie0(rstout), tdm(int), audio(sdi), sd0(d6), ptp(clk)
+mpp53         53       gpio, sata1(prsnt), sata0(prsnt), tdm(rst), audio(bclk), sd0(d7), ptp(evreq)
+mpp54         54       gpio, sata0(prsnt), sata1(prsnt), pcie0(rstout), ge0(txerr), sd0(d3)
+mpp55         55       gpio, ua1(cts), ge(mdio), pcie1(clkreq) [1], spi1(cs1), sd0(d0), ua1(rxd)
+mpp56         56       gpio, ua1(rts), ge(mdc), dram(deccerr), spi1(mosi), ua1(txd)
+mpp57         57       gpio, spi1(sck), sd0(clk), ua1(txd)
+mpp58         58       gpio, pcie1(clkreq) [1], i2c1(sck), pcie2(clkreq), spi1(miso), sd0(d1), ua1(rxd)
+mpp59         59       gpio, pcie0(rstout), i2c1(sda), spi1(cs0), sd0(d2)
 
 [1]: only available on 88F6820 and 88F6828
 [2]: only available on 88F6828
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-39x-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-39x-pinctrl.txt
index 5b1a9dc004f4..a40b60f1ca4c 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-39x-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-39x-pinctrl.txt
@@ -4,8 +4,9 @@ Please refer to marvell,mvebu-pinctrl.txt in this directory for common binding
 part and usage.
 
 Required properties:
-- compatible: "marvell,88f6920-pinctrl", "marvell,88f6928-pinctrl"
-  depending on the specific variant of the SoC being used.
+- compatible: "marvell,88f6920-pinctrl", "marvell,88f6925-pinctrl" or
+  "marvell,88f6928-pinctrl" depending on the specific variant of the
+  SoC being used.
 - reg: register specifier of MPP registers
 
 Available mpp pins/groups and functions:
@@ -24,55 +25,60 @@ mpp6	6	gpio, dev(cs3), xsmi(mdio)
 mpp7	7	gpio, dev(ad9), xsmi(mdc)
 mpp8	8	gpio, dev(ad10), ptp(trig)
 mpp9	9	gpio, dev(ad11), ptp(clk)
-mpp10	10	gpio, dev(ad12), ptp(event)
+mpp10	10	gpio, dev(ad12), ptp(evreq)
 mpp11	11	gpio, dev(ad13), led(clk)
 mpp12	12	gpio, pcie0(rstout), dev(ad14), led(stb)
-mpp13	13	gpio, dev(ad15), led(data)
-mpp14	14	gpio, m(vtt), dev(wen1), ua1(txd)
+mpp13	13	gpio, dev(ad15), pcie2(clkreq), led(data)
+mpp14	14	gpio, dram(vttctrl), dev(we1), ua1(txd)
 mpp15	15	gpio, pcie0(rstout), spi0(mosi), i2c1(sck)
-mpp16	16	gpio, m(decc), spi0(miso), i2c1(sda)
-mpp17	17	gpio, ua1(rxd), spi0(sck), smi(mdio)
+mpp16	16	gpio, dram(deccerr), spi0(miso), pcie0(clkreq), i2c1(sda)
+mpp17	17	gpio, ua1(rxd), spi0(sck), sata1(prsnt) [1], sata0(prsnt) [1], smi(mdio)
 mpp18	18	gpio, ua1(txd), spi0(cs0), i2c2(sck)
-mpp19	19	gpio, sata1(present) [1], ua0(cts), ua1(rxd), i2c2(sda)
-mpp20	20	gpio, sata0(present) [1], ua0(rts), ua1(txd), smi(mdc)
-mpp21	21	gpio, spi0(cs1), sata0(present) [1], sd(cmd), dev(bootcs), ge(rxd0)
+mpp19	19	gpio, sata1(prsnt) [1], ua0(cts), ua1(rxd), i2c2(sda)
+mpp20	20	gpio, sata0(prsnt) [1], ua0(rts), ua1(txd), smi(mdc)
+mpp21	21	gpio, spi0(cs1), sata0(prsnt) [1], sd0(cmd), dev(bootcs),
+                sata1(prsnt) [1], ge(rxd0)
 mpp22	22	gpio, spi0(mosi), dev(ad0)
 mpp23	23	gpio, spi0(sck), dev(ad2)
-mpp24	24	gpio, spi0(miso), ua0(cts), ua1(rxd), sd(d4), dev(readyn)
-mpp25	25	gpio, spi0(cs0), ua0(rts), ua1(txd), sd(d5), dev(cs0)
-mpp26	26	gpio, spi0(cs2), i2c1(sck), sd(d6), dev(cs1)
-mpp27	27	gpio, spi0(cs3), i2c1(sda), sd(d7), dev(cs2), ge(txclkout)
-mpp28	28	gpio, sd(clk), dev(ad5), ge(txd0)
+mpp24	24	gpio, spi0(miso), ua0(cts), ua1(rxd), sd0(d4), dev(ready)
+mpp25	25	gpio, spi0(cs0), ua0(rts), ua1(txd), sd0(d5), dev(cs0)
+mpp26	26	gpio, spi0(cs2), i2c1(sck), sd0(d6), dev(cs1)
+mpp27	27	gpio, spi0(cs3), i2c1(sda), sd0(d7), dev(cs2), ge(txclkout)
+mpp28	28	gpio, sd0(clk), dev(ad5), ge(txd0)
 mpp29	29	gpio, dev(ale0), ge(txd1)
-mpp30	30	gpio, dev(oen), ge(txd2)
+mpp30	30	gpio, dev(oe), ge(txd2)
 mpp31	31	gpio, dev(ale1), ge(txd3)
-mpp32	32	gpio, dev(wen0), ge(txctl)
-mpp33	33	gpio, m(decc), dev(ad3)
+mpp32	32	gpio, dev(we0), ge(txctl)
+mpp33	33	gpio, dram(deccerr), dev(ad3)
 mpp34	34	gpio, dev(ad1)
 mpp35	35	gpio, ref(clk), dev(a1)
 mpp36	36	gpio, dev(a0)
-mpp37	37	gpio, sd(d3), dev(ad8), ge(rxclk)
-mpp38	38	gpio, ref(clk), sd(d0), dev(ad4), ge(rxd1)
-mpp39	39	gpio, i2c1(sck), ua0(cts), sd(d1), dev(a2), ge(rxd2)
-mpp40	40	gpio, i2c1(sda), ua0(rts), sd(d2), dev(ad6), ge(rxd3)
-mpp41	41	gpio, ua1(rxd), ua0(cts), spi1(cs3), dev(burstn), nd(rbn0), ge(rxctl)
+mpp37	37	gpio, sd0(d3), dev(ad8), ge(rxclk)
+mpp38	38	gpio, ref(clk), sd0(d0), dev(ad4), ge(rxd1)
+mpp39	39	gpio, i2c1(sck), ua0(cts), sd0(d1), dev(a2), ge(rxd2)
+mpp40	40	gpio, i2c1(sda), ua0(rts), sd0(d2), dev(ad6), ge(rxd3)
+mpp41	41	gpio, ua1(rxd), ua0(cts), spi1(cs3), dev(burst/last), nand(rb0), ge(rxctl)
 mpp42	42	gpio, ua1(txd), ua0(rts), dev(ad7)
-mpp43	43	gpio, pcie0(clkreq), m(vtt), m(decc), spi1(cs2), dev(clkout), nd(rbn1)
-mpp44	44	gpio, sata0(present) [1], sata1(present) [1], led(clk)
+mpp43	43	gpio, pcie0(clkreq), dram(vttctrl), dram(deccerr), spi1(cs2), dev(clkout), nand(rb1)
+mpp44	44	gpio, sata0(prsnt) [1], sata1(prsnt) [1], sata2(prsnt) [2],
+                sata3(prsnt) [2], led(clk)
 mpp45	45	gpio, ref(clk), pcie0(rstout), ua1(rxd)
 mpp46	46	gpio, ref(clk), pcie0(rstout), ua1(txd), led(stb)
-mpp47	47	gpio, sata0(present) [1], sata1(present) [1], led(data)
-mpp48	48	gpio, sata0(present) [1], m(vtt), tdm(pclk) [1], audio(mclk) [1], sd(d4), pcie0(clkreq), ua1(txd)
-mpp49	49	gpio, tdm(fsync) [1], audio(lrclk) [1], sd(d5), ua2(rxd)
-mpp50	50	gpio, pcie0(rstout), tdm(drx) [1], audio(extclk) [1], sd(cmd), ua2(rxd)
-mpp51	51	gpio, tdm(dtx) [1], audio(sdo) [1], m(decc), ua2(txd)
-mpp52	52	gpio, pcie0(rstout), tdm(intn) [1], audio(sdi) [1], sd(d6), i2c3(sck)
-mpp53	53	gpio, sata1(present) [1], sata0(present) [1], tdm(rstn) [1], audio(bclk) [1], sd(d7), i2c3(sda)
-mpp54	54	gpio, sata0(present) [1], sata1(present) [1], pcie0(rstout), sd(d3), ua3(txd)
-mpp55	55	gpio, ua1(cts), spi1(cs1), sd(d0), ua1(rxd), ua3(rxd)
-mpp56	56	gpio, ua1(rts), m(decc), spi1(mosi), ua1(txd)
-mpp57	57	gpio, spi1(sck), sd(clk), ua1(txd)
-mpp58	58	gpio, i2c1(sck), pcie2(clkreq), spi1(miso), sd(d1), ua1(rxd)
-mpp59	59	gpio, pcie0(rstout), i2c1(sda), spi1(cs0), sd(d2)
+mpp47	47	gpio, sata0(prsnt) [1], sata1(prsnt) [1], sata2(prsnt) [2],
+                sata3(prsnt) [2], led(data)
+mpp48	48	gpio, sata0(prsnt) [1], dram(vttctrl), tdm(pclk) [2], audio(mclk) [2], sd0(d4), pcie0(clkreq), ua1(txd)
+mpp49	49	gpio, sata2(prsnt) [2], sata3(prsnt) [2], tdm(fsync) [2],
+                audio(lrclk) [2], sd0(d5), ua2(rxd)
+mpp50	50	gpio, pcie0(rstout), tdm(drx) [2], audio(extclk) [2], sd0(cmd), ua2(rxd)
+mpp51	51	gpio, tdm(dtx) [2], audio(sdo) [2], dram(deccerr), ua2(txd)
+mpp52	52	gpio, pcie0(rstout), tdm(int) [2], audio(sdi) [2], sd0(d6), i2c3(sck)
+mpp53	53	gpio, sata1(prsnt) [1], sata0(prsnt) [1], tdm(rst) [2], audio(bclk) [2], sd0(d7), i2c3(sda)
+mpp54	54	gpio, sata0(prsnt) [1], sata1(prsnt) [1], pcie0(rstout), sd0(d3), ua3(txd)
+mpp55	55	gpio, ua1(cts), spi1(cs1), sd0(d0), ua1(rxd), ua3(rxd)
+mpp56	56	gpio, ua1(rts), dram(deccerr), spi1(mosi), ua1(txd)
+mpp57	57	gpio, spi1(sck), sd0(clk), ua1(txd)
+mpp58	58	gpio, i2c1(sck), pcie2(clkreq), spi1(miso), sd0(d1), ua1(rxd)
+mpp59	59	gpio, pcie0(rstout), i2c1(sda), spi1(cs0), sd0(d2)
 
-[1]: only available on 88F6928
+[1]: only available on 88F6925/88F6928
+[2]: only available on 88F6928
diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
index 373dbccd7ab0..76da7222ff92 100644
--- a/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/marvell,armada-xp-pinctrl.txt
@@ -18,7 +18,7 @@ only for more detailed description in this document.
 
 name          pins     functions
 ================================================================================
-mpp0          0        gpio, ge0(txclko), lcd(d0)
+mpp0          0        gpio, ge0(txclkout), lcd(d0)
 mpp1          1        gpio, ge0(txd0), lcd(d1)
 mpp2          2        gpio, ge0(txd1), lcd(d2)
 mpp3          3        gpio, ge0(txd2), lcd(d3)
@@ -30,49 +30,50 @@ mpp8          8        gpio, ge0(rxd2), lcd(d8)
 mpp9          9        gpio, ge0(rxd3), lcd(d9)
 mpp10         10       gpio, ge0(rxctl), lcd(d10)
 mpp11         11       gpio, ge0(rxclk), lcd(d11)
-mpp12         12       gpio, ge0(txd4), ge1(txd0), lcd(d12)
-mpp13         13       gpio, ge0(txd5), ge1(txd1), lcd(d13)
-mpp14         14       gpio, ge0(txd6), ge1(txd2), lcd(d15)
-mpp15         15       gpio, ge0(txd7), ge1(txd3), lcd(d16)
-mpp16         16       gpio, ge0(txd7), ge1(txd3), lcd(d16)
-mpp17         17       gpio, ge0(col), ge1(txctl), lcd(d17)
+mpp12         12       gpio, ge0(txd4), ge1(txclkout), lcd(d12)
+mpp13         13       gpio, ge0(txd5), ge1(txd0), spi1(mosi), lcd(d13)
+mpp14         14       gpio, ge0(txd6), ge1(txd1), spi1(sck), lcd(d15)
+mpp15         15       gpio, ge0(txd7), ge1(txd2), lcd(d16)
+mpp16         16       gpio, ge0(txd7), ge1(txd3), spi1(cs0), lcd(d16)
+mpp17         17       gpio, ge0(col), ge1(txctl), spi1(miso), lcd(d17)
 mpp18         18       gpio, ge0(rxerr), ge1(rxd0), lcd(d18), ptp(trig)
 mpp19         19       gpio, ge0(crs), ge1(rxd1), lcd(d19), ptp(evreq)
 mpp20         20       gpio, ge0(rxd4), ge1(rxd2), lcd(d20), ptp(clk)
-mpp21         21       gpio, ge0(rxd5), ge1(rxd3), lcd(d21), mem(bat)
+mpp21         21       gpio, ge0(rxd5), ge1(rxd3), lcd(d21), dram(bat)
 mpp22         22       gpio, ge0(rxd6), ge1(rxctl), lcd(d22), sata0(prsnt)
 mpp23         23       gpio, ge0(rxd7), ge1(rxclk), lcd(d23), sata1(prsnt)
-mpp24         24       gpio, lcd(hsync), sata1(prsnt), nf(bootcs-re), tdm(rst)
-mpp25         25       gpio, lcd(vsync), sata0(prsnt), nf(bootcs-we), tdm(pclk)
-mpp26         26       gpio, lcd(clk), tdm(fsync), vdd(cpu1-pd)
+mpp24         24       gpio, lcd(hsync), sata1(prsnt), tdm(rst)
+mpp25         25       gpio, lcd(vsync), sata0(prsnt), tdm(pclk)
+mpp26         26       gpio, lcd(clk), tdm(fsync)
 mpp27         27       gpio, lcd(e), tdm(dtx), ptp(trig)
 mpp28         28       gpio, lcd(pwm), tdm(drx), ptp(evreq)
-mpp29         29       gpio, lcd(ref-clk), tdm(int0), ptp(clk), vdd(cpu0-pd)
+mpp29         29       gpio, lcd(ref-clk), tdm(int0), ptp(clk)
 mpp30         30       gpio, tdm(int1), sd0(clk)
-mpp31         31       gpio, tdm(int2), sd0(cmd), vdd(cpu0-pd)
-mpp32         32       gpio, tdm(int3), sd0(d0), vdd(cpu1-pd)
-mpp33         33       gpio, tdm(int4), sd0(d1), mem(bat)
-mpp34         34       gpio, tdm(int5), sd0(d2), sata0(prsnt)
+mpp31         31       gpio, tdm(int2), sd0(cmd)
+mpp32         32       gpio, tdm(int3), sd0(d0)
+mpp33         33       gpio, tdm(int4), sd0(d1), dram(bat), dram(vttctrl)
+mpp34         34       gpio, tdm(int5), sd0(d2), sata0(prsnt), dram(deccerr)
 mpp35         35       gpio, tdm(int6), sd0(d3), sata1(prsnt)
-mpp36         36       gpio, spi(mosi)
-mpp37         37       gpio, spi(miso)
-mpp38         38       gpio, spi(sck)
-mpp39         39       gpio, spi(cs0)
-mpp40         40       gpio, spi(cs1), uart2(cts), lcd(vga-hsync), vdd(cpu1-pd),
-                       pcie(clkreq0)
-mpp41         41       gpio, spi(cs2), uart2(rts), lcd(vga-vsync), sata1(prsnt),
-                       pcie(clkreq1)
-mpp42         42       gpio, uart2(rxd), uart0(cts), tdm(int7), tdm-1(timer),
-                       vdd(cpu0-pd)
-mpp43         43       gpio, uart2(txd), uart0(rts), spi(cs3), pcie(rstout),
-                       vdd(cpu2-3-pd){1}
-mpp44         44       gpio, uart2(cts), uart3(rxd), spi(cs4), pcie(clkreq2),
-                       mem(bat)
-mpp45         45       gpio, uart2(rts), uart3(txd), spi(cs5), sata1(prsnt)
-mpp46         46       gpio, uart3(rts), uart1(rts), spi(cs6), sata0(prsnt)
-mpp47         47       gpio, uart3(cts), uart1(cts), spi(cs7), pcie(clkreq3),
-                       ref(clkout)
-mpp48         48       gpio, tclk, dev(burst/last)
+mpp36         36       gpio, spi0(mosi)
+mpp37         37       gpio, spi0(miso)
+mpp38         38       gpio, spi0(sck)
+mpp39         39       gpio, spi0(cs0)
+mpp40         40       gpio, spi0(cs1), uart2(cts), lcd(vga-hsync), pcie(clkreq0),
+                       spi1(cs1)
+mpp41         41       gpio, spi0(cs2), uart2(rts), lcd(vga-vsync), sata1(prsnt),
+                       pcie(clkreq1), spi1(cs2)
+mpp42         42       gpio, uart2(rxd), uart0(cts), tdm(int7), tdm(timer)
+mpp43         43       gpio, uart2(txd), uart0(rts), spi0(cs3), pcie(rstout),
+                       spi1(cs3)
+mpp44         44       gpio, uart2(cts), uart3(rxd), spi0(cs4), pcie(clkreq2),
+                       dram(bat), spi1(cs4)
+mpp45         45       gpio, uart2(rts), uart3(txd), spi0(cs5), sata1(prsnt),
+                       spi1(cs5), dram(vttctrl)
+mpp46         46       gpio, uart3(rts), uart1(rts), spi0(cs6), sata0(prsnt),
+                       spi1(cs6)
+mpp47         47       gpio, uart3(cts), uart1(cts), spi0(cs7), pcie(clkreq3),
+                       ref(clkout), spi1(cs7)
+mpp48         48       gpio, dev(clkout), dev(burst/last), nand(rb)
 
 * Marvell Armada XP (mv78260 and mv78460 only)
 
@@ -84,9 +85,9 @@ mpp51         51       gpio, dev(ad16)
 mpp52         52       gpio, dev(ad17)
 mpp53         53       gpio, dev(ad18)
 mpp54         54       gpio, dev(ad19)
-mpp55         55       gpio, dev(ad20), vdd(cpu0-pd)
-mpp56         56       gpio, dev(ad21), vdd(cpu1-pd)
-mpp57         57       gpio, dev(ad22), vdd(cpu2-3-pd){1}
+mpp55         55       gpio, dev(ad20)
+mpp56         56       gpio, dev(ad21)
+mpp57         57       gpio, dev(ad22)
 mpp58         58       gpio, dev(ad23)
 mpp59         59       gpio, dev(ad24)
 mpp60         60       gpio, dev(ad25)
@@ -96,6 +97,3 @@ mpp63         63       gpio, dev(ad28)
 mpp64         64       gpio, dev(ad29)
 mpp65         65       gpio, dev(ad30)
 mpp66         66       gpio, dev(ad31)
-
-Notes:
-* {1} vdd(cpu2-3-pd) only available on mv78460.
diff --git a/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt b/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt
new file mode 100644
index 000000000000..df0309c57505
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/nxp,lpc1850-scu.txt
@@ -0,0 +1,57 @@
+NXP LPC18xx/43xx SCU pin controller Device Tree Bindings
+--------------------------------------------------------
+
+Required properties:
+- compatible		: Should be "nxp,lpc1850-scu"
+- reg			: Address and length of the register set for the device
+- clocks		: Clock specifier (see clock bindings for details)
+
+The lpc1850-scu driver uses the generic pin multiplexing and generic pin
+configuration documented in pinctrl-bindings.txt.
+
+The following generic nodes are supported:
+ - function
+ - pins
+ - bias-disable
+ - bias-pull-up
+ - bias-pull-down
+ - drive-strength
+ - input-enable
+ - input-disable
+ - input-schmitt-enable
+ - input-schmitt-disable
+ - slew-rate
+
+Not all pins support all properties so either refer to the NXP 1850/4350
+user manual or the pin table in the pinctrl-lpc18xx driver for supported
+pin properties.
+
+Example:
+pinctrl: pinctrl@40086000 {
+	compatible = "nxp,lpc1850-scu";
+	reg = <0x40086000 0x1000>;
+	clocks = <&ccu1 CLK_CPU_SCU>;
+
+	i2c0_pins: i2c0-pins {
+		i2c0_pins_cfg {
+			pins = "i2c0_scl", "i2c0_sda";
+			function = "i2c0";
+			input-enable;
+		};
+	};
+
+	uart0_pins: uart0-pins {
+		uart0_rx_cfg {
+			pins = "pf_11";
+			function = "uart0";
+			bias-disable;
+			input-enable;
+		};
+
+		uart0_tx_cfg {
+			pins = "pf_10";
+			function = "uart0";
+			bias-disable;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt
new file mode 100644
index 000000000000..eecf028ff485
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-atlas7.txt
@@ -0,0 +1,109 @@
+CSR SiRFatlas7 pinmux controller
+
+Required properties:
+- compatible	: "sirf,atlas7-ioc"
+- reg		: Address range of the pinctrl registers
+
+For example, pinctrl might have properties like the following:
+	pinctrl: ioc@18880000 {
+			compatible = "sirf,atlas7-ioc";
+			reg = <0x18880000 0x1000>;
+
+			a_ac97_pmx: ac97@0 {
+				ac97 {
+					groups = "audio_ac97_grp";
+					function = "audio_ac97";
+				};
+			};
+
+			...
+
+			sd2_pmx: sd2@0 {
+				sd2 {
+					groups = "sd2_grp0";
+					function = "sd2";
+				};
+			};
+
+			...
+
+
+			sample0_cfg: sample0@0 {
+				sample0 {
+					pins = "ldd_0", "ldd_1";
+					bias-pull-up;
+				};
+			};
+
+			sample1_cfg: sample1@0 {
+				sample1 {
+					pins = "ldd_2", "ldd_3";
+					input-schmitt-enable;
+				};
+			};
+
+			sample2_cfg: sample2@0 {
+				sample2 {
+					groups = "uart4_nopause_grp";
+					bias-pull-down;
+				};
+			};
+
+			sample3_cfg: sample3@0 {
+				sample3 {
+					pins = "ldd_4", "ldd_5";
+					drive-strength = <2>;
+				};
+			};
+	};
+
+Please refer to pinctrl-bindings.txt in this directory for details of the common
+pinctrl bindings used by client devices.
+
+SiRFatlas7's pinmux nodes act as a container for an abitrary number of subnodes.
+Each of these subnodes represents some desired configuration for a group of pins.
+
+Required subnode-properties:
+- groups : An array of strings. Each string contains the name of a group.
+- function: A string containing the name of the function to mux to the
+  group.
+
+  Valid values for group and function names can be found from looking at the
+  group and function arrays in driver files:
+  drivers/pinctrl/pinctrl-sirf.c
+
+For example, pinctrl might have subnodes like the following:
+	sd0_pmx: sd0@0 {
+		sd0 {
+			groups = "sd0_grp";
+			function = "sd0";
+		};
+	};
+
+	sd1_pmx0: sd1@0 {
+		sd1 {
+			groups = "sd1_grp0";
+			function = "sd1_m0";
+		};
+	};
+
+	sd1_pmx1: sd1@1 {
+		sd1 {
+			groups = "sd1_grp1";
+			function = "sd1_m1";
+		};
+	};
+
+For a specific board, if it wants to use sd1,
+it can add the following to its board-specific .dts file.
+sd1: sd@0x12340000 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&sd1_pmx0>;
+}
+
+or
+
+sd1: sd@0x12340000 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&sd1_pmx1>;
+}
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
index 5868a0f7255d..0480bc31bfd7 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt65xx.txt
@@ -3,9 +3,11 @@
 The Mediatek's Pin controller is used to control SoC pins.
 
 Required properties:
-- compatible: value should be either of the following.
+- compatible: value should be one of the following.
     (a) "mediatek,mt8135-pinctrl", compatible with mt8135 pinctrl.
-- mediatek,pctl-regmap: Should be a phandle of the syscfg node.
+    (b) "mediatek,mt8173-pinctrl", compatible with mt8173 pinctrl.
+    (c) "mediatek,mt6397-pinctrl", compatible with mt6397 pinctrl.
+    (d) "mediatek,mt8127-pinctrl", compatible with mt8127 pinctrl.
 - pins-are-numbered: Specify the subnodes are using numbered pinmux to
   specify pins.
 - gpio-controller : Marks the device node as a gpio controller.
@@ -24,6 +26,9 @@ Required properties:
             Only the following flags are supported:
             0 - GPIO_ACTIVE_HIGH
             1 - GPIO_ACTIVE_LOW
+
+Optional properties:
+- mediatek,pctl-regmap: Should be a phandle of the syscfg node.
 - reg: physicall address base for EINT registers
 - interrupt-controller: Marks the device node as an interrupt controller
 - #interrupt-cells: Should be two.
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
new file mode 100644
index 000000000000..77aa11790163
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
@@ -0,0 +1,90 @@
+Qualcomm MSM8660 TLMM block
+
+Required properties:
+- compatible: "qcom,msm8660-pinctrl"
+- reg: Should be the base address and length of the TLMM block.
+- interrupts: Should be the parent IRQ of the TLMM block.
+- interrupt-controller: Marks the device node as an interrupt controller.
+- #interrupt-cells: Should be two.
+- gpio-controller: Marks the device node as a GPIO controller.
+- #gpio-cells : Should be two.
+                The first cell is the gpio pin number and the
+                second cell is used for optional parameters.
+
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+
+Qualcomm's pin configuration nodes act as a container for an arbitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin, a group, or a list of pins or groups. This configuration can include the
+mux function to select on those pin(s)/group(s), and various pin configuration
+parameters, such as pull-up, drive strength, etc.
+
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+
+
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+
+ pins, function, bias-disable, bias-pull-down, bias-pull,up, drive-strength,
+ output-low, output-high.
+
+Non-empty subnodes must specify the 'pins' property.
+
+Valid values for pins are:
+  gpio0-gpio172, sdc3_clk, sdc3_cmd, sdc3_data sdc4_clk, sdc4_cmd, sdc4_data
+
+Valid values for function are:
+  gpio, cam_mclk, dsub, ext_gps, gp_clk_0a, gp_clk_0b, gp_clk_1a, gp_clk_1b,
+  gp_clk_2a, gp_clk_2b, gp_mn, gsbi1, gsbi1_spi_cs1_n, gsbi1_spi_cs2a_n,
+  gsbi1_spi_cs2b_n, gsbi1_spi_cs3_n, gsbi2, gsbi2_spi_cs1_n, gsbi2_spi_cs2_n,
+  gsbi2_spi_cs3_n, gsbi3, gsbi3_spi_cs1_n, gsbi3_spi_cs2_n, gsbi3_spi_cs3_n,
+  gsbi4, gsbi5, gsbi6, gsbi7, gsbi8, gsbi9, gsbi10, gsbi11, gsbi12, hdmi, i2s,
+  lcdc, mdp_vsync, mi2s, pcm, ps_hold, sdc1, sdc2, sdc5, tsif1, tsif2, usb_fs1,
+  usb_fs1_oe_n, usb_fs2, usb_fs2_oe_n, vfe, vsens_alarm,
+
+Example:
+
+	msmgpio: pinctrl@800000 {
+		compatible = "qcom,msm8660-pinctrl";
+		reg = <0x800000 0x4000>;
+
+		gpio-controller;
+		#gpio-cells = <2>;
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		interrupts = <0 16 0x4>;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&gsbi12_uart>;
+
+		gsbi12_uart: gsbi12-uart {
+			mux {
+				pins = "gpio117", "gpio118";
+				function = "gsbi12";
+			};
+
+			tx {
+				pins = "gpio118";
+				drive-strength = <8>;
+				bias-disable;
+			};
+
+			rx {
+				pins = "gpio117";
+				drive-strength = <2>;
+				bias-pull-up;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
index bfe72ec055e3..51cee44fc140 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
@@ -16,7 +16,9 @@ Required Properties:
     - "renesas,pfc-r8a7778": for R8A7778 (R-Mobile M1) compatible pin-controller.
     - "renesas,pfc-r8a7779": for R8A7779 (R-Car H1) compatible pin-controller.
     - "renesas,pfc-r8a7790": for R8A7790 (R-Car H2) compatible pin-controller.
-    - "renesas,pfc-r8a7791": for R8A7791 (R-Car M2) compatible pin-controller.
+    - "renesas,pfc-r8a7791": for R8A7791 (R-Car M2-W) compatible pin-controller.
+    - "renesas,pfc-r8a7793": for R8A7793 (R-Car M2-N) compatible pin-controller.
+    - "renesas,pfc-r8a7794": for R8A7794 (R-Car E2) compatible pin-controller.
     - "renesas,pfc-sh73a0": for SH73A0 (SH-Mobile AG5) compatible pin-controller.
 
   - reg: Base address and length of each memory resource used by the pin
diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
index 388b213249fd..391ef4be8d50 100644
--- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.txt
@@ -21,14 +21,15 @@ defined as gpio sub-nodes of the pinmux controller.
 Required properties for iomux controller:
   - compatible: one of "rockchip,rk2928-pinctrl", "rockchip,rk3066a-pinctrl"
 		       "rockchip,rk3066b-pinctrl", "rockchip,rk3188-pinctrl"
-		       "rockchip,rk3288-pinctrl"
+		       "rockchip,rk3288-pinctrl", "rockchip,rk3368-pinctrl"
   - rockchip,grf: phandle referencing a syscon providing the
 	 "general register files"
 
 Optional properties for iomux controller:
   - rockchip,pmu: phandle referencing a syscon providing the pmu registers
 	 as some SoCs carry parts of the iomux controller registers there.
-	 Required for at least rk3188 and rk3288.
+	 Required for at least rk3188 and rk3288. On the rk3368 this should
+	 point to the PMUGRF syscon.
 
 Deprecated properties for iomux controller:
   - reg: first element is the general register space of the iomux controller
diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.txt
index b7b55a964f65..f488b0f77406 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.txt
@@ -45,8 +45,9 @@ to specify in a pinconf subnode:
 
  Valid values for groups are:
    ethernet0_0_grp, ethernet1_0_grp, mdio0_0_grp, mdio1_0_grp,
-   qspi0_0_grp, qspi1_0_grp, qspi_fbclk, qspi_cs1_grp, spi0_0_grp,
-   spi0_1_grp - spi0_2_grp, spi1_0_grp - spi1_3_grp, sdio0_0_grp - sdio0_2_grp,
+   qspi0_0_grp, qspi1_0_grp, qspi_fbclk, qspi_cs1_grp, spi0_0_grp - spi0_2_grp,
+   spi0_X_ssY (X=0..2, Y=0..2), spi1_0_grp - spi1_3_grp,
+   spi1_X_ssY (X=0..3, Y=0..2), sdio0_0_grp - sdio0_2_grp,
    sdio1_0_grp - sdio1_3_grp, sdio0_emio_wp, sdio0_emio_cd, sdio1_emio_wp,
    sdio1_emio_cd, smc0_nor, smc0_nor_cs1_grp, smc0_nor_addr25_grp, smc0_nand,
    can0_0_grp - can0_10_grp, can1_0_grp - can1_11_grp, uart0_0_grp - uart0_10_grp,
@@ -59,7 +60,7 @@ to specify in a pinconf subnode:
 
  Valid values for function are:
    ethernet0, ethernet1, mdio0, mdio1, qspi0, qspi1, qspi_fbclk, qspi_cs1,
-   spi0, spi1, sdio0, sdio0_pc, sdio0_cd, sdio0_wp,
+   spi0, spi0_ss, spi1, spi1_ss, sdio0, sdio0_pc, sdio0_cd, sdio0_wp,
    sdio1, sdio1_pc, sdio1_cd, sdio1_wp,
    smc0_nor, smc0_nor_cs1, smc0_nor_addr25, smc0_nand, can0, can1, uart0, uart1,
    i2c0, i2c1, ttc0, ttc1, swdt0, gpio0, usb0, usb1
diff --git a/Documentation/devicetree/bindings/power/bq24257.txt b/Documentation/devicetree/bindings/power/bq24257.txt
new file mode 100644
index 000000000000..5c9d3940d07c
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/bq24257.txt
@@ -0,0 +1,21 @@
+Binding for TI bq24257 Li-Ion Charger
+
+Required properties:
+- compatible: Should contain one of the following:
+ * "ti,bq24257"
+- reg:			   integer, i2c address of the device.
+- ti,battery-regulation-voltage: integer, maximum charging voltage in uV.
+- ti,charge-current:	   integer, maximum charging current in uA.
+- ti,termination-current:  integer, charge will be terminated when current in
+			   constant-voltage phase drops below this value (in uA).
+
+Example:
+
+bq24257 {
+	compatible = "ti,bq24257";
+	reg = <0x6a>;
+
+	ti,battery-regulation-voltage = <4200000>;
+	ti,charge-current = <1000000>;
+	ti,termination-current = <50000>;
+};
diff --git a/Documentation/devicetree/bindings/power/bq25890.txt b/Documentation/devicetree/bindings/power/bq25890.txt
new file mode 100644
index 000000000000..c9dd17d142ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/bq25890.txt
@@ -0,0 +1,46 @@
+Binding for TI bq25890 Li-Ion Charger
+
+Required properties:
+- compatible: Should contain one of the following:
+    * "ti,bq25890"
+- reg: integer, i2c address of the device.
+- ti,battery-regulation-voltage: integer, maximum charging voltage (in uV);
+- ti,charge-current: integer, maximum charging current (in uA);
+- ti,termination-current: integer, charge will be terminated when current in
+    constant-voltage phase drops below this value (in uA);
+- ti,precharge-current: integer, maximum charge current during precharge
+    phase (in uA);
+- ti,minimum-sys-voltage: integer, when battery is charging and it is below
+    minimum system voltage, the system will be regulated above
+    minimum-sys-voltage setting (in uV);
+- ti,boost-voltage: integer, VBUS voltage level in boost mode (in uV);
+- ti,boost-max-current: integer, maximum allowed current draw in boost mode
+    (in uA).
+
+Optional properties:
+- ti,boost-low-freq: boolean, if present boost mode frequency will be 500kHz,
+    otherwise 1.5MHz;
+- ti,use-ilim-pin: boolean, if present the ILIM resistor will be used and the
+    input current will be the lower between the resistor setting and the IINLIM
+    register setting;
+- ti,thermal-regulation-threshold: integer, temperature above which the charge
+    current is lowered, to avoid overheating (in degrees Celsius). If omitted,
+    the default setting will be used (120 degrees);
+
+Example:
+
+bq25890 {
+        compatible = "ti,bq25890";
+        reg = <0x6a>;
+
+        ti,battery-regulation-voltage = <4200000>;
+        ti,charge-current = <1000000>;
+        ti,termination-current = <50000>;
+        ti,precharge-current = <128000>;
+        ti,minimum-sys-voltage = <3600000>;
+        ti,boost-voltage = <5000000>;
+        ti,boost-max-current = <1000000>;
+
+        ti,use-ilim-pin;
+        ti,thermal-regulation-threshold = <120>;
+};
diff --git a/Documentation/devicetree/bindings/power/opp.txt b/Documentation/devicetree/bindings/power/opp.txt
index 74499e5033fc..0d5e7c978121 100644
--- a/Documentation/devicetree/bindings/power/opp.txt
+++ b/Documentation/devicetree/bindings/power/opp.txt
@@ -1,8 +1,19 @@
-* Generic OPP Interface
+Generic OPP (Operating Performance Points) Bindings
+----------------------------------------------------
 
-SoCs have a standard set of tuples consisting of frequency and
-voltage pairs that the device will support per voltage domain. These
-are called Operating Performance Points or OPPs.
+Devices work at voltage-current-frequency combinations and some implementations
+have the liberty of choosing these. These combinations are called Operating
+Performance Points aka OPPs. This document defines bindings for these OPPs
+applicable across wide range of devices. For illustration purpose, this document
+uses CPU as a device.
+
+This document contain multiple versions of OPP binding and only one of them
+should be used per device.
+
+Binding 1: operating-points
+============================
+
+This binding only supports voltage-frequency pairs.
 
 Properties:
 - operating-points: An array of 2-tuples items, and each item consists
@@ -23,3 +34,432 @@ cpu@0 {
 		198000  850000
 	>;
 };
+
+
+Binding 2: operating-points-v2
+============================
+
+* Property: operating-points-v2
+
+Devices supporting OPPs must set their "operating-points-v2" property with
+phandle to a OPP table in their DT node. The OPP core will use this phandle to
+find the operating points for the device.
+
+Devices may want to choose OPP tables at runtime and so can provide a list of
+phandles here. But only *one* of them should be chosen at runtime. This must be
+accompanied by a corresponding "operating-points-names" property, to uniquely
+identify the OPP tables.
+
+If required, this can be extended for SoC vendor specfic bindings. Such bindings
+should be documented as Documentation/devicetree/bindings/power/<vendor>-opp.txt
+and should have a compatible description like: "operating-points-v2-<vendor>".
+
+Optional properties:
+- operating-points-names: Names of OPP tables (required if multiple OPP
+  tables are present), to uniquely identify them. The same list must be present
+  for all the CPUs which are sharing clock/voltage rails and hence the OPP
+  tables.
+
+* OPP Table Node
+
+This describes the OPPs belonging to a device. This node can have following
+properties:
+
+Required properties:
+- compatible: Allow OPPs to express their compatibility. It should be:
+  "operating-points-v2".
+
+- OPP nodes: One or more OPP nodes describing voltage-current-frequency
+  combinations. Their name isn't significant but their phandle can be used to
+  reference an OPP.
+
+Optional properties:
+- opp-shared: Indicates that device nodes using this OPP Table Node's phandle
+  switch their DVFS state together, i.e. they share clock/voltage/current lines.
+  Missing property means devices have independent clock/voltage/current lines,
+  but they share OPP tables.
+
+- status: Marks the OPP table enabled/disabled.
+
+
+* OPP Node
+
+This defines voltage-current-frequency combinations along with other related
+properties.
+
+Required properties:
+- opp-hz: Frequency in Hz
+
+Optional properties:
+- opp-microvolt: voltage in micro Volts.
+
+  A single regulator's voltage is specified with an array of size one or three.
+  Single entry is for target voltage and three entries are for <target min max>
+  voltages.
+
+  Entries for multiple regulators must be present in the same order as
+  regulators are specified in device's DT node.
+
+- opp-microamp: The maximum current drawn by the device in microamperes
+  considering system specific parameters (such as transients, process, aging,
+  maximum operating temperature range etc.) as necessary. This may be used to
+  set the most efficient regulator operating mode.
+
+  Should only be set if opp-microvolt is set for the OPP.
+
+  Entries for multiple regulators must be present in the same order as
+  regulators are specified in device's DT node. If this property isn't required
+  for few regulators, then this should be marked as zero for them. If it isn't
+  required for any regulator, then this property need not be present.
+
+- clock-latency-ns: Specifies the maximum possible transition latency (in
+  nanoseconds) for switching to this OPP from any other OPP.
+
+- turbo-mode: Marks the OPP to be used only for turbo modes. Turbo mode is
+  available on some platforms, where the device can run over its operating
+  frequency for a short duration of time limited by the device's power, current
+  and thermal limits.
+
+- opp-suspend: Marks the OPP to be used during device suspend. Only one OPP in
+  the table should have this.
+
+- status: Marks the node enabled/disabled.
+
+Example 1: Single cluster Dual-core ARM cortex A9, switch DVFS states together.
+
+/ {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a9";
+			reg = <0>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 0>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply0>;
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a9";
+			reg = <1>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 0>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply0>;
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+	};
+
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000 975000 985000>;
+			opp-microamp = <70000>;
+			clock-latency-ns = <300000>;
+			opp-suspend;
+		};
+		opp01 {
+			opp-hz = <1100000000>;
+			opp-microvolt = <980000 1000000 1010000>;
+			opp-microamp = <80000>;
+			clock-latency-ns = <310000>;
+		};
+		opp02 {
+			opp-hz = <1200000000>;
+			opp-microvolt = <1025000>;
+			clock-latency-ns = <290000>;
+			turbo-mode;
+		};
+	};
+};
+
+Example 2: Single cluster, Quad-core Qualcom-krait, switches DVFS states
+independently.
+
+/ {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "qcom,krait";
+			reg = <0>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 0>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply0>;
+			operating-points-v2 = <&cpu_opp_table>;
+		};
+
+		cpu@1 {
+			compatible = "qcom,krait";
+			reg = <1>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 1>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply1>;
+			operating-points-v2 = <&cpu_opp_table>;
+		};
+
+		cpu@2 {
+			compatible = "qcom,krait";
+			reg = <2>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 2>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply2>;
+			operating-points-v2 = <&cpu_opp_table>;
+		};
+
+		cpu@3 {
+			compatible = "qcom,krait";
+			reg = <3>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 3>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply3>;
+			operating-points-v2 = <&cpu_opp_table>;
+		};
+	};
+
+	cpu_opp_table: opp_table {
+		compatible = "operating-points-v2";
+
+		/*
+		 * Missing opp-shared property means CPUs switch DVFS states
+		 * independently.
+		 */
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000 975000 985000>;
+			opp-microamp = <70000>;
+			clock-latency-ns = <300000>;
+			opp-suspend;
+		};
+		opp01 {
+			opp-hz = <1100000000>;
+			opp-microvolt = <980000 1000000 1010000>;
+			opp-microamp = <80000>;
+			clock-latency-ns = <310000>;
+		};
+		opp02 {
+			opp-hz = <1200000000>;
+			opp-microvolt = <1025000>;
+			opp-microamp = <90000;
+			lock-latency-ns = <290000>;
+			turbo-mode;
+		};
+	};
+};
+
+Example 3: Dual-cluster, Dual-core per cluster. CPUs within a cluster switch
+DVFS state together.
+
+/ {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			reg = <0>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 0>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply0>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		cpu@1 {
+			compatible = "arm,cortex-a7";
+			reg = <1>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 0>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply0>;
+			operating-points-v2 = <&cluster0_opp>;
+		};
+
+		cpu@100 {
+			compatible = "arm,cortex-a15";
+			reg = <100>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 1>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply1>;
+			operating-points-v2 = <&cluster1_opp>;
+		};
+
+		cpu@101 {
+			compatible = "arm,cortex-a15";
+			reg = <101>;
+			next-level-cache = <&L2>;
+			clocks = <&clk_controller 1>;
+			clock-names = "cpu";
+			cpu-supply = <&cpu_supply1>;
+			operating-points-v2 = <&cluster1_opp>;
+		};
+	};
+
+	cluster0_opp: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000 975000 985000>;
+			opp-microamp = <70000>;
+			clock-latency-ns = <300000>;
+			opp-suspend;
+		};
+		opp01 {
+			opp-hz = <1100000000>;
+			opp-microvolt = <980000 1000000 1010000>;
+			opp-microamp = <80000>;
+			clock-latency-ns = <310000>;
+		};
+		opp02 {
+			opp-hz = <1200000000>;
+			opp-microvolt = <1025000>;
+			opp-microamp = <90000>;
+			clock-latency-ns = <290000>;
+			turbo-mode;
+		};
+	};
+
+	cluster1_opp: opp_table1 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp10 {
+			opp-hz = <1300000000>;
+			opp-microvolt = <1045000 1050000 1055000>;
+			opp-microamp = <95000>;
+			clock-latency-ns = <400000>;
+			opp-suspend;
+		};
+		opp11 {
+			opp-hz = <1400000000>;
+			opp-microvolt = <1075000>;
+			opp-microamp = <100000>;
+			clock-latency-ns = <400000>;
+		};
+		opp12 {
+			opp-hz = <1500000000>;
+			opp-microvolt = <1010000 1100000 1110000>;
+			opp-microamp = <95000>;
+			clock-latency-ns = <400000>;
+			turbo-mode;
+		};
+	};
+};
+
+Example 4: Handling multiple regulators
+
+/ {
+	cpus {
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			...
+
+			cpu-supply = <&cpu_supply0>, <&cpu_supply1>, <&cpu_supply2>;
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+	};
+
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000>, /* Supply 0 */
+					<960000>, /* Supply 1 */
+					<960000>; /* Supply 2 */
+			opp-microamp =  <70000>,  /* Supply 0 */
+					<70000>,  /* Supply 1 */
+					<70000>;  /* Supply 2 */
+			clock-latency-ns = <300000>;
+		};
+
+		/* OR */
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
+					<960000 965000 975000>, /* Supply 1 */
+					<960000 965000 975000>; /* Supply 2 */
+			opp-microamp =  <70000>,		/* Supply 0 */
+					<70000>,		/* Supply 1 */
+					<70000>;		/* Supply 2 */
+			clock-latency-ns = <300000>;
+		};
+
+		/* OR */
+
+		opp00 {
+			opp-hz = <1000000000>;
+			opp-microvolt = <970000 975000 985000>, /* Supply 0 */
+					<960000 965000 975000>, /* Supply 1 */
+					<960000 965000 975000>; /* Supply 2 */
+			opp-microamp =  <70000>,		/* Supply 0 */
+					<0>,			/* Supply 1 doesn't need this */
+					<70000>;		/* Supply 2 */
+			clock-latency-ns = <300000>;
+		};
+	};
+};
+
+Example 5: Multiple OPP tables
+
+/ {
+	cpus {
+		cpu@0 {
+			compatible = "arm,cortex-a7";
+			...
+
+			cpu-supply = <&cpu_supply>
+			operating-points-v2 = <&cpu0_opp_table_slow>, <&cpu0_opp_table_fast>;
+			operating-points-names = "slow", "fast";
+		};
+	};
+
+	cpu0_opp_table_slow: opp_table_slow {
+		compatible = "operating-points-v2";
+		status = "okay";
+		opp-shared;
+
+		opp00 {
+			opp-hz = <600000000>;
+			...
+		};
+
+		opp01 {
+			opp-hz = <800000000>;
+			...
+		};
+	};
+
+	cpu0_opp_table_fast: opp_table_fast {
+		compatible = "operating-points-v2";
+		status = "okay";
+		opp-shared;
+
+		opp10 {
+			opp-hz = <1000000000>;
+			...
+		};
+
+		opp11 {
+			opp-hz = <1100000000>;
+			...
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/power/rt9455_charger.txt b/Documentation/devicetree/bindings/power/rt9455_charger.txt
new file mode 100644
index 000000000000..5d9ad5cf2c5a
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/rt9455_charger.txt
@@ -0,0 +1,48 @@
+Binding for Richtek rt9455 battery charger
+
+Required properties:
+- compatible:				it should contain one of the following:
+					"richtek,rt9455".
+- reg:					integer, i2c address of the device.
+- interrupt-parent:			the phandle for the interrupt controller that
+					services interrupts for this device.
+- interrupts:				interrupt mapping for GPIO IRQ, it should be
+					configured with IRQ_TYPE_LEVEL_LOW flag.
+- richtek,output-charge-current:	integer, output current from the charger to the
+					battery, in uA.
+- richtek,end-of-charge-percentage:	integer, percent of the output charge current.
+					When the current in constant-voltage phase drops
+					below output_charge_current x end-of-charge-percentage,
+					charge is terminated.
+- richtek,battery-regulation-voltage:	integer, maximum battery voltage in uV.
+- richtek,boost-output-voltage:		integer, maximum voltage provided to consumer
+					devices, when the charger is in boost mode, in uV.
+
+Optional properties:
+- richtek,min-input-voltage-regulation: integer, input voltage level in uV, used to
+					decrease voltage level when the over current
+					of the input power source occurs.
+					This prevents input voltage drop due to insufficient
+					current provided by the power source.
+					Default: 4500000 uV (4.5V)
+- richtek,avg-input-current-regulation: integer, input current value in uA drained by the
+					charger from the power source.
+					Default: 500000 uA (500mA)
+
+Example:
+
+rt9455@22 {
+	compatible = "richtek,rt9455";
+	reg = <0x22>;
+
+	interrupt-parent = <&gpio1>;
+	interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
+
+	richtek,output-charge-current	    = <500000>;
+	richtek,end-of-charge-percentage    = <10>;
+	richtek,battery-regulation-voltage  = <4200000>;
+	richtek,boost-output-voltage	    = <5050000>;
+
+	richtek,min-input-voltage-regulation = <4500000>;
+	richtek,avg-input-current-regulation = <500000>;
+};
diff --git a/Documentation/devicetree/bindings/power_supply/max17042_battery.txt b/Documentation/devicetree/bindings/power_supply/max17042_battery.txt
index 5bc9b685cf8a..3f3894aaeebc 100644
--- a/Documentation/devicetree/bindings/power_supply/max17042_battery.txt
+++ b/Documentation/devicetree/bindings/power_supply/max17042_battery.txt
@@ -9,10 +9,23 @@ Optional properties :
                          (datasheet-recommended value is 10000).
    Defining this property enables current-sense functionality.
 
+Optional threshold properties :
+ If skipped the condition won't be reported.
+ - maxim,cold-temp :      Temperature threshold to report battery
+                          as cold (in tenths of degree Celsius).
+ - maxim,over-heat-temp : Temperature threshold to report battery
+                          as over heated (in tenths of degree Celsius).
+ - maxim,dead-volt :      Voltage threshold to report battery
+                          as dead (in mV).
+ - maxim,over-volt :      Voltage threshold to report battery
+                          as over voltage (in mV).
+
 Example:
 
 	battery-charger@36 {
 		compatible = "maxim,max17042";
 		reg = <0x36>;
 		maxim,rsns-microohm = <10000>;
+		maxim,over-heat-temp = <600>;
+		maxim,over-volt = <4300>;
 	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/fman.txt b/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
index edda55f74004..1fc5328c0651 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/fman.txt
@@ -189,6 +189,19 @@ PROPERTIES
 		Definition: There is one reg region describing the port
 		configuration registers.
 
+- fsl,fman-10g-port
+		Usage: optional
+		Value type: boolean
+		Definition: The default port rate is 1G.
+		If this property exists, the port is s 10G port.
+
+- fsl,fman-best-effort-port
+		Usage: optional
+		Value type: boolean
+		Definition: Can be defined only if 10G-support is set.
+		This property marks a best-effort 10G port (10G port that
+		may not be capable of line rate).
+
 EXAMPLE
 
 port@a8000 {
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/guts.txt b/Documentation/devicetree/bindings/powerpc/fsl/guts.txt
index 7f150b5012cc..b71b2039e112 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/guts.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/guts.txt
@@ -9,6 +9,11 @@ Required properties:
 
  - compatible : Should define the compatible device type for
    global-utilities.
+   Possible compatibles:
+	"fsl,qoriq-device-config-1.0"
+	"fsl,qoriq-device-config-2.0"
+	"fsl,<chip>-device-config"
+	"fsl,<chip>-guts"
  - reg : Offset and length of the register set for the device.
 
 Recommended properties:
diff --git a/Documentation/devicetree/bindings/regulator/max8973-regulator.txt b/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
index 4f15d8a1bfd0..55efb24e5683 100644
--- a/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/max8973-regulator.txt
@@ -2,12 +2,30 @@
 
 Required properties:
 
-- compatible:	must be "maxim,max8973"
+- compatible:	must be one of following:
+			"maxim,max8973"
+			"maxim,max77621".
 - reg:		the i2c slave address of the regulator. It should be 0x1b.
 
 Any standard regulator properties can be used to configure the single max8973
 DCDC.
 
+Optional properties:
+
+-maxim,externally-enable: boolean, externally control the regulator output
+		enable/disable.
+-maxim,enable-gpio: GPIO for enable control. If the valid GPIO is provided
+		then externally enable control will be considered.
+-maxim,dvs-gpio: GPIO which is connected to DVS pin of device.
+-maxim,dvs-default-state: Default state of GPIO during initialisation.
+		1 for HIGH and 0 for LOW.
+-maxim,enable-remote-sense: boolean, enable reote sense.
+-maxim,enable-falling-slew-rate: boolean, enable falling slew rate.
+-maxim,enable-active-discharge: boolean: enable active discharge.
+-maxim,enable-frequency-shift: boolean, enable 9% frequency shift.
+-maxim,enable-bias-control: boolean, enable bias control. By enabling this
+		startup delay can be reduce to 20us from 220us.
+
 Example:
 
 	max8973@1b {
diff --git a/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
new file mode 100644
index 000000000000..75b4604bad07
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/qcom,spmi-regulator.txt
@@ -0,0 +1,121 @@
+Qualcomm SPMI Regulators
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+			"qcom,pm8841-regulators"
+			"qcom,pm8916-regulators"
+			"qcom,pm8941-regulators"
+
+- interrupts:
+	Usage: optional
+	Value type: <prop-encoded-array>
+	Definition: List of OCP interrupts.
+
+- interrupt-names:
+	Usage: required if 'interrupts' property present
+	Value type: <string-array>
+	Definition: List of strings defining the names of the
+		    interrupts in the 'interrupts' property 1-to-1.
+		    Supported values are "ocp-<regulator_name>", where
+		    <regulator_name> corresponds to a voltage switch
+		    type regulator.
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_s5-supply:
+- vdd_s6-supply:
+- vdd_s7-supply:
+- vdd_s8-supply:
+	Usage: optional (pm8841 only)
+	Value type: <phandle>
+	Definition: Reference to regulator supplying the input pin, as
+		    described in the data sheet.
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_l1_l3-supply:
+- vdd_l2-supply:
+- vdd_l4_l5_l6-supply:
+- vdd_l7-supply:
+- vdd_l8_l11_l14_l15_l16-supply:
+- vdd_l9_l10_l12_l13_l17_l18-supply:
+	Usage: optional (pm8916 only)
+	Value type: <phandle>
+	Definition: Reference to regulator supplying the input pin, as
+		    described in the data sheet.
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_l1_l3-supply:
+- vdd_l2_lvs_1_2_3-supply:
+- vdd_l4_l11-supply:
+- vdd_l5_l7-supply:
+- vdd_l6_l12_l14_l15-supply:
+- vdd_l8_l16_l18_19-supply:
+- vdd_l9_l10_l17_l22-supply:
+- vdd_l13_l20_l23_l24-supply:
+- vdd_l21-supply:
+- vin_5vs-supply:
+	Usage: optional (pm8941 only)
+	Value type: <phandle>
+	Definition: Reference to regulator supplying the input pin, as
+		    described in the data sheet.
+
+
+The regulator node houses sub-nodes for each regulator within the device. Each
+sub-node is identified using the node's name, with valid values listed for each
+of the PMICs below.
+
+pm8841:
+	s1, s2, s3, s4, s5, s6, s7, s8
+
+pm8916:
+	s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13,
+	l14, l15, l16, l17, l18
+
+pm8941:
+	s1, s2, s3, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14,
+	l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2, lvs3,
+	mvs1, mvs2
+
+The content of each sub-node is defined by the standard binding for regulators -
+see regulator.txt - with additional custom properties described below:
+
+- regulator-initial-mode:
+	Usage: optional
+	Value type: <u32>
+	Descrption: 1 = Set initial mode to high power mode (HPM), also referred
+		    to as NPM.  HPM consumes more ground current than LPM, but
+		    it can source significantly higher load current. HPM is not
+		    available on boost type regulators. For voltage switch type
+		    regulators, HPM implies that over current protection and
+		    soft start are active all the time. 0 = Set initial mode to
+		    low power mode (LPM).
+
+Example:
+
+	regulators {
+		compatible = "qcom,pm8941-regulators";
+		vdd_l1_l3-supply = <&s1>;
+
+		s1: s1 {
+			regulator-min-microvolt = <1300000>;
+			regulator-max-microvolt = <1400000>;
+		};
+
+		...
+
+		l1: l1 {
+			regulator-min-microvolt = <1225000>;
+			regulator-max-microvolt = <1300000>;
+		};
+
+		....
+	};
diff --git a/Documentation/devicetree/bindings/regulator/regulator.txt b/Documentation/devicetree/bindings/regulator/regulator.txt
index abb26b58c83e..db88feb28c03 100644
--- a/Documentation/devicetree/bindings/regulator/regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/regulator.txt
@@ -7,18 +7,20 @@ Optional properties:
 - regulator-microvolt-offset: Offset applied to voltages to compensate for voltage drops
 - regulator-min-microamp: smallest current consumers may set
 - regulator-max-microamp: largest current consumers may set
+- regulator-input-current-limit-microamp: maximum input current regulator allows
 - regulator-always-on: boolean, regulator should never be disabled
 - regulator-boot-on: bootloader/firmware enabled regulator
 - regulator-allow-bypass: allow the regulator to go into bypass mode
 - <name>-supply: phandle to the parent supply/regulator node
 - regulator-ramp-delay: ramp delay for regulator(in uV/uS)
   For hardware which supports disabling ramp rate, it should be explicitly
-  intialised to zero (regulator-ramp-delay = <0>) for disabling ramp delay.
+  initialised to zero (regulator-ramp-delay = <0>) for disabling ramp delay.
 - regulator-enable-ramp-delay: The time taken, in microseconds, for the supply
   rail to reach the target voltage, plus/minus whatever tolerance the board
   design requires. This property describes the total system ramp time
   required due to the combination of internal ramping of the regulator itself,
   and board design issues such as trace capacitance and load on the supply.
+- regulator-soft-start: Enable soft start so that voltage ramps slowly
 - regulator-state-mem sub-root node for Suspend-to-RAM mode
   : suspend to memory, the device goes to sleep, but all data stored in memory,
   only some external interrupt can wake the device.
@@ -37,6 +39,9 @@ Optional properties:
 - regulator-initial-mode: initial operating mode. The set of possible operating
   modes depends on the capabilities of every hardware so each device binding
   documentation explains which values the regulator supports.
+- regulator-system-load: Load in uA present on regulator that is not captured by
+  any consumer request.
+- regulator-pull-down: Enable pull down resistor when the regulator is disabled.
 
 Deprecated properties:
 - regulator-compatible: If a regulator chip contains multiple
diff --git a/Documentation/devicetree/bindings/rtc/abracon,abx80x.txt b/Documentation/devicetree/bindings/rtc/abracon,abx80x.txt
new file mode 100644
index 000000000000..be789685a1c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/abracon,abx80x.txt
@@ -0,0 +1,30 @@
+Abracon ABX80X I2C ultra low power RTC/Alarm chip
+
+The Abracon ABX80X family consist of the ab0801, ab0803, ab0804, ab0805, ab1801,
+ab1803, ab1804 and ab1805. The ab0805 is the superset of ab080x and the ab1805
+is the superset of ab180x.
+
+Required properties:
+
+ - "compatible": should one of:
+        "abracon,abx80x"
+        "abracon,ab0801"
+        "abracon,ab0803"
+        "abracon,ab0804"
+        "abracon,ab0805"
+        "abracon,ab1801"
+        "abracon,ab1803"
+        "abracon,ab1804"
+        "abracon,ab1805"
+	Using "abracon,abx80x" will enable chip autodetection.
+ - "reg": I2C bus address of the device
+
+Optional properties:
+
+The abx804 and abx805 have a trickle charger that is able to charge the
+connected battery or supercap. Both the following properties have to be defined
+and valid to enable charging:
+
+ - "abracon,tc-diode": should be "standard" (0.6V) or "schottky" (0.3V)
+ - "abracon,tc-resistor": should be <0>, <3>, <6> or <11>. 0 disables the output
+                          resistor, the other values are in ohm.
diff --git a/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt b/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt
new file mode 100644
index 000000000000..73407f502e4e
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/rtc-st-lpc.txt
@@ -0,0 +1,25 @@
+STMicroelectronics Low Power Controller (LPC) - RTC
+===================================================
+
+LPC currently supports Watchdog OR Real Time Clock functionality.
+
+[See: ../watchdog/st_lpc_wdt.txt for Watchdog options]
+
+Required properties
+
+- compatible 	: Must be one of: "st,stih407-lpc" "st,stih416-lpc"
+				  "st,stih415-lpc" "st,stid127-lpc"
+- reg		: LPC registers base address + size
+- interrupts    : LPC interrupt line number and associated flags
+- clocks	: Clock used by LPC device (See: ../clock/clock-bindings.txt)
+- st,lpc-mode	: The LPC can run either one of two modes ST_LPC_MODE_RTC [0] or
+		  ST_LPC_MODE_WDT [1].  One (and only one) mode must be
+		  selected.
+
+Example:
+	lpc@fde05000 {
+		compatible	= "st,stih407-lpc";
+		reg		= <0xfde05000 0x1000>;
+		clocks 		= <&clk_s_d3_flexgen CLK_LPC_0>;
+		st,lpc-mode	= <ST_LPC_MODE_RTC>;
+	};
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index ae73bb0e9ad9..7534d46e9ad8 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -29,6 +29,7 @@ Required properties:
     - "renesas,scifa" for generic SCIFA compatible UART.
     - "renesas,scifb" for generic SCIFB compatible UART.
     - "renesas,hscif" for generic HSCIF compatible UART.
+    - "renesas,sci" for generic SCI compatible UART.
 
     When compatible with the generic version, nodes must list the
     SoC-specific version corresponding to the platform first followed by the
diff --git a/Documentation/devicetree/bindings/soc/fsl/qman-portals.txt b/Documentation/devicetree/bindings/soc/fsl/qman-portals.txt
index 48c4dae5d6f9..47e46ccbc170 100644
--- a/Documentation/devicetree/bindings/soc/fsl/qman-portals.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/qman-portals.txt
@@ -47,7 +47,7 @@ PROPERTIES
 
 	For additional details about the PAMU/LIODN binding(s) see pamu.txt
 
-- fsl,qman-channel-id
+- cell-index
 	Usage:		Required
 	Value type:	<u32>
 	Definition:	The hardware index of the channel. This can also be
@@ -136,7 +136,7 @@ The example below shows a (P4080) QMan portals container/bus node with two porta
 			reg = <0x4000 0x4000>, <0x101000 0x1000>;
 			interrupts = <106 2 0 0>;
 			fsl,liodn = <3 4>;
-			fsl,qman-channel-id = <1>;
+			cell-index = <1>;
 
 			fman0 {
 				fsl,liodn = <0x22>;
diff --git a/Documentation/devicetree/bindings/spi/spi-ath79.txt b/Documentation/devicetree/bindings/spi/spi-ath79.txt
new file mode 100644
index 000000000000..f1ad9c367532
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-ath79.txt
@@ -0,0 +1,24 @@
+Binding for Qualcomm Atheros AR7xxx/AR9xxx SPI controller
+
+Required properties:
+- compatible: has to be "qca,<soc-type>-spi", "qca,ar7100-spi" as fallback.
+- reg: Base address and size of the controllers memory area
+- clocks: phandle to the AHB clock.
+- clock-names: has to be "ahb".
+- #address-cells: <1>, as required by generic SPI binding.
+- #size-cells: <0>, also as required by generic SPI binding.
+
+Child nodes as per the generic SPI binding.
+
+Example:
+
+	spi@1F000000 {
+		compatible = "qca,ar9132-spi", "qca,ar7100-spi";
+		reg = <0x1F000000 0x10>;
+
+		clocks = <&pll 2>;
+		clock-names = "ahb";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+	};
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
index 70af78a9185e..fa77f874e321 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt
@@ -1,7 +1,7 @@
 ARM Freescale DSPI controller
 
 Required properties:
-- compatible : "fsl,vf610-dspi"
+- compatible : "fsl,vf610-dspi", "fsl,ls1021a-v1.0-dspi", "fsl,ls2085a-dspi"
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain SPI controller interrupt
 - clocks: from common clock binding: handle to dspi clock.
diff --git a/Documentation/devicetree/bindings/spi/spi-orion.txt b/Documentation/devicetree/bindings/spi/spi-orion.txt
index 50c3a3de61c1..98bc69815eb3 100644
--- a/Documentation/devicetree/bindings/spi/spi-orion.txt
+++ b/Documentation/devicetree/bindings/spi/spi-orion.txt
@@ -1,7 +1,13 @@
 Marvell Orion SPI device
 
 Required properties:
-- compatible : should be "marvell,orion-spi" or "marvell,armada-370-spi".
+- compatible : should be on of the following:
+    - "marvell,orion-spi" for the Orion, mv78x00, Kirkwood and Dove SoCs
+    - "marvell,armada-370-spi", for the Armada 370 SoCs
+    - "marvell,armada-375-spi", for the Armada 375 SoCs
+    - "marvell,armada-380-spi", for the Armada 38x SoCs
+    - "marvell,armada-390-spi", for the Armada 39x SoCs
+    - "marvell,armada-xp-spi", for the Armada XP SoCs
 - reg : offset and length of the register set for the device
 - cell-index : Which of multiple SPI controllers is this.
 Optional properties:
diff --git a/Documentation/devicetree/bindings/spi/spi-sirf.txt b/Documentation/devicetree/bindings/spi/spi-sirf.txt
index 4c7adb8f777c..ddd78ff68fae 100644
--- a/Documentation/devicetree/bindings/spi/spi-sirf.txt
+++ b/Documentation/devicetree/bindings/spi/spi-sirf.txt
@@ -1,7 +1,8 @@
 * CSR SiRFprimaII Serial Peripheral Interface
 
 Required properties:
-- compatible : Should be "sirf,prima2-spi"
+- compatible : Should be "sirf,prima2-spi", "sirf,prima2-usp"
+               or "sirf,atlas7-usp"
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain SPI interrupt
 - resets: phandle to the reset controller asserting this device in
diff --git a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
new file mode 100644
index 000000000000..c8f50e5cf70b
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
@@ -0,0 +1,26 @@
+Xilinx Zynq UltraScale+ MPSoC GQSPI controller Device Tree Bindings
+-------------------------------------------------------------------
+
+Required properties:
+- compatible		: Should be "xlnx,zynqmp-qspi-1.0".
+- reg			: Physical base address and size of GQSPI registers map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- interrupt-parent	: Must be core interrupt controller.
+- clock-names		: List of input clock names - "ref_clk", "pclk"
+			  (See clock bindings for details).
+- clocks		: Clock phandles (see clock bindings for details).
+
+Optional properties:
+- num-cs		: Number of chip selects used.
+
+Example:
+	qspi: spi@ff0f0000 {
+		compatible = "xlnx,zynqmp-qspi-1.0";
+		clock-names = "ref_clk", "pclk";
+		clocks = <&misc_clk &misc_clk>;
+		interrupts = <0 15 4>;
+		interrupt-parent = <&gic>;
+		num-cs = <1>;
+		reg = <0x0 0xff0f0000 0x1000>,<0x0 0xc0000000 0x8000000>;
+	};
diff --git a/Documentation/devicetree/bindings/spi/spi_atmel.txt b/Documentation/devicetree/bindings/spi/spi_atmel.txt
index 4f8184d069cb..fb588b3e6a9a 100644
--- a/Documentation/devicetree/bindings/spi/spi_atmel.txt
+++ b/Documentation/devicetree/bindings/spi/spi_atmel.txt
@@ -4,11 +4,16 @@ Required properties:
 - compatible : should be "atmel,at91rm9200-spi".
 - reg: Address and length of the register set for the device
 - interrupts: Should contain spi interrupt
-- cs-gpios: chipselects
+- cs-gpios: chipselects (optional for SPI controller version >= 2 with the
+  Chip Select Active After Transfer feature).
 - clock-names: tuple listing input clock names.
 	Required elements: "spi_clk"
 - clocks: phandles to input clocks.
 
+Optional properties:
+- atmel,fifo-size: maximum number of data the RX and TX FIFOs can store for FIFO
+  capable SPI controllers.
+
 Example:
 
 spi1: spi@fffcc000 {
@@ -20,6 +25,7 @@ spi1: spi@fffcc000 {
 	clocks = <&spi1_clk>;
 	clock-names = "spi_clk";
 	cs-gpios = <&pioB 3 0>;
+	atmel,fifo-size = <32>;
 	status = "okay";
 
 	mmc-slot@0 {
diff --git a/Documentation/devicetree/bindings/spi/spi_pl022.txt b/Documentation/devicetree/bindings/spi/spi_pl022.txt
index 22ed6797216d..4d1673ca8cf8 100644
--- a/Documentation/devicetree/bindings/spi/spi_pl022.txt
+++ b/Documentation/devicetree/bindings/spi/spi_pl022.txt
@@ -4,9 +4,9 @@ Required properties:
 - compatible : "arm,pl022", "arm,primecell"
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain SPI controller interrupt
+- num-cs : total number of chipselects
 
 Optional properties:
-- num-cs : total number of chipselects
 - cs-gpios : should specify GPIOs used for chipselects.
   The gpios will be referred to as reg = <index> in the SPI child nodes.
   If unspecified, a single SPI device without a chip select can be used.
diff --git a/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt b/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt
new file mode 100644
index 000000000000..51b05a0e70d1
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/nxp,lpc3220-timer.txt
@@ -0,0 +1,26 @@
+* NXP LPC3220 timer
+
+The NXP LPC3220 timer is used on a wide range of NXP SoCs. This
+includes LPC32xx, LPC178x, LPC18xx and LPC43xx parts.
+
+Required properties:
+- compatible:
+	Should be "nxp,lpc3220-timer".
+- reg:
+	Address and length of the register set.
+- interrupts:
+	Reference to the timer interrupt
+- clocks:
+	Should contain a reference to timer clock.
+- clock-names:
+	Should contain "timerclk".
+
+Example:
+
+timer1: timer@40085000 {
+	compatible = "nxp,lpc3220-timer";
+	reg = <0x40085000 0x1000>;
+	interrupts = <13>;
+	clocks = <&ccu1 CLK_CPU_TIMER1>;
+	clock-names = "timerclk";
+};
diff --git a/Documentation/devicetree/bindings/timer/renesas,16bit-timer.txt b/Documentation/devicetree/bindings/timer/renesas,16bit-timer.txt
new file mode 100644
index 000000000000..e8792447a199
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/renesas,16bit-timer.txt
@@ -0,0 +1,25 @@
+* Renesas H8/300 16bit timer
+
+The 16bit timer is a 16bit timer/counter with configurable clock inputs and
+programmable compare match.
+
+Required Properties:
+
+  - compatible: must contain "renesas,16bit-timer"
+  - reg: base address and length of the registers block for the timer module.
+  - interrupts: interrupt-specifier for the timer, IMIA
+  - clocks: a list of phandle, one for each entry in clock-names.
+  - clock-names: must contain "peripheral_clk" for the functional clock.
+  - renesas,channel: timer channel number.
+
+Example:
+
+	timer16: timer@ffff68 {
+		compatible = "reneas,16bit-timer";
+		reg = <0xffff68 8>, <0xffff60 8>;
+		interrupts = <24>;
+		renesas,channel = <0>;
+		clocks = <&pclk>;
+		clock-names = "peripheral_clk";
+	};
+
diff --git a/Documentation/devicetree/bindings/timer/renesas,8bit-timer.txt b/Documentation/devicetree/bindings/timer/renesas,8bit-timer.txt
new file mode 100644
index 000000000000..9dca3759a0f0
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/renesas,8bit-timer.txt
@@ -0,0 +1,25 @@
+* Renesas H8/300 8bit timer
+
+The 8bit timer is a 8bit timer/counter with configurable clock inputs and
+programmable compare match.
+
+This implement only supported cascade mode.
+
+Required Properties:
+
+  - compatible: must contain "renesas,8bit-timer"
+  - reg: base address and length of the registers block for the timer module.
+  - interrupts: interrupt-specifier for the timer, CMIA and TOVI
+  - clocks: a list of phandle, one for each entry in clock-names.
+  - clock-names: must contain "fck" for the functional clock.
+
+Example:
+
+	timer8_0: timer@ffff80 {
+		compatible = "renesas,8bit-timer";
+		reg = <0xffff80 10>;
+		interrupts = <36>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
diff --git a/Documentation/devicetree/bindings/timer/renesas,tpu.txt b/Documentation/devicetree/bindings/timer/renesas,tpu.txt
new file mode 100644
index 000000000000..f8b25897fb31
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/renesas,tpu.txt
@@ -0,0 +1,21 @@
+* Renesas H8/300 Timer Pluse Unit
+
+The TPU is a 16bit timer/counter with configurable clock inputs and
+programmable compare match.
+This implementation support only cascade mode.
+
+Required Properties:
+
+  - compatible: must contain "renesas,tpu"
+  - reg: base address and length of the registers block in 2 channel.
+  - clocks: a list of phandle, one for each entry in clock-names.
+  - clock-names: must contain "peripheral_clk" for the functional clock.
+
+
+Example:
+	tpu: tpu@ffffe0 {
+		compatible = "renesas,tpu";
+		reg = <0xffffe0 16>, <0xfffff0 12>;
+		clocks = <&pclk>;
+		clock-names = "peripheral_clk";
+	};
diff --git a/Documentation/devicetree/bindings/timer/st,stm32-timer.txt b/Documentation/devicetree/bindings/timer/st,stm32-timer.txt
new file mode 100644
index 000000000000..8ef28e70d6e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/st,stm32-timer.txt
@@ -0,0 +1,22 @@
+. STMicroelectronics STM32 timer
+
+The STM32 MCUs family has several general-purpose 16 and 32 bits timers.
+
+Required properties:
+- compatible : Should be "st,stm32-timer"
+- reg : Address and length of the register set
+- clocks : Reference on the timer input clock
+- interrupts : Reference to the timer interrupt
+
+Optional properties:
+- resets: Reference to a reset controller asserting the timer
+
+Example:
+
+timer5: timer@40000c00 {
+	compatible = "st,stm32-timer";
+	reg = <0x40000c00 0x400>;
+	interrupts = <50>;
+	resets = <&rrc 259>;
+	clocks = <&clk_pmtr1>;
+};
diff --git a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
index dc2a18f0b3a1..ddbe304beb21 100644
--- a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
+++ b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt
@@ -15,10 +15,8 @@ Optional properties:
   - phys: phandle + phy specifier pair
   - phy-names: must be "usb"
   - dmas: Must contain a list of references to DMA specifiers.
-  - dma-names : Must contain a list of DMA names:
-   - tx0 ... tx<n>
-   - rx0 ... rx<n>
-    - This <n> means DnFIFO in USBHS module.
+  - dma-names : named "ch%d", where %d is the channel number ranging from zero
+                to the number of channels (DnFIFOs) minus one.
 
 Example:
 	usbhs: usb@e6590000 {
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 80339192c93e..53d87bad0adc 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -161,6 +161,7 @@ ralink	Mediatek/Ralink Technology Corp.
 ramtron	Ramtron International
 realtek Realtek Semiconductor Corp.
 renesas	Renesas Electronics Corporation
+richtek	Richtek Technology Corporation
 ricoh	Ricoh Co. Ltd.
 rockchip	Fuzhou Rockchip Electronics Co., Ltd
 samsung	Samsung Semiconductor
@@ -181,6 +182,7 @@ skyworks	Skyworks Solutions, Inc.
 smsc	Standard Microsystems Corporation
 snps	Synopsys, Inc.
 solidrun	SolidRun
+solomon        Solomon Systech Limited
 sony	Sony Corporation
 spansion	Spansion Inc.
 sprd	Spreadtrum Communications Inc.
diff --git a/Documentation/devicetree/bindings/video/ssd1307fb.txt b/Documentation/devicetree/bindings/video/ssd1307fb.txt
index 7a125427ff4b..d1be78db63f5 100644
--- a/Documentation/devicetree/bindings/video/ssd1307fb.txt
+++ b/Documentation/devicetree/bindings/video/ssd1307fb.txt
@@ -2,7 +2,7 @@
 
 Required properties:
   - compatible: Should be "solomon,<chip>fb-<bus>". The only supported bus for
-    now is i2c, and the supported chips are ssd1306 and ssd1307.
+    now is i2c, and the supported chips are ssd1305, ssd1306 and ssd1307.
   - reg: Should contain address of the controller on the I2C bus. Most likely
          0x3c or 0x3d
   - pwm: Should contain the pwm to use according to the OF device tree PWM
@@ -15,6 +15,16 @@ Required properties:
 
 Optional properties:
   - reset-active-low: Is the reset gpio is active on physical low?
+  - solomon,segment-no-remap: Display needs normal (non-inverted) data column
+                              to segment mapping
+  - solomon,com-seq: Display uses sequential COM pin configuration
+  - solomon,com-lrremap: Display uses left-right COM pin remap
+  - solomon,com-invdir: Display uses inverted COM pin scan direction
+  - solomon,com-offset: Number of the COM pin wired to the first display line
+  - solomon,prechargep1: Length of deselect period (phase 1) in clock cycles.
+  - solomon,prechargep2: Length of precharge period (phase 2) in clock cycles.
+                         This needs to be the higher, the higher the capacitance
+                         of the OLED's pixels is
 
 [0]: Documentation/devicetree/bindings/pwm/pwm.txt
 
@@ -26,3 +36,14 @@ ssd1307: oled@3c {
         reset-gpios = <&gpio2 7>;
         reset-active-low;
 };
+
+ssd1306: oled@3c {
+        compatible = "solomon,ssd1306fb-i2c";
+        reg = <0x3c>;
+        pwms = <&pwm 4 3000>;
+        reset-gpios = <&gpio2 7>;
+        reset-active-low;
+        solomon,com-lrremap;
+        solomon,com-invdir;
+        solomon,com-offset = <32>;
+};
diff --git a/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt b/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt
new file mode 100644
index 000000000000..388c88a01222
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/st_lpc_wdt.txt
@@ -0,0 +1,38 @@
+STMicroelectronics Low Power Controller (LPC) - Watchdog
+========================================================
+
+LPC currently supports Watchdog OR Real Time Clock functionality.
+
+[See: ../rtc/rtc-st-lpc.txt for RTC options]
+
+Required properties
+
+- compatible 	: Must be one of: "st,stih407-lpc" "st,stih416-lpc"
+				  "st,stih415-lpc" "st,stid127-lpc"
+- reg		: LPC registers base address + size
+- interrupts    : LPC interrupt line number and associated flags
+- clocks	: Clock used by LPC device (See: ../clock/clock-bindings.txt)
+- st,lpc-mode	: The LPC can run either one of two modes ST_LPC_MODE_RTC [0] or
+		  ST_LPC_MODE_WDT [1].  One (and only one) mode must be
+		  selected.
+
+Required properties [watchdog mode]
+
+- st,syscfg	: Phandle to syscfg node used to enable watchdog and configure
+		  CPU reset type.
+- timeout-sec	: Watchdog timeout in seconds
+
+Optional properties [watchdog mode]
+
+- st,warm-reset	: If present reset type will be 'warm' - if not it will be cold
+
+Example:
+	lpc@fde05000 {
+		compatible	= "st,stih407-lpc";
+		reg		= <0xfde05000 0x1000>;
+		clocks 		= <&clk_s_d3_flexgen CLK_LPC_0>;
+		st,syscfg	= <&syscfg_core>;
+		timeout-sec	= <120>;
+		st,lpc-mode	= <ST_LPC_MODE_WDT>;
+		st,warm-reset;
+	};
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index 73fff13e848f..0cf27a3544a5 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -1,53 +1,34 @@
-
-
 EDAC - Error Detection And Correction
-
-Written by Doug Thompson <dougthompson@xmission.com>
-7 Dec 2005
-17 Jul 2007	Updated
-
-(c) Mauro Carvalho Chehab
-05 Aug 2009	Nehalem interface
-
-EDAC is maintained and written by:
-
-	Doug Thompson, Dave Jiang, Dave Peterson et al,
-	original author: Thayne Harbaugh,
-
-Contact:
-	website:	bluesmoke.sourceforge.net
-	mailing list:	bluesmoke-devel@lists.sourceforge.net
+=====================================
 
 "bluesmoke" was the name for this device driver when it was "out-of-tree"
 and maintained at sourceforge.net.  When it was pushed into 2.6.16 for the
 first time, it was renamed to 'EDAC'.
 
-The bluesmoke project at sourceforge.net is now utilized as a 'staging area'
-for EDAC development, before it is sent upstream to kernel.org
-
-At the bluesmoke/EDAC project site is a series of quilt patches against
-recent kernels, stored in a SVN repository. For easier downloading, there
-is also a tarball snapshot available.
+PURPOSE
+-------
 
-============================================================================
-EDAC PURPOSE
-
-The 'edac' kernel module goal is to detect and report errors that occur
-within the computer system running under linux.
+The 'edac' kernel module's goal is to detect and report hardware errors
+that occur within the computer system running under linux.
 
 MEMORY
+------
 
-In the initial release, memory Correctable Errors (CE) and Uncorrectable
-Errors (UE) are the primary errors being harvested. These types of errors
-are harvested by the 'edac_mc' class of device.
+Memory Correctable Errors (CE) and Uncorrectable Errors (UE) are the
+primary errors being harvested. These types of errors are harvested by
+the 'edac_mc' device.
 
 Detecting CE events, then harvesting those events and reporting them,
-CAN be a predictor of future UE events.  With CE events, the system can
-continue to operate, but with less safety. Preventive maintenance and
-proactive part replacement of memory DIMMs exhibiting CEs can reduce
-the likelihood of the dreaded UE events and system 'panics'.
+*can* but must not necessarily be a predictor of future UE events. With
+CE events only, the system can and will continue to operate as no data
+has been damaged yet.
+
+However, preventive maintenance and proactive part replacement of memory
+DIMMs exhibiting CEs can reduce the likelihood of the dreaded UE events
+and system panics.
 
-NON-MEMORY
+OTHER HARDWARE ELEMENTS
+-----------------------
 
 A new feature for EDAC, the edac_device class of device, was added in
 the 2.6.23 version of the kernel.
@@ -56,70 +37,57 @@ This new device type allows for non-memory type of ECC hardware detectors
 to have their states harvested and presented to userspace via the sysfs
 interface.
 
-Some architectures have ECC detectors for L1, L2 and L3 caches, along with DMA
-engines, fabric switches, main data path switches, interconnections,
-and various other hardware data paths. If the hardware reports it, then
-a edac_device device probably can be constructed to harvest and present
-that to userspace.
+Some architectures have ECC detectors for L1, L2 and L3 caches,
+along with DMA engines, fabric switches, main data path switches,
+interconnections, and various other hardware data paths. If the hardware
+reports it, then a edac_device device probably can be constructed to
+harvest and present that to userspace.
 
 
 PCI BUS SCANNING
+----------------
 
-In addition, PCI Bus Parity and SERR Errors are scanned for on PCI devices
-in order to determine if errors are occurring on data transfers.
+In addition, PCI devices are scanned for PCI Bus Parity and SERR Errors
+in order to determine if errors are occurring during data transfers.
 
 The presence of PCI Parity errors must be examined with a grain of salt.
-There are several add-in adapters that do NOT follow the PCI specification
+There are several add-in adapters that do *not* follow the PCI specification
 with regards to Parity generation and reporting. The specification says
 the vendor should tie the parity status bits to 0 if they do not intend
 to generate parity.  Some vendors do not do this, and thus the parity bit
 can "float" giving false positives.
 
-In the kernel there is a PCI device attribute located in sysfs that is
-checked by the EDAC PCI scanning code. If that attribute is set,
-PCI parity/error scanning is skipped for that device. The attribute
-is:
+There is a PCI device attribute located in sysfs that is checked by
+the EDAC PCI scanning code. If that attribute is set, PCI parity/error
+scanning is skipped for that device. The attribute is:
 
 	broken_parity_status
 
-as is located in /sys/devices/pci<XXX>/0000:XX:YY.Z directories for
+and is located in /sys/devices/pci<XXX>/0000:XX:YY.Z directories for
 PCI devices.
 
-FUTURE HARDWARE SCANNING
 
-EDAC will have future error detectors that will be integrated with
-EDAC or added to it, in the following list:
-
-	MCE	Machine Check Exception
-	MCA	Machine Check Architecture
-	NMI	NMI notification of ECC errors
-	MSRs 	Machine Specific Register error cases
-	and other mechanisms.
-
-These errors are usually bus errors, ECC errors, thermal throttling
-and the like.
-
-
-============================================================================
-EDAC VERSIONING
+VERSIONING
+----------
 
 EDAC is composed of a "core" module (edac_core.ko) and several Memory
-Controller (MC) driver modules. On a given system, the CORE
-is loaded and one MC driver will be loaded. Both the CORE and
-the MC driver (or edac_device driver) have individual versions that reflect
-current release level of their respective modules.
+Controller (MC) driver modules. On a given system, the CORE is loaded
+and one MC driver will be loaded. Both the CORE and the MC driver (or
+edac_device driver) have individual versions that reflect current
+release level of their respective modules.
 
-Thus, to "report" on what version a system is running, one must report both
-the CORE's and the MC driver's versions.
+Thus, to "report" on what version a system is running, one must report
+both the CORE's and the MC driver's versions.
 
 
 LOADING
+-------
 
-If 'edac' was statically linked with the kernel then no loading is
-necessary.  If 'edac' was built as modules then simply modprobe the
-'edac' pieces that you need.  You should be able to modprobe
-hardware-specific modules and have the dependencies load the necessary core
-modules.
+If 'edac' was statically linked with the kernel then no loading
+is necessary. If 'edac' was built as modules then simply modprobe
+the 'edac' pieces that you need. You should be able to modprobe
+hardware-specific modules and have the dependencies load the necessary
+core modules.
 
 Example:
 
@@ -129,35 +97,33 @@ loads both the amd76x_edac.ko memory controller module and the edac_mc.ko
 core module.
 
 
-============================================================================
-EDAC sysfs INTERFACE
-
-EDAC presents a 'sysfs' interface for control, reporting and attribute
-reporting purposes.
+SYSFS INTERFACE
+---------------
 
-EDAC lives in the /sys/devices/system/edac directory.
+EDAC presents a 'sysfs' interface for control and reporting purposes. It
+lives in the /sys/devices/system/edac directory.
 
-Within this directory there currently reside 2 'edac' components:
+Within this directory there currently reside 2 components:
 
 	mc	memory controller(s) system
 	pci	PCI control and status system
 
 
-============================================================================
+
 Memory Controller (mc) Model
+----------------------------
 
-First a background on the memory controller's model abstracted in EDAC.
-Each 'mc' device controls a set of DIMM memory modules. These modules are
-laid out in a Chip-Select Row (csrowX) and Channel table (chX). There can
-be multiple csrows and multiple channels.
+Each 'mc' device controls a set of DIMM memory modules. These modules
+are laid out in a Chip-Select Row (csrowX) and Channel table (chX).
+There can be multiple csrows and multiple channels.
 
-Memory controllers allow for several csrows, with 8 csrows being a typical value.
-Yet, the actual number of csrows depends on the electrical "loading"
-of a given motherboard, memory controller and DIMM characteristics.
+Memory controllers allow for several csrows, with 8 csrows being a
+typical value. Yet, the actual number of csrows depends on the layout of
+a given motherboard, memory controller and DIMM characteristics.
 
-Dual channels allows for 128 bit data transfers to the CPU from memory.
-Some newer chipsets allow for more than 2 channels, like Fully Buffered DIMMs
-(FB-DIMMs). The following example will assume 2 channels:
+Dual channels allows for 128 bit data transfers to/from the CPU from/to
+memory. Some newer chipsets allow for more than 2 channels, like Fully
+Buffered DIMMs (FB-DIMMs). The following example will assume 2 channels:
 
 
 		Channel 0	Channel 1
@@ -179,12 +145,12 @@ for memory DIMMs:
 	DIMM_A1
 	DIMM_B1
 
-Labels for these slots are usually silk screened on the motherboard. Slots
-labeled 'A' are channel 0 in this example. Slots labeled 'B'
-are channel 1. Notice that there are two csrows possible on a
-physical DIMM. These csrows are allocated their csrow assignment
-based on the slot into which the memory DIMM is placed. Thus, when 1 DIMM
-is placed in each Channel, the csrows cross both DIMMs.
+Labels for these slots are usually silk-screened on the motherboard.
+Slots labeled 'A' are channel 0 in this example. Slots labeled 'B' are
+channel 1. Notice that there are two csrows possible on a physical DIMM.
+These csrows are allocated their csrow assignment based on the slot into
+which the memory DIMM is placed. Thus, when 1 DIMM is placed in each
+Channel, the csrows cross both DIMMs.
 
 Memory DIMMs come single or dual "ranked". A rank is a populated csrow.
 Thus, 2 single ranked DIMMs, placed in slots DIMM_A0 and DIMM_B0 above
@@ -193,8 +159,8 @@ when 2 dual ranked DIMMs are similarly placed, then both csrow0 and
 csrow1 will be populated. The pattern repeats itself for csrow2 and
 csrow3.
 
-The representation of the above is reflected in the directory tree
-in EDAC's sysfs interface. Starting in directory
+The representation of the above is reflected in the directory
+tree in EDAC's sysfs interface. Starting in directory
 /sys/devices/system/edac/mc each memory controller will be represented
 by its own 'mcX' directory, where 'X' is the index of the MC.
 
@@ -217,34 +183,35 @@ Under each 'mcX' directory each 'csrowX' is again represented by a
 		|->csrow3
 		....
 
-Notice that there is no csrow1, which indicates that csrow0 is
-composed of a single ranked DIMMs. This should also apply in both
-Channels, in order to have dual-channel mode be operational. Since
-both csrow2 and csrow3 are populated, this indicates a dual ranked
-set of DIMMs for channels 0 and 1.
+Notice that there is no csrow1, which indicates that csrow0 is composed
+of a single ranked DIMMs. This should also apply in both Channels, in
+order to have dual-channel mode be operational. Since both csrow2 and
+csrow3 are populated, this indicates a dual ranked set of DIMMs for
+channels 0 and 1.
 
 
-Within each of the 'mcX' and 'csrowX' directories are several
-EDAC control and attribute files.
+Within each of the 'mcX' and 'csrowX' directories are several EDAC
+control and attribute files.
 
-============================================================================
-'mcX' DIRECTORIES
 
+'mcX' directories
+-----------------
 
 In 'mcX' directories are EDAC control and attribute files for
 this 'X' instance of the memory controllers.
 
 For a description of the sysfs API, please see:
-	Documentation/ABI/testing/sysfs/devices-edac
+	Documentation/ABI/testing/sysfs-devices-edac
+
 
 
-============================================================================
-'csrowX' DIRECTORIES
+'csrowX' directories
+--------------------
 
-When CONFIG_EDAC_LEGACY_SYSFS is enabled, the sysfs will contain the
-csrowX directories. As this API doesn't work properly for Rambus, FB-DIMMs
-and modern Intel Memory Controllers, this is being deprecated in favor
-of dimmX directories.
+When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the csrowX
+directories. As this API doesn't work properly for Rambus, FB-DIMMs and
+modern Intel Memory Controllers, this is being deprecated in favor of
+dimmX directories.
 
 In the 'csrowX' directories are EDAC control and attribute files for
 this 'X' instance of csrow:
@@ -265,18 +232,18 @@ Total Correctable Errors count attribute file:
 	'ce_count'
 
 	This attribute file displays the total count of correctable
-	errors that have occurred on this csrow. This
-	count is very important to examine. CEs provide early
-	indications that a DIMM is beginning to fail. This count
-	field should be monitored for non-zero values and report
-	such information to the system administrator.
+	errors that have occurred on this csrow. This count is very
+	important to examine. CEs provide early indications that a
+	DIMM is beginning to fail. This count field should be
+	monitored for non-zero values and report such information
+	to the system administrator.
 
 
 Total memory managed by this csrow attribute file:
 
 	'size_mb'
 
-	This attribute file displays, in count of megabytes, of memory
+	This attribute file displays, in count of megabytes, the memory
 	that this csrow contains.
 
 
@@ -377,11 +344,13 @@ Channel 1 DIMM Label control file:
 	motherboard specific and determination of this information
 	must occur in userland at this time.
 
-============================================================================
+
+
 SYSTEM LOGGING
+--------------
 
-If logging for UEs and CEs are enabled then system logs will have
-error notices indicating errors that have been detected:
+If logging for UEs and CEs is enabled, then system logs will contain
+information indicating that errors have been detected:
 
 EDAC MC0: CE page 0x283, offset 0xce0, grain 8, syndrome 0x6ec3, row 0,
 channel 1 "DIMM_B1": amd76x_edac
@@ -404,24 +373,23 @@ The structure of the message is:
 	and then an optional, driver-specific message that may
 		have additional information.
 
-Both UEs and CEs with no info will lack all but memory controller,
-error type, a notice of "no info" and then an optional,
-driver-specific error message.
+Both UEs and CEs with no info will lack all but memory controller, error
+type, a notice of "no info" and then an optional, driver-specific error
+message.
 
 
-============================================================================
 PCI Bus Parity Detection
+------------------------
 
-
-On Header Type 00 devices the primary status is looked at
-for any parity error regardless of whether Parity is enabled on the
-device.  (The spec indicates parity is generated in some cases).
-On Header Type 01 bridges, the secondary status register is also
-looked at to see if parity occurred on the bus on the other side of
-the bridge.
+On Header Type 00 devices, the primary status is looked at for any
+parity error regardless of whether parity is enabled on the device or
+not. (The spec indicates parity is generated in some cases). On Header
+Type 01 bridges, the secondary status register is also looked at to see
+if parity occurred on the bus on the other side of the bridge.
 
 
 SYSFS CONFIGURATION
+-------------------
 
 Under /sys/devices/system/edac/pci are control and attribute files as follows:
 
@@ -450,8 +418,9 @@ Parity Count:
 	have been detected.
 
 
-============================================================================
+
 MODULE PARAMETERS
+-----------------
 
 Panic on UE control file:
 
@@ -516,7 +485,7 @@ Panic on PCI PARITY Error:
 	'panic_on_pci_parity'
 
 
-	This control files enables or disables panicking when a parity
+	This control file enables or disables panicking when a parity
 	error has been detected.
 
 
@@ -530,10 +499,8 @@ Panic on PCI PARITY Error:
 
 
 
-=======================================================================
-
-
-EDAC_DEVICE type of device
+EDAC device type
+----------------
 
 In the header file, edac_core.h, there is a series of edac_device structures
 and APIs for the EDAC_DEVICE.
@@ -573,6 +540,7 @@ The test_device_edac device adds at least one of its own custom control:
 The symlink points to the 'struct dev' that is registered for this edac_device.
 
 INSTANCES
+---------
 
 One or more instance directories are present. For the 'test_device_edac' case:
 
@@ -586,6 +554,7 @@ counter in deeper subdirectories.
 	ue_count	total of UE events of subdirectories
 
 BLOCKS
+------
 
 At the lowest directory level is the 'block' directory. There can be 0, 1
 or more blocks specified in each instance.
@@ -617,14 +586,15 @@ The 'test_device_edac' device adds 4 attributes and 1 control:
 				reset all the above counters.
 
 
-Use of the 'test_device_edac' driver should any others to create their own
+Use of the 'test_device_edac' driver should enable any others to create their own
 unique drivers for their hardware systems.
 
 The 'test_device_edac' sample driver is located at the
 bluesmoke.sourceforge.net project site for EDAC.
 
-=======================================================================
+
 NEHALEM USAGE OF EDAC APIs
+--------------------------
 
 This chapter documents some EXPERIMENTAL mappings for EDAC API to handle
 Nehalem EDAC driver. They will likely be changed on future versions
@@ -633,7 +603,7 @@ of the driver.
 Due to the way Nehalem exports Memory Controller data, some adjustments
 were done at i7core_edac driver. This chapter will cover those differences
 
-1) On Nehalem, there are one Memory Controller per Quick Patch Interconnect
+1) On Nehalem, there is one Memory Controller per Quick Patch Interconnect
    (QPI). At the driver, the term "socket" means one QPI. This is
    associated with a physical CPU socket.
 
@@ -642,7 +612,7 @@ were done at i7core_edac driver. This chapter will cover those differences
    Each channel can have up to 3 DIMMs.
 
    The minimum known unity is DIMMs. There are no information about csrows.
-   As EDAC API maps the minimum unity is csrows, the driver sequencially
+   As EDAC API maps the minimum unity is csrows, the driver sequentially
    maps channel/dimm into different csrows.
 
    For example, supposing the following layout:
@@ -664,7 +634,7 @@ exports one
 
    Each QPI is exported as a different memory controller.
 
-2) Nehalem MC has the hability to generate errors. The driver implements this
+2) Nehalem MC has the ability to generate errors. The driver implements this
    functionality via some error injection nodes:
 
    For injecting a memory error, there are some sysfs nodes, under
@@ -771,5 +741,22 @@ exports one
 
    The standard error counters are generated when an mcelog error is received
    by the driver. Since, with udimm, this is counted by software, it is
-   possible that some errors could be lost. With rdimm's, they displays the
+   possible that some errors could be lost. With rdimm's, they display the
    contents of the registers
+
+CREDITS:
+========
+
+Written by Doug Thompson <dougthompson@xmission.com>
+7 Dec 2005
+17 Jul 2007	Updated
+
+(c) Mauro Carvalho Chehab
+05 Aug 2009	Nehalem interface
+
+EDAC authors/maintainers:
+
+	Doug Thompson, Dave Jiang, Dave Peterson et al,
+	Mauro Carvalho Chehab
+	Borislav Petkov
+	original author: Thayne Harbaugh
diff --git a/Documentation/features/arch-support.txt b/Documentation/features/arch-support.txt
new file mode 100644
index 000000000000..d22a1095e661
--- /dev/null
+++ b/Documentation/features/arch-support.txt
@@ -0,0 +1,11 @@
+
+For generic kernel features that need architecture support, the
+arch-support.txt file in each feature directory shows the arch
+support matrix, for all upstream Linux architectures.
+
+The meaning of entries in the tables is:
+
+    | ok |  # feature supported by the architecture
+    |TODO|  # feature not yet supported by the architecture
+    | .. |  # feature cannot be supported by the hardware
+
diff --git a/Documentation/features/core/BPF-JIT/arch-support.txt b/Documentation/features/core/BPF-JIT/arch-support.txt
new file mode 100644
index 000000000000..c1b4f917238f
--- /dev/null
+++ b/Documentation/features/core/BPF-JIT/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          BPF-JIT
+#         Kconfig:       HAVE_BPF_JIT
+#         description:   arch supports BPF JIT optimizations
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/core/generic-idle-thread/arch-support.txt b/Documentation/features/core/generic-idle-thread/arch-support.txt
new file mode 100644
index 000000000000..6d930fcbe519
--- /dev/null
+++ b/Documentation/features/core/generic-idle-thread/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          generic-idle-thread
+#         Kconfig:       GENERIC_SMP_IDLE_THREAD
+#         description:   arch makes use of the generic SMP idle thread facility
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: |  ok  |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: |  ok  |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: |  ok  |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: |  ok  |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt
new file mode 100644
index 000000000000..136868b636e6
--- /dev/null
+++ b/Documentation/features/core/jump-labels/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          jump-labels
+#         Kconfig:       HAVE_ARCH_JUMP_LABEL
+#         description:   arch supports live patched, high efficiency branches
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt
new file mode 100644
index 000000000000..728061d763b1
--- /dev/null
+++ b/Documentation/features/core/tracehook/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          tracehook
+#         Kconfig:       HAVE_ARCH_TRACEHOOK
+#         description:   arch supports tracehook (ptrace) register handling APIs
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: |  ok  |
+    |         c6x: |  ok  |
+    |        cris: | TODO |
+    |         frv: |  ok  |
+    |       h8300: | TODO |
+    |     hexagon: |  ok  |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: |  ok  |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: |  ok  |
+    |       nios2: |  ok  |
+    |    openrisc: |  ok  |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/KASAN/arch-support.txt b/Documentation/features/debug/KASAN/arch-support.txt
new file mode 100644
index 000000000000..14531da2fb54
--- /dev/null
+++ b/Documentation/features/debug/KASAN/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          KASAN
+#         Kconfig:       HAVE_ARCH_KASAN
+#         description:   arch supports the KASAN runtime memory checker
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/gcov-profile-all/arch-support.txt b/Documentation/features/debug/gcov-profile-all/arch-support.txt
new file mode 100644
index 000000000000..38dea8eeba0a
--- /dev/null
+++ b/Documentation/features/debug/gcov-profile-all/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          gcov-profile-all
+#         Kconfig:       ARCH_HAS_GCOV_PROFILE_ALL
+#         description:   arch supports whole-kernel GCOV code coverage profiling
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: |  ok  |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/kgdb/arch-support.txt b/Documentation/features/debug/kgdb/arch-support.txt
new file mode 100644
index 000000000000..862e15d6f79e
--- /dev/null
+++ b/Documentation/features/debug/kgdb/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          kgdb
+#         Kconfig:       HAVE_ARCH_KGDB
+#         description:   arch supports the kGDB kernel debugger
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: |  ok  |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: |  ok  |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: |  ok  |
+    |       nios2: |  ok  |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
new file mode 100644
index 000000000000..40f44d041fb4
--- /dev/null
+++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          kprobes-on-ftrace
+#         Kconfig:       HAVE_KPROBES_ON_FTRACE
+#         description:   arch supports combined kprobes and ftrace live patching
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/kprobes/arch-support.txt b/Documentation/features/debug/kprobes/arch-support.txt
new file mode 100644
index 000000000000..a44bfff6940b
--- /dev/null
+++ b/Documentation/features/debug/kprobes/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          kprobes
+#         Kconfig:       HAVE_KPROBES
+#         description:   arch supports live patched kernel probe
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: | TODO |
+    |       avr32: |  ok  |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/kretprobes/arch-support.txt b/Documentation/features/debug/kretprobes/arch-support.txt
new file mode 100644
index 000000000000..d87c1ce24204
--- /dev/null
+++ b/Documentation/features/debug/kretprobes/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          kretprobes
+#         Kconfig:       HAVE_KRETPROBES
+#         description:   arch supports kernel function-return probes
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/optprobes/arch-support.txt b/Documentation/features/debug/optprobes/arch-support.txt
new file mode 100644
index 000000000000..b8999d8544ca
--- /dev/null
+++ b/Documentation/features/debug/optprobes/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          optprobes
+#         Kconfig:       HAVE_OPTPROBES
+#         description:   arch supports live patched optprobes
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/stackprotector/arch-support.txt b/Documentation/features/debug/stackprotector/arch-support.txt
new file mode 100644
index 000000000000..0fa423313409
--- /dev/null
+++ b/Documentation/features/debug/stackprotector/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          stackprotector
+#         Kconfig:       HAVE_CC_STACKPROTECTOR
+#         description:   arch supports compiler driven stack overflow protection
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/uprobes/arch-support.txt b/Documentation/features/debug/uprobes/arch-support.txt
new file mode 100644
index 000000000000..4efe36c3ace9
--- /dev/null
+++ b/Documentation/features/debug/uprobes/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          uprobes
+#         Kconfig:       ARCH_SUPPORTS_UPROBES
+#         description:   arch supports live patched user probes
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/debug/user-ret-profiler/arch-support.txt b/Documentation/features/debug/user-ret-profiler/arch-support.txt
new file mode 100644
index 000000000000..44cc1ff3f603
--- /dev/null
+++ b/Documentation/features/debug/user-ret-profiler/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          user-ret-profiler
+#         Kconfig:       HAVE_USER_RETURN_NOTIFIER
+#         description:   arch supports user-space return from system call profiler
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/io/dma-api-debug/arch-support.txt b/Documentation/features/io/dma-api-debug/arch-support.txt
new file mode 100644
index 000000000000..4f4a3443b114
--- /dev/null
+++ b/Documentation/features/io/dma-api-debug/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          dma-api-debug
+#         Kconfig:       HAVE_DMA_API_DEBUG
+#         description:   arch supports DMA debug facilities
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: |  ok  |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/io/dma-contiguous/arch-support.txt b/Documentation/features/io/dma-contiguous/arch-support.txt
new file mode 100644
index 000000000000..a97e8e3f4ebb
--- /dev/null
+++ b/Documentation/features/io/dma-contiguous/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          dma-contiguous
+#         Kconfig:       HAVE_DMA_CONTIGUOUS
+#         description:   arch supports the DMA CMA (continuous memory allocator)
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/io/dma_map_attrs/arch-support.txt b/Documentation/features/io/dma_map_attrs/arch-support.txt
new file mode 100644
index 000000000000..51d0f1c02a3e
--- /dev/null
+++ b/Documentation/features/io/dma_map_attrs/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          dma_map_attrs
+#         Kconfig:       HAVE_DMA_ATTRS
+#         description:   arch provides dma_*map*_attrs() APIs
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: |  ok  |
+    |     hexagon: |  ok  |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: |  ok  |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: |  ok  |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/io/sg-chain/arch-support.txt b/Documentation/features/io/sg-chain/arch-support.txt
new file mode 100644
index 000000000000..b9b675539b9d
--- /dev/null
+++ b/Documentation/features/io/sg-chain/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          sg-chain
+#         Kconfig:       ARCH_HAS_SG_CHAIN
+#         description:   arch supports chained scatter-gather lists
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/lib/strncasecmp/arch-support.txt b/Documentation/features/lib/strncasecmp/arch-support.txt
new file mode 100644
index 000000000000..12b1c9358e57
--- /dev/null
+++ b/Documentation/features/lib/strncasecmp/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          strncasecmp
+#         Kconfig:       __HAVE_ARCH_STRNCASECMP
+#         description:   arch provides an optimized strncasecmp() function
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: | TODO |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/list-arch.sh b/Documentation/features/list-arch.sh
new file mode 100755
index 000000000000..6065124a072f
--- /dev/null
+++ b/Documentation/features/list-arch.sh
@@ -0,0 +1,24 @@
+#
+# Small script that visualizes the kernel feature support status
+# of an architecture.
+#
+# (If no arguments are given then it will print the host architecture's status.)
+#
+
+ARCH=${1:-$(arch | sed 's/x86_64/x86/' | sed 's/i386/x86/')}
+
+cd $(dirname $0)
+echo "#"
+echo "# Kernel feature support matrix of the '$ARCH' architecture:"
+echo "#"
+
+for F in */*/arch-support.txt; do
+  SUBSYS=$(echo $F | cut -d/ -f1)
+  N=$(grep -h "^# Feature name:"        $F | cut -c25-)
+  C=$(grep -h "^#         Kconfig:"     $F | cut -c25-)
+  D=$(grep -h "^#         description:" $F | cut -c25-)
+  S=$(grep -hw $ARCH $F | cut -d\| -f3)
+
+  printf "%10s/%-22s:%s| %35s # %s\n" "$SUBSYS" "$N" "$S" "$C" "$D"
+done
+
diff --git a/Documentation/features/locking/cmpxchg-local/arch-support.txt b/Documentation/features/locking/cmpxchg-local/arch-support.txt
new file mode 100644
index 000000000000..d9c310889bc1
--- /dev/null
+++ b/Documentation/features/locking/cmpxchg-local/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          cmpxchg-local
+#         Kconfig:       HAVE_CMPXCHG_LOCAL
+#         description:   arch supports the this_cpu_cmpxchg() API
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/locking/lockdep/arch-support.txt b/Documentation/features/locking/lockdep/arch-support.txt
new file mode 100644
index 000000000000..cf90635bdcbb
--- /dev/null
+++ b/Documentation/features/locking/lockdep/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          lockdep
+#         Kconfig:       LOCKDEP_SUPPORT
+#         description:   arch supports the runtime locking correctness debug facility
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: |  ok  |
+    |    blackfin: |  ok  |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: |  ok  |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: |  ok  |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: |  ok  |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: |  ok  |
+    |   unicore32: |  ok  |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/locking/queued-rwlocks/arch-support.txt b/Documentation/features/locking/queued-rwlocks/arch-support.txt
new file mode 100644
index 000000000000..68c3a5ddd9b9
--- /dev/null
+++ b/Documentation/features/locking/queued-rwlocks/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          queued-rwlocks
+#         Kconfig:       ARCH_USE_QUEUED_RWLOCKS
+#         description:   arch supports queued rwlocks
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/locking/queued-spinlocks/arch-support.txt b/Documentation/features/locking/queued-spinlocks/arch-support.txt
new file mode 100644
index 000000000000..e973b1a9572f
--- /dev/null
+++ b/Documentation/features/locking/queued-spinlocks/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          queued-spinlocks
+#         Kconfig:       ARCH_USE_QUEUED_SPINLOCKS
+#         description:   arch supports queued spinlocks
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/locking/rwsem-optimized/arch-support.txt b/Documentation/features/locking/rwsem-optimized/arch-support.txt
new file mode 100644
index 000000000000..ac93d7ab66c4
--- /dev/null
+++ b/Documentation/features/locking/rwsem-optimized/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          rwsem-optimized
+#         Kconfig:       Optimized asm/rwsem.h
+#         description:   arch provides optimized rwsem APIs
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/perf/kprobes-event/arch-support.txt b/Documentation/features/perf/kprobes-event/arch-support.txt
new file mode 100644
index 000000000000..9855ad044386
--- /dev/null
+++ b/Documentation/features/perf/kprobes-event/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          kprobes-event
+#         Kconfig:       HAVE_REGS_AND_STACK_ACCESS_API
+#         description:   arch supports kprobes with perf events
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: |  ok  |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: | TODO |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/perf/perf-regs/arch-support.txt b/Documentation/features/perf/perf-regs/arch-support.txt
new file mode 100644
index 000000000000..e2b4a78ec543
--- /dev/null
+++ b/Documentation/features/perf/perf-regs/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          perf-regs
+#         Kconfig:       HAVE_PERF_REGS
+#         description:   arch supports perf events register access
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/perf/perf-stackdump/arch-support.txt b/Documentation/features/perf/perf-stackdump/arch-support.txt
new file mode 100644
index 000000000000..3dc24b0673c0
--- /dev/null
+++ b/Documentation/features/perf/perf-stackdump/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          perf-stackdump
+#         Kconfig:       HAVE_PERF_USER_STACK_DUMP
+#         description:   arch supports perf events stack dumps
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/sched/numa-balancing/arch-support.txt b/Documentation/features/sched/numa-balancing/arch-support.txt
new file mode 100644
index 000000000000..ac7cd6b1502b
--- /dev/null
+++ b/Documentation/features/sched/numa-balancing/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          numa-balancing
+#         Kconfig:       ARCH_SUPPORTS_NUMA_BALANCING
+#         description:   arch supports NUMA balancing
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ..  |
+    |         arm: |  ..  |
+    |       arm64: |  ..  |
+    |       avr32: |  ..  |
+    |    blackfin: |  ..  |
+    |         c6x: |  ..  |
+    |        cris: |  ..  |
+    |         frv: |  ..  |
+    |       h8300: |  ..  |
+    |     hexagon: |  ..  |
+    |        ia64: | TODO |
+    |        m32r: |  ..  |
+    |        m68k: |  ..  |
+    |       metag: |  ..  |
+    |  microblaze: |  ..  |
+    |        mips: | TODO |
+    |     mn10300: |  ..  |
+    |       nios2: |  ..  |
+    |    openrisc: |  ..  |
+    |      parisc: |  ..  |
+    |     powerpc: |  ok  |
+    |        s390: |  ..  |
+    |       score: |  ..  |
+    |          sh: |  ..  |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: |  ..  |
+    |   unicore32: |  ..  |
+    |         x86: |  ok  |
+    |      xtensa: |  ..  |
+    -----------------------
diff --git a/Documentation/features/seccomp/seccomp-filter/arch-support.txt b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
new file mode 100644
index 000000000000..bea800910342
--- /dev/null
+++ b/Documentation/features/seccomp/seccomp-filter/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          seccomp-filter
+#         Kconfig:       HAVE_ARCH_SECCOMP_FILTER
+#         description:   arch supports seccomp filters
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/time/arch-tick-broadcast/arch-support.txt b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
new file mode 100644
index 000000000000..8acb439a4a17
--- /dev/null
+++ b/Documentation/features/time/arch-tick-broadcast/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          arch-tick-broadcast
+#         Kconfig:       ARCH_HAS_TICK_BROADCAST
+#         description:   arch provides tick_broadcast()
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: | TODO |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/time/clockevents/arch-support.txt b/Documentation/features/time/clockevents/arch-support.txt
new file mode 100644
index 000000000000..ff670b2207f1
--- /dev/null
+++ b/Documentation/features/time/clockevents/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          clockevents
+#         Kconfig:       GENERIC_CLOCKEVENTS
+#         description:   arch support generic clock events
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: |  ok  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: |  ok  |
+    |    blackfin: |  ok  |
+    |         c6x: |  ok  |
+    |        cris: |  ok  |
+    |         frv: | TODO |
+    |       h8300: |  ok  |
+    |     hexagon: |  ok  |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: |  ok  |
+    |       metag: |  ok  |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: |  ok  |
+    |       nios2: |  ok  |
+    |    openrisc: |  ok  |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: |  ok  |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: |  ok  |
+    |   unicore32: |  ok  |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/time/context-tracking/arch-support.txt b/Documentation/features/time/context-tracking/arch-support.txt
new file mode 100644
index 000000000000..a1e3eea7003f
--- /dev/null
+++ b/Documentation/features/time/context-tracking/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          context-tracking
+#         Kconfig:       HAVE_CONTEXT_TRACKING
+#         description:   arch supports context tracking for NO_HZ_FULL
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/time/irq-time-acct/arch-support.txt b/Documentation/features/time/irq-time-acct/arch-support.txt
new file mode 100644
index 000000000000..e63316239938
--- /dev/null
+++ b/Documentation/features/time/irq-time-acct/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          irq-time-acct
+#         Kconfig:       HAVE_IRQ_TIME_ACCOUNTING
+#         description:   arch supports precise IRQ time accounting
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ..  |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ..  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ..  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: |  ..  |
+    |     powerpc: |  ..  |
+    |        s390: |  ..  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ..  |
+    |        tile: |  ..  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
new file mode 100644
index 000000000000..17f68a02e84d
--- /dev/null
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          modern-timekeeping
+#         Kconfig:       !ARCH_USES_GETTIMEOFFSET
+#         description:   arch does not use arch_gettimeoffset() anymore
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: |  ok  |
+    |         arm: | TODO |
+    |       arm64: |  ok  |
+    |       avr32: |  ok  |
+    |    blackfin: | TODO |
+    |         c6x: |  ok  |
+    |        cris: | TODO |
+    |         frv: |  ok  |
+    |       h8300: |  ok  |
+    |     hexagon: |  ok  |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: |  ok  |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: |  ok  |
+    |       nios2: |  ok  |
+    |    openrisc: |  ok  |
+    |      parisc: |  ok  |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: |  ok  |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: |  ok  |
+    |   unicore32: |  ok  |
+    |         x86: |  ok  |
+    |      xtensa: |  ok  |
+    -----------------------
diff --git a/Documentation/features/time/virt-cpuacct/arch-support.txt b/Documentation/features/time/virt-cpuacct/arch-support.txt
new file mode 100644
index 000000000000..cf3c3e383d15
--- /dev/null
+++ b/Documentation/features/time/virt-cpuacct/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          virt-cpuacct
+#         Kconfig:       HAVE_VIRT_CPU_ACCOUNTING
+#         description:   arch supports precise virtual CPU time accounting
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: |  ok  |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: |  ok  |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: |  ok  |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt
new file mode 100644
index 000000000000..ec4dd28e1297
--- /dev/null
+++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          ELF-ASLR
+#         Kconfig:       ARCH_HAS_ELF_RANDOMIZE
+#         description:   arch randomizes the stack, heap and binary images of ELF binaries
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/PG_uncached/arch-support.txt b/Documentation/features/vm/PG_uncached/arch-support.txt
new file mode 100644
index 000000000000..991974275a3e
--- /dev/null
+++ b/Documentation/features/vm/PG_uncached/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          PG_uncached
+#         Kconfig:       ARCH_USES_PG_UNCACHED
+#         description:   arch supports the PG_uncached page flag
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/THP/arch-support.txt b/Documentation/features/vm/THP/arch-support.txt
new file mode 100644
index 000000000000..972d02c2a74c
--- /dev/null
+++ b/Documentation/features/vm/THP/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          THP
+#         Kconfig:       HAVE_ARCH_TRANSPARENT_HUGEPAGE
+#         description:   arch supports transparent hugepages
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ..  |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: |  ..  |
+    |    blackfin: |  ..  |
+    |         c6x: |  ..  |
+    |        cris: |  ..  |
+    |         frv: |  ..  |
+    |       h8300: |  ..  |
+    |     hexagon: |  ..  |
+    |        ia64: | TODO |
+    |        m32r: |  ..  |
+    |        m68k: |  ..  |
+    |       metag: |  ..  |
+    |  microblaze: |  ..  |
+    |        mips: |  ok  |
+    |     mn10300: |  ..  |
+    |       nios2: |  ..  |
+    |    openrisc: |  ..  |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: |  ..  |
+    |          sh: |  ..  |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: |  ..  |
+    |   unicore32: |  ..  |
+    |         x86: |  ok  |
+    |      xtensa: |  ..  |
+    -----------------------
diff --git a/Documentation/features/vm/huge-vmap/arch-support.txt b/Documentation/features/vm/huge-vmap/arch-support.txt
new file mode 100644
index 000000000000..af6816bccb43
--- /dev/null
+++ b/Documentation/features/vm/huge-vmap/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          huge-vmap
+#         Kconfig:       HAVE_ARCH_HUGE_VMAP
+#         description:   arch supports the ioremap_pud_enabled() and ioremap_pmd_enabled() VM APIs
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: | TODO |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/ioremap_prot/arch-support.txt b/Documentation/features/vm/ioremap_prot/arch-support.txt
new file mode 100644
index 000000000000..90c53749fde7
--- /dev/null
+++ b/Documentation/features/vm/ioremap_prot/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          ioremap_prot
+#         Kconfig:       HAVE_IOREMAP_PROT
+#         description:   arch has ioremap_prot()
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ok  |
+    |         arm: | TODO |
+    |       arm64: | TODO |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: | TODO |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: | TODO |
+    |        tile: |  ok  |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/numa-memblock/arch-support.txt b/Documentation/features/vm/numa-memblock/arch-support.txt
new file mode 100644
index 000000000000..e7c252a0c531
--- /dev/null
+++ b/Documentation/features/vm/numa-memblock/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          numa-memblock
+#         Kconfig:       HAVE_MEMBLOCK_NODE_MAP
+#         description:   arch supports NUMA aware memblocks
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: |  ..  |
+    |         arm: |  ..  |
+    |       arm64: |  ..  |
+    |       avr32: |  ..  |
+    |    blackfin: |  ..  |
+    |         c6x: |  ..  |
+    |        cris: |  ..  |
+    |         frv: |  ..  |
+    |       h8300: |  ..  |
+    |     hexagon: |  ..  |
+    |        ia64: |  ok  |
+    |        m32r: | TODO |
+    |        m68k: |  ..  |
+    |       metag: |  ok  |
+    |  microblaze: |  ok  |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: |  ..  |
+    |    openrisc: |  ..  |
+    |      parisc: |  ..  |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: |  ok  |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: |  ..  |
+    |   unicore32: |  ..  |
+    |         x86: |  ok  |
+    |      xtensa: |  ..  |
+    -----------------------
diff --git a/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt b/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt
new file mode 100644
index 000000000000..26f74b457e0b
--- /dev/null
+++ b/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          pmdp_splitting_flush
+#         Kconfig:       __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+#         description:   arch supports the pmdp_splitting_flush() VM API
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: |  ok  |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: | TODO |
+    |       sparc: | TODO |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/features/vm/pte_special/arch-support.txt b/Documentation/features/vm/pte_special/arch-support.txt
new file mode 100644
index 000000000000..aaaa21db6226
--- /dev/null
+++ b/Documentation/features/vm/pte_special/arch-support.txt
@@ -0,0 +1,40 @@
+#
+# Feature name:          pte_special
+#         Kconfig:       __HAVE_ARCH_PTE_SPECIAL
+#         description:   arch supports the pte_special()/pte_mkspecial() VM APIs
+#
+    -----------------------
+    |         arch |status|
+    -----------------------
+    |       alpha: | TODO |
+    |         arc: | TODO |
+    |         arm: |  ok  |
+    |       arm64: |  ok  |
+    |       avr32: | TODO |
+    |    blackfin: | TODO |
+    |         c6x: | TODO |
+    |        cris: | TODO |
+    |         frv: | TODO |
+    |       h8300: | TODO |
+    |     hexagon: | TODO |
+    |        ia64: | TODO |
+    |        m32r: | TODO |
+    |        m68k: | TODO |
+    |       metag: | TODO |
+    |  microblaze: | TODO |
+    |        mips: | TODO |
+    |     mn10300: | TODO |
+    |       nios2: | TODO |
+    |    openrisc: | TODO |
+    |      parisc: | TODO |
+    |     powerpc: |  ok  |
+    |        s390: |  ok  |
+    |       score: | TODO |
+    |          sh: |  ok  |
+    |       sparc: |  ok  |
+    |        tile: | TODO |
+    |          um: | TODO |
+    |   unicore32: | TODO |
+    |         x86: |  ok  |
+    |      xtensa: | TODO |
+    -----------------------
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 0a926e2ba3ab..6a34a0f4d37c 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -50,8 +50,8 @@ prototypes:
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-	void * (*follow_link) (struct dentry *, struct nameidata *);
-	void (*put_link) (struct dentry *, struct nameidata *, void *);
+	const char *(*follow_link) (struct dentry *, void **);
+	void (*put_link) (struct inode *, void *);
 	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int, unsigned int);
 	int (*get_acl)(struct inode *, int);
diff --git a/Documentation/filesystems/automount-support.txt b/Documentation/filesystems/automount-support.txt
index 7cac200e2a85..7eb762eb3136 100644
--- a/Documentation/filesystems/automount-support.txt
+++ b/Documentation/filesystems/automount-support.txt
@@ -1,41 +1,15 @@
-Support is available for filesystems that wish to do automounting support (such
-as kAFS which can be found in fs/afs/). This facility includes allowing
-in-kernel mounts to be performed and mountpoint degradation to be
-requested. The latter can also be requested by userspace.
+Support is available for filesystems that wish to do automounting
+support (such as kAFS which can be found in fs/afs/ and NFS in
+fs/nfs/). This facility includes allowing in-kernel mounts to be
+performed and mountpoint degradation to be requested. The latter can
+also be requested by userspace.
 
 
 ======================
 IN-KERNEL AUTOMOUNTING
 ======================
 
-A filesystem can now mount another filesystem on one of its directories by the
-following procedure:
-
- (1) Give the directory a follow_link() operation.
-
-     When the directory is accessed, the follow_link op will be called, and
-     it will be provided with the location of the mountpoint in the nameidata
-     structure (vfsmount and dentry).
-
- (2) Have the follow_link() op do the following steps:
-
-     (a) Call vfs_kern_mount() to call the appropriate filesystem to set up a
-         superblock and gain a vfsmount structure representing it.
-
-     (b) Copy the nameidata provided as an argument and substitute the dentry
-	 argument into it the copy.
-
-     (c) Call do_add_mount() to install the new vfsmount into the namespace's
-	 mountpoint tree, thus making it accessible to userspace. Use the
-	 nameidata set up in (b) as the destination.
-
-	 If the mountpoint will be automatically expired, then do_add_mount()
-	 should also be given the location of an expiration list (see further
-	 down).
-
-     (d) Release the path in the nameidata argument and substitute in the new
-	 vfsmount and its root dentry. The ref counts on these will need
-	 incrementing.
+See section "Mount Traps" of  Documentation/filesystems/autofs4.txt
 
 Then from userspace, you can just do something like:
 
@@ -61,17 +35,18 @@ AUTOMATIC MOUNTPOINT EXPIRY
 ===========================
 
 Automatic expiration of mountpoints is easy, provided you've mounted the
-mountpoint to be expired in the automounting procedure outlined above.
+mountpoint to be expired in the automounting procedure outlined separately.
 
 To do expiration, you need to follow these steps:
 
- (3) Create at least one list off which the vfsmounts to be expired can be
-     hung. Access to this list will be governed by the vfsmount_lock.
+ (1) Create at least one list off which the vfsmounts to be expired can be
+     hung.
 
- (4) In step (2c) above, the call to do_add_mount() should be provided with a
-     pointer to this list. It will hang the vfsmount off of it if it succeeds.
+ (2) When a new mountpoint is created in the ->d_automount method, add
+     the mnt to the list using mnt_set_expiry()
+             mnt_set_expiry(newmnt, &afs_vfsmounts);
 
- (5) When you want mountpoints to be expired, call mark_mounts_for_expiry()
+ (3) When you want mountpoints to be expired, call mark_mounts_for_expiry()
      with a pointer to this list. This will process the list, marking every
      vfsmount thereon for potential expiry on the next call.
 
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index e69274de8d0c..68f1c9106573 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -379,10 +379,10 @@ may now be called in rcu-walk mode (nd->flags & LOOKUP_RCU). -ECHILD should be
 returned if the filesystem cannot handle rcu-walk. See
 Documentation/filesystems/vfs.txt for more details.
 
-	permission and check_acl are inode permission checks that are called
-on many or all directory inodes on the way down a path walk (to check for
-exec permission). These must now be rcu-walk aware (flags & IPERM_FLAG_RCU).
-See Documentation/filesystems/vfs.txt for more details.
+	permission is an inode permission check that is called on many or all
+directory inodes on the way down a path walk (to check for exec permission). It
+must now be rcu-walk aware (mask & MAY_NOT_BLOCK).  See
+Documentation/filesystems/vfs.txt for more details.
  
 --
 [mandatory]
@@ -483,3 +483,20 @@ in your dentry operations instead.
 --
 [mandatory]
 	->aio_read/->aio_write are gone.  Use ->read_iter/->write_iter.
+---
+[recommended]
+	for embedded ("fast") symlinks just set inode->i_link to wherever the
+	symlink body is and use simple_follow_link() as ->follow_link().
+--
+[mandatory]
+	calling conventions for ->follow_link() have changed.  Instead of returning
+	cookie and using nd_set_link() to store the body to traverse, we return
+	the body to traverse and store the cookie using explicit void ** argument.
+	nameidata isn't passed at all - nd_jump_link() doesn't need it and
+	nd_[gs]et_link() is gone.
+--
+[mandatory]
+	calling conventions for ->put_link() have changed.  It gets inode instead of
+	dentry,  it does not get nameidata at all and it gets called only when cookie
+	is non-NULL.  Note that link body isn't available anymore, so if you need it,
+	store it as cookie.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index c3b6b301d8b0..6f7fafde0884 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -205,7 +205,7 @@ asynchronous manner and the value may not be very precise. To see a precise
 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 It's slow but very precise.
 
-Table 1-2: Contents of the status files (as of 3.20.0)
+Table 1-2: Contents of the status files (as of 4.1)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
@@ -235,6 +235,7 @@ Table 1-2: Contents of the status files (as of 3.20.0)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmPMD                       size of second level page tables
  VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
diff --git a/Documentation/filesystems/quota.txt b/Documentation/filesystems/quota.txt
index 5e8de25bf0f1..29fc01552646 100644
--- a/Documentation/filesystems/quota.txt
+++ b/Documentation/filesystems/quota.txt
@@ -32,7 +32,10 @@ The interface uses generic netlink framework (see
 http://lwn.net/Articles/208755/ and http://people.suug.ch/~tgr/libnl/ for more
 details about this layer). The name of the quota generic netlink interface
 is "VFS_DQUOT". Definitions of constants below are in <linux/quota.h>.
-  Currently, the interface supports only one message type QUOTA_NL_C_WARNING.
+Since the quota netlink protocol is not namespace aware, quota netlink messages
+are sent only in initial network namespace.
+
+Currently, the interface supports only one message type QUOTA_NL_C_WARNING.
 This command is used to send a notification about any of the above mentioned
 events. Each message has six attributes. These are (type of the argument is
 in parentheses):
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 5d833b32bbcd..5eb8456fc41e 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -350,8 +350,8 @@ struct inode_operations {
 	int (*rename2) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
-        void * (*follow_link) (struct dentry *, struct nameidata *);
-        void (*put_link) (struct dentry *, struct nameidata *, void *);
+	const char *(*follow_link) (struct dentry *, void **);
+	void (*put_link) (struct inode *, void *);
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
@@ -436,16 +436,18 @@ otherwise noted.
 
   follow_link: called by the VFS to follow a symbolic link to the
 	inode it points to.  Only required if you want to support
-	symbolic links.  This method returns a void pointer cookie
-	that is passed to put_link().
+	symbolic links.  This method returns the symlink body
+	to traverse (and possibly resets the current position with
+	nd_jump_link()).  If the body won't go away until the inode
+	is gone, nothing else is needed; if it needs to be otherwise
+	pinned, the data needed to release whatever we'd grabbed
+	is to be stored in void * variable passed by address to
+	follow_link() instance.
 
   put_link: called by the VFS to release resources allocated by
-  	follow_link().  The cookie returned by follow_link() is passed
-  	to this method as the last parameter.  It is used by
-  	filesystems such as NFS where page cache is not stable
-  	(i.e. page that was installed when the symbolic link walk
-  	started might not be in the page cache at the end of the
-  	walk).
+	follow_link().  The cookie stored by follow_link() is passed
+	to this method as the last parameter; only called when
+	cookie isn't NULL.
 
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
@@ -797,7 +799,7 @@ struct file_operations
 ----------------------
 
 This describes how the VFS can manipulate an open file. As of kernel
-3.12, the following members are defined:
+4.1, the following members are defined:
 
 struct file_operations {
 	struct module *owner;
@@ -811,8 +813,9 @@ struct file_operations {
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
+	int (*mremap)(struct file *, struct vm_area_struct *);
 	int (*open) (struct inode *, struct file *);
-	int (*flush) (struct file *);
+	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
 	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
 	int (*aio_fsync) (struct kiocb *, int datasync);
@@ -822,11 +825,15 @@ struct file_operations {
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
 	int (*flock) (struct file *, int, struct file_lock *);
-	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
-	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
-	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
+	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
+	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
+	int (*setlease)(struct file *, long, struct file_lock **, void **);
+	long (*fallocate)(struct file *file, int mode, loff_t offset,
+			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
+#ifndef CONFIG_MMU
+	unsigned (*mmap_capabilities)(struct file *);
+#endif
 };
 
 Again, all methods are called without any locks being held, unless
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index c21c1313f09e..75542b91b766 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -241,18 +241,18 @@ Set multiple GPIO outputs with a single function call
 -----------------------------------------------------
 The following functions set the output values of an array of GPIOs:
 
-	void gpiod_set_array(unsigned int array_size,
-			     struct gpio_desc **desc_array,
-			     int *value_array)
-	void gpiod_set_raw_array(unsigned int array_size,
-				 struct gpio_desc **desc_array,
-				 int *value_array)
-	void gpiod_set_array_cansleep(unsigned int array_size,
-				      struct gpio_desc **desc_array,
-				      int *value_array)
-	void gpiod_set_raw_array_cansleep(unsigned int array_size,
-					  struct gpio_desc **desc_array,
-					  int *value_array)
+	void gpiod_set_array_value(unsigned int array_size,
+				   struct gpio_desc **desc_array,
+				   int *value_array)
+	void gpiod_set_raw_array_value(unsigned int array_size,
+				       struct gpio_desc **desc_array,
+				       int *value_array)
+	void gpiod_set_array_value_cansleep(unsigned int array_size,
+					    struct gpio_desc **desc_array,
+					    int *value_array)
+	void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
+						struct gpio_desc **desc_array,
+						int *value_array)
 
 The array can be an arbitrary set of GPIOs. The functions will try to set
 GPIOs belonging to the same bank or chip simultaneously if supported by the
@@ -271,8 +271,8 @@ matches the desired group of GPIOs, those GPIOs can be set by simply using
 the struct gpio_descs returned by gpiod_get_array():
 
 	struct gpio_descs *my_gpio_descs = gpiod_get_array(...);
-	gpiod_set_array(my_gpio_descs->ndescs, my_gpio_descs->desc,
-			my_gpio_values);
+	gpiod_set_array_value(my_gpio_descs->ndescs, my_gpio_descs->desc,
+			      my_gpio_values);
 
 It is also possible to set a completely arbitrary array of descriptors. The
 descriptors may be obtained using any combination of gpiod_get() and
@@ -290,7 +290,7 @@ corresponding to a given GPIO using the following call:
 
 	int gpiod_to_irq(const struct gpio_desc *desc)
 
-It will return an IRQ number, or an negative errno code if the mapping can't be
+It will return an IRQ number, or a negative errno code if the mapping can't be
 done (most likely because that particular GPIO cannot be used as IRQ). It is an
 unchecked error to use a GPIO that wasn't set up as an input using
 gpiod_direction_input(), or to use an IRQ number that didn't originally come
diff --git a/Documentation/gpio/gpio-legacy.txt b/Documentation/gpio/gpio-legacy.txt
index 6f83fa965b4b..79ab5648d69b 100644
--- a/Documentation/gpio/gpio-legacy.txt
+++ b/Documentation/gpio/gpio-legacy.txt
@@ -751,9 +751,6 @@ requested using gpio_request():
 	int gpio_export_link(struct device *dev, const char *name,
 		unsigned gpio)
 
-	/* change the polarity of a GPIO node in sysfs */
-	int gpio_sysfs_set_active_low(unsigned gpio, int value);
-
 After a kernel driver requests a GPIO, it may only be made available in
 the sysfs interface by gpio_export().  The driver can control whether the
 signal direction may change.  This helps drivers prevent userspace code
@@ -767,9 +764,3 @@ After the GPIO has been exported, gpio_export_link() allows creating
 symlinks from elsewhere in sysfs to the GPIO sysfs node.  Drivers can
 use this to provide the interface under their own device in sysfs with
 a descriptive name.
-
-Drivers can use gpio_sysfs_set_active_low() to hide GPIO line polarity
-differences between boards from user space.  This only affects the
-sysfs interface.  Polarity change can be done both before and after
-gpio_export(), and previously enabled poll(2) support for either
-rising or falling edge will be reconfigured to follow this setting.
diff --git a/Documentation/gpio/sysfs.txt b/Documentation/gpio/sysfs.txt
index c2c3a97f8ff7..535b6a8a7a7c 100644
--- a/Documentation/gpio/sysfs.txt
+++ b/Documentation/gpio/sysfs.txt
@@ -132,9 +132,6 @@ requested using gpio_request():
 	int gpiod_export_link(struct device *dev, const char *name,
 		      struct gpio_desc *desc);
 
-	/* change the polarity of a GPIO node in sysfs */
-	int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value);
-
 After a kernel driver requests a GPIO, it may only be made available in
 the sysfs interface by gpiod_export(). The driver can control whether the
 signal direction may change. This helps drivers prevent userspace code
@@ -148,8 +145,3 @@ After the GPIO has been exported, gpiod_export_link() allows creating
 symlinks from elsewhere in sysfs to the GPIO sysfs node. Drivers can
 use this to provide the interface under their own device in sysfs with
 a descriptive name.
-
-Drivers can use gpiod_sysfs_set_active_low() to hide GPIO line polarity
-differences between boards from user space. Polarity change can be done both
-before and after gpiod_export(), and previously enabled poll(2) support for
-either rising or falling edge will be reconfigured to follow this setting.
diff --git a/Documentation/hwmon/ntc_thermistor b/Documentation/hwmon/ntc_thermistor
index c5e05e2900a3..1d4cc847c6fe 100644
--- a/Documentation/hwmon/ntc_thermistor
+++ b/Documentation/hwmon/ntc_thermistor
@@ -2,8 +2,10 @@ Kernel driver ntc_thermistor
 =================
 
 Supported thermistors from Murata:
-* Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333
-  Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473', 'ncp15wl333'
+* Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473,
+  NCP15WL333, NCP03WF104
+  Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473',
+  'ncp15wl333', 'ncp03wf104'
   Datasheet: Publicly available at Murata
 
 Supported thermistors from EPCOS:
diff --git a/Documentation/hwmon/tc74 b/Documentation/hwmon/tc74
new file mode 100644
index 000000000000..43027aad5f8e
--- /dev/null
+++ b/Documentation/hwmon/tc74
@@ -0,0 +1,20 @@
+Kernel driver tc74
+====================
+
+Supported chips:
+   * Microchip TC74
+     Prefix: 'tc74'
+     Datasheet: Publicly available at Microchip website.
+
+Description
+-----------
+
+Driver supports the above part.
+
+The tc74 has an 8-bit sensor, with 1 degree centigrade resolution
+and +- 2 degrees centigrade accuracy.
+
+Notes
+-----
+
+Currently entering low power standby mode is not supported.
diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401
index 8eb88e974055..711f75e189eb 100644
--- a/Documentation/hwmon/tmp401
+++ b/Documentation/hwmon/tmp401
@@ -20,7 +20,7 @@ Supported chips:
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html
   * Texas Instruments TMP435
     Prefix: 'tmp435'
-    Addresses scanned: I2C 0x37, 0x48 - 0x4f
+    Addresses scanned: I2C 0x48 - 0x4f
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html
 
 Authors:
diff --git a/Documentation/i2c/slave-interface b/Documentation/i2c/slave-interface
index 389bb5d61854..b228ca54bcf4 100644
--- a/Documentation/i2c/slave-interface
+++ b/Documentation/i2c/slave-interface
@@ -31,10 +31,10 @@ User manual
 ===========
 
 I2C slave backends behave like standard I2C clients. So, you can instantiate
-them like described in the document 'instantiating-devices'. A quick example
-for instantiating the slave-eeprom driver from userspace:
+them as described in the document 'instantiating-devices'. A quick example for
+instantiating the slave-eeprom driver from userspace at address 0x64 on bus 1:
 
-  # echo 0-0064 > /sys/bus/i2c/drivers/i2c-slave-eeprom/bind
+  # echo slave-24c02 0x64 > /sys/bus/i2c/devices/i2c-1/new_device
 
 Each backend should come with separate documentation to describe its specific
 behaviour and setup.
diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt
index 92e68bce13a4..5737e3590adb 100644
--- a/Documentation/input/rotary-encoder.txt
+++ b/Documentation/input/rotary-encoder.txt
@@ -33,7 +33,7 @@ The phase diagram of these two outputs look like this:
 	          one step (half-period mode)
 
 For more information, please see
-	http://en.wikipedia.org/wiki/Rotary_encoder
+	https://en.wikipedia.org/wiki/Rotary_encoder
 
 
 1. Events / state machine
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index b61885c35ce1..5a0f2bdc2cf9 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -445,7 +445,7 @@ MAINTAINERS ファイルにリストがありますので参照してくださ�
 メールの先頭でなく、各引用行の間にあなたの言いたいことを追加するべきで
 す。
 
-もしパッチをメールに付ける場合は、Documentaion/SubmittingPatches に提
+もしパッチをメールに付ける場合は、Documentation/SubmittingPatches に提
 示されているように、それは プレーンな可読テキストにすることを忘れない
 ようにしましょう。カーネル開発者は 添付や圧縮したパッチを扱いたがりま
 せん-
diff --git a/Documentation/kasan.txt b/Documentation/kasan.txt
index 092fc10961fe..0d32355a4c34 100644
--- a/Documentation/kasan.txt
+++ b/Documentation/kasan.txt
@@ -9,7 +9,9 @@ a fast and comprehensive solution for finding use-after-free and out-of-bounds
 bugs.
 
 KASan uses compile-time instrumentation for checking every memory access,
-therefore you will need a certain version of GCC > 4.9.2
+therefore you will need a gcc version of 4.9.2 or later. KASan could detect out
+of bounds accesses to stack or global variables, but only if gcc 5.0 or later was
+used to built the kernel.
 
 Currently KASan is supported only for x86_64 architecture and requires that the
 kernel be built with the SLUB allocator.
@@ -23,8 +25,8 @@ To enable KASAN configure kernel with:
 
 and choose between CONFIG_KASAN_OUTLINE and CONFIG_KASAN_INLINE. Outline/inline
 is compiler instrumentation types. The former produces smaller binary the
-latter is 1.1 - 2 times faster. Inline instrumentation requires GCC 5.0 or
-latter.
+latter is 1.1 - 2 times faster. Inline instrumentation requires a gcc version
+of 5.0 or later.
 
 Currently KASAN works only with the SLUB memory allocator.
 For better bug detection and nicer report, enable CONFIG_STACKTRACE and put
@@ -148,7 +150,7 @@ AddressSanitizer dedicates 1/8 of kernel memory to its shadow memory
 (e.g. 16TB to cover 128TB on x86_64) and uses direct mapping with a scale and
 offset to translate a memory address to its corresponding shadow address.
 
-Here is the function witch translate an address to its corresponding shadow
+Here is the function which translates an address to its corresponding shadow
 address:
 
 static inline void *kasan_mem_to_shadow(const void *addr)
diff --git a/Documentation/kbuild/headers_install.txt b/Documentation/kbuild/headers_install.txt
index 951eb9f1e040..f0153adb95e2 100644
--- a/Documentation/kbuild/headers_install.txt
+++ b/Documentation/kbuild/headers_install.txt
@@ -24,7 +24,7 @@ The "make headers_install" command can be run in the top level directory of the
 kernel source code (or using a standard out-of-tree build).  It takes two
 optional arguments:
 
-  make headers_install ARCH=i386 INSTALL_HDR_PATH=/usr/include
+  make headers_install ARCH=i386 INSTALL_HDR_PATH=/usr
 
 ARCH indicates which architecture to produce headers for, and defaults to the
 current architecture.  The linux/asm directory of the exported kernel headers
@@ -33,8 +33,11 @@ the command:
 
   ls -d include/asm-* | sed 's/.*-//'
 
-INSTALL_HDR_PATH indicates where to install the headers.  It defaults to
-"./usr/include".
+INSTALL_HDR_PATH indicates where to install the headers. It defaults to
+"./usr".
+
+An 'include' directory is automatically created inside INSTALL_HDR_PATH and
+headers are installed in 'INSTALL_HDR_PATH/include'.
 
 The command "make headers_install_all" exports headers for all architectures
 simultaneously.  (This is mostly of interest to distribution maintainers,
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 74b6c6d97210..e63b446d973c 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -755,8 +755,8 @@ Additional files can be specified in kbuild makefiles by use of $(clean-files).
 		#lib/Makefile
 		clean-files := crc32table.h
 
-When executing "make clean", the two files "devlist.h classlist.h" will be
-deleted. Kbuild will assume files to be in the same relative directory as the
+When executing "make clean", the file "crc32table.h" will be deleted.
+Kbuild will assume files to be in the same relative directory as the
 Makefile, except if prefixed with $(objtree).
 
 To delete a directory hierarchy use:
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 61ab1628a057..fd66d220c115 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -179,11 +179,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 			See also Documentation/power/runtime_pm.txt, pci=noacpi
 
-	acpi_rsdp=	[ACPI,EFI,KEXEC]
-			Pass the RSDP address to the kernel, mostly used
-			on machines running EFI runtime service to boot the
-			second kernel for kdump.
-
 	acpi_apic_instance=	[ACPI, IOAPIC]
 			Format: <int>
 			2: use 2nd APIC table, if available
@@ -197,6 +192,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			(e.g. thinkpad_acpi, sony_acpi, etc.) instead
 			of the ACPI video.ko driver.
 
+	acpica_no_return_repair [HW, ACPI]
+			Disable AML predefined validation mechanism
+			This mechanism can repair the evaluation result to make
+			the return objects more ACPI specification compliant.
+			This option is useful for developers to identify the
+			root cause of an AML interpreter issue when the issue
+			has something to do with the repair mechanism.
+
 	acpi.debug_layer=	[HW,ACPI,ACPI_DEBUG]
 	acpi.debug_level=	[HW,ACPI,ACPI_DEBUG]
 			Format: <int>
@@ -225,6 +228,22 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			unusable.  The "log_buf_len" parameter may be useful
 			if you need to capture more output.
 
+	acpi_enforce_resources=	[ACPI]
+			{ strict | lax | no }
+			Check for resource conflicts between native drivers
+			and ACPI OperationRegions (SystemIO and SystemMemory
+			only). IO ports and memory declared in ACPI might be
+			used by the ACPI subsystem in arbitrary AML code and
+			can interfere with legacy drivers.
+			strict (default): access to resources claimed by ACPI
+			is denied; legacy drivers trying to access reserved
+			resources will fail to bind to device using them.
+			lax: access to resources claimed by ACPI is allowed;
+			legacy drivers trying to access reserved resources
+			will bind successfully but a warning message is logged.
+			no: ACPI OperationRegions are not marked as reserved,
+			no further checks are performed.
+
 	acpi_force_table_verification	[HW,ACPI]
 			Enable table checksum verification during early stage.
 			By default, this is disabled due to x86 early mapping
@@ -253,6 +272,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			This feature is enabled by default.
 			This option allows to turn off the feature.
 
+	acpi_no_memhotplug [ACPI] Disable memory hotplug.  Useful for kdump
+			   kernels.
+
 	acpi_no_static_ssdt	[HW,ACPI]
 			Disable installation of static SSDTs at early boot time
 			By default, SSDTs contained in the RSDT/XSDT will be
@@ -263,13 +285,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			dynamic table installation which will install SSDT
 			tables to /sys/firmware/acpi/tables/dynamic.
 
-	acpica_no_return_repair [HW, ACPI]
-			Disable AML predefined validation mechanism
-			This mechanism can repair the evaluation result to make
-			the return objects more ACPI specification compliant.
-			This option is useful for developers to identify the
-			root cause of an AML interpreter issue when the issue
-			has something to do with the repair mechanism.
+	acpi_rsdp=	[ACPI,EFI,KEXEC]
+			Pass the RSDP address to the kernel, mostly used
+			on machines running EFI runtime service to boot the
+			second kernel for kdump.
 
 	acpi_os_name=	[HW,ACPI] Tell ACPI BIOS the name of the OS
 			Format: To spoof as Windows 98: ="Microsoft Windows"
@@ -365,25 +384,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Use timer override. For some broken Nvidia NF5 boards
 			that require a timer override, but don't have HPET
 
-	acpi_enforce_resources=	[ACPI]
-			{ strict | lax | no }
-			Check for resource conflicts between native drivers
-			and ACPI OperationRegions (SystemIO and SystemMemory
-			only). IO ports and memory declared in ACPI might be
-			used by the ACPI subsystem in arbitrary AML code and
-			can interfere with legacy drivers.
-			strict (default): access to resources claimed by ACPI
-			is denied; legacy drivers trying to access reserved
-			resources will fail to bind to device using them.
-			lax: access to resources claimed by ACPI is allowed;
-			legacy drivers trying to access reserved resources
-			will bind successfully but a warning message is logged.
-			no: ACPI OperationRegions are not marked as reserved,
-			no further checks are performed.
-
-	acpi_no_memhotplug [ACPI] Disable memory hotplug.  Useful for kdump
-			   kernels.
-
 	add_efi_memmap	[EFI; X86] Include EFI memory map in
 			kernel's map of available physical RAM.
 
@@ -746,6 +746,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	cpuidle.off=1	[CPU_IDLE]
 			disable the cpuidle sub-system
 
+	cpu_init_udelay=N
+			[X86] Delay for N microsec between assert and de-assert
+			of APIC INIT to start processors.  This delay occurs
+			on every CPU online, such as boot, and resume from suspend.
+			Default: 10000
+
 	cpcihp_generic=	[HW,PCI] Generic port I/O CompactPCI driver
 			Format:
 			<first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>]
@@ -937,6 +943,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Enable debug messages at boot time.  See
 			Documentation/dynamic-debug-howto.txt for details.
 
+	nompx		[X86] Disables Intel Memory Protection Extensions.
+			See Documentation/x86/intel_mpx.txt for more
+			information about the feature.
+
 	eagerfpu=	[X86]
 			on	enable eager fpu restore
 			off	disable eager fpu restore
@@ -1009,6 +1019,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			earlyprintk=serial[,0x...[,baudrate]]
 			earlyprintk=ttySn[,baudrate]
 			earlyprintk=dbgp[debugController#]
+			earlyprintk=pciserial,bus:device.function[,baudrate]
 
 			earlyprintk is useful when the kernel crashes before
 			the normal console is initialized. It is not enabled by
@@ -1481,6 +1492,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			By default, super page will be supported if Intel IOMMU
 			has the capability. With this option, super page will
 			not be supported.
+		ecs_off [Default Off]
+			By default, extended context tables will be supported if
+			the hardware advertises that it has support both for the
+			extended tables themselves, and also PASID support. With
+			this option set, extended tables will not be used even
+			on hardware which claims to support them.
 
 	intel_idle.max_cstate=	[KNL,HW,ACPI,X86]
 			0	disables intel_idle and fall back on acpi_idle.
@@ -2437,7 +2454,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	nomca		[IA-64] Disable machine check abort handling
 
-	nomce		[X86-32] Machine Check Exception
+	nomce		[X86-32] Disable Machine Check Exception
 
 	nomfgpt		[X86-32] Disable Multi-Function General Purpose
 			Timer usage (for AMD Geode machines).
@@ -2992,11 +3009,34 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Set maximum number of finished RCU callbacks to
 			process in one batch.
 
+	rcutree.dump_tree=	[KNL]
+			Dump the structure of the rcu_node combining tree
+			out at early boot.  This is used for diagnostic
+			purposes, to verify correct tree setup.
+
+	rcutree.gp_cleanup_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period cleanup.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP is set.
+
 	rcutree.gp_init_delay=	[KNL]
 			Set the number of jiffies to delay each step of
 			RCU grace-period initialization.  This only has
-			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT is
-			set.
+			effect when CONFIG_RCU_TORTURE_TEST_SLOW_INIT
+			is set.
+
+	rcutree.gp_preinit_delay=	[KNL]
+			Set the number of jiffies to delay each step of
+			RCU grace-period pre-initialization, that is,
+			the propagation of recent CPU-hotplug changes up
+			the rcu_node combining tree.  This only has effect
+			when CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT is set.
+
+	rcutree.rcu_fanout_exact= [KNL]
+			Disable autobalancing of the rcu_node combining
+			tree.  This is used by rcutorture, and might
+			possibly be useful for architectures having high
+			cache-to-cache transfer latencies.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -3101,7 +3141,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			test, hence the "fake".
 
 	rcutorture.nreaders= [KNL]
-			Set number of RCU readers.
+			Set number of RCU readers.  The value -1 selects
+			N-1, where N is the number of CPUs.  A value
+			"n" less than -1 selects N-n-2, where N is again
+			the number of CPUs.  For example, -2 selects N
+			(the number of CPUs), -3 selects N+1, and so on.
 
 	rcutorture.object_debug= [KNL]
 			Enable debug-object double-call_rcu() testing.
diff --git a/Documentation/kmemleak.txt b/Documentation/kmemleak.txt
index 45e777f4e41d..18e24abb3ecf 100644
--- a/Documentation/kmemleak.txt
+++ b/Documentation/kmemleak.txt
@@ -6,7 +6,7 @@ Introduction
 
 Kmemleak provides a way of detecting possible kernel memory leaks in a
 way similar to a tracing garbage collector
-(http://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
+(https://en.wikipedia.org/wiki/Garbage_collection_%28computer_science%29#Tracing_garbage_collectors),
 with the difference that the orphan objects are not freed but only
 reported via /sys/kernel/debug/kmemleak. A similar method is used by the
 Valgrind tool (memcheck --leak-check) to detect the memory leaks in
diff --git a/Documentation/laptops/.gitignore b/Documentation/laptops/.gitignore
index da2bd065f4bc..9fc984e64386 100644
--- a/Documentation/laptops/.gitignore
+++ b/Documentation/laptops/.gitignore
@@ -1,2 +1 @@
 dslm
-freefall
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index a3b4f209e562..7c0ac2a26b9e 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -8,8 +8,6 @@ disk-shock-protection.txt
 	- information on hard disk shock protection.
 dslm.c
 	- Simple Disk Sleep Monitor program
-freefall.c
-	- (HP/DELL) laptop accelerometer program for disk protection.
 laptop-mode.txt
 	- how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile
index 2b0fa5edf1d3..0abe44f68965 100644
--- a/Documentation/laptops/Makefile
+++ b/Documentation/laptops/Makefile
@@ -1,5 +1,5 @@
 # List of programs to build
-hostprogs-y := dslm freefall
+hostprogs-y := dslm
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 79699c200766..62261c04060a 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -2,9 +2,6 @@
 LED handling under Linux
 ========================
 
-If you're reading this and thinking about keyboard leds, these are
-handled by the input subsystem and the led class is *not* needed.
-
 In its simplest form, the LED class just allows control of LEDs from
 userspace. LEDs appear in /sys/class/leds/. The maximum brightness of the
 LED is defined in max_brightness file. The brightness file will set the brightness
diff --git a/Documentation/lockup-watchdogs.txt b/Documentation/lockup-watchdogs.txt
index ab0baa692c13..22dd6af2e4bd 100644
--- a/Documentation/lockup-watchdogs.txt
+++ b/Documentation/lockup-watchdogs.txt
@@ -61,3 +61,21 @@ As explained above, a kernel knob is provided that allows
 administrators to configure the period of the hrtimer and the perf
 event. The right value for a particular environment is a trade-off
 between fast response to lockups and detection overhead.
+
+By default, the watchdog runs on all online cores.  However, on a
+kernel configured with NO_HZ_FULL, by default the watchdog runs only
+on the housekeeping cores, not the cores specified in the "nohz_full"
+boot argument.  If we allowed the watchdog to run by default on
+the "nohz_full" cores, we would have to run timer ticks to activate
+the scheduler, which would prevent the "nohz_full" functionality
+from protecting the user code on those cores from the kernel.
+Of course, disabling it by default on the nohz_full cores means that
+when those cores do enter the kernel, by default we will not be
+able to detect if they lock up.  However, allowing the watchdog
+to continue to run on the housekeeping (non-tickless) cores means
+that we will continue to detect lockups properly on those cores.
+
+In either case, the set of cores excluded from running the watchdog
+may be adjusted via the kernel.watchdog_cpumask sysctl.  For
+nohz_full cores, this may be useful for debugging a case where the
+kernel seems to be hanging on the nohz_full cores.
diff --git a/Documentation/magic-number.txt b/Documentation/magic-number.txt
index 4c8e142db2ef..28befed9f610 100644
--- a/Documentation/magic-number.txt
+++ b/Documentation/magic-number.txt
@@ -116,7 +116,6 @@ COW_MAGIC             0x4f4f4f4d  cow_header_v1     arch/um/drivers/ubd_user.c
 I810_CARD_MAGIC       0x5072696E  i810_card         sound/oss/i810_audio.c
 TRIDENT_CARD_MAGIC    0x5072696E  trident_card      sound/oss/trident.c
 ROUTER_MAGIC          0x524d4157  wan_device        [in wanrouter.h pre 3.9]
-SCC_MAGIC             0x52696368  gs_port           drivers/char/scc.h
 SAVEKMSG_MAGIC1       0x53415645  savekmsg          arch/*/amiga/config.c
 GDA_MAGIC             0x58464552  gda               arch/mips/include/asm/sn/gda.h
 RED_MAGIC1            0x5a2cf071  (any)             mm/slab.c
@@ -138,7 +137,6 @@ KMALLOC_MAGIC         0x87654321  snd_alloc_track   sound/core/memory.c
 PWC_MAGIC             0x89DC10AB  pwc_device        drivers/usb/media/pwc.h
 NBD_REPLY_MAGIC       0x96744668  nbd_reply         include/linux/nbd.h
 ENI155_MAGIC          0xa54b872d  midway_eprom	    drivers/atm/eni.h
-SCI_MAGIC             0xbabeface  gs_port           drivers/char/sh-sci.h
 CODA_MAGIC            0xC0DAC0DA  coda_file_info    fs/coda/coda_fs_i.h
 DPMEM_MAGIC           0xc0ffee11  gdt_pci_sram      drivers/scsi/gdth.h
 YAM_MAGIC             0xF10A7654  yam_port          drivers/net/hamradio/yam.c
diff --git a/Documentation/md.txt b/Documentation/md.txt
index f925666e4342..1a2ada46aaed 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -549,7 +549,7 @@ also have
    sync_speed_max
      This are similar to /proc/sys/dev/raid/speed_limit_{min,max}
      however they only apply to the particular array.
-     If no value has been written to these, of if the word 'system'
+     If no value has been written to these, or if the word 'system'
      is written, then the system-wide value is used.  If a value,
      in kibibytes-per-second is written, then it is used.
      When the files are read, they show the currently active value
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f95746189b5d..13feb697271f 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -617,16 +617,16 @@ case what's actually required is:
 However, stores are not speculated.  This means that ordering -is- provided
 for load-store control dependencies, as in the following example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 	}
 
-Control dependencies pair normally with other types of barriers.
-That said, please note that ACCESS_ONCE() is not optional!  Without the
-ACCESS_ONCE(), might combine the load from 'a' with other loads from
-'a', and the store to 'b' with other stores to 'b', with possible highly
-counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers.  That
+said, please note that READ_ONCE_CTRL() is not optional!  Without the
+READ_ONCE_CTRL(), the compiler might combine the load from 'a' with
+other loads from 'a', and the store to 'b' with other stores to 'b',
+with possible highly counterintuitive effects on ordering.
 
 Worse yet, if the compiler is able to prove (say) that the value of
 variable 'a' is always non-zero, it would be well within its rights
@@ -636,12 +636,15 @@ as follows:
 	q = a;
 	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
 
-So don't leave out the ACCESS_ONCE().
+Finally, the READ_ONCE_CTRL() includes an smp_read_barrier_depends()
+that DEC Alpha needs in order to respect control depedencies.
+
+So don't leave out the READ_ONCE_CTRL().
 
 It is tempting to try to enforce ordering on identical stores on both
 branches of the "if" statement as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		barrier();
 		ACCESS_ONCE(b) = p;
@@ -655,7 +658,7 @@ branches of the "if" statement as follows:
 Unfortunately, current compilers will transform this as follows at high
 optimization levels:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	barrier();
 	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
@@ -685,7 +688,7 @@ memory barriers, for example, smp_store_release():
 In contrast, without explicit memory barriers, two-legged-if control
 ordering is guaranteed only when the stores differ, for example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -694,14 +697,14 @@ ordering is guaranteed only when the stores differ, for example:
 		do_something_else();
 	}
 
-The initial ACCESS_ONCE() is still required to prevent the compiler from
-proving the value of 'a'.
+The initial READ_ONCE_CTRL() is still required to prevent the compiler
+from proving the value of 'a'.
 
 In addition, you need to be careful what you do with the local variable 'q',
 otherwise the compiler might be able to guess the value and again remove
 the needed conditional.  For example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
 		do_something();
@@ -714,7 +717,7 @@ If MAX is defined to be 1, then the compiler knows that (q % MAX) is
 equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = p;
 	do_something_else();
 
@@ -725,7 +728,7 @@ is gone, and the barrier won't bring it back.  Therefore, if you are
 relying on this ordering, you should make sure that MAX is greater than
 one, perhaps as follows:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
 		ACCESS_ONCE(b) = p;
@@ -742,14 +745,15 @@ of the 'if' statement.
 You must also be careful not to rely too much on boolean short-circuit
 evaluation.  Consider this example:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	if (a || 1 > 0)
 		ACCESS_ONCE(b) = 1;
 
-Because the second condition is always true, the compiler can transform
-this example as following, defeating control dependency:
+Because the first condition cannot fault and the second condition is
+always true, the compiler can transform this example as following,
+defeating control dependency:
 
-	q = ACCESS_ONCE(a);
+	q = READ_ONCE_CTRL(a);
 	ACCESS_ONCE(b) = 1;
 
 This example underscores the need to ensure that the compiler cannot
@@ -762,8 +766,8 @@ demonstrated by two related examples, with the initial values of
 x and y both being zero:
 
 	CPU 0                     CPU 1
-	=====================     =====================
-	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+	=======================   =======================
+	r1 = READ_ONCE_CTRL(x);   r2 = READ_ONCE_CTRL(y);
 	if (r1 > 0)               if (r2 > 0)
 	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
 
@@ -783,7 +787,8 @@ But because control dependencies do -not- provide transitivity, the above
 assertion can fail after the combined three-CPU example completes.  If you
 need the three-CPU example to provide ordering, you will need smp_mb()
 between the loads and stores in the CPU 0 and CPU 1 code fragments,
-that is, just before or just after the "if" statements.
+that is, just before or just after the "if" statements.  Furthermore,
+the original two-CPU example is very fragile and should be avoided.
 
 These two examples are the LB and WWC litmus tests from this paper:
 http://www.cl.cam.ac.uk/users/pes20/ppc-supplemental/test6.pdf and this
@@ -791,6 +796,12 @@ site: https://www.cl.cam.ac.uk/~pes20/ppcmem/index.html.
 
 In summary:
 
+  (*) Control dependencies must be headed by READ_ONCE_CTRL().
+      Or, as a much less preferable alternative, interpose
+      be headed by READ_ONCE() or an ACCESS_ONCE() read and must
+      have smp_read_barrier_depends() between this read and the
+      control-dependent write.
+
   (*) Control dependencies can order prior loads against later stores.
       However, they do -not- guarantee any other sort of ordering:
       Not prior loads against later loads, nor prior stores against
@@ -1662,7 +1673,7 @@ CPU from reordering them.
 
 There are some more advanced barrier functions:
 
- (*) set_mb(var, value)
+ (*) smp_store_mb(var, value)
 
      This assigns the value to the variable and then inserts a full memory
      barrier after it, depending on the function.  It isn't guaranteed to
@@ -1784,10 +1795,9 @@ for each construct.  These operations all imply certain barriers:
 
      Memory operations issued before the ACQUIRE may be completed after
      the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
-     combined with a following ACQUIRE, orders prior loads against
-     subsequent loads and stores and also orders prior stores against
-     subsequent stores.  Note that this is weaker than smp_mb()!  The
-     smp_mb__before_spinlock() primitive is free on many architectures.
+     combined with a following ACQUIRE, orders prior stores against
+     subsequent loads and stores. Note that this is weaker than smp_mb()!
+     The smp_mb__before_spinlock() primitive is free on many architectures.
 
  (2) RELEASE operation implication:
 
@@ -1975,7 +1985,7 @@ after it has altered the task state:
 	CPU 1
 	===============================
 	set_current_state();
-	  set_mb();
+	  smp_store_mb();
 	    STORE current->state
 	    <general barrier>
 	LOAD event_indicated
@@ -2016,7 +2026,7 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING:
 	CPU 1				CPU 2
 	===============================	===============================
 	set_current_state();		STORE event_indicated
-	  set_mb();			wake_up();
+	  smp_store_mb();		wake_up();
 	    STORE current->state	  <write barrier>
 	    <general barrier>		  STORE current->state
 	LOAD event_indicated
diff --git a/Documentation/mic/mpssd/Makefile b/Documentation/mic/mpssd/Makefile
index f47fe6ba7300..06871b0c08a6 100644
--- a/Documentation/mic/mpssd/Makefile
+++ b/Documentation/mic/mpssd/Makefile
@@ -1,3 +1,4 @@
+ifndef CROSS_COMPILE
 # List of programs to build
 hostprogs-$(CONFIG_X86_64) := mpssd
 
@@ -17,3 +18,4 @@ HOSTLOADLIBES_mpssd := -lpthread
 install:
 	install mpssd /usr/sbin/mpssd
 	install micctrl /usr/sbin/micctrl
+endif
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index 83bf4986baea..334b49ef02d1 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -51,6 +51,7 @@ Table of Contents
 3.4	Configuring Bonding Manually via Sysfs
 3.5	Configuration with Interfaces Support
 3.6	Overriding Configuration for Special Cases
+3.7 Configuring LACP for 802.3ad mode in a more secure way
 
 4. Querying Bonding Configuration
 4.1	Bonding Configuration
@@ -178,6 +179,27 @@ active_slave
 	active slave, or the empty string if there is no active slave or
 	the current mode does not use an active slave.
 
+ad_actor_sys_prio
+
+	In an AD system, this specifies the system priority. The allowed range
+	is 1 - 65535. If the value is not specified, it takes 65535 as the
+	default value.
+
+	This parameter has effect only in 802.3ad mode and is available through
+	SysFs interface.
+
+ad_actor_system
+
+	In an AD system, this specifies the mac-address for the actor in
+	protocol packet exchanges (LACPDUs). The value cannot be NULL or
+	multicast. It is preferred to have the local-admin bit set for this
+	mac but driver does not enforce it. If the value is not given then
+	system defaults to using the masters' mac address as actors' system
+	address.
+
+	This parameter has effect only in 802.3ad mode and is available through
+	SysFs interface.
+
 ad_select
 
 	Specifies the 802.3ad aggregation selection logic to use.  The
@@ -220,6 +242,21 @@ ad_select
 
 	This option was added in bonding version 3.4.0.
 
+ad_user_port_key
+
+	In an AD system, the port-key has three parts as shown below -
+
+	   Bits   Use
+	   00     Duplex
+	   01-05  Speed
+	   06-15  User-defined
+
+	This defines the upper 10 bits of the port key. The values can be
+	from 0 - 1023. If not given, the system defaults to 0.
+
+	This parameter has effect only in 802.3ad mode and is available through
+	SysFs interface.
+
 all_slaves_active
 
 	Specifies that duplicate frames (received on inactive ports) should be
@@ -1622,6 +1659,53 @@ output port selection.
 This feature first appeared in bonding driver version 3.7.0 and support for
 output slave selection was limited to round-robin and active-backup modes.
 
+3.7 Configuring LACP for 802.3ad mode in a more secure way
+----------------------------------------------------------
+
+When using 802.3ad bonding mode, the Actor (host) and Partner (switch)
+exchange LACPDUs.  These LACPDUs cannot be sniffed, because they are
+destined to link local mac addresses (which switches/bridges are not
+supposed to forward).  However, most of the values are easily predictable
+or are simply the machine's MAC address (which is trivially known to all
+other hosts in the same L2).  This implies that other machines in the L2
+domain can spoof LACPDU packets from other hosts to the switch and potentially
+cause mayhem by joining (from the point of view of the switch) another
+machine's aggregate, thus receiving a portion of that hosts incoming
+traffic and / or spoofing traffic from that machine themselves (potentially
+even successfully terminating some portion of flows). Though this is not
+a likely scenario, one could avoid this possibility by simply configuring
+few bonding parameters:
+
+   (a) ad_actor_system : You can set a random mac-address that can be used for
+       these LACPDU exchanges. The value can not be either NULL or Multicast.
+       Also it's preferable to set the local-admin bit. Following shell code
+       generates a random mac-address as described above.
+
+       # sys_mac_addr=$(printf '%02x:%02x:%02x:%02x:%02x:%02x' \
+                                $(( (RANDOM & 0xFE) | 0x02 )) \
+                                $(( RANDOM & 0xFF )) \
+                                $(( RANDOM & 0xFF )) \
+                                $(( RANDOM & 0xFF )) \
+                                $(( RANDOM & 0xFF )) \
+                                $(( RANDOM & 0xFF )))
+       # echo $sys_mac_addr > /sys/class/net/bond0/bonding/ad_actor_system
+
+   (b) ad_actor_sys_prio : Randomize the system priority. The default value
+       is 65535, but system can take the value from 1 - 65535. Following shell
+       code generates random priority and sets it.
+
+       # sys_prio=$(( 1 + RANDOM + RANDOM ))
+       # echo $sys_prio > /sys/class/net/bond0/bonding/ad_actor_sys_prio
+
+   (c) ad_user_port_key : Use the user portion of the port-key. The default
+       keeps this empty. These are the upper 10 bits of the port-key and value
+       ranges from 0 - 1023. Following shell code generates these 10 bits and
+       sets it.
+
+       # usr_port_key=$(( RANDOM & 0x3FF ))
+       # echo $usr_port_key > /sys/class/net/bond0/bonding/ad_user_port_key
+
+
 4 Querying Bonding Configuration
 =================================
 
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 5abad1e921ca..b48d4a149411 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -268,6 +268,9 @@ solution for a couple of reasons:
     struct can_frame {
             canid_t can_id;  /* 32 bit CAN_ID + EFF/RTR/ERR flags */
             __u8    can_dlc; /* frame payload length in byte (0 .. 8) */
+            __u8    __pad;   /* padding */
+            __u8    __res0;  /* reserved / padding */
+            __u8    __res1;  /* reserved / padding */
             __u8    data[8] __attribute__((aligned(8)));
     };
 
diff --git a/Documentation/networking/dctcp.txt b/Documentation/networking/dctcp.txt
index 0d5dfbc89ec9..13a857753208 100644
--- a/Documentation/networking/dctcp.txt
+++ b/Documentation/networking/dctcp.txt
@@ -8,6 +8,7 @@ the data center network to provide multi-bit feedback to the end hosts.
 To enable it on end hosts:
 
   sysctl -w net.ipv4.tcp_congestion_control=dctcp
+  sysctl -w net.ipv4.tcp_ecn_fallback=0 (optional)
 
 All switches in the data center network running DCTCP must support ECN
 marking and be configured for marking when reaching defined switch buffer
diff --git a/Documentation/networking/fore200e.txt b/Documentation/networking/fore200e.txt
index d52af53efdc5..1f98f62b4370 100644
--- a/Documentation/networking/fore200e.txt
+++ b/Documentation/networking/fore200e.txt
@@ -37,7 +37,7 @@ version. Alternative binary firmware images can be found somewhere on the
 ForeThought CD-ROM supplied with your adapter by FORE Systems.
 
 You can also get the latest firmware images from FORE Systems at
-http://en.wikipedia.org/wiki/FORE_Systems. Register TACTics Online and go to
+https://en.wikipedia.org/wiki/FORE_Systems. Register TACTics Online and go to
 the 'software updates' pages. The firmware binaries are part of
 the various ForeThought software distributions.
 
diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt
index 22bbc7225f8e..1700756af057 100644
--- a/Documentation/networking/ieee802154.txt
+++ b/Documentation/networking/ieee802154.txt
@@ -30,8 +30,8 @@ int sd = socket(PF_IEEE802154, SOCK_DGRAM, 0);
 
 The address family, socket addresses etc. are defined in the
 include/net/af_ieee802154.h header or in the special header
-in our userspace package (see either linux-zigbee sourceforge download page
-or git tree at git://linux-zigbee.git.sourceforge.net/gitroot/linux-zigbee).
+in the userspace package (see either http://wpan.cakelab.org/ or the
+git tree at https://github.com/linux-wpan/wpan-tools).
 
 One can use SOCK_RAW for passing raw data towards device xmit function. YMMV.
 
@@ -49,15 +49,6 @@ Like with WiFi, there are several types of devices implementing IEEE 802.15.4.
 Those types of devices require different approach to be hooked into Linux kernel.
 
 
-MLME - MAC Level Management
-============================
-
-Most of IEEE 802.15.4 MLME interfaces are directly mapped on netlink commands.
-See the include/net/nl802154.h header. Our userspace tools package
-(see above) provides CLI configuration utility for radio interfaces and simple
-coordinator for IEEE 802.15.4 networks as an example users of MLME protocol.
-
-
 HardMAC
 =======
 
@@ -75,8 +66,6 @@ net_device with a pointer to struct ieee802154_mlme_ops instance. The fields
 assoc_req, assoc_resp, disassoc_req, start_req, and scan_req are optional.
 All other fields are required.
 
-We provide an example of simple HardMAC driver at drivers/ieee802154/fakehard.c
-
 
 SoftMAC
 =======
@@ -89,7 +78,8 @@ stack interface for network sniffers (e.g. WireShark).
 
 This layer is going to be extended soon.
 
-See header include/net/mac802154.h and several drivers in drivers/ieee802154/.
+See header include/net/mac802154.h and several drivers in
+drivers/net/ieee802154/.
 
 
 Device drivers API
@@ -114,18 +104,17 @@ Moreover IEEE 802.15.4 device operations structure should be filled.
 Fake drivers
 ============
 
-In addition there are two drivers available which simulate real devices with
-HardMAC (fakehard) and SoftMAC (fakelb - IEEE 802.15.4 loopback driver)
-interfaces. This option provides possibility to test and debug stack without
-usage of real hardware.
+In addition there is a driver available which simulates a real device with
+SoftMAC (fakelb - IEEE 802.15.4 loopback driver) interface. This option
+provides possibility to test and debug stack without usage of real hardware.
 
-See sources in drivers/ieee802154 folder for more details.
+See sources in drivers/net/ieee802154 folder for more details.
 
 
 6LoWPAN Linux implementation
 ============================
 
-The IEEE 802.15.4 standard specifies an MTU of 128 bytes, yielding about 80
+The IEEE 802.15.4 standard specifies an MTU of 127 bytes, yielding about 80
 octets of actual MAC payload once security is turned on, on a wireless link
 with a link throughput of 250 kbps or less.  The 6LoWPAN adaptation format
 [RFC4944] was specified to carry IPv6 datagrams over such constrained links,
@@ -140,7 +129,8 @@ In Semptember 2011 the standard update was published - [RFC6282].
 It deprecates HC1 and HC2 compression and defines IPHC encoding format which is
 used in this Linux implementation.
 
-All the code related to 6lowpan you may find in files: net/ieee802154/6lowpan.*
+All the code related to 6lowpan you may find in files: net/6lowpan/*
+and net/ieee802154/6lowpan/*
 
 To setup 6lowpan interface you need (busybox release > 1.17.0):
 1. Add IEEE802.15.4 interface and initialize PANid;
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 071fb18dc57c..5fae7704daab 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -267,6 +267,15 @@ tcp_ecn - INTEGER
 		  but do not request ECN on outgoing connections.
 	Default: 2
 
+tcp_ecn_fallback - BOOLEAN
+	If the kernel detects that ECN connection misbehaves, enable fall
+	back to non-ECN. Currently, this knob implements the fallback
+	from RFC3168, section 6.1.1.1., but we reserve that in future,
+	additional detection mechanisms could be implemented under this
+	knob. The value	is not used, if tcp_ecn or per route (or congestion
+	control) ECN settings are disabled.
+	Default: 1 (fallback enabled)
+
 tcp_fack - BOOLEAN
 	Enable FACK congestion avoidance and fast retransmission.
 	The value is not used, if tcp_sack is not enabled.
@@ -742,8 +751,10 @@ IP Variables:
 ip_local_port_range - 2 INTEGERS
 	Defines the local port range that is used by TCP and UDP to
 	choose the local port. The first number is the first, the
-	second the last local port number. The default values are
-	32768 and 61000 respectively.
+	second the last local port number.
+	If possible, it is better these numbers have different parity.
+	(one even and one odd values)
+	The default values are 32768 and 60999 respectively.
 
 ip_local_reserved_ports - list of comma separated ranges
 	Specify the ports which are reserved for known third-party
@@ -766,7 +777,7 @@ ip_local_reserved_ports - list of comma separated ranges
 	ip_local_port_range, e.g.:
 
 	$ cat /proc/sys/net/ipv4/ip_local_port_range
-	32000	61000
+	32000	60999
 	$ cat /proc/sys/net/ipv4/ip_local_reserved_ports
 	8080,9148
 
@@ -1213,6 +1224,14 @@ auto_flowlabels - BOOLEAN
 	FALSE: disabled
 	Default: false
 
+flowlabel_state_ranges - BOOLEAN
+	Split the flow label number space into two ranges. 0-0x7FFFF is
+	reserved for the IPv6 flow manager facility, 0x80000-0xFFFFF
+	is reserved for stateless flow labels as described in RFC6437.
+	TRUE: enabled
+	FALSE: disabled
+	Default: true
+
 anycast_src_echo_reply - BOOLEAN
 	Controls the use of anycast addresses as source addresses for ICMPv6
 	echo reply
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index 0344f1d45b37..f4be85e96005 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -1,6 +1,6 @@
 
 
-                  HOWTO for the linux packet generator 
+                  HOWTO for the linux packet generator
                   ------------------------------------
 
 Enable CONFIG_NET_PKTGEN to compile and build pktgen either in-kernel
@@ -50,17 +50,33 @@ For ixgbe use e.g. "30" resulting in approx 33K interrupts/sec (1/30*10^6):
  # ethtool -C ethX rx-usecs 30
 
 
-Viewing threads
-===============
-/proc/net/pktgen/kpktgend_0 
-Name: kpktgend_0  max_before_softirq: 10000
-Running: 
-Stopped: eth1 
-Result: OK: max_before_softirq=10000
+Kernel threads
+==============
+Pktgen creates a thread for each CPU with affinity to that CPU.
+Which is controlled through procfile /proc/net/pktgen/kpktgend_X.
+
+Example: /proc/net/pktgen/kpktgend_0
+
+ Running:
+ Stopped: eth4@0
+ Result: OK: add_device=eth4@0
+
+Most important are the devices assigned to the thread.
+
+The two basic thread commands are:
+ * add_device DEVICE@NAME -- adds a single device
+ * rem_device_all         -- remove all associated devices
+
+When adding a device to a thread, a corrosponding procfile is created
+which is used for configuring this device. Thus, device names need to
+be unique.
 
-Most important are the devices assigned to the thread.  Note that a
-device can only belong to one thread.
+To support adding the same device to multiple threads, which is useful
+with multi queue NICs, a the device naming scheme is extended with "@":
+ device@something
 
+The part after "@" can be anything, but it is custom to use the thread
+number.
 
 Viewing devices
 ===============
@@ -69,29 +85,32 @@ The Params section holds configured information.  The Current section
 holds running statistics.  The Result is printed after a run or after
 interruption.  Example:
 
-/proc/net/pktgen/eth1       
+/proc/net/pktgen/eth4@0
 
-Params: count 10000000  min_pkt_size: 60  max_pkt_size: 60
-     frags: 0  delay: 0  clone_skb: 1000000  ifname: eth1
+ Params: count 100000  min_pkt_size: 60  max_pkt_size: 60
+     frags: 0  delay: 0  clone_skb: 64  ifname: eth4@0
      flows: 0 flowlen: 0
-     dst_min: 10.10.11.2  dst_max: 
-     src_min:   src_max: 
-     src_mac: 00:00:00:00:00:00  dst_mac: 00:04:23:AC:FD:82
-     udp_src_min: 9  udp_src_max: 9  udp_dst_min: 9  udp_dst_max: 9
-     src_mac_count: 0  dst_mac_count: 0 
-     Flags: 
-Current:
-     pkts-sofar: 10000000  errors: 39664
-     started: 1103053986245187us  stopped: 1103053999346329us idle: 880401us
-     seq_num: 10000011  cur_dst_mac_offset: 0  cur_src_mac_offset: 0
-     cur_saddr: 0x10a0a0a  cur_daddr: 0x20b0a0a
-     cur_udp_dst: 9  cur_udp_src: 9
+     queue_map_min: 0  queue_map_max: 0
+     dst_min: 192.168.81.2  dst_max:
+     src_min:   src_max:
+     src_mac: 90:e2:ba:0a:56:b4 dst_mac: 00:1b:21:3c:9d:f8
+     udp_src_min: 9  udp_src_max: 109  udp_dst_min: 9  udp_dst_max: 9
+     src_mac_count: 0  dst_mac_count: 0
+     Flags: UDPSRC_RND  NO_TIMESTAMP  QUEUE_MAP_CPU
+ Current:
+     pkts-sofar: 100000  errors: 0
+     started: 623913381008us  stopped: 623913396439us idle: 25us
+     seq_num: 100001  cur_dst_mac_offset: 0  cur_src_mac_offset: 0
+     cur_saddr: 192.168.8.3  cur_daddr: 192.168.81.2
+     cur_udp_dst: 9  cur_udp_src: 42
+     cur_queue_map: 0
      flows: 0
-Result: OK: 13101142(c12220741+d880401) usec, 10000000 (60byte,0frags)
-  763292pps 390Mb/sec (390805504bps) errors: 39664
+ Result: OK: 15430(c15405+d25) usec, 100000 (60byte,0frags)
+  6480562pps 3110Mb/sec (3110669760bps) errors: 0
 
-Configuring threads and devices
-================================
+
+Configuring devices
+===================
 This is done via the /proc interface, and most easily done via pgset
 as defined in the sample scripts.
 
@@ -126,7 +145,7 @@ Examples:
                          To select queue 1 of a given device,
                          use queue_map_min=1 and queue_map_max=1
 
- pgset "src_mac_count 1" Sets the number of MACs we'll range through.  
+ pgset "src_mac_count 1" Sets the number of MACs we'll range through.
                          The 'minimum' MAC is what you set with srcmac.
 
  pgset "dst_mac_count 1" Sets the number of MACs we'll range through.
@@ -145,6 +164,7 @@ Examples:
                               UDPCSUM,
                               IPSEC # IPsec encapsulation (needs CONFIG_XFRM)
                               NODE_ALLOC # node specific memory allocation
+                              NO_TIMESTAMP # disable timestamping
 
  pgset spi SPI_VALUE     Set specific SA used to transform packet.
 
@@ -192,24 +212,43 @@ Examples:
  pgset "rate 300M"        set rate to 300 Mb/s
  pgset "ratep 1000000"    set rate to 1Mpps
 
+ pgset "xmit_mode netif_receive"  RX inject into stack netif_receive_skb()
+				  Works with "burst" but not with "clone_skb".
+				  Default xmit_mode is "start_xmit".
+
 Sample scripts
 ==============
 
-A collection of small tutorial scripts for pktgen is in the
-samples/pktgen directory:
+A collection of tutorial scripts and helpers for pktgen is in the
+samples/pktgen directory. The helper parameters.sh file support easy
+and consistant parameter parsing across the sample scripts.
+
+Usage example and help:
+ ./pktgen_sample01_simple.sh -i eth4 -m 00:1B:21:3C:9D:F8 -d 192.168.8.2
+
+Usage: ./pktgen_sample01_simple.sh [-vx] -i ethX
+  -i : ($DEV)       output interface/device (required)
+  -s : ($PKT_SIZE)  packet size
+  -d : ($DEST_IP)   destination IP
+  -m : ($DST_MAC)   destination MAC-addr
+  -t : ($THREADS)   threads to start
+  -c : ($SKB_CLONE) SKB clones send before alloc new SKB
+  -b : ($BURST)     HW level bursting of SKBs
+  -v : ($VERBOSE)   verbose
+  -x : ($DEBUG)     debug
+
+The global variables being set are also listed.  E.g. the required
+interface/device parameter "-i" sets variable $DEV.  Copy the
+pktgen_sampleXX scripts and modify them to fit your own needs.
+
+The old scripts:
 
-pktgen.conf-1-1                  # 1 CPU 1 dev 
 pktgen.conf-1-2                  # 1 CPU 2 dev
-pktgen.conf-2-1                  # 2 CPU's 1 dev 
-pktgen.conf-2-2                  # 2 CPU's 2 dev
 pktgen.conf-1-1-rdos             # 1 CPU 1 dev w. route DoS 
 pktgen.conf-1-1-ip6              # 1 CPU 1 dev ipv6
 pktgen.conf-1-1-ip6-rdos         # 1 CPU 1 dev ipv6  w. route DoS
 pktgen.conf-1-1-flows            # 1 CPU 1 dev multiple flows.
 
-Run in shell: ./pktgen.conf-X-Y
-This does all the setup including sending.
-
 
 Interrupt affinity
 ===================
@@ -217,6 +256,9 @@ Note that when adding devices to a specific CPU it is a good idea to
 also assign /proc/irq/XX/smp_affinity so that the TX interrupts are bound
 to the same CPU.  This reduces cache bouncing when freeing skbs.
 
+Plus using the device flag QUEUE_MAP_CPU, which maps the SKBs TX queue
+to the running threads CPU (directly from smp_processor_id()).
+
 Enable IPsec
 ============
 Default IPsec transformation with ESP encapsulation plus transport mode
@@ -237,18 +279,19 @@ Current commands and configuration options
 
 start
 stop
+reset
 
 ** Thread commands:
 
 add_device
 rem_device_all
-max_before_softirq
 
 
 ** Device commands:
 
 count
 clone_skb
+burst
 debug
 
 frags
@@ -257,10 +300,17 @@ delay
 src_mac_count
 dst_mac_count
 
-pkt_size 
+pkt_size
 min_pkt_size
 max_pkt_size
 
+queue_map_min
+queue_map_max
+skb_priority
+
+tos           (ipv4)
+traffic_class (ipv6)
+
 mpls
 
 udp_src_min
@@ -269,6 +319,8 @@ udp_src_max
 udp_dst_min
 udp_dst_max
 
+node
+
 flag
   IPSRC_RND
   IPDST_RND
@@ -287,6 +339,9 @@ flag
   UDPCSUM
   IPSEC
   NODE_ALLOC
+  NO_TIMESTAMP
+
+spi (ipsec)
 
 dst_min
 dst_max
@@ -299,8 +354,10 @@ src_mac
 
 clear_counters
 
-dst6
 src6
+dst6
+dst6_max
+dst6_min
 
 flows
 flowlen
@@ -308,6 +365,17 @@ flowlen
 rate
 ratep
 
+xmit_mode <start_xmit|netif_receive>
+
+vlan_cfi
+vlan_id
+vlan_p
+
+svlan_cfi
+svlan_id
+svlan_p
+
+
 References:
 ftp://robur.slu.se/pub/Linux/net-development/pktgen-testing/
 ftp://robur.slu.se/pub/Linux/net-development/pktgen-testing/examples/
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
index f981a9295a39..c5d7ade10ff2 100644
--- a/Documentation/networking/switchdev.txt
+++ b/Documentation/networking/switchdev.txt
@@ -1,59 +1,360 @@
-Switch (and switch-ish) device drivers HOWTO
-===========================
-
-Please note that the word "switch" is here used in very generic meaning.
-This include devices supporting L2/L3 but also various flow offloading chips,
-including switches embedded into SR-IOV NICs.
-
-Lets describe a topology a bit. Imagine the following example:
-
-       +----------------------------+    +---------------+
-       |     SOME switch chip       |    |      CPU      |
-       +----------------------------+    +---------------+
-       port1 port2 port3 port4 MNGMNT    |     PCI-E     |
-         |     |     |     |     |       +---------------+
-        PHY   PHY    |     |     |         |  NIC0 NIC1
-                     |     |     |         |   |    |
-                     |     |     +- PCI-E -+   |    |
-                     |     +------- MII -------+    |
-                     +------------- MII ------------+
-
-In this example, there are two independent lines between the switch silicon
-and CPU. NIC0 and NIC1 drivers are not aware of a switch presence. They are
-separate from the switch driver. SOME switch chip is by managed by a driver
-via PCI-E device MNGMNT. Note that MNGMNT device, NIC0 and NIC1 may be
-connected to some other type of bus.
-
-Now, for the previous example show the representation in kernel:
-
-       +----------------------------+    +---------------+
-       |     SOME switch chip       |    |      CPU      |
-       +----------------------------+    +---------------+
-       sw0p0 sw0p1 sw0p2 sw0p3 MNGMNT    |     PCI-E     |
-         |     |     |     |     |       +---------------+
-        PHY   PHY    |     |     |         |  eth0 eth1
-                     |     |     |         |   |    |
-                     |     |     +- PCI-E -+   |    |
-                     |     +------- MII -------+    |
-                     +------------- MII ------------+
-
-Lets call the example switch driver for SOME switch chip "SOMEswitch". This
-driver takes care of PCI-E device MNGMNT. There is a netdevice instance sw0pX
-created for each port of a switch. These netdevices are instances
-of "SOMEswitch" driver. sw0pX netdevices serve as a "representation"
-of the switch chip. eth0 and eth1 are instances of some other existing driver.
-
-The only difference of the switch-port netdevice from the ordinary netdevice
-is that is implements couple more NDOs:
-
-  ndo_switch_parent_id_get - This returns the same ID for two port netdevices
-			     of the same physical switch chip. This is
-			     mandatory to be implemented by all switch drivers
-			     and serves the caller for recognition of a port
-			     netdevice.
-  ndo_switch_parent_* - Functions that serve for a manipulation of the switch
-			chip itself (it can be though of as a "parent" of the
-			port, therefore the name). They are not port-specific.
-			Caller might use arbitrary port netdevice of the same
-			switch and it will make no difference.
-  ndo_switch_port_* - Functions that serve for a port-specific manipulation.
+Ethernet switch device driver model (switchdev)
+===============================================
+Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com>
+
+
+The Ethernet switch device driver model (switchdev) is an in-kernel driver
+model for switch devices which offload the forwarding (data) plane from the
+kernel.
+
+Figure 1 is a block diagram showing the components of the switchdev model for
+an example setup using a data-center-class switch ASIC chip.  Other setups
+with SR-IOV or soft switches, such as OVS, are possible.
+
+
+                             User-space tools                                 
+                                                                              
+       user space                   |                                         
+      +-------------------------------------------------------------------+   
+       kernel                       | Netlink                                 
+                                    |                                         
+                     +--------------+-------------------------------+         
+                     |         Network stack                        |         
+                     |           (Linux)                            |         
+                     |                                              |         
+                     +----------------------------------------------+         
+                                                                              
+                           sw1p2     sw1p4     sw1p6
+                      sw1p1  +  sw1p3  +  sw1p5  +          eth1             
+                        +    |    +    |    +    |            +               
+                        |    |    |    |    |    |            |               
+                     +--+----+----+----+-+--+----+---+  +-----+-----+         
+                     |         Switch driver         |  |    mgmt   |         
+                     |        (this document)        |  |   driver  |         
+                     |                               |  |           |         
+                     +--------------+----------------+  +-----------+         
+                                    |                                         
+       kernel                       | HW bus (eg PCI)                         
+      +-------------------------------------------------------------------+   
+       hardware                     |                                         
+                     +--------------+---+------------+                        
+                     |         Switch device (sw1)   |                        
+                     |  +----+                       +--------+               
+                     |  |    v offloaded data path   | mgmt port              
+                     |  |    |                       |                        
+                     +--|----|----+----+----+----+---+                        
+                        |    |    |    |    |    |                            
+                        +    +    +    +    +    +                            
+                       p1   p2   p3   p4   p5   p6
+                                       
+                             front-panel ports                                
+                                                                              
+
+                                    Fig 1.
+
+
+Include Files
+-------------
+
+#include <linux/netdevice.h>
+#include <net/switchdev.h>
+
+
+Configuration
+-------------
+
+Use "depends NET_SWITCHDEV" in driver's Kconfig to ensure switchdev model
+support is built for driver.
+
+
+Switch Ports
+------------
+
+On switchdev driver initialization, the driver will allocate and register a
+struct net_device (using register_netdev()) for each enumerated physical switch
+port, called the port netdev.  A port netdev is the software representation of
+the physical port and provides a conduit for control traffic to/from the
+controller (the kernel) and the network, as well as an anchor point for higher
+level constructs such as bridges, bonds, VLANs, tunnels, and L3 routers.  Using
+standard netdev tools (iproute2, ethtool, etc), the port netdev can also
+provide to the user access to the physical properties of the switch port such
+as PHY link state and I/O statistics.
+
+There is (currently) no higher-level kernel object for the switch beyond the
+port netdevs.  All of the switchdev driver ops are netdev ops or switchdev ops.
+
+A switch management port is outside the scope of the switchdev driver model.
+Typically, the management port is not participating in offloaded data plane and
+is loaded with a different driver, such as a NIC driver, on the management port
+device.
+
+Port Netdev Naming
+^^^^^^^^^^^^^^^^^^
+
+Udev rules should be used for port netdev naming, using some unique attribute
+of the port as a key, for example the port MAC address or the port PHYS name.
+Hard-coding of kernel netdev names within the driver is discouraged; let the
+kernel pick the default netdev name, and let udev set the final name based on a
+port attribute.
+
+Using port PHYS name (ndo_get_phys_port_name) for the key is particularly
+useful for dynamically-named ports where the device names its ports based on
+external configuration.  For example, if a physical 40G port is split logically
+into 4 10G ports, resulting in 4 port netdevs, the device can give a unique
+name for each port using port PHYS name.  The udev rule would be:
+
+SUBSYSTEM=="net", ACTION=="add", DRIVER="<driver>", ATTR{phys_port_name}!="", \
+	NAME="$attr{phys_port_name}"
+
+Suggested naming convention is "swXpYsZ", where X is the switch name or ID, Y
+is the port name or ID, and Z is the sub-port name or ID.  For example, sw1p1s0
+would be sub-port 0 on port 1 on switch 1.
+
+Switch ID
+^^^^^^^^^
+
+The switchdev driver must implement the switchdev op switchdev_port_attr_get
+for SWITCHDEV_ATTR_PORT_PARENT_ID for each port netdev, returning the same
+physical ID for each port of a switch.  The ID must be unique between switches
+on the same system.  The ID does not need to be unique between switches on
+different systems.
+
+The switch ID is used to locate ports on a switch and to know if aggregated
+ports belong to the same switch.
+
+Port Features
+^^^^^^^^^^^^^
+
+NETIF_F_NETNS_LOCAL
+
+If the switchdev driver (and device) only supports offloading of the default
+network namespace (netns), the driver should set this feature flag to prevent
+the port netdev from being moved out of the default netns.  A netns-aware
+driver/device would not set this flag and be responsible for partitioning
+hardware to preserve netns containment.  This means hardware cannot forward
+traffic from a port in one namespace to another port in another namespace.
+
+Port Topology
+^^^^^^^^^^^^^
+
+The port netdevs representing the physical switch ports can be organized into
+higher-level switching constructs.  The default construct is a standalone
+router port, used to offload L3 forwarding.  Two or more ports can be bonded
+together to form a LAG.  Two or more ports (or LAGs) can be bridged to bridge
+L2 networks.  VLANs can be applied to sub-divide L2 networks.  L2-over-L3
+tunnels can be built on ports.  These constructs are built using standard Linux
+tools such as the bridge driver, the bonding/team drivers, and netlink-based
+tools such as iproute2.
+
+The switchdev driver can know a particular port's position in the topology by
+monitoring NETDEV_CHANGEUPPER notifications.  For example, a port moved into a
+bond will see it's upper master change.  If that bond is moved into a bridge,
+the bond's upper master will change.  And so on.  The driver will track such
+movements to know what position a port is in in the overall topology by
+registering for netdevice events and acting on NETDEV_CHANGEUPPER.
+
+L2 Forwarding Offload
+---------------------
+
+The idea is to offload the L2 data forwarding (switching) path from the kernel
+to the switchdev device by mirroring bridge FDB entries down to the device.  An
+FDB entry is the {port, MAC, VLAN} tuple forwarding destination.
+
+To offloading L2 bridging, the switchdev driver/device should support:
+
+	- Static FDB entries installed on a bridge port
+	- Notification of learned/forgotten src mac/vlans from device
+	- STP state changes on the port
+	- VLAN flooding of multicast/broadcast and unknown unicast packets
+
+Static FDB Entries
+^^^^^^^^^^^^^^^^^^
+
+The switchdev driver should implement ndo_fdb_add, ndo_fdb_del and ndo_fdb_dump
+to support static FDB entries installed to the device.  Static bridge FDB
+entries are installed, for example, using iproute2 bridge cmd:
+
+	bridge fdb add ADDR dev DEV [vlan VID] [self]
+
+The driver should use the helper switchdev_port_fdb_xxx ops for ndo_fdb_xxx
+ops, and handle add/delete/dump of SWITCHDEV_OBJ_PORT_FDB object using
+switchdev_port_obj_xxx ops.
+
+XXX: what should be done if offloading this rule to hardware fails (for
+example, due to full capacity in hardware tables) ?
+
+Note: by default, the bridge does not filter on VLAN and only bridges untagged
+traffic.  To enable VLAN support, turn on VLAN filtering:
+
+	echo 1 >/sys/class/net/<bridge>/bridge/vlan_filtering
+
+Notification of Learned/Forgotten Source MAC/VLANs
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The switch device will learn/forget source MAC address/VLAN on ingress packets
+and notify the switch driver of the mac/vlan/port tuples.  The switch driver,
+in turn, will notify the bridge driver using the switchdev notifier call:
+
+	err = call_switchdev_notifiers(val, dev, info);
+
+Where val is SWITCHDEV_FDB_ADD when learning and SWITCHDEV_FDB_DEL when
+forgetting, and info points to a struct switchdev_notifier_fdb_info.  On
+SWITCHDEV_FDB_ADD, the bridge driver will install the FDB entry into the
+bridge's FDB and mark the entry as NTF_EXT_LEARNED.  The iproute2 bridge
+command will label these entries "offload":
+
+	$ bridge fdb
+	52:54:00:12:35:01 dev sw1p1 master br0 permanent
+	00:02:00:00:02:00 dev sw1p1 master br0 offload
+	00:02:00:00:02:00 dev sw1p1 self
+	52:54:00:12:35:02 dev sw1p2 master br0 permanent
+	00:02:00:00:03:00 dev sw1p2 master br0 offload
+	00:02:00:00:03:00 dev sw1p2 self
+	33:33:00:00:00:01 dev eth0 self permanent
+	01:00:5e:00:00:01 dev eth0 self permanent
+	33:33:ff:00:00:00 dev eth0 self permanent
+	01:80:c2:00:00:0e dev eth0 self permanent
+	33:33:00:00:00:01 dev br0 self permanent
+	01:00:5e:00:00:01 dev br0 self permanent
+	33:33:ff:12:35:01 dev br0 self permanent
+
+Learning on the port should be disabled on the bridge using the bridge command:
+
+	bridge link set dev DEV learning off
+
+Learning on the device port should be enabled, as well as learning_sync:
+
+	bridge link set dev DEV learning on self
+	bridge link set dev DEV learning_sync on self
+
+Learning_sync attribute enables syncing of the learned/forgotton FDB entry to
+the bridge's FDB.  It's possible, but not optimal, to enable learning on the
+device port and on the bridge port, and disable learning_sync.
+
+To support learning and learning_sync port attributes, the driver implements
+switchdev op switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS.
+The driver should initialize the attributes to the hardware defaults.
+
+FDB Ageing
+^^^^^^^^^^
+
+There are two FDB ageing models supported: 1) ageing by the device, and 2)
+ageing by the kernel.  Ageing by the device is preferred if many FDB entries
+are supported.  The driver calls call_switchdev_notifiers(SWITCHDEV_FDB_DEL,
+...) to age out the FDB entry.  In this model, ageing by the kernel should be
+turned off.  XXX: how to turn off ageing in kernel on a per-port basis or
+otherwise prevent the kernel from ageing out the FDB entry?
+
+In the kernel ageing model, the standard bridge ageing mechanism is used to age
+out stale FDB entries.  To keep an FDB entry "alive", the driver should refresh
+the FDB entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...).  The
+notification will reset the FDB entry's last-used time to now.  The driver
+should rate limit refresh notifications, for example, no more than once a
+second.  If the FDB entry expires, fdb_delete is called to remove entry from
+the device.
+
+STP State Change on Port
+^^^^^^^^^^^^^^^^^^^^^^^^
+
+Internally or with a third-party STP protocol implementation (e.g. mstpd), the
+bridge driver maintains the STP state for ports, and will notify the switch
+driver of STP state change on a port using the switchdev op
+switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_STP_UPDATE.
+
+State is one of BR_STATE_*.  The switch driver can use STP state updates to
+update ingress packet filter list for the port.  For example, if port is
+DISABLED, no packets should pass, but if port moves to BLOCKED, then STP BPDUs
+and other IEEE 01:80:c2:xx:xx:xx link-local multicast packets can pass.
+
+Note that STP BDPUs are untagged and STP state applies to all VLANs on the port
+so packet filters should be applied consistently across untagged and tagged
+VLANs on the port.
+
+Flooding L2 domain
+^^^^^^^^^^^^^^^^^^
+
+For a given L2 VLAN domain, the switch device should flood multicast/broadcast
+and unknown unicast packets to all ports in domain, if allowed by port's
+current STP state.  The switch driver, knowing which ports are within which
+vlan L2 domain, can program the switch device for flooding.  The packet should
+also be sent to the port netdev for processing by the bridge driver.  The
+bridge should not reflood the packet to the same ports the device flooded.
+XXX: the mechanism to avoid duplicate flood packets is being discuseed.
+
+It is possible for the switch device to not handle flooding and push the
+packets up to the bridge driver for flooding.  This is not ideal as the number
+of ports scale in the L2 domain as the device is much more efficient at
+flooding packets that software.
+
+IGMP Snooping
+^^^^^^^^^^^^^
+
+XXX: complete this section
+
+
+L3 Routing Offload
+------------------
+
+Offloading L3 routing requires that device be programmed with FIB entries from
+the kernel, with the device doing the FIB lookup and forwarding.  The device
+does a longest prefix match (LPM) on FIB entries matching route prefix and
+forwards the packet to the matching FIB entry's nexthop(s) egress ports.
+
+To program the device, the driver implements support for
+SWITCHDEV_OBJ_IPV[4|6]_FIB object using switchdev_port_obj_xxx ops.
+switchdev_port_obj_add is used for both adding a new FIB entry to the device,
+or modifying an existing entry on the device.
+
+XXX: Currently, only SWITCHDEV_OBJ_IPV4_FIB objects are supported.
+
+SWITCHDEV_OBJ_IPV4_FIB object passes:
+
+	struct switchdev_obj_ipv4_fib {         /* IPV4_FIB */
+		u32 dst;
+		int dst_len;
+		struct fib_info *fi;
+		u8 tos;
+		u8 type;
+		u32 nlflags;
+		u32 tb_id;
+	} ipv4_fib;
+
+to add/modify/delete IPv4 dst/dest_len prefix on table tb_id.  The *fi
+structure holds details on the route and route's nexthops.  *dev is one of the
+port netdevs mentioned in the routes next hop list.  If the output port netdevs
+referenced in the route's nexthop list don't all have the same switch ID, the
+driver is not called to add/modify/delete the FIB entry.
+
+Routes offloaded to the device are labeled with "offload" in the ip route
+listing:
+
+	$ ip route show
+	default via 192.168.0.2 dev eth0
+	11.0.0.0/30 dev sw1p1  proto kernel  scope link  src 11.0.0.2 offload
+	11.0.0.4/30 via 11.0.0.1 dev sw1p1  proto zebra  metric 20 offload
+	11.0.0.8/30 dev sw1p2  proto kernel  scope link  src 11.0.0.10 offload
+	11.0.0.12/30 via 11.0.0.9 dev sw1p2  proto zebra  metric 20 offload
+	12.0.0.2  proto zebra  metric 30 offload
+		nexthop via 11.0.0.1  dev sw1p1 weight 1
+		nexthop via 11.0.0.9  dev sw1p2 weight 1
+	12.0.0.3 via 11.0.0.1 dev sw1p1  proto zebra  metric 20 offload
+	12.0.0.4 via 11.0.0.9 dev sw1p2  proto zebra  metric 20 offload
+	192.168.0.0/24 dev eth0  proto kernel  scope link  src 192.168.0.15
+
+XXX: add/mod/del IPv6 FIB API
+
+Nexthop Resolution
+^^^^^^^^^^^^^^^^^^
+
+The FIB entry's nexthop list contains the nexthop tuple (gateway, dev), but for
+the switch device to forward the packet with the correct dst mac address, the
+nexthop gateways must be resolved to the neighbor's mac address.  Neighbor mac
+address discovery comes via the ARP (or ND) process and is available via the
+arp_tbl neighbor table.  To resolve the routes nexthop gateways, the driver
+should trigger the kernel's neighbor resolution process.  See the rocker
+driver's rocker_port_ipv4_resolve() for an example.
+
+The driver can monitor for updates to arp_tbl using the netevent notifier
+NETEVENT_NEIGH_UPDATE.  The device can be programmed with resolved nexthops
+for the routes as arp_tbl updates.
diff --git a/Documentation/networking/tc-actions-env-rules.txt b/Documentation/networking/tc-actions-env-rules.txt
index 70d6cf608251..f37814693ad3 100644
--- a/Documentation/networking/tc-actions-env-rules.txt
+++ b/Documentation/networking/tc-actions-env-rules.txt
@@ -8,14 +8,8 @@ For example if your action queues a packet to be processed later,
 or intentionally branches by redirecting a packet, then you need to
 clone the packet.
 
-There are certain fields in the skb tc_verd that need to be reset so we
-avoid loops, etc.  A few are generic enough that skb_act_clone()
-resets them for you, so invoke skb_act_clone() rather than skb_clone().
-
 2) If you munge any packet thou shalt call pskb_expand_head in the case
 someone else is referencing the skb. After that you "own" the skb.
-You must also tell us if it is ok to munge the packet (TC_OK2MUNGE),
-this way any action downstream can stomp on the packet.
 
 3) Dropping packets you don't own is a no-no. You simply return
 TC_ACT_SHOT to the caller and they will drop it.
diff --git a/Documentation/networking/timestamping/txtimestamp.c b/Documentation/networking/timestamping/txtimestamp.c
index 8217510d3842..5df07047ca86 100644
--- a/Documentation/networking/timestamping/txtimestamp.c
+++ b/Documentation/networking/timestamping/txtimestamp.c
@@ -36,6 +36,7 @@
 #include <asm/types.h>
 #include <error.h>
 #include <errno.h>
+#include <inttypes.h>
 #include <linux/errqueue.h>
 #include <linux/if_ether.h>
 #include <linux/net_tstamp.h>
@@ -49,7 +50,6 @@
 #include <poll.h>
 #include <stdarg.h>
 #include <stdbool.h>
-#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -96,7 +96,7 @@ static void __print_timestamp(const char *name, struct timespec *cur,
 		prev_ms = (long) ts_prev.tv_sec * 1000 * 1000;
 		prev_ms += ts_prev.tv_nsec / 1000;
 
-		fprintf(stderr, "  (%+ld us)", cur_ms - prev_ms);
+		fprintf(stderr, "  (%+" PRId64 " us)", cur_ms - prev_ms);
 	}
 
 	ts_prev = *cur;
diff --git a/Documentation/networking/udplite.txt b/Documentation/networking/udplite.txt
index d727a3829100..53a726855e49 100644
--- a/Documentation/networking/udplite.txt
+++ b/Documentation/networking/udplite.txt
@@ -20,7 +20,7 @@
 	files/UDP-Lite-HOWTO.txt
 
    o The Wireshark UDP-Lite WiKi (with capture files):
-       http://wiki.wireshark.org/Lightweight_User_Datagram_Protocol
+       https://wiki.wireshark.org/Lightweight_User_Datagram_Protocol
 
    o The Protocol Spec, RFC 3828, http://www.ietf.org/rfc/rfc3828.txt
 
diff --git a/Documentation/nfc/nfc-hci.txt b/Documentation/nfc/nfc-hci.txt
index 0686c9e211c2..0dc078cab972 100644
--- a/Documentation/nfc/nfc-hci.txt
+++ b/Documentation/nfc/nfc-hci.txt
@@ -122,7 +122,7 @@ This must be done from a context that can sleep.
 PHY Management
 --------------
 
-The physical link (i2c, ...) management is defined by the following struture:
+The physical link (i2c, ...) management is defined by the following structure:
 
 struct nfc_phy_ops {
 	int (*write)(void *dev_id, struct sk_buff *skb);
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index a9b47163bb5d..4976389e432d 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -714,6 +714,7 @@ static struct pinmux_ops foo_pmxops = {
 	.get_function_name = foo_get_fname,
 	.get_function_groups = foo_get_groups,
 	.set_mux = foo_set_mux,
+	.strict = true,
 };
 
 /* Pinmux operations are handled by some pin controller */
@@ -830,6 +831,11 @@ separate memory range only intended for GPIO driving, and the register
 range dealing with pin config and pin multiplexing get placed into a
 different memory range and a separate section of the data sheet.
 
+A flag "strict" in struct pinctrl_desc is available to check and deny
+simultaneous access to the same pin from GPIO and pin multiplexing
+consumers on hardware of this type. The pinctrl driver should set this flag
+accordingly.
+
 (B)
 
                        pin config
@@ -850,6 +856,11 @@ possible that the GPIO, pin config and pin multiplex registers are placed into
 the same memory range and the same section of the data sheet, although that
 need not be the case.
 
+In some pin controllers, although the physical pins are designed in the same
+way as (B), the GPIO function still can't be enabled at the same time as the
+peripheral functions. So again the "strict" flag should be set, denying
+simultaneous activation by GPIO and other muxed in devices.
+
 From a kernel point of view, however, these are different aspects of the
 hardware and shall be put into different subsystems:
 
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 44fe1d28a163..e76dc0ad4d2b 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -556,6 +556,12 @@ helper functions described in Section 4.  In that case, pm_runtime_resume()
 should be used.  Of course, for this purpose the device's runtime PM has to be
 enabled earlier by calling pm_runtime_enable().
 
+Note, if the device may execute pm_runtime calls during the probe (such as
+if it is registers with a subsystem that may call back in) then the
+pm_runtime_get_sync() call paired with a pm_runtime_put() call will be
+appropriate to ensure that the device is not put back to sleep during the
+probe. This can happen with systems such as the network device layer.
+
 It may be desirable to suspend the device once ->probe() has finished.
 Therefore the driver core uses the asyncronous pm_request_idle() to submit a
 request to execute the subsystem-level idle callback for the device at that
diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX
index 6fd0e8bb8140..9dc845cf7d88 100644
--- a/Documentation/powerpc/00-INDEX
+++ b/Documentation/powerpc/00-INDEX
@@ -30,3 +30,5 @@ ptrace.txt
 	- Information on the ptrace interfaces for hardware debug registers.
 transactional_memory.txt
 	- Overview of the Power8 transactional memory support.
+dscr.txt
+	- Overview DSCR (Data Stream Control Register) support.
diff --git a/Documentation/powerpc/cxl.txt b/Documentation/powerpc/cxl.txt
index 2c71ecc519d9..2a230d01cd8c 100644
--- a/Documentation/powerpc/cxl.txt
+++ b/Documentation/powerpc/cxl.txt
@@ -133,6 +133,9 @@ User API
     The following file operations are supported on both slave and
     master devices.
 
+    A userspace library libcxl is avaliable here:
+	https://github.com/ibm-capi/libcxl
+    This provides a C interface to this kernel API.
 
 open
 ----
@@ -366,6 +369,7 @@ Sysfs Class
     enumeration and tuning of the accelerators. Its layout is
     described in Documentation/ABI/testing/sysfs-class-cxl
 
+
 Udev rules
 ==========
 
diff --git a/Documentation/powerpc/dscr.txt b/Documentation/powerpc/dscr.txt
new file mode 100644
index 000000000000..1ff4400c57b3
--- /dev/null
+++ b/Documentation/powerpc/dscr.txt
@@ -0,0 +1,83 @@
+			DSCR (Data Stream Control Register)
+		================================================
+
+DSCR register in powerpc allows user to have some control of prefetch of data
+stream in the processor. Please refer to the ISA documents or related manual
+for more detailed information regarding how to use this DSCR to attain this
+control of the pefetches . This document here provides an overview of kernel
+support for DSCR, related kernel objects, it's functionalities and exported
+user interface.
+
+(A) Data Structures:
+
+	(1) thread_struct:
+		dscr		/* Thread DSCR value */
+		dscr_inherit	/* Thread has changed default DSCR */
+
+	(2) PACA:
+		dscr_default	/* per-CPU DSCR default value */
+
+	(3) sysfs.c:
+		dscr_default	/* System DSCR default value */
+
+(B) Scheduler Changes:
+
+	Scheduler will write the per-CPU DSCR default which is stored in the
+	CPU's PACA value into the register if the thread has dscr_inherit value
+	cleared which means that it has not changed the default DSCR till now.
+	If the dscr_inherit value is set which means that it has changed the
+	default DSCR value, scheduler will write the changed value which will
+	now be contained in thread struct's dscr into the register instead of
+	the per-CPU default PACA based DSCR value.
+
+	NOTE: Please note here that the system wide global DSCR value never
+	gets used directly in the scheduler process context switch at all.
+
+(C) SYSFS Interface:
+
+	Global DSCR default:		/sys/devices/system/cpu/dscr_default
+	CPU specific DSCR default:	/sys/devices/system/cpu/cpuN/dscr
+
+	Changing the global DSCR default in the sysfs will change all the CPU
+	specific DSCR defaults immediately in their PACA structures. Again if
+	the current process has the dscr_inherit clear, it also writes the new
+	value into every CPU's DSCR register right away and updates the current
+	thread's DSCR value as well.
+
+	Changing the CPU specif DSCR default value in the sysfs does exactly
+	the same thing as above but unlike the global one above, it just changes
+	stuff for that particular CPU instead for all the CPUs on the system.
+
+(D) User Space Instructions:
+
+	The DSCR register can be accessed in the user space using any of these
+	two SPR numbers available for that purpose.
+
+	(1) Problem state SPR:		0x03	(Un-privileged, POWER8 only)
+	(2) Privileged state SPR:	0x11	(Privileged)
+
+	Accessing DSCR through privileged SPR number (0x11) from user space
+	works, as it is emulated following an illegal instruction exception
+	inside the kernel. Both mfspr and mtspr instructions are emulated.
+
+	Accessing DSCR through user level SPR (0x03) from user space will first
+	create a facility unavailable exception. Inside this exception handler
+	all mfspr isntruction based read attempts will get emulated and returned
+	where as the first mtspr instruction based write attempts will enable
+	the DSCR facility for the next time around (both for read and write) by
+	setting DSCR facility in the FSCR register.
+
+(E) Specifics about 'dscr_inherit':
+
+	The thread struct element 'dscr_inherit' represents whether the thread
+	in question has attempted and changed the DSCR itself using any of the
+	following methods. This element signifies whether the thread wants to
+	use the CPU default DSCR value or its own changed DSCR value in the
+	kernel.
+
+		(1) mtspr instruction	(SPR number 0x03)
+		(2) mtspr instruction	(SPR number 0x11)
+		(3) ptrace interface	(Explicitly set user DSCR value)
+
+	Any child of the process created after this event in the process inherits
+	this same behaviour as well.
diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt
index ded69794a5c0..ba0a2a4a54ba 100644
--- a/Documentation/powerpc/transactional_memory.txt
+++ b/Documentation/powerpc/transactional_memory.txt
@@ -74,22 +74,23 @@ Causes of transaction aborts
 Syscalls
 ========
 
-Performing syscalls from within transaction is not recommended, and can lead
-to unpredictable results.
+Syscalls made from within an active transaction will not be performed and the
+transaction will be doomed by the kernel with the failure code TM_CAUSE_SYSCALL
+| TM_CAUSE_PERSISTENT.
 
-Syscalls do not by design abort transactions, but beware: The kernel code will
-not be running in transactional state.  The effect of syscalls will always
-remain visible, but depending on the call they may abort your transaction as a
-side-effect, read soon-to-be-aborted transactional data that should not remain
-invisible, etc.  If you constantly retry a transaction that constantly aborts
-itself by calling a syscall, you'll have a livelock & make no progress.
+Syscalls made from within a suspended transaction are performed as normal and
+the transaction is not explicitly doomed by the kernel.  However, what the
+kernel does to perform the syscall may result in the transaction being doomed
+by the hardware.  The syscall is performed in suspended mode so any side
+effects will be persistent, independent of transaction success or failure.  No
+guarantees are provided by the kernel about which syscalls will affect
+transaction success.
 
-Simple syscalls (e.g. sigprocmask()) "could" be OK.  Even things like write()
-from, say, printf() should be OK as long as the kernel does not access any
-memory that was accessed transactionally.
-
-Consider any syscalls that happen to work as debug-only -- not recommended for
-production use.  Best to queue them up till after the transaction is over.
+Care must be taken when relying on syscalls to abort during active transactions
+if the calls are made via a library.  Libraries may cache values (which may
+give the appearance of success) or perform operations that cause transaction
+failure before entering the kernel (which may produce different failure codes).
+Examples are glibc's getpid() and lazy symbol resolution.
 
 
 Signals
@@ -176,8 +177,7 @@ kernel aborted a transaction:
  TM_CAUSE_RESCHED       Thread was rescheduled.
  TM_CAUSE_TLBI          Software TLB invalid.
  TM_CAUSE_FAC_UNAV      FP/VEC/VSX unavailable trap.
- TM_CAUSE_SYSCALL       Currently unused; future syscalls that must abort
-                        transactions for consistency will use this.
+ TM_CAUSE_SYSCALL       Syscall from active transaction.
  TM_CAUSE_SIGNAL        Signal delivered.
  TM_CAUSE_MISC          Currently unused.
  TM_CAUSE_ALIGNMENT     Alignment fault.
diff --git a/Documentation/pps/pps.txt b/Documentation/pps/pps.txt
index c03b1be5eb15..c508cceeee7d 100644
--- a/Documentation/pps/pps.txt
+++ b/Documentation/pps/pps.txt
@@ -166,7 +166,7 @@ Testing the PPS support
 
 In order to test the PPS support even without specific hardware you can use
 the ktimer driver (see the client subsection in the PPS configuration menu)
-and the userland tools provided into Documentaion/pps/ directory.
+and the userland tools provided in the Documentation/pps/ directory.
 
 Once you have enabled the compilation of ktimer just modprobe it (if
 not statically compiled):
diff --git a/Documentation/prctl/Makefile b/Documentation/prctl/Makefile
index 2948b7b124b9..44de3080c7f2 100644
--- a/Documentation/prctl/Makefile
+++ b/Documentation/prctl/Makefile
@@ -1,3 +1,4 @@
+ifndef CROSS_COMPILE
 # List of programs to build
 hostprogs-$(CONFIG_X86) := disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test
 # Tell kbuild to always build the programs
@@ -6,3 +7,4 @@ always := $(hostprogs-y)
 HOSTCFLAGS_disable-tsc-ctxt-sw-stress-test.o += -I$(objtree)/usr/include
 HOSTCFLAGS_disable-tsc-on-off-stress-test.o += -I$(objtree)/usr/include
 HOSTCFLAGS_disable-tsc-test.o += -I$(objtree)/usr/include
+endif
diff --git a/Documentation/preempt-locking.txt b/Documentation/preempt-locking.txt
index 57883ca2498b..e89ce6624af2 100644
--- a/Documentation/preempt-locking.txt
+++ b/Documentation/preempt-locking.txt
@@ -48,7 +48,7 @@ preemption must be disabled around such regions.
 
 Note, some FPU functions are already explicitly preempt safe.  For example,
 kernel_fpu_begin and kernel_fpu_end will disable and enable preemption.
-However, math_state_restore must be called with preemption disabled.
+However, fpu__restore() must be called with preemption disabled.
 
 
 RULE #3: Lock acquire and release must be performed by same task
diff --git a/Documentation/s390/qeth.txt b/Documentation/s390/qeth.txt
index 74122ada9949..aa06fcf5f8c2 100644
--- a/Documentation/s390/qeth.txt
+++ b/Documentation/s390/qeth.txt
@@ -1,6 +1,6 @@
 IBM s390 QDIO Ethernet Driver
 
-HiperSockets Bridge Port Support
+OSA and HiperSockets Bridge Port Support
 
 Uevents
 
@@ -8,7 +8,7 @@ To generate the events the device must be assigned a role of either
 a primary or a secondary Bridge Port. For more information, see
 "z/VM Connectivity, SC24-6174".
 
-When run on HiperSockets Bridge Capable Port hardware, and the state
+When run on an OSA or HiperSockets Bridge Capable Port hardware, and the state
 of some configured Bridge Port device on the channel changes, a udev
 event with ACTION=CHANGE is emitted on behalf of the corresponding
 ccwgroup device. The event has the following attributes:
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 21461a0441c1..e114513a2731 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -8,6 +8,10 @@ CONTENTS
  1. Overview
  2. Scheduling algorithm
  3. Scheduling Real-Time Tasks
+   3.1 Definitions
+   3.2 Schedulability Analysis for Uniprocessor Systems
+   3.3 Schedulability Analysis for Multiprocessor Systems
+   3.4 Relationship with SCHED_DEADLINE Parameters
  4. Bandwidth management
    4.1 System-wide settings
    4.2 Task interface
@@ -43,7 +47,7 @@ CONTENTS
  "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
  "runtime" microseconds of execution time every "period" microseconds, and
  these "runtime" microseconds are available within "deadline" microseconds
- from the beginning of the period.  In order to implement this behaviour,
+ from the beginning of the period.  In order to implement this behavior,
  every time the task wakes up, the scheduler computes a "scheduling deadline"
  consistent with the guarantee (using the CBS[2,3] algorithm). Tasks are then
  scheduled using EDF[1] on these scheduling deadlines (the task with the
@@ -52,7 +56,7 @@ CONTENTS
  "admission control" strategy (see Section "4. Bandwidth management") is used
  (clearly, if the system is overloaded this guarantee cannot be respected).
 
- Summing up, the CBS[2,3] algorithms assigns scheduling deadlines to tasks so
+ Summing up, the CBS[2,3] algorithm assigns scheduling deadlines to tasks so
  that each task runs for at most its runtime every period, avoiding any
  interference between different tasks (bandwidth isolation), while the EDF[1]
  algorithm selects the task with the earliest scheduling deadline as the one
@@ -63,7 +67,7 @@ CONTENTS
  In more details, the CBS algorithm assigns scheduling deadlines to
  tasks in the following way:
 
-  - Each SCHED_DEADLINE task is characterised by the "runtime",
+  - Each SCHED_DEADLINE task is characterized by the "runtime",
     "deadline", and "period" parameters;
 
   - The state of the task is described by a "scheduling deadline", and
@@ -78,7 +82,7 @@ CONTENTS
 
     then, if the scheduling deadline is smaller than the current time, or
     this condition is verified, the scheduling deadline and the
-    remaining runtime are re-initialised as
+    remaining runtime are re-initialized as
 
          scheduling deadline = current time + deadline
          remaining runtime = runtime
@@ -126,31 +130,37 @@ CONTENTS
  suited for periodic or sporadic real-time tasks that need guarantees on their
  timing behavior, e.g., multimedia, streaming, control applications, etc.
 
+3.1 Definitions
+------------------------
+
  A typical real-time task is composed of a repetition of computation phases
  (task instances, or jobs) which are activated on a periodic or sporadic
  fashion.
- Each job J_j (where J_j is the j^th job of the task) is characterised by an
+ Each job J_j (where J_j is the j^th job of the task) is characterized by an
  arrival time r_j (the time when the job starts), an amount of computation
  time c_j needed to finish the job, and a job absolute deadline d_j, which
  is the time within which the job should be finished. The maximum execution
- time max_j{c_j} is called "Worst Case Execution Time" (WCET) for the task.
+ time max{c_j} is called "Worst Case Execution Time" (WCET) for the task.
  A real-time task can be periodic with period P if r_{j+1} = r_j + P, or
  sporadic with minimum inter-arrival time P is r_{j+1} >= r_j + P. Finally,
  d_j = r_j + D, where D is the task's relative deadline.
- The utilisation of a real-time task is defined as the ratio between its
+ Summing up, a real-time task can be described as
+	Task = (WCET, D, P)
+
+ The utilization of a real-time task is defined as the ratio between its
  WCET and its period (or minimum inter-arrival time), and represents
  the fraction of CPU time needed to execute the task.
 
- If the total utilisation sum_i(WCET_i/P_i) is larger than M (with M equal
+ If the total utilization U=sum(WCET_i/P_i) is larger than M (with M equal
  to the number of CPUs), then the scheduler is unable to respect all the
  deadlines.
- Note that total utilisation is defined as the sum of the utilisations
+ Note that total utilization is defined as the sum of the utilizations
  WCET_i/P_i over all the real-time tasks in the system. When considering
  multiple real-time tasks, the parameters of the i-th task are indicated
  with the "_i" suffix.
- Moreover, if the total utilisation is larger than M, then we risk starving
+ Moreover, if the total utilization is larger than M, then we risk starving
  non- real-time tasks by real-time tasks.
- If, instead, the total utilisation is smaller than M, then non real-time
+ If, instead, the total utilization is smaller than M, then non real-time
  tasks will not be starved and the system might be able to respect all the
  deadlines.
  As a matter of fact, in this case it is possible to provide an upper bound
@@ -159,38 +169,119 @@ CONTENTS
  More precisely, it can be proven that using a global EDF scheduler the
  maximum tardiness of each task is smaller or equal than
 	((M − 1) · WCET_max − WCET_min)/(M − (M − 2) · U_max) + WCET_max
- where WCET_max = max_i{WCET_i} is the maximum WCET, WCET_min=min_i{WCET_i}
- is the minimum WCET, and U_max = max_i{WCET_i/P_i} is the maximum utilisation.
+ where WCET_max = max{WCET_i} is the maximum WCET, WCET_min=min{WCET_i}
+ is the minimum WCET, and U_max = max{WCET_i/P_i} is the maximum
+ utilization[12].
+
+3.2 Schedulability Analysis for Uniprocessor Systems
+------------------------
 
  If M=1 (uniprocessor system), or in case of partitioned scheduling (each
  real-time task is statically assigned to one and only one CPU), it is
  possible to formally check if all the deadlines are respected.
  If D_i = P_i for all tasks, then EDF is able to respect all the deadlines
- of all the tasks executing on a CPU if and only if the total utilisation
+ of all the tasks executing on a CPU if and only if the total utilization
  of the tasks running on such a CPU is smaller or equal than 1.
  If D_i != P_i for some task, then it is possible to define the density of
- a task as C_i/min{D_i,T_i}, and EDF is able to respect all the deadlines
- of all the tasks running on a CPU if the sum sum_i C_i/min{D_i,T_i} of the
- densities of the tasks running on such a CPU is smaller or equal than 1
- (notice that this condition is only sufficient, and not necessary).
+ a task as WCET_i/min{D_i,P_i}, and EDF is able to respect all the deadlines
+ of all the tasks running on a CPU if the sum of the densities of the tasks
+ running on such a CPU is smaller or equal than 1:
+	sum(WCET_i / min{D_i, P_i}) <= 1
+ It is important to notice that this condition is only sufficient, and not
+ necessary: there are task sets that are schedulable, but do not respect the
+ condition. For example, consider the task set {Task_1,Task_2} composed by
+ Task_1=(50ms,50ms,100ms) and Task_2=(10ms,100ms,100ms).
+ EDF is clearly able to schedule the two tasks without missing any deadline
+ (Task_1 is scheduled as soon as it is released, and finishes just in time
+ to respect its deadline; Task_2 is scheduled immediately after Task_1, hence
+ its response time cannot be larger than 50ms + 10ms = 60ms) even if
+	50 / min{50,100} + 10 / min{100, 100} = 50 / 50 + 10 / 100 = 1.1
+ Of course it is possible to test the exact schedulability of tasks with
+ D_i != P_i (checking a condition that is both sufficient and necessary),
+ but this cannot be done by comparing the total utilization or density with
+ a constant. Instead, the so called "processor demand" approach can be used,
+ computing the total amount of CPU time h(t) needed by all the tasks to
+ respect all of their deadlines in a time interval of size t, and comparing
+ such a time with the interval size t. If h(t) is smaller than t (that is,
+ the amount of time needed by the tasks in a time interval of size t is
+ smaller than the size of the interval) for all the possible values of t, then
+ EDF is able to schedule the tasks respecting all of their deadlines. Since
+ performing this check for all possible values of t is impossible, it has been
+ proven[4,5,6] that it is sufficient to perform the test for values of t
+ between 0 and a maximum value L. The cited papers contain all of the
+ mathematical details and explain how to compute h(t) and L.
+ In any case, this kind of analysis is too complex as well as too
+ time-consuming to be performed on-line. Hence, as explained in Section
+ 4 Linux uses an admission test based on the tasks' utilizations.
+
+3.3 Schedulability Analysis for Multiprocessor Systems
+------------------------
 
  On multiprocessor systems with global EDF scheduling (non partitioned
  systems), a sufficient test for schedulability can not be based on the
- utilisations (it can be shown that task sets with utilisations slightly
- larger than 1 can miss deadlines regardless of the number of CPUs M).
- However, as previously stated, enforcing that the total utilisation is smaller
- than M is enough to guarantee that non real-time tasks are not starved and
- that the tardiness of real-time tasks has an upper bound.
+ utilizations or densities: it can be shown that even if D_i = P_i task
+ sets with utilizations slightly larger than 1 can miss deadlines regardless
+ of the number of CPUs.
+
+ Consider a set {Task_1,...Task_{M+1}} of M+1 tasks on a system with M
+ CPUs, with the first task Task_1=(P,P,P) having period, relative deadline
+ and WCET equal to P. The remaining M tasks Task_i=(e,P-1,P-1) have an
+ arbitrarily small worst case execution time (indicated as "e" here) and a
+ period smaller than the one of the first task. Hence, if all the tasks
+ activate at the same time t, global EDF schedules these M tasks first
+ (because their absolute deadlines are equal to t + P - 1, hence they are
+ smaller than the absolute deadline of Task_1, which is t + P). As a
+ result, Task_1 can be scheduled only at time t + e, and will finish at
+ time t + e + P, after its absolute deadline. The total utilization of the
+ task set is U = M · e / (P - 1) + P / P = M · e / (P - 1) + 1, and for small
+ values of e this can become very close to 1. This is known as "Dhall's
+ effect"[7]. Note: the example in the original paper by Dhall has been
+ slightly simplified here (for example, Dhall more correctly computed
+ lim_{e->0}U).
+
+ More complex schedulability tests for global EDF have been developed in
+ real-time literature[8,9], but they are not based on a simple comparison
+ between total utilization (or density) and a fixed constant. If all tasks
+ have D_i = P_i, a sufficient schedulability condition can be expressed in
+ a simple way:
+	sum(WCET_i / P_i) <= M - (M - 1) · U_max
+ where U_max = max{WCET_i / P_i}[10]. Notice that for U_max = 1,
+ M - (M - 1) · U_max becomes M - M + 1 = 1 and this schedulability condition
+ just confirms the Dhall's effect. A more complete survey of the literature
+ about schedulability tests for multi-processor real-time scheduling can be
+ found in [11].
+
+ As seen, enforcing that the total utilization is smaller than M does not
+ guarantee that global EDF schedules the tasks without missing any deadline
+ (in other words, global EDF is not an optimal scheduling algorithm). However,
+ a total utilization smaller than M is enough to guarantee that non real-time
+ tasks are not starved and that the tardiness of real-time tasks has an upper
+ bound[12] (as previously noted). Different bounds on the maximum tardiness
+ experienced by real-time tasks have been developed in various papers[13,14],
+ but the theoretical result that is important for SCHED_DEADLINE is that if
+ the total utilization is smaller or equal than M then the response times of
+ the tasks are limited.
+
+3.4 Relationship with SCHED_DEADLINE Parameters
+------------------------
 
- SCHED_DEADLINE can be used to schedule real-time tasks guaranteeing that
- the jobs' deadlines of a task are respected. In order to do this, a task
- must be scheduled by setting:
+ Finally, it is important to understand the relationship between the
+ SCHED_DEADLINE scheduling parameters described in Section 2 (runtime,
+ deadline and period) and the real-time task parameters (WCET, D, P)
+ described in this section. Note that the tasks' temporal constraints are
+ represented by its absolute deadlines d_j = r_j + D described above, while
+ SCHED_DEADLINE schedules the tasks according to scheduling deadlines (see
+ Section 2).
+ If an admission test is used to guarantee that the scheduling deadlines
+ are respected, then SCHED_DEADLINE can be used to schedule real-time tasks
+ guaranteeing that all the jobs' deadlines of a task are respected.
+ In order to do this, a task must be scheduled by setting:
 
   - runtime >= WCET
   - deadline = D
   - period <= P
 
- IOW, if runtime >= WCET and if period is >= P, then the scheduling deadlines
+ IOW, if runtime >= WCET and if period is <= P, then the scheduling deadlines
  and the absolute deadlines (d_j) coincide, so a proper admission control
  allows to respect the jobs' absolute deadlines for this task (this is what is
  called "hard schedulability property" and is an extension of Lemma 1 of [2]).
@@ -206,6 +297,39 @@ CONTENTS
       Symposium, 1998. http://retis.sssup.it/~giorgio/paps/1998/rtss98-cbs.pdf
   3 - L. Abeni. Server Mechanisms for Multimedia Applications. ReTiS Lab
       Technical Report. http://disi.unitn.it/~abeni/tr-98-01.pdf
+  4 - J. Y. Leung and M.L. Merril. A Note on Preemptive Scheduling of
+      Periodic, Real-Time Tasks. Information Processing Letters, vol. 11,
+      no. 3, pp. 115-118, 1980.
+  5 - S. K. Baruah, A. K. Mok and L. E. Rosier. Preemptively Scheduling
+      Hard-Real-Time Sporadic Tasks on One Processor. Proceedings of the
+      11th IEEE Real-time Systems Symposium, 1990.
+  6 - S. K. Baruah, L. E. Rosier and R. R. Howell. Algorithms and Complexity
+      Concerning the Preemptive Scheduling of Periodic Real-Time tasks on
+      One Processor. Real-Time Systems Journal, vol. 4, no. 2, pp 301-324,
+      1990.
+  7 - S. J. Dhall and C. L. Liu. On a real-time scheduling problem. Operations
+      research, vol. 26, no. 1, pp 127-140, 1978.
+  8 - T. Baker. Multiprocessor EDF and Deadline Monotonic Schedulability
+      Analysis. Proceedings of the 24th IEEE Real-Time Systems Symposium, 2003.
+  9 - T. Baker. An Analysis of EDF Schedulability on a Multiprocessor.
+      IEEE Transactions on Parallel and Distributed Systems, vol. 16, no. 8,
+      pp 760-768, 2005.
+  10 - J. Goossens, S. Funk and S. Baruah, Priority-Driven Scheduling of
+       Periodic Task Systems on Multiprocessors. Real-Time Systems Journal,
+       vol. 25, no. 2–3, pp. 187–205, 2003.
+  11 - R. Davis and A. Burns. A Survey of Hard Real-Time Scheduling for
+       Multiprocessor Systems. ACM Computing Surveys, vol. 43, no. 4, 2011.
+       http://www-users.cs.york.ac.uk/~robdavis/papers/MPSurveyv5.0.pdf
+  12 - U. C. Devi and J. H. Anderson. Tardiness Bounds under Global EDF
+       Scheduling on a Multiprocessor. Real-Time Systems Journal, vol. 32,
+       no. 2, pp 133-189, 2008.
+  13 - P. Valente and G. Lipari. An Upper Bound to the Lateness of Soft
+       Real-Time Tasks Scheduled by EDF on Multiprocessors. Proceedings of
+       the 26th IEEE Real-Time Systems Symposium, 2005.
+  14 - J. Erickson, U. Devi and S. Baruah. Improved tardiness bounds for
+       Global EDF. Proceedings of the 22nd Euromicro Conference on
+       Real-Time Systems, 2010.
+
 
 4. Bandwidth management
 =======================
@@ -218,10 +342,10 @@ CONTENTS
  no guarantee can be given on the actual scheduling of the -deadline tasks.
 
  As already stated in Section 3, a necessary condition to be respected to
- correctly schedule a set of real-time tasks is that the total utilisation
+ correctly schedule a set of real-time tasks is that the total utilization
  is smaller than M. When talking about -deadline tasks, this requires that
  the sum of the ratio between runtime and period for all tasks is smaller
- than M. Notice that the ratio runtime/period is equivalent to the utilisation
+ than M. Notice that the ratio runtime/period is equivalent to the utilization
  of a "traditional" real-time task, and is also often referred to as
  "bandwidth".
  The interface used to control the CPU bandwidth that can be allocated
@@ -251,7 +375,7 @@ CONTENTS
  The system wide settings are configured under the /proc virtual file system.
 
  For now the -rt knobs are used for -deadline admission control and the
- -deadline runtime is accounted against the -rt runtime. We realise that this
+ -deadline runtime is accounted against the -rt runtime. We realize that this
  isn't entirely desirable; however, it is better to have a small interface for
  now, and be able to change it easily later. The ideal situation (see 5.) is to
  run -rt tasks from a -deadline server; in which case the -rt bandwidth is a
diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index 731bc4f4c5e6..255075157511 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -1269,7 +1269,7 @@ Members of interest:
     request_buffer - either contains data buffer or scatter gather list
                      depending on the setting of use_sg. Scatter gather
                      elements are defined by 'struct scatterlist' found
-                     in include/asm/scatterlist.h .
+                     in include/linux/scatterlist.h .
     done         - function pointer that should be invoked by LLD when the
                    SCSI command is completed (successfully or otherwise).
                    Should only be called by an LLD if the LLD has accepted
diff --git a/Documentation/scsi/st.txt b/Documentation/scsi/st.txt
index 0d5bdb153d3b..f29fa550665a 100644
--- a/Documentation/scsi/st.txt
+++ b/Documentation/scsi/st.txt
@@ -151,6 +151,65 @@ A link named 'tape' is made from the SCSI device directory to the class
 directory corresponding to the mode 0 auto-rewind device (e.g., st0). 
 
 
+SYSFS AND STATISTICS FOR TAPE DEVICES
+
+The st driver maintains statistics for tape drives inside the sysfs filesystem.
+The following method can be used to locate the statistics that are
+available (assuming that sysfs is mounted at /sys):
+
+1. Use opendir(3) on the directory /sys/class/scsi_tape
+2. Use readdir(3) to read the directory contents
+3. Use regcomp(3)/regexec(3) to match directory entries to the extended
+        regular expression "^st[0-9]+$"
+4. Access the statistics from the /sys/class/scsi_tape/<match>/stats
+        directory (where <match> is a directory entry from /sys/class/scsi_tape
+        that matched the extended regular expression)
+
+The reason for using this approach is that all the character devices
+pointing to the same tape drive use the same statistics. That means
+that st0 would have the same statistics as nst0.
+
+The directory contains the following statistics files:
+
+1.  in_flight - The number of I/Os currently outstanding to this device.
+2.  io_ns - The amount of time spent waiting (in nanoseconds) for all I/O
+        to complete (including read and write). This includes tape movement
+        commands such as seeking between file or set marks and implicit tape
+        movement such as when rewind on close tape devices are used.
+3.  other_cnt - The number of I/Os issued to the tape drive other than read or
+        write commands. The time taken to complete these commands uses the
+        following calculation io_ms-read_ms-write_ms.
+4.  read_byte_cnt - The number of bytes read from the tape drive.
+5.  read_cnt - The number of read requests issued to the tape drive.
+6.  read_ns - The amount of time (in nanoseconds) spent waiting for read
+        requests to complete.
+7.  write_byte_cnt - The number of bytes written to the tape drive.
+8.  write_cnt - The number of write requests issued to the tape drive.
+9.  write_ns - The amount of time (in nanoseconds) spent waiting for write
+        requests to complete.
+10. resid_cnt - The number of times during a read or write we found
+	the residual amount to be non-zero. This should mean that a program
+	is issuing a read larger thean the block size on tape. For write
+	not all data made it to tape.
+
+Note: The in_flight value is incremented when an I/O starts the I/O
+itself is not added to the statistics until it completes.
+
+The total of read_cnt, write_cnt, and other_cnt may not total to the same
+value as iodone_cnt at the device level. The tape statistics only count
+I/O issued via the st module.
+
+When read the statistics may not be temporally consistent while I/O is in
+progress. The individual values are read and written to atomically however
+when reading them back via sysfs they may be in the process of being
+updated when starting an I/O or when it is completed.
+
+The value shown in in_flight is incremented before any statstics are
+updated and decremented when an I/O completes after updating statistics.
+The value of in_flight is 0 when there are no I/Os outstanding that are
+issued by the st driver. Tape statistics do not take into account any
+I/O performed via the sg device.
+
 BSD AND SYS V SEMANTICS
 
 The user can choose between these two behaviours of the tape driver by
diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt
index 1e52d67d0abf..dbe6623fed1c 100644
--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@@ -198,6 +198,9 @@ TTY_IO_ERROR		If set, causes all subsequent userspace read/write
 
 TTY_OTHER_CLOSED	Device is a pty and the other side has closed.
 
+TTY_OTHER_DONE		Device is a pty and the other side has closed and
+			all pending input processing has been completed.
+
 TTY_NO_WRITE_SPLIT	Prevent driver from splitting up writes into
 			smaller chunks.
 
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index 58d0ac4df946..3049a612291b 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -59,11 +59,20 @@ For all other submissions, choose one of the following procedures:
    changelog of your submission, as well as the kernel version you wish
    it to be applied to.
 
-Option 1 is probably the easiest and most common. Options 2 and 3 are more
-useful if the patch isn't deemed worthy at the time it is applied to a public
-git tree (for instance, because it deserves more regression testing first).
-Option 3 is especially useful if the patch needs some special handling to apply
-to an older kernel (e.g., if API's have changed in the meantime).
+Option 1 is *strongly* preferred, is the easiest and most common.  Options 2 and
+3 are more useful if the patch isn't deemed worthy at the time it is applied to
+a public git tree (for instance, because it deserves more regression testing
+first).  Option 3 is especially useful if the patch needs some special handling
+to apply to an older kernel (e.g., if API's have changed in the meantime).
+
+Note that for Option 3, if the patch deviates from the original upstream patch
+(for example because it had to be backported) this must be very clearly
+documented and justified in the patch description.
+
+The upstream commit ID must be specified with a separate line above the commit
+text, like this:
+
+    commit <sha1> upstream.
 
 Additionally, some patches submitted via Option 1 may have additional patch
 prerequisites which can be cherry-picked. This can be specified in the following
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index c831001c45f1..e5d528e0c46e 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -923,6 +923,27 @@ and nmi_watchdog.
 
 ==============================================================
 
+watchdog_cpumask:
+
+This value can be used to control on which cpus the watchdog may run.
+The default cpumask is all possible cores, but if NO_HZ_FULL is
+enabled in the kernel config, and cores are specified with the
+nohz_full= boot argument, those cores are excluded by default.
+Offline cores can be included in this mask, and if the core is later
+brought online, the watchdog will be started based on the mask value.
+
+Typically this value would only be touched in the nohz_full case
+to re-enable cores that by default were not running the watchdog,
+if a kernel lockup was suspected on those cores.
+
+The argument value is the standard cpulist format for cpumasks,
+so for example to enable the watchdog on cores 0, 2, 3, and 4 you
+might say:
+
+  echo 0,2-4 > /proc/sys/kernel/watchdog_cpumask
+
+==============================================================
+
 watchdog_thresh:
 
 This value can be used to control the frequency of hrtimer and NMI
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 2ba71cea0172..6085e1f19c9d 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -503,11 +503,8 @@ def tcm_mod_dump_fabric_ops(proto_ident, fabric_mod_dir_var, fabric_mod_name):
 	buf += "#include <linux/string.h>\n"
 	buf += "#include <linux/ctype.h>\n"
 	buf += "#include <asm/unaligned.h>\n"
-	buf += "#include <scsi/scsi.h>\n"
-	buf += "#include <scsi/scsi_host.h>\n"
-	buf += "#include <scsi/scsi_device.h>\n"
-	buf += "#include <scsi/scsi_cmnd.h>\n"
-	buf += "#include <scsi/libfc.h>\n\n"
+	buf += "#include <scsi/scsi_common.h>\n"
+	buf += "#include <scsi/scsi_proto.h>\n"
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
 	buf += "#include <target/target_core_configfs.h>\n\n"
diff --git a/Documentation/target/tcmu-design.txt b/Documentation/target/tcmu-design.txt
index 43e94ea6d2ca..263b907517ac 100644
--- a/Documentation/target/tcmu-design.txt
+++ b/Documentation/target/tcmu-design.txt
@@ -15,8 +15,7 @@ Contents:
   a) Discovering and configuring TCMU uio devices
   b) Waiting for events on the device(s)
   c) Managing the command ring
-3) Command filtering and pass_level
-4) A final note
+3) A final note
 
 
 TCM Userspace Design
@@ -324,7 +323,7 @@ int handle_device_events(int fd, void *map)
   /* Process events from cmd ring until we catch up with cmd_head */
   while (ent != (void *)mb + mb->cmdr_off + mb->cmd_head) {
 
-    if (tcmu_hdr_get_op(&ent->hdr) == TCMU_OP_CMD) {
+    if (tcmu_hdr_get_op(ent->hdr.len_op) == TCMU_OP_CMD) {
       uint8_t *cdb = (void *)mb + ent->req.cdb_off;
       bool success = true;
 
@@ -339,8 +338,12 @@ int handle_device_events(int fd, void *map)
         ent->rsp.scsi_status = SCSI_CHECK_CONDITION;
       }
     }
+    else if (tcmu_hdr_get_op(ent->hdr.len_op) != TCMU_OP_PAD) {
+      /* Tell the kernel we didn't handle unknown opcodes */
+      ent->hdr.uflags |= TCMU_UFLAG_UNKNOWN_OP;
+    }
     else {
-      /* Do nothing for PAD entries */
+      /* Do nothing for PAD entries except update cmd_tail */
     }
 
     /* update cmd_tail */
@@ -360,28 +363,6 @@ int handle_device_events(int fd, void *map)
 }
 
 
-Command filtering and pass_level
---------------------------------
-
-TCMU supports a "pass_level" option with valid values of 0 or 1.  When
-the value is 0 (the default), nearly all SCSI commands received for
-the device are passed through to the handler. This allows maximum
-flexibility but increases the amount of code required by the handler,
-to support all mandatory SCSI commands. If pass_level is set to 1,
-then only IO-related commands are presented, and the rest are handled
-by LIO's in-kernel command emulation. The commands presented at level
-1 include all versions of:
-
-READ
-WRITE
-WRITE_VERIFY
-XDWRITEREAD
-WRITE_SAME
-COMPARE_AND_WRITE
-SYNCHRONIZE_CACHE
-UNMAP
-
-
 A final note
 ------------
 
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 572ca923631a..7ddb1e319f84 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -108,8 +108,8 @@ of ftrace. Here is a list of some of the key files:
 	data is read from this file, it is consumed, and
 	will not be read again with a sequential read. The
 	"trace" file is static, and if the tracer is not
-	adding more data,they will display the same
-	information every time they are read.
+	adding more data, it will display the same
+	information every time it is read.
 
   trace_options:
 
diff --git a/Documentation/usb/usb-serial.txt b/Documentation/usb/usb-serial.txt
index 947fa62bccf2..349f3104fa4f 100644
--- a/Documentation/usb/usb-serial.txt
+++ b/Documentation/usb/usb-serial.txt
@@ -465,12 +465,14 @@ Generic Serial driver
   device, and does not support any kind of device flow control. All that
   is required of your device is that it has at least one bulk in endpoint,
   or one bulk out endpoint. 
-  
-  To enable the generic driver to recognize your device, build the driver
-  as a module and load it by the following invocation:
+
+  To enable the generic driver to recognize your device, provide
+	echo <vid> <pid> >/sys/bus/usb-serial/drivers/generic/new_id
+  where the <vid> and <pid> is replaced with the hex representation of your
+  device's vendor id and product id.
+  If the driver is compiled as a module you can also provide one id when
+  loading the module
 	insmod usbserial vendor=0x#### product=0x####
-  where the #### is replaced with the hex representation of your device's
-  vendor id and product id.
 
   This driver has been successfully used to connect to the NetChip USB
   development board, providing a way to develop USB firmware without
diff --git a/Documentation/vDSO/Makefile b/Documentation/vDSO/Makefile
index ee075c3d2124..b12e98770e1f 100644
--- a/Documentation/vDSO/Makefile
+++ b/Documentation/vDSO/Makefile
@@ -1,3 +1,4 @@
+ifndef CROSS_COMPILE
 # vdso_test won't build for glibc < 2.16, so disable it
 # hostprogs-y := vdso_test
 hostprogs-$(CONFIG_X86) := vdso_standalone_test_x86
@@ -13,3 +14,4 @@ HOSTLOADLIBES_vdso_standalone_test_x86 := -nostdlib
 ifeq ($(CONFIG_X86_32),y)
 HOSTLOADLIBES_vdso_standalone_test_x86 += -lgcc_s
 endif
+endif
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index 96978eced341..1dd3fddfd3a1 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -289,10 +289,12 @@ PPC64 sPAPR implementation note
 
 This implementation has some specifics:
 
-1) Only one IOMMU group per container is supported as an IOMMU group
-represents the minimal entity which isolation can be guaranteed for and
-groups are allocated statically, one per a Partitionable Endpoint (PE)
+1) On older systems (POWER7 with P5IOC2/IODA1) only one IOMMU group per
+container is supported as an IOMMU table is allocated at the boot time,
+one table per a IOMMU group which is a Partitionable Endpoint (PE)
 (PE is often a PCI domain but not always).
+Newer systems (POWER8 with IODA2) have improved hardware design which allows
+to remove this limitation and have multiple IOMMU groups per a VFIO container.
 
 2) The hardware supports so called DMA windows - the PCI address range
 within which DMA transfer is allowed, any attempt to access address space
@@ -385,6 +387,18 @@ The code flow from the example above should be slightly changed:
 
 	....
 
+	/* Inject EEH error, which is expected to be caused by 32-bits
+	 * config load.
+	 */
+	pe_op.op = VFIO_EEH_PE_INJECT_ERR;
+	pe_op.err.type = EEH_ERR_TYPE_32;
+	pe_op.err.func = EEH_ERR_FUNC_LD_CFG_ADDR;
+	pe_op.err.addr = 0ul;
+	pe_op.err.mask = 0ul;
+	ioctl(container, VFIO_EEH_PE_OP, &pe_op);
+
+	....
+
 	/* When 0xFF's returned from reading PCI config space or IO BARs
 	 * of the PCI device. Check the PE's state to see if that has been
 	 * frozen.
@@ -427,6 +441,48 @@ The code flow from the example above should be slightly changed:
 
 	....
 
+5) There is v2 of SPAPR TCE IOMMU. It deprecates VFIO_IOMMU_ENABLE/
+VFIO_IOMMU_DISABLE and implements 2 new ioctls:
+VFIO_IOMMU_SPAPR_REGISTER_MEMORY and VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY
+(which are unsupported in v1 IOMMU).
+
+PPC64 paravirtualized guests generate a lot of map/unmap requests,
+and the handling of those includes pinning/unpinning pages and updating
+mm::locked_vm counter to make sure we do not exceed the rlimit.
+The v2 IOMMU splits accounting and pinning into separate operations:
+
+- VFIO_IOMMU_SPAPR_REGISTER_MEMORY/VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY ioctls
+receive a user space address and size of the block to be pinned.
+Bisecting is not supported and VFIO_IOMMU_UNREGISTER_MEMORY is expected to
+be called with the exact address and size used for registering
+the memory block. The userspace is not expected to call these often.
+The ranges are stored in a linked list in a VFIO container.
+
+- VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA ioctls only update the actual
+IOMMU table and do not do pinning; instead these check that the userspace
+address is from pre-registered range.
+
+This separation helps in optimizing DMA for guests.
+
+6) sPAPR specification allows guests to have an additional DMA window(s) on
+a PCI bus with a variable page size. Two ioctls have been added to support
+this: VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE.
+The platform has to support the functionality or error will be returned to
+the userspace. The existing hardware supports up to 2 DMA windows, one is
+2GB long, uses 4K pages and called "default 32bit window"; the other can
+be as big as entire RAM, use different page size, it is optional - guests
+create those in run-time if the guest driver supports 64bit DMA.
+
+VFIO_IOMMU_SPAPR_TCE_CREATE receives a page shift, a DMA window size and
+a number of TCE table levels (if a TCE table is going to be big enough and
+the kernel may not be able to allocate enough of physically contiguous memory).
+It creates a new window in the available slot and returns the bus address where
+the new window starts. Due to hardware limitation, the user space cannot choose
+the location of DMA windows.
+
+VFIO_IOMMU_SPAPR_TCE_REMOVE receives the bus start address of the window
+and removes it.
+
 -------------------------------------------------------------------------------
 
 [1] VFIO was originally an acronym for "Virtual Function I/O" in its
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 9fa2bf8c3f6f..a7926a90156f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -254,6 +254,11 @@ since the last call to this ioctl.  Bit 0 is the first page in the
 memory slot.  Ensure the entire structure is cleared to avoid padding
 issues.
 
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
+the address space for which you want to return the dirty bitmap.
+They must be less than the value that KVM_CHECK_EXTENSION returns for
+the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+
 
 4.9 KVM_SET_MEMORY_ALIAS
 
@@ -820,11 +825,21 @@ struct kvm_vcpu_events {
 	} nmi;
 	__u32 sipi_vector;
 	__u32 flags;
+	struct {
+		__u8 smm;
+		__u8 pending;
+		__u8 smm_inside_nmi;
+		__u8 latched_init;
+	} smi;
 };
 
-KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
-interrupt.shadow contains a valid state. Otherwise, this field is undefined.
+Only two fields are defined in the flags field:
+
+- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+  interrupt.shadow contains a valid state.
 
+- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
+  smi contains a valid state.
 
 4.32 KVM_SET_VCPU_EVENTS
 
@@ -841,17 +856,20 @@ vcpu.
 See KVM_GET_VCPU_EVENTS for the data structure.
 
 Fields that may be modified asynchronously by running VCPUs can be excluded
-from the update. These fields are nmi.pending and sipi_vector. Keep the
-corresponding bits in the flags field cleared to suppress overwriting the
-current in-kernel state. The bits are:
+from the update. These fields are nmi.pending, sipi_vector, smi.smm,
+smi.pending. Keep the corresponding bits in the flags field cleared to
+suppress overwriting the current in-kernel state. The bits are:
 
 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+KVM_VCPUEVENT_VALID_SMM         - transfer the smi sub-struct.
 
 If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
 the flags field to signal that interrupt.shadow contains a valid state and
 shall be written into the VCPU.
 
+KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
+
 
 4.33 KVM_GET_DEBUGREGS
 
@@ -911,6 +929,13 @@ slot.  When changing an existing slot, it may be moved in the guest
 physical memory space, or its flags may be modified.  It may not be
 resized.  Slots may not overlap in guest physical address space.
 
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
+specifies the address space which is being modified.  They must be
+less than the value that KVM_CHECK_EXTENSION returns for the
+KVM_CAP_MULTI_ADDRESS_SPACE capability.  Slots in separate address spaces
+are unrelated; the restriction on overlapping slots only applies within
+each address space.
+
 Memory for the region is taken starting at the address denoted by the
 field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
@@ -959,7 +984,8 @@ documentation when it pops into existence).
 4.37 KVM_ENABLE_CAP
 
 Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
-Architectures: ppc, s390
+Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
+	       mips (only KVM_CAP_ENABLE_CAP), ppc, s390
 Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
 Parameters: struct kvm_enable_cap (in)
 Returns: 0 on success; -1 on error
@@ -1268,7 +1294,7 @@ The flags bitmap is defined as:
    /* the host supports the ePAPR idle hcall
    #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
 
-4.48 KVM_ASSIGN_PCI_DEVICE
+4.48 KVM_ASSIGN_PCI_DEVICE (deprecated)
 
 Capability: none
 Architectures: x86
@@ -1318,7 +1344,7 @@ Errors:
   have their standard meanings.
 
 
-4.49 KVM_DEASSIGN_PCI_DEVICE
+4.49 KVM_DEASSIGN_PCI_DEVICE (deprecated)
 
 Capability: none
 Architectures: x86
@@ -1337,7 +1363,7 @@ Errors:
   Other error conditions may be defined by individual device types or
   have their standard meanings.
 
-4.50 KVM_ASSIGN_DEV_IRQ
+4.50 KVM_ASSIGN_DEV_IRQ (deprecated)
 
 Capability: KVM_CAP_ASSIGN_DEV_IRQ
 Architectures: x86
@@ -1377,7 +1403,7 @@ Errors:
   have their standard meanings.
 
 
-4.51 KVM_DEASSIGN_DEV_IRQ
+4.51 KVM_DEASSIGN_DEV_IRQ (deprecated)
 
 Capability: KVM_CAP_ASSIGN_DEV_IRQ
 Architectures: x86
@@ -1451,7 +1477,7 @@ struct kvm_irq_routing_s390_adapter {
 };
 
 
-4.53 KVM_ASSIGN_SET_MSIX_NR
+4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
 
 Capability: none
 Architectures: x86
@@ -1473,7 +1499,7 @@ struct kvm_assigned_msix_nr {
 #define KVM_MAX_MSIX_PER_DEV		256
 
 
-4.54 KVM_ASSIGN_SET_MSIX_ENTRY
+4.54 KVM_ASSIGN_SET_MSIX_ENTRY (deprecated)
 
 Capability: none
 Architectures: x86
@@ -1629,7 +1655,7 @@ should skip processing the bitmap and just invalidate everything.  It must
 be set to the number of set bits in the bitmap.
 
 
-4.61 KVM_ASSIGN_SET_INTX_MASK
+4.61 KVM_ASSIGN_SET_INTX_MASK (deprecated)
 
 Capability: KVM_CAP_PCI_2_3
 Architectures: x86
@@ -2978,6 +3004,16 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
 which is the maximum number of possibly pending cpu-local interrupts.
 
+4.90 KVM_SMI
+
+Capability: KVM_CAP_X86_SMM
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+Queues an SMI on the thread's vcpu.
+
 5. The kvm_run structure
 ------------------------
 
@@ -3013,7 +3049,12 @@ an interrupt can be injected now with KVM_INTERRUPT.
 The value of the current interrupt flag.  Only valid if in-kernel
 local APIC is not used.
 
-	__u8 padding2[2];
+	__u16 flags;
+
+More architecture-specific flags detailing state of the VCPU that may
+affect the device's behavior.  The only currently defined flag is
+KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
+VCPU is in system management mode.
 
 	/* in (pre_kvm_run), out (post_kvm_run) */
 	__u64 cr8;
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 53838d9c6295..3a4d681c3e98 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -169,6 +169,16 @@ Shadow pages contain the following information:
     Contains the value of cr4.smep && !cr0.wp for which the page is valid
     (pages for which this is true are different from other pages; see the
     treatment of cr0.wp=0 below).
+  role.smap_andnot_wp:
+    Contains the value of cr4.smap && !cr0.wp for which the page is valid
+    (pages for which this is true are different from other pages; see the
+    treatment of cr0.wp=0 below).
+  role.smm:
+    Is 1 if the page is valid in system management mode.  This field
+    determines which of the kvm_memslots array was used to build this
+    shadow page; it is also used to go back from a struct kvm_mmu_page
+    to a memslot, through the kvm_memslots_for_spte_role macro and
+    __gfn_to_memslot.
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
@@ -344,10 +354,16 @@ on fault type:
 
 (user write faults generate a #PF)
 
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it.  We handle this by also setting spte.nx.  If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+  the kernel may now execute it.  We handle this by also setting spte.nx.
+  If we get a user fetch or read fault, we'll change spte.u=1 and
+  spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+  page, it can not be reused when CR4.SMAP is enabled. We set
+  CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+  here we do not care the case that CR4.SMAP is enabled since KVM will
+  directly inject #PF to guest due to failed permission check.
 
 To prevent an spte that was converted into a kernel page with cr0.wp=0
 from being written by the kernel after cr0.wp has changed to 1, we make
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt
index 3be0bfc4738d..32ee3a67dba2 100644
--- a/Documentation/vm/unevictable-lru.txt
+++ b/Documentation/vm/unevictable-lru.txt
@@ -467,7 +467,13 @@ mmap(MAP_LOCKED) SYSTEM CALL HANDLING
 
 In addition the mlock()/mlockall() system calls, an application can request
 that a region of memory be mlocked supplying the MAP_LOCKED flag to the mmap()
-call.  Furthermore, any mmap() call or brk() call that expands the heap by a
+call. There is one important and subtle difference here, though. mmap() + mlock()
+will fail if the range cannot be faulted in (e.g. because mm_populate fails)
+and returns with ENOMEM while mmap(MAP_LOCKED) will not fail. The mmaped
+area will still have properties of the locked area - aka. pages will not get
+swapped out - but major page faults to fault memory in might still happen.
+
+Furthermore, any mmap() call or brk() call that expands the heap by a
 task that has previously called mlockall() with the MCL_FUTURE flag will result
 in the newly mapped memory being mlocked.  Before the unevictable/mlock
 changes, the kernel simply called make_pages_present() to allocate pages and
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 88b85899d309..7c1f9fad6674 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -1124,7 +1124,6 @@ The boot loader *must* fill out the following fields in bp,
 
     o hdr.code32_start
     o hdr.cmd_line_ptr
-    o hdr.cmdline_size
     o hdr.ramdisk_image (if applicable)
     o hdr.ramdisk_size  (if applicable)
 
diff --git a/Documentation/x86/entry_64.txt b/Documentation/x86/entry_64.txt
index 9132b86176a3..33884d156125 100644
--- a/Documentation/x86/entry_64.txt
+++ b/Documentation/x86/entry_64.txt
@@ -18,10 +18,10 @@ Some of these entries are:
 
  - system_call: syscall instruction from 64-bit code.
 
- - ia32_syscall: int 0x80 from 32-bit or 64-bit code; compat syscall
+ - entry_INT80_compat: int 0x80 from 32-bit or 64-bit code; compat syscall
    either way.
 
- - ia32_syscall, ia32_sysenter: syscall and sysenter from 32-bit
+ - entry_INT80_compat, ia32_sysenter: syscall and sysenter from 32-bit
    code
 
  - interrupt: An array of entries.  Every IDT vector that doesn't
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/kernel-stacks
index e3c8a49d1a2f..0f3a6c201943 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/kernel-stacks
@@ -1,3 +1,6 @@
+Kernel stacks on x86-64 bit
+---------------------------
+
 Most of the text from Keith Owens, hacked by AK
 
 x86_64 page size (PAGE_SIZE) is 4K.
@@ -56,13 +59,6 @@ If that assumption is ever broken then the stacks will become corrupt.
 
 The currently assigned IST stacks are :-
 
-* STACKFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
-
-  Used for interrupt 12 - Stack Fault Exception (#SS).
-
-  This allows the CPU to recover from invalid stack segments. Rarely
-  happens.
-
 * DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
@@ -99,3 +95,47 @@ The currently assigned IST stacks are :-
   assumptions about the previous state of the kernel stack.
 
 For more details see the Intel IA32 or AMD AMD64 architecture manuals.
+
+
+Printing backtraces on x86
+--------------------------
+
+The question about the '?' preceding function names in an x86 stacktrace
+keeps popping up, here's an indepth explanation. It helps if the reader
+stares at print_context_stack() and the whole machinery in and around
+arch/x86/kernel/dumpstack.c.
+
+Adapted from Ingo's mail, Message-ID: <20150521101614.GA10889@gmail.com>:
+
+We always scan the full kernel stack for return addresses stored on
+the kernel stack(s) [*], from stack top to stack bottom, and print out
+anything that 'looks like' a kernel text address.
+
+If it fits into the frame pointer chain, we print it without a question
+mark, knowing that it's part of the real backtrace.
+
+If the address does not fit into our expected frame pointer chain we
+still print it, but we print a '?'. It can mean two things:
+
+ - either the address is not part of the call chain: it's just stale
+   values on the kernel stack, from earlier function calls. This is
+   the common case.
+
+ - or it is part of the call chain, but the frame pointer was not set
+   up properly within the function, so we don't recognize it.
+
+This way we will always print out the real call chain (plus a few more
+entries), regardless of whether the frame pointer was set up correctly
+or not - but in most cases we'll get the call chain right as well. The
+entries printed are strictly in stack order, so you can deduce more
+information from that as well.
+
+The most important property of this method is that we _never_ lose
+information: we always strive to print _all_ addresses on the stack(s)
+that look like kernel text addresses, so if debug information is wrong,
+we still print out the real call chain as well - just with more question
+marks than ideal.
+
+[*] For things like IRQ and IST stacks, we also scan those stacks, in
+    the right order, and try to cross from one stack into another
+    reconstructing the call chain. This works most of the time.
diff --git a/Documentation/x86/mtrr.txt b/Documentation/x86/mtrr.txt
index cc071dc333c2..860bc3adc223 100644
--- a/Documentation/x86/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -1,7 +1,19 @@
 MTRR (Memory Type Range Register) control
-3 Jun 1999
-Richard Gooch
-<rgooch@atnf.csiro.au>
+
+Richard Gooch <rgooch@atnf.csiro.au> - 3 Jun 1999
+Luis R. Rodriguez <mcgrof@do-not-panic.com> - April 9, 2015
+
+===============================================================================
+Phasing out MTRR use
+
+MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
+of effective MTRR that is expected to be supported will be for write-combining.
+As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
+MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+
+For details refer to Documentation/x86/pat.txt.
+
+===============================================================================
 
   On Intel P6 family processors (Pentium Pro, Pentium II and later)
   the Memory Type Range Registers (MTRRs) may be used to control
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index cf08c9fff3cd..54944c71b819 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -12,7 +12,7 @@ virtual addresses.
 
 PAT allows for different types of memory attributes. The most commonly used
 ones that will be supported at this time are Write-back, Uncached,
-Write-combined and Uncached Minus.
+Write-combined, Write-through and Uncached Minus.
 
 
 PAT APIs
@@ -34,16 +34,23 @@ ioremap                |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_cache          |    --    |    WB      |       WB         |
                        |          |            |                  |
+ioremap_uc             |    --    |    UC      |       UC         |
+                       |          |            |                  |
 ioremap_nocache        |    --    |    UC-     |       UC-        |
                        |          |            |                  |
 ioremap_wc             |    --    |    --      |       WC         |
                        |          |            |                  |
+ioremap_wt             |    --    |    --      |       WT         |
+                       |          |            |                  |
 set_memory_uc          |    UC-   |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
 set_memory_wc          |    WC    |    --      |       --         |
  set_memory_wb         |          |            |                  |
                        |          |            |                  |
+set_memory_wt          |    WT    |    --      |       --         |
+ set_memory_wb         |          |            |                  |
+                       |          |            |                  |
 pci sysfs resource     |    --    |    --      |       UC-        |
                        |          |            |                  |
 pci sysfs resource_wc  |    --    |    --      |       WC         |
@@ -102,7 +109,38 @@ wants to export a RAM region, it has to do set_memory_uc() or set_memory_wc()
 as step 0 above and also track the usage of those pages and use set_memory_wb()
 before the page is freed to free pool.
 
-
+MTRR effects on PAT / non-PAT systems
+-------------------------------------
+
+The following table provides the effects of using write-combining MTRRs when
+using ioremap*() calls on x86 for both non-PAT and PAT systems. Ideally
+mtrr_add() usage will be phased out in favor of arch_phys_wc_add() which will
+be a no-op on PAT enabled systems. The region over which a arch_phys_wc_add()
+is made, should already have been ioremapped with WC attributes or PAT entries,
+this can be done by using ioremap_wc() / set_memory_wc().  Devices which
+combine areas of IO memory desired to remain uncacheable with areas where
+write-combining is desirable should consider use of ioremap_uc() followed by
+set_memory_wc() to white-list effective write-combined areas.  Such use is
+nevertheless discouraged as the effective memory type is considered
+implementation defined, yet this strategy can be used as last resort on devices
+with size-constrained regions where otherwise MTRR write-combining would
+otherwise not be effective.
+
+----------------------------------------------------------------------
+MTRR Non-PAT   PAT    Linux ioremap value        Effective memory type
+----------------------------------------------------------------------
+                                                  Non-PAT |  PAT
+     PAT
+     |PCD
+     ||PWT
+     |||
+WC   000      WB      _PAGE_CACHE_MODE_WB            WC   |   WC
+WC   001      WC      _PAGE_CACHE_MODE_WC            WC*  |   WC
+WC   010      UC-     _PAGE_CACHE_MODE_UC_MINUS      WC*  |   UC
+WC   011      UC      _PAGE_CACHE_MODE_UC            UC   |   UC
+----------------------------------------------------------------------
+
+(*) denotes implementation defined and is discouraged
 
 Notes:
 
@@ -115,8 +153,8 @@ can be more restrictive, in case of any existing aliasing for that address.
 For example: If there is an existing uncached mapping, a new ioremap_wc can
 return uncached mapping in place of write-combine requested.
 
-set_memory_[uc|wc] and set_memory_wb should be used in pairs, where driver will
-first make a region uc or wc and switch it back to wb after use.
+set_memory_[uc|wc|wt] and set_memory_wb should be used in pairs, where driver
+will first make a region uc, wc or wt and switch it back to wb after use.
 
 Over time writes to /proc/mtrr will be deprecated in favor of using PAT based
 interfaces. Users writing to /proc/mtrr are suggested to use above interfaces.
@@ -124,7 +162,7 @@ interfaces. Users writing to /proc/mtrr are suggested to use above interfaces.
 Drivers should use ioremap_[uc|wc] to access PCI BARs with [uc|wc] access
 types.
 
-Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
+Drivers should use set_memory_[uc|wc|wt] to set access type for RAM ranges.
 
 
 PAT debugging
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 5223479291a2..68ed3114c363 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -31,6 +31,9 @@ Machine check
 		(e.g. BIOS or hardware monitoring applications), conflicting
 		with OS's error handling, and you cannot deactivate the agent,
 		then this option will be a help.
+   mce=no_lmce
+		Do not opt-in to Local MCE delivery. Use legacy method
+		to broadcast MCEs.
    mce=bootlog
 		Enable logging of machine checks left over from booting.
 		Disabled by default on AMD because some BIOS leave bogus ones.
diff --git a/Documentation/zh_CN/gpio.txt b/Documentation/zh_CN/gpio.txt
index d5b8f01833f4..bce972521065 100644
--- a/Documentation/zh_CN/gpio.txt
+++ b/Documentation/zh_CN/gpio.txt
@@ -638,9 +638,6 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 	int gpio_export_link(struct device *dev, const char *name,
 		unsigned gpio)
 
-	/* 改变 sysfs 中的一个 GPIO 节点的极性 */
-	int gpio_sysfs_set_active_low(unsigned gpio, int value);
-
 在一个内核驱动申请一个 GPIO 之后，它可以通过 gpio_export()使其在 sysfs
 接口中可见。该驱动可以控制信号方向是否可修改。这有助于防止用户空间代码无意间
 破坏重要的系统状态。
@@ -651,8 +648,3 @@ GPIO 控制器的路径类似 /sys/class/gpio/gpiochip42/ (对于从#42 GPIO
 在 GPIO 被导出之后，gpio_export_link()允许在 sysfs 文件系统的任何地方
 创建一个到这个 GPIO sysfs 节点的符号链接。这样驱动就可以通过一个描述性的
 名字，在 sysfs 中他们所拥有的设备下提供一个(到这个 GPIO sysfs 节点的)接口。
-
-驱动可以使用 gpio_sysfs_set_active_low() 来在用户空间隐藏电路板之间
-GPIO 线的极性差异。这个仅对 sysfs 接口起作用。极性的改变可以在 gpio_export()
-前后进行,且之前使能的轮询操作(poll(2))支持(上升或下降沿)将会被重新配置来遵循
-这个设置。
diff --git a/Documentation/zh_CN/magic-number.txt b/Documentation/zh_CN/magic-number.txt
index dfb72a5c63e9..e9db693c0a23 100644
--- a/Documentation/zh_CN/magic-number.txt
+++ b/Documentation/zh_CN/magic-number.txt
@@ -116,7 +116,6 @@ COW_MAGIC             0x4f4f4f4d  cow_header_v1     arch/um/drivers/ubd_user.c
 I810_CARD_MAGIC       0x5072696E  i810_card         sound/oss/i810_audio.c
 TRIDENT_CARD_MAGIC    0x5072696E  trident_card      sound/oss/trident.c
 ROUTER_MAGIC          0x524d4157  wan_device        [in wanrouter.h pre 3.9]
-SCC_MAGIC             0x52696368  gs_port           drivers/char/scc.h
 SAVEKMSG_MAGIC1       0x53415645  savekmsg          arch/*/amiga/config.c
 GDA_MAGIC             0x58464552  gda               arch/mips/include/asm/sn/gda.h
 RED_MAGIC1            0x5a2cf071  (any)             mm/slab.c
@@ -138,7 +137,6 @@ KMALLOC_MAGIC         0x87654321  snd_alloc_track   sound/core/memory.c
 PWC_MAGIC             0x89DC10AB  pwc_device        drivers/usb/media/pwc.h
 NBD_REPLY_MAGIC       0x96744668  nbd_reply         include/linux/nbd.h
 ENI155_MAGIC          0xa54b872d  midway_eprom	    drivers/atm/eni.h
-SCI_MAGIC             0xbabeface  gs_port           drivers/char/sh-sci.h
 CODA_MAGIC            0xC0DAC0DA  coda_file_info    include/linux/coda_fs_i.h
 DPMEM_MAGIC           0xc0ffee11  gdt_pci_sram      drivers/scsi/gdth.h
 YAM_MAGIC             0xF10A7654  yam_port          drivers/net/hamradio/yam.c
diff --git a/Kbuild b/Kbuild
index 6f0d82a9245d..df99a5f53beb 100644
--- a/Kbuild
+++ b/Kbuild
@@ -2,8 +2,9 @@
 # Kbuild for top-level directory of the kernel
 # This file takes care of the following:
 # 1) Generate bounds.h
-# 2) Generate asm-offsets.h (may need bounds.h)
-# 3) Check for missing system calls
+# 2) Generate timeconst.h
+# 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
+# 4) Check for missing system calls
 
 # Default sed regexp - multiline due to syntax constraints
 define sed-y
@@ -47,7 +48,26 @@ $(obj)/$(bounds-file): kernel/bounds.s FORCE
 	$(call filechk,offsets,__LINUX_BOUNDS_H__)
 
 #####
-# 2) Generate asm-offsets.h
+# 2) Generate timeconst.h
+
+timeconst-file := include/generated/timeconst.h
+
+#always  += $(timeconst-file)
+targets += $(timeconst-file)
+
+quiet_cmd_gentimeconst = GEN     $@
+define cmd_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< ) > $@
+endef
+define filechk_gentimeconst
+	(echo $(CONFIG_HZ) | bc -q $< )
+endef
+
+$(obj)/$(timeconst-file): kernel/time/timeconst.bc FORCE
+	$(call filechk,gentimeconst)
+
+#####
+# 3) Generate asm-offsets.h
 #
 
 offsets-file := include/generated/asm-offsets.h
@@ -57,7 +77,7 @@ targets += arch/$(SRCARCH)/kernel/asm-offsets.s
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
 arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
-                                      $(obj)/$(bounds-file) FORCE
+                                      $(obj)/$(timeconst-file) $(obj)/$(bounds-file) FORCE
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
@@ -65,7 +85,7 @@ $(obj)/$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
 	$(call filechk,offsets,__ASM_OFFSETS_H__)
 
 #####
-# 3) Check for missing system calls
+# 4) Check for missing system calls
 #
 
 always += missing-syscalls
@@ -77,5 +97,5 @@ quiet_cmd_syscalls = CALL    $<
 missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
 	$(call cmd,syscalls)
 
-# Keep these two files during make clean
-no-clean-files := $(bounds-file) $(offsets-file)
+# Keep these three files during make clean
+no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)
diff --git a/MAINTAINERS b/MAINTAINERS
index 781e099495d3..73cfd4b0f539 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -51,9 +51,9 @@ trivial patch so apply some common sense.
 	or does something very odd once a month document it.
 
 	PLEASE remember that submissions must be made under the terms
-	of the OSDL certificate of contribution and should include a
-	Signed-off-by: line.  The current version of this "Developer's
-	Certificate of Origin" (DCO) is listed in the file
+	of the Linux Foundation certificate of contribution and should
+	include a Signed-off-by: line.  The current version of this
+	"Developer's Certificate of Origin" (DCO) is listed in the file
 	Documentation/SubmittingPatches.
 
 6.	Make sure you have the right to send any changes you make. If you
@@ -445,6 +445,7 @@ F:	drivers/input/misc/adxl34x.c
 
 ADVANSYS SCSI DRIVER
 M:	Matthew Wilcox <matthew@wil.cx>
+M:	Hannes Reinecke <hare@suse.de>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	Documentation/scsi/advansys.txt
@@ -652,7 +653,6 @@ M:	Tom Lendacky <thomas.lendacky@amd.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/amd/xgbe/
-F:	drivers/net/phy/amd-xgbe-phy.c
 
 AMS (Apple Motion Sensor) DRIVER
 M:	Michael Hanselmann <linux-kernel@hansmi.ch>
@@ -892,11 +892,10 @@ S:	Maintained
 F:	arch/arm/mach-alpine/
 
 ARM/ATMEL AT91RM9200 AND AT91SAM ARM ARCHITECTURES
-M:	Andrew Victor <linux@maxim.org.za>
 M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Alexandre Belloni <alexandre.belloni@free-electrons.com>
 M:	Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-W:	http://maxim.org.za/at91_26.html
 W:	http://www.linux4sam.org
 S:	Supported
 F:	arch/arm/mach-at91/
@@ -923,6 +922,13 @@ M:	Krzysztof Halasa <khalasa@piap.pl>
 S:	Maintained
 F:	arch/arm/mach-cns3xxx/
 
+ARM/CAVIUM THUNDER NETWORK DRIVER
+M:	Sunil Goutham <sgoutham@cavium.com>
+M:	Robert Richter <rric@kernel.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Supported
+F:	drivers/net/ethernet/cavium/
+
 ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE
 M:	Alexander Shiyan <shc_work@mail.ru>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -975,7 +981,7 @@ S:	Maintained
 ARM/CORTINA SYSTEMS GEMINI ARM ARCHITECTURE
 M:	Hans Ulli Kroll <ulli.kroll@googlemail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-T:	git git://git.berlios.de/gemini-board
+T:	git git://github.com/ulli-kroll/linux.git
 S:	Maintained
 F:	arch/arm/mach-gemini/
 
@@ -990,6 +996,12 @@ F:	drivers/clocksource/timer-prima2.c
 F:	drivers/clocksource/timer-atlas7.c
 N:	[^a-z]sirf
 
+ARM/CONEXANT DIGICOLOR MACHINE SUPPORT
+M:	Baruch Siach <baruch@tkos.co.il>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+N:	digicolor
+
 ARM/EBSA110 MACHINE SUPPORT
 M:	Russell King <linux@arm.linux.org.uk>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1188,7 +1200,7 @@ ARM/MAGICIAN MACHINE SUPPORT
 M:	Philipp Zabel <philipp.zabel@gmail.com>
 S:	Maintained
 
-ARM/Marvell Armada 370 and Armada XP SOC support
+ARM/Marvell Kirkwood and Armada 370, 375, 38x, XP SOC support
 M:	Jason Cooper <jason@lakedaemon.net>
 M:	Andrew Lunn <andrew@lunn.ch>
 M:	Gregory Clement <gregory.clement@free-electrons.com>
@@ -1197,12 +1209,17 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-mvebu/
 F:	drivers/rtc/rtc-armada38x.c
+F:	arch/arm/boot/dts/armada*
+F:	arch/arm/boot/dts/kirkwood*
+
 
 ARM/Marvell Berlin SoC support
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-berlin/
+F:	arch/arm/boot/dts/berlin*
+
 
 ARM/Marvell Dove/MV78xx0/Orion SOC support
 M:	Jason Cooper <jason@lakedaemon.net>
@@ -1215,6 +1232,9 @@ F:	arch/arm/mach-dove/
 F:	arch/arm/mach-mv78xx0/
 F:	arch/arm/mach-orion5x/
 F:	arch/arm/plat-orion/
+F:	arch/arm/boot/dts/dove*
+F:	arch/arm/boot/dts/orion5x*
+
 
 ARM/Orion SoC/Technologic Systems TS-78xx platform support
 M:	Alexander Clouter <alex@digriz.org.uk>
@@ -1366,6 +1386,7 @@ N:	rockchip
 
 ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
 M:	Kukjin Kim <kgene@kernel.org>
+M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 S:	Maintained
@@ -1439,9 +1460,10 @@ ARM/SOCFPGA ARCHITECTURE
 M:	Dinh Nguyen <dinguyen@opensource.altera.com>
 S:	Maintained
 F:	arch/arm/mach-socfpga/
+F:	arch/arm/boot/dts/socfpga*
+F:	arch/arm/configs/socfpga_defconfig
 W:	http://www.rocketboards.org
-T:	git://git.rocketboards.org/linux-socfpga.git
-T:	git://git.rocketboards.org/linux-socfpga-next.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git
 
 ARM/SOCFPGA CLOCK FRAMEWORK SUPPORT
 M:	Dinh Nguyen <dinguyen@opensource.altera.com>
@@ -1473,10 +1495,12 @@ F:	drivers/phy/phy-stih407-usb.c
 F:	drivers/phy/phy-stih41x-usb.c
 F:	drivers/pinctrl/pinctrl-st.c
 F:	drivers/reset/sti/
+F:	drivers/rtc/rtc-st-lpc.c
 F:	drivers/tty/serial/st-asc.c
 F:	drivers/usb/dwc3/dwc3-st.c
 F:	drivers/usb/host/ehci-st.c
 F:	drivers/usb/host/ohci-st.c
+F:	drivers/watchdog/st_lpc_wdt.c
 F:	drivers/ata/ahci_st.c
 
 ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
@@ -1619,11 +1643,12 @@ F:	drivers/i2c/busses/i2c-cadence.c
 F:	drivers/mmc/host/sdhci-of-arasan.c
 F:	drivers/edac/synopsys_edac.c
 
-ARM SMMU DRIVER
+ARM SMMU DRIVERS
 M:	Will Deacon <will.deacon@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/iommu/arm-smmu.c
+F:	drivers/iommu/arm-smmu-v3.c
 F:	drivers/iommu/io-pgtable-arm.c
 
 ARM64 PORT (AARCH64 ARCHITECTURE)
@@ -1854,6 +1879,14 @@ W:	http://www.attotech.com
 S:	Supported
 F:	drivers/scsi/esas2r
 
+ATUSB IEEE 802.15.4 RADIO DRIVER
+M:	Stefan Schmidt <stefan@osg.samsung.com>
+L:	linux-wpan@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ieee802154/atusb.c
+F:	drivers/net/ieee802154/atusb.h
+F:	drivers/net/ieee802154/at86rf230.h
+
 AUDIT SUBSYSTEM
 M:	Paul Moore <paul@paul-moore.com>
 M:	Eric Paris <eparis@redhat.com>
@@ -1929,7 +1962,7 @@ S:	Maintained
 F:	drivers/net/wireless/b43legacy/
 
 BACKLIGHT CLASS/SUBSYSTEM
-M:	Jingoo Han <jg1.han@samsung.com>
+M:	Jingoo Han <jingoohan1@gmail.com>
 M:	Lee Jones <lee.jones@linaro.org>
 S:	Maintained
 F:	drivers/video/backlight/
@@ -2042,6 +2075,7 @@ M:	Jens Axboe <axboe@kernel.dk>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 S:	Maintained
 F:	block/
+F:	kernel/trace/blktrace.c
 
 BLOCK2MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>
@@ -2116,8 +2150,9 @@ S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
 BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
-M:	Christian Daudt <bcm@fixthebug.org>
 M:	Florian Fainelli <f.fainelli@gmail.com>
+M:	Ray Jui <rjui@broadcom.com>
+M:	Scott Branden <sbranden@broadcom.com>
 L:	bcm-kernel-feedback-list@broadcom.com
 T:	git git://github.com/broadcom/mach-bcm
 S:	Maintained
@@ -2168,7 +2203,6 @@ S:	Maintained
 F:	drivers/usb/gadget/udc/bcm63xx_udc.*
 
 BROADCOM BCM7XXX ARM ARCHITECTURE
-M:	Marc Carino <marc.ceeeee@gmail.com>
 M:	Brian Norris <computersforpeace@gmail.com>
 M:	Gregory Fong <gregory.0xf0@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
@@ -2235,6 +2269,13 @@ N:	bcm9583*
 N:	bcm583*
 N:	bcm113*
 
+BROADCOM BRCMSTB GPIO DRIVER
+M:	Gregory Fong <gregory.0xf0@gmail.com>
+L:	bcm-kernel-feedback-list@broadcom.com>
+S:	Supported
+F:	drivers/gpio/gpio-brcmstb.c
+F:	Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+
 BROADCOM KONA GPIO DRIVER
 M:	Ray Jui <rjui@broadcom.com>
 L:	bcm-kernel-feedback-list@broadcom.com
@@ -2242,6 +2283,12 @@ S:	Supported
 F:	drivers/gpio/gpio-bcm-kona.c
 F:	Documentation/devicetree/bindings/gpio/gpio-bcm-kona.txt
 
+BROADCOM STB NAND FLASH DRIVER
+M:	Brian Norris <computersforpeace@gmail.com>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/nand/brcmnand/
+
 BROADCOM SPECIFIC AMBA DRIVER (BCMA)
 M:	Rafał Miłecki <zajec5@gmail.com>
 L:	linux-wireless@vger.kernel.org
@@ -2412,7 +2459,6 @@ L:	linux-security-module@vger.kernel.org
 S:	Supported
 F:	include/linux/capability.h
 F:	include/uapi/linux/capability.h
-F:	security/capability.c
 F:	security/commoncap.c
 F:	kernel/capability.c
 
@@ -2422,6 +2468,17 @@ S:	Maintained
 F:	drivers/iio/light/cm*
 F:	Documentation/devicetree/bindings/i2c/trivial-devices.txt
 
+CAVIUM LIQUIDIO NETWORK DRIVER
+M:     Derek Chickles <derek.chickles@caviumnetworks.com>
+M:     Satanand Burla <satananda.burla@caviumnetworks.com>
+M:     Felix Manlunas <felix.manlunas@caviumnetworks.com>
+M:     Raghu Vatsavayi <raghu.vatsavayi@caviumnetworks.com>
+L:     netdev@vger.kernel.org
+W:     http://www.cavium.com
+S:     Supported
+F:     drivers/net/ethernet/cavium/
+F:     drivers/net/ethernet/cavium/liquidio/
+
 CC2520 IEEE-802.15.4 RADIO DRIVER
 M:	Varka Bhadram <varkabhadram@gmail.com>
 L:	linux-wpan@vger.kernel.org
@@ -2433,7 +2490,6 @@ F:	Documentation/devicetree/bindings/net/ieee802154/cc2520.txt
 CELL BROADBAND ENGINE ARCHITECTURE
 M:	Arnd Bergmann <arnd@arndb.de>
 L:	linuxppc-dev@lists.ozlabs.org
-L:	cbe-oss-dev@lists.ozlabs.org
 W:	http://www.ibm.com/developerworks/power/cell/
 S:	Supported
 F:	arch/powerpc/include/asm/cell*.h
@@ -2589,6 +2645,13 @@ L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	drivers/scsi/fnic/
 
+CISCO SCSI HBA DRIVER
+M:	Narsimhulu Musini <nmusini@cisco.com>
+M:	Sesidhar Baddela <sebaddel@cisco.com>
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/snic/
+
 CMPC ACPI DRIVER
 M:	Thadeu Lima de Souza Cascardo <cascardo@holoscopio.com>
 M:	Daniel Oliveira Nascimento <don@syst.com.br>
@@ -2941,7 +3004,7 @@ M:	Michael Neuling <mikey@neuling.org>
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Supported
 F:	drivers/misc/cxl/
-F:	include/misc/cxl.h
+F:	include/misc/cxl*
 F:	include/uapi/misc/cxl.h
 F:	Documentation/powerpc/cxl.txt
 F:	Documentation/powerpc/cxl.txt
@@ -3715,7 +3778,7 @@ S:	Maintained
 F:	drivers/edac/ie31200_edac.c
 
 EDAC-MPC85XX
-M:	Johannes Thumshirn <johannes.thumshirn@men.de>
+M:	Johannes Thumshirn <morbidrsa@gmail.com>
 L:	linux-edac@vger.kernel.org
 W:	bluesmoke.sourceforge.net
 S:	Maintained
@@ -3742,6 +3805,13 @@ W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/sb_edac.c
 
+EDAC-XGENE
+APPLIED MICRO (APM) X-GENE SOC EDAC
+M:     Loc Ho <lho@apm.com>
+S:     Supported
+F:     drivers/edac/xgene_edac.c
+F:     Documentation/devicetree/bindings/edac/apm-xgene-edac.txt
+
 EDIROL UA-101/UA-1000 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -3810,10 +3880,11 @@ M:	David Woodhouse <dwmw2@infradead.org>
 L:	linux-embedded@vger.kernel.org
 S:	Maintained
 
-EMULEX LPFC FC SCSI DRIVER
-M:	James Smart <james.smart@emulex.com>
+EMULEX/AVAGO LPFC FC/FCOE SCSI DRIVER
+M:	James Smart <james.smart@avagotech.com>
+M:	Dick Kennedy <dick.kennedy@avagotech.com>
 L:	linux-scsi@vger.kernel.org
-W:	http://sourceforge.net/projects/lpfcxxxx
+W:	http://www.avagotech.com
 S:	Supported
 F:	drivers/scsi/lpfc/
 
@@ -3912,7 +3983,7 @@ F:	drivers/extcon/
 F:	Documentation/extcon/
 
 EXYNOS DP DRIVER
-M:	Jingoo Han <jg1.han@samsung.com>
+M:	Jingoo Han <jingoohan1@gmail.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 F:	drivers/gpu/drm/exynos/exynos_dp*
@@ -4371,11 +4442,10 @@ F:	fs/gfs2/
 F:	include/uapi/linux/gfs2_ondisk.h
 
 GIGASET ISDN DRIVERS
-M:	Hansjoerg Lipp <hjlipp@web.de>
-M:	Tilman Schmidt <tilman@imap.cc>
+M:	Paul Bolle <pebolle@tiscali.nl>
 L:	gigaset307x-common@lists.sourceforge.net
 W:	http://gigaset307x.sourceforge.net/
-S:	Maintained
+S:	Odd Fixes
 F:	Documentation/isdn/README.gigaset
 F:	drivers/isdn/gigaset/
 F:	include/uapi/linux/gigaset_dev.h
@@ -4480,6 +4550,17 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/stk1160/
 
+H8/300 ARCHITECTURE
+M:	Yoshinori Sato <ysato@users.sourceforge.jp>
+L:	uclinux-h8-devel@lists.sourceforge.jp
+W:	http://uclinux-h8.sourceforge.jp
+T:	git git://git.sourceforge.jp/gitroot/uclinux-h8/linux.git
+S:	Maintained
+F:	arch/h8300/
+F:	drivers/clocksource/h8300_*.c
+F:	drivers/clk/h8300/
+F:	drivers/irqchip/irq-renesas-h8*.c
+
 HARD DRIVE ACTIVE PROTECTION SYSTEM (HDAPS) DRIVER
 M:	Frank Seidel <frank@f-seidel.de>
 L:	platform-driver-x86@vger.kernel.org
@@ -4522,7 +4603,7 @@ M:	Jean Delvare <jdelvare@suse.de>
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
-T:	quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
+T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git
 S:	Maintained
 F:	Documentation/hwmon/
@@ -4629,6 +4710,18 @@ F:	drivers/hid/
 F:	include/linux/hid*
 F:	include/uapi/linux/hid*
 
+HID SENSOR HUB DRIVERS
+M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jonathan Cameron <jic23@kernel.org>
+M:	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
+L:	linux-input@vger.kernel.org
+L:	linux-iio@vger.kernel.org
+S:	Maintained
+F:	Documentation/hid/hid-sensor*
+F:	drivers/hid/hid-sensor-*
+F:	drivers/iio/*/hid-*
+F:	include/linux/hid-sensor-*
+
 HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS
 M:	Thomas Gleixner <tglx@linutronix.de>
 L:	linux-kernel@vger.kernel.org
@@ -4865,13 +4958,23 @@ M:	Marcelo Henrique Cerri <mhcerri@linux.vnet.ibm.com>
 M:	Fionnuala Gunter <fin@linux.vnet.ibm.com>
 L:	linux-crypto@vger.kernel.org
 S:	Supported
-F:	drivers/crypto/nx/
+F:	drivers/crypto/nx/Makefile
+F:	drivers/crypto/nx/Kconfig
+F:	drivers/crypto/nx/nx-aes*
+F:	drivers/crypto/nx/nx-sha*
+F:	drivers/crypto/nx/nx.*
+F:	drivers/crypto/nx/nx_csbcpb.h
+F:	drivers/crypto/nx/nx_debugfs.h
 
 IBM Power 842 compression accelerator
 M:	Dan Streetman <ddstreet@us.ibm.com>
 S:	Supported
-F:	drivers/crypto/nx/nx-842.c
-F:	include/linux/nx842.h
+F:	drivers/crypto/nx/Makefile
+F:	drivers/crypto/nx/Kconfig
+F:	drivers/crypto/nx/nx-842*
+F:	include/linux/sw842.h
+F:	crypto/842.c
+F:	lib/842/
 
 IBM Power Linux RAID adapter
 M:	Brian King <brking@us.ibm.com>
@@ -5042,17 +5145,19 @@ S:	Orphan
 F:	drivers/video/fbdev/imsttfb.c
 
 INFINIBAND SUBSYSTEM
-M:	Roland Dreier <roland@kernel.org>
+M:	Doug Ledford <dledford@redhat.com>
 M:	Sean Hefty <sean.hefty@intel.com>
 M:	Hal Rosenstock <hal.rosenstock@gmail.com>
 L:	linux-rdma@vger.kernel.org
 W:	http://www.openfabrics.org/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma.git
 S:	Supported
 F:	Documentation/infiniband/
 F:	drivers/infiniband/
 F:	include/uapi/linux/if_infiniband.h
+F:	include/uapi/rdma/
+F:	include/rdma/
 
 INOTIFY
 M:	John McCutchan <john@johnmccutchan.com>
@@ -5078,7 +5183,6 @@ F:	include/linux/input/
 INPUT MULTITOUCH (MT) PROTOCOL
 M:	Henrik Rydberg <rydberg@bitmath.org>
 L:	linux-input@vger.kernel.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rydberg/input-mt.git
 S:	Odd fixes
 F:	Documentation/input/multi-touch-protocol.txt
 F:	drivers/input/input-mt.c
@@ -5805,6 +5909,7 @@ F:	drivers/scsi/53c700*
 LED SUBSYSTEM
 M:	Bryan Wu <cooloney@gmail.com>
 M:	Richard Purdie <rpurdie@rpsys.net>
+M:	Jacek Anaszewski <j.anaszewski@samsung.com>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds.git
 S:	Maintained
@@ -6349,6 +6454,12 @@ F:	include/uapi/linux/meye.h
 F:	include/uapi/linux/ivtv*
 F:	include/uapi/linux/uvcvideo.h
 
+MEDIATEK MT7601U WIRELESS LAN DRIVER
+M:	Jakub Kicinski <kubakici@wp.pl>
+L:	linux-wireless@vger.kernel.org
+S:	Maintained
+F:	drivers/net/wireless/mediatek/mt7601u/
+
 MEGARAID SCSI/SAS DRIVERS
 M:	Kashyap Desai <kashyap.desai@avagotech.com>
 M:	Sumit Saxena <sumit.saxena@avagotech.com>
@@ -6395,14 +6506,14 @@ F:	include/linux/mtd/
 F:	include/uapi/mtd/
 
 MEN A21 WATCHDOG DRIVER
-M:	Johannes Thumshirn <johannes.thumshirn@men.de>
+M:	Johannes Thumshirn <morbidrsa@gmail.com>
 L:	linux-watchdog@vger.kernel.org
-S:	Supported
+S:	Maintained
 F:	drivers/watchdog/mena21_wdt.c
 
 MEN CHAMELEON BUS (mcb)
-M:	Johannes Thumshirn <johannes.thumshirn@men.de>
-S:	Supported
+M:	Johannes Thumshirn <morbidrsa@gmail.com>
+S:	Maintained
 F:	drivers/mcb/
 F:	include/linux/mcb.h
 
@@ -6950,6 +7061,17 @@ T:	git git://git.rocketboards.org/linux-socfpga-next.git
 S:	Maintained
 F:	arch/nios2/
 
+NOKIA N900 POWER SUPPLY DRIVERS
+M:	Pali Rohár <pali.rohar@gmail.com>
+S:	Maintained
+F:	include/linux/power/bq2415x_charger.h
+F:	include/linux/power/bq27x00_battery.h
+F:	include/linux/power/isp1704_charger.h
+F:	drivers/power/bq2415x_charger.c
+F:	drivers/power/bq27x00_battery.c
+F:	drivers/power/isp1704_charger.c
+F:	drivers/power/rx51_battery.c
+
 NTB DRIVER
 M:	Jon Mason <jdmason@kudzu.us>
 M:	Dave Jiang <dave.jiang@intel.com>
@@ -7538,7 +7660,7 @@ S:	Maintained
 F:	drivers/pci/host/*rcar*
 
 PCI DRIVER FOR SAMSUNG EXYNOS
-M:	Jingoo Han <jg1.han@samsung.com>
+M:	Jingoo Han <jingoohan1@gmail.com>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
@@ -7546,7 +7668,8 @@ S:	Maintained
 F:	drivers/pci/host/pci-exynos.c
 
 PCI DRIVER FOR SYNOPSIS DESIGNWARE
-M:	Jingoo Han <jg1.han@samsung.com>
+M:	Jingoo Han <jingoohan1@gmail.com>
+M:	Pratyush Anand <pratyush.anand@gmail.com>
 L:	linux-pci@vger.kernel.org
 S:	Maintained
 F:	drivers/pci/host/*designware*
@@ -7560,10 +7683,19 @@ F:	Documentation/devicetree/bindings/pci/host-generic-pci.txt
 F:	drivers/pci/host/pci-host-generic.c
 
 PCIE DRIVER FOR ST SPEAR13XX
+M:	Pratyush Anand <pratyush.anand@gmail.com>
 L:	linux-pci@vger.kernel.org
-S:	Orphan
+S:	Maintained
 F:	drivers/pci/host/*spear*
 
+PCI MSI DRIVER FOR APPLIEDMICRO XGENE
+M:	Duc Dang <dhdang@apm.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
+F:	drivers/pci/host/pci-xgene-msi.c
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org
@@ -7604,7 +7736,6 @@ F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
-M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -7831,14 +7962,13 @@ F:	drivers/net/wireless/prism54/
 PS3 NETWORK SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
 L:	netdev@vger.kernel.org
-L:	cbe-oss-dev@lists.ozlabs.org
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/net/ethernet/toshiba/ps3_gelic_net.*
 
 PS3 PLATFORM SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
 L:	linuxppc-dev@lists.ozlabs.org
-L:	cbe-oss-dev@lists.ozlabs.org
 S:	Maintained
 F:	arch/powerpc/boot/ps3*
 F:	arch/powerpc/include/asm/lv1call.h
@@ -7852,7 +7982,8 @@ F:	sound/ppc/snd_ps3*
 
 PS3VRAM DRIVER
 M:	Jim Paris <jim@jtan.com>
-L:	cbe-oss-dev@lists.ozlabs.org
+M:	Geoff Levand <geoff@infradead.org>
+L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
 F:	drivers/block/ps3vram.c
 
@@ -8116,8 +8247,6 @@ P:	rt2x00 project
 M:	Stanislaw Gruszka <sgruszka@redhat.com>
 M:	Helmut Schaa <helmut.schaa@googlemail.com>
 L:	linux-wireless@vger.kernel.org
-L:	users@rt2x00.serialmonkey.com (moderated for non-subscribers)
-W:	http://rt2x00.serialmonkey.com/
 S:	Maintained
 F:	drivers/net/wireless/rt2x00/
 
@@ -8502,19 +8631,25 @@ S:	Supported
 F:	sound/soc/samsung/
 
 SAMSUNG FRAMEBUFFER DRIVER
-M:	Jingoo Han <jg1.han@samsung.com>
+M:	Jingoo Han <jingoohan1@gmail.com>
 L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/fbdev/s3c-fb.c
 
-SAMSUNG MULTIFUNCTION DEVICE DRIVERS
+SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
 M:	Sangbeom Kim <sbkim73@samsung.com>
+M:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
 L:	linux-kernel@vger.kernel.org
+L:	linux-samsung-soc@vger.kernel.org
 S:	Supported
 F:	drivers/mfd/sec*.c
 F:	drivers/regulator/s2m*.c
 F:	drivers/regulator/s5m*.c
+F:	drivers/clk/clk-s2mps11.c
+F:	drivers/rtc/rtc-s5m.c
 F:	include/linux/mfd/samsung/
+F:	Documentation/devicetree/bindings/regulator/s5m8767-regulator.txt
+F:	Documentation/devicetree/bindings/mfd/s2mp*.txt
 
 SAMSUNG S5P/EXYNOS4 SOC SERIES CAMERA SUBSYSTEM DRIVERS
 M:	Kyungmin Park <kyungmin.park@samsung.com>
@@ -8801,16 +8936,19 @@ F:	drivers/misc/phantom.c
 F:	include/uapi/linux/phantom.h
 
 SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
-M:	Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
+M:	Jayamohan Kallickal <jayamohan.kallickal@avagotech.com>
+M:	Minh Tran <minh.tran@avagotech.com>
+M:	John Soni Jose <sony.john-n@avagotech.com>
 L:	linux-scsi@vger.kernel.org
-W:	http://www.emulex.com
+W:	http://www.avagotech.com
 S:	Supported
 F:	drivers/scsi/be2iscsi/
 
-SERVER ENGINES 10Gbps NIC - BladeEngine 2 DRIVER
-M:	Sathya Perla <sathya.perla@emulex.com>
-M:	Subbu Seetharaman <subbu.seetharaman@emulex.com>
-M:	Ajit Khaparde <ajit.khaparde@emulex.com>
+Emulex 10Gbps NIC BE2, BE3-R, Lancer, Skyhawk-R DRIVER
+M:	Sathya Perla <sathya.perla@avagotech.com>
+M:	Ajit Khaparde <ajit.khaparde@avagotech.com>
+M:	Padmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
+M:	Sriharsha Basavapatna <sriharsha.basavapatna@avagotech.com>
 L:	netdev@vger.kernel.org
 W:	http://www.emulex.com
 S:	Supported
@@ -9328,7 +9466,6 @@ F:	drivers/net/ethernet/toshiba/spider_net*
 SPU FILE SYSTEM
 M:	Jeremy Kerr <jk@ozlabs.org>
 L:	linuxppc-dev@lists.ozlabs.org
-L:	cbe-oss-dev@lists.ozlabs.org
 W:	http://www.ibm.com/developerworks/power/cell/
 S:	Supported
 F:	Documentation/filesystems/spufs.txt
@@ -9550,6 +9687,13 @@ F:	arch/arc/
 F:	Documentation/devicetree/bindings/arc/
 F:	drivers/tty/serial/arc_uart.c
 
+SYSTEM CONFIGURATION (SYSCON)
+M:	Lee Jones <lee.jones@linaro.org>
+M:	Arnd Bergmann <arnd@arndb.de>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd.git
+S:	Supported
+F:	drivers/mfd/syscon.c
+
 SYSV FILESYSTEM
 M:	Christoph Hellwig <hch@infradead.org>
 S:	Maintained
@@ -9984,7 +10128,7 @@ F:	include/linux/toshiba.h
 F:	include/uapi/linux/toshiba.h
 
 TMIO MMC DRIVER
-M:	Ian Molton <ian.molton@codethink.co.uk>
+M:	Ian Molton <ian@mnementh.co.uk>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/tmio_mmc*
@@ -10556,8 +10700,7 @@ F:	drivers/virtio/virtio_input.c
 F:	include/uapi/linux/virtio_input.h
 
 VIA RHINE NETWORK DRIVER
-M:	Roger Luethi <rl@hellgate.ch>
-S:	Maintained
+S:	Orphan
 F:	drivers/net/ethernet/via/via-rhine.c
 
 VIA SD/MMC CARD CONTROLLER DRIVER
@@ -10863,7 +11006,7 @@ M:	Andy Lutomirski <luto@amacapital.net>
 L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
 S:	Maintained
-F:	arch/x86/vdso/
+F:	arch/x86/entry/vdso/
 
 XC2028/3028 TUNER DRIVER
 M:	Mauro Carvalho Chehab <mchehab@osg.samsung.com>
@@ -11037,6 +11180,7 @@ F:	drivers/media/pci/zoran/
 ZRAM COMPRESSED RAM BLOCK DEVICE DRVIER
 M:	Minchan Kim <minchan@kernel.org>
 M:	Nitin Gupta <ngupta@vflare.org>
+R:	Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	drivers/block/zram/
diff --git a/Makefile b/Makefile
index 2da553fd7fc3..6c6f14628f32 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -215,7 +215,6 @@ VPATH		:= $(srctree)$(if $(KBUILD_EXTMOD),:$(KBUILD_EXTMOD))
 
 export srctree objtree VPATH
 
-
 # SUBARCH tells the usermode build what the underlying arch is.  That is set
 # first, and if a usermode build is happening, the "ARCH=um" on the command
 # line overrides the setting of ARCH below.  If a native build is happening,
@@ -1497,11 +1496,11 @@ image_name:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile
index cd143887380a..8399bd0e68e8 100644
--- a/arch/alpha/boot/Makefile
+++ b/arch/alpha/boot/Makefile
@@ -14,6 +14,9 @@ targets		:= vmlinux.gz vmlinux \
 		   tools/bootpzh bootloader bootpheader bootpzheader 
 OBJSTRIP	:= $(obj)/tools/objstrip
 
+HOSTCFLAGS	:= -Wall -I$(objtree)/usr/include
+BOOTCFLAGS	+= -I$(obj) -I$(srctree)/$(obj)
+
 # SRM bootable image.  Copy to offset 512 of a partition.
 $(obj)/bootimage: $(addprefix $(obj)/tools/,mkbb lxboot bootlx) $(obj)/vmlinux.nh
 	( cat $(obj)/tools/lxboot $(obj)/tools/bootlx $(obj)/vmlinux.nh ) > $@ 
@@ -96,13 +99,14 @@ $(obj)/tools/bootph: $(obj)/bootpheader $(OBJSTRIP) FORCE
 $(obj)/tools/bootpzh: $(obj)/bootpzheader $(OBJSTRIP) FORCE
 	$(call if_changed,objstrip)
 
-LDFLAGS_bootloader   := -static -uvsprintf -T  #-N -relax
-LDFLAGS_bootpheader  := -static -uvsprintf -T  #-N -relax
-LDFLAGS_bootpzheader := -static -uvsprintf -T  #-N -relax
+LDFLAGS_bootloader   := -static -T # -N -relax
+LDFLAGS_bootloader   := -static -T # -N -relax
+LDFLAGS_bootpheader  := -static -T # -N -relax
+LDFLAGS_bootpzheader := -static -T # -N -relax
 
-OBJ_bootlx   := $(obj)/head.o $(obj)/main.o
-OBJ_bootph   := $(obj)/head.o $(obj)/bootp.o
-OBJ_bootpzh  := $(obj)/head.o $(obj)/bootpz.o $(obj)/misc.o
+OBJ_bootlx   := $(obj)/head.o $(obj)/stdio.o $(obj)/main.o
+OBJ_bootph   := $(obj)/head.o $(obj)/stdio.o $(obj)/bootp.o
+OBJ_bootpzh  := $(obj)/head.o $(obj)/stdio.o $(obj)/bootpz.o $(obj)/misc.o
 
 $(obj)/bootloader: $(obj)/bootloader.lds $(OBJ_bootlx) $(LIBS_Y) FORCE
 	$(call if_changed,ld)
diff --git a/arch/alpha/boot/main.c b/arch/alpha/boot/main.c
index 3baf2d1e908d..dd6eb4a33582 100644
--- a/arch/alpha/boot/main.c
+++ b/arch/alpha/boot/main.c
@@ -19,7 +19,6 @@
 
 #include "ksize.h"
 
-extern int vsprintf(char *, const char *, va_list);
 extern unsigned long switch_to_osf_pal(unsigned long nr,
 	struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
 	unsigned long *vptb);
diff --git a/arch/alpha/boot/stdio.c b/arch/alpha/boot/stdio.c
new file mode 100644
index 000000000000..f844dae8a54a
--- /dev/null
+++ b/arch/alpha/boot/stdio.c
@@ -0,0 +1,306 @@
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+
+size_t strnlen(const char * s, size_t count)
+{
+	const char *sc;
+
+	for (sc = s; count-- && *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+
+# define do_div(n, base) ({						\
+	unsigned int __base = (base);					\
+	unsigned int __rem;						\
+	__rem = ((unsigned long long)(n)) % __base;			\
+	(n) = ((unsigned long long)(n)) / __base;			\
+	__rem;								\
+})
+
+
+static int skip_atoi(const char **s)
+{
+	int i, c;
+
+	for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s)
+		i = i*10 + c - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SPECIAL	32		/* 0x */
+#define LARGE	64		/* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, unsigned long long num, int base, int size, int precision, int type)
+{
+	char c,sign,tmp[66];
+	const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+	int i;
+
+	if (type & LARGE)
+		digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 36)
+		return 0;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if ((signed long long)num < 0) {
+			sign = '-';
+			num = - (signed long long)num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++]='0';
+	else while (num != 0) {
+		tmp[i++] = digits[do_div(num, base)];
+	}
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type&(ZEROPAD+LEFT)))
+		while(size-->0)
+			*str++ = ' ';
+	if (sign)
+		*str++ = sign;
+	if (type & SPECIAL) {
+		if (base==8)
+			*str++ = '0';
+		else if (base==16) {
+			*str++ = '0';
+			*str++ = digits[33];
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			*str++ = c;
+	while (i < precision--)
+		*str++ = '0';
+	while (i-- > 0)
+		*str++ = tmp[i];
+	while (size-- > 0)
+		*str++ = ' ';
+	return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long long num;
+	int i, base;
+	char * str;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+	                        /* 'z' support added 23/7/1999 S.H.    */
+				/* 'z' changed to 'Z' --davidm 1/25/99 */
+
+
+	for (str=buf ; *fmt ; ++fmt) {
+		if (*fmt != '%') {
+			*str++ = *fmt;
+			continue;
+		}
+
+		/* process flags */
+		flags = 0;
+		repeat:
+			++fmt;		/* this also skips first '%' */
+			switch (*fmt) {
+				case '-': flags |= LEFT; goto repeat;
+				case '+': flags |= PLUS; goto repeat;
+				case ' ': flags |= SPACE; goto repeat;
+				case '#': flags |= SPECIAL; goto repeat;
+				case '0': flags |= ZEROPAD; goto repeat;
+				}
+
+		/* get field width */
+		field_width = -1;
+		if ('0' <= *fmt && *fmt <= '9')
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;
+			if ('0' <= *fmt && *fmt <= '9')
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'l' && *(fmt + 1) == 'l') {
+			qualifier = 'q';
+			fmt += 2;
+		} else if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L'
+			|| *fmt == 'Z') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					*str++ = ' ';
+			*str++ = (unsigned char) va_arg(args, int);
+			while (--field_width > 0)
+				*str++ = ' ';
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			if (!s)
+				s = "<NULL>";
+
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					*str++ = ' ';
+			for (i = 0; i < len; ++i)
+				*str++ = *s++;
+			while (len < field_width--)
+				*str++ = ' ';
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2*sizeof(void *);
+				flags |= ZEROPAD;
+			}
+			str = number(str,
+				(unsigned long) va_arg(args, void *), 16,
+				field_width, precision, flags);
+			continue;
+
+
+		case 'n':
+			if (qualifier == 'l') {
+				long * ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else if (qualifier == 'Z') {
+				size_t * ip = va_arg(args, size_t *);
+				*ip = (str - buf);
+			} else {
+				int * ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			*str++ = '%';
+			continue;
+
+		/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'X':
+			flags |= LARGE;
+		case 'x':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+		case 'u':
+			break;
+
+		default:
+			*str++ = '%';
+			if (*fmt)
+				*str++ = *fmt;
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'l') {
+			num = va_arg(args, unsigned long);
+			if (flags & SIGN)
+				num = (signed long) num;
+		} else if (qualifier == 'q') {
+			num = va_arg(args, unsigned long long);
+			if (flags & SIGN)
+				num = (signed long long) num;
+		} else if (qualifier == 'Z') {
+			num = va_arg(args, size_t);
+		} else if (qualifier == 'h') {
+			num = (unsigned short) va_arg(args, int);
+			if (flags & SIGN)
+				num = (signed short) num;
+		} else {
+			num = va_arg(args, unsigned int);
+			if (flags & SIGN)
+				num = (signed int) num;
+		}
+		str = number(str, num, base, field_width, precision, flags);
+	}
+	*str = '\0';
+	return str-buf;
+}
+
+int sprintf(char * buf, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i=vsprintf(buf,fmt,args);
+	va_end(args);
+	return i;
+}
diff --git a/arch/alpha/boot/tools/objstrip.c b/arch/alpha/boot/tools/objstrip.c
index 367d53d031fc..dee82695f48b 100644
--- a/arch/alpha/boot/tools/objstrip.c
+++ b/arch/alpha/boot/tools/objstrip.c
@@ -27,6 +27,9 @@
 #include <linux/param.h>
 #ifdef __ELF__
 # include <linux/elf.h>
+# define elfhdr elf64_hdr
+# define elf_phdr elf64_phdr
+# define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
 #endif
 
 /* bootfile size must be multiple of BLOCK_SIZE: */
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 429e8cd0d78e..e5117766529e 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -66,6 +66,4 @@
 #undef __ASM__MB
 #undef ____cmpxchg
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/alpha/include/asm/mm-arch-hooks.h b/arch/alpha/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..b07fd862fec3
--- /dev/null
+++ b/arch/alpha/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ALPHA_MM_ARCH_HOOKS_H
+#define _ASM_ALPHA_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ALPHA_MM_ARCH_HOOKS_H */
diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h
index bf7d97dce9e8..98f2eeee8f68 100644
--- a/arch/alpha/include/asm/pci.h
+++ b/arch/alpha/include/asm/pci.h
@@ -71,22 +71,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_BOUNDARY;
-	*strategy_parameter = cacheline_size;
-}
 #endif
 
 /* TODO: integrate with include/asm-generic/pci.h ? */
diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h
index f61e1a56c378..4cb4b6d3452c 100644
--- a/arch/alpha/include/asm/types.h
+++ b/arch/alpha/include/asm/types.h
@@ -2,6 +2,5 @@
 #define _ALPHA_TYPES_H
 
 #include <asm-generic/int-ll64.h>
-#include <uapi/asm/types.h>
 
 #endif /* _ALPHA_TYPES_H */
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index c509d306db45..a56e608db2f9 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -3,7 +3,7 @@
 
 #include <uapi/asm/unistd.h>
 
-#define NR_SYSCALLS			511
+#define NR_SYSCALLS			514
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h
index d214a0358100..aa33bf5aacb6 100644
--- a/arch/alpha/include/uapi/asm/unistd.h
+++ b/arch/alpha/include/uapi/asm/unistd.h
@@ -472,5 +472,8 @@
 #define __NR_sched_setattr		508
 #define __NR_sched_getattr		509
 #define __NR_renameat2			510
+#define __NR_getrandom			511
+#define __NR_memfd_create		512
+#define __NR_execveat			513
 
 #endif /* _UAPI_ALPHA_UNISTD_H */
diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c
index 00096df0f6ad..83d0a359a1b2 100644
--- a/arch/alpha/kernel/core_irongate.c
+++ b/arch/alpha/kernel/core_irongate.c
@@ -22,7 +22,6 @@
 #include <linux/bootmem.h>
 
 #include <asm/ptrace.h>
-#include <asm/pci.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c
index 253cf1a87481..51267ac5729b 100644
--- a/arch/alpha/kernel/err_ev6.c
+++ b/arch/alpha/kernel/err_ev6.c
@@ -6,7 +6,6 @@
  *	Error handling code supporting Alpha systems
  */
 
-#include <linux/init.h>
 #include <linux/sched.h>
 
 #include <asm/io.h>
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 7b2be251c30f..51f2c8654253 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -19,7 +19,6 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 #include <linux/random.h>
-#include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index e51f578636a5..36dc91ace83a 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1019,14 +1019,13 @@ SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
  	if (tv) {
 		if (get_tv32((struct timeval *)&kts, tv))
 			return -EFAULT;
+		kts.tv_nsec *= 1000;
 	}
 	if (tz) {
 		if (copy_from_user(&ktz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	kts.tv_nsec *= 1000;
-
 	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 1941a07b5811..84d13263ce46 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -236,12 +236,11 @@ release_thread(struct task_struct *dead_task)
 }
 
 /*
- * Copy an alpha thread..
+ * Copy architecture-specific thread state
  */
-
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long arg,
+	    unsigned long kthread_arg,
 	    struct task_struct *p)
 {
 	extern void ret_from_fork(void);
@@ -262,7 +261,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 			sizeof(struct switch_stack) + sizeof(struct pt_regs));
 		childstack->r26 = (unsigned long) ret_from_kernel_thread;
 		childstack->r9 = usp;	/* function */
-		childstack->r10 = arg;
+		childstack->r10 = kthread_arg;
 		childregs->hae = alpha_mv.hae_cache,
 		childti->pcb.usp = 0;
 		return 0;
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 99ac36d5de4e..2f24447fef92 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -63,7 +63,6 @@ static struct {
 enum ipi_message_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
 };
 
@@ -506,7 +505,6 @@ setup_profiling_timer(unsigned int multiplier)
 	return -EINVAL;
 }
 
-
 static void
 send_ipi_message(const struct cpumask *to_whom, enum ipi_message_type operation)
 {
@@ -552,10 +550,6 @@ handle_ipi(struct pt_regs *regs)
 			generic_smp_call_function_interrupt();
 			break;
 
-		case IPI_CALL_FUNC_SINGLE:
-			generic_smp_call_function_single_interrupt();
-			break;
-
 		case IPI_CPU_STOP:
 			halt();
 
@@ -606,7 +600,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
 static void
diff --git a/arch/alpha/kernel/srmcons.c b/arch/alpha/kernel/srmcons.c
index 6f01d9ad7b81..72b59511e59a 100644
--- a/arch/alpha/kernel/srmcons.c
+++ b/arch/alpha/kernel/srmcons.c
@@ -237,8 +237,7 @@ srmcons_init(void)
 
 	return -ENODEV;
 }
-
-module_init(srmcons_init);
+device_initcall(srmcons_init);
 
 
 /*
diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c
index 79d69d7f63f8..15f42083bdb3 100644
--- a/arch/alpha/kernel/sys_eiger.c
+++ b/arch/alpha/kernel/sys_eiger.c
@@ -22,7 +22,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pci.h>
 #include <asm/pgtable.h>
 #include <asm/core_tsunami.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c
index f21d61fab678..24e41bd7d3c9 100644
--- a/arch/alpha/kernel/sys_marvel.c
+++ b/arch/alpha/kernel/sys_marvel.c
@@ -331,7 +331,7 @@ marvel_map_irq(const struct pci_dev *cdev, u8 slot, u8 pin)
 	pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &intline);
 	irq = intline;
 
-	msi_loc = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	msi_loc = dev->msi_cap;
 	msg_ctl = 0;
 	if (msi_loc) 
 		pci_read_config_word(dev, msi_loc + PCI_MSI_FLAGS, &msg_ctl);
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 700686d04869..2cfaa0e5c577 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -39,7 +39,6 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/io.h>
-#include <asm/pci.h>
 #include <asm/pgtable.h>
 #include <asm/core_irongate.h>
 #include <asm/hwrpb.h>
diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S
index 24789713f1ea..9b62e3fd4f03 100644
--- a/arch/alpha/kernel/systbls.S
+++ b/arch/alpha/kernel/systbls.S
@@ -529,6 +529,9 @@ sys_call_table:
 	.quad sys_sched_setattr
 	.quad sys_sched_getattr
 	.quad sys_renameat2			/* 510 */
+	.quad sys_getrandom
+	.quad sys_memfd_create
+	.quad sys_execveat
 
 	.size sys_call_table, . - sys_call_table
 	.type sys_call_table, @object
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 9c4c189eb22f..74aceead06e9 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -14,7 +14,6 @@
 #include <linux/tty.h>
 #include <linux/delay.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/kallsyms.h>
 #include <linux/ratelimit.h>
 
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 9d0ac091a52a..4a905bd667e2 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -23,8 +23,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
 
@@ -107,7 +106,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 
 	/* If we're in an interrupt context, or have no user context,
 	   we must not take the fault.  */
-	if (!mm || in_atomic())
+	if (!mm || faulthandler_disabled())
 		goto no_context;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/alpha/oprofile/op_model_ev4.c b/arch/alpha/oprofile/op_model_ev4.c
index 18aa9b4f94f1..086a0d5445c5 100644
--- a/arch/alpha/oprofile/op_model_ev4.c
+++ b/arch/alpha/oprofile/op_model_ev4.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/alpha/oprofile/op_model_ev5.c b/arch/alpha/oprofile/op_model_ev5.c
index c32f8a0ad925..c300f5ef3482 100644
--- a/arch/alpha/oprofile/op_model_ev5.c
+++ b/arch/alpha/oprofile/op_model_ev5.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/alpha/oprofile/op_model_ev6.c b/arch/alpha/oprofile/op_model_ev6.c
index 1c84cc257fc7..02edf5971614 100644
--- a/arch/alpha/oprofile/op_model_ev6.c
+++ b/arch/alpha/oprofile/op_model_ev6.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/alpha/oprofile/op_model_ev67.c b/arch/alpha/oprofile/op_model_ev67.c
index 34a57a126553..adb1744d20f3 100644
--- a/arch/alpha/oprofile/op_model_ev67.c
+++ b/arch/alpha/oprofile/op_model_ev67.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 
diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug
index a7fc0da25650..ff6a4b5ce927 100644
--- a/arch/arc/Kconfig.debug
+++ b/arch/arc/Kconfig.debug
@@ -2,19 +2,6 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config EARLY_PRINTK
-	bool "Early printk" if EMBEDDED
-	default y
-	help
-	  Write kernel log output directly into the VGA buffer or to a serial
-	  port.
-
-	  This is useful for kernel debugging when your machine crashes very
-	  early before the console code is initialized. For normal operation
-	  it is not recommended because it looks ugly and doesn't cooperate
-	  with klogd/syslogd or the X server. You should normally N here,
-	  unless you want to debug such a crash.
-
 config 16KSTACKS
 	bool "Use 16Kb for kernel stacks instead of 8Kb"
 	help
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 067551b6920a..9917a45fc430 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -99,7 +99,7 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 	atomic_ops_unlock(flags);					\
 }
 
-#define ATOMIC_OP_RETURN(op, c_op)					\
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
 	unsigned long flags;						\
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 4dc64ddebece..05b5aaf5b0f9 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -53,7 +53,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -75,7 +75,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
@@ -104,7 +104,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-/* Compare-xchg with preemption disabled.
+/* Compare-xchg with pagefaults disabled.
  *  Notes:
  *      -Best-Effort: Exchg happens only if compare succeeds.
  *          If compare fails, returns; leaving retry/looping to upper layers
@@ -121,7 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
@@ -142,7 +142,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 	: "r"(oldval), "r"(newval), "r"(uaddr), "ir"(-EFAULT)
 	: "cc", "memory");
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	*uval = val;
 	return val;
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index cabd518cb253..7cc4ced5dbf4 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -20,6 +20,7 @@ extern void iounmap(const void __iomem *addr);
 
 #define ioremap_nocache(phy, sz)	ioremap(phy, sz)
 #define ioremap_wc(phy, sz)		ioremap(phy, sz)
+#define ioremap_wt(phy, sz)		ioremap(phy, sz)
 
 /* Change struct page to physical address */
 #define page_to_phys(page)		(page_to_pfn(page) << PAGE_SHIFT)
diff --git a/arch/arc/include/asm/mm-arch-hooks.h b/arch/arc/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..c37541c5f8ba
--- /dev/null
+++ b/arch/arc/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARC_MM_ARCH_HOOKS_H
+#define _ASM_ARC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARC_MM_ARCH_HOOKS_H */
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 8c3a3e02ba92..12b2100db073 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -266,7 +266,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
  * Machine specific helpers for Entire D-Cache or Per Line ops
  */
 
-static unsigned int __before_dc_op(const int op)
+static inline unsigned int __before_dc_op(const int op)
 {
 	unsigned int reg = reg;
 
@@ -284,7 +284,7 @@ static unsigned int __before_dc_op(const int op)
 	return reg;
 }
 
-static void __after_dc_op(const int op, unsigned int reg)
+static inline void __after_dc_op(const int op, unsigned int reg)
 {
 	if (op & OP_FLUSH)	/* flush / flush-n-inv both wait */
 		while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS);
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6a2e006cbcce..d948e4e9d89c 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -86,7 +86,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 45df48ba0b12..325d6f3a596a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -15,6 +15,8 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select EDAC_SUPPORT
+	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 86217db2937a..992736b5229b 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \
 	imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \
 	imx25-karo-tx25.dtb \
 	imx25-pdk.dtb
-dtb-$(CONFIG_SOC_IMX31) += \
+dtb-$(CONFIG_SOC_IMX27) += \
 	imx27-apf27.dtb \
 	imx27-apf27dev.dtb \
 	imx27-eukrea-mbimxsd27-baseboard.dtb \
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index c3255e0c90aa..dbb3f4d2bf84 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -223,6 +223,25 @@
 /include/ "tps65217.dtsi"
 
 &tps {
+	/*
+	 * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only
+	 * mode") at poweroff.  Most BeagleBone versions do not support RTC-only
+	 * mode and risk hardware damage if this mode is entered.
+	 *
+	 * For details, see linux-omap mailing list May 2015 thread
+	 *	[PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller
+	 * In particular, messages:
+	 *	http://www.spinics.net/lists/linux-omap/msg118585.html
+	 *	http://www.spinics.net/lists/linux-omap/msg118615.html
+	 *
+	 * You can override this later with
+	 *	&tps {  /delete-property/ ti,pmic-shutdown-controller;  }
+	 * if you want to use RTC-only mode and made sure you are not affected
+	 * by the hardware problems. (Tip: double-check by performing a current
+	 * measurement after shutdown: it should be less than 1 mA.)
+	 */
+	ti,pmic-shutdown-controller;
+
 	regulators {
 		dcdc1_reg: regulator@0 {
 			regulator-name = "vdds_dpr";
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 5c42d259fa68..901739fcb85a 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,7 +80,3 @@
 		status = "okay";
 	};
 };
-
-&rtc {
-	system-power-controller;
-};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 87fc7a35e802..156d05efcb70 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -654,7 +654,7 @@
 	wlcore: wlcore@2 {
 		compatible = "ti,wl1271";
 		reg = <2>;
-		interrupt-parent = <&gpio1>;
+		interrupt-parent = <&gpio0>;
 		interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */
 		ref-clock-frequency = <38400000>;
 	};
diff --git a/arch/arm/boot/dts/am35xx-clocks.dtsi b/arch/arm/boot/dts/am35xx-clocks.dtsi
index 518b8fde88b0..18cc826e9db5 100644
--- a/arch/arm/boot/dts/am35xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am35xx-clocks.dtsi
@@ -12,7 +12,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&ipss_ick>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <1>;
 	};
 
@@ -20,7 +20,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
 		clocks = <&rmii_ck>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <9>;
 	};
 
@@ -28,7 +28,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&ipss_ick>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <2>;
 	};
 
@@ -36,7 +36,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
 		clocks = <&pclk_ck>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <10>;
 	};
 
@@ -44,7 +44,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&ipss_ick>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <0>;
 	};
 
@@ -52,7 +52,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
 		clocks = <&sys_ck>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <8>;
 	};
 
@@ -60,7 +60,7 @@
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&sys_ck>;
-		reg = <0x059c>;
+		reg = <0x032c>;
 		ti,bit-shift = <3>;
 	};
 };
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 8ae29c955c11..c17097d2c167 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -49,7 +49,7 @@
 		pinctrl-0 = <&matrix_keypad_pins>;
 
 		debounce-delay-ms = <5>;
-		col-scan-delay-us = <1500>;
+		col-scan-delay-us = <5>;
 
 		row-gpios = <&gpio5 5 GPIO_ACTIVE_HIGH		/* Bank5, pin5 */
 				&gpio5 6 GPIO_ACTIVE_HIGH>;	/* Bank5, pin6 */
@@ -473,7 +473,7 @@
 		interrupt-parent = <&gpio0>;
 		interrupts = <31 0>;
 
-		wake-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio1 28 GPIO_ACTIVE_LOW>;
 
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <272>;
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 15f198e4864d..a42cc377a862 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -18,6 +18,8 @@
 	aliases {
 		rtc0 = &mcp_rtc;
 		rtc1 = &tps659038_rtc;
+		rtc2 = &rtc;
+		display0 = &hdmi0;
 	};
 
 	memory {
@@ -83,7 +85,7 @@
 	gpio_fan: gpio_fan {
 		/* Based on 5v 500mA AFB02505HHB */
 		compatible = "gpio-fan";
-		gpios =  <&tps659038_gpio 1 GPIO_ACTIVE_HIGH>;
+		gpios =  <&tps659038_gpio 2 GPIO_ACTIVE_HIGH>;
 		gpio-fan,speed-map = <0     0>,
 				     <13000 1>;
 		#cooling-cells = <2>;
@@ -102,6 +104,51 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&extcon_usb2_pins>;
 	};
+
+	hdmi0: connector {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&tpd12s015_out>;
+			};
+		};
+	};
+
+	tpd12s015: encoder {
+		compatible = "ti,tpd12s015";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&tpd12s015_pins>;
+
+		gpios = <&gpio7 10 GPIO_ACTIVE_HIGH>,	/* gpio7_10, CT CP HPD */
+			<&gpio6 28 GPIO_ACTIVE_HIGH>,	/* gpio6_28, LS OE */
+			<&gpio7 12 GPIO_ACTIVE_HIGH>;	/* gpio7_12/sp1_cs2, HPD */
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				tpd12s015_in: endpoint {
+					remote-endpoint = <&hdmi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				tpd12s015_out: endpoint {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
 };
 
 &dra7_pmx_core {
@@ -121,6 +168,13 @@
 		>;
 	};
 
+	hdmi_pins: pinmux_hdmi_pins {
+		pinctrl-single,pins = <
+			0x408 (PIN_INPUT | MUX_MODE1)	/* i2c2_sda.hdmi1_ddc_scl */
+			0x40c (PIN_INPUT | MUX_MODE1)	/* i2c2_scl.hdmi1_ddc_sda */
+		>;
+	};
+
 	i2c3_pins_default: i2c3_pins_default {
 		pinctrl-single,pins = <
 			0x2a4 (PIN_INPUT| MUX_MODE10)	/* mcasp1_aclkx.i2c3_sda */
@@ -130,8 +184,8 @@
 
 	uart3_pins_default: uart3_pins_default {
 		pinctrl-single,pins = <
-			0x248 (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_rxd.rxd */
-			0x24c (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_txd.txd */
+			0x3f8 (PIN_INPUT_SLEW | MUX_MODE2) /* uart2_ctsn.uart3_rxd */
+			0x3fc (PIN_INPUT_SLEW | MUX_MODE1) /* uart2_rtsn.uart3_txd */
 		>;
 	};
 
@@ -277,6 +331,14 @@
 			0x3e8 (PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_ctsn.gpio7_24 */
 		>;
 	};
+
+	tpd12s015_pins: pinmux_tpd12s015_pins {
+		pinctrl-single,pins = <
+			0x3b0 (PIN_OUTPUT | MUX_MODE14)		/* gpio7_10 CT_CP_HPD */
+			0x3b8 (PIN_INPUT_PULLDOWN | MUX_MODE14)	/* gpio7_12 HPD */
+			0x370 (PIN_OUTPUT | MUX_MODE14)		/* gpio6_28 LS_OE */
+		>;
+	};
 };
 
 &i2c1 {
@@ -455,7 +517,7 @@
 	mcp_rtc: rtc@6f {
 		compatible = "microchip,mcp7941x";
 		reg = <0x6f>;
-		interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_LOW>;  /* IRQ_SYS_1N */
+		interrupts = <GIC_SPI 2 IRQ_TYPE_EDGE_RISING>;  /* IRQ_SYS_1N */
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&mcp79410_pins_default>;
@@ -478,7 +540,7 @@
 &uart3 {
 	status = "okay";
 	interrupts-extended = <&crossbar_mpu GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>,
-			      <&dra7_pmx_core 0x248>;
+			      <&dra7_pmx_core 0x3f8>;
 
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart3_pins_default>;
@@ -607,3 +669,23 @@
 		};
        };
 };
+
+&dss {
+	status = "ok";
+
+	vdda_video-supply = <&ldoln_reg>;
+};
+
+&hdmi {
+	status = "ok";
+	vdda-supply = <&ldo3_reg>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmi_pins>;
+
+	port {
+		hdmi_out: endpoint {
+			remote-endpoint = <&tpd12s015_in>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi
index c675257f2377..f076ff856d8b 100644
--- a/arch/arm/boot/dts/armada-375.dtsi
+++ b/arch/arm/boot/dts/armada-375.dtsi
@@ -69,7 +69,7 @@
 		mainpll: mainpll {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <2000000000>;
+			clock-frequency = <1000000000>;
 		};
 		/* 25 MHz reference crystal */
 		refclk: oscillator {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index ed2dd8ba4080..218a2acd36e5 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -585,7 +585,7 @@
 		mainpll: mainpll {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <2000000000>;
+			clock-frequency = <1000000000>;
 		};
 
 		/* 25 MHz reference crystal */
diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi
index 0e85fc15ceda..ecd1318109ba 100644
--- a/arch/arm/boot/dts/armada-39x.dtsi
+++ b/arch/arm/boot/dts/armada-39x.dtsi
@@ -502,7 +502,7 @@
 		mainpll: mainpll {
 			compatible = "fixed-clock";
 			#clock-cells = <0>;
-			clock-frequency = <2000000000>;
+			clock-frequency = <1000000000>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
index a2cf2154dcdb..fdd187c55aa5 100644
--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
@@ -95,6 +95,11 @@
 
 		internal-regs {
 
+			rtc@10300 {
+				/* No crystal connected to the internal RTC */
+				status = "disabled";
+			};
+
 			/* J10: VCC, NC, RX, NC, TX, GND  */
 			serial@12000 {
 				status = "okay";
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index e3b08fb959e5..990e8a2100f0 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -105,6 +105,10 @@
 		};
 
 		internal-regs {
+			rtc@10300 {
+				/* No crystal connected to the internal RTC */
+				status = "disabled";
+			};
 			serial@12000 {
 				status = "okay";
 			};
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index de8427be830a..289806adb343 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -382,7 +382,7 @@
 			ti,hwmods = "usb_otg_hs";
 
 			usb0: usb@47401000 {
-				compatible = "ti,musb-am33xx";
+				compatible = "ti,musb-dm816";
 				reg = <0x47401400 0x400
 				       0x47401000 0x200>;
 				reg-names = "mc", "control";
@@ -422,7 +422,7 @@
 			};
 
 			usb1: usb@47401800 {
-				compatible = "ti,musb-am33xx";
+				compatible = "ti,musb-dm816";
 				reg = <0x47401c00 0x400
 				       0x47401800 0x200>;
 				reg-names = "mc", "control";
diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts
index aae7efc09b0b..e6fa251e17b9 100644
--- a/arch/arm/boot/dts/dove-cubox.dts
+++ b/arch/arm/boot/dts/dove-cubox.dts
@@ -87,6 +87,7 @@
 
 		/* connect xtal input to 25MHz reference */
 		clocks = <&ref25>;
+		clock-names = "xtal";
 
 		/* connect xtal input as source of pll0 and pll1 */
 		silabs,pll-source = <0 0>, <1 0>;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 5332b57b4950..8f1e25bcecbd 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -131,6 +131,11 @@
 							regulator-max-microvolt = <3000000>;
 						};
 					};
+
+					scm_conf_clocks: clocks {
+						#address-cells = <1>;
+						#size-cells = <0>;
+					};
 				};
 
 				dra7_pmx_core: pinmux@1400 {
@@ -911,7 +916,7 @@
 			ti,clock-cycles = <16>;
 
 			reg = <0x4ae07ddc 0x4>, <0x4ae07de0 0x4>,
-			      <0x4ae06014 0x4>, <0x4a003b20 0x8>,
+			      <0x4ae06014 0x4>, <0x4a003b20 0xc>,
 			      <0x4ae0c158 0x4>;
 			reg-names = "setup-address", "control-address",
 				    "int-address", "efuse-address",
@@ -944,7 +949,7 @@
 			ti,clock-cycles = <16>;
 
 			reg = <0x4ae07e34 0x4>, <0x4ae07e24 0x4>,
-			      <0x4ae06010 0x4>, <0x4a0025cc 0x8>,
+			      <0x4ae06010 0x4>, <0x4a0025cc 0xc>,
 			      <0x4a002470 0x4>;
 			reg-names = "setup-address", "control-address",
 				    "int-address", "efuse-address",
@@ -977,7 +982,7 @@
 			ti,clock-cycles = <16>;
 
 			reg = <0x4ae07e30 0x4>, <0x4ae07e20 0x4>,
-			      <0x4ae06010 0x4>, <0x4a0025e0 0x8>,
+			      <0x4ae06010 0x4>, <0x4a0025e0 0xc>,
 			      <0x4a00246c 0x4>;
 			reg-names = "setup-address", "control-address",
 				    "int-address", "efuse-address",
@@ -1010,7 +1015,7 @@
 			ti,clock-cycles = <16>;
 
 			reg = <0x4ae07de4 0x4>, <0x4ae07de8 0x4>,
-			      <0x4ae06010 0x4>, <0x4a003b08 0x8>,
+			      <0x4ae06010 0x4>, <0x4a003b08 0xc>,
 			      <0x4ae0c154 0x4>;
 			reg-names = "setup-address", "control-address",
 				    "int-address", "efuse-address",
@@ -1203,7 +1208,7 @@
 			status = "disabled";
 		};
 
-		rtc@48838000 {
+		rtc: rtc@48838000 {
 			compatible = "ti,am3352-rtc";
 			reg = <0x48838000 0x100>;
 			interrupts = <GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>,
@@ -1469,6 +1474,44 @@
 			clocks = <&sys_clkin1>;
 			status = "disabled";
 		};
+
+		dss: dss@58000000 {
+			compatible = "ti,dra7-dss";
+			/* 'reg' defined in dra72x.dtsi and dra74x.dtsi */
+			/* 'clocks' defined in dra72x.dtsi and dra74x.dtsi */
+			status = "disabled";
+			ti,hwmods = "dss_core";
+			/* CTRL_CORE_DSS_PLL_CONTROL */
+			syscon-pll-ctrl = <&scm_conf 0x538>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			dispc@58001000 {
+				compatible = "ti,dra7-dispc";
+				reg = <0x58001000 0x1000>;
+				interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
+				ti,hwmods = "dss_dispc";
+				clocks = <&dss_dss_clk>;
+				clock-names = "fck";
+				/* CTRL_CORE_SMA_SW_1 */
+				syscon-pol = <&scm_conf 0x534>;
+			};
+
+			hdmi: encoder@58060000 {
+				compatible = "ti,dra7-hdmi";
+				reg = <0x58040000 0x200>,
+				      <0x58040200 0x80>,
+				      <0x58040300 0x80>,
+				      <0x58060000 0x19000>;
+				reg-names = "wp", "pll", "phy", "core";
+				interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+				ti,hwmods = "dss_hdmi";
+				clocks = <&dss_48mhz_clk>, <&dss_hdmi_clk>;
+				clock-names = "fck", "sys_clk";
+			};
+		};
 	};
 
 	thermal_zones: thermal-zones {
diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts
index ce0390f081d9..4e1b60581782 100644
--- a/arch/arm/boot/dts/dra72-evm.dts
+++ b/arch/arm/boot/dts/dra72-evm.dts
@@ -19,6 +19,10 @@
 		reg = <0x80000000 0x40000000>; /* 1024 MB */
 	};
 
+	aliases {
+		display0 = &hdmi0;
+	};
+
 	evm_3v3: fixedregulator-evm_3v3 {
 		compatible = "regulator-fixed";
 		regulator-name = "evm_3v3";
@@ -35,6 +39,51 @@
 		compatible = "linux,extcon-usb-gpio";
 		id-gpio = <&pcf_gpio_21 2 GPIO_ACTIVE_HIGH>;
 	};
+
+	hdmi0: connector {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+
+		type = "a";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&tpd12s015_out>;
+			};
+		};
+	};
+
+	tpd12s015: encoder {
+		compatible = "ti,tpd12s015";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&tpd12s015_pins>;
+
+		gpios = <&pcf_hdmi 4 GPIO_ACTIVE_HIGH>,	/* P4, CT CP HPD */
+			<&pcf_hdmi 5 GPIO_ACTIVE_HIGH>,	/* P5, LS OE */
+			<&gpio7 12 GPIO_ACTIVE_HIGH>;	/* gpio7_12/sp1_cs2, HPD */
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				tpd12s015_in: endpoint {
+					remote-endpoint = <&hdmi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				tpd12s015_out: endpoint {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
 };
 
 &dra7_pmx_core {
@@ -45,6 +94,13 @@
 		>;
 	};
 
+	i2c5_pins: pinmux_i2c5_pins {
+		pinctrl-single,pins = <
+			0x2b4 (PIN_INPUT | MUX_MODE10) /* mcasp1_axr0.i2c5_sda */
+			0x2b8 (PIN_INPUT | MUX_MODE10) /* mcasp1_axr1.i2c5_scl */
+		>;
+	};
+
 	nand_default: nand_default {
 		pinctrl-single,pins = <
 			0x0	(PIN_INPUT  | MUX_MODE0) /* gpmc_ad0 */
@@ -142,6 +198,19 @@
 			0xb8 (PIN_OUTPUT | MUX_MODE1)	/* gpmc_cs2.qspi1_cs0 */
 		>;
 	};
+
+	hdmi_pins: pinmux_hdmi_pins {
+		pinctrl-single,pins = <
+			0x408 (PIN_INPUT | MUX_MODE1) /* i2c2_sda.hdmi1_ddc_scl */
+			0x40c (PIN_INPUT | MUX_MODE1) /* i2c2_scl.hdmi1_ddc_sda */
+		>;
+	};
+
+	tpd12s015_pins: pinmux_tpd12s015_pins {
+		pinctrl-single,pins = <
+			0x3b8 (PIN_INPUT_PULLDOWN | MUX_MODE14) /* gpio7_12 HPD */
+		>;
+	};
 };
 
 &i2c1 {
@@ -277,6 +346,27 @@
 	};
 };
 
+&i2c5 {
+	status = "okay";
+	pinctrl-names = "default";
+	pinctrl-0 = <&i2c5_pins>;
+	clock-frequency = <400000>;
+
+	pcf_hdmi: pcf8575@26 {
+		compatible = "nxp,pcf8575";
+		reg = <0x26>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		/*
+		 * initial state is used here to keep the mdio interface
+		 * selected on RU89 through SEL_VIN4_MUX_S0, VIN2_S1 and
+		 * VIN2_S0 driven high otherwise Ethernet stops working
+		 * VIN6_SEL_S0 is low, thus selecting McASP3 over VIN6
+		 */
+		lines-initial-states = <0x0f2b>;
+	};
+};
+
 &uart1 {
 	status = "okay";
 };
@@ -566,3 +656,23 @@
 		};
 	};
 };
+
+&dss {
+	status = "ok";
+
+	vdda_video-supply = <&ldo5_reg>;
+};
+
+&hdmi {
+	status = "ok";
+	vdda-supply = <&ldo3_reg>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&hdmi_pins>;
+
+	port {
+		hdmi_out: endpoint {
+			remote-endpoint = <&tpd12s015_in>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/dra72x.dtsi b/arch/arm/boot/dts/dra72x.dtsi
index 03d742f8d572..eaca143faa77 100644
--- a/arch/arm/boot/dts/dra72x.dtsi
+++ b/arch/arm/boot/dts/dra72x.dtsi
@@ -34,3 +34,14 @@
 		interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
 	};
 };
+
+&dss {
+	reg = <0x58000000 0x80>,
+	      <0x58004054 0x4>,
+	      <0x58004300 0x20>;
+	reg-names = "dss", "pll1_clkctrl", "pll1";
+
+	clocks = <&dss_dss_clk>,
+		 <&dss_video1_clk>;
+	clock-names = "fck", "video1_clk";
+};
diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi
index cc560a70926f..fa995d0ca1f2 100644
--- a/arch/arm/boot/dts/dra74x.dtsi
+++ b/arch/arm/boot/dts/dra74x.dtsi
@@ -73,3 +73,18 @@
 		};
 	};
 };
+
+&dss {
+	reg = <0x58000000 0x80>,
+	      <0x58004054 0x4>,
+	      <0x58004300 0x20>,
+	      <0x58005054 0x4>,
+	      <0x58005300 0x20>;
+	reg-names = "dss", "pll1_clkctrl", "pll1",
+		    "pll2_clkctrl", "pll2";
+
+	clocks = <&dss_dss_clk>,
+		 <&dss_video1_clk>,
+		 <&dss_video2_clk>;
+	clock-names = "fck", "video1_clk", "video2_clk";
+};
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 3b933f74d000..357bedeebfac 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -1531,6 +1531,7 @@
 		clocks = <&dpll_per_h12x2_ck>;
 		ti,bit-shift = <8>;
 		reg = <0x1120>;
+		ti,set-rate-parent;
 	};
 
 	dss_hdmi_clk: dss_hdmi_clk {
@@ -2136,3 +2137,13 @@
 		clocks = <&dpll_usb_ck>;
 	};
 };
+
+&scm_conf_clocks {
+	dss_deshdcp_clk: dss_deshdcp_clk {
+		#clock-cells = <0>;
+		compatible = "ti,gate-clock";
+		clocks = <&l3_iclk_div>;
+		ti,bit-shift = <0>;
+		reg = <0x558>;
+	};
+};
diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
index 8de12af7c276..d6b49e5b32e9 100644
--- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
+++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi
@@ -9,6 +9,7 @@
 
 #include <dt-bindings/sound/samsung-i2s.h>
 #include <dt-bindings/input/input.h>
+#include <dt-bindings/clock/maxim,max77686.h>
 #include "exynos4412.dtsi"
 
 / {
@@ -105,6 +106,8 @@
 
 	rtc@10070000 {
 		status = "okay";
+		clocks = <&clock CLK_RTC>, <&max77686 MAX77686_CLK_AP>;
+		clock-names = "rtc", "rtc_src";
 	};
 
 	g2d@10800000 {
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 173ffa479ad3..792394dd0f2a 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -736,7 +736,7 @@
 
 			display-timings {
 				timing-0 {
-					clock-frequency = <0>;
+					clock-frequency = <57153600>;
 					hactive = <720>;
 					vactive = <1280>;
 					hfront-porch = <5>;
diff --git a/arch/arm/boot/dts/exynos5250-snow.dts b/arch/arm/boot/dts/exynos5250-snow.dts
index 2657e842e5a5..1eca97ee4bd6 100644
--- a/arch/arm/boot/dts/exynos5250-snow.dts
+++ b/arch/arm/boot/dts/exynos5250-snow.dts
@@ -567,6 +567,7 @@
 	num-slots = <1>;
 	broken-cd;
 	cap-sdio-irq;
+	keep-power-in-suspend;
 	card-detect-delay = <200>;
 	samsung,dw-mshc-ciu-div = <3>;
 	samsung,dw-mshc-sdr-timing = <2 3>;
diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts
index 0788d08fb43e..146e71118a72 100644
--- a/arch/arm/boot/dts/exynos5420-peach-pit.dts
+++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts
@@ -711,6 +711,7 @@
 	num-slots = <1>;
 	broken-cd;
 	cap-sdio-irq;
+	keep-power-in-suspend;
 	card-detect-delay = <200>;
 	clock-frequency = <400000000>;
 	samsung,dw-mshc-ciu-div = <1>;
diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
index 5d31fc140823..2180a0152c9b 100644
--- a/arch/arm/boot/dts/exynos5420-trip-points.dtsi
+++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi
@@ -28,7 +28,7 @@ trips {
 		type = "active";
 	};
 	cpu-crit-0 {
-		temperature = <1200000>; /* millicelsius */
+		temperature = <120000>; /* millicelsius */
 		hysteresis = <0>; /* millicelsius */
 		type = "critical";
 	};
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index f67b23f303c3..45317538bbae 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -536,6 +536,7 @@
 		clock-names = "dp";
 		phys = <&dp_phy>;
 		phy-names = "dp";
+		power-domains = <&disp_pd>;
 	};
 
 	mipi_phy: video-phy@10040714 {
diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
index 48adfa8f4300..356e963edf11 100644
--- a/arch/arm/boot/dts/exynos5440-trip-points.dtsi
+++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi
@@ -18,7 +18,7 @@ trips {
 		type = "active";
 	};
 	cpu-crit-0 {
-		temperature = <1050000>; /* millicelsius */
+		temperature = <105000>; /* millicelsius */
 		hysteresis = <0>; /* millicelsius */
 		type = "critical";
 	};
diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts
index 412f41d62686..02eb8b15374f 100644
--- a/arch/arm/boot/dts/exynos5800-peach-pi.dts
+++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts
@@ -674,6 +674,7 @@
 	num-slots = <1>;
 	broken-cd;
 	cap-sdio-irq;
+	keep-power-in-suspend;
 	card-detect-delay = <200>;
 	clock-frequency = <400000000>;
 	samsung,dw-mshc-ciu-div = <1>;
diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts
index 7e6eef2488e8..82045398bf1f 100644
--- a/arch/arm/boot/dts/imx23-olinuxino.dts
+++ b/arch/arm/boot/dts/imx23-olinuxino.dts
@@ -12,6 +12,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx23.dtsi"
 
 / {
@@ -93,6 +94,7 @@
 
 	ahb@80080000 {
 		usb0: usb@80080000 {
+			dr_mode = "host";
 			vbus-supply = <&reg_usb0_vbus>;
 			status = "okay";
 		};
@@ -122,7 +124,7 @@
 
 		user {
 			label = "green";
-			gpios = <&gpio2 1 1>;
+			gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index e4d3aecc4ed2..677f81d9dcd5 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -428,6 +428,7 @@
 
 			pwm4: pwm@53fc8000 {
 				compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
+				#pwm-cells = <2>;
 				reg = <0x53fc8000 0x4000>;
 				clocks = <&clks 108>, <&clks 52>;
 				clock-names = "ipg", "per";
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 6951b66d1ab7..bc215e4b75fd 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -533,7 +533,7 @@
 
 			fec: ethernet@1002b000 {
 				compatible = "fsl,imx27-fec";
-				reg = <0x1002b000 0x4000>;
+				reg = <0x1002b000 0x1000>;
 				interrupts = <50>;
 				clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
 					 <&clks IMX27_CLK_FEC_AHB_GATE>;
diff --git a/arch/arm/boot/dts/imx28-cfa10036.dts b/arch/arm/boot/dts/imx28-cfa10036.dts
index b04b6b8850a7..570aa339a05e 100644
--- a/arch/arm/boot/dts/imx28-cfa10036.dts
+++ b/arch/arm/boot/dts/imx28-cfa10036.dts
@@ -99,6 +99,9 @@
 					solomon,height = <32>;
 					solomon,width = <128>;
 					solomon,page-offset = <0>;
+					solomon,com-lrremap;
+					solomon,com-invdir;
+					solomon,com-offset = <32>;
 				};
 			};
 
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 25e25f82fbae..4e073e854742 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -913,7 +913,7 @@
 					      80 81 68 69
 					      70 71 72 73
 					      74 75 76 77>;
-				interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty",
+				interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty",
 						  "saif0", "saif1", "i2c0", "i2c1",
 						  "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx",
 						  "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx";
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 19cc269a08d4..1ce6133b67f5 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -31,6 +31,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio4 15 0>;
+			enable-active-high;
 		};
 
 		reg_usb_h1_vbus: regulator@1 {
@@ -40,6 +41,7 @@
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
 			gpio = <&gpio1 0 0>;
+			enable-active-high;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 46b2fed7c319..3b24b12651b2 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -185,7 +185,6 @@
 &i2c3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_i2c3>;
-	pinctrl-assert-gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 
 	max7310_a: gpio@30 {
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index 134d3f27a8ec..921de6605f07 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -110,6 +110,8 @@
 	nand@0,0 {
 		reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
 		nand-bus-width = <16>;
+		gpmc,device-width = <2>;
+		ti,nand-ecc-opt = "sw";
 
 		gpmc,sync-clk-ps = <0>;
 		gpmc,cs-on-ns = <0>;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index a29315833ecd..5f5e0f3d5b64 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -498,6 +498,8 @@
 		DRVDD-supply = <&vmmc2>;
 		IOVDD-supply = <&vio>;
 		DVDD-supply = <&vio>;
+
+		ai3x-micbias-vg = <1>;
 	};
 
 	tlv320aic3x_aux: tlv320aic3x@19 {
@@ -509,6 +511,8 @@
 		DRVDD-supply = <&vmmc2>;
 		IOVDD-supply = <&vio>;
 		DVDD-supply = <&vio>;
+
+		ai3x-micbias-vg = <2>;
 	};
 
 	tsl2563: tsl2563@29 {
@@ -828,8 +832,8 @@
 		touchscreen-fuzz-x = <4>;
 		touchscreen-fuzz-y = <7>;
 		touchscreen-fuzz-pressure = <2>;
-		touchscreen-max-x = <4096>;
-		touchscreen-max-y = <4096>;
+		touchscreen-size-x = <4096>;
+		touchscreen-size-y = <4096>;
 		touchscreen-max-pressure = <2048>;
 
 		ti,x-plate-ohms = <280>;
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index d18a90f5eca3..69a40cfc1f29 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -456,6 +456,7 @@
 		};
 
 		mmu_isp: mmu@480bd400 {
+			#iommu-cells = <0>;
 			compatible = "ti,omap2-iommu";
 			reg = <0x480bd400 0x80>;
 			interrupts = <24>;
@@ -464,6 +465,7 @@
 		};
 
 		mmu_iva: mmu@5d000000 {
+			#iommu-cells = <0>;
 			compatible = "ti,omap2-iommu";
 			reg = <0x5d000000 0x80>;
 			interrupts = <28>;
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index efe5f737f39b..7d24ae0306b5 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -128,7 +128,7 @@
 	 * hierarchy.
 	 */
 	ocp {
-		compatible = "ti,omap4-l3-noc", "simple-bus";
+		compatible = "ti,omap5-l3-noc", "simple-bus";
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ranges;
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index 74c3212f1f11..824ddab9c3ad 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -545,7 +545,7 @@
 		compatible = "adi,adv7511w";
 		reg = <0x39>;
 		interrupt-parent = <&gpio3>;
-		interrupts = <29 IRQ_TYPE_EDGE_FALLING>;
+		interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
 
 		adi,input-depth = <8>;
 		adi,input-colorspace = "rgb";
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 8a05c47fd57f..4be75960a603 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -253,6 +253,17 @@
 			status = "disabled";
 		};
 
+		sdr: sdr@ffc25000 {
+			compatible = "syscon";
+			reg = <0xffcfb100 0x80>;
+		};
+
+		sdramedac {
+			compatible = "altr,sdram-edac-a10";
+			altr,sdr-syscon = <&sdr>;
+			interrupts = <0 2 4>, <0 0 4>;
+		};
+
 		L2: l2-cache@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index bfd3f1c734b8..2201cd5da3bb 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -1017,23 +1017,6 @@
 			status = "disabled";
 		};
 
-		vmmci: regulator-gpio {
-			compatible = "regulator-gpio";
-
-			regulator-min-microvolt = <1800000>;
-			regulator-max-microvolt = <2900000>;
-			regulator-name = "mmci-reg";
-			regulator-type = "voltage";
-
-			startup-delay-us = <100>;
-			enable-active-high;
-
-			states = <1800000 0x1
-				  2900000 0x0>;
-
-			status = "disabled";
-		};
-
 		mcde@a0350000 {
 			compatible = "stericsson,mcde";
 			reg = <0xa0350000 0x1000>, /* MCDE */
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index bf8f0eddc2c0..744c1e3a744d 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -111,6 +111,21 @@
 			pinctrl-1 = <&i2c3_sleep_mode>;
 		};
 
+		vmmci: regulator-gpio {
+			compatible = "regulator-gpio";
+
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2900000>;
+			regulator-name = "mmci-reg";
+			regulator-type = "voltage";
+
+			startup-delay-us = <100>;
+			enable-active-high;
+
+			states = <1800000 0x1
+				  2900000 0x0>;
+		};
+
 		// External Micro SD slot
 		sdi0_per1@80126000 {
 			arm,primecell-periphid = <0x10480180>;
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 206826a855c0..1bc84ebdccaa 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -146,8 +146,21 @@
 		};
 
 		vmmci: regulator-gpio {
+			compatible = "regulator-gpio";
+
 			gpios = <&gpio7 4 0x4>;
 			enable-gpio = <&gpio6 25 0x4>;
+
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <2900000>;
+			regulator-name = "mmci-reg";
+			regulator-type = "voltage";
+
+			startup-delay-us = <100>;
+			enable-active-high;
+
+			states = <1800000 0x1
+				  2900000 0x0>;
 		};
 
 		// External Micro SD slot
diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi
index cf01c818b8ea..13cc7ca5e031 100644
--- a/arch/arm/boot/dts/tegra124.dtsi
+++ b/arch/arm/boot/dts/tegra124.dtsi
@@ -826,7 +826,7 @@
 			 <&tegra_car TEGRA124_CLK_PLL_U>,
 			 <&tegra_car TEGRA124_CLK_USBD>;
 		clock-names = "reg", "pll_u", "utmi-pads";
-		resets = <&tegra_car 59>, <&tegra_car 22>;
+		resets = <&tegra_car 22>, <&tegra_car 22>;
 		reset-names = "usb", "utmi-pads";
 		nvidia,hssync-start-delay = <0>;
 		nvidia,idle-wait-delay = <17>;
@@ -838,6 +838,7 @@
 		nvidia,hssquelch-level = <2>;
 		nvidia,hsdiscon-level = <5>;
 		nvidia,xcvr-hsslew = <12>;
+		nvidia,has-utmi-pad-registers;
 		status = "disabled";
 	};
 
@@ -862,7 +863,7 @@
 			 <&tegra_car TEGRA124_CLK_PLL_U>,
 			 <&tegra_car TEGRA124_CLK_USBD>;
 		clock-names = "reg", "pll_u", "utmi-pads";
-		resets = <&tegra_car 22>, <&tegra_car 22>;
+		resets = <&tegra_car 58>, <&tegra_car 22>;
 		reset-names = "usb", "utmi-pads";
 		nvidia,hssync-start-delay = <0>;
 		nvidia,idle-wait-delay = <17>;
@@ -874,7 +875,6 @@
 		nvidia,hssquelch-level = <2>;
 		nvidia,hsdiscon-level = <5>;
 		nvidia,xcvr-hsslew = <12>;
-		nvidia,has-utmi-pad-registers;
 		status = "disabled";
 	};
 
@@ -899,7 +899,7 @@
 			 <&tegra_car TEGRA124_CLK_PLL_U>,
 			 <&tegra_car TEGRA124_CLK_USBD>;
 		clock-names = "reg", "pll_u", "utmi-pads";
-		resets = <&tegra_car 58>, <&tegra_car 22>;
+		resets = <&tegra_car 59>, <&tegra_car 22>;
 		reset-names = "usb", "utmi-pads";
 		nvidia,hssync-start-delay = <0>;
 		nvidia,idle-wait-delay = <17>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 7a2aeacd62c0..107395c32d82 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -191,6 +191,7 @@
 		compatible = "arm,cortex-a15-pmu";
 		interrupts = <0 68 4>,
 			     <0 69 4>;
+		interrupt-affinity = <&cpu0>, <&cpu1>;
 	};
 
 	oscclk6a: oscclk6a {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 23662b5a5e9d..d949facba376 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -33,28 +33,28 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu@0 {
+		A9_0: cpu@0 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0>;
 			next-level-cache = <&L2>;
 		};
 
-		cpu@1 {
+		A9_1: cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <1>;
 			next-level-cache = <&L2>;
 		};
 
-		cpu@2 {
+		A9_2: cpu@2 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <2>;
 			next-level-cache = <&L2>;
 		};
 
-		cpu@3 {
+		A9_3: cpu@3 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <3>;
@@ -170,6 +170,7 @@
 		compatible = "arm,pl310-cache";
 		reg = <0x1e00a000 0x1000>;
 		interrupts = <0 43 4>;
+		cache-unified;
 		cache-level = <2>;
 		arm,data-latency = <1 1 1>;
 		arm,tag-latency = <1 1 1>;
@@ -181,6 +182,8 @@
 			     <0 61 4>,
 			     <0 62 4>,
 			     <0 63 4>;
+		interrupt-affinity = <&A9_0>, <&A9_1>, <&A9_2>, <&A9_3>;
+
 	};
 
 	dcc {
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index a5cd2eda3edf..9ea54b3dba09 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -193,7 +193,7 @@
 		};
 
 		gem0: ethernet@e000b000 {
-			compatible = "cdns,gem";
+			compatible = "cdns,zynq-gem";
 			reg = <0xe000b000 0x1000>;
 			status = "disabled";
 			interrupts = <0 22 4>;
@@ -204,7 +204,7 @@
 		};
 
 		gem1: ethernet@e000c000 {
-			compatible = "cdns,gem";
+			compatible = "cdns,zynq-gem";
 			reg = <0xe000c000 0x1000>;
 			status = "disabled";
 			interrupts = <0 45 4>;
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 5cc779c8e9c6..93ee70dbbdd3 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -501,8 +501,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base)
 	 * Register SA1111 interrupt
 	 */
 	irq_set_irq_type(sachip->irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(sachip->irq, sachip);
-	irq_set_chained_handler(sachip->irq, sa1111_irq_handler);
+	irq_set_chained_handler_and_data(sachip->irq, sa1111_irq_handler,
+					 sachip);
 
 	dev_info(sachip->dev, "Providing IRQ%u-%u\n",
 		sachip->irq_base, sachip->irq_base + SA1111_IRQ_NR - 1);
@@ -836,8 +836,7 @@ static void __sa1111_remove(struct sa1111 *sachip)
 	clk_unprepare(sachip->clk);
 
 	if (sachip->irq != NO_IRQ) {
-		irq_set_chained_handler(sachip->irq, NULL);
-		irq_set_handler_data(sachip->irq, NULL);
+		irq_set_chained_handler_and_data(sachip->irq, NULL, NULL);
 		irq_free_descs(sachip->irq_base, SA1111_IRQ_NR);
 
 		release_mem_region(sachip->phys + SA1111_INTC, 512);
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index ab86655c1f4b..fbbb1915c6a9 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -39,11 +39,14 @@ CONFIG_ARCH_HIP04=y
 CONFIG_ARCH_KEYSTONE=y
 CONFIG_ARCH_MESON=y
 CONFIG_ARCH_MXC=y
+CONFIG_SOC_IMX50=y
 CONFIG_SOC_IMX51=y
 CONFIG_SOC_IMX53=y
 CONFIG_SOC_IMX6Q=y
 CONFIG_SOC_IMX6SL=y
+CONFIG_SOC_IMX6SX=y
 CONFIG_SOC_VF610=y
+CONFIG_SOC_LS1021A=y
 CONFIG_ARCH_OMAP3=y
 CONFIG_ARCH_OMAP4=y
 CONFIG_SOC_OMAP5=y
@@ -426,7 +429,7 @@ CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_STI=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_STI=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 9ff7b54b2a83..3743ca221d40 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -393,7 +393,7 @@ CONFIG_TI_EDMA=y
 CONFIG_DMA_OMAP=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXTCON=m
-CONFIG_EXTCON_GPIO=m
+CONFIG_EXTCON_USB_GPIO=m
 CONFIG_EXTCON_PALMAS=m
 CONFIG_TI_EMIF=m
 CONFIG_PWM=y
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 8da2207b0072..27ed1b1cd1d7 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -53,20 +53,13 @@ config CRYPTO_SHA256_ARM
 	  SHA-256 secure hash standard (DFIPS 180-2) implemented
 	  using optimized ARM assembler and NEON, when available.
 
-config CRYPTO_SHA512_ARM_NEON
-	tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_SHA512
+config CRYPTO_SHA512_ARM
+	tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
 	select CRYPTO_HASH
+	depends on !CPU_V7M
 	help
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
-	  using ARM NEON instructions, when available.
-
-	  This version of SHA implements a 512 bit hash with 256 bits of
-	  security against collision attacks.
-
-	  This code also includes SHA-384, a 384 bit hash with 192 bits
-	  of security against collision attacks.
+	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_AES_ARM
 	tristate "AES cipher algorithms (ARM-asm)"
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 6ea828241fcb..fc5150702b64 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -30,7 +30,8 @@ sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
 sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
-sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
+sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
+sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
@@ -45,4 +46,7 @@ $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
 $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 	$(call cmd,perl)
 
-.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
+$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
+	$(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index 8cfa468ee570..987aa632c9f0 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -101,15 +101,14 @@
 	\dround		q10, q11
 	blo		0f			@ AES-128: 10 rounds
 	vld1.8		{q10-q11}, [ip]!
-	beq		1f			@ AES-192: 12 rounds
 	\dround		q12, q13
+	beq		1f			@ AES-192: 12 rounds
 	vld1.8		{q12-q13}, [ip]
 	\dround		q10, q11
 0:	\fround		q12, q13, q14
 	bx		lr
 
-1:	\dround		q12, q13
-	\fround		q10, q11, q14
+1:	\fround		q10, q11, q14
 	bx		lr
 	.endm
 
@@ -122,8 +121,8 @@
 	 *   q2        : third in/output block (_3x version only)
 	 *   q8        : first round key
 	 *   q9        : secound round key
-	 *   ip        : address of 3rd round key
 	 *   q14       : final round key
+	 *   r2        : address of round key array
 	 *   r3        : number of rounds
 	 */
 	.align		6
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
new file mode 100644
index 000000000000..a2b11a844357
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -0,0 +1,649 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA512 block procedure for ARMv4. September 2007.
+
+# This code is ~4.5 (four and a half) times faster than code generated
+# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+# Xscale PXA250 core].
+#
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 6% improvement on
+# Cortex A8 core and ~40 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 7%
+# improvement on Coxtex A8 core and ~38 cycles per byte.
+
+# March 2011.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process
+# one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+# August 2012.
+#
+# Improve NEON performance by 12% on Snapdragon S4. In absolute
+# terms it's 22.6 cycles per byte, which is disappointing result.
+# Technical writers asserted that 3-way S4 pipeline can sustain
+# multiple NEON instructions per cycle, but dual NEON issue could
+# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# for further details. On side note Cortex-A15 processes one byte in
+# 16 cycles.
+
+# Byte order [in]dependence. =========================================
+#
+# Originally caller was expected to maintain specific *dword* order in
+# h[0-7], namely with most significant dword at *lower* address, which
+# was reflected in below two parameters as 0 and 4. Now caller is
+# expected to maintain native byte order for whole 64-bit values.
+$hi="HI";
+$lo="LO";
+# ====================================================================
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0";	# parameter block
+$inp="r1";
+$len="r2";
+
+$Tlo="r3";
+$Thi="r4";
+$Alo="r5";
+$Ahi="r6";
+$Elo="r7";
+$Ehi="r8";
+$t0="r9";
+$t1="r10";
+$t2="r11";
+$t3="r12";
+############	r13 is stack pointer
+$Ktbl="r14";
+############	r15 is program counter
+
+$Aoff=8*0;
+$Boff=8*1;
+$Coff=8*2;
+$Doff=8*3;
+$Eoff=8*4;
+$Foff=8*5;
+$Goff=8*6;
+$Hoff=8*7;
+$Xoff=8*8;
+
+sub BODY_00_15() {
+my $magic = shift;
+$code.=<<___;
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	$t0,$Elo,lsr#14
+	str	$Tlo,[sp,#$Xoff+0]
+	mov	$t1,$Ehi,lsr#14
+	str	$Thi,[sp,#$Xoff+4]
+	eor	$t0,$t0,$Ehi,lsl#18
+	ldr	$t2,[sp,#$Hoff+0]	@ h.lo
+	eor	$t1,$t1,$Elo,lsl#18
+	ldr	$t3,[sp,#$Hoff+4]	@ h.hi
+	eor	$t0,$t0,$Elo,lsr#18
+	eor	$t1,$t1,$Ehi,lsr#18
+	eor	$t0,$t0,$Ehi,lsl#14
+	eor	$t1,$t1,$Elo,lsl#14
+	eor	$t0,$t0,$Ehi,lsr#9
+	eor	$t1,$t1,$Elo,lsr#9
+	eor	$t0,$t0,$Elo,lsl#23
+	eor	$t1,$t1,$Ehi,lsl#23	@ Sigma1(e)
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#$Foff+0]	@ f.lo
+	adc	$Thi,$Thi,$t1		@ T += Sigma1(e)
+	ldr	$t1,[sp,#$Foff+4]	@ f.hi
+	adds	$Tlo,$Tlo,$t2
+	ldr	$t2,[sp,#$Goff+0]	@ g.lo
+	adc	$Thi,$Thi,$t3		@ T += h
+	ldr	$t3,[sp,#$Goff+4]	@ g.hi
+
+	eor	$t0,$t0,$t2
+	str	$Elo,[sp,#$Eoff+0]
+	eor	$t1,$t1,$t3
+	str	$Ehi,[sp,#$Eoff+4]
+	and	$t0,$t0,$Elo
+	str	$Alo,[sp,#$Aoff+0]
+	and	$t1,$t1,$Ehi
+	str	$Ahi,[sp,#$Aoff+4]
+	eor	$t0,$t0,$t2
+	ldr	$t2,[$Ktbl,#$lo]	@ K[i].lo
+	eor	$t1,$t1,$t3		@ Ch(e,f,g)
+	ldr	$t3,[$Ktbl,#$hi]	@ K[i].hi
+
+	adds	$Tlo,$Tlo,$t0
+	ldr	$Elo,[sp,#$Doff+0]	@ d.lo
+	adc	$Thi,$Thi,$t1		@ T += Ch(e,f,g)
+	ldr	$Ehi,[sp,#$Doff+4]	@ d.hi
+	adds	$Tlo,$Tlo,$t2
+	and	$t0,$t2,#0xff
+	adc	$Thi,$Thi,$t3		@ T += K[i]
+	adds	$Elo,$Elo,$Tlo
+	ldr	$t2,[sp,#$Boff+0]	@ b.lo
+	adc	$Ehi,$Ehi,$Thi		@ d += T
+	teq	$t0,#$magic
+
+	ldr	$t3,[sp,#$Coff+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	$Ktbl,$Ktbl,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	$t0,$Alo,lsr#28
+	mov	$t1,$Ahi,lsr#28
+	eor	$t0,$t0,$Ahi,lsl#4
+	eor	$t1,$t1,$Alo,lsl#4
+	eor	$t0,$t0,$Ahi,lsr#2
+	eor	$t1,$t1,$Alo,lsr#2
+	eor	$t0,$t0,$Alo,lsl#30
+	eor	$t1,$t1,$Ahi,lsl#30
+	eor	$t0,$t0,$Ahi,lsr#7
+	eor	$t1,$t1,$Alo,lsr#7
+	eor	$t0,$t0,$Alo,lsl#25
+	eor	$t1,$t1,$Ahi,lsl#25	@ Sigma0(a)
+	adds	$Tlo,$Tlo,$t0
+	and	$t0,$Alo,$t2
+	adc	$Thi,$Thi,$t1		@ T += Sigma0(a)
+
+	ldr	$t1,[sp,#$Boff+4]	@ b.hi
+	orr	$Alo,$Alo,$t2
+	ldr	$t2,[sp,#$Coff+4]	@ c.hi
+	and	$Alo,$Alo,$t3
+	and	$t3,$Ahi,$t1
+	orr	$Ahi,$Ahi,$t1
+	orr	$Alo,$Alo,$t0		@ Maj(a,b,c).lo
+	and	$Ahi,$Ahi,$t2
+	adds	$Alo,$Alo,$Tlo
+	orr	$Ahi,$Ahi,$t3		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	$Ahi,$Ahi,$Thi		@ h += T
+	tst	$Ktbl,#1
+	add	$Ktbl,$Ktbl,#8
+___
+}
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	$Ktbl,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	$Elo,[$ctx,#$Eoff+$lo]
+	ldr	$Ehi,[$ctx,#$Eoff+$hi]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+.Loop:
+	str	$t0, [sp,#$Goff+0]
+	str	$t1, [sp,#$Goff+4]
+	str	$t2, [sp,#$Hoff+0]
+	str	$t3, [sp,#$Hoff+4]
+	ldr	$Alo,[$ctx,#$Aoff+$lo]
+	ldr	$Ahi,[$ctx,#$Aoff+$hi]
+	ldr	$Tlo,[$ctx,#$Boff+$lo]
+	ldr	$Thi,[$ctx,#$Boff+$hi]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	str	$Tlo,[sp,#$Boff+0]
+	str	$Thi,[sp,#$Boff+4]
+	str	$t0, [sp,#$Coff+0]
+	str	$t1, [sp,#$Coff+4]
+	str	$t2, [sp,#$Doff+0]
+	str	$t3, [sp,#$Doff+4]
+	ldr	$Tlo,[$ctx,#$Foff+$lo]
+	ldr	$Thi,[$ctx,#$Foff+$hi]
+	str	$Tlo,[sp,#$Foff+0]
+	str	$Thi,[sp,#$Foff+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	$Tlo,[$inp,#7]
+	ldrb	$t0, [$inp,#6]
+	ldrb	$t1, [$inp,#5]
+	ldrb	$t2, [$inp,#4]
+	ldrb	$Thi,[$inp,#3]
+	ldrb	$t3, [$inp,#2]
+	orr	$Tlo,$Tlo,$t0,lsl#8
+	ldrb	$t0, [$inp,#1]
+	orr	$Tlo,$Tlo,$t1,lsl#16
+	ldrb	$t1, [$inp],#8
+	orr	$Tlo,$Tlo,$t2,lsl#24
+	orr	$Thi,$Thi,$t3,lsl#8
+	orr	$Thi,$Thi,$t0,lsl#16
+	orr	$Thi,$Thi,$t1,lsl#24
+#else
+	ldr	$Tlo,[$inp,#4]
+	ldr	$Thi,[$inp],#8
+#ifdef __ARMEL__
+	rev	$Tlo,$Tlo
+	rev	$Thi,$Thi
+#endif
+#endif
+___
+	&BODY_00_15(0x94);
+$code.=<<___;
+	tst	$Ktbl,#1
+	beq	.L00_15
+	ldr	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldr	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	bic	$Ktbl,$Ktbl,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	$Tlo,$t0,lsr#1
+	ldr	$t2,[sp,#`$Xoff+8*(16-14)`+0]
+	mov	$Thi,$t1,lsr#1
+	ldr	$t3,[sp,#`$Xoff+8*(16-14)`+4]
+	eor	$Tlo,$Tlo,$t1,lsl#31
+	eor	$Thi,$Thi,$t0,lsl#31
+	eor	$Tlo,$Tlo,$t0,lsr#8
+	eor	$Thi,$Thi,$t1,lsr#8
+	eor	$Tlo,$Tlo,$t1,lsl#24
+	eor	$Thi,$Thi,$t0,lsl#24
+	eor	$Tlo,$Tlo,$t0,lsr#7
+	eor	$Thi,$Thi,$t1,lsr#7
+	eor	$Tlo,$Tlo,$t1,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	$t0,$t2,lsr#19
+	mov	$t1,$t3,lsr#19
+	eor	$t0,$t0,$t3,lsl#13
+	eor	$t1,$t1,$t2,lsl#13
+	eor	$t0,$t0,$t3,lsr#29
+	eor	$t1,$t1,$t2,lsr#29
+	eor	$t0,$t0,$t2,lsl#3
+	eor	$t1,$t1,$t3,lsl#3
+	eor	$t0,$t0,$t2,lsr#6
+	eor	$t1,$t1,$t3,lsr#6
+	ldr	$t2,[sp,#`$Xoff+8*(16-9)`+0]
+	eor	$t0,$t0,$t3,lsl#26
+
+	ldr	$t3,[sp,#`$Xoff+8*(16-9)`+4]
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#`$Xoff+8*16`+0]
+	adc	$Thi,$Thi,$t1
+
+	ldr	$t1,[sp,#`$Xoff+8*16`+4]
+	adds	$Tlo,$Tlo,$t2
+	adc	$Thi,$Thi,$t3
+	adds	$Tlo,$Tlo,$t0
+	adc	$Thi,$Thi,$t1
+___
+	&BODY_00_15(0x17);
+$code.=<<___;
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldreq	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	beq	.L16_79
+	bic	$Ktbl,$Ktbl,#1
+
+	ldr	$Tlo,[sp,#$Boff+0]
+	ldr	$Thi,[sp,#$Boff+4]
+	ldr	$t0, [$ctx,#$Aoff+$lo]
+	ldr	$t1, [$ctx,#$Aoff+$hi]
+	ldr	$t2, [$ctx,#$Boff+$lo]
+	ldr	$t3, [$ctx,#$Boff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Aoff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Aoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Boff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Boff+$hi]
+
+	ldr	$Alo,[sp,#$Coff+0]
+	ldr	$Ahi,[sp,#$Coff+4]
+	ldr	$Tlo,[sp,#$Doff+0]
+	ldr	$Thi,[sp,#$Doff+4]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Coff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Coff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Doff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Doff+$hi]
+
+	ldr	$Tlo,[sp,#$Foff+0]
+	ldr	$Thi,[sp,#$Foff+4]
+	ldr	$t0, [$ctx,#$Eoff+$lo]
+	ldr	$t1, [$ctx,#$Eoff+$hi]
+	ldr	$t2, [$ctx,#$Foff+$lo]
+	ldr	$t3, [$ctx,#$Foff+$hi]
+	adds	$Elo,$Elo,$t0
+	str	$Elo,[$ctx,#$Eoff+$lo]
+	adc	$Ehi,$Ehi,$t1
+	str	$Ehi,[$ctx,#$Eoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Foff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Foff+$hi]
+
+	ldr	$Alo,[sp,#$Goff+0]
+	ldr	$Ahi,[sp,#$Goff+4]
+	ldr	$Tlo,[sp,#$Hoff+0]
+	ldr	$Thi,[sp,#$Hoff+4]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Goff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Goff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Hoff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Hoff+$hi]
+
+	add	sp,sp,#640
+	sub	$Ktbl,$Ktbl,#640
+
+	teq	$inp,$len
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+___
+
+{
+my @Sigma0=(28,34,39);
+my @Sigma1=(14,18,41);
+my @sigma0=(1, 8, 7);
+my @sigma1=(19,61,6);
+
+my $Ktbl="r3";
+my $cnt="r12";	# volatile register known as ip, intra-procedure-call scratch
+
+my @X=map("d$_",(0..15));
+my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23));
+
+sub NEON_00_15() {
+my $i=shift;
+my ($a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31));	# temps
+
+$code.=<<___ if ($i<16 || $i&1);
+	vshr.u64	$t0,$e,#@Sigma1[0]	@ $i
+#if $i<16
+	vld1.64		{@X[$i%16]},[$inp]!	@ handles unaligned
+#endif
+	vshr.u64	$t1,$e,#@Sigma1[1]
+#if $i>0
+	 vadd.i64	$a,$Maj			@ h+=Maj from the past
+#endif
+	vshr.u64	$t2,$e,#@Sigma1[2]
+___
+$code.=<<___;
+	vld1.64		{$K},[$Ktbl,:64]!	@ K[i++]
+	vsli.64		$t0,$e,#`64-@Sigma1[0]`
+	vsli.64		$t1,$e,#`64-@Sigma1[1]`
+	vmov		$Ch,$e
+	vsli.64		$t2,$e,#`64-@Sigma1[2]`
+#if $i<16 && defined(__ARMEL__)
+	vrev64.8	@X[$i],@X[$i]
+#endif
+	veor		$t1,$t0
+	vbsl		$Ch,$f,$g		@ Ch(e,f,g)
+	vshr.u64	$t0,$a,#@Sigma0[0]
+	veor		$t2,$t1			@ Sigma1(e)
+	vadd.i64	$T1,$Ch,$h
+	vshr.u64	$t1,$a,#@Sigma0[1]
+	vsli.64		$t0,$a,#`64-@Sigma0[0]`
+	vadd.i64	$T1,$t2
+	vshr.u64	$t2,$a,#@Sigma0[2]
+	vadd.i64	$K,@X[$i%16]
+	vsli.64		$t1,$a,#`64-@Sigma0[1]`
+	veor		$Maj,$a,$b
+	vsli.64		$t2,$a,#`64-@Sigma0[2]`
+	veor		$h,$t0,$t1
+	vadd.i64	$T1,$K
+	vbsl		$Maj,$c,$b		@ Maj(a,b,c)
+	veor		$h,$t2			@ Sigma0(a)
+	vadd.i64	$d,$T1
+	vadd.i64	$Maj,$T1
+	@ vadd.i64	$h,$Maj
+___
+}
+
+sub NEON_16_79() {
+my $i=shift;
+
+if ($i&1)	{ &NEON_00_15($i,@_); return; }
+
+# 2x-vectorized, therefore runs every 2nd round
+my @X=map("q$_",(0..7));			# view @X as 128-bit vector
+my ($t0,$t1,$s0,$s1) = map("q$_",(12..15));	# temps
+my ($d0,$d1,$d2) = map("d$_",(24..26));		# temps from NEON_00_15
+my $e=@_[4];					# $e from NEON_00_15
+$i /= 2;
+$code.=<<___;
+	vshr.u64	$t0,@X[($i+7)%8],#@sigma1[0]
+	vshr.u64	$t1,@X[($i+7)%8],#@sigma1[1]
+	 vadd.i64	@_[0],d30			@ h+=Maj from the past
+	vshr.u64	$s1,@X[($i+7)%8],#@sigma1[2]
+	vsli.64		$t0,@X[($i+7)%8],#`64-@sigma1[0]`
+	vext.8		$s0,@X[$i%8],@X[($i+1)%8],#8	@ X[i+1]
+	vsli.64		$t1,@X[($i+7)%8],#`64-@sigma1[1]`
+	veor		$s1,$t0
+	vshr.u64	$t0,$s0,#@sigma0[0]
+	veor		$s1,$t1				@ sigma1(X[i+14])
+	vshr.u64	$t1,$s0,#@sigma0[1]
+	vadd.i64	@X[$i%8],$s1
+	vshr.u64	$s1,$s0,#@sigma0[2]
+	vsli.64		$t0,$s0,#`64-@sigma0[0]`
+	vsli.64		$t1,$s0,#`64-@sigma0[1]`
+	vext.8		$s0,@X[($i+4)%8],@X[($i+5)%8],#8	@ X[i+9]
+	veor		$s1,$t0
+	vshr.u64	$d0,$e,#@Sigma1[0]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s0
+	vshr.u64	$d1,$e,#@Sigma1[1]		@ from NEON_00_15
+	veor		$s1,$t1				@ sigma0(X[i+1])
+	vshr.u64	$d2,$e,#@Sigma1[2]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s1
+___
+	&NEON_00_15(2*$i,@_);
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	$Ktbl,K512
+	vldmia	$ctx,{$A-$H}		@ load context
+.Loop_neon:
+___
+for($i=0;$i<16;$i++)	{ &NEON_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	mov		$cnt,#4
+.L16_79_neon:
+	subs		$cnt,#1
+___
+for(;$i<32;$i++)	{ &NEON_16_79($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	bne		.L16_79_neon
+
+	 vadd.i64	$A,d30		@ h+=Maj from the past
+	vldmia		$ctx,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		$ctx,{$A-$H}	@ save context
+	teq		$inp,$len
+	sub		$Ktbl,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	ret				@ bx lr
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+___
+}
+$code.=<<___;
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
+___
+
+$code =~ s/\`([^\`]*)\`/eval $1/gem;
+$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
+$code =~ s/\bret\b/bx	lr/gm;
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+print $code;
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
deleted file mode 100644
index fe99472e507c..000000000000
--- a/arch/arm/crypto/sha512-armv7-neon.S
+++ /dev/null
@@ -1,455 +0,0 @@
-/* sha512-armv7-neon.S  -  ARM/NEON assembly implementation of SHA-512 transform
- *
- * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/linkage.h>
-
-
-.syntax unified
-.code   32
-.fpu neon
-
-.text
-
-/* structure of SHA512_CONTEXT */
-#define hd_a 0
-#define hd_b ((hd_a) + 8)
-#define hd_c ((hd_b) + 8)
-#define hd_d ((hd_c) + 8)
-#define hd_e ((hd_d) + 8)
-#define hd_f ((hd_e) + 8)
-#define hd_g ((hd_f) + 8)
-
-/* register macros */
-#define RK %r2
-
-#define RA d0
-#define RB d1
-#define RC d2
-#define RD d3
-#define RE d4
-#define RF d5
-#define RG d6
-#define RH d7
-
-#define RT0 d8
-#define RT1 d9
-#define RT2 d10
-#define RT3 d11
-#define RT4 d12
-#define RT5 d13
-#define RT6 d14
-#define RT7 d15
-
-#define RT01q q4
-#define RT23q q5
-#define RT45q q6
-#define RT67q q7
-
-#define RW0 d16
-#define RW1 d17
-#define RW2 d18
-#define RW3 d19
-#define RW4 d20
-#define RW5 d21
-#define RW6 d22
-#define RW7 d23
-#define RW8 d24
-#define RW9 d25
-#define RW10 d26
-#define RW11 d27
-#define RW12 d28
-#define RW13 d29
-#define RW14 d30
-#define RW15 d31
-
-#define RW01q q8
-#define RW23q q9
-#define RW45q q10
-#define RW67q q11
-#define RW89q q12
-#define RW1011q q13
-#define RW1213q q14
-#define RW1415q q15
-
-/***********************************************************************
- * ARM assembly implementation of sha512 transform
- ***********************************************************************/
-#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
-                     rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3; \
-	\
-	/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
-	/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
-	\
-	/**** S0(w[1:2]) */ \
-	\
-	/* w[0:1] += w[9:10] */ \
-	/* RT23q = rw1:rw2 */ \
-	vext.u64 RT23q, rw01q, rw23q, #1; \
-	vadd.u64 rw0, rw9; \
-	vadd.u64 rg, rg, RT0; \
-	vadd.u64 rw1, rw10;\
-	vadd.u64 rg, rg, RT1; /* g+=t1; */ \
-	\
-	vshr.u64 RT45q, RT23q, #1; \
-	vshl.u64 RT67q, RT23q, #64 - 1; \
-	vshr.u64 RT01q, RT23q, #8; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	vshl.u64 RT67q, RT23q, #64 - 8; \
-	veor.u64 RT45q, RT45q, RT01q; \
-	vshr.u64 RT01q, RT23q, #7; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	\
-	/**** S1(w[14:15]) */ \
-	vshr.u64 RT23q, rw1415q, #6; \
-	veor.u64 RT01q, RT01q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #19; \
-	vshl.u64 RT67q, rw1415q, #64 - 19; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #61; \
-	veor.u64 RT23q, RT23q, RT67q; \
-	vshl.u64 RT67q, rw1415q, #64 - 61; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
-	veor.u64 RT01q, RT23q, RT67q;
-#define vadd_RT01q(rw01q) \
-	/* w[0:1] += S(w[14:15]) */ \
-	vadd.u64 rw01q, RT01q;
-
-#define dummy(_) /*_*/
-
-#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
-	              interleave_op1, arg1, interleave_op2, arg2) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op1(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	interleave_op2(arg2); \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3;
-#define vadd_rg_RT0(rg) \
-	vadd.u64 rg, rg, RT0;
-#define vadd_rg_RT1(rg) \
-	vadd.u64 rg, rg, RT1; /* g+=t1; */
-
-.align 3
-ENTRY(sha512_transform_neon)
-	/* Input:
-	 *	%r0: SHA512_CONTEXT
-	 *	%r1: data
-	 *	%r2: u64 k[] constants
-	 *	%r3: nblks
-	 */
-	push {%lr};
-
-	mov %lr, #0;
-
-	/* Load context to d0-d7 */
-	vld1.64 {RA-RD}, [%r0]!;
-	vld1.64 {RE-RH}, [%r0];
-	sub %r0, #(4*8);
-
-	/* Load input to w[16], d16-d31 */
-	/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
-	vld1.64 {RW0-RW3}, [%r1]!;
-	vld1.64 {RW4-RW7}, [%r1]!;
-	vld1.64 {RW8-RW11}, [%r1]!;
-	vld1.64 {RW12-RW15}, [%r1]!;
-#ifdef __ARMEL__
-	/* byteswap */
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	/* EABI says that d8-d15 must be preserved by callee. */
-	/*vpush {RT0-RT7};*/
-
-.Loop:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, dummy, _);
-	b .Lenter_rounds;
-
-.Loop_rounds:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
-.Lenter_rounds:
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
-		     RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
-		     RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
-		     RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
-		     RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
-		     RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
-	add %lr, #16;
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
-		     RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
-	cmp %lr, #64;
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
-		     RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
-	bne .Loop_rounds;
-
-	subs %r3, #1;
-
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
-		      vadd_RT01q, RW1415q, dummy, _);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	beq .Lhandle_tail;
-	vld1.64 {RW0-RW3}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-#endif
-	vld1.64 {RW4-RW7}, [%r1]!;
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-#ifdef __ARMEL__
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-#endif
-	vld1.64 {RW8-RW11}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-#endif
-	vld1.64 {RW12-RW15}, [%r1]!;
-	vadd_rg_RT0(RA);
-	vadd_rg_RT1(RA);
-
-	/* Load context */
-	vld1.64 {RT0-RT3}, [%r0]!;
-	vld1.64 {RT4-RT7}, [%r0];
-	sub %r0, #(4*8);
-
-#ifdef __ARMEL__
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	vadd.u64 RA, RT0;
-	vadd.u64 RB, RT1;
-	vadd.u64 RC, RT2;
-	vadd.u64 RD, RT3;
-	vadd.u64 RE, RT4;
-	vadd.u64 RF, RT5;
-	vadd.u64 RG, RT6;
-	vadd.u64 RH, RT7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-	sub RK, $(8*80);
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	mov %lr, #0;
-	sub %r0, #(4*8);
-
-	b .Loop;
-
-.Lhandle_tail:
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-
-	/* Load context to d16-d23 */
-	vld1.64 {RW0-RW3}, [%r0]!;
-	vadd_rg_RT0(RA);
-	vld1.64 {RW4-RW7}, [%r0];
-	vadd_rg_RT1(RA);
-	sub %r0, #(4*8);
-
-	vadd.u64 RA, RW0;
-	vadd.u64 RB, RW1;
-	vadd.u64 RC, RW2;
-	vadd.u64 RD, RW3;
-	vadd.u64 RE, RW4;
-	vadd.u64 RF, RW5;
-	vadd.u64 RG, RW6;
-	vadd.u64 RH, RW7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-
-	/* Clear used registers */
-	/* d16-d31 */
-	veor.u64 RW01q, RW01q;
-	veor.u64 RW23q, RW23q;
-	veor.u64 RW45q, RW45q;
-	veor.u64 RW67q, RW67q;
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	veor.u64 RW89q, RW89q;
-	veor.u64 RW1011q, RW1011q;
-	veor.u64 RW1213q, RW1213q;
-	veor.u64 RW1415q, RW1415q;
-	/* d8-d15 */
-	/*vpop {RT0-RT7};*/
-	/* d0-d7 (q0-q3) */
-	veor.u64 %q0, %q0;
-	veor.u64 %q1, %q1;
-	veor.u64 %q2, %q2;
-	veor.u64 %q3, %q3;
-
-	pop {%pc};
-ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
new file mode 100644
index 000000000000..3694c4d4ca2b
--- /dev/null
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -0,0 +1,1861 @@
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA512 block procedure for ARMv4. September 2007.
+
+@ This code is ~4.5 (four and a half) times faster than code generated
+@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+@ Xscale PXA250 core].
+@
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
+@ Cortex A8 core and ~40 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 7%
+@ improvement on Coxtex A8 core and ~38 cycles per byte.
+
+@ March 2011.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process
+@ one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+@ August 2012.
+@
+@ Improve NEON performance by 12% on Snapdragon S4. In absolute
+@ terms it's 22.6 cycles per byte, which is disappointing result.
+@ Technical writers asserted that 3-way S4 pipeline can sustain
+@ multiple NEON instructions per cycle, but dual NEON issue could
+@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ for further details. On side note Cortex-A15 processes one byte in
+@ 16 cycles.
+
+@ Byte order [in]dependence. =========================================
+@
+@ Originally caller was expected to maintain specific *dword* order in
+@ h[0-7], namely with most significant dword at *lower* address, which
+@ was reflected in below two parameters as 0 and 4. Now caller is
+@ expected to maintain native byte order for whole 64-bit values.
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	r14,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	r7,[r0,#32+LO]
+	ldr	r8,[r0,#32+HI]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+.Loop:
+	str	r9, [sp,#48+0]
+	str	r10, [sp,#48+4]
+	str	r11, [sp,#56+0]
+	str	r12, [sp,#56+4]
+	ldr	r5,[r0,#0+LO]
+	ldr	r6,[r0,#0+HI]
+	ldr	r3,[r0,#8+LO]
+	ldr	r4,[r0,#8+HI]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	str	r3,[sp,#8+0]
+	str	r4,[sp,#8+4]
+	str	r9, [sp,#16+0]
+	str	r10, [sp,#16+4]
+	str	r11, [sp,#24+0]
+	str	r12, [sp,#24+4]
+	ldr	r3,[r0,#40+LO]
+	ldr	r4,[r0,#40+HI]
+	str	r3,[sp,#40+0]
+	str	r4,[sp,#40+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	r3,[r1,#7]
+	ldrb	r9, [r1,#6]
+	ldrb	r10, [r1,#5]
+	ldrb	r11, [r1,#4]
+	ldrb	r4,[r1,#3]
+	ldrb	r12, [r1,#2]
+	orr	r3,r3,r9,lsl#8
+	ldrb	r9, [r1,#1]
+	orr	r3,r3,r10,lsl#16
+	ldrb	r10, [r1],#8
+	orr	r3,r3,r11,lsl#24
+	orr	r4,r4,r12,lsl#8
+	orr	r4,r4,r9,lsl#16
+	orr	r4,r4,r10,lsl#24
+#else
+	ldr	r3,[r1,#4]
+	ldr	r4,[r1],#8
+#ifdef __ARMEL__
+	rev	r3,r3
+	rev	r4,r4
+#endif
+#endif
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#148
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+	tst	r14,#1
+	beq	.L00_15
+	ldr	r9,[sp,#184+0]
+	ldr	r10,[sp,#184+4]
+	bic	r14,r14,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	r3,r9,lsr#1
+	ldr	r11,[sp,#80+0]
+	mov	r4,r10,lsr#1
+	ldr	r12,[sp,#80+4]
+	eor	r3,r3,r10,lsl#31
+	eor	r4,r4,r9,lsl#31
+	eor	r3,r3,r9,lsr#8
+	eor	r4,r4,r10,lsr#8
+	eor	r3,r3,r10,lsl#24
+	eor	r4,r4,r9,lsl#24
+	eor	r3,r3,r9,lsr#7
+	eor	r4,r4,r10,lsr#7
+	eor	r3,r3,r10,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	r9,r11,lsr#19
+	mov	r10,r12,lsr#19
+	eor	r9,r9,r12,lsl#13
+	eor	r10,r10,r11,lsl#13
+	eor	r9,r9,r12,lsr#29
+	eor	r10,r10,r11,lsr#29
+	eor	r9,r9,r11,lsl#3
+	eor	r10,r10,r12,lsl#3
+	eor	r9,r9,r11,lsr#6
+	eor	r10,r10,r12,lsr#6
+	ldr	r11,[sp,#120+0]
+	eor	r9,r9,r12,lsl#26
+
+	ldr	r12,[sp,#120+4]
+	adds	r3,r3,r9
+	ldr	r9,[sp,#192+0]
+	adc	r4,r4,r10
+
+	ldr	r10,[sp,#192+4]
+	adds	r3,r3,r11
+	adc	r4,r4,r12
+	adds	r3,r3,r9
+	adc	r4,r4,r10
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#23
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	r9,[sp,#184+0]
+	ldreq	r10,[sp,#184+4]
+	beq	.L16_79
+	bic	r14,r14,#1
+
+	ldr	r3,[sp,#8+0]
+	ldr	r4,[sp,#8+4]
+	ldr	r9, [r0,#0+LO]
+	ldr	r10, [r0,#0+HI]
+	ldr	r11, [r0,#8+LO]
+	ldr	r12, [r0,#8+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#0+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#0+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#8+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#8+HI]
+
+	ldr	r5,[sp,#16+0]
+	ldr	r6,[sp,#16+4]
+	ldr	r3,[sp,#24+0]
+	ldr	r4,[sp,#24+4]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#16+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#16+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#24+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#24+HI]
+
+	ldr	r3,[sp,#40+0]
+	ldr	r4,[sp,#40+4]
+	ldr	r9, [r0,#32+LO]
+	ldr	r10, [r0,#32+HI]
+	ldr	r11, [r0,#40+LO]
+	ldr	r12, [r0,#40+HI]
+	adds	r7,r7,r9
+	str	r7,[r0,#32+LO]
+	adc	r8,r8,r10
+	str	r8,[r0,#32+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#40+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#40+HI]
+
+	ldr	r5,[sp,#48+0]
+	ldr	r6,[sp,#48+4]
+	ldr	r3,[sp,#56+0]
+	ldr	r4,[sp,#56+4]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#48+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#48+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#56+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#56+HI]
+
+	add	sp,sp,#640
+	sub	r14,r14,#640
+
+	teq	r1,r2
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	r3,K512
+	vldmia	r0,{d16-d23}		@ load context
+.Loop_neon:
+	vshr.u64	d24,d20,#14	@ 0
+#if 0<16
+	vld1.64		{d0},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 0>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 0<16 && defined(__ARMEL__)
+	vrev64.8	d0,d0
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 1
+#if 1<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 1>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 1<16 && defined(__ARMEL__)
+	vrev64.8	d1,d1
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 2
+#if 2<16
+	vld1.64		{d2},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 2>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 2<16 && defined(__ARMEL__)
+	vrev64.8	d2,d2
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 3
+#if 3<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 3>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 3<16 && defined(__ARMEL__)
+	vrev64.8	d3,d3
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 4
+#if 4<16
+	vld1.64		{d4},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 4>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 4<16 && defined(__ARMEL__)
+	vrev64.8	d4,d4
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 5
+#if 5<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 5>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 5<16 && defined(__ARMEL__)
+	vrev64.8	d5,d5
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 6
+#if 6<16
+	vld1.64		{d6},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 6>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 6<16 && defined(__ARMEL__)
+	vrev64.8	d6,d6
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 7
+#if 7<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 7>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 7<16 && defined(__ARMEL__)
+	vrev64.8	d7,d7
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	d24,d20,#14	@ 8
+#if 8<16
+	vld1.64		{d8},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 8>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 8<16 && defined(__ARMEL__)
+	vrev64.8	d8,d8
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 9
+#if 9<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 9>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 9<16 && defined(__ARMEL__)
+	vrev64.8	d9,d9
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 10
+#if 10<16
+	vld1.64		{d10},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 10>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 10<16 && defined(__ARMEL__)
+	vrev64.8	d10,d10
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 11
+#if 11<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 11>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 11<16 && defined(__ARMEL__)
+	vrev64.8	d11,d11
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 12
+#if 12<16
+	vld1.64		{d12},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 12>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 12<16 && defined(__ARMEL__)
+	vrev64.8	d12,d12
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 13
+#if 13<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 13>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 13<16 && defined(__ARMEL__)
+	vrev64.8	d13,d13
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 14
+#if 14<16
+	vld1.64		{d14},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 14>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 14<16 && defined(__ARMEL__)
+	vrev64.8	d14,d14
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 15
+#if 15<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 15>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 15<16 && defined(__ARMEL__)
+	vrev64.8	d15,d15
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	mov		r12,#4
+.L16_79_neon:
+	subs		r12,#1
+	vshr.u64	q12,q7,#19
+	vshr.u64	q13,q7,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q7,#6
+	vsli.64		q12,q7,#45
+	vext.8		q14,q0,q1,#8	@ X[i+1]
+	vsli.64		q13,q7,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q0,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q4,q5,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q0,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q0,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 16<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 17
+#if 17<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 17>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 17<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q0,#19
+	vshr.u64	q13,q0,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q0,#6
+	vsli.64		q12,q0,#45
+	vext.8		q14,q1,q2,#8	@ X[i+1]
+	vsli.64		q13,q0,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q1,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q5,q6,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q1,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q1,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 18<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 19
+#if 19<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 19>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 19<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q1,#19
+	vshr.u64	q13,q1,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q1,#6
+	vsli.64		q12,q1,#45
+	vext.8		q14,q2,q3,#8	@ X[i+1]
+	vsli.64		q13,q1,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q2,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q6,q7,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q2,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q2,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 20<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 21
+#if 21<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 21>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 21<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q2,#19
+	vshr.u64	q13,q2,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q2,#6
+	vsli.64		q12,q2,#45
+	vext.8		q14,q3,q4,#8	@ X[i+1]
+	vsli.64		q13,q2,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q3,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q7,q0,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q3,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q3,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 22<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 23
+#if 23<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 23>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 23<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	q12,q3,#19
+	vshr.u64	q13,q3,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q3,#6
+	vsli.64		q12,q3,#45
+	vext.8		q14,q4,q5,#8	@ X[i+1]
+	vsli.64		q13,q3,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q4,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q0,q1,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q4,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q4,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 24<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 25
+#if 25<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 25>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 25<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q4,#19
+	vshr.u64	q13,q4,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q4,#6
+	vsli.64		q12,q4,#45
+	vext.8		q14,q5,q6,#8	@ X[i+1]
+	vsli.64		q13,q4,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q5,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q1,q2,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q5,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q5,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 26<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 27
+#if 27<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 27>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 27<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q5,#19
+	vshr.u64	q13,q5,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q5,#6
+	vsli.64		q12,q5,#45
+	vext.8		q14,q6,q7,#8	@ X[i+1]
+	vsli.64		q13,q5,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q6,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q2,q3,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q6,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q6,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 28<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 29
+#if 29<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 29>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 29<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q6,#19
+	vshr.u64	q13,q6,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q6,#6
+	vsli.64		q12,q6,#45
+	vext.8		q14,q7,q0,#8	@ X[i+1]
+	vsli.64		q13,q6,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q7,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q3,q4,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q7,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q7,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 30<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 31
+#if 31<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 31>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 31<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	bne		.L16_79_neon
+
+	 vadd.i64	d16,d30		@ h+=Maj from the past
+	vldmia		r0,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		r0,{d16-d23}	@ save context
+	teq		r1,r2
+	sub		r3,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	bx	lr				@ .word	0xe12fff1e
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
new file mode 100644
index 000000000000..269a394e4a53
--- /dev/null
+++ b/arch/arm/crypto/sha512-glue.c
@@ -0,0 +1,121 @@
+/*
+ * sha512-glue.c - accelerated SHA-384/512 for ARM
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384-arm");
+MODULE_ALIAS_CRYPTO("sha512-arm");
+
+asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks);
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len)
+{
+	return sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+}
+
+int sha512_arm_final(struct shash_desc *desc, u8 *out)
+{
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_base_finish(desc, out);
+}
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out)
+{
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_arm_final(desc, out);
+}
+
+static struct shash_alg sha512_arm_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha512_arm_mod_init(void)
+{
+	int err;
+
+	err = crypto_register_shashes(sha512_arm_algs,
+				      ARRAY_SIZE(sha512_arm_algs));
+	if (err)
+		return err;
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+		err = crypto_register_shashes(sha512_neon_algs,
+					      ARRAY_SIZE(sha512_neon_algs));
+		if (err)
+			goto err_unregister;
+	}
+	return 0;
+
+err_unregister:
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+
+	return err;
+}
+
+static void __exit sha512_arm_mod_fini(void)
+{
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+		crypto_unregister_shashes(sha512_neon_algs,
+					  ARRAY_SIZE(sha512_neon_algs));
+}
+
+module_init(sha512_arm_mod_init);
+module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
new file mode 100644
index 000000000000..32693684a3ab
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,98 @@
+/*
+ * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_ALIAS_CRYPTO("sha384-neon");
+MODULE_ALIAS_CRYPTO("sha512-neon");
+
+asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src,
+					     int blocks);
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	if (!may_use_simd() ||
+	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+		return sha512_arm_update(desc, data, len);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	if (!may_use_simd())
+		return sha512_arm_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	if (len)
+		sha512_base_do_update(desc, data, len,
+			(sha512_block_fn *)sha512_block_data_order_neon);
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
new file mode 100644
index 000000000000..a75d9a82988a
--- /dev/null
+++ b/arch/arm/crypto/sha512.h
@@ -0,0 +1,8 @@
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len);
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out);
+
+extern struct shash_alg sha512_neon_algs[2];
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
deleted file mode 100644
index b124dce838d6..000000000000
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
- * using NEON instructions.
- *
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This file is based on sha512_ssse3_glue.c:
- *   Copyright (C) 2013 Intel Corporation
- *   Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha.h>
-#include <asm/byteorder.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-
-static const u64 sha512_k[] = {
-	0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
-	0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
-	0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
-	0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
-	0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
-	0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
-	0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
-	0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
-	0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
-	0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
-	0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
-	0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
-	0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
-	0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
-	0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
-	0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
-	0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
-	0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
-	0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
-	0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
-	0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
-	0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
-	0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
-	0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
-	0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
-	0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
-	0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
-	0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
-	0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
-	0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
-	0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
-	0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
-	0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
-	0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
-	0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
-	0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
-	0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
-	0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
-	0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
-	0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
-};
-
-
-asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
-				      const u64 k[], unsigned int num_blks);
-
-
-static int sha512_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA512_H0;
-	sctx->state[1] = SHA512_H1;
-	sctx->state[2] = SHA512_H2;
-	sctx->state[3] = SHA512_H3;
-	sctx->state[4] = SHA512_H4;
-	sctx->state[5] = SHA512_H5;
-	sctx->state[6] = SHA512_H6;
-	sctx->state[7] = SHA512_H7;
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
-				unsigned int len, unsigned int partial)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int done = 0;
-
-	sctx->count[0] += len;
-	if (sctx->count[0] < len)
-		sctx->count[1]++;
-
-	if (partial) {
-		done = SHA512_BLOCK_SIZE - partial;
-		memcpy(sctx->buf + partial, data, done);
-		sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
-	}
-
-	if (len - done >= SHA512_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
-
-		sha512_transform_neon(sctx->state, data + done, sha512_k,
-				      rounds);
-
-		done += rounds * SHA512_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buf, data + done, len - done);
-
-	return 0;
-}
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
-	int res;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA512_BLOCK_SIZE) {
-		sctx->count[0] += len;
-		if (sctx->count[0] < len)
-			sctx->count[1]++;
-		memcpy(sctx->buf + partial, data, len);
-
-		return 0;
-	}
-
-	if (!may_use_simd()) {
-		res = crypto_sha512_update(desc, data, len);
-	} else {
-		kernel_neon_begin();
-		res = __sha512_neon_update(desc, data, len, partial);
-		kernel_neon_end();
-	}
-
-	return res;
-}
-
-
-/* Add padding and return the message digest. */
-static int sha512_neon_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be64 *dst = (__be64 *)out;
-	__be64 bits[2];
-	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
-
-	/* save number of bits */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128 and append length */
-	index = sctx->count[0] & 0x7f;
-	padlen = (index < 112) ? (112 - index) : ((128+112) - index);
-
-	if (!may_use_simd()) {
-		crypto_sha512_update(desc, padding, padlen);
-		crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
-	} else {
-		kernel_neon_begin();
-		/* We need to fill a whole block for __sha512_neon_update() */
-		if (padlen <= 112) {
-			sctx->count[0] += padlen;
-			if (sctx->count[0] < padlen)
-				sctx->count[1]++;
-			memcpy(sctx->buf + index, padding, padlen);
-		} else {
-			__sha512_neon_update(desc, padding, padlen, index);
-		}
-		__sha512_neon_update(desc, (const u8 *)&bits,
-					sizeof(bits), 112);
-		kernel_neon_end();
-	}
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_export(struct shash_desc *desc, void *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_import(struct shash_desc *desc, const void *in)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha384_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA384_H0;
-	sctx->state[1] = SHA384_H1;
-	sctx->state[2] = SHA384_H2;
-	sctx->state[3] = SHA384_H3;
-	sctx->state[4] = SHA384_H4;
-	sctx->state[5] = SHA384_H5;
-	sctx->state[6] = SHA384_H6;
-	sctx->state[7] = SHA384_H7;
-
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA512_DIGEST_SIZE];
-
-	sha512_neon_final(desc, D);
-
-	memcpy(hash, D, SHA384_DIGEST_SIZE);
-	memzero_explicit(D, SHA512_DIGEST_SIZE);
-
-	return 0;
-}
-
-static struct shash_alg algs[] = { {
-	.digestsize	=	SHA512_DIGEST_SIZE,
-	.init		=	sha512_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha512_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha512",
-		.cra_driver_name =	"sha512-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA512_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-},  {
-	.digestsize	=	SHA384_DIGEST_SIZE,
-	.init		=	sha384_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha384_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha384",
-		.cra_driver_name =	"sha384-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA384_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init sha512_neon_mod_init(void)
-{
-	if (!cpu_has_neon())
-		return -ENODEV;
-
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha512_neon_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha512_neon_mod_init);
-module_exit(sha512_neon_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
-
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6b8c1c..6c2327e1c732 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_mb__before_atomic()	smp_mb()
 #define smp_mb__after_atomic()	smp_mb()
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 8e3fcb924db6..2ef282f96651 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -25,7 +25,7 @@ struct dma_iommu_mapping {
 };
 
 struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size);
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size);
 
 void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping);
 
diff --git a/arch/arm/include/asm/edac.h b/arch/arm/include/asm/edac.h
index 0df7a2c1fc3d..5189fa819b60 100644
--- a/arch/arm/include/asm/edac.h
+++ b/arch/arm/include/asm/edac.h
@@ -18,11 +18,12 @@
 #define ASM_EDAC_H
 /*
  * ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
  * ECC scrubbing.  It reads memory and then writes back the original
  * value, allowing the hardware to detect and correct memory errors.
  */
-static inline void atomic_scrub(void *va, u32 size)
+
+static inline void edac_atomic_scrub(void *va, u32 size)
 {
 #if __LINUX_ARM_ARCH__ >= 6
 	unsigned int *virt_addr = va;
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 4e78065a16aa..5eed82809d82 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	preempt_disable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+	preempt_enable();
+
 	return ret;
 }
 
@@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+#ifndef CONFIG_SMP
+	preempt_disable();
+#endif
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
+#ifndef CONFIG_SMP
+	preempt_enable();
+#endif
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 1f1b1cd112f3..31bb7dccb971 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -53,10 +53,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index db58deb00aa7..1b7677d1e5e1 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -336,6 +336,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
 #define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
 #define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
+#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
 #define iounmap				__arm_iounmap
 
 /*
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 25410b2d8bc1..194c91b610ff 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -23,7 +23,7 @@
 #define c0_MPIDR	1	/* MultiProcessor ID Register */
 #define c0_CSSELR	2	/* Cache Size Selection Register */
 #define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxilliary Control Register */
+#define c1_ACTLR	4	/* Auxiliary Control Register */
 #define c1_CPACR	5	/* Coprocessor Access Control */
 #define c2_TTBR0	6	/* Translation Table Base Register 0 */
 #define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d71607c16601..e896d2c196e6 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -218,11 +218,6 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
-	BUG_ON(vgic->type != VGIC_V2);
-}
-
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
diff --git a/arch/arm/include/asm/mm-arch-hooks.h b/arch/arm/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..7056660c7cc4
--- /dev/null
+++ b/arch/arm/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARM_MM_ARCH_HOOKS_H
+#define _ASM_ARM_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARM_MM_ARCH_HOOKS_H */
diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h
index 585dc33a7a24..a5635444ca41 100644
--- a/arch/arm/include/asm/pci.h
+++ b/arch/arm/include/asm/pci.h
@@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                                enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 2fe85fff5cca..370f7a732900 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 2f7e6ff67d51..0b579b2f4e0e 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -110,5 +110,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 bool xen_arch_need_swiotlb(struct device *dev,
 			   unsigned long pfn,
 			   unsigned long mfn);
+unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21fa032..4e7f40c577e6 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq				@ disable interrupts
-	ldr	r1, [tsk, #TI_FLAGS]
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return
 	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
 	asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 91c7ba182dcd..3b8c2833c537 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -303,9 +303,15 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 
 static int of_pmu_irq_cfg(struct platform_device *pdev)
 {
-	int i;
-	int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+	int i, irq;
+	int *irqs;
 
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
 		return -ENOMEM;
 
@@ -317,7 +323,7 @@ static int of_pmu_irq_cfg(struct platform_device *pdev)
 				      i);
 		if (!dn) {
 			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
-				of_node_full_name(dn), i);
+				of_node_full_name(pdev->dev.of_node), i);
 			break;
 		}
 
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index f1f79d104309..bfb915d05665 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	select MMU_NOTIFIER
+	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 139e46c08b6e..c5eef02c52ba 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 
 KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d9631ecddd56..bc738d2b8392 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
@@ -532,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_vgic_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 
+		preempt_disable();
 		local_irq_disable();
 
 		/*
@@ -544,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
 			local_irq_enable();
+			preempt_enable();
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			continue;
@@ -553,14 +554,16 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		kvm_guest_enter();
+		__kvm_guest_enter();
 		vcpu->mode = IN_GUEST_MODE;
 
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
-		kvm_guest_exit();
-		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		/*
+		 * Back from guest
+		 *************************************************************/
+
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
@@ -574,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();
 
 		/*
-		 * Back from guest
-		 *************************************************************/
+		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * that if a timer interrupt hits while running the guest we
+		 * account that tick as being spent in the guest.  We enable
+		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preempted we make sure ticks after that is not counted as
+		 * guest time.
+		 */
+		kvm_guest_exit();
+		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		preempt_enable();
+
 
 		kvm_timer_sync_hwstate(vcpu);
 		kvm_vgic_sync_hwstate(vcpu);
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index 79caf79b304a..f7db3a5d80e3 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -170,13 +170,9 @@ __kvm_vcpu_return:
 	@ Don't trap coprocessor accesses for host kernel
 	set_hstr vmexit
 	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
 
 #ifdef CONFIG_VFPv3
-	@ Save floating point registers we if let guest use them.
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	bne	after_vfp_restore
-
 	@ Switch VFP/NEON hardware state to the host's
 	add	r7, vcpu, #VCPU_VFP_GUEST
 	store_vfp_state r7
@@ -188,6 +184,8 @@ after_vfp_restore:
 	@ Restore FPEXC_EN which we clobbered on entry
 	pop	{r2}
 	VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
 #endif
 
 	@ Reset Hyp-role
@@ -483,7 +481,7 @@ switch_to_guest_vfp:
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
 
 	@ Switch VFP/NEON hardware state to the guest's
 	add	r7, r0, #VCPU_VFP_HOST
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 35e4a3a0c476..702740d37465 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -412,7 +412,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r11, vcpu, #VCPU_VGIC_CPU
 
 	/* Save all interesting registers */
-	ldr	r3, [r2, #GICH_HCR]
 	ldr	r4, [r2, #GICH_VMCR]
 	ldr	r5, [r2, #GICH_MISR]
 	ldr	r6, [r2, #GICH_EISR0]
@@ -420,7 +419,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	ldr	r8, [r2, #GICH_ELRSR0]
 	ldr	r9, [r2, #GICH_ELRSR1]
 	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r3, r3	)
 ARM_BE8(rev	r4, r4	)
 ARM_BE8(rev	r5, r5	)
 ARM_BE8(rev	r6, r6	)
@@ -429,7 +427,6 @@ ARM_BE8(rev	r8, r8	)
 ARM_BE8(rev	r9, r9	)
 ARM_BE8(rev	r10, r10	)
 
-	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
 #ifdef CONFIG_CPU_ENDIAN_BE8
@@ -591,8 +588,13 @@ ARM_BE8(rev	r6, r6  )
 .endm
 
 /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
 	mrc	p15, 4, r2, c1, c1, 2
 	ldr	r3, =\mask
 	.if \operation == vmentry
@@ -601,6 +603,17 @@ ARM_BE8(rev	r6, r6  )
 	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
 	.endif
 	mcr	p15, 4, r3, c1, c1, 2
+	.if \operation != vmentry
+	.if \operation == vmexit
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	beq	1f
+	.endif
+	isb
+	.if \label != none
+	b	\label
+	.endif
+1:
+	.endif
 .endm
 
 /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 1d5accbd3dcf..7b4201294187 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 * work.  This is not used by the hardware and we have no
 		 * alignment requirement for this allocation.
 		 */
-		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
-				       GFP_KERNEL | __GFP_ZERO);
+		pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+				GFP_KERNEL | __GFP_ZERO);
 
 		if (!pgd) {
 			kvm_free_hwpgd(hwpgd);
@@ -1155,7 +1155,8 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
  */
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot)
 {
-	struct kvm_memory_slot *memslot = id_to_memslot(kvm->memslots, slot);
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
 	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
 	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
 
@@ -1718,8 +1719,9 @@ out:
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   const struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	/*
@@ -1733,7 +1735,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
 	hva_t hva = mem->userspace_addr;
@@ -1838,7 +1840,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return 0;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
 {
 }
 
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 02fa8eff6ae1..4b94b513168d 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -24,6 +24,8 @@
 #include <asm/kvm_psci.h>
 #include <asm/kvm_host.h>
 
+#include <uapi/linux/psci.h>
+
 /*
  * This is an implementation of the Power State Coordination Interface
  * as described in ARM document number ARM DEN 0022A.
@@ -230,10 +232,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
-	case PSCI_0_2_FN_MIGRATE:
-	case PSCI_0_2_FN64_MIGRATE:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 		/*
 		 * Trusted OS is MP hence does not require migration
@@ -242,10 +240,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 */
 		val = PSCI_0_2_TOS_MP;
 		break;
-	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
-	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_SYSTEM_OFF:
 		kvm_psci_system_off(vcpu);
 		/*
@@ -271,7 +265,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		ret = 0;
 		break;
 	default:
-		return -EINVAL;
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
@@ -291,12 +286,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
-	case KVM_PSCI_FN_CPU_SUSPEND:
-	case KVM_PSCI_FN_MIGRATE:
+	default:
 		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S
index 947567ff67f9..af2267f6a529 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib/lib1funcs.S
@@ -167,7 +167,7 @@ Boston, MA 02111-1307, USA.  */
 
 #endif
 
-	@ Perform all needed substractions to keep only the reminder.
+	@ Perform all needed subtractions to keep only the reminder.
 	@ Do comparisons in batch of 4 first.
 	subs	\order, \order, #3		@ yes, 3 is intended here
 	blt	2f
@@ -189,7 +189,7 @@ Boston, MA 02111-1307, USA.  */
 	teqne	\dividend, #0
 	beq	5f
 
-	@ Either 1, 2 or 3 comparison/substractions are left.
+	@ Either 1, 2 or 3 comparison/subtractions are left.
 2:	cmn	\order, #2
 	blt	4f
 	beq	3f
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 45ce065e7170..3b8740c083c4 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -11,6 +11,7 @@
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
  */
+#include <linux/clkdev.h>
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/clk.h>
diff --git a/arch/arm/mach-davinci/pm_domain.c b/arch/arm/mach-davinci/pm_domain.c
index 641edc313938..78eac2c0c146 100644
--- a/arch/arm/mach-davinci/pm_domain.c
+++ b/arch/arm/mach-davinci/pm_domain.c
@@ -14,39 +14,9 @@
 #include <linux/pm_clock.h>
 #include <linux/platform_device.h>
 
-#ifdef CONFIG_PM
-static int davinci_pm_runtime_suspend(struct device *dev)
-{
-	int ret;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	ret = pm_generic_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	ret = pm_clk_suspend(dev);
-	if (ret) {
-		pm_generic_runtime_resume(dev);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int davinci_pm_runtime_resume(struct device *dev)
-{
-	dev_dbg(dev, "%s\n", __func__);
-
-	pm_clk_resume(dev);
-	return pm_generic_runtime_resume(dev);
-}
-#endif
-
 static struct dev_pm_domain davinci_pm_domain = {
 	.ops = {
-		SET_RUNTIME_PM_OPS(davinci_pm_runtime_suspend,
-				   davinci_pm_runtime_resume, NULL)
+		USE_PM_CLK_RUNTIME_OPS
 		USE_PLATFORM_PM_SLEEP_OPS
 	},
 };
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index acd5b560b728..5f5cd562c593 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -159,6 +159,8 @@ extern void exynos_enter_aftr(void);
 
 extern struct cpuidle_exynos_data cpuidle_coupled_exynos_data;
 
+extern void exynos_set_delayed_reset_assertion(bool enable);
+
 extern void s5p_init_cpu(void __iomem *cpuid_addr);
 extern unsigned int samsung_rev(void);
 extern void __iomem *cpu_boot_reg_base(void);
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index bcde0dd668df..5917a30eee33 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -167,6 +167,33 @@ static void __init exynos_init_io(void)
 }
 
 /*
+ * Set or clear the USE_DELAYED_RESET_ASSERTION option. Used by smp code
+ * and suspend.
+ *
+ * This is necessary only on Exynos4 SoCs. When system is running
+ * USE_DELAYED_RESET_ASSERTION should be set so the ARM CLK clock down
+ * feature could properly detect global idle state when secondary CPU is
+ * powered down.
+ *
+ * However this should not be set when such system is going into suspend.
+ */
+void exynos_set_delayed_reset_assertion(bool enable)
+{
+	if (of_machine_is_compatible("samsung,exynos4")) {
+		unsigned int tmp, core_id;
+
+		for (core_id = 0; core_id < num_possible_cpus(); core_id++) {
+			tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id));
+			if (enable)
+				tmp |= S5P_USE_DELAYED_RESET_ASSERTION;
+			else
+				tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION);
+			pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id));
+		}
+	}
+}
+
+/*
  * Apparently, these SoCs are not able to wake-up from suspend using
  * the PMU. Too bad. Should they suddenly become capable of such a
  * feat, the matches below should be moved to suspend.c.
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index ebd135bb0995..a825bca2a2b6 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -34,30 +34,6 @@
 
 extern void exynos4_secondary_startup(void);
 
-/*
- * Set or clear the USE_DELAYED_RESET_ASSERTION option, set on Exynos4 SoCs
- * during hot-(un)plugging CPUx.
- *
- * The feature can be cleared safely during first boot of secondary CPU.
- *
- * Exynos4 SoCs require setting USE_DELAYED_RESET_ASSERTION during powering
- * down a CPU so the CPU idle clock down feature could properly detect global
- * idle state when CPUx is off.
- */
-static void exynos_set_delayed_reset_assertion(u32 core_id, bool enable)
-{
-	if (soc_is_exynos4()) {
-		unsigned int tmp;
-
-		tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id));
-		if (enable)
-			tmp |= S5P_USE_DELAYED_RESET_ASSERTION;
-		else
-			tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION);
-		pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id));
-	}
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 static inline void cpu_leave_lowpower(u32 core_id)
 {
@@ -73,8 +49,6 @@ static inline void cpu_leave_lowpower(u32 core_id)
 	  : "=&r" (v)
 	  : "Ir" (CR_C), "Ir" (0x40)
 	  : "cc");
-
-	 exynos_set_delayed_reset_assertion(core_id, false);
 }
 
 static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
@@ -87,14 +61,6 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 		/* Turn the CPU off on next WFI instruction. */
 		exynos_cpu_power_down(core_id);
 
-		/*
-		 * Exynos4 SoCs require setting
-		 * USE_DELAYED_RESET_ASSERTION so the CPU idle
-		 * clock down feature could properly detect
-		 * global idle state when CPUx is off.
-		 */
-		exynos_set_delayed_reset_assertion(core_id, true);
-
 		wfi();
 
 		if (pen_release == core_id) {
@@ -371,9 +337,6 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		udelay(10);
 	}
 
-	/* No harm if this is called during first boot of secondary CPU */
-	exynos_set_delayed_reset_assertion(core_id, false);
-
 	/*
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
@@ -420,6 +383,8 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 
 	exynos_sysram_init();
 
+	exynos_set_delayed_reset_assertion(true);
+
 	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(scu_base_addr());
 
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index cbe56b35aea0..a9686535f9ed 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -188,7 +188,7 @@ no_clk:
 		args.np = np;
 		args.args_count = 0;
 		child_domain = of_genpd_get_from_provider(&args);
-		if (!child_domain)
+		if (IS_ERR(child_domain))
 			continue;
 
 		if (of_parse_phandle_with_args(np, "power-domains",
@@ -196,7 +196,7 @@ no_clk:
 			continue;
 
 		parent_domain = of_genpd_get_from_provider(&args);
-		if (!parent_domain)
+		if (IS_ERR(parent_domain))
 			continue;
 
 		if (pm_genpd_add_subdomain(parent_domain, child_domain))
diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index 3e6aea7f83af..7d23ce04cad5 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -87,8 +87,8 @@ static unsigned int exynos_pmu_spare3;
 static u32 exynos_irqwake_intmask = 0xffffffff;
 
 static const struct exynos_wkup_irq exynos3250_wkup_irq[] = {
-	{ 105, BIT(1) }, /* RTC alarm */
-	{ 106, BIT(2) }, /* RTC tick */
+	{ 73, BIT(1) }, /* RTC alarm */
+	{ 74, BIT(2) }, /* RTC tick */
 	{ /* sentinel */ },
 };
 
@@ -342,6 +342,8 @@ static void exynos_pm_enter_sleep_mode(void)
 
 static void exynos_pm_prepare(void)
 {
+	exynos_set_delayed_reset_assertion(false);
+
 	/* Set wake-up mask registers */
 	exynos_pm_set_wakeup_mask();
 
@@ -482,6 +484,7 @@ early_wakeup:
 
 	/* Clear SLEEP mode set in INFORM1 */
 	pmu_raw_writel(0x0, S5P_INFORM1);
+	exynos_set_delayed_reset_assertion(true);
 }
 
 static void exynos3250_pm_resume(void)
@@ -723,8 +726,10 @@ void __init exynos_pm_init(void)
 		return;
 	}
 
-	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL)))
+	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
 		pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+		return;
+	}
 
 	pm_data = (const struct exynos_pm_data *) match->data;
 
diff --git a/arch/arm/mach-gemini/common.h b/arch/arm/mach-gemini/common.h
index 38a45260a7c8..dd883698ff7e 100644
--- a/arch/arm/mach-gemini/common.h
+++ b/arch/arm/mach-gemini/common.h
@@ -12,6 +12,8 @@
 #ifndef __GEMINI_COMMON_H__
 #define __GEMINI_COMMON_H__
 
+#include <linux/reboot.h>
+
 struct mtd_partition;
 
 extern void gemini_map_io(void);
@@ -26,6 +28,6 @@ extern int platform_register_pflash(unsigned int size,
 				    struct mtd_partition *parts,
 				    unsigned int nr_parts);
 
-extern void gemini_restart(char mode, const char *cmd);
+extern void gemini_restart(enum reboot_mode mode, const char *cmd);
 
 #endif /* __GEMINI_COMMON_H__ */
diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c
index f8cb5710d6ee..3292f2e6ed6f 100644
--- a/arch/arm/mach-gemini/gpio.c
+++ b/arch/arm/mach-gemini/gpio.c
@@ -223,8 +223,8 @@ void __init gemini_gpio_init(void)
 			set_irq_flags(j, IRQF_VALID);
 		}
 
-		irq_set_chained_handler(IRQ_GPIO(i), gpio_irq_handler);
-		irq_set_handler_data(IRQ_GPIO(i), (void *)i);
+		irq_set_chained_handler_and_data(IRQ_GPIO(i), gpio_irq_handler,
+						 (void *)i);
 	}
 
 	BUG_ON(gpiochip_add(&gemini_gpio_chip));
diff --git a/arch/arm/mach-gemini/reset.c b/arch/arm/mach-gemini/reset.c
index b26659759e27..21a6d6d4f9c4 100644
--- a/arch/arm/mach-gemini/reset.c
+++ b/arch/arm/mach-gemini/reset.c
@@ -14,7 +14,9 @@
 #include <mach/hardware.h>
 #include <mach/global_reg.h>
 
-void gemini_restart(char mode, const char *cmd)
+#include "common.h"
+
+void gemini_restart(enum reboot_mode mode, const char *cmd)
 {
 	__raw_writel(RESET_GLOBAL | RESET_CPU1,
 		     IO_ADDRESS(GEMINI_GLOBAL_BASE) + GLOBAL_RESET);
diff --git a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c
index fb8d4a2ad48c..a5edd7d60266 100644
--- a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c
+++ b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Pengutronix, Wolfram Sang <w.sang@pengutronix.de>
+ * Copyright (C) 2010 Pengutronix, Wolfram Sang <kernel@pengutronix.de>
  *
  * This program is free software; you can redistribute it and/or modify it under
  * the terms of the GNU General Public License version 2 as published by the
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 4d60005e9277..6d0893a3828e 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -280,9 +280,15 @@ void __init imx_gpc_check_dt(void)
 	struct device_node *np;
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc");
-	if (WARN_ON(!np ||
-		    !of_find_property(np, "interrupt-controller", NULL)))
-		pr_warn("Outdated DT detected, system is about to crash!!!\n");
+	if (WARN_ON(!np))
+		return;
+
+	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
+		pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+
+		/* map GPC, so that at least CPUidle and WARs keep working */
+		gpc_base = of_iomap(np, 0);
+	}
 }
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS
@@ -443,6 +449,10 @@ static int imx_gpc_probe(struct platform_device *pdev)
 	struct regulator *pu_reg;
 	int ret;
 
+	/* bail out if DT too old and doesn't provide the necessary info */
+	if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells"))
+		return 0;
+
 	pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
 	if (PTR_ERR(pu_reg) == -ENODEV)
 		pu_reg = NULL;
diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c
index 41bebfd296dc..edea697e8253 100644
--- a/arch/arm/mach-keystone/pm_domain.c
+++ b/arch/arm/mach-keystone/pm_domain.c
@@ -19,40 +19,9 @@
 #include <linux/clk-provider.h>
 #include <linux/of.h>
 
-#ifdef CONFIG_PM
-static int keystone_pm_runtime_suspend(struct device *dev)
-{
-	int ret;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	ret = pm_generic_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	ret = pm_clk_suspend(dev);
-	if (ret) {
-		pm_generic_runtime_resume(dev);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int keystone_pm_runtime_resume(struct device *dev)
-{
-	dev_dbg(dev, "%s\n", __func__);
-
-	pm_clk_resume(dev);
-
-	return pm_generic_runtime_resume(dev);
-}
-#endif
-
 static struct dev_pm_domain keystone_pm_domain = {
 	.ops = {
-		SET_RUNTIME_PM_OPS(keystone_pm_runtime_suspend,
-				   keystone_pm_runtime_resume, NULL)
+		USE_PM_CLK_RUNTIME_OPS
 		USE_PLATFORM_PM_SLEEP_OPS
 	},
 };
diff --git a/arch/arm/mach-lpc32xx/clock.c b/arch/arm/mach-lpc32xx/clock.c
index dd5d6f532e8c..661c8f4b2310 100644
--- a/arch/arm/mach-lpc32xx/clock.c
+++ b/arch/arm/mach-lpc32xx/clock.c
@@ -1238,10 +1238,7 @@ static struct clk_lookup lookups[] = {
 
 static int __init clk_init(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	/*
 	 * Setup muxed SYSCLK for HCLK PLL base -this selects the
diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c
index 85089d821982..3bc59390a943 100644
--- a/arch/arm/mach-omap1/board-nokia770.c
+++ b/arch/arm/mach-omap1/board-nokia770.c
@@ -7,6 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/clkdev.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/kernel.h>
@@ -14,7 +15,6 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/input.h>
-#include <linux/clk.h>
 #include <linux/omapfb.h>
 
 #include <linux/spi/spi.h>
diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c
index c40e209de65c..667c1637ff91 100644
--- a/arch/arm/mach-omap1/pm_bus.c
+++ b/arch/arm/mach-omap1/pm_bus.c
@@ -21,48 +21,15 @@
 
 #include "soc.h"
 
-#ifdef CONFIG_PM
-static int omap1_pm_runtime_suspend(struct device *dev)
-{
-	int ret;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	ret = pm_generic_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	ret = pm_clk_suspend(dev);
-	if (ret) {
-		pm_generic_runtime_resume(dev);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int omap1_pm_runtime_resume(struct device *dev)
-{
-	dev_dbg(dev, "%s\n", __func__);
-
-	pm_clk_resume(dev);
-	return pm_generic_runtime_resume(dev);
-}
-
 static struct dev_pm_domain default_pm_domain = {
 	.ops = {
-		.runtime_suspend = omap1_pm_runtime_suspend,
-		.runtime_resume = omap1_pm_runtime_resume,
+		USE_PM_CLK_RUNTIME_OPS
 		USE_PLATFORM_PM_SLEEP_OPS
 	},
 };
-#define OMAP1_PM_DOMAIN (&default_pm_domain)
-#else
-#define OMAP1_PM_DOMAIN NULL
-#endif /* CONFIG_PM */
 
 static struct pm_clk_notifier_block platform_bus_notifier = {
-	.pm_domain = OMAP1_PM_DOMAIN,
+	.pm_domain = &default_pm_domain,
 	.con_ids = { "ick", "fck", NULL, },
 };
 
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index 85e0b0c06718..b64d717bfab6 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -232,14 +232,12 @@ void omap2xxx_clkt_vps_init(void)
 	struct clk_hw_omap *hw = NULL;
 	struct clk *clk;
 	const char *parent_name = "mpu_ck";
-	struct clk_lookup *lookup = NULL;
 
 	omap2xxx_clkt_vps_late_init();
 	omap2xxx_clkt_vps_check_bootloader_rates();
 
 	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
-	lookup = kzalloc(sizeof(*lookup), GFP_KERNEL);
-	if (!hw || !lookup)
+	if (!hw)
 		goto cleanup;
 	init.name = "virt_prcm_set";
 	init.ops = &virt_prcm_set_ops;
@@ -249,15 +247,9 @@ void omap2xxx_clkt_vps_init(void)
 	hw->hw.init = &init;
 
 	clk = clk_register(NULL, &hw->hw);
-
-	lookup->dev_id = NULL;
-	lookup->con_id = "cpufreq_ck";
-	lookup->clk = clk;
-
-	clkdev_add(lookup);
+	clkdev_create(clk, "cpufreq_ck", NULL);
 	return;
 cleanup:
 	kfree(hw);
-	kfree(lookup);
 }
 #endif
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index f492ae147c6a..6ab13d18c636 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -287,6 +287,8 @@ static enum omapdss_version __init omap_display_get_version(void)
 		return OMAPDSS_VER_OMAP5;
 	else if (soc_is_am43xx())
 		return OMAPDSS_VER_AM43xx;
+	else if (soc_is_dra7xx())
+		return OMAPDSS_VER_DRA7xx;
 	else
 		return OMAPDSS_VER_UNKNOWN;
 }
@@ -568,25 +570,25 @@ void __init omapdss_early_init_of(void)
 
 }
 
+static const char * const omapdss_compat_names[] __initconst = {
+	"ti,omap2-dss",
+	"ti,omap3-dss",
+	"ti,omap4-dss",
+	"ti,omap5-dss",
+	"ti,dra7-dss",
+};
+
 struct device_node * __init omapdss_find_dss_of_node(void)
 {
 	struct device_node *node;
+	int i;
 
-	node = of_find_compatible_node(NULL, NULL, "ti,omap2-dss");
-	if (node)
-		return node;
-
-	node = of_find_compatible_node(NULL, NULL, "ti,omap3-dss");
-	if (node)
-		return node;
-
-	node = of_find_compatible_node(NULL, NULL, "ti,omap4-dss");
-	if (node)
-		return node;
-
-	node = of_find_compatible_node(NULL, NULL, "ti,omap5-dss");
-	if (node)
-		return node;
+	for (i = 0; i < ARRAY_SIZE(omapdss_compat_names); ++i) {
+		node = of_find_compatible_node(NULL, NULL,
+			omapdss_compat_names[i]);
+		if (node)
+			return node;
+	}
 
 	return NULL;
 }
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 166b18f515a2..e417f7fcb2ba 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -47,7 +47,7 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
 		       const char *clk_name)
 {
 	struct clk *r;
-	struct clk_lookup *l;
+	int rc;
 
 	if (!clk_alias || !clk_name)
 		return;
@@ -62,21 +62,15 @@ static void _add_clkdev(struct omap_device *od, const char *clk_alias,
 		return;
 	}
 
-	r = clk_get(NULL, clk_name);
-	if (IS_ERR(r)) {
-		dev_err(&od->pdev->dev,
-			"clk_get for %s failed\n", clk_name);
-		return;
+	rc = clk_add_alias(clk_alias, dev_name(&od->pdev->dev), clk_name, NULL);
+	if (rc) {
+		if (rc == -ENODEV || rc == -ENOMEM)
+			dev_err(&od->pdev->dev,
+				"clkdev_alloc for %s failed\n", clk_alias);
+		else
+			dev_err(&od->pdev->dev,
+				"clk_get for %s failed\n", clk_name);
 	}
-
-	l = clkdev_alloc(r, clk_alias, dev_name(&od->pdev->dev));
-	if (!l) {
-		dev_err(&od->pdev->dev,
-			"clkdev_alloc for %s failed\n", clk_alias);
-		return;
-	}
-
-	clkdev_add(l);
 }
 
 /**
@@ -688,11 +682,8 @@ struct dev_pm_domain omap_device_pm_domain = {
 		SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume,
 				   NULL)
 		USE_PLATFORM_PM_SLEEP_OPS
-		.suspend_noirq = _od_suspend_noirq,
-		.resume_noirq = _od_resume_noirq,
-		.freeze_noirq = _od_suspend_noirq,
-		.thaw_noirq = _od_resume_noirq,
-		.restore_noirq = _od_resume_noirq,
+		SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(_od_suspend_noirq,
+					      _od_resume_noirq)
 	}
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 355b08936871..752969ff9de0 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -171,6 +171,12 @@
  */
 #define LINKS_PER_OCP_IF		2
 
+/*
+ * Address offset (in bytes) between the reset control and the reset
+ * status registers: 4 bytes on OMAP4
+ */
+#define OMAP4_RST_CTRL_ST_OFFSET	4
+
 /**
  * struct omap_hwmod_soc_ops - fn ptrs for some SoC-specific operations
  * @enable_module: function to enable a module (via MODULEMODE)
@@ -3016,10 +3022,12 @@ static int _omap4_deassert_hardreset(struct omap_hwmod *oh,
 	if (ohri->st_shift)
 		pr_err("omap_hwmod: %s: %s: hwmod data error: OMAP4 does not support st_shift\n",
 		       oh->name, ohri->name);
-	return omap_prm_deassert_hardreset(ohri->rst_shift, 0,
+	return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->rst_shift,
 					   oh->clkdm->pwrdm.ptr->prcm_partition,
 					   oh->clkdm->pwrdm.ptr->prcm_offs,
-					   oh->prcm.omap4.rstctrl_offs, 0);
+					   oh->prcm.omap4.rstctrl_offs,
+					   oh->prcm.omap4.rstctrl_offs +
+					   OMAP4_RST_CTRL_ST_OFFSET);
 }
 
 /**
@@ -3048,27 +3056,6 @@ static int _omap4_is_hardreset_asserted(struct omap_hwmod *oh,
 }
 
 /**
- * _am33xx_assert_hardreset - call AM33XX PRM hardreset fn with hwmod args
- * @oh: struct omap_hwmod * to assert hardreset
- * @ohri: hardreset line data
- *
- * Call am33xx_prminst_assert_hardreset() with parameters extracted
- * from the hwmod @oh and the hardreset line data @ohri.  Only
- * intended for use as an soc_ops function pointer.  Passes along the
- * return value from am33xx_prminst_assert_hardreset().  XXX This
- * function is scheduled for removal when the PRM code is moved into
- * drivers/.
- */
-static int _am33xx_assert_hardreset(struct omap_hwmod *oh,
-				   struct omap_hwmod_rst_info *ohri)
-
-{
-	return omap_prm_assert_hardreset(ohri->rst_shift, 0,
-					 oh->clkdm->pwrdm.ptr->prcm_offs,
-					 oh->prcm.omap4.rstctrl_offs);
-}
-
-/**
  * _am33xx_deassert_hardreset - call AM33XX PRM hardreset fn with hwmod args
  * @oh: struct omap_hwmod * to deassert hardreset
  * @ohri: hardreset line data
@@ -3083,32 +3070,13 @@ static int _am33xx_assert_hardreset(struct omap_hwmod *oh,
 static int _am33xx_deassert_hardreset(struct omap_hwmod *oh,
 				     struct omap_hwmod_rst_info *ohri)
 {
-	return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift, 0,
+	return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift,
+					   oh->clkdm->pwrdm.ptr->prcm_partition,
 					   oh->clkdm->pwrdm.ptr->prcm_offs,
 					   oh->prcm.omap4.rstctrl_offs,
 					   oh->prcm.omap4.rstst_offs);
 }
 
-/**
- * _am33xx_is_hardreset_asserted - call AM33XX PRM hardreset fn with hwmod args
- * @oh: struct omap_hwmod * to test hardreset
- * @ohri: hardreset line data
- *
- * Call am33xx_prminst_is_hardreset_asserted() with parameters
- * extracted from the hwmod @oh and the hardreset line data @ohri.
- * Only intended for use as an soc_ops function pointer.  Passes along
- * the return value from am33xx_prminst_is_hardreset_asserted().  XXX
- * This function is scheduled for removal when the PRM code is moved
- * into drivers/.
- */
-static int _am33xx_is_hardreset_asserted(struct omap_hwmod *oh,
-					struct omap_hwmod_rst_info *ohri)
-{
-	return omap_prm_is_hardreset_asserted(ohri->rst_shift, 0,
-					      oh->clkdm->pwrdm.ptr->prcm_offs,
-					      oh->prcm.omap4.rstctrl_offs);
-}
-
 /* Public functions */
 
 u32 omap_hwmod_read(struct omap_hwmod *oh, u16 reg_offs)
@@ -3908,21 +3876,13 @@ void __init omap_hwmod_init(void)
 		soc_ops.init_clkdm = _init_clkdm;
 		soc_ops.update_context_lost = _omap4_update_context_lost;
 		soc_ops.get_context_lost = _omap4_get_context_lost;
-	} else if (soc_is_am43xx()) {
+	} else if (cpu_is_ti816x() || soc_is_am33xx() || soc_is_am43xx()) {
 		soc_ops.enable_module = _omap4_enable_module;
 		soc_ops.disable_module = _omap4_disable_module;
 		soc_ops.wait_target_ready = _omap4_wait_target_ready;
 		soc_ops.assert_hardreset = _omap4_assert_hardreset;
-		soc_ops.deassert_hardreset = _omap4_deassert_hardreset;
-		soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
-		soc_ops.init_clkdm = _init_clkdm;
-	} else if (cpu_is_ti816x() || soc_is_am33xx()) {
-		soc_ops.enable_module = _omap4_enable_module;
-		soc_ops.disable_module = _omap4_disable_module;
-		soc_ops.wait_target_ready = _omap4_wait_target_ready;
-		soc_ops.assert_hardreset = _am33xx_assert_hardreset;
 		soc_ops.deassert_hardreset = _am33xx_deassert_hardreset;
-		soc_ops.is_hardreset_asserted = _am33xx_is_hardreset_asserted;
+		soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
 		soc_ops.init_clkdm = _init_clkdm;
 	} else {
 		WARN(1, "omap_hwmod: unknown SoC type\n");
diff --git a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
index e2223148ba4d..17e8004fc20f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c
@@ -544,6 +544,44 @@ static struct omap_hwmod am43xx_hdq1w_hwmod = {
 	},
 };
 
+static struct omap_hwmod_class_sysconfig am43xx_vpfe_sysc = {
+	.rev_offs       = 0x0,
+	.sysc_offs      = 0x104,
+	.sysc_flags     = SYSC_HAS_MIDLEMODE | SYSC_HAS_SIDLEMODE,
+	.idlemodes      = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+				MSTANDBY_FORCE | MSTANDBY_SMART | MSTANDBY_NO),
+	.sysc_fields    = &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class am43xx_vpfe_hwmod_class = {
+	.name           = "vpfe",
+	.sysc           = &am43xx_vpfe_sysc,
+};
+
+static struct omap_hwmod am43xx_vpfe0_hwmod = {
+	.name           = "vpfe0",
+	.class          = &am43xx_vpfe_hwmod_class,
+	.clkdm_name     = "l3s_clkdm",
+	.prcm           = {
+		.omap4  = {
+			.modulemode     = MODULEMODE_SWCTRL,
+			.clkctrl_offs   = AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET,
+		},
+	},
+};
+
+static struct omap_hwmod am43xx_vpfe1_hwmod = {
+	.name           = "vpfe1",
+	.class          = &am43xx_vpfe_hwmod_class,
+	.clkdm_name     = "l3s_clkdm",
+	.prcm           = {
+		.omap4  = {
+			.modulemode     = MODULEMODE_SWCTRL,
+			.clkctrl_offs   = AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET,
+		},
+	},
+};
+
 /* Interfaces */
 static struct omap_hwmod_ocp_if am43xx_l3_main__l4_hs = {
 	.master		= &am33xx_l3_main_hwmod,
@@ -825,6 +863,34 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__hdq1w = {
 	.user           = OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+static struct omap_hwmod_ocp_if am43xx_l3__vpfe0 = {
+	.master         = &am43xx_vpfe0_hwmod,
+	.slave          = &am33xx_l3_main_hwmod,
+	.clk            = "l3_gclk",
+	.user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l3__vpfe1 = {
+	.master         = &am43xx_vpfe1_hwmod,
+	.slave          = &am33xx_l3_main_hwmod,
+	.clk            = "l3_gclk",
+	.user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe0 = {
+	.master         = &am33xx_l4_ls_hwmod,
+	.slave          = &am43xx_vpfe0_hwmod,
+	.clk            = "l4ls_gclk",
+	.user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe1 = {
+	.master         = &am33xx_l4_ls_hwmod,
+	.slave          = &am43xx_vpfe1_hwmod,
+	.clk            = "l4ls_gclk",
+	.user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am33xx_l4_wkup__synctimer,
 	&am43xx_l4_ls__timer8,
@@ -925,6 +991,10 @@ static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = {
 	&am43xx_l4_ls__dss_dispc,
 	&am43xx_l4_ls__dss_rfbi,
 	&am43xx_l4_ls__hdq1w,
+	&am43xx_l3__vpfe0,
+	&am43xx_l3__vpfe1,
+	&am43xx_l4_ls__vpfe0,
+	&am43xx_l4_ls__vpfe1,
 	NULL,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 0e64c2fac0b5..9961f95f52ae 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -49,6 +49,27 @@
  */
 
 /*
+ * 'dmm' class
+ * instance(s): dmm
+ */
+static struct omap_hwmod_class dra7xx_dmm_hwmod_class = {
+	.name	= "dmm",
+};
+
+/* dmm */
+static struct omap_hwmod dra7xx_dmm_hwmod = {
+	.name		= "dmm",
+	.class		= &dra7xx_dmm_hwmod_class,
+	.clkdm_name	= "emif_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_EMIF_DMM_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_EMIF_DMM_CONTEXT_OFFSET,
+		},
+	},
+};
+
+/*
  * 'l3' class
  * instance(s): l3_instr, l3_main_1, l3_main_2
  */
@@ -438,6 +459,7 @@ static struct omap_hwmod_opt_clk dss_opt_clks[] = {
 	{ .role = "video2_clk", .clk = "dss_video2_clk" },
 	{ .role = "video1_clk", .clk = "dss_video1_clk" },
 	{ .role = "hdmi_clk", .clk = "dss_hdmi_clk" },
+	{ .role = "hdcp_clk", .clk = "dss_deshdcp_clk" },
 };
 
 static struct omap_hwmod dra7xx_dss_hwmod = {
@@ -500,6 +522,7 @@ static struct omap_hwmod dra7xx_dss_dispc_hwmod = {
 		},
 	},
 	.dev_attr	= &dss_dispc_dev_attr,
+	.parent_hwmod	= &dra7xx_dss_hwmod,
 };
 
 /*
@@ -541,6 +564,7 @@ static struct omap_hwmod dra7xx_dss_hdmi_hwmod = {
 	},
 	.opt_clks	= dss_hdmi_opt_clks,
 	.opt_clks_cnt	= ARRAY_SIZE(dss_hdmi_opt_clks),
+	.parent_hwmod	= &dra7xx_dss_hwmod,
 };
 
 /*
@@ -2321,6 +2345,14 @@ static struct omap_hwmod dra7xx_wd_timer2_hwmod = {
  * Interfaces
  */
 
+/* l3_main_1 -> dmm */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__dmm = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_dmm_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_SDMA,
+};
+
 /* l3_main_2 -> l3_instr */
 static struct omap_hwmod_ocp_if dra7xx_l3_main_2__l3_instr = {
 	.master		= &dra7xx_l3_main_2_hwmod,
@@ -3289,6 +3321,7 @@ static struct omap_hwmod_ocp_if dra7xx_l4_wkup__wd_timer2 = {
 };
 
 static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
+	&dra7xx_l3_main_1__dmm,
 	&dra7xx_l3_main_2__l3_instr,
 	&dra7xx_l4_cfg__l3_main_1,
 	&dra7xx_mpu__l3_main_1,
diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h
index 48df3b55057e..d0261996db6d 100644
--- a/arch/arm/mach-omap2/prcm43xx.h
+++ b/arch/arm/mach-omap2/prcm43xx.h
@@ -144,5 +144,6 @@
 #define AM43XX_CM_PER_USBPHYOCP2SCP1_CLKCTRL_OFFSET	0x05C0
 #define AM43XX_CM_PER_DSS_CLKCTRL_OFFSET		0x0a20
 #define AM43XX_CM_PER_HDQ1W_CLKCTRL_OFFSET		0x04a0
-
+#define AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET		0x0068
+#define AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET		0x0070
 #endif
diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h
index cbefbd7cfdb5..661d753df584 100644
--- a/arch/arm/mach-omap2/prm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-34xx.h
@@ -112,6 +112,7 @@
 #define OMAP3430_VC_CMD_ONLP_SHIFT			16
 #define OMAP3430_VC_CMD_RET_SHIFT			8
 #define OMAP3430_VC_CMD_OFF_SHIFT			0
+#define OMAP3430_SREN_MASK				(1 << 4)
 #define OMAP3430_HSEN_MASK				(1 << 3)
 #define OMAP3430_MCODE_MASK				(0x7 << 0)
 #define OMAP3430_VALID_MASK				(1 << 24)
diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h
index b1c7a33e00e7..e794828dee55 100644
--- a/arch/arm/mach-omap2/prm-regbits-44xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-44xx.h
@@ -35,6 +35,7 @@
 #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT				1
 #define OMAP4430_GLOBAL_WUEN_MASK					(1 << 16)
 #define OMAP4430_HSMCODE_MASK						(0x7 << 0)
+#define OMAP4430_SRMODEEN_MASK						(1 << 4)
 #define OMAP4430_HSMODEEN_MASK						(1 << 3)
 #define OMAP4430_HSSCLL_SHIFT						24
 #define OMAP4430_ICEPICK_RST_SHIFT					9
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index c4859c4d3646..d0b15dbafa2e 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -87,12 +87,6 @@ u32 omap4_prminst_rmw_inst_reg_bits(u32 mask, u32 bits, u8 part, s16 inst,
 	return v;
 }
 
-/*
- * Address offset (in bytes) between the reset control and the reset
- * status registers: 4 bytes on OMAP4
- */
-#define OMAP4_RST_CTRL_ST_OFFSET		4
-
 /**
  * omap4_prminst_is_hardreset_asserted - read the HW reset line state of
  * submodules contained in the hwmod module
@@ -141,11 +135,11 @@ int omap4_prminst_assert_hardreset(u8 shift, u8 part, s16 inst,
  * omap4_prminst_deassert_hardreset - deassert a submodule hardreset line and
  * wait
  * @shift: register bit shift corresponding to the reset line to deassert
- * @st_shift: status bit offset, not used for OMAP4+
+ * @st_shift: status bit offset corresponding to the reset line
  * @part: PRM partition
  * @inst: PRM instance offset
  * @rstctrl_offs: reset register offset
- * @st_offs: reset status register offset, not used for OMAP4+
+ * @rstst_offs: reset status register offset
  *
  * Some IPs like dsp, ipu or iva contain processors that require an HW
  * reset line to be asserted / deasserted in order to fully enable the
@@ -157,11 +151,11 @@ int omap4_prminst_assert_hardreset(u8 shift, u8 part, s16 inst,
  * of reset, or -EBUSY if the submodule did not exit reset promptly.
  */
 int omap4_prminst_deassert_hardreset(u8 shift, u8 st_shift, u8 part, s16 inst,
-				     u16 rstctrl_offs, u16 st_offs)
+				     u16 rstctrl_offs, u16 rstst_offs)
 {
 	int c;
 	u32 mask = 1 << shift;
-	u16 rstst_offs = rstctrl_offs + OMAP4_RST_CTRL_ST_OFFSET;
+	u32 st_mask = 1 << st_shift;
 
 	/* Check the current status to avoid de-asserting the line twice */
 	if (omap4_prminst_is_hardreset_asserted(shift, part, inst,
@@ -169,13 +163,13 @@ int omap4_prminst_deassert_hardreset(u8 shift, u8 st_shift, u8 part, s16 inst,
 		return -EEXIST;
 
 	/* Clear the reset status by writing 1 to the status bit */
-	omap4_prminst_rmw_inst_reg_bits(0xffffffff, mask, part, inst,
+	omap4_prminst_rmw_inst_reg_bits(0xffffffff, st_mask, part, inst,
 					rstst_offs);
 	/* de-assert the reset control line */
 	omap4_prminst_rmw_inst_reg_bits(mask, 0, part, inst, rstctrl_offs);
 	/* wait the status to be set */
-	omap_test_timeout(omap4_prminst_is_hardreset_asserted(shift, part, inst,
-							      rstst_offs),
+	omap_test_timeout(omap4_prminst_is_hardreset_asserted(st_shift, part,
+							      inst, rstst_offs),
 			  MAX_MODULE_HARDRESET_WAIT, c);
 
 	return (c == MAX_MODULE_HARDRESET_WAIT) ? -EBUSY : 0;
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index d1dedc8195ed..eafd120b53f1 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -203,23 +203,8 @@ save_context_wfi:
 	 */
 	ldr	r1, kernel_flush
 	blx	r1
-	/*
-	 * The kernel doesn't interwork: v7_flush_dcache_all in particluar will
-	 * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled.
-	 * This sequence switches back to ARM.  Note that .align may insert a
-	 * nop: bx pc needs to be word-aligned in order to work.
-	 */
- THUMB(	.thumb		)
- THUMB(	.align		)
- THUMB(	bx	pc	)
- THUMB(	nop		)
-	.arm
-
 	b	omap3_do_wfi
-
-/*
- * Local variables
- */
+ENDPROC(omap34xx_cpu_suspend)
 omap3_do_wfi_sram_addr:
 	.word omap3_do_wfi_sram
 kernel_flush:
@@ -364,10 +349,7 @@ exit_nonoff_modes:
  * ===================================
  */
 	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
-
-/*
- * Local variables
- */
+ENDPROC(omap3_do_wfi)
 sdrc_power:
 	.word	SDRC_POWER_V
 cm_idlest1_core:
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index cef67af9e9b8..cac46d852da1 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -298,14 +298,11 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
-	if (clk_get_parent(timer->fclk) != src) {
-		r = clk_set_parent(timer->fclk, src);
-		if (r < 0) {
-			pr_warn("%s: %s cannot set source\n", __func__,
-				oh->name);
-			clk_put(src);
-			return r;
-		}
+	r = clk_set_parent(timer->fclk, src);
+	if (r < 0) {
+		pr_warn("%s: %s cannot set source\n", __func__, oh->name);
+		clk_put(src);
+		return r;
 	}
 
 	clk_put(src);
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index be9ef834fa81..076fd20d7e5a 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -316,7 +316,8 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm)
 	 * idle. And we can also scale voltages to zero for off-idle.
 	 * Note that no actual voltage scaling during off-idle will
 	 * happen unless the board specific twl4030 PMIC scripts are
-	 * loaded.
+	 * loaded. See also omap_vc_i2c_init for comments regarding
+	 * erratum i531.
 	 */
 	val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET);
 	if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) {
@@ -704,9 +705,16 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm)
 		return;
 	}
 
+	/*
+	 * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around
+	 * erratum i531 "Extra Power Consumed When Repeated Start Operation
+	 * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)".
+	 * Otherwise I2C4 eventually leads into about 23mW extra power being
+	 * consumed even during off idle using VMODE.
+	 */
 	i2c_high_speed = voltdm->pmic->i2c_high_speed;
 	if (i2c_high_speed)
-		voltdm->rmw(vc->common->i2c_cfg_hsen_mask,
+		voltdm->rmw(vc->common->i2c_cfg_clear_mask,
 			    vc->common->i2c_cfg_hsen_mask,
 			    vc->common->i2c_cfg_reg);
 
diff --git a/arch/arm/mach-omap2/vc.h b/arch/arm/mach-omap2/vc.h
index cdbdd78e755e..89b83b7ff3ec 100644
--- a/arch/arm/mach-omap2/vc.h
+++ b/arch/arm/mach-omap2/vc.h
@@ -34,6 +34,7 @@ struct voltagedomain;
  * @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register
  * @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register
  * @i2c_cfg_reg: I2C configuration register offset
+ * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register
  * @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register
  * @i2c_mcode_mask: MCODE field mask for I2C config register
  *
@@ -52,6 +53,7 @@ struct omap_vc_common {
 	u8 cmd_ret_shift;
 	u8 cmd_off_shift;
 	u8 i2c_cfg_reg;
+	u8 i2c_cfg_clear_mask;
 	u8 i2c_cfg_hsen_mask;
 	u8 i2c_mcode_mask;
 };
diff --git a/arch/arm/mach-omap2/vc3xxx_data.c b/arch/arm/mach-omap2/vc3xxx_data.c
index 75bc4aa22b3a..71d74c9172c1 100644
--- a/arch/arm/mach-omap2/vc3xxx_data.c
+++ b/arch/arm/mach-omap2/vc3xxx_data.c
@@ -40,6 +40,7 @@ static struct omap_vc_common omap3_vc_common = {
 	.cmd_onlp_shift	 = OMAP3430_VC_CMD_ONLP_SHIFT,
 	.cmd_ret_shift	 = OMAP3430_VC_CMD_RET_SHIFT,
 	.cmd_off_shift	 = OMAP3430_VC_CMD_OFF_SHIFT,
+	.i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK,
 	.i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK,
 	.i2c_cfg_reg	 = OMAP3_PRM_VC_I2C_CFG_OFFSET,
 	.i2c_mcode_mask	 = OMAP3430_MCODE_MASK,
diff --git a/arch/arm/mach-omap2/vc44xx_data.c b/arch/arm/mach-omap2/vc44xx_data.c
index 085e5d6a04fd..2abd5fa8a697 100644
--- a/arch/arm/mach-omap2/vc44xx_data.c
+++ b/arch/arm/mach-omap2/vc44xx_data.c
@@ -42,6 +42,7 @@ static const struct omap_vc_common omap4_vc_common = {
 	.cmd_ret_shift = OMAP4430_RET_SHIFT,
 	.cmd_off_shift = OMAP4430_OFF_SHIFT,
 	.i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET,
+	.i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK,
 	.i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK,
 	.i2c_mcode_mask	 = OMAP4430_HSMCODE_MASK,
 };
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 8896e71586f5..f09683687963 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -691,4 +691,13 @@ config SHARPSL_PM_MAX1111
 config PXA310_ULPI
 	bool
 
+config PXA_SYSTEMS_CPLDS
+	tristate "Motherboard cplds"
+	default ARCH_LUBBOCK || MACH_MAINSTONE
+	help
+	  This driver supports the Lubbock and Mainstone multifunction chip
+	  found on the pxa25x development platform system (Lubbock) and pxa27x
+	  development platform system (Mainstone). This IO board supports the
+	  interrupts handling, ethernet controller, flash chips, etc ...
+
 endif
diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile
index eb0bf7678a99..4087d334ecdf 100644
--- a/arch/arm/mach-pxa/Makefile
+++ b/arch/arm/mach-pxa/Makefile
@@ -90,4 +90,5 @@ obj-$(CONFIG_MACH_RAUMFELD_CONNECTOR)	+= raumfeld.o
 obj-$(CONFIG_MACH_RAUMFELD_SPEAKER)	+= raumfeld.o
 obj-$(CONFIG_MACH_ZIPIT2)	+= z2.o
 
+obj-$(CONFIG_PXA_SYSTEMS_CPLDS)	+= pxa_cplds_irqs.o
 obj-$(CONFIG_TOSA_BT)		+= tosa-bt.o
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index cfb864173ce3..4427bf26ea47 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -10,6 +10,7 @@
  *
  */
 
+#include <linux/clkdev.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h
index 958cd6af9384..1eecf794acd2 100644
--- a/arch/arm/mach-pxa/include/mach/lubbock.h
+++ b/arch/arm/mach-pxa/include/mach/lubbock.h
@@ -37,7 +37,9 @@
 #define LUB_GP			__LUB_REG(LUBBOCK_FPGA_PHYS + 0x100)
 
 /* Board specific IRQs */
-#define LUBBOCK_IRQ(x)		(IRQ_BOARD_START + (x))
+#define LUBBOCK_NR_IRQS		IRQ_BOARD_START
+
+#define LUBBOCK_IRQ(x)		(LUBBOCK_NR_IRQS + (x))
 #define LUBBOCK_SD_IRQ		LUBBOCK_IRQ(0)
 #define LUBBOCK_SA1111_IRQ	LUBBOCK_IRQ(1)
 #define LUBBOCK_USB_IRQ		LUBBOCK_IRQ(2)  /* usb connect */
@@ -47,8 +49,7 @@
 #define LUBBOCK_USB_DISC_IRQ	LUBBOCK_IRQ(6)  /* usb disconnect */
 #define LUBBOCK_LAST_IRQ	LUBBOCK_IRQ(6)
 
-#define LUBBOCK_SA1111_IRQ_BASE	(IRQ_BOARD_START + 16)
-#define LUBBOCK_NR_IRQS		(IRQ_BOARD_START + 16 + 55)
+#define LUBBOCK_SA1111_IRQ_BASE	(LUBBOCK_NR_IRQS + 32)
 
 #ifndef __ASSEMBLY__
 extern void lubbock_set_misc_wr(unsigned int mask, unsigned int set);
diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h
index 1bfc4e822a41..e82a7d31104e 100644
--- a/arch/arm/mach-pxa/include/mach/mainstone.h
+++ b/arch/arm/mach-pxa/include/mach/mainstone.h
@@ -120,7 +120,9 @@
 #define MST_PCMCIA_PWR_VCC_50   0x4	   /* voltage VCC = 5.0V */
 
 /* board specific IRQs */
-#define MAINSTONE_IRQ(x)	(IRQ_BOARD_START + (x))
+#define MAINSTONE_NR_IRQS	IRQ_BOARD_START
+
+#define MAINSTONE_IRQ(x)	(MAINSTONE_NR_IRQS + (x))
 #define MAINSTONE_MMC_IRQ	MAINSTONE_IRQ(0)
 #define MAINSTONE_USIM_IRQ	MAINSTONE_IRQ(1)
 #define MAINSTONE_USBC_IRQ	MAINSTONE_IRQ(2)
@@ -136,6 +138,4 @@
 #define MAINSTONE_S1_STSCHG_IRQ	MAINSTONE_IRQ(14)
 #define MAINSTONE_S1_IRQ	MAINSTONE_IRQ(15)
 
-#define MAINSTONE_NR_IRQS	(IRQ_BOARD_START + 16)
-
 #endif
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index d8a1be619f21..7518310c9015 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -11,7 +11,9 @@
  *  it under the terms of the GNU General Public License version 2 as
  *  published by the Free Software Foundation.
  */
+#include <linux/clkdev.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -123,84 +125,6 @@ void lubbock_set_misc_wr(unsigned int mask, unsigned int set)
 }
 EXPORT_SYMBOL(lubbock_set_misc_wr);
 
-static unsigned long lubbock_irq_enabled;
-
-static void lubbock_mask_irq(struct irq_data *d)
-{
-	int lubbock_irq = (d->irq - LUBBOCK_IRQ(0));
-	LUB_IRQ_MASK_EN = (lubbock_irq_enabled &= ~(1 << lubbock_irq));
-}
-
-static void lubbock_unmask_irq(struct irq_data *d)
-{
-	int lubbock_irq = (d->irq - LUBBOCK_IRQ(0));
-	/* the irq can be acknowledged only if deasserted, so it's done here */
-	LUB_IRQ_SET_CLR &= ~(1 << lubbock_irq);
-	LUB_IRQ_MASK_EN = (lubbock_irq_enabled |= (1 << lubbock_irq));
-}
-
-static struct irq_chip lubbock_irq_chip = {
-	.name		= "FPGA",
-	.irq_ack	= lubbock_mask_irq,
-	.irq_mask	= lubbock_mask_irq,
-	.irq_unmask	= lubbock_unmask_irq,
-};
-
-static void lubbock_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
-	unsigned long pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled;
-	do {
-		/* clear our parent irq */
-		desc->irq_data.chip->irq_ack(&desc->irq_data);
-		if (likely(pending)) {
-			irq = LUBBOCK_IRQ(0) + __ffs(pending);
-			generic_handle_irq(irq);
-		}
-		pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled;
-	} while (pending);
-}
-
-static void __init lubbock_init_irq(void)
-{
-	int irq;
-
-	pxa25x_init_irq();
-
-	/* setup extra lubbock irqs */
-	for (irq = LUBBOCK_IRQ(0); irq <= LUBBOCK_LAST_IRQ; irq++) {
-		irq_set_chip_and_handler(irq, &lubbock_irq_chip,
-					 handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
-	}
-
-	irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), lubbock_irq_handler);
-	irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING);
-}
-
-#ifdef CONFIG_PM
-
-static void lubbock_irq_resume(void)
-{
-	LUB_IRQ_MASK_EN = lubbock_irq_enabled;
-}
-
-static struct syscore_ops lubbock_irq_syscore_ops = {
-	.resume = lubbock_irq_resume,
-};
-
-static int __init lubbock_irq_device_init(void)
-{
-	if (machine_is_lubbock()) {
-		register_syscore_ops(&lubbock_irq_syscore_ops);
-		return 0;
-	}
-	return -ENODEV;
-}
-
-device_initcall(lubbock_irq_device_init);
-
-#endif
-
 static int lubbock_udc_is_connected(void)
 {
 	return (LUB_MISC_RD & (1 << 9)) == 0;
@@ -383,11 +307,38 @@ static struct platform_device lubbock_flash_device[2] = {
 	},
 };
 
+static struct resource lubbock_cplds_resources[] = {
+	[0] = {
+		.start	= LUBBOCK_FPGA_PHYS + 0xc0,
+		.end	= LUBBOCK_FPGA_PHYS + 0xe0 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= PXA_GPIO_TO_IRQ(0),
+		.end	= PXA_GPIO_TO_IRQ(0),
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
+	},
+	[2] = {
+		.start	= LUBBOCK_IRQ(0),
+		.end	= LUBBOCK_IRQ(6),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device lubbock_cplds_device = {
+	.name		= "pxa_cplds_irqs",
+	.id		= -1,
+	.resource	= &lubbock_cplds_resources[0],
+	.num_resources	= 3,
+};
+
+
 static struct platform_device *devices[] __initdata = {
 	&sa1111_device,
 	&smc91x_device,
 	&lubbock_flash_device[0],
 	&lubbock_flash_device[1],
+	&lubbock_cplds_device,
 };
 
 static struct pxafb_mode_info sharp_lm8v31_mode = {
@@ -648,7 +599,7 @@ MACHINE_START(LUBBOCK, "Intel DBPXA250 Development Platform (aka Lubbock)")
 	/* Maintainer: MontaVista Software Inc. */
 	.map_io		= lubbock_map_io,
 	.nr_irqs	= LUBBOCK_NR_IRQS,
-	.init_irq	= lubbock_init_irq,
+	.init_irq	= pxa25x_init_irq,
 	.handle_irq	= pxa25x_handle_irq,
 	.init_time	= pxa_timer_init,
 	.init_machine	= lubbock_init,
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index 78b84c0dfc79..2c0658cf6be2 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -13,6 +13,7 @@
  *  published by the Free Software Foundation.
  */
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/syscore_ops.h>
@@ -122,92 +123,6 @@ static unsigned long mainstone_pin_config[] = {
 	GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH,
 };
 
-static unsigned long mainstone_irq_enabled;
-
-static void mainstone_mask_irq(struct irq_data *d)
-{
-	int mainstone_irq = (d->irq - MAINSTONE_IRQ(0));
-	MST_INTMSKENA = (mainstone_irq_enabled &= ~(1 << mainstone_irq));
-}
-
-static void mainstone_unmask_irq(struct irq_data *d)
-{
-	int mainstone_irq = (d->irq - MAINSTONE_IRQ(0));
-	/* the irq can be acknowledged only if deasserted, so it's done here */
-	MST_INTSETCLR &= ~(1 << mainstone_irq);
-	MST_INTMSKENA = (mainstone_irq_enabled |= (1 << mainstone_irq));
-}
-
-static struct irq_chip mainstone_irq_chip = {
-	.name		= "FPGA",
-	.irq_ack	= mainstone_mask_irq,
-	.irq_mask	= mainstone_mask_irq,
-	.irq_unmask	= mainstone_unmask_irq,
-};
-
-static void mainstone_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
-	unsigned long pending = MST_INTSETCLR & mainstone_irq_enabled;
-	do {
-		/* clear useless edge notification */
-		desc->irq_data.chip->irq_ack(&desc->irq_data);
-		if (likely(pending)) {
-			irq = MAINSTONE_IRQ(0) + __ffs(pending);
-			generic_handle_irq(irq);
-		}
-		pending = MST_INTSETCLR & mainstone_irq_enabled;
-	} while (pending);
-}
-
-static void __init mainstone_init_irq(void)
-{
-	int irq;
-
-	pxa27x_init_irq();
-
-	/* setup extra Mainstone irqs */
-	for(irq = MAINSTONE_IRQ(0); irq <= MAINSTONE_IRQ(15); irq++) {
-		irq_set_chip_and_handler(irq, &mainstone_irq_chip,
-					 handle_level_irq);
-		if (irq == MAINSTONE_IRQ(10) || irq == MAINSTONE_IRQ(14))
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE | IRQF_NOAUTOEN);
-		else
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
-	}
-	set_irq_flags(MAINSTONE_IRQ(8), 0);
-	set_irq_flags(MAINSTONE_IRQ(12), 0);
-
-	MST_INTMSKENA = 0;
-	MST_INTSETCLR = 0;
-
-	irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), mainstone_irq_handler);
-	irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING);
-}
-
-#ifdef CONFIG_PM
-
-static void mainstone_irq_resume(void)
-{
-	MST_INTMSKENA = mainstone_irq_enabled;
-}
-
-static struct syscore_ops mainstone_irq_syscore_ops = {
-	.resume = mainstone_irq_resume,
-};
-
-static int __init mainstone_irq_device_init(void)
-{
-	if (machine_is_mainstone())
-		register_syscore_ops(&mainstone_irq_syscore_ops);
-
-	return 0;
-}
-
-device_initcall(mainstone_irq_device_init);
-
-#endif
-
-
 static struct resource smc91x_resources[] = {
 	[0] = {
 		.start	= (MST_ETH_PHYS + 0x300),
@@ -487,11 +402,37 @@ static struct platform_device mst_gpio_keys_device = {
 	},
 };
 
+static struct resource mst_cplds_resources[] = {
+	[0] = {
+		.start	= MST_FPGA_PHYS + 0xc0,
+		.end	= MST_FPGA_PHYS + 0xe0 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= PXA_GPIO_TO_IRQ(0),
+		.end	= PXA_GPIO_TO_IRQ(0),
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE,
+	},
+	[2] = {
+		.start	= MAINSTONE_IRQ(0),
+		.end	= MAINSTONE_IRQ(15),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mst_cplds_device = {
+	.name		= "pxa_cplds_irqs",
+	.id		= -1,
+	.resource	= &mst_cplds_resources[0],
+	.num_resources	= 3,
+};
+
 static struct platform_device *platform_devices[] __initdata = {
 	&smc91x_device,
 	&mst_flash_device[0],
 	&mst_flash_device[1],
 	&mst_gpio_keys_device,
+	&mst_cplds_device,
 };
 
 static struct pxaohci_platform_data mainstone_ohci_platform_data = {
@@ -718,7 +659,7 @@ MACHINE_START(MAINSTONE, "Intel HCDDBBVA0 Development Platform (aka Mainstone)")
 	.atag_offset	= 0x100,	/* BLOB boot parameter setting */
 	.map_io		= mainstone_map_io,
 	.nr_irqs	= MAINSTONE_NR_IRQS,
-	.init_irq	= mainstone_init_irq,
+	.init_irq	= pxa27x_init_irq,
 	.handle_irq	= pxa27x_handle_irq,
 	.init_time	= pxa_timer_init,
 	.init_machine	= mainstone_init,
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
new file mode 100644
index 000000000000..2385052b0ce1
--- /dev/null
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -0,0 +1,200 @@
+/*
+ * Intel Reference Systems cplds
+ *
+ * Copyright (C) 2014 Robert Jarzmik
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Cplds motherboard driver, supporting lubbock and mainstone SoC board.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+
+#define FPGA_IRQ_MASK_EN 0x0
+#define FPGA_IRQ_SET_CLR 0x10
+
+#define CPLDS_NB_IRQ	32
+
+struct cplds {
+	void __iomem *base;
+	int irq;
+	unsigned int irq_mask;
+	struct gpio_desc *gpio0;
+	struct irq_domain *irqdomain;
+};
+
+static irqreturn_t cplds_irq_handler(int in_irq, void *d)
+{
+	struct cplds *fpga = d;
+	unsigned long pending;
+	unsigned int bit;
+
+	pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask;
+	for_each_set_bit(bit, &pending, CPLDS_NB_IRQ)
+		generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit));
+
+	return IRQ_HANDLED;
+}
+
+static void cplds_irq_mask_ack(struct irq_data *d)
+{
+	struct cplds *fpga = irq_data_get_irq_chip_data(d);
+	unsigned int cplds_irq = irqd_to_hwirq(d);
+	unsigned int set, bit = BIT(cplds_irq);
+
+	fpga->irq_mask &= ~bit;
+	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+	set = readl(fpga->base + FPGA_IRQ_SET_CLR);
+	writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR);
+}
+
+static void cplds_irq_unmask(struct irq_data *d)
+{
+	struct cplds *fpga = irq_data_get_irq_chip_data(d);
+	unsigned int cplds_irq = irqd_to_hwirq(d);
+	unsigned int bit = BIT(cplds_irq);
+
+	fpga->irq_mask |= bit;
+	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+}
+
+static struct irq_chip cplds_irq_chip = {
+	.name		= "pxa_cplds",
+	.irq_mask_ack	= cplds_irq_mask_ack,
+	.irq_unmask	= cplds_irq_unmask,
+	.flags		= IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE,
+};
+
+static int cplds_irq_domain_map(struct irq_domain *d, unsigned int irq,
+				   irq_hw_number_t hwirq)
+{
+	struct cplds *fpga = d->host_data;
+
+	irq_set_chip_and_handler(irq, &cplds_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, fpga);
+
+	return 0;
+}
+
+static const struct irq_domain_ops cplds_irq_domain_ops = {
+	.xlate = irq_domain_xlate_twocell,
+	.map = cplds_irq_domain_map,
+};
+
+static int cplds_resume(struct platform_device *pdev)
+{
+	struct cplds *fpga = platform_get_drvdata(pdev);
+
+	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+
+	return 0;
+}
+
+static int cplds_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct cplds *fpga;
+	int ret;
+	int base_irq;
+	unsigned long irqflags = 0;
+
+	fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL);
+	if (!fpga)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (res) {
+		fpga->irq = (unsigned int)res->start;
+		irqflags = res->flags;
+	}
+	if (!fpga->irq)
+		return -ENODEV;
+
+	base_irq = platform_get_irq(pdev, 1);
+	if (base_irq < 0)
+		base_irq = 0;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	fpga->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fpga->base))
+		return PTR_ERR(fpga->base);
+
+	platform_set_drvdata(pdev, fpga);
+
+	writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN);
+	writel(0, fpga->base + FPGA_IRQ_SET_CLR);
+
+	ret = devm_request_irq(&pdev->dev, fpga->irq, cplds_irq_handler,
+			       irqflags, dev_name(&pdev->dev), fpga);
+	if (ret == -ENOSYS)
+		return -EPROBE_DEFER;
+
+	if (ret) {
+		dev_err(&pdev->dev, "couldn't request main irq%d: %d\n",
+			fpga->irq, ret);
+		return ret;
+	}
+
+	irq_set_irq_wake(fpga->irq, 1);
+	fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node,
+					       CPLDS_NB_IRQ,
+					       &cplds_irq_domain_ops, fpga);
+	if (!fpga->irqdomain)
+		return -ENODEV;
+
+	if (base_irq) {
+		ret = irq_create_strict_mappings(fpga->irqdomain, base_irq, 0,
+						 CPLDS_NB_IRQ);
+		if (ret) {
+			dev_err(&pdev->dev, "couldn't create the irq mapping %d..%d\n",
+				base_irq, base_irq + CPLDS_NB_IRQ);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int cplds_remove(struct platform_device *pdev)
+{
+	struct cplds *fpga = platform_get_drvdata(pdev);
+
+	irq_set_chip_and_handler(fpga->irq, NULL, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id cplds_id_table[] = {
+	{ .compatible = "intel,lubbock-cplds-irqs", },
+	{ .compatible = "intel,mainstone-cplds-irqs", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, cplds_id_table);
+
+static struct platform_driver cplds_driver = {
+	.driver		= {
+		.name	= "pxa_cplds_irqs",
+		.of_match_table = of_match_ptr(cplds_id_table),
+	},
+	.probe		= cplds_probe,
+	.remove		= cplds_remove,
+	.resume		= cplds_resume,
+};
+
+module_platform_driver(cplds_driver);
+
+MODULE_DESCRIPTION("PXA Cplds interrupts driver");
+MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>");
+MODULE_LICENSE("GPL");
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 7780d1faa06f..92e56d8a24d8 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -12,6 +12,7 @@
  *
  */
 
+#include <linux/clkdev.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c
index b07d88602073..b0dcbe28f78c 100644
--- a/arch/arm/mach-rockchip/pm.c
+++ b/arch/arm/mach-rockchip/pm.c
@@ -83,6 +83,13 @@ static void rk3288_slp_mode_set(int level)
 		     SGRF_PCLK_WDT_GATE | SGRF_FAST_BOOT_EN
 		     | SGRF_PCLK_WDT_GATE_WRITE | SGRF_FAST_BOOT_EN_WRITE);
 
+	/*
+	 * The dapswjdp can not auto reset before resume, that cause it may
+	 * access some illegal address during resume. Let's disable it before
+	 * suspend, and the MASKROM will enable it back.
+	 */
+	regmap_write(sgrf_regmap, RK3288_SGRF_CPU_CON0, SGRF_DAPDEVICEEN_WRITE);
+
 	/* booting address of resuming system is from this register value */
 	regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR,
 		     rk3288_bootram_phy);
diff --git a/arch/arm/mach-rockchip/pm.h b/arch/arm/mach-rockchip/pm.h
index 03ff31d8282d..3e8d39c0c3d5 100644
--- a/arch/arm/mach-rockchip/pm.h
+++ b/arch/arm/mach-rockchip/pm.h
@@ -55,6 +55,10 @@ static inline void rockchip_suspend_init(void)
 #define SGRF_FAST_BOOT_EN		BIT(8)
 #define SGRF_FAST_BOOT_EN_WRITE		BIT(24)
 
+#define RK3288_SGRF_CPU_CON0		(0x40)
+#define SGRF_DAPDEVICEEN		BIT(0)
+#define SGRF_DAPDEVICEEN_WRITE		BIT(16)
+
 #define RK3288_CRU_MODE_CON		0x50
 #define RK3288_CRU_SEL0_CON		0x60
 #define RK3288_CRU_SEL1_CON		0x64
diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c
index d360ec044b66..b6cf3b449428 100644
--- a/arch/arm/mach-rockchip/rockchip.c
+++ b/arch/arm/mach-rockchip/rockchip.c
@@ -30,11 +30,30 @@
 #include "pm.h"
 
 #define RK3288_GRF_SOC_CON0 0x244
+#define RK3288_TIMER6_7_PHYS 0xff810000
 
 static void __init rockchip_timer_init(void)
 {
 	if (of_machine_is_compatible("rockchip,rk3288")) {
 		struct regmap *grf;
+		void __iomem *reg_base;
+
+		/*
+		 * Most/all uboot versions for rk3288 don't enable timer7
+		 * which is needed for the architected timer to work.
+		 * So make sure it is running during early boot.
+		 */
+		reg_base = ioremap(RK3288_TIMER6_7_PHYS, SZ_16K);
+		if (reg_base) {
+			writel(0, reg_base + 0x30);
+			writel(0xffffffff, reg_base + 0x20);
+			writel(0xffffffff, reg_base + 0x24);
+			writel(1, reg_base + 0x30);
+			dsb();
+			iounmap(reg_base);
+		} else {
+			pr_err("rockchip: could not map timer7 registers\n");
+		}
 
 		/*
 		 * Disable auto jtag/sdmmc switching that causes issues
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index af868d258e66..99d9a3b1bf34 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -327,8 +327,7 @@ static int neponset_probe(struct platform_device *dev)
 	irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip);
 
 	irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(irq, d);
-	irq_set_chained_handler(irq, neponset_irq_handler);
+	irq_set_chained_handler_and_data(irq, neponset_irq_handler, d);
 
 	/*
 	 * We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 09c5fe3d30c2..7e7583ddd607 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1878,7 +1878,7 @@ struct dma_map_ops iommu_coherent_ops = {
  * arm_iommu_attach_device function.
  */
 struct dma_iommu_mapping *
-arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
+arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size)
 {
 	unsigned int bits = size >> PAGE_SHIFT;
 	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
@@ -1886,6 +1886,10 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 	int extensions = 1;
 	int err = -ENOMEM;
 
+	/* currently only 32-bit DMA address space is supported */
+	if (size > DMA_BIT_MASK(32) + 1)
+		return ERR_PTR(-ERANGE);
+
 	if (!bitmap_size)
 		return ERR_PTR(-EINVAL);
 
@@ -2057,13 +2061,6 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (!iommu)
 		return false;
 
-	/*
-	 * currently arm_iommu_create_mapping() takes a max of size_t
-	 * for size param. So check this limit for now.
-	 */
-	if (size > SIZE_MAX)
-		return false;
-
 	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 6333d9c17875..0d629b8f973f 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index b98895d9fe57..ee8dfa793989 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page)
 	void *kmap;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr)
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	int idx, type;
 	struct page *page = pfn_to_page(pfn);
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index c72412415093..fcafb521f14e 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -41,11 +41,6 @@ int pud_huge(pud_t pud)
 	return 0;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index be92fa0f2f35..8a63b4cdc0f2 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -268,6 +268,7 @@ void __init arm_memblock_init(const struct machine_desc *mdesc)
 	if (mdesc->reserve)
 		mdesc->reserve();
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* reserve memory for DMA contiguous allocations */
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4e6ef896c619..7186382672b5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void)
 			}
 
 			/*
-			 * Find the first non-section-aligned page, and point
+			 * Find the first non-pmd-aligned page, and point
 			 * memblock_limit at it. This relies on rounding the
-			 * limit down to be section-aligned, which happens at
-			 * the end of this function.
+			 * limit down to be pmd-aligned, which happens at the
+			 * end of this function.
 			 *
 			 * With this algorithm, the start or end of almost any
-			 * bank can be non-section-aligned. The only exception
-			 * is that the start of the bank 0 must be section-
+			 * bank can be non-pmd-aligned. The only exception is
+			 * that the start of the bank 0 must be section-
 			 * aligned, since otherwise memory would need to be
 			 * allocated when mapping the start of bank 0, which
 			 * occurs before any free memory is mapped.
 			 */
 			if (!memblock_limit) {
-				if (!IS_ALIGNED(block_start, SECTION_SIZE))
+				if (!IS_ALIGNED(block_start, PMD_SIZE))
 					memblock_limit = block_start;
-				else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+				else if (!IS_ALIGNED(block_end, PMD_SIZE))
 					memblock_limit = arm_lowmem_limit;
 			}
 
@@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void)
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
-	 * Round the memblock limit down to a section size.  This
+	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
-	 * last full section, which should be mapped.
+	 * last full pmd, which should be mapped.
 	 */
 	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+		memblock_limit = round_down(memblock_limit, PMD_SIZE);
 	if (!memblock_limit)
 		memblock_limit = arm_lowmem_limit;
 
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index aa0519eed698..774ef1323554 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -22,8 +22,6 @@
  *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020.
- *
- *  CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index bff4c7f70fd6..ae3c27b71594 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -22,8 +22,6 @@
  *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020e.
- *
- *  CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ede8c54ab4aa..32a47cc19076 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -441,9 +441,6 @@ ENTRY(cpu_arm925_set_pte_ext)
 	.type	__arm925_setup, #function
 __arm925_setup:
 	mov	r0, #0
-#if defined(CONFIG_CPU_ICACHE_STREAMING_DISABLE)
-        orr     r0,r0,#1 << 7
-#endif
 
 	/* Transparent on, D-cache clean & flush mode. See  NOTE2 above */
         orr     r0,r0,#1 << 1			@ transparent mode on
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index e494d6d6acbe..92e08bf37aad 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -602,7 +602,6 @@ __\name\()_proc_info:
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
 	initfn	__feroceon_setup, __\name\()_proc_info
-	.long __feroceon_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e1268f905026..4550d247e308 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -54,6 +54,7 @@
 #define SEEN_DATA		(1 << (BPF_MEMWORDS + 3))
 
 #define FLAG_NEED_X_RESET	(1 << 0)
+#define FLAG_IMM_OVERFLOW	(1 << 1)
 
 struct jit_ctx {
 	const struct bpf_prog *skf;
@@ -293,6 +294,15 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx)
 	/* PC in ARM mode == address of the instruction + 8 */
 	imm = offset - (8 + ctx->idx * 4);
 
+	if (imm & ~0xfff) {
+		/*
+		 * literal pool is too far, signal it into flags. we
+		 * can only detect it on the second pass unfortunately.
+		 */
+		ctx->flags |= FLAG_IMM_OVERFLOW;
+		return 0;
+	}
+
 	return imm;
 }
 
@@ -449,10 +459,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
 		return;
 	}
 #endif
-	if (rm != ARM_R0)
-		emit(ARM_MOV_R(ARM_R0, rm), ctx);
+
+	/*
+	 * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4
+	 * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into
+	 * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm
+	 * before using it as a source for ARM_R1.
+	 *
+	 * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is
+	 * ARM_R5 (r_X) so there is no particular register overlap
+	 * issues.
+	 */
 	if (rn != ARM_R1)
 		emit(ARM_MOV_R(ARM_R1, rn), ctx);
+	if (rm != ARM_R0)
+		emit(ARM_MOV_R(ARM_R0, rm), ctx);
 
 	ctx->seen |= SEEN_CALL;
 	emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
@@ -852,9 +873,27 @@ b_epilogue:
 			off = offsetof(struct sk_buff, queue_mapping);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			break;
+		case BPF_LDX | BPF_W | BPF_ABS:
+			/*
+			 * load a 32bit word from struct seccomp_data.
+			 * seccomp_check_filter() will already have checked
+			 * that k is 32bit aligned and lies within the
+			 * struct seccomp_data.
+			 */
+			ctx->seen |= SEEN_SKB;
+			emit(ARM_LDR_I(r_A, r_skb, k), ctx);
+			break;
 		default:
 			return -1;
 		}
+
+		if (ctx->flags & FLAG_IMM_OVERFLOW)
+			/*
+			 * this instruction generated an overflow when
+			 * trying to access the literal pool, so
+			 * delegate this filter to the kernel interpreter.
+			 */
+			return -1;
 	}
 
 	/* compute offsets only during the first pass */
@@ -917,7 +956,14 @@ void bpf_jit_compile(struct bpf_prog *fp)
 	ctx.idx = 0;
 
 	build_prologue(&ctx);
-	build_body(&ctx);
+	if (build_body(&ctx) < 0) {
+#if __LINUX_ARM_ARCH__ < 7
+		if (ctx.imm_count)
+			kfree(ctx.imms);
+#endif
+		bpf_jit_binary_free(header);
+		goto out;
+	}
 	build_epilogue(&ctx);
 
 	flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx));
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index f5b00f41c4f6..2235081a04ee 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -28,11 +28,7 @@
 void __init orion_clkdev_add(const char *con_id, const char *dev_id,
 			     struct clk *clk)
 {
-	struct clk_lookup *cl;
-
-	cl = clkdev_alloc(clk, con_id, dev_id);
-	if (cl)
-		clkdev_add(cl);
+	clkdev_create(clk, con_id, "%s", dev_id);
 }
 
 /* Create clkdev entries for all orion platforms except kirkwood.
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 224081ccc92f..7d0f07020c80 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -272,6 +272,7 @@ void xen_arch_pre_suspend(void) { }
 void xen_arch_post_suspend(int suspend_cancelled) { }
 void xen_timer_resume(void) { }
 void xen_arch_resume(void) { }
+void xen_arch_suspend(void) { }
 
 
 /* In the hypervisor.S file. */
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 793551d15f1d..498325074a06 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -4,6 +4,7 @@
 #include <linux/gfp.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
+#include <linux/memblock.h>
 #include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -21,6 +22,20 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
+unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+{
+	struct memblock_region *reg;
+	gfp_t flags = __GFP_NOWARN;
+
+	for_each_memblock(memory, reg) {
+		if (reg->base < (phys_addr_t)0xffffffff) {
+			flags |= __GFP_DMA;
+			break;
+		}
+	}
+	return __get_free_pages(flags, order);
+}
+
 enum dma_cache_op {
        DMA_UNMAP,
        DMA_MAP,
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7796af4b1d6f..290ed648aa11 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,5 +1,6 @@
 config ARM64
 	def_bool y
+	select ACPI_CCA_REQUIRED if ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -22,6 +23,7 @@ config ARM64
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
+	select EDAC_SUPPORT
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
 	select GENERIC_ALLOCATOR
@@ -71,6 +73,7 @@ config ARM64
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_DOMAIN
+	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_RELA
 	select NO_BOOTMEM
 	select OF
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index c8d3e0e86678..0bb287ca0a98 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -374,6 +374,111 @@
 			};
 		};
 
+		msi: msi@79000000 {
+			compatible = "apm,xgene1-msi";
+			msi-controller;
+			reg = <0x00 0x79000000 0x0 0x900000>;
+			interrupts = <  0x0 0x10 0x4
+					0x0 0x11 0x4
+					0x0 0x12 0x4
+					0x0 0x13 0x4
+					0x0 0x14 0x4
+					0x0 0x15 0x4
+					0x0 0x16 0x4
+					0x0 0x17 0x4
+					0x0 0x18 0x4
+					0x0 0x19 0x4
+					0x0 0x1a 0x4
+					0x0 0x1b 0x4
+					0x0 0x1c 0x4
+					0x0 0x1d 0x4
+					0x0 0x1e 0x4
+					0x0 0x1f 0x4>;
+		};
+
+		csw: csw@7e200000 {
+			compatible = "apm,xgene-csw", "syscon";
+			reg = <0x0 0x7e200000 0x0 0x1000>;
+		};
+
+		mcba: mcba@7e700000 {
+			compatible = "apm,xgene-mcb", "syscon";
+			reg = <0x0 0x7e700000 0x0 0x1000>;
+		};
+
+		mcbb: mcbb@7e720000 {
+			compatible = "apm,xgene-mcb", "syscon";
+			reg = <0x0 0x7e720000 0x0 0x1000>;
+		};
+
+		efuse: efuse@1054a000 {
+			compatible = "apm,xgene-efuse", "syscon";
+			reg = <0x0 0x1054a000 0x0 0x20>;
+		};
+
+		edac@78800000 {
+			compatible = "apm,xgene-edac";
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
+			regmap-csw = <&csw>;
+			regmap-mcba = <&mcba>;
+			regmap-mcbb = <&mcbb>;
+			regmap-efuse = <&efuse>;
+			reg = <0x0 0x78800000 0x0 0x100>;
+			interrupts = <0x0 0x20 0x4>,
+				     <0x0 0x21 0x4>,
+				     <0x0 0x27 0x4>;
+
+			edacmc@7e800000 {
+				compatible = "apm,xgene-edac-mc";
+				reg = <0x0 0x7e800000 0x0 0x1000>;
+				memory-controller = <0>;
+			};
+
+			edacmc@7e840000 {
+				compatible = "apm,xgene-edac-mc";
+				reg = <0x0 0x7e840000 0x0 0x1000>;
+				memory-controller = <1>;
+			};
+
+			edacmc@7e880000 {
+				compatible = "apm,xgene-edac-mc";
+				reg = <0x0 0x7e880000 0x0 0x1000>;
+				memory-controller = <2>;
+			};
+
+			edacmc@7e8c0000 {
+				compatible = "apm,xgene-edac-mc";
+				reg = <0x0 0x7e8c0000 0x0 0x1000>;
+				memory-controller = <3>;
+			};
+
+			edacpmd@7c000000 {
+				compatible = "apm,xgene-edac-pmd";
+				reg = <0x0 0x7c000000 0x0 0x200000>;
+				pmd-controller = <0>;
+			};
+
+			edacpmd@7c200000 {
+				compatible = "apm,xgene-edac-pmd";
+				reg = <0x0 0x7c200000 0x0 0x200000>;
+				pmd-controller = <1>;
+			};
+
+			edacpmd@7c400000 {
+				compatible = "apm,xgene-edac-pmd";
+				reg = <0x0 0x7c400000 0x0 0x200000>;
+				pmd-controller = <2>;
+			};
+
+			edacpmd@7c600000 {
+				compatible = "apm,xgene-edac-pmd";
+				reg = <0x0 0x7c600000 0x0 0x200000>;
+				pmd-controller = <3>;
+			};
+		};
+
 		pcie0: pcie@1f2b0000 {
 			status = "disabled";
 			device_type = "pci";
@@ -395,6 +500,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
 			dma-coherent;
 			clocks = <&pcie0clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie1: pcie@1f2c0000 {
@@ -418,6 +524,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
 			dma-coherent;
 			clocks = <&pcie1clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie2: pcie@1f2d0000 {
@@ -441,6 +548,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
 			dma-coherent;
 			clocks = <&pcie2clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie3: pcie@1f500000 {
@@ -464,6 +572,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
 			dma-coherent;
 			clocks = <&pcie3clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie4: pcie@1f510000 {
@@ -487,6 +596,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
 			dma-coherent;
 			clocks = <&pcie4clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		serial0: serial@1c020000 {
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index c138b95a8356..351c95bda89e 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -21,6 +21,20 @@
 			clock-output-names = "juno_mb:clk25mhz";
 		};
 
+		v2m_refclk1mhz: refclk1mhz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <1000000>;
+			clock-output-names = "juno_mb:refclk1mhz";
+		};
+
+		v2m_refclk32khz: refclk32khz {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+			clock-output-names = "juno_mb:refclk32khz";
+		};
+
 		motherboard {
 			compatible = "arm,vexpress,v2p-p1", "simple-bus";
 			#address-cells = <2>;  /* SMB chipselect number and offset */
@@ -66,6 +80,15 @@
 				#size-cells = <1>;
 				ranges = <0 3 0 0x200000>;
 
+				v2m_sysctl: sysctl@020000 {
+					compatible = "arm,sp810", "arm,primecell";
+					reg = <0x020000 0x1000>;
+					clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&mb_clk24mhz>;
+					clock-names = "refclk", "timclk", "apb_pclk";
+					#clock-cells = <1>;
+					clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+				};
+
 				mmci@050000 {
 					compatible = "arm,pl180", "arm,primecell";
 					reg = <0x050000 0x1000>;
@@ -106,16 +129,16 @@
 					compatible = "arm,sp804", "arm,primecell";
 					reg = <0x110000 0x10000>;
 					interrupts = <9>;
-					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
-					clock-names = "timclken1", "apb_pclk";
+					clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&mb_clk24mhz>;
+					clock-names = "timclken1", "timclken2", "apb_pclk";
 				};
 
 				v2m_timer23: timer@120000 {
 					compatible = "arm,sp804", "arm,primecell";
 					reg = <0x120000 0x10000>;
 					interrupts = <9>;
-					clocks = <&mb_clk24mhz>, <&soc_smc50mhz>;
-					clock-names = "timclken1", "apb_pclk";
+					clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&mb_clk24mhz>;
+					clock-names = "timclken1", "timclken2", "apb_pclk";
 				};
 
 				rtc@170000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
index 43d54017b779..d0ab012fa379 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts
@@ -16,7 +16,8 @@
 #include "mt8173.dtsi"
 
 / {
-	model = "mediatek,mt8173-evb";
+	model = "MediaTek MT8173 evaluation board";
+	compatible = "mediatek,mt8173-evb", "mediatek,mt8173";
 
 	aliases {
 		serial0 = &uart0;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 2ed7449d9273..daefbf0329a6 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -180,6 +180,7 @@ CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
 # CONFIG_FTRACE is not set
+CONFIG_MEMTEST=y
 CONFIG_SECURITY=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 6c348df5bf36..3303e8a7b837 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -13,7 +13,7 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
-#include <linux/crypto.h>
+#include <crypto/internal/aead.h>
 #include <linux/module.h>
 
 #include "aes-ce-setkey.h"
diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c
index 9499199924ae..6a37c3c6b11d 100644
--- a/arch/arm64/crypto/crc32-arm64.c
+++ b/arch/arm64/crypto/crc32-arm64.c
@@ -147,13 +147,21 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
+	put_unaligned_le32(ctx->crc, out);
+	return 0;
+}
+
+static int chksumc_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
 	put_unaligned_le32(~ctx->crc, out);
 	return 0;
 }
 
 static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
 {
-	put_unaligned_le32(~crc32_arm64_le_hw(crc, data, len), out);
+	put_unaligned_le32(crc32_arm64_le_hw(crc, data, len), out);
 	return 0;
 }
 
@@ -199,6 +207,14 @@ static int crc32_cra_init(struct crypto_tfm *tfm)
 {
 	struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
 
+	mctx->key = 0;
+	return 0;
+}
+
+static int crc32c_cra_init(struct crypto_tfm *tfm)
+{
+	struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
+
 	mctx->key = ~0;
 	return 0;
 }
@@ -229,7 +245,7 @@ static struct shash_alg crc32c_alg = {
 	.setkey			=	chksum_setkey,
 	.init			=	chksum_init,
 	.update			=	chksumc_update,
-	.final			=	chksum_final,
+	.final			=	chksumc_final,
 	.finup			=	chksumc_finup,
 	.digest			=	chksumc_digest,
 	.descsize		=	sizeof(struct chksum_desc_ctx),
@@ -241,7 +257,7 @@ static struct shash_alg crc32c_alg = {
 		.cra_alignmask		=	0,
 		.cra_ctxsize		=	sizeof(struct chksum_ctx),
 		.cra_module		=	THIS_MODULE,
-		.cra_init		=	crc32_cra_init,
+		.cra_init		=	crc32c_cra_init,
 	}
 };
 
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 114e7cc5de8c..aefda9868627 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -74,6 +74,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 
 static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 {
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+	sctx->finalize = 0;
 	kernel_neon_begin_partial(16);
 	sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
 	kernel_neon_end();
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 1340e44c048b..7cd587564a41 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -75,6 +75,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 
 static int sha256_ce_final(struct shash_desc *desc, u8 *out)
 {
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+	sctx->finalize = 0;
 	kernel_neon_begin_partial(28);
 	sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
 	kernel_neon_end();
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 59c05d8ea4a0..39248d3adf5d 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -16,6 +16,7 @@
 #include <linux/irqchip/arm-gic-acpi.h>
 
 #include <asm/cputype.h>
+#include <asm/psci.h>
 #include <asm/smp_plat.h>
 
 /* Basic configuration for ACPI */
@@ -39,18 +40,6 @@ extern int acpi_disabled;
 extern int acpi_noirq;
 extern int acpi_pci_disabled;
 
-/* 1 to indicate PSCI 0.2+ is implemented */
-static inline bool acpi_psci_present(void)
-{
-	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
-}
-
-/* 1 to indicate HVC must be used instead of SMC as the PSCI conduit */
-static inline bool acpi_psci_use_hvc(void)
-{
-	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
-}
-
 static inline void disable_acpi(void)
 {
 	acpi_disabled = 1;
@@ -88,9 +77,11 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { }
 void __init acpi_init_cpus(void);
 
 #else
-static inline bool acpi_psci_present(void) { return false; }
-static inline bool acpi_psci_use_hvc(void) { return false; }
 static inline void acpi_init_cpus(void) { }
 #endif /* CONFIG_ACPI */
 
+static inline const char *acpi_get_enable_method(int cpu)
+{
+	return acpi_psci_present() ? "psci" : NULL;
+}
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/alternative-asm.h b/arch/arm64/include/asm/alternative-asm.h
deleted file mode 100644
index 919a67855b63..000000000000
--- a/arch/arm64/include/asm/alternative-asm.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __ASM_ALTERNATIVE_ASM_H
-#define __ASM_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
-	.word \orig_offset - .
-	.word \alt_offset - .
-	.hword \feature
-	.byte \orig_len
-	.byte \alt_len
-.endm
-
-.macro alternative_insn insn1 insn2 cap
-661:	\insn1
-662:	.pushsection .altinstructions, "a"
-	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
-	.popsection
-	.pushsection .altinstr_replacement, "ax"
-663:	\insn2
-664:	.popsection
-	.if ((664b-663b) != (662b-661b))
-		.error "Alternatives instruction length mismatch"
-	.endif
-.endm
-
-#endif  /*  __ASSEMBLY__  */
-
-#endif /* __ASM_ALTERNATIVE_ASM_H */
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index d261f01e2bae..c385a0c4057f 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -1,6 +1,8 @@
 #ifndef __ASM_ALTERNATIVE_H
 #define __ASM_ALTERNATIVE_H
 
+#ifndef __ASSEMBLY__
+
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/stringify.h>
@@ -24,7 +26,20 @@ void free_alternatives_memory(void);
 	" .byte 662b-661b\n"				/* source len      */ \
 	" .byte 664f-663f\n"				/* replacement len */
 
-/* alternative assembly primitive: */
+/*
+ * alternative assembly primitive:
+ *
+ * If any of these .org directive fail, it means that insn1 and insn2
+ * don't have the same length. This used to be written as
+ *
+ * .if ((664b-663b) != (662b-661b))
+ * 	.error "Alternatives instruction length mismatch"
+ * .endif
+ *
+ * but most assemblers die if insn1 or insn2 have a .inst. This should
+ * be fixed in a binutils release posterior to 2.25.51.0.2 (anything
+ * containing commit 4e4d08cf7399b606 or c1baaddf8861).
+ */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
 	"661:\n\t"							\
 	oldinstr "\n"							\
@@ -37,8 +52,31 @@ void free_alternatives_memory(void);
 	newinstr "\n"							\
 	"664:\n\t"							\
 	".popsection\n\t"						\
-	".if ((664b-663b) != (662b-661b))\n\t"				\
-	"	.error \"Alternatives instruction length mismatch\"\n\t"\
-	".endif\n"
+	".org	. - (664b-663b) + (662b-661b)\n\t"			\
+	".org	. - (662b-661b) + (664b-663b)\n"
+
+#else
+
+.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len
+	.word \orig_offset - .
+	.word \alt_offset - .
+	.hword \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+.macro alternative_insn insn1 insn2 cap
+661:	\insn1
+662:	.pushsection .altinstructions, "a"
+	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+663:	\insn2
+664:	.popsection
+	.org	. - (664b-663b) + (662b-661b)
+	.org	. - (662b-661b) + (664b-663b)
+.endm
+
+#endif  /*  __ASSEMBLY__  */
 
 #endif /* __ASM_ALTERNATIVE_H */
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4dc0de..0fa47c4275cb 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -114,7 +114,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 #define nop()		asm volatile("nop");
 
 #define smp_mb__before_atomic()	smp_mb()
diff --git a/arch/arm64/include/asm/boot.h b/arch/arm64/include/asm/boot.h
new file mode 100644
index 000000000000..81151b67b26b
--- /dev/null
+++ b/arch/arm64/include/asm/boot.h
@@ -0,0 +1,14 @@
+
+#ifndef __ASM_BOOT_H
+#define __ASM_BOOT_H
+
+#include <asm/sizes.h>
+
+/*
+ * arm64 requires the DTB to be 8 byte aligned and
+ * not exceed 2MB in size.
+ */
+#define MIN_FDT_ALIGN		8
+#define MAX_FDT_SIZE		SZ_2M
+
+#endif
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 67d309cc3b6b..c75b8d027eb1 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -40,10 +40,6 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT or ASID-tagged VIVT I-cache.
  *
- *	flush_cache_all()
- *
- *		Unconditionally clean and invalidate the entire cache.
- *
  *	flush_cache_mm(mm)
  *
  *		Clean and invalidate all user space cache entries
@@ -69,7 +65,6 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
-extern void flush_cache_all(void);
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 5a31d6716914..8f03446cf89f 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -19,15 +19,15 @@
 #include <linux/init.h>
 #include <linux/threads.h>
 
-struct device_node;
-
 /**
  * struct cpu_operations - Callback operations for hotplugging CPUs.
  *
  * @name:	Name of the property as appears in a devicetree cpu node's
- *		enable-method property.
- * @cpu_init:	Reads any data necessary for a specific enable-method from the
- *		devicetree, for a given cpu node and proposed logical id.
+ *		enable-method property. On systems booting with ACPI, @name
+ *		identifies the struct cpu_operations entry corresponding to
+ *		the boot protocol specified in the ACPI MADT table.
+ * @cpu_init:	Reads any data necessary for a specific enable-method for a
+ *		proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -40,15 +40,15 @@ struct device_node;
  * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
  *		cpu being killed.
  * @cpu_kill:  Ensures a cpu has left the kernel. Called from another cpu.
- * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
- *		devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states for
+ *		   a proposed logical id.
  * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
  *               to wrong parameters or error conditions. Called from the
  *               CPU being suspended. Must be called with IRQs disabled.
  */
 struct cpu_operations {
 	const char	*name;
-	int		(*cpu_init)(struct device_node *, unsigned int);
+	int		(*cpu_init)(unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
@@ -58,14 +58,17 @@ struct cpu_operations {
 	int		(*cpu_kill)(unsigned int cpu);
 #endif
 #ifdef CONFIG_CPU_IDLE
-	int		(*cpu_init_idle)(struct device_node *, unsigned int);
+	int		(*cpu_init_idle)(unsigned int);
 	int		(*cpu_suspend)(unsigned long);
 #endif
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
-int __init cpu_read_ops(struct device_node *dn, int cpu);
-void __init cpu_read_bootcpu_ops(void);
-const struct cpu_operations *cpu_get_ops(const char *name);
+int __init cpu_read_ops(int cpu);
+
+static inline void __init cpu_read_bootcpu_ops(void)
+{
+	cpu_read_ops(0);
+}
 
 #endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 82cb9f98ba1a..c1044218a63a 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -24,8 +24,9 @@
 #define ARM64_WORKAROUND_CLEAN_CACHE		0
 #define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE	1
 #define ARM64_WORKAROUND_845719			2
+#define ARM64_HAS_SYSREG_GIC_CPUIF		3
 
-#define ARM64_NCAPS				3
+#define ARM64_NCAPS				4
 
 #ifndef __ASSEMBLY__
 
@@ -38,6 +39,11 @@ struct arm64_cpu_capabilities {
 			u32 midr_model;
 			u32 midr_range_min, midr_range_max;
 		};
+
+		struct {	/* Feature register checking */
+			u64 register_mask;
+			u64 register_value;
+		};
 	};
 };
 
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
index 141b2fcabaa6..0f74f05d662a 100644
--- a/arch/arm64/include/asm/cpuidle.h
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -5,20 +5,16 @@
 
 #ifdef CONFIG_CPU_IDLE
 extern int arm_cpuidle_init(unsigned int cpu);
-extern int cpu_suspend(unsigned long arg);
+extern int arm_cpuidle_suspend(int index);
 #else
 static inline int arm_cpuidle_init(unsigned int cpu)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int cpu_suspend(unsigned long arg)
+static inline int arm_cpuidle_suspend(int index)
 {
 	return -EOPNOTSUPP;
 }
 #endif
-static inline int arm_cpuidle_suspend(int index)
-{
-	return cpu_suspend(index);
-}
 #endif
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 9437e3dc5833..f0d6d0bfe55c 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,6 +18,7 @@
 
 #ifdef __KERNEL__
 
+#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -28,13 +29,23 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev) || !dev->archdata.dma_ops)
+	if (unlikely(!dev))
 		return dma_ops;
-	else
+	else if (dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
+	else if (acpi_disabled)
+		return dma_ops;
+
+	/*
+	 * When ACPI is enabled, if arch_set_dma_ops is not called,
+	 * we will disable device DMA capability by setting it
+	 * to dummy_dma_ops.
+	 */
+	return &dummy_dma_ops;
 }
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
@@ -48,6 +59,9 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 				      struct iommu_ops *iommu, bool coherent)
 {
+	if (!acpi_disabled && !dev->archdata.dma_ops)
+		dev->archdata.dma_ops = dma_ops;
+
 	dev->archdata.dma_coherent = coherent;
 }
 #define arch_setup_dma_ops	arch_setup_dma_ops
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 95e6b6dcbe37..c0739187a920 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
+#include <asm/boot.h>
 #include <asm/page.h>
 
 /*
@@ -32,6 +33,20 @@
  */
 enum fixed_addresses {
 	FIX_HOLE,
+
+	/*
+	 * Reserve a virtual window for the FDT that is 2 MB larger than the
+	 * maximum supported size, and put it at the top of the fixmap region.
+	 * The additional space ensures that any FDT that does not exceed
+	 * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
+	 * 2 MB alignment boundaries.
+	 *
+	 * Keep this at the top so it remains 2 MB aligned.
+	 */
+#define FIX_FDT_SIZE		(MAX_FDT_SIZE + SZ_2M)
+	FIX_FDT_END,
+	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
+
 	FIX_EARLYCON_MEM_BASE,
 	FIX_TEXT_POKE0,
 	__end_of_permanent_fixed_addresses,
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index 5f750dc96e0f..74069b3bd919 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -58,7 +58,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
-	pagefault_disable();	/* implies preempt_disable() */
+	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -85,7 +85,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 		ret = -ENOSYS;
 	}
 
-	pagefault_enable();	/* subsumes preempt_enable() */
+	pagefault_enable();
 
 	if (!ret) {
 		switch (cmp) {
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 5b7ca8ace95f..734c17e89e94 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -86,10 +86,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index f81b328d9cf4..30e50eb54a67 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -281,6 +281,7 @@ __AARCH64_INSN_FUNCS(ret,	0xFFFFFC1F, 0xD65F0000)
 #undef	__AARCH64_INSN_FUNCS
 
 bool aarch64_insn_is_nop(u32 insn);
+bool aarch64_insn_is_branch_imm(u32 insn);
 
 int aarch64_insn_read(void *addr, u32 *insnp);
 int aarch64_insn_write(void *addr, u32 insn);
@@ -351,6 +352,8 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 					 int shift,
 					 enum aarch64_insn_variant variant,
 					 enum aarch64_insn_logic_type type);
+s32 aarch64_get_branch_offset(u32 insn);
+u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 540f7c0aea82..44be1e03ed65 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -117,10 +117,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  * ordering rules but do not guarantee any ordering relative to Normal memory
  * accesses.
  */
-#define readb_relaxed(c)	({ u8  __v = __raw_readb(c); __v; })
-#define readw_relaxed(c)	({ u16 __v = le16_to_cpu((__force __le16)__raw_readw(c)); __v; })
-#define readl_relaxed(c)	({ u32 __v = le32_to_cpu((__force __le32)__raw_readl(c)); __v; })
-#define readq_relaxed(c)	({ u64 __v = le64_to_cpu((__force __le64)__raw_readq(c)); __v; })
+#define readb_relaxed(c)	({ u8  __r = __raw_readb(c); __r; })
+#define readw_relaxed(c)	({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; })
+#define readl_relaxed(c)	({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+#define readq_relaxed(c)	({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; })
 
 #define writeb_relaxed(v,c)	((void)__raw_writeb((v),(c)))
 #define writew_relaxed(v,c)	((void)__raw_writew((__force u16)cpu_to_le16(v),(c)))
@@ -170,6 +170,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define ioremap(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_nocache(addr, size)	__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define ioremap_wc(addr, size)		__ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
+#define ioremap_wt(addr, size)		__ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
 #define iounmap				__iounmap
 
 /*
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 4f7310fa77f0..3c5fe685a2d6 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -27,7 +27,7 @@
 #define	MPIDR_EL1	1	/* MultiProcessor Affinity Register */
 #define	CSSELR_EL1	2	/* Cache Size Selection Register */
 #define	SCTLR_EL1	3	/* System Control Register */
-#define	ACTLR_EL1	4	/* Auxilliary Control Register */
+#define	ACTLR_EL1	4	/* Auxiliary Control Register */
 #define	CPACR_EL1	5	/* Coprocessor Access Control */
 #define	TTBR0_EL1	6	/* Translation Table Base Register 0 */
 #define	TTBR1_EL1	7	/* Translation Table Base Register 1 */
@@ -132,11 +132,6 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
 
-extern char __save_vgic_v2_state[];
-extern char __restore_vgic_v2_state[];
-extern char __save_vgic_v3_state[];
-extern char __restore_vgic_v3_state[];
-
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f0f58c9beec0..2709db2a7eac 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -221,29 +221,6 @@ struct vgic_sr_vectors {
 	void	*restore_vgic;
 };
 
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
-	extern struct vgic_sr_vectors __vgic_sr_vectors;
-
-	switch(vgic->type)
-	{
-	case VGIC_V2:
-		__vgic_sr_vectors.save_vgic	= __save_vgic_v2_state;
-		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v2_state;
-		break;
-
-#ifdef CONFIG_ARM_GIC_V3
-	case VGIC_V3:
-		__vgic_sr_vectors.save_vgic	= __save_vgic_v3_state;
-		__vgic_sr_vectors.restore_vgic	= __restore_vgic_v3_state;
-		break;
-#endif
-
-	default:
-		BUG();
-	}
-}
-
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
diff --git a/arch/arm64/include/asm/mm-arch-hooks.h b/arch/arm64/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..562b655f5ba9
--- /dev/null
+++ b/arch/arm64/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_ARM64_MM_ARCH_HOOKS_H
+#define _ASM_ARM64_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_ARM64_MM_ARCH_HOOKS_H */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 3d311761e3c2..79fcfb048884 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -34,5 +34,6 @@ extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot);
+extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 
 #endif
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index d26d1d53c0d7..6471773db6fd 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -24,4 +24,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 #endif
 
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->pc = (__ip);    \
+	(regs)->regs[29] = (unsigned long) __builtin_frame_address(0); \
+	(regs)->sp = current_stack_pointer; \
+	(regs)->pstate = PSR_MODE_EL1h;	\
+}
+
 #endif
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 220633b791b8..14ad6e4e87d1 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -28,12 +28,8 @@
 struct mm_struct;
 struct cpu_suspend_ctx;
 
-extern void cpu_cache_off(void);
 extern void cpu_do_idle(void);
 extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
-void cpu_soft_restart(phys_addr_t cpu_reset,
-		unsigned long addr) __attribute__((noreturn));
 extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
 extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index d2c37a1df0eb..e4c893e54f01 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -78,13 +78,30 @@ struct cpu_context {
 
 struct thread_struct {
 	struct cpu_context	cpu_context;	/* cpu context */
-	unsigned long		tp_value;
+	unsigned long		tp_value;	/* TLS register */
+#ifdef CONFIG_COMPAT
+	unsigned long		tp2_value;
+#endif
 	struct fpsimd_state	fpsimd_state;
 	unsigned long		fault_address;	/* fault info */
 	unsigned long		fault_code;	/* ESR_EL1 value */
 	struct debug_info	debug;		/* debugging */
 };
 
+#ifdef CONFIG_COMPAT
+#define task_user_tls(t)						\
+({									\
+	unsigned long *__tls;						\
+	if (is_compat_thread(task_thread_info(t)))			\
+		__tls = &(t)->thread.tp2_value;				\
+	else								\
+		__tls = &(t)->thread.tp_value;				\
+	__tls;								\
+ })
+#else
+#define task_user_tls(t)	(&(t)->thread.tp_value)
+#endif
+
 #define INIT_THREAD  {	}
 
 static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index 2454bc59c916..49d7e1aaebdc 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,7 +14,15 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-int psci_dt_init(void);
-int psci_acpi_init(void);
+int __init psci_dt_init(void);
+
+#ifdef CONFIG_ACPI
+int __init psci_acpi_init(void);
+bool __init acpi_psci_present(void);
+bool __init acpi_psci_use_hvc(void);
+#else
+static inline int psci_acpi_init(void) { return 0; }
+static inline bool acpi_psci_present(void) { return false; }
+#endif
 
 #endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index bf22650b1a78..db02be81b90a 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -42,7 +42,7 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs);
  * Discover the set of possible CPUs and determine their
  * SMP operations.
  */
-extern void of_smp_init_cpus(void);
+extern void smp_init_cpus(void);
 
 /*
  * Provide a function to raise an IPI cross call on CPUs in callmap.
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index 8dcd61e32176..7abf7570c00f 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -19,6 +19,8 @@
 #ifndef __ASM_SMP_PLAT_H
 #define __ASM_SMP_PLAT_H
 
+#include <linux/cpumask.h>
+
 #include <asm/types.h>
 
 struct mpidr_hash {
@@ -39,6 +41,20 @@ static inline u32 mpidr_hash_size(void)
  */
 extern u64 __cpu_logical_map[NR_CPUS];
 #define cpu_logical_map(cpu)    __cpu_logical_map[cpu]
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR.Aff*
+ *  - mpidr: MPIDR.Aff* bits to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u64 mpidr)
+{
+	int cpu;
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (cpu_logical_map(cpu) == mpidr)
+			return cpu;
+	return -EINVAL;
+}
 
 void __init do_post_cpus_up_work(void);
 
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 003802f58963..59a5b0f1e81c 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -21,6 +21,6 @@ struct sleep_save_sp {
 	phys_addr_t save_ptr_stash_phys;
 };
 
-extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
+extern int cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
 #endif
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 7a18fabbe0f6..57f110bea6a8 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -23,6 +23,8 @@
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/irqflags.h>
+#include <linux/signal.h>
+#include <linux/ratelimit.h>
 #include <linux/reboot.h>
 
 struct pt_regs;
@@ -41,9 +43,19 @@ struct mm_struct;
 extern void show_pte(struct mm_struct *mm, unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
-void soft_restart(unsigned long);
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 
+#define show_unhandled_signals_ratelimited()				\
+({									\
+	static DEFINE_RATELIMIT_STATE(_rs,				\
+				      DEFAULT_RATELIMIT_INTERVAL,	\
+				      DEFAULT_RATELIMIT_BURST);		\
+	bool __show_ratelimited = false;				\
+	if (show_unhandled_signals && __ratelimit(&_rs))		\
+		__show_ratelimited = true;				\
+	__show_ratelimited;						\
+})
+
 #define UDBG_UNDEFINED	(1 << 0)
 #define UDBG_SYSCALL	(1 << 1)
 #define UDBG_BADABORT	(1 << 2)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index c3bb05b98616..934815d45eda 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -28,8 +28,6 @@
  *	TLB Management
  *	==============
  *
- *	The arch/arm64/mm/tlb.S files implement these methods.
- *
  *	The TLB specific code is expected to perform whatever tests it needs
  *	to determine if it should invalidate the TLB for each call.  Start
  *	addresses are inclusive and end addresses are exclusive; it is safe to
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 7ebcd31ce51c..225ec3524fbf 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].cluster_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 8b839558838e..19de7537e7d3 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -36,12 +36,6 @@ EXPORT_SYMBOL(acpi_disabled);
 int acpi_pci_disabled = 1;	/* skip ACPI PCI scan and IRQ initialization */
 EXPORT_SYMBOL(acpi_pci_disabled);
 
-/* Processors with enabled flag and sane MPIDR */
-static int enabled_cpus;
-
-/* Boot CPU is valid or not in MADT */
-static bool bootcpu_valid  __initdata;
-
 static bool param_acpi_off __initdata;
 static bool param_acpi_force __initdata;
 
@@ -95,122 +89,15 @@ void __init __acpi_unmap_table(char *map, unsigned long size)
 	early_memunmap(map, size);
 }
 
-/**
- * acpi_map_gic_cpu_interface - generates a logical cpu number
- * and map to MPIDR represented by GICC structure
- */
-static void __init
-acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+bool __init acpi_psci_present(void)
 {
-	int i;
-	u64 mpidr = processor->arm_mpidr & MPIDR_HWID_BITMASK;
-	bool enabled = !!(processor->flags & ACPI_MADT_ENABLED);
-
-	if (mpidr == INVALID_HWID) {
-		pr_info("Skip MADT cpu entry with invalid MPIDR\n");
-		return;
-	}
-
-	total_cpus++;
-	if (!enabled)
-		return;
-
-	if (enabled_cpus >=  NR_CPUS) {
-		pr_warn("NR_CPUS limit of %d reached, Processor %d/0x%llx ignored.\n",
-			NR_CPUS, total_cpus, mpidr);
-		return;
-	}
-
-	/* Check if GICC structure of boot CPU is available in the MADT */
-	if (cpu_logical_map(0) == mpidr) {
-		if (bootcpu_valid) {
-			pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
-			       mpidr);
-			return;
-		}
-
-		bootcpu_valid = true;
-	}
-
-	/*
-	 * Duplicate MPIDRs are a recipe for disaster. Scan
-	 * all initialized entries and check for
-	 * duplicates. If any is found just ignore the CPU.
-	 */
-	for (i = 1; i < enabled_cpus; i++) {
-		if (cpu_logical_map(i) == mpidr) {
-			pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
-			       mpidr);
-			return;
-		}
-	}
-
-	if (!acpi_psci_present())
-		return;
-
-	cpu_ops[enabled_cpus] = cpu_get_ops("psci");
-	/* CPU 0 was already initialized */
-	if (enabled_cpus) {
-		if (!cpu_ops[enabled_cpus])
-			return;
-
-		if (cpu_ops[enabled_cpus]->cpu_init(NULL, enabled_cpus))
-			return;
-
-		/* map the logical cpu id to cpu MPIDR */
-		cpu_logical_map(enabled_cpus) = mpidr;
-	}
-
-	enabled_cpus++;
+	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
 }
 
-static int __init
-acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
-				const unsigned long end)
+/* Whether HVC must be used instead of SMC as the PSCI conduit */
+bool __init acpi_psci_use_hvc(void)
 {
-	struct acpi_madt_generic_interrupt *processor;
-
-	processor = (struct acpi_madt_generic_interrupt *)header;
-
-	if (BAD_MADT_ENTRY(processor, end))
-		return -EINVAL;
-
-	acpi_table_print_madt_entry(header);
-	acpi_map_gic_cpu_interface(processor);
-	return 0;
-}
-
-/* Parse GIC cpu interface entries in MADT for SMP init */
-void __init acpi_init_cpus(void)
-{
-	int count, i;
-
-	/*
-	 * do a partial walk of MADT to determine how many CPUs
-	 * we have including disabled CPUs, and get information
-	 * we need for SMP init
-	 */
-	count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
-			acpi_parse_gic_cpu_interface, 0);
-
-	if (!count) {
-		pr_err("No GIC CPU interface entries present\n");
-		return;
-	} else if (count < 0) {
-		pr_err("Error parsing GIC CPU interface entry\n");
-		return;
-	}
-
-	if (!bootcpu_valid) {
-		pr_err("MADT missing boot CPU MPIDR, not enabling secondaries\n");
-		return;
-	}
-
-	for (i = 0; i < enabled_cpus; i++)
-		set_cpu_possible(i, true);
-
-	/* Make boot-up look pretty */
-	pr_info("%d CPUs enabled, %d CPUs total\n", enabled_cpus, total_cpus);
+	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
 }
 
 /*
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 21033bba9390..221b98312f0c 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -27,6 +27,10 @@
 #include <asm/insn.h>
 #include <linux/stop_machine.h>
 
+#define __ALT_PTR(a,f)		(u32 *)((void *)&(a)->f + (a)->f)
+#define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
+#define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
+
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 
 struct alt_region {
@@ -35,42 +39,47 @@ struct alt_region {
 };
 
 /*
- * Decode the imm field of a b/bl instruction, and return the byte
- * offset as a signed value (so it can be used when computing a new
- * branch target).
+ * Check if the target PC is within an alternative block.
  */
-static s32 get_branch_offset(u32 insn)
+static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	s32 imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+	unsigned long replptr;
+
+	if (kernel_text_address(pc))
+		return 1;
+
+	replptr = (unsigned long)ALT_REPL_PTR(alt);
+	if (pc >= replptr && pc <= (replptr + alt->alt_len))
+		return 0;
 
-	/* sign-extend the immediate before turning it into a byte offset */
-	return (imm << 6) >> 4;
+	/*
+	 * Branching into *another* alternate sequence is doomed, and
+	 * we're not even trying to fix it up.
+	 */
+	BUG();
 }
 
-static u32 get_alt_insn(u8 *insnptr, u8 *altinsnptr)
+static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 {
 	u32 insn;
 
-	aarch64_insn_read(altinsnptr, &insn);
+	insn = le32_to_cpu(*altinsnptr);
 
-	/* Stop the world on instructions we don't support... */
-	BUG_ON(aarch64_insn_is_cbz(insn));
-	BUG_ON(aarch64_insn_is_cbnz(insn));
-	BUG_ON(aarch64_insn_is_bcond(insn));
-	/* ... and there is probably more. */
-
-	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
-		enum aarch64_insn_branch_type type;
+	if (aarch64_insn_is_branch_imm(insn)) {
+		s32 offset = aarch64_get_branch_offset(insn);
 		unsigned long target;
 
-		if (aarch64_insn_is_b(insn))
-			type = AARCH64_INSN_BRANCH_NOLINK;
-		else
-			type = AARCH64_INSN_BRANCH_LINK;
+		target = (unsigned long)altinsnptr + offset;
 
-		target = (unsigned long)altinsnptr + get_branch_offset(insn);
-		insn = aarch64_insn_gen_branch_imm((unsigned long)insnptr,
-						   target, type);
+		/*
+		 * If we're branching inside the alternate sequence,
+		 * do not rewrite the instruction, as it is already
+		 * correct. Otherwise, generate the new instruction.
+		 */
+		if (branch_insn_requires_update(alt, target)) {
+			offset = target - (unsigned long)insnptr;
+			insn = aarch64_set_branch_offset(insn, offset);
+		}
 	}
 
 	return insn;
@@ -80,11 +89,11 @@ static int __apply_alternatives(void *alt_region)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
-	u8 *origptr, *replptr;
+	u32 *origptr, *replptr;
 
 	for (alt = region->begin; alt < region->end; alt++) {
 		u32 insn;
-		int i;
+		int i, nr_inst;
 
 		if (!cpus_have_cap(alt->cpufeature))
 			continue;
@@ -93,16 +102,17 @@ static int __apply_alternatives(void *alt_region)
 
 		pr_info_once("patching kernel code\n");
 
-		origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
-		replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
+		origptr = ALT_ORIG_PTR(alt);
+		replptr = ALT_REPL_PTR(alt);
+		nr_inst = alt->alt_len / sizeof(insn);
 
-		for (i = 0; i < alt->alt_len; i += sizeof(insn)) {
-			insn = get_alt_insn(origptr + i, replptr + i);
-			aarch64_insn_write(origptr + i, insn);
+		for (i = 0; i < nr_inst; i++) {
+			insn = get_alt_insn(alt, origptr + i, replptr + i);
+			*(origptr + i) = cpu_to_le32(insn);
 		}
 
 		flush_icache_range((uintptr_t)origptr,
-				   (uintptr_t)(origptr + alt->alt_len));
+				   (uintptr_t)(origptr + nr_inst));
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index da675cc5dfae..c99701a34d7b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -127,7 +127,6 @@ int main(void)
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_SAVE_FN,		offsetof(struct vgic_sr_vectors, save_vgic));
   DEFINE(VGIC_RESTORE_FN,	offsetof(struct vgic_sr_vectors, restore_vgic));
-  DEFINE(VGIC_SR_VECTOR_SZ,	sizeof(struct vgic_sr_vectors));
   DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
   DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
   DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index fb8ff9ba467a..5ea337dd2f15 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -16,11 +16,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <asm/cpu_ops.h>
-#include <asm/smp_plat.h>
+#include <linux/acpi.h>
 #include <linux/errno.h>
 #include <linux/of.h>
 #include <linux/string.h>
+#include <asm/acpi.h>
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
 
 extern const struct cpu_operations smp_spin_table_ops;
 extern const struct cpu_operations cpu_psci_ops;
@@ -35,7 +37,7 @@ static const struct cpu_operations *supported_cpu_ops[] __initconst = {
 	NULL,
 };
 
-const struct cpu_operations * __init cpu_get_ops(const char *name)
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
 {
 	const struct cpu_operations **ops = supported_cpu_ops;
 
@@ -49,39 +51,53 @@ const struct cpu_operations * __init cpu_get_ops(const char *name)
 	return NULL;
 }
 
+static const char *__init cpu_read_enable_method(int cpu)
+{
+	const char *enable_method;
+
+	if (acpi_disabled) {
+		struct device_node *dn = of_get_cpu_node(cpu, NULL);
+
+		if (!dn) {
+			if (!cpu)
+				pr_err("Failed to find device node for boot cpu\n");
+			return NULL;
+		}
+
+		enable_method = of_get_property(dn, "enable-method", NULL);
+		if (!enable_method) {
+			/*
+			 * The boot CPU may not have an enable method (e.g.
+			 * when spin-table is used for secondaries).
+			 * Don't warn spuriously.
+			 */
+			if (cpu != 0)
+				pr_err("%s: missing enable-method property\n",
+					dn->full_name);
+		}
+	} else {
+		enable_method = acpi_get_enable_method(cpu);
+		if (!enable_method)
+			pr_err("Unsupported ACPI enable-method\n");
+	}
+
+	return enable_method;
+}
 /*
- * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ * Read a cpu's enable method and record it in cpu_ops.
  */
-int __init cpu_read_ops(struct device_node *dn, int cpu)
+int __init cpu_read_ops(int cpu)
 {
-	const char *enable_method = of_get_property(dn, "enable-method", NULL);
-	if (!enable_method) {
-		/*
-		 * The boot CPU may not have an enable method (e.g. when
-		 * spin-table is used for secondaries). Don't warn spuriously.
-		 */
-		if (cpu != 0)
-			pr_err("%s: missing enable-method property\n",
-				dn->full_name);
-		return -ENOENT;
-	}
+	const char *enable_method = cpu_read_enable_method(cpu);
+
+	if (!enable_method)
+		return -ENODEV;
 
 	cpu_ops[cpu] = cpu_get_ops(enable_method);
 	if (!cpu_ops[cpu]) {
-		pr_warn("%s: unsupported enable-method property: %s\n",
-			dn->full_name, enable_method);
+		pr_warn("Unsupported enable-method: %s\n", enable_method);
 		return -EOPNOTSUPP;
 	}
 
 	return 0;
 }
-
-void __init cpu_read_bootcpu_ops(void)
-{
-	struct device_node *dn = of_get_cpu_node(0, NULL);
-	if (!dn) {
-		pr_err("Failed to find device node for boot cpu\n");
-		return;
-	}
-	cpu_read_ops(dn, 0);
-}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3d9967e43d89..5ad86ceac010 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -22,7 +22,23 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
+static bool
+has_id_aa64pfr0_feature(const struct arm64_cpu_capabilities *entry)
+{
+	u64 val;
+
+	val = read_cpuid(id_aa64pfr0_el1);
+	return (val & entry->register_mask) == entry->register_value;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
+	{
+		.desc = "GIC system register CPU interface",
+		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
+		.matches = has_id_aa64pfr0_feature,
+		.register_mask = (0xf << 24),
+		.register_value = (1 << 24),
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index a78143a5c99f..7ce589ca54a4 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -18,15 +18,10 @@
 int arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
-	struct device_node *cpu_node = of_cpu_device_node_get(cpu);
-
-	if (!cpu_node)
-		return -ENODEV;
 
 	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
-		ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+		ret = cpu_ops[cpu]->cpu_init_idle(cpu);
 
-	of_node_put(cpu_node);
 	return ret;
 }
 
@@ -37,7 +32,7 @@ int arm_cpuidle_init(unsigned int cpu)
  * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
  * operations back-end error code otherwise.
  */
-int cpu_suspend(unsigned long arg)
+int arm_cpuidle_suspend(int index)
 {
 	int cpu = smp_processor_id();
 
@@ -47,5 +42,5 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
-	return cpu_ops[cpu]->cpu_suspend(arg);
+	return cpu_ops[cpu]->cpu_suspend(index);
 }
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 959fe8733560..a7691a378668 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
@@ -124,21 +124,24 @@
 	msr	sp_el0, x23
 
 #ifdef CONFIG_ARM64_ERRATUM_845719
-	alternative_insn						\
-	"nop",								\
-	"tbz x22, #4, 1f",						\
-	ARM64_WORKAROUND_845719
+
+#undef SEQUENCE_ORG
+#undef SEQUENCE_ALT
+
 #ifdef CONFIG_PID_IN_CONTEXTIDR
-	alternative_insn						\
-	"nop; nop",							\
-	"mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:",		\
-	ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG	"nop ; nop ; nop"
+#define SEQUENCE_ALT	"tbz x22, #4, 1f ; mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:"
+
 #else
-	alternative_insn						\
-	"nop",								\
-	"msr contextidr_el1, xzr; 1:",					\
-	ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG	"nop ; nop"
+#define SEQUENCE_ALT	"tbz x22, #4, 1f ; msr contextidr_el1, xzr; 1:"
+
 #endif
+
+	alternative_insn SEQUENCE_ORG, SEQUENCE_ALT, ARM64_WORKAROUND_845719
+
 #endif
 	.endif
 	msr	elr_el1, x21			// set up the return data
@@ -517,6 +520,7 @@ el0_sp_pc:
 	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -608,11 +612,16 @@ ENDPROC(cpu_switch_to)
  */
 ret_fast_syscall:
 	disable_irq				// disable interrupts
-	ldr	x1, [tsk, #TI_FLAGS]
+	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
+	and	x2, x1, #_TIF_SYSCALL_WORK
+	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, fast_work_pending
 	enable_step_tsk x1, x2
 	kernel_exit 0, ret = 1
+ret_fast_syscall_trace:
+	enable_irq				// enable interrupts
+	b	__sys_trace_return
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 3dca15634e69..44d6f7545505 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -296,6 +297,35 @@ static void fpsimd_pm_init(void)
 static inline void fpsimd_pm_init(void) { }
 #endif /* CONFIG_CPU_PM */
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb,
+				       unsigned long action,
+				       void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		per_cpu(fpsimd_last_state, cpu) = NULL;
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_hotplug_notifier_block = {
+	.notifier_call = fpsimd_cpu_hotplug_notifier,
+};
+
+static inline void fpsimd_hotplug_init(void)
+{
+	register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block);
+}
+
+#else
+static inline void fpsimd_hotplug_init(void) { }
+#endif
+
 /*
  * FP/SIMD support code initialisation.
  */
@@ -315,6 +345,7 @@ static int __init fpsimd_init(void)
 		elf_hwcap |= HWCAP_ASIMD;
 
 	fpsimd_pm_init();
+	fpsimd_hotplug_init();
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 19f915e8f6e0..c0ff3ce4299e 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -237,8 +237,6 @@ ENTRY(stext)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
-
-	bl	__vet_fdt
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -270,24 +268,6 @@ preserve_boot_args:
 ENDPROC(preserve_boot_args)
 
 /*
- * Determine validity of the x21 FDT pointer.
- * The dtb must be 8-byte aligned and live in the first 512M of memory.
- */
-__vet_fdt:
-	tst	x21, #0x7
-	b.ne	1f
-	cmp	x21, x24
-	b.lt	1f
-	mov	x0, #(1 << 29)
-	add	x0, x0, x24
-	cmp	x21, x0
-	b.ge	1f
-	ret
-1:
-	mov	x21, #0
-	ret
-ENDPROC(__vet_fdt)
-/*
  * Macro to create a table entry to the next page.
  *
  *	tbl:	page table address
@@ -348,8 +328,7 @@ ENDPROC(__vet_fdt)
  * required to get the kernel running. The following sections are required:
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
- *     been enabled, including the FDT blob (TTBR1)
- *   - pgd entry for fixed mappings (TTBR1)
+ *     been enabled
  */
 __create_page_tables:
 	adrp	x25, idmap_pg_dir
@@ -382,7 +361,7 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	mov	x0, x25				// idmap_pg_dir
-	adrp	x3, KERNEL_START		// __pa(KERNEL_START)
+	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
 #ifndef CONFIG_ARM64_VA_BITS_48
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
@@ -405,11 +384,11 @@ __create_page_tables:
 
 	/*
 	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
-	 * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used),
+	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
 	 * this number conveniently equals the number of leading zeroes in
-	 * the physical address of KERNEL_END.
+	 * the physical address of __idmap_text_end.
 	 */
-	adrp	x5, KERNEL_END
+	adrp	x5, __idmap_text_end
 	clz	x5, x5
 	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
 	b.ge	1f			// .. then skip additional level
@@ -424,8 +403,8 @@ __create_page_tables:
 #endif
 
 	create_pgd_entry x0, x3, x5, x6
-	mov	x5, x3				// __pa(KERNEL_START)
-	adr_l	x6, KERNEL_END			// __pa(KERNEL_END)
+	mov	x5, x3				// __pa(__idmap_text_start)
+	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
@@ -439,22 +418,6 @@ __create_page_tables:
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
-	 * Map the FDT blob (maximum 2MB; must be within 512MB of
-	 * PHYS_OFFSET).
-	 */
-	mov	x3, x21				// FDT phys address
-	and	x3, x3, #~((1 << 21) - 1)	// 2MB aligned
-	mov	x6, #PAGE_OFFSET
-	sub	x5, x3, x24			// subtract PHYS_OFFSET
-	tst	x5, #~((1 << 29) - 1)		// within 512MB?
-	csel	x21, xzr, x21, ne		// zero the FDT pointer
-	b.ne	1f
-	add	x5, x5, x6			// __va(FDT blob)
-	add	x6, x5, #1 << 21		// 2MB for the FDT blob
-	sub	x6, x6, #1			// inclusive range
-	create_block_map x0, x7, x3, x5, x6
-1:
-	/*
 	 * Since the page tables have been populated with non-cacheable
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
@@ -669,6 +632,7 @@ ENDPROC(__secondary_switched)
  *
  * other registers depend on the function called upon completion
  */
+	.section	".idmap.text", "ax"
 __enable_mmu:
 	ldr	x5, =vectors
 	msr	vbar_el1, x5
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 924902083e47..dd9671cd0bb2 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -77,6 +77,14 @@ bool __kprobes aarch64_insn_is_nop(u32 insn)
 	}
 }
 
+bool aarch64_insn_is_branch_imm(u32 insn)
+{
+	return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) ||
+		aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) ||
+		aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+		aarch64_insn_is_bcond(insn));
+}
+
 static DEFINE_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
@@ -1057,6 +1065,58 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
 
+/*
+ * Decode the imm field of a branch, and return the byte offset as a
+ * signed value (so it can be used when computing a new branch
+ * target).
+ */
+s32 aarch64_get_branch_offset(u32 insn)
+{
+	s32 imm;
+
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+		return (imm << 6) >> 4;
+	}
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn);
+		return (imm << 13) >> 11;
+	}
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn);
+		return (imm << 18) >> 16;
+	}
+
+	/* Unhandled instruction */
+	BUG();
+}
+
+/*
+ * Encode the displacement of a branch in the imm field and return the
+ * updated instruction.
+ */
+u32 aarch64_set_branch_offset(u32 insn, s32 offset)
+{
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn,
+						     offset >> 2);
+
+	/* Unhandled instruction */
+	BUG();
+}
+
 bool aarch32_insn_is_wide(u32 insn)
 {
 	return insn >= 0xe800;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 23f25acf43a9..702591f6180a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -488,7 +488,7 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 			}
 
 			err = request_irq(irq, armpmu->handle_irq,
-					IRQF_NOBALANCING,
+					IRQF_NOBALANCING | IRQF_NO_THREAD,
 					"arm-pmu", armpmu);
 			if (err) {
 				pr_err("unable to request IRQ%d for ARM PMU counters\n",
@@ -1315,15 +1315,15 @@ static int armpmu_device_probe(struct platform_device *pdev)
 	if (!cpu_pmu)
 		return -ENODEV;
 
-	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
-	if (!irqs)
-		return -ENOMEM;
-
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
 	if (irq >= 0 && irq_is_percpu(irq))
 		return 0;
 
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+	if (!irqs)
+		return -ENOMEM;
+
 	for (i = 0; i < pdev->num_resources; ++i) {
 		struct device_node *dn;
 		int cpu;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c6b1f3b96f45..223b093c9440 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -58,14 +58,6 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-void soft_restart(unsigned long addr)
-{
-	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
-	/* Should never get here */
-	BUG();
-}
-
 /*
  * Function pointers to optional machine specific functions
  */
@@ -136,9 +128,7 @@ void machine_power_off(void)
 
 /*
  * Restart requires that the secondary CPUs stop performing any activity
- * while the primary CPU resets the system. Systems with a single CPU can
- * use soft_restart() as their machine descriptor's .restart hook, since that
- * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * while the primary CPU resets the system. Systems with multiple CPUs must
  * provide a HW restart implementation, to ensure that all CPUs reset at once.
  * This is required so that any code running after reset on the primary CPU
  * doesn't have to co-ordinate with other CPUs to ensure they aren't still
@@ -243,7 +233,8 @@ void release_thread(struct task_struct *dead_task)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	fpsimd_preserve_current_state();
+	if (current->mm)
+		fpsimd_preserve_current_state();
 	*dst = *src;
 	return 0;
 }
@@ -254,35 +245,35 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		unsigned long stk_sz, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
-	unsigned long tls = p->thread.tp_value;
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
-		if (is_compat_thread(task_thread_info(p))) {
-			if (stack_start)
+
+		/*
+		 * Read the current TLS pointer from tpidr_el0 as it may be
+		 * out-of-sync with the saved value.
+		 */
+		asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+
+		if (stack_start) {
+			if (is_compat_thread(task_thread_info(p)))
 				childregs->compat_sp = stack_start;
-		} else {
-			/*
-			 * Read the current TLS pointer from tpidr_el0 as it may be
-			 * out-of-sync with the saved value.
-			 */
-			asm("mrs %0, tpidr_el0" : "=r" (tls));
-			if (stack_start) {
-				/* 16-byte aligned stack mandatory on AArch64 */
-				if (stack_start & 15)
-					return -EINVAL;
+			/* 16-byte aligned stack mandatory on AArch64 */
+			else if (stack_start & 15)
+				return -EINVAL;
+			else
 				childregs->sp = stack_start;
-			}
 		}
+
 		/*
 		 * If a TLS pointer was passed to clone (4th argument), use it
 		 * for the new thread.
 		 */
 		if (clone_flags & CLONE_SETTLS)
-			tls = childregs->regs[3];
+			p->thread.tp_value = childregs->regs[3];
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h;
@@ -291,7 +282,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;
-	p->thread.tp_value = tls;
 
 	ptrace_hw_copy_thread(p);
 
@@ -302,18 +292,12 @@ static void tls_thread_switch(struct task_struct *next)
 {
 	unsigned long tpidr, tpidrro;
 
-	if (!is_compat_task()) {
-		asm("mrs %0, tpidr_el0" : "=r" (tpidr));
-		current->thread.tp_value = tpidr;
-	}
+	asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+	*task_user_tls(current) = tpidr;
 
-	if (is_compat_thread(task_thread_info(next))) {
-		tpidr = 0;
-		tpidrro = next->thread.tp_value;
-	} else {
-		tpidr = next->thread.tp_value;
-		tpidrro = 0;
-	}
+	tpidr = *task_user_tls(next);
+	tpidrro = is_compat_thread(task_thread_info(next)) ?
+		  next->thread.tp_value : 0;
 
 	asm(
 	"	msr	tpidr_el0, %0\n"
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index ea18cb53921e..869f202748e8 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -15,7 +15,6 @@
 
 #define pr_fmt(fmt) "psci: " fmt
 
-#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
@@ -25,8 +24,8 @@
 #include <linux/slab.h>
 #include <uapi/linux/psci.h>
 
-#include <asm/acpi.h>
 #include <asm/compiler.h>
+#include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
@@ -37,16 +36,31 @@
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
 
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
+static bool psci_power_state_loses_context(u32 state)
+{
+	return state & PSCI_0_2_POWER_STATE_TYPE_MASK;
+}
+
+static bool psci_power_state_is_valid(u32 state)
+{
+	const u32 valid_mask = PSCI_0_2_POWER_STATE_ID_MASK |
+			       PSCI_0_2_POWER_STATE_TYPE_MASK |
+			       PSCI_0_2_POWER_STATE_AFFL_MASK;
+
+	return !(state & ~valid_mask);
+}
+
+/*
+ * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
+ * calls to its resident CPU, so we must avoid issuing those. We never migrate
+ * a Trusted OS even if it claims to be capable of migration -- doing so will
+ * require cooperation with a Trusted OS driver.
+ */
+static int resident_cpu = -1;
 
 struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
+	int (*cpu_suspend)(u32 state, unsigned long entry_point);
+	int (*cpu_off)(u32 state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
 	int (*migrate)(unsigned long cpuid);
 	int (*affinity_info)(unsigned long target_affinity,
@@ -56,23 +70,21 @@ struct psci_operations {
 
 static struct psci_operations psci_ops;
 
-static int (*invoke_psci_fn)(u64, u64, u64, u64);
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
-asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
+typedef unsigned long (psci_fn)(unsigned long, unsigned long,
+				unsigned long, unsigned long);
+asmlinkage psci_fn __invoke_psci_fn_hvc;
+asmlinkage psci_fn __invoke_psci_fn_smc;
+static psci_fn *invoke_psci_fn;
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
-	PSCI_FN_AFFINITY_INFO,
-	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
-static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
 
 static u32 psci_function_id[PSCI_FN_MAX];
 
@@ -92,56 +104,28 @@ static int psci_to_linux_errno(int errno)
 	return -EINVAL;
 }
 
-static u32 psci_power_state_pack(struct psci_power_state state)
-{
-	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
-			& PSCI_0_2_POWER_STATE_ID_MASK) |
-		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
-		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
-		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
-		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
-}
-
-static void psci_power_state_unpack(u32 power_state,
-				    struct psci_power_state *state)
-{
-	state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >>
-			PSCI_0_2_POWER_STATE_ID_SHIFT;
-	state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >>
-			PSCI_0_2_POWER_STATE_TYPE_SHIFT;
-	state->affinity_level =
-			(power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >>
-			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
-}
-
-static int psci_get_version(void)
+static u32 psci_get_version(void)
 {
-	int err;
-
-	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
-	return err;
+	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
 }
 
-static int psci_cpu_suspend(struct psci_power_state state,
-			    unsigned long entry_point)
+static int psci_cpu_suspend(u32 state, unsigned long entry_point)
 {
 	int err;
-	u32 fn, power_state;
+	u32 fn;
 
 	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, entry_point, 0);
+	err = invoke_psci_fn(fn, state, entry_point, 0);
 	return psci_to_linux_errno(err);
 }
 
-static int psci_cpu_off(struct psci_power_state state)
+static int psci_cpu_off(u32 state)
 {
 	int err;
-	u32 fn, power_state;
+	u32 fn;
 
 	fn = psci_function_id[PSCI_FN_CPU_OFF];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, 0, 0);
+	err = invoke_psci_fn(fn, state, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
@@ -168,30 +152,29 @@ static int psci_migrate(unsigned long cpuid)
 static int psci_affinity_info(unsigned long target_affinity,
 		unsigned long lowest_affinity_level)
 {
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
-	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
-	return err;
+	return invoke_psci_fn(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity,
+			      lowest_affinity_level, 0);
 }
 
 static int psci_migrate_info_type(void)
 {
-	int err;
-	u32 fn;
+	return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
+}
 
-	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
-	err = invoke_psci_fn(fn, 0, 0, 0);
-	return err;
+static unsigned long psci_migrate_info_up_cpu(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU, 0, 0, 0);
 }
 
-static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
-						 unsigned int cpu)
+static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu)
 {
 	int i, ret, count = 0;
-	struct psci_power_state *psci_states;
-	struct device_node *state_node;
+	u32 *psci_states;
+	struct device_node *state_node, *cpu_node;
+
+	cpu_node = of_get_cpu_node(cpu, NULL);
+	if (!cpu_node)
+		return -ENODEV;
 
 	/*
 	 * If the PSCI cpu_suspend function hook has not been initialized
@@ -215,13 +198,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
 		return -ENOMEM;
 
 	for (i = 0; i < count; i++) {
-		u32 psci_power_state;
+		u32 state;
 
 		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
 
 		ret = of_property_read_u32(state_node,
 					   "arm,psci-suspend-param",
-					   &psci_power_state);
+					   &state);
 		if (ret) {
 			pr_warn(" * %s missing arm,psci-suspend-param property\n",
 				state_node->full_name);
@@ -230,9 +213,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
 		}
 
 		of_node_put(state_node);
-		pr_debug("psci-power-state %#x index %d\n", psci_power_state,
-							    i);
-		psci_power_state_unpack(psci_power_state, &psci_states[i]);
+		pr_debug("psci-power-state %#x index %d\n", state, i);
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			ret = -EINVAL;
+			goto free_mem;
+		}
+		psci_states[i] = state;
 	}
 	/* Idle states parsed correctly, initialize per-cpu pointer */
 	per_cpu(psci_power_state, cpu) = psci_states;
@@ -275,6 +262,46 @@ static void psci_sys_poweroff(void)
 	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
 }
 
+/*
+ * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
+ * return DENIED (which would be fatal).
+ */
+static void __init psci_init_migrate(void)
+{
+	unsigned long cpuid;
+	int type, cpu;
+
+	type = psci_ops.migrate_info_type();
+
+	if (type == PSCI_0_2_TOS_MP) {
+		pr_info("Trusted OS migration not required\n");
+		return;
+	}
+
+	if (type == PSCI_RET_NOT_SUPPORTED) {
+		pr_info("MIGRATE_INFO_TYPE not supported.\n");
+		return;
+	}
+
+	if (type != PSCI_0_2_TOS_UP_MIGRATE &&
+	    type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
+		pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
+		return;
+	}
+
+	cpuid = psci_migrate_info_up_cpu();
+	if (cpuid & ~MPIDR_HWID_BITMASK) {
+		pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
+			cpuid);
+		return;
+	}
+
+	cpu = get_logical_index(cpuid);
+	resident_cpu = cpu >= 0 ? cpu : -1;
+
+	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
+}
+
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
@@ -290,11 +317,8 @@ static void __init psci_0_2_set_functions(void)
 	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
 	psci_ops.migrate = psci_migrate;
 
-	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO;
 	psci_ops.affinity_info = psci_affinity_info;
 
-	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
-		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
 	psci_ops.migrate_info_type = psci_migrate_info_type;
 
 	arm_pm_restart = psci_sys_reset;
@@ -307,32 +331,26 @@ static void __init psci_0_2_set_functions(void)
  */
 static int __init psci_probe(void)
 {
-	int ver = psci_get_version();
-
-	if (ver == PSCI_RET_NOT_SUPPORTED) {
-		/*
-		 * PSCI versions >=0.2 mandates implementation of
-		 * PSCI_VERSION.
-		 */
-		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
-		return -EOPNOTSUPP;
-	} else {
-		pr_info("PSCIv%d.%d detected in firmware.\n",
-				PSCI_VERSION_MAJOR(ver),
-				PSCI_VERSION_MINOR(ver));
-
-		if (PSCI_VERSION_MAJOR(ver) == 0 &&
-				PSCI_VERSION_MINOR(ver) < 2) {
-			pr_err("Conflicting PSCI version detected.\n");
-			return -EINVAL;
-		}
+	u32 ver = psci_get_version();
+
+	pr_info("PSCIv%d.%d detected in firmware.\n",
+			PSCI_VERSION_MAJOR(ver),
+			PSCI_VERSION_MINOR(ver));
+
+	if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
+		pr_err("Conflicting PSCI version detected.\n");
+		return -EINVAL;
 	}
 
 	psci_0_2_set_functions();
 
+	psci_init_migrate();
+
 	return 0;
 }
 
+typedef int (*psci_initcall_t)(const struct device_node *);
+
 /*
  * PSCI init function for PSCI versions >=0.2
  *
@@ -421,6 +439,7 @@ int __init psci_dt_init(void)
 	return init_fn(np);
 }
 
+#ifdef CONFIG_ACPI
 /*
  * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
  * explicitly clarified in SBBR
@@ -441,10 +460,11 @@ int __init psci_acpi_init(void)
 
 	return psci_probe();
 }
+#endif
 
 #ifdef CONFIG_SMP
 
-static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+static int __init cpu_psci_cpu_init(unsigned int cpu)
 {
 	return 0;
 }
@@ -469,11 +489,21 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static bool psci_tos_resident_on(int cpu)
+{
+	return cpu == resident_cpu;
+}
+
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
 	if (!psci_ops.cpu_off)
 		return -EOPNOTSUPP;
+
+	/* Trusted OS will deny CPU_OFF */
+	if (psci_tos_resident_on(cpu))
+		return -EPERM;
+
 	return 0;
 }
 
@@ -484,9 +514,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 	 * There are no known implementations of PSCI actually using the
 	 * power state field, pass a sensible default for now.
 	 */
-	struct psci_power_state state = {
-		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
-	};
+	u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
+		    PSCI_0_2_POWER_STATE_TYPE_SHIFT;
 
 	ret = psci_ops.cpu_off(state);
 
@@ -498,7 +527,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	int err, i;
 
 	if (!psci_ops.affinity_info)
-		return 1;
+		return 0;
 	/*
 	 * cpu_kill could race with cpu_die and we can
 	 * potentially end up declaring this cpu undead
@@ -509,7 +538,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
 			pr_info("CPU%d killed.\n", cpu);
-			return 1;
+			return 0;
 		}
 
 		msleep(10);
@@ -518,15 +547,14 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
-	/* Make op_cpu_kill() fail. */
-	return 0;
+	return -ETIMEDOUT;
 }
 #endif
 #endif
 
 static int psci_suspend_finisher(unsigned long index)
 {
-	struct psci_power_state *state = __this_cpu_read(psci_power_state);
+	u32 *state = __this_cpu_read(psci_power_state);
 
 	return psci_ops.cpu_suspend(state[index - 1],
 				    virt_to_phys(cpu_resume));
@@ -535,7 +563,7 @@ static int psci_suspend_finisher(unsigned long index)
 static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
 {
 	int ret;
-	struct psci_power_state *state = __this_cpu_read(psci_power_state);
+	u32 *state = __this_cpu_read(psci_power_state);
 	/*
 	 * idle state index 0 corresponds to wfi, should never be called
 	 * from the cpu_suspend operations
@@ -543,10 +571,10 @@ static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
 	if (WARN_ON_ONCE(!index))
 		return -EINVAL;
 
-	if (state[index - 1].type == PSCI_POWER_STATE_TYPE_STANDBY)
+	if (!psci_power_state_loses_context(state[index - 1]))
 		ret = psci_ops.cpu_suspend(state[index - 1], 0);
 	else
-		ret = __cpu_suspend(index, psci_suspend_finisher);
+		ret = cpu_suspend(index, psci_suspend_finisher);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 74753132c3ac..ffd3970721bf 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -105,18 +105,6 @@ static struct resource mem_res[] = {
 #define kernel_code mem_res[0]
 #define kernel_data mem_res[1]
 
-void __init early_print(const char *str, ...)
-{
-	char buf[256];
-	va_list ap;
-
-	va_start(ap, str);
-	vsnprintf(buf, sizeof(buf), str, ap);
-	va_end(ap);
-
-	printk("%s", buf);
-}
-
 /*
  * The recorded values of x0 .. x3 upon kernel entry.
  */
@@ -326,12 +314,14 @@ static void __init setup_processor(void)
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) {
-		early_print("\n"
-			"Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n"
-			"The dtb must be 8-byte aligned and passed in the first 512MB of memory\n"
-			"\nPlease check your bootloader.\n",
-			dt_phys, phys_to_virt(dt_phys));
+	void *dt_virt = fixmap_remap_fdt(dt_phys);
+
+	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
+		pr_crit("\n"
+			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
+			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
+			"\nPlease check your bootloader.",
+			&dt_phys, dt_virt);
 
 		while (true)
 			cpu_relax();
@@ -374,8 +364,6 @@ void __init setup_arch(char **cmdline_p)
 {
 	setup_processor();
 
-	setup_machine_fdt(__fdt_pointer);
-
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -386,6 +374,8 @@ void __init setup_arch(char **cmdline_p)
 	early_fixmap_init();
 	early_ioremap_init();
 
+	setup_machine_fdt(__fdt_pointer);
+
 	parse_early_param();
 
 	/*
@@ -408,16 +398,13 @@ void __init setup_arch(char **cmdline_p)
 	if (acpi_disabled) {
 		unflatten_device_tree();
 		psci_dt_init();
-		cpu_read_bootcpu_ops();
-#ifdef CONFIG_SMP
-		of_smp_init_cpus();
-#endif
 	} else {
 		psci_acpi_init();
-		acpi_init_cpus();
 	}
 
+	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
+	smp_init_cpus();
 	smp_build_mpidr_hash();
 #endif
 
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d26fcd4cd6e6..1670f15ef69e 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -370,7 +370,7 @@ badframe:
 	if (show_unhandled_signals)
 		pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
 				    current->comm, task_pid_nr(current), __func__,
-				    regs->pc, regs->sp);
+				    regs->pc, regs->compat_sp);
 	force_sig(SIGSEGV, current);
 	return 0;
 }
@@ -407,7 +407,7 @@ badframe:
 	if (show_unhandled_signals)
 		pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
 				    current->comm, task_pid_nr(current), __func__,
-				    regs->pc, regs->sp);
+				    regs->pc, regs->compat_sp);
 	force_sig(SIGSEGV, current);
 	return 0;
 }
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ede186cdd452..803cfea41962 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -130,12 +130,14 @@ ENDPROC(__cpu_suspend_enter)
 /*
  * x0 must contain the sctlr value retrieved from restored context
  */
+	.pushsection	".idmap.text", "ax"
 ENTRY(cpu_resume_mmu)
 	ldr	x3, =cpu_resume_after_mmu
 	msr	sctlr_el1, x0		// restore sctlr_el1
 	isb
 	br	x3			// global jump to virtual address
 ENDPROC(cpu_resume_mmu)
+	.popsection
 cpu_resume_after_mmu:
 	mov	x0, #0			// return zero on success
 	ldp	x19, x20, [sp, #16]
@@ -162,15 +164,12 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adrp	x0, sleep_save_sp
-	add	x0, x0, #:lo12:sleep_save_sp
-	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
+	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
+	adrp	x1, idmap_pg_dir
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2cb008177252..4b2121bd7f9c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
@@ -248,20 +249,20 @@ static int op_cpu_kill(unsigned int cpu)
 	 * time and hope that it's dead, so let's skip the wait and just hope.
 	 */
 	if (!cpu_ops[cpu]->cpu_kill)
-		return 1;
+		return 0;
 
 	return cpu_ops[cpu]->cpu_kill(cpu);
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	int err;
+
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_crit("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -273,8 +274,10 @@ void __cpu_die(unsigned int cpu)
 	 * verify that it has really left the kernel before we consider
 	 * clobbering anything it might still be using.
 	 */
-	if (!op_cpu_kill(cpu))
-		pr_warn("CPU%d may not have shut down cleanly\n", cpu);
+	err = op_cpu_kill(cpu);
+	if (err)
+		pr_warn("CPU%d may not have shut down cleanly: %d\n",
+			cpu, err);
 }
 
 /*
@@ -294,7 +297,7 @@ void cpu_die(void)
 	local_irq_disable();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Actually shutdown the CPU. This must never fail. The specific hotplug
@@ -318,57 +321,158 @@ void __init smp_prepare_boot_cpu(void)
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 }
 
+static u64 __init of_get_cpu_mpidr(struct device_node *dn)
+{
+	const __be32 *cell;
+	u64 hwid;
+
+	/*
+	 * A cpu node with missing "reg" property is
+	 * considered invalid to build a cpu_logical_map
+	 * entry.
+	 */
+	cell = of_get_property(dn, "reg", NULL);
+	if (!cell) {
+		pr_err("%s: missing reg property\n", dn->full_name);
+		return INVALID_HWID;
+	}
+
+	hwid = of_read_number(cell, of_n_addr_cells(dn));
+	/*
+	 * Non affinity bits must be set to 0 in the DT
+	 */
+	if (hwid & ~MPIDR_HWID_BITMASK) {
+		pr_err("%s: invalid reg property\n", dn->full_name);
+		return INVALID_HWID;
+	}
+	return hwid;
+}
+
+/*
+ * Duplicate MPIDRs are a recipe for disaster. Scan all initialized
+ * entries and check for duplicates. If any is found just ignore the
+ * cpu. cpu_logical_map was initialized to INVALID_HWID to avoid
+ * matching valid MPIDR values.
+ */
+static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
+{
+	unsigned int i;
+
+	for (i = 1; (i < cpu) && (i < NR_CPUS); i++)
+		if (cpu_logical_map(i) == hwid)
+			return true;
+	return false;
+}
+
+/*
+ * Initialize cpu operations for a logical cpu and
+ * set it in the possible mask on success
+ */
+static int __init smp_cpu_setup(int cpu)
+{
+	if (cpu_read_ops(cpu))
+		return -ENODEV;
+
+	if (cpu_ops[cpu]->cpu_init(cpu))
+		return -ENODEV;
+
+	set_cpu_possible(cpu, true);
+
+	return 0;
+}
+
+static bool bootcpu_valid __initdata;
+static unsigned int cpu_count = 1;
+
+#ifdef CONFIG_ACPI
+/*
+ * acpi_map_gic_cpu_interface - parse processor MADT entry
+ *
+ * Carry out sanity checks on MADT processor entry and initialize
+ * cpu_logical_map on success
+ */
+static void __init
+acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+{
+	u64 hwid = processor->arm_mpidr;
+
+	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
+		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
+		return;
+	}
+
+	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+		pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
+		return;
+	}
+
+	if (is_mpidr_duplicate(cpu_count, hwid)) {
+		pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid);
+		return;
+	}
+
+	/* Check if GICC structure of boot CPU is available in the MADT */
+	if (cpu_logical_map(0) == hwid) {
+		if (bootcpu_valid) {
+			pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n",
+			       hwid);
+			return;
+		}
+		bootcpu_valid = true;
+		return;
+	}
+
+	if (cpu_count >= NR_CPUS)
+		return;
+
+	/* map the logical cpu id to cpu MPIDR */
+	cpu_logical_map(cpu_count) = hwid;
+
+	cpu_count++;
+}
+
+static int __init
+acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
+			     const unsigned long end)
+{
+	struct acpi_madt_generic_interrupt *processor;
+
+	processor = (struct acpi_madt_generic_interrupt *)header;
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(header);
+
+	acpi_map_gic_cpu_interface(processor);
+
+	return 0;
+}
+#else
+#define acpi_table_parse_madt(...)	do { } while (0)
+#endif
+
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
  * cpus. Assumes that cpu_logical_map(0) has already been initialized.
  */
-void __init of_smp_init_cpus(void)
+void __init of_parse_and_init_cpus(void)
 {
 	struct device_node *dn = NULL;
-	unsigned int i, cpu = 1;
-	bool bootcpu_valid = false;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
-		const u32 *cell;
-		u64 hwid;
+		u64 hwid = of_get_cpu_mpidr(dn);
 
-		/*
-		 * A cpu node with missing "reg" property is
-		 * considered invalid to build a cpu_logical_map
-		 * entry.
-		 */
-		cell = of_get_property(dn, "reg", NULL);
-		if (!cell) {
-			pr_err("%s: missing reg property\n", dn->full_name);
+		if (hwid == INVALID_HWID)
 			goto next;
-		}
-		hwid = of_read_number(cell, of_n_addr_cells(dn));
 
-		/*
-		 * Non affinity bits must be set to 0 in the DT
-		 */
-		if (hwid & ~MPIDR_HWID_BITMASK) {
-			pr_err("%s: invalid reg property\n", dn->full_name);
+		if (is_mpidr_duplicate(cpu_count, hwid)) {
+			pr_err("%s: duplicate cpu reg properties in the DT\n",
+				dn->full_name);
 			goto next;
 		}
 
 		/*
-		 * Duplicate MPIDRs are a recipe for disaster. Scan
-		 * all initialized entries and check for
-		 * duplicates. If any is found just ignore the cpu.
-		 * cpu_logical_map was initialized to INVALID_HWID to
-		 * avoid matching valid MPIDR values.
-		 */
-		for (i = 1; (i < cpu) && (i < NR_CPUS); i++) {
-			if (cpu_logical_map(i) == hwid) {
-				pr_err("%s: duplicate cpu reg properties in the DT\n",
-					dn->full_name);
-				goto next;
-			}
-		}
-
-		/*
 		 * The numbering scheme requires that the boot CPU
 		 * must be assigned logical id 0. Record it so that
 		 * the logical map built from DT is validated and can
@@ -392,38 +496,58 @@ void __init of_smp_init_cpus(void)
 			continue;
 		}
 
-		if (cpu >= NR_CPUS)
-			goto next;
-
-		if (cpu_read_ops(dn, cpu) != 0)
-			goto next;
-
-		if (cpu_ops[cpu]->cpu_init(dn, cpu))
+		if (cpu_count >= NR_CPUS)
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
-		cpu_logical_map(cpu) = hwid;
+		cpu_logical_map(cpu_count) = hwid;
 next:
-		cpu++;
+		cpu_count++;
 	}
+}
+
+/*
+ * Enumerate the possible CPU set from the device tree or ACPI and build the
+ * cpu logical map array containing MPIDR values related to logical
+ * cpus. Assumes that cpu_logical_map(0) has already been initialized.
+ */
+void __init smp_init_cpus(void)
+{
+	int i;
 
-	/* sanity check */
-	if (cpu > NR_CPUS)
-		pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n",
-			   cpu, NR_CPUS);
+	if (acpi_disabled)
+		of_parse_and_init_cpus();
+	else
+		/*
+		 * do a walk of MADT to determine how many CPUs
+		 * we have including disabled CPUs, and get information
+		 * we need for SMP init
+		 */
+		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+				      acpi_parse_gic_cpu_interface, 0);
+
+	if (cpu_count > NR_CPUS)
+		pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
+			cpu_count, NR_CPUS);
 
 	if (!bootcpu_valid) {
-		pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n");
+		pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
 		return;
 	}
 
 	/*
-	 * All the cpus that made it to the cpu_logical_map have been
-	 * validated so set them as possible cpus.
+	 * We need to set the cpu_logical_map entries before enabling
+	 * the cpus so that cpu processor description entries (DT cpu nodes
+	 * and ACPI MADT entries) can be retrieved by matching the cpu hwid
+	 * with entries in cpu_logical_map while initializing the cpus.
+	 * If the cpu set-up fails, invalidate the cpu_logical_map entry.
 	 */
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_logical_map(i) != INVALID_HWID)
-			set_cpu_possible(i, true);
+	for (i = 1; i < NR_CPUS; i++) {
+		if (cpu_logical_map(i) != INVALID_HWID) {
+			if (smp_cpu_setup(i))
+				cpu_logical_map(i) = INVALID_HWID;
+		}
+	}
 }
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 14944e5b28da..aef3605a8c47 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -49,8 +49,14 @@ static void write_pen_release(u64 val)
 }
 
 
-static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
+static int smp_spin_table_cpu_init(unsigned int cpu)
 {
+	struct device_node *dn;
+
+	dn = of_get_cpu_node(cpu, NULL);
+	if (!dn)
+		return -ENODEV;
+
 	/*
 	 * Determine the address from which the CPU is polling.
 	 */
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index d7daf45ae7a2..8297d502217e 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -51,13 +51,13 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /*
- * __cpu_suspend
+ * cpu_suspend
  *
  * arg: argument to pass to the finisher function
  * fn: finisher function pointer
  *
  */
-int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	struct mm_struct *mm = current->active_mm;
 	int ret;
@@ -82,7 +82,7 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		 * We are resuming from reset with TTBR0_EL1 set to the
 		 * idmap to enable the MMU; restore the active_mm mappings in
 		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
-		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * the thread entered cpu_suspend with TTBR0_EL1 set to
 		 * reserved TTBR0 page tables and should be restored as such.
 		 */
 		if (mm == &init_mm)
@@ -118,7 +118,6 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 }
 
 struct sleep_save_sp sleep_save_sp;
-phys_addr_t sleep_idmap_phys;
 
 static int __init cpu_suspend_init(void)
 {
@@ -132,9 +131,7 @@ static int __init cpu_suspend_init(void)
 
 	sleep_save_sp.save_ptr_stash = ctx_ptr;
 	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
-	sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
 	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
-	__flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 1ef2940df13c..a12251c074a8 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -335,8 +335,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (call_undef_hook(regs) == 0)
 		return;
 
-	if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
-	    printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
 		dump_instr(KERN_INFO, regs);
@@ -363,7 +362,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 	}
 #endif
 
-	if (show_unhandled_signals && printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: syscall %d\n", current->comm,
 			task_pid_nr(current), (int)regs->syscallno);
 		dump_instr("", regs);
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index ff3bddea482d..f6fe17d88da5 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
+# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
+# down to collect2, resulting in silent corruption of the vDSO image.
+ccflags-y += -Wl,-shared
+
 obj-y += vdso.o
 extra-y += vdso.lds vdso-offsets.h
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index a2c29865c3fe..98073332e2d0 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -38,6 +38,12 @@ jiffies = jiffies_64;
 	*(.hyp.text)					\
 	VMLINUX_SYMBOL(__hyp_text_end) = .;
 
+#define IDMAP_TEXT					\
+	. = ALIGN(SZ_4K);				\
+	VMLINUX_SYMBOL(__idmap_text_start) = .;		\
+	*(.idmap.text)					\
+	VMLINUX_SYMBOL(__idmap_text_end) = .;
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -95,6 +101,7 @@ SECTIONS
 			SCHED_TEXT
 			LOCK_TEXT
 			HYPERVISOR_TEXT
+			IDMAP_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
@@ -167,11 +174,13 @@ SECTIONS
 }
 
 /*
- * The HYP init code can't be more than a page long,
+ * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.
  */
 ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
 	"HYP init code too big or misaligned")
+ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
+	"ID map text too big or misaligned")
 
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 5105e297ed5f..bfffe8f4bd53 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select KVM_ARM_HOST
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
+	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	---help---
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index d5904f876cdb..f90f4aa7f88d 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
 
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
 
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 5befd010e232..17a8fb14f428 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -17,8 +17,10 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/fpsimdmacros.h>
@@ -50,8 +52,8 @@
 	stp	x29, lr, [x3, #80]
 
 	mrs	x19, sp_el0
-	mrs	x20, elr_el2		// EL1 PC
-	mrs	x21, spsr_el2		// EL1 pstate
+	mrs	x20, elr_el2		// pc before entering el2
+	mrs	x21, spsr_el2		// pstate before entering el2
 
 	stp	x19, x20, [x3, #96]
 	str	x21, [x3, #112]
@@ -82,8 +84,8 @@
 	ldr	x21, [x3, #16]
 
 	msr	sp_el0, x19
-	msr	elr_el2, x20 				// EL1 PC
-	msr	spsr_el2, x21 				// EL1 pstate
+	msr	elr_el2, x20 		// pc on return from el2
+	msr	spsr_el2, x21 		// pstate on return from el2
 
 	add	x3, x2, #CPU_XREG_OFFSET(19)
 	ldp	x19, x20, [x3]
@@ -808,10 +810,7 @@
  * Call into the vgic backend for state saving
  */
 .macro save_vgic_state
-	adr	x24, __vgic_sr_vectors
-	ldr	x24, [x24, VGIC_SAVE_FN]
-	kern_hyp_va	x24
-	blr	x24
+	alternative_insn "bl __save_vgic_v2_state", "bl __save_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
 	mrs	x24, hcr_el2
 	mov	x25, #HCR_INT_OVERRIDE
 	neg	x25, x25
@@ -828,10 +827,7 @@
 	orr	x24, x24, #HCR_INT_OVERRIDE
 	orr	x24, x24, x25
 	msr	hcr_el2, x24
-	adr	x24, __vgic_sr_vectors
-	ldr	x24, [x24, #VGIC_RESTORE_FN]
-	kern_hyp_va	x24
-	blr	x24
+	alternative_insn "bl __restore_vgic_v2_state", "bl __restore_vgic_v3_state", ARM64_HAS_SYSREG_GIC_CPUIF
 .endm
 
 .macro save_timer_state
@@ -1062,12 +1058,6 @@ ENTRY(__kvm_flush_vm_context)
 	ret
 ENDPROC(__kvm_flush_vm_context)
 
-	// struct vgic_sr_vectors __vgi_sr_vectors;
-	.align 3
-ENTRY(__vgic_sr_vectors)
-	.skip	VGIC_SR_VECTOR_SZ
-ENDPROC(__vgic_sr_vectors)
-
 __kvm_hyp_panic:
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
index f002fe1c3700..3f000712a85d 100644
--- a/arch/arm64/kvm/vgic-v2-switch.S
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -47,7 +47,6 @@ __save_vgic_v2_state:
 	add	x3, x0, #VCPU_VGIC_CPU
 
 	/* Save all interesting registers */
-	ldr	w4, [x2, #GICH_HCR]
 	ldr	w5, [x2, #GICH_VMCR]
 	ldr	w6, [x2, #GICH_MISR]
 	ldr	w7, [x2, #GICH_EISR0]
@@ -55,7 +54,6 @@ __save_vgic_v2_state:
 	ldr	w9, [x2, #GICH_ELRSR0]
 	ldr	w10, [x2, #GICH_ELRSR1]
 	ldr	w11, [x2, #GICH_APR]
-CPU_BE(	rev	w4,  w4  )
 CPU_BE(	rev	w5,  w5  )
 CPU_BE(	rev	w6,  w6  )
 CPU_BE(	rev	w7,  w7  )
@@ -64,7 +62,6 @@ CPU_BE(	rev	w9,  w9  )
 CPU_BE(	rev	w10, w10 )
 CPU_BE(	rev	w11, w11 )
 
-	str	w4, [x3, #VGIC_V2_CPU_HCR]
 	str	w5, [x3, #VGIC_V2_CPU_VMCR]
 	str	w6, [x3, #VGIC_V2_CPU_MISR]
 CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
index 617a012a0107..3c20730ddff5 100644
--- a/arch/arm64/kvm/vgic-v3-switch.S
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -48,13 +48,11 @@
 	dsb	st
 
 	// Save all interesting registers
-	mrs_s	x4, ICH_HCR_EL2
 	mrs_s	x5, ICH_VMCR_EL2
 	mrs_s	x6, ICH_MISR_EL2
 	mrs_s	x7, ICH_EISR_EL2
 	mrs_s	x8, ICH_ELSR_EL2
 
-	str	w4, [x3, #VGIC_V3_CPU_HCR]
 	str	w5, [x3, #VGIC_V3_CPU_VMCR]
 	str	w6, [x3, #VGIC_V3_CPU_MISR]
 	str	w7, [x3, #VGIC_V3_CPU_EISR]
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 773d37a14039..9d84feb41a16 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,3 +4,5 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+
+CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 2560e1e1562e..bdeb5d38c2dd 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -22,84 +22,11 @@
 #include <linux/init.h>
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 
 #include "proc-macros.S"
 
 /*
- *	__flush_dcache_all()
- *
- *	Flush the whole D-cache.
- *
- *	Corrupted registers: x0-x7, x9-x11
- */
-__flush_dcache_all:
-	dmb	sy				// ensure ordering with previous memory accesses
-	mrs	x0, clidr_el1			// read clidr
-	and	x3, x0, #0x7000000		// extract loc from clidr
-	lsr	x3, x3, #23			// left align loc bit field
-	cbz	x3, finished			// if loc is 0, then no need to clean
-	mov	x10, #0				// start clean at cache level 0
-loop1:
-	add	x2, x10, x10, lsr #1		// work out 3x current cache level
-	lsr	x1, x0, x2			// extract cache type bits from clidr
-	and	x1, x1, #7			// mask of the bits for current cache only
-	cmp	x1, #2				// see what cache we have at this level
-	b.lt	skip				// skip if no cache, or just i-cache
-	save_and_disable_irqs x9		// make CSSELR and CCSIDR access atomic
-	msr	csselr_el1, x10			// select current cache level in csselr
-	isb					// isb to sych the new cssr&csidr
-	mrs	x1, ccsidr_el1			// read the new ccsidr
-	restore_irqs x9
-	and	x2, x1, #7			// extract the length of the cache lines
-	add	x2, x2, #4			// add 4 (line length offset)
-	mov	x4, #0x3ff
-	and	x4, x4, x1, lsr #3		// find maximum number on the way size
-	clz	w5, w4				// find bit position of way size increment
-	mov	x7, #0x7fff
-	and	x7, x7, x1, lsr #13		// extract max number of the index size
-loop2:
-	mov	x9, x4				// create working copy of max way size
-loop3:
-	lsl	x6, x9, x5
-	orr	x11, x10, x6			// factor way and cache number into x11
-	lsl	x6, x7, x2
-	orr	x11, x11, x6			// factor index number into x11
-	dc	cisw, x11			// clean & invalidate by set/way
-	subs	x9, x9, #1			// decrement the way
-	b.ge	loop3
-	subs	x7, x7, #1			// decrement the index
-	b.ge	loop2
-skip:
-	add	x10, x10, #2			// increment cache number
-	cmp	x3, x10
-	b.gt	loop1
-finished:
-	mov	x10, #0				// swith back to cache level 0
-	msr	csselr_el1, x10			// select current cache level in csselr
-	dsb	sy
-	isb
-	ret
-ENDPROC(__flush_dcache_all)
-
-/*
- *	flush_cache_all()
- *
- *	Flush the entire cache system.  The data cache flush is now achieved
- *	using atomic clean / invalidates working outwards from L1 cache. This
- *	is done using Set/Way based cache maintainance instructions.  The
- *	instruction cache can still be invalidated back to the point of
- *	unification in a single instruction.
- */
-ENTRY(flush_cache_all)
-	mov	x12, lr
-	bl	__flush_dcache_all
-	mov	x0, #0
-	ic	ialluis				// I+BTB cache invalidate
-	ret	x12
-ENDPROC(flush_cache_all)
-
-/*
  *	flush_icache_range(start,end)
  *
  *	Ensure that the I and D caches are coherent within specified region.
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index baa758d37021..76c1e6cd36fc 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -92,6 +92,14 @@ static void reset_context(void *info)
 	unsigned int cpu = smp_processor_id();
 	struct mm_struct *mm = current->active_mm;
 
+	/*
+	 * current->active_mm could be init_mm for the idle thread immediately
+	 * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to
+	 * the reserved value, so no need to reset any context.
+	 */
+	if (mm == &init_mm)
+		return;
+
 	smp_rmb();
 	asid = cpu_last_asid + cpu;
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index b0bd4e5fd5cf..d16a1cead23f 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -414,6 +414,98 @@ out:
 	return -ENOMEM;
 }
 
+/********************************************
+ * The following APIs are for dummy DMA ops *
+ ********************************************/
+
+static void *__dummy_alloc(struct device *dev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags,
+			   struct dma_attrs *attrs)
+{
+	return NULL;
+}
+
+static void __dummy_free(struct device *dev, size_t size,
+			 void *vaddr, dma_addr_t dma_handle,
+			 struct dma_attrs *attrs)
+{
+}
+
+static int __dummy_mmap(struct device *dev,
+			struct vm_area_struct *vma,
+			void *cpu_addr, dma_addr_t dma_addr, size_t size,
+			struct dma_attrs *attrs)
+{
+	return -ENXIO;
+}
+
+static dma_addr_t __dummy_map_page(struct device *dev, struct page *page,
+				   unsigned long offset, size_t size,
+				   enum dma_data_direction dir,
+				   struct dma_attrs *attrs)
+{
+	return DMA_ERROR_CODE;
+}
+
+static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr,
+			       size_t size, enum dma_data_direction dir,
+			       struct dma_attrs *attrs)
+{
+}
+
+static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl,
+			  int nelems, enum dma_data_direction dir,
+			  struct dma_attrs *attrs)
+{
+	return 0;
+}
+
+static void __dummy_unmap_sg(struct device *dev,
+			     struct scatterlist *sgl, int nelems,
+			     enum dma_data_direction dir,
+			     struct dma_attrs *attrs)
+{
+}
+
+static void __dummy_sync_single(struct device *dev,
+				dma_addr_t dev_addr, size_t size,
+				enum dma_data_direction dir)
+{
+}
+
+static void __dummy_sync_sg(struct device *dev,
+			    struct scatterlist *sgl, int nelems,
+			    enum dma_data_direction dir)
+{
+}
+
+static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+	return 1;
+}
+
+static int __dummy_dma_supported(struct device *hwdev, u64 mask)
+{
+	return 0;
+}
+
+struct dma_map_ops dummy_dma_ops = {
+	.alloc                  = __dummy_alloc,
+	.free                   = __dummy_free,
+	.mmap                   = __dummy_mmap,
+	.map_page               = __dummy_map_page,
+	.unmap_page             = __dummy_unmap_page,
+	.map_sg                 = __dummy_map_sg,
+	.unmap_sg               = __dummy_unmap_sg,
+	.sync_single_for_cpu    = __dummy_sync_single,
+	.sync_single_for_device = __dummy_sync_single,
+	.sync_sg_for_cpu        = __dummy_sync_sg,
+	.sync_sg_for_device     = __dummy_sync_sg,
+	.mapping_error          = __dummy_mapping_error,
+	.dma_supported          = __dummy_dma_supported,
+};
+EXPORT_SYMBOL(dummy_dma_ops);
+
 static int __init arm64_dma_init(void)
 {
 	int ret;
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 74c256744b25..f3d6221cd5bd 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -328,10 +328,12 @@ static int ptdump_init(void)
 			for (j = 0; j < pg_level[i].num; j++)
 				pg_level[i].mask |= pg_level[i].bits[j].mask;
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	address_markers[VMEMMAP_START_NR].start_address =
 				(unsigned long)virt_to_page(PAGE_OFFSET);
 	address_markers[VMEMMAP_END_NR].start_address =
 				(unsigned long)virt_to_page(high_memory);
+#endif
 
 	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
 				 &ptdump_fops);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 96da13167d4a..b1fc69cd1499 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -115,8 +115,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
 {
 	struct siginfo si;
 
-	if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
-	    printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited() && unhandled_signal(tsk, sig)) {
 		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
 			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
 			addr, esr);
@@ -211,7 +210,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
@@ -478,12 +477,19 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
 					   struct pt_regs *regs)
 {
 	struct siginfo info;
+	struct task_struct *tsk = current;
+
+	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
+		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
+				    tsk->comm, task_pid_nr(tsk),
+				    esr_get_class_string(esr), (void *)regs->pc,
+				    (void *)regs->sp);
 
 	info.si_signo = SIGBUS;
 	info.si_errno = 0;
 	info.si_code  = BUS_ADRALN;
 	info.si_addr  = (void __user *)addr;
-	arm64_notify_die("", regs, &info, esr);
+	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
 }
 
 static struct fault_info debug_fault_info[] = {
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index b6f14e8d2121..4dfa3975ce5b 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -102,7 +102,6 @@ EXPORT_SYMBOL(flush_dcache_page);
 /*
  * Additional functions defined in assembly.
  */
-EXPORT_SYMBOL(flush_cache_all);
 EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 2de9d2e59d96..cccc4af87a03 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -31,13 +31,6 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
-#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-#endif
-
 int pmd_huge(pmd_t pmd)
 {
 	return !(pmd_val(pmd) & PMD_TABLE_BIT);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 597831bdddf3..ad87ce826cce 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -262,7 +262,7 @@ static void __init free_unused_memmap(void)
 		 * memmap entries are valid from the bank end aligned to
 		 * MAX_ORDER_NR_PAGES.
 		 */
-		prev_end = ALIGN(start + __phys_to_pfn(reg->size),
+		prev_end = ALIGN(__phys_to_pfn(reg->base + reg->size),
 				 MAX_ORDER_NR_PAGES);
 	}
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 5b8b664422d3..82d3435bf14f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
@@ -643,3 +644,68 @@ void __set_fixmap(enum fixed_addresses idx,
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
+
+void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
+{
+	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
+	pgprot_t prot = PAGE_KERNEL | PTE_RDONLY;
+	int granularity, size, offset;
+	void *dt_virt;
+
+	/*
+	 * Check whether the physical FDT address is set and meets the minimum
+	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
+	 * at least 8 bytes so that we can always access the size field of the
+	 * FDT header after mapping the first chunk, double check here if that
+	 * is indeed the case.
+	 */
+	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
+	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
+		return NULL;
+
+	/*
+	 * Make sure that the FDT region can be mapped without the need to
+	 * allocate additional translation table pages, so that it is safe
+	 * to call create_mapping() this early.
+	 *
+	 * On 64k pages, the FDT will be mapped using PTEs, so we need to
+	 * be in the same PMD as the rest of the fixmap.
+	 * On 4k pages, we'll use section mappings for the FDT so we only
+	 * have to be in the same PUD.
+	 */
+	BUILD_BUG_ON(dt_virt_base % SZ_2M);
+
+	if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PMD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT);
+
+		granularity = PAGE_SIZE;
+	} else {
+		BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> PUD_SHIFT !=
+			     __fix_to_virt(FIX_BTMAP_BEGIN) >> PUD_SHIFT);
+
+		granularity = PMD_SIZE;
+	}
+
+	offset = dt_phys % granularity;
+	dt_virt = (void *)dt_virt_base + offset;
+
+	/* map the first chunk so we can read the size from the header */
+	create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+		       granularity, prot);
+
+	if (fdt_check_header(dt_virt) != 0)
+		return NULL;
+
+	size = fdt_totalsize(dt_virt);
+	if (size > MAX_FDT_SIZE)
+		return NULL;
+
+	if (offset + size > granularity)
+		create_mapping(round_down(dt_phys, granularity), dt_virt_base,
+			       round_up(offset + size, granularity), prot);
+
+	memblock_reserve(dt_phys, size);
+
+	return dt_virt;
+}
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index cdd754e19b9b..39139a3aa16d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,52 +46,6 @@
 #define MAIR(attr, mt)	((attr) << ((mt) * 8))
 
 /*
- *	cpu_cache_off()
- *
- *	Turn the CPU D-cache off.
- */
-ENTRY(cpu_cache_off)
-	mrs	x0, sctlr_el1
-	bic	x0, x0, #1 << 2			// clear SCTLR.C
-	msr	sctlr_el1, x0
-	isb
-	ret
-ENDPROC(cpu_cache_off)
-
-/*
- *	cpu_reset(loc)
- *
- *	Perform a soft reset of the system.  Put the CPU into the same state
- *	as it would be if it had been reset, and branch to what would be the
- *	reset vector. It must be executed with the flat identity mapping.
- *
- *	- loc   - location to jump to for soft reset
- */
-	.align	5
-ENTRY(cpu_reset)
-	mrs	x1, sctlr_el1
-	bic	x1, x1, #1
-	msr	sctlr_el1, x1			// disable the MMU
-	isb
-	ret	x0
-ENDPROC(cpu_reset)
-
-ENTRY(cpu_soft_restart)
-	/* Save address of cpu_reset() and reset address */
-	mov	x19, x0
-	mov	x20, x1
-
-	/* Turn D-cache off */
-	bl	cpu_cache_off
-
-	/* Push out all dirty data, and ensure cache is empty */
-	bl	flush_cache_all
-
-	mov	x0, x20
-	ret	x19
-ENDPROC(cpu_soft_restart)
-
-/*
  *	cpu_do_idle()
  *
  *	Idle the processor (wait for interrupt).
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index edba042b2325..dc6a4842683a 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -487,7 +487,7 @@ emit_cond_jmp:
 			return -EINVAL;
 		}
 
-		imm64 = (u64)insn1.imm << 32 | imm;
+		imm64 = (u64)insn1.imm << 32 | (u32)imm;
 		emit_a64_mov_i64(dst, imm64, ctx);
 
 		return 1;
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 962a6aeab787..366bbeaeb405 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -70,8 +70,6 @@ extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
    if something tries to do an invalid cmpxchg().  */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
 {
diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h
index 4f5ec2bb7172..e998ff5d8e1a 100644
--- a/arch/avr32/include/asm/io.h
+++ b/arch/avr32/include/asm/io.h
@@ -296,6 +296,7 @@ extern void __iounmap(void __iomem *addr);
 	__iounmap(addr)
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 #define cached(addr) P1SEGADDR(addr)
 #define uncached(addr) P2SEGADDR(addr)
diff --git a/arch/avr32/include/asm/mm-arch-hooks.h b/arch/avr32/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..145452ffbdad
--- /dev/null
+++ b/arch/avr32/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_AVR32_MM_ARCH_HOOKS_H
+#define _ASM_AVR32_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_AVR32_MM_ARCH_HOOKS_H */
diff --git a/arch/avr32/include/asm/uaccess.h b/arch/avr32/include/asm/uaccess.h
index a46f7cf3e1ea..68cf638faf48 100644
--- a/arch/avr32/include/asm/uaccess.h
+++ b/arch/avr32/include/asm/uaccess.h
@@ -97,7 +97,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -116,7 +117,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -136,7 +138,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -158,7 +161,8 @@ static inline __kernel_size_t __copy_from_user(void *to,
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index d223a8b57c1e..c03533937a9f 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -14,11 +14,11 @@
 #include <linux/pagemap.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/mmu_context.h>
 #include <asm/sysreg.h>
 #include <asm/tlb.h>
-#include <asm/uaccess.h>
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs, int trap)
@@ -81,7 +81,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user context, we must
 	 * not take the fault...
 	 */
-	if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+	if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
 		goto no_context;
 
 	local_irq_enable();
diff --git a/arch/blackfin/include/asm/io.h b/arch/blackfin/include/asm/io.h
index 4e8ad0523118..6abebe82d4e9 100644
--- a/arch/blackfin/include/asm/io.h
+++ b/arch/blackfin/include/asm/io.h
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
+#include <asm/def_LPBlackfin.h>
 
 #define __raw_readb bfin_read8
 #define __raw_readw bfin_read16
diff --git a/arch/blackfin/include/asm/mm-arch-hooks.h b/arch/blackfin/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..1c5211ec338f
--- /dev/null
+++ b/arch/blackfin/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_BLACKFIN_MM_ARCH_HOOKS_H
+#define _ASM_BLACKFIN_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_BLACKFIN_MM_ARCH_HOOKS_H */
diff --git a/arch/c6x/include/asm/mm-arch-hooks.h b/arch/c6x/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..bb3c4a6ce8e9
--- /dev/null
+++ b/arch/c6x/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_C6X_MM_ARCH_HOOKS_H
+#define _ASM_C6X_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_C6X_MM_ARCH_HOOKS_H */
diff --git a/arch/cris/include/asm/mm-arch-hooks.h b/arch/cris/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..314f774db2b0
--- /dev/null
+++ b/arch/cris/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_CRIS_MM_ARCH_HOOKS_H
+#define _ASM_CRIS_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_CRIS_MM_ARCH_HOOKS_H */
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 83f12f2ed9e3..3066d40a6db1 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -8,7 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/wait.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <arch/system.h>
 
 extern int find_fixup_code(struct pt_regs *);
@@ -109,11 +109,11 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
 	info.si_code = SEGV_MAPERR;
 
 	/*
-	 * If we're in an interrupt or "atomic" operation or have no
+	 * If we're in an interrupt, have pagefaults disabled or have no
 	 * user context, we must not take the fault.
 	 */
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/frv/include/asm/io.h b/arch/frv/include/asm/io.h
index 0b78bc89e840..a31b63ec4930 100644
--- a/arch/frv/include/asm/io.h
+++ b/arch/frv/include/asm/io.h
@@ -17,6 +17,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <linux/types.h>
 #include <asm/virtconvert.h>
 #include <asm/string.h>
@@ -265,7 +267,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
 
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void __iomem *ioremap_wt(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
diff --git a/arch/frv/include/asm/mm-arch-hooks.h b/arch/frv/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..51d13a870404
--- /dev/null
+++ b/arch/frv/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_FRV_MM_ARCH_HOOKS_H
+#define _ASM_FRV_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_FRV_MM_ARCH_HOOKS_H */
diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h
index 43d224685144..e43d22c58ad5 100644
--- a/arch/frv/include/asm/pci.h
+++ b/arch/frv/include/asm/pci.h
@@ -41,16 +41,6 @@ extern void pci_free_consistent(struct pci_dev *hwdev, size_t size,
 /* Return the index of the PCI controller for device PDEV. */
 #define pci_controller_num(PDEV)	(0)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 /*
  *	These are pretty much arbitrary with the CoMEM implementation.
  *	We have the whole address space to ourselves.
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index ec4917ddf678..61d99767fe16 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -19,9 +19,9 @@
 #include <linux/kernel.h>
 #include <linux/ptrace.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
-#include <asm/uaccess.h>
 #include <asm/gdb-stub.h>
 
 /*****************************************************************************/
@@ -78,7 +78,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(__frame))
diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c
index bed9a9bd3c10..785344bbdc07 100644
--- a/arch/frv/mm/highmem.c
+++ b/arch/frv/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long paddr;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 	type = kmap_atomic_idx_push();
 	paddr = page_to_phys(page);
@@ -85,5 +86,6 @@ void __kunmap_atomic(void *kvaddr)
 	}
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
new file mode 100644
index 000000000000..db589167838c
--- /dev/null
+++ b/arch/h8300/Kconfig
@@ -0,0 +1,76 @@
+config H8300
+        def_bool y
+	select GENERIC_ATOMIC64
+	select HAVE_UID16
+	select VIRT_TO_BUS
+	select GENERIC_IRQ_SHOW
+	select FRAME_POINTER
+	select GENERIC_CPU_DEVICES
+	select MODULES_USE_ELF_RELA
+	select GENERIC_CLOCKEVENTS
+	select CLKDEV_LOOKUP
+	select COMMON_CLK
+	select ARCH_WANT_FRAME_POINTERS
+	select OF
+	select OF_IRQ
+	select OF_EARLY_FLATTREE
+	select HAVE_MEMBLOCK
+	select HAVE_DMA_ATTRS
+
+config RWSEM_GENERIC_SPINLOCK
+	def_bool y
+
+config GENERIC_HWEIGHT
+	def_bool y
+
+config NO_IOPORT_MAP
+	def_bool y
+
+config GENERIC_CSUM
+        def_bool y
+
+config HZ
+	int
+	default 100
+
+config NR_CPUS
+	int
+	default 1
+
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+source "arch/h8300/Kconfig.cpu"
+
+menu "Kernel Features"
+
+source "kernel/Kconfig.preempt"
+
+source "mm/Kconfig"
+
+endmenu
+
+menu "Executable file formats"
+
+source "fs/Kconfig.binfmt"
+
+endmenu
+
+source "net/Kconfig"
+
+source "drivers/Kconfig"
+
+source "fs/Kconfig"
+
+menu "Kernel hacking"
+
+source "lib/Kconfig.debug"
+
+endmenu
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu
new file mode 100644
index 000000000000..8d0ff20c749a
--- /dev/null
+++ b/arch/h8300/Kconfig.cpu
@@ -0,0 +1,99 @@
+config CPU_H8300H
+	bool
+
+config CPU_H8S
+	bool
+
+config H83069
+	bool
+	select CPU_H8300H
+	select H8300_TMR16
+	select RENESAS_H8300H_INTC
+
+config H8S2678
+	bool
+	select CPU_H8S
+	select H8300_TPU
+	select RENESAS_H8S_INTC
+
+config RAMKERNEL
+	bool
+
+config ROMKERNEL
+	bool
+
+menu "Processor type and features"
+
+choice
+prompt "H8/300 platform"
+
+config H8300_AE3068
+	bool "AE-3068/69"
+	select H83069
+	select RAMKERNEL
+	help
+	  AKI-H8/3068F / AKI-H8/3069F Flashmicom LAN Board Support
+	  More Information. (Japanese Only)
+	  <http://akizukidenshi.com/catalog/default.aspx>
+	  AE-3068/69 Evaluation Board Support
+	  More Information.
+	  <http://www.microtronique.com/ae3069lan.htm>
+
+config H8300_H8MAX
+	bool "H8MAX"
+	select H83069
+	select RAMKERNEL
+	select HAVE_IDE
+	help
+	  H8MAX Evaluation Board Support
+	  More Information. (Japanese Only)
+	  <http://strawberry-linux.com/h8/index.html>
+
+config H8300_KANEBEBE
+	bool "KaneBebe"
+	select H83069
+	select RAMKERNEL
+	help
+	  KaneBebe Evalition Board Support
+	  More Information. (Japanese Only)
+	  <http://www.nissin-tech.com/2009/10/uclinuxkane-bebe-h83069f.html>
+
+config H8300H_SIM
+	bool "H8/300H GDB Simulator"
+	select H83069
+	select ROMKERNEL
+	help
+	  GDB Simulator Support
+	  More Information.
+	  <http://sourceware.org/sid/>
+
+config H8S_EDOSK2674
+	bool "EDOSK-2674"
+	select H8S2678
+	select RAMKERNEL
+	help
+	  Renesas EDOSK-2674 Evaluation Board Support
+	  More Information.
+	  <http://www.azpower.com/H8-uClinux/index.html>
+	  <http://www.renesas.eu/products/tools/introductory_evaluation_tools/evaluation_development_os_kits/edosk2674r/edosk2674r_software_tools_root.jsp>
+
+config H8S_SIM
+	bool "H8S GDB Simulator"
+	select H8S2678
+	select ROMKERNEL
+	help
+	  GDB Simulator Support
+	  More Information.
+	  <http://sourceware.org/sid/>
+
+endchoice
+
+config H8300_BUILTIN_DTB
+        string "Builtin DTB"
+	default ""
+
+config OFFSET
+        hex "Load offset"
+	default 0
+
+endmenu
diff --git a/arch/h8300/Makefile b/arch/h8300/Makefile
new file mode 100644
index 000000000000..0d2d96e52d9f
--- /dev/null
+++ b/arch/h8300/Makefile
@@ -0,0 +1,55 @@
+#
+# arch/h8300/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# (C) Copyright 2002-2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+#
+
+cflags-$(CONFIG_CPU_H8300H)	:= -mh
+aflags-$(CONFIG_CPU_H8300H)	:= -mh -Wa,--mach=h8300h
+ldflags-$(CONFIG_CPU_H8300H)	:= -mh8300helf_linux
+cflags-$(CONFIG_CPU_H8S)	:= -ms
+aflags-$(CONFIG_CPU_H8S)	:= -ms -Wa,--mach=h8300s
+ldflags-$(CONFIG_CPU_H8S)	:= -mh8300self_linux
+
+KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mint32 -fno-builtin
+KBUILD_CFLAGS += -D__linux__
+KBUILD_CFLAGS += -DUTS_SYSNAME=\"uClinux\"
+KBUILD_AFLAGS += $(aflags-y)
+LDFLAGS += $(ldflags-y)
+
+CROSS_COMPILE := h8300-unknown-linux-
+
+core-y	+= arch/$(ARCH)/kernel/ arch/$(ARCH)/mm/
+ifneq '$(CONFIG_H8300_BUILTIN_DTB)' '""'
+core-y += arch/h8300/boot/dts/
+endif
+
+libs-y	+= arch/$(ARCH)/lib/
+
+boot := arch/h8300/boot
+
+%.dtb %.dtb.S %.dtb.o: | scripts
+	$(Q)$(MAKE) $(build)=arch/h8300/boot/dts arch/h8300/boot/dts/$@
+
+PHONY += dtbs
+dtbs: scripts
+	$(Q)$(MAKE) $(build)=arch/h8300/boot/dts
+
+archmrproper:
+
+archclean:
+	$(Q)$(MAKE) $(clean)=$(boot)
+
+vmlinux.srec vmlinux.bin zImage uImage.bin: vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+
+define archhelp
+  @echo  'vmlinux.bin  - Create raw binary'
+  @echo  'vmlinux.srec - Create srec binary'
+  @echo  'zImage       - Compressed kernel image'
+endef
diff --git a/arch/h8300/boot/Makefile b/arch/h8300/boot/Makefile
new file mode 100644
index 000000000000..2f6393a5da57
--- /dev/null
+++ b/arch/h8300/boot/Makefile
@@ -0,0 +1,26 @@
+# arch/h8300/boot/Makefile
+
+targets := vmlinux.srec vmlinux.bin zImage
+subdir- := compressed
+
+OBJCOPYFLAGS_vmlinux.srec := -Osrec
+OBJCOPYFLAGS_vmlinux.bin  := -Obinary
+OBJCOPYFLAGS_zImage := -O binary -R .note -R .comment -R .stab -R .stabstr -S
+
+UIMAGE_LOADADDR = $(CONFIG_RAMBASE)
+UIMAGE_ENTRYADDR = $(shell /bin/bash -c 'printf "0x%08x" \
+	$$[$(CONFIG_RAMBASE) + $(CONFIG_OFFSET)]')
+
+$(obj)/vmlinux.srec $(obj)/vmlinux.bin:  vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/zImage: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/compressed/vmlinux: FORCE
+	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
+
+$(obj)/uImage.bin: $(obj)/vmlinux.bin
+	$(call if_changed,uimage,none)
+
+CLEAN_FILES += arch/$(ARCH)/vmlinux.bin arch/$(ARCH)/vmlinux.srec arch/$(ARCH)/uImage.bin
diff --git a/arch/h8300/boot/compressed/Makefile b/arch/h8300/boot/compressed/Makefile
new file mode 100644
index 000000000000..87d03b7ee97e
--- /dev/null
+++ b/arch/h8300/boot/compressed/Makefile
@@ -0,0 +1,37 @@
+#
+# linux/arch/sh/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets		:= vmlinux vmlinux.bin vmlinux.bin.gz head.o misc.o piggy.o
+
+OBJECTS = $(obj)/head.o $(obj)/misc.o
+
+#
+# IMAGE_OFFSET is the load offset of the compression loader
+# Assign dummy values if these 2 variables are not defined,
+# in order to suppress error message.
+#
+CONFIG_MEMORY_START     ?= 0x00400000
+CONFIG_BOOT_LINK_OFFSET ?= 0x00140000
+IMAGE_OFFSET := $(shell printf "0x%08x" $$(($(CONFIG_MEMORY_START)+$(CONFIG_BOOT_LINK_OFFSET))))
+
+LIBGCC := $(shell $(CROSS-COMPILE)$(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
+LDFLAGS_vmlinux := -Ttext $(IMAGE_OFFSET) -estartup $(obj)/vmlinux.lds
+
+$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(LIBGCC) FORCE
+	$(call if_changed,ld)
+	@:
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vmlinux.bin.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,gzip)
+
+LDFLAGS_piggy.o := -r --format binary --oformat elf32-h8300-linux -T
+OBJCOPYFLAGS := -O binary
+
+$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.gz FORCE
+	$(call if_changed,ld)
diff --git a/arch/h8300/boot/compressed/head.S b/arch/h8300/boot/compressed/head.S
new file mode 100644
index 000000000000..74c0d8cc40ba
--- /dev/null
+++ b/arch/h8300/boot/compressed/head.S
@@ -0,0 +1,48 @@
+/*
+ *  linux/arch/h8300/boot/compressed/head.S
+ *
+ *  Copyright (C) 2006 Yoshinori Sato
+ */
+
+#include <linux/linkage.h>
+
+	.section	.text..startup,"ax"
+	.global	startup
+startup:
+	mov.l	er0, er4
+	mov.l	er0, sp
+	mov.l	#__sbss, er0
+	mov.l	#__ebss, er1
+	sub.l	er0, er1
+	shlr	er1
+	shlr	er1
+	sub.l	er2, er2
+1:
+	mov.l	er2, @er0
+	adds	#4, er0
+	dec.l	#1, er1
+	bne	1b
+	jsr	@decompress_kernel
+	mov.l	er4, er0
+	jmp	@0x400000
+
+	.align	9
+fake_headers_as_bzImage:
+	.word	0
+	.ascii	"HdrS"		; header signature
+	.word	0x0202		; header version number (>= 0x0105)
+				; or else old loadlin-1.5 will fail)
+	.word	0		; default_switch
+	.word	0		; SETUPSEG
+	.word	0x1000
+	.word	0		; pointing to kernel version string
+	.byte	0		; = 0, old one (LILO, Loadlin,
+				; 0xTV: T=0 for LILO
+				;       V = version
+	.byte	1		; Load flags bzImage=1
+	.word	0x8000		; size to move, when setup is not
+	.long	0x100000	; 0x100000 = default for big kernel
+	.long	0		; address of loaded ramdisk image
+	.long	0		; its size in bytes
+
+	.end
diff --git a/arch/h8300/boot/compressed/misc.c b/arch/h8300/boot/compressed/misc.c
new file mode 100644
index 000000000000..704274127c07
--- /dev/null
+++ b/arch/h8300/boot/compressed/misc.c
@@ -0,0 +1,74 @@
+/*
+ * arch/h8300/boot/compressed/misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ *
+ * Adapted for h8300 by Yoshinori Sato 2006
+ */
+
+#include <asm/uaccess.h>
+
+/*
+ * gzip declarations
+ */
+
+#define OF(args)  args
+#define STATIC static
+
+#undef memset
+#undef memcpy
+#define memzero(s, n)     memset((s), (0), (n))
+
+extern int _end;
+static unsigned long free_mem_ptr;
+static unsigned long free_mem_end_ptr;
+
+extern char input_data[];
+extern int input_len;
+static unsigned char *output;
+
+#define HEAP_SIZE             0x10000
+
+#include "../../../../lib/decompress_inflate.c"
+
+void *memset(void *s, int c, size_t n)
+{
+	int i;
+	char *ss = (char *)s;
+
+	for (i = 0; i < n; i++)
+		ss[i] = c;
+	return s;
+}
+
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	int i;
+	char *d = (char *)dest, *s = (char *)src;
+
+	for (i = 0; i < n; i++)
+		d[i] = s[i];
+	return dest;
+}
+
+static void error(char *x)
+{
+
+	while (1)
+		;	/* Halt */
+}
+
+#define STACK_SIZE (4096)
+long user_stack[STACK_SIZE];
+long *stack_start = &user_stack[STACK_SIZE];
+
+void decompress_kernel(void)
+{
+	free_mem_ptr = (unsigned long)&_end;
+	free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
+	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
+}
diff --git a/arch/h8300/boot/compressed/vmlinux.lds b/arch/h8300/boot/compressed/vmlinux.lds
new file mode 100644
index 000000000000..a0a3a0ed54ef
--- /dev/null
+++ b/arch/h8300/boot/compressed/vmlinux.lds
@@ -0,0 +1,32 @@
+SECTIONS
+{
+        .text :
+        {
+        __stext = . ;
+	__text = .;
+	       *(.text..startup)
+	       *(.text)
+        __etext = . ;
+        }
+
+	.rodata :
+	{
+		*(.rodata)
+	}
+        .data :
+
+        {
+        __sdata = . ;
+        ___data_start = . ;
+                *(.data.*)
+	}
+        .bss :
+        {
+        . = ALIGN(0x4) ;
+        __sbss = . ;
+                *(.bss*)
+        . = ALIGN(0x4) ;
+        __ebss = . ;
+        __end = . ;
+        }
+}
diff --git a/arch/h8300/boot/compressed/vmlinux.scr b/arch/h8300/boot/compressed/vmlinux.scr
new file mode 100644
index 000000000000..a084903603fe
--- /dev/null
+++ b/arch/h8300/boot/compressed/vmlinux.scr
@@ -0,0 +1,9 @@
+SECTIONS
+{
+  .data : {
+	input_len = .;
+	LONG(input_data_end - input_data) input_data = .;
+	*(.data)
+	input_data_end = .;
+	}
+}
diff --git a/arch/h8300/boot/dts/Makefile b/arch/h8300/boot/dts/Makefile
new file mode 100644
index 000000000000..0abaf1ad830e
--- /dev/null
+++ b/arch/h8300/boot/dts/Makefile
@@ -0,0 +1,12 @@
+ifneq '$(CONFIG_H8300_BUILTIN_DTB)' '""'
+BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_H8300_BUILTIN_DTB)).dtb.o
+endif
+
+obj-y += $(BUILTIN_DTB)
+
+dtb-$(CONFIG_H8300H_SIM) := h8300h_sim.dtb
+dtb-$(CONFIG_H8S_SIM) := h8s_sim.dtb
+dtb-$(CONFIG_H8S_EDOSK2674) := edosk2674.dtb
+
+always	    := $(dtb-y)
+clean-files := *.dtb.S *.dtb
diff --git a/arch/h8300/boot/dts/edosk2674.dts b/arch/h8300/boot/dts/edosk2674.dts
new file mode 100644
index 000000000000..dfb5c102f8da
--- /dev/null
+++ b/arch/h8300/boot/dts/edosk2674.dts
@@ -0,0 +1,107 @@
+/dts-v1/;
+/ {
+	compatible = "renesas,edosk2674";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&h8intc>;
+
+	chosen {
+		bootargs = "console=ttySC2,38400";
+		stdout-path = <&sci2>;
+	};
+	aliases {
+		serial0 = &sci0;
+		serial1 = &sci1;
+		serial2 = &sci2;
+	};
+
+	xclk: oscillator {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <33333333>;
+		clock-output-names = "xtal";
+	};
+	pllclk: pllclk {
+		compatible = "renesas,h8s2678-pll-clock";
+		clocks = <&xclk>;
+		#clock-cells = <0>;
+		reg = <0xfee03b 2>, <0xfee045 2>;
+	};
+	core_clk: core_clk {
+		compatible = "renesas,h8300-div-clock";
+		clocks = <&pllclk>;
+		#clock-cells = <0>;
+		reg = <0xfee03b 2>;
+		renesas,width = <3>;
+	};
+	fclk: fclk {
+		compatible = "fixed-factor-clock";
+		clocks = <&core_clk>;
+		#clock-cells = <0>;
+		clock-div = <1>;
+		clock-mult = <1>;
+	};
+
+	memory@400000 {
+		device_type = "memory";
+		reg = <0x400000 0x800000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			compatible = "renesas,h8300";
+			clock-frequency = <33333333>;
+		};
+	};
+
+	h8intc: interrupt-controller@fffe00 {
+		compatible = "renesas,h8s-intc", "renesas,h8300-intc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xfffe00 24>;
+	};
+
+	bsc: memory-controller@fffec0 {
+		compatible = "renesas,h8s-bsc", "renesas,h8300-bsc";
+		reg = <0xfffec0 24>;
+	};
+
+	tpu: timer@ffffe0 {
+		compatible = "renesas,tpu";
+		reg = <0xffffe0 16>, <0xfffff0 12>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	timer8: timer@ffffb0 {
+		compatible = "renesas,8bit-timer";
+		reg = <0xffffb0 10>;
+		interrupts = <72 0>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	sci0: serial@ffff78 {
+		compatible = "renesas,sci";
+		reg = <0xffff78 8>;
+		interrupts = <88 0>, <89 0>, <90 0>, <91 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+	sci1: serial@ffff80 {
+		compatible = "renesas,sci";
+		reg = <0xffff80 8>;
+		interrupts = <92 0>, <93 0>, <94 0>, <95 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+	sci2: serial@ffff88 {
+		compatible = "renesas,sci";
+		reg = <0xffff88 8>;
+		interrupts = <96 0>, <97 0>, <98 0>, <99 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+};
diff --git a/arch/h8300/boot/dts/h8300h_sim.dts b/arch/h8300/boot/dts/h8300h_sim.dts
new file mode 100644
index 000000000000..545bfb57af9a
--- /dev/null
+++ b/arch/h8300/boot/dts/h8300h_sim.dts
@@ -0,0 +1,96 @@
+/dts-v1/;
+/ {
+	compatible = "gnu,gdbsim";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&h8intc>;
+
+	chosen {
+		bootargs = "earlyprintk=h8300-sim";
+		stdout-path = <&sci0>;
+	};
+	aliases {
+		serial0 = &sci0;
+		serial1 = &sci1;
+	};
+
+	xclk: oscillator {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <20000000>;
+		clock-output-names = "xtal";
+	};
+	core_clk: core_clk {
+		compatible = "renesas,h8300-div-clock";
+		clocks = <&xclk>;
+		#clock-cells = <0>;
+		reg = <0xfee01b 2>;
+		renesas,width = <2>;
+	};
+	fclk: fclk {
+		compatible = "fixed-factor-clock";
+		clocks = <&core_clk>;
+		#clock-cells = <0>;
+		clock-div = <1>;
+		clock-mult = <1>;
+	};
+
+	memory@400000 {
+		device_type = "memory";
+		reg = <0x400000 0x400000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			compatible = "renesas,h8300";
+			clock-frequency = <20000000>;
+		};
+	};
+
+	h8intc: interrupt-controller@fee012 {
+		compatible = "renesas,h8300h-intc", "renesas,h8300-intc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xfee012 7>;
+	};
+
+	bsc: memory-controller@fee01e {
+		compatible = "renesas,h8300h-bsc", "renesas,h8300-bsc";
+		reg = <0xfee01e 8>;
+	};
+
+	timer8: timer@ffff80 {
+		compatible = "renesas,8bit-timer";
+		reg = <0xffff80 10>;
+		interrupts = <36 0>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	timer16: timer@ffff68 {
+		compatible = "renesas,16bit-timer";
+		reg = <0xffff68 8>, <0xffff60 8>;
+		interrupts = <24 0>;
+		renesas,channel = <0>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	sci0: serial@ffffb0 {
+		compatible = "renesas,sci";
+		reg = <0xffffb0 8>;
+		interrupts = <52 0>, <53 0>, <54 0>, <55 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+
+	sci1: serial@ffffb8 {
+		compatible = "renesas,sci";
+		reg = <0xffffb8 8>;
+		interrupts = <56 0>, <57 0>, <58 0>, <59 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+};
diff --git a/arch/h8300/boot/dts/h8s_sim.dts b/arch/h8300/boot/dts/h8s_sim.dts
new file mode 100644
index 000000000000..bcedba5a3ce7
--- /dev/null
+++ b/arch/h8300/boot/dts/h8s_sim.dts
@@ -0,0 +1,99 @@
+/dts-v1/;
+/ {
+	compatible = "gnu,gdbsim";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	interrupt-parent = <&h8intc>;
+
+	chosen {
+		bootargs = "earlyprintk=h8300-sim";
+		stdout-path = <&sci0>;
+	};
+	aliases {
+		serial0 = &sci0;
+		serial1 = &sci1;
+	};
+
+	xclk: oscillator {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <33333333>;
+		clock-output-names = "xtal";
+	};
+	pllclk: pllclk {
+		compatible = "renesas,h8s2678-pll-clock";
+		clocks = <&xclk>;
+		#clock-cells = <0>;
+		reg = <0xfee03b 2>, <0xfee045 2>;
+	};
+	core_clk: core_clk {
+		compatible = "renesas,h8300-div-clock";
+		clocks = <&pllclk>;
+		#clock-cells = <0>;
+		reg = <0xfee03b 2>;
+		renesas,width = <3>;
+	};
+	fclk: fclk {
+		compatible = "fixed-factor-clock";
+		clocks = <&core_clk>;
+		#clock-cells = <0>;
+		clock-div = <1>;
+		clock-mult = <1>;
+	};
+
+	memory@400000 {
+		device_type = "memory";
+		reg = <0x400000 0x800000>;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		cpu@0 {
+			compatible = "renesas,h8300";
+			clock-frequency = <33333333>;
+		};
+	};
+
+	h8intc: interrupt-controller@fffe00 {
+		compatible = "renesas,h8s-intc", "renesas,h8300-intc";
+		#interrupt-cells = <2>;
+		interrupt-controller;
+		reg = <0xfffe00 24>;
+	};
+
+	bsc: memory-controller@fffec0 {
+		compatible = "renesas,h8s-bsc", "renesas,h8300-bsc";
+		reg = <0xfffec0 24>;
+	};
+
+	tpu: timer@ffffe0 {
+		compatible = "renesas,tpu";
+		reg = <0xffffe0 16>, <0xfffff0 12>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	timer8: timer@ffffb0 {
+		compatible = "renesas,8bit-timer";
+		reg = <0xffffb0 10>;
+		interrupts = <72 0>;
+		clocks = <&fclk>;
+		clock-names = "fck";
+	};
+
+	sci0: serial@ffff78 {
+		compatible = "renesas,sci";
+		reg = <0xffff78 8>;
+		interrupts = <88 0>, <89 0>, <90 0>, <91 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+	sci1: serial@ffff80 {
+		compatible = "renesas,sci";
+		reg = <0xffff80 8>;
+		interrupts = <92 0>, <93 0>, <94 0>, <95 0>;
+		clocks = <&fclk>;
+		clock-names = "sci_ick";
+	};
+};
diff --git a/arch/h8300/configs/edosk2674_defconfig b/arch/h8300/configs/edosk2674_defconfig
new file mode 100644
index 000000000000..29fda12d5da9
--- /dev/null
+++ b/arch/h8300/configs/edosk2674_defconfig
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_USELIB is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_UID16 is not set
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_KALLSYMS is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_FUTEX is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_BLOCK is not set
+CONFIG_H8S_SIM=y
+CONFIG_H8300_BUILTIN_DTB="h8s_sim"
+# CONFIG_BINFMT_SCRIPT is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+# CONFIG_UEVENT_HELPER is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_FS is not set
+# CONFIG_SYSFS is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/h8300/configs/h8300h-sim_defconfig b/arch/h8300/configs/h8300h-sim_defconfig
new file mode 100644
index 000000000000..067bfe9c49b3
--- /dev/null
+++ b/arch/h8300/configs/h8300h-sim_defconfig
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_USELIB is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_UID16 is not set
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_KALLSYMS is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_FUTEX is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_BLOCK is not set
+CONFIG_H8300H_SIM=y
+CONFIG_H8300_BUILTIN_DTB="h8300h_sim"
+# CONFIG_BINFMT_SCRIPT is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+# CONFIG_UEVENT_HELPER is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_FS is not set
+# CONFIG_SYSFS is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/h8300/configs/h8s-sim_defconfig b/arch/h8300/configs/h8s-sim_defconfig
new file mode 100644
index 000000000000..29fda12d5da9
--- /dev/null
+++ b/arch/h8300/configs/h8s-sim_defconfig
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_USELIB is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_UID16 is not set
+# CONFIG_SYSFS_SYSCALL is not set
+# CONFIG_KALLSYMS is not set
+# CONFIG_BASE_FULL is not set
+# CONFIG_FUTEX is not set
+# CONFIG_EPOLL is not set
+# CONFIG_SIGNALFD is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_EVENTFD is not set
+# CONFIG_AIO is not set
+# CONFIG_ADVISE_SYSCALLS is not set
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLOB=y
+# CONFIG_BLOCK is not set
+CONFIG_H8S_SIM=y
+CONFIG_H8300_BUILTIN_DTB="h8s_sim"
+# CONFIG_BINFMT_SCRIPT is not set
+CONFIG_BINFMT_FLAT=y
+# CONFIG_COREDUMP is not set
+# CONFIG_UEVENT_HELPER is not set
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+# CONFIG_PROC_FS is not set
+# CONFIG_SYSFS is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
new file mode 100644
index 000000000000..00379d64f707
--- /dev/null
+++ b/arch/h8300/include/asm/Kbuild
@@ -0,0 +1,75 @@
+generic-y += asm-offsets.h
+generic-y += auxvec.h
+generic-y += barrier.h
+generic-y += bugs.h
+generic-y += cacheflush.h
+generic-y += checksum.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += dma.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += exec.h
+generic-y += fb.h
+generic-y += fcntl.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += ioctl.h
+generic-y += ioctls.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += irq_work.h
+generic-y += kdebug.h
+generic-y += kmap_types.h
+generic-y += kvm_para.h
+generic-y += linkage.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mman.h
+generic-y += mmu.h
+generic-y += mmu_context.h
+generic-y += module.h
+generic-y += msgbuf.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += pgalloc.h
+generic-y += poll.h
+generic-y += posix_types.h
+generic-y += preempt.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += setup.h
+generic-y += shmbuf.h
+generic-y += shmparam.h
+generic-y += siginfo.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += sockios.h
+generic-y += spinlock.h
+generic-y += stat.h
+generic-y += statfs.h
+generic-y += swab.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += timex.h
+generic-y += tlbflush.h
+generic-y += trace_clock.h
+generic-y += topology.h
+generic-y += types.h
+generic-y += uaccess.h
+generic-y += ucontext.h
+generic-y += unaligned.h
+generic-y += vga.h
+generic-y += xor.h
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
new file mode 100644
index 000000000000..7ca73f8546cc
--- /dev/null
+++ b/arch/h8300/include/asm/atomic.h
@@ -0,0 +1,159 @@
+#ifndef __ARCH_H8300_ATOMIC__
+#define __ARCH_H8300_ATOMIC__
+
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic_set(v, i)	(((v)->counter) = i)
+
+#include <linux/kernel.h>
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	h8300flags flags;
+	int ret;
+
+	flags = arch_local_irq_save();
+	ret = v->counter += i;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+#define atomic_add(i, v) atomic_add_return(i, v)
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	h8300flags flags;
+	int ret;
+
+	flags = arch_local_irq_save();
+	ret = v->counter -= i;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+#define atomic_sub(i, v) atomic_sub_return(i, v)
+#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
+
+static inline int atomic_inc_return(atomic_t *v)
+{
+	h8300flags flags;
+	int ret;
+
+	flags = arch_local_irq_save();
+	v->counter++;
+	ret = v->counter;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+#define atomic_inc(v) atomic_inc_return(v)
+
+/*
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
+
+static inline int atomic_dec_return(atomic_t *v)
+{
+	h8300flags flags;
+	int ret;
+
+	flags = arch_local_irq_save();
+	--v->counter;
+	ret = v->counter;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+#define atomic_dec(v) atomic_dec_return(v)
+
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	h8300flags flags;
+	int ret;
+
+	flags = arch_local_irq_save();
+	--v->counter;
+	ret = v->counter;
+	arch_local_irq_restore(flags);
+	return ret == 0;
+}
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	int ret;
+	h8300flags flags;
+
+	flags = arch_local_irq_save();
+	ret = v->counter;
+	if (likely(ret == old))
+		v->counter = new;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int ret;
+	h8300flags flags;
+
+	flags = arch_local_irq_save();
+	ret = v->counter;
+	if (ret != u)
+		v->counter += a;
+	arch_local_irq_restore(flags);
+	return ret;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *v)
+{
+	unsigned char ccr;
+	unsigned long tmp;
+
+	__asm__ __volatile__("stc ccr,%w3\n\t"
+			     "orc #0x80,ccr\n\t"
+			     "mov.l %0,%1\n\t"
+			     "and.l %2,%1\n\t"
+			     "mov.l %1,%0\n\t"
+			     "ldc %w3,ccr"
+			     : "=m"(*v), "=r"(tmp)
+			     : "g"(~(mask)), "r"(ccr));
+}
+
+static inline void atomic_set_mask(unsigned long mask, unsigned long *v)
+{
+	unsigned char ccr;
+	unsigned long tmp;
+
+	__asm__ __volatile__("stc ccr,%w3\n\t"
+			     "orc #0x80,ccr\n\t"
+			     "mov.l %0,%1\n\t"
+			     "or.l %2,%1\n\t"
+			     "mov.l %1,%0\n\t"
+			     "ldc %w3,ccr"
+			     : "=m"(*v), "=r"(tmp)
+			     : "g"(~(mask)), "r"(ccr));
+}
+
+/* Atomic operations are already serializing */
+#define smp_mb__before_atomic_dec()    barrier()
+#define smp_mb__after_atomic_dec() barrier()
+#define smp_mb__before_atomic_inc()    barrier()
+#define smp_mb__after_atomic_inc() barrier()
+
+#endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h
new file mode 100644
index 000000000000..05999aba1d6a
--- /dev/null
+++ b/arch/h8300/include/asm/bitops.h
@@ -0,0 +1,185 @@
+#ifndef _H8300_BITOPS_H
+#define _H8300_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ * Copyright 2002, Yoshinori Sato
+ */
+
+#include <linux/compiler.h>
+
+#ifdef __KERNEL__
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+/*
+ * Function prototypes to keep gcc -Wall happy
+ */
+
+/*
+ * ffz = Find First Zero in word. Undefined if no zero exists,
+ * so code should check against ~0UL first..
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+	unsigned long result;
+
+	result = -1;
+	__asm__("1:\n\t"
+		"shlr.l %2\n\t"
+		"adds #1,%0\n\t"
+		"bcs 1b"
+		: "=r"(result)
+		: "0"(result), "r"(word));
+	return result;
+}
+
+#define H8300_GEN_BITOP(FNAME, OP)				\
+static inline void FNAME(int nr, volatile unsigned long *addr)	\
+{								\
+	unsigned char *b_addr;					\
+	unsigned char bit = nr & 7;				\
+								\
+	b_addr = (unsigned char *)addr + ((nr >> 3) ^ 3);	\
+	if (__builtin_constant_p(nr)) {				\
+		__asm__(OP " %1,%0" : "+WU"(*b_addr) : "i"(nr & 7));	\
+	} else {						\
+		__asm__(OP " %s1,%0" : "+WU"(*b_addr) : "r"(bit));	\
+	}							\
+}
+
+/*
+ * clear_bit() doesn't provide any barrier for the compiler.
+ */
+#define smp_mb__before_clear_bit()	barrier()
+#define smp_mb__after_clear_bit()	barrier()
+
+H8300_GEN_BITOP(set_bit,    "bset")
+H8300_GEN_BITOP(clear_bit,  "bclr")
+H8300_GEN_BITOP(change_bit, "bnot")
+#define __set_bit(nr, addr)    set_bit((nr), (addr))
+#define __clear_bit(nr, addr)  clear_bit((nr), (addr))
+#define __change_bit(nr, addr) change_bit((nr), (addr))
+
+#undef H8300_GEN_BITOP
+
+static inline int test_bit(int nr, const unsigned long *addr)
+{
+	int ret = 0;
+	unsigned char *b_addr;
+	unsigned char bit = nr & 7;
+
+	b_addr = (unsigned char *)addr + ((nr >> 3) ^ 3);
+	if (__builtin_constant_p(nr)) {
+		__asm__("bld %Z2,%1\n\t"
+			"rotxl %0\n\t"
+			: "=r"(ret)
+			: "WU"(*b_addr), "i"(nr & 7), "0"(ret) : "cc");
+	} else {
+		__asm__("btst %w2,%1\n\t"
+			"beq 1f\n\t"
+			"inc.l #1,%0\n"
+			"1:"
+			: "=r"(ret)
+			: "WU"(*b_addr), "r"(bit), "0"(ret) : "cc");
+	}
+	return ret;
+}
+
+#define __test_bit(nr, addr) test_bit(nr, addr)
+
+#define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
+static inline int FNNAME(int nr, void *addr)				\
+{									\
+	int retval = 0;							\
+	char ccrsave;							\
+	unsigned char *b_addr;						\
+	unsigned char bit = nr & 7;					\
+									\
+	b_addr = (unsigned char *)addr + ((nr >> 3) ^ 3);		\
+	if (__builtin_constant_p(nr)) {					\
+		__asm__("stc ccr,%s2\n\t"				\
+			"orc #0x80,ccr\n\t"				\
+			"bld %4,%1\n\t"					\
+			OP " %4,%1\n\t"					\
+			"rotxl.l %0\n\t"				\
+			"ldc %s2,ccr"					\
+			: "=r"(retval), "+WU" (*b_addr), "=&r"(ccrsave)	\
+			: "0"(retval), "i"(nr & 7) : "cc");		\
+	} else {							\
+		__asm__("stc ccr,%t3\n\t"				\
+			"orc #0x80,ccr\n\t"				\
+			"btst %s3,%1\n\t"				\
+			OP " %s3,%1\n\t"				\
+			"beq 1f\n\t"					\
+			"inc.l #1,%0\n\t"				\
+			"1:\n"						\
+			"ldc %t3,ccr"					\
+			: "=r"(retval), "+WU" (*b_addr)			\
+			: "0" (retval), "r"(bit) : "cc");		\
+	}								\
+	return retval;							\
+}									\
+									\
+static inline int __ ## FNNAME(int nr, void *addr)			\
+{									\
+	int retval = 0;							\
+	unsigned char *b_addr;						\
+	unsigned char bit = nr & 7;					\
+									\
+	b_addr = (unsigned char *)addr + ((nr >> 3) ^ 3);		\
+	if (__builtin_constant_p(nr)) {					\
+		__asm__("bld %3,%1\n\t"					\
+			OP " %3,%1\n\t"					\
+			"rotxl.l %0\n\t"				\
+			: "=r"(retval), "+WU"(*b_addr)			\
+			: "0" (retval), "i"(nr & 7));			\
+	} else {							\
+		__asm__("btst %s3,%1\n\t"				\
+			OP " %s3,%1\n\t"				\
+			"beq 1f\n\t"					\
+			"inc.l #1,%0\n\t"				\
+			"1:"						\
+			: "=r"(retval), "+WU"(*b_addr)			\
+			: "0" (retval), "r"(bit));			\
+	}								\
+	return retval;							\
+}
+
+H8300_GEN_TEST_BITOP(test_and_set_bit,	  "bset")
+H8300_GEN_TEST_BITOP(test_and_clear_bit,  "bclr")
+H8300_GEN_TEST_BITOP(test_and_change_bit, "bnot")
+#undef H8300_GEN_TEST_BITOP
+
+#include <asm-generic/bitops/ffs.h>
+
+static inline unsigned long __ffs(unsigned long word)
+{
+	unsigned long result;
+
+	result = -1;
+	__asm__("1:\n\t"
+		"shlr.l %2\n\t"
+		"adds #1,%0\n\t"
+		"bcc 1b"
+		: "=r" (result)
+		: "0"(result), "r"(word));
+	return result;
+}
+
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/sched.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/le.h>
+#include <asm-generic/bitops/ext2-atomic.h>
+
+#endif /* __KERNEL__ */
+
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+
+#endif /* _H8300_BITOPS_H */
diff --git a/arch/h8300/include/asm/bitsperlong.h b/arch/h8300/include/asm/bitsperlong.h
new file mode 100644
index 000000000000..e140e46729ac
--- /dev/null
+++ b/arch/h8300/include/asm/bitsperlong.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_H8300_BITS_PER_LONG
+#define __ASM_H8300_BITS_PER_LONG
+
+#include <asm-generic/bitsperlong.h>
+
+#if !defined(__ASSEMBLY__)
+/* h8300-unknown-linux required long */
+#define __kernel_size_t __kernel_size_t
+typedef unsigned long	__kernel_size_t;
+typedef long		__kernel_ssize_t;
+typedef long		__kernel_ptrdiff_t;
+#endif
+
+#endif /* __ASM_H8300_BITS_PER_LONG */
diff --git a/arch/h8300/include/asm/bug.h b/arch/h8300/include/asm/bug.h
new file mode 100644
index 000000000000..1e1be8119935
--- /dev/null
+++ b/arch/h8300/include/asm/bug.h
@@ -0,0 +1,12 @@
+#ifndef _H8300_BUG_H
+#define _H8300_BUG_H
+
+/* always true */
+#define is_valid_bugaddr(addr) (1)
+
+#include <asm-generic/bug.h>
+
+struct pt_regs;
+extern void die(const char *str, struct pt_regs *fp, unsigned long err);
+
+#endif
diff --git a/arch/h8300/include/asm/byteorder.h b/arch/h8300/include/asm/byteorder.h
new file mode 100644
index 000000000000..888478a38145
--- /dev/null
+++ b/arch/h8300/include/asm/byteorder.h
@@ -0,0 +1,7 @@
+#ifndef __H8300_BYTEORDER_H__
+#define __H8300_BYTEORDER_H__
+
+#define __BIG_ENDIAN __ORDER_BIG_ENDIAN__
+#include <linux/byteorder/big_endian.h>
+
+#endif
diff --git a/arch/h8300/include/asm/cache.h b/arch/h8300/include/asm/cache.h
new file mode 100644
index 000000000000..0ef1edc5a6a6
--- /dev/null
+++ b/arch/h8300/include/asm/cache.h
@@ -0,0 +1,11 @@
+#ifndef __ARCH_H8300_CACHE_H
+#define __ARCH_H8300_CACHE_H
+
+/* bytes per L1 cache line */
+#define        L1_CACHE_SHIFT  2
+#define        L1_CACHE_BYTES  (1 << L1_CACHE_SHIFT)
+
+#define __cacheline_aligned
+#define ____cacheline_aligned
+
+#endif
diff --git a/arch/h8300/include/asm/cmpxchg.h b/arch/h8300/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..95fec4cd1081
--- /dev/null
+++ b/arch/h8300/include/asm/cmpxchg.h
@@ -0,0 +1,65 @@
+#ifndef __ARCH_H8300_CMPXCHG__
+#define __ARCH_H8300_CMPXCHG__
+
+#include <linux/irqflags.h>
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), \
+				    sizeof(*(ptr))))
+
+struct __xchg_dummy { unsigned long a[100]; };
+#define __xg(x) ((volatile struct __xchg_dummy *)(x))
+
+static inline unsigned long __xchg(unsigned long x,
+				   volatile void *ptr, int size)
+{
+	unsigned long tmp, flags;
+
+	local_irq_save(flags);
+
+	switch (size) {
+	case 1:
+		__asm__ __volatile__
+			("mov.b %2,%0\n\t"
+			 "mov.b %1,%2"
+			 : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)));
+		break;
+	case 2:
+		__asm__ __volatile__
+			("mov.w %2,%0\n\t"
+			 "mov.w %1,%2"
+			 : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)));
+		break;
+	case 4:
+		__asm__ __volatile__
+			("mov.l %2,%0\n\t"
+			 "mov.l %1,%2"
+			 : "=&r" (tmp) : "r" (x), "m" (*__xg(ptr)));
+		break;
+	default:
+		tmp = 0;
+	}
+	local_irq_restore(flags);
+	return tmp;
+}
+
+#include <asm-generic/cmpxchg-local.h>
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)					 \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr),		 \
+						     (unsigned long)(o), \
+						     (unsigned long)(n), \
+						     sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#ifndef CONFIG_SMP
+#include <asm-generic/cmpxchg.h>
+#endif
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+#endif /* __ARCH_H8300_CMPXCHG__ */
diff --git a/arch/h8300/include/asm/dma-mapping.h b/arch/h8300/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..6e67a90902f2
--- /dev/null
+++ b/arch/h8300/include/asm/dma-mapping.h
@@ -0,0 +1,57 @@
+#ifndef _H8300_DMA_MAPPING_H
+#define _H8300_DMA_MAPPING_H
+
+#include <asm-generic/dma-coherent.h>
+
+extern struct dma_map_ops h8300_dma_map_ops;
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return &h8300_dma_map_ops;
+}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	return 0;
+}
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	return 0;
+}
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	memory = ops->alloc(dev, size, dma_handle, flag, attrs);
+	return memory;
+}
+
+#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+#endif
diff --git a/arch/h8300/include/asm/elf.h b/arch/h8300/include/asm/elf.h
new file mode 100644
index 000000000000..09031d0127a3
--- /dev/null
+++ b/arch/h8300/include/asm/elf.h
@@ -0,0 +1,101 @@
+#ifndef __ASM_H8300_ELF_H
+#define __ASM_H8300_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+typedef unsigned long elf_fpregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == EM_H8_300)
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#define ELF_DATA	ELFDATA2MSB
+#define ELF_ARCH	EM_H8_300
+#if defined(CONFIG_CPU_H8300H)
+#define ELF_CORE_EFLAGS 0x810000
+#endif
+#if defined(CONFIG_CPU_H8S)
+#define ELF_CORE_EFLAGS 0x820000
+#endif
+
+#define ELF_PLAT_INIT(_r) do { (_r)->er1 = 0; } while (0)
+
+#define ELF_EXEC_PAGESIZE	4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE         0xD0000000UL
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this cpu supports.  */
+
+#define ELF_HWCAP	(0)
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.  */
+
+#define ELF_PLATFORM  (NULL)
+
+#define R_H8_NONE       0
+#define R_H8_DIR32      1
+#define R_H8_DIR32_28   2
+#define R_H8_DIR32_24   3
+#define R_H8_DIR32_16   4
+#define R_H8_DIR32U     6
+#define R_H8_DIR32U_28  7
+#define R_H8_DIR32U_24  8
+#define R_H8_DIR32U_20  9
+#define R_H8_DIR32U_16 10
+#define R_H8_DIR24     11
+#define R_H8_DIR24_20  12
+#define R_H8_DIR24_16  13
+#define R_H8_DIR24U    14
+#define R_H8_DIR24U_20 15
+#define R_H8_DIR24U_16 16
+#define R_H8_DIR16     17
+#define R_H8_DIR16U    18
+#define R_H8_DIR16S_32 19
+#define R_H8_DIR16S_28 20
+#define R_H8_DIR16S_24 21
+#define R_H8_DIR16S_20 22
+#define R_H8_DIR16S    23
+#define R_H8_DIR8      24
+#define R_H8_DIR8U     25
+#define R_H8_DIR8Z_32  26
+#define R_H8_DIR8Z_28  27
+#define R_H8_DIR8Z_24  28
+#define R_H8_DIR8Z_20  29
+#define R_H8_DIR8Z_16  30
+#define R_H8_PCREL16   31
+#define R_H8_PCREL8    32
+#define R_H8_BPOS      33
+#define R_H8_PCREL32   34
+#define R_H8_GOT32O    35
+#define R_H8_GOT16O    36
+#define R_H8_DIR16A8   59
+#define R_H8_DIR16R8   60
+#define R_H8_DIR24A8   61
+#define R_H8_DIR24R8   62
+#define R_H8_DIR32A16  63
+#define R_H8_ABS32     65
+#define R_H8_ABS32A16 127
+
+#endif
diff --git a/arch/h8300/include/asm/flat.h b/arch/h8300/include/asm/flat.h
new file mode 100644
index 000000000000..a4898eccf2bf
--- /dev/null
+++ b/arch/h8300/include/asm/flat.h
@@ -0,0 +1,28 @@
+/*
+ * arch/h8300/asm/include/flat.h -- uClinux flat-format executables
+ */
+
+#ifndef __H8300_FLAT_H__
+#define __H8300_FLAT_H__
+
+#define	flat_argvp_envp_on_stack()		1
+#define	flat_old_ram_flag(flags)		1
+#define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
+#define	flat_set_persistent(relval, p)		0
+
+/*
+ * on the H8 a couple of the relocations have an instruction in the
+ * top byte.  As there can only be 24bits of address space,  we just
+ * always preserve that 8bits at the top,  when it isn't an instruction
+ * is is 0 (davidm@snapgear.com)
+ */
+
+#define	flat_get_relocate_addr(rel)		(rel & ~0x00000001)
+#define flat_get_addr_from_rp(rp, relval, flags, persistent) \
+	({(void)persistent; \
+		get_unaligned(rp) & (((flags) & FLAT_FLAG_GOTPIC) ?	\
+				     0xffffffff : 0x00ffffff); })
+#define flat_put_addr_at_rp(rp, addr, rel) \
+	put_unaligned(((*(char *)(rp)) << 24) | ((addr) & 0x00ffffff), (rp))
+
+#endif /* __H8300_FLAT_H__ */
diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h
new file mode 100644
index 000000000000..1d09b2f2e0fe
--- /dev/null
+++ b/arch/h8300/include/asm/io.h
@@ -0,0 +1,57 @@
+#ifndef _H8300_IO_H
+#define _H8300_IO_H
+
+#ifdef __KERNEL__
+
+#include <asm-generic/io.h>
+
+/* H8/300 internal I/O functions */
+static inline unsigned char ctrl_inb(unsigned long addr)
+{
+	return *(volatile unsigned char *)addr;
+}
+
+static inline unsigned short ctrl_inw(unsigned long addr)
+{
+	return *(volatile unsigned short *)addr;
+}
+
+static inline unsigned long ctrl_inl(unsigned long addr)
+{
+	return *(volatile unsigned long *)addr;
+}
+
+static inline void ctrl_outb(unsigned char b, unsigned long addr)
+{
+	*(volatile unsigned char *)addr = b;
+}
+
+static inline void ctrl_outw(unsigned short b, unsigned long addr)
+{
+	*(volatile unsigned short *)addr = b;
+}
+
+static inline void ctrl_outl(unsigned long b, unsigned long addr)
+{
+	*(volatile unsigned long *)addr = b;
+}
+
+static inline void ctrl_bclr(int b, unsigned long addr)
+{
+	if (__builtin_constant_p(b))
+		__asm__("bclr %1,%0" : : "WU"(addr), "i"(b));
+	else
+		__asm__("bclr %w1,%0" : : "WU"(addr), "r"(b));
+}
+
+static inline void ctrl_bset(int b, unsigned long addr)
+{
+	if (__builtin_constant_p(b))
+		__asm__("bset %1,%0" : : "WU"(addr), "i"(b));
+	else
+		__asm__("bset %w1,%0" : : "WU"(addr), "r"(b));
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* _H8300_IO_H */
diff --git a/arch/h8300/include/asm/irq.h b/arch/h8300/include/asm/irq.h
new file mode 100644
index 000000000000..69f23f0981b3
--- /dev/null
+++ b/arch/h8300/include/asm/irq.h
@@ -0,0 +1,26 @@
+#ifndef _H8300_IRQ_H_
+#define _H8300_IRQ_H_
+
+#include <linux/irqchip.h>
+
+#if defined(CONFIG_CPU_H8300H)
+#define NR_IRQS 64
+#define IRQ_CHIP h8300h_irq_chip
+#define EXT_IRQ0 12
+#define EXT_IRQS 6
+#elif defined(CONFIG_CPU_H8S)
+#define NR_IRQS 128
+#define IRQ_CHIP h8s_irq_chip
+#define EXT_IRQ0 16
+#define EXT_IRQS 16
+#endif
+
+static inline int irq_canonicalize(int irq)
+{
+	return irq;
+}
+
+void h8300_init_ipr(void);
+extern struct irq_chip h8300h_irq_chip;
+extern struct irq_chip h8s_irq_chip;
+#endif /* _H8300_IRQ_H_ */
diff --git a/arch/h8300/include/asm/irqflags.h b/arch/h8300/include/asm/irqflags.h
new file mode 100644
index 000000000000..5e1e3242e470
--- /dev/null
+++ b/arch/h8300/include/asm/irqflags.h
@@ -0,0 +1,96 @@
+#ifndef _H8300_IRQFLAGS_H
+#define _H8300_IRQFLAGS_H
+
+#ifdef CONFIG_CPU_H8300H
+typedef unsigned char h8300flags;
+
+static inline h8300flags arch_local_save_flags(void)
+{
+	h8300flags flags;
+
+	__asm__ volatile ("stc ccr,%w0" : "=r" (flags));
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	__asm__ volatile ("orc  #0xc0,ccr");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	__asm__ volatile ("andc #0x3f,ccr");
+}
+
+static inline h8300flags arch_local_irq_save(void)
+{
+	h8300flags flags;
+
+	__asm__ volatile ("stc ccr,%w0\n\t"
+		      "orc  #0xc0,ccr" : "=r" (flags));
+	return flags;
+}
+
+static inline void arch_local_irq_restore(h8300flags flags)
+{
+	__asm__ volatile ("ldc %w0,ccr" : : "r" (flags) : "cc");
+}
+
+static inline int arch_irqs_disabled_flags(unsigned long flags)
+{
+	return (flags & 0xc0) == 0xc0;
+}
+#endif
+#ifdef CONFIG_CPU_H8S
+typedef unsigned short h8300flags;
+
+static inline h8300flags arch_local_save_flags(void)
+{
+	h8300flags flags;
+
+	__asm__ volatile ("stc ccr,%w0\n\tstc exr,%x0" : "=r" (flags));
+	return flags;
+}
+
+static inline void arch_local_irq_disable(void)
+{
+	__asm__ volatile ("orc #0x80,ccr\n\t");
+}
+
+static inline void arch_local_irq_enable(void)
+{
+	__asm__ volatile ("andc #0x7f,ccr\n\t"
+		      "andc #0xf0,exr\n\t");
+}
+
+static inline h8300flags arch_local_irq_save(void)
+{
+	h8300flags flags;
+
+	__asm__ volatile ("stc ccr,%w0\n\t"
+		      "stc exr,%x0\n\t"
+		      "orc  #0x80,ccr\n\t"
+		      : "=r" (flags));
+	return flags;
+}
+
+static inline void arch_local_irq_restore(h8300flags flags)
+{
+	__asm__ volatile ("ldc %w0,ccr\n\t"
+		      "ldc %x0,exr"
+		      : : "r" (flags) : "cc");
+}
+
+static inline int arch_irqs_disabled_flags(h8300flags flags)
+{
+	return (flags & 0x0080) == 0x0080;
+}
+
+#endif
+
+static inline int arch_irqs_disabled(void)
+{
+	return arch_irqs_disabled_flags(arch_local_save_flags());
+}
+
+#endif /* _H8300_IRQFLAGS_H */
diff --git a/arch/h8300/include/asm/mc146818rtc.h b/arch/h8300/include/asm/mc146818rtc.h
new file mode 100644
index 000000000000..ab9d9646d241
--- /dev/null
+++ b/arch/h8300/include/asm/mc146818rtc.h
@@ -0,0 +1,9 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _H8300_MC146818RTC_H
+#define _H8300_MC146818RTC_H
+
+/* empty include file to satisfy the include in genrtc.c/ide-geometry.c */
+
+#endif /* _H8300_MC146818RTC_H */
diff --git a/arch/h8300/include/asm/mutex.h b/arch/h8300/include/asm/mutex.h
new file mode 100644
index 000000000000..458c1f7fbc18
--- /dev/null
+++ b/arch/h8300/include/asm/mutex.h
@@ -0,0 +1,9 @@
+/*
+ * Pull in the generic implementation for the mutex fastpath.
+ *
+ * TODO: implement optimized primitives instead, or leave the generic
+ * implementation in place, or pick the atomic_xchg() based generic
+ * implementation. (see asm-generic/mutex-xchg.h for details)
+ */
+
+#include <asm-generic/mutex-dec.h>
diff --git a/arch/h8300/include/asm/page.h b/arch/h8300/include/asm/page.h
new file mode 100644
index 000000000000..3a987a567258
--- /dev/null
+++ b/arch/h8300/include/asm/page.h
@@ -0,0 +1,18 @@
+#ifndef _H8300_PAGE_H
+#define _H8300_PAGE_H
+
+#include <asm-generic/page.h>
+#include <linux/types.h>
+
+#define MAP_NR(addr) (((uintptr_t)(addr)-PAGE_OFFSET) >> PAGE_SHIFT)
+#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#ifndef __ASSEMBLY__
+extern unsigned long rom_length;
+extern unsigned long memory_start;
+extern unsigned long memory_end;
+extern unsigned long _ramend;
+#endif
+
+#endif
diff --git a/arch/h8300/include/asm/page_offset.h b/arch/h8300/include/asm/page_offset.h
new file mode 100644
index 000000000000..888576d7cc2a
--- /dev/null
+++ b/arch/h8300/include/asm/page_offset.h
@@ -0,0 +1,2 @@
+
+#define PAGE_OFFSET_RAW		0x00000000
diff --git a/arch/h8300/include/asm/pci.h b/arch/h8300/include/asm/pci.h
new file mode 100644
index 000000000000..0b2acaa3dd84
--- /dev/null
+++ b/arch/h8300/include/asm/pci.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_H8300_PCI_H
+#define _ASM_H8300_PCI_H
+
+/*
+ * asm-h8300/pci.h - H8/300 specific PCI declarations.
+ *
+ * Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#define pcibios_assign_all_busses()	0
+
+static inline void pcibios_penalize_isa_irq(int irq, int active)
+{
+	/* We don't do dynamic PCI IRQ allocation */
+}
+
+#define PCI_DMA_BUS_IS_PHYS	(1)
+
+#endif /* _ASM_H8300_PCI_H */
diff --git a/arch/h8300/include/asm/pgtable.h b/arch/h8300/include/asm/pgtable.h
new file mode 100644
index 000000000000..8341db67821d
--- /dev/null
+++ b/arch/h8300/include/asm/pgtable.h
@@ -0,0 +1,49 @@
+#ifndef _H8300_PGTABLE_H
+#define _H8300_PGTABLE_H
+#include <asm-generic/pgtable-nopud.h>
+#include <asm-generic/pgtable.h>
+#define pgtable_cache_init()   do { } while (0)
+extern void paging_init(void);
+#define PAGE_NONE		__pgprot(0)    /* these mean nothing to NO_MM */
+#define PAGE_SHARED		__pgprot(0)    /* these mean nothing to NO_MM */
+#define PAGE_COPY		__pgprot(0)    /* these mean nothing to NO_MM */
+#define PAGE_READONLY	__pgprot(0)    /* these mean nothing to NO_MM */
+#define PAGE_KERNEL		__pgprot(0)    /* these mean nothing to NO_MM */
+#define __swp_type(x)		(0)
+#define __swp_offset(x)		(0)
+#define __swp_entry(typ, off)	((swp_entry_t) { ((typ) | ((off) << 7)) })
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
+#define kern_addr_valid(addr)	(1)
+#define pgprot_writecombine(prot)  (prot)
+#define pgprot_noncached pgprot_writecombine
+
+static inline int pte_file(pte_t pte) { return 0; }
+#define swapper_pg_dir ((pgd_t *) 0)
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+#define ZERO_PAGE(vaddr)	(virt_to_page(0))
+
+/*
+ * These would be in other places but having them here reduces the diffs.
+ */
+extern unsigned int kobjsize(const void *objp);
+extern int is_in_rom(unsigned long);
+
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()   do { } while (0)
+
+/*
+ * All 32bit addresses are effectively valid for vmalloc...
+ * Sort of meaningless for non-VM targets.
+ */
+#define	VMALLOC_START	0
+#define	VMALLOC_END	0xffffffff
+
+#define arch_enter_lazy_cpu_mode()    do {} while (0)
+
+#endif /* _H8300_PGTABLE_H */
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
new file mode 100644
index 000000000000..54e3fd83c336
--- /dev/null
+++ b/arch/h8300/include/asm/processor.h
@@ -0,0 +1,144 @@
+/*
+ * include/asm-h8300/processor.h
+ *
+ * Copyright (C) 2002 Yoshinori Sato
+ *
+ * Based on: linux/asm-m68nommu/processor.h
+ *
+ * Copyright (C) 1995 Hamish Macdonald
+ */
+
+#ifndef __ASM_H8300_PROCESSOR_H
+#define __ASM_H8300_PROCESSOR_H
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#define current_text_addr() ({ __label__ _l; _l: &&_l; })
+
+#include <linux/compiler.h>
+#include <asm/segment.h>
+#include <asm/ptrace.h>
+#include <asm/current.h>
+
+static inline unsigned long rdusp(void)
+{
+	extern unsigned int	_sw_usp;
+
+	return _sw_usp;
+}
+
+static inline void wrusp(unsigned long usp)
+{
+	extern unsigned int	_sw_usp;
+
+	_sw_usp = usp;
+}
+
+/*
+ * User space process size: 3.75GB. This is hardcoded into a few places,
+ * so don't change it unless you know what you are doing.
+ */
+#define TASK_SIZE	(0xFFFFFFFFUL)
+
+#ifdef __KERNEL__
+#define STACK_TOP	TASK_SIZE
+#define STACK_TOP_MAX	STACK_TOP
+#endif
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's. We won't be using it
+ */
+#define TASK_UNMAPPED_BASE	0
+
+struct thread_struct {
+	unsigned long  ksp;		/* kernel stack pointer */
+	unsigned long  usp;		/* user stack pointer */
+	unsigned long  ccr;		/* saved status register */
+	unsigned long  esp0;            /* points to SR of stack frame */
+	struct {
+		unsigned short *addr;
+		unsigned short inst;
+	} breakinfo;
+};
+
+#define INIT_THREAD  {						\
+	.ksp  = sizeof(init_stack) + (unsigned long)init_stack, \
+	.usp  = 0,						\
+	.ccr  = PS_S,						\
+	.esp0 = 0,						\
+	.breakinfo = {						\
+		.addr = (unsigned short *)-1,			\
+		.inst = 0					\
+	}							\
+}
+
+/*
+ * Do necessary setup to start up a newly executed thread.
+ *
+ * pass the data segment into user programs if it exists,
+ * it can't hurt anything as far as I can tell
+ */
+#if defined(CONFIG_CPU_H8300H)
+#define start_thread(_regs, _pc, _usp)				\
+do {								\
+	(_regs)->pc = (_pc);					\
+	(_regs)->ccr = 0x00;	   /* clear all flags */	\
+	(_regs)->er5 = current->mm->start_data;	/* GOT base */	\
+	(_regs)->sp = ((unsigned long)(_usp)) - sizeof(unsigned long) * 3; \
+} while (0)
+#endif
+#if defined(CONFIG_CPU_H8S)
+#define start_thread(_regs, _pc, _usp)				\
+do {								\
+	(_regs)->pc = (_pc);					\
+	(_regs)->ccr = 0x00;	   /* clear kernel flag */	\
+	(_regs)->exr = 0x78;	   /* enable all interrupts */	\
+	(_regs)->er5 = current->mm->start_data;	/* GOT base */	\
+	/* 14 = space for retaddr(4), vector(4), er0(4) and exr(2) on stack */ \
+	(_regs)->sp = ((unsigned long)(_usp)) - 14;		\
+} while (0)
+#endif
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+
+/* Free all resources held by a thread. */
+static inline void release_thread(struct task_struct *dead_task)
+{
+}
+
+/*
+ * Free current thread data structures etc..
+ */
+static inline void exit_thread(void)
+{
+}
+
+/*
+ * Return saved PC of a blocked thread.
+ */
+unsigned long thread_saved_pc(struct task_struct *tsk);
+unsigned long get_wchan(struct task_struct *p);
+
+#define	KSTK_EIP(tsk)	\
+	({			 \
+		unsigned long eip = 0;	      \
+		if ((tsk)->thread.esp0 > PAGE_SIZE &&	\
+		    MAP_NR((tsk)->thread.esp0) < max_mapnr)	 \
+			eip = ((struct pt_regs *) (tsk)->thread.esp0)->pc; \
+		eip; })
+
+#define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
+
+#define cpu_relax()    barrier()
+#define cpu_relax_lowlatency()	cpu_relax()
+
+#define HARD_RESET_NOW() ({		\
+	local_irq_disable();		\
+	asm("jmp @@0");			\
+})
+
+#endif
diff --git a/arch/h8300/include/asm/ptrace.h b/arch/h8300/include/asm/ptrace.h
new file mode 100644
index 000000000000..e693fb463ea8
--- /dev/null
+++ b/arch/h8300/include/asm/ptrace.h
@@ -0,0 +1,36 @@
+#ifndef _H8300_PTRACE_H
+#define _H8300_PTRACE_H
+
+#include <uapi/asm/ptrace.h>
+
+#ifndef __ASSEMBLY__
+#ifndef PS_S
+#define PS_S  (0x10)
+#endif
+
+#if defined(CONFIG_CPU_H8300H)
+#define H8300_REGS_NO 11
+#endif
+#if defined(CONFIG_CPU_H8S)
+#define H8300_REGS_NO 12
+#endif
+
+#define arch_has_single_step()	(1)
+
+#define user_mode(regs) (!((regs)->ccr & PS_S))
+#define instruction_pointer(regs) ((regs)->pc)
+#define profile_pc(regs) instruction_pointer(regs)
+#define user_stack_pointer(regs) ((regs)->sp)
+#define current_pt_regs() ((struct pt_regs *) \
+	(THREAD_SIZE + (unsigned long)current_thread_info()) - 1)
+#define signal_pt_regs() ((struct pt_regs *)current->thread.esp0)
+#define current_user_stack_pointer() rdusp()
+#define task_pt_regs(task) \
+	((struct pt_regs *) (task_stack_page(task) + THREAD_SIZE) - 1)
+
+extern long h8300_get_reg(struct task_struct *task, int regno);
+extern int h8300_put_reg(struct task_struct *task, int regno,
+			 unsigned long data);
+
+#endif /* __ASSEMBLY__ */
+#endif /* _H8300_PTRACE_H */
diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h
new file mode 100644
index 000000000000..48424c6e169f
--- /dev/null
+++ b/arch/h8300/include/asm/segment.h
@@ -0,0 +1,45 @@
+#ifndef _H8300_SEGMENT_H
+#define _H8300_SEGMENT_H
+
+/* define constants */
+#define USER_DATA     (1)
+#ifndef __USER_DS
+#define __USER_DS     (USER_DATA)
+#endif
+#define USER_PROGRAM  (2)
+#define SUPER_DATA    (3)
+#ifndef __KERNEL_DS
+#define __KERNEL_DS   (SUPER_DATA)
+#endif
+#define SUPER_PROGRAM (4)
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+#define USER_DS		MAKE_MM_SEG(__USER_DS)
+#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
+
+/*
+ * Get/set the SFC/DFC registers for MOVES instructions
+ */
+
+static inline mm_segment_t get_fs(void)
+{
+	return USER_DS;
+}
+
+static inline mm_segment_t get_ds(void)
+{
+	/* return the supervisor data space code */
+	return KERNEL_DS;
+}
+
+#define segment_eq(a, b)	((a).seg == (b).seg)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _H8300_SEGMENT_H */
diff --git a/arch/h8300/include/asm/signal.h b/arch/h8300/include/asm/signal.h
new file mode 100644
index 000000000000..5870835c0470
--- /dev/null
+++ b/arch/h8300/include/asm/signal.h
@@ -0,0 +1,22 @@
+#ifndef _H8300_SIGNAL_H
+#define _H8300_SIGNAL_H
+
+#include <uapi/asm/signal.h>
+
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+#define _NSIG		64
+#define _NSIG_BPW	32
+#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t;		/* at least 32 bits */
+
+typedef struct {
+	unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#define __ARCH_HAS_SA_RESTORER
+#include <asm/sigcontext.h>
+
+#endif /* _H8300_SIGNAL_H */
diff --git a/arch/h8300/include/asm/smp.h b/arch/h8300/include/asm/smp.h
new file mode 100644
index 000000000000..9e9bd7e58922
--- /dev/null
+++ b/arch/h8300/include/asm/smp.h
@@ -0,0 +1 @@
+/* nothing required here yet */
diff --git a/arch/h8300/include/asm/string.h b/arch/h8300/include/asm/string.h
new file mode 100644
index 000000000000..5dc5a8ac0544
--- /dev/null
+++ b/arch/h8300/include/asm/string.h
@@ -0,0 +1,17 @@
+#ifndef _H8300_STRING_H_
+#define _H8300_STRING_H_
+
+#ifdef __KERNEL__ /* only set these up for kernel code */
+
+#include <asm/setup.h>
+#include <asm/page.h>
+
+#define __HAVE_ARCH_MEMSET
+extern void *memset(void *s, int c, size_t count);
+
+#define __HAVE_ARCH_MEMCPY
+extern void *memcpy(void *d, const void *s, size_t count);
+
+#endif /* KERNEL */
+
+#endif
diff --git a/arch/h8300/include/asm/switch_to.h b/arch/h8300/include/asm/switch_to.h
new file mode 100644
index 000000000000..7ad1bf92dbc3
--- /dev/null
+++ b/arch/h8300/include/asm/switch_to.h
@@ -0,0 +1,51 @@
+#ifndef _H8300_SWITCH_TO_H
+#define _H8300_SWITCH_TO_H
+
+/*
+ * switch_to(n) should switch tasks to task ptr, first checking that
+ * ptr isn't the current task, in which case it does nothing.  This
+ * also clears the TS-flag if the task we switched to has used the
+ * math co-processor latest.
+ */
+/*
+ * switch_to() saves the extra registers, that are not saved
+ * automatically by SAVE_SWITCH_STACK in resume(), ie. d0-d5 and
+ * a0-a1. Some of these are used by schedule() and its predecessors
+ * and so we might get see unexpected behaviors when a task returns
+ * with unexpected register values.
+ *
+ * syscall stores these registers itself and none of them are used
+ * by syscall after the function in the syscall has been called.
+ *
+ * Beware that resume now expects *next to be in d1 and the offset of
+ * tss to be in a1. This saves a few instructions as we no longer have
+ * to push them onto the stack and read them back right after.
+ *
+ * 02/17/96 - Jes Sorensen (jds@kom.auc.dk)
+ *
+ * Changed 96/09/19 by Andreas Schwab
+ * pass prev in a0, next in a1, offset of tss in d1, and whether
+ * the mm structures are shared in d2 (to avoid atc flushing).
+ *
+ * H8/300 Porting 2002/09/04 Yoshinori Sato
+ */
+
+asmlinkage void resume(void);
+#define switch_to(prev, next, last) \
+do {			     \
+	void *_last;					    \
+	__asm__ __volatile__(				    \
+		"mov.l	%1, er0\n\t"			    \
+		"mov.l	%2, er1\n\t"			    \
+		"mov.l	%3, er2\n\t"			    \
+		"jsr @_resume\n\t"			    \
+		"mov.l	er2,%0\n\t"			    \
+		: "=r" (_last)				    \
+		: "r" (&(prev->thread)),		    \
+		  "r" (&(next->thread)),		    \
+		  "g" (prev)				    \
+		: "cc", "er0", "er1", "er2", "er3");	    \
+	(last) = _last;					    \
+} while (0)
+
+#endif /* _H8300_SWITCH_TO_H */
diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h
new file mode 100644
index 000000000000..b41f688d02cf
--- /dev/null
+++ b/arch/h8300/include/asm/syscall.h
@@ -0,0 +1,56 @@
+#ifndef __ASM_H8300_SYSCALLS_32_H
+#define __ASM_H8300_SYSCALLS_32_H
+
+#ifdef __KERNEL__
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+
+static inline int
+syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+{
+	return regs->orig_er0;
+}
+
+static inline void
+syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned int i, unsigned int n, unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+
+	while (n > 0) {
+		switch (i) {
+		case 0:
+			*args++ = regs->er1;
+			break;
+		case 1:
+			*args++ = regs->er2;
+			break;
+		case 2:
+			*args++ = regs->er3;
+			break;
+		case 3:
+			*args++ = regs->er4;
+			break;
+		case 4:
+			*args++ = regs->er5;
+			break;
+		case 5:
+			*args++ = regs->er6;
+			break;
+		}
+		i++;
+		n--;
+	}
+}
+
+
+
+/* Misc syscall related bits */
+asmlinkage long do_syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void do_syscall_trace_leave(struct pt_regs *regs);
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_H8300_SYSCALLS_32_H */
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
new file mode 100644
index 000000000000..544c30785ad4
--- /dev/null
+++ b/arch/h8300/include/asm/thread_info.h
@@ -0,0 +1,111 @@
+/* thread_info.h: h8300 low-level thread information
+ * adapted from the i386 and PPC versions by Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+
+#ifndef _ASM_THREAD_INFO_H
+#define _ASM_THREAD_INFO_H
+
+#include <asm/page.h>
+#include <asm/segment.h>
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+
+/*
+ * low level task data.
+ * If you change this, change the TI_* offsets below to match.
+ */
+struct thread_info {
+	struct task_struct *task;		/* main task structure */
+	unsigned long	   flags;		/* low level flags */
+	int		   cpu;			/* cpu we're on */
+	int		   preempt_count;	/* 0 => preemptable, <0 => BUG */
+	mm_segment_t		addr_limit;
+	struct restart_block restart_block;
+};
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ */
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task =		&tsk,			\
+	.flags =	0,			\
+	.cpu =		0,			\
+	.preempt_count = INIT_PREEMPT_COUNT,	\
+	.addr_limit	= KERNEL_DS,		\
+	.restart_block	= {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+
+/*
+ * Size of kernel stack for each process. This must be a power of 2...
+ */
+#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE		8192	/* 2 pages */
+
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	struct thread_info *ti;
+
+	__asm__("mov.l	sp, %0\n\t"
+		"and.w	%1, %T0"
+		: "=&r"(ti)
+		: "i" (~(THREAD_SIZE-1) & 0xffff));
+	return ti;
+}
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * thread information flag bit numbers
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_SINGLESTEP		3	/* singlestepping active */
+#define TIF_MEMDIE		4	/* is terminating due to OOM killer */
+#define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
+#define TIF_NOTIFY_RESUME	6	/* callback before returning to user */
+#define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	8	/* for ftrace syscall instrumentation */
+#define TIF_POLLING_NRFLAG	9	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+
+/* as above, but as bit values */
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+
+/* work to do in syscall trace */
+#define _TIF_WORK_SYSCALL_MASK	(_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on any return to u-space */
+#define _TIF_ALLWORK_MASK	(_TIF_SYSCALL_TRACE | _TIF_SIGPENDING      | \
+				 _TIF_NEED_RESCHED  | _TIF_SYSCALL_AUDIT   | \
+				 _TIF_SINGLESTEP    | _TIF_NOTIFY_RESUME   | \
+				 _TIF_SYSCALL_TRACEPOINT)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK		(_TIF_ALLWORK_MASK & ~(_TIF_SYSCALL_TRACE | \
+				 _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP))
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h
new file mode 100644
index 000000000000..2c6fa4eed448
--- /dev/null
+++ b/arch/h8300/include/asm/tlb.h
@@ -0,0 +1,8 @@
+#ifndef __H8300_TLB_H__
+#define __H8300_TLB_H__
+
+#define tlb_flush(tlb)	do { } while (0)
+
+#include <asm-generic/tlb.h>
+
+#endif
diff --git a/arch/h8300/include/asm/traps.h b/arch/h8300/include/asm/traps.h
new file mode 100644
index 000000000000..aa34e75fd767
--- /dev/null
+++ b/arch/h8300/include/asm/traps.h
@@ -0,0 +1,41 @@
+/*
+ *  linux/include/asm-h8300/traps.h
+ *
+ *  Copyright (C) 2003 Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _H8300_TRAPS_H
+#define _H8300_TRAPS_H
+
+extern void _system_call(void);
+extern void _interrupt_entry(void);
+extern void _trace_break(void);
+extern void _nmi(void);
+extern void _interrupt_entry(void);
+
+extern unsigned long *_interrupt_redirect_table;
+
+#define JMP_OP 0x5a000000
+#define JSR_OP 0x5e000000
+#define VECTOR(address) ((JMP_OP)|((unsigned long)address))
+#define REDIRECT(address) ((JSR_OP)|((unsigned long)address))
+#define CPU_VECTOR ((unsigned long *)0x000000)
+#define ADDR_MASK (0xffffff)
+
+#define TRACE_VEC 5
+
+#define TRAP0_VEC 8
+#define TRAP1_VEC 9
+#define TRAP2_VEC 10
+#define TRAP3_VEC 11
+
+extern char _start, _etext;
+#define check_kernel_text(addr) \
+	((addr >= (unsigned long)(&_start)) && \
+	 (addr <  (unsigned long)(&_etext)))
+
+#endif /* _H8300_TRAPS_H */
diff --git a/arch/h8300/include/asm/user.h b/arch/h8300/include/asm/user.h
new file mode 100644
index 000000000000..2e3555f451f0
--- /dev/null
+++ b/arch/h8300/include/asm/user.h
@@ -0,0 +1,74 @@
+#ifndef _H8300_USER_H
+#define _H8300_USER_H
+
+#include <asm/page.h>
+
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user (under
+   linux we use the 'trad-core' bfd).  There are quite a number of
+   obstacles to being able to view the contents of the floating point
+   registers, and until these are solved you will not be able to view the
+   contents of them.  Actually, you can read in the core file and look at
+   the contents of the user struct to find out what the floating point
+   registers contain.
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+/* This is the old layout of "struct pt_regs" as of Linux 1.x, and
+   is still the layout used by user (the new pt_regs doesn't have
+   all registers). */
+struct user_regs_struct {
+	long er1, er2, er3, er4, er5, er6;
+	long er0;
+	long usp;
+	long orig_er0;
+	long ccr;
+	long pc;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+struct user {
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+	struct user_regs_struct regs;	/* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+/* The rest of this junk is to help gdb figure out what goes where */
+	unsigned long int u_tsize;	/* Text segment size (pages). */
+	unsigned long int u_dsize;	/* Data segment size (pages). */
+	unsigned long int u_ssize;	/* Stack segment size (pages). */
+	unsigned long start_code;     /* Starting virtual address of text. */
+	unsigned long start_stack;	/* Starting virtual address of stack area.
+					   This is actually the bottom of the stack,
+					   the top of the stack is always found in the
+					   esp register.  */
+	long int signal;		/* Signal that caused the core dump. */
+	int reserved;			/* No longer used */
+	unsigned long u_ar0;		/* Used by gdb to help find the values for */
+	/* the registers. */
+	unsigned long magic;		/* To uniquely identify a core file */
+	char u_comm[32];		/* User command that was responsible */
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
new file mode 100644
index 000000000000..fb6101a5d4f1
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -0,0 +1,30 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+
+header-y += auxvec.h
+header-y += bitsperlong.h
+header-y += errno.h
+header-y += fcntl.h
+header-y += ioctl.h
+header-y += ioctls.h
+header-y += ipcbuf.h
+header-y += kvm_para.h
+header-y += mman.h
+header-y += msgbuf.h
+header-y += param.h
+header-y += poll.h
+header-y += posix_types.h
+header-y += resource.h
+header-y += sembuf.h
+header-y += setup.h
+header-y += shmbuf.h
+header-y += siginfo.h
+header-y += socket.h
+header-y += sockios.h
+header-y += stat.h
+header-y += statfs.h
+header-y += swab.h
+header-y += termbits.h
+header-y += termios.h
+header-y += types.h
+header-y += unistd.h
diff --git a/arch/h8300/include/uapi/asm/byteorder.h b/arch/h8300/include/uapi/asm/byteorder.h
new file mode 100644
index 000000000000..13539da99efd
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/byteorder.h
@@ -0,0 +1,6 @@
+#ifndef _H8300_BYTEORDER_H
+#define _H8300_BYTEORDER_H
+
+#include <linux/byteorder/big_endian.h>
+
+#endif /* _H8300_BYTEORDER_H */
diff --git a/arch/h8300/include/uapi/asm/ptrace.h b/arch/h8300/include/uapi/asm/ptrace.h
new file mode 100644
index 000000000000..e132670d70ec
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/ptrace.h
@@ -0,0 +1,42 @@
+#ifndef _UAPI_H8300_PTRACE_H
+#define _UAPI_H8300_PTRACE_H
+
+#ifndef __ASSEMBLY__
+
+#define PT_ER1	   0
+#define PT_ER2	   1
+#define PT_ER3	   2
+#define PT_ER4	   3
+#define PT_ER5	   4
+#define PT_ER6	   5
+#define PT_ER0	   6
+#define PT_USP	   7
+#define PT_ORIG_ER0	   8
+#define PT_CCR	   9
+#define PT_PC	   10
+#define PT_EXR     11
+
+/* this struct defines the way the registers are stored on the
+   stack during a system call. */
+
+struct pt_regs {
+	long     retpc;
+	long     er4;
+	long     er5;
+	long     er6;
+	long     er3;
+	long     er2;
+	long     er1;
+	long     orig_er0;
+	long	 sp;
+	unsigned short	 ccr;
+	long     er0;
+	long     vector;
+#if defined(__H8300S__)
+	unsigned short	 exr;
+#endif
+	unsigned long  pc;
+} __attribute__((aligned(2), packed));
+
+#endif /* __ASSEMBLY__ */
+#endif /* _UAPI_H8300_PTRACE_H */
diff --git a/arch/h8300/include/uapi/asm/sigcontext.h b/arch/h8300/include/uapi/asm/sigcontext.h
new file mode 100644
index 000000000000..c41fdaa04657
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/sigcontext.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_H8300_SIGCONTEXT_H
+#define _ASM_H8300_SIGCONTEXT_H
+
+struct sigcontext {
+	unsigned long  sc_mask;		/* old sigmask */
+	unsigned long  sc_usp;		/* old user stack pointer */
+	unsigned long  sc_er0;
+	unsigned long  sc_er1;
+	unsigned long  sc_er2;
+	unsigned long  sc_er3;
+	unsigned long  sc_er4;
+	unsigned long  sc_er5;
+	unsigned long  sc_er6;
+	unsigned short sc_ccr;
+	unsigned long  sc_pc;
+};
+
+#endif
diff --git a/arch/h8300/include/uapi/asm/signal.h b/arch/h8300/include/uapi/asm/signal.h
new file mode 100644
index 000000000000..af3a6c37fee6
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/signal.h
@@ -0,0 +1,115 @@
+#ifndef _UAPI_H8300_SIGNAL_H
+#define _UAPI_H8300_SIGNAL_H
+
+#include <linux/types.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+#ifndef __KERNEL__
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+#define NSIG		32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+
+#define SIGHUP		 1
+#define SIGINT		 2
+#define SIGQUIT		 3
+#define SIGILL		 4
+#define SIGTRAP		 5
+#define SIGABRT		 6
+#define SIGIOT		 6
+#define SIGBUS		 7
+#define SIGFPE		 8
+#define SIGKILL		 9
+#define SIGUSR1		10
+#define SIGSEGV		11
+#define SIGUSR2		12
+#define SIGPIPE		13
+#define SIGALRM		14
+#define SIGTERM		15
+#define SIGSTKFLT	16
+#define SIGCHLD		17
+#define SIGCONT		18
+#define SIGSTOP		19
+#define SIGTSTP		20
+#define SIGTTIN		21
+#define SIGTTOU		22
+#define SIGURG		23
+#define SIGXCPU		24
+#define SIGXFSZ		25
+#define SIGVTALRM	26
+#define SIGPROF		27
+#define SIGWINCH	28
+#define SIGIO		29
+#define SIGPOLL		SIGIO
+/*
+#define SIGLOST		29
+*/
+#define SIGPWR		30
+#define SIGSYS		31
+#define	SIGUNUSED	31
+
+/* These should not be considered constants from userland.  */
+#define SIGRTMIN	32
+#define SIGRTMAX	_NSIG
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP	0x00000001
+#define SA_NOCLDWAIT	0x00000002 /* not supported yet */
+#define SA_SIGINFO	0x00000004
+#define SA_ONSTACK	0x08000000
+#define SA_RESTART	0x10000000
+#define SA_NODEFER	0x40000000
+#define SA_RESETHAND	0x80000000
+
+#define SA_NOMASK	SA_NODEFER
+#define SA_ONESHOT	SA_RESETHAND
+
+#define SA_RESTORER	0x04000000
+
+#define MINSIGSTKSZ	2048
+#define SIGSTKSZ	8192
+
+#include <asm-generic/signal-defs.h>
+
+#ifndef __KERNEL__
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+struct sigaction {
+	union {
+	  __sighandler_t _sa_handler;
+	  void (*_sa_sigaction)(int, struct siginfo *, void *);
+	} _u;
+	sigset_t sa_mask;
+	unsigned long sa_flags;
+	void (*sa_restorer)(void);
+};
+
+#define sa_handler	_u._sa_handler
+#define sa_sigaction	_u._sa_sigaction
+
+#endif /* __KERNEL__ */
+
+typedef struct sigaltstack {
+	void *ss_sp;
+	int ss_flags;
+	size_t ss_size;
+} stack_t;
+
+
+#endif /* _UAPI_H8300_SIGNAL_H */
diff --git a/arch/h8300/include/uapi/asm/unistd.h b/arch/h8300/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..7a2eb698def3
--- /dev/null
+++ b/arch/h8300/include/uapi/asm/unistd.h
@@ -0,0 +1,3 @@
+#define __ARCH_NOMMU
+
+#include <asm-generic/unistd.h>
diff --git a/arch/h8300/kernel/Makefile b/arch/h8300/kernel/Makefile
new file mode 100644
index 000000000000..5bc33f2fcc08
--- /dev/null
+++ b/arch/h8300/kernel/Makefile
@@ -0,0 +1,19 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-y := vmlinux.lds
+
+obj-y := process.o traps.o ptrace.o \
+	 signal.o setup.o syscalls.o \
+	 irq.o entry.o dma.o
+
+obj-$(CONFIG_ROMKERNEL) += head_rom.o
+obj-$(CONFIG_RAMKERNEL) += head_ram.o
+
+obj-$(CONFIG_MODULES) += module.o h8300_ksyms.o
+obj-$(CONFIG_H8300H_SIM) += sim-console.o
+obj-$(CONFIG_H8S_SIM) += sim-console.o
+
+obj-$(CONFIG_CPU_H8300H) += ptrace_h.o
+obj-$(CONFIG_CPU_H8S) += ptrace_s.o
diff --git a/arch/h8300/kernel/asm-offsets.c b/arch/h8300/kernel/asm-offsets.c
new file mode 100644
index 000000000000..dc2d16ce8a0d
--- /dev/null
+++ b/arch/h8300/kernel/asm-offsets.c
@@ -0,0 +1,67 @@
+/*
+ * This program is used to generate definitions needed by
+ * assembly language modules.
+ *
+ * We use the technique used in the OSF Mach kernel code:
+ * generate asm statements containing #defines,
+ * compile this file to assembler, and then extract the
+ * #defines from the assembly-language output.
+ */
+
+#include <linux/stddef.h>
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/ptrace.h>
+#include <linux/hardirq.h>
+#include <linux/kbuild.h>
+#include <asm/irq.h>
+#include <asm/ptrace.h>
+
+int main(void)
+{
+	/* offsets into the task struct */
+	OFFSET(TASK_STATE, task_struct, state);
+	OFFSET(TASK_FLAGS, task_struct, flags);
+	OFFSET(TASK_PTRACE, task_struct, ptrace);
+	OFFSET(TASK_BLOCKED, task_struct, blocked);
+	OFFSET(TASK_THREAD, task_struct, thread);
+	OFFSET(TASK_THREAD_INFO, task_struct, stack);
+	OFFSET(TASK_MM, task_struct, mm);
+	OFFSET(TASK_ACTIVE_MM, task_struct, active_mm);
+
+	/* offsets into the irq_cpustat_t struct */
+	DEFINE(CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t,
+						 __softirq_pending));
+
+	/* offsets into the thread struct */
+	OFFSET(THREAD_KSP, thread_struct, ksp);
+	OFFSET(THREAD_USP, thread_struct, usp);
+	OFFSET(THREAD_CCR, thread_struct, ccr);
+
+	/* offsets into the pt_regs struct */
+	DEFINE(LER0,  offsetof(struct pt_regs, er0)      - sizeof(long));
+	DEFINE(LER1,  offsetof(struct pt_regs, er1)      - sizeof(long));
+	DEFINE(LER2,  offsetof(struct pt_regs, er2)      - sizeof(long));
+	DEFINE(LER3,  offsetof(struct pt_regs, er3)      - sizeof(long));
+	DEFINE(LER4,  offsetof(struct pt_regs, er4)      - sizeof(long));
+	DEFINE(LER5,  offsetof(struct pt_regs, er5)      - sizeof(long));
+	DEFINE(LER6,  offsetof(struct pt_regs, er6)      - sizeof(long));
+	DEFINE(LORIG, offsetof(struct pt_regs, orig_er0) - sizeof(long));
+	DEFINE(LSP,   offsetof(struct pt_regs, sp)       - sizeof(long));
+	DEFINE(LCCR,  offsetof(struct pt_regs, ccr)      - sizeof(long));
+	DEFINE(LVEC,  offsetof(struct pt_regs, vector)   - sizeof(long));
+#if defined(CONFIG_CPU_H8S)
+	DEFINE(LEXR,  offsetof(struct pt_regs, exr)      - sizeof(long));
+#endif
+	DEFINE(LRET,  offsetof(struct pt_regs, pc)       - sizeof(long));
+
+	DEFINE(PT_PTRACED, PT_PTRACED);
+
+	/* offsets in thread_info structure */
+	OFFSET(TI_TASK, thread_info, task);
+	OFFSET(TI_FLAGS, thread_info, flags);
+	OFFSET(TI_CPU, thread_info, cpu);
+	OFFSET(TI_PRE, thread_info, preempt_count);
+
+	return 0;
+}
diff --git a/arch/h8300/kernel/dma.c b/arch/h8300/kernel/dma.c
new file mode 100644
index 000000000000..eeb13d3f2424
--- /dev/null
+++ b/arch/h8300/kernel/dma.c
@@ -0,0 +1,69 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/scatterlist.h>
+#include <linux/module.h>
+#include <asm/pgalloc.h>
+
+static void *dma_alloc(struct device *dev, size_t size,
+		       dma_addr_t *dma_handle, gfp_t gfp,
+		       struct dma_attrs *attrs)
+{
+	void *ret;
+
+	/* ignore region specifiers */
+	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
+
+	if (dev == NULL || (*dev->dma_mask < 0xffffffff))
+		gfp |= GFP_DMA;
+	ret = (void *)__get_free_pages(gfp, get_order(size));
+
+	if (ret != NULL) {
+		memset(ret, 0, size);
+		*dma_handle = virt_to_phys(ret);
+	}
+	return ret;
+}
+
+static void dma_free(struct device *dev, size_t size,
+		     void *vaddr, dma_addr_t dma_handle,
+		     struct dma_attrs *attrs)
+
+{
+	free_pages((unsigned long)vaddr, get_order(size));
+}
+
+static dma_addr_t map_page(struct device *dev, struct page *page,
+				  unsigned long offset, size_t size,
+				  enum dma_data_direction direction,
+				  struct dma_attrs *attrs)
+{
+	return page_to_phys(page) + offset;
+}
+
+static int map_sg(struct device *dev, struct scatterlist *sgl,
+		  int nents, enum dma_data_direction direction,
+		  struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = sg_phys(sg);
+	}
+
+	return nents;
+}
+
+struct dma_map_ops h8300_dma_map_ops = {
+	.alloc = dma_alloc,
+	.free = dma_free,
+	.map_page = map_page,
+	.map_sg = map_sg,
+};
+EXPORT_SYMBOL(h8300_dma_map_ops);
diff --git a/arch/h8300/kernel/entry.S b/arch/h8300/kernel/entry.S
new file mode 100644
index 000000000000..797dfa8ddeb2
--- /dev/null
+++ b/arch/h8300/kernel/entry.S
@@ -0,0 +1,414 @@
+/*
+ *
+ *  linux/arch/h8300/kernel/entry.S
+ *
+ *  Yoshinori Sato <ysato@users.sourceforge.jp>
+ *  David McCullough <davidm@snapgear.com>
+ *
+ */
+
+/*
+ *  entry.S
+ *  include exception/interrupt gateway
+ *          system call entry
+ */
+
+#include <linux/sys.h>
+#include <asm/unistd.h>
+#include <asm/setup.h>
+#include <asm/segment.h>
+#include <asm/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+
+#if defined(CONFIG_CPU_H8300H)
+#define USERRET 8
+INTERRUPTS = 64
+	.h8300h
+	.macro	SHLL2 reg
+	shll.l	\reg
+	shll.l	\reg
+	.endm
+	.macro	SHLR2 reg
+	shlr.l	\reg
+	shlr.l	\reg
+	.endm
+	.macro	SAVEREGS
+	mov.l	er0,@-sp
+	mov.l	er1,@-sp
+	mov.l	er2,@-sp
+	mov.l	er3,@-sp
+	.endm
+	.macro	RESTOREREGS
+	mov.l	@sp+,er3
+	mov.l	@sp+,er2
+	.endm
+	.macro	SAVEEXR
+	.endm
+	.macro	RESTOREEXR
+	.endm
+#endif
+#if defined(CONFIG_CPU_H8S)
+#define USERRET 10
+#define USEREXR 8
+INTERRUPTS = 128
+	.h8300s
+	.macro	SHLL2 reg
+	shll.l	#2,\reg
+	.endm
+	.macro	SHLR2 reg
+	shlr.l	#2,\reg
+	.endm
+	.macro	SAVEREGS
+	stm.l	er0-er3,@-sp
+	.endm
+	.macro	RESTOREREGS
+	ldm.l	@sp+,er2-er3
+	.endm
+	.macro	SAVEEXR
+	mov.w	@(USEREXR:16,er0),r1
+	mov.w	r1,@(LEXR-LER3:16,sp)		/* copy EXR */
+	.endm
+	.macro	RESTOREEXR
+	mov.w	@(LEXR-LER1:16,sp),r1		/* restore EXR */
+	mov.b	r1l,r1h
+	mov.w	r1,@(USEREXR:16,er0)
+	.endm
+#endif
+
+
+/* CPU context save/restore macros. */
+
+	.macro	SAVE_ALL
+	mov.l	er0,@-sp
+	stc	ccr,r0l				/* check kernel mode */
+	btst	#4,r0l
+	bne	5f
+
+	/* user mode */
+	mov.l	sp,@_sw_usp
+	mov.l	@sp,er0				/* restore saved er0 */
+	orc	#0x10,ccr			/* switch kernel stack */
+	mov.l	@_sw_ksp,sp
+	sub.l	#(LRET-LORIG),sp		/* allocate LORIG - LRET */
+	SAVEREGS
+	mov.l   @_sw_usp,er0
+	mov.l   @(USERRET:16,er0),er1           /* copy the RET addr */
+	mov.l   er1,@(LRET-LER3:16,sp)
+	SAVEEXR
+
+	mov.l	@(LORIG-LER3:16,sp),er0
+	mov.l	er0,@(LER0-LER3:16,sp)		/* copy ER0 */
+	mov.w	e1,r1				/* e1 highbyte = ccr */
+	and	#0xef,r1h			/* mask mode? flag */
+	bra	6f
+5:
+	/* kernel mode */
+	mov.l	@sp,er0				/* restore saved er0 */
+	subs	#2,sp				/* set dummy ccr */
+	subs	#4,sp				/* set dummp sp */
+	SAVEREGS
+	mov.w	@(LRET-LER3:16,sp),r1		/* copy old ccr */
+6:
+	mov.b	r1h,r1l
+	mov.b	#0,r1h
+	mov.w	r1,@(LCCR-LER3:16,sp)		/* set ccr */
+	mov.l	@_sw_usp,er2
+	mov.l	er2,@(LSP-LER3:16,sp)		/* set usp */
+	mov.l	er6,@-sp			/* syscall arg #6 */
+	mov.l	er5,@-sp			/* syscall arg #5 */
+	mov.l	er4,@-sp			/* syscall arg #4 */
+	.endm					/* r1 = ccr */
+
+	.macro	RESTORE_ALL
+	mov.l	@sp+,er4
+	mov.l	@sp+,er5
+	mov.l	@sp+,er6
+	RESTOREREGS
+	mov.w	@(LCCR-LER1:16,sp),r0		/* check kernel mode */
+	btst	#4,r0l
+	bne	7f
+
+	orc	#0xc0,ccr
+	mov.l	@(LSP-LER1:16,sp),er0
+	mov.l	@(LER0-LER1:16,sp),er1		/* restore ER0 */
+	mov.l	er1,@er0
+	RESTOREEXR
+	mov.w	@(LCCR-LER1:16,sp),r1		/* restore the RET addr */
+	mov.b	r1l,r1h
+	mov.b	@(LRET+1-LER1:16,sp),r1l
+	mov.w	r1,e1
+	mov.w	@(LRET+2-LER1:16,sp),r1
+	mov.l	er1,@(USERRET:16,er0)
+
+	mov.l	@sp+,er1
+	add.l	#(LRET-LER1),sp			/* remove LORIG - LRET */
+	mov.l	sp,@_sw_ksp
+	andc	#0xef,ccr			/* switch to user mode */
+	mov.l	er0,sp
+	bra	8f
+7:
+	mov.l	@sp+,er1
+	add.l	#10,sp
+8:
+	mov.l	@sp+,er0
+	adds	#4,sp				/* remove the sw created LVEC */
+	rte
+	.endm
+
+.globl _system_call
+.globl ret_from_exception
+.globl ret_from_fork
+.globl ret_from_kernel_thread
+.globl ret_from_interrupt
+.globl _interrupt_redirect_table
+.globl _sw_ksp,_sw_usp
+.globl _resume
+.globl _interrupt_entry
+.globl _trace_break
+.globl _nmi
+
+#if defined(CONFIG_ROMKERNEL)
+	.section .int_redirect,"ax"
+_interrupt_redirect_table:
+#if defined(CONFIG_CPU_H8300H)
+	.rept	7
+	.long	0
+	.endr
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.rept	5
+	.long	0
+	.endr
+	jmp	@_trace_break
+	.long	0
+#endif
+
+	jsr	@_interrupt_entry		/* NMI */
+	jmp	@_system_call			/* TRAPA #0 (System call) */
+	.long	0
+	.long	0
+	jmp	@_trace_break			/* TRAPA #3 (breakpoint) */
+	.rept	INTERRUPTS-12
+	jsr	@_interrupt_entry
+	.endr
+#endif
+#if defined(CONFIG_RAMKERNEL)
+.globl _interrupt_redirect_table
+	.section .bss
+_interrupt_redirect_table:
+	.space	4
+#endif
+
+	.section .text
+	.align	2
+_interrupt_entry:
+	SAVE_ALL
+/* r1l is saved ccr */
+	mov.l	sp,er0
+	add.l	#LVEC,er0
+	btst	#4,r1l
+	bne	1f
+	/* user LVEC */
+	mov.l	@_sw_usp,er0
+	adds	#4,er0
+1:
+	mov.l	@er0,er0			/* LVEC address */
+#if defined(CONFIG_ROMKERNEL)
+	sub.l	#_interrupt_redirect_table,er0
+#endif
+#if defined(CONFIG_RAMKERNEL)
+	mov.l	@_interrupt_redirect_table,er1
+	sub.l	er1,er0
+#endif
+	SHLR2	er0
+	dec.l	#1,er0
+	mov.l	sp,er1
+	subs	#4,er1				/* adjust ret_pc */
+#if defined(CONFIG_CPU_H8S)
+	orc	#7,exr
+#endif
+	jsr	@do_IRQ
+	jmp	@ret_from_interrupt
+
+_system_call:
+	subs	#4,sp				/* dummy LVEC */
+	SAVE_ALL
+	/* er0: syscall nr */
+	andc	#0xbf,ccr
+	mov.l	er0,er4
+
+	/* save top of frame */
+	mov.l	sp,er0
+	jsr	@set_esp0
+	mov.l	sp,er2
+	and.w	#0xe000,r2
+	mov.l	@(TI_FLAGS:16,er2),er2
+	and.w	#_TIF_WORK_SYSCALL_MASK,r2
+	beq	1f
+	mov.l	sp,er0
+	jsr	@do_syscall_trace_enter
+1:
+	cmp.l	#__NR_syscalls,er4
+	bcc	badsys
+	SHLL2	er4
+	mov.l	#_sys_call_table,er0
+	add.l	er4,er0
+	mov.l	@er0,er4
+	beq	ret_from_exception:16
+	mov.l	@(LER1:16,sp),er0
+	mov.l	@(LER2:16,sp),er1
+	mov.l	@(LER3:16,sp),er2
+	jsr	@er4
+	mov.l	er0,@(LER0:16,sp)		/* save the return value */
+	mov.l	sp,er2
+	and.w	#0xe000,r2
+	mov.l	@(TI_FLAGS:16,er2),er2
+	and.w	#_TIF_WORK_SYSCALL_MASK,r2
+	beq	2f
+	mov.l	sp,er0
+	jsr	@do_syscall_trace_leave
+2:
+	orc	#0xc0,ccr
+	bra	resume_userspace
+
+badsys:
+	mov.l	#-ENOSYS,er0
+	mov.l	er0,@(LER0:16,sp)
+	bra	resume_userspace
+
+#if !defined(CONFIG_PREEMPT)
+#define resume_kernel restore_all
+#endif
+
+ret_from_exception:
+#if defined(CONFIG_PREEMPT)
+	orc	#0xc0,ccr
+#endif
+ret_from_interrupt:
+	mov.b	@(LCCR+1:16,sp),r0l
+	btst	#4,r0l
+	bne	resume_kernel:16	/* return from kernel */
+resume_userspace:
+	andc	#0xbf,ccr
+	mov.l	sp,er4
+	and.w	#0xe000,r4		/* er4 <- current thread info */
+	mov.l	@(TI_FLAGS:16,er4),er1
+	and.l	#_TIF_WORK_MASK,er1
+	beq	restore_all:8
+work_pending:
+	btst	#TIF_NEED_RESCHED,r1l
+	bne	work_resched:8
+	/* work notifysig */
+	mov.l	sp,er0
+	subs	#4,er0			/* er0: pt_regs */
+	jsr	@do_notify_resume
+	bra	resume_userspace:8
+work_resched:
+	mov.l	sp,er0
+	jsr	@set_esp0
+	jsr	@schedule
+	bra	resume_userspace:8
+restore_all:
+	RESTORE_ALL			/* Does RTE */
+
+#if defined(CONFIG_PREEMPT)
+resume_kernel:
+	mov.l	@(TI_PRE_COUNT:16,er4),er0
+	bne	restore_all:8
+need_resched:
+	mov.l	@(TI_FLAGS:16,er4),er0
+	btst	#TIF_NEED_RESCHED,r0l
+	beq	restore_all:8
+	mov.b	@(LCCR+1:16,sp),r0l	/* Interrupt Enabled? */
+	bmi	restore_all:8
+	mov.l	sp,er0
+	jsr	@set_esp0
+	jsr	@preempt_schedule_irq
+	bra	need_resched:8
+#endif
+
+ret_from_fork:
+	mov.l	er2,er0
+	jsr	@schedule_tail
+	jmp	@ret_from_exception
+
+ret_from_kernel_thread:
+	mov.l	er2,er0
+	jsr	@schedule_tail
+	mov.l	@(LER4:16,sp),er0
+	mov.l	@(LER5:16,sp),er1
+	jsr	@er1
+	jmp	@ret_from_exception
+
+_resume:
+	/*
+	 * Beware - when entering resume, offset of tss is in d1,
+	 * prev (the current task) is in a0, next (the new task)
+	 * is in a1 and d2.b is non-zero if the mm structure is
+	 * shared between the tasks, so don't change these
+	 * registers until their contents are no longer needed.
+	 */
+
+	/* save sr */
+	sub.w	r3,r3
+	stc	ccr,r3l
+	mov.w	r3,@(THREAD_CCR+2:16,er0)
+
+	/* disable interrupts */
+	orc	#0xc0,ccr
+	mov.l	@_sw_usp,er3
+	mov.l	er3,@(THREAD_USP:16,er0)
+	mov.l	sp,@(THREAD_KSP:16,er0)
+
+	/* Skip address space switching if they are the same. */
+	/* FIXME: what did we hack out of here, this does nothing! */
+
+	mov.l	@(THREAD_USP:16,er1),er0
+	mov.l	er0,@_sw_usp
+	mov.l	@(THREAD_KSP:16,er1),sp
+
+	/* restore status register */
+	mov.w	@(THREAD_CCR+2:16,er1),r3
+
+	ldc	r3l,ccr
+	rts
+
+_trace_break:
+	subs	#4,sp
+	SAVE_ALL
+	sub.l	er1,er1
+	dec.l	#1,er1
+	mov.l	er1,@(LORIG,sp)
+	mov.l	sp,er0
+	jsr	@set_esp0
+	mov.l	@_sw_usp,er0
+	mov.l	@er0,er1
+	mov.w	@(-2:16,er1),r2
+	cmp.w	#0x5730,r2
+	beq	1f
+	subs	#2,er1
+	mov.l	er1,@er0
+1:
+	and.w	#0xff,e1
+	mov.l	er1,er0
+	jsr	@trace_trap
+	jmp	@ret_from_exception
+
+_nmi:
+	subs	#4, sp
+	mov.l	er0, @-sp
+	mov.l	@_interrupt_redirect_table, er0
+	add.l	#8*4, er0
+	mov.l	er0, @(4,sp)
+	mov.l	@sp+, er0
+	jmp	@_interrupt_entry
+
+	.section	.bss
+_sw_ksp:
+	.space	4
+_sw_usp:
+	.space	4
+
+	.end
diff --git a/arch/h8300/kernel/h8300_ksyms.c b/arch/h8300/kernel/h8300_ksyms.c
new file mode 100644
index 000000000000..a9033c838968
--- /dev/null
+++ b/arch/h8300/kernel/h8300_ksyms.c
@@ -0,0 +1,36 @@
+#include <linux/module.h>
+#include <linux/linkage.h>
+
+/*
+ * libgcc functions - functions that are used internally by the
+ * compiler...  (prototypes are not correct though, but that
+ * doesn't really matter since they're not versioned).
+ */
+asmlinkage long __ucmpdi2(long long, long long);
+asmlinkage long long __ashldi3(long long, int);
+asmlinkage long long __ashrdi3(long long, int);
+asmlinkage long long __lshrdi3(long long, int);
+asmlinkage long __divsi3(long, long);
+asmlinkage long __modsi3(long, long);
+asmlinkage unsigned long __umodsi3(unsigned long, unsigned long);
+asmlinkage long long __muldi3(long long, long long);
+asmlinkage long __mulsi3(long, long);
+asmlinkage long __udivsi3(long, long);
+asmlinkage void *memcpy(void *, const void *, size_t);
+asmlinkage void *memset(void *, int, size_t);
+asmlinkage long strncpy_from_user(void *to, void *from, size_t n);
+
+	/* gcc lib functions */
+EXPORT_SYMBOL(__ucmpdi2);
+EXPORT_SYMBOL(__ashldi3);
+EXPORT_SYMBOL(__ashrdi3);
+EXPORT_SYMBOL(__lshrdi3);
+EXPORT_SYMBOL(__divsi3);
+EXPORT_SYMBOL(__modsi3);
+EXPORT_SYMBOL(__umodsi3);
+EXPORT_SYMBOL(__muldi3);
+EXPORT_SYMBOL(__mulsi3);
+EXPORT_SYMBOL(__udivsi3);
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/h8300/kernel/head_ram.S b/arch/h8300/kernel/head_ram.S
new file mode 100644
index 000000000000..84ac5c3ed31a
--- /dev/null
+++ b/arch/h8300/kernel/head_ram.S
@@ -0,0 +1,60 @@
+
+#include <linux/sys.h>
+#include <linux/init.h>
+#include <asm/unistd.h>
+#include <asm/setup.h>
+#include <asm/segment.h>
+#include <asm/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+
+#if defined(CONFIG_CPU_H8300H)
+	.h8300h
+#define SYSCR 0xfee012
+#define IRAMTOP 0xffff20
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.h8300s
+#define INTCR 0xffff31
+#define IRAMTOP 0xffc000
+#endif
+
+	__HEAD
+	.global	_start
+_start:
+	mov.l	#IRAMTOP,sp
+	/* .bss clear */
+	mov.l	#_sbss,er5
+	mov.l	#_ebss,er4
+	sub.l	er5,er4
+	shlr	er4
+	shlr	er4
+	sub.l	er2,er2
+1:
+	mov.l	er2,@er5
+	adds	#4,er5
+	dec.l	#1,er4
+	bne	1b
+	jsr	@h8300_fdt_init
+
+	/* linux kernel start */
+#if defined(CONFIG_CPU_H8300H)
+	ldc	#0xd0,ccr	/* running kernel */
+	mov.l	#SYSCR,er0
+	bclr	#3,@er0
+#endif
+#if defined(CONFIG_CPU_H8S)
+	ldc	#0x07,exr
+	bclr	#4,@INTCR:8
+	bset	#5,@INTCR:8	/* Interrupt mode 2 */
+	ldc	#0x90,ccr	/* running kernel */
+#endif
+	mov.l	#init_thread_union,sp
+	add.l	#0x2000,sp
+	jsr	@start_kernel
+
+1:
+	bra	1b
+
+	.end
diff --git a/arch/h8300/kernel/head_rom.S b/arch/h8300/kernel/head_rom.S
new file mode 100644
index 000000000000..9868a4121a1f
--- /dev/null
+++ b/arch/h8300/kernel/head_rom.S
@@ -0,0 +1,110 @@
+#include <linux/init.h>
+#include <asm/thread_info.h>
+
+#if defined(CONFIG_CPU_H8300H)
+	.h8300h
+#define SYSCR 0xfee012
+#define IRAMTOP 0xffff20
+#define NR_INT 64
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.h8300s
+#define INTCR 0xffff31
+#define IRAMTOP 0xffc000
+#define NR_INT 128
+#endif
+
+	__HEAD
+	.global	_start
+_start:
+	mov.l	#IRAMTOP,sp
+#if !defined(CONFIG_H8300H_SIM) && \
+    !defined(CONFIG_H8S_SIM)
+	jsr	@lowlevel_init
+
+	/* copy .data */
+	mov.l	#_begin_data,er5
+	mov.l	#_sdata,er6
+	mov.l	#_edata,er4
+	sub.l	er6,er4
+	shlr.l	er4
+	shlr.l	er4
+1:
+	mov.l	@er5+,er0
+	mov.l	er0,@er6
+	adds	#4,er6
+	dec.l	#1,er4
+	bne	1b
+	/* .bss clear */
+	mov.l	#_sbss,er5
+	mov.l	#_ebss,er4
+	sub.l	er5,er4
+	shlr	er4
+	shlr	er4
+	sub.l	er0,er0
+1:
+	mov.l	er0,@er5
+	adds	#4,er5
+	dec.l	#1,er4
+	bne	1b
+#else
+	/* get cmdline from gdb */
+	jsr	@0xcc
+	;; er0 - argc
+	;; er1 - argv
+	mov.l	#command_line,er3
+	adds	#4,er1
+	dec.l	#1,er0
+	beq	4f
+1:
+	mov.l	@er1+,er2
+2:
+	mov.b	@er2+,r4l
+	beq	3f
+	mov.b	r4l,@er3
+	adds	#1,er3
+	bra	2b
+3:
+	mov.b	#' ',r4l
+	mov.b	r4l,@er3
+	adds	#1,er3
+	dec.l	#1,er0
+	bne	1b
+	subs	#1,er3
+	mov.b	#0,r4l
+	mov.b	r4l,@er3
+4:
+#endif
+	sub.l	er0,er0
+	jsr	@h8300_fdt_init
+	/* linux kernel start */
+#if defined(CONFIG_CPU_H8300H)
+	ldc	#0xd0,ccr	/* running kernel */
+	mov.l	#SYSCR,er0
+	bclr	#3,@er0
+#endif
+#if defined(CONFIG_CPU_H8S)
+	ldc	#0x07,exr
+	bclr	#4,@INTCR:8
+	bset	#5,@INTCR:8	/* Interrupt mode 2 */
+	ldc	#0x90,ccr	/* running kernel */
+#endif
+	mov.l	#init_thread_union,sp
+	add.l	#0x2000,sp
+	jsr	@start_kernel
+
+1:
+	bra	1b
+
+#if defined(CONFIG_ROMKERNEL)
+	/* interrupt vector */
+	.section .vectors,"ax"
+	.long	_start
+	.long	_start
+vector	=	2
+	.rept	NR_INT - 2
+	.long	_interrupt_redirect_table+vector*4
+vector	=	vector + 1
+	.endr
+#endif
+	.end
diff --git a/arch/h8300/kernel/irq.c b/arch/h8300/kernel/irq.c
new file mode 100644
index 000000000000..da79f9521699
--- /dev/null
+++ b/arch/h8300/kernel/irq.c
@@ -0,0 +1,97 @@
+/*
+ * linux/arch/h8300/kernel/irq.c
+ *
+ * Copyright 2014-2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_irq.h>
+#include <asm/traps.h>
+
+#ifdef CONFIG_RAMKERNEL
+typedef void (*h8300_vector)(void);
+
+static const h8300_vector __initconst trap_table[] = {
+	0, 0, 0, 0,
+	_trace_break,
+	0, 0,
+	_nmi,
+	_system_call,
+	0, 0,
+	_trace_break,
+};
+
+static unsigned long __init *get_vector_address(void)
+{
+	unsigned long *rom_vector = CPU_VECTOR;
+	unsigned long base, tmp;
+	int vec_no;
+
+	base = rom_vector[EXT_IRQ0] & ADDR_MASK;
+
+	/* check romvector format */
+	for (vec_no = EXT_IRQ0 + 1; vec_no <= EXT_IRQ0+EXT_IRQS; vec_no++) {
+		if ((base+(vec_no - EXT_IRQ0)*4) !=
+		    (rom_vector[vec_no] & ADDR_MASK))
+			return NULL;
+	}
+
+	/* ramvector base address */
+	base -= EXT_IRQ0*4;
+
+	/* writerble? */
+	tmp = ~(*(volatile unsigned long *)base);
+	(*(volatile unsigned long *)base) = tmp;
+	if ((*(volatile unsigned long *)base) != tmp)
+		return NULL;
+	return (unsigned long *)base;
+}
+
+static void __init setup_vector(void)
+{
+	int i;
+	unsigned long *ramvec, *ramvec_p;
+	const h8300_vector *trap_entry;
+
+	ramvec = get_vector_address();
+	if (ramvec == NULL)
+		panic("interrupt vector serup failed.");
+	else
+		pr_debug("virtual vector at 0x%p\n", ramvec);
+
+	/* create redirect table */
+	ramvec_p = ramvec;
+	trap_entry = trap_table;
+	for (i = 0; i < NR_IRQS; i++) {
+		if (i < 12) {
+			if (*trap_entry)
+				*ramvec_p = VECTOR(*trap_entry);
+			ramvec_p++;
+			trap_entry++;
+		} else
+			*ramvec_p++ = REDIRECT(_interrupt_entry);
+	}
+	_interrupt_redirect_table = ramvec;
+}
+#else
+void setup_vector(void)
+{
+	/* noting do */
+}
+#endif
+
+void __init init_IRQ(void)
+{
+	setup_vector();
+	irqchip_init();
+}
+
+asmlinkage void do_IRQ(int irq)
+{
+	irq_enter();
+	generic_handle_irq(irq);
+	irq_exit();
+}
diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c
new file mode 100644
index 000000000000..515f6c4e8d80
--- /dev/null
+++ b/arch/h8300/kernel/module.c
@@ -0,0 +1,70 @@
+#include <linux/moduleloader.h>
+#include <linux/elf.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+
+int apply_relocate_add(Elf32_Shdr *sechdrs,
+		       const char *strtab,
+		       unsigned int symindex,
+		       unsigned int relsec,
+		       struct module *me)
+{
+	unsigned int i;
+	Elf32_Rela *rela = (void *)sechdrs[relsec].sh_addr;
+
+	pr_debug("Applying relocate section %u to %u\n", relsec,
+	       sechdrs[relsec].sh_info);
+	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
+		/* This is where to make the change */
+		uint32_t *loc =
+			(uint32_t *)(sechdrs[sechdrs[relsec].sh_info].sh_addr
+					     + rela[i].r_offset);
+		/* This is the symbol it is referring to.  Note that all
+		   undefined symbols have been resolved.  */
+		Elf32_Sym *sym = (Elf32_Sym *)sechdrs[symindex].sh_addr
+			+ ELF32_R_SYM(rela[i].r_info);
+		uint32_t v = sym->st_value + rela[i].r_addend;
+
+		switch (ELF32_R_TYPE(rela[i].r_info)) {
+		case R_H8_DIR24R8:
+			loc = (uint32_t *)((uint32_t)loc - 1);
+			*loc = (*loc & 0xff000000) | ((*loc & 0xffffff) + v);
+			break;
+		case R_H8_DIR24A8:
+			if (ELF32_R_SYM(rela[i].r_info))
+				*loc += v;
+			break;
+		case R_H8_DIR32:
+		case R_H8_DIR32A16:
+			*loc += v;
+			break;
+		case R_H8_PCREL16:
+			v -= (unsigned long)loc + 2;
+			if ((Elf32_Sword)v > 0x7fff ||
+			    (Elf32_Sword)v < -(Elf32_Sword)0x8000)
+				goto overflow;
+			else
+				*(unsigned short *)loc = v;
+			break;
+		case R_H8_PCREL8:
+			v -= (unsigned long)loc + 1;
+			if ((Elf32_Sword)v > 0x7f ||
+			    (Elf32_Sword)v < -(Elf32_Sword)0x80)
+				goto overflow;
+			else
+				*(unsigned char *)loc = v;
+			break;
+		default:
+			pr_err("module %s: Unknown relocation: %u\n",
+			       me->name, ELF32_R_TYPE(rela[i].r_info));
+			return -ENOEXEC;
+		}
+	}
+	return 0;
+ overflow:
+	pr_err("module %s: relocation offset overflow: %08x\n",
+	       me->name, rela[i].r_offset);
+	return -ENOEXEC;
+}
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
new file mode 100644
index 000000000000..dee41256922c
--- /dev/null
+++ b/arch/h8300/kernel/process.c
@@ -0,0 +1,171 @@
+/*
+ *  linux/arch/h8300/kernel/process.c
+ *
+ * Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ *  Based on:
+ *
+ *  linux/arch/m68knommu/kernel/process.c
+ *
+ *  Copyright (C) 1998  D. Jeff Dionne <jeff@ryeham.ee.ryerson.ca>,
+ *                      Kenneth Albanowski <kjahds@kjahds.com>,
+ *                      The Silver Hammer Group, Ltd.
+ *
+ *  linux/arch/m68k/kernel/process.c
+ *
+ *  Copyright (C) 1995  Hamish Macdonald
+ *
+ *  68060 fixes by Jesper Skov
+ */
+
+/*
+ * This file handles the architecture-dependent parts of process handling..
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/ptrace.h>
+#include <linux/user.h>
+#include <linux/interrupt.h>
+#include <linux/reboot.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+
+#include <asm/uaccess.h>
+#include <asm/traps.h>
+#include <asm/setup.h>
+#include <asm/pgtable.h>
+
+void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
+
+asmlinkage void ret_from_fork(void);
+asmlinkage void ret_from_kernel_thread(void);
+
+/*
+ * The idle loop on an H8/300..
+ */
+void arch_cpu_idle(void)
+{
+	local_irq_enable();
+	__asm__("sleep");
+}
+
+void machine_restart(char *__unused)
+{
+	local_irq_disable();
+	__asm__("jmp @@0");
+}
+
+void machine_halt(void)
+{
+	local_irq_disable();
+	__asm__("sleep");
+	for (;;)
+		;
+}
+
+void machine_power_off(void)
+{
+	local_irq_disable();
+	__asm__("sleep");
+	for (;;)
+		;
+}
+
+void show_regs(struct pt_regs *regs)
+{
+	show_regs_print_info(KERN_DEFAULT);
+
+	pr_notice("\n");
+	pr_notice("PC: %08lx  Status: %02x\n",
+	       regs->pc, regs->ccr);
+	pr_notice("ORIG_ER0: %08lx ER0: %08lx ER1: %08lx\n",
+	       regs->orig_er0, regs->er0, regs->er1);
+	pr_notice("ER2: %08lx ER3: %08lx ER4: %08lx ER5: %08lx\n",
+	       regs->er2, regs->er3, regs->er4, regs->er5);
+	pr_notice("ER6' %08lx ", regs->er6);
+	if (user_mode(regs))
+		printk("USP: %08lx\n", rdusp());
+	else
+		printk("\n");
+}
+
+void flush_thread(void)
+{
+}
+
+int copy_thread(unsigned long clone_flags,
+		unsigned long usp, unsigned long topstk,
+		struct task_struct *p)
+{
+	struct pt_regs *childregs;
+
+	childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1;
+
+	if (unlikely(p->flags & PF_KTHREAD)) {
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->retpc = (unsigned long) ret_from_kernel_thread;
+		childregs->er4 = topstk; /* arg */
+		childregs->er5 = usp; /* fn */
+	}  else {
+		*childregs = *current_pt_regs();
+		childregs->er0 = 0;
+		childregs->retpc = (unsigned long) ret_from_fork;
+		p->thread.usp = usp ?: rdusp();
+	}
+	p->thread.ksp = (unsigned long)childregs;
+
+	return 0;
+}
+
+unsigned long thread_saved_pc(struct task_struct *tsk)
+{
+	return ((struct pt_regs *)tsk->thread.esp0)->pc;
+}
+
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long fp, pc;
+	unsigned long stack_page;
+	int count = 0;
+
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
+
+	stack_page = (unsigned long)p;
+	fp = ((struct pt_regs *)p->thread.ksp)->er6;
+	do {
+		if (fp < stack_page+sizeof(struct thread_info) ||
+		    fp >= 8184+stack_page)
+			return 0;
+		pc = ((unsigned long *)fp)[1];
+		if (!in_sched_functions(pc))
+			return pc;
+		fp = *(unsigned long *) fp;
+	} while (count++ < 16);
+	return 0;
+}
+
+/* generic sys_clone is not enough registers */
+asmlinkage int sys_clone(unsigned long __user *args)
+{
+	unsigned long clone_flags;
+	unsigned long  newsp;
+	uintptr_t parent_tidptr;
+	uintptr_t child_tidptr;
+
+	get_user(clone_flags, &args[0]);
+	get_user(newsp, &args[1]);
+	get_user(parent_tidptr, &args[2]);
+	get_user(child_tidptr, &args[3]);
+	return do_fork(clone_flags, newsp, 0,
+		       (int __user *)parent_tidptr, (int __user *)child_tidptr);
+}
diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c
new file mode 100644
index 000000000000..92075544a19a
--- /dev/null
+++ b/arch/h8300/kernel/ptrace.c
@@ -0,0 +1,203 @@
+/*
+ *  linux/arch/h8300/kernel/ptrace.c
+ *
+ *  Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License.  See the file COPYING in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/audit.h>
+#include <linux/tracehook.h>
+#include <linux/regset.h>
+#include <linux/elf.h>
+
+#define CCR_MASK 0x6f    /* mode/imask not set */
+#define EXR_MASK 0x80    /* modify only T */
+
+#define PT_REG(r) offsetof(struct pt_regs, r)
+
+extern void user_disable_single_step(struct task_struct *child);
+
+/* Mapping from PT_xxx to the stack offset at which the register is
+   saved.  Notice that usp has no stack-slot and needs to be treated
+   specially (see get_reg/put_reg below). */
+static const int register_offset[] = {
+	PT_REG(er1), PT_REG(er2), PT_REG(er3), PT_REG(er4),
+	PT_REG(er5), PT_REG(er6), PT_REG(er0), -1,
+	PT_REG(orig_er0), PT_REG(ccr), PT_REG(pc),
+#if defined(CONFIG_CPU_H8S)
+	PT_REG(exr),
+#endif
+};
+
+/* read register */
+long h8300_get_reg(struct task_struct *task, int regno)
+{
+	switch (regno) {
+	case PT_USP:
+		return task->thread.usp + sizeof(long)*2;
+	case PT_CCR:
+	case PT_EXR:
+	    return *(unsigned short *)(task->thread.esp0 +
+				       register_offset[regno]);
+	default:
+	    return *(unsigned long *)(task->thread.esp0 +
+				      register_offset[regno]);
+	}
+}
+
+int h8300_put_reg(struct task_struct *task, int regno, unsigned long data)
+{
+	unsigned short oldccr;
+	unsigned short oldexr;
+
+	switch (regno) {
+	case PT_USP:
+		task->thread.usp = data - sizeof(long)*2;
+	case PT_CCR:
+		oldccr = *(unsigned short *)(task->thread.esp0 +
+					     register_offset[regno]);
+		oldccr &= ~CCR_MASK;
+		data &= CCR_MASK;
+		data |= oldccr;
+		*(unsigned short *)(task->thread.esp0 +
+				    register_offset[regno]) = data;
+		break;
+	case PT_EXR:
+		oldexr = *(unsigned short *)(task->thread.esp0 +
+					     register_offset[regno]);
+		oldccr &= ~EXR_MASK;
+		data &= EXR_MASK;
+		data |= oldexr;
+		*(unsigned short *)(task->thread.esp0 +
+				    register_offset[regno]) = data;
+		break;
+	default:
+		*(unsigned long *)(task->thread.esp0 +
+				   register_offset[regno]) = data;
+		break;
+	}
+	return 0;
+}
+
+static int regs_get(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    void *kbuf, void __user *ubuf)
+{
+	int r;
+	struct user_regs_struct regs;
+	long *reg = (long *)&regs;
+
+	/* build user regs in buffer */
+	for (r = 0; r < ARRAY_SIZE(register_offset); r++)
+		*reg++ = h8300_get_reg(target, r);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &regs, 0, sizeof(regs));
+}
+
+static int regs_set(struct task_struct *target,
+		    const struct user_regset *regset,
+		    unsigned int pos, unsigned int count,
+		    const void *kbuf, const void __user *ubuf)
+{
+	int r;
+	int ret;
+	struct user_regs_struct regs;
+	long *reg;
+
+	/* build user regs in buffer */
+	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+		*reg++ = h8300_get_reg(target, r);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &regs, 0, sizeof(regs));
+	if (ret)
+		return ret;
+
+	/* write back to pt_regs */
+	for (reg = (long *)&regs, r = 0; r < ARRAY_SIZE(register_offset); r++)
+		h8300_put_reg(target, r, *reg++);
+	return 0;
+}
+
+enum h8300_regset {
+	REGSET_GENERAL,
+};
+
+static const struct user_regset h8300_regsets[] = {
+	[REGSET_GENERAL] = {
+		.core_note_type	= NT_PRSTATUS,
+		.n		= ELF_NGREG,
+		.size		= sizeof(long),
+		.align		= sizeof(long),
+		.get		= regs_get,
+		.set		= regs_set,
+	},
+};
+
+static const struct user_regset_view user_h8300_native_view = {
+	.name = "h8300",
+	.e_machine = EM_H8_300,
+	.regsets = h8300_regsets,
+	.n = ARRAY_SIZE(h8300_regsets),
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	return &user_h8300_native_view;
+}
+
+void ptrace_disable(struct task_struct *child)
+{
+	user_disable_single_step(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	int ret;
+
+	switch (request) {
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+	return ret;
+}
+
+asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
+{
+	long ret = 0;
+
+	if (test_thread_flag(TIF_SYSCALL_TRACE) &&
+	    tracehook_report_syscall_entry(regs))
+		/*
+		 * Tracing decided this syscall should not happen.
+		 * We'll return a bogus call number to get an ENOSYS
+		 * error, but leave the original number in regs->regs[0].
+		 */
+		ret = -1L;
+
+	audit_syscall_entry(regs->er1, regs->er2, regs->er3,
+			    regs->er4, regs->er5);
+
+	return ret ?: regs->er0;
+}
+
+asmlinkage void do_syscall_trace_leave(struct pt_regs *regs)
+{
+	int step;
+
+	audit_syscall_exit(regs);
+
+	step = test_thread_flag(TIF_SINGLESTEP);
+	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, step);
+}
diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c
new file mode 100644
index 000000000000..fe3b5673baba
--- /dev/null
+++ b/arch/h8300/kernel/ptrace_h.c
@@ -0,0 +1,256 @@
+/*
+ *    ptrace cpu depend helper functions
+ *
+ *  Copyright 2003, 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License.  See the file COPYING in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/linkage.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+
+#define BREAKINST 0x5730 /* trapa #3 */
+
+/* disable singlestep */
+void user_disable_single_step(struct task_struct *child)
+{
+	if ((long)child->thread.breakinfo.addr != -1L) {
+		*(child->thread.breakinfo.addr) = child->thread.breakinfo.inst;
+		child->thread.breakinfo.addr = (unsigned short *)-1L;
+	}
+}
+
+/* calculate next pc */
+enum jump_type {none,	 /* normal instruction */
+		jabs,	 /* absolute address jump */
+		ind,	 /* indirect address jump */
+		ret,	 /* return to subrutine */
+		reg,	 /* register indexed jump */
+		relb,	 /* pc relative jump (byte offset) */
+		relw,	 /* pc relative jump (word offset) */
+	       };
+
+/* opcode decode table define
+   ptn: opcode pattern
+   msk: opcode bitmask
+   len: instruction length (<0 next table index)
+   jmp: jump operation mode */
+struct optable {
+	unsigned char bitpattern;
+	unsigned char bitmask;
+	signed char length;
+	signed char type;
+} __packed __aligned(1);
+
+#define OPTABLE(ptn, msk, len, jmp)	\
+	{				\
+		.bitpattern = ptn,	\
+		.bitmask    = msk,	\
+		.length	    = len,	\
+		.type	    = jmp,	\
+	}
+
+static const struct optable optable_0[] = {
+	OPTABLE(0x00, 0xff,  1, none), /* 0x00 */
+	OPTABLE(0x01, 0xff, -1, none), /* 0x01 */
+	OPTABLE(0x02, 0xfe,  1, none), /* 0x02-0x03 */
+	OPTABLE(0x04, 0xee,  1, none), /* 0x04-0x05/0x14-0x15 */
+	OPTABLE(0x06, 0xfe,  1, none), /* 0x06-0x07 */
+	OPTABLE(0x08, 0xea,  1, none), /* 0x08-0x09/0x0c-0x0d/0x18-0x19/0x1c-0x1d */
+	OPTABLE(0x0a, 0xee,  1, none), /* 0x0a-0x0b/0x1a-0x1b */
+	OPTABLE(0x0e, 0xee,  1, none), /* 0x0e-0x0f/0x1e-0x1f */
+	OPTABLE(0x10, 0xfc,  1, none), /* 0x10-0x13 */
+	OPTABLE(0x16, 0xfe,  1, none), /* 0x16-0x17 */
+	OPTABLE(0x20, 0xe0,  1, none), /* 0x20-0x3f */
+	OPTABLE(0x40, 0xf0,  1, relb), /* 0x40-0x4f */
+	OPTABLE(0x50, 0xfc,  1, none), /* 0x50-0x53 */
+	OPTABLE(0x54, 0xfd,  1, ret), /* 0x54/0x56 */
+	OPTABLE(0x55, 0xff,  1, relb), /* 0x55 */
+	OPTABLE(0x57, 0xff,  1, none), /* 0x57 */
+	OPTABLE(0x58, 0xfb,  2, relw), /* 0x58/0x5c */
+	OPTABLE(0x59, 0xfb,  1, reg), /* 0x59/0x5b */
+	OPTABLE(0x5a, 0xfb,  2, jabs), /* 0x5a/0x5e */
+	OPTABLE(0x5b, 0xfb,  2, ind), /* 0x5b/0x5f */
+	OPTABLE(0x60, 0xe8,  1, none), /* 0x60-0x67/0x70-0x77 */
+	OPTABLE(0x68, 0xfa,  1, none), /* 0x68-0x69/0x6c-0x6d */
+	OPTABLE(0x6a, 0xfe, -2, none), /* 0x6a-0x6b */
+	OPTABLE(0x6e, 0xfe,  2, none), /* 0x6e-0x6f */
+	OPTABLE(0x78, 0xff,  4, none), /* 0x78 */
+	OPTABLE(0x79, 0xff,  2, none), /* 0x79 */
+	OPTABLE(0x7a, 0xff,  3, none), /* 0x7a */
+	OPTABLE(0x7b, 0xff,  2, none), /* 0x7b */
+	OPTABLE(0x7c, 0xfc,  2, none), /* 0x7c-0x7f */
+	OPTABLE(0x80, 0x80,  1, none), /* 0x80-0xff */
+};
+
+static const struct optable optable_1[] = {
+	OPTABLE(0x00, 0xff, -3, none), /* 0x0100 */
+	OPTABLE(0x40, 0xf0, -3, none), /* 0x0140-0x14f */
+	OPTABLE(0x80, 0xf0,  1, none), /* 0x0180-0x018f */
+	OPTABLE(0xc0, 0xc0,  2, none), /* 0x01c0-0x01ff */
+};
+
+static const struct optable optable_2[] = {
+	OPTABLE(0x00, 0x20,  2, none), /* 0x6a0?/0x6a8?/0x6b0?/0x6b8? */
+	OPTABLE(0x20, 0x20,  3, none), /* 0x6a2?/0x6aa?/0x6b2?/0x6ba? */
+};
+
+static const struct optable optable_3[] = {
+	OPTABLE(0x69, 0xfb,  2, none), /* 0x010069/0x01006d/014069/0x01406d */
+	OPTABLE(0x6b, 0xff, -4, none), /* 0x01006b/0x01406b */
+	OPTABLE(0x6f, 0xff,  3, none), /* 0x01006f/0x01406f */
+	OPTABLE(0x78, 0xff,  5, none), /* 0x010078/0x014078 */
+};
+
+static const struct optable optable_4[] = {
+/* 0x0100690?/0x01006d0?/0140690?/0x01406d0?/
+   0x0100698?/0x01006d8?/0140698?/0x01406d8? */
+	OPTABLE(0x00, 0x78, 3, none),
+/* 0x0100692?/0x01006d2?/0140692?/0x01406d2?/
+   0x010069a?/0x01006da?/014069a?/0x01406da? */
+	OPTABLE(0x20, 0x78, 4, none),
+};
+
+static const struct optables_list {
+	const struct optable *ptr;
+	int size;
+} optables[] = {
+#define OPTABLES(no)                                                   \
+	{                                                              \
+		.ptr  = optable_##no,                                  \
+		.size = sizeof(optable_##no) / sizeof(struct optable), \
+	}
+	OPTABLES(0),
+	OPTABLES(1),
+	OPTABLES(2),
+	OPTABLES(3),
+	OPTABLES(4),
+
+};
+
+const unsigned char condmask[] = {
+	0x00, 0x40, 0x01, 0x04, 0x02, 0x08, 0x10, 0x20
+};
+
+static int isbranch(struct task_struct *task, int reson)
+{
+	unsigned char cond = h8300_get_reg(task, PT_CCR);
+
+	/* encode complex conditions */
+	/* B4: N^V
+	   B5: Z|(N^V)
+	   B6: C|Z */
+	__asm__("bld #3,%w0\n\t"
+		"bxor #1,%w0\n\t"
+		"bst #4,%w0\n\t"
+		"bor #2,%w0\n\t"
+		"bst #5,%w0\n\t"
+		"bld #2,%w0\n\t"
+		"bor #0,%w0\n\t"
+		"bst #6,%w0\n\t"
+		: "=&r"(cond) : "0"(cond) : "cc");
+	cond &= condmask[reson >> 1];
+	if (!(reson & 1))
+		return cond == 0;
+	else
+		return cond != 0;
+}
+
+static unsigned short *decode(struct task_struct *child,
+			      const struct optable *op,
+			      char *fetch_p, unsigned short *pc,
+			      unsigned char inst)
+{
+	unsigned long addr;
+	unsigned long *sp;
+	int regno;
+
+	switch (op->type) {
+	case none:
+		return (unsigned short *)pc + op->length;
+	case jabs:
+		addr = *(unsigned long *)pc;
+		return (unsigned short *)(addr & 0x00ffffff);
+	case ind:
+		addr = *pc & 0xff;
+		return (unsigned short *)(*(unsigned long *)addr);
+	case ret:
+		sp = (unsigned long *)h8300_get_reg(child, PT_USP);
+		/* user stack frames
+		   |   er0  | temporary saved
+		   +--------+
+		   |   exp  | exception stack frames
+		   +--------+
+		   | ret pc | userspace return address
+		*/
+		return (unsigned short *)(*(sp+2) & 0x00ffffff);
+	case reg:
+		regno = (*pc >> 4) & 0x07;
+		if (regno == 0)
+			addr = h8300_get_reg(child, PT_ER0);
+		else
+			addr = h8300_get_reg(child, regno-1 + PT_ER1);
+		return (unsigned short *)addr;
+	case relb:
+		if (inst == 0x55 || isbranch(child, inst & 0x0f))
+			pc = (unsigned short *)((unsigned long)pc +
+						((signed char)(*fetch_p)));
+		return pc+1; /* skip myself */
+	case relw:
+		if (inst == 0x5c || isbranch(child, (*fetch_p & 0xf0) >> 4))
+			pc = (unsigned short *)((unsigned long)pc +
+						((signed short)(*(pc+1))));
+		return pc+2; /* skip myself */
+	default:
+		return NULL;
+	}
+}
+
+static unsigned short *nextpc(struct task_struct *child, unsigned short *pc)
+{
+	const struct optable *op;
+	unsigned char *fetch_p;
+	int op_len;
+	unsigned char inst;
+
+	op = optables[0].ptr;
+	op_len = optables[0].size;
+	fetch_p = (unsigned char *)pc;
+	inst = *fetch_p++;
+	do {
+		if ((inst & op->bitmask) == op->bitpattern) {
+			if (op->length < 0) {
+				op = optables[-op->length].ptr;
+				op_len = optables[-op->length].size + 1;
+				inst = *fetch_p++;
+			} else
+				return decode(child, op, fetch_p, pc, inst);
+		} else
+			op++;
+	} while (--op_len > 0);
+	return NULL;
+}
+
+/* Set breakpoint(s) to simulate a single step from the current PC.  */
+
+void user_enable_single_step(struct task_struct *child)
+{
+	unsigned short *next;
+
+	next = nextpc(child, (unsigned short *)h8300_get_reg(child, PT_PC));
+	child->thread.breakinfo.addr = next;
+	child->thread.breakinfo.inst = *next;
+	*next = BREAKINST;
+}
+
+asmlinkage void trace_trap(unsigned long bp)
+{
+	if ((unsigned long)current->thread.breakinfo.addr == bp) {
+		user_disable_single_step(current);
+		force_sig(SIGTRAP, current);
+	} else
+		force_sig(SIGILL, current);
+}
diff --git a/arch/h8300/kernel/ptrace_s.c b/arch/h8300/kernel/ptrace_s.c
new file mode 100644
index 000000000000..ef5a9c13e76d
--- /dev/null
+++ b/arch/h8300/kernel/ptrace_s.c
@@ -0,0 +1,44 @@
+/*
+ *  linux/arch/h8300/kernel/ptrace_h8s.c
+ *    ptrace cpu depend helper functions
+ *
+ *  Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License.  See the file COPYING in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/linkage.h>
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <asm/ptrace.h>
+
+#define CCR_MASK  0x6f
+#define EXR_TRACE 0x80
+
+/* disable singlestep */
+void user_disable_single_step(struct task_struct *child)
+{
+	unsigned char exr;
+
+	exr = h8300_get_reg(child, PT_EXR);
+	exr &= ~EXR_TRACE;
+	h8300_put_reg(child, PT_EXR, exr);
+}
+
+/* enable singlestep */
+void user_enable_single_step(struct task_struct *child)
+{
+	unsigned char exr;
+
+	exr = h8300_get_reg(child, PT_EXR);
+	exr |= EXR_TRACE;
+	h8300_put_reg(child, PT_EXR, exr);
+}
+
+asmlinkage void trace_trap(unsigned long bp)
+{
+	(void)bp;
+	force_sig(SIGTRAP, current);
+}
diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c
new file mode 100644
index 000000000000..0fd1fe65c0b8
--- /dev/null
+++ b/arch/h8300/kernel/setup.c
@@ -0,0 +1,255 @@
+/*
+ *  linux/arch/h8300/kernel/setup.c
+ *
+ *  Copyright (C) 2001-2014 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+/*
+ * This file handles the architecture-dependent parts of system setup
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/console.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/clk-provider.h>
+#include <linux/memblock.h>
+#include <linux/screen_info.h>
+
+#include <asm/setup.h>
+#include <asm/irq.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
+#include <asm/page.h>
+
+#if defined(CONFIG_CPU_H8300H)
+#define CPU "H8/300H"
+#elif defined(CONFIG_CPU_H8S)
+#define CPU "H8S"
+#else
+#define CPU "Unknown"
+#endif
+
+unsigned long memory_start;
+unsigned long memory_end;
+EXPORT_SYMBOL(memory_end);
+static unsigned long freq;
+extern char __dtb_start[];
+
+#ifdef CONFIG_VT
+struct screen_info screen_info;
+#endif
+
+char __initdata command_line[COMMAND_LINE_SIZE];
+
+void sim_console_register(void);
+
+void __init h8300_fdt_init(void *fdt, char *bootargs)
+{
+	if (!fdt)
+		fdt = __dtb_start;
+	else
+		strcpy(command_line, bootargs);
+
+	early_init_dt_scan(fdt);
+	memblock_allow_resize();
+}
+
+static void __init bootmem_init(void)
+{
+	int bootmap_size;
+	unsigned long ram_start_pfn;
+	unsigned long free_ram_start_pfn;
+	unsigned long ram_end_pfn;
+	struct memblock_region *region;
+
+	memory_end = memory_start = 0;
+
+	/* Find main memory where is the kernel */
+	for_each_memblock(memory, region) {
+		memory_start = region->base;
+		memory_end = region->base + region->size;
+	}
+
+	if (!memory_end)
+		panic("No memory!");
+
+	ram_start_pfn = PFN_UP(memory_start);
+	/* free_ram_start_pfn is first page after kernel */
+	free_ram_start_pfn = PFN_UP(__pa(_end));
+	ram_end_pfn = PFN_DOWN(memblock_end_of_DRAM());
+
+	max_pfn = ram_end_pfn;
+
+	/*
+	 * give all the memory to the bootmap allocator,  tell it to put the
+	 * boot mem_map at the start of memory
+	 */
+	bootmap_size = init_bootmem_node(NODE_DATA(0),
+					 free_ram_start_pfn,
+					 0,
+					 ram_end_pfn);
+	/*
+	 * free the usable memory,  we have to make sure we do not free
+	 * the bootmem bitmap so we then reserve it after freeing it :-)
+	 */
+	free_bootmem(PFN_PHYS(free_ram_start_pfn),
+		     (ram_end_pfn - free_ram_start_pfn) << PAGE_SHIFT);
+	reserve_bootmem(PFN_PHYS(free_ram_start_pfn), bootmap_size,
+			BOOTMEM_DEFAULT);
+
+	for_each_memblock(reserved, region) {
+		reserve_bootmem(region->base, region->size, BOOTMEM_DEFAULT);
+	}
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	unflatten_and_copy_device_tree();
+
+	init_mm.start_code = (unsigned long) _stext;
+	init_mm.end_code = (unsigned long) _etext;
+	init_mm.end_data = (unsigned long) _edata;
+	init_mm.brk = (unsigned long) 0;
+
+	pr_notice("\r\n\nuClinux " CPU "\n");
+	pr_notice("Flat model support (C) 1998,1999 Kenneth Albanowski, D. Jeff Dionne\n");
+
+	if (*command_line)
+		strcpy(boot_command_line, command_line);
+	*cmdline_p = boot_command_line;
+
+	parse_early_param();
+
+	bootmem_init();
+#if defined(CONFIG_H8300H_SIM) || defined(CONFIG_H8S_SIM)
+	sim_console_register();
+#endif
+
+	early_platform_driver_probe("earlyprintk", 1, 0);
+	/*
+	 * get kmalloc into gear
+	 */
+	paging_init();
+}
+
+/*
+ *	Get CPU information for use by the procfs.
+ */
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	char *cpu;
+
+	cpu = CPU;
+
+	seq_printf(m,  "CPU:\t\t%s\n"
+		   "Clock:\t\t%lu.%1luMHz\n"
+		   "BogoMips:\t%lu.%02lu\n"
+		   "Calibration:\t%lu loops\n",
+		   cpu,
+		   freq/1000, freq%1000,
+		   (loops_per_jiffy*HZ)/500000,
+		   ((loops_per_jiffy*HZ)/5000)%100,
+		   (loops_per_jiffy*HZ));
+
+	return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	return *pos < num_possible_cpus() ?
+		((void *) 0x12345678) : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo,
+};
+
+static int __init device_probe(void)
+{
+	of_platform_populate(NULL, NULL, NULL, NULL);
+
+	return 0;
+}
+
+device_initcall(device_probe);
+
+#if defined(CONFIG_CPU_H8300H)
+#define get_wait(base, addr) ({		\
+	int baddr;			\
+	baddr = ((addr) / 0x200000 * 2);			     \
+	w *= (ctrl_inw((unsigned long)(base) + 2) & (3 << baddr)) + 1;	\
+	})
+#endif
+#if defined(CONFIG_CPU_H8S)
+#define get_wait(base, addr) ({		\
+	int baddr;			\
+	baddr = ((addr) / 0x200000 * 16);			     \
+	w *= (ctrl_inl((unsigned long)(base) + 2) & (7 << baddr)) + 1;	\
+	})
+#endif
+
+static __init int access_timing(void)
+{
+	struct device_node *bsc;
+	void __iomem *base;
+	unsigned long addr = (unsigned long)&__delay;
+	int bit = 1 << (addr / 0x200000);
+	int w;
+
+	bsc = of_find_compatible_node(NULL, NULL, "renesas,h8300-bsc");
+	base = of_iomap(bsc, 0);
+	w = (ctrl_inb((unsigned long)base + 0) & bit)?2:1;
+	if (ctrl_inb((unsigned long)base + 1) & bit)
+		w *= get_wait(base, addr);
+	else
+		w *= 2;
+	return w * 3 / 2;
+}
+
+void __init calibrate_delay(void)
+{
+	struct device_node *cpu;
+	int freq;
+
+	cpu = of_find_compatible_node(NULL, NULL, "renesas,h8300");
+	of_property_read_s32(cpu, "clock-frequency", &freq);
+	loops_per_jiffy = freq / HZ / (access_timing() * 2);
+	pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",
+		loops_per_jiffy / (500000 / HZ),
+		(loops_per_jiffy / (5000 / HZ)) % 100, loops_per_jiffy);
+}
+
+
+void __init time_init(void)
+{
+	of_clk_init(NULL);
+}
diff --git a/arch/h8300/kernel/signal.c b/arch/h8300/kernel/signal.c
new file mode 100644
index 000000000000..380fffd081b2
--- /dev/null
+++ b/arch/h8300/kernel/signal.c
@@ -0,0 +1,289 @@
+/*
+ *  linux/arch/h8300/kernel/signal.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+/*
+ * uClinux H8/300 support by Yoshinori Sato <ysato@users.sourceforge.jp>
+ *                and David McCullough <davidm@snapgear.com>
+ *
+ * Based on
+ * Linux/m68k by Hamish Macdonald
+ */
+
+/*
+ * ++roman (07/09/96): implemented signal stacks (specially for tosemu on
+ * Atari :-) Current limitation: Only one sigstack can be active at one time.
+ * If a second signal with SA_ONSTACK set arrives while working on a sigstack,
+ * SA_ONSTACK is ignored. This behaviour avoids lots of trouble with nested
+ * signal handlers!
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/syscalls.h>
+#include <linux/errno.h>
+#include <linux/wait.h>
+#include <linux/ptrace.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/highuid.h>
+#include <linux/personality.h>
+#include <linux/tty.h>
+#include <linux/binfmts.h>
+#include <linux/tracehook.h>
+
+#include <asm/setup.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/traps.h>
+#include <asm/ucontext.h>
+
+/*
+ * Do a signal return; undo the signal stack.
+ *
+ * Keep the return code on the stack quadword aligned!
+ * That makes the cache flush below easier.
+ */
+
+struct rt_sigframe {
+	long dummy_er0;
+	long dummy_vector;
+#if defined(CONFIG_CPU_H8S)
+	short dummy_exr;
+#endif
+	long dummy_pc;
+	char *pretcode;
+	struct siginfo *pinfo;
+	void *puc;
+	unsigned char retcode[8];
+	struct siginfo info;
+	struct ucontext uc;
+	int sig;
+} __packed __aligned(2);
+
+static inline int
+restore_sigcontext(struct sigcontext *usc, int *pd0)
+{
+	struct pt_regs *regs = current_pt_regs();
+	int err = 0;
+	unsigned int ccr;
+	unsigned int usp;
+	unsigned int er0;
+
+	/* Always make any pending restarted system calls return -EINTR */
+	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+
+	/* restore passed registers */
+#define COPY(r)  do { err |= get_user(regs->r, &usc->sc_##r); } while (0)
+	COPY(er1);
+	COPY(er2);
+	COPY(er3);
+	COPY(er5);
+	COPY(pc);
+	ccr = regs->ccr & 0x10;
+	COPY(ccr);
+#undef COPY
+	regs->ccr &= 0xef;
+	regs->ccr |= ccr;
+	regs->orig_er0 = -1;		/* disable syscall checks */
+	err |= __get_user(usp, &usc->sc_usp);
+	wrusp(usp);
+
+	err |= __get_user(er0, &usc->sc_er0);
+	*pd0 = er0;
+	return err;
+}
+
+asmlinkage int sys_rt_sigreturn(void)
+{
+	unsigned long usp = rdusp();
+	struct rt_sigframe *frame = (struct rt_sigframe *)(usp - 4);
+	sigset_t set;
+	int er0;
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	set_current_blocked(&set);
+
+	if (restore_sigcontext(&frame->uc.uc_mcontext, &er0))
+		goto badframe;
+
+	if (restore_altstack(&frame->uc.uc_stack))
+		goto badframe;
+
+	return er0;
+
+badframe:
+	force_sig(SIGSEGV, current);
+	return 0;
+}
+
+static int setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
+			     unsigned long mask)
+{
+	int err = 0;
+
+	err |= __put_user(regs->er0, &sc->sc_er0);
+	err |= __put_user(regs->er1, &sc->sc_er1);
+	err |= __put_user(regs->er2, &sc->sc_er2);
+	err |= __put_user(regs->er3, &sc->sc_er3);
+	err |= __put_user(regs->er4, &sc->sc_er4);
+	err |= __put_user(regs->er5, &sc->sc_er5);
+	err |= __put_user(regs->er6, &sc->sc_er6);
+	err |= __put_user(rdusp(),   &sc->sc_usp);
+	err |= __put_user(regs->pc,  &sc->sc_pc);
+	err |= __put_user(regs->ccr, &sc->sc_ccr);
+	err |= __put_user(mask,      &sc->sc_mask);
+
+	return err;
+}
+
+static inline void __user *
+get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size)
+{
+	return (void __user *)((sigsp(rdusp(), ksig) - frame_size) & -8UL);
+}
+
+static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
+			  struct pt_regs *regs)
+{
+	struct rt_sigframe *frame;
+	int err = 0;
+	unsigned char *ret;
+
+	frame = get_sigframe(ksig, regs, sizeof(*frame));
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (ksig->ka.sa.sa_flags & SA_SIGINFO)
+		err |= copy_siginfo_to_user(&frame->info, &ksig->info);
+
+	/* Create the ucontext.  */
+	err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(0, &frame->uc.uc_link);
+	err |= __save_altstack(&frame->uc.uc_stack, rdusp());
+	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0]);
+	err |= copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+	if (err)
+		return -EFAULT;
+
+	/* Set up to return from userspace.  */
+	ret = frame->retcode;
+	if (ksig->ka.sa.sa_flags & SA_RESTORER)
+		ret = (unsigned char *)(ksig->ka.sa.sa_restorer);
+	else {
+		/* sub.l er0,er0; mov.b #__NR_rt_sigreturn,r0l; trapa #0 */
+		err |= __put_user(0x1a80f800 + (__NR_rt_sigreturn & 0xff),
+				  (unsigned long *)(frame->retcode + 0));
+		err |= __put_user(0x5700,
+				  (unsigned short *)(frame->retcode + 4));
+	}
+	err |= __put_user(ret, &frame->pretcode);
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	wrusp((unsigned long) frame);
+	regs->pc  = (unsigned long) ksig->ka.sa.sa_handler;
+	regs->er0 = ksig->sig;
+	regs->er1 = (unsigned long)&(frame->info);
+	regs->er2 = (unsigned long)&frame->uc;
+	regs->er5 = current->mm->start_data;	/* GOT base */
+
+	return 0;
+}
+
+static void
+handle_restart(struct pt_regs *regs, struct k_sigaction *ka)
+{
+	switch (regs->er0) {
+	case -ERESTARTNOHAND:
+		if (!ka)
+			goto do_restart;
+		regs->er0 = -EINTR;
+		break;
+	case -ERESTART_RESTARTBLOCK:
+		if (!ka) {
+			regs->er0 = __NR_restart_syscall;
+			regs->pc -= 2;
+		} else
+			regs->er0 = -EINTR;
+		break;
+	case -ERESTARTSYS:
+		if (!(ka->sa.sa_flags & SA_RESTART)) {
+			regs->er0 = -EINTR;
+			break;
+		}
+		/* fallthrough */
+	case -ERESTARTNOINTR:
+do_restart:
+		regs->er0 = regs->orig_er0;
+		regs->pc -= 2;
+		break;
+	}
+}
+
+/*
+ * OK, we're invoking a handler
+ */
+static void
+handle_signal(struct ksignal *ksig, struct pt_regs *regs)
+{
+	sigset_t *oldset = sigmask_to_save();
+	int ret;
+	/* are we from a system call? */
+	if (regs->orig_er0 >= 0)
+		handle_restart(regs, &ksig->ka);
+
+	ret = setup_rt_frame(ksig, oldset, regs);
+
+	signal_setup_done(ret, ksig, 0);
+}
+
+/*
+ * Note that 'init' is a special process: it doesn't get signals it doesn't
+ * want to handle. Thus you cannot kill init even with a SIGKILL even by
+ * mistake.
+ */
+static void do_signal(struct pt_regs *regs)
+{
+	struct ksignal ksig;
+
+	current->thread.esp0 = (unsigned long) regs;
+
+	if (get_signal(&ksig)) {
+		/* Whee!  Actually deliver the signal.  */
+		handle_signal(&ksig, regs);
+		return;
+	}
+	/* Did we come from a system call? */
+	if (regs->orig_er0 >= 0)
+		handle_restart(regs, NULL);
+
+	/* If there's no signal to deliver, we just restore the saved mask.  */
+	restore_saved_sigmask();
+}
+
+asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
+{
+	if (thread_info_flags & _TIF_SIGPENDING)
+		do_signal(regs);
+
+	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+	}
+}
diff --git a/arch/h8300/kernel/sim-console.c b/arch/h8300/kernel/sim-console.c
new file mode 100644
index 000000000000..a15edf0565d9
--- /dev/null
+++ b/arch/h8300/kernel/sim-console.c
@@ -0,0 +1,79 @@
+/*
+ * arch/h8300/kernel/early_printk.c
+ *
+ *  Copyright (C) 2009 Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/console.h>
+#include <linux/tty.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+
+static void sim_write(struct console *co, const char *ptr,
+				 unsigned len)
+{
+	register const int fd __asm__("er0") = 1; /* stdout */
+	register const char *_ptr __asm__("er1") = ptr;
+	register const unsigned _len __asm__("er2") = len;
+
+	__asm__(".byte 0x5e,0x00,0x00,0xc7\n\t" /* jsr @0xc7 (sys_write) */
+		: : "g"(fd), "g"(_ptr), "g"(_len));
+}
+
+static struct console sim_console = {
+	.name		= "sim_console",
+	.write		= sim_write,
+	.setup		= NULL,
+	.flags		= CON_PRINTBUFFER,
+	.index		= -1,
+};
+
+static char sim_console_buf[32];
+
+static int sim_probe(struct platform_device *pdev)
+{
+	if (sim_console.data)
+		return -EEXIST;
+
+	if (!strstr(sim_console_buf, "keep"))
+		sim_console.flags |= CON_BOOT;
+
+	register_console(&sim_console);
+	return 0;
+}
+
+static int sim_remove(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static struct platform_driver sim_driver = {
+	.probe		= sim_probe,
+	.remove		= sim_remove,
+	.driver		= {
+		.name	= "h8300-sim",
+		.owner	= THIS_MODULE,
+	},
+};
+
+early_platform_init_buffer("earlyprintk", &sim_driver,
+			   sim_console_buf, ARRAY_SIZE(sim_console_buf));
+
+static struct platform_device sim_console_device = {
+	.name		= "h8300-sim",
+	.id		= 0,
+};
+
+static struct platform_device *devices[] __initdata = {
+	&sim_console_device,
+};
+
+void __init sim_console_register(void)
+{
+	early_platform_add_devices(devices,
+				   ARRAY_SIZE(devices));
+}
diff --git a/arch/h8300/kernel/syscalls.c b/arch/h8300/kernel/syscalls.c
new file mode 100644
index 000000000000..1f9123a013d3
--- /dev/null
+++ b/arch/h8300/kernel/syscalls.c
@@ -0,0 +1,14 @@
+#include <linux/syscalls.h>
+#include <linux/signal.h>
+#include <linux/unistd.h>
+
+#undef __SYSCALL
+#define __SYSCALL(nr, call) [nr] = (call),
+
+#define sys_mmap2 sys_mmap_pgoff
+
+asmlinkage int sys_rt_sigreturn(void);
+
+void *_sys_call_table[__NR_syscalls] = {
+#include <asm/unistd.h>
+};
diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c
new file mode 100644
index 000000000000..1b2d7cdd6591
--- /dev/null
+++ b/arch/h8300/kernel/traps.c
@@ -0,0 +1,161 @@
+/*
+ * linux/arch/h8300/boot/traps.c -- general exception handling code
+ * H8/300 support Yoshinori Sato <ysato@users.sourceforge.jp>
+ *
+ * Cloned from Linux/m68k.
+ *
+ * No original Copyright holder listed,
+ * Probable original (C) Roman Zippel (assigned DJD, 1999)
+ *
+ * Copyright 1999-2000 D. Jeff Dionne, <jeff@rt-control.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/bug.h>
+
+#include <asm/irq.h>
+#include <asm/traps.h>
+#include <asm/page.h>
+
+static DEFINE_SPINLOCK(die_lock);
+
+/*
+ * this must be called very early as the kernel might
+ * use some instruction that are emulated on the 060
+ */
+
+void __init base_trap_init(void)
+{
+}
+
+void __init trap_init(void)
+{
+}
+
+asmlinkage void set_esp0(unsigned long ssp)
+{
+	current->thread.esp0 = ssp;
+}
+
+/*
+ *	Generic dumping code. Used for panic and debug.
+ */
+
+static void dump(struct pt_regs *fp)
+{
+	unsigned long	*sp;
+	unsigned char	*tp;
+	int		i;
+
+	pr_info("\nCURRENT PROCESS:\n\n");
+	pr_info("COMM=%s PID=%d\n", current->comm, current->pid);
+	if (current->mm) {
+		pr_info("TEXT=%08x-%08x DATA=%08x-%08x BSS=%08x-%08x\n",
+			(int) current->mm->start_code,
+			(int) current->mm->end_code,
+			(int) current->mm->start_data,
+			(int) current->mm->end_data,
+			(int) current->mm->end_data,
+			(int) current->mm->brk);
+		pr_info("USER-STACK=%08x  KERNEL-STACK=%08lx\n\n",
+			(int) current->mm->start_stack,
+			(int) PAGE_SIZE+(unsigned long)current);
+	}
+
+	show_regs(fp);
+	pr_info("\nCODE:");
+	tp = ((unsigned char *) fp->pc) - 0x20;
+	for (sp = (unsigned long *) tp, i = 0; (i < 0x40);  i += 4) {
+		if ((i % 0x10) == 0)
+			pr_info("\n%08x: ", (int) (tp + i));
+		pr_info("%08x ", (int) *sp++);
+	}
+	pr_info("\n");
+
+	pr_info("\nKERNEL STACK:");
+	tp = ((unsigned char *) fp) - 0x40;
+	for (sp = (unsigned long *) tp, i = 0; (i < 0xc0); i += 4) {
+		if ((i % 0x10) == 0)
+			pr_info("\n%08x: ", (int) (tp + i));
+		pr_info("%08x ", (int) *sp++);
+	}
+	pr_info("\n");
+	if (STACK_MAGIC != *(unsigned long *)((unsigned long)current+PAGE_SIZE))
+		pr_info("(Possibly corrupted stack page??)\n");
+
+	pr_info("\n\n");
+}
+
+void die(const char *str, struct pt_regs *fp, unsigned long err)
+{
+	static int diecount;
+
+	oops_enter();
+
+	console_verbose();
+	spin_lock_irq(&die_lock);
+	report_bug(fp->pc, fp);
+	pr_crit("%s: %04lx [#%d] ", str, err & 0xffff, ++diecount);
+	dump(fp);
+
+	spin_unlock_irq(&die_lock);
+	do_exit(SIGSEGV);
+}
+
+static int kstack_depth_to_print = 24;
+
+void show_stack(struct task_struct *task, unsigned long *esp)
+{
+	unsigned long *stack,  addr;
+	int i;
+
+	if (esp == NULL)
+		esp = (unsigned long *) &esp;
+
+	stack = esp;
+
+	pr_info("Stack from %08lx:", (unsigned long)stack);
+	for (i = 0; i < kstack_depth_to_print; i++) {
+		if (((unsigned long)stack & (THREAD_SIZE - 1)) == 0)
+			break;
+		if (i % 8 == 0)
+			pr_info("\n       ");
+		pr_info(" %08lx", *stack++);
+	}
+
+	pr_info("\nCall Trace:");
+	i = 0;
+	stack = esp;
+	while (((unsigned long)stack & (THREAD_SIZE - 1)) != 0) {
+		addr = *stack++;
+		/*
+		 * If the address is either in the text segment of the
+		 * kernel, or in the region which contains vmalloc'ed
+		 * memory, it *may* be the address of a calling
+		 * routine; if so, print it so that someone tracing
+		 * down the cause of the crash will be able to figure
+		 * out the call path that was taken.
+		 */
+		if (check_kernel_text(addr)) {
+			if (i % 4 == 0)
+				pr_info("\n       ");
+			pr_info(" [<%08lx>]", addr);
+			i++;
+		}
+	}
+	pr_info("\n");
+}
+
+void show_trace_task(struct task_struct *tsk)
+{
+	show_stack(tsk, (unsigned long *)tsk->thread.esp0);
+}
diff --git a/arch/h8300/kernel/vmlinux.lds.S b/arch/h8300/kernel/vmlinux.lds.S
new file mode 100644
index 000000000000..7c302dcf5249
--- /dev/null
+++ b/arch/h8300/kernel/vmlinux.lds.S
@@ -0,0 +1,67 @@
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/page.h>
+
+#define ROMTOP 0x000000
+#define RAMTOP 0x400000
+
+jiffies = jiffies_64 + 4;
+
+ENTRY(_start)
+
+SECTIONS
+{
+#if defined(CONFIG_ROMKERNEL)
+	. = ROMTOP;
+	.vectors :
+	{
+	_vector = . ;
+		*(.vector*)
+	}
+#else
+	. = RAMTOP;
+	_ramstart = .;
+	. = . + CONFIG_OFFSET;
+#endif
+	_text = .;
+	HEAD_TEXT_SECTION
+	.text : {
+	_stext = . ;
+		TEXT_TEXT
+		SCHED_TEXT
+		LOCK_TEXT
+#if defined(CONFIG_ROMKERNEL)
+		*(.int_redirect)
+#endif
+	_etext = . ;
+	}
+	EXCEPTION_TABLE(16)
+	NOTES
+	RO_DATA_SECTION(4)
+	ROMEND = .;
+#if defined(CONFIG_ROMKERNEL)
+	. = RAMTOP;
+	_ramstart = .;
+#define ADDR(x) ROMEND
+#else
+#endif
+	_sdata = . ;
+	__data_start = . ;
+	RW_DATA_SECTION(0,0,0)
+#if defined(CONFIG_ROMKERNEL)
+#undef ADDR
+#endif
+	. = ALIGN(0x4) ;
+	__init_begin = .;
+	INIT_TEXT_SECTION(4)
+	INIT_DATA_SECTION(4)
+	SECURITY_INIT
+	__init_end = .;
+	_edata = . ;
+	_begin_data = LOADADDR(.data);
+	_sbss =.;
+	BSS_SECTION(0, 0 ,0)
+	_ebss =.;
+	_ramend = .;
+	_end = .;
+	DISCARDS
+}
diff --git a/arch/h8300/lib/Makefile b/arch/h8300/lib/Makefile
new file mode 100644
index 000000000000..28ff560d825f
--- /dev/null
+++ b/arch/h8300/lib/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for H8/300-specific library files..
+#
+
+lib-y  = memcpy.o memset.o abs.o strncpy.o \
+	 mulsi3.o udivsi3.o muldi3.o moddivsi3.o \
+	 ashldi3.o lshrdi3.o ashrdi3.o ucmpdi2.o \
+	 delay.o
diff --git a/arch/h8300/lib/abs.S b/arch/h8300/lib/abs.S
new file mode 100644
index 000000000000..efda749db03e
--- /dev/null
+++ b/arch/h8300/lib/abs.S
@@ -0,0 +1,20 @@
+;;; abs.S
+
+#include <asm/linkage.h>
+
+#if defined(CONFIG_CPU_H8300H)
+	.h8300h
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.h8300s
+#endif
+	.text
+.global _abs
+
+;;; int abs(int n)
+_abs:
+	mov.l	er0,er0
+	bpl	1f
+	neg.l	er0
+1:
+	rts
diff --git a/arch/h8300/lib/ashldi3.c b/arch/h8300/lib/ashldi3.c
new file mode 100644
index 000000000000..c6aa8ea5f4be
--- /dev/null
+++ b/arch/h8300/lib/ashldi3.c
@@ -0,0 +1,24 @@
+#include "libgcc.h"
+
+DWtype
+__ashldi3(DWtype u, word_type b)
+{
+	const DWunion uu = {.ll = u};
+	const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+	DWunion w;
+
+	if (b == 0)
+		return u;
+
+	if (bm <= 0) {
+		w.s.low = 0;
+		w.s.high = (UWtype) uu.s.low << -bm;
+	} else {
+		const UWtype carries = (UWtype) uu.s.low >> bm;
+
+		w.s.low = (UWtype) uu.s.low << b;
+		w.s.high = ((UWtype) uu.s.high << b) | carries;
+	}
+
+	return w.ll;
+}
diff --git a/arch/h8300/lib/ashrdi3.c b/arch/h8300/lib/ashrdi3.c
new file mode 100644
index 000000000000..070adf96d3b6
--- /dev/null
+++ b/arch/h8300/lib/ashrdi3.c
@@ -0,0 +1,24 @@
+#include "libgcc.h"
+
+DWtype __ashrdi3(DWtype u, word_type b)
+{
+	const DWunion uu = {.ll = u};
+	const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+	DWunion w;
+
+	if (b == 0)
+		return u;
+
+	if (bm <= 0) {
+		/* w.s.high = 1..1 or 0..0 */
+		w.s.high = uu.s.high >> (sizeof (Wtype) * BITS_PER_UNIT - 1);
+		w.s.low = uu.s.high >> -bm;
+	} else {
+		const UWtype carries = (UWtype) uu.s.high << bm;
+
+		w.s.high = uu.s.high >> b;
+		w.s.low = ((UWtype) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
+}
diff --git a/arch/h8300/lib/delay.c b/arch/h8300/lib/delay.c
new file mode 100644
index 000000000000..463f6b3afb52
--- /dev/null
+++ b/arch/h8300/lib/delay.c
@@ -0,0 +1,40 @@
+/*
+ * delay loops
+ *
+ * Copyright (C) 2015 Yoshinori Sato
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <asm/param.h>
+#include <asm/processor.h>
+#include <asm/timex.h>
+
+void __delay(unsigned long cycles)
+{
+	__asm__ volatile ("1: dec.l #1,%0\n\t"
+			  "bne 1b":"=r"(cycles):"0"(cycles));
+}
+EXPORT_SYMBOL(__delay);
+
+void __const_udelay(unsigned long xloops)
+{
+	u64 loops;
+
+	loops = (u64)xloops * loops_per_jiffy * HZ;
+
+	__delay(loops >> 32);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+	__const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+	__const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/h8300/lib/libgcc.h b/arch/h8300/lib/libgcc.h
new file mode 100644
index 000000000000..468a8f78197a
--- /dev/null
+++ b/arch/h8300/lib/libgcc.h
@@ -0,0 +1,77 @@
+#ifndef __H8300_LIBGCC_H__
+#define __H8300_LIBGCC_H__
+
+#ifdef __ASSEMBLY__
+#define A0 r0
+#define A0L r0l
+#define A0H r0h
+
+#define A1 r1
+#define A1L r1l
+#define A1H r1h
+
+#define A2 r2
+#define A2L r2l
+#define A2H r2h
+
+#define A3 r3
+#define A3L r3l
+#define A3H r3h
+
+#define S0 r4
+#define S0L r4l
+#define S0H r4h
+
+#define S1 r5
+#define S1L r5l
+#define S1H r5h
+
+#define S2 r6
+#define S2L r6l
+#define S2H r6h
+
+#define PUSHP	push.l
+#define POPP	pop.l
+
+#define A0P	er0
+#define A1P	er1
+#define A2P	er2
+#define A3P	er3
+#define S0P	er4
+#define S1P	er5
+#define S2P	er6
+
+#define A0E	e0
+#define A1E	e1
+#define A2E	e2
+#define A3E	e3
+#else
+#define Wtype   SItype
+#define UWtype  USItype
+#define HWtype  SItype
+#define UHWtype USItype
+#define DWtype  DItype
+#define UDWtype UDItype
+#define UWtype  USItype
+#define Wtype   SItype
+#define UWtype  USItype
+#define W_TYPE_SIZE (4 * BITS_PER_UNIT)
+#define BITS_PER_UNIT (8)
+
+typedef          int SItype     __attribute__ ((mode (SI)));
+typedef unsigned int USItype    __attribute__ ((mode (SI)));
+typedef		 int DItype	__attribute__ ((mode (DI)));
+typedef unsigned int UDItype	__attribute__ ((mode (DI)));
+struct DWstruct {
+	Wtype high, low;
+};
+typedef union {
+	struct DWstruct s;
+	DWtype ll;
+} DWunion;
+
+typedef int word_type __attribute__ ((mode (__word__)));
+
+#endif
+
+#endif
diff --git a/arch/h8300/lib/lshrdi3.c b/arch/h8300/lib/lshrdi3.c
new file mode 100644
index 000000000000..a86bbe395f17
--- /dev/null
+++ b/arch/h8300/lib/lshrdi3.c
@@ -0,0 +1,23 @@
+#include "libgcc.h"
+
+DWtype __lshrdi3(DWtype u, word_type b)
+{
+	const DWunion uu = {.ll = u};
+	const word_type bm = (sizeof (Wtype) * BITS_PER_UNIT) - b;
+	DWunion w;
+
+	if (b == 0)
+		return u;
+
+	if (bm <= 0) {
+		w.s.high = 0;
+		w.s.low = (UWtype) uu.s.high >> -bm;
+	} else {
+		const UWtype carries = (UWtype) uu.s.high << bm;
+
+		w.s.high = (UWtype) uu.s.high >> b;
+		w.s.low = ((UWtype) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
+}
diff --git a/arch/h8300/lib/memcpy.S b/arch/h8300/lib/memcpy.S
new file mode 100644
index 000000000000..0c9a51fcdea1
--- /dev/null
+++ b/arch/h8300/lib/memcpy.S
@@ -0,0 +1,85 @@
+;;; memcpy.S
+
+#include <asm/linkage.h>
+
+#if defined(CONFIG_CPU_H8300H)
+	.h8300h
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.h8300s
+#endif
+	.text
+.global memcpy
+
+;;; void *memcpy(void *to, void *from, size_t n)
+memcpy:
+	mov.l	er2,er2
+	bne	1f
+	rts
+1:
+	;; address check
+	bld	#0,r0l
+	bxor	#0,r1l
+	bcs	4f
+	mov.l	er4,@-sp
+	mov.l	er0,@-sp
+	btst	#0,r0l
+	beq	1f
+	;; (aligned even) odd address
+	mov.b	@er1,r3l
+	mov.b	r3l,@er0
+	adds	#1,er1
+	adds	#1,er0
+	dec.l	#1,er2
+	beq	3f
+1:
+	;; n < sizeof(unsigned long) check
+	sub.l	er4,er4
+	adds	#4,er4		; loop count check value
+	cmp.l	er4,er2
+	blo	2f
+	;; unsigned long copy
+1:
+	mov.l	@er1,er3
+	mov.l	er3,@er0
+	adds	#4,er0
+	adds	#4,er1
+	subs	#4,er2
+	cmp.l	er4,er2
+	bcc	1b
+	;; rest
+2:
+	mov.l	er2,er2
+	beq	3f
+1:
+	mov.b	@er1,r3l
+	mov.b	r3l,@er0
+	adds	#1,er1
+	adds	#1,er0
+	dec.l	#1,er2
+	bne	1b
+3:
+	mov.l	@sp+,er0
+	mov.l	@sp+,er4
+	rts
+
+	;; odd <- even / even <- odd
+4:
+	mov.l	er4,er3
+	mov.l	er2,er4
+	mov.l	er5,er2
+	mov.l	er1,er5
+	mov.l	er6,er1
+	mov.l	er0,er6
+1:
+	eepmov.w
+	mov.w	r4,r4
+	bne	1b
+	dec.w	#1,e4
+	bpl	1b
+	mov.l	er1,er6
+	mov.l	er2,er5
+	mov.l	er3,er4
+	rts
+
+	.end
diff --git a/arch/h8300/lib/memset.S b/arch/h8300/lib/memset.S
new file mode 100644
index 000000000000..18d4e709b5f4
--- /dev/null
+++ b/arch/h8300/lib/memset.S
@@ -0,0 +1,69 @@
+/* memset.S */
+
+#include <asm/linkage.h>
+
+#if defined(CONFIG_CPU_H8300H)
+	.h8300h
+#endif
+#if defined(CONFIG_CPU_H8S)
+	.h8300s
+#endif
+	.text
+
+.global	memset
+.global	clear_user
+
+;;void *memset(*ptr, int c, size_t count)
+;; ptr = er0
+;; c   = er1(r1l)
+;; count = er2
+memset:
+	btst	#0,r0l
+	beq	2f
+
+	;; odd address
+1:
+	mov.b	r1l,@er0
+	adds	#1,er0
+	dec.l	#1,er2
+	beq	6f
+
+	;; even address
+2:
+	mov.l	er2,er3
+	cmp.l	#4,er2
+	blo	4f
+	;; count>=4 -> count/4
+#if defined(CONFIG_CPU_H8300H)
+	shlr.l	er2
+	shlr.l	er2
+#endif
+#if defined(CONFIG_CPU_H8S)
+	shlr.l	#2,er2
+#endif
+	;; byte -> long
+	mov.b	r1l,r1h
+	mov.w	r1,e1
+3:
+	mov.l	er1,@er0
+	adds	#4,er0
+	dec.l	#1,er2
+	bne	3b
+4:
+	;; count % 4
+	and.b	#3,r3l
+	beq	6f
+5:
+	mov.b	r1l,@er0
+	adds	#1,er0
+	dec.b	r3l
+	bne	5b
+6:
+	rts
+
+clear_user:
+	mov.l	er1, er2
+	sub.l	er1, er1
+	bra	memset
+
+	.end
diff --git a/arch/h8300/lib/moddivsi3.S b/arch/h8300/lib/moddivsi3.S
new file mode 100644
index 000000000000..c803129e877f
--- /dev/null
+++ b/arch/h8300/lib/moddivsi3.S
@@ -0,0 +1,72 @@
+#include "libgcc.h"
+
+; numerator in A0/A1
+; denominator in A2/A3
+	.global	__modsi3
+__modsi3:
+	PUSHP	S2P
+	bsr	modnorm
+	bsr	__divsi3
+	mov.l	er3,er0
+	bra	exitdiv
+
+	.global	__umodsi3
+__umodsi3:
+	bsr	__udivsi3:16
+	mov.l	er3,er0
+	rts
+
+	.global	__divsi3
+__divsi3:
+	PUSHP	S2P
+	bsr	divnorm
+	bsr	__udivsi3:16
+
+	; examine what the sign should be
+exitdiv:
+	btst	#3,S2L
+	beq	reti
+
+	; should be -ve
+	neg.l	A0P
+
+reti:
+	POPP	S2P
+	rts
+
+divnorm:
+	mov.l	A0P,A0P		; is the numerator -ve
+	stc	ccr,S2L		; keep the sign in bit 3 of S2L
+	bge	postive
+
+	neg.l	A0P		; negate arg
+
+postive:
+	mov.l	A1P,A1P		; is the denominator -ve
+	bge	postive2
+
+	neg.l	A1P		; negate arg
+	xor.b	#0x08,S2L	; toggle the result sign
+
+postive2:
+	rts
+
+;; Basically the same, except that the sign of the divisor determines
+;; the sign.
+modnorm:
+	mov.l	A0P,A0P		; is the numerator -ve
+	stc	ccr,S2L		; keep the sign in bit 3 of S2L
+	bge	mpostive
+
+	neg.l	A0P		; negate arg
+
+mpostive:
+	mov.l	A1P,A1P		; is the denominator -ve
+	bge	mpostive2
+
+	neg.l	A1P		; negate arg
+
+mpostive2:
+	rts
+
+	.end
diff --git a/arch/h8300/lib/modsi3.S b/arch/h8300/lib/modsi3.S
new file mode 100644
index 000000000000..68b1dfc32824
--- /dev/null
+++ b/arch/h8300/lib/modsi3.S
@@ -0,0 +1,72 @@
+#include "libgcc.h"
+
+; numerator in A0/A1
+; denominator in A2/A3
+	.global	__modsi3
+__modsi3:
+	PUSHP	S2P
+	bsr	modnorm
+	bsr	__divsi3
+	mov.l	er3,er0
+	bra	exitdiv
+
+	.global	__umodsi3
+__umodsi3:
+	bsr	__udivsi3
+	mov.l	er3,er0
+	rts
+
+	.global	__divsi3
+__divsi3:
+	PUSHP	S2P
+	jsr	divnorm
+	bsr	__udivsi3
+
+	; examine what the sign should be
+exitdiv:
+	btst	#3,S2L
+	beq	reti
+
+	; should be -ve
+	neg.l	A0P
+
+reti:
+	POPP	S2P
+	rts
+
+divnorm:
+	mov.l	A0P,A0P		; is the numerator -ve
+	stc	ccr,S2L		; keep the sign in bit 3 of S2L
+	bge	postive
+
+	neg.l	A0P		; negate arg
+
+postive:
+	mov.l	A1P,A1P		; is the denominator -ve
+	bge	postive2
+
+	neg.l	A1P		; negate arg
+	xor.b	#0x08,S2L	; toggle the result sign
+
+postive2:
+	rts
+
+;; Basically the same, except that the sign of the divisor determines
+;; the sign.
+modnorm:
+	mov.l	A0P,A0P		; is the numerator -ve
+	stc	ccr,S2L		; keep the sign in bit 3 of S2L
+	bge	mpostive
+
+	neg.l	A0P		; negate arg
+
+mpostive:
+	mov.l	A1P,A1P		; is the denominator -ve
+	bge	mpostive2
+
+	neg.l	A1P		; negate arg
+
+mpostive2:
+	rts
+
+	.end
diff --git a/arch/h8300/lib/muldi3.c b/arch/h8300/lib/muldi3.c
new file mode 100644
index 000000000000..790512243531
--- /dev/null
+++ b/arch/h8300/lib/muldi3.c
@@ -0,0 +1,44 @@
+#include "libgcc.h"
+
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+#define umul_ppmm(w1, w0, u, v) \
+	do {			   \
+		UWtype __x0, __x1, __x2, __x3;	\
+		UHWtype __ul, __vl, __uh, __vh; \
+		__ul = __ll_lowpart(u);	\
+		__uh = __ll_highpart(u);	\
+		__vl = __ll_lowpart(v);	\
+		__vh = __ll_highpart(v);	\
+		__x0 = (UWtype) __ul * __vl;	\
+		__x1 = (UWtype) __ul * __vh;	\
+		__x2 = (UWtype) __uh * __vl;	\
+		__x3 = (UWtype) __uh * __vh;	\
+		__x1 += __ll_highpart(__x0);	\
+		__x1 += __x2;			\
+		if (__x1 < __x2)		\
+			__x3 += __ll_B;		\
+		(w1) = __x3 + __ll_highpart(__x1);	       \
+		(w0) = __ll_lowpart(__x1) * __ll_B + __ll_lowpart(__x0); \
+	} while (0)
+
+#define __umulsidi3(u, v) (			\
+		{				\
+			DWunion __w;		\
+			umul_ppmm(__w.s.high, __w.s.low, u, v);	\
+			__w.ll; }					\
+		)
+
+DWtype __muldi3(DWtype u, DWtype v)
+{
+	const DWunion uu = {.ll = u};
+	const DWunion vv = {.ll = v};
+	DWunion w = {.ll = __umulsidi3(uu.s.low, vv.s.low)};
+
+	w.s.high += ((UWtype) uu.s.low * (UWtype) vv.s.high
+		     + (UWtype) uu.s.high * (UWtype) vv.s.low);
+
+	return w.ll;
+}
diff --git a/arch/h8300/lib/mulsi3.S b/arch/h8300/lib/mulsi3.S
new file mode 100644
index 000000000000..451f0e0538ee
--- /dev/null
+++ b/arch/h8300/lib/mulsi3.S
@@ -0,0 +1,38 @@
+;
+; mulsi3 for H8/300H - based on Renesas SH implementation
+;
+; by Toshiyasu Morita
+;
+; Old code:
+;
+; 16b * 16b = 372 states (worst case)
+; 32b * 32b = 724 states (worst case)
+;
+; New code:
+;
+; 16b * 16b =  48 states
+; 16b * 32b =  72 states
+; 32b * 32b =  92 states
+;
+
+	.global __mulsi3
+__mulsi3:
+	mov.w	r1,r2   ; ( 2 states) b * d
+	mulxu	r0,er2  ; (22 states)
+
+	mov.w	e0,r3   ; ( 2 states) a * d
+	beq	L_skip1 ; ( 4 states)
+	mulxu	r1,er3  ; (22 states)
+	add.w	r3,e2   ; ( 2 states)
+
+L_skip1:
+	mov.w	e1,r3   ; ( 2 states) c * b
+	beq	L_skip2 ; ( 4 states)
+	mulxu	r0,er3  ; (22 states)
+	add.w	r3,e2   ; ( 2 states)
+
+L_skip2:
+	mov.l	er2,er0	; ( 2 states)
+	rts		; (10 states)
+
+	.end
diff --git a/arch/h8300/lib/strncpy.S b/arch/h8300/lib/strncpy.S
new file mode 100644
index 000000000000..d00396a378f4
--- /dev/null
+++ b/arch/h8300/lib/strncpy.S
@@ -0,0 +1,34 @@
+;;; strncpy.S
+
+#include <asm/linkage.h>
+
+	.text
+.global strncpy_from_user
+
+;;; long strncpy_from_user(void *to, void *from, size_t n)
+strncpy_from_user:
+	mov.l	er2,er2
+	bne	1f
+	sub.l	er0,er0
+	rts
+1:
+	mov.l	er4,@-sp
+	sub.l	er3,er3
+2:
+	mov.b	@er1+,r4l
+	mov.b	r4l,@er0
+	adds	#1,er0
+	beq	3f
+	inc.l	#1,er3
+	dec.l	#1,er2
+	bne	2b
+3:
+	dec.l	#1,er2
+4:
+	mov.b	r4l,@er0
+	adds	#1,er0
+	dec.l	#1,er2
+	bne	4b
+	mov.l	er3,er0
+	mov.l	@sp+,er4
+	rts
diff --git a/arch/h8300/lib/ucmpdi2.c b/arch/h8300/lib/ucmpdi2.c
new file mode 100644
index 000000000000..772399d705cb
--- /dev/null
+++ b/arch/h8300/lib/ucmpdi2.c
@@ -0,0 +1,17 @@
+#include "libgcc.h"
+
+word_type __ucmpdi2(DWtype a, DWtype b)
+{
+	const DWunion au = {.ll = a};
+	const DWunion bu = {.ll = b};
+
+	if ((UWtype) au.s.high < (UWtype) bu.s.high)
+		return 0;
+	else if ((UWtype) au.s.high > (UWtype) bu.s.high)
+		return 2;
+	if ((UWtype) au.s.low < (UWtype) bu.s.low)
+		return 0;
+	else if ((UWtype) au.s.low > (UWtype) bu.s.low)
+		return 2;
+	return 1;
+}
diff --git a/arch/h8300/lib/udivsi3.S b/arch/h8300/lib/udivsi3.S
new file mode 100644
index 000000000000..bbe65610f316
--- /dev/null
+++ b/arch/h8300/lib/udivsi3.S
@@ -0,0 +1,76 @@
+#include "libgcc.h"
+
+	;; This function also computes the remainder and stores it in er3.
+	.global	__udivsi3
+__udivsi3:
+	mov.w	A1E,A1E		; denominator top word 0?
+	bne	DenHighNonZero
+
+	; do it the easy way, see page 107 in manual
+	mov.w	A0E,A2
+	extu.l	A2P
+	divxu.w	A1,A2P
+	mov.w	A2E,A0E
+	divxu.w	A1,A0P
+	mov.w	A0E,A3
+	mov.w	A2,A0E
+	extu.l	A3P
+	rts
+
+	; er0 = er0 / er1
+	; er3 = er0 % er1
+	; trashes er1 er2
+	; expects er1 >= 2^16
+DenHighNonZero:
+	mov.l	er0,er3
+	mov.l	er1,er2
+#ifdef CONFIG_CPU_H8300H
+divmod_L21:
+	shlr.l	er0
+	shlr.l	er2		; make divisor < 2^16
+	mov.w	e2,e2
+	bne	divmod_L21
+#else
+	shlr.l	#2,er2		; make divisor < 2^16
+	mov.w	e2,e2
+	beq	divmod_L22A
+divmod_L21:
+	shlr.l	#2,er0
+divmod_L22:
+	shlr.l	#2,er2		; make divisor < 2^16
+	mov.w	e2,e2
+	bne	divmod_L21
+divmod_L22A:
+	rotxl.w	r2
+	bcs	divmod_L23
+	shlr.l	er0
+	bra	divmod_L24
+divmod_L23:
+	rotxr.w	r2
+	shlr.l	#2,er0
+divmod_L24:
+#endif
+	;; At this point,
+	;;  er0 contains shifted dividend
+	;;  er1 contains divisor
+	;;  er2 contains shifted divisor
+	;;  er3 contains dividend, later remainder
+	divxu.w	r2,er0		; r0 now contains the approximate quotient (AQ)
+	extu.l	er0
+	beq	divmod_L25
+	subs	#1,er0		; er0 = AQ - 1
+	mov.w	e1,r2
+	mulxu.w	r0,er2		; er2 = upper (AQ - 1) * divisor
+	sub.w	r2,e3		; dividend - 65536 * er2
+	mov.w	r1,r2
+	mulxu.w	r0,er2		; compute er3 = remainder (tentative)
+	sub.l	er2,er3		; er3 = dividend - (AQ - 1) * divisor
+divmod_L25:
+	cmp.l	er1,er3		; is divisor < remainder?
+	blo	divmod_L26
+	adds	#1,er0
+	sub.l	er1,er3		; correct the remainder
+divmod_L26:
+	rts
+
+	.end
diff --git a/arch/h8300/mm/Makefile b/arch/h8300/mm/Makefile
new file mode 100644
index 000000000000..508697f0d97c
--- /dev/null
+++ b/arch/h8300/mm/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the linux h8300-specific parts of the memory manager.
+#
+
+obj-y	 := init.o fault.o memory.o
diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c
new file mode 100644
index 000000000000..5924ff555ded
--- /dev/null
+++ b/arch/h8300/mm/fault.c
@@ -0,0 +1,57 @@
+/*
+ *  linux/arch/h8300/mm/fault.c
+ *
+ *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
+ *  Copyright (C) 2000  Lineo, Inc.  (www.lineo.com)
+ *
+ *  Based on:
+ *
+ *  linux/arch/m68knommu/mm/fault.c
+ *  linux/arch/m68k/mm/fault.c
+ *
+ *  Copyright (C) 1995  Hamish Macdonald
+ */
+
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+
+#include <asm/pgtable.h>
+
+void die(const char *str, struct pt_regs *fp, unsigned long err);
+
+/*
+ * This routine handles page faults.  It determines the problem, and
+ * then passes it off to one of the appropriate routines.
+ *
+ * error_code:
+ *	bit 0 == 0 means no page found, 1 means protection fault
+ *	bit 1 == 0 means read, 1 means write
+ *
+ * If this routine detects a bad access, it returns 1, otherwise it
+ * returns 0.
+ */
+asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
+			      unsigned long error_code)
+{
+#ifdef DEBUG
+	pr_debug("regs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld\n",
+		 regs->sr, regs->pc, address, error_code);
+#endif
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+	if ((unsigned long) address < PAGE_SIZE)
+		pr_alert("Unable to handle kernel NULL pointer dereference");
+	else
+		pr_alert("Unable to handle kernel access");
+	printk(" at virtual address %08lx\n", address);
+	if (!user_mode(regs))
+		die("Oops", regs, error_code);
+	do_exit(SIGKILL);
+
+	return 1;
+}
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
new file mode 100644
index 000000000000..495a3d6b539b
--- /dev/null
+++ b/arch/h8300/mm/init.c
@@ -0,0 +1,128 @@
+/*
+ *  linux/arch/h8300/mm/init.c
+ *
+ *  Copyright (C) 1998  D. Jeff Dionne <jeff@lineo.ca>,
+ *                      Kenneth Albanowski <kjahds@kjahds.com>,
+ *  Copyright (C) 2000  Lineo, Inc.  (www.lineo.com)
+ *
+ *  Based on:
+ *
+ *  linux/arch/m68knommu/mm/init.c
+ *  linux/arch/m68k/mm/init.c
+ *
+ *  Copyright (C) 1995  Hamish Macdonald
+ *
+ *  JAN/1999 -- hacked to support ColdFire (gerg@snapgear.com)
+ *  DEC/2000 -- linux 2.4 support <davidm@snapgear.com>
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/gfp.h>
+
+#include <asm/setup.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/sections.h>
+
+/*
+ * BAD_PAGE is the page that is used for page faults when linux
+ * is out-of-memory. Older versions of linux just did a
+ * do_exit(), but using this instead means there is less risk
+ * for a process dying in kernel mode, possibly leaving a inode
+ * unused etc..
+ *
+ * BAD_PAGETABLE is the accompanying page-table: it is initialized
+ * to point to BAD_PAGE entries.
+ *
+ * ZERO_PAGE is a special page that is used for zero-initialized
+ * data and COW.
+ */
+static unsigned long empty_bad_page_table;
+static unsigned long empty_bad_page;
+unsigned long empty_zero_page;
+
+/*
+ * paging_init() continues the virtual memory environment setup which
+ * was begun by the code in arch/head.S.
+ * The parameters are pointers to where to stick the starting and ending
+ * addresses of available kernel virtual memory.
+ */
+void __init paging_init(void)
+{
+	/*
+	 * Make sure start_mem is page aligned,  otherwise bootmem and
+	 * page_alloc get different views og the world.
+	 */
+	unsigned long start_mem = PAGE_ALIGN(memory_start);
+	unsigned long end_mem   = memory_end & PAGE_MASK;
+
+	pr_debug("start_mem is %#lx\nvirtual_end is %#lx\n",
+		 start_mem, end_mem);
+
+	/*
+	 * Initialize the bad page table and bad page to point
+	 * to a couple of allocated pages.
+	 */
+	empty_bad_page_table = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
+	empty_bad_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
+	empty_zero_page = (unsigned long)alloc_bootmem_pages(PAGE_SIZE);
+	memset((void *)empty_zero_page, 0, PAGE_SIZE);
+
+	/*
+	 * Set up SFC/DFC registers (user data space).
+	 */
+	set_fs(USER_DS);
+
+	pr_debug("before free_area_init\n");
+
+	pr_debug("free_area_init -> start_mem is %#lx\nvirtual_end is %#lx\n",
+		 start_mem, end_mem);
+
+	{
+		unsigned long zones_size[MAX_NR_ZONES] = {0, };
+
+		zones_size[ZONE_NORMAL] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
+		free_area_init(zones_size);
+	}
+}
+
+void __init mem_init(void)
+{
+	pr_devel("Mem_init: start=%lx, end=%lx\n", memory_start, memory_end);
+
+	high_memory = (void *) (memory_end & PAGE_MASK);
+	max_mapnr = MAP_NR(high_memory);
+
+	/* this will put all low memory onto the freelists */
+	free_all_bootmem();
+
+	mem_init_print_info(NULL);
+}
+
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void free_initrd_mem(unsigned long start, unsigned long end)
+{
+	free_reserved_area((void *)start, (void *)end, -1, "initrd");
+}
+#endif
+
+void
+free_initmem(void)
+{
+	free_initmem_default(-1);
+}
diff --git a/arch/h8300/mm/memory.c b/arch/h8300/mm/memory.c
new file mode 100644
index 000000000000..4974aa40bcb8
--- /dev/null
+++ b/arch/h8300/mm/memory.c
@@ -0,0 +1,53 @@
+/*
+ *  linux/arch/h8300/mm/memory.c
+ *
+ *  Copyright (C) 2002  Yoshinori Sato <ysato@users.sourceforge.jp>,
+ *
+ *  Based on:
+ *
+ *  linux/arch/m68knommu/mm/memory.c
+ *
+ *  Copyright (C) 1998  Kenneth Albanowski <kjahds@kjahds.com>,
+ *  Copyright (C) 1999-2002, Greg Ungerer (gerg@snapgear.com)
+ *
+ *  Based on:
+ *
+ *  linux/arch/m68k/mm/memory.c
+ *
+ *  Copyright (C) 1995  Hamish Macdonald
+ */
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/setup.h>
+#include <asm/segment.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/traps.h>
+#include <asm/io.h>
+
+void cache_clear(unsigned long paddr, int len)
+{
+}
+
+
+void cache_push(unsigned long paddr, int len)
+{
+}
+
+void cache_push_v(unsigned long vaddr, int len)
+{
+}
+
+/*
+ * Map some physical address range into the kernel address space.
+ */
+
+unsigned long kernel_map(unsigned long paddr, unsigned long size,
+			 int nocacheflag, unsigned long *memavailp)
+{
+	return paddr;
+}
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 9e7802911a57..a6e34e2acbba 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -64,7 +64,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
  *  looks just like atomic_cmpxchg on our arch currently with a bunch of
  *  variable casting.
  */
-#define __HAVE_ARCH_CMPXCHG 1
 
 #define cmpxchg(ptr, old, new)					\
 ({								\
diff --git a/arch/hexagon/include/asm/mm-arch-hooks.h b/arch/hexagon/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..05e8b939e416
--- /dev/null
+++ b/arch/hexagon/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_HEXAGON_MM_ARCH_HOOKS_H
+#define _ASM_HEXAGON_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_HEXAGON_MM_ARCH_HOOKS_H */
diff --git a/arch/hexagon/include/asm/uaccess.h b/arch/hexagon/include/asm/uaccess.h
index e4127e4d6a5b..f000a382bc7f 100644
--- a/arch/hexagon/include/asm/uaccess.h
+++ b/arch/hexagon/include/asm/uaccess.h
@@ -36,7 +36,8 @@
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 76d25b2cfbbe..42a91a7aa2b0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -137,29 +137,6 @@ config AUDIT_ARCH
 	bool
 	default y
 
-menuconfig PARAVIRT_GUEST
-	bool "Paravirtualized guest support"
-	depends on BROKEN
-	help
-	  Say Y here to get to see options related to running Linux under
-	  various hypervisors.  This option alone does not add any kernel code.
-
-	  If you say N, all options in this submenu will be skipped and disabled.
-
-if PARAVIRT_GUEST
-
-config PARAVIRT
-	bool "Enable paravirtualization code"
-	depends on PARAVIRT_GUEST
-	default y
-	help
-	  This changes the kernel so it can modify itself when it is run
-	  under a hypervisor, potentially improving performance significantly
-	  over full virtualization.  However, when run without a hypervisor
-	  the kernel is theoretically slower and slightly larger.
-
-endif
-
 choice
 	prompt "System type"
 	default IA64_GENERIC
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index f6769eb2bbf9..843ba435e43b 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,12 +77,7 @@ do {									\
 	___p1;								\
 })
 
-/*
- * XXX check on this ---I suspect what Linus really wants here is
- * acquire vs release semantics but we can't discuss this stuff with
- * Linus just yet.  Grrr...
- */
-#define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index aa910054b8e7..ff1377bc02a6 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -20,10 +20,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 668786e84af8..74347ebf7d68 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -15,11 +15,7 @@
 #include <asm/ptrace.h>
 #include <asm/smp.h>
 
-#ifndef CONFIG_PARAVIRT
 typedef u8 ia64_vector;
-#else
-typedef u16 ia64_vector;
-#endif
 
 /*
  * 0 special
@@ -114,15 +110,11 @@ DECLARE_PER_CPU(int[IA64_NUM_VECTORS], vector_irq);
 
 extern struct irq_chip irq_type_ia64_lsapic;	/* CPU-internal interrupt controller */
 
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
 #define ia64_register_ipi	ia64_native_register_ipi
 #define assign_irq_vector	ia64_native_assign_irq_vector
 #define free_irq_vector		ia64_native_free_irq_vector
 #define register_percpu_irq	ia64_native_register_percpu_irq
 #define ia64_resend_irq		ia64_native_resend_irq
-#endif
 
 extern void ia64_native_register_ipi(void);
 extern int bind_irq_vector(int irq, int vector, cpumask_t domain);
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index 20477ea111ba..ec970a920132 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -7,19 +7,6 @@
 #ifndef _ASM_IA64_INTRINSICS_H
 #define _ASM_IA64_INTRINSICS_H
 
-#include <asm/paravirt_privop.h>
 #include <uapi/asm/intrinsics.h>
 
-#ifndef __ASSEMBLY__
-#if defined(CONFIG_PARAVIRT)
-# undef IA64_INTRINSIC_API
-# undef IA64_INTRINSIC_MACRO
-# ifdef ASM_SUPPORTED
-#  define IA64_INTRINSIC_API(name)	paravirt_ ## name
-# else
-#  define IA64_INTRINSIC_API(name)	pv_cpu_ops.name
-# endif
-#define IA64_INTRINSIC_MACRO(name)	paravirt_ ## name
-#endif
-#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_IA64_INTRINSICS_H */
diff --git a/arch/ia64/include/asm/iosapic.h b/arch/ia64/include/asm/iosapic.h
index 94c89a2d97fe..4ae1fbd7f10e 100644
--- a/arch/ia64/include/asm/iosapic.h
+++ b/arch/ia64/include/asm/iosapic.h
@@ -55,14 +55,10 @@
 
 #define NR_IOSAPICS			256
 
-#ifdef CONFIG_PARAVIRT_GUEST
-#include <asm/paravirt.h>
-#else
 #define iosapic_pcat_compat_init	ia64_native_iosapic_pcat_compat_init
 #define __iosapic_read			__ia64_native_iosapic_read
 #define __iosapic_write			__ia64_native_iosapic_write
 #define iosapic_get_irq_chip		ia64_native_iosapic_get_irq_chip
-#endif
 
 extern void __init ia64_native_iosapic_pcat_compat_init(void);
 extern struct irq_chip *ia64_native_iosapic_get_irq_chip(unsigned long trigger);
diff --git a/arch/ia64/include/asm/irq_remapping.h b/arch/ia64/include/asm/irq_remapping.h
index e3b3556e2e1b..a8687b1d8906 100644
--- a/arch/ia64/include/asm/irq_remapping.h
+++ b/arch/ia64/include/asm/irq_remapping.h
@@ -1,6 +1,4 @@
 #ifndef __IA64_INTR_REMAPPING_H
 #define __IA64_INTR_REMAPPING_H
 #define irq_remapping_enabled 0
-#define dmar_alloc_hwirq	create_irq
-#define dmar_free_hwirq		destroy_irq
 #endif
diff --git a/arch/ia64/include/asm/mm-arch-hooks.h b/arch/ia64/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..ab4b5c698322
--- /dev/null
+++ b/arch/ia64/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_IA64_MM_ARCH_HOOKS_H
+#define _ASM_IA64_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_IA64_MM_ARCH_HOOKS_H */
diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h
index dfba22a872c3..f31894b2a354 100644
--- a/arch/ia64/include/asm/module.h
+++ b/arch/ia64/include/asm/module.h
@@ -18,12 +18,6 @@ struct mod_arch_specific {
 	struct elf64_shdr *got;		/* global offset table */
 	struct elf64_shdr *opd;		/* official procedure descriptors */
 	struct elf64_shdr *unwind;	/* unwind-table section */
-#ifdef CONFIG_PARAVIRT
-	struct elf64_shdr *paravirt_bundles;
-					/* paravirt_alt_bundle_patch table */
-	struct elf64_shdr *paravirt_insts;
-					/* paravirt_alt_inst_patch table */
-#endif
 	unsigned long gp;		/* global-pointer for module */
 
 	void *core_unw_table;		/* core unwind-table cookie returned by unwinder */
diff --git a/arch/ia64/include/asm/native/inst.h b/arch/ia64/include/asm/native/inst.h
index d2d46efb3e6e..7e08f17accd5 100644
--- a/arch/ia64/include/asm/native/inst.h
+++ b/arch/ia64/include/asm/native/inst.h
@@ -22,32 +22,6 @@
 
 #define DO_SAVE_MIN		IA64_NATIVE_DO_SAVE_MIN
 
-#define __paravirt_switch_to			ia64_native_switch_to
-#define __paravirt_leave_syscall		ia64_native_leave_syscall
-#define __paravirt_work_processed_syscall	ia64_native_work_processed_syscall
-#define __paravirt_leave_kernel			ia64_native_leave_kernel
-#define __paravirt_pending_syscall_end		ia64_work_pending_syscall_end
-#define __paravirt_work_processed_syscall_target \
-						ia64_work_processed_syscall
-
-#define paravirt_fsyscall_table			ia64_native_fsyscall_table
-#define paravirt_fsys_bubble_down		ia64_native_fsys_bubble_down
-
-#ifdef CONFIG_PARAVIRT_GUEST_ASM_CLOBBER_CHECK
-# define PARAVIRT_POISON	0xdeadbeefbaadf00d
-# define CLOBBER(clob)				\
-	;;					\
-	movl clob = PARAVIRT_POISON;		\
-	;;
-# define CLOBBER_PRED(pred_clob)		\
-	;;					\
-	cmp.eq pred_clob, p0 = r0, r0		\
-	;;
-#else
-# define CLOBBER(clob)			/* nothing */
-# define CLOBBER_PRED(pred_clob)	/* nothing */
-#endif
-
 #define MOV_FROM_IFA(reg)	\
 	mov reg = cr.ifa
 
@@ -70,106 +44,76 @@
 	mov reg = cr.iip
 
 #define MOV_FROM_IVR(reg, clob)	\
-	mov reg = cr.ivr	\
-	CLOBBER(clob)
+	mov reg = cr.ivr
 
 #define MOV_FROM_PSR(pred, reg, clob)	\
-(pred)	mov reg = psr			\
-	CLOBBER(clob)
+(pred)	mov reg = psr
 
 #define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
-(pred)	mov reg = ar.itc				\
-	CLOBBER(clob)					\
-	CLOBBER_PRED(pred_clob)
+(pred)	mov reg = ar.itc
 
 #define MOV_TO_IFA(reg, clob)	\
-	mov cr.ifa = reg	\
-	CLOBBER(clob)
+	mov cr.ifa = reg
 
 #define MOV_TO_ITIR(pred, reg, clob)	\
-(pred)	mov cr.itir = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.itir = reg
 
 #define MOV_TO_IHA(pred, reg, clob)	\
-(pred)	mov cr.iha = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.iha = reg
 
 #define MOV_TO_IPSR(pred, reg, clob)		\
-(pred)	mov cr.ipsr = reg			\
-	CLOBBER(clob)
+(pred)	mov cr.ipsr = reg
 
 #define MOV_TO_IFS(pred, reg, clob)	\
-(pred)	mov cr.ifs = reg		\
-	CLOBBER(clob)
+(pred)	mov cr.ifs = reg
 
 #define MOV_TO_IIP(reg, clob)	\
-	mov cr.iip = reg	\
-	CLOBBER(clob)
+	mov cr.iip = reg
 
 #define MOV_TO_KR(kr, reg, clob0, clob1)	\
-	mov IA64_KR(kr) = reg			\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)
+	mov IA64_KR(kr) = reg
 
 #define ITC_I(pred, reg, clob)	\
-(pred)	itc.i reg		\
-	CLOBBER(clob)
+(pred)	itc.i reg
 
 #define ITC_D(pred, reg, clob)	\
-(pred)	itc.d reg		\
-	CLOBBER(clob)
+(pred)	itc.d reg
 
 #define ITC_I_AND_D(pred_i, pred_d, reg, clob)	\
 (pred_i) itc.i reg;				\
-(pred_d) itc.d reg				\
-	CLOBBER(clob)
+(pred_d) itc.d reg
 
 #define THASH(pred, reg0, reg1, clob)		\
-(pred)	thash reg0 = reg1			\
-	CLOBBER(clob)
+(pred)	thash reg0 = reg1
 
 #define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1)		\
 	ssm psr.ic | PSR_DEFAULT_BITS					\
-	CLOBBER(clob0)							\
-	CLOBBER(clob1)							\
 	;;								\
 	srlz.i /* guarantee that interruption collectin is on */	\
 	;;
 
 #define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1)	\
 	ssm psr.ic				\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)				\
 	;;					\
 	srlz.d
 
 #define RSM_PSR_IC(clob)	\
-	rsm psr.ic		\
-	CLOBBER(clob)
+	rsm psr.ic
 
 #define SSM_PSR_I(pred, pred_clob, clob)	\
-(pred)	ssm psr.i				\
-	CLOBBER(clob)				\
-	CLOBBER_PRED(pred_clob)
+(pred)	ssm psr.i
 
 #define RSM_PSR_I(pred, clob0, clob1)	\
-(pred)	rsm psr.i			\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)
+(pred)	rsm psr.i
 
 #define RSM_PSR_I_IC(clob0, clob1, clob2)	\
-	rsm psr.i | psr.ic			\
-	CLOBBER(clob0)				\
-	CLOBBER(clob1)				\
-	CLOBBER(clob2)
+	rsm psr.i | psr.ic
 
 #define RSM_PSR_DT		\
 	rsm psr.dt
 
 #define RSM_PSR_BE_I(clob0, clob1)	\
-	rsm psr.be | psr.i		\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)
+	rsm psr.be | psr.i
 
 #define SSM_PSR_DT_AND_SRLZ_I	\
 	ssm psr.dt		\
@@ -177,15 +121,10 @@
 	srlz.i
 
 #define BSW_0(clob0, clob1, clob2)	\
-	bsw.0				\
-	CLOBBER(clob0)			\
-	CLOBBER(clob1)			\
-	CLOBBER(clob2)
+	bsw.0
 
 #define BSW_1(clob0, clob1)	\
-	bsw.1			\
-	CLOBBER(clob0)		\
-	CLOBBER(clob1)
+	bsw.1
 
 #define COVER	\
 	cover
diff --git a/arch/ia64/include/asm/native/pvchk_inst.h b/arch/ia64/include/asm/native/pvchk_inst.h
deleted file mode 100644
index 8d72962ec838..000000000000
--- a/arch/ia64/include/asm/native/pvchk_inst.h
+++ /dev/null
@@ -1,271 +0,0 @@
-#ifndef _ASM_NATIVE_PVCHK_INST_H
-#define _ASM_NATIVE_PVCHK_INST_H
-
-/******************************************************************************
- * arch/ia64/include/asm/native/pvchk_inst.h
- * Checker for paravirtualizations of privileged operations.
- *
- * Copyright (C) 2005 Hewlett-Packard Co
- *      Dan Magenheimer <dan.magenheimer@hp.com>
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-/**********************************************
- * Instructions paravirtualized for correctness
- **********************************************/
-
-/* "fc" and "thash" are privilege-sensitive instructions, meaning they
- *  may have different semantics depending on whether they are executed
- *  at PL0 vs PL!=0.  When paravirtualized, these instructions mustn't
- *  be allowed to execute directly, lest incorrect semantics result.
- */
-
-#define fc	.error "fc should not be used directly."
-#define thash	.error "thash should not be used directly."
-
-/* Note that "ttag" and "cover" are also privilege-sensitive; "ttag"
- * is not currently used (though it may be in a long-format VHPT system!)
- * and the semantics of cover only change if psr.ic is off which is very
- * rare (and currently non-existent outside of assembly code
- */
-#define ttag	.error "ttag should not be used directly."
-#define cover	.error "cover should not be used directly."
-
-/* There are also privilege-sensitive registers.  These registers are
- * readable at any privilege level but only writable at PL0.
- */
-#define cpuid	.error "cpuid should not be used directly."
-#define pmd	.error "pmd should not be used directly."
-
-/*
- * mov ar.eflag =
- * mov = ar.eflag
- */
-
-/**********************************************
- * Instructions paravirtualized for performance
- **********************************************/
-/*
- * Those instructions include '.' which can't be handled by cpp.
- * or can't be handled by cpp easily.
- * They are handled by sed instead of cpp.
- */
-
-/* for .S
- * itc.i
- * itc.d
- *
- * bsw.0
- * bsw.1
- *
- * ssm psr.ic | PSR_DEFAULT_BITS
- * ssm psr.ic
- * rsm psr.ic
- * ssm psr.i
- * rsm psr.i
- * rsm psr.i | psr.ic
- * rsm psr.dt
- * ssm psr.dt
- *
- * mov = cr.ifa
- * mov = cr.itir
- * mov = cr.isr
- * mov = cr.iha
- * mov = cr.ipsr
- * mov = cr.iim
- * mov = cr.iip
- * mov = cr.ivr
- * mov = psr
- *
- * mov cr.ifa =
- * mov cr.itir =
- * mov cr.iha =
- * mov cr.ipsr =
- * mov cr.ifs =
- * mov cr.iip =
- * mov cr.kr =
- */
-
-/* for intrinsics
- * ssm psr.i
- * rsm psr.i
- * mov = psr
- * mov = ivr
- * mov = tpr
- * mov cr.itm =
- * mov eoi =
- * mov rr[] =
- * mov = rr[]
- * mov = kr
- * mov kr =
- * ptc.ga
- */
-
-/*************************************************************
- * define paravirtualized instrcution macros as nop to ingore.
- * and check whether arguments are appropriate.
- *************************************************************/
-
-/* check whether reg is a regular register */
-.macro is_rreg_in reg
-	.ifc "\reg", "r0"
-		nop 0
-		.exitm
-	.endif
-	;;
-	mov \reg = r0
-	;;
-.endm
-#define IS_RREG_IN(reg)	is_rreg_in reg ;
-
-#define IS_RREG_OUT(reg)			\
-	;;					\
-	mov reg = r0				\
-	;;
-
-#define IS_RREG_CLOB(reg)	IS_RREG_OUT(reg)
-
-/* check whether pred is a predicate register */
-#define IS_PRED_IN(pred)			\
-	;;					\
-	(pred)	nop 0				\
-	;;
-
-#define IS_PRED_OUT(pred)			\
-	;;					\
-	cmp.eq pred, p0 = r0, r0		\
-	;;
-
-#define IS_PRED_CLOB(pred)	IS_PRED_OUT(pred)
-
-
-#define DO_SAVE_MIN(__COVER, SAVE_IFS, EXTRA, WORKAROUND)	\
-	nop 0
-#define MOV_FROM_IFA(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_ITIR(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_ISR(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IHA(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IPSR(pred, reg)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IIM(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IIP(reg)			\
-	IS_RREG_OUT(reg)
-#define MOV_FROM_IVR(reg, clob)			\
-	IS_RREG_OUT(reg)			\
-	IS_RREG_CLOB(clob)
-#define MOV_FROM_PSR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg)			\
-	IS_RREG_CLOB(clob)
-#define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
-	IS_PRED_IN(pred)				\
-	IS_PRED_CLOB(pred_clob)				\
-	IS_RREG_OUT(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IFA(reg, clob)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_ITIR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IHA(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IPSR(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IFS(pred, reg, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_IIP(reg, clob)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define MOV_TO_KR(kr, reg, clob0, clob1)	\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define ITC_I(pred, reg, clob)			\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define ITC_D(pred, reg, clob)			\
-	IS_PRED_IN(pred)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define ITC_I_AND_D(pred_i, pred_d, reg, clob)	\
-	IS_PRED_IN(pred_i)			\
-	IS_PRED_IN(pred_d)			\
-	IS_RREG_IN(reg)				\
-	IS_RREG_CLOB(clob)
-#define THASH(pred, reg0, reg1, clob)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_OUT(reg0)			\
-	IS_RREG_IN(reg1)			\
-	IS_RREG_CLOB(clob)
-#define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1)	\
-	IS_RREG_CLOB(clob0)					\
-	IS_RREG_CLOB(clob1)
-#define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1)	\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define RSM_PSR_IC(clob)			\
-	IS_RREG_CLOB(clob)
-#define SSM_PSR_I(pred, pred_clob, clob)	\
-	IS_PRED_IN(pred)			\
-	IS_PRED_CLOB(pred_clob)			\
-	IS_RREG_CLOB(clob)
-#define RSM_PSR_I(pred, clob0, clob1)		\
-	IS_PRED_IN(pred)			\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define RSM_PSR_I_IC(clob0, clob1, clob2)	\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)			\
-	IS_RREG_CLOB(clob2)
-#define RSM_PSR_DT				\
-	nop 0
-#define RSM_PSR_BE_I(clob0, clob1)		\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define SSM_PSR_DT_AND_SRLZ_I			\
-	nop 0
-#define BSW_0(clob0, clob1, clob2)		\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)			\
-	IS_RREG_CLOB(clob2)
-#define BSW_1(clob0, clob1)			\
-	IS_RREG_CLOB(clob0)			\
-	IS_RREG_CLOB(clob1)
-#define COVER					\
-	nop 0
-#define RFI					\
-	br.ret.sptk.many rp /* defining nop causes dependency error */
-
-#endif /* _ASM_NATIVE_PVCHK_INST_H */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
deleted file mode 100644
index b53518a98026..000000000000
--- a/arch/ia64/include/asm/paravirt.h
+++ /dev/null
@@ -1,321 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-
-#ifndef __ASM_PARAVIRT_H
-#define __ASM_PARAVIRT_H
-
-#ifndef __ASSEMBLY__
-/******************************************************************************
- * fsys related addresses
- */
-struct pv_fsys_data {
-	unsigned long *fsyscall_table;
-	void *fsys_bubble_down;
-};
-
-extern struct pv_fsys_data pv_fsys_data;
-
-unsigned long *paravirt_get_fsyscall_table(void);
-char *paravirt_get_fsys_bubble_down(void);
-
-/******************************************************************************
- * patchlist addresses for gate page
- */
-enum pv_gate_patchlist {
-	PV_GATE_START_FSYSCALL,
-	PV_GATE_END_FSYSCALL,
-
-	PV_GATE_START_BRL_FSYS_BUBBLE_DOWN,
-	PV_GATE_END_BRL_FSYS_BUBBLE_DOWN,
-
-	PV_GATE_START_VTOP,
-	PV_GATE_END_VTOP,
-
-	PV_GATE_START_MCKINLEY_E9,
-	PV_GATE_END_MCKINLEY_E9,
-};
-
-struct pv_patchdata {
-	unsigned long start_fsyscall_patchlist;
-	unsigned long end_fsyscall_patchlist;
-	unsigned long start_brl_fsys_bubble_down_patchlist;
-	unsigned long end_brl_fsys_bubble_down_patchlist;
-	unsigned long start_vtop_patchlist;
-	unsigned long end_vtop_patchlist;
-	unsigned long start_mckinley_e9_patchlist;
-	unsigned long end_mckinley_e9_patchlist;
-
-	void *gate_section;
-};
-
-extern struct pv_patchdata pv_patchdata;
-
-unsigned long paravirt_get_gate_patchlist(enum pv_gate_patchlist type);
-void *paravirt_get_gate_section(void);
-#endif
-
-#ifdef CONFIG_PARAVIRT_GUEST
-
-#define PARAVIRT_HYPERVISOR_TYPE_DEFAULT	0
-
-#ifndef __ASSEMBLY__
-
-#include <asm/hw_irq.h>
-#include <asm/meminit.h>
-
-/******************************************************************************
- * general info
- */
-struct pv_info {
-	unsigned int kernel_rpl;
-	int paravirt_enabled;
-	const char *name;
-};
-
-extern struct pv_info pv_info;
-
-static inline int paravirt_enabled(void)
-{
-	return pv_info.paravirt_enabled;
-}
-
-static inline unsigned int get_kernel_rpl(void)
-{
-	return pv_info.kernel_rpl;
-}
-
-/******************************************************************************
- * initialization hooks.
- */
-struct rsvd_region;
-
-struct pv_init_ops {
-	void (*banner)(void);
-
-	int (*reserve_memory)(struct rsvd_region *region);
-
-	void (*arch_setup_early)(void);
-	void (*arch_setup_console)(char **cmdline_p);
-	int (*arch_setup_nomca)(void);
-
-	void (*post_smp_prepare_boot_cpu)(void);
-
-#ifdef ASM_SUPPORTED
-	unsigned long (*patch_bundle)(void *sbundle, void *ebundle,
-				      unsigned long type);
-	unsigned long (*patch_inst)(unsigned long stag, unsigned long etag,
-				    unsigned long type);
-#endif
-	void (*patch_branch)(unsigned long tag, unsigned long type);
-};
-
-extern struct pv_init_ops pv_init_ops;
-
-static inline void paravirt_banner(void)
-{
-	if (pv_init_ops.banner)
-		pv_init_ops.banner();
-}
-
-static inline int paravirt_reserve_memory(struct rsvd_region *region)
-{
-	if (pv_init_ops.reserve_memory)
-		return pv_init_ops.reserve_memory(region);
-	return 0;
-}
-
-static inline void paravirt_arch_setup_early(void)
-{
-	if (pv_init_ops.arch_setup_early)
-		pv_init_ops.arch_setup_early();
-}
-
-static inline void paravirt_arch_setup_console(char **cmdline_p)
-{
-	if (pv_init_ops.arch_setup_console)
-		pv_init_ops.arch_setup_console(cmdline_p);
-}
-
-static inline int paravirt_arch_setup_nomca(void)
-{
-	if (pv_init_ops.arch_setup_nomca)
-		return pv_init_ops.arch_setup_nomca();
-	return 0;
-}
-
-static inline void paravirt_post_smp_prepare_boot_cpu(void)
-{
-	if (pv_init_ops.post_smp_prepare_boot_cpu)
-		pv_init_ops.post_smp_prepare_boot_cpu();
-}
-
-/******************************************************************************
- * replacement of iosapic operations.
- */
-
-struct pv_iosapic_ops {
-	void (*pcat_compat_init)(void);
-
-	struct irq_chip *(*__get_irq_chip)(unsigned long trigger);
-
-	unsigned int (*__read)(char __iomem *iosapic, unsigned int reg);
-	void (*__write)(char __iomem *iosapic, unsigned int reg, u32 val);
-};
-
-extern struct pv_iosapic_ops pv_iosapic_ops;
-
-static inline void
-iosapic_pcat_compat_init(void)
-{
-	if (pv_iosapic_ops.pcat_compat_init)
-		pv_iosapic_ops.pcat_compat_init();
-}
-
-static inline struct irq_chip*
-iosapic_get_irq_chip(unsigned long trigger)
-{
-	return pv_iosapic_ops.__get_irq_chip(trigger);
-}
-
-static inline unsigned int
-__iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
-	return pv_iosapic_ops.__read(iosapic, reg);
-}
-
-static inline void
-__iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
-	return pv_iosapic_ops.__write(iosapic, reg, val);
-}
-
-/******************************************************************************
- * replacement of irq operations.
- */
-
-struct pv_irq_ops {
-	void (*register_ipi)(void);
-
-	int (*assign_irq_vector)(int irq);
-	void (*free_irq_vector)(int vector);
-
-	void (*register_percpu_irq)(ia64_vector vec,
-				    struct irqaction *action);
-
-	void (*resend_irq)(unsigned int vector);
-};
-
-extern struct pv_irq_ops pv_irq_ops;
-
-static inline void
-ia64_register_ipi(void)
-{
-	pv_irq_ops.register_ipi();
-}
-
-static inline int
-assign_irq_vector(int irq)
-{
-	return pv_irq_ops.assign_irq_vector(irq);
-}
-
-static inline void
-free_irq_vector(int vector)
-{
-	return pv_irq_ops.free_irq_vector(vector);
-}
-
-static inline void
-register_percpu_irq(ia64_vector vec, struct irqaction *action)
-{
-	pv_irq_ops.register_percpu_irq(vec, action);
-}
-
-static inline void
-ia64_resend_irq(unsigned int vector)
-{
-	pv_irq_ops.resend_irq(vector);
-}
-
-/******************************************************************************
- * replacement of time operations.
- */
-
-extern struct itc_jitter_data_t itc_jitter_data;
-extern volatile int time_keeper_id;
-
-struct pv_time_ops {
-	void (*init_missing_ticks_accounting)(int cpu);
-	int (*do_steal_accounting)(unsigned long *new_itm);
-
-	void (*clocksource_resume)(void);
-
-	unsigned long long (*sched_clock)(void);
-};
-
-extern struct pv_time_ops pv_time_ops;
-
-static inline void
-paravirt_init_missing_ticks_accounting(int cpu)
-{
-	if (pv_time_ops.init_missing_ticks_accounting)
-		pv_time_ops.init_missing_ticks_accounting(cpu);
-}
-
-struct static_key;
-extern struct static_key paravirt_steal_enabled;
-extern struct static_key paravirt_steal_rq_enabled;
-
-static inline int
-paravirt_do_steal_accounting(unsigned long *new_itm)
-{
-	return pv_time_ops.do_steal_accounting(new_itm);
-}
-
-static inline unsigned long long paravirt_sched_clock(void)
-{
-	return pv_time_ops.sched_clock();
-}
-
-#endif /* !__ASSEMBLY__ */
-
-#else
-/* fallback for native case */
-
-#ifndef __ASSEMBLY__
-
-#define paravirt_banner()				do { } while (0)
-#define paravirt_reserve_memory(region)			0
-
-#define paravirt_arch_setup_early()			do { } while (0)
-#define paravirt_arch_setup_console(cmdline_p)		do { } while (0)
-#define paravirt_arch_setup_nomca()			0
-#define paravirt_post_smp_prepare_boot_cpu()		do { } while (0)
-
-#define paravirt_init_missing_ticks_accounting(cpu)	do { } while (0)
-#define paravirt_do_steal_accounting(new_itm)		0
-
-#endif /* __ASSEMBLY__ */
-
-
-#endif /* CONFIG_PARAVIRT_GUEST */
-
-#endif /* __ASM_PARAVIRT_H */
diff --git a/arch/ia64/include/asm/paravirt_patch.h b/arch/ia64/include/asm/paravirt_patch.h
deleted file mode 100644
index 128ff5db6e67..000000000000
--- a/arch/ia64/include/asm/paravirt_patch.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef __ASM_PARAVIRT_PATCH_H
-#define __ASM_PARAVIRT_PATCH_H
-
-#ifdef __ASSEMBLY__
-
-	.section .paravirt_branches, "a"
-	.previous
-#define PARAVIRT_PATCH_SITE_BR(type)		\
-	{					\
-	[1:] ;					\
-	br.cond.sptk.many 2f ;			\
-	nop.b 0 ;				\
-	nop.b 0;; ;				\
-	} ;					\
-	2:					\
-	.xdata8 ".paravirt_branches", 1b, type
-
-#else
-
-#include <linux/stringify.h>
-#include <asm/intrinsics.h>
-
-/* for binary patch */
-struct paravirt_patch_site_bundle {
-	void		*sbundle;
-	void		*ebundle;
-	unsigned long	type;
-};
-
-/* label means the beginning of new bundle */
-#define paravirt_alt_bundle(instr, privop)				\
-	"\t998:\n"							\
-	"\t" instr "\n"							\
-	"\t999:\n"							\
-	"\t.pushsection .paravirt_bundles, \"a\"\n"			\
-	"\t.popsection\n"						\
-	"\t.xdata8 \".paravirt_bundles\", 998b, 999b, "			\
-	__stringify(privop) "\n"
-
-
-struct paravirt_patch_bundle_elem {
-	const void	*sbundle;
-	const void	*ebundle;
-	unsigned long	type;
-};
-
-
-struct paravirt_patch_site_inst {
-	unsigned long	stag;
-	unsigned long	etag;
-	unsigned long	type;
-};
-
-#define paravirt_alt_inst(instr, privop)				\
-	"\t[998:]\n"							\
-	"\t" instr "\n"							\
-	"\t[999:]\n"							\
-	"\t.pushsection .paravirt_insts, \"a\"\n"			\
-	"\t.popsection\n"						\
-	"\t.xdata8 \".paravirt_insts\", 998b, 999b, "			\
-	__stringify(privop) "\n"
-
-struct paravirt_patch_site_branch {
-	unsigned long	tag;
-	unsigned long	type;
-};
-
-struct paravirt_patch_branch_target {
-	const void	*entry;
-	unsigned long	type;
-};
-
-void
-__paravirt_patch_apply_branch(
-	unsigned long tag, unsigned long type,
-	const struct paravirt_patch_branch_target *entries,
-	unsigned int nr_entries);
-
-void
-paravirt_patch_reloc_br(unsigned long tag, const void *target);
-
-void
-paravirt_patch_reloc_brl(unsigned long tag, const void *target);
-
-
-#if defined(ASM_SUPPORTED) && defined(CONFIG_PARAVIRT)
-unsigned long
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
-
-unsigned long
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
-			      const struct paravirt_patch_bundle_elem *elems,
-			      unsigned long nelems,
-			      const struct paravirt_patch_bundle_elem **found);
-
-void
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
-			    const struct paravirt_patch_site_bundle *end);
-
-void
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
-			  const struct paravirt_patch_site_inst *end);
-
-void paravirt_patch_apply(void);
-#else
-#define paravirt_patch_apply_bundle(start, end)	do { } while (0)
-#define paravirt_patch_apply_inst(start, end)	do { } while (0)
-#define paravirt_patch_apply()			do { } while (0)
-#endif
-
-#endif /* !__ASSEMBLEY__ */
-
-#endif /* __ASM_PARAVIRT_PATCH_H */
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/include/asm/paravirt_privop.h b/arch/ia64/include/asm/paravirt_privop.h
deleted file mode 100644
index 8f6cb11c9fae..000000000000
--- a/arch/ia64/include/asm/paravirt_privop.h
+++ /dev/null
@@ -1,479 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef _ASM_IA64_PARAVIRT_PRIVOP_H
-#define _ASM_IA64_PARAVIRT_PRIVOP_H
-
-#ifdef CONFIG_PARAVIRT
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <asm/kregs.h> /* for IA64_PSR_I */
-
-/******************************************************************************
- * replacement of intrinsics operations.
- */
-
-struct pv_cpu_ops {
-	void (*fc)(void *addr);
-	unsigned long (*thash)(unsigned long addr);
-	unsigned long (*get_cpuid)(int index);
-	unsigned long (*get_pmd)(int index);
-	unsigned long (*getreg)(int reg);
-	void (*setreg)(int reg, unsigned long val);
-	void (*ptcga)(unsigned long addr, unsigned long size);
-	unsigned long (*get_rr)(unsigned long index);
-	void (*set_rr)(unsigned long index, unsigned long val);
-	void (*set_rr0_to_rr4)(unsigned long val0, unsigned long val1,
-			       unsigned long val2, unsigned long val3,
-			       unsigned long val4);
-	void (*ssm_i)(void);
-	void (*rsm_i)(void);
-	unsigned long (*get_psr_i)(void);
-	void (*intrin_local_irq_restore)(unsigned long flags);
-};
-
-extern struct pv_cpu_ops pv_cpu_ops;
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-extern unsigned long ia64_native_getreg_func(int regnum);
-
-/************************************************/
-/* Instructions paravirtualized for performance */
-/************************************************/
-
-#ifndef ASM_SUPPORTED
-#define paravirt_ssm_i()	pv_cpu_ops.ssm_i()
-#define paravirt_rsm_i()	pv_cpu_ops.rsm_i()
-#define __paravirt_getreg()	pv_cpu_ops.getreg()
-#endif
-
-/* mask for ia64_native_ssm/rsm() must be constant.("i" constraing).
- * static inline function doesn't satisfy it. */
-#define paravirt_ssm(mask)			\
-	do {					\
-		if ((mask) == IA64_PSR_I)	\
-			paravirt_ssm_i();	\
-		else				\
-			ia64_native_ssm(mask);	\
-	} while (0)
-
-#define paravirt_rsm(mask)			\
-	do {					\
-		if ((mask) == IA64_PSR_I)	\
-			paravirt_rsm_i();	\
-		else				\
-			ia64_native_rsm(mask);	\
-	} while (0)
-
-/* returned ip value should be the one in the caller,
- * not in __paravirt_getreg() */
-#define paravirt_getreg(reg)					\
-	({							\
-		unsigned long res;				\
-		if ((reg) == _IA64_REG_IP)			\
-			res = ia64_native_getreg(_IA64_REG_IP); \
-		else						\
-			res = __paravirt_getreg(reg);		\
-		res;						\
-	})
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-struct pv_cpu_asm_switch {
-	unsigned long switch_to;
-	unsigned long leave_syscall;
-	unsigned long work_processed_syscall;
-	unsigned long leave_kernel;
-};
-void paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch);
-
-#endif /* __ASSEMBLY__ */
-
-#define IA64_PARAVIRT_ASM_FUNC(name)	paravirt_ ## name
-
-#else
-
-/* fallback for native case */
-#define IA64_PARAVIRT_ASM_FUNC(name)	ia64_native_ ## name
-
-#endif /* CONFIG_PARAVIRT */
-
-#if defined(CONFIG_PARAVIRT) && defined(ASM_SUPPORTED)
-#define paravirt_dv_serialize_data()	ia64_dv_serialize_data()
-#else
-#define paravirt_dv_serialize_data()	/* nothing */
-#endif
-
-/* these routines utilize privilege-sensitive or performance-sensitive
- * privileged instructions so the code must be replaced with
- * paravirtualized versions */
-#define ia64_switch_to			IA64_PARAVIRT_ASM_FUNC(switch_to)
-#define ia64_leave_syscall		IA64_PARAVIRT_ASM_FUNC(leave_syscall)
-#define ia64_work_processed_syscall	\
-	IA64_PARAVIRT_ASM_FUNC(work_processed_syscall)
-#define ia64_leave_kernel		IA64_PARAVIRT_ASM_FUNC(leave_kernel)
-
-
-#if defined(CONFIG_PARAVIRT)
-/******************************************************************************
- * binary patching infrastructure
- */
-#define PARAVIRT_PATCH_TYPE_FC				1
-#define PARAVIRT_PATCH_TYPE_THASH			2
-#define PARAVIRT_PATCH_TYPE_GET_CPUID			3
-#define PARAVIRT_PATCH_TYPE_GET_PMD			4
-#define PARAVIRT_PATCH_TYPE_PTCGA			5
-#define PARAVIRT_PATCH_TYPE_GET_RR			6
-#define PARAVIRT_PATCH_TYPE_SET_RR			7
-#define PARAVIRT_PATCH_TYPE_SET_RR0_TO_RR4		8
-#define PARAVIRT_PATCH_TYPE_SSM_I			9
-#define PARAVIRT_PATCH_TYPE_RSM_I			10
-#define PARAVIRT_PATCH_TYPE_GET_PSR_I			11
-#define PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE	12
-
-/* PARAVIRT_PATY_TYPE_[GS]ETREG + _IA64_REG_xxx */
-#define PARAVIRT_PATCH_TYPE_GETREG			0x10000000
-#define PARAVIRT_PATCH_TYPE_SETREG			0x20000000
-
-/*
- * struct task_struct* (*ia64_switch_to)(void* next_task);
- * void *ia64_leave_syscall;
- * void *ia64_work_processed_syscall
- * void *ia64_leave_kernel;
- */
-
-#define PARAVIRT_PATCH_TYPE_BR_START			0x30000000
-#define PARAVIRT_PATCH_TYPE_BR_SWITCH_TO		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 0)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_SYSCALL		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 1)
-#define PARAVIRT_PATCH_TYPE_BR_WORK_PROCESSED_SYSCALL	\
-	(PARAVIRT_PATCH_TYPE_BR_START + 2)
-#define PARAVIRT_PATCH_TYPE_BR_LEAVE_KERNEL		\
-	(PARAVIRT_PATCH_TYPE_BR_START + 3)
-
-#ifdef ASM_SUPPORTED
-#include <asm/paravirt_patch.h>
-
-/*
- * pv_cpu_ops calling stub.
- * normal function call convension can't be written by gcc
- * inline assembly.
- *
- * from the caller's point of view,
- * the following registers will be clobbered.
- * r2, r3
- * r8-r15
- * r16, r17
- * b6, b7
- * p6-p15
- * ar.ccv
- *
- * from the callee's point of view ,
- * the following registers can be used.
- * r2, r3: scratch
- * r8: scratch, input argument0 and return value
- * r0-r15: scratch, input argument1-5
- * b6: return pointer
- * b7: scratch
- * p6-p15: scratch
- * ar.ccv: scratch
- *
- * other registers must not be changed. especially
- * b0: rp: preserved. gcc ignores b0 in clobbered register.
- * r16: saved gp
- */
-/* 5 bundles */
-#define __PARAVIRT_BR							\
-	";;\n"								\
-	"{ .mlx\n"							\
-	"nop 0\n"							\
-	"movl r2 = %[op_addr]\n"/* get function pointer address */	\
-	";;\n"								\
-	"}\n"								\
-	"1:\n"								\
-	"{ .mii\n"							\
-	"ld8 r2 = [r2]\n"	/* load function descriptor address */	\
-	"mov r17 = ip\n"	/* get ip to calc return address */	\
-	"mov r16 = gp\n"	/* save gp */				\
-	";;\n"								\
-	"}\n"								\
-	"{ .mii\n"							\
-	"ld8 r3 = [r2], 8\n"	/* load entry address */		\
-	"adds r17 =  1f - 1b, r17\n"	/* calculate return address */	\
-	";;\n"								\
-	"mov b7 = r3\n"		/* set entry address */			\
-	"}\n"								\
-	"{ .mib\n"							\
-	"ld8 gp = [r2]\n"	/* load gp value */			\
-	"mov b6 = r17\n"	/* set return address */		\
-	"br.cond.sptk.few b7\n"	/* intrinsics are very short isns */	\
-	"}\n"								\
-	"1:\n"								\
-	"{ .mii\n"							\
-	"mov gp = r16\n"	/* restore gp value */			\
-	"nop 0\n"							\
-	"nop 0\n"							\
-	";;\n"								\
-	"}\n"
-
-#define PARAVIRT_OP(op)				\
-	[op_addr] "i"(&pv_cpu_ops.op)
-
-#define PARAVIRT_TYPE(type)			\
-	PARAVIRT_PATCH_TYPE_ ## type
-
-#define PARAVIRT_REG_CLOBBERS0					\
-	"r2", "r3", /*"r8",*/ "r9", "r10", "r11", "r14",	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS1					\
-	"r2","r3", /*"r8",*/ "r9", "r10", "r11", "r14",		\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS2					\
-	"r2", "r3", /*"r8", "r9",*/ "r10", "r11", "r14",	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_REG_CLOBBERS5					\
-	"r2", "r3", /*"r8", "r9", "r10", "r11", "r14",*/	\
-		"r15", "r16", "r17"
-
-#define PARAVIRT_BR_CLOBBERS			\
-	"b6", "b7"
-
-#define PARAVIRT_PR_CLOBBERS						\
-	"p6", "p7", "p8", "p9", "p10", "p11", "p12", "p13", "p14", "p15"
-
-#define PARAVIRT_AR_CLOBBERS			\
-	"ar.ccv"
-
-#define PARAVIRT_CLOBBERS0			\
-		PARAVIRT_REG_CLOBBERS0,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS1			\
-		PARAVIRT_REG_CLOBBERS1,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS2			\
-		PARAVIRT_REG_CLOBBERS2,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_CLOBBERS5			\
-		PARAVIRT_REG_CLOBBERS5,		\
-		PARAVIRT_BR_CLOBBERS,		\
-		PARAVIRT_PR_CLOBBERS,		\
-		PARAVIRT_AR_CLOBBERS,		\
-		"memory"
-
-#define PARAVIRT_BR0(op, type)					\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op)				\
-		      : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR0_RET(op, type)				\
-	register unsigned long ia64_intri_res asm ("r8");	\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      : "=r"(ia64_intri_res)			\
-		      : PARAVIRT_OP(op)				\
-		      : PARAVIRT_CLOBBERS0)
-
-#define PARAVIRT_BR1(op, type, arg1)				\
-	register unsigned long __##arg1 asm ("r8") = arg1;	\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_RET(op, type, arg1)			\
-	register unsigned long ia64_intri_res asm ("r8");	\
-	register unsigned long __##arg1 asm ("r8") = arg1;	\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      : "=r"(ia64_intri_res)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR1_VOID(op, type, arg1)			\
-	register void *__##arg1 asm ("r8") = arg1;		\
-	register unsigned long ia64_clobber asm ("r8");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-					  PARAVIRT_TYPE(type))	\
-		      :	"=r"(ia64_clobber)			\
-		      : PARAVIRT_OP(op), "0"(__##arg1)		\
-		      : PARAVIRT_CLOBBERS1)
-
-#define PARAVIRT_BR2(op, type, arg1, arg2)				\
-	register unsigned long __##arg1 asm ("r8") = arg1;		\
-	register unsigned long __##arg2 asm ("r9") = arg2;		\
-	register unsigned long ia64_clobber1 asm ("r8");		\
-	register unsigned long ia64_clobber2 asm ("r9");		\
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,		\
-					  PARAVIRT_TYPE(type))		\
-		      : "=r"(ia64_clobber1), "=r"(ia64_clobber2)	\
-		      : PARAVIRT_OP(op), "0"(__##arg1), "1"(__##arg2)	\
-		      : PARAVIRT_CLOBBERS2)
-
-
-#define PARAVIRT_DEFINE_CPU_OP0(op, type)		\
-	static inline void				\
-	paravirt_ ## op (void)				\
-	{						\
-		PARAVIRT_BR0(op, type);			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP0_RET(op, type)		\
-	static inline unsigned long			\
-	paravirt_ ## op (void)				\
-	{						\
-		PARAVIRT_BR0_RET(op, type);		\
-		return ia64_intri_res;			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1_VOID(op, type)		\
-	static inline void				\
-	paravirt_ ## op (void *arg1)			\
-	{						\
-		PARAVIRT_BR1_VOID(op, type, arg1);	\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1(op, type)		\
-	static inline void				\
-	paravirt_ ## op (unsigned long arg1)		\
-	{						\
-		PARAVIRT_BR1(op, type, arg1);		\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP1_RET(op, type)		\
-	static inline unsigned long			\
-	paravirt_ ## op (unsigned long arg1)		\
-	{						\
-		PARAVIRT_BR1_RET(op, type, arg1);	\
-		return ia64_intri_res;			\
-	}
-
-#define PARAVIRT_DEFINE_CPU_OP2(op, type)		\
-	static inline void				\
-	paravirt_ ## op (unsigned long arg1,		\
-			 unsigned long arg2)		\
-	{						\
-		PARAVIRT_BR2(op, type, arg1, arg2);	\
-	}
-
-
-PARAVIRT_DEFINE_CPU_OP1_VOID(fc, FC);
-PARAVIRT_DEFINE_CPU_OP1_RET(thash, THASH)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_cpuid, GET_CPUID)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_pmd, GET_PMD)
-PARAVIRT_DEFINE_CPU_OP2(ptcga, PTCGA)
-PARAVIRT_DEFINE_CPU_OP1_RET(get_rr, GET_RR)
-PARAVIRT_DEFINE_CPU_OP2(set_rr, SET_RR)
-PARAVIRT_DEFINE_CPU_OP0(ssm_i, SSM_I)
-PARAVIRT_DEFINE_CPU_OP0(rsm_i, RSM_I)
-PARAVIRT_DEFINE_CPU_OP0_RET(get_psr_i, GET_PSR_I)
-PARAVIRT_DEFINE_CPU_OP1(intrin_local_irq_restore, INTRIN_LOCAL_IRQ_RESTORE)
-
-static inline void
-paravirt_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
-			unsigned long val2, unsigned long val3,
-			unsigned long val4)
-{
-	register unsigned long __val0 asm ("r8") = val0;
-	register unsigned long __val1 asm ("r9") = val1;
-	register unsigned long __val2 asm ("r10") = val2;
-	register unsigned long __val3 asm ("r11") = val3;
-	register unsigned long __val4 asm ("r14") = val4;
-
-	register unsigned long ia64_clobber0 asm ("r8");
-	register unsigned long ia64_clobber1 asm ("r9");
-	register unsigned long ia64_clobber2 asm ("r10");
-	register unsigned long ia64_clobber3 asm ("r11");
-	register unsigned long ia64_clobber4 asm ("r14");
-
-	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,
-					  PARAVIRT_TYPE(SET_RR0_TO_RR4))
-		      : "=r"(ia64_clobber0),
-			"=r"(ia64_clobber1),
-			"=r"(ia64_clobber2),
-			"=r"(ia64_clobber3),
-			"=r"(ia64_clobber4)
-		      : PARAVIRT_OP(set_rr0_to_rr4),
-			"0"(__val0), "1"(__val1), "2"(__val2),
-			"3"(__val3), "4"(__val4)
-		      : PARAVIRT_CLOBBERS5);
-}
-
-/* unsigned long paravirt_getreg(int reg) */
-#define __paravirt_getreg(reg)						\
-	({								\
-		register unsigned long ia64_intri_res asm ("r8");	\
-		register unsigned long __reg asm ("r8") = (reg);	\
-									\
-		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-						  PARAVIRT_TYPE(GETREG) \
-						  + (reg))		\
-			      : "=r"(ia64_intri_res)			\
-			      : PARAVIRT_OP(getreg), "0"(__reg)		\
-			      : PARAVIRT_CLOBBERS1);			\
-									\
-		ia64_intri_res;						\
-	})
-
-/* void paravirt_setreg(int reg, unsigned long val) */
-#define paravirt_setreg(reg, val)					\
-	do {								\
-		register unsigned long __val asm ("r8") = val;		\
-		register unsigned long __reg asm ("r9") = reg;		\
-		register unsigned long ia64_clobber1 asm ("r8");	\
-		register unsigned long ia64_clobber2 asm ("r9");	\
-									\
-		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
-						  PARAVIRT_TYPE(SETREG) \
-						  + (reg))		\
-			      : "=r"(ia64_clobber1),			\
-				"=r"(ia64_clobber2)			\
-			      : PARAVIRT_OP(setreg),			\
-				"1"(__reg), "0"(__val)			\
-			      : PARAVIRT_CLOBBERS2);			\
-	} while (0)
-
-#endif /* ASM_SUPPORTED */
-#endif /* CONFIG_PARAVIRT && ASM_SUPPOTED */
-
-#endif /* _ASM_IA64_PARAVIRT_PRIVOP_H */
diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h
index 0c0e25d6427a..36d2c1e3928b 100644
--- a/arch/ia64/include/asm/pci.h
+++ b/arch/ia64/include/asm/pci.h
@@ -52,25 +52,6 @@ extern unsigned long ia64_max_iommu_merge_mask;
 
 #include <asm-generic/pci-dma-compat.h>
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range (struct pci_dev *dev, struct vm_area_struct *vma,
 				enum pci_mmap_state mmap_state, int write_combine);
@@ -108,19 +89,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 	return (pci_domain_nr(bus) != 0);
 }
 
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 #define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 6437ca21f61b..3ad8f6988363 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -53,7 +53,7 @@ void build_cpu_to_node_map(void);
 #define topology_physical_package_id(cpu)	(cpu_data(cpu)->socket_id)
 #define topology_core_id(cpu)			(cpu_data(cpu)->core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h
index f35109b1d907..a0e3620f8f13 100644
--- a/arch/ia64/include/uapi/asm/cmpxchg.h
+++ b/arch/ia64/include/uapi/asm/cmpxchg.h
@@ -61,8 +61,6 @@ extern void ia64_xchg_called_with_bad_pointer(void);
  * indicated by comparing RETURN with OLD.
  */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * This function doesn't exist, so you'll get a linker error
  * if something tries to do an invalid cmpxchg().
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index d68b5cf81e31..3686d6abafde 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -9,7 +9,7 @@ endif
 extra-y	:= head.o init_task.o vmlinux.lds
 
 obj-y := entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o	\
-	 irq_lsapic.o ivt.o machvec.o pal.o paravirt_patchlist.o patch.o process.o perfmon.o ptrace.o sal.o		\
+	 irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o		\
 	 salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \
 	 unwind.o mca.o mca_asm.o topology.o dma-mapping.o
 
@@ -35,9 +35,6 @@ mca_recovery-y			+= mca_drv.o mca_drv_asm.o
 obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirtentry.o \
-				   paravirt_patch.o
-
 obj-$(CONFIG_IA64_ESI)		+= esi.o
 ifneq ($(CONFIG_IA64_ESI),)
 obj-y				+= esi_stub.o	# must be in kernel proper
@@ -52,8 +49,6 @@ CFLAGS_traps.o  += -mfixed-range=f2-f5,f16-f31
 
 # The gate DSO image is built using a special linker script.
 include $(src)/Makefile.gate
-# tell compiled for native
-CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_NATIVE
 
 # Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
 define sed-y
@@ -84,30 +79,3 @@ arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
 include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
 	$(Q)mkdir -p $(dir $@)
 	$(call cmd,nr_irqs)
-
-#
-# native ivt.S, entry.S and fsys.S
-#
-ASM_PARAVIRT_OBJS = ivt.o entry.o fsys.o
-define paravirtualized_native
-AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
-AFLAGS_pvchk-sed-$(1) += -D__IA64_ASM_PARAVIRTUALIZED_PVCHECK
-extra-y += pvchk-$(1)
-endef
-$(foreach obj,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_native,$(obj))))
-
-#
-# Checker for paravirtualizations of privileged operations.
-#
-quiet_cmd_pv_check_sed = PVCHK   $@
-define cmd_pv_check_sed
-	sed -f $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed $< > $@
-endef
-
-$(obj)/pvchk-sed-%.s: $(src)/%.S $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed FORCE
-	$(call if_changed_dep,as_s_S)
-$(obj)/pvchk-%.s: $(obj)/pvchk-sed-%.s FORCE
-	$(call if_changed,pv_check_sed)
-$(obj)/pvchk-%.o: $(obj)/pvchk-%.s FORCE
-	$(call if_changed,as_o_S)
-.PRECIOUS: $(obj)/pvchk-sed-%.s $(obj)/pvchk-%.s $(obj)/pvchk-%.o
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c52d7540dc05..47e962f7ed5a 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -464,7 +464,6 @@ efi_map_pal_code (void)
 		 GRANULEROUNDDOWN((unsigned long) pal_vaddr),
 		 pte_val(pfn_pte(__pa(pal_vaddr) >> PAGE_SHIFT, PAGE_KERNEL)),
 		 IA64_GRANULE_SHIFT);
-	paravirt_dv_serialize_data();
 	ia64_set_psr(psr);		/* restore psr */
 }
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index fcf8b8cbca0b..ae0de7bf5525 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -51,7 +51,6 @@
 
 #include "minstate.h"
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 	/*
 	 * execve() is special because in case of success, we need to
 	 * setup a null register window frame.
@@ -161,7 +160,6 @@ GLOBAL_ENTRY(sys_clone)
 	mov rp=loc0
 	br.ret.sptk.many rp
 END(sys_clone)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 /*
  * prev_task <- ia64_switch_to(struct task_struct *next)
@@ -169,7 +167,7 @@ END(sys_clone)
  *	called.  The code starting at .map relies on this.  The rest of the code
  *	doesn't care about the interrupt masking status.
  */
-GLOBAL_ENTRY(__paravirt_switch_to)
+GLOBAL_ENTRY(ia64_switch_to)
 	.prologue
 	alloc r16=ar.pfs,1,0,0,0
 	DO_SAVE_SWITCH_STACK
@@ -221,9 +219,8 @@ GLOBAL_ENTRY(__paravirt_switch_to)
 	itr.d dtr[r25]=r23		// wire in new mapping...
 	SSM_PSR_IC_AND_SRLZ_D(r8, r9)	// reenable the psr.ic bit
 	br.cond.sptk .done
-END(__paravirt_switch_to)
+END(ia64_switch_to)
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 /*
  * Note that interrupts are enabled during save_switch_stack and load_switch_stack.  This
  * means that we may get an interrupt with "sp" pointing to the new kernel stack while
@@ -639,16 +636,8 @@ GLOBAL_ENTRY(ia64_ret_from_syscall)
 	adds r2=PT(R8)+16,sp			// r2 = &pt_regs.r8
 	mov r10=r0				// clear error indication in r10
 (p7)	br.cond.spnt handle_syscall_error	// handle potential syscall failure
-#ifdef CONFIG_PARAVIRT
-	;;
-	br.cond.sptk.few ia64_leave_syscall
-	;;
-#endif /* CONFIG_PARAVIRT */
 END(ia64_ret_from_syscall)
-#ifndef CONFIG_PARAVIRT
 	// fall through
-#endif
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 /*
  * ia64_leave_syscall(): Same as ia64_leave_kernel, except that it doesn't
@@ -694,7 +683,7 @@ END(ia64_ret_from_syscall)
  *	      ar.csd: cleared
  *	      ar.ssd: cleared
  */
-GLOBAL_ENTRY(__paravirt_leave_syscall)
+GLOBAL_ENTRY(ia64_leave_syscall)
 	PT_REGS_UNWIND_INFO(0)
 	/*
 	 * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -722,8 +711,8 @@ GLOBAL_ENTRY(__paravirt_leave_syscall)
 	cmp.eq pLvSys,p0=r0,r0		// pLvSys=1: leave from syscall
 (pUStk)	cmp.eq.unc p6,p0=r0,r0		// p6 <- pUStk
 #endif
-.global __paravirt_work_processed_syscall;
-__paravirt_work_processed_syscall:
+.global ia64_work_processed_syscall;
+ia64_work_processed_syscall:
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	adds r2=PT(LOADRS)+16,r12
 	MOV_FROM_ITC(pUStk, p9, r22, r19)	// fetch time at leave
@@ -836,9 +825,9 @@ __paravirt_work_processed_syscall:
 	mov.m ar.ssd=r0			// M2   clear ar.ssd
 	mov f11=f0			// F    clear f11
 	br.cond.sptk.many rbs_switch	// B
-END(__paravirt_leave_syscall)
+END(ia64_leave_syscall)
 
-GLOBAL_ENTRY(__paravirt_leave_kernel)
+GLOBAL_ENTRY(ia64_leave_kernel)
 	PT_REGS_UNWIND_INFO(0)
 	/*
 	 * work.need_resched etc. mustn't get changed by this CPU before it returns to
@@ -1171,26 +1160,25 @@ skip_rbs_switch:
 (p6)	br.cond.sptk.few .notify
 	br.call.spnt.many rp=preempt_schedule_irq
 .ret9:	cmp.eq p6,p0=r0,r0	// p6 <- 1 (re-check)
-(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few  ia64_work_pending_syscall_end
 	br.cond.sptk.many .work_processed_kernel
 
 .notify:
 (pUStk)	br.call.spnt.many rp=notify_resume_user
 .ret10:	cmp.ne p6,p0=r0,r0	// p6 <- 0 (don't re-check)
-(pLvSys)br.cond.sptk.few  __paravirt_pending_syscall_end
+(pLvSys)br.cond.sptk.few  ia64_work_pending_syscall_end
 	br.cond.sptk.many .work_processed_kernel
 
-.global __paravirt_pending_syscall_end;
-__paravirt_pending_syscall_end:
+.global ia64_work_pending_syscall_end;
+ia64_work_pending_syscall_end:
 	adds r2=PT(R8)+16,r12
 	adds r3=PT(R10)+16,r12
 	;;
 	ld8 r8=[r2]
 	ld8 r10=[r3]
-	br.cond.sptk.many __paravirt_work_processed_syscall_target
-END(__paravirt_leave_kernel)
+	br.cond.sptk.many ia64_work_processed_syscall
+END(ia64_leave_kernel)
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 ENTRY(handle_syscall_error)
 	/*
 	 * Some system calls (e.g., ptrace, mmap) can return arbitrary values which could
@@ -1294,7 +1282,7 @@ ENTRY(sys_rt_sigreturn)
 	adds sp=16,sp
 	;;
 	ld8 r9=[sp]				// load new ar.unat
-	mov.sptk b7=r8,ia64_native_leave_kernel
+	mov.sptk b7=r8,ia64_leave_kernel
 	;;
 	mov ar.unat=r9
 	br.many b7
@@ -1782,4 +1770,3 @@ sys_call_table:
 	data8 sys_execveat
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index abc6dee3799c..edbf7af95849 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -24,7 +24,7 @@
 #include <asm/unistd.h>
 
 #include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 /*
  * See Documentation/ia64/fsys.txt for details on fsyscalls.
@@ -402,7 +402,7 @@ ENTRY(fsys_fallback_syscall)
 	mov r26=ar.pfs
 END(fsys_fallback_syscall)
 	/* FALL THROUGH */
-GLOBAL_ENTRY(paravirt_fsys_bubble_down)
+GLOBAL_ENTRY(fsys_bubble_down)
 	.prologue
 	.altrp b6
 	.body
@@ -440,7 +440,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	 *
 	 * PSR.BE : already is turned off in __kernel_syscall_via_epc()
 	 * PSR.AC : don't care (kernel normally turns PSR.AC on)
-	 * PSR.I  : already turned off by the time paravirt_fsys_bubble_down gets
+	 * PSR.I  : already turned off by the time fsys_bubble_down gets
 	 *	    invoked
 	 * PSR.DFL: always 0 (kernel never turns it on)
 	 * PSR.DFH: don't care --- kernel never touches f32-f127 on its own
@@ -450,7 +450,7 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	 * PSR.DB : don't care --- kernel never enables kernel-level
 	 *	    breakpoints
 	 * PSR.TB : must be 0 already; if it wasn't zero on entry to
-	 *          __kernel_syscall_via_epc, the branch to paravirt_fsys_bubble_down
+	 *          __kernel_syscall_via_epc, the branch to fsys_bubble_down
 	 *          will trigger a taken branch; the taken-trap-handler then
 	 *          converts the syscall into a break-based system-call.
 	 */
@@ -541,14 +541,14 @@ GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	nop.m 0
 (p8)	br.call.sptk.many b6=b6			// B    (ignore return address)
 	br.cond.spnt ia64_trace_syscall		// B
-END(paravirt_fsys_bubble_down)
+END(fsys_bubble_down)
 
 	.rodata
 	.align 8
-	.globl paravirt_fsyscall_table
+	.globl fsyscall_table
 
-	data8 paravirt_fsys_bubble_down
-paravirt_fsyscall_table:
+	data8 fsys_bubble_down
+fsyscall_table:
 	data8 fsys_ni_syscall
 	data8 0				// exit			// 1025
 	data8 0				// read
@@ -833,4 +833,4 @@ paravirt_fsyscall_table:
 
 	// fill in zeros for the remaining entries
 	.zero:
-	.space paravirt_fsyscall_table + 8*NR_syscalls - .zero, 0
+	.space fsyscall_table + 8*NR_syscalls - .zero, 0
diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S
index b5f8bdd8618e..0bd1b3bfaf1c 100644
--- a/arch/ia64/kernel/gate.S
+++ b/arch/ia64/kernel/gate.S
@@ -14,7 +14,7 @@
 #include <asm/unistd.h>
 #include <asm/kregs.h>
 #include <asm/page.h>
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 /*
  * We can't easily refer to symbols inside the kernel.  To avoid full runtime relocation,
@@ -376,11 +376,4 @@ GLOBAL_ENTRY(__kernel_syscall_via_epc)
 (p9)	mov r8=ENOSYS
 	FSYS_RETURN
 
-#ifdef CONFIG_PARAVIRT
-	/*
-	 * padd to make the size of this symbol constant
-	 * independent of paravirtualization.
-	 */
-	.align PAGE_SIZE / 8
-#endif
 END(__kernel_syscall_via_epc)
diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S
index e518f7902af6..3e8271e85a1e 100644
--- a/arch/ia64/kernel/gate.lds.S
+++ b/arch/ia64/kernel/gate.lds.S
@@ -6,7 +6,6 @@
  */
 
 #include <asm/page.h>
-#include "paravirt_patchlist.h"
 
 SECTIONS
 {
@@ -33,21 +32,21 @@ SECTIONS
 	. = GATE_ADDR + 0x600;
 
 	.data..patch		: {
-		__paravirt_start_gate_mckinley_e9_patchlist = .;
+		__start_gate_mckinley_e9_patchlist = .;
 		*(.data..patch.mckinley_e9)
-		__paravirt_end_gate_mckinley_e9_patchlist = .;
+		__end_gate_mckinley_e9_patchlist = .;
 
-		__paravirt_start_gate_vtop_patchlist = .;
+		__start_gate_vtop_patchlist = .;
 		*(.data..patch.vtop)
-		__paravirt_end_gate_vtop_patchlist = .;
+		__end_gate_vtop_patchlist = .;
 
-		__paravirt_start_gate_fsyscall_patchlist = .;
+		__start_gate_fsyscall_patchlist = .;
 		*(.data..patch.fsyscall_table)
-		__paravirt_end_gate_fsyscall_patchlist = .;
+		__end_gate_fsyscall_patchlist = .;
 
-		__paravirt_start_gate_brl_fsys_bubble_down_patchlist = .;
+		__start_gate_brl_fsys_bubble_down_patchlist = .;
 		*(.data..patch.brl_fsys_bubble_down)
-		__paravirt_end_gate_brl_fsys_bubble_down_patchlist = .;
+		__end_gate_brl_fsys_bubble_down_patchlist = .;
 	}						:readable
 
 	.IA_64.unwind_info	: { *(.IA_64.unwind_info*) }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index a4acddad0c78..bb748c596443 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -26,7 +26,6 @@
 #include <asm/mmu_context.h>
 #include <asm/asm-offsets.h>
 #include <asm/pal.h>
-#include <asm/paravirt.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
@@ -394,41 +393,6 @@ start_ap:
 	;;
 (isBP)	st8 [r2]=r28		// save the address of the boot param area passed by the bootloader
 
-#ifdef CONFIG_PARAVIRT
-
-	movl r14=hypervisor_setup_hooks
-	movl r15=hypervisor_type
-	mov r16=num_hypervisor_hooks
-	;;
-	ld8 r2=[r15]
-	;;
-	cmp.ltu p7,p0=r2,r16	// array size check
-	shladd r8=r2,3,r14
-	;;
-(p7)	ld8 r9=[r8]
-	;;
-(p7)	mov b1=r9
-(p7)	cmp.ne.unc p7,p0=r9,r0	// no actual branch to NULL
-	;;
-(p7)	br.call.sptk.many rp=b1
-
-	__INITDATA
-
-default_setup_hook = 0		// Currently nothing needs to be done.
-
-	.global hypervisor_type
-hypervisor_type:
-	data8		PARAVIRT_HYPERVISOR_TYPE_DEFAULT
-
-	// must have the same order with PARAVIRT_HYPERVISOR_TYPE_xxx
-
-hypervisor_setup_hooks:
-	data8		default_setup_hook
-num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8
-	.previous
-
-#endif
-
 #ifdef CONFIG_SMP
 (isAP)	br.call.sptk.many rp=start_secondary
 .ret0:
@@ -1063,12 +1027,6 @@ GLOBAL_ENTRY(ia64_native_sched_clock)
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
 END(ia64_native_sched_clock)
-#ifndef CONFIG_PARAVIRT
-	//unsigned long long
-	//sched_clock(void) __attribute__((alias("ia64_native_sched_clock")));
-	.global sched_clock
-sched_clock = ia64_native_sched_clock
-#endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 GLOBAL_ENTRY(cycle_to_cputime)
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index e42bf7a913f3..b1c3cfc93e71 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -937,7 +937,6 @@ END(interrupt)
 	 *	- ar.fpsr: set to kernel settings
 	 *	-  b6: preserved (same as on entry)
 	 */
-#ifdef __IA64_ASM_PARAVIRTUALIZED_NATIVE
 GLOBAL_ENTRY(ia64_syscall_setup)
 #if PT(B6) != 0
 # error This code assumes that b6 is the first field in pt_regs.
@@ -1029,7 +1028,6 @@ GLOBAL_ENTRY(ia64_syscall_setup)
 (p10)	mov r8=-EINVAL
 	br.ret.sptk.many b7
 END(ia64_syscall_setup)
-#endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
 
 	.org ia64_ivt+0x3c00
 /////////////////////////////////////////////////////////////////////////////////////////
@@ -1043,7 +1041,7 @@ END(ia64_syscall_setup)
 	DBG_FAULT(16)
 	FAULT(16)
 
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(__IA64_ASM_PARAVIRTUALIZED_NATIVE)
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
 	/*
 	 * There is no particular reason for this code to be here, other than
 	 * that there happens to be space here that would go unused otherwise.
diff --git a/arch/ia64/kernel/minstate.h b/arch/ia64/kernel/minstate.h
index cc82a7d744c9..5704700fb703 100644
--- a/arch/ia64/kernel/minstate.h
+++ b/arch/ia64/kernel/minstate.h
@@ -2,7 +2,7 @@
 #include <asm/cache.h>
 
 #include "entry.h"
-#include "paravirt_inst.h"
+#include <asm/native/inst.h>
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /* read ar.itc in advance, and use it before leaving bank 0 */
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 29754aae5177..b15933c31b2f 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -439,14 +439,6 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings,
 			mod->arch.opd = s;
 		else if (strcmp(".IA_64.unwind", secstrings + s->sh_name) == 0)
 			mod->arch.unwind = s;
-#ifdef CONFIG_PARAVIRT
-		else if (strcmp(".paravirt_bundles",
-				secstrings + s->sh_name) == 0)
-			mod->arch.paravirt_bundles = s;
-		else if (strcmp(".paravirt_insts",
-				secstrings + s->sh_name) == 0)
-			mod->arch.paravirt_insts = s;
-#endif
 
 	if (!mod->arch.core_plt || !mod->arch.init_plt || !mod->arch.got || !mod->arch.opd) {
 		printk(KERN_ERR "%s: sections missing\n", mod->name);
@@ -914,30 +906,6 @@ module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mo
 	DEBUGP("%s: init: entry=%p\n", __func__, mod->init);
 	if (mod->arch.unwind)
 		register_unwind_table(mod);
-#ifdef CONFIG_PARAVIRT
-        if (mod->arch.paravirt_bundles) {
-                struct paravirt_patch_site_bundle *start =
-                        (struct paravirt_patch_site_bundle *)
-                        mod->arch.paravirt_bundles->sh_addr;
-                struct paravirt_patch_site_bundle *end =
-                        (struct paravirt_patch_site_bundle *)
-                        (mod->arch.paravirt_bundles->sh_addr +
-                         mod->arch.paravirt_bundles->sh_size);
-
-                paravirt_patch_apply_bundle(start, end);
-        }
-        if (mod->arch.paravirt_insts) {
-                struct paravirt_patch_site_inst *start =
-                        (struct paravirt_patch_site_inst *)
-                        mod->arch.paravirt_insts->sh_addr;
-                struct paravirt_patch_site_inst *end =
-                        (struct paravirt_patch_site_inst *)
-                        (mod->arch.paravirt_insts->sh_addr +
-                         mod->arch.paravirt_insts->sh_size);
-
-                paravirt_patch_apply_inst(start, end);
-        }
-#endif
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 9dd7464f8c17..d70bf15c690a 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -165,7 +165,7 @@ static struct irq_chip dmar_msi_type = {
 	.irq_retrigger = ia64_msi_retrigger_irq,
 };
 
-static int
+static void
 msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
@@ -186,21 +186,29 @@ msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 		MSI_DATA_LEVEL_ASSERT |
 		MSI_DATA_DELIVERY_FIXED |
 		MSI_DATA_VECTOR(cfg->vector);
-	return 0;
 }
 
-int arch_setup_dmar_msi(unsigned int irq)
+int dmar_alloc_hwirq(int id, int node, void *arg)
 {
-	int ret;
+	int irq;
 	struct msi_msg msg;
 
-	ret = msi_compose_msg(NULL, irq, &msg);
-	if (ret < 0)
-		return ret;
-	dmar_msi_write(irq, &msg);
-	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-				      "edge");
-	return 0;
+	irq = create_irq();
+	if (irq > 0) {
+		irq_set_handler_data(irq, arg);
+		irq_set_chip_and_handler_name(irq, &dmar_msi_type,
+					      handle_edge_irq, "edge");
+		msi_compose_msg(NULL, irq, &msg);
+		dmar_msi_write(irq, &msg);
+	}
+
+	return irq;
+}
+
+void dmar_free_hwirq(int irq)
+{
+	irq_set_handler_data(irq, NULL);
+	destroy_irq(irq);
 }
 #endif /* CONFIG_INTEL_IOMMU */
 
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
deleted file mode 100644
index 1b22f6de2932..000000000000
--- a/arch/ia64/kernel/paravirt.c
+++ /dev/null
@@ -1,902 +0,0 @@
-/******************************************************************************
- * arch/ia64/kernel/paravirt.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *     Yaozu (Eddie) Dong <eddie.dong@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-
-#include <linux/compiler.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/types.h>
-
-#include <asm/iosapic.h>
-#include <asm/paravirt.h>
-
-/***************************************************************************
- * general info
- */
-struct pv_info pv_info = {
-	.kernel_rpl = 0,
-	.paravirt_enabled = 0,
-	.name = "bare hardware"
-};
-
-/***************************************************************************
- * pv_init_ops
- * initialization hooks.
- */
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type);
-
-struct pv_init_ops pv_init_ops =
-{
-#ifdef ASM_SUPPORTED
-	.patch_bundle = ia64_native_patch_bundle,
-#endif
-	.patch_branch = ia64_native_patch_branch,
-};
-
-/***************************************************************************
- * pv_cpu_ops
- * intrinsics hooks.
- */
-
-#ifndef ASM_SUPPORTED
-/* ia64_native_xxx are macros so that we have to make them real functions */
-
-#define DEFINE_VOID_FUNC1(name)					\
-	static void						\
-	ia64_native_ ## name ## _func(unsigned long arg)	\
-	{							\
-		ia64_native_ ## name(arg);			\
-	}
-
-#define DEFINE_VOID_FUNC1_VOID(name)				\
-	static void						\
-	ia64_native_ ## name ## _func(void *arg)		\
-	{							\
-		ia64_native_ ## name(arg);			\
-	}
-
-#define DEFINE_VOID_FUNC2(name)					\
-	static void						\
-	ia64_native_ ## name ## _func(unsigned long arg0,	\
-				      unsigned long arg1)	\
-	{							\
-		ia64_native_ ## name(arg0, arg1);		\
-	}
-
-#define DEFINE_FUNC0(name)			\
-	static unsigned long			\
-	ia64_native_ ## name ## _func(void)	\
-	{					\
-		return ia64_native_ ## name();	\
-	}
-
-#define DEFINE_FUNC1(name, type)			\
-	static unsigned long				\
-	ia64_native_ ## name ## _func(type arg)		\
-	{						\
-		return ia64_native_ ## name(arg);	\
-	}						\
-
-DEFINE_VOID_FUNC1_VOID(fc);
-DEFINE_VOID_FUNC1(intrin_local_irq_restore);
-
-DEFINE_VOID_FUNC2(ptcga);
-DEFINE_VOID_FUNC2(set_rr);
-
-DEFINE_FUNC0(get_psr_i);
-
-DEFINE_FUNC1(thash, unsigned long);
-DEFINE_FUNC1(get_cpuid, int);
-DEFINE_FUNC1(get_pmd, int);
-DEFINE_FUNC1(get_rr, unsigned long);
-
-static void
-ia64_native_ssm_i_func(void)
-{
-	ia64_native_ssm(IA64_PSR_I);
-}
-
-static void
-ia64_native_rsm_i_func(void)
-{
-	ia64_native_rsm(IA64_PSR_I);
-}
-
-static void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
-				unsigned long val2, unsigned long val3,
-				unsigned long val4)
-{
-	ia64_native_set_rr0_to_rr4(val0, val1, val2, val3, val4);
-}
-
-#define CASE_GET_REG(id)				\
-	case _IA64_REG_ ## id:				\
-	res = ia64_native_getreg(_IA64_REG_ ## id);	\
-	break;
-#define CASE_GET_AR(id) CASE_GET_REG(AR_ ## id)
-#define CASE_GET_CR(id) CASE_GET_REG(CR_ ## id)
-
-unsigned long
-ia64_native_getreg_func(int regnum)
-{
-	unsigned long res = -1;
-	switch (regnum) {
-	CASE_GET_REG(GP);
-	/*CASE_GET_REG(IP);*/ /* returned ip value shouldn't be constant */
-	CASE_GET_REG(PSR);
-	CASE_GET_REG(TP);
-	CASE_GET_REG(SP);
-
-	CASE_GET_AR(KR0);
-	CASE_GET_AR(KR1);
-	CASE_GET_AR(KR2);
-	CASE_GET_AR(KR3);
-	CASE_GET_AR(KR4);
-	CASE_GET_AR(KR5);
-	CASE_GET_AR(KR6);
-	CASE_GET_AR(KR7);
-	CASE_GET_AR(RSC);
-	CASE_GET_AR(BSP);
-	CASE_GET_AR(BSPSTORE);
-	CASE_GET_AR(RNAT);
-	CASE_GET_AR(FCR);
-	CASE_GET_AR(EFLAG);
-	CASE_GET_AR(CSD);
-	CASE_GET_AR(SSD);
-	CASE_GET_AR(CFLAG);
-	CASE_GET_AR(FSR);
-	CASE_GET_AR(FIR);
-	CASE_GET_AR(FDR);
-	CASE_GET_AR(CCV);
-	CASE_GET_AR(UNAT);
-	CASE_GET_AR(FPSR);
-	CASE_GET_AR(ITC);
-	CASE_GET_AR(PFS);
-	CASE_GET_AR(LC);
-	CASE_GET_AR(EC);
-
-	CASE_GET_CR(DCR);
-	CASE_GET_CR(ITM);
-	CASE_GET_CR(IVA);
-	CASE_GET_CR(PTA);
-	CASE_GET_CR(IPSR);
-	CASE_GET_CR(ISR);
-	CASE_GET_CR(IIP);
-	CASE_GET_CR(IFA);
-	CASE_GET_CR(ITIR);
-	CASE_GET_CR(IIPA);
-	CASE_GET_CR(IFS);
-	CASE_GET_CR(IIM);
-	CASE_GET_CR(IHA);
-	CASE_GET_CR(LID);
-	CASE_GET_CR(IVR);
-	CASE_GET_CR(TPR);
-	CASE_GET_CR(EOI);
-	CASE_GET_CR(IRR0);
-	CASE_GET_CR(IRR1);
-	CASE_GET_CR(IRR2);
-	CASE_GET_CR(IRR3);
-	CASE_GET_CR(ITV);
-	CASE_GET_CR(PMV);
-	CASE_GET_CR(CMCV);
-	CASE_GET_CR(LRR0);
-	CASE_GET_CR(LRR1);
-
-	default:
-		printk(KERN_CRIT "wrong_getreg %d\n", regnum);
-		break;
-	}
-	return res;
-}
-
-#define CASE_SET_REG(id)				\
-	case _IA64_REG_ ## id:				\
-	ia64_native_setreg(_IA64_REG_ ## id, val);	\
-	break;
-#define CASE_SET_AR(id) CASE_SET_REG(AR_ ## id)
-#define CASE_SET_CR(id) CASE_SET_REG(CR_ ## id)
-
-void
-ia64_native_setreg_func(int regnum, unsigned long val)
-{
-	switch (regnum) {
-	case _IA64_REG_PSR_L:
-		ia64_native_setreg(_IA64_REG_PSR_L, val);
-		ia64_dv_serialize_data();
-		break;
-	CASE_SET_REG(SP);
-	CASE_SET_REG(GP);
-
-	CASE_SET_AR(KR0);
-	CASE_SET_AR(KR1);
-	CASE_SET_AR(KR2);
-	CASE_SET_AR(KR3);
-	CASE_SET_AR(KR4);
-	CASE_SET_AR(KR5);
-	CASE_SET_AR(KR6);
-	CASE_SET_AR(KR7);
-	CASE_SET_AR(RSC);
-	CASE_SET_AR(BSP);
-	CASE_SET_AR(BSPSTORE);
-	CASE_SET_AR(RNAT);
-	CASE_SET_AR(FCR);
-	CASE_SET_AR(EFLAG);
-	CASE_SET_AR(CSD);
-	CASE_SET_AR(SSD);
-	CASE_SET_AR(CFLAG);
-	CASE_SET_AR(FSR);
-	CASE_SET_AR(FIR);
-	CASE_SET_AR(FDR);
-	CASE_SET_AR(CCV);
-	CASE_SET_AR(UNAT);
-	CASE_SET_AR(FPSR);
-	CASE_SET_AR(ITC);
-	CASE_SET_AR(PFS);
-	CASE_SET_AR(LC);
-	CASE_SET_AR(EC);
-
-	CASE_SET_CR(DCR);
-	CASE_SET_CR(ITM);
-	CASE_SET_CR(IVA);
-	CASE_SET_CR(PTA);
-	CASE_SET_CR(IPSR);
-	CASE_SET_CR(ISR);
-	CASE_SET_CR(IIP);
-	CASE_SET_CR(IFA);
-	CASE_SET_CR(ITIR);
-	CASE_SET_CR(IIPA);
-	CASE_SET_CR(IFS);
-	CASE_SET_CR(IIM);
-	CASE_SET_CR(IHA);
-	CASE_SET_CR(LID);
-	CASE_SET_CR(IVR);
-	CASE_SET_CR(TPR);
-	CASE_SET_CR(EOI);
-	CASE_SET_CR(IRR0);
-	CASE_SET_CR(IRR1);
-	CASE_SET_CR(IRR2);
-	CASE_SET_CR(IRR3);
-	CASE_SET_CR(ITV);
-	CASE_SET_CR(PMV);
-	CASE_SET_CR(CMCV);
-	CASE_SET_CR(LRR0);
-	CASE_SET_CR(LRR1);
-	default:
-		printk(KERN_CRIT "wrong setreg %d\n", regnum);
-		break;
-	}
-}
-#else
-
-#define __DEFINE_FUNC(name, code)					\
-	extern const char ia64_native_ ## name ## _direct_start[];	\
-	extern const char ia64_native_ ## name ## _direct_end[];	\
-	asm (".align 32\n"						\
-	     ".proc ia64_native_" #name "_func\n"			\
-	     "ia64_native_" #name "_func:\n"				\
-	     "ia64_native_" #name "_direct_start:\n"			\
-	     code							\
-	     "ia64_native_" #name "_direct_end:\n"			\
-	     "br.cond.sptk.many b6\n"					\
-	     ".endp ia64_native_" #name "_func\n")
-
-#define DEFINE_VOID_FUNC0(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(void);			\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(unsigned long arg);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1_VOID(name, code)			\
-	extern void						\
-	ia64_native_ ## name ## _func(void *arg);		\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC2(name, code)				\
-	extern void						\
-	ia64_native_ ## name ## _func(unsigned long arg0,	\
-				      unsigned long arg1);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC0(name, code)		\
-	extern unsigned long			\
-	ia64_native_ ## name ## _func(void);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC1(name, type, code)			\
-	extern unsigned long				\
-	ia64_native_ ## name ## _func(type arg);	\
-	__DEFINE_FUNC(name, code)
-
-DEFINE_VOID_FUNC1_VOID(fc,
-		       "fc r8\n");
-DEFINE_VOID_FUNC1(intrin_local_irq_restore,
-		  ";;\n"
-		  "     cmp.ne p6, p7 = r8, r0\n"
-		  ";;\n"
-		  "(p6) ssm psr.i\n"
-		  "(p7) rsm psr.i\n"
-		  ";;\n"
-		  "(p6) srlz.d\n");
-
-DEFINE_VOID_FUNC2(ptcga,
-		  "ptc.ga r8, r9\n");
-DEFINE_VOID_FUNC2(set_rr,
-		  "mov rr[r8] = r9\n");
-
-/* ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I */
-DEFINE_FUNC0(get_psr_i,
-	     "mov r2 = " __stringify(1 << IA64_PSR_I_BIT) "\n"
-	     "mov r8 = psr\n"
-	     ";;\n"
-	     "and r8 = r2, r8\n");
-
-DEFINE_FUNC1(thash, unsigned long,
-	     "thash r8 = r8\n");
-DEFINE_FUNC1(get_cpuid, int,
-	     "mov r8 = cpuid[r8]\n");
-DEFINE_FUNC1(get_pmd, int,
-	     "mov r8 = pmd[r8]\n");
-DEFINE_FUNC1(get_rr, unsigned long,
-	     "mov r8 = rr[r8]\n");
-
-DEFINE_VOID_FUNC0(ssm_i,
-		  "ssm psr.i\n");
-DEFINE_VOID_FUNC0(rsm_i,
-		  "rsm psr.i\n");
-
-extern void
-ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
-				unsigned long val2, unsigned long val3,
-				unsigned long val4);
-__DEFINE_FUNC(set_rr0_to_rr4,
-	      "mov rr[r0] = r8\n"
-	      "movl r2 = 0x2000000000000000\n"
-	      ";;\n"
-	      "mov rr[r2] = r9\n"
-	      "shl r3 = r2, 1\n"	/* movl r3 = 0x4000000000000000 */
-	      ";;\n"
-	      "add r2 = r2, r3\n"	/* movl r2 = 0x6000000000000000 */
-	      "mov rr[r3] = r10\n"
-	      ";;\n"
-	      "mov rr[r2] = r11\n"
-	      "shl r3 = r3, 1\n"	/* movl r3 = 0x8000000000000000 */
-	      ";;\n"
-	      "mov rr[r3] = r14\n");
-
-extern unsigned long ia64_native_getreg_func(int regnum);
-asm(".global ia64_native_getreg_func\n");
-#define __DEFINE_GET_REG(id, reg)			\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
-	";;\n"						\
-	"cmp.eq p6, p0 = r2, r8\n"			\
-	";;\n"						\
-	"(p6) mov r8 = " #reg "\n"			\
-	"(p6) br.cond.sptk.many b6\n"			\
-	";;\n"
-#define __DEFINE_GET_AR(id, reg)	__DEFINE_GET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_GET_CR(id, reg)	__DEFINE_GET_REG(CR_ ## id, cr.reg)
-
-__DEFINE_FUNC(getreg,
-	      __DEFINE_GET_REG(GP, gp)
-	      /*__DEFINE_GET_REG(IP, ip)*/ /* returned ip value shouldn't be constant */
-	      __DEFINE_GET_REG(PSR, psr)
-	      __DEFINE_GET_REG(TP, tp)
-	      __DEFINE_GET_REG(SP, sp)
-
-	      __DEFINE_GET_REG(AR_KR0, ar0)
-	      __DEFINE_GET_REG(AR_KR1, ar1)
-	      __DEFINE_GET_REG(AR_KR2, ar2)
-	      __DEFINE_GET_REG(AR_KR3, ar3)
-	      __DEFINE_GET_REG(AR_KR4, ar4)
-	      __DEFINE_GET_REG(AR_KR5, ar5)
-	      __DEFINE_GET_REG(AR_KR6, ar6)
-	      __DEFINE_GET_REG(AR_KR7, ar7)
-	      __DEFINE_GET_AR(RSC, rsc)
-	      __DEFINE_GET_AR(BSP, bsp)
-	      __DEFINE_GET_AR(BSPSTORE, bspstore)
-	      __DEFINE_GET_AR(RNAT, rnat)
-	      __DEFINE_GET_AR(FCR, fcr)
-	      __DEFINE_GET_AR(EFLAG, eflag)
-	      __DEFINE_GET_AR(CSD, csd)
-	      __DEFINE_GET_AR(SSD, ssd)
-	      __DEFINE_GET_REG(AR_CFLAG, ar27)
-	      __DEFINE_GET_AR(FSR, fsr)
-	      __DEFINE_GET_AR(FIR, fir)
-	      __DEFINE_GET_AR(FDR, fdr)
-	      __DEFINE_GET_AR(CCV, ccv)
-	      __DEFINE_GET_AR(UNAT, unat)
-	      __DEFINE_GET_AR(FPSR, fpsr)
-	      __DEFINE_GET_AR(ITC, itc)
-	      __DEFINE_GET_AR(PFS, pfs)
-	      __DEFINE_GET_AR(LC, lc)
-	      __DEFINE_GET_AR(EC, ec)
-
-	      __DEFINE_GET_CR(DCR, dcr)
-	      __DEFINE_GET_CR(ITM, itm)
-	      __DEFINE_GET_CR(IVA, iva)
-	      __DEFINE_GET_CR(PTA, pta)
-	      __DEFINE_GET_CR(IPSR, ipsr)
-	      __DEFINE_GET_CR(ISR, isr)
-	      __DEFINE_GET_CR(IIP, iip)
-	      __DEFINE_GET_CR(IFA, ifa)
-	      __DEFINE_GET_CR(ITIR, itir)
-	      __DEFINE_GET_CR(IIPA, iipa)
-	      __DEFINE_GET_CR(IFS, ifs)
-	      __DEFINE_GET_CR(IIM, iim)
-	      __DEFINE_GET_CR(IHA, iha)
-	      __DEFINE_GET_CR(LID, lid)
-	      __DEFINE_GET_CR(IVR, ivr)
-	      __DEFINE_GET_CR(TPR, tpr)
-	      __DEFINE_GET_CR(EOI, eoi)
-	      __DEFINE_GET_CR(IRR0, irr0)
-	      __DEFINE_GET_CR(IRR1, irr1)
-	      __DEFINE_GET_CR(IRR2, irr2)
-	      __DEFINE_GET_CR(IRR3, irr3)
-	      __DEFINE_GET_CR(ITV, itv)
-	      __DEFINE_GET_CR(PMV, pmv)
-	      __DEFINE_GET_CR(CMCV, cmcv)
-	      __DEFINE_GET_CR(LRR0, lrr0)
-	      __DEFINE_GET_CR(LRR1, lrr1)
-
-	      "mov r8 = -1\n"	/* unsupported case */
-	);
-
-extern void ia64_native_setreg_func(int regnum, unsigned long val);
-asm(".global ia64_native_setreg_func\n");
-#define __DEFINE_SET_REG(id, reg)			\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
-	";;\n"						\
-	"cmp.eq p6, p0 = r2, r9\n"			\
-	";;\n"						\
-	"(p6) mov " #reg " = r8\n"			\
-	"(p6) br.cond.sptk.many b6\n"			\
-	";;\n"
-#define __DEFINE_SET_AR(id, reg)	__DEFINE_SET_REG(AR_ ## id, ar.reg)
-#define __DEFINE_SET_CR(id, reg)	__DEFINE_SET_REG(CR_ ## id, cr.reg)
-__DEFINE_FUNC(setreg,
-	      "mov r2 = " __stringify(_IA64_REG_PSR_L) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r9\n"
-	      ";;\n"
-	      "(p6) mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
-	      ".serialize.data\n"
-#endif
-	      "(p6) br.cond.sptk.many b6\n"
-	      __DEFINE_SET_REG(GP, gp)
-	      __DEFINE_SET_REG(SP, sp)
-
-	      __DEFINE_SET_REG(AR_KR0, ar0)
-	      __DEFINE_SET_REG(AR_KR1, ar1)
-	      __DEFINE_SET_REG(AR_KR2, ar2)
-	      __DEFINE_SET_REG(AR_KR3, ar3)
-	      __DEFINE_SET_REG(AR_KR4, ar4)
-	      __DEFINE_SET_REG(AR_KR5, ar5)
-	      __DEFINE_SET_REG(AR_KR6, ar6)
-	      __DEFINE_SET_REG(AR_KR7, ar7)
-	      __DEFINE_SET_AR(RSC, rsc)
-	      __DEFINE_SET_AR(BSP, bsp)
-	      __DEFINE_SET_AR(BSPSTORE, bspstore)
-	      __DEFINE_SET_AR(RNAT, rnat)
-	      __DEFINE_SET_AR(FCR, fcr)
-	      __DEFINE_SET_AR(EFLAG, eflag)
-	      __DEFINE_SET_AR(CSD, csd)
-	      __DEFINE_SET_AR(SSD, ssd)
-	      __DEFINE_SET_REG(AR_CFLAG, ar27)
-	      __DEFINE_SET_AR(FSR, fsr)
-	      __DEFINE_SET_AR(FIR, fir)
-	      __DEFINE_SET_AR(FDR, fdr)
-	      __DEFINE_SET_AR(CCV, ccv)
-	      __DEFINE_SET_AR(UNAT, unat)
-	      __DEFINE_SET_AR(FPSR, fpsr)
-	      __DEFINE_SET_AR(ITC, itc)
-	      __DEFINE_SET_AR(PFS, pfs)
-	      __DEFINE_SET_AR(LC, lc)
-	      __DEFINE_SET_AR(EC, ec)
-
-	      __DEFINE_SET_CR(DCR, dcr)
-	      __DEFINE_SET_CR(ITM, itm)
-	      __DEFINE_SET_CR(IVA, iva)
-	      __DEFINE_SET_CR(PTA, pta)
-	      __DEFINE_SET_CR(IPSR, ipsr)
-	      __DEFINE_SET_CR(ISR, isr)
-	      __DEFINE_SET_CR(IIP, iip)
-	      __DEFINE_SET_CR(IFA, ifa)
-	      __DEFINE_SET_CR(ITIR, itir)
-	      __DEFINE_SET_CR(IIPA, iipa)
-	      __DEFINE_SET_CR(IFS, ifs)
-	      __DEFINE_SET_CR(IIM, iim)
-	      __DEFINE_SET_CR(IHA, iha)
-	      __DEFINE_SET_CR(LID, lid)
-	      __DEFINE_SET_CR(IVR, ivr)
-	      __DEFINE_SET_CR(TPR, tpr)
-	      __DEFINE_SET_CR(EOI, eoi)
-	      __DEFINE_SET_CR(IRR0, irr0)
-	      __DEFINE_SET_CR(IRR1, irr1)
-	      __DEFINE_SET_CR(IRR2, irr2)
-	      __DEFINE_SET_CR(IRR3, irr3)
-	      __DEFINE_SET_CR(ITV, itv)
-	      __DEFINE_SET_CR(PMV, pmv)
-	      __DEFINE_SET_CR(CMCV, cmcv)
-	      __DEFINE_SET_CR(LRR0, lrr0)
-	      __DEFINE_SET_CR(LRR1, lrr1)
-	);
-#endif
-
-struct pv_cpu_ops pv_cpu_ops = {
-	.fc		= ia64_native_fc_func,
-	.thash		= ia64_native_thash_func,
-	.get_cpuid	= ia64_native_get_cpuid_func,
-	.get_pmd	= ia64_native_get_pmd_func,
-	.ptcga		= ia64_native_ptcga_func,
-	.get_rr		= ia64_native_get_rr_func,
-	.set_rr		= ia64_native_set_rr_func,
-	.set_rr0_to_rr4	= ia64_native_set_rr0_to_rr4_func,
-	.ssm_i		= ia64_native_ssm_i_func,
-	.getreg		= ia64_native_getreg_func,
-	.setreg		= ia64_native_setreg_func,
-	.rsm_i		= ia64_native_rsm_i_func,
-	.get_psr_i	= ia64_native_get_psr_i_func,
-	.intrin_local_irq_restore
-			= ia64_native_intrin_local_irq_restore_func,
-};
-EXPORT_SYMBOL(pv_cpu_ops);
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-
-void
-paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch)
-{
-	extern unsigned long paravirt_switch_to_targ;
-	extern unsigned long paravirt_leave_syscall_targ;
-	extern unsigned long paravirt_work_processed_syscall_targ;
-	extern unsigned long paravirt_leave_kernel_targ;
-
-	paravirt_switch_to_targ = cpu_asm_switch->switch_to;
-	paravirt_leave_syscall_targ = cpu_asm_switch->leave_syscall;
-	paravirt_work_processed_syscall_targ =
-		cpu_asm_switch->work_processed_syscall;
-	paravirt_leave_kernel_targ = cpu_asm_switch->leave_kernel;
-}
-
-/***************************************************************************
- * pv_iosapic_ops
- * iosapic read/write hooks.
- */
-
-static unsigned int
-ia64_native_iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
-	return __ia64_native_iosapic_read(iosapic, reg);
-}
-
-static void
-ia64_native_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
-	__ia64_native_iosapic_write(iosapic, reg, val);
-}
-
-struct pv_iosapic_ops pv_iosapic_ops = {
-	.pcat_compat_init = ia64_native_iosapic_pcat_compat_init,
-	.__get_irq_chip = ia64_native_iosapic_get_irq_chip,
-
-	.__read = ia64_native_iosapic_read,
-	.__write = ia64_native_iosapic_write,
-};
-
-/***************************************************************************
- * pv_irq_ops
- * irq operations
- */
-
-struct pv_irq_ops pv_irq_ops = {
-	.register_ipi = ia64_native_register_ipi,
-
-	.assign_irq_vector = ia64_native_assign_irq_vector,
-	.free_irq_vector = ia64_native_free_irq_vector,
-	.register_percpu_irq = ia64_native_register_percpu_irq,
-
-	.resend_irq = ia64_native_resend_irq,
-};
-
-/***************************************************************************
- * pv_time_ops
- * time operations
- */
-struct static_key paravirt_steal_enabled;
-struct static_key paravirt_steal_rq_enabled;
-
-static int
-ia64_native_do_steal_accounting(unsigned long *new_itm)
-{
-	return 0;
-}
-
-struct pv_time_ops pv_time_ops = {
-	.do_steal_accounting = ia64_native_do_steal_accounting,
-	.sched_clock = ia64_native_sched_clock,
-};
-
-/***************************************************************************
- * binary pacthing
- * pv_init_ops.patch_bundle
- */
-
-#ifdef ASM_SUPPORTED
-#define IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg)	\
-	__DEFINE_FUNC(get_ ## name,			\
-		      ";;\n"				\
-		      "mov r8 = " #reg "\n"		\
-		      ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
-	__DEFINE_FUNC(set_ ## name,			\
-		      ";;\n"				\
-		      "mov " #reg " = r8\n"		\
-		      ";;\n")
-
-#define IA64_NATIVE_PATCH_DEFINE_REG(name, reg)		\
-	IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg);	\
-	IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
-
-#define IA64_NATIVE_PATCH_DEFINE_AR(name, reg)			\
-	IA64_NATIVE_PATCH_DEFINE_REG(ar_ ## name, ar.reg)
-
-#define IA64_NATIVE_PATCH_DEFINE_CR(name, reg)			\
-	IA64_NATIVE_PATCH_DEFINE_REG(cr_ ## name, cr.reg)
-
-
-IA64_NATIVE_PATCH_DEFINE_GET_REG(psr, psr);
-IA64_NATIVE_PATCH_DEFINE_GET_REG(tp, tp);
-
-/* IA64_NATIVE_PATCH_DEFINE_SET_REG(psr_l, psr.l); */
-__DEFINE_FUNC(set_psr_l,
-	      ";;\n"
-	      "mov psr.l = r8\n"
-#ifdef HAVE_SERIALIZE_DIRECTIVE
-	      ".serialize.data\n"
-#endif
-	      ";;\n");
-
-IA64_NATIVE_PATCH_DEFINE_REG(gp, gp);
-IA64_NATIVE_PATCH_DEFINE_REG(sp, sp);
-
-IA64_NATIVE_PATCH_DEFINE_REG(kr0, ar0);
-IA64_NATIVE_PATCH_DEFINE_REG(kr1, ar1);
-IA64_NATIVE_PATCH_DEFINE_REG(kr2, ar2);
-IA64_NATIVE_PATCH_DEFINE_REG(kr3, ar3);
-IA64_NATIVE_PATCH_DEFINE_REG(kr4, ar4);
-IA64_NATIVE_PATCH_DEFINE_REG(kr5, ar5);
-IA64_NATIVE_PATCH_DEFINE_REG(kr6, ar6);
-IA64_NATIVE_PATCH_DEFINE_REG(kr7, ar7);
-
-IA64_NATIVE_PATCH_DEFINE_AR(rsc, rsc);
-IA64_NATIVE_PATCH_DEFINE_AR(bsp, bsp);
-IA64_NATIVE_PATCH_DEFINE_AR(bspstore, bspstore);
-IA64_NATIVE_PATCH_DEFINE_AR(rnat, rnat);
-IA64_NATIVE_PATCH_DEFINE_AR(fcr, fcr);
-IA64_NATIVE_PATCH_DEFINE_AR(eflag, eflag);
-IA64_NATIVE_PATCH_DEFINE_AR(csd, csd);
-IA64_NATIVE_PATCH_DEFINE_AR(ssd, ssd);
-IA64_NATIVE_PATCH_DEFINE_REG(ar27, ar27);
-IA64_NATIVE_PATCH_DEFINE_AR(fsr, fsr);
-IA64_NATIVE_PATCH_DEFINE_AR(fir, fir);
-IA64_NATIVE_PATCH_DEFINE_AR(fdr, fdr);
-IA64_NATIVE_PATCH_DEFINE_AR(ccv, ccv);
-IA64_NATIVE_PATCH_DEFINE_AR(unat, unat);
-IA64_NATIVE_PATCH_DEFINE_AR(fpsr, fpsr);
-IA64_NATIVE_PATCH_DEFINE_AR(itc, itc);
-IA64_NATIVE_PATCH_DEFINE_AR(pfs, pfs);
-IA64_NATIVE_PATCH_DEFINE_AR(lc, lc);
-IA64_NATIVE_PATCH_DEFINE_AR(ec, ec);
-
-IA64_NATIVE_PATCH_DEFINE_CR(dcr, dcr);
-IA64_NATIVE_PATCH_DEFINE_CR(itm, itm);
-IA64_NATIVE_PATCH_DEFINE_CR(iva, iva);
-IA64_NATIVE_PATCH_DEFINE_CR(pta, pta);
-IA64_NATIVE_PATCH_DEFINE_CR(ipsr, ipsr);
-IA64_NATIVE_PATCH_DEFINE_CR(isr, isr);
-IA64_NATIVE_PATCH_DEFINE_CR(iip, iip);
-IA64_NATIVE_PATCH_DEFINE_CR(ifa, ifa);
-IA64_NATIVE_PATCH_DEFINE_CR(itir, itir);
-IA64_NATIVE_PATCH_DEFINE_CR(iipa, iipa);
-IA64_NATIVE_PATCH_DEFINE_CR(ifs, ifs);
-IA64_NATIVE_PATCH_DEFINE_CR(iim, iim);
-IA64_NATIVE_PATCH_DEFINE_CR(iha, iha);
-IA64_NATIVE_PATCH_DEFINE_CR(lid, lid);
-IA64_NATIVE_PATCH_DEFINE_CR(ivr, ivr);
-IA64_NATIVE_PATCH_DEFINE_CR(tpr, tpr);
-IA64_NATIVE_PATCH_DEFINE_CR(eoi, eoi);
-IA64_NATIVE_PATCH_DEFINE_CR(irr0, irr0);
-IA64_NATIVE_PATCH_DEFINE_CR(irr1, irr1);
-IA64_NATIVE_PATCH_DEFINE_CR(irr2, irr2);
-IA64_NATIVE_PATCH_DEFINE_CR(irr3, irr3);
-IA64_NATIVE_PATCH_DEFINE_CR(itv, itv);
-IA64_NATIVE_PATCH_DEFINE_CR(pmv, pmv);
-IA64_NATIVE_PATCH_DEFINE_CR(cmcv, cmcv);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr0, lrr0);
-IA64_NATIVE_PATCH_DEFINE_CR(lrr1, lrr1);
-
-static const struct paravirt_patch_bundle_elem ia64_native_patch_bundle_elems[]
-__initdata_or_module =
-{
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM(name, type)		\
-	{							\
-		(void*)ia64_native_ ## name ## _direct_start,	\
-		(void*)ia64_native_ ## name ## _direct_end,	\
-		PARAVIRT_PATCH_TYPE_ ## type,			\
-	}
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(fc, FC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(thash, THASH),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM(intrin_local_irq_restore,
-				      INTRIN_LOCAL_IRQ_RESTORE),
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg)			\
-	{								\
-		(void*)ia64_native_get_ ## name ## _direct_start,	\
-		(void*)ia64_native_get_ ## name ## _direct_end,		\
-		PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg,		\
-	}
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)			\
-	{								\
-		(void*)ia64_native_set_ ## name ## _direct_start,	\
-		(void*)ia64_native_set_ ## name ## _direct_end,		\
-		PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg,		\
-	}
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg),	\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)		\
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar_ ## name, AR_ ## reg)
-
-#define IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(name, reg)		\
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(cr_ ## name, CR_ ## reg)
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(tp, TP),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(psr_l, PSR_L),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(gp, GP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(sp, SP),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr0, AR_KR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr1, AR_KR1),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr2, AR_KR2),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr3, AR_KR3),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr4, AR_KR4),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr5, AR_KR5),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr6, AR_KR6),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr7, AR_KR7),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rsc, RSC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bsp, BSP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bspstore, BSPSTORE),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rnat, RNAT),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fcr, FCR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(eflag, EFLAG),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(csd, CSD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ssd, SSD),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar27, AR_CFLAG),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fsr, FSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fir, FIR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fdr, FDR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ccv, CCV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(unat, UNAT),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fpsr, FPSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(itc, ITC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(pfs, PFS),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(lc, LC),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ec, EC),
-
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(dcr, DCR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itm, ITM),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iva, IVA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pta, PTA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ipsr, IPSR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(isr, ISR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iip, IIP),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifa, IFA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itir, ITIR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iipa, IIPA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifs, IFS),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iim, IIM),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iha, IHA),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lid, LID),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ivr, IVR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(tpr, TPR),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(eoi, EOI),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr0, IRR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr1, IRR1),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr2, IRR2),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr3, IRR3),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itv, ITV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pmv, PMV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(cmcv, CMCV),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr0, LRR0),
-	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr1, LRR1),
-};
-
-unsigned long __init_or_module
-ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
-{
-	const unsigned long nelems = sizeof(ia64_native_patch_bundle_elems) /
-		sizeof(ia64_native_patch_bundle_elems[0]);
-
-	return __paravirt_patch_apply_bundle(sbundle, ebundle, type,
-					      ia64_native_patch_bundle_elems,
-					      nelems, NULL);
-}
-#endif /* ASM_SUPPOTED */
-
-extern const char ia64_native_switch_to[];
-extern const char ia64_native_leave_syscall[];
-extern const char ia64_native_work_processed_syscall[];
-extern const char ia64_native_leave_kernel[];
-
-const struct paravirt_patch_branch_target ia64_native_branch_target[]
-__initconst = {
-#define PARAVIRT_BR_TARGET(name, type)			\
-	{						\
-		ia64_native_ ## name,			\
-		PARAVIRT_PATCH_TYPE_BR_ ## type,	\
-	}
-	PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
-	PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
-	PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
-	PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
-};
-
-static void __init
-ia64_native_patch_branch(unsigned long tag, unsigned long type)
-{
-	const unsigned long nelem =
-		sizeof(ia64_native_branch_target) /
-		sizeof(ia64_native_branch_target[0]);
-	__paravirt_patch_apply_branch(tag, type,
-				      ia64_native_branch_target, nelem);
-}
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
deleted file mode 100644
index 1ad7512b5f65..000000000000
--- a/arch/ia64/kernel/paravirt_inst.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_inst.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK
-#include <asm/native/pvchk_inst.h>
-#else
-#include <asm/native/inst.h>
-#endif
-
diff --git a/arch/ia64/kernel/paravirt_patch.c b/arch/ia64/kernel/paravirt_patch.c
deleted file mode 100644
index bfdfef1b1ffd..000000000000
--- a/arch/ia64/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,514 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patch.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/intrinsics.h>
-#include <asm/kprobes.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
-
-typedef union ia64_inst {
-        struct {
-		unsigned long long qp : 6;
-		unsigned long long : 31;
-		unsigned long long opcode : 4;
-		unsigned long long reserved : 23;
-        } generic;
-        unsigned long long l;
-} ia64_inst_t;
-
-/*
- * flush_icache_range() can't be used here.
- * we are here before cpu_init() which initializes
- * ia64_i_cache_stride_shift. flush_icache_range() uses it.
- */
-void __init_or_module
-paravirt_flush_i_cache_range(const void *instr, unsigned long size)
-{
-	extern void paravirt_fc_i(const void *addr);
-	unsigned long i;
-
-	for (i = 0; i < size; i += sizeof(bundle_t))
-		paravirt_fc_i(instr + i);
-}
-
-bundle_t* __init_or_module
-paravirt_get_bundle(unsigned long tag)
-{
-	return (bundle_t *)(tag & ~3UL);
-}
-
-unsigned long __init_or_module
-paravirt_get_slot(unsigned long tag)
-{
-	return tag & 3UL;
-}
-
-unsigned long __init_or_module
-paravirt_get_num_inst(unsigned long stag, unsigned long etag)
-{
-	bundle_t *sbundle = paravirt_get_bundle(stag);
-	unsigned long sslot = paravirt_get_slot(stag);
-	bundle_t *ebundle = paravirt_get_bundle(etag);
-	unsigned long eslot = paravirt_get_slot(etag);
-
-	return (ebundle - sbundle) * 3 + eslot - sslot + 1;
-}
-
-unsigned long __init_or_module
-paravirt_get_next_tag(unsigned long tag)
-{
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-	case 1:
-		return tag + 1;
-	case 2: {
-		bundle_t *bundle = paravirt_get_bundle(tag);
-		return (unsigned long)(bundle + 1);
-	}
-	default:
-		BUG();
-	}
-	/* NOTREACHED */
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot0(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad0.slot0;
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot1(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad0.slot1_p0 |
-		((unsigned long long)bundle->quad1.slot1_p1 << 18UL);
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_slot2(const bundle_t *bundle)
-{
-	ia64_inst_t inst;
-	inst.l = bundle->quad1.slot2;
-	return inst;
-}
-
-ia64_inst_t __init_or_module
-paravirt_read_inst(unsigned long tag)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-		return paravirt_read_slot0(bundle);
-	case 1:
-		return paravirt_read_slot1(bundle);
-	case 2:
-		return paravirt_read_slot2(bundle);
-	default:
-		BUG();
-	}
-	/* NOTREACHED */
-}
-
-void __init_or_module
-paravirt_write_slot0(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad0.slot0 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_slot1(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad0.slot1_p0 = inst.l;
-	bundle->quad1.slot1_p1 = inst.l >> 18UL;
-}
-
-void __init_or_module
-paravirt_write_slot2(bundle_t *bundle, ia64_inst_t inst)
-{
-	bundle->quad1.slot2 = inst.l;
-}
-
-void __init_or_module
-paravirt_write_inst(unsigned long tag, ia64_inst_t inst)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	unsigned long slot = paravirt_get_slot(tag);
-
-	switch (slot) {
-	case 0:
-		paravirt_write_slot0(bundle, inst);
-		break;
-	case 1:
-		paravirt_write_slot1(bundle, inst);
-		break;
-	case 2:
-		paravirt_write_slot2(bundle, inst);
-		break;
-	default:
-		BUG();
-		break;
-	}
-	paravirt_flush_i_cache_range(bundle, sizeof(*bundle));
-}
-
-/* for debug */
-void
-paravirt_print_bundle(const bundle_t *bundle)
-{
-	const unsigned long *quad = (const unsigned long *)bundle;
-	ia64_inst_t slot0 = paravirt_read_slot0(bundle);
-	ia64_inst_t slot1 = paravirt_read_slot1(bundle);
-	ia64_inst_t slot2 = paravirt_read_slot2(bundle);
-
-	printk(KERN_DEBUG
-	       "bundle 0x%p 0x%016lx 0x%016lx\n", bundle, quad[0], quad[1]);
-	printk(KERN_DEBUG
-	       "bundle template 0x%x\n",
-	       bundle->quad0.template);
-	printk(KERN_DEBUG
-	       "slot0 0x%lx slot1_p0 0x%lx slot1_p1 0x%lx slot2 0x%lx\n",
-	       (unsigned long)bundle->quad0.slot0,
-	       (unsigned long)bundle->quad0.slot1_p0,
-	       (unsigned long)bundle->quad1.slot1_p1,
-	       (unsigned long)bundle->quad1.slot2);
-	printk(KERN_DEBUG
-	       "slot0 0x%016llx slot1 0x%016llx slot2 0x%016llx\n",
-	       slot0.l, slot1.l, slot2.l);
-}
-
-static int noreplace_paravirt __init_or_module = 0;
-
-static int __init setup_noreplace_paravirt(char *str)
-{
-	noreplace_paravirt = 1;
-	return 1;
-}
-__setup("noreplace-paravirt", setup_noreplace_paravirt);
-
-#ifdef ASM_SUPPORTED
-static void __init_or_module
-fill_nop_bundle(void *sbundle, void *ebundle)
-{
-	extern const char paravirt_nop_bundle[];
-	extern const unsigned long paravirt_nop_bundle_size;
-
-	void *bundle = sbundle;
-
-	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
-	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
-	while (bundle < ebundle) {
-		memcpy(bundle, paravirt_nop_bundle, paravirt_nop_bundle_size);
-
-		bundle += paravirt_nop_bundle_size;
-	}
-}
-
-/* helper function */
-unsigned long __init_or_module
-__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
-			      const struct paravirt_patch_bundle_elem *elems,
-			      unsigned long nelems,
-			      const struct paravirt_patch_bundle_elem **found)
-{
-	unsigned long used = 0;
-	unsigned long i;
-
-	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
-	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
-
-	found = NULL;
-	for (i = 0; i < nelems; i++) {
-		const struct paravirt_patch_bundle_elem *p = &elems[i];
-		if (p->type == type) {
-			unsigned long need = p->ebundle - p->sbundle;
-			unsigned long room = ebundle - sbundle;
-
-			if (found != NULL)
-				*found = p;
-
-			if (room < need) {
-				/* no room to replace. skip it */
-				printk(KERN_DEBUG
-				       "the space is too small to put "
-				       "bundles. type %ld need %ld room %ld\n",
-				       type, need, room);
-				break;
-			}
-
-			used = need;
-			memcpy(sbundle, p->sbundle, used);
-			break;
-		}
-	}
-
-	return used;
-}
-
-void __init_or_module
-paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
-			    const struct paravirt_patch_site_bundle *end)
-{
-	const struct paravirt_patch_site_bundle *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_bundle == NULL)
-		return;
-
-	for (p = start; p < end; p++) {
-		unsigned long used;
-
-		used = (*pv_init_ops.patch_bundle)(p->sbundle, p->ebundle,
-						   p->type);
-		if (used == 0)
-			continue;
-
-		fill_nop_bundle(p->sbundle + used, p->ebundle);
-		paravirt_flush_i_cache_range(p->sbundle,
-					     p->ebundle - p->sbundle);
-	}
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-
-/*
- * nop.i, nop.m, nop.f instruction are same format.
- * but nop.b has differennt format.
- * This doesn't support nop.b for now.
- */
-static void __init_or_module
-fill_nop_inst(unsigned long stag, unsigned long etag)
-{
-	extern const bundle_t paravirt_nop_mfi_inst_bundle[];
-	unsigned long tag;
-	const ia64_inst_t nop_inst =
-		paravirt_read_slot0(paravirt_nop_mfi_inst_bundle);
-
-	for (tag = stag; tag < etag; tag = paravirt_get_next_tag(tag))
-		paravirt_write_inst(tag, nop_inst);
-}
-
-void __init_or_module
-paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
-			  const struct paravirt_patch_site_inst *end)
-{
-	const struct paravirt_patch_site_inst *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_inst == NULL)
-		return;
-
-	for (p = start; p < end; p++) {
-		unsigned long tag;
-		bundle_t *sbundle;
-		bundle_t *ebundle;
-
-		tag = (*pv_init_ops.patch_inst)(p->stag, p->etag, p->type);
-		if (tag == p->stag)
-			continue;
-
-		fill_nop_inst(tag, p->etag);
-		sbundle = paravirt_get_bundle(p->stag);
-		ebundle = paravirt_get_bundle(p->etag) + 1;
-		paravirt_flush_i_cache_range(sbundle, (ebundle - sbundle) *
-					     sizeof(bundle_t));
-	}
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-#endif /* ASM_SUPPOTED */
-
-/* brl.cond.sptk.many <target64> X3 */
-typedef union inst_x3_op {
-	ia64_inst_t inst;
-	struct {
-		unsigned long qp: 6;
-		unsigned long btyp: 3;
-		unsigned long unused: 3;
-		unsigned long p: 1;
-		unsigned long imm20b: 20;
-		unsigned long wh: 2;
-		unsigned long d: 1;
-		unsigned long i: 1;
-		unsigned long opcode: 4;
-	};
-	unsigned long l;
-} inst_x3_op_t;
-
-typedef union inst_x3_imm {
-	ia64_inst_t inst;
-	struct {
-		unsigned long unused: 2;
-		unsigned long imm39: 39;
-	};
-	unsigned long l;
-} inst_x3_imm_t;
-
-void __init_or_module
-paravirt_patch_reloc_brl(unsigned long tag, const void *target)
-{
-	unsigned long tag_op = paravirt_get_next_tag(tag);
-	unsigned long tag_imm = tag;
-	bundle_t *bundle = paravirt_get_bundle(tag);
-
-	ia64_inst_t inst_op = paravirt_read_inst(tag_op);
-	ia64_inst_t inst_imm = paravirt_read_inst(tag_imm);
-
-	inst_x3_op_t inst_x3_op = { .l = inst_op.l };
-	inst_x3_imm_t inst_x3_imm = { .l = inst_imm.l };
-
-	unsigned long imm60 =
-		((unsigned long)target - (unsigned long)bundle) >> 4;
-
-	BUG_ON(paravirt_get_slot(tag) != 1); /* MLX */
-	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
-	/* imm60[59] 1bit */
-	inst_x3_op.i = (imm60 >> 59) & 1;
-	/* imm60[19:0] 20bit */
-	inst_x3_op.imm20b = imm60 & ((1UL << 20) - 1);
-	/* imm60[58:20] 39bit */
-	inst_x3_imm.imm39 = (imm60 >> 20) & ((1UL << 39) - 1);
-
-	inst_op.l = inst_x3_op.l;
-	inst_imm.l = inst_x3_imm.l;
-
-	paravirt_write_inst(tag_op, inst_op);
-	paravirt_write_inst(tag_imm, inst_imm);
-}
-
-/* br.cond.sptk.many <target25>	B1 */
-typedef union inst_b1 {
-	ia64_inst_t inst;
-	struct {
-		unsigned long qp: 6;
-		unsigned long btype: 3;
-		unsigned long unused: 3;
-		unsigned long p: 1;
-		unsigned long imm20b: 20;
-		unsigned long wh: 2;
-		unsigned long d: 1;
-		unsigned long s: 1;
-		unsigned long opcode: 4;
-	};
-	unsigned long l;
-} inst_b1_t;
-
-void __init
-paravirt_patch_reloc_br(unsigned long tag, const void *target)
-{
-	bundle_t *bundle = paravirt_get_bundle(tag);
-	ia64_inst_t inst = paravirt_read_inst(tag);
-	unsigned long target25 = (unsigned long)target - (unsigned long)bundle;
-	inst_b1_t inst_b1;
-
-	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
-
-	inst_b1.l = inst.l;
-	if (target25 & (1UL << 63))
-		inst_b1.s = 1;
-	else
-		inst_b1.s = 0;
-
-	inst_b1.imm20b = target25 >> 4;
-	inst.l = inst_b1.l;
-
-	paravirt_write_inst(tag, inst);
-}
-
-void __init
-__paravirt_patch_apply_branch(
-	unsigned long tag, unsigned long type,
-	const struct paravirt_patch_branch_target *entries,
-	unsigned int nr_entries)
-{
-	unsigned int i;
-	for (i = 0; i < nr_entries; i++) {
-		if (entries[i].type == type) {
-			paravirt_patch_reloc_br(tag, entries[i].entry);
-			break;
-		}
-	}
-}
-
-static void __init
-paravirt_patch_apply_branch(const struct paravirt_patch_site_branch *start,
-			    const struct paravirt_patch_site_branch *end)
-{
-	const struct paravirt_patch_site_branch *p;
-
-	if (noreplace_paravirt)
-		return;
-	if (pv_init_ops.patch_branch == NULL)
-		return;
-
-	for (p = start; p < end; p++)
-		(*pv_init_ops.patch_branch)(p->tag, p->type);
-
-	ia64_sync_i();
-	ia64_srlz_i();
-}
-
-void __init
-paravirt_patch_apply(void)
-{
-	extern const char __start_paravirt_bundles[];
-	extern const char __stop_paravirt_bundles[];
-	extern const char __start_paravirt_insts[];
-	extern const char __stop_paravirt_insts[];
-	extern const char __start_paravirt_branches[];
-	extern const char __stop_paravirt_branches[];
-
-	paravirt_patch_apply_bundle((const struct paravirt_patch_site_bundle *)
-				    __start_paravirt_bundles,
-				    (const struct paravirt_patch_site_bundle *)
-				    __stop_paravirt_bundles);
-	paravirt_patch_apply_inst((const struct paravirt_patch_site_inst *)
-				  __start_paravirt_insts,
-				  (const struct paravirt_patch_site_inst *)
-				  __stop_paravirt_insts);
-	paravirt_patch_apply_branch((const struct paravirt_patch_site_branch *)
-				    __start_paravirt_branches,
-				    (const struct paravirt_patch_site_branch *)
-				    __stop_paravirt_branches);
-}
-
-/*
- * Local variables:
- * mode: C
- * c-set-style: "linux"
- * c-basic-offset: 8
- * tab-width: 8
- * indent-tabs-mode: t
- * End:
- */
diff --git a/arch/ia64/kernel/paravirt_patchlist.c b/arch/ia64/kernel/paravirt_patchlist.c
deleted file mode 100644
index 0a70720662ed..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.c
+++ /dev/null
@@ -1,81 +0,0 @@
-/******************************************************************************
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/bug.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <asm/paravirt.h>
-
-#define DECLARE(name)						\
-	extern unsigned long					\
-		__ia64_native_start_gate_##name##_patchlist[];	\
-	extern unsigned long					\
-		__ia64_native_end_gate_##name##_patchlist[]
-
-DECLARE(fsyscall);
-DECLARE(brl_fsys_bubble_down);
-DECLARE(vtop);
-DECLARE(mckinley_e9);
-
-extern unsigned long __start_gate_section[];
-
-#define ASSIGN(name)							    \
-	.start_##name##_patchlist =					    \
-		(unsigned long)__ia64_native_start_gate_##name##_patchlist, \
-	.end_##name##_patchlist =					    \
-		(unsigned long)__ia64_native_end_gate_##name##_patchlist
-
-struct pv_patchdata pv_patchdata __initdata = {
-	ASSIGN(fsyscall),
-	ASSIGN(brl_fsys_bubble_down),
-	ASSIGN(vtop),
-	ASSIGN(mckinley_e9),
-
-	.gate_section = (void*)__start_gate_section,
-};
-
-
-unsigned long __init
-paravirt_get_gate_patchlist(enum pv_gate_patchlist type)
-{
-
-#define CASE(NAME, name)					\
-	case PV_GATE_START_##NAME:				\
-		return pv_patchdata.start_##name##_patchlist;	\
-	case PV_GATE_END_##NAME:				\
-		return pv_patchdata.end_##name##_patchlist;	\
-
-	switch (type) {
-		CASE(FSYSCALL, fsyscall);
-		CASE(BRL_FSYS_BUBBLE_DOWN, brl_fsys_bubble_down);
-		CASE(VTOP, vtop);
-		CASE(MCKINLEY_E9, mckinley_e9);
-	default:
-		BUG();
-		break;
-	}
-	return 0;
-}
-
-void * __init
-paravirt_get_gate_section(void)
-{
-	return pv_patchdata.gate_section;
-}
diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h
deleted file mode 100644
index 67cffc3643a3..000000000000
--- a/arch/ia64/kernel/paravirt_patchlist.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirt_patchlist.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <asm/native/patchlist.h>
-
diff --git a/arch/ia64/kernel/paravirtentry.S b/arch/ia64/kernel/paravirtentry.S
deleted file mode 100644
index 92d880c4d3d1..000000000000
--- a/arch/ia64/kernel/paravirtentry.S
+++ /dev/null
@@ -1,121 +0,0 @@
-/******************************************************************************
- * linux/arch/ia64/xen/paravirtentry.S
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/init.h>
-#include <asm/asmmacro.h>
-#include <asm/asm-offsets.h>
-#include <asm/paravirt_privop.h>
-#include <asm/paravirt_patch.h>
-#include "entry.h"
-
-#define DATA8(sym, init_value)			\
-	.pushsection .data..read_mostly ;	\
-	.align 8 ;				\
-	.global sym ;				\
-	sym: ;					\
-	data8 init_value ;			\
-	.popsection
-
-#define BRANCH(targ, reg, breg, type)					\
-	PARAVIRT_PATCH_SITE_BR(PARAVIRT_PATCH_TYPE_BR_ ## type) ;	\
-	;;								\
-	movl reg=targ ;							\
-	;;								\
-	ld8 reg=[reg] ;							\
-	;;								\
-	mov breg=reg ;							\
-	br.cond.sptk.many breg
-
-#define BRANCH_PROC(sym, reg, breg, type)				\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
-	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
-	END(paravirt_ ## sym)
-
-#define BRANCH_PROC_UNWINFO(sym, reg, breg, type)			\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
-	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
-		PT_REGS_UNWIND_INFO(0) ;				\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
-	END(paravirt_ ## sym)
-
-
-BRANCH_PROC(switch_to, r22, b7, SWITCH_TO)
-BRANCH_PROC_UNWINFO(leave_syscall, r22, b7, LEAVE_SYSCALL)
-BRANCH_PROC(work_processed_syscall, r2, b7, WORK_PROCESSED_SYSCALL)
-BRANCH_PROC_UNWINFO(leave_kernel, r22, b7, LEAVE_KERNEL)
-
-
-#ifdef CONFIG_MODULES
-#define __INIT_OR_MODULE	.text
-#define __INITDATA_OR_MODULE	.data
-#else
-#define __INIT_OR_MODULE	__INIT
-#define __INITDATA_OR_MODULE	__INITDATA
-#endif /* CONFIG_MODULES */
-
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_fc_i)
-	fc.i r32
-	br.ret.sptk.many rp
-	END(paravirt_fc_i)
-	__FINIT
-
-	__INIT_OR_MODULE
-	.align 32
-	GLOBAL_ENTRY(paravirt_nop_b_inst_bundle)
-	{
-		nop.b 0
-		nop.b 0
-		nop.b 0
-	}
-	END(paravirt_nop_b_inst_bundle)
-	__FINIT
-
-	/* NOTE: nop.[mfi] has same format */
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_nop_mfi_inst_bundle)
-	{
-		nop.m 0
-		nop.f 0
-		nop.i 0
-	}
-	END(paravirt_nop_mfi_inst_bundle)
-	__FINIT
-
-	__INIT_OR_MODULE
-	GLOBAL_ENTRY(paravirt_nop_bundle)
-paravirt_nop_bundle_start:
-	{
-		nop 0
-		nop 0
-		nop 0
-	}
-paravirt_nop_bundle_end:
-	END(paravirt_nop_bundle)
-	__FINIT
-
-	__INITDATA_OR_MODULE
-	.align 8
-	.global paravirt_nop_bundle_size
-paravirt_nop_bundle_size:
-	data8	paravirt_nop_bundle_end - paravirt_nop_bundle_start
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index 1cf091793714..944a8e2438a6 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -7,7 +7,6 @@
 #include <linux/init.h>
 #include <linux/string.h>
 
-#include <asm/paravirt.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -169,35 +168,16 @@ ia64_patch_mckinley_e9 (unsigned long start, unsigned long end)
 	ia64_srlz_i();
 }
 
-extern unsigned long ia64_native_fsyscall_table[NR_syscalls];
-extern char ia64_native_fsys_bubble_down[];
-struct pv_fsys_data pv_fsys_data __initdata = {
-	.fsyscall_table = (unsigned long *)ia64_native_fsyscall_table,
-	.fsys_bubble_down = (void *)ia64_native_fsys_bubble_down,
-};
-
-unsigned long * __init
-paravirt_get_fsyscall_table(void)
-{
-	return pv_fsys_data.fsyscall_table;
-}
-
-char * __init
-paravirt_get_fsys_bubble_down(void)
-{
-	return pv_fsys_data.fsys_bubble_down;
-}
-
 static void __init
 patch_fsyscall_table (unsigned long start, unsigned long end)
 {
-	u64 fsyscall_table = (u64)paravirt_get_fsyscall_table();
+	extern unsigned long fsyscall_table[NR_syscalls];
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
 	while (offp < (s32 *) end) {
 		ip = (u64) ia64_imva((char *) offp + *offp);
-		ia64_patch_imm64(ip, fsyscall_table);
+		ia64_patch_imm64(ip, (u64) fsyscall_table);
 		ia64_fc((void *) ip);
 		++offp;
 	}
@@ -208,7 +188,7 @@ patch_fsyscall_table (unsigned long start, unsigned long end)
 static void __init
 patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 {
-	u64 fsys_bubble_down = (u64)paravirt_get_fsys_bubble_down();
+	extern char fsys_bubble_down[];
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
@@ -226,13 +206,13 @@ patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 void __init
 ia64_patch_gate (void)
 {
-#	define START(name)	paravirt_get_gate_patchlist(PV_GATE_START_##name)
-#	define END(name)	paravirt_get_gate_patchlist(PV_GATE_END_##name)
+#	define START(name)	((unsigned long) __start_gate_##name##_patchlist)
+#	define END(name)	((unsigned long)__end_gate_##name##_patchlist)
 
-	patch_fsyscall_table(START(FSYSCALL), END(FSYSCALL));
-	patch_brl_fsys_bubble_down(START(BRL_FSYS_BUBBLE_DOWN), END(BRL_FSYS_BUBBLE_DOWN));
-	ia64_patch_vtop(START(VTOP), END(VTOP));
-	ia64_patch_mckinley_e9(START(MCKINLEY_E9), END(MCKINLEY_E9));
+	patch_fsyscall_table(START(fsyscall), END(fsyscall));
+	patch_brl_fsys_bubble_down(START(brl_fsys_bubble_down), END(brl_fsys_bubble_down));
+	ia64_patch_vtop(START(vtop), END(vtop));
+	ia64_patch_mckinley_e9(START(mckinley_e9), END(mckinley_e9));
 }
 
 void ia64_patch_phys_stack_reg(unsigned long val)
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index b9761389cb8d..4f118b0d3091 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -50,8 +50,6 @@
 #include <asm/mca.h>
 #include <asm/meminit.h>
 #include <asm/page.h>
-#include <asm/paravirt.h>
-#include <asm/paravirt_patch.h>
 #include <asm/patch.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -360,8 +358,6 @@ reserve_memory (void)
 	rsvd_region[n].end   = (unsigned long) ia64_imva(_end);
 	n++;
 
-	n += paravirt_reserve_memory(&rsvd_region[n]);
-
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (ia64_boot_param->initrd_start) {
 		rsvd_region[n].start = (unsigned long)__va(ia64_boot_param->initrd_start);
@@ -528,10 +524,7 @@ setup_arch (char **cmdline_p)
 {
 	unw_init();
 
-	paravirt_arch_setup_early();
-
 	ia64_patch_vtop((u64) __start___vtop_patchlist, (u64) __end___vtop_patchlist);
-	paravirt_patch_apply();
 
 	*cmdline_p = __va(ia64_boot_param->command_line);
 	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -594,9 +587,6 @@ setup_arch (char **cmdline_p)
 	cpu_init();	/* initialize the bootstrap CPU */
 	mmu_context_init();	/* initialize context_id bitmap */
 
-	paravirt_banner();
-	paravirt_arch_setup_console(cmdline_p);
-
 #ifdef CONFIG_VT
 	if (!conswitchp) {
 # if defined(CONFIG_DUMMY_CONSOLE)
@@ -616,8 +606,6 @@ setup_arch (char **cmdline_p)
 #endif
 
 	/* enable IA-64 Machine Check Abort Handling unless disabled */
-	if (paravirt_arch_setup_nomca())
-		nomca = 1;
 	if (!nomca)
 		ia64_mca_init();
 
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 15051e9c2c6f..0e76fad27975 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -49,7 +49,6 @@
 #include <asm/machvec.h>
 #include <asm/mca.h>
 #include <asm/page.h>
-#include <asm/paravirt.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -127,7 +126,7 @@ int smp_num_siblings = 1;
 volatile int ia64_cpu_to_sapicid[NR_CPUS];
 EXPORT_SYMBOL(ia64_cpu_to_sapicid);
 
-static volatile cpumask_t cpu_callin_map;
+static cpumask_t cpu_callin_map;
 
 struct smp_boot_data smp_boot_data __initdata;
 
@@ -477,6 +476,7 @@ do_boot_cpu (int sapicid, int cpu, struct task_struct *idle)
 	for (timeout = 0; timeout < 100000; timeout++) {
 		if (cpumask_test_cpu(cpu, &cpu_callin_map))
 			break;  /* It has booted */
+		barrier(); /* Make sure we re-read cpu_callin_map */
 		udelay(100);
 	}
 	Dprintk("\n");
@@ -568,7 +568,6 @@ void smp_prepare_boot_cpu(void)
 	cpumask_set_cpu(smp_processor_id(), &cpu_callin_map);
 	set_numa_node(cpu_to_node_map[smp_processor_id()]);
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
-	paravirt_post_smp_prepare_boot_cpu();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 9a0104a38cd3..c8dbe2acd735 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -25,7 +25,6 @@
 #include <asm/machvec.h>
 #include <asm/delay.h>
 #include <asm/hw_irq.h>
-#include <asm/paravirt.h>
 #include <asm/ptrace.h>
 #include <asm/sal.h>
 #include <asm/sections.h>
@@ -47,33 +46,12 @@ EXPORT_SYMBOL(last_cli_ip);
 
 #endif
 
-#ifdef CONFIG_PARAVIRT
-/* We need to define a real function for sched_clock, to override the
-   weak default version */
-unsigned long long sched_clock(void)
-{
-        return paravirt_sched_clock();
-}
-#endif
-
-#ifdef CONFIG_PARAVIRT
-static void
-paravirt_clocksource_resume(struct clocksource *cs)
-{
-	if (pv_time_ops.clocksource_resume)
-		pv_time_ops.clocksource_resume();
-}
-#endif
-
 static struct clocksource clocksource_itc = {
 	.name           = "itc",
 	.rating         = 350,
 	.read           = itc_get_cycles,
 	.mask           = CLOCKSOURCE_MASK(64),
 	.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
-#ifdef CONFIG_PARAVIRT
-	.resume		= paravirt_clocksource_resume,
-#endif
 };
 static struct clocksource *itc_clocksource;
 
@@ -164,9 +142,6 @@ timer_interrupt (int irq, void *dev_id)
 
 	profile_tick(CPU_PROFILING);
 
-	if (paravirt_do_steal_accounting(&new_itm))
-		goto skip_process_time_accounting;
-
 	while (1) {
 		update_process_times(user_mode(get_irq_regs()));
 
@@ -187,8 +162,6 @@ timer_interrupt (int irq, void *dev_id)
 		local_irq_disable();
 	}
 
-skip_process_time_accounting:
-
 	do {
 		/*
 		 * If we're too close to the next clock tick for
@@ -337,8 +310,6 @@ void ia64_init_itm(void)
 		 */
 		clocksource_itc.rating = 50;
 
-	paravirt_init_missing_ticks_accounting(smp_processor_id());
-
 	/* avoid softlock up message when cpu is unplug and plugged again. */
 	touch_softlockup_watchdog();
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 84f8a52ac5ae..dc506b05ffbd 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -136,27 +136,6 @@ SECTIONS {
 		__end___mckinley_e9_bundles = .;
 	}
 
-#if defined(CONFIG_PARAVIRT)
-	. = ALIGN(16);
-	.paravirt_bundles : AT(ADDR(.paravirt_bundles) - LOAD_OFFSET) {
-		__start_paravirt_bundles = .;
-		*(.paravirt_bundles)
-		__stop_paravirt_bundles = .;
-	}
-	. = ALIGN(16);
-	.paravirt_insts : AT(ADDR(.paravirt_insts) - LOAD_OFFSET) {
-		__start_paravirt_insts = .;
-		*(.paravirt_insts)
-		__stop_paravirt_insts = .;
-	}
-	. = ALIGN(16);
-	.paravirt_branches : AT(ADDR(.paravirt_branches) - LOAD_OFFSET) {
-		__start_paravirt_branches = .;
-		*(.paravirt_branches)
-		__stop_paravirt_branches = .;
-	}
-#endif
-
 #if defined(CONFIG_IA64_GENERIC)
 	/* Machine Vector */
 	. = ALIGN(16);
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index ba5ba7accd0d..70b40d1205a6 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -11,10 +11,10 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/prefetch.h>
+#include <linux/uaccess.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
 
 extern int die(char *, struct pt_regs *, long);
 
@@ -96,7 +96,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	/*
 	 * If we're in an interrupt or have no user context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 52b7604b5215..f50d4b3f501a 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -65,11 +65,6 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #define mk_pte_huge(entry) { pte_val(entry) |= _PAGE_P; }
 
 /*
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index a9b65cf7b34a..7f3028965064 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -34,7 +34,6 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
-#include <asm/paravirt.h>
 
 extern void ia64_tlb_init (void);
 
@@ -244,7 +243,6 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
 static void __init
 setup_gate (void)
 {
-	void *gate_section;
 	struct page *page;
 
 	/*
@@ -252,11 +250,10 @@ setup_gate (void)
 	 * headers etc. and once execute-only page to enable
 	 * privilege-promotion via "epc":
 	 */
-	gate_section = paravirt_get_gate_section();
-	page = virt_to_page(ia64_imva(gate_section));
+	page = virt_to_page(ia64_imva(__start_gate_section));
 	put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
 #ifdef HAVE_BUGGY_SEGREL
-	page = virt_to_page(ia64_imva(gate_section + PAGE_SIZE));
+	page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
 	put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
 #else
 	put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
@@ -642,8 +639,8 @@ mem_init (void)
 	 * code can tell them apart.
 	 */
 	for (i = 0; i < NR_syscalls; ++i) {
+		extern unsigned long fsyscall_table[NR_syscalls];
 		extern unsigned long sys_call_table[NR_syscalls];
-		unsigned long *fsyscall_table = paravirt_get_fsyscall_table();
 
 		if (!fsyscall_table[i] || nolwsys)
 			fsyscall_table[i] = sys_call_table[i] | 1;
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d4e162d35b34..7cc3be9fa7c6 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -478,9 +478,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
-	struct pci_controller *controller = bridge->bus->sysdata;
-
-	ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+	/*
+	 * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+	 * here, pci_create_root_bus() has been called by someone else and
+	 * sysdata is likely to be different from what we expect.  Let it go in
+	 * that case.
+	 */
+	if (!bridge->dev.parent) {
+		struct pci_controller *controller = bridge->bus->sysdata;
+		ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+	}
 	return 0;
 }
 
diff --git a/arch/ia64/scripts/pvcheck.sed b/arch/ia64/scripts/pvcheck.sed
deleted file mode 100644
index e59809a3fc01..000000000000
--- a/arch/ia64/scripts/pvcheck.sed
+++ /dev/null
@@ -1,33 +0,0 @@
-#
-# Checker for paravirtualizations of privileged operations.
-#
-s/ssm.*psr\.ic.*/.warning \"ssm psr.ic should not be used directly\"/g
-s/rsm.*psr\.ic.*/.warning \"rsm psr.ic should not be used directly\"/g
-s/ssm.*psr\.i.*/.warning \"ssm psr.i should not be used directly\"/g
-s/rsm.*psr\.i.*/.warning \"rsm psr.i should not be used directly\"/g
-s/ssm.*psr\.dt.*/.warning \"ssm psr.dt should not be used directly\"/g
-s/rsm.*psr\.dt.*/.warning \"rsm psr.dt should not be used directly\"/g
-s/mov.*=.*cr\.ifa/.warning \"cr.ifa should not used directly\"/g
-s/mov.*=.*cr\.itir/.warning \"cr.itir should not used directly\"/g
-s/mov.*=.*cr\.isr/.warning \"cr.isr should not used directly\"/g
-s/mov.*=.*cr\.iha/.warning \"cr.iha should not used directly\"/g
-s/mov.*=.*cr\.ipsr/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*=.*cr\.iim/.warning \"cr.iim should not used directly\"/g
-s/mov.*=.*cr\.iip/.warning \"cr.iip should not used directly\"/g
-s/mov.*=.*cr\.ivr/.warning \"cr.ivr should not used directly\"/g
-s/mov.*=[^\.]*psr/.warning \"psr should not used directly\"/g	# avoid ar.fpsr
-s/mov.*=.*ar\.eflags/.warning \"ar.eflags should not used directly\"/g
-s/mov.*=.*ar\.itc.*/.warning \"ar.itc should not used directly\"/g
-s/mov.*cr\.ifa.*=.*/.warning \"cr.ifa should not used directly\"/g
-s/mov.*cr\.itir.*=.*/.warning \"cr.itir should not used directly\"/g
-s/mov.*cr\.iha.*=.*/.warning \"cr.iha should not used directly\"/g
-s/mov.*cr\.ipsr.*=.*/.warning \"cr.ipsr should not used directly\"/g
-s/mov.*cr\.ifs.*=.*/.warning \"cr.ifs should not used directly\"/g
-s/mov.*cr\.iip.*=.*/.warning \"cr.iip should not used directly\"/g
-s/mov.*cr\.kr.*=.*/.warning \"cr.kr should not used directly\"/g
-s/mov.*ar\.eflags.*=.*/.warning \"ar.eflags should not used directly\"/g
-s/itc\.i.*/.warning \"itc.i should not be used directly.\"/g
-s/itc\.d.*/.warning \"itc.d should not be used directly.\"/g
-s/bsw\.0/.warning \"bsw.0 should not be used directly.\"/g
-s/bsw\.1/.warning \"bsw.1 should not be used directly.\"/g
-s/ptc\.ga.*/.warning \"ptc.ga should not be used directly.\"/g
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
index de651db20b43..14bf9b739dd2 100644
--- a/arch/m32r/include/asm/cmpxchg.h
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -107,8 +107,6 @@ __xchg_local(unsigned long x, volatile void *ptr, int size)
 	((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr),	\
 			sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 static inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
 {
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 9cc00dbd59ce..0c3f25ee3381 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -68,6 +68,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(off,size) ioremap(off,size)
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 /*
  * IO bus memory addresses are also 1:1 with the physical address
diff --git a/arch/m32r/include/asm/mm-arch-hooks.h b/arch/m32r/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..6d60b4750f41
--- /dev/null
+++ b/arch/m32r/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_M32R_MM_ARCH_HOOKS_H
+#define _ASM_M32R_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_M32R_MM_ARCH_HOOKS_H */
diff --git a/arch/m32r/include/asm/uaccess.h b/arch/m32r/include/asm/uaccess.h
index 71adff209405..cac7014daef3 100644
--- a/arch/m32r/include/asm/uaccess.h
+++ b/arch/m32r/include/asm/uaccess.h
@@ -91,7 +91,8 @@ static inline void set_fs(mm_segment_t s)
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -155,7 +156,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -175,7 +177,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -194,7 +197,8 @@ extern int fixup_exception(struct pt_regs *regs);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -274,7 +278,8 @@ do {									\
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -568,7 +573,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -588,7 +594,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -606,7 +613,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -626,7 +634,8 @@ unsigned long __generic_copy_from_user(void *, const void __user *, unsigned lon
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -677,7 +686,8 @@ unsigned long clear_user(void __user *mem, unsigned long len);
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c
index ce7aea34fdf4..c18ddc74ef9a 100644
--- a/arch/m32r/kernel/smp.c
+++ b/arch/m32r/kernel/smp.c
@@ -45,7 +45,7 @@ static volatile unsigned long flushcache_cpumask = 0;
 /*
  * For flush_tlb_others()
  */
-static volatile cpumask_t flush_cpumask;
+static cpumask_t flush_cpumask;
 static struct mm_struct *flush_mm;
 static struct vm_area_struct *flush_vma;
 static volatile unsigned long flush_va;
@@ -415,7 +415,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	 */
 	send_IPI_mask(&cpumask, INVALIDATE_TLB_IPI, 0);
 
-	while (!cpumask_empty((cpumask_t*)&flush_cpumask)) {
+	while (!cpumask_empty(&flush_cpumask)) {
 		/* nothing. lockup detection does not belong here */
 		mb();
 	}
@@ -468,7 +468,7 @@ void smp_invalidate_interrupt(void)
 			__flush_tlb_page(va);
 		}
 	}
-	cpumask_clear_cpu(cpu_id, (cpumask_t*)&flush_cpumask);
+	cpumask_clear_cpu(cpu_id, &flush_cpumask);
 }
 
 /*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e3d4d4890104..8f9875b7933d 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -24,9 +24,9 @@
 #include <linux/vt_kern.h>		/* For unblank_screen() */
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/m32r.h>
-#include <asm/uaccess.h>
 #include <asm/hardirq.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -111,10 +111,10 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	mm = tsk->mm;
 
 	/*
-	 * If we're in an interrupt or have no user context or are running in an
-	 * atomic region then we must not take the fault..
+	 * If we're in an interrupt or have no user context or have pagefaults
+	 * disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (error_code & ACE_USERMODE)
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index ed1643b4c678..753a6237f99a 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -177,9 +177,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -285,6 +287,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -324,6 +327,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -348,6 +352,7 @@ CONFIG_VETH=m
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_HP is not set
@@ -414,7 +419,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index d38822b1847e..1f93dcaf02e5 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -327,6 +331,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -375,7 +380,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index c429199cf4a9..831b8b8b92ad 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -281,6 +283,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -337,6 +341,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -391,7 +396,6 @@ CONFIG_DMASOUND_ATARI=m
 CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
-# CONFIG_HID_PLANTRONICS is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 9b880371d642..91fd187c16d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 49ae3376e993..9d4934f1d2c3 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -175,9 +175,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -265,7 +265,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -277,6 +279,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -306,6 +309,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -328,6 +332,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -378,7 +383,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index ee143a57058c..72bc187ca995 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -174,9 +174,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -267,7 +267,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -280,6 +282,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -315,6 +318,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -344,6 +348,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -400,7 +405,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index c777aa05048f..8fb65535597f 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -184,9 +184,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -277,7 +277,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -299,6 +301,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -348,6 +351,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -384,6 +388,7 @@ CONFIG_MVME147_NET=y
 CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_HP is not set
@@ -468,7 +473,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MSM6242=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index a7628a85e260..f34491ec0126 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -172,9 +172,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -262,7 +262,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -274,6 +276,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -304,6 +307,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ebaa68268a4a..3d3614d1b041 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -275,6 +277,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -305,6 +308,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -326,6 +330,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -369,7 +374,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2c16853aedd3..643e9c93bea7 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -173,9 +173,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -263,7 +263,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -278,6 +280,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -311,6 +314,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -334,6 +338,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_HP is not set
@@ -390,7 +395,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index e3056bf0f65b..8fecc5aa166c 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 73c36b7a0009..9902c5bfbdc8 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -170,9 +170,9 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NF_TABLES_ARP=m
+CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NFT_MASQ_IPV4=m
 CONFIG_NFT_REDIR_IPV4=m
@@ -260,7 +260,9 @@ CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
 CONFIG_NETLINK_DIAG=m
+CONFIG_MPLS=y
 CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
 # CONFIG_WIRELESS is not set
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
@@ -272,6 +274,7 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_PMEM=m
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
 CONFIG_DUMMY_IRQ=m
@@ -302,6 +305,7 @@ CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_LOG_WRITES=m
 CONFIG_TARGET_CORE=m
 CONFIG_TCM_IBLOCK=m
 CONFIG_TCM_FILEIO=m
@@ -324,6 +328,7 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -370,7 +375,6 @@ CONFIG_HID=m
 CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
-# CONFIG_HID_PLANTRONICS is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index bc755bc620ad..83b1df80f0ac 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -90,7 +90,6 @@ extern unsigned long __invalid_cmpxchg_size(volatile void *,
  * indicated by comparing RETURN with OLD.
  */
 #ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG	1
 
 static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 				      unsigned long new, int size)
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 8955b40a5dc4..618c85d3c786 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -20,6 +20,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
@@ -465,7 +467,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
-static inline void __iomem *ioremap_writethrough(unsigned long physaddr,
+static inline void __iomem *ioremap_wt(unsigned long physaddr,
 					 unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index a93c8cde4d38..ad7bd40e6742 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -3,6 +3,8 @@
 
 #ifdef __KERNEL__
 
+#define ARCH_HAS_IOREMAP_WT
+
 #include <asm/virtconvert.h>
 #include <asm-generic/iomap.h>
 
@@ -153,7 +155,7 @@ static inline void *ioremap_nocache(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
-static inline void *ioremap_writethrough(unsigned long physaddr, unsigned long size)
+static inline void *ioremap_wt(unsigned long physaddr, unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h
index a823cd73dc09..b5941818346f 100644
--- a/arch/m68k/include/asm/irqflags.h
+++ b/arch/m68k/include/asm/irqflags.h
@@ -2,9 +2,6 @@
 #define _M68K_IRQFLAGS_H
 
 #include <linux/types.h>
-#ifdef CONFIG_MMU
-#include <linux/preempt_mask.h>
-#endif
 #include <linux/preempt.h>
 #include <asm/thread_info.h>
 #include <asm/entry.h>
diff --git a/arch/m68k/include/asm/mm-arch-hooks.h b/arch/m68k/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..7e8709bc90ae
--- /dev/null
+++ b/arch/m68k/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_M68K_MM_ARCH_HOOKS_H
+#define _ASM_M68K_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_M68K_MM_ARCH_HOOKS_H */
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index e546a5534dd4..564665f9af30 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -120,13 +120,16 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
 }
 EXPORT_SYMBOL(dma_sync_single_for_device);
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
-			    enum dma_data_direction dir)
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+			    int nents, enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nents; sg++, i++)
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+	for_each_sg(sglist, sg, nents, i) {
+		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+					   dir);
+	}
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
 
@@ -151,14 +154,16 @@ dma_addr_t dma_map_page(struct device *dev, struct page *page,
 }
 EXPORT_SYMBOL(dma_map_page);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	       enum dma_data_direction dir)
 {
 	int i;
+	struct scatterlist *sg;
 
-	for (i = 0; i < nents; sg++, i++) {
+	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length, dir);
+		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
+					   dir);
 	}
 	return nents;
 }
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index b2f04aee46ec..6a94cdd0c830 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -10,10 +10,10 @@
 #include <linux/ptrace.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
 #include <asm/setup.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 extern void die_if_kernel(char *, struct pt_regs *, long);
@@ -81,7 +81,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index d703d8e26a65..5a696e507930 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -84,7 +84,7 @@ static inline void fence(void)
 #define read_barrier_depends()		do { } while (0)
 #define smp_read_barrier_depends()	do { } while (0)
 
-#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/metag/include/asm/cmpxchg.h b/arch/metag/include/asm/cmpxchg.h
index b1bc1be8540f..be29e3e44321 100644
--- a/arch/metag/include/asm/cmpxchg.h
+++ b/arch/metag/include/asm/cmpxchg.h
@@ -51,8 +51,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		__typeof__(*(ptr)) _o_ = (o);				\
diff --git a/arch/metag/include/asm/dma-mapping.h b/arch/metag/include/asm/dma-mapping.h
index 14b23efd9b7a..eb5cdec94be0 100644
--- a/arch/metag/include/asm/dma-mapping.h
+++ b/arch/metag/include/asm/dma-mapping.h
@@ -134,20 +134,24 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 }
 
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		    enum dma_data_direction direction)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		       enum dma_data_direction direction)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction direction)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		dma_sync_for_device(sg_virt(sg), sg->length, direction);
 }
 
diff --git a/arch/metag/include/asm/hugetlb.h b/arch/metag/include/asm/hugetlb.h
index 471f481e67f3..f730b396d79b 100644
--- a/arch/metag/include/asm/hugetlb.h
+++ b/arch/metag/include/asm/hugetlb.h
@@ -14,10 +14,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 int prepare_hugepage_range(struct file *file, unsigned long addr,
 						unsigned long len);
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index d5779b0ec573..9890f21eadbe 100644
--- a/arch/metag/include/asm/io.h
+++ b/arch/metag/include/asm/io.h
@@ -160,6 +160,9 @@ extern void __iounmap(void __iomem *addr);
 #define ioremap_wc(offset, size)                \
 	__ioremap((offset), (size), _PAGE_WR_COMBINE)
 
+#define ioremap_wt(offset, size)                \
+	__ioremap((offset), (size), 0)
+
 #define iounmap(addr)                           \
 	__iounmap(addr)
 
diff --git a/arch/metag/include/asm/mm-arch-hooks.h b/arch/metag/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..b0072b2eb0de
--- /dev/null
+++ b/arch/metag/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_METAG_MM_ARCH_HOOKS_H
+#define _ASM_METAG_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_METAG_MM_ARCH_HOOKS_H */
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2de5dc695a87..f57edca63609 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -105,7 +105,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 
 	mm = tsk->mm;
 
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/metag/mm/highmem.c b/arch/metag/mm/highmem.c
index d71f621a2c0b..807f1b1c4e65 100644
--- a/arch/metag/mm/highmem.c
+++ b/arch/metag/mm/highmem.c
@@ -43,7 +43,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -82,6 +82,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -95,6 +96,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	unsigned long vaddr;
 	int type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
diff --git a/arch/metag/mm/hugetlbpage.c b/arch/metag/mm/hugetlbpage.c
index 7ca80ac42ed5..53f0f6c47027 100644
--- a/arch/metag/mm/hugetlbpage.c
+++ b/arch/metag/mm/hugetlbpage.c
@@ -89,11 +89,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_page_shift(pmd) > PAGE_SHIFT;
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 940f5fc1d1da..39b6315db82e 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -39,10 +39,10 @@ extern resource_size_t isa_mem_base;
 extern void iounmap(void __iomem *addr);
 
 extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
-#define ioremap_writethrough(addr, size)	ioremap((addr), (size))
 #define ioremap_nocache(addr, size)		ioremap((addr), (size))
 #define ioremap_fullcache(addr, size)		ioremap((addr), (size))
 #define ioremap_wc(addr, size)			ioremap((addr), (size))
+#define ioremap_wt(addr, size)			ioremap((addr), (size))
 
 #endif /* CONFIG_MMU */
 
diff --git a/arch/microblaze/include/asm/mm-arch-hooks.h b/arch/microblaze/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..5c4065911bda
--- /dev/null
+++ b/arch/microblaze/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
+#define _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MICROBLAZE_MM_ARCH_HOOKS_H */
diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h
index 81f27aef979c..dc9eb6657e3a 100644
--- a/arch/microblaze/include/asm/pci.h
+++ b/arch/microblaze/include/asm/pci.h
@@ -27,8 +27,6 @@
 #define PCIBIOS_MIN_IO		0x1000
 #define PCIBIOS_MIN_MEM		0x10000000
 
-struct pci_dev;
-
 /* Values for the `which' argument to sys_pciconfig_iobase syscall.  */
 #define IOBASE_BRIDGE_NUMBER	0
 #define IOBASE_MEMORY		1
@@ -44,16 +42,6 @@ struct pci_dev;
  */
 #define pcibios_assign_all_busses()	0
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 extern int pci_domain_nr(struct pci_bus *bus);
 
 /* Decide whether to display the domain number in /proc */
@@ -83,40 +71,12 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
-			struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
 
 extern void pcibios_resource_survey(void);
 
-extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
-extern int remove_phb_dynamic(struct pci_controller *phb);
-
-extern struct pci_dev *of_create_pci_dev(struct device_node *node,
-					struct pci_bus *bus, int devfn);
-
-extern void of_scan_pci_bridge(struct device_node *node,
-				struct pci_dev *dev);
-
-extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
-extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
-
-extern int pci_bus_find_capability(struct pci_bus *bus,
-						unsigned int devfn, int cap);
-
 struct file;
 extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
 					 unsigned long pfn,
diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h
index 62942fd12672..331b0d35f89c 100644
--- a/arch/microblaze/include/asm/uaccess.h
+++ b/arch/microblaze/include/asm/uaccess.h
@@ -178,7 +178,8 @@ extern long __user_bad(void);
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -290,7 +291,8 @@ extern long __user_bad(void);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index d1dd6e83d59b..b70bb538f001 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -47,6 +47,8 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
 	{"9.1", 0x1d},
 	{"9.2", 0x1f},
 	{"9.3", 0x20},
+	{"9.4", 0x21},
+	{"9.5", 0x22},
 	{NULL, 0},
 };
 
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index ed7ba8a11822..bf4dec229437 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -154,6 +154,7 @@ dma_direct_sync_sg_for_device(struct device *dev,
 			__dma_sync(sg->dma_address, sg->length, direction);
 }
 
+static
 int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 			     void *cpu_addr, dma_addr_t handle, size_t size,
 			     struct dma_attrs *attrs)
diff --git a/arch/microblaze/kernel/kgdb.c b/arch/microblaze/kernel/kgdb.c
index 8736af5806ae..6366f69d118e 100644
--- a/arch/microblaze/kernel/kgdb.c
+++ b/arch/microblaze/kernel/kgdb.c
@@ -32,7 +32,7 @@
 #define GDB_RTLBHI	56
 
 /* keep pvr separately because it is unchangeble */
-struct pvr_s pvr;
+static struct pvr_s pvr;
 
 void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index d46a5ebb7570..177dfc003643 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -107,14 +107,14 @@ void do_page_fault(struct pt_regs *regs, unsigned long address,
 	if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
 		is_write = 0;
 
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		if (kernel_mode(regs))
 			goto bad_area_nosemaphore;
 
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
-		pr_emerg("Page fault in user mode with in_atomic(), mm = %p\n",
-									mm);
+		pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
+			 mm);
 		pr_emerg("r15 = %lx  MSR = %lx\n",
 		       regs->r15, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
index 5a92576fad92..2fcc5a52d84d 100644
--- a/arch/microblaze/mm/highmem.c
+++ b/arch/microblaze/mm/highmem.c
@@ -37,7 +37,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -63,6 +63,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -84,5 +85,6 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f5016656494f..b65edf514b40 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -819,6 +819,7 @@ config CAVIUM_OCTEON_SOC
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select EDAC_SUPPORT
+	select EDAC_ATOMIC_SCRUB
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HOTPLUG_CPU if CPU_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 5200f649dd4e..ae2dd59050f7 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -277,7 +277,7 @@ LDFLAGS			+= -m $(ld-emul)
 ifdef CONFIG_MIPS
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
-	sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/")
+	sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
 ifdef CONFIG_64BIT
 CHECKFLAGS		+= -m64
 endif
diff --git a/arch/mips/ath79/prom.c b/arch/mips/ath79/prom.c
index e1fe63051136..597899ad5438 100644
--- a/arch/mips/ath79/prom.c
+++ b/arch/mips/ath79/prom.c
@@ -1,6 +1,7 @@
 /*
  *  Atheros AR71XX/AR724X/AR913X specific prom routines
  *
+ *  Copyright (C) 2015 Laurent Fasnacht <l@libres.ch>
  *  Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
  *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
  *
@@ -25,12 +26,14 @@ void __init prom_init(void)
 {
 	fw_init_cmdline();
 
+#ifdef CONFIG_BLK_DEV_INITRD
 	/* Read the initrd address from the firmware environment */
 	initrd_start = fw_getenvl("initrd_start");
 	if (initrd_start) {
 		initrd_start = KSEG0ADDR(initrd_start);
 		initrd_end = initrd_start + fw_getenvl("initrd_size");
 	}
+#endif
 }
 
 void __init prom_free_prom_memory(void)
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index a73c93c3d44a..7fc8397d16f2 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -225,7 +225,7 @@ void __init plat_time_init(void)
 	ddr_clk_rate = ath79_get_sys_clk_rate("ddr");
 	ref_clk_rate = ath79_get_sys_clk_rate("ref");
 
-	pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz",
+	pr_info("Clocks: CPU:%lu.%03luMHz, DDR:%lu.%03luMHz, AHB:%lu.%03luMHz, Ref:%lu.%03luMHz\n",
 		cpu_clk_rate / 1000000, (cpu_clk_rate / 1000) % 1000,
 		ddr_clk_rate / 1000000, (ddr_clk_rate / 1000) % 1000,
 		ahb_clk_rate / 1000000, (ahb_clk_rate / 1000) % 1000,
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index 12dccdb38286..af4c712f7afc 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -69,10 +69,10 @@ static int octeon_md5_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = cpu_to_le32(0x67452301);
-	mctx->hash[1] = cpu_to_le32(0xefcdab89);
-	mctx->hash[2] = cpu_to_le32(0x98badcfe);
-	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/mips/cobalt/Makefile b/arch/mips/cobalt/Makefile
index 558e94977942..68f0c5871adc 100644
--- a/arch/mips/cobalt/Makefile
+++ b/arch/mips/cobalt/Makefile
@@ -2,7 +2,6 @@
 # Makefile for the Cobalt micro systems family specific parts of the kernel
 #
 
-obj-y := buttons.o irq.o lcd.o led.o reset.o rtc.o serial.o setup.o time.o
+obj-y := buttons.o irq.o lcd.o led.o mtd.o reset.o rtc.o serial.o setup.o time.o
 
 obj-$(CONFIG_PCI)		+= pci.o
-obj-$(CONFIG_MTD_PHYSMAP)	+= mtd.o
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 002680648dcb..b2a577ebce0b 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -194,7 +194,7 @@ CONFIG_USB_WUSB_CBAF=m
 CONFIG_USB_C67X00_HCD=m
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_ISP1760_HCD=m
+CONFIG_USB_ISP1760=m
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_UHCI_HCD=m
 CONFIG_USB_R8A66597_HCD=m
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 2b8bbbcb9be0..7ecba84656d4 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -112,8 +112,8 @@
 #define __WEAK_LLSC_MB		"		\n"
 #endif
 
-#define set_mb(var, value) \
-	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_llsc_mb()	__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
 
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 412f945f1f5e..b71ab4a5fd50 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -138,8 +138,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))));	\
 })
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define __cmpxchg_asm(ld, st, m, old, new)				\
 ({									\
 	__typeof(*(m)) __ret;						\
diff --git a/arch/mips/include/asm/edac.h b/arch/mips/include/asm/edac.h
index 94105d3f58f4..980b16527374 100644
--- a/arch/mips/include/asm/edac.h
+++ b/arch/mips/include/asm/edac.h
@@ -5,7 +5,7 @@
 
 /* ECC atomic, DMA, SMP and interrupt safe scrub function */
 
-static inline void atomic_scrub(void *va, u32 size)
+static inline void edac_atomic_scrub(void *va, u32 size)
 {
 	unsigned long *virt_addr = va;
 	unsigned long temp;
@@ -21,7 +21,7 @@ static inline void atomic_scrub(void *va, u32 size)
 
 		__asm__ __volatile__ (
 		"	.set	mips2					\n"
-		"1:	ll	%0, %1		# atomic_scrub		\n"
+		"1:	ll	%0, %1		# edac_atomic_scrub	\n"
 		"	addu	%0, $0					\n"
 		"	sc	%0, %1					\n"
 		"	beqz	%0, 1b					\n"
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index a594d8ed9698..f19e890b99d2 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -304,7 +304,7 @@ do {									\
 									\
 	current->thread.abi = &mips_abi;				\
 									\
-	current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31;		\
+	current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31;		\
 } while (0)
 
 #endif /* CONFIG_32BIT */
@@ -366,7 +366,7 @@ do {									\
 	else								\
 		current->thread.abi = &mips_abi;			\
 									\
-	current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31;		\
+	current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31;		\
 									\
 	p = personality(current->personality);				\
 	if (p != PER_LINUX32 && p != PER_LINUX)				\
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index fe0d15d32660..4a5bb5453408 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -38,10 +38,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr,
 					  unsigned long end,
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 4c25823563fe..e8c8d9d0c45f 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -839,7 +839,7 @@ static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
 static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *slot) {}
diff --git a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h b/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
index aa2283e602fc..aa71216edf99 100644
--- a/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
+++ b/arch/mips/include/asm/mach-ath79/ath79_spi_platform.h
@@ -16,8 +16,4 @@ struct ath79_spi_platform_data {
 	unsigned	num_chipselect;
 };
 
-struct ath79_spi_controller_data {
-	unsigned	gpio;
-};
-
 #endif /* _ATH79_SPI_PLATFORM_H */
diff --git a/arch/mips/include/asm/mm-arch-hooks.h b/arch/mips/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..b5609fe8e475
--- /dev/null
+++ b/arch/mips/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_MIPS_MM_ARCH_HOOKS_H
+#define _ASM_MIPS_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MIPS_MM_ARCH_HOOKS_H */
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 3413b10d833b..98c31e5d9579 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -113,16 +113,6 @@ struct pci_dev;
  */
 extern unsigned int PCI_DMA_BUS_IS_PHYS;
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #ifdef CONFIG_PCI_DOMAINS
 #define pci_domain_nr(bus) ((struct pci_controller *)(bus)->sysdata)->index
 
diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h
index 18ae5ddef118..c28a8499aec7 100644
--- a/arch/mips/include/asm/pgtable-bits.h
+++ b/arch/mips/include/asm/pgtable-bits.h
@@ -113,7 +113,7 @@
 #define _PAGE_PRESENT_SHIFT	0
 #define _PAGE_PRESENT		(1 << _PAGE_PRESENT_SHIFT)
 /* R2 or later cores check for RI/XI support to determine _PAGE_READ */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 #define _PAGE_WRITE_SHIFT	(_PAGE_PRESENT_SHIFT + 1)
 #define _PAGE_WRITE		(1 << _PAGE_WRITE_SHIFT)
 #else
@@ -135,16 +135,16 @@
 #define _PAGE_SPLITTING		(1 << _PAGE_SPLITTING_SHIFT)
 
 /* Only R2 or newer cores have the XI bit */
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 #define _PAGE_NO_EXEC_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
 #else
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_SPLITTING_SHIFT + 1)
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-#endif	/* CONFIG_CPU_MIPSR2 */
+#endif	/* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 
 #endif	/* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */
 
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 /* XI - page cannot be executed */
 #ifndef _PAGE_NO_EXEC_SHIFT
 #define _PAGE_NO_EXEC_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
@@ -160,10 +160,10 @@
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_NO_READ_SHIFT + 1)
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
 
-#else	/* !CONFIG_CPU_MIPSR2 */
+#else	/* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */
 #define _PAGE_GLOBAL_SHIFT	(_PAGE_MODIFIED_SHIFT + 1)
 #define _PAGE_GLOBAL		(1 << _PAGE_GLOBAL_SHIFT)
-#endif	/* CONFIG_CPU_MIPSR2 */
+#endif	/* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 
 #define _PAGE_VALID_SHIFT	(_PAGE_GLOBAL_SHIFT + 1)
 #define _PAGE_VALID		(1 << _PAGE_VALID_SHIFT)
@@ -205,7 +205,7 @@
  */
 static inline uint64_t pte_to_entrylo(unsigned long pte_val)
 {
-#ifdef CONFIG_CPU_MIPSR2
+#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	if (cpu_has_rixi) {
 		int sa;
 #ifdef CONFIG_32BIT
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 819af9d057a8..9d8106758142 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -568,12 +568,12 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 }
 
 /*
- * The generic version pmdp_get_and_clear uses a version of pmd_clear() with a
+ * The generic version pmdp_huge_get_and_clear uses a version of pmd_clear() with a
  * different prototype.
  */
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	pmd_t old = *pmdp;
 
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index bb02fac9b4fa..2b25d1ba1ea0 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -45,7 +45,7 @@ extern int __cpu_logical_map[NR_CPUS];
 #define SMP_DUMP		0x8
 #define SMP_ASK_C0COUNT		0x10
 
-extern volatile cpumask_t cpu_callin_map;
+extern cpumask_t cpu_callin_map;
 
 /* Mask of CPUs which are currently definitely operating coherently */
 extern cpumask_t cpu_coherent_mask;
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index e92d6c4b5ed1..7163cd7fdd69 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -104,7 +104,6 @@ do {									\
 	if (test_and_clear_tsk_thread_flag(prev, TIF_USEDMSA))		\
 		__fpsave = FP_SAVE_VECTOR;				\
 	(last) = resume(prev, next, task_thread_info(next), __fpsave);	\
-	disable_msa();							\
 } while (0)
 
 #define finish_arch_switch(prev)					\
@@ -122,6 +121,7 @@ do {									\
 	if (cpu_has_userlocal)						\
 		write_c0_userlocal(current_thread_info()->tp_value);	\
 	__restore_watch();						\
+	disable_msa();							\
 } while (0)
 
 #endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 3e307ec2afba..7afda4150a59 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -15,7 +15,7 @@
 #define topology_physical_package_id(cpu)	(cpu_data[cpu].package)
 #define topology_core_id(cpu)			(cpu_data[cpu].core)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&cpu_sibling_map[cpu])
+#define topology_sibling_cpumask(cpu)		(&cpu_sibling_map[cpu])
 #endif
 
 #endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index bf8b32450ef6..9722357d2854 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -103,7 +103,8 @@ extern u64 __ua_limit;
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -138,7 +139,8 @@ extern u64 __ua_limit;
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -157,7 +159,8 @@ extern u64 __ua_limit;
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -177,7 +180,8 @@ extern u64 __ua_limit;
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -199,7 +203,8 @@ extern u64 __ua_limit;
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -498,7 +503,8 @@ extern void __put_user_unknown(void);
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -517,7 +523,8 @@ extern void __put_user_unknown(void);
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -537,7 +544,8 @@ extern void __put_user_unknown(void);
  * @x:	 Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -559,7 +567,8 @@ extern void __put_user_unknown(void);
  * @x:	 Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -815,7 +824,8 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -888,7 +898,8 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -1075,7 +1086,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -1107,7 +1119,8 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -1329,7 +1342,8 @@ strncpy_from_user(char *__to, const char __user *__from, long __len)
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
@@ -1398,7 +1412,8 @@ static inline long __strnlen_user(const char __user *s, long n)
  * strnlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index e36515dcd3b2..209e5b76c1bc 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -74,13 +74,12 @@ static inline void cpu_set_fpu_fcsr_mask(struct cpuinfo_mips *c)
 {
 	unsigned long sr, mask, fcsr, fcsr0, fcsr1;
 
+	fcsr = c->fpu_csr31;
 	mask = FPU_CSR_ALL_X | FPU_CSR_ALL_E | FPU_CSR_ALL_S | FPU_CSR_RM;
 
 	sr = read_c0_status();
 	__enable_fpu(FPU_AS_IS);
 
-	fcsr = read_32bit_cp1_register(CP1_STATUS);
-
 	fcsr0 = fcsr & mask;
 	write_32bit_cp1_register(CP1_STATUS, fcsr0);
 	fcsr0 = read_32bit_cp1_register(CP1_STATUS);
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index be4899f3c393..4a4d9e067c89 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -76,14 +76,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 
 	/* Lets see if this is an O32 ELF */
 	if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) {
-		/* FR = 1 for N32 */
-		if (ehdr32->e_flags & EF_MIPS_ABI2)
-			state->overall_fp_mode = FP_FR1;
-		else
-			/* Set a good default FPU mode for O32 */
-			state->overall_fp_mode = cpu_has_mips_r6 ?
-				FP_FRE : FP_FR0;
-
 		if (ehdr32->e_flags & EF_MIPS_FP64) {
 			/*
 			 * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it
@@ -104,9 +96,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 				  (char *)&abiflags,
 				  sizeof(abiflags));
 	} else {
-		/* FR=1 is really the only option for 64-bit */
-		state->overall_fp_mode = FP_FR1;
-
 		if (phdr64->p_type != PT_MIPS_ABIFLAGS)
 			return 0;
 		if (phdr64->p_filesz < sizeof(abiflags))
@@ -137,6 +126,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
 	struct elf32_hdr *ehdr = _ehdr;
 	struct mode_req prog_req, interp_req;
 	int fp_abi, interp_fp_abi, abi0, abi1, max_abi;
+	bool is_mips64;
 
 	if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
 		return 0;
@@ -152,10 +142,22 @@ int arch_check_elf(void *_ehdr, bool has_interpreter,
 		abi0 = abi1 = fp_abi;
 	}
 
-	/* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */
-	max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) &&
-		   (!(ehdr->e_flags & EF_MIPS_ABI2))) ?
-		MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT;
+	is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) ||
+		    (ehdr->e_flags & EF_MIPS_ABI2);
+
+	if (is_mips64) {
+		/* MIPS64 code always uses FR=1, thus the default is easy */
+		state->overall_fp_mode = FP_FR1;
+
+		/* Disallow access to the various FPXX & FP64 ABIs */
+		max_abi = MIPS_ABI_FP_SOFT;
+	} else {
+		/* Default to a mode capable of running code expecting FR=0 */
+		state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0;
+
+		/* Allow all ABIs we know about */
+		max_abi = MIPS_ABI_FP_64A;
+	}
 
 	if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) ||
 	    (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN))
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2e8995..3c8a18a00a65 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -29,7 +29,7 @@
 int kgdb_early_setup;
 #endif
 
-static unsigned long irq_map[NR_IRQS / BITS_PER_LONG];
+static DECLARE_BITMAP(irq_map, NR_IRQS);
 
 int allocate_irqno(void)
 {
@@ -109,7 +109,7 @@ void __init init_IRQ(void)
 #endif
 }
 
-#ifdef DEBUG_STACKOVERFLOW
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
 static inline void check_stack_overflow(void)
 {
 	unsigned long sp;
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index d544e774eea6..e933a309f2ea 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -176,7 +176,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data)
 
 	__get_user(value, data + 64);
 	fcr31 = child->thread.fpu.fcr31;
-	mask = current_cpu_data.fpu_msk31;
+	mask = boot_cpu_data.fpu_msk31;
 	child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask);
 
 	/* FIR may not be written.  */
diff --git a/arch/mips/kernel/signal-common.h b/arch/mips/kernel/signal-common.h
index 06805e09bcd3..0b85f827cd18 100644
--- a/arch/mips/kernel/signal-common.h
+++ b/arch/mips/kernel/signal-common.h
@@ -28,12 +28,7 @@ extern void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 extern int fpcsr_pending(unsigned int __user *fpcsr);
 
 /* Make sure we will not lose FPU ownership */
-#ifdef CONFIG_PREEMPT
-#define lock_fpu_owner()	preempt_disable()
-#define unlock_fpu_owner()	preempt_enable()
-#else
-#define lock_fpu_owner()	pagefault_disable()
-#define unlock_fpu_owner()	pagefault_enable()
-#endif
+#define lock_fpu_owner()	({ preempt_disable(); pagefault_disable(); })
+#define unlock_fpu_owner()	({ pagefault_enable(); preempt_enable(); })
 
 #endif	/* __SIGNAL_COMMON_H */
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index fd528d7ea278..336708ae5c5b 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -444,7 +444,7 @@ struct plat_smp_ops bmips5000_smp_ops = {
 static void bmips_wr_vec(unsigned long dst, char *start, char *end)
 {
 	memcpy((void *)dst, start, end - start);
-	dma_cache_wback((unsigned long)start, end - start);
+	dma_cache_wback(dst, end - start);
 	local_flush_icache_range(dst, dst + (end - start));
 	instruction_hazard();
 }
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 7e011f95bb8e..4251d390b5b6 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -92,7 +92,7 @@ static void __init cps_smp_setup(void)
 #ifdef CONFIG_MIPS_MT_FPAFF
 	/* If we have an FPU, enroll ourselves in the FPU-full mask */
 	if (cpu_has_fpu)
-		cpu_set(0, mt_fpu_cpumask);
+		cpumask_set_cpu(0, &mt_fpu_cpumask);
 #endif /* CONFIG_MIPS_MT_FPAFF */
 }
 
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 193ace7955fb..faa46ebd9dda 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -43,7 +43,7 @@
 #include <asm/time.h>
 #include <asm/setup.h>
 
-volatile cpumask_t cpu_callin_map;	/* Bitmask of started secondaries */
+cpumask_t cpu_callin_map;		/* Bitmask of started secondaries */
 
 int __cpu_number_map[NR_CPUS];		/* Map physical to logical */
 EXPORT_SYMBOL(__cpu_number_map);
@@ -218,8 +218,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	/*
 	 * Trust is futile.  We should really have timeouts ...
 	 */
-	while (!cpumask_test_cpu(cpu, &cpu_callin_map))
+	while (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
 		udelay(100);
+		schedule();
+	}
 
 	synchronise_count_master(cpu);
 	return 0;
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ba32e48d4697..d2d1c1933bc9 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -269,7 +269,6 @@ static void __show_regs(const struct pt_regs *regs)
 	 */
 	printk("epc   : %0*lx %pS\n", field, regs->cp0_epc,
 	       (void *) regs->cp0_epc);
-	printk("    %s\n", print_tainted());
 	printk("ra    : %0*lx %pS\n", field, regs->regs[31],
 	       (void *) regs->regs[31]);
 
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 6230f376a44e..d5fa3eaf39a1 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -2389,7 +2389,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 {
 	unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr];
 	enum emulation_result er = EMULATE_DONE;
-	unsigned long curr_pc;
 
 	if (run->mmio.len > sizeof(*gpr)) {
 		kvm_err("Bad MMIO length: %d", run->mmio.len);
@@ -2397,11 +2396,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		goto done;
 	}
 
-	/*
-	 * Update PC and hold onto current PC in case there is
-	 * an error and we want to rollback the PC
-	 */
-	curr_pc = vcpu->arch.pc;
 	er = update_pc(vcpu, vcpu->arch.pending_load_cause);
 	if (er == EMULATE_FAIL)
 		return er;
@@ -2415,7 +2409,7 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
 		if (vcpu->mmio_needed == 2)
 			*gpr = *(int16_t *) run->mmio.data;
 		else
-			*gpr = *(int16_t *) run->mmio.data;
+			*gpr = *(uint16_t *)run->mmio.data;
 
 		break;
 	case 1:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index bb68e8d520e8..cd4c129ce743 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -198,15 +198,16 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   const struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
 	unsigned long npages = 0;
@@ -393,7 +394,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	kvm_mips_deliver_interrupts(vcpu,
 				    kvm_read_c0_guest_cause(vcpu->arch.cop0));
 
-	kvm_guest_enter();
+	__kvm_guest_enter();
 
 	/* Disable hardware page table walking while in guest */
 	htw_stop();
@@ -403,7 +404,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	/* Re-enable HTW before enabling interrupts */
 	htw_start();
 
-	kvm_guest_exit();
+	__kvm_guest_exit();
 	local_irq_enable();
 
 	if (vcpu->sigset_active)
@@ -968,6 +969,7 @@ out:
 /* Get (and clear) the dirty memory log for a memory slot. */
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	unsigned long ga, ga_end;
 	int is_dirty = 0;
@@ -982,7 +984,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = &kvm->memslots->memslots[log->slot];
+		slots = kvm_memslots(kvm);
+		memslot = id_to_memslot(slots, log->slot);
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index 7d12c0dded3d..77e64942f004 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -34,7 +34,12 @@ LEAF(__strnlen_\func\()_asm)
 FEXPORT(__strnlen_\func\()_nocheck_asm)
 	move		v0, a0
 	PTR_ADDU	a1, a0			# stop pointer
-1:	beq		v0, a1, 1f		# limit reached?
+1:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+	.set		noat
+	li		AT, 1
+#endif
+	beq		v0, a1, 1f		# limit reached?
 .ifeqs "\func", "kernel"
 	EX(lb, t0, (v0), .Lfault\@)
 .else
@@ -42,7 +47,13 @@ FEXPORT(__strnlen_\func\()_nocheck_asm)
 .endif
 	.set		noreorder
 	bnez		t0, 1b
-1:	 PTR_ADDIU	v0, 1
+1:
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+	 PTR_ADDIU	v0, 1
+#else
+	 PTR_ADDU	v0, AT
+	.set		at
+#endif
 	.set		reorder
 	PTR_SUBU	v0, a0
 	jr		ra
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index e70c33fdb881..f2e8153e44f5 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -3,15 +3,13 @@
 #
 
 obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
-    bonito-irq.o mem.o machtype.o platform.o
+    bonito-irq.o mem.o machtype.o platform.o serial.o
 obj-$(CONFIG_PCI) += pci.o
 
 #
 # Serial port support
 #
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
-obj-y += $(loongson-serial-m) $(loongson-serial-y)
 obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
 obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
 
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index e3c68b5da18d..509877c6e9d9 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -272,7 +272,7 @@ void loongson3_ipi_interrupt(struct pt_regs *regs)
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);
 		c0count = read_c0_count();
-		for (i = 1; i < loongson_sysconf.nr_cpus; i++)
+		for (i = 1; i < num_possible_cpus(); i++)
 			per_cpu(core0_c0count, i) = c0count;
 	}
 }
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index d31c537ace1d..22b9b2cb9219 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -889,7 +889,7 @@ static inline void cop1_cfc(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		break;
 
 	case FPCREG_RID:
-		value = current_cpu_data.fpu_id;
+		value = boot_cpu_data.fpu_id;
 		break;
 
 	default:
@@ -921,7 +921,7 @@ static inline void cop1_ctc(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			 (void *)xcp->cp0_epc, MIPSInst_RT(ir), value);
 
 		/* Preserve read-only bits.  */
-		mask = current_cpu_data.fpu_msk31;
+		mask = boot_cpu_data.fpu_msk31;
 		fcr31 = (value & ~mask) | (fcr31 & mask);
 		break;
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 0dbb65a51ce5..2e03ab173591 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1372,7 +1372,7 @@ static int probe_scache(void)
 	scache_size = addr;
 	c->scache.linesz = 16 << ((config & R4K_CONF_SB) >> 22);
 	c->scache.ways = 1;
-	c->dcache.waybit = 0;		/* does not matter */
+	c->scache.waybit = 0;		/* does not matter */
 
 	return 1;
 }
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 7ff8637e530d..36c0f26fac6b 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -21,10 +21,10 @@
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
+#include <linux/uaccess.h>
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/ptrace.h>
 #include <asm/highmem.h>		/* For VMALLOC_END */
 #include <linux/kdebug.h>
@@ -94,7 +94,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index da815d295239..11661cbc11a8 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -47,7 +47,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -72,6 +72,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -92,6 +93,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
@@ -104,6 +106,7 @@ void *kmap_atomic_pfn(unsigned long pfn)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 06e0f421b41b..74aa6f62468f 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -51,11 +51,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return (pte_t *) pmd;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 /*
  * This function checks for proper alignment of input addr and len parameters.
  */
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index faa5c9822ecc..198a3147dd7d 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -90,6 +90,7 @@ static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot)
 
 	BUG_ON(Page_dcache_dirty(page));
 
+	preempt_disable();
 	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 	idx += in_interrupt() ? FIX_N_COLOURS : 0;
@@ -152,6 +153,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	local_irq_restore(flags);
 	pagefault_enable();
+	preempt_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index a27a088e6f9f..08318ecb803a 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -495,7 +495,7 @@ static void r4k_tlb_configure(void)
 
 	if (cpu_has_rixi) {
 		/*
-		 * Enable the no read, no exec bits, and enable large virtual
+		 * Enable the no read, no exec bits, and enable large physical
 		 * address.
 		 */
 #ifdef CONFIG_64BIT
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 5d6139390bf8..e23fdf2a9c80 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -681,11 +681,7 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx)
 		sp_off += config_enabled(CONFIG_64BIT) ?
 			(ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE;
 
-	/*
-	 * Subtract the bytes for the last registers since we only care about
-	 * the location on the stack pointer.
-	 */
-	return sp_off - RSIZE;
+	return sp_off;
 }
 
 static void build_prologue(struct jit_ctx *ctx)
diff --git a/arch/mips/pci/fixup-cobalt.c b/arch/mips/pci/fixup-cobalt.c
index a138e8ee5cfc..b3ab59318d91 100644
--- a/arch/mips/pci/fixup-cobalt.c
+++ b/arch/mips/pci/fixup-cobalt.c
@@ -13,7 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 
-#include <asm/pci.h>
 #include <asm/io.h>
 #include <asm/gt64120.h>
 
diff --git a/arch/mips/pci/ops-mace.c b/arch/mips/pci/ops-mace.c
index 6b5821febc38..951d8070fb48 100644
--- a/arch/mips/pci/ops-mace.c
+++ b/arch/mips/pci/ops-mace.c
@@ -8,7 +8,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/types.h>
-#include <asm/pci.h>
 #include <asm/ip32/mace.h>
 
 #if 0
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 8b117e638306..c5347d99cf3a 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -20,7 +20,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 
-#include <asm/pci.h>
 #include <asm/gpio.h>
 #include <asm/addrspace.h>
 
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index e20b02e3ae28..e10d10b9e82a 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -41,7 +41,7 @@ static irqreturn_t ill_acc_irq_handler(int irq, void *_priv)
 		addr, (type >> ILL_ACC_OFF_S) & ILL_ACC_OFF_M,
 		type & ILL_ACC_LEN_M);
 
-	rt_memc_w32(REG_ILL_ACC_TYPE, REG_ILL_ACC_TYPE);
+	rt_memc_w32(ILL_INT_STATUS, REG_ILL_ACC_TYPE);
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/sgi-ip32/ip32-platform.c b/arch/mips/sgi-ip32/ip32-platform.c
index 0134db2ad0a8..5a2a82148d8d 100644
--- a/arch/mips/sgi-ip32/ip32-platform.c
+++ b/arch/mips/sgi-ip32/ip32-platform.c
@@ -130,9 +130,9 @@ struct platform_device ip32_rtc_device = {
 	.resource		= ip32_rtc_resources,
 };
 
-+static int __init sgio2_rtc_devinit(void)
+static __init int sgio2_rtc_devinit(void)
 {
 	return platform_device_register(&ip32_rtc_device);
 }
 
-device_initcall(sgio2_cmos_devinit);
+device_initcall(sgio2_rtc_devinit);
diff --git a/arch/mn10300/include/asm/highmem.h b/arch/mn10300/include/asm/highmem.h
index 2fbbe4d920aa..1ddea5afba09 100644
--- a/arch/mn10300/include/asm/highmem.h
+++ b/arch/mn10300/include/asm/highmem.h
@@ -75,6 +75,7 @@ static inline void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 	if (page < highmem_start_page)
 		return page_address(page);
@@ -98,6 +99,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 
 	if (vaddr < FIXADDR_START) { /* FIXME */
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -122,6 +124,7 @@ static inline void __kunmap_atomic(unsigned long vaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 #endif /* __KERNEL__ */
 
diff --git a/arch/mn10300/include/asm/io.h b/arch/mn10300/include/asm/io.h
index cc4a2ba9e228..07c5b4a3903b 100644
--- a/arch/mn10300/include/asm/io.h
+++ b/arch/mn10300/include/asm/io.h
@@ -282,6 +282,7 @@ static inline void __iomem *ioremap_nocache(unsigned long offset, unsigned long
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 static inline void iounmap(void __iomem *addr)
 {
diff --git a/arch/mn10300/include/asm/mm-arch-hooks.h b/arch/mn10300/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..e2029a652f4c
--- /dev/null
+++ b/arch/mn10300/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_MN10300_MM_ARCH_HOOKS_H
+#define _ASM_MN10300_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_MN10300_MM_ARCH_HOOKS_H */
diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h
index 393b51d38f36..be3debb8fc02 100644
--- a/arch/mn10300/include/asm/pci.h
+++ b/arch/mn10300/include/asm/pci.h
@@ -83,19 +83,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 0c2cc5d39c8e..4a1d181ed32f 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -23,8 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 #include <asm/hardirq.h>
 #include <asm/cpu-regs.h>
@@ -168,7 +168,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long fault_code,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
diff --git a/arch/nios2/include/asm/io.h b/arch/nios2/include/asm/io.h
index 6e24d7cceb0c..c5a62da22cd2 100644
--- a/arch/nios2/include/asm/io.h
+++ b/arch/nios2/include/asm/io.h
@@ -46,6 +46,7 @@ static inline void iounmap(void __iomem *addr)
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 /* Pages to physical address... */
 #define page_to_phys(page)	virt_to_phys(page_to_virt(page))
diff --git a/arch/nios2/include/asm/mm-arch-hooks.h b/arch/nios2/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..d7290dc68558
--- /dev/null
+++ b/arch/nios2/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_NIOS2_MM_ARCH_HOOKS_H
+#define _ASM_NIOS2_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_NIOS2_MM_ARCH_HOOKS_H */
diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c
index 7f4547418ee1..be186a75f622 100644
--- a/arch/nios2/kernel/time.c
+++ b/arch/nios2/kernel/time.c
@@ -8,6 +8,7 @@
  * for more details.
  */
 
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/clockchips.h>
 #include <linux/clocksource.h>
@@ -106,6 +107,7 @@ cycles_t get_cycles(void)
 {
 	return nios2_timer_read(&nios2_cs.cs);
 }
+EXPORT_SYMBOL(get_cycles);
 
 static void nios2_timer_start(struct nios2_timer *timer)
 {
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 0c9b6afe69e9..b51878b0c6b8 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -77,7 +77,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/openrisc/include/asm/mm-arch-hooks.h b/arch/openrisc/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..6d33cb555fe1
--- /dev/null
+++ b/arch/openrisc/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_OPENRISC_MM_ARCH_HOOKS_H
+#define _ASM_OPENRISC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_OPENRISC_MM_ARCH_HOOKS_H */
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index de65f66ea64e..ec2df4bab302 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -142,6 +142,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
+	preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -150,6 +151,7 @@ static inline void __kunmap_atomic(void *addr)
 {
 	flush_kernel_dcache_page_addr(addr);
 	pagefault_enable();
+	preempt_enable();
 }
 
 #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd13354ec41..0a90b965cccb 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 3391d061eccc..78c9fd32c554 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -348,6 +348,10 @@ struct pt_regs;	/* forward declaration... */
 
 #define ELF_HWCAP	0
 
+#define STACK_RND_MASK	(is_32bit_task() ? \
+				0x7ff >> (PAGE_SHIFT - 12) : \
+				0x3ffff >> (PAGE_SHIFT - 12))
+
 struct mm_struct;
 extern unsigned long arch_randomize_brk(struct mm_struct *);
 #define arch_randomize_brk arch_randomize_brk
diff --git a/arch/parisc/include/asm/mm-arch-hooks.h b/arch/parisc/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..654ec63b0ee9
--- /dev/null
+++ b/arch/parisc/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_PARISC_MM_ARCH_HOOKS_H
+#define _ASM_PARISC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_PARISC_MM_ARCH_HOOKS_H */
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 794d8820db5d..71889ea72740 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -196,25 +196,6 @@ static inline void pcibios_register_hba(struct pci_hba_data *x)
 /* export the pci_ DMA API in terms of the dma_ one */
 #include <asm-generic/pci-dma-compat.h>
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
 	return channel ? 15 : 14;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ff834fd67478..b9402c9b3454 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -478,14 +478,16 @@ static void pa11_dma_unmap_single(struct device *dev, dma_addr_t dma_handle, siz
 static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sglist++ ) {
-		unsigned long vaddr = (unsigned long)sg_virt(sglist);
-		sg_dma_address(sglist) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sglist) = sglist->length;
-		flush_kernel_dcache_range(vaddr, sglist->length);
+	for_each_sg(sglist, sg, nents, i) {
+		unsigned long vaddr = (unsigned long)sg_virt(sg);
+
+		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
+		sg_dma_len(sg) = sg->length;
+		flush_kernel_dcache_range(vaddr, sg->length);
 	}
 	return nents;
 }
@@ -493,6 +495,7 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int n
 static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
@@ -501,8 +504,8 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, in
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 	return;
 }
 
@@ -523,21 +526,23 @@ static void pa11_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_h
 static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
-	for (i = 0; i < nents; i++, sglist++ )
-		flush_kernel_vmap_range(sg_virt(sglist), sglist->length);
+	for_each_sg(sglist, sg, nents, i)
+		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
 struct hppa_dma_ops pcxl_dma_ops = {
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 8a488c22a99f..809905a811ed 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -181,9 +181,12 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
 	return 1;
 }
 
+/*
+ * Copy architecture-specific thread state
+ */
 int
 copy_thread(unsigned long clone_flags, unsigned long usp,
-	    unsigned long arg, struct task_struct *p)
+	    unsigned long kthread_arg, struct task_struct *p)
 {
 	struct pt_regs *cregs = &(p->thread.regs);
 	void *stack = task_stack_page(p);
@@ -195,11 +198,10 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	extern void * const child_return;
 
 	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
 		memset(cregs, 0, sizeof(struct pt_regs));
 		if (!usp) /* idle thread */
 			return 0;
-
-		/* kernel thread */
 		/* Must exit via ret_from_kernel_thread in order
 		 * to call schedule_tail()
 		 */
@@ -215,7 +217,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 #else
 		cregs->gr[26] = usp;
 #endif
-		cregs->gr[25] = arg;
+		cregs->gr[25] = kthread_arg;
 	} else {
 		/* user thread */
 		/* usp must be word aligned.  This also prevents users from
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index e1ffea2f9a0b..5aba01ac457f 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -77,6 +77,9 @@ static unsigned long mmap_upper_limit(void)
 	if (stack_base > STACK_SIZE_MAX)
 		stack_base = STACK_SIZE_MAX;
 
+	/* Add space for stack randomization. */
+	stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+
 	return PAGE_ALIGN(STACK_TOP - stack_base);
 }
 
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 47ee620d15d2..6548fd1d2e62 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -26,9 +26,9 @@
 #include <linux/console.h>
 #include <linux/bug.h>
 #include <linux/ratelimit.h>
+#include <linux/uaccess.h>
 
 #include <asm/assembly.h>
-#include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/traps.h>
@@ -800,7 +800,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 	     * unless pagefault_disable() was called before.
 	     */
 
-	    if (fault_space == 0 && !in_atomic())
+	    if (fault_space == 0 && !faulthandler_disabled())
 	    {
 		pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
 		parisc_terminate("Kernel Fault", regs, code, fault_address);
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index e5120e653240..15503adddf4f 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -15,8 +15,8 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/traps.h>
 
 /* Various important other fields */
@@ -207,7 +207,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code,
 	int fault;
 	unsigned int flags;
 
-	if (in_atomic())
+	if (pagefault_disabled())
 		goto no_context;
 
 	tsk = current;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 190cc48abc0c..5ef27113b898 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -153,6 +153,8 @@ config PPC
 	select NO_BOOTMEM
 	select HAVE_GENERIC_RCU_GUP
 	select HAVE_PERF_EVENTS_NMI if PPC64
+	select EDAC_SUPPORT
+	select EDAC_ATOMIC_SCRUB
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 0efa8f90a8f1..3a510f4a6b68 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -19,6 +19,14 @@ config PPC_WERROR
 	depends on !PPC_DISABLE_WERROR
 	default y
 
+config STRICT_MM_TYPECHECKS
+	bool "Do extra type checking on mm types"
+	default n
+	help
+	  This option turns on extra type checking for some mm related types.
+
+	  If you don't know what this means, say N.
+
 config PRINT_STACK_DEPTH
 	int "Stack depth to print" if DEBUG_KERNEL
 	default 64
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 07a480861f78..05f464eb6952 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -66,7 +66,10 @@ endif
 UTS_MACHINE := $(OLDARCH)
 
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override CC	+= -mlittle-endian -mno-strict-align
+override CC	+= -mlittle-endian
+ifneq ($(COMPILER),clang)
+override CC	+= -mno-strict-align
+endif
 override AS	+= -mlittle-endian
 override LD	+= -EL
 override CROSS32CC += -mlittle-endian
@@ -113,14 +116,14 @@ else
 endif
 endif
 
-CFLAGS-$(CONFIG_PPC64)	:= -mtraceback=no
+CFLAGS-$(CONFIG_PPC64)	:= $(call cc-option,-mtraceback=no)
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,-mcall-aixdesc)
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
 else
-CFLAGS-$(CONFIG_PPC64)	+= -mcall-aixdesc
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
 endif
-CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,-mminimal-toc)
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 $(MULTIPLEWORD)
 
@@ -160,7 +163,8 @@ asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
 KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
 KBUILD_AFLAGS	+= -Iarch/$(ARCH) $(AFLAGS-y)
-KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
+KBUILD_CFLAGS	+= $(call cc-option,-msoft-float)
+KBUILD_CFLAGS	+= -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 
 CHECKFLAGS	+= -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)__
@@ -192,7 +196,7 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
 
 # Never use string load/store instructions as they are
 # often slow when they are implemented at all
-KBUILD_CFLAGS		+= -mno-string
+KBUILD_CFLAGS		+= $(call cc-option,-mno-string)
 
 ifeq ($(CONFIG_6xx),y)
 KBUILD_CFLAGS		+= -mcpu=powerpc
@@ -269,6 +273,21 @@ bootwrapper_install:
 %.dtb: scripts
 	$(Q)$(MAKE) ARCH=ppc64 $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
+# Used to create 'merged defconfigs'
+# To use it $(call) it with the first argument as the base defconfig
+# and the second argument as a space separated list of .config files to merge,
+# without the .config suffix.
+define merge_into_defconfig
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
+		-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/$(1) \
+		$(foreach config,$(2),$(srctree)/arch/$(ARCH)/configs/$(config).config)
+	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
+endef
+
+PHONY += pseries_le_defconfig
+pseries_le_defconfig:
+	$(call merge_into_defconfig,pseries_defconfig,le)
+
 define archhelp
   @echo '* zImage          - Build default images selected by kernel config'
   @echo '  zImage.*        - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)'
@@ -314,7 +333,8 @@ TOUT	:= .tmp_gas_check
 # - Require gcc 4.0 or above on 64-bit
 # - gcc-4.2.0 has issues compiling modules on 64-bit
 checkbin:
-	@if test "$(cc-version)" = "0304" ; then \
+	@if test "${COMPILER}" != "clang" \
+	    && test "$(cc-version)" = "0304" ; then \
 		if ! /bin/echo mftb 5 | $(AS) -v -mppc -many -o $(TOUT) >/dev/null 2>&1 ; then \
 			echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build '; \
 			echo 'correctly with gcc-3.4 and your version of binutils.'; \
@@ -322,13 +342,15 @@ checkbin:
 			false; \
 		fi ; \
 	fi
-	@if test "$(cc-version)" -lt "0400" \
+	@if test "${COMPILER}" != "clang" \
+	    && test "$(cc-version)" -lt "0400" \
 	    && test "x${CONFIG_PPC64}" = "xy" ; then \
                 echo -n "Sorry, GCC v4.0 or above is required to build " ; \
                 echo "the 64-bit powerpc kernel." ; \
                 false ; \
         fi
-	@if test "$(cc-fullversion)" = "040200" \
+	@if test "${COMPILER}" != "clang" \
+	    && test "$(cc-fullversion)" = "040200" \
 	    && test "x${CONFIG_MODULES}${CONFIG_PPC64}" = "xyy" ; then \
 		echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \
 		echo 'kernel with modules enabled.' ; \
@@ -336,6 +358,14 @@ checkbin:
 		echo 'disable kernel modules' ; \
 		false ; \
 	fi
+	@if test "x${CONFIG_CPU_LITTLE_ENDIAN}" = "xy" \
+	    && $(LD) --version | head -1 | grep ' 2\.24$$' >/dev/null ; then \
+		echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \
+		echo 'in some circumstances.' ; \
+		echo -n '*** Please use a different binutils version.' ; \
+		false ; \
+	fi
+
 
 CLEAN_FILES += $(TOUT)
 
diff --git a/arch/powerpc/boot/dts/b4qds.dtsi b/arch/powerpc/boot/dts/b4qds.dtsi
index 24ed80dc2120..559d00657fb5 100644
--- a/arch/powerpc/boot/dts/b4qds.dtsi
+++ b/arch/powerpc/boot/dts/b4qds.dtsi
@@ -106,6 +106,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -116,6 +124,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
index 86161ae6c966..1ea8602e4345 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
@@ -80,20 +80,9 @@
 		compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0";
 	};
 
-/include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
-		compatible = "fsl,b4420-clockgen", "fsl,qoriq-clockgen-2.0";
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				<&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux0";
-		};
+		compatible = "fsl,b4420-clockgen", "fsl,b4-clockgen",
+			      "fsl,qoriq-clockgen-2.0";
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
index f35e9e0a5445..9ba904be39ee 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
@@ -167,6 +167,75 @@
 	};
 };
 
+&qportals {
+	qportal14: qman-portal@38000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+		interrupts = <132 0x2 0 0>;
+		cell-index = <0xe>;
+	};
+	qportal15: qman-portal@3c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+		interrupts = <134 0x2 0 0>;
+		cell-index = <0xf>;
+	};
+	qportal16: qman-portal@40000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+		interrupts = <136 0x2 0 0>;
+		cell-index = <0x10>;
+	};
+	qportal17: qman-portal@44000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+		interrupts = <138 0x2 0 0>;
+		cell-index = <0x11>;
+	};
+	qportal18: qman-portal@48000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x48000 0x4000>, <0x1012000 0x1000>;
+		interrupts = <140 0x2 0 0>;
+		cell-index = <0x12>;
+	};
+	qportal19: qman-portal@4c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4c000 0x4000>, <0x1013000 0x1000>;
+		interrupts = <142 0x2 0 0>;
+		cell-index = <0x13>;
+	};
+	qportal20: qman-portal@50000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x50000 0x4000>, <0x1014000 0x1000>;
+		interrupts = <144 0x2 0 0>;
+		cell-index = <0x14>;
+	};
+	qportal21: qman-portal@54000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x54000 0x4000>, <0x1015000 0x1000>;
+		interrupts = <146 0x2 0 0>;
+		cell-index = <0x15>;
+	};
+	qportal22: qman-portal@58000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x58000 0x4000>, <0x1016000 0x1000>;
+		interrupts = <148 0x2 0 0>;
+		cell-index = <0x16>;
+	};
+	qportal23: qman-portal@5c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x5c000 0x4000>, <0x1017000 0x1000>;
+		interrupts = <150 0x2 0 0>;
+		cell-index = <0x17>;
+	};
+	qportal24: qman-portal@60000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x60000 0x4000>, <0x1018000 0x1000>;
+		interrupts = <152 0x2 0 0>;
+		cell-index = <0x18>;
+	};
+};
+
 &soc {
 	ddr2: memory-controller@9000 {
 		compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
@@ -182,20 +251,9 @@
 		compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0";
 	};
 
-/include/ "qoriq-clockgen2.dtsi"
 	global-utilities@e1000 {
-		compatible = "fsl,b4860-clockgen", "fsl,qoriq-clockgen-2.0";
-
-		mux0: mux0@0 {
-			#clock-cells = <0>;
-			reg = <0x0 0x4>;
-			compatible = "fsl,qoriq-core-mux-2.0";
-			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
-				<&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll0-div4",
-				"pll1", "pll1-div2", "pll1-div4";
-			clock-output-names = "cmux0";
-		};
+		compatible = "fsl,b4860-clockgen", "fsl,b4-clockgen",
+			      "fsl,qoriq-clockgen-2.0";
 	};
 
 	rcpm: global-utilities@e2000 {
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 73136c0029d2..603910ac1db0 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -210,6 +220,97 @@
 	};
 };
 
+&qportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <104 0x2 0 0>;
+		cell-index = <0x0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <106 0x2 0 0>;
+		cell-index = <0x1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <108 0x2 0 0>;
+		cell-index = <0x2>;
+	};
+	qportal3: qman-portal@c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <110 0x2 0 0>;
+		cell-index = <0x3>;
+	};
+	qportal4: qman-portal@10000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <112 0x2 0 0>;
+		cell-index = <0x4>;
+	};
+	qportal5: qman-portal@14000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <114 0x2 0 0>;
+		cell-index = <0x5>;
+	};
+	qportal6: qman-portal@18000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+		interrupts = <116 0x2 0 0>;
+		cell-index = <0x6>;
+	};
+	qportal7: qman-portal@1c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+		interrupts = <118 0x2 0 0>;
+		cell-index = <0x7>;
+	};
+	qportal8: qman-portal@20000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+		interrupts = <120 0x2 0 0>;
+		cell-index = <0x8>;
+	};
+	qportal9: qman-portal@24000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+		interrupts = <122 0x2 0 0>;
+		cell-index = <0x9>;
+	};
+	qportal10: qman-portal@28000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+		interrupts = <124 0x2 0 0>;
+		cell-index = <0xa>;
+	};
+	qportal11: qman-portal@2c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+		interrupts = <126 0x2 0 0>;
+		cell-index = <0xb>;
+	};
+	qportal12: qman-portal@30000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+		interrupts = <128 0x2 0 0>;
+		cell-index = <0xc>;
+	};
+	qportal13: qman-portal@34000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+		interrupts = <130 0x2 0 0>;
+		cell-index = <0xd>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -296,9 +397,21 @@
 		fsl,liodn-bits = <12>;
 	};
 
+/include/ "qoriq-clockgen2.dtsi"
 	clockgen: global-utilities@e1000 {
 		compatible = "fsl,b4-clockgen", "fsl,qoriq-clockgen-2.0";
 		reg = <0xe1000 0x1000>;
+
+		mux0: mux0@0 {
+			#clock-cells = <0>;
+			reg = <0x0 0x4>;
+			compatible = "fsl,qoriq-core-mux-2.0";
+			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+				<&pll1 0>, <&pll1 1>, <&pll1 2>;
+			clock-names = "pll0", "pll0-div2", "pll0-div4",
+				"pll1", "pll1-div2", "pll1-div4";
+			clock-output-names = "cmux0";
+		};
 	};
 
 	rcpm: global-utilities@e2000 {
@@ -343,6 +456,11 @@
 /include/ "qoriq-duart-1.dtsi"
 /include/ "qoriq-sec5.3-0.dtsi"
 
+/include/ "qoriq-qman3.dtsi"
+	qman: qman@318000 {
+		interrupts = <16 2 1 28>;
+	};
+
 /include/ "qoriq-bman1.dtsi"
 	bman: bman@31a000 {
 		interrupts = <16 2 1 29>;
diff --git a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
index 7780f21430cb..da6d3fc6ba41 100644
--- a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
 &lbc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -102,6 +112,31 @@
 	};
 };
 
+&qportals {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x100000 0x1000>;
+		interrupts = <29 2 0 0>;
+		cell-index = <0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x101000 0x1000>;
+		interrupts = <31 2 0 0>;
+		cell-index = <1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x102000 0x1000>;
+		interrupts = <33 2 0 0>;
+		cell-index = <2>;
+	};
+};
+
 &bportals {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -248,6 +283,14 @@
 /include/ "pq3-mpic.dtsi"
 /include/ "pq3-mpic-timer-B.dtsi"
 
+	qman: qman@88000 {
+		compatible = "fsl,qman";
+		reg = <0x88000 0x1000>;
+		interrupts = <16 2 0 0>;
+		fsl,qman-portals = <&qportals>;
+		memory-region = <&qman_fqd &qman_pfdr>;
+	};
+
 	bman: bman@8a000 {
 		compatible = "fsl,bman";
 		reg = <0x8a000 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index f2feacfd9a25..04ad177b6a12 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
 &lbc {
 	compatible = "fsl,p2041-elbc", "fsl,elbc", "simple-bus";
 	interrupts = <25 2 0 0>;
@@ -223,6 +233,8 @@
 
 /include/ "qoriq-bman1-portals.dtsi"
 
+/include/ "qoriq-qman1-portals.dtsi"
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -370,6 +382,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p2041-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
@@ -415,5 +428,6 @@ crypto: crypto@300000 {
 		fsl,iommu-parent = <&pamu1>;
 	};
 
+/include/ "qoriq-qman1.dtsi"
 /include/ "qoriq-bman1.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index d6fea37395ad..2cab18af6df2 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
 &lbc {
 	compatible = "fsl,p3041-elbc", "fsl,elbc", "simple-bus";
 	interrupts = <25 2 0 0>;
@@ -250,6 +260,8 @@
 
 /include/ "qoriq-bman1-portals.dtsi"
 
+/include/ "qoriq-qman1-portals.dtsi"
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -397,6 +409,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p3041-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
@@ -442,5 +455,6 @@ crypto: crypto@300000 {
 		fsl,iommu-parent = <&pamu1>;
 	};
 
+/include/ "qoriq-qman1.dtsi"
 /include/ "qoriq-bman1.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index 89482c9b2301..dfc76bc41cb2 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10 0>;
+};
+
 &lbc {
 	compatible = "fsl,p4080-elbc", "fsl,elbc", "simple-bus";
 	interrupts = <25 2 0 0>;
@@ -250,6 +260,8 @@
 
 /include/ "qoriq-bman1-portals.dtsi"
 
+/include/ "qoriq-qman1-portals.dtsi"
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -469,6 +481,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p4080-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		voltage-ranges = <3300 3300>;
@@ -498,5 +511,6 @@ crypto: crypto@300000 {
 		fsl,iommu-parent = <&pamu1>;
 	};
 
+/include/ "qoriq-qman1.dtsi"
 /include/ "qoriq-bman1.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
index 6e04851e2fc9..b77923ad72cf 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &lbc {
 	compatible = "fsl,p5020-elbc", "fsl,elbc", "simple-bus";
 	interrupts = <25 2 0 0>;
@@ -247,6 +257,8 @@
 
 /include/ "qoriq-bman1-portals.dtsi"
 
+/include/ "qoriq-qman1-portals.dtsi"
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -384,6 +396,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p5020-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu1>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
@@ -428,6 +441,7 @@
 		fsl,iommu-parent = <&pamu1>;
 	};
 
+/include/ "qoriq-qman1.dtsi"
 /include/ "qoriq-bman1.dtsi"
 
 /include/ "qoriq-raid1.0-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
index 5e44dfa1e1a5..6d214526b81b 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &lbc {
 	compatible = "fsl,p5040-elbc", "fsl,elbc", "simple-bus";
 	interrupts = <25 2 0 0>;
@@ -202,6 +212,8 @@
 
 /include/ "qoriq-bman1-portals.dtsi"
 
+/include/ "qoriq-qman1-portals.dtsi"
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -362,6 +374,7 @@
 
 /include/ "qoriq-esdhc-0.dtsi"
 	sdhc@114000 {
+		compatible = "fsl,p5040-esdhc", "fsl,esdhc";
 		fsl,iommu-parent = <&pamu2>;
 		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
 		sdhci,auto-cmd12;
@@ -407,5 +420,6 @@
 		fsl,iommu-parent = <&pamu4>;
 	};
 
+/include/ "qoriq-qman1.dtsi"
 /include/ "qoriq-bman1.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
index 05d51acafa67..e77e4b4ed53b 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-qman1-portals.dtsi
@@ -41,61 +41,61 @@
 		compatible = "fsl,qman-portal";
 		reg = <0x0 0x4000>, <0x100000 0x1000>;
 		interrupts = <104 2 0 0>;
-		fsl,qman-channel-id = <0x0>;
+		cell-index = <0x0>;
 	};
 	qportal1: qman-portal@4000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x4000 0x4000>, <0x101000 0x1000>;
 		interrupts = <106 2 0 0>;
-		fsl,qman-channel-id = <1>;
+		cell-index = <1>;
 	};
 	qportal2: qman-portal@8000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x8000 0x4000>, <0x102000 0x1000>;
 		interrupts = <108 2 0 0>;
-		fsl,qman-channel-id = <2>;
+		cell-index = <2>;
 	};
 	qportal3: qman-portal@c000 {
 		compatible = "fsl,qman-portal";
 		reg = <0xc000 0x4000>, <0x103000 0x1000>;
 		interrupts = <110 2 0 0>;
-		fsl,qman-channel-id = <3>;
+		cell-index = <3>;
 	};
 	qportal4: qman-portal@10000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x10000 0x4000>, <0x104000 0x1000>;
 		interrupts = <112 2 0 0>;
-		fsl,qman-channel-id = <4>;
+		cell-index = <4>;
 	};
 	qportal5: qman-portal@14000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x14000 0x4000>, <0x105000 0x1000>;
 		interrupts = <114 2 0 0>;
-		fsl,qman-channel-id = <5>;
+		cell-index = <5>;
 	};
 	qportal6: qman-portal@18000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x18000 0x4000>, <0x106000 0x1000>;
 		interrupts = <116 2 0 0>;
-		fsl,qman-channel-id = <6>;
+		cell-index = <6>;
 	};
 
 	qportal7: qman-portal@1c000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x1c000 0x4000>, <0x107000 0x1000>;
 		interrupts = <118 2 0 0>;
-		fsl,qman-channel-id = <7>;
+		cell-index = <7>;
 	};
 	qportal8: qman-portal@20000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x20000 0x4000>, <0x108000 0x1000>;
 		interrupts = <120 2 0 0>;
-		fsl,qman-channel-id = <8>;
+		cell-index = <8>;
 	};
 	qportal9: qman-portal@24000 {
 		compatible = "fsl,qman-portal";
 		reg = <0x24000 0x4000>, <0x109000 0x1000>;
 		interrupts = <122 2 0 0>;
-		fsl,qman-channel-id = <9>;
+		cell-index = <9>;
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
new file mode 100644
index 000000000000..df1f068a5376
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi
@@ -0,0 +1,330 @@
+/*
+ * T1023 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	compatible = "fsl,ifc", "simple-bus";
+	interrupts = <25 2 0 0>;
+};
+
+&pci0 {
+	compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0x0 0xff>;
+	interrupts = <20 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <20 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 40 1 0 0
+			0000 0 0 2 &mpic 1 1 0 0
+			0000 0 0 3 &mpic 2 1 0 0
+			0000 0 0 4 &mpic 3 1 0 0
+			>;
+	};
+};
+
+&pci1 {
+	compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0 0xff>;
+	interrupts = <21 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <21 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 41 1 0 0
+			0000 0 0 2 &mpic 5 1 0 0
+			0000 0 0 3 &mpic 6 1 0 0
+			0000 0 0 4 &mpic 7 1 0 0
+			>;
+	};
+};
+
+&pci2 {
+	compatible = "fsl,t1023-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0x0 0xff>;
+	interrupts = <22 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <22 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 42 1 0 0
+			0000 0 0 2 &mpic 9 1 0 0
+			0000 0 0 3 &mpic 10 1 0 0
+			0000 0 0 4 &mpic 11 1 0 0
+			>;
+	};
+};
+
+&dcsr {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,dcsr", "simple-bus";
+
+	dcsr-epu@0 {
+		compatible = "fsl,t1023-dcsr-epu", "fsl,dcsr-epu";
+		interrupts = <52 2 0 0
+			      84 2 0 0
+			      85 2 0 0>;
+		reg = <0x0 0x1000>;
+	};
+	dcsr-npc {
+		compatible = "fsl,t1023-dcsr-cnpc", "fsl,dcsr-cnpc";
+		reg = <0x1000 0x1000 0x1002000 0x10000>;
+	};
+	dcsr-nxc@2000 {
+		compatible = "fsl,dcsr-nxc";
+		reg = <0x2000 0x1000>;
+	};
+	dcsr-corenet {
+		compatible = "fsl,dcsr-corenet";
+		reg = <0x8000 0x1000 0x1A000 0x1000>;
+	};
+	dcsr-ocn@11000 {
+		compatible = "fsl,t1023-dcsr-ocn", "fsl,dcsr-ocn";
+		reg = <0x11000 0x1000>;
+	};
+	dcsr-ddr@12000 {
+		compatible = "fsl,dcsr-ddr";
+		dev-handle = <&ddr1>;
+		reg = <0x12000 0x1000>;
+	};
+	dcsr-nal@18000 {
+		compatible = "fsl,t1023-dcsr-nal", "fsl,dcsr-nal";
+		reg = <0x18000 0x1000>;
+	};
+	dcsr-rcpm@22000 {
+		compatible = "fsl,t1023-dcsr-rcpm", "fsl,dcsr-rcpm";
+		reg = <0x22000 0x1000>;
+	};
+	dcsr-snpc@30000 {
+		compatible = "fsl,t1023-dcsr-snpc", "fsl,dcsr-snpc";
+		reg = <0x30000 0x1000 0x1022000 0x10000>;
+	};
+	dcsr-snpc@31000 {
+		compatible = "fsl,t1023-dcsr-snpc", "fsl,dcsr-snpc";
+		reg = <0x31000 0x1000 0x1042000 0x10000>;
+	};
+	dcsr-cpu-sb-proxy@100000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu0>;
+		reg = <0x100000 0x1000 0x101000 0x1000>;
+	};
+	dcsr-cpu-sb-proxy@108000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu1>;
+		reg = <0x108000 0x1000 0x109000 0x1000>;
+	};
+};
+
+&soc {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "soc";
+	compatible = "simple-bus";
+
+	soc-sram-error {
+		compatible = "fsl,soc-sram-error";
+		interrupts = <16 2 1 29>;
+	};
+
+	corenet-law@0 {
+		compatible = "fsl,corenet-law";
+		reg = <0x0 0x1000>;
+		fsl,num-laws = <16>;
+	};
+
+	ddr1: memory-controller@8000 {
+		compatible = "fsl,qoriq-memory-controller-v5.0",
+				"fsl,qoriq-memory-controller";
+		reg = <0x8000 0x1000>;
+		interrupts = <16 2 1 23>;
+	};
+
+	cpc: l3-cache-controller@10000 {
+		compatible = "fsl,t1023-l3-cache-controller", "cache";
+		reg = <0x10000 0x1000>;
+		interrupts = <16 2 1 27>;
+	};
+
+	corenet-cf@18000 {
+		compatible = "fsl,corenet2-cf";
+		reg = <0x18000 0x1000>;
+		interrupts = <16 2 1 31>;
+	};
+
+	iommu@20000 {
+		compatible = "fsl,pamu-v1.0", "fsl,pamu";
+		reg = <0x20000 0x1000>;
+		ranges = <0 0x20000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupts = <
+			24 2 0 0
+			16 2 1 30>;
+		pamu0: pamu@0 {
+			reg = <0 0x1000>;
+			fsl,primary-cache-geometry = <128 1>;
+			fsl,secondary-cache-geometry = <32 2>;
+		};
+	};
+
+/include/ "qoriq-mpic.dtsi"
+
+	guts: global-utilities@e0000 {
+		compatible = "fsl,t1023-device-config", "fsl,qoriq-device-config-2.0";
+		reg = <0xe0000 0xe00>;
+		fsl,has-rstcr;
+		fsl,liodn-bits = <12>;
+	};
+
+/include/ "qoriq-clockgen2.dtsi"
+	global-utilities@e1000 {
+		compatible = "fsl,t1023-clockgen", "fsl,qoriq-clockgen-2.0";
+		mux0: mux0@0 {
+			#clock-cells = <0>;
+			reg = <0x0 4>;
+			compatible = "fsl,core-mux-clock";
+			clocks = <&pll0 0>, <&pll0 1>;
+			clock-names = "pll0_0", "pll0_1";
+			clock-output-names = "cmux0";
+		};
+		mux1: mux1@20 {
+			#clock-cells = <0>;
+			reg = <0x20 4>;
+			compatible = "fsl,core-mux-clock";
+			clocks = <&pll0 0>, <&pll0 1>;
+			clock-names = "pll0_0", "pll0_1";
+			clock-output-names = "cmux1";
+		};
+	};
+
+	rcpm: global-utilities@e2000 {
+		compatible = "fsl,t1023-rcpm", "fsl,qoriq-rcpm-2.0";
+		reg = <0xe2000 0x1000>;
+	};
+
+	sfp: sfp@e8000 {
+		compatible = "fsl,t1023-sfp";
+		reg = <0xe8000 0x1000>;
+	};
+
+	serdes: serdes@ea000 {
+		compatible = "fsl,t1023-serdes";
+		reg = <0xea000 0x4000>;
+	};
+
+	scfg: global-utilities@fc000 {
+		compatible = "fsl,t1023-scfg";
+		reg = <0xfc000 0x1000>;
+	};
+
+/include/ "elo3-dma-0.dtsi"
+/include/ "elo3-dma-1.dtsi"
+
+/include/ "qoriq-espi-0.dtsi"
+	spi@110000 {
+		fsl,espi-num-chipselects = <4>;
+	};
+
+/include/ "qoriq-esdhc-0.dtsi"
+	sdhc@114000 {
+		compatible = "fsl,t1023-esdhc", "fsl,esdhc";
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
+		sdhci,auto-cmd12;
+		no-1-8-v;
+	};
+/include/ "qoriq-i2c-0.dtsi"
+/include/ "qoriq-i2c-1.dtsi"
+/include/ "qoriq-duart-0.dtsi"
+/include/ "qoriq-duart-1.dtsi"
+/include/ "qoriq-gpio-0.dtsi"
+/include/ "qoriq-gpio-1.dtsi"
+/include/ "qoriq-gpio-2.dtsi"
+/include/ "qoriq-gpio-3.dtsi"
+/include/ "qoriq-usb2-mph-0.dtsi"
+	usb0: usb@210000 {
+		compatible = "fsl-usb2-mph-v2.5", "fsl-usb2-mph";
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
+		phy_type = "utmi";
+		port0;
+	};
+/include/ "qoriq-usb2-dr-0.dtsi"
+	usb1: usb@211000 {
+		compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr";
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */
+		dr_mode = "host";
+		phy_type = "utmi";
+	};
+/include/ "qoriq-sata2-0.dtsi"
+	sata@220000 {
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x550>; /* SATA1LIODNR */
+	};
+
+/include/ "qoriq-sec5.0-0.dtsi"
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi
new file mode 100644
index 000000000000..95e3af8d768e
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1024si-post.dtsi
@@ -0,0 +1,100 @@
+/*
+ * T1024 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "t1023si-post.dtsi"
+
+/ {
+	aliases {
+		vga = &display;
+		display = &display;
+	};
+
+	qe:qe@ffe140000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "qe";
+		compatible = "fsl,qe";
+		ranges = <0x0 0xf 0xfe140000 0x40000>;
+		reg = <0xf 0xfe140000 0 0x480>;
+		fsl,qe-num-riscs = <1>;
+		fsl,qe-num-snums = <28>;
+		brg-frequency = <0>;
+		bus-frequency = <0>;
+	};
+};
+
+&soc {
+	display:display@180000 {
+		compatible = "fsl,t1024-diu", "fsl,diu";
+		reg = <0x180000 1000>;
+		interrupts = <74 2 0 0>;
+	};
+};
+
+&qe {
+	qeic: interrupt-controller@80 {
+		interrupt-controller;
+		compatible = "fsl,qe-ic";
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		reg = <0x80 0x80>;
+		interrupts = <95 2 0 0  94 2 0 0>; //high:79 low:78
+	};
+
+	ucc@2000 {
+		cell-index = <1>;
+		reg = <0x2000 0x200>;
+		interrupts = <32>;
+		interrupt-parent = <&qeic>;
+	};
+
+	ucc@2200 {
+		cell-index = <3>;
+		reg = <0x2200 0x200>;
+		interrupts = <34>;
+		interrupt-parent = <&qeic>;
+	};
+
+	muram@10000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,qe-muram", "fsl,cpm-muram";
+		ranges = <0x0 0x10000 0x6000>;
+
+		data-only@0 {
+			compatible = "fsl,qe-muram-data", "fsl,cpm-muram-data";
+			reg = <0x0 0x6000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
new file mode 100644
index 000000000000..1f1a9f8474d5
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t102xsi-pre.dtsi
@@ -0,0 +1,87 @@
+/*
+ * T1024/T1023 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e5500_power_isa.dtsi"
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	aliases {
+		ccsr = &soc;
+		dcsr = &dcsr;
+
+		dma0 = &dma0;
+		dma1 = &dma1;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		pci0 = &pci0;
+		pci1 = &pci1;
+		pci2 = &pci2;
+		usb0 = &usb0;
+		usb1 = &usb1;
+		sdhc = &sdhc;
+
+		crypto = &crypto;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: PowerPC,e5500@0 {
+			device_type = "cpu";
+			reg = <0>;
+			clocks = <&mux0>;
+			next-level-cache = <&L2_1>;
+			L2_1: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+		cpu1: PowerPC,e5500@1 {
+			device_type = "cpu";
+			reg = <1>;
+			clocks = <&mux1>;
+			next-level-cache = <&L2_2>;
+			L2_2: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
index 5cc01be5b152..9e9f7e201d43 100644
--- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -280,6 +290,73 @@
 	};
 };
 
+&qportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <104 0x2 0 0>;
+		cell-index = <0x0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <106 0x2 0 0>;
+		cell-index = <0x1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <108 0x2 0 0>;
+		cell-index = <0x2>;
+	};
+	qportal3: qman-portal@c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <110 0x2 0 0>;
+		cell-index = <0x3>;
+	};
+	qportal4: qman-portal@10000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <112 0x2 0 0>;
+		cell-index = <0x4>;
+	};
+	qportal5: qman-portal@14000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <114 0x2 0 0>;
+		cell-index = <0x5>;
+	};
+	qportal6: qman-portal@18000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+		interrupts = <116 0x2 0 0>;
+		cell-index = <0x6>;
+	};
+	qportal7: qman-portal@1c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+		interrupts = <118 0x2 0 0>;
+		cell-index = <0x7>;
+	};
+	qportal8: qman-portal@20000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+		interrupts = <120 0x2 0 0>;
+		cell-index = <0x8>;
+	};
+	qportal9: qman-portal@24000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+		interrupts = <122 0x2 0 0>;
+		cell-index = <0x9>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -463,5 +540,6 @@
 		fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */
 	};
 /include/ "qoriq-sec5.0-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
 /include/ "qoriq-bman1.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 86bdaf6cbd14..32c790ae7fde 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -326,6 +336,121 @@
 	};
 };
 
+&qportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <104 0x2 0 0>;
+		cell-index = <0x0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <106 0x2 0 0>;
+		cell-index = <0x1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <108 0x2 0 0>;
+		cell-index = <0x2>;
+	};
+	qportal3: qman-portal@c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <110 0x2 0 0>;
+		cell-index = <0x3>;
+	};
+	qportal4: qman-portal@10000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <112 0x2 0 0>;
+		cell-index = <0x4>;
+	};
+	qportal5: qman-portal@14000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <114 0x2 0 0>;
+		cell-index = <0x5>;
+	};
+	qportal6: qman-portal@18000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+		interrupts = <116 0x2 0 0>;
+		cell-index = <0x6>;
+	};
+	qportal7: qman-portal@1c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+		interrupts = <118 0x2 0 0>;
+		cell-index = <0x7>;
+	};
+	qportal8: qman-portal@20000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+		interrupts = <120 0x2 0 0>;
+		cell-index = <0x8>;
+	};
+	qportal9: qman-portal@24000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+		interrupts = <122 0x2 0 0>;
+		cell-index = <0x9>;
+	};
+	qportal10: qman-portal@28000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+		interrupts = <124 0x2 0 0>;
+		cell-index = <0xa>;
+	};
+	qportal11: qman-portal@2c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+		interrupts = <126 0x2 0 0>;
+		cell-index = <0xb>;
+	};
+	qportal12: qman-portal@30000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+		interrupts = <128 0x2 0 0>;
+		cell-index = <0xc>;
+	};
+	qportal13: qman-portal@34000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+		interrupts = <130 0x2 0 0>;
+		cell-index = <0xd>;
+	};
+	qportal14: qman-portal@38000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+		interrupts = <132 0x2 0 0>;
+		cell-index = <0xe>;
+	};
+	qportal15: qman-portal@3c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+		interrupts = <134 0x2 0 0>;
+		cell-index = <0xf>;
+	};
+	qportal16: qman-portal@40000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+		interrupts = <136 0x2 0 0>;
+		cell-index = <0x10>;
+	};
+	qportal17: qman-portal@44000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+		interrupts = <138 0x2 0 0>;
+		cell-index = <0x11>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -417,7 +542,7 @@
 			compatible = "fsl,qoriq-core-mux-2.0";
 			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
 				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll1-div4",
+			clock-names = "pll0", "pll0-div2", "pll0-div4",
 				"pll1", "pll1-div2", "pll1-div4";
 			clock-output-names = "cmux0";
 		};
@@ -428,7 +553,7 @@
 			compatible = "fsl,qoriq-core-mux-2.0";
 			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
 				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
-			clock-names = "pll0", "pll0-div2", "pll1-div4",
+			clock-names = "pll0", "pll0-div2", "pll0-div4",
 				"pll1", "pll1-div2", "pll1-div4";
 			clock-output-names = "cmux1";
 		};
@@ -502,6 +627,7 @@
 		phy_type = "utmi";
 	};
 /include/ "qoriq-sec5.2-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
 /include/ "qoriq-bman1.dtsi"
 
 	L2_1: l2-cache-controller@c20000 {
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index 4d4f25895d8c..d806360d0f64 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -37,6 +37,16 @@
 	alloc-ranges = <0 0 0x10000 0>;
 };
 
+&qman_fqd {
+	compatible = "fsl,qman-fqd";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
+&qman_pfdr {
+	compatible = "fsl,qman-pfdr";
+	alloc-ranges = <0 0 0x10000 0>;
+};
+
 &ifc {
 	#address-cells = <2>;
 	#size-cells = <1>;
@@ -556,6 +566,313 @@
 	};
 };
 
+&qportals {
+	#address-cells = <0x1>;
+	#size-cells = <0x1>;
+	compatible = "simple-bus";
+
+	qportal0: qman-portal@0 {
+		compatible = "fsl,qman-portal";
+		reg = <0x0 0x4000>, <0x1000000 0x1000>;
+		interrupts = <104 0x2 0 0>;
+		cell-index = <0x0>;
+	};
+	qportal1: qman-portal@4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4000 0x4000>, <0x1001000 0x1000>;
+		interrupts = <106 0x2 0 0>;
+		cell-index = <0x1>;
+	};
+	qportal2: qman-portal@8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8000 0x4000>, <0x1002000 0x1000>;
+		interrupts = <108 0x2 0 0>;
+		cell-index = <0x2>;
+	};
+	qportal3: qman-portal@c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc000 0x4000>, <0x1003000 0x1000>;
+		interrupts = <110 0x2 0 0>;
+		cell-index = <0x3>;
+	};
+	qportal4: qman-portal@10000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x10000 0x4000>, <0x1004000 0x1000>;
+		interrupts = <112 0x2 0 0>;
+		cell-index = <0x4>;
+	};
+	qportal5: qman-portal@14000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x14000 0x4000>, <0x1005000 0x1000>;
+		interrupts = <114 0x2 0 0>;
+		cell-index = <0x5>;
+	};
+	qportal6: qman-portal@18000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x18000 0x4000>, <0x1006000 0x1000>;
+		interrupts = <116 0x2 0 0>;
+		cell-index = <0x6>;
+	};
+	qportal7: qman-portal@1c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x1c000 0x4000>, <0x1007000 0x1000>;
+		interrupts = <118 0x2 0 0>;
+		cell-index = <0x7>;
+	};
+	qportal8: qman-portal@20000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x20000 0x4000>, <0x1008000 0x1000>;
+		interrupts = <120 0x2 0 0>;
+		cell-index = <0x8>;
+	};
+	qportal9: qman-portal@24000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x24000 0x4000>, <0x1009000 0x1000>;
+		interrupts = <122 0x2 0 0>;
+		cell-index = <0x9>;
+	};
+	qportal10: qman-portal@28000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x28000 0x4000>, <0x100a000 0x1000>;
+		interrupts = <124 0x2 0 0>;
+		cell-index = <0xa>;
+	};
+	qportal11: qman-portal@2c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x2c000 0x4000>, <0x100b000 0x1000>;
+		interrupts = <126 0x2 0 0>;
+		cell-index = <0xb>;
+	};
+	qportal12: qman-portal@30000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x30000 0x4000>, <0x100c000 0x1000>;
+		interrupts = <128 0x2 0 0>;
+		cell-index = <0xc>;
+	};
+	qportal13: qman-portal@34000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x34000 0x4000>, <0x100d000 0x1000>;
+		interrupts = <130 0x2 0 0>;
+		cell-index = <0xd>;
+	};
+	qportal14: qman-portal@38000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x38000 0x4000>, <0x100e000 0x1000>;
+		interrupts = <132 0x2 0 0>;
+		cell-index = <0xe>;
+	};
+	qportal15: qman-portal@3c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x3c000 0x4000>, <0x100f000 0x1000>;
+		interrupts = <134 0x2 0 0>;
+		cell-index = <0xf>;
+	};
+	qportal16: qman-portal@40000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x40000 0x4000>, <0x1010000 0x1000>;
+		interrupts = <136 0x2 0 0>;
+		cell-index = <0x10>;
+	};
+	qportal17: qman-portal@44000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x44000 0x4000>, <0x1011000 0x1000>;
+		interrupts = <138 0x2 0 0>;
+		cell-index = <0x11>;
+	};
+	qportal18: qman-portal@48000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x48000 0x4000>, <0x1012000 0x1000>;
+		interrupts = <140 0x2 0 0>;
+		cell-index = <0x12>;
+	};
+	qportal19: qman-portal@4c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x4c000 0x4000>, <0x1013000 0x1000>;
+		interrupts = <142 0x2 0 0>;
+		cell-index = <0x13>;
+	};
+	qportal20: qman-portal@50000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x50000 0x4000>, <0x1014000 0x1000>;
+		interrupts = <144 0x2 0 0>;
+		cell-index = <0x14>;
+	};
+	qportal21: qman-portal@54000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x54000 0x4000>, <0x1015000 0x1000>;
+		interrupts = <146 0x2 0 0>;
+		cell-index = <0x15>;
+	};
+	qportal22: qman-portal@58000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x58000 0x4000>, <0x1016000 0x1000>;
+		interrupts = <148 0x2 0 0>;
+		cell-index = <0x16>;
+	};
+	qportal23: qman-portal@5c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x5c000 0x4000>, <0x1017000 0x1000>;
+		interrupts = <150 0x2 0 0>;
+		cell-index = <0x17>;
+	};
+	qportal24: qman-portal@60000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x60000 0x4000>, <0x1018000 0x1000>;
+		interrupts = <152 0x2 0 0>;
+		cell-index = <0x18>;
+	};
+	qportal25: qman-portal@64000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x64000 0x4000>, <0x1019000 0x1000>;
+		interrupts = <154 0x2 0 0>;
+		cell-index = <0x19>;
+	};
+	qportal26: qman-portal@68000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x68000 0x4000>, <0x101a000 0x1000>;
+		interrupts = <156 0x2 0 0>;
+		cell-index = <0x1a>;
+	};
+	qportal27: qman-portal@6c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x6c000 0x4000>, <0x101b000 0x1000>;
+		interrupts = <158 0x2 0 0>;
+		cell-index = <0x1b>;
+	};
+	qportal28: qman-portal@70000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x70000 0x4000>, <0x101c000 0x1000>;
+		interrupts = <160 0x2 0 0>;
+		cell-index = <0x1c>;
+	};
+	qportal29: qman-portal@74000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x74000 0x4000>, <0x101d000 0x1000>;
+		interrupts = <162 0x2 0 0>;
+		cell-index = <0x1d>;
+	};
+	qportal30: qman-portal@78000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x78000 0x4000>, <0x101e000 0x1000>;
+		interrupts = <164 0x2 0 0>;
+		cell-index = <0x1e>;
+	};
+	qportal31: qman-portal@7c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x7c000 0x4000>, <0x101f000 0x1000>;
+		interrupts = <166 0x2 0 0>;
+		cell-index = <0x1f>;
+	};
+	qportal32: qman-portal@80000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x80000 0x4000>, <0x1020000 0x1000>;
+		interrupts = <168 0x2 0 0>;
+		cell-index = <0x20>;
+	};
+	qportal33: qman-portal@84000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x84000 0x4000>, <0x1021000 0x1000>;
+		interrupts = <170 0x2 0 0>;
+		cell-index = <0x21>;
+	};
+	qportal34: qman-portal@88000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x88000 0x4000>, <0x1022000 0x1000>;
+		interrupts = <172 0x2 0 0>;
+		cell-index = <0x22>;
+	};
+	qportal35: qman-portal@8c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x8c000 0x4000>, <0x1023000 0x1000>;
+		interrupts = <174 0x2 0 0>;
+		cell-index = <0x23>;
+	};
+	qportal36: qman-portal@90000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x90000 0x4000>, <0x1024000 0x1000>;
+		interrupts = <384 0x2 0 0>;
+		cell-index = <0x24>;
+	};
+	qportal37: qman-portal@94000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x94000 0x4000>, <0x1025000 0x1000>;
+		interrupts = <386 0x2 0 0>;
+		cell-index = <0x25>;
+	};
+	qportal38: qman-portal@98000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x98000 0x4000>, <0x1026000 0x1000>;
+		interrupts = <388 0x2 0 0>;
+		cell-index = <0x26>;
+	};
+	qportal39: qman-portal@9c000 {
+		compatible = "fsl,qman-portal";
+		reg = <0x9c000 0x4000>, <0x1027000 0x1000>;
+		interrupts = <390 0x2 0 0>;
+		cell-index = <0x27>;
+	};
+	qportal40: qman-portal@a0000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xa0000 0x4000>, <0x1028000 0x1000>;
+		interrupts = <392 0x2 0 0>;
+		cell-index = <0x28>;
+	};
+	qportal41: qman-portal@a4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xa4000 0x4000>, <0x1029000 0x1000>;
+		interrupts = <394 0x2 0 0>;
+		cell-index = <0x29>;
+	};
+	qportal42: qman-portal@a8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xa8000 0x4000>, <0x102a000 0x1000>;
+		interrupts = <396 0x2 0 0>;
+		cell-index = <0x2a>;
+	};
+	qportal43: qman-portal@ac000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xac000 0x4000>, <0x102b000 0x1000>;
+		interrupts = <398 0x2 0 0>;
+		cell-index = <0x2b>;
+	};
+	qportal44: qman-portal@b0000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xb0000 0x4000>, <0x102c000 0x1000>;
+		interrupts = <400 0x2 0 0>;
+		cell-index = <0x2c>;
+	};
+	qportal45: qman-portal@b4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xb4000 0x4000>, <0x102d000 0x1000>;
+		interrupts = <402 0x2 0 0>;
+		cell-index = <0x2d>;
+	};
+	qportal46: qman-portal@b8000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xb8000 0x4000>, <0x102e000 0x1000>;
+		interrupts = <404 0x2 0 0>;
+		cell-index = <0x2e>;
+	};
+	qportal47: qman-portal@bc000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xbc000 0x4000>, <0x102f000 0x1000>;
+		interrupts = <406 0x2 0 0>;
+		cell-index = <0x2f>;
+	};
+	qportal48: qman-portal@c0000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc0000 0x4000>, <0x1030000 0x1000>;
+		interrupts = <408 0x2 0 0>;
+		cell-index = <0x30>;
+	};
+	qportal49: qman-portal@c4000 {
+		compatible = "fsl,qman-portal";
+		reg = <0xc4000 0x4000>, <0x1031000 0x1000>;
+		interrupts = <410 0x2 0 0>;
+		cell-index = <0x31>;
+	};
+};
+
 &soc {
 	#address-cells = <1>;
 	#size-cells = <1>;
@@ -748,6 +1065,7 @@
 /include/ "qoriq-sata2-0.dtsi"
 /include/ "qoriq-sata2-1.dtsi"
 /include/ "qoriq-sec5.0-0.dtsi"
+/include/ "qoriq-qman3.dtsi"
 /include/ "qoriq-bman1.dtsi"
 
 	L2_1: l2-cache-controller@c20000 {
diff --git a/arch/powerpc/boot/dts/kmcoge4.dts b/arch/powerpc/boot/dts/kmcoge4.dts
index 97e6d11d1e6d..48dab6a50437 100644
--- a/arch/powerpc/boot/dts/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/kmcoge4.dts
@@ -34,6 +34,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -44,6 +52,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/oca4080.dts b/arch/powerpc/boot/dts/oca4080.dts
index eb76caae11d9..42796c5b0561 100644
--- a/arch/powerpc/boot/dts/oca4080.dts
+++ b/arch/powerpc/boot/dts/oca4080.dts
@@ -58,6 +58,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -68,6 +76,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p1023rdb.dts b/arch/powerpc/boot/dts/p1023rdb.dts
index 9236e3742a23..05a00a4d2861 100644
--- a/arch/powerpc/boot/dts/p1023rdb.dts
+++ b/arch/powerpc/boot/dts/p1023rdb.dts
@@ -56,6 +56,18 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
+	};
+
+	qportals: qman-portals@ff000000 {
+		ranges = <0x0 0xf 0xff000000 0x200000>;
 	};
 
 	bportals: bman-portals@ff200000 {
diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index c1e69dc7188e..d2bb0765bd5a 100644
--- a/arch/powerpc/boot/dts/p2041rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -54,6 +54,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index 2192fe94866d..eca6c697cfd7 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -54,6 +54,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index fad441654642..4f80c9d02c27 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -54,6 +54,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts
index 7382636dc560..d0309a8b9749 100644
--- a/arch/powerpc/boot/dts/p5020ds.dts
+++ b/arch/powerpc/boot/dts/p5020ds.dts
@@ -54,6 +54,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/p5040ds.dts b/arch/powerpc/boot/dts/p5040ds.dts
index 35dabf5b6098..05168236d3ab 100644
--- a/arch/powerpc/boot/dts/p5040ds.dts
+++ b/arch/powerpc/boot/dts/p5040ds.dts
@@ -54,6 +54,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -64,6 +72,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x200000>;
 	};
 
+	qportals: qman-portals@ff4200000 {
+		ranges = <0x0 0xf 0xf4200000 0x200000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t1023rdb.dts b/arch/powerpc/boot/dts/t1023rdb.dts
new file mode 100644
index 000000000000..06b090aba066
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1023rdb.dts
@@ -0,0 +1,151 @@
+/*
+ * T1023 RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+	model = "fsl,T1023RDB";
+	compatible = "fsl,T1023RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  1 0 0xf 0xff800000 0x00010000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			status = "disabled";
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "spansion,s25fl512s";
+				reg = <0>;
+				spi-max-frequency = <10000000>; /* input clk */
+			};
+		};
+
+		i2c@118000 {
+			eeprom@50 {
+				compatible = "st,m24256";
+				reg = <0x50>;
+			};
+
+			rtc@68 {
+				compatible = "dallas,ds1339";
+				reg = <0x68>;
+				interrupts = <0x5 0x1 0 0>;
+			};
+		};
+
+		i2c@118100 {
+		};
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
+
+/include/ "fsl/t1023si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1024qds.dts b/arch/powerpc/boot/dts/t1024qds.dts
new file mode 100644
index 000000000000..f31fabb383b9
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1024qds.dts
@@ -0,0 +1,251 @@
+/*
+ * T1024 QDS Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+	model = "fsl,T1024QDS";
+	compatible = "fsl,T1024QDS";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  2 0 0xf 0xff800000 0x00010000
+			  3 0 0xf 0xffdf0000 0x00008000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+
+		board-control@3,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,tetra-fpga", "fsl,fpga-qixis";
+			reg = <3 0 0x300>;
+			ranges = <0 3 0 0x300>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,n25q128a11";  /* 16MB */
+				reg = <0>;
+				spi-max-frequency = <10000000>;
+			};
+
+			flash@1 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "sst,sst25wf040";  /* 512KB */
+				reg = <1>;
+				spi-max-frequency = <10000000>;
+			};
+
+			flash@2 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "eon,en25s64";   /* 8MB */
+				reg = <2>;
+				spi-max-frequency = <10000000>;
+			};
+
+			slic@2 {
+				compatible = "maxim,ds26522";
+				reg = <2>;
+				spi-max-frequency = <2000000>;
+			};
+
+			slic@3 {
+				compatible = "maxim,ds26522";
+				reg = <3>;
+				spi-max-frequency = <2000000>;
+			};
+		};
+
+		i2c@118000 {
+			pca9547@77 {
+				compatible = "nxp,pca9547";
+				reg = <0x77>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				i2c@0 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x0>;
+
+					eeprom@50 {
+						compatible = "atmel,24c512";
+						reg = <0x50>;
+					};
+
+					eeprom@51 {
+						compatible = "atmel,24c02";
+						reg = <0x51>;
+					};
+
+					eeprom@57 {
+						compatible = "atmel,24c02";
+						reg = <0x57>;
+					};
+				};
+
+				i2c@2 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x2>;
+
+					ina220@40 {
+						compatible = "ti,ina220";
+						reg = <0x40>;
+						shunt-resistor = <1000>;
+					};
+
+					ina220@41 {
+						compatible = "ti,ina220";
+						reg = <0x41>;
+						shunt-resistor = <1000>;
+					};
+				};
+
+				i2c@3 {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0x3>;
+
+					adt7461@4c {
+						/* Thermal Monitor */
+						compatible = "adi,adt7461";
+						reg = <0x4c>;
+					};
+
+					eeprom@55 {
+						compatible = "atmel,24c02";
+						reg = <0x55>;
+					};
+
+					eeprom@56 {
+						compatible = "atmel,24c512";
+						reg = <0x56>;
+					};
+
+					eeprom@57 {
+						compatible = "atmel,24c512";
+						reg = <0x57>;
+					};
+				};
+			};
+			rtc@68 {
+				compatible = "dallas,ds3232";
+				reg = <0x68>;
+				interrupts = <0x5 0x1 0 0>;
+			};
+		};
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
+
+/include/ "fsl/t1024si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1024rdb.dts b/arch/powerpc/boot/dts/t1024rdb.dts
new file mode 100644
index 000000000000..733e723ffed6
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1024rdb.dts
@@ -0,0 +1,185 @@
+/*
+ * T1024 RDB Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t102xsi-pre.dtsi"
+
+/ {
+	model = "fsl,T1024RDB";
+	compatible = "fsl,T1024RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  2 0 0xf 0xff800000 0x00010000
+			  3 0 0xf 0xffdf0000 0x00008000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+
+		board-control@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,t1024-cpld";
+			reg = <3 0 0x300>;
+			ranges = <0 3 0 0x300>;
+			bank-width = <1>;
+			device-width = <1>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,n25q512ax3";
+				reg = <0>;
+				spi-max-frequency = <10000000>; /* input clk */
+			};
+
+			slic@1 {
+				compatible = "maxim,ds26522";
+				reg = <1>;
+				spi-max-frequency = <2000000>;
+			};
+
+			slic@2 {
+				compatible = "maxim,ds26522";
+				reg = <2>;
+				spi-max-frequency = <2000000>;
+			};
+		};
+
+		i2c@118000 {
+			adt7461@4c {
+				/* Thermal Monitor */
+				compatible = "adi,adt7461";
+				reg = <0x4c>;
+			};
+
+			eeprom@50 {
+				compatible = "atmel,24c256";
+				reg = <0x50>;
+			};
+
+			rtc@68 {
+				compatible = "dallas,ds1339";
+				reg = <0x68>;
+				interrupts = <0x1 0x1 0 0>;
+			};
+		};
+
+		i2c@118100 {
+			pca9546@77 {
+				compatible = "nxp,pca9546";
+				reg = <0x77>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+			};
+		};
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x10000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
+
+/include/ "fsl/t1024si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/t104xqds.dtsi
index f7e9bfbeefc7..1498d1e4aecf 100644
--- a/arch/powerpc/boot/dts/t104xqds.dtsi
+++ b/arch/powerpc/boot/dts/t104xqds.dtsi
@@ -47,6 +47,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	ifc: localbus@ffe124000 {
@@ -92,6 +100,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t104xrdb.dtsi b/arch/powerpc/boot/dts/t104xrdb.dtsi
index 76e07a3f2ca8..830ea484295b 100644
--- a/arch/powerpc/boot/dts/t104xrdb.dtsi
+++ b/arch/powerpc/boot/dts/t104xrdb.dtsi
@@ -42,6 +42,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	ifc: localbus@ffe124000 {
@@ -83,6 +91,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t208xqds.dtsi b/arch/powerpc/boot/dts/t208xqds.dtsi
index c42e07f4f648..869f9159b4d1 100644
--- a/arch/powerpc/boot/dts/t208xqds.dtsi
+++ b/arch/powerpc/boot/dts/t208xqds.dtsi
@@ -48,6 +48,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	ifc: localbus@ffe124000 {
@@ -93,6 +101,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t208xrdb.dtsi b/arch/powerpc/boot/dts/t208xrdb.dtsi
index e1463b165d0e..693d2a8fa01c 100644
--- a/arch/powerpc/boot/dts/t208xrdb.dtsi
+++ b/arch/powerpc/boot/dts/t208xrdb.dtsi
@@ -48,6 +48,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	ifc: localbus@ffe124000 {
@@ -94,6 +102,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t4240qds.dts b/arch/powerpc/boot/dts/t4240qds.dts
index 6df77766410b..93722da10e16 100644
--- a/arch/powerpc/boot/dts/t4240qds.dts
+++ b/arch/powerpc/boot/dts/t4240qds.dts
@@ -109,6 +109,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -119,6 +127,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/boot/dts/t4240rdb.dts b/arch/powerpc/boot/dts/t4240rdb.dts
index 46049cf37f02..993eb4b8a487 100644
--- a/arch/powerpc/boot/dts/t4240rdb.dts
+++ b/arch/powerpc/boot/dts/t4240rdb.dts
@@ -78,6 +78,14 @@
 			size = <0 0x1000000>;
 			alignment = <0 0x1000000>;
 		};
+		qman_fqd: qman-fqd {
+			size = <0 0x400000>;
+			alignment = <0 0x400000>;
+		};
+		qman_pfdr: qman-pfdr {
+			size = <0 0x2000000>;
+			alignment = <0 0x2000000>;
+		};
 	};
 
 	dcsr: dcsr@f00000000 {
@@ -88,6 +96,10 @@
 		ranges = <0x0 0xf 0xf4000000 0x2000000>;
 	};
 
+	qportals: qman-portals@ff6000000 {
+		ranges = <0x0 0xf 0xf6000000 0x2000000>;
+	};
+
 	soc: soc@ffe000000 {
 		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
 		reg = <0xf 0xfe000000 0 0x00001000>;
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 34f3ea1729e0..858b539d004b 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -108,7 +108,7 @@ CONFIG_SENSORS_LM90=y
 CONFIG_WATCHDOG=y
 CONFIG_USB=y
 CONFIG_USB_MON=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
 CONFIG_USB_STORAGE=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
diff --git a/arch/powerpc/configs/le.config b/arch/powerpc/configs/le.config
new file mode 100644
index 000000000000..ee43fdb3b8f4
--- /dev/null
+++ b/arch/powerpc/configs/le.config
@@ -0,0 +1 @@
+CONFIG_CPU_LITTLE_ENDIAN=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index aad501ae3834..a97efc2146fd 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -155,6 +155,7 @@ CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
 CONFIG_PCNET32=y
 CONFIG_TIGON3=y
+CONFIG_BNX2X=m
 CONFIG_CHELSIO_T1=m
 CONFIG_BE2NET=m
 CONFIG_S2IO=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index c2e39f66b182..0d9efcedaf34 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -154,6 +154,7 @@ CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
 CONFIG_PCNET32=y
 CONFIG_TIGON3=y
+CONFIG_BNX2X=m
 CONFIG_CHELSIO_T1=m
 CONFIG_BE2NET=m
 CONFIG_S2IO=m
@@ -297,7 +298,6 @@ CONFIG_CODE_PATCHING_SELFTEST=y
 CONFIG_FTR_FIXUP_SELFTEST=y
 CONFIG_MSI_BITMAP_SELFTEST=y
 CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
diff --git a/arch/powerpc/configs/pseries_le_defconfig b/arch/powerpc/configs/pseries_le_defconfig
deleted file mode 100644
index 09bc96e792cd..000000000000
--- a/arch/powerpc/configs/pseries_le_defconfig
+++ /dev/null
@@ -1,319 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=2048
-CONFIG_CPU_LITTLE_ENDIAN=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_FHANDLE=y
-CONFIG_AUDIT=y
-CONFIG_AUDITSYSCALL=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_NUMA_BALANCING=y
-CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_FREEZER=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
-CONFIG_CGROUP_PERF=y
-CONFIG_CGROUP_SCHED=y
-CONFIG_USER_NS=y
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
-CONFIG_JUMP_LABEL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_PPC_SPLPAR=y
-CONFIG_SCANLOG=m
-CONFIG_PPC_SMLPAR=y
-CONFIG_DTL=y
-# CONFIG_PPC_PMAC is not set
-CONFIG_RTAS_FLASH=m
-CONFIG_IBMEBUS=y
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_HZ_100=y
-CONFIG_BINFMT_MISC=m
-CONFIG_PPC_TRANSACTIONAL_MEM=y
-CONFIG_KEXEC=y
-CONFIG_IRQ_ALL_CPUS=y
-CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTREMOVE=y
-CONFIG_KSM=y
-CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_PPC_64K_PAGES=y
-CONFIG_PPC_SUBPAGE_PROT=y
-CONFIG_SCHED_SMT=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_RPA=m
-CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_NET_IPIP=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-CONFIG_PARPORT=m
-CONFIG_PARPORT_PC=m
-CONFIG_BLK_DEV_FD=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_VIRTIO_BLK=m
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_AMD74XX=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_CXGB3_ISCSI=m
-CONFIG_SCSI_CXGB4_ISCSI=m
-CONFIG_SCSI_BNX2_ISCSI=m
-CONFIG_BE2ISCSI=m
-CONFIG_SCSI_MPT2SAS=m
-CONFIG_SCSI_IBMVSCSI=y
-CONFIG_SCSI_IBMVFC=m
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
-CONFIG_SCSI_IPR=y
-CONFIG_SCSI_QLA_FC=m
-CONFIG_SCSI_QLA_ISCSI=m
-CONFIG_SCSI_LPFC=m
-CONFIG_SCSI_VIRTIO=m
-CONFIG_SCSI_DH=m
-CONFIG_SCSI_DH_RDAC=m
-CONFIG_SCSI_DH_ALUA=m
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-# CONFIG_ATA_SFF is not set
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_MD_RAID10=m
-CONFIG_MD_RAID456=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
-CONFIG_BLK_DEV_DM=y
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_THIN_PROVISIONING=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_QL=m
-CONFIG_DM_MULTIPATH_ST=m
-CONFIG_DM_UEVENT=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_MACVLAN=m
-CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
-CONFIG_NETCONSOLE=y
-CONFIG_TUN=m
-CONFIG_VETH=m
-CONFIG_VIRTIO_NET=m
-CONFIG_VHOST_NET=m
-CONFIG_VORTEX=y
-CONFIG_ACENIC=m
-CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_PCNET32=y
-CONFIG_TIGON3=y
-CONFIG_CHELSIO_T1=m
-CONFIG_BE2NET=m
-CONFIG_S2IO=m
-CONFIG_IBMVETH=y
-CONFIG_EHEA=y
-CONFIG_E100=y
-CONFIG_E1000=y
-CONFIG_E1000E=y
-CONFIG_IXGB=m
-CONFIG_IXGBE=m
-CONFIG_MLX4_EN=m
-CONFIG_MYRI10GE=m
-CONFIG_QLGE=m
-CONFIG_NETXEN_NIC=m
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_PCSPKR=m
-# CONFIG_SERIO_SERPORT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_ICOM=m
-CONFIG_SERIAL_JSM=m
-CONFIG_HVC_CONSOLE=y
-CONFIG_HVC_RTAS=y
-CONFIG_HVCS=m
-CONFIG_VIRTIO_CONSOLE=m
-CONFIG_IBM_BSR=m
-CONFIG_GEN_RTC=y
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=1024
-CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_OF=y
-CONFIG_FB_MATROX=y
-CONFIG_FB_MATROX_MILLENIUM=y
-CONFIG_FB_MATROX_MYSTIQUE=y
-CONFIG_FB_MATROX_G=y
-CONFIG_FB_RADEON=y
-CONFIG_FB_IBM_GXT4500=y
-CONFIG_LCD_PLATFORM=m
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB=y
-CONFIG_USB_MON=m
-CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_HCD_PPC_OF is not set
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=m
-CONFIG_INFINIBAND=m
-CONFIG_INFINIBAND_USER_MAD=m
-CONFIG_INFINIBAND_USER_ACCESS=m
-CONFIG_INFINIBAND_MTHCA=m
-CONFIG_INFINIBAND_EHCA=m
-CONFIG_INFINIBAND_CXGB3=m
-CONFIG_INFINIBAND_CXGB4=m
-CONFIG_MLX4_INFINIBAND=m
-CONFIG_INFINIBAND_IPOIB=m
-CONFIG_INFINIBAND_IPOIB_CM=y
-CONFIG_INFINIBAND_SRP=m
-CONFIG_INFINIBAND_ISER=m
-CONFIG_VIRTIO_PCI=m
-CONFIG_VIRTIO_BALLOON=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_EXT4_FS=y
-CONFIG_EXT4_FS_POSIX_ACL=y
-CONFIG_EXT4_FS_SECURITY=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
-CONFIG_JFS_FS=m
-CONFIG_JFS_POSIX_ACL=y
-CONFIG_JFS_SECURITY=y
-CONFIG_XFS_FS=m
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_BTRFS_FS=m
-CONFIG_BTRFS_FS_POSIX_ACL=y
-CONFIG_NILFS2_FS=m
-CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
-CONFIG_OVERLAY_FS=m
-CONFIG_ISO9660_FS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_HUGETLBFS=y
-CONFIG_CRAMFS=m
-CONFIG_SQUASHFS=m
-CONFIG_SQUASHFS_XATTR=y
-CONFIG_SQUASHFS_LZO=y
-CONFIG_SQUASHFS_XZ=y
-CONFIG_PSTORE=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_DEFAULT="utf8"
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_LOCKUP_DETECTOR=y
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_CODE_PATCHING_SELFTEST=y
-CONFIG_FTR_FIXUP_SELFTEST=y
-CONFIG_MSI_BITMAP_SELFTEST=y
-CONFIG_XMON=y
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_LZO=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_VIRTUALIZATION=y
-CONFIG_KVM_BOOK3S_64=m
-CONFIG_KVM_BOOK3S_64_HV=m
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 452fb4dc575f..92289679b4c4 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -37,10 +37,10 @@ static int ppc_md5_init(struct shash_desc *desc)
 {
 	struct md5_state *sctx = shash_desc_ctx(desc);
 
-	sctx->hash[0] = 0x67452301;
-	sctx->hash[1] = 0xefcdab89;
-	sctx->hash[2] = 0x98badcfe;
-	sctx->hash[3] =	0x10325476;
+	sctx->hash[0] = MD5_H0;
+	sctx->hash[1] = MD5_H1;
+	sctx->hash[2] = MD5_H2;
+	sctx->hash[3] =	MD5_H3;
 	sctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index a3bf5be111ff..51ccc7232042 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
@@ -89,5 +89,6 @@ do {									\
 
 #define smp_mb__before_atomic()     smp_mb()
 #define smp_mb__after_atomic()      smp_mb()
+#define smp_mb__before_spinlock()   smp_mb()
 
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68fe7f0..ad6263cffb0f 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 6367b8347dad..b118072670fb 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -242,11 +242,13 @@ enum {
 
 /* We only set the TM feature if the kernel was compiled with TM supprt */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-#define CPU_FTR_TM_COMP		CPU_FTR_TM
-#define PPC_FEATURE2_HTM_COMP	PPC_FEATURE2_HTM
+#define CPU_FTR_TM_COMP			CPU_FTR_TM
+#define PPC_FEATURE2_HTM_COMP		PPC_FEATURE2_HTM
+#define PPC_FEATURE2_HTM_NOSC_COMP	PPC_FEATURE2_HTM_NOSC
 #else
-#define CPU_FTR_TM_COMP		0
-#define PPC_FEATURE2_HTM_COMP	0
+#define CPU_FTR_TM_COMP			0
+#define PPC_FEATURE2_HTM_COMP		0
+#define PPC_FEATURE2_HTM_NOSC_COMP	0
 #endif
 
 /* We need to mark all pages as being coherent if we're SMP or we have a
@@ -366,7 +368,7 @@ enum {
 	    CPU_FTR_USE_TB | CPU_FTR_MAYBE_CAN_NAP | \
 	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE)
 #define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON | CPU_FTR_USE_TB)
-#define CPU_FTRS_8XX	(CPU_FTR_USE_TB)
+#define CPU_FTRS_8XX	(CPU_FTR_USE_TB | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_40X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_44X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_440x6	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index 5be6c4753667..ba42e46ea58e 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -31,9 +31,9 @@ extern cpumask_t threads_core_mask;
 /* cpu_thread_mask_to_cores - Return a cpumask of one per cores
  *                            hit by the argument
  *
- * @threads:	a cpumask of threads
+ * @threads:	a cpumask of online threads
  *
- * This function returns a cpumask which will have one "cpu" (or thread)
+ * This function returns a cpumask which will have one online cpu's
  * bit set for each core that has at least one thread set in the argument.
  *
  * This can typically be used for things like IPI for tlb invalidations
@@ -42,13 +42,16 @@ extern cpumask_t threads_core_mask;
 static inline cpumask_t cpu_thread_mask_to_cores(const struct cpumask *threads)
 {
 	cpumask_t	tmp, res;
-	int		i;
+	int		i, cpu;
 
 	cpumask_clear(&res);
 	for (i = 0; i < NR_CPUS; i += threads_per_core) {
 		cpumask_shift_left(&tmp, &threads_core_mask, i);
-		if (cpumask_intersects(threads, &tmp))
-			cpumask_set_cpu(i, &res);
+		if (cpumask_intersects(threads, &tmp)) {
+			cpu = cpumask_next_and(-1, &tmp, cpu_online_mask);
+			if (cpu < nr_cpu_ids)
+				cpumask_set_cpu(cpu, &res);
+		}
 	}
 	return res;
 }
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 9f1371bab5fc..e9bdda88f1fb 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -46,6 +46,9 @@ struct dev_archdata {
 #ifdef CONFIG_FAIL_IOMMU
 	int fail_iommu;
 #endif
+#ifdef CONFIG_CXL_BASE
+	struct cxl_context	*cxl_ctx;
+#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/powerpc/include/asm/edac.h b/arch/powerpc/include/asm/edac.h
index 6ead88bbfbb8..5571e23d253e 100644
--- a/arch/powerpc/include/asm/edac.h
+++ b/arch/powerpc/include/asm/edac.h
@@ -12,11 +12,11 @@
 #define ASM_EDAC_H
 /*
  * ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
  * ECC scrubbing.  It reads memory and then writes back the original
  * value, allowing the hardware to detect and correct memory errors.
  */
-static __inline__ void atomic_scrub(void *va, u32 size)
+static __inline__ void edac_atomic_scrub(void *va, u32 size)
 {
 	unsigned int *virt_addr = va;
 	unsigned int temp;
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index a52db28ecc1e..c5eb86f3d452 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -27,6 +27,8 @@
 #include <linux/time.h>
 #include <linux/atomic.h>
 
+#include <uapi/asm/eeh.h>
+
 struct pci_dev;
 struct pci_bus;
 struct pci_dn;
@@ -185,11 +187,6 @@ enum {
 #define EEH_STATE_DMA_ACTIVE	(1 << 4)	/* Active DMA		*/
 #define EEH_STATE_MMIO_ENABLED	(1 << 5)	/* MMIO enabled		*/
 #define EEH_STATE_DMA_ENABLED	(1 << 6)	/* DMA enabled		*/
-#define EEH_PE_STATE_NORMAL		0	/* Normal state		*/
-#define EEH_PE_STATE_RESET		1	/* PE reset asserted	*/
-#define EEH_PE_STATE_STOPPED_IO_DMA	2	/* Frozen PE		*/
-#define EEH_PE_STATE_STOPPED_DMA	4	/* Stopped DMA, Enabled IO */
-#define EEH_PE_STATE_UNAVAIL		5	/* Unavailable		*/
 #define EEH_RESET_DEACTIVATE	0	/* Deactivate the PE reset	*/
 #define EEH_RESET_HOT		1	/* Hot reset			*/
 #define EEH_RESET_FUNDAMENTAL	3	/* Fundamental reset		*/
@@ -294,6 +291,8 @@ int eeh_pe_set_option(struct eeh_pe *pe, int option);
 int eeh_pe_get_state(struct eeh_pe *pe);
 int eeh_pe_reset(struct eeh_pe *pe, int option);
 int eeh_pe_configure(struct eeh_pe *pe);
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+		      unsigned long addr, unsigned long mask);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 1d53a65b4ec1..4bbd3c8c2888 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -112,11 +112,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h
new file mode 100644
index 000000000000..9f8402b35115
--- /dev/null
+++ b/arch/powerpc/include/asm/icswx.h
@@ -0,0 +1,184 @@
+/*
+ * ICSWX api
+ *
+ * Copyright (C) 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * This provides the Initiate Coprocessor Store Word Indexed (ICSWX)
+ * instruction.  This instruction is used to communicate with PowerPC
+ * coprocessors.  This also provides definitions of the structures used
+ * to communicate with the coprocessor.
+ *
+ * The RFC02130: Coprocessor Architecture document is the reference for
+ * everything in this file unless otherwise noted.
+ */
+#ifndef _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+#define _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_
+
+#include <asm/ppc-opcode.h> /* for PPC_ICSWX */
+
+/* Chapter 6.5.8 Coprocessor-Completion Block (CCB) */
+
+#define CCB_VALUE		(0x3fffffffffffffff)
+#define CCB_ADDRESS		(0xfffffffffffffff8)
+#define CCB_CM			(0x0000000000000007)
+#define CCB_CM0			(0x0000000000000004)
+#define CCB_CM12		(0x0000000000000003)
+
+#define CCB_CM0_ALL_COMPLETIONS	(0x0)
+#define CCB_CM0_LAST_IN_CHAIN	(0x4)
+#define CCB_CM12_STORE		(0x0)
+#define CCB_CM12_INTERRUPT	(0x1)
+
+#define CCB_SIZE		(0x10)
+#define CCB_ALIGN		CCB_SIZE
+
+struct coprocessor_completion_block {
+	__be64 value;
+	__be64 address;
+} __packed __aligned(CCB_ALIGN);
+
+
+/* Chapter 6.5.7 Coprocessor-Status Block (CSB) */
+
+#define CSB_V			(0x80)
+#define CSB_F			(0x04)
+#define CSB_CH			(0x03)
+#define CSB_CE_INCOMPLETE	(0x80)
+#define CSB_CE_TERMINATION	(0x40)
+#define CSB_CE_TPBC		(0x20)
+
+#define CSB_CC_SUCCESS		(0)
+#define CSB_CC_INVALID_ALIGN	(1)
+#define CSB_CC_OPERAND_OVERLAP	(2)
+#define CSB_CC_DATA_LENGTH	(3)
+#define CSB_CC_TRANSLATION	(5)
+#define CSB_CC_PROTECTION	(6)
+#define CSB_CC_RD_EXTERNAL	(7)
+#define CSB_CC_INVALID_OPERAND	(8)
+#define CSB_CC_PRIVILEGE	(9)
+#define CSB_CC_INTERNAL		(10)
+#define CSB_CC_WR_EXTERNAL	(12)
+#define CSB_CC_NOSPC		(13)
+#define CSB_CC_EXCESSIVE_DDE	(14)
+#define CSB_CC_WR_TRANSLATION	(15)
+#define CSB_CC_WR_PROTECTION	(16)
+#define CSB_CC_UNKNOWN_CODE	(17)
+#define CSB_CC_ABORT		(18)
+#define CSB_CC_TRANSPORT	(20)
+#define CSB_CC_SEGMENTED_DDL	(31)
+#define CSB_CC_PROGRESS_POINT	(32)
+#define CSB_CC_DDE_OVERFLOW	(33)
+#define CSB_CC_SESSION		(34)
+#define CSB_CC_PROVISION	(36)
+#define CSB_CC_CHAIN		(37)
+#define CSB_CC_SEQUENCE		(38)
+#define CSB_CC_HW		(39)
+
+#define CSB_SIZE		(0x10)
+#define CSB_ALIGN		CSB_SIZE
+
+struct coprocessor_status_block {
+	u8 flags;
+	u8 cs;
+	u8 cc;
+	u8 ce;
+	__be32 count;
+	__be64 address;
+} __packed __aligned(CSB_ALIGN);
+
+
+/* Chapter 6.5.10 Data-Descriptor List (DDL)
+ * each list contains one or more Data-Descriptor Entries (DDE)
+ */
+
+#define DDE_P			(0x8000)
+
+#define DDE_SIZE		(0x10)
+#define DDE_ALIGN		DDE_SIZE
+
+struct data_descriptor_entry {
+	__be16 flags;
+	u8 count;
+	u8 index;
+	__be32 length;
+	__be64 address;
+} __packed __aligned(DDE_ALIGN);
+
+
+/* Chapter 6.5.2 Coprocessor-Request Block (CRB) */
+
+#define CRB_SIZE		(0x80)
+#define CRB_ALIGN		(0x100) /* Errata: requires 256 alignment */
+
+/* Coprocessor Status Block field
+ *   ADDRESS	address of CSB
+ *   C		CCB is valid
+ *   AT		0 = addrs are virtual, 1 = addrs are phys
+ *   M		enable perf monitor
+ */
+#define CRB_CSB_ADDRESS		(0xfffffffffffffff0)
+#define CRB_CSB_C		(0x0000000000000008)
+#define CRB_CSB_AT		(0x0000000000000002)
+#define CRB_CSB_M		(0x0000000000000001)
+
+struct coprocessor_request_block {
+	__be32 ccw;
+	__be32 flags;
+	__be64 csb_addr;
+
+	struct data_descriptor_entry source;
+	struct data_descriptor_entry target;
+
+	struct coprocessor_completion_block ccb;
+
+	u8 reserved[48];
+
+	struct coprocessor_status_block csb;
+} __packed __aligned(CRB_ALIGN);
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1.1.1 RS
+ * Chapter 8.2.3 Coprocessor Directive
+ * Chapter 8.2.4 Execution
+ *
+ * The CCW must be converted to BE before passing to icswx()
+ */
+
+#define CCW_PS			(0xff000000)
+#define CCW_CT			(0x00ff0000)
+#define CCW_CD			(0x0000ffff)
+#define CCW_CL			(0x0000c000)
+
+
+/* RFC02167 Initiate Coprocessor Instructions document
+ * Chapter 8.2.1 Initiate Coprocessor Store Word Indexed (ICSWX)
+ * Chapter 8.2.4.1 Condition Register 0
+ */
+
+#define ICSWX_INITIATED		(0x8)
+#define ICSWX_BUSY		(0x4)
+#define ICSWX_REJECTED		(0x2)
+
+static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb)
+{
+	__be64 ccw_reg = ccw;
+	u32 cr;
+
+	__asm__ __volatile__(
+	PPC_ICSWX(%1,0,%2) "\n"
+	"mfcr %0\n"
+	: "=r" (cr)
+	: "r" (ccw_reg), "r" (crb)
+	: "cr0", "memory");
+
+	return (int)((cr >> 28) & 0xf);
+}
+
+
+#endif /* _ARCH_POWERPC_INCLUDE_ASM_ICSWX_H_ */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 1e27d6338565..ca18cff90900 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -44,6 +44,39 @@
 extern int iommu_is_off;
 extern int iommu_force_on;
 
+struct iommu_table_ops {
+	/*
+	 * When called with direction==DMA_NONE, it is equal to clear().
+	 * uaddr is a linear map address.
+	 */
+	int (*set)(struct iommu_table *tbl,
+			long index, long npages,
+			unsigned long uaddr,
+			enum dma_data_direction direction,
+			struct dma_attrs *attrs);
+#ifdef CONFIG_IOMMU_API
+	/*
+	 * Exchanges existing TCE with new TCE plus direction bits;
+	 * returns old TCE and DMA direction mask.
+	 * @tce is a physical address.
+	 */
+	int (*exchange)(struct iommu_table *tbl,
+			long index,
+			unsigned long *hpa,
+			enum dma_data_direction *direction);
+#endif
+	void (*clear)(struct iommu_table *tbl,
+			long index, long npages);
+	/* get() returns a physical address */
+	unsigned long (*get)(struct iommu_table *tbl, long index);
+	void (*flush)(struct iommu_table *tbl);
+	void (*free)(struct iommu_table *tbl);
+};
+
+/* These are used by VIO */
+extern struct iommu_table_ops iommu_table_lpar_multi_ops;
+extern struct iommu_table_ops iommu_table_pseries_ops;
+
 /*
  * IOMAP_MAX_ORDER defines the largest contiguous block
  * of dma space we can get.  IOMAP_MAX_ORDER = 13
@@ -64,6 +97,9 @@ struct iommu_pool {
 struct iommu_table {
 	unsigned long  it_busno;     /* Bus number this table belongs to */
 	unsigned long  it_size;      /* Size of iommu table in entries */
+	unsigned long  it_indirect_levels;
+	unsigned long  it_level_size;
+	unsigned long  it_allocated_size;
 	unsigned long  it_offset;    /* Offset into global table */
 	unsigned long  it_base;      /* mapped address of tce table */
 	unsigned long  it_index;     /* which iommu table this is */
@@ -75,15 +111,16 @@ struct iommu_table {
 	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
 	unsigned long  it_page_shift;/* table iommu page size */
-#ifdef CONFIG_IOMMU_API
-	struct iommu_group *it_group;
-#endif
-	void (*set_bypass)(struct iommu_table *tbl, bool enable);
-#ifdef CONFIG_PPC_POWERNV
-	void           *data;
-#endif
+	struct list_head it_group_list;/* List of iommu_table_group_link */
+	unsigned long *it_userspace; /* userspace view of the table */
+	struct iommu_table_ops *it_ops;
 };
 
+#define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
+		((tbl)->it_userspace ? \
+			&((tbl)->it_userspace[(entry) - (tbl)->it_offset]) : \
+			NULL)
+
 /* Pure 2^n version of get_order */
 static inline __attribute_const__
 int get_iommu_order(unsigned long size, struct iommu_table *tbl)
@@ -112,14 +149,62 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
+#define IOMMU_TABLE_GROUP_MAX_TABLES	2
+
+struct iommu_table_group;
+
+struct iommu_table_group_ops {
+	unsigned long (*get_table_size)(
+			__u32 page_shift,
+			__u64 window_size,
+			__u32 levels);
+	long (*create_table)(struct iommu_table_group *table_group,
+			int num,
+			__u32 page_shift,
+			__u64 window_size,
+			__u32 levels,
+			struct iommu_table **ptbl);
+	long (*set_window)(struct iommu_table_group *table_group,
+			int num,
+			struct iommu_table *tblnew);
+	long (*unset_window)(struct iommu_table_group *table_group,
+			int num);
+	/* Switch ownership from platform code to external user (e.g. VFIO) */
+	void (*take_ownership)(struct iommu_table_group *table_group);
+	/* Switch ownership from external user (e.g. VFIO) back to core */
+	void (*release_ownership)(struct iommu_table_group *table_group);
+};
+
+struct iommu_table_group_link {
+	struct list_head next;
+	struct rcu_head rcu;
+	struct iommu_table_group *table_group;
+};
+
+struct iommu_table_group {
+	/* IOMMU properties */
+	__u32 tce32_start;
+	__u32 tce32_size;
+	__u64 pgsizes; /* Bitmap of supported page sizes */
+	__u32 max_dynamic_windows_supported;
+	__u32 max_levels;
+
+	struct iommu_group *group;
+	struct iommu_table *tables[IOMMU_TABLE_GROUP_MAX_TABLES];
+	struct iommu_table_group_ops *ops;
+};
+
 #ifdef CONFIG_IOMMU_API
-extern void iommu_register_group(struct iommu_table *tbl,
+
+extern void iommu_register_group(struct iommu_table_group *table_group,
 				 int pci_domain_number, unsigned long pe_num);
 extern int iommu_add_device(struct device *dev);
 extern void iommu_del_device(struct device *dev);
 extern int __init tce_iommu_bus_notifier_init(void);
+extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction);
 #else
-static inline void iommu_register_group(struct iommu_table *tbl,
+static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,
 					unsigned long pe_num)
 {
@@ -140,13 +225,6 @@ static inline int __init tce_iommu_bus_notifier_init(void)
 }
 #endif /* !CONFIG_IOMMU_API */
 
-static inline void set_iommu_table_base_and_group(struct device *dev,
-						  void *base)
-{
-	set_iommu_table_base(dev, base);
-	iommu_add_device(dev);
-}
-
 extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			    struct scatterlist *sglist, int nelems,
 			    unsigned long mask,
@@ -197,20 +275,13 @@ extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
 		unsigned long npages);
 extern int iommu_tce_put_param_check(struct iommu_table *tbl,
 		unsigned long ioba, unsigned long tce);
-extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
-		unsigned long hwaddr, enum dma_data_direction direction);
-extern unsigned long iommu_clear_tce(struct iommu_table *tbl,
-		unsigned long entry);
-extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
-		unsigned long entry, unsigned long pages);
-extern int iommu_put_tce_user_mode(struct iommu_table *tbl,
-		unsigned long entry, unsigned long tce);
 
 extern void iommu_flush_tce(struct iommu_table *tbl);
 extern int iommu_take_ownership(struct iommu_table *tbl);
 extern void iommu_release_ownership(struct iommu_table *tbl);
 
 extern enum dma_data_direction iommu_tce_direction(unsigned long tce);
+extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 3536d12eb798..2aa79c864e91 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -430,7 +430,7 @@ static inline void note_hpte_modification(struct kvm *kvm,
  */
 static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 {
-	return rcu_dereference_raw_notrace(kvm->memslots);
+	return rcu_dereference_raw_notrace(kvm->memslots[0]);
 }
 
 extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index a193a13cf08b..d91f65b28e32 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -698,7 +698,7 @@ struct kvm_vcpu_arch {
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_exit(void) {}
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b8475daad884..c6ef05bd0765 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -182,10 +182,11 @@ extern int kvmppc_core_create_memslot(struct kvm *kvm,
 				      unsigned long npages);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
-				struct kvm_userspace_memory_region *mem);
+				const struct kvm_userspace_memory_region *mem);
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old);
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
 extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -243,10 +244,11 @@ struct kvmppc_ops {
 	void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot);
 	int (*prepare_memory_region)(struct kvm *kvm,
 				     struct kvm_memory_slot *memslot,
-				     struct kvm_userspace_memory_region *mem);
+				     const struct kvm_userspace_memory_region *mem);
 	void (*commit_memory_region)(struct kvm *kvm,
-				     struct kvm_userspace_memory_region *mem,
-				     const struct kvm_memory_slot *old);
+				     const struct kvm_userspace_memory_region *mem,
+				     const struct kvm_memory_slot *old,
+				     const struct kvm_memory_slot *new);
 	int (*unmap_hva)(struct kvm *kvm, unsigned long hva);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ef8899432ae7..952579f5e79a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -65,31 +65,6 @@ struct machdep_calls {
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
 
-	int		(*tce_build)(struct iommu_table *tbl,
-				     long index,
-				     long npages,
-				     unsigned long uaddr,
-				     enum dma_data_direction direction,
-				     struct dma_attrs *attrs);
-	void		(*tce_free)(struct iommu_table *tbl,
-				    long index,
-				    long npages);
-	unsigned long	(*tce_get)(struct iommu_table *tbl,
-				    long index);
-	void		(*tce_flush)(struct iommu_table *tbl);
-
-	/* _rm versions are for real mode use only */
-	int		(*tce_build_rm)(struct iommu_table *tbl,
-				     long index,
-				     long npages,
-				     unsigned long uaddr,
-				     enum dma_data_direction direction,
-				     struct dma_attrs *attrs);
-	void		(*tce_free_rm)(struct iommu_table *tbl,
-				    long index,
-				    long npages);
-	void		(*tce_flush_rm)(struct iommu_table *tbl);
-
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
 				   unsigned long flags, void *caller);
 	void		(*iounmap)(volatile void __iomem *token);
@@ -131,12 +106,6 @@ struct machdep_calls {
 	/* To setup PHBs when using automatic OF platform driver for PCI */
 	int		(*pci_setup_phb)(struct pci_controller *host);
 
-#ifdef CONFIG_PCI_MSI
-	int		(*setup_msi_irqs)(struct pci_dev *dev,
-					  int nvec, int type);
-	void		(*teardown_msi_irqs)(struct pci_dev *dev);
-#endif
-
 	void		(*restart)(char *cmd);
 	void		(*halt)(void);
 	void		(*panic)(char *str);
diff --git a/arch/powerpc/include/asm/mm-arch-hooks.h b/arch/powerpc/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..f2a2da895897
--- /dev/null
+++ b/arch/powerpc/include/asm/mm-arch-hooks.h
@@ -0,0 +1,28 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_POWERPC_MM_ARCH_HOOKS_H
+#define _ASM_POWERPC_MM_ARCH_HOOKS_H
+
+static inline void arch_remap(struct mm_struct *mm,
+			      unsigned long old_start, unsigned long old_end,
+			      unsigned long new_start, unsigned long new_end)
+{
+	/*
+	 * mremap() doesn't allow moving multiple vmas so we can limit the
+	 * check to old_start == vdso_base.
+	 */
+	if (old_start == mm->context.vdso_base)
+		mm->context.vdso_base = new_start;
+}
+#define arch_remap arch_remap
+
+#endif /* _ASM_POWERPC_MM_ARCH_HOOKS_H */
diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h
index 986b9e1e1044..f05500a29a60 100644
--- a/arch/powerpc/include/asm/mmu-8xx.h
+++ b/arch/powerpc/include/asm/mmu-8xx.h
@@ -27,6 +27,19 @@
 #define MI_Ks		0x80000000	/* Should not be set */
 #define MI_Kp		0x40000000	/* Should always be set */
 
+/*
+ * All pages' PP exec bits are set to 000, which means Execute for Supervisor
+ * and no Execute for User.
+ * Then we use the APG to say whether accesses are according to Page rules,
+ * "all Supervisor" rules (Exec for all) and "all User" rules (Exec for noone)
+ * Therefore, we define 4 APG groups. msb is _PAGE_EXEC, lsb is _PAGE_USER
+ * 0 (00) => Not User, no exec => 11 (all accesses performed as user)
+ * 1 (01) => User but no exec => 11 (all accesses performed as user)
+ * 2 (10) => Not User, exec => 01 (rights according to page definition)
+ * 3 (11) => User, exec => 00 (all accesses performed as supervisor)
+ */
+#define MI_APG_INIT	0xf4ffffff
+
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MI_RPN is written, bits in
  * this register are used to create the TLB entry.
@@ -87,6 +100,19 @@
 #define MD_Ks		0x80000000	/* Should not be set */
 #define MD_Kp		0x40000000	/* Should always be set */
 
+/*
+ * All pages' PP data bits are set to either 000 or 011, which means
+ * respectively RW for Supervisor and no access for User, or RO for
+ * Supervisor and no access for user.
+ * Then we use the APG to say whether accesses are according to Page rules or
+ * "all Supervisor" rules (Access to all)
+ * Therefore, we define 2 APG groups. lsb is _PAGE_USER
+ * 0 => No user => 01 (all accesses performed according to page definition)
+ * 1 => User => 00 (all accesses performed as supervisor
+ *                                 according to page definition)
+ */
+#define MD_APG_INIT	0x4fffffff
+
 /* The effective page number register.  When read, contains the information
  * about the last instruction TLB miss.  When MD_RPN is written, bits in
  * this register are used to create the TLB entry.
@@ -145,7 +171,14 @@ typedef struct {
 } mm_context_t;
 #endif /* !__ASSEMBLY__ */
 
+#if (PAGE_SHIFT == 12)
 #define mmu_virtual_psize	MMU_PAGE_4K
+#elif (PAGE_SHIFT == 14)
+#define mmu_virtual_psize	MMU_PAGE_16K
+#else
+#error "Unsupported PAGE_SIZE"
+#endif
+
 #define mmu_linear_psize	MMU_PAGE_8M
 
 #endif /* _ASM_POWERPC_MMU_8XX_H_ */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 1da6a81ce541..a82f5347540a 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -536,6 +536,9 @@ typedef struct {
 	/* for 4K PTE fragment support */
 	void *pte_frag;
 #endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	struct list_head iommu_group_mem_list;
+#endif
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 73382eba02dc..878c27771717 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -8,7 +8,6 @@
 #include <linux/spinlock.h>
 #include <asm/mmu.h>	
 #include <asm/cputable.h>
-#include <asm-generic/mm_hooks.h>
 #include <asm/cputhreads.h>
 
 /*
@@ -16,6 +15,24 @@
  */
 extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 extern void destroy_context(struct mm_struct *mm);
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+struct mm_iommu_table_group_mem_t;
+
+extern bool mm_iommu_preregistered(void);
+extern long mm_iommu_get(unsigned long ua, unsigned long entries,
+		struct mm_iommu_table_group_mem_t **pmem);
+extern long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem);
+extern void mm_iommu_init(mm_context_t *ctx);
+extern void mm_iommu_cleanup(mm_context_t *ctx);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
+		unsigned long size);
+extern struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
+		unsigned long entries);
+extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa);
+extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
+extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
+#endif
 
 extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next);
 extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
@@ -109,5 +126,27 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+			      struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+	if (start <= mm->context.vdso_base && mm->context.vdso_base < end)
+		mm->context.vdso_base = 0;
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+				     struct vm_area_struct *vma)
+{
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index 0321a909e663..e9e4c52f3685 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -153,7 +153,8 @@
 #define OPAL_FLASH_READ				110
 #define OPAL_FLASH_WRITE			111
 #define OPAL_FLASH_ERASE			112
-#define OPAL_LAST				112
+#define OPAL_PRD_MSG				113
+#define OPAL_LAST				113
 
 /* Device tree flags */
 
@@ -165,6 +166,13 @@
 #define OPAL_PM_WINKLE_ENABLED		0x00040000
 #define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000 /* with workaround */
 
+/*
+ * OPAL_CONFIG_CPU_IDLE_STATE parameters
+ */
+#define OPAL_CONFIG_IDLE_FASTSLEEP	1
+#define OPAL_CONFIG_IDLE_UNDO		0
+#define OPAL_CONFIG_IDLE_APPLY		1
+
 #ifndef __ASSEMBLY__
 
 /* Other enums */
@@ -352,6 +360,7 @@ enum opal_msg_type {
 	OPAL_MSG_SHUTDOWN,		/* params[0] = 1 reboot, 0 shutdown */
 	OPAL_MSG_HMI_EVT,
 	OPAL_MSG_DPO,
+	OPAL_MSG_PRD,
 	OPAL_MSG_TYPE_MAX,
 };
 
@@ -674,6 +683,23 @@ typedef struct oppanel_line {
 	__be64 line_len;
 } oppanel_line_t;
 
+enum opal_prd_msg_type {
+	OPAL_PRD_MSG_TYPE_INIT = 0,	/* HBRT --> OPAL */
+	OPAL_PRD_MSG_TYPE_FINI,		/* HBRT/kernel --> OPAL */
+	OPAL_PRD_MSG_TYPE_ATTN,		/* HBRT <-- OPAL */
+	OPAL_PRD_MSG_TYPE_ATTN_ACK,	/* HBRT --> OPAL */
+	OPAL_PRD_MSG_TYPE_OCC_ERROR,	/* HBRT <-- OPAL */
+	OPAL_PRD_MSG_TYPE_OCC_RESET,	/* HBRT <-- OPAL */
+};
+
+struct opal_prd_msg_header {
+	uint8_t		type;
+	uint8_t		pad[1];
+	__be16		size;
+};
+
+struct opal_prd_msg;
+
 /*
  * SG entries
  *
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 042af1abfc4d..958e941c0cda 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -186,6 +186,7 @@ int64_t opal_handle_hmi(void);
 int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end);
 int64_t opal_unregister_dump_region(uint32_t id);
 int64_t opal_slw_set_reg(uint64_t cpu_pir, uint64_t sprn, uint64_t val);
+int64_t opal_config_cpu_idle_state(uint64_t state, uint64_t flag);
 int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number);
 int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t msg_len);
@@ -193,6 +194,7 @@ int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
 		uint64_t *msg_len);
 int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id,
 			 struct opal_i2c_request *oreq);
+int64_t opal_prd_msg(struct opal_prd_msg *msg);
 
 int64_t opal_flash_read(uint64_t id, uint64_t offset, uint64_t buf,
 		uint64_t size, uint64_t token);
@@ -239,6 +241,10 @@ extern int opal_elog_init(void);
 extern void opal_platform_dump_init(void);
 extern void opal_sys_param_init(void);
 extern void opal_msglog_init(void);
+extern int opal_async_comp_init(void);
+extern int opal_sensor_init(void);
+extern int opal_hmi_handler_init(void);
+extern int opal_event_init(void);
 
 extern int opal_machine_check(struct pt_regs *regs);
 extern bool opal_mce_check_early_recovery(struct pt_regs *regs);
@@ -250,6 +256,8 @@ extern int opal_resync_timebase(void);
 
 extern void opal_lpc_init(void);
 
+extern int opal_event_request(unsigned int opal_event_nr);
+
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
 					     unsigned long vmalloc_size);
 void opal_free_sg_list(struct opal_sg_list *sg);
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 69c059887a2c..71294a6e976e 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -278,9 +278,7 @@ extern long long virt_phys_offset;
 
 #ifndef __ASSEMBLY__
 
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
 /* These are used to make use of C type-checking. */
 
 /* PTE level */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 1811c44bf34b..712add590445 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -27,9 +27,23 @@ struct pci_controller_ops {
 	 * allow assignment/enabling of the device. */
 	bool		(*enable_device_hook)(struct pci_dev *);
 
+	void		(*disable_device)(struct pci_dev *);
+
+	void		(*release_device)(struct pci_dev *);
+
 	/* Called during PCI resource reassignment */
 	resource_size_t (*window_alignment)(struct pci_bus *, unsigned long type);
 	void		(*reset_secondary_bus)(struct pci_dev *dev);
+
+#ifdef CONFIG_PCI_MSI
+	int		(*setup_msi_irqs)(struct pci_dev *dev,
+					  int nvec, int type);
+	void		(*teardown_msi_irqs)(struct pci_dev *dev);
+#endif
+
+	int             (*dma_set_mask)(struct pci_dev *dev, u64 dma_mask);
+
+	void		(*shutdown)(struct pci_controller *);
 };
 
 /*
@@ -185,7 +199,7 @@ struct pci_dn {
 
 	struct  pci_dn *parent;
 	struct  pci_controller *phb;	/* for pci devices */
-	struct	iommu_table *iommu_table;	/* for phb's or bridges */
+	struct	iommu_table_group *table_group;	/* for phb's or bridges */
 	struct	device_node *node;	/* back-pointer to the device_node */
 
 	int	pci_ext_config_space;	/* for pci devices */
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 3be43ab63181..3453bd8dc18f 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -71,36 +71,6 @@ extern struct dma_map_ops *get_pci_dma_ops(void);
  */
 #define PCI_DISABLE_MWI
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
-#else /* 32-bit */
-
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
 #endif /* CONFIG_PPC64 */
 
 extern int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/powerpc/include/asm/pgtable-ppc32.h b/arch/powerpc/include/asm/pgtable-ppc32.h
index 64b52b1cf542..9c326565d498 100644
--- a/arch/powerpc/include/asm/pgtable-ppc32.h
+++ b/arch/powerpc/include/asm/pgtable-ppc32.h
@@ -170,24 +170,6 @@ static inline unsigned long pte_update(pte_t *p,
 #ifdef PTE_ATOMIC_UPDATES
 	unsigned long old, tmp;
 
-#ifdef CONFIG_PPC_8xx
-	unsigned long tmp2;
-
-	__asm__ __volatile__("\
-1:	lwarx	%0,0,%4\n\
-	andc	%1,%0,%5\n\
-	or	%1,%1,%6\n\
-	/* 0x200 == Extended encoding, bit 22 */ \
-	/* Bit 22 has to be 1 when _PAGE_USER is unset and _PAGE_RO is set */ \
-	rlwimi	%1,%1,32-1,0x200\n /* get _PAGE_RO */ \
-	rlwinm	%3,%1,32-2,0x200\n /* get _PAGE_USER */ \
-	andc	%1,%1,%3\n\
-	stwcx.	%1,0,%4\n\
-	bne-	1b"
-	: "=&r" (old), "=&r" (tmp), "=m" (*p), "=&r" (tmp2)
-	: "r" (p), "r" (clr), "r" (set), "m" (*p)
-	: "cc" );
-#else /* CONFIG_PPC_8xx */
 	__asm__ __volatile__("\
 1:	lwarx	%0,0,%3\n\
 	andc	%1,%0,%4\n\
@@ -198,7 +180,6 @@ static inline unsigned long pte_update(pte_t *p,
 	: "=&r" (old), "=&r" (tmp), "=m" (*p)
 	: "r" (p), "r" (clr), "r" (set), "m" (*p)
 	: "cc" );
-#endif /* CONFIG_PPC_8xx */
 #else /* PTE_ATOMIC_UPDATES */
 	unsigned long old = pte_val(*p);
 	*p = __pte((old & ~clr) | set);
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 43e6ad424c7f..3bb7488bd24b 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -118,7 +118,7 @@
  */
 #ifndef __real_pte
 
-#ifdef STRICT_MM_TYPECHECKS
+#ifdef CONFIG_STRICT_MM_TYPECHECKS
 #define __real_pte(e,p)		((real_pte_t){(e)})
 #define __rpte_to_pte(r)	((r).pte)
 #else
@@ -347,11 +347,27 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 /* Encode and de-code a swap entry */
-#define __swp_type(entry)	(((entry).val >> 1) & 0x3f)
-#define __swp_offset(entry)	((entry).val >> 8)
-#define __swp_entry(type, offset) ((swp_entry_t){((type)<< 1)|((offset)<<8)})
-#define __pte_to_swp_entry(pte)	((swp_entry_t){pte_val(pte) >> PTE_RPN_SHIFT})
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val << PTE_RPN_SHIFT })
+#define MAX_SWAPFILES_CHECK() do { \
+	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \
+	/*							\
+	 * Don't have overlapping bits with _PAGE_HPTEFLAGS	\
+	 * We filter HPTEFLAGS on set_pte.			\
+	 */							\
+	BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \
+	} while (0)
+/*
+ * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT;
+ */
+#define SWP_TYPE_BITS 5
+#define __swp_type(x)		(((x).val >> _PAGE_BIT_SWAP_TYPE) \
+				& ((1UL << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)		((x).val >> PTE_RPN_SHIFT)
+#define __swp_entry(type, offset)	((swp_entry_t) { \
+					((type) << _PAGE_BIT_SWAP_TYPE) \
+					| ((offset) << PTE_RPN_SHIFT) })
+
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
+#define __swp_entry_to_pte(x)		__pte((x).val)
 
 void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
@@ -553,13 +569,9 @@ extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-extern pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				unsigned long addr, pmd_t *pmdp);
-
-#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
-extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
-			      pmd_t *pmdp);
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pmd_t *pmdp);
 
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
@@ -576,6 +588,10 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
 
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
+#define pmdp_collapse_flush pmdp_collapse_flush
+
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
 extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 				       pgtable_t pgtable);
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index f9b498292a5c..6f77f71ee964 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -11,7 +11,7 @@
 #define _ASM_PNV_PCI_H
 
 #include <linux/pci.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode);
 int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 5c93f691b495..8452335661a5 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -136,6 +136,8 @@
 #define PPC_INST_DCBAL			0x7c2005ec
 #define PPC_INST_DCBZL			0x7c2007ec
 #define PPC_INST_ICBT			0x7c00002c
+#define PPC_INST_ICSWX			0x7c00032d
+#define PPC_INST_ICSWEPX		0x7c00076d
 #define PPC_INST_ISEL			0x7c00001e
 #define PPC_INST_ISEL_MASK		0xfc00003e
 #define PPC_INST_LDARX			0x7c0000a8
@@ -403,4 +405,15 @@
 #define MFTMR(tmr, r)		stringify_in_c(.long PPC_INST_MFTMR | \
 					       TMRN(tmr) | ___PPC_RT(r))
 
+/* Coprocessor instructions */
+#define PPC_ICSWX(s, a, b)	stringify_in_c(.long PPC_INST_ICSWX |	\
+					       ___PPC_RS(s) |		\
+					       ___PPC_RA(a) |		\
+					       ___PPC_RB(b))
+#define PPC_ICSWEPX(s, a, b)	stringify_in_c(.long PPC_INST_ICSWEPX | \
+					       ___PPC_RS(s) |		\
+					       ___PPC_RA(a) |		\
+					       ___PPC_RB(b))
+
+
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bf117d8fb45f..28ded5d9b579 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -295,6 +295,15 @@ struct thread_struct {
 #endif
 #ifdef CONFIG_PPC64
 	unsigned long	dscr;
+	/*
+	 * This member element dscr_inherit indicates that the process
+	 * has explicitly attempted and changed the DSCR register value
+	 * for itself. Hence kernel wont use the default CPU DSCR value
+	 * contained in the PACA structure anymore during process context
+	 * switch. Once this variable is set, this behaviour will also be
+	 * inherited to all the children of this process from that point
+	 * onwards.
+	 */
 	int		dscr_inherit;
 	unsigned long	ppr;	/* used to save/restore SMT priority */
 #endif
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 97bae64afdaa..a0e2ba960976 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -34,35 +34,32 @@
 #define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
 #define _PAGE_DIRTY	0x0100	/* C: page changed */
 
-/* These 4 software bits must be masked out when the entry is loaded
- * into the TLB, 1 SW bit left(0x0080).
+/* These 4 software bits must be masked out when the L2 entry is loaded
+ * into the TLB.
  */
-#define _PAGE_GUARDED	0x0010	/* software: guarded access */
-#define _PAGE_ACCESSED	0x0020	/* software: page referenced */
-#define _PAGE_WRITETHRU	0x0040	/* software: caching is write through */
+#define _PAGE_GUARDED	0x0010	/* Copied to L1 G entry in DTLB */
+#define _PAGE_USER	0x0020	/* Copied to L1 APG lsb */
+#define _PAGE_EXEC	0x0040	/* Copied to L1 APG */
+#define _PAGE_WRITETHRU	0x0080	/* software: caching is write through */
+#define _PAGE_ACCESSED	0x0800	/* software: page referenced */
 
-/* Setting any bits in the nibble with the follow two controls will
- * require a TLB exception handler change.  It is assumed unused bits
- * are always zero.
- */
-#define _PAGE_RO	0x0400	/* lsb PP bits */
-#define _PAGE_USER	0x0800	/* msb PP bits */
-/* set when _PAGE_USER is unset and _PAGE_RO is set */
-#define _PAGE_KNLRO	0x0200
+#define _PAGE_RO	0x0600	/* Supervisor RO, User no access */
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
 #define _PMD_PAGE_MASK	0x000c
 #define _PMD_PAGE_8M	0x000c
 
-#define _PTE_NONE_MASK _PAGE_KNLRO
-
 /* Until my rework is finished, 8xx still needs atomic PTE updates */
 #define PTE_ATOMIC_UPDATES	1
 
 /* We need to add _PAGE_SHARED to kernel pages */
-#define _PAGE_KERNEL_RO	(_PAGE_SHARED | _PAGE_RO | _PAGE_KNLRO)
-#define _PAGE_KERNEL_ROX	(_PAGE_EXEC | _PAGE_RO | _PAGE_KNLRO)
+#define _PAGE_KERNEL_RO		(_PAGE_SHARED | _PAGE_RO)
+#define _PAGE_KERNEL_ROX	(_PAGE_SHARED | _PAGE_RO | _PAGE_EXEC)
+#define _PAGE_KERNEL_RW		(_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
+				 _PAGE_HWWRITE)
+#define _PAGE_KERNEL_RWX	(_PAGE_SHARED | _PAGE_DIRTY | _PAGE_RW | \
+				 _PAGE_HWWRITE | _PAGE_EXEC)
 
 #endif /* __KERNEL__ */
 #endif /*  _ASM_POWERPC_PTE_8xx_H */
diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h
index 91a704952ca1..8d8473278d91 100644
--- a/arch/powerpc/include/asm/pte-book3e.h
+++ b/arch/powerpc/include/asm/pte-book3e.h
@@ -11,6 +11,7 @@
 /* Architected bits */
 #define _PAGE_PRESENT	0x000001 /* software: pte contains a translation */
 #define _PAGE_SW1	0x000002
+#define _PAGE_BIT_SWAP_TYPE	2
 #define _PAGE_BAP_SR	0x000004
 #define _PAGE_BAP_UR	0x000008
 #define _PAGE_BAP_SW	0x000010
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index c5a755ef7011..b7c8d079c121 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -85,10 +85,8 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
  * 64-bit PTEs
  */
 #if defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
-#define PTE_RPN_MAX	(1ULL << (64 - PTE_RPN_SHIFT))
 #define PTE_RPN_MASK	(~((1ULL<<PTE_RPN_SHIFT)-1))
 #else
-#define PTE_RPN_MAX	(1UL << (32 - PTE_RPN_SHIFT))
 #define PTE_RPN_MASK	(~((1UL<<PTE_RPN_SHIFT)-1))
 #endif
 
diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h
index fc852f7e7b3a..ef612c160da7 100644
--- a/arch/powerpc/include/asm/pte-hash64.h
+++ b/arch/powerpc/include/asm/pte-hash64.h
@@ -16,6 +16,7 @@
  */
 #define _PAGE_PRESENT		0x0001 /* software: pte contains a translation */
 #define _PAGE_USER		0x0002 /* matches one of the PP bits */
+#define _PAGE_BIT_SWAP_TYPE	2
 #define _PAGE_EXEC		0x0004 /* No execute on POWER4 and newer (we invert) */
 #define _PAGE_GUARDED		0x0008
 /* We can derive Memory coherence from _PAGE_NO_CACHE */
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index f1863a138b4a..71f2b3f02cf8 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -358,7 +358,7 @@ SYSCALL_SPU(setns)
 COMPAT_SYS(process_vm_readv)
 COMPAT_SYS(process_vm_writev)
 SYSCALL(finit_module)
-SYSCALL(ni_syscall) /* sys_kcmp */
+SYSCALL(kcmp) /* sys_kcmp */
 SYSCALL_SPU(sched_setattr)
 SYSCALL_SPU(sched_getattr)
 SYSCALL_SPU(renameat2)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 5f1048eaa5b6..8b3b46b7b0f2 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -87,7 +87,7 @@ static inline int prrn_is_enabled(void)
 #include <asm/smp.h>
 
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
-#define topology_thread_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
 #endif
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index c15da6073cb8..8e86b48d0369 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -144,6 +144,26 @@ TRACE_EVENT_FN(opal_exit,
 );
 #endif
 
+TRACE_EVENT(hash_fault,
+
+	    TP_PROTO(unsigned long addr, unsigned long access, unsigned long trap),
+	    TP_ARGS(addr, access, trap),
+	    TP_STRUCT__entry(
+		    __field(unsigned long, addr)
+		    __field(unsigned long, access)
+		    __field(unsigned long, trap)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->addr = addr;
+		    __entry->access = access;
+		    __entry->trap = trap;
+		    ),
+
+	    TP_printk("hash fault with addr 0x%lx and access = 0x%lx trap = 0x%lx",
+		      __entry->addr, __entry->access, __entry->trap)
+);
+
 #endif /* _TRACE_POWERPC_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index a0c071d24e0e..2a8ebae0936b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -265,7 +265,7 @@ do {								\
 ({								\
 	long __gu_err;						\
 	unsigned long __gu_val;					\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
@@ -279,7 +279,7 @@ do {								\
 ({								\
 	long __gu_err;						\
 	long long __gu_val;					\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
@@ -293,7 +293,7 @@ do {								\
 ({									\
 	long __gu_err = -EFAULT;					\
 	unsigned long  __gu_val = 0;					\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
 	might_fault();							\
 	if (access_ok(VERIFY_READ, __gu_addr, (size)))			\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
@@ -305,7 +305,7 @@ do {								\
 ({								\
 	long __gu_err;						\
 	unsigned long __gu_val;					\
-	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
+	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
 	__chk_user_ptr(ptr);					\
 	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 79c4068be278..f44a027818af 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -18,6 +18,7 @@ header-y += kvm_para.h
 header-y += mman.h
 header-y += msgbuf.h
 header-y += nvram.h
+header-y += opal-prd.h
 header-y += param.h
 header-y += perf_event.h
 header-y += poll.h
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index de2c0e4ee1aa..43686043e297 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -42,5 +42,6 @@
 #define PPC_FEATURE2_ISEL		0x08000000
 #define PPC_FEATURE2_TAR		0x04000000
 #define PPC_FEATURE2_VEC_CRYPTO		0x02000000
+#define PPC_FEATURE2_HTM_NOSC		0x01000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/uapi/asm/eeh.h b/arch/powerpc/include/uapi/asm/eeh.h
new file mode 100644
index 000000000000..291b7d1814a6
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/eeh.h
@@ -0,0 +1,56 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2015
+ *
+ * Authors: Gavin Shan <gwshan@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_POWERPC_EEH_H
+#define _ASM_POWERPC_EEH_H
+
+/* PE states */
+#define EEH_PE_STATE_NORMAL		0	/* Normal state		*/
+#define EEH_PE_STATE_RESET		1	/* PE reset asserted	*/
+#define EEH_PE_STATE_STOPPED_IO_DMA	2	/* Frozen PE		*/
+#define EEH_PE_STATE_STOPPED_DMA	4	/* Stopped DMA only	*/
+#define EEH_PE_STATE_UNAVAIL		5	/* Unavailable		*/
+
+/* EEH error types and functions */
+#define EEH_ERR_TYPE_32			0       /* 32-bits error	*/
+#define EEH_ERR_TYPE_64			1       /* 64-bits error	*/
+#define EEH_ERR_FUNC_MIN		0
+#define EEH_ERR_FUNC_LD_MEM_ADDR	0	/* Memory load	*/
+#define EEH_ERR_FUNC_LD_MEM_DATA	1
+#define EEH_ERR_FUNC_LD_IO_ADDR		2	/* IO load	*/
+#define EEH_ERR_FUNC_LD_IO_DATA		3
+#define EEH_ERR_FUNC_LD_CFG_ADDR	4	/* Config load	*/
+#define EEH_ERR_FUNC_LD_CFG_DATA	5
+#define EEH_ERR_FUNC_ST_MEM_ADDR	6	/* Memory store	*/
+#define EEH_ERR_FUNC_ST_MEM_DATA	7
+#define EEH_ERR_FUNC_ST_IO_ADDR		8	/* IO store	*/
+#define EEH_ERR_FUNC_ST_IO_DATA		9
+#define EEH_ERR_FUNC_ST_CFG_ADDR	10	/* Config store	*/
+#define EEH_ERR_FUNC_ST_CFG_DATA	11
+#define EEH_ERR_FUNC_DMA_RD_ADDR	12	/* DMA read	*/
+#define EEH_ERR_FUNC_DMA_RD_DATA	13
+#define EEH_ERR_FUNC_DMA_RD_MASTER	14
+#define EEH_ERR_FUNC_DMA_RD_TARGET	15
+#define EEH_ERR_FUNC_DMA_WR_ADDR	16	/* DMA write	*/
+#define EEH_ERR_FUNC_DMA_WR_DATA	17
+#define EEH_ERR_FUNC_DMA_WR_MASTER	18
+#define EEH_ERR_FUNC_DMA_WR_TARGET	19
+#define EEH_ERR_FUNC_MAX		19
+
+#endif /* _ASM_POWERPC_EEH_H */
diff --git a/arch/powerpc/include/uapi/asm/opal-prd.h b/arch/powerpc/include/uapi/asm/opal-prd.h
new file mode 100644
index 000000000000..319ff4a26158
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/opal-prd.h
@@ -0,0 +1,58 @@
+/*
+ * OPAL Runtime Diagnostics interface driver
+ * Supported on POWERNV platform
+ *
+ * (C) Copyright IBM 2015
+ *
+ * Author: Vaidyanathan Srinivasan <svaidy at linux.vnet.ibm.com>
+ * Author: Jeremy Kerr <jk@ozlabs.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _UAPI_ASM_POWERPC_OPAL_PRD_H_
+#define _UAPI_ASM_POWERPC_OPAL_PRD_H_
+
+#include <linux/types.h>
+
+/**
+ * The version of the kernel interface of the PRD system. This describes the
+ * interface available for the /dev/opal-prd device. The actual PRD message
+ * layout and content is private to the firmware <--> userspace interface, so
+ * is not covered by this versioning.
+ *
+ * Future interface versions are backwards-compatible; if a later kernel
+ * version is encountered, functionality provided in earlier versions
+ * will work.
+ */
+#define OPAL_PRD_KERNEL_VERSION		1
+
+#define OPAL_PRD_GET_INFO		_IOR('o', 0x01, struct opal_prd_info)
+#define OPAL_PRD_SCOM_READ		_IOR('o', 0x02, struct opal_prd_scom)
+#define OPAL_PRD_SCOM_WRITE		_IOW('o', 0x03, struct opal_prd_scom)
+
+#ifndef __ASSEMBLY__
+
+struct opal_prd_info {
+	__u64	version;
+	__u64	reserved[3];
+};
+
+struct opal_prd_scom {
+	__u64	chip;
+	__u64	addr;
+	__u64	data;
+	__s64	rc;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _UAPI_ASM_POWERPC_OPAL_PRD_H */
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
index 5d836b7c1176..5047659815a5 100644
--- a/arch/powerpc/include/uapi/asm/tm.h
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -11,7 +11,7 @@
 #define TM_CAUSE_RESCHED	0xde
 #define TM_CAUSE_TLBI		0xdc
 #define TM_CAUSE_FAC_UNAV	0xda
-#define TM_CAUSE_SYSCALL	0xd8  /* future use */
+#define TM_CAUSE_SYSCALL	0xd8
 #define TM_CAUSE_MISC		0xd6  /* future use */
 #define TM_CAUSE_SIGNAL		0xd4
 #define TM_CAUSE_ALIGNMENT	0xd2
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index c1ebbdaac28f..87c7d1473488 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -33,11 +33,12 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o dma.o \
-				   misc_$(CONFIG_WORD_SIZE).o vdso32/ \
+				   misc_$(CONFIG_WORD_SIZE).o \
 				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
+obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0034b6b3556a..98230579d99c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -247,7 +247,7 @@ int main(void)
 #endif
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
-	DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default));
+	DEFINE(PACA_DSCR_DEFAULT, offsetof(struct paca_struct, dscr_default));
 	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
 	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 60262fdf35ba..7d80bfdfb15e 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -108,7 +108,9 @@ extern void __restore_cpu_e6500(void);
 				 PPC_FEATURE_TRUE_LE | \
 				 PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8	(PPC_FEATURE2_ARCH_2_07 | \
-				 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
+				 PPC_FEATURE2_HTM_COMP | \
+				 PPC_FEATURE2_HTM_NOSC_COMP | \
+				 PPC_FEATURE2_DSCR | \
 				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
 				 PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T	(COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 484b2d4462c1..35e4dcc5dce3 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -248,6 +248,14 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 {
 	if (ppc_md.dma_set_mask)
 		return ppc_md.dma_set_mask(dev, dma_mask);
+
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+		if (phb->controller_ops.dma_set_mask)
+			return phb->controller_ops.dma_set_mask(pdev, dma_mask);
+	}
+
 	return __dma_set_mask(dev, dma_mask);
 }
 EXPORT_SYMBOL(dma_set_mask);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9ee61d15653d..af9b597b10af 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -144,8 +144,6 @@ struct eeh_stats {
 
 static struct eeh_stats eeh_stats;
 
-#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
-
 static int __init eeh_setup(char *str)
 {
 	if (!strcmp(str, "off"))
@@ -719,7 +717,7 @@ static void *eeh_restore_dev_state(void *data, void *userdata)
 
 	/* The caller should restore state for the specified device */
 	if (pdev != dev)
-		pci_save_state(pdev);
+		pci_restore_state(pdev);
 
 	return NULL;
 }
@@ -1412,13 +1410,11 @@ static int dev_has_iommu_table(struct device *dev, void *data)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pci_dev **ppdev = data;
-	struct iommu_table *tbl;
 
 	if (!dev)
 		return 0;
 
-	tbl = get_iommu_table_base(dev);
-	if (tbl && tbl->it_group) {
+	if (dev->iommu_group) {
 		*ppdev = pdev;
 		return 1;
 	}
@@ -1647,6 +1643,41 @@ int eeh_pe_configure(struct eeh_pe *pe)
 }
 EXPORT_SYMBOL_GPL(eeh_pe_configure);
 
+/**
+ * eeh_pe_inject_err - Injecting the specified PCI error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @function: error function
+ * @addr: address
+ * @mask: address mask
+ *
+ * The routine is called to inject the specified PCI error, which
+ * is determined by @type and @function, to the indicated PE for
+ * testing purpose.
+ */
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+		      unsigned long addr, unsigned long mask)
+{
+	/* Invalid PE ? */
+	if (!pe)
+		return -ENODEV;
+
+	/* Unsupported operation ? */
+	if (!eeh_ops || !eeh_ops->err_inject)
+		return -ENOENT;
+
+	/* Check on PCI error type */
+	if (type != EEH_ERR_TYPE_32 && type != EEH_ERR_TYPE_64)
+		return -EINVAL;
+
+	/* Check on PCI error function */
+	if (func < EEH_ERR_FUNC_MIN || func > EEH_ERR_FUNC_MAX)
+		return -EINVAL;
+
+	return eeh_ops->err_inject(pe, type, func, addr, mask);
+}
+EXPORT_SYMBOL_GPL(eeh_pe_inject_err);
+
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
 	if (!eeh_enabled()) {
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index eeabeabea49c..a1e86e172e3c 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -48,11 +48,11 @@
  */
 struct pci_io_addr_range {
 	struct rb_node rb_node;
-	unsigned long addr_lo;
-	unsigned long addr_hi;
+	resource_size_t addr_lo;
+	resource_size_t addr_hi;
 	struct eeh_dev *edev;
 	struct pci_dev *pcidev;
-	unsigned int flags;
+	unsigned long flags;
 };
 
 static struct pci_io_addr_cache {
@@ -125,8 +125,8 @@ static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
 
 /* Insert address range into the rb tree. */
 static struct pci_io_addr_range *
-eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
-		      unsigned long ahi, unsigned int flags)
+eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
+		      resource_size_t ahi, unsigned long flags)
 {
 	struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
 	struct rb_node *parent = NULL;
@@ -197,9 +197,9 @@ static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 
 	/* Walk resources on this device, poke them into the tree */
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
-		unsigned long start = pci_resource_start(dev,i);
-		unsigned long end = pci_resource_end(dev,i);
-		unsigned int flags = pci_resource_flags(dev,i);
+		resource_size_t start = pci_resource_start(dev,i);
+		resource_size_t end = pci_resource_end(dev,i);
+		unsigned long flags = pci_resource_flags(dev,i);
 
 		/* We are interested only bus addresses, not dma or other stuff */
 		if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 24768ff3cb73..89eb4bc34d3a 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -660,7 +660,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Get the current PCI slot state. This can take a long time,
-	 * sometimes over 3 seconds for certain systems.
+	 * sometimes over 300 seconds for certain systems.
 	 */
 	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
 	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index afbc20019c2e..579e0f9a2d57 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,6 +34,7 @@
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
 #include <asm/context_tracking.h>
+#include <asm/tm.h>
 
 /*
  * System calls.
@@ -51,6 +52,12 @@ exception_marker:
 
 	.globl system_call_common
 system_call_common:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	extrdi.	r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+	bne	tabort_syscall
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
 	andi.	r10,r12,MSR_PR
 	mr	r10,r1
 	addi	r1,r1,-INT_FRAME_SIZE
@@ -311,6 +318,34 @@ syscall_exit_work:
 	bl	do_syscall_trace_leave
 	b	ret_from_except
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+tabort_syscall:
+	/* Firstly we need to enable TM in the kernel */
+	mfmsr	r10
+	li	r13, 1
+	rldimi	r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r10, 0
+
+	/* tabort, this dooms the transaction, nothing else */
+	li	r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R13)
+
+	/*
+	 * Return directly to userspace. We have corrupted user register state,
+	 * but userspace will never see that register state. Execution will
+	 * resume after the tbegin of the aborted transaction with the
+	 * checkpointed register state.
+	 */
+	li	r13, MSR_RI
+	andc	r10, r10, r13
+	mtmsrd	r10, 1
+	mtspr	SPRN_SRR0, r11
+	mtspr	SPRN_SRR1, r12
+
+	rfid
+	b	.	/* prevent speculative execution */
+#endif
+
 /* Save non-volatile GPRs, if not already saved. */
 _GLOBAL(save_nvgprs)
 	ld	r11,_TRAP(r1)
@@ -556,7 +591,7 @@ BEGIN_FTR_SECTION
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
 	bne	1f
-	ld	r0,PACA_DSCR(r13)
+	ld	r0,PACA_DSCR_DEFAULT(r13)
 1:
 BEGIN_FTR_SECTION_NESTED(70)
 	mfspr	r8, SPRN_FSCR
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9519e6bdc6d7..0a0399c2af11 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -59,14 +59,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 
 #if defined(CONFIG_RELOCATABLE)
 	/*
-	 * We can't branch directly; in the direct case we use LR
-	 * and system_call_entry restores LR.  (We thus need to move
-	 * LR to r10 in the RFID case too.)
+	 * We can't branch directly so we do it via the CTR which
+	 * is volatile across system calls.
 	 */
 #define SYSCALL_PSERIES_2_DIRECT				\
 	mflr	r10 ;						\
 	ld	r12,PACAKBASE(r13) ; 				\
-	LOAD_HANDLER(r12, system_call_entry_direct) ;		\
+	LOAD_HANDLER(r12, system_call_entry) ;			\
 	mtctr	r12 ;						\
 	mfspr	r12,SPRN_SRR1 ;					\
 	/* Re-use of r13... No spare regs to do this */	\
@@ -80,7 +79,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	mfspr	r12,SPRN_SRR1 ;					\
 	li	r10,MSR_RI ;					\
 	mtmsrd 	r10,1 ;			/* Set RI (EE=0) */	\
-	b	system_call_entry_direct ;
+	b	system_call_common ;
 #endif
 
 /*
@@ -969,13 +968,6 @@ hv_facility_unavailable_relon_trampoline:
 __end_interrupts:
 
 	.align	7
-system_call_entry_direct:
-#if defined(CONFIG_RELOCATABLE)
-	/* The first level prologue may have used LR to get here, saving
-	 * orig in r10.  To save hacking/ifdeffing common code, restore here.
-	 */
-	mtlr	r10
-#endif
 system_call_entry:
 	b	system_call_common
 
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 9b53fe139bf6..78c1eba4c04a 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -48,6 +48,19 @@
 	mtspr	spr, reg
 #endif
 
+/* Macro to test if an address is a kernel address */
+#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
+#define IS_KERNEL(tmp, addr)		\
+	andis.	tmp, addr, 0x8000	/* Address >= 0x80000000 */
+#define BRANCH_UNLESS_KERNEL(label)	beq	label
+#else
+#define IS_KERNEL(tmp, addr)		\
+	rlwinm	tmp, addr, 16, 16, 31;	\
+	cmpli	cr0, tmp, PAGE_OFFSET >> 16
+#define BRANCH_UNLESS_KERNEL(label)	blt	label
+#endif
+
+
 /*
  * Value for the bits that have fixed value in RPN entries.
  * Also used for tagging DAR for DTLBerror.
@@ -116,13 +129,13 @@ turn_on_mmu:
  */
 #define EXCEPTION_PROLOG	\
 	EXCEPTION_PROLOG_0;	\
+	mfcr	r10;		\
 	EXCEPTION_PROLOG_1;	\
 	EXCEPTION_PROLOG_2
 
 #define EXCEPTION_PROLOG_0	\
 	mtspr	SPRN_SPRG_SCRATCH0,r10;	\
-	mtspr	SPRN_SPRG_SCRATCH1,r11;	\
-	mfcr	r10
+	mtspr	SPRN_SPRG_SCRATCH1,r11
 
 #define EXCEPTION_PROLOG_1	\
 	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
@@ -162,7 +175,6 @@ turn_on_mmu:
  * Exception exit code.
  */
 #define EXCEPTION_EPILOG_0	\
-	mtcr	r10;		\
 	mfspr	r10,SPRN_SPRG_SCRATCH0;	\
 	mfspr	r11,SPRN_SPRG_SCRATCH1
 
@@ -297,19 +309,22 @@ SystemCall:
  * We have to use the MD_xxx registers for the tablewalk because the
  * equivalent MI_xxx registers only perform the attribute functions.
  */
+
+#ifdef CONFIG_8xx_CPU15
+#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)	\
+	addi	tmp, addr, PAGE_SIZE;	\
+	tlbie	tmp;			\
+	addi	tmp, addr, -PAGE_SIZE;	\
+	tlbie	tmp
+#else
+#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr)
+#endif
+
 InstructionTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	mtspr	SPRN_DAR, r3
+	mtspr	SPRN_SPRG_SCRATCH2, r3
 #endif
 	EXCEPTION_PROLOG_0
-	mtspr	SPRN_SPRG_SCRATCH2, r10
-	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
-#ifdef CONFIG_8xx_CPU15
-	addi	r11, r10, PAGE_SIZE
-	tlbie	r11
-	addi	r11, r10, -PAGE_SIZE
-	tlbie	r11
-#endif
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
@@ -317,24 +332,34 @@ InstructionTLBMiss:
 #ifdef CONFIG_MODULES
 	/* Only modules will cause ITLB Misses as we always
 	 * pin the first 8MB of kernel memory */
-	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
-#endif
+	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	INVALIDATE_ADJACENT_PAGES_CPU15(r10, r11)
+	mfcr	r10
+	IS_KERNEL(r11, r11)
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
-#ifdef CONFIG_MODULES
-	beq	3f
+	BRANCH_UNLESS_KERNEL(3f)
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
+	mtcr	r10
+	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
+#else
+	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
+	INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10)
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
 #endif
 	/* Insert level 1 index */
 	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
 
-	/* Load the MI_TWC with the attributes for this "segment." */
-	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
-	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
 	/* Extract level 2 index */
 	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
-	lwzx	r10, r10, r11	/* Get the pte */
+	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
+	lwz	r10, 0(r10)	/* Get the pte */
+
+	/* Insert the APG into the TWC from the Linux PTE. */
+	rlwimi	r11, r10, 0, 25, 26
+	/* Load the MI_TWC with the attributes for this "segment." */
+	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 
 #ifdef CONFIG_SWAP
 	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
@@ -343,40 +368,41 @@ InstructionTLBMiss:
 #endif
 	li	r11, RPN_PATTERN
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21 and 28 must be clear.
+	 * Software indicator bits 20-23 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
+	rlwimi	r10, r11, 0, 0x0ff8	/* Set 24-27, clear 20-23,28 */
 	MTSPR_CPU6(SPRN_MI_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	mfspr	r3, SPRN_DAR
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r3, SPRN_SPRG_SCRATCH2
 #endif
-	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
 	rfi
 
 	. = 0x1200
 DataStoreTLBMiss:
 #ifdef CONFIG_8xx_CPU6
-	mtspr	SPRN_DAR, r3
+	mtspr	SPRN_SPRG_SCRATCH2, r3
 #endif
 	EXCEPTION_PROLOG_0
-	mtspr	SPRN_SPRG_SCRATCH2, r10
-	mfspr	r10, SPRN_MD_EPN
+	mfcr	r10
 
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
-	andis.	r11, r10, 0x8000
+	mfspr	r11, SPRN_MD_EPN
+	IS_KERNEL(r11, r11)
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
-	beq	3f
+	BRANCH_UNLESS_KERNEL(3f)
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
+	mtcr	r10
+	mfspr	r10, SPRN_MD_EPN
+
 	/* Insert level 1 index */
 	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
@@ -388,13 +414,13 @@ DataStoreTLBMiss:
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
 	lwz	r10, 0(r10)	/* Get the pte */
 
-	/* Insert the Guarded flag into the TWC from the Linux PTE.
-	 * It is bit 27 of both the Linux PTE and the TWC (at least
+	/* Insert the Guarded flag and APG into the TWC from the Linux PTE.
+	 * It is bit 26-27 of both the Linux PTE and the TWC (at least
 	 * I got that right :-).  It will be better when we can put
 	 * this into the Linux pgd/pmd and load it in the operation
 	 * above.
 	 */
-	rlwimi	r11, r10, 0, 27, 27
+	rlwimi	r11, r10, 0, 26, 27
 	/* Insert the WriteThru flag into the TWC from the Linux PTE.
 	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
 	 */
@@ -423,14 +449,14 @@ DataStoreTLBMiss:
 	 */
 	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
+	rlwimi	r10, r11, 0, 20, 20	/* clear 20 */
 	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
 	/* Restore registers */
 #ifdef CONFIG_8xx_CPU6
-	mfspr	r3, SPRN_DAR
+	mfspr	r3, SPRN_SPRG_SCRATCH2
 #endif
 	mtspr	SPRN_DAR, r11	/* Tag DAR */
-	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
 	rfi
 
@@ -456,6 +482,7 @@ InstructionTLBError:
 	. = 0x1400
 DataTLBError:
 	EXCEPTION_PROLOG_0
+	mfcr	r10
 
 	mfspr	r11, SPRN_DAR
 	cmpwi	cr0, r11, RPN_PATTERN
@@ -503,9 +530,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
-	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
+	IS_KERNEL(r11, r10)
 	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
-	beq	3f
+	BRANCH_UNLESS_KERNEL(3f)
 	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 	/* Insert level 1 index */
 3:	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
@@ -743,15 +770,20 @@ initial_mmu:
 	ori	r8, r8, MI_EVALID	/* Mark it valid */
 	mtspr	SPRN_MI_EPN, r8
 	mtspr	SPRN_MD_EPN, r8
-	li	r8, MI_PS8MEG		/* Set 8M byte page */
+	li	r8, MI_PS8MEG | (2 << 5)	/* Set 8M byte page, APG 2 */
 	ori	r8, r8, MI_SVALID	/* Make it valid */
 	mtspr	SPRN_MI_TWC, r8
+	li	r8, MI_PS8MEG		/* Set 8M byte page, APG 0 */
+	ori	r8, r8, MI_SVALID	/* Make it valid */
 	mtspr	SPRN_MD_TWC, r8
 	li	r8, MI_BOOTINIT		/* Create RPN for address 0 */
 	mtspr	SPRN_MI_RPN, r8		/* Store TLB entry */
 	mtspr	SPRN_MD_RPN, r8
-	lis	r8, MI_Kp@h		/* Set the protection mode */
+	lis	r8, MI_APG_INIT@h	/* Set protection modes */
+	ori	r8, r8, MI_APG_INIT@l
 	mtspr	SPRN_MI_AP, r8
+	lis	r8, MD_APG_INIT@h
+	ori	r8, r8, MD_APG_INIT@l
 	mtspr	SPRN_MD_AP, r8
 
 	/* Map another 8 MByte at the IMMR to get the processor
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 15448668988d..b9b6ef510be1 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -58,15 +58,6 @@ BEGIN_FTR_SECTION
 	mtlr	r0
 	lis	r3,HID0_NAP@h
 END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
-BEGIN_FTR_SECTION
-	msync
-	li	r7,L2CSR0_L2FL@l
-	mtspr	SPRN_L2CSR0,r7
-2:
-	mfspr	r7,SPRN_L2CSR0
-	andi.	r4,r7,L2CSR0_L2FL@l
-	bne	2b
-END_FTR_SECTION_IFSET(CPU_FTR_L2CSR|CPU_FTR_CAN_NAP)
 1:
 	/* Go to NAP or DOZE now */
 	mfspr	r4,SPRN_HID0
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index b054f33ab1fb..a8e3490b54e3 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -322,11 +322,11 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
 
 	/* Put the TCEs in the HW table */
-	build_fail = ppc_md.tce_build(tbl, entry, npages,
+	build_fail = tbl->it_ops->set(tbl, entry, npages,
 				      (unsigned long)page &
 				      IOMMU_PAGE_MASK(tbl), direction, attrs);
 
-	/* ppc_md.tce_build() only returns non-zero for transient errors.
+	/* tbl->it_ops->set() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
 	 * DMA_ERROR_CODE. For all other errors the functionality is
 	 * not altered.
@@ -337,8 +337,8 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
-	if (ppc_md.tce_flush)
-		ppc_md.tce_flush(tbl);
+	if (tbl->it_ops->flush)
+		tbl->it_ops->flush(tbl);
 
 	/* Make sure updates are seen by hardware */
 	mb();
@@ -408,7 +408,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	if (!iommu_free_check(tbl, dma_addr, npages))
 		return;
 
-	ppc_md.tce_free(tbl, entry, npages);
+	tbl->it_ops->clear(tbl, entry, npages);
 
 	spin_lock_irqsave(&(pool->lock), flags);
 	bitmap_clear(tbl->it_map, free_entry, npages);
@@ -424,8 +424,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	 * not do an mb() here on purpose, it is not needed on any of
 	 * the current platforms.
 	 */
-	if (ppc_md.tce_flush)
-		ppc_md.tce_flush(tbl);
+	if (tbl->it_ops->flush)
+		tbl->it_ops->flush(tbl);
 }
 
 int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
@@ -495,7 +495,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
-		build_fail = ppc_md.tce_build(tbl, entry, npages,
+		build_fail = tbl->it_ops->set(tbl, entry, npages,
 					      vaddr & IOMMU_PAGE_MASK(tbl),
 					      direction, attrs);
 		if(unlikely(build_fail))
@@ -534,8 +534,8 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
-	if (ppc_md.tce_flush)
-		ppc_md.tce_flush(tbl);
+	if (tbl->it_ops->flush)
+		tbl->it_ops->flush(tbl);
 
 	DBG("mapped %d elements:\n", outcount);
 
@@ -600,8 +600,8 @@ void ppc_iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	 * do not do an mb() here, the affected platforms do not need it
 	 * when freeing.
 	 */
-	if (ppc_md.tce_flush)
-		ppc_md.tce_flush(tbl);
+	if (tbl->it_ops->flush)
+		tbl->it_ops->flush(tbl);
 }
 
 static void iommu_table_clear(struct iommu_table *tbl)
@@ -613,17 +613,17 @@ static void iommu_table_clear(struct iommu_table *tbl)
 	 */
 	if (!is_kdump_kernel() || is_fadump_active()) {
 		/* Clear the table in case firmware left allocations in it */
-		ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
+		tbl->it_ops->clear(tbl, tbl->it_offset, tbl->it_size);
 		return;
 	}
 
 #ifdef CONFIG_CRASH_DUMP
-	if (ppc_md.tce_get) {
+	if (tbl->it_ops->get) {
 		unsigned long index, tceval, tcecount = 0;
 
 		/* Reserve the existing mappings left by the first kernel. */
 		for (index = 0; index < tbl->it_size; index++) {
-			tceval = ppc_md.tce_get(tbl, index + tbl->it_offset);
+			tceval = tbl->it_ops->get(tbl, index + tbl->it_offset);
 			/*
 			 * Freed TCE entry contains 0x7fffffffffffffff on JS20
 			 */
@@ -657,6 +657,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	unsigned int i;
 	struct iommu_pool *p;
 
+	BUG_ON(!tbl->it_ops);
+
 	/* number of bytes needed for the bitmap */
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
@@ -713,9 +715,11 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	unsigned long bitmap_sz;
 	unsigned int order;
 
-	if (!tbl || !tbl->it_map) {
-		printk(KERN_ERR "%s: expected TCE map for %s\n", __func__,
-				node_name);
+	if (!tbl)
+		return;
+
+	if (!tbl->it_map) {
+		kfree(tbl);
 		return;
 	}
 
@@ -726,13 +730,6 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	if (tbl->it_offset == 0)
 		clear_bit(0, tbl->it_map);
 
-#ifdef CONFIG_IOMMU_API
-	if (tbl->it_group) {
-		iommu_group_put(tbl->it_group);
-		BUG_ON(tbl->it_group);
-	}
-#endif
-
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
 		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
@@ -871,17 +868,33 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 	}
 }
 
+unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		return TCE_PCI_READ | TCE_PCI_WRITE;
+	case DMA_FROM_DEVICE:
+		return TCE_PCI_WRITE;
+	case DMA_TO_DEVICE:
+		return TCE_PCI_READ;
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(iommu_direction_to_tce_perm);
+
 #ifdef CONFIG_IOMMU_API
 /*
  * SPAPR TCE API
  */
 static void group_release(void *iommu_data)
 {
-	struct iommu_table *tbl = iommu_data;
-	tbl->it_group = NULL;
+	struct iommu_table_group *table_group = iommu_data;
+
+	table_group->group = NULL;
 }
 
-void iommu_register_group(struct iommu_table *tbl,
+void iommu_register_group(struct iommu_table_group *table_group,
 		int pci_domain_number, unsigned long pe_num)
 {
 	struct iommu_group *grp;
@@ -893,8 +906,8 @@ void iommu_register_group(struct iommu_table *tbl,
 				PTR_ERR(grp));
 		return;
 	}
-	tbl->it_group = grp;
-	iommu_group_set_iommudata(grp, tbl, group_release);
+	table_group->group = grp;
+	iommu_group_set_iommudata(grp, table_group, group_release);
 	name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
 			pci_domain_number, pe_num);
 	if (!name)
@@ -919,8 +932,8 @@ EXPORT_SYMBOL_GPL(iommu_tce_direction);
 void iommu_flush_tce(struct iommu_table *tbl)
 {
 	/* Flush/invalidate TLB caches if necessary */
-	if (ppc_md.tce_flush)
-		ppc_md.tce_flush(tbl);
+	if (tbl->it_ops->flush)
+		tbl->it_ops->flush(tbl);
 
 	/* Make sure updates are seen by hardware */
 	mb();
@@ -931,7 +944,7 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl,
 		unsigned long ioba, unsigned long tce_value,
 		unsigned long npages)
 {
-	/* ppc_md.tce_free() does not support any value but 0 */
+	/* tbl->it_ops->clear() does not support any value but 0 */
 	if (tce_value)
 		return -EINVAL;
 
@@ -952,10 +965,7 @@ EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
 int iommu_tce_put_param_check(struct iommu_table *tbl,
 		unsigned long ioba, unsigned long tce)
 {
-	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
-		return -EINVAL;
-
-	if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ))
+	if (tce & ~IOMMU_PAGE_MASK(tbl))
 		return -EINVAL;
 
 	if (ioba & ~IOMMU_PAGE_MASK(tbl))
@@ -972,68 +982,16 @@ int iommu_tce_put_param_check(struct iommu_table *tbl,
 }
 EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
 
-unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
-{
-	unsigned long oldtce;
-	struct iommu_pool *pool = get_pool(tbl, entry);
-
-	spin_lock(&(pool->lock));
-
-	oldtce = ppc_md.tce_get(tbl, entry);
-	if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
-		ppc_md.tce_free(tbl, entry, 1);
-	else
-		oldtce = 0;
-
-	spin_unlock(&(pool->lock));
-
-	return oldtce;
-}
-EXPORT_SYMBOL_GPL(iommu_clear_tce);
-
-int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
-		unsigned long entry, unsigned long pages)
-{
-	unsigned long oldtce;
-	struct page *page;
-
-	for ( ; pages; --pages, ++entry) {
-		oldtce = iommu_clear_tce(tbl, entry);
-		if (!oldtce)
-			continue;
-
-		page = pfn_to_page(oldtce >> PAGE_SHIFT);
-		WARN_ON(!page);
-		if (page) {
-			if (oldtce & TCE_PCI_WRITE)
-				SetPageDirty(page);
-			put_page(page);
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
-
-/*
- * hwaddr is a kernel virtual address here (0xc... bazillion),
- * tce_build converts it to a physical address.
- */
-int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
-		unsigned long hwaddr, enum dma_data_direction direction)
+long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
+		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	int ret = -EBUSY;
-	unsigned long oldtce;
-	struct iommu_pool *pool = get_pool(tbl, entry);
-
-	spin_lock(&(pool->lock));
+	long ret;
 
-	oldtce = ppc_md.tce_get(tbl, entry);
-	/* Add new entry if it is not busy */
-	if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
-		ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+	ret = tbl->it_ops->exchange(tbl, entry, hpa, direction);
 
-	spin_unlock(&(pool->lock));
+	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
+			(*direction == DMA_BIDIRECTIONAL)))
+		SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
 
 	/* if (unlikely(ret))
 		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
@@ -1042,84 +1000,72 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_build);
+EXPORT_SYMBOL_GPL(iommu_tce_xchg);
 
-int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
-		unsigned long tce)
+int iommu_take_ownership(struct iommu_table *tbl)
 {
-	int ret;
-	struct page *page = NULL;
-	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
-	enum dma_data_direction direction = iommu_tce_direction(tce);
-
-	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
-			direction != DMA_TO_DEVICE, &page);
-	if (unlikely(ret != 1)) {
-		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
-				tce, entry << tbl->it_page_shift, ret); */
-		return -EFAULT;
-	}
-	hwaddr = (unsigned long) page_address(page) + offset;
-
-	ret = iommu_tce_build(tbl, entry, hwaddr, direction);
-	if (ret)
-		put_page(page);
-
-	if (ret < 0)
-		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
-			__func__, entry << tbl->it_page_shift, tce, ret);
+	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+	int ret = 0;
 
-	return ret;
-}
-EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+	/*
+	 * VFIO does not control TCE entries allocation and the guest
+	 * can write new TCEs on top of existing ones so iommu_tce_build()
+	 * must be able to release old pages. This functionality
+	 * requires exchange() callback defined so if it is not
+	 * implemented, we disallow taking ownership over the table.
+	 */
+	if (!tbl->it_ops->exchange)
+		return -EINVAL;
 
-int iommu_take_ownership(struct iommu_table *tbl)
-{
-	unsigned long sz = (tbl->it_size + 7) >> 3;
+	spin_lock_irqsave(&tbl->large_pool.lock, flags);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_lock(&tbl->pools[i].lock);
 
 	if (tbl->it_offset == 0)
 		clear_bit(0, tbl->it_map);
 
 	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
 		pr_err("iommu_tce: it_map is not empty");
-		return -EBUSY;
+		ret = -EBUSY;
+		/* Restore bit#0 set by iommu_init_table() */
+		if (tbl->it_offset == 0)
+			set_bit(0, tbl->it_map);
+	} else {
+		memset(tbl->it_map, 0xff, sz);
 	}
 
-	memset(tbl->it_map, 0xff, sz);
-	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_unlock(&tbl->pools[i].lock);
+	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
 
-	/*
-	 * Disable iommu bypass, otherwise the user can DMA to all of
-	 * our physical memory via the bypass window instead of just
-	 * the pages that has been explicitly mapped into the iommu
-	 */
-	if (tbl->set_bypass)
-		tbl->set_bypass(tbl, false);
-
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_take_ownership);
 
 void iommu_release_ownership(struct iommu_table *tbl)
 {
-	unsigned long sz = (tbl->it_size + 7) >> 3;
+	unsigned long flags, i, sz = (tbl->it_size + 7) >> 3;
+
+	spin_lock_irqsave(&tbl->large_pool.lock, flags);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_lock(&tbl->pools[i].lock);
 
-	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
 	memset(tbl->it_map, 0, sz);
 
 	/* Restore bit#0 set by iommu_init_table() */
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
 
-	/* The kernel owns the device now, we can restore the iommu bypass */
-	if (tbl->set_bypass)
-		tbl->set_bypass(tbl, true);
+	for (i = 0; i < tbl->nr_pools; i++)
+		spin_unlock(&tbl->pools[i].lock);
+	spin_unlock_irqrestore(&tbl->large_pool.lock, flags);
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
 int iommu_add_device(struct device *dev)
 {
 	struct iommu_table *tbl;
+	struct iommu_table_group_link *tgl;
 
 	/*
 	 * The sysfs entries should be populated before
@@ -1137,15 +1083,22 @@ int iommu_add_device(struct device *dev)
 	}
 
 	tbl = get_iommu_table_base(dev);
-	if (!tbl || !tbl->it_group) {
+	if (!tbl) {
 		pr_debug("%s: Skipping device %s with no tbl\n",
 			 __func__, dev_name(dev));
 		return 0;
 	}
 
+	tgl = list_first_entry_or_null(&tbl->it_group_list,
+			struct iommu_table_group_link, next);
+	if (!tgl) {
+		pr_debug("%s: Skipping device %s with no group\n",
+			 __func__, dev_name(dev));
+		return 0;
+	}
 	pr_debug("%s: Adding %s to iommu group %d\n",
 		 __func__, dev_name(dev),
-		 iommu_group_id(tbl->it_group));
+		 iommu_group_id(tgl->table_group->group));
 
 	if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
 		pr_err("%s: Invalid IOMMU page size %lx (%lx) on %s\n",
@@ -1154,7 +1107,7 @@ int iommu_add_device(struct device *dev)
 		return -EINVAL;
 	}
 
-	return iommu_group_add_device(tbl->it_group, dev);
+	return iommu_group_add_device(tgl->table_group->group, dev);
 }
 EXPORT_SYMBOL_GPL(iommu_add_device);
 
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 15c99b649b04..b2eb4686bd8f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -73,7 +73,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __this_cpu_inc_return(mce_nest_count);
+	int index = __this_cpu_inc_return(mce_nest_count) - 1;
 	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
@@ -184,7 +184,7 @@ void machine_check_queue_event(void)
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __this_cpu_inc_return(mce_queue_count);
+	index = __this_cpu_inc_return(mce_queue_count) - 1;
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
 		__this_cpu_dec(mce_queue_count);
diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c
index 71bd161640cf..dab616a33b8d 100644
--- a/arch/powerpc/kernel/msi.c
+++ b/arch/powerpc/kernel/msi.c
@@ -15,7 +15,10 @@
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	if (!ppc_md.setup_msi_irqs || !ppc_md.teardown_msi_irqs) {
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (!phb->controller_ops.setup_msi_irqs ||
+	    !phb->controller_ops.teardown_msi_irqs) {
 		pr_debug("msi: Platform doesn't provide MSI callbacks.\n");
 		return -ENOSYS;
 	}
@@ -24,10 +27,12 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	return ppc_md.setup_msi_irqs(dev, nvec, type);
+	return phb->controller_ops.setup_msi_irqs(dev, nvec, type);
 }
 
 void arch_teardown_msi_irqs(struct pci_dev *dev)
 {
-	ppc_md.teardown_msi_irqs(dev);
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	phb->controller_ops.teardown_msi_irqs(dev);
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 0d054068a21d..b9de34d44fcb 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -89,6 +89,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 #endif
 	return phb;
 }
+EXPORT_SYMBOL_GPL(pcibios_alloc_controller);
 
 void pcibios_free_controller(struct pci_controller *phb)
 {
@@ -1447,6 +1448,7 @@ void pcibios_claim_one_bus(struct pci_bus *bus)
 	list_for_each_entry(child_bus, &bus->children, node)
 		pcibios_claim_one_bus(child_bus);
 }
+EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
 
 
 /* pcibios_finish_adding_to_bus
@@ -1488,6 +1490,14 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
+void pcibios_disable_device(struct pci_dev *dev)
+{
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (phb->controller_ops.disable_device)
+		phb->controller_ops.disable_device(dev);
+}
+
 resource_size_t pcibios_io_space_offset(struct pci_controller *hose)
 {
 	return (unsigned long) hose->io_base_virt - _IO_BASE;
@@ -1680,6 +1690,7 @@ void pcibios_scan_phb(struct pci_controller *hose)
 			pcie_bus_configure_settings(child);
 	}
 }
+EXPORT_SYMBOL_GPL(pcibios_scan_phb);
 
 static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
 {
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 7ed85a69a9c2..7f9ed0c1f6b9 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -29,7 +29,12 @@
  */
 void pcibios_release_device(struct pci_dev *dev)
 {
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
 	eeh_remove_device(dev);
+
+	if (phb->controller_ops.release_device)
+		phb->controller_ops.release_device(dev);
 }
 
 /**
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index febb50dd5328..8005e18d1b40 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1112,7 +1112,6 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
 /*
  * Copy a thread..
  */
-extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
 
 /*
  * Copy architecture-specific thread state
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 308c5e15676b..8b888b12a475 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -46,7 +46,6 @@
 #include <asm/mmu.h>
 #include <asm/paca.h>
 #include <asm/pgtable.h>
-#include <asm/pci.h>
 #include <asm/iommu.h>
 #include <asm/btext.h>
 #include <asm/sections.h>
@@ -573,6 +572,7 @@ static void __init early_reserve_mem_dt(void)
 	int len;
 	const __be32 *prop;
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	dt_root = of_get_flat_dt_root();
@@ -800,6 +800,7 @@ int of_get_ibm_chip_id(struct device_node *np)
 	}
 	return -1;
 }
+EXPORT_SYMBOL(of_get_ibm_chip_id);
 
 /**
  * cpu_to_chip_id - Return the cpus chip-id
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index fd1fe4c37599..fcca8077e6a2 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -37,7 +37,6 @@
 #include <asm/smp.h>
 #include <asm/mmu.h>
 #include <asm/pgtable.h>
-#include <asm/pci.h>
 #include <asm/iommu.h>
 #include <asm/btext.h>
 #include <asm/sections.h>
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c69671c03c3b..bdcbb716f4d6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -523,7 +523,8 @@ void __init setup_system(void)
 	smp_release_cpus();
 #endif
 
-	pr_info("Starting Linux PPC64 %s\n", init_utsname()->version);
+	pr_info("Starting Linux %s %s\n", init_utsname()->machine,
+		 init_utsname()->version);
 
 	pr_info("-----------------------------------------------------\n");
 	pr_info("ppc64_pft_size    = 0x%llx\n", ppc64_pft_size);
@@ -686,6 +687,9 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_PPC_64K_PAGES
 	init_mm.context.pte_frag = NULL;
 #endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	mm_iommu_init(&init_mm.context);
+#endif
 	irqstack_early_init();
 	exc_lvl_early_init();
 	emergency_stack_init();
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index fa1fd8a0c867..692873bff334 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -496,13 +496,34 @@ static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
+/*
+ * This is the system wide DSCR register default value. Any
+ * change to this default value through the sysfs interface
+ * will update all per cpu DSCR default values across the
+ * system stored in their respective PACA structures.
+ */
 static unsigned long dscr_default;
 
+/**
+ * read_dscr() - Fetch the cpu specific DSCR default
+ * @val:	Returned cpu specific DSCR default value
+ *
+ * This function returns the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
 static void read_dscr(void *val)
 {
 	*(unsigned long *)val = get_paca()->dscr_default;
 }
 
+
+/**
+ * write_dscr() - Update the cpu specific DSCR default
+ * @val:	New cpu specific DSCR default value to update
+ *
+ * This function updates the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
 static void write_dscr(void *val)
 {
 	get_paca()->dscr_default = *(unsigned long *)val;
@@ -520,12 +541,29 @@ static void add_write_permission_dev_attr(struct device_attribute *attr)
 	attr->attr.mode |= 0200;
 }
 
+/**
+ * show_dscr_default() - Fetch the system wide DSCR default
+ * @dev:	Device structure
+ * @attr:	Device attribute structure
+ * @buf:	Interface buffer
+ *
+ * This function returns the system wide DSCR default value.
+ */
 static ssize_t show_dscr_default(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
+/**
+ * store_dscr_default() - Update the system wide DSCR default
+ * @dev:	Device structure
+ * @attr:	Device attribute structure
+ * @buf:	Interface buffer
+ * @count:	Size of the update
+ *
+ * This function updates the system wide DSCR default value.
+ */
 static ssize_t __used store_dscr_default(struct device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 5754b226da7e..bf8f34a58670 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -293,7 +293,7 @@ dont_backup_fp:
 	ld	r2, STK_GOT(r1)
 
 	/* Load CPU's default DSCR */
-	ld	r0, PACA_DSCR(r13)
+	ld	r0, PACA_DSCR_DEFAULT(r13)
 	mtspr	SPRN_DSCR, r0
 
 	blr
@@ -473,7 +473,7 @@ restore_gprs:
 	ld	r2, STK_GOT(r1)
 
 	/* Load CPU's default DSCR */
-	ld	r0, PACA_DSCR(r13)
+	ld	r0, PACA_DSCR_DEFAULT(r13)
 	mtspr	SPRN_DSCR, r0
 
 	blr
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 19e4744b6eba..6530f1b8874d 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1377,6 +1377,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 	};
 	char *facility = "unknown";
 	u64 value;
+	u32 instword, rd;
 	u8 status;
 	bool hv;
 
@@ -1388,12 +1389,46 @@ void facility_unavailable_exception(struct pt_regs *regs)
 
 	status = value >> 56;
 	if (status == FSCR_DSCR_LG) {
-		/* User is acessing the DSCR.  Set the inherit bit and allow
-		 * the user to set it directly in future by setting via the
-		 * FSCR DSCR bit.  We always leave HFSCR DSCR set.
+		/*
+		 * User is accessing the DSCR register using the problem
+		 * state only SPR number (0x03) either through a mfspr or
+		 * a mtspr instruction. If it is a write attempt through
+		 * a mtspr, then we set the inherit bit. This also allows
+		 * the user to write or read the register directly in the
+		 * future by setting via the FSCR DSCR bit. But in case it
+		 * is a read DSCR attempt through a mfspr instruction, we
+		 * just emulate the instruction instead. This code path will
+		 * always emulate all the mfspr instructions till the user
+		 * has attempted atleast one mtspr instruction. This way it
+		 * preserves the same behaviour when the user is accessing
+		 * the DSCR through privilege level only SPR number (0x11)
+		 * which is emulated through illegal instruction exception.
+		 * We always leave HFSCR DSCR set.
 		 */
-		current->thread.dscr_inherit = 1;
-		mtspr(SPRN_FSCR, value | FSCR_DSCR);
+		if (get_user(instword, (u32 __user *)(regs->nip))) {
+			pr_err("Failed to fetch the user instruction\n");
+			return;
+		}
+
+		/* Write into DSCR (mtspr 0x03, RS) */
+		if ((instword & PPC_INST_MTSPR_DSCR_USER_MASK)
+				== PPC_INST_MTSPR_DSCR_USER) {
+			rd = (instword >> 21) & 0x1f;
+			current->thread.dscr = regs->gpr[rd];
+			current->thread.dscr_inherit = 1;
+			mtspr(SPRN_FSCR, value | FSCR_DSCR);
+		}
+
+		/* Read from DSCR (mfspr RT, 0x03) */
+		if ((instword & PPC_INST_MFSPR_DSCR_USER_MASK)
+				== PPC_INST_MFSPR_DSCR_USER) {
+			if (emulate_instruction(regs)) {
+				pr_err("DSCR based mfspr emulation failed\n");
+				return;
+			}
+			regs->nip += 4;
+			emulate_single_step(regs);
+		}
 		return;
 	}
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 305eb0d9b768..b457bfa28436 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -49,13 +49,16 @@
 /* The alignment of the vDSO */
 #define VDSO_ALIGNMENT	(1 << 16)
 
-extern char vdso32_start, vdso32_end;
-static void *vdso32_kbase = &vdso32_start;
 static unsigned int vdso32_pages;
+static void *vdso32_kbase;
 static struct page **vdso32_pagelist;
 unsigned long vdso32_sigtramp;
 unsigned long vdso32_rt_sigtramp;
 
+#ifdef CONFIG_VDSO32
+extern char vdso32_start, vdso32_end;
+#endif
+
 #ifdef CONFIG_PPC64
 extern char vdso64_start, vdso64_end;
 static void *vdso64_kbase = &vdso64_start;
@@ -140,50 +143,6 @@ struct lib64_elfinfo
 };
 
 
-#ifdef __DEBUG
-static void dump_one_vdso_page(struct page *pg, struct page *upg)
-{
-	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
-	       page_count(pg),
-	       pg->flags);
-	if (upg && !IS_ERR(upg) /* && pg != upg*/) {
-		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
-						       << PAGE_SHIFT),
-		       page_count(upg),
-		       upg->flags);
-	}
-	printk("\n");
-}
-
-static void dump_vdso_pages(struct vm_area_struct * vma)
-{
-	int i;
-
-	if (!vma || is_32bit_task()) {
-		printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
-		for (i=0; i<vdso32_pages; i++) {
-			struct page *pg = virt_to_page(vdso32_kbase +
-						       i*PAGE_SIZE);
-			struct page *upg = (vma && vma->vm_mm) ?
-				follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
-				: NULL;
-			dump_one_vdso_page(pg, upg);
-		}
-	}
-	if (!vma || !is_32bit_task()) {
-		printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
-		for (i=0; i<vdso64_pages; i++) {
-			struct page *pg = virt_to_page(vdso64_kbase +
-						       i*PAGE_SIZE);
-			struct page *upg = (vma && vma->vm_mm) ?
-				follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0)
-				: NULL;
-			dump_one_vdso_page(pg, upg);
-		}
-	}
-}
-#endif /* DEBUG */
-
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
@@ -292,6 +251,7 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 
 
 
+#ifdef CONFIG_VDSO32
 static void * __init find_section32(Elf32_Ehdr *ehdr, const char *secname,
 				  unsigned long *size)
 {
@@ -379,6 +339,20 @@ static int __init vdso_do_func_patch32(struct lib32_elfinfo *v32,
 
 	return 0;
 }
+#else /* !CONFIG_VDSO32 */
+static unsigned long __init find_function32(struct lib32_elfinfo *lib,
+					    const char *symname)
+{
+	return 0;
+}
+
+static int __init vdso_do_func_patch32(struct lib32_elfinfo *v32,
+				       struct lib64_elfinfo *v64,
+				       const char *orig, const char *fix)
+{
+	return 0;
+}
+#endif /* CONFIG_VDSO32 */
 
 
 #ifdef CONFIG_PPC64
@@ -489,6 +463,7 @@ static __init int vdso_do_find_sections(struct lib32_elfinfo *v32,
 	 * Locate symbol tables & text section
 	 */
 
+#ifdef CONFIG_VDSO32
 	v32->dynsym = find_section32(v32->hdr, ".dynsym", &v32->dynsymsize);
 	v32->dynstr = find_section32(v32->hdr, ".dynstr", NULL);
 	if (v32->dynsym == NULL || v32->dynstr == NULL) {
@@ -501,6 +476,7 @@ static __init int vdso_do_find_sections(struct lib32_elfinfo *v32,
 		return -1;
 	}
 	v32->text = sect - vdso32_kbase;
+#endif
 
 #ifdef CONFIG_PPC64
 	v64->dynsym = find_section64(v64->hdr, ".dynsym", &v64->dynsymsize);
@@ -537,7 +513,9 @@ static __init void vdso_setup_trampolines(struct lib32_elfinfo *v32,
 static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
 				       struct lib64_elfinfo *v64)
 {
+#ifdef CONFIG_VDSO32
 	Elf32_Sym *sym32;
+#endif
 #ifdef CONFIG_PPC64
 	Elf64_Sym *sym64;
 
@@ -552,6 +530,7 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
 		(sym64->st_value - VDSO64_LBASE);
 #endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_VDSO32
 	sym32 = find_symbol32(v32, "__kernel_datapage_offset");
 	if (sym32 == NULL) {
 		printk(KERN_ERR "vDSO32: Can't find symbol "
@@ -561,6 +540,7 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
 	*((int *)(vdso32_kbase + (sym32->st_value - VDSO32_LBASE))) =
 		(vdso32_pages << PAGE_SHIFT) -
 		(sym32->st_value - VDSO32_LBASE);
+#endif
 
 	return 0;
 }
@@ -569,55 +549,54 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
 static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
 				      struct lib64_elfinfo *v64)
 {
-	void *start32;
-	unsigned long size32;
+	unsigned long size;
+	void *start;
 
 #ifdef CONFIG_PPC64
-	void *start64;
-	unsigned long size64;
-
-	start64 = find_section64(v64->hdr, "__ftr_fixup", &size64);
-	if (start64)
+	start = find_section64(v64->hdr, "__ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(cur_cpu_spec->cpu_features,
-				  start64, start64 + size64);
+				  start, start + size);
 
-	start64 = find_section64(v64->hdr, "__mmu_ftr_fixup", &size64);
-	if (start64)
+	start = find_section64(v64->hdr, "__mmu_ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(cur_cpu_spec->mmu_features,
-				  start64, start64 + size64);
+				  start, start + size);
 
-	start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
-	if (start64)
+	start = find_section64(v64->hdr, "__fw_ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(powerpc_firmware_features,
-				  start64, start64 + size64);
+				  start, start + size);
 
-	start64 = find_section64(v64->hdr, "__lwsync_fixup", &size64);
-	if (start64)
+	start = find_section64(v64->hdr, "__lwsync_fixup", &size);
+	if (start)
 		do_lwsync_fixups(cur_cpu_spec->cpu_features,
-				 start64, start64 + size64);
+				 start, start + size);
 #endif /* CONFIG_PPC64 */
 
-	start32 = find_section32(v32->hdr, "__ftr_fixup", &size32);
-	if (start32)
+#ifdef CONFIG_VDSO32
+	start = find_section32(v32->hdr, "__ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(cur_cpu_spec->cpu_features,
-				  start32, start32 + size32);
+				  start, start + size);
 
-	start32 = find_section32(v32->hdr, "__mmu_ftr_fixup", &size32);
-	if (start32)
+	start = find_section32(v32->hdr, "__mmu_ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(cur_cpu_spec->mmu_features,
-				  start32, start32 + size32);
+				  start, start + size);
 
 #ifdef CONFIG_PPC64
-	start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
-	if (start32)
+	start = find_section32(v32->hdr, "__fw_ftr_fixup", &size);
+	if (start)
 		do_feature_fixups(powerpc_firmware_features,
-				  start32, start32 + size32);
+				  start, start + size);
 #endif /* CONFIG_PPC64 */
 
-	start32 = find_section32(v32->hdr, "__lwsync_fixup", &size32);
-	if (start32)
+	start = find_section32(v32->hdr, "__lwsync_fixup", &size);
+	if (start)
 		do_lwsync_fixups(cur_cpu_spec->cpu_features,
-				 start32, start32 + size32);
+				 start, start + size);
+#endif
 
 	return 0;
 }
@@ -779,11 +758,15 @@ static int __init vdso_init(void)
 #endif /* CONFIG_PPC64 */
 
 
+#ifdef CONFIG_VDSO32
+	vdso32_kbase = &vdso32_start;
+
 	/*
 	 * Calculate the size of the 32 bits vDSO
 	 */
 	vdso32_pages = (&vdso32_end - &vdso32_start) >> PAGE_SHIFT;
 	DBG("vdso32_kbase: %p, 0x%x pages\n", vdso32_kbase, vdso32_pages);
+#endif
 
 
 	/*
@@ -804,6 +787,7 @@ static int __init vdso_init(void)
 		return 0;
 	}
 
+#ifdef CONFIG_VDSO32
 	/* Make sure pages are in the correct state */
 	vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 2),
 				  GFP_KERNEL);
@@ -816,6 +800,7 @@ static int __init vdso_init(void)
 	}
 	vdso32_pagelist[i++] = virt_to_page(vdso_data);
 	vdso32_pagelist[i] = NULL;
+#endif
 
 #ifdef CONFIG_PPC64
 	vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 2),
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 5bfdab9047be..5f8dcdaa2820 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -557,11 +557,11 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl;
 	struct scatterlist *sgl;
-	int ret, count = 0;
+	int ret, count;
 	size_t alloc_size = 0;
 
 	tbl = get_iommu_table_base(dev);
-	for (sgl = sglist; count < nelems; count++, sgl++)
+	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
 	if (vio_cmo_alloc(viodev, alloc_size)) {
@@ -577,7 +577,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 		return ret;
 	}
 
-	for (sgl = sglist, count = 0; count < ret; count++, sgl++)
+	for_each_sg(sglist, sgl, ret, count)
 		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
@@ -594,10 +594,10 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 	struct iommu_table *tbl;
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
-	int count = 0;
+	int count;
 
 	tbl = get_iommu_table_base(dev);
-	for (sgl = sglist; count < nelems; count++, sgl++)
+	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
 	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
@@ -1196,6 +1196,11 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	tbl->it_type = TCE_VB;
 	tbl->it_blocksize = 16;
 
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+	else
+		tbl->it_ops = &iommu_table_pseries_ops;
+
 	return iommu_init_table(tbl, -1);
 }
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f096e72262f4..1db685104ffc 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -213,6 +213,7 @@ SECTIONS
 		*(.opd)
 	}
 
+	. = ALIGN(256);
 	.got : AT(ADDR(.got) - LOAD_OFFSET) {
 		__toc_start = .;
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 453a8a47a467..05ea8fc7f829 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -757,16 +757,17 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
-				struct kvm_userspace_memory_region *mem)
+				const struct kvm_userspace_memory_region *mem)
 {
 	return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new)
 {
-	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 1a4acf8bf4f4..dab68b7af3f2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -650,7 +650,7 @@ static void kvmppc_rmap_reset(struct kvm *kvm)
 	int srcu_idx;
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	slots = kvm->memslots;
+	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
 		/*
 		 * This assumes it is acceptable to lose reference and
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48d3c5d2ecc9..68d067ad4222 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1952,7 +1952,7 @@ static void post_guest_process(struct kvmppc_vcore *vc)
  */
 static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu, *vnext;
 	int i;
 	int srcu_idx;
 
@@ -1982,7 +1982,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	if ((threads_per_core > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+		list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+					 arch.run_list) {
 			vcpu->arch.ret = -EBUSY;
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
@@ -2320,6 +2321,7 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
 static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
 					 struct kvm_dirty_log *log)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int r;
 	unsigned long n;
@@ -2330,7 +2332,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
 	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
-	memslot = id_to_memslot(kvm->memslots, log->slot);
+	slots = kvm_memslots(kvm);
+	memslot = id_to_memslot(slots, log->slot);
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -2373,16 +2376,18 @@ static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
 
 static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
 					struct kvm_memory_slot *memslot,
-					struct kvm_userspace_memory_region *mem)
+					const struct kvm_userspace_memory_region *mem)
 {
 	return 0;
 }
 
 static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 
 	if (npages && old->npages) {
@@ -2392,7 +2397,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 		 * since the rmap array starts out as all zeroes,
 		 * i.e. no pages are dirty.
 		 */
-		memslot = id_to_memslot(kvm->memslots, mem->slot);
+		slots = kvm_memslots(kvm);
+		memslot = id_to_memslot(slots, mem->slot);
 		kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
 	}
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 4d70df26c402..faa86e9c0551 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -324,7 +324,7 @@ kvm_start_guest:
 kvm_secondary_got_guest:
 
 	/* Set HSTATE_DSCR(r13) to something sensible */
-	ld	r6, PACA_DSCR(r13)
+	ld	r6, PACA_DSCR_DEFAULT(r13)
 	std	r6, HSTATE_DSCR(r13)
 
 	/* Order load of vcore, ptid etc. after load of vcpu */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index f57383941d03..64891b081ad5 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1530,6 +1530,7 @@ out:
 static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
 					 struct kvm_dirty_log *log)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	struct kvm_vcpu *vcpu;
 	ulong ga, ga_end;
@@ -1545,7 +1546,8 @@ static int kvm_vm_ioctl_get_dirty_log_pr(struct kvm *kvm,
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = id_to_memslot(kvm->memslots, log->slot);
+		slots = kvm_memslots(kvm);
+		memslot = id_to_memslot(slots, log->slot);
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
@@ -1571,14 +1573,15 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm,
 
 static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
 					struct kvm_memory_slot *memslot,
-					struct kvm_userspace_memory_region *mem)
+					const struct kvm_userspace_memory_region *mem)
 {
 	return 0;
 }
 
 static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new)
 {
 	return;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6c1316a15a27..cc5842657161 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1004,10 +1004,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	local_irq_enable();
-
 	trace_kvm_exit(exit_nr, vcpu);
-	kvm_guest_exit();
+	__kvm_guest_exit();
+
+	local_irq_enable();
 
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
@@ -1784,14 +1784,15 @@ int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_memory_slot *memslot,
-				      struct kvm_userspace_memory_region *mem)
+				      const struct kvm_userspace_memory_region *mem)
 {
 	return 0;
 }
 
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old)
+				const struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new)
 {
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index ac3ddf115f3d..e5dde32fe71f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -115,7 +115,7 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		kvm_guest_enter();
+		__kvm_guest_enter();
 		return 1;
 	}
 
@@ -595,18 +595,19 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
 	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   const struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
-	kvmppc_core_commit_memory_region(kvm, mem, old);
+	kvmppc_core_commit_memory_region(kvm, mem, old, new);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 7902802a19a5..a47e14277fd8 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -33,6 +33,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
 obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
 
 obj-$(CONFIG_ALTIVEC)	+= xor_vmx.o
-CFLAGS_xor_vmx.o += -maltivec -mabi=altivec
+CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
 
 obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index 3cf529ceec5b..ac93a3bd2730 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -27,11 +27,11 @@ int enter_vmx_usercopy(void)
 	if (in_interrupt())
 		return 0;
 
-	/* This acts as preempt_disable() as well and will make
-	 * enable_kernel_altivec(). We need to disable page faults
-	 * as they can call schedule and thus make us lose the VMX
-	 * context. So on page faults, we just fail which will cause
-	 * a fallback to the normal non-vmx copy.
+	preempt_disable();
+	/*
+	 * We need to disable page faults as they can call schedule and
+	 * thus make us lose the VMX context. So on page faults, we just
+	 * fail which will cause a fallback to the normal non-vmx copy.
 	 */
 	pagefault_disable();
 
@@ -47,6 +47,7 @@ int enter_vmx_usercopy(void)
 int exit_vmx_usercopy(void)
 {
 	pagefault_enable();
+	preempt_enable();
 	return 0;
 }
 
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 9c8770b5f96f..3eb73a38220d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -36,3 +36,4 @@ obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
+obj-$(CONFIG_SPAPR_TCE_IOMMU)	+= mmu_context_iommu.o
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index f031a47d7701..6527882ce05e 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -26,7 +26,7 @@
 #include <asm/reg.h>
 #include <asm/copro.h>
 #include <asm/spu.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 /*
  * This ought to be kept in sync with the powerpc specific do_page_fault
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
 
 int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 {
-	u64 vsid;
+	u64 vsid, vsidkey;
 	int psize, ssize;
 
 	switch (REGION_ID(ea)) {
@@ -109,6 +109,7 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 		psize = get_slice_psize(mm, ea);
 		ssize = user_segment_size(ea);
 		vsid = get_vsid(mm->context.id, ea, ssize);
+		vsidkey = SLB_VSID_USER;
 		break;
 	case VMALLOC_REGION_ID:
 		pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
@@ -118,19 +119,21 @@ int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
 			psize = mmu_io_psize;
 		ssize = mmu_kernel_ssize;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		vsidkey = SLB_VSID_KERNEL;
 		break;
 	case KERNEL_REGION_ID:
 		pr_devel("%s: 0x%llx -- KERNEL_REGION_ID\n", __func__, ea);
 		psize = mmu_linear_psize;
 		ssize = mmu_kernel_ssize;
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
+		vsidkey = SLB_VSID_KERNEL;
 		break;
 	default:
 		pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
 		return 1;
 	}
 
-	vsid = (vsid << slb_vsid_shift(ssize)) | SLB_VSID_USER;
+	vsid = (vsid << slb_vsid_shift(ssize)) | vsidkey;
 
 	vsid |= mmu_psize_defs[psize].sllp |
 		((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b396868d2aa7..6d535973b200 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -33,13 +33,13 @@
 #include <linux/ratelimit.h>
 #include <linux/context_tracking.h>
 #include <linux/hugetlb.h>
+#include <linux/uaccess.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 #include <asm/mmu_context.h>
-#include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
 #include <asm/debug.h>
@@ -272,15 +272,16 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (in_atomic() || mm == NULL) {
+	if (faulthandler_disabled() || mm == NULL) {
 		if (!user_mode(regs)) {
 			rc = SIGSEGV;
 			goto bail;
 		}
-		/* in_atomic() in user mode is really bad,
+		/* faulthandler_disabled() in user mode is really bad,
 		   as is current->mm == NULL. */
 		printk(KERN_EMERG "Page fault in user mode with "
-		       "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+		       "faulthandler_disabled() = %d mm = %p\n",
+		       faulthandler_disabled(), mm);
 		printk(KERN_EMERG "NIP = %lx  MSR = %lx\n",
 		       regs->nip, regs->msr);
 		die("Weird page fault", regs, SIGSEGV);
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 9c4880ddecd6..13befa35d8a8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -29,7 +29,7 @@
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
 
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #ifdef DEBUG_LOW
 #define DBG_LOW(fmt...) udbg_printf(fmt)
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index fda236f908eb..5ec987f65b2c 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -57,6 +57,7 @@
 #include <asm/fadump.h>
 #include <asm/firmware.h>
 #include <asm/tm.h>
+#include <asm/trace.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -1004,6 +1005,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 
 	DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n",
 		ea, access, trap);
+	trace_hash_fault(ea, access, trap);
 
 	/* Get region & vsid */
  	switch (REGION_ID(ea)) {
@@ -1475,7 +1477,7 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long hash;
 	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
 	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
-	unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL);
+	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL));
 	long ret;
 
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
index e7450bdbe83a..e292c8a60952 100644
--- a/arch/powerpc/mm/highmem.c
+++ b/arch/powerpc/mm/highmem.c
@@ -34,7 +34,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -59,6 +59,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < __fix_to_virt(FIX_KMAP_END)) {
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -82,5 +83,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0ce968b00b7c..38bd5d998c81 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -439,11 +439,6 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 }
 #endif
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #ifdef CONFIG_PPC_FSL_BOOK3E
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
@@ -689,27 +684,34 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
-	pte_t *ptep;
-	struct page *page;
+	pte_t *ptep, pte;
 	unsigned shift;
 	unsigned long mask, flags;
+	struct page *page = ERR_PTR(-EINVAL);
+
+	local_irq_save(flags);
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!ptep)
+		goto no_page;
+	pte = READ_ONCE(*ptep);
 	/*
+	 * Verify it is a huge page else bail.
 	 * Transparent hugepages are handled by generic code. We can skip them
 	 * here.
 	 */
-	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!shift || pmd_trans_huge(__pmd(pte_val(pte))))
+		goto no_page;
 
-	/* Verify it is a huge page else bail. */
-	if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) {
-		local_irq_restore(flags);
-		return ERR_PTR(-EINVAL);
+	if (!pte_present(pte)) {
+		page = NULL;
+		goto no_page;
 	}
 	mask = (1UL << shift) - 1;
-	page = pte_page(*ptep);
+	page = pte_page(pte);
 	if (page)
 		page += (address & mask) / PAGE_SIZE;
 
+no_page:
 	local_irq_restore(flags);
 	return page;
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 45fda71feb27..0f11819d8f1d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -560,7 +560,7 @@ subsys_initcall(add_system_ram_resources);
  */
 int devmem_is_allowed(unsigned long pfn)
 {
-	if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+	if (iomem_is_exclusive(PFN_PHYS(pfn)))
 		return 0;
 	if (!page_is_ram(pfn))
 		return 1;
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 178876aef40f..4e4efbc2658e 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -89,6 +89,9 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 #ifdef CONFIG_PPC_64K_PAGES
 	mm->context.pte_frag = NULL;
 #endif
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	mm_iommu_init(&mm->context);
+#endif
 	return 0;
 }
 
@@ -132,6 +135,9 @@ static inline void destroy_pagetable_page(struct mm_struct *mm)
 
 void destroy_context(struct mm_struct *mm)
 {
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	mm_iommu_cleanup(&mm->context);
+#endif
 
 #ifdef CONFIG_PPC_ICSWX
 	drop_cop(mm->context.acop, mm);
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
new file mode 100644
index 000000000000..da6a2168ae9e
--- /dev/null
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -0,0 +1,316 @@
+/*
+ *  IOMMU helpers in MMU context.
+ *
+ *  Copyright (C) 2015 IBM Corp. <aik@ozlabs.ru>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+#include <linux/vmalloc.h>
+#include <linux/mutex.h>
+#include <asm/mmu_context.h>
+
+static DEFINE_MUTEX(mem_list_mutex);
+
+struct mm_iommu_table_group_mem_t {
+	struct list_head next;
+	struct rcu_head rcu;
+	unsigned long used;
+	atomic64_t mapped;
+	u64 ua;			/* userspace address */
+	u64 entries;		/* number of entries in hpas[] */
+	u64 *hpas;		/* vmalloc'ed */
+};
+
+static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
+		unsigned long npages, bool incr)
+{
+	long ret = 0, locked, lock_limit;
+
+	if (!npages)
+		return 0;
+
+	down_write(&mm->mmap_sem);
+
+	if (incr) {
+		locked = mm->locked_vm + npages;
+		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
+			ret = -ENOMEM;
+		else
+			mm->locked_vm += npages;
+	} else {
+		if (WARN_ON_ONCE(npages > mm->locked_vm))
+			npages = mm->locked_vm;
+		mm->locked_vm -= npages;
+	}
+
+	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
+			current->pid,
+			incr ? '+' : '-',
+			npages << PAGE_SHIFT,
+			mm->locked_vm << PAGE_SHIFT,
+			rlimit(RLIMIT_MEMLOCK));
+	up_write(&mm->mmap_sem);
+
+	return ret;
+}
+
+bool mm_iommu_preregistered(void)
+{
+	if (!current || !current->mm)
+		return false;
+
+	return !list_empty(&current->mm->context.iommu_group_mem_list);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
+
+long mm_iommu_get(unsigned long ua, unsigned long entries,
+		struct mm_iommu_table_group_mem_t **pmem)
+{
+	struct mm_iommu_table_group_mem_t *mem;
+	long i, j, ret = 0, locked_entries = 0;
+	struct page *page = NULL;
+
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
+	mutex_lock(&mem_list_mutex);
+
+	list_for_each_entry_rcu(mem, &current->mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua == ua) && (mem->entries == entries)) {
+			++mem->used;
+			*pmem = mem;
+			goto unlock_exit;
+		}
+
+		/* Overlap? */
+		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
+				(ua < (mem->ua +
+				       (mem->entries << PAGE_SHIFT)))) {
+			ret = -EINVAL;
+			goto unlock_exit;
+		}
+
+	}
+
+	ret = mm_iommu_adjust_locked_vm(current->mm, entries, true);
+	if (ret)
+		goto unlock_exit;
+
+	locked_entries = entries;
+
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	if (!mem) {
+		ret = -ENOMEM;
+		goto unlock_exit;
+	}
+
+	mem->hpas = vzalloc(entries * sizeof(mem->hpas[0]));
+	if (!mem->hpas) {
+		kfree(mem);
+		ret = -ENOMEM;
+		goto unlock_exit;
+	}
+
+	for (i = 0; i < entries; ++i) {
+		if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+					1/* pages */, 1/* iswrite */, &page)) {
+			for (j = 0; j < i; ++j)
+				put_page(pfn_to_page(
+						mem->hpas[j] >> PAGE_SHIFT));
+			vfree(mem->hpas);
+			kfree(mem);
+			ret = -EFAULT;
+			goto unlock_exit;
+		}
+
+		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
+	}
+
+	atomic64_set(&mem->mapped, 1);
+	mem->used = 1;
+	mem->ua = ua;
+	mem->entries = entries;
+	*pmem = mem;
+
+	list_add_rcu(&mem->next, &current->mm->context.iommu_group_mem_list);
+
+unlock_exit:
+	if (locked_entries && ret)
+		mm_iommu_adjust_locked_vm(current->mm, locked_entries, false);
+
+	mutex_unlock(&mem_list_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_get);
+
+static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
+{
+	long i;
+	struct page *page = NULL;
+
+	for (i = 0; i < mem->entries; ++i) {
+		if (!mem->hpas[i])
+			continue;
+
+		page = pfn_to_page(mem->hpas[i] >> PAGE_SHIFT);
+		if (!page)
+			continue;
+
+		put_page(page);
+		mem->hpas[i] = 0;
+	}
+}
+
+static void mm_iommu_do_free(struct mm_iommu_table_group_mem_t *mem)
+{
+
+	mm_iommu_unpin(mem);
+	vfree(mem->hpas);
+	kfree(mem);
+}
+
+static void mm_iommu_free(struct rcu_head *head)
+{
+	struct mm_iommu_table_group_mem_t *mem = container_of(head,
+			struct mm_iommu_table_group_mem_t, rcu);
+
+	mm_iommu_do_free(mem);
+}
+
+static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
+{
+	list_del_rcu(&mem->next);
+	mm_iommu_adjust_locked_vm(current->mm, mem->entries, false);
+	call_rcu(&mem->rcu, mm_iommu_free);
+}
+
+long mm_iommu_put(struct mm_iommu_table_group_mem_t *mem)
+{
+	long ret = 0;
+
+	if (!current || !current->mm)
+		return -ESRCH; /* process exited */
+
+	mutex_lock(&mem_list_mutex);
+
+	if (mem->used == 0) {
+		ret = -ENOENT;
+		goto unlock_exit;
+	}
+
+	--mem->used;
+	/* There are still users, exit */
+	if (mem->used)
+		goto unlock_exit;
+
+	/* Are there still mappings? */
+	if (atomic_cmpxchg(&mem->mapped, 1, 0) != 1) {
+		++mem->used;
+		ret = -EBUSY;
+		goto unlock_exit;
+	}
+
+	/* @mapped became 0 so now mappings are disabled, release the region */
+	mm_iommu_release(mem);
+
+unlock_exit:
+	mutex_unlock(&mem_list_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_put);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_lookup(unsigned long ua,
+		unsigned long size)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_rcu(mem,
+			&current->mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua <= ua) &&
+				(ua + size <= mem->ua +
+				 (mem->entries << PAGE_SHIFT))) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_lookup);
+
+struct mm_iommu_table_group_mem_t *mm_iommu_find(unsigned long ua,
+		unsigned long entries)
+{
+	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;
+
+	list_for_each_entry_rcu(mem,
+			&current->mm->context.iommu_group_mem_list,
+			next) {
+		if ((mem->ua == ua) && (mem->entries == entries)) {
+			ret = mem;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_find);
+
+long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
+		unsigned long ua, unsigned long *hpa)
+{
+	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
+	u64 *va = &mem->hpas[entry];
+
+	if (entry >= mem->entries)
+		return -EFAULT;
+
+	*hpa = *va | (ua & ~PAGE_MASK);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
+
+long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
+{
+	if (atomic64_inc_not_zero(&mem->mapped))
+		return 0;
+
+	/* Last mm_iommu_put() has been called, no more mappings allowed() */
+	return -ENXIO;
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_inc);
+
+void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
+{
+	atomic64_add_unless(&mem->mapped, -1, 1);
+}
+EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);
+
+void mm_iommu_init(mm_context_t *ctx)
+{
+	INIT_LIST_HEAD_RCU(&ctx->iommu_group_mem_list);
+}
+
+void mm_iommu_cleanup(mm_context_t *ctx)
+{
+	struct mm_iommu_table_group_mem_t *mem, *tmp;
+
+	list_for_each_entry_safe(mem, tmp, &ctx->iommu_group_mem_list, next) {
+		list_del_rcu(&mem->next);
+		mm_iommu_do_free(mem);
+	}
+}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 59daa5eeec25..876232d64126 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -554,47 +554,42 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 	return old;
 }
 
-pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
-		       pmd_t *pmdp)
+pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
+			  pmd_t *pmdp)
 {
 	pmd_t pmd;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	if (pmd_trans_huge(*pmdp)) {
-		pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
-	} else {
-		/*
-		 * khugepaged calls this for normal pmd
-		 */
-		pmd = *pmdp;
-		pmd_clear(pmdp);
-		/*
-		 * Wait for all pending hash_page to finish. This is needed
-		 * in case of subpage collapse. When we collapse normal pages
-		 * to hugepage, we first clear the pmd, then invalidate all
-		 * the PTE entries. The assumption here is that any low level
-		 * page fault will see a none pmd and take the slow path that
-		 * will wait on mmap_sem. But we could very well be in a
-		 * hash_page with local ptep pointer value. Such a hash page
-		 * can result in adding new HPTE entries for normal subpages.
-		 * That means we could be modifying the page content as we
-		 * copy them to a huge page. So wait for parallel hash_page
-		 * to finish before invalidating HPTE entries. We can do this
-		 * by sending an IPI to all the cpus and executing a dummy
-		 * function there.
-		 */
-		kick_all_cpus_sync();
-		/*
-		 * Now invalidate the hpte entries in the range
-		 * covered by pmd. This make sure we take a
-		 * fault and will find the pmd as none, which will
-		 * result in a major fault which takes mmap_sem and
-		 * hence wait for collapse to complete. Without this
-		 * the __collapse_huge_page_copy can result in copying
-		 * the old content.
-		 */
-		flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
-	}
+	VM_BUG_ON(pmd_trans_huge(*pmdp));
+
+	pmd = *pmdp;
+	pmd_clear(pmdp);
+	/*
+	 * Wait for all pending hash_page to finish. This is needed
+	 * in case of subpage collapse. When we collapse normal pages
+	 * to hugepage, we first clear the pmd, then invalidate all
+	 * the PTE entries. The assumption here is that any low level
+	 * page fault will see a none pmd and take the slow path that
+	 * will wait on mmap_sem. But we could very well be in a
+	 * hash_page with local ptep pointer value. Such a hash page
+	 * can result in adding new HPTE entries for normal subpages.
+	 * That means we could be modifying the page content as we
+	 * copy them to a huge page. So wait for parallel hash_page
+	 * to finish before invalidating HPTE entries. We can do this
+	 * by sending an IPI to all the cpus and executing a dummy
+	 * function there.
+	 */
+	kick_all_cpus_sync();
+	/*
+	 * Now invalidate the hpte entries in the range
+	 * covered by pmd. This make sure we take a
+	 * fault and will find the pmd as none, which will
+	 * result in a major fault which takes mmap_sem and
+	 * hence wait for collapse to complete. Without this
+	 * the __collapse_huge_page_copy can result in copying
+	 * the old content.
+	 */
+	flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
 	return pmd;
 }
 
@@ -817,8 +812,8 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return;
 }
 
-pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-			 unsigned long addr, pmd_t *pmdp)
+pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr, pmd_t *pmdp)
 {
 	pmd_t old_pmd;
 	pgtable_t pgtable;
@@ -839,6 +834,17 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	 * hash fault look at them.
 	 */
 	memset(pgtable, 0, PTE_FRAG_SIZE);
+	/*
+	 * Serialize against find_linux_pte_or_hugepte which does lock-less
+	 * lookup in page tables with local interrupts disabled. For huge pages
+	 * it casts pmd_t to pte_t. Since format of pte_t is different from
+	 * pmd_t we want to prevent transit from pmd pointing to page table
+	 * to pmd pointing to huge page (and back) while interrupts are disabled.
+	 * We clear pmd to possibly replace it with page table pointer in
+	 * different code paths. So make sure we wait for the parallel
+	 * find_linux_pte_or_hugepage to finish.
+	 */
+	kick_all_cpus_sync();
 	return old_pmd;
 }
 
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 89bf95bd63b1..765b419883f2 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -398,18 +398,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_SMT)
 	rldicl	r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
 	cmpdi	cr0,r14,0
-	bge	tlb_miss_fault_e6500	/* Bad pgd entry or hugepage; bail */
+	bge	tlb_miss_huge_e6500	/* Bad pgd entry or hugepage; bail */
 	ldx	r14,r14,r15		/* grab pud entry */
 
 	rldicl	r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
 	clrrdi	r15,r15,3
 	cmpdi	cr0,r14,0
-	bge	tlb_miss_fault_e6500
+	bge	tlb_miss_huge_e6500
 	ldx	r14,r14,r15		/* Grab pmd entry */
 
 	mfspr	r10,SPRN_MAS0
 	cmpdi	cr0,r14,0
-	bge	tlb_miss_fault_e6500
+	bge	tlb_miss_huge_e6500
 
 	/* Now we build the MAS for a 2M indirect page:
 	 *
@@ -428,6 +428,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_SMT)
 	clrrdi	r15,r16,21		/* make EA 2M-aligned */
 	mtspr	SPRN_MAS2,r15
 
+tlb_miss_huge_done_e6500:
 	lbz	r15,TCD_ESEL_NEXT(r11)
 	lbz	r16,TCD_ESEL_MAX(r11)
 	lbz	r14,TCD_ESEL_FIRST(r11)
@@ -456,6 +457,50 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
 	tlb_epilog_bolted
 	rfi
 
+tlb_miss_huge_e6500:
+	beq	tlb_miss_fault_e6500
+	li	r10,1
+	andi.	r15,r14,HUGEPD_SHIFT_MASK@l /* r15 = psize */
+	rldimi	r14,r10,63,0		/* Set PD_HUGE */
+	xor	r14,r14,r15		/* Clear size bits */
+	ldx	r14,0,r14
+
+	/*
+	 * Now we build the MAS for a huge page.
+	 *
+	 * MAS 0   :	ESEL needs to be filled by software round-robin
+	 *		 - can be handled by indirect code
+	 * MAS 1   :	Need to clear IND and set TSIZE
+	 * MAS 2,3+7:	Needs to be redone similar to non-tablewalk handler
+	 */
+
+	subi	r15,r15,10		/* Convert psize to tsize */
+	mfspr	r10,SPRN_MAS1
+	rlwinm	r10,r10,0,~MAS1_IND
+	rlwimi	r10,r15,MAS1_TSIZE_SHIFT,MAS1_TSIZE_MASK
+	mtspr	SPRN_MAS1,r10
+
+	li	r10,-0x400
+	sld	r15,r10,r15		/* Generate mask based on size */
+	and	r10,r16,r15
+	rldicr	r15,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
+	rlwimi	r10,r14,32-19,27,31	/* Insert WIMGE */
+	clrldi	r15,r15,PAGE_SHIFT	/* Clear crap at the top */
+	rlwimi	r15,r14,32-8,22,25	/* Move in U bits */
+	mtspr	SPRN_MAS2,r10
+	andi.	r10,r14,_PAGE_DIRTY
+	rlwimi	r15,r14,32-2,26,31	/* Move in BAP bits */
+
+	/* Mask out SW and UW if !DIRTY (XXX optimize this !) */
+	bne	1f
+	li	r10,MAS3_SW|MAS3_UW
+	andc	r15,r15,r10
+1:
+	mtspr	SPRN_MAS7_MAS3,r15
+
+	mfspr	r10,SPRN_MAS0
+	b	tlb_miss_huge_done_e6500
+
 tlb_miss_kernel_e6500:
 	ld	r14,PACA_KERNELPGD(r13)
 	cmpldi	cr1,r15,8		/* Check for vmalloc region */
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index cbd3d069897f..723a099f6be3 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -217,7 +217,7 @@ static DEFINE_RAW_SPINLOCK(tlbivax_lock);
 static int mm_is_core_local(struct mm_struct *mm)
 {
 	return cpumask_subset(mm_cpumask(mm),
-			      topology_thread_cpumask(smp_processor_id()));
+			      topology_sibling_cpumask(smp_processor_id()));
 }
 
 struct tlb_flush_param {
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 12b638425bb9..d90893b76e7c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -131,7 +131,16 @@ static void pmao_restore_workaround(bool ebb) { }
 
 static bool regs_use_siar(struct pt_regs *regs)
 {
-	return !!regs->result;
+	/*
+	 * When we take a performance monitor exception the regs are setup
+	 * using perf_read_regs() which overloads some fields, in particular
+	 * regs->result to tell us whether to use SIAR.
+	 *
+	 * However if the regs are from another exception, eg. a syscall, then
+	 * they have not been setup using perf_read_regs() and so regs->result
+	 * is something random.
+	 */
+	return ((TRAP(regs) == 0xf00) && regs->result);
 }
 
 /*
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index c949ca055712..63016621aff8 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -193,7 +193,7 @@ static struct irq_chip mpc52xx_gpt_irq_chip = {
 
 void mpc52xx_gpt_irq_cascade(unsigned int virq, struct irq_desc *desc)
 {
-	struct mpc52xx_gpt_priv *gpt = irq_get_handler_data(virq);
+	struct mpc52xx_gpt_priv *gpt = irq_desc_get_handler_data(desc);
 	int sub_virq;
 	u32 status;
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
index e2d401ad8fbb..6eb3b2abae90 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c
@@ -12,7 +12,7 @@
 
 #undef DEBUG
 
-#include <asm/pci.h>
+#include <linux/pci.h>
 #include <asm/mpc52xx.h>
 #include <asm/delay.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 2fb4b24368a6..97915feffd42 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -282,7 +282,7 @@ config CORENET_GENERIC
 	  For 64bit kernel, the following boards are supported:
 	    T208x QDS/RDB, T4240 QDS/RDB and B4 QDS
 	  The following boards are supported for both 32bit and 64bit kernel:
-	    P5020 DS, P5040 DS and T104xQDS/RDB
+	    P5020 DS, P5040 DS, T102x QDS/RDB, T104x QDS/RDB
 
 endif # FSL_SOC_BOOKE
 
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 9824d2cf79bd..bd839dc287fe 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -150,6 +150,9 @@ static const char * const boards[] __initconst = {
 	"fsl,B4860QDS",
 	"fsl,B4420QDS",
 	"fsl,B4220QDS",
+	"fsl,T1023RDB",
+	"fsl,T1024QDS",
+	"fsl,T1024RDB",
 	"fsl,T1040QDS",
 	"fsl,T1042QDS",
 	"fsl,T1040RDB",
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 8631ac5f0e57..b8b821697910 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -345,6 +345,7 @@ void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary)
 	local_irq_disable();
 
 	if (secondary) {
+		__flush_disable_L1();
 		atomic_inc(&kexec_down_cpus);
 		/* loop forever */
 		while (1);
@@ -357,61 +358,11 @@ static void mpc85xx_smp_kexec_down(void *arg)
 		ppc_md.kexec_cpu_down(0,1);
 }
 
-static void map_and_flush(unsigned long paddr)
-{
-	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
-	unsigned long kaddr  = (unsigned long)kmap_atomic(page);
-
-	flush_dcache_range(kaddr, kaddr + PAGE_SIZE);
-	kunmap_atomic((void *)kaddr);
-}
-
-/**
- * Before we reset the other cores, we need to flush relevant cache
- * out to memory so we don't get anything corrupted, some of these flushes
- * are performed out of an overabundance of caution as interrupts are not
- * disabled yet and we can switch cores
- */
-static void mpc85xx_smp_flush_dcache_kexec(struct kimage *image)
-{
-	kimage_entry_t *ptr, entry;
-	unsigned long paddr;
-	int i;
-
-	if (image->type == KEXEC_TYPE_DEFAULT) {
-		/* normal kexec images are stored in temporary pages */
-		for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
-		     ptr = (entry & IND_INDIRECTION) ?
-				phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
-			if (!(entry & IND_DESTINATION)) {
-				map_and_flush(entry);
-			}
-		}
-		/* flush out last IND_DONE page */
-		map_and_flush(entry);
-	} else {
-		/* crash type kexec images are copied to the crash region */
-		for (i = 0; i < image->nr_segments; i++) {
-			struct kexec_segment *seg = &image->segment[i];
-			for (paddr = seg->mem; paddr < seg->mem + seg->memsz;
-			     paddr += PAGE_SIZE) {
-				map_and_flush(paddr);
-			}
-		}
-	}
-
-	/* also flush the kimage struct to be passed in as well */
-	flush_dcache_range((unsigned long)image,
-			   (unsigned long)image + sizeof(*image));
-}
-
 static void mpc85xx_smp_machine_kexec(struct kimage *image)
 {
 	int timeout = INT_MAX;
 	int i, num_cpus = num_present_cpus();
 
-	mpc85xx_smp_flush_dcache_kexec(image);
-
 	if (image->type == KEXEC_TYPE_DEFAULT)
 		smp_call_function(mpc85xx_smp_kexec_down, NULL, 0);
 
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 1eadb6d0dc64..30e002f4648c 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -79,7 +79,7 @@ static void __init twr_p1025_setup_arch(void)
 	mpc85xx_qe_init();
 	mpc85xx_qe_par_io_init();
 
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE)
+#if IS_ENABLED(CONFIG_UCC_GETH) || IS_ENABLED(CONFIG_SERIAL_QE)
 	if (machine_is(twr_p1025)) {
 		struct ccsr_guts __iomem *guts;
 
@@ -101,7 +101,7 @@ static void __init twr_p1025_setup_arch(void)
 					MPC85xx_PMUXCR_QE(12));
 			iounmap(guts);
 
-#if defined(CONFIG_SERIAL_QE)
+#if IS_ENABLED(CONFIG_SERIAL_QE)
 			/* On P1025TWR board, the UCC7 acted as UART port.
 			 * However, The UCC7's CTS pin is low level in default,
 			 * it will impact the transmission in full duplex
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7264e91190be..c140e94c7c72 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -405,6 +405,16 @@ config PPC_DOORBELL
 
 endmenu
 
+config VDSO32
+	def_bool y
+	depends on PPC32 || CPU_BIG_ENDIAN
+	help
+	  This symbol controls whether we build the 32-bit VDSO. We obviously
+	  want to do that if we're building a 32-bit kernel. If we're building
+	  a 64-bit kernel then we only want a 32-bit VDSO if we're building for
+	  big endian. That is because the only little endian configuration we
+	  support is ppc64le which is 64-bit only.
+
 choice
 	prompt "Endianness selection"
 	default CPU_BIG_ENDIAN
@@ -421,6 +431,7 @@ config CPU_BIG_ENDIAN
 
 config CPU_LITTLE_ENDIAN
 	bool "Build little endian kernel"
+	depends on PPC_BOOK3S_64
 	select PPC64_BOOT_WRAPPER
 	help
 	  Build a little endian kernel.
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 623bd961465a..fe51de4fcf13 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -22,6 +22,7 @@
 #include <asm/machdep.h>
 #include <asm/prom.h>
 
+#include "cell.h"
 
 /*
  * MSIC registers, specified as offsets from dcr_base
@@ -95,7 +96,7 @@ static void msic_dcr_write(struct axon_msic *msic, unsigned int dcr_n, u32 val)
 static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct axon_msic *msic = irq_get_handler_data(irq);
+	struct axon_msic *msic = irq_desc_get_handler_data(desc);
 	u32 write_offset, msi;
 	int idx;
 	int retry = 0;
@@ -406,8 +407,8 @@ static int axon_msi_probe(struct platform_device *device)
 
 	dev_set_drvdata(&device->dev, msic);
 
-	ppc_md.setup_msi_irqs = axon_msi_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
+	cell_pci_controller_ops.setup_msi_irqs = axon_msi_setup_msi_irqs;
+	cell_pci_controller_ops.teardown_msi_irqs = axon_msi_teardown_msi_irqs;
 
 	axon_msi_debug_setup(dn, msic);
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 21b502398bf3..14a582b21274 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -466,6 +466,11 @@ static inline u32 cell_iommu_get_ioid(struct device_node *np)
 	return *ioid;
 }
 
+static struct iommu_table_ops cell_iommu_ops = {
+	.set = tce_build_cell,
+	.clear = tce_free_cell
+};
+
 static struct iommu_window * __init
 cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 			unsigned long offset, unsigned long size,
@@ -492,6 +497,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->table.it_offset =
 		(offset >> window->table.it_page_shift) + pte_offset;
 	window->table.it_size = size >> window->table.it_page_shift;
+	window->table.it_ops = &cell_iommu_ops;
 
 	iommu_init_table(&window->table, iommu->nid);
 
@@ -1201,8 +1207,6 @@ static int __init cell_iommu_init(void)
 	/* Setup various callbacks */
 	cell_pci_controller_ops.dma_dev_setup = cell_pci_dma_dev_setup;
 	ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
-	ppc_md.tce_build = tce_build_cell;
-	ppc_md.tce_free = tce_free_cell;
 
 	if (!iommu_fixed_disabled && cell_iommu_fixed_mapping_init() == 0)
 		goto bail;
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index c269caee58f9..9dd154d6f89a 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -124,7 +124,7 @@ static void hlwd_pic_irq_cascade(unsigned int cascade_virq,
 				      struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irq_domain *irq_domain = irq_get_handler_data(cascade_virq);
+	struct irq_domain *irq_domain = irq_desc_get_handler_data(desc);
 	unsigned int virq;
 
 	raw_spin_lock(&desc->lock);
diff --git a/arch/powerpc/platforms/pasemi/Makefile b/arch/powerpc/platforms/pasemi/Makefile
index 8e8d4cae5ebe..60b4e0fd9808 100644
--- a/arch/powerpc/platforms/pasemi/Makefile
+++ b/arch/powerpc/platforms/pasemi/Makefile
@@ -1,2 +1,3 @@
 obj-y	+= setup.o pci.o time.o idle.o powersave.o iommu.o dma_lib.o misc.o
 obj-$(CONFIG_PPC_PASEMI_MDIO)	+= gpio_mdio.o
+obj-$(CONFIG_PCI_MSI)		+= msi.o
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index b8f567b2ea19..c929644e74a6 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -134,6 +134,10 @@ static void iobmap_free(struct iommu_table *tbl, long index,
 	}
 }
 
+static struct iommu_table_ops iommu_table_iobmap_ops = {
+	.set = iobmap_build,
+	.clear  = iobmap_free
+};
 
 static void iommu_table_iobmap_setup(void)
 {
@@ -153,6 +157,7 @@ static void iommu_table_iobmap_setup(void)
 	 * Should probably be 8 (64 bytes)
 	 */
 	iommu_table_iobmap.it_blocksize = 4;
+	iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops;
 	iommu_init_table(&iommu_table_iobmap, 0);
 	pr_debug(" <- %s\n", __func__);
 }
@@ -252,8 +257,6 @@ void __init iommu_init_early_pasemi(void)
 
 	pasemi_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pasemi;
 	pasemi_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pasemi;
-	ppc_md.tce_build = iobmap_build;
-	ppc_md.tce_free  = iobmap_free;
 	set_pci_dma_ops(&dma_iommu_ops);
 }
 
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/platforms/pasemi/msi.c
index a3f660eed6de..27f2b187a91b 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -13,8 +13,6 @@
  *
  */
 
-#undef DEBUG
-
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <asm/mpic.h>
@@ -23,7 +21,7 @@
 #include <asm/ppc-pci.h>
 #include <asm/msi_bitmap.h>
 
-#include "mpic.h"
+#include <sysdev/mpic.h>
 
 /* Allocate 16 interrupts per device, to give an alignment of 16,
  * since that's the size of the grouping w.r.t. affinity. If someone
@@ -144,6 +142,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 int mpic_pasemi_msi_init(struct mpic *mpic)
 {
 	int rc;
+	struct pci_controller *phb;
 
 	if (!mpic->irqhost->of_node ||
 	    !of_device_is_compatible(mpic->irqhost->of_node,
@@ -159,9 +158,11 @@ int mpic_pasemi_msi_init(struct mpic *mpic)
 	pr_debug("pasemi_msi: Registering PA Semi MPIC MSI callbacks\n");
 
 	msi_mpic = mpic;
-	WARN_ON(ppc_md.setup_msi_irqs);
-	ppc_md.setup_msi_irqs = pasemi_msi_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = pasemi_msi_teardown_msi_irqs;
+	list_for_each_entry(phb, &hose_list, list_node) {
+		WARN_ON(phb->controller_ops.setup_msi_irqs);
+		phb->controller_ops.setup_msi_irqs = pasemi_msi_setup_msi_irqs;
+		phb->controller_ops.teardown_msi_irqs = pasemi_msi_teardown_msi_irqs;
+	}
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 4b044d8cb49a..604190cab522 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -19,3 +19,10 @@ config PPC_POWERNV
 	select CPU_FREQ_GOV_CONSERVATIVE
 	select PPC_DOORBELL
 	default y
+
+config OPAL_PRD
+	tristate 'OPAL PRD driver'
+	depends on PPC_POWERNV
+	help
+	  This enables the opal-prd driver, a facility to run processor
+	  recovery diagnostics on OpenPower machines
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 33e44f37212f..1c8cdb6250e7 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,7 +1,7 @@
-obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
 obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
-obj-y			+= opal-msglog.o opal-hmi.o opal-power.o
+obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
@@ -9,3 +9,4 @@ obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
+obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index ce738ab3d5a9..5cf5e6ea213b 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/msi.h>
 #include <linux/of.h>
@@ -40,6 +41,7 @@
 #include "pci.h"
 
 static bool pnv_eeh_nb_init = false;
+static int eeh_event_irq = -EINVAL;
 
 /**
  * pnv_eeh_init - EEH platform dependent initialization
@@ -88,34 +90,22 @@ static int pnv_eeh_init(void)
 	return 0;
 }
 
-static int pnv_eeh_event(struct notifier_block *nb,
-			 unsigned long events, void *change)
+static irqreturn_t pnv_eeh_event(int irq, void *data)
 {
-	uint64_t changed_evts = (uint64_t)change;
-
 	/*
-	 * We simply send special EEH event if EEH has
-	 * been enabled, or clear pending events in
-	 * case that we enable EEH soon
+	 * We simply send a special EEH event if EEH has been
+	 * enabled. We don't care about EEH events until we've
+	 * finished processing the outstanding ones. Event processing
+	 * gets unmasked in next_error() if EEH is enabled.
 	 */
-	if (!(changed_evts & OPAL_EVENT_PCI_ERROR) ||
-	    !(events & OPAL_EVENT_PCI_ERROR))
-		return 0;
+	disable_irq_nosync(irq);
 
 	if (eeh_enabled())
 		eeh_send_failure_event(NULL);
-	else
-		opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
-	return 0;
+	return IRQ_HANDLED;
 }
 
-static struct notifier_block pnv_eeh_nb = {
-	.notifier_call	= pnv_eeh_event,
-	.next		= NULL,
-	.priority	= 0
-};
-
 #ifdef CONFIG_DEBUG_FS
 static ssize_t pnv_eeh_ei_write(struct file *filp,
 				const char __user *user_buf,
@@ -237,16 +227,28 @@ static int pnv_eeh_post_init(void)
 
 	/* Register OPAL event notifier */
 	if (!pnv_eeh_nb_init) {
-		ret = opal_notifier_register(&pnv_eeh_nb);
-		if (ret) {
-			pr_warn("%s: Can't register OPAL event notifier (%d)\n",
-				__func__, ret);
+		eeh_event_irq = opal_event_request(ilog2(OPAL_EVENT_PCI_ERROR));
+		if (eeh_event_irq < 0) {
+			pr_err("%s: Can't register OPAL event interrupt (%d)\n",
+			       __func__, eeh_event_irq);
+			return eeh_event_irq;
+		}
+
+		ret = request_irq(eeh_event_irq, pnv_eeh_event,
+				IRQ_TYPE_LEVEL_HIGH, "opal-eeh", NULL);
+		if (ret < 0) {
+			irq_dispose_mapping(eeh_event_irq);
+			pr_err("%s: Can't request OPAL event interrupt (%d)\n",
+			       __func__, eeh_event_irq);
 			return ret;
 		}
 
 		pnv_eeh_nb_init = true;
 	}
 
+	if (!eeh_enabled())
+		disable_irq(eeh_event_irq);
+
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 
@@ -979,7 +981,7 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 /**
  * pnv_eeh_wait_state - Wait for PE state
  * @pe: EEH PE
- * @max_wait: maximal period in microsecond
+ * @max_wait: maximal period in millisecond
  *
  * Wait for the state of associated PE. It might take some time
  * to retrieve the PE's state.
@@ -1000,13 +1002,13 @@ static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
 		if (ret != EEH_STATE_UNAVAILABLE)
 			return ret;
 
-		max_wait -= mwait;
 		if (max_wait <= 0) {
 			pr_warn("%s: Timeout getting PE#%x's state (%d)\n",
 				__func__, pe->addr, max_wait);
 			return EEH_STATE_NOT_SUPPORT;
 		}
 
+		max_wait -= mwait;
 		msleep(mwait);
 	}
 
@@ -1303,12 +1305,10 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	int state, ret = EEH_NEXT_ERR_NONE;
 
 	/*
-	 * While running here, it's safe to purge the event queue.
-	 * And we should keep the cached OPAL notifier event sychronized
-	 * between the kernel and firmware.
+	 * While running here, it's safe to purge the event queue. The
+	 * event should still be masked.
 	 */
 	eeh_remove_event(NULL, false);
-	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
 	list_for_each_entry(hose, &hose_list, list_node) {
 		/*
@@ -1477,6 +1477,10 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 			break;
 	}
 
+	/* Unmask the event */
+	if (eeh_enabled())
+		enable_irq(eeh_event_irq);
+
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
new file mode 100644
index 000000000000..59d735d2e5c0
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -0,0 +1,293 @@
+/*
+ * PowerNV cpuidle code
+ *
+ * Copyright 2015 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/cpu.h>
+
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+#include <asm/opal.h>
+#include <asm/cputhreads.h>
+#include <asm/cpuidle.h>
+#include <asm/code-patching.h>
+#include <asm/smp.h>
+
+#include "powernv.h"
+#include "subcore.h"
+
+static u32 supported_cpuidle_states;
+
+int pnv_save_sprs_for_winkle(void)
+{
+	int cpu;
+	int rc;
+
+	/*
+	 * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
+	 * all cpus at boot. Get these reg values of current cpu and use the
+	 * same accross all cpus.
+	 */
+	uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+	uint64_t hid0_val = mfspr(SPRN_HID0);
+	uint64_t hid1_val = mfspr(SPRN_HID1);
+	uint64_t hid4_val = mfspr(SPRN_HID4);
+	uint64_t hid5_val = mfspr(SPRN_HID5);
+	uint64_t hmeer_val = mfspr(SPRN_HMEER);
+
+	for_each_possible_cpu(cpu) {
+		uint64_t pir = get_hard_smp_processor_id(cpu);
+		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
+
+		/*
+		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
+		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
+		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
+		 * can use this bit to distinguish between fastsleep and
+		 * deep winkle.
+		 */
+		hsprg0_val |= 1;
+
+		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
+		if (rc != 0)
+			return rc;
+
+		rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+		if (rc != 0)
+			return rc;
+
+		/* HIDs are per core registers */
+		if (cpu_thread_in_core(cpu) == 0) {
+
+			rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
+			if (rc != 0)
+				return rc;
+
+			rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
+			if (rc != 0)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
+static void pnv_alloc_idle_core_states(void)
+{
+	int i, j;
+	int nr_cores = cpu_nr_cores();
+	u32 *core_idle_state;
+
+	/*
+	 * core_idle_state - First 8 bits track the idle state of each thread
+	 * of the core. The 8th bit is the lock bit. Initially all thread bits
+	 * are set. They are cleared when the thread enters deep idle state
+	 * like sleep and winkle. Initially the lock bit is cleared.
+	 * The lock bit has 2 purposes
+	 * a. While the first thread is restoring core state, it prevents
+	 * other threads in the core from switching to process context.
+	 * b. While the last thread in the core is saving the core state, it
+	 * prevents a different thread from waking up.
+	 */
+	for (i = 0; i < nr_cores; i++) {
+		int first_cpu = i * threads_per_core;
+		int node = cpu_to_node(first_cpu);
+
+		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
+		*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
+
+		for (j = 0; j < threads_per_core; j++) {
+			int cpu = first_cpu + j;
+
+			paca[cpu].core_idle_state_ptr = core_idle_state;
+			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
+			paca[cpu].thread_mask = 1 << j;
+		}
+	}
+
+	update_subcore_sibling_mask();
+
+	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
+		pnv_save_sprs_for_winkle();
+}
+
+u32 pnv_get_supported_cpuidle_states(void)
+{
+	return supported_cpuidle_states;
+}
+EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
+
+
+static void pnv_fastsleep_workaround_apply(void *info)
+
+{
+	int rc;
+	int *err = info;
+
+	rc = opal_config_cpu_idle_state(OPAL_CONFIG_IDLE_FASTSLEEP,
+					OPAL_CONFIG_IDLE_APPLY);
+	if (rc)
+		*err = 1;
+}
+
+/*
+ * Used to store fastsleep workaround state
+ * 0 - Workaround applied/undone at fastsleep entry/exit path (Default)
+ * 1 - Workaround applied once, never undone.
+ */
+static u8 fastsleep_workaround_applyonce;
+
+static ssize_t show_fastsleep_workaround_applyonce(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", fastsleep_workaround_applyonce);
+}
+
+static ssize_t store_fastsleep_workaround_applyonce(struct device *dev,
+		struct device_attribute *attr, const char *buf,
+		size_t count)
+{
+	cpumask_t primary_thread_mask;
+	int err;
+	u8 val;
+
+	if (kstrtou8(buf, 0, &val) || val != 1)
+		return -EINVAL;
+
+	if (fastsleep_workaround_applyonce == 1)
+		return count;
+
+	/*
+	 * fastsleep_workaround_applyonce = 1 implies
+	 * fastsleep workaround needs to be left in 'applied' state on all
+	 * the cores. Do this by-
+	 * 1. Patching out the call to 'undo' workaround in fastsleep exit path
+	 * 2. Sending ipi to all the cores which have atleast one online thread
+	 * 3. Patching out the call to 'apply' workaround in fastsleep entry
+	 * path
+	 * There is no need to send ipi to cores which have all threads
+	 * offlined, as last thread of the core entering fastsleep or deeper
+	 * state would have applied workaround.
+	 */
+	err = patch_instruction(
+		(unsigned int *)pnv_fastsleep_workaround_at_exit,
+		PPC_INST_NOP);
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_exit");
+		goto fail;
+	}
+
+	get_online_cpus();
+	primary_thread_mask = cpu_online_cores_map();
+	on_each_cpu_mask(&primary_thread_mask,
+				pnv_fastsleep_workaround_apply,
+				&err, 1);
+	put_online_cpus();
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while running pnv_fastsleep_workaround_apply");
+		goto fail;
+	}
+
+	err = patch_instruction(
+		(unsigned int *)pnv_fastsleep_workaround_at_entry,
+		PPC_INST_NOP);
+	if (err) {
+		pr_err("fastsleep_workaround_applyonce change failed while patching pnv_fastsleep_workaround_at_entry");
+		goto fail;
+	}
+
+	fastsleep_workaround_applyonce = 1;
+
+	return count;
+fail:
+	return -EIO;
+}
+
+static DEVICE_ATTR(fastsleep_workaround_applyonce, 0600,
+			show_fastsleep_workaround_applyonce,
+			store_fastsleep_workaround_applyonce);
+
+static int __init pnv_init_idle_states(void)
+{
+	struct device_node *power_mgt;
+	int dt_idle_states;
+	u32 *flags;
+	int i;
+
+	supported_cpuidle_states = 0;
+
+	if (cpuidle_disable != IDLE_NO_OVERRIDE)
+		goto out;
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3))
+		goto out;
+
+	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
+	if (!power_mgt) {
+		pr_warn("opal: PowerMgmt Node not found\n");
+		goto out;
+	}
+	dt_idle_states = of_property_count_u32_elems(power_mgt,
+			"ibm,cpu-idle-state-flags");
+	if (dt_idle_states < 0) {
+		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
+		goto out;
+	}
+
+	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
+	if (of_property_read_u32_array(power_mgt,
+			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
+		goto out_free;
+	}
+
+	for (i = 0; i < dt_idle_states; i++)
+		supported_cpuidle_states |= flags[i];
+
+	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_entry,
+			PPC_INST_NOP);
+		patch_instruction(
+			(unsigned int *)pnv_fastsleep_workaround_at_exit,
+			PPC_INST_NOP);
+	} else {
+		/*
+		 * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that
+		 * workaround is needed to use fastsleep. Provide sysfs
+		 * control to choose how this workaround has to be applied.
+		 */
+		device_create_file(cpu_subsys.dev_root,
+				&dev_attr_fastsleep_workaround_applyonce);
+	}
+
+	pnv_alloc_idle_core_states();
+out_free:
+	kfree(flags);
+out:
+	return 0;
+}
+machine_subsys_initcall(powernv, pnv_init_idle_states);
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index 693b6cdac691..bdc8c0c71d15 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -151,7 +151,7 @@ static struct notifier_block opal_async_comp_nb = {
 		.priority	= 0,
 };
 
-static int __init opal_async_comp_init(void)
+int __init opal_async_comp_init(void)
 {
 	struct device_node *opal_node;
 	const __be32 *async;
@@ -205,4 +205,3 @@ out_opal_node:
 out:
 	return err;
 }
-machine_subsys_initcall(powernv, opal_async_comp_init);
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 5aa9c1ce4de3..2ee96431f736 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -15,6 +15,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/delay.h>
+#include <linux/interrupt.h>
 
 #include <asm/opal.h>
 
@@ -60,7 +61,7 @@ static ssize_t dump_type_show(struct dump_obj *dump_obj,
 			      struct dump_attribute *attr,
 			      char *buf)
 {
-	
+
 	return sprintf(buf, "0x%x %s\n", dump_obj->type,
 		       dump_type_to_string(dump_obj->type));
 }
@@ -363,7 +364,7 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size,
 	return dump;
 }
 
-static int process_dump(void)
+static irqreturn_t process_dump(int irq, void *data)
 {
 	int rc;
 	uint32_t dump_id, dump_size, dump_type;
@@ -387,45 +388,13 @@ static int process_dump(void)
 	if (!dump)
 		return -1;
 
-	return 0;
-}
-
-static void dump_work_fn(struct work_struct *work)
-{
-	process_dump();
+	return IRQ_HANDLED;
 }
 
-static DECLARE_WORK(dump_work, dump_work_fn);
-
-static void schedule_process_dump(void)
-{
-	schedule_work(&dump_work);
-}
-
-/*
- * New dump available notification
- *
- * Once we get notification, we add sysfs entries for it.
- * We only fetch the dump on demand, and create sysfs asynchronously.
- */
-static int dump_event(struct notifier_block *nb,
-		      unsigned long events, void *change)
-{
-	if (events & OPAL_EVENT_DUMP_AVAIL)
-		schedule_process_dump();
-
-	return 0;
-}
-
-static struct notifier_block dump_nb = {
-	.notifier_call  = dump_event,
-	.next           = NULL,
-	.priority       = 0
-};
-
 void __init opal_platform_dump_init(void)
 {
 	int rc;
+	int dump_irq;
 
 	/* ELOG not supported by firmware */
 	if (!opal_check_token(OPAL_DUMP_READ))
@@ -445,10 +414,19 @@ void __init opal_platform_dump_init(void)
 		return;
 	}
 
-	rc = opal_notifier_register(&dump_nb);
+	dump_irq = opal_event_request(ilog2(OPAL_EVENT_DUMP_AVAIL));
+	if (!dump_irq) {
+		pr_err("%s: Can't register OPAL event irq (%d)\n",
+		       __func__, dump_irq);
+		return;
+	}
+
+	rc = request_threaded_irq(dump_irq, NULL, process_dump,
+				IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+				"opal-dump", NULL);
 	if (rc) {
-		pr_warn("%s: Can't register OPAL event notifier (%d)\n",
-			__func__, rc);
+		pr_err("%s: Can't request OPAL event irq (%d)\n",
+		       __func__, rc);
 		return;
 	}
 
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 38ce757e5e2a..4949ef0d9400 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -10,6 +10,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
@@ -276,24 +277,15 @@ static void elog_work_fn(struct work_struct *work)
 
 static DECLARE_WORK(elog_work, elog_work_fn);
 
-static int elog_event(struct notifier_block *nb,
-				unsigned long events, void *change)
+static irqreturn_t elog_event(int irq, void *data)
 {
-	/* check for error log event */
-	if (events & OPAL_EVENT_ERROR_LOG_AVAIL)
-		schedule_work(&elog_work);
-	return 0;
+	schedule_work(&elog_work);
+	return IRQ_HANDLED;
 }
 
-static struct notifier_block elog_nb = {
-	.notifier_call  = elog_event,
-	.next           = NULL,
-	.priority       = 0
-};
-
 int __init opal_elog_init(void)
 {
-	int rc = 0;
+	int rc = 0, irq;
 
 	/* ELOG not supported by firmware */
 	if (!opal_check_token(OPAL_ELOG_READ))
@@ -305,10 +297,18 @@ int __init opal_elog_init(void)
 		return -1;
 	}
 
-	rc = opal_notifier_register(&elog_nb);
+	irq = opal_event_request(ilog2(OPAL_EVENT_ERROR_LOG_AVAIL));
+	if (!irq) {
+		pr_err("%s: Can't register OPAL event irq (%d)\n",
+		       __func__, irq);
+		return irq;
+	}
+
+	rc = request_irq(irq, elog_event,
+			IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
 	if (rc) {
-		pr_err("%s: Can't register OPAL event notifier (%d)\n",
-		__func__, rc);
+		pr_err("%s: Can't request OPAL event irq (%d)\n",
+		       __func__, rc);
 		return rc;
 	}
 
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index b322bfb51343..a8f49d380449 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -170,7 +170,7 @@ static struct notifier_block opal_hmi_handler_nb = {
 	.priority	= 0,
 };
 
-static int __init opal_hmi_handler_init(void)
+int __init opal_hmi_handler_init(void)
 {
 	int ret;
 
@@ -186,4 +186,3 @@ static int __init opal_hmi_handler_init(void)
 	}
 	return 0;
 }
-machine_subsys_initcall(powernv, opal_hmi_handler_init);
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
new file mode 100644
index 000000000000..e2e7d75f52f3
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -0,0 +1,253 @@
+/*
+ * This file implements an irqchip for OPAL events. Whenever there is
+ * an interrupt that is handled by OPAL we get passed a list of events
+ * that Linux needs to do something about. These basically look like
+ * interrupts to Linux so we implement an irqchip to handle them.
+ *
+ * Copyright Alistair Popple, IBM Corporation 2014.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/irq_work.h>
+
+#include <asm/machdep.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+/* Maximum number of events supported by OPAL firmware */
+#define MAX_NUM_EVENTS 64
+
+struct opal_event_irqchip {
+	struct irq_chip irqchip;
+	struct irq_domain *domain;
+	unsigned long mask;
+};
+static struct opal_event_irqchip opal_event_irqchip;
+
+static unsigned int opal_irq_count;
+static unsigned int *opal_irqs;
+
+static void opal_handle_irq_work(struct irq_work *work);
+static __be64 last_outstanding_events;
+static struct irq_work opal_event_irq_work = {
+	.func = opal_handle_irq_work,
+};
+
+static void opal_event_mask(struct irq_data *d)
+{
+	clear_bit(d->hwirq, &opal_event_irqchip.mask);
+}
+
+static void opal_event_unmask(struct irq_data *d)
+{
+	set_bit(d->hwirq, &opal_event_irqchip.mask);
+
+	opal_poll_events(&last_outstanding_events);
+	if (last_outstanding_events & opal_event_irqchip.mask)
+		/* Need to retrigger the interrupt */
+		irq_work_queue(&opal_event_irq_work);
+}
+
+static int opal_event_set_type(struct irq_data *d, unsigned int flow_type)
+{
+	/*
+	 * For now we only support level triggered events. The irq
+	 * handler will be called continuously until the event has
+	 * been cleared in OPAL.
+	 */
+	if (flow_type != IRQ_TYPE_LEVEL_HIGH)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct opal_event_irqchip opal_event_irqchip = {
+	.irqchip = {
+		.name = "OPAL EVT",
+		.irq_mask = opal_event_mask,
+		.irq_unmask = opal_event_unmask,
+		.irq_set_type = opal_event_set_type,
+	},
+	.mask = 0,
+};
+
+static int opal_event_map(struct irq_domain *d, unsigned int irq,
+			irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, &opal_event_irqchip);
+	irq_set_chip_and_handler(irq, &opal_event_irqchip.irqchip,
+				handle_level_irq);
+
+	return 0;
+}
+
+void opal_handle_events(uint64_t events)
+{
+	int virq, hwirq = 0;
+	u64 mask = opal_event_irqchip.mask;
+
+	if (!in_irq() && (events & mask)) {
+		last_outstanding_events = events;
+		irq_work_queue(&opal_event_irq_work);
+		return;
+	}
+
+	while (events & mask) {
+		hwirq = fls64(events) - 1;
+		if (BIT_ULL(hwirq) & mask) {
+			virq = irq_find_mapping(opal_event_irqchip.domain,
+						hwirq);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+		events &= ~BIT_ULL(hwirq);
+	}
+}
+
+static irqreturn_t opal_interrupt(int irq, void *data)
+{
+	__be64 events;
+
+	opal_handle_interrupt(virq_to_hw(irq), &events);
+	opal_handle_events(be64_to_cpu(events));
+
+	return IRQ_HANDLED;
+}
+
+static void opal_handle_irq_work(struct irq_work *work)
+{
+	opal_handle_events(be64_to_cpu(last_outstanding_events));
+}
+
+static int opal_event_match(struct irq_domain *h, struct device_node *node)
+{
+	return h->of_node == node;
+}
+
+static int opal_event_xlate(struct irq_domain *h, struct device_node *np,
+			   const u32 *intspec, unsigned int intsize,
+			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
+{
+	*out_hwirq = intspec[0];
+	*out_flags = IRQ_TYPE_LEVEL_HIGH;
+
+	return 0;
+}
+
+static const struct irq_domain_ops opal_event_domain_ops = {
+	.match	= opal_event_match,
+	.map	= opal_event_map,
+	.xlate	= opal_event_xlate,
+};
+
+void opal_event_shutdown(void)
+{
+	unsigned int i;
+
+	/* First free interrupts, which will also mask them */
+	for (i = 0; i < opal_irq_count; i++) {
+		if (opal_irqs[i])
+			free_irq(opal_irqs[i], NULL);
+		opal_irqs[i] = 0;
+	}
+}
+
+int __init opal_event_init(void)
+{
+	struct device_node *dn, *opal_node;
+	const __be32 *irqs;
+	int i, irqlen, rc = 0;
+
+	opal_node = of_find_node_by_path("/ibm,opal");
+	if (!opal_node) {
+		pr_warn("opal: Node not found\n");
+		return -ENODEV;
+	}
+
+	/* If dn is NULL it means the domain won't be linked to a DT
+	 * node so therefore irq_of_parse_and_map(...) wont work. But
+	 * that shouldn't be problem because if we're running a
+	 * version of skiboot that doesn't have the dn then the
+	 * devices won't have the correct properties and will have to
+	 * fall back to the legacy method (opal_event_request(...))
+	 * anyway. */
+	dn = of_find_compatible_node(NULL, NULL, "ibm,opal-event");
+	opal_event_irqchip.domain = irq_domain_add_linear(dn, MAX_NUM_EVENTS,
+				&opal_event_domain_ops, &opal_event_irqchip);
+	of_node_put(dn);
+	if (!opal_event_irqchip.domain) {
+		pr_warn("opal: Unable to create irq domain\n");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Get interrupt property */
+	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+	opal_irq_count = irqs ? (irqlen / 4) : 0;
+	pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count);
+
+	/* Install interrupt handlers */
+	opal_irqs = kcalloc(opal_irq_count, sizeof(*opal_irqs), GFP_KERNEL);
+	for (i = 0; irqs && i < opal_irq_count; i++, irqs++) {
+		unsigned int irq, virq;
+
+		/* Get hardware and virtual IRQ */
+		irq = be32_to_cpup(irqs);
+		virq = irq_create_mapping(NULL, irq);
+		if (virq == NO_IRQ) {
+			pr_warn("Failed to map irq 0x%x\n", irq);
+			continue;
+		}
+
+		/* Install interrupt handler */
+		rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+		if (rc) {
+			irq_dispose_mapping(virq);
+			pr_warn("Error %d requesting irq %d (0x%x)\n",
+				 rc, virq, irq);
+			continue;
+		}
+
+		/* Cache IRQ */
+		opal_irqs[i] = virq;
+	}
+
+out:
+	of_node_put(opal_node);
+	return rc;
+}
+machine_arch_initcall(powernv, opal_event_init);
+
+/**
+ * opal_event_request(unsigned int opal_event_nr) - Request an event
+ * @opal_event_nr: the opal event number to request
+ *
+ * This routine can be used to find the linux virq number which can
+ * then be passed to request_irq to assign a handler for a particular
+ * opal event. This should only be used by legacy devices which don't
+ * have proper device tree bindings. Most devices should use
+ * irq_of_parse_and_map() instead.
+ */
+int opal_event_request(unsigned int opal_event_nr)
+{
+	if (WARN_ON_ONCE(!opal_event_irqchip.domain))
+		return NO_IRQ;
+
+	return irq_create_mapping(opal_event_irqchip.domain, opal_event_nr);
+}
+EXPORT_SYMBOL(opal_event_request);
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index 43db2136dbff..00a29432be39 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -144,4 +144,4 @@ static int __init opal_mem_err_init(void)
 	}
 	return 0;
 }
-machine_subsys_initcall(powernv, opal_mem_err_init);
+machine_device_initcall(powernv, opal_mem_err_init);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
new file mode 100644
index 000000000000..46cb3feb0a13
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -0,0 +1,449 @@
+/*
+ * OPAL Runtime Diagnostics interface driver
+ * Supported on POWERNV platform
+ *
+ * Copyright IBM Corporation 2015
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) "opal-prd: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/poll.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/opal-prd.h>
+#include <asm/opal.h>
+#include <asm/io.h>
+#include <asm/uaccess.h>
+
+
+/**
+ * The msg member must be at the end of the struct, as it's followed by the
+ * message data.
+ */
+struct opal_prd_msg_queue_item {
+	struct list_head		list;
+	struct opal_prd_msg_header	msg;
+};
+
+static struct device_node *prd_node;
+static LIST_HEAD(opal_prd_msg_queue);
+static DEFINE_SPINLOCK(opal_prd_msg_queue_lock);
+static DECLARE_WAIT_QUEUE_HEAD(opal_prd_msg_wait);
+static atomic_t prd_usage;
+
+static bool opal_prd_range_is_valid(uint64_t addr, uint64_t size)
+{
+	struct device_node *parent, *node;
+	bool found;
+
+	if (addr + size < addr)
+		return false;
+
+	parent = of_find_node_by_path("/reserved-memory");
+	if (!parent)
+		return false;
+
+	found = false;
+
+	for_each_child_of_node(parent, node) {
+		uint64_t range_addr, range_size, range_end;
+		const __be32 *addrp;
+		const char *label;
+
+		addrp = of_get_address(node, 0, &range_size, NULL);
+
+		range_addr = of_read_number(addrp, 2);
+		range_end = range_addr + range_size;
+
+		label = of_get_property(node, "ibm,prd-label", NULL);
+
+		/* PRD ranges need a label */
+		if (!label)
+			continue;
+
+		if (range_end <= range_addr)
+			continue;
+
+		if (addr >= range_addr && addr + size <= range_end) {
+			found = true;
+			of_node_put(node);
+			break;
+		}
+	}
+
+	of_node_put(parent);
+	return found;
+}
+
+static int opal_prd_open(struct inode *inode, struct file *file)
+{
+	/*
+	 * Prevent multiple (separate) processes from concurrent interactions
+	 * with the FW PRD channel
+	 */
+	if (atomic_xchg(&prd_usage, 1) == 1)
+		return -EBUSY;
+
+	return 0;
+}
+
+/*
+ * opal_prd_mmap - maps firmware-provided ranges into userspace
+ * @file: file structure for the device
+ * @vma: VMA to map the registers into
+ */
+
+static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	size_t addr, size;
+	int rc;
+
+	pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
+			vma->vm_start, vma->vm_end, vma->vm_pgoff,
+			vma->vm_flags);
+
+	addr = vma->vm_pgoff << PAGE_SHIFT;
+	size = vma->vm_end - vma->vm_start;
+
+	/* ensure we're mapping within one of the allowable ranges */
+	if (!opal_prd_range_is_valid(addr, size))
+		return -EINVAL;
+
+	vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
+						vma->vm_pgoff,
+						 size, vma->vm_page_prot))
+					| _PAGE_SPECIAL);
+
+	rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
+			vma->vm_page_prot);
+
+	return rc;
+}
+
+static bool opal_msg_queue_empty(void)
+{
+	unsigned long flags;
+	bool ret;
+
+	spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+	ret = list_empty(&opal_prd_msg_queue);
+	spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+	return ret;
+}
+
+static unsigned int opal_prd_poll(struct file *file,
+		struct poll_table_struct *wait)
+{
+	poll_wait(file, &opal_prd_msg_wait, wait);
+
+	if (!opal_msg_queue_empty())
+		return POLLIN | POLLRDNORM;
+
+	return 0;
+}
+
+static ssize_t opal_prd_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct opal_prd_msg_queue_item *item;
+	unsigned long flags;
+	ssize_t size, err;
+	int rc;
+
+	/* we need at least a header's worth of data */
+	if (count < sizeof(item->msg))
+		return -EINVAL;
+
+	if (*ppos)
+		return -ESPIPE;
+
+	item = NULL;
+
+	for (;;) {
+
+		spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+		if (!list_empty(&opal_prd_msg_queue)) {
+			item = list_first_entry(&opal_prd_msg_queue,
+					struct opal_prd_msg_queue_item, list);
+			list_del(&item->list);
+		}
+		spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+		if (item)
+			break;
+
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+
+		rc = wait_event_interruptible(opal_prd_msg_wait,
+				!opal_msg_queue_empty());
+		if (rc)
+			return -EINTR;
+	}
+
+	size = be16_to_cpu(item->msg.size);
+	if (size > count) {
+		err = -EINVAL;
+		goto err_requeue;
+	}
+
+	rc = copy_to_user(buf, &item->msg, size);
+	if (rc) {
+		err = -EFAULT;
+		goto err_requeue;
+	}
+
+	kfree(item);
+
+	return size;
+
+err_requeue:
+	/* eep! re-queue at the head of the list */
+	spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+	list_add(&item->list, &opal_prd_msg_queue);
+	spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+	return err;
+}
+
+static ssize_t opal_prd_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct opal_prd_msg_header hdr;
+	ssize_t size;
+	void *msg;
+	int rc;
+
+	size = sizeof(hdr);
+
+	if (count < size)
+		return -EINVAL;
+
+	/* grab the header */
+	rc = copy_from_user(&hdr, buf, sizeof(hdr));
+	if (rc)
+		return -EFAULT;
+
+	size = be16_to_cpu(hdr.size);
+
+	msg = kmalloc(size, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	rc = copy_from_user(msg, buf, size);
+	if (rc) {
+		size = -EFAULT;
+		goto out_free;
+	}
+
+	rc = opal_prd_msg(msg);
+	if (rc) {
+		pr_warn("write: opal_prd_msg returned %d\n", rc);
+		size = -EIO;
+	}
+
+out_free:
+	kfree(msg);
+
+	return size;
+}
+
+static int opal_prd_release(struct inode *inode, struct file *file)
+{
+	struct opal_prd_msg_header msg;
+
+	msg.size = cpu_to_be16(sizeof(msg));
+	msg.type = OPAL_PRD_MSG_TYPE_FINI;
+
+	opal_prd_msg((struct opal_prd_msg *)&msg);
+
+	atomic_xchg(&prd_usage, 0);
+
+	return 0;
+}
+
+static long opal_prd_ioctl(struct file *file, unsigned int cmd,
+		unsigned long param)
+{
+	struct opal_prd_info info;
+	struct opal_prd_scom scom;
+	int rc = 0;
+
+	switch (cmd) {
+	case OPAL_PRD_GET_INFO:
+		memset(&info, 0, sizeof(info));
+		info.version = OPAL_PRD_KERNEL_VERSION;
+		rc = copy_to_user((void __user *)param, &info, sizeof(info));
+		if (rc)
+			return -EFAULT;
+		break;
+
+	case OPAL_PRD_SCOM_READ:
+		rc = copy_from_user(&scom, (void __user *)param, sizeof(scom));
+		if (rc)
+			return -EFAULT;
+
+		scom.rc = opal_xscom_read(scom.chip, scom.addr,
+				(__be64 *)&scom.data);
+		scom.data = be64_to_cpu(scom.data);
+		pr_devel("ioctl SCOM_READ: chip %llx addr %016llx data %016llx rc %lld\n",
+				scom.chip, scom.addr, scom.data, scom.rc);
+
+		rc = copy_to_user((void __user *)param, &scom, sizeof(scom));
+		if (rc)
+			return -EFAULT;
+		break;
+
+	case OPAL_PRD_SCOM_WRITE:
+		rc = copy_from_user(&scom, (void __user *)param, sizeof(scom));
+		if (rc)
+			return -EFAULT;
+
+		scom.rc = opal_xscom_write(scom.chip, scom.addr, scom.data);
+		pr_devel("ioctl SCOM_WRITE: chip %llx addr %016llx data %016llx rc %lld\n",
+				scom.chip, scom.addr, scom.data, scom.rc);
+
+		rc = copy_to_user((void __user *)param, &scom, sizeof(scom));
+		if (rc)
+			return -EFAULT;
+		break;
+
+	default:
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static const struct file_operations opal_prd_fops = {
+	.open		= opal_prd_open,
+	.mmap		= opal_prd_mmap,
+	.poll		= opal_prd_poll,
+	.read		= opal_prd_read,
+	.write		= opal_prd_write,
+	.unlocked_ioctl	= opal_prd_ioctl,
+	.release	= opal_prd_release,
+	.owner		= THIS_MODULE,
+};
+
+static struct miscdevice opal_prd_dev = {
+	.minor		= MISC_DYNAMIC_MINOR,
+	.name		= "opal-prd",
+	.fops		= &opal_prd_fops,
+};
+
+/* opal interface */
+static int opal_prd_msg_notifier(struct notifier_block *nb,
+		unsigned long msg_type, void *_msg)
+{
+	struct opal_prd_msg_queue_item *item;
+	struct opal_prd_msg_header *hdr;
+	struct opal_msg *msg = _msg;
+	int msg_size, item_size;
+	unsigned long flags;
+
+	if (msg_type != OPAL_MSG_PRD)
+		return 0;
+
+	/* Calculate total size of the message and item we need to store. The
+	 * 'size' field in the header includes the header itself. */
+	hdr = (void *)msg->params;
+	msg_size = be16_to_cpu(hdr->size);
+	item_size = msg_size + sizeof(*item) - sizeof(item->msg);
+
+	item = kzalloc(item_size, GFP_ATOMIC);
+	if (!item)
+		return -ENOMEM;
+
+	memcpy(&item->msg, msg->params, msg_size);
+
+	spin_lock_irqsave(&opal_prd_msg_queue_lock, flags);
+	list_add_tail(&item->list, &opal_prd_msg_queue);
+	spin_unlock_irqrestore(&opal_prd_msg_queue_lock, flags);
+
+	wake_up_interruptible(&opal_prd_msg_wait);
+
+	return 0;
+}
+
+static struct notifier_block opal_prd_event_nb = {
+	.notifier_call	= opal_prd_msg_notifier,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int opal_prd_probe(struct platform_device *pdev)
+{
+	int rc;
+
+	if (!pdev || !pdev->dev.of_node)
+		return -ENODEV;
+
+	/* We should only have one prd driver instance per machine; ensure
+	 * that we only get a valid probe on a single OF node.
+	 */
+	if (prd_node)
+		return -EBUSY;
+
+	prd_node = pdev->dev.of_node;
+
+	rc = opal_message_notifier_register(OPAL_MSG_PRD, &opal_prd_event_nb);
+	if (rc) {
+		pr_err("Couldn't register event notifier\n");
+		return rc;
+	}
+
+	rc = misc_register(&opal_prd_dev);
+	if (rc) {
+		pr_err("failed to register miscdev\n");
+		opal_message_notifier_unregister(OPAL_MSG_PRD,
+				&opal_prd_event_nb);
+		return rc;
+	}
+
+	return 0;
+}
+
+static int opal_prd_remove(struct platform_device *pdev)
+{
+	misc_deregister(&opal_prd_dev);
+	opal_message_notifier_unregister(OPAL_MSG_PRD, &opal_prd_event_nb);
+	return 0;
+}
+
+static const struct of_device_id opal_prd_match[] = {
+	{ .compatible = "ibm,opal-prd" },
+	{ },
+};
+
+static struct platform_driver opal_prd_driver = {
+	.driver = {
+		.name		= "opal-prd",
+		.owner		= THIS_MODULE,
+		.of_match_table	= opal_prd_match,
+	},
+	.probe	= opal_prd_probe,
+	.remove	= opal_prd_remove,
+};
+
+module_platform_driver(opal_prd_driver);
+
+MODULE_DEVICE_TABLE(of, opal_prd_match);
+MODULE_DESCRIPTION("PowerNV OPAL runtime diagnostic driver");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 655250499d18..a06059df9239 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -77,7 +77,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(opal_get_sensor_data);
 
-static __init int opal_sensor_init(void)
+int __init opal_sensor_init(void)
 {
 	struct platform_device *pdev;
 	struct device_node *sensor;
@@ -93,4 +93,3 @@ static __init int opal_sensor_init(void)
 
 	return PTR_ERR_OR_ZERO(pdev);
 }
-machine_subsys_initcall(powernv, opal_sensor_init);
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 9d1acf22a099..afe66c576a38 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -55,8 +55,10 @@ static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 	}
 
 	ret = opal_get_param(token, param_id, (u64)buffer, length);
-	if (ret != OPAL_ASYNC_COMPLETION)
+	if (ret != OPAL_ASYNC_COMPLETION) {
+		ret = opal_error_code(ret);
 		goto out_token;
+	}
 
 	ret = opal_async_wait_response(token, &msg);
 	if (ret) {
@@ -65,7 +67,7 @@ static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 		goto out_token;
 	}
 
-	ret = be64_to_cpu(msg.params[1]);
+	ret = opal_error_code(be64_to_cpu(msg.params[1]));
 
 out_token:
 	opal_async_release_token(token);
@@ -89,8 +91,10 @@ static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
 
 	ret = opal_set_param(token, param_id, (u64)buffer, length);
 
-	if (ret != OPAL_ASYNC_COMPLETION)
+	if (ret != OPAL_ASYNC_COMPLETION) {
+		ret = opal_error_code(ret);
 		goto out_token;
+	}
 
 	ret = opal_async_wait_response(token, &msg);
 	if (ret) {
@@ -99,7 +103,7 @@ static int opal_set_sys_param(u32 param_id, u32 length, void *buffer)
 		goto out_token;
 	}
 
-	ret = be64_to_cpu(msg.params[1]);
+	ret = opal_error_code(be64_to_cpu(msg.params[1]));
 
 out_token:
 	opal_async_release_token(token);
@@ -162,10 +166,20 @@ void __init opal_sys_param_init(void)
 		goto out;
 	}
 
+	/* Some systems do not use sysparams; this is not an error */
+	sysparam = of_find_node_by_path("/ibm,opal/sysparams");
+	if (!sysparam)
+		goto out;
+
+	if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
+		pr_err("SYSPARAM: Opal sysparam node not compatible\n");
+		goto out_node_put;
+	}
+
 	sysparam_kobj = kobject_create_and_add("sysparams", opal_kobj);
 	if (!sysparam_kobj) {
 		pr_err("SYSPARAM: Failed to create sysparam kobject\n");
-		goto out;
+		goto out_node_put;
 	}
 
 	/* Allocate big enough buffer for any get/set transactions */
@@ -176,30 +190,19 @@ void __init opal_sys_param_init(void)
 		goto out_kobj_put;
 	}
 
-	sysparam = of_find_node_by_path("/ibm,opal/sysparams");
-	if (!sysparam) {
-		pr_err("SYSPARAM: Opal sysparam node not found\n");
-		goto out_param_buf;
-	}
-
-	if (!of_device_is_compatible(sysparam, "ibm,opal-sysparams")) {
-		pr_err("SYSPARAM: Opal sysparam node not compatible\n");
-		goto out_node_put;
-	}
-
 	/* Number of parameters exposed through DT */
 	count = of_property_count_strings(sysparam, "param-name");
 	if (count < 0) {
 		pr_err("SYSPARAM: No string found of property param-name in "
 				"the node %s\n", sysparam->name);
-		goto out_node_put;
+		goto out_param_buf;
 	}
 
 	id = kzalloc(sizeof(*id) * count, GFP_KERNEL);
 	if (!id) {
 		pr_err("SYSPARAM: Failed to allocate memory to read parameter "
 				"id\n");
-		goto out_node_put;
+		goto out_param_buf;
 	}
 
 	size = kzalloc(sizeof(*size) * count, GFP_KERNEL);
@@ -293,12 +296,12 @@ out_free_size:
 	kfree(size);
 out_free_id:
 	kfree(id);
-out_node_put:
-	of_node_put(sysparam);
 out_param_buf:
 	kfree(param_data_buf);
 out_kobj_put:
 	kobject_put(sysparam_kobj);
+out_node_put:
+	of_node_put(sysparam);
 out:
 	return;
 }
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index a7ade94cdf87..d6a7b8252e4d 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -283,6 +283,7 @@ OPAL_CALL(opal_sensor_read,			OPAL_SENSOR_READ);
 OPAL_CALL(opal_get_param,			OPAL_GET_PARAM);
 OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
+OPAL_CALL(opal_config_cpu_idle_state,		OPAL_CONFIG_CPU_IDLE_STATE);
 OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
@@ -295,3 +296,4 @@ OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
 OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
 OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
 OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
+OPAL_CALL(opal_prd_msg,				OPAL_PRD_MSG);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2241565b0739..f084afa0e3ba 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -53,13 +53,7 @@ static int mc_recoverable_range_len;
 
 struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
-static unsigned int *opal_irqs;
-static unsigned int opal_irq_count;
-static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
 static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
-static DEFINE_SPINLOCK(opal_notifier_lock);
-static uint64_t last_notified_mask = 0x0ul;
-static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
 static uint32_t opal_heartbeat;
 
 static void opal_reinit_cores(void)
@@ -225,82 +219,6 @@ static int __init opal_register_exception_handlers(void)
 }
 machine_early_initcall(powernv, opal_register_exception_handlers);
 
-int opal_notifier_register(struct notifier_block *nb)
-{
-	if (!nb) {
-		pr_warning("%s: Invalid argument (%p)\n",
-			   __func__, nb);
-		return -EINVAL;
-	}
-
-	atomic_notifier_chain_register(&opal_notifier_head, nb);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(opal_notifier_register);
-
-int opal_notifier_unregister(struct notifier_block *nb)
-{
-	if (!nb) {
-		pr_warning("%s: Invalid argument (%p)\n",
-			   __func__, nb);
-		return -EINVAL;
-	}
-
-	atomic_notifier_chain_unregister(&opal_notifier_head, nb);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(opal_notifier_unregister);
-
-static void opal_do_notifier(uint64_t events)
-{
-	unsigned long flags;
-	uint64_t changed_mask;
-
-	if (atomic_read(&opal_notifier_hold))
-		return;
-
-	spin_lock_irqsave(&opal_notifier_lock, flags);
-	changed_mask = last_notified_mask ^ events;
-	last_notified_mask = events;
-	spin_unlock_irqrestore(&opal_notifier_lock, flags);
-
-	/*
-	 * We feed with the event bits and changed bits for
-	 * enough information to the callback.
-	 */
-	atomic_notifier_call_chain(&opal_notifier_head,
-				   events, (void *)changed_mask);
-}
-
-void opal_notifier_update_evt(uint64_t evt_mask,
-			      uint64_t evt_val)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&opal_notifier_lock, flags);
-	last_notified_mask &= ~evt_mask;
-	last_notified_mask |= evt_val;
-	spin_unlock_irqrestore(&opal_notifier_lock, flags);
-}
-
-void opal_notifier_enable(void)
-{
-	int64_t rc;
-	__be64 evt = 0;
-
-	atomic_set(&opal_notifier_hold, 0);
-
-	/* Process pending events */
-	rc = opal_poll_events(&evt);
-	if (rc == OPAL_SUCCESS && evt)
-		opal_do_notifier(be64_to_cpu(evt));
-}
-
-void opal_notifier_disable(void)
-{
-	atomic_set(&opal_notifier_hold, 1);
-}
-
 /*
  * Opal message notifier based on message type. Allow subscribers to get
  * notified for specific messgae type.
@@ -317,6 +235,7 @@ int opal_message_notifier_register(enum opal_msg_type msg_type,
 	return atomic_notifier_chain_register(
 				&opal_msg_notifier_head[msg_type], nb);
 }
+EXPORT_SYMBOL_GPL(opal_message_notifier_register);
 
 int opal_message_notifier_unregister(enum opal_msg_type msg_type,
 				     struct notifier_block *nb)
@@ -324,6 +243,7 @@ int opal_message_notifier_unregister(enum opal_msg_type msg_type,
 	return atomic_notifier_chain_unregister(
 			&opal_msg_notifier_head[msg_type], nb);
 }
+EXPORT_SYMBOL_GPL(opal_message_notifier_unregister);
 
 static void opal_message_do_notify(uint32_t msg_type, void *msg)
 {
@@ -364,36 +284,36 @@ static void opal_handle_message(void)
 	opal_message_do_notify(type, (void *)&msg);
 }
 
-static int opal_message_notify(struct notifier_block *nb,
-			  unsigned long events, void *change)
+static irqreturn_t opal_message_notify(int irq, void *data)
 {
-	if (events & OPAL_EVENT_MSG_PENDING)
-		opal_handle_message();
-	return 0;
+	opal_handle_message();
+	return IRQ_HANDLED;
 }
 
-static struct notifier_block opal_message_nb = {
-	.notifier_call	= opal_message_notify,
-	.next		= NULL,
-	.priority	= 0,
-};
-
 static int __init opal_message_init(void)
 {
-	int ret, i;
+	int ret, i, irq;
 
 	for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
 		ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
 
-	ret = opal_notifier_register(&opal_message_nb);
+	irq = opal_event_request(ilog2(OPAL_EVENT_MSG_PENDING));
+	if (!irq) {
+		pr_err("%s: Can't register OPAL event irq (%d)\n",
+		       __func__, irq);
+		return irq;
+	}
+
+	ret = request_irq(irq, opal_message_notify,
+			IRQ_TYPE_LEVEL_HIGH, "opal-msg", NULL);
 	if (ret) {
-		pr_err("%s: Can't register OPAL event notifier (%d)\n",
+		pr_err("%s: Can't request OPAL event irq (%d)\n",
 		       __func__, ret);
 		return ret;
 	}
+
 	return 0;
 }
-machine_early_initcall(powernv, opal_message_init);
 
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
@@ -573,7 +493,7 @@ int opal_handle_hmi_exception(struct pt_regs *regs)
 	local_paca->hmi_event_available = 0;
 	rc = opal_poll_events(&evt);
 	if (rc == OPAL_SUCCESS && evt)
-		opal_do_notifier(be64_to_cpu(evt));
+		opal_handle_events(be64_to_cpu(evt));
 
 	return 1;
 }
@@ -610,17 +530,6 @@ out:
 	return !!recover_addr;
 }
 
-static irqreturn_t opal_interrupt(int irq, void *data)
-{
-	__be64 events;
-
-	opal_handle_interrupt(virq_to_hw(irq), &events);
-
-	opal_do_notifier(be64_to_cpu(events));
-
-	return IRQ_HANDLED;
-}
-
 static int opal_sysfs_init(void)
 {
 	opal_kobj = kobject_create_and_add("opal", firmware_kobj);
@@ -693,21 +602,13 @@ static void __init opal_dump_region_init(void)
 			"rc = %d\n", rc);
 }
 
-static void opal_flash_init(struct device_node *opal_node)
-{
-	struct device_node *np;
-
-	for_each_child_of_node(opal_node, np)
-		if (of_device_is_compatible(np, "ibm,opal-flash"))
-			of_platform_device_create(np, NULL, NULL);
-}
-
-static void opal_ipmi_init(struct device_node *opal_node)
+static void opal_pdev_init(struct device_node *opal_node,
+		const char *compatible)
 {
 	struct device_node *np;
 
 	for_each_child_of_node(opal_node, np)
-		if (of_device_is_compatible(np, "ibm,opal-ipmi"))
+		if (of_device_is_compatible(np, compatible))
 			of_platform_device_create(np, NULL, NULL);
 }
 
@@ -719,52 +620,15 @@ static void opal_i2c_create_devs(void)
 		of_platform_device_create(np, NULL, NULL);
 }
 
-static void __init opal_irq_init(struct device_node *dn)
-{
-	const __be32 *irqs;
-	int i, irqlen;
-
-	/* Get interrupt property */
-	irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
-	opal_irq_count = irqs ? (irqlen / 4) : 0;
-	pr_debug("Found %d interrupts reserved for OPAL\n", opal_irq_count);
-	if (!opal_irq_count)
-		return;
-
-	/* Install interrupt handlers */
-	opal_irqs = kzalloc(opal_irq_count * sizeof(unsigned int), GFP_KERNEL);
-	for (i = 0; irqs && i < opal_irq_count; i++, irqs++) {
-		unsigned int irq, virq;
-		int rc;
-
-		/* Get hardware and virtual IRQ */
-		irq = be32_to_cpup(irqs);
-		virq = irq_create_mapping(NULL, irq);
-		if (virq == NO_IRQ) {
-			pr_warn("Failed to map irq 0x%x\n", irq);
-			continue;
-		}
-
-		/* Install interrupt handler */
-		rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
-		if (rc) {
-			irq_dispose_mapping(virq);
-			pr_warn("Error %d requesting irq %d (0x%x)\n",
-				 rc, virq, irq);
-			continue;
-		}
-
-		/* Cache IRQ */
-		opal_irqs[i] = virq;
-	}
-}
-
 static int kopald(void *unused)
 {
+	__be64 events;
+
 	set_freezable();
 	do {
 		try_to_freeze();
-		opal_poll_events(NULL);
+		opal_poll_events(&events);
+		opal_handle_events(be64_to_cpu(events));
 		msleep_interruptible(opal_heartbeat);
 	} while (!kthread_should_stop());
 
@@ -807,15 +671,24 @@ static int __init opal_init(void)
 		of_node_put(consoles);
 	}
 
+	/* Initialise OPAL messaging system */
+	opal_message_init();
+
+	/* Initialise OPAL asynchronous completion interface */
+	opal_async_comp_init();
+
+	/* Initialise OPAL sensor interface */
+	opal_sensor_init();
+
+	/* Initialise OPAL hypervisor maintainence interrupt handling */
+	opal_hmi_handler_init();
+
 	/* Create i2c platform devices */
 	opal_i2c_create_devs();
 
 	/* Setup a heatbeat thread if requested by OPAL */
 	opal_init_heartbeat();
 
-	/* Find all OPAL interrupts and request them */
-	opal_irq_init(opal_node);
-
 	/* Create "opal" kobject under /sys/firmware */
 	rc = opal_sysfs_init();
 	if (rc == 0) {
@@ -835,10 +708,10 @@ static int __init opal_init(void)
 		opal_msglog_init();
 	}
 
-	/* Initialize OPAL IPMI backend */
-	opal_ipmi_init(opal_node);
-
-	opal_flash_init(opal_node);
+	/* Initialize platform devices: IPMI backend, PRD & flash interface */
+	opal_pdev_init(opal_node, "ibm,opal-ipmi");
+	opal_pdev_init(opal_node, "ibm,opal-flash");
+	opal_pdev_init(opal_node, "ibm,opal-prd");
 
 	return 0;
 }
@@ -846,15 +719,9 @@ machine_subsys_initcall(powernv, opal_init);
 
 void opal_shutdown(void)
 {
-	unsigned int i;
 	long rc = OPAL_BUSY;
 
-	/* First free interrupts, which will also mask them */
-	for (i = 0; i < opal_irq_count; i++) {
-		if (opal_irqs[i])
-			free_irq(opal_irqs[i], NULL);
-		opal_irqs[i] = 0;
-	}
+	opal_event_shutdown();
 
 	/*
 	 * Then sync with OPAL which ensure anything that can
@@ -876,11 +743,14 @@ void opal_shutdown(void)
 
 /* Export this so that test modules can use it */
 EXPORT_SYMBOL_GPL(opal_invalid_call);
+EXPORT_SYMBOL_GPL(opal_xscom_read);
+EXPORT_SYMBOL_GPL(opal_xscom_write);
 EXPORT_SYMBOL_GPL(opal_ipmi_send);
 EXPORT_SYMBOL_GPL(opal_ipmi_recv);
 EXPORT_SYMBOL_GPL(opal_flash_read);
 EXPORT_SYMBOL_GPL(opal_flash_write);
 EXPORT_SYMBOL_GPL(opal_flash_erase);
+EXPORT_SYMBOL_GPL(opal_prd_msg);
 
 /* Convert a region of vmalloc memory to an opal sg list */
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
@@ -954,6 +824,7 @@ int opal_error_code(int rc)
 	case OPAL_ASYNC_COMPLETION:	return -EINPROGRESS;
 	case OPAL_BUSY_EVENT:		return -EBUSY;
 	case OPAL_NO_MEM:		return -ENOMEM;
+	case OPAL_PERMISSION:		return -EPERM;
 
 	case OPAL_UNSUPPORTED:		return -EIO;
 	case OPAL_HARDWARE:		return -EIO;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f8bc950efcae..5738d315248b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -23,6 +23,9 @@
 #include <linux/io.h>
 #include <linux/msi.h>
 #include <linux/memblock.h>
+#include <linux/iommu.h>
+#include <linux/rculist.h>
+#include <linux/sizes.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -38,8 +41,9 @@
 #include <asm/debug.h>
 #include <asm/firmware.h>
 #include <asm/pnv-pci.h>
+#include <asm/mmzone.h>
 
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -47,6 +51,11 @@
 /* 256M DMA window, 4K TCE pages, 8 bytes TCE */
 #define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
 
+#define POWERNV_IOMMU_DEFAULT_LEVELS	1
+#define POWERNV_IOMMU_MAX_LEVELS	5
+
+static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl);
+
 static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
 {
@@ -1086,10 +1095,6 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 		return;
 	}
 
-	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
-			GFP_KERNEL, hose->node);
-	pe->tce32_table->data = pe;
-
 	/* Associate it with all child devices */
 	pnv_ioda_setup_same_PE(bus, pe);
 
@@ -1283,36 +1288,27 @@ m64_failed:
 	return -EBUSY;
 }
 
+static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
+		int num);
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+
 static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
 {
-	struct pci_bus        *bus;
-	struct pci_controller *hose;
-	struct pnv_phb        *phb;
 	struct iommu_table    *tbl;
-	unsigned long         addr;
 	int64_t               rc;
 
-	bus = dev->bus;
-	hose = pci_bus_to_host(bus);
-	phb = hose->private_data;
-	tbl = pe->tce32_table;
-	addr = tbl->it_base;
-
-	opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
-				   pe->pe_number << 1, 1, __pa(addr),
-				   0, 0x1000);
-
-	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
-				        pe->pe_number,
-				        (pe->pe_number << 1) + 1,
-				        pe->tce_bypass_base,
-				        0);
+	tbl = pe->table_group.tables[0];
+	rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (rc)
 		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
 
+	pnv_pci_ioda2_set_bypass(pe, false);
+	if (pe->table_group.group) {
+		iommu_group_put(pe->table_group.group);
+		BUG_ON(pe->table_group.group);
+	}
+	pnv_pci_ioda2_table_free_pages(tbl);
 	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
-	free_pages(addr, get_order(TCE32_TABLE_SIZE));
-	pe->tce32_table = NULL;
 }
 
 static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
@@ -1460,10 +1456,6 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 			continue;
 		}
 
-		pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
-				GFP_KERNEL, hose->node);
-		pe->tce32_table->data = pe;
-
 		/* Put PE to the list */
 		mutex_lock(&phb->ioda.pe_list_mutex);
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
@@ -1598,12 +1590,19 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
+	set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
+	/*
+	 * Note: iommu_add_device() will fail here as
+	 * for physical PE: the device is already added by now;
+	 * for virtual PE: sysfs entries are not ready yet and
+	 * tce_iommu_bus_notifier will add the device to a group later.
+	 */
 }
 
-static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
-				     struct pci_dev *pdev, u64 dma_mask)
+static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 {
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 	uint64_t top;
@@ -1625,7 +1624,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	} else {
 		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		set_iommu_table_base(&pdev->dev, pe->tce32_table);
+		set_iommu_table_base(&pdev->dev, pe->table_group.tables[0]);
 	}
 	*pdev->dev.dma_mask = dma_mask;
 	return 0;
@@ -1654,36 +1653,36 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
-				   struct pci_bus *bus,
-				   bool add_to_iommu_group)
+				   struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		if (add_to_iommu_group)
-			set_iommu_table_base_and_group(&dev->dev,
-						       pe->tce32_table);
-		else
-			set_iommu_table_base(&dev->dev, pe->tce32_table);
+		set_iommu_table_base(&dev->dev, pe->table_group.tables[0]);
+		iommu_add_device(&dev->dev);
 
-		if (dev->subordinate)
-			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
-					       add_to_iommu_group);
+		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
 }
 
-static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
-					 struct iommu_table *tbl,
-					 __be64 *startp, __be64 *endp, bool rm)
+static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
+		unsigned long index, unsigned long npages, bool rm)
 {
+	struct iommu_table_group_link *tgl = list_first_entry_or_null(
+			&tbl->it_group_list, struct iommu_table_group_link,
+			next);
+	struct pnv_ioda_pe *pe = container_of(tgl->table_group,
+			struct pnv_ioda_pe, table_group);
 	__be64 __iomem *invalidate = rm ?
-		(__be64 __iomem *)pe->tce_inval_reg_phys :
-		(__be64 __iomem *)tbl->it_index;
+		(__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+		pe->phb->ioda.tce_inval_reg;
 	unsigned long start, end, inc;
 	const unsigned shift = tbl->it_page_shift;
 
-	start = __pa(startp);
-	end = __pa(endp);
+	start = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset);
+	end = __pa(((__be64 *)tbl->it_base) + index - tbl->it_offset +
+			npages - 1);
 
 	/* BML uses this case for p6/p7/galaxy2: Shift addr and put in node */
 	if (tbl->it_busno) {
@@ -1719,26 +1718,79 @@ static void pnv_pci_ioda1_tce_invalidate(struct pnv_ioda_pe *pe,
 	 */
 }
 
-static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
-					 struct iommu_table *tbl,
-					 __be64 *startp, __be64 *endp, bool rm)
+static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
+		long npages, unsigned long uaddr,
+		enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
+			attrs);
+
+	if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
+		pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+
+	return ret;
+}
+
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret && (tbl->it_type &
+			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+		pnv_pci_ioda1_tce_invalidate(tbl, index, 1, false);
+
+	return ret;
+}
+#endif
+
+static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
+		long npages)
+{
+	pnv_tce_free(tbl, index, npages);
+
+	if (tbl->it_type & TCE_PCI_SWINV_FREE)
+		pnv_pci_ioda1_tce_invalidate(tbl, index, npages, false);
+}
+
+static struct iommu_table_ops pnv_ioda1_iommu_ops = {
+	.set = pnv_ioda1_tce_build,
+#ifdef CONFIG_IOMMU_API
+	.exchange = pnv_ioda1_tce_xchg,
+#endif
+	.clear = pnv_ioda1_tce_free,
+	.get = pnv_tce_get,
+};
+
+static inline void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_ioda_pe *pe)
+{
+	/* 01xb - invalidate TCEs that match the specified PE# */
+	unsigned long val = (0x4ull << 60) | (pe->pe_number & 0xFF);
+	struct pnv_phb *phb = pe->phb;
+
+	if (!phb->ioda.tce_inval_reg)
+		return;
+
+	mb(); /* Ensure above stores are visible */
+	__raw_writeq(cpu_to_be64(val), phb->ioda.tce_inval_reg);
+}
+
+static void pnv_pci_ioda2_do_tce_invalidate(unsigned pe_number, bool rm,
+		__be64 __iomem *invalidate, unsigned shift,
+		unsigned long index, unsigned long npages)
 {
 	unsigned long start, end, inc;
-	__be64 __iomem *invalidate = rm ?
-		(__be64 __iomem *)pe->tce_inval_reg_phys :
-		(__be64 __iomem *)tbl->it_index;
-	const unsigned shift = tbl->it_page_shift;
 
 	/* We'll invalidate DMA address in PE scope */
 	start = 0x2ull << 60;
-	start |= (pe->pe_number & 0xFF);
+	start |= (pe_number & 0xFF);
 	end = start;
 
 	/* Figure out the start, end and step */
-	inc = tbl->it_offset + (((u64)startp - tbl->it_base) / sizeof(u64));
-	start |= (inc << shift);
-	inc = tbl->it_offset + (((u64)endp - tbl->it_base) / sizeof(u64));
-	end |= (inc << shift);
+	start |= (index << shift);
+	end |= ((index + npages - 1) << shift);
 	inc = (0x1ull << shift);
 	mb();
 
@@ -1751,25 +1803,83 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 	}
 }
 
-void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
-				 __be64 *startp, __be64 *endp, bool rm)
+static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
+		unsigned long index, unsigned long npages, bool rm)
 {
-	struct pnv_ioda_pe *pe = tbl->data;
-	struct pnv_phb *phb = pe->phb;
+	struct iommu_table_group_link *tgl;
 
-	if (phb->type == PNV_PHB_IODA1)
-		pnv_pci_ioda1_tce_invalidate(pe, tbl, startp, endp, rm);
-	else
-		pnv_pci_ioda2_tce_invalidate(pe, tbl, startp, endp, rm);
+	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+		struct pnv_ioda_pe *pe = container_of(tgl->table_group,
+				struct pnv_ioda_pe, table_group);
+		__be64 __iomem *invalidate = rm ?
+			(__be64 __iomem *)pe->phb->ioda.tce_inval_reg_phys :
+			pe->phb->ioda.tce_inval_reg;
+
+		pnv_pci_ioda2_do_tce_invalidate(pe->pe_number, rm,
+			invalidate, tbl->it_page_shift,
+			index, npages);
+	}
+}
+
+static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
+		long npages, unsigned long uaddr,
+		enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	int ret = pnv_tce_build(tbl, index, npages, uaddr, direction,
+			attrs);
+
+	if (!ret && (tbl->it_type & TCE_PCI_SWINV_CREATE))
+		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+
+	return ret;
+}
+
+#ifdef CONFIG_IOMMU_API
+static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
+{
+	long ret = pnv_tce_xchg(tbl, index, hpa, direction);
+
+	if (!ret && (tbl->it_type &
+			(TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE)))
+		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
+
+	return ret;
+}
+#endif
+
+static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
+		long npages)
+{
+	pnv_tce_free(tbl, index, npages);
+
+	if (tbl->it_type & TCE_PCI_SWINV_FREE)
+		pnv_pci_ioda2_tce_invalidate(tbl, index, npages, false);
+}
+
+static void pnv_ioda2_table_free(struct iommu_table *tbl)
+{
+	pnv_pci_ioda2_table_free_pages(tbl);
+	iommu_free_table(tbl, "pnv");
 }
 
+static struct iommu_table_ops pnv_ioda2_iommu_ops = {
+	.set = pnv_ioda2_tce_build,
+#ifdef CONFIG_IOMMU_API
+	.exchange = pnv_ioda2_tce_xchg,
+#endif
+	.clear = pnv_ioda2_tce_free,
+	.get = pnv_tce_get,
+	.free = pnv_ioda2_table_free,
+};
+
 static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 				      struct pnv_ioda_pe *pe, unsigned int base,
 				      unsigned int segs)
 {
 
 	struct page *tce_mem = NULL;
-	const __be64 *swinvp;
 	struct iommu_table *tbl;
 	unsigned int i;
 	int64_t rc;
@@ -1783,6 +1893,11 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	if (WARN_ON(pe->tce32_seg >= 0))
 		return;
 
+	tbl = pnv_pci_table_alloc(phb->hose->node);
+	iommu_register_group(&pe->table_group, phb->hose->global_number,
+			pe->pe_number);
+	pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group);
+
 	/* Grab a 32-bit TCE table */
 	pe->tce32_seg = base;
 	pe_info(pe, " Setting up 32-bit TCE table at %08x..%08x\n",
@@ -1817,39 +1932,30 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
 				  base << 28, IOMMU_PAGE_SHIFT_4K);
 
 	/* OPAL variant of P7IOC SW invalidated TCEs */
-	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
-	if (swinvp) {
-		/* We need a couple more fields -- an address and a data
-		 * to or.  Since the bus is only printed out on table free
-		 * errors, and on the first pass the data will be a relative
-		 * bus number, print that out instead.
-		 */
-		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
-		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
-				8);
+	if (phb->ioda.tce_inval_reg)
 		tbl->it_type |= (TCE_PCI_SWINV_CREATE |
 				 TCE_PCI_SWINV_FREE   |
 				 TCE_PCI_SWINV_PAIR);
-	}
+
+	tbl->it_ops = &pnv_ioda1_iommu_ops;
+	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
+	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
 	iommu_init_table(tbl, phb->hose->node);
 
 	if (pe->flags & PNV_IODA_PE_DEV) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
-	} else if (pe->flags & PNV_IODA_PE_VF) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-	}
+		/*
+		 * Setting table base here only for carrying iommu_group
+		 * further down to let iommu_add_device() do the job.
+		 * pnv_pci_ioda_dma_dev_setup will override it later anyway.
+		 */
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+		iommu_add_device(&pe->pdev->dev);
+	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
 	return;
  fail:
@@ -1858,11 +1964,53 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		pe->tce32_seg = -1;
 	if (tce_mem)
 		__free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs));
+	if (tbl) {
+		pnv_pci_unlink_table_and_group(tbl, &pe->table_group);
+		iommu_free_table(tbl, "pnv");
+	}
 }
 
-static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
+static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
+		int num, struct iommu_table *tbl)
+{
+	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
+	struct pnv_phb *phb = pe->phb;
+	int64_t rc;
+	const unsigned long size = tbl->it_indirect_levels ?
+			tbl->it_level_size : tbl->it_size;
+	const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
+	const __u64 win_size = tbl->it_size << tbl->it_page_shift;
+
+	pe_info(pe, "Setting up window#%d %llx..%llx pg=%x\n", num,
+			start_addr, start_addr + win_size - 1,
+			IOMMU_PAGE_SIZE(tbl));
+
+	/*
+	 * Map TCE table through TVT. The TVE index is the PE number
+	 * shifted by 1 bit for 32-bits DMA space.
+	 */
+	rc = opal_pci_map_pe_dma_window(phb->opal_id,
+			pe->pe_number,
+			(pe->pe_number << 1) + num,
+			tbl->it_indirect_levels + 1,
+			__pa(tbl->it_base),
+			size << 3,
+			IOMMU_PAGE_SIZE(tbl));
+	if (rc) {
+		pe_err(pe, "Failed to configure TCE table, err %ld\n", rc);
+		return rc;
+	}
+
+	pnv_pci_link_table_and_group(phb->hose->node, num,
+			tbl, &pe->table_group);
+	pnv_pci_ioda2_tce_invalidate_entire(pe);
+
+	return 0;
+}
+
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
 {
-	struct pnv_ioda_pe *pe = tbl->data;
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
 
@@ -1882,17 +2030,6 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 						     window_id,
 						     pe->tce_bypass_base,
 						     0);
-
-		/*
-		 * EEH needs the mapping between IOMMU table and group
-		 * of those VFIO/KVM pass-through devices. We can postpone
-		 * resetting DMA ops until the DMA mask is configured in
-		 * host side.
-		 */
-		if (pe->pdev)
-			set_iommu_table_base(&pe->pdev->dev, tbl);
-		else
-			pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
 	}
 	if (rc)
 		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
@@ -1900,106 +2037,363 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 		pe->tce_bypass_enabled = enable;
 }
 
-static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
-					  struct pnv_ioda_pe *pe)
+static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
+		__u32 page_shift, __u64 window_size, __u32 levels,
+		struct iommu_table *tbl);
+
+static long pnv_pci_ioda2_create_table(struct iommu_table_group *table_group,
+		int num, __u32 page_shift, __u64 window_size, __u32 levels,
+		struct iommu_table **ptbl)
 {
-	/* TVE #1 is selected by PCI address bit 59 */
-	pe->tce_bypass_base = 1ull << 59;
+	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
+	int nid = pe->phb->hose->node;
+	__u64 bus_offset = num ? pe->tce_bypass_base : table_group->tce32_start;
+	long ret;
+	struct iommu_table *tbl;
 
-	/* Install set_bypass callback for VFIO */
-	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
+	tbl = pnv_pci_table_alloc(nid);
+	if (!tbl)
+		return -ENOMEM;
 
-	/* Enable bypass by default */
-	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
+	ret = pnv_pci_ioda2_table_alloc_pages(nid,
+			bus_offset, page_shift, window_size,
+			levels, tbl);
+	if (ret) {
+		iommu_free_table(tbl, "pnv");
+		return ret;
+	}
+
+	tbl->it_ops = &pnv_ioda2_iommu_ops;
+	if (pe->phb->ioda.tce_inval_reg)
+		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+
+	*ptbl = tbl;
+
+	return 0;
 }
 
-static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
-				       struct pnv_ioda_pe *pe)
+static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
+{
+	struct iommu_table *tbl = NULL;
+	long rc;
+
+	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
+			IOMMU_PAGE_SHIFT_4K,
+			pe->table_group.tce32_size,
+			POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
+	if (rc) {
+		pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
+				rc);
+		return rc;
+	}
+
+	iommu_init_table(tbl, pe->phb->hose->node);
+
+	rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+	if (rc) {
+		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
+				rc);
+		pnv_ioda2_table_free(tbl);
+		return rc;
+	}
+
+	if (!pnv_iommu_bypass_disabled)
+		pnv_pci_ioda2_set_bypass(pe, true);
+
+	/* OPAL variant of PHB3 invalidated TCEs */
+	if (pe->phb->ioda.tce_inval_reg)
+		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+
+	/*
+	 * Setting table base here only for carrying iommu_group
+	 * further down to let iommu_add_device() do the job.
+	 * pnv_pci_ioda_dma_dev_setup will override it later anyway.
+	 */
+	if (pe->flags & PNV_IODA_PE_DEV)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+
+	return 0;
+}
+
+#if defined(CONFIG_IOMMU_API) || defined(CONFIG_PCI_IOV)
+static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
+		int num)
+{
+	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+			table_group);
+	struct pnv_phb *phb = pe->phb;
+	long ret;
+
+	pe_info(pe, "Removing DMA window #%d\n", num);
+
+	ret = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+			(pe->pe_number << 1) + num,
+			0/* levels */, 0/* table address */,
+			0/* table size */, 0/* page size */);
+	if (ret)
+		pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
+	else
+		pnv_pci_ioda2_tce_invalidate_entire(pe);
+
+	pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_IOMMU_API
+static unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
+		__u64 window_size, __u32 levels)
+{
+	unsigned long bytes = 0;
+	const unsigned window_shift = ilog2(window_size);
+	unsigned entries_shift = window_shift - page_shift;
+	unsigned table_shift = entries_shift + 3;
+	unsigned long tce_table_size = max(0x1000UL, 1UL << table_shift);
+	unsigned long direct_table_size;
+
+	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS) ||
+			(window_size > memory_hotplug_max()) ||
+			!is_power_of_2(window_size))
+		return 0;
+
+	/* Calculate a direct table size from window_size and levels */
+	entries_shift = (entries_shift + levels - 1) / levels;
+	table_shift = entries_shift + 3;
+	table_shift = max_t(unsigned, table_shift, PAGE_SHIFT);
+	direct_table_size =  1UL << table_shift;
+
+	for ( ; levels; --levels) {
+		bytes += _ALIGN_UP(tce_table_size, direct_table_size);
+
+		tce_table_size /= direct_table_size;
+		tce_table_size <<= 3;
+		tce_table_size = _ALIGN_UP(tce_table_size, direct_table_size);
+	}
+
+	return bytes;
+}
+
+static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
+{
+	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+						table_group);
+	/* Store @tbl as pnv_pci_ioda2_unset_window() resets it */
+	struct iommu_table *tbl = pe->table_group.tables[0];
+
+	pnv_pci_ioda2_set_bypass(pe, false);
+	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
+	pnv_ioda2_table_free(tbl);
+}
+
+static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group)
+{
+	struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe,
+						table_group);
+
+	pnv_pci_ioda2_setup_default_config(pe);
+}
+
+static struct iommu_table_group_ops pnv_pci_ioda2_ops = {
+	.get_table_size = pnv_pci_ioda2_get_table_size,
+	.create_table = pnv_pci_ioda2_create_table,
+	.set_window = pnv_pci_ioda2_set_window,
+	.unset_window = pnv_pci_ioda2_unset_window,
+	.take_ownership = pnv_ioda2_take_ownership,
+	.release_ownership = pnv_ioda2_release_ownership,
+};
+#endif
+
+static void pnv_pci_ioda_setup_opal_tce_kill(struct pnv_phb *phb)
 {
-	struct page *tce_mem = NULL;
-	void *addr;
 	const __be64 *swinvp;
-	struct iommu_table *tbl;
-	unsigned int tce_table_size, end;
-	int64_t rc;
 
-	/* We shouldn't already have a 32-bit DMA associated */
-	if (WARN_ON(pe->tce32_seg >= 0))
+	/* OPAL variant of PHB3 invalidated TCEs */
+	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
+	if (!swinvp)
 		return;
 
-	/* The PE will reserve all possible 32-bits space */
-	pe->tce32_seg = 0;
-	end = (1 << ilog2(phb->ioda.m32_pci_base));
-	tce_table_size = (end / 0x1000) * 8;
-	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
-		end);
+	phb->ioda.tce_inval_reg_phys = be64_to_cpup(swinvp);
+	phb->ioda.tce_inval_reg = ioremap(phb->ioda.tce_inval_reg_phys, 8);
+}
 
-	/* Allocate TCE table */
-	tce_mem = alloc_pages_node(phb->hose->node, GFP_KERNEL,
-				   get_order(tce_table_size));
+static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
+		unsigned levels, unsigned long limit,
+		unsigned long *current_offset)
+{
+	struct page *tce_mem = NULL;
+	__be64 *addr, *tmp;
+	unsigned order = max_t(unsigned, shift, PAGE_SHIFT) - PAGE_SHIFT;
+	unsigned long allocated = 1UL << (order + PAGE_SHIFT);
+	unsigned entries = 1UL << (shift - 3);
+	long i;
+
+	tce_mem = alloc_pages_node(nid, GFP_KERNEL, order);
 	if (!tce_mem) {
-		pe_err(pe, "Failed to allocate a 32-bit TCE memory\n");
-		goto fail;
+		pr_err("Failed to allocate a TCE memory, order=%d\n", order);
+		return NULL;
 	}
 	addr = page_address(tce_mem);
-	memset(addr, 0, tce_table_size);
+	memset(addr, 0, allocated);
+
+	--levels;
+	if (!levels) {
+		*current_offset += allocated;
+		return addr;
+	}
+
+	for (i = 0; i < entries; ++i) {
+		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
+				levels, limit, current_offset);
+		if (!tmp)
+			break;
+
+		addr[i] = cpu_to_be64(__pa(tmp) |
+				TCE_PCI_READ | TCE_PCI_WRITE);
+
+		if (*current_offset >= limit)
+			break;
+	}
+
+	return addr;
+}
+
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+		unsigned long size, unsigned level);
+
+static long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset,
+		__u32 page_shift, __u64 window_size, __u32 levels,
+		struct iommu_table *tbl)
+{
+	void *addr;
+	unsigned long offset = 0, level_shift;
+	const unsigned window_shift = ilog2(window_size);
+	unsigned entries_shift = window_shift - page_shift;
+	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
+	const unsigned long tce_table_size = 1UL << table_shift;
+
+	if (!levels || (levels > POWERNV_IOMMU_MAX_LEVELS))
+		return -EINVAL;
+
+	if ((window_size > memory_hotplug_max()) || !is_power_of_2(window_size))
+		return -EINVAL;
+
+	/* Adjust direct table size from window_size and levels */
+	entries_shift = (entries_shift + levels - 1) / levels;
+	level_shift = entries_shift + 3;
+	level_shift = max_t(unsigned, level_shift, PAGE_SHIFT);
+
+	/* Allocate TCE table */
+	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
+			levels, tce_table_size, &offset);
+
+	/* addr==NULL means that the first level allocation failed */
+	if (!addr)
+		return -ENOMEM;
 
 	/*
-	 * Map TCE table through TVT. The TVE index is the PE number
-	 * shifted by 1 bit for 32-bits DMA space.
+	 * First level was allocated but some lower level failed as
+	 * we did not allocate as much as we wanted,
+	 * release partially allocated table.
 	 */
-	rc = opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
-					pe->pe_number << 1, 1, __pa(addr),
-					tce_table_size, 0x1000);
-	if (rc) {
-		pe_err(pe, "Failed to configure 32-bit TCE table,"
-		       " err %ld\n", rc);
-		goto fail;
+	if (offset < tce_table_size) {
+		pnv_pci_ioda2_table_do_free_pages(addr,
+				1ULL << (level_shift - 3), levels - 1);
+		return -ENOMEM;
 	}
 
 	/* Setup linux iommu table */
-	tbl = pe->tce32_table;
-	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
-			IOMMU_PAGE_SHIFT_4K);
+	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, bus_offset,
+			page_shift);
+	tbl->it_level_size = 1ULL << (level_shift - 3);
+	tbl->it_indirect_levels = levels - 1;
+	tbl->it_allocated_size = offset;
 
-	/* OPAL variant of PHB3 invalidated TCEs */
-	swinvp = of_get_property(phb->hose->dn, "ibm,opal-tce-kill", NULL);
-	if (swinvp) {
-		/* We need a couple more fields -- an address and a data
-		 * to or.  Since the bus is only printed out on table free
-		 * errors, and on the first pass the data will be a relative
-		 * bus number, print that out instead.
-		 */
-		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
-		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
-				8);
-		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
+	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
+			window_size, tce_table_size, bus_offset);
+
+	return 0;
+}
+
+static void pnv_pci_ioda2_table_do_free_pages(__be64 *addr,
+		unsigned long size, unsigned level)
+{
+	const unsigned long addr_ul = (unsigned long) addr &
+			~(TCE_PCI_READ | TCE_PCI_WRITE);
+
+	if (level) {
+		long i;
+		u64 *tmp = (u64 *) addr_ul;
+
+		for (i = 0; i < size; ++i) {
+			unsigned long hpa = be64_to_cpu(tmp[i]);
+
+			if (!(hpa & (TCE_PCI_READ | TCE_PCI_WRITE)))
+				continue;
+
+			pnv_pci_ioda2_table_do_free_pages(__va(hpa), size,
+					level - 1);
+		}
 	}
-	iommu_init_table(tbl, phb->hose->node);
 
-	if (pe->flags & PNV_IODA_PE_DEV) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
-	} else if (pe->flags & PNV_IODA_PE_VF) {
-		iommu_register_group(tbl, phb->hose->global_number,
-				     pe->pe_number);
-	}
-
-	/* Also create a bypass window */
-	if (!pnv_iommu_bypass_disabled)
-		pnv_pci_ioda2_setup_bypass_pe(phb, pe);
+	free_pages(addr_ul, get_order(size << 3));
+}
 
-	return;
-fail:
-	if (pe->tce32_seg >= 0)
-		pe->tce32_seg = -1;
-	if (tce_mem)
-		__free_pages(tce_mem, get_order(tce_table_size));
+static void pnv_pci_ioda2_table_free_pages(struct iommu_table *tbl)
+{
+	const unsigned long size = tbl->it_indirect_levels ?
+			tbl->it_level_size : tbl->it_size;
+
+	if (!tbl->it_size)
+		return;
+
+	pnv_pci_ioda2_table_do_free_pages((__be64 *)tbl->it_base, size,
+			tbl->it_indirect_levels);
+}
+
+static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+				       struct pnv_ioda_pe *pe)
+{
+	int64_t rc;
+
+	/* We shouldn't already have a 32-bit DMA associated */
+	if (WARN_ON(pe->tce32_seg >= 0))
+		return;
+
+	/* TVE #1 is selected by PCI address bit 59 */
+	pe->tce_bypass_base = 1ull << 59;
+
+	iommu_register_group(&pe->table_group, phb->hose->global_number,
+			pe->pe_number);
+
+	/* The PE will reserve all possible 32-bits space */
+	pe->tce32_seg = 0;
+	pe_info(pe, "Setting up 32-bit TCE table at 0..%08x\n",
+		phb->ioda.m32_pci_base);
+
+	/* Setup linux iommu table */
+	pe->table_group.tce32_start = 0;
+	pe->table_group.tce32_size = phb->ioda.m32_pci_base;
+	pe->table_group.max_dynamic_windows_supported =
+			IOMMU_TABLE_GROUP_MAX_TABLES;
+	pe->table_group.max_levels = POWERNV_IOMMU_MAX_LEVELS;
+	pe->table_group.pgsizes = SZ_4K | SZ_64K | SZ_16M;
+#ifdef CONFIG_IOMMU_API
+	pe->table_group.ops = &pnv_pci_ioda2_ops;
+#endif
+
+	rc = pnv_pci_ioda2_setup_default_config(pe);
+	if (rc) {
+		if (pe->tce32_seg >= 0)
+			pe->tce32_seg = -1;
+		return;
+	}
+
+	if (pe->flags & PNV_IODA_PE_DEV)
+		iommu_add_device(&pe->pdev->dev);
+	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 }
 
 static void pnv_ioda_setup_dma(struct pnv_phb *phb)
@@ -2024,6 +2418,8 @@ static void pnv_ioda_setup_dma(struct pnv_phb *phb)
 	pr_info("PCI: %d PE# for a total weight of %d\n",
 		phb->ioda.dma_pe_count, phb->ioda.dma_weight);
 
+	pnv_pci_ioda_setup_opal_tce_kill(phb);
+
 	/* Walk our PE list and configure their DMA segments, hand them
 	 * out one base segment plus any residual segments based on
 	 * weight
@@ -2642,12 +3038,27 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 	return phb->ioda.pe_rmap[(bus->number << 8) | devfn];
 }
 
-static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
+static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
+	struct pnv_phb *phb = hose->private_data;
+
 	opal_pci_reset(phb->opal_id, OPAL_RESET_PCI_IODA_TABLE,
 		       OPAL_ASSERT_RESET);
 }
 
+static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
+       .dma_dev_setup = pnv_pci_dma_dev_setup,
+#ifdef CONFIG_PCI_MSI
+       .setup_msi_irqs = pnv_setup_msi_irqs,
+       .teardown_msi_irqs = pnv_teardown_msi_irqs,
+#endif
+       .enable_device_hook = pnv_pci_enable_device_hook,
+       .window_alignment = pnv_pci_window_alignment,
+       .reset_secondary_bus = pnv_pci_reset_secondary_bus,
+       .dma_set_mask = pnv_pci_ioda_dma_set_mask,
+       .shutdown = pnv_pci_ioda_shutdown,
+};
+
 static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 					 u64 hub_id, int ioda_type)
 {
@@ -2791,12 +3202,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
-	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
 	phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
 
-	/* Setup shutdown function for kexec */
-	phb->shutdown = pnv_pci_ioda_shutdown;
-
 	/* Setup MSI support */
 	pnv_pci_init_ioda_msis(phb);
 
@@ -2808,10 +3215,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 * the child P2P bridges) can form individual PE.
 	 */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
-	pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook;
-	pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment;
-	pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus;
-	hose->controller_ops = pnv_pci_controller_ops;
+	hose->controller_ops = pnv_pci_ioda_controller_ops;
 
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 4729ca793813..f2bdfea3b68d 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -83,18 +83,42 @@ static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb)
 static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
 #endif /* CONFIG_PCI_MSI */
 
+static struct iommu_table_ops pnv_p5ioc2_iommu_ops = {
+	.set = pnv_tce_build,
+#ifdef CONFIG_IOMMU_API
+	.exchange = pnv_tce_xchg,
+#endif
+	.clear = pnv_tce_free,
+	.get = pnv_tce_get,
+};
+
 static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 					 struct pci_dev *pdev)
 {
-	if (phb->p5ioc2.iommu_table.it_map == NULL) {
-		iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
-		iommu_register_group(&phb->p5ioc2.iommu_table,
+	struct iommu_table *tbl = phb->p5ioc2.table_group.tables[0];
+
+	if (!tbl->it_map) {
+		tbl->it_ops = &pnv_p5ioc2_iommu_ops;
+		iommu_init_table(tbl, phb->hose->node);
+		iommu_register_group(&phb->p5ioc2.table_group,
 				pci_domain_nr(phb->hose->bus), phb->opal_id);
+		INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+		pnv_pci_link_table_and_group(phb->hose->node, 0,
+				tbl, &phb->p5ioc2.table_group);
 	}
 
-	set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
+	set_iommu_table_base(&pdev->dev, tbl);
+	iommu_add_device(&pdev->dev);
 }
 
+static const struct pci_controller_ops pnv_pci_p5ioc2_controller_ops = {
+	.dma_dev_setup = pnv_pci_dma_dev_setup,
+#ifdef CONFIG_PCI_MSI
+       .setup_msi_irqs = pnv_setup_msi_irqs,
+       .teardown_msi_irqs = pnv_teardown_msi_irqs,
+#endif
+};
+
 static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 					   void *tce_mem, u64 tce_size)
 {
@@ -103,6 +127,8 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 	u64 phb_id;
 	int64_t rc;
 	static int primary = 1;
+	struct iommu_table_group *table_group;
+	struct iommu_table *tbl;
 
 	pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
 
@@ -133,7 +159,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 	phb->hose->first_busno = 0;
 	phb->hose->last_busno = 0xff;
 	phb->hose->private_data = phb;
-	phb->hose->controller_ops = pnv_pci_controller_ops;
+	phb->hose->controller_ops = pnv_pci_p5ioc2_controller_ops;
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = PNV_PHB_P5IOC2;
@@ -172,6 +198,15 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 	pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table,
 				  tce_mem, tce_size, 0,
 				  IOMMU_PAGE_SHIFT_4K);
+	/*
+	 * We do not allocate iommu_table as we do not support
+	 * hotplug or SRIOV on P5IOC2 and therefore iommu_free_table()
+	 * should not be called for phb->p5ioc2.table_group.tables[0] ever.
+	 */
+	tbl = phb->p5ioc2.table_group.tables[0] = &phb->p5ioc2.iommu_table;
+	table_group = &phb->p5ioc2.table_group;
+	table_group->tce32_start = tbl->it_offset << tbl->it_page_shift;
+	table_group->tce32_size = tbl->it_size << tbl->it_page_shift;
 }
 
 void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index bca2aeb6e4b6..765d8ed558d0 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -45,7 +45,7 @@
 //#define cfg_dbg(fmt...)	printk(fmt)
 
 #ifdef CONFIG_PCI_MSI
-static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -94,7 +94,7 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 	return 0;
 }
 
-static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
+void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -572,80 +572,152 @@ struct pci_ops pnv_pci_ops = {
 	.write = pnv_pci_write_config,
 };
 
-static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
-			 unsigned long uaddr, enum dma_data_direction direction,
-			 struct dma_attrs *attrs, bool rm)
+static __be64 *pnv_tce(struct iommu_table *tbl, long idx)
 {
-	u64 proto_tce;
-	__be64 *tcep, *tces;
-	u64 rpn;
-
-	proto_tce = TCE_PCI_READ; // Read allowed
+	__be64 *tmp = ((__be64 *)tbl->it_base);
+	int  level = tbl->it_indirect_levels;
+	const long shift = ilog2(tbl->it_level_size);
+	unsigned long mask = (tbl->it_level_size - 1) << (level * shift);
+
+	while (level) {
+		int n = (idx & mask) >> (level * shift);
+		unsigned long tce = be64_to_cpu(tmp[n]);
+
+		tmp = __va(tce & ~(TCE_PCI_READ | TCE_PCI_WRITE));
+		idx &= ~mask;
+		mask >>= shift;
+		--level;
+	}
 
-	if (direction != DMA_TO_DEVICE)
-		proto_tce |= TCE_PCI_WRITE;
+	return tmp + idx;
+}
 
-	tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
-	rpn = __pa(uaddr) >> tbl->it_page_shift;
+int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+		unsigned long uaddr, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	u64 proto_tce = iommu_direction_to_tce_perm(direction);
+	u64 rpn = __pa(uaddr) >> tbl->it_page_shift;
+	long i;
 
-	while (npages--)
-		*(tcep++) = cpu_to_be64(proto_tce |
-				(rpn++ << tbl->it_page_shift));
+	for (i = 0; i < npages; i++) {
+		unsigned long newtce = proto_tce |
+			((rpn + i) << tbl->it_page_shift);
+		unsigned long idx = index - tbl->it_offset + i;
 
-	/* Some implementations won't cache invalid TCEs and thus may not
-	 * need that flush. We'll probably turn it_type into a bit mask
-	 * of flags if that becomes the case
-	 */
-	if (tbl->it_type & TCE_PCI_SWINV_CREATE)
-		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+		*(pnv_tce(tbl, idx)) = cpu_to_be64(newtce);
+	}
 
 	return 0;
 }
 
-static int pnv_tce_build_vm(struct iommu_table *tbl, long index, long npages,
-			    unsigned long uaddr,
-			    enum dma_data_direction direction,
-			    struct dma_attrs *attrs)
+#ifdef CONFIG_IOMMU_API
+int pnv_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction)
 {
-	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs,
-			false);
+	u64 proto_tce = iommu_direction_to_tce_perm(*direction);
+	unsigned long newtce = *hpa | proto_tce, oldtce;
+	unsigned long idx = index - tbl->it_offset;
+
+	BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl));
+
+	oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce));
+	*hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	*direction = iommu_tce_direction(oldtce);
+
+	return 0;
 }
+#endif
 
-static void pnv_tce_free(struct iommu_table *tbl, long index, long npages,
-		bool rm)
+void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
 {
-	__be64 *tcep, *tces;
+	long i;
 
-	tces = tcep = ((__be64 *)tbl->it_base) + index - tbl->it_offset;
+	for (i = 0; i < npages; i++) {
+		unsigned long idx = index - tbl->it_offset + i;
 
-	while (npages--)
-		*(tcep++) = cpu_to_be64(0);
+		*(pnv_tce(tbl, idx)) = cpu_to_be64(0);
+	}
+}
 
-	if (tbl->it_type & TCE_PCI_SWINV_FREE)
-		pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1, rm);
+unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
+{
+	return *(pnv_tce(tbl, index - tbl->it_offset));
 }
 
-static void pnv_tce_free_vm(struct iommu_table *tbl, long index, long npages)
+struct iommu_table *pnv_pci_table_alloc(int nid)
 {
-	pnv_tce_free(tbl, index, npages, false);
+	struct iommu_table *tbl;
+
+	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, nid);
+	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+
+	return tbl;
 }
 
-static unsigned long pnv_tce_get(struct iommu_table *tbl, long index)
+long pnv_pci_link_table_and_group(int node, int num,
+		struct iommu_table *tbl,
+		struct iommu_table_group *table_group)
 {
-	return ((u64 *)tbl->it_base)[index - tbl->it_offset];
+	struct iommu_table_group_link *tgl = NULL;
+
+	if (WARN_ON(!tbl || !table_group))
+		return -EINVAL;
+
+	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+			node);
+	if (!tgl)
+		return -ENOMEM;
+
+	tgl->table_group = table_group;
+	list_add_rcu(&tgl->next, &tbl->it_group_list);
+
+	table_group->tables[num] = tbl;
+
+	return 0;
 }
 
-static int pnv_tce_build_rm(struct iommu_table *tbl, long index, long npages,
-			    unsigned long uaddr,
-			    enum dma_data_direction direction,
-			    struct dma_attrs *attrs)
+static void pnv_iommu_table_group_link_free(struct rcu_head *head)
 {
-	return pnv_tce_build(tbl, index, npages, uaddr, direction, attrs, true);
+	struct iommu_table_group_link *tgl = container_of(head,
+			struct iommu_table_group_link, rcu);
+
+	kfree(tgl);
 }
 
-static void pnv_tce_free_rm(struct iommu_table *tbl, long index, long npages)
+void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
+		struct iommu_table_group *table_group)
 {
-	pnv_tce_free(tbl, index, npages, true);
+	long i;
+	bool found;
+	struct iommu_table_group_link *tgl;
+
+	if (!tbl || !table_group)
+		return;
+
+	/* Remove link to a group from table's list of attached groups */
+	found = false;
+	list_for_each_entry_rcu(tgl, &tbl->it_group_list, next) {
+		if (tgl->table_group == table_group) {
+			list_del_rcu(&tgl->next);
+			call_rcu(&tgl->rcu, pnv_iommu_table_group_link_free);
+			found = true;
+			break;
+		}
+	}
+	if (WARN_ON(!found))
+		return;
+
+	/* Clean a pointer to iommu_table in iommu_table_group::tables[] */
+	found = false;
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		if (table_group->tables[i] == tbl) {
+			table_group->tables[i] = NULL;
+			found = true;
+			break;
+		}
+	}
+	WARN_ON(!found);
 }
 
 void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
@@ -662,7 +734,7 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 	tbl->it_type = TCE_PCI;
 }
 
-static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
+void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -689,16 +761,6 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 		phb->dma_dev_setup(phb, pdev);
 }
 
-int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-
-	if (phb && phb->dma_set_mask)
-		return phb->dma_set_mask(phb, pdev, dma_mask);
-	return __dma_set_mask(&pdev->dev, dma_mask);
-}
-
 u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
@@ -714,12 +776,9 @@ void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
 
-	list_for_each_entry(hose, &hose_list, list_node) {
-		struct pnv_phb *phb = hose->private_data;
-
-		if (phb && phb->shutdown)
-			phb->shutdown(phb);
-	}
+	list_for_each_entry(hose, &hose_list, list_node)
+		if (hose->controller_ops.shutdown)
+			hose->controller_ops.shutdown(hose);
 }
 
 /* Fixup wrong class code in p7ioc and p8 root complex */
@@ -762,22 +821,7 @@ void __init pnv_pci_init(void)
 	pci_devs_phb_init();
 
 	/* Configure IOMMU DMA hooks */
-	ppc_md.tce_build = pnv_tce_build_vm;
-	ppc_md.tce_free = pnv_tce_free_vm;
-	ppc_md.tce_build_rm = pnv_tce_build_rm;
-	ppc_md.tce_free_rm = pnv_tce_free_rm;
-	ppc_md.tce_get = pnv_tce_get;
 	set_pci_dma_ops(&dma_iommu_ops);
-
-	/* Configure MSIs */
-#ifdef CONFIG_PCI_MSI
-	ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
-#endif
 }
 
 machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
-
-struct pci_controller_ops pnv_pci_controller_ops = {
-	.dma_dev_setup = pnv_pci_dma_dev_setup,
-};
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 070ee888fc95..8ef2d28aded0 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -57,8 +57,7 @@ struct pnv_ioda_pe {
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	int			tce32_seg;
 	int			tce32_segcount;
-	struct iommu_table	*tce32_table;
-	phys_addr_t		tce_inval_reg_phys;
+	struct iommu_table_group table_group;
 
 	/* 64-bit TCE bypass region */
 	bool			tce_bypass_enabled;
@@ -106,13 +105,10 @@ struct pnv_phb {
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
-	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
-			    u64 dma_mask);
 	u64 (*dma_get_required_mask)(struct pnv_phb *phb,
 				     struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
-	void (*shutdown)(struct pnv_phb *phb);
 	int (*init_m64)(struct pnv_phb *phb);
 	void (*reserve_m64_pe)(struct pnv_phb *phb);
 	int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all);
@@ -123,6 +119,7 @@ struct pnv_phb {
 	union {
 		struct {
 			struct iommu_table iommu_table;
+			struct iommu_table_group table_group;
 		} p5ioc2;
 
 		struct {
@@ -186,6 +183,12 @@ struct pnv_phb {
 			 * boot for resource allocation purposes
 			 */
 			struct list_head	pe_dma_list;
+
+			/* TCE cache invalidate registers (physical and
+			 * remapped)
+			 */
+			phys_addr_t		tce_inval_reg_phys;
+			__be64 __iomem		*tce_inval_reg;
 		} ioda;
 	};
 
@@ -200,6 +203,13 @@ struct pnv_phb {
 };
 
 extern struct pci_ops pnv_pci_ops;
+extern int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+		unsigned long uaddr, enum dma_data_direction direction,
+		struct dma_attrs *attrs);
+extern void pnv_tce_free(struct iommu_table *tbl, long index, long npages);
+extern int pnv_tce_xchg(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction);
+extern unsigned long pnv_tce_get(struct iommu_table *tbl, long index);
 
 void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
 				unsigned char *log_buff);
@@ -207,6 +217,13 @@ int pnv_pci_cfg_read(struct pci_dn *pdn,
 		     int where, int size, u32 *val);
 int pnv_pci_cfg_write(struct pci_dn *pdn,
 		      int where, int size, u32 val);
+extern struct iommu_table *pnv_pci_table_alloc(int nid);
+
+extern long pnv_pci_link_table_and_group(int node, int num,
+		struct iommu_table *tbl,
+		struct iommu_table_group *table_group);
+extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
+		struct iommu_table_group *table_group);
 extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 				      void *tce_mem, u64 tce_size,
 				      u64 dma_offset, unsigned page_shift);
@@ -218,4 +235,8 @@ extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
+extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
+extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
+extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
+
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 826d2c9bea56..9269e30e4ca0 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -12,29 +12,24 @@ struct pci_dev;
 #ifdef CONFIG_PCI
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
-extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
 extern u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
 
-static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
-{
-	return -ENODEV;
-}
-
 static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
 {
 	return 0;
 }
 #endif
 
-extern struct pci_controller_ops pnv_pci_controller_ops;
-
 extern u32 pnv_get_supported_cpuidle_states(void);
 
 extern void pnv_lpc_init(void);
 
+extern void opal_handle_events(uint64_t events);
+extern void opal_event_shutdown(void);
+
 bool cpu_core_split_required(void);
 
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 16fdcb23f4c3..53737e019ae3 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -35,12 +35,8 @@
 #include <asm/opal.h>
 #include <asm/kexec.h>
 #include <asm/smp.h>
-#include <asm/cputhreads.h>
-#include <asm/cpuidle.h>
-#include <asm/code-patching.h>
 
 #include "powernv.h"
-#include "subcore.h"
 
 static void __init pnv_setup_arch(void)
 {
@@ -111,7 +107,7 @@ static void pnv_prepare_going_down(void)
 	 * Disable all notifiers from OPAL, we can't
 	 * service interrupts anymore anyway
 	 */
-	opal_notifier_disable();
+	opal_event_shutdown();
 
 	/* Soft disable interrupts */
 	local_irq_disable();
@@ -169,13 +165,6 @@ static void pnv_progress(char *s, unsigned short hex)
 {
 }
 
-static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (dev_is_pci(dev))
-		return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask);
-	return __dma_set_mask(dev, dma_mask);
-}
-
 static u64 pnv_dma_get_required_mask(struct device *dev)
 {
 	if (dev_is_pci(dev))
@@ -277,173 +266,6 @@ static void __init pnv_setup_machdep_opal(void)
 	ppc_md.handle_hmi_exception = opal_handle_hmi_exception;
 }
 
-static u32 supported_cpuidle_states;
-
-int pnv_save_sprs_for_winkle(void)
-{
-	int cpu;
-	int rc;
-
-	/*
-	 * hid0, hid1, hid4, hid5, hmeer and lpcr values are symmetric accross
-	 * all cpus at boot. Get these reg values of current cpu and use the
-	 * same accross all cpus.
-	 */
-	uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
-	uint64_t hid0_val = mfspr(SPRN_HID0);
-	uint64_t hid1_val = mfspr(SPRN_HID1);
-	uint64_t hid4_val = mfspr(SPRN_HID4);
-	uint64_t hid5_val = mfspr(SPRN_HID5);
-	uint64_t hmeer_val = mfspr(SPRN_HMEER);
-
-	for_each_possible_cpu(cpu) {
-		uint64_t pir = get_hard_smp_processor_id(cpu);
-		uint64_t hsprg0_val = (uint64_t)&paca[cpu];
-
-		/*
-		 * HSPRG0 is used to store the cpu's pointer to paca. Hence last
-		 * 3 bits are guaranteed to be 0. Program slw to restore HSPRG0
-		 * with 63rd bit set, so that when a thread wakes up at 0x100 we
-		 * can use this bit to distinguish between fastsleep and
-		 * deep winkle.
-		 */
-		hsprg0_val |= 1;
-
-		rc = opal_slw_set_reg(pir, SPRN_HSPRG0, hsprg0_val);
-		if (rc != 0)
-			return rc;
-
-		rc = opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
-		if (rc != 0)
-			return rc;
-
-		/* HIDs are per core registers */
-		if (cpu_thread_in_core(cpu) == 0) {
-
-			rc = opal_slw_set_reg(pir, SPRN_HMEER, hmeer_val);
-			if (rc != 0)
-				return rc;
-
-			rc = opal_slw_set_reg(pir, SPRN_HID0, hid0_val);
-			if (rc != 0)
-				return rc;
-
-			rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val);
-			if (rc != 0)
-				return rc;
-
-			rc = opal_slw_set_reg(pir, SPRN_HID4, hid4_val);
-			if (rc != 0)
-				return rc;
-
-			rc = opal_slw_set_reg(pir, SPRN_HID5, hid5_val);
-			if (rc != 0)
-				return rc;
-		}
-	}
-
-	return 0;
-}
-
-static void pnv_alloc_idle_core_states(void)
-{
-	int i, j;
-	int nr_cores = cpu_nr_cores();
-	u32 *core_idle_state;
-
-	/*
-	 * core_idle_state - First 8 bits track the idle state of each thread
-	 * of the core. The 8th bit is the lock bit. Initially all thread bits
-	 * are set. They are cleared when the thread enters deep idle state
-	 * like sleep and winkle. Initially the lock bit is cleared.
-	 * The lock bit has 2 purposes
-	 * a. While the first thread is restoring core state, it prevents
-	 * other threads in the core from switching to process context.
-	 * b. While the last thread in the core is saving the core state, it
-	 * prevents a different thread from waking up.
-	 */
-	for (i = 0; i < nr_cores; i++) {
-		int first_cpu = i * threads_per_core;
-		int node = cpu_to_node(first_cpu);
-
-		core_idle_state = kmalloc_node(sizeof(u32), GFP_KERNEL, node);
-		*core_idle_state = PNV_CORE_IDLE_THREAD_BITS;
-
-		for (j = 0; j < threads_per_core; j++) {
-			int cpu = first_cpu + j;
-
-			paca[cpu].core_idle_state_ptr = core_idle_state;
-			paca[cpu].thread_idle_state = PNV_THREAD_RUNNING;
-			paca[cpu].thread_mask = 1 << j;
-		}
-	}
-
-	update_subcore_sibling_mask();
-
-	if (supported_cpuidle_states & OPAL_PM_WINKLE_ENABLED)
-		pnv_save_sprs_for_winkle();
-}
-
-u32 pnv_get_supported_cpuidle_states(void)
-{
-	return supported_cpuidle_states;
-}
-EXPORT_SYMBOL_GPL(pnv_get_supported_cpuidle_states);
-
-static int __init pnv_init_idle_states(void)
-{
-	struct device_node *power_mgt;
-	int dt_idle_states;
-	u32 *flags;
-	int i;
-
-	supported_cpuidle_states = 0;
-
-	if (cpuidle_disable != IDLE_NO_OVERRIDE)
-		goto out;
-
-	if (!firmware_has_feature(FW_FEATURE_OPALv3))
-		goto out;
-
-	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
-	if (!power_mgt) {
-		pr_warn("opal: PowerMgmt Node not found\n");
-		goto out;
-	}
-	dt_idle_states = of_property_count_u32_elems(power_mgt,
-			"ibm,cpu-idle-state-flags");
-	if (dt_idle_states < 0) {
-		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
-		goto out;
-	}
-
-	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
-	if (of_property_read_u32_array(power_mgt,
-			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
-		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
-		goto out_free;
-	}
-
-	for (i = 0; i < dt_idle_states; i++)
-		supported_cpuidle_states |= flags[i];
-
-	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
-		patch_instruction(
-			(unsigned int *)pnv_fastsleep_workaround_at_entry,
-			PPC_INST_NOP);
-		patch_instruction(
-			(unsigned int *)pnv_fastsleep_workaround_at_exit,
-			PPC_INST_NOP);
-	}
-	pnv_alloc_idle_core_states();
-out_free:
-	kfree(flags);
-out:
-	return 0;
-}
-
-subsys_initcall(pnv_init_idle_states);
-
 static int __init pnv_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
@@ -492,7 +314,6 @@ define_machine(powernv) {
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
-	.dma_set_mask		= pnv_dma_set_mask,
 	.dma_get_required_mask	= pnv_dma_get_required_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 019d34aaf054..47d9cebe7159 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -421,11 +421,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 		return -ENODEV;
 
 	dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
+	of_node_put(parent);
 	if (!dn)
 		return -EINVAL;
 
-	of_node_put(parent);
-
 	rc = dlpar_attach_node(dn);
 	if (rc) {
 		dlpar_release_drc(drc_index);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 2039397cc75d..1ba55d0bb449 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -519,7 +519,7 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option)
 /**
  * pseries_eeh_wait_state - Wait for PE state
  * @pe: EEH PE
- * @max_wait: maximal period in microsecond
+ * @max_wait: maximal period in millisecond
  *
  * Wait for the state of associated PE. It might take some time
  * to retrieve the PE's state.
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 61d5a17f45c0..10510dea16b3 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,6 +36,8 @@
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
 #include <linux/of.h>
+#include <linux/iommu.h>
+#include <linux/rculist.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -51,6 +53,73 @@
 
 #include "pseries.h"
 
+static struct iommu_table_group *iommu_pseries_alloc_group(int node)
+{
+	struct iommu_table_group *table_group = NULL;
+	struct iommu_table *tbl = NULL;
+	struct iommu_table_group_link *tgl = NULL;
+
+	table_group = kzalloc_node(sizeof(struct iommu_table_group), GFP_KERNEL,
+			   node);
+	if (!table_group)
+		goto fail_exit;
+
+	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, node);
+	if (!tbl)
+		goto fail_exit;
+
+	tgl = kzalloc_node(sizeof(struct iommu_table_group_link), GFP_KERNEL,
+			node);
+	if (!tgl)
+		goto fail_exit;
+
+	INIT_LIST_HEAD_RCU(&tbl->it_group_list);
+	tgl->table_group = table_group;
+	list_add_rcu(&tgl->next, &tbl->it_group_list);
+
+	table_group->tables[0] = tbl;
+
+	return table_group;
+
+fail_exit:
+	kfree(tgl);
+	kfree(table_group);
+	kfree(tbl);
+
+	return NULL;
+}
+
+static void iommu_pseries_free_group(struct iommu_table_group *table_group,
+		const char *node_name)
+{
+	struct iommu_table *tbl;
+#ifdef CONFIG_IOMMU_API
+	struct iommu_table_group_link *tgl;
+#endif
+
+	if (!table_group)
+		return;
+
+	tbl = table_group->tables[0];
+#ifdef CONFIG_IOMMU_API
+	tgl = list_first_entry_or_null(&tbl->it_group_list,
+			struct iommu_table_group_link, next);
+
+	WARN_ON_ONCE(!tgl);
+	if (tgl) {
+		list_del_rcu(&tgl->next);
+		kfree(tgl);
+	}
+	if (table_group->group) {
+		iommu_group_put(table_group->group);
+		BUG_ON(table_group->group);
+	}
+#endif
+	iommu_free_table(tbl, node_name);
+
+	kfree(table_group);
+}
+
 static void tce_invalidate_pSeries_sw(struct iommu_table *tbl,
 				      __be64 *startp, __be64 *endp)
 {
@@ -193,7 +262,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	unsigned long flags;
 
-	if (npages == 1) {
+	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 		                           direction, attrs);
 	}
@@ -285,6 +354,9 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
 {
 	u64 rc;
 
+	if (!firmware_has_feature(FW_FEATURE_MULTITCE))
+		return tce_free_pSeriesLP(tbl, tcenum, npages);
+
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
 	if (rc && printk_ratelimit()) {
@@ -460,7 +532,6 @@ static int tce_setrange_multi_pSeriesLP_walk(unsigned long start_pfn,
 	return tce_setrange_multi_pSeriesLP(start_pfn, num_pfn, arg);
 }
 
-
 #ifdef CONFIG_PCI
 static void iommu_table_setparms(struct pci_controller *phb,
 				 struct device_node *dn,
@@ -546,6 +617,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	tbl->it_size = size >> tbl->it_page_shift;
 }
 
+struct iommu_table_ops iommu_table_pseries_ops = {
+	.set = tce_build_pSeries,
+	.clear = tce_free_pSeries,
+	.get = tce_get_pseries
+};
+
 static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 {
 	struct device_node *dn;
@@ -610,12 +687,13 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	pci->phb->dma_window_size = 0x8000000ul;
 	pci->phb->dma_window_base_cur = 0x8000000ul;
 
-	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-			   pci->phb->node);
+	pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+	tbl = pci->table_group->tables[0];
 
 	iommu_table_setparms(pci->phb, dn, tbl);
-	pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
-	iommu_register_group(tbl, pci_domain_nr(bus), 0);
+	tbl->it_ops = &iommu_table_pseries_ops;
+	iommu_init_table(tbl, pci->phb->node);
+	iommu_register_group(pci->table_group, pci_domain_nr(bus), 0);
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -625,6 +703,11 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 	pr_debug("ISA/IDE, window size is 0x%llx\n", pci->phb->dma_window_size);
 }
 
+struct iommu_table_ops iommu_table_lpar_multi_ops = {
+	.set = tce_buildmulti_pSeriesLP,
+	.clear = tce_freemulti_pSeriesLP,
+	.get = tce_get_pSeriesLP
+};
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 {
@@ -653,15 +736,17 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	ppci = PCI_DN(pdn);
 
 	pr_debug("  parent is %s, iommu_table: 0x%p\n",
-		 pdn->full_name, ppci->iommu_table);
+		 pdn->full_name, ppci->table_group);
 
-	if (!ppci->iommu_table) {
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   ppci->phb->node);
+	if (!ppci->table_group) {
+		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
+		tbl = ppci->table_group->tables[0];
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
-		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
-		iommu_register_group(tbl, pci_domain_nr(bus), 0);
-		pr_debug("  created table: %p\n", ppci->iommu_table);
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+		iommu_init_table(tbl, ppci->phb->node);
+		iommu_register_group(ppci->table_group,
+				pci_domain_nr(bus), 0);
+		pr_debug("  created table: %p\n", ppci->table_group);
 	}
 }
 
@@ -683,13 +768,15 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		struct pci_controller *phb = PCI_DN(dn)->phb;
 
 		pr_debug(" --> first child, no bridge. Allocating iommu table.\n");
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   phb->node);
+		PCI_DN(dn)->table_group = iommu_pseries_alloc_group(phb->node);
+		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
-		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
-		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
-		set_iommu_table_base_and_group(&dev->dev,
-					       PCI_DN(dn)->iommu_table);
+		tbl->it_ops = &iommu_table_pseries_ops;
+		iommu_init_table(tbl, phb->node);
+		iommu_register_group(PCI_DN(dn)->table_group,
+				pci_domain_nr(phb->bus), 0);
+		set_iommu_table_base(&dev->dev, tbl);
+		iommu_add_device(&dev->dev);
 		return;
 	}
 
@@ -697,13 +784,14 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 	 * an already allocated iommu table is found and use that.
 	 */
 
-	while (dn && PCI_DN(dn) && PCI_DN(dn)->iommu_table == NULL)
+	while (dn && PCI_DN(dn) && PCI_DN(dn)->table_group == NULL)
 		dn = dn->parent;
 
-	if (dn && PCI_DN(dn))
-		set_iommu_table_base_and_group(&dev->dev,
-					       PCI_DN(dn)->iommu_table);
-	else
+	if (dn && PCI_DN(dn)) {
+		set_iommu_table_base(&dev->dev,
+				PCI_DN(dn)->table_group->tables[0]);
+		iommu_add_device(&dev->dev);
+	} else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
 }
@@ -1088,7 +1176,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %s\n", dn->full_name);
 
-	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+	for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
 	     pdn = pdn->parent) {
 		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
 		if (dma_window)
@@ -1104,18 +1192,21 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	pr_debug("  parent is %s\n", pdn->full_name);
 
 	pci = PCI_DN(pdn);
-	if (!pci->iommu_table) {
-		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
-				   pci->phb->node);
+	if (!pci->table_group) {
+		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
+		tbl = pci->table_group->tables[0];
 		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
-		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
-		iommu_register_group(tbl, pci_domain_nr(pci->phb->bus), 0);
-		pr_debug("  created table: %p\n", pci->iommu_table);
+		tbl->it_ops = &iommu_table_lpar_multi_ops;
+		iommu_init_table(tbl, pci->phb->node);
+		iommu_register_group(pci->table_group,
+				pci_domain_nr(pci->phb->bus), 0);
+		pr_debug("  created table: %p\n", pci->table_group);
 	} else {
-		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
+		pr_debug("  found DMA window, table: %p\n", pci->table_group);
 	}
 
-	set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
+	set_iommu_table_base(&dev->dev, pci->table_group->tables[0]);
+	iommu_add_device(&dev->dev);
 }
 
 static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
@@ -1145,7 +1236,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
 		 * search upwards in the tree until we either hit a dma-window
 		 * property, OR find a parent with a table already allocated.
 		 */
-		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->iommu_table;
+		for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group;
 				pdn = pdn->parent) {
 			dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
 			if (dma_window)
@@ -1189,7 +1280,7 @@ static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
 		dn = pci_device_to_OF_node(pdev);
 
 		/* search upwards for ibm,dma-window */
-		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+		for (; dn && PCI_DN(dn) && !PCI_DN(dn)->table_group;
 				dn = dn->parent)
 			if (of_get_property(dn, "ibm,dma-window", NULL))
 				break;
@@ -1269,8 +1360,9 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 		 * the device node.
 		 */
 		remove_ddw(np, false);
-		if (pci && pci->iommu_table)
-			iommu_free_table(pci->iommu_table, np->full_name);
+		if (pci && pci->table_group)
+			iommu_pseries_free_group(pci->table_group,
+					np->full_name);
 
 		spin_lock(&direct_window_list_lock);
 		list_for_each_entry(window, &direct_window_list, list) {
@@ -1300,22 +1392,11 @@ void iommu_init_early_pSeries(void)
 		return;
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
-		if (firmware_has_feature(FW_FEATURE_MULTITCE)) {
-			ppc_md.tce_build = tce_buildmulti_pSeriesLP;
-			ppc_md.tce_free	 = tce_freemulti_pSeriesLP;
-		} else {
-			ppc_md.tce_build = tce_build_pSeriesLP;
-			ppc_md.tce_free	 = tce_free_pSeriesLP;
-		}
-		ppc_md.tce_get   = tce_get_pSeriesLP;
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
 		ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
 		ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
 	} else {
-		ppc_md.tce_build = tce_build_pSeries;
-		ppc_md.tce_free  = tce_free_pSeries;
-		ppc_md.tce_get   = tce_get_pseries;
 		pseries_pci_controller_ops.dma_bus_setup = pci_dma_bus_setup_pSeries;
 		pseries_pci_controller_ops.dma_dev_setup = pci_dma_dev_setup_pSeries;
 	}
@@ -1333,8 +1414,6 @@ static int __init disable_multitce(char *str)
 	    firmware_has_feature(FW_FEATURE_LPAR) &&
 	    firmware_has_feature(FW_FEATURE_MULTITCE)) {
 		printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
-		ppc_md.tce_build = tce_build_pSeriesLP;
-		ppc_md.tce_free	 = tce_free_pSeriesLP;
 		powerpc_firmware_features &= ~FW_FEATURE_MULTITCE;
 	}
 	return 1;
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index c8d24f9a6948..c22bb647cce6 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -18,6 +18,8 @@
 #include <asm/ppc-pci.h>
 #include <asm/machdep.h>
 
+#include "pseries.h"
+
 static int query_token, change_token;
 
 #define RTAS_QUERY_FN		0
@@ -505,6 +507,8 @@ static void rtas_msi_pci_irq_fixup(struct pci_dev *pdev)
 
 static int rtas_msi_init(void)
 {
+	struct pci_controller *phb;
+
 	query_token  = rtas_token("ibm,query-interrupt-source-number");
 	change_token = rtas_token("ibm,change-msi");
 
@@ -516,9 +520,15 @@ static int rtas_msi_init(void)
 
 	pr_debug("rtas_msi: Registering RTAS MSI callbacks.\n");
 
-	WARN_ON(ppc_md.setup_msi_irqs);
-	ppc_md.setup_msi_irqs = rtas_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = rtas_teardown_msi_irqs;
+	WARN_ON(pseries_pci_controller_ops.setup_msi_irqs);
+	pseries_pci_controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
+	pseries_pci_controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
+
+	list_for_each_entry(phb, &hose_list, list_node) {
+		WARN_ON(phb->controller_ops.setup_msi_irqs);
+		phb->controller_ops.setup_msi_irqs = rtas_setup_msi_irqs;
+		phb->controller_ops.teardown_msi_irqs = rtas_teardown_msi_irqs;
+	}
 
 	WARN_ON(ppc_md.pci_irq_fixup);
 	ppc_md.pci_irq_fixup = rtas_msi_pci_irq_fixup;
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f7cb2a1b01fa..5b492a6438ff 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -2,7 +2,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ccflags-$(CONFIG_PPC64)		:= $(NO_MINIMAL_TOC)
 
-mpic-msi-obj-$(CONFIG_PCI_MSI)	+= mpic_msi.o mpic_u3msi.o mpic_pasemi_msi.o
+mpic-msi-obj-$(CONFIG_PCI_MSI)	+= mpic_msi.o mpic_u3msi.o
 obj-$(CONFIG_MPIC)		+= mpic.o $(mpic-msi-obj-y)
 obj-$(CONFIG_MPIC_TIMER)        += mpic_timer.o
 obj-$(CONFIG_FSL_MPIC_TIMER_WAKEUP)	+= fsl_mpic_timer_wakeup.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index d00a5663e312..90bcdfeedf48 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -286,6 +286,12 @@ static int __init dart_init(struct device_node *dart_node)
 	return 0;
 }
 
+static struct iommu_table_ops iommu_dart_ops = {
+	.set = dart_build,
+	.clear = dart_free,
+	.flush = dart_flush,
+};
+
 static void iommu_table_dart_setup(void)
 {
 	iommu_table_dart.it_busno = 0;
@@ -298,6 +304,7 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_base = (unsigned long)dart_vbase;
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
+	iommu_table_dart.it_ops = &iommu_dart_ops;
 	iommu_init_table(&iommu_table_dart, -1);
 
 	/* Reserve the last page of the DART to avoid possible prefetch
@@ -386,11 +393,6 @@ void __init iommu_init_early_dart(struct pci_controller_ops *controller_ops)
 	if (dart_init(dn) != 0)
 		goto bail;
 
-	/* Setup low level TCE operations for the core IOMMU code */
-	ppc_md.tce_build = dart_build;
-	ppc_md.tce_free  = dart_free;
-	ppc_md.tce_flush = dart_flush;
-
 	/* Setup bypass if supported */
 	if (dart_is_u4)
 		ppc_md.dma_set_mask = dart_dma_set_mask;
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index f086c6f22dc9..5236e5427c38 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -405,6 +405,7 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	const struct fsl_msi_feature *features;
 	int len;
 	u32 offset;
+	struct pci_controller *phb;
 
 	match = of_match_device(fsl_of_msi_ids, &dev->dev);
 	if (!match)
@@ -541,14 +542,20 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 
 	list_add_tail(&msi->list, &msi_head);
 
-	/* The multiple setting ppc_md.setup_msi_irqs will not harm things */
-	if (!ppc_md.setup_msi_irqs) {
-		ppc_md.setup_msi_irqs = fsl_setup_msi_irqs;
-		ppc_md.teardown_msi_irqs = fsl_teardown_msi_irqs;
-	} else if (ppc_md.setup_msi_irqs != fsl_setup_msi_irqs) {
-		dev_err(&dev->dev, "Different MSI driver already installed!\n");
-		err = -ENODEV;
-		goto error_out;
+	/*
+	 * Apply the MSI ops to all the controllers.
+	 * It doesn't hurt to reassign the same ops,
+	 * but bail out if we find another MSI driver.
+	 */
+	list_for_each_entry(phb, &hose_list, list_node) {
+		if (!phb->controller_ops.setup_msi_irqs) {
+			phb->controller_ops.setup_msi_irqs = fsl_setup_msi_irqs;
+			phb->controller_ops.teardown_msi_irqs = fsl_teardown_msi_irqs;
+		} else if (phb->controller_ops.setup_msi_irqs != fsl_setup_msi_irqs) {
+			dev_err(&dev->dev, "Different MSI driver already installed!\n");
+			err = -ENODEV;
+			goto error_out;
+		}
 	}
 	return 0;
 error_out:
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 45598da0b321..31c33475c7b7 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -204,7 +204,7 @@ static int i8259_host_xlate(struct irq_domain *h, struct device_node *ct,
 	return 0;
 }
 
-static struct irq_domain_ops i8259_host_ops = {
+static const struct irq_domain_ops i8259_host_ops = {
 	.match = i8259_host_match,
 	.map = i8259_host_map,
 	.xlate = i8259_host_xlate,
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index b28733727ed3..d78f1364b639 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -691,7 +691,7 @@ static int ipic_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops ipic_host_ops = {
+static const struct irq_domain_ops ipic_host_ops = {
 	.match	= ipic_host_match,
 	.map	= ipic_host_map,
 	.xlate	= irq_domain_xlate_onetwocell,
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index c4828c0be5bd..d93a78be4346 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -120,7 +120,7 @@ static int mpc8xx_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
 }
 
 
-static struct irq_domain_ops mpc8xx_pic_host_ops = {
+static const struct irq_domain_ops mpc8xx_pic_host_ops = {
 	.map = mpc8xx_pic_host_map,
 	.xlate = mpc8xx_pic_host_xlate,
 };
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index b2b8447a227a..c8e73332eaad 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1195,7 +1195,7 @@ static void mpic_cascade(unsigned int irq, struct irq_desc *desc)
 	chip->irq_eoi(&desc->irq_data);
 }
 
-static struct irq_domain_ops mpic_host_ops = {
+static const struct irq_domain_ops mpic_host_ops = {
 	.match = mpic_host_match,
 	.map = mpic_host_map,
 	.xlate = mpic_host_xlate,
diff --git a/arch/powerpc/sysdev/mpic.h b/arch/powerpc/sysdev/mpic.h
index 24bf07a63924..32971a41853b 100644
--- a/arch/powerpc/sysdev/mpic.h
+++ b/arch/powerpc/sysdev/mpic.h
@@ -15,7 +15,6 @@
 extern void mpic_msi_reserve_hwirq(struct mpic *mpic, irq_hw_number_t hwirq);
 extern int mpic_msi_init_allocator(struct mpic *mpic);
 extern int mpic_u3msi_init(struct mpic *mpic);
-extern int mpic_pasemi_msi_init(struct mpic *mpic);
 #else
 static inline void mpic_msi_reserve_hwirq(struct mpic *mpic,
 					  irq_hw_number_t hwirq)
@@ -27,11 +26,12 @@ static inline int mpic_u3msi_init(struct mpic *mpic)
 {
 	return -1;
 }
+#endif
 
-static inline int mpic_pasemi_msi_init(struct mpic *mpic)
-{
-	return -1;
-}
+#if defined(CONFIG_PCI_MSI) && defined(CONFIG_PPC_PASEMI)
+int mpic_pasemi_msi_init(struct mpic *mpic);
+#else
+static inline int mpic_pasemi_msi_init(struct mpic *mpic) { return -1; }
 #endif
 
 extern int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type);
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index b2cef1809389..fc46ef3b816e 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -181,6 +181,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 int mpic_u3msi_init(struct mpic *mpic)
 {
 	int rc;
+	struct pci_controller *phb;
 
 	rc = mpic_msi_init_allocator(mpic);
 	if (rc) {
@@ -193,9 +194,11 @@ int mpic_u3msi_init(struct mpic *mpic)
 	BUG_ON(msi_mpic);
 	msi_mpic = mpic;
 
-	WARN_ON(ppc_md.setup_msi_irqs);
-	ppc_md.setup_msi_irqs = u3msi_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = u3msi_teardown_msi_irqs;
+	list_for_each_entry(phb, &hose_list, list_node) {
+		WARN_ON(phb->controller_ops.setup_msi_irqs);
+		phb->controller_ops.setup_msi_irqs = u3msi_setup_msi_irqs;
+		phb->controller_ops.teardown_msi_irqs = u3msi_teardown_msi_irqs;
+	}
 
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c
index 8848e99a83f2..0f842dd16bcd 100644
--- a/arch/powerpc/sysdev/mv64x60_pic.c
+++ b/arch/powerpc/sysdev/mv64x60_pic.c
@@ -223,7 +223,7 @@ static int mv64x60_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops mv64x60_host_ops = {
+static const struct irq_domain_ops mv64x60_host_ops = {
 	.map   = mv64x60_host_map,
 };
 
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index f366d2d4c079..2bc33674ebfc 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -128,6 +128,7 @@ static int hsta_msi_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct resource *mem;
 	int irq, ret, irq_count;
+	struct pci_controller *phb;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (IS_ERR(mem)) {
@@ -171,8 +172,10 @@ static int hsta_msi_probe(struct platform_device *pdev)
 		}
 	}
 
-	ppc_md.setup_msi_irqs = hsta_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = hsta_teardown_msi_irqs;
+	list_for_each_entry(phb, &hose_list, list_node) {
+		phb->controller_ops.setup_msi_irqs = hsta_setup_msi_irqs;
+		phb->controller_ops.teardown_msi_irqs = hsta_teardown_msi_irqs;
+	}
 	return 0;
 
 out2:
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 6e2e6aa378bb..6eb21f2ea585 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -218,6 +218,7 @@ static int ppc4xx_msi_probe(struct platform_device *dev)
 	struct ppc4xx_msi *msi;
 	struct resource res;
 	int err = 0;
+	struct pci_controller *phb;
 
 	dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n");
 
@@ -250,8 +251,10 @@ static int ppc4xx_msi_probe(struct platform_device *dev)
 	}
 	ppc4xx_msi = *msi;
 
-	ppc_md.setup_msi_irqs = ppc4xx_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
+	list_for_each_entry(phb, &hose_list, list_node) {
+		phb->controller_ops.setup_msi_irqs = ppc4xx_setup_msi_irqs;
+		phb->controller_ops.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
+	}
 	return err;
 
 error_out:
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 543765e1ef14..6512cd8caa51 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -271,7 +271,7 @@ static int qe_ic_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops qe_ic_host_ops = {
+static const struct irq_domain_ops qe_ic_host_ops = {
 	.match = qe_ic_host_match,
 	.map = qe_ic_host_map,
 	.xlate = irq_domain_xlate_onetwocell,
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 188012c58f7f..57b54476e747 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -397,7 +397,7 @@ static int pci_irq_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops pci_irq_domain_ops = {
+static const struct irq_domain_ops pci_irq_domain_ops = {
 	.map = pci_irq_host_map,
 	.xlate = pci_irq_host_xlate,
 };
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 7c37157d4c24..d77345338671 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -189,7 +189,7 @@ static int uic_host_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops uic_host_ops = {
+static const struct irq_domain_ops uic_host_ops = {
 	.map	= uic_host_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
@@ -198,7 +198,7 @@ void uic_irq_cascade(unsigned int virq, struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irq_data *idata = irq_desc_get_irq_data(desc);
-	struct uic *uic = irq_get_handler_data(virq);
+	struct uic *uic = irq_desc_get_handler_data(desc);
 	u32 msr;
 	int src;
 	int subvirq;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 2fc4cf1b7557..eae32654bdf2 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -147,12 +147,16 @@ static void icp_native_cause_ipi(int cpu, unsigned long data)
 {
 	kvmppc_set_host_ipi(cpu, 1);
 #ifdef CONFIG_PPC_DOORBELL
-	if (cpu_has_feature(CPU_FTR_DBELL) &&
-	    (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id()))))
-		doorbell_cause_ipi(cpu, data);
-	else
+	if (cpu_has_feature(CPU_FTR_DBELL)) {
+		if (cpumask_test_cpu(cpu, cpu_sibling_mask(get_cpu()))) {
+			doorbell_cause_ipi(cpu, data);
+			put_cpu();
+			return;
+		}
+		put_cpu();
+	}
 #endif
-		icp_native_set_qirr(cpu, IPI_PRIORITY);
+	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
 /*
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 878a54036a25..08c248eb491b 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -227,7 +227,7 @@ void xics_migrate_irqs_away(void)
 
 		/* Locate interrupt server */
 		server = -1;
-		ics = irq_get_chip_data(virq);
+		ics = irq_desc_get_chip_data(desc);
 		if (ics)
 			server = ics->get_server(ics, irq);
 		if (server < 0) {
@@ -360,7 +360,7 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct,
 	return 0;
 }
 
-static struct irq_domain_ops xics_host_ops = {
+static const struct irq_domain_ops xics_host_ops = {
 	.match = xics_host_match,
 	.map = xics_host_map,
 	.xlate = xics_host_xlate,
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 56f0524e47a6..43b8b275bc5c 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -179,7 +179,7 @@ static int xilinx_intc_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops xilinx_intc_ops = {
+static const struct irq_domain_ops xilinx_intc_ops = {
 	.map = xilinx_intc_map,
 	.xlate = xilinx_intc_xlate,
 };
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 7940dc90e80b..b258110da952 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -16,11 +16,12 @@
 #define GHASH_DIGEST_SIZE	16
 
 struct ghash_ctx {
-	u8 icv[16];
-	u8 key[16];
+	u8 key[GHASH_BLOCK_SIZE];
 };
 
 struct ghash_desc_ctx {
+	u8 icv[GHASH_BLOCK_SIZE];
+	u8 key[GHASH_BLOCK_SIZE];
 	u8 buffer[GHASH_BLOCK_SIZE];
 	u32 bytes;
 };
@@ -28,8 +29,10 @@ struct ghash_desc_ctx {
 static int ghash_init(struct shash_desc *desc)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 
 	memset(dctx, 0, sizeof(*dctx));
+	memcpy(dctx->key, ctx->key, GHASH_BLOCK_SIZE);
 
 	return 0;
 }
@@ -45,7 +48,6 @@ static int ghash_setkey(struct crypto_shash *tfm,
 	}
 
 	memcpy(ctx->key, key, GHASH_BLOCK_SIZE);
-	memset(ctx->icv, 0, GHASH_BLOCK_SIZE);
 
 	return 0;
 }
@@ -54,7 +56,6 @@ static int ghash_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	unsigned int n;
 	u8 *buf = dctx->buffer;
 	int ret;
@@ -70,7 +71,7 @@ static int ghash_update(struct shash_desc *desc,
 		src += n;
 
 		if (!dctx->bytes) {
-			ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf,
+			ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf,
 					      GHASH_BLOCK_SIZE);
 			if (ret != GHASH_BLOCK_SIZE)
 				return -EIO;
@@ -79,7 +80,7 @@ static int ghash_update(struct shash_desc *desc,
 
 	n = srclen & ~(GHASH_BLOCK_SIZE - 1);
 	if (n) {
-		ret = crypt_s390_kimd(KIMD_GHASH, ctx, src, n);
+		ret = crypt_s390_kimd(KIMD_GHASH, dctx, src, n);
 		if (ret != n)
 			return -EIO;
 		src += n;
@@ -94,7 +95,7 @@ static int ghash_update(struct shash_desc *desc,
 	return 0;
 }
 
-static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static int ghash_flush(struct ghash_desc_ctx *dctx)
 {
 	u8 *buf = dctx->buffer;
 	int ret;
@@ -104,24 +105,24 @@ static int ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
 
 		memset(pos, 0, dctx->bytes);
 
-		ret = crypt_s390_kimd(KIMD_GHASH, ctx, buf, GHASH_BLOCK_SIZE);
+		ret = crypt_s390_kimd(KIMD_GHASH, dctx, buf, GHASH_BLOCK_SIZE);
 		if (ret != GHASH_BLOCK_SIZE)
 			return -EIO;
+
+		dctx->bytes = 0;
 	}
 
-	dctx->bytes = 0;
 	return 0;
 }
 
 static int ghash_final(struct shash_desc *desc, u8 *dst)
 {
 	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
 	int ret;
 
-	ret = ghash_flush(ctx, dctx);
+	ret = ghash_flush(dctx);
 	if (!ret)
-		memcpy(dst, ctx->icv, GHASH_BLOCK_SIZE);
+		memcpy(dst, dctx->icv, GHASH_BLOCK_SIZE);
 	return ret;
 }
 
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 1f374b39a4ec..9d5192c94963 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -125,7 +125,7 @@ static int generate_entropy(u8 *ebuf, size_t nbytes)
 		/* fill page with urandom bytes */
 		get_random_bytes(pg, PAGE_SIZE);
 		/* exor page with stckf values */
-		for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) {
+		for (n = 0; n < PAGE_SIZE / sizeof(u64); n++) {
 			u64 *p = ((u64 *)pg) + n;
 			*p ^= get_tod_clock_fast();
 		}
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index f043c3c7e73c..dd42a26d049d 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -128,14 +128,14 @@ static struct hypfs_dbfs_file hypfs_sprp_file = {
 
 int hypfs_sprp_init(void)
 {
-	if (!sclp_has_sprp())
+	if (!sclp.has_sprp)
 		return 0;
 	return hypfs_dbfs_create_file(&hypfs_sprp_file);
 }
 
 void hypfs_sprp_exit(void)
 {
-	if (!sclp_has_sprp())
+	if (!sclp.has_sprp)
 		return;
 	hypfs_dbfs_remove_file(&hypfs_sprp_file);
 }
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 8d724718ec21..e6f8615a11eb 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #define smp_mb__before_atomic()		smp_mb()
 #define smp_mb__after_atomic()		smp_mb()
 
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 4eadec466b8c..411464f4c97a 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,8 +32,6 @@
 	__old;								\
 })
 
-#define __HAVE_ARCH_CMPXCHG
-
 #define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn)		\
 ({									\
 	register __typeof__(*(p1)) __old1 asm("2") = (o1);		\
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 11eae5f55b70..dfb542ade6b1 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -35,7 +35,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define hugetlb_prefault_arch_hook(mm)		do { } while (0)
 #define arch_clear_hugepage_flags(page)		do { } while (0)
 
 int arch_prepare_hugepage(struct page *page);
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index 30fd5c84680e..cb5fdf3a78fc 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -29,6 +29,7 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 
 #define ioremap_nocache(addr, size)	ioremap(addr, size)
 #define ioremap_wc			ioremap_nocache
+#define ioremap_wt			ioremap_nocache
 
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index d01fc588b5c3..3024acbe1f9d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -80,6 +80,7 @@ struct sca_block {
 #define CPUSTAT_MCDS       0x00000100
 #define CPUSTAT_SM         0x00000080
 #define CPUSTAT_IBS        0x00000040
+#define CPUSTAT_GED2       0x00000010
 #define CPUSTAT_G          0x00000008
 #define CPUSTAT_GED        0x00000004
 #define CPUSTAT_J          0x00000002
@@ -95,7 +96,8 @@ struct kvm_s390_sie_block {
 #define PROG_IN_SIE (1<<0)
 	__u32	prog0c;			/* 0x000c */
 	__u8	reserved10[16];		/* 0x0010 */
-#define PROG_BLOCK_SIE 0x00000001
+#define PROG_BLOCK_SIE	(1<<0)
+#define PROG_REQUEST	(1<<1)
 	atomic_t prog20;		/* 0x0020 */
 	__u8	reserved24[4];		/* 0x0024 */
 	__u64	cputm;			/* 0x0028 */
@@ -634,7 +636,7 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
-static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {}
 static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
 static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *slot) {}
diff --git a/arch/s390/include/asm/mm-arch-hooks.h b/arch/s390/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..07680b2f3c59
--- /dev/null
+++ b/arch/s390/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_S390_MM_ARCH_HOOKS_H
+#define _ASM_S390_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_S390_MM_ARCH_HOOKS_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index fc642399b489..f66d82798a6a 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -494,7 +494,7 @@ static inline int pmd_large(pmd_t pmd)
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
 }
 
-static inline int pmd_pfn(pmd_t pmd)
+static inline unsigned long pmd_pfn(pmd_t pmd)
 {
 	unsigned long origin_mask;
 
@@ -1498,9 +1498,9 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 	return pmd_young(pmd);
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 
@@ -1509,10 +1509,10 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	return pmd;
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL
-static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address,
-					    pmd_t *pmdp, int full)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
+static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
+						 unsigned long address,
+						 pmd_t *pmdp, int full)
 {
 	pmd_t pmd = *pmdp;
 
@@ -1522,11 +1522,11 @@ static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm,
 	return pmd;
 }
 
-#define __HAVE_ARCH_PMDP_CLEAR_FLUSH
-static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
-				     unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
+static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
+					  unsigned long address, pmd_t *pmdp)
 {
-	return pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 }
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
@@ -1548,6 +1548,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	}
 }
 
+static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address,
+					pmd_t *pmdp)
+{
+	return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+}
+#define pmdp_collapse_flush pmdp_collapse_flush
+
 #define pfn_pmd(pfn, pgprot)	mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot))
 #define mk_pmd(page, pgprot)	pfn_pmd(page_to_pfn(page), (pgprot))
 
@@ -1565,9 +1573,9 @@ static inline int has_transparent_hugepage(void)
 /*
  * 64 bit swap entry format:
  * A page-table entry has some bits we have to treat in a special way.
- * Bits 52 and bit 55 have to be zero, otherwise an specification
+ * Bits 52 and bit 55 have to be zero, otherwise a specification
  * exception will occur instead of a page translation exception. The
- * specifiation exception has the bad habit not to store necessary
+ * specification exception has the bad habit not to store necessary
  * information in the lowcore.
  * Bits 54 and 63 are used to indicate the page type.
  * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index f1096bab5199..c891f41b2753 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,33 +46,39 @@ struct sclp_cpu_info {
 	struct sclp_cpu_entry cpu[MAX_CPU_ADDRESS + 1];
 };
 
+struct sclp_info {
+	unsigned char has_linemode : 1;
+	unsigned char has_vt220 : 1;
+	unsigned char has_siif : 1;
+	unsigned char has_sigpif : 1;
+	unsigned char has_cpu_type : 1;
+	unsigned char has_sprp : 1;
+	unsigned int ibc;
+	unsigned int mtid;
+	unsigned int mtid_cp;
+	unsigned int mtid_prev;
+	unsigned long long rzm;
+	unsigned long long rnmax;
+	unsigned long long hamax;
+	unsigned int max_cpu;
+	unsigned long hsa_size;
+	unsigned long long facilities;
+};
+extern struct sclp_info sclp;
+
 int sclp_get_cpu_info(struct sclp_cpu_info *info);
 int sclp_cpu_configure(u8 cpu);
 int sclp_cpu_deconfigure(u8 cpu);
-unsigned long long sclp_get_rnmax(void);
-unsigned long long sclp_get_rzm(void);
-unsigned int sclp_get_max_cpu(void);
-unsigned int sclp_get_mtid(u8 cpu_type);
-unsigned int sclp_get_mtid_max(void);
-unsigned int sclp_get_mtid_prev(void);
 int sclp_sdias_blk_count(void);
 int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
 int sclp_chp_deconfigure(struct chp_id chpid);
 int sclp_chp_read_info(struct sclp_chp_info *info);
 void sclp_get_ipl_info(struct sclp_ipl_info *info);
-bool __init sclp_has_linemode(void);
-bool __init sclp_has_vt220(void);
-bool sclp_has_sprp(void);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
-unsigned long sclp_get_hsa_size(void);
 void sclp_early_detect(void);
-int sclp_has_siif(void);
-int sclp_has_sigpif(void);
-unsigned int sclp_get_ibc(void);
-
 long _sclp_print_early(const char *);
 
 #endif /* _ASM_S390_SCLP_H */
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 98eb2a579223..dcb6312a0b91 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -10,6 +10,7 @@
 #define _ASM_S390_TIMEX_H
 
 #include <asm/lowcore.h>
+#include <linux/time64.h>
 
 /* The value of the TOD clock for 1.1.1970. */
 #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL
@@ -108,10 +109,10 @@ int get_sync_clock(unsigned long long *clock);
 void init_cpu_timer(void);
 unsigned long long monotonic_clock(void);
 
-void tod_to_timeval(__u64, struct timespec *);
+void tod_to_timeval(__u64 todval, struct timespec64 *xt);
 
 static inline
-void stck_to_timespec(unsigned long long stck, struct timespec *ts)
+void stck_to_timespec64(unsigned long long stck, struct timespec64 *ts)
 {
 	tod_to_timeval(stck - TOD_UNIX_EPOCH, ts);
 }
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index b1453a2ae1ca..4990f6c66288 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -22,7 +22,8 @@ DECLARE_PER_CPU(struct cpu_topology_s390, cpu_topology);
 
 #define topology_physical_package_id(cpu) (per_cpu(cpu_topology, cpu).socket_id)
 #define topology_thread_id(cpu)		  (per_cpu(cpu_topology, cpu).thread_id)
-#define topology_thread_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).thread_mask)
+#define topology_sibling_cpumask(cpu) \
+		(&per_cpu(cpu_topology, cpu).thread_mask)
 #define topology_core_id(cpu)		  (per_cpu(cpu_topology, cpu).core_id)
 #define topology_core_cpumask(cpu)	  (&per_cpu(cpu_topology, cpu).core_mask)
 #define topology_book_id(cpu)		  (per_cpu(cpu_topology, cpu).book_id)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index d64a7a62164f..9dd4cc47ddc7 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -98,7 +98,8 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
  * @from: Source address, in user space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -118,7 +119,8 @@ unsigned long __must_check __copy_from_user(void *to, const void __user *from,
  * @from: Source address, in kernel space.
  * @n:	  Number of bytes to copy.
  *
- * Context: User context only.	This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -264,7 +266,8 @@ int __get_user_bad(void) __attribute__((noreturn));
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -290,7 +293,8 @@ __compiletime_warning("copy_from_user() buffer size is not provably correct")
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
@@ -348,7 +352,8 @@ static inline unsigned long strnlen_user(const char __user *src, unsigned long n
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Get the size of a NUL-terminated string in user space.
  *
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f73c8059022..7a75ad4594e3 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -33,11 +33,12 @@ static struct memblock_type oldmem_type = {
 };
 
 #define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\
-	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\
+	for (i = 0, __next_mem_range(&i, nid, MEMBLOCK_NONE,		\
+				     &memblock.physmem,			\
 				     &oldmem_type, p_start,		\
 				     p_end, p_nid);			\
 	     i != (u64)ULLONG_MAX;					\
-	     __next_mem_range(&i, nid, &memblock.physmem,		\
+	     __next_mem_range(&i, nid, MEMBLOCK_NONE, &memblock.physmem,\
 			      &oldmem_type,				\
 			      p_start, p_end, p_nid))
 
@@ -122,7 +123,7 @@ static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
 {
 	int rc;
 
-	if (src < sclp_get_hsa_size()) {
+	if (src < sclp.hsa_size) {
 		rc = memcpy_hsa(buf, src, csize, userbuf);
 	} else {
 		if (userbuf)
@@ -215,7 +216,7 @@ static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
 					   unsigned long pfn,
 					   unsigned long size, pgprot_t prot)
 {
-	unsigned long hsa_end = sclp_get_hsa_size();
+	unsigned long hsa_end = sclp.hsa_size;
 	unsigned long size_hsa;
 
 	if (pfn < hsa_end >> PAGE_SHIFT) {
@@ -258,7 +259,7 @@ int copy_from_oldmem(void *dest, void *src, size_t count)
 				return rc;
 		}
 	} else {
-		unsigned long hsa_end = sclp_get_hsa_size();
+		unsigned long hsa_end = sclp.hsa_size;
 		if ((unsigned long) src < hsa_end) {
 			copied = min(count, hsa_end - (unsigned long) src);
 			rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
@@ -609,7 +610,7 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 	if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
 		return 0;
 	/* If we cannot get HSA size for zfcpdump return error */
-	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size())
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp.hsa_size)
 		return -ENODEV;
 
 	/* For kdump, exclude previous crashkernel memory */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index c1f21aca76e7..6fca0e46464e 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1457,23 +1457,24 @@ int
 debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 			 int area, debug_entry_t * entry, char *out_buf)
 {
-	struct timespec time_spec;
+	struct timespec64 time_spec;
 	char *except_str;
 	unsigned long caller;
 	int rc = 0;
 	unsigned int level;
 
 	level = entry->id.fields.level;
-	stck_to_timespec(entry->id.stck, &time_spec);
+	stck_to_timespec64(entry->id.stck, &time_spec);
 
 	if (entry->id.fields.exception)
 		except_str = "*";
 	else
 		except_str = "-";
 	caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN;
-	rc += sprintf(out_buf, "%02i %011lu:%06lu %1u %1s %02i %p  ",
-		      area, time_spec.tv_sec, time_spec.tv_nsec / 1000, level,
-		      except_str, entry->id.fields.cpuid, (void *) caller);
+	rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p  ",
+		      area, (long long)time_spec.tv_sec,
+		      time_spec.tv_nsec / 1000, level, except_str,
+		      entry->id.fields.cpuid, (void *)caller);
 	return rc;
 }
 EXPORT_SYMBOL(debug_dflt_header_fn);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 99b44acbfcc7..3238893c9d4f 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -1005,7 +1005,7 @@ ENTRY(sie64a)
 .Lsie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	oi	__SIE_PROG0C+3(%r14),1		# we are going into SIE now
-	tm	__SIE_PROG20+3(%r14),1		# last exit...
+	tm	__SIE_PROG20+3(%r14),3		# last exit...
 	jnz	.Lsie_done
 	LPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 7262fe438c99..af4f41d52cde 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -128,9 +128,9 @@ __setup("condev=", condev_setup);
 static void __init set_preferred_console(void)
 {
 	if (MACHINE_IS_KVM) {
-		if (sclp_has_vt220())
+		if (sclp.has_vt220)
 			add_preferred_console("ttyS", 1, NULL);
-		else if (sclp_has_linemode())
+		else if (sclp.has_linemode)
 			add_preferred_console("ttyS", 0, NULL);
 		else
 			add_preferred_console("hvc", 0, NULL);
@@ -510,8 +510,8 @@ static void reserve_memory_end(void)
 {
 #ifdef CONFIG_CRASH_DUMP
 	if (ipl_info.type == IPL_TYPE_FCP_DUMP &&
-	    !OLDMEM_BASE && sclp_get_hsa_size()) {
-		memory_end = sclp_get_hsa_size();
+	    !OLDMEM_BASE && sclp.hsa_size) {
+		memory_end = sclp.hsa_size;
 		memory_end &= PAGE_MASK;
 		memory_end_set = 1;
 	}
@@ -576,7 +576,7 @@ static void __init reserve_crashkernel(void)
 		crash_base = low;
 	} else {
 		/* Find suitable area in free memory */
-		low = max_t(unsigned long, crash_size, sclp_get_hsa_size());
+		low = max_t(unsigned long, crash_size, sclp.hsa_size);
 		high = crash_base ? crash_base + crash_size : ULONG_MAX;
 
 		if (crash_base && crash_base < low) {
@@ -640,19 +640,24 @@ static void __init check_initrd(void)
 }
 
 /*
- * Reserve all kernel text
+ * Reserve memory used for lowcore/command line/kernel image.
  */
 static void __init reserve_kernel(void)
 {
-	unsigned long start_pfn;
-	start_pfn = PFN_UP(__pa(&_end));
+	unsigned long start_pfn = PFN_UP(__pa(&_end));
 
+#ifdef CONFIG_DMA_API_DEBUG
 	/*
-	 * Reserve memory used for lowcore/command line/kernel image.
+	 * DMA_API_DEBUG code stumbles over addresses from the
+	 * range [_ehead, _stext]. Mark the memory as reserved
+	 * so it is not used for CONFIG_DMA_API_DEBUG=y.
 	 */
+	memblock_reserve(0, PFN_PHYS(start_pfn));
+#else
 	memblock_reserve(0, (unsigned long)_ehead);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
+#endif
 }
 
 static void __init reserve_elfcorehdr(void)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index efd2c1968000..0d9d59d4710e 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -601,7 +601,7 @@ static void __init smp_store_cpu_states(struct sclp_cpu_info *info)
 		/* No previous system present, normal boot. */
 		return;
 	/* Set multi-threading state to the previous system. */
-	pcpu_set_smt(sclp_get_mtid_prev());
+	pcpu_set_smt(sclp.mtid_prev);
 	/* Collect CPU states. */
 	cpu = 0;
 	for (i = 0; i < info->configured; i++) {
@@ -740,7 +740,7 @@ static void __init smp_detect_cpus(void)
 #endif
 
 	/* Set multi-threading state for the current system */
-	mtid = sclp_get_mtid(boot_cpu_type);
+	mtid = boot_cpu_type ? sclp.mtid : sclp.mtid_cp;
 	mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
 	pcpu_set_smt(mtid);
 
@@ -880,12 +880,13 @@ void __noreturn cpu_die(void)
 
 void __init smp_fill_possible_mask(void)
 {
-	unsigned int possible, sclp, cpu;
+	unsigned int possible, sclp_max, cpu;
 
-	sclp = min(smp_max_threads, sclp_get_mtid_max() + 1);
-	sclp = sclp_get_max_cpu()*sclp ?: nr_cpu_ids;
+	sclp_max = max(sclp.mtid, sclp.mtid_cp) + 1;
+	sclp_max = min(smp_max_threads, sclp_max);
+	sclp_max = sclp.max_cpu * sclp_max ?: nr_cpu_ids;
 	possible = setup_possible_cpus ?: nr_cpu_ids;
-	possible = min(possible, sclp);
+	possible = min(possible, sclp_max);
 	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
 		set_cpu_possible(cpu, true);
 }
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index d3236c9e226b..39e2f41b6cf0 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,10 +9,10 @@
 #include <linux/pfn.h>
 #include <linux/suspend.h>
 #include <linux/mm.h>
+#include <linux/pci.h>
 #include <asm/ctl_reg.h>
 #include <asm/ipl.h>
 #include <asm/cio.h>
-#include <asm/pci.h>
 #include <asm/sections.h>
 #include "entry.h"
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 170ddd2018b3..9e733d965e08 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -76,7 +76,7 @@ unsigned long long monotonic_clock(void)
 }
 EXPORT_SYMBOL(monotonic_clock);
 
-void tod_to_timeval(__u64 todval, struct timespec *xt)
+void tod_to_timeval(__u64 todval, struct timespec64 *xt)
 {
 	unsigned long long sec;
 
@@ -181,12 +181,12 @@ static void timing_alert_interrupt(struct ext_code ext_code,
 static void etr_reset(void);
 static void stp_reset(void);
 
-void read_persistent_clock(struct timespec *ts)
+void read_persistent_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(get_tod_clock() - TOD_UNIX_EPOCH, ts);
 }
 
-void read_boot_clock(struct timespec *ts)
+void read_boot_clock64(struct timespec64 *ts)
 {
 	tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts);
 }
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 9e3779e3e496..7365e8a46032 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -241,21 +241,6 @@ static int handle_prog(struct kvm_vcpu *vcpu)
 	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
-static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
-{
-	int rc, rc2;
-
-	vcpu->stat.exit_instr_and_program++;
-	rc = handle_instruction(vcpu);
-	rc2 = handle_prog(vcpu);
-
-	if (rc == -EOPNOTSUPP)
-		vcpu->arch.sie_block->icptcode = 0x04;
-	if (rc)
-		return rc;
-	return rc2;
-}
-
 /**
  * handle_external_interrupt - used for external interruption interceptions
  *
@@ -355,7 +340,6 @@ static const intercept_handler_t intercept_funcs[] = {
 	[0x00 >> 2] = handle_noop,
 	[0x04 >> 2] = handle_instruction,
 	[0x08 >> 2] = handle_prog,
-	[0x0C >> 2] = handle_instruction_and_prog,
 	[0x10 >> 2] = handle_noop,
 	[0x14 >> 2] = handle_external_interrupt,
 	[0x18 >> 2] = handle_noop,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 9de47265ef73..c98d89708e99 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -134,6 +134,8 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 
 	active_mask = pending_local_irqs(vcpu);
 	active_mask |= pending_floating_irqs(vcpu);
+	if (!active_mask)
+		return 0;
 
 	if (psw_extint_disabled(vcpu))
 		active_mask &= ~IRQ_PEND_EXT_MASK;
@@ -799,7 +801,7 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
 
-	if (!sclp_has_sigpif())
+	if (!sclp.has_sigpif)
 		return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
 
 	return (sigp_ctrl & SIGP_CTRL_C) &&
@@ -941,12 +943,9 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	if (cpu_timer_irq_pending(vcpu))
 		set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
 
-	do {
-		irqs = deliverable_irqs(vcpu);
+	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
 		/* bits are in the order of interrupt priority */
 		irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
-		if (irq_type == IRQ_PEND_COUNT)
-			break;
 		if (is_ioirq(irq_type)) {
 			rc = __deliver_io(vcpu, irq_type);
 		} else {
@@ -958,9 +957,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 			}
 			rc = func(vcpu);
 		}
-		if (rc)
-			break;
-	} while (!rc);
+	}
 
 	set_intercept_indicators(vcpu);
 
@@ -1058,10 +1055,10 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	    kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
 		return -EINVAL;
 
-	if (sclp_has_sigpif())
+	if (sclp.has_sigpif)
 		return __inject_extcall_sigpif(vcpu, src_id);
 
-	if (!test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
+	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
 	*extcall = irq->u.extcall;
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
@@ -1340,12 +1337,54 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	return 0;
 }
 
-static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+/*
+ * Find a destination VCPU for a floating irq and kick it.
+ */
+static void __floating_irq_kick(struct kvm *kvm, u64 type)
 {
+	struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu;
+	int sigcpu, online_vcpus, nr_tries = 0;
+
+	online_vcpus = atomic_read(&kvm->online_vcpus);
+	if (!online_vcpus)
+		return;
+
+	/* find idle VCPUs first, then round robin */
+	sigcpu = find_first_bit(fi->idle_mask, online_vcpus);
+	if (sigcpu == online_vcpus) {
+		do {
+			sigcpu = fi->next_rr_cpu;
+			fi->next_rr_cpu = (fi->next_rr_cpu + 1) % online_vcpus;
+			/* avoid endless loops if all vcpus are stopped */
+			if (nr_tries++ >= online_vcpus)
+				return;
+		} while (is_vcpu_stopped(kvm_get_vcpu(kvm, sigcpu)));
+	}
+	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+
+	/* make the VCPU drop out of the SIE, or wake it up if sleeping */
+	li = &dst_vcpu->arch.local_int;
+	spin_lock(&li->lock);
+	switch (type) {
+	case KVM_S390_MCHK:
+		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
+		break;
+	default:
+		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+		break;
+	}
+	spin_unlock(&li->lock);
+	kvm_s390_vcpu_wakeup(dst_vcpu);
+}
+
+static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
+{
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_vcpu *dst_vcpu = NULL;
-	int sigcpu;
 	u64 type = READ_ONCE(inti->type);
 	int rc;
 
@@ -1373,32 +1412,8 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	if (rc)
 		return rc;
 
-	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
-	if (sigcpu == KVM_MAX_VCPUS) {
-		do {
-			sigcpu = fi->next_rr_cpu++;
-			if (sigcpu == KVM_MAX_VCPUS)
-				sigcpu = fi->next_rr_cpu = 0;
-		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
-	}
-	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
-	li = &dst_vcpu->arch.local_int;
-	spin_lock(&li->lock);
-	switch (type) {
-	case KVM_S390_MCHK:
-		atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
-		break;
-	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags);
-		break;
-	default:
-		atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-		break;
-	}
-	spin_unlock(&li->lock);
-	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
+	__floating_irq_kick(kvm, type);
 	return 0;
-
 }
 
 int kvm_s390_inject_vm(struct kvm *kvm,
@@ -1606,6 +1621,9 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
 	int i;
 
 	spin_lock(&fi->lock);
+	fi->pending_irqs = 0;
+	memset(&fi->srv_signal, 0, sizeof(fi->srv_signal));
+	memset(&fi->mchk, 0, sizeof(fi->mchk));
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
 		clear_irq_list(&fi->lists[i]);
 	for (i = 0; i < FIRQ_MAX_COUNT; i++)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8cd8e7b288c5..2078f92d15ac 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -36,6 +36,10 @@
 #include "kvm-s390.h"
 #include "gaccess.h"
 
+#define KMSG_COMPONENT "kvm-s390"
+#undef pr_fmt
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 #include "trace-s390.h"
@@ -110,7 +114,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 /* upper facilities limit for kvm */
 unsigned long kvm_s390_fac_list_mask[] = {
 	0xffe6fffbfcfdfc40UL,
-	0x005c800000000000UL,
+	0x005e800000000000UL,
 };
 
 unsigned long kvm_s390_fac_list_mask_size(void)
@@ -236,6 +240,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 {
 	int r;
 	unsigned long n;
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
@@ -245,7 +250,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
-	memslot = id_to_memslot(kvm->memslots, log->slot);
+	slots = kvm_memslots(kvm);
+	memslot = id_to_memslot(slots, log->slot);
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -454,10 +460,10 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
 
 	mutex_lock(&kvm->lock);
 	kvm->arch.epoch = gtod - host_tod;
-	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm) {
+	kvm_s390_vcpu_block_all(kvm);
+	kvm_for_each_vcpu(vcpu_idx, cur_vcpu, kvm)
 		cur_vcpu->arch.sie_block->epoch = kvm->arch.epoch;
-		exit_sie(cur_vcpu);
-	}
+	kvm_s390_vcpu_unblock_all(kvm);
 	mutex_unlock(&kvm->lock);
 	return 0;
 }
@@ -604,7 +610,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 		goto out;
 	}
 	get_cpu_id((struct cpuid *) &mach->cpuid);
-	mach->ibc = sclp_get_ibc();
+	mach->ibc = sclp.ibc;
 	memcpy(&mach->fac_mask, kvm->arch.model.fac->mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
@@ -1068,7 +1074,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 
 	kvm_s390_get_cpu_id(&kvm->arch.model.cpu_id);
-	kvm->arch.model.ibc = sclp_get_ibc() & 0x0fff;
+	kvm->arch.model.ibc = sclp.ibc & 0x0fff;
 
 	if (kvm_s390_crypto_init(kvm) < 0)
 		goto out_err;
@@ -1311,8 +1317,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
-						    CPUSTAT_STOPPED |
-						    CPUSTAT_GED);
+						    CPUSTAT_STOPPED);
+
+	if (test_kvm_facility(vcpu->kvm, 78))
+		atomic_set_mask(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+	else if (test_kvm_facility(vcpu->kvm, 8))
+		atomic_set_mask(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+
 	kvm_s390_vcpu_setup_model(vcpu);
 
 	vcpu->arch.sie_block->ecb   = 6;
@@ -1321,9 +1332,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.sie_block->ecb2  = 8;
 	vcpu->arch.sie_block->eca   = 0xC1002000U;
-	if (sclp_has_siif())
+	if (sclp.has_siif)
 		vcpu->arch.sie_block->eca |= 1;
-	if (sclp_has_sigpif())
+	if (sclp.has_sigpif)
 		vcpu->arch.sie_block->eca |= 0x10000000U;
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		vcpu->arch.sie_block->eca |= 0x00020000;
@@ -1409,16 +1420,28 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 	return kvm_s390_vcpu_has_irq(vcpu, 0);
 }
 
-void s390_vcpu_block(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	atomic_set_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
+	exit_sie(vcpu);
 }
 
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu)
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu)
 {
 	atomic_clear_mask(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
 }
 
+static void kvm_s390_vcpu_request(struct kvm_vcpu *vcpu)
+{
+	atomic_set_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	exit_sie(vcpu);
+}
+
+static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+}
+
 /*
  * Kick a guest cpu out of SIE and wait until SIE is not running.
  * If the CPU is not running (e.g. waiting as idle) the function will
@@ -1430,11 +1453,11 @@ void exit_sie(struct kvm_vcpu *vcpu)
 		cpu_relax();
 }
 
-/* Kick a guest cpu out of SIE and prevent SIE-reentry */
-void exit_sie_sync(struct kvm_vcpu *vcpu)
+/* Kick a guest cpu out of SIE to process a request synchronously */
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
 {
-	s390_vcpu_block(vcpu);
-	exit_sie(vcpu);
+	kvm_make_request(req, vcpu);
+	kvm_s390_vcpu_request(vcpu);
 }
 
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
@@ -1447,8 +1470,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long address)
 		/* match against both prefix pages */
 		if (kvm_s390_get_prefix(vcpu) == (address & ~0x1000UL)) {
 			VCPU_EVENT(vcpu, 2, "gmap notifier for %lx", address);
-			kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
-			exit_sie_sync(vcpu);
+			kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
 		}
 	}
 }
@@ -1720,8 +1742,10 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
+	if (!vcpu->requests)
+		return 0;
 retry:
-	s390_vcpu_unblock(vcpu);
+	kvm_s390_vcpu_request_handled(vcpu);
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
@@ -1993,12 +2017,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		 * As PF_VCPU will be used in fault handler, between
 		 * guest_enter and guest_exit should be no uaccess.
 		 */
-		preempt_disable();
-		kvm_guest_enter();
-		preempt_enable();
+		local_irq_disable();
+		__kvm_guest_enter();
+		local_irq_enable();
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
-		kvm_guest_exit();
+		local_irq_disable();
+		__kvm_guest_exit();
+		local_irq_enable();
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 		rc = vcpu_post_run(vcpu, exit_reason);
@@ -2068,7 +2094,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
 		kvm_s390_vcpu_start(vcpu);
 	} else if (is_vcpu_stopped(vcpu)) {
-		pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
+		pr_err_ratelimited("can't run stopped vcpu %d\n",
 				   vcpu->vcpu_id);
 		return -EINVAL;
 	}
@@ -2206,8 +2232,7 @@ int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
 static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
-	kvm_make_request(KVM_REQ_DISABLE_IBS, vcpu);
-	exit_sie_sync(vcpu);
+	kvm_s390_sync_request(KVM_REQ_DISABLE_IBS, vcpu);
 }
 
 static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
@@ -2223,8 +2248,7 @@ static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
 static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu);
-	kvm_make_request(KVM_REQ_ENABLE_IBS, vcpu);
-	exit_sie_sync(vcpu);
+	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
 }
 
 void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
@@ -2563,7 +2587,7 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_userspace_memory_region *mem,
 				   enum kvm_mr_change change)
 {
 	/* A few sanity checks. We can have memory slots which have to be
@@ -2581,8 +2605,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
+				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
 	int rc;
@@ -2601,7 +2626,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
 		mem->guest_phys_addr, mem->memory_size);
 	if (rc)
-		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
+		pr_warn("failed to commit memory region\n");
 	return;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index ca108b90ae56..c5704786e473 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -211,10 +211,10 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr);
 int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu);
-void s390_vcpu_block(struct kvm_vcpu *vcpu);
-void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
-void exit_sie_sync(struct kvm_vcpu *vcpu);
+void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu);
 int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 /* is cmma enabled */
@@ -228,6 +228,25 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
 			     struct kvm_s390_pgm_info *pgm_info);
 
+static inline void kvm_s390_vcpu_block_all(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	WARN_ON(!mutex_is_locked(&kvm->lock));
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_s390_vcpu_block(vcpu);
+}
+
+static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_s390_vcpu_unblock(vcpu);
+}
+
 /**
  * kvm_s390_inject_prog_cond - conditionally inject a program check
  * @vcpu: virtual cpu
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d22d8ee1ff9d..ad4242245771 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -698,10 +698,14 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	case 0x00001000:
 		end = (start + (1UL << 20)) & ~((1UL << 20) - 1);
 		break;
-	/* We dont support EDAT2
 	case 0x00002000:
+		/* only support 2G frame size if EDAT2 is available and we are
+		   not in 24-bit addressing mode */
+		if (!test_kvm_facility(vcpu->kvm, 78) ||
+		    psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_AMODE_24BIT)
+			return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 		end = (start + (1UL << 31)) & ~((1UL << 31) - 1);
-		break;*/
+		break;
 	default:
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 	}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 76515bcea2f1..4c8f5d7f9c23 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -399,7 +399,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
 	 * user context.
 	 */
 	fault = VM_FAULT_BADCONTEXT;
-	if (unlikely(!user_space_fault(regs) || in_atomic() || !mm))
+	if (unlikely(!user_space_fault(regs) || faulthandler_disabled() || !mm))
 		goto out;
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e617e74b7be2..c3f8e3df92ff 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -193,11 +193,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return (pte_t *) pmdp;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	if (!MACHINE_HAS_HPAGE)
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 80875c43a4a4..76e873748b56 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -213,7 +213,7 @@ unsigned long memory_block_size_bytes(void)
 	 * Make sure the memory block size is always greater
 	 * or equal than the memory increment size.
 	 */
-	return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp_get_rzm());
+	return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp.rzm);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
diff --git a/arch/s390/mm/mem_detect.c b/arch/s390/mm/mem_detect.c
index 0f3604395805..e00f0d5d296d 100644
--- a/arch/s390/mm/mem_detect.c
+++ b/arch/s390/mm/mem_detect.c
@@ -31,8 +31,8 @@ void __init detect_memory_memblock(void)
 	unsigned long addr, size;
 	int type;
 
-	rzm = sclp_get_rzm();
-	rnmax = sclp_get_rnmax();
+	rzm = sclp.rzm;
+	rnmax = sclp.rnmax;
 	memsize = rzm * rnmax;
 	if (!rzm)
 		rzm = 1ULL << 17;
diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h
index ba8593a515ba..f6498eec9ee1 100644
--- a/arch/s390/net/bpf_jit.h
+++ b/arch/s390/net/bpf_jit.h
@@ -28,6 +28,9 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  *	      | old backchain |     |
  *	      +---------------+     |
  *	      |   r15 - r6    |     |
+ *	      +---------------+     |
+ *	      | 4 byte align  |     |
+ *	      | tail_call_cnt |     |
  * BFP	   -> +===============+     |
  *	      |		      |     |
  *	      |   BPF stack   |     |
@@ -46,12 +49,17 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
  * R15	   -> +---------------+     + low
  *
  * We get 160 bytes stack space from calling function, but only use
- * 11 * 8 byte (old backchain + r15 - r6) for storing registers.
+ * 12 * 8 byte for old backchain, r15..r6, and tail_call_cnt.
  */
-#define STK_OFF (MAX_BPF_STACK + 8 + 4 + 4 + (160 - 11 * 8))
+#define STK_SPACE	(MAX_BPF_STACK + 8 + 4 + 4 + 160)
+#define STK_160_UNUSED	(160 - 12 * 8)
+#define STK_OFF		(STK_SPACE - STK_160_UNUSED)
 #define STK_OFF_TMP	160	/* Offset of tmp buffer on stack */
 #define STK_OFF_HLEN	168	/* Offset of SKB header length on stack */
 
+#define STK_OFF_R6	(160 - 11 * 8)	/* Offset of r6 on stack */
+#define STK_OFF_TCCNT	(160 - 12 * 8)	/* Offset of tail_call_cnt on stack */
+
 /* Offset to skip condition code check */
 #define OFF_OK		4
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 7690dc8e1ab5..d3766dd67e23 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -21,6 +21,7 @@
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/init.h>
+#include <linux/bpf.h>
 #include <asm/cacheflush.h>
 #include <asm/dis.h>
 #include "bpf_jit.h"
@@ -40,6 +41,8 @@ struct bpf_jit {
 	int base_ip;		/* Base address for literal pool */
 	int ret0_ip;		/* Address of return 0 */
 	int exit_ip;		/* Address of exit */
+	int tail_call_start;	/* Tail call start offset */
+	int labels[1];		/* Labels for local jumps */
 };
 
 #define BPF_SIZE_MAX	4096	/* Max size for program */
@@ -49,6 +52,7 @@ struct bpf_jit {
 #define SEEN_RET0	4	/* ret0_ip points to a valid return 0 */
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
+#define SEEN_TAIL_CALL	32	/* code uses tail calls */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -60,6 +64,7 @@ struct bpf_jit {
 #define REG_L		(__MAX_BPF_REG+3)	/* Literal pool register */
 #define REG_15		(__MAX_BPF_REG+4)	/* Register 15 */
 #define REG_0		REG_W0			/* Register 0 */
+#define REG_1		REG_W1			/* Register 1 */
 #define REG_2		BPF_REG_1		/* Register 2 */
 #define REG_14		BPF_REG_0		/* Register 14 */
 
@@ -223,6 +228,24 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
 	REG_SET_SEEN(b3);					\
 })
 
+#define EMIT6_PCREL_LABEL(op1, op2, b1, b2, label, mask)	\
+({								\
+	int rel = (jit->labels[label] - jit->prg) >> 1;		\
+	_EMIT6(op1 | reg(b1, b2) << 16 | (rel & 0xffff),	\
+	       op2 | mask << 12);				\
+	REG_SET_SEEN(b1);					\
+	REG_SET_SEEN(b2);					\
+})
+
+#define EMIT6_PCREL_IMM_LABEL(op1, op2, b1, imm, label, mask)	\
+({								\
+	int rel = (jit->labels[label] - jit->prg) >> 1;		\
+	_EMIT6(op1 | (reg_high(b1) | mask) << 16 |		\
+		(rel & 0xffff), op2 | (imm & 0xff) << 8);	\
+	REG_SET_SEEN(b1);					\
+	BUILD_BUG_ON(((unsigned long) imm) > 0xff);		\
+})
+
 #define EMIT6_PCREL(op1, op2, b1, b2, i, off, mask)		\
 ({								\
 	/* Branch instruction needs 6 bytes */			\
@@ -286,7 +309,7 @@ static void jit_fill_hole(void *area, unsigned int size)
  */
 static void save_regs(struct bpf_jit *jit, u32 rs, u32 re)
 {
-	u32 off = 72 + (rs - 6) * 8;
+	u32 off = STK_OFF_R6 + (rs - 6) * 8;
 
 	if (rs == re)
 		/* stg %rs,off(%r15) */
@@ -301,7 +324,7 @@ static void save_regs(struct bpf_jit *jit, u32 rs, u32 re)
  */
 static void restore_regs(struct bpf_jit *jit, u32 rs, u32 re)
 {
-	u32 off = 72 + (rs - 6) * 8;
+	u32 off = STK_OFF_R6 + (rs - 6) * 8;
 
 	if (jit->seen & SEEN_STACK)
 		off += STK_OFF;
@@ -374,6 +397,16 @@ static void save_restore_regs(struct bpf_jit *jit, int op)
  */
 static void bpf_jit_prologue(struct bpf_jit *jit)
 {
+	if (jit->seen & SEEN_TAIL_CALL) {
+		/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
+		_EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT);
+	} else {
+		/* j tail_call_start: NOP if no tail calls are used */
+		EMIT4_PCREL(0xa7f40000, 6);
+		_EMIT2(0);
+	}
+	/* Tail calls have to skip above initialization */
+	jit->tail_call_start = jit->prg;
 	/* Save registers */
 	save_restore_regs(jit, REGS_SAVE);
 	/* Setup literal pool */
@@ -384,13 +417,16 @@ static void bpf_jit_prologue(struct bpf_jit *jit)
 	}
 	/* Setup stack and backchain */
 	if (jit->seen & SEEN_STACK) {
-		/* lgr %bfp,%r15 (BPF frame pointer) */
-		EMIT4(0xb9040000, BPF_REG_FP, REG_15);
+		if (jit->seen & SEEN_FUNC)
+			/* lgr %w1,%r15 (backchain) */
+			EMIT4(0xb9040000, REG_W1, REG_15);
+		/* la %bfp,STK_160_UNUSED(%r15) (BPF frame pointer) */
+		EMIT4_DISP(0x41000000, BPF_REG_FP, REG_15, STK_160_UNUSED);
 		/* aghi %r15,-STK_OFF */
 		EMIT4_IMM(0xa70b0000, REG_15, -STK_OFF);
 		if (jit->seen & SEEN_FUNC)
-			/* stg %bfp,152(%r15) (backchain) */
-			EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_FP, REG_0,
+			/* stg %w1,152(%r15) (backchain) */
+			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
 	/*
@@ -443,8 +479,11 @@ static void bpf_jit_epilogue(struct bpf_jit *jit)
 
 /*
  * Compile one eBPF instruction into s390x code
+ *
+ * NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of
+ * stack space for the large switch statement.
  */
-static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
+static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
 	int jmp_off, last, insn_count = 1;
@@ -588,8 +627,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 		EMIT4(0xb9160000, dst_reg, rc_reg);
 		break;
 	}
-	case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / (u32) src */
-	case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % (u32) src */
+	case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
+	case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
@@ -602,10 +641,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 		EMIT4_IMM(0xa7090000, REG_W0, 0);
 		/* lgr %w1,%dst */
 		EMIT4(0xb9040000, REG_W1, dst_reg);
-		/* llgfr %dst,%src (u32 cast) */
-		EMIT4(0xb9160000, dst_reg, src_reg);
 		/* dlgr %w0,%dst */
-		EMIT4(0xb9870000, REG_W0, dst_reg);
+		EMIT4(0xb9870000, REG_W0, src_reg);
 		/* lgr %dst,%rc */
 		EMIT4(0xb9040000, dst_reg, rc_reg);
 		break;
@@ -632,8 +669,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 		EMIT4(0xb9160000, dst_reg, rc_reg);
 		break;
 	}
-	case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / (u32) imm */
-	case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % (u32) imm */
+	case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
+	case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */
 	{
 		int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
 
@@ -649,7 +686,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 		EMIT4(0xb9040000, REG_W1, dst_reg);
 		/* dlg %w0,<d(imm)>(%l) */
 		EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
-			      EMIT_CONST_U64((u32) imm));
+			      EMIT_CONST_U64(imm));
 		/* lgr %dst,%rc */
 		EMIT4(0xb9040000, dst_reg, rc_reg);
 		break;
@@ -947,6 +984,75 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i)
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
 		break;
 	}
+	case BPF_JMP | BPF_CALL | BPF_X:
+		/*
+		 * Implicit input:
+		 *  B1: pointer to ctx
+		 *  B2: pointer to bpf_array
+		 *  B3: index in bpf_array
+		 */
+		jit->seen |= SEEN_TAIL_CALL;
+
+		/*
+		 * if (index >= array->map.max_entries)
+		 *         goto out;
+		 */
+
+		/* llgf %w1,map.max_entries(%b2) */
+		EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
+			      offsetof(struct bpf_array, map.max_entries));
+		/* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */
+		EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3,
+				  REG_W1, 0, 0xa);
+
+		/*
+		 * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT)
+		 *         goto out;
+		 */
+
+		if (jit->seen & SEEN_STACK)
+			off = STK_OFF_TCCNT + STK_OFF;
+		else
+			off = STK_OFF_TCCNT;
+		/* lhi %w0,1 */
+		EMIT4_IMM(0xa7080000, REG_W0, 1);
+		/* laal %w1,%w0,off(%r15) */
+		EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off);
+		/* clij %w1,MAX_TAIL_CALL_CNT,0x2,label0 */
+		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007f, REG_W1,
+				      MAX_TAIL_CALL_CNT, 0, 0x2);
+
+		/*
+		 * prog = array->prog[index];
+		 * if (prog == NULL)
+		 *         goto out;
+		 */
+
+		/* sllg %r1,%b3,3: %r1 = index * 8 */
+		EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
+		/* lg %r1,prog(%b2,%r1) */
+		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
+			      REG_1, offsetof(struct bpf_array, prog));
+		/* clgij %r1,0,0x8,label0 */
+		EMIT6_PCREL_IMM_LABEL(0xec000000, 0x007d, REG_1, 0, 0, 0x8);
+
+		/*
+		 * Restore registers before calling function
+		 */
+		save_restore_regs(jit, REGS_RESTORE);
+
+		/*
+		 * goto *(prog->bpf_func + tail_call_start);
+		 */
+
+		/* lg %r1,bpf_func(%r1) */
+		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, REG_1, REG_0,
+			      offsetof(struct bpf_prog, bpf_func));
+		/* bc 0xf,tail_call_start(%r1) */
+		_EMIT4(0x47f01000 + jit->tail_call_start);
+		/* out: */
+		jit->labels[0] = jit->prg;
+		break;
 	case BPF_JMP | BPF_EXIT: /* return b0 */
 		last = (i == fp->len - 1) ? 1 : 0;
 		if (last && !(jit->seen & SEEN_RET0))
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 460fdb21cf61..ed2394dd14e9 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -75,7 +75,13 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
 	switch (ccdf->pec) {
-	case 0x0301: /* Standby -> Configured */
+	case 0x0301: /* Reserved|Standby -> Configured */
+		if (!zdev) {
+			ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 0);
+			if (ret)
+				break;
+			zdev = get_zdev_by_fid(ccdf->fid);
+		}
 		if (!zdev || zdev->state != ZPCI_FN_STATE_STANDBY)
 			break;
 		zdev->state = ZPCI_FN_STATE_CONFIGURED;
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
index f384839c3ee5..cc3f6420b71c 100644
--- a/arch/score/include/asm/cmpxchg.h
+++ b/arch/score/include/asm/cmpxchg.h
@@ -42,8 +42,6 @@ static inline unsigned long __cmpxchg(volatile unsigned long *m,
 					(unsigned long)(o),	\
 					(unsigned long)(n)))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 #include <asm-generic/cmpxchg-local.h>
 
 #endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/score/include/asm/mm-arch-hooks.h b/arch/score/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..5e38689f189a
--- /dev/null
+++ b/arch/score/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_SCORE_MM_ARCH_HOOKS_H
+#define _ASM_SCORE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SCORE_MM_ARCH_HOOKS_H */
diff --git a/arch/score/include/asm/uaccess.h b/arch/score/include/asm/uaccess.h
index ab66ddde777b..20a3591225cc 100644
--- a/arch/score/include/asm/uaccess.h
+++ b/arch/score/include/asm/uaccess.h
@@ -36,7 +36,8 @@
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -61,7 +62,8 @@
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -79,7 +81,8 @@
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -98,7 +101,8 @@
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -119,7 +123,8 @@
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/score/lib/string.S b/arch/score/lib/string.S
index 00b7d3a2fc60..16efa3ad037f 100644
--- a/arch/score/lib/string.S
+++ b/arch/score/lib/string.S
@@ -175,10 +175,10 @@ ENTRY(__clear_user)
 	br	r3
 
 	.section .fixup, "ax"
+99:
 	br	r3
 	.previous
 	.section __ex_table, "a"
 	.align	2
-99:
 	.word	0b, 99b
 	.previous
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 6860beb2a280..37a6c2e0e969 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -34,6 +34,7 @@
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ptrace.h>
+#include <linux/uaccess.h>
 
 /*
  * This routine handles page faults.  It determines the address,
@@ -73,7 +74,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
 	* If we're in an interrupt or have no user
 	* context, we must not take the fault..
 	*/
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto bad_area_nosemaphore;
 
 	if (user_mode(regs))
diff --git a/arch/sh/drivers/pci/ops-sh5.c b/arch/sh/drivers/pci/ops-sh5.c
index 4ce95a001b80..45361946460f 100644
--- a/arch/sh/drivers/pci/ops-sh5.c
+++ b/arch/sh/drivers/pci/ops-sh5.c
@@ -18,7 +18,6 @@
 #include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/irq.h>
-#include <asm/pci.h>
 #include <asm/io.h>
 #include "pci-sh5.h"
 
diff --git a/arch/sh/drivers/pci/pci-sh5.c b/arch/sh/drivers/pci/pci-sh5.c
index 16c1e721bf54..8229114c6a58 100644
--- a/arch/sh/drivers/pci/pci-sh5.c
+++ b/arch/sh/drivers/pci/pci-sh5.c
@@ -20,7 +20,6 @@
 #include <linux/types.h>
 #include <linux/irq.h>
 #include <cpu/irq.h>
-#include <asm/pci.h>
 #include <asm/io.h>
 #include "pci-sh5.h"
 
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 43715308b068..bf91037db4e0 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,7 @@
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
 #endif
 
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index f6bd1406b897..85c97b188d71 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ extern void __xchg_called_with_bad_pointer(void);
  * if something tries to do an invalid cmpxchg(). */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
 		unsigned long new, int size)
 {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 699255d6d1c6..b788a9bc8918 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,
diff --git a/arch/sh/include/asm/mm-arch-hooks.h b/arch/sh/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..18087298b728
--- /dev/null
+++ b/arch/sh/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_SH_MM_ARCH_HOOKS_H
+#define _ASM_SH_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SH_MM_ARCH_HOOKS_H */
diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h
index 5b4511552998..e343dbd02e41 100644
--- a/arch/sh/include/asm/pci.h
+++ b/arch/sh/include/asm/pci.h
@@ -86,24 +86,6 @@ extern void pcibios_set_master(struct pci_dev *dev);
  * direct memory write.
  */
 #define PCI_DISABLE_MWI
-
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-
-	if (byte == 0)
-		cacheline_size = L1_CACHE_BYTES;
-	else
-		cacheline_size = byte << 2;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
 #endif
 
 /* Board-specific fixup routines. */
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
index 1fdf1ee672de..7f54bf2f453d 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7734.c
@@ -246,8 +246,7 @@ int __init arch_clk_init(void)
 	for (i = 0; i < ARRAY_SIZE(main_clks); i++)
 		ret |= clk_register(main_clks[i]);
 
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
index 9a28fdb36387..e40ec2c97ad1 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7757.c
@@ -141,8 +141,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
index 17d0ea55a5a2..8eb6e62340c9 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7785.c
@@ -164,8 +164,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
index bec2a83f1ba5..5e50e7ebeff0 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7786.c
@@ -179,8 +179,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/kernel/cpu/sh4a/clock-shx3.c b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
index 9a49a44f6f94..605221d1448a 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-shx3.c
@@ -138,8 +138,8 @@ int __init arch_clk_init(void)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++)
 		ret |= clk_register(clks[i]);
-	for (i = 0; i < ARRAY_SIZE(lookups); i++)
-		clkdev_add(&lookups[i]);
+
+	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
 	if (!ret)
 		ret = sh_clk_div4_register(div4_clks, ARRAY_SIZE(div4_clks),
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index a58fec9b55e0..79d8276377d1 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -17,6 +17,7 @@
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 #include <asm/io_trapped.h>
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
@@ -438,9 +439,9 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * with pagefaults disabled then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 534bc978af8a..6385f60209b6 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -62,11 +62,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 int pmd_huge(pmd_t pmd)
 {
 	return 0;
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index b688731d7ede..c9d2b922734b 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -33,10 +33,10 @@ static int md5_sparc64_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = cpu_to_le32(0x67452301);
-	mctx->hash[1] = cpu_to_le32(0xefcdab89);
-	mctx->hash[2] = cpu_to_le32(0x98badcfe);
-	mctx->hash[3] = cpu_to_le32(0x10325476);
+	mctx->hash[0] = cpu_to_le32(MD5_H0);
+	mctx->hash[1] = cpu_to_le32(MD5_H1);
+	mctx->hash[2] = cpu_to_le32(MD5_H2);
+	mctx->hash[3] = cpu_to_le32(MD5_H3);
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 76648941fea7..809941e33e12 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define dma_rmb()	rmb()
 #define dma_wmb()	wmb()
 
-#define set_mb(__var, __value) \
-	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+	do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52dca216..83ffb83c5397 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
  *
  * Cribbed from <asm-parisc/atomic.h>
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
 void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6cfbf68..faa2f61058c2 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 
 #include <asm-generic/cmpxchg-local.h>
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long
 __cmpxchg_u32(volatile int *m, int old, int new)
 {
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6e424d185d0..a6cfdabb6054 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,7 +24,8 @@ typedef struct {
 	unsigned int	icache_line_size;
 	unsigned int	ecache_size;
 	unsigned int	ecache_line_size;
-	int		core_id;
+	unsigned short	sock_id;
+	unsigned short	core_id;
 	int		proc_id;
 } cpuinfo_sparc;
 
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index e4cab465b81f..3130d7636312 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -11,10 +11,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
 					 unsigned long len) {
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index 407ac14295f4..57f26c398dc9 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -129,6 +129,7 @@ static inline void sbus_memcpy_toio(volatile void __iomem *dst,
 void __iomem *ioremap(unsigned long offset, unsigned long size);
 #define ioremap_nocache(X,Y)	ioremap((X),(Y))
 #define ioremap_wc(X,Y)		ioremap((X),(Y))
+#define ioremap_wt(X,Y)		ioremap((X),(Y))
 void iounmap(volatile void __iomem *addr);
 
 /* Create a virtual mapping cookie for an IO port range */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 50d4840d9aeb..c32fa3f752c8 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -402,6 +402,7 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 
 #define ioremap_nocache(X,Y)		ioremap((X),(Y))
 #define ioremap_wc(X,Y)			ioremap((X),(Y))
+#define ioremap_wt(X,Y)			ioremap((X),(Y))
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/sparc/include/asm/mm-arch-hooks.h b/arch/sparc/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..b89ba44c16f1
--- /dev/null
+++ b/arch/sparc/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_SPARC_MM_ARCH_HOOKS_H
+#define _ASM_SPARC_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_SPARC_MM_ARCH_HOOKS_H */
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index 53e9b4987db0..b7c092df3134 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -22,16 +22,6 @@
 
 struct pci_dev;
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #endif /* __KERNEL__ */
 
 #ifndef CONFIG_LEON_PCI
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index bd00a6226169..022d16008a00 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -31,25 +31,6 @@
 #define PCI64_REQUIRED_MASK	(~(u64)0)
 #define PCI64_ADDR_BASE		0xfffc000000000000UL
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_BOUNDARY;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
 /* Return the index of the PCI controller for device PDEV. */
 
 int pci_domain_nr(struct pci_bus *bus);
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc165ebdf05a..131d36fcd07a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -308,12 +308,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
 	"	sllx		%1, 32, %1\n"
 	"	or		%0, %1, %0\n"
 	"	.previous\n"
+	"	.section	.sun_m7_2insn_patch, \"ax\"\n"
+	"	.word		661b\n"
+	"	sethi		%%uhi(%4), %1\n"
+	"	sethi		%%hi(%4), %0\n"
+	"	.word		662b\n"
+	"	or		%1, %%ulo(%4), %1\n"
+	"	or		%0, %%lo(%4), %0\n"
+	"	.word		663b\n"
+	"	sllx		%1, 32, %1\n"
+	"	or		%0, %1, %0\n"
+	"	.previous\n"
 	: "=r" (mask), "=r" (tmp)
 	: "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
 	       _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
 	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
 	       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+	  "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+	       _PAGE_CP_4V | _PAGE_E_4V |
 	       _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
 
 	return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -342,9 +356,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
 	"	andn		%0, %4, %0\n"
 	"	or		%0, %5, %0\n"
 	"	.previous\n"
+	"	.section	.sun_m7_2insn_patch, \"ax\"\n"
+	"	.word		661b\n"
+	"	andn		%0, %6, %0\n"
+	"	or		%0, %5, %0\n"
+	"	.previous\n"
 	: "=r" (val)
 	: "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
-	             "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+	             "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+	             "i" (_PAGE_CP_4V));
 
 	return __pgprot(val);
 }
@@ -845,10 +865,10 @@ static inline unsigned long pud_pfn(pud_t pud)
 void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		   pte_t *ptep, pte_t orig, int fullmm);
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long addr,
-				       pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr,
+					    pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
 	set_pmd_at(mm, addr, pmdp, __pmd(0UL));
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ed8f071132e4..01d17046225a 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -40,11 +40,12 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(&cpu_core_sib_map[cpu])
+#define topology_sibling_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
 static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
         return &cpu_core_map[cpu];
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 6fd4436d32f0..ec9c04de3664 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -79,6 +79,8 @@ struct sun4v_2insn_patch_entry {
 };
 extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
 	__sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+	__sun_m7_2insn_patch_end;
 
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index a35194b7dba0..ea6e9a20f3ff 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -49,6 +49,28 @@ do {										\
 	__asm__ __volatile__ ("wr %%g0, %0, %%asi" : : "r" ((val).seg));	\
 } while(0)
 
+/*
+ * Test whether a block of memory is a valid user space address.
+ * Returns 0 if the range is valid, nonzero otherwise.
+ */
+static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
+{
+	if (__builtin_constant_p(size))
+		return addr > limit - size;
+
+	addr += size;
+	if (addr < size)
+		return true;
+
+	return addr > limit;
+}
+
+#define __range_not_ok(addr, size, limit)                               \
+({                                                                      \
+	__chk_user_ptr(addr);                                           \
+	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
+})
+
 static inline int __access_ok(const void __user * addr, unsigned long size)
 {
 	return 1;
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 07cc49e541f4..0f679421b468 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -69,6 +69,8 @@ void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
 			     struct sun4v_1insn_patch_entry *);
 void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
 			     struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+			     struct sun4v_2insn_patch_entry *);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 7d3ca30fcd15..1ae5eb1bb045 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -2086,6 +2086,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
 	int err;
+	struct scatterlist *s;
 
 	if (map_perm & ~LDC_MAP_ALL)
 		return -EINVAL;
@@ -2112,9 +2113,10 @@ int ldc_map_sg(struct ldc_channel *lp,
 	state.pte_idx = (base - iommu->page_table);
 	state.nc = 0;
 
-	for (i = 0; i < num_sg; i++)
-		fill_cookies(&state, page_to_pfn(sg_page(&sg[i])) << PAGE_SHIFT,
-			     sg[i].offset, sg[i].length);
+	for_each_sg(sg, s, num_sg, i) {
+		fill_cookies(&state, page_to_pfn(sg_page(s)) << PAGE_SHIFT,
+			     s->offset, s->length);
+	}
 
 	return state.nc;
 }
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 94e392bdee7d..814fb1729b12 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -723,7 +723,6 @@ static int grpci2_of_probe(struct platform_device *ofdev)
 		err = -ENOMEM;
 		goto err1;
 	}
-	memset(grpci2priv, 0, sizeof(*grpci2priv));
 	priv->regs = regs;
 	priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
 	priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 26c80e18d7b1..6f80936e0eea 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -614,45 +614,68 @@ static void fill_in_one_cache(cpuinfo_sparc *c, struct mdesc_handle *hp, u64 mp)
 	}
 }
 
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+				 char *srch_val,
+				 void (*func)(struct mdesc_handle *, u64, int),
+				 u64 val, int depth)
 {
-	u64 a;
-
-	mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
-		u64 t = mdesc_arc_target(hp, a);
-		const char *name;
-		const u64 *id;
+	u64 arc;
 
-		name = mdesc_node_name(hp, t);
-		if (!strcmp(name, "cpu")) {
-			id = mdesc_get_property(hp, t, "id", NULL);
-			if (*id < NR_CPUS)
-				cpu_data(*id).core_id = core_id;
-		} else {
-			u64 j;
+	/* Since we have an estimate of recursion depth, do a sanity check. */
+	if (depth == 0)
+		return;
 
-			mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
-				u64 n = mdesc_arc_target(hp, j);
-				const char *n_name;
+	mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 n = mdesc_arc_target(hp, arc);
+		const char *name = mdesc_node_name(hp, n);
 
-				n_name = mdesc_node_name(hp, n);
-				if (strcmp(n_name, "cpu"))
-					continue;
+		if (!strcmp(srch_val, name))
+			(*func)(hp, n, val);
 
-				id = mdesc_get_property(hp, n, "id", NULL);
-				if (*id < NR_CPUS)
-					cpu_data(*id).core_id = core_id;
-			}
-		}
+		find_back_node_value(hp, n, srch_val, func, val, depth-1);
 	}
 }
 
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+			   int core_id)
+{
+	const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+	if (*id < num_possible_cpus())
+		cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+			   int sock_id)
+{
+	const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+	if (*id < num_possible_cpus())
+		cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+			  int core_id)
+{
+	find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+			  int sock_id)
+{
+	find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
 static void set_core_ids(struct mdesc_handle *hp)
 {
 	int idx;
 	u64 mp;
 
 	idx = 1;
+
+	/* Identify unique cores by looking for cpus backpointed to by
+	 * level 1 instruction caches.
+	 */
 	mdesc_for_each_node_by_name(hp, mp, "cache") {
 		const u64 *level;
 		const char *type;
@@ -667,11 +690,72 @@ static void set_core_ids(struct mdesc_handle *hp)
 			continue;
 
 		mark_core_ids(hp, mp, idx);
+		idx++;
+	}
+}
+
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+	u64 mp;
+	int idx = 1;
+	int fnd = 0;
+
+	/* Identify unique sockets by looking for cpus backpointed to by
+	 * shared level n caches.
+	 */
+	mdesc_for_each_node_by_name(hp, mp, "cache") {
+		const u64 *cur_lvl;
+
+		cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+		if (*cur_lvl != level)
+			continue;
+
+		mark_sock_ids(hp, mp, idx);
+		idx++;
+		fnd = 1;
+	}
+	return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+	int idx = 1;
 
+	mdesc_for_each_node_by_name(hp, mp, "socket") {
+		u64 a;
+
+		mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+			u64 t = mdesc_arc_target(hp, a);
+			const char *name;
+			const u64 *id;
+
+			name = mdesc_node_name(hp, t);
+			if (strcmp(name, "cpu"))
+				continue;
+
+			id = mdesc_get_property(hp, t, "id", NULL);
+			if (*id < num_possible_cpus())
+				cpu_data(*id).sock_id = idx;
+		}
 		idx++;
 	}
 }
 
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+	u64 mp;
+
+	/* If machine description exposes sockets data use it.
+	 * Otherwise fallback to use shared L3 or L2 caches.
+	 */
+	mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+	if (mp != MDESC_NODE_NULL)
+		return set_sock_ids_by_socket(hp, mp);
+
+	if (!set_sock_ids_by_cache(hp, 3))
+		set_sock_ids_by_cache(hp, 2);
+}
+
 static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
 {
 	u64 a;
@@ -707,7 +791,6 @@ static void __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name)
 			continue;
 
 		mark_proc_ids(hp, mp, idx);
-
 		idx++;
 	}
 }
@@ -900,6 +983,7 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
 
 	set_core_ids(hp);
 	set_proc_ids(hp);
+	set_sock_ids(hp);
 
 	mdesc_release(hp);
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 6f7251fd2eab..c928bc64b4ba 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1002,6 +1002,38 @@ static int __init pcibios_init(void)
 subsys_initcall(pcibios_init);
 
 #ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE  11  /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+	struct pci_dev *pdev;
+	struct pci_bus *bus;
+
+	list_for_each_entry(pdev, &pbus->devices, bus_list) {
+		char name[SLOT_NAME_SIZE];
+		struct pci_slot *pci_slot;
+		const u32 *slot_num;
+		int len;
+
+		slot_num = of_get_property(pdev->dev.of_node,
+					   "physical-slot#", &len);
+
+		if (slot_num == NULL || len != 4)
+			continue;
+
+		snprintf(name, sizeof(name), "%u", slot_num[0]);
+		pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+		if (IS_ERR(pci_slot))
+			pr_err("PCI: pci_create_slot returned %ld.\n",
+			       PTR_ERR(pci_slot));
+	}
+
+	list_for_each_entry(bus, &pbus->children, node)
+		pcie_bus_slot_names(bus);
+}
+
 static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
 {
 	const struct pci_slot_names {
@@ -1053,18 +1085,29 @@ static int __init of_pci_slot_init(void)
 
 	while ((pbus = pci_find_next_bus(pbus)) != NULL) {
 		struct device_node *node;
+		struct pci_dev *pdev;
+
+		pdev = list_first_entry(&pbus->devices, struct pci_dev,
+					bus_list);
 
-		if (pbus->self) {
-			/* PCI->PCI bridge */
-			node = pbus->self->dev.of_node;
+		if (pdev && pci_is_pcie(pdev)) {
+			pcie_bus_slot_names(pbus);
 		} else {
-			struct pci_pbm_info *pbm = pbus->sysdata;
 
-			/* Host PCI controller */
-			node = pbm->op->dev.of_node;
-		}
+			if (pbus->self) {
+
+				/* PCI->PCI bridge */
+				node = pbus->self->dev.of_node;
+
+			} else {
+				struct pci_pbm_info *pbm = pbus->sysdata;
 
-		pci_bus_slot_names(node, pbus);
+				/* Host PCI controller */
+				node = pbm->op->dev.of_node;
+			}
+
+			pci_bus_slot_names(node, pbus);
+		}
 	}
 
 	return 0;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 59cf917a77b5..689db65f8529 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -21,7 +21,7 @@
 
 #include <asm/stacktrace.h>
 #include <asm/cpudata.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <asm/nmi.h>
 #include <asm/pcr.h>
@@ -1741,18 +1741,31 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	} while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	/* addresses should be at least 4-byte aligned */
+	if (((unsigned long) fp) & 3)
+		return 0;
+
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 				   struct pt_regs *regs)
 {
 	unsigned long ufp;
 
-	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
+	ufp = regs->u_regs[UREG_FP] + STACK_BIAS;
 	do {
 		struct sparc_stackf __user *usf;
 		struct sparc_stackf sf;
 		unsigned long pc;
 
 		usf = (struct sparc_stackf __user *)ufp;
+		if (!valid_user_frame(usf, sizeof(sf)))
+			break;
+
 		if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 			break;
 
@@ -1767,7 +1780,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 {
 	unsigned long ufp;
 
-	ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
+	ufp = regs->u_regs[UREG_FP] & 0xffffffffUL;
 	do {
 		unsigned long pc;
 
@@ -1803,8 +1816,13 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		return;
 
 	flushw_user();
+
+	pagefault_disable();
+
 	if (test_thread_flag(TIF_32BIT))
 		perf_callchain_user_32(entry, regs);
 	else
 		perf_callchain_user_64(entry, regs);
+
+	pagefault_enable();
 }
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c38d19fc27ba..f7b261749383 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -255,6 +255,24 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
 	}
 }
 
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+			     struct sun4v_2insn_patch_entry *end)
+{
+	while (start < end) {
+		unsigned long addr = start->addr;
+
+		*(unsigned int *) (addr +  0) = start->insns[0];
+		wmb();
+		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
+
+		*(unsigned int *) (addr +  4) = start->insns[1];
+		wmb();
+		__asm__ __volatile__("flush	%0" : : "r" (addr +  4));
+
+		start++;
+	}
+}
+
 static void __init sun4v_patch(void)
 {
 	extern void sun4v_hvapi_init(void);
@@ -267,6 +285,9 @@ static void __init sun4v_patch(void)
 
 	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
 				&__sun4v_2insn_patch_end);
+	if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+		sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+					 &__sun_m7_2insn_patch_end);
 
 	sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 61139d9924ca..19cd08d18672 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -60,8 +60,12 @@ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
 	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+	[0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
 
 static cpumask_t smp_commenced_mask;
 
@@ -1243,6 +1247,15 @@ void smp_fill_in_sib_core_maps(void)
 		}
 	}
 
+	for_each_present_cpu(i)  {
+		unsigned int j;
+
+		for_each_present_cpu(j)  {
+			if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+				cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+		}
+	}
+
 	for_each_present_cpu(i) {
 		unsigned int j;
 
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 09243057cb0b..f1a2f688b28a 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -138,6 +138,11 @@ SECTIONS
 		*(.pause_3insn_patch)
 		__pause_3insn_patch_end = .;
 	}
+	.sun_m7_2insn_patch : {
+		__sun_m7_2insn_patch = .;
+		*(.sun_m7_2insn_patch)
+		__sun_m7_2insn_patch_end = .;
+	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 70d817154fe8..c399e7b3b035 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -21,6 +21,7 @@
 #include <linux/perf_event.h>
 #include <linux/interrupt.h>
 #include <linux/kdebug.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -29,7 +30,6 @@
 #include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
-#include <asm/uaccess.h>
 
 #include "mm_32.h"
 
@@ -196,7 +196,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (pagefault_disabled() || !mm)
 		goto no_context;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 479823249429..dbabe5713a15 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -22,12 +22,12 @@
 #include <linux/kdebug.h>
 #include <linux/percpu.h>
 #include <linux/context_tracking.h>
+#include <linux/uaccess.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
-#include <asm/uaccess.h>
 #include <asm/asi.h>
 #include <asm/lsu.h>
 #include <asm/sections.h>
@@ -330,7 +330,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto intr_or_no_mm;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
@@ -413,8 +413,9 @@ good_area:
 	 * that here.
 	 */
 	if ((fault_code & FAULT_CODE_ITLB) && !(vma->vm_flags & VM_EXEC)) {
-		BUG_ON(address != regs->tpc);
-		BUG_ON(regs->tstate & TSTATE_PRIV);
+		WARN(address != regs->tpc,
+		     "address (%lx) != regs->tpc (%lx)\n", address, regs->tpc);
+		WARN_ON(regs->tstate & TSTATE_PRIV);
 		goto bad_area;
 	}
 
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 449f864f0cef..a454ec5ff07a 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -53,7 +53,7 @@ void *kmap_atomic(struct page *page)
 	unsigned long vaddr;
 	long idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -91,6 +91,7 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (vaddr < FIXADDR_START) { // FIXME
 		pagefault_enable();
+		preempt_enable();
 		return;
 	}
 
@@ -126,5 +127,6 @@ void __kunmap_atomic(void *kvaddr)
 
 	kmap_atomic_idx_pop();
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 4242eab12e10..131eaf4ad7f5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -172,11 +172,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	return pte;
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 4ca0d6ba5ec8..4ac88b757514 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -54,6 +54,7 @@
 #include "init_64.h"
 
 unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
 
 /* A bitmap, two bits for every 256MB of physical memory.  These two
  * bits determine what page size we use for kernel linear
@@ -1909,11 +1910,24 @@ static void __init sun4u_linear_pte_xor_finalize(void)
 
 static void __init sun4v_linear_pte_xor_finalize(void)
 {
+	unsigned long pagecv_flag;
+
+	/* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+	 * enables MCD error. Do not set bit 9 on M7 processor.
+	 */
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+		pagecv_flag = 0x00;
+		break;
+	default:
+		pagecv_flag = _PAGE_CV_4V;
+		break;
+	}
 #ifndef CONFIG_DEBUG_PAGEALLOC
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
 		kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
@@ -1922,7 +1936,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
 		kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
@@ -1931,7 +1945,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
 	if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
 		kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
 			PAGE_OFFSET;
-		kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+		kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
 					   _PAGE_P_4V | _PAGE_W_4V);
 	} else {
 		kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
@@ -1952,12 +1966,20 @@ static phys_addr_t __init available_memory(void)
 	phys_addr_t pa_start, pa_end;
 	u64 i;
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,
+				&pa_end, NULL)
 		available = available + (pa_end  - pa_start);
 
 	return available;
 }
 
+#define _PAGE_CACHE_4U	(_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V	(_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U	 (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V	 (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
 /* We need to exclude reserved regions. This exclusion will include
  * vmlinux and initrd. To be more precise the initrd size could be used to
  * compute a new lower limit because it is freed later during initialization.
@@ -1971,7 +1993,8 @@ static void __init reduce_memory(phys_addr_t limit_ram)
 	if (limit_ram >= avail_ram)
 		return;
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &pa_start,
+				&pa_end, NULL) {
 		phys_addr_t region_size = pa_end - pa_start;
 		phys_addr_t clip_start = pa_start;
 
@@ -2034,6 +2057,25 @@ void __init paging_init(void)
 	memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
 #endif
 
+	/* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+	 * bit on M7 processor. This is a conflicting usage of the same
+	 * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+	 * Detection error on all pages and this will lead to problems
+	 * later. Kernel does not run with MCD enabled and hence rest
+	 * of the required steps to fully configure memory corruption
+	 * detection are not taken. We need to ensure TTE.mcde is not
+	 * set on M7 processor. Compute the value of cacheability
+	 * flag for use later taking this into consideration.
+	 */
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_SPARC_M7:
+		page_cache4v_flag = _PAGE_CP_4V;
+		break;
+	default:
+		page_cache4v_flag = _PAGE_CACHE_4V;
+		break;
+	}
+
 	if (tlb_type == hypervisor)
 		sun4v_pgprot_init();
 	else
@@ -2274,13 +2316,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-#define _PAGE_CACHE_4U	(_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V	(_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U	 (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V	 (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
 pgprot_t PAGE_KERNEL __read_mostly;
 EXPORT_SYMBOL(PAGE_KERNEL);
 
@@ -2312,8 +2347,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 		    _PAGE_P_4U | _PAGE_W_4U);
 	if (tlb_type == hypervisor)
 		pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-			    _PAGE_CP_4V | _PAGE_CV_4V |
-			    _PAGE_P_4V | _PAGE_W_4V);
+			    page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
 
 	pte_base |= _PAGE_PMD_HUGE;
 
@@ -2450,14 +2484,14 @@ static void __init sun4v_pgprot_init(void)
 	int i;
 
 	PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
-				_PAGE_CACHE_4V | _PAGE_P_4V |
+				page_cache4v_flag | _PAGE_P_4V |
 				__ACCESS_BITS_4V | __DIRTY_BITS_4V |
 				_PAGE_EXEC_4V);
 	PAGE_KERNEL_LOCKED = PAGE_KERNEL;
 
 	_PAGE_IE = _PAGE_IE_4V;
 	_PAGE_E = _PAGE_E_4V;
-	_PAGE_CACHE = _PAGE_CACHE_4V;
+	_PAGE_CACHE = page_cache4v_flag;
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
@@ -2465,8 +2499,8 @@ static void __init sun4v_pgprot_init(void)
 	kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
 		PAGE_OFFSET;
 #endif
-	kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
-				   _PAGE_P_4V | _PAGE_W_4V);
+	kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+				   _PAGE_W_4V);
 
 	for (i = 1; i < 4; i++)
 		kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
@@ -2479,12 +2513,12 @@ static void __init sun4v_pgprot_init(void)
 			     _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
 			     _PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
 
-	page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
-	page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+	page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 		       __ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
-	page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 		       __ACCESS_BITS_4V | _PAGE_EXEC_4V);
-	page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+	page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
 			 __ACCESS_BITS_4V | _PAGE_EXEC_4V);
 
 	page_exec_bit = _PAGE_EXEC_4V;
@@ -2542,7 +2576,7 @@ static unsigned long kern_large_tte(unsigned long paddr)
 	       _PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
 	if (tlb_type == hypervisor)
 		val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-		       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+		       page_cache4v_flag | _PAGE_P_4V |
 		       _PAGE_EXEC_4V | _PAGE_W_4V);
 
 	return val | paddr;
@@ -2706,7 +2740,7 @@ void hugetlb_setup(struct pt_regs *regs)
 	struct mm_struct *mm = current->mm;
 	struct tsb_config *tp;
 
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		const struct exception_table_entry *entry;
 
 		entry = search_exception_tables(regs->tpc);
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index a07e31b50d3f..59cf0b911898 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -28,6 +28,7 @@ config TILE
 	select HAVE_DEBUG_STACKOVERFLOW
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_CONTEXT_TRACKING
+	select EDAC_SUPPORT
 
 # FIXME: investigate whether we need/want these options.
 #	select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 7b11c5fadd42..0496970cef82 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,9 +105,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/tile/include/asm/edac.h b/arch/tile/include/asm/edac.h
deleted file mode 100644
index 87fc83eeaffd..000000000000
--- a/arch/tile/include/asm/edac.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Copyright 2011 Tilera Corporation. All Rights Reserved.
- *
- *   This program is free software; you can redistribute it and/or
- *   modify it under the terms of the GNU General Public License
- *   as published by the Free Software Foundation, version 2.
- *
- *   This program is distributed in the hope that it will be useful, but
- *   WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- *   NON INFRINGEMENT.  See the GNU General Public License for
- *   more details.
- */
-
-#ifndef _ASM_TILE_EDAC_H
-#define _ASM_TILE_EDAC_H
-
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static inline void atomic_scrub(void *va, u32 size)
-{
-	/*
-	 * These is nothing to be done here because CE is
-	 * corrected by the mshim.
-	 */
-	return;
-}
-
-#endif /* _ASM_TILE_EDAC_H */
diff --git a/arch/tile/include/asm/hugetlb.h b/arch/tile/include/asm/hugetlb.h
index 3257733003f8..1abd00c55236 100644
--- a/arch/tile/include/asm/hugetlb.h
+++ b/arch/tile/include/asm/hugetlb.h
@@ -40,10 +40,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,
diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h
index 6ef4ecab1df2..dc61de15c1f9 100644
--- a/arch/tile/include/asm/io.h
+++ b/arch/tile/include/asm/io.h
@@ -54,7 +54,7 @@ extern void iounmap(volatile void __iomem *addr);
 
 #define ioremap_nocache(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wc(physaddr, size)		ioremap(physaddr, size)
-#define ioremap_writethrough(physaddr, size)	ioremap(physaddr, size)
+#define ioremap_wt(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_fullcache(physaddr, size)	ioremap(physaddr, size)
 
 #define mmiowb()
diff --git a/arch/tile/include/asm/mm-arch-hooks.h b/arch/tile/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..d1709ea774f7
--- /dev/null
+++ b/arch/tile/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_TILE_MM_ARCH_HOOKS_H
+#define _ASM_TILE_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_TILE_MM_ARCH_HOOKS_H */
diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h
index 95a4f19d16c5..2b05ccbebed9 100644
--- a/arch/tile/include/asm/pgtable.h
+++ b/arch/tile/include/asm/pgtable.h
@@ -414,10 +414,10 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 }
 
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address,
-				       pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address,
+					    pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, pmdp_ptep(pmdp)));
 }
diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h
index 938311844233..76b0d0ebb244 100644
--- a/arch/tile/include/asm/topology.h
+++ b/arch/tile/include/asm/topology.h
@@ -55,7 +55,7 @@ static inline const struct cpumask *cpumask_of_node(int node)
 #define topology_physical_package_id(cpu)       ((void)(cpu), 0)
 #define topology_core_id(cpu)                   (cpu)
 #define topology_core_cpumask(cpu)              ((void)(cpu), cpu_online_mask)
-#define topology_thread_cpumask(cpu)            cpumask_of(cpu)
+#define topology_sibling_cpumask(cpu)           cpumask_of(cpu)
 #endif
 
 #endif /* _ASM_TILE_TOPOLOGY_H */
diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h
index f41cb53cf645..a33276bf5ca1 100644
--- a/arch/tile/include/asm/uaccess.h
+++ b/arch/tile/include/asm/uaccess.h
@@ -78,7 +78,8 @@ int __range_ok(unsigned long addr, unsigned long size);
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -192,7 +193,8 @@ extern int __get_user_bad(void)
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -274,7 +276,8 @@ extern int __put_user_bad(void)
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -330,7 +333,8 @@ extern int __put_user_bad(void)
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -366,7 +370,8 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -437,7 +442,8 @@ static inline unsigned long __must_check copy_from_user(void *to,
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to user space.  Caller must check
  * the specified blocks with access_ok() before calling this function.
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index e83cc999da02..3f4f58d34a92 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -354,9 +354,9 @@ static int handle_page_fault(struct pt_regs *regs,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running in an
-	 * atomic region then we must not take the fault.
+	 * region with pagefaults disabled then we must not take the fault.
 	 */
-	if (in_atomic() || !mm) {
+	if (pagefault_disabled() || !mm) {
 		vma = NULL;  /* happy compiler */
 		goto bad_area_nosemaphore;
 	}
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index 6aa2f2625447..fcd545014e79 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -201,7 +201,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	int idx, type;
 	pte_t *pte;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 
 	/* Avoid icache flushes by disallowing atomic executable mappings. */
@@ -259,6 +259,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/tile/mm/hugetlbpage.c b/arch/tile/mm/hugetlbpage.c
index 8416240c322c..c034dc3fe2d4 100644
--- a/arch/tile/mm/hugetlbpage.c
+++ b/arch/tile/mm/hugetlbpage.c
@@ -160,11 +160,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_HUGE_PAGE);
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	return 0;
-}
-
 #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
diff --git a/arch/um/include/asm/mm-arch-hooks.h b/arch/um/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..a7c8b0dfdd4e
--- /dev/null
+++ b/arch/um/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_UM_MM_ARCH_HOOKS_H
+#define _ASM_UM_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_UM_MM_ARCH_HOOKS_H */
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 8e4daf44e980..47ff9b7f3e5d 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/current.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -35,10 +36,10 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	*code_out = SEGV_MAPERR;
 
 	/*
-	 * If the fault was during atomic operation, don't take the fault, just
+	 * If the fault was with pagefaults disabled, don't take the fault, just
 	 * fail.
 	 */
-	if (in_atomic())
+	if (faulthandler_disabled())
 		goto out_nosemaphore;
 
 	if (is_user)
diff --git a/arch/unicore32/include/asm/mm-arch-hooks.h b/arch/unicore32/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..4d79a850c509
--- /dev/null
+++ b/arch/unicore32/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_UNICORE32_MM_ARCH_HOOKS_H
+#define _ASM_UNICORE32_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_UNICORE32_MM_ARCH_HOOKS_H */
diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h
index 654407e98619..38b3f3785c3c 100644
--- a/arch/unicore32/include/asm/pci.h
+++ b/arch/unicore32/include/asm/pci.h
@@ -18,16 +18,6 @@
 #include <asm-generic/pci.h>
 #include <mach/hardware.h> /* for PCIBIOS_MIN_* */
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 	enum pci_mmap_state mmap_state, int write_combine);
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index 0dc922dba915..afccef5529cc 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -218,7 +218,7 @@ static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (faulthandler_disabled() || !mm)
 		goto no_context;
 
 	if (user_mode(regs))
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 3942f74c92d7..1538562cc720 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,3 +1,6 @@
+
+obj-y += entry/
+
 obj-$(CONFIG_KVM) += kvm/
 
 # Xen paravirtualization support
@@ -11,7 +14,7 @@ obj-y += kernel/
 obj-y += mm/
 
 obj-y += crypto/
-obj-y += vdso/
+
 obj-$(CONFIG_IA32_EMULATION) += ia32/
 
 obj-y += platform/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 226d5696e1d1..8e0b76ad8350 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -9,140 +9,143 @@ config 64BIT
 config X86_32
 	def_bool y
 	depends on !64BIT
-	select CLKSRC_I8253
-	select HAVE_UID16
 
 config X86_64
 	def_bool y
 	depends on 64BIT
-	select X86_DEV_DMA_OPS
-	select ARCH_USE_CMPXCHG_LOCKREF
-	select HAVE_LIVEPATCH
 
 ### Arch settings
 config X86
 	def_bool y
-	select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
-	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
+	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
+	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
+	select ANON_INODES
+	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_DISCARD_MEMBLOCK
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
-	select HAVE_AOUT if X86_32
-	select HAVE_UNSTABLE_SCHED_CLOCK
-	select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
-	select ARCH_SUPPORTS_INT128 if X86_64
-	select HAVE_IDE
-	select HAVE_OPROFILE
-	select HAVE_PCSPKR_PLATFORM
-	select HAVE_PERF_EVENTS
-	select HAVE_IOREMAP_PROT
-	select HAVE_KPROBES
-	select HAVE_MEMBLOCK
-	select HAVE_MEMBLOCK_NODE_MAP
-	select ARCH_DISCARD_MEMBLOCK
-	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_INT128		if X86_64
+	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
+	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS
-	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS
-	select HAVE_KRETPROBES
+	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
+	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select BUILDTIME_EXTABLE_SORT
+	select CLKEVT_I8253
+	select CLKSRC_I8253			if X86_32
+	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
+	select CLOCKSOURCE_WATCHDOG
+	select CLONE_BACKWARDS			if X86_32
+	select COMPAT_OLD_SIGACTION		if IA32_EMULATION
+	select DCACHE_WORD_ACCESS
+	select EDAC_ATOMIC_SCRUB
+	select EDAC_SUPPORT
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if X86_64 || (X86_32 && X86_LOCAL_APIC)
+	select GENERIC_CLOCKEVENTS_MIN_ADJUST
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
-	select HAVE_OPTPROBES
-	select HAVE_KPROBES_ON_FTRACE
-	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FENTRY if X86_64
+	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_IOMAP
+	select GENERIC_IRQ_PROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_PENDING_IRQ		if SMP
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL
+	select HAVE_ACPI_APEI			if ACPI
+	select HAVE_ACPI_APEI_NMI		if ACPI
+	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
+	select HAVE_AOUT			if X86_32
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KASAN			if X86_64 && SPARSEMEM_VMEMMAP
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_KMEMCHECK
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_SOFT_DIRTY		if X86_64
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_BPF_JIT			if X86_64
+	select HAVE_CC_STACKPROTECTOR
+	select HAVE_CMPXCHG_DOUBLE
+	select HAVE_CMPXCHG_LOCAL
+	select HAVE_CONTEXT_TRACKING		if X86_64
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_GRAPH_FP_TEST
-	select HAVE_SYSCALL_TRACEPOINTS
-	select SYSCTL_EXCEPTION_TRACE
-	select HAVE_KVM
-	select HAVE_ARCH_KGDB
-	select HAVE_ARCH_TRACEHOOK
-	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select USER_STACKTRACE_SUPPORT
-	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_DMA_API_DEBUG
-	select HAVE_KERNEL_GZIP
+	select HAVE_FENTRY			if X86_64
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_FP_TEST
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
+	select HAVE_GENERIC_DMA_COHERENT	if X86_32
+	select HAVE_HW_BREAKPOINT
+	select HAVE_IDE
+	select HAVE_IOREMAP_PROT
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK	if X86_64
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KERNEL_BZIP2
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
-	select HAVE_KERNEL_XZ
 	select HAVE_KERNEL_LZO
-	select HAVE_KERNEL_LZ4
-	select HAVE_HW_BREAKPOINT
+	select HAVE_KERNEL_XZ
+	select HAVE_KPROBES
+	select HAVE_KPROBES_ON_FTRACE
+	select HAVE_KRETPROBES
+	select HAVE_KVM
+	select HAVE_LIVEPATCH			if X86_64
+	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MIXED_BREAKPOINTS_REGS
-	select PERF_EVENTS
+	select HAVE_OPROFILE
+	select HAVE_OPTPROBES
+	select HAVE_PCSPKR_PLATFORM
+	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_DEBUG_KMEMLEAK
-	select ANON_INODES
-	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
-	select HAVE_CMPXCHG_LOCAL
-	select HAVE_CMPXCHG_DOUBLE
-	select HAVE_ARCH_KMEMCHECK
-	select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_UID16			if X86_32
+	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
-	select ARCH_HAS_ELF_RANDOMIZE
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select SPARSE_IRQ
-	select GENERIC_FIND_FIRST_BIT
-	select GENERIC_IRQ_PROBE
-	select GENERIC_PENDING_IRQ if SMP
-	select GENERIC_IRQ_SHOW
-	select GENERIC_CLOCKEVENTS_MIN_ADJUST
 	select IRQ_FORCED_THREADING
-	select HAVE_BPF_JIT if X86_64
-	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
-	select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE)
-	select ARCH_HAS_SG_CHAIN
-	select CLKEVT_I8253
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select GENERIC_IOMAP
-	select DCACHE_WORD_ACCESS
-	select GENERIC_SMP_IDLE_THREAD
-	select ARCH_WANT_IPC_PARSE_VERSION if X86_32
-	select HAVE_ARCH_SECCOMP_FILTER
-	select BUILDTIME_EXTABLE_SORT
-	select GENERIC_CMOS_UPDATE
-	select HAVE_ARCH_SOFT_DIRTY if X86_64
-	select CLOCKSOURCE_WATCHDOG
-	select GENERIC_CLOCKEVENTS
-	select ARCH_CLOCKSOURCE_DATA
-	select CLOCKSOURCE_VALIDATE_LAST_CYCLE
-	select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
-	select GENERIC_TIME_VSYSCALL
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_CONTEXT_TRACKING if X86_64
-	select HAVE_IRQ_TIME_ACCOUNTING
-	select VIRT_TO_BUS
-	select MODULES_USE_ELF_REL if X86_32
-	select MODULES_USE_ELF_RELA if X86_64
-	select CLONE_BACKWARDS if X86_32
-	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_QUEUE_RWLOCK
-	select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
-	select OLD_SIGACTION if X86_32
-	select COMPAT_OLD_SIGACTION if IA32_EMULATION
+	select MODULES_USE_ELF_RELA		if X86_64
+	select MODULES_USE_ELF_REL		if X86_32
+	select OLD_SIGACTION			if X86_32
+	select OLD_SIGSUSPEND3			if X86_32 || IA32_EMULATION
+	select PERF_EVENTS
 	select RTC_LIB
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
-	select HAVE_CC_STACKPROTECTOR
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select HAVE_ACPI_APEI if ACPI
-	select HAVE_ACPI_APEI_NMI if ACPI
-	select ACPI_LEGACY_TABLES_LOOKUP if ACPI
-	select X86_FEATURE_NAMES if PROC_FS
+	select SPARSE_IRQ
 	select SRCU
+	select SYSCTL_EXCEPTION_TRACE
+	select USER_STACKTRACE_SUPPORT
+	select VIRT_TO_BUS
+	select X86_DEV_DMA_OPS			if X86_64
+	select X86_FEATURE_NAMES		if PROC_FS
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -260,10 +263,6 @@ config X86_64_SMP
 	def_bool y
 	depends on X86_64 && SMP
 
-config X86_HT
-	def_bool y
-	depends on SMP
-
 config X86_32_LAZY_GS
 	def_bool y
 	depends on X86_32 && !CC_STACKPROTECTOR
@@ -341,7 +340,7 @@ config X86_FEATURE_NAMES
 
 config X86_X2APIC
 	bool "Support x2apic"
-	depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
+	depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST)
 	---help---
 	  This enables x2apic support on CPUs that have this feature.
 
@@ -441,6 +440,7 @@ config X86_UV
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
 	depends on X86_X2APIC
+	depends on PCI
 	---help---
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
@@ -466,7 +466,6 @@ config X86_INTEL_CE
 	select X86_REBOOTFIXUPS
 	select OF
 	select OF_EARLY_FLATTREE
-	select IRQ_DOMAIN
 	---help---
 	  Select for the Intel CE media processor (CE4100) SOC.
 	  This option compiles in support for the CE4100 SOC for settop
@@ -666,7 +665,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
-	select UNINLINE_SPIN_UNLOCK
+	select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
@@ -851,11 +850,12 @@ config NR_CPUS
 	default "1" if !SMP
 	default "8192" if MAXSMP
 	default "32" if SMP && X86_BIGSMP
-	default "8" if SMP
+	default "8" if SMP && X86_32
+	default "64" if SMP
 	---help---
 	  This allows you to specify the maximum number of CPUs which this
 	  kernel will support.  If CPUMASK_OFFSTACK is enabled, the maximum
-	  supported value is 4096, otherwise the maximum value is 512.  The
+	  supported value is 8192, otherwise the maximum value is 512.  The
 	  minimum value which makes sense is 2.
 
 	  This is purely to save memory - each supported CPU adds
@@ -863,7 +863,7 @@ config NR_CPUS
 
 config SCHED_SMT
 	bool "SMT (Hyperthreading) scheduler support"
-	depends on X86_HT
+	depends on SMP
 	---help---
 	  SMT scheduler support improves the CPU scheduler's decision making
 	  when dealing with Intel Pentium 4 chips with HyperThreading at a
@@ -873,7 +873,7 @@ config SCHED_SMT
 config SCHED_MC
 	def_bool y
 	prompt "Multi-core scheduler support"
-	depends on X86_HT
+	depends on SMP
 	---help---
 	  Multi-core scheduler support improves the CPU scheduler's decision
 	  making when dealing with multi-core CPU chips at a cost of slightly
@@ -914,12 +914,12 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
 	def_bool y
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
-	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+	select IRQ_DOMAIN_HIERARCHY
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
 
 config X86_IO_APIC
 	def_bool y
 	depends on X86_LOCAL_APIC || X86_UP_IOAPIC
-	select IRQ_DOMAIN
 
 config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
 	bool "Reroute for broken boot IRQs"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 72484a645f05..a15893d17c55 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -332,4 +332,27 @@ config X86_DEBUG_STATIC_CPU_HAS
 
 	  If unsure, say N.
 
+config X86_DEBUG_FPU
+	bool "Debug the x86 FPU code"
+	depends on DEBUG_KERNEL
+	default y
+	---help---
+	  If this option is enabled then there will be extra sanity
+	  checks and (boot time) debug printouts added to the kernel.
+	  This debugging adds some small amount of runtime overhead
+	  to the kernel.
+
+	  If unsure, say N.
+
+config PUNIT_ATOM_DEBUG
+	tristate "ATOM Punit debug driver"
+	select DEBUG_FS
+	select IOSF_MBI
+	---help---
+	  This is a debug driver, which gets the power states
+	  of all Punit North Complex devices. The power states of
+	  each device is exposed as part of the debugfs interface.
+	  The current power state can be read from
+	  /sys/kernel/debug/punit_atom/dev_power_state
+
 endmenu
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2fda005bb334..118e6debc483 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -77,6 +77,12 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
+        # Align jump targets to 1 byte, not the default 16 bytes:
+        KBUILD_CFLAGS += -falign-jumps=1
+
+        # Pack loops tightly as well:
+        KBUILD_CFLAGS += -falign-loops=1
+
         # Don't autogenerate traditional x87 instructions
         KBUILD_CFLAGS += $(call cc-option,-mno-80387)
         KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
@@ -84,6 +90,9 @@ else
 	# Use -mpreferred-stack-boundary=3 if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
 
+	# Use -mskip-rax-setup if supported.
+	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
         cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
@@ -140,12 +149,6 @@ endif
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp
 
-# do binutils support CFI?
-cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
-# is .cfi_signal_frame supported too?
-cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
-cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
 asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
@@ -153,8 +156,8 @@ asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
@@ -178,7 +181,7 @@ archscripts: scripts_basic
 # Syscall table generation
 
 archheaders:
-	$(Q)$(MAKE) $(build)=arch/x86/syscalls all
+	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
 archprepare:
 ifeq ($(CONFIG_KEXEC_FILE),y)
@@ -241,7 +244,7 @@ install:
 
 PHONY += vdso_install
 vdso_install:
-	$(Q)$(MAKE) $(build)=arch/x86/vdso $@
+	$(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@
 
 archclean:
 	$(Q)rm -rf $(objtree)/arch/i386
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ef17683484e9..48304b89b601 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1109,6 +1109,8 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (!cmdline_ptr)
 		goto fail;
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
+	/* Fill in upper bits of command line address, NOP on 32 bit  */
+	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
 
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 89dd0d78013a..805d25ca5f1d 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -2,15 +2,14 @@
 #define BOOT_COMPRESSED_MISC_H
 
 /*
- * we have to be careful, because no indirections are allowed here, and
- * paravirt_ops is a kind of one. As it will only run in baremetal anyway,
- * we just keep it from happening
+ * Special hack: we have to be careful, because no indirections are allowed here,
+ * and paravirt_ops is a kind of one. As it will only run in baremetal anyway,
+ * we just keep it from happening. (This list needs to be extended when new
+ * paravirt and debugging variants are added.)
  */
 #undef CONFIG_PARAVIRT
+#undef CONFIG_PARAVIRT_SPINLOCKS
 #undef CONFIG_KASAN
-#ifdef CONFIG_X86_32
-#define _ASM_X86_DESC_H 1
-#endif
 
 #include <linux/linkage.h>
 #include <linux/screen_info.h>
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 112cefacf2af..2bfc8a7c88c1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -32,7 +32,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
 #include <crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>
@@ -44,15 +44,19 @@
 #endif
 
 
+#define AESNI_ALIGN	16
+#define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE - 1))
+#define RFC4106_HASH_SUBKEY_SIZE 16
+
 /* This data is stored at the end of the crypto_tfm struct.
  * It's a type of per "session" data storage location.
  * This needs to be 16 byte aligned.
  */
 struct aesni_rfc4106_gcm_ctx {
-	u8 hash_subkey[16];
-	struct crypto_aes_ctx aes_key_expanded;
+	u8 hash_subkey[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	struct crypto_aes_ctx aes_key_expanded
+		__attribute__ ((__aligned__(AESNI_ALIGN)));
 	u8 nonce[4];
-	struct cryptd_aead *cryptd_tfm;
 };
 
 struct aesni_gcm_set_hash_subkey_result {
@@ -66,10 +70,6 @@ struct aesni_hash_subkey_req_data {
 	struct scatterlist sg;
 };
 
-#define AESNI_ALIGN	(16)
-#define AES_BLOCK_MASK	(~(AES_BLOCK_SIZE-1))
-#define RFC4106_HASH_SUBKEY_SIZE 16
-
 struct aesni_lrw_ctx {
 	struct lrw_table_ctx lrw_table;
 	u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
@@ -283,10 +283,11 @@ static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out,
 static inline struct
 aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm)
 {
-	return
-		(struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)
-		crypto_tfm_ctx(crypto_aead_tfm(tfm)), AESNI_ALIGN);
+	unsigned long align = AESNI_ALIGN;
+
+	if (align <= crypto_tfm_ctx_alignment())
+		align = 1;
+	return PTR_ALIGN(crypto_aead_ctx(tfm), align);
 }
 #endif
 
@@ -790,36 +791,30 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 #endif
 
 #ifdef CONFIG_X86_64
-static int rfc4106_init(struct crypto_tfm *tfm)
+static int rfc4106_init(struct crypto_aead *aead)
 {
 	struct cryptd_aead *cryptd_tfm;
-	struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
-	struct crypto_aead *cryptd_child;
-	struct aesni_rfc4106_gcm_ctx *child_ctx;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
 	cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni",
 				       CRYPTO_ALG_INTERNAL,
 				       CRYPTO_ALG_INTERNAL);
 	if (IS_ERR(cryptd_tfm))
 		return PTR_ERR(cryptd_tfm);
 
-	cryptd_child = cryptd_aead_child(cryptd_tfm);
-	child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child);
-	memcpy(child_ctx, ctx, sizeof(*ctx));
-	ctx->cryptd_tfm = cryptd_tfm;
-	tfm->crt_aead.reqsize = sizeof(struct aead_request)
-		+ crypto_aead_reqsize(&cryptd_tfm->base);
+	*ctx = cryptd_tfm;
+	crypto_aead_set_reqsize(
+		aead,
+		sizeof(struct aead_request) +
+		crypto_aead_reqsize(&cryptd_tfm->base));
 	return 0;
 }
 
-static void rfc4106_exit(struct crypto_tfm *tfm)
+static void rfc4106_exit(struct crypto_aead *aead)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx =
-		(struct aesni_rfc4106_gcm_ctx *)
-		PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN);
-	if (!IS_ERR(ctx->cryptd_tfm))
-		cryptd_free_aead(ctx->cryptd_tfm);
-	return;
+	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
+
+	cryptd_free_aead(*ctx);
 }
 
 static void
@@ -845,8 +840,6 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 	if (IS_ERR(ctr_tfm))
 		return PTR_ERR(ctr_tfm);
 
-	crypto_ablkcipher_clear_flags(ctr_tfm, ~0);
-
 	ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len);
 	if (ret)
 		goto out_free_ablkcipher;
@@ -895,73 +888,29 @@ out_free_ablkcipher:
 static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 				  unsigned int key_len)
 {
-	int ret = 0;
-	struct crypto_tfm *tfm = crypto_aead_tfm(aead);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead);
-	u8 *new_key_align, *new_key_mem = NULL;
 
 	if (key_len < 4) {
-		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 	/*Account for 4 byte nonce at the end.*/
 	key_len -= 4;
-	if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 &&
-	    key_len != AES_KEYSIZE_256) {
-		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
 
 	memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce));
-	/*This must be on a 16 byte boundary!*/
-	if ((unsigned long)(&(ctx->aes_key_expanded.key_enc[0])) % AESNI_ALIGN)
-		return -EINVAL;
-
-	if ((unsigned long)key % AESNI_ALIGN) {
-		/*key is not aligned: use an auxuliar aligned pointer*/
-		new_key_mem = kmalloc(key_len+AESNI_ALIGN, GFP_KERNEL);
-		if (!new_key_mem)
-			return -ENOMEM;
-
-		new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN);
-		memcpy(new_key_align, key, key_len);
-		key = new_key_align;
-	}
 
-	if (!irq_fpu_usable())
-		ret = crypto_aes_expand_key(&(ctx->aes_key_expanded),
-		key, key_len);
-	else {
-		kernel_fpu_begin();
-		ret = aesni_set_key(&(ctx->aes_key_expanded), key, key_len);
-		kernel_fpu_end();
-	}
-	/*This must be on a 16 byte boundary!*/
-	if ((unsigned long)(&(ctx->hash_subkey[0])) % AESNI_ALIGN) {
-		ret = -EINVAL;
-		goto exit;
-	}
-	ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
-exit:
-	kfree(new_key_mem);
-	return ret;
+	return aes_set_key_common(crypto_aead_tfm(aead),
+				  &ctx->aes_key_expanded, key, key_len) ?:
+	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
 }
 
 static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
 			   unsigned int key_len)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
-	struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
-	struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child);
-	struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm;
-	int ret;
+	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	ret = crypto_aead_setkey(child, key, key_len);
-	if (!ret) {
-		memcpy(ctx, c_ctx, sizeof(*ctx));
-		ctx->cryptd_tfm = cryptd_tfm;
-	}
-	return ret;
+	return crypto_aead_setkey(&cryptd_tfm->base, key, key_len);
 }
 
 static int common_rfc4106_set_authsize(struct crypto_aead *aead,
@@ -975,7 +924,7 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 	default:
 		return -EINVAL;
 	}
-	crypto_aead_crt(aead)->authsize = authsize;
+
 	return 0;
 }
 
@@ -984,30 +933,23 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 static int rfc4106_set_authsize(struct crypto_aead *parent,
 				unsigned int authsize)
 {
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent);
-	struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm);
-	int ret;
+	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
+	struct cryptd_aead *cryptd_tfm = *ctx;
 
-	ret = crypto_aead_setauthsize(child, authsize);
-	if (!ret)
-		crypto_aead_crt(parent)->authsize = authsize;
-	return ret;
+	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
 }
 
-static int __driver_rfc4106_encrypt(struct aead_request *req)
+static int helper_rfc4106_encrypt(struct aead_request *req)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
 	__be32 counter = cpu_to_be32(1);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv_tab[16+AESNI_ALIGN];
-	u8* iv = (u8 *) PTR_ALIGN((u8 *)iv_tab, AESNI_ALIGN);
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk assoc_sg_walk;
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
@@ -1016,12 +958,6 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 	/* to 8 or 12 bytes */
 	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
 		return -EINVAL;
-	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
-	        return -EINVAL;
-	if (unlikely(key_len != AES_KEYSIZE_128 &&
-	             key_len != AES_KEYSIZE_192 &&
-	             key_len != AES_KEYSIZE_256))
-	        return -EINVAL;
 
 	/* IV below built */
 	for (i = 0; i < 4; i++)
@@ -1030,55 +966,57 @@ static int __driver_rfc4106_encrypt(struct aead_request *req)
 		*(iv+4+i) = req->iv[i];
 	*((__be32 *)(iv+12)) = counter;
 
-	if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+	if (sg_is_last(req->src) &&
+	    req->src->offset + req->src->length <= PAGE_SIZE &&
+	    sg_is_last(req->dst) &&
+	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
-		scatterwalk_start(&assoc_sg_walk, req->assoc);
-		src = scatterwalk_map(&src_sg_walk);
-		assoc = scatterwalk_map(&assoc_sg_walk);
+		assoc = scatterwalk_map(&src_sg_walk);
+		src = assoc + req->assoclen;
 		dst = src;
 		if (unlikely(req->src != req->dst)) {
 			scatterwalk_start(&dst_sg_walk, req->dst);
-			dst = scatterwalk_map(&dst_sg_walk);
+			dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
 		}
-
 	} else {
 		/* Allocate memory for src, dst, assoc */
-		src = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
+		assoc = kmalloc(req->cryptlen + auth_tag_len + req->assoclen,
 			GFP_ATOMIC);
-		if (unlikely(!src))
+		if (unlikely(!assoc))
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
-		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
-		scatterwalk_map_and_copy(assoc, req->assoc, 0,
-					req->assoclen, 0);
+		scatterwalk_map_and_copy(assoc, req->src, 0,
+					 req->assoclen + req->cryptlen, 0);
+		src = assoc + req->assoclen;
 		dst = src;
 	}
 
+	kernel_fpu_begin();
 	aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv,
 		ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst
 		+ ((unsigned long)req->cryptlen), auth_tag_len);
+	kernel_fpu_end();
 
 	/* The authTag (aka the Integrity Check Value) needs to be written
 	 * back to the packet. */
 	if (one_entry_in_sg) {
 		if (unlikely(req->src != req->dst)) {
-			scatterwalk_unmap(dst);
-			scatterwalk_done(&dst_sg_walk, 0, 0);
+			scatterwalk_unmap(dst - req->assoclen);
+			scatterwalk_advance(&dst_sg_walk, req->dst->length);
+			scatterwalk_done(&dst_sg_walk, 1, 0);
 		}
-		scatterwalk_unmap(src);
 		scatterwalk_unmap(assoc);
-		scatterwalk_done(&src_sg_walk, 0, 0);
-		scatterwalk_done(&assoc_sg_walk, 0, 0);
+		scatterwalk_advance(&src_sg_walk, req->src->length);
+		scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0,
-			req->cryptlen + auth_tag_len, 1);
-		kfree(src);
+		scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+					 req->cryptlen + auth_tag_len, 1);
+		kfree(assoc);
 	}
 	return 0;
 }
 
-static int __driver_rfc4106_decrypt(struct aead_request *req)
+static int helper_rfc4106_decrypt(struct aead_request *req)
 {
 	u8 one_entry_in_sg = 0;
 	u8 *src, *dst, *assoc;
@@ -1087,26 +1025,16 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 	int retval = 0;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
-	u32 key_len = ctx->aes_key_expanded.key_length;
 	void *aes_ctx = &(ctx->aes_key_expanded);
 	unsigned long auth_tag_len = crypto_aead_authsize(tfm);
-	u8 iv_and_authTag[32+AESNI_ALIGN];
-	u8 *iv = (u8 *) PTR_ALIGN((u8 *)iv_and_authTag, AESNI_ALIGN);
-	u8 *authTag = iv + 16;
+	u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN)));
+	u8 authTag[16];
 	struct scatter_walk src_sg_walk;
-	struct scatter_walk assoc_sg_walk;
 	struct scatter_walk dst_sg_walk;
 	unsigned int i;
 
-	if (unlikely((req->cryptlen < auth_tag_len) ||
-		(req->assoclen != 8 && req->assoclen != 12)))
+	if (unlikely(req->assoclen != 8 && req->assoclen != 12))
 		return -EINVAL;
-	if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16))
-	        return -EINVAL;
-	if (unlikely(key_len != AES_KEYSIZE_128 &&
-	             key_len != AES_KEYSIZE_192 &&
-	             key_len != AES_KEYSIZE_256))
-	        return -EINVAL;
 
 	/* Assuming we are supporting rfc4106 64-bit extended */
 	/* sequence numbers We need to have the AAD length */
@@ -1120,33 +1048,36 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		*(iv+4+i) = req->iv[i];
 	*((__be32 *)(iv+12)) = counter;
 
-	if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) {
+	if (sg_is_last(req->src) &&
+	    req->src->offset + req->src->length <= PAGE_SIZE &&
+	    sg_is_last(req->dst) &&
+	    req->dst->offset + req->dst->length <= PAGE_SIZE) {
 		one_entry_in_sg = 1;
 		scatterwalk_start(&src_sg_walk, req->src);
-		scatterwalk_start(&assoc_sg_walk, req->assoc);
-		src = scatterwalk_map(&src_sg_walk);
-		assoc = scatterwalk_map(&assoc_sg_walk);
+		assoc = scatterwalk_map(&src_sg_walk);
+		src = assoc + req->assoclen;
 		dst = src;
 		if (unlikely(req->src != req->dst)) {
 			scatterwalk_start(&dst_sg_walk, req->dst);
-			dst = scatterwalk_map(&dst_sg_walk);
+			dst = scatterwalk_map(&dst_sg_walk) + req->assoclen;
 		}
 
 	} else {
 		/* Allocate memory for src, dst, assoc */
-		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
-		if (!src)
+		assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
+		if (!assoc)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen);
-		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
-		scatterwalk_map_and_copy(assoc, req->assoc, 0,
-			req->assoclen, 0);
+		scatterwalk_map_and_copy(assoc, req->src, 0,
+					 req->assoclen + req->cryptlen, 0);
+		src = assoc + req->assoclen;
 		dst = src;
 	}
 
+	kernel_fpu_begin();
 	aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv,
 		ctx->hash_subkey, assoc, (unsigned long)req->assoclen,
 		authTag, auth_tag_len);
+	kernel_fpu_end();
 
 	/* Compare generated tag with passed in tag. */
 	retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ?
@@ -1154,90 +1085,59 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 
 	if (one_entry_in_sg) {
 		if (unlikely(req->src != req->dst)) {
-			scatterwalk_unmap(dst);
-			scatterwalk_done(&dst_sg_walk, 0, 0);
+			scatterwalk_unmap(dst - req->assoclen);
+			scatterwalk_advance(&dst_sg_walk, req->dst->length);
+			scatterwalk_done(&dst_sg_walk, 1, 0);
 		}
-		scatterwalk_unmap(src);
 		scatterwalk_unmap(assoc);
-		scatterwalk_done(&src_sg_walk, 0, 0);
-		scatterwalk_done(&assoc_sg_walk, 0, 0);
+		scatterwalk_advance(&src_sg_walk, req->src->length);
+		scatterwalk_done(&src_sg_walk, req->src == req->dst, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
-		kfree(src);
+		scatterwalk_map_and_copy(dst, req->dst, req->assoclen,
+					 tempCipherLen, 1);
+		kfree(assoc);
 	}
 	return retval;
 }
 
 static int rfc4106_encrypt(struct aead_request *req)
 {
-	int ret;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+	struct aead_request *subreq = aead_request_ctx(req);
 
-	if (!irq_fpu_usable()) {
-		struct aead_request *cryptd_req =
-			(struct aead_request *) aead_request_ctx(req);
+	aead_request_set_tfm(subreq, irq_fpu_usable() ?
+				     cryptd_aead_child(cryptd_tfm) :
+				     &cryptd_tfm->base);
 
-		memcpy(cryptd_req, req, sizeof(*req));
-		aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		ret = crypto_aead_encrypt(cryptd_req);
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_encrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	return crypto_aead_encrypt(subreq);
 }
 
 static int rfc4106_decrypt(struct aead_request *req)
 {
-	int ret;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm);
+	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
+	struct cryptd_aead *cryptd_tfm = *ctx;
+	struct aead_request *subreq = aead_request_ctx(req);
 
-	if (!irq_fpu_usable()) {
-		struct aead_request *cryptd_req =
-			(struct aead_request *) aead_request_ctx(req);
+	aead_request_set_tfm(subreq, irq_fpu_usable() ?
+				     cryptd_aead_child(cryptd_tfm) :
+				     &cryptd_tfm->base);
 
-		memcpy(cryptd_req, req, sizeof(*req));
-		aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		ret = crypto_aead_decrypt(cryptd_req);
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_decrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
-}
-
-static int helper_rfc4106_encrypt(struct aead_request *req)
-{
-	int ret;
-
-	if (unlikely(!irq_fpu_usable())) {
-		WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
-		ret = -EINVAL;
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_encrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
-}
-
-static int helper_rfc4106_decrypt(struct aead_request *req)
-{
-	int ret;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
 
-	if (unlikely(!irq_fpu_usable())) {
-		WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context");
-		ret = -EINVAL;
-	} else {
-		kernel_fpu_begin();
-		ret = __driver_rfc4106_decrypt(req);
-		kernel_fpu_end();
-	}
-	return ret;
+	return crypto_aead_decrypt(subreq);
 }
 #endif
 
@@ -1410,51 +1310,6 @@ static struct crypto_alg aesni_algs[] = { {
 			.geniv		= "chainiv",
 		},
 	},
-}, {
-	.cra_name		= "__gcm-aes-aesni",
-	.cra_driver_name	= "__driver-gcm-aes-aesni",
-	.cra_priority		= 0,
-	.cra_flags		= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx) +
-				  AESNI_ALIGN,
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_aead_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u = {
-		.aead = {
-			.setkey		= common_rfc4106_set_key,
-			.setauthsize	= common_rfc4106_set_authsize,
-			.encrypt	= helper_rfc4106_encrypt,
-			.decrypt	= helper_rfc4106_decrypt,
-			.ivsize		= 8,
-			.maxauthsize	= 16,
-		},
-	},
-}, {
-	.cra_name		= "rfc4106(gcm(aes))",
-	.cra_driver_name	= "rfc4106-gcm-aesni",
-	.cra_priority		= 400,
-	.cra_flags		= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx) +
-				  AESNI_ALIGN,
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_nivaead_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= rfc4106_init,
-	.cra_exit		= rfc4106_exit,
-	.cra_u = {
-		.aead = {
-			.setkey		= rfc4106_set_key,
-			.setauthsize	= rfc4106_set_authsize,
-			.encrypt	= rfc4106_encrypt,
-			.decrypt	= rfc4106_decrypt,
-			.geniv		= "seqiv",
-			.ivsize		= 8,
-			.maxauthsize	= 16,
-		},
-	},
 #endif
 #if IS_ENABLED(CONFIG_CRYPTO_PCBC)
 }, {
@@ -1569,6 +1424,46 @@ static struct crypto_alg aesni_algs[] = { {
 	},
 } };
 
+#ifdef CONFIG_X86_64
+static struct aead_alg aesni_aead_algs[] = { {
+	.setkey			= common_rfc4106_set_key,
+	.setauthsize		= common_rfc4106_set_authsize,
+	.encrypt		= helper_rfc4106_encrypt,
+	.decrypt		= helper_rfc4106_decrypt,
+	.ivsize			= 8,
+	.maxauthsize		= 16,
+	.base = {
+		.cra_name		= "__gcm-aes-aesni",
+		.cra_driver_name	= "__driver-gcm-aes-aesni",
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx),
+		.cra_alignmask		= AESNI_ALIGN - 1,
+		.cra_module		= THIS_MODULE,
+	},
+}, {
+	.init			= rfc4106_init,
+	.exit			= rfc4106_exit,
+	.setkey			= rfc4106_set_key,
+	.setauthsize		= rfc4106_set_authsize,
+	.encrypt		= rfc4106_encrypt,
+	.decrypt		= rfc4106_decrypt,
+	.ivsize			= 8,
+	.maxauthsize		= 16,
+	.base = {
+		.cra_name		= "rfc4106(gcm(aes))",
+		.cra_driver_name	= "rfc4106-gcm-aesni",
+		.cra_priority		= 400,
+		.cra_flags		= CRYPTO_ALG_ASYNC,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct cryptd_aead *),
+		.cra_module		= THIS_MODULE,
+	},
+} };
+#else
+static struct aead_alg aesni_aead_algs[0];
+#endif
+
 
 static const struct x86_cpu_id aesni_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_AES),
@@ -1616,11 +1511,27 @@ static int __init aesni_init(void)
 	if (err)
 		return err;
 
-	return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+	err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+	if (err)
+		goto fpu_exit;
+
+	err = crypto_register_aeads(aesni_aead_algs,
+				    ARRAY_SIZE(aesni_aead_algs));
+	if (err)
+		goto unregister_algs;
+
+	return err;
+
+unregister_algs:
+	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
+fpu_exit:
+	crypto_fpu_exit();
+	return err;
 }
 
 static void __exit aesni_exit(void)
 {
+	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 
 	crypto_fpu_exit();
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index baf0ac21ace5..4c65c70e628b 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -561,16 +560,15 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
 		pr_info("AVX2 or AES-NI instructions are not detected.\n");
 		return -ENODEV;
 	}
 
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX2 detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 78818a1e73e3..80a0e4389c9a 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -19,8 +19,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/camellia.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -553,16 +552,10 @@ static struct crypto_alg cmll_algs[10] = { {
 
 static int __init camellia_aesni_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
-		pr_info("AVX or AES-NI instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 236c80974457..be00aa48b2b5 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -31,8 +31,7 @@
 #include <crypto/cast5.h>
 #include <crypto/cryptd.h>
 #include <crypto/ctr.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST5_PARALLEL_BLOCKS 16
@@ -468,16 +467,10 @@ static struct crypto_alg cast5_algs[6] = { {
 
 static int __init cast5_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index f448810ca4ac..5dbba7224221 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/glue_helper.h>
 
 #define CAST6_PARALLEL_BLOCKS 8
@@ -590,16 +589,10 @@ static struct crypto_alg cast6_algs[10] = { {
 
 static int __init cast6_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		pr_info("AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 1937fc1d8763..07d2c6c86a54 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -35,7 +35,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 28640c3d6af7..81a595d75cf5 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -32,8 +32,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index b6c67bf30fdf..a3fcfc97a311 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -29,7 +29,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_device_id.h>
 
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index f368ba261739..e7d679e2a018 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -18,7 +18,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct crypto_fpu_ctx {
 	struct crypto_blkcipher *child;
@@ -156,7 +156,7 @@ int __init crypto_fpu_init(void)
 	return crypto_register_template(&crypto_fpu_tmpl);
 }
 
-void __exit crypto_fpu_exit(void)
+void crypto_fpu_exit(void)
 {
 	crypto_unregister_template(&crypto_fpu_tmpl);
 }
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 2079baf06bdd..64d7cf1b50e1 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,7 +19,7 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/cpu_device_id.h>
 
 #define GHASH_BLOCK_SIZE	16
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2f63dc89e7a9..7d838dc4d888 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -20,8 +20,7 @@
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 #include <crypto/serpent.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -537,16 +536,14 @@ static struct crypto_alg srp_algs[10] = { {
 
 static int __init init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
 	if (!cpu_has_avx2 || !cpu_has_osxsave) {
 		pr_info("AVX2 instructions are not detected.\n");
 		return -ENODEV;
 	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index c8d478af8456..da7dafc9b16d 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -36,8 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/serpent-avx.h>
 #include <asm/crypto/glue_helper.h>
 
@@ -596,16 +595,10 @@ static struct crypto_alg serpent_algs[10] = { {
 
 static int __init serpent_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index e510b1c5d690..a841e9765bd6 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -65,11 +65,8 @@
 #include <crypto/mcryptd.h>
 #include <crypto/crypto_wq.h>
 #include <asm/byteorder.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
 #include <linux/hardirq.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/api.h>
 #include "sha_mb_ctx.h"
 
 #define FLUSH_INTERVAL 1000 /* in usec */
@@ -885,7 +882,8 @@ static int __init sha1_mb_mod_init(void)
 		INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
 		cpu_state->cpu = cpu;
 		cpu_state->alg_state = &sha1_mb_alg_state;
-		cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL);
+		cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr),
+					GFP_KERNEL);
 		if (!cpu_state->mgr)
 			goto err2;
 		sha1_ctx_mgr_init(cpu_state->mgr);
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 33d1b9dc14cc..7c48e8b20848 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -29,9 +29,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 
 asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
@@ -123,15 +121,9 @@ static struct shash_alg alg = {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index ccc338881ee8..f8097fc0d1d1 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -37,9 +37,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <linux/string.h>
 
 asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
@@ -132,15 +130,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index d9fa4c1e063f..2edad7b81870 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -35,9 +35,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 
 #include <linux/string.h>
 
@@ -131,15 +129,9 @@ static struct shash_alg algs[] = { {
 #ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
-	u64 xcr0;
-
-	if (!cpu_has_avx || !cpu_has_osxsave)
-		return false;
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		pr_info("AVX detected but unusable.\n");
-
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, NULL)) {
+		if (cpu_has_avx)
+			pr_info("AVX detected but unusable.\n");
 		return false;
 	}
 
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b5e2d5651851..c2bd0ce718ee 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -36,9 +36,7 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
-#include <asm/xsave.h>
+#include <asm/fpu/api.h>
 #include <asm/crypto/twofish.h>
 #include <asm/crypto/glue_helper.h>
 #include <crypto/scatterwalk.h>
@@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { {
 
 static int __init twofish_init(void)
 {
-	u64 xcr0;
+	const char *feature_name;
 
-	if (!cpu_has_avx || !cpu_has_osxsave) {
-		printk(KERN_INFO "AVX instructions are not detected.\n");
-		return -ENODEV;
-	}
-
-	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
-		printk(KERN_INFO "AVX detected but unusable.\n");
+	if (!cpu_has_xfeatures(XSTATE_SSE | XSTATE_YMM, &feature_name)) {
+		pr_info("CPU feature '%s' is not supported.\n", feature_name);
 		return -ENODEV;
 	}
 
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
new file mode 100644
index 000000000000..7a144971db79
--- /dev/null
+++ b/arch/x86/entry/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for the x86 low level entry code
+#
+obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+
+obj-y				+= vdso/
+obj-y				+= vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
+
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/entry/calling.h
index 1c8b50edb2db..f4e6308c4200 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/entry/calling.h
@@ -46,8 +46,6 @@ For 32-bit we have the following conventions - kernel is built with
 
 */
 
-#include <asm/dwarf2.h>
-
 #ifdef CONFIG_X86_64
 
 /*
@@ -91,28 +89,27 @@ For 32-bit we have the following conventions - kernel is built with
 #define SIZEOF_PTREGS	21*8
 
 	.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
-	subq	$15*8+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET 15*8+\addskip
+	addq	$-(15*8+\addskip), %rsp
 	.endm
 
 	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
 	.if \r11
-	movq_cfi r11, 6*8+\offset
+	movq %r11, 6*8+\offset(%rsp)
 	.endif
 	.if \r8910
-	movq_cfi r10, 7*8+\offset
-	movq_cfi r9,  8*8+\offset
-	movq_cfi r8,  9*8+\offset
+	movq %r10, 7*8+\offset(%rsp)
+	movq %r9,  8*8+\offset(%rsp)
+	movq %r8,  9*8+\offset(%rsp)
 	.endif
 	.if \rax
-	movq_cfi rax, 10*8+\offset
+	movq %rax, 10*8+\offset(%rsp)
 	.endif
 	.if \rcx
-	movq_cfi rcx, 11*8+\offset
+	movq %rcx, 11*8+\offset(%rsp)
 	.endif
-	movq_cfi rdx, 12*8+\offset
-	movq_cfi rsi, 13*8+\offset
-	movq_cfi rdi, 14*8+\offset
+	movq %rdx, 12*8+\offset(%rsp)
+	movq %rsi, 13*8+\offset(%rsp)
+	movq %rdi, 14*8+\offset(%rsp)
 	.endm
 	.macro SAVE_C_REGS offset=0
 	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
@@ -131,24 +128,24 @@ For 32-bit we have the following conventions - kernel is built with
 	.endm
 
 	.macro SAVE_EXTRA_REGS offset=0
-	movq_cfi r15, 0*8+\offset
-	movq_cfi r14, 1*8+\offset
-	movq_cfi r13, 2*8+\offset
-	movq_cfi r12, 3*8+\offset
-	movq_cfi rbp, 4*8+\offset
-	movq_cfi rbx, 5*8+\offset
+	movq %r15, 0*8+\offset(%rsp)
+	movq %r14, 1*8+\offset(%rsp)
+	movq %r13, 2*8+\offset(%rsp)
+	movq %r12, 3*8+\offset(%rsp)
+	movq %rbp, 4*8+\offset(%rsp)
+	movq %rbx, 5*8+\offset(%rsp)
 	.endm
 	.macro SAVE_EXTRA_REGS_RBP offset=0
-	movq_cfi rbp, 4*8+\offset
+	movq %rbp, 4*8+\offset(%rsp)
 	.endm
 
 	.macro RESTORE_EXTRA_REGS offset=0
-	movq_cfi_restore 0*8+\offset, r15
-	movq_cfi_restore 1*8+\offset, r14
-	movq_cfi_restore 2*8+\offset, r13
-	movq_cfi_restore 3*8+\offset, r12
-	movq_cfi_restore 4*8+\offset, rbp
-	movq_cfi_restore 5*8+\offset, rbx
+	movq 0*8+\offset(%rsp), %r15
+	movq 1*8+\offset(%rsp), %r14
+	movq 2*8+\offset(%rsp), %r13
+	movq 3*8+\offset(%rsp), %r12
+	movq 4*8+\offset(%rsp), %rbp
+	movq 5*8+\offset(%rsp), %rbx
 	.endm
 
 	.macro ZERO_EXTRA_REGS
@@ -162,24 +159,24 @@ For 32-bit we have the following conventions - kernel is built with
 
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
 	.if \rstor_r11
-	movq_cfi_restore 6*8, r11
+	movq 6*8(%rsp), %r11
 	.endif
 	.if \rstor_r8910
-	movq_cfi_restore 7*8, r10
-	movq_cfi_restore 8*8, r9
-	movq_cfi_restore 9*8, r8
+	movq 7*8(%rsp), %r10
+	movq 8*8(%rsp), %r9
+	movq 9*8(%rsp), %r8
 	.endif
 	.if \rstor_rax
-	movq_cfi_restore 10*8, rax
+	movq 10*8(%rsp), %rax
 	.endif
 	.if \rstor_rcx
-	movq_cfi_restore 11*8, rcx
+	movq 11*8(%rsp), %rcx
 	.endif
 	.if \rstor_rdx
-	movq_cfi_restore 12*8, rdx
+	movq 12*8(%rsp), %rdx
 	.endif
-	movq_cfi_restore 13*8, rsi
-	movq_cfi_restore 14*8, rdi
+	movq 13*8(%rsp), %rsi
+	movq 14*8(%rsp), %rdi
 	.endm
 	.macro RESTORE_C_REGS
 	RESTORE_C_REGS_HELPER 1,1,1,1,1
@@ -204,8 +201,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endm
 
 	.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
-	addq $15*8+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET -(15*8+\addskip)
+	subq $-(15*8+\addskip), %rsp
 	.endm
 
 	.macro icebp
@@ -224,23 +220,23 @@ For 32-bit we have the following conventions - kernel is built with
  */
 
 	.macro SAVE_ALL
-	pushl_cfi_reg eax
-	pushl_cfi_reg ebp
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg edx
-	pushl_cfi_reg ecx
-	pushl_cfi_reg ebx
+	pushl %eax
+	pushl %ebp
+	pushl %edi
+	pushl %esi
+	pushl %edx
+	pushl %ecx
+	pushl %ebx
 	.endm
 
 	.macro RESTORE_ALL
-	popl_cfi_reg ebx
-	popl_cfi_reg ecx
-	popl_cfi_reg edx
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi_reg ebp
-	popl_cfi_reg eax
+	popl %ebx
+	popl %ecx
+	popl %edx
+	popl %esi
+	popl %edi
+	popl %ebp
+	popl %eax
 	.endm
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
new file mode 100644
index 000000000000..21dc60a60b5f
--- /dev/null
+++ b/arch/x86/entry/entry_32.S
@@ -0,0 +1,1248 @@
+/*
+ *  Copyright (C) 1991,1992  Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * Stack layout in 'syscall_exit':
+ *	ptrace needs to have all registers on the stack.
+ *	If the order here is changed, it needs to be
+ *	updated in fork.c:copy_process(), signal.c:do_signal(),
+ *	ptrace.c and ptrace.h
+ *
+ *	 0(%esp) - %ebx
+ *	 4(%esp) - %ecx
+ *	 8(%esp) - %edx
+ *	 C(%esp) - %esi
+ *	10(%esp) - %edi
+ *	14(%esp) - %ebp
+ *	18(%esp) - %eax
+ *	1C(%esp) - %ds
+ *	20(%esp) - %es
+ *	24(%esp) - %fs
+ *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
+ *	2C(%esp) - orig_eax
+ *	30(%esp) - %eip
+ *	34(%esp) - %cs
+ *	38(%esp) - %eflags
+ *	3C(%esp) - %oldesp
+ *	40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/ftrace.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE		0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysenter_audit		syscall_trace_entry
+# define sysexit_audit		syscall_exit_work
+#endif
+
+	.section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization.  The following will never clobber any registers:
+ *   INTERRUPT_RETURN (aka. "iret")
+ *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel		restore_all
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)     # interrupts off?
+	jz	1f
+	TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc.  Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+	pushl	$0
+.endm
+.macro POP_GS pop=0
+	addl	$(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else	/* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+	pushl	%gs
+.endm
+
+.macro POP_GS pop=0
+98:	popl	%gs
+  .if \pop <> 0
+	add	$\pop, %esp
+  .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99:	movl	$0, (%esp)
+	jmp	98b
+.popsection
+	_ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98:	mov	PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99:	movl	$0, PT_GS(%esp)
+	jmp	98b
+.popsection
+	_ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+	movl	%gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+	movl	\reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+	movl	$(__KERNEL_STACK_CANARY), \reg
+	movl	\reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+.macro SAVE_ALL
+	cld
+	PUSH_GS
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+	movl	$(__USER_DS), %edx
+	movl	%edx, %ds
+	movl	%edx, %es
+	movl	$(__KERNEL_PERCPU), %edx
+	movl	%edx, %fs
+	SET_KERNEL_GS %edx
+.endm
+
+.macro RESTORE_INT_REGS
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+.endm
+
+.macro RESTORE_REGS pop=0
+	RESTORE_INT_REGS
+1:	popl	%ds
+2:	popl	%es
+3:	popl	%fs
+	POP_GS \pop
+.pushsection .fixup, "ax"
+4:	movl	$0, (%esp)
+	jmp	1b
+5:	movl	$0, (%esp)
+	jmp	2b
+6:	movl	$0, (%esp)
+	jmp	3b
+.popsection
+	_ASM_EXTABLE(1b, 4b)
+	_ASM_EXTABLE(2b, 5b)
+	_ASM_EXTABLE(3b, 6b)
+	POP_GS_EX
+.endm
+
+ENTRY(ret_from_fork)
+	pushl	%eax
+	call	schedule_tail
+	GET_THREAD_INFO(%ebp)
+	popl	%eax
+	pushl	$0x0202				# Reset kernel eflags
+	popfl
+	jmp	syscall_exit
+END(ret_from_fork)
+
+ENTRY(ret_from_kernel_thread)
+	pushl	%eax
+	call	schedule_tail
+	GET_THREAD_INFO(%ebp)
+	popl	%eax
+	pushl	$0x0202				# Reset kernel eflags
+	popfl
+	movl	PT_EBP(%esp), %eax
+	call	*PT_EBX(%esp)
+	movl	$0, PT_EAX(%esp)
+	jmp	syscall_exit
+ENDPROC(ret_from_kernel_thread)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+	# userspace resumption stub bypassing syscall exit tracing
+	ALIGN
+ret_from_exception:
+	preempt_stop(CLBR_ANY)
+ret_from_intr:
+	GET_THREAD_INFO(%ebp)
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+	/*
+	 * We can be coming here from child spawned by kernel_thread().
+	 */
+	movl	PT_CS(%esp), %eax
+	andl	$SEGMENT_RPL_MASK, %eax
+#endif
+	cmpl	$USER_RPL, %eax
+	jb	resume_kernel			# not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done on
+						# int/exception return?
+	jne	work_pending
+	jmp	restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+	DISABLE_INTERRUPTS(CLBR_ANY)
+need_resched:
+	cmpl	$0, PER_CPU_VAR(__preempt_count)
+	jnz	restore_all
+	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
+	jz	restore_all
+	call	preempt_schedule_irq
+	jmp	need_resched
+END(resume_kernel)
+#endif
+
+/*
+ * SYSENTER_RETURN points to after the SYSENTER instruction
+ * in the vsyscall page.  See vsyscall-sysentry.S, which defines
+ * the symbol.
+ */
+
+	# SYSENTER  call handler stub
+ENTRY(entry_SYSENTER_32)
+	movl	TSS_sysenter_sp0(%esp), %esp
+sysenter_past_esp:
+	/*
+	 * Interrupts are disabled here, but we can't trace it until
+	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
+	 * we immediately enable interrupts at that point anyway.
+	 */
+	pushl	$__USER_DS
+	pushl	%ebp
+	pushfl
+	orl	$X86_EFLAGS_IF, (%esp)
+	pushl	$__USER_CS
+	/*
+	 * Push current_thread_info()->sysenter_return to the stack.
+	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
+	 * is relative to thread_info, which is at the bottom of the
+	 * kernel stack page.  4*4 means the 4 words pushed above;
+	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+	 * and THREAD_SIZE takes us to the bottom.
+	 */
+	pushl	((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
+
+	pushl	%eax
+	SAVE_ALL
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+/*
+ * Load the potential sixth argument from user stack.
+ * Careful about security.
+ */
+	cmpl	$__PAGE_OFFSET-3, %ebp
+	jae	syscall_fault
+	ASM_STAC
+1:	movl	(%ebp), %ebp
+	ASM_CLAC
+	movl	%ebp, PT_EBP(%esp)
+	_ASM_EXTABLE(1b, syscall_fault)
+
+	GET_THREAD_INFO(%ebp)
+
+	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+	jnz	sysenter_audit
+sysenter_do_call:
+	cmpl	$(NR_syscalls), %eax
+	jae	sysenter_badsys
+	call	*sys_call_table(, %eax, 4)
+sysenter_after_call:
+	movl	%eax, PT_EAX(%esp)
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$_TIF_ALLWORK_MASK, %ecx
+	jnz	sysexit_audit
+sysenter_exit:
+/* if something modifies registers it must also disable sysexit */
+	movl	PT_EIP(%esp), %edx
+	movl	PT_OLDESP(%esp), %ecx
+	xorl	%ebp, %ebp
+	TRACE_IRQS_ON
+1:	mov	PT_FS(%esp), %fs
+	PTGS_TO_GS
+	ENABLE_INTERRUPTS_SYSEXIT
+
+#ifdef CONFIG_AUDITSYSCALL
+sysenter_audit:
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp)
+	jnz	syscall_trace_entry
+	/* movl	PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+	movl	PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
+	/* movl	PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+	pushl	PT_ESI(%esp)			/* a3: 5th arg */
+	pushl	PT_EDX+4(%esp)			/* a2: 4th arg */
+	call	__audit_syscall_entry
+	popl	%ecx				/* get that remapped edx off the stack */
+	popl	%ecx				/* get that remapped esi off the stack */
+	movl	PT_EAX(%esp), %eax		/* reload syscall number */
+	jmp	sysenter_do_call
+
+sysexit_audit:
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+	jnz	syscall_exit_work
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_ANY)
+	movl	%eax, %edx			/* second arg, syscall return value */
+	cmpl	$-MAX_ERRNO, %eax		/* is it an error ? */
+	setbe %al				/* 1 if so, 0 if not */
+	movzbl %al, %eax			/* zero-extend that */
+	call	__audit_syscall_exit
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
+	jnz	syscall_exit_work
+	movl	PT_EAX(%esp), %eax		/* reload syscall return value */
+	jmp	sysenter_exit
+#endif
+
+.pushsection .fixup, "ax"
+2:	movl	$0, PT_FS(%esp)
+	jmp	1b
+.popsection
+	_ASM_EXTABLE(1b, 2b)
+	PTGS_TO_GS_EX
+ENDPROC(entry_SYSENTER_32)
+
+	# system call handler stub
+ENTRY(entry_INT80_32)
+	ASM_CLAC
+	pushl	%eax				# save orig_eax
+	SAVE_ALL
+	GET_THREAD_INFO(%ebp)
+						# system call tracing in operation / emulation
+	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
+	jnz	syscall_trace_entry
+	cmpl	$(NR_syscalls), %eax
+	jae	syscall_badsys
+syscall_call:
+	call	*sys_call_table(, %eax, 4)
+syscall_after_call:
+	movl	%eax, PT_EAX(%esp)		# store the return value
+syscall_exit:
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	testl	$_TIF_ALLWORK_MASK, %ecx	# current->work
+	jnz	syscall_exit_work
+
+restore_all:
+	TRACE_IRQS_IRET
+restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
+	/*
+	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+	 * are returning to the kernel.
+	 * See comments in process.c:copy_thread() for details.
+	 */
+	movb	PT_OLDSS(%esp), %ah
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
+	je ldt_ss				# returning to user-space with LDT SS
+#endif
+restore_nocheck:
+	RESTORE_REGS 4				# skip orig_eax/error_code
+irq_return:
+	INTERRUPT_RETURN
+.section .fixup, "ax"
+ENTRY(iret_exc	)
+	pushl	$0				# no error code
+	pushl	$do_iret_error
+	jmp	error_code
+.previous
+	_ASM_EXTABLE(irq_return, iret_exc)
+
+#ifdef CONFIG_X86_ESPFIX32
+ldt_ss:
+#ifdef CONFIG_PARAVIRT
+	/*
+	 * The kernel can't run on a non-flat stack if paravirt mode
+	 * is active.  Rather than try to fixup the high bits of
+	 * ESP, bypass this code entirely.  This may break DOSemu
+	 * and/or Wine support in a paravirt VM, although the option
+	 * is still available to implement the setting of the high
+	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
+	 */
+	cmpl	$0, pv_info+PARAVIRT_enabled
+	jne	restore_nocheck
+#endif
+
+/*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+	mov	%esp, %edx			/* load kernel esp */
+	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
+	mov	%dx, %ax			/* eax: new kernel esp */
+	sub	%eax, %edx			/* offset (low word is 0) */
+	shr	$16, %edx
+	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
+	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
+	pushl	$__ESPFIX_SS
+	pushl	%eax				/* new kernel esp */
+	/*
+	 * Disable interrupts, but do not irqtrace this section: we
+	 * will soon execute iret and the tracer was already set to
+	 * the irqstate after the IRET:
+	 */
+	DISABLE_INTERRUPTS(CLBR_EAX)
+	lss	(%esp), %esp			/* switch to espfix segment */
+	jmp	restore_nocheck
+#endif
+ENDPROC(entry_INT80_32)
+
+	# perform work that needs to be done immediately before resumption
+	ALIGN
+work_pending:
+	testb	$_TIF_NEED_RESCHED, %cl
+	jz	work_notifysig
+work_resched:
+	call	schedule
+	LOCKDEP_SYS_EXIT
+	DISABLE_INTERRUPTS(CLBR_ANY)		# make sure we don't miss an interrupt
+						# setting need_resched or sigpending
+						# between sampling and the iret
+	TRACE_IRQS_OFF
+	movl	TI_flags(%ebp), %ecx
+	andl	$_TIF_WORK_MASK, %ecx		# is there any work to be done other
+						# than syscall tracing?
+	jz	restore_all
+	testb	$_TIF_NEED_RESCHED, %cl
+	jnz	work_resched
+
+work_notifysig:					# deal with pending signals and
+						# notify-resume requests
+#ifdef CONFIG_VM86
+	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esp)
+	movl	%esp, %eax
+	jnz	work_notifysig_v86		# returning to kernel-space or
+						# vm86-space
+1:
+#else
+	movl	%esp, %eax
+#endif
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	movb	PT_CS(%esp), %bl
+	andb	$SEGMENT_RPL_MASK, %bl
+	cmpb	$USER_RPL, %bl
+	jb	resume_kernel
+	xorl	%edx, %edx
+	call	do_notify_resume
+	jmp	resume_userspace
+
+#ifdef CONFIG_VM86
+	ALIGN
+work_notifysig_v86:
+	pushl	%ecx				# save ti_flags for do_notify_resume
+	call	save_v86_state			# %eax contains pt_regs pointer
+	popl	%ecx
+	movl	%eax, %esp
+	jmp	1b
+#endif
+END(work_pending)
+
+	# perform syscall exit tracing
+	ALIGN
+syscall_trace_entry:
+	movl	$-ENOSYS, PT_EAX(%esp)
+	movl	%esp, %eax
+	call	syscall_trace_enter
+	/* What it returned is what we'll actually use.  */
+	cmpl	$(NR_syscalls), %eax
+	jnae	syscall_call
+	jmp	syscall_exit
+END(syscall_trace_entry)
+
+	# perform syscall exit tracing
+	ALIGN
+syscall_exit_work:
+	testl	$_TIF_WORK_SYSCALL_EXIT, %ecx
+	jz	work_pending
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_ANY)		# could let syscall_trace_leave() call
+						# schedule() instead
+	movl	%esp, %eax
+	call	syscall_trace_leave
+	jmp	resume_userspace
+END(syscall_exit_work)
+
+syscall_fault:
+	ASM_CLAC
+	GET_THREAD_INFO(%ebp)
+	movl	$-EFAULT, PT_EAX(%esp)
+	jmp	resume_userspace
+END(syscall_fault)
+
+syscall_badsys:
+	movl	$-ENOSYS, %eax
+	jmp	syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl	$-ENOSYS, %eax
+	jmp	sysenter_after_call
+END(sysenter_badsys)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+	/* fixup the stack */
+	mov	GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+	mov	GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+	shl	$16, %eax
+	addl	%esp, %eax			/* the adjusted stack pointer */
+	pushl	$__KERNEL_DS
+	pushl	%eax
+	lss	(%esp), %esp			/* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+	movl	%ss, %eax
+	/* see if on espfix stack */
+	cmpw	$__ESPFIX_SS, %ax
+	jne	27f
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	/* switch to normal stack */
+	FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+	.align 8
+ENTRY(irq_entries_start)
+    vector=FIRST_EXTERNAL_VECTOR
+    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
+    vector=vector+1
+	jmp	common_interrupt
+	.align	8
+    .endr
+END(irq_entries_start)
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+	ASM_CLAC
+	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	movl	%esp, %eax
+	call	do_IRQ
+	jmp	ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn)	\
+ENTRY(name)				\
+	ASM_CLAC;			\
+	pushl	$~(nr);			\
+	SAVE_ALL;			\
+	TRACE_IRQS_OFF			\
+	movl	%esp, %eax;		\
+	call	fn;			\
+	jmp	ret_from_intr;		\
+ENDPROC(name)
+
+
+#ifdef CONFIG_TRACING
+# define TRACE_BUILD_INTERRUPT(name, nr)	BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
+#else
+# define TRACE_BUILD_INTERRUPT(name, nr)
+#endif
+
+#define BUILD_INTERRUPT(name, nr)		\
+	BUILD_INTERRUPT3(name, nr, smp_##name);	\
+	TRACE_BUILD_INTERRUPT(name, nr)
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_coprocessor_error
+	jmp	error_code
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+	ASM_CLAC
+	pushl	$0
+#ifdef CONFIG_X86_INVD_BUG
+	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+	ALTERNATIVE "pushl	$do_general_protection",	\
+		    "pushl	$do_simd_coprocessor_error",	\
+		    X86_FEATURE_XMM
+#else
+	pushl	$do_simd_coprocessor_error
+#endif
+	jmp	error_code
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+	ASM_CLAC
+	pushl	$-1				# mark this as an int
+	pushl	$do_device_not_available
+	jmp	error_code
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+	iret
+	_ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+
+ENTRY(native_irq_enable_sysexit)
+	sti
+	sysexit
+END(native_irq_enable_sysexit)
+#endif
+
+ENTRY(overflow)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_overflow
+	jmp	error_code
+END(overflow)
+
+ENTRY(bounds)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_bounds
+	jmp	error_code
+END(bounds)
+
+ENTRY(invalid_op)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_invalid_op
+	jmp	error_code
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_coprocessor_segment_overrun
+	jmp	error_code
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+	ASM_CLAC
+	pushl	$do_invalid_TSS
+	jmp	error_code
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+	ASM_CLAC
+	pushl	$do_segment_not_present
+	jmp	error_code
+END(segment_not_present)
+
+ENTRY(stack_segment)
+	ASM_CLAC
+	pushl	$do_stack_segment
+	jmp	error_code
+END(stack_segment)
+
+ENTRY(alignment_check)
+	ASM_CLAC
+	pushl	$do_alignment_check
+	jmp	error_code
+END(alignment_check)
+
+ENTRY(divide_error)
+	ASM_CLAC
+	pushl	$0				# no error code
+	pushl	$do_divide_error
+	jmp	error_code
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+	ASM_CLAC
+	pushl	$0
+	pushl	machine_check_vector
+	jmp	error_code
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+	ASM_CLAC
+	pushl	$0
+	pushl	$do_spurious_interrupt_bug
+	jmp	error_code
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+	addl	$5*4, %esp			/* remove xen-provided frame */
+	jmp	sysenter_past_esp
+
+ENTRY(xen_hypervisor_callback)
+	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	TRACE_IRQS_OFF
+
+	/*
+	 * Check to see if we got the event in the critical
+	 * region in xen_iret_direct, after we've reenabled
+	 * events and checked for pending events.  This simulates
+	 * iret instruction's behaviour where it delivers a
+	 * pending interrupt when enabling interrupts:
+	 */
+	movl	PT_EIP(%esp), %eax
+	cmpl	$xen_iret_start_crit, %eax
+	jb	1f
+	cmpl	$xen_iret_end_crit, %eax
+	jae	1f
+
+	jmp	xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1:	mov	%esp, %eax
+	call	xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call	xen_maybe_preempt_hcall
+#endif
+	jmp	ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ *  1. Fault while reloading DS, ES, FS or GS
+ *  2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+	pushl	%eax
+	movl	$1, %eax
+1:	mov	4(%esp), %ds
+2:	mov	8(%esp), %es
+3:	mov	12(%esp), %fs
+4:	mov	16(%esp), %gs
+	/* EAX == 0 => Category 1 (Bad segment)
+	   EAX != 0 => Category 2 (Bad IRET) */
+	testl	%eax, %eax
+	popl	%eax
+	lea	16(%esp), %esp
+	jz	5f
+	jmp	iret_exc
+5:	pushl	$-1				/* orig_ax = -1 => not a system call */
+	SAVE_ALL
+	jmp	ret_from_exception
+
+.section .fixup, "ax"
+6:	xorl	%eax, %eax
+	movl	%eax, 4(%esp)
+	jmp	1b
+7:	xorl	%eax, %eax
+	movl	%eax, 8(%esp)
+	jmp	2b
+8:	xorl	%eax, %eax
+	movl	%eax, 12(%esp)
+	jmp	3b
+9:	xorl	%eax, %eax
+	movl	%eax, 16(%esp)
+	jmp	4b
+.previous
+	_ASM_EXTABLE(1b, 6b)
+	_ASM_EXTABLE(2b, 7b)
+	_ASM_EXTABLE(3b, 8b)
+	_ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+		xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+	hyperv_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+	ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	pushl	$0				/* Pass NULL as regs pointer */
+	movl	4*4(%esp), %eax
+	movl	0x4(%ebp), %edx
+	movl	function_trace_op, %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+	call	ftrace_stub
+
+	addl	$4, %esp			/* skip NULL pointer */
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+ftrace_ret:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+	jmp	ftrace_stub
+#endif
+
+.globl ftrace_stub
+ftrace_stub:
+	ret
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+	pushf	/* push flags before compare (in cs location) */
+
+	/*
+	 * i386 does not save SS and ESP when coming from kernel.
+	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
+	 * Unfortunately, that means eflags must be at the same location
+	 * as the current return ip is. We move the return ip into the
+	 * ip location, and move flags into the return ip location.
+	 */
+	pushl	4(%esp)				/* save return ip into ip slot */
+
+	pushl	$0				/* Load 0 into orig_ax */
+	pushl	%gs
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+
+	movl	13*4(%esp), %eax		/* Get the saved flags */
+	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
+						/* clobbering return ip */
+	movl	$__KERNEL_CS, 13*4(%esp)
+
+	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
+	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
+	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
+	movl	function_trace_op, %ecx		/* Save ftrace_pos in 3rd parameter */
+	pushl	%esp				/* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+	call	ftrace_stub
+
+	addl	$4, %esp			/* Skip pt_regs */
+	movl	14*4(%esp), %eax		/* Move flags back into cs */
+	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
+	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
+	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
+
+	popl	%ebx
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+	popl	%edi
+	popl	%ebp
+	popl	%eax
+	popl	%ds
+	popl	%es
+	popl	%fs
+	popl	%gs
+	addl	$8, %esp			/* Skip orig_ax and ip */
+	popf					/* Pop flags at end (no addl to corrupt flags) */
+	jmp	ftrace_ret
+
+	popf
+	jmp	ftrace_stub
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+	cmpl	$__PAGE_OFFSET, %esp
+	jb	ftrace_stub			/* Paging not enabled yet? */
+
+	cmpl	$ftrace_stub, ftrace_trace_function
+	jnz	trace
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	cmpl	$ftrace_stub, ftrace_graph_return
+	jnz	ftrace_graph_caller
+
+	cmpl	$ftrace_graph_entry_stub, ftrace_graph_entry
+	jnz	ftrace_graph_caller
+#endif
+.globl ftrace_stub
+ftrace_stub:
+	ret
+
+	/* taken from glibc */
+trace:
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	movl	0x4(%ebp), %edx
+	subl	$MCOUNT_INSN_SIZE, %eax
+
+	call	*ftrace_trace_function
+
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	jmp	ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	pushl	%eax
+	pushl	%ecx
+	pushl	%edx
+	movl	0xc(%esp), %eax
+	lea	0x4(%ebp), %edx
+	movl	(%ebp), %ecx
+	subl	$MCOUNT_INSN_SIZE, %eax
+	call	prepare_ftrace_return
+	popl	%edx
+	popl	%ecx
+	popl	%eax
+	ret
+END(ftrace_graph_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl	%eax
+	pushl	%edx
+	movl	%ebp, %eax
+	call	ftrace_return_to_handler
+	movl	%eax, %ecx
+	popl	%edx
+	popl	%eax
+	jmp	*%ecx
+#endif
+
+#ifdef CONFIG_TRACING
+ENTRY(trace_page_fault)
+	ASM_CLAC
+	pushl	$trace_do_page_fault
+	jmp	error_code
+END(trace_page_fault)
+#endif
+
+ENTRY(page_fault)
+	ASM_CLAC
+	pushl	$do_page_fault
+	ALIGN
+error_code:
+	/* the function address is in %gs's slot on the stack */
+	pushl	%fs
+	pushl	%es
+	pushl	%ds
+	pushl	%eax
+	pushl	%ebp
+	pushl	%edi
+	pushl	%esi
+	pushl	%edx
+	pushl	%ecx
+	pushl	%ebx
+	cld
+	movl	$(__KERNEL_PERCPU), %ecx
+	movl	%ecx, %fs
+	UNWIND_ESPFIX_STACK
+	GS_TO_REG %ecx
+	movl	PT_GS(%esp), %edi		# get the function address
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+	REG_TO_PTGS %ecx
+	SET_KERNEL_GS %ecx
+	movl	$(__USER_DS), %ecx
+	movl	%ecx, %ds
+	movl	%ecx, %es
+	TRACE_IRQS_OFF
+	movl	%esp, %eax			# pt_regs pointer
+	call	*%edi
+	jmp	ret_from_exception
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+.macro FIX_STACK offset ok label
+	cmpw	$__KERNEL_CS, 4(%esp)
+	jne	\ok
+\label:
+	movl	TSS_sysenter_sp0 + \offset(%esp), %esp
+	pushfl
+	pushl	$__KERNEL_CS
+	pushl	$sysenter_past_esp
+.endm
+
+ENTRY(debug)
+	ASM_CLAC
+	cmpl	$entry_SYSENTER_32, (%esp)
+	jne	debug_stack_correct
+	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
+debug_stack_correct:
+	pushl	$-1				# mark this as an int
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl	%edx, %edx			# error code 0
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_debug
+	jmp	ret_from_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got  an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
+	pushl	%eax
+	movl	%ss, %eax
+	cmpw	$__ESPFIX_SS, %ax
+	popl	%eax
+	je	nmi_espfix_stack
+#endif
+	cmpl	$entry_SYSENTER_32, (%esp)
+	je	nmi_stack_fixup
+	pushl	%eax
+	movl	%esp, %eax
+	/*
+	 * Do not access memory above the end of our stack page,
+	 * it might not exist.
+	 */
+	andl	$(THREAD_SIZE-1), %eax
+	cmpl	$(THREAD_SIZE-20), %eax
+	popl	%eax
+	jae	nmi_stack_correct
+	cmpl	$entry_SYSENTER_32, 12(%esp)
+	je	nmi_debug_stack_check
+nmi_stack_correct:
+	pushl	%eax
+	SAVE_ALL
+	xorl	%edx, %edx			# zero error code
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_nmi
+	jmp	restore_all_notrace
+
+nmi_stack_fixup:
+	FIX_STACK 12, nmi_stack_correct, 1
+	jmp	nmi_stack_correct
+
+nmi_debug_stack_check:
+	cmpw	$__KERNEL_CS, 16(%esp)
+	jne	nmi_stack_correct
+	cmpl	$debug, (%esp)
+	jb	nmi_stack_correct
+	cmpl	$debug_esp_fix_insn, (%esp)
+	ja	nmi_stack_correct
+	FIX_STACK 24, nmi_stack_correct, 1
+	jmp	nmi_stack_correct
+
+#ifdef CONFIG_X86_ESPFIX32
+nmi_espfix_stack:
+	/*
+	 * create the pointer to lss back
+	 */
+	pushl	%ss
+	pushl	%esp
+	addl	$4, (%esp)
+	/* copy the iret frame of 12 bytes */
+	.rept 3
+	pushl	16(%esp)
+	.endr
+	pushl	%eax
+	SAVE_ALL
+	FIXUP_ESPFIX_STACK			# %eax == %esp
+	xorl	%edx, %edx			# zero error code
+	call	do_nmi
+	RESTORE_REGS
+	lss	12+4(%esp), %esp		# back to espfix stack
+	jmp	irq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+	ASM_CLAC
+	pushl	$-1				# mark this as an int
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl	%edx, %edx			# zero error code
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_int3
+	jmp	ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+	pushl	$do_general_protection
+	jmp	error_code
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+	ASM_CLAC
+	pushl	$do_async_page_fault
+	jmp	error_code
+END(async_page_fault)
+#endif
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/entry/entry_64.S
index 02c2eff7478d..3bb2c4302df1 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -4,34 +4,25 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  *  Copyright (C) 2000, 2001, 2002  Andi Kleen SuSE Labs
  *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
- */
-
-/*
+ *
  * entry.S contains the system-call and fault low-level handling routines.
  *
  * Some of this is documented in Documentation/x86/entry_64.txt
  *
- * NOTE: This code handles signal-recognition, which happens every time
- * after an interrupt and after each system call.
- *
  * A note on terminology:
- * - iret frame: Architecture defined interrupt frame from SS to RIP
- * at the top of the kernel process stack.
+ * - iret frame:	Architecture defined interrupt frame from SS to RIP
+ *			at the top of the kernel process stack.
  *
  * Some macro usage:
- * - CFI macros are used to generate dwarf2 unwind information for better
- * backtraces. They don't change any code.
- * - ENTRY/END Define functions in the symbol table.
- * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
- * - idtentry - Define exception entry points.
+ * - ENTRY/END:		Define functions in the symbol table.
+ * - TRACE_IRQ_*:	Trace hardirq state for lock debugging.
+ * - idtentry:		Define exception entry points.
  */
-
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/msr.h>
 #include <asm/unistd.h>
@@ -49,13 +40,12 @@
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64	(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT 0x80000000
-#define __AUDIT_ARCH_LE	   0x40000000
-
-	.code64
-	.section .entry.text, "ax"
+#define AUDIT_ARCH_X86_64			(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_64BIT			0x80000000
+#define __AUDIT_ARCH_LE				0x40000000
 
+.code64
+.section .entry.text, "ax"
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -64,11 +54,10 @@ ENTRY(native_usergs_sysret64)
 ENDPROC(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
-
 .macro TRACE_IRQS_IRETQ
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt   $9,EFLAGS(%rsp)	/* interrupts off? */
-	jnc  1f
+	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	jnc	1f
 	TRACE_IRQS_ON
 1:
 #endif
@@ -88,89 +77,34 @@ ENDPROC(native_usergs_sysret64)
 #if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
 
 .macro TRACE_IRQS_OFF_DEBUG
-	call debug_stack_set_zero
+	call	debug_stack_set_zero
 	TRACE_IRQS_OFF
-	call debug_stack_reset
+	call	debug_stack_reset
 .endm
 
 .macro TRACE_IRQS_ON_DEBUG
-	call debug_stack_set_zero
+	call	debug_stack_set_zero
 	TRACE_IRQS_ON
-	call debug_stack_reset
+	call	debug_stack_reset
 .endm
 
 .macro TRACE_IRQS_IRETQ_DEBUG
-	bt   $9,EFLAGS(%rsp)	/* interrupts off? */
-	jnc  1f
+	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	jnc	1f
 	TRACE_IRQS_ON_DEBUG
 1:
 .endm
 
 #else
-# define TRACE_IRQS_OFF_DEBUG		TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG		TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG		TRACE_IRQS_IRETQ
+# define TRACE_IRQS_OFF_DEBUG			TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG			TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG			TRACE_IRQS_IRETQ
 #endif
 
 /*
- * empty frame
- */
-	.macro EMPTY_FRAME start=1 offset=0
-	.if \start
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA rsp,8+\offset
-	.else
-	CFI_DEF_CFA_OFFSET 8+\offset
-	.endif
-	.endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
- */
-	.macro INTR_FRAME start=1 offset=0
-	EMPTY_FRAME \start, 5*8+\offset
-	/*CFI_REL_OFFSET ss, 4*8+\offset*/
-	CFI_REL_OFFSET rsp, 3*8+\offset
-	/*CFI_REL_OFFSET rflags, 2*8+\offset*/
-	/*CFI_REL_OFFSET cs, 1*8+\offset*/
-	CFI_REL_OFFSET rip, 0*8+\offset
-	.endm
-
-/*
- * initial frame state for exceptions with error code (and interrupts
- * with vector already pushed)
- */
-	.macro XCPT_FRAME start=1 offset=0
-	INTR_FRAME \start, 1*8+\offset
-	.endm
-
-/*
- * frame that enables passing a complete pt_regs to a C function.
- */
-	.macro DEFAULT_FRAME start=1 offset=0
-	XCPT_FRAME \start, ORIG_RAX+\offset
-	CFI_REL_OFFSET rdi, RDI+\offset
-	CFI_REL_OFFSET rsi, RSI+\offset
-	CFI_REL_OFFSET rdx, RDX+\offset
-	CFI_REL_OFFSET rcx, RCX+\offset
-	CFI_REL_OFFSET rax, RAX+\offset
-	CFI_REL_OFFSET r8, R8+\offset
-	CFI_REL_OFFSET r9, R9+\offset
-	CFI_REL_OFFSET r10, R10+\offset
-	CFI_REL_OFFSET r11, R11+\offset
-	CFI_REL_OFFSET rbx, RBX+\offset
-	CFI_REL_OFFSET rbp, RBP+\offset
-	CFI_REL_OFFSET r12, R12+\offset
-	CFI_REL_OFFSET r13, R13+\offset
-	CFI_REL_OFFSET r14, R14+\offset
-	CFI_REL_OFFSET r15, R15+\offset
-	.endm
-
-/*
- * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
- * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
  * then loads new ss, cs, and rip from previously programmed MSRs.
  * rflags gets masked by a value from another MSR (so CLD and CLAC
  * are not needed). SYSCALL does not save anything on the stack
@@ -186,7 +120,7 @@ ENDPROC(native_usergs_sysret64)
  * r10  arg3 (needs to be moved to rcx to conform to C ABI)
  * r8   arg4
  * r9   arg5
- * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
  *
  * Only called from user space.
  *
@@ -195,13 +129,7 @@ ENDPROC(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
-ENTRY(system_call)
-	CFI_STARTPROC	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rip,rcx
-	/*CFI_REGISTER	rflags,r11*/
-
+ENTRY(entry_SYSCALL_64)
 	/*
 	 * Interrupts are off on entry.
 	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
@@ -213,14 +141,14 @@ ENTRY(system_call)
 	 * after the swapgs, so that it can do the swapgs
 	 * for the guest and jump here on syscall.
 	 */
-GLOBAL(system_call_after_swapgs)
+GLOBAL(entry_SYSCALL_64_after_swapgs)
 
-	movq	%rsp,PER_CPU_VAR(rsp_scratch)
-	movq	PER_CPU_VAR(kernel_stack),%rsp
+	movq	%rsp, PER_CPU_VAR(rsp_scratch)
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
-	pushq_cfi $__USER_DS			/* pt_regs->ss */
-	pushq_cfi PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
 	/*
 	 * Re-enable interrupts.
 	 * We use 'rsp_scratch' as a scratch space, hence irq-off block above
@@ -229,36 +157,34 @@ GLOBAL(system_call_after_swapgs)
 	 * with using rsp_scratch:
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi	%r11			/* pt_regs->flags */
-	pushq_cfi	$__USER_CS		/* pt_regs->cs */
-	pushq_cfi	%rcx			/* pt_regs->ip */
-	CFI_REL_OFFSET rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi	$-ENOSYS		/* pt_regs->ax */
-	pushq_cfi_reg	r8			/* pt_regs->r8 */
-	pushq_cfi_reg	r9			/* pt_regs->r9 */
-	pushq_cfi_reg	r10			/* pt_regs->r10 */
-	pushq_cfi_reg	r11			/* pt_regs->r11 */
-	sub	$(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 6*8
-
-	testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz tracesys
-system_call_fastpath:
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+	pushq	%rax				/* pt_regs->orig_ax */
+	pushq	%rdi				/* pt_regs->di */
+	pushq	%rsi				/* pt_regs->si */
+	pushq	%rdx				/* pt_regs->dx */
+	pushq	%rcx				/* pt_regs->cx */
+	pushq	$-ENOSYS			/* pt_regs->ax */
+	pushq	%r8				/* pt_regs->r8 */
+	pushq	%r9				/* pt_regs->r9 */
+	pushq	%r10				/* pt_regs->r10 */
+	pushq	%r11				/* pt_regs->r11 */
+	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
+
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	tracesys
+entry_SYSCALL_64_fastpath:
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$__NR_syscall_max, %rax
 #else
-	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	andl	$__SYSCALL_MASK, %eax
+	cmpl	$__NR_syscall_max, %eax
 #endif
-	ja	1f	/* return -ENOSYS (already in pt_regs->ax) */
-	movq %r10,%rcx
-	call *sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
+	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
+	movq	%r10, %rcx
+	call	*sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
 1:
 /*
  * Syscall return path ending with SYSRET (fast path).
@@ -279,19 +205,15 @@ system_call_fastpath:
 	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
 	 * very bad.
 	 */
-	testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz int_ret_from_sys_call_irqs_off	/* Go to the slow path */
-
-	CFI_REMEMBER_STATE
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	int_ret_from_sys_call_irqs_off	/* Go to the slow path */
 
 	RESTORE_C_REGS_EXCEPT_RCX_R11
-	movq	RIP(%rsp),%rcx
-	CFI_REGISTER	rip,rcx
-	movq	EFLAGS(%rsp),%r11
-	/*CFI_REGISTER	rflags,r11*/
-	movq	RSP(%rsp),%rsp
+	movq	RIP(%rsp), %rcx
+	movq	EFLAGS(%rsp), %r11
+	movq	RSP(%rsp), %rsp
 	/*
-	 * 64bit SYSRET restores rip from rcx,
+	 * 64-bit SYSRET restores rip from rcx,
 	 * rflags from r11 (but RF and VM bits are forced to 0),
 	 * cs and ss are loaded from MSRs.
 	 * Restoration of rflags re-enables interrupts.
@@ -307,25 +229,23 @@ system_call_fastpath:
 	 */
 	USERGS_SYSRET64
 
-	CFI_RESTORE_STATE
-
 	/* Do syscall entry tracing */
 tracesys:
-	movq %rsp, %rdi
-	movl $AUDIT_ARCH_X86_64, %esi
-	call syscall_trace_enter_phase1
-	test %rax, %rax
-	jnz tracesys_phase2		/* if needed, run the slow path */
-	RESTORE_C_REGS_EXCEPT_RAX	/* else restore clobbered regs */
-	movq ORIG_RAX(%rsp), %rax
-	jmp system_call_fastpath	/*      and return to the fast path */
+	movq	%rsp, %rdi
+	movl	$AUDIT_ARCH_X86_64, %esi
+	call	syscall_trace_enter_phase1
+	test	%rax, %rax
+	jnz	tracesys_phase2			/* if needed, run the slow path */
+	RESTORE_C_REGS_EXCEPT_RAX		/* else restore clobbered regs */
+	movq	ORIG_RAX(%rsp), %rax
+	jmp	entry_SYSCALL_64_fastpath	/* and return to the fast path */
 
 tracesys_phase2:
 	SAVE_EXTRA_REGS
-	movq %rsp, %rdi
-	movl $AUDIT_ARCH_X86_64, %esi
-	movq %rax,%rdx
-	call syscall_trace_enter_phase2
+	movq	%rsp, %rdi
+	movl	$AUDIT_ARCH_X86_64, %esi
+	movq	%rax, %rdx
+	call	syscall_trace_enter_phase2
 
 	/*
 	 * Reload registers from stack in case ptrace changed them.
@@ -335,15 +255,15 @@ tracesys_phase2:
 	RESTORE_C_REGS_EXCEPT_RAX
 	RESTORE_EXTRA_REGS
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$__NR_syscall_max, %rax
 #else
-	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	andl	$__SYSCALL_MASK, %eax
+	cmpl	$__NR_syscall_max, %eax
 #endif
-	ja	1f	/* return -ENOSYS (already in pt_regs->ax) */
-	movq %r10,%rcx	/* fixup for C */
-	call *sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
+	ja	1f				/* return -ENOSYS (already in pt_regs->ax) */
+	movq	%r10, %rcx			/* fixup for C */
+	call	*sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
 1:
 	/* Use IRET because user could have changed pt_regs->foo */
 
@@ -355,31 +275,33 @@ GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
 	TRACE_IRQS_OFF
-	movl $_TIF_ALLWORK_MASK,%edi
+	movl	$_TIF_ALLWORK_MASK, %edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)
 	LOCKDEP_SYS_EXIT_IRQ
 	GET_THREAD_INFO(%rcx)
-	movl TI_flags(%rcx),%edx
-	andl %edi,%edx
-	jnz   int_careful
-	andl	$~TS_COMPAT,TI_status(%rcx)
+	movl	TI_flags(%rcx), %edx
+	andl	%edi, %edx
+	jnz	int_careful
+	andl	$~TS_COMPAT, TI_status(%rcx)
 	jmp	syscall_return
 
-	/* Either reschedule or signal or syscall exit tracking needed. */
-	/* First do a reschedule test. */
-	/* edx:	work, edi: workmask */
+	/*
+	 * Either reschedule or signal or syscall exit tracking needed.
+	 * First do a reschedule test.
+	 * edx:	work, edi: workmask
+	 */
 int_careful:
-	bt $TIF_NEED_RESCHED,%edx
-	jnc  int_very_careful
+	bt	$TIF_NEED_RESCHED, %edx
+	jnc	int_very_careful
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi %rdi
+	pushq	%rdi
 	SCHEDULE_USER
-	popq_cfi %rdi
+	popq	%rdi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp int_with_check
+	jmp	int_with_check
 
 	/* handle signals and tracing -- both require a full pt_regs */
 int_very_careful:
@@ -387,27 +309,27 @@ int_very_careful:
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_EXTRA_REGS
 	/* Check for syscall exit trace */
-	testl $_TIF_WORK_SYSCALL_EXIT,%edx
-	jz int_signal
-	pushq_cfi %rdi
-	leaq 8(%rsp),%rdi	# &ptregs -> arg1
-	call syscall_trace_leave
-	popq_cfi %rdi
-	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
-	jmp int_restore_rest
+	testl	$_TIF_WORK_SYSCALL_EXIT, %edx
+	jz	int_signal
+	pushq	%rdi
+	leaq	8(%rsp), %rdi			/* &ptregs -> arg1 */
+	call	syscall_trace_leave
+	popq	%rdi
+	andl	$~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi
+	jmp	int_restore_rest
 
 int_signal:
-	testl $_TIF_DO_NOTIFY_MASK,%edx
-	jz 1f
-	movq %rsp,%rdi		# &ptregs -> arg1
-	xorl %esi,%esi		# oldset -> arg2
-	call do_notify_resume
-1:	movl $_TIF_WORK_MASK,%edi
+	testl	$_TIF_DO_NOTIFY_MASK, %edx
+	jz	1f
+	movq	%rsp, %rdi			/* &ptregs -> arg1 */
+	xorl	%esi, %esi			/* oldset -> arg2 */
+	call	do_notify_resume
+1:	movl	$_TIF_WORK_MASK, %edi
 int_restore_rest:
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp int_with_check
+	jmp	int_with_check
 
 syscall_return:
 	/* The IRETQ could re-enable interrupts: */
@@ -418,34 +340,37 @@ syscall_return:
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.
 	 */
-	movq RCX(%rsp),%rcx
-	cmpq %rcx,RIP(%rsp)		/* RCX == RIP */
-	jne opportunistic_sysret_failed
+	movq	RCX(%rsp), %rcx
+	movq	RIP(%rsp), %r11
+	cmpq	%rcx, %r11			/* RCX == RIP */
+	jne	opportunistic_sysret_failed
 
 	/*
 	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
 	 * in kernel space.  This essentially lets the user take over
-	 * the kernel, since userspace controls RSP.  It's not worth
-	 * testing for canonicalness exactly -- this check detects any
-	 * of the 17 high bits set, which is true for non-canonical
-	 * or kernel addresses.  (This will pessimize vsyscall=native.
-	 * Big deal.)
+	 * the kernel, since userspace controls RSP.
 	 *
-	 * If virtual addresses ever become wider, this will need
+	 * If width of "canonical tail" ever becomes variable, this will need
 	 * to be updated to remain correct on both old and new CPUs.
 	 */
 	.ifne __VIRTUAL_MASK_SHIFT - 47
 	.error "virtual address width changed -- SYSRET checks need update"
 	.endif
-	shr $__VIRTUAL_MASK_SHIFT, %rcx
-	jnz opportunistic_sysret_failed
 
-	cmpq $__USER_CS,CS(%rsp)	/* CS must match SYSRET */
-	jne opportunistic_sysret_failed
+	/* Change top 16 bits to be the sign-extension of 47th bit */
+	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
 
-	movq R11(%rsp),%r11
-	cmpq %r11,EFLAGS(%rsp)		/* R11 == RFLAGS */
-	jne opportunistic_sysret_failed
+	/* If this changed %rcx, it was not canonical */
+	cmpq	%rcx, %r11
+	jne	opportunistic_sysret_failed
+
+	cmpq	$__USER_CS, CS(%rsp)		/* CS must match SYSRET */
+	jne	opportunistic_sysret_failed
+
+	movq	R11(%rsp), %r11
+	cmpq	%r11, EFLAGS(%rsp)		/* R11 == RFLAGS */
+	jne	opportunistic_sysret_failed
 
 	/*
 	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
@@ -454,47 +379,41 @@ syscall_return:
 	 * with register state that satisfies the opportunistic SYSRET
 	 * conditions.  For example, single-stepping this user code:
 	 *
-	 *           movq $stuck_here,%rcx
+	 *           movq	$stuck_here, %rcx
 	 *           pushfq
 	 *           popq %r11
 	 *   stuck_here:
 	 *
 	 * would never get past 'stuck_here'.
 	 */
-	testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
-	jnz opportunistic_sysret_failed
+	testq	$(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+	jnz	opportunistic_sysret_failed
 
 	/* nothing to check for RSP */
 
-	cmpq $__USER_DS,SS(%rsp)	/* SS must match SYSRET */
-	jne opportunistic_sysret_failed
+	cmpq	$__USER_DS, SS(%rsp)		/* SS must match SYSRET */
+	jne	opportunistic_sysret_failed
 
 	/*
-	 * We win!  This label is here just for ease of understanding
-	 * perf profiles.  Nothing jumps here.
+	 * We win! This label is here just for ease of understanding
+	 * perf profiles. Nothing jumps here.
 	 */
 syscall_return_via_sysret:
-	CFI_REMEMBER_STATE
-	/* r11 is already restored (see code above) */
-	RESTORE_C_REGS_EXCEPT_R11
-	movq RSP(%rsp),%rsp
+	/* rcx and r11 are already restored (see code above) */
+	RESTORE_C_REGS_EXCEPT_RCX_R11
+	movq	RSP(%rsp), %rsp
 	USERGS_SYSRET64
-	CFI_RESTORE_STATE
 
 opportunistic_sysret_failed:
 	SWAPGS
 	jmp	restore_c_regs_and_iret
-	CFI_ENDPROC
-END(system_call)
+END(entry_SYSCALL_64)
 
 
 	.macro FORK_LIKE func
 ENTRY(stub_\func)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8		/* offset 8: return address */
 	SAVE_EXTRA_REGS 8
-	jmp sys_\func
-	CFI_ENDPROC
+	jmp	sys_\func
 END(stub_\func)
 	.endm
 
@@ -503,8 +422,6 @@ END(stub_\func)
 	FORK_LIKE  vfork
 
 ENTRY(stub_execve)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	call	sys_execve
 return_from_execve:
 	testl	%eax, %eax
@@ -514,11 +431,9 @@ return_from_execve:
 1:
 	/* must use IRET code path (pt_regs->cs may have changed) */
 	addq	$8, %rsp
-	CFI_ADJUST_CFA_OFFSET -8
 	ZERO_EXTRA_REGS
-	movq	%rax,RAX(%rsp)
+	movq	%rax, RAX(%rsp)
 	jmp	int_ret_from_sys_call
-	CFI_ENDPROC
 END(stub_execve)
 /*
  * Remaining execve stubs are only 7 bytes long.
@@ -526,47 +441,25 @@ END(stub_execve)
  */
 	.align	8
 GLOBAL(stub_execveat)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	call	sys_execveat
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub_execveat)
 
-#ifdef CONFIG_X86_X32_ABI
+#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
 	.align	8
 GLOBAL(stub_x32_execve)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
-	call	compat_sys_execve
-	jmp	return_from_execve
-	CFI_ENDPROC
-END(stub_x32_execve)
-	.align	8
-GLOBAL(stub_x32_execveat)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
-	call	compat_sys_execveat
-	jmp	return_from_execve
-	CFI_ENDPROC
-END(stub_x32_execveat)
-#endif
-
-#ifdef CONFIG_IA32_EMULATION
-	.align	8
 GLOBAL(stub32_execve)
-	CFI_STARTPROC
 	call	compat_sys_execve
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub32_execve)
+END(stub_x32_execve)
 	.align	8
+GLOBAL(stub_x32_execveat)
 GLOBAL(stub32_execveat)
-	CFI_STARTPROC
 	call	compat_sys_execveat
 	jmp	return_from_execve
-	CFI_ENDPROC
 END(stub32_execveat)
+END(stub_x32_execveat)
 #endif
 
 /*
@@ -574,8 +467,6 @@ END(stub32_execveat)
  * This cannot be done with SYSRET, so use the IRET return path instead.
  */
 ENTRY(stub_rt_sigreturn)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	/*
 	 * SAVE_EXTRA_REGS result is not normally needed:
 	 * sigreturn overwrites all pt_regs->GPREGS.
@@ -584,24 +475,19 @@ ENTRY(stub_rt_sigreturn)
 	 * we SAVE_EXTRA_REGS here.
 	 */
 	SAVE_EXTRA_REGS 8
-	call sys_rt_sigreturn
+	call	sys_rt_sigreturn
 return_from_stub:
 	addq	$8, %rsp
-	CFI_ADJUST_CFA_OFFSET -8
 	RESTORE_EXTRA_REGS
-	movq %rax,RAX(%rsp)
-	jmp int_ret_from_sys_call
-	CFI_ENDPROC
+	movq	%rax, RAX(%rsp)
+	jmp	int_ret_from_sys_call
 END(stub_rt_sigreturn)
 
 #ifdef CONFIG_X86_X32_ABI
 ENTRY(stub_x32_rt_sigreturn)
-	CFI_STARTPROC
-	DEFAULT_FRAME 0, 8
 	SAVE_EXTRA_REGS 8
-	call sys32_x32_rt_sigreturn
-	jmp  return_from_stub
-	CFI_ENDPROC
+	call	sys32_x32_rt_sigreturn
+	jmp	return_from_stub
 END(stub_x32_rt_sigreturn)
 #endif
 
@@ -611,36 +497,36 @@ END(stub_x32_rt_sigreturn)
  * rdi: prev task we switched from
  */
 ENTRY(ret_from_fork)
-	DEFAULT_FRAME
 
-	LOCK ; btr $TIF_FORK,TI_flags(%r8)
+	LOCK ; btr $TIF_FORK, TI_flags(%r8)
 
-	pushq_cfi $0x0002
-	popfq_cfi				# reset kernel eflags
+	pushq	$0x0002
+	popfq					/* reset kernel eflags */
 
-	call schedule_tail			# rdi: 'prev' task parameter
+	call	schedule_tail			/* rdi: 'prev' task parameter */
 
 	RESTORE_EXTRA_REGS
 
-	testl $3,CS(%rsp)			# from kernel_thread?
+	testb	$3, CS(%rsp)			/* from kernel_thread? */
 
 	/*
 	 * By the time we get here, we have no idea whether our pt_regs,
 	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
-	 * the slow path, or one of the ia32entry paths.
+	 * the slow path, or one of the 32-bit compat paths.
 	 * Use IRET code path to return, since it can safely handle
 	 * all of the above.
 	 */
 	jnz	int_ret_from_sys_call
 
-	/* We came from kernel_thread */
-	/* nb: we depend on RESTORE_EXTRA_REGS above */
-	movq %rbp, %rdi
-	call *%rbx
-	movl $0, RAX(%rsp)
+	/*
+	 * We came from kernel_thread
+	 * nb: we depend on RESTORE_EXTRA_REGS above
+	 */
+	movq	%rbp, %rdi
+	call	*%rbx
+	movl	$0, RAX(%rsp)
 	RESTORE_EXTRA_REGS
-	jmp int_ret_from_sys_call
-	CFI_ENDPROC
+	jmp	int_ret_from_sys_call
 END(ret_from_fork)
 
 /*
@@ -649,16 +535,13 @@ END(ret_from_fork)
  */
 	.align 8
 ENTRY(irq_entries_start)
-	INTR_FRAME
     vector=FIRST_EXTERNAL_VECTOR
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	pushq_cfi $(~vector+0x80)	/* Note: always in signed byte range */
+	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
     vector=vector+1
 	jmp	common_interrupt
-	CFI_ADJUST_CFA_OFFSET -8
 	.align	8
     .endr
-	CFI_ENDPROC
 END(irq_entries_start)
 
 /*
@@ -684,10 +567,10 @@ END(irq_entries_start)
 	/* this goes to 0(%rsp) for unwinder, not for saving the value: */
 	SAVE_EXTRA_REGS_RBP -RBP
 
-	leaq -RBP(%rsp),%rdi	/* arg1 for \func (pointer to pt_regs) */
+	leaq	-RBP(%rsp), %rdi		/* arg1 for \func (pointer to pt_regs) */
 
-	testl $3, CS-RBP(%rsp)
-	je 1f
+	testb	$3, CS-RBP(%rsp)
+	jz	1f
 	SWAPGS
 1:
 	/*
@@ -697,24 +580,14 @@ END(irq_entries_start)
 	 * a little cheaper to use a separate counter in the PDA (short of
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
-	movq %rsp, %rsi
-	incl PER_CPU_VAR(irq_count)
-	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
-	CFI_DEF_CFA_REGISTER	rsi
-	pushq %rsi
-	/*
-	 * For debugger:
-	 * "CFA (Current Frame Address) is the value on stack + offset"
-	 */
-	CFI_ESCAPE	0x0f /* DW_CFA_def_cfa_expression */, 6, \
-			0x77 /* DW_OP_breg7 (rsp) */, 0, \
-			0x06 /* DW_OP_deref */, \
-			0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
-			0x22 /* DW_OP_plus */
+	movq	%rsp, %rsi
+	incl	PER_CPU_VAR(irq_count)
+	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	pushq	%rsi
 	/* We entered an interrupt context - irqs are off: */
 	TRACE_IRQS_OFF
 
-	call \func
+	call	\func
 	.endm
 
 	/*
@@ -723,42 +596,36 @@ END(irq_entries_start)
 	 */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
-	XCPT_FRAME
 	ASM_CLAC
-	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
+	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): old RSP */
 ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	decl PER_CPU_VAR(irq_count)
+	decl	PER_CPU_VAR(irq_count)
 
 	/* Restore saved previous stack */
-	popq %rsi
-	CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
+	popq	%rsi
 	/* return code expects complete pt_regs - adjust rsp accordingly: */
-	leaq -RBP(%rsi),%rsp
-	CFI_DEF_CFA_REGISTER	rsp
-	CFI_ADJUST_CFA_OFFSET	RBP
+	leaq	-RBP(%rsi), %rsp
 
-	testl $3,CS(%rsp)
-	je retint_kernel
+	testb	$3, CS(%rsp)
+	jz	retint_kernel
 	/* Interrupt came from user space */
-
+retint_user:
 	GET_THREAD_INFO(%rcx)
-	/*
-	 * %rcx: thread info. Interrupts off.
-	 */
+
+	/* %rcx: thread info. Interrupts are off. */
 retint_with_reschedule:
-	movl $_TIF_WORK_MASK,%edi
+	movl	$_TIF_WORK_MASK, %edi
 retint_check:
 	LOCKDEP_SYS_EXIT_IRQ
-	movl TI_flags(%rcx),%edx
-	andl %edi,%edx
-	CFI_REMEMBER_STATE
-	jnz  retint_careful
+	movl	TI_flags(%rcx), %edx
+	andl	%edi, %edx
+	jnz	retint_careful
 
-retint_swapgs:		/* return to user-space */
+retint_swapgs:					/* return to user-space */
 	/*
 	 * The iretq could re-enable interrupts:
 	 */
@@ -773,9 +640,9 @@ retint_kernel:
 #ifdef CONFIG_PREEMPT
 	/* Interrupts are off */
 	/* Check if we need preemption */
-	bt	$9,EFLAGS(%rsp)	/* interrupts were off? */
+	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
-0:	cmpl	$0,PER_CPU_VAR(__preempt_count)
+0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
 	call	preempt_schedule_irq
 	jmp	0b
@@ -793,8 +660,6 @@ retint_kernel:
 restore_c_regs_and_iret:
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
 	INTERRUPT_RETURN
 
 ENTRY(native_iret)
@@ -803,8 +668,8 @@ ENTRY(native_iret)
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
 #ifdef CONFIG_X86_ESPFIX64
-	testb $4,(SS-RIP)(%rsp)
-	jnz native_irq_return_ldt
+	testb	$4, (SS-RIP)(%rsp)
+	jnz	native_irq_return_ldt
 #endif
 
 .global native_irq_return_iret
@@ -819,62 +684,60 @@ native_irq_return_iret:
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
-	pushq_cfi %rax
-	pushq_cfi %rdi
+	pushq	%rax
+	pushq	%rdi
 	SWAPGS
-	movq PER_CPU_VAR(espfix_waddr),%rdi
-	movq %rax,(0*8)(%rdi)	/* RAX */
-	movq (2*8)(%rsp),%rax	/* RIP */
-	movq %rax,(1*8)(%rdi)
-	movq (3*8)(%rsp),%rax	/* CS */
-	movq %rax,(2*8)(%rdi)
-	movq (4*8)(%rsp),%rax	/* RFLAGS */
-	movq %rax,(3*8)(%rdi)
-	movq (6*8)(%rsp),%rax	/* SS */
-	movq %rax,(5*8)(%rdi)
-	movq (5*8)(%rsp),%rax	/* RSP */
-	movq %rax,(4*8)(%rdi)
-	andl $0xffff0000,%eax
-	popq_cfi %rdi
-	orq PER_CPU_VAR(espfix_stack),%rax
+	movq	PER_CPU_VAR(espfix_waddr), %rdi
+	movq	%rax, (0*8)(%rdi)		/* RAX */
+	movq	(2*8)(%rsp), %rax		/* RIP */
+	movq	%rax, (1*8)(%rdi)
+	movq	(3*8)(%rsp), %rax		/* CS */
+	movq	%rax, (2*8)(%rdi)
+	movq	(4*8)(%rsp), %rax		/* RFLAGS */
+	movq	%rax, (3*8)(%rdi)
+	movq	(6*8)(%rsp), %rax		/* SS */
+	movq	%rax, (5*8)(%rdi)
+	movq	(5*8)(%rsp), %rax		/* RSP */
+	movq	%rax, (4*8)(%rdi)
+	andl	$0xffff0000, %eax
+	popq	%rdi
+	orq	PER_CPU_VAR(espfix_stack), %rax
 	SWAPGS
-	movq %rax,%rsp
-	popq_cfi %rax
-	jmp native_irq_return_iret
+	movq	%rax, %rsp
+	popq	%rax
+	jmp	native_irq_return_iret
 #endif
 
 	/* edi: workmask, edx: work */
 retint_careful:
-	CFI_RESTORE_STATE
-	bt    $TIF_NEED_RESCHED,%edx
-	jnc   retint_signal
+	bt	$TIF_NEED_RESCHED, %edx
+	jnc	retint_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
-	pushq_cfi %rdi
+	pushq	%rdi
 	SCHEDULE_USER
-	popq_cfi %rdi
+	popq	%rdi
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	jmp retint_check
+	jmp	retint_check
 
 retint_signal:
-	testl $_TIF_DO_NOTIFY_MASK,%edx
-	jz    retint_swapgs
+	testl	$_TIF_DO_NOTIFY_MASK, %edx
+	jz	retint_swapgs
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_EXTRA_REGS
-	movq $-1,ORIG_RAX(%rsp)
-	xorl %esi,%esi		# oldset
-	movq %rsp,%rdi		# &pt_regs
-	call do_notify_resume
+	movq	$-1, ORIG_RAX(%rsp)
+	xorl	%esi, %esi			/* oldset */
+	movq	%rsp, %rdi			/* &pt_regs */
+	call	do_notify_resume
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	GET_THREAD_INFO(%rcx)
-	jmp retint_with_reschedule
+	jmp	retint_with_reschedule
 
-	CFI_ENDPROC
 END(common_interrupt)
 
 /*
@@ -882,13 +745,11 @@ END(common_interrupt)
  */
 .macro apicinterrupt3 num sym do_sym
 ENTRY(\sym)
-	INTR_FRAME
 	ASM_CLAC
-	pushq_cfi $~(\num)
+	pushq	$~(\num)
 .Lcommon_\sym:
 	interrupt \do_sym
-	jmp ret_from_intr
-	CFI_ENDPROC
+	jmp	ret_from_intr
 END(\sym)
 .endm
 
@@ -910,53 +771,45 @@ trace_apicinterrupt \num \sym
 .endm
 
 #ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \
-	irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR \
-	reboot_interrupt smp_reboot_interrupt
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR		irq_move_cleanup_interrupt	smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR			reboot_interrupt		smp_reboot_interrupt
 #endif
 
 #ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE \
-	uv_bau_message_intr1 uv_bau_message_interrupt
+apicinterrupt3 UV_BAU_MESSAGE			uv_bau_message_intr1		uv_bau_message_interrupt
 #endif
-apicinterrupt LOCAL_TIMER_VECTOR \
-	apic_timer_interrupt smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR \
-	x86_platform_ipi smp_x86_platform_ipi
+
+apicinterrupt LOCAL_TIMER_VECTOR		apic_timer_interrupt		smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
 
 #ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR \
-	kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
 #endif
 
 #ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR \
-	threshold_interrupt smp_threshold_interrupt
+apicinterrupt THRESHOLD_APIC_VECTOR		threshold_interrupt		smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR		deferred_error_interrupt	smp_deferred_error_interrupt
 #endif
 
 #ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR \
-	thermal_interrupt smp_thermal_interrupt
+apicinterrupt THERMAL_APIC_VECTOR		thermal_interrupt		smp_thermal_interrupt
 #endif
 
 #ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
-	call_function_single_interrupt smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR \
-	call_function_interrupt smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR \
-	reschedule_interrupt smp_reschedule_interrupt
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR	call_function_single_interrupt	smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR		call_function_interrupt		smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR			reschedule_interrupt		smp_reschedule_interrupt
 #endif
 
-apicinterrupt ERROR_APIC_VECTOR \
-	error_interrupt smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR \
-	spurious_interrupt smp_spurious_interrupt
+apicinterrupt ERROR_APIC_VECTOR			error_interrupt			smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR		spurious_interrupt		smp_spurious_interrupt
 
 #ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR \
-	irq_work_interrupt smp_irq_work_interrupt
+apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 #endif
 
 /*
@@ -971,100 +824,87 @@ ENTRY(\sym)
 	.error "using shift_ist requires paranoid=1"
 	.endif
 
-	.if \has_error_code
-	XCPT_FRAME
-	.else
-	INTR_FRAME
-	.endif
-
 	ASM_CLAC
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 
 	.ifeq \has_error_code
-	pushq_cfi $-1			/* ORIG_RAX: no syscall to restart */
+	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
 	ALLOC_PT_GPREGS_ON_STACK
 
 	.if \paranoid
 	.if \paranoid == 1
-	CFI_REMEMBER_STATE
-	testl $3, CS(%rsp)		/* If coming from userspace, switch */
-	jnz 1f				/* stacks. */
+	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
+	jnz	1f
 	.endif
-	call paranoid_entry
+	call	paranoid_entry
 	.else
-	call error_entry
+	call	error_entry
 	.endif
 	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
 
-	DEFAULT_FRAME 0
-
 	.if \paranoid
 	.if \shift_ist != -1
-	TRACE_IRQS_OFF_DEBUG		/* reload IDT in case of recursion */
+	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
 	.else
 	TRACE_IRQS_OFF
 	.endif
 	.endif
 
-	movq %rsp,%rdi			/* pt_regs pointer */
+	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */
-	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
 	.else
-	xorl %esi,%esi			/* no error code */
+	xorl	%esi, %esi			/* no error code */
 	.endif
 
 	.if \shift_ist != -1
-	subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	subq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
 	.endif
 
-	call \do_sym
+	call	\do_sym
 
 	.if \shift_ist != -1
-	addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	addq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	/* these procedures expect "no swapgs" flag in ebx */
 	.if \paranoid
-	jmp paranoid_exit
+	jmp	paranoid_exit
 	.else
-	jmp error_exit
+	jmp	error_exit
 	.endif
 
 	.if \paranoid == 1
-	CFI_RESTORE_STATE
 	/*
 	 * Paranoid entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
 1:
-	call error_entry
+	call	error_entry
 
-	DEFAULT_FRAME 0
 
-	movq %rsp,%rdi			/* pt_regs pointer */
-	call sync_regs
-	movq %rax,%rsp			/* switch stack */
+	movq	%rsp, %rdi			/* pt_regs pointer */
+	call	sync_regs
+	movq	%rax, %rsp			/* switch stack */
 
-	movq %rsp,%rdi			/* pt_regs pointer */
+	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */
-	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
 	.else
-	xorl %esi,%esi			/* no error code */
+	xorl	%esi, %esi			/* no error code */
 	.endif
 
-	call \do_sym
+	call	\do_sym
 
-	jmp error_exit			/* %ebx: no swapgs flag */
+	jmp	error_exit			/* %ebx: no swapgs flag */
 	.endif
-
-	CFI_ENDPROC
 END(\sym)
 .endm
 
@@ -1079,65 +919,58 @@ idtentry \sym \do_sym has_error_code=\has_error_code
 .endm
 #endif
 
-idtentry divide_error do_divide_error has_error_code=0
-idtentry overflow do_overflow has_error_code=0
-idtentry bounds do_bounds has_error_code=0
-idtentry invalid_op do_invalid_op has_error_code=0
-idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=2
-idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
-idtentry invalid_TSS do_invalid_TSS has_error_code=1
-idtentry segment_not_present do_segment_not_present has_error_code=1
-idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
-idtentry coprocessor_error do_coprocessor_error has_error_code=0
-idtentry alignment_check do_alignment_check has_error_code=1
-idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
-
-
-	/* Reload gs selector with exception handling */
-	/* edi:  new selector */
+idtentry divide_error			do_divide_error			has_error_code=0
+idtentry overflow			do_overflow			has_error_code=0
+idtentry bounds				do_bounds			has_error_code=0
+idtentry invalid_op			do_invalid_op			has_error_code=0
+idtentry device_not_available		do_device_not_available		has_error_code=0
+idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun	do_coprocessor_segment_overrun	has_error_code=0
+idtentry invalid_TSS			do_invalid_TSS			has_error_code=1
+idtentry segment_not_present		do_segment_not_present		has_error_code=1
+idtentry spurious_interrupt_bug		do_spurious_interrupt_bug	has_error_code=0
+idtentry coprocessor_error		do_coprocessor_error		has_error_code=0
+idtentry alignment_check		do_alignment_check		has_error_code=1
+idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
+
+
+	/*
+	 * Reload gs selector with exception handling
+	 * edi:  new selector
+	 */
 ENTRY(native_load_gs_index)
-	CFI_STARTPROC
-	pushfq_cfi
+	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
 	SWAPGS
 gs_change:
-	movl %edi,%gs
-2:	mfence		/* workaround */
+	movl	%edi, %gs
+2:	mfence					/* workaround */
 	SWAPGS
-	popfq_cfi
+	popfq
 	ret
-	CFI_ENDPROC
 END(native_load_gs_index)
 
-	_ASM_EXTABLE(gs_change,bad_gs)
-	.section .fixup,"ax"
+	_ASM_EXTABLE(gs_change, bad_gs)
+	.section .fixup, "ax"
 	/* running with kernelgs */
 bad_gs:
-	SWAPGS			/* switch back to user gs */
-	xorl %eax,%eax
-	movl %eax,%gs
-	jmp  2b
+	SWAPGS					/* switch back to user gs */
+	xorl	%eax, %eax
+	movl	%eax, %gs
+	jmp	2b
 	.previous
 
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(do_softirq_own_stack)
-	CFI_STARTPROC
-	pushq_cfi %rbp
-	CFI_REL_OFFSET rbp,0
-	mov  %rsp,%rbp
-	CFI_DEF_CFA_REGISTER rbp
-	incl PER_CPU_VAR(irq_count)
-	cmove PER_CPU_VAR(irq_stack_ptr),%rsp
-	push  %rbp			# backlink for old unwinder
-	call __do_softirq
+	pushq	%rbp
+	mov	%rsp, %rbp
+	incl	PER_CPU_VAR(irq_count)
+	cmove	PER_CPU_VAR(irq_stack_ptr), %rsp
+	push	%rbp				/* frame pointer backlink */
+	call	__do_softirq
 	leaveq
-	CFI_RESTORE		rbp
-	CFI_DEF_CFA_REGISTER	rsp
-	CFI_ADJUST_CFA_OFFSET   -8
-	decl PER_CPU_VAR(irq_count)
+	decl	PER_CPU_VAR(irq_count)
 	ret
-	CFI_ENDPROC
 END(do_softirq_own_stack)
 
 #ifdef CONFIG_XEN
@@ -1156,29 +989,24 @@ idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
  * existing activation in its critical region -- if so, we pop the current
  * activation and restart the handler using the previous one.
  */
-ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
-	CFI_STARTPROC
+ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
+
 /*
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
  * see the correct pointer to the pt_regs
  */
-	movq %rdi, %rsp            # we don't return, adjust the stack frame
-	CFI_ENDPROC
-	DEFAULT_FRAME
-11:	incl PER_CPU_VAR(irq_count)
-	movq %rsp,%rbp
-	CFI_DEF_CFA_REGISTER rbp
-	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
-	pushq %rbp			# backlink for old unwinder
-	call xen_evtchn_do_upcall
-	popq %rsp
-	CFI_DEF_CFA_REGISTER rsp
-	decl PER_CPU_VAR(irq_count)
+	movq	%rdi, %rsp			/* we don't return, adjust the stack frame */
+11:	incl	PER_CPU_VAR(irq_count)
+	movq	%rsp, %rbp
+	cmovzq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	pushq	%rbp				/* frame pointer backlink */
+	call	xen_evtchn_do_upcall
+	popq	%rsp
+	decl	PER_CPU_VAR(irq_count)
 #ifndef CONFIG_PREEMPT
-	call xen_maybe_preempt_hcall
+	call	xen_maybe_preempt_hcall
 #endif
-	jmp  error_exit
-	CFI_ENDPROC
+	jmp	error_exit
 END(xen_do_hypervisor_callback)
 
 /*
@@ -1195,51 +1023,35 @@ END(xen_do_hypervisor_callback)
  * with its current contents: any discrepancy means we in category 1.
  */
 ENTRY(xen_failsafe_callback)
-	INTR_FRAME 1 (6*8)
-	/*CFI_REL_OFFSET gs,GS*/
-	/*CFI_REL_OFFSET fs,FS*/
-	/*CFI_REL_OFFSET es,ES*/
-	/*CFI_REL_OFFSET ds,DS*/
-	CFI_REL_OFFSET r11,8
-	CFI_REL_OFFSET rcx,0
-	movw %ds,%cx
-	cmpw %cx,0x10(%rsp)
-	CFI_REMEMBER_STATE
-	jne 1f
-	movw %es,%cx
-	cmpw %cx,0x18(%rsp)
-	jne 1f
-	movw %fs,%cx
-	cmpw %cx,0x20(%rsp)
-	jne 1f
-	movw %gs,%cx
-	cmpw %cx,0x28(%rsp)
-	jne 1f
+	movl	%ds, %ecx
+	cmpw	%cx, 0x10(%rsp)
+	jne	1f
+	movl	%es, %ecx
+	cmpw	%cx, 0x18(%rsp)
+	jne	1f
+	movl	%fs, %ecx
+	cmpw	%cx, 0x20(%rsp)
+	jne	1f
+	movl	%gs, %ecx
+	cmpw	%cx, 0x28(%rsp)
+	jne	1f
 	/* All segments match their saved values => Category 2 (Bad IRET). */
-	movq (%rsp),%rcx
-	CFI_RESTORE rcx
-	movq 8(%rsp),%r11
-	CFI_RESTORE r11
-	addq $0x30,%rsp
-	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $0	/* RIP */
-	pushq_cfi %r11
-	pushq_cfi %rcx
-	jmp general_protection
-	CFI_RESTORE_STATE
+	movq	(%rsp), %rcx
+	movq	8(%rsp), %r11
+	addq	$0x30, %rsp
+	pushq	$0				/* RIP */
+	pushq	%r11
+	pushq	%rcx
+	jmp	general_protection
 1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
-	movq (%rsp),%rcx
-	CFI_RESTORE rcx
-	movq 8(%rsp),%r11
-	CFI_RESTORE r11
-	addq $0x30,%rsp
-	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq_cfi $-1 /* orig_ax = -1 => not a system call */
+	movq	(%rsp), %rcx
+	movq	8(%rsp), %r11
+	addq	$0x30, %rsp
+	pushq	$-1 /* orig_ax = -1 => not a system call */
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
-	jmp error_exit
-	CFI_ENDPROC
+	jmp	error_exit
 END(xen_failsafe_callback)
 
 apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
@@ -1252,21 +1064,25 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 	hyperv_callback_vector hyperv_vector_handler
 #endif /* CONFIG_HYPERV */
 
-idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1
+idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3			do_int3			has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry stack_segment		do_stack_segment	has_error_code=1
+
 #ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
+idtentry xen_debug		do_debug		has_error_code=0
+idtentry xen_int3		do_int3			has_error_code=0
+idtentry xen_stack_segment	do_stack_segment	has_error_code=1
 #endif
-idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
+
+idtentry general_protection	do_general_protection	has_error_code=1
+trace_idtentry page_fault	do_page_fault		has_error_code=1
+
 #ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault do_async_page_fault has_error_code=1
+idtentry async_page_fault	do_async_page_fault	has_error_code=1
 #endif
+
 #ifdef CONFIG_X86_MCE
-idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
+idtentry machine_check					has_error_code=0	paranoid=1 do_sym=*machine_check_vector(%rip)
 #endif
 
 /*
@@ -1275,19 +1091,17 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
 ENTRY(paranoid_entry)
-	XCPT_FRAME 1 15*8
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
-	movl $1,%ebx
-	movl $MSR_GS_BASE,%ecx
+	movl	$1, %ebx
+	movl	$MSR_GS_BASE, %ecx
 	rdmsr
-	testl %edx,%edx
-	js 1f	/* negative -> in kernel */
+	testl	%edx, %edx
+	js	1f				/* negative -> in kernel */
 	SWAPGS
-	xorl %ebx,%ebx
+	xorl	%ebx, %ebx
 1:	ret
-	CFI_ENDPROC
 END(paranoid_entry)
 
 /*
@@ -1299,17 +1113,17 @@ END(paranoid_entry)
  * in syscall entry), so checking for preemption here would
  * be complicated.  Fortunately, we there's no good reason
  * to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
  */
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
 ENTRY(paranoid_exit)
-	DEFAULT_FRAME
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF_DEBUG
-	testl %ebx,%ebx				/* swapgs needed? */
-	jnz paranoid_exit_no_swapgs
+	testl	%ebx, %ebx			/* swapgs needed? */
+	jnz	paranoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
 	SWAPGS_UNSAFE_STACK
-	jmp paranoid_exit_restore
+	jmp	paranoid_exit_restore
 paranoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
 paranoid_exit_restore:
@@ -1317,24 +1131,24 @@ paranoid_exit_restore:
 	RESTORE_C_REGS
 	REMOVE_PT_GPREGS_FROM_STACK 8
 	INTERRUPT_RETURN
-	CFI_ENDPROC
 END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch gs if needed.
- * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
-	XCPT_FRAME 1 15*8
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
-	xorl %ebx,%ebx
-	testl $3,CS+8(%rsp)
-	je error_kernelspace
-error_swapgs:
+	xorl	%ebx, %ebx
+	testb	$3, CS+8(%rsp)
+	jz	error_kernelspace
+
+	/* We entered from user mode */
 	SWAPGS
-error_sti:
+
+error_entry_done:
 	TRACE_IRQS_OFF
 	ret
 
@@ -1345,56 +1159,66 @@ error_sti:
 	 * for these here too.
 	 */
 error_kernelspace:
-	CFI_REL_OFFSET rcx, RCX+8
-	incl %ebx
-	leaq native_irq_return_iret(%rip),%rcx
-	cmpq %rcx,RIP+8(%rsp)
-	je error_bad_iret
-	movl %ecx,%eax	/* zero extend */
-	cmpq %rax,RIP+8(%rsp)
-	je bstep_iret
-	cmpq $gs_change,RIP+8(%rsp)
-	je error_swapgs
-	jmp error_sti
+	incl	%ebx
+	leaq	native_irq_return_iret(%rip), %rcx
+	cmpq	%rcx, RIP+8(%rsp)
+	je	error_bad_iret
+	movl	%ecx, %eax			/* zero extend */
+	cmpq	%rax, RIP+8(%rsp)
+	je	bstep_iret
+	cmpq	$gs_change, RIP+8(%rsp)
+	jne	error_entry_done
+
+	/*
+	 * hack: gs_change can fail with user gsbase.  If this happens, fix up
+	 * gsbase and proceed.  We'll fix up the exception and land in
+	 * gs_change's error handler with kernel gsbase.
+	 */
+	SWAPGS
+	jmp	error_entry_done
 
 bstep_iret:
 	/* Fix truncated RIP */
-	movq %rcx,RIP+8(%rsp)
+	movq	%rcx, RIP+8(%rsp)
 	/* fall through */
 
 error_bad_iret:
+	/*
+	 * We came from an IRET to user mode, so we have user gsbase.
+	 * Switch to kernel gsbase:
+	 */
 	SWAPGS
-	mov %rsp,%rdi
-	call fixup_bad_iret
-	mov %rax,%rsp
-	decl %ebx	/* Return to usergs */
-	jmp error_sti
-	CFI_ENDPROC
+
+	/*
+	 * Pretend that the exception came from user mode: set up pt_regs
+	 * as if we faulted immediately after IRET and clear EBX so that
+	 * error_exit knows that we will be returning to user mode.
+	 */
+	mov	%rsp, %rdi
+	call	fixup_bad_iret
+	mov	%rax, %rsp
+	decl	%ebx
+	jmp	error_entry_done
 END(error_entry)
 
 
-/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
+/*
+ * On entry, EBS is a "return to kernel mode" flag:
+ *   1: already in kernel mode, don't need SWAPGS
+ *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
+ */
 ENTRY(error_exit)
-	DEFAULT_FRAME
-	movl %ebx,%eax
+	movl	%ebx, %eax
 	RESTORE_EXTRA_REGS
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)
-	testl %eax,%eax
-	jne retint_kernel
-	LOCKDEP_SYS_EXIT_IRQ
-	movl TI_flags(%rcx),%edx
-	movl $_TIF_WORK_MASK,%edi
-	andl %edi,%edx
-	jnz retint_careful
-	jmp retint_swapgs
-	CFI_ENDPROC
+	testl	%eax, %eax
+	jnz	retint_kernel
+	jmp	retint_user
 END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
-	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
@@ -1429,22 +1253,21 @@ ENTRY(nmi)
 	 */
 
 	/* Use %rdx as our temp variable throughout */
-	pushq_cfi %rdx
-	CFI_REL_OFFSET rdx, 0
+	pushq	%rdx
 
 	/*
 	 * If %cs was not the kernel segment, then the NMI triggered in user
 	 * space, which means it is definitely not nested.
 	 */
-	cmpl $__KERNEL_CS, 16(%rsp)
-	jne first_nmi
+	cmpl	$__KERNEL_CS, 16(%rsp)
+	jne	first_nmi
 
 	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
-	cmpl $1, -8(%rsp)
-	je nested_nmi
+	cmpl	$1, -8(%rsp)
+	je	nested_nmi
 
 	/*
 	 * Now test if the previous stack was an NMI stack.
@@ -1458,51 +1281,46 @@ ENTRY(nmi)
 	cmpq	%rdx, 4*8(%rsp)
 	/* If the stack pointer is above the NMI stack, this is a normal NMI */
 	ja	first_nmi
+
 	subq	$EXCEPTION_STKSZ, %rdx
 	cmpq	%rdx, 4*8(%rsp)
 	/* If it is below the NMI stack, it is a normal NMI */
 	jb	first_nmi
 	/* Ah, it is within the NMI stack, treat it as nested */
 
-	CFI_REMEMBER_STATE
-
 nested_nmi:
 	/*
 	 * Do nothing if we interrupted the fixup in repeat_nmi.
 	 * It's about to repeat the NMI handler, so we are fine
 	 * with ignoring this one.
 	 */
-	movq $repeat_nmi, %rdx
-	cmpq 8(%rsp), %rdx
-	ja 1f
-	movq $end_repeat_nmi, %rdx
-	cmpq 8(%rsp), %rdx
-	ja nested_nmi_out
+	movq	$repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	1f
+	movq	$end_repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	nested_nmi_out
 
 1:
 	/* Set up the interrupted NMIs stack to jump to repeat_nmi */
-	leaq -1*8(%rsp), %rdx
-	movq %rdx, %rsp
-	CFI_ADJUST_CFA_OFFSET 1*8
-	leaq -10*8(%rsp), %rdx
-	pushq_cfi $__KERNEL_DS
-	pushq_cfi %rdx
-	pushfq_cfi
-	pushq_cfi $__KERNEL_CS
-	pushq_cfi $repeat_nmi
+	leaq	-1*8(%rsp), %rdx
+	movq	%rdx, %rsp
+	leaq	-10*8(%rsp), %rdx
+	pushq	$__KERNEL_DS
+	pushq	%rdx
+	pushfq
+	pushq	$__KERNEL_CS
+	pushq	$repeat_nmi
 
 	/* Put stack back */
-	addq $(6*8), %rsp
-	CFI_ADJUST_CFA_OFFSET -6*8
+	addq	$(6*8), %rsp
 
 nested_nmi_out:
-	popq_cfi %rdx
-	CFI_RESTORE rdx
+	popq	%rdx
 
 	/* No need to check faults here */
 	INTERRUPT_RETURN
 
-	CFI_RESTORE_STATE
 first_nmi:
 	/*
 	 * Because nested NMIs will use the pushed location that we
@@ -1540,23 +1358,18 @@ first_nmi:
 	 * is also used by nested NMIs and can not be trusted on exit.
 	 */
 	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
-	movq (%rsp), %rdx
-	CFI_RESTORE rdx
+	movq	(%rsp), %rdx
 
 	/* Set the NMI executing variable on the stack. */
-	pushq_cfi $1
+	pushq	$1
 
-	/*
-	 * Leave room for the "copied" frame
-	 */
-	subq $(5*8), %rsp
-	CFI_ADJUST_CFA_OFFSET 5*8
+	/* Leave room for the "copied" frame */
+	subq	$(5*8), %rsp
 
 	/* Copy the stack frame to the Saved frame */
 	.rept 5
-	pushq_cfi 11*8(%rsp)
+	pushq	11*8(%rsp)
 	.endr
-	CFI_DEF_CFA_OFFSET 5*8
 
 	/* Everything up to here is safe from nested NMIs */
 
@@ -1575,16 +1388,14 @@ repeat_nmi:
 	 * is benign for the non-repeat case, where 1 was pushed just above
 	 * to this very stack slot).
 	 */
-	movq $1, 10*8(%rsp)
+	movq	$1, 10*8(%rsp)
 
 	/* Make another copy, this one may be modified by nested NMIs */
-	addq $(10*8), %rsp
-	CFI_ADJUST_CFA_OFFSET -10*8
+	addq	$(10*8), %rsp
 	.rept 5
-	pushq_cfi -6*8(%rsp)
+	pushq	-6*8(%rsp)
 	.endr
-	subq $(5*8), %rsp
-	CFI_DEF_CFA_OFFSET 5*8
+	subq	$(5*8), %rsp
 end_repeat_nmi:
 
 	/*
@@ -1592,7 +1403,7 @@ end_repeat_nmi:
 	 * NMI if the first NMI took an exception and reset our iret stack
 	 * so that we repeat another NMI.
 	 */
-	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	ALLOC_PT_GPREGS_ON_STACK
 
 	/*
@@ -1602,8 +1413,7 @@ end_repeat_nmi:
 	 * setting NEED_RESCHED or anything that normal interrupts and
 	 * exceptions might do.
 	 */
-	call paranoid_entry
-	DEFAULT_FRAME 0
+	call	paranoid_entry
 
 	/*
 	 * Save off the CR2 register. If we take a page fault in the NMI then
@@ -1614,22 +1424,21 @@ end_repeat_nmi:
 	 * origin fault. Save it off and restore it if it changes.
 	 * Use the r12 callee-saved register.
 	 */
-	movq %cr2, %r12
+	movq	%cr2, %r12
 
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
-	movq %rsp,%rdi
-	movq $-1,%rsi
-	call do_nmi
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
 
 	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq %cr2, %rcx
-	cmpq %rcx, %r12
-	je 1f
-	movq %r12, %cr2
+	movq	%cr2, %rcx
+	cmpq	%rcx, %r12
+	je	1f
+	movq	%r12, %cr2
 1:
-	
-	testl %ebx,%ebx				/* swapgs needed? */
-	jnz nmi_restore
+	testl	%ebx, %ebx			/* swapgs needed? */
+	jnz	nmi_restore
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
@@ -1639,15 +1448,11 @@ nmi_restore:
 	REMOVE_PT_GPREGS_FROM_STACK 6*8
 
 	/* Clear the NMI executing stack variable */
-	movq $0, 5*8(%rsp)
-	jmp irq_return
-	CFI_ENDPROC
+	movq	$0, 5*8(%rsp)
+	INTERRUPT_RETURN
 END(nmi)
 
 ENTRY(ignore_sysret)
-	CFI_STARTPROC
-	mov $-ENOSYS,%eax
+	mov	$-ENOSYS, %eax
 	sysret
-	CFI_ENDPROC
 END(ignore_sysret)
-
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
new file mode 100644
index 000000000000..bb187a6a877c
--- /dev/null
+++ b/arch/x86/entry/entry_64_compat.S
@@ -0,0 +1,556 @@
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
+#include <linux/elf-em.h>
+#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
+#define __AUDIT_ARCH_LE		0x40000000
+
+#ifndef CONFIG_AUDITSYSCALL
+# define sysexit_audit		ia32_ret_from_sys_call
+# define sysretl_audit		ia32_ret_from_sys_call
+#endif
+
+	.section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret32)
+	swapgs
+	sysretl
+ENDPROC(native_usergs_sysret32)
+#endif
+
+/*
+ * 32-bit SYSENTER instruction entry.
+ *
+ * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
+ * IF and VM in rflags are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old rip (!!!) and rflags.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  user stack
+ * 0(%ebp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSENTER_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	SWAPGS_UNSAFE_STACK
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%ebp, %ebp
+	movl	%eax, %eax
+
+	movl	ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
+
+	/* Construct struct pt_regs on stack */
+	pushq	$__USER32_DS		/* pt_regs->ss */
+	pushq	%rbp			/* pt_regs->sp */
+	pushfq				/* pt_regs->flags */
+	pushq	$__USER32_CS		/* pt_regs->cs */
+	pushq	%r10			/* pt_regs->ip = thread_info->sysenter_return */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rcx			/* pt_regs->cx */
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	cld
+	sub	$(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+	/*
+	 * no need to do an access_ok check here because rbp has been
+	 * 32-bit zero extended
+	 */
+	ASM_STAC
+1:	movl	(%rbp), %ebp
+	_ASM_EXTABLE(1b, ia32_badarg)
+	ASM_CLAC
+
+	/*
+	 * Sysenter doesn't filter flags, so we need to clear NT
+	 * ourselves.  To save a few cycles, we can check whether
+	 * NT was set instead of doing an unconditional popfq.
+	 */
+	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
+	jnz	sysenter_fix_flags
+sysenter_flags_fixed:
+
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysenter_tracesys
+
+sysenter_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+sysenter_dispatch:
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysexit_audit
+sysexit_from_sys_call:
+	/*
+	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
+	 * NMI between STI and SYSEXIT has poorly specified behavior,
+	 * and and NMI followed by an IRQ with usergs is fatal.  So
+	 * we just pretend we're using SYSEXIT but we really use
+	 * SYSRETL instead.
+	 *
+	 * This code path is still called 'sysexit' because it pairs
+	 * with 'sysenter' and it uses the SYSENTER calling convention.
+	 */
+	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	movl	RIP(%rsp), %ecx		/* User %eip */
+	RESTORE_RSI_RDI
+	xorl	%edx, %edx		/* Do not leak kernel information */
+	xorq	%r8, %r8
+	xorq	%r9, %r9
+	xorq	%r10, %r10
+	movl	EFLAGS(%rsp), %r11d	/* User eflags */
+	TRACE_IRQS_ON
+
+	/*
+	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
+	 * since it avoids a dicey window with interrupts enabled.
+	 */
+	movl	RSP(%rsp), %esp
+
+	/*
+	 * USERGS_SYSRET32 does:
+	 *  gsbase = user's gs base
+	 *  eip = ecx
+	 *  rflags = r11
+	 *  cs = __USER32_CS
+	 *  ss = __USER_DS
+	 *
+	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
+	 *
+	 *  pop %ebp
+	 *  pop %edx
+	 *  pop %ecx
+	 *
+	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
+	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
+	 * address (already known to user code), and R12-R15 are
+	 * callee-saved and therefore don't contain any interesting
+	 * kernel data.
+	 */
+	USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+	.macro auditsys_entry_common
+	/*
+	 * At this point, registers hold syscall args in the 32-bit syscall ABI:
+	 * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
+	 *
+	 * We want to pass them to __audit_syscall_entry(), which is a 64-bit
+	 * C function with 5 parameters, so shuffle them to match what
+	 * the function expects: RDI,RSI,RDX,RCX,R8.
+	 */
+	movl	%esi, %r8d		/* arg5 (R8 ) <= 4th syscall arg (ESI) */
+	xchg	%ecx, %edx		/* arg4 (RCX) <= 3rd syscall arg (EDX) */
+					/* arg3 (RDX) <= 2nd syscall arg (ECX) */
+	movl	%ebx, %esi		/* arg2 (RSI) <= 1st syscall arg (EBX) */
+	movl	%eax, %edi		/* arg1 (RDI) <= syscall number  (EAX) */
+	call	__audit_syscall_entry
+
+	/*
+	 * We are going to jump back to the syscall dispatch code.
+	 * Prepare syscall args as required by the 64-bit C ABI.
+	 * Registers clobbered by __audit_syscall_entry() are
+	 * loaded from pt_regs on stack:
+	 */
+	movl	ORIG_RAX(%rsp), %eax	/* syscall number */
+	movl	%ebx, %edi		/* arg1 */
+	movl	RCX(%rsp), %esi		/* arg2 */
+	movl	RDX(%rsp), %edx		/* arg3 */
+	movl	RSI(%rsp), %ecx		/* arg4 */
+	movl	RDI(%rsp), %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	.endm
+
+	.macro auditsys_exit exit
+	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	ia32_ret_from_sys_call
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	movl	%eax, %esi		/* second arg, syscall return value */
+	cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
+	jbe	1f
+	movslq	%eax, %rsi		/* if error sign extend to 64 bits */
+1:	setbe	%al			/* 1 if error, 0 if not */
+	movzbl	%al, %edi		/* zero-extend that into %edi */
+	call	__audit_syscall_exit
+	movq	RAX(%rsp), %rax		/* reload syscall return value */
+	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	%edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	\exit
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	jmp	int_with_check
+	.endm
+
+sysenter_auditsys:
+	auditsys_entry_common
+	jmp	sysenter_dispatch
+
+sysexit_audit:
+	auditsys_exit sysexit_from_sys_call
+#endif
+
+sysenter_fix_flags:
+	pushq	$(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	popfq
+	jmp	sysenter_flags_fixed
+
+sysenter_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	sysenter_auditsys
+#endif
+	SAVE_EXTRA_REGS
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+
+	/* Reload arg registers from stack. (see sysenter_tracesys) */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+
+	RESTORE_EXTRA_REGS
+	jmp	sysenter_do_call
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL instruction entry.
+ *
+ * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Note: rflags saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: rflags saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax  system call number
+ * ecx  return address
+ * ebx  arg1
+ * ebp  arg2	(note: not saved in the stack frame, should not be touched)
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * esp  user stack
+ * 0(%esp) arg6
+ *
+ * This is purely a fast path. For anything complicated we use the int 0x80
+ * path below. We set up a complete hardware stack frame to share code
+ * with the int 0x80 path.
+ */
+ENTRY(entry_SYSCALL_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	SWAPGS_UNSAFE_STACK
+	movl	%esp, %r8d
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%eax, %eax
+
+	/* Construct struct pt_regs on stack */
+	pushq	$__USER32_DS		/* pt_regs->ss */
+	pushq	%r8			/* pt_regs->sp */
+	pushq	%r11			/* pt_regs->flags */
+	pushq	$__USER32_CS		/* pt_regs->cs */
+	pushq	%rcx			/* pt_regs->ip */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rbp			/* pt_regs->cx */
+	movl	%ebp, %ecx
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	sub	$(10*8), %rsp		/* pt_regs->r8-11, bp, bx, r12-15 not saved */
+
+	/*
+	 * No need to do an access_ok check here because r8 has been
+	 * 32-bit zero extended:
+	 */
+	ASM_STAC
+1:	movl	(%r8), %ebp
+	_ASM_EXTABLE(1b, ia32_badarg)
+	ASM_CLAC
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	cstar_tracesys
+
+cstar_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+
+cstar_dispatch:
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	movl	RCX(%rsp), %ebp
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	sysretl_audit
+
+sysretl_from_sys_call:
+	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	RESTORE_RSI_RDI_RDX
+	movl	RIP(%rsp), %ecx
+	movl	EFLAGS(%rsp), %r11d
+	xorq	%r10, %r10
+	xorq	%r9, %r9
+	xorq	%r8, %r8
+	TRACE_IRQS_ON
+	movl	RSP(%rsp), %esp
+	/*
+	 * 64-bit->32-bit SYSRET restores eip from ecx,
+	 * eflags from r11 (but RF and VM bits are forced to 0),
+	 * cs and ss are loaded from MSRs.
+	 * (Note: 32-bit->32-bit SYSRET is different: since r11
+	 * does not exist, it merely sets eflags.IF=1).
+	 *
+	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
+	 * descriptor is not reinitialized.  This means that we must
+	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
+	 * exit the kernel, and re-enter using an interrupt vector.  (All
+	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
+	 * from happening by reloading SS in __switch_to.
+	 */
+	USERGS_SYSRET32
+
+#ifdef CONFIG_AUDITSYSCALL
+cstar_auditsys:
+	auditsys_entry_common
+	jmp	cstar_dispatch
+
+sysretl_audit:
+	auditsys_exit sysretl_from_sys_call
+#endif
+
+cstar_tracesys:
+#ifdef CONFIG_AUDITSYSCALL
+	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jz	cstar_auditsys
+#endif
+	SAVE_EXTRA_REGS
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+
+	/* Reload arg registers from stack. (see sysenter_tracesys) */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+
+	RESTORE_EXTRA_REGS
+	jmp	cstar_do_call
+END(entry_SYSCALL_compat)
+
+ia32_badarg:
+	ASM_CLAC
+	movq	$-EFAULT, RAX(%rsp)
+ia32_ret_from_sys_call:
+	xorl	%eax, %eax		/* Do not leak kernel information */
+	movq	%rax, R11(%rsp)
+	movq	%rax, R10(%rsp)
+	movq	%rax, R9(%rsp)
+	movq	%rax, R8(%rsp)
+	jmp	int_ret_from_sys_call
+
+/*
+ * Emulated IA32 system calls via int 0x80.
+ *
+ * Arguments:
+ * eax  system call number
+ * ebx  arg1
+ * ecx  arg2
+ * edx  arg3
+ * esi  arg4
+ * edi  arg5
+ * ebp  arg6	(note: not saved in the stack frame, should not be touched)
+ *
+ * Notes:
+ * Uses the same stack frame as the x86-64 version.
+ * All registers except eax must be saved (but ptrace may violate that).
+ * Arguments are zero extended. For system calls that want sign extension and
+ * take long arguments a wrapper is needed. Most calls can just be called
+ * directly.
+ * Assumes it is only called from user space and entered with interrupts off.
+ */
+
+ENTRY(entry_INT80_compat)
+	/*
+	 * Interrupts are off on entry.
+	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+	 * it is too small to ever cause noticeable irq latency.
+	 */
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	SWAPGS
+	ENABLE_INTERRUPTS(CLBR_NONE)
+
+	/* Zero-extending 32-bit regs, do not remove */
+	movl	%eax, %eax
+
+	/* Construct struct pt_regs on stack (iret frame is already on stack) */
+	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+	pushq	%rsi			/* pt_regs->si */
+	pushq	%rdx			/* pt_regs->dx */
+	pushq	%rcx			/* pt_regs->cx */
+	pushq	$-ENOSYS		/* pt_regs->ax */
+	pushq	$0			/* pt_regs->r8 */
+	pushq	$0			/* pt_regs->r9 */
+	pushq	$0			/* pt_regs->r10 */
+	pushq	$0			/* pt_regs->r11 */
+	cld
+	sub	$(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+
+	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
+	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	jnz	ia32_tracesys
+
+ia32_do_call:
+	/* 32-bit syscall -> 64-bit C ABI argument conversion */
+	movl	%edi, %r8d		/* arg5 */
+	movl	%ebp, %r9d		/* arg6 */
+	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
+	movl	%ebx, %edi		/* arg1 */
+	movl	%edx, %edx		/* arg3 (zero extension) */
+	cmpq	$(IA32_NR_syscalls-1), %rax
+	ja	1f
+
+	call	*ia32_sys_call_table(, %rax, 8)
+	movq	%rax, RAX(%rsp)
+1:
+	jmp	int_ret_from_sys_call
+
+ia32_tracesys:
+	SAVE_EXTRA_REGS
+	movq	%rsp, %rdi			/* &pt_regs -> arg1 */
+	call	syscall_trace_enter
+	/*
+	 * Reload arg registers from stack in case ptrace changed them.
+	 * Don't reload %eax because syscall_trace_enter() returned
+	 * the %rax value we should see.  But do truncate it to 32 bits.
+	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
+	 * an appropriately invalid value.
+	 */
+	movl	RCX(%rsp), %ecx
+	movl	RDX(%rsp), %edx
+	movl	RSI(%rsp), %esi
+	movl	RDI(%rsp), %edi
+	movl	%eax, %eax		/* zero extension */
+	RESTORE_EXTRA_REGS
+	jmp	ia32_do_call
+END(entry_INT80_compat)
+
+	.macro PTREGSCALL label, func
+	ALIGN
+GLOBAL(\label)
+	leaq	\func(%rip), %rax
+	jmp	ia32_ptregs_common
+	.endm
+
+	PTREGSCALL stub32_rt_sigreturn,	sys32_rt_sigreturn
+	PTREGSCALL stub32_sigreturn,	sys32_sigreturn
+	PTREGSCALL stub32_fork,		sys_fork
+	PTREGSCALL stub32_vfork,	sys_vfork
+
+	ALIGN
+GLOBAL(stub32_clone)
+	leaq	sys_clone(%rip), %rax
+	/*
+	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
+	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
+	 *
+	 * The native 64-bit kernel's sys_clone() implements the latter,
+	 * so we need to swap arguments here before calling it:
+	 */
+	xchg	%r8, %rcx
+	jmp	ia32_ptregs_common
+
+	ALIGN
+ia32_ptregs_common:
+	SAVE_EXTRA_REGS 8
+	call	*%rax
+	RESTORE_EXTRA_REGS 8
+	ret
+END(ia32_ptregs_common)
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/entry/syscall_32.c
index 3777189c4a19..8ea34f94e973 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -10,7 +10,7 @@
 #else
 #define SYM(sym, compat) sym
 #define ia32_sys_call_table sys_call_table
-#define __NR_ia32_syscall_max __NR_syscall_max
+#define __NR_syscall_compat_max __NR_syscall_max
 #endif
 
 #define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
@@ -23,11 +23,11 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
 
 extern asmlinkage void sys_ni_syscall(void);
 
-__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
 	/*
 	 * Smells like a compiler bug -- it doesn't work
 	 * when the & below is removed.
 	 */
-	[0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
+	[0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
 #include <asm/syscalls_32.h>
 };
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/entry/syscall_64.c
index 4ac730b37f0b..4ac730b37f0b 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
index a55abb9f6c5e..57aa59fd140c 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/entry/syscalls/Makefile
@@ -1,5 +1,5 @@
-out := $(obj)/../include/generated/asm
-uapi := $(obj)/../include/generated/uapi/asm
+out := $(obj)/../../include/generated/asm
+uapi := $(obj)/../../include/generated/uapi/asm
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f9d28d..ef8187f9d28d 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5f1b19..9ef32d5f1b19 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
index 31fd5f1f38f7..31fd5f1f38f7 100644
--- a/arch/x86/syscalls/syscallhdr.sh
+++ b/arch/x86/entry/syscalls/syscallhdr.sh
diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
index 0e7f8ec071e7..0e7f8ec071e7 100644
--- a/arch/x86/syscalls/syscalltbl.sh
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/entry/thunk_32.S
index 5eb715087b80..e5a17114a8c4 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -6,16 +6,14 @@
  */
 	#include <linux/linkage.h>
 	#include <asm/asm.h>
-	#include <asm/dwarf2.h>
 
 	/* put return address in eax (arg1) */
 	.macro THUNK name, func, put_ret_addr_in_eax=0
 	.globl \name
 \name:
-	CFI_STARTPROC
-	pushl_cfi_reg eax
-	pushl_cfi_reg ecx
-	pushl_cfi_reg edx
+	pushl %eax
+	pushl %ecx
+	pushl %edx
 
 	.if \put_ret_addr_in_eax
 	/* Place EIP in the arg1 */
@@ -23,11 +21,10 @@
 	.endif
 
 	call \func
-	popl_cfi_reg edx
-	popl_cfi_reg ecx
-	popl_cfi_reg eax
+	popl %edx
+	popl %ecx
+	popl %eax
 	ret
-	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -38,8 +35,6 @@
 
 #ifdef CONFIG_PREEMPT
 	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 #endif
 
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/entry/thunk_64.S
index f89ba4e93025..efb2b932b748 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -6,35 +6,32 @@
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
+#include "calling.h"
 #include <asm/asm.h>
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
 	.globl \name
 \name:
-	CFI_STARTPROC
 
 	/* this one pushes 9 elems, the next one would be %rIP */
-	pushq_cfi_reg rdi
-	pushq_cfi_reg rsi
-	pushq_cfi_reg rdx
-	pushq_cfi_reg rcx
-	pushq_cfi_reg rax
-	pushq_cfi_reg r8
-	pushq_cfi_reg r9
-	pushq_cfi_reg r10
-	pushq_cfi_reg r11
+	pushq %rdi
+	pushq %rsi
+	pushq %rdx
+	pushq %rcx
+	pushq %rax
+	pushq %r8
+	pushq %r9
+	pushq %r10
+	pushq %r11
 
 	.if \put_ret_addr_in_rdi
 	/* 9*8(%rsp) is return addr on stack */
-	movq_cfi_restore 9*8, rdi
+	movq 9*8(%rsp), %rdi
 	.endif
 
 	call \func
 	jmp  restore
-	CFI_ENDPROC
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -49,27 +46,22 @@
 
 #ifdef CONFIG_PREEMPT
 	THUNK ___preempt_schedule, preempt_schedule
-#ifdef CONFIG_CONTEXT_TRACKING
-	THUNK ___preempt_schedule_context, preempt_schedule_context
-#endif
+	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 #endif
 
 #if defined(CONFIG_TRACE_IRQFLAGS) \
  || defined(CONFIG_DEBUG_LOCK_ALLOC) \
  || defined(CONFIG_PREEMPT)
-	CFI_STARTPROC
-	CFI_ADJUST_CFA_OFFSET 9*8
 restore:
-	popq_cfi_reg r11
-	popq_cfi_reg r10
-	popq_cfi_reg r9
-	popq_cfi_reg r8
-	popq_cfi_reg rax
-	popq_cfi_reg rcx
-	popq_cfi_reg rdx
-	popq_cfi_reg rsi
-	popq_cfi_reg rdi
+	popq %r11
+	popq %r10
+	popq %r9
+	popq %r8
+	popq %rax
+	popq %rcx
+	popq %rdx
+	popq %rsi
+	popq %rdi
 	ret
-	CFI_ENDPROC
 	_ASM_NOKPROBE(restore)
 #endif
diff --git a/arch/x86/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore
index aae8ffdd5880..aae8ffdd5880 100644
--- a/arch/x86/vdso/.gitignore
+++ b/arch/x86/entry/vdso/.gitignore
diff --git a/arch/x86/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 275a3a8b78af..e97032069f88 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -51,7 +51,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
diff --git a/arch/x86/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
index 7ee90a9b549d..7ee90a9b549d 100755
--- a/arch/x86/vdso/checkundef.sh
+++ b/arch/x86/entry/vdso/checkundef.sh
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 9793322751e0..9793322751e0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921025f5..de2c921025f5 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
diff --git a/arch/x86/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
index 79a071e4357e..79a071e4357e 100644
--- a/arch/x86/vdso/vdso-note.S
+++ b/arch/x86/entry/vdso/vdso-note.S
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
index 6807932643c2..6807932643c2 100644
--- a/arch/x86/vdso/vdso.lds.S
+++ b/arch/x86/entry/vdso/vdso.lds.S
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 8627db24a7f6..8627db24a7f6 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 0224987556ce..0224987556ce 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index e904c270573b..e904c270573b 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
diff --git a/arch/x86/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore
index e45fba9d0ced..e45fba9d0ced 100644
--- a/arch/x86/vdso/vdso32/.gitignore
+++ b/arch/x86/entry/vdso/vdso32/.gitignore
diff --git a/arch/x86/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S
index b15b7c01aedb..b15b7c01aedb 100644
--- a/arch/x86/vdso/vdso32/int80.S
+++ b/arch/x86/entry/vdso/vdso32/int80.S
diff --git a/arch/x86/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
index c83f25734696..c83f25734696 100644
--- a/arch/x86/vdso/vdso32/note.S
+++ b/arch/x86/entry/vdso/vdso32/note.S
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index d7ec4e251c0a..d7ec4e251c0a 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S
index 6b286bb5251c..6b286bb5251c 100644
--- a/arch/x86/vdso/vdso32/syscall.S
+++ b/arch/x86/entry/vdso/vdso32/syscall.S
diff --git a/arch/x86/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S
index e354bceee0e0..e354bceee0e0 100644
--- a/arch/x86/vdso/vdso32/sysenter.S
+++ b/arch/x86/entry/vdso/vdso32/sysenter.S
diff --git a/arch/x86/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 175cc72c0f68..175cc72c0f68 100644
--- a/arch/x86/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
index 541468e25265..541468e25265 100644
--- a/arch/x86/vdso/vdso32/vdso-fakesections.c
+++ b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c
diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
index 31056cf294bf..31056cf294bf 100644
--- a/arch/x86/vdso/vdso32/vdso32.lds.S
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
index 697c11ece90c..697c11ece90c 100644
--- a/arch/x86/vdso/vdsox32.lds.S
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
index 8ec3d1f4ce9a..8ec3d1f4ce9a 100644
--- a/arch/x86/vdso/vgetcpu.c
+++ b/arch/x86/entry/vdso/vgetcpu.c
diff --git a/arch/x86/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 1c9f750c3859..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000000..a9f4856f622a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y					:= vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2dcc6ff6fdcc..2dcc6ff6fdcc 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
index c9596a9af159..c9596a9af159 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
index 51e330416995..51e330416995 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
index a8b2edec54fe..9dd7359a38a8 100644
--- a/arch/x86/kernel/vsyscall_trace.h
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -24,6 +24,6 @@ TRACE_EVENT(emulate_vsyscall,
 #endif
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../arch/x86/kernel
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
 #define TRACE_INCLUDE_FILE vsyscall_trace
 #include <trace/define_trace.h>
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index bb635c641869..cd4339bae066 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the ia32 kernel emulation subsystem.
 #
 
-obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o
 
 obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
 
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index c81d35e6c7f1..ae3a29ae875b 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -21,8 +21,8 @@
 #include <linux/binfmts.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/ptrace.h>
 #include <asm/ia32_unistd.h>
 #include <asm/user32.h>
@@ -198,7 +198,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, 1);
+	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
 
@@ -308,6 +308,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 				 size_t frame_size,
 				 void __user **fpstate)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	unsigned long sp;
 
 	/* Default to using normal stack */
@@ -322,12 +323,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
 		 ksig->ka.sa.sa_restorer)
 		sp = (unsigned long) ksig->ka.sa.sa_restorer;
 
-	if (used_math()) {
+	if (fpu->fpstate_active) {
 		unsigned long fx_aligned, math_size;
 
-		sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+		sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
 		*fpstate = (struct _fpstate_ia32 __user *) sp;
-		if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+		if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned,
 				    math_size) < 0)
 			return (void __user *) -1L;
 	}
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
deleted file mode 100644
index 72bf2680f819..000000000000
--- a/arch/x86/ia32/ia32entry.S
+++ /dev/null
@@ -1,611 +0,0 @@
-/*
- * Compatibility mode system call entry point for x86-64. 
- * 		
- * Copyright 2000-2002 Andi Kleen, SuSE Labs.
- */		 
-
-#include <asm/dwarf2.h>
-#include <asm/calling.h>
-#include <asm/asm-offsets.h>
-#include <asm/current.h>
-#include <asm/errno.h>
-#include <asm/ia32_unistd.h>	
-#include <asm/thread_info.h>	
-#include <asm/segment.h>
-#include <asm/irqflags.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-#include <linux/linkage.h>
-#include <linux/err.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE	   0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysexit_audit ia32_ret_from_sys_call
-#define sysretl_audit ia32_ret_from_sys_call
-#endif
-
-	.section .entry.text, "ax"
-
-	/* clobbers %rax */
-	.macro  CLEAR_RREGS _r9=rax
-	xorl 	%eax,%eax
-	movq	%rax,R11(%rsp)
-	movq	%rax,R10(%rsp)
-	movq	%\_r9,R9(%rsp)
-	movq	%rax,R8(%rsp)
-	.endm
-
-	/*
-	 * Reload arg registers from stack in case ptrace changed them.
-	 * We don't reload %eax because syscall_trace_enter() returned
-	 * the %rax value we should see.  Instead, we just truncate that
-	 * value to 32 bits again as we did on entry from user mode.
-	 * If it's a new value set by user_regset during entry tracing,
-	 * this matches the normal truncation of the user-mode value.
-	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
-	 * an appropriately invalid value.
-	 */
-	.macro LOAD_ARGS32 _r9=0
-	.if \_r9
-	movl R9(%rsp),%r9d
-	.endif
-	movl RCX(%rsp),%ecx
-	movl RDX(%rsp),%edx
-	movl RSI(%rsp),%esi
-	movl RDI(%rsp),%edi
-	movl %eax,%eax			/* zero extension */
-	.endm
-	
-	.macro CFI_STARTPROC32 simple
-	CFI_STARTPROC	\simple
-	CFI_UNDEFINED	r8
-	CFI_UNDEFINED	r9
-	CFI_UNDEFINED	r10
-	CFI_UNDEFINED	r11
-	CFI_UNDEFINED	r12
-	CFI_UNDEFINED	r13
-	CFI_UNDEFINED	r14
-	CFI_UNDEFINED	r15
-	.endm
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
-	swapgs
-	sysretl
-ENDPROC(native_usergs_sysret32)
-
-ENTRY(native_irq_enable_sysexit)
-	swapgs
-	sti
-	sysexit
-ENDPROC(native_irq_enable_sysexit)
-#endif
-
-/*
- * 32bit SYSENTER instruction entry.
- *
- * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
- * IF and VM in rflags are cleared (IOW: interrupts are off).
- * SYSENTER does not save anything on the stack,
- * and does not save old rip (!!!) and rflags.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  user stack
- * 0(%ebp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_sysenter_target)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rsp,rbp
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	SWAPGS_UNSAFE_STACK
-	movq	PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%ebp, %ebp
-	movl	%eax, %eax
-
-	movl	ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
-	CFI_REGISTER rip,r10
-
-	/* Construct struct pt_regs on stack */
-	pushq_cfi	$__USER32_DS		/* pt_regs->ss */
-	pushq_cfi	%rbp			/* pt_regs->sp */
-	CFI_REL_OFFSET	rsp,0
-	pushfq_cfi				/* pt_regs->flags */
-	pushq_cfi	$__USER32_CS		/* pt_regs->cs */
-	pushq_cfi	%r10 /* pt_regs->ip = thread_info->sysenter_return */
-	CFI_REL_OFFSET	rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	cld
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	/*
-	 * no need to do an access_ok check here because rbp has been
-	 * 32bit zero extended
-	 */
-	ASM_STAC
-1:	movl	(%rbp),%ebp
-	_ASM_EXTABLE(1b,ia32_badarg)
-	ASM_CLAC
-
-	/*
-	 * Sysenter doesn't filter flags, so we need to clear NT
-	 * ourselves.  To save a few cycles, we can check whether
-	 * NT was set instead of doing an unconditional popfq.
-	 */
-	testl $X86_EFLAGS_NT,EFLAGS(%rsp)
-	jnz sysenter_fix_flags
-sysenter_flags_fixed:
-
-	orl     $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	CFI_REMEMBER_STATE
-	jnz  sysenter_tracesys
-	cmpq	$(IA32_NR_syscalls-1),%rax
-	ja	ia32_badsys
-sysenter_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl	%edi,%r8d	/* arg5 */
-	movl	%ebp,%r9d	/* arg6 */
-	xchg	%ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl	%ebx,%edi	/* arg1 */
-	movl	%edx,%edx	/* arg3 (zero extension) */
-sysenter_dispatch:
-	call	*ia32_sys_call_table(,%rax,8)
-	movq	%rax,RAX(%rsp)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysexit_audit
-sysexit_from_sys_call:
-	/*
-	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
-	 * NMI between STI and SYSEXIT has poorly specified behavior,
-	 * and and NMI followed by an IRQ with usergs is fatal.  So
-	 * we just pretend we're using SYSEXIT but we really use
-	 * SYSRETL instead.
-	 *
-	 * This code path is still called 'sysexit' because it pairs
-	 * with 'sysenter' and it uses the SYSENTER calling convention.
-	 */
-	andl    $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	movl	RIP(%rsp),%ecx		/* User %eip */
-	CFI_REGISTER rip,rcx
-	RESTORE_RSI_RDI
-	xorl	%edx,%edx		/* avoid info leaks */
-	xorq	%r8,%r8
-	xorq	%r9,%r9
-	xorq	%r10,%r10
-	movl	EFLAGS(%rsp),%r11d	/* User eflags */
-	/*CFI_RESTORE rflags*/
-	TRACE_IRQS_ON
-
-	/*
-	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
-	 * since it avoids a dicey window with interrupts enabled.
-	 */
-	movl	RSP(%rsp),%esp
-
-	/*
-	 * USERGS_SYSRET32 does:
-	 *  gsbase = user's gs base
-	 *  eip = ecx
-	 *  rflags = r11
-	 *  cs = __USER32_CS
-	 *  ss = __USER_DS
-	 *
-	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
-	 *
-	 *  pop %ebp
-	 *  pop %edx
-	 *  pop %ecx
-	 *
-	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
-	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
-	 * address (already known to user code), and R12-R15 are
-	 * callee-saved and therefore don't contain any interesting
-	 * kernel data.
-	 */
-	USERGS_SYSRET32
-
-	CFI_RESTORE_STATE
-
-#ifdef CONFIG_AUDITSYSCALL
-	.macro auditsys_entry_common
-	movl %esi,%r8d			/* 5th arg: 4th syscall arg */
-	movl %ecx,%r9d			/*swap with edx*/
-	movl %edx,%ecx			/* 4th arg: 3rd syscall arg */
-	movl %r9d,%edx			/* 3rd arg: 2nd syscall arg */
-	movl %ebx,%esi			/* 2nd arg: 1st syscall arg */
-	movl %eax,%edi			/* 1st arg: syscall number */
-	call __audit_syscall_entry
-	movl RAX(%rsp),%eax	/* reload syscall number */
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja ia32_badsys
-	movl %ebx,%edi			/* reload 1st syscall arg */
-	movl RCX(%rsp),%esi	/* reload 2nd syscall arg */
-	movl RDX(%rsp),%edx	/* reload 3rd syscall arg */
-	movl RSI(%rsp),%ecx	/* reload 4th syscall arg */
-	movl RDI(%rsp),%r8d	/* reload 5th syscall arg */
-	.endm
-
-	.macro auditsys_exit exit
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz ia32_ret_from_sys_call
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	movl %eax,%esi		/* second arg, syscall return value */
-	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
-	jbe 1f
-	movslq %eax, %rsi	/* if error sign extend to 64 bits */
-1:	setbe %al		/* 1 if error, 0 if not */
-	movzbl %al,%edi		/* zero-extend that into %edi */
-	call __audit_syscall_exit
-	movq RAX(%rsp),%rax	/* reload syscall return value */
-	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz \exit
-	CLEAR_RREGS
-	jmp int_with_check
-	.endm
-
-sysenter_auditsys:
-	auditsys_entry_common
-	movl %ebp,%r9d			/* reload 6th syscall arg */
-	jmp sysenter_dispatch
-
-sysexit_audit:
-	auditsys_exit sysexit_from_sys_call
-#endif
-
-sysenter_fix_flags:
-	pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
-	popfq_cfi
-	jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	sysenter_auditsys
-#endif
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS
-	movq	$-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
-	movq	%rsp,%rdi        /* &pt_regs -> arg1 */
-	call	syscall_trace_enter
-	LOAD_ARGS32  /* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	cmpq	$(IA32_NR_syscalls-1),%rax
-	ja	int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
-	jmp	sysenter_do_call
-	CFI_ENDPROC
-ENDPROC(ia32_sysenter_target)
-
-/*
- * 32bit SYSCALL instruction entry.
- *
- * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
- * then loads new ss, cs, and rip from previously programmed MSRs.
- * rflags gets masked by a value from another MSR (so CLD and CLAC
- * are not needed). SYSCALL does not save anything on the stack
- * and does not change rsp.
- *
- * Note: rflags saving+masking-with-MSR happens only in Long mode
- * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it).
- * Don't get confused: rflags saving+masking depends on Long Mode Active bit
- * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
- * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
- *
- * Arguments:
- * eax  system call number
- * ecx  return address
- * ebx  arg1
- * ebp  arg2	(note: not saved in the stack frame, should not be touched)
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * esp  user stack
- * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
- */
-ENTRY(ia32_cstar_target)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,0
-	CFI_REGISTER	rip,rcx
-	/*CFI_REGISTER	rflags,r11*/
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	SWAPGS_UNSAFE_STACK
-	movl	%esp,%r8d
-	CFI_REGISTER	rsp,r8
-	movq	PER_CPU_VAR(kernel_stack),%rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%eax,%eax
-
-	/* Construct struct pt_regs on stack */
-	pushq_cfi	$__USER32_DS		/* pt_regs->ss */
-	pushq_cfi	%r8			/* pt_regs->sp */
-	CFI_REL_OFFSET rsp,0
-	pushq_cfi	%r11			/* pt_regs->flags */
-	pushq_cfi	$__USER32_CS		/* pt_regs->cs */
-	pushq_cfi	%rcx			/* pt_regs->ip */
-	CFI_REL_OFFSET rip,0
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rbp			/* pt_regs->cx */
-	movl	%ebp,%ecx
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	/*
-	 * no need to do an access_ok check here because r8 has been
-	 * 32bit zero extended
-	 */
-	ASM_STAC
-1:	movl	(%r8),%r9d
-	_ASM_EXTABLE(1b,ia32_badarg)
-	ASM_CLAC
-	orl     $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl   $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	CFI_REMEMBER_STATE
-	jnz   cstar_tracesys
-	cmpq $IA32_NR_syscalls-1,%rax
-	ja  ia32_badsys
-cstar_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl	%edi,%r8d	/* arg5 */
-	/* r9 already loaded */	/* arg6 */
-	xchg	%ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl	%ebx,%edi	/* arg1 */
-	movl	%edx,%edx	/* arg3 (zero extension) */
-cstar_dispatch:
-	call *ia32_sys_call_table(,%rax,8)
-	movq %rax,RAX(%rsp)
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz sysretl_audit
-sysretl_from_sys_call:
-	andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	RESTORE_RSI_RDI_RDX
-	movl RIP(%rsp),%ecx
-	CFI_REGISTER rip,rcx
-	movl EFLAGS(%rsp),%r11d
-	/*CFI_REGISTER rflags,r11*/
-	xorq	%r10,%r10
-	xorq	%r9,%r9
-	xorq	%r8,%r8
-	TRACE_IRQS_ON
-	movl RSP(%rsp),%esp
-	CFI_RESTORE rsp
-	/*
-	 * 64bit->32bit SYSRET restores eip from ecx,
-	 * eflags from r11 (but RF and VM bits are forced to 0),
-	 * cs and ss are loaded from MSRs.
-	 * (Note: 32bit->32bit SYSRET is different: since r11
-	 * does not exist, it merely sets eflags.IF=1).
-	 *
-	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
-	 * descriptor is not reinitialized.  This means that we must
-	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
-	 * exit the kernel, and re-enter using an interrupt vector.  (All
-	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
-	 * from happening by reloading SS in __switch_to.
-	 */
-	USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
-	CFI_RESTORE_STATE
-	movl %r9d,R9(%rsp)	/* register to be clobbered by call */
-	auditsys_entry_common
-	movl R9(%rsp),%r9d	/* reload 6th syscall arg */
-	jmp cstar_dispatch
-
-sysretl_audit:
-	auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz cstar_auditsys
-#endif
-	xchgl %r9d,%ebp
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS r9
-	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
-	movq %rsp,%rdi        /* &pt_regs -> arg1 */
-	call syscall_trace_enter
-	LOAD_ARGS32 1	/* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	xchgl %ebp,%r9d
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
-	jmp cstar_do_call
-END(ia32_cstar_target)
-				
-ia32_badarg:
-	ASM_CLAC
-	movq $-EFAULT,%rax
-	jmp ia32_sysret
-	CFI_ENDPROC
-
-/*
- * Emulated IA32 system calls via int 0x80.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6	(note: not saved in the stack frame, should not be touched)
- *
- * Notes:
- * Uses the same stack frame as the x86-64 version.
- * All registers except eax must be saved (but ptrace may violate that).
- * Arguments are zero extended. For system calls that want sign extension and
- * take long arguments a wrapper is needed. Most calls can just be called
- * directly.
- * Assumes it is only called from user space and entered with interrupts off.
- */
-
-ENTRY(ia32_syscall)
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,5*8
-	/*CFI_REL_OFFSET	ss,4*8 */
-	CFI_REL_OFFSET	rsp,3*8
-	/*CFI_REL_OFFSET	rflags,2*8 */
-	/*CFI_REL_OFFSET	cs,1*8 */
-	CFI_REL_OFFSET	rip,0*8
-
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	SWAPGS
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%eax,%eax
-
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
-	pushq_cfi_reg	rax			/* pt_regs->orig_ax */
-	pushq_cfi_reg	rdi			/* pt_regs->di */
-	pushq_cfi_reg	rsi			/* pt_regs->si */
-	pushq_cfi_reg	rdx			/* pt_regs->dx */
-	pushq_cfi_reg	rcx			/* pt_regs->cx */
-	pushq_cfi_reg	rax			/* pt_regs->ax */
-	cld
-	sub	$(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */
-	CFI_ADJUST_CFA_OFFSET 10*8
-
-	orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz ia32_tracesys
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja ia32_badsys
-ia32_do_call:
-	/* 32bit syscall -> 64bit C ABI argument conversion */
-	movl %edi,%r8d	/* arg5 */
-	movl %ebp,%r9d	/* arg6 */
-	xchg %ecx,%esi	/* rsi:arg2, rcx:arg4 */
-	movl %ebx,%edi	/* arg1 */
-	movl %edx,%edx	/* arg3 (zero extension) */
-	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
-ia32_sysret:
-	movq %rax,RAX(%rsp)
-ia32_ret_from_sys_call:
-	CLEAR_RREGS
-	jmp int_ret_from_sys_call
-
-ia32_tracesys:
-	SAVE_EXTRA_REGS
-	CLEAR_RREGS
-	movq $-ENOSYS,RAX(%rsp)	/* ptrace can change this for a bad syscall */
-	movq %rsp,%rdi        /* &pt_regs -> arg1 */
-	call syscall_trace_enter
-	LOAD_ARGS32	/* reload args from stack in case ptrace changed it */
-	RESTORE_EXTRA_REGS
-	cmpq $(IA32_NR_syscalls-1),%rax
-	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
-	jmp ia32_do_call
-END(ia32_syscall)
-
-ia32_badsys:
-	movq $0,ORIG_RAX(%rsp)
-	movq $-ENOSYS,%rax
-	jmp ia32_sysret
-
-	CFI_ENDPROC
-	
-	.macro PTREGSCALL label, func
-	ALIGN
-GLOBAL(\label)
-	leaq \func(%rip),%rax
-	jmp  ia32_ptregs_common	
-	.endm
-
-	CFI_STARTPROC32
-
-	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
-	PTREGSCALL stub32_sigreturn, sys32_sigreturn
-	PTREGSCALL stub32_fork, sys_fork
-	PTREGSCALL stub32_vfork, sys_vfork
-
-	ALIGN
-GLOBAL(stub32_clone)
-	leaq sys_clone(%rip),%rax
-	mov	%r8, %rcx
-	jmp  ia32_ptregs_common	
-
-	ALIGN
-ia32_ptregs_common:
-	CFI_ENDPROC
-	CFI_STARTPROC32	simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,SIZEOF_PTREGS
-	CFI_REL_OFFSET	rax,RAX
-	CFI_REL_OFFSET	rcx,RCX
-	CFI_REL_OFFSET	rdx,RDX
-	CFI_REL_OFFSET	rsi,RSI
-	CFI_REL_OFFSET	rdi,RDI
-	CFI_REL_OFFSET	rip,RIP
-/*	CFI_REL_OFFSET	cs,CS*/
-/*	CFI_REL_OFFSET	rflags,EFLAGS*/
-	CFI_REL_OFFSET	rsp,RSP
-/*	CFI_REL_OFFSET	ss,SS*/
-	SAVE_EXTRA_REGS 8
-	call *%rax
-	RESTORE_EXTRA_REGS 8
-	ret
-	CFI_ENDPROC
-END(ia32_ptregs_common)
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index bdf02eeee765..e7636bac7372 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -18,6 +18,12 @@
 	.endm
 #endif
 
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
 .macro altinstruction_entry orig alt feature orig_len alt_len pad_len
 	.long \orig - .
 	.long \alt - .
@@ -27,6 +33,12 @@
 	.byte \pad_len
 .endm
 
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
 .macro ALTERNATIVE oldinstr, newinstr, feature
 140:
 	\oldinstr
@@ -55,6 +67,12 @@
  */
 #define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
 .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
 140:
 	\oldinstr
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index ba32af062f61..7bfc85bbb8ff 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -52,6 +52,12 @@ struct alt_instr {
 	u8  padlen;		/* length of build-time padding */
 } __packed;
 
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index aaac3b2fb746..1a5da2e63aee 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev)
 	return 0;
 }
 
+static inline bool amd_gart_present(void)
+{
+	/* GART present only on Fam15h, upto model 0fh */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+		return true;
+
+	return false;
+}
+
 #else
 
 #define amd_nb_num(x)		0
 #define amd_nb_has_feature(x)	false
 #define node_to_amd_nb(x)	NULL
+#define amd_gart_present(x)	false
 
 #endif
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 976b86a325e5..c8393634ca0c 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -644,6 +644,12 @@ static inline void entering_ack_irq(void)
 	entering_irq();
 }
 
+static inline void ipi_entering_ack_irq(void)
+{
+	ack_APIC_irq();
+	irq_enter();
+}
+
 static inline void exiting_irq(void)
 {
 	irq_exit();
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7730c1c5c83a..189679aba703 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -63,6 +63,31 @@
 	_ASM_ALIGN ;						\
 	_ASM_PTR (entry);					\
 	.popsection
+
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE(100b,103b)
+	_ASM_EXTABLE(101b,103b)
+	.endm
+
 #else
 # define _ASM_EXTABLE(from,to)					\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 5e5cd123fdfb..e9168955c42f 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
  *
  * Atomically reads the value of @v.
  */
-static inline int atomic_read(const atomic_t *v)
+static __always_inline int atomic_read(const atomic_t *v)
 {
 	return ACCESS_ONCE((v)->counter);
 }
@@ -34,7 +34,7 @@ static inline int atomic_read(const atomic_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void atomic_set(atomic_t *v, int i)
+static __always_inline void atomic_set(atomic_t *v, int i)
 {
 	v->counter = i;
 }
@@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic_add(int i, atomic_t *v)
+static __always_inline void atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
@@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void atomic_sub(int i, atomic_t *v)
+static __always_inline void atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
@@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
 }
@@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic_inc(atomic_t *v)
+static __always_inline void atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter));
@@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic_dec(atomic_t *v)
+static __always_inline void atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter));
@@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline int atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
@@ -126,7 +126,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline int atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
@@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline int atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
 }
@@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_return(int i, atomic_t *v)
+static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
@@ -164,7 +164,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
  *
  * Atomically subtracts @i from @v and returns @v - @i
  */
-static inline int atomic_sub_return(int i, atomic_t *v)
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
 {
 	return atomic_add_return(-i, v);
 }
@@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return cmpxchg(&v->counter, old, new);
 }
@@ -191,7 +191,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
@@ -213,7 +213,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
  * Atomically adds 1 to @v
  * Returns the new value of @u
  */
-static inline short int atomic_inc_short(short int *v)
+static __always_inline short int atomic_inc_short(short int *v)
 {
 	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
 	return *v;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index f8d273e18516..b965f9e03f2a 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i)
  *
  * Atomically adds @i to @v.
  */
-static inline void atomic64_add(long i, atomic64_t *v)
+static __always_inline void atomic64_add(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
@@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
-static inline void atomic64_inc(atomic64_t *v)
+static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
@@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
-static inline void atomic64_dec(atomic64_t *v)
+static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
@@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static __always_inline long atomic64_add_return(long i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 959e45b81fe2..e51a8f803f55 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -35,12 +35,12 @@
 #define smp_mb()	mb()
 #define smp_rmb()	dma_rmb()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
 #endif /* SMP */
 
 #define read_barrier_depends()		do { } while (0)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 47c8e32f621a..b6f7457d12e4 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -8,7 +8,7 @@
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
  * address range. The attributes include:
- * Cachability   : UnCached, WriteCombining, WriteBack
+ * Cachability   : UnCached, WriteCombining, WriteThrough, WriteBack
  * Executability : eXeutable, NoteXecutable
  * Read/Write    : ReadOnly, ReadWrite
  * Presence      : NotPresent
@@ -35,9 +35,11 @@
 
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wt(unsigned long addr, int numpages);
 int _set_memory_wb(unsigned long addr, int numpages);
 int set_memory_uc(unsigned long addr, int numpages);
 int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wt(unsigned long addr, int numpages);
 int set_memory_wb(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
@@ -48,10 +50,12 @@ int set_memory_4k(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wc(unsigned long *addr, int addrinarray);
+int set_memory_array_wt(unsigned long *addr, int addrinarray);
 int set_memory_array_wb(unsigned long *addr, int addrinarray);
 
 int set_pages_array_uc(struct page **pages, int addrinarray);
 int set_pages_array_wc(struct page **pages, int addrinarray);
+int set_pages_array_wt(struct page **pages, int addrinarray);
 int set_pages_array_wb(struct page **pages, int addrinarray);
 
 /*
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99c105d78b7e..ad19841eddfe 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
index 1eef55596e82..03bb1065c335 100644
--- a/arch/x86/include/asm/crypto/glue_helper.h
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -7,7 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/crypto.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <crypto/b128ops.h>
 
 typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 808dae63eeea..1f5b7287d1ad 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -127,50 +127,14 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
 
 #define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
 
-static inline void *
+void *
 dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *memory;
-
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
-		return memory;
-
-	if (!dev)
-		dev = &x86_dma_fallback_dev;
-
-	if (!is_device_dma_capable(dev))
-		return NULL;
-
-	if (!ops->alloc)
-		return NULL;
-
-	memory = ops->alloc(dev, size, dma_handle,
-			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
-
-	return memory;
-}
+		gfp_t gfp, struct dma_attrs *attrs);
 
 #define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
 
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t bus,
-				  struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	WARN_ON(irqs_disabled());       /* for portability */
-
-	if (dma_release_from_coherent(dev, get_order(size), vaddr))
-		return;
-
-	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free)
-		ops->free(dev, size, vaddr, bus, attrs);
-}
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *vaddr, dma_addr_t bus,
+		    struct dma_attrs *attrs);
 
 #endif
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
deleted file mode 100644
index de1cdaf4d743..000000000000
--- a/arch/x86/include/asm/dwarf2.h
+++ /dev/null
@@ -1,170 +0,0 @@
-#ifndef _ASM_X86_DWARF2_H
-#define _ASM_X86_DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
- * Macros for dwarf2 CFI unwind table entries.
- * See "as.info" for details on these pseudo ops. Unfortunately
- * they are only supported in very new binutils, so define them
- * away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC		.cfi_startproc
-#define CFI_ENDPROC		.cfi_endproc
-#define CFI_DEF_CFA		.cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
-#define CFI_OFFSET		.cfi_offset
-#define CFI_REL_OFFSET		.cfi_rel_offset
-#define CFI_REGISTER		.cfi_register
-#define CFI_RESTORE		.cfi_restore
-#define CFI_REMEMBER_STATE	.cfi_remember_state
-#define CFI_RESTORE_STATE	.cfi_restore_state
-#define CFI_UNDEFINED		.cfi_undefined
-#define CFI_ESCAPE		.cfi_escape
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME	.cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
-	/*
-	 * Emit CFI data in .debug_frame sections, not .eh_frame sections.
-	 * The latter we currently just discard since we don't do DWARF
-	 * unwinding at runtime.  So only the offline DWARF information is
-	 * useful to anyone.  Note we should not use this directive if this
-	 * file is used in the vDSO assembly, or if vmlinux.lds.S gets
-	 * changed so it doesn't discard .eh_frame.
-	 */
-	.cfi_sections .debug_frame
-#endif
-
-#else
-
-/*
- * Due to the structure of pre-exisiting code, don't use assembler line
- * comment character # to ignore the arguments. Instead, use a dummy macro.
- */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC		cfi_ignore
-#define CFI_ENDPROC		cfi_ignore
-#define CFI_DEF_CFA		cfi_ignore
-#define CFI_DEF_CFA_REGISTER	cfi_ignore
-#define CFI_DEF_CFA_OFFSET	cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
-#define CFI_OFFSET		cfi_ignore
-#define CFI_REL_OFFSET		cfi_ignore
-#define CFI_REGISTER		cfi_ignore
-#define CFI_RESTORE		cfi_ignore
-#define CFI_REMEMBER_STATE	cfi_ignore
-#define CFI_RESTORE_STATE	cfi_ignore
-#define CFI_UNDEFINED		cfi_ignore
-#define CFI_ESCAPE		cfi_ignore
-#define CFI_SIGNAL_FRAME	cfi_ignore
-
-#endif
-
-/*
- * An attempt to make CFI annotations more or less
- * correct and shorter. It is implied that you know
- * what you're doing if you use them.
- */
-#ifdef __ASSEMBLY__
-#ifdef CONFIG_X86_64
-	.macro pushq_cfi reg
-	pushq \reg
-	CFI_ADJUST_CFA_OFFSET 8
-	.endm
-
-	.macro pushq_cfi_reg reg
-	pushq %\reg
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET \reg, 0
-	.endm
-
-	.macro popq_cfi reg
-	popq \reg
-	CFI_ADJUST_CFA_OFFSET -8
-	.endm
-
-	.macro popq_cfi_reg reg
-	popq %\reg
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_RESTORE \reg
-	.endm
-
-	.macro pushfq_cfi
-	pushfq
-	CFI_ADJUST_CFA_OFFSET 8
-	.endm
-
-	.macro popfq_cfi
-	popfq
-	CFI_ADJUST_CFA_OFFSET -8
-	.endm
-
-	.macro movq_cfi reg offset=0
-	movq %\reg, \offset(%rsp)
-	CFI_REL_OFFSET \reg, \offset
-	.endm
-
-	.macro movq_cfi_restore offset reg
-	movq \offset(%rsp), %\reg
-	CFI_RESTORE \reg
-	.endm
-#else /*!CONFIG_X86_64*/
-	.macro pushl_cfi reg
-	pushl \reg
-	CFI_ADJUST_CFA_OFFSET 4
-	.endm
-
-	.macro pushl_cfi_reg reg
-	pushl %\reg
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET \reg, 0
-	.endm
-
-	.macro popl_cfi reg
-	popl \reg
-	CFI_ADJUST_CFA_OFFSET -4
-	.endm
-
-	.macro popl_cfi_reg reg
-	popl %\reg
-	CFI_ADJUST_CFA_OFFSET -4
-	CFI_RESTORE \reg
-	.endm
-
-	.macro pushfl_cfi
-	pushfl
-	CFI_ADJUST_CFA_OFFSET 4
-	.endm
-
-	.macro popfl_cfi
-	popfl
-	CFI_ADJUST_CFA_OFFSET -4
-	.endm
-
-	.macro movl_cfi reg offset=0
-	movl %\reg, \offset(%esp)
-	CFI_REL_OFFSET \reg, \offset
-	.endm
-
-	.macro movl_cfi_restore offset reg
-	movl \offset(%esp), %\reg
-	CFI_RESTORE \reg
-	.endm
-#endif /*!CONFIG_X86_64*/
-#endif /*__ASSEMBLY__*/
-
-#endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
index e9b57ecc70c5..cf8fdf83b231 100644
--- a/arch/x86/include/asm/edac.h
+++ b/arch/x86/include/asm/edac.h
@@ -3,7 +3,7 @@
 
 /* ECC atomic, DMA, SMP and interrupt safe scrub function */
 
-static inline void atomic_scrub(void *va, u32 size)
+static inline void edac_atomic_scrub(void *va, u32 size)
 {
 	u32 i, *virt_addr = va;
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3738b138b843..155162ea0e00 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/pgtable.h>
 
 /*
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index dc5fa661465f..df002992d8fd 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
 #ifdef CONFIG_HAVE_KVM
 BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
 		 smp_kvm_posted_intr_ipi)
+BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR,
+		 smp_kvm_posted_intr_wakeup_ipi)
 #endif
 
 /*
@@ -50,4 +52,7 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
 #endif
 
+#ifdef CONFIG_X86_MCE_AMD
+BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR)
+#endif
 #endif
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
deleted file mode 100644
index da5e96756570..000000000000
--- a/arch/x86/include/asm/fpu-internal.h
+++ /dev/null
@@ -1,626 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _FPU_INTERNAL_H
-#define _FPU_INTERNAL_H
-
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
-#include <linux/compat.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-#include <asm/smap.h>
-
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-struct ksignal;
-int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
-			compat_sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct ksignal *ksig,
-		     compat_sigset_t *set, struct pt_regs *regs);
-#else
-# define user_i387_ia32_struct	user_i387_struct
-# define user32_fxsr_struct	user_fxsr_struct
-# define ia32_setup_frame	__setup_frame
-# define ia32_setup_rt_frame	__setup_rt_frame
-#endif
-
-extern unsigned int mxcsr_feature_mask;
-extern void fpu_init(void);
-extern void eager_fpu_init(void);
-
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
-			      struct task_struct *tsk);
-extern void convert_to_fxsr(struct task_struct *tsk,
-			    const struct user_i387_ia32_struct *env);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
-				xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
-				 xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active	fpregs_active
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-/*
- * Must be run with preemption disabled: this clears the fpu_owner_task,
- * on this CPU.
- *
- * This will disable any lazy FPU state restore of the current FPU state,
- * but if the current thread owns the FPU, it will still be saved by.
- */
-static inline void __cpu_disable_lazy_restore(unsigned int cpu)
-{
-	per_cpu(fpu_owner_task, cpu) = NULL;
-}
-
-/*
- * Used to indicate that the FPU state in memory is newer than the FPU
- * state in registers, and the FPU state should be reloaded next time the
- * task is run. Only safe on the current task, or non-running tasks.
- */
-static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk)
-{
-	tsk->thread.fpu.last_cpu = ~0;
-}
-
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
-	return new == this_cpu_read_stable(fpu_owner_task) &&
-		cpu == new->thread.fpu.last_cpu;
-}
-
-static inline int is_ia32_compat_frame(void)
-{
-	return config_enabled(CONFIG_IA32_EMULATION) &&
-	       test_thread_flag(TIF_IA32);
-}
-
-static inline int is_ia32_frame(void)
-{
-	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
-}
-
-static inline int is_x32_frame(void)
-{
-	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
-}
-
-#define X87_FSW_ES (1 << 7)	/* Exception Summary */
-
-static __always_inline __pure bool use_eager_fpu(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
-}
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
-	return static_cpu_has_safe(X86_FEATURE_FXSR);
-}
-
-static inline void fx_finit(struct i387_fxsave_struct *fx)
-{
-	fx->cwd = 0x37f;
-	fx->mxcsr = MXCSR_DEFAULT;
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
-	if (!use_xsaveopt())
-		return;
-	__sanitize_i387_state(tsk);
-}
-
-#define user_insn(insn, output, input...)				\
-({									\
-	int err;							\
-	asm volatile(ASM_STAC "\n"					\
-		     "1:" #insn "\n\t"					\
-		     "2: " ASM_CLAC "\n"				\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
-
-#define check_insn(insn, output, input...)				\
-({									\
-	int err;							\
-	asm volatile("1:" #insn "\n\t"					\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:  movl $-1,%[err]\n"				\
-		     "    jmp  2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : [err] "=r" (err), output				\
-		     : "0"(0), input);					\
-	err;								\
-})
-
-static inline int fsave_user(struct i387_fsave_struct __user *fx)
-{
-	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
-{
-	if (config_enabled(CONFIG_X86_32))
-		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-
-	/* See comment in fpu_fxsave() below. */
-	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
-			  "m" (*fx));
-}
-
-static inline int frstor_checking(struct i387_fsave_struct *fx)
-{
-	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline int frstor_user(struct i387_fsave_struct __user *fx)
-{
-	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	if (config_enabled(CONFIG_X86_32))
-		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
-	else if (config_enabled(CONFIG_AS_FXSAVEQ))
-		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave));
-	else {
-		/* Using "rex64; fxsave %0" is broken because, if the memory
-		 * operand uses any extended registers for addressing, a second
-		 * REX prefix will be generated (to the assembler, rex64
-		 * followed by semicolon is a separate instruction), and hence
-		 * the 64-bitness is lost.
-		 *
-		 * Using "fxsaveq %0" would be the ideal choice, but is only
-		 * supported starting with gas 2.16.
-		 *
-		 * Using, as a workaround, the properly prefixed form below
-		 * isn't accepted by any binutils version so far released,
-		 * complaining that the same type of prefix is used twice if
-		 * an extended register is needed for addressing (fix submitted
-		 * to mainline 2005-11-21).
-		 *
-		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
-		 *
-		 * This, however, we can work around by forcing the compiler to
-		 * select an addressing mode that doesn't require extended
-		 * registers.
-		 */
-		asm volatile( "rex64/fxsave (%[fx])"
-			     : "=m" (fpu->state->fxsave)
-			     : [fx] "R" (&fpu->state->fxsave));
-	}
-}
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave()) {
-		fpu_xsave(fpu);
-
-		/*
-		 * xsave header may indicate the init state of the FP.
-		 */
-		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return 1;
-	} else if (use_fxsr()) {
-		fpu_fxsave(fpu);
-	} else {
-		asm volatile("fnsave %[fx]; fwait"
-			     : [fx] "=m" (fpu->state->fsave));
-		return 0;
-	}
-
-	/*
-	 * If exceptions are pending, we need to clear them so
-	 * that we don't randomly get exceptions later.
-	 *
-	 * FIXME! Is this perhaps only true for the old-style
-	 * irq13 case? Maybe we could leave the x87 state
-	 * intact otherwise?
-	 */
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
-		asm volatile("fnclex");
-		return 0;
-	}
-	return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
-	return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
-	if (use_xsave())
-		return fpu_xrstor_checking(&fpu->state->xsave);
-	else if (use_fxsr())
-		return fxrstor_checking(&fpu->state->fxsave);
-	else
-		return frstor_checking(&fpu->state->fsave);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	/*
-	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
-	 * pending. Clear the x87 state here by setting it to fixed values.
-	 * "m" is a random variable that should be in L1.
-	 */
-	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
-		asm volatile(
-			"fnclex\n\t"
-			"emms\n\t"
-			"fildl %P[addr]"	/* set F?P to defined value */
-			: : [addr] "m" (tsk->thread.fpu.has_fpu));
-	}
-
-	return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
-	return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 0;
-	this_cpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 1;
-	this_cpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
-	__thread_clear_has_fpu(tsk);
-	if (!use_eager_fpu())
-		stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		clts();
-	__thread_set_has_fpu(tsk);
-}
-
-static inline void drop_fpu(struct task_struct *tsk)
-{
-	/*
-	 * Forget coprocessor state..
-	 */
-	preempt_disable();
-	tsk->thread.fpu_counter = 0;
-
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
-	}
-
-	clear_stopped_child_used_math(tsk);
-	preempt_enable();
-}
-
-static inline void restore_init_xstate(void)
-{
-	if (use_xsave())
-		xrstor_state(init_xstate_buf, -1);
-	else
-		fxrstor_checking(&init_xstate_buf->i387);
-}
-
-/*
- * Reset the FPU state in the eager case and drop it in the lazy case (later use
- * will reinit it).
- */
-static inline void fpu_reset_state(struct task_struct *tsk)
-{
-	if (!use_eager_fpu())
-		drop_fpu(tsk);
-	else
-		restore_init_xstate();
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
- *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
-	fpu_switch_t fpu;
-
-	/*
-	 * If the task has used the math, pre-load the FPU on xsave processors
-	 * or if the past 5 consecutive context-switches used math.
-	 */
-	fpu.preload = tsk_used_math(new) &&
-		      (use_eager_fpu() || new->thread.fpu_counter > 5);
-
-	if (__thread_has_fpu(old)) {
-		if (!__save_init_fpu(old))
-			task_disable_lazy_fpu_restore(old);
-		else
-			old->thread.fpu.last_cpu = cpu;
-
-		/* But leave fpu_owner_task! */
-		old->thread.fpu.has_fpu = 0;
-
-		/* Don't change CR0.TS if we just switch! */
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			__thread_set_has_fpu(new);
-			prefetch(new->thread.fpu.state);
-		} else if (!use_eager_fpu())
-			stts();
-	} else {
-		old->thread.fpu_counter = 0;
-		task_disable_lazy_fpu_restore(old);
-		if (fpu.preload) {
-			new->thread.fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
-				fpu.preload = 0;
-			else
-				prefetch(new->thread.fpu.state);
-			__thread_fpu_begin(new);
-		}
-	}
-	return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
-	if (fpu.preload) {
-		if (unlikely(restore_fpu_checking(new)))
-			fpu_reset_state(new);
-	}
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
-extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-
-static inline int xstate_sigframe_size(void)
-{
-	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
-}
-
-static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
-{
-	void __user *buf_fx = buf;
-	int size = xstate_sigframe_size();
-
-	if (ia32_frame && use_fxsr()) {
-		buf_fx = buf + sizeof(struct i387_fsave_struct);
-		size += sizeof(struct i387_fsave_struct);
-	}
-
-	return __restore_xstate_sig(buf, buf_fx, size);
-}
-
-/*
- * Needs to be preemption-safe.
- *
- * NOTE! user_fpu_begin() must be used only immediately before restoring
- * the save state. It does not do any saving/restoring on its own. In
- * lazy FPU mode, it is just an optimization to avoid a #NM exception,
- * the task can lose the FPU right after preempt_enable().
- */
-static inline void user_fpu_begin(void)
-{
-	preempt_disable();
-	if (!user_has_fpu())
-		__thread_fpu_begin(current);
-	preempt_enable();
-}
-
-static inline void __save_fpu(struct task_struct *tsk)
-{
-	if (use_xsave()) {
-		if (unlikely(system_state == SYSTEM_BOOTING))
-			xsave_state_booting(&tsk->thread.fpu.state->xsave, -1);
-		else
-			xsave_state(&tsk->thread.fpu.state->xsave, -1);
-	} else
-		fpu_fxsave(&tsk->thread.fpu);
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.cwd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.swd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
-	if (cpu_has_xmm) {
-		return tsk->thread.fpu.state->fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
-	return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
-	if (fpu_allocated(fpu))
-		return 0;
-	fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
-	if (!fpu->state)
-		return -ENOMEM;
-	WARN_ON((unsigned long)fpu->state & 15);
-	return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
-	if (fpu->state) {
-		kmem_cache_free(task_xstate_cachep, fpu->state);
-		fpu->state = NULL;
-	}
-}
-
-static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
-{
-	if (use_eager_fpu()) {
-		memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
-		__save_fpu(dst);
-	} else {
-		struct fpu *dfpu = &dst->thread.fpu;
-		struct fpu *sfpu = &src->thread.fpu;
-
-		unlazy_fpu(src);
-		memcpy(dfpu->state, sfpu->state, xstate_size);
-	}
-}
-
-static inline unsigned long
-alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
-		unsigned long *size)
-{
-	unsigned long frame_size = xstate_sigframe_size();
-
-	*buf_fx = sp = round_down(sp - frame_size, 64);
-	if (ia32_frame && use_fxsr()) {
-		frame_size += sizeof(struct i387_fsave_struct);
-		sp -= sizeof(struct i387_fsave_struct);
-	}
-
-	*size = frame_size;
-	return sp;
-}
-
-#endif
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
new file mode 100644
index 000000000000..1429a7c736db
--- /dev/null
+++ b/arch/x86/include/asm/fpu/api.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_API_H
+#define _ASM_X86_FPU_API_H
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
+extern bool irq_fpu_usable(void);
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context as well. To prevent these kernel instructions
+ * in interrupt context interacting wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+extern int  irq_ts_save(void);
+extern void irq_ts_restore(int TS_state);
+
+/*
+ * Query the presence of one or more xfeatures. Works on any legacy CPU as well.
+ *
+ * If 'feature_name' is set then put a human-readable description of
+ * the feature there as well - this can be used to print error (or success)
+ * messages.
+ */
+extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+
+#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
new file mode 100644
index 000000000000..3c3550c3a4a3
--- /dev/null
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -0,0 +1,694 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _ASM_X86_FPU_INTERNAL_H
+#define _ASM_X86_FPU_INTERNAL_H
+
+#include <linux/compat.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/user.h>
+#include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
+
+/*
+ * High level FPU state handling functions:
+ */
+extern void fpu__activate_curr(struct fpu *fpu);
+extern void fpu__activate_fpstate_read(struct fpu *fpu);
+extern void fpu__activate_fpstate_write(struct fpu *fpu);
+extern void fpu__save(struct fpu *fpu);
+extern void fpu__restore(struct fpu *fpu);
+extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
+extern void fpu__drop(struct fpu *fpu);
+extern int  fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu);
+extern void fpu__clear(struct fpu *fpu);
+extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
+extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
+
+/*
+ * Boot time FPU initialization functions:
+ */
+extern void fpu__init_cpu(void);
+extern void fpu__init_system_xstate(void);
+extern void fpu__init_cpu_xstate(void);
+extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_check_bugs(void);
+extern void fpu__resume_cpu(void);
+
+/*
+ * Debugging facility:
+ */
+#ifdef CONFIG_X86_DEBUG_FPU
+# define WARN_ON_FPU(x) WARN_ON_ONCE(x)
+#else
+# define WARN_ON_FPU(x) ({ (void)(x); 0; })
+#endif
+
+/*
+ * FPU related CPU feature flag helper routines:
+ */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+	return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+/*
+ * fpstate handling functions:
+ */
+
+extern union fpregs_state init_fpstate;
+
+extern void fpstate_init(union fpregs_state *state);
+#ifdef CONFIG_MATH_EMULATION
+extern void fpstate_init_soft(struct swregs_state *soft);
+#else
+static inline void fpstate_init_soft(struct swregs_state *soft) {}
+#endif
+static inline void fpstate_init_fxstate(struct fxregs_state *fx)
+{
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+extern void fpstate_sanitize_xstate(struct fpu *fpu);
+
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:" #insn "\n\t"					\
+		     "2: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+#define check_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+static inline int copy_fregs_to_user(struct fregs_state __user *fx)
+{
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int copy_fxregs_to_user(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
+{
+	int err;
+
+	if (config_enabled(CONFIG_X86_32)) {
+		err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	} else {
+		if (config_enabled(CONFIG_AS_FXSAVEQ)) {
+			err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+		} else {
+			/* See comment in copy_fxregs_to_kernel() below. */
+			err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+		}
+	}
+	/* Copying from a kernel buffer to FPU registers should never fail: */
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
+{
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	/* See comment in copy_fxregs_to_kernel() below. */
+	return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
+}
+
+static inline void copy_kernel_to_fregs(struct fregs_state *fx)
+{
+	int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+	WARN_ON_FPU(err);
+}
+
+static inline int copy_user_to_fregs(struct fregs_state __user *fx)
+{
+	return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void copy_fxregs_to_kernel(struct fpu *fpu)
+{
+	if (config_enabled(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave));
+	else {
+		/* Using "rex64; fxsave %0" is broken because, if the memory
+		 * operand uses any extended registers for addressing, a second
+		 * REX prefix will be generated (to the assembler, rex64
+		 * followed by semicolon is a separate instruction), and hence
+		 * the 64-bitness is lost.
+		 *
+		 * Using "fxsaveq %0" would be the ideal choice, but is only
+		 * supported starting with gas 2.16.
+		 *
+		 * Using, as a workaround, the properly prefixed form below
+		 * isn't accepted by any binutils version so far released,
+		 * complaining that the same type of prefix is used twice if
+		 * an extended register is needed for addressing (fix submitted
+		 * to mainline 2005-11-21).
+		 *
+		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave));
+		 *
+		 * This, however, we can work around by forcing the compiler to
+		 * select an addressing mode that doesn't require extended
+		 * registers.
+		 */
+		asm volatile( "rex64/fxsave (%[fx])"
+			     : "=m" (fpu->state.fxsave)
+			     : [fx] "R" (&fpu->state.fxsave));
+	}
+}
+
+/* These macros all use (%edi)/(%rdi) as the single memory argument. */
+#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
+#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
+#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
+#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
+#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
+
+/* xstate instruction fault handler: */
+#define xstate_fault(__err)		\
+					\
+	".section .fixup,\"ax\"\n"	\
+					\
+	"3:  movl $-2,%[_err]\n"	\
+	"    jmp  2b\n"			\
+					\
+	".previous\n"			\
+					\
+	_ASM_EXTABLE(1b, 3b)		\
+	: [_err] "=r" (__err)
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XSAVES"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XSAVE"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * This function is called only during boot time when x86 caps are not set
+ * up and alternative can not be used yet.
+ */
+static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(system_state != SYSTEM_BOOTING);
+
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
+		asm volatile("1:"XRSTORS"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+	else
+		asm volatile("1:"XRSTOR"\n\t"
+			"2:\n\t"
+			     xstate_fault(err)
+			: "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err)
+			: "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save processor xstate to xsave area.
+ */
+static inline void copy_xregs_to_kernel(struct xregs_state *xstate)
+{
+	u64 mask = -1;
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	WARN_ON(!alternatives_patched);
+
+	/*
+	 * If xsaves is enabled, xsaves replaces xsaveopt because
+	 * it supports compact format and supervisor states in addition to
+	 * modified optimization in xsaveopt.
+	 *
+	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
+	 * because xsaveopt supports modified optimization which is not
+	 * supported by xsave.
+	 *
+	 * If none of xsaves and xsaveopt is enabled, use xsave.
+	 */
+	alternative_input_2(
+		"1:"XSAVE,
+		XSAVEOPT,
+		X86_FEATURE_XSAVEOPT,
+		XSAVES,
+		X86_FEATURE_XSAVES,
+		[xstate] "D" (xstate), "a" (lmask), "d" (hmask) :
+		"memory");
+	asm volatile("2:\n\t"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying to a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Restore processor xstate from xsave area.
+ */
+static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	/*
+	 * Use xrstors to restore context if it is enabled. xrstors supports
+	 * compacted format of xsave area which is not supported by xrstor.
+	 */
+	alternative_input(
+		"1: " XRSTOR,
+		XRSTORS,
+		X86_FEATURE_XSAVES,
+		"D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask)
+		: "memory");
+
+	asm volatile("2:\n"
+		     xstate_fault(err)
+		     : "0" (err)
+		     : "memory");
+
+	/* We should never fault when copying from a kernel buffer: */
+	WARN_ON_FPU(err);
+}
+
+/*
+ * Save xstate to user space xsave area.
+ *
+ * We don't use modified optimization because xrstor/xrstors might track
+ * a different application.
+ *
+ * We don't use compacted format xsave area for
+ * backward compatibility for old applications which don't understand
+ * compacted format of xsave area.
+ */
+static inline int copy_xregs_to_user(struct xregs_state __user *buf)
+{
+	int err;
+
+	/*
+	 * Clear the xsave header first, so that reserved fields are
+	 * initialized to zero.
+	 */
+	err = __clear_user(&buf->header, sizeof(buf->header));
+	if (unlikely(err))
+		return -EFAULT;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XSAVE"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (buf), "a" (-1), "d" (-1), "0" (err)
+			     : "memory");
+	return err;
+}
+
+/*
+ * Restore xstate from user space xsave area.
+ */
+static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask)
+{
+	struct xregs_state *xstate = ((__force struct xregs_state *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+	int err = 0;
+
+	__asm__ __volatile__(ASM_STAC "\n"
+			     "1:"XRSTOR"\n"
+			     "2: " ASM_CLAC "\n"
+			     xstate_fault(err)
+			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err)
+			     : "memory");	/* memory required? */
+	return err;
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+static inline int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+
+static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	if (use_xsave()) {
+		copy_kernel_to_xregs(&fpstate->xsave, -1);
+	} else {
+		if (use_fxsr())
+			copy_kernel_to_fxregs(&fpstate->fxsave);
+		else
+			copy_kernel_to_fregs(&fpstate->fsave);
+	}
+}
+
+static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate)
+{
+	/*
+	 * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is
+	 * pending. Clear the x87 state here by setting it to fixed values.
+	 * "m" is a random variable that should be in L1.
+	 */
+	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (fpstate));
+	}
+
+	__copy_kernel_to_fpregs(fpstate);
+}
+
+extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+
+/*
+ * FPU context switch related helper methods:
+ */
+
+DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
+}
+
+static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu)
+{
+	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+}
+
+
+/*
+ * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation'
+ * idiom, which is then paired with the sw-flag (fpregs_active) later on:
+ */
+
+static inline void __fpregs_activate_hw(void)
+{
+	if (!use_eager_fpu())
+		clts();
+}
+
+static inline void __fpregs_deactivate_hw(void)
+{
+	if (!use_eager_fpu())
+		stts();
+}
+
+/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */
+static inline void __fpregs_deactivate(struct fpu *fpu)
+{
+	WARN_ON_FPU(!fpu->fpregs_active);
+
+	fpu->fpregs_active = 0;
+	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+}
+
+/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
+static inline void __fpregs_activate(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu->fpregs_active);
+
+	fpu->fpregs_active = 1;
+	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+}
+
+/*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ */
+static inline int fpregs_active(void)
+{
+	return current->thread.fpu.fpregs_active;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void fpregs_activate(struct fpu *fpu)
+{
+	__fpregs_activate_hw();
+	__fpregs_activate(fpu);
+}
+
+static inline void fpregs_deactivate(struct fpu *fpu)
+{
+	__fpregs_deactivate(fpu);
+	__fpregs_deactivate_hw();
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+static inline fpu_switch_t
+switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
+{
+	fpu_switch_t fpu;
+
+	/*
+	 * If the task has used the math, pre-load the FPU on xsave processors
+	 * or if the past 5 consecutive context-switches used math.
+	 */
+	fpu.preload = new_fpu->fpstate_active &&
+		      (use_eager_fpu() || new_fpu->counter > 5);
+
+	if (old_fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(old_fpu))
+			old_fpu->last_cpu = -1;
+		else
+			old_fpu->last_cpu = cpu;
+
+		/* But leave fpu_fpregs_owner_ctx! */
+		old_fpu->fpregs_active = 0;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			new_fpu->counter++;
+			__fpregs_activate(new_fpu);
+			prefetch(&new_fpu->state);
+		} else {
+			__fpregs_deactivate_hw();
+		}
+	} else {
+		old_fpu->counter = 0;
+		old_fpu->last_cpu = -1;
+		if (fpu.preload) {
+			new_fpu->counter++;
+			if (fpu_want_lazy_restore(new_fpu, cpu))
+				fpu.preload = 0;
+			else
+				prefetch(&new_fpu->state);
+			fpregs_activate(new_fpu);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * Misc helper functions:
+ */
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch)
+{
+	if (fpu_switch.preload)
+		copy_kernel_to_fpregs(&new_fpu->state);
+}
+
+/*
+ * Needs to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * the save state. It does not do any saving/restoring on its own. In
+ * lazy FPU mode, it is just an optimization to avoid a #NM exception,
+ * the task can lose the FPU right after preempt_enable().
+ */
+static inline void user_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	preempt_disable();
+	if (!fpregs_active())
+		fpregs_activate(fpu);
+	preempt_enable();
+}
+
+/*
+ * MXCSR and XCR definitions:
+ */
+
+extern unsigned int mxcsr_feature_mask;
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+		     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+#endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h
new file mode 100644
index 000000000000..39d3107ac6c7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/regset.h
@@ -0,0 +1,21 @@
+/*
+ * FPU regset handling methods:
+ */
+#ifndef _ASM_X86_FPU_REGSET_H
+#define _ASM_X86_FPU_REGSET_H
+
+#include <linux/regset.h>
+
+extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+				xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+				 xstateregs_set;
+
+/*
+ * xstateregs_active == regset_fpregs_active. Please refer to the comment
+ * at the definition of regset_fpregs_active.
+ */
+#define xstateregs_active	regset_fpregs_active
+
+#endif /* _ASM_X86_FPU_REGSET_H */
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
new file mode 100644
index 000000000000..7358e9d61f1e
--- /dev/null
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -0,0 +1,33 @@
+/*
+ * x86 FPU signal frame handling methods:
+ */
+#ifndef _ASM_X86_FPU_SIGNAL_H
+#define _ASM_X86_FPU_SIGNAL_H
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+			compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+		     compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct	user_i387_struct
+# define user32_fxsr_struct	user_fxsr_struct
+# define ia32_setup_frame	__setup_frame
+# define ia32_setup_rt_frame	__setup_rt_frame
+#endif
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+			      struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+			    const struct user_i387_ia32_struct *env);
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+		     unsigned long *buf_fx, unsigned long *size);
+
+extern void fpu__init_prepare_fx_sw_frame(void);
+
+#endif /* _ASM_X86_FPU_SIGNAL_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
new file mode 100644
index 000000000000..0637826292de
--- /dev/null
+++ b/arch/x86/include/asm/fpu/types.h
@@ -0,0 +1,293 @@
+/*
+ * FPU data structures:
+ */
+#ifndef _ASM_X86_FPU_H
+#define _ASM_X86_FPU_H
+
+/*
+ * The legacy x87 FPU state format, as saved by FSAVE and
+ * restored by the FRSTOR instructions:
+ */
+struct fregs_state {
+	u32			cwd;	/* FPU Control Word		*/
+	u32			swd;	/* FPU Status Word		*/
+	u32			twd;	/* FPU Tag Word			*/
+	u32			fip;	/* FPU IP Offset		*/
+	u32			fcs;	/* FPU IP Selector		*/
+	u32			foo;	/* FPU Operand Pointer Offset	*/
+	u32			fos;	/* FPU Operand Pointer Selector	*/
+
+	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
+	u32			st_space[20];
+
+	/* Software status information [not touched by FSAVE]:		*/
+	u32			status;
+};
+
+/*
+ * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and
+ * restored by the FXRSTOR instructions. It's similar to the FSAVE
+ * format, but differs in some areas, plus has extensions at
+ * the end for the XMM registers.
+ */
+struct fxregs_state {
+	u16			cwd; /* Control Word			*/
+	u16			swd; /* Status Word			*/
+	u16			twd; /* Tag Word			*/
+	u16			fop; /* Last Instruction Opcode		*/
+	union {
+		struct {
+			u64	rip; /* Instruction Pointer		*/
+			u64	rdp; /* Data Pointer			*/
+		};
+		struct {
+			u32	fip; /* FPU IP Offset			*/
+			u32	fcs; /* FPU IP Selector			*/
+			u32	foo; /* FPU Operand Offset		*/
+			u32	fos; /* FPU Operand Selector		*/
+		};
+	};
+	u32			mxcsr;		/* MXCSR Register State */
+	u32			mxcsr_mask;	/* MXCSR Mask		*/
+
+	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
+	u32			st_space[32];
+
+	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
+	u32			xmm_space[64];
+
+	u32			padding[12];
+
+	union {
+		u32		padding1[12];
+		u32		sw_reserved[12];
+	};
+
+} __attribute__((aligned(16)));
+
+/* Default value for fxregs_state.mxcsr: */
+#define MXCSR_DEFAULT		0x1f80
+
+/*
+ * Software based FPU emulation state. This is arbitrary really,
+ * it matches the x87 format to make it easier to understand:
+ */
+struct swregs_state {
+	u32			cwd;
+	u32			swd;
+	u32			twd;
+	u32			fip;
+	u32			fcs;
+	u32			foo;
+	u32			fos;
+	/* 8*10 bytes for each FP-reg = 80 bytes: */
+	u32			st_space[20];
+	u8			ftop;
+	u8			changed;
+	u8			lookahead;
+	u8			no_update;
+	u8			rm;
+	u8			alimit;
+	struct math_emu_info	*info;
+	u32			entry_eip;
+};
+
+/*
+ * List of XSAVE features Linux knows about:
+ */
+enum xfeature_bit {
+	XSTATE_BIT_FP,
+	XSTATE_BIT_SSE,
+	XSTATE_BIT_YMM,
+	XSTATE_BIT_BNDREGS,
+	XSTATE_BIT_BNDCSR,
+	XSTATE_BIT_OPMASK,
+	XSTATE_BIT_ZMM_Hi256,
+	XSTATE_BIT_Hi16_ZMM,
+
+	XFEATURES_NR_MAX,
+};
+
+#define XSTATE_FP		(1 << XSTATE_BIT_FP)
+#define XSTATE_SSE		(1 << XSTATE_BIT_SSE)
+#define XSTATE_YMM		(1 << XSTATE_BIT_YMM)
+#define XSTATE_BNDREGS		(1 << XSTATE_BIT_BNDREGS)
+#define XSTATE_BNDCSR		(1 << XSTATE_BIT_BNDCSR)
+#define XSTATE_OPMASK		(1 << XSTATE_BIT_OPMASK)
+#define XSTATE_ZMM_Hi256	(1 << XSTATE_BIT_ZMM_Hi256)
+#define XSTATE_Hi16_ZMM		(1 << XSTATE_BIT_Hi16_ZMM)
+
+#define XSTATE_FPSSE		(XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512		(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/*
+ * There are 16x 256-bit AVX registers named YMM0-YMM15.
+ * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
+ * and are stored in 'struct fxregs_state::xmm_space[]'.
+ *
+ * The high 128 bits are stored here:
+ *    16x 128 bits == 256 bytes.
+ */
+struct ymmh_struct {
+	u8				ymmh_space[256];
+};
+
+/* We don't support LWP yet: */
+struct lwp_struct {
+	u8				reserved[128];
+};
+
+/* Intel MPX support: */
+struct bndreg {
+	u64				lower_bound;
+	u64				upper_bound;
+} __packed;
+
+struct bndcsr {
+	u64				bndcfgu;
+	u64				bndstatus;
+} __packed;
+
+struct mpx_struct {
+	struct bndreg			bndreg[4];
+	struct bndcsr			bndcsr;
+};
+
+struct xstate_header {
+	u64				xfeatures;
+	u64				xcomp_bv;
+	u64				reserved[6];
+} __attribute__((packed));
+
+/* New processor state extensions should be added here: */
+#define XSTATE_RESERVE			(sizeof(struct ymmh_struct) + \
+					 sizeof(struct lwp_struct)  + \
+					 sizeof(struct mpx_struct)  )
+/*
+ * This is our most modern FPU state format, as saved by the XSAVE
+ * and restored by the XRSTOR instructions.
+ *
+ * It consists of a legacy fxregs portion, an xstate header and
+ * subsequent fixed size areas as defined by the xstate header.
+ * Not all CPUs support all the extensions.
+ */
+struct xregs_state {
+	struct fxregs_state		i387;
+	struct xstate_header		header;
+	u8				__reserved[XSTATE_RESERVE];
+} __attribute__ ((packed, aligned (64)));
+
+/*
+ * This is a union of all the possible FPU state formats
+ * put together, so that we can pick the right one runtime.
+ *
+ * The size of the structure is determined by the largest
+ * member - which is the xsave area:
+ */
+union fpregs_state {
+	struct fregs_state		fsave;
+	struct fxregs_state		fxsave;
+	struct swregs_state		soft;
+	struct xregs_state		xsave;
+};
+
+/*
+ * Highest level per task FPU state data structure that
+ * contains the FPU register state plus various FPU
+ * state fields:
+ */
+struct fpu {
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 *
+	 * After context switches there may be a (short) time period
+	 * during which the in-FPU hardware registers are unchanged
+	 * and still perfectly match this state, if the tasks
+	 * scheduled afterwards are not using the FPU.
+	 *
+	 * This is the 'lazy restore' window of optimization, which
+	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+	 *
+	 * We detect whether a subsequent task uses the FPU via setting
+	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+	 *
+	 * During this window, if the task gets scheduled again, we
+	 * might be able to skip having to do a restore from this
+	 * memory buffer to the hardware registers - at the cost of
+	 * incurring the overhead of #NM fault traps.
+	 *
+	 * Note that on modern CPUs that support the XSAVEOPT (or other
+	 * optimized XSAVE instructions), we don't use #NM traps anymore,
+	 * as the hardware can track whether FPU registers need saving
+	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+	 * logic, which unconditionally saves/restores all FPU state
+	 * across context switches. (if FPU state exists.)
+	 */
+	union fpregs_state		state;
+
+	/*
+	 * @last_cpu:
+	 *
+	 * Records the last CPU on which this context was loaded into
+	 * FPU registers. (In the lazy-restore case we might be
+	 * able to reuse FPU registers across multiple context switches
+	 * this way, if no intermediate task used the FPU.)
+	 *
+	 * A value of -1 is used to indicate that the FPU state in context
+	 * memory is newer than the FPU state in registers, and that the
+	 * FPU state should be reloaded next time the task is run.
+	 */
+	unsigned int			last_cpu;
+
+	/*
+	 * @fpstate_active:
+	 *
+	 * This flag indicates whether this context is active: if the task
+	 * is not running then we can restore from this context, if the task
+	 * is running then we should save into this context.
+	 */
+	unsigned char			fpstate_active;
+
+	/*
+	 * @fpregs_active:
+	 *
+	 * This flag determines whether a given context is actively
+	 * loaded into the FPU's registers and that those registers
+	 * represent the task's current FPU state.
+	 *
+	 * Note the interaction with fpstate_active:
+	 *
+	 *   # task does not use the FPU:
+	 *   fpstate_active == 0
+	 *
+	 *   # task uses the FPU and regs are active:
+	 *   fpstate_active == 1 && fpregs_active == 1
+	 *
+	 *   # the regs are inactive but still match fpstate:
+	 *   fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
+	 *
+	 * The third state is what we use for the lazy restore optimization
+	 * on lazy-switching CPUs.
+	 */
+	unsigned char			fpregs_active;
+
+	/*
+	 * @counter:
+	 *
+	 * This counter contains the number of consecutive context switches
+	 * during which the FPU stays used. If this is over a threshold, the
+	 * lazy FPU restore logic becomes eager, to save the trap overhead.
+	 * This is an unsigned char so that after 256 iterations the counter
+	 * wraps and the context switch behavior turns lazy again; this is to
+	 * deal with bursty apps that only use the FPU for a short time:
+	 */
+	unsigned char			counter;
+};
+
+#endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
new file mode 100644
index 000000000000..4656b25bb9a7
--- /dev/null
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -0,0 +1,46 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+
+/* Bit 63 of XCR0 is reserved for future expansion */
+#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
+
+#define XSTATE_CPUID		0x0000000d
+
+#define FXSAVE_SIZE	512
+
+#define XSAVE_HDR_SIZE	    64
+#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE	    256
+#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
+/* Supported features which support lazy state saving */
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+
+/* Supported features which require eager state saving */
+#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
+
+/* All currently supported features */
+#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 xfeatures_mask;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+
+void *get_xsave_addr(struct xregs_state *xsave, int xstate);
+const void *get_xsave_field_ptr(int xstate_field);
+
+#endif
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 3b629f47eb65..793179cf8e21 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,20 +1,17 @@
 #ifdef __ASSEMBLY__
 
 #include <asm/asm.h>
-#include <asm/dwarf2.h>
 
 /* The annotation hides the frame from the unwinder and makes it look
    like a ordinary ebp save/restore. This avoids some special cases for
    frame pointer later */
 #ifdef CONFIG_FRAME_POINTER
 	.macro FRAME
-	__ASM_SIZE(push,_cfi)	%__ASM_REG(bp)
-	CFI_REL_OFFSET		__ASM_REG(bp), 0
+	__ASM_SIZE(push,)	%__ASM_REG(bp)
 	__ASM_SIZE(mov)		%__ASM_REG(sp), %__ASM_REG(bp)
 	.endm
 	.macro ENDFRAME
-	__ASM_SIZE(pop,_cfi)	%__ASM_REG(bp)
-	CFI_RESTORE		__ASM_REG(bp)
+	__ASM_SIZE(pop,)	%__ASM_REG(bp)
 	.endm
 #else
 	.macro FRAME
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f5fb6b6567e..7178043b0e1d 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -14,6 +14,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_HAVE_KVM
 	unsigned int kvm_posted_intr_ipis;
+	unsigned int kvm_posted_intr_wakeup_ipis;
 #endif
 	unsigned int x86_platform_ipis;	/* arch dependent */
 	unsigned int apic_perf_irqs;
@@ -33,6 +34,9 @@ typedef struct {
 #ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
 #endif
+#ifdef CONFIG_X86_MCE_AMD
+	unsigned int irq_deferred_error_count;
+#endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	unsigned int irq_hv_callback_count;
 #endif
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 36f7125945e3..5fa9fb0f8809 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,20 +74,16 @@ extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
 struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
 extern void hpet_msi_unmask(struct irq_data *data);
 extern void hpet_msi_mask(struct irq_data *data);
-struct hpet_dev;
 extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
 extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
-#else
-static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
-	return -EINVAL;
-}
-#endif
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+			   struct hpet_dev *dev, int dev_num);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
 
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 68c05398bba9..dab7a3a750bf 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
-}
-
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
 					  unsigned long floor,
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e9571ddabc4f..6615032e19c8 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -29,6 +29,7 @@
 extern asmlinkage void apic_timer_interrupt(void);
 extern asmlinkage void x86_platform_ipi(void);
 extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void kvm_posted_intr_wakeup_ipi(void);
 extern asmlinkage void error_interrupt(void);
 extern asmlinkage void irq_work_interrupt(void);
 
@@ -36,43 +37,10 @@ extern asmlinkage void spurious_interrupt(void);
 extern asmlinkage void thermal_interrupt(void);
 extern asmlinkage void reschedule_interrupt(void);
 
-extern asmlinkage void invalidate_interrupt(void);
-extern asmlinkage void invalidate_interrupt0(void);
-extern asmlinkage void invalidate_interrupt1(void);
-extern asmlinkage void invalidate_interrupt2(void);
-extern asmlinkage void invalidate_interrupt3(void);
-extern asmlinkage void invalidate_interrupt4(void);
-extern asmlinkage void invalidate_interrupt5(void);
-extern asmlinkage void invalidate_interrupt6(void);
-extern asmlinkage void invalidate_interrupt7(void);
-extern asmlinkage void invalidate_interrupt8(void);
-extern asmlinkage void invalidate_interrupt9(void);
-extern asmlinkage void invalidate_interrupt10(void);
-extern asmlinkage void invalidate_interrupt11(void);
-extern asmlinkage void invalidate_interrupt12(void);
-extern asmlinkage void invalidate_interrupt13(void);
-extern asmlinkage void invalidate_interrupt14(void);
-extern asmlinkage void invalidate_interrupt15(void);
-extern asmlinkage void invalidate_interrupt16(void);
-extern asmlinkage void invalidate_interrupt17(void);
-extern asmlinkage void invalidate_interrupt18(void);
-extern asmlinkage void invalidate_interrupt19(void);
-extern asmlinkage void invalidate_interrupt20(void);
-extern asmlinkage void invalidate_interrupt21(void);
-extern asmlinkage void invalidate_interrupt22(void);
-extern asmlinkage void invalidate_interrupt23(void);
-extern asmlinkage void invalidate_interrupt24(void);
-extern asmlinkage void invalidate_interrupt25(void);
-extern asmlinkage void invalidate_interrupt26(void);
-extern asmlinkage void invalidate_interrupt27(void);
-extern asmlinkage void invalidate_interrupt28(void);
-extern asmlinkage void invalidate_interrupt29(void);
-extern asmlinkage void invalidate_interrupt30(void);
-extern asmlinkage void invalidate_interrupt31(void);
-
 extern asmlinkage void irq_move_cleanup_interrupt(void);
 extern asmlinkage void reboot_interrupt(void);
 extern asmlinkage void threshold_interrupt(void);
+extern asmlinkage void deferred_error_interrupt(void);
 
 extern asmlinkage void call_function_interrupt(void);
 extern asmlinkage void call_function_single_interrupt(void);
@@ -87,60 +55,93 @@ extern void trace_spurious_interrupt(void);
 extern void trace_thermal_interrupt(void);
 extern void trace_reschedule_interrupt(void);
 extern void trace_threshold_interrupt(void);
+extern void trace_deferred_error_interrupt(void);
 extern void trace_call_function_interrupt(void);
 extern void trace_call_function_single_interrupt(void);
 #define trace_irq_move_cleanup_interrupt  irq_move_cleanup_interrupt
 #define trace_reboot_interrupt  reboot_interrupt
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi
 #endif /* CONFIG_TRACING */
 
-#ifdef CONFIG_IRQ_REMAP
-/* Intel specific interrupt remapping information */
-struct irq_2_iommu {
-	struct intel_iommu *iommu;
-	u16 irte_index;
-	u16 sub_handle;
-	u8  irte_mask;
-};
-
-/* AMD specific interrupt remapping information */
-struct irq_2_irte {
-	u16 devid; /* Device ID for IRTE table */
-	u16 index; /* Index into IRTE table*/
-};
-#endif	/* CONFIG_IRQ_REMAP */
-
 #ifdef	CONFIG_X86_LOCAL_APIC
 struct irq_data;
+struct pci_dev;
+struct msi_desc;
+
+enum irq_alloc_type {
+	X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+	X86_IRQ_ALLOC_TYPE_HPET,
+	X86_IRQ_ALLOC_TYPE_MSI,
+	X86_IRQ_ALLOC_TYPE_MSIX,
+	X86_IRQ_ALLOC_TYPE_DMAR,
+	X86_IRQ_ALLOC_TYPE_UV,
+};
 
-struct irq_cfg {
-	cpumask_var_t		domain;
-	cpumask_var_t		old_domain;
-	u8			vector;
-	u8			move_in_progress : 1;
-#ifdef CONFIG_IRQ_REMAP
-	u8			remapped : 1;
+struct irq_alloc_info {
+	enum irq_alloc_type	type;
+	u32			flags;
+	const struct cpumask	*mask;	/* CPU mask for vector allocation */
 	union {
-		struct irq_2_iommu irq_2_iommu;
-		struct irq_2_irte  irq_2_irte;
-	};
+		int		unused;
+#ifdef	CONFIG_HPET_TIMER
+		struct {
+			int		hpet_id;
+			int		hpet_index;
+			void		*hpet_data;
+		};
 #endif
-	union {
-#ifdef CONFIG_X86_IO_APIC
+#ifdef	CONFIG_PCI_MSI
 		struct {
-			struct list_head	irq_2_pin;
+			struct pci_dev	*msi_dev;
+			irq_hw_number_t	msi_hwirq;
+		};
+#endif
+#ifdef	CONFIG_X86_IO_APIC
+		struct {
+			int		ioapic_id;
+			int		ioapic_pin;
+			int		ioapic_node;
+			u32		ioapic_trigger : 1;
+			u32		ioapic_polarity : 1;
+			u32		ioapic_valid : 1;
+			struct IO_APIC_route_entry *ioapic_entry;
+		};
+#endif
+#ifdef	CONFIG_DMAR_TABLE
+		struct {
+			int		dmar_id;
+			void		*dmar_data;
+		};
+#endif
+#ifdef	CONFIG_HT_IRQ
+		struct {
+			int		ht_pos;
+			int		ht_idx;
+			struct pci_dev	*ht_dev;
+			void		*ht_update;
+		};
+#endif
+#ifdef	CONFIG_X86_UV
+		struct {
+			int		uv_limit;
+			int		uv_blade;
+			unsigned long	uv_offset;
+			char		*uv_name;
 		};
 #endif
 	};
 };
 
+struct irq_cfg {
+	unsigned int		dest_apicid;
+	u8			vector;
+};
+
 extern struct irq_cfg *irq_cfg(unsigned int irq);
 extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
 extern void lock_vector_lock(void);
 extern void unlock_vector_lock(void);
-extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
-extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
 extern void setup_vector_irq(int cpu);
 #ifdef CONFIG_SMP
 extern void send_cleanup_vector(struct irq_cfg *);
@@ -150,10 +151,7 @@ static inline void send_cleanup_vector(struct irq_cfg *c) { }
 static inline void irq_complete_move(struct irq_cfg *c) { }
 #endif
 
-extern int apic_retrigger_irq(struct irq_data *data);
 extern void apic_ack_edge(struct irq_data *data);
-extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-			     unsigned int *dest_id);
 #else	/*  CONFIG_X86_LOCAL_APIC */
 static inline void lock_vector_lock(void) {}
 static inline void unlock_vector_lock(void) {}
@@ -163,8 +161,7 @@ static inline void unlock_vector_lock(void) {}
 extern atomic_t irq_err_count;
 extern atomic_t irq_mis_count;
 
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
+extern void elcr_set_level_irq(unsigned int irq);
 
 /* SMP */
 extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
@@ -178,7 +175,6 @@ extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
 extern __visible void smp_reschedule_interrupt(struct pt_regs *);
 extern __visible void smp_call_function_interrupt(struct pt_regs *);
 extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
-extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
 extern char irq_entries_start[];
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index e42f758a0fbd..055ea9941dd5 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -50,7 +50,7 @@ extern const struct hypervisor_x86 *x86_hyper;
 /* Recognized hypervisors */
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
-extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_xen;
 extern const struct hypervisor_x86 x86_hyper_kvm;
 
 extern void init_hypervisor(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
deleted file mode 100644
index 6eb6fcb83f63..000000000000
--- a/arch/x86/include/asm/i387.h
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef _ASM_X86_I387_H
-#define _ASM_X86_I387_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/hardirq.h>
-
-struct pt_regs;
-struct user_i387_struct;
-
-extern int init_fpu(struct task_struct *child);
-extern void fpu_finit(struct fpu *fpu);
-extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
-extern void math_state_restore(void);
-
-extern bool irq_fpu_usable(void);
-
-/*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
- */
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
-
-static inline void kernel_fpu_begin(void)
-{
-	preempt_disable();
-	WARN_ON_ONCE(!irq_fpu_usable());
-	__kernel_fpu_begin();
-}
-
-static inline void kernel_fpu_end(void)
-{
-	__kernel_fpu_end();
-	preempt_enable();
-}
-
-/* Must be called with preempt disabled */
-extern void kernel_fpu_disable(void);
-extern void kernel_fpu_enable(void);
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context as well. To prevent these kernel instructions
- * in interrupt context interacting wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
-	/*
-	 * If in process context and not atomic, we can take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context requires disabling preemption
-	 * or some heavy lifting like kernel_fpu_begin()
-	 */
-	if (!in_atomic())
-		return 0;
-
-	if (read_cr0() & X86_CR0_TS) {
-		clts();
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
-	if (TS_state)
-		stts();
-}
-
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int user_has_fpu(void)
-{
-	return current->thread.fpu.has_fpu;
-}
-
-extern void unlazy_fpu(struct task_struct *tsk);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34a5b93704d3..83ec9b1d77cc 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -35,11 +35,13 @@
   */
 
 #define ARCH_HAS_IOREMAP_WC
+#define ARCH_HAS_IOREMAP_WT
 
 #include <linux/string.h>
 #include <linux/compiler.h>
 #include <asm/page.h>
 #include <asm/early_ioremap.h>
+#include <asm/pgtable_types.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -177,6 +179,7 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
  * look at pci_iomap().
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
 				unsigned long prot_val);
@@ -197,8 +200,6 @@ extern void set_iounmap_nonlazy(void);
 
 #include <asm-generic/iomap.h>
 
-#include <linux/vmalloc.h>
-
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
@@ -320,6 +321,7 @@ extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 				enum page_cache_mode pcm);
 extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
 
 extern bool is_early_ioremap_ptep(pte_t *ptep);
 
@@ -338,6 +340,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 #define IO_SPACE_LIMIT 0xffff
 
 #ifdef CONFIG_MTRR
+extern int __must_check arch_phys_wc_index(int handle);
+#define arch_phys_wc_index arch_phys_wc_index
+
 extern int __must_check arch_phys_wc_add(unsigned long base,
 					 unsigned long size);
 extern void arch_phys_wc_del(int handle);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 2f91685fe1cd..6cbf2cfb3f8a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -95,9 +95,22 @@ struct IR_IO_APIC_route_entry {
 		index		: 15;
 } __attribute__ ((packed));
 
-#define IOAPIC_AUTO     -1
-#define IOAPIC_EDGE     0
-#define IOAPIC_LEVEL    1
+struct irq_alloc_info;
+struct ioapic_domain_cfg;
+
+#define IOAPIC_AUTO			-1
+#define IOAPIC_EDGE			0
+#define IOAPIC_LEVEL			1
+
+#define IOAPIC_MASKED			1
+#define IOAPIC_UNMASKED			0
+
+#define IOAPIC_POL_HIGH			0
+#define IOAPIC_POL_LOW			1
+
+#define IOAPIC_DEST_MODE_PHYSICAL	0
+#define IOAPIC_DEST_MODE_LOGICAL	1
+
 #define	IOAPIC_MAP_ALLOC		0x1
 #define	IOAPIC_MAP_CHECK		0x2
 
@@ -110,9 +123,6 @@ extern int nr_ioapics;
 
 extern int mpc_ioapic_id(int ioapic);
 extern unsigned int mpc_ioapic_addr(int ioapic);
-extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic);
-
-#define MP_MAX_IOAPIC_PIN 127
 
 /* # of MP IRQ source entries */
 extern int mp_irq_entries;
@@ -120,9 +130,6 @@ extern int mp_irq_entries;
 /* MP IRQ source entries */
 extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES];
 
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
@@ -132,6 +139,8 @@ extern int noioapicquirk;
 /* -1 if "noapic" boot option passed */
 extern int noioapicreroute;
 
+extern u32 gsi_top;
+
 extern unsigned long io_apic_irqs;
 
 #define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
@@ -147,13 +156,6 @@ struct irq_cfg;
 extern void ioapic_insert_resources(void);
 extern int arch_early_ioapic_init(void);
 
-extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
-				     unsigned int, int,
-				     struct io_apic_irq_attr *);
-extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-
-extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
-
 extern int save_ioapic_entries(void);
 extern void mask_ioapic_entries(void);
 extern int restore_ioapic_entries(void);
@@ -161,82 +163,32 @@ extern int restore_ioapic_entries(void);
 extern void setup_ioapic_ids_from_mpc(void);
 extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
-struct io_apic_irq_attr {
-	int ioapic;
-	int ioapic_pin;
-	int trigger;
-	int polarity;
-};
-
-enum ioapic_domain_type {
-	IOAPIC_DOMAIN_INVALID,
-	IOAPIC_DOMAIN_LEGACY,
-	IOAPIC_DOMAIN_STRICT,
-	IOAPIC_DOMAIN_DYNAMIC,
-};
-
-struct device_node;
-struct irq_domain;
-struct irq_domain_ops;
-
-struct ioapic_domain_cfg {
-	enum ioapic_domain_type		type;
-	const struct irq_domain_ops	*ops;
-	struct device_node		*dev;
-};
-
-struct mp_ioapic_gsi{
-	u32 gsi_base;
-	u32 gsi_end;
-};
-extern u32 gsi_top;
-
 extern int mp_find_ioapic(u32 gsi);
 extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
-extern u32 mp_pin_to_gsi(int ioapic, int pin);
-extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
+extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+			     struct irq_alloc_info *info);
 extern void mp_unmap_irq(int irq);
 extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
 			      struct ioapic_domain_cfg *cfg);
 extern int mp_unregister_ioapic(u32 gsi_base);
 extern int mp_ioapic_registered(u32 gsi_base);
-extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
-			    irq_hw_number_t hwirq);
-extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
-extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node);
-extern void __init pre_init_apic_IRQ0(void);
+
+extern void ioapic_set_alloc_attr(struct irq_alloc_info *info,
+				  int node, int trigger, int polarity);
 
 extern void mp_save_irq(struct mpc_intsrc *m);
 
 extern void disable_ioapic_support(void);
 
-extern void __init native_io_apic_init_mappings(void);
+extern void __init io_apic_init_mappings(void);
 extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg);
-extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val);
-extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val);
 extern void native_disable_io_apic(void);
-extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries);
-extern int native_ioapic_set_affinity(struct irq_data *,
-				      const struct cpumask *,
-				      bool);
 
 static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
 {
 	return x86_io_apic_ops.read(apic, reg);
 }
 
-static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	x86_io_apic_ops.write(apic, reg, value);
-}
-static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	x86_io_apic_ops.modify(apic, reg, value);
-}
-
-extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-
 extern void setup_IO_APIC(void);
 extern void enable_IO_APIC(void);
 extern void disable_IO_APIC(void);
@@ -253,8 +205,12 @@ static inline int arch_early_ioapic_init(void) { return 0; }
 static inline void print_IO_APICs(void) {}
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
-static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
-static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
+static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags,
+				    struct irq_alloc_info *info)
+{
+	return gsi;
+}
+
 static inline void mp_unmap_irq(int irq) { }
 
 static inline int save_ioapic_entries(void)
@@ -268,17 +224,11 @@ static inline int restore_ioapic_entries(void)
 	return -ENOMEM;
 }
 
-static inline void mp_save_irq(struct mpc_intsrc *m) { };
+static inline void mp_save_irq(struct mpc_intsrc *m) { }
 static inline void disable_ioapic_support(void) { }
-#define native_io_apic_init_mappings	NULL
+static inline void io_apic_init_mappings(void) { }
 #define native_io_apic_read		NULL
-#define native_io_apic_write		NULL
-#define native_io_apic_modify		NULL
 #define native_disable_io_apic		NULL
-#define native_io_apic_print_entries	NULL
-#define native_ioapic_set_affinity	NULL
-#define native_setup_ioapic_entry	NULL
-#define native_eoi_ioapic_pin		NULL
 
 static inline void setup_IO_APIC(void) { }
 static inline void enable_IO_APIC(void) { }
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index a80cbb88ea91..8008d06581c7 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -30,6 +30,10 @@ extern void fixup_irqs(void);
 extern void irq_force_complete_move(int);
 #endif
 
+#ifdef CONFIG_HAVE_KVM
+extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
+#endif
+
 extern void (*x86_platform_ipi_callback)(void);
 extern void native_init_IRQ(void);
 extern bool handle_irq(unsigned irq, struct pt_regs *regs);
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 6224d316c405..046c7fb1ca43 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -22,84 +22,72 @@
 #ifndef __X86_IRQ_REMAPPING_H
 #define __X86_IRQ_REMAPPING_H
 
+#include <asm/irqdomain.h>
+#include <asm/hw_irq.h>
 #include <asm/io_apic.h>
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_chip;
 struct msi_msg;
-struct pci_dev;
-struct irq_cfg;
+struct irq_alloc_info;
+
+enum irq_remap_cap {
+	IRQ_POSTING_CAP = 0,
+};
 
 #ifdef CONFIG_IRQ_REMAP
 
+extern bool irq_remapping_cap(enum irq_remap_cap cap);
 extern void set_irq_remapping_broken(void);
 extern int irq_remapping_prepare(void);
 extern int irq_remapping_enable(void);
 extern void irq_remapping_disable(void);
 extern int irq_remapping_reenable(int);
 extern int irq_remap_enable_fault_handling(void);
-extern int setup_ioapic_remapped_entry(int irq,
-				       struct IO_APIC_route_entry *entry,
-				       unsigned int destination,
-				       int vector,
-				       struct io_apic_irq_attr *attr);
-extern void free_remapped_irq(int irq);
-extern void compose_remapped_msi_msg(struct pci_dev *pdev,
-				     unsigned int irq, unsigned int dest,
-				     struct msi_msg *msg, u8 hpet_id);
-extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id);
 extern void panic_if_irq_remap(const char *msg);
-extern bool setup_remapped_irq(int irq,
-			       struct irq_cfg *cfg,
-			       struct irq_chip *chip);
 
-void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent);
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+	return x86_vector_domain;
+}
+
+struct vcpu_data {
+	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
+	u32 vector;		/* Guest vector of the interrupt */
+};
 
 #else  /* CONFIG_IRQ_REMAP */
 
+static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
 static inline void set_irq_remapping_broken(void) { }
 static inline int irq_remapping_prepare(void) { return -ENODEV; }
 static inline int irq_remapping_enable(void) { return -ENODEV; }
 static inline void irq_remapping_disable(void) { }
 static inline int irq_remapping_reenable(int eim) { return -ENODEV; }
 static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; }
-static inline int setup_ioapic_remapped_entry(int irq,
-					      struct IO_APIC_route_entry *entry,
-					      unsigned int destination,
-					      int vector,
-					      struct io_apic_irq_attr *attr)
-{
-	return -ENODEV;
-}
-static inline void free_remapped_irq(int irq) { }
-static inline void compose_remapped_msi_msg(struct pci_dev *pdev,
-					    unsigned int irq, unsigned int dest,
-					    struct msi_msg *msg, u8 hpet_id)
-{
-}
-static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
-	return -ENODEV;
-}
 
 static inline void panic_if_irq_remap(const char *msg)
 {
 }
 
-static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
 {
+	return NULL;
 }
 
-static inline bool setup_remapped_irq(int irq,
-				      struct irq_cfg *cfg,
-				      struct irq_chip *chip)
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
 {
-	return false;
+	return NULL;
 }
-#endif /* CONFIG_IRQ_REMAP */
-
-#define dmar_alloc_hwirq()	irq_alloc_hwirq(-1)
-#define dmar_free_hwirq		irq_free_hwirq
 
+#endif /* CONFIG_IRQ_REMAP */
 #endif /* __X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 666c89ec4bd7..4c2d2eb2060a 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -47,31 +47,12 @@
 #define IRQ_MOVE_CLEANUP_VECTOR		FIRST_EXTERNAL_VECTOR
 
 #define IA32_SYSCALL_VECTOR		0x80
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR			0x80
-#endif
 
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
  *   round up to the next 16-vector boundary
  */
-#define IRQ0_VECTOR			((FIRST_EXTERNAL_VECTOR + 16) & ~15)
-
-#define IRQ1_VECTOR			(IRQ0_VECTOR +  1)
-#define IRQ2_VECTOR			(IRQ0_VECTOR +  2)
-#define IRQ3_VECTOR			(IRQ0_VECTOR +  3)
-#define IRQ4_VECTOR			(IRQ0_VECTOR +  4)
-#define IRQ5_VECTOR			(IRQ0_VECTOR +  5)
-#define IRQ6_VECTOR			(IRQ0_VECTOR +  6)
-#define IRQ7_VECTOR			(IRQ0_VECTOR +  7)
-#define IRQ8_VECTOR			(IRQ0_VECTOR +  8)
-#define IRQ9_VECTOR			(IRQ0_VECTOR +  9)
-#define IRQ10_VECTOR			(IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR			(IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR			(IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR			(IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR			(IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR			(IRQ0_VECTOR + 15)
+#define ISA_IRQ_VECTOR(irq)		(((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq)
 
 /*
  * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
@@ -102,21 +83,23 @@
  */
 #define X86_PLATFORM_IPI_VECTOR		0xf7
 
-/* Vector for KVM to deliver posted interrupt IPI */
-#ifdef CONFIG_HAVE_KVM
-#define POSTED_INTR_VECTOR		0xf2
-#endif
-
+#define POSTED_INTR_WAKEUP_VECTOR	0xf1
 /*
  * IRQ work vector:
  */
 #define IRQ_WORK_VECTOR			0xf6
 
 #define UV_BAU_MESSAGE			0xf5
+#define DEFERRED_ERROR_VECTOR		0xf4
 
 /* Vector on which hypervisor callbacks will be delivered */
 #define HYPERVISOR_CALLBACK_VECTOR	0xf3
 
+/* Vector for KVM to deliver posted interrupt IPI */
+#ifdef CONFIG_HAVE_KVM
+#define POSTED_INTR_VECTOR		0xf2
+#endif
+
 /*
  * Local APIC timer IRQ vector is on a different priority level,
  * to work around the 'lost local interrupt if more than 2 IRQ
@@ -155,18 +138,22 @@ static inline int invalid_vm86_irq(int irq)
  * static arrays.
  */
 
-#define NR_IRQS_LEGACY			  16
+#define NR_IRQS_LEGACY			16
 
-#define IO_APIC_VECTOR_LIMIT		( 32 * MAX_IO_APICS )
+#define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
+#define IO_APIC_VECTOR_LIMIT		(32 * MAX_IO_APICS)
 
-#ifdef CONFIG_X86_IO_APIC
-# define CPU_VECTOR_LIMIT		(64 * NR_CPUS)
-# define NR_IRQS					\
+#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI)
+#define NR_IRQS						\
 	(CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ?	\
 		(NR_VECTORS + CPU_VECTOR_LIMIT)  :	\
 		(NR_VECTORS + IO_APIC_VECTOR_LIMIT))
-#else /* !CONFIG_X86_IO_APIC: */
-# define NR_IRQS			NR_IRQS_LEGACY
+#elif defined(CONFIG_X86_IO_APIC)
+#define	NR_IRQS				(NR_VECTORS + IO_APIC_VECTOR_LIMIT)
+#elif defined(CONFIG_PCI_MSI)
+#define NR_IRQS				(NR_VECTORS + CPU_VECTOR_LIMIT)
+#else
+#define NR_IRQS				NR_IRQS_LEGACY
 #endif
 
 #endif /* _ASM_X86_IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
new file mode 100644
index 000000000000..d26075b52885
--- /dev/null
+++ b/arch/x86/include/asm/irqdomain.h
@@ -0,0 +1,63 @@
+#ifndef _ASM_IRQDOMAIN_H
+#define _ASM_IRQDOMAIN_H
+
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+enum {
+	/* Allocate contiguous CPU vectors */
+	X86_IRQ_ALLOC_CONTIGUOUS_VECTORS		= 0x1,
+};
+
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+				const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+				struct irq_alloc_info *src);
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#ifdef CONFIG_X86_IO_APIC
+struct device_node;
+struct irq_data;
+
+enum ioapic_domain_type {
+	IOAPIC_DOMAIN_INVALID,
+	IOAPIC_DOMAIN_LEGACY,
+	IOAPIC_DOMAIN_STRICT,
+	IOAPIC_DOMAIN_DYNAMIC,
+};
+
+struct ioapic_domain_cfg {
+	enum ioapic_domain_type		type;
+	const struct irq_domain_ops	*ops;
+	struct device_node		*dev;
+};
+
+extern const struct irq_domain_ops mp_ioapic_irqdomain_ops;
+
+extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg);
+extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs);
+extern void mp_irqdomain_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data);
+extern void mp_irqdomain_deactivate(struct irq_domain *domain,
+				    struct irq_data *irq_data);
+extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
+#endif /* CONFIG_X86_IO_APIC */
+
+#ifdef CONFIG_PCI_MSI
+extern void arch_init_msi_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+#endif
+
+#ifdef CONFIG_HT_IRQ
+extern void arch_init_htirq_domain(struct irq_domain *domain);
+#else
+static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 57a9d94fe160..e16466ec473c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -193,6 +193,8 @@ struct x86_emulate_ops {
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
+	u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
+	void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
 	int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
 	int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
@@ -262,6 +264,11 @@ enum x86emul_mode {
 	X86EMUL_MODE_PROT64,	/* 64-bit (long) mode.    */
 };
 
+/* These match some of the HF_* flags defined in kvm_host.h  */
+#define X86EMUL_GUEST_MASK           (1 << 5) /* VCPU is in guest-mode */
+#define X86EMUL_SMM_MASK             (1 << 6)
+#define X86EMUL_SMM_INSIDE_NMI_MASK  (1 << 7)
+
 struct x86_emulate_ctxt {
 	const struct x86_emulate_ops *ops;
 
@@ -273,8 +280,8 @@ struct x86_emulate_ctxt {
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
+	int emul_flags;
 
-	bool guest_mode; /* guest running a nested guest */
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dea2e7e962e3..c7fa57b529d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -184,29 +184,28 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
-/*
- * kvm_mmu_page_role, below, is defined as:
- *
- *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
- *   bits 4:7 - page table level for this shadow (1-4)
- *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - direct mapping of virtual to physical mapping at gfn
- *              used for real mode and two-dimensional paging
- *   bits 17:19 - common access permissions for all ptes in this shadow page
- */
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
 		unsigned level:4;
 		unsigned cr4_pae:1;
 		unsigned quadrant:2;
-		unsigned pad_for_nice_hex_output:6;
 		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
 		unsigned nxe:1;
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
+		unsigned smap_andnot_wp:1;
+		unsigned :8;
+
+		/*
+		 * This is left at the top of the word so that
+		 * kvm_memslots_for_spte_role can extract it with a
+		 * simple shift.  While there is room, give it a whole
+		 * byte so it is also faster to load it from memory.
+		 */
+		unsigned smm:8;
 	};
 };
 
@@ -337,12 +336,28 @@ struct kvm_pmu {
 	u64 reprogram_pmi;
 };
 
+struct kvm_pmu_ops;
+
 enum {
 	KVM_DEBUGREG_BP_ENABLED = 1,
 	KVM_DEBUGREG_WONT_EXIT = 2,
 	KVM_DEBUGREG_RELOAD = 4,
 };
 
+struct kvm_mtrr_range {
+	u64 base;
+	u64 mask;
+	struct list_head node;
+};
+
+struct kvm_mtrr {
+	struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR];
+	mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION];
+	u64 deftype;
+
+	struct list_head head;
+};
+
 struct kvm_vcpu_arch {
 	/*
 	 * rip and regs accesses must go through
@@ -367,6 +382,7 @@ struct kvm_vcpu_arch {
 	int32_t apic_arb_prio;
 	int mp_state;
 	u64 ia32_misc_enable_msr;
+	u64 smbase;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
 
@@ -400,6 +416,7 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	struct fpu guest_fpu;
+	bool eager_fpu;
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -469,8 +486,9 @@ struct kvm_vcpu_arch {
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
 	unsigned nmi_pending; /* NMI queued after currently running handler */
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
+	bool smi_pending;    /* SMI queued after currently running handler */
 
-	struct mtrr_state_type mtrr_state;
+	struct kvm_mtrr mtrr_state;
 	u64 pat;
 
 	unsigned switch_db_regs;
@@ -635,6 +653,8 @@ struct kvm_arch {
 	#endif
 
 	bool boot_vcpu_runs_old_kvmclock;
+
+	u64 disabled_quirks;
 };
 
 struct kvm_vm_stat {
@@ -687,12 +707,13 @@ struct msr_data {
 
 struct kvm_lapic_irq {
 	u32 vector;
-	u32 delivery_mode;
-	u32 dest_mode;
-	u32 level;
-	u32 trig_mode;
+	u16 delivery_mode;
+	u16 dest_mode;
+	bool level;
+	u16 trig_mode;
 	u32 shorthand;
 	u32 dest_id;
+	bool msi_redir_hint;
 };
 
 struct kvm_x86_ops {
@@ -704,19 +725,20 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
+	bool (*cpu_has_high_real_mode_segbase)(void);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
 	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
-	void (*vcpu_reset)(struct kvm_vcpu *vcpu);
+	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
 
 	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
 	void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
-	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
 	void (*get_segment)(struct kvm_vcpu *vcpu,
@@ -743,6 +765,7 @@ struct kvm_x86_ops {
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	void (*fpu_activate)(struct kvm_vcpu *vcpu);
 	void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
@@ -833,6 +856,8 @@ struct kvm_x86_ops {
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
+	/* pmu operations of sub-arch */
+	const struct kvm_pmu_ops *pmu_ops;
 };
 
 struct kvm_arch_async_pf {
@@ -868,7 +893,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
 				      struct kvm_memory_slot *memslot);
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
-					struct kvm_memory_slot *memslot);
+				   const struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot);
 void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
@@ -879,7 +904,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				   struct kvm_memory_slot *slot,
 				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm);
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
@@ -887,7 +912,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
-u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 struct kvm_irq_mask_notifier {
 	void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
@@ -935,7 +959,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer);
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
+int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 struct x86_emulate_ctxt;
@@ -964,7 +988,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
@@ -999,8 +1023,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
-int fx_init(struct kvm_vcpu *vcpu);
-
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes);
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
@@ -1109,6 +1131,14 @@ enum {
 #define HF_NMI_MASK		(1 << 3)
 #define HF_IRET_MASK		(1 << 4)
 #define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
+#define HF_SMM_MASK		(1 << 6)
+#define HF_SMM_INSIDE_NMI_MASK	(1 << 7)
+
+#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#define KVM_ADDRESS_SPACE_NUM 2
+
+#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
 
 /*
  * Hardware virtualization extension instructions may fault if a
@@ -1143,7 +1173,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 					   unsigned long address);
@@ -1167,16 +1197,9 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 
-void kvm_pmu_init(struct kvm_vcpu *vcpu);
-void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
-void kvm_pmu_reset(struct kvm_vcpu *vcpu);
-void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
-bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
-int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
-int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc);
-int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
-void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
+int __x86_set_memory_region(struct kvm *kvm,
+			    const struct kvm_userspace_memory_region *mem);
+int x86_set_memory_region(struct kvm *kvm,
+			  const struct kvm_userspace_memory_region *mem);
 
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 2d29197bd2fb..19c099afa861 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -21,6 +21,7 @@
 #ifndef _ASM_X86_LIVEPATCH_H
 #define _ASM_X86_LIVEPATCH_H
 
+#include <asm/setup.h>
 #include <linux/module.h>
 #include <linux/ftrace.h>
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 1f5a86d518db..982dfc3679ad 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -17,11 +17,16 @@
 #define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
 #define MCG_SER_P		(1ULL<<24)   /* MCA recovery/new status bits */
 #define MCG_ELOG_P		(1ULL<<26)   /* Extended error log supported */
+#define MCG_LMCE_P		(1ULL<<27)   /* Local machine check supported */
 
 /* MCG_STATUS register defines */
 #define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
 #define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
 #define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
+#define MCG_STATUS_LMCES (1ULL<<3)   /* LMCE signaled */
+
+/* MCG_EXT_CTL register defines */
+#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
 
 /* MCi_STATUS register defines */
 #define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
@@ -104,6 +109,7 @@ struct mce_log {
 struct mca_config {
 	bool dont_log_ce;
 	bool cmci_disabled;
+	bool lmce_disabled;
 	bool ignore_ce;
 	bool disabled;
 	bool ser;
@@ -117,8 +123,19 @@ struct mca_config {
 };
 
 struct mce_vendor_flags {
-	__u64		overflow_recov	: 1, /* cpuid_ebx(80000007) */
-			__reserved_0	: 63;
+			/*
+			 * overflow recovery cpuid bit indicates that overflow
+			 * conditions are not fatal
+			 */
+	__u64		overflow_recov	: 1,
+
+			/*
+			 * SUCCOR stands for S/W UnCorrectable error COntainment
+			 * and Recovery. It indicates support for data poisoning
+			 * in HW and deferred error interrupts.
+			 */
+			succor		: 1,
+			__reserved_0	: 62;
 };
 extern struct mce_vendor_flags mce_flags;
 
@@ -168,12 +185,16 @@ void cmci_clear(void);
 void cmci_reenable(void);
 void cmci_rediscover(void);
 void cmci_recheck(void);
+void lmce_clear(void);
+void lmce_enable(void);
 #else
 static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
 static inline void cmci_clear(void) {}
 static inline void cmci_reenable(void) {}
 static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
+static inline void lmce_clear(void) {}
+static inline void lmce_enable(void) {}
 #endif
 
 #ifdef CONFIG_X86_MCE_AMD
@@ -223,6 +244,9 @@ void do_machine_check(struct pt_regs *, long);
 extern void (*mce_threshold_vector)(void);
 extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
+/* Deferred error interrupt handler */
+extern void (*deferred_error_int_vector)(void);
+
 /*
  * Thermal handler
  */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 2fb20d6f7e23..9e6278c7140e 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#include <linux/earlycpio.h>
+
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
 	u64 __val = native_read_msr((msr));		\
@@ -152,6 +154,7 @@ extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 void reload_early_microcode(void);
+extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 #else
 static inline void __init load_ucode_bsp(void) {}
 static inline void load_ucode_ap(void) {}
@@ -160,6 +163,9 @@ static inline int __init save_microcode_in_initrd(void)
 	return 0;
 }
 static inline void reload_early_microcode(void) {}
+static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+	return false;
+}
 #endif
-
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index af935397e053..ac6d328977a6 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -65,12 +65,12 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
 #ifdef CONFIG_MICROCODE_AMD_EARLY
-extern void __init load_ucode_amd_bsp(void);
+extern void __init load_ucode_amd_bsp(unsigned int family);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
 void reload_ucode_amd(void);
 #else
-static inline void __init load_ucode_amd_bsp(void) {}
+static inline void __init load_ucode_amd_bsp(unsigned int family) {}
 static inline void load_ucode_amd_ap(void) {}
 static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
 void reload_ucode_amd(void) {}
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 2b9209c46ca9..7991c606125d 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -51,20 +51,11 @@ struct extended_sigtable {
 	(((struct microcode_intel *)mc)->hdr.datasize ? \
 	 ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE)
 
-#define sigmatch(s1, s2, p1, p2) \
-	(((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0))))
-
 #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE)
 
-extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc);
+extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev);
 extern int microcode_sanity_check(void *mc, int print_err);
-extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc);
-
-static inline int
-revision_is_newer(struct microcode_header_intel *mc_header, int rev)
-{
-	return (mc_header->rev <= rev) ? 0 : 1;
-}
+extern int find_matching_signature(void *mc, unsigned int csig, int cpf);
 
 #ifdef CONFIG_MICROCODE_INTEL_EARLY
 extern void __init load_ucode_intel_bsp(void);
diff --git a/arch/x86/include/asm/mm-arch-hooks.h b/arch/x86/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..4e881a342236
--- /dev/null
+++ b/arch/x86/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_X86_MM_ARCH_HOOKS_H
+#define _ASM_X86_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_X86_MM_ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 883f6b933fa4..5e8daee7c5c9 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -142,6 +142,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 	paravirt_arch_exit_mmap(mm);
 }
 
+#ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return	!config_enabled(CONFIG_IA32_EMULATION) ||
+		!(mm->context.ia32_compat == TIF_IA32);
+}
+#else
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return false;
+}
+#endif
+
 static inline void arch_bprm_mm_init(struct mm_struct *mm,
 		struct vm_area_struct *vma)
 {
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
index a952a13d59a7..7a35495275a9 100644
--- a/arch/x86/include/asm/mpx.h
+++ b/arch/x86/include/asm/mpx.h
@@ -13,55 +13,50 @@
 #define MPX_BNDCFG_ENABLE_FLAG	0x1
 #define MPX_BD_ENTRY_VALID_FLAG	0x1
 
-#ifdef CONFIG_X86_64
-
-/* upper 28 bits [47:20] of the virtual address in 64-bit used to
- * index into bounds directory (BD).
- */
-#define MPX_BD_ENTRY_OFFSET	28
-#define MPX_BD_ENTRY_SHIFT	3
-/* bits [19:3] of the virtual address in 64-bit used to index into
- * bounds table (BT).
+/*
+ * The upper 28 bits [47:20] of the virtual address in 64-bit
+ * are used to index into bounds directory (BD).
+ *
+ * The directory is 2G (2^31) in size, and with 8-byte entries
+ * it has 2^28 entries.
  */
-#define MPX_BT_ENTRY_OFFSET	17
-#define MPX_BT_ENTRY_SHIFT	5
-#define MPX_IGN_BITS		3
-#define MPX_BD_ENTRY_TAIL	3
+#define MPX_BD_SIZE_BYTES_64	(1UL<<31)
+#define MPX_BD_ENTRY_BYTES_64	8
+#define MPX_BD_NR_ENTRIES_64	(MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
 
-#else
-
-#define MPX_BD_ENTRY_OFFSET	20
-#define MPX_BD_ENTRY_SHIFT	2
-#define MPX_BT_ENTRY_OFFSET	10
-#define MPX_BT_ENTRY_SHIFT	4
-#define MPX_IGN_BITS		2
-#define MPX_BD_ENTRY_TAIL	2
+/*
+ * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
+ * entries it has 2^20 entries.
+ */
+#define MPX_BD_SIZE_BYTES_32	(1UL<<22)
+#define MPX_BD_ENTRY_BYTES_32	4
+#define MPX_BD_NR_ENTRIES_32	(MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
 
-#endif
+/*
+ * A 64-bit table is 4MB total in size, and an entry is
+ * 4 64-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_64	(1UL<<22)
+#define MPX_BT_ENTRY_BYTES_64	32
+#define MPX_BT_NR_ENTRIES_64	(MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
 
-#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
-#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+/*
+ * A 32-bit table is 16kB total in size, and an entry is
+ * 4 32-bit pointers in size.
+ */
+#define MPX_BT_SIZE_BYTES_32	(1UL<<14)
+#define MPX_BT_ENTRY_BYTES_32	16
+#define MPX_BT_NR_ENTRIES_32	(MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
 
 #define MPX_BNDSTA_TAIL		2
 #define MPX_BNDCFG_TAIL		12
 #define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
 #define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BT_ADDR_MASK	(~((1UL<<MPX_BD_ENTRY_TAIL)-1))
-
-#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
 #define MPX_BNDSTA_ERROR_CODE	0x3
 
-#define MPX_BD_ENTRY_MASK	((1<<MPX_BD_ENTRY_OFFSET)-1)
-#define MPX_BT_ENTRY_MASK	((1<<MPX_BT_ENTRY_OFFSET)-1)
-#define MPX_GET_BD_ENTRY_OFFSET(addr)	((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
-		MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
-#define MPX_GET_BT_ENTRY_OFFSET(addr)	((((addr)>>MPX_IGN_BITS) & \
-		MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
-
 #ifdef CONFIG_X86_INTEL_MPX
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf);
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs);
+int mpx_handle_bd_fault(void);
 static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
 {
 	return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
@@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);
 #else
-static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-					      struct xsave_struct *xsave_buf)
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
 	return NULL;
 }
-static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+static inline int mpx_handle_bd_fault(void)
 {
 	return -EINVAL;
 }
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
new file mode 100644
index 000000000000..93724cc62177
--- /dev/null
+++ b/arch/x86/include/asm/msi.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_MSI_H
+#define _ASM_X86_MSI_H
+#include <asm/hw_irq.h>
+
+typedef struct irq_alloc_info msi_alloc_info_t;
+
+#endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c469490db4a8..9ebc3d009373 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,7 @@
 #define MSR_IA32_MCG_CAP		0x00000179
 #define MSR_IA32_MCG_STATUS		0x0000017a
 #define MSR_IA32_MCG_CTL		0x0000017b
+#define MSR_IA32_MCG_EXT_CTL		0x000004d0
 
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
@@ -140,6 +141,7 @@
 #define MSR_CORE_C3_RESIDENCY		0x000003fc
 #define MSR_CORE_C6_RESIDENCY		0x000003fd
 #define MSR_CORE_C7_RESIDENCY		0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY	0x000003ff
 #define MSR_PKG_C2_RESIDENCY		0x0000060d
 #define MSR_PKG_C8_RESIDENCY		0x00000630
 #define MSR_PKG_C9_RESIDENCY		0x00000631
@@ -379,6 +381,7 @@
 #define FEATURE_CONTROL_LOCKED				(1<<0)
 #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
 #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
+#define FEATURE_CONTROL_LMCE				(1<<20)
 
 #define MSR_IA32_APICBASE		0x0000001b
 #define MSR_IA32_APICBASE_BSP		(1<<8)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index de36f22eb0b9..e6a707eb5081 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -1,13 +1,14 @@
 #ifndef _ASM_X86_MSR_H
 #define _ASM_X86_MSR_H
 
-#include <uapi/asm/msr.h>
+#include "msr-index.h"
 
 #ifndef __ASSEMBLY__
 
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/cpumask.h>
+#include <uapi/asm/msr.h>
 
 struct msr {
 	union {
@@ -205,8 +206,13 @@ do {                                                            \
 
 #endif	/* !CONFIG_PARAVIRT */
 
-#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val),		\
-					     (u32)((val) >> 32))
+/*
+ * 64-bit version of wrmsr_safe():
+ */
+static inline int wrmsrl_safe(u32 msr, u64 val)
+{
+	return wrmsr_safe(msr, (u32)val,  (u32)(val >> 32));
+}
 
 #define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high))
 
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index f768f6298419..b94f6f64e23d 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -31,7 +31,7 @@
  * arch_phys_wc_add and arch_phys_wc_del.
  */
 # ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
 extern void mtrr_save_fixed_ranges(void *);
 extern void mtrr_save_state(void);
 extern int mtrr_add(unsigned long base, unsigned long size,
@@ -48,14 +48,13 @@ extern void mtrr_aps_init(void);
 extern void mtrr_bp_restore(void);
 extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
 extern int amd_special_default_mtrr(void);
-extern int phys_wc_to_mtrr_index(int handle);
 #  else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
 {
 	/*
 	 * Return no-MTRRs:
 	 */
-	return 0xff;
+	return MTRR_TYPE_INVALID;
 }
 #define mtrr_save_fixed_ranges(arg) do {} while (0)
 #define mtrr_save_state() do {} while (0)
@@ -84,10 +83,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
 static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
 {
 }
-static inline int phys_wc_to_mtrr_index(int handle)
-{
-	return -1;
-}
 
 #define mtrr_ap_init() do {} while (0)
 #define mtrr_bp_init() do {} while (0)
@@ -127,4 +122,8 @@ struct mtrr_gentry32 {
 				 _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry32)
 #endif /* CONFIG_COMPAT */
 
+/* Bit fields for enabled in struct mtrr_state_type */
+#define MTRR_STATE_MTRR_FIXED_ENABLED	0x01
+#define MTRR_STATE_MTRR_ENABLED		0x02
+
 #endif /* _ASM_X86_MTRR_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8957810ad7d1..d143bfad45d7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 
 #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+							u32 val)
+{
+	PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+	PVOP_VCALL2(pv_lock_ops.wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+	PVOP_VCALL1(pv_lock_ops.kick, cpu);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
 static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
 							__ticket_t ticket)
 {
@@ -724,7 +749,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
 	PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
 }
 
-#endif
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+#endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f7b0b5c112f2..a6b8f9fadb06 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -160,13 +160,14 @@ struct pv_cpu_ops {
 	u64 (*read_pmc)(int counter);
 	unsigned long long (*read_tscp)(unsigned int *aux);
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Atomically enable interrupts and return to userspace.  This
-	 * is only ever used to return to 32-bit processes; in a
-	 * 64-bit kernel, it's used for 32-on-64 compat processes, but
-	 * never native 64-bit processes.  (Jump, not call.)
+	 * is only used in 32-bit kernels.  64-bit kernels use
+	 * usergs_sysret32 instead.
 	 */
 	void (*irq_enable_sysexit)(void);
+#endif
 
 	/*
 	 * Switch to usermode gs and return to 64-bit usermode using
@@ -333,9 +334,19 @@ struct arch_spinlock;
 typedef u16 __ticket_t;
 #endif
 
+struct qspinlock;
+
 struct pv_lock_ops {
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+	struct paravirt_callee_save queued_spin_unlock;
+
+	void (*wait)(u8 *ptr, u8 val);
+	void (*kick)(int cpu);
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	struct paravirt_callee_save lock_spinning;
 	void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
 };
 
 /* This contains all the paravirt structures: we get a convenient
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 91bc4ba95f91..ca6c228d5e62 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -4,14 +4,9 @@
 #include <linux/types.h>
 #include <asm/pgtable_types.h>
 
-#ifdef CONFIG_X86_PAT
-extern int pat_enabled;
-#else
-static const int pat_enabled;
-#endif
-
+bool pat_enabled(void);
 extern void pat_init(void);
-void pat_init_cache_modes(void);
+void pat_init_cache_modes(u64);
 
 extern int reserve_memtype(u64 start, u64 end,
 		enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 81da003df21b..462594320d39 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -80,13 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 #ifdef CONFIG_PCI
 extern void early_quirks(void);
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
 #else
 static inline void early_quirks(void) { }
 #endif
@@ -96,15 +89,10 @@ extern void pci_iommu_alloc(void);
 #ifdef CONFIG_PCI_MSI
 /* implemented in arch/x86/kernel/apic/io_apic. */
 struct msi_desc;
-void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
-			    unsigned int dest, struct msi_msg *msg, u8 hpet_id);
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void native_teardown_msi_irq(unsigned int irq);
 void native_restore_msi_irqs(struct pci_dev *dev);
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-		  unsigned int irq_base, unsigned int irq_offset);
 #else
-#define native_compose_msi_msg		NULL
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
 #endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index fe57e7a98839..867da5bbb4a3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -398,11 +398,17 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 	 * requested memtype:
 	 * - request is uncached, return cannot be write-back
 	 * - request is write-combine, return cannot be write-back
+	 * - request is write-through, return cannot be write-back
+	 * - request is write-through, return cannot be write-combine
 	 */
 	if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
 	     new_pcm == _PAGE_CACHE_MODE_WB) ||
 	    (pcm == _PAGE_CACHE_MODE_WC &&
-	     new_pcm == _PAGE_CACHE_MODE_WB)) {
+	     new_pcm == _PAGE_CACHE_MODE_WB) ||
+	    (pcm == _PAGE_CACHE_MODE_WT &&
+	     new_pcm == _PAGE_CACHE_MODE_WB) ||
+	    (pcm == _PAGE_CACHE_MODE_WT &&
+	     new_pcm == _PAGE_CACHE_MODE_WC)) {
 		return 0;
 	}
 
@@ -799,8 +805,8 @@ static inline int pmd_write(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_RW;
 }
 
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr,
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
 				       pmd_t *pmdp)
 {
 	pmd_t pmd = native_pmdp_get_and_clear(pmdp);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 78f0c8cbe316..13f310bfc09a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -367,6 +367,9 @@ extern int nx_enabled;
 #define pgprot_writecombine	pgprot_writecombine
 extern pgprot_t pgprot_writecombine(pgprot_t prot);
 
+#define pgprot_writethrough	pgprot_writethrough
+extern pgprot_t pgprot_writethrough(pgprot_t prot);
+
 /* Indicate that x86 has its own track and untrack pfn vma functions */
 #define __HAVE_PFNMAP_TRACKING
 
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8f3271842533..dca71714f860 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -99,11 +99,9 @@ static __always_inline bool should_resched(void)
   extern asmlinkage void ___preempt_schedule(void);
 # define __preempt_schedule() asm ("call ___preempt_schedule")
   extern asmlinkage void preempt_schedule(void);
-# ifdef CONFIG_CONTEXT_TRACKING
-    extern asmlinkage void ___preempt_schedule_context(void);
-#   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
-    extern asmlinkage void preempt_schedule_context(void);
-# endif
+  extern asmlinkage void ___preempt_schedule_notrace(void);
+# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace")
+  extern asmlinkage void preempt_schedule_notrace(void);
 #endif
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 23ba6765b718..43e6519df0d5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -21,6 +21,7 @@ struct mm_struct;
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
 #include <asm/special_insns.h>
+#include <asm/fpu/types.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -52,11 +53,16 @@ static inline void *current_text_addr(void)
 	return pc;
 }
 
+/*
+ * These alignment constraints are for performance in the vSMP case,
+ * but in the task_struct case we must also meet hardware imposed
+ * alignment requirements of the FPU state:
+ */
 #ifdef CONFIG_X86_VSMP
 # define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
 # define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
 #else
-# define ARCH_MIN_TASKALIGN		16
+# define ARCH_MIN_TASKALIGN		__alignof__(union fpregs_state)
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
@@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op;
 #define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
-extern void fpu_detect(struct cpuinfo_x86 *c);
 
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
@@ -313,128 +318,6 @@ struct orig_ist {
 	unsigned long		ist[7];
 };
 
-#define	MXCSR_DEFAULT		0x1f80
-
-struct i387_fsave_struct {
-	u32			cwd;	/* FPU Control Word		*/
-	u32			swd;	/* FPU Status Word		*/
-	u32			twd;	/* FPU Tag Word			*/
-	u32			fip;	/* FPU IP Offset		*/
-	u32			fcs;	/* FPU IP Selector		*/
-	u32			foo;	/* FPU Operand Pointer Offset	*/
-	u32			fos;	/* FPU Operand Pointer Selector	*/
-
-	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
-	u32			st_space[20];
-
-	/* Software status information [not touched by FSAVE ]:		*/
-	u32			status;
-};
-
-struct i387_fxsave_struct {
-	u16			cwd; /* Control Word			*/
-	u16			swd; /* Status Word			*/
-	u16			twd; /* Tag Word			*/
-	u16			fop; /* Last Instruction Opcode		*/
-	union {
-		struct {
-			u64	rip; /* Instruction Pointer		*/
-			u64	rdp; /* Data Pointer			*/
-		};
-		struct {
-			u32	fip; /* FPU IP Offset			*/
-			u32	fcs; /* FPU IP Selector			*/
-			u32	foo; /* FPU Operand Offset		*/
-			u32	fos; /* FPU Operand Selector		*/
-		};
-	};
-	u32			mxcsr;		/* MXCSR Register State */
-	u32			mxcsr_mask;	/* MXCSR Mask		*/
-
-	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
-	u32			st_space[32];
-
-	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
-	u32			xmm_space[64];
-
-	u32			padding[12];
-
-	union {
-		u32		padding1[12];
-		u32		sw_reserved[12];
-	};
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
-	u32			cwd;
-	u32			swd;
-	u32			twd;
-	u32			fip;
-	u32			fcs;
-	u32			foo;
-	u32			fos;
-	/* 8*10 bytes for each FP-reg = 80 bytes: */
-	u32			st_space[20];
-	u8			ftop;
-	u8			changed;
-	u8			lookahead;
-	u8			no_update;
-	u8			rm;
-	u8			alimit;
-	struct math_emu_info	*info;
-	u32			entry_eip;
-};
-
-struct ymmh_struct {
-	/* 16 * 16 bytes for each YMMH-reg = 256 bytes */
-	u32 ymmh_space[64];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
-	u8 reserved[128];
-};
-
-struct bndreg {
-	u64 lower_bound;
-	u64 upper_bound;
-} __packed;
-
-struct bndcsr {
-	u64 bndcfgu;
-	u64 bndstatus;
-} __packed;
-
-struct xsave_hdr_struct {
-	u64 xstate_bv;
-	u64 xcomp_bv;
-	u64 reserved[6];
-} __attribute__((packed));
-
-struct xsave_struct {
-	struct i387_fxsave_struct i387;
-	struct xsave_hdr_struct xsave_hdr;
-	struct ymmh_struct ymmh;
-	struct lwp_struct lwp;
-	struct bndreg bndreg[4];
-	struct bndcsr bndcsr;
-	/* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
-	struct i387_fsave_struct	fsave;
-	struct i387_fxsave_struct	fxsave;
-	struct i387_soft_struct		soft;
-	struct xsave_struct		xsave;
-};
-
-struct fpu {
-	unsigned int last_cpu;
-	unsigned int has_fpu;
-	union thread_xstate *state;
-};
-
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(struct orig_ist, orig_ist);
 
@@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
 
 struct perf_event;
 
@@ -508,6 +389,10 @@ struct thread_struct {
 	unsigned long		fs;
 #endif
 	unsigned long		gs;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -518,8 +403,6 @@ struct thread_struct {
 	unsigned long		cr2;
 	unsigned long		trap_nr;
 	unsigned long		error_code;
-	/* floating point and extended processor state */
-	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
 	struct vm86_struct __user *vm86_info;
@@ -535,15 +418,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-	/*
-	 * fpu_counter contains the number of consecutive context switches
-	 * that the FPU is used. If this is over a threshold, the lazy fpu
-	 * saving becomes unlazy to save the trap. This is an unsigned char
-	 * so that after 256 times the counter wraps and the behavior turns
-	 * lazy again; this to deal with bursty apps that only use FPU for
-	 * a short time
-	 */
-	unsigned char fpu_counter;
 };
 
 /*
@@ -928,24 +802,25 @@ extern int get_tsc_mode(unsigned long adr);
 extern int set_tsc_mode(unsigned int val);
 
 /* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT(tsk)	mpx_enable_management((tsk))
-#define MPX_DISABLE_MANAGEMENT(tsk)	mpx_disable_management((tsk))
+#define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
+#define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()
 
 #ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(struct task_struct *tsk);
-extern int mpx_disable_management(struct task_struct *tsk);
+extern int mpx_enable_management(void);
+extern int mpx_disable_management(void);
 #else
-static inline int mpx_enable_management(struct task_struct *tsk)
+static inline int mpx_enable_management(void)
 {
 	return -EINVAL;
 }
-static inline int mpx_disable_management(struct task_struct *tsk)
+static inline int mpx_disable_management(void)
 {
 	return -EINVAL;
 }
 #endif /* CONFIG_X86_INTEL_MPX */
 
 extern u16 amd_get_nb_id(int cpu);
+extern u32 amd_get_nodes_per_socket(void);
 
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 {
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index a90f8972dad5..a4a77286cb1d 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -5,12 +5,14 @@
 
 /* misc architecture specific prototypes */
 
-void system_call(void);
 void syscall_init(void);
 
-void ia32_syscall(void);
-void ia32_cstar_target(void);
-void ia32_sysenter_target(void);
+void entry_SYSCALL_64(void);
+void entry_SYSCALL_compat(void);
+void entry_INT80_32(void);
+void entry_INT80_compat(void);
+void entry_SYSENTER_32(void);
+void entry_SYSENTER_compat(void);
 
 void x86_configure_nx(void);
 void x86_report_nx(void);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 19507ffa5d28..5fabf1362942 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -107,7 +107,7 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 static inline int user_mode(struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
-	return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
+	return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL;
 #else
 	return !!(regs->cs & 3);
 #endif
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 6167fd798188..655e07a48f6c 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,5 +41,6 @@ struct pvclock_wall_clock {
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
+#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e9fa28..628954ceede1 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -86,7 +86,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	offset = pvclock_get_nsec_offset(src);
 	ret = src->system_time + offset;
 	ret_flags = src->flags;
-	rdtsc_barrier();
 
 	*cycles = ret;
 	*flags = ret_flags;
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 000000000000..9d51fae1cba3
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,57 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm/cpufeature.h>
+#include <asm-generic/qspinlock_types.h>
+#include <asm/paravirt.h>
+
+#define	queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+	smp_store_release((u8 *)lock, 0);
+}
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+	pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	pv_queued_spin_unlock(lock);
+}
+#else
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	native_queued_spin_unlock(lock);
+}
+#endif
+
+#define virt_queued_spin_lock virt_queued_spin_lock
+
+static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+{
+	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+		return false;
+
+	while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
+		cpu_relax();
+
+	return true;
+}
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
new file mode 100644
index 000000000000..b002e711ba88
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_QSPINLOCK_PARAVIRT_H
+#define __ASM_QSPINLOCK_PARAVIRT_H
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
+
+#endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5a9856eb12ba..7d5a1929d76b 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -231,11 +231,21 @@
 #define TLS_SIZE			(GDT_ENTRY_TLS_ENTRIES* 8)
 
 #ifdef __KERNEL__
+
+/*
+ * early_idt_handler_array is an array of entry points referenced in the
+ * early IDT.  For simplicity, it's a real array with one entry point
+ * every nine bytes.  That leaves room for an optional 'push $0' if the
+ * vector has no error code (two bytes), a 'push $vector_number' (two
+ * bytes), and a jump to the common entry code (up to five bytes).
+ */
+#define EARLY_IDT_HANDLER_SIZE 9
+
 #ifndef __ASSEMBLY__
 
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 #ifdef CONFIG_TRACING
-# define trace_early_idt_handlers early_idt_handlers
+# define trace_early_idt_handler_array early_idt_handler_array
 #endif
 
 /*
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f69e06b283fb..11af24e09c8a 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -60,17 +60,24 @@ static inline void x86_ce4100_early_setup(void) { }
 #ifndef _SETUP
 
 #include <asm/espfix.h>
+#include <linux/kernel.h>
 
 /*
  * This is set up by the setup-routine at boot-time
  */
 extern struct boot_params boot_params;
+extern char _text[];
 
 static inline bool kaslr_enabled(void)
 {
 	return !!(boot_params.hdr.loadflags & KASLR_FLAG);
 }
 
+static inline unsigned long kaslr_offset(void)
+{
+	return (unsigned long)&_text - __START_KERNEL;
+}
+
 /*
  * Do NOT EVER look at the BIOS memory size location.
  * It does not work on many machines.
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index ee80b92f0096..6c8a7ed13365 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,5 +1,5 @@
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * may_use_simd - whether it is allowable at this time to issue SIMD
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 17a8dced12da..222a6a3ca2b5 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
-static inline struct cpumask *cpu_sibling_mask(int cpu)
-{
-	return per_cpu(cpu_sibling_map, cpu);
-}
-
-static inline struct cpumask *cpu_core_mask(int cpu)
-{
-	return per_cpu(cpu_core_map, cpu);
-}
-
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return per_cpu(cpu_llc_shared_map, cpu);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index aeb4666e0c0a..2270e41b32fd 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -215,6 +215,44 @@ static inline void clwb(volatile void *__p)
 		: [pax] "a" (p));
 }
 
+/**
+ * pcommit_sfence() - persistent commit and fence
+ *
+ * The PCOMMIT instruction ensures that data that has been flushed from the
+ * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
+ * memory and is durable on the DIMM.  The primary use case for this is
+ * persistent memory.
+ *
+ * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
+ * with appropriate fencing.
+ *
+ * Example:
+ * void flush_and_commit_buffer(void *vaddr, unsigned int size)
+ * {
+ *         unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+ *         void *vend = vaddr + size;
+ *         void *p;
+ *
+ *         for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+ *              p < vend; p += boot_cpu_data.x86_clflush_size)
+ *                 clwb(p);
+ *
+ *         // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
+ *         // MFENCE via mb() also works
+ *         wmb();
+ *
+ *         // PCOMMIT and the required SFENCE for ordering
+ *         pcommit_sfence();
+ * }
+ *
+ * After this function completes the data pointed to by 'vaddr' has been
+ * accepted to memory and will be durable if the 'vaddr' points to persistent
+ * memory.
+ *
+ * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
+ * things we include both the PCOMMIT and the required SFENCE in the
+ * alternatives generated by pcommit_sfence().
+ */
 static inline void pcommit_sfence(void)
 {
 	alternative(ASM_NOP7,
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index cf87de3fc390..be0a05913b91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
 extern struct static_key paravirt_ticketlocks_enabled;
 static __always_inline bool static_key_false(struct static_key *key);
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#else
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 
 static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -169,7 +173,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 	struct __raw_tickets tmp = READ_ONCE(lock->tickets);
 
 	tmp.head &= ~TICKET_SLOWPATH_FLAG;
-	return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
+	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
 #define arch_spin_is_contended	arch_spin_is_contended
 
@@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 		cpu_relax();
 	}
 }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 /*
  * Read-write spinlocks, allowing multiple readers
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 5f9d7572d82b..65c3e37f879a 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm-generic/qspinlock_types.h>
+#else
 typedef struct arch_spinlock {
 	union {
 		__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
 } arch_spinlock_t;
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 #include <asm-generic/qrwlock_types.h>
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 6a998598f172..c2e00bb2a136 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -39,7 +39,9 @@
 #include <asm/processor.h>
 #include <asm/percpu.h>
 #include <asm/desc.h>
+
 #include <linux/random.h>
+#include <linux/sched.h>
 
 /*
  * 24 byte read-only segment initializer for stack canary.  Linker
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 552d6c90a6d4..d1793f06854d 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_32_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /* image of the saved processor state */
 struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index bc6232834bab..7ebf0ebe4e68 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -7,7 +7,7 @@
 #define _ASM_X86_SUSPEND_64_H
 
 #include <asm/desc.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b4bdec3e9523..225ee545e1a0 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -177,8 +177,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-DECLARE_PER_CPU(unsigned long, kernel_stack);
-
 static inline struct thread_info *current_thread_info(void)
 {
 	return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
@@ -197,9 +195,13 @@ static inline unsigned long current_stack_pointer(void)
 
 #else /* !__ASSEMBLY__ */
 
+#ifdef CONFIG_X86_64
+# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+#endif
+
 /* Load thread_info address into "reg" */
 #define GET_THREAD_INFO(reg) \
-	_ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+	_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
 	_ASM_SUB $(THREAD_SIZE),reg ;
 
 /*
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 0e8f04f2c26f..0fb46482dfde 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -26,7 +26,7 @@
 #define _ASM_X86_TOPOLOGY_H
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
 #  define ENABLE_TOPO_DEFINES
 # endif
 #else
@@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 4cab890007a7..38a09a13a9bc 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -101,6 +101,12 @@ DEFINE_IRQ_VECTOR_EVENT(call_function_single);
 DEFINE_IRQ_VECTOR_EVENT(threshold_apic);
 
 /*
+ * deferred_error_apic - called when entering/exiting a deferred apic interrupt
+ * vector handler
+ */
+DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
+
+/*
  * thermal_apic - called when entering/exiting a thermal apic interrupt
  * vector handler
  */
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
new file mode 100644
index 000000000000..173dd3ba108c
--- /dev/null
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -0,0 +1,132 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mpx
+
+#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MPX_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_X86_INTEL_MPX
+
+TRACE_EVENT(mpx_bounds_register_exception,
+
+	TP_PROTO(void *addr_referenced,
+		 const struct bndreg *bndreg),
+	TP_ARGS(addr_referenced, bndreg),
+
+	TP_STRUCT__entry(
+		__field(void *, addr_referenced)
+		__field(u64, lower_bound)
+		__field(u64, upper_bound)
+	),
+
+	TP_fast_assign(
+		__entry->addr_referenced = addr_referenced;
+		__entry->lower_bound = bndreg->lower_bound;
+		__entry->upper_bound = bndreg->upper_bound;
+	),
+	/*
+	 * Note that we are printing out the '~' of the upper
+	 * bounds register here.  It is actually stored in its
+	 * one's complement form so that its 'init' state
+	 * corresponds to all 0's.  But, that looks like
+	 * gibberish when printed out, so print out the 1's
+	 * complement instead of the actual value here.  Note
+	 * though that you still need to specify filters for the
+	 * actual value, not the displayed one.
+	 */
+	TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
+		__entry->addr_referenced,
+		__entry->lower_bound,
+		~__entry->upper_bound
+	)
+);
+
+TRACE_EVENT(bounds_exception_mpx,
+
+	TP_PROTO(const struct bndcsr *bndcsr),
+	TP_ARGS(bndcsr),
+
+	TP_STRUCT__entry(
+		__field(u64, bndcfgu)
+		__field(u64, bndstatus)
+	),
+
+	TP_fast_assign(
+		/* need to get rid of the 'const' on bndcsr */
+		__entry->bndcfgu   = (u64)bndcsr->bndcfgu;
+		__entry->bndstatus = (u64)bndcsr->bndstatus;
+	),
+
+	TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
+		__entry->bndcfgu,
+		__entry->bndstatus)
+);
+
+DECLARE_EVENT_CLASS(mpx_range_trace,
+
+	TP_PROTO(unsigned long start,
+		 unsigned long end),
+	TP_ARGS(start, end),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, start)
+		__field(unsigned long, end)
+	),
+
+	TP_fast_assign(
+		__entry->start = start;
+		__entry->end   = end;
+	),
+
+	TP_printk("[0x%p:0x%p]",
+		(void *)__entry->start,
+		(void *)__entry->end
+	)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
+	TP_PROTO(unsigned long start, unsigned long end),
+	TP_ARGS(start, end)
+);
+
+TRACE_EVENT(mpx_new_bounds_table,
+
+	TP_PROTO(unsigned long table_vaddr),
+	TP_ARGS(table_vaddr),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, table_vaddr)
+	),
+
+	TP_fast_assign(
+		__entry->table_vaddr = table_vaddr;
+	),
+
+	TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
+);
+
+#else
+
+/*
+ * This gets used outside of MPX-specific code, so we need a stub.
+ */
+static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+{
+}
+
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mpx
+#endif /* _TRACE_MPX_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 4e49d7dff78e..c5380bea2a36 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -108,7 +108,8 @@ extern int panic_on_unrecovered_nmi;
 void math_emulate(struct math_emu_info *);
 #ifndef CONFIG_X86_32
 asmlinkage void smp_thermal_interrupt(void);
-asmlinkage void mce_threshold_interrupt(void);
+asmlinkage void smp_threshold_interrupt(void);
+asmlinkage void smp_deferred_error_interrupt(void);
 #endif
 
 extern enum ctx_state ist_enter(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index ace9dec050b1..a8df874f3e88 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -74,7 +74,8 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  * @addr: User space pointer to start of block to check
  * @size: Size of block to check
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Checks if a pointer to a block of memory in user space is valid.
  *
@@ -145,7 +146,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -240,7 +242,8 @@ extern void __put_user_8(void);
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
@@ -455,7 +458,8 @@ struct __large_struct { unsigned long buf[100]; };
  * @x:   Variable to store result.
  * @ptr: Source address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple variable from user space to kernel
  * space.  It supports simple types like char and int, but not larger
@@ -479,7 +483,8 @@ struct __large_struct { unsigned long buf[100]; };
  * @x:   Value to copy to user space.
  * @ptr: Destination address, in user space.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * This macro copies a single simple value from kernel space to user
  * space.  It supports simple types like char and int, but not larger
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 3c03a5de64d3..f5dcb5204dcd 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -59,6 +59,10 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
 			return ret;
+		case 8:
+			__put_user_size(*(u64 *)from, (u64 __user *)to,
+					8, ret, 8);
+			return ret;
 		}
 	}
 	return __copy_to_user_ll(to, from, n);
@@ -70,7 +74,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.  Caller must check
  * the specified block with access_ok() before calling this function.
@@ -117,7 +122,8 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.  Caller must check
  * the specified block with access_ok() before calling this function.
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index ccab4af1646d..59a54e869f15 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -14,8 +14,8 @@ struct user_ymmh_regs {
 	__u32 ymmh_space[64];
 };
 
-struct user_xsave_hdr {
-	__u64 xstate_bv;
+struct user_xstate_header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -41,11 +41,11 @@ struct user_xsave_hdr {
  * particular process/thread.
  *
  * Also when the user modifies certain state FP/SSE/etc through the
- * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * ptrace interface, they must ensure that the header.xfeatures
  * bytes[512..519] of the memory layout are updated correspondingly.
  * i.e., for example when FP state is modified to a non-init state,
- * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
- * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ * header.xfeatures's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, header.xfeatures's bit 1 must to be set to '1', etc.
  */
 #define USER_XSTATE_FX_SW_WORDS 6
 #define USER_XSTATE_XCR0_WORD	0
@@ -55,7 +55,7 @@ struct user_xstateregs {
 		__u64 fpx_space[58];
 		__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
 	} i387;
-	struct user_xsave_hdr xsave_hdr;
+	struct user_xstate_header header;
 	struct user_ymmh_regs ymmh;
 	/* further processor state extensions go here */
 };
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index f58a9c7a3c86..48d34d28f5a6 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -171,38 +171,17 @@ struct x86_platform_ops {
 };
 
 struct pci_dev;
-struct msi_msg;
 
 struct x86_msi_ops {
 	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
-	void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq,
-				unsigned int dest, struct msi_msg *msg,
-			       u8 hpet_id);
 	void (*teardown_msi_irq)(unsigned int irq);
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev);
-	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
 };
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
-struct irq_data;
-struct cpumask;
-
 struct x86_io_apic_ops {
-	void		(*init)   (void);
 	unsigned int	(*read)   (unsigned int apic, unsigned int reg);
-	void		(*write)  (unsigned int apic, unsigned int reg, unsigned int value);
-	void		(*modify) (unsigned int apic, unsigned int reg, unsigned int value);
 	void		(*disable)(void);
-	void		(*print_entries)(unsigned int apic, unsigned int nr_entries);
-	int		(*set_affinity)(struct irq_data *data,
-					const struct cpumask *mask,
-					bool force);
-	int		(*setup_entry)(int irq, struct IO_APIC_route_entry *entry,
-				       unsigned int destination, int vector,
-				       struct io_apic_irq_attr *attr);
-	void		(*eoi_ioapic_pin)(int apic, int pin, int vector);
 };
 
 extern struct x86_init_ops x86_init;
diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h
deleted file mode 100644
index f2cba4e79a23..000000000000
--- a/arch/x86/include/asm/xcr.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2 or (at your
- *   option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK	0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
-	u32 eax, edx;
-
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
-	return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
-	u32 eax = value;
-	u32 edx = value >> 32;
-
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 358dcd338915..c44a5d53e464 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -269,4 +269,9 @@ static inline bool xen_arch_need_swiotlb(struct device *dev,
 	return false;
 }
 
+static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+{
+	return __get_free_pages(__GFP_NOWARN, order);
+}
+
 #endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index d8829751b3f8..1f5c5161ead6 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -36,7 +36,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #ifdef CONFIG_X86_32
 /* reduce register pressure */
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index ce05722e3c68..5a08bc8bff33 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -26,7 +26,7 @@
 #define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
 #define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 static void
 xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 492b29802f57..7c0a517ec751 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -18,7 +18,7 @@
 #ifdef CONFIG_AS_AVX
 
 #include <linux/compiler.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
deleted file mode 100644
index c9a6d68b8d62..000000000000
--- a/arch/x86/include/asm/xsave.h
+++ /dev/null
@@ -1,257 +0,0 @@
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-
-#define XSTATE_CPUID		0x0000000d
-
-#define XSTATE_FP		0x1
-#define XSTATE_SSE		0x2
-#define XSTATE_YMM		0x4
-#define XSTATE_BNDREGS		0x8
-#define XSTATE_BNDCSR		0x10
-#define XSTATE_OPMASK		0x20
-#define XSTATE_ZMM_Hi256	0x40
-#define XSTATE_Hi16_ZMM		0x80
-
-#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512	(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-/* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
-
-#define FXSAVE_SIZE	512
-
-#define XSAVE_HDR_SIZE	    64
-#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
-
-#define XSAVE_YMM_SIZE	    256
-#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
-
-/* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
-			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
-
-/* Supported features which require eager state saving */
-#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
-
-/* All currently supported features */
-#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern unsigned int xstate_size;
-extern u64 pcntxt_mask;
-extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern struct xsave_struct *init_xstate_buf;
-
-extern void xsave_init(void);
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
-extern int init_fpu(struct task_struct *child);
-
-/* These macros all use (%edi)/(%rdi) as the single memory argument. */
-#define XSAVE		".byte " REX_PREFIX "0x0f,0xae,0x27"
-#define XSAVEOPT	".byte " REX_PREFIX "0x0f,0xae,0x37"
-#define XSAVES		".byte " REX_PREFIX "0x0f,0xc7,0x2f"
-#define XRSTOR		".byte " REX_PREFIX "0x0f,0xae,0x2f"
-#define XRSTORS		".byte " REX_PREFIX "0x0f,0xc7,0x1f"
-
-#define xstate_fault	".section .fixup,\"ax\"\n"	\
-			"3:  movl $-1,%[err]\n"		\
-			"    jmp  2b\n"			\
-			".previous\n"			\
-			_ASM_EXTABLE(1b, 3b)		\
-			: [err] "=r" (err)
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XSAVES"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XSAVE"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * This function is called only during boot time when x86 caps are not set
- * up and alternative can not be used yet.
- */
-static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	WARN_ON(system_state != SYSTEM_BOOTING);
-
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		asm volatile("1:"XRSTORS"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	else
-		asm volatile("1:"XRSTOR"\n\t"
-			"2:\n\t"
-			     xstate_fault
-			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-			:   "memory");
-	return err;
-}
-
-/*
- * Save processor xstate to xsave area.
- */
-static inline int xsave_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-	int err = 0;
-
-	/*
-	 * If xsaves is enabled, xsaves replaces xsaveopt because
-	 * it supports compact format and supervisor states in addition to
-	 * modified optimization in xsaveopt.
-	 *
-	 * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave
-	 * because xsaveopt supports modified optimization which is not
-	 * supported by xsave.
-	 *
-	 * If none of xsaves and xsaveopt is enabled, use xsave.
-	 */
-	alternative_input_2(
-		"1:"XSAVE,
-		XSAVEOPT,
-		X86_FEATURE_XSAVEOPT,
-		XSAVES,
-		X86_FEATURE_XSAVES,
-		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
-		"memory");
-	asm volatile("2:\n\t"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Restore processor xstate from xsave area.
- */
-static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	int err = 0;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	/*
-	 * Use xrstors to restore context if it is enabled. xrstors supports
-	 * compacted format of xsave area which is not supported by xrstor.
-	 */
-	alternative_input(
-		"1: " XRSTOR,
-		XRSTORS,
-		X86_FEATURE_XSAVES,
-		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		: "memory");
-
-	asm volatile("2:\n"
-		     xstate_fault
-		     : "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-/*
- * Save xstate context for old process during context switch.
- */
-static inline void fpu_xsave(struct fpu *fpu)
-{
-	xsave_state(&fpu->state->xsave, -1);
-}
-
-/*
- * Restore xstate context for new process during context switch.
- */
-static inline int fpu_xrstor_checking(struct xsave_struct *fx)
-{
-	return xrstor_state(fx, -1);
-}
-
-/*
- * Save xstate to user space xsave area.
- *
- * We don't use modified optimization because xrstor/xrstors might track
- * a different application.
- *
- * We don't use compacted format xsave area for
- * backward compatibility for old applications which don't understand
- * compacted format of xsave area.
- */
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
-	int err;
-
-	/*
-	 * Clear the xsave header first, so that reserved fields are
-	 * initialized to zero.
-	 */
-	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
-	if (unlikely(err))
-		return -EFAULT;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XSAVE"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
-			     : "memory");
-	return err;
-}
-
-/*
- * Restore xstate from user space xsave area.
- */
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
-	int err = 0;
-	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	__asm__ __volatile__(ASM_STAC "\n"
-			     "1:"XRSTOR"\n"
-			     "2: " ASM_CLAC "\n"
-			     xstate_fault
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
-			     : "memory");	/* memory required? */
-	return err;
-}
-
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate);
-void setup_xstate_comp(void);
-
-#endif
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d7dcef58aefa..a4ae82eb82aa 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -106,6 +106,8 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_IOAPIC       2
 #define KVM_NR_IRQCHIPS          3
 
+#define KVM_RUN_X86_SMM		 (1 << 0)
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
@@ -281,6 +283,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+#define KVM_VCPUEVENT_VALID_SMM		0x00000008
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -309,7 +312,13 @@ struct kvm_vcpu_events {
 	} nmi;
 	__u32 sipi_vector;
 	__u32 flags;
-	__u32 reserved[10];
+	struct {
+		__u8 smm;
+		__u8 pending;
+		__u8 smm_inside_nmi;
+		__u8 latched_init;
+	} smi;
+	__u32 reserved[9];
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
@@ -345,4 +354,7 @@ struct kvm_xcrs {
 struct kvm_sync_regs {
 };
 
+#define KVM_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_QUIRK_CD_NW_CLEARED		(1 << 1)
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index 155e51048fa4..c41f4fe25483 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -1,8 +1,6 @@
 #ifndef _UAPI_ASM_X86_MSR_H
 #define _UAPI_ASM_X86_MSR_H
 
-#include <asm/msr-index.h>
-
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h
index d0acb658c8f4..7528dcf59691 100644
--- a/arch/x86/include/uapi/asm/mtrr.h
+++ b/arch/x86/include/uapi/asm/mtrr.h
@@ -103,7 +103,7 @@ struct mtrr_state_type {
 #define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
 #define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
 
-/*  These are the region types  */
+/* MTRR memory types, which are defined in SDM */
 #define MTRR_TYPE_UNCACHABLE 0
 #define MTRR_TYPE_WRCOMB     1
 /*#define MTRR_TYPE_         2*/
@@ -113,5 +113,11 @@ struct mtrr_state_type {
 #define MTRR_TYPE_WRBACK     6
 #define MTRR_NUM_TYPES       7
 
+/*
+ * Invalid MTRR memory type.  mtrr_type_lookup() returns this value when
+ * MTRRs are disabled.  Note, this value is allocated from the reserved
+ * values (0x7-0xff) of the MTRR memory types.
+ */
+#define MTRR_TYPE_INVALID    0xff
 
 #endif /* _UAPI_ASM_X86_MTRR_H */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 16dc4e8a2cd3..0e8a973de9ee 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -25,7 +25,7 @@ struct _fpx_sw_bytes {
 	__u32 extended_size;	/* total size of the layout referred by
 				 * fpstate pointer in the sigcontext.
 				 */
-	__u64 xstate_bv;
+	__u64 xfeatures;
 				/* feature bit mask (including fp/sse/extended
 				 * state) that is present in the memory
 				 * layout.
@@ -209,8 +209,8 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
-struct _xsave_hdr {
-	__u64 xstate_bv;
+struct _header {
+	__u64 xfeatures;
 	__u64 reserved1[2];
 	__u64 reserved2[5];
 };
@@ -228,7 +228,7 @@ struct _ymmh_state {
  */
 struct _xstate {
 	struct _fpstate fpstate;
-	struct _xsave_hdr xstate_hdr;
+	struct _header xstate_hdr;
 	struct _ymmh_state ymmh;
 	/* new processor state extensions go here */
 };
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9bcd0b56ca17..0f15af41bd80 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -22,7 +22,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n
 
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
-obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
+obj-y			:= process_$(BITS).o signal.o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
@@ -31,9 +31,6 @@ obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= mcount_64.o
-obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_IA32_EMULATION)	+= syscall_32.o
-obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
@@ -44,7 +41,7 @@ obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
 obj-y				+= process.o
-obj-y				+= i387.o xsave.o
+obj-y				+= fpu/
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index dbe76a14c3c9..e49ee24da85e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,12 +31,12 @@
 #include <linux/module.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
-#include <linux/irqdomain.h>
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
 
+#include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
@@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
 	return 0;
 }
 
-static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
-			   int polarity)
-{
-	int irq, node;
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return gsi;
-
-	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
-	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
-	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
-	if (mp_set_gsi_attr(gsi, trigger, polarity, node)) {
-		pr_warn("Failed to set pin attr for GSI%d\n", gsi);
-		return -1;
-	}
-
-	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
-	if (irq < 0)
-		return irq;
-
-	/* Don't set up the ACPI SCI because it's already set up */
-	if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
-		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
-
-	return irq;
-}
-
-static void mp_unregister_gsi(u32 gsi)
-{
-	int irq;
-
-	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
-		return;
-
-	irq = mp_map_gsi_to_irq(gsi, 0);
-	if (irq > 0)
-		mp_unmap_irq(irq);
-}
-
-static struct irq_domain_ops acpi_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-};
-
 static int __init
 acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 {
 	struct acpi_madt_io_apic *ioapic = NULL;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_DYNAMIC,
-		.ops = &acpi_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	ioapic = (struct acpi_madt_io_apic *)header;
@@ -652,7 +608,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi,
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (trigger == ACPI_LEVEL_SENSITIVE)
-		eisa_set_level_irq(gsi);
+		elcr_set_level_irq(gsi);
 #endif
 
 	return gsi;
@@ -663,10 +619,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 				    int trigger, int polarity)
 {
 	int irq = gsi;
-
 #ifdef CONFIG_X86_IO_APIC
+	int node;
+	struct irq_alloc_info info;
+
+	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
+	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
+	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
+	ioapic_set_alloc_attr(&info, node, trigger, polarity);
+
 	mutex_lock(&acpi_ioapic_lock);
-	irq = mp_register_gsi(dev, gsi, trigger, polarity);
+	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+	/* Don't set up the ACPI SCI because it's already set up */
+	if (irq >= 0 && enable_update_mptable &&
+	    acpi_gbl_FADT.sci_interrupt != gsi)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 	mutex_unlock(&acpi_ioapic_lock);
 #endif
 
@@ -676,8 +643,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 static void acpi_unregister_gsi_ioapic(u32 gsi)
 {
 #ifdef CONFIG_X86_IO_APIC
+	int irq;
+
 	mutex_lock(&acpi_ioapic_lock);
-	mp_unregister_gsi(gsi);
+	irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+	if (irq > 0)
+		mp_unmap_irq(irq);
 	mutex_unlock(&acpi_ioapic_lock);
 #endif
 }
@@ -786,7 +757,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 	u64 addr;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_DYNAMIC,
-		.ops = &acpi_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 665c6b7d2ea9..0c26b1b44e51 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return)
 wakeup_pmode_return:
 	movw	$__KERNEL_DS, %ax
 	movw	%ax, %ss
-	movw	%ax, %ds
-	movw	%ax, %es
 	movw	%ax, %fs
 	movw	%ax, %gs
 
+	movw	$__USER_DS, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
 	# reload the gdt, as we need the full 32 bit address
 	lidt	saved_idt
 	lldt	saved_ldt
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index ae693b51ed8e..8c35df468104 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	movq	$resume_point, saved_rip(%rip)
+	movq	$.Lresume_point, saved_rip(%rip)
 
 	movq	%rsp, saved_rsp
 	movq	%rbp, saved_rbp
@@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel)
 	xorl	%eax, %eax
 	call	x86_acpi_enter_sleep_state
 	/* in case something went wrong, restore the machine status and go on */
-	jmp	resume_point
+	jmp	.Lresume_point
 
 	.align 4
-resume_point:
+.Lresume_point:
 	/* We don't restore %rax, it must be 0 anyway */
 	movq	$saved_context, %rax
 	movq	saved_context_cr4(%rax), %rbx
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index aef653193160..c42827eb86cf 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -21,6 +21,10 @@
 #include <asm/io.h>
 #include <asm/fixmap.h>
 
+int __read_mostly alternatives_patched;
+
+EXPORT_SYMBOL_GPL(alternatives_patched);
+
 #define MAX_PATCH_LEN (255-1)
 
 static int __initdata_or_module debug_alternative;
@@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void)
 #endif
 		}
 		break;
+
+	case X86_VENDOR_AMD:
+		if (boot_cpu_data.x86 > 0xf) {
+			ideal_nops = p6_nops;
+			return;
+		}
+
+		/* fall through */
+
 	default:
 #ifdef CONFIG_X86_64
 		ideal_nops = k8_nops;
@@ -627,6 +640,7 @@ void __init alternative_instructions(void)
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
 	restart_nmi();
+	alternatives_patched = 1;
 }
 
 /**
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 5caed1dd7ccf..29fa475ec518 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -89,9 +89,7 @@ int amd_cache_northbridges(void)
 			next_northbridge(link, amd_nb_link_ids);
 	}
 
-	/* GART present only on Fam15h upto model 0fh */
-	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
+	if (amd_gart_present())
 		amd_northbridges.flags |= AMD_NB_GART;
 
 	/*
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 6a7c23ff21d3..ede92c3364d3 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void)
 
 static void apbt_setup_irq(struct apbt_dev *adev)
 {
-	/* timer0 irq has been setup early */
-	if (adev->irq == 0)
-		return;
-
 	irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
 	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
 }
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 76164e173a24..6e85f713641d 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void)
 	u64 aper_base = 0, last_aper_base = 0;
 	int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0;
 
+	if (!amd_gart_present())
+		return;
+
 	if (!early_pci_allowed())
 		return;
 
@@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void)
 	int fix, slot, valid_agp = 0;
 	int i, node;
 
+	if (!amd_gart_present())
+		return -ENODEV;
+
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
 		return -ENODEV;
@@ -452,7 +458,7 @@ out:
 		   force_iommu ||
 		   valid_agp ||
 		   fallback_aper_force) {
-		pr_info("Your BIOS doesn't leave a aperture memory hole\n");
+		pr_info("Your BIOS doesn't leave an aperture memory hole\n");
 		pr_info("Please enable the IOMMU option in the BIOS setup\n");
 		pr_info("This costs you %dMB of RAM\n",
 			32 << fallback_aper_order);
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
index 816f36e979ad..ae50d3454d78 100644
--- a/arch/x86/kernel/apic/htirq.c
+++ b/arch/x86/kernel/apic/htirq.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Add support of hierarchical irqdomain
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,78 +16,112 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/htirq.h>
+#include <asm/irqdomain.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/hypertransport.h>
 
+static struct irq_domain *htirq_domain;
+
 /*
  * Hypertransport interrupt support
  */
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
-	struct ht_irq_msg msg;
-
-	fetch_ht_irq_msg(irq, &msg);
-
-	msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
-	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
-	msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
-	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
-	write_ht_irq_msg(irq, &msg);
-}
-
 static int
 ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest;
+	struct irq_data *parent = data->parent_data;
 	int ret;
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	target_ht_irq(data->irq, dest, cfg->vector);
-	return IRQ_SET_MASK_OK_NOCOPY;
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret >= 0) {
+		struct ht_irq_msg msg;
+		struct irq_cfg *cfg = irqd_cfg(data);
+
+		fetch_ht_irq_msg(data->irq, &msg);
+		msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
+				    HT_IRQ_LOW_DEST_ID_MASK);
+		msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
+				  HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
+		msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+		msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
+		write_ht_irq_msg(data->irq, &msg);
+	}
+
+	return ret;
 }
 
 static struct irq_chip ht_irq_chip = {
 	.name			= "PCI-HT",
 	.irq_mask		= mask_ht_irq,
 	.irq_unmask		= unmask_ht_irq,
-	.irq_ack		= apic_ack_edge,
+	.irq_ack		= irq_chip_ack_parent,
 	.irq_set_affinity	= ht_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
 {
-	struct irq_cfg *cfg;
-	struct ht_irq_msg msg;
-	unsigned dest;
-	int err;
+	struct ht_irq_cfg *ht_cfg;
+	struct irq_alloc_info *info = arg;
+	struct pci_dev *dev;
+	irq_hw_number_t hwirq;
+	int ret;
 
-	if (disable_apic)
-		return -ENXIO;
+	if (nr_irqs > 1 || !info)
+		return -EINVAL;
 
-	cfg = irq_cfg(irq);
-	err = assign_irq_vector(irq, cfg, apic->target_cpus());
-	if (err)
-		return err;
+	dev = info->ht_dev;
+	hwirq = (info->ht_idx & 0xFF) |
+		PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
+		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
+	if (irq_find_mapping(domain, hwirq) > 0)
+		return -EEXIST;
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain,
-					   apic->target_cpus(), &dest);
-	if (err)
-		return err;
+	ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
+	if (!ht_cfg)
+		return -ENOMEM;
 
-	msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+	if (ret < 0) {
+		kfree(ht_cfg);
+		return ret;
+	}
+
+	/* Initialize msg to a value that will never match the first write. */
+	ht_cfg->msg.address_lo = 0xffffffff;
+	ht_cfg->msg.address_hi = 0xffffffff;
+	ht_cfg->dev = info->ht_dev;
+	ht_cfg->update = info->ht_update;
+	ht_cfg->pos = info->ht_pos;
+	ht_cfg->idx = 0x10 + (info->ht_idx * 2);
+	irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
+			    handle_edge_irq, ht_cfg, "edge");
+
+	return 0;
+}
+
+static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs)
+{
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+	BUG_ON(nr_irqs != 1);
+	kfree(irq_data->chip_data);
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
 
+static void htirq_domain_activate(struct irq_domain *domain,
+				  struct irq_data *irq_data)
+{
+	struct ht_irq_msg msg;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+	msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
 	msg.address_lo =
 		HT_IRQ_LOW_BASE |
-		HT_IRQ_LOW_DEST_ID(dest) |
+		HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
 		HT_IRQ_LOW_VECTOR(cfg->vector) |
 		((apic->irq_dest_mode == 0) ?
 			HT_IRQ_LOW_DM_PHYSICAL :
@@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 			HT_IRQ_LOW_MT_FIXED :
 			HT_IRQ_LOW_MT_ARBITRATED) |
 		HT_IRQ_LOW_IRQ_MASKED;
+	write_ht_irq_msg(irq_data->irq, &msg);
+}
 
-	write_ht_irq_msg(irq, &msg);
+static void htirq_domain_deactivate(struct irq_domain *domain,
+				    struct irq_data *irq_data)
+{
+	struct ht_irq_msg msg;
 
-	irq_set_chip_and_handler_name(irq, &ht_irq_chip,
-				      handle_edge_irq, "edge");
+	memset(&msg, 0, sizeof(msg));
+	write_ht_irq_msg(irq_data->irq, &msg);
+}
 
-	dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+static const struct irq_domain_ops htirq_domain_ops = {
+	.alloc		= htirq_domain_alloc,
+	.free		= htirq_domain_free,
+	.activate	= htirq_domain_activate,
+	.deactivate	= htirq_domain_deactivate,
+};
 
-	return 0;
+void arch_init_htirq_domain(struct irq_domain *parent)
+{
+	if (disable_apic)
+		return;
+
+	htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL);
+	if (!htirq_domain)
+		pr_warn("failed to initialize irqdomain for HTIRQ.\n");
+	else
+		htirq_domain->parent = parent;
+}
+
+int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
+		      ht_irq_update_t *update)
+{
+	struct irq_alloc_info info;
+
+	if (!htirq_domain)
+		return -ENOSYS;
+
+	init_irq_alloc_info(&info, NULL);
+	info.ht_idx = idx;
+	info.ht_pos = pos;
+	info.ht_dev = dev;
+	info.ht_update = update;
+
+	return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
+				     &info);
+}
+
+void arch_teardown_ht_irq(unsigned int irq)
+{
+	irq_domain_free_irqs(irq, 1);
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index f4dc2462a1ac..845dc0df2002 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -18,6 +18,16 @@
  *					and Rolf G. Tews
  *					for testing these extensively
  *	Paul Diefenbaugh	:	Added full ACPI support
+ *
+ * Historical information which is worth to be preserved:
+ *
+ * - SiS APIC rmw bug:
+ *
+ *	We used to have a workaround for a bug in SiS chips which
+ *	required to rewrite the index register for a read-modify-write
+ *	operation as the chip lost the index information which was
+ *	setup for the read already. We cache the data now, so that
+ *	workaround has been removed.
  */
 
 #include <linux/mm.h>
@@ -31,13 +41,13 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <linux/syscore_ops.h>
-#include <linux/irqdomain.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>	/* time_after() */
 #include <linux/slab.h>
 #include <linux/bootmem.h>
 
+#include <asm/irqdomain.h>
 #include <asm/idle.h>
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -63,27 +73,31 @@
 #define	for_each_ioapic_pin(idx, pin)	\
 	for_each_ioapic((idx))		\
 		for_each_pin((idx), (pin))
-
 #define for_each_irq_pin(entry, head) \
 	list_for_each_entry(entry, &head, list)
 
-/*
- *      Is the SiS APIC rmw bug present ?
- *      -1 = don't know, 0 = no, 1 = yes
- */
-int sis_apic_bug = -1;
-
 static DEFINE_RAW_SPINLOCK(ioapic_lock);
 static DEFINE_MUTEX(ioapic_mutex);
 static unsigned int ioapic_dynirq_base;
 static int ioapic_initialized;
 
-struct mp_pin_info {
+struct irq_pin_list {
+	struct list_head list;
+	int apic, pin;
+};
+
+struct mp_chip_data {
+	struct list_head irq_2_pin;
+	struct IO_APIC_route_entry entry;
 	int trigger;
 	int polarity;
-	int node;
-	int set;
 	u32 count;
+	bool isa_irq;
+};
+
+struct mp_ioapic_gsi {
+	u32 gsi_base;
+	u32 gsi_end;
 };
 
 static struct ioapic {
@@ -101,7 +115,6 @@ static struct ioapic {
 	struct mp_ioapic_gsi  gsi_config;
 	struct ioapic_domain_cfg irqdomain_cfg;
 	struct irq_domain *irqdomain;
-	struct mp_pin_info *pin_info;
 	struct resource *iomem_res;
 } ioapics[MAX_IO_APICS];
 
@@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx)
 	return ioapics[ioapic_idx].mp_config.apicaddr;
 }
 
-struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
+static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx)
 {
 	return &ioapics[ioapic_idx].gsi_config;
 }
@@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic)
 	return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
 }
 
-u32 mp_pin_to_gsi(int ioapic, int pin)
+static inline u32 mp_pin_to_gsi(int ioapic, int pin)
 {
 	return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin;
 }
 
+static inline bool mp_is_legacy_irq(int irq)
+{
+	return irq >= 0 && irq < nr_legacy_irqs();
+}
+
 /*
  * Initialize all legacy IRQs and all pins on the first IOAPIC
  * if we have legacy interrupt controller. Kernel boot option "pirq="
@@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq)
 	if (!nr_legacy_irqs())
 		return 0;
 
-	return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs());
-}
-
-static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin)
-{
-	return ioapics[ioapic_idx].pin_info + pin;
+	return ioapic == 0 || mp_is_legacy_irq(irq);
 }
 
 static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic)
@@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m)
 		panic("Max # of irq sources exceeded!!\n");
 }
 
-struct irq_pin_list {
-	struct list_head list;
-	int apic, pin;
-};
-
-static struct irq_pin_list *alloc_irq_pin_list(int node)
-{
-	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
-}
-
 static void alloc_ioapic_saved_registers(int idx)
 {
 	size_t size;
@@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx)
 
 int __init arch_early_ioapic_init(void)
 {
-	struct irq_cfg *cfg;
-	int i, node = cpu_to_node(0);
+	int i;
 
 	if (!nr_legacy_irqs())
 		io_apic_irqs = ~0UL;
@@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void)
 	for_each_ioapic(i)
 		alloc_ioapic_saved_registers(i);
 
-	/*
-	 * For legacy IRQ's, start with assigning irq0 to irq15 to
-	 * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's.
-	 */
-	for (i = 0; i < nr_legacy_irqs(); i++) {
-		cfg = alloc_irq_and_cfg_at(i, node);
-		cfg->vector = IRQ0_VECTOR + i;
-		cpumask_setall(cfg->domain);
-	}
-
 	return 0;
 }
 
@@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
 		+ (mpc_ioapic_addr(idx) & ~PAGE_MASK);
 }
 
-void io_apic_eoi(unsigned int apic, unsigned int vector)
+static inline void io_apic_eoi(unsigned int apic, unsigned int vector)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 	writel(vector, &io_apic->eoi);
@@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg)
 	return readl(&io_apic->data);
 }
 
-void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+static void io_apic_write(unsigned int apic, unsigned int reg,
+			  unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
 
@@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu
 	writel(value, &io_apic->data);
 }
 
-/*
- * Re-write a value: to be used for read-modify-write
- * cycles where the read already set up the index register.
- *
- * Older SiS APIC requires we rewrite the index register
- */
-void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
-{
-	struct io_apic __iomem *io_apic = io_apic_base(apic);
-
-	if (sis_apic_bug)
-		writel(reg, &io_apic->index);
-	writel(value, &io_apic->data);
-}
-
 union entry_union {
 	struct { u32 w1, w2; };
 	struct IO_APIC_route_entry entry;
@@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 static void ioapic_mask_entry(int apic, int pin)
 {
 	unsigned long flags;
-	union entry_union eu = { .entry.mask = 1 };
+	union entry_union eu = { .entry.mask = IOAPIC_MASKED };
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
@@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin)
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
-static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static int __add_pin_to_irq_node(struct mp_chip_data *data,
+				 int node, int apic, int pin)
 {
 	struct irq_pin_list *entry;
 
 	/* don't allow duplicates */
-	for_each_irq_pin(entry, cfg->irq_2_pin)
+	for_each_irq_pin(entry, data->irq_2_pin)
 		if (entry->apic == apic && entry->pin == pin)
 			return 0;
 
-	entry = alloc_irq_pin_list(node);
+	entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node);
 	if (!entry) {
 		pr_err("can not alloc irq_pin_list (%d,%d,%d)\n",
 		       node, apic, pin);
@@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
 	}
 	entry->apic = apic;
 	entry->pin = pin;
+	list_add_tail(&entry->list, &data->irq_2_pin);
 
-	list_add_tail(&entry->list, &cfg->irq_2_pin);
 	return 0;
 }
 
-static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
+static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin)
 {
 	struct irq_pin_list *tmp, *entry;
 
-	list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
+	list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list)
 		if (entry->apic == apic && entry->pin == pin) {
 			list_del(&entry->list);
 			kfree(entry);
@@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
 		}
 }
 
-static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
+static void add_pin_to_irq_node(struct mp_chip_data *data,
+				int node, int apic, int pin)
 {
-	if (__add_pin_to_irq_node(cfg, node, apic, pin))
+	if (__add_pin_to_irq_node(data, node, apic, pin))
 		panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
 /*
  * Reroute an IRQ to a different pin.
  */
-static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
+static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node,
 					   int oldapic, int oldpin,
 					   int newapic, int newpin)
 {
 	struct irq_pin_list *entry;
 
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
+	for_each_irq_pin(entry, data->irq_2_pin) {
 		if (entry->apic == oldapic && entry->pin == oldpin) {
 			entry->apic = newapic;
 			entry->pin = newpin;
@@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node,
 	}
 
 	/* old apic/pin didn't exist, so just add new ones */
-	add_pin_to_irq_node(cfg, node, newapic, newpin);
-}
-
-static void __io_apic_modify_irq(struct irq_pin_list *entry,
-				 int mask_and, int mask_or,
-				 void (*final)(struct irq_pin_list *entry))
-{
-	unsigned int reg, pin;
-
-	pin = entry->pin;
-	reg = io_apic_read(entry->apic, 0x10 + pin * 2);
-	reg &= mask_and;
-	reg |= mask_or;
-	io_apic_modify(entry->apic, 0x10 + pin * 2, reg);
-	if (final)
-		final(entry);
+	add_pin_to_irq_node(data, node, newapic, newpin);
 }
 
-static void io_apic_modify_irq(struct irq_cfg *cfg,
+static void io_apic_modify_irq(struct mp_chip_data *data,
 			       int mask_and, int mask_or,
 			       void (*final)(struct irq_pin_list *entry))
 {
+	union entry_union eu;
 	struct irq_pin_list *entry;
 
-	for_each_irq_pin(entry, cfg->irq_2_pin)
-		__io_apic_modify_irq(entry, mask_and, mask_or, final);
+	eu.entry = data->entry;
+	eu.w1 &= mask_and;
+	eu.w1 |= mask_or;
+	data->entry = eu.entry;
+
+	for_each_irq_pin(entry, data->irq_2_pin) {
+		io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1);
+		if (final)
+			final(entry);
+	}
 }
 
 static void io_apic_sync(struct irq_pin_list *entry)
@@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	readl(&io_apic->data);
 }
 
-static void mask_ioapic(struct irq_cfg *cfg)
+static void mask_ioapic_irq(struct irq_data *irq_data)
 {
+	struct mp_chip_data *data = irq_data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+	io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_ioapic_irq(struct irq_data *data)
+static void __unmask_ioapic(struct mp_chip_data *data)
 {
-	mask_ioapic(irqd_cfg(data));
+	io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL);
 }
 
-static void __unmask_ioapic(struct irq_cfg *cfg)
-{
-	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
-static void unmask_ioapic(struct irq_cfg *cfg)
+static void unmask_ioapic_irq(struct irq_data *irq_data)
 {
+	struct mp_chip_data *data = irq_data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__unmask_ioapic(cfg);
+	__unmask_ioapic(data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void unmask_ioapic_irq(struct irq_data *data)
-{
-	unmask_ioapic(irqd_cfg(data));
-}
-
 /*
  * IO-APIC versions below 0x20 don't support EOI register.
  * For the record, here is the information about various versions:
@@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data)
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
  */
-void native_eoi_ioapic_pin(int apic, int pin, int vector)
+static void __eoi_ioapic_pin(int apic, int pin, int vector)
 {
 	if (mpc_ioapic_ver(apic) >= 0x20) {
 		io_apic_eoi(apic, vector);
@@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
 		/*
 		 * Mask the entry and change the trigger mode to edge.
 		 */
-		entry1.mask = 1;
+		entry1.mask = IOAPIC_MASKED;
 		entry1.trigger = IOAPIC_EDGE;
 
 		__ioapic_write_entry(apic, pin, entry1);
@@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector)
 	}
 }
 
-void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+void eoi_ioapic_pin(int vector, struct mp_chip_data *data)
 {
-	struct irq_pin_list *entry;
 	unsigned long flags;
+	struct irq_pin_list *entry;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	for_each_irq_pin(entry, cfg->irq_2_pin)
-		x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin,
-					       cfg->vector);
+	for_each_irq_pin(entry, data->irq_2_pin)
+		__eoi_ioapic_pin(entry->apic, entry->pin, vector);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
@@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 	 * Make sure the entry is masked and re-read the contents to check
 	 * if it is a level triggered pin and if the remote-IRR is set.
 	 */
-	if (!entry.mask) {
-		entry.mask = 1;
+	if (entry.mask == IOAPIC_UNMASKED) {
+		entry.mask = IOAPIC_MASKED;
 		ioapic_write_entry(apic, pin, entry);
 		entry = ioapic_read_entry(apic, pin);
 	}
@@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 		 * doesn't clear the remote-IRR if the trigger mode is not
 		 * set to level.
 		 */
-		if (!entry.trigger) {
+		if (entry.trigger == IOAPIC_EDGE) {
 			entry.trigger = IOAPIC_LEVEL;
 			ioapic_write_entry(apic, pin, entry);
 		}
-
 		raw_spin_lock_irqsave(&ioapic_lock, flags);
-		x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector);
+		__eoi_ioapic_pin(apic, pin, entry.vector);
 		raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 	}
 
@@ -706,8 +670,8 @@ void mask_ioapic_entries(void)
 			struct IO_APIC_route_entry entry;
 
 			entry = ioapics[apic].saved_registers[pin];
-			if (!entry.mask) {
-				entry.mask = 1;
+			if (entry.mask == IOAPIC_UNMASKED) {
+				entry.mask = IOAPIC_MASKED;
 				ioapic_write_entry(apic, pin, entry);
 			}
 		}
@@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq)
 
 #endif
 
-/* ISA interrupts are always polarity zero edge triggered,
+/* ISA interrupts are always active high edge triggered,
  * when listed as conforming in the MP table. */
 
-#define default_ISA_trigger(idx)	(0)
-#define default_ISA_polarity(idx)	(0)
+#define default_ISA_trigger(idx)	(IOAPIC_EDGE)
+#define default_ISA_polarity(idx)	(IOAPIC_POL_HIGH)
 
 /* EISA interrupts are always polarity zero and can be edge or level
  * trigger depending on the ELCR value.  If an interrupt is listed as
@@ -823,53 +787,55 @@ static int EISA_ELCR(unsigned int irq)
 #define default_EISA_trigger(idx)	(EISA_ELCR(mp_irqs[idx].srcbusirq))
 #define default_EISA_polarity(idx)	default_ISA_polarity(idx)
 
-/* PCI interrupts are always polarity one level triggered,
+/* PCI interrupts are always active low level triggered,
  * when listed as conforming in the MP table. */
 
-#define default_PCI_trigger(idx)	(1)
-#define default_PCI_polarity(idx)	(1)
+#define default_PCI_trigger(idx)	(IOAPIC_LEVEL)
+#define default_PCI_polarity(idx)	(IOAPIC_POL_LOW)
 
 static int irq_polarity(int idx)
 {
 	int bus = mp_irqs[idx].srcbus;
-	int polarity;
 
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].irqflag & 3)
-	{
-		case 0: /* conforms, ie. bus-type dependent polarity */
-			if (test_bit(bus, mp_bus_not_pci))
-				polarity = default_ISA_polarity(idx);
-			else
-				polarity = default_PCI_polarity(idx);
-			break;
-		case 1: /* high active */
-		{
-			polarity = 0;
-			break;
-		}
-		case 2: /* reserved */
-		{
-			pr_warn("broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
-		case 3: /* low active */
-		{
-			polarity = 1;
-			break;
-		}
-		default: /* invalid */
-		{
-			pr_warn("broken BIOS!!\n");
-			polarity = 1;
-			break;
-		}
+	switch (mp_irqs[idx].irqflag & 0x03) {
+	case 0:
+		/* conforms to spec, ie. bus-type dependent polarity */
+		if (test_bit(bus, mp_bus_not_pci))
+			return default_ISA_polarity(idx);
+		else
+			return default_PCI_polarity(idx);
+	case 1:
+		return IOAPIC_POL_HIGH;
+	case 2:
+		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
+	case 3:
+	default: /* Pointless default required due to do gcc stupidity */
+		return IOAPIC_POL_LOW;
+	}
+}
+
+#ifdef CONFIG_EISA
+static int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+	switch (mp_bus_id_to_type[bus]) {
+	case MP_BUS_PCI:
+	case MP_BUS_ISA:
+		return trigger;
+	case MP_BUS_EISA:
+		return default_EISA_trigger(idx);
 	}
-	return polarity;
+	pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus);
+	return IOAPIC_LEVEL;
 }
+#else
+static inline int eisa_irq_trigger(int idx, int bus, int trigger)
+{
+	return trigger;
+}
+#endif
 
 static int irq_trigger(int idx)
 {
@@ -879,153 +845,227 @@ static int irq_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].irqflag>>2) & 3)
-	{
-		case 0: /* conforms, ie. bus-type dependent */
-			if (test_bit(bus, mp_bus_not_pci))
-				trigger = default_ISA_trigger(idx);
-			else
-				trigger = default_PCI_trigger(idx);
-#ifdef CONFIG_EISA
-			switch (mp_bus_id_to_type[bus]) {
-				case MP_BUS_ISA: /* ISA pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				case MP_BUS_EISA: /* EISA pin */
-				{
-					trigger = default_EISA_trigger(idx);
-					break;
-				}
-				case MP_BUS_PCI: /* PCI pin */
-				{
-					/* set before the switch */
-					break;
-				}
-				default:
-				{
-					pr_warn("broken BIOS!!\n");
-					trigger = 1;
-					break;
-				}
-			}
+	switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
+	case 0:
+		/* conforms to spec, ie. bus-type dependent trigger mode */
+		if (test_bit(bus, mp_bus_not_pci))
+			trigger = default_ISA_trigger(idx);
+		else
+			trigger = default_PCI_trigger(idx);
+		/* Take EISA into account */
+		return eisa_irq_trigger(idx, bus, trigger);
+	case 1:
+		return IOAPIC_EDGE;
+	case 2:
+		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
+	case 3:
+	default: /* Pointless default required due to do gcc stupidity */
+		return IOAPIC_LEVEL;
+	}
+}
+
+void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
+			   int trigger, int polarity)
+{
+	init_irq_alloc_info(info, NULL);
+	info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	info->ioapic_node = node;
+	info->ioapic_trigger = trigger;
+	info->ioapic_polarity = polarity;
+	info->ioapic_valid = 1;
+}
+
+#ifndef CONFIG_ACPI
+int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
 #endif
-			break;
-		case 1: /* edge */
-		{
-			trigger = 0;
-			break;
-		}
-		case 2: /* reserved */
-		{
-			pr_warn("broken BIOS!!\n");
-			trigger = 1;
-			break;
-		}
-		case 3: /* level */
-		{
-			trigger = 1;
-			break;
-		}
-		default: /* invalid */
-		{
-			pr_warn("broken BIOS!!\n");
-			trigger = 0;
-			break;
+
+static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
+				   struct irq_alloc_info *src,
+				   u32 gsi, int ioapic_idx, int pin)
+{
+	int trigger, polarity;
+
+	copy_irq_alloc_info(dst, src);
+	dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
+	dst->ioapic_pin = pin;
+	dst->ioapic_valid = 1;
+	if (src && src->ioapic_valid) {
+		dst->ioapic_node = src->ioapic_node;
+		dst->ioapic_trigger = src->ioapic_trigger;
+		dst->ioapic_polarity = src->ioapic_polarity;
+	} else {
+		dst->ioapic_node = NUMA_NO_NODE;
+		if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
+			dst->ioapic_trigger = trigger;
+			dst->ioapic_polarity = polarity;
+		} else {
+			/*
+			 * PCI interrupts are always active low level
+			 * triggered.
+			 */
+			dst->ioapic_trigger = IOAPIC_LEVEL;
+			dst->ioapic_polarity = IOAPIC_POL_LOW;
 		}
 	}
-	return trigger;
 }
 
-static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin)
+static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
+{
+	return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+}
+
+static void mp_register_handler(unsigned int irq, unsigned long trigger)
+{
+	irq_flow_handler_t hdl;
+	bool fasteoi;
+
+	if (trigger) {
+		irq_set_status_flags(irq, IRQ_LEVEL);
+		fasteoi = true;
+	} else {
+		irq_clear_status_flags(irq, IRQ_LEVEL);
+		fasteoi = false;
+	}
+
+	hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
+	__irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge");
+}
+
+static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
 {
+	struct mp_chip_data *data = irq_get_chip_data(irq);
+
+	/*
+	 * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
+	 * and polarity attirbutes. So allow the first user to reprogram the
+	 * pin with real trigger and polarity attributes.
+	 */
+	if (irq < nr_legacy_irqs() && data->count == 1) {
+		if (info->ioapic_trigger != data->trigger)
+			mp_register_handler(irq, data->trigger);
+		data->entry.trigger = data->trigger = info->ioapic_trigger;
+		data->entry.polarity = data->polarity = info->ioapic_polarity;
+	}
+
+	return data->trigger == info->ioapic_trigger &&
+	       data->polarity == info->ioapic_polarity;
+}
+
+static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
+				 struct irq_alloc_info *info)
+{
+	bool legacy = false;
 	int irq = -1;
-	int ioapic = (int)(long)domain->host_data;
 	int type = ioapics[ioapic].irqdomain_cfg.type;
 
 	switch (type) {
 	case IOAPIC_DOMAIN_LEGACY:
 		/*
-		 * Dynamically allocate IRQ number for non-ISA IRQs in the first 16
-		 * GSIs on some weird platforms.
+		 * Dynamically allocate IRQ number for non-ISA IRQs in the first
+		 * 16 GSIs on some weird platforms.
 		 */
-		if (gsi < nr_legacy_irqs())
-			irq = irq_create_mapping(domain, pin);
-		else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
+		if (!ioapic_initialized || gsi >= nr_legacy_irqs())
 			irq = gsi;
+		legacy = mp_is_legacy_irq(irq);
 		break;
 	case IOAPIC_DOMAIN_STRICT:
-		if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0)
-			irq = gsi;
+		irq = gsi;
 		break;
 	case IOAPIC_DOMAIN_DYNAMIC:
-		irq = irq_create_mapping(domain, pin);
 		break;
 	default:
 		WARN(1, "ioapic: unknown irqdomain type %d\n", type);
-		break;
+		return -1;
+	}
+
+	return __irq_domain_alloc_irqs(domain, irq, 1,
+				       ioapic_alloc_attr_node(info),
+				       info, legacy);
+}
+
+/*
+ * Need special handling for ISA IRQs because there may be multiple IOAPIC pins
+ * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping
+ * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are
+ * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
+ * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and
+ * some BIOSes may use MP Interrupt Source records to override IRQ numbers for
+ * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be
+ * multiple pins sharing the same legacy IRQ number when ACPI is disabled.
+ */
+static int alloc_isa_irq_from_domain(struct irq_domain *domain,
+				     int irq, int ioapic, int pin,
+				     struct irq_alloc_info *info)
+{
+	struct mp_chip_data *data;
+	struct irq_data *irq_data = irq_get_irq_data(irq);
+	int node = ioapic_alloc_attr_node(info);
+
+	/*
+	 * Legacy ISA IRQ has already been allocated, just add pin to
+	 * the pin list assoicated with this IRQ and program the IOAPIC
+	 * entry. The IOAPIC entry
+	 */
+	if (irq_data && irq_data->parent_data) {
+		if (!mp_check_pin_attr(irq, info))
+			return -EBUSY;
+		if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
+					  info->ioapic_pin))
+			return -ENOMEM;
+	} else {
+		irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true);
+		if (irq >= 0) {
+			irq_data = irq_domain_get_irq_data(domain, irq);
+			data = irq_data->chip_data;
+			data->isa_irq = true;
+		}
 	}
 
-	return irq > 0 ? irq : -1;
+	return irq;
 }
 
 static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
-			     unsigned int flags)
+			     unsigned int flags, struct irq_alloc_info *info)
 {
 	int irq;
+	bool legacy = false;
+	struct irq_alloc_info tmp;
+	struct mp_chip_data *data;
 	struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
-	struct mp_pin_info *info = mp_pin_info(ioapic, pin);
 
 	if (!domain)
-		return -1;
+		return -ENOSYS;
 
-	mutex_lock(&ioapic_mutex);
-
-	/*
-	 * Don't use irqdomain to manage ISA IRQs because there may be
-	 * multiple IOAPIC pins sharing the same ISA IRQ number and
-	 * irqdomain only supports 1:1 mapping between IOAPIC pin and
-	 * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used
-	 * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H).
-	 * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are
-	 * available, and some BIOSes may use MP Interrupt Source records
-	 * to override IRQ numbers for PIRQs instead of reprogramming
-	 * the interrupt routing logic. Thus there may be multiple pins
-	 * sharing the same legacy IRQ number when ACPI is disabled.
-	 */
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
-		if (flags & IOAPIC_MAP_ALLOC) {
-			if (info->count == 0 &&
-			    mp_irqdomain_map(domain, irq, pin) != 0)
-				irq = -1;
+		legacy = mp_is_legacy_irq(irq);
+	}
 
-			/* special handling for timer IRQ0 */
+	mutex_lock(&ioapic_mutex);
+	if (!(flags & IOAPIC_MAP_ALLOC)) {
+		if (!legacy) {
+			irq = irq_find_mapping(domain, pin);
 			if (irq == 0)
-				info->count++;
+				irq = -ENOENT;
 		}
 	} else {
-		irq = irq_find_mapping(domain, pin);
-		if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC))
-			irq = alloc_irq_from_domain(domain, gsi, pin);
-	}
-
-	if (flags & IOAPIC_MAP_ALLOC) {
-		/* special handling for legacy IRQs */
-		if (irq < nr_legacy_irqs() && info->count == 1 &&
-		    mp_irqdomain_map(domain, irq, pin) != 0)
-			irq = -1;
-
-		if (irq > 0)
-			info->count++;
-		else if (info->count == 0)
-			info->set = 0;
+		ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin);
+		if (legacy)
+			irq = alloc_isa_irq_from_domain(domain, irq,
+							ioapic, pin, &tmp);
+		else if ((irq = irq_find_mapping(domain, pin)) == 0)
+			irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp);
+		else if (!mp_check_pin_attr(irq, &tmp))
+			irq = -EBUSY;
+		if (irq >= 0) {
+			data = irq_get_chip_data(irq);
+			data->count++;
+		}
 	}
-
 	mutex_unlock(&ioapic_mutex);
 
-	return irq > 0 ? irq : -1;
+	return irq;
 }
 
 static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
@@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags)
 	}
 #endif
 
-	return  mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+	return  mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL);
 }
 
-int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
+int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
 {
 	int ioapic, pin, idx;
 
@@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags)
 	if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
 		return -1;
 
-	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags);
+	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
 }
 
 void mp_unmap_irq(int irq)
 {
-	struct irq_data *data = irq_get_irq_data(irq);
-	struct mp_pin_info *info;
-	int ioapic, pin;
+	struct irq_data *irq_data = irq_get_irq_data(irq);
+	struct mp_chip_data *data;
 
-	if (!data || !data->domain)
+	if (!irq_data || !irq_data->domain)
 		return;
 
-	ioapic = (int)(long)data->domain->host_data;
-	pin = (int)data->hwirq;
-	info = mp_pin_info(ioapic, pin);
+	data = irq_data->chip_data;
+	if (!data || data->isa_irq)
+		return;
 
 	mutex_lock(&ioapic_mutex);
-	if (--info->count == 0) {
-		info->set = 0;
-		if (irq < nr_legacy_irqs() &&
-		    ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY)
-			mp_irqdomain_unmap(data->domain, irq);
-		else
-			irq_dispose_mapping(irq);
-	}
+	if (--data->count == 0)
+		irq_domain_free_irqs(irq, 1);
 	mutex_unlock(&ioapic_mutex);
 }
 
@@ -1165,7 +1198,7 @@ out:
 }
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
-static struct irq_chip ioapic_chip;
+static struct irq_chip ioapic_chip, ioapic_ir_chip;
 
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
@@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
-				 unsigned long trigger)
-{
-	struct irq_chip *chip = &ioapic_chip;
-	irq_flow_handler_t hdl;
-	bool fasteoi;
-
-	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
-	    trigger == IOAPIC_LEVEL) {
-		irq_set_status_flags(irq, IRQ_LEVEL);
-		fasteoi = true;
-	} else {
-		irq_clear_status_flags(irq, IRQ_LEVEL);
-		fasteoi = false;
-	}
-
-	if (setup_remapped_irq(irq, cfg, chip))
-		fasteoi = trigger != 0;
-
-	hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq;
-	irq_set_chip_and_handler_name(irq, chip, hdl,
-				      fasteoi ? "fasteoi" : "edge");
-}
-
-int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int vector,
-			      struct io_apic_irq_attr *attr)
-{
-	memset(entry, 0, sizeof(*entry));
-
-	entry->delivery_mode = apic->irq_delivery_mode;
-	entry->dest_mode     = apic->irq_dest_mode;
-	entry->dest	     = destination;
-	entry->vector	     = vector;
-	entry->mask	     = 0;			/* enable IRQ */
-	entry->trigger	     = attr->trigger;
-	entry->polarity	     = attr->polarity;
-
-	/*
-	 * Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
-
-	return 0;
-}
-
-static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
-				struct io_apic_irq_attr *attr)
-{
-	struct IO_APIC_route_entry entry;
-	unsigned int dest;
-
-	if (!IO_APIC_IRQ(irq))
-		return;
-
-	if (assign_irq_vector(irq, cfg, apic->target_cpus()))
-		return;
-
-	if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(),
-					 &dest)) {
-		pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
-			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		clear_irq_vector(irq, cfg);
-
-		return;
-	}
-
-	apic_printk(APIC_VERBOSE,KERN_DEBUG
-		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
-		    "IRQ %d Mode:%i Active:%i Dest:%d)\n",
-		    attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin,
-		    cfg->vector, irq, attr->trigger, attr->polarity, dest);
-
-	if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
-		pr_warn("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
-			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		clear_irq_vector(irq, cfg);
-
-		return;
-	}
-
-	ioapic_register_intr(irq, cfg, attr->trigger);
-	if (irq < nr_legacy_irqs())
-		legacy_pic->mask(irq);
-
-	ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry);
-}
-
 static void __init setup_IO_APIC_irqs(void)
 {
 	unsigned int ioapic, pin;
@@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void)
 	}
 }
 
-/*
- * Set up the timer pin, possibly with the 8259A-master behind.
- */
-static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
-					unsigned int pin, int vector)
-{
-	struct IO_APIC_route_entry entry;
-	unsigned int dest;
-
-	memset(&entry, 0, sizeof(entry));
-
-	/*
-	 * We use logical delivery to get the timer IRQ
-	 * to the first CPU.
-	 */
-	if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(),
-						  apic->target_cpus(), &dest)))
-		dest = BAD_APICID;
-
-	entry.dest_mode = apic->irq_dest_mode;
-	entry.mask = 0;			/* don't mask IRQ for edge */
-	entry.dest = dest;
-	entry.delivery_mode = apic->irq_delivery_mode;
-	entry.polarity = 0;
-	entry.trigger = 0;
-	entry.vector = vector;
-
-	/*
-	 * The timer IRQ doesn't have to know that behind the
-	 * scene we may have a 8259A-master in AEOI mode ...
-	 */
-	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
-				      "edge");
-
-	/*
-	 * Add it to the IO-APIC irq-routing table:
-	 */
-	ioapic_write_entry(ioapic_idx, pin, entry);
-}
-
-void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
+void ioapic_zap_locks(void)
 {
-	int i;
-
-	pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n");
-
-	for (i = 0; i <= nr_entries; i++) {
-		struct IO_APIC_route_entry entry;
-
-		entry = ioapic_read_entry(apic, i);
-
-		pr_debug(" %02x %02X  ", i, entry.dest);
-		pr_cont("%1d    %1d    %1d   %1d   %1d    "
-			"%1d    %1d    %02X\n",
-			entry.mask,
-			entry.trigger,
-			entry.irr,
-			entry.polarity,
-			entry.delivery_status,
-			entry.dest_mode,
-			entry.delivery_mode,
-			entry.vector);
-	}
+	raw_spin_lock_init(&ioapic_lock);
 }
 
-void intel_ir_io_apic_print_entries(unsigned int apic,
-				    unsigned int nr_entries)
+static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
 {
 	int i;
+	char buf[256];
+	struct IO_APIC_route_entry entry;
+	struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry;
 
-	pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n");
-
+	printk(KERN_DEBUG "IOAPIC %d:\n", apic);
 	for (i = 0; i <= nr_entries; i++) {
-		struct IR_IO_APIC_route_entry *ir_entry;
-		struct IO_APIC_route_entry entry;
-
 		entry = ioapic_read_entry(apic, i);
-
-		ir_entry = (struct IR_IO_APIC_route_entry *)&entry;
-
-		pr_debug(" %02x %04X ", i, ir_entry->index);
-		pr_cont("%1d   %1d    %1d    %1d   %1d   "
-			"%1d    %1d     %X    %02X\n",
-			ir_entry->format,
-			ir_entry->mask,
-			ir_entry->trigger,
-			ir_entry->irr,
-			ir_entry->polarity,
-			ir_entry->delivery_status,
-			ir_entry->index2,
-			ir_entry->zero,
-			ir_entry->vector);
+		snprintf(buf, sizeof(buf),
+			 " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)",
+			 i,
+			 entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ",
+			 entry.trigger == IOAPIC_LEVEL ? "level" : "edge ",
+			 entry.polarity == IOAPIC_POL_LOW ? "low " : "high",
+			 entry.vector, entry.irr, entry.delivery_status);
+		if (ir_entry->format)
+			printk(KERN_DEBUG "%s, remapped, I(%04X),  Z(%X)\n",
+			       buf, (ir_entry->index << 15) | ir_entry->index,
+			       ir_entry->zero);
+		else
+			printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n",
+			       buf,
+			       entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ?
+			       "logical " : "physical",
+			       entry.dest, entry.delivery_mode);
 	}
 }
 
-void ioapic_zap_locks(void)
-{
-	raw_spin_lock_init(&ioapic_lock);
-}
-
 static void __init print_IO_APIC(int ioapic_idx)
 {
 	union IO_APIC_reg_00 reg_00;
@@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx)
 	}
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
-
-	x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
+	io_apic_print_entries(ioapic_idx, reg_01.bits.entries);
 }
 
 void __init print_IO_APICs(void)
 {
 	int ioapic_idx;
-	struct irq_cfg *cfg;
 	unsigned int irq;
-	struct irq_chip *chip;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for_each_ioapic(ioapic_idx)
@@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void)
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
 	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
+		struct irq_chip *chip;
+		struct mp_chip_data *data;
 
 		chip = irq_get_chip(irq);
-		if (chip != &ioapic_chip)
+		if (chip != &ioapic_chip && chip != &ioapic_ir_chip)
 			continue;
-
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = irq_get_chip_data(irq);
+		if (!data)
 			continue;
-		if (list_empty(&cfg->irq_2_pin))
+		if (list_empty(&data->irq_2_pin))
 			continue;
+
 		printk(KERN_DEBUG "IRQ%d ", irq);
-		for_each_irq_pin(entry, cfg->irq_2_pin)
+		for_each_irq_pin(entry, data->irq_2_pin)
 			pr_cont("-> %d:%d", entry->apic, entry->pin);
 		pr_cont("\n");
 	}
@@ -1564,15 +1441,12 @@ void native_disable_io_apic(void)
 		struct IO_APIC_route_entry entry;
 
 		memset(&entry, 0, sizeof(entry));
-		entry.mask            = 0; /* Enabled */
-		entry.trigger         = 0; /* Edge */
-		entry.irr             = 0;
-		entry.polarity        = 0; /* High */
-		entry.delivery_status = 0;
-		entry.dest_mode       = 0; /* Physical */
-		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
-		entry.vector          = 0;
-		entry.dest            = read_apic_id();
+		entry.mask		= IOAPIC_UNMASKED;
+		entry.trigger		= IOAPIC_EDGE;
+		entry.polarity		= IOAPIC_POL_HIGH;
+		entry.dest_mode		= IOAPIC_DEST_MODE_PHYSICAL;
+		entry.delivery_mode	= dest_ExtINT;
+		entry.dest		= read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
@@ -1582,7 +1456,6 @@ void native_disable_io_apic(void)
 
 	if (cpu_has_apic || apic_from_smp_config())
 		disconnect_bsp_APIC(ioapic_i8259.pin != -1);
-
 }
 
 /*
@@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void)
  * This is not complete - we should be able to fake
  * an edge even if it isn't on the 8259A...
  */
-
 static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
 	int was_pending = 0, irq = data->irq;
@@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	__unmask_ioapic(irqd_cfg(data));
+	__unmask_ioapic(data->chip_data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-/*
- * Level and edge triggered IO-APIC interrupts need different handling,
- * so we use two separate IRQ descriptors. Edge triggered IRQs can be
- * handled with the level-triggered descriptor, but that one has slightly
- * more overhead. Level-triggered interrupts cannot be handled with the
- * edge-triggered handler, without risking IRQ storms and other ugly
- * races.
- */
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
-		unsigned int reg;
-
-		apic = entry->apic;
-		pin = entry->pin;
-
-		io_apic_write(apic, 0x11 + pin*2, dest);
-		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
-		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-	}
-}
-
-int native_ioapic_set_affinity(struct irq_data *data,
-			       const struct cpumask *mask,
-			       bool force)
-{
-	unsigned int dest, irq = data->irq;
-	unsigned long flags;
-	int ret;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -EPERM;
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = apic_set_affinity(data, mask, &dest);
-	if (!ret) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, irqd_cfg(data));
-		ret = IRQ_SET_MASK_OK_NOCOPY;
-	}
-	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-	return ret;
-}
-
 atomic_t irq_mis_count;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
+static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 {
 	struct irq_pin_list *entry;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
+	for_each_irq_pin(entry, data->irq_2_pin) {
 		unsigned int reg;
 		int pin;
 
@@ -1888,18 +1708,17 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
 	return false;
 }
 
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		mask_ioapic(cfg);
+		mask_ioapic_irq(data);
 		return true;
 	}
 	return false;
 }
 
-static inline void ioapic_irqd_unmask(struct irq_data *data,
-				      struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 {
 	if (unlikely(masked)) {
 		/* Only migrate the irq if the ack has been received.
@@ -1928,31 +1747,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data,
 		 * accurate and is causing problems then it is a hardware bug
 		 * and you can go talk to the chipset vendor about it.
 		 */
-		if (!io_apic_level_ack_pending(cfg))
+		if (!io_apic_level_ack_pending(data->chip_data))
 			irq_move_masked_irq(data);
-		unmask_ioapic(cfg);
+		unmask_ioapic_irq(data);
 	}
 }
 #else
-static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg)
+static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
 	return false;
 }
-static inline void ioapic_irqd_unmask(struct irq_data *data,
-				      struct irq_cfg *cfg, bool masked)
+static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 {
 }
 #endif
 
-static void ack_ioapic_level(struct irq_data *data)
+static void ioapic_ack_level(struct irq_data *irq_data)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	int i, irq = data->irq;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	unsigned long v;
 	bool masked;
+	int i;
 
 	irq_complete_move(cfg);
-	masked = ioapic_irqd_mask(data, cfg);
+	masked = ioapic_irqd_mask(irq_data);
 
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
@@ -2004,11 +1822,49 @@ static void ack_ioapic_level(struct irq_data *data)
 	 */
 	if (!(v & (1 << (i & 0x1f)))) {
 		atomic_inc(&irq_mis_count);
+		eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
+	}
+
+	ioapic_irqd_unmask(irq_data, masked);
+}
+
+static void ioapic_ir_ack_level(struct irq_data *irq_data)
+{
+	struct mp_chip_data *data = irq_data->chip_data;
+
+	/*
+	 * Intr-remapping uses pin number as the virtual vector
+	 * in the RTE. Actual vector is programmed in
+	 * intr-remapping table entry. Hence for the io-apic
+	 * EOI we use the pin number.
+	 */
+	ack_APIC_irq();
+	eoi_ioapic_pin(data->entry.vector, data);
+}
 
-		eoi_ioapic_irq(irq, cfg);
+static int ioapic_set_affinity(struct irq_data *irq_data,
+			       const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = irq_data->parent_data;
+	struct mp_chip_data *data = irq_data->chip_data;
+	struct irq_pin_list *entry;
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+		cfg = irqd_cfg(irq_data);
+		data->entry.dest = cfg->dest_apicid;
+		data->entry.vector = cfg->vector;
+		for_each_irq_pin(entry, data->irq_2_pin)
+			__ioapic_write_entry(entry->apic, entry->pin,
+					     data->entry);
 	}
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
-	ioapic_irqd_unmask(data, cfg, masked);
+	return ret;
 }
 
 static struct irq_chip ioapic_chip __read_mostly = {
@@ -2016,10 +1872,20 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_startup		= startup_ioapic_irq,
 	.irq_mask		= mask_ioapic_irq,
 	.irq_unmask		= unmask_ioapic_irq,
-	.irq_ack		= apic_ack_edge,
-	.irq_eoi		= ack_ioapic_level,
-	.irq_set_affinity	= native_ioapic_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_eoi		= ioapic_ack_level,
+	.irq_set_affinity	= ioapic_set_affinity,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct irq_chip ioapic_ir_chip __read_mostly = {
+	.name			= "IR-IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_eoi		= ioapic_ir_ack_level,
+	.irq_set_affinity	= ioapic_set_affinity,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2113,12 +1979,12 @@ static inline void __init unlock_ExtINT_logic(void)
 
 	memset(&entry1, 0, sizeof(entry1));
 
-	entry1.dest_mode = 0;			/* physical delivery */
-	entry1.mask = 0;			/* unmask IRQ now */
+	entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL;
+	entry1.mask = IOAPIC_UNMASKED;
 	entry1.dest = hard_smp_processor_id();
 	entry1.delivery_mode = dest_ExtINT;
 	entry1.polarity = entry0.polarity;
-	entry1.trigger = 0;
+	entry1.trigger = IOAPIC_EDGE;
 	entry1.vector = 0;
 
 	ioapic_write_entry(apic, pin, entry1);
@@ -2152,6 +2018,25 @@ static int __init disable_timer_pin_setup(char *arg)
 }
 early_param("disable_timer_pin_1", disable_timer_pin_setup);
 
+static int mp_alloc_timer_irq(int ioapic, int pin)
+{
+	int irq = -1;
+	struct irq_domain *domain = mp_ioapic_irqdomain(ioapic);
+
+	if (domain) {
+		struct irq_alloc_info info;
+
+		ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
+		info.ioapic_id = mpc_ioapic_id(ioapic);
+		info.ioapic_pin = pin;
+		mutex_lock(&ioapic_mutex);
+		irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
+		mutex_unlock(&ioapic_mutex);
+	}
+
+	return irq;
+}
+
 /*
  * This code may look a bit paranoid, but it's supposed to cooperate with
  * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
@@ -2162,7 +2047,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup);
  */
 static inline void __init check_timer(void)
 {
-	struct irq_cfg *cfg = irq_cfg(0);
+	struct irq_data *irq_data = irq_get_irq_data(0);
+	struct mp_chip_data *data = irq_data->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -2174,7 +2061,6 @@ static inline void __init check_timer(void)
 	 * get/set the timer IRQ vector:
 	 */
 	legacy_pic->mask(0);
-	assign_irq_vector(0, cfg, apic->target_cpus());
 
 	/*
 	 * As IRQ0 is to be enabled in the 8259A, the virtual
@@ -2215,23 +2101,21 @@ static inline void __init check_timer(void)
 	}
 
 	if (pin1 != -1) {
-		/*
-		 * Ok, does IRQ0 through the IOAPIC work?
-		 */
+		/* Ok, does IRQ0 through the IOAPIC work? */
 		if (no_pin1) {
-			add_pin_to_irq_node(cfg, node, apic1, pin1);
-			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+			mp_alloc_timer_irq(apic1, pin1);
 		} else {
-			/* for edge trigger, setup_ioapic_irq already
-			 * leave it unmasked.
+			/*
+			 * for edge trigger, it's already unmasked,
 			 * so only need to unmask if it is level-trigger
 			 * do we really have level trigger timer?
 			 */
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_ioapic(cfg);
+				unmask_ioapic_irq(irq_get_chip_data(0));
 		}
+		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -2251,8 +2135,8 @@ static inline void __init check_timer(void)
 		/*
 		 * legacy devices should be connected to IO APIC #0
 		 */
-		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
-		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2329,36 +2213,35 @@ out:
 
 static int mp_irqdomain_create(int ioapic)
 {
-	size_t size;
+	struct irq_alloc_info info;
+	struct irq_domain *parent;
 	int hwirqs = mp_ioapic_pin_count(ioapic);
 	struct ioapic *ip = &ioapics[ioapic];
 	struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg;
 	struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic);
 
-	size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic);
-	ip->pin_info = kzalloc(size, GFP_KERNEL);
-	if (!ip->pin_info)
-		return -ENOMEM;
-
 	if (cfg->type == IOAPIC_DOMAIN_INVALID)
 		return 0;
 
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
+	info.ioapic_id = mpc_ioapic_id(ioapic);
+	parent = irq_remapping_get_ir_irq_domain(&info);
+	if (!parent)
+		parent = x86_vector_domain;
+
 	ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops,
 					      (void *)(long)ioapic);
-	if(!ip->irqdomain) {
-		kfree(ip->pin_info);
-		ip->pin_info = NULL;
+	if (!ip->irqdomain)
 		return -ENOMEM;
-	}
+
+	ip->irqdomain->parent = parent;
 
 	if (cfg->type == IOAPIC_DOMAIN_LEGACY ||
 	    cfg->type == IOAPIC_DOMAIN_STRICT)
 		ioapic_dynirq_base = max(ioapic_dynirq_base,
 					 gsi_cfg->gsi_end + 1);
 
-	if (gsi_cfg->gsi_base == 0)
-		irq_set_default_host(ip->irqdomain);
-
 	return 0;
 }
 
@@ -2368,8 +2251,6 @@ static void ioapic_destroy_irqdomain(int idx)
 		irq_domain_remove(ioapics[idx].irqdomain);
 		ioapics[idx].irqdomain = NULL;
 	}
-	kfree(ioapics[idx].pin_info);
-	ioapics[idx].pin_info = NULL;
 }
 
 void __init setup_IO_APIC(void)
@@ -2399,20 +2280,6 @@ void __init setup_IO_APIC(void)
 	ioapic_initialized = 1;
 }
 
-/*
- *      Called after all the initialization is done. If we didn't find any
- *      APIC bugs then we can allow the modify fast path
- */
-
-static int __init io_apic_bug_finalize(void)
-{
-	if (sis_apic_bug == -1)
-		sis_apic_bug = 0;
-	return 0;
-}
-
-late_initcall(io_apic_bug_finalize);
-
 static void resume_ioapic_id(int ioapic_idx)
 {
 	unsigned long flags;
@@ -2451,20 +2318,6 @@ static int __init ioapic_init_ops(void)
 
 device_initcall(ioapic_init_ops);
 
-static int
-io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
-{
-	struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
-	int ret;
-
-	if (!cfg)
-		return -EINVAL;
-	ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin);
-	if (!ret)
-		setup_ioapic_irq(irq, cfg, attr);
-	return ret;
-}
-
 static int io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
@@ -2692,7 +2545,7 @@ void __init setup_ioapic_dest(void)
 		else
 			mask = apic->target_cpus();
 
-		x86_io_apic_ops.set_affinity(idata, mask, false);
+		irq_set_affinity(irq, mask);
 	}
 
 }
@@ -2737,7 +2590,7 @@ static struct resource * __init ioapic_setup_resources(void)
 	return res;
 }
 
-void __init native_io_apic_init_mappings(void)
+void __init io_apic_init_mappings(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
@@ -2962,7 +2815,6 @@ int mp_unregister_ioapic(u32 gsi_base)
 {
 	int ioapic, pin;
 	int found = 0;
-	struct mp_pin_info *pin_info;
 
 	for_each_ioapic(ioapic)
 		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
@@ -2975,11 +2827,17 @@ int mp_unregister_ioapic(u32 gsi_base)
 	}
 
 	for_each_pin(ioapic, pin) {
-		pin_info = mp_pin_info(ioapic, pin);
-		if (pin_info->count) {
-			pr_warn("pin%d on IOAPIC%d is still in use.\n",
-				pin, ioapic);
-			return -EBUSY;
+		u32 gsi = mp_pin_to_gsi(ioapic, pin);
+		int irq = mp_map_gsi_to_irq(gsi, 0, NULL);
+		struct mp_chip_data *data;
+
+		if (irq >= 0) {
+			data = irq_get_chip_data(irq);
+			if (data && data->count) {
+				pr_warn("pin%d on IOAPIC%d is still in use.\n",
+					pin, ioapic);
+				return -EBUSY;
+			}
 		}
 	}
 
@@ -3006,108 +2864,141 @@ int mp_ioapic_registered(u32 gsi_base)
 	return 0;
 }
 
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
-					int ioapic, int ioapic_pin,
-					int trigger, int polarity)
+static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
+				  struct irq_alloc_info *info)
 {
-	irq_attr->ioapic	= ioapic;
-	irq_attr->ioapic_pin	= ioapic_pin;
-	irq_attr->trigger	= trigger;
-	irq_attr->polarity	= polarity;
+	if (info && info->ioapic_valid) {
+		data->trigger = info->ioapic_trigger;
+		data->polarity = info->ioapic_polarity;
+	} else if (acpi_get_override_irq(gsi, &data->trigger,
+					 &data->polarity) < 0) {
+		/* PCI interrupts are always active low level triggered. */
+		data->trigger = IOAPIC_LEVEL;
+		data->polarity = IOAPIC_POL_LOW;
+	}
 }
 
-int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
-		     irq_hw_number_t hwirq)
+static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data,
+			   struct IO_APIC_route_entry *entry)
 {
-	int ioapic = (int)(long)domain->host_data;
-	struct mp_pin_info *info = mp_pin_info(ioapic, hwirq);
-	struct io_apic_irq_attr attr;
+	memset(entry, 0, sizeof(*entry));
+	entry->delivery_mode = apic->irq_delivery_mode;
+	entry->dest_mode     = apic->irq_dest_mode;
+	entry->dest	     = cfg->dest_apicid;
+	entry->vector	     = cfg->vector;
+	entry->trigger	     = data->trigger;
+	entry->polarity	     = data->polarity;
+	/*
+	 * Mask level triggered irqs. Edge triggered irqs are masked
+	 * by the irq core code in case they fire.
+	 */
+	if (data->trigger == IOAPIC_LEVEL)
+		entry->mask = IOAPIC_MASKED;
+	else
+		entry->mask = IOAPIC_UNMASKED;
+}
 
-	/* Get default attribute if not set by caller yet */
-	if (!info->set) {
-		u32 gsi = mp_pin_to_gsi(ioapic, hwirq);
+int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+		       unsigned int nr_irqs, void *arg)
+{
+	int ret, ioapic, pin;
+	struct irq_cfg *cfg;
+	struct irq_data *irq_data;
+	struct mp_chip_data *data;
+	struct irq_alloc_info *info = arg;
 
-		if (acpi_get_override_irq(gsi, &info->trigger,
-					  &info->polarity) < 0) {
-			/*
-			 * PCI interrupts are always polarity one level
-			 * triggered.
-			 */
-			info->trigger = 1;
-			info->polarity = 1;
-		}
-		info->node = NUMA_NO_NODE;
+	if (!info || nr_irqs > 1)
+		return -EINVAL;
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data)
+		return -EINVAL;
 
-		/*
-		 * setup_IO_APIC_irqs() programs all legacy IRQs with default
-		 * trigger and polarity attributes. Don't set the flag for that
-		 * case so the first legacy IRQ user could reprogram the pin
-		 * with real trigger and polarity attributes.
-		 */
-		if (virq >= nr_legacy_irqs() || info->count)
-			info->set = 1;
-	}
-	set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
-			     info->polarity);
+	ioapic = mp_irqdomain_ioapic_idx(domain);
+	pin = info->ioapic_pin;
+	if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
+		return -EEXIST;
 
-	return io_apic_setup_irq_pin(virq, info->node, &attr);
-}
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
-void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
-{
-	struct irq_data *data = irq_get_irq_data(virq);
-	struct irq_cfg *cfg = irq_cfg(virq);
-	int ioapic = (int)(long)domain->host_data;
-	int pin = (int)data->hwirq;
+	info->ioapic_entry = &data->entry;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
+	if (ret < 0) {
+		kfree(data);
+		return ret;
+	}
+
+	INIT_LIST_HEAD(&data->irq_2_pin);
+	irq_data->hwirq = info->ioapic_pin;
+	irq_data->chip = (domain->parent == x86_vector_domain) ?
+			  &ioapic_chip : &ioapic_ir_chip;
+	irq_data->chip_data = data;
+	mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info);
+
+	cfg = irqd_cfg(irq_data);
+	add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+	if (info->ioapic_entry)
+		mp_setup_entry(cfg, data, info->ioapic_entry);
+	mp_register_handler(virq, data->trigger);
+	if (virq < nr_legacy_irqs())
+		legacy_pic->mask(virq);
+
+	apic_printk(APIC_VERBOSE, KERN_DEBUG
+		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
+		    ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector,
+		    virq, data->trigger, data->polarity, cfg->dest_apicid);
 
-	ioapic_mask_entry(ioapic, pin);
-	__remove_pin_from_irq(cfg, ioapic, pin);
-	WARN_ON(!list_empty(&cfg->irq_2_pin));
-	arch_teardown_hwirq(virq);
+	return 0;
 }
 
-int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
+void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
+		       unsigned int nr_irqs)
 {
-	int ret = 0;
-	int ioapic, pin;
-	struct mp_pin_info *info;
+	struct irq_data *irq_data;
+	struct mp_chip_data *data;
 
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0)
-		return -ENODEV;
-
-	pin = mp_find_ioapic_pin(ioapic, gsi);
-	info = mp_pin_info(ioapic, pin);
-	trigger = trigger ? 1 : 0;
-	polarity = polarity ? 1 : 0;
-
-	mutex_lock(&ioapic_mutex);
-	if (!info->set) {
-		info->trigger = trigger;
-		info->polarity = polarity;
-		info->node = node;
-		info->set = 1;
-	} else if (info->trigger != trigger || info->polarity != polarity) {
-		ret = -EBUSY;
+	BUG_ON(nr_irqs != 1);
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (irq_data && irq_data->chip_data) {
+		data = irq_data->chip_data;
+		__remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain),
+				      (int)irq_data->hwirq);
+		WARN_ON(!list_empty(&data->irq_2_pin));
+		kfree(irq_data->chip_data);
 	}
-	mutex_unlock(&ioapic_mutex);
-
-	return ret;
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-/* Enable IOAPIC early just for system timer */
-void __init pre_init_apic_IRQ0(void)
+void mp_irqdomain_activate(struct irq_domain *domain,
+			   struct irq_data *irq_data)
 {
-	struct io_apic_irq_attr attr = { 0, 0, 0, 0 };
+	unsigned long flags;
+	struct irq_pin_list *entry;
+	struct mp_chip_data *data = irq_data->chip_data;
 
-	printk(KERN_INFO "Early APIC setup for system timer0\n");
-#ifndef CONFIG_SMP
-	physid_set_mask_of_physid(boot_cpu_physical_apicid,
-					 &phys_cpu_present_map);
-#endif
-	setup_local_APIC();
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	for_each_irq_pin(entry, data->irq_2_pin)
+		__ioapic_write_entry(entry->apic, entry->pin, data->entry);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+}
 
-	io_apic_setup_irq_pin(0, 0, &attr);
-	irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq,
-				      "edge");
+void mp_irqdomain_deactivate(struct irq_domain *domain,
+			     struct irq_data *irq_data)
+{
+	/* It won't be called for IRQ with multiple IOAPIC pins associated */
+	ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain),
+			  (int)irq_data->hwirq);
+}
+
+int mp_irqdomain_ioapic_idx(struct irq_domain *domain)
+{
+	return (int)(long)domain->host_data;
 }
+
+const struct irq_domain_ops mp_ioapic_irqdomain_ops = {
+	.alloc		= mp_irqdomain_alloc,
+	.free		= mp_irqdomain_free,
+	.activate	= mp_irqdomain_activate,
+	.deactivate	= mp_irqdomain_deactivate,
+};
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index d6ba2d660dc5..1a9d735e09c6 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Convert to hierarchical irqdomain
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -14,22 +16,23 @@
 #include <linux/dmar.h>
 #include <linux/hpet.h>
 #include <linux/msi.h>
+#include <asm/irqdomain.h>
 #include <asm/msidef.h>
 #include <asm/hpet.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 
-void native_compose_msi_msg(struct pci_dev *pdev,
-			    unsigned int irq, unsigned int dest,
-			    struct msi_msg *msg, u8 hpet_id)
+static struct irq_domain *msi_default_domain;
+
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_cfg *cfg = irqd_cfg(data);
 
 	msg->address_hi = MSI_ADDR_BASE_HI;
 
 	if (x2apic_enabled())
-		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
 
 	msg->address_lo =
 		MSI_ADDR_BASE_LO |
@@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev,
 		((apic->irq_delivery_mode != dest_LowestPrio) ?
 			MSI_ADDR_REDIRECTION_CPU :
 			MSI_ADDR_REDIRECTION_LOWPRI) |
-		MSI_ADDR_DEST_ID(dest);
+		MSI_ADDR_DEST_ID(cfg->dest_apicid);
 
 	msg->data =
 		MSI_DATA_TRIGGER_EDGE |
@@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev,
 		MSI_DATA_VECTOR(cfg->vector);
 }
 
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
-			   struct msi_msg *msg, u8 hpet_id)
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip pci_msi_controller = {
+	.name			= "PCI-MSI",
+	.irq_unmask		= pci_msi_unmask_irq,
+	.irq_mask		= pci_msi_mask_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg	= irq_msi_compose_msg,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	struct irq_cfg *cfg;
-	int err;
-	unsigned dest;
+	struct irq_domain *domain;
+	struct irq_alloc_info info;
 
-	if (disable_apic)
-		return -ENXIO;
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_MSI;
+	info.msi_dev = dev;
 
-	cfg = irq_cfg(irq);
-	err = assign_irq_vector(irq, cfg, apic->target_cpus());
-	if (err)
-		return err;
+	domain = irq_remapping_get_irq_domain(&info);
+	if (domain == NULL)
+		domain = msi_default_domain;
+	if (domain == NULL)
+		return -ENOSYS;
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain,
-					   apic->target_cpus(), &dest);
-	if (err)
-		return err;
+	return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
+}
 
-	x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+void native_teardown_msi_irq(unsigned int irq)
+{
+	irq_domain_free_irqs(irq, 1);
+}
 
-	return 0;
+static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
+					 msi_alloc_info_t *arg)
+{
+	return arg->msi_hwirq;
 }
 
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+static int pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+			   int nvec, msi_alloc_info_t *arg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct msi_desc *desc = first_pci_msi_entry(pdev);
+
+	init_irq_alloc_info(arg, NULL);
+	arg->msi_dev = pdev;
+	if (desc->msi_attrib.is_msix) {
+		arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+	} else {
+		arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+		arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+	}
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+	return 0;
+}
 
-	__get_cached_msi_msg(data->msi_desc, &msg);
+static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
+{
+	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+	.get_hwirq	= pci_msi_get_hwirq,
+	.msi_prepare	= pci_msi_prepare,
+	.set_desc	= pci_msi_set_desc,
+};
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static struct msi_domain_info pci_msi_domain_info = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			  MSI_FLAG_PCI_MSIX,
+	.ops		= &pci_msi_domain_ops,
+	.chip		= &pci_msi_controller,
+	.handler	= handle_edge_irq,
+	.handler_name	= "edge",
+};
 
-	__pci_write_msi_msg(data->msi_desc, &msg);
+void arch_init_msi_domain(struct irq_domain *parent)
+{
+	if (disable_apic)
+		return;
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+	msi_default_domain = pci_msi_create_irq_domain(NULL,
+					&pci_msi_domain_info, parent);
+	if (!msi_default_domain)
+		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
 }
 
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
-	.name			= "PCI-MSI",
+#ifdef CONFIG_IRQ_REMAP
+static struct irq_chip pci_msi_ir_controller = {
+	.name			= "IR-PCI-MSI",
 	.irq_unmask		= pci_msi_unmask_irq,
 	.irq_mask		= pci_msi_mask_irq,
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= msi_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_vcpu_affinity	= irq_chip_set_vcpu_affinity_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-		  unsigned int irq_base, unsigned int irq_offset)
-{
-	struct irq_chip *chip = &msi_chip;
-	struct msi_msg msg;
-	unsigned int irq = irq_base + irq_offset;
-	int ret;
-
-	ret = msi_compose_msg(dev, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-
-	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
-	/*
-	 * MSI-X message is written per-IRQ, the offset is always 0.
-	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
-	 */
-	if (!irq_offset)
-		pci_write_msi_msg(irq, &msg);
+static struct msi_domain_info pci_msi_ir_domain_info = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			  MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.ops		= &pci_msi_domain_ops,
+	.chip		= &pci_msi_ir_controller,
+	.handler	= handle_edge_irq,
+	.handler_name	= "edge",
+};
 
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
+struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+	return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent);
+}
+#endif
 
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+#ifdef CONFIG_DMAR_TABLE
+static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	dmar_msi_write(data->irq, msg);
+}
 
-	dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+static struct irq_chip dmar_msi_controller = {
+	.name			= "DMAR-MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_set_affinity	= msi_domain_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg	= irq_msi_compose_msg,
+	.irq_write_msi_msg	= dmar_msi_write_msg,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
 
-	return 0;
+static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
+					  msi_alloc_info_t *arg)
+{
+	return arg->dmar_id;
 }
 
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+static int dmar_msi_init(struct irq_domain *domain,
+			 struct msi_domain_info *info, unsigned int virq,
+			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
 {
-	struct msi_desc *msidesc;
-	unsigned int irq;
-	int node, ret;
+	irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
+			    handle_edge_irq, arg->dmar_data, "edge");
 
-	/* Multiple MSI vectors only supported with interrupt remapping */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
+	return 0;
+}
 
-	node = dev_to_node(&dev->dev);
+static struct msi_domain_ops dmar_msi_domain_ops = {
+	.get_hwirq	= dmar_msi_get_hwirq,
+	.msi_init	= dmar_msi_init,
+};
 
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = irq_alloc_hwirq(node);
-		if (!irq)
-			return -ENOSPC;
+static struct msi_domain_info dmar_msi_domain_info = {
+	.ops		= &dmar_msi_domain_ops,
+	.chip		= &dmar_msi_controller,
+};
 
-		ret = setup_msi_irq(dev, msidesc, irq, 0);
-		if (ret < 0) {
-			irq_free_hwirq(irq);
-			return ret;
-		}
+static struct irq_domain *dmar_get_irq_domain(void)
+{
+	static struct irq_domain *dmar_domain;
+	static DEFINE_MUTEX(dmar_lock);
 
-	}
-	return 0;
-}
+	mutex_lock(&dmar_lock);
+	if (dmar_domain == NULL)
+		dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info,
+						    x86_vector_domain);
+	mutex_unlock(&dmar_lock);
 
-void native_teardown_msi_irq(unsigned int irq)
-{
-	irq_free_hwirq(irq);
+	return dmar_domain;
 }
 
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		      bool force)
+int dmar_alloc_hwirq(int id, int node, void *arg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest, irq = data->irq;
-	struct msi_msg msg;
-	int ret;
-
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+	struct irq_domain *domain = dmar_get_irq_domain();
+	struct irq_alloc_info info;
 
-	dmar_msi_read(irq, &msg);
+	if (!domain)
+		return -1;
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_DMAR;
+	info.dmar_id = id;
+	info.dmar_data = arg;
 
-	dmar_msi_write(irq, &msg);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
+	return irq_domain_alloc_irqs(domain, 1, node, &info);
 }
 
-static struct irq_chip dmar_msi_type = {
-	.name			= "DMAR_MSI",
-	.irq_unmask		= dmar_msi_unmask,
-	.irq_mask		= dmar_msi_mask,
-	.irq_ack		= apic_ack_edge,
-	.irq_set_affinity	= dmar_msi_set_affinity,
-	.irq_retrigger		= apic_retrigger_irq,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
+void dmar_free_hwirq(int irq)
 {
-	int ret;
-	struct msi_msg msg;
-
-	ret = msi_compose_msg(NULL, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-	dmar_msi_write(irq, &msg);
-	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-				      "edge");
-	return 0;
+	irq_domain_free_irqs(irq, 1);
 }
 #endif
 
@@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq)
  * MSI message composition
  */
 #ifdef CONFIG_HPET_TIMER
+static inline int hpet_dev_id(struct irq_domain *domain)
+{
+	struct msi_domain_info *info = msi_get_domain_info(domain);
+
+	return (int)(long)info->data;
+}
 
-static int hpet_msi_set_affinity(struct irq_data *data,
-				 const struct cpumask *mask, bool force)
+static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
+	hpet_msi_write(data->handler_data, msg);
+}
 
-	ret = apic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
+static struct irq_chip hpet_msi_controller = {
+	.name = "HPET-MSI",
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = irq_chip_ack_parent,
+	.irq_set_affinity = msi_domain_set_affinity,
+	.irq_retrigger = irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg = irq_msi_compose_msg,
+	.irq_write_msi_msg = hpet_msi_write_msg,
+	.flags = IRQCHIP_SKIP_SET_WAKE,
+};
 
-	hpet_msi_read(data->handler_data, &msg);
+static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
+					  msi_alloc_info_t *arg)
+{
+	return arg->hpet_index;
+}
 
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+static int hpet_msi_init(struct irq_domain *domain,
+			 struct msi_domain_info *info, unsigned int virq,
+			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
+{
+	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+	irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
+			    handle_edge_irq, arg->hpet_data, "edge");
 
-	hpet_msi_write(data->handler_data, &msg);
+	return 0;
+}
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+static void hpet_msi_free(struct irq_domain *domain,
+			  struct msi_domain_info *info, unsigned int virq)
+{
+	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
 }
 
-static struct irq_chip hpet_msi_type = {
-	.name = "HPET_MSI",
-	.irq_unmask = hpet_msi_unmask,
-	.irq_mask = hpet_msi_mask,
-	.irq_ack = apic_ack_edge,
-	.irq_set_affinity = hpet_msi_set_affinity,
-	.irq_retrigger = apic_retrigger_irq,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
+static struct msi_domain_ops hpet_msi_domain_ops = {
+	.get_hwirq	= hpet_msi_get_hwirq,
+	.msi_init	= hpet_msi_init,
+	.msi_free	= hpet_msi_free,
+};
+
+static struct msi_domain_info hpet_msi_domain_info = {
+	.ops		= &hpet_msi_domain_ops,
+	.chip		= &hpet_msi_controller,
 };
 
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
 {
-	struct irq_chip *chip = &hpet_msi_type;
-	struct msi_msg msg;
-	int ret;
+	struct irq_domain *parent;
+	struct irq_alloc_info info;
+	struct msi_domain_info *domain_info;
+
+	if (x86_vector_domain == NULL)
+		return NULL;
+
+	domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL);
+	if (!domain_info)
+		return NULL;
+
+	*domain_info = hpet_msi_domain_info;
+	domain_info->data = (void *)(long)hpet_id;
+
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_HPET;
+	info.hpet_id = hpet_id;
+	parent = irq_remapping_get_ir_irq_domain(&info);
+	if (parent == NULL)
+		parent = x86_vector_domain;
+	else
+		hpet_msi_controller.name = "IR-HPET-MSI";
+
+	return msi_create_irq_domain(NULL, domain_info, parent);
+}
 
-	ret = msi_compose_msg(NULL, irq, &msg, id);
-	if (ret < 0)
-		return ret;
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+		    int dev_num)
+{
+	struct irq_alloc_info info;
 
-	hpet_msi_write(irq_get_handler_data(irq), &msg);
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
+	init_irq_alloc_info(&info, NULL);
+	info.type = X86_IRQ_ALLOC_TYPE_HPET;
+	info.hpet_data = dev;
+	info.hpet_id = hpet_dev_id(domain);
+	info.hpet_index = dev_num;
 
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-	return 0;
+	return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
 }
 #endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6cedd7914581..28eba2d38b15 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -3,6 +3,8 @@
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
+ * Jiang Liu <jiang.liu@linux.intel.com>
+ *	Enable support of hierarchical irqdomains
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -11,15 +13,28 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
-#include <linux/irqdomain.h>
 #include <linux/slab.h>
+#include <asm/irqdomain.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
 #include <asm/desc.h>
 #include <asm/irq_remapping.h>
 
+struct apic_chip_data {
+	struct irq_cfg		cfg;
+	cpumask_var_t		domain;
+	cpumask_var_t		old_domain;
+	u8			move_in_progress : 1;
+};
+
+struct irq_domain *x86_vector_domain;
 static DEFINE_RAW_SPINLOCK(vector_lock);
+static cpumask_var_t vector_cpumask;
+static struct irq_chip lapic_controller;
+#ifdef	CONFIG_X86_IO_APIC
+static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY];
+#endif
 
 void lock_vector_lock(void)
 {
@@ -34,71 +49,59 @@ void unlock_vector_lock(void)
 	raw_spin_unlock(&vector_lock);
 }
 
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data)
 {
-	return irq_get_chip_data(irq);
+	if (!irq_data)
+		return NULL;
+
+	while (irq_data->parent_data)
+		irq_data = irq_data->parent_data;
+
+	return irq_data->chip_data;
 }
 
 struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
 {
-	return irq_data->chip_data;
+	struct apic_chip_data *data = apic_chip_data(irq_data);
+
+	return data ? &data->cfg : NULL;
 }
 
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	struct irq_cfg *cfg;
+	return irqd_cfg(irq_get_irq_data(irq));
+}
 
-	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
-	if (!cfg)
+static struct apic_chip_data *alloc_apic_chip_data(int node)
+{
+	struct apic_chip_data *data;
+
+	data = kzalloc_node(sizeof(*data), GFP_KERNEL, node);
+	if (!data)
 		return NULL;
-	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
-		goto out_cfg;
-	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+	if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node))
+		goto out_data;
+	if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node))
 		goto out_domain;
-#ifdef	CONFIG_X86_IO_APIC
-	INIT_LIST_HEAD(&cfg->irq_2_pin);
-#endif
-	return cfg;
+	return data;
 out_domain:
-	free_cpumask_var(cfg->domain);
-out_cfg:
-	kfree(cfg);
+	free_cpumask_var(data->domain);
+out_data:
+	kfree(data);
 	return NULL;
 }
 
-struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+static void free_apic_chip_data(struct apic_chip_data *data)
 {
-	int res = irq_alloc_desc_at(at, node);
-	struct irq_cfg *cfg;
-
-	if (res < 0) {
-		if (res != -EEXIST)
-			return NULL;
-		cfg = irq_cfg(at);
-		if (cfg)
-			return cfg;
+	if (data) {
+		free_cpumask_var(data->domain);
+		free_cpumask_var(data->old_domain);
+		kfree(data);
 	}
-
-	cfg = alloc_irq_cfg(at, node);
-	if (cfg)
-		irq_set_chip_data(at, cfg);
-	else
-		irq_free_desc(at);
-	return cfg;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
-	if (!cfg)
-		return;
-	irq_set_chip_data(at, NULL);
-	free_cpumask_var(cfg->domain);
-	free_cpumask_var(cfg->old_domain);
-	kfree(cfg);
 }
 
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int __assign_irq_vector(int irq, struct apic_chip_data *d,
+			       const struct cpumask *mask)
 {
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -114,36 +117,33 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
 	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
 	static int current_offset = VECTOR_OFFSET_START % 16;
 	int cpu, err;
-	cpumask_var_t tmp_mask;
 
-	if (cfg->move_in_progress)
+	if (d->move_in_progress)
 		return -EBUSY;
 
-	if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
-		return -ENOMEM;
-
 	/* Only try and allocate irqs on cpus that are present */
 	err = -ENOSPC;
-	cpumask_clear(cfg->old_domain);
+	cpumask_clear(d->old_domain);
 	cpu = cpumask_first_and(mask, cpu_online_mask);
 	while (cpu < nr_cpu_ids) {
 		int new_cpu, vector, offset;
 
-		apic->vector_allocation_domain(cpu, tmp_mask, mask);
+		apic->vector_allocation_domain(cpu, vector_cpumask, mask);
 
-		if (cpumask_subset(tmp_mask, cfg->domain)) {
+		if (cpumask_subset(vector_cpumask, d->domain)) {
 			err = 0;
-			if (cpumask_equal(tmp_mask, cfg->domain))
+			if (cpumask_equal(vector_cpumask, d->domain))
 				break;
 			/*
 			 * New cpumask using the vector is a proper subset of
 			 * the current in use mask. So cleanup the vector
 			 * allocation for the members that are not used anymore.
 			 */
-			cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
-			cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+			cpumask_andnot(d->old_domain, d->domain,
+				       vector_cpumask);
+			d->move_in_progress =
+			   cpumask_intersects(d->old_domain, cpu_online_mask);
+			cpumask_and(d->domain, d->domain, vector_cpumask);
 			break;
 		}
 
@@ -157,16 +157,18 @@ next:
 		}
 
 		if (unlikely(current_vector == vector)) {
-			cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
-			cpumask_andnot(tmp_mask, mask, cfg->old_domain);
-			cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+			cpumask_or(d->old_domain, d->old_domain,
+				   vector_cpumask);
+			cpumask_andnot(vector_cpumask, mask, d->old_domain);
+			cpu = cpumask_first_and(vector_cpumask,
+						cpu_online_mask);
 			continue;
 		}
 
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) {
 			if (per_cpu(vector_irq, new_cpu)[vector] >
 			    VECTOR_UNDEFINED)
 				goto next;
@@ -174,55 +176,73 @@ next:
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
-		if (cfg->vector) {
-			cpumask_copy(cfg->old_domain, cfg->domain);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
+		if (d->cfg.vector) {
+			cpumask_copy(d->old_domain, d->domain);
+			d->move_in_progress =
+			   cpumask_intersects(d->old_domain, cpu_online_mask);
 		}
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+		for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask)
 			per_cpu(vector_irq, new_cpu)[vector] = irq;
-		cfg->vector = vector;
-		cpumask_copy(cfg->domain, tmp_mask);
+		d->cfg.vector = vector;
+		cpumask_copy(d->domain, vector_cpumask);
 		err = 0;
 		break;
 	}
-	free_cpumask_var(tmp_mask);
+
+	if (!err) {
+		/* cache destination APIC IDs into cfg->dest_apicid */
+		err = apic->cpu_mask_to_apicid_and(mask, d->domain,
+						   &d->cfg.dest_apicid);
+	}
 
 	return err;
 }
 
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+static int assign_irq_vector(int irq, struct apic_chip_data *data,
+			     const struct cpumask *mask)
 {
 	int err;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	err = __assign_irq_vector(irq, cfg, mask);
+	err = __assign_irq_vector(irq, data, mask);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 	return err;
 }
 
-void clear_irq_vector(int irq, struct irq_cfg *cfg)
+static int assign_irq_vector_policy(int irq, int node,
+				    struct apic_chip_data *data,
+				    struct irq_alloc_info *info)
+{
+	if (info && info->mask)
+		return assign_irq_vector(irq, data, info->mask);
+	if (node != NUMA_NO_NODE &&
+	    assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+		return 0;
+	return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
+static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	int cpu, vector;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	BUG_ON(!cfg->vector);
+	BUG_ON(!data->cfg.vector);
 
-	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+	vector = data->cfg.vector;
+	for_each_cpu_and(cpu, data->domain, cpu_online_mask)
 		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 
-	cfg->vector = 0;
-	cpumask_clear(cfg->domain);
+	data->cfg.vector = 0;
+	cpumask_clear(data->domain);
 
-	if (likely(!cfg->move_in_progress)) {
+	if (likely(!data->move_in_progress)) {
 		raw_spin_unlock_irqrestore(&vector_lock, flags);
 		return;
 	}
 
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+	for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 		     vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)
@@ -231,10 +251,95 @@ void clear_irq_vector(int irq, struct irq_cfg *cfg)
 			break;
 		}
 	}
-	cfg->move_in_progress = 0;
+	data->move_in_progress = 0;
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 }
 
+void init_irq_alloc_info(struct irq_alloc_info *info,
+			 const struct cpumask *mask)
+{
+	memset(info, 0, sizeof(*info));
+	info->mask = mask;
+}
+
+void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
+{
+	if (src)
+		*dst = *src;
+	else
+		memset(dst, 0, sizeof(*dst));
+}
+
+static void x86_vector_free_irqs(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i);
+		if (irq_data && irq_data->chip_data) {
+			clear_irq_vector(virq + i, irq_data->chip_data);
+			free_apic_chip_data(irq_data->chip_data);
+#ifdef	CONFIG_X86_IO_APIC
+			if (virq + i < nr_legacy_irqs())
+				legacy_irq_data[virq + i] = NULL;
+#endif
+			irq_domain_reset_irq_data(irq_data);
+		}
+	}
+}
+
+static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct apic_chip_data *data;
+	struct irq_data *irq_data;
+	int i, err;
+
+	if (disable_apic)
+		return -ENXIO;
+
+	/* Currently vector allocator can't guarantee contiguous allocations */
+	if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
+		return -ENOSYS;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		BUG_ON(!irq_data);
+#ifdef	CONFIG_X86_IO_APIC
+		if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i])
+			data = legacy_irq_data[virq + i];
+		else
+#endif
+			data = alloc_apic_chip_data(irq_data->node);
+		if (!data) {
+			err = -ENOMEM;
+			goto error;
+		}
+
+		irq_data->chip = &lapic_controller;
+		irq_data->chip_data = data;
+		irq_data->hwirq = virq + i;
+		err = assign_irq_vector_policy(virq, irq_data->node, data,
+					       info);
+		if (err)
+			goto error;
+	}
+
+	return 0;
+
+error:
+	x86_vector_free_irqs(domain, virq, i + 1);
+	return err;
+}
+
+static const struct irq_domain_ops x86_vector_domain_ops = {
+	.alloc	= x86_vector_alloc_irqs,
+	.free	= x86_vector_free_irqs,
+};
+
 int __init arch_probe_nr_irqs(void)
 {
 	int nr;
@@ -258,8 +363,43 @@ int __init arch_probe_nr_irqs(void)
 	return nr_legacy_irqs();
 }
 
+#ifdef	CONFIG_X86_IO_APIC
+static void init_legacy_irqs(void)
+{
+	int i, node = cpu_to_node(0);
+	struct apic_chip_data *data;
+
+	/*
+	 * For legacy IRQ's, start with assigning irq0 to irq15 to
+	 * ISA_IRQ_VECTOR(i) for all cpu's.
+	 */
+	for (i = 0; i < nr_legacy_irqs(); i++) {
+		data = legacy_irq_data[i] = alloc_apic_chip_data(node);
+		BUG_ON(!data);
+
+		data->cfg.vector = ISA_IRQ_VECTOR(i);
+		cpumask_setall(data->domain);
+		irq_set_chip_data(i, data);
+	}
+}
+#else
+static void init_legacy_irqs(void) { }
+#endif
+
 int __init arch_early_irq_init(void)
 {
+	init_legacy_irqs();
+
+	x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops,
+						NULL);
+	BUG_ON(x86_vector_domain == NULL);
+	irq_set_default_host(x86_vector_domain);
+
+	arch_init_msi_domain(x86_vector_domain);
+	arch_init_htirq_domain(x86_vector_domain);
+
+	BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL));
+
 	return arch_early_ioapic_init();
 }
 
@@ -267,7 +407,7 @@ static void __setup_vector_irq(int cpu)
 {
 	/* Initialize vector_irq on a new cpu */
 	int irq, vector;
-	struct irq_cfg *cfg;
+	struct apic_chip_data *data;
 
 	/*
 	 * vector_lock will make sure that we don't run into irq vector
@@ -277,13 +417,13 @@ static void __setup_vector_irq(int cpu)
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = apic_chip_data(irq_get_irq_data(irq));
+		if (!data)
 			continue;
 
-		if (!cpumask_test_cpu(cpu, cfg->domain))
+		if (!cpumask_test_cpu(cpu, data->domain))
 			continue;
-		vector = cfg->vector;
+		vector = data->cfg.vector;
 		per_cpu(vector_irq, cpu)[vector] = irq;
 	}
 	/* Mark the free vectors */
@@ -292,8 +432,8 @@ static void __setup_vector_irq(int cpu)
 		if (irq <= VECTOR_UNDEFINED)
 			continue;
 
-		cfg = irq_cfg(irq);
-		if (!cpumask_test_cpu(cpu, cfg->domain))
+		data = apic_chip_data(irq_get_irq_data(irq));
+		if (!cpumask_test_cpu(cpu, data->domain))
 			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
 	raw_spin_unlock(&vector_lock);
@@ -314,20 +454,20 @@ void setup_vector_irq(int cpu)
 	 * legacy vector to irq mapping:
 	 */
 	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+		per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq;
 
 	__setup_vector_irq(cpu);
 }
 
-int apic_retrigger_irq(struct irq_data *data)
+static int apic_retrigger_irq(struct irq_data *irq_data)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
+	struct apic_chip_data *data = apic_chip_data(irq_data);
 	unsigned long flags;
 	int cpu;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
-	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+	cpu = cpumask_first_and(data->domain, cpu_online_mask);
+	apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;
@@ -340,73 +480,76 @@ void apic_ack_edge(struct irq_data *data)
 	ack_APIC_irq();
 }
 
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		      unsigned int *dest_id)
+static int apic_set_affinity(struct irq_data *irq_data,
+			     const struct cpumask *dest, bool force)
 {
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int irq = data->irq;
-	int err;
+	struct apic_chip_data *data = irq_data->chip_data;
+	int err, irq = irq_data->irq;
 
 	if (!config_enabled(CONFIG_SMP))
 		return -EPERM;
 
-	if (!cpumask_intersects(mask, cpu_online_mask))
+	if (!cpumask_intersects(dest, cpu_online_mask))
 		return -EINVAL;
 
-	err = assign_irq_vector(irq, cfg, mask);
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+	err = assign_irq_vector(irq, data, dest);
 	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
+		struct irq_data *top = irq_get_irq_data(irq);
+
+		if (assign_irq_vector(irq, data, top->affinity))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
 
-	cpumask_copy(data->affinity, mask);
-
-	return 0;
+	return IRQ_SET_MASK_OK;
 }
 
+static struct irq_chip lapic_controller = {
+	.irq_ack		= apic_ack_edge,
+	.irq_set_affinity	= apic_set_affinity,
+	.irq_retrigger		= apic_retrigger_irq,
+};
+
 #ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
+static void __send_cleanup_vector(struct apic_chip_data *data)
 {
 	cpumask_var_t cleanup_mask;
 
 	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
 		unsigned int i;
 
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+		for_each_cpu_and(i, data->old_domain, cpu_online_mask)
 			apic->send_IPI_mask(cpumask_of(i),
 					    IRQ_MOVE_CLEANUP_VECTOR);
 	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask);
 		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
 		free_cpumask_var(cleanup_mask);
 	}
-	cfg->move_in_progress = 0;
+	data->move_in_progress = 0;
+}
+
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	struct apic_chip_data *data;
+
+	data = container_of(cfg, struct apic_chip_data, cfg);
+	if (data->move_in_progress)
+		__send_cleanup_vector(data);
 }
 
 asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
 
-	ack_APIC_irq();
-	irq_enter();
-	exit_idle();
+	entering_ack_irq();
 
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		int irq;
 		unsigned int irr;
 		struct irq_desc *desc;
-		struct irq_cfg *cfg;
+		struct apic_chip_data *data;
 
 		irq = __this_cpu_read(vector_irq[vector]);
 
@@ -417,8 +560,8 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 		if (!desc)
 			continue;
 
-		cfg = irq_cfg(irq);
-		if (!cfg)
+		data = apic_chip_data(&desc->irq_data);
+		if (!data)
 			continue;
 
 		raw_spin_lock(&desc->lock);
@@ -427,10 +570,11 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 		 * Check if the irq migration is in progress. If so, we
 		 * haven't received the cleanup request yet for this irq.
 		 */
-		if (cfg->move_in_progress)
+		if (data->move_in_progress)
 			goto unlock;
 
-		if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+		if (vector == data->cfg.vector &&
+		    cpumask_test_cpu(me, data->domain))
 			goto unlock;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -450,20 +594,21 @@ unlock:
 		raw_spin_unlock(&desc->lock);
 	}
 
-	irq_exit();
+	exiting_irq();
 }
 
 static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
 	unsigned me;
+	struct apic_chip_data *data;
 
-	if (likely(!cfg->move_in_progress))
+	data = container_of(cfg, struct apic_chip_data, cfg);
+	if (likely(!data->move_in_progress))
 		return;
 
 	me = smp_processor_id();
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
-		send_cleanup_vector(cfg);
+	if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain))
+		__send_cleanup_vector(data);
 }
 
 void irq_complete_move(struct irq_cfg *cfg)
@@ -475,46 +620,11 @@ void irq_force_complete_move(int irq)
 {
 	struct irq_cfg *cfg = irq_cfg(irq);
 
-	if (!cfg)
-		return;
-
-	__irq_complete_move(cfg, cfg->vector);
+	if (cfg)
+		__irq_complete_move(cfg, cfg->vector);
 }
 #endif
 
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	int ret;
-
-	cfg = alloc_irq_cfg(irq, node);
-	if (!cfg)
-		return -ENOMEM;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-
-	if (!ret)
-		irq_set_chip_data(irq, cfg);
-	else
-		free_irq_cfg(irq, cfg);
-	return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	free_remapped_irq(irq);
-	clear_irq_vector(irq, cfg);
-	free_irq_cfg(irq, cfg);
-}
-
 static void __init print_APIC_field(int base)
 {
 	int i;
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 6fae733e9194..3ffd925655e0 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode);
 
 static bool x2apic_fadt_phys(void)
 {
+#ifdef CONFIG_ACPI
 	if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
 		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) {
 		printk(KERN_DEBUG "System requires x2apic physical mode\n");
 		return true;
 	}
+#endif
 	return false;
 }
 
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 9f6b9341950f..8e3d22a1af94 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -41,6 +41,25 @@ void common(void) {
 	OFFSET(pbe_orig_address, pbe, orig_address);
 	OFFSET(pbe_next, pbe, next);
 
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+	BLANK();
+	OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax);
+	OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx);
+	OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx);
+	OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx);
+	OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si);
+	OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di);
+	OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp);
+	OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
+	OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
+
+	BLANK();
+	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
+
+	BLANK();
+	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
+#endif
+
 #ifdef CONFIG_PARAVIRT
 	BLANK();
 	OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled);
@@ -49,7 +68,9 @@ void common(void) {
 	OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
 	OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
 	OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
+#ifdef CONFIG_X86_32
 	OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
+#endif
 	OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
 	OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
 #endif
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 47703aed74cf..6ce39025f467 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -17,17 +17,6 @@ void foo(void);
 
 void foo(void)
 {
-	OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax);
-	OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx);
-	OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx);
-	OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx);
-	OFFSET(IA32_SIGCONTEXT_si, sigcontext, si);
-	OFFSET(IA32_SIGCONTEXT_di, sigcontext, di);
-	OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp);
-	OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp);
-	OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip);
-	BLANK();
-
 	OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
 	OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
 	OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
@@ -37,10 +26,6 @@ void foo(void)
 	OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
 	BLANK();
 
-	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
-	OFFSET(TI_cpu, thread_info, cpu);
-	BLANK();
-
 	OFFSET(PT_EBX, pt_regs, bx);
 	OFFSET(PT_ECX, pt_regs, cx);
 	OFFSET(PT_EDX, pt_regs, dx);
@@ -60,9 +45,6 @@ void foo(void)
 	OFFSET(PT_OLDSS,  pt_regs, ss);
 	BLANK();
 
-	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
-	BLANK();
-
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 5ce6f2da8763..d8f42f902a0f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -29,27 +29,6 @@ int main(void)
 	BLANK();
 #endif
 
-#ifdef CONFIG_IA32_EMULATION
-	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
-	BLANK();
-
-#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry)
-	ENTRY(ax);
-	ENTRY(bx);
-	ENTRY(cx);
-	ENTRY(dx);
-	ENTRY(si);
-	ENTRY(di);
-	ENTRY(bp);
-	ENTRY(sp);
-	ENTRY(ip);
-	BLANK();
-#undef ENTRY
-
-	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
-	BLANK();
-#endif
-
 #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
 	ENTRY(bx);
 	ENTRY(cx);
@@ -87,7 +66,7 @@ int main(void)
 	DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
 	DEFINE(NR_syscalls, sizeof(syscalls_64));
 
-	DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+	DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1);
 	DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
 
 	return 0;
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
index 83a7995625a6..58118e207a69 100644
--- a/arch/x86/kernel/check.c
+++ b/arch/x86/kernel/check.c
@@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void)
 
 	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-	for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE),
 				PAGE_SIZE, corruption_check_size);
 		end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE),
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e4cf63301ff4..dd3a4baffe50 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -19,6 +19,13 @@
 
 #include "cpu.h"
 
+/*
+ * nodes_per_socket: Stores the number of nodes per socket.
+ * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
+ * Node Identifiers[10:8]
+ */
+static u32 nodes_per_socket = 1;
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -288,10 +295,10 @@ static int nearby_node(int apicid)
  *     Assumption: Number of cores in each internal node is the same.
  * (2) AMD processors supporting compute units
  */
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 nodes, cores_per_cu = 1;
+	u32 cores_per_cu = 1;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u32 eax, ebx, ecx, edx;
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		nodes = ((ecx >> 8) & 7) + 1;
+		nodes_per_socket = ((ecx >> 8) & 7) + 1;
 		node_id = ecx & 7;
 
 		/* get compute unit information */
@@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes = ((value >> 3) & 7) + 1;
+		nodes_per_socket = ((value >> 3) & 7) + 1;
 		node_id = value & 7;
 	} else
 		return;
 
 	/* fixup multi-node processor information */
-	if (nodes > 1) {
+	if (nodes_per_socket > 1) {
 		u32 cores_per_node;
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes;
+		cores_per_node = c->x86_max_cores / nodes_per_socket;
 		cus_per_node = cores_per_node / cores_per_cu;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
@@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
  */
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
 
@@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu)
 }
 EXPORT_SYMBOL_GPL(amd_get_nb_id);
 
+u32 amd_get_nodes_per_socket(void)
+{
+	return nodes_per_socket;
+}
+EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
+
 static void srat_detect_node(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_NUMA
@@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 
 static void early_init_amd_mc(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned bits, ecx;
 
 	/* Multi core CPU? */
@@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_K6_MTRR);
 #endif
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI)
-	/* check CPU config space for extended APIC ID */
-	if (cpu_has_apic && c->x86 >= 0xf) {
+	/*
+	 * ApicID can always be treated as an 8-bit value for AMD APIC versions
+	 * >= 0x10, but even old K8s came out of reset with version 0x10. So, we
+	 * can safely set X86_FEATURE_EXTD_APICID unconditionally for families
+	 * after 16h.
+	 */
+	if (cpu_has_apic && c->x86 > 0x16) {
+		set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
+	} else if (cpu_has_apic && c->x86 >= 0xf) {
+		/* check CPU config space for extended APIC ID */
 		unsigned int val;
 		val = read_pci_config(0, 24, 0, 0x68);
 		if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18)))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03445346ee0a..bd17db15a2c1 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -12,57 +12,11 @@
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/msr.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 
-static double __initdata x = 4195835.0;
-static double __initdata y = 3145727.0;
-
-/*
- * This used to check for exceptions..
- * However, it turns out that to support that,
- * the XMM trap handlers basically had to
- * be buggy. So let's have a correct XMM trap
- * handler, and forget about printing out
- * some status at boot.
- *
- * We should really only care about bugs here
- * anyway. Not features.
- */
-static void __init check_fpu(void)
-{
-	s32 fdiv_bug;
-
-	kernel_fpu_begin();
-
-	/*
-	 * trap_init() enabled FXSR and company _before_ testing for FP
-	 * problems here.
-	 *
-	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
-	 */
-	__asm__("fninit\n\t"
-		"fldl %1\n\t"
-		"fdivl %2\n\t"
-		"fmull %2\n\t"
-		"fldl %1\n\t"
-		"fsubp %%st,%%st(1)\n\t"
-		"fistpl %0\n\t"
-		"fwait\n\t"
-		"fninit"
-		: "=m" (*&fdiv_bug)
-		: "m" (*&x), "m" (*&y));
-
-	kernel_fpu_end();
-
-	if (fdiv_bug) {
-		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
-		pr_warn("Hmm, FPU with FDIV bug\n");
-	}
-}
-
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -85,10 +39,5 @@ void __init check_bugs(void)
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
 
-	/*
-	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
-	 * alternative instructions.
-	 */
-	if (cpu_has_fpu)
-		check_fpu();
+	fpu__init_check_bugs();
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a62cf04dac8a..9fc5e3d9d9c8 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/string.h>
+#include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/init.h>
@@ -31,8 +32,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
@@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-static int __init x86_xsave_setup(char *s)
+static int __init x86_mpx_setup(char *s)
 {
+	/* require an exact match without trailing characters */
 	if (strlen(s))
 		return 0;
-	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
-	setup_clear_cpu_cap(X86_FEATURE_AVX);
-	setup_clear_cpu_cap(X86_FEATURE_AVX2);
-	return 1;
-}
-__setup("noxsave", x86_xsave_setup);
 
-static int __init x86_xsaveopt_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-	return 1;
-}
-__setup("noxsaveopt", x86_xsaveopt_setup);
+	/* do not emit a message if the feature is not present */
+	if (!boot_cpu_has(X86_FEATURE_MPX))
+		return 1;
 
-static int __init x86_xsaves_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
+	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
 	return 1;
 }
-__setup("noxsaves", x86_xsaves_setup);
+__setup("nompx", x86_mpx_setup);
 
 #ifdef CONFIG_X86_32
 static int cachesize_override = -1;
@@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str)
 }
 __setup("cachesize=", cachesize_setup);
 
-static int __init x86_fxsr_setup(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FXSR);
-	setup_clear_cpu_cap(X86_FEATURE_XMM);
-	return 1;
-}
-__setup("nofxsr", x86_fxsr_setup);
-
 static int __init x86_sep_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SEP);
@@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
 static void get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
-	char *p, *q;
+	char *p, *q, *s;
 
 	if (c->extended_cpuid_level < 0x80000004)
 		return;
@@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c)
 	cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]);
 	c->x86_model_id[48] = 0;
 
-	/*
-	 * Intel chips right-justify this string for some dumb reason;
-	 * undo that brain damage:
-	 */
-	p = q = &c->x86_model_id[0];
+	/* Trim whitespace */
+	p = q = s = &c->x86_model_id[0];
+
 	while (*p == ' ')
 		p++;
-	if (p != q) {
-		while (*p)
-			*q++ = *p++;
-		while (q <= &c->x86_model_id[48])
-			*q++ = '\0';	/* Zero-pad the rest */
+
+	while (*p) {
+		/* Note the last non-whitespace index */
+		if (!isspace(*p))
+			s = q;
+
+		*q++ = *p++;
 	}
+
+	*(s + 1) = '\0';
 }
 
 void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
@@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 
 void detect_ht(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
 	static bool printed;
@@ -759,7 +742,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	cpu_detect(c);
 	get_cpu_vendor(c);
 	get_cpu_cap(c);
-	fpu_detect(c);
+	fpu__init_system(c);
 
 	if (this_cpu->c_early_init)
 		this_cpu->c_early_init(c);
@@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c)
 	if (c->cpuid_level >= 0x00000001) {
 		c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
+# ifdef CONFIG_SMP
 		c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 # else
 		c->apicid = c->initial_apicid;
@@ -1026,7 +1009,7 @@ void enable_sep_cpu(void)
 	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
 	      0);
 
-	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 out:
 	put_cpu();
@@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 		printk(KERN_CONT "%s ", vendor);
 
 	if (c->x86_model_id[0])
-		printk(KERN_CONT "%s", strim(c->x86_model_id));
+		printk(KERN_CONT "%s", c->x86_model_id);
 	else
 		printk(KERN_CONT "%d86", c->x86);
 
@@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
-	(unsigned long)&init_thread_union + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
-
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1208,10 +1185,10 @@ void syscall_init(void)
 	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
 	 */
 	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
-	wrmsrl(MSR_LSTAR, system_call);
+	wrmsrl(MSR_LSTAR, entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
-	wrmsrl(MSR_CSTAR, ia32_cstar_target);
+	wrmsrl(MSR_CSTAR, entry_SYSCALL_compat);
 	/*
 	 * This only works on Intel CPUs.
 	 * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
@@ -1220,7 +1197,7 @@ void syscall_init(void)
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
 	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
-	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, ignore_sysret);
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
@@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
-DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
 
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
@@ -1439,7 +1415,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 
 	if (is_uv_system())
 		uv_cpu_init();
@@ -1495,7 +1471,7 @@ void cpu_init(void)
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
 
-	fpu_init();
+	fpu__init_cpu();
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 36ce402a3fa5..d820d8eae96b 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -27,8 +27,8 @@
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
-#ifdef CONFIG_XEN_PVHVM
-	&x86_hyper_xen_hvm,
+#ifdef CONFIG_XEN
+	&x86_hyper_xen,
 #endif
 	&x86_hyper_vmware,
 	&x86_hyper_ms_hyperv,
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index edcb0e28c336..be4febc58b94 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	unsigned int cpu = c->cpu_index;
 #endif
 
@@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 
 	if (new_l2) {
 		l2 = new_l2;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l2_id;
 #endif
 	}
 
 	if (new_l3) {
 		l3 = new_l3;
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 		per_cpu(cpu_llc_id, cpu) = l3_id;
 #endif
 	}
 
-#ifdef CONFIG_X86_HT
+#ifdef CONFIG_SMP
 	/*
 	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
 	 * turns means that the only possibility is SMT (as indicated in
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e535533d5ab8..df919ff103c3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -53,9 +53,12 @@
 static DEFINE_MUTEX(mce_chrdev_read_mutex);
 
 #define rcu_dereference_check_mce(p) \
-	rcu_dereference_index_check((p), \
-			      rcu_read_lock_sched_held() || \
-			      lockdep_is_held(&mce_chrdev_read_mutex))
+({ \
+	rcu_lockdep_assert(rcu_read_lock_sched_held() || \
+			   lockdep_is_held(&mce_chrdev_read_mutex), \
+			   "suspicious rcu_dereference_check_mce() usage"); \
+	smp_load_acquire(&(p)); \
+})
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
@@ -708,6 +711,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			  struct pt_regs *regs)
 {
 	int i, ret = 0;
+	char *tmp;
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
@@ -716,9 +720,11 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			if (quirk_no_way_out)
 				quirk_no_way_out(i, m, regs);
 		}
-		if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
-		    MCE_PANIC_SEVERITY)
+
+		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			*msg = tmp;
 			ret = 1;
+		}
 	}
 	return ret;
 }
@@ -1047,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	char *msg = "Unknown";
 	u64 recover_paddr = ~0ull;
 	int flags = MF_ACTION_REQUIRED;
+	int lmce = 0;
 
 	prev_state = ist_enter(regs);
 
@@ -1074,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		kill_it = 1;
 
 	/*
-	 * Go through all the banks in exclusion of the other CPUs.
-	 * This way we don't report duplicated events on shared banks
-	 * because the first one to see it will clear it.
+	 * Check if this MCE is signaled to only this logical processor
 	 */
-	order = mce_start(&no_way_out);
+	if (m.mcgstatus & MCG_STATUS_LMCES)
+		lmce = 1;
+	else {
+		/*
+		 * Go through all the banks in exclusion of the other CPUs.
+		 * This way we don't report duplicated events on shared banks
+		 * because the first one to see it will clear it.
+		 * If this is a Local MCE, then no need to perform rendezvous.
+		 */
+		order = mce_start(&no_way_out);
+	}
+
 	for (i = 0; i < cfg->banks; i++) {
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
@@ -1155,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * Do most of the synchronization with other CPUs.
 	 * When there's any problem use only local no_way_out state.
 	 */
-	if (mce_end(order) < 0)
-		no_way_out = worst >= MCE_PANIC_SEVERITY;
+	if (!lmce) {
+		if (mce_end(order) < 0)
+			no_way_out = worst >= MCE_PANIC_SEVERITY;
+	} else {
+		/*
+		 * Local MCE skipped calling mce_reign()
+		 * If we found a fatal error, we need to panic here.
+		 */
+		 if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
+			mce_panic("Machine check from unknown source",
+				NULL, NULL);
+	}
 
 	/*
 	 * At insane "tolerant" levels we take no action. Otherwise
@@ -1637,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 		mce_intel_feature_init(c);
 		mce_adjust_timer = cmci_intel_adjust_timer;
 		break;
-	case X86_VENDOR_AMD:
+
+	case X86_VENDOR_AMD: {
+		u32 ebx = cpuid_ebx(0x80000007);
+
 		mce_amd_feature_init(c);
-		mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1;
+		mce_flags.overflow_recov = !!(ebx & BIT(0));
+		mce_flags.succor	 = !!(ebx & BIT(1));
 		break;
+		}
+
 	default:
 		break;
 	}
@@ -1884,7 +1916,7 @@ out:
 static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_chrdev_wait, wait);
-	if (rcu_access_index(mcelog.next))
+	if (READ_ONCE(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	if (!mce_apei_read_done && apei_check_mce())
 		return POLLIN | POLLRDNORM;
@@ -1929,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
 }
 EXPORT_SYMBOL_GPL(register_mce_write_callback);
 
-ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
-			 size_t usize, loff_t *off)
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+				size_t usize, loff_t *off)
 {
 	if (mce_write)
 		return mce_write(filp, ubuf, usize, off);
@@ -1976,6 +2008,7 @@ void mce_disable_bank(int bank)
 /*
  * mce=off Disables machine check
  * mce=no_cmci Disables CMCI
+ * mce=no_lmce Disables LMCE
  * mce=dont_log_ce Clears corrected events silently, no log created for CEs.
  * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared.
  * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above)
@@ -1999,6 +2032,8 @@ static int __init mcheck_enable(char *str)
 		cfg->disabled = true;
 	else if (!strcmp(str, "no_cmci"))
 		cfg->cmci_disabled = true;
+	else if (!strcmp(str, "no_lmce"))
+		cfg->lmce_disabled = true;
 	else if (!strcmp(str, "dont_log_ce"))
 		cfg->dont_log_ce = true;
 	else if (!strcmp(str, "ignore_ce"))
@@ -2008,11 +2043,8 @@ static int __init mcheck_enable(char *str)
 	else if (!strcmp(str, "bios_cmci_threshold"))
 		cfg->bios_cmci_threshold = true;
 	else if (isdigit(str[0])) {
-		get_option(&str, &(cfg->tolerant));
-		if (*str == ',') {
-			++str;
+		if (get_option(&str, &cfg->tolerant) == 2)
 			get_option(&str, &(cfg->monarch_timeout));
-		}
 	} else {
 		pr_info("mce argument %s ignored. Please use /sys\n", str);
 		return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 55ad9b37cae8..e99b15077e94 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -1,19 +1,13 @@
 /*
- *  (c) 2005-2012 Advanced Micro Devices, Inc.
+ *  (c) 2005-2015 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
  *  GNU general public license version 2. See "COPYING" or
  *  http://www.gnu.org/licenses/gpl.html
  *
  *  Written by Jacob Shin - AMD, Inc.
- *
  *  Maintained by: Borislav Petkov <bp@alien8.de>
  *
- *  April 2006
- *     - added support for AMD Family 0x10 processors
- *  May 2012
- *     - major scrubbing
- *
- *  All MC4_MISCi registers are shared between multi-cores
+ *  All MC4_MISCi registers are shared between cores on a node.
  */
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
@@ -32,6 +26,7 @@
 #include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
 
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -47,6 +42,13 @@
 #define MASK_BLKPTR_LO    0xFF000000
 #define MCG_XBLK_ADDR     0xC0000400
 
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR		0xC0000410
+#define MASK_DEF_LVTOFF		0x000000F0
+#define MASK_DEF_INT_TYPE	0x00000006
+#define DEF_LVT_OFF		0x2
+#define DEF_INT_TYPE_APIC	0x2
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
 static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+	pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
 /*
  * CPU Initialization
@@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset)
 	threshold_restart_bank(&tr);
 };
 
-static int setup_APIC_mce(int reserved, int new)
+static int setup_APIC_mce_threshold(int reserved, int new)
 {
 	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
 					      APIC_EILVT_MSG_FIX, 0))
@@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new)
 	return reserved;
 }
 
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+	u32 low = 0, high = 0;
+	int def_offset = -1, def_new;
+
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+		return;
+
+	def_new = (low & MASK_DEF_LVTOFF) >> 4;
+	if (!(low & MASK_DEF_LVTOFF)) {
+		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+		def_new = DEF_LVT_OFF;
+		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+	}
+
+	def_offset = setup_APIC_deferred_error(def_offset, def_new);
+	if ((def_offset == def_new) &&
+	    (deferred_error_int_vector != amd_deferred_error_interrupt))
+		deferred_error_int_vector = amd_deferred_error_interrupt;
+
+	low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+	wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 			b.interrupt_enable = 1;
 			new	= (high & MASK_LVTOFF_HI) >> 20;
-			offset  = setup_APIC_mce(offset, new);
+			offset  = setup_APIC_mce_threshold(offset, new);
 
 			if ((offset == new) &&
 			    (mce_threshold_vector != amd_threshold_interrupt))
@@ -262,6 +304,73 @@ init:
 			mce_threshold_block_init(&b, offset);
 		}
 	}
+
+	if (mce_flags.succor)
+		deferred_error_interrupt_enable(c);
+}
+
+static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
+{
+	struct mce m;
+	u64 status;
+
+	rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+	if (!(status & MCI_STATUS_VAL))
+		return;
+
+	mce_setup(&m);
+
+	m.status = status;
+	m.bank = bank;
+
+	if (threshold_err)
+		m.misc = misc;
+
+	if (m.status & MCI_STATUS_ADDRV)
+		rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr);
+
+	mce_log(&m);
+	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+}
+
+static inline void __smp_deferred_error_interrupt(void)
+{
+	inc_irq_stat(irq_deferred_error_count);
+	deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+	entering_irq();
+	__smp_deferred_error_interrupt();
+	exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+	entering_irq();
+	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+	__smp_deferred_error_interrupt();
+	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+	exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+	u64 status;
+	unsigned int bank;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+		if (!(status & MCI_STATUS_VAL) ||
+		    !(status & MCI_STATUS_DEFERRED))
+			continue;
+
+		__log_error(bank, false, 0);
+		break;
+	}
 }
 
 /*
@@ -273,12 +382,12 @@ init:
  * the interrupt goes off when error_count reaches threshold_limit.
  * the handler will simply log mcelog w/ software defined bank number.
  */
+
 static void amd_threshold_interrupt(void)
 {
 	u32 low = 0, high = 0, address = 0;
 	int cpu = smp_processor_id();
 	unsigned int bank, block;
-	struct mce m;
 
 	/* assume first bank caused it */
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
@@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void)
 	return;
 
 log:
-	mce_setup(&m);
-	rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
-	if (!(m.status & MCI_STATUS_VAL))
-		return;
-	m.misc = ((u64)high << 32) | low;
-	m.bank = bank;
-	mce_log(&m);
-
-	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
+	__log_error(bank, true, ((u64)high << 32) | low);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index b4a41cf030ed..844f56c5616d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -91,6 +91,36 @@ static int cmci_supported(int *banks)
 	return !!(cap & MCG_CMCI_P);
 }
 
+static bool lmce_supported(void)
+{
+	u64 tmp;
+
+	if (mca_cfg.lmce_disabled)
+		return false;
+
+	rdmsrl(MSR_IA32_MCG_CAP, tmp);
+
+	/*
+	 * LMCE depends on recovery support in the processor. Hence both
+	 * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP.
+	 */
+	if ((tmp & (MCG_SER_P | MCG_LMCE_P)) !=
+		   (MCG_SER_P | MCG_LMCE_P))
+		return false;
+
+	/*
+	 * BIOS should indicate support for LMCE by setting bit 20 in
+	 * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will
+	 * generate a #GP fault.
+	 */
+	rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp);
+	if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) ==
+		   (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE))
+		return true;
+
+	return false;
+}
+
 bool mce_intel_cmci_poll(void)
 {
 	if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
@@ -405,8 +435,22 @@ static void intel_init_cmci(void)
 	cmci_recheck();
 }
 
+void intel_init_lmce(void)
+{
+	u64 val;
+
+	if (!lmce_supported())
+		return;
+
+	rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+
+	if (!(val & MCG_EXT_CTL_LMCE_EN))
+		wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+}
+
 void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 	intel_init_cmci();
+	intel_init_lmce();
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 737737edbd1e..e8a215a9a345 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
 	}
 }
 
-void __init load_ucode_amd_bsp(void)
+static bool __init load_builtin_amd_microcode(struct cpio_data *cp,
+					      unsigned int family)
+{
+#ifdef CONFIG_X86_64
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
+
+	if (family >= 0x15)
+		snprintf(fw_name, sizeof(fw_name),
+			 "amd-ucode/microcode_amd_fam%.2xh.bin", family);
+
+	return get_builtin_firmware(cp, fw_name);
+#else
+	return false;
+#endif
+}
+
+void __init load_ucode_amd_bsp(unsigned int family)
 {
 	struct cpio_data cp;
 	void **data;
@@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void)
 #endif
 
 	cp = find_ucode_in_initrd();
-	if (!cp.data)
-		return;
+	if (!cp.data) {
+		if (!load_builtin_amd_microcode(&cp, family))
+			return;
+	}
 
 	*data = cp.data;
 	*size = cp.size;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 36a83617eb21..6236a54a63f4 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -1,74 +1,16 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *	      2006	Shaohua Li <shaohua.li@intel.com>
+ *	      2013-2015	Borislav Petkov <bp@alien8.de>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
+ * This driver allows to upgrade microcode on x86 processors.
  *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index a413a69cbd74..8ebc421d6299 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -3,6 +3,7 @@
  *
  *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
  *			   H Peter Anvin" <hpa@zytor.com>
+ *		  (C) 2015 Borislav Petkov <bp@alien8.de>
  *
  *	This driver allows to early upgrade microcode on Intel processors
  *	belonging to IA-32 family - PentiumPro, Pentium II,
@@ -17,6 +18,7 @@
  *	2 of the License, or (at your option) any later version.
  */
 #include <linux/module.h>
+#include <linux/firmware.h>
 #include <asm/microcode.h>
 #include <asm/microcode_intel.h>
 #include <asm/microcode_amd.h>
@@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void)
 	return *res;
 }
 
+extern struct builtin_fw __start_builtin_fw[];
+extern struct builtin_fw __end_builtin_fw[];
+
+bool get_builtin_firmware(struct cpio_data *cd, const char *name)
+{
+#ifdef CONFIG_FW_LOADER
+	struct builtin_fw *b_fw;
+
+	for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) {
+		if (!strcmp(name, b_fw->name)) {
+			cd->size = b_fw->size;
+			cd->data = b_fw->data;
+			return true;
+		}
+	}
+#endif
+	return false;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor, family;
+	int vendor;
+	unsigned int family;
 
 	if (check_loader_disabled_bsp())
 		return;
@@ -63,7 +85,7 @@ void __init load_ucode_bsp(void)
 		break;
 	case X86_VENDOR_AMD:
 		if (family >= 0x10)
-			load_ucode_amd_bsp();
+			load_ucode_amd_bsp(family);
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a41beadb3db9..969dc17eb1b4 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -1,74 +1,13 @@
 /*
- *	Intel CPU Microcode Update Driver for Linux
+ * Intel CPU Microcode Update Driver for Linux
  *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
+ * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *		 2006 Shaohua Li <shaohua.li@intel.com>
  *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
 	cpf = cpu_sig.pf;
 	crev = cpu_sig.rev;
 
-	return get_matching_microcode(csig, cpf, crev, mc_intel);
+	return has_newer_microcode(mc_intel, csig, cpf, crev);
 }
 
 static int apply_microcode_intel(int cpu)
@@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 
 		csig = uci->cpu_sig.sig;
 		cpf = uci->cpu_sig.pf;
-		if (get_matching_microcode(csig, cpf, new_rev, mc)) {
+		if (has_newer_microcode(mc, csig, cpf, new_rev)) {
 			vfree(new_mc);
 			new_rev = mc_header.rev;
 			new_mc  = mc;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 2f49ab4ac0ae..8187b7247d1c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved,
 		ucode_ptr = saved[i];
 		mc_hdr	  = (struct microcode_header_intel *)ucode_ptr;
 
-		ret = get_matching_microcode(uci->cpu_sig.sig,
-					     uci->cpu_sig.pf,
-					     new_rev,
-					     ucode_ptr);
+		ret = has_newer_microcode(ucode_ptr,
+					  uci->cpu_sig.sig,
+					  uci->cpu_sig.pf,
+					  new_rev);
 		if (!ret)
 			continue;
 
@@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 			     u8 *ucode_ptr, unsigned int num_saved)
 {
 	struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
-	unsigned int sig, pf, new_rev;
+	unsigned int sig, pf;
 	int found = 0, i;
 
 	mc_hdr = (struct microcode_header_intel *)ucode_ptr;
@@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved,
 		mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i];
 		sig	     = mc_saved_hdr->sig;
 		pf	     = mc_saved_hdr->pf;
-		new_rev	     = mc_hdr->rev;
 
-		if (!get_matching_sig(sig, pf, new_rev, ucode_ptr))
+		if (!find_matching_signature(ucode_ptr, sig, pf))
 			continue;
 
 		found = 1;
 
-		if (!revision_is_newer(mc_hdr, new_rev))
+		if (mc_hdr->rev <= mc_saved_hdr->rev)
 			continue;
 
 		/*
@@ -522,6 +521,27 @@ out:
 EXPORT_SYMBOL_GPL(save_mc_for_early);
 #endif
 
+static bool __init load_builtin_intel_microcode(struct cpio_data *cp)
+{
+#ifdef CONFIG_X86_64
+	unsigned int eax = 0x00000001, ebx, ecx = 0, edx;
+	unsigned int family, model, stepping;
+	char name[30];
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	family   = __x86_family(eax);
+	model    = x86_model(eax);
+	stepping = eax & 0xf;
+
+	sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping);
+
+	return get_builtin_firmware(cp, name);
+#else
+	return false;
+#endif
+}
+
 static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
 static __init enum ucode_state
 scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
@@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd,
 	cd.size = 0;
 
 	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data)
-		return UCODE_ERROR;
+	if (!cd.data) {
+		if (!load_builtin_intel_microcode(&cd))
+			return UCODE_ERROR;
+	}
 
 	return get_matching_model_microcode(0, start, cd.data, cd.size,
 					    mc_saved_data, initrd, uci);
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
index cd47a510a3f1..1883d252ff7d 100644
--- a/arch/x86/kernel/cpu/microcode/intel_lib.c
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -31,11 +31,18 @@
 #include <asm/processor.h>
 #include <asm/msr.h>
 
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
-		 unsigned int sig, unsigned int pf)
+static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
+					unsigned int s2, unsigned int p2)
 {
-	return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+	if (s1 != s2)
+		return false;
+
+	/* Processor flags are either both 0 ... */
+	if (!p1 && !p2)
+		return true;
+
+	/* ... or they intersect. */
+	return p1 & p2;
 }
 
 int microcode_sanity_check(void *mc, int print_err)
@@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check);
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
+int find_matching_signature(void *mc, unsigned int csig, int cpf)
 {
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header;
-	unsigned long total_size = get_totalsize(mc_header);
-	int ext_sigcount, i;
+	struct microcode_header_intel *mc_hdr = mc;
+	struct extended_sigtable *ext_hdr;
 	struct extended_signature *ext_sig;
+	int i;
 
-	if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+	if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf))
 		return 1;
 
 	/* Look for ext. headers: */
-	if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+	if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE)
 		return 0;
 
-	ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+	ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE;
+	ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE;
 
-	for (i = 0; i < ext_sigcount; i++) {
-		if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+	for (i = 0; i < ext_hdr->count; i++) {
+		if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf))
 			return 1;
 		ext_sig++;
 	}
@@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc)
 /*
  * Returns 1 if update has been found, 0 otherwise.
  */
-int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc)
+int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev)
 {
 	struct microcode_header_intel *mc_hdr = mc;
 
-	if (!revision_is_newer(mc_hdr, rev))
+	if (mc_hdr->rev <= new_rev)
 		return 0;
 
-	return get_matching_sig(csig, cpf, rev, mc);
+	return find_matching_signature(mc, csig, cpf);
 }
-EXPORT_SYMBOL_GPL(get_matching_microcode);
+EXPORT_SYMBOL_GPL(has_newer_microcode);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155ffdece..aad4bd84b475 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	irq_enter();
-	exit_idle();
-
+	entering_irq();
 	inc_irq_stat(irq_hv_callback_count);
 	if (vmbus_handler)
 		vmbus_handler();
 
-	irq_exit();
+	exiting_irq();
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 5f90b85ff22e..70d7c93f4550 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range,
 			continue;
 		base = range_state[i].base_pfn;
 		if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed &&
-		    (mtrr_state.enabled & 1)) {
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+		    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
 			/* Var MTRR contains UC entry below 1M? Skip it: */
 			printk(BIOS_BUG_MSG, i);
 			if (base + size <= (1<<(20-PAGE_SHIFT)))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d74f7b3c6ba..3b533cf37c74 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr)
 	return 0;
 }
 
-/*
- * Error/Semi-error returns:
- * 0xFF - when MTRR is not enabled
- * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
- *		corresponds only to [start:*partial_end].
- *		Caller has to lookup again for [*partial_end:end].
+/**
+ * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries
+ *
+ * Return the MTRR fixed memory type of 'start'.
+ *
+ * MTRR fixed entries are divided into the following ways:
+ *  0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges
+ *  0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges
+ *  0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - Matched memory type
+ * MTRR_TYPE_INVALID - Unmatched
+ */
+static u8 mtrr_type_lookup_fixed(u64 start, u64 end)
+{
+	int idx;
+
+	if (start >= 0x100000)
+		return MTRR_TYPE_INVALID;
+
+	/* 0x0 - 0x7FFFF */
+	if (start < 0x80000) {
+		idx = 0;
+		idx += (start >> 16);
+		return mtrr_state.fixed_ranges[idx];
+	/* 0x80000 - 0xBFFFF */
+	} else if (start < 0xC0000) {
+		idx = 1 * 8;
+		idx += ((start - 0x80000) >> 14);
+		return mtrr_state.fixed_ranges[idx];
+	}
+
+	/* 0xC0000 - 0xFFFFF */
+	idx = 3 * 8;
+	idx += ((start - 0xC0000) >> 12);
+	return mtrr_state.fixed_ranges[idx];
+}
+
+/**
+ * mtrr_type_lookup_variable - look up memory type in MTRR variable entries
+ *
+ * Return Value:
+ * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched)
+ *
+ * Output Arguments:
+ * repeat - Set to 1 when [start:end] spanned across MTRR range and type
+ *	    returned corresponds only to [start:*partial_end].  Caller has
+ *	    to lookup again for [*partial_end:end].
+ *
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
+static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
+				    int *repeat, u8 *uniform)
 {
 	int i;
 	u64 base, mask;
 	u8 prev_match, curr_match;
 
 	*repeat = 0;
-	if (!mtrr_state_set)
-		return 0xFF;
-
-	if (!mtrr_state.enabled)
-		return 0xFF;
+	*uniform = 1;
 
-	/* Make end inclusive end, instead of exclusive */
+	/* Make end inclusive instead of exclusive */
 	end--;
 
-	/* Look in fixed ranges. Just return the type as per start */
-	if (mtrr_state.have_fixed && (start < 0x100000)) {
-		int idx;
-
-		if (start < 0x80000) {
-			idx = 0;
-			idx += (start >> 16);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0xC0000) {
-			idx = 1 * 8;
-			idx += ((start - 0x80000) >> 14);
-			return mtrr_state.fixed_ranges[idx];
-		} else if (start < 0x1000000) {
-			idx = 3 * 8;
-			idx += ((start - 0xC0000) >> 12);
-			return mtrr_state.fixed_ranges[idx];
-		}
-	}
-
-	/*
-	 * Look in variable ranges
-	 * Look of multiple ranges matching this address and pick type
-	 * as per MTRR precedence
-	 */
-	if (!(mtrr_state.enabled & 2))
-		return mtrr_state.def_type;
-
-	prev_match = 0xFF;
+	prev_match = MTRR_TYPE_INVALID;
 	for (i = 0; i < num_var_ranges; ++i) {
-		unsigned short start_state, end_state;
+		unsigned short start_state, end_state, inclusive;
 
 		if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11)))
 			continue;
@@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 		start_state = ((start & mask) == (base & mask));
 		end_state = ((end & mask) == (base & mask));
+		inclusive = ((start < base) && (end > base));
 
-		if (start_state != end_state) {
+		if ((start_state != end_state) || inclusive) {
 			/*
 			 * We have start:end spanning across an MTRR.
-			 * We split the region into
-			 * either
-			 * (start:mtrr_end) (mtrr_end:end)
-			 * or
-			 * (start:mtrr_start) (mtrr_start:end)
+			 * We split the region into either
+			 *
+			 * - start_state:1
+			 * (start:mtrr_end)(mtrr_end:end)
+			 * - end_state:1
+			 * (start:mtrr_start)(mtrr_start:end)
+			 * - inclusive:1
+			 * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end)
+			 *
 			 * depending on kind of overlap.
-			 * Return the type for first region and a pointer to
-			 * the start of second region so that caller will
-			 * lookup again on the second region.
-			 * Note: This way we handle multiple overlaps as well.
+			 *
+			 * Return the type of the first region and a pointer
+			 * to the start of next region so that caller will be
+			 * advised to lookup again after having adjusted start
+			 * and end.
+			 *
+			 * Note: This way we handle overlaps with multiple
+			 * entries and the default type properly.
 			 */
 			if (start_state)
 				*partial_end = base + get_mtrr_size(mask);
@@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 
 			end = *partial_end - 1; /* end is inclusive */
 			*repeat = 1;
+			*uniform = 0;
 		}
 
 		if ((start & mask) != (base & mask))
 			continue;
 
 		curr_match = mtrr_state.var_ranges[i].base_lo & 0xff;
-		if (prev_match == 0xFF) {
+		if (prev_match == MTRR_TYPE_INVALID) {
 			prev_match = curr_match;
 			continue;
 		}
 
+		*uniform = 0;
 		if (check_type_overlap(&prev_match, &curr_match))
 			return curr_match;
 	}
 
-	if (mtrr_tom2) {
-		if (start >= (1ULL<<32) && (end < mtrr_tom2))
-			return MTRR_TYPE_WRBACK;
-	}
-
-	if (prev_match != 0xFF)
+	if (prev_match != MTRR_TYPE_INVALID)
 		return prev_match;
 
 	return mtrr_state.def_type;
 }
 
-/*
- * Returns the effective MTRR type for the region
- * Error return:
- * 0xFF - when MTRR is not enabled
+/**
+ * mtrr_type_lookup - look up memory type in MTRR
+ *
+ * Return Values:
+ * MTRR_TYPE_(type)  - The effective MTRR type for the region
+ * MTRR_TYPE_INVALID - MTRR is disabled
+ *
+ * Output Argument:
+ * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the
+ *	     region is fully covered by a single MTRR entry or the default
+ *	     type.
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform)
 {
-	u8 type, prev_type;
+	u8 type, prev_type, is_uniform = 1, dummy;
 	int repeat;
 	u64 partial_end;
 
-	type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+	if (!mtrr_state_set)
+		return MTRR_TYPE_INVALID;
+
+	if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED))
+		return MTRR_TYPE_INVALID;
+
+	/*
+	 * Look up the fixed ranges first, which take priority over
+	 * the variable ranges.
+	 */
+	if ((start < 0x100000) &&
+	    (mtrr_state.have_fixed) &&
+	    (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) {
+		is_uniform = 0;
+		type = mtrr_type_lookup_fixed(start, end);
+		goto out;
+	}
+
+	/*
+	 * Look up the variable ranges.  Look of multiple ranges matching
+	 * this address and pick type as per MTRR precedence.
+	 */
+	type = mtrr_type_lookup_variable(start, end, &partial_end,
+					 &repeat, &is_uniform);
 
 	/*
 	 * Common path is with repeat = 0.
 	 * However, we can have cases where [start:end] spans across some
-	 * MTRR range. Do repeated lookups for that case here.
+	 * MTRR ranges and/or the default type.  Do repeated lookups for
+	 * that case here.
 	 */
 	while (repeat) {
 		prev_type = type;
 		start = partial_end;
-		type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+		is_uniform = 0;
+		type = mtrr_type_lookup_variable(start, end, &partial_end,
+						 &repeat, &dummy);
 
 		if (check_type_overlap(&prev_type, &type))
-			return type;
+			goto out;
 	}
 
+	if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2))
+		type = MTRR_TYPE_WRBACK;
+
+out:
+	*uniform = is_uniform;
 	return type;
 }
 
@@ -347,7 +408,9 @@ static void __init print_mtrr_state(void)
 		 mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
 		pr_debug("MTRR fixed ranges %sabled:\n",
-			 mtrr_state.enabled & 1 ? "en" : "dis");
+			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
+			 "en" : "dis");
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -360,7 +423,7 @@ static void __init print_mtrr_state(void)
 		print_fixed_last();
 	}
 	pr_debug("MTRR variable ranges %sabled:\n",
-		 mtrr_state.enabled & 2 ? "en" : "dis");
+		 mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
 	high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {
@@ -382,7 +445,7 @@ static void __init print_mtrr_state(void)
 }
 
 /* Grab all of the MTRR state for this CPU into *state */
-void __init get_mtrr_state(void)
+bool __init get_mtrr_state(void)
 {
 	struct mtrr_var_range *vrs;
 	unsigned long flags;
@@ -426,6 +489,8 @@ void __init get_mtrr_state(void)
 
 	post_set();
 	local_irq_restore(flags);
+
+	return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
 }
 
 /* Some BIOS's are messed up and don't set all MTRRs the same! */
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ea5f363a1948..e7ed0d8ebacb 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -59,6 +59,12 @@
 #define MTRR_TO_PHYS_WC_OFFSET 1000
 
 u32 num_var_ranges;
+static bool __mtrr_enabled;
+
+static bool mtrr_enabled(void)
+{
+	return __mtrr_enabled;
+}
 
 unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
 static DEFINE_MUTEX(mtrr_mutex);
@@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 	int i, replace, error;
 	mtrr_type ltype;
 
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return -ENXIO;
 
 	error = mtrr_if->validate_add_page(base, size, type);
@@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size)
 int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
 	     bool increment)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
@@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
 	unsigned long lbase, lsize;
 	int error = -EINVAL;
 
-	if (!mtrr_if)
-		return -ENXIO;
+	if (!mtrr_enabled())
+		return -ENODEV;
 
 	max = num_var_ranges;
 	/* No CPU hotplug when we change MTRR entries */
@@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
  */
 int mtrr_del(int reg, unsigned long base, unsigned long size)
 {
+	if (!mtrr_enabled())
+		return -ENODEV;
 	if (mtrr_check(base, size))
 		return -EINVAL;
 	return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
@@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del);
  * attempts to add a WC MTRR covering size bytes starting at base and
  * logs an error if this fails.
  *
+ * The called should provide a power of two size on an equivalent
+ * power of two boundary.
+ *
  * Drivers must store the return value to pass to mtrr_del_wc_if_needed,
  * but drivers should not try to interpret that return value.
  */
@@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size)
 {
 	int ret;
 
-	if (pat_enabled)
+	if (pat_enabled() || !mtrr_enabled())
 		return 0;  /* Success!  (We don't need to do anything.) */
 
 	ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
@@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle)
 EXPORT_SYMBOL(arch_phys_wc_del);
 
 /*
- * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * arch_phys_wc_index - translates arch_phys_wc_add's return value
  * @handle: Return value from arch_phys_wc_add
  *
  * This will turn the return value from arch_phys_wc_add into an mtrr
@@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del);
  * in printk line.  Alas there is an illegitimate use in some ancient
  * drm ioctls.
  */
-int phys_wc_to_mtrr_index(int handle)
+int arch_phys_wc_index(int handle)
 {
 	if (handle < MTRR_TO_PHYS_WC_OFFSET)
 		return -1;
 	else
 		return handle - MTRR_TO_PHYS_WC_OFFSET;
 }
-EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+EXPORT_SYMBOL_GPL(arch_phys_wc_index);
 
 /*
  * HACK ALERT!
@@ -734,10 +747,12 @@ void __init mtrr_bp_init(void)
 	}
 
 	if (mtrr_if) {
+		__mtrr_enabled = true;
 		set_num_var_ranges();
 		init_table();
 		if (use_intel()) {
-			get_mtrr_state();
+			/* BIOS may override */
+			__mtrr_enabled = get_mtrr_state();
 
 			if (mtrr_cleanup(phys_addr)) {
 				changed_by_mtrr_cleanup = 1;
@@ -745,10 +760,16 @@ void __init mtrr_bp_init(void)
 			}
 		}
 	}
+
+	if (!mtrr_enabled())
+		pr_info("MTRR: Disabled\n");
 }
 
 void mtrr_ap_init(void)
 {
+	if (!mtrr_enabled())
+		return;
+
 	if (!use_intel() || mtrr_aps_delayed_init)
 		return;
 	/*
@@ -774,6 +795,9 @@ void mtrr_save_state(void)
 {
 	int first_cpu;
 
+	if (!mtrr_enabled())
+		return;
+
 	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
@@ -782,6 +806,8 @@ void mtrr_save_state(void)
 
 void set_mtrr_aps_delayed_init(void)
 {
+	if (!mtrr_enabled())
+		return;
 	if (!use_intel())
 		return;
 
@@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void)
  */
 void mtrr_aps_init(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	/*
@@ -810,7 +836,7 @@ void mtrr_aps_init(void)
 
 void mtrr_bp_restore(void)
 {
-	if (!use_intel())
+	if (!use_intel() || !mtrr_enabled())
 		return;
 
 	mtrr_if->set_all();
@@ -818,7 +844,7 @@ void mtrr_bp_restore(void)
 
 static int __init mtrr_init_finialize(void)
 {
-	if (!mtrr_if)
+	if (!mtrr_enabled())
 		return 0;
 
 	if (use_intel()) {
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index df5e41f31a27..951884dcc433 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
 
 void fill_mtrr_var_range(unsigned int index,
 		u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
-void get_mtrr_state(void);
+bool get_mtrr_state(void);
 
 extern void set_mtrr_ops(const struct mtrr_ops *ops);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 87848ebe2bb7..5801a14f7524 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 }
 
 static atomic_t active_events;
+static atomic_t pmc_refcount;
 static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -190,6 +191,7 @@ static bool check_hw_exists(void)
 	u64 val, val_fail, val_new= ~0;
 	int i, reg, reg_fail, ret = 0;
 	int bios_fail = 0;
+	int reg_safe = -1;
 
 	/*
 	 * Check to see if the BIOS enabled any of the counters, if so
@@ -204,6 +206,8 @@ static bool check_hw_exists(void)
 			bios_fail = 1;
 			val_fail = val;
 			reg_fail = reg;
+		} else {
+			reg_safe = i;
 		}
 	}
 
@@ -222,11 +226,22 @@ static bool check_hw_exists(void)
 	}
 
 	/*
+	 * If all the counters are enabled, the below test will always
+	 * fail.  The tools will also become useless in this scenario.
+	 * Just fail and disable the hardware counters.
+	 */
+
+	if (reg_safe == -1) {
+		reg = reg_safe;
+		goto msr_fail;
+	}
+
+	/*
 	 * Read the current value, change it and read it back to see if it
 	 * matches, this is needed to detect certain hardware emulators
 	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
 	 */
-	reg = x86_pmu_event_addr(0);
+	reg = x86_pmu_event_addr(reg_safe);
 	if (rdmsrl_safe(reg, &val))
 		goto msr_fail;
 	val ^= 0xffffUL;
@@ -256,11 +271,8 @@ msr_fail:
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
-	if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) {
-		release_pmc_hardware();
-		release_ds_buffers();
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	x86_release_hardware();
+	atomic_dec(&active_events);
 }
 
 void hw_perf_lbr_event_destroy(struct perf_event *event)
@@ -310,6 +322,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 	return x86_pmu_extra_regs(val, event);
 }
 
+int x86_reserve_hardware(void)
+{
+	int err = 0;
+
+	if (!atomic_inc_not_zero(&pmc_refcount)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&pmc_refcount) == 0) {
+			if (!reserve_pmc_hardware())
+				err = -EBUSY;
+			else
+				reserve_ds_buffers();
+		}
+		if (!err)
+			atomic_inc(&pmc_refcount);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+
+	return err;
+}
+
+void x86_release_hardware(void)
+{
+	if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) {
+		release_pmc_hardware();
+		release_ds_buffers();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
 /*
  * Check if we can create event of a certain type (that no conflicting events
  * are present).
@@ -322,21 +363,34 @@ int x86_add_exclusive(unsigned int what)
 		return 0;
 
 	mutex_lock(&pmc_reserve_mutex);
-	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++)
+	for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
 		if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i]))
 			goto out;
+	}
 
 	atomic_inc(&x86_pmu.lbr_exclusive[what]);
 	ret = 0;
 
 out:
 	mutex_unlock(&pmc_reserve_mutex);
+
+	/*
+	 * Assuming that all exclusive events will share the PMI handler
+	 * (which checks active_events for whether there is work to do),
+	 * we can bump active_events counter right here, except for
+	 * x86_lbr_exclusive_lbr events that go through x86_pmu_event_init()
+	 * path, which already bumps active_events for them.
+	 */
+	if (!ret && what != x86_lbr_exclusive_lbr)
+		atomic_inc(&active_events);
+
 	return ret;
 }
 
 void x86_del_exclusive(unsigned int what)
 {
 	atomic_dec(&x86_pmu.lbr_exclusive[what]);
+	atomic_dec(&active_events);
 }
 
 int x86_setup_perfctr(struct perf_event *event)
@@ -513,22 +567,11 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	if (!x86_pmu_initialized())
 		return -ENODEV;
 
-	err = 0;
-	if (!atomic_inc_not_zero(&active_events)) {
-		mutex_lock(&pmc_reserve_mutex);
-		if (atomic_read(&active_events) == 0) {
-			if (!reserve_pmc_hardware())
-				err = -EBUSY;
-			else
-				reserve_ds_buffers();
-		}
-		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmc_reserve_mutex);
-	}
+	err = x86_reserve_hardware();
 	if (err)
 		return err;
 
+	atomic_inc(&active_events);
 	event->destroy = hw_perf_event_destroy;
 
 	event->hw.idx = -1;
@@ -611,6 +654,7 @@ struct sched_state {
 	int	event;		/* event index */
 	int	counter;	/* counter index */
 	int	unassigned;	/* number of events to be assigned left */
+	int	nr_gp;		/* number of GP counters used */
 	unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 };
 
@@ -620,27 +664,29 @@ struct sched_state {
 struct perf_sched {
 	int			max_weight;
 	int			max_events;
-	struct perf_event	**events;
-	struct sched_state	state;
+	int			max_gp;
 	int			saved_states;
+	struct event_constraint	**constraints;
+	struct sched_state	state;
 	struct sched_state	saved[SCHED_STATES_MAX];
 };
 
 /*
  * Initialize interator that runs through all events and counters.
  */
-static void perf_sched_init(struct perf_sched *sched, struct perf_event **events,
-			    int num, int wmin, int wmax)
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
+			    int num, int wmin, int wmax, int gpmax)
 {
 	int idx;
 
 	memset(sched, 0, sizeof(*sched));
 	sched->max_events	= num;
 	sched->max_weight	= wmax;
-	sched->events		= events;
+	sched->max_gp		= gpmax;
+	sched->constraints	= constraints;
 
 	for (idx = 0; idx < num; idx++) {
-		if (events[idx]->hw.constraint->weight == wmin)
+		if (constraints[idx]->weight == wmin)
 			break;
 	}
 
@@ -687,7 +733,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 	if (sched->state.event >= sched->max_events)
 		return false;
 
-	c = sched->events[sched->state.event]->hw.constraint;
+	c = sched->constraints[sched->state.event];
 	/* Prefer fixed purpose counters */
 	if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) {
 		idx = INTEL_PMC_IDX_FIXED;
@@ -696,11 +742,16 @@ static bool __perf_sched_find_counter(struct perf_sched *sched)
 				goto done;
 		}
 	}
+
 	/* Grab the first unused counter starting with idx */
 	idx = sched->state.counter;
 	for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) {
-		if (!__test_and_set_bit(idx, sched->state.used))
+		if (!__test_and_set_bit(idx, sched->state.used)) {
+			if (sched->state.nr_gp++ >= sched->max_gp)
+				return false;
+
 			goto done;
+		}
 	}
 
 	return false;
@@ -745,7 +796,7 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 			if (sched->state.weight > sched->max_weight)
 				return false;
 		}
-		c = sched->events[sched->state.event]->hw.constraint;
+		c = sched->constraints[sched->state.event];
 	} while (c->weight != sched->state.weight);
 
 	sched->state.counter = 0;	/* start with first counter */
@@ -756,12 +807,12 @@ static bool perf_sched_next_event(struct perf_sched *sched)
 /*
  * Assign a counter for each event.
  */
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign)
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign)
 {
 	struct perf_sched sched;
 
-	perf_sched_init(&sched, events, n, wmin, wmax);
+	perf_sched_init(&sched, constraints, n, wmin, wmax, gpmax);
 
 	do {
 		if (!perf_sched_find_counter(&sched))
@@ -788,9 +839,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &cpuc->event_list[i]->hw;
+		cpuc->event_constraint[i] = NULL;
 		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		hwc->constraint = c;
+		cpuc->event_constraint[i] = c;
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -801,7 +852,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	 */
 	for (i = 0; i < n; i++) {
 		hwc = &cpuc->event_list[i]->hw;
-		c = hwc->constraint;
+		c = cpuc->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -821,9 +872,26 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	}
 
 	/* slow path */
-	if (i != n)
-		unsched = perf_assign_events(cpuc->event_list, n, wmin,
-					     wmax, assign);
+	if (i != n) {
+		int gpmax = x86_pmu.num_counters;
+
+		/*
+		 * Do not allow scheduling of more than half the available
+		 * generic counters.
+		 *
+		 * This helps avoid counter starvation of sibling thread by
+		 * ensuring at most half the counters cannot be in exclusive
+		 * mode. There is no designated counters for the limits. Any
+		 * N/2 counters can be used. This helps with events with
+		 * specific counter constraints.
+		 */
+		if (is_ht_workaround_enabled() && !cpuc->is_fake &&
+		    READ_ONCE(cpuc->excl_cntrs->exclusive_present))
+			gpmax /= 2;
+
+		unsched = perf_assign_events(cpuc->event_constraint, n, wmin,
+					     wmax, gpmax, assign);
+	}
 
 	/*
 	 * In case of success (unsched = 0), mark events as committed,
@@ -840,12 +908,9 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			e = cpuc->event_list[i];
 			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
 			if (x86_pmu.commit_scheduling)
-				x86_pmu.commit_scheduling(cpuc, e, assign[i]);
+				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
-	}
-
-	if (!assign || unsched) {
-
+	} else {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
 			/*
@@ -1058,13 +1123,16 @@ int x86_perf_event_set_period(struct perf_event *event)
 
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
-	/*
-	 * The hw event starts counting from this event offset,
-	 * mark it to be able to extra future deltas:
-	 */
-	local64_set(&hwc->prev_count, (u64)-left);
+	if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+	    local64_read(&hwc->prev_count) != (u64)-left) {
+		/*
+		 * The hw event starts counting from this event offset,
+		 * mark it to be able to extra future deltas:
+		 */
+		local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	/*
 	 * Due to erratum on certan cpu we need
@@ -1292,8 +1360,10 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 		x86_pmu.put_event_constraints(cpuc, event);
 
 	/* Delete the array entry. */
-	while (++i < cpuc->n_events)
+	while (++i < cpuc->n_events) {
 		cpuc->event_list[i-1] = cpuc->event_list[i];
+		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+	}
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
@@ -1374,6 +1444,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 	u64 finish_clock;
 	int ret;
 
+	/*
+	 * All PMUs/events that share this PMI handler should make sure to
+	 * increment active_events for their events.
+	 */
 	if (!atomic_read(&active_events))
 		return NMI_DONE;
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6ac5cb7a9e14..3e7fd27dfe20 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -74,6 +74,9 @@ struct event_constraint {
 #define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
 #define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
 
 
 struct amd_nb {
@@ -87,6 +90,18 @@ struct amd_nb {
 #define MAX_PEBS_EVENTS		8
 
 /*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+	PERF_SAMPLE_TRANSACTION)
+
+/*
  * A debug store configuration.
  *
  * We only support architectures that use 64bit fields.
@@ -132,10 +147,7 @@ enum intel_excl_state_type {
 };
 
 struct intel_excl_states {
-	enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
 	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
-	int  num_alloc_cntrs;/* #counters allocated */
-	int  max_alloc_cntrs;/* max #counters allowed */
 	bool sched_started; /* true if scheduling has started */
 };
 
@@ -144,6 +156,11 @@ struct intel_excl_cntrs {
 
 	struct intel_excl_states states[2];
 
+	union {
+		u16	has_exclusive[2];
+		u32	exclusive_present;
+	};
+
 	int		refcnt;		/* per-core: #HT threads */
 	unsigned	core_id;	/* per-core: core id */
 };
@@ -172,7 +189,11 @@ struct cpu_hw_events {
 					     added in the current transaction */
 	int			assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
 	u64			tags[X86_PMC_IDX_MAX];
+
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
+	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
+
+	int			n_excl; /* the number of exclusive events */
 
 	unsigned int		group_flag;
 	int			is_fake;
@@ -519,12 +540,10 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 
-	void		(*commit_scheduling)(struct cpu_hw_events *cpuc,
-					     struct perf_event *event,
-					     int cntr);
-
 	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
 
+	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
 	void		(*stop_scheduling)(struct cpu_hw_events *cpuc);
 
 	struct event_constraint *event_constraints;
@@ -697,6 +716,10 @@ int x86_add_exclusive(unsigned int what);
 
 void x86_del_exclusive(unsigned int what);
 
+int x86_reserve_hardware(void);
+
+void x86_release_hardware(void);
+
 void hw_perf_lbr_event_destroy(struct perf_event *event);
 
 int x86_setup_perfctr(struct perf_event *event);
@@ -717,8 +740,8 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 
 void x86_pmu_enable_all(int added);
 
-int perf_assign_events(struct perf_event **events, int n,
-			int wmin, int wmax, int *assign);
+int perf_assign_events(struct event_constraint **constraints, int n,
+			int wmin, int wmax, int gpmax, int *assign);
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign);
 
 void x86_pmu_stop(struct perf_event *event, int flags);
@@ -860,6 +883,8 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
@@ -929,4 +954,8 @@ static inline struct intel_shared_regs *allocate_shared_regs(int cpu)
 	return NULL;
 }
 
+static inline int is_ht_workaround_enabled(void)
+{
+	return 0;
+}
 #endif /* CONFIG_CPU_SUP_INTEL */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 219d3fb423a1..b9826a981fb2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
-		[ C(RESULT_MISS)   ] = SLM_DMND_READ|SLM_LLC_MISS,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
@@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids
 	[ C(OP_READ) ] = {
 		/* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
 		[ C(RESULT_ACCESS) ] = 0x01b7,
-		/* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
-		[ C(RESULT_MISS)   ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_WRITE) ] = {
 		/* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
@@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids
  [ C(ITLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
-		[ C(RESULT_MISS)   ] = 0x0282, /* ITLB.MISSES */
+		[ C(RESULT_MISS)   ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = -1,
@@ -1904,9 +1903,8 @@ static void
 intel_start_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1917,35 +1915,52 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
 	xl->sched_started = true;
-	xl->num_alloc_cntrs = 0;
 	/*
 	 * lock shared state until we are done scheduling
 	 * in stop_event_scheduling()
 	 * makes scheduling appear as a transaction
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
 	raw_spin_lock(&excl_cntrs->lock);
+}
 
-	/*
-	 * save initial state of sibling thread
-	 */
-	memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+	struct event_constraint *c = cpuc->event_constraint[idx];
+	struct intel_excl_states *xl;
+	int tid = cpuc->excl_thread_id;
+
+	if (cpuc->is_fake || !is_ht_workaround_enabled())
+		return;
+
+	if (WARN_ON_ONCE(!excl_cntrs))
+		return;
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+		return;
+
+	xl = &excl_cntrs->states[tid];
+
+	lockdep_assert_held(&excl_cntrs->lock);
+
+	if (c->flags & PERF_X86_EVENT_EXCL)
+		xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+	else
+		xl->state[cntr] = INTEL_EXCL_SHARED;
 }
 
 static void
 intel_stop_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1955,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
-	/*
-	 * make new sibling thread state visible
-	 */
-	memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
 	xl->sched_started = false;
 	/*
 	 * release shared state lock (acquired in intel_start_scheduling())
@@ -1977,12 +1986,10 @@ static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
-	struct event_constraint *cx;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
-	int is_excl, i;
+	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* alternate */
+	int is_excl, i;
 
 	/*
 	 * validating a group does not require
@@ -1994,34 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return c;
-	/*
-	 * event requires exclusive counter access
-	 * across HT threads
-	 */
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	/*
-	 * xl = state of current HT
-	 * xlo = state of sibling HT
-	 */
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	/*
-	 * do not allow scheduling of more than max_alloc_cntrs
-	 * which is set to half the available generic counters.
-	 * this helps avoid counter starvation of sibling thread
-	 * by ensuring at most half the counters cannot be in
-	 * exclusive mode. There is not designated counters for the
-	 * limits. Any N/2 counters can be used. This helps with
-	 * events with specifix counter constraints
-	 */
-	if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs)
-		return &emptyconstraint;
-
-	cx = c;
 
 	/*
 	 * because we modify the constraint, we need
@@ -2032,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * been cloned (marked dynamic)
 	 */
 	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
-		/* sanity check */
-		if (idx < 0)
-			return &emptyconstraint;
+		struct event_constraint *cx;
 
 		/*
 		 * grab pre-allocated constraint entry
@@ -2046,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 		 * initialize dynamic constraint
 		 * with static constraint
 		 */
-		memcpy(cx, c, sizeof(*cx));
+		*cx = *c;
 
 		/*
 		 * mark constraint as dynamic, so we
 		 * can free it later on
 		 */
 		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
 	}
 
 	/*
@@ -2063,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 */
 
 	/*
+	 * state of sibling HT
+	 */
+	xlo = &excl_cntrs->states[tid ^ 1];
+
+	/*
+	 * event requires exclusive counter access
+	 * across HT threads
+	 */
+	is_excl = c->flags & PERF_X86_EVENT_EXCL;
+	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+		if (!cpuc->n_excl++)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+	}
+
+	/*
 	 * Modify static constraint with current dynamic
 	 * state of thread
 	 *
@@ -2070,44 +2065,44 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
-	for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
-			__clear_bit(i, cx->idxmsk);
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+			__clear_bit(i, c->idxmsk);
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
-			__clear_bit(i, cx->idxmsk);
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+			__clear_bit(i, c->idxmsk);
 	}
 
 	/*
 	 * recompute actual bit weight for scheduling algorithm
 	 */
-	cx->weight = hweight64(cx->idxmsk64);
+	c->weight = hweight64(c->idxmsk64);
 
 	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (cx->weight == 0)
-		cx = &emptyconstraint;
+	if (c->weight == 0)
+		c = &emptyconstraint;
 
-	return cx;
+	return c;
 }
 
 static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = event->hw.constraint;
+	struct event_constraint *c1 = cpuc->event_constraint[idx];
 	struct event_constraint *c2;
 
 	/*
@@ -2133,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xlo, *xl;
-	unsigned long flags = 0; /* keep compiler happy */
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
+	struct intel_excl_states *xl;
 
 	/*
 	 * nothing needed if in group validation mode
@@ -2144,31 +2137,35 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	if (cpuc->is_fake)
 		return;
 
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
+	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
+		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
+		if (!--cpuc->n_excl)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 0);
+	}
 
 	/*
-	 * put_constraint may be called from x86_schedule_events()
-	 * which already has the lock held so here make locking
-	 * conditional
+	 * If event was actually assigned, then mark the counter state as
+	 * unused now.
 	 */
-	if (!xl->sched_started)
-		raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+	if (hwc->idx >= 0) {
+		xl = &excl_cntrs->states[tid];
 
-	/*
-	 * if event was actually assigned, then mark the
-	 * counter state as unused now
-	 */
-	if (hwc->idx >= 0)
-		xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+		/*
+		 * put_constraint may be called from x86_schedule_events()
+		 * which already has the lock held so here make locking
+		 * conditional.
+		 */
+		if (!xl->sched_started)
+			raw_spin_lock(&excl_cntrs->lock);
+
+		xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
 
-	if (!xl->sched_started)
-		raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+		if (!xl->sched_started)
+			raw_spin_unlock(&excl_cntrs->lock);
+	}
 }
 
 static void
@@ -2189,8 +2186,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc,
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
-	struct event_constraint *c = event->hw.constraint;
-
 	intel_put_shared_regs_event_constraints(cpuc, event);
 
 	/*
@@ -2198,48 +2193,8 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	 * all events are subject to and must call the
 	 * put_excl_constraints() routine
 	 */
-	if (c && cpuc->excl_cntrs)
+	if (cpuc->excl_cntrs)
 		intel_put_excl_constraints(cpuc, event);
-
-	/* cleanup dynamic constraint */
-	if (c && (c->flags & PERF_X86_EVENT_DYNAMIC))
-		event->hw.constraint = NULL;
-}
-
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc,
-				    struct perf_event *event, int cntr)
-{
-	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct event_constraint *c = event->hw.constraint;
-	struct intel_excl_states *xlo, *xl;
-	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
-	int is_excl;
-
-	if (cpuc->is_fake || !c)
-		return;
-
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
-		return;
-
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
-		return;
-
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
-	if (cntr >= 0) {
-		if (is_excl)
-			xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
-		else
-			xlo->init_state[cntr] = INTEL_EXCL_SHARED;
-	}
 }
 
 static void intel_pebs_aliases_core2(struct perf_event *event)
@@ -2305,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if (!event->attr.freq) {
+			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+			if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+		}
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -2533,34 +2495,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-static __initconst const struct x86_pmu core_pmu = {
-	.name			= "core",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= core_pmu_enable_all,
-	.enable			= core_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.hw_config		= x86_pmu_hw_config,
-	.schedule_events	= x86_schedule_events,
-	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
-	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
-	.event_map		= intel_pmu_event_map,
-	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
-	.apic			= 1,
-	/*
-	 * Intel PMCs cannot be accessed sanely above 32 bit width,
-	 * so we install an artificial 1<<31 period regardless of
-	 * the generic event period:
-	 */
-	.max_period		= (1ULL << 31) - 1,
-	.get_event_constraints	= intel_get_event_constraints,
-	.put_event_constraints	= intel_put_event_constraints,
-	.event_constraints	= intel_core_event_constraints,
-	.guest_get_msrs		= core_guest_get_msrs,
-	.format_attrs		= intel_arch_formats_attr,
-	.events_sysfs_show	= intel_event_sysfs_show,
-};
-
 struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
@@ -2583,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu)
 static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 {
 	struct intel_excl_cntrs *c;
-	int i;
 
 	c = kzalloc_node(sizeof(struct intel_excl_cntrs),
 			 GFP_KERNEL, cpu_to_node(cpu));
 	if (c) {
 		raw_spin_lock_init(&c->lock);
-		for (i = 0; i < X86_PMC_IDX_MAX; i++) {
-			c->states[0].state[i] = INTEL_EXCL_UNUSED;
-			c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
-			c->states[1].state[i] = INTEL_EXCL_UNUSED;
-			c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
-		}
 		c->core_id = -1;
 	}
 	return c;
@@ -2650,7 +2576,7 @@ static void intel_pmu_cpu_starting(int cpu)
 	if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) {
 		void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED];
 
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_shared_regs *pc;
 
 			pc = per_cpu(cpu_hw_events, i).shared_regs;
@@ -2668,9 +2594,7 @@ static void intel_pmu_cpu_starting(int cpu)
 		cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR];
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
-		int h = x86_pmu.num_counters >> 1;
-
-		for_each_cpu(i, topology_thread_cpumask(cpu)) {
+		for_each_cpu(i, topology_sibling_cpumask(cpu)) {
 			struct intel_excl_cntrs *c;
 
 			c = per_cpu(cpu_hw_events, i).excl_cntrs;
@@ -2683,11 +2607,6 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 		cpuc->excl_cntrs->core_id = core_id;
 		cpuc->excl_cntrs->refcnt++;
-		/*
-		 * set hard limit to half the number of generic counters
-		 */
-		cpuc->excl_cntrs->states[0].max_alloc_cntrs = h;
-		cpuc->excl_cntrs->states[1].max_alloc_cntrs = h;
 	}
 }
 
@@ -2723,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+				 bool sched_in)
+{
+	if (x86_pmu.pebs_active)
+		intel_pmu_pebs_sched_task(ctx, sched_in);
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2743,6 +2671,44 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static __initconst const struct x86_pmu core_pmu = {
+	.name			= "core",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= intel_pmu_event_map,
+	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
+	.apic			= 1,
+	/*
+	 * Intel PMCs cannot be accessed sanely above 32-bit width,
+	 * so we install an artificial 1<<31 period regardless of
+	 * the generic event period:
+	 */
+	.max_period		= (1ULL<<31) - 1,
+	.get_event_constraints	= intel_get_event_constraints,
+	.put_event_constraints	= intel_put_event_constraints,
+	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
+	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
+	/*
+	 * Virtual (or funny metal) CPU can define x86_pmu.extra_regs
+	 * together with PMU version 1 and thus be using core_pmu with
+	 * shared_regs. We need following callbacks here to allocate
+	 * it properly.
+	 */
+	.cpu_prepare		= intel_pmu_cpu_prepare,
+	.cpu_starting		= intel_pmu_cpu_starting,
+	.cpu_dying		= intel_pmu_cpu_dying,
+};
+
 static __initconst const struct x86_pmu intel_pmu = {
 	.name			= "Intel",
 	.handle_irq		= intel_pmu_handle_irq,
@@ -2774,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
-	.sched_task		= intel_pmu_lbr_sched_task,
+	.sched_task		= intel_pmu_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -2947,8 +2913,8 @@ static __init void intel_ht_bug(void)
 {
 	x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
 
-	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.start_scheduling = intel_start_scheduling;
+	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.stop_scheduling = intel_stop_scheduling;
 }
 
@@ -3261,6 +3227,8 @@ __init int intel_pmu_init(void)
 
 	case 61: /* 14nm Broadwell Core-M */
 	case 86: /* 14nm Broadwell Xeon D */
+	case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */
+	case 79: /* 14nm Broadwell Server */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -3330,13 +3298,13 @@ __init int intel_pmu_init(void)
 		 * counter, so do not extend mask to generic counters
 		 */
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if (c->cmask != FIXED_EVENT_FLAGS
-			    || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) {
-				continue;
+			if (c->cmask == FIXED_EVENT_FLAGS
+			    && c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) {
+				c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
 			}
-
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 &=
+				~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed));
+			c->weight = hweight64(c->idxmsk64);
 		}
 	}
 
@@ -3394,7 +3362,7 @@ static __init int fixup_ht_bug(void)
 	if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED))
 		return 0;
 
-	w = cpumask_weight(topology_thread_cpumask(cpu));
+	w = cpumask_weight(topology_sibling_cpumask(cpu));
 	if (w > 1) {
 		pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n");
 		return 0;
@@ -3404,8 +3372,8 @@ static __init int fixup_ht_bug(void)
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
-	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.start_scheduling = NULL;
+	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
 	watchdog_nmi_enable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index ac1f0c55f379..7795f3f8b1d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -483,17 +483,26 @@ static int bts_event_add(struct perf_event *event, int mode)
 
 static void bts_event_destroy(struct perf_event *event)
 {
+	x86_release_hardware();
 	x86_del_exclusive(x86_lbr_exclusive_bts);
 }
 
 static int bts_event_init(struct perf_event *event)
 {
+	int ret;
+
 	if (event->attr.type != bts_pmu.type)
 		return -ENOENT;
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;
 
+	ret = x86_reserve_hardware();
+	if (ret) {
+		x86_del_exclusive(x86_lbr_exclusive_bts);
+		return ret;
+	}
+
 	event->destroy = bts_event_destroy;
 
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e4d1b8b738fa..188076161c1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -13,16 +13,35 @@
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 
-struct intel_cqm_state {
-	raw_spinlock_t		lock;
-	int			rmid;
-	int			cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
 };
 
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 
 /*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask;
  * near-zero occupancy value, i.e. no cachelines are tagged with this
  * RMID, once __intel_cqm_rmid_rotate() returns.
  */
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
 
 #define INVALID_RMID		(-1)
 
@@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid;
  * Likewise, an rmid value of -1 is used to indicate "no rmid currently
  * assigned" and is used as part of the rotation code.
  */
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
 {
 	if (!rmid || rmid == INVALID_RMID)
 		return false;
@@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid)
 	return true;
 }
 
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
 {
 	u64 val;
 
@@ -102,7 +121,7 @@ enum rmid_recycle_state {
 };
 
 struct cqm_rmid_entry {
-	unsigned int rmid;
+	u32 rmid;
 	enum rmid_recycle_state state;
 	struct list_head list;
 	unsigned long queue_time;
@@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru);
  */
 static struct cqm_rmid_entry **cqm_rmid_ptrs;
 
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
  *
  * We expect to be called with cache_mutex held.
  */
-static int __get_rmid(void)
+static u32 __get_rmid(void)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -177,7 +196,7 @@ static int __get_rmid(void)
 	return entry->rmid;
 }
 
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
 }
 
 struct rmid_read {
-	unsigned int rmid;
+	u32 rmid;
 	atomic64_t value;
 };
 
@@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info);
 /*
  * Exchange the RMID of a group of events.
  */
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 {
 	struct perf_event *event;
-	unsigned int old_rmid = group->hw.cqm_rmid;
 	struct list_head *head = &group->hw.cqm_group_entry;
+	u32 old_rmid = group->hw.cqm_rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg)
  * If we have group events waiting for an RMID that don't conflict with
  * events already running, assign @rmid.
  */
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
 {
 	struct perf_event *leader, *event;
 
@@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available)
 static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 {
 	struct perf_event *rotor;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
 {
 	struct perf_event *group, *g;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event,
 				  struct perf_event **group)
 {
 	struct perf_event *iter;
-	unsigned int rmid;
 	bool conflict = false;
+	u32 rmid;
 
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
@@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 static void intel_cqm_event_read(struct perf_event *event)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 	u64 val;
 
 	/*
@@ -961,55 +979,48 @@ out:
 
 static void intel_cqm_event_start(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned int rmid = event->hw.cqm_rmid;
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	u32 rmid = event->hw.cqm_rmid;
 
 	if (!(event->hw.cqm_state & PERF_HES_STOPPED))
 		return;
 
 	event->hw.cqm_state &= ~PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
-
-	if (state->cnt++)
-		WARN_ON_ONCE(state->rmid != rmid);
-	else
+	if (state->rmid_usecnt++) {
+		if (!WARN_ON_ONCE(state->rmid != rmid))
+			return;
+	} else {
 		WARN_ON_ONCE(state->rmid);
+	}
 
 	state->rmid = rmid;
-	wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
+	wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
 }
 
 static void intel_cqm_event_stop(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	if (event->hw.cqm_state & PERF_HES_STOPPED)
 		return;
 
 	event->hw.cqm_state |= PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
 	intel_cqm_event_read(event);
 
-	if (!--state->cnt) {
+	if (!--state->rmid_usecnt) {
 		state->rmid = 0;
-		wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+		wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
 	} else {
 		WARN_ON_ONCE(!state->rmid);
 	}
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
 }
 
 static int intel_cqm_event_add(struct perf_event *event, int mode)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 
 	raw_spin_lock_irqsave(&cache_lock, flags);
 
@@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
-	intel_cqm_event_stop(event, mode);
-}
-
 static void intel_cqm_event_destroy(struct perf_event *event)
 {
 	struct perf_event *group_other = NULL;
@@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event)
 			list_replace(&event->hw.cqm_groups_entry,
 				     &group_other->hw.cqm_groups_entry);
 		} else {
-			unsigned int rmid = event->hw.cqm_rmid;
+			u32 rmid = event->hw.cqm_rmid;
 
 			if (__rmid_valid(rmid))
 				__put_rmid(rmid);
@@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = {
 	.task_ctx_nr	     = perf_sw_context,
 	.event_init	     = intel_cqm_event_init,
 	.add		     = intel_cqm_event_add,
-	.del		     = intel_cqm_event_del,
+	.del		     = intel_cqm_event_stop,
 	.start		     = intel_cqm_event_start,
 	.stop		     = intel_cqm_event_stop,
 	.read		     = intel_cqm_event_read,
@@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu)
 
 static void intel_cqm_cpu_prepare(unsigned int cpu)
 {
-	struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	raw_spin_lock_init(&state->lock);
 	state->rmid = 0;
-	state->cnt  = 0;
+	state->closid = 0;
+	state->rmid_usecnt = 0;
 
 	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
 	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 813f75d71175..71fc40238843 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -11,7 +11,7 @@
 #define BTS_RECORD_SIZE		24
 
 #define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	PAGE_SIZE
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 	int node = cpu_to_node(cpu);
-	int max, thresh = 1; /* always use a single PEBS record */
+	int max;
 	void *buffer, *ibuffer;
 
 	if (!x86_pmu.pebs)
@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
 	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
 		max * x86_pmu.pebs_record_size;
 
-	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-		thresh * x86_pmu.pebs_record_size;
-
 	return 0;
 }
 
@@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
 	return 1;
 }
 
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+	struct pt_regs regs;
+
+	x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	if (!sched_in)
+		intel_pmu_drain_pebs_buffer();
+}
+
 /*
  * PEBS
  */
@@ -684,33 +694,81 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+	bool first_pebs;
+	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
+	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
+
+	/*
+	 * When the event is constrained enough we can use a larger
+	 * threshold and run the event with less frequent PMI.
+	 */
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+		if (first_pebs)
+			perf_sched_cb_inc(event->ctx->pmu);
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+		/*
+		 * If not all events can use larger buffer,
+		 * roll back to threshold = 1
+		 */
+		if (!first_pebs &&
+		    (ds->pebs_interrupt_threshold > threshold))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
+	/* Use auto-reload if possible to save a MSR write in the PMI */
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		ds->pebs_event_reset[hwc->idx] =
+			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	}
+
+	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+		ds->pebs_interrupt_threshold = threshold;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
-	if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
-	else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST)
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	if (ds->pebs_interrupt_threshold >
+	    ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+		intel_pmu_drain_pebs_buffer();
+		if (!pebs_is_enabled(cpuc))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 	return txn;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
 {
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
@@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
-	struct perf_sample_data data;
-	struct pt_regs regs;
 	u64 sample_type;
 	int fll, fst, dsrc;
 	int fl = event->hw.flags;
 
-	if (!intel_pmu_save_and_restart(event))
+	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
@@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
 	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
-	perf_sample_data_init(&data, 0, event->hw.last_period);
+	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data.period = event->hw.last_period;
+	data->period = event->hw.last_period;
 
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
 	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-		data.weight = pebs->lat;
+		data->weight = pebs->lat;
 
 	/*
 	 * data.data_src encodes the data source
@@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			val = precise_datala_hsw(event, pebs->dse);
 		else if (fst)
 			val = precise_store_data(pebs->dse);
-		data.data_src.val = val;
+		data->data_src.val = val;
 	}
 
 	/*
@@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
 	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
 	 */
-	regs = *iregs;
-	regs.flags = pebs->flags;
-	set_linear_ip(&regs, pebs->ip);
-	regs.bp = pebs->bp;
-	regs.sp = pebs->sp;
+	*regs = *iregs;
+	regs->flags = pebs->flags;
+	set_linear_ip(regs, pebs->ip);
+	regs->bp = pebs->bp;
+	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
-		regs.ax = pebs->ax;
-		regs.bx = pebs->bx;
-		regs.cx = pebs->cx;
-		regs.dx = pebs->dx;
-		regs.si = pebs->si;
-		regs.di = pebs->di;
-		regs.bp = pebs->bp;
-		regs.sp = pebs->sp;
-
-		regs.flags = pebs->flags;
+		regs->ax = pebs->ax;
+		regs->bx = pebs->bx;
+		regs->cx = pebs->cx;
+		regs->dx = pebs->dx;
+		regs->si = pebs->si;
+		regs->di = pebs->di;
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
+
+		regs->flags = pebs->flags;
 #ifndef CONFIG_X86_32
-		regs.r8 = pebs->r8;
-		regs.r9 = pebs->r9;
-		regs.r10 = pebs->r10;
-		regs.r11 = pebs->r11;
-		regs.r12 = pebs->r12;
-		regs.r13 = pebs->r13;
-		regs.r14 = pebs->r14;
-		regs.r15 = pebs->r15;
+		regs->r8 = pebs->r8;
+		regs->r9 = pebs->r9;
+		regs->r10 = pebs->r10;
+		regs->r11 = pebs->r11;
+		regs->r12 = pebs->r12;
+		regs->r13 = pebs->r13;
+		regs->r14 = pebs->r14;
+		regs->r15 = pebs->r15;
 #endif
 	}
 
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs.ip = pebs->real_ip;
-		regs.flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
-		regs.flags |= PERF_EFLAGS_EXACT;
+		regs->ip = pebs->real_ip;
+		regs->flags |= PERF_EFLAGS_EXACT;
+	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+		regs->flags |= PERF_EFLAGS_EXACT;
 	else
-		regs.flags &= ~PERF_EFLAGS_EXACT;
+		regs->flags &= ~PERF_EFLAGS_EXACT;
 
 	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
-		data.addr = pebs->dla;
+		data->addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data.weight = intel_hsw_weight(pebs);
+			data->weight = intel_hsw_weight(pebs);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data.txn = intel_hsw_transaction(pebs);
+			data->txn = intel_hsw_transaction(pebs);
 	}
 
 	if (has_branch_stack(event))
-		data.br_stack = &cpuc->lbr_stack;
+		data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	void *at;
+	u64 pebs_status;
+
+	if (base == NULL)
+		return NULL;
+
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;
 
-	if (perf_event_overflow(event, &data, &regs))
+		if (test_bit(bit, (unsigned long *)&p->status)) {
+			/* PEBS v3 has accurate status bits */
+			if (x86_pmu.intel_cap.pebs_format >= 3)
+				return at;
+
+			if (p->status == (1 << bit))
+				return at;
+
+			/* clear non-PEBS bit and re-check */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status == (1 << bit))
+				return at;
+		}
+	}
+	return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+				   struct pt_regs *iregs,
+				   void *base, void *top,
+				   int bit, int count)
+{
+	struct perf_sample_data data;
+	struct pt_regs regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+	if (!intel_pmu_save_and_restart(event) &&
+	    !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+		return;
+
+	while (count > 1) {
+		setup_pebs_sample_data(event, iregs, at, &data, &regs);
+		perf_event_output(event, &data, &regs);
+		at += x86_pmu.pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		count--;
+	}
+
+	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+
+	/*
+	 * All but the last records are processed.
+	 * The last one is left to be able to call the overflow handler.
+	 */
+	if (perf_event_overflow(event, &data, &regs)) {
 		x86_pmu_stop(event, 0);
+		return;
+	}
+
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
@@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	if (!event->attr.precise_ip)
 		return;
 
-	n = top - at;
+	n = (top - at) / x86_pmu.pebs_record_size;
 	if (n <= 0)
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
-	at += n - 1;
-
-	__intel_pmu_pebs_event(event, iregs, at);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct perf_event *event = NULL;
-	void *at, *top;
-	u64 status = 0;
-	int bit;
+	struct perf_event *event;
+	void *base, *at, *top;
+	short counts[MAX_PEBS_EVENTS] = {};
+	short error[MAX_PEBS_EVENTS] = {};
+	int bit, i;
 
 	if (!x86_pmu.pebs_active)
 		return;
 
-	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	if (unlikely(at > top))
+	if (unlikely(base >= top))
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
-		  "Unexpected number of pebs records %ld\n",
-		  (long)(top - at) / x86_pmu.pebs_record_size);
-
-	for (; at < top; at += x86_pmu.pebs_record_size) {
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
 
-		for_each_set_bit(bit, (unsigned long *)&p->status,
-				 x86_pmu.max_pebs_events) {
-			event = cpuc->events[bit];
-			if (!test_bit(bit, cpuc->active_mask))
-				continue;
-
-			WARN_ON_ONCE(!event);
+		/* PEBS v3 has accurate status bits */
+		if (x86_pmu.intel_cap.pebs_format >= 3) {
+			for_each_set_bit(bit, (unsigned long *)&p->status,
+					 MAX_PEBS_EVENTS)
+				counts[bit]++;
 
-			if (!event->attr.precise_ip)
-				continue;
+			continue;
+		}
 
-			if (__test_and_set_bit(bit, (unsigned long *)&status))
+		bit = find_first_bit((unsigned long *)&p->status,
+					x86_pmu.max_pebs_events);
+		if (bit >= x86_pmu.max_pebs_events)
+			continue;
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+		/*
+		 * The PEBS hardware does not deal well with the situation
+		 * when events happen near to each other and multiple bits
+		 * are set. But it should happen rarely.
+		 *
+		 * If these events include one PEBS and multiple non-PEBS
+		 * events, it doesn't impact PEBS record. The record will
+		 * be handled normally. (slow path)
+		 *
+		 * If these events include two or more PEBS events, the
+		 * records for the events can be collapsed into a single
+		 * one, and it's not possible to reconstruct all events
+		 * that caused the PEBS record. It's called collision.
+		 * If collision happened, the record will be dropped.
+		 *
+		 */
+		if (p->status != (1 << bit)) {
+			u64 pebs_status;
+
+			/* slow path */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status != (1 << bit)) {
+				for_each_set_bit(i, (unsigned long *)&pebs_status,
+						 MAX_PEBS_EVENTS)
+					error[i]++;
 				continue;
-
-			break;
+			}
 		}
+		counts[bit]++;
+	}
 
-		if (!event || bit >= x86_pmu.max_pebs_events)
+	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
+		event = cpuc->events[bit];
+		WARN_ON_ONCE(!event);
+		WARN_ON_ONCE(!event->attr.precise_ip);
 
-		__intel_pmu_pebs_event(event, iregs, at);
+		/* log dropped samples number */
+		if (error[bit])
+			perf_log_lost_samples(event, error[bit]);
+
+		if (counts[bit]) {
+			__intel_pmu_pebs_event(event, iregs, base,
+					       top, bit, counts[bit]);
+		}
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 94e5b506caa6..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -96,6 +96,7 @@ enum {
 	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
 	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
 	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
+	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -113,6 +114,7 @@ enum {
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL |\
+	 X86_BR_IND_JMP  |\
 	 X86_BR_ZERO_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
-	if (!x86_pmu.lbr_nr)
-		return;
-
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
@@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 			X86_BR_CALL_STACK;
 	}
 
+	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+		mask |= X86_BR_IND_JMP;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			break;
 		case 4:
 		case 5:
-			ret = X86_BR_JMP;
+			ret = X86_BR_IND_JMP;
 			break;
 		}
 		break;
@@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
 };
 
 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 						| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
 	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
 						| LBR_RETURN | LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 /* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index ffe666c2c6b5..159887c3a89d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -151,7 +151,7 @@ static int __init pt_pmu_hw_init(void)
 
 		de_attr->attr.attr.name = pt_caps[i].name;
 
-		sysfs_attr_init(&de_attrs->attr.attr);
+		sysfs_attr_init(&de_attr->attr.attr);
 
 		de_attr->attr.attr.mode		= S_IRUGO;
 		de_attr->attr.show		= pt_cap_show;
@@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
-static bool pt_is_running(void)
-{
-	u64 ctl;
-
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
-	return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
 static void pt_config(struct perf_event *event)
 {
 	u64 reg;
@@ -609,16 +600,19 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
  * @handle:	Current output handle.
  *
  * Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
  */
 static int pt_buffer_reset_markers(struct pt_buffer *buf,
 				   struct perf_output_handle *handle)
 
 {
-	unsigned long idx, npages, end;
-
-	if (buf->snapshot)
-		return 0;
+	unsigned long head = local64_read(&buf->head);
+	unsigned long idx, npages, wakeup;
 
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 <
@@ -634,17 +628,26 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	buf->topa_index[buf->stop_pos]->stop = 0;
 	buf->topa_index[buf->intr_pos]->intr = 0;
 
-	if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
-		npages = (handle->size + 1) >> PAGE_SHIFT;
-		end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
-		/*if (end > handle->wakeup >> PAGE_SHIFT)
-		  end = handle->wakeup >> PAGE_SHIFT;*/
-		idx = end & (buf->nr_pages - 1);
-		buf->stop_pos = idx;
-		idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1;
-		idx &= buf->nr_pages - 1;
-		buf->intr_pos = idx;
-	}
+	/* how many pages till the STOP marker */
+	npages = handle->size >> PAGE_SHIFT;
+
+	/* if it's on a page boundary, fill up one more page */
+	if (!offset_in_page(head + handle->size + 1))
+		npages++;
+
+	idx = (head >> PAGE_SHIFT) + npages;
+	idx &= buf->nr_pages - 1;
+	buf->stop_pos = idx;
+
+	wakeup = handle->wakeup >> PAGE_SHIFT;
+
+	/* in the worst case, wake up the consumer one page before hard stop */
+	idx = (head >> PAGE_SHIFT) + npages - 1;
+	if (idx > wakeup)
+		idx = wakeup;
+
+	idx &= buf->nr_pages - 1;
+	buf->intr_pos = idx;
 
 	buf->topa_index[buf->stop_pos]->stop = 1;
 	buf->topa_index[buf->intr_pos]->intr = 1;
@@ -664,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 	struct topa *cur = buf->first, *prev = buf->last;
 	struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
 		*te_prev = TOPA_ENTRY(prev, prev->last - 1);
-	int pg = 0, idx = 0, ntopa = 0;
+	int pg = 0, idx = 0;
 
 	while (pg < buf->nr_pages) {
 		int tidx;
@@ -679,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 			/* advance to next topa table */
 			idx = 0;
 			cur = list_entry(cur->list.next, struct topa, list);
-			ntopa++;
-		} else
+		} else {
 			idx++;
+		}
 		te_cur = TOPA_ENTRY(cur, idx);
 	}
 
@@ -693,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
  * @head:	Write pointer (aux_head) from AUX buffer.
  *
  * Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
  */
 static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
 {
@@ -891,6 +901,7 @@ void intel_pt_interrupt(void)
 		}
 
 		pt_buffer_reset_offsets(buf, pt->handle.head);
+		/* snapshot counters don't use PMI, so it's safe */
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
 			perf_aux_output_end(&pt->handle, 0, true);
@@ -913,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
-	if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
 	}
@@ -944,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	event->hw.state = PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_UPDATE) {
-		struct pt *pt = this_cpu_ptr(&pt_ctx);
 		struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
 		if (!buf)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 999289b94025..5cbd4e64feb5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -204,9 +204,8 @@ again:
 
 static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 {
-	__hrtimer_start_range_ns(&pmu->hrtimer,
-			pmu->timer_interval, 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+       hrtimer_start(&pmu->hrtimer, pmu->timer_interval,
+		     HRTIMER_MODE_REL_PINNED);
 }
 
 static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
@@ -722,6 +721,7 @@ static int __init rapl_pmu_init(void)
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell-Celeron */
+	case 61: /* Broadwell */
 		rapl_cntr_mask = RAPL_IDX_HSW;
 		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
 		break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c635b8b49e93..21b5e38c921b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
-	__hrtimer_start_range_ns(&box->hrtimer,
-			ns_to_ktime(box->hrtimer_duration), 0,
-			HRTIMER_MODE_REL_PINNED, 0);
+	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -365,9 +364,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX);
 
 	for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		hwc = &box->event_list[i]->hw;
 		c = uncore_get_event_constraint(box, box->event_list[i]);
-		hwc->constraint = c;
+		box->event_constraint[i] = c;
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
 	}
@@ -375,7 +373,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	/* fastpath, try to reuse previous register */
 	for (i = 0; i < n; i++) {
 		hwc = &box->event_list[i]->hw;
-		c = hwc->constraint;
+		c = box->event_constraint[i];
 
 		/* never assigned */
 		if (hwc->idx == -1)
@@ -395,8 +393,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	}
 	/* slow path */
 	if (i != n)
-		ret = perf_assign_events(box->event_list, n,
-					 wmin, wmax, assign);
+		ret = perf_assign_events(box->event_constraint, n,
+					 wmin, wmax, n, assign);
 
 	if (!assign || ret) {
 		for (i = 0; i < n; i++)
@@ -840,6 +838,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
+	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -922,6 +921,9 @@ static int __init uncore_pci_init(void)
 	case 69: /* Haswell Celeron */
 		ret = hsw_uncore_pci_init();
 		break;
+	case 61: /* Broadwell */
+		ret = bdw_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
@@ -1003,8 +1005,10 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0)
+			if (box && box->phys_id >= 0) {
+				uncore_box_init(box);
 				continue;
+			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1020,8 +1024,10 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box)
+			if (box) {
 				box->phys_id = phys_id;
+				uncore_box_init(box);
+			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 6c8c1e7e69d8..0f77f0a196e4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -97,6 +97,7 @@ struct intel_uncore_box {
 	atomic_t refcnt;
 	struct perf_event *events[UNCORE_PMC_IDX_MAX];
 	struct perf_event *event_list[UNCORE_PMC_IDX_MAX];
+	struct event_constraint *event_constraint[UNCORE_PMC_IDX_MAX];
 	unsigned long active_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
 	u64 tags[UNCORE_PMC_IDX_MAX];
 	struct pci_dev *pci_dev;
@@ -257,14 +258,6 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -273,8 +266,6 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
-	uncore_box_init(box);
-
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -297,6 +288,14 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
@@ -326,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty;
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 3001015b755c..b005a78c7012 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -1,6 +1,14 @@
 /* Nehalem/SandBridge/Haswell uncore support */
 #include "perf_event_intel_uncore.h"
 
+/* Uncore IMC PCI IDs */
+#define PCI_DEVICE_ID_INTEL_SNB_IMC	0x0100
+#define PCI_DEVICE_ID_INTEL_IVB_IMC	0x0154
+#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
+#define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
+#define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
+
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
 #define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
@@ -472,6 +480,18 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 	{ /* end: all zeroes */ },
 };
 
@@ -490,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = {
 	.id_table	= hsw_uncore_pci_ids,
 };
 
+static struct pci_driver bdw_uncore_pci_driver = {
+	.name		= "bdw_uncore",
+	.id_table	= bdw_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -502,6 +527,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver),    /* 3rd Gen Core processor */
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
+	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
+	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	{  /* end marker */ }
 };
 
@@ -549,6 +576,11 @@ int hsw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int bdw_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 12d9548457e7..6d6e85dd5849 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -164,8 +164,8 @@
 				((1ULL << (n)) - 1)))
 
 /* Haswell-EP Ubox */
-#define HSWEP_U_MSR_PMON_CTR0			0x705
-#define HSWEP_U_MSR_PMON_CTL0			0x709
+#define HSWEP_U_MSR_PMON_CTR0			0x709
+#define HSWEP_U_MSR_PMON_CTL0			0x705
 #define HSWEP_U_MSR_PMON_FILTER			0x707
 
 #define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL		0x703
@@ -1914,7 +1914,7 @@ static struct intel_uncore_type hswep_uncore_cbox = {
 	.name			= "cbox",
 	.num_counters		= 4,
 	.num_boxes		= 18,
-	.perf_ctr_bits		= 44,
+	.perf_ctr_bits		= 48,
 	.event_ctl		= HSWEP_C0_MSR_PMON_CTL0,
 	.perf_ctr		= HSWEP_C0_MSR_PMON_CTR0,
 	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index e7d8c7608471..18ca99f2798b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 {
 #ifdef CONFIG_SMP
 	seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
-	seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+	seq_printf(m, "siblings\t: %d\n",
+		   cpumask_weight(topology_core_cpumask(cpu)));
 	seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 	seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c76d3e37c6e1..e068d6683dba 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -22,6 +22,7 @@
 #include <linux/elfcore.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 6367a780cc8c..5ee771859b6f 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -4,7 +4,6 @@
 #include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/io.h>
-#include <linux/irqdomain.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/of.h>
@@ -17,6 +16,7 @@
 #include <linux/of_pci.h>
 #include <linux/initrd.h>
 
+#include <asm/irqdomain.h>
 #include <asm/hpet.h>
 #include <asm/apic.h>
 #include <asm/pci_x86.h>
@@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] =
 	},
 };
 
-static int ioapic_xlate(struct irq_domain *domain,
-			struct device_node *controller,
-			const u32 *intspec, u32 intsize,
-			irq_hw_number_t *out_hwirq, u32 *out_type)
+static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
+			      unsigned int nr_irqs, void *arg)
 {
+	struct of_phandle_args *irq_data = (void *)arg;
 	struct of_ioapic_type *it;
-	u32 line, idx, gsi;
+	struct irq_alloc_info tmp;
 
-	if (WARN_ON(intsize < 2))
+	if (WARN_ON(irq_data->args_count < 2))
 		return -EINVAL;
-
-	line = intspec[0];
-
-	if (intspec[1] >= ARRAY_SIZE(of_ioapic_type))
+	if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type))
 		return -EINVAL;
 
-	it = &of_ioapic_type[intspec[1]];
+	it = &of_ioapic_type[irq_data->args[1]];
+	ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
+	tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+	tmp.ioapic_pin = irq_data->args[0];
 
-	idx = (u32)(long)domain->host_data;
-	gsi = mp_pin_to_gsi(idx, line);
-	if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0)))
-		return -EBUSY;
-
-	*out_hwirq = line;
-	*out_type = it->out_type;
-	return 0;
+	return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
 }
 
-const struct irq_domain_ops ioapic_irq_domain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-	.xlate = ioapic_xlate,
+static const struct irq_domain_ops ioapic_irq_domain_ops = {
+	.alloc		= dt_irqdomain_alloc,
+	.free		= mp_irqdomain_free,
+	.activate	= mp_irqdomain_activate,
+	.deactivate	= mp_irqdomain_deactivate,
 };
 
 static void __init dtb_add_ioapic(struct device_node *dn)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index e2ce85db2283..c8dda42cb6a3 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1123,7 +1123,8 @@ void __init memblock_find_dma_reserve(void)
 		nr_pages += end_pfn - start_pfn;
 	}
 
-	for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) {
+	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
+				NULL) {
 		start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
 		end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
 		if (start_pfn < end_pfn)
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index fe9f0b79a18b..5cb9a4d6f623 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -627,8 +627,12 @@ static struct chipset early_qrk[] __initdata = {
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
 	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
 	/*
-	 * HPET on current version of Baytrail platform has accuracy
-	 * problems, disable it for now:
+	 * HPET on the current version of the Baytrail platform has accuracy
+	 * problems: it will halt in deep idle state - so we disable it.
+	 *
+	 * More details can be found in section 18.10.1.3 of the datasheet:
+	 *
+	 *    http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
deleted file mode 100644
index 1c309763e321..000000000000
--- a/arch/x86/kernel/entry_32.S
+++ /dev/null
@@ -1,1401 +0,0 @@
-/*
- *
- *  Copyright (C) 1991, 1992  Linus Torvalds
- */
-
-/*
- * entry.S contains the system-call and fault low-level handling routines.
- * This also contains the timer-interrupt handler, as well as all interrupts
- * and faults that can result in a task-switch.
- *
- * NOTE: This code handles signal-recognition, which happens every time
- * after a timer-interrupt and after each system call.
- *
- * I changed all the .align's to 4 (16 byte alignment), as that's faster
- * on a 486.
- *
- * Stack layout in 'syscall_exit':
- * 	ptrace needs to have all regs on the stack.
- *	if the order here is changed, it needs to be
- *	updated in fork.c:copy_process, signal.c:do_signal,
- *	ptrace.c and ptrace.h
- *
- *	 0(%esp) - %ebx
- *	 4(%esp) - %ecx
- *	 8(%esp) - %edx
- *       C(%esp) - %esi
- *	10(%esp) - %edi
- *	14(%esp) - %ebp
- *	18(%esp) - %eax
- *	1C(%esp) - %ds
- *	20(%esp) - %es
- *	24(%esp) - %fs
- *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
- *	2C(%esp) - orig_eax
- *	30(%esp) - %eip
- *	34(%esp) - %cs
- *	38(%esp) - %eflags
- *	3C(%esp) - %oldesp
- *	40(%esp) - %oldss
- *
- * "current" is in register %ebx during any slow entries.
- */
-
-#include <linux/linkage.h>
-#include <linux/err.h>
-#include <asm/thread_info.h>
-#include <asm/irqflags.h>
-#include <asm/errno.h>
-#include <asm/segment.h>
-#include <asm/smp.h>
-#include <asm/page_types.h>
-#include <asm/percpu.h>
-#include <asm/dwarf2.h>
-#include <asm/processor-flags.h>
-#include <asm/ftrace.h>
-#include <asm/irq_vectors.h>
-#include <asm/cpufeature.h>
-#include <asm/alternative-asm.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE	   0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-#define sysenter_audit	syscall_trace_entry
-#define sysexit_audit	syscall_exit_work
-#endif
-
-	.section .entry.text, "ax"
-
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization.  The following will never clobber any registers:
- *   INTERRUPT_RETURN (aka. "iret")
- *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPT
-#define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-#define preempt_stop(clobbers)
-#define resume_kernel		restore_all
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
-	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)     # interrupts off?
-	jz 1f
-	TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc.  Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
-	pushl_cfi $0
-.endm
-.macro POP_GS pop=0
-	addl $(4 + \pop), %esp
-	CFI_ADJUST_CFA_OFFSET -(4 + \pop)
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else	/* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
-	pushl_cfi %gs
-	/*CFI_REL_OFFSET gs, 0*/
-.endm
-
-.macro POP_GS pop=0
-98:	popl_cfi %gs
-	/*CFI_RESTORE gs*/
-  .if \pop <> 0
-	add $\pop, %esp
-	CFI_ADJUST_CFA_OFFSET -\pop
-  .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99:	movl $0, (%esp)
-	jmp 98b
-.popsection
-	_ASM_EXTABLE(98b,99b)
-.endm
-
-.macro PTGS_TO_GS
-98:	mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99:	movl $0, PT_GS(%esp)
-	jmp 98b
-.popsection
-	_ASM_EXTABLE(98b,99b)
-.endm
-
-.macro GS_TO_REG reg
-	movl %gs, \reg
-	/*CFI_REGISTER gs, \reg*/
-.endm
-.macro REG_TO_PTGS reg
-	movl \reg, PT_GS(%esp)
-	/*CFI_REL_OFFSET gs, PT_GS*/
-.endm
-.macro SET_KERNEL_GS reg
-	movl $(__KERNEL_STACK_CANARY), \reg
-	movl \reg, %gs
-.endm
-
-#endif	/* CONFIG_X86_32_LAZY_GS */
-
-.macro SAVE_ALL
-	cld
-	PUSH_GS
-	pushl_cfi %fs
-	/*CFI_REL_OFFSET fs, 0;*/
-	pushl_cfi %es
-	/*CFI_REL_OFFSET es, 0;*/
-	pushl_cfi %ds
-	/*CFI_REL_OFFSET ds, 0;*/
-	pushl_cfi %eax
-	CFI_REL_OFFSET eax, 0
-	pushl_cfi %ebp
-	CFI_REL_OFFSET ebp, 0
-	pushl_cfi %edi
-	CFI_REL_OFFSET edi, 0
-	pushl_cfi %esi
-	CFI_REL_OFFSET esi, 0
-	pushl_cfi %edx
-	CFI_REL_OFFSET edx, 0
-	pushl_cfi %ecx
-	CFI_REL_OFFSET ecx, 0
-	pushl_cfi %ebx
-	CFI_REL_OFFSET ebx, 0
-	movl $(__USER_DS), %edx
-	movl %edx, %ds
-	movl %edx, %es
-	movl $(__KERNEL_PERCPU), %edx
-	movl %edx, %fs
-	SET_KERNEL_GS %edx
-.endm
-
-.macro RESTORE_INT_REGS
-	popl_cfi %ebx
-	CFI_RESTORE ebx
-	popl_cfi %ecx
-	CFI_RESTORE ecx
-	popl_cfi %edx
-	CFI_RESTORE edx
-	popl_cfi %esi
-	CFI_RESTORE esi
-	popl_cfi %edi
-	CFI_RESTORE edi
-	popl_cfi %ebp
-	CFI_RESTORE ebp
-	popl_cfi %eax
-	CFI_RESTORE eax
-.endm
-
-.macro RESTORE_REGS pop=0
-	RESTORE_INT_REGS
-1:	popl_cfi %ds
-	/*CFI_RESTORE ds;*/
-2:	popl_cfi %es
-	/*CFI_RESTORE es;*/
-3:	popl_cfi %fs
-	/*CFI_RESTORE fs;*/
-	POP_GS \pop
-.pushsection .fixup, "ax"
-4:	movl $0, (%esp)
-	jmp 1b
-5:	movl $0, (%esp)
-	jmp 2b
-6:	movl $0, (%esp)
-	jmp 3b
-.popsection
-	_ASM_EXTABLE(1b,4b)
-	_ASM_EXTABLE(2b,5b)
-	_ASM_EXTABLE(3b,6b)
-	POP_GS_EX
-.endm
-
-.macro RING0_INT_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 3*4
-	/*CFI_OFFSET cs, -2*4;*/
-	CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_EC_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 4*4
-	/*CFI_OFFSET cs, -2*4;*/
-	CFI_OFFSET eip, -3*4
-.endm
-
-.macro RING0_PTREGS_FRAME
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, PT_OLDESP-PT_EBX
-	/*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/
-	CFI_OFFSET eip, PT_EIP-PT_OLDESP
-	/*CFI_OFFSET es, PT_ES-PT_OLDESP;*/
-	/*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/
-	CFI_OFFSET eax, PT_EAX-PT_OLDESP
-	CFI_OFFSET ebp, PT_EBP-PT_OLDESP
-	CFI_OFFSET edi, PT_EDI-PT_OLDESP
-	CFI_OFFSET esi, PT_ESI-PT_OLDESP
-	CFI_OFFSET edx, PT_EDX-PT_OLDESP
-	CFI_OFFSET ecx, PT_ECX-PT_OLDESP
-	CFI_OFFSET ebx, PT_EBX-PT_OLDESP
-.endm
-
-ENTRY(ret_from_fork)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	call schedule_tail
-	GET_THREAD_INFO(%ebp)
-	popl_cfi %eax
-	pushl_cfi $0x0202		# Reset kernel eflags
-	popfl_cfi
-	jmp syscall_exit
-	CFI_ENDPROC
-END(ret_from_fork)
-
-ENTRY(ret_from_kernel_thread)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	call schedule_tail
-	GET_THREAD_INFO(%ebp)
-	popl_cfi %eax
-	pushl_cfi $0x0202		# Reset kernel eflags
-	popfl_cfi
-	movl PT_EBP(%esp),%eax
-	call *PT_EBX(%esp)
-	movl $0,PT_EAX(%esp)
-	jmp syscall_exit
-	CFI_ENDPROC
-ENDPROC(ret_from_kernel_thread)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
-	# userspace resumption stub bypassing syscall exit tracing
-	ALIGN
-	RING0_PTREGS_FRAME
-ret_from_exception:
-	preempt_stop(CLBR_ANY)
-ret_from_intr:
-	GET_THREAD_INFO(%ebp)
-#ifdef CONFIG_VM86
-	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS and CS
-	movb PT_CS(%esp), %al
-	andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
-	/*
-	 * We can be coming here from child spawned by kernel_thread().
-	 */
-	movl PT_CS(%esp), %eax
-	andl $SEGMENT_RPL_MASK, %eax
-#endif
-	cmpl $USER_RPL, %eax
-	jb resume_kernel		# not returning to v8086 or userspace
-
-ENTRY(resume_userspace)
-	LOCKDEP_SYS_EXIT
- 	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
-					# int/exception return?
-	jne work_pending
-	jmp restore_all
-END(ret_from_exception)
-
-#ifdef CONFIG_PREEMPT
-ENTRY(resume_kernel)
-	DISABLE_INTERRUPTS(CLBR_ANY)
-need_resched:
-	cmpl $0,PER_CPU_VAR(__preempt_count)
-	jnz restore_all
-	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz restore_all
-	call preempt_schedule_irq
-	jmp need_resched
-END(resume_kernel)
-#endif
-	CFI_ENDPROC
-
-/* SYSENTER_RETURN points to after the "sysenter" instruction in
-   the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */
-
-	# sysenter call handler stub
-ENTRY(ia32_sysenter_target)
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA esp, 0
-	CFI_REGISTER esp, ebp
-	movl TSS_sysenter_sp0(%esp),%esp
-sysenter_past_esp:
-	/*
-	 * Interrupts are disabled here, but we can't trace it until
-	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
-	 * we immediately enable interrupts at that point anyway.
-	 */
-	pushl_cfi $__USER_DS
-	/*CFI_REL_OFFSET ss, 0*/
-	pushl_cfi %ebp
-	CFI_REL_OFFSET esp, 0
-	pushfl_cfi
-	orl $X86_EFLAGS_IF, (%esp)
-	pushl_cfi $__USER_CS
-	/*CFI_REL_OFFSET cs, 0*/
-	/*
-	 * Push current_thread_info()->sysenter_return to the stack.
-	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
-	 * is relative to thread_info, which is at the bottom of the
-	 * kernel stack page.  4*4 means the 4 words pushed above;
-	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
-	 * and THREAD_SIZE takes us to the bottom.
-	 */
-	pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
-	CFI_REL_OFFSET eip, 0
-
-	pushl_cfi %eax
-	SAVE_ALL
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
-	cmpl $__PAGE_OFFSET-3,%ebp
-	jae syscall_fault
-	ASM_STAC
-1:	movl (%ebp),%ebp
-	ASM_CLAC
-	movl %ebp,PT_EBP(%esp)
-	_ASM_EXTABLE(1b,syscall_fault)
-
-	GET_THREAD_INFO(%ebp)
-
-	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
-	jnz sysenter_audit
-sysenter_do_call:
-	cmpl $(NR_syscalls), %eax
-	jae sysenter_badsys
-	call *sys_call_table(,%eax,4)
-sysenter_after_call:
-	movl %eax,PT_EAX(%esp)
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $_TIF_ALLWORK_MASK, %ecx
-	jnz sysexit_audit
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
-	movl PT_EIP(%esp), %edx
-	movl PT_OLDESP(%esp), %ecx
-	xorl %ebp,%ebp
-	TRACE_IRQS_ON
-1:	mov  PT_FS(%esp), %fs
-	PTGS_TO_GS
-	ENABLE_INTERRUPTS_SYSEXIT
-
-#ifdef CONFIG_AUDITSYSCALL
-sysenter_audit:
-	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
-	jnz syscall_trace_entry
-	/* movl PT_EAX(%esp), %eax	already set, syscall number: 1st arg to audit */
-	movl PT_EBX(%esp), %edx		/* ebx/a0: 2nd arg to audit */
-	/* movl PT_ECX(%esp), %ecx	already set, a1: 3nd arg to audit */
-	pushl_cfi PT_ESI(%esp)		/* a3: 5th arg */
-	pushl_cfi PT_EDX+4(%esp)	/* a2: 4th arg */
-	call __audit_syscall_entry
-	popl_cfi %ecx /* get that remapped edx off the stack */
-	popl_cfi %ecx /* get that remapped esi off the stack */
-	movl PT_EAX(%esp),%eax		/* reload syscall number */
-	jmp sysenter_do_call
-
-sysexit_audit:
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz syscall_exit_work
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)
-	movl %eax,%edx		/* second arg, syscall return value */
-	cmpl $-MAX_ERRNO,%eax	/* is it an error ? */
-	setbe %al		/* 1 if so, 0 if not */
-	movzbl %al,%eax		/* zero-extend that */
-	call __audit_syscall_exit
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
-	jnz syscall_exit_work
-	movl PT_EAX(%esp),%eax	/* reload syscall return value */
-	jmp sysenter_exit
-#endif
-
-	CFI_ENDPROC
-.pushsection .fixup,"ax"
-2:	movl $0,PT_FS(%esp)
-	jmp 1b
-.popsection
-	_ASM_EXTABLE(1b,2b)
-	PTGS_TO_GS_EX
-ENDPROC(ia32_sysenter_target)
-
-	# system call handler stub
-ENTRY(system_call)
-	RING0_INT_FRAME			# can't unwind into user space anyway
-	ASM_CLAC
-	pushl_cfi %eax			# save orig_eax
-	SAVE_ALL
-	GET_THREAD_INFO(%ebp)
-					# system call tracing in operation / emulation
-	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
-	jnz syscall_trace_entry
-	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
-syscall_call:
-	call *sys_call_table(,%eax,4)
-syscall_after_call:
-	movl %eax,PT_EAX(%esp)		# store the return value
-syscall_exit:
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	testl $_TIF_ALLWORK_MASK, %ecx	# current->work
-	jnz syscall_exit_work
-
-restore_all:
-	TRACE_IRQS_IRET
-restore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
-	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
-	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
-	# are returning to the kernel.
-	# See comments in process.c:copy_thread() for details.
-	movb PT_OLDSS(%esp), %ah
-	movb PT_CS(%esp), %al
-	andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
-	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
-	CFI_REMEMBER_STATE
-	je ldt_ss			# returning to user-space with LDT SS
-#endif
-restore_nocheck:
-	RESTORE_REGS 4			# skip orig_eax/error_code
-irq_return:
-	INTERRUPT_RETURN
-.section .fixup,"ax"
-ENTRY(iret_exc)
-	pushl $0			# no error code
-	pushl $do_iret_error
-	jmp error_code
-.previous
-	_ASM_EXTABLE(irq_return,iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
-	CFI_RESTORE_STATE
-ldt_ss:
-#ifdef CONFIG_PARAVIRT
-	/*
-	 * The kernel can't run on a non-flat stack if paravirt mode
-	 * is active.  Rather than try to fixup the high bits of
-	 * ESP, bypass this code entirely.  This may break DOSemu
-	 * and/or Wine support in a paravirt VM, although the option
-	 * is still available to implement the setting of the high
-	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
-	 */
-	cmpl $0, pv_info+PARAVIRT_enabled
-	jne restore_nocheck
-#endif
-
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
-	mov %esp, %edx			/* load kernel esp */
-	mov PT_OLDESP(%esp), %eax	/* load userspace esp */
-	mov %dx, %ax			/* eax: new kernel esp */
-	sub %eax, %edx			/* offset (low word is 0) */
-	shr $16, %edx
-	mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
-	mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
-	pushl_cfi $__ESPFIX_SS
-	pushl_cfi %eax			/* new kernel esp */
-	/* Disable interrupts, but do not irqtrace this section: we
-	 * will soon execute iret and the tracer was already set to
-	 * the irqstate after the iret */
-	DISABLE_INTERRUPTS(CLBR_EAX)
-	lss (%esp), %esp		/* switch to espfix segment */
-	CFI_ADJUST_CFA_OFFSET -8
-	jmp restore_nocheck
-#endif
-	CFI_ENDPROC
-ENDPROC(system_call)
-
-	# perform work that needs to be done immediately before resumption
-	ALIGN
-	RING0_PTREGS_FRAME		# can't unwind into user space anyway
-work_pending:
-	testb $_TIF_NEED_RESCHED, %cl
-	jz work_notifysig
-work_resched:
-	call schedule
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
-					# setting need_resched or sigpending
-					# between sampling and the iret
-	TRACE_IRQS_OFF
-	movl TI_flags(%ebp), %ecx
-	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
-					# than syscall tracing?
-	jz restore_all
-	testb $_TIF_NEED_RESCHED, %cl
-	jnz work_resched
-
-work_notifysig:				# deal with pending signals and
-					# notify-resume requests
-#ifdef CONFIG_VM86
-	testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
-	movl %esp, %eax
-	jnz work_notifysig_v86		# returning to kernel-space or
-					# vm86-space
-1:
-#else
-	movl %esp, %eax
-#endif
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	movb PT_CS(%esp), %bl
-	andb $SEGMENT_RPL_MASK, %bl
-	cmpb $USER_RPL, %bl
-	jb resume_kernel
-	xorl %edx, %edx
-	call do_notify_resume
-	jmp resume_userspace
-
-#ifdef CONFIG_VM86
-	ALIGN
-work_notifysig_v86:
-	pushl_cfi %ecx			# save ti_flags for do_notify_resume
-	call save_v86_state		# %eax contains pt_regs pointer
-	popl_cfi %ecx
-	movl %eax, %esp
-	jmp 1b
-#endif
-END(work_pending)
-
-	# perform syscall exit tracing
-	ALIGN
-syscall_trace_entry:
-	movl $-ENOSYS,PT_EAX(%esp)
-	movl %esp, %eax
-	call syscall_trace_enter
-	/* What it returned is what we'll actually use.  */
-	cmpl $(NR_syscalls), %eax
-	jnae syscall_call
-	jmp syscall_exit
-END(syscall_trace_entry)
-
-	# perform syscall exit tracing
-	ALIGN
-syscall_exit_work:
-	testl $_TIF_WORK_SYSCALL_EXIT, %ecx
-	jz work_pending
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)	# could let syscall_trace_leave() call
-					# schedule() instead
-	movl %esp, %eax
-	call syscall_trace_leave
-	jmp resume_userspace
-END(syscall_exit_work)
-	CFI_ENDPROC
-
-	RING0_INT_FRAME			# can't unwind into user space anyway
-syscall_fault:
-	ASM_CLAC
-	GET_THREAD_INFO(%ebp)
-	movl $-EFAULT,PT_EAX(%esp)
-	jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
-	movl $-ENOSYS,%eax
-	jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
-	movl $-ENOSYS,%eax
-	jmp sysenter_after_call
-END(sysenter_badsys)
-	CFI_ENDPROC
-
-.macro FIXUP_ESPFIX_STACK
-/*
- * Switch back for ESPFIX stack to the normal zerobased stack
- *
- * We can't call C functions using the ESPFIX stack. This code reads
- * the high word of the segment base from the GDT and swiches to the
- * normal stack and adjusts ESP with the matching offset.
- */
-#ifdef CONFIG_X86_ESPFIX32
-	/* fixup the stack */
-	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
-	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
-	shl $16, %eax
-	addl %esp, %eax			/* the adjusted stack pointer */
-	pushl_cfi $__KERNEL_DS
-	pushl_cfi %eax
-	lss (%esp), %esp		/* switch to the normal stack segment */
-	CFI_ADJUST_CFA_OFFSET -8
-#endif
-.endm
-.macro UNWIND_ESPFIX_STACK
-#ifdef CONFIG_X86_ESPFIX32
-	movl %ss, %eax
-	/* see if on espfix stack */
-	cmpw $__ESPFIX_SS, %ax
-	jne 27f
-	movl $__KERNEL_DS, %eax
-	movl %eax, %ds
-	movl %eax, %es
-	/* switch to normal stack */
-	FIXUP_ESPFIX_STACK
-27:
-#endif
-.endm
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
-	.align 8
-ENTRY(irq_entries_start)
-	RING0_INT_FRAME
-    vector=FIRST_EXTERNAL_VECTOR
-    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	pushl_cfi $(~vector+0x80)	/* Note: always in signed byte range */
-    vector=vector+1
-	jmp	common_interrupt
-	CFI_ADJUST_CFA_OFFSET -4
-	.align	8
-    .endr
-END(irq_entries_start)
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
-	.p2align CONFIG_X86_L1_CACHE_SHIFT
-common_interrupt:
-	ASM_CLAC
-	addl $-0x80,(%esp)	/* Adjust vector into the [-256,-1] range */
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	movl %esp,%eax
-	call do_IRQ
-	jmp ret_from_intr
-ENDPROC(common_interrupt)
-	CFI_ENDPROC
-
-#define BUILD_INTERRUPT3(name, nr, fn)	\
-ENTRY(name)				\
-	RING0_INT_FRAME;		\
-	ASM_CLAC;			\
-	pushl_cfi $~(nr);		\
-	SAVE_ALL;			\
-	TRACE_IRQS_OFF			\
-	movl %esp,%eax;			\
-	call fn;			\
-	jmp ret_from_intr;		\
-	CFI_ENDPROC;			\
-ENDPROC(name)
-
-
-#ifdef CONFIG_TRACING
-#define TRACE_BUILD_INTERRUPT(name, nr)		\
-	BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
-#else
-#define TRACE_BUILD_INTERRUPT(name, nr)
-#endif
-
-#define BUILD_INTERRUPT(name, nr) \
-	BUILD_INTERRUPT3(name, nr, smp_##name); \
-	TRACE_BUILD_INTERRUPT(name, nr)
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-ENTRY(coprocessor_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_coprocessor_error
-	jmp error_code
-	CFI_ENDPROC
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-#ifdef CONFIG_X86_INVD_BUG
-	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-	ALTERNATIVE "pushl_cfi $do_general_protection",	\
-		    "pushl $do_simd_coprocessor_error", \
-		    X86_FEATURE_XMM
-#else
-	pushl_cfi $do_simd_coprocessor_error
-#endif
-	jmp error_code
-	CFI_ENDPROC
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $-1			# mark this as an int
-	pushl_cfi $do_device_not_available
-	jmp error_code
-	CFI_ENDPROC
-END(device_not_available)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
-	iret
-	_ASM_EXTABLE(native_iret, iret_exc)
-END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
-	sti
-	sysexit
-END(native_irq_enable_sysexit)
-#endif
-
-ENTRY(overflow)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_overflow
-	jmp error_code
-	CFI_ENDPROC
-END(overflow)
-
-ENTRY(bounds)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_bounds
-	jmp error_code
-	CFI_ENDPROC
-END(bounds)
-
-ENTRY(invalid_op)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_invalid_op
-	jmp error_code
-	CFI_ENDPROC
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_coprocessor_segment_overrun
-	jmp error_code
-	CFI_ENDPROC
-END(coprocessor_segment_overrun)
-
-ENTRY(invalid_TSS)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_invalid_TSS
-	jmp error_code
-	CFI_ENDPROC
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_segment_not_present
-	jmp error_code
-	CFI_ENDPROC
-END(segment_not_present)
-
-ENTRY(stack_segment)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_stack_segment
-	jmp error_code
-	CFI_ENDPROC
-END(stack_segment)
-
-ENTRY(alignment_check)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_alignment_check
-	jmp error_code
-	CFI_ENDPROC
-END(alignment_check)
-
-ENTRY(divide_error)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0			# no error code
-	pushl_cfi $do_divide_error
-	jmp error_code
-	CFI_ENDPROC
-END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-ENTRY(machine_check)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi machine_check_vector
-	jmp error_code
-	CFI_ENDPROC
-END(machine_check)
-#endif
-
-ENTRY(spurious_interrupt_bug)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $0
-	pushl_cfi $do_spurious_interrupt_bug
-	jmp error_code
-	CFI_ENDPROC
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_XEN
-/* Xen doesn't set %esp to be precisely what the normal sysenter
-   entrypoint expects, so fix it up before using the normal path. */
-ENTRY(xen_sysenter_target)
-	RING0_INT_FRAME
-	addl $5*4, %esp		/* remove xen-provided frame */
-	CFI_ADJUST_CFA_OFFSET -5*4
-	jmp sysenter_past_esp
-	CFI_ENDPROC
-
-ENTRY(xen_hypervisor_callback)
-	CFI_STARTPROC
-	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	TRACE_IRQS_OFF
-
-	/* Check to see if we got the event in the critical
-	   region in xen_iret_direct, after we've reenabled
-	   events and checked for pending events.  This simulates
-	   iret instruction's behaviour where it delivers a
-	   pending interrupt when enabling interrupts. */
-	movl PT_EIP(%esp),%eax
-	cmpl $xen_iret_start_crit,%eax
-	jb   1f
-	cmpl $xen_iret_end_crit,%eax
-	jae  1f
-
-	jmp  xen_iret_crit_fixup
-
-ENTRY(xen_do_upcall)
-1:	mov %esp, %eax
-	call xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
-	call xen_maybe_preempt_hcall
-#endif
-	jmp  ret_from_intr
-	CFI_ENDPROC
-ENDPROC(xen_hypervisor_callback)
-
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-#  1. Fault while reloading DS, ES, FS or GS
-#  2. Fault while executing IRET
-# Category 1 we fix up by reattempting the load, and zeroing the segment
-# register if the load fails.
-# Category 2 we fix up by jumping to do_iret_error. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by maintaining a status value in EAX.
-ENTRY(xen_failsafe_callback)
-	CFI_STARTPROC
-	pushl_cfi %eax
-	movl $1,%eax
-1:	mov 4(%esp),%ds
-2:	mov 8(%esp),%es
-3:	mov 12(%esp),%fs
-4:	mov 16(%esp),%gs
-	/* EAX == 0 => Category 1 (Bad segment)
-	   EAX != 0 => Category 2 (Bad IRET) */
-	testl %eax,%eax
-	popl_cfi %eax
-	lea 16(%esp),%esp
-	CFI_ADJUST_CFA_OFFSET -16
-	jz 5f
-	jmp iret_exc
-5:	pushl_cfi $-1 /* orig_ax = -1 => not a system call */
-	SAVE_ALL
-	jmp ret_from_exception
-	CFI_ENDPROC
-
-.section .fixup,"ax"
-6:	xorl %eax,%eax
-	movl %eax,4(%esp)
-	jmp 1b
-7:	xorl %eax,%eax
-	movl %eax,8(%esp)
-	jmp 2b
-8:	xorl %eax,%eax
-	movl %eax,12(%esp)
-	jmp 3b
-9:	xorl %eax,%eax
-	movl %eax,16(%esp)
-	jmp 4b
-.previous
-	_ASM_EXTABLE(1b,6b)
-	_ASM_EXTABLE(2b,7b)
-	_ASM_EXTABLE(3b,8b)
-	_ASM_EXTABLE(4b,9b)
-ENDPROC(xen_failsafe_callback)
-
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-		xen_evtchn_do_upcall)
-
-#endif	/* CONFIG_XEN */
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-	hyperv_vector_handler)
-
-#endif /* CONFIG_HYPERV */
-
-#ifdef CONFIG_FUNCTION_TRACER
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(mcount)
-	ret
-END(mcount)
-
-ENTRY(ftrace_caller)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	pushl $0	/* Pass NULL as regs pointer */
-	movl 4*4(%esp), %eax
-	movl 0x4(%ebp), %edx
-	movl function_trace_op, %ecx
-	subl $MCOUNT_INSN_SIZE, %eax
-
-.globl ftrace_call
-ftrace_call:
-	call ftrace_stub
-
-	addl $4,%esp	/* skip NULL pointer */
-	popl %edx
-	popl %ecx
-	popl %eax
-ftrace_ret:
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
-	jmp ftrace_stub
-#endif
-
-.globl ftrace_stub
-ftrace_stub:
-	ret
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
-	pushf	/* push flags before compare (in cs location) */
-
-	/*
-	 * i386 does not save SS and ESP when coming from kernel.
-	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
-	 * Unfortunately, that means eflags must be at the same location
-	 * as the current return ip is. We move the return ip into the
-	 * ip location, and move flags into the return ip location.
-	 */
-	pushl 4(%esp)	/* save return ip into ip slot */
-
-	pushl $0	/* Load 0 into orig_ax */
-	pushl %gs
-	pushl %fs
-	pushl %es
-	pushl %ds
-	pushl %eax
-	pushl %ebp
-	pushl %edi
-	pushl %esi
-	pushl %edx
-	pushl %ecx
-	pushl %ebx
-
-	movl 13*4(%esp), %eax	/* Get the saved flags */
-	movl %eax, 14*4(%esp)	/* Move saved flags into regs->flags location */
-				/* clobbering return ip */
-	movl $__KERNEL_CS,13*4(%esp)
-
-	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
-	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
-	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
-	pushl %esp		/* Save pt_regs as 4th parameter */
-
-GLOBAL(ftrace_regs_call)
-	call ftrace_stub
-
-	addl $4, %esp		/* Skip pt_regs */
-	movl 14*4(%esp), %eax	/* Move flags back into cs */
-	movl %eax, 13*4(%esp)	/* Needed to keep addl from modifying flags */
-	movl 12*4(%esp), %eax	/* Get return ip from regs->ip */
-	movl %eax, 14*4(%esp)	/* Put return ip back for ret */
-
-	popl %ebx
-	popl %ecx
-	popl %edx
-	popl %esi
-	popl %edi
-	popl %ebp
-	popl %eax
-	popl %ds
-	popl %es
-	popl %fs
-	popl %gs
-	addl $8, %esp		/* Skip orig_ax and ip */
-	popf			/* Pop flags at end (no addl to corrupt flags) */
-	jmp ftrace_ret
-
-	popf
-	jmp  ftrace_stub
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(mcount)
-	cmpl $__PAGE_OFFSET, %esp
-	jb ftrace_stub		/* Paging not enabled yet? */
-
-	cmpl $ftrace_stub, ftrace_trace_function
-	jnz trace
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpl $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-.globl ftrace_stub
-ftrace_stub:
-	ret
-
-	/* taken from glibc */
-trace:
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	movl 0x4(%ebp), %edx
-	subl $MCOUNT_INSN_SIZE, %eax
-
-	call *ftrace_trace_function
-
-	popl %edx
-	popl %ecx
-	popl %eax
-	jmp ftrace_stub
-END(mcount)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
-	pushl %eax
-	pushl %ecx
-	pushl %edx
-	movl 0xc(%esp), %eax
-	lea 0x4(%ebp), %edx
-	movl (%ebp), %ecx
-	subl $MCOUNT_INSN_SIZE, %eax
-	call prepare_ftrace_return
-	popl %edx
-	popl %ecx
-	popl %eax
-	ret
-END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
-	pushl %eax
-	pushl %edx
-	movl %ebp, %eax
-	call ftrace_return_to_handler
-	movl %eax, %ecx
-	popl %edx
-	popl %eax
-	jmp *%ecx
-#endif
-
-#ifdef CONFIG_TRACING
-ENTRY(trace_page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $trace_do_page_fault
-	jmp error_code
-	CFI_ENDPROC
-END(trace_page_fault)
-#endif
-
-ENTRY(page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_page_fault
-	ALIGN
-error_code:
-	/* the function address is in %gs's slot on the stack */
-	pushl_cfi %fs
-	/*CFI_REL_OFFSET fs, 0*/
-	pushl_cfi %es
-	/*CFI_REL_OFFSET es, 0*/
-	pushl_cfi %ds
-	/*CFI_REL_OFFSET ds, 0*/
-	pushl_cfi_reg eax
-	pushl_cfi_reg ebp
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg edx
-	pushl_cfi_reg ecx
-	pushl_cfi_reg ebx
-	cld
-	movl $(__KERNEL_PERCPU), %ecx
-	movl %ecx, %fs
-	UNWIND_ESPFIX_STACK
-	GS_TO_REG %ecx
-	movl PT_GS(%esp), %edi		# get the function address
-	movl PT_ORIG_EAX(%esp), %edx	# get the error code
-	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
-	REG_TO_PTGS %ecx
-	SET_KERNEL_GS %ecx
-	movl $(__USER_DS), %ecx
-	movl %ecx, %ds
-	movl %ecx, %es
-	TRACE_IRQS_OFF
-	movl %esp,%eax			# pt_regs pointer
-	call *%edi
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(page_fault)
-
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-.macro FIX_STACK offset ok label
-	cmpw $__KERNEL_CS, 4(%esp)
-	jne \ok
-\label:
-	movl TSS_sysenter_sp0 + \offset(%esp), %esp
-	CFI_DEF_CFA esp, 0
-	CFI_UNDEFINED eip
-	pushfl_cfi
-	pushl_cfi $__KERNEL_CS
-	pushl_cfi $sysenter_past_esp
-	CFI_REL_OFFSET eip, 0
-.endm
-
-ENTRY(debug)
-	RING0_INT_FRAME
-	ASM_CLAC
-	cmpl $ia32_sysenter_target,(%esp)
-	jne debug_stack_correct
-	FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
-debug_stack_correct:
-	pushl_cfi $-1			# mark this as an int
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx			# error code 0
-	movl %esp,%eax			# pt_regs pointer
-	call do_debug
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got  an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-ENTRY(nmi)
-	RING0_INT_FRAME
-	ASM_CLAC
-#ifdef CONFIG_X86_ESPFIX32
-	pushl_cfi %eax
-	movl %ss, %eax
-	cmpw $__ESPFIX_SS, %ax
-	popl_cfi %eax
-	je nmi_espfix_stack
-#endif
-	cmpl $ia32_sysenter_target,(%esp)
-	je nmi_stack_fixup
-	pushl_cfi %eax
-	movl %esp,%eax
-	/* Do not access memory above the end of our stack page,
-	 * it might not exist.
-	 */
-	andl $(THREAD_SIZE-1),%eax
-	cmpl $(THREAD_SIZE-20),%eax
-	popl_cfi %eax
-	jae nmi_stack_correct
-	cmpl $ia32_sysenter_target,12(%esp)
-	je nmi_debug_stack_check
-nmi_stack_correct:
-	/* We have a RING0_INT_FRAME here */
-	pushl_cfi %eax
-	SAVE_ALL
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_nmi
-	jmp restore_all_notrace
-	CFI_ENDPROC
-
-nmi_stack_fixup:
-	RING0_INT_FRAME
-	FIX_STACK 12, nmi_stack_correct, 1
-	jmp nmi_stack_correct
-
-nmi_debug_stack_check:
-	/* We have a RING0_INT_FRAME here */
-	cmpw $__KERNEL_CS,16(%esp)
-	jne nmi_stack_correct
-	cmpl $debug,(%esp)
-	jb nmi_stack_correct
-	cmpl $debug_esp_fix_insn,(%esp)
-	ja nmi_stack_correct
-	FIX_STACK 24, nmi_stack_correct, 1
-	jmp nmi_stack_correct
-
-#ifdef CONFIG_X86_ESPFIX32
-nmi_espfix_stack:
-	/* We have a RING0_INT_FRAME here.
-	 *
-	 * create the pointer to lss back
-	 */
-	pushl_cfi %ss
-	pushl_cfi %esp
-	addl $4, (%esp)
-	/* copy the iret frame of 12 bytes */
-	.rept 3
-	pushl_cfi 16(%esp)
-	.endr
-	pushl_cfi %eax
-	SAVE_ALL
-	FIXUP_ESPFIX_STACK		# %eax == %esp
-	xorl %edx,%edx			# zero error code
-	call do_nmi
-	RESTORE_REGS
-	lss 12+4(%esp), %esp		# back to espfix stack
-	CFI_ADJUST_CFA_OFFSET -24
-	jmp irq_return
-#endif
-	CFI_ENDPROC
-END(nmi)
-
-ENTRY(int3)
-	RING0_INT_FRAME
-	ASM_CLAC
-	pushl_cfi $-1			# mark this as an int
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_int3
-	jmp ret_from_exception
-	CFI_ENDPROC
-END(int3)
-
-ENTRY(general_protection)
-	RING0_EC_FRAME
-	pushl_cfi $do_general_protection
-	jmp error_code
-	CFI_ENDPROC
-END(general_protection)
-
-#ifdef CONFIG_KVM_GUEST
-ENTRY(async_page_fault)
-	RING0_EC_FRAME
-	ASM_CLAC
-	pushl_cfi $do_async_page_fault
-	jmp error_code
-	CFI_ENDPROC
-END(async_page_fault)
-#endif
-
diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile
new file mode 100644
index 000000000000..68279efb811a
--- /dev/null
+++ b/arch/x86/kernel/fpu/Makefile
@@ -0,0 +1,5 @@
+#
+# Build rules for the FPU support code:
+#
+
+obj-y				+= init.o bugs.o core.o regset.o signal.o xstate.o
diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c
new file mode 100644
index 000000000000..dd9ca9b60ff3
--- /dev/null
+++ b/arch/x86/kernel/fpu/bugs.c
@@ -0,0 +1,71 @@
+/*
+ * x86 FPU bug checks:
+ */
+#include <asm/fpu/internal.h>
+
+/*
+ * Boot time CPU/FPU FDIV bug detection code:
+ */
+
+static double __initdata x = 4195835.0;
+static double __initdata y = 3145727.0;
+
+/*
+ * This used to check for exceptions..
+ * However, it turns out that to support that,
+ * the XMM trap handlers basically had to
+ * be buggy. So let's have a correct XMM trap
+ * handler, and forget about printing out
+ * some status at boot.
+ *
+ * We should really only care about bugs here
+ * anyway. Not features.
+ */
+static void __init check_fpu(void)
+{
+	u32 cr0_saved;
+	s32 fdiv_bug;
+
+	/* We might have CR0::TS set already, clear it: */
+	cr0_saved = read_cr0();
+	write_cr0(cr0_saved & ~X86_CR0_TS);
+
+	kernel_fpu_begin();
+
+	/*
+	 * trap_init() enabled FXSR and company _before_ testing for FP
+	 * problems here.
+	 *
+	 * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug
+	 */
+	__asm__("fninit\n\t"
+		"fldl %1\n\t"
+		"fdivl %2\n\t"
+		"fmull %2\n\t"
+		"fldl %1\n\t"
+		"fsubp %%st,%%st(1)\n\t"
+		"fistpl %0\n\t"
+		"fwait\n\t"
+		"fninit"
+		: "=m" (*&fdiv_bug)
+		: "m" (*&x), "m" (*&y));
+
+	kernel_fpu_end();
+
+	write_cr0(cr0_saved);
+
+	if (fdiv_bug) {
+		set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV);
+		pr_warn("Hmm, FPU with FDIV bug\n");
+	}
+}
+
+void __init fpu__init_check_bugs(void)
+{
+	/*
+	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
+	 * alternative instructions.
+	 */
+	if (cpu_has_fpu)
+		check_fpu();
+}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
new file mode 100644
index 000000000000..79de954626fd
--- /dev/null
+++ b/arch/x86/kernel/fpu/core.c
@@ -0,0 +1,523 @@
+/*
+ *  Copyright (C) 1994 Linus Torvalds
+ *
+ *  Pentium III FXSR, SSE support
+ *  General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/regset.h>
+#include <asm/fpu/signal.h>
+#include <asm/traps.h>
+
+#include <linux/hardirq.h>
+
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union fpregs_state init_fpstate __read_mostly;
+
+/*
+ * Track whether the kernel is using the FPU state
+ * currently.
+ *
+ * This flag is used:
+ *
+ *   - by IRQ context code to potentially use the FPU
+ *     if it's unused.
+ *
+ *   - to debug kernel_fpu_begin()/end() correctness
+ */
+static DEFINE_PER_CPU(bool, in_kernel_fpu);
+
+/*
+ * Track which context is using the FPU on the CPU:
+ */
+DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+
+static void kernel_fpu_disable(void)
+{
+	WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, true);
+}
+
+static void kernel_fpu_enable(void)
+{
+	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+	this_cpu_write(in_kernel_fpu, false);
+}
+
+static bool kernel_fpu_disabled(void)
+{
+	return this_cpu_read(in_kernel_fpu);
+}
+
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: the thread must not have fpu (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ *
+ * Except for the eagerfpu case when we return true; in the likely case
+ * the thread has FPU but we are not going to set/clear TS.
+ */
+static bool interrupted_kernel_fpu_idle(void)
+{
+	if (kernel_fpu_disabled())
+		return false;
+
+	if (use_eager_fpu())
+		return true;
+
+	return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static bool interrupted_user_mode(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+	return regs && user_mode(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+bool irq_fpu_usable(void)
+{
+	return !in_interrupt() ||
+		interrupted_user_mode() ||
+		interrupted_kernel_fpu_idle();
+}
+EXPORT_SYMBOL(irq_fpu_usable);
+
+void __kernel_fpu_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	WARN_ON_FPU(!irq_fpu_usable());
+
+	kernel_fpu_disable();
+
+	if (fpu->fpregs_active) {
+		copy_fpregs_to_fpstate(fpu);
+	} else {
+		this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+		__fpregs_activate_hw();
+	}
+}
+EXPORT_SYMBOL(__kernel_fpu_begin);
+
+void __kernel_fpu_end(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (fpu->fpregs_active)
+		copy_kernel_to_fpregs(&fpu->state);
+	else
+		__fpregs_deactivate_hw();
+
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL(__kernel_fpu_end);
+
+void kernel_fpu_begin(void)
+{
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_begin);
+
+void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_end);
+
+/*
+ * CR0::TS save/restore functions:
+ */
+int irq_ts_save(void)
+{
+	/*
+	 * If in process context and not atomic, we can take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context requires disabling preemption
+	 * or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_atomic())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_ts_save);
+
+void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+EXPORT_SYMBOL_GPL(irq_ts_restore);
+
+/*
+ * Save the FPU state (mark it for reload if necessary):
+ *
+ * This only ever gets called for the current task.
+ */
+void fpu__save(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	preempt_disable();
+	if (fpu->fpregs_active) {
+		if (!copy_fpregs_to_fpstate(fpu))
+			fpregs_deactivate(fpu);
+	}
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__save);
+
+/*
+ * Legacy x87 fpstate state init:
+ */
+static inline void fpstate_init_fstate(struct fregs_state *fp)
+{
+	fp->cwd = 0xffff037fu;
+	fp->swd = 0xffff0000u;
+	fp->twd = 0xffffffffu;
+	fp->fos = 0xffff0000u;
+}
+
+void fpstate_init(union fpregs_state *state)
+{
+	if (!cpu_has_fpu) {
+		fpstate_init_soft(&state->soft);
+		return;
+	}
+
+	memset(state, 0, xstate_size);
+
+	if (cpu_has_fxsr)
+		fpstate_init_fxstate(&state->fxsave);
+	else
+		fpstate_init_fstate(&state->fsave);
+}
+EXPORT_SYMBOL_GPL(fpstate_init);
+
+/*
+ * Copy the current task's FPU state to a new task's FPU context.
+ *
+ * In both the 'eager' and the 'lazy' case we save hardware registers
+ * directly to the destination buffer.
+ */
+static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	WARN_ON_FPU(src_fpu != &current->thread.fpu);
+
+	/*
+	 * Don't let 'init optimized' areas of the XSAVE area
+	 * leak into the child task:
+	 */
+	if (use_eager_fpu())
+		memset(&dst_fpu->state.xsave, 0, xstate_size);
+
+	/*
+	 * Save current FPU registers directly into the child
+	 * FPU context, without any memory-to-memory copying.
+	 *
+	 * If the FPU context got destroyed in the process (FNSAVE
+	 * done on old CPUs) then copy it back into the source
+	 * context and mark the current task for lazy restore.
+	 *
+	 * We have to do all this with preemption disabled,
+	 * mostly because of the FNSAVE case, because in that
+	 * case we must not allow preemption in the window
+	 * between the FNSAVE and us marking the context lazy.
+	 *
+	 * It shouldn't be an issue as even FNSAVE is plenty
+	 * fast in terms of critical section length.
+	 */
+	preempt_disable();
+	if (!copy_fpregs_to_fpstate(dst_fpu)) {
+		memcpy(&src_fpu->state, &dst_fpu->state, xstate_size);
+		fpregs_deactivate(src_fpu);
+	}
+	preempt_enable();
+}
+
+int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
+{
+	dst_fpu->counter = 0;
+	dst_fpu->fpregs_active = 0;
+	dst_fpu->last_cpu = -1;
+
+	if (src_fpu->fpstate_active)
+		fpu_copy(dst_fpu, src_fpu);
+
+	return 0;
+}
+
+/*
+ * Activate the current task's in-memory FPU context,
+ * if it has not been used before:
+ */
+void fpu__activate_curr(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu);
+
+	if (!fpu->fpstate_active) {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for the current task: */
+		fpu->fpstate_active = 1;
+	}
+}
+EXPORT_SYMBOL_GPL(fpu__activate_curr);
+
+/*
+ * This function must be called before we read a task's fpstate.
+ *
+ * If the task has not used the FPU before then initialize its
+ * fpstate.
+ *
+ * If the task has used the FPU before then save it.
+ */
+void fpu__activate_fpstate_read(struct fpu *fpu)
+{
+	/*
+	 * If fpregs are active (in the current CPU), then
+	 * copy them to the fpstate:
+	 */
+	if (fpu->fpregs_active) {
+		fpu__save(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpstate_init(&fpu->state);
+
+			/* Safe to do for current and for stopped child tasks: */
+			fpu->fpstate_active = 1;
+		}
+	}
+}
+
+/*
+ * This function must be called before we write a task's fpstate.
+ *
+ * If the task has used the FPU before then unlazy it.
+ * If the task has not used the FPU before then initialize its fpstate.
+ *
+ * After this function call, after registers in the fpstate are
+ * modified and the child task has woken up, the child task will
+ * restore the modified FPU state from the modified context. If we
+ * didn't clear its lazy status here then the lazy in-registers
+ * state pending on its former CPU could be restored, corrupting
+ * the modifications.
+ */
+void fpu__activate_fpstate_write(struct fpu *fpu)
+{
+	/*
+	 * Only stopped child tasks can be used to modify the FPU
+	 * state in the fpstate buffer:
+	 */
+	WARN_ON_FPU(fpu == &current->thread.fpu);
+
+	if (fpu->fpstate_active) {
+		/* Invalidate any lazy state: */
+		fpu->last_cpu = -1;
+	} else {
+		fpstate_init(&fpu->state);
+
+		/* Safe to do for stopped child tasks: */
+		fpu->fpstate_active = 1;
+	}
+}
+
+/*
+ * 'fpu__restore()' is called to copy FPU registers from
+ * the FPU fpstate to the live hw registers and to activate
+ * access to the hardware registers, so that FPU instructions
+ * can be used afterwards.
+ *
+ * Must be called with kernel preemption disabled (for example
+ * with local interrupts disabled, as it is in the case of
+ * do_device_not_available()).
+ */
+void fpu__restore(struct fpu *fpu)
+{
+	fpu__activate_curr(fpu);
+
+	/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
+	kernel_fpu_disable();
+	fpregs_activate(fpu);
+	copy_kernel_to_fpregs(&fpu->state);
+	fpu->counter++;
+	kernel_fpu_enable();
+}
+EXPORT_SYMBOL_GPL(fpu__restore);
+
+/*
+ * Drops current FPU state: deactivates the fpregs and
+ * the fpstate. NOTE: it still leaves previous contents
+ * in the fpregs in the eager-FPU case.
+ *
+ * This function can be used in cases where we know that
+ * a state-restore is coming: either an explicit one,
+ * or a reschedule.
+ */
+void fpu__drop(struct fpu *fpu)
+{
+	preempt_disable();
+	fpu->counter = 0;
+
+	if (fpu->fpregs_active) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		fpregs_deactivate(fpu);
+	}
+
+	fpu->fpstate_active = 0;
+
+	preempt_enable();
+}
+
+/*
+ * Clear FPU registers by setting them up from
+ * the init fpstate:
+ */
+static inline void copy_init_fpstate_to_fpregs(void)
+{
+	if (use_xsave())
+		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+	else
+		copy_kernel_to_fxregs(&init_fpstate.fxsave);
+}
+
+/*
+ * Clear the FPU state back to init state.
+ *
+ * Called by sys_execve(), by the signal handler code and by various
+ * error paths.
+ */
+void fpu__clear(struct fpu *fpu)
+{
+	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+
+	if (!use_eager_fpu()) {
+		/* FPU state will be reallocated lazily at the first use. */
+		fpu__drop(fpu);
+	} else {
+		if (!fpu->fpstate_active) {
+			fpu__activate_curr(fpu);
+			user_fpu_begin();
+		}
+		copy_init_fpstate_to_fpregs();
+	}
+}
+
+/*
+ * x87 math exception handling:
+ */
+
+static inline unsigned short get_fpu_cwd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.cwd;
+	} else {
+		return (unsigned short)fpu->state.fsave.cwd;
+	}
+}
+
+static inline unsigned short get_fpu_swd(struct fpu *fpu)
+{
+	if (cpu_has_fxsr) {
+		return fpu->state.fxsave.swd;
+	} else {
+		return (unsigned short)fpu->state.fsave.swd;
+	}
+}
+
+static inline unsigned short get_fpu_mxcsr(struct fpu *fpu)
+{
+	if (cpu_has_xmm) {
+		return fpu->state.fxsave.mxcsr;
+	} else {
+		return MXCSR_DEFAULT;
+	}
+}
+
+int fpu__exception_code(struct fpu *fpu, int trap_nr)
+{
+	int err;
+
+	if (trap_nr == X86_TRAP_MF) {
+		unsigned short cwd, swd;
+		/*
+		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
+		 * status.  0x3f is the exception bits in these regs, 0x200 is the
+		 * C1 reg you need in case of a stack fault, 0x040 is the stack
+		 * fault bit.  We should only be taking one exception at a time,
+		 * so if this combination doesn't produce any single exception,
+		 * then we have a bad program that isn't synchronizing its FPU usage
+		 * and it will suffer the consequences since we won't be able to
+		 * fully reproduce the context of the exception
+		 */
+		cwd = get_fpu_cwd(fpu);
+		swd = get_fpu_swd(fpu);
+
+		err = swd & ~cwd;
+	} else {
+		/*
+		 * The SIMD FPU exceptions are handled a little differently, as there
+		 * is only a single status/control register.  Thus, to determine which
+		 * unmasked exception was caught we must mask the exception mask bits
+		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+		 */
+		unsigned short mxcsr = get_fpu_mxcsr(fpu);
+		err = ~(mxcsr >> 7) & mxcsr;
+	}
+
+	if (err & 0x001) {	/* Invalid op */
+		/*
+		 * swd & 0x240 == 0x040: Stack Underflow
+		 * swd & 0x240 == 0x240: Stack Overflow
+		 * User must clear the SF bit (0x40) if set
+		 */
+		return FPE_FLTINV;
+	} else if (err & 0x004) { /* Divide by Zero */
+		return FPE_FLTDIV;
+	} else if (err & 0x008) { /* Overflow */
+		return FPE_FLTOVF;
+	} else if (err & 0x012) { /* Denormal, Underflow */
+		return FPE_FLTUND;
+	} else if (err & 0x020) { /* Precision */
+		return FPE_FLTRES;
+	}
+
+	/*
+	 * If we're using IRQ 13, or supposedly even some trap
+	 * X86_TRAP_MF implementations, it's possible
+	 * we get a spurious trap, which is not an error.
+	 */
+	return 0;
+}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
new file mode 100644
index 000000000000..fc878fee6a51
--- /dev/null
+++ b/arch/x86/kernel/fpu/init.c
@@ -0,0 +1,354 @@
+/*
+ * x86 FPU boot time init code:
+ */
+#include <asm/fpu/internal.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Initialize the TS bit in CR0 according to the style of context-switches
+ * we are using:
+ */
+static void fpu__init_cpu_ctx_switch(void)
+{
+	if (!cpu_has_eager_fpu)
+		stts();
+	else
+		clts();
+}
+
+/*
+ * Initialize the registers found in all CPUs, CR0 and CR4:
+ */
+static void fpu__init_cpu_generic(void)
+{
+	unsigned long cr0;
+	unsigned long cr4_mask = 0;
+
+	if (cpu_has_fxsr)
+		cr4_mask |= X86_CR4_OSFXSR;
+	if (cpu_has_xmm)
+		cr4_mask |= X86_CR4_OSXMMEXCPT;
+	if (cr4_mask)
+		cr4_set_bits(cr4_mask);
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+	if (!cpu_has_fpu)
+		cr0 |= X86_CR0_EM;
+	write_cr0(cr0);
+
+	/* Flush out any pending x87 state: */
+	asm volatile ("fninit");
+}
+
+/*
+ * Enable all supported FPU features. Called when a CPU is brought online:
+ */
+void fpu__init_cpu(void)
+{
+	fpu__init_cpu_generic();
+	fpu__init_cpu_xstate();
+	fpu__init_cpu_ctx_switch();
+}
+
+/*
+ * The earliest FPU detection code.
+ *
+ * Set the X86_FEATURE_FPU CPU-capability bit based on
+ * trying to execute an actual sequence of FPU instructions:
+ */
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+	unsigned long cr0;
+	u16 fsw, fcw;
+
+	fsw = fcw = 0xffff;
+
+	cr0 = read_cr0();
+	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
+	write_cr0(cr0);
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
+		set_cpu_cap(c, X86_FEATURE_FPU);
+	else
+		clear_cpu_cap(c, X86_FEATURE_FPU);
+
+#ifndef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu) {
+		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
+		for (;;)
+			asm volatile("hlt");
+	}
+#endif
+}
+
+/*
+ * Boot time FPU feature detection code:
+ */
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+
+static void __init fpu__init_system_mxcsr(void)
+{
+	unsigned int mask = 0;
+
+	if (cpu_has_fxsr) {
+		struct fxregs_state fx_tmp __aligned(32) = { };
+
+		asm volatile("fxsave %0" : "+m" (fx_tmp));
+
+		mask = fx_tmp.mxcsr_mask;
+
+		/*
+		 * If zero then use the default features mask,
+		 * which has all features set, except the
+		 * denormals-are-zero feature bit:
+		 */
+		if (mask == 0)
+			mask = 0x0000ffbf;
+	}
+	mxcsr_feature_mask &= mask;
+}
+
+/*
+ * Once per bootup FPU initialization sequences that will run on most x86 CPUs:
+ */
+static void __init fpu__init_system_generic(void)
+{
+	/*
+	 * Set up the legacy init FPU context. (xstate init might overwrite this
+	 * with a more modern format, if the CPU supports it.)
+	 */
+	fpstate_init_fxstate(&init_fpstate.fxsave);
+
+	fpu__init_system_mxcsr();
+}
+
+/*
+ * Size of the FPU context state. All tasks in the system use the
+ * same context size, regardless of what portion they use.
+ * This is inherent to the XSAVE architecture which puts all state
+ * components into a single, continuous memory block:
+ */
+unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
+
+/*
+ * Set up the xstate_size based on the legacy FPU context size.
+ *
+ * We set this up first, and later it will be overwritten by
+ * fpu__init_system_xstate() if the CPU knows about xstates.
+ */
+static void __init fpu__init_system_xstate_size_legacy(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	/*
+	 * Note that xstate_size might be overwriten later during
+	 * fpu__init_system_xstate().
+	 */
+
+	if (!cpu_has_fpu) {
+		/*
+		 * Disable xsave as we do not support it if i387
+		 * emulation is enabled.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+		xstate_size = sizeof(struct swregs_state);
+	} else {
+		if (cpu_has_fxsr)
+			xstate_size = sizeof(struct fxregs_state);
+		else
+			xstate_size = sizeof(struct fregs_state);
+	}
+	/*
+	 * Quirk: we don't yet handle the XSAVES* instructions
+	 * correctly, as we don't correctly convert between
+	 * standard and compacted format when interfacing
+	 * with user-space - so disable it for now.
+	 *
+	 * The difference is small: with recent CPUs the
+	 * compacted format is only marginally smaller than
+	 * the standard FPU state format.
+	 *
+	 * ( This is easy to backport while we are fixing
+	 *   XSAVES* support. )
+	 */
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+}
+
+/*
+ * FPU context switching strategies:
+ *
+ * Against popular belief, we don't do lazy FPU saves, due to the
+ * task migration complications it brings on SMP - we only do
+ * lazy FPU restores.
+ *
+ * 'lazy' is the traditional strategy, which is based on setting
+ * CR0::TS to 1 during context-switch (instead of doing a full
+ * restore of the FPU state), which causes the first FPU instruction
+ * after the context switch (whenever it is executed) to fault - at
+ * which point we lazily restore the FPU state into FPU registers.
+ *
+ * Tasks are of course under no obligation to execute FPU instructions,
+ * so it can easily happen that another context-switch occurs without
+ * a single FPU instruction being executed. If we eventually switch
+ * back to the original task (that still owns the FPU) then we have
+ * not only saved the restores along the way, but we also have the
+ * FPU ready to be used for the original task.
+ *
+ * 'eager' switching is used on modern CPUs, there we switch the FPU
+ * state during every context switch, regardless of whether the task
+ * has used FPU instructions in that time slice or not. This is done
+ * because modern FPU context saving instructions are able to optimize
+ * state saving and restoration in hardware: they can detect both
+ * unused and untouched FPU state and optimize accordingly.
+ *
+ * [ Note that even in 'lazy' mode we might optimize context switches
+ *   to use 'eager' restores, if we detect that a task is using the FPU
+ *   frequently. See the fpu->counter logic in fpu/internal.h for that. ]
+ */
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+
+static int __init eager_fpu_setup(char *s)
+{
+	if (!strcmp(s, "on"))
+		eagerfpu = ENABLE;
+	else if (!strcmp(s, "off"))
+		eagerfpu = DISABLE;
+	else if (!strcmp(s, "auto"))
+		eagerfpu = AUTO;
+	return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
+/*
+ * Pick the FPU context switching strategy:
+ */
+static void __init fpu__init_system_ctx_switch(void)
+{
+	static bool on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	WARN_ON_FPU(current->thread.fpu.fpstate_active);
+	current_thread_info()->status = 0;
+
+	/* Auto enable eagerfpu for xsaveopt */
+	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+		eagerfpu = ENABLE;
+
+	if (xfeatures_mask & XSTATE_EAGER) {
+		if (eagerfpu == DISABLE) {
+			pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n",
+			       xfeatures_mask & XSTATE_EAGER);
+			xfeatures_mask &= ~XSTATE_EAGER;
+		} else {
+			eagerfpu = ENABLE;
+		}
+	}
+
+	if (eagerfpu == ENABLE)
+		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+	printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy");
+}
+
+/*
+ * Called on the boot CPU once per system bootup, to set up the initial
+ * FPU state that is later cloned into all processes:
+ */
+void __init fpu__init_system(struct cpuinfo_x86 *c)
+{
+	fpu__init_system_early_generic(c);
+
+	/*
+	 * The FPU has to be operational for some of the
+	 * later FPU init activities:
+	 */
+	fpu__init_cpu();
+
+	/*
+	 * But don't leave CR0::TS set yet, as some of the FPU setup
+	 * methods depend on being able to execute FPU instructions
+	 * that will fault on a set TS, such as the FXSAVE in
+	 * fpu__init_system_mxcsr().
+	 */
+	clts();
+
+	fpu__init_system_generic();
+	fpu__init_system_xstate_size_legacy();
+	fpu__init_system_xstate();
+
+	fpu__init_system_ctx_switch();
+}
+
+/*
+ * Boot parameter to turn off FPU support and fall back to math-emu:
+ */
+static int __init no_387(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FPU);
+	return 1;
+}
+__setup("no387", no_387);
+
+/*
+ * Disable all xstate CPU features:
+ */
+static int __init x86_noxsave_setup(char *s)
+{
+	if (strlen(s))
+		return 0;
+
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+	setup_clear_cpu_cap(X86_FEATURE_AVX);
+	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+
+	return 1;
+}
+__setup("noxsave", x86_noxsave_setup);
+
+/*
+ * Disable the XSAVEOPT instruction specifically:
+ */
+static int __init x86_noxsaveopt_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+
+	return 1;
+}
+__setup("noxsaveopt", x86_noxsaveopt_setup);
+
+/*
+ * Disable the XSAVES instruction:
+ */
+static int __init x86_noxsaves_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
+
+	return 1;
+}
+__setup("noxsaves", x86_noxsaves_setup);
+
+/*
+ * Disable FX save/restore and SSE support:
+ */
+static int __init x86_nofxsr_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_FXSR);
+	setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT);
+	setup_clear_cpu_cap(X86_FEATURE_XMM);
+
+	return 1;
+}
+__setup("nofxsr", x86_nofxsr_setup);
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
new file mode 100644
index 000000000000..dc60810c1c74
--- /dev/null
+++ b/arch/x86/kernel/fpu/regset.c
@@ -0,0 +1,356 @@
+/*
+ * FPU register's regset abstraction, for ptrace, core dumps, etc.
+ */
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+/*
+ * The xstateregs_active() routine is the same as the regset_fpregs_active() routine,
+ * as the "regset->n" for the xstate regset will be updated based on the feature
+ * capabilites supported by the xsave.
+ */
+int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return target_fpu->fpstate_active ? regset->n : 0;
+}
+
+int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
+{
+	struct fpu *target_fpu = &target->thread.fpu;
+
+	return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0;
+}
+
+int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &fpu->state.fxsave, 0, -1);
+}
+
+int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	int ret;
+
+	if (!cpu_has_fxsr)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &fpu->state.fxsave, 0, -1);
+
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	fpu->state.fxsave.mxcsr &= mxcsr_feature_mask;
+
+	/*
+	 * update the header bits in the xsave header, indicating the
+	 * presence of FP and SSE state.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE;
+
+	return ret;
+}
+
+int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_read(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	/*
+	 * Copy the 48bytes defined by the software first into the xstate
+	 * memory layout in the thread struct, so that we can copy the entire
+	 * xstateregs to the user using one user_regset_copyout().
+	 */
+	memcpy(&xsave->i387.sw_reserved,
+		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
+	/*
+	 * Copy the xstate memory layout.
+	 */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	return ret;
+}
+
+int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave;
+	int ret;
+
+	if (!cpu_has_xsave)
+		return -ENODEV;
+
+	fpu__activate_fpstate_write(fpu);
+
+	xsave = &fpu->state.xsave;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
+	/*
+	 * mxcsr reserved bits must be masked to zero for security reasons.
+	 */
+	xsave->i387.mxcsr &= mxcsr_feature_mask;
+	xsave->header.xfeatures &= xfeatures_mask;
+	/*
+	 * These bits must be zero.
+	 */
+	memset(&xsave->header.reserved, 0, 48);
+
+	return ret;
+}
+
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+
+/*
+ * FPU tag word conversions.
+ */
+
+static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
+{
+	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
+
+	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
+	tmp = ~twd;
+	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
+	/* and move the valid bits to the lower byte. */
+	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
+	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
+	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
+
+	return tmp;
+}
+
+#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
+#define FP_EXP_TAG_VALID	0
+#define FP_EXP_TAG_ZERO		1
+#define FP_EXP_TAG_SPECIAL	2
+#define FP_EXP_TAG_EMPTY	3
+
+static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave)
+{
+	struct _fpxreg *st;
+	u32 tos = (fxsave->swd >> 11) & 7;
+	u32 twd = (unsigned long) fxsave->twd;
+	u32 tag;
+	u32 ret = 0xffff0000u;
+	int i;
+
+	for (i = 0; i < 8; i++, twd >>= 1) {
+		if (twd & 0x1) {
+			st = FPREG_ADDR(fxsave, (i - tos) & 7);
+
+			switch (st->exponent & 0x7fff) {
+			case 0x7fff:
+				tag = FP_EXP_TAG_SPECIAL;
+				break;
+			case 0x0000:
+				if (!st->significand[0] &&
+				    !st->significand[1] &&
+				    !st->significand[2] &&
+				    !st->significand[3])
+					tag = FP_EXP_TAG_ZERO;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			default:
+				if (st->significand[3] & 0x8000)
+					tag = FP_EXP_TAG_VALID;
+				else
+					tag = FP_EXP_TAG_SPECIAL;
+				break;
+			}
+		} else {
+			tag = FP_EXP_TAG_EMPTY;
+		}
+		ret |= tag << (2 * i);
+	}
+	return ret;
+}
+
+/*
+ * FXSR floating point environment conversions.
+ */
+
+void
+convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	env->cwd = fxsave->cwd | 0xffff0000u;
+	env->swd = fxsave->swd | 0xffff0000u;
+	env->twd = twd_fxsr_to_i387(fxsave);
+
+#ifdef CONFIG_X86_64
+	env->fip = fxsave->rip;
+	env->foo = fxsave->rdp;
+	/*
+	 * should be actually ds/cs at fpu exception time, but
+	 * that information is not available in 64bit mode.
+	 */
+	env->fcs = task_pt_regs(tsk)->cs;
+	if (tsk == current) {
+		savesegment(ds, env->fos);
+	} else {
+		env->fos = tsk->thread.ds;
+	}
+	env->fos |= 0xffff0000;
+#else
+	env->fip = fxsave->fip;
+	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
+	env->foo = fxsave->foo;
+	env->fos = fxsave->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(to[0]));
+}
+
+void convert_to_fxsr(struct task_struct *tsk,
+		     const struct user_i387_ia32_struct *env)
+
+{
+	struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave;
+	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
+	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
+	int i;
+
+	fxsave->cwd = env->cwd;
+	fxsave->swd = env->swd;
+	fxsave->twd = twd_i387_to_fxsr(env->twd);
+	fxsave->fop = (u16) ((u32) env->fcs >> 16);
+#ifdef CONFIG_X86_64
+	fxsave->rip = env->fip;
+	fxsave->rdp = env->foo;
+	/* cs and ds ignored */
+#else
+	fxsave->fip = env->fip;
+	fxsave->fcs = (env->fcs & 0xffff);
+	fxsave->foo = env->foo;
+	fxsave->fos = env->fos;
+#endif
+
+	for (i = 0; i < 8; ++i)
+		memcpy(&to[i], &from[i], sizeof(from[0]));
+}
+
+int fpregs_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       void *kbuf, void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+
+	fpu__activate_fpstate_read(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					   &fpu->state.fsave, 0,
+					   -1);
+
+	fpstate_sanitize_xstate(fpu);
+
+	if (kbuf && pos == 0 && count == sizeof(env)) {
+		convert_from_fxsr(kbuf, target);
+		return 0;
+	}
+
+	convert_from_fxsr(&env, target);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+}
+
+int fpregs_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct user_i387_ia32_struct env;
+	int ret;
+
+	fpu__activate_fpstate_write(fpu);
+	fpstate_sanitize_xstate(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
+
+	if (!cpu_has_fxsr)
+		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					  &fpu->state.fsave, 0,
+					  -1);
+
+	if (pos > 0 || count < sizeof(env))
+		convert_from_fxsr(&env, target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
+	if (!ret)
+		convert_to_fxsr(target, &env);
+
+	/*
+	 * update the header bit in the xsave header, indicating the
+	 * presence of FP.
+	 */
+	if (cpu_has_xsave)
+		fpu->state.xsave.header.xfeatures |= XSTATE_FP;
+	return ret;
+}
+
+/*
+ * FPU state for core dumps.
+ * This is only used for a.out dumps now.
+ * It is declared generically using elf_fpregset_t (which is
+ * struct user_i387_struct) but is in fact only used for 32-bit
+ * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
+ */
+int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu)
+{
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int fpvalid;
+
+	fpvalid = fpu->fpstate_active;
+	if (fpvalid)
+		fpvalid = !fpregs_get(tsk, NULL,
+				      0, sizeof(struct user_i387_ia32_struct),
+				      ufpu, NULL);
+
+	return fpvalid;
+}
+EXPORT_SYMBOL(dump_fpu);
+
+#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
new file mode 100644
index 000000000000..50ec9af1bd51
--- /dev/null
+++ b/arch/x86/kernel/fpu/signal.c
@@ -0,0 +1,404 @@
+/*
+ * FPU signal frame handling routines.
+ */
+
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/sigframe.h>
+
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
+
+/*
+ * Check for the presence of extended state information in the
+ * user fpstate pointer in the sigcontext.
+ */
+static inline int check_for_xstate(struct fxregs_state __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
+{
+	int min_xstate_size = sizeof(struct fxregs_state) +
+			      sizeof(struct xstate_header);
+	unsigned int magic2;
+
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
+
+	/* Check for the first magic field and other error scenarios. */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+	    fx_sw->xstate_size < min_xstate_size ||
+	    fx_sw->xstate_size > xstate_size ||
+	    fx_sw->xstate_size > fx_sw->extended_size)
+		return -1;
+
+	/*
+	 * Check for the presence of second magic word at the end of memory
+	 * layout. This detects the case where the user just copied the legacy
+	 * fpstate layout with out copying the extended state information
+	 * in the memory layout.
+	 */
+	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Signal frame handlers.
+ */
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
+{
+	if (use_fxsr()) {
+		struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
+
+		convert_from_fxsr(&env, tsk);
+
+		if (__copy_to_user(buf, &env, sizeof(env)) ||
+		    __put_user(xsave->i387.swd, &fp->status) ||
+		    __put_user(X86_FXSR_MAGIC, &fp->magic))
+			return -1;
+	} else {
+		struct fregs_state __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
+			return -1;
+	}
+
+	return 0;
+}
+
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+	struct xregs_state __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xfeatures;
+	int err;
+
+	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
+
+	if (!use_xsave())
+		return err;
+
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
+
+	/*
+	 * Read the xfeatures which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
+	 */
+	err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	/*
+	 * For legacy compatible, we always set FP/SSE bits in the bit
+	 * vector while saving the state to the user context. This will
+	 * enable us capturing any changes(during sigreturn) to
+	 * the FP/SSE bits by the legacy applications which don't touch
+	 * xfeatures in the xsave header.
+	 *
+	 * xsave aware apps can change the xfeatures in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	xfeatures |= XSTATE_FPSSE;
+
+	err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
+
+	return err;
+}
+
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = copy_xregs_to_user(buf);
+	else if (use_fxsr())
+		err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
+	else
+		err = copy_fregs_to_user((struct fregs_state __user *) buf);
+
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	return err;
+}
+
+/*
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ *  state is copied.
+ *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ *	buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
+ */
+int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+{
+	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct task_struct *tsk = current;
+	int ia32_fxstate = (buf != buf_fx);
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!access_ok(VERIFY_WRITE, buf, size))
+		return -EACCES;
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (fpregs_active()) {
+		/* Save the live register state to the user directly. */
+		if (copy_fpregs_to_sigframe(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			copy_fxregs_to_kernel(&tsk->thread.fpu);
+	} else {
+		fpstate_sanitize_xstate(&tsk->thread.fpu);
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
+			return -1;
+	}
+
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
+
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xfeatures, int fx_only)
+{
+	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct xstate_header *header = &xsave->header;
+
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		memset(header->reserved, 0, 48);
+
+		/*
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
+		 */
+		if (fx_only)
+			header->xfeatures = XSTATE_FPSSE;
+		else
+			header->xfeatures &= (xfeatures_mask & xfeatures);
+	}
+
+	if (use_fxsr()) {
+		/*
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
+		 */
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+		convert_to_fxsr(tsk, ia32_env);
+	}
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
+{
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
+			copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_fxregs(buf);
+		} else {
+			u64 init_bv = xfeatures_mask & ~xbv;
+			if (unlikely(init_bv))
+				copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
+			return copy_user_to_xregs(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return copy_user_to_fxregs(buf);
+	} else
+		return copy_user_to_fregs(buf);
+}
+
+static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	int ia32_fxstate = (buf != buf_fx);
+	struct task_struct *tsk = current;
+	struct fpu *fpu = &tsk->thread.fpu;
+	int state_size = xstate_size;
+	u64 xfeatures = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!buf) {
+		fpu__clear(fpu);
+		return 0;
+	}
+
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	fpu__activate_curr(fpu);
+
+	if (!static_cpu_has(X86_FEATURE_FPU))
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
+
+	if (use_xsave()) {
+		struct _fpx_sw_bytes fx_sw_user;
+		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+			/*
+			 * Couldn't find the extended state information in the
+			 * memory layout. Restore just the FP/SSE and init all
+			 * the other extended state.
+			 */
+			state_size = sizeof(struct fxregs_state);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xfeatures = fx_sw_user.xfeatures;
+		}
+	}
+
+	if (ia32_fxstate) {
+		/*
+		 * For 32-bit frames with fxstate, copy the user state to the
+		 * thread's fpu state, reconstruct fxstate from the fsave
+		 * header. Sanitize the copied state etc.
+		 */
+		struct fpu *fpu = &tsk->thread.fpu;
+		struct user_i387_ia32_struct env;
+		int err = 0;
+
+		/*
+		 * Drop the current fpu which clears fpu->fpstate_active. This ensures
+		 * that any context-switch during the copy of the new state,
+		 * avoids the intermediate state from getting restored/saved.
+		 * Thus avoiding the new restored state from getting corrupted.
+		 * We will be ready to restore/save the state only after
+		 * fpu->fpstate_active is again set.
+		 */
+		fpu__drop(fpu);
+
+		if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpstate_init(&fpu->state);
+			err = -1;
+		} else {
+			sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
+		}
+
+		fpu->fpstate_active = 1;
+		if (use_eager_fpu()) {
+			preempt_disable();
+			fpu__restore(fpu);
+			preempt_enable();
+		}
+
+		return err;
+	} else {
+		/*
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
+		 */
+		user_fpu_begin();
+		if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
+			fpu__clear(fpu);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int xstate_sigframe_size(void)
+{
+	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+/*
+ * Restore FPU state from a sigframe:
+ */
+int fpu__restore_sig(void __user *buf, int ia32_frame)
+{
+	void __user *buf_fx = buf;
+	int size = xstate_sigframe_size();
+
+	if (ia32_frame && use_fxsr()) {
+		buf_fx = buf + sizeof(struct fregs_state);
+		size += sizeof(struct fregs_state);
+	}
+
+	return __fpu__restore_sig(buf, buf_fx, size);
+}
+
+unsigned long
+fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
+		     unsigned long *buf_fx, unsigned long *size)
+{
+	unsigned long frame_size = xstate_sigframe_size();
+
+	*buf_fx = sp = round_down(sp - frame_size, 64);
+	if (ia32_frame && use_fxsr()) {
+		frame_size += sizeof(struct fregs_state);
+		sp -= sizeof(struct fregs_state);
+	}
+
+	*size = frame_size;
+
+	return sp;
+}
+/*
+ * Prepare the SW reserved portion of the fxsave memory layout, indicating
+ * the presence of the extended state information in the memory layout
+ * pointed by the fpstate pointer in the sigcontext.
+ * This will be saved when ever the FP and extended state context is
+ * saved on the user stack during the signal handler delivery to the user.
+ */
+void fpu__init_prepare_fx_sw_frame(void)
+{
+	int fsave_header_size = sizeof(struct fregs_state);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
+
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
+
+	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
+	fx_sw_reserved.extended_size = size;
+	fx_sw_reserved.xfeatures = xfeatures_mask;
+	fx_sw_reserved.xstate_size = xstate_size;
+
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
+
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
new file mode 100644
index 000000000000..62fc001c7846
--- /dev/null
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -0,0 +1,461 @@
+/*
+ * xsave/xrstor support.
+ *
+ * Author: Suresh Siddha <suresh.b.siddha@intel.com>
+ */
+#include <linux/compat.h>
+#include <linux/cpu.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
+
+#include <asm/tlbflush.h>
+
+static const char *xfeature_names[] =
+{
+	"x87 floating point registers"	,
+	"SSE registers"			,
+	"AVX registers"			,
+	"MPX bounds registers"		,
+	"MPX CSR"			,
+	"AVX-512 opmask"		,
+	"AVX-512 Hi256"			,
+	"AVX-512 ZMM_Hi256"		,
+	"unknown xstate feature"	,
+};
+
+/*
+ * Mask of xstate features supported by the CPU and the kernel:
+ */
+u64 xfeatures_mask __read_mostly;
+
+static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_sizes[XFEATURES_NR_MAX]   = { [ 0 ... XFEATURES_NR_MAX - 1] = -1};
+static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
+
+/* The number of supported xfeatures in xfeatures_mask: */
+static unsigned int xfeatures_nr;
+
+/*
+ * Return whether the system supports a given xfeature.
+ *
+ * Also return the name of the (most advanced) feature that the caller requested:
+ */
+int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name)
+{
+	u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask;
+
+	if (unlikely(feature_name)) {
+		long xfeature_idx, max_idx;
+		u64 xfeatures_print;
+		/*
+		 * So we use FLS here to be able to print the most advanced
+		 * feature that was requested but is missing. So if a driver
+		 * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the
+		 * missing AVX feature - this is the most informative message
+		 * to users:
+		 */
+		if (xfeatures_missing)
+			xfeatures_print = xfeatures_missing;
+		else
+			xfeatures_print = xfeatures_needed;
+
+		xfeature_idx = fls64(xfeatures_print)-1;
+		max_idx = ARRAY_SIZE(xfeature_names)-1;
+		xfeature_idx = min(xfeature_idx, max_idx);
+
+		*feature_name = xfeature_names[xfeature_idx];
+	}
+
+	if (xfeatures_missing)
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(cpu_has_xfeatures);
+
+/*
+ * When executing XSAVEOPT (or other optimized XSAVE instructions), if
+ * a processor implementation detects that an FPU state component is still
+ * (or is again) in its initialized state, it may clear the corresponding
+ * bit in the header.xfeatures field, and can skip the writeout of registers
+ * to the corresponding memory layout.
+ *
+ * This means that when the bit is zero, the state component might still contain
+ * some previous - non-initialized register state.
+ *
+ * Before writing xstate information to user-space we sanitize those components,
+ * to always ensure that the memory layout of a feature will be in the init state
+ * if the corresponding header bit is zero. This is to ensure that user-space doesn't
+ * see some stale state in the memory layout during signal handling, debugging etc.
+ */
+void fpstate_sanitize_xstate(struct fpu *fpu)
+{
+	struct fxregs_state *fx = &fpu->state.fxsave;
+	int feature_bit;
+	u64 xfeatures;
+
+	if (!use_xsaveopt())
+		return;
+
+	xfeatures = fpu->state.xsave.header.xfeatures;
+
+	/*
+	 * None of the feature bits are in init state. So nothing else
+	 * to do for us, as the memory layout is up to date.
+	 */
+	if ((xfeatures & xfeatures_mask) == xfeatures_mask)
+		return;
+
+	/*
+	 * FP is in init state
+	 */
+	if (!(xfeatures & XSTATE_FP)) {
+		fx->cwd = 0x37f;
+		fx->swd = 0;
+		fx->twd = 0;
+		fx->fop = 0;
+		fx->rip = 0;
+		fx->rdp = 0;
+		memset(&fx->st_space[0], 0, 128);
+	}
+
+	/*
+	 * SSE is in init state
+	 */
+	if (!(xfeatures & XSTATE_SSE))
+		memset(&fx->xmm_space[0], 0, 256);
+
+	/*
+	 * First two features are FPU and SSE, which above we handled
+	 * in a special way already:
+	 */
+	feature_bit = 0x2;
+	xfeatures = (xfeatures_mask & ~xfeatures) >> 2;
+
+	/*
+	 * Update all the remaining memory layouts according to their
+	 * standard xstate layout, if their header bit is in the init
+	 * state:
+	 */
+	while (xfeatures) {
+		if (xfeatures & 0x1) {
+			int offset = xstate_offsets[feature_bit];
+			int size = xstate_sizes[feature_bit];
+
+			memcpy((void *)fx + offset,
+			       (void *)&init_fpstate.xsave + offset,
+			       size);
+		}
+
+		xfeatures >>= 1;
+		feature_bit++;
+	}
+}
+
+/*
+ * Enable the extended processor state save/restore feature.
+ * Called once per CPU onlining.
+ */
+void fpu__init_cpu_xstate(void)
+{
+	if (!cpu_has_xsave || !xfeatures_mask)
+		return;
+
+	cr4_set_bits(X86_CR4_OSXSAVE);
+	xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Record the offsets and sizes of various xstates contained
+ * in the XSAVE state memory layout.
+ *
+ * ( Note that certain features might be non-present, for them
+ *   we'll have 0 offset and 0 size. )
+ */
+static void __init setup_xstate_features(void)
+{
+	u32 eax, ebx, ecx, edx, leaf;
+
+	xfeatures_nr = fls64(xfeatures_mask);
+
+	for (leaf = 2; leaf < xfeatures_nr; leaf++) {
+		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
+
+		xstate_offsets[leaf] = ebx;
+		xstate_sizes[leaf] = eax;
+
+		printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax);
+	}
+}
+
+static void __init print_xstate_feature(u64 xstate_mask)
+{
+	const char *feature_name;
+
+	if (cpu_has_xfeatures(xstate_mask, &feature_name))
+		pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+}
+
+/*
+ * Print out all the supported xstate features:
+ */
+static void __init print_xstate_features(void)
+{
+	print_xstate_feature(XSTATE_FP);
+	print_xstate_feature(XSTATE_SSE);
+	print_xstate_feature(XSTATE_YMM);
+	print_xstate_feature(XSTATE_BNDREGS);
+	print_xstate_feature(XSTATE_BNDCSR);
+	print_xstate_feature(XSTATE_OPMASK);
+	print_xstate_feature(XSTATE_ZMM_Hi256);
+	print_xstate_feature(XSTATE_Hi16_ZMM);
+}
+
+/*
+ * This function sets up offsets and sizes of all extended states in
+ * xsave area. This supports both standard format and compacted format
+ * of the xsave aread.
+ */
+static void __init setup_xstate_comp(void)
+{
+	unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8];
+	int i;
+
+	/*
+	 * The FP xstates and SSE xstates are legacy states. They are always
+	 * in the fixed offsets in the xsave area in either compacted form
+	 * or standard form.
+	 */
+	xstate_comp_offsets[0] = 0;
+	xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space);
+
+	if (!cpu_has_xsaves) {
+		for (i = 2; i < xfeatures_nr; i++) {
+			if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+				xstate_comp_offsets[i] = xstate_offsets[i];
+				xstate_comp_sizes[i] = xstate_sizes[i];
+			}
+		}
+		return;
+	}
+
+	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+
+	for (i = 2; i < xfeatures_nr; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask))
+			xstate_comp_sizes[i] = xstate_sizes[i];
+		else
+			xstate_comp_sizes[i] = 0;
+
+		if (i > 2)
+			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
+					+ xstate_comp_sizes[i-1];
+
+	}
+}
+
+/*
+ * setup the xstate image representing the init state
+ */
+static void __init setup_init_fpu_buf(void)
+{
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave)
+		return;
+
+	setup_xstate_features();
+	print_xstate_features();
+
+	if (cpu_has_xsaves) {
+		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
+	}
+
+	/*
+	 * Init all the features state with header_bv being 0x0
+	 */
+	copy_kernel_to_xregs_booting(&init_fpstate.xsave);
+
+	/*
+	 * Dump the init state again. This is to identify the init state
+	 * of any feature which is not represented by all zero's.
+	 */
+	copy_xregs_to_kernel_booting(&init_fpstate.xsave);
+}
+
+/*
+ * Calculate total size of enabled xstates in XCR0/xfeatures_mask.
+ */
+static void __init init_xstate_size(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	int i;
+
+	if (!cpu_has_xsaves) {
+		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+		xstate_size = ebx;
+		return;
+	}
+
+	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
+	for (i = 2; i < 64; i++) {
+		if (test_bit(i, (unsigned long *)&xfeatures_mask)) {
+			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
+			xstate_size += eax;
+		}
+	}
+}
+
+/*
+ * Enable and initialize the xsave feature.
+ * Called once per system bootup.
+ */
+void __init fpu__init_system_xstate(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	static int on_boot_cpu = 1;
+
+	WARN_ON_FPU(!on_boot_cpu);
+	on_boot_cpu = 0;
+
+	if (!cpu_has_xsave) {
+		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+		return;
+	}
+
+	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
+		WARN_ON_FPU(1);
+		return;
+	}
+
+	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
+	xfeatures_mask = eax + ((u64)edx << 32);
+
+	if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
+		pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask);
+		BUG();
+	}
+
+	/* Support only the state known to the OS: */
+	xfeatures_mask = xfeatures_mask & XCNTXT_MASK;
+
+	/* Enable xstate instructions to be able to continue with initialization: */
+	fpu__init_cpu_xstate();
+
+	/* Recompute the context size for enabled features: */
+	init_xstate_size();
+
+	update_regset_xstate_info(xstate_size, xfeatures_mask);
+	fpu__init_prepare_fx_sw_frame();
+	setup_init_fpu_buf();
+	setup_xstate_comp();
+
+	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n",
+		xfeatures_mask,
+		xstate_size,
+		cpu_has_xsaves ? "compacted" : "standard");
+}
+
+/*
+ * Restore minimal FPU state after suspend:
+ */
+void fpu__resume_cpu(void)
+{
+	/*
+	 * Restore XCR0 on xsave capable CPUs:
+	 */
+	if (cpu_has_xsave)
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask);
+}
+
+/*
+ * Given the xsave area and a state inside, this function returns the
+ * address of the state.
+ *
+ * This is the API that is called to get xstate address in either
+ * standard format or compacted format of xsave area.
+ *
+ * Note that if there is no data for the field in the xsave buffer
+ * this will return NULL.
+ *
+ * Inputs:
+ *	xstate: the thread's storage area for all FPU data
+ *	xstate_feature: state which is defined in xsave.h (e.g.
+ *	XSTATE_FP, XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area, or NULL if the
+ *	field is not present in the xsave buffer.
+ */
+void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
+{
+	int feature_nr = fls64(xstate_feature) - 1;
+	/*
+	 * Do we even *have* xsave state?
+	 */
+	if (!boot_cpu_has(X86_FEATURE_XSAVE))
+		return NULL;
+
+	xsave = &current->thread.fpu.state.xsave;
+	/*
+	 * We should not ever be requesting features that we
+	 * have not enabled.  Remember that pcntxt_mask is
+	 * what we write to the XCR0 register.
+	 */
+	WARN_ONCE(!(xfeatures_mask & xstate_feature),
+		  "get of unsupported state");
+	/*
+	 * This assumes the last 'xsave*' instruction to
+	 * have requested that 'xstate_feature' be saved.
+	 * If it did not, we might be seeing and old value
+	 * of the field in the buffer.
+	 *
+	 * This can happen because the last 'xsave' did not
+	 * request that this feature be saved (unlikely)
+	 * or because the "init optimization" caused it
+	 * to not be saved.
+	 */
+	if (!(xsave->header.xfeatures & xstate_feature))
+		return NULL;
+
+	return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
+
+/*
+ * This wraps up the common operations that need to occur when retrieving
+ * data from xsave state.  It first ensures that the current task was
+ * using the FPU and retrieves the data in to a buffer.  It then calculates
+ * the offset of the requested field in the buffer.
+ *
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ *	@xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP,
+ *	XSTATE_SSE, etc...)
+ * Output:
+ *	address of the state in the xsave area or NULL if the state
+ *	is not present or is in its 'init state'.
+ */
+const void *get_xsave_field_ptr(int xsave_state)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	if (!fpu->fpstate_active)
+		return NULL;
+	/*
+	 * fpu__save() takes the CPU's xstate registers
+	 * and saves them off to the 'fpu memory buffer.
+	 */
+	fpu__save(fpu);
+
+	return get_xsave_addr(&fpu->state.xsave, xsave_state);
+}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 2b55ee6db053..5a4668136e98 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -167,7 +167,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	clear_bss();
 
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
-		set_intr_gate(i, early_idt_handlers[i]);
+		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
 
 	copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index d031bad9e07e..0e2d96ffd158 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -62,9 +62,16 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
-/* Number of possible pages in the lowmem region */
-LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
-	
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
+
 /* Enough space to fit pagetables for the low memory linear map */
 MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
@@ -478,21 +485,22 @@ is486:
 __INIT
 setup_once:
 	/*
-	 * Set up a idt with 256 entries pointing to ignore_int,
-	 * interrupt gates. It doesn't actually load idt - that needs
-	 * to be done on each CPU. Interrupts are enabled elsewhere,
-	 * when we can be relatively sure everything is ok.
+	 * Set up a idt with 256 interrupt gates that push zero if there
+	 * is no error code and then jump to early_idt_handler_common.
+	 * It doesn't actually load the idt - that needs to be done on
+	 * each CPU. Interrupts are enabled elsewhere, when we can be
+	 * relatively sure everything is ok.
 	 */
 
 	movl $idt_table,%edi
-	movl $early_idt_handlers,%eax
+	movl $early_idt_handler_array,%eax
 	movl $NUM_EXCEPTION_VECTORS,%ecx
 1:
 	movl %eax,(%edi)
 	movl %eax,4(%edi)
 	/* interrupt gate, dpl=0, present */
 	movl $(0x8E000000 + __KERNEL_CS),2(%edi)
-	addl $9,%eax
+	addl $EARLY_IDT_HANDLER_SIZE,%eax
 	addl $8,%edi
 	loop 1b
 
@@ -524,30 +532,32 @@ setup_once:
 	andl $0,setup_once_ref	/* Once is enough, thanks */
 	ret
 
-ENTRY(early_idt_handlers)
+ENTRY(early_idt_handler_array)
 	# 36(%esp) %eflags
 	# 32(%esp) %cs
 	# 28(%esp) %eip
 	# 24(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushl $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushl $i		# 20(%esp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
-ENDPROC(early_idt_handlers)
+ENDPROC(early_idt_handler_array)
 	
-	/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%esp)		# X86_TRAP_NMI
-	je is_nmi		# Ignore NMI
+	je .Lis_nmi		# Ignore NMI
 
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
@@ -600,10 +610,10 @@ ex_entry:
 	pop %ecx
 	pop %eax
 	decl %ss:early_recursion_flag
-is_nmi:
+.Lis_nmi:
 	addl $8,%esp		/* drop vector number and error code */
 	iret
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 /* This is the default interrupt "handler" :-) */
 	ALIGN
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ae6588b301c2..e5c27f729a38 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -321,30 +321,32 @@ bad_address:
 	jmp bad_address
 
 	__INIT
-	.globl early_idt_handlers
-early_idt_handlers:
+ENTRY(early_idt_handler_array)
 	# 104(%rsp) %rflags
 	#  96(%rsp) %cs
 	#  88(%rsp) %rip
 	#  80(%rsp) error code
 	i = 0
 	.rept NUM_EXCEPTION_VECTORS
-	.if (EXCEPTION_ERRCODE_MASK >> i) & 1
-	ASM_NOP2
-	.else
+	.ifeq (EXCEPTION_ERRCODE_MASK >> i) & 1
 	pushq $0		# Dummy error code, to make stack frame uniform
 	.endif
 	pushq $i		# 72(%rsp) Vector number
-	jmp early_idt_handler
+	jmp early_idt_handler_common
 	i = i + 1
+	.fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
 	.endr
+ENDPROC(early_idt_handler_array)
 
-/* This is global to keep gas from relaxing the jumps */
-ENTRY(early_idt_handler)
+early_idt_handler_common:
+	/*
+	 * The stack is the hardware frame, an error code or zero, and the
+	 * vector number.
+	 */
 	cld
 
 	cmpl $2,(%rsp)		# X86_TRAP_NMI
-	je is_nmi		# Ignore NMI
+	je .Lis_nmi		# Ignore NMI
 
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
@@ -409,10 +411,10 @@ ENTRY(early_idt_handler)
 	popq %rcx
 	popq %rax
 	decl early_recursion_flag(%rip)
-is_nmi:
+.Lis_nmi:
 	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
-ENDPROC(early_idt_handler)
+ENDPROC(early_idt_handler_common)
 
 	__INITDATA
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3acbff4716b0..10757d0a3fcf 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -12,6 +12,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 
+#include <asm/irqdomain.h>
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
@@ -305,8 +306,6 @@ static void hpet_legacy_clockevent_register(void)
 	printk(KERN_DEBUG "hpet clockevent registered\n");
 }
 
-static int hpet_setup_msi_irq(unsigned int irq);
-
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
@@ -357,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 			hpet_enable_legacy_int();
 		} else {
 			struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-			hpet_setup_msi_irq(hdev->irq);
+			irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 			disable_irq(hdev->irq);
 			irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 			enable_irq(hdev->irq);
@@ -423,6 +422,7 @@ static int hpet_legacy_next_event(unsigned long delta,
 
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
+static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
@@ -473,31 +473,6 @@ static int hpet_msi_next_event(unsigned long delta,
 	return hpet_next_event(delta, evt, hdev->num);
 }
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-	if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
-		irq_free_hwirq(irq);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
-	unsigned int irq = irq_alloc_hwirq(-1);
-
-	if (!irq)
-		return -EINVAL;
-
-	irq_set_handler_data(irq, dev);
-
-	if (hpet_setup_msi_irq(irq))
-		return -EINVAL;
-
-	dev->irq = irq;
-	return 0;
-}
-
 static irqreturn_t hpet_interrupt_handler(int irq, void *data)
 {
 	struct hpet_dev *dev = (struct hpet_dev *)data;
@@ -540,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
 	if (!(hdev->flags & HPET_DEV_VALID))
 		return;
 
-	if (hpet_setup_msi_irq(hdev->irq))
-		return;
-
 	hdev->cpu = cpu;
 	per_cpu(cpu_hpet_dev, cpu) = hdev;
 	evt->name = hdev->name;
@@ -574,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	unsigned int id;
 	unsigned int num_timers;
 	unsigned int num_timers_used = 0;
-	int i;
+	int i, irq;
 
 	if (hpet_msi_disable)
 		return;
@@ -587,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 	num_timers++; /* Value read out starts from 0 */
 	hpet_print_config();
 
+	hpet_domain = hpet_create_irq_domain(hpet_blockid);
+	if (!hpet_domain)
+		return;
+
 	hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
 	if (!hpet_devs)
 		return;
@@ -604,12 +580,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
 		hdev->flags = 0;
 		if (cfg & HPET_TN_PERIODIC_CAP)
 			hdev->flags |= HPET_DEV_PERI_CAP;
+		sprintf(hdev->name, "hpet%d", i);
 		hdev->num = i;
 
-		sprintf(hdev->name, "hpet%d", i);
-		if (hpet_assign_irq(hdev))
+		irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+		if (irq <= 0)
 			continue;
 
+		hdev->irq = irq;
 		hdev->flags |= HPET_DEV_FSB_CAP;
 		hdev->flags |= HPET_DEV_VALID;
 		num_timers_used++;
@@ -709,10 +687,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 }
 #else
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-	return 0;
-}
 static void hpet_msi_capability_lookup(unsigned int start_timer)
 {
 	return;
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 05fd74f537d6..64341aa485ae 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page);
 
 #ifdef CONFIG_PREEMPT
 EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
deleted file mode 100644
index 009183276bb7..000000000000
--- a/arch/x86/kernel/i387.c
+++ /dev/null
@@ -1,656 +0,0 @@
-/*
- *  Copyright (C) 1994 Linus Torvalds
- *
- *  Pentium III FXSR, SSE support
- *  General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- */
-#include <linux/module.h>
-#include <linux/regset.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-
-#include <asm/sigcontext.h>
-#include <asm/processor.h>
-#include <asm/math_emu.h>
-#include <asm/tlbflush.h>
-#include <asm/uaccess.h>
-#include <asm/ptrace.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/user.h>
-
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
-
-void kernel_fpu_disable(void)
-{
-	WARN_ON(this_cpu_read(in_kernel_fpu));
-	this_cpu_write(in_kernel_fpu, true);
-}
-
-void kernel_fpu_enable(void)
-{
-	this_cpu_write(in_kernel_fpu, false);
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- *
- * Except for the eagerfpu case when we return true; in the likely case
- * the thread has FPU but we are not going to set/clear TS.
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
-	if (this_cpu_read(in_kernel_fpu))
-		return false;
-
-	if (use_eager_fpu())
-		return true;
-
-	return !__thread_has_fpu(current) &&
-		(read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
-	struct pt_regs *regs = get_irq_regs();
-	return regs && user_mode(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-bool irq_fpu_usable(void)
-{
-	return !in_interrupt() ||
-		interrupted_user_mode() ||
-		interrupted_kernel_fpu_idle();
-}
-EXPORT_SYMBOL(irq_fpu_usable);
-
-void __kernel_fpu_begin(void)
-{
-	struct task_struct *me = current;
-
-	this_cpu_write(in_kernel_fpu, true);
-
-	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
-	} else {
-		this_cpu_write(fpu_owner_task, NULL);
-		if (!use_eager_fpu())
-			clts();
-	}
-}
-EXPORT_SYMBOL(__kernel_fpu_begin);
-
-void __kernel_fpu_end(void)
-{
-	struct task_struct *me = current;
-
-	if (__thread_has_fpu(me)) {
-		if (WARN_ON(restore_fpu_checking(me)))
-			fpu_reset_state(me);
-	} else if (!use_eager_fpu()) {
-		stts();
-	}
-
-	this_cpu_write(in_kernel_fpu, false);
-}
-EXPORT_SYMBOL(__kernel_fpu_end);
-
-void unlazy_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	if (__thread_has_fpu(tsk)) {
-		if (use_eager_fpu()) {
-			__save_fpu(tsk);
-		} else {
-			__save_init_fpu(tsk);
-			__thread_fpu_end(tsk);
-		}
-	}
-	preempt_enable();
-}
-EXPORT_SYMBOL(unlazy_fpu);
-
-unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
-unsigned int xstate_size;
-EXPORT_SYMBOL_GPL(xstate_size);
-static struct i387_fxsave_struct fx_scratch;
-
-static void mxcsr_feature_mask_init(void)
-{
-	unsigned long mask = 0;
-
-	if (cpu_has_fxsr) {
-		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : "+m" (fx_scratch));
-		mask = fx_scratch.mxcsr_mask;
-		if (mask == 0)
-			mask = 0x0000ffbf;
-	}
-	mxcsr_feature_mask &= mask;
-}
-
-static void init_thread_xstate(void)
-{
-	/*
-	 * Note that xstate_size might be overwriten later during
-	 * xsave_init().
-	 */
-
-	if (!cpu_has_fpu) {
-		/*
-		 * Disable xsave as we do not support it if i387
-		 * emulation is enabled.
-		 */
-		setup_clear_cpu_cap(X86_FEATURE_XSAVE);
-		setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
-		xstate_size = sizeof(struct i387_soft_struct);
-		return;
-	}
-
-	if (cpu_has_fxsr)
-		xstate_size = sizeof(struct i387_fxsave_struct);
-	else
-		xstate_size = sizeof(struct i387_fsave_struct);
-}
-
-/*
- * Called at bootup to set up the initial FPU state that is later cloned
- * into all processes.
- */
-
-void fpu_init(void)
-{
-	unsigned long cr0;
-	unsigned long cr4_mask = 0;
-
-#ifndef CONFIG_MATH_EMULATION
-	if (!cpu_has_fpu) {
-		pr_emerg("No FPU found and no math emulation present\n");
-		pr_emerg("Giving up\n");
-		for (;;)
-			asm volatile("hlt");
-	}
-#endif
-	if (cpu_has_fxsr)
-		cr4_mask |= X86_CR4_OSFXSR;
-	if (cpu_has_xmm)
-		cr4_mask |= X86_CR4_OSXMMEXCPT;
-	if (cr4_mask)
-		cr4_set_bits(cr4_mask);
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
-	if (!cpu_has_fpu)
-		cr0 |= X86_CR0_EM;
-	write_cr0(cr0);
-
-	/*
-	 * init_thread_xstate is only called once to avoid overriding
-	 * xstate_size during boot time or during CPU hotplug.
-	 */
-	if (xstate_size == 0)
-		init_thread_xstate();
-
-	mxcsr_feature_mask_init();
-	xsave_init();
-	eager_fpu_init();
-}
-
-void fpu_finit(struct fpu *fpu)
-{
-	if (!cpu_has_fpu) {
-		finit_soft_fpu(&fpu->state->soft);
-		return;
-	}
-
-	memset(fpu->state, 0, xstate_size);
-
-	if (cpu_has_fxsr) {
-		fx_finit(&fpu->state->fxsave);
-	} else {
-		struct i387_fsave_struct *fp = &fpu->state->fsave;
-		fp->cwd = 0xffff037fu;
-		fp->swd = 0xffff0000u;
-		fp->twd = 0xffffffffu;
-		fp->fos = 0xffff0000u;
-	}
-}
-EXPORT_SYMBOL_GPL(fpu_finit);
-
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remember the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
-{
-	int ret;
-
-	if (tsk_used_math(tsk)) {
-		if (cpu_has_fpu && tsk == current)
-			unlazy_fpu(tsk);
-		task_disable_lazy_fpu_restore(tsk);
-		return 0;
-	}
-
-	/*
-	 * Memory allocation at the first usage of the FPU and other state.
-	 */
-	ret = fpu_alloc(&tsk->thread.fpu);
-	if (ret)
-		return ret;
-
-	fpu_finit(&tsk->thread.fpu);
-
-	set_stopped_child_used_math(tsk);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(init_fpu);
-
-/*
- * The xstateregs_active() routine is the same as the fpregs_active() routine,
- * as the "regset->n" for the xstate regset will be updated based on the feature
- * capabilites supported by the xsave.
- */
-int fpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return tsk_used_math(target) ? regset->n : 0;
-}
-
-int xfpregs_active(struct task_struct *target, const struct user_regset *regset)
-{
-	return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0;
-}
-
-int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fpu.state->fxsave, 0, -1);
-}
-
-int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_fxsr)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.fpu.state->fxsave, 0, -1);
-
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-
-	/*
-	 * update the header bits in the xsave header, indicating the
-	 * presence of FP and SSE state.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
-	return ret;
-}
-
-int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
-		unsigned int pos, unsigned int count,
-		void *kbuf, void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	/*
-	 * Copy the 48bytes defined by the software first into the xstate
-	 * memory layout in the thread struct, so that we can copy the entire
-	 * xstateregs to the user using one user_regset_copyout().
-	 */
-	memcpy(&xsave->i387.sw_reserved,
-		xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
-	/*
-	 * Copy the xstate memory layout.
-	 */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	return ret;
-}
-
-int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
-		  unsigned int pos, unsigned int count,
-		  const void *kbuf, const void __user *ubuf)
-{
-	struct xsave_struct *xsave;
-	int ret;
-
-	if (!cpu_has_xsave)
-		return -ENODEV;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	xsave = &target->thread.fpu.state->xsave;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-	/*
-	 * mxcsr reserved bits must be masked to zero for security reasons.
-	 */
-	xsave->i387.mxcsr &= mxcsr_feature_mask;
-	xsave->xsave_hdr.xstate_bv &= pcntxt_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	memset(&xsave->xsave_hdr.reserved, 0, 48);
-	return ret;
-}
-
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
-
-/*
- * FPU tag word conversions.
- */
-
-static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
-{
-	unsigned int tmp; /* to avoid 16 bit prefixes in the code */
-
-	/* Transform each pair of bits into 01 (valid) or 00 (empty) */
-	tmp = ~twd;
-	tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */
-	/* and move the valid bits to the lower byte. */
-	tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */
-	tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */
-	tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */
-
-	return tmp;
-}
-
-#define FPREG_ADDR(f, n)	((void *)&(f)->st_space + (n) * 16)
-#define FP_EXP_TAG_VALID	0
-#define FP_EXP_TAG_ZERO		1
-#define FP_EXP_TAG_SPECIAL	2
-#define FP_EXP_TAG_EMPTY	3
-
-static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
-{
-	struct _fpxreg *st;
-	u32 tos = (fxsave->swd >> 11) & 7;
-	u32 twd = (unsigned long) fxsave->twd;
-	u32 tag;
-	u32 ret = 0xffff0000u;
-	int i;
-
-	for (i = 0; i < 8; i++, twd >>= 1) {
-		if (twd & 0x1) {
-			st = FPREG_ADDR(fxsave, (i - tos) & 7);
-
-			switch (st->exponent & 0x7fff) {
-			case 0x7fff:
-				tag = FP_EXP_TAG_SPECIAL;
-				break;
-			case 0x0000:
-				if (!st->significand[0] &&
-				    !st->significand[1] &&
-				    !st->significand[2] &&
-				    !st->significand[3])
-					tag = FP_EXP_TAG_ZERO;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			default:
-				if (st->significand[3] & 0x8000)
-					tag = FP_EXP_TAG_VALID;
-				else
-					tag = FP_EXP_TAG_SPECIAL;
-				break;
-			}
-		} else {
-			tag = FP_EXP_TAG_EMPTY;
-		}
-		ret |= tag << (2 * i);
-	}
-	return ret;
-}
-
-/*
- * FXSR floating point environment conversions.
- */
-
-void
-convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
-	struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	env->cwd = fxsave->cwd | 0xffff0000u;
-	env->swd = fxsave->swd | 0xffff0000u;
-	env->twd = twd_fxsr_to_i387(fxsave);
-
-#ifdef CONFIG_X86_64
-	env->fip = fxsave->rip;
-	env->foo = fxsave->rdp;
-	/*
-	 * should be actually ds/cs at fpu exception time, but
-	 * that information is not available in 64bit mode.
-	 */
-	env->fcs = task_pt_regs(tsk)->cs;
-	if (tsk == current) {
-		savesegment(ds, env->fos);
-	} else {
-		env->fos = tsk->thread.ds;
-	}
-	env->fos |= 0xffff0000;
-#else
-	env->fip = fxsave->fip;
-	env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
-	env->foo = fxsave->foo;
-	env->fos = fxsave->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(to[0]));
-}
-
-void convert_to_fxsr(struct task_struct *tsk,
-		     const struct user_i387_ia32_struct *env)
-
-{
-	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
-	struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
-	struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
-	int i;
-
-	fxsave->cwd = env->cwd;
-	fxsave->swd = env->swd;
-	fxsave->twd = twd_i387_to_fxsr(env->twd);
-	fxsave->fop = (u16) ((u32) env->fcs >> 16);
-#ifdef CONFIG_X86_64
-	fxsave->rip = env->fip;
-	fxsave->rdp = env->foo;
-	/* cs and ds ignored */
-#else
-	fxsave->fip = env->fip;
-	fxsave->fcs = (env->fcs & 0xffff);
-	fxsave->foo = env->foo;
-	fxsave->fos = env->fos;
-#endif
-
-	for (i = 0; i < 8; ++i)
-		memcpy(&to[i], &from[i], sizeof(from[0]));
-}
-
-int fpregs_get(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       void *kbuf, void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &target->thread.fpu.state->fsave, 0,
-					   -1);
-
-	sanitize_i387_state(target);
-
-	if (kbuf && pos == 0 && count == sizeof(env)) {
-		convert_from_fxsr(kbuf, target);
-		return 0;
-	}
-
-	convert_from_fxsr(&env, target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-}
-
-int fpregs_set(struct task_struct *target, const struct user_regset *regset,
-	       unsigned int pos, unsigned int count,
-	       const void *kbuf, const void __user *ubuf)
-{
-	struct user_i387_ia32_struct env;
-	int ret;
-
-	ret = init_fpu(target);
-	if (ret)
-		return ret;
-
-	sanitize_i387_state(target);
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf);
-
-	if (!cpu_has_fxsr)
-		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu.state->fsave, 0,
-					  -1);
-
-	if (pos > 0 || count < sizeof(env))
-		convert_from_fxsr(&env, target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1);
-	if (!ret)
-		convert_to_fxsr(target, &env);
-
-	/*
-	 * update the header bit in the xsave header, indicating the
-	 * presence of FP.
-	 */
-	if (cpu_has_xsave)
-		target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
-	return ret;
-}
-
-/*
- * FPU state for core dumps.
- * This is only used for a.out dumps now.
- * It is declared generically using elf_fpregset_t (which is
- * struct user_i387_struct) but is in fact only used for 32-bit
- * dumps, so on 64-bit it is really struct user_i387_ia32_struct.
- */
-int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu)
-{
-	struct task_struct *tsk = current;
-	int fpvalid;
-
-	fpvalid = !!used_math();
-	if (fpvalid)
-		fpvalid = !fpregs_get(tsk, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      fpu, NULL);
-
-	return fpvalid;
-}
-EXPORT_SYMBOL(dump_fpu);
-
-#endif	/* CONFIG_X86_32 || CONFIG_IA32_EMULATION */
-
-static int __init no_387(char *s)
-{
-	setup_clear_cpu_cap(X86_FEATURE_FPU);
-	return 1;
-}
-
-__setup("no387", no_387);
-
-void fpu_detect(struct cpuinfo_x86 *c)
-{
-	unsigned long cr0;
-	u16 fsw, fcw;
-
-	fsw = fcw = 0xffff;
-
-	cr0 = read_cr0();
-	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
-	write_cr0(cr0);
-
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
-
-	if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-		set_cpu_cap(c, X86_FEATURE_FPU);
-	else
-		clear_cpu_cap(c, X86_FEATURE_FPU);
-
-	/* The final cr0 value is set in fpu_init() */
-}
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index e7cc5370cd2f..16cb827a5b27 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -329,8 +329,8 @@ static void init_8259A(int auto_eoi)
 	 */
 	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
 
-	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
-	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+	/* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */
+	outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR);
 
 	/* 8259A-1 (the master) has a slave on IR2 */
 	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
@@ -342,8 +342,8 @@ static void init_8259A(int auto_eoi)
 
 	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
 
-	/* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
-	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
+	/* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */
+	outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR);
 	/* 8259A-2 is a slave on master's IR2 */
 	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
 	/* (slave's support for AEOI in flat mode is to be investigated) */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e5952c225532..88b366487b0e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -22,6 +22,12 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
+DEFINE_PER_CPU(struct pt_regs *, irq_regs);
+EXPORT_PER_CPU_SYMBOL(irq_regs);
+
 atomic_t irq_err_count;
 
 /* Function pointer for generic interrupt vector handling */
@@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
 	seq_puts(p, "  Threshold APIC interrupts\n");
 #endif
+#ifdef CONFIG_X86_MCE_AMD
+	seq_printf(p, "%*s: ", prec, "DFR");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count);
+	seq_puts(p, "  Deferred Error APIC interrupts\n");
+#endif
 #ifdef CONFIG_X86_MCE
 	seq_printf(p, "%*s: ", prec, "MCE");
 	for_each_online_cpu(j)
@@ -136,6 +148,18 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 #if defined(CONFIG_X86_IO_APIC)
 	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
 #endif
+#ifdef CONFIG_HAVE_KVM
+	seq_printf(p, "%*s: ", prec, "PIN");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis);
+	seq_puts(p, "  Posted-interrupt notification event\n");
+
+	seq_printf(p, "%*s: ", prec, "PIW");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ",
+			   irq_stats(j)->kvm_posted_intr_wakeup_ipis);
+	seq_puts(p, "  Posted-interrupt wakeup event\n");
+#endif
 	return 0;
 }
 
@@ -192,8 +216,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	unsigned vector = ~regs->orig_ax;
 	unsigned irq;
 
-	irq_enter();
-	exit_idle();
+	entering_irq();
 
 	irq = __this_cpu_read(vector_irq[vector]);
 
@@ -209,7 +232,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 		}
 	}
 
-	irq_exit();
+	exiting_irq();
 
 	set_irq_regs(old_regs);
 	return 1;
@@ -237,6 +260,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_HAVE_KVM
+static void dummy_handler(void) {}
+static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler;
+
+void kvm_set_posted_intr_wakeup_handler(void (*handler)(void))
+{
+	if (handler)
+		kvm_posted_intr_wakeup_handler = handler;
+	else
+		kvm_posted_intr_wakeup_handler = dummy_handler;
+}
+EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler);
+
 /*
  * Handler for POSTED_INTERRUPT_VECTOR.
  */
@@ -244,16 +279,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ack_APIC_irq();
-
-	irq_enter();
-
-	exit_idle();
-
+	entering_ack_irq();
 	inc_irq_stat(kvm_posted_intr_ipis);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 
-	irq_exit();
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
 
+	entering_ack_irq();
+	inc_irq_stat(kvm_posted_intr_wakeup_ipis);
+	kvm_posted_intr_wakeup_handler();
+	exiting_irq();
 	set_irq_regs(old_regs);
 }
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index f9fd86a7fcc7..cd74f5978ab9 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -21,12 +21,6 @@
 
 #include <asm/apic.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 
 int sysctl_panic_on_stackoverflow __read_mostly;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 394e643d7830..bc4604e500a3 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -20,12 +20,6 @@
 #include <asm/idle.h>
 #include <asm/apic.h>
 
-DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
-EXPORT_PER_CPU_SYMBOL(irq_stat);
-
-DEFINE_PER_CPU(struct pt_regs *, irq_regs);
-EXPORT_PER_CPU_SYMBOL(irq_regs);
-
 int sysctl_panic_on_stackoverflow;
 
 /*
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 15d741ddfeeb..dc5fa6a1e8d6 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -10,12 +10,6 @@
 #include <asm/apic.h>
 #include <asm/trace/irq_vectors.h>
 
-static inline void irq_work_entering_irq(void)
-{
-	irq_enter();
-	ack_APIC_irq();
-}
-
 static inline void __smp_irq_work_interrupt(void)
 {
 	inc_irq_stat(apic_irq_work_irqs);
@@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void)
 
 __visible void smp_irq_work_interrupt(struct pt_regs *regs)
 {
-	irq_work_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_irq_work_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
 {
-	irq_work_entering_irq();
+	ipi_entering_ack_irq();
 	trace_irq_work_entry(IRQ_WORK_VECTOR);
 	__smp_irq_work_interrupt();
 	trace_irq_work_exit(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index cd10a6437264..a3a5e158ed69 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -86,7 +86,7 @@ void __init init_IRQ(void)
 	int i;
 
 	/*
-	 * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15.
+	 * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15.
 	 * If these IRQ's are handled by legacy interrupt-controllers like PIC,
 	 * then this configuration will likely be static after the boot. If
 	 * these IRQ's are handled by more mordern controllers like IO-APIC,
@@ -94,7 +94,7 @@ void __init init_IRQ(void)
 	 * irq's migrate etc.
 	 */
 	for (i = 0; i < nr_legacy_irqs(); i++)
-		per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i;
+		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i;
 
 	x86_init.irqs.intr_init();
 }
@@ -135,6 +135,10 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
 #endif
 
+#ifdef CONFIG_X86_MCE_AMD
+	alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt);
+#endif
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -144,6 +148,8 @@ static void __init apic_intr_init(void)
 #ifdef CONFIG_HAVE_KVM
 	/* IPI for KVM to deliver posted interrupt */
 	alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+	/* IPI for KVM to deliver interrupt to wake up tasks */
+	alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi);
 #endif
 
 	/* IPI vectors for APIC spurious and error interrupts */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9435620062df..47190bd399e7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
 	apic_write(APIC_EOI, APIC_EOI_ACK);
 }
 
-void kvm_guest_cpu_init(void)
+static void kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
 		return;
@@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu)
 	kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
 }
 
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void kvm_wait(u8 *ptr, u8 val)
+{
+	unsigned long flags;
+
+	if (in_nmi())
+		return;
+
+	local_irq_save(flags);
+
+	if (READ_ONCE(*ptr) != val)
+		goto out;
+
+	/*
+	 * halt until it's our turn and kicked. Note that we do safe halt
+	 * for irq enabled case to avoid hang when lock info is overwritten
+	 * in irq spinlock slowpath and no spurious interrupt occur to save us.
+	 */
+	if (arch_irqs_disabled_flags(flags))
+		halt();
+	else
+		safe_halt();
+
+out:
+	local_irq_restore(flags);
+}
+
+#else /* !CONFIG_QUEUED_SPINLOCKS */
+
 enum kvm_contention_stat {
 	TAKEN_SLOW,
 	TAKEN_SLOW_PICKUP,
@@ -655,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start)
 static struct dentry *d_spin_debug;
 static struct dentry *d_kvm_debug;
 
-struct dentry *kvm_init_debugfs(void)
+static struct dentry *kvm_init_debugfs(void)
 {
 	d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
 	if (!d_kvm_debug)
@@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
 	}
 }
 
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	__pv_init_lock_hash();
+	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_lock_ops.wait = kvm_wait;
+	pv_lock_ops.kick = kvm_kick_cpu;
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
 	pv_lock_ops.unlock_kick = kvm_unlock_kick;
+#endif
 }
 
 static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 42caaef897c8..49487b488061 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -24,6 +24,7 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/memblock.h>
+#include <linux/sched.h>
 
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
@@ -217,8 +218,10 @@ static void kvm_shutdown(void)
 
 void __init kvmclock_init(void)
 {
+	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned long mem;
-	int size;
+	int size, cpu;
+	u8 flags;
 
 	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
@@ -264,7 +267,14 @@ void __init kvmclock_init(void)
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
+		pvclock_set_flags(~0);
+
+	cpu = get_cpu();
+	vcpu_time = &hv_clock[cpu].pvti;
+	flags = pvclock_read_flags(vcpu_time);
+	if (flags & PVCLOCK_COUNTS_FROM_ZERO)
+		set_sched_clock_stable();
+	put_cpu();
 }
 
 int __init kvm_setup_vsyscall_timeinfo(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 415480d3ea84..819ab3f9c9c7 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -17,6 +17,7 @@
 #include <linux/ftrace.h>
 #include <linux/io.h>
 #include <linux/suspend.h>
+#include <linux/vmalloc.h>
 
 #include <asm/init.h>
 #include <asm/pgtable.h>
@@ -25,6 +26,7 @@
 #include <asm/io_apic.h>
 #include <asm/debugreg.h>
 #include <asm/kexec-bzimage64.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_KEXEC_FILE
 static struct kexec_file_ops *kexec_file_loaders[] = {
@@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
-			      (unsigned long)&_text - __START_KERNEL);
+			      kaslr_offset());
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 2d2a237f2c73..30ca7607cbbb 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -19,8 +19,8 @@
 #include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/pci.h>
-#include <linux/irqdomain.h>
 
+#include <asm/irqdomain.h>
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
 #include <asm/pgalloc.h>
@@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		pr_warn("Unknown bustype %s - ignoring\n", str);
 }
 
-static struct irq_domain_ops mp_ioapic_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-	.unmap = mp_irqdomain_unmap,
-};
-
 static void __init MP_ioapic_info(struct mpc_ioapic *m)
 {
 	struct ioapic_domain_cfg cfg = {
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index bbb6c7316341..33ee3e0efd65 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,11 +8,33 @@
 
 #include <asm/paravirt.h>
 
+#ifdef CONFIG_QUEUED_SPINLOCKS
+__visible void __native_queued_spin_unlock(struct qspinlock *lock)
+{
+	native_queued_spin_unlock(lock);
+}
+
+PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
+
+bool pv_is_native_spin_unlock(void)
+{
+	return pv_lock_ops.queued_spin_unlock.func ==
+		__raw_callee_save___native_queued_spin_unlock;
+}
+#endif
+
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+	.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+	.wait = paravirt_nop,
+	.kick = paravirt_nop,
+#else /* !CONFIG_QUEUED_SPINLOCKS */
 	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
 	.unlock_kick = paravirt_nop,
-#endif
+#endif /* !CONFIG_QUEUED_SPINLOCKS */
+#endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c614dd492f5f..58bcfb67c01f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -154,7 +154,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
 		ret = paravirt_patch_ident_64(insnbuf, len);
 
 	else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
+#ifdef CONFIG_X86_32
 		 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
+#endif
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
 		 type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
 		/* If operation requires a jmp, then jmp */
@@ -371,7 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 
 	.load_sp0 = native_load_sp0,
 
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_32)
 	.irq_enable_sysexit = native_irq_enable_sysexit,
 #endif
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index d9f32e6d6ab6..e1b013696dde 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	/* arg in %eax, return in %eax */
@@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 	return 0;
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_cpu_ops, read_tsc);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queued_spin_unlock;
+				end   = end_pv_lock_ops_queued_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index a1da6737ba5b..8aa05583bc42 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 DEF_NATIVE(, mov32, "mov %edi, %eax");
 DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+#endif
+
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
 {
 	return paravirt_patch_insns(insnbuf, len,
@@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 				    start__mov64, end__mov64);
 }
 
+extern bool pv_is_native_spin_unlock(void);
+
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
 {
@@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
 		PATCH_SITE(pv_cpu_ops, swapgs);
@@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
-
-	patch_site:
-		ret = paravirt_patch_insns(ibuf, len, start, end);
-		break;
+#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
+			if (pv_is_native_spin_unlock()) {
+				start = start_pv_lock_ops_queued_spin_unlock;
+				end   = end_pv_lock_ops_queued_spin_unlock;
+				goto patch_site;
+			}
+#endif
 
 	default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
+
+patch_site:
+		ret = paravirt_patch_insns(ibuf, len, start, end);
+		break;
 	}
 #undef PATCH_SITE
 	return ret;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a25e202bb319..353972c1946c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
 		free_pages((unsigned long)vaddr, get_order(size));
 }
 
+void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		      gfp_t gfp, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+		return memory;
+
+	if (!dev)
+		dev = &x86_dma_fallback_dev;
+
+	if (!is_device_dma_capable(dev))
+		return NULL;
+
+	if (!ops->alloc)
+		return NULL;
+
+	memory = ops->alloc(dev, size, dma_handle,
+			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+
+	return memory;
+}
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *vaddr, dma_addr_t bus,
+		    struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	WARN_ON(irqs_disabled());       /* for portability */
+
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
+
+	debug_dma_free_coherent(dev, size, vaddr, bus);
+	if (ops->free)
+		ops->free(dev, size, vaddr, bus, attrs);
+}
+EXPORT_SYMBOL(dma_free_attrs);
+
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 77dd0ad58be4..adf0392d549a 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 {
 	void *vaddr;
 
+	/*
+	 * Don't print a warning when the first allocation attempt fails.
+	 * swiotlb_alloc_coherent() will print a warning when the DMA
+	 * memory allocation ultimately failed.
+	 */
+	flags |= __GFP_NOWARN;
+
 	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
 					   attrs);
 	if (vaddr)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 8213da62b1b7..9cad694ed7c4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -25,8 +25,7 @@
 #include <asm/idle.h>
 #include <asm/uaccess.h>
 #include <asm/mwait.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/nmi.h>
 #include <asm/tlbflush.h>
@@ -57,7 +56,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
 };
-EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss);
 
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU(unsigned char, is_idle);
@@ -76,9 +75,6 @@ void idle_notifier_unregister(struct notifier_block *n)
 EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 #endif
 
-struct kmem_cache *task_xstate_cachep;
-EXPORT_SYMBOL_GPL(task_xstate_cachep);
-
 /*
  * this gets called so that we can store lazy state into memory and copy the
  * current task into the new thread.
@@ -87,36 +83,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
 
-	dst->thread.fpu_counter = 0;
-	dst->thread.fpu.has_fpu = 0;
-	dst->thread.fpu.state = NULL;
-	task_disable_lazy_fpu_restore(dst);
-	if (tsk_used_math(src)) {
-		int err = fpu_alloc(&dst->thread.fpu);
-		if (err)
-			return err;
-		fpu_copy(dst, src);
-	}
-	return 0;
-}
-
-void free_thread_xstate(struct task_struct *tsk)
-{
-	fpu_free(&tsk->thread.fpu);
-}
-
-void arch_release_task_struct(struct task_struct *tsk)
-{
-	free_thread_xstate(tsk);
-}
-
-void arch_task_cache_init(void)
-{
-        task_xstate_cachep =
-        	kmem_cache_create("task_xstate", xstate_size,
-				  __alignof__(union thread_xstate),
-				  SLAB_PANIC | SLAB_NOTRACK, NULL);
-	setup_xstate_comp();
+	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
 
 /*
@@ -127,6 +94,7 @@ void exit_thread(void)
 	struct task_struct *me = current;
 	struct thread_struct *t = &me->thread;
 	unsigned long *bp = t->io_bitmap_ptr;
+	struct fpu *fpu = &t->fpu;
 
 	if (bp) {
 		struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
@@ -142,7 +110,7 @@ void exit_thread(void)
 		kfree(bp);
 	}
 
-	drop_fpu(me);
+	fpu__drop(fpu);
 }
 
 void flush_thread(void)
@@ -152,17 +120,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-	if (!use_eager_fpu()) {
-		/* FPU state will be reallocated lazily at the first use. */
-		drop_fpu(tsk);
-		free_thread_xstate(tsk);
-	} else if (!used_math()) {
-		/* kthread execs. TODO: cleanup this horror. */
-		if (WARN_ON(init_fpu(tsk)))
-			force_sig(SIGKILL, tsk);
-		user_fpu_begin();
-		restore_init_xstate();
-	}
+	fpu__clear(&tsk->thread.fpu);
 }
 
 static void hard_disable_TSC(void)
@@ -443,11 +401,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 }
 
 /*
- * MONITOR/MWAIT with no hints, used for default default C1 state.
- * This invokes MWAIT with interrutps enabled and no flags,
- * which is backwards compatible with the original MWAIT implementation.
+ * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT
+ * with interrupts enabled and no flags, which is backwards compatible with the
+ * original MWAIT implementation.
  */
-
 static void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8ed2106b06da..c09c99ccf3e3 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -39,8 +39,7 @@
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/desc.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
@@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
-				 *next = &next_p->thread;
+			     *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -296,19 +297,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
 	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
+	 * done before fpu__restore(), so the TS bit is up
 	 * to date.
 	 */
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0, kernel_stack, and current_top_of_stack.  This changes
+	 * Reload esp0 and cpu_current_top_of_stack.  This changes
 	 * current_thread_info().
 	 */
 	load_sp0(tss, next);
-	this_cpu_write(kernel_stack,
-		       (unsigned long)task_stack_page(next_p) +
-		       THREAD_SIZE);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
@@ -319,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	this_cpu_write(current_task, next_p);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ddfdbf74f174..843f92e4c711 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -38,8 +38,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mmu_context.h>
 #include <asm/prctl.h>
 #include <asm/desc.h>
@@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
 	struct thread_struct *next = &next_p->thread;
+	struct fpu *prev_fpu = &prev->fpu;
+	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
 	unsigned fsindex, gsindex;
-	fpu_switch_t fpu;
+	fpu_switch_t fpu_switch;
 
-	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
+	fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Leave lazy mode, flushing any hypercalls made here.  This
 	 * must be done after loading TLS entries in the GDT but before
 	 * loading segments that might reference them, and and it must
-	 * be done before math_state_restore, so the TS bit is up to
+	 * be done before fpu__restore(), so the TS bit is up to
 	 * date.
 	 */
 	arch_end_context_switch(next_p);
@@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
-	switch_fpu_finish(next_p, fpu);
+	switch_fpu_finish(next_fpu, fpu_switch);
 
 	/*
 	 * Switch the PDA and FPU contexts.
@@ -409,9 +410,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/* Reload esp0 and ss1.  This changes current_thread_info(). */
 	load_sp0(tss, next);
 
-	this_cpu_write(kernel_stack,
-		(unsigned long)task_stack_page(next_p) + THREAD_SIZE);
-
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
 	 */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a7bc79480719..9be72bc3613f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/ptrace.h>
-#include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/user.h>
 #include <linux/elf.h>
@@ -28,8 +27,9 @@
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
+#include <asm/fpu/regset.h>
 #include <asm/debugreg.h>
 #include <asm/ldt.h>
 #include <asm/desc.h>
@@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_struct) / sizeof(long),
 		.size = sizeof(long), .align = sizeof(long),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,
@@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = {
 		.core_note_type = NT_PRFPREG,
 		.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = fpregs_active, .get = fpregs_get, .set = fpregs_set
+		.active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set
 	},
 	[REGSET_XFP] = {
 		.core_note_type = NT_PRXFPREG,
 		.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
 		.size = sizeof(u32), .align = sizeof(u32),
-		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
+		.active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set
 	},
 	[REGSET_XSTATE] = {
 		.core_note_type = NT_X86_XSTATE,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d74ac33290ae..d3b95b89e9b2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -531,12 +531,14 @@ static void __init reserve_crashkernel_low(void)
 	if (ret != 0) {
 		/*
 		 * two parts from lib/swiotlb.c:
-		 *	swiotlb size: user specified with swiotlb= or default.
-		 *	swiotlb overflow buffer: now is hardcoded to 32k.
-		 *		We round it to 8M for other buffers that
-		 *		may need to stay low too.
+		 * -swiotlb size: user-specified with swiotlb= or default.
+		 *
+		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+		 * to 8M for other buffers that may need to stay low too. Also
+		 * make sure we allocate enough extra low memory so that we
+		 * don't run out of DMA buffers for 32-bit devices.
 		 */
-		low_size = swiotlb_size_or_default() + (8UL<<20);
+		low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
 		auto_set = true;
 	} else {
 		/* passed with crashkernel=0,low ? */
@@ -834,7 +836,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
 	if (kaslr_enabled()) {
 		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
+			 kaslr_offset(),
 			 __START_KERNEL,
 			 __START_KERNEL_map,
 			 MODULES_VADDR-1);
@@ -1103,6 +1105,9 @@ void __init setup_arch(char **cmdline_p)
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	memblock_x86_fill();
 
+	if (efi_enabled(EFI_BOOT))
+		efi_find_mirror();
+
 	/*
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
@@ -1222,8 +1227,7 @@ void __init setup_arch(char **cmdline_p)
 	init_cpu_to_node();
 
 	init_apic_mappings();
-	if (x86_io_apic_ops.init)
-		x86_io_apic_ops.init();
+	io_apic_init_mappings();
 
 	kvm_guest_init();
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 1ea14fd53933..206996c1669d 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -26,8 +26,8 @@
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+#include <asm/fpu/signal.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
 #include <asm/sighandling.h>
@@ -103,7 +103,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		get_user_ex(buf, &sc->fpstate);
 	} get_user_catch(err);
 
-	err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+	err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32));
 
 	force_iret();
 
@@ -199,6 +199,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* redzone */
 	if (config_enabled(CONFIG_X86_64))
@@ -218,9 +219,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		}
 	}
 
-	if (used_math()) {
-		sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
-				     &buf_fx, &math_size);
+	if (fpu->fpstate_active) {
+		sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+					  &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
 	}
 
@@ -234,8 +235,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 
 	/* save i387 and extended state */
-	if (used_math() &&
-	    save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
+	if (fpu->fpstate_active &&
+	    copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -593,6 +594,22 @@ badframe:
 	return 0;
 }
 
+static inline int is_ia32_compat_frame(void)
+{
+	return config_enabled(CONFIG_IA32_EMULATION) &&
+	       test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
 static int
 setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 {
@@ -617,6 +634,7 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
 	bool stepping, failed;
+	struct fpu *fpu = &current->thread.fpu;
 
 	/* Are we from a system call? */
 	if (syscall_get_nr(current, regs) >= 0) {
@@ -665,8 +683,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		if (used_math())
-			fpu_reset_state(current);
+		if (fpu->fpstate_active)
+			fpu__clear(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index be8e1bde07aa..15aaa69bbb5e 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -170,8 +170,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 
 asmlinkage __visible void smp_reboot_interrupt(void)
 {
-	ack_APIC_irq();
-	irq_enter();
+	ipi_entering_ack_irq();
 	stop_this_cpu(NULL);
 	irq_exit();
 }
@@ -265,12 +264,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs)
 	 */
 }
 
-static inline void smp_entering_irq(void)
-{
-	ack_APIC_irq();
-	irq_enter();
-}
-
 __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
 {
 	/*
@@ -279,7 +272,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
 	 * scheduler_ipi(). This is OK, since those functions are allowed
 	 * to nest.
 	 */
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_reschedule_entry(RESCHEDULE_VECTOR);
 	__smp_reschedule_interrupt();
 	trace_reschedule_exit(RESCHEDULE_VECTOR);
@@ -297,14 +290,14 @@ static inline void __smp_call_function_interrupt(void)
 
 __visible void smp_call_function_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_call_function_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
 	__smp_call_function_interrupt();
 	trace_call_function_exit(CALL_FUNCTION_VECTOR);
@@ -319,14 +312,14 @@ static inline void __smp_call_function_single_interrupt(void)
 
 __visible void smp_call_function_single_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	__smp_call_function_single_interrupt();
 	exiting_irq();
 }
 
 __visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
 {
-	smp_entering_irq();
+	ipi_entering_ack_irq();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
 	__smp_call_function_single_interrupt();
 	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 50e547eac8cd..8add66b22f33 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,8 +68,7 @@
 #include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
 #include <linux/mc146818rtc.h>
@@ -314,10 +313,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
 		cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
 }
 
-#define link_mask(_m, c1, c2)						\
+#define link_mask(mfunc, c1, c2)					\
 do {									\
-	cpumask_set_cpu((c1), cpu_##_m##_mask(c2));			\
-	cpumask_set_cpu((c2), cpu_##_m##_mask(c1));			\
+	cpumask_set_cpu((c1), mfunc(c2));				\
+	cpumask_set_cpu((c2), mfunc(c1));				\
 } while (0)
 
 static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -398,9 +397,9 @@ void set_cpu_sibling_map(int cpu)
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
 	if (!has_mp) {
-		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
-		cpumask_set_cpu(cpu, cpu_core_mask(cpu));
+		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
 		c->booted_cores = 1;
 		return;
 	}
@@ -409,32 +408,34 @@ void set_cpu_sibling_map(int cpu)
 		o = &cpu_data(i);
 
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
-			link_mask(sibling, cpu, i);
+			link_mask(topology_sibling_cpumask, cpu, i);
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
-			link_mask(llc_shared, cpu, i);
+			link_mask(cpu_llc_shared_mask, cpu, i);
 
 	}
 
 	/*
 	 * This needs a separate iteration over the cpus because we rely on all
-	 * cpu_sibling_mask links to be set-up.
+	 * topology_sibling_cpumask links to be set-up.
 	 */
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
 		if ((i == cpu) || (has_mp && match_die(c, o))) {
-			link_mask(core, cpu, i);
+			link_mask(topology_core_cpumask, cpu, i);
 
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
+			if (cpumask_weight(
+			    topology_sibling_cpumask(cpu)) == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
 				 */
-				if (cpumask_first(cpu_sibling_mask(i)) == i)
+				if (cpumask_first(
+				    topology_sibling_cpumask(i)) == i)
 					c->booted_cores++;
 				/*
 				 * increment the core count for all
@@ -514,6 +515,40 @@ void __inquire_remote_apic(int apicid)
 }
 
 /*
+ * The Multiprocessor Specification 1.4 (1997) example code suggests
+ * that there should be a 10ms delay between the BSP asserting INIT
+ * and de-asserting INIT, when starting a remote processor.
+ * But that slows boot and resume on modern processors, which include
+ * many cores and don't require that delay.
+ *
+ * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
+ * Modern processor families are quirked to remove the delay entirely.
+ */
+#define UDELAY_10MS_DEFAULT 10000
+
+static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+
+static int __init cpu_init_udelay(char *str)
+{
+	get_option(&str, &init_udelay);
+
+	return 0;
+}
+early_param("cpu_init_udelay", cpu_init_udelay);
+
+static void __init smp_quirk_init_udelay(void)
+{
+	/* if cmdline changed it from default, leave it alone */
+	if (init_udelay != UDELAY_10MS_DEFAULT)
+		return;
+
+	/* if modern processor, use no delay */
+	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+		init_udelay = 0;
+}
+
+/*
  * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
@@ -555,7 +590,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
 static int
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
-	unsigned long send_status, accept_status = 0;
+	unsigned long send_status = 0, accept_status = 0;
 	int maxlvt, num_starts, j;
 
 	maxlvt = lapic_get_maxlvt();
@@ -583,7 +618,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 	pr_debug("Waiting for send to finish...\n");
 	send_status = safe_apic_wait_icr_idle();
 
-	mdelay(10);
+	udelay(init_udelay);
 
 	pr_debug("Deasserting INIT\n");
 
@@ -651,6 +686,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		 * Give the other CPU some time to accept the IPI.
 		 */
 		udelay(200);
+
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
 		accept_status = (apic_read(APIC_ESR) & 0xEF);
@@ -792,8 +828,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
 #endif
-	per_cpu(kernel_stack, cpu) =
-		(unsigned long)task_stack_page(idle) + THREAD_SIZE;
 }
 
 /*
@@ -1009,8 +1043,8 @@ static __init void disable_smp(void)
 		physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
 	else
 		physid_set_mask_of_physid(0, &phys_cpu_present_map);
-	cpumask_set_cpu(0, cpu_sibling_mask(0));
-	cpumask_set_cpu(0, cpu_core_mask(0));
+	cpumask_set_cpu(0, topology_sibling_cpumask(0));
+	cpumask_set_cpu(0, topology_core_cpumask(0));
 }
 
 enum {
@@ -1176,6 +1210,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		uv_system_init();
 
 	set_mtrr_aps_delayed_init();
+
+	smp_quirk_init_udelay();
 }
 
 void arch_enable_nonboot_cpus_begin(void)
@@ -1293,22 +1329,22 @@ static void remove_siblinginfo(int cpu)
 	int sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	for_each_cpu(sibling, cpu_core_mask(cpu)) {
-		cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
+	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
+		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
 		/*/
 		 * last thread sibling in this cpu core going down
 		 */
-		if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+		if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
 			cpu_data(sibling).booted_cores--;
 	}
 
-	for_each_cpu(sibling, cpu_sibling_mask(cpu))
-		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
 	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
 	cpumask_clear(cpu_llc_shared_mask(cpu));
-	cpumask_clear(cpu_sibling_mask(cpu));
-	cpumask_clear(cpu_core_mask(cpu));
+	cpumask_clear(topology_sibling_cpumask(cpu));
+	cpumask_clear(topology_core_cpumask(cpu));
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 324ab5247687..f5791927aa64 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -54,12 +54,13 @@
 #include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
+#include <asm/fpu/xstate.h>
+#include <asm/trace/mpx.h>
 #include <asm/mpx.h>
 
 #ifdef CONFIG_X86_64
@@ -72,8 +73,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss;
 #else
 #include <asm/processor-flags.h>
 #include <asm/setup.h>
-
-asmlinkage int system_call(void);
+#include <asm/proto.h>
 #endif
 
 /* Must be page-aligned because the real IDT is used in a fixmap. */
@@ -371,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	struct task_struct *tsk = current;
-	struct xsave_struct *xsave_buf;
 	enum ctx_state prev_state;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 	siginfo_t *info;
 
 	prev_state = exception_enter();
@@ -393,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 
 	/*
 	 * We need to look at BNDSTATUS to resolve this exception.
-	 * It is not directly accessible, though, so we need to
-	 * do an xsave and then pull it out of the xsave buffer.
+	 * A NULL here might mean that it is in its 'init state',
+	 * which is all zeros which indicates MPX was not
+	 * responsible for the exception.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	xsave_buf = &(tsk->thread.fpu.state->xsave);
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		goto exit_trap;
 
+	trace_bounds_exception_mpx(bndcsr);
 	/*
 	 * The error code field of the BNDSTATUS register communicates status
 	 * information of a bound range exception #BR or operation involving
@@ -409,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	 */
 	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
 	case 2:	/* Bound directory has invalid entry. */
-		if (mpx_handle_bd_fault(xsave_buf))
+		if (mpx_handle_bd_fault())
 			goto exit_trap;
 		break; /* Success, it was handled */
 	case 1: /* Bound violation. */
-		info = mpx_generate_siginfo(regs, xsave_buf);
+		info = mpx_generate_siginfo(regs);
 		if (IS_ERR(info)) {
 			/*
 			 * We failed to decode the MPX instruction.  Act as if
@@ -709,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug);
 static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
+	struct fpu *fpu = &task->thread.fpu;
 	siginfo_t info;
-	unsigned short err;
 	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
 
@@ -718,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 		return;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
-	{
+	if (!user_mode(regs)) {
 		if (!fixup_exception(regs)) {
 			task->thread.error_code = error_code;
 			task->thread.trap_nr = trapnr;
@@ -731,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	/*
 	 * Save the info for the exception handler and clear the error.
 	 */
-	unlazy_fpu(task);
-	task->thread.trap_nr = trapnr;
+	fpu__save(fpu);
+
+	task->thread.trap_nr	= trapnr;
 	task->thread.error_code = error_code;
-	info.si_signo = SIGFPE;
-	info.si_errno = 0;
-	info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
-	if (trapnr == X86_TRAP_MF) {
-		unsigned short cwd, swd;
-		/*
-		 * (~cwd & swd) will mask out exceptions that are not set to unmasked
-		 * status.  0x3f is the exception bits in these regs, 0x200 is the
-		 * C1 reg you need in case of a stack fault, 0x040 is the stack
-		 * fault bit.  We should only be taking one exception at a time,
-		 * so if this combination doesn't produce any single exception,
-		 * then we have a bad program that isn't synchronizing its FPU usage
-		 * and it will suffer the consequences since we won't be able to
-		 * fully reproduce the context of the exception
-		 */
-		cwd = get_fpu_cwd(task);
-		swd = get_fpu_swd(task);
+	info.si_signo		= SIGFPE;
+	info.si_errno		= 0;
+	info.si_addr		= (void __user *)uprobe_get_trap_addr(regs);
 
-		err = swd & ~cwd;
-	} else {
-		/*
-		 * The SIMD FPU exceptions are handled a little differently, as there
-		 * is only a single status/control register.  Thus, to determine which
-		 * unmasked exception was caught we must mask the exception mask bits
-		 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
-		 */
-		unsigned short mxcsr = get_fpu_mxcsr(task);
-		err = ~(mxcsr >> 7) & mxcsr;
-	}
+	info.si_code = fpu__exception_code(fpu, trapnr);
 
-	if (err & 0x001) {	/* Invalid op */
-		/*
-		 * swd & 0x240 == 0x040: Stack Underflow
-		 * swd & 0x240 == 0x240: Stack Overflow
-		 * User must clear the SF bit (0x40) if set
-		 */
-		info.si_code = FPE_FLTINV;
-	} else if (err & 0x004) { /* Divide by Zero */
-		info.si_code = FPE_FLTDIV;
-	} else if (err & 0x008) { /* Overflow */
-		info.si_code = FPE_FLTOVF;
-	} else if (err & 0x012) { /* Denormal, Underflow */
-		info.si_code = FPE_FLTUND;
-	} else if (err & 0x020) { /* Precision */
-		info.si_code = FPE_FLTRES;
-	} else {
-		/*
-		 * If we're using IRQ 13, or supposedly even some trap
-		 * X86_TRAP_MF implementations, it's possible
-		 * we get a spurious trap, which is not an error.
-		 */
+	/* Retry when we get spurious exceptions: */
+	if (!info.si_code)
 		return;
-	}
+
 	force_sig_info(SIGFPE, &info, task);
 }
 
@@ -813,62 +768,8 @@ dotraplinkage void
 do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 {
 	conditional_sti(regs);
-#if 0
-	/* No need to warn about this any longer. */
-	pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
-#endif
-}
-
-asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
-{
 }
 
-asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
-{
-}
-
-/*
- * 'math_state_restore()' saves the current math information in the
- * old math state array, and gets the new ones from the current task
- *
- * Careful.. There are problems with IBM-designed IRQ13 behaviour.
- * Don't touch unless you *really* know how it works.
- *
- * Must be called with kernel preemption disabled (eg with local
- * local interrupts as in the case of do_device_not_available).
- */
-void math_state_restore(void)
-{
-	struct task_struct *tsk = current;
-
-	if (!tsk_used_math(tsk)) {
-		local_irq_enable();
-		/*
-		 * does a slab alloc which can sleep
-		 */
-		if (init_fpu(tsk)) {
-			/*
-			 * ran out of memory!
-			 */
-			do_group_exit(SIGKILL);
-			return;
-		}
-		local_irq_disable();
-	}
-
-	/* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */
-	kernel_fpu_disable();
-	__thread_fpu_begin(tsk);
-	if (unlikely(restore_fpu_checking(tsk))) {
-		fpu_reset_state(tsk);
-		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
-	} else {
-		tsk->thread.fpu_counter++;
-	}
-	kernel_fpu_enable();
-}
-EXPORT_SYMBOL_GPL(math_state_restore);
-
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
@@ -889,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 		return;
 	}
 #endif
-	math_state_restore(); /* interrupts still off */
+	fpu__restore(&current->thread.fpu); /* interrupts still off */
 #ifdef CONFIG_X86_32
 	conditional_sti(regs);
 #endif
@@ -992,13 +893,13 @@ void __init trap_init(void)
 		set_bit(i, used_vectors);
 
 #ifdef CONFIG_IA32_EMULATION
-	set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
+	set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
 	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
 #ifdef CONFIG_X86_32
-	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
-	set_bit(SYSCALL_VECTOR, used_vectors);
+	set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
+	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
 	/*
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 26488487bc61..dd8d0791dfb5 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout)
  */
 static inline unsigned int loop_timeout(int cpu)
 {
-	return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20;
+	return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
 }
 
 /*
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 0b81ad67da07..66476244731e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -29,6 +29,7 @@
 #include <linux/kdebug.h>
 #include <asm/processor.h>
 #include <asm/insn.h>
+#include <asm/mmu_context.h>
 
 /* Post-execution fixups. */
 
@@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 }
 
 #ifdef CONFIG_X86_64
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return	!config_enabled(CONFIG_IA32_EMULATION) ||
-		!(mm->context.ia32_compat == TIF_IA32);
-}
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
@@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	}
 }
 #else /* 32-bit: */
-static inline bool is_64bit_mm(struct mm_struct *mm)
-{
-	return false;
-}
 /*
  * No RIP-relative addressing on 32-bit
  */
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 37d8fa4438f0..a0695be19864 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index);
 
 #ifdef CONFIG_PREEMPT
 EXPORT_SYMBOL(___preempt_schedule);
-#ifdef CONFIG_CONTEXT_TRACKING
-EXPORT_SYMBOL(___preempt_schedule_context);
-#endif
+EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 234b0722de53..3839628d962e 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -11,7 +11,6 @@
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
 #include <asm/pci_x86.h>
-#include <asm/pci.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
@@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform);
 #if defined(CONFIG_PCI_MSI)
 struct x86_msi_ops x86_msi = {
 	.setup_msi_irqs		= native_setup_msi_irqs,
-	.compose_msi_msg	= native_compose_msi_msg,
 	.teardown_msi_irq	= native_teardown_msi_irq,
 	.teardown_msi_irqs	= default_teardown_msi_irqs,
 	.restore_msi_irqs	= default_restore_msi_irqs,
-	.setup_hpet_msi		= default_setup_hpet_msi,
 };
 
 /* MSI arch specific hooks */
@@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
 #endif
 
 struct x86_io_apic_ops x86_io_apic_ops = {
-	.init			= native_io_apic_init_mappings,
 	.read			= native_io_apic_read,
-	.write			= native_io_apic_write,
-	.modify			= native_io_apic_modify,
 	.disable		= native_disable_io_apic,
-	.print_entries		= native_io_apic_print_entries,
-	.set_affinity		= native_ioapic_set_affinity,
-	.setup_entry		= native_setup_ioapic_entry,
-	.eoi_ioapic_pin		= native_eoi_ioapic_pin,
 };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
deleted file mode 100644
index 87a815b85f3e..000000000000
--- a/arch/x86/kernel/xsave.c
+++ /dev/null
@@ -1,724 +0,0 @@
-/*
- * xsave/xrstor support.
- *
- * Author: Suresh Siddha <suresh.b.siddha@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/bootmem.h>
-#include <linux/compat.h>
-#include <linux/cpu.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h>
-#include <asm/sigframe.h>
-#include <asm/tlbflush.h>
-#include <asm/xcr.h>
-
-/*
- * Supported feature mask by the CPU and the kernel.
- */
-u64 pcntxt_mask;
-
-/*
- * Represents init state for the supported extended state.
- */
-struct xsave_struct *init_xstate_buf;
-
-static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
-static unsigned int *xstate_offsets, *xstate_sizes;
-static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
-static unsigned int xstate_features;
-
-/*
- * If a processor implementation discern that a processor state component is
- * in its initialized state it may modify the corresponding bit in the
- * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
- * layout in the case of xsaveopt. While presenting the xstate information to
- * the user, we always ensure that the memory layout of a feature will be in
- * the init state if the corresponding header bit is zero. This is to ensure
- * that the user doesn't see some stale state in the memory layout during
- * signal handling, debugging etc.
- */
-void __sanitize_i387_state(struct task_struct *tsk)
-{
-	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
-	int feature_bit = 0x2;
-	u64 xstate_bv;
-
-	if (!fx)
-		return;
-
-	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
-
-	/*
-	 * None of the feature bits are in init state. So nothing else
-	 * to do for us, as the memory layout is up to date.
-	 */
-	if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
-		return;
-
-	/*
-	 * FP is in init state
-	 */
-	if (!(xstate_bv & XSTATE_FP)) {
-		fx->cwd = 0x37f;
-		fx->swd = 0;
-		fx->twd = 0;
-		fx->fop = 0;
-		fx->rip = 0;
-		fx->rdp = 0;
-		memset(&fx->st_space[0], 0, 128);
-	}
-
-	/*
-	 * SSE is in init state
-	 */
-	if (!(xstate_bv & XSTATE_SSE))
-		memset(&fx->xmm_space[0], 0, 256);
-
-	xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;
-
-	/*
-	 * Update all the other memory layouts for which the corresponding
-	 * header bit is in the init state.
-	 */
-	while (xstate_bv) {
-		if (xstate_bv & 0x1) {
-			int offset = xstate_offsets[feature_bit];
-			int size = xstate_sizes[feature_bit];
-
-			memcpy(((void *) fx) + offset,
-			       ((void *) init_xstate_buf) + offset,
-			       size);
-		}
-
-		xstate_bv >>= 1;
-		feature_bit++;
-	}
-}
-
-/*
- * Check for the presence of extended state information in the
- * user fpstate pointer in the sigcontext.
- */
-static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
-				   void __user *fpstate,
-				   struct _fpx_sw_bytes *fx_sw)
-{
-	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
-			      sizeof(struct xsave_hdr_struct);
-	unsigned int magic2;
-
-	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
-		return -1;
-
-	/* Check for the first magic field and other error scenarios. */
-	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
-	    fx_sw->xstate_size < min_xstate_size ||
-	    fx_sw->xstate_size > xstate_size ||
-	    fx_sw->xstate_size > fx_sw->extended_size)
-		return -1;
-
-	/*
-	 * Check for the presence of second magic word at the end of memory
-	 * layout. This detects the case where the user just copied the legacy
-	 * fpstate layout with out copying the extended state information
-	 * in the memory layout.
-	 */
-	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
-	    || magic2 != FP_XSTATE_MAGIC2)
-		return -1;
-
-	return 0;
-}
-
-/*
- * Signal frame handlers.
- */
-static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
-{
-	if (use_fxsr()) {
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
-		struct user_i387_ia32_struct env;
-		struct _fpstate_ia32 __user *fp = buf;
-
-		convert_from_fxsr(&env, tsk);
-
-		if (__copy_to_user(buf, &env, sizeof(env)) ||
-		    __put_user(xsave->i387.swd, &fp->status) ||
-		    __put_user(X86_FXSR_MAGIC, &fp->magic))
-			return -1;
-	} else {
-		struct i387_fsave_struct __user *fp = buf;
-		u32 swd;
-		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
-			return -1;
-	}
-
-	return 0;
-}
-
-static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
-{
-	struct xsave_struct __user *x = buf;
-	struct _fpx_sw_bytes *sw_bytes;
-	u32 xstate_bv;
-	int err;
-
-	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
-	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
-	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
-
-	if (!use_xsave())
-		return err;
-
-	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
-
-	/*
-	 * Read the xstate_bv which we copied (directly from the cpu or
-	 * from the state in task struct) to the user buffers.
-	 */
-	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
-	/*
-	 * For legacy compatible, we always set FP/SSE bits in the bit
-	 * vector while saving the state to the user context. This will
-	 * enable us capturing any changes(during sigreturn) to
-	 * the FP/SSE bits by the legacy applications which don't touch
-	 * xstate_bv in the xsave header.
-	 *
-	 * xsave aware apps can change the xstate_bv in the xsave
-	 * header as well as change any contents in the memory layout.
-	 * xrestore as part of sigreturn will capture all the changes.
-	 */
-	xstate_bv |= XSTATE_FPSSE;
-
-	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
-
-	return err;
-}
-
-static inline int save_user_xstate(struct xsave_struct __user *buf)
-{
-	int err;
-
-	if (use_xsave())
-		err = xsave_user(buf);
-	else if (use_fxsr())
-		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
-	else
-		err = fsave_user((struct i387_fsave_struct __user *) buf);
-
-	if (unlikely(err) && __clear_user(buf, xstate_size))
-		err = -EFAULT;
-	return err;
-}
-
-/*
- * Save the fpu, extended register state to the user signal frame.
- *
- * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
- *  state is copied.
- *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
- *
- *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
- *	buf != buf_fx for 32-bit frames with fxstate.
- *
- * If the fpu, extended register state is live, save the state directly
- * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
- * copy the thread's fpu state to the user frame starting at 'buf_fx'.
- *
- * If this is a 32-bit frame with fxstate, put a fsave header before
- * the aligned state at 'buf_fx'.
- *
- * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
- * indicating the absence/presence of the extended state to the user.
- */
-int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
-	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
-	struct task_struct *tsk = current;
-	int ia32_fxstate = (buf != buf_fx);
-
-	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
-			 config_enabled(CONFIG_IA32_EMULATION));
-
-	if (!access_ok(VERIFY_WRITE, buf, size))
-		return -EACCES;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_get(current, NULL, 0,
-			sizeof(struct user_i387_ia32_struct), NULL,
-			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
-
-	if (user_has_fpu()) {
-		/* Save the live register state to the user directly. */
-		if (save_user_xstate(buf_fx))
-			return -1;
-		/* Update the thread's fxstate to save the fsave header. */
-		if (ia32_fxstate)
-			fpu_fxsave(&tsk->thread.fpu);
-	} else {
-		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf_fx, xsave, xstate_size))
-			return -1;
-	}
-
-	/* Save the fsave header for the 32-bit frames. */
-	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
-		return -1;
-
-	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
-		return -1;
-
-	return 0;
-}
-
-static inline void
-sanitize_restored_xstate(struct task_struct *tsk,
-			 struct user_i387_ia32_struct *ia32_env,
-			 u64 xstate_bv, int fx_only)
-{
-	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
-	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
-
-	if (use_xsave()) {
-		/* These bits must be zero. */
-		memset(xsave_hdr->reserved, 0, 48);
-
-		/*
-		 * Init the state that is not present in the memory
-		 * layout and not enabled by the OS.
-		 */
-		if (fx_only)
-			xsave_hdr->xstate_bv = XSTATE_FPSSE;
-		else
-			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
-	}
-
-	if (use_fxsr()) {
-		/*
-		 * mscsr reserved bits must be masked to zero for security
-		 * reasons.
-		 */
-		xsave->i387.mxcsr &= mxcsr_feature_mask;
-
-		convert_to_fxsr(tsk, ia32_env);
-	}
-}
-
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE state.
- */
-static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
-{
-	if (use_xsave()) {
-		if ((unsigned long)buf % 64 || fx_only) {
-			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
-			xrstor_state(init_xstate_buf, init_bv);
-			return fxrstor_user(buf);
-		} else {
-			u64 init_bv = pcntxt_mask & ~xbv;
-			if (unlikely(init_bv))
-				xrstor_state(init_xstate_buf, init_bv);
-			return xrestore_user(buf, xbv);
-		}
-	} else if (use_fxsr()) {
-		return fxrstor_user(buf);
-	} else
-		return frstor_user(buf);
-}
-
-int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
-{
-	int ia32_fxstate = (buf != buf_fx);
-	struct task_struct *tsk = current;
-	int state_size = xstate_size;
-	u64 xstate_bv = 0;
-	int fx_only = 0;
-
-	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
-			 config_enabled(CONFIG_IA32_EMULATION));
-
-	if (!buf) {
-		fpu_reset_state(tsk);
-		return 0;
-	}
-
-	if (!access_ok(VERIFY_READ, buf, size))
-		return -EACCES;
-
-	if (!used_math() && init_fpu(tsk))
-		return -1;
-
-	if (!static_cpu_has(X86_FEATURE_FPU))
-		return fpregs_soft_set(current, NULL,
-				       0, sizeof(struct user_i387_ia32_struct),
-				       NULL, buf) != 0;
-
-	if (use_xsave()) {
-		struct _fpx_sw_bytes fx_sw_user;
-		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
-			/*
-			 * Couldn't find the extended state information in the
-			 * memory layout. Restore just the FP/SSE and init all
-			 * the other extended state.
-			 */
-			state_size = sizeof(struct i387_fxsave_struct);
-			fx_only = 1;
-		} else {
-			state_size = fx_sw_user.xstate_size;
-			xstate_bv = fx_sw_user.xstate_bv;
-		}
-	}
-
-	if (ia32_fxstate) {
-		/*
-		 * For 32-bit frames with fxstate, copy the user state to the
-		 * thread's fpu state, reconstruct fxstate from the fsave
-		 * header. Sanitize the copied state etc.
-		 */
-		struct fpu *fpu = &tsk->thread.fpu;
-		struct user_i387_ia32_struct env;
-		int err = 0;
-
-		/*
-		 * Drop the current fpu which clears used_math(). This ensures
-		 * that any context-switch during the copy of the new state,
-		 * avoids the intermediate state from getting restored/saved.
-		 * Thus avoiding the new restored state from getting corrupted.
-		 * We will be ready to restore/save the state only after
-		 * set_used_math() is again set.
-		 */
-		drop_fpu(tsk);
-
-		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
-		    __copy_from_user(&env, buf, sizeof(env))) {
-			fpu_finit(fpu);
-			err = -1;
-		} else {
-			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-		}
-
-		set_used_math();
-		if (use_eager_fpu()) {
-			preempt_disable();
-			math_state_restore();
-			preempt_enable();
-		}
-
-		return err;
-	} else {
-		/*
-		 * For 64-bit frames and 32-bit fsave frames, restore the user
-		 * state to the registers directly (with exceptions handled).
-		 */
-		user_fpu_begin();
-		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
-			fpu_reset_state(tsk);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * Prepare the SW reserved portion of the fxsave memory layout, indicating
- * the presence of the extended state information in the memory layout
- * pointed by the fpstate pointer in the sigcontext.
- * This will be saved when ever the FP and extended state context is
- * saved on the user stack during the signal handler delivery to the user.
- */
-static void prepare_fx_sw_frame(void)
-{
-	int fsave_header_size = sizeof(struct i387_fsave_struct);
-	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
-
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
-	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = size;
-	fx_sw_reserved.xstate_bv = pcntxt_mask;
-	fx_sw_reserved.xstate_size = xstate_size;
-
-	if (config_enabled(CONFIG_IA32_EMULATION)) {
-		fx_sw_reserved_ia32 = fx_sw_reserved;
-		fx_sw_reserved_ia32.extended_size += fsave_header_size;
-	}
-}
-
-/*
- * Enable the extended processor state save/restore feature
- */
-static inline void xstate_enable(void)
-{
-	cr4_set_bits(X86_CR4_OSXSAVE);
-	xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-}
-
-/*
- * Record the offsets and sizes of different state managed by the xsave
- * memory layout.
- */
-static void __init setup_xstate_features(void)
-{
-	int eax, ebx, ecx, edx, leaf = 0x2;
-
-	xstate_features = fls64(pcntxt_mask);
-	xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
-	xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));
-
-	do {
-		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);
-
-		if (eax == 0)
-			break;
-
-		xstate_offsets[leaf] = ebx;
-		xstate_sizes[leaf] = eax;
-
-		leaf++;
-	} while (1);
-}
-
-/*
- * This function sets up offsets and sizes of all extended states in
- * xsave area. This supports both standard format and compacted format
- * of the xsave aread.
- *
- * Input: void
- * Output: void
- */
-void setup_xstate_comp(void)
-{
-	unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
-	int i;
-
-	/*
-	 * The FP xstates and SSE xstates are legacy states. They are always
-	 * in the fixed offsets in the xsave area in either compacted form
-	 * or standard form.
-	 */
-	xstate_comp_offsets[0] = 0;
-	xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);
-
-	if (!cpu_has_xsaves) {
-		for (i = 2; i < xstate_features; i++) {
-			if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-				xstate_comp_offsets[i] = xstate_offsets[i];
-				xstate_comp_sizes[i] = xstate_sizes[i];
-			}
-		}
-		return;
-	}
-
-	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-
-	for (i = 2; i < xstate_features; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask))
-			xstate_comp_sizes[i] = xstate_sizes[i];
-		else
-			xstate_comp_sizes[i] = 0;
-
-		if (i > 2)
-			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
-					+ xstate_comp_sizes[i-1];
-
-	}
-}
-
-/*
- * setup the xstate image representing the init state
- */
-static void __init setup_init_fpu_buf(void)
-{
-	/*
-	 * Setup init_xstate_buf to represent the init state of
-	 * all the features managed by the xsave
-	 */
-	init_xstate_buf = alloc_bootmem_align(xstate_size,
-					      __alignof__(struct xsave_struct));
-	fx_finit(&init_xstate_buf->i387);
-
-	if (!cpu_has_xsave)
-		return;
-
-	setup_xstate_features();
-
-	if (cpu_has_xsaves) {
-		init_xstate_buf->xsave_hdr.xcomp_bv =
-						(u64)1 << 63 | pcntxt_mask;
-		init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
-	}
-
-	/*
-	 * Init all the features state with header_bv being 0x0
-	 */
-	xrstor_state_booting(init_xstate_buf, -1);
-	/*
-	 * Dump the init state again. This is to identify the init state
-	 * of any feature which is not represented by all zero's.
-	 */
-	xsave_state_booting(init_xstate_buf, -1);
-}
-
-static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
-static int __init eager_fpu_setup(char *s)
-{
-	if (!strcmp(s, "on"))
-		eagerfpu = ENABLE;
-	else if (!strcmp(s, "off"))
-		eagerfpu = DISABLE;
-	else if (!strcmp(s, "auto"))
-		eagerfpu = AUTO;
-	return 1;
-}
-__setup("eagerfpu=", eager_fpu_setup);
-
-
-/*
- * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
- */
-static void __init init_xstate_size(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	int i;
-
-	if (!cpu_has_xsaves) {
-		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-		xstate_size = ebx;
-		return;
-	}
-
-	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
-	for (i = 2; i < 64; i++) {
-		if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
-			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
-			xstate_size += eax;
-		}
-	}
-}
-
-/*
- * Enable and initialize the xsave feature.
- */
-static void __init xstate_enable_boot_cpu(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
-		WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
-		return;
-	}
-
-	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
-	pcntxt_mask = eax + ((u64)edx << 32);
-
-	if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
-		pr_err("FP/SSE not shown under xsave features 0x%llx\n",
-		       pcntxt_mask);
-		BUG();
-	}
-
-	/*
-	 * Support only the state known to OS.
-	 */
-	pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
-
-	xstate_enable();
-
-	/*
-	 * Recompute the context size for enabled features
-	 */
-	init_xstate_size();
-
-	update_regset_xstate_info(xstate_size, pcntxt_mask);
-	prepare_fx_sw_frame();
-	setup_init_fpu_buf();
-
-	/* Auto enable eagerfpu for xsaveopt */
-	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
-		eagerfpu = ENABLE;
-
-	if (pcntxt_mask & XSTATE_EAGER) {
-		if (eagerfpu == DISABLE) {
-			pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
-					pcntxt_mask & XSTATE_EAGER);
-			pcntxt_mask &= ~XSTATE_EAGER;
-		} else {
-			eagerfpu = ENABLE;
-		}
-	}
-
-	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
-		pcntxt_mask, xstate_size,
-		cpu_has_xsaves ? "compacted form" : "standard form");
-}
-
-/*
- * For the very first instance, this calls xstate_enable_boot_cpu();
- * for all subsequent instances, this calls xstate_enable().
- *
- * This is somewhat obfuscated due to the lack of powerful enough
- * overrides for the section checks.
- */
-void xsave_init(void)
-{
-	static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
-	void (*this_func)(void);
-
-	if (!cpu_has_xsave)
-		return;
-
-	this_func = next_func;
-	next_func = xstate_enable;
-	this_func();
-}
-
-/*
- * setup_init_fpu_buf() is __init and it is OK to call it here because
- * init_xstate_buf will be unset only once during boot.
- */
-void __init_refok eager_fpu_init(void)
-{
-	WARN_ON(used_math());
-	current_thread_info()->status = 0;
-
-	if (eagerfpu == ENABLE)
-		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
-
-	if (!cpu_has_eager_fpu) {
-		stts();
-		return;
-	}
-
-	if (!init_xstate_buf)
-		setup_init_fpu_buf();
-}
-
-/*
- * Given the xsave area and a state inside, this function returns the
- * address of the state.
- *
- * This is the API that is called to get xstate address in either
- * standard format or compacted format of xsave area.
- *
- * Inputs:
- *	xsave: base address of the xsave area;
- *	xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
- *	etc.)
- * Output:
- *	address of the state in the xsave area.
- */
-void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
-{
-	int feature = fls64(xstate) - 1;
-	if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
-		return NULL;
-
-	return (void *)xsave + xstate_comp_offsets[feature];
-}
-EXPORT_SYMBOL_GPL(get_xsave_addr);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 413a7bf9efbb..d8a1d56276e1 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -86,15 +86,16 @@ config KVM_MMU_AUDIT
 	 auditing of KVM MMU events at runtime.
 
 config KVM_DEVICE_ASSIGNMENT
-	bool "KVM legacy PCI device assignment support"
+	bool "KVM legacy PCI device assignment support (DEPRECATED)"
 	depends on KVM && PCI && IOMMU_API
-	default y
+	default n
 	---help---
 	  Provide support for legacy PCI device assignment through KVM.  The
 	  kernel now also supports a full featured userspace device driver
-	  framework through VFIO, which supersedes much of this support.
+	  framework through VFIO, which supersedes this support and provides
+	  better security.
 
-	  If unsure, say Y.
+	  If unsure, say N.
 
 # OK, it's a little counter-intuitive to do this, but it puts it neatly under
 # the virtualization menu.
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 16e8f962eaad..67d215cb8953 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,10 +12,10 @@ kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
+			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= assigned-dev.o iommu.o
-kvm-intel-y		+= vmx.o
-kvm-amd-y		+= svm.o
+kvm-intel-y		+= vmx.o pmu_intel.o
+kvm-amd-y		+= svm.o pmu_amd.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
 obj-$(CONFIG_KVM_INTEL)	+= kvm-intel.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 59b69f6a2844..64dd46793099 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -16,12 +16,14 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
+#include <asm/fpu/internal.h> /* For use_eager_fpu.  Ugh! */
 #include <asm/user.h>
-#include <asm/xsave.h>
+#include <asm/fpu/xstate.h>
 #include "cpuid.h"
 #include "lapic.h"
 #include "mmu.h"
 #include "trace.h"
+#include "pmu.h"
 
 static u32 xstate_required_size(u64 xstate_bv, bool compacted)
 {
@@ -95,6 +97,8 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
+	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
 	 * address checks; exit if it is ever changed.
@@ -107,7 +111,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 
-	kvm_pmu_cpuid_update(vcpu);
+	kvm_pmu_refresh(vcpu);
 	return 0;
 }
 
@@ -411,6 +415,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		}
 		break;
 	}
+	case 6: /* Thermal management */
+		entry->eax = 0x4; /* allow ARAT */
+		entry->ebx = 0;
+		entry->ecx = 0;
+		entry->edx = 0;
+		break;
 	case 7: {
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		/* Mask ebx against host capability word 9 */
@@ -587,7 +597,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	case 3: /* Processor serial number */
 	case 5: /* MONITOR/MWAIT */
-	case 6: /* Thermal management */
 	case 0xC0000002:
 	case 0xC0000003:
 	case 0xC0000004:
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index c3b1ad9fca81..dd05b9cef6ae 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
 }
 
+static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_LM));
+}
+
 static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -117,4 +125,12 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 7, 0);
 	return best && (best->ebx & bit(X86_FEATURE_RTM));
 }
+
+static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_MPX));
+}
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 630bcb0d7a04..e7a4fde5d631 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
+#include <asm/debugreg.h>
 
 #include "x86.h"
 #include "tss.h"
@@ -523,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc)
 static inline void
 register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
 {
-	ulong mask;
+	ulong *preg = reg_rmw(ctxt, reg);
 
-	if (ctxt->ad_bytes == sizeof(unsigned long))
-		mask = ~0UL;
-	else
-		mask = ad_mask(ctxt);
-	masked_increment(reg_rmw(ctxt, reg), mask, inc);
+	assign_register(preg, *preg + inc, ctxt->ad_bytes);
 }
 
 static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -2262,6 +2259,260 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 	return rc;
 }
 
+static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax, ebx, ecx, edx;
+
+	eax = 0x80000001;
+	ecx = 0;
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	return edx & bit(X86_FEATURE_LM);
+}
+
+#define GET_SMSTATE(type, smbase, offset)				  \
+	({								  \
+	 type __val;							  \
+	 int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val,       \
+				     sizeof(__val), NULL);		  \
+	 if (r != X86EMUL_CONTINUE)					  \
+		 return X86EMUL_UNHANDLEABLE;				  \
+	 __val;								  \
+	})
+
+static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
+{
+	desc->g    = (flags >> 23) & 1;
+	desc->d    = (flags >> 22) & 1;
+	desc->l    = (flags >> 21) & 1;
+	desc->avl  = (flags >> 20) & 1;
+	desc->p    = (flags >> 15) & 1;
+	desc->dpl  = (flags >> 13) & 3;
+	desc->s    = (flags >> 12) & 1;
+	desc->type = (flags >>  8) & 15;
+}
+
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+
+	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+
+	if (n < 3)
+		offset = 0x7f84 + n * 12;
+	else
+		offset = 0x7f2c + (n - 3) * 12;
+
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+	u32 base3;
+
+	offset = 0x7e00 + n * 16;
+
+	selector =                GET_SMSTATE(u16, smbase, offset);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
+				     u64 cr0, u64 cr4)
+{
+	int bad;
+
+	/*
+	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+	 * Then enable protected mode.	However, PCID cannot be enabled
+	 * if EFER.LMA=0, so set it separately.
+	 */
+	bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	bad = ctxt->ops->set_cr(ctxt, 0, cr0);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	if (cr4 & X86_CR4_PCIDE) {
+		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
+		if (bad)
+			return X86EMUL_UNHANDLEABLE;
+	}
+
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u16 selector;
+	u32 val, cr0, cr4;
+	int i;
+
+	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
+	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+
+	for (i = 0; i < 8; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+
+	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	ctxt->ops->set_gdt(ctxt, &dt);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	for (i = 0; i < 6; i++) {
+		int r = rsm_load_seg_32(ctxt, smbase, i);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
+	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+
+	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u64 val, cr0, cr4;
+	u32 base3;
+	u16 selector;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+
+	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
+	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+
+	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
+	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
+	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
+	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+
+	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
+	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+
+	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e64);
+	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
+	ctxt->ops->set_gdt(ctxt, &dt);
+
+	for (i = 0; i < 6; i++) {
+		int r = rsm_load_seg_64(ctxt, smbase, i);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
+	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int em_rsm(struct x86_emulate_ctxt *ctxt)
+{
+	unsigned long cr0, cr4, efer;
+	u64 smbase;
+	int ret;
+
+	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
+		return emulate_ud(ctxt);
+
+	/*
+	 * Get back to real mode, to prepare a safe state in which to load
+	 * CR0/CR3/CR4/EFER.  Also this will ensure that addresses passed
+	 * to read_std/write_std are not virtual.
+	 *
+	 * CR4.PCIDE must be zero, because it is a 64-bit mode only feature.
+	 */
+	cr0 = ctxt->ops->get_cr(ctxt, 0);
+	if (cr0 & X86_CR0_PE)
+		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
+	cr4 = ctxt->ops->get_cr(ctxt, 4);
+	if (cr4 & X86_CR4_PAE)
+		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+	efer = 0;
+	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+
+	smbase = ctxt->ops->get_smbase(ctxt);
+	if (emulator_has_longmode(ctxt))
+		ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+	else
+		ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+
+	if (ret != X86EMUL_CONTINUE) {
+		/* FIXME: should triple fault */
+		return X86EMUL_UNHANDLEABLE;
+	}
+
+	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+		ctxt->ops->set_nmi_mask(ctxt, false);
+
+	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
+	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	return X86EMUL_CONTINUE;
+}
+
 static void
 setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
 			struct desc_struct *cs, struct desc_struct *ss)
@@ -2573,6 +2824,30 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt,
 	return true;
 }
 
+static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
+{
+	/*
+	 * Intel CPUs mask the counter and pointers in quite strange
+	 * manner when ECX is zero due to REP-string optimizations.
+	 */
+#ifdef CONFIG_X86_64
+	if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt))
+		return;
+
+	*reg_write(ctxt, VCPU_REGS_RCX) = 0;
+
+	switch (ctxt->b) {
+	case 0xa4:	/* movsb */
+	case 0xa5:	/* movsd/w */
+		*reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1;
+		/* fall through */
+	case 0xaa:	/* stosb */
+	case 0xab:	/* stosd/w */
+		*reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1;
+	}
+#endif
+}
+
 static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
 				struct tss_segment_16 *tss)
 {
@@ -2849,7 +3124,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	ulong old_tss_base =
 		ops->get_cached_segment_base(ctxt, VCPU_SREG_TR);
 	u32 desc_limit;
-	ulong desc_addr;
+	ulong desc_addr, dr7;
 
 	/* FIXME: old_tss_base == ~0 ? */
 
@@ -2934,6 +3209,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 		ret = em_push(ctxt);
 	}
 
+	ops->get_dr(ctxt, 7, &dr7);
+	ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN));
+
 	return ret;
 }
 
@@ -3840,7 +4118,7 @@ static const struct opcode group5[] = {
 	F(DstMem | SrcNone | Lock,		em_inc),
 	F(DstMem | SrcNone | Lock,		em_dec),
 	I(SrcMem | NearBranch,			em_call_near_abs),
-	I(SrcMemFAddr | ImplicitOps | Stack,	em_call_far),
+	I(SrcMemFAddr | ImplicitOps,		em_call_far),
 	I(SrcMem | NearBranch,			em_jmp_abs),
 	I(SrcMemFAddr | ImplicitOps,		em_jmp_far),
 	I(SrcMem | Stack,			em_push), D(Undefined),
@@ -4173,7 +4451,7 @@ static const struct opcode twobyte_table[256] = {
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N,
 	/* 0xA8 - 0xAF */
 	I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg),
-	DI(ImplicitOps, rsm),
+	II(No64 | EmulateOnUD | ImplicitOps, em_rsm, rsm),
 	F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
 	F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
 	F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
@@ -4871,7 +5149,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
 		}
 
-		if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -4900,7 +5178,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 		}
 
-		if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+		if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -4910,6 +5188,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		if (ctxt->rep_prefix && (ctxt->d & String)) {
 			/* All REP prefixes have the same first termination condition */
 			if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
+				string_registers_quirk(ctxt);
 				ctxt->eip = ctxt->_eip;
 				ctxt->eflags &= ~X86_EFLAGS_RF;
 				goto done;
@@ -4953,7 +5232,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 special_insn:
 
-	if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+	if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 28146f03c514..856f79105bb5 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -349,6 +349,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	irqe.delivery_mode = entry->fields.delivery_mode << 8;
 	irqe.level = 1;
 	irqe.shorthand = 0;
+	irqe.msi_redir_hint = false;
 
 	if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
 		ioapic->irr_delivered |= 1 << irq;
@@ -637,11 +638,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
 	cancel_delayed_work_sync(&ioapic->eoi_inject);
-	if (ioapic) {
-		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
-		kvm->arch.vioapic = NULL;
-		kfree(ioapic);
-	}
+	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
+	kvm->arch.vioapic = NULL;
+	kfree(ioapic);
 }
 
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 72298b3ac025..9efff9e5b58c 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -31,6 +31,8 @@
 
 #include "ioapic.h"
 
+#include "lapic.h"
+
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level,
 			   bool line_status)
@@ -48,11 +50,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 				line_status);
 }
 
-inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
-{
-	return irq->delivery_mode == APIC_DM_LOWEST;
-}
-
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, unsigned long *dest_map)
 {
@@ -60,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
-			kvm_is_dm_lowest_prio(irq)) {
+			kvm_lowest_prio_delivery(irq)) {
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
 		irq->delivery_mode = APIC_DM_FIXED;
 	}
@@ -76,7 +73,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 					irq->dest_id, irq->dest_mode))
 			continue;
 
-		if (!kvm_is_dm_lowest_prio(irq)) {
+		if (!kvm_lowest_prio_delivery(irq)) {
 			if (r < 0)
 				r = 0;
 			r += kvm_apic_set_irq(vcpu, irq, dest_map);
@@ -106,9 +103,10 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
 	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
 	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
 	irq->delivery_mode = e->msi.data & 0x700;
+	irq->msi_redir_hint = ((e->msi.address_lo
+		& MSI_ADDR_REDIRECTION_LOWPRI) > 0);
 	irq->level = 1;
 	irq->shorthand = 0;
-	/* TODO Deal with RH bit of MSI message address */
 }
 
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 544076c4f44b..e1e89ee4af75 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -99,4 +99,9 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu)
 	return vcpu->arch.hflags & HF_GUEST_MASK;
 }
 
+static inline bool is_smm(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.hflags & HF_SMM_MASK;
+}
+
 #endif
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 629af0f1c5c4..36e9de1b4127 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -240,6 +240,15 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
+static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id)
+{
+	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+
+	apic_set_reg(apic, APIC_ID, id << 24);
+	apic_set_reg(apic, APIC_LDR, ldr);
+	recalculate_apic_map(apic->vcpu->kvm);
+}
+
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
 {
 	return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
@@ -728,7 +737,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 
 		dst = map->logical_map[cid];
 
-		if (irq->delivery_mode == APIC_DM_LOWEST) {
+		if (kvm_lowest_prio_delivery(irq)) {
 			int l = -1;
 			for_each_set_bit(i, &bitmap, 16) {
 				if (!dst[i])
@@ -799,7 +808,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 		break;
 
 	case APIC_DM_SMI:
-		apic_debug("Ignoring guest SMI\n");
+		result = 1;
+		kvm_make_request(KVM_REQ_SMI, vcpu);
+		kvm_vcpu_kick(vcpu);
 		break;
 
 	case APIC_DM_NMI:
@@ -914,9 +925,10 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 	irq.vector = icr_low & APIC_VECTOR_MASK;
 	irq.delivery_mode = icr_low & APIC_MODE_MASK;
 	irq.dest_mode = icr_low & APIC_DEST_MASK;
-	irq.level = icr_low & APIC_INT_ASSERT;
+	irq.level = (icr_low & APIC_INT_ASSERT) != 0;
 	irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
 	irq.shorthand = icr_low & APIC_SHORT_MASK;
+	irq.msi_redir_hint = false;
 	if (apic_x2apic_mode(apic))
 		irq.dest_id = icr_high;
 	else
@@ -926,10 +938,11 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 
 	apic_debug("icr_high 0x%x, icr_low 0x%x, "
 		   "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
-		   "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
+		   "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, "
+		   "msi_redir_hint 0x%x\n",
 		   icr_high, icr_low, irq.shorthand, irq.dest_id,
 		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
-		   irq.vector);
+		   irq.vector, irq.msi_redir_hint);
 
 	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL);
 }
@@ -1090,6 +1103,17 @@ static void update_divide_count(struct kvm_lapic *apic)
 				   apic->divide_count);
 }
 
+static void apic_update_lvtt(struct kvm_lapic *apic)
+{
+	u32 timer_mode = kvm_apic_get_reg(apic, APIC_LVTT) &
+			apic->lapic_timer.timer_mode_mask;
+
+	if (apic->lapic_timer.timer_mode != timer_mode) {
+		apic->lapic_timer.timer_mode = timer_mode;
+		hrtimer_cancel(&apic->lapic_timer.timer);
+	}
+}
+
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1298,6 +1322,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
 			}
+			apic_update_lvtt(apic);
 			atomic_set(&apic->lapic_timer.pending, 0);
 
 		}
@@ -1330,20 +1355,13 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 		break;
 
-	case APIC_LVTT: {
-		u32 timer_mode = val & apic->lapic_timer.timer_mode_mask;
-
-		if (apic->lapic_timer.timer_mode != timer_mode) {
-			apic->lapic_timer.timer_mode = timer_mode;
-			hrtimer_cancel(&apic->lapic_timer.timer);
-		}
-
+	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 		val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
 		apic_set_reg(apic, APIC_LVTT, val);
+		apic_update_lvtt(apic);
 		break;
-	}
 
 	case APIC_TMICT:
 		if (apic_lvtt_tscdeadline(apic))
@@ -1536,9 +1554,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 	if ((old_value ^ value) & X2APIC_ENABLE) {
 		if (value & X2APIC_ENABLE) {
-			u32 id = kvm_apic_id(apic);
-			u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
-			kvm_apic_set_ldr(apic, ldr);
+			kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
 			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
 		} else
 			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
@@ -1557,7 +1573,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 }
 
-void kvm_lapic_reset(struct kvm_vcpu *vcpu)
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct kvm_lapic *apic;
 	int i;
@@ -1571,19 +1587,22 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	kvm_apic_set_id(apic, vcpu->vcpu_id);
+	if (!init_event)
+		kvm_apic_set_id(apic, vcpu->vcpu_id);
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < APIC_LVT_NUM; i++)
 		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
-	apic->lapic_timer.timer_mode = 0;
-	apic_set_reg(apic, APIC_LVT0,
-		     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
+	apic_update_lvtt(apic);
+	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+		apic_set_reg(apic, APIC_LVT0,
+			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 
 	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
 	apic_set_spiv(apic, 0xff);
 	apic_set_reg(apic, APIC_TASKPRI, 0);
-	kvm_apic_set_ldr(apic, 0);
+	if (!apic_x2apic_mode(apic))
+		kvm_apic_set_ldr(apic, 0);
 	apic_set_reg(apic, APIC_ESR, 0);
 	apic_set_reg(apic, APIC_ICR, 0);
 	apic_set_reg(apic, APIC_ICR2, 0);
@@ -1712,7 +1731,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 			APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
 
 	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
-	kvm_lapic_reset(vcpu);
+	kvm_lapic_reset(vcpu, false);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
 	return 0;
@@ -1802,6 +1821,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 
 	apic_update_ppr(apic);
 	hrtimer_cancel(&apic->lapic_timer.timer);
+	apic_update_lvtt(apic);
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
@@ -2043,11 +2063,22 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
 		return;
 
-	pe = xchg(&apic->pending_events, 0);
+	/*
+	 * INITs are latched while in SMM.  Because an SMM CPU cannot
+	 * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs
+	 * and delay processing of INIT until the next RSM.
+	 */
+	if (is_smm(vcpu)) {
+		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
+		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
+			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+		return;
+	}
 
+	pe = xchg(&apic->pending_events, 0);
 	if (test_bit(KVM_APIC_INIT, &pe)) {
-		kvm_lapic_reset(vcpu);
-		kvm_vcpu_reset(vcpu);
+		kvm_lapic_reset(vcpu, true);
+		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
 			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		else
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 9d28383fc1e7..f2f4e10ab772 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -48,7 +48,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu);
 int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu);
 void kvm_apic_accept_events(struct kvm_vcpu *vcpu);
-void kvm_lapic_reset(struct kvm_vcpu *vcpu);
+void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
@@ -150,7 +150,18 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
 
 static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.apic->pending_events;
+	return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events;
+}
+
+static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq)
+{
+	return (irq->delivery_mode == APIC_DM_LOWEST ||
+			irq->msi_redir_hint);
+}
+
+static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
 }
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d43867c33bc4..f807496b62c2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -223,15 +223,15 @@ static unsigned int get_mmio_spte_generation(u64 spte)
 	return gen;
 }
 
-static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
+static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu)
 {
-	return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
+	return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK;
 }
 
-static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
+static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn,
 			   unsigned access)
 {
-	unsigned int gen = kvm_current_mmio_generation(kvm);
+	unsigned int gen = kvm_current_mmio_generation(vcpu);
 	u64 mask = generation_mmio_spte_mask(gen);
 
 	access &= ACC_WRITE_MASK | ACC_USER_MASK;
@@ -258,22 +258,22 @@ static unsigned get_mmio_spte_access(u64 spte)
 	return (spte & ~mask) & ~PAGE_MASK;
 }
 
-static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 			  pfn_t pfn, unsigned access)
 {
 	if (unlikely(is_noslot_pfn(pfn))) {
-		mark_mmio_spte(kvm, sptep, gfn, access);
+		mark_mmio_spte(vcpu, sptep, gfn, access);
 		return true;
 	}
 
 	return false;
 }
 
-static bool check_mmio_spte(struct kvm *kvm, u64 spte)
+static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 {
 	unsigned int kvm_gen, spte_gen;
 
-	kvm_gen = kvm_current_mmio_generation(kvm);
+	kvm_gen = kvm_current_mmio_generation(vcpu);
 	spte_gen = get_mmio_spte_generation(spte);
 
 	trace_check_mmio_spte(spte, kvm_gen, spte_gen);
@@ -804,30 +804,36 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 	return &slot->arch.lpage_info[level - 2][idx];
 }
 
-static void account_shadowed(struct kvm *kvm, gfn_t gfn)
+static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
+	gfn_t gfn;
 	int i;
 
-	slot = gfn_to_memslot(kvm, gfn);
-	for (i = PT_DIRECTORY_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+	gfn = sp->gfn;
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
+	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->write_count += 1;
 	}
 	kvm->arch.indirect_shadow_pages++;
 }
 
-static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
+static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
+	gfn_t gfn;
 	int i;
 
-	slot = gfn_to_memslot(kvm, gfn);
-	for (i = PT_DIRECTORY_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+	gfn = sp->gfn;
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
+	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->write_count -= 1;
 		WARN_ON(linfo->write_count < 0);
@@ -835,14 +841,14 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
 	kvm->arch.indirect_shadow_pages--;
 }
 
-static int has_wrprotected_page(struct kvm *kvm,
+static int has_wrprotected_page(struct kvm_vcpu *vcpu,
 				gfn_t gfn,
 				int level)
 {
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
 
-	slot = gfn_to_memslot(kvm, gfn);
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (slot) {
 		linfo = lpage_info_slot(gfn, slot, level);
 		return linfo->write_count;
@@ -858,8 +864,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
 
 	page_size = kvm_host_page_size(kvm, gfn);
 
-	for (i = PT_PAGE_TABLE_LEVEL;
-	     i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) {
+	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))
 			ret = i;
 		else
@@ -875,7 +880,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot;
 
-	slot = gfn_to_memslot(vcpu->kvm, gfn);
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID ||
 	      (no_dirty_log && slot->dirty_bitmap))
 		slot = NULL;
@@ -900,7 +905,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
-		if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
+		if (has_wrprotected_page(vcpu, large_gfn, level))
 			break;
 
 	return level - 1;
@@ -1042,12 +1047,14 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
 /*
  * Take gfn and return the reverse mapping to it.
  */
-static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level)
+static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 
-	slot = gfn_to_memslot(kvm, gfn);
-	return __gfn_to_rmap(gfn, level, slot);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
+	return __gfn_to_rmap(gfn, sp->role.level, slot);
 }
 
 static bool rmap_can_add(struct kvm_vcpu *vcpu)
@@ -1065,7 +1072,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	sp = page_header(__pa(spte));
 	kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn);
-	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
+	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
 	return pte_list_add(vcpu, spte, rmapp);
 }
 
@@ -1077,7 +1084,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
 
 	sp = page_header(__pa(spte));
 	gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
-	rmapp = gfn_to_rmap(kvm, gfn, sp->role.level);
+	rmapp = gfn_to_rmap(kvm, gfn, sp);
 	pte_list_remove(spte, rmapp);
 }
 
@@ -1142,6 +1149,11 @@ static u64 *rmap_get_next(struct rmap_iterator *iter)
 	return NULL;
 }
 
+#define for_each_rmap_spte(_rmap_, _iter_, _spte_)			    \
+	   for (_spte_ = rmap_get_first(*_rmap_, _iter_);		    \
+		_spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;});  \
+			_spte_ = rmap_get_next(_iter_))
+
 static void drop_spte(struct kvm *kvm, u64 *sptep)
 {
 	if (mmu_spte_clear_track_bits(sptep))
@@ -1205,12 +1217,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
-		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		flush |= spte_write_protect(kvm, sptep, pt_protect);
-		sptep = rmap_get_next(&iter);
-	}
 
 	return flush;
 }
@@ -1232,12 +1240,8 @@ static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
-		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		flush |= spte_clear_dirty(kvm, sptep);
-		sptep = rmap_get_next(&iter);
-	}
 
 	return flush;
 }
@@ -1259,12 +1263,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp)
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
-		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		flush |= spte_set_dirty(kvm, sptep);
-		sptep = rmap_get_next(&iter);
-	}
 
 	return flush;
 }
@@ -1342,42 +1342,45 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 		kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
+static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
 {
 	struct kvm_memory_slot *slot;
 	unsigned long *rmapp;
 	int i;
 	bool write_protected = false;
 
-	slot = gfn_to_memslot(kvm, gfn);
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	for (i = PT_PAGE_TABLE_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		rmapp = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(kvm, rmapp, true);
+		write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true);
 	}
 
 	return write_protected;
 }
 
-static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
-			   unsigned long data)
+static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
-	int need_tlb_flush = 0;
+	bool flush = false;
 
 	while ((sptep = rmap_get_first(*rmapp, &iter))) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
-			     sptep, *sptep, gfn, level);
+		rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
 
 		drop_spte(kvm, sptep);
-		need_tlb_flush = 1;
+		flush = true;
 	}
 
-	return need_tlb_flush;
+	return flush;
+}
+
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			   struct kvm_memory_slot *slot, gfn_t gfn, int level,
+			   unsigned long data)
+{
+	return kvm_zap_rmapp(kvm, rmapp);
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
@@ -1394,8 +1397,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	WARN_ON(pte_huge(*ptep));
 	new_pfn = pte_pfn(*ptep);
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
-		BUG_ON(!is_shadow_present_pte(*sptep));
+restart:
+	for_each_rmap_spte(rmapp, &iter, sptep) {
 		rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
 			     sptep, *sptep, gfn, level);
 
@@ -1403,7 +1406,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 		if (pte_write(*ptep)) {
 			drop_spte(kvm, sptep);
-			sptep = rmap_get_first(*rmapp, &iter);
+			goto restart;
 		} else {
 			new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
 			new_spte |= (u64)new_pfn << PAGE_SHIFT;
@@ -1414,7 +1417,6 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 			mmu_spte_clear_track_bits(sptep);
 			mmu_spte_set(sptep, new_spte);
-			sptep = rmap_get_next(&iter);
 		}
 	}
 
@@ -1424,6 +1426,74 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return 0;
 }
 
+struct slot_rmap_walk_iterator {
+	/* input fields. */
+	struct kvm_memory_slot *slot;
+	gfn_t start_gfn;
+	gfn_t end_gfn;
+	int start_level;
+	int end_level;
+
+	/* output fields. */
+	gfn_t gfn;
+	unsigned long *rmap;
+	int level;
+
+	/* private field. */
+	unsigned long *end_rmap;
+};
+
+static void
+rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level)
+{
+	iterator->level = level;
+	iterator->gfn = iterator->start_gfn;
+	iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot);
+	iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level,
+					   iterator->slot);
+}
+
+static void
+slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator,
+		    struct kvm_memory_slot *slot, int start_level,
+		    int end_level, gfn_t start_gfn, gfn_t end_gfn)
+{
+	iterator->slot = slot;
+	iterator->start_level = start_level;
+	iterator->end_level = end_level;
+	iterator->start_gfn = start_gfn;
+	iterator->end_gfn = end_gfn;
+
+	rmap_walk_init_level(iterator, iterator->start_level);
+}
+
+static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator)
+{
+	return !!iterator->rmap;
+}
+
+static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator)
+{
+	if (++iterator->rmap <= iterator->end_rmap) {
+		iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level));
+		return;
+	}
+
+	if (++iterator->level > iterator->end_level) {
+		iterator->rmap = NULL;
+		return;
+	}
+
+	rmap_walk_init_level(iterator, iterator->level);
+}
+
+#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_,	\
+	   _start_gfn, _end_gfn, _iter_)				\
+	for (slot_rmap_walk_init(_iter_, _slot_, _start_level_,		\
+				 _end_level_, _start_gfn, _end_gfn);	\
+	     slot_rmap_walk_okay(_iter_);				\
+	     slot_rmap_walk_next(_iter_))
+
 static int kvm_handle_hva_range(struct kvm *kvm,
 				unsigned long start,
 				unsigned long end,
@@ -1435,48 +1505,36 @@ static int kvm_handle_hva_range(struct kvm *kvm,
 					       int level,
 					       unsigned long data))
 {
-	int j;
-	int ret = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
+	struct slot_rmap_walk_iterator iterator;
+	int ret = 0;
+	int i;
 
-	slots = kvm_memslots(kvm);
-
-	kvm_for_each_memslot(memslot, slots) {
-		unsigned long hva_start, hva_end;
-		gfn_t gfn_start, gfn_end;
-
-		hva_start = max(start, memslot->userspace_addr);
-		hva_end = min(end, memslot->userspace_addr +
-					(memslot->npages << PAGE_SHIFT));
-		if (hva_start >= hva_end)
-			continue;
-		/*
-		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
-		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
-		 */
-		gfn_start = hva_to_gfn_memslot(hva_start, memslot);
-		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
-
-		for (j = PT_PAGE_TABLE_LEVEL;
-		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
-			unsigned long idx, idx_end;
-			unsigned long *rmapp;
-			gfn_t gfn = gfn_start;
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
+		kvm_for_each_memslot(memslot, slots) {
+			unsigned long hva_start, hva_end;
+			gfn_t gfn_start, gfn_end;
 
+			hva_start = max(start, memslot->userspace_addr);
+			hva_end = min(end, memslot->userspace_addr +
+				      (memslot->npages << PAGE_SHIFT));
+			if (hva_start >= hva_end)
+				continue;
 			/*
-			 * {idx(page_j) | page_j intersects with
-			 *  [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+			 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+			 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
 			 */
-			idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
-			idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
-
-			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
-
-			for (; idx <= idx_end;
-			       ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
-				ret |= handler(kvm, rmapp++, memslot,
-					       gfn, j, data);
+			gfn_start = hva_to_gfn_memslot(hva_start, memslot);
+			gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
+
+			for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL,
+						 PT_MAX_HUGEPAGE_LEVEL,
+						 gfn_start, gfn_end - 1,
+						 &iterator)
+				ret |= handler(kvm, iterator.rmap, memslot,
+					       iterator.gfn, iterator.level, data);
 		}
 	}
 
@@ -1518,16 +1576,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 
 	BUG_ON(!shadow_accessed_mask);
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
-	     sptep = rmap_get_next(&iter)) {
-		BUG_ON(!is_shadow_present_pte(*sptep));
-
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		if (*sptep & shadow_accessed_mask) {
 			young = 1;
 			clear_bit((ffs(shadow_accessed_mask) - 1),
 				 (unsigned long *)sptep);
 		}
-	}
+
 	trace_kvm_age_page(gfn, level, slot, young);
 	return young;
 }
@@ -1548,15 +1603,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	if (!shadow_accessed_mask)
 		goto out;
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
-	     sptep = rmap_get_next(&iter)) {
-		BUG_ON(!is_shadow_present_pte(*sptep));
-
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		if (*sptep & shadow_accessed_mask) {
 			young = 1;
 			break;
 		}
-	}
 out:
 	return young;
 }
@@ -1570,7 +1621,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	sp = page_header(__pa(spte));
 
-	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
+	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp);
 
 	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
@@ -1990,7 +2041,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu,
 		bool protected = false;
 
 		for_each_sp(pages, sp, parents, i)
-			protected |= rmap_write_protect(vcpu->kvm, sp->gfn);
+			protected |= rmap_write_protect(vcpu, sp->gfn);
 
 		if (protected)
 			kvm_flush_remote_tlbs(vcpu->kvm);
@@ -2088,12 +2139,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	hlist_add_head(&sp->hash_link,
 		&vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]);
 	if (!direct) {
-		if (rmap_write_protect(vcpu->kvm, gfn))
+		if (rmap_write_protect(vcpu, gfn))
 			kvm_flush_remote_tlbs(vcpu->kvm);
 		if (level > PT_PAGE_TABLE_LEVEL && need_sync)
 			kvm_sync_pages(vcpu, gfn);
 
-		account_shadowed(vcpu->kvm, gfn);
+		account_shadowed(vcpu->kvm, sp);
 	}
 	sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
 	init_shadow_page_table(sp);
@@ -2274,7 +2325,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 	kvm_mmu_unlink_parents(kvm, sp);
 
 	if (!sp->role.invalid && !sp->role.direct)
-		unaccount_shadowed(kvm, sp->gfn);
+		unaccount_shadowed(kvm, sp);
 
 	if (sp->unsync)
 		kvm_unlink_unsync_page(kvm, sp);
@@ -2386,111 +2437,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-/*
- * The function is based on mtrr_type_lookup() in
- * arch/x86/kernel/cpu/mtrr/generic.c
- */
-static int get_mtrr_type(struct mtrr_state_type *mtrr_state,
-			 u64 start, u64 end)
-{
-	int i;
-	u64 base, mask;
-	u8 prev_match, curr_match;
-	int num_var_ranges = KVM_NR_VAR_MTRR;
-
-	if (!mtrr_state->enabled)
-		return 0xFF;
-
-	/* Make end inclusive end, instead of exclusive */
-	end--;
-
-	/* Look in fixed ranges. Just return the type as per start */
-	if (mtrr_state->have_fixed && (start < 0x100000)) {
-		int idx;
-
-		if (start < 0x80000) {
-			idx = 0;
-			idx += (start >> 16);
-			return mtrr_state->fixed_ranges[idx];
-		} else if (start < 0xC0000) {
-			idx = 1 * 8;
-			idx += ((start - 0x80000) >> 14);
-			return mtrr_state->fixed_ranges[idx];
-		} else if (start < 0x1000000) {
-			idx = 3 * 8;
-			idx += ((start - 0xC0000) >> 12);
-			return mtrr_state->fixed_ranges[idx];
-		}
-	}
-
-	/*
-	 * Look in variable ranges
-	 * Look of multiple ranges matching this address and pick type
-	 * as per MTRR precedence
-	 */
-	if (!(mtrr_state->enabled & 2))
-		return mtrr_state->def_type;
-
-	prev_match = 0xFF;
-	for (i = 0; i < num_var_ranges; ++i) {
-		unsigned short start_state, end_state;
-
-		if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11)))
-			continue;
-
-		base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) +
-		       (mtrr_state->var_ranges[i].base_lo & PAGE_MASK);
-		mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) +
-		       (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK);
-
-		start_state = ((start & mask) == (base & mask));
-		end_state = ((end & mask) == (base & mask));
-		if (start_state != end_state)
-			return 0xFE;
-
-		if ((start & mask) != (base & mask))
-			continue;
-
-		curr_match = mtrr_state->var_ranges[i].base_lo & 0xff;
-		if (prev_match == 0xFF) {
-			prev_match = curr_match;
-			continue;
-		}
-
-		if (prev_match == MTRR_TYPE_UNCACHABLE ||
-		    curr_match == MTRR_TYPE_UNCACHABLE)
-			return MTRR_TYPE_UNCACHABLE;
-
-		if ((prev_match == MTRR_TYPE_WRBACK &&
-		     curr_match == MTRR_TYPE_WRTHROUGH) ||
-		    (prev_match == MTRR_TYPE_WRTHROUGH &&
-		     curr_match == MTRR_TYPE_WRBACK)) {
-			prev_match = MTRR_TYPE_WRTHROUGH;
-			curr_match = MTRR_TYPE_WRTHROUGH;
-		}
-
-		if (prev_match != curr_match)
-			return MTRR_TYPE_UNCACHABLE;
-	}
-
-	if (prev_match != 0xFF)
-		return prev_match;
-
-	return mtrr_state->def_type;
-}
-
-u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
-	u8 mtrr;
-
-	mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT,
-			     (gfn << PAGE_SHIFT) + PAGE_SIZE);
-	if (mtrr == 0xfe || mtrr == 0xff)
-		mtrr = MTRR_TYPE_WRBACK;
-	return mtrr;
-}
-EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type);
-
 static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
 	trace_kvm_mmu_unsync_page(sp);
@@ -2541,7 +2487,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	u64 spte;
 	int ret = 0;
 
-	if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access))
+	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
 	spte = PT_PRESENT_MASK;
@@ -2578,7 +2524,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		 * be fixed if guest refault.
 		 */
 		if (level > PT_PAGE_TABLE_LEVEL &&
-		    has_wrprotected_page(vcpu->kvm, gfn, level))
+		    has_wrprotected_page(vcpu, gfn, level))
 			goto done;
 
 		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
@@ -2602,7 +2548,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 
 	if (pte_access & ACC_WRITE_MASK) {
-		mark_page_dirty(vcpu->kvm, gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
 		spte |= shadow_dirty_mask;
 	}
 
@@ -2692,15 +2638,17 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 				    u64 *start, u64 *end)
 {
 	struct page *pages[PTE_PREFETCH_NUM];
+	struct kvm_memory_slot *slot;
 	unsigned access = sp->role.access;
 	int i, ret;
 	gfn_t gfn;
 
 	gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt);
-	if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK))
+	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK);
+	if (!slot)
 		return -1;
 
-	ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start);
+	ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start);
 	if (ret <= 0)
 		return -1;
 
@@ -2818,7 +2766,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
 		return 1;
 
 	if (pfn == KVM_PFN_ERR_HWPOISON) {
-		kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
+		kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current);
 		return 0;
 	}
 
@@ -2841,7 +2789,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
 	    level == PT_PAGE_TABLE_LEVEL &&
 	    PageTransCompound(pfn_to_page(pfn)) &&
-	    !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
+	    !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
 		unsigned long mask;
 		/*
 		 * mmu_notifier_retry was successful and we hold the
@@ -2933,7 +2881,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * Compare with set_spte where instead shadow_dirty_mask is set.
 	 */
 	if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte)
-		mark_page_dirty(vcpu->kvm, gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
 
 	return true;
 }
@@ -3388,7 +3336,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 		gfn_t gfn = get_mmio_spte_gfn(spte);
 		unsigned access = get_mmio_spte_access(spte);
 
-		if (!check_mmio_spte(vcpu->kvm, spte))
+		if (!check_mmio_spte(vcpu, spte))
 			return RET_MMIO_PF_INVALID;
 
 		if (direct)
@@ -3460,7 +3408,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu.direct_map;
 	arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -3475,10 +3423,12 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu)
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			 gva_t gva, pfn_t *pfn, bool write, bool *writable)
 {
+	struct kvm_memory_slot *slot;
 	bool async;
 
-	*pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable);
-
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	async = false;
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
 	if (!async)
 		return false; /* *pfn has correct page already */
 
@@ -3492,11 +3442,20 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			return true;
 	}
 
-	*pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable);
-
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
 	return false;
 }
 
+static bool
+check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
+{
+	int page_num = KVM_PAGES_PER_HPAGE(level);
+
+	gfn &= ~(page_num - 1);
+
+	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
+}
+
 static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 			  bool prefault)
 {
@@ -3522,9 +3481,17 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 	if (r)
 		return r;
 
-	force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn);
+	if (mapping_level_dirty_bitmap(vcpu, gfn) ||
+	    !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL))
+		force_pt_level = 1;
+	else
+		force_pt_level = 0;
+
 	if (likely(!force_pt_level)) {
 		level = mapping_level(vcpu, gfn);
+		if (level > PT_DIRECTORY_LEVEL &&
+		    !check_hugepage_cache_consistency(vcpu, gfn, level))
+			level = PT_DIRECTORY_LEVEL;
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	} else
 		level = PT_PAGE_TABLE_LEVEL;
@@ -3590,7 +3557,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmu.inject_page_fault(vcpu, fault);
 }
 
-static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
+static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
 			   unsigned access, int *nr_present)
 {
 	if (unlikely(is_mmio_spte(*sptep))) {
@@ -3600,7 +3567,7 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 		}
 
 		(*nr_present)++;
-		mark_mmio_spte(kvm, sptep, gfn, access);
+		mark_mmio_spte(vcpu, sptep, gfn, access);
 		return true;
 	}
 
@@ -3736,8 +3703,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+				      struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3878,6 +3845,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	context->base_role.word = 0;
+	context->base_role.smm = is_smm(vcpu);
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
@@ -3918,6 +3886,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 {
 	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	MMU_WARN_ON(VALID_PAGE(context->root_hpa));
@@ -3936,6 +3905,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 	context->base_role.cr0_wp  = is_write_protection(vcpu);
 	context->base_role.smep_andnot_wp
 		= smep && !is_write_protection(vcpu);
+	context->base_role.smap_andnot_wp
+		= smap && !is_write_protection(vcpu);
+	context->base_role.smm = is_smm(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -4107,7 +4079,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
 		*gpa &= ~(gpa_t)7;
 		*bytes = 8;
-		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8);
+		r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8);
 		if (r)
 			gentry = 0;
 		new = (const u8 *)&gentry;
@@ -4207,12 +4179,19 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
-	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
 	bool remote_flush, local_flush, zap_page;
+	union kvm_mmu_page_role mask = { };
+
+	mask.cr0_wp = 1;
+	mask.cr4_pae = 1;
+	mask.nxe = 1;
+	mask.smep_andnot_wp = 1;
+	mask.smap_andnot_wp = 1;
+	mask.smm = 1;
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
@@ -4238,7 +4217,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
-	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
@@ -4412,36 +4390,115 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 	init_kvm_mmu(vcpu);
 }
 
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
-				      struct kvm_memory_slot *memslot)
+/* The return value indicates if tlb flush on all vcpus is needed. */
+typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap);
+
+/* The caller should hold mmu-lock before calling this function. */
+static bool
+slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			slot_level_handler fn, int start_level, int end_level,
+			gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb)
 {
-	gfn_t last_gfn;
-	int i;
+	struct slot_rmap_walk_iterator iterator;
 	bool flush = false;
 
-	last_gfn = memslot->base_gfn + memslot->npages - 1;
+	for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn,
+			end_gfn, &iterator) {
+		if (iterator.rmap)
+			flush |= fn(kvm, iterator.rmap);
 
-	spin_lock(&kvm->mmu_lock);
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			if (flush && lock_flush_tlb) {
+				kvm_flush_remote_tlbs(kvm);
+				flush = false;
+			}
+			cond_resched_lock(&kvm->mmu_lock);
+		}
+	}
 
-	for (i = PT_PAGE_TABLE_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		unsigned long *rmapp;
-		unsigned long last_index, index;
+	if (flush && lock_flush_tlb) {
+		kvm_flush_remote_tlbs(kvm);
+		flush = false;
+	}
 
-		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
-		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
+	return flush;
+}
 
-		for (index = 0; index <= last_index; ++index, ++rmapp) {
-			if (*rmapp)
-				flush |= __rmap_write_protect(kvm, rmapp,
-						false);
+static bool
+slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		  slot_level_handler fn, int start_level, int end_level,
+		  bool lock_flush_tlb)
+{
+	return slot_handle_level_range(kvm, memslot, fn, start_level,
+			end_level, memslot->base_gfn,
+			memslot->base_gfn + memslot->npages - 1,
+			lock_flush_tlb);
+}
+
+static bool
+slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		      slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1,
+				 PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb);
+}
+
+static bool
+slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
+		 slot_level_handler fn, bool lock_flush_tlb)
+{
+	return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL,
+				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
+}
 
-			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
-				cond_resched_lock(&kvm->mmu_lock);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int i;
+
+	spin_lock(&kvm->mmu_lock);
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
+		kvm_for_each_memslot(memslot, slots) {
+			gfn_t start, end;
+
+			start = max(gfn_start, memslot->base_gfn);
+			end = min(gfn_end, memslot->base_gfn + memslot->npages);
+			if (start >= end)
+				continue;
+
+			slot_handle_level_range(kvm, memslot, kvm_zap_rmapp,
+						PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL,
+						start, end - 1, true);
 		}
 	}
 
 	spin_unlock(&kvm->mmu_lock);
+}
+
+static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp)
+{
+	return __rmap_write_protect(kvm, rmapp, false);
+}
+
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot)
+{
+	bool flush;
+
+	spin_lock(&kvm->mmu_lock);
+	flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect,
+				      false);
+	spin_unlock(&kvm->mmu_lock);
 
 	/*
 	 * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log()
@@ -4474,9 +4531,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 	pfn_t pfn;
 	struct kvm_mmu_page *sp;
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
-		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-
+restart:
+	for_each_rmap_spte(rmapp, &iter, sptep) {
 		sp = page_header(__pa(sptep));
 		pfn = spte_to_pfn(*sptep);
 
@@ -4491,71 +4547,31 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 			!kvm_is_reserved_pfn(pfn) &&
 			PageTransCompound(pfn_to_page(pfn))) {
 			drop_spte(kvm, sptep);
-			sptep = rmap_get_first(*rmapp, &iter);
 			need_tlb_flush = 1;
-		} else
-			sptep = rmap_get_next(&iter);
+			goto restart;
+		}
 	}
 
 	return need_tlb_flush;
 }
 
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
-			struct kvm_memory_slot *memslot)
+				   const struct kvm_memory_slot *memslot)
 {
-	bool flush = false;
-	unsigned long *rmapp;
-	unsigned long last_index, index;
-
+	/* FIXME: const-ify all uses of struct kvm_memory_slot.  */
 	spin_lock(&kvm->mmu_lock);
-
-	rmapp = memslot->arch.rmap[0];
-	last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
-				memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
-
-	for (index = 0; index <= last_index; ++index, ++rmapp) {
-		if (*rmapp)
-			flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp);
-
-		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
-			if (flush) {
-				kvm_flush_remote_tlbs(kvm);
-				flush = false;
-			}
-			cond_resched_lock(&kvm->mmu_lock);
-		}
-	}
-
-	if (flush)
-		kvm_flush_remote_tlbs(kvm);
-
+	slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot,
+			 kvm_mmu_zap_collapsible_spte, true);
 	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot)
 {
-	gfn_t last_gfn;
-	unsigned long *rmapp;
-	unsigned long last_index, index;
-	bool flush = false;
-
-	last_gfn = memslot->base_gfn + memslot->npages - 1;
+	bool flush;
 
 	spin_lock(&kvm->mmu_lock);
-
-	rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1];
-	last_index = gfn_to_index(last_gfn, memslot->base_gfn,
-			PT_PAGE_TABLE_LEVEL);
-
-	for (index = 0; index <= last_index; ++index, ++rmapp) {
-		if (*rmapp)
-			flush |= __rmap_clear_dirty(kvm, rmapp);
-
-		if (need_resched() || spin_needbreak(&kvm->mmu_lock))
-			cond_resched_lock(&kvm->mmu_lock);
-	}
-
+	flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false);
 	spin_unlock(&kvm->mmu_lock);
 
 	lockdep_assert_held(&kvm->slots_lock);
@@ -4574,31 +4590,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty);
 void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
 					struct kvm_memory_slot *memslot)
 {
-	gfn_t last_gfn;
-	int i;
-	bool flush = false;
-
-	last_gfn = memslot->base_gfn + memslot->npages - 1;
+	bool flush;
 
 	spin_lock(&kvm->mmu_lock);
-
-	for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		unsigned long *rmapp;
-		unsigned long last_index, index;
-
-		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
-		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
-		for (index = 0; index <= last_index; ++index, ++rmapp) {
-			if (*rmapp)
-				flush |= __rmap_write_protect(kvm, rmapp,
-						false);
-
-			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
-				cond_resched_lock(&kvm->mmu_lock);
-		}
-	}
+	flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect,
+					false);
 	spin_unlock(&kvm->mmu_lock);
 
 	/* see kvm_mmu_slot_remove_write_access */
@@ -4612,31 +4608,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access);
 void kvm_mmu_slot_set_dirty(struct kvm *kvm,
 			    struct kvm_memory_slot *memslot)
 {
-	gfn_t last_gfn;
-	int i;
-	bool flush = false;
-
-	last_gfn = memslot->base_gfn + memslot->npages - 1;
+	bool flush;
 
 	spin_lock(&kvm->mmu_lock);
-
-	for (i = PT_PAGE_TABLE_LEVEL;
-	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
-		unsigned long *rmapp;
-		unsigned long last_index, index;
-
-		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
-		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
-
-		for (index = 0; index <= last_index; ++index, ++rmapp) {
-			if (*rmapp)
-				flush |= __rmap_set_dirty(kvm, rmapp);
-
-			if (need_resched() || spin_needbreak(&kvm->mmu_lock))
-				cond_resched_lock(&kvm->mmu_lock);
-		}
-	}
-
+	flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false);
 	spin_unlock(&kvm->mmu_lock);
 
 	lockdep_assert_held(&kvm->slots_lock);
@@ -4733,13 +4708,13 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
+void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots)
 {
 	/*
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
+	if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) {
 		printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
@@ -4861,15 +4836,18 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	unsigned int  nr_pages = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
+	int i;
 
-	slots = kvm_memslots(kvm);
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
 
-	kvm_for_each_memslot(memslot, slots)
-		nr_pages += memslot->npages;
+		kvm_for_each_memslot(memslot, slots)
+			nr_pages += memslot->npages;
+	}
 
 	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
 	nr_mmu_pages = max(nr_mmu_pages,
-			(unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+			   (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
 
 	return nr_mmu_pages;
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index c7d65637c851..398d21c0f6dd 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,6 +43,7 @@
 #define PT_PDPE_LEVEL 3
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
+#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
 
 static inline u64 rsvd_bits(int s, int e)
 {
@@ -71,8 +72,6 @@ enum {
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-		bool ept);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
@@ -166,8 +165,11 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 
+	WARN_ON(pfec & PFERR_RSVD_MASK);
+
 	return (mmu->permissions[index] >> pte_access) & 1;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
+void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end);
 #endif
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 9ade5cfb5a4c..a4f62e6f2db2 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -114,7 +114,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 		return;
 
 	gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
-	pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
+	pfn = kvm_vcpu_gfn_to_pfn_atomic(vcpu, gfn);
 
 	if (is_error_pfn(pfn))
 		return;
@@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
 	unsigned long *rmapp;
 	struct kvm_mmu_page *rev_sp;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *slot;
 	gfn_t gfn;
 
 	rev_sp = page_header(__pa(sptep));
 	gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt);
 
-	if (!gfn_to_memslot(kvm, gfn)) {
+	slots = kvm_memslots_for_spte_role(kvm, rev_sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
+	if (!slot) {
 		if (!__ratelimit(&ratelimit_state))
 			return;
 		audit_printk(kvm, "no memslot for gfn %llx\n", gfn);
@@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 		return;
 	}
 
-	rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level);
+	rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot);
 	if (!*rmapp) {
 		if (!__ratelimit(&ratelimit_state))
 			return;
@@ -191,19 +195,21 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	unsigned long *rmapp;
 	u64 *sptep;
 	struct rmap_iterator iter;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *slot;
 
 	if (sp->role.direct || sp->unsync || sp->role.invalid)
 		return;
 
-	rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, sp->gfn);
+	rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
 
-	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
-	     sptep = rmap_get_next(&iter)) {
+	for_each_rmap_spte(rmapp, &iter, sptep)
 		if (is_writable_pte(*sptep))
 			audit_printk(kvm, "shadow page has writable "
 				     "mappings: gfn %llx role %x\n",
 				     sp->gfn, sp->role.word);
-	}
 }
 
 static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
new file mode 100644
index 000000000000..de1d2d8062e2
--- /dev/null
+++ b/arch/x86/kvm/mtrr.c
@@ -0,0 +1,699 @@
+/*
+ * vMTRR implementation
+ *
+ * Copyright (C) 2006 Qumranet, Inc.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ * Copyright(C) 2015 Intel Corporation.
+ *
+ * Authors:
+ *   Yaniv Kamay  <yaniv@qumranet.com>
+ *   Avi Kivity   <avi@qumranet.com>
+ *   Marcelo Tosatti <mtosatti@redhat.com>
+ *   Paolo Bonzini <pbonzini@redhat.com>
+ *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/mtrr.h>
+
+#include "cpuid.h"
+#include "mmu.h"
+
+#define IA32_MTRR_DEF_TYPE_E		(1ULL << 11)
+#define IA32_MTRR_DEF_TYPE_FE		(1ULL << 10)
+#define IA32_MTRR_DEF_TYPE_TYPE_MASK	(0xff)
+
+static bool msr_mtrr_valid(unsigned msr)
+{
+	switch (msr) {
+	case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
+	case MSR_MTRRfix64K_00000:
+	case MSR_MTRRfix16K_80000:
+	case MSR_MTRRfix16K_A0000:
+	case MSR_MTRRfix4K_C0000:
+	case MSR_MTRRfix4K_C8000:
+	case MSR_MTRRfix4K_D0000:
+	case MSR_MTRRfix4K_D8000:
+	case MSR_MTRRfix4K_E0000:
+	case MSR_MTRRfix4K_E8000:
+	case MSR_MTRRfix4K_F0000:
+	case MSR_MTRRfix4K_F8000:
+	case MSR_MTRRdefType:
+	case MSR_IA32_CR_PAT:
+		return true;
+	case 0x2f8:
+		return true;
+	}
+	return false;
+}
+
+static bool valid_pat_type(unsigned t)
+{
+	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
+}
+
+static bool valid_mtrr_type(unsigned t)
+{
+	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
+}
+
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	int i;
+	u64 mask;
+
+	if (!msr_mtrr_valid(msr))
+		return false;
+
+	if (msr == MSR_IA32_CR_PAT) {
+		for (i = 0; i < 8; i++)
+			if (!valid_pat_type((data >> (i * 8)) & 0xff))
+				return false;
+		return true;
+	} else if (msr == MSR_MTRRdefType) {
+		if (data & ~0xcff)
+			return false;
+		return valid_mtrr_type(data & 0xff);
+	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
+		for (i = 0; i < 8 ; i++)
+			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
+				return false;
+		return true;
+	}
+
+	/* variable MTRRs */
+	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
+
+	mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	if ((msr & 1) == 0) {
+		/* MTRR base */
+		if (!valid_mtrr_type(data & 0xff))
+			return false;
+		mask |= 0xf00;
+	} else
+		/* MTRR mask */
+		mask |= 0x7ff;
+	if (data & mask) {
+		kvm_inject_gp(vcpu, 0);
+		return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
+
+static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
+{
+	return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E);
+}
+
+static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state)
+{
+	return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE);
+}
+
+static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
+{
+	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
+}
+
+/*
+* Three terms are used in the following code:
+* - segment, it indicates the address segments covered by fixed MTRRs.
+* - unit, it corresponds to the MSR entry in the segment.
+* - range, a range is covered in one memory cache type.
+*/
+struct fixed_mtrr_segment {
+	u64 start;
+	u64 end;
+
+	int range_shift;
+
+	/* the start position in kvm_mtrr.fixed_ranges[]. */
+	int range_start;
+};
+
+static struct fixed_mtrr_segment fixed_seg_table[] = {
+	/* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */
+	{
+		.start = 0x0,
+		.end = 0x80000,
+		.range_shift = 16, /* 64K */
+		.range_start = 0,
+	},
+
+	/*
+	 * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units,
+	 * 16K fixed mtrr.
+	 */
+	{
+		.start = 0x80000,
+		.end = 0xc0000,
+		.range_shift = 14, /* 16K */
+		.range_start = 8,
+	},
+
+	/*
+	 * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units,
+	 * 4K fixed mtrr.
+	 */
+	{
+		.start = 0xc0000,
+		.end = 0x100000,
+		.range_shift = 12, /* 12K */
+		.range_start = 24,
+	}
+};
+
+/*
+ * The size of unit is covered in one MSR, one MSR entry contains
+ * 8 ranges so that unit size is always 8 * 2^range_shift.
+ */
+static u64 fixed_mtrr_seg_unit_size(int seg)
+{
+	return 8 << fixed_seg_table[seg].range_shift;
+}
+
+static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit)
+{
+	switch (msr) {
+	case MSR_MTRRfix64K_00000:
+		*seg = 0;
+		*unit = 0;
+		break;
+	case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
+		*seg = 1;
+		*unit = msr - MSR_MTRRfix16K_80000;
+		break;
+	case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
+		*seg = 2;
+		*unit = msr - MSR_MTRRfix4K_C0000;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end)
+{
+	struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+	u64 unit_size = fixed_mtrr_seg_unit_size(seg);
+
+	*start = mtrr_seg->start + unit * unit_size;
+	*end = *start + unit_size;
+	WARN_ON(*end > mtrr_seg->end);
+}
+
+static int fixed_mtrr_seg_unit_range_index(int seg, int unit)
+{
+	struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+
+	WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg)
+		> mtrr_seg->end);
+
+	/* each unit has 8 ranges. */
+	return mtrr_seg->range_start + 8 * unit;
+}
+
+static int fixed_mtrr_seg_end_range_index(int seg)
+{
+	struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+	int n;
+
+	n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift;
+	return mtrr_seg->range_start + n - 1;
+}
+
+static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end)
+{
+	int seg, unit;
+
+	if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
+		return false;
+
+	fixed_mtrr_seg_unit_range(seg, unit, start, end);
+	return true;
+}
+
+static int fixed_msr_to_range_index(u32 msr)
+{
+	int seg, unit;
+
+	if (!fixed_msr_to_seg_unit(msr, &seg, &unit))
+		return -1;
+
+	return fixed_mtrr_seg_unit_range_index(seg, unit);
+}
+
+static int fixed_mtrr_addr_to_seg(u64 addr)
+{
+	struct fixed_mtrr_segment *mtrr_seg;
+	int seg, seg_num = ARRAY_SIZE(fixed_seg_table);
+
+	for (seg = 0; seg < seg_num; seg++) {
+		mtrr_seg = &fixed_seg_table[seg];
+		if (mtrr_seg->start >= addr && addr < mtrr_seg->end)
+			return seg;
+	}
+
+	return -1;
+}
+
+static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg)
+{
+	struct fixed_mtrr_segment *mtrr_seg;
+	int index;
+
+	mtrr_seg = &fixed_seg_table[seg];
+	index = mtrr_seg->range_start;
+	index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift;
+	return index;
+}
+
+static u64 fixed_mtrr_range_end_addr(int seg, int index)
+{
+	struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg];
+	int pos = index - mtrr_seg->range_start;
+
+	return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift);
+}
+
+static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
+{
+	u64 mask;
+
+	*start = range->base & PAGE_MASK;
+
+	mask = range->mask & PAGE_MASK;
+	mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
+
+	/* This cannot overflow because writing to the reserved bits of
+	 * variable MTRRs causes a #GP.
+	 */
+	*end = (*start | ~mask) + 1;
+}
+
+static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+	gfn_t start, end;
+	int index;
+
+	if (msr == MSR_IA32_CR_PAT || !tdp_enabled ||
+	      !kvm_arch_has_noncoherent_dma(vcpu->kvm))
+		return;
+
+	if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType)
+		return;
+
+	/* fixed MTRRs. */
+	if (fixed_msr_to_range(msr, &start, &end)) {
+		if (!fixed_mtrr_is_enabled(mtrr_state))
+			return;
+	} else if (msr == MSR_MTRRdefType) {
+		start = 0x0;
+		end = ~0ULL;
+	} else {
+		/* variable range MTRRs. */
+		index = (msr - 0x200) / 2;
+		var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end);
+	}
+
+	kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end));
+}
+
+static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range)
+{
+	return (range->mask & (1 << 11)) != 0;
+}
+
+static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+	struct kvm_mtrr_range *tmp, *cur;
+	int index, is_mtrr_mask;
+
+	index = (msr - 0x200) / 2;
+	is_mtrr_mask = msr - 0x200 - 2 * index;
+	cur = &mtrr_state->var_ranges[index];
+
+	/* remove the entry if it's in the list. */
+	if (var_mtrr_range_is_valid(cur))
+		list_del(&mtrr_state->var_ranges[index].node);
+
+	if (!is_mtrr_mask)
+		cur->base = data;
+	else
+		cur->mask = data;
+
+	/* add it to the list if it's enabled. */
+	if (var_mtrr_range_is_valid(cur)) {
+		list_for_each_entry(tmp, &mtrr_state->head, node)
+			if (cur->base >= tmp->base)
+				break;
+		list_add_tail(&cur->node, &tmp->node);
+	}
+}
+
+int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	int index;
+
+	if (!kvm_mtrr_valid(vcpu, msr, data))
+		return 1;
+
+	index = fixed_msr_to_range_index(msr);
+	if (index >= 0)
+		*(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data;
+	else if (msr == MSR_MTRRdefType)
+		vcpu->arch.mtrr_state.deftype = data;
+	else if (msr == MSR_IA32_CR_PAT)
+		vcpu->arch.pat = data;
+	else
+		set_var_mtrr_msr(vcpu, msr, data);
+
+	update_mtrr(vcpu, msr);
+	return 0;
+}
+
+int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	int index;
+
+	/* MSR_MTRRcap is a readonly MSR. */
+	if (msr == MSR_MTRRcap) {
+		/*
+		 * SMRR = 0
+		 * WC = 1
+		 * FIX = 1
+		 * VCNT = KVM_NR_VAR_MTRR
+		 */
+		*pdata = 0x500 | KVM_NR_VAR_MTRR;
+		return 0;
+	}
+
+	if (!msr_mtrr_valid(msr))
+		return 1;
+
+	index = fixed_msr_to_range_index(msr);
+	if (index >= 0)
+		*pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index];
+	else if (msr == MSR_MTRRdefType)
+		*pdata = vcpu->arch.mtrr_state.deftype;
+	else if (msr == MSR_IA32_CR_PAT)
+		*pdata = vcpu->arch.pat;
+	else {	/* Variable MTRRs */
+		int is_mtrr_mask;
+
+		index = (msr - 0x200) / 2;
+		is_mtrr_mask = msr - 0x200 - 2 * index;
+		if (!is_mtrr_mask)
+			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
+		else
+			*pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+	}
+
+	return 0;
+}
+
+void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu)
+{
+	INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head);
+}
+
+struct mtrr_iter {
+	/* input fields. */
+	struct kvm_mtrr *mtrr_state;
+	u64 start;
+	u64 end;
+
+	/* output fields. */
+	int mem_type;
+	/* [start, end) is not fully covered in MTRRs? */
+	bool partial_map;
+
+	/* private fields. */
+	union {
+		/* used for fixed MTRRs. */
+		struct {
+			int index;
+			int seg;
+		};
+
+		/* used for var MTRRs. */
+		struct {
+			struct kvm_mtrr_range *range;
+			/* max address has been covered in var MTRRs. */
+			u64 start_max;
+		};
+	};
+
+	bool fixed;
+};
+
+static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter)
+{
+	int seg, index;
+
+	if (!fixed_mtrr_is_enabled(iter->mtrr_state))
+		return false;
+
+	seg = fixed_mtrr_addr_to_seg(iter->start);
+	if (seg < 0)
+		return false;
+
+	iter->fixed = true;
+	index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg);
+	iter->index = index;
+	iter->seg = seg;
+	return true;
+}
+
+static bool match_var_range(struct mtrr_iter *iter,
+			    struct kvm_mtrr_range *range)
+{
+	u64 start, end;
+
+	var_mtrr_range(range, &start, &end);
+	if (!(start >= iter->end || end <= iter->start)) {
+		iter->range = range;
+
+		/*
+		 * the function is called when we do kvm_mtrr.head walking.
+		 * Range has the minimum base address which interleaves
+		 * [looker->start_max, looker->end).
+		 */
+		iter->partial_map |= iter->start_max < start;
+
+		/* update the max address has been covered. */
+		iter->start_max = max(iter->start_max, end);
+		return true;
+	}
+
+	return false;
+}
+
+static void __mtrr_lookup_var_next(struct mtrr_iter *iter)
+{
+	struct kvm_mtrr *mtrr_state = iter->mtrr_state;
+
+	list_for_each_entry_continue(iter->range, &mtrr_state->head, node)
+		if (match_var_range(iter, iter->range))
+			return;
+
+	iter->range = NULL;
+	iter->partial_map |= iter->start_max < iter->end;
+}
+
+static void mtrr_lookup_var_start(struct mtrr_iter *iter)
+{
+	struct kvm_mtrr *mtrr_state = iter->mtrr_state;
+
+	iter->fixed = false;
+	iter->start_max = iter->start;
+	iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node);
+
+	__mtrr_lookup_var_next(iter);
+}
+
+static void mtrr_lookup_fixed_next(struct mtrr_iter *iter)
+{
+	/* terminate the lookup. */
+	if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) {
+		iter->fixed = false;
+		iter->range = NULL;
+		return;
+	}
+
+	iter->index++;
+
+	/* have looked up for all fixed MTRRs. */
+	if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges))
+		return mtrr_lookup_var_start(iter);
+
+	/* switch to next segment. */
+	if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg))
+		iter->seg++;
+}
+
+static void mtrr_lookup_var_next(struct mtrr_iter *iter)
+{
+	__mtrr_lookup_var_next(iter);
+}
+
+static void mtrr_lookup_start(struct mtrr_iter *iter)
+{
+	if (!mtrr_is_enabled(iter->mtrr_state)) {
+		iter->partial_map = true;
+		return;
+	}
+
+	if (!mtrr_lookup_fixed_start(iter))
+		mtrr_lookup_var_start(iter);
+}
+
+static void mtrr_lookup_init(struct mtrr_iter *iter,
+			     struct kvm_mtrr *mtrr_state, u64 start, u64 end)
+{
+	iter->mtrr_state = mtrr_state;
+	iter->start = start;
+	iter->end = end;
+	iter->partial_map = false;
+	iter->fixed = false;
+	iter->range = NULL;
+
+	mtrr_lookup_start(iter);
+}
+
+static bool mtrr_lookup_okay(struct mtrr_iter *iter)
+{
+	if (iter->fixed) {
+		iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index];
+		return true;
+	}
+
+	if (iter->range) {
+		iter->mem_type = iter->range->base & 0xff;
+		return true;
+	}
+
+	return false;
+}
+
+static void mtrr_lookup_next(struct mtrr_iter *iter)
+{
+	if (iter->fixed)
+		mtrr_lookup_fixed_next(iter);
+	else
+		mtrr_lookup_var_next(iter);
+}
+
+#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \
+	for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \
+	     mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_))
+
+u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+	struct mtrr_iter iter;
+	u64 start, end;
+	int type = -1;
+	const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK)
+			       | (1 << MTRR_TYPE_WRTHROUGH);
+
+	start = gfn_to_gpa(gfn);
+	end = start + PAGE_SIZE;
+
+	mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
+		int curr_type = iter.mem_type;
+
+		/*
+		 * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR
+		 * Precedences.
+		 */
+
+		if (type == -1) {
+			type = curr_type;
+			continue;
+		}
+
+		/*
+		 * If two or more variable memory ranges match and the
+		 * memory types are identical, then that memory type is
+		 * used.
+		 */
+		if (type == curr_type)
+			continue;
+
+		/*
+		 * If two or more variable memory ranges match and one of
+		 * the memory types is UC, the UC memory type used.
+		 */
+		if (curr_type == MTRR_TYPE_UNCACHABLE)
+			return MTRR_TYPE_UNCACHABLE;
+
+		/*
+		 * If two or more variable memory ranges match and the
+		 * memory types are WT and WB, the WT memory type is used.
+		 */
+		if (((1 << type) & wt_wb_mask) &&
+		      ((1 << curr_type) & wt_wb_mask)) {
+			type = MTRR_TYPE_WRTHROUGH;
+			continue;
+		}
+
+		/*
+		 * For overlaps not defined by the above rules, processor
+		 * behavior is undefined.
+		 */
+
+		/* We use WB for this undefined behavior. :( */
+		return MTRR_TYPE_WRBACK;
+	}
+
+	/* It is not covered by MTRRs. */
+	if (iter.partial_map) {
+		/*
+		 * We just check one page, partially covered by MTRRs is
+		 * impossible.
+		 */
+		WARN_ON(type != -1);
+		type = mtrr_default_type(mtrr_state);
+	}
+	return type;
+}
+EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
+
+bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
+					  int page_num)
+{
+	struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state;
+	struct mtrr_iter iter;
+	u64 start, end;
+	int type = -1;
+
+	start = gfn_to_gpa(gfn);
+	end = gfn_to_gpa(gfn + page_num);
+	mtrr_for_each_mem_type(&iter, mtrr_state, start, end) {
+		if (type == -1) {
+			type = iter.mem_type;
+			continue;
+		}
+
+		if (type != iter.mem_type)
+			return false;
+	}
+
+	if (!iter.partial_map)
+		return true;
+
+	if (type == -1)
+		return true;
+
+	return type == mtrr_default_type(mtrr_state);
+}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index fd49c867b25a..0f67d7e24800 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -256,7 +256,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 		if (ret)
 			return ret;
 
-		mark_page_dirty(vcpu->kvm, table_gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, table_gfn);
 		walker->ptes[level] = pte;
 	}
 	return 0;
@@ -338,7 +338,7 @@ retry_walk:
 
 		real_gfn = gpa_to_gfn(real_gfn);
 
-		host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
@@ -511,11 +511,11 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu,
 		base_gpa = pte_gpa & ~mask;
 		index = (pte_gpa - base_gpa) / sizeof(pt_element_t);
 
-		r = kvm_read_guest_atomic(vcpu->kvm, base_gpa,
+		r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa,
 				gw->prefetch_ptes, sizeof(gw->prefetch_ptes));
 		curr_pte = gw->prefetch_ptes[index];
 	} else
-		r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa,
+		r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa,
 				  &curr_pte, sizeof(curr_pte));
 
 	return r || curr_pte != gw->ptes[level - 1];
@@ -718,6 +718,13 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 					      mmu_is_nested(vcpu));
 		if (likely(r != RET_MMIO_PF_INVALID))
 			return r;
+
+		/*
+		 * page fault with PFEC.RSVD  = 1 is caused by shadow
+		 * page fault, should not be used to walk guest page
+		 * table.
+		 */
+		error_code &= ~PFERR_RSVD_MASK;
 	};
 
 	r = mmu_topup_memory_caches(vcpu);
@@ -862,8 +869,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 			if (!rmap_can_add(vcpu))
 				break;
 
-			if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
-						  sizeof(pt_element_t)))
+			if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+						       sizeof(pt_element_t)))
 				break;
 
 			FNAME(update_pte)(vcpu, sp, sptep, &gpte);
@@ -949,8 +956,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
 
-		if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
-					  sizeof(pt_element_t)))
+		if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte,
+					       sizeof(pt_element_t)))
 			return -EINVAL;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
@@ -963,7 +970,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 		pte_access &= FNAME(gpte_access)(vcpu, gpte);
 		FNAME(protect_clean_gpte)(&pte_access, gpte);
 
-		if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
+		if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
 		      &nr_present))
 			continue;
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 29fbf9dfdc54..31aa2c85dc97 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,11 +1,12 @@
 /*
  * Kernel-based Virtual Machine -- Performance Monitoring Unit support
  *
- * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ * Copyright 2015 Red Hat, Inc. and/or its affiliates.
  *
  * Authors:
  *   Avi Kivity   <avi@redhat.com>
  *   Gleb Natapov <gleb@redhat.com>
+ *   Wei Huang    <wei@redhat.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
@@ -19,88 +20,39 @@
 #include "x86.h"
 #include "cpuid.h"
 #include "lapic.h"
+#include "pmu.h"
+
+/* NOTE:
+ * - Each perf counter is defined as "struct kvm_pmc";
+ * - There are two types of perf counters: general purpose (gp) and fixed.
+ *   gp counters are stored in gp_counters[] and fixed counters are stored
+ *   in fixed_counters[] respectively. Both of them are part of "struct
+ *   kvm_pmu";
+ * - pmu.c understands the difference between gp counters and fixed counters.
+ *   However AMD doesn't support fixed-counters;
+ * - There are three types of index to access perf counters (PMC):
+ *     1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD
+ *        has MSR_K7_PERFCTRn.
+ *     2. MSR Index (named idx): This normally is used by RDPMC instruction.
+ *        For instance AMD RDPMC instruction uses 0000_0003h in ECX to access
+ *        C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except
+ *        that it also supports fixed counters. idx can be used to as index to
+ *        gp and fixed counters.
+ *     3. Global PMC Index (named pmc): pmc is an index specific to PMU
+ *        code. Each pmc, stored in kvm_pmc.idx field, is unique across
+ *        all perf counters (both gp and fixed). The mapping relationship
+ *        between pmc and perf counters is as the following:
+ *        * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters
+ *                 [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
+ *        * AMD:   [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters
+ */
 
-static struct kvm_arch_event_perf_mapping {
-	u8 eventsel;
-	u8 unit_mask;
-	unsigned event_type;
-	bool inexact;
-} arch_events[] = {
-	/* Index must match CPUID 0x0A.EBX bit vector */
-	[0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
-	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
-	[2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES  },
-	[3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES },
-	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
-	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
-	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
-};
-
-/* mapping between fixed pmc index and arch_events array */
-static int fixed_pmc_events[] = {1, 0, 7};
-
-static bool pmc_is_gp(struct kvm_pmc *pmc)
-{
-	return pmc->type == KVM_PMC_GP;
-}
-
-static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
-{
-	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-
-	return pmu->counter_bitmask[pmc->type];
-}
-
-static inline bool pmc_enabled(struct kvm_pmc *pmc)
-{
-	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-	return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
-}
-
-static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
-					 u32 base)
-{
-	if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
-		return &pmu->gp_counters[msr - base];
-	return NULL;
-}
-
-static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
-{
-	int base = MSR_CORE_PERF_FIXED_CTR0;
-	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
-		return &pmu->fixed_counters[msr - base];
-	return NULL;
-}
-
-static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx)
-{
-	return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx);
-}
-
-static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx)
-{
-	if (idx < INTEL_PMC_IDX_FIXED)
-		return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0);
-	else
-		return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED);
-}
-
-void kvm_deliver_pmi(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.apic)
-		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
-}
-
-static void trigger_pmi(struct irq_work *irq_work)
+static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
 {
-	struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu,
-			irq_work);
-	struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu,
-			arch.pmu);
+	struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
 
-	kvm_deliver_pmi(vcpu);
+	kvm_pmu_deliver_pmi(vcpu);
 }
 
 static void kvm_perf_overflow(struct perf_event *perf_event,
@@ -108,63 +60,46 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
 			      struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
-	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (!test_and_set_bit(pmc->idx,
+			      (unsigned long *)&pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
 	}
 }
 
 static void kvm_perf_overflow_intr(struct perf_event *perf_event,
-		struct perf_sample_data *data, struct pt_regs *regs)
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
-	struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
-	if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	if (!test_and_set_bit(pmc->idx,
+			      (unsigned long *)&pmu->reprogram_pmi)) {
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 		kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+
 		/*
 		 * Inject PMI. If vcpu was in a guest mode during NMI PMI
 		 * can be ejected on a guest mode re-entry. Otherwise we can't
 		 * be sure that vcpu wasn't executing hlt instruction at the
-		 * time of vmexit and is not going to re-enter guest mode until,
+		 * time of vmexit and is not going to re-enter guest mode until
 		 * woken up. So we should wake it, but this is impossible from
 		 * NMI context. Do it from irq work instead.
 		 */
 		if (!kvm_is_in_guest())
-			irq_work_queue(&pmc->vcpu->arch.pmu.irq_work);
+			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
 		else
 			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
 	}
 }
 
-static u64 read_pmc(struct kvm_pmc *pmc)
-{
-	u64 counter, enabled, running;
-
-	counter = pmc->counter;
-
-	if (pmc->perf_event)
-		counter += perf_event_read_value(pmc->perf_event,
-						 &enabled, &running);
-
-	/* FIXME: Scaling needed? */
-
-	return counter & pmc_bitmask(pmc);
-}
-
-static void stop_counter(struct kvm_pmc *pmc)
-{
-	if (pmc->perf_event) {
-		pmc->counter = read_pmc(pmc);
-		perf_event_release_kernel(pmc->perf_event);
-		pmc->perf_event = NULL;
-	}
-}
-
-static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
-		unsigned config, bool exclude_user, bool exclude_kernel,
-		bool intr, bool in_tx, bool in_tx_cp)
+static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
+				  unsigned config, bool exclude_user,
+				  bool exclude_kernel, bool intr,
+				  bool in_tx, bool in_tx_cp)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -177,6 +112,7 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+
 	if (in_tx)
 		attr.config |= HSW_IN_TX;
 	if (in_tx_cp)
@@ -188,33 +124,16 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 						 intr ? kvm_perf_overflow_intr :
 						 kvm_perf_overflow, pmc);
 	if (IS_ERR(event)) {
-		printk_once("kvm: pmu event creation failed %ld\n",
-				PTR_ERR(event));
+		printk_once("kvm_pmu: event creation failed %ld\n",
+			    PTR_ERR(event));
 		return;
 	}
 
 	pmc->perf_event = event;
-	clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi);
-}
-
-static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select,
-		u8 unit_mask)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(arch_events); i++)
-		if (arch_events[i].eventsel == event_select
-				&& arch_events[i].unit_mask == unit_mask
-				&& (pmu->available_event_types & (1 << i)))
-			break;
-
-	if (i == ARRAY_SIZE(arch_events))
-		return PERF_COUNT_HW_MAX;
-
-	return arch_events[i].event_type;
+	clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi);
 }
 
-static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
+void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
@@ -224,21 +143,22 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	pmc->eventsel = eventsel;
 
-	stop_counter(pmc);
+	pmc_stop_counter(pmc);
 
-	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc))
+	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
 
 	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
 	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
-				ARCH_PERFMON_EVENTSEL_INV |
-				ARCH_PERFMON_EVENTSEL_CMASK |
-				HSW_IN_TX |
-				HSW_IN_TX_CHECKPOINTED))) {
-		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
-				unit_mask);
+			  ARCH_PERFMON_EVENTSEL_INV |
+			  ARCH_PERFMON_EVENTSEL_CMASK |
+			  HSW_IN_TX |
+			  HSW_IN_TX_CHECKPOINTED))) {
+		config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc),
+						      event_select,
+						      unit_mask);
 		if (config != PERF_COUNT_HW_MAX)
 			type = PERF_TYPE_HARDWARE;
 	}
@@ -246,56 +166,36 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (type == PERF_TYPE_RAW)
 		config = eventsel & X86_RAW_EVENT_MASK;
 
-	reprogram_counter(pmc, type, config,
-			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
-			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			eventsel & ARCH_PERFMON_EVENTSEL_INT,
-			(eventsel & HSW_IN_TX),
-			(eventsel & HSW_IN_TX_CHECKPOINTED));
+	pmc_reprogram_counter(pmc, type, config,
+			      !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+			      !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+			      eventsel & ARCH_PERFMON_EVENTSEL_INT,
+			      (eventsel & HSW_IN_TX),
+			      (eventsel & HSW_IN_TX_CHECKPOINTED));
 }
+EXPORT_SYMBOL_GPL(reprogram_gp_counter);
 
-static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
+void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx)
 {
-	unsigned en = en_pmi & 0x3;
-	bool pmi = en_pmi & 0x8;
+	unsigned en_field = ctrl & 0x3;
+	bool pmi = ctrl & 0x8;
 
-	stop_counter(pmc);
+	pmc_stop_counter(pmc);
 
-	if (!en || !pmc_enabled(pmc))
+	if (!en_field || !pmc_is_enabled(pmc))
 		return;
 
-	reprogram_counter(pmc, PERF_TYPE_HARDWARE,
-			arch_events[fixed_pmc_events[idx]].event_type,
-			!(en & 0x2), /* exclude user */
-			!(en & 0x1), /* exclude kernel */
-			pmi, false, false);
+	pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
+			      kvm_x86_ops->pmu_ops->find_fixed_event(idx),
+			      !(en_field & 0x2), /* exclude user */
+			      !(en_field & 0x1), /* exclude kernel */
+			      pmi, false, false);
 }
+EXPORT_SYMBOL_GPL(reprogram_fixed_counter);
 
-static inline u8 fixed_en_pmi(u64 ctrl, int idx)
+void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
 {
-	return (ctrl >> (idx * 4)) & 0xf;
-}
-
-static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
-{
-	int i;
-
-	for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
-		u8 en_pmi = fixed_en_pmi(data, i);
-		struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i);
-
-		if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi)
-			continue;
-
-		reprogram_fixed_counter(pmc, en_pmi, i);
-	}
-
-	pmu->fixed_ctr_ctrl = data;
-}
-
-static void reprogram_idx(struct kvm_pmu *pmu, int idx)
-{
-	struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx);
+	struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx);
 
 	if (!pmc)
 		return;
@@ -303,274 +203,107 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx)
 	if (pmc_is_gp(pmc))
 		reprogram_gp_counter(pmc, pmc->eventsel);
 	else {
-		int fidx = idx - INTEL_PMC_IDX_FIXED;
-		reprogram_fixed_counter(pmc,
-				fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx);
+		int idx = pmc_idx - INTEL_PMC_IDX_FIXED;
+		u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx);
+
+		reprogram_fixed_counter(pmc, ctrl, idx);
 	}
 }
+EXPORT_SYMBOL_GPL(reprogram_counter);
 
-static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	u64 bitmask;
 	int bit;
-	u64 diff = pmu->global_ctrl ^ data;
-
-	pmu->global_ctrl = data;
-
-	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
-		reprogram_idx(pmu, bit);
-}
 
-bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	int ret;
-
-	switch (msr) {
-	case MSR_CORE_PERF_FIXED_CTR_CTRL:
-	case MSR_CORE_PERF_GLOBAL_STATUS:
-	case MSR_CORE_PERF_GLOBAL_CTRL:
-	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		ret = pmu->version > 1;
-		break;
-	default:
-		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)
-			|| get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0)
-			|| get_fixed_pmc(pmu, msr);
-		break;
-	}
-	return ret;
-}
+	bitmask = pmu->reprogram_pmi;
 
-int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
+	for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
+		struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit);
 
-	switch (index) {
-	case MSR_CORE_PERF_FIXED_CTR_CTRL:
-		*data = pmu->fixed_ctr_ctrl;
-		return 0;
-	case MSR_CORE_PERF_GLOBAL_STATUS:
-		*data = pmu->global_status;
-		return 0;
-	case MSR_CORE_PERF_GLOBAL_CTRL:
-		*data = pmu->global_ctrl;
-		return 0;
-	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		*data = pmu->global_ovf_ctrl;
-		return 0;
-	default:
-		if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
-				(pmc = get_fixed_pmc(pmu, index))) {
-			*data = read_pmc(pmc);
-			return 0;
-		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
-			*data = pmc->eventsel;
-			return 0;
+		if (unlikely(!pmc || !pmc->perf_event)) {
+			clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
+			continue;
 		}
-	}
-	return 1;
-}
 
-int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
-	u32 index = msr_info->index;
-	u64 data = msr_info->data;
-
-	switch (index) {
-	case MSR_CORE_PERF_FIXED_CTR_CTRL:
-		if (pmu->fixed_ctr_ctrl == data)
-			return 0;
-		if (!(data & 0xfffffffffffff444ull)) {
-			reprogram_fixed_counters(pmu, data);
-			return 0;
-		}
-		break;
-	case MSR_CORE_PERF_GLOBAL_STATUS:
-		if (msr_info->host_initiated) {
-			pmu->global_status = data;
-			return 0;
-		}
-		break; /* RO MSR */
-	case MSR_CORE_PERF_GLOBAL_CTRL:
-		if (pmu->global_ctrl == data)
-			return 0;
-		if (!(data & pmu->global_ctrl_mask)) {
-			global_ctrl_changed(pmu, data);
-			return 0;
-		}
-		break;
-	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
-		if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
-			if (!msr_info->host_initiated)
-				pmu->global_status &= ~data;
-			pmu->global_ovf_ctrl = data;
-			return 0;
-		}
-		break;
-	default:
-		if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) ||
-				(pmc = get_fixed_pmc(pmu, index))) {
-			if (!msr_info->host_initiated)
-				data = (s64)(s32)data;
-			pmc->counter += data - read_pmc(pmc);
-			return 0;
-		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
-			if (data == pmc->eventsel)
-				return 0;
-			if (!(data & pmu->reserved_bits)) {
-				reprogram_gp_counter(pmc, data);
-				return 0;
-			}
-		}
+		reprogram_counter(pmu, bit);
 	}
-	return 1;
 }
 
-int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc)
+/* check if idx is a valid index to access PMU */
+int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	bool fixed = pmc & (1u << 30);
-	pmc &= ~(3u << 30);
-	return (!fixed && pmc >= pmu->nr_arch_gp_counters) ||
-		(fixed && pmc >= pmu->nr_arch_fixed_counters);
+	return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx);
 }
 
-int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data)
+int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	bool fast_mode = pmc & (1u << 31);
-	bool fixed = pmc & (1u << 30);
-	struct kvm_pmc *counters;
-	u64 ctr;
-
-	pmc &= ~(3u << 30);
-	if (!fixed && pmc >= pmu->nr_arch_gp_counters)
-		return 1;
-	if (fixed && pmc >= pmu->nr_arch_fixed_counters)
+	bool fast_mode = idx & (1u << 31);
+	struct kvm_pmc *pmc;
+	u64 ctr_val;
+
+	pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx);
+	if (!pmc)
 		return 1;
-	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
-	ctr = read_pmc(&counters[pmc]);
+
+	ctr_val = pmc_read_counter(pmc);
 	if (fast_mode)
-		ctr = (u32)ctr;
-	*data = ctr;
+		ctr_val = (u32)ctr_val;
 
+	*data = ctr_val;
 	return 0;
 }
 
-void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
+void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_cpuid_entry2 *entry;
-	union cpuid10_eax eax;
-	union cpuid10_edx edx;
-
-	pmu->nr_arch_gp_counters = 0;
-	pmu->nr_arch_fixed_counters = 0;
-	pmu->counter_bitmask[KVM_PMC_GP] = 0;
-	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
-	pmu->version = 0;
-	pmu->reserved_bits = 0xffffffff00200000ull;
-
-	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
-	if (!entry)
-		return;
-	eax.full = entry->eax;
-	edx.full = entry->edx;
-
-	pmu->version = eax.split.version_id;
-	if (!pmu->version)
-		return;
-
-	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
-					INTEL_PMC_MAX_GENERIC);
-	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
-	pmu->available_event_types = ~entry->ebx &
-					((1ull << eax.split.mask_length) - 1);
-
-	if (pmu->version == 1) {
-		pmu->nr_arch_fixed_counters = 0;
-	} else {
-		pmu->nr_arch_fixed_counters =
-			min_t(int, edx.split.num_counters_fixed,
-				INTEL_PMC_MAX_FIXED);
-		pmu->counter_bitmask[KVM_PMC_FIXED] =
-			((u64)1 << edx.split.bit_width_fixed) - 1;
-	}
+	if (vcpu->arch.apic)
+		kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC);
+}
 
-	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
-		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
-	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr);
+}
 
-	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
-	if (entry &&
-	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
-	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
-		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+	return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data);
 }
 
-void kvm_pmu_init(struct kvm_vcpu *vcpu)
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
-	int i;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info);
+}
 
-	memset(pmu, 0, sizeof(*pmu));
-	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
-		pmu->gp_counters[i].type = KVM_PMC_GP;
-		pmu->gp_counters[i].vcpu = vcpu;
-		pmu->gp_counters[i].idx = i;
-	}
-	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
-		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
-		pmu->fixed_counters[i].vcpu = vcpu;
-		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
-	}
-	init_irq_work(&pmu->irq_work, trigger_pmi);
-	kvm_pmu_cpuid_update(vcpu);
+/* refresh PMU settings. This function generally is called when underlying
+ * settings are changed (such as changes of PMU CPUID by guest VMs), which
+ * should rarely happen.
+ */
+void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops->pmu_ops->refresh(vcpu);
 }
 
 void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	int i;
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
 	irq_work_sync(&pmu->irq_work);
-	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
-		struct kvm_pmc *pmc = &pmu->gp_counters[i];
-		stop_counter(pmc);
-		pmc->counter = pmc->eventsel = 0;
-	}
+	kvm_x86_ops->pmu_ops->reset(vcpu);
+}
 
-	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
-		stop_counter(&pmu->fixed_counters[i]);
+void kvm_pmu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
-	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
-		pmu->global_ovf_ctrl = 0;
+	memset(pmu, 0, sizeof(*pmu));
+	kvm_x86_ops->pmu_ops->init(vcpu);
+	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
+	kvm_pmu_refresh(vcpu);
 }
 
 void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
 }
-
-void kvm_handle_pmu_event(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	u64 bitmask;
-	int bit;
-
-	bitmask = pmu->reprogram_pmi;
-
-	for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) {
-		struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit);
-
-		if (unlikely(!pmc || !pmc->perf_event)) {
-			clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi);
-			continue;
-		}
-
-		reprogram_idx(pmu, bit);
-	}
-}
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
new file mode 100644
index 000000000000..f96e1f962587
--- /dev/null
+++ b/arch/x86/kvm/pmu.h
@@ -0,0 +1,118 @@
+#ifndef __KVM_X86_PMU_H
+#define __KVM_X86_PMU_H
+
+#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
+#define pmu_to_vcpu(pmu)  (container_of((pmu), struct kvm_vcpu, arch.pmu))
+#define pmc_to_pmu(pmc)   (&(pmc)->vcpu->arch.pmu)
+
+/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */
+#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf)
+
+struct kvm_event_hw_type_mapping {
+	u8 eventsel;
+	u8 unit_mask;
+	unsigned event_type;
+};
+
+struct kvm_pmu_ops {
+	unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select,
+				    u8 unit_mask);
+	unsigned (*find_fixed_event)(int idx);
+	bool (*pmc_is_enabled)(struct kvm_pmc *pmc);
+	struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx);
+	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx);
+	int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
+	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
+	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+	void (*refresh)(struct kvm_vcpu *vcpu);
+	void (*init)(struct kvm_vcpu *vcpu);
+	void (*reset)(struct kvm_vcpu *vcpu);
+};
+
+static inline u64 pmc_bitmask(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	return pmu->counter_bitmask[pmc->type];
+}
+
+static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
+{
+	u64 counter, enabled, running;
+
+	counter = pmc->counter;
+	if (pmc->perf_event)
+		counter += perf_event_read_value(pmc->perf_event,
+						 &enabled, &running);
+	/* FIXME: Scaling needed? */
+	return counter & pmc_bitmask(pmc);
+}
+
+static inline void pmc_stop_counter(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event) {
+		pmc->counter = pmc_read_counter(pmc);
+		perf_event_release_kernel(pmc->perf_event);
+		pmc->perf_event = NULL;
+	}
+}
+
+static inline bool pmc_is_gp(struct kvm_pmc *pmc)
+{
+	return pmc->type == KVM_PMC_GP;
+}
+
+static inline bool pmc_is_fixed(struct kvm_pmc *pmc)
+{
+	return pmc->type == KVM_PMC_FIXED;
+}
+
+static inline bool pmc_is_enabled(struct kvm_pmc *pmc)
+{
+	return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc);
+}
+
+/* returns general purpose PMC with the specified MSR. Note that it can be
+ * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
+ * paramenter to tell them apart.
+ */
+static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
+					 u32 base)
+{
+	if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
+		return &pmu->gp_counters[msr - base];
+
+	return NULL;
+}
+
+/* returns fixed PMC with the specified MSR */
+static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
+{
+	int base = MSR_CORE_PERF_FIXED_CTR0;
+
+	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
+		return &pmu->fixed_counters[msr - base];
+
+	return NULL;
+}
+
+void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
+void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
+void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
+
+void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
+void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
+int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
+int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx);
+bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
+int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
+int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+void kvm_pmu_refresh(struct kvm_vcpu *vcpu);
+void kvm_pmu_reset(struct kvm_vcpu *vcpu);
+void kvm_pmu_init(struct kvm_vcpu *vcpu);
+void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
+
+extern struct kvm_pmu_ops intel_pmu_ops;
+extern struct kvm_pmu_ops amd_pmu_ops;
+#endif /* __KVM_X86_PMU_H */
diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c
new file mode 100644
index 000000000000..886aa25a7131
--- /dev/null
+++ b/arch/x86/kvm/pmu_amd.c
@@ -0,0 +1,207 @@
+/*
+ * KVM PMU support for AMD
+ *
+ * Copyright 2015, Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ *   Wei Huang <wei@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Implementation is based on pmu_intel.c file
+ */
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
+#include "pmu.h"
+
+/* duplicated from amd_perfmon_event_map, K7 and above should work. */
+static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
+	[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
+	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
+	[2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
+	[3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+	[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+	[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+	[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+	[7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
+};
+
+static unsigned amd_find_arch_event(struct kvm_pmu *pmu,
+				    u8 event_select,
+				    u8 unit_mask)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++)
+		if (amd_event_mapping[i].eventsel == event_select
+		    && amd_event_mapping[i].unit_mask == unit_mask)
+			break;
+
+	if (i == ARRAY_SIZE(amd_event_mapping))
+		return PERF_COUNT_HW_MAX;
+
+	return amd_event_mapping[i].event_type;
+}
+
+/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */
+static unsigned amd_find_fixed_event(int idx)
+{
+	return PERF_COUNT_HW_MAX;
+}
+
+/* check if a PMC is enabled by comparing it against global_ctrl bits. Because
+ * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE).
+ */
+static bool amd_pmc_is_enabled(struct kvm_pmc *pmc)
+{
+	return true;
+}
+
+static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
+{
+	return get_gp_pmc(pmu, MSR_K7_EVNTSEL0 + pmc_idx, MSR_K7_EVNTSEL0);
+}
+
+/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
+static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	idx &= ~(3u << 30);
+
+	return (idx >= pmu->nr_arch_gp_counters);
+}
+
+/* idx is the ECX register of RDPMC instruction */
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *counters;
+
+	idx &= ~(3u << 30);
+	if (idx >= pmu->nr_arch_gp_counters)
+		return NULL;
+	counters = pmu->gp_counters;
+
+	return &counters[idx];
+}
+
+static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int ret = false;
+
+	ret = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0) ||
+		get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+
+	return ret;
+}
+
+static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	/* MSR_K7_PERFCTRn */
+	pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
+	if (pmc) {
+		*data = pmc_read_counter(pmc);
+		return 0;
+	}
+	/* MSR_K7_EVNTSELn */
+	pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+	if (pmc) {
+		*data = pmc->eventsel;
+		return 0;
+	}
+
+	return 1;
+}
+
+static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	u32 msr = msr_info->index;
+	u64 data = msr_info->data;
+
+	/* MSR_K7_PERFCTRn */
+	pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0);
+	if (pmc) {
+		if (!msr_info->host_initiated)
+			data = (s64)data;
+		pmc->counter += data - pmc_read_counter(pmc);
+		return 0;
+	}
+	/* MSR_K7_EVNTSELn */
+	pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0);
+	if (pmc) {
+		if (data == pmc->eventsel)
+			return 0;
+		if (!(data & pmu->reserved_bits)) {
+			reprogram_gp_counter(pmc, data);
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
+	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
+	pmu->reserved_bits = 0xffffffff00200000ull;
+	/* not applicable to AMD; but clean them to prevent any fall out */
+	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+	pmu->nr_arch_fixed_counters = 0;
+	pmu->version = 0;
+	pmu->global_status = 0;
+}
+
+static void amd_pmu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int i;
+
+	for (i = 0; i < AMD64_NUM_COUNTERS ; i++) {
+		pmu->gp_counters[i].type = KVM_PMC_GP;
+		pmu->gp_counters[i].vcpu = vcpu;
+		pmu->gp_counters[i].idx = i;
+	}
+}
+
+static void amd_pmu_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int i;
+
+	for (i = 0; i < AMD64_NUM_COUNTERS; i++) {
+		struct kvm_pmc *pmc = &pmu->gp_counters[i];
+
+		pmc_stop_counter(pmc);
+		pmc->counter = pmc->eventsel = 0;
+	}
+}
+
+struct kvm_pmu_ops amd_pmu_ops = {
+	.find_arch_event = amd_find_arch_event,
+	.find_fixed_event = amd_find_fixed_event,
+	.pmc_is_enabled = amd_pmc_is_enabled,
+	.pmc_idx_to_pmc = amd_pmc_idx_to_pmc,
+	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
+	.is_valid_msr_idx = amd_is_valid_msr_idx,
+	.is_valid_msr = amd_is_valid_msr,
+	.get_msr = amd_pmu_get_msr,
+	.set_msr = amd_pmu_set_msr,
+	.refresh = amd_pmu_refresh,
+	.init = amd_pmu_init,
+	.reset = amd_pmu_reset,
+};
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
new file mode 100644
index 000000000000..ab38af4f4947
--- /dev/null
+++ b/arch/x86/kvm/pmu_intel.c
@@ -0,0 +1,358 @@
+/*
+ * KVM PMU support for Intel CPUs
+ *
+ * Copyright 2011 Red Hat, Inc. and/or its affiliates.
+ *
+ * Authors:
+ *   Avi Kivity   <avi@redhat.com>
+ *   Gleb Natapov <gleb@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include <asm/perf_event.h>
+#include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
+#include "pmu.h"
+
+static struct kvm_event_hw_type_mapping intel_arch_events[] = {
+	/* Index must match CPUID 0x0A.EBX bit vector */
+	[0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES },
+	[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
+	[2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES  },
+	[3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES },
+	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
+	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
+	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+};
+
+/* mapping between fixed pmc index and intel_arch_events array */
+static int fixed_pmc_events[] = {1, 0, 7};
+
+static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
+{
+	int i;
+
+	for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+		u8 new_ctrl = fixed_ctrl_field(data, i);
+		u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i);
+		struct kvm_pmc *pmc;
+
+		pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
+
+		if (old_ctrl == new_ctrl)
+			continue;
+
+		reprogram_fixed_counter(pmc, new_ctrl, i);
+	}
+
+	pmu->fixed_ctr_ctrl = data;
+}
+
+/* function is called when global control register has been updated. */
+static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data)
+{
+	int bit;
+	u64 diff = pmu->global_ctrl ^ data;
+
+	pmu->global_ctrl = data;
+
+	for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX)
+		reprogram_counter(pmu, bit);
+}
+
+static unsigned intel_find_arch_event(struct kvm_pmu *pmu,
+				      u8 event_select,
+				      u8 unit_mask)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++)
+		if (intel_arch_events[i].eventsel == event_select
+		    && intel_arch_events[i].unit_mask == unit_mask
+		    && (pmu->available_event_types & (1 << i)))
+			break;
+
+	if (i == ARRAY_SIZE(intel_arch_events))
+		return PERF_COUNT_HW_MAX;
+
+	return intel_arch_events[i].event_type;
+}
+
+static unsigned intel_find_fixed_event(int idx)
+{
+	if (idx >= ARRAY_SIZE(fixed_pmc_events))
+		return PERF_COUNT_HW_MAX;
+
+	return intel_arch_events[fixed_pmc_events[idx]].event_type;
+}
+
+/* check if a PMC is enabled by comparising it with globl_ctrl bits. */
+static bool intel_pmc_is_enabled(struct kvm_pmc *pmc)
+{
+	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+
+	return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl);
+}
+
+static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
+{
+	if (pmc_idx < INTEL_PMC_IDX_FIXED)
+		return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx,
+				  MSR_P6_EVNTSEL0);
+	else {
+		u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED;
+
+		return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0);
+	}
+}
+
+/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
+static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	bool fixed = idx & (1u << 30);
+
+	idx &= ~(3u << 30);
+
+	return (!fixed && idx >= pmu->nr_arch_gp_counters) ||
+		(fixed && idx >= pmu->nr_arch_fixed_counters);
+}
+
+static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu,
+					    unsigned idx)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	bool fixed = idx & (1u << 30);
+	struct kvm_pmc *counters;
+
+	idx &= ~(3u << 30);
+	if (!fixed && idx >= pmu->nr_arch_gp_counters)
+		return NULL;
+	if (fixed && idx >= pmu->nr_arch_fixed_counters)
+		return NULL;
+	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
+
+	return &counters[idx];
+}
+
+static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int ret;
+
+	switch (msr) {
+	case MSR_CORE_PERF_FIXED_CTR_CTRL:
+	case MSR_CORE_PERF_GLOBAL_STATUS:
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+		ret = pmu->version > 1;
+		break;
+	default:
+		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
+			get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
+			get_fixed_pmc(pmu, msr);
+		break;
+	}
+
+	return ret;
+}
+
+static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	switch (msr) {
+	case MSR_CORE_PERF_FIXED_CTR_CTRL:
+		*data = pmu->fixed_ctr_ctrl;
+		return 0;
+	case MSR_CORE_PERF_GLOBAL_STATUS:
+		*data = pmu->global_status;
+		return 0;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		*data = pmu->global_ctrl;
+		return 0;
+	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+		*data = pmu->global_ovf_ctrl;
+		return 0;
+	default:
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+		    (pmc = get_fixed_pmc(pmu, msr))) {
+			*data = pmc_read_counter(pmc);
+			return 0;
+		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
+			*data = pmc->eventsel;
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	u32 msr = msr_info->index;
+	u64 data = msr_info->data;
+
+	switch (msr) {
+	case MSR_CORE_PERF_FIXED_CTR_CTRL:
+		if (pmu->fixed_ctr_ctrl == data)
+			return 0;
+		if (!(data & 0xfffffffffffff444ull)) {
+			reprogram_fixed_counters(pmu, data);
+			return 0;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_STATUS:
+		if (msr_info->host_initiated) {
+			pmu->global_status = data;
+			return 0;
+		}
+		break; /* RO MSR */
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		if (pmu->global_ctrl == data)
+			return 0;
+		if (!(data & pmu->global_ctrl_mask)) {
+			global_ctrl_changed(pmu, data);
+			return 0;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+		if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) {
+			if (!msr_info->host_initiated)
+				pmu->global_status &= ~data;
+			pmu->global_ovf_ctrl = data;
+			return 0;
+		}
+		break;
+	default:
+		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
+		    (pmc = get_fixed_pmc(pmu, msr))) {
+			if (!msr_info->host_initiated)
+				data = (s64)(s32)data;
+			pmc->counter += data - pmc_read_counter(pmc);
+			return 0;
+		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
+			if (data == pmc->eventsel)
+				return 0;
+			if (!(data & pmu->reserved_bits)) {
+				reprogram_gp_counter(pmc, data);
+				return 0;
+			}
+		}
+	}
+
+	return 1;
+}
+
+static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_cpuid_entry2 *entry;
+	union cpuid10_eax eax;
+	union cpuid10_edx edx;
+
+	pmu->nr_arch_gp_counters = 0;
+	pmu->nr_arch_fixed_counters = 0;
+	pmu->counter_bitmask[KVM_PMC_GP] = 0;
+	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+	pmu->version = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
+
+	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+	if (!entry)
+		return;
+	eax.full = entry->eax;
+	edx.full = entry->edx;
+
+	pmu->version = eax.split.version_id;
+	if (!pmu->version)
+		return;
+
+	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
+					INTEL_PMC_MAX_GENERIC);
+	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+	pmu->available_event_types = ~entry->ebx &
+					((1ull << eax.split.mask_length) - 1);
+
+	if (pmu->version == 1) {
+		pmu->nr_arch_fixed_counters = 0;
+	} else {
+		pmu->nr_arch_fixed_counters =
+			min_t(int, edx.split.num_counters_fixed,
+				INTEL_PMC_MAX_FIXED);
+		pmu->counter_bitmask[KVM_PMC_FIXED] =
+			((u64)1 << edx.split.bit_width_fixed) - 1;
+	}
+
+	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
+	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (entry &&
+	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+		pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
+}
+
+static void intel_pmu_init(struct kvm_vcpu *vcpu)
+{
+	int i;
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+		pmu->gp_counters[i].type = KVM_PMC_GP;
+		pmu->gp_counters[i].vcpu = vcpu;
+		pmu->gp_counters[i].idx = i;
+	}
+
+	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
+		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
+		pmu->fixed_counters[i].vcpu = vcpu;
+		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
+	}
+}
+
+static void intel_pmu_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int i;
+
+	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+		struct kvm_pmc *pmc = &pmu->gp_counters[i];
+
+		pmc_stop_counter(pmc);
+		pmc->counter = pmc->eventsel = 0;
+	}
+
+	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++)
+		pmc_stop_counter(&pmu->fixed_counters[i]);
+
+	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
+		pmu->global_ovf_ctrl = 0;
+}
+
+struct kvm_pmu_ops intel_pmu_ops = {
+	.find_arch_event = intel_find_arch_event,
+	.find_fixed_event = intel_find_fixed_event,
+	.pmc_is_enabled = intel_pmc_is_enabled,
+	.pmc_idx_to_pmc = intel_pmc_idx_to_pmc,
+	.msr_idx_to_pmc = intel_msr_idx_to_pmc,
+	.is_valid_msr_idx = intel_is_valid_msr_idx,
+	.is_valid_msr = intel_is_valid_msr,
+	.get_msr = intel_pmu_get_msr,
+	.set_msr = intel_pmu_set_msr,
+	.refresh = intel_pmu_refresh,
+	.init = intel_pmu_init,
+	.reset = intel_pmu_reset,
+};
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ce741b8650f6..851a9a1c6dfc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -21,6 +21,7 @@
 #include "kvm_cache_regs.h"
 #include "x86.h"
 #include "cpuid.h"
+#include "pmu.h"
 
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
@@ -511,8 +512,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0)
+	if (svm->vmcb->control.next_rip != 0) {
+		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
+	}
 
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -1082,7 +1085,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void init_vmcb(struct vcpu_svm *svm)
+static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
@@ -1153,17 +1156,17 @@ static void init_vmcb(struct vcpu_svm *svm)
 	init_sys_seg(&save->ldtr, SEG_TYPE_LDT);
 	init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16);
 
-	svm_set_efer(&svm->vcpu, 0);
+	if (!init_event)
+		svm_set_efer(&svm->vcpu, 0);
 	save->dr6 = 0xffff0ff0;
 	kvm_set_rflags(&svm->vcpu, 2);
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
 
 	/*
-	 * This is the guest-visible cr0 value.
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
+	 * It also updates the guest-visible cr0 value.
 	 */
-	svm->vcpu.arch.cr0 = 0;
 	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
 
 	save->cr4 = X86_CR4_PAE;
@@ -1176,7 +1179,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 		clr_exception_intercept(svm, PF_VECTOR);
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
-		save->g_pat = 0x0007040600070406ULL;
+		save->g_pat = svm->vcpu.arch.pat;
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1195,13 +1198,19 @@ static void init_vmcb(struct vcpu_svm *svm)
 	enable_gif(svm);
 }
 
-static void svm_vcpu_reset(struct kvm_vcpu *vcpu)
+static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 dummy;
 	u32 eax = 1;
 
-	init_vmcb(svm);
+	if (!init_event) {
+		svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+					   MSR_IA32_APICBASE_ENABLE;
+		if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
+			svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+	}
+	init_vmcb(svm, init_event);
 
 	kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, eax);
@@ -1257,12 +1266,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	clear_page(svm->vmcb);
 	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	svm->asid_generation = 0;
-	init_vmcb(svm);
-
-	svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
-				   MSR_IA32_APICBASE_ENABLE;
-	if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
-		svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
+	init_vmcb(svm, false);
 
 	svm_init_osvw(&svm->vcpu);
 
@@ -1575,7 +1579,8 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	 * does not do it - this results in some delay at
 	 * reboot
 	 */
-	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
+	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -1883,7 +1888,7 @@ static int shutdown_interception(struct vcpu_svm *svm)
 	 * so reinitialize it.
 	 */
 	clear_page(svm->vmcb);
-	init_vmcb(svm);
+	init_vmcb(svm, false);
 
 	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
 	return 0;
@@ -1953,8 +1958,8 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
 	u64 pdpte;
 	int ret;
 
-	ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte,
-				  offset_in_page(cr3) + index * 8, 8);
+	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
+				       offset_in_page(cr3) + index * 8, 8);
 	if (ret)
 		return 0;
 	return pdpte;
@@ -2112,7 +2117,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
 
 	might_sleep();
 
-	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
+	page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT);
 	if (is_error_page(page))
 		goto error;
 
@@ -2151,7 +2156,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 	mask = (0xf >> (4 - size)) << start_bit;
 	val = 0;
 
-	if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len))
+	if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len))
 		return NESTED_EXIT_DONE;
 
 	return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
@@ -2176,7 +2181,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 	/* Offset is in 32 bit units but need in 8 bit units */
 	offset *= 4;
 
-	if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+	if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4))
 		return NESTED_EXIT_DONE;
 
 	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
@@ -2447,7 +2452,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 		p      = msrpm_offsets[i];
 		offset = svm->nested.vmcb_msrpm + (p * 4);
 
-		if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+		if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
 			return false;
 
 		svm->nested.msrpm[p] = svm->msrpm[p] | value;
@@ -3067,42 +3072,42 @@ static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 		svm_scale_tsc(vcpu, host_tsc);
 }
 
-static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
+static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	switch (ecx) {
+	switch (msr_info->index) {
 	case MSR_IA32_TSC: {
-		*data = svm->vmcb->control.tsc_offset +
+		msr_info->data = svm->vmcb->control.tsc_offset +
 			svm_scale_tsc(vcpu, native_read_tsc());
 
 		break;
 	}
 	case MSR_STAR:
-		*data = svm->vmcb->save.star;
+		msr_info->data = svm->vmcb->save.star;
 		break;
 #ifdef CONFIG_X86_64
 	case MSR_LSTAR:
-		*data = svm->vmcb->save.lstar;
+		msr_info->data = svm->vmcb->save.lstar;
 		break;
 	case MSR_CSTAR:
-		*data = svm->vmcb->save.cstar;
+		msr_info->data = svm->vmcb->save.cstar;
 		break;
 	case MSR_KERNEL_GS_BASE:
-		*data = svm->vmcb->save.kernel_gs_base;
+		msr_info->data = svm->vmcb->save.kernel_gs_base;
 		break;
 	case MSR_SYSCALL_MASK:
-		*data = svm->vmcb->save.sfmask;
+		msr_info->data = svm->vmcb->save.sfmask;
 		break;
 #endif
 	case MSR_IA32_SYSENTER_CS:
-		*data = svm->vmcb->save.sysenter_cs;
+		msr_info->data = svm->vmcb->save.sysenter_cs;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
-		*data = svm->sysenter_eip;
+		msr_info->data = svm->sysenter_eip;
 		break;
 	case MSR_IA32_SYSENTER_ESP:
-		*data = svm->sysenter_esp;
+		msr_info->data = svm->sysenter_esp;
 		break;
 	/*
 	 * Nobody will change the following 5 values in the VMCB so we can
@@ -3110,31 +3115,31 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	 * implemented.
 	 */
 	case MSR_IA32_DEBUGCTLMSR:
-		*data = svm->vmcb->save.dbgctl;
+		msr_info->data = svm->vmcb->save.dbgctl;
 		break;
 	case MSR_IA32_LASTBRANCHFROMIP:
-		*data = svm->vmcb->save.br_from;
+		msr_info->data = svm->vmcb->save.br_from;
 		break;
 	case MSR_IA32_LASTBRANCHTOIP:
-		*data = svm->vmcb->save.br_to;
+		msr_info->data = svm->vmcb->save.br_to;
 		break;
 	case MSR_IA32_LASTINTFROMIP:
-		*data = svm->vmcb->save.last_excp_from;
+		msr_info->data = svm->vmcb->save.last_excp_from;
 		break;
 	case MSR_IA32_LASTINTTOIP:
-		*data = svm->vmcb->save.last_excp_to;
+		msr_info->data = svm->vmcb->save.last_excp_to;
 		break;
 	case MSR_VM_HSAVE_PA:
-		*data = svm->nested.hsave_msr;
+		msr_info->data = svm->nested.hsave_msr;
 		break;
 	case MSR_VM_CR:
-		*data = svm->nested.vm_cr_msr;
+		msr_info->data = svm->nested.vm_cr_msr;
 		break;
 	case MSR_IA32_UCODE_REV:
-		*data = 0x01000065;
+		msr_info->data = 0x01000065;
 		break;
 	default:
-		return kvm_get_msr_common(vcpu, ecx, data);
+		return kvm_get_msr_common(vcpu, msr_info);
 	}
 	return 0;
 }
@@ -3142,16 +3147,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 static int rdmsr_interception(struct vcpu_svm *svm)
 {
 	u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
-	u64 data;
+	struct msr_data msr_info;
 
-	if (svm_get_msr(&svm->vcpu, ecx, &data)) {
+	msr_info.index = ecx;
+	msr_info.host_initiated = false;
+	if (svm_get_msr(&svm->vcpu, &msr_info)) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(&svm->vcpu, 0);
 	} else {
-		trace_kvm_msr_read(ecx, data);
+		trace_kvm_msr_read(ecx, msr_info.data);
 
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff);
-		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32);
+		kvm_register_write(&svm->vcpu, VCPU_REGS_RAX,
+				   msr_info.data & 0xffffffff);
+		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
+				   msr_info.data >> 32);
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 		skip_emulated_instruction(&svm->vcpu);
 	}
@@ -3388,6 +3397,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
+	[SVM_EXIT_RSM]                          = emulate_on_interception,
 };
 
 static void dump_vmcb(struct kvm_vcpu *vcpu)
@@ -4073,6 +4083,11 @@ static bool svm_cpu_has_accelerated_tpr(void)
 	return false;
 }
 
+static bool svm_has_high_real_mode_segbase(void)
+{
+	return true;
+}
+
 static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
 	return 0;
@@ -4317,7 +4332,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	vmcb->control.next_rip  = info->next_rip;
+	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+	if (static_cpu_has(X86_FEATURE_NRIPS))
+		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
 	vmexit = nested_svm_exit_handled(svm);
 
@@ -4346,6 +4363,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.hardware_enable = svm_hardware_enable,
 	.hardware_disable = svm_hardware_disable,
 	.cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr,
+	.cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase,
 
 	.vcpu_create = svm_create_vcpu,
 	.vcpu_free = svm_free_vcpu,
@@ -4381,6 +4399,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.fpu_activate = svm_fpu_activate,
 	.fpu_deactivate = svm_fpu_deactivate,
 
 	.tlb_flush = svm_flush_tlb,
@@ -4439,6 +4458,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.handle_external_intr = svm_handle_external_intr,
 
 	.sched_in = svm_sched_in,
+
+	.pmu_ops = &amd_pmu_ops,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 7c7bc8bef21f..4eae7c35ddf5 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -952,6 +952,28 @@ TRACE_EVENT(kvm_wait_lapic_expire,
 		  __entry->delta < 0 ? "early" : "late")
 );
 
+TRACE_EVENT(kvm_enter_smm,
+	TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering),
+	TP_ARGS(vcpu_id, smbase, entering),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+		__field(	u64,		smbase		)
+		__field(	bool,		entering	)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+		__entry->smbase		= smbase;
+		__entry->entering	= entering;
+	),
+
+	TP_printk("vcpu %u: %s SMM, smbase 0x%llx",
+		  __entry->vcpu_id,
+		  __entry->entering ? "entering" : "leaving",
+		  __entry->smbase)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b61687bd79..ab53d80b0f64 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -40,14 +40,14 @@
 #include <asm/vmx.h>
 #include <asm/virtext.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/xcr.h>
+#include <asm/fpu/internal.h>
 #include <asm/perf_event.h>
 #include <asm/debugreg.h>
 #include <asm/kexec.h>
 #include <asm/apic.h>
 
 #include "trace.h"
+#include "pmu.h"
 
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 #define __ex_clear(x, reg) \
@@ -786,7 +786,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 
 static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
 {
-	struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
+	struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT);
 	if (is_error_page(page))
 		return NULL;
 
@@ -1883,7 +1883,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 	 * If the FPU is not active (through the host task or
 	 * the guest vcpu), then restore the cr0.TS bit.
 	 */
-	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+	if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded)
 		stts();
 	load_gdt(this_cpu_ptr(&host_gdt));
 }
@@ -2170,8 +2170,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 
 	if (is_guest_mode(vcpu))
 		msr_bitmap = vmx_msr_bitmap_nested;
-	else if (irqchip_in_kernel(vcpu->kvm) &&
-		apic_x2apic_mode(vcpu->arch.apic)) {
+	else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -2623,76 +2622,69 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
-	u64 data;
 	struct shared_msr_entry *msr;
 
-	if (!pdata) {
-		printk(KERN_ERR "BUG: get_msr called with NULL pdata\n");
-		return -EINVAL;
-	}
-
-	switch (msr_index) {
+	switch (msr_info->index) {
 #ifdef CONFIG_X86_64
 	case MSR_FS_BASE:
-		data = vmcs_readl(GUEST_FS_BASE);
+		msr_info->data = vmcs_readl(GUEST_FS_BASE);
 		break;
 	case MSR_GS_BASE:
-		data = vmcs_readl(GUEST_GS_BASE);
+		msr_info->data = vmcs_readl(GUEST_GS_BASE);
 		break;
 	case MSR_KERNEL_GS_BASE:
 		vmx_load_host_state(to_vmx(vcpu));
-		data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
+		msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base;
 		break;
 #endif
 	case MSR_EFER:
-		return kvm_get_msr_common(vcpu, msr_index, pdata);
+		return kvm_get_msr_common(vcpu, msr_info);
 	case MSR_IA32_TSC:
-		data = guest_read_tsc();
+		msr_info->data = guest_read_tsc();
 		break;
 	case MSR_IA32_SYSENTER_CS:
-		data = vmcs_read32(GUEST_SYSENTER_CS);
+		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
 	case MSR_IA32_SYSENTER_EIP:
-		data = vmcs_readl(GUEST_SYSENTER_EIP);
+		msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP);
 		break;
 	case MSR_IA32_SYSENTER_ESP:
-		data = vmcs_readl(GUEST_SYSENTER_ESP);
+		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
 		if (!vmx_mpx_supported())
 			return 1;
-		data = vmcs_read64(GUEST_BNDCFGS);
+		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
 	case MSR_IA32_FEATURE_CONTROL:
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
-		data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+		msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
 		break;
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
 		if (!nested_vmx_allowed(vcpu))
 			return 1;
-		return vmx_get_vmx_msr(vcpu, msr_index, pdata);
+		return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data);
 	case MSR_IA32_XSS:
 		if (!vmx_xsaves_supported())
 			return 1;
-		data = vcpu->arch.ia32_xss;
+		msr_info->data = vcpu->arch.ia32_xss;
 		break;
 	case MSR_TSC_AUX:
 		if (!to_vmx(vcpu)->rdtscp_enabled)
 			return 1;
 		/* Otherwise falls through */
 	default:
-		msr = find_msr_entry(to_vmx(vcpu), msr_index);
+		msr = find_msr_entry(to_vmx(vcpu), msr_info->index);
 		if (msr) {
-			data = msr->data;
+			msr_info->data = msr->data;
 			break;
 		}
-		return kvm_get_msr_common(vcpu, msr_index, pdata);
+		return kvm_get_msr_common(vcpu, msr_info);
 	}
 
-	*pdata = data;
 	return 0;
 }
 
@@ -4123,7 +4115,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	kvm_userspace_mem.flags = 0;
 	kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
 	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
 	if (r)
 		goto out;
 
@@ -4158,7 +4150,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	kvm_userspace_mem.guest_phys_addr =
 		kvm->arch.ept_identity_map_addr;
 	kvm_userspace_mem.memory_size = PAGE_SIZE;
-	r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
+	r = __x86_set_memory_region(kvm, &kvm_userspace_mem);
 
 	return r;
 }
@@ -4667,16 +4659,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
 	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
 
-	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
-		u32 msr_low, msr_high;
-		u64 host_pat;
-		rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high);
-		host_pat = msr_low | ((u64) msr_high << 32);
-		/* Write the default value follow host pat */
-		vmcs_write64(GUEST_IA32_PAT, host_pat);
-		/* Keep arch.pat sync with GUEST_IA32_PAT */
-		vmx->vcpu.arch.pat = host_pat;
-	}
+	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
 	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
 		u32 index = vmx_msr_index[i];
@@ -4708,22 +4692,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	return 0;
 }
 
-static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct msr_data apic_base_msr;
+	u64 cr0;
 
 	vmx->rmode.vm86_active = 0;
 
 	vmx->soft_vnmi_blocked = 0;
 
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
-	kvm_set_cr8(&vmx->vcpu, 0);
-	apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
-	if (kvm_vcpu_is_reset_bsp(&vmx->vcpu))
-		apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
-	apic_base_msr.host_initiated = true;
-	kvm_set_apic_base(&vmx->vcpu, &apic_base_msr);
+	kvm_set_cr8(vcpu, 0);
+
+	if (!init_event) {
+		apic_base_msr.data = APIC_DEFAULT_PHYS_BASE |
+				     MSR_IA32_APICBASE_ENABLE;
+		if (kvm_vcpu_is_reset_bsp(vcpu))
+			apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+		apic_base_msr.host_initiated = true;
+		kvm_set_apic_base(vcpu, &apic_base_msr);
+	}
 
 	vmx_segment_cache_clear(vmx);
 
@@ -4747,9 +4736,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_LDTR_LIMIT, 0xffff);
 	vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082);
 
-	vmcs_write32(GUEST_SYSENTER_CS, 0);
-	vmcs_writel(GUEST_SYSENTER_ESP, 0);
-	vmcs_writel(GUEST_SYSENTER_EIP, 0);
+	if (!init_event) {
+		vmcs_write32(GUEST_SYSENTER_CS, 0);
+		vmcs_writel(GUEST_SYSENTER_ESP, 0);
+		vmcs_writel(GUEST_SYSENTER_EIP, 0);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+	}
 
 	vmcs_writel(GUEST_RFLAGS, 0x02);
 	kvm_rip_write(vcpu, 0xfff0);
@@ -4764,18 +4756,15 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
 	vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
 
-	/* Special registers */
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
-
 	setup_msrs(vmx);
 
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */
 
-	if (cpu_has_vmx_tpr_shadow()) {
+	if (cpu_has_vmx_tpr_shadow() && !init_event) {
 		vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
-		if (vm_need_tpr_shadow(vmx->vcpu.kvm))
+		if (vm_need_tpr_shadow(vcpu->kvm))
 			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
-				     __pa(vmx->vcpu.arch.apic->regs));
+				     __pa(vcpu->arch.apic->regs));
 		vmcs_write32(TPR_THRESHOLD, 0);
 	}
 
@@ -4787,12 +4776,14 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	if (vmx->vpid != 0)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 
-	vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
-	vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
-	vmx_set_cr4(&vmx->vcpu, 0);
-	vmx_set_efer(&vmx->vcpu, 0);
-	vmx_fpu_activate(&vmx->vcpu);
-	update_exception_bitmap(&vmx->vcpu);
+	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+	vmx_set_cr0(vcpu, cr0); /* enter rmode */
+	vmx->vcpu.arch.cr0 = cr0;
+	vmx_set_cr4(vcpu, 0);
+	if (!init_event)
+		vmx_set_efer(vcpu, 0);
+	vmx_fpu_activate(vcpu);
+	update_exception_bitmap(vcpu);
 
 	vpid_sync_context(vmx);
 }
@@ -4965,7 +4956,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 		.flags = 0,
 	};
 
-	ret = kvm_set_memory_region(kvm, &tss_mem);
+	ret = x86_set_memory_region(kvm, &tss_mem);
 	if (ret)
 		return ret;
 	kvm->arch.tss_addr = addr;
@@ -5475,19 +5466,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu)
 static int handle_rdmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX];
-	u64 data;
+	struct msr_data msr_info;
 
-	if (vmx_get_msr(vcpu, ecx, &data)) {
+	msr_info.index = ecx;
+	msr_info.host_initiated = false;
+	if (vmx_get_msr(vcpu, &msr_info)) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
 
-	trace_kvm_msr_read(ecx, data);
+	trace_kvm_msr_read(ecx, msr_info.data);
 
 	/* FIXME: handling of bits 32:63 of rax, rdx */
-	vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u;
-	vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u;
+	vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u;
+	vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u;
 	skip_emulated_instruction(vcpu);
 	return 1;
 }
@@ -5710,9 +5703,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	/* clear all local breakpoint enable flags */
-	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155);
-
 	/*
 	 * TODO: What about debug traps on tss switch?
 	 *       Are we supposed to inject them and update dr6?
@@ -7333,7 +7323,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
 		bitmap += (port & 0x7fff) / 8;
 
 		if (last_bitmap != bitmap)
-			if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1))
+			if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1))
 				return true;
 		if (b & (1 << (port & 7)))
 			return true;
@@ -7377,7 +7367,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
 	/* Then read the msr_index'th bit from this bitmap: */
 	if (msr_index < 1024*8) {
 		unsigned char b;
-		if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1))
+		if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1))
 			return true;
 		return 1 & (b >> (msr_index & 7));
 	} else
@@ -7642,9 +7632,9 @@ static void vmx_disable_pml(struct vcpu_vmx *vmx)
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
 }
 
-static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx)
+static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = vmx->vcpu.kvm;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u64 *pml_buf;
 	u16 pml_idx;
 
@@ -7666,7 +7656,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx)
 
 		gpa = pml_buf[pml_idx];
 		WARN_ON(gpa & (PAGE_SIZE - 1));
-		mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+		kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
 	}
 
 	/* reset PML index */
@@ -7691,6 +7681,158 @@ static void kvm_flush_pml_buffers(struct kvm *kvm)
 		kvm_vcpu_kick(vcpu);
 }
 
+static void vmx_dump_sel(char *name, uint32_t sel)
+{
+	pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n",
+	       name, vmcs_read32(sel),
+	       vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR),
+	       vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR),
+	       vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR));
+}
+
+static void vmx_dump_dtsel(char *name, uint32_t limit)
+{
+	pr_err("%s                           limit=0x%08x, base=0x%016lx\n",
+	       name, vmcs_read32(limit),
+	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
+}
+
+static void dump_vmcs(void)
+{
+	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
+	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
+	u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
+	u32 secondary_exec_control = 0;
+	unsigned long cr4 = vmcs_readl(GUEST_CR4);
+	u64 efer = vmcs_readl(GUEST_IA32_EFER);
+	int i, n;
+
+	if (cpu_has_secondary_exec_ctrls())
+		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+
+	pr_err("*** Guest State ***\n");
+	pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+	       vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW),
+	       vmcs_readl(CR0_GUEST_HOST_MASK));
+	pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
+	       cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
+	pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
+	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
+	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
+	{
+		pr_err("PDPTR0 = 0x%016lx  PDPTR1 = 0x%016lx\n",
+		       vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1));
+		pr_err("PDPTR2 = 0x%016lx  PDPTR3 = 0x%016lx\n",
+		       vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3));
+	}
+	pr_err("RSP = 0x%016lx  RIP = 0x%016lx\n",
+	       vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP));
+	pr_err("RFLAGS=0x%08lx         DR7 = 0x%016lx\n",
+	       vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7));
+	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+	       vmcs_readl(GUEST_SYSENTER_ESP),
+	       vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP));
+	vmx_dump_sel("CS:  ", GUEST_CS_SELECTOR);
+	vmx_dump_sel("DS:  ", GUEST_DS_SELECTOR);
+	vmx_dump_sel("SS:  ", GUEST_SS_SELECTOR);
+	vmx_dump_sel("ES:  ", GUEST_ES_SELECTOR);
+	vmx_dump_sel("FS:  ", GUEST_FS_SELECTOR);
+	vmx_dump_sel("GS:  ", GUEST_GS_SELECTOR);
+	vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT);
+	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
+	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
+	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
+	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
+	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
+		pr_err("EFER =     0x%016llx  PAT = 0x%016lx\n",
+		       efer, vmcs_readl(GUEST_IA32_PAT));
+	pr_err("DebugCtl = 0x%016lx  DebugExceptions = 0x%016lx\n",
+	       vmcs_readl(GUEST_IA32_DEBUGCTL),
+	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
+	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+		pr_err("PerfGlobCtl = 0x%016lx\n",
+		       vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL));
+	if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS)
+		pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS));
+	pr_err("Interruptibility = %08x  ActivityState = %08x\n",
+	       vmcs_read32(GUEST_INTERRUPTIBILITY_INFO),
+	       vmcs_read32(GUEST_ACTIVITY_STATE));
+	if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
+		pr_err("InterruptStatus = %04x\n",
+		       vmcs_read16(GUEST_INTR_STATUS));
+
+	pr_err("*** Host State ***\n");
+	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
+	       vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
+	pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n",
+	       vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR),
+	       vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR),
+	       vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR),
+	       vmcs_read16(HOST_TR_SELECTOR));
+	pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n",
+	       vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE),
+	       vmcs_readl(HOST_TR_BASE));
+	pr_err("GDTBase=%016lx IDTBase=%016lx\n",
+	       vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE));
+	pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n",
+	       vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3),
+	       vmcs_readl(HOST_CR4));
+	pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n",
+	       vmcs_readl(HOST_IA32_SYSENTER_ESP),
+	       vmcs_read32(HOST_IA32_SYSENTER_CS),
+	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
+	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
+		pr_err("EFER = 0x%016lx  PAT = 0x%016lx\n",
+		       vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT));
+	if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+		pr_err("PerfGlobCtl = 0x%016lx\n",
+		       vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL));
+
+	pr_err("*** Control State ***\n");
+	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
+	       pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control);
+	pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl);
+	pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n",
+	       vmcs_read32(EXCEPTION_BITMAP),
+	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK),
+	       vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH));
+	pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n",
+	       vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
+	       vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE),
+	       vmcs_read32(VM_ENTRY_INSTRUCTION_LEN));
+	pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n",
+	       vmcs_read32(VM_EXIT_INTR_INFO),
+	       vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
+	       vmcs_read32(VM_EXIT_INSTRUCTION_LEN));
+	pr_err("        reason=%08x qualification=%016lx\n",
+	       vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION));
+	pr_err("IDTVectoring: info=%08x errcode=%08x\n",
+	       vmcs_read32(IDT_VECTORING_INFO_FIELD),
+	       vmcs_read32(IDT_VECTORING_ERROR_CODE));
+	pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET));
+	if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW)
+		pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD));
+	if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR)
+		pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV));
+	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT))
+		pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER));
+	n = vmcs_read32(CR3_TARGET_COUNT);
+	for (i = 0; i + 1 < n; i += 4)
+		pr_err("CR3 target%u=%016lx target%u=%016lx\n",
+		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2),
+		       i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2));
+	if (i < n)
+		pr_err("CR3 target%u=%016lx\n",
+		       i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2));
+	if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+		pr_err("PLE Gap=%08x Window=%08x\n",
+		       vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW));
+	if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID)
+		pr_err("Virtual processor ID = 0x%04x\n",
+		       vmcs_read16(VIRTUAL_PROCESSOR_ID));
+}
+
 /*
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
@@ -7709,7 +7851,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	 * flushed already.
 	 */
 	if (enable_pml)
-		vmx_flush_pml_buffer(vmx);
+		vmx_flush_pml_buffer(vcpu);
 
 	/* If guest state is invalid, start emulating */
 	if (vmx->emulation_required)
@@ -7723,6 +7865,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 
 	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
+		dump_vmcs();
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		vcpu->run->fail_entry.hardware_entry_failure_reason
 			= exit_reason;
@@ -7996,6 +8139,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 		local_irq_enable();
 }
 
+static bool vmx_has_high_real_mode_segbase(void)
+{
+	return enable_unrestricted_guest || emulate_invalid_guest_state;
+}
+
 static bool vmx_mpx_supported(void)
 {
 	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) &&
@@ -8480,7 +8628,8 @@ static int get_ept_level(void)
 
 static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
-	u64 ret;
+	u8 cache;
+	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
 	 * 1. MMIO: always map as UC
@@ -8493,16 +8642,27 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (is_mmio)
-		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
-		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
-		      VMX_EPT_MT_EPTE_SHIFT;
-	else
-		ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT)
-			| VMX_EPT_IPAT_BIT;
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
 
-	return ret;
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+		ipat = VMX_EPT_IPAT_BIT;
+		cache = MTRR_TYPE_WRBACK;
+		goto exit;
+	}
+
+	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
+		ipat = VMX_EPT_IPAT_BIT;
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+
+exit:
+	return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
 }
 
 static int vmx_get_lpage_level(void)
@@ -8924,7 +9084,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
 				       struct vmx_msr_entry *e)
 {
 	/* x2APIC MSR accesses are not allowed */
-	if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8)
+	if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
 		return -EINVAL;
 	if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
 	    e->index == MSR_IA32_UCODE_REV)
@@ -8966,8 +9126,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 
 	msr.host_initiated = false;
 	for (i = 0; i < count; i++) {
-		if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e),
-				   &e, sizeof(e))) {
+		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
+					&e, sizeof(e))) {
 			pr_warn_ratelimited(
 				"%s cannot read MSR entry (%u, 0x%08llx)\n",
 				__func__, i, gpa + i * sizeof(e));
@@ -8999,9 +9159,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	struct vmx_msr_entry e;
 
 	for (i = 0; i < count; i++) {
-		if (kvm_read_guest(vcpu->kvm,
-				   gpa + i * sizeof(e),
-				   &e, 2 * sizeof(u32))) {
+		struct msr_data msr_info;
+		if (kvm_vcpu_read_guest(vcpu,
+					gpa + i * sizeof(e),
+					&e, 2 * sizeof(u32))) {
 			pr_warn_ratelimited(
 				"%s cannot read MSR entry (%u, 0x%08llx)\n",
 				__func__, i, gpa + i * sizeof(e));
@@ -9013,19 +9174,21 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 				__func__, i, e.index, e.reserved);
 			return -EINVAL;
 		}
-		if (kvm_get_msr(vcpu, e.index, &e.value)) {
+		msr_info.host_initiated = false;
+		msr_info.index = e.index;
+		if (kvm_get_msr(vcpu, &msr_info)) {
 			pr_warn_ratelimited(
 				"%s cannot read MSR (%u, 0x%x)\n",
 				__func__, i, e.index);
 			return -EINVAL;
 		}
-		if (kvm_write_guest(vcpu->kvm,
-				    gpa + i * sizeof(e) +
-					offsetof(struct vmx_msr_entry, value),
-				    &e.value, sizeof(e.value))) {
+		if (kvm_vcpu_write_guest(vcpu,
+					 gpa + i * sizeof(e) +
+					     offsetof(struct vmx_msr_entry, value),
+					 &msr_info.data, sizeof(msr_info.data))) {
 			pr_warn_ratelimited(
 				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
-				__func__, i, e.index, e.value);
+				__func__, i, e.index, msr_info.data);
 			return -EINVAL;
 		}
 	}
@@ -10150,6 +10313,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
+	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
 
 	.vcpu_create = vmx_create_vcpu,
 	.vcpu_free = vmx_free_vcpu,
@@ -10185,6 +10349,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
+	.fpu_activate = vmx_fpu_activate,
 	.fpu_deactivate = vmx_fpu_deactivate,
 
 	.tlb_flush = vmx_flush_tlb,
@@ -10254,6 +10419,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
 	.flush_log_dirty = vmx_flush_log_dirty,
 	.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+
+	.pmu_ops = &intel_pmu_ops,
 };
 
 static int __init vmx_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c73efcd03e29..ac165c2fb8e5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -28,6 +28,7 @@
 #include "x86.h"
 #include "cpuid.h"
 #include "assigned-dev.h"
+#include "pmu.h"
 
 #include <linux/clocksource.h>
 #include <linux/interrupt.h>
@@ -57,11 +58,9 @@
 #include <asm/debugreg.h>
 #include <asm/msr.h>
 #include <asm/desc.h>
-#include <asm/mtrr.h>
 #include <asm/mce.h>
-#include <asm/i387.h>
-#include <asm/fpu-internal.h> /* Ugh! */
-#include <asm/xcr.h>
+#include <linux/kernel_stat.h>
+#include <asm/fpu/internal.h> /* Ugh! */
 #include <asm/pvclock.h>
 #include <asm/div64.h>
 
@@ -99,6 +98,9 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 unsigned int min_timer_period_us = 500;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
+static bool __read_mostly kvmclock_periodic_sync = true;
+module_param(kvmclock_periodic_sync, bool, S_IRUGO);
+
 bool kvm_has_tsc_control;
 EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
 u32  kvm_max_guest_tsc_khz;
@@ -475,7 +477,7 @@ EXPORT_SYMBOL_GPL(kvm_require_dr);
 
 /*
  * This function will be used to read from the physical memory of the currently
- * running guest. The difference to kvm_read_guest_page is that this function
+ * running guest. The difference to kvm_vcpu_read_guest_page is that this function
  * can read from guest physical or from the guest's guest physical memory.
  */
 int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
@@ -493,7 +495,7 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 	real_gfn = gpa_to_gfn(real_gfn);
 
-	return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len);
+	return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);
 
@@ -572,8 +574,7 @@ out:
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	unsigned long old_cr0 = kvm_read_cr0(vcpu);
-	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
-				    X86_CR0_CD | X86_CR0_NW;
+	unsigned long update_bits = X86_CR0_PG | X86_CR0_WP;
 
 	cr0 |= X86_CR0_ET;
 
@@ -619,6 +620,10 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if ((cr0 ^ old_cr0) & update_bits)
 		kvm_mmu_reset_context(vcpu);
+
+	if ((cr0 ^ old_cr0) & X86_CR0_CD)
+		kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr0);
@@ -702,8 +707,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
-				   X86_CR4_PAE | X86_CR4_SMEP;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP;
+
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
@@ -744,9 +750,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
-		update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
 	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
 		kvm_update_cpuid(vcpu);
 
@@ -910,7 +913,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu)
 	u64 data;
 	int err;
 
-	err = kvm_pmu_read_pmc(vcpu, ecx, &data);
+	err = kvm_pmu_rdpmc(vcpu, ecx, &data);
 	if (err)
 		return err;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
@@ -925,17 +928,11 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
  *
  * This list is modified at module load time to reflect the
  * capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in the beginning of the list.
+ * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * may depend on host virtualization features rather than host cpu features.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	12
 static u32 msrs_to_save[] = {
-	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
-	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
-	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
-	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
-	MSR_KVM_PV_EOI_EN,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_STAR,
 #ifdef CONFIG_X86_64
@@ -947,14 +944,24 @@ static u32 msrs_to_save[] = {
 
 static unsigned num_msrs_to_save;
 
-static const u32 emulated_msrs[] = {
+static u32 emulated_msrs[] = {
+	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
+	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC,
+	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
+	MSR_KVM_PV_EOI_EN,
+
 	MSR_IA32_TSC_ADJUST,
 	MSR_IA32_TSCDEADLINE,
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
+	MSR_IA32_SMBASE,
 };
 
+static unsigned num_emulated_msrs;
+
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits)
@@ -1048,6 +1055,21 @@ EXPORT_SYMBOL_GPL(kvm_set_msr);
 /*
  * Adapt set_msr() to msr_io()'s calling convention
  */
+static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
+{
+	struct msr_data msr;
+	int r;
+
+	msr.index = index;
+	msr.host_initiated = true;
+	r = kvm_get_msr(vcpu, &msr);
+	if (r)
+		return r;
+
+	*data = msr.data;
+	return 0;
+}
+
 static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 {
 	struct msr_data msr;
@@ -1700,6 +1722,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->pvclock_set_guest_stopped_request = false;
 	}
 
+	pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
+
 	/* If the host uses TSC clocksource, then it is stable */
 	if (use_master_clock)
 		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -1770,127 +1794,14 @@ static void kvmclock_sync_fn(struct work_struct *work)
 					   kvmclock_sync_work);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
 
+	if (!kvmclock_periodic_sync)
+		return;
+
 	schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0);
 	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
 					KVMCLOCK_SYNC_PERIOD);
 }
 
-static bool msr_mtrr_valid(unsigned msr)
-{
-	switch (msr) {
-	case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1:
-	case MSR_MTRRfix64K_00000:
-	case MSR_MTRRfix16K_80000:
-	case MSR_MTRRfix16K_A0000:
-	case MSR_MTRRfix4K_C0000:
-	case MSR_MTRRfix4K_C8000:
-	case MSR_MTRRfix4K_D0000:
-	case MSR_MTRRfix4K_D8000:
-	case MSR_MTRRfix4K_E0000:
-	case MSR_MTRRfix4K_E8000:
-	case MSR_MTRRfix4K_F0000:
-	case MSR_MTRRfix4K_F8000:
-	case MSR_MTRRdefType:
-	case MSR_IA32_CR_PAT:
-		return true;
-	case 0x2f8:
-		return true;
-	}
-	return false;
-}
-
-static bool valid_pat_type(unsigned t)
-{
-	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
-}
-
-static bool valid_mtrr_type(unsigned t)
-{
-	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
-}
-
-bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	int i;
-	u64 mask;
-
-	if (!msr_mtrr_valid(msr))
-		return false;
-
-	if (msr == MSR_IA32_CR_PAT) {
-		for (i = 0; i < 8; i++)
-			if (!valid_pat_type((data >> (i * 8)) & 0xff))
-				return false;
-		return true;
-	} else if (msr == MSR_MTRRdefType) {
-		if (data & ~0xcff)
-			return false;
-		return valid_mtrr_type(data & 0xff);
-	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
-		for (i = 0; i < 8 ; i++)
-			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
-				return false;
-		return true;
-	}
-
-	/* variable MTRRs */
-	WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
-
-	mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
-	if ((msr & 1) == 0) {
-		/* MTRR base */
-		if (!valid_mtrr_type(data & 0xff))
-			return false;
-		mask |= 0xf00;
-	} else
-		/* MTRR mask */
-		mask |= 0x7ff;
-	if (data & mask) {
-		kvm_inject_gp(vcpu, 0);
-		return false;
-	}
-
-	return true;
-}
-EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
-
-static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
-{
-	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
-
-	if (!kvm_mtrr_valid(vcpu, msr, data))
-		return 1;
-
-	if (msr == MSR_MTRRdefType) {
-		vcpu->arch.mtrr_state.def_type = data;
-		vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10;
-	} else if (msr == MSR_MTRRfix64K_00000)
-		p[0] = data;
-	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
-		p[1 + msr - MSR_MTRRfix16K_80000] = data;
-	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
-		p[3 + msr - MSR_MTRRfix4K_C0000] = data;
-	else if (msr == MSR_IA32_CR_PAT)
-		vcpu->arch.pat = data;
-	else {	/* Variable MTRRs */
-		int idx, is_mtrr_mask;
-		u64 *pt;
-
-		idx = (msr - 0x200) / 2;
-		is_mtrr_mask = msr - 0x200 - 2 * idx;
-		if (!is_mtrr_mask)
-			pt =
-			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
-		else
-			pt =
-			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
-		*pt = data;
-	}
-
-	kvm_mmu_reset_context(vcpu);
-	return 0;
-}
-
 static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	u64 mcg_cap = vcpu->arch.mcg_cap;
@@ -1949,7 +1860,7 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
 		r = PTR_ERR(page);
 		goto out;
 	}
-	if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
+	if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE))
 		goto out_free;
 	r = 0;
 out_free:
@@ -2049,13 +1960,13 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			break;
 		}
 		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
-		addr = gfn_to_hva(vcpu->kvm, gfn);
+		addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
 		if (kvm_is_error_hva(addr))
 			return 1;
 		if (__clear_user((void __user *)addr, PAGE_SIZE))
 			return 1;
 		vcpu->arch.hv_vapic = data;
-		mark_page_dirty(vcpu->kvm, gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
 		if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
 			return 1;
 		break;
@@ -2182,7 +2093,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			    __func__, data);
 		break;
 	case 0x200 ... 0x2ff:
-		return set_msr_mtrr(vcpu, msr, data);
+		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
 	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
@@ -2202,6 +2113,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MISC_ENABLE:
 		vcpu->arch.ia32_misc_enable_msr = data;
 		break;
+	case MSR_IA32_SMBASE:
+		if (!msr_info->host_initiated)
+			return 1;
+		vcpu->arch.smbase = data;
+		break;
 	case MSR_KVM_WALL_CLOCK_NEW:
 	case MSR_KVM_WALL_CLOCK:
 		vcpu->kvm->arch.wall_clock = data;
@@ -2222,6 +2138,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					&vcpu->requests);
 
 			ka->boot_vcpu_runs_old_kvmclock = tmp;
+
+			ka->kvmclock_offset = -get_kernel_ns();
 		}
 
 		vcpu->arch.time = data;
@@ -2283,37 +2201,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
 		return set_msr_mce(vcpu, msr, data);
 
-	/* Performance counters are not protected by a CPUID bit,
-	 * so we should check all of them in the generic path for the sake of
-	 * cross vendor migration.
-	 * Writing a zero into the event select MSRs disables them,
-	 * which we perfectly emulate ;-). Any other value should be at least
-	 * reported, some guests depend on them.
-	 */
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_EVNTSEL3:
-		if (data != 0)
-			vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: "
-				    "0x%x data 0x%llx\n", msr, data);
-		break;
-	/* at least RHEL 4 unconditionally writes to the perfctr registers,
-	 * so we ignore writes to make it happy.
-	 */
-	case MSR_K7_PERFCTR0:
-	case MSR_K7_PERFCTR1:
-	case MSR_K7_PERFCTR2:
-	case MSR_K7_PERFCTR3:
-		vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: "
-			    "0x%x data 0x%llx\n", msr, data);
-		break;
-	case MSR_P6_PERFCTR0:
-	case MSR_P6_PERFCTR1:
-		pr = true;
-	case MSR_P6_EVNTSEL0:
-	case MSR_P6_EVNTSEL1:
-		if (kvm_pmu_msr(vcpu, msr))
+	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
+	case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
+		pr = true; /* fall through */
+	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
+	case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
+		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 
 		if (pr || data != 0)
@@ -2359,7 +2252,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
-		if (kvm_pmu_msr(vcpu, msr))
+		if (kvm_pmu_is_valid_msr(vcpu, msr))
 			return kvm_pmu_set_msr(vcpu, msr_info);
 		if (!ignore_msrs) {
 			vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
@@ -2381,48 +2274,12 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common);
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
+int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
-	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
+	return kvm_x86_ops->get_msr(vcpu, msr);
 }
 EXPORT_SYMBOL_GPL(kvm_get_msr);
 
-static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
-{
-	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
-
-	if (!msr_mtrr_valid(msr))
-		return 1;
-
-	if (msr == MSR_MTRRdefType)
-		*pdata = vcpu->arch.mtrr_state.def_type +
-			 (vcpu->arch.mtrr_state.enabled << 10);
-	else if (msr == MSR_MTRRfix64K_00000)
-		*pdata = p[0];
-	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
-		*pdata = p[1 + msr - MSR_MTRRfix16K_80000];
-	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
-		*pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
-	else if (msr == MSR_IA32_CR_PAT)
-		*pdata = vcpu->arch.pat;
-	else {	/* Variable MTRRs */
-		int idx, is_mtrr_mask;
-		u64 *pt;
-
-		idx = (msr - 0x200) / 2;
-		is_mtrr_mask = msr - 0x200 - 2 * idx;
-		if (!is_mtrr_mask)
-			pt =
-			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
-		else
-			pt =
-			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
-		*pdata = *pt;
-	}
-
-	return 0;
-}
-
 static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
 	u64 data;
@@ -2520,11 +2377,11 @@ static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 data;
 
-	switch (msr) {
+	switch (msr_info->index) {
 	case MSR_IA32_PLATFORM_ID:
 	case MSR_IA32_EBL_CR_POWERON:
 	case MSR_IA32_DEBUGCTLMSR:
@@ -2535,38 +2392,28 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_K8_SYSCFG:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_EVNTSEL3:
-	case MSR_K7_PERFCTR0:
-	case MSR_K7_PERFCTR1:
-	case MSR_K7_PERFCTR2:
-	case MSR_K7_PERFCTR3:
 	case MSR_K8_INT_PENDING_MSG:
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
 	case MSR_AMD64_BU_CFG2:
-		data = 0;
+		msr_info->data = 0;
 		break;
-	case MSR_P6_PERFCTR0:
-	case MSR_P6_PERFCTR1:
-	case MSR_P6_EVNTSEL0:
-	case MSR_P6_EVNTSEL1:
-		if (kvm_pmu_msr(vcpu, msr))
-			return kvm_pmu_get_msr(vcpu, msr, pdata);
-		data = 0;
+	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
+	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
+	case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1:
+	case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1:
+		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
+			return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
+		msr_info->data = 0;
 		break;
 	case MSR_IA32_UCODE_REV:
-		data = 0x100000000ULL;
+		msr_info->data = 0x100000000ULL;
 		break;
 	case MSR_MTRRcap:
-		data = 0x500 | KVM_NR_VAR_MTRR;
-		break;
 	case 0x200 ... 0x2ff:
-		return get_msr_mtrr(vcpu, msr, pdata);
+		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
 	case 0xcd: /* fsb frequency */
-		data = 3;
+		msr_info->data = 3;
 		break;
 		/*
 		 * MSR_EBC_FREQUENCY_ID
@@ -2580,48 +2427,53 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		 * multiplying by zero otherwise.
 		 */
 	case MSR_EBC_FREQUENCY_ID:
-		data = 1 << 24;
+		msr_info->data = 1 << 24;
 		break;
 	case MSR_IA32_APICBASE:
-		data = kvm_get_apic_base(vcpu);
+		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
 	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
-		return kvm_x2apic_msr_read(vcpu, msr, pdata);
+		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_TSCDEADLINE:
-		data = kvm_get_lapic_tscdeadline_msr(vcpu);
+		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
 		break;
 	case MSR_IA32_TSC_ADJUST:
-		data = (u64)vcpu->arch.ia32_tsc_adjust_msr;
+		msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr;
 		break;
 	case MSR_IA32_MISC_ENABLE:
-		data = vcpu->arch.ia32_misc_enable_msr;
+		msr_info->data = vcpu->arch.ia32_misc_enable_msr;
+		break;
+	case MSR_IA32_SMBASE:
+		if (!msr_info->host_initiated)
+			return 1;
+		msr_info->data = vcpu->arch.smbase;
 		break;
 	case MSR_IA32_PERF_STATUS:
 		/* TSC increment by tick */
-		data = 1000ULL;
+		msr_info->data = 1000ULL;
 		/* CPU multiplier */
 		data |= (((uint64_t)4ULL) << 40);
 		break;
 	case MSR_EFER:
-		data = vcpu->arch.efer;
+		msr_info->data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
 	case MSR_KVM_WALL_CLOCK_NEW:
-		data = vcpu->kvm->arch.wall_clock;
+		msr_info->data = vcpu->kvm->arch.wall_clock;
 		break;
 	case MSR_KVM_SYSTEM_TIME:
 	case MSR_KVM_SYSTEM_TIME_NEW:
-		data = vcpu->arch.time;
+		msr_info->data = vcpu->arch.time;
 		break;
 	case MSR_KVM_ASYNC_PF_EN:
-		data = vcpu->arch.apf.msr_val;
+		msr_info->data = vcpu->arch.apf.msr_val;
 		break;
 	case MSR_KVM_STEAL_TIME:
-		data = vcpu->arch.st.msr_val;
+		msr_info->data = vcpu->arch.st.msr_val;
 		break;
 	case MSR_KVM_PV_EOI_EN:
-		data = vcpu->arch.pv_eoi.msr_val;
+		msr_info->data = vcpu->arch.pv_eoi.msr_val;
 		break;
 	case MSR_IA32_P5_MC_ADDR:
 	case MSR_IA32_P5_MC_TYPE:
@@ -2629,7 +2481,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
-		return get_msr_mce(vcpu, msr, pdata);
+		return get_msr_mce(vcpu, msr_info->index, &msr_info->data);
 	case MSR_K7_CLK_CTL:
 		/*
 		 * Provide expected ramp-up count for K7. All other
@@ -2640,17 +2492,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		 * type 6, model 8 and higher from exploding due to
 		 * the rdmsr failing.
 		 */
-		data = 0x20000000;
+		msr_info->data = 0x20000000;
 		break;
 	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
-		if (kvm_hv_msr_partition_wide(msr)) {
+		if (kvm_hv_msr_partition_wide(msr_info->index)) {
 			int r;
 			mutex_lock(&vcpu->kvm->lock);
-			r = get_msr_hyperv_pw(vcpu, msr, pdata);
+			r = get_msr_hyperv_pw(vcpu, msr_info->index, &msr_info->data);
 			mutex_unlock(&vcpu->kvm->lock);
 			return r;
 		} else
-			return get_msr_hyperv(vcpu, msr, pdata);
+			return get_msr_hyperv(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_BBL_CR_CTL3:
 		/* This legacy MSR exists but isn't fully documented in current
@@ -2663,31 +2515,30 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		 * L2 cache control register 3: 64GB range, 256KB size,
 		 * enabled, latency 0x1, configured
 		 */
-		data = 0xbe702111;
+		msr_info->data = 0xbe702111;
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
 		if (!guest_cpuid_has_osvw(vcpu))
 			return 1;
-		data = vcpu->arch.osvw.length;
+		msr_info->data = vcpu->arch.osvw.length;
 		break;
 	case MSR_AMD64_OSVW_STATUS:
 		if (!guest_cpuid_has_osvw(vcpu))
 			return 1;
-		data = vcpu->arch.osvw.status;
+		msr_info->data = vcpu->arch.osvw.status;
 		break;
 	default:
-		if (kvm_pmu_msr(vcpu, msr))
-			return kvm_pmu_get_msr(vcpu, msr, pdata);
+		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
+			return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
 		if (!ignore_msrs) {
-			vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
+			vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
-			data = 0;
+			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+			msr_info->data = 0;
 		}
 		break;
 	}
-	*pdata = data;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_get_msr_common);
@@ -2800,12 +2651,25 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_TIME:
 	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 	case KVM_CAP_TSC_DEADLINE_TIMER:
+	case KVM_CAP_ENABLE_CAP_VM:
+	case KVM_CAP_DISABLE_QUIRKS:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_X86_SMM:
+		/* SMBASE is usually relocated above 1M on modern chipsets,
+		 * and SMM handlers might indeed rely on 4G segment limits,
+		 * so do not report SMM to be available if real mode is
+		 * emulated via vm86 mode.  Still, do not go to great lengths
+		 * to avoid userspace's usage of the feature, because it is a
+		 * fringe case that is not enabled except via specific settings
+		 * of the module parameters.
+		 */
+		r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
@@ -2862,7 +2726,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
 			goto out;
 		n = msr_list.nmsrs;
-		msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
+		msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs;
 		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
 			goto out;
 		r = -E2BIG;
@@ -2874,7 +2738,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			goto out;
 		if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
 				 &emulated_msrs,
-				 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
+				 num_emulated_msrs * sizeof(u32)))
 			goto out;
 		r = 0;
 		break;
@@ -3018,6 +2882,13 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu)
+{
+	kvm_make_request(KVM_REQ_SMI, vcpu);
+
+	return 0;
+}
+
 static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
 					   struct kvm_tpr_access_ctl *tac)
 {
@@ -3123,8 +2994,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 
 	events->sipi_vector = 0; /* never valid when reporting to user space */
 
+	events->smi.smm = is_smm(vcpu);
+	events->smi.pending = vcpu->arch.smi_pending;
+	events->smi.smm_inside_nmi =
+		!!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
+	events->smi.latched_init = kvm_lapic_latched_init(vcpu);
+
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
-			 | KVM_VCPUEVENT_VALID_SHADOW);
+			 | KVM_VCPUEVENT_VALID_SHADOW
+			 | KVM_VCPUEVENT_VALID_SMM);
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
@@ -3133,7 +3011,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 {
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
-			      | KVM_VCPUEVENT_VALID_SHADOW))
+			      | KVM_VCPUEVENT_VALID_SHADOW
+			      | KVM_VCPUEVENT_VALID_SMM))
 		return -EINVAL;
 
 	process_nmi(vcpu);
@@ -3158,6 +3037,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	    kvm_vcpu_has_lapic(vcpu))
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
+	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+		if (events->smi.smm)
+			vcpu->arch.hflags |= HF_SMM_MASK;
+		else
+			vcpu->arch.hflags &= ~HF_SMM_MASK;
+		vcpu->arch.smi_pending = events->smi.pending;
+		if (events->smi.smm_inside_nmi)
+			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+		else
+			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+		if (kvm_vcpu_has_lapic(vcpu)) {
+			if (events->smi.latched_init)
+				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			else
+				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+		}
+	}
+
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
 	return 0;
@@ -3196,8 +3093,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 
 static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
-	u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
+	u64 xstate_bv = xsave->header.xfeatures;
 	u64 valid;
 
 	/*
@@ -3232,7 +3129,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 
 static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 {
-	struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+	struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave;
 	u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
 	u64 valid;
 
@@ -3243,9 +3140,9 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
 	memcpy(xsave, src, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV and possibly XCOMP_BV.  */
-	xsave->xsave_hdr.xstate_bv = xstate_bv;
+	xsave->header.xfeatures = xstate_bv;
 	if (cpu_has_xsaves)
-		xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+		xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
 	 * Copy each region from the non-compacted offset to the
@@ -3277,8 +3174,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 		fill_xsave((u8 *) guest_xsave->region, vcpu);
 	} else {
 		memcpy(guest_xsave->region,
-			&vcpu->arch.guest_fpu.state->fxsave,
-			sizeof(struct i387_fxsave_struct));
+			&vcpu->arch.guest_fpu.state.fxsave,
+			sizeof(struct fxregs_state));
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
 			XSTATE_FPSSE;
 	}
@@ -3302,8 +3199,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
-		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
-			guest_xsave->region, sizeof(struct i387_fxsave_struct));
+		memcpy(&vcpu->arch.guest_fpu.state.fxsave,
+			guest_xsave->region, sizeof(struct fxregs_state));
 	}
 	return 0;
 }
@@ -3417,6 +3314,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_nmi(vcpu);
 		break;
 	}
+	case KVM_SMI: {
+		r = kvm_vcpu_ioctl_smi(vcpu);
+		break;
+	}
 	case KVM_SET_CPUID: {
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
@@ -3456,7 +3357,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_GET_MSRS:
-		r = msr_io(vcpu, argp, kvm_get_msr, 1);
+		r = msr_io(vcpu, argp, do_get_msr, 1);
 		break;
 	case KVM_SET_MSRS:
 		r = msr_io(vcpu, argp, do_set_msr, 0);
@@ -3847,6 +3748,26 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
 	return 0;
 }
 
+static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
+				   struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_DISABLE_QUIRKS:
+		kvm->arch.disabled_quirks = cap->args[0];
+		r = 0;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -4099,7 +4020,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_ENABLE_CAP: {
+		struct kvm_enable_cap cap;
 
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			goto out;
+		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
+		break;
+	}
 	default:
 		r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
 	}
@@ -4112,8 +4041,7 @@ static void kvm_init_msr_list(void)
 	u32 dummy[2];
 	unsigned i, j;
 
-	/* skip the first msrs in the list. KVM-specific */
-	for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
+	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 
@@ -4138,6 +4066,22 @@ static void kvm_init_msr_list(void)
 		j++;
 	}
 	num_msrs_to_save = j;
+
+	for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
+		switch (emulated_msrs[i]) {
+		case MSR_IA32_SMBASE:
+			if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
+				continue;
+			break;
+		default:
+			break;
+		}
+
+		if (j < i)
+			emulated_msrs[j] = emulated_msrs[i];
+		j++;
+	}
+	num_emulated_msrs = j;
 }
 
 static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@@ -4255,8 +4199,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 
 		if (gpa == UNMAPPED_GVA)
 			return X86EMUL_PROPAGATE_FAULT;
-		ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data,
-					  offset, toread);
+		ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data,
+					       offset, toread);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
 			goto out;
@@ -4289,8 +4233,8 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 	offset = addr & (PAGE_SIZE-1);
 	if (WARN_ON(offset + bytes > PAGE_SIZE))
 		bytes = (unsigned)PAGE_SIZE - offset;
-	ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val,
-				  offset, bytes);
+	ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val,
+				       offset, bytes);
 	if (unlikely(ret < 0))
 		return X86EMUL_IO_NEEDED;
 
@@ -4336,7 +4280,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 
 		if (gpa == UNMAPPED_GVA)
 			return X86EMUL_PROPAGATE_FAULT;
-		ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
+		ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
 			goto out;
@@ -4389,7 +4333,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 {
 	int ret;
 
-	ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
+	ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes);
 	if (ret < 0)
 		return 0;
 	kvm_mmu_pte_write(vcpu, gpa, val, bytes);
@@ -4423,7 +4367,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
 static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
 			void *val, int bytes)
 {
-	return !kvm_read_guest(vcpu->kvm, gpa, val, bytes);
+	return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes);
 }
 
 static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -4621,7 +4565,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
 		goto emul_write;
 
-	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+	page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT);
 	if (is_error_page(page))
 		goto emul_write;
 
@@ -4649,7 +4593,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (!exchanged)
 		return X86EMUL_CMPXCHG_FAILED;
 
-	mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT);
+	kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT);
 	kvm_mmu_pte_write(vcpu, gpa, new, bytes);
 
 	return X86EMUL_CONTINUE;
@@ -4948,7 +4892,17 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	struct msr_data msr;
+	int r;
+
+	msr.index = msr_index;
+	msr.host_initiated = false;
+	r = kvm_get_msr(emul_to_vcpu(ctxt), &msr);
+	if (r)
+		return r;
+
+	*pdata = msr.data;
+	return 0;
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
@@ -4962,16 +4916,30 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 	return kvm_set_msr(emul_to_vcpu(ctxt), &msr);
 }
 
+static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+	return vcpu->arch.smbase;
+}
+
+static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+	vcpu->arch.smbase = smbase;
+}
+
 static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
 			      u32 pmc)
 {
-	return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc);
+	return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc);
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
 			     u32 pmc, u64 *pdata)
 {
-	return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata);
+	return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata);
 }
 
 static void emulator_halt(struct x86_emulate_ctxt *ctxt)
@@ -5047,6 +5015,8 @@ static const struct x86_emulate_ops emulate_ops = {
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,
+	.get_smbase          = emulator_get_smbase,
+	.set_smbase          = emulator_set_smbase,
 	.set_msr             = emulator_set_msr,
 	.get_msr             = emulator_get_msr,
 	.check_pmc	     = emulator_check_pmc,
@@ -5108,7 +5078,10 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 		     (cs_l && is_long_mode(vcpu))	? X86EMUL_MODE_PROT64 :
 		     cs_db				? X86EMUL_MODE_PROT32 :
 							  X86EMUL_MODE_PROT16;
-	ctxt->guest_mode = is_guest_mode(vcpu);
+	BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
+	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
+	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
+	ctxt->emul_flags = vcpu->arch.hflags;
 
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
@@ -5277,6 +5250,34 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
 static int complete_emulated_pio(struct kvm_vcpu *vcpu);
 
+static void kvm_smm_changed(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.hflags & HF_SMM_MASK)) {
+		/* This is a good place to trace that we are exiting SMM.  */
+		trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false);
+
+		if (unlikely(vcpu->arch.smi_pending)) {
+			kvm_make_request(KVM_REQ_SMI, vcpu);
+			vcpu->arch.smi_pending = 0;
+		} else {
+			/* Process a latched INIT, if any.  */
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
+		}
+	}
+
+	kvm_mmu_reset_context(vcpu);
+}
+
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
+{
+	unsigned changed = vcpu->arch.hflags ^ emul_flags;
+
+	vcpu->arch.hflags = emul_flags;
+
+	if (changed & HF_SMM_MASK)
+		kvm_smm_changed(vcpu);
+}
+
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -5476,6 +5477,8 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
+		if (vcpu->arch.hflags != ctxt->emul_flags)
+			kvm_set_hflags(vcpu, ctxt->emul_flags);
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
 			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
@@ -5954,6 +5957,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 	lapic_irq.shorthand = 0;
 	lapic_irq.dest_mode = 0;
 	lapic_irq.dest_id = apicid;
+	lapic_irq.msi_redir_hint = false;
 
 	lapic_irq.delivery_mode = APIC_DM_REMRD;
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
@@ -6041,6 +6045,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 
 	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 	if (irqchip_in_kernel(vcpu->kvm))
@@ -6164,6 +6169,233 @@ static void process_nmi(struct kvm_vcpu *vcpu)
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 
+#define put_smstate(type, buf, offset, val)			  \
+	*(type *)((buf) + (offset) - 0x7e00) = val
+
+static u32 process_smi_get_segment_flags(struct kvm_segment *seg)
+{
+	u32 flags = 0;
+	flags |= seg->g       << 23;
+	flags |= seg->db      << 22;
+	flags |= seg->l       << 21;
+	flags |= seg->avl     << 20;
+	flags |= seg->present << 15;
+	flags |= seg->dpl     << 13;
+	flags |= seg->s       << 12;
+	flags |= seg->type    << 8;
+	return flags;
+}
+
+static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+{
+	struct kvm_segment seg;
+	int offset;
+
+	kvm_get_segment(vcpu, &seg, n);
+	put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
+
+	if (n < 3)
+		offset = 0x7f84 + n * 12;
+	else
+		offset = 0x7f2c + (n - 3) * 12;
+
+	put_smstate(u32, buf, offset + 8, seg.base);
+	put_smstate(u32, buf, offset + 4, seg.limit);
+	put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg));
+}
+
+static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+{
+	struct kvm_segment seg;
+	int offset;
+	u16 flags;
+
+	kvm_get_segment(vcpu, &seg, n);
+	offset = 0x7e00 + n * 16;
+
+	flags = process_smi_get_segment_flags(&seg) >> 8;
+	put_smstate(u16, buf, offset, seg.selector);
+	put_smstate(u16, buf, offset + 2, flags);
+	put_smstate(u32, buf, offset + 4, seg.limit);
+	put_smstate(u64, buf, offset + 8, seg.base);
+}
+
+static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+{
+	struct desc_ptr dt;
+	struct kvm_segment seg;
+	unsigned long val;
+	int i;
+
+	put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
+	put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
+	put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
+	put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
+
+	for (i = 0; i < 8; i++)
+		put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i));
+
+	kvm_get_dr(vcpu, 6, &val);
+	put_smstate(u32, buf, 0x7fcc, (u32)val);
+	kvm_get_dr(vcpu, 7, &val);
+	put_smstate(u32, buf, 0x7fc8, (u32)val);
+
+	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+	put_smstate(u32, buf, 0x7fc4, seg.selector);
+	put_smstate(u32, buf, 0x7f64, seg.base);
+	put_smstate(u32, buf, 0x7f60, seg.limit);
+	put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg));
+
+	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+	put_smstate(u32, buf, 0x7fc0, seg.selector);
+	put_smstate(u32, buf, 0x7f80, seg.base);
+	put_smstate(u32, buf, 0x7f7c, seg.limit);
+	put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg));
+
+	kvm_x86_ops->get_gdt(vcpu, &dt);
+	put_smstate(u32, buf, 0x7f74, dt.address);
+	put_smstate(u32, buf, 0x7f70, dt.size);
+
+	kvm_x86_ops->get_idt(vcpu, &dt);
+	put_smstate(u32, buf, 0x7f58, dt.address);
+	put_smstate(u32, buf, 0x7f54, dt.size);
+
+	for (i = 0; i < 6; i++)
+		process_smi_save_seg_32(vcpu, buf, i);
+
+	put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
+
+	/* revision id */
+	put_smstate(u32, buf, 0x7efc, 0x00020000);
+	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
+}
+
+static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+{
+#ifdef CONFIG_X86_64
+	struct desc_ptr dt;
+	struct kvm_segment seg;
+	unsigned long val;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i));
+
+	put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
+	put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
+
+	kvm_get_dr(vcpu, 6, &val);
+	put_smstate(u64, buf, 0x7f68, val);
+	kvm_get_dr(vcpu, 7, &val);
+	put_smstate(u64, buf, 0x7f60, val);
+
+	put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
+	put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
+	put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
+
+	put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
+
+	/* revision id */
+	put_smstate(u32, buf, 0x7efc, 0x00020064);
+
+	put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
+
+	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+	put_smstate(u16, buf, 0x7e90, seg.selector);
+	put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8);
+	put_smstate(u32, buf, 0x7e94, seg.limit);
+	put_smstate(u64, buf, 0x7e98, seg.base);
+
+	kvm_x86_ops->get_idt(vcpu, &dt);
+	put_smstate(u32, buf, 0x7e84, dt.size);
+	put_smstate(u64, buf, 0x7e88, dt.address);
+
+	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+	put_smstate(u16, buf, 0x7e70, seg.selector);
+	put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8);
+	put_smstate(u32, buf, 0x7e74, seg.limit);
+	put_smstate(u64, buf, 0x7e78, seg.base);
+
+	kvm_x86_ops->get_gdt(vcpu, &dt);
+	put_smstate(u32, buf, 0x7e64, dt.size);
+	put_smstate(u64, buf, 0x7e68, dt.address);
+
+	for (i = 0; i < 6; i++)
+		process_smi_save_seg_64(vcpu, buf, i);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
+static void process_smi(struct kvm_vcpu *vcpu)
+{
+	struct kvm_segment cs, ds;
+	char buf[512];
+	u32 cr0;
+
+	if (is_smm(vcpu)) {
+		vcpu->arch.smi_pending = true;
+		return;
+	}
+
+	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
+	vcpu->arch.hflags |= HF_SMM_MASK;
+	memset(buf, 0, 512);
+	if (guest_cpuid_has_longmode(vcpu))
+		process_smi_save_state_64(vcpu, buf);
+	else
+		process_smi_save_state_32(vcpu, buf);
+
+	kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
+
+	if (kvm_x86_ops->get_nmi_mask(vcpu))
+		vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+	else
+		kvm_x86_ops->set_nmi_mask(vcpu, true);
+
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+	kvm_rip_write(vcpu, 0x8000);
+
+	cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
+	kvm_x86_ops->set_cr0(vcpu, cr0);
+	vcpu->arch.cr0 = cr0;
+
+	kvm_x86_ops->set_cr4(vcpu, 0);
+
+	__kvm_set_dr(vcpu, 7, DR7_FIXED_1);
+
+	cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
+	cs.base = vcpu->arch.smbase;
+
+	ds.selector = 0;
+	ds.base = 0;
+
+	cs.limit    = ds.limit = 0xffffffff;
+	cs.type     = ds.type = 0x3;
+	cs.dpl      = ds.dpl = 0;
+	cs.db       = ds.db = 0;
+	cs.s        = ds.s = 1;
+	cs.l        = ds.l = 0;
+	cs.g        = ds.g = 1;
+	cs.avl      = ds.avl = 0;
+	cs.present  = ds.present = 1;
+	cs.unusable = ds.unusable = 0;
+	cs.padding  = ds.padding = 0;
+
+	kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
+	kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
+	kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
+	kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
+	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
+	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+
+	if (guest_cpuid_has_longmode(vcpu))
+		kvm_x86_ops->set_efer(vcpu, 0);
+
+	kvm_update_cpuid(vcpu);
+	kvm_mmu_reset_context(vcpu);
+}
+
 static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 {
 	u64 eoi_exit_bitmap[4];
@@ -6197,6 +6429,8 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 		return;
 
 	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (is_error_page(page))
+		return;
 	kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
 
 	/*
@@ -6270,12 +6504,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
 			record_steal_time(vcpu);
+		if (kvm_check_request(KVM_REQ_SMI, vcpu))
+			process_smi(vcpu);
 		if (kvm_check_request(KVM_REQ_NMI, vcpu))
 			process_nmi(vcpu);
 		if (kvm_check_request(KVM_REQ_PMU, vcpu))
-			kvm_handle_pmu_event(vcpu);
+			kvm_pmu_handle_event(vcpu);
 		if (kvm_check_request(KVM_REQ_PMI, vcpu))
-			kvm_deliver_pmi(vcpu);
+			kvm_pmu_deliver_pmi(vcpu);
 		if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
 			vcpu_scan_ioapic(vcpu);
 		if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
@@ -6347,7 +6583,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
-	kvm_guest_enter();
+	__kvm_guest_enter();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -6597,11 +6833,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
+	struct fpu *fpu = &current->thread.fpu;
 	int r;
 	sigset_t sigsaved;
 
-	if (!tsk_used_math(current) && init_fpu(current))
-		return -ENOMEM;
+	fpu__activate_curr(fpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
@@ -6971,8 +7207,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fpu->fpr, fxsave->st_space, 128);
 	fpu->fcw = fxsave->cwd;
@@ -6988,8 +7224,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	struct i387_fxsave_struct *fxsave =
-			&vcpu->arch.guest_fpu.state->fxsave;
+	struct fxregs_state *fxsave =
+			&vcpu->arch.guest_fpu.state.fxsave;
 
 	memcpy(fxsave->st_space, fpu->fpr, 128);
 	fxsave->cwd = fpu->fcw;
@@ -7003,17 +7239,11 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return 0;
 }
 
-int fx_init(struct kvm_vcpu *vcpu)
+static void fx_init(struct kvm_vcpu *vcpu)
 {
-	int err;
-
-	err = fpu_alloc(&vcpu->arch.guest_fpu);
-	if (err)
-		return err;
-
-	fpu_finit(&vcpu->arch.guest_fpu);
+	fpstate_init(&vcpu->arch.guest_fpu.state);
 	if (cpu_has_xsaves)
-		vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+		vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv =
 			host_xcr0 | XSTATE_COMPACTION_ENABLED;
 
 	/*
@@ -7022,14 +7252,6 @@ int fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.xcr0 = XSTATE_FP;
 
 	vcpu->arch.cr0 |= X86_CR0_ET;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(fx_init);
-
-static void fx_free(struct kvm_vcpu *vcpu)
-{
-	fpu_free(&vcpu->arch.guest_fpu);
 }
 
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
@@ -7045,7 +7267,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
-	fpu_restore_checking(&vcpu->arch.guest_fpu);
+	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
 	trace_kvm_fpu(1);
 }
 
@@ -7053,14 +7275,25 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	kvm_put_guest_xcr0(vcpu);
 
-	if (!vcpu->guest_fpu_loaded)
+	if (!vcpu->guest_fpu_loaded) {
+		vcpu->fpu_counter = 0;
 		return;
+	}
 
 	vcpu->guest_fpu_loaded = 0;
-	fpu_save_init(&vcpu->arch.guest_fpu);
+	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
 	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
-	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+	/*
+	 * If using eager FPU mode, or if the guest is a frequent user
+	 * of the FPU, just leave the FPU active for next time.
+	 * Every 255 times fpu_counter rolls over to 0; a guest that uses
+	 * the FPU in bursts will revert to loading it on demand.
+	 */
+	if (!vcpu->arch.eager_fpu) {
+		if (++vcpu->fpu_counter < 5)
+			kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
+	}
 	trace_kvm_fpu(0);
 }
 
@@ -7069,32 +7302,40 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvmclock_reset(vcpu);
 
 	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 						unsigned int id)
 {
+	struct kvm_vcpu *vcpu;
+
 	if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
 		printk_once(KERN_WARNING
 		"kvm: SMP vm created on host with unstable TSC; "
 		"guest TSC will not be reliable\n");
-	return kvm_x86_ops->vcpu_create(kvm, id);
+
+	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+
+	/*
+	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
+	 * deactivated soon if it doesn't.
+	 */
+	kvm_x86_ops->fpu_activate(vcpu);
+	return vcpu;
 }
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int r;
 
-	vcpu->arch.mtrr_state.have_fixed = 1;
+	kvm_vcpu_mtrr_init(vcpu);
 	r = vcpu_load(vcpu);
 	if (r)
 		return r;
-	kvm_vcpu_reset(vcpu);
+	kvm_vcpu_reset(vcpu, false);
 	kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
-
 	return r;
 }
 
@@ -7111,6 +7352,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	kvm_write_tsc(vcpu, &msr);
 	vcpu_put(vcpu);
 
+	if (!kvmclock_periodic_sync)
+		return;
+
 	schedule_delayed_work(&kvm->arch.kvmclock_sync_work,
 					KVMCLOCK_SYNC_PERIOD);
 }
@@ -7125,12 +7369,13 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
 
-	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
-void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
+void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
+	vcpu->arch.hflags = 0;
+
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
@@ -7156,13 +7401,16 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
 	kvm_async_pf_hash_reset(vcpu);
 	vcpu->arch.apf.halted = false;
 
-	kvm_pmu_reset(vcpu);
+	if (!init_event) {
+		kvm_pmu_reset(vcpu);
+		vcpu->arch.smbase = 0x30000;
+	}
 
 	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
 	vcpu->arch.regs_avail = ~0;
 	vcpu->arch.regs_dirty = ~0;
 
-	kvm_x86_ops->vcpu_reset(vcpu);
+	kvm_x86_ops->vcpu_reset(vcpu, init_event);
 }
 
 void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
@@ -7351,9 +7599,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		goto fail_free_mce_banks;
 	}
 
-	r = fx_init(vcpu);
-	if (r)
-		goto fail_free_wbinvd_dirty_mask;
+	fx_init(vcpu);
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
@@ -7363,12 +7609,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 
+	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
+
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
 	return 0;
-fail_free_wbinvd_dirty_mask:
-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+
 fail_free_mce_banks:
 	kfree(vcpu->arch.mce_banks);
 fail_free_lapic:
@@ -7470,6 +7717,40 @@ void kvm_arch_sync_events(struct kvm *kvm)
 	kvm_free_pit(kvm);
 }
 
+int __x86_set_memory_region(struct kvm *kvm,
+			    const struct kvm_userspace_memory_region *mem)
+{
+	int i, r;
+
+	/* Called with kvm->slots_lock held.  */
+	BUG_ON(mem->slot >= KVM_MEM_SLOTS_NUM);
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		struct kvm_userspace_memory_region m = *mem;
+
+		m.slot |= i << 16;
+		r = __kvm_set_memory_region(kvm, &m);
+		if (r < 0)
+			return r;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__x86_set_memory_region);
+
+int x86_set_memory_region(struct kvm *kvm,
+			  const struct kvm_userspace_memory_region *mem)
+{
+	int r;
+
+	mutex_lock(&kvm->slots_lock);
+	r = __x86_set_memory_region(kvm, mem);
+	mutex_unlock(&kvm->slots_lock);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(x86_set_memory_region);
+
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	if (current->mm == kvm->mm) {
@@ -7481,13 +7762,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		struct kvm_userspace_memory_region mem;
 		memset(&mem, 0, sizeof(mem));
 		mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
-		kvm_set_memory_region(kvm, &mem);
+		x86_set_memory_region(kvm, &mem);
 
 		mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
-		kvm_set_memory_region(kvm, &mem);
+		x86_set_memory_region(kvm, &mem);
 
 		mem.slot = TSS_PRIVATE_MEMSLOT;
-		kvm_set_memory_region(kvm, &mem);
+		x86_set_memory_region(kvm, &mem);
 	}
 	kvm_iommu_unmap_guest(kvm);
 	kfree(kvm->arch.vpic);
@@ -7576,18 +7857,18 @@ out_free:
 	return -ENOMEM;
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
+void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots)
 {
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
-	kvm_mmu_invalidate_mmio_sptes(kvm);
+	kvm_mmu_invalidate_mmio_sptes(kvm, slots);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
-				struct kvm_userspace_memory_region *mem,
+				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
 	/*
@@ -7665,14 +7946,14 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
+				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
+				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	struct kvm_memory_slot *new;
 	int nr_mmu_pages = 0;
 
-	if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) {
+	if (change == KVM_MR_DELETE && old->id >= KVM_USER_MEM_SLOTS) {
 		int ret;
 
 		ret = vm_munmap(old->userspace_addr,
@@ -7689,9 +7970,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (nr_mmu_pages)
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
 
-	/* It's OK to get 'new' slot here as it has already been installed */
-	new = id_to_memslot(kvm->memslots, mem->slot);
-
 	/*
 	 * Dirty logging tracks sptes in 4k granularity, meaning that large
 	 * sptes have to be split.  If live migration is successful, the guest
@@ -7716,9 +7994,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	 * been zapped so no dirty logging staff is needed for old slot. For
 	 * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the
 	 * new and it's also covered when dealing with the new slot.
+	 *
+	 * FIXME: const-ify all uses of struct kvm_memory_slot.
 	 */
 	if (change != KVM_MR_DELETE)
-		kvm_mmu_slot_apply_flags(kvm, new);
+		kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new);
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f5fef1868096..edc8cdcd786b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -4,6 +4,8 @@
 #include <linux/kvm_host.h>
 #include "kvm_cache_regs.h"
 
+#define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
+
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.exception.pending = false;
@@ -160,7 +162,13 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);
 
+void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
+u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
+					  int page_num);
 
 #define KVM_SUPPORTED_XCR0     (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
 				| XSTATE_BNDREGS | XSTATE_BNDCSR \
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 8f9a133cc099..f2dc08c003eb 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -70,7 +70,7 @@
 #include <asm/e820.h>
 #include <asm/mce.h>
 #include <asm/io.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/stackprotector.h>
 #include <asm/reboot.h>		/* for struct machine_ops */
 #include <asm/kvm_para.h>
@@ -90,7 +90,7 @@ struct lguest_data lguest_data = {
 	.noirq_iret = (u32)lguest_noirq_iret,
 	.kernel_address = PAGE_OFFSET,
 	.blocked_interrupts = { 1 }, /* Block timer interrupts */
-	.syscall_vec = SYSCALL_VECTOR,
+	.syscall_vec = IA32_SYSCALL_VECTOR,
 };
 
 /*G:037
@@ -866,7 +866,7 @@ static void __init lguest_init_IRQ(void)
 	for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
 		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
-		if (i != SYSCALL_VECTOR)
+		if (i != IA32_SYSCALL_VECTOR)
 			set_intr_gate(i, irq_entries_start +
 					8 * (i - FIRST_EXTERNAL_VECTOR));
 	}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1530afb07c85..f2587888d987 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -17,7 +17,6 @@ clean-files := inat-tables.c
 obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 
 lib-y := delay.o misc.o cmdline.o
-lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
@@ -40,6 +39,6 @@ else
         lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
-        lib-y += copy_user_64.o copy_user_nocache_64.o
+        lib-y += copy_user_64.o
 	lib-y += cmpxchg16b_emu.o
 endif
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
index 00933d5e992f..9b0ca8fe80fc 100644
--- a/arch/x86/lib/atomic64_386_32.S
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -11,26 +11,23 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 /* if you want SMP support, implement these with real spinlocks */
 .macro LOCK reg
-	pushfl_cfi
+	pushfl
 	cli
 .endm
 
 .macro UNLOCK reg
-	popfl_cfi
+	popfl
 .endm
 
 #define BEGIN(op) \
 .macro endp; \
-	CFI_ENDPROC; \
 ENDPROC(atomic64_##op##_386); \
 .purgem endp; \
 .endm; \
 ENTRY(atomic64_##op##_386); \
-	CFI_STARTPROC; \
 	LOCK v;
 
 #define ENDP endp
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
index 082a85167a5b..db3ae85440ff 100644
--- a/arch/x86/lib/atomic64_cx8_32.S
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -11,7 +11,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 .macro read64 reg
 	movl %ebx, %eax
@@ -22,16 +21,11 @@
 .endm
 
 ENTRY(atomic64_read_cx8)
-	CFI_STARTPROC
-
 	read64 %ecx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_read_cx8)
 
 ENTRY(atomic64_set_cx8)
-	CFI_STARTPROC
-
 1:
 /* we don't need LOCK_PREFIX since aligned 64-bit writes
  * are atomic on 586 and newer */
@@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_set_cx8)
 
 ENTRY(atomic64_xchg_cx8)
-	CFI_STARTPROC
-
 1:
 	LOCK_PREFIX
 	cmpxchg8b (%esi)
 	jne 1b
 
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_xchg_cx8)
 
 .macro addsub_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
+	pushl %ebp
+	pushl %ebx
+	pushl %esi
+	pushl %edi
 
 	movl %eax, %esi
 	movl %edx, %edi
@@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %edi
+	popl %esi
+	popl %ebx
+	popl %ebp
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -93,8 +81,7 @@ addsub_return sub sub sbb
 
 .macro incdec_return func ins insc
 ENTRY(atomic64_\func\()_return_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8)
 10:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_\func\()_return_cx8)
 .endm
 
@@ -119,8 +105,7 @@ incdec_return inc add adc
 incdec_return dec sub sbb
 
 ENTRY(atomic64_dec_if_positive_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8)
 2:
 	movl %ebx, %eax
 	movl %ecx, %edx
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_dec_if_positive_cx8)
 
 ENTRY(atomic64_add_unless_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebp
-	pushl_cfi_reg ebx
+	pushl %ebp
+	pushl %ebx
 /* these just push these two parameters on the stack */
-	pushl_cfi_reg edi
-	pushl_cfi_reg ecx
+	pushl %edi
+	pushl %ecx
 
 	movl %eax, %ebp
 	movl %edx, %edi
@@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8)
 	movl $1, %eax
 3:
 	addl $8, %esp
-	CFI_ADJUST_CFA_OFFSET -8
-	popl_cfi_reg ebx
-	popl_cfi_reg ebp
+	popl %ebx
+	popl %ebp
 	ret
 4:
 	cmpl %edx, 4(%esp)
 	jne 2b
 	xorl %eax, %eax
 	jmp 3b
-	CFI_ENDPROC
 ENDPROC(atomic64_add_unless_cx8)
 
 ENTRY(atomic64_inc_not_zero_cx8)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
+	pushl %ebx
 
 	read64 %esi
 1:
@@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8)
 
 	movl $1, %eax
 3:
-	popl_cfi_reg ebx
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 9bc944a91274..c1e623209853 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 				
@@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
 	   * alignment for the unrolled loop.
 	   */		
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg: unsigned char *buff
@@ -129,10 +127,9 @@ ENTRY(csum_partial)
 	jz 8f
 	roll $8, %eax
 8:
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 
 #else
@@ -140,9 +137,8 @@ ENDPROC(csum_partial)
 /* Version for PentiumII/PPro */
 
 ENTRY(csum_partial)
-	CFI_STARTPROC
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %esi
+	pushl %ebx
 	movl 20(%esp),%eax	# Function arg: unsigned int sum
 	movl 16(%esp),%ecx	# Function arg: int len
 	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
@@ -249,10 +245,9 @@ ENTRY(csum_partial)
 	jz 90f
 	roll $8, %eax
 90: 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
+	popl %ebx
+	popl %esi
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial)
 				
 #endif
@@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
 #define FP		12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	subl  $4,%esp	
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
-	pushl_cfi_reg ebx
+	pushl %edi
+	pushl %esi
+	pushl %ebx
 	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
 	movl ARGBASE+4(%esp),%esi	# src
@@ -401,12 +394,11 @@ DST(	movb %cl, (%edi)	)
 
 .previous
 
-	popl_cfi_reg ebx
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi %ecx			# equivalent to addl $4,%esp
+	popl %ebx
+	popl %esi
+	popl %edi
+	popl %ecx			# equivalent to addl $4,%esp
 	ret	
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 
 #else
@@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic)
 #define ARGBASE 12
 		
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg edi
-	pushl_cfi_reg esi
+	pushl %ebx
+	pushl %edi
+	pushl %esi
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
 	movl ARGBASE+12(%esp),%ecx	#len
@@ -489,11 +480,10 @@ DST(	movb %dl, (%edi)         )
 	jmp  7b			
 .previous				
 
-	popl_cfi_reg esi
-	popl_cfi_reg edi
-	popl_cfi_reg ebx
+	popl %esi
+	popl %edi
+	popl %ebx
 	ret
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
 				
 #undef ROUND
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index e67e579c93bd..a2fe51b00cce 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,5 +1,4 @@
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -15,7 +14,6 @@
  * %rdi	- page
  */
 ENTRY(clear_page)
-	CFI_STARTPROC
 
 	ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp clear_page_c_e", X86_FEATURE_ERMS
@@ -24,11 +22,9 @@ ENTRY(clear_page)
 	xorl %eax,%eax
 	rep stosq
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page)
 
 ENTRY(clear_page_orig)
-	CFI_STARTPROC
 
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
@@ -48,14 +44,11 @@ ENTRY(clear_page_orig)
 	jnz	.Lloop
 	nop
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_orig)
 
 ENTRY(clear_page_c_e)
-	CFI_STARTPROC
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
 	ret
-	CFI_ENDPROC
 ENDPROC(clear_page_c_e)
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 40a172541ee2..9b330242e740 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,7 +6,6 @@
  *
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/percpu.h>
 
 .text
@@ -21,7 +20,6 @@
  * %al  : Operation successful
  */
 ENTRY(this_cpu_cmpxchg16b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not
@@ -32,7 +30,7 @@ CFI_STARTPROC
 # *atomic* on a single cpu (as provided by the this_cpu_xx class of
 # macros).
 #
-	pushfq_cfi
+	pushfq
 	cli
 
 	cmpq PER_CPU_VAR((%rsi)), %rax
@@ -43,17 +41,13 @@ CFI_STARTPROC
 	movq %rbx, PER_CPU_VAR((%rsi))
 	movq %rcx, PER_CPU_VAR(8(%rsi))
 
-	CFI_REMEMBER_STATE
-	popfq_cfi
+	popfq
 	mov $1, %al
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
-	popfq_cfi
+	popfq
 	xor %al,%al
 	ret
 
-CFI_ENDPROC
-
 ENDPROC(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index b4807fce5177..ad5349778490 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 .text
 
@@ -20,14 +19,13 @@
  * %ecx : high 32 bits of new value
  */
 ENTRY(cmpxchg8b_emu)
-CFI_STARTPROC
 
 #
 # Emulate 'cmpxchg8b (%esi)' on UP except we don't
 # set the whole ZF thing (caller will just compare
 # eax:edx with the expected value)
 #
-	pushfl_cfi
+	pushfl
 	cli
 
 	cmpl  (%esi), %eax
@@ -38,18 +36,15 @@ CFI_STARTPROC
 	movl %ebx,  (%esi)
 	movl %ecx, 4(%esi)
 
-	CFI_REMEMBER_STATE
-	popfl_cfi
+	popfl
 	ret
 
-	CFI_RESTORE_STATE
 .Lnot_same:
 	movl  (%esi), %eax
 .Lhalf_same:
 	movl 4(%esi), %edx
 
-	popfl_cfi
+	popfl
 	ret
 
-CFI_ENDPROC
 ENDPROC(cmpxchg8b_emu)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 8239dbcbf984..009f98216b7e 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,7 +1,6 @@
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -13,22 +12,16 @@
  */
 	ALIGN
 ENTRY(copy_page)
-	CFI_STARTPROC
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page)
 
 ENTRY(copy_page_regs)
-	CFI_STARTPROC
 	subq	$2*8,	%rsp
-	CFI_ADJUST_CFA_OFFSET 2*8
 	movq	%rbx,	(%rsp)
-	CFI_REL_OFFSET rbx, 0
 	movq	%r12,	1*8(%rsp)
-	CFI_REL_OFFSET r12, 1*8
 
 	movl	$(4096/64)-5,	%ecx
 	.p2align 4
@@ -87,11 +80,7 @@ ENTRY(copy_page_regs)
 	jnz	.Loop2
 
 	movq	(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq	1*8(%rsp), %r12
-	CFI_RESTORE r12
 	addq	$2*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -2*8
 	ret
-	CFI_ENDPROC
 ENDPROC(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997dfaef24..982ce34f4a9b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -7,7 +7,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/current.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
@@ -16,33 +15,8 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 
-	.macro ALIGN_DESTINATION
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-	.endm
-
 /* Standard copy_to_user with segment limit checking */
 ENTRY(_copy_to_user)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rdi,%rcx
 	addq %rdx,%rcx
@@ -54,12 +28,10 @@ ENTRY(_copy_to_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_to_user)
 
 /* Standard copy_from_user with segment limit checking */
 ENTRY(_copy_from_user)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%rax)
 	movq %rsi,%rcx
 	addq %rdx,%rcx
@@ -71,14 +43,12 @@ ENTRY(_copy_from_user)
 		      X86_FEATURE_REP_GOOD,			\
 		      "jmp copy_user_enhanced_fast_string",	\
 		      X86_FEATURE_ERMS
-	CFI_ENDPROC
 ENDPROC(_copy_from_user)
 
 	.section .fixup,"ax"
 	/* must zero dest */
 ENTRY(bad_from_user)
 bad_from_user:
-	CFI_STARTPROC
 	movl %edx,%ecx
 	xorl %eax,%eax
 	rep
@@ -86,7 +56,6 @@ bad_from_user:
 bad_to_user:
 	movl %edx,%eax
 	ret
-	CFI_ENDPROC
 ENDPROC(bad_from_user)
 	.previous
 
@@ -104,7 +73,6 @@ ENDPROC(bad_from_user)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_unrolled)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 20f		/* less then 8 bytes, go to byte copy loop */
@@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled)
 	_ASM_EXTABLE(19b,40b)
 	_ASM_EXTABLE(21b,50b)
 	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_unrolled)
 
 /* Some CPUs run faster using the string copy instructions.
@@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_generic_string)
-	CFI_STARTPROC
 	ASM_STAC
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
@@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string)
 
 	_ASM_EXTABLE(1b,11b)
 	_ASM_EXTABLE(3b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_generic_string)
 
 /*
@@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string)
  * eax uncopied bytes or 0 if successful.
  */
 ENTRY(copy_user_enhanced_fast_string)
-	CFI_STARTPROC
 	ASM_STAC
 	movl %edx,%ecx
 1:	rep
@@ -264,5 +228,94 @@ ENTRY(copy_user_enhanced_fast_string)
 	.previous
 
 	_ASM_EXTABLE(1b,12b)
-	CFI_ENDPROC
 ENDPROC(copy_user_enhanced_fast_string)
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ * This will force destination/source out of cache for more performance.
+ */
+ENTRY(__copy_user_nocache)
+	ASM_STAC
+	cmpl $8,%edx
+	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	ALIGN_DESTINATION
+	movl %edx,%ecx
+	andl $63,%edx
+	shrl $6,%ecx
+	jz 17f
+1:	movq (%rsi),%r8
+2:	movq 1*8(%rsi),%r9
+3:	movq 2*8(%rsi),%r10
+4:	movq 3*8(%rsi),%r11
+5:	movnti %r8,(%rdi)
+6:	movnti %r9,1*8(%rdi)
+7:	movnti %r10,2*8(%rdi)
+8:	movnti %r11,3*8(%rdi)
+9:	movq 4*8(%rsi),%r8
+10:	movq 5*8(%rsi),%r9
+11:	movq 6*8(%rsi),%r10
+12:	movq 7*8(%rsi),%r11
+13:	movnti %r8,4*8(%rdi)
+14:	movnti %r9,5*8(%rdi)
+15:	movnti %r10,6*8(%rdi)
+16:	movnti %r11,7*8(%rdi)
+	leaq 64(%rsi),%rsi
+	leaq 64(%rdi),%rdi
+	decl %ecx
+	jnz 1b
+17:	movl %edx,%ecx
+	andl $7,%edx
+	shrl $3,%ecx
+	jz 20f
+18:	movq (%rsi),%r8
+19:	movnti %r8,(%rdi)
+	leaq 8(%rsi),%rsi
+	leaq 8(%rdi),%rdi
+	decl %ecx
+	jnz 18b
+20:	andl %edx,%edx
+	jz 23f
+	movl %edx,%ecx
+21:	movb (%rsi),%al
+22:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 21b
+23:	xorl %eax,%eax
+	ASM_CLAC
+	sfence
+	ret
+
+	.section .fixup,"ax"
+30:	shll $6,%ecx
+	addl %ecx,%edx
+	jmp 60f
+40:	lea (%rdx,%rcx,8),%rdx
+	jmp 60f
+50:	movl %ecx,%edx
+60:	sfence
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE(1b,30b)
+	_ASM_EXTABLE(2b,30b)
+	_ASM_EXTABLE(3b,30b)
+	_ASM_EXTABLE(4b,30b)
+	_ASM_EXTABLE(5b,30b)
+	_ASM_EXTABLE(6b,30b)
+	_ASM_EXTABLE(7b,30b)
+	_ASM_EXTABLE(8b,30b)
+	_ASM_EXTABLE(9b,30b)
+	_ASM_EXTABLE(10b,30b)
+	_ASM_EXTABLE(11b,30b)
+	_ASM_EXTABLE(12b,30b)
+	_ASM_EXTABLE(13b,30b)
+	_ASM_EXTABLE(14b,30b)
+	_ASM_EXTABLE(15b,30b)
+	_ASM_EXTABLE(16b,30b)
+	_ASM_EXTABLE(18b,40b)
+	_ASM_EXTABLE(19b,40b)
+	_ASM_EXTABLE(21b,50b)
+	_ASM_EXTABLE(22b,50b)
+ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
deleted file mode 100644
index 6a4f43c2d9e6..000000000000
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ /dev/null
@@ -1,136 +0,0 @@
-/*
- * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
- * Copyright 2002 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License v2.
- *
- * Functions to copy from and to user space.
- */
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-
-#define FIX_ALIGNMENT 1
-
-#include <asm/current.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-#include <asm/smap.h>
-
-	.macro ALIGN_DESTINATION
-#ifdef FIX_ALIGNMENT
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(100b,103b)
-	_ASM_EXTABLE(101b,103b)
-#endif
-	.endm
-
-/*
- * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
- */
-ENTRY(__copy_user_nocache)
-	CFI_STARTPROC
-	ASM_STAC
-	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
-	ALIGN_DESTINATION
-	movl %edx,%ecx
-	andl $63,%edx
-	shrl $6,%ecx
-	jz 17f
-1:	movq (%rsi),%r8
-2:	movq 1*8(%rsi),%r9
-3:	movq 2*8(%rsi),%r10
-4:	movq 3*8(%rsi),%r11
-5:	movnti %r8,(%rdi)
-6:	movnti %r9,1*8(%rdi)
-7:	movnti %r10,2*8(%rdi)
-8:	movnti %r11,3*8(%rdi)
-9:	movq 4*8(%rsi),%r8
-10:	movq 5*8(%rsi),%r9
-11:	movq 6*8(%rsi),%r10
-12:	movq 7*8(%rsi),%r11
-13:	movnti %r8,4*8(%rdi)
-14:	movnti %r9,5*8(%rdi)
-15:	movnti %r10,6*8(%rdi)
-16:	movnti %r11,7*8(%rdi)
-	leaq 64(%rsi),%rsi
-	leaq 64(%rdi),%rdi
-	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
-	andl $7,%edx
-	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
-	leaq 8(%rsi),%rsi
-	leaq 8(%rdi),%rdi
-	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
-	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
-	ASM_CLAC
-	sfence
-	ret
-
-	.section .fixup,"ax"
-30:	shll $6,%ecx
-	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
-	CFI_ENDPROC
-ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 9734182966f3..7e48807b2fa1 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -6,7 +6,6 @@
  * for more details. No warranty for anything given at all.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 
@@ -47,23 +46,16 @@
 
 
 ENTRY(csum_partial_copy_generic)
-	CFI_STARTPROC
 	cmpl	$3*64, %edx
 	jle	.Lignore
 
 .Lignore:
 	subq  $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET 7*8
 	movq  %rbx, 2*8(%rsp)
-	CFI_REL_OFFSET rbx, 2*8
 	movq  %r12, 3*8(%rsp)
-	CFI_REL_OFFSET r12, 3*8
 	movq  %r14, 4*8(%rsp)
-	CFI_REL_OFFSET r14, 4*8
 	movq  %r13, 5*8(%rsp)
-	CFI_REL_OFFSET r13, 5*8
 	movq  %rbp, 6*8(%rsp)
-	CFI_REL_OFFSET rbp, 6*8
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -206,22 +198,14 @@ ENTRY(csum_partial_copy_generic)
 	addl %ebx, %eax
 	adcl %r9d, %eax		/* carry */
 
-	CFI_REMEMBER_STATE
 .Lende:
 	movq 2*8(%rsp), %rbx
-	CFI_RESTORE rbx
 	movq 3*8(%rsp), %r12
-	CFI_RESTORE r12
 	movq 4*8(%rsp), %r14
-	CFI_RESTORE r14
 	movq 5*8(%rsp), %r13
-	CFI_RESTORE r13
 	movq 6*8(%rsp), %rbp
-	CFI_RESTORE rbp
 	addq $7*8, %rsp
-	CFI_ADJUST_CFA_OFFSET -7*8
 	ret
-	CFI_RESTORE_STATE
 
 	/* Exception handlers. Very simple, zeroing is done in the wrappers */
 .Lbad_source:
@@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic)
 	jz   .Lende
 	movl $-EFAULT, (%rax)
 	jmp .Lende
-	CFI_ENDPROC
 ENDPROC(csum_partial_copy_generic)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index a4512359656a..46668cda4ffd 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,7 +26,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
@@ -36,7 +35,6 @@
 
 	.text
 ENTRY(__get_user_1)
-	CFI_STARTPROC
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
@@ -45,11 +43,9 @@ ENTRY(__get_user_1)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
-	CFI_STARTPROC
 	add $1,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -60,11 +56,9 @@ ENTRY(__get_user_2)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-	CFI_STARTPROC
 	add $3,%_ASM_AX
 	jc bad_get_user
 	GET_THREAD_INFO(%_ASM_DX)
@@ -75,11 +69,9 @@ ENTRY(__get_user_4)
 	xor %eax,%eax
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	CFI_STARTPROC
 #ifdef CONFIG_X86_64
 	add $7,%_ASM_AX
 	jc bad_get_user
@@ -104,28 +96,23 @@ ENTRY(__get_user_8)
 	ASM_CLAC
 	ret
 #endif
-	CFI_ENDPROC
 ENDPROC(__get_user_8)
 
 
 bad_get_user:
-	CFI_STARTPROC
 	xor %edx,%edx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user)
 
 #ifdef CONFIG_X86_32
 bad_get_user_8:
-	CFI_STARTPROC
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX
 	ASM_CLAC
 	ret
-	CFI_ENDPROC
 END(bad_get_user_8)
 #endif
 
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index 05a95e713da8..33147fef3452 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -16,15 +16,12 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 /*
  * override generic version in lib/iomap_copy.c
  */
 ENTRY(__iowrite32_copy)
-	CFI_STARTPROC
 	movl %edx,%ecx
 	rep movsd
 	ret
-	CFI_ENDPROC
 ENDPROC(__iowrite32_copy)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index b046664f5a1c..16698bba87de 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -2,7 +2,6 @@
 
 #include <linux/linkage.h>
 #include <asm/cpufeature.h>
-#include <asm/dwarf2.h>
 #include <asm/alternative-asm.h>
 
 /*
@@ -53,7 +52,6 @@ ENTRY(memcpy_erms)
 ENDPROC(memcpy_erms)
 
 ENTRY(memcpy_orig)
-	CFI_STARTPROC
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -178,5 +176,4 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-	CFI_ENDPROC
 ENDPROC(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0f8a0d0331b9..ca2afdd6d98e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,7 +6,6 @@
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -27,7 +26,6 @@
 
 ENTRY(memmove)
 ENTRY(__memmove)
-	CFI_STARTPROC
 
 	/* Handle more 32 bytes in loop */
 	mov %rdi, %rax
@@ -207,6 +205,5 @@ ENTRY(__memmove)
 	movb %r11b, (%rdi)
 13:
 	retq
-	CFI_ENDPROC
 ENDPROC(__memmove)
 ENDPROC(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 93118fb23976..2661fad05827 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,7 +1,6 @@
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative-asm.h>
 
@@ -66,7 +65,6 @@ ENTRY(memset_erms)
 ENDPROC(memset_erms)
 
 ENTRY(memset_orig)
-	CFI_STARTPROC
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -78,7 +76,6 @@ ENTRY(memset_orig)
 	movl  %edi,%r9d
 	andl  $7,%r9d
 	jnz  .Lbad_alignment
-	CFI_REMEMBER_STATE
 .Lafter_bad_alignment:
 
 	movq  %rdx,%rcx
@@ -128,7 +125,6 @@ ENTRY(memset_orig)
 	movq	%r10,%rax
 	ret
 
-	CFI_RESTORE_STATE
 .Lbad_alignment:
 	cmpq $7,%rdx
 	jbe	.Lhandle_7
@@ -139,5 +135,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-	CFI_ENDPROC
 ENDPROC(memset_orig)
diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c
index c9f2d9ba8dd8..e5e3ed8dc079 100644
--- a/arch/x86/lib/mmx_32.c
+++ b/arch/x86/lib/mmx_32.c
@@ -22,7 +22,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 #include <asm/asm.h>
 
 void *_mmx_memcpy(void *to, const void *from, size_t len)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index 3ca5218fbece..c81556409bbb 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,5 @@
 #include <linux/linkage.h>
 #include <linux/errno.h>
-#include <asm/dwarf2.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -13,9 +12,8 @@
  */
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushq_cfi_reg rbx
-	pushq_cfi_reg rbp
+	pushq %rbx
+	pushq %rbp
 	movq	%rdi, %r10	/* Save pointer */
 	xorl	%r11d, %r11d	/* Return value */
 	movl    (%rdi), %eax
@@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs)
 	movl    20(%rdi), %ebp
 	movl    24(%rdi), %esi
 	movl    28(%rdi), %edi
-	CFI_REMEMBER_STATE
 1:	\op
 2:	movl    %eax, (%r10)
 	movl	%r11d, %eax	/* Return value */
@@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs)
 	movl    %ebp, 20(%r10)
 	movl    %esi, 24(%r10)
 	movl    %edi, 28(%r10)
-	popq_cfi_reg rbp
-	popq_cfi_reg rbx
+	popq %rbp
+	popq %rbx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, %r11d
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
@@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs)
 
 .macro op_safe_regs op
 ENTRY(\op\()_safe_regs)
-	CFI_STARTPROC
-	pushl_cfi_reg ebx
-	pushl_cfi_reg ebp
-	pushl_cfi_reg esi
-	pushl_cfi_reg edi
-	pushl_cfi $0              /* Return value */
-	pushl_cfi %eax
+	pushl %ebx
+	pushl %ebp
+	pushl %esi
+	pushl %edi
+	pushl $0              /* Return value */
+	pushl %eax
 	movl    4(%eax), %ecx
 	movl    8(%eax), %edx
 	movl    12(%eax), %ebx
@@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs)
 	movl    24(%eax), %esi
 	movl    28(%eax), %edi
 	movl    (%eax), %eax
-	CFI_REMEMBER_STATE
 1:	\op
-2:	pushl_cfi %eax
+2:	pushl %eax
 	movl    4(%esp), %eax
-	popl_cfi (%eax)
+	popl (%eax)
 	addl    $4, %esp
-	CFI_ADJUST_CFA_OFFSET -4
 	movl    %ecx, 4(%eax)
 	movl    %edx, 8(%eax)
 	movl    %ebx, 12(%eax)
 	movl    %ebp, 20(%eax)
 	movl    %esi, 24(%eax)
 	movl    %edi, 28(%eax)
-	popl_cfi %eax
-	popl_cfi_reg edi
-	popl_cfi_reg esi
-	popl_cfi_reg ebp
-	popl_cfi_reg ebx
+	popl %eax
+	popl %edi
+	popl %esi
+	popl %ebp
+	popl %ebx
 	ret
 3:
-	CFI_RESTORE_STATE
 	movl    $-EIO, 4(%esp)
 	jmp     2b
 
 	_ASM_EXTABLE(1b, 3b)
-	CFI_ENDPROC
 ENDPROC(\op\()_safe_regs)
 .endm
 
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index fc6ba17a7eec..e0817a12d323 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,7 +11,6 @@
  * return value.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -30,11 +29,9 @@
  * as they get called from within inline assembly.
  */
 
-#define ENTER	CFI_STARTPROC ; \
-		GET_THREAD_INFO(%_ASM_BX)
+#define ENTER	GET_THREAD_INFO(%_ASM_BX)
 #define EXIT	ASM_CLAC ;	\
-		ret ;		\
-		CFI_ENDPROC
+		ret
 
 .text
 ENTRY(__put_user_1)
@@ -87,7 +84,6 @@ ENTRY(__put_user_8)
 ENDPROC(__put_user_8)
 
 bad_put_user:
-	CFI_STARTPROC
 	movl $-EFAULT,%eax
 	EXIT
 END(bad_put_user)
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
index 2322abe4da3b..40027db99140 100644
--- a/arch/x86/lib/rwsem.S
+++ b/arch/x86/lib/rwsem.S
@@ -15,7 +15,6 @@
 
 #include <linux/linkage.h>
 #include <asm/alternative-asm.h>
-#include <asm/dwarf2.h>
 
 #define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
 #define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
@@ -34,10 +33,10 @@
  */
 
 #define save_common_regs \
-	pushl_cfi_reg ecx
+	pushl %ecx
 
 #define restore_common_regs \
-	popl_cfi_reg ecx
+	popl %ecx
 
 	/* Avoid uglifying the argument copying x86-64 needs to do. */
 	.macro movq src, dst
@@ -64,50 +63,45 @@
  */
 
 #define save_common_regs \
-	pushq_cfi_reg rdi; \
-	pushq_cfi_reg rsi; \
-	pushq_cfi_reg rcx; \
-	pushq_cfi_reg r8;  \
-	pushq_cfi_reg r9;  \
-	pushq_cfi_reg r10; \
-	pushq_cfi_reg r11
+	pushq %rdi; \
+	pushq %rsi; \
+	pushq %rcx; \
+	pushq %r8;  \
+	pushq %r9;  \
+	pushq %r10; \
+	pushq %r11
 
 #define restore_common_regs \
-	popq_cfi_reg r11; \
-	popq_cfi_reg r10; \
-	popq_cfi_reg r9; \
-	popq_cfi_reg r8; \
-	popq_cfi_reg rcx; \
-	popq_cfi_reg rsi; \
-	popq_cfi_reg rdi
+	popq %r11; \
+	popq %r10; \
+	popq %r9; \
+	popq %r8; \
+	popq %rcx; \
+	popq %rsi; \
+	popq %rdi
 
 #endif
 
 /* Fix up special calling conventions */
 ENTRY(call_rwsem_down_read_failed)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_down_read_failed
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_read_failed)
 
 ENTRY(call_rwsem_down_write_failed)
-	CFI_STARTPROC
 	save_common_regs
 	movq %rax,%rdi
 	call rwsem_down_write_failed
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	CFI_STARTPROC
 	/* do nothing if still outstanding active readers */
 	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
 	jnz 1f
@@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake)
 	call rwsem_wake
 	restore_common_regs
 1:	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_wake)
 
 ENTRY(call_rwsem_downgrade_wake)
-	CFI_STARTPROC
 	save_common_regs
-	__ASM_SIZE(push,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(push,) %__ASM_REG(dx)
 	movq %rax,%rdi
 	call rwsem_downgrade_wake
-	__ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx)
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
 	restore_common_regs
 	ret
-	CFI_ENDPROC
 ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index e2f5e21c03b3..91d93b95bd86 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -647,7 +647,8 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
  * @from: Source address, in kernel space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from kernel space to user space.
  *
@@ -668,7 +669,8 @@ EXPORT_SYMBOL(_copy_to_user);
  * @from: Source address, in user space.
  * @n:    Number of bytes to copy.
  *
- * Context: User context only.  This function may sleep.
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
  *
  * Copy data from user space to kernel space.
  *
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index dc8adad10a2f..dd76a05729b0 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -30,7 +30,7 @@ static void fclex(void)
 }
 
 /* Needs to be externally visible */
-void finit_soft_fpu(struct i387_soft_struct *soft)
+void fpstate_init_soft(struct swregs_state *soft)
 {
 	struct address *oaddr, *iaddr;
 	memset(soft, 0, sizeof(*soft));
@@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft)
 
 void finit(void)
 {
-	finit_soft_fpu(&current->thread.fpu.state->soft);
+	fpstate_init_soft(&current->thread.fpu.state.soft);
 }
 
 /*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 9b868124128d..f37e84ab49f3 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -31,7 +31,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/user.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 
 #include "fpu_system.h"
 #include "fpu_emu.h"
@@ -147,13 +147,9 @@ void math_emulate(struct math_emu_info *info)
 	unsigned long code_base = 0;
 	unsigned long code_limit = 0;	/* Initialized to stop compiler warnings */
 	struct desc_struct code_descriptor;
+	struct fpu *fpu = &current->thread.fpu;
 
-	if (!used_math()) {
-		if (init_fpu(current)) {
-			do_group_exit(SIGKILL);
-			return;
-		}
-	}
+	fpu__activate_curr(fpu);
 
 #ifdef RE_ENTRANT_CHECKING
 	if (emulating) {
@@ -673,7 +669,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal)
 #endif /* PARANOID */
 }
 
-#define S387 ((struct i387_soft_struct *)s387)
+#define S387 ((struct swregs_state *)s387)
 #define sstatus_word() \
   ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top))
 
@@ -682,14 +678,14 @@ int fpregs_soft_set(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    const void *kbuf, const void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	void *space = s387->st_space;
 	int ret;
 	int offset, other, i, tags, regnr, tag, newtop;
 
 	RE_ENTRANT_CHECK_OFF;
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0,
-				 offsetof(struct i387_soft_struct, st_space));
+				 offsetof(struct swregs_state, st_space));
 	RE_ENTRANT_CHECK_ON;
 
 	if (ret)
@@ -734,7 +730,7 @@ int fpregs_soft_get(struct task_struct *target,
 		    unsigned int pos, unsigned int count,
 		    void *kbuf, void __user *ubuf)
 {
-	struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+	struct swregs_state *s387 = &target->thread.fpu.state.soft;
 	const void *space = s387->st_space;
 	int ret;
 	int offset = (S387->ftop & 7) * 10, other = 80 - offset;
@@ -752,7 +748,7 @@ int fpregs_soft_get(struct task_struct *target,
 #endif /* PECULIAR_486 */
 
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0,
-				  offsetof(struct i387_soft_struct, st_space));
+				  offsetof(struct swregs_state, st_space));
 
 	/* Copy all registers in stack order. */
 	if (!ret)
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 2c614410a5f3..9ccecb61a4fa 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -31,7 +31,7 @@
 #define SEG_EXPAND_DOWN(s)	(((s).b & ((1 << 11) | (1 << 10))) \
 				 == (1 << 10))
 
-#define I387			(current->thread.fpu.state)
+#define I387			(&current->thread.fpu.state)
 #define FPU_info		(I387->soft.info)
 
 #define FPU_CS			(*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 181c53bac3a7..9dc909841739 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
+#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -1126,9 +1127,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * in a region with pagefaults disabled then we must not take the fault
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(faulthandler_disabled() || !mm)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 4500142bc4aa..eecb207a2037 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -35,7 +35,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
-	/* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
+	preempt_disable();
 	pagefault_disable();
 
 	if (!PageHighMem(page))
@@ -100,6 +100,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1d553186c434..8533b46e6bee 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -40,7 +40,7 @@
  */
 uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
 	[_PAGE_CACHE_MODE_WB      ]	= 0         | 0        ,
-	[_PAGE_CACHE_MODE_WC      ]	= _PAGE_PWT | 0        ,
+	[_PAGE_CACHE_MODE_WC      ]	= 0         | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_UC_MINUS]	= 0         | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_UC      ]	= _PAGE_PWT | _PAGE_PCD,
 	[_PAGE_CACHE_MODE_WT      ]	= 0         | _PAGE_PCD,
@@ -50,11 +50,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl);
 
 uint8_t __pte2cachemode_tbl[8] = {
 	[__pte2cm_idx( 0        | 0         | 0        )] = _PAGE_CACHE_MODE_WB,
-	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx( 0        | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC,
 	[__pte2cm_idx( 0        | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
-	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(0         | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
 	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
 };
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c8140e12816a..8340e45c891a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -433,7 +433,7 @@ void __init add_highpages_with_active_regions(int nid,
 	phys_addr_t start, end;
 	u64 i;
 
-	for_each_free_mem_range(i, nid, &start, &end, NULL) {
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) {
 		unsigned long pfn = clamp_t(unsigned long, PFN_UP(start),
 					    start_pfn, end_pfn);
 		unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end),
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 9ca35fc60cfe..9c0ff045fdd4 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -59,6 +59,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	unsigned long vaddr;
 	int idx, type;
 
+	preempt_disable();
 	pagefault_disable();
 
 	type = kmap_atomic_idx_push();
@@ -77,13 +78,13 @@ void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 {
 	/*
-	 * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
-	 * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
-	 * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
-	 * user, which is "WC if the MTRR is WC, UC if you can't do that."
+	 * For non-PAT systems, translate non-WB request to UC- just in
+	 * case the caller set the PWT bit to prot directly without using
+	 * pgprot_writecombine(). UC- translates to uncached if the MTRR
+	 * is UC or WC. UC- gets the real intention, of the user, which is
+	 * "WC if the MTRR is WC, UC if you can't do that."
 	 */
-	if (!pat_enabled && pgprot_val(prot) ==
-	    (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+	if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB)
 		prot = __pgprot(__PAGE_KERNEL |
 				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
 
@@ -117,5 +118,6 @@ iounmap_atomic(void __iomem *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5ead4d6cf3a7..cc5ccc415cc0 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
 	case _PAGE_CACHE_MODE_WC:
 		err = _set_memory_wc(vaddr, nrpages);
 		break;
+	case _PAGE_CACHE_MODE_WT:
+		err = _set_memory_wt(vaddr, nrpages);
+		break;
 	case _PAGE_CACHE_MODE_WB:
 		err = _set_memory_wb(vaddr, nrpages);
 		break;
@@ -172,6 +175,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		prot = __pgprot(pgprot_val(prot) |
 				cachemode2protval(_PAGE_CACHE_MODE_WC));
 		break;
+	case _PAGE_CACHE_MODE_WT:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WT));
+		break;
 	case _PAGE_CACHE_MODE_WB:
 		break;
 	}
@@ -234,10 +241,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 {
 	/*
 	 * Ideally, this should be:
-	 *	pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
+	 *	pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
 	 *
 	 * Till we fix all X drivers to use ioremap_wc(), we will use
-	 * UC MINUS.
+	 * UC MINUS. Drivers that are certain they need or can already
+	 * be converted over to strong UC can use ioremap_uc().
 	 */
 	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
 
@@ -247,6 +255,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_nocache);
 
 /**
+ * ioremap_uc     -   map bus memory into CPU space as strongly uncachable
+ * @phys_addr:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_uc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked with a strong
+ * preference as completely uncachable on the CPU when possible. For non-PAT
+ * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
+ * systems this will set the PAT entry for the pages as strong UC.  This call
+ * will honor existing caching rules from things like the PCI bus. Note that
+ * there are other caches and buffers on many busses. In particular driver
+ * authors should read up on PCI writes.
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
+{
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
+
+	return __ioremap_caller(phys_addr, size, pcm,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL_GPL(ioremap_uc);
+
+/**
  * ioremap_wc	-	map memory into CPU space write combined
  * @phys_addr:	bus address of the memory
  * @size:	size of the resource to map
@@ -258,14 +299,28 @@ EXPORT_SYMBOL(ioremap_nocache);
  */
 void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
 {
-	if (pat_enabled)
-		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
 					__builtin_return_address(0));
-	else
-		return ioremap_nocache(phys_addr, size);
 }
 EXPORT_SYMBOL(ioremap_wc);
 
+/**
+ * ioremap_wt	-	map memory into CPU space write through
+ * @phys_addr:	bus address of the memory
+ * @size:	size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write through.
+ * Write through stores data into memory while keeping the cache up-to-date.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
+					__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
 void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 {
 	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
@@ -331,7 +386,7 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
-int arch_ioremap_pud_supported(void)
+int __init arch_ioremap_pud_supported(void)
 {
 #ifdef CONFIG_X86_64
 	return cpu_has_gbpages;
@@ -340,7 +395,7 @@ int arch_ioremap_pud_supported(void)
 #endif
 }
 
-int arch_ioremap_pmd_supported(void)
+int __init arch_ioremap_pmd_supported(void)
 {
 	return cpu_has_pse;
 }
@@ -351,18 +406,20 @@ int arch_ioremap_pmd_supported(void)
  */
 void *xlate_dev_mem_ptr(phys_addr_t phys)
 {
-	void *addr;
-	unsigned long start = phys & PAGE_MASK;
+	unsigned long start  = phys &  PAGE_MASK;
+	unsigned long offset = phys & ~PAGE_MASK;
+	void *vaddr;
 
 	/* If page is RAM, we can use __va. Otherwise ioremap and unmap. */
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	addr = (void __force *)ioremap_cache(start, PAGE_SIZE);
-	if (addr)
-		addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
+	vaddr = ioremap_cache(start, PAGE_SIZE);
+	/* Only add the offset on success and return NULL if the ioremap() failed: */
+	if (vaddr)
+		vaddr += offset;
 
-	return addr;
+	return vaddr;
 }
 
 void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
@@ -371,7 +428,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
 		return;
 
 	iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK));
-	return;
 }
 
 static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index c439ec478216..7a657f58bbea 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -10,13 +10,15 @@
 #include <linux/syscalls.h>
 #include <linux/sched/sysctl.h>
 
-#include <asm/i387.h>
 #include <asm/insn.h>
 #include <asm/mman.h>
 #include <asm/mmu_context.h>
 #include <asm/mpx.h>
 #include <asm/processor.h>
-#include <asm/fpu-internal.h>
+#include <asm/fpu/internal.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/mpx.h>
 
 static const char *mpx_mapping_name(struct vm_area_struct *vma)
 {
@@ -32,6 +34,22 @@ static int is_mpx_vma(struct vm_area_struct *vma)
 	return (vma->vm_ops == &mpx_vma_ops);
 }
 
+static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BD_SIZE_BYTES_64;
+	else
+		return MPX_BD_SIZE_BYTES_32;
+}
+
+static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_SIZE_BYTES_64;
+	else
+		return MPX_BT_SIZE_BYTES_32;
+}
+
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
@@ -47,8 +65,8 @@ static unsigned long mpx_mmap(unsigned long len)
 	vm_flags_t vm_flags;
 	struct vm_area_struct *vma;
 
-	/* Only bounds table and bounds directory can be allocated here */
-	if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+	/* Only bounds table can be allocated here */
+	if (len != mpx_bt_size_bytes(mm))
 		return -EINVAL;
 
 	down_write(&mm->mmap_sem);
@@ -272,10 +290,9 @@ bad_opcode:
  *
  * The caller is expected to kfree() the returned siginfo_t.
  */
-siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
-				struct xsave_struct *xsave_buf)
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {
-	struct bndreg *bndregs, *bndreg;
+	const struct bndreg *bndregs, *bndreg;
 	siginfo_t *info = NULL;
 	struct insn insn;
 	uint8_t bndregno;
@@ -295,8 +312,8 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
-	/* get the bndregs _area_ of the xsave structure */
-	bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+	/* get bndregs field from current task's xsave area */
+	bndregs = get_xsave_field_ptr(XSTATE_BNDREGS);
 	if (!bndregs) {
 		err = -EINVAL;
 		goto err_out;
@@ -334,6 +351,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 		err = -EINVAL;
 		goto err_out;
 	}
+	trace_mpx_bounds_register_exception(info->si_addr, bndreg);
 	return info;
 err_out:
 	/* info might be NULL, but kfree() handles that */
@@ -341,25 +359,18 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static __user void *task_get_bounds_dir(struct task_struct *tsk)
+static __user void *mpx_get_bounds_dir(void)
 {
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX))
 		return MPX_INVALID_BOUNDS_DIR;
 
 	/*
-	 * 32-bit binaries on 64-bit kernels are currently
-	 * unsupported.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32))
-		return MPX_INVALID_BOUNDS_DIR;
-	/*
 	 * The bounds directory pointer is stored in a register
 	 * only accessible if we first do an xsave.
 	 */
-	fpu_save_init(&tsk->thread.fpu);
-	bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return MPX_INVALID_BOUNDS_DIR;
 
@@ -378,10 +389,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk)
 		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
 }
 
-int mpx_enable_management(struct task_struct *tsk)
+int mpx_enable_management(void)
 {
 	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	int ret = 0;
 
 	/*
@@ -390,11 +401,12 @@ int mpx_enable_management(struct task_struct *tsk)
 	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
 	 * XRSTOR instruction.
 	 *
-	 * fpu_xsave() is expected to be very expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the unmap
-	 * path; we can just use mm->bd_addr instead.
+	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
+	 * expected to be relatively expensive. Storing the bounds
+	 * directory here means that we do not have to do xsave in the
+	 * unmap path; we can just use mm->bd_addr instead.
 	 */
-	bd_base = task_get_bounds_dir(tsk);
+	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
 	mm->bd_addr = bd_base;
 	if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
@@ -404,7 +416,7 @@ int mpx_enable_management(struct task_struct *tsk)
 	return ret;
 }
 
-int mpx_disable_management(struct task_struct *tsk)
+int mpx_disable_management(void)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -417,29 +429,59 @@ int mpx_disable_management(struct task_struct *tsk)
 	return 0;
 }
 
+static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
+		unsigned long *curval,
+		unsigned long __user *addr,
+		unsigned long old_val, unsigned long new_val)
+{
+	int ret;
+	/*
+	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
+	 * the pointer that we pass to it to figure out how much
+	 * data to cmpxchg.  We have to be careful here not to
+	 * pass a pointer to a 64-bit data type when we only want
+	 * a 32-bit copy.
+	 */
+	if (is_64bit_mm(mm)) {
+		ret = user_atomic_cmpxchg_inatomic(curval,
+				addr, old_val, new_val);
+	} else {
+		u32 uninitialized_var(curval_32);
+		u32 old_val_32 = old_val;
+		u32 new_val_32 = new_val;
+		u32 __user *addr_32 = (u32 __user *)addr;
+
+		ret = user_atomic_cmpxchg_inatomic(&curval_32,
+				addr_32, old_val_32, new_val_32);
+		*curval = curval_32;
+	}
+	return ret;
+}
+
 /*
- * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * With 32-bit mode, a bounds directory is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
  * and the size of each bounds table is 4MB.
  */
-static int allocate_bt(long __user *bd_entry)
+static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
 {
 	unsigned long expected_old_val = 0;
 	unsigned long actual_old_val = 0;
 	unsigned long bt_addr;
+	unsigned long bd_new_entry;
 	int ret = 0;
 
 	/*
 	 * Carve the virtual space out of userspace for the new
 	 * bounds table:
 	 */
-	bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
 	if (IS_ERR((void *)bt_addr))
 		return PTR_ERR((void *)bt_addr);
 	/*
 	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
 	 */
-	bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
 
 	/*
 	 * Go poke the address of the new bounds table in to the
@@ -452,8 +494,8 @@ static int allocate_bt(long __user *bd_entry)
 	 * mmap_sem at this point, unlike some of the other part
 	 * of the MPX code that have to pagefault_disable().
 	 */
-	ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-					   expected_old_val, bt_addr);
+	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
+				   expected_old_val, bd_new_entry);
 	if (ret)
 		goto out_unmap;
 
@@ -481,9 +523,10 @@ static int allocate_bt(long __user *bd_entry)
 		ret = -EINVAL;
 		goto out_unmap;
 	}
+	trace_mpx_new_bounds_table(bt_addr);
 	return 0;
 out_unmap:
-	vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
 	return ret;
 }
 
@@ -498,12 +541,13 @@ out_unmap:
  * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
  * and the size of each bound table is 4MB.
  */
-static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+static int do_mpx_bt_fault(void)
 {
 	unsigned long bd_entry, bd_base;
-	struct bndcsr *bndcsr;
+	const struct bndcsr *bndcsr;
+	struct mm_struct *mm = current->mm;
 
-	bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+	bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR);
 	if (!bndcsr)
 		return -EINVAL;
 	/*
@@ -520,13 +564,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
 	 * the directory is.
 	 */
 	if ((bd_entry < bd_base) ||
-	    (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
 		return -EINVAL;
 
-	return allocate_bt((long __user *)bd_entry);
+	return allocate_bt(mm, (long __user *)bd_entry);
 }
 
-int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+int mpx_handle_bd_fault(void)
 {
 	/*
 	 * Userspace never asked us to manage the bounds tables,
@@ -535,7 +579,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
 	if (!kernel_managing_mpx_tables(current->mm))
 		return -EINVAL;
 
-	if (do_mpx_bt_fault(xsave_buf)) {
+	if (do_mpx_bt_fault()) {
 		force_sig(SIGSEGV, current);
 		/*
 		 * The force_sig() is essentially "handling" this
@@ -572,29 +616,55 @@ static int mpx_resolve_fault(long __user *addr, int write)
 	return 0;
 }
 
+static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
+					     unsigned long bd_entry)
+{
+	unsigned long bt_addr = bd_entry;
+	int align_to_bytes;
+	/*
+	 * Bit 0 in a bt_entry is always the valid bit.
+	 */
+	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
+	/*
+	 * Tables are naturally aligned at 8-byte boundaries
+	 * on 64-bit and 4-byte boundaries on 32-bit.  The
+	 * documentation makes it appear that the low bits
+	 * are ignored by the hardware, so we do the same.
+	 */
+	if (is_64bit_mm(mm))
+		align_to_bytes = 8;
+	else
+		align_to_bytes = 4;
+	bt_addr &= ~(align_to_bytes-1);
+	return bt_addr;
+}
+
 /*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
 static int get_bt_addr(struct mm_struct *mm,
-			long __user *bd_entry, unsigned long *bt_addr)
+			long __user *bd_entry_ptr,
+			unsigned long *bt_addr_result)
 {
 	int ret;
 	int valid_bit;
+	unsigned long bd_entry;
+	unsigned long bt_addr;
 
-	if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+	if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr)))
 		return -EFAULT;
 
 	while (1) {
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(*bt_addr, bd_entry);
+		ret = get_user(bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
 		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry, need_write);
+			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
 		/*
 		 * If we could not resolve the fault, consider it
 		 * userspace's fault and error out.
@@ -603,8 +673,8 @@ static int get_bt_addr(struct mm_struct *mm,
 			return ret;
 	}
 
-	valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
-	*bt_addr &= MPX_BT_ADDR_MASK;
+	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
+	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
 
 	/*
 	 * When the kernel is managing bounds tables, a bounds directory
@@ -613,7 +683,7 @@ static int get_bt_addr(struct mm_struct *mm,
 	 * data in the address field, we know something is wrong. This
 	 * -EINVAL return will cause a SIGSEGV.
 	 */
-	if (!valid_bit && *bt_addr)
+	if (!valid_bit && bt_addr)
 		return -EINVAL;
 	/*
 	 * Do we have an completely zeroed bt entry?  That is OK.  It
@@ -624,19 +694,100 @@ static int get_bt_addr(struct mm_struct *mm,
 	if (!valid_bit)
 		return -ENOENT;
 
+	*bt_addr_result = bt_addr;
 	return 0;
 }
 
+static inline int bt_entry_size_bytes(struct mm_struct *mm)
+{
+	if (is_64bit_mm(mm))
+		return MPX_BT_ENTRY_BYTES_64;
+	else
+		return MPX_BT_ENTRY_BYTES_32;
+}
+
+/*
+ * Take a virtual address and turns it in to the offset in bytes
+ * inside of the bounds table where the bounds table entry
+ * controlling 'addr' can be found.
+ */
+static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
+		unsigned long addr)
+{
+	unsigned long bt_table_nr_entries;
+	unsigned long offset = addr;
+
+	if (is_64bit_mm(mm)) {
+		/* Bottom 3 bits are ignored on 64-bit */
+		offset >>= 3;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
+	} else {
+		/* Bottom 2 bits are ignored on 32-bit */
+		offset >>= 2;
+		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
+	}
+	/*
+	 * We know the size of the table in to which we are
+	 * indexing, and we have eliminated all the low bits
+	 * which are ignored for indexing.
+	 *
+	 * Mask out all the high bits which we do not need
+	 * to index in to the table.  Note that the tables
+	 * are always powers of two so this gives us a proper
+	 * mask.
+	 */
+	offset &= (bt_table_nr_entries-1);
+	/*
+	 * We now have an entry offset in terms of *entries* in
+	 * the table.  We need to scale it back up to bytes.
+	 */
+	offset *= bt_entry_size_bytes(mm);
+	return offset;
+}
+
+/*
+ * How much virtual address space does a single bounds
+ * directory entry cover?
+ *
+ * Note, we need a long long because 4GB doesn't fit in
+ * to a long on 32-bit.
+ */
+static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
+{
+	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	if (is_64bit_mm(mm))
+		return virt_space / MPX_BD_NR_ENTRIES_64;
+	else
+		return virt_space / MPX_BD_NR_ENTRIES_32;
+}
+
 /*
  * Free the backing physical pages of bounds table 'bt_addr'.
  * Assume start...end is within that bounds table.
  */
-static int zap_bt_entries(struct mm_struct *mm,
+static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		unsigned long bt_addr,
-		unsigned long start, unsigned long end)
+		unsigned long start_mapping, unsigned long end_mapping)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, len;
+	unsigned long start;
+	unsigned long end;
+
+	/*
+	 * if we 'end' on a boundary, the offset will be 0 which
+	 * is not what we want.  Back it up a byte to get the
+	 * last bt entry.  Then once we have the entry itself,
+	 * move 'end' back up by the table entry size.
+	 */
+	start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
+	end   = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
+	/*
+	 * Move end back up by one entry.  Among other things
+	 * this ensures that it remains page-aligned and does
+	 * not screw up zap_page_range()
+	 */
+	end += bt_entry_size_bytes(mm);
 
 	/*
 	 * Find the first overlapping vma. If vma->vm_start > start, there
@@ -648,7 +799,7 @@ static int zap_bt_entries(struct mm_struct *mm,
 		return -EINVAL;
 
 	/*
-	 * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+	 * A NUMA policy on a VM_MPX VMA could cause this bounds table to
 	 * be split. So we need to look across the entire 'start -> end'
 	 * range of this bounds table, find all of the VM_MPX VMAs, and
 	 * zap only those.
@@ -666,27 +817,65 @@ static int zap_bt_entries(struct mm_struct *mm,
 
 		len = min(vma->vm_end, end) - addr;
 		zap_page_range(vma, addr, len, NULL);
+		trace_mpx_unmap_zap(addr, addr+len);
 
 		vma = vma->vm_next;
 		addr = vma->vm_start;
 	}
-
 	return 0;
 }
 
-static int unmap_single_bt(struct mm_struct *mm,
+static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
+		unsigned long addr)
+{
+	/*
+	 * There are several ways to derive the bd offsets.  We
+	 * use the following approach here:
+	 * 1. We know the size of the virtual address space
+	 * 2. We know the number of entries in a bounds table
+	 * 3. We know that each entry covers a fixed amount of
+	 *    virtual address space.
+	 * So, we can just divide the virtual address by the
+	 * virtual space used by one entry to determine which
+	 * entry "controls" the given virtual address.
+	 */
+	if (is_64bit_mm(mm)) {
+		int bd_entry_size = 8; /* 64-bit pointer */
+		/*
+		 * Take the 64-bit addressing hole in to account.
+		 */
+		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	} else {
+		int bd_entry_size = 4; /* 32-bit pointer */
+		/*
+		 * 32-bit has no hole so this case needs no mask
+		 */
+		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
+	}
+	/*
+	 * The two return calls above are exact copies.  If we
+	 * pull out a single copy and put it in here, gcc won't
+	 * realize that we're doing a power-of-2 divide and use
+	 * shifts.  It uses a real divide.  If we put them up
+	 * there, it manages to figure it out (gcc 4.8.3).
+	 */
+}
+
+static int unmap_entire_bt(struct mm_struct *mm,
 		long __user *bd_entry, unsigned long bt_addr)
 {
 	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-	unsigned long actual_old_val = 0;
+	unsigned long uninitialized_var(actual_old_val);
 	int ret;
 
 	while (1) {
 		int need_write = 1;
+		unsigned long cleared_bd_entry = 0;
 
 		pagefault_disable();
-		ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
-						   expected_old_val, 0);
+		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
+				bd_entry, expected_old_val, cleared_bd_entry);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -705,9 +894,8 @@ static int unmap_single_bt(struct mm_struct *mm,
 	if (actual_old_val != expected_old_val) {
 		/*
 		 * Someone else raced with us to unmap the table.
-		 * There was no bounds table pointed to by the
-		 * directory, so declare success.  Somebody freed
-		 * it.
+		 * That is OK, since we were both trying to do
+		 * the same thing.  Declare success.
 		 */
 		if (!actual_old_val)
 			return 0;
@@ -720,176 +908,113 @@ static int unmap_single_bt(struct mm_struct *mm,
 		 */
 		return -EINVAL;
 	}
-
 	/*
 	 * Note, we are likely being called under do_munmap() already. To
 	 * avoid recursion, do_munmap() will check whether it comes
 	 * from one bounds table through VM_MPX flag.
 	 */
-	return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm));
 }
 
-/*
- * If the bounds table pointed by bounds directory 'bd_entry' is
- * not shared, unmap this whole bounds table. Otherwise, only free
- * those backing physical pages of bounds table entries covered
- * in this virtual address region start...end.
- */
-static int unmap_shared_bt(struct mm_struct *mm,
-		long __user *bd_entry, unsigned long start,
-		unsigned long end, bool prev_shared, bool next_shared)
+static int try_unmap_single_bt(struct mm_struct *mm,
+	       unsigned long start, unsigned long end)
 {
-	unsigned long bt_addr;
-	int ret;
-
-	ret = get_bt_addr(mm, bd_entry, &bt_addr);
+	struct vm_area_struct *next;
+	struct vm_area_struct *prev;
 	/*
-	 * We could see an "error" ret for not-present bounds
-	 * tables (not really an error), or actual errors, but
-	 * stop unmapping either way.
+	 * "bta" == Bounds Table Area: the area controlled by the
+	 * bounds table that we are unmapping.
 	 */
-	if (ret)
-		return ret;
-
-	if (prev_shared && next_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else if (prev_shared)
-		ret = zap_bt_entries(mm, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
-				bt_addr+MPX_BT_SIZE_BYTES);
-	else if (next_shared)
-		ret = zap_bt_entries(mm, bt_addr, bt_addr,
-				bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
-	else
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
-
-	return ret;
-}
-
-/*
- * A virtual address region being munmap()ed might share bounds table
- * with adjacent VMAs. We only need to free the backing physical
- * memory of these shared bounds tables entries covered in this virtual
- * address region.
- */
-static int unmap_edge_bts(struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
+	unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
+	unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
+	unsigned long uninitialized_var(bt_addr);
+	void __user *bde_vaddr;
 	int ret;
-	long __user *bde_start, *bde_end;
-	struct vm_area_struct *prev, *next;
-	bool prev_shared = false, next_shared = false;
-
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-
 	/*
-	 * Check whether bde_start and bde_end are shared with adjacent
-	 * VMAs.
-	 *
-	 * We already unliked the VMAs from the mm's rbtree so 'start'
+	 * We already unlinked the VMAs from the mm's rbtree so 'start'
 	 * is guaranteed to be in a hole. This gets us the first VMA
 	 * before the hole in to 'prev' and the next VMA after the hole
 	 * in to 'next'.
 	 */
 	next = find_vma_prev(mm, start, &prev);
-	if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
-			== bde_start)
-		prev_shared = true;
-	if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
-			== bde_end)
-		next_shared = true;
-
 	/*
-	 * This virtual address region being munmap()ed is only
-	 * covered by one bounds table.
-	 *
-	 * In this case, if this table is also shared with adjacent
-	 * VMAs, only part of the backing physical memory of the bounds
-	 * table need be freeed. Otherwise the whole bounds table need
-	 * be unmapped.
-	 */
-	if (bde_start == bde_end) {
-		return unmap_shared_bt(mm, bde_start, start, end,
-				prev_shared, next_shared);
+	 * Do not count other MPX bounds table VMAs as neighbors.
+	 * Although theoretically possible, we do not allow bounds
+	 * tables for bounds tables so our heads do not explode.
+	 * If we count them as neighbors here, we may end up with
+	 * lots of tables even though we have no actual table
+	 * entries in use.
+	 */
+	while (next && is_mpx_vma(next))
+		next = next->vm_next;
+	while (prev && is_mpx_vma(prev))
+		prev = prev->vm_prev;
+	/*
+	 * We know 'start' and 'end' lie within an area controlled
+	 * by a single bounds table.  See if there are any other
+	 * VMAs controlled by that bounds table.  If there are not
+	 * then we can "expand" the are we are unmapping to possibly
+	 * cover the entire table.
+	 */
+	next = find_vma_prev(mm, start, &prev);
+	if ((!prev || prev->vm_end <= bta_start_vaddr) &&
+	    (!next || next->vm_start >= bta_end_vaddr)) {
+		/*
+		 * No neighbor VMAs controlled by same bounds
+		 * table.  Try to unmap the whole thing
+		 */
+		start = bta_start_vaddr;
+		end = bta_end_vaddr;
 	}
 
+	bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start);
+	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
 	/*
-	 * If more than one bounds tables are covered in this virtual
-	 * address region being munmap()ed, we need to separately check
-	 * whether bde_start and bde_end are shared with adjacent VMAs.
+	 * No bounds table there, so nothing to unmap.
 	 */
-	ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
-	if (ret)
-		return ret;
-	ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+	if (ret == -ENOENT) {
+		ret = 0;
+		return 0;
+	}
 	if (ret)
 		return ret;
-
-	return 0;
+	/*
+	 * We are unmapping an entire table.  Either because the
+	 * unmap that started this whole process was large enough
+	 * to cover an entire table, or that the unmap was small
+	 * but was the area covered by a bounds table.
+	 */
+	if ((start == bta_start_vaddr) &&
+	    (end == bta_end_vaddr))
+		return unmap_entire_bt(mm, bde_vaddr, bt_addr);
+	return zap_bt_entries_mapping(mm, bt_addr, start, end);
 }
 
 static int mpx_unmap_tables(struct mm_struct *mm,
 		unsigned long start, unsigned long end)
 {
-	int ret;
-	long __user *bd_entry, *bde_start, *bde_end;
-	unsigned long bt_addr;
-
-	/*
-	 * "Edge" bounds tables are those which are being used by the region
-	 * (start -> end), but that may be shared with adjacent areas.  If they
-	 * turn out to be completely unshared, they will be freed.  If they are
-	 * shared, we will free the backing store (like an MADV_DONTNEED) for
-	 * areas used by this region.
-	 */
-	ret = unmap_edge_bts(mm, start, end);
-	switch (ret) {
-		/* non-present tables are OK */
-		case 0:
-		case -ENOENT:
-			/* Success, or no tables to unmap */
-			break;
-		case -EINVAL:
-		case -EFAULT:
-		default:
-			return ret;
-	}
-
-	/*
-	 * Only unmap the bounds table that are
-	 *   1. fully covered
-	 *   2. not at the edges of the mapping, even if full aligned
-	 */
-	bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
-	bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
-	for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
-		ret = get_bt_addr(mm, bd_entry, &bt_addr);
-		switch (ret) {
-			case 0:
-				break;
-			case -ENOENT:
-				/* No table here, try the next one */
-				continue;
-			case -EINVAL:
-			case -EFAULT:
-			default:
-				/*
-				 * Note: we are being strict here.
-				 * Any time we run in to an issue
-				 * unmapping tables, we stop and
-				 * SIGSEGV.
-				 */
-				return ret;
-		}
-
-		ret = unmap_single_bt(mm, bd_entry, bt_addr);
+	unsigned long one_unmap_start;
+	trace_mpx_unmap_search(start, end);
+
+	one_unmap_start = start;
+	while (one_unmap_start < end) {
+		int ret;
+		unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
+						       bd_entry_virt_space(mm));
+		unsigned long one_unmap_end = end;
+		/*
+		 * if the end is beyond the current bounds table,
+		 * move it back so we only deal with a single one
+		 * at a time
+		 */
+		if (one_unmap_end > next_unmap_start)
+			one_unmap_end = next_unmap_start;
+		ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
 		if (ret)
 			return ret;
-	}
 
+		one_unmap_start = next_unmap_start;
+	}
 	return 0;
 }
 
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 6629f397b467..8ff686aa7e8c 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -9,6 +9,7 @@
 #include <linux/random.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 89af288ec674..727158cb3b3c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/vmalloc.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -129,16 +130,15 @@ within(unsigned long addr, unsigned long start, unsigned long end)
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
-	void *vend = vaddr + size - 1;
+	unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+	void *vend = vaddr + size;
+	void *p;
 
 	mb();
 
-	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
-		clflushopt(vaddr);
-	/*
-	 * Flush any possible final partial cacheline:
-	 */
-	clflushopt(vend);
+	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	     p < vend; p += boot_cpu_data.x86_clflush_size)
+		clflushopt(p);
 
 	mb();
 }
@@ -418,13 +418,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
 	phys_addr_t phys_addr;
 	unsigned long offset;
 	enum pg_level level;
-	unsigned long psize;
 	unsigned long pmask;
 	pte_t *pte;
 
 	pte = lookup_address(virt_addr, &level);
 	BUG_ON(!pte);
-	psize = page_level_size(level);
 	pmask = page_level_mask(level);
 	offset = virt_addr & ~pmask;
 	phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
@@ -1468,6 +1466,9 @@ int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
+	 * If you really need strong UC use ioremap_uc(), but note
+	 * that you cannot override IO areas with set_memory_*() as
+	 * these helpers cannot work with IO memory.
 	 */
 	return change_page_attr_set(&addr, numpages,
 				    cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
@@ -1502,12 +1503,10 @@ EXPORT_SYMBOL(set_memory_uc);
 static int _set_memory_array(unsigned long *addr, int addrinarray,
 		enum page_cache_mode new_type)
 {
+	enum page_cache_mode set_type;
 	int i, j;
 	int ret;
 
-	/*
-	 * for now UC MINUS. see comments in ioremap_nocache()
-	 */
 	for (i = 0; i < addrinarray; i++) {
 		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
 					new_type, NULL);
@@ -1515,9 +1514,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
 			goto out_free;
 	}
 
+	/* If WC, set to UC- first and then WC */
+	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+				_PAGE_CACHE_MODE_UC_MINUS : new_type;
+
 	ret = change_page_attr_set(addr, addrinarray,
-				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
-				   1);
+				   cachemode2pgprot(set_type), 1);
 
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(addr, addrinarray,
@@ -1549,6 +1551,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray)
 }
 EXPORT_SYMBOL(set_memory_array_wc);
 
+int set_memory_array_wt(unsigned long *addr, int addrinarray)
+{
+	return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_memory_array_wt);
+
 int _set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
@@ -1571,27 +1579,42 @@ int set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
 
-	if (!pat_enabled)
-		return set_memory_uc(addr, numpages);
-
 	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 		_PAGE_CACHE_MODE_WC, NULL);
 	if (ret)
-		goto out_err;
+		return ret;
 
 	ret = _set_memory_wc(addr, numpages);
 	if (ret)
-		goto out_free;
-
-	return 0;
+		free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
-out_free:
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
-out_err:
 	return ret;
 }
 EXPORT_SYMBOL(set_memory_wc);
 
+int _set_memory_wt(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
+}
+
+int set_memory_wt(unsigned long addr, int numpages)
+{
+	int ret;
+
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+			      _PAGE_CACHE_MODE_WT, NULL);
+	if (ret)
+		return ret;
+
+	ret = _set_memory_wt(addr, numpages);
+	if (ret)
+		free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(set_memory_wt);
+
 int _set_memory_wb(unsigned long addr, int numpages)
 {
 	/* WB cache mode is hard wired to all cache attribute bits being 0 */
@@ -1682,6 +1705,7 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 {
 	unsigned long start;
 	unsigned long end;
+	enum page_cache_mode set_type;
 	int i;
 	int free_idx;
 	int ret;
@@ -1695,8 +1719,12 @@ static int _set_pages_array(struct page **pages, int addrinarray,
 			goto err_out;
 	}
 
+	/* If WC, set to UC- first and then WC */
+	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+				_PAGE_CACHE_MODE_UC_MINUS : new_type;
+
 	ret = cpa_set_pages_array(pages, addrinarray,
-			cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+				  cachemode2pgprot(set_type));
 	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
 		ret = change_page_attr_set_clr(NULL, addrinarray,
 					       cachemode2pgprot(
@@ -1730,6 +1758,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray)
 }
 EXPORT_SYMBOL(set_pages_array_wc);
 
+int set_pages_array_wt(struct page **pages, int addrinarray)
+{
+	return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT);
+}
+EXPORT_SYMBOL_GPL(set_pages_array_wt);
+
 int set_pages_wb(struct page *page, int numpages)
 {
 	unsigned long addr = (unsigned long)page_address(page);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 35af6771a95a..188e3e07eeeb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -33,13 +33,17 @@
 #include "pat_internal.h"
 #include "mm_internal.h"
 
-#ifdef CONFIG_X86_PAT
-int __read_mostly pat_enabled = 1;
+#undef pr_fmt
+#define pr_fmt(fmt) "" fmt
+
+static bool boot_cpu_done;
+
+static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
 
 static inline void pat_disable(const char *reason)
 {
-	pat_enabled = 0;
-	printk(KERN_INFO "%s\n", reason);
+	__pat_enabled = 0;
+	pr_info("x86/PAT: %s\n", reason);
 }
 
 static int __init nopat(char *str)
@@ -48,13 +52,12 @@ static int __init nopat(char *str)
 	return 0;
 }
 early_param("nopat", nopat);
-#else
-static inline void pat_disable(const char *reason)
+
+bool pat_enabled(void)
 {
-	(void)reason;
+	return !!__pat_enabled;
 }
-#endif
-
+EXPORT_SYMBOL_GPL(pat_enabled);
 
 int pat_debug_enable;
 
@@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str)
 }
 __setup("debugpat", pat_debug_setup);
 
-static u64 __read_mostly boot_pat_state;
-
 #ifdef CONFIG_X86_PAT
 /*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
- * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_MODE_UC here.
+ * X86 PAT uses page flags arch_1 and uncached together to keep track of
+ * memory type of pages that have backing page struct.
+ *
+ * X86 PAT supports 4 different memory types:
+ *  - _PAGE_CACHE_MODE_WB
+ *  - _PAGE_CACHE_MODE_WC
+ *  - _PAGE_CACHE_MODE_UC_MINUS
+ *  - _PAGE_CACHE_MODE_WT
+ *
+ * _PAGE_CACHE_MODE_WB is the default type.
  */
 
-#define _PGMT_DEFAULT		0
+#define _PGMT_WB		0
 #define _PGMT_WC		(1UL << PG_arch_1)
 #define _PGMT_UC_MINUS		(1UL << PG_uncached)
-#define _PGMT_WB		(1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_WT		(1UL << PG_uncached | 1UL << PG_arch_1)
 #define _PGMT_MASK		(1UL << PG_uncached | 1UL << PG_arch_1)
 #define _PGMT_CLEAR_MASK	(~_PGMT_MASK)
 
@@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg)
 {
 	unsigned long pg_flags = pg->flags & _PGMT_MASK;
 
-	if (pg_flags == _PGMT_DEFAULT)
-		return -1;
+	if (pg_flags == _PGMT_WB)
+		return _PAGE_CACHE_MODE_WB;
 	else if (pg_flags == _PGMT_WC)
 		return _PAGE_CACHE_MODE_WC;
 	else if (pg_flags == _PGMT_UC_MINUS)
 		return _PAGE_CACHE_MODE_UC_MINUS;
 	else
-		return _PAGE_CACHE_MODE_WB;
+		return _PAGE_CACHE_MODE_WT;
 }
 
 static inline void set_page_memtype(struct page *pg,
@@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg,
 	case _PAGE_CACHE_MODE_UC_MINUS:
 		memtype_flags = _PGMT_UC_MINUS;
 		break;
-	case _PAGE_CACHE_MODE_WB:
-		memtype_flags = _PGMT_WB;
+	case _PAGE_CACHE_MODE_WT:
+		memtype_flags = _PGMT_WT;
 		break;
+	case _PAGE_CACHE_MODE_WB:
 	default:
-		memtype_flags = _PGMT_DEFAULT;
+		memtype_flags = _PGMT_WB;
 		break;
 	}
 
@@ -174,78 +180,154 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
  * configuration.
  * Using lower indices is preferred, so we start with highest index.
  */
-void pat_init_cache_modes(void)
+void pat_init_cache_modes(u64 pat)
 {
-	int i;
 	enum page_cache_mode cache;
 	char pat_msg[33];
-	u64 pat;
+	int i;
 
-	rdmsrl(MSR_IA32_CR_PAT, pat);
 	pat_msg[32] = 0;
 	for (i = 7; i >= 0; i--) {
 		cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
 					   pat_msg + 4 * i);
 		update_cache_mode_entry(i, cache);
 	}
-	pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
 }
 
 #define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))
 
-void pat_init(void)
+static void pat_bsp_init(u64 pat)
 {
-	u64 pat;
-	bool boot_cpu = !boot_pat_state;
+	u64 tmp_pat;
 
-	if (!pat_enabled)
+	if (!cpu_has_pat) {
+		pat_disable("PAT not supported by CPU.");
 		return;
+	}
 
-	if (!cpu_has_pat) {
-		if (!boot_pat_state) {
-			pat_disable("PAT not supported by CPU.");
-			return;
-		} else {
-			/*
-			 * If this happens we are on a secondary CPU, but
-			 * switched to PAT on the boot CPU. We have no way to
-			 * undo PAT.
-			 */
-			printk(KERN_ERR "PAT enabled, "
-			       "but not supported by secondary CPU\n");
-			BUG();
-		}
+	if (!pat_enabled())
+		goto done;
+
+	rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
+	if (!tmp_pat) {
+		pat_disable("PAT MSR is 0, disabled.");
+		return;
 	}
 
-	/* Set PWT to Write-Combining. All other bits stay the same */
-	/*
-	 * PTE encoding used in Linux:
-	 *      PAT
-	 *      |PCD
-	 *      ||PWT
-	 *      |||
-	 *      000 WB		_PAGE_CACHE_WB
-	 *      001 WC		_PAGE_CACHE_WC
-	 *      010 UC-		_PAGE_CACHE_UC_MINUS
-	 *      011 UC		_PAGE_CACHE_UC
-	 * PAT bit unused
-	 */
-	pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
-	      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
-
-	/* Boot CPU check */
-	if (!boot_pat_state) {
-		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
-		if (!boot_pat_state) {
-			pat_disable("PAT read returns always zero, disabled.");
-			return;
-		}
+	wrmsrl(MSR_IA32_CR_PAT, pat);
+
+done:
+	pat_init_cache_modes(pat);
+}
+
+static void pat_ap_init(u64 pat)
+{
+	if (!pat_enabled())
+		return;
+
+	if (!cpu_has_pat) {
+		/*
+		 * If this happens we are on a secondary CPU, but switched to
+		 * PAT on the boot CPU. We have no way to undo PAT.
+		 */
+		panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
+}
+
+void pat_init(void)
+{
+	u64 pat;
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (!pat_enabled()) {
+		/*
+		 * No PAT. Emulate the PAT table that corresponds to the two
+		 * cache bits, PWT (Write Through) and PCD (Cache Disable). This
+		 * setup is the same as the BIOS default setup when the system
+		 * has PAT but the "nopat" boot option has been specified. This
+		 * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+		 *
+		 * PTE encoding:
+		 *
+		 *       PCD
+		 *       |PWT  PAT
+		 *       ||    slot
+		 *       00    0    WB : _PAGE_CACHE_MODE_WB
+		 *       01    1    WT : _PAGE_CACHE_MODE_WT
+		 *       10    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *       11    3    UC : _PAGE_CACHE_MODE_UC
+		 *
+		 * NOTE: When WC or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
 
-	if (boot_cpu)
-		pat_init_cache_modes();
+	} else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+		   (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+		    ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+		/*
+		 * PAT support with the lower four entries. Intel Pentium 2,
+		 * 3, M, and 4 are affected by PAT errata, which makes the
+		 * upper four entries unusable. To be on the safe side, we don't
+		 * use those.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 * PAT bit unused
+		 *
+		 * NOTE: When WT or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
+	} else {
+		/*
+		 * Full PAT support.  We put WT in slot 7 to improve
+		 * robustness in the presence of errata that might cause
+		 * the high PAT bit to be ignored.  This way, a buggy slot 7
+		 * access will hit slot 3, and slot 3 is UC, so at worst
+		 * we lose performance without causing a correctness issue.
+		 * Pentium 4 erratum N46 is an example for such an erratum,
+		 * although we try not to use PAT at all on affected CPUs.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 *      100    4    WB : Reserved
+		 *      101    5    WC : Reserved
+		 *      110    6    UC-: Reserved
+		 *      111    7    WT : _PAGE_CACHE_MODE_WT
+		 *
+		 * The reserved slots are unused, but mapped to their
+		 * corresponding types in the presence of PAT errata.
+		 */
+		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
+		      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT);
+	}
+
+	if (!boot_cpu_done) {
+		pat_bsp_init(pat);
+		boot_cpu_done = true;
+	} else {
+		pat_ap_init(pat);
+	}
 }
 
 #undef PAT
@@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
 	 * request is for WB.
 	 */
 	if (req_type == _PAGE_CACHE_MODE_WB) {
-		u8 mtrr_type;
+		u8 mtrr_type, uniform;
 
-		mtrr_type = mtrr_type_lookup(start, end);
+		mtrr_type = mtrr_type_lookup(start, end, &uniform);
 		if (mtrr_type != MTRR_TYPE_WRBACK)
 			return _PAGE_CACHE_MODE_UC_MINUS;
 
@@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
 
 /*
  * For RAM pages, we use page flags to mark the pages with appropriate type.
- * Here we do two pass:
- * - Find the memtype of all the pages in the range, look for any conflicts
- * - In case of no conflicts, set the new memtype for pages in the range
+ * The page flags are limited to four types, WB (default), WC, WT and UC-.
+ * WP request fails with -EINVAL, and UC gets redirected to UC-.  Setting
+ * a new memory type is only allowed for a page mapped with the default WB
+ * type.
+ *
+ * Here we do two passes:
+ * - Find the memtype of all the pages in the range, look for any conflicts.
+ * - In case of no conflicts, set the new memtype for pages in the range.
  */
 static int reserve_ram_pages_type(u64 start, u64 end,
 				  enum page_cache_mode req_type,
@@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end,
 	struct page *page;
 	u64 pfn;
 
+	if (req_type == _PAGE_CACHE_MODE_WP) {
+		if (new_type)
+			*new_type = _PAGE_CACHE_MODE_UC_MINUS;
+		return -EINVAL;
+	}
+
 	if (req_type == _PAGE_CACHE_MODE_UC) {
 		/* We do not support strong UC */
 		WARN_ON_ONCE(1);
@@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end,
 
 		page = pfn_to_page(pfn);
 		type = get_page_memtype(page);
-		if (type != -1) {
-			pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
+		if (type != _PAGE_CACHE_MODE_WB) {
+			pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
 				start, end - 1, type, req_type);
 			if (new_type)
 				*new_type = type;
@@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end)
 
 	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
 		page = pfn_to_page(pfn);
-		set_page_memtype(page, -1);
+		set_page_memtype(page, _PAGE_CACHE_MODE_WB);
 	}
 	return 0;
 }
@@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end)
  * - _PAGE_CACHE_MODE_WC
  * - _PAGE_CACHE_MODE_UC_MINUS
  * - _PAGE_CACHE_MODE_UC
+ * - _PAGE_CACHE_MODE_WT
  *
  * If new_type is NULL, function will return an error if it cannot reserve the
  * region with req_type. If new_type is non-NULL, function will return
@@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	BUG_ON(start >= end); /* end is exclusive */
 
-	if (!pat_enabled) {
+	if (!pat_enabled()) {
 		/* This is identical to page table setting without PAT */
-		if (new_type) {
-			if (req_type == _PAGE_CACHE_MODE_WC)
-				*new_type = _PAGE_CACHE_MODE_UC_MINUS;
-			else
-				*new_type = req_type;
-		}
+		if (new_type)
+			*new_type = req_type;
 		return 0;
 	}
 
@@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
 
 	err = rbt_memtype_check_insert(new, new_type);
 	if (err) {
-		printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
-		       start, end - 1,
-		       cattr_name(new->type), cattr_name(req_type));
+		pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+			start, end - 1,
+			cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
 
@@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end)
 	int is_range_ram;
 	struct memtype *entry;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/* Low ISA region is always mapped WB. No need to track */
@@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end)
 	spin_unlock(&memtype_lock);
 
 	if (!entry) {
-		printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
-		       current->comm, current->pid, start, end - 1);
+		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+			current->comm, current->pid, start, end - 1);
 		return -EINVAL;
 	}
 
@@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end)
  * Only to be called when PAT is enabled
  *
  * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
- * or _PAGE_CACHE_MODE_UC
+ * or _PAGE_CACHE_MODE_WT.
  */
 static enum page_cache_mode lookup_memtype(u64 paddr)
 {
@@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
 
 	if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
 		struct page *page;
-		page = pfn_to_page(paddr >> PAGE_SHIFT);
-		rettype = get_page_memtype(page);
-		/*
-		 * -1 from get_page_memtype() implies RAM page is in its
-		 * default state and not reserved, and hence of type WB
-		 */
-		if (rettype == -1)
-			rettype = _PAGE_CACHE_MODE_WB;
 
-		return rettype;
+		page = pfn_to_page(paddr >> PAGE_SHIFT);
+		return get_page_memtype(page);
 	}
 
 	spin_lock(&memtype_lock);
@@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	u64 to = from + size;
 	u64 cursor = from;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 1;
 
 	while (cursor < to) {
 		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
-			       current->comm, from, to - 1);
+			pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
+				current->comm, from, to - 1);
 			return 0;
 		}
 		cursor += PAGE_SIZE;
@@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	 * caching for the high addresses through the KEN pin, but
 	 * we maintain the tradition of paranoia in this code.
 	 */
-	if (!pat_enabled &&
+	if (!pat_enabled() &&
 	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
 	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
@@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size,
 				size;
 
 	if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
-		printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
-			"for [mem %#010Lx-%#010Lx]\n",
+		pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid,
 			cattr_name(pcm),
 			base, (unsigned long long)(base + size-1));
@@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 	 * the type requested matches the type of first page in the range.
 	 */
 	if (is_ram) {
-		if (!pat_enabled)
+		if (!pat_enabled())
 			return 0;
 
 		pcm = lookup_memtype(paddr);
 		if (want_pcm != pcm) {
-			printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+			pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
 				cattr_name(want_pcm),
 				(unsigned long long)paddr,
@@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		if (strict_prot ||
 		    !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
 			free_memtype(paddr, paddr + size);
-			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
-				" for [mem %#010Lx-%#010Lx], got %s\n",
-				current->comm, current->pid,
-				cattr_name(want_pcm),
-				(unsigned long long)paddr,
-				(unsigned long long)(paddr + size - 1),
-				cattr_name(pcm));
+			pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
+			       current->comm, current->pid,
+			       cattr_name(want_pcm),
+			       (unsigned long long)paddr,
+			       (unsigned long long)(paddr + size - 1),
+			       cattr_name(pcm));
 			return -EINVAL;
 		}
 		/*
@@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 		return ret;
 	}
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/*
@@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 {
 	enum page_cache_mode pcm;
 
-	if (!pat_enabled)
+	if (!pat_enabled())
 		return 0;
 
 	/* Set prot based on lookup */
@@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
-	if (pat_enabled)
-		return __pgprot(pgprot_val(prot) |
+	return __pgprot(pgprot_val(prot) |
 				cachemode2protval(_PAGE_CACHE_MODE_WC));
-	else
-		return pgprot_noncached(prot);
 }
 EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WT));
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
 static struct memtype *memtype_get_idx(loff_t pos)
@@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = {
 
 static int __init pat_memtype_list_init(void)
 {
-	if (pat_enabled) {
+	if (pat_enabled()) {
 		debugfs_create_file("pat_memtype_list", S_IRUSR,
 				    arch_debugfs_dir, NULL, &memtype_fops);
 	}
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index f6411620305d..a739bfc40690 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -4,7 +4,7 @@
 extern int pat_debug_enable;
 
 #define dprintk(fmt, arg...) \
-	do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
+	do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0)
 
 struct memtype {
 	u64			start;
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 6582adcc8bd9..63931080366a 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -160,9 +160,9 @@ success:
 	return 0;
 
 failure:
-	printk(KERN_INFO "%s:%d conflicting memory types "
-		"%Lx-%Lx %s<->%s\n", current->comm, current->pid, start,
-		end, cattr_name(found_type), cattr_name(match->type));
+	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+		current->comm, current->pid, start, end,
+		cattr_name(found_type), cattr_name(match->type));
 	return -EBUSY;
 }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 0b97d2c75df3..fb0a9dd1d6e4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
 }
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+/**
+ * pud_set_huge - setup kernel PUD mapping
+ *
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if any of the following conditions are met:
+ *
+ * - MTRRs are disabled, or
+ *
+ * - MTRRs are enabled and the range is completely covered by a single MTRR, or
+ *
+ * - MTRRs are enabled and the corresponding MTRR memory type is WB, which
+ *   has no effect on the requested PAT memory type.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 {
-	u8 mtrr;
+	u8 mtrr, uniform;
 
-	/*
-	 * Do not use a huge page when the range is covered by non-WB type
-	 * of MTRRs.
-	 */
-	mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE);
-	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+	mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+	if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+	    (mtrr != MTRR_TYPE_WRBACK))
 		return 0;
 
 	prot = pgprot_4k_2_large(prot);
@@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 	return 1;
 }
 
+/**
+ * pmd_set_huge - setup kernel PMD mapping
+ *
+ * See text over pud_set_huge() above.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
-	u8 mtrr;
+	u8 mtrr, uniform;
 
-	/*
-	 * Do not use a huge page when the range is covered by non-WB type
-	 * of MTRRs.
-	 */
-	mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE);
-	if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF))
+	mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+	if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) &&
+	    (mtrr != MTRR_TYPE_WRBACK)) {
+		pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+			     __func__, addr, addr + PMD_SIZE);
 		return 0;
+	}
 
 	prot = pgprot_4k_2_large(prot);
 
@@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 	return 1;
 }
 
+/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
 int pud_clear_huge(pud_t *pud)
 {
 	if (pud_large(*pud)) {
@@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud)
 	return 0;
 }
 
+/**
+ * pmd_clear_huge - clear kernel PMD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PMD map is found).
+ */
 int pmd_clear_huge(pmd_t *pmd)
 {
 	if (pmd_large(*pmd)) {
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 6440221ced0d..4093216b3791 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -8,7 +8,6 @@
  * of the License.
  */
 #include <linux/linkage.h>
-#include <asm/dwarf2.h>
 
 /*
  * Calling convention :
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 987514396c1e..579a8fd74be0 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
 #include <asm/cacheflush.h>
+#include <linux/bpf.h>
 
 int bpf_jit_enable __read_mostly;
 
@@ -37,7 +38,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 	return ptr + len;
 }
 
-#define EMIT(bytes, len)	do { prog = emit_code(prog, bytes, len); } while (0)
+#define EMIT(bytes, len) \
+	do { prog = emit_code(prog, bytes, len); cnt += len; } while (0)
 
 #define EMIT1(b1)		EMIT(b1, 1)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
@@ -186,31 +188,31 @@ struct jit_context {
 #define BPF_MAX_INSN_SIZE	128
 #define BPF_INSN_SAFETY		64
 
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
-		  int oldproglen, struct jit_context *ctx)
+#define STACKSIZE \
+	(MAX_BPF_STACK + \
+	 32 /* space for rbx, r13, r14, r15 */ + \
+	 8 /* space for skb_copy_bits() buffer */)
+
+#define PROLOGUE_SIZE 51
+
+/* emit x64 prologue code for BPF program and check it's size.
+ * bpf_tail_call helper will skip it while jumping into another program
+ */
+static void emit_prologue(u8 **pprog)
 {
-	struct bpf_insn *insn = bpf_prog->insnsi;
-	int insn_cnt = bpf_prog->len;
-	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
-	bool seen_exit = false;
-	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
-	int i;
-	int proglen = 0;
-	u8 *prog = temp;
-	int stacksize = MAX_BPF_STACK +
-		32 /* space for rbx, r13, r14, r15 */ +
-		8 /* space for skb_copy_bits() buffer */;
+	u8 *prog = *pprog;
+	int cnt = 0;
 
 	EMIT1(0x55); /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
 
-	/* sub rsp, stacksize */
-	EMIT3_off32(0x48, 0x81, 0xEC, stacksize);
+	/* sub rsp, STACKSIZE */
+	EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE);
 
 	/* all classic BPF filters use R6(rbx) save it */
 
 	/* mov qword ptr [rbp-X],rbx */
-	EMIT3_off32(0x48, 0x89, 0x9D, -stacksize);
+	EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE);
 
 	/* bpf_convert_filter() maps classic BPF register X to R7 and uses R8
 	 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
@@ -221,16 +223,112 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	 */
 
 	/* mov qword ptr [rbp-X],r13 */
-	EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8);
+	EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8);
 	/* mov qword ptr [rbp-X],r14 */
-	EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16);
+	EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16);
 	/* mov qword ptr [rbp-X],r15 */
-	EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24);
+	EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24);
 
 	/* clear A and X registers */
 	EMIT2(0x31, 0xc0); /* xor eax, eax */
 	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
 
+	/* clear tail_cnt: mov qword ptr [rbp-X], rax */
+	EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32);
+
+	BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+	*pprog = prog;
+}
+
+/* generate the following code:
+ * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
+ *   if (index >= array->map.max_entries)
+ *     goto out;
+ *   if (++tail_call_cnt > MAX_TAIL_CALL_CNT)
+ *     goto out;
+ *   prog = array->prog[index];
+ *   if (prog == NULL)
+ *     goto out;
+ *   goto *(prog->bpf_func + prologue_size);
+ * out:
+ */
+static void emit_bpf_tail_call(u8 **pprog)
+{
+	u8 *prog = *pprog;
+	int label1, label2, label3;
+	int cnt = 0;
+
+	/* rdi - pointer to ctx
+	 * rsi - pointer to bpf_array
+	 * rdx - index in bpf_array
+	 */
+
+	/* if (index >= array->map.max_entries)
+	 *   goto out;
+	 */
+	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
+	      offsetof(struct bpf_array, map.max_entries));
+	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
+#define OFFSET1 44 /* number of bytes to jump */
+	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
+	label1 = cnt;
+
+	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
+	 *   goto out;
+	 */
+	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
+	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
+#define OFFSET2 33
+	EMIT2(X86_JA, OFFSET2);                   /* ja out */
+	label2 = cnt;
+	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
+	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
+
+	/* prog = array->prog[index]; */
+	EMIT4(0x48, 0x8D, 0x44, 0xD6);            /* lea rax, [rsi + rdx * 8 + 0x50] */
+	EMIT1(offsetof(struct bpf_array, prog));
+	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
+
+	/* if (prog == NULL)
+	 *   goto out;
+	 */
+	EMIT4(0x48, 0x83, 0xF8, 0x00);            /* cmp rax, 0 */
+#define OFFSET3 10
+	EMIT2(X86_JE, OFFSET3);                   /* je out */
+	label3 = cnt;
+
+	/* goto *(prog->bpf_func + prologue_size); */
+	EMIT4(0x48, 0x8B, 0x40,                   /* mov rax, qword ptr [rax + 32] */
+	      offsetof(struct bpf_prog, bpf_func));
+	EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE);   /* add rax, prologue_size */
+
+	/* now we're ready to jump into next BPF program
+	 * rdi == ctx (1st arg)
+	 * rax == prog->bpf_func + prologue_size
+	 */
+	EMIT2(0xFF, 0xE0);                        /* jmp rax */
+
+	/* out: */
+	BUILD_BUG_ON(cnt - label1 != OFFSET1);
+	BUILD_BUG_ON(cnt - label2 != OFFSET2);
+	BUILD_BUG_ON(cnt - label3 != OFFSET3);
+	*pprog = prog;
+}
+
+static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+		  int oldproglen, struct jit_context *ctx)
+{
+	struct bpf_insn *insn = bpf_prog->insnsi;
+	int insn_cnt = bpf_prog->len;
+	bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+	bool seen_exit = false;
+	u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
+	int i, cnt = 0;
+	int proglen = 0;
+	u8 *prog = temp;
+
+	emit_prologue(&prog);
+
 	if (seen_ld_abs) {
 		/* r9d : skb->len - skb->data_len (headlen)
 		 * r10 : skb->data
@@ -559,6 +657,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 				if (is_ereg(dst_reg))
 					EMIT1(0x41);
 				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+
+				/* emit 'movzwl eax, ax' */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
 				break;
 			case 32:
 				/* emit 'bswap eax' to swap lower 4 bytes */
@@ -577,6 +682,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			switch (imm32) {
+			case 16:
+				/* emit 'movzwl eax, ax' to zero extend 16-bit
+				 * into 64 bit
+				 */
+				if (is_ereg(dst_reg))
+					EMIT3(0x45, 0x0F, 0xB7);
+				else
+					EMIT2(0x0F, 0xB7);
+				EMIT1(add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 32:
+				/* emit 'mov eax, eax' to clear upper 32-bits */
+				if (is_ereg(dst_reg))
+					EMIT1(0x45);
+				EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg));
+				break;
+			case 64:
+				/* nop */
+				break;
+			}
 			break;
 
 			/* ST: *(u8*)(dst_reg + off) = imm */
@@ -711,6 +837,10 @@ xadd:			if (is_imm8(insn->off))
 			}
 			break;
 
+		case BPF_JMP | BPF_CALL | BPF_X:
+			emit_bpf_tail_call(&prog);
+			break;
+
 			/* cond jump */
 		case BPF_JMP | BPF_JEQ | BPF_X:
 		case BPF_JMP | BPF_JNE | BPF_X:
@@ -863,13 +993,13 @@ common_load:
 			/* update cleanup_addr */
 			ctx->cleanup_addr = proglen;
 			/* mov rbx, qword ptr [rbp-X] */
-			EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize);
+			EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE);
 			/* mov r13, qword ptr [rbp-X] */
-			EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8);
+			EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8);
 			/* mov r14, qword ptr [rbp-X] */
-			EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16);
+			EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16);
 			/* mov r15, qword ptr [rbp-X] */
-			EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24);
+			EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24);
 
 			EMIT1(0xC9); /* leave */
 			EMIT1(0xC3); /* ret */
@@ -938,7 +1068,12 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 	ctx.cleanup_addr = proglen;
 
-	for (pass = 0; pass < 10; pass++) {
+	/* JITed image shrinks with every pass and the loop iterates
+	 * until the image stops shrinking. Very large bpf programs
+	 * may converge on the last pass. In such case do one more
+	 * pass to emit the final image
+	 */
+	for (pass = 0; pass < 10 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
 			image = NULL;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index e4695985f9de..ff9911707160 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -81,6 +81,17 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
 		},
 	},
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/931368 */
+	/* https://bugs.launchpad.net/ubuntu/+source/alsa-driver/+bug/1033299 */
+	{
+		.callback = set_use_crs,
+		.ident = "Foxconn K8M890-8237A",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Foxconn"),
+			DMI_MATCH(DMI_BOARD_NAME, "K8M890-8237A"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+		},
+	},
 
 	/* Now for the blacklist.. */
 
@@ -121,8 +132,10 @@ void __init pci_acpi_crs_quirks(void)
 {
 	int year;
 
-	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008)
-		pci_use_crs = false;
+	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year < 2008) {
+		if (iomem_resource.end <= 0xffffffff)
+			pci_use_crs = false;
+	}
 
 	dmi_check_system(pci_crs_quirks);
 
@@ -325,6 +338,26 @@ static void release_pci_root_info(struct pci_host_bridge *bridge)
 	kfree(info);
 }
 
+/*
+ * An IO port or MMIO resource assigned to a PCI host bridge may be
+ * consumed by the host bridge itself or available to its child
+ * bus/devices. The ACPI specification defines a bit (Producer/Consumer)
+ * to tell whether the resource is consumed by the host bridge itself,
+ * but firmware hasn't used that bit consistently, so we can't rely on it.
+ *
+ * On x86 and IA64 platforms, all IO port and MMIO resources are assumed
+ * to be available to child bus/devices except one special case:
+ *     IO port [0xCF8-0xCFF] is consumed by the host bridge itself
+ *     to access PCI configuration space.
+ *
+ * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF].
+ */
+static bool resource_is_pcicfg_ioport(struct resource *res)
+{
+	return (res->flags & IORESOURCE_IO) &&
+		res->start == 0xCF8 && res->end == 0xCFF;
+}
+
 static void probe_pci_root_info(struct pci_root_info *info,
 				struct acpi_device *device,
 				int busnum, int domain,
@@ -346,8 +379,8 @@ static void probe_pci_root_info(struct pci_root_info *info,
 			"no IO and memory resources present in _CRS\n");
 	else
 		resource_list_for_each_entry_safe(entry, tmp, list) {
-			if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
-			    (entry->res->flags & IORESOURCE_DISABLED))
+			if ((entry->res->flags & IORESOURCE_DISABLED) ||
+			    resource_is_pcicfg_ioport(entry->res))
 				resource_list_destroy_entry(entry);
 			else
 				entry->res->name = info->name;
@@ -462,9 +495,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
-	struct pci_sysdata *sd = bridge->bus->sysdata;
-
-	ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+	/*
+	 * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+	 * here, pci_create_root_bus() has been called by someone else and
+	 * sysdata is likely to be different from what we expect.  Let it go in
+	 * that case.
+	 */
+	if (!bridge->dev.parent) {
+		struct pci_sysdata *sd = bridge->bus->sysdata;
+		ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+	}
 	return 0;
 }
 
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 349c0d32cc0b..0a9f2caf358f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -429,12 +429,12 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
  	 * Caller can followup with UC MINUS request and add a WC mtrr if there
  	 * is a free mtrr slot.
  	 */
-	if (!pat_enabled && write_combine)
+	if (!pat_enabled() && write_combine)
 		return -EINVAL;
 
-	if (pat_enabled && write_combine)
+	if (pat_enabled() && write_combine)
 		prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
-	else if (pat_enabled || boot_cpu_data.x86 > 3)
+	else if (pat_enabled() || boot_cpu_data.x86 > 3)
 		/*
 		 * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
 		 * To avoid attribute conflicts, request UC MINUS here
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 852aa4c92da0..27062303c881 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -208,6 +208,7 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
 
 static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
+	struct irq_alloc_info info;
 	int polarity;
 
 	if (dev->irq_managed && dev->irq > 0)
@@ -217,14 +218,13 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 		polarity = 0; /* active high */
 	else
 		polarity = 1; /* active low */
+	ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
 
 	/*
 	 * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
 	 * IOAPIC RTE entries, so we just enable RTE for the device.
 	 */
-	if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev)))
-		return -EBUSY;
-	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
+	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info) < 0)
 		return -EBUSY;
 
 	dev->irq_managed = 1;
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 5dc6ca5e1741..9bd115484745 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -146,19 +146,20 @@ static void __init pirq_peer_trick(void)
 
 /*
  *  Code for querying and setting of IRQ routes on various interrupt routers.
+ *  PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1.
  */
 
-void eisa_set_level_irq(unsigned int irq)
+void elcr_set_level_irq(unsigned int irq)
 {
 	unsigned char mask = 1 << (irq & 7);
 	unsigned int port = 0x4d0 + (irq >> 3);
 	unsigned char val;
-	static u16 eisa_irq_mask;
+	static u16 elcr_irq_mask;
 
-	if (irq >= 16 || (1 << irq) & eisa_irq_mask)
+	if (irq >= 16 || (1 << irq) & elcr_irq_mask)
 		return;
 
-	eisa_irq_mask |= (1 << irq);
+	elcr_irq_mask |= (1 << irq);
 	printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq);
 	val = inb(port);
 	if (!(val & mask)) {
@@ -965,11 +966,11 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
 	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
 		msg = "found";
-		eisa_set_level_irq(irq);
+		elcr_set_level_irq(irq);
 	} else if (newirq && r->set &&
 		(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
 		if (r->set(pirq_router_dev, dev, pirq, newirq)) {
-			eisa_set_level_irq(newirq);
+			elcr_set_level_irq(newirq);
 			msg = "assigned";
 			irq = newirq;
 		}
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index a62e0be3a2f1..f1a6c8e86ddd 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -1,4 +1,5 @@
 # Platform specific code goes here
+obj-y	+= atom/
 obj-y	+= ce4100/
 obj-y	+= efi/
 obj-y	+= geode/
diff --git a/arch/x86/platform/atom/Makefile b/arch/x86/platform/atom/Makefile
new file mode 100644
index 000000000000..0a3a40cbc794
--- /dev/null
+++ b/arch/x86/platform/atom/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
new file mode 100644
index 000000000000..5ca8ead91579
--- /dev/null
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -0,0 +1,183 @@
+/*
+ * Intel SOC Punit device state debug driver
+ * Punit controls power management for North Complex devices (Graphics
+ * blocks, Image Signal Processing, video processing, display, DSP etc.)
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/io.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+/* Side band Interface port */
+#define PUNIT_PORT		0x04
+/* Power gate status reg */
+#define PWRGT_STATUS		0x61
+/* Subsystem config/status Video processor */
+#define VED_SS_PM0		0x32
+/* Subsystem config/status ISP (Image Signal Processor) */
+#define ISP_SS_PM0		0x39
+/* Subsystem config/status Input/output controller */
+#define MIO_SS_PM		0x3B
+/* Shift bits for getting status for video, isp and i/o */
+#define SSS_SHIFT		24
+/* Shift bits for getting status for graphics rendering */
+#define RENDER_POS		0
+/* Shift bits for getting status for media control */
+#define MEDIA_POS		2
+/* Shift bits for getting status for Valley View/Baytrail display */
+#define VLV_DISPLAY_POS		6
+/* Subsystem config/status display for Cherry Trail SOC */
+#define CHT_DSP_SSS		0x36
+/* Shift bits for getting status for display */
+#define CHT_DSP_SSS_POS		16
+
+struct punit_device {
+	char *name;
+	int reg;
+	int sss_pos;
+};
+
+static const struct punit_device punit_device_byt[] = {
+	{ "GFX RENDER",	PWRGT_STATUS,	RENDER_POS },
+	{ "GFX MEDIA",	PWRGT_STATUS,	MEDIA_POS },
+	{ "DISPLAY",	PWRGT_STATUS,	VLV_DISPLAY_POS },
+	{ "VED",	VED_SS_PM0,	SSS_SHIFT },
+	{ "ISP",	ISP_SS_PM0,	SSS_SHIFT },
+	{ "MIO",	MIO_SS_PM,	SSS_SHIFT },
+	{ NULL }
+};
+
+static const struct punit_device punit_device_cht[] = {
+	{ "GFX RENDER",	PWRGT_STATUS,	RENDER_POS },
+	{ "GFX MEDIA",	PWRGT_STATUS,	MEDIA_POS },
+	{ "DISPLAY",	CHT_DSP_SSS,	CHT_DSP_SSS_POS },
+	{ "VED",	VED_SS_PM0,	SSS_SHIFT },
+	{ "ISP",	ISP_SS_PM0,	SSS_SHIFT },
+	{ "MIO",	MIO_SS_PM,	SSS_SHIFT },
+	{ NULL }
+};
+
+static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"};
+
+static int punit_dev_state_show(struct seq_file *seq_file, void *unused)
+{
+	u32 punit_pwr_status;
+	struct punit_device *punit_devp = seq_file->private;
+	int index;
+	int status;
+
+	seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n");
+	while (punit_devp->name) {
+		status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ,
+				       punit_devp->reg,
+				       &punit_pwr_status);
+		if (status) {
+			seq_printf(seq_file, "%9s : Read Failed\n",
+				   punit_devp->name);
+		} else  {
+			index = (punit_pwr_status >> punit_devp->sss_pos) & 3;
+			seq_printf(seq_file, "%9s : %s\n", punit_devp->name,
+				   dstates[index]);
+		}
+		punit_devp++;
+	}
+
+	return 0;
+}
+
+static int punit_dev_state_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, punit_dev_state_show, inode->i_private);
+}
+
+static const struct file_operations punit_dev_state_ops = {
+	.open		= punit_dev_state_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *punit_dbg_file;
+
+static int punit_dbgfs_register(struct punit_device *punit_device)
+{
+	static struct dentry *dev_state;
+
+	punit_dbg_file = debugfs_create_dir("punit_atom", NULL);
+	if (!punit_dbg_file)
+		return -ENXIO;
+
+	dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO,
+					punit_dbg_file, punit_device,
+					&punit_dev_state_ops);
+	if (!dev_state) {
+		pr_err("punit_dev_state register failed\n");
+		debugfs_remove(punit_dbg_file);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void punit_dbgfs_unregister(void)
+{
+	debugfs_remove_recursive(punit_dbg_file);
+}
+
+#define ICPU(model, drv_data) \
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
+	  (kernel_ulong_t)&drv_data }
+
+static const struct x86_cpu_id intel_punit_cpu_ids[] = {
+	ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */
+	ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */
+	{}
+};
+
+MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
+
+static int __init punit_atom_debug_init(void)
+{
+	const struct x86_cpu_id *id;
+	int ret;
+
+	id = x86_match_cpu(intel_punit_cpu_ids);
+	if (!id)
+		return -ENODEV;
+
+	ret = punit_dbgfs_register((struct punit_device *)id->driver_data);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static void __exit punit_atom_debug_exit(void)
+{
+	punit_dbgfs_unregister();
+}
+
+module_init(punit_atom_debug_init);
+module_exit(punit_atom_debug_exit);
+
+MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Driver for Punit devices states debugging");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 02744df576d5..c1c382c58c60 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -117,6 +117,27 @@ void efi_get_time(struct timespec *now)
 	now->tv_nsec = 0;
 }
 
+void __init efi_find_mirror(void)
+{
+	void *p;
+	u64 mirror_size = 0, total_size = 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		total_size += size;
+		if (md->attribute & EFI_MEMORY_MORE_RELIABLE) {
+			memblock_mark_mirror(start, size);
+			mirror_size += size;
+		}
+	}
+	if (mirror_size)
+		pr_info("Memory: %lldM/%lldM mirrored memory\n",
+			mirror_size>>20, total_size>>20);
+}
+
 /*
  * Tell the kernel about the EFI memory map.  This might include
  * more than the max 128 entries that can fit in the e820 legacy
@@ -501,6 +522,8 @@ void __init efi_init(void)
 
 	if (efi_enabled(EFI_DBG))
 		print_efi_memmap();
+
+	efi_esrt_init();
 }
 
 void __init efi_late_init(void)
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
index 0b283d4d0ad7..de734134bc8d 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -27,6 +27,7 @@ static struct platform_device wdt_dev = {
 static int tangier_probe(struct platform_device *pdev)
 {
 	int gsi;
+	struct irq_alloc_info info;
 	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
 
 	if (!pdata)
@@ -34,8 +35,8 @@ static int tangier_probe(struct platform_device *pdev)
 
 	/* IOAPIC builds identity mapping between GSI and IRQ on MID */
 	gsi = pdata->irq;
-	if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) ||
-	    mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) {
+	ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
+	if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
 		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
 			 gsi);
 		return -EINVAL;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 3005f0c89f2e..01d54ea766c1 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -81,26 +81,34 @@ static unsigned long __init intel_mid_calibrate_tsc(void)
 	return 0;
 }
 
+static void __init intel_mid_setup_bp_timer(void)
+{
+	apbt_time_init();
+	setup_boot_APIC_clock();
+}
+
 static void __init intel_mid_time_init(void)
 {
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+
 	switch (intel_mid_timer_options) {
 	case INTEL_MID_TIMER_APBT_ONLY:
 		break;
 	case INTEL_MID_TIMER_LAPIC_APBT:
-		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+		/* Use apbt and local apic */
+		x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer;
 		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
-		break;
+		return;
 	default:
 		if (!boot_cpu_has(X86_FEATURE_ARAT))
 			break;
+		/* Lapic only, no apbt */
 		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
 		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
 		return;
 	}
-	/* we need at least one APB timer */
-	pre_init_apic_IRQ0();
-	apbt_time_init();
+
+	x86_init.timers.setup_percpu_clockev = apbt_time_init;
 }
 
 static void intel_mid_arch_setup(void)
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index c14ad34776c4..ce992e8cc065 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -95,18 +95,16 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
 		pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
 			totallen, (u32)pentry->phys_addr,
 			pentry->freq_hz, pentry->irq);
-			if (!pentry->irq)
-				continue;
-			mp_irq.type = MP_INTSRC;
-			mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
-			mp_irq.irqflag = 5;
-			mp_irq.srcbus = MP_BUS_ISA;
-			mp_irq.srcbusirq = pentry->irq;	/* IRQ */
-			mp_irq.dstapic = MP_APIC_ALL;
-			mp_irq.dstirq = pentry->irq;
-			mp_save_irq(&mp_irq);
-			mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+		mp_irq.type = MP_INTSRC;
+		mp_irq.irqtype = mp_INT;
+		/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+		mp_irq.irqflag = 5;
+		mp_irq.srcbus = MP_BUS_ISA;
+		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
+		mp_irq.dstapic = MP_APIC_ALL;
+		mp_irq.dstirq = pentry->irq;
+		mp_save_irq(&mp_irq);
+		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
 	}
 
 	return 0;
@@ -177,7 +175,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 		mp_irq.dstapic = MP_APIC_ALL;
 		mp_irq.dstirq = pentry->irq;
 		mp_save_irq(&mp_irq);
-		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
+		mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL);
 	}
 	return 0;
 }
@@ -436,6 +434,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 	struct devs_id *dev = NULL;
 	int num, i, ret;
 	int polarity;
+	struct irq_alloc_info info;
 
 	sb = (struct sfi_table_simple *)table;
 	num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
@@ -469,9 +468,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 				polarity = 1;
 			}
 
-			ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE);
-			if (ret == 0)
-				ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC);
+			ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity);
+			ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info);
 			WARN_ON(ret < 0);
 		}
 
diff --git a/arch/x86/platform/sfi/sfi.c b/arch/x86/platform/sfi/sfi.c
index 2a8a74f3bd76..6c7111bbd1e9 100644
--- a/arch/x86/platform/sfi/sfi.c
+++ b/arch/x86/platform/sfi/sfi.c
@@ -25,8 +25,8 @@
 #include <linux/init.h>
 #include <linux/sfi.h>
 #include <linux/io.h>
-#include <linux/irqdomain.h>
 
+#include <asm/irqdomain.h>
 #include <asm/io_apic.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
@@ -71,9 +71,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table)
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_IO_APIC
-static struct irq_domain_ops sfi_ioapic_irqdomain_ops = {
-	.map = mp_irqdomain_map,
-};
 
 static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 {
@@ -82,7 +79,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table)
 	int i, num;
 	struct ioapic_domain_cfg cfg = {
 		.type = IOAPIC_DOMAIN_STRICT,
-		.ops = &sfi_ioapic_irqdomain_ops,
+		.ops = &mp_ioapic_irqdomain_ops,
 	};
 
 	sb = (struct sfi_table_simple *)table;
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 0ce673645432..8570abe68be1 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -13,22 +13,37 @@
 #include <linux/slab.h>
 #include <linux/irq.h>
 
+#include <asm/irqdomain.h>
 #include <asm/apic.h>
 #include <asm/uv/uv_irq.h>
 #include <asm/uv/uv_hub.h>
 
 /* MMR offset and pnode of hub sourcing interrupts for a given irq */
-struct uv_irq_2_mmr_pnode{
-	struct rb_node		list;
+struct uv_irq_2_mmr_pnode {
 	unsigned long		offset;
 	int			pnode;
-	int			irq;
 };
 
-static DEFINE_SPINLOCK(uv_irq_lock);
-static struct rb_root		uv_irq_root;
+static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info)
+{
+	unsigned long mmr_value;
+	struct uv_IO_APIC_route_entry *entry;
+
+	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
+		     sizeof(unsigned long));
+
+	mmr_value = 0;
+	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+	entry->vector		= cfg->vector;
+	entry->delivery_mode	= apic->irq_delivery_mode;
+	entry->dest_mode	= apic->irq_dest_mode;
+	entry->polarity		= 0;
+	entry->trigger		= 0;
+	entry->mask		= 0;
+	entry->dest		= cfg->dest_apicid;
 
-static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
+	uv_write_global_mmr64(info->pnode, info->offset, mmr_value);
+}
 
 static void uv_noop(struct irq_data *data) { }
 
@@ -37,6 +52,23 @@ static void uv_ack_apic(struct irq_data *data)
 	ack_APIC_irq();
 }
 
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret >= 0) {
+		uv_program_mmr(cfg, data->chip_data);
+		send_cleanup_vector(cfg);
+	}
+
+	return ret;
+}
+
 static struct irq_chip uv_irq_chip = {
 	.name			= "UV-CORE",
 	.irq_mask		= uv_noop,
@@ -45,189 +77,99 @@ static struct irq_chip uv_irq_chip = {
 	.irq_set_affinity	= uv_set_irq_affinity,
 };
 
-/*
- * Add offset and pnode information of the hub sourcing interrupts to the
- * rb tree for a specific irq.
- */
-static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade)
+static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
+			   unsigned int nr_irqs, void *arg)
 {
-	struct rb_node **link = &uv_irq_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct uv_irq_2_mmr_pnode *n;
-	struct uv_irq_2_mmr_pnode *e;
-	unsigned long irqflags;
-
-	n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL,
-				uv_blade_to_memory_nid(blade));
-	if (!n)
+	struct uv_irq_2_mmr_pnode *chip_data;
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+	int ret;
+
+	if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV)
+		return -EINVAL;
+
+	chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL,
+				 irq_data->node);
+	if (!chip_data)
 		return -ENOMEM;
 
-	n->irq = irq;
-	n->offset = offset;
-	n->pnode = uv_blade_to_pnode(blade);
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	/* Find the right place in the rbtree: */
-	while (*link) {
-		parent = *link;
-		e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list);
-
-		if (unlikely(irq == e->irq)) {
-			/* irq entry exists */
-			e->pnode = uv_blade_to_pnode(blade);
-			e->offset = offset;
-			spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-			kfree(n);
-			return 0;
-		}
-
-		if (irq < e->irq)
-			link = &(*link)->rb_left;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret >= 0) {
+		if (info->uv_limit == UV_AFFINITY_CPU)
+			irq_set_status_flags(virq, IRQ_NO_BALANCING);
 		else
-			link = &(*link)->rb_right;
+			irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+
+		chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
+		chip_data->offset = info->uv_offset;
+		irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
+				    handle_percpu_irq, NULL, info->uv_name);
+	} else {
+		kfree(chip_data);
 	}
 
-	/* Insert the node into the rbtree. */
-	rb_link_node(&n->list, parent, link);
-	rb_insert_color(&n->list, &uv_irq_root);
-
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	return 0;
+	return ret;
 }
 
-/* Retrieve offset and pnode information from the rb tree for a specific irq */
-int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode)
+static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
+			   unsigned int nr_irqs)
 {
-	struct uv_irq_2_mmr_pnode *e;
-	struct rb_node *n;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	n = uv_irq_root.rb_node;
-	while (n) {
-		e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-
-		if (e->irq == irq) {
-			*offset = e->offset;
-			*pnode = e->pnode;
-			spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-			return 0;
-		}
-
-		if (irq < e->irq)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	return -1;
+	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
+
+	BUG_ON(nr_irqs != 1);
+	kfree(irq_data->chip_data);
+	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+	irq_clear_status_flags(virq, IRQ_NO_BALANCING);
+	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
 /*
  * Re-target the irq to the specified CPU and enable the specified MMR located
  * on the specified blade to allow the sending of MSIs to the specified CPU.
  */
-static int
-arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
-		       unsigned long mmr_offset, int limit)
+static void uv_domain_activate(struct irq_domain *domain,
+			       struct irq_data *irq_data)
 {
-	const struct cpumask *eligible_cpu = cpumask_of(cpu);
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned long mmr_value;
-	struct uv_IO_APIC_route_entry *entry;
-	int mmr_pnode, err;
-	unsigned int dest;
-
-	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
-			sizeof(unsigned long));
-
-	err = assign_irq_vector(irq, cfg, eligible_cpu);
-	if (err != 0)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
-	if (err != 0)
-		return err;
-
-	if (limit == UV_AFFINITY_CPU)
-		irq_set_status_flags(irq, IRQ_NO_BALANCING);
-	else
-		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
-	irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
-				      irq_name);
-
-	mmr_value = 0;
-	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-	entry->vector		= cfg->vector;
-	entry->delivery_mode	= apic->irq_delivery_mode;
-	entry->dest_mode	= apic->irq_dest_mode;
-	entry->polarity		= 0;
-	entry->trigger		= 0;
-	entry->mask		= 0;
-	entry->dest		= dest;
-
-	mmr_pnode = uv_blade_to_pnode(mmr_blade);
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
-
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
-
-	return irq;
+	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
 }
 
 /*
  * Disable the specified MMR located on the specified blade so that MSIs are
  * longer allowed to be sent.
  */
-static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
+static void uv_domain_deactivate(struct irq_domain *domain,
+				 struct irq_data *irq_data)
 {
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
 
-	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
-			sizeof(unsigned long));
-
 	mmr_value = 0;
 	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
 	entry->mask = 1;
-
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
 }
 
-static int
-uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
-		    bool force)
-{
-	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest;
-	unsigned long mmr_value, mmr_offset;
-	struct uv_IO_APIC_route_entry *entry;
-	int mmr_pnode;
-
-	if (apic_set_affinity(data, mask, &dest))
-		return -1;
-
-	mmr_value = 0;
-	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
-
-	entry->vector		= cfg->vector;
-	entry->delivery_mode	= apic->irq_delivery_mode;
-	entry->dest_mode	= apic->irq_dest_mode;
-	entry->polarity		= 0;
-	entry->trigger		= 0;
-	entry->mask		= 0;
-	entry->dest		= dest;
-
-	/* Get previously stored MMR and pnode of hub sourcing interrupts */
-	if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
-		return -1;
-
-	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+static const struct irq_domain_ops uv_domain_ops = {
+	.alloc		= uv_domain_alloc,
+	.free		= uv_domain_free,
+	.activate	= uv_domain_activate,
+	.deactivate	= uv_domain_deactivate,
+};
 
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+static struct irq_domain *uv_get_irq_domain(void)
+{
+	static struct irq_domain *uv_domain;
+	static DEFINE_MUTEX(uv_lock);
+
+	mutex_lock(&uv_lock);
+	if (uv_domain == NULL) {
+		uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL);
+		if (uv_domain)
+			uv_domain->parent = x86_vector_domain;
+	}
+	mutex_unlock(&uv_lock);
 
-	return IRQ_SET_MASK_OK_NOCOPY;
+	return uv_domain;
 }
 
 /*
@@ -238,19 +180,21 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
 int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
 		 unsigned long mmr_offset, int limit)
 {
-	int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+	struct irq_alloc_info info;
+	struct irq_domain *domain = uv_get_irq_domain();
 
-	if (!irq)
-		return -EBUSY;
+	if (!domain)
+		return -ENOMEM;
 
-	ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,
-		limit);
-	if (ret == irq)
-		uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
-	else
-		irq_free_hwirq(irq);
+	init_irq_alloc_info(&info, cpumask_of(cpu));
+	info.type = X86_IRQ_ALLOC_TYPE_UV;
+	info.uv_limit = limit;
+	info.uv_blade = mmr_blade;
+	info.uv_offset = mmr_offset;
+	info.uv_name = irq_name;
 
-	return ret;
+	return irq_domain_alloc_irqs(domain, 1,
+				     uv_blade_to_memory_nid(mmr_blade), &info);
 }
 EXPORT_SYMBOL_GPL(uv_setup_irq);
 
@@ -263,26 +207,6 @@ EXPORT_SYMBOL_GPL(uv_setup_irq);
  */
 void uv_teardown_irq(unsigned int irq)
 {
-	struct uv_irq_2_mmr_pnode *e;
-	struct rb_node *n;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&uv_irq_lock, irqflags);
-	n = uv_irq_root.rb_node;
-	while (n) {
-		e = rb_entry(n, struct uv_irq_2_mmr_pnode, list);
-		if (e->irq == irq) {
-			arch_disable_uv_irq(e->pnode, e->offset);
-			rb_erase(n, &uv_irq_root);
-			kfree(e);
-			break;
-		}
-		if (irq < e->irq)
-			n = n->rb_left;
-		else
-			n = n->rb_right;
-	}
-	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	irq_free_hwirq(irq);
+	irq_domain_free_irqs(irq, 1);
 }
 EXPORT_SYMBOL_GPL(uv_teardown_irq);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 757678fb26e1..0d7dd1f5ac36 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -18,10 +18,9 @@
 #include <asm/mtrr.h>
 #include <asm/page.h>
 #include <asm/mce.h>
-#include <asm/xcr.h>
 #include <asm/suspend.h>
+#include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
-#include <asm/fpu-internal.h> /* pcntxt_mask */
 #include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
@@ -155,6 +154,8 @@ static void fix_processor_context(void)
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_LDT(&current->active_mm->context);	/* This does lldt */
+
+	fpu__resume_cpu();
 }
 
 /**
@@ -221,12 +222,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
 #endif
 
-	/*
-	 * restore XCR0 for xsave capable cpu's.
-	 */
-	if (cpu_has_xsave)
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
-
 	fix_processor_context();
 
 	do_fpu_end();
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 3c4469a7a929..e2386cb4e0c3 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -78,9 +78,9 @@ ENTRY(restore_image)
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
-loop:
+.Lloop:
 	testq	%rdx, %rdx
-	jz	done
+	jz	.Ldone
 
 	/* get addresses from the pbe and copy the page */
 	movq	pbe_address(%rdx), %rsi
@@ -91,8 +91,8 @@ loop:
 
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
-	jmp	loop
-done:
+	jmp	.Lloop
+.Ldone:
 	/* jump to the restore_registers address from the image header */
 	jmpq	*%rax
 	/*
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index acb384d24669..a8fecc226946 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -26,7 +26,7 @@ else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
 		../lib/rwsem.o
 
 endif
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7e8a1a650435..b9531d343134 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -39,7 +39,8 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
 
 #define read_barrier_depends()		do { } while (0)
 #define smp_read_barrier_depends()	do { } while (0)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 94578efd3067..0b95c9b8283f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1181,10 +1181,11 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.read_tscp = native_read_tscp,
 
 	.iret = xen_iret,
-	.irq_enable_sysexit = xen_sysexit,
 #ifdef CONFIG_X86_64
 	.usergs_sysret32 = xen_sysret32,
 	.usergs_sysret64 = xen_sysret64,
+#else
+	.irq_enable_sysexit = xen_sysexit,
 #endif
 
 	.load_tr_desc = paravirt_nop,
@@ -1423,7 +1424,7 @@ static void xen_pvh_set_cr_flags(int cpu)
 		return;
 	/*
 	 * For BSP, PSE PGE are set in probe_page_size_mask(), for APs
-	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init.
+	 * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
 	*/
 	if (cpu_has_pse)
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
@@ -1467,6 +1468,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	unsigned long initrd_start = 0;
+	u64 pat;
 	int rc;
 
 	if (!xen_start_info)
@@ -1574,8 +1576,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * Modify the cache mode translation tables to match Xen's PAT
 	 * configuration.
 	 */
-
-	pat_init_cache_modes();
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	pat_init_cache_modes(pat);
 
 	/* keep using Xen gdt for now; no urgent need to change it */
 
@@ -1760,6 +1762,9 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 
 static void __init xen_hvm_guest_init(void)
 {
+	if (xen_pv_domain())
+		return;
+
 	init_hvm_pv_info();
 
 	xen_hvm_init_shared_info();
@@ -1775,6 +1780,7 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
 }
+#endif
 
 static bool xen_nopv = false;
 static __init int xen_parse_nopv(char *arg)
@@ -1784,14 +1790,11 @@ static __init int xen_parse_nopv(char *arg)
 }
 early_param("xen_nopv", xen_parse_nopv);
 
-static uint32_t __init xen_hvm_platform(void)
+static uint32_t __init xen_platform(void)
 {
 	if (xen_nopv)
 		return 0;
 
-	if (xen_pv_domain())
-		return 0;
-
 	return xen_cpuid_base();
 }
 
@@ -1809,11 +1812,19 @@ bool xen_hvm_need_lapic(void)
 }
 EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
 
-const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = {
-	.name			= "Xen HVM",
-	.detect			= xen_hvm_platform,
+static void xen_set_cpu_features(struct cpuinfo_x86 *c)
+{
+	if (xen_pv_domain())
+		clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+}
+
+const struct hypervisor_x86 x86_hyper_xen = {
+	.name			= "Xen",
+	.detect			= xen_platform,
+#ifdef CONFIG_XEN_PVHVM
 	.init_platform		= xen_hvm_guest_init,
+#endif
 	.x2apic_available	= xen_x2apic_para_available,
+	.set_cpu_features       = xen_set_cpu_features,
 };
-EXPORT_SYMBOL(x86_hyper_xen_hvm);
-#endif
+EXPORT_SYMBOL(x86_hyper_xen);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b47124d4cd67..8b7f18e200aa 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -67,6 +67,7 @@
 #include <linux/seq_file.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <asm/cache.h>
 #include <asm/setup.h>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 956374c1edbc..9e2ba5c6e1dd 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,6 +17,56 @@
 #include "xen-ops.h"
 #include "debugfs.h"
 
+static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
+static DEFINE_PER_CPU(char *, irq_name);
+static bool xen_pvspin = true;
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
+#include <asm/qspinlock.h>
+
+static void xen_qlock_kick(int cpu)
+{
+	xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+}
+
+/*
+ * Halt the current CPU & release it back to the host
+ */
+static void xen_qlock_wait(u8 *byte, u8 val)
+{
+	int irq = __this_cpu_read(lock_kicker_irq);
+
+	/* If kicker interrupts not initialized yet, just spin */
+	if (irq == -1)
+		return;
+
+	/* clear pending */
+	xen_clear_irq_pending(irq);
+	barrier();
+
+	/*
+	 * We check the byte value after clearing pending IRQ to make sure
+	 * that we won't miss a wakeup event because of the clearing.
+	 *
+	 * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
+	 * So it is effectively a memory barrier for x86.
+	 */
+	if (READ_ONCE(*byte) != val)
+		return;
+
+	/*
+	 * If an interrupt happens here, it will leave the wakeup irq
+	 * pending, which will cause xen_poll_irq() to return
+	 * immediately.
+	 */
+
+	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
+	xen_poll_irq(irq);
+}
+
+#else /* CONFIG_QUEUED_SPINLOCKS */
+
 enum xen_contention_stat {
 	TAKEN_SLOW,
 	TAKEN_SLOW_PICKUP,
@@ -100,12 +150,9 @@ struct xen_lock_waiting {
 	__ticket_t want;
 };
 
-static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(char *, irq_name);
 static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
 static cpumask_t waiting_cpus;
 
-static bool xen_pvspin = true;
 __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
@@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
 		}
 	}
 }
+#endif /* CONFIG_QUEUED_SPINLOCKS */
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)
 {
@@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
+#ifdef CONFIG_QUEUED_SPINLOCKS
+	__pv_init_lock_hash();
+	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_lock_ops.wait = xen_qlock_wait;
+	pv_lock_ops.kick = xen_qlock_kick;
+#else
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
+#endif
 }
 
 /*
@@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg)
 }
 early_param("xen_nopvspin", xen_parse_nopvspin);
 
-#ifdef CONFIG_XEN_DEBUG_FS
+#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
 
 static struct dentry *d_spin_debug;
 
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index d9497698645a..53b4c0811f4f 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -88,7 +88,17 @@ static void xen_vcpu_notify_restore(void *data)
 	tick_resume_local();
 }
 
+static void xen_vcpu_notify_suspend(void *data)
+{
+	tick_suspend_local();
+}
+
 void xen_arch_resume(void)
 {
 	on_each_cpu(xen_vcpu_notify_restore, NULL, 1);
 }
+
+void xen_arch_suspend(void)
+{
+	on_each_cpu(xen_vcpu_notify_suspend, NULL, 1);
+}
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 985fc3ee0973..f22667abf7b9 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,8 @@
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
 #include <asm/segment.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
 
 #include <xen/interface/xen.h>
 
@@ -47,29 +49,13 @@ ENTRY(xen_iret)
 ENDPATCH(xen_iret)
 RELOC(xen_iret, 1b+1)
 
-/*
- * sysexit is not used for 64-bit processes, so it's only ever used to
- * return to 32-bit compat userspace.
- */
-ENTRY(xen_sysexit)
-	pushq $__USER32_DS
-	pushq %rcx
-	pushq $X86_EFLAGS_IF
-	pushq $__USER32_CS
-	pushq %rdx
-
-	pushq $0
-1:	jmp hypercall_iret
-ENDPATCH(xen_sysexit)
-RELOC(xen_sysexit, 1b+1)
-
 ENTRY(xen_sysret64)
 	/*
 	 * We're already on the usermode stack at this point, but
 	 * still with the kernel gs, so we can easily switch back
 	 */
 	movq %rsp, PER_CPU_VAR(rsp_scratch)
-	movq PER_CPU_VAR(kernel_stack), %rsp
+	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq $__USER_DS
 	pushq PER_CPU_VAR(rsp_scratch)
@@ -88,7 +74,7 @@ ENTRY(xen_sysret32)
 	 * still with the kernel gs, so we can easily switch back
 	 */
 	movq %rsp, PER_CPU_VAR(rsp_scratch)
-	movq PER_CPU_VAR(kernel_stack), %rsp
+	movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq $__USER32_DS
 	pushq PER_CPU_VAR(rsp_scratch)
@@ -128,7 +114,7 @@ RELOC(xen_sysret32, 1b+1)
 /* Normal 64-bit system call target */
 ENTRY(xen_syscall_target)
 	undo_xen_syscall
-	jmp system_call_after_swapgs
+	jmp entry_SYSCALL_64_after_swapgs
 ENDPROC(xen_syscall_target)
 
 #ifdef CONFIG_IA32_EMULATION
@@ -136,13 +122,13 @@ ENDPROC(xen_syscall_target)
 /* 32-bit compat syscall target */
 ENTRY(xen_syscall32_target)
 	undo_xen_syscall
-	jmp ia32_cstar_target
+	jmp entry_SYSCALL_compat
 ENDPROC(xen_syscall32_target)
 
 /* 32-bit compat sysenter target */
 ENTRY(xen_sysenter_target)
 	undo_xen_syscall
-	jmp ia32_sysenter_target
+	jmp entry_SYSENTER_compat
 ENDPROC(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 9e195c683549..c20fe29e65f4 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -134,7 +134,9 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long);
 
 /* These are not functions, and cannot be called normally */
 __visible void xen_iret(void);
+#ifdef CONFIG_X86_32
 __visible void xen_sysexit(void);
+#endif
 __visible void xen_sysret32(void);
 __visible void xen_sysret64(void);
 __visible void xen_adjust_exception_frame(void);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 87be10e8b57a..e5b872ba2484 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -151,7 +151,7 @@ config HAVE_SMP
 	  the CPU core definition and currently needs to be selected manually.
 
 	  Multiprocessor support in implemented with external cache and
-	  interrupt controlers.
+	  interrupt controllers.
 
 	  The MX interrupt distributer adds Interprocessor Interrupts
 	  and causes the IRQ numbers to be increased by 4 for devices
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 172a02a6ad14..1f5f6dc09736 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -52,14 +52,15 @@ dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 }
 
 static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	   enum dma_data_direction direction)
 {
 	int i;
+	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
-	for (i = 0; i < nents; i++, sg++ ) {
+	for_each_sg(sglist, sg, nents, i) {
 		BUG_ON(!sg_page(sg));
 
 		sg->dma_address = sg_phys(sg);
@@ -124,20 +125,24 @@ dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
 	consistent_sync((void *)bus_to_virt(dma_handle)+offset,size,direction);
 }
 static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
 		 enum dma_data_direction dir)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		consistent_sync(sg_virt(sg), sg->length, dir);
 }
 
 static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction dir)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
+		       int nelems, enum dma_data_direction dir)
 {
 	int i;
-	for (i = 0; i < nelems; i++, sg++)
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
 		consistent_sync(sg_virt(sg), sg->length, dir);
 }
 static inline int
@@ -185,4 +190,17 @@ static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return -EINVAL;
 }
 
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
+{
+	return NULL;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+}
+
 #endif	/* _XTENSA_DMA_MAPPING_H */
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index fe1600a09438..c39bb6e61911 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -59,6 +59,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset,
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_wt ioremap_nocache
 
 static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 {
diff --git a/arch/xtensa/include/asm/mm-arch-hooks.h b/arch/xtensa/include/asm/mm-arch-hooks.h
new file mode 100644
index 000000000000..d2e5cfd3dd02
--- /dev/null
+++ b/arch/xtensa/include/asm/mm-arch-hooks.h
@@ -0,0 +1,15 @@
+/*
+ * Architecture specific mm hooks
+ *
+ * Copyright (C) 2015, IBM Corporation
+ * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_XTENSA_MM_ARCH_HOOKS_H
+#define _ASM_XTENSA_MM_ARCH_HOOKS_H
+
+#endif /* _ASM_XTENSA_MM_ARCH_HOOKS_H */
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 9e3571a6535c..83a44a33cfa1 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -15,10 +15,10 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/hardirq.h>
-#include <asm/uaccess.h>
 #include <asm/pgalloc.h>
 
 DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST;
@@ -57,7 +57,7 @@ void do_page_fault(struct pt_regs *regs)
 	/* If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm) {
+	if (faulthandler_disabled() || !mm) {
 		bad_page_fault(regs, address, SIGSEGV);
 		return;
 	}
diff --git a/arch/xtensa/mm/highmem.c b/arch/xtensa/mm/highmem.c
index 8cfb71ec0937..184ceadccc1a 100644
--- a/arch/xtensa/mm/highmem.c
+++ b/arch/xtensa/mm/highmem.c
@@ -42,6 +42,7 @@ void *kmap_atomic(struct page *page)
 	enum fixed_addresses idx;
 	unsigned long vaddr;
 
+	preempt_disable();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -79,6 +80,7 @@ void __kunmap_atomic(void *kvaddr)
 	}
 
 	pagefault_enable();
+	preempt_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 5cbd5d9ea61d..0436c21db7f2 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -361,7 +361,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-	bio_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 /**
@@ -388,7 +388,7 @@ void bio_integrity_endio(struct bio *bio, int error)
 	 */
 	if (error) {
 		bio->bi_end_io = bip->bip_end_io;
-		bio_endio_nodec(bio, error);
+		bio_endio(bio, error);
 
 		return;
 	}
diff --git a/block/bio.c b/block/bio.c
index f66a4eae16ee..259197d97de1 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -270,8 +270,8 @@ void bio_init(struct bio *bio)
 {
 	memset(bio, 0, sizeof(*bio));
 	bio->bi_flags = 1 << BIO_UPTODATE;
-	atomic_set(&bio->bi_remaining, 1);
-	atomic_set(&bio->bi_cnt, 1);
+	atomic_set(&bio->__bi_remaining, 1);
+	atomic_set(&bio->__bi_cnt, 1);
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -292,8 +292,8 @@ void bio_reset(struct bio *bio)
 	__bio_free(bio);
 
 	memset(bio, 0, BIO_RESET_BYTES);
-	bio->bi_flags = flags|(1 << BIO_UPTODATE);
-	atomic_set(&bio->bi_remaining, 1);
+	bio->bi_flags = flags | (1 << BIO_UPTODATE);
+	atomic_set(&bio->__bi_remaining, 1);
 }
 EXPORT_SYMBOL(bio_reset);
 
@@ -303,6 +303,17 @@ static void bio_chain_endio(struct bio *bio, int error)
 	bio_put(bio);
 }
 
+/*
+ * Increment chain count for the bio. Make sure the CHAIN flag update
+ * is visible before the raised count.
+ */
+static inline void bio_inc_remaining(struct bio *bio)
+{
+	bio->bi_flags |= (1 << BIO_CHAIN);
+	smp_mb__before_atomic();
+	atomic_inc(&bio->__bi_remaining);
+}
+
 /**
  * bio_chain - chain bio completions
  * @bio: the target bio
@@ -320,7 +331,7 @@ void bio_chain(struct bio *bio, struct bio *parent)
 
 	bio->bi_private = parent;
 	bio->bi_end_io	= bio_chain_endio;
-	atomic_inc(&parent->bi_remaining);
+	bio_inc_remaining(parent);
 }
 EXPORT_SYMBOL(bio_chain);
 
@@ -524,13 +535,17 @@ EXPORT_SYMBOL(zero_fill_bio);
  **/
 void bio_put(struct bio *bio)
 {
-	BIO_BUG_ON(!atomic_read(&bio->bi_cnt));
-
-	/*
-	 * last put frees it
-	 */
-	if (atomic_dec_and_test(&bio->bi_cnt))
+	if (!bio_flagged(bio, BIO_REFFED))
 		bio_free(bio);
+	else {
+		BIO_BUG_ON(!atomic_read(&bio->__bi_cnt));
+
+		/*
+		 * last put frees it
+		 */
+		if (atomic_dec_and_test(&bio->__bi_cnt))
+			bio_free(bio);
+	}
 }
 EXPORT_SYMBOL(bio_put);
 
@@ -1741,6 +1756,25 @@ void bio_flush_dcache_pages(struct bio *bi)
 EXPORT_SYMBOL(bio_flush_dcache_pages);
 #endif
 
+static inline bool bio_remaining_done(struct bio *bio)
+{
+	/*
+	 * If we're not chaining, then ->__bi_remaining is always 1 and
+	 * we always end io on the first invocation.
+	 */
+	if (!bio_flagged(bio, BIO_CHAIN))
+		return true;
+
+	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);
+
+	if (atomic_dec_and_test(&bio->__bi_remaining)) {
+		clear_bit(BIO_CHAIN, &bio->bi_flags);
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * bio_endio - end I/O on a bio
  * @bio:	bio
@@ -1758,15 +1792,13 @@ EXPORT_SYMBOL(bio_flush_dcache_pages);
 void bio_endio(struct bio *bio, int error)
 {
 	while (bio) {
-		BUG_ON(atomic_read(&bio->bi_remaining) <= 0);
-
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 			error = -EIO;
 
-		if (!atomic_dec_and_test(&bio->bi_remaining))
-			return;
+		if (unlikely(!bio_remaining_done(bio)))
+			break;
 
 		/*
 		 * Need to have a real endio function for chained bios,
@@ -1790,21 +1822,6 @@ void bio_endio(struct bio *bio, int error)
 EXPORT_SYMBOL(bio_endio);
 
 /**
- * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
- * @bio:	bio
- * @error:	error, if any
- *
- * For code that has saved and restored bi_end_io; thing hard before using this
- * function, probably you should've cloned the entire bio.
- **/
-void bio_endio_nodec(struct bio *bio, int error)
-{
-	atomic_inc(&bio->bi_remaining);
-	bio_endio(bio, error);
-}
-EXPORT_SYMBOL(bio_endio_nodec);
-
-/**
  * bio_split - split a bio
  * @bio:	bio to split
  * @sectors:	number of sectors to split from the front of @bio
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 0ac817b750db..6e43fa355e71 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -9,6 +9,10 @@
  *
  * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
  * 	              Nauman Rafique <nauman@google.com>
+ *
+ * For policy-specific per-blkcg data:
+ * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
+ *                    Arianna Avanzini <avanzini.arianna@gmail.com>
  */
 #include <linux/ioprio.h>
 #include <linux/kdev_t.h>
@@ -26,8 +30,7 @@
 
 static DEFINE_MUTEX(blkcg_pol_mutex);
 
-struct blkcg blkcg_root = { .cfq_weight = 2 * CFQ_WEIGHT_DEFAULT,
-			    .cfq_leaf_weight = 2 * CFQ_WEIGHT_DEFAULT, };
+struct blkcg blkcg_root;
 EXPORT_SYMBOL_GPL(blkcg_root);
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
@@ -823,6 +826,8 @@ static struct cgroup_subsys_state *
 blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct blkcg *blkcg;
+	struct cgroup_subsys_state *ret;
+	int i;
 
 	if (!parent_css) {
 		blkcg = &blkcg_root;
@@ -830,17 +835,49 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
 	}
 
 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
-	if (!blkcg)
-		return ERR_PTR(-ENOMEM);
+	if (!blkcg) {
+		ret = ERR_PTR(-ENOMEM);
+		goto free_blkcg;
+	}
+
+	for (i = 0; i < BLKCG_MAX_POLS ; i++) {
+		struct blkcg_policy *pol = blkcg_policy[i];
+		struct blkcg_policy_data *cpd;
+
+		/*
+		 * If the policy hasn't been attached yet, wait for it
+		 * to be attached before doing anything else. Otherwise,
+		 * check if the policy requires any specific per-cgroup
+		 * data: if it does, allocate and initialize it.
+		 */
+		if (!pol || !pol->cpd_size)
+			continue;
+
+		BUG_ON(blkcg->pd[i]);
+		cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+		if (!cpd) {
+			ret = ERR_PTR(-ENOMEM);
+			goto free_pd_blkcg;
+		}
+		blkcg->pd[i] = cpd;
+		cpd->plid = i;
+		pol->cpd_init_fn(blkcg);
+	}
 
-	blkcg->cfq_weight = CFQ_WEIGHT_DEFAULT;
-	blkcg->cfq_leaf_weight = CFQ_WEIGHT_DEFAULT;
 done:
 	spin_lock_init(&blkcg->lock);
 	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&blkcg->blkg_list);
 
 	return &blkcg->css;
+
+free_pd_blkcg:
+	for (i--; i >= 0; i--)
+		kfree(blkcg->pd[i]);
+
+free_blkcg:
+	kfree(blkcg);
+	return ret;
 }
 
 /**
@@ -958,8 +995,10 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
+	LIST_HEAD(cpds);
 	struct blkcg_gq *blkg, *new_blkg;
-	struct blkg_policy_data *pd, *n;
+	struct blkg_policy_data *pd, *nd;
+	struct blkcg_policy_data *cpd, *cnd;
 	int cnt = 0, ret;
 	bool preloaded;
 
@@ -1003,7 +1042,10 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	spin_unlock_irq(q->queue_lock);
 
-	/* allocate policy_data for all existing blkgs */
+	/*
+	 * Allocate per-blkg and per-blkcg policy data
+	 * for all existing blkgs.
+	 */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {
@@ -1011,26 +1053,50 @@ int blkcg_activate_policy(struct request_queue *q,
 			goto out_free;
 		}
 		list_add_tail(&pd->alloc_node, &pds);
+
+		if (!pol->cpd_size)
+			continue;
+		cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
+		if (!cpd) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+		list_add_tail(&cpd->alloc_node, &cpds);
 	}
 
 	/*
-	 * Install the allocated pds.  With @q bypassing, no new blkg
+	 * Install the allocated pds and cpds. With @q bypassing, no new blkg
 	 * should have been created while the queue lock was dropped.
 	 */
 	spin_lock_irq(q->queue_lock);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		if (WARN_ON(list_empty(&pds))) {
+		if (WARN_ON(list_empty(&pds)) ||
+		    WARN_ON(pol->cpd_size && list_empty(&cpds))) {
 			/* umm... this shouldn't happen, just abort */
 			ret = -ENOMEM;
 			goto out_unlock;
 		}
+		cpd = list_first_entry(&cpds, struct blkcg_policy_data,
+				       alloc_node);
+		list_del_init(&cpd->alloc_node);
 		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
 		list_del_init(&pd->alloc_node);
 
 		/* grab blkcg lock too while installing @pd on @blkg */
 		spin_lock(&blkg->blkcg->lock);
 
+		if (!pol->cpd_size)
+			goto no_cpd;
+		if (!blkg->blkcg->pd[pol->plid]) {
+			/* Per-policy per-blkcg data */
+			blkg->blkcg->pd[pol->plid] = cpd;
+			cpd->plid = pol->plid;
+			pol->cpd_init_fn(blkg->blkcg);
+		} else { /* must free it as it has already been extracted */
+			kfree(cpd);
+		}
+no_cpd:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
@@ -1045,8 +1111,10 @@ out_unlock:
 	spin_unlock_irq(q->queue_lock);
 out_free:
 	blk_queue_bypass_end(q);
-	list_for_each_entry_safe(pd, n, &pds, alloc_node)
+	list_for_each_entry_safe(pd, nd, &pds, alloc_node)
 		kfree(pd);
+	list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
+		kfree(cpd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1087,6 +1155,8 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		kfree(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid] = NULL;
+		kfree(blkg->blkcg->pd[pol->plid]);
+		blkg->blkcg->pd[pol->plid] = NULL;
 
 		spin_unlock(&blkg->blkcg->lock);
 	}
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index c567865b5f1d..74296a78bba1 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -23,11 +23,6 @@
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
 
-/* CFQ specific, out here for blkcg->cfq_weight */
-#define CFQ_WEIGHT_MIN		10
-#define CFQ_WEIGHT_MAX		1000
-#define CFQ_WEIGHT_DEFAULT	500
-
 #ifdef CONFIG_BLK_CGROUP
 
 enum blkg_rwstat_type {
@@ -50,9 +45,7 @@ struct blkcg {
 	struct blkcg_gq			*blkg_hint;
 	struct hlist_head		blkg_list;
 
-	/* TODO: per-policy storage in blkcg */
-	unsigned int			cfq_weight;	/* belongs to cfq */
-	unsigned int			cfq_leaf_weight;
+	struct blkcg_policy_data	*pd[BLKCG_MAX_POLS];
 };
 
 struct blkg_stat {
@@ -87,6 +80,24 @@ struct blkg_policy_data {
 	struct list_head		alloc_node;
 };
 
+/*
+ * Policies that need to keep per-blkcg data which is independent
+ * from any request_queue associated to it must specify its size
+ * with the cpd_size field of the blkcg_policy structure and
+ * embed a blkcg_policy_data in it. blkcg core allocates
+ * policy-specific per-blkcg structures lazily the first time
+ * they are actually needed, so it handles them together with
+ * blkgs. cpd_init() is invoked to let each policy handle
+ * per-blkcg data.
+ */
+struct blkcg_policy_data {
+	/* the policy id this per-policy data belongs to */
+	int				plid;
+
+	/* used during policy activation */
+	struct list_head		alloc_node;
+};
+
 /* association between a blk cgroup and a request queue */
 struct blkcg_gq {
 	/* Pointer to the associated request_queue */
@@ -112,6 +123,7 @@ struct blkcg_gq {
 	struct rcu_head			rcu_head;
 };
 
+typedef void (blkcg_pol_init_cpd_fn)(const struct blkcg *blkcg);
 typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);
 typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg);
@@ -122,10 +134,13 @@ struct blkcg_policy {
 	int				plid;
 	/* policy specific private data size */
 	size_t				pd_size;
+	/* policy specific per-blkcg data size */
+	size_t				cpd_size;
 	/* cgroup files for the policy */
 	struct cftype			*cftypes;
 
 	/* operations */
+	blkcg_pol_init_cpd_fn		*cpd_init_fn;
 	blkcg_pol_init_pd_fn		*pd_init_fn;
 	blkcg_pol_online_pd_fn		*pd_online_fn;
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
@@ -218,6 +233,12 @@ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
 	return blkg ? blkg->pd[pol->plid] : NULL;
 }
 
+static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg,
+						     struct blkcg_policy *pol)
+{
+	return blkcg ? blkcg->pd[pol->plid] : NULL;
+}
+
 /**
  * pdata_to_blkg - get blkg associated with policy private data
  * @pd: policy private data of interest
@@ -564,6 +585,9 @@ struct blkcg;
 struct blkg_policy_data {
 };
 
+struct blkcg_policy_data {
+};
+
 struct blkcg_gq {
 };
 
diff --git a/block/blk-core.c b/block/blk-core.c
index fd154b94447a..f6ab750060fe 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -117,7 +117,7 @@ EXPORT_SYMBOL(blk_rq_init);
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
 {
-	if (error)
+	if (error && !(rq->cmd_flags & REQ_CLONE))
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
@@ -128,7 +128,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ|REQ_CLONE)))
 		bio_endio(bio, error);
 }
 
@@ -285,6 +286,7 @@ inline void __blk_run_queue_uncond(struct request_queue *q)
 	q->request_fn(q);
 	q->request_fn_active--;
 }
+EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
 
 /**
  * __blk_run_queue - run a single device queue
@@ -552,6 +554,8 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
+	bdi_destroy(&q->backing_dev_info);
+
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }
@@ -732,6 +736,8 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
+static void blk_queue_bio(struct request_queue *q, struct bio *bio);
+
 struct request_queue *
 blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 			 spinlock_t *lock)
@@ -1521,7 +1527,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
  * Caller must ensure !blk_queue_nomerges(q) beforehand.
  */
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count)
+			    unsigned int *request_count,
+			    struct request **same_queue_rq)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1541,8 +1548,16 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
 		int el_ret;
 
-		if (rq->q == q)
+		if (rq->q == q) {
 			(*request_count)++;
+			/*
+			 * Only blk-mq multiple hardware queues case checks the
+			 * rq in the same queue, there should be only one such
+			 * rq in a queue
+			 **/
+			if (same_queue_rq)
+				*same_queue_rq = rq;
+		}
 
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
@@ -1576,7 +1591,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	blk_rq_bio_prep(req->q, req, bio);
 }
 
-void blk_queue_bio(struct request_queue *q, struct bio *bio)
+static void blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	const bool sync = !!(bio->bi_rw & REQ_SYNC);
 	struct blk_plug *plug;
@@ -1607,7 +1622,7 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * any locks.
 	 */
 	if (!blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1684,7 +1699,6 @@ out_unlock:
 		spin_unlock_irq(q->queue_lock);
 	}
 }
-EXPORT_SYMBOL_GPL(blk_queue_bio);	/* for device mapper only */
 
 /*
  * If bio->bi_dev is a partition, remap the location
@@ -1715,8 +1729,6 @@ static void handle_bad_sector(struct bio *bio)
 			bio->bi_rw,
 			(unsigned long long)bio_end_sector(bio),
 			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
-
-	set_bit(BIO_EOF, &bio->bi_flags);
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -2901,95 +2913,22 @@ int blk_lld_busy(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_lld_busy);
 
-/**
- * blk_rq_unprep_clone - Helper function to free all bios in a cloned request
- * @rq: the clone request to be cleaned up
- *
- * Description:
- *     Free all bios in @rq for a cloned request.
- */
-void blk_rq_unprep_clone(struct request *rq)
-{
-	struct bio *bio;
-
-	while ((bio = rq->bio) != NULL) {
-		rq->bio = bio->bi_next;
-
-		bio_put(bio);
-	}
-}
-EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-
-/*
- * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->sense) are not copied.
- */
-static void __blk_rq_prep_clone(struct request *dst, struct request *src)
+void blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
+	dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK);
+	dst->cmd_flags |= REQ_NOMERGE | REQ_CLONE;
 	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
 	dst->nr_phys_segments = src->nr_phys_segments;
 	dst->ioprio = src->ioprio;
 	dst->extra_len = src->extra_len;
-}
-
-/**
- * blk_rq_prep_clone - Helper function to setup clone request
- * @rq: the request to be setup
- * @rq_src: original request to be cloned
- * @bs: bio_set that bios for clone are allocated from
- * @gfp_mask: memory allocation mask for bio
- * @bio_ctr: setup function to be called for each clone bio.
- *           Returns %0 for success, non %0 for failure.
- * @data: private data to be passed to @bio_ctr
- *
- * Description:
- *     Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- *     The actual data parts of @rq_src (e.g. ->cmd, ->sense)
- *     are not copied, and copying such parts is the caller's responsibility.
- *     Also, pages which the original bios are pointing to are not copied
- *     and the cloned bios just point same pages.
- *     So cloned bios must be completed before original bios, which means
- *     the caller must complete @rq before @rq_src.
- */
-int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
-		      struct bio_set *bs, gfp_t gfp_mask,
-		      int (*bio_ctr)(struct bio *, struct bio *, void *),
-		      void *data)
-{
-	struct bio *bio, *bio_src;
-
-	if (!bs)
-		bs = fs_bio_set;
-
-	__rq_for_each_bio(bio_src, rq_src) {
-		bio = bio_clone_fast(bio_src, gfp_mask, bs);
-		if (!bio)
-			goto free_and_out;
-
-		if (bio_ctr && bio_ctr(bio, bio_src, data))
-			goto free_and_out;
-
-		if (rq->bio) {
-			rq->biotail->bi_next = bio;
-			rq->biotail = bio;
-		} else
-			rq->bio = rq->biotail = bio;
-	}
-
-	__blk_rq_prep_clone(rq, rq_src);
-
-	return 0;
-
-free_and_out:
-	if (bio)
-		bio_put(bio);
-	blk_rq_unprep_clone(rq);
-
-	return -ENOMEM;
+	dst->bio = src->bio;
+	dst->biotail = src->biotail;
+	dst->cmd = src->cmd;
+	dst->cmd_len = src->cmd_len;
+	dst->sense = src->sense;
 }
 EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
 
@@ -3031,21 +2970,20 @@ void blk_start_plug(struct blk_plug *plug)
 {
 	struct task_struct *tsk = current;
 
+	/*
+	 * If this is a nested plug, don't actually assign it.
+	 */
+	if (tsk->plug)
+		return;
+
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->mq_list);
 	INIT_LIST_HEAD(&plug->cb_list);
-
 	/*
-	 * If this is a nested plug, don't actually assign it. It will be
-	 * flushed on its own.
+	 * Store ordering should not be needed here, since a potential
+	 * preempt will imply a full memory barrier
 	 */
-	if (!tsk->plug) {
-		/*
-		 * Store ordering should not be needed here, since a potential
-		 * preempt will imply a full memory barrier
-		 */
-		tsk->plug = plug;
-	}
+	tsk->plug = plug;
 }
 EXPORT_SYMBOL(blk_start_plug);
 
@@ -3192,10 +3130,11 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 void blk_finish_plug(struct blk_plug *plug)
 {
+	if (plug != current->plug)
+		return;
 	blk_flush_plug_list(plug, false);
 
-	if (plug == current->plug)
-		current->plug = NULL;
+	current->plug = NULL;
 }
 EXPORT_SYMBOL(blk_finish_plug);
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 9924725fa50d..3fec8a29d0fa 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -53,7 +53,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 			   rq_end_io_fn *done)
 {
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
-	bool is_pm_resume;
 
 	WARN_ON(irqs_disabled());
 	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
@@ -70,12 +69,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 		return;
 	}
 
-	/*
-	 * need to check this before __blk_run_queue(), because rq can
-	 * be freed before that returns.
-	 */
-	is_pm_resume = rq->cmd_type == REQ_TYPE_PM_RESUME;
-
 	spin_lock_irq(q->queue_lock);
 
 	if (unlikely(blk_queue_dying(q))) {
@@ -88,9 +81,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	__elv_add_request(q, rq, where);
 	__blk_run_queue(q);
-	/* the queue is stopped so it won't be run */
-	if (is_pm_resume)
-		__blk_run_queue_uncond(q);
 	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index fd3fee81c23c..30a0d9f89017 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -589,7 +589,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
-	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
+	/* Only check gaps if the bio carries data */
+	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && bio_has_data(bio)) {
 		struct bio_vec *bprev;
 
 		bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 5f13f4d0bcce..1e28ddb656b8 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -24,7 +24,7 @@ static int get_first_sibling(unsigned int cpu)
 {
 	unsigned int ret;
 
-	ret = cpumask_first(topology_thread_cpumask(cpu));
+	ret = cpumask_first(topology_sibling_cpumask(cpu));
 	if (ret < nr_cpu_ids)
 		return ret;
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index be3290cc0644..9b6e28830b82 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -438,6 +438,39 @@ static void bt_for_each(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
+static void bt_tags_for_each(struct blk_mq_tags *tags,
+		struct blk_mq_bitmap_tags *bt, unsigned int off,
+		busy_tag_iter_fn *fn, void *data, bool reserved)
+{
+	struct request *rq;
+	int bit, i;
+
+	if (!tags->rqs)
+		return;
+	for (i = 0; i < bt->map_nr; i++) {
+		struct blk_align_bitmap *bm = &bt->map[i];
+
+		for (bit = find_first_bit(&bm->word, bm->depth);
+		     bit < bm->depth;
+		     bit = find_next_bit(&bm->word, bm->depth, bit + 1)) {
+			rq = blk_mq_tag_to_rq(tags, off + bit);
+			fn(rq, data, reserved);
+		}
+
+		off += (1 << bt->bits_per_word);
+	}
+}
+
+void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
+		void *priv)
+{
+	if (tags->nr_reserved_tags)
+		bt_tags_for_each(tags, &tags->breserved_tags, 0, fn, priv, true);
+	bt_tags_for_each(tags, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
+			false);
+}
+EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
+
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv)
 {
@@ -580,6 +613,11 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	if (!tags)
 		return NULL;
 
+	if (!zalloc_cpumask_var(&tags->cpumask, GFP_KERNEL)) {
+		kfree(tags);
+		return NULL;
+	}
+
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 90767b370308..75893a34237d 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -44,6 +44,7 @@ struct blk_mq_tags {
 	struct list_head page_list;
 
 	int alloc_policy;
+	cpumask_var_t cpumask;
 };
 
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ade8a2d1b0aa..f53779692c77 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -89,7 +89,8 @@ static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp)
 			return -EBUSY;
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!q->mq_freeze_depth || blk_queue_dying(q));
+				!atomic_read(&q->mq_freeze_depth) ||
+				blk_queue_dying(q));
 		if (blk_queue_dying(q))
 			return -ENODEV;
 		if (ret)
@@ -112,13 +113,10 @@ static void blk_mq_usage_counter_release(struct percpu_ref *ref)
 
 void blk_mq_freeze_queue_start(struct request_queue *q)
 {
-	bool freeze;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
-	freeze = !q->mq_freeze_depth++;
-	spin_unlock_irq(q->queue_lock);
-
-	if (freeze) {
+	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
+	if (freeze_depth == 1) {
 		percpu_ref_kill(&q->mq_usage_counter);
 		blk_mq_run_hw_queues(q, false);
 	}
@@ -143,13 +141,11 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
 {
-	bool wake;
+	int freeze_depth;
 
-	spin_lock_irq(q->queue_lock);
-	wake = !--q->mq_freeze_depth;
-	WARN_ON_ONCE(q->mq_freeze_depth < 0);
-	spin_unlock_irq(q->queue_lock);
-	if (wake) {
+	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
+	WARN_ON_ONCE(freeze_depth < 0);
+	if (!freeze_depth) {
 		percpu_ref_reinit(&q->mq_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
@@ -677,8 +673,11 @@ static void blk_mq_rq_timer(unsigned long priv)
 		data.next = blk_rq_timeout(round_jiffies_up(data.next));
 		mod_timer(&q->timeout, data.next);
 	} else {
-		queue_for_each_hw_ctx(q, hctx, i)
-			blk_mq_tag_idle(hctx);
+		queue_for_each_hw_ctx(q, hctx, i) {
+			/* the hctx may be unmapped, so check it here */
+			if (blk_mq_hw_queue_mapped(hctx))
+				blk_mq_tag_idle(hctx);
+		}
 	}
 }
 
@@ -855,6 +854,16 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		spin_lock(&hctx->lock);
 		list_splice(&rq_list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
+		/*
+		 * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
+		 * it's possible the queue is stopped and restarted again
+		 * before this. Queue restart will dispatch requests. And since
+		 * requests in rq_list aren't added into hctx->dispatch yet,
+		 * the requests in rq_list might get lost.
+		 *
+		 * blk_mq_run_hw_queue() already checks the STOPPED bit
+		 **/
+		blk_mq_run_hw_queue(hctx, true);
 	}
 }
 
@@ -1224,6 +1233,38 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	return rq;
 }
 
+static int blk_mq_direct_issue_request(struct request *rq)
+{
+	int ret;
+	struct request_queue *q = rq->q;
+	struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q,
+			rq->mq_ctx->cpu);
+	struct blk_mq_queue_data bd = {
+		.rq = rq,
+		.list = NULL,
+		.last = 1
+	};
+
+	/*
+	 * For OK queue, we are done. For error, kill it. Any other
+	 * error (busy), just add it to our list as we previously
+	 * would have done
+	 */
+	ret = q->mq_ops->queue_rq(hctx, &bd);
+	if (ret == BLK_MQ_RQ_QUEUE_OK)
+		return 0;
+	else {
+		__blk_mq_requeue_request(rq);
+
+		if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+			rq->errors = -EIO;
+			blk_mq_end_request(rq, rq->errors);
+			return 0;
+		}
+		return -1;
+	}
+}
+
 /*
  * Multiple hardware queue variant. This will not use per-process plugs,
  * but will attempt to bypass the hctx queueing if we can go straight to
@@ -1235,6 +1276,9 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
 	struct blk_map_ctx data;
 	struct request *rq;
+	unsigned int request_count = 0;
+	struct blk_plug *plug;
+	struct request *same_queue_rq = NULL;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1243,6 +1287,10 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return;
+
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
 		return;
@@ -1253,38 +1301,42 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto run_queue;
 	}
 
+	plug = current->plug;
 	/*
 	 * If the driver supports defer issued based on 'last', then
 	 * queue it up like normal since we can potentially save some
 	 * CPU this way.
 	 */
-	if (is_sync && !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
-		struct blk_mq_queue_data bd = {
-			.rq = rq,
-			.list = NULL,
-			.last = 1
-		};
-		int ret;
+	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
+	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
+		struct request *old_rq = NULL;
 
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * For OK queue, we are done. For error, kill it. Any other
-		 * error (busy), just add it to our list as we previously
-		 * would have done
+		 * we do limited pluging. If bio can be merged, do merge.
+		 * Otherwise the existing request in the plug list will be
+		 * issued. So the plug list will have one request at most
 		 */
-		ret = q->mq_ops->queue_rq(data.hctx, &bd);
-		if (ret == BLK_MQ_RQ_QUEUE_OK)
-			goto done;
-		else {
-			__blk_mq_requeue_request(rq);
-
-			if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
-				rq->errors = -EIO;
-				blk_mq_end_request(rq, rq->errors);
-				goto done;
+		if (plug) {
+			/*
+			 * The plug list might get flushed before this. If that
+			 * happens, same_queue_rq is invalid and plug list is empty
+			 **/
+			if (same_queue_rq && !list_empty(&plug->mq_list)) {
+				old_rq = same_queue_rq;
+				list_del_init(&old_rq->queuelist);
 			}
-		}
+			list_add_tail(&rq->queuelist, &plug->mq_list);
+		} else /* is_sync */
+			old_rq = rq;
+		blk_mq_put_ctx(data.ctx);
+		if (!old_rq)
+			return;
+		if (!blk_mq_direct_issue_request(old_rq))
+			return;
+		blk_mq_insert_request(old_rq, false, true, true);
+		return;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1297,7 +1349,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 run_queue:
 		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
 	}
-done:
 	blk_mq_put_ctx(data.ctx);
 }
 
@@ -1309,16 +1360,11 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = rw_is_sync(bio->bi_rw);
 	const int is_flush_fua = bio->bi_rw & (REQ_FLUSH | REQ_FUA);
-	unsigned int use_plug, request_count = 0;
+	struct blk_plug *plug;
+	unsigned int request_count = 0;
 	struct blk_map_ctx data;
 	struct request *rq;
 
-	/*
-	 * If we have multiple hardware queues, just go directly to
-	 * one of those for sync IO.
-	 */
-	use_plug = !is_flush_fua && !is_sync;
-
 	blk_queue_bounce(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
@@ -1326,8 +1372,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
-	if (use_plug && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count))
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
 		return;
 
 	rq = blk_mq_map_request(q, bio, &data);
@@ -1345,21 +1391,18 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	 * utilize that to temporarily store requests until the task is
 	 * either done or scheduled away.
 	 */
-	if (use_plug) {
-		struct blk_plug *plug = current->plug;
-
-		if (plug) {
-			blk_mq_bio_to_request(rq, bio);
-			if (list_empty(&plug->mq_list))
-				trace_block_plug(q);
-			else if (request_count >= BLK_MAX_REQUEST_COUNT) {
-				blk_flush_plug_list(plug, false);
-				trace_block_plug(q);
-			}
-			list_add_tail(&rq->queuelist, &plug->mq_list);
-			blk_mq_put_ctx(data.ctx);
-			return;
+	plug = current->plug;
+	if (plug) {
+		blk_mq_bio_to_request(rq, bio);
+		if (list_empty(&plug->mq_list))
+			trace_block_plug(q);
+		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+			blk_flush_plug_list(plug, false);
+			trace_block_plug(q);
 		}
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+		blk_mq_put_ctx(data.ctx);
+		return;
 	}
 
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
@@ -1495,7 +1538,6 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			i++;
 		}
 	}
-
 	return tags;
 
 fail:
@@ -1571,22 +1613,6 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
 	return NOTIFY_OK;
 }
 
-static int blk_mq_hctx_cpu_online(struct blk_mq_hw_ctx *hctx, int cpu)
-{
-	struct request_queue *q = hctx->queue;
-	struct blk_mq_tag_set *set = q->tag_set;
-
-	if (set->tags[hctx->queue_num])
-		return NOTIFY_OK;
-
-	set->tags[hctx->queue_num] = blk_mq_init_rq_map(set, hctx->queue_num);
-	if (!set->tags[hctx->queue_num])
-		return NOTIFY_STOP;
-
-	hctx->tags = set->tags[hctx->queue_num];
-	return NOTIFY_OK;
-}
-
 static int blk_mq_hctx_notify(void *data, unsigned long action,
 			      unsigned int cpu)
 {
@@ -1594,12 +1620,16 @@ static int blk_mq_hctx_notify(void *data, unsigned long action,
 
 	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
 		return blk_mq_hctx_cpu_offline(hctx, cpu);
-	else if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
-		return blk_mq_hctx_cpu_online(hctx, cpu);
+
+	/*
+	 * In case of CPU online, tags may be reallocated
+	 * in blk_mq_map_swqueue() after mapping is updated.
+	 */
 
 	return NOTIFY_OK;
 }
 
+/* hctx->ctxs will be freed in queue's release handler */
 static void blk_mq_exit_hctx(struct request_queue *q,
 		struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
@@ -1618,7 +1648,6 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 
 	blk_mq_unregister_cpu_notifier(&hctx->cpu_notifier);
 	blk_free_flush_queue(hctx->fq);
-	kfree(hctx->ctxs);
 	blk_mq_free_bitmap(&hctx->ctx_map);
 }
 
@@ -1775,6 +1804,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	unsigned int i;
 	struct blk_mq_hw_ctx *hctx;
 	struct blk_mq_ctx *ctx;
+	struct blk_mq_tag_set *set = q->tag_set;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		cpumask_clear(hctx->cpumask);
@@ -1791,6 +1821,7 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 		hctx = q->mq_ops->map_queue(q, i);
 		cpumask_set_cpu(i, hctx->cpumask);
+		cpumask_set_cpu(i, hctx->tags->cpumask);
 		ctx->index_hw = hctx->nr_ctx;
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
 	}
@@ -1803,16 +1834,20 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		 * disable it and free the request entries.
 		 */
 		if (!hctx->nr_ctx) {
-			struct blk_mq_tag_set *set = q->tag_set;
-
 			if (set->tags[i]) {
 				blk_mq_free_rq_map(set, set->tags[i], i);
 				set->tags[i] = NULL;
-				hctx->tags = NULL;
 			}
+			hctx->tags = NULL;
 			continue;
 		}
 
+		/* unmapped hw queue can be remapped after CPU topo changed */
+		if (!set->tags[i])
+			set->tags[i] = blk_mq_init_rq_map(set, i);
+		hctx->tags = set->tags[i];
+		WARN_ON(!hctx->tags);
+
 		/*
 		 * Set the map size to the number of mapped software queues.
 		 * This is more accurate and more efficient than looping
@@ -1886,8 +1921,12 @@ void blk_mq_release(struct request_queue *q)
 	unsigned int i;
 
 	/* hctx kobj stays in hctx */
-	queue_for_each_hw_ctx(q, hctx, i)
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx)
+			continue;
+		kfree(hctx->ctxs);
 		kfree(hctx);
+	}
 
 	kfree(q->queue_hw_ctx);
 
@@ -2047,7 +2086,7 @@ void blk_mq_free_queue(struct request_queue *q)
 /* Basically redo blk_mq_init_queue with queue frozen */
 static void blk_mq_queue_reinit(struct request_queue *q)
 {
-	WARN_ON_ONCE(!q->mq_freeze_depth);
+	WARN_ON_ONCE(!atomic_read(&q->mq_freeze_depth));
 
 	blk_mq_sysfs_unregister(q);
 
@@ -2090,9 +2129,16 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	 */
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_freeze_queue_start(q);
-	list_for_each_entry(q, &all_q_list, all_q_node)
+	list_for_each_entry(q, &all_q_list, all_q_node) {
 		blk_mq_freeze_queue_wait(q);
 
+		/*
+		 * timeout handler can't touch hw queue during the
+		 * reinitialization
+		 */
+		del_timer_sync(&q->timeout);
+	}
+
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_queue_reinit(q);
 
@@ -2157,6 +2203,12 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 	return 0;
 }
 
+struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags)
+{
+	return tags->cpumask;
+}
+EXPORT_SYMBOL_GPL(blk_mq_tags_cpumask);
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -2218,8 +2270,10 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	int i;
 
 	for (i = 0; i < set->nr_hw_queues; i++) {
-		if (set->tags[i])
+		if (set->tags[i]) {
 			blk_mq_free_rq_map(set, set->tags[i], i);
+			free_cpumask_var(set->tags[i]->cpumask);
+		}
 	}
 
 	kfree(set->tags);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index faaf36ade7eb..2b8fd302f677 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -522,8 +522,6 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
-	bdi_destroy(&q->backing_dev_info);
-
 	ida_simple_remove(&blk_queue_ida, q->id);
 	call_rcu(&q->rcu_head, blk_free_queue_rcu);
 }
diff --git a/block/blk.h b/block/blk.h
index 43b036185712..026d9594142b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -78,7 +78,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
-			    unsigned int *request_count);
+			    unsigned int *request_count,
+			    struct request **same_queue_rq);
 
 void blk_account_io_start(struct request *req, bool new_io);
 void blk_account_io_completion(struct request *req, unsigned int bytes);
@@ -193,8 +194,6 @@ int blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
-void __blk_run_queue_uncond(struct request_queue *q);
-
 int blk_dev_init(void);
 
 
diff --git a/block/bounce.c b/block/bounce.c
index ab21ba203d5c..3ab0bce1c947 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -128,9 +128,6 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 	struct bio_vec *bvec, *org_vec;
 	int i;
 
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags);
-
 	/*
 	 * free up bounce indirect pages used
 	 */
@@ -221,8 +218,8 @@ bounce:
 		if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
 			continue;
 
-		inc_zone_page_state(to->bv_page, NR_BOUNCE);
 		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
+		inc_zone_page_state(to->bv_page, NR_BOUNCE);
 
 		if (rw == WRITE) {
 			char *vto, *vfrom;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 5da8e6e9ab4b..d8ad45ccd8fa 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -67,6 +67,11 @@ static struct kmem_cache *cfq_pool;
 #define sample_valid(samples)	((samples) > 80)
 #define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)
 
+/* blkio-related constants */
+#define CFQ_WEIGHT_MIN          10
+#define CFQ_WEIGHT_MAX          1000
+#define CFQ_WEIGHT_DEFAULT      500
+
 struct cfq_ttime {
 	unsigned long last_end_request;
 
@@ -212,6 +217,15 @@ struct cfqg_stats {
 #endif	/* CONFIG_CFQ_GROUP_IOSCHED */
 };
 
+/* Per-cgroup data */
+struct cfq_group_data {
+	/* must be the first member */
+	struct blkcg_policy_data pd;
+
+	unsigned int weight;
+	unsigned int leaf_weight;
+};
+
 /* This is per cgroup per device grouping structure */
 struct cfq_group {
 	/* must be the first member */
@@ -446,16 +460,6 @@ CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
 
-static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
-{
-	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
-}
-
-static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
-{
-	return pd_to_blkg(&cfqg->pd);
-}
-
 #if defined(CONFIG_CFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 
 /* cfqg stats flags */
@@ -600,6 +604,22 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 
+static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
+}
+
+static struct cfq_group_data
+*cpd_to_cfqgd(struct blkcg_policy_data *cpd)
+{
+	return cpd ? container_of(cpd, struct cfq_group_data, pd) : NULL;
+}
+
+static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
+{
+	return pd_to_blkg(&cfqg->pd);
+}
+
 static struct blkcg_policy blkcg_policy_cfq;
 
 static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
@@ -607,6 +627,11 @@ static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
 	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
 }
 
+static struct cfq_group_data *blkcg_to_cfqgd(struct blkcg *blkcg)
+{
+	return cpd_to_cfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_cfq));
+}
+
 static inline struct cfq_group *cfqg_parent(struct cfq_group *cfqg)
 {
 	struct blkcg_gq *pblkg = cfqg_to_blkg(cfqg)->parent;
@@ -1544,13 +1569,28 @@ static void cfqg_stats_init(struct cfqg_stats *stats)
 #endif
 }
 
+static void cfq_cpd_init(const struct blkcg *blkcg)
+{
+	struct cfq_group_data *cgd =
+		cpd_to_cfqgd(blkcg->pd[blkcg_policy_cfq.plid]);
+
+	if (blkcg == &blkcg_root) {
+		cgd->weight = 2 * CFQ_WEIGHT_DEFAULT;
+		cgd->leaf_weight = 2 * CFQ_WEIGHT_DEFAULT;
+	} else {
+		cgd->weight = CFQ_WEIGHT_DEFAULT;
+		cgd->leaf_weight = CFQ_WEIGHT_DEFAULT;
+	}
+}
+
 static void cfq_pd_init(struct blkcg_gq *blkg)
 {
 	struct cfq_group *cfqg = blkg_to_cfqg(blkg);
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkg->blkcg);
 
 	cfq_init_cfqg_base(cfqg);
-	cfqg->weight = blkg->blkcg->cfq_weight;
-	cfqg->leaf_weight = blkg->blkcg->cfq_leaf_weight;
+	cfqg->weight = cgd->weight;
+	cfqg->leaf_weight = cgd->leaf_weight;
 	cfqg_stats_init(&cfqg->stats);
 	cfqg_stats_init(&cfqg->dead_stats);
 }
@@ -1673,13 +1713,27 @@ static int cfqg_print_leaf_weight_device(struct seq_file *sf, void *v)
 
 static int cfq_print_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_weight);
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (cgd)
+		val = cgd->weight;
+
+	seq_printf(sf, "%u\n", val);
 	return 0;
 }
 
 static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 {
-	seq_printf(sf, "%u\n", css_to_blkcg(seq_css(sf))->cfq_leaf_weight);
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (cgd)
+		val = cgd->leaf_weight;
+
+	seq_printf(sf, "%u\n", val);
 	return 0;
 }
 
@@ -1690,6 +1744,7 @@ static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
 	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
+	struct cfq_group_data *cfqgd;
 	int ret;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_cfq, buf, &ctx);
@@ -1698,17 +1753,22 @@ static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
 
 	ret = -EINVAL;
 	cfqg = blkg_to_cfqg(ctx.blkg);
+	cfqgd = blkcg_to_cfqgd(blkcg);
+	if (!cfqg || !cfqgd)
+		goto err;
+
 	if (!ctx.v || (ctx.v >= CFQ_WEIGHT_MIN && ctx.v <= CFQ_WEIGHT_MAX)) {
 		if (!is_leaf_weight) {
 			cfqg->dev_weight = ctx.v;
-			cfqg->new_weight = ctx.v ?: blkcg->cfq_weight;
+			cfqg->new_weight = ctx.v ?: cfqgd->weight;
 		} else {
 			cfqg->dev_leaf_weight = ctx.v;
-			cfqg->new_leaf_weight = ctx.v ?: blkcg->cfq_leaf_weight;
+			cfqg->new_leaf_weight = ctx.v ?: cfqgd->leaf_weight;
 		}
 		ret = 0;
 	}
 
+err:
 	blkg_conf_finish(&ctx);
 	return ret ?: nbytes;
 }
@@ -1730,16 +1790,23 @@ static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 	struct blkcg_gq *blkg;
+	struct cfq_group_data *cfqgd;
+	int ret = 0;
 
 	if (val < CFQ_WEIGHT_MIN || val > CFQ_WEIGHT_MAX)
 		return -EINVAL;
 
 	spin_lock_irq(&blkcg->lock);
+	cfqgd = blkcg_to_cfqgd(blkcg);
+	if (!cfqgd) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (!is_leaf_weight)
-		blkcg->cfq_weight = val;
+		cfqgd->weight = val;
 	else
-		blkcg->cfq_leaf_weight = val;
+		cfqgd->leaf_weight = val;
 
 	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
 		struct cfq_group *cfqg = blkg_to_cfqg(blkg);
@@ -1749,15 +1816,16 @@ static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
 
 		if (!is_leaf_weight) {
 			if (!cfqg->dev_weight)
-				cfqg->new_weight = blkcg->cfq_weight;
+				cfqg->new_weight = cfqgd->weight;
 		} else {
 			if (!cfqg->dev_leaf_weight)
-				cfqg->new_leaf_weight = blkcg->cfq_leaf_weight;
+				cfqg->new_leaf_weight = cfqgd->leaf_weight;
 		}
 	}
 
+out:
 	spin_unlock_irq(&blkcg->lock);
-	return 0;
+	return ret;
 }
 
 static int cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -4477,6 +4545,18 @@ out_free:
 	return ret;
 }
 
+static void cfq_registered_queue(struct request_queue *q)
+{
+	struct elevator_queue *e = q->elevator;
+	struct cfq_data *cfqd = e->elevator_data;
+
+	/*
+	 * Default to IOPS mode with no idling for SSDs
+	 */
+	if (blk_queue_nonrot(q))
+		cfqd->cfq_slice_idle = 0;
+}
+
 /*
  * sysfs parts below -->
  */
@@ -4592,6 +4672,7 @@ static struct elevator_type iosched_cfq = {
 		.elevator_may_queue_fn =	cfq_may_queue,
 		.elevator_init_fn =		cfq_init_queue,
 		.elevator_exit_fn =		cfq_exit_queue,
+		.elevator_registered_fn =	cfq_registered_queue,
 	},
 	.icq_size	=	sizeof(struct cfq_io_cq),
 	.icq_align	=	__alignof__(struct cfq_io_cq),
@@ -4603,8 +4684,10 @@ static struct elevator_type iosched_cfq = {
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 static struct blkcg_policy blkcg_policy_cfq = {
 	.pd_size		= sizeof(struct cfq_group),
+	.cpd_size		= sizeof(struct cfq_group_data),
 	.cftypes		= cfq_blkcg_files,
 
+	.cpd_init_fn		= cfq_cpd_init,
 	.pd_init_fn		= cfq_pd_init,
 	.pd_offline_fn		= cfq_pd_offline,
 	.pd_reset_stats_fn	= cfq_pd_reset_stats,
diff --git a/block/elevator.c b/block/elevator.c
index 59794d0d38e3..942579d04128 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -157,7 +157,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 
 	eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
 	if (unlikely(!eq))
-		goto err;
+		return NULL;
 
 	eq->type = e;
 	kobject_init(&eq->kobj, &elv_ktype);
@@ -165,10 +165,6 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 	hash_init(eq->hash);
 
 	return eq;
-err:
-	kfree(eq);
-	elevator_put(e);
-	return NULL;
 }
 EXPORT_SYMBOL(elevator_alloc);
 
@@ -810,6 +806,8 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
+		if (e->type->ops.elevator_registered_fn)
+			e->type->ops.elevator_registered_fn(q);
 	}
 	return error;
 }
diff --git a/block/genhd.c b/block/genhd.c
index 0a536dc05f3b..ea982eadaf63 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -422,9 +422,9 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	/* allocate ext devt */
 	idr_preload(GFP_KERNEL);
 
-	spin_lock(&ext_devt_lock);
+	spin_lock_bh(&ext_devt_lock);
 	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
-	spin_unlock(&ext_devt_lock);
+	spin_unlock_bh(&ext_devt_lock);
 
 	idr_preload_end();
 	if (idx < 0)
@@ -449,9 +449,9 @@ void blk_free_devt(dev_t devt)
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		spin_lock(&ext_devt_lock);
+		spin_lock_bh(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		spin_unlock(&ext_devt_lock);
+		spin_unlock_bh(&ext_devt_lock);
 	}
 }
 
@@ -653,7 +653,6 @@ void del_gendisk(struct gendisk *disk)
 	disk->flags &= ~GENHD_FL_UP;
 
 	sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
-	bdi_unregister(&disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
 	blk_unregister_region(disk_devt(disk), disk->minors);
 
@@ -691,13 +690,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		spin_lock(&ext_devt_lock);
+		spin_lock_bh(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		spin_unlock(&ext_devt_lock);
+		spin_unlock_bh(&ext_devt_lock);
 	}
 
 	return disk;
diff --git a/block/ioctl.c b/block/ioctl.c
index 7d8befde2aca..8061eba42887 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -150,21 +150,48 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
-static int blkdev_reread_part(struct block_device *bdev)
+/*
+ * This is an exported API for the block driver, and will not
+ * acquire bd_mutex. This API should be used in case that
+ * caller has held bd_mutex already.
+ */
+int __blkdev_reread_part(struct block_device *bdev)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	int res;
 
 	if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains)
 		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (!mutex_trylock(&bdev->bd_mutex))
-		return -EBUSY;
-	res = rescan_partitions(disk, bdev);
+
+	lockdep_assert_held(&bdev->bd_mutex);
+
+	return rescan_partitions(disk, bdev);
+}
+EXPORT_SYMBOL(__blkdev_reread_part);
+
+/*
+ * This is an exported API for the block driver, and will
+ * try to acquire bd_mutex. If bd_mutex has been held already
+ * in current context, please call __blkdev_reread_part().
+ *
+ * Make sure the held locks in current context aren't required
+ * in open()/close() handler and I/O path for avoiding ABBA deadlock:
+ * - bd_mutex is held before calling block driver's open/close
+ *   handler
+ * - reading partition table may submit I/O to the block device
+ */
+int blkdev_reread_part(struct block_device *bdev)
+{
+	int res;
+
+	mutex_lock(&bdev->bd_mutex);
+	res = __blkdev_reread_part(bdev);
 	mutex_unlock(&bdev->bd_mutex);
+
 	return res;
 }
+EXPORT_SYMBOL(blkdev_reread_part);
 
 static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 			     uint64_t len, int secure)
diff --git a/crypto/842.c b/crypto/842.c
index b48f4f108c47..98e387efb8c8 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -1,5 +1,5 @@
 /*
- * Cryptographic API for the 842 compression algorithm.
+ * Cryptographic API for the 842 software compression algorithm.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -11,173 +11,73 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ * Copyright (C) IBM Corporation, 2011-2015
  *
- * Copyright (C) IBM Corporation, 2011
+ * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
  *
- * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
- *          Seth Jennings <sjenning@linux.vnet.ibm.com>
+ * Rewrite: Dan Streetman <ddstreet@ieee.org>
+ *
+ * This is the software implementation of compression and decompression using
+ * the 842 format.  This uses the software 842 library at lib/842/ which is
+ * only a reference implementation, and is very, very slow as compared to other
+ * software compressors.  You probably do not want to use this software
+ * compression.  If you have access to the PowerPC 842 compression hardware, you
+ * want to use the 842 hardware compression interface, which is at:
+ * drivers/crypto/nx/nx-842-crypto.c
  */
 
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/crypto.h>
-#include <linux/vmalloc.h>
-#include <linux/nx842.h>
-#include <linux/lzo.h>
-#include <linux/timer.h>
-
-static int nx842_uselzo;
-
-struct nx842_ctx {
-	void *nx842_wmem; /* working memory for 842/lzo */
-};
+#include <linux/sw842.h>
 
-enum nx842_crypto_type {
-	NX842_CRYPTO_TYPE_842,
-	NX842_CRYPTO_TYPE_LZO
+struct crypto842_ctx {
+	char wmem[SW842_MEM_COMPRESS];	/* working memory for compress */
 };
 
-#define NX842_SENTINEL 0xdeadbeef
-
-struct nx842_crypto_header {
-	unsigned int sentinel; /* debug */
-	enum nx842_crypto_type type;
-};
-
-static int nx842_init(struct crypto_tfm *tfm)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	int wmemsize;
-
-	wmemsize = max_t(int, nx842_get_workmem_size(), LZO1X_MEM_COMPRESS);
-	ctx->nx842_wmem = kmalloc(wmemsize, GFP_NOFS);
-	if (!ctx->nx842_wmem)
-		return -ENOMEM;
-
-	return 0;
-}
-
-static void nx842_exit(struct crypto_tfm *tfm)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	kfree(ctx->nx842_wmem);
-}
-
-static void nx842_reset_uselzo(unsigned long data)
+static int crypto842_compress(struct crypto_tfm *tfm,
+			      const u8 *src, unsigned int slen,
+			      u8 *dst, unsigned int *dlen)
 {
-	nx842_uselzo = 0;
-}
-
-static DEFINE_TIMER(failover_timer, nx842_reset_uselzo, 0, 0);
-
-static int nx842_crypto_compress(struct crypto_tfm *tfm, const u8 *src,
-			    unsigned int slen, u8 *dst, unsigned int *dlen)
-{
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr;
-	unsigned int tmp_len = *dlen;
-	size_t lzodlen; /* needed for lzo */
-	int err;
-
-	*dlen = 0;
-	hdr = (struct nx842_crypto_header *)dst;
-	hdr->sentinel = NX842_SENTINEL; /* debug */
-	dst += sizeof(struct nx842_crypto_header);
-	tmp_len -= sizeof(struct nx842_crypto_header);
-	lzodlen = tmp_len;
-
-	if (likely(!nx842_uselzo)) {
-		err = nx842_compress(src, slen, dst, &tmp_len, ctx->nx842_wmem);
-
-		if (likely(!err)) {
-			hdr->type = NX842_CRYPTO_TYPE_842;
-			*dlen = tmp_len + sizeof(struct nx842_crypto_header);
-			return 0;
-		}
-
-		/* hardware failed */
-		nx842_uselzo = 1;
+	struct crypto842_ctx *ctx = crypto_tfm_ctx(tfm);
 
-		/* set timer to check for hardware again in 1 second */
-		mod_timer(&failover_timer, jiffies + msecs_to_jiffies(1000));
-	}
-
-	/* no hardware, use lzo */
-	err = lzo1x_1_compress(src, slen, dst, &lzodlen, ctx->nx842_wmem);
-	if (err != LZO_E_OK)
-		return -EINVAL;
-
-	hdr->type = NX842_CRYPTO_TYPE_LZO;
-	*dlen = lzodlen + sizeof(struct nx842_crypto_header);
-	return 0;
+	return sw842_compress(src, slen, dst, dlen, ctx->wmem);
 }
 
-static int nx842_crypto_decompress(struct crypto_tfm *tfm, const u8 *src,
-			      unsigned int slen, u8 *dst, unsigned int *dlen)
+static int crypto842_decompress(struct crypto_tfm *tfm,
+				const u8 *src, unsigned int slen,
+				u8 *dst, unsigned int *dlen)
 {
-	struct nx842_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct nx842_crypto_header *hdr;
-	unsigned int tmp_len = *dlen;
-	size_t lzodlen; /* needed for lzo */
-	int err;
-
-	*dlen = 0;
-	hdr = (struct nx842_crypto_header *)src;
-
-	if (unlikely(hdr->sentinel != NX842_SENTINEL))
-		return -EINVAL;
-
-	src += sizeof(struct nx842_crypto_header);
-	slen -= sizeof(struct nx842_crypto_header);
-
-	if (likely(hdr->type == NX842_CRYPTO_TYPE_842)) {
-		err = nx842_decompress(src, slen, dst, &tmp_len,
-			ctx->nx842_wmem);
-		if (err)
-			return -EINVAL;
-		*dlen = tmp_len;
-	} else if (hdr->type == NX842_CRYPTO_TYPE_LZO) {
-		lzodlen = tmp_len;
-		err = lzo1x_decompress_safe(src, slen, dst, &lzodlen);
-		if (err != LZO_E_OK)
-			return -EINVAL;
-		*dlen = lzodlen;
-	} else
-		return -EINVAL;
-
-	return 0;
+	return sw842_decompress(src, slen, dst, dlen);
 }
 
 static struct crypto_alg alg = {
 	.cra_name		= "842",
+	.cra_driver_name	= "842-generic",
+	.cra_priority		= 100,
 	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
-	.cra_ctxsize		= sizeof(struct nx842_ctx),
+	.cra_ctxsize		= sizeof(struct crypto842_ctx),
 	.cra_module		= THIS_MODULE,
-	.cra_init		= nx842_init,
-	.cra_exit		= nx842_exit,
 	.cra_u			= { .compress = {
-	.coa_compress		= nx842_crypto_compress,
-	.coa_decompress		= nx842_crypto_decompress } }
+	.coa_compress		= crypto842_compress,
+	.coa_decompress		= crypto842_decompress } }
 };
 
-static int __init nx842_mod_init(void)
+static int __init crypto842_mod_init(void)
 {
-	del_timer(&failover_timer);
 	return crypto_register_alg(&alg);
 }
+module_init(crypto842_mod_init);
 
-static void __exit nx842_mod_exit(void)
+static void __exit crypto842_mod_exit(void)
 {
 	crypto_unregister_alg(&alg);
 }
-
-module_init(nx842_mod_init);
-module_exit(nx842_mod_exit);
+module_exit(crypto842_mod_exit);
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_DESCRIPTION("842 Software Compression Algorithm");
 MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-generic");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 8aaf298a80e1..b4cfc5754033 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -78,6 +78,10 @@ config CRYPTO_RNG2
 	tristate
 	select CRYPTO_ALGAPI2
 
+config CRYPTO_RNG_DEFAULT
+	tristate
+	select CRYPTO_DRBG_MENU
+
 config CRYPTO_PCOMP
 	tristate
 	select CRYPTO_PCOMP2
@@ -87,6 +91,23 @@ config CRYPTO_PCOMP2
 	tristate
 	select CRYPTO_ALGAPI2
 
+config CRYPTO_AKCIPHER2
+	tristate
+	select CRYPTO_ALGAPI2
+
+config CRYPTO_AKCIPHER
+	tristate
+	select CRYPTO_AKCIPHER2
+	select CRYPTO_ALGAPI
+
+config CRYPTO_RSA
+	tristate "RSA algorithm"
+	select CRYPTO_AKCIPHER
+	select MPILIB
+	select ASN1
+	help
+	  Generic implementation of the RSA public key algorithm.
+
 config CRYPTO_MANAGER
 	tristate "Cryptographic algorithm manager"
 	select CRYPTO_MANAGER2
@@ -100,6 +121,7 @@ config CRYPTO_MANAGER2
 	select CRYPTO_HASH2
 	select CRYPTO_BLKCIPHER2
 	select CRYPTO_PCOMP2
+	select CRYPTO_AKCIPHER2
 
 config CRYPTO_USER
 	tristate "Userspace cryptographic algorithm configuration"
@@ -217,15 +239,39 @@ config CRYPTO_GCM
 	  Support for Galois/Counter Mode (GCM) and Galois Message
 	  Authentication Code (GMAC). Required for IPSec.
 
+config CRYPTO_CHACHA20POLY1305
+	tristate "ChaCha20-Poly1305 AEAD support"
+	select CRYPTO_CHACHA20
+	select CRYPTO_POLY1305
+	select CRYPTO_AEAD
+	help
+	  ChaCha20-Poly1305 AEAD support, RFC7539.
+
+	  Support for the AEAD wrapper using the ChaCha20 stream cipher combined
+	  with the Poly1305 authenticator. It is defined in RFC7539 for use in
+	  IETF protocols.
+
 config CRYPTO_SEQIV
 	tristate "Sequence Number IV Generator"
 	select CRYPTO_AEAD
 	select CRYPTO_BLKCIPHER
-	select CRYPTO_RNG
+	select CRYPTO_NULL
+	select CRYPTO_RNG_DEFAULT
 	help
 	  This IV generator generates an IV based on a sequence number by
 	  xoring it with a salt.  This algorithm is mainly useful for CTR
 
+config CRYPTO_ECHAINIV
+	tristate "Encrypted Chain IV Generator"
+	select CRYPTO_AEAD
+	select CRYPTO_NULL
+	select CRYPTO_RNG_DEFAULT
+	default m
+	help
+	  This IV generator generates an IV based on the encryption of
+	  a sequence number xored with a salt.  This is the default
+	  algorithm for CBC.
+
 comment "Block modes"
 
 config CRYPTO_CBC
@@ -415,6 +461,15 @@ config CRYPTO_GHASH
 	help
 	  GHASH is message digest algorithm for GCM (Galois/Counter Mode).
 
+config CRYPTO_POLY1305
+	tristate "Poly1305 authenticator algorithm"
+	help
+	  Poly1305 authenticator algorithm, RFC7539.
+
+	  Poly1305 is an authenticator algorithm designed by Daniel J. Bernstein.
+	  It is used for the ChaCha20-Poly1305 AEAD, specified in RFC7539 for use
+	  in IETF protocols. This is the portable C implementation of Poly1305.
+
 config CRYPTO_MD4
 	tristate "MD4 digest algorithm"
 	select CRYPTO_HASH
@@ -1145,6 +1200,19 @@ config CRYPTO_SALSA20_X86_64
 	  The Salsa20 stream cipher algorithm is designed by Daniel J.
 	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
 
+config CRYPTO_CHACHA20
+	tristate "ChaCha20 cipher algorithm"
+	select CRYPTO_BLKCIPHER
+	help
+	  ChaCha20 cipher algorithm, RFC7539.
+
+	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
+	  Bernstein and further specified in RFC7539 for use in IETF protocols.
+	  This is the portable C implementation of ChaCha20.
+
+	  See also:
+	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"
 	select CRYPTO_ALGAPI
@@ -1412,10 +1480,9 @@ config CRYPTO_LZO
 
 config CRYPTO_842
 	tristate "842 compression algorithm"
-	depends on CRYPTO_DEV_NX_COMPRESS
-	# 842 uses lzo if the hardware becomes unavailable
-	select LZO_COMPRESS
-	select LZO_DECOMPRESS
+	select CRYPTO_ALGAPI
+	select 842_COMPRESS
+	select 842_DECOMPRESS
 	help
 	  This is the 842 algorithm.
 
@@ -1439,7 +1506,6 @@ comment "Random Number Generation"
 
 config CRYPTO_ANSI_CPRNG
 	tristate "Pseudo Random Number Generation for Cryptographic modules"
-	default m
 	select CRYPTO_AES
 	select CRYPTO_RNG
 	help
@@ -1457,15 +1523,14 @@ menuconfig CRYPTO_DRBG_MENU
 if CRYPTO_DRBG_MENU
 
 config CRYPTO_DRBG_HMAC
-	bool "Enable HMAC DRBG"
+	bool
 	default y
 	select CRYPTO_HMAC
-	help
-	  Enable the HMAC DRBG variant as defined in NIST SP800-90A.
+	select CRYPTO_SHA256
 
 config CRYPTO_DRBG_HASH
 	bool "Enable Hash DRBG"
-	select CRYPTO_HASH
+	select CRYPTO_SHA256
 	help
 	  Enable the Hash DRBG variant as defined in NIST SP800-90A.
 
@@ -1477,11 +1542,21 @@ config CRYPTO_DRBG_CTR
 
 config CRYPTO_DRBG
 	tristate
-	default CRYPTO_DRBG_MENU if (CRYPTO_DRBG_HMAC || CRYPTO_DRBG_HASH || CRYPTO_DRBG_CTR)
+	default CRYPTO_DRBG_MENU
 	select CRYPTO_RNG
+	select CRYPTO_JITTERENTROPY
 
 endif	# if CRYPTO_DRBG_MENU
 
+config CRYPTO_JITTERENTROPY
+	tristate "Jitterentropy Non-Deterministic Random Number Generator"
+	help
+	  The Jitterentropy RNG is a noise that is intended
+	  to provide seed to another RNG. The RNG does not
+	  perform any cryptographic whitening of the generated
+	  random numbers. This Jitterentropy RNG registers with
+	  the kernel crypto API and can be used by any caller.
+
 config CRYPTO_USER_API
 	tristate
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 97b7d3ac87e7..0077476f5024 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -21,12 +21,22 @@ obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += chainiv.o
 obj-$(CONFIG_CRYPTO_BLKCIPHER2) += eseqiv.o
 obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o
+obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o
 
 crypto_hash-y += ahash.o
 crypto_hash-y += shash.o
 obj-$(CONFIG_CRYPTO_HASH2) += crypto_hash.o
 
 obj-$(CONFIG_CRYPTO_PCOMP2) += pcompress.o
+obj-$(CONFIG_CRYPTO_AKCIPHER2) += akcipher.o
+
+$(obj)/rsakey-asn1.o: $(obj)/rsakey-asn1.c $(obj)/rsakey-asn1.h
+clean-files += rsakey-asn1.c rsakey-asn1.h
+
+rsa_generic-y := rsakey-asn1.o
+rsa_generic-y += rsa.o
+rsa_generic-y += rsa_helper.o
+obj-$(CONFIG_CRYPTO_RSA) += rsa_generic.o
 
 cryptomgr-y := algboss.o testmgr.o
 
@@ -58,6 +68,7 @@ obj-$(CONFIG_CRYPTO_XTS) += xts.o
 obj-$(CONFIG_CRYPTO_CTR) += ctr.o
 obj-$(CONFIG_CRYPTO_GCM) += gcm.o
 obj-$(CONFIG_CRYPTO_CCM) += ccm.o
+obj-$(CONFIG_CRYPTO_CHACHA20POLY1305) += chacha20poly1305.o
 obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o
 obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o
 obj-$(CONFIG_CRYPTO_MCRYPTD) += mcryptd.o
@@ -79,6 +90,8 @@ obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o
 obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o
 obj-$(CONFIG_CRYPTO_SEED) += seed.o
 obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o
+obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o
+obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o
 obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o
 obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
@@ -91,9 +104,9 @@ obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
 obj-$(CONFIG_CRYPTO_LZ4HC) += lz4hc.o
 obj-$(CONFIG_CRYPTO_842) += 842.o
 obj-$(CONFIG_CRYPTO_RNG2) += rng.o
-obj-$(CONFIG_CRYPTO_RNG2) += krng.o
 obj-$(CONFIG_CRYPTO_ANSI_CPRNG) += ansi_cprng.o
 obj-$(CONFIG_CRYPTO_DRBG) += drbg.o
+obj-$(CONFIG_CRYPTO_JITTERENTROPY) += jitterentropy.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index db201bca1581..b788f169cc98 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -454,7 +454,7 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 		      alg->setkey : setkey;
 	crt->encrypt = alg->encrypt;
 	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt;
+	crt->givencrypt = alg->givencrypt ?: no_givdecrypt;
 	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
@@ -586,6 +586,13 @@ static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
 	if (!tmpl)
 		goto kill_larval;
 
+	if (tmpl->create) {
+		err = tmpl->create(tmpl, tb);
+		if (err)
+			goto put_tmpl;
+		goto ok;
+	}
+
 	inst = tmpl->alloc(tb);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
@@ -597,6 +604,7 @@ static int crypto_givcipher_default(struct crypto_alg *alg, u32 type, u32 mask)
 		goto put_tmpl;
 	}
 
+ok:
 	/* Redo the lookup to use the instance we just registered. */
 	err = -EAGAIN;
 
@@ -636,7 +644,7 @@ struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask)
 
 	if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) ==
 	    CRYPTO_ALG_TYPE_GIVCIPHER) {
-		if ((alg->cra_flags ^ type ^ ~mask) & CRYPTO_ALG_TESTED) {
+		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
 			crypto_mod_put(alg);
 			alg = ERR_PTR(-ENOENT);
 		}
diff --git a/crypto/aead.c b/crypto/aead.c
index 222271070b49..07bf99773548 100644
--- a/crypto/aead.c
+++ b/crypto/aead.c
@@ -12,7 +12,8 @@
  *
  */
 
-#include <crypto/internal/aead.h>
+#include <crypto/internal/geniv.h>
+#include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -26,10 +27,20 @@
 
 #include "internal.h"
 
+struct compat_request_ctx {
+	struct scatterlist src[2];
+	struct scatterlist dst[2];
+	struct scatterlist ivbuf[2];
+	struct scatterlist *ivsg;
+	struct aead_givcrypt_request subreq;
+};
+
+static int aead_null_givencrypt(struct aead_givcrypt_request *req);
+static int aead_null_givdecrypt(struct aead_givcrypt_request *req);
+
 static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 			    unsigned int keylen)
 {
-	struct aead_alg *aead = crypto_aead_alg(tfm);
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
 	int ret;
 	u8 *buffer, *alignbuffer;
@@ -42,47 +53,95 @@ static int setkey_unaligned(struct crypto_aead *tfm, const u8 *key,
 
 	alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1);
 	memcpy(alignbuffer, key, keylen);
-	ret = aead->setkey(tfm, alignbuffer, keylen);
+	ret = tfm->setkey(tfm, alignbuffer, keylen);
 	memset(alignbuffer, 0, keylen);
 	kfree(buffer);
 	return ret;
 }
 
-static int setkey(struct crypto_aead *tfm, const u8 *key, unsigned int keylen)
+int crypto_aead_setkey(struct crypto_aead *tfm,
+		       const u8 *key, unsigned int keylen)
 {
-	struct aead_alg *aead = crypto_aead_alg(tfm);
 	unsigned long alignmask = crypto_aead_alignmask(tfm);
 
+	tfm = tfm->child;
+
 	if ((unsigned long)key & alignmask)
 		return setkey_unaligned(tfm, key, keylen);
 
-	return aead->setkey(tfm, key, keylen);
+	return tfm->setkey(tfm, key, keylen);
 }
+EXPORT_SYMBOL_GPL(crypto_aead_setkey);
 
 int crypto_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 {
-	struct aead_tfm *crt = crypto_aead_crt(tfm);
 	int err;
 
-	if (authsize > crypto_aead_alg(tfm)->maxauthsize)
+	if (authsize > crypto_aead_maxauthsize(tfm))
 		return -EINVAL;
 
-	if (crypto_aead_alg(tfm)->setauthsize) {
-		err = crypto_aead_alg(tfm)->setauthsize(crt->base, authsize);
+	if (tfm->setauthsize) {
+		err = tfm->setauthsize(tfm->child, authsize);
 		if (err)
 			return err;
 	}
 
-	crypto_aead_crt(crt->base)->authsize = authsize;
-	crt->authsize = authsize;
+	tfm->child->authsize = authsize;
+	tfm->authsize = authsize;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_aead_setauthsize);
 
-static unsigned int crypto_aead_ctxsize(struct crypto_alg *alg, u32 type,
-					u32 mask)
+struct aead_old_request {
+	struct scatterlist srcbuf[2];
+	struct scatterlist dstbuf[2];
+	struct aead_request subreq;
+};
+
+unsigned int crypto_aead_reqsize(struct crypto_aead *tfm)
 {
-	return alg->cra_ctxsize;
+	return tfm->reqsize + sizeof(struct aead_old_request);
+}
+EXPORT_SYMBOL_GPL(crypto_aead_reqsize);
+
+static int old_crypt(struct aead_request *req,
+		     int (*crypt)(struct aead_request *req))
+{
+	struct aead_old_request *nreq = aead_request_ctx(req);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct scatterlist *src, *dst;
+
+	if (req->old)
+		return crypt(req);
+
+	src = scatterwalk_ffwd(nreq->srcbuf, req->src, req->assoclen);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(nreq->dstbuf, req->dst, req->assoclen);
+
+	aead_request_set_tfm(&nreq->subreq, aead);
+	aead_request_set_callback(&nreq->subreq, aead_request_flags(req),
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(&nreq->subreq, src, dst, req->cryptlen,
+			       req->iv);
+	aead_request_set_assoc(&nreq->subreq, req->src, req->assoclen);
+
+	return crypt(&nreq->subreq);
+}
+
+static int old_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
+
+	return old_crypt(req, alg->encrypt);
+}
+
+static int old_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct old_aead_alg *alg = crypto_old_aead_alg(aead);
+
+	return old_crypt(req, alg->decrypt);
 }
 
 static int no_givcrypt(struct aead_givcrypt_request *req)
@@ -90,32 +149,68 @@ static int no_givcrypt(struct aead_givcrypt_request *req)
 	return -ENOSYS;
 }
 
-static int crypto_init_aead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+static int crypto_old_aead_init_tfm(struct crypto_tfm *tfm)
 {
-	struct aead_alg *alg = &tfm->__crt_alg->cra_aead;
-	struct aead_tfm *crt = &tfm->crt_aead;
+	struct old_aead_alg *alg = &tfm->__crt_alg->cra_aead;
+	struct crypto_aead *crt = __crypto_aead_cast(tfm);
 
 	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
 		return -EINVAL;
 
-	crt->setkey = tfm->__crt_alg->cra_flags & CRYPTO_ALG_GENIV ?
-		      alg->setkey : setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-	crt->givencrypt = alg->givencrypt ?: no_givcrypt;
-	crt->givdecrypt = alg->givdecrypt ?: no_givcrypt;
-	crt->base = __crypto_aead_cast(tfm);
-	crt->ivsize = alg->ivsize;
+	crt->setkey = alg->setkey;
+	crt->setauthsize = alg->setauthsize;
+	crt->encrypt = old_encrypt;
+	crt->decrypt = old_decrypt;
+	if (alg->ivsize) {
+		crt->givencrypt = alg->givencrypt ?: no_givcrypt;
+		crt->givdecrypt = alg->givdecrypt ?: no_givcrypt;
+	} else {
+		crt->givencrypt = aead_null_givencrypt;
+		crt->givdecrypt = aead_null_givdecrypt;
+	}
+	crt->child = __crypto_aead_cast(tfm);
 	crt->authsize = alg->maxauthsize;
 
 	return 0;
 }
 
+static void crypto_aead_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *aead = __crypto_aead_cast(tfm);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+
+	alg->exit(aead);
+}
+
+static int crypto_aead_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *aead = __crypto_aead_cast(tfm);
+	struct aead_alg *alg = crypto_aead_alg(aead);
+
+	if (crypto_old_aead_alg(aead)->encrypt)
+		return crypto_old_aead_init_tfm(tfm);
+
+	aead->setkey = alg->setkey;
+	aead->setauthsize = alg->setauthsize;
+	aead->encrypt = alg->encrypt;
+	aead->decrypt = alg->decrypt;
+	aead->child = __crypto_aead_cast(tfm);
+	aead->authsize = alg->maxauthsize;
+
+	if (alg->exit)
+		aead->base.exit = crypto_aead_exit_tfm;
+
+	if (alg->init)
+		return alg->init(aead);
+
+	return 0;
+}
+
 #ifdef CONFIG_NET
-static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	strncpy(raead.type, "aead", sizeof(raead.type));
 	strncpy(raead.geniv, aead->geniv ?: "<built-in>", sizeof(raead.geniv));
@@ -133,6 +228,64 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 #else
+static int crypto_old_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+static void crypto_old_aead_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	struct old_aead_alg *aead = &alg->cra_aead;
+
+	seq_printf(m, "type         : aead\n");
+	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
+					     "yes" : "no");
+	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
+	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
+	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
+	seq_printf(m, "geniv        : %s\n", aead->geniv ?: "<built-in>");
+}
+
+const struct crypto_type crypto_aead_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_old_aead_show,
+#endif
+	.report = crypto_old_aead_report,
+	.lookup = crypto_lookup_aead,
+	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
+};
+EXPORT_SYMBOL_GPL(crypto_aead_type);
+
+#ifdef CONFIG_NET
+static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_aead raead;
+	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
+
+	strncpy(raead.type, "aead", sizeof(raead.type));
+	strncpy(raead.geniv, "<none>", sizeof(raead.geniv));
+
+	raead.blocksize = alg->cra_blocksize;
+	raead.maxauthsize = aead->maxauthsize;
+	raead.ivsize = aead->ivsize;
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AEAD,
+		    sizeof(struct crypto_report_aead), &raead))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
 static int crypto_aead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	return -ENOSYS;
@@ -143,7 +296,7 @@ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	__attribute__ ((unused));
 static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 {
-	struct aead_alg *aead = &alg->cra_aead;
+	struct aead_alg *aead = container_of(alg, struct aead_alg, base);
 
 	seq_printf(m, "type         : aead\n");
 	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
@@ -151,18 +304,21 @@ static void crypto_aead_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_printf(m, "blocksize    : %u\n", alg->cra_blocksize);
 	seq_printf(m, "ivsize       : %u\n", aead->ivsize);
 	seq_printf(m, "maxauthsize  : %u\n", aead->maxauthsize);
-	seq_printf(m, "geniv        : %s\n", aead->geniv ?: "<built-in>");
+	seq_printf(m, "geniv        : <none>\n");
 }
 
-const struct crypto_type crypto_aead_type = {
-	.ctxsize = crypto_aead_ctxsize,
-	.init = crypto_init_aead_ops,
+static const struct crypto_type crypto_new_aead_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_aead_show,
 #endif
 	.report = crypto_aead_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
 };
-EXPORT_SYMBOL_GPL(crypto_aead_type);
 
 static int aead_null_givencrypt(struct aead_givcrypt_request *req)
 {
@@ -174,33 +330,11 @@ static int aead_null_givdecrypt(struct aead_givcrypt_request *req)
 	return crypto_aead_decrypt(&req->areq);
 }
 
-static int crypto_init_nivaead_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
-{
-	struct aead_alg *alg = &tfm->__crt_alg->cra_aead;
-	struct aead_tfm *crt = &tfm->crt_aead;
-
-	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
-		return -EINVAL;
-
-	crt->setkey = setkey;
-	crt->encrypt = alg->encrypt;
-	crt->decrypt = alg->decrypt;
-	if (!alg->ivsize) {
-		crt->givencrypt = aead_null_givencrypt;
-		crt->givdecrypt = aead_null_givdecrypt;
-	}
-	crt->base = __crypto_aead_cast(tfm);
-	crt->ivsize = alg->ivsize;
-	crt->authsize = alg->maxauthsize;
-
-	return 0;
-}
-
 #ifdef CONFIG_NET
 static int crypto_nivaead_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
 	struct crypto_report_aead raead;
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	strncpy(raead.type, "nivaead", sizeof(raead.type));
 	strncpy(raead.geniv, aead->geniv, sizeof(raead.geniv));
@@ -229,7 +363,7 @@ static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 	__attribute__ ((unused));
 static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 {
-	struct aead_alg *aead = &alg->cra_aead;
+	struct old_aead_alg *aead = &alg->cra_aead;
 
 	seq_printf(m, "type         : nivaead\n");
 	seq_printf(m, "async        : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ?
@@ -241,43 +375,215 @@ static void crypto_nivaead_show(struct seq_file *m, struct crypto_alg *alg)
 }
 
 const struct crypto_type crypto_nivaead_type = {
-	.ctxsize = crypto_aead_ctxsize,
-	.init = crypto_init_nivaead_ops,
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_aead_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_nivaead_show,
 #endif
 	.report = crypto_nivaead_report,
+	.maskclear = ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV),
+	.maskset = CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV,
+	.type = CRYPTO_ALG_TYPE_AEAD,
+	.tfmsize = offsetof(struct crypto_aead, base),
 };
 EXPORT_SYMBOL_GPL(crypto_nivaead_type);
 
 static int crypto_grab_nivaead(struct crypto_aead_spawn *spawn,
 			       const char *name, u32 type, u32 mask)
 {
-	struct crypto_alg *alg;
+	spawn->base.frontend = &crypto_nivaead_type;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+
+static int aead_geniv_setkey(struct crypto_aead *tfm,
+			     const u8 *key, unsigned int keylen)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setkey(ctx->child, key, keylen);
+}
+
+static int aead_geniv_setauthsize(struct crypto_aead *tfm,
+				  unsigned int authsize)
+{
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return crypto_aead_setauthsize(ctx->child, authsize);
+}
+
+static void compat_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_givcrypt_request *subreq = &rctx->subreq;
+	struct crypto_aead *geniv;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	scatterwalk_map_and_copy(subreq->giv, rctx->ivsg, 0,
+				 crypto_aead_ivsize(geniv), 1);
+
+out:
+	kzfree(subreq->giv);
+}
+
+static void compat_encrypt_complete(struct crypto_async_request *base, int err)
+{
+	struct aead_request *req = base->data;
+
+	compat_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static int compat_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_givcrypt_request *subreq = &rctx->subreq;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	struct scatterlist *src, *dst;
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	__be64 seq;
 	int err;
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask |= CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	alg = crypto_alg_mod_lookup(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
+	compl = req->base.complete;
+	data = req->base.data;
+
+	rctx->ivsg = scatterwalk_ffwd(rctx->ivbuf, req->dst, req->assoclen);
+	info = PageHighMem(sg_page(rctx->ivsg)) ? NULL : sg_virt(rctx->ivsg);
+
+	if (!info) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		compl = compat_encrypt_complete;
+		data = req;
+	}
+
+	memcpy(&seq, req->iv + ivsize - sizeof(seq), sizeof(seq));
+
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(rctx->dst, rctx->ivsg, ivsize);
+
+	aead_givcrypt_set_tfm(subreq, ctx->child);
+	aead_givcrypt_set_callback(subreq, req->base.flags,
+				   req->base.complete, req->base.data);
+	aead_givcrypt_set_crypt(subreq, src, dst,
+				req->cryptlen - ivsize, req->iv);
+	aead_givcrypt_set_assoc(subreq, req->src, req->assoclen);
+	aead_givcrypt_set_giv(subreq, info, be64_to_cpu(seq));
+
+	err = crypto_aead_givencrypt(subreq);
+	if (unlikely(PageHighMem(sg_page(rctx->ivsg))))
+		compat_encrypt_complete2(req, err);
+	return err;
+}
+
+static int compat_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct compat_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq.areq;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	struct scatterlist *src, *dst;
+	crypto_completion_t compl;
+	void *data;
+
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	src = scatterwalk_ffwd(rctx->src, req->src, req->assoclen + ivsize);
+	dst = req->src == req->dst ?
+	      src : scatterwalk_ffwd(rctx->dst, req->dst,
+				     req->assoclen + ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, src, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_assoc(subreq, req->src, req->assoclen);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+
+	return crypto_aead_decrypt(subreq);
+}
+
+static int compat_encrypt_first(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err = 0;
+
+	spin_lock_bh(&ctx->lock);
+	if (geniv->encrypt != compat_encrypt_first)
+		goto unlock;
+
+	geniv->encrypt = compat_encrypt;
+
+unlock:
+	spin_unlock_bh(&ctx->lock);
+
+	if (err)
+		return err;
+
+	return compat_encrypt(req);
+}
+
+static int aead_geniv_init_compat(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
+
+	spin_lock_init(&ctx->lock);
+
+	crypto_aead_set_reqsize(geniv, sizeof(struct compat_request_ctx));
+
+	err = aead_geniv_init(tfm);
+
+	ctx->child = geniv->child;
+	geniv->child = geniv;
 
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
 	return err;
 }
 
-struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
-					 struct rtattr **tb, u32 type,
-					 u32 mask)
+static void aead_geniv_exit_compat(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
+
+	crypto_free_aead(ctx->child);
+}
+
+struct aead_instance *aead_geniv_alloc(struct crypto_template *tmpl,
+				       struct rtattr **tb, u32 type, u32 mask)
 {
 	const char *name;
 	struct crypto_aead_spawn *spawn;
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	unsigned int ivsize;
+	unsigned int maxauthsize;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
@@ -296,20 +602,25 @@ struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	if (!inst)
 		return ERR_PTR(-ENOMEM);
 
-	spawn = crypto_instance_ctx(inst);
+	spawn = aead_instance_ctx(inst);
 
 	/* Ignore async algorithms if necessary. */
 	mask |= crypto_requires_sync(algt->type, algt->mask);
 
-	crypto_set_aead_spawn(spawn, inst);
-	err = crypto_grab_nivaead(spawn, name, type, mask);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
+	err = (algt->mask & CRYPTO_ALG_GENIV) ?
+	      crypto_grab_nivaead(spawn, name, type, mask) :
+	      crypto_grab_aead(spawn, name, type, mask);
 	if (err)
 		goto err_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	ivsize = crypto_aead_alg_ivsize(alg);
+	maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
 	err = -EINVAL;
-	if (!alg->cra_aead.ivsize)
+	if (ivsize < sizeof(u64))
 		goto err_drop_alg;
 
 	/*
@@ -318,39 +629,64 @@ struct crypto_instance *aead_geniv_alloc(struct crypto_template *tmpl,
 	 * template name and double-check the IV generator.
 	 */
 	if (algt->mask & CRYPTO_ALG_GENIV) {
-		if (strcmp(tmpl->name, alg->cra_aead.geniv))
+		if (!alg->base.cra_aead.encrypt)
+			goto err_drop_alg;
+		if (strcmp(tmpl->name, alg->base.cra_aead.geniv))
 			goto err_drop_alg;
 
-		memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-		memcpy(inst->alg.cra_driver_name, alg->cra_driver_name,
+		memcpy(inst->alg.base.cra_name, alg->base.cra_name,
 		       CRYPTO_MAX_ALG_NAME);
-	} else {
-		err = -ENAMETOOLONG;
-		if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
-		if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-			     "%s(%s)", tmpl->name, alg->cra_driver_name) >=
-		    CRYPTO_MAX_ALG_NAME)
-			goto err_drop_alg;
+		memcpy(inst->alg.base.cra_driver_name,
+		       alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME);
+
+		inst->alg.base.cra_flags = CRYPTO_ALG_TYPE_AEAD |
+					   CRYPTO_ALG_GENIV;
+		inst->alg.base.cra_flags |= alg->base.cra_flags &
+					    CRYPTO_ALG_ASYNC;
+		inst->alg.base.cra_priority = alg->base.cra_priority;
+		inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+		inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
+		inst->alg.base.cra_type = &crypto_aead_type;
+
+		inst->alg.base.cra_aead.ivsize = ivsize;
+		inst->alg.base.cra_aead.maxauthsize = maxauthsize;
+
+		inst->alg.base.cra_aead.setkey = alg->base.cra_aead.setkey;
+		inst->alg.base.cra_aead.setauthsize =
+			alg->base.cra_aead.setauthsize;
+		inst->alg.base.cra_aead.encrypt = alg->base.cra_aead.encrypt;
+		inst->alg.base.cra_aead.decrypt = alg->base.cra_aead.decrypt;
+
+		goto out;
 	}
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_GENIV;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_aead_type;
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s)", tmpl->name, alg->base.cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto err_drop_alg;
+
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = alg->base.cra_blocksize;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
+
+	inst->alg.setkey = aead_geniv_setkey;
+	inst->alg.setauthsize = aead_geniv_setauthsize;
 
-	inst->alg.cra_aead.ivsize = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
-	inst->alg.cra_aead.geniv = alg->cra_aead.geniv;
+	inst->alg.ivsize = ivsize;
+	inst->alg.maxauthsize = maxauthsize;
 
-	inst->alg.cra_aead.setkey = alg->cra_aead.setkey;
-	inst->alg.cra_aead.setauthsize = alg->cra_aead.setauthsize;
-	inst->alg.cra_aead.encrypt = alg->cra_aead.encrypt;
-	inst->alg.cra_aead.decrypt = alg->cra_aead.decrypt;
+	inst->alg.encrypt = compat_encrypt_first;
+	inst->alg.decrypt = compat_decrypt;
+
+	inst->alg.base.cra_init = aead_geniv_init_compat;
+	inst->alg.base.cra_exit = aead_geniv_exit_compat;
 
 out:
 	return inst;
@@ -364,9 +700,9 @@ err_free_inst:
 }
 EXPORT_SYMBOL_GPL(aead_geniv_alloc);
 
-void aead_geniv_free(struct crypto_instance *inst)
+void aead_geniv_free(struct aead_instance *inst)
 {
-	crypto_drop_aead(crypto_instance_ctx(inst));
+	crypto_drop_aead(aead_instance_ctx(inst));
 	kfree(inst);
 }
 EXPORT_SYMBOL_GPL(aead_geniv_free);
@@ -374,14 +710,17 @@ EXPORT_SYMBOL_GPL(aead_geniv_free);
 int aead_geniv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct crypto_aead *child;
 	struct crypto_aead *aead;
 
-	aead = crypto_spawn_aead(crypto_instance_ctx(inst));
-	if (IS_ERR(aead))
-		return PTR_ERR(aead);
+	aead = __crypto_aead_cast(tfm);
+
+	child = crypto_spawn_aead(crypto_instance_ctx(inst));
+	if (IS_ERR(child))
+		return PTR_ERR(child);
 
-	tfm->crt_aead.base = aead;
-	tfm->crt_aead.reqsize += crypto_aead_reqsize(aead);
+	aead->child = child;
+	aead->reqsize += crypto_aead_reqsize(child);
 
 	return 0;
 }
@@ -389,7 +728,7 @@ EXPORT_SYMBOL_GPL(aead_geniv_init);
 
 void aead_geniv_exit(struct crypto_tfm *tfm)
 {
-	crypto_free_aead(tfm->crt_aead.base);
+	crypto_free_aead(__crypto_aead_cast(tfm)->child);
 }
 EXPORT_SYMBOL_GPL(aead_geniv_exit);
 
@@ -443,6 +782,13 @@ static int crypto_nivaead_default(struct crypto_alg *alg, u32 type, u32 mask)
 	if (!tmpl)
 		goto kill_larval;
 
+	if (tmpl->create) {
+		err = tmpl->create(tmpl, tb);
+		if (err)
+			goto put_tmpl;
+		goto ok;
+	}
+
 	inst = tmpl->alloc(tb);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
@@ -454,6 +800,7 @@ static int crypto_nivaead_default(struct crypto_alg *alg, u32 type, u32 mask)
 		goto put_tmpl;
 	}
 
+ok:
 	/* Redo the lookup to use the instance we just registered. */
 	err = -EAGAIN;
 
@@ -489,7 +836,7 @@ struct crypto_alg *crypto_lookup_aead(const char *name, u32 type, u32 mask)
 		return alg;
 
 	if (alg->cra_type == &crypto_aead_type) {
-		if ((alg->cra_flags ^ type ^ ~mask) & CRYPTO_ALG_TESTED) {
+		if (~alg->cra_flags & (type ^ ~mask) & CRYPTO_ALG_TESTED) {
 			crypto_mod_put(alg);
 			alg = ERR_PTR(-ENOENT);
 		}
@@ -505,62 +852,91 @@ EXPORT_SYMBOL_GPL(crypto_lookup_aead);
 int crypto_grab_aead(struct crypto_aead_spawn *spawn, const char *name,
 		     u32 type, u32 mask)
 {
-	struct crypto_alg *alg;
-	int err;
+	spawn->base.frontend = &crypto_aead_type;
+	return crypto_grab_spawn(&spawn->base, name, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_grab_aead);
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	mask |= CRYPTO_ALG_TYPE_MASK;
+struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_aead_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_aead);
 
-	alg = crypto_lookup_aead(name, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
+static int aead_prepare_alg(struct aead_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
 
-	err = crypto_init_spawn(&spawn->base, alg, spawn->base.inst, mask);
-	crypto_mod_put(alg);
-	return err;
+	if (max(alg->maxauthsize, alg->ivsize) > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	base->cra_type = &crypto_new_aead_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_AEAD;
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(crypto_grab_aead);
 
-struct crypto_aead *crypto_alloc_aead(const char *alg_name, u32 type, u32 mask)
+int crypto_register_aead(struct aead_alg *alg)
 {
-	struct crypto_tfm *tfm;
+	struct crypto_alg *base = &alg->base;
 	int err;
 
-	type &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	type |= CRYPTO_ALG_TYPE_AEAD;
-	mask &= ~(CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_GENIV);
-	mask |= CRYPTO_ALG_TYPE_MASK;
+	err = aead_prepare_alg(alg);
+	if (err)
+		return err;
 
-	for (;;) {
-		struct crypto_alg *alg;
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_aead);
 
-		alg = crypto_lookup_aead(alg_name, type, mask);
-		if (IS_ERR(alg)) {
-			err = PTR_ERR(alg);
-			goto err;
-		}
+void crypto_unregister_aead(struct aead_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_aead);
 
-		tfm = __crypto_alloc_tfm(alg, type, mask);
-		if (!IS_ERR(tfm))
-			return __crypto_aead_cast(tfm);
+int crypto_register_aeads(struct aead_alg *algs, int count)
+{
+	int i, ret;
 
-		crypto_mod_put(alg);
-		err = PTR_ERR(tfm);
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_aead(&algs[i]);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
 
 err:
-		if (err != -EAGAIN)
-			break;
-		if (signal_pending(current)) {
-			err = -EINTR;
-			break;
-		}
-	}
+	for (--i; i >= 0; --i)
+		crypto_unregister_aead(&algs[i]);
 
-	return ERR_PTR(err);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(crypto_alloc_aead);
+EXPORT_SYMBOL_GPL(crypto_register_aeads);
+
+void crypto_unregister_aeads(struct aead_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_aead(&algs[i]);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_aeads);
+
+int aead_register_instance(struct crypto_template *tmpl,
+			   struct aead_instance *inst)
+{
+	int err;
+
+	err = aead_prepare_alg(&inst->alg);
+	if (err)
+		return err;
+
+	return crypto_register_instance(tmpl, aead_crypto_instance(inst));
+}
+EXPORT_SYMBOL_GPL(aead_register_instance);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Authenticated Encryption with Associated Data (AEAD)");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index f22cc56fd1b3..a8e7aa3e257b 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -127,6 +127,7 @@ EXPORT_SYMBOL_GPL(af_alg_release);
 
 static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
+	const u32 forbidden = CRYPTO_ALG_INTERNAL;
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct sockaddr_alg *sa = (void *)uaddr;
@@ -151,7 +152,9 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
-	private = type->bind(sa->salg_name, sa->salg_feat, sa->salg_mask);
+	private = type->bind(sa->salg_name,
+			     sa->salg_feat & ~forbidden,
+			     sa->salg_mask & ~forbidden);
 	if (IS_ERR(private)) {
 		module_put(type->owner);
 		return PTR_ERR(private);
@@ -244,7 +247,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 	if (!type)
 		goto unlock;
 
-	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto);
+	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0);
 	err = -ENOMEM;
 	if (!sk2)
 		goto unlock;
@@ -324,7 +327,7 @@ static int alg_create(struct net *net, struct socket *sock, int protocol,
 		return -EPROTONOSUPPORT;
 
 	err = -ENOMEM;
-	sk = sk_alloc(net, PF_ALG, GFP_KERNEL, &alg_proto);
+	sk = sk_alloc(net, PF_ALG, GFP_KERNEL, &alg_proto, kern);
 	if (!sk)
 		goto out;
 
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
new file mode 100644
index 000000000000..d7986414814e
--- /dev/null
+++ b/crypto/akcipher.c
@@ -0,0 +1,117 @@
+/*
+ * Public Key Encryption
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <linux/cryptouser.h>
+#include <net/netlink.h>
+#include <crypto/akcipher.h>
+#include <crypto/public_key.h>
+#include "internal.h"
+
+#ifdef CONFIG_NET
+static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_akcipher rakcipher;
+
+	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
+		    sizeof(struct crypto_report_akcipher), &rakcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+#else
+static int crypto_akcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	return -ENOSYS;
+}
+#endif
+
+static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg)
+	__attribute__ ((unused));
+
+static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg)
+{
+	seq_puts(m, "type         : akcipher\n");
+}
+
+static void crypto_akcipher_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm);
+	struct akcipher_alg *alg = crypto_akcipher_alg(akcipher);
+
+	alg->exit(akcipher);
+}
+
+static int crypto_akcipher_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm);
+	struct akcipher_alg *alg = crypto_akcipher_alg(akcipher);
+
+	if (alg->exit)
+		akcipher->base.exit = crypto_akcipher_exit_tfm;
+
+	if (alg->init)
+		return alg->init(akcipher);
+
+	return 0;
+}
+
+static const struct crypto_type crypto_akcipher_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_akcipher_init_tfm,
+#ifdef CONFIG_PROC_FS
+	.show = crypto_akcipher_show,
+#endif
+	.report = crypto_akcipher_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_AKCIPHER,
+	.tfmsize = offsetof(struct crypto_akcipher, base),
+};
+
+struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type,
+					      u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_akcipher_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_akcipher);
+
+int crypto_register_akcipher(struct akcipher_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	base->cra_type = &crypto_akcipher_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER;
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_akcipher);
+
+void crypto_unregister_akcipher(struct akcipher_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_akcipher);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Generic public key cihper type");
diff --git a/crypto/algapi.c b/crypto/algapi.c
index d2627a3d4ed8..3c079b7f23f6 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -12,6 +12,7 @@
 
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/fips.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -43,12 +44,9 @@ static inline int crypto_set_driver_name(struct crypto_alg *alg)
 
 static inline void crypto_check_module_sig(struct module *mod)
 {
-#ifdef CONFIG_CRYPTO_FIPS
-	if (fips_enabled && mod && !mod->sig_ok)
+	if (fips_enabled && mod && !module_sig_ok(mod))
 		panic("Module %s signature verification failed in FIPS mode\n",
-		      mod->name);
-#endif
-	return;
+		      module_name(mod));
 }
 
 static int crypto_check_alg(struct crypto_alg *alg)
@@ -614,6 +612,22 @@ out:
 }
 EXPORT_SYMBOL_GPL(crypto_init_spawn2);
 
+int crypto_grab_spawn(struct crypto_spawn *spawn, const char *name,
+		      u32 type, u32 mask)
+{
+	struct crypto_alg *alg;
+	int err;
+
+	alg = crypto_find_alg(name, spawn->frontend, type, mask);
+	if (IS_ERR(alg))
+		return PTR_ERR(alg);
+
+	err = crypto_init_spawn(spawn, alg, spawn->inst, mask);
+	crypto_mod_put(alg);
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_grab_spawn);
+
 void crypto_drop_spawn(struct crypto_spawn *spawn)
 {
 	if (!spawn->alg)
@@ -964,6 +978,13 @@ void crypto_xor(u8 *dst, const u8 *src, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(crypto_xor);
 
+unsigned int crypto_alg_extsize(struct crypto_alg *alg)
+{
+	return alg->cra_ctxsize +
+	       (alg->cra_alignmask & ~(crypto_tfm_ctx_alignment() - 1));
+}
+EXPORT_SYMBOL_GPL(crypto_alg_extsize);
+
 static int __init crypto_algapi_init(void)
 {
 	crypto_init_proc();
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 00a6fe166fed..e0408a480d2f 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -13,6 +13,7 @@
  * any later version.
  */
 
+#include <crypto/aead.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/if_alg.h>
 #include <linux/init.h>
@@ -33,7 +34,7 @@ struct aead_ctx {
 	/*
 	 * RSGL_MAX_ENTRIES is an artificial limit where user space at maximum
 	 * can cause the kernel to allocate RSGL_MAX_ENTRIES * ALG_MAX_PAGES
-	 * bytes
+	 * pages
 	 */
 #define RSGL_MAX_ENTRIES ALG_MAX_PAGES
 	struct af_alg_sgl rsgl[RSGL_MAX_ENTRIES];
@@ -71,7 +72,7 @@ static inline bool aead_sufficient_data(struct aead_ctx *ctx)
 {
 	unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req));
 
-	return (ctx->used >= (ctx->aead_assoclen + (ctx->enc ? 0 : as)));
+	return ctx->used >= ctx->aead_assoclen + as;
 }
 
 static void aead_put_sgl(struct sock *sk)
@@ -352,12 +353,8 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct aead_ctx *ctx = ask->private;
-	unsigned bs = crypto_aead_blocksize(crypto_aead_reqtfm(&ctx->aead_req));
 	unsigned as = crypto_aead_authsize(crypto_aead_reqtfm(&ctx->aead_req));
 	struct aead_sg_list *sgl = &ctx->tsgl;
-	struct scatterlist *sg = NULL;
-	struct scatterlist assoc[ALG_MAX_PAGES];
-	size_t assoclen = 0;
 	unsigned int i = 0;
 	int err = -EINVAL;
 	unsigned long used = 0;
@@ -406,23 +403,13 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	if (!aead_sufficient_data(ctx))
 		goto unlock;
 
+	outlen = used;
+
 	/*
 	 * The cipher operation input data is reduced by the associated data
 	 * length as this data is processed separately later on.
 	 */
-	used -= ctx->aead_assoclen;
-
-	if (ctx->enc) {
-		/* round up output buffer to multiple of block size */
-		outlen = ((used + bs - 1) / bs * bs);
-		/* add the size needed for the auth tag to be created */
-		outlen += as;
-	} else {
-		/* output data size is input without the authentication tag */
-		outlen = used - as;
-		/* round up output buffer to multiple of block size */
-		outlen = ((outlen + bs - 1) / bs * bs);
-	}
+	used -= ctx->aead_assoclen + (ctx->enc ? as : 0);
 
 	/* convert iovecs of output buffers into scatterlists */
 	while (iov_iter_count(&msg->msg_iter)) {
@@ -435,11 +422,10 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 		if (err < 0)
 			goto unlock;
 		usedpages += err;
-		/* chain the new scatterlist with initial list */
+		/* chain the new scatterlist with previous one */
 		if (cnt)
-			scatterwalk_crypto_chain(ctx->rsgl[0].sg,
-					ctx->rsgl[cnt].sg, 1,
-					sg_nents(ctx->rsgl[cnt-1].sg));
+			af_alg_link_sg(&ctx->rsgl[cnt-1], &ctx->rsgl[cnt]);
+
 		/* we do not need more iovecs as we have sufficient memory */
 		if (outlen <= usedpages)
 			break;
@@ -452,47 +438,11 @@ static int aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t ignored,
 	if (usedpages < outlen)
 		goto unlock;
 
-	sg_init_table(assoc, ALG_MAX_PAGES);
-	assoclen = ctx->aead_assoclen;
-	/*
-	 * Split scatterlist into two: first part becomes AD, second part
-	 * is plaintext / ciphertext. The first part is assigned to assoc
-	 * scatterlist. When this loop finishes, sg points to the start of the
-	 * plaintext / ciphertext.
-	 */
-	for (i = 0; i < ctx->tsgl.cur; i++) {
-		sg = sgl->sg + i;
-		if (sg->length <= assoclen) {
-			/* AD is larger than one page */
-			sg_set_page(assoc + i, sg_page(sg),
-				    sg->length, sg->offset);
-			assoclen -= sg->length;
-			if (i >= ctx->tsgl.cur)
-				goto unlock;
-		} else if (!assoclen) {
-			/* current page is to start of plaintext / ciphertext */
-			if (i)
-				/* AD terminates at page boundary */
-				sg_mark_end(assoc + i - 1);
-			else
-				/* AD size is zero */
-				sg_mark_end(assoc);
-			break;
-		} else {
-			/* AD does not terminate at page boundary */
-			sg_set_page(assoc + i, sg_page(sg),
-				    assoclen, sg->offset);
-			sg_mark_end(assoc + i);
-			/* plaintext / ciphertext starts after AD */
-			sg->length -= assoclen;
-			sg->offset += assoclen;
-			break;
-		}
-	}
+	sg_mark_end(sgl->sg + sgl->cur - 1);
 
-	aead_request_set_assoc(&ctx->aead_req, assoc, ctx->aead_assoclen);
-	aead_request_set_crypt(&ctx->aead_req, sg, ctx->rsgl[0].sg, used,
-			       ctx->iv);
+	aead_request_set_crypt(&ctx->aead_req, sgl->sg, ctx->rsgl[0].sg,
+			       used, ctx->iv);
+	aead_request_set_ad(&ctx->aead_req, ctx->aead_assoclen);
 
 	err = af_alg_wait_for_completion(ctx->enc ?
 					 crypto_aead_encrypt(&ctx->aead_req) :
@@ -564,7 +514,8 @@ static struct proto_ops algif_aead_ops = {
 
 static void *aead_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_aead(name, type, mask);
+	return crypto_alloc_aead(name, type | CRYPTO_ALG_AEAD_NEW,
+				 mask | CRYPTO_ALG_AEAD_NEW);
 }
 
 static void aead_release(void *private)
diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c
index 8109aaad2726..150c2b6480ed 100644
--- a/crypto/algif_rng.c
+++ b/crypto/algif_rng.c
@@ -164,7 +164,7 @@ static int rng_setkey(void *private, const u8 *seed, unsigned int seedlen)
 	 * Check whether seedlen is of sufficient size is done in RNG
 	 * implementations.
 	 */
-	return crypto_rng_reset(private, (u8 *)seed, seedlen);
+	return crypto_rng_reset(private, seed, seedlen);
 }
 
 static const struct af_alg_type algif_type_rng = {
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index 765fe7609348..eff337ce9003 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -20,8 +20,6 @@
 #include <linux/moduleparam.h>
 #include <linux/string.h>
 
-#include "internal.h"
-
 #define DEFAULT_PRNG_KEY "0123456789abcdef"
 #define DEFAULT_PRNG_KSZ 16
 #define DEFAULT_BLK_SZ 16
@@ -281,11 +279,11 @@ static void free_prng_context(struct prng_context *ctx)
 }
 
 static int reset_prng_context(struct prng_context *ctx,
-			      unsigned char *key, size_t klen,
-			      unsigned char *V, unsigned char *DT)
+			      const unsigned char *key, size_t klen,
+			      const unsigned char *V, const unsigned char *DT)
 {
 	int ret;
-	unsigned char *prng_key;
+	const unsigned char *prng_key;
 
 	spin_lock_bh(&ctx->prng_lock);
 	ctx->flags |= PRNG_NEED_RESET;
@@ -353,8 +351,9 @@ static void cprng_exit(struct crypto_tfm *tfm)
 	free_prng_context(crypto_tfm_ctx(tfm));
 }
 
-static int cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
-			    unsigned int dlen)
+static int cprng_get_random(struct crypto_rng *tfm,
+			    const u8 *src, unsigned int slen,
+			    u8 *rdata, unsigned int dlen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
@@ -367,11 +366,12 @@ static int cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
  *  V and KEY are required during reset, and DT is optional, detected
  *  as being present by testing the length of the seed
  */
-static int cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int cprng_reset(struct crypto_rng *tfm,
+		       const u8 *seed, unsigned int slen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
-	u8 *key = seed + DEFAULT_BLK_SZ;
-	u8 *dt = NULL;
+	const u8 *key = seed + DEFAULT_BLK_SZ;
+	const u8 *dt = NULL;
 
 	if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ)
 		return -EINVAL;
@@ -387,18 +387,20 @@ static int cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 }
 
 #ifdef CONFIG_CRYPTO_FIPS
-static int fips_cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
-			    unsigned int dlen)
+static int fips_cprng_get_random(struct crypto_rng *tfm,
+				 const u8 *src, unsigned int slen,
+				 u8 *rdata, unsigned int dlen)
 {
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
 	return get_prng_bytes(rdata, dlen, prng, 1);
 }
 
-static int fips_cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int fips_cprng_reset(struct crypto_rng *tfm,
+			    const u8 *seed, unsigned int slen)
 {
 	u8 rdata[DEFAULT_BLK_SZ];
-	u8 *key = seed + DEFAULT_BLK_SZ;
+	const u8 *key = seed + DEFAULT_BLK_SZ;
 	int rc;
 
 	struct prng_context *prng = crypto_rng_ctx(tfm);
@@ -424,40 +426,32 @@ out:
 }
 #endif
 
-static struct crypto_alg rng_algs[] = { {
-	.cra_name		= "stdrng",
-	.cra_driver_name	= "ansi_cprng",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= sizeof(struct prng_context),
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= cprng_init,
-	.cra_exit		= cprng_exit,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= cprng_get_random,
-			.rng_reset		= cprng_reset,
-			.seedsize = DEFAULT_PRNG_KSZ + 2*DEFAULT_BLK_SZ,
-		}
+static struct rng_alg rng_algs[] = { {
+	.generate		= cprng_get_random,
+	.seed			= cprng_reset,
+	.seedsize		= DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ,
+	.base			=	{
+		.cra_name		= "stdrng",
+		.cra_driver_name	= "ansi_cprng",
+		.cra_priority		= 100,
+		.cra_ctxsize		= sizeof(struct prng_context),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= cprng_init,
+		.cra_exit		= cprng_exit,
 	}
 #ifdef CONFIG_CRYPTO_FIPS
 }, {
-	.cra_name		= "fips(ansi_cprng)",
-	.cra_driver_name	= "fips_ansi_cprng",
-	.cra_priority		= 300,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= sizeof(struct prng_context),
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= cprng_init,
-	.cra_exit		= cprng_exit,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= fips_cprng_get_random,
-			.rng_reset		= fips_cprng_reset,
-			.seedsize = DEFAULT_PRNG_KSZ + 2*DEFAULT_BLK_SZ,
-		}
+	.generate		= fips_cprng_get_random,
+	.seed			= fips_cprng_reset,
+	.seedsize		= DEFAULT_PRNG_KSZ + 2 * DEFAULT_BLK_SZ,
+	.base			=	{
+		.cra_name		= "fips(ansi_cprng)",
+		.cra_driver_name	= "fips_ansi_cprng",
+		.cra_priority		= 300,
+		.cra_ctxsize		= sizeof(struct prng_context),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= cprng_init,
+		.cra_exit		= cprng_exit,
 	}
 #endif
 } };
@@ -465,12 +459,12 @@ static struct crypto_alg rng_algs[] = { {
 /* Module initalization */
 static int __init prng_mod_init(void)
 {
-	return crypto_register_algs(rng_algs, ARRAY_SIZE(rng_algs));
+	return crypto_register_rngs(rng_algs, ARRAY_SIZE(rng_algs));
 }
 
 static void __exit prng_mod_fini(void)
 {
-	crypto_unregister_algs(rng_algs, ARRAY_SIZE(rng_algs));
+	crypto_unregister_rngs(rng_algs, ARRAY_SIZE(rng_algs));
 }
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 78fb16cab13f..3e852299afb4 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -10,7 +10,7 @@
  *
  */
 
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
@@ -570,13 +570,14 @@ static int crypto_authenc_init_tfm(struct crypto_tfm *tfm)
 			    crypto_ahash_alignmask(auth) + 1) +
 		      crypto_ablkcipher_ivsize(enc);
 
-	tfm->crt_aead.reqsize = sizeof(struct authenc_request_ctx) +
-				ctx->reqoff +
-				max_t(unsigned int,
-				crypto_ahash_reqsize(auth) +
-				sizeof(struct ahash_request),
-				sizeof(struct skcipher_givcrypt_request) +
-				crypto_ablkcipher_reqsize(enc));
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct authenc_request_ctx) +
+		ctx->reqoff +
+		max_t(unsigned int,
+			crypto_ahash_reqsize(auth) +
+			sizeof(struct ahash_request),
+			sizeof(struct skcipher_givcrypt_request) +
+			crypto_ablkcipher_reqsize(enc)));
 
 	return 0;
 
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 024bff2344fc..a3da6770bc9e 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -12,7 +12,7 @@
  *
  */
 
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/authenc.h>
@@ -662,13 +662,14 @@ static int crypto_authenc_esn_init_tfm(struct crypto_tfm *tfm)
 			    crypto_ahash_alignmask(auth) + 1) +
 		      crypto_ablkcipher_ivsize(enc);
 
-	tfm->crt_aead.reqsize = sizeof(struct authenc_esn_request_ctx) +
-				ctx->reqoff +
-				max_t(unsigned int,
-				crypto_ahash_reqsize(auth) +
-				sizeof(struct ahash_request),
-				sizeof(struct skcipher_givcrypt_request) +
-				crypto_ablkcipher_reqsize(enc));
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct authenc_esn_request_ctx) +
+		ctx->reqoff +
+		max_t(unsigned int,
+			crypto_ahash_reqsize(auth) +
+			sizeof(struct ahash_request),
+			sizeof(struct skcipher_givcrypt_request) +
+			crypto_ablkcipher_reqsize(enc)));
 
 	return 0;
 
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 0122bec38564..11b981492031 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -14,6 +14,7 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/errno.h>
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 003bbbd21a2b..a4d1a5eda18b 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -453,9 +453,9 @@ static int crypto_ccm_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_tfm_alg_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = align +
-				sizeof(struct crypto_ccm_req_priv_ctx) +
-				crypto_ablkcipher_reqsize(ctr);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		align + sizeof(struct crypto_ccm_req_priv_ctx) +
+		crypto_ablkcipher_reqsize(ctr));
 
 	return 0;
 
@@ -729,10 +729,10 @@ static int crypto_rfc4309_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct aead_request) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 16);
 
 	return 0;
 }
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
new file mode 100644
index 000000000000..fa42e708aa96
--- /dev/null
+++ b/crypto/chacha20_generic.c
@@ -0,0 +1,216 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define CHACHA20_NONCE_SIZE 16
+#define CHACHA20_KEY_SIZE   32
+#define CHACHA20_BLOCK_SIZE 64
+
+struct chacha20_ctx {
+	u32 key[8];
+};
+
+static inline u32 rotl32(u32 v, u8 n)
+{
+	return (v << n) | (v >> (sizeof(v) * 8 - n));
+}
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static void chacha20_block(u32 *state, void *stream)
+{
+	u32 x[16], *out = stream;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		x[i] = state[i];
+
+	for (i = 0; i < 20; i += 2) {
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],  16);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],  16);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],  16);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],  16);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],  12);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],  12);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10], 12);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11], 12);
+
+		x[0]  += x[4];    x[12] = rotl32(x[12] ^ x[0],   8);
+		x[1]  += x[5];    x[13] = rotl32(x[13] ^ x[1],   8);
+		x[2]  += x[6];    x[14] = rotl32(x[14] ^ x[2],   8);
+		x[3]  += x[7];    x[15] = rotl32(x[15] ^ x[3],   8);
+
+		x[8]  += x[12];   x[4]  = rotl32(x[4]  ^ x[8],   7);
+		x[9]  += x[13];   x[5]  = rotl32(x[5]  ^ x[9],   7);
+		x[10] += x[14];   x[6]  = rotl32(x[6]  ^ x[10],  7);
+		x[11] += x[15];   x[7]  = rotl32(x[7]  ^ x[11],  7);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],  16);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],  16);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],  16);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],  16);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10], 12);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11], 12);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],  12);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],  12);
+
+		x[0]  += x[5];    x[15] = rotl32(x[15] ^ x[0],   8);
+		x[1]  += x[6];    x[12] = rotl32(x[12] ^ x[1],   8);
+		x[2]  += x[7];    x[13] = rotl32(x[13] ^ x[2],   8);
+		x[3]  += x[4];    x[14] = rotl32(x[14] ^ x[3],   8);
+
+		x[10] += x[15];   x[5]  = rotl32(x[5]  ^ x[10],  7);
+		x[11] += x[12];   x[6]  = rotl32(x[6]  ^ x[11],  7);
+		x[8]  += x[13];   x[7]  = rotl32(x[7]  ^ x[8],   7);
+		x[9]  += x[14];   x[4]  = rotl32(x[4]  ^ x[9],   7);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		out[i] = cpu_to_le32(x[i] + state[i]);
+
+	state[12]++;
+}
+
+static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
+			     unsigned int bytes)
+{
+	u8 stream[CHACHA20_BLOCK_SIZE];
+
+	if (dst != src)
+		memcpy(dst, src, bytes);
+
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha20_block(state, stream);
+		crypto_xor(dst, stream, bytes);
+	}
+}
+
+static void chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv)
+{
+	static const char constant[16] = "expand 32-byte k";
+
+	state[0]  = le32_to_cpuvp(constant +  0);
+	state[1]  = le32_to_cpuvp(constant +  4);
+	state[2]  = le32_to_cpuvp(constant +  8);
+	state[3]  = le32_to_cpuvp(constant + 12);
+	state[4]  = ctx->key[0];
+	state[5]  = ctx->key[1];
+	state[6]  = ctx->key[2];
+	state[7]  = ctx->key[3];
+	state[8]  = ctx->key[4];
+	state[9]  = ctx->key[5];
+	state[10] = ctx->key[6];
+	state[11] = ctx->key[7];
+	state[12] = le32_to_cpuvp(iv +  0);
+	state[13] = le32_to_cpuvp(iv +  4);
+	state[14] = le32_to_cpuvp(iv +  8);
+	state[15] = le32_to_cpuvp(iv + 12);
+}
+
+static int chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
+			   unsigned int keysize)
+{
+	struct chacha20_ctx *ctx = crypto_tfm_ctx(tfm);
+	int i;
+
+	if (keysize != CHACHA20_KEY_SIZE)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->key); i++)
+		ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32));
+
+	return 0;
+}
+
+static int chacha20_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
+
+	chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
+
+	while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % CHACHA20_BLOCK_SIZE);
+	}
+
+	if (walk.nbytes) {
+		chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
+				 walk.nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "chacha20",
+	.cra_driver_name	= "chacha20-generic",
+	.cra_priority		= 100,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_ctxsize		= sizeof(struct chacha20_ctx),
+	.cra_alignmask		= sizeof(u32) - 1,
+	.cra_module		= THIS_MODULE,
+	.cra_u			= {
+		.blkcipher = {
+			.min_keysize	= CHACHA20_KEY_SIZE,
+			.max_keysize	= CHACHA20_KEY_SIZE,
+			.ivsize		= CHACHA20_NONCE_SIZE,
+			.geniv		= "seqiv",
+			.setkey		= chacha20_setkey,
+			.encrypt	= chacha20_crypt,
+			.decrypt	= chacha20_crypt,
+		},
+	},
+};
+
+static int __init chacha20_generic_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+
+static void __exit chacha20_generic_mod_fini(void)
+{
+	crypto_unregister_alg(&alg);
+}
+
+module_init(chacha20_generic_mod_init);
+module_exit(chacha20_generic_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("chacha20 cipher algorithm");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-generic");
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
new file mode 100644
index 000000000000..7b46ed799a64
--- /dev/null
+++ b/crypto/chacha20poly1305.c
@@ -0,0 +1,695 @@
+/*
+ * ChaCha20-Poly1305 AEAD, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+#define POLY1305_BLOCK_SIZE	16
+#define POLY1305_DIGEST_SIZE	16
+#define POLY1305_KEY_SIZE	32
+#define CHACHA20_KEY_SIZE	32
+#define CHACHA20_IV_SIZE	16
+#define CHACHAPOLY_IV_SIZE	12
+
+struct chachapoly_instance_ctx {
+	struct crypto_skcipher_spawn chacha;
+	struct crypto_ahash_spawn poly;
+	unsigned int saltlen;
+};
+
+struct chachapoly_ctx {
+	struct crypto_ablkcipher *chacha;
+	struct crypto_ahash *poly;
+	/* key bytes we use for the ChaCha20 IV */
+	unsigned int saltlen;
+	u8 salt[];
+};
+
+struct poly_req {
+	/* zero byte padding for AD/ciphertext, as needed */
+	u8 pad[POLY1305_BLOCK_SIZE];
+	/* tail data with AD/ciphertext lengths */
+	struct {
+		__le64 assoclen;
+		__le64 cryptlen;
+	} tail;
+	struct scatterlist src[1];
+	struct ahash_request req; /* must be last member */
+};
+
+struct chacha_req {
+	u8 iv[CHACHA20_IV_SIZE];
+	struct scatterlist src[1];
+	struct ablkcipher_request req; /* must be last member */
+};
+
+struct chachapoly_req_ctx {
+	/* the key we generate for Poly1305 using Chacha20 */
+	u8 key[POLY1305_KEY_SIZE];
+	/* calculated Poly1305 tag */
+	u8 tag[POLY1305_DIGEST_SIZE];
+	/* length of data to en/decrypt, without ICV */
+	unsigned int cryptlen;
+	union {
+		struct poly_req poly;
+		struct chacha_req chacha;
+	} u;
+};
+
+static inline void async_done_continue(struct aead_request *req, int err,
+				       int (*cont)(struct aead_request *))
+{
+	if (!err)
+		err = cont(req);
+
+	if (err != -EINPROGRESS && err != -EBUSY)
+		aead_request_complete(req, err);
+}
+
+static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	__le32 leicb = cpu_to_le32(icb);
+
+	memcpy(iv, &leicb, sizeof(leicb));
+	memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen);
+	memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv,
+	       CHACHA20_IV_SIZE - sizeof(leicb) - ctx->saltlen);
+}
+
+static int poly_verify_tag(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	u8 tag[sizeof(rctx->tag)];
+
+	scatterwalk_map_and_copy(tag, req->src, rctx->cryptlen, sizeof(tag), 0);
+	if (crypto_memneq(tag, rctx->tag, sizeof(tag)))
+		return -EBADMSG;
+	return 0;
+}
+
+static int poly_copy_tag(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	scatterwalk_map_and_copy(rctx->tag, req->dst, rctx->cryptlen,
+				 sizeof(rctx->tag), 1);
+	return 0;
+}
+
+static void chacha_decrypt_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_verify_tag);
+}
+
+static int chacha_decrypt(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	chacha_iv(creq->iv, req, 1);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					chacha_decrypt_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+				     rctx->cryptlen, creq->iv);
+	err = crypto_ablkcipher_decrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_verify_tag(req);
+}
+
+static int poly_tail_continue(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	if (rctx->cryptlen == req->cryptlen) /* encrypting */
+		return poly_copy_tag(req);
+
+	return chacha_decrypt(req);
+}
+
+static void poly_tail_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_tail_continue);
+}
+
+static int poly_tail(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	__le64 len;
+	int err;
+
+	sg_init_table(preq->src, 1);
+	len = cpu_to_le64(req->assoclen);
+	memcpy(&preq->tail.assoclen, &len, sizeof(len));
+	len = cpu_to_le64(rctx->cryptlen);
+	memcpy(&preq->tail.cryptlen, &len, sizeof(len));
+	sg_set_buf(preq->src, &preq->tail, sizeof(preq->tail));
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_tail_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src,
+				rctx->tag, sizeof(preq->tail));
+
+	err = crypto_ahash_finup(&preq->req);
+	if (err)
+		return err;
+
+	return poly_tail_continue(req);
+}
+
+static void poly_cipherpad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_tail);
+}
+
+static int poly_cipherpad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	unsigned int padlen, bs = POLY1305_BLOCK_SIZE;
+	int err;
+
+	padlen = (bs - (rctx->cryptlen % bs)) % bs;
+	memset(preq->pad, 0, sizeof(preq->pad));
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, &preq->pad, padlen);
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_cipherpad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_tail(req);
+}
+
+static void poly_cipher_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_cipherpad);
+}
+
+static int poly_cipher(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	struct scatterlist *crypt = req->src;
+	int err;
+
+	if (rctx->cryptlen == req->cryptlen) /* encrypting */
+		crypt = req->dst;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_cipher_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, crypt, NULL, rctx->cryptlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_cipherpad(req);
+}
+
+static void poly_adpad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_cipher);
+}
+
+static int poly_adpad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	unsigned int padlen, bs = POLY1305_BLOCK_SIZE;
+	int err;
+
+	padlen = (bs - (req->assoclen % bs)) % bs;
+	memset(preq->pad, 0, sizeof(preq->pad));
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, preq->pad, padlen);
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_adpad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, padlen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_cipher(req);
+}
+
+static void poly_ad_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_adpad);
+}
+
+static int poly_ad(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_ad_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, req->assoc, NULL, req->assoclen);
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_adpad(req);
+}
+
+static void poly_setkey_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_ad);
+}
+
+static int poly_setkey(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	sg_init_table(preq->src, 1);
+	sg_set_buf(preq->src, rctx->key, sizeof(rctx->key));
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_setkey_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+	ahash_request_set_crypt(&preq->req, preq->src, NULL, sizeof(rctx->key));
+
+	err = crypto_ahash_update(&preq->req);
+	if (err)
+		return err;
+
+	return poly_ad(req);
+}
+
+static void poly_init_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_setkey);
+}
+
+static int poly_init(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct poly_req *preq = &rctx->u.poly;
+	int err;
+
+	ahash_request_set_callback(&preq->req, aead_request_flags(req),
+				   poly_init_done, req);
+	ahash_request_set_tfm(&preq->req, ctx->poly);
+
+	err = crypto_ahash_init(&preq->req);
+	if (err)
+		return err;
+
+	return poly_setkey(req);
+}
+
+static void poly_genkey_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_init);
+}
+
+static int poly_genkey(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	sg_init_table(creq->src, 1);
+	memset(rctx->key, 0, sizeof(rctx->key));
+	sg_set_buf(creq->src, rctx->key, sizeof(rctx->key));
+
+	chacha_iv(creq->iv, req, 0);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					poly_genkey_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, creq->src, creq->src,
+				     POLY1305_KEY_SIZE, creq->iv);
+
+	err = crypto_ablkcipher_decrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_init(req);
+}
+
+static void chacha_encrypt_done(struct crypto_async_request *areq, int err)
+{
+	async_done_continue(areq->data, err, poly_genkey);
+}
+
+static int chacha_encrypt(struct aead_request *req)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+	struct chacha_req *creq = &rctx->u.chacha;
+	int err;
+
+	chacha_iv(creq->iv, req, 1);
+
+	ablkcipher_request_set_callback(&creq->req, aead_request_flags(req),
+					chacha_encrypt_done, req);
+	ablkcipher_request_set_tfm(&creq->req, ctx->chacha);
+	ablkcipher_request_set_crypt(&creq->req, req->src, req->dst,
+				     req->cryptlen, creq->iv);
+	err = crypto_ablkcipher_encrypt(&creq->req);
+	if (err)
+		return err;
+
+	return poly_genkey(req);
+}
+
+static int chachapoly_encrypt(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	rctx->cryptlen = req->cryptlen;
+
+	/* encrypt call chain:
+	 * - chacha_encrypt/done()
+	 * - poly_genkey/done()
+	 * - poly_init/done()
+	 * - poly_setkey/done()
+	 * - poly_ad/done()
+	 * - poly_adpad/done()
+	 * - poly_cipher/done()
+	 * - poly_cipherpad/done()
+	 * - poly_tail/done/continue()
+	 * - poly_copy_tag()
+	 */
+	return chacha_encrypt(req);
+}
+
+static int chachapoly_decrypt(struct aead_request *req)
+{
+	struct chachapoly_req_ctx *rctx = aead_request_ctx(req);
+
+	if (req->cryptlen < POLY1305_DIGEST_SIZE)
+		return -EINVAL;
+	rctx->cryptlen = req->cryptlen - POLY1305_DIGEST_SIZE;
+
+	/* decrypt call chain:
+	 * - poly_genkey/done()
+	 * - poly_init/done()
+	 * - poly_setkey/done()
+	 * - poly_ad/done()
+	 * - poly_adpad/done()
+	 * - poly_cipher/done()
+	 * - poly_cipherpad/done()
+	 * - poly_tail/done/continue()
+	 * - chacha_decrypt/done()
+	 * - poly_verify_tag()
+	 */
+	return poly_genkey(req);
+}
+
+static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key,
+			     unsigned int keylen)
+{
+	struct chachapoly_ctx *ctx = crypto_aead_ctx(aead);
+	int err;
+
+	if (keylen != ctx->saltlen + CHACHA20_KEY_SIZE)
+		return -EINVAL;
+
+	keylen -= ctx->saltlen;
+	memcpy(ctx->salt, key + keylen, ctx->saltlen);
+
+	crypto_ablkcipher_clear_flags(ctx->chacha, CRYPTO_TFM_REQ_MASK);
+	crypto_ablkcipher_set_flags(ctx->chacha, crypto_aead_get_flags(aead) &
+				    CRYPTO_TFM_REQ_MASK);
+
+	err = crypto_ablkcipher_setkey(ctx->chacha, key, keylen);
+	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctx->chacha) &
+			      CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int chachapoly_setauthsize(struct crypto_aead *tfm,
+				  unsigned int authsize)
+{
+	if (authsize != POLY1305_DIGEST_SIZE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int chachapoly_init(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct chachapoly_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_ablkcipher *chacha;
+	struct crypto_ahash *poly;
+	unsigned long align;
+
+	poly = crypto_spawn_ahash(&ictx->poly);
+	if (IS_ERR(poly))
+		return PTR_ERR(poly);
+
+	chacha = crypto_spawn_skcipher(&ictx->chacha);
+	if (IS_ERR(chacha)) {
+		crypto_free_ahash(poly);
+		return PTR_ERR(chacha);
+	}
+
+	ctx->chacha = chacha;
+	ctx->poly = poly;
+	ctx->saltlen = ictx->saltlen;
+
+	align = crypto_tfm_alg_alignmask(tfm);
+	align &= ~(crypto_tfm_ctx_alignment() - 1);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				align + offsetof(struct chachapoly_req_ctx, u) +
+				max(offsetof(struct chacha_req, req) +
+				    sizeof(struct ablkcipher_request) +
+				    crypto_ablkcipher_reqsize(chacha),
+				    offsetof(struct poly_req, req) +
+				    sizeof(struct ahash_request) +
+				    crypto_ahash_reqsize(poly)));
+
+	return 0;
+}
+
+static void chachapoly_exit(struct crypto_tfm *tfm)
+{
+	struct chachapoly_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ahash(ctx->poly);
+	crypto_free_ablkcipher(ctx->chacha);
+}
+
+static struct crypto_instance *chachapoly_alloc(struct rtattr **tb,
+						const char *name,
+						unsigned int ivsize)
+{
+	struct crypto_attr_type *algt;
+	struct crypto_instance *inst;
+	struct crypto_alg *chacha;
+	struct crypto_alg *poly;
+	struct ahash_alg *poly_ahash;
+	struct chachapoly_instance_ctx *ctx;
+	const char *chacha_name, *poly_name;
+	int err;
+
+	if (ivsize > CHACHAPOLY_IV_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return ERR_CAST(algt);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
+		return ERR_PTR(-EINVAL);
+
+	chacha_name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(chacha_name))
+		return ERR_CAST(chacha_name);
+	poly_name = crypto_attr_alg_name(tb[2]);
+	if (IS_ERR(poly_name))
+		return ERR_CAST(poly_name);
+
+	poly = crypto_find_alg(poly_name, &crypto_ahash_type,
+			       CRYPTO_ALG_TYPE_HASH,
+			       CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(poly))
+		return ERR_CAST(poly);
+
+	err = -ENOMEM;
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		goto out_put_poly;
+
+	ctx = crypto_instance_ctx(inst);
+	ctx->saltlen = CHACHAPOLY_IV_SIZE - ivsize;
+	poly_ahash = container_of(poly, struct ahash_alg, halg.base);
+	err = crypto_init_ahash_spawn(&ctx->poly, &poly_ahash->halg, inst);
+	if (err)
+		goto err_free_inst;
+
+	crypto_set_skcipher_spawn(&ctx->chacha, inst);
+	err = crypto_grab_skcipher(&ctx->chacha, chacha_name, 0,
+				   crypto_requires_sync(algt->type,
+							algt->mask));
+	if (err)
+		goto err_drop_poly;
+
+	chacha = crypto_skcipher_spawn_alg(&ctx->chacha);
+
+	err = -EINVAL;
+	/* Need 16-byte IV size, including Initial Block Counter value */
+	if (chacha->cra_ablkcipher.ivsize != CHACHA20_IV_SIZE)
+		goto out_drop_chacha;
+	/* Not a stream cipher? */
+	if (chacha->cra_blocksize != 1)
+		goto out_drop_chacha;
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s,%s)", name, chacha_name,
+		     poly_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_drop_chacha;
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "%s(%s,%s)", name, chacha->cra_driver_name,
+		     poly->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_drop_chacha;
+
+	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
+	inst->alg.cra_flags |= (chacha->cra_flags |
+				poly->cra_flags) & CRYPTO_ALG_ASYNC;
+	inst->alg.cra_priority = (chacha->cra_priority +
+				  poly->cra_priority) / 2;
+	inst->alg.cra_blocksize = 1;
+	inst->alg.cra_alignmask = chacha->cra_alignmask | poly->cra_alignmask;
+	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.cra_aead.ivsize = ivsize;
+	inst->alg.cra_aead.maxauthsize = POLY1305_DIGEST_SIZE;
+	inst->alg.cra_ctxsize = sizeof(struct chachapoly_ctx) + ctx->saltlen;
+	inst->alg.cra_init = chachapoly_init;
+	inst->alg.cra_exit = chachapoly_exit;
+	inst->alg.cra_aead.encrypt = chachapoly_encrypt;
+	inst->alg.cra_aead.decrypt = chachapoly_decrypt;
+	inst->alg.cra_aead.setkey = chachapoly_setkey;
+	inst->alg.cra_aead.setauthsize = chachapoly_setauthsize;
+	inst->alg.cra_aead.geniv = "seqiv";
+
+out:
+	crypto_mod_put(poly);
+	return inst;
+
+out_drop_chacha:
+	crypto_drop_skcipher(&ctx->chacha);
+err_drop_poly:
+	crypto_drop_ahash(&ctx->poly);
+err_free_inst:
+	kfree(inst);
+out_put_poly:
+	inst = ERR_PTR(err);
+	goto out;
+}
+
+static struct crypto_instance *rfc7539_alloc(struct rtattr **tb)
+{
+	return chachapoly_alloc(tb, "rfc7539", 12);
+}
+
+static struct crypto_instance *rfc7539esp_alloc(struct rtattr **tb)
+{
+	return chachapoly_alloc(tb, "rfc7539esp", 8);
+}
+
+static void chachapoly_free(struct crypto_instance *inst)
+{
+	struct chachapoly_instance_ctx *ctx = crypto_instance_ctx(inst);
+
+	crypto_drop_skcipher(&ctx->chacha);
+	crypto_drop_ahash(&ctx->poly);
+	kfree(inst);
+}
+
+static struct crypto_template rfc7539_tmpl = {
+	.name = "rfc7539",
+	.alloc = rfc7539_alloc,
+	.free = chachapoly_free,
+	.module = THIS_MODULE,
+};
+
+static struct crypto_template rfc7539esp_tmpl = {
+	.name = "rfc7539esp",
+	.alloc = rfc7539esp_alloc,
+	.free = chachapoly_free,
+	.module = THIS_MODULE,
+};
+
+static int __init chacha20poly1305_module_init(void)
+{
+	int err;
+
+	err = crypto_register_template(&rfc7539_tmpl);
+	if (err)
+		return err;
+
+	err = crypto_register_template(&rfc7539esp_tmpl);
+	if (err)
+		crypto_unregister_template(&rfc7539_tmpl);
+
+	return err;
+}
+
+static void __exit chacha20poly1305_module_exit(void)
+{
+	crypto_unregister_template(&rfc7539esp_tmpl);
+	crypto_unregister_template(&rfc7539_tmpl);
+}
+
+module_init(chacha20poly1305_module_init);
+module_exit(chacha20poly1305_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("ChaCha20-Poly1305 AEAD");
+MODULE_ALIAS_CRYPTO("chacha20poly1305");
+MODULE_ALIAS_CRYPTO("rfc7539");
+MODULE_ALIAS_CRYPTO("rfc7539esp");
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
index 63c17d5992f7..b4340018c8d4 100644
--- a/crypto/chainiv.c
+++ b/crypto/chainiv.c
@@ -80,44 +80,37 @@ unlock:
 	return err;
 }
 
-static int chainiv_givencrypt_first(struct skcipher_givcrypt_request *req)
+static int chainiv_init_common(struct crypto_tfm *tfm, char iv[])
 {
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	int err = 0;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt !=
-	    chainiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->iv,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	if (err)
-		return err;
-
-	return chainiv_givencrypt(req);
-}
-
-static int chainiv_init_common(struct crypto_tfm *tfm)
-{
 	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	if (iv) {
+		err = crypto_rng_get_bytes(crypto_default_rng, iv,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
 static int chainiv_init(struct crypto_tfm *tfm)
 {
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+	char *iv;
 
 	spin_lock_init(&ctx->lock);
 
-	return chainiv_init_common(tfm);
+	iv = NULL;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = chainiv_givencrypt;
+		iv = ctx->iv;
+	}
+
+	return chainiv_init_common(tfm, iv);
 }
 
 static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
@@ -205,33 +198,6 @@ postpone:
 	return async_chainiv_postpone_request(req);
 }
 
-static int async_chainiv_givencrypt_first(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct async_chainiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
-
-	if (test_and_set_bit(CHAINIV_STATE_INUSE, &ctx->state))
-		goto out;
-
-	if (crypto_ablkcipher_crt(geniv)->givencrypt !=
-	    async_chainiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = async_chainiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->iv,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
-
-	if (err)
-		return err;
-
-out:
-	return async_chainiv_givencrypt(req);
-}
-
 static void async_chainiv_do_postponed(struct work_struct *work)
 {
 	struct async_chainiv_ctx *ctx = container_of(work,
@@ -263,14 +229,23 @@ static void async_chainiv_do_postponed(struct work_struct *work)
 
 static int async_chainiv_init(struct crypto_tfm *tfm)
 {
+	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct async_chainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+	char *iv;
 
 	spin_lock_init(&ctx->lock);
 
 	crypto_init_queue(&ctx->queue, 100);
 	INIT_WORK(&ctx->postponed, async_chainiv_do_postponed);
 
-	return chainiv_init_common(tfm);
+	iv = NULL;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt =
+			async_chainiv_givencrypt;
+		iv = ctx->iv;
+	}
+
+	return chainiv_init_common(tfm, iv);
 }
 
 static void async_chainiv_exit(struct crypto_tfm *tfm)
@@ -288,21 +263,14 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
 	struct crypto_instance *inst;
-	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
 		return ERR_CAST(algt);
 
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
-
 	inst = skcipher_geniv_alloc(&chainiv_tmpl, tb, 0, 0);
 	if (IS_ERR(inst))
-		goto put_rng;
-
-	inst->alg.cra_ablkcipher.givencrypt = chainiv_givencrypt_first;
+		goto out;
 
 	inst->alg.cra_init = chainiv_init;
 	inst->alg.cra_exit = skcipher_geniv_exit;
@@ -312,9 +280,6 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 	if (!crypto_requires_sync(algt->type, algt->mask)) {
 		inst->alg.cra_flags |= CRYPTO_ALG_ASYNC;
 
-		inst->alg.cra_ablkcipher.givencrypt =
-			async_chainiv_givencrypt_first;
-
 		inst->alg.cra_init = async_chainiv_init;
 		inst->alg.cra_exit = async_chainiv_exit;
 
@@ -325,22 +290,12 @@ static struct crypto_instance *chainiv_alloc(struct rtattr **tb)
 
 out:
 	return inst;
-
-put_rng:
-	crypto_put_default_rng();
-	goto out;
-}
-
-static void chainiv_free(struct crypto_instance *inst)
-{
-	skcipher_geniv_free(inst);
-	crypto_put_default_rng();
 }
 
 static struct crypto_template chainiv_tmpl = {
 	.name = "chainiv",
 	.alloc = chainiv_alloc,
-	.free = chainiv_free,
+	.free = skcipher_geniv_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index b0602ba03111..22ba81f76764 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -295,6 +295,23 @@ static void cryptd_blkcipher_exit_tfm(struct crypto_tfm *tfm)
 	crypto_free_blkcipher(ctx->child);
 }
 
+static int cryptd_init_instance(struct crypto_instance *inst,
+				struct crypto_alg *alg)
+{
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "cryptd(%s)",
+		     alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		return -ENAMETOOLONG;
+
+	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.cra_priority = alg->cra_priority + 50;
+	inst->alg.cra_blocksize = alg->cra_blocksize;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+
+	return 0;
+}
+
 static void *cryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
 				   unsigned int tail)
 {
@@ -308,17 +325,10 @@ static void *cryptd_alloc_instance(struct crypto_alg *alg, unsigned int head,
 
 	inst = (void *)(p + head);
 
-	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "cryptd(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+	err = cryptd_init_instance(inst, alg);
+	if (err)
 		goto out_free_inst;
 
-	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
-
-	inst->alg.cra_priority = alg->cra_priority + 50;
-	inst->alg.cra_blocksize = alg->cra_blocksize;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-
 out:
 	return p;
 
@@ -654,6 +664,24 @@ out_put_alg:
 	return err;
 }
 
+static int cryptd_aead_setkey(struct crypto_aead *parent,
+			      const u8 *key, unsigned int keylen)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent);
+	struct crypto_aead *child = ctx->child;
+
+	return crypto_aead_setkey(child, key, keylen);
+}
+
+static int cryptd_aead_setauthsize(struct crypto_aead *parent,
+				   unsigned int authsize)
+{
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(parent);
+	struct crypto_aead *child = ctx->child;
+
+	return crypto_aead_setauthsize(child, authsize);
+}
+
 static void cryptd_aead_crypt(struct aead_request *req,
 			struct crypto_aead *child,
 			int err,
@@ -715,27 +743,26 @@ static int cryptd_aead_decrypt_enqueue(struct aead_request *req)
 	return cryptd_aead_enqueue(req, cryptd_aead_decrypt );
 }
 
-static int cryptd_aead_init_tfm(struct crypto_tfm *tfm)
+static int cryptd_aead_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct aead_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct aead_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_aead_spawn *spawn = &ictx->aead_spawn;
-	struct cryptd_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *cipher;
 
 	cipher = crypto_spawn_aead(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	crypto_aead_set_flags(cipher, CRYPTO_TFM_REQ_MAY_SLEEP);
 	ctx->child = cipher;
-	tfm->crt_aead.reqsize = sizeof(struct cryptd_aead_request_ctx);
+	crypto_aead_set_reqsize(tfm, sizeof(struct cryptd_aead_request_ctx));
 	return 0;
 }
 
-static void cryptd_aead_exit_tfm(struct crypto_tfm *tfm)
+static void cryptd_aead_exit_tfm(struct crypto_aead *tfm)
 {
-	struct cryptd_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	crypto_free_aead(ctx->child);
 }
 
@@ -744,57 +771,57 @@ static int cryptd_create_aead(struct crypto_template *tmpl,
 			      struct cryptd_queue *queue)
 {
 	struct aead_instance_ctx *ctx;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
-	u32 type = CRYPTO_ALG_TYPE_AEAD;
-	u32 mask = CRYPTO_ALG_TYPE_MASK;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	const char *name;
+	u32 type = 0;
+	u32 mask = 0;
 	int err;
 
 	cryptd_check_internal(tb, &type, &mask);
 
-	alg = crypto_get_attr_alg(tb, type, mask);
-        if (IS_ERR(alg))
-		return PTR_ERR(alg);
+	name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 
-	inst = cryptd_alloc_instance(alg, 0, sizeof(*ctx));
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 	ctx->queue = queue;
 
-	err = crypto_init_spawn(&ctx->aead_spawn.base, alg, inst,
-			CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC);
+	crypto_set_aead_spawn(&ctx->aead_spawn, aead_crypto_instance(inst));
+	err = crypto_grab_aead(&ctx->aead_spawn, name, type, mask);
 	if (err)
 		goto out_free_inst;
 
-	type = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.cra_flags = type;
-	inst->alg.cra_type = alg->cra_type;
-	inst->alg.cra_ctxsize = sizeof(struct cryptd_aead_ctx);
-	inst->alg.cra_init = cryptd_aead_init_tfm;
-	inst->alg.cra_exit = cryptd_aead_exit_tfm;
-	inst->alg.cra_aead.setkey      = alg->cra_aead.setkey;
-	inst->alg.cra_aead.setauthsize = alg->cra_aead.setauthsize;
-	inst->alg.cra_aead.geniv       = alg->cra_aead.geniv;
-	inst->alg.cra_aead.ivsize      = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
-	inst->alg.cra_aead.encrypt     = cryptd_aead_encrypt_enqueue;
-	inst->alg.cra_aead.decrypt     = cryptd_aead_decrypt_enqueue;
-	inst->alg.cra_aead.givencrypt  = alg->cra_aead.givencrypt;
-	inst->alg.cra_aead.givdecrypt  = alg->cra_aead.givdecrypt;
+	alg = crypto_spawn_aead_alg(&ctx->aead_spawn);
+	err = cryptd_init_instance(aead_crypto_instance(inst), &alg->base);
+	if (err)
+		goto out_drop_aead;
 
-	err = crypto_register_instance(tmpl, inst);
+	inst->alg.base.cra_flags = CRYPTO_ALG_ASYNC |
+				   (alg->base.cra_flags & CRYPTO_ALG_INTERNAL);
+	inst->alg.base.cra_ctxsize = sizeof(struct cryptd_aead_ctx);
+
+	inst->alg.ivsize = crypto_aead_alg_ivsize(alg);
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
+
+	inst->alg.init = cryptd_aead_init_tfm;
+	inst->alg.exit = cryptd_aead_exit_tfm;
+	inst->alg.setkey = cryptd_aead_setkey;
+	inst->alg.setauthsize = cryptd_aead_setauthsize;
+	inst->alg.encrypt = cryptd_aead_encrypt_enqueue;
+	inst->alg.decrypt = cryptd_aead_decrypt_enqueue;
+
+	err = aead_register_instance(tmpl, inst);
 	if (err) {
-		crypto_drop_spawn(&ctx->aead_spawn.base);
+out_drop_aead:
+		crypto_drop_aead(&ctx->aead_spawn);
 out_free_inst:
 		kfree(inst);
 	}
-out_put_alg:
-	crypto_mod_put(alg);
 	return err;
 }
 
@@ -832,8 +859,8 @@ static void cryptd_free(struct crypto_instance *inst)
 		kfree(ahash_instance(inst));
 		return;
 	case CRYPTO_ALG_TYPE_AEAD:
-		crypto_drop_spawn(&aead_ctx->aead_spawn.base);
-		kfree(inst);
+		crypto_drop_aead(&aead_ctx->aead_spawn);
+		kfree(aead_instance(inst));
 		return;
 	default:
 		crypto_drop_spawn(&ctx->spawn);
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index a20319132e33..941c9a434d50 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -25,6 +25,10 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 
+static DEFINE_MUTEX(crypto_default_null_skcipher_lock);
+static struct crypto_blkcipher *crypto_default_null_skcipher;
+static int crypto_default_null_skcipher_refcnt;
+
 static int null_compress(struct crypto_tfm *tfm, const u8 *src,
 			 unsigned int slen, u8 *dst, unsigned int *dlen)
 {
@@ -149,6 +153,41 @@ MODULE_ALIAS_CRYPTO("compress_null");
 MODULE_ALIAS_CRYPTO("digest_null");
 MODULE_ALIAS_CRYPTO("cipher_null");
 
+struct crypto_blkcipher *crypto_get_default_null_skcipher(void)
+{
+	struct crypto_blkcipher *tfm;
+
+	mutex_lock(&crypto_default_null_skcipher_lock);
+	tfm = crypto_default_null_skcipher;
+
+	if (!tfm) {
+		tfm = crypto_alloc_blkcipher("ecb(cipher_null)", 0, 0);
+		if (IS_ERR(tfm))
+			goto unlock;
+
+		crypto_default_null_skcipher = tfm;
+	}
+
+	crypto_default_null_skcipher_refcnt++;
+
+unlock:
+	mutex_unlock(&crypto_default_null_skcipher_lock);
+
+	return tfm;
+}
+EXPORT_SYMBOL_GPL(crypto_get_default_null_skcipher);
+
+void crypto_put_default_null_skcipher(void)
+{
+	mutex_lock(&crypto_default_null_skcipher_lock);
+	if (!--crypto_default_null_skcipher_refcnt) {
+		crypto_free_blkcipher(crypto_default_null_skcipher);
+		crypto_default_null_skcipher = NULL;
+	}
+	mutex_unlock(&crypto_default_null_skcipher_lock);
+}
+EXPORT_SYMBOL_GPL(crypto_put_default_null_skcipher);
+
 static int __init crypto_null_mod_init(void)
 {
 	int ret = 0;
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 41dfe762b7fb..08ea2867fc8a 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -27,6 +27,8 @@
 #include <net/net_namespace.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/internal/rng.h>
+#include <crypto/akcipher.h>
 
 #include "internal.h"
 
@@ -110,6 +112,21 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg)
+{
+	struct crypto_report_akcipher rakcipher;
+
+	strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type));
+
+	if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER,
+		    sizeof(struct crypto_report_akcipher), &rakcipher))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int crypto_report_one(struct crypto_alg *alg,
 			     struct crypto_user_alg *ualg, struct sk_buff *skb)
 {
@@ -154,6 +171,12 @@ static int crypto_report_one(struct crypto_alg *alg,
 			goto nla_put_failure;
 
 		break;
+
+	case CRYPTO_ALG_TYPE_AKCIPHER:
+		if (crypto_report_akcipher(skb, alg))
+			goto nla_put_failure;
+
+		break;
 	}
 
 out:
@@ -450,13 +473,21 @@ static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 }
 
+static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct nlattr **attrs)
+{
+	if (!netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+	return crypto_del_default_rng();
+}
+
 #define MSGSIZE(type) sizeof(struct type)
 
 static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = {
 	[CRYPTO_MSG_NEWALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_DELALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
 	[CRYPTO_MSG_UPDATEALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
-	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg),
+	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = 0,
 };
 
 static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = {
@@ -476,6 +507,7 @@ static const struct crypto_link {
 	[CRYPTO_MSG_GETALG	- CRYPTO_MSG_BASE] = { .doit = crypto_report,
 						       .dump = crypto_dump_report,
 						       .done = crypto_dump_report_done},
+	[CRYPTO_MSG_DELRNG	- CRYPTO_MSG_BASE] = { .doit = crypto_del_rng },
 };
 
 static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
diff --git a/crypto/drbg.c b/crypto/drbg.c
index b69409cb7e6a..a7c23146b87f 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -98,6 +98,7 @@
  */
 
 #include <crypto/drbg.h>
+#include <linux/kernel.h>
 
 /***************************************************************
  * Backend cipher definitions available to DRBG
@@ -190,6 +191,8 @@ static const struct drbg_core drbg_cores[] = {
 #endif /* CONFIG_CRYPTO_DRBG_HMAC */
 };
 
+static int drbg_uninstantiate(struct drbg_state *drbg);
+
 /******************************************************************
  * Generic helper functions
  ******************************************************************/
@@ -235,7 +238,7 @@ static bool drbg_fips_continuous_test(struct drbg_state *drbg,
 #ifdef CONFIG_CRYPTO_FIPS
 	int ret = 0;
 	/* skip test if we test the overall system */
-	if (drbg->test_data)
+	if (list_empty(&drbg->test_data.list))
 		return true;
 	/* only perform test in FIPS mode */
 	if (0 == fips_enabled)
@@ -487,7 +490,7 @@ static int drbg_ctr_df(struct drbg_state *drbg,
 
 out:
 	memset(iv, 0, drbg_blocklen(drbg));
-	memset(temp, 0, drbg_statelen(drbg));
+	memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg));
 	memset(pad, 0, drbg_blocklen(drbg));
 	return ret;
 }
@@ -1041,6 +1044,58 @@ static struct drbg_state_ops drbg_hash_ops = {
  * Functions common for DRBG implementations
  ******************************************************************/
 
+static inline int __drbg_seed(struct drbg_state *drbg, struct list_head *seed,
+			      int reseed)
+{
+	int ret = drbg->d_ops->update(drbg, seed, reseed);
+
+	if (ret)
+		return ret;
+
+	drbg->seeded = true;
+	/* 10.1.1.2 / 10.1.1.3 step 5 */
+	drbg->reseed_ctr = 1;
+
+	return ret;
+}
+
+static void drbg_async_seed(struct work_struct *work)
+{
+	struct drbg_string data;
+	LIST_HEAD(seedlist);
+	struct drbg_state *drbg = container_of(work, struct drbg_state,
+					       seed_work);
+	unsigned int entropylen = drbg_sec_strength(drbg->core->flags);
+	unsigned char entropy[32];
+
+	BUG_ON(!entropylen);
+	BUG_ON(entropylen > sizeof(entropy));
+	get_random_bytes(entropy, entropylen);
+
+	drbg_string_fill(&data, entropy, entropylen);
+	list_add_tail(&data.list, &seedlist);
+
+	mutex_lock(&drbg->drbg_mutex);
+
+	/* If nonblocking pool is initialized, deactivate Jitter RNG */
+	crypto_free_rng(drbg->jent);
+	drbg->jent = NULL;
+
+	/* Set seeded to false so that if __drbg_seed fails the
+	 * next generate call will trigger a reseed.
+	 */
+	drbg->seeded = false;
+
+	__drbg_seed(drbg, &seedlist, true);
+
+	if (drbg->seeded)
+		drbg->reseed_threshold = drbg_max_requests(drbg);
+
+	mutex_unlock(&drbg->drbg_mutex);
+
+	memzero_explicit(entropy, entropylen);
+}
+
 /*
  * Seeding or reseeding of the DRBG
  *
@@ -1055,9 +1110,9 @@ static struct drbg_state_ops drbg_hash_ops = {
 static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		     bool reseed)
 {
-	int ret = 0;
-	unsigned char *entropy = NULL;
-	size_t entropylen = 0;
+	int ret;
+	unsigned char entropy[((32 + 16) * 2)];
+	unsigned int entropylen = drbg_sec_strength(drbg->core->flags);
 	struct drbg_string data1;
 	LIST_HEAD(seedlist);
 
@@ -1068,31 +1123,45 @@ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		return -EINVAL;
 	}
 
-	if (drbg->test_data && drbg->test_data->testentropy) {
-		drbg_string_fill(&data1, drbg->test_data->testentropy->buf,
-				 drbg->test_data->testentropy->len);
+	if (list_empty(&drbg->test_data.list)) {
+		drbg_string_fill(&data1, drbg->test_data.buf,
+				 drbg->test_data.len);
 		pr_devel("DRBG: using test entropy\n");
 	} else {
 		/*
 		 * Gather entropy equal to the security strength of the DRBG.
 		 * With a derivation function, a nonce is required in addition
 		 * to the entropy. A nonce must be at least 1/2 of the security
-		 * strength of the DRBG in size. Thus, entropy * nonce is 3/2
+		 * strength of the DRBG in size. Thus, entropy + nonce is 3/2
 		 * of the strength. The consideration of a nonce is only
 		 * applicable during initial seeding.
 		 */
-		entropylen = drbg_sec_strength(drbg->core->flags);
-		if (!entropylen)
-			return -EFAULT;
+		BUG_ON(!entropylen);
 		if (!reseed)
 			entropylen = ((entropylen + 1) / 2) * 3;
-		pr_devel("DRBG: (re)seeding with %zu bytes of entropy\n",
-			 entropylen);
-		entropy = kzalloc(entropylen, GFP_KERNEL);
-		if (!entropy)
-			return -ENOMEM;
+		BUG_ON((entropylen * 2) > sizeof(entropy));
+
+		/* Get seed from in-kernel /dev/urandom */
 		get_random_bytes(entropy, entropylen);
-		drbg_string_fill(&data1, entropy, entropylen);
+
+		if (!drbg->jent) {
+			drbg_string_fill(&data1, entropy, entropylen);
+			pr_devel("DRBG: (re)seeding with %u bytes of entropy\n",
+				 entropylen);
+		} else {
+			/* Get seed from Jitter RNG */
+			ret = crypto_rng_get_bytes(drbg->jent,
+						   entropy + entropylen,
+						   entropylen);
+			if (ret) {
+				pr_devel("DRBG: jent failed with %d\n", ret);
+				return ret;
+			}
+
+			drbg_string_fill(&data1, entropy, entropylen * 2);
+			pr_devel("DRBG: (re)seeding with %u bytes of entropy\n",
+				 entropylen * 2);
+		}
 	}
 	list_add_tail(&data1.list, &seedlist);
 
@@ -1111,16 +1180,10 @@ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
 		memset(drbg->C, 0, drbg_statelen(drbg));
 	}
 
-	ret = drbg->d_ops->update(drbg, &seedlist, reseed);
-	if (ret)
-		goto out;
+	ret = __drbg_seed(drbg, &seedlist, reseed);
 
-	drbg->seeded = true;
-	/* 10.1.1.2 / 10.1.1.3 step 5 */
-	drbg->reseed_ctr = 1;
+	memzero_explicit(entropy, entropylen * 2);
 
-out:
-	kzfree(entropy);
 	return ret;
 }
 
@@ -1136,6 +1199,8 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg)
 	kzfree(drbg->scratchpad);
 	drbg->scratchpad = NULL;
 	drbg->reseed_ctr = 0;
+	drbg->d_ops = NULL;
+	drbg->core = NULL;
 #ifdef CONFIG_CRYPTO_FIPS
 	kzfree(drbg->prev);
 	drbg->prev = NULL;
@@ -1152,6 +1217,27 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 	int ret = -ENOMEM;
 	unsigned int sb_size = 0;
 
+	switch (drbg->core->flags & DRBG_TYPE_MASK) {
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+	case DRBG_HMAC:
+		drbg->d_ops = &drbg_hmac_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HMAC */
+#ifdef CONFIG_CRYPTO_DRBG_HASH
+	case DRBG_HASH:
+		drbg->d_ops = &drbg_hash_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HASH */
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+	case DRBG_CTR:
+		drbg->d_ops = &drbg_ctr_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+	default:
+		ret = -EOPNOTSUPP;
+		goto err;
+	}
+
 	drbg->V = kmalloc(drbg_statelen(drbg), GFP_KERNEL);
 	if (!drbg->V)
 		goto err;
@@ -1181,87 +1267,14 @@ static inline int drbg_alloc_state(struct drbg_state *drbg)
 		if (!drbg->scratchpad)
 			goto err;
 	}
-	spin_lock_init(&drbg->drbg_lock);
-	return 0;
-
-err:
-	drbg_dealloc_state(drbg);
-	return ret;
-}
-
-/*
- * Strategy to avoid holding long term locks: generate a shadow copy of DRBG
- * and perform all operations on this shadow copy. After finishing, restore
- * the updated state of the shadow copy into original drbg state. This way,
- * only the read and write operations of the original drbg state must be
- * locked
- */
-static inline void drbg_copy_drbg(struct drbg_state *src,
-				  struct drbg_state *dst)
-{
-	if (!src || !dst)
-		return;
-	memcpy(dst->V, src->V, drbg_statelen(src));
-	memcpy(dst->C, src->C, drbg_statelen(src));
-	dst->reseed_ctr = src->reseed_ctr;
-	dst->seeded = src->seeded;
-	dst->pr = src->pr;
-#ifdef CONFIG_CRYPTO_FIPS
-	dst->fips_primed = src->fips_primed;
-	memcpy(dst->prev, src->prev, drbg_blocklen(src));
-#endif
-	/*
-	 * Not copied:
-	 * scratchpad is initialized drbg_alloc_state;
-	 * priv_data is initialized with call to crypto_init;
-	 * d_ops and core are set outside, as these parameters are const;
-	 * test_data is set outside to prevent it being copied back.
-	 */
-}
-
-static int drbg_make_shadow(struct drbg_state *drbg, struct drbg_state **shadow)
-{
-	int ret = -ENOMEM;
-	struct drbg_state *tmp = NULL;
-
-	tmp = kzalloc(sizeof(struct drbg_state), GFP_KERNEL);
-	if (!tmp)
-		return -ENOMEM;
-
-	/* read-only data as they are defined as const, no lock needed */
-	tmp->core = drbg->core;
-	tmp->d_ops = drbg->d_ops;
 
-	ret = drbg_alloc_state(tmp);
-	if (ret)
-		goto err;
-
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg_copy_drbg(drbg, tmp);
-	/* only make a link to the test buffer, as we only read that data */
-	tmp->test_data = drbg->test_data;
-	spin_unlock_bh(&drbg->drbg_lock);
-	*shadow = tmp;
 	return 0;
 
 err:
-	kzfree(tmp);
+	drbg_dealloc_state(drbg);
 	return ret;
 }
 
-static void drbg_restore_shadow(struct drbg_state *drbg,
-				struct drbg_state **shadow)
-{
-	struct drbg_state *tmp = *shadow;
-
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg_copy_drbg(tmp, drbg);
-	spin_unlock_bh(&drbg->drbg_lock);
-	drbg_dealloc_state(tmp);
-	kzfree(tmp);
-	*shadow = NULL;
-}
-
 /*************************************************************************
  * DRBG interface functions
  *************************************************************************/
@@ -1287,14 +1300,12 @@ static int drbg_generate(struct drbg_state *drbg,
 			 struct drbg_string *addtl)
 {
 	int len = 0;
-	struct drbg_state *shadow = NULL;
 	LIST_HEAD(addtllist);
-	struct drbg_string timestamp;
-	union {
-		cycles_t cycles;
-		unsigned char char_cycles[sizeof(cycles_t)];
-	} now;
 
+	if (!drbg->core) {
+		pr_devel("DRBG: not yet seeded\n");
+		return -EINVAL;
+	}
 	if (0 == buflen || !buf) {
 		pr_devel("DRBG: no output buffer provided\n");
 		return -EINVAL;
@@ -1304,15 +1315,9 @@ static int drbg_generate(struct drbg_state *drbg,
 		return -EINVAL;
 	}
 
-	len = drbg_make_shadow(drbg, &shadow);
-	if (len) {
-		pr_devel("DRBG: shadow copy cannot be generated\n");
-		return len;
-	}
-
 	/* 9.3.1 step 2 */
 	len = -EINVAL;
-	if (buflen > (drbg_max_request_bytes(shadow))) {
+	if (buflen > (drbg_max_request_bytes(drbg))) {
 		pr_devel("DRBG: requested random numbers too large %u\n",
 			 buflen);
 		goto err;
@@ -1321,7 +1326,7 @@ static int drbg_generate(struct drbg_state *drbg,
 	/* 9.3.1 step 3 is implicit with the chosen DRBG */
 
 	/* 9.3.1 step 4 */
-	if (addtl && addtl->len > (drbg_max_addtl(shadow))) {
+	if (addtl && addtl->len > (drbg_max_addtl(drbg))) {
 		pr_devel("DRBG: additional information string too long %zu\n",
 			 addtl->len);
 		goto err;
@@ -1332,46 +1337,29 @@ static int drbg_generate(struct drbg_state *drbg,
 	 * 9.3.1 step 6 and 9 supplemented by 9.3.2 step c is implemented
 	 * here. The spec is a bit convoluted here, we make it simpler.
 	 */
-	if ((drbg_max_requests(shadow)) < shadow->reseed_ctr)
-		shadow->seeded = false;
+	if (drbg->reseed_threshold < drbg->reseed_ctr)
+		drbg->seeded = false;
 
-	/* allocate cipher handle */
-	len = shadow->d_ops->crypto_init(shadow);
-	if (len)
-		goto err;
-
-	if (shadow->pr || !shadow->seeded) {
+	if (drbg->pr || !drbg->seeded) {
 		pr_devel("DRBG: reseeding before generation (prediction "
 			 "resistance: %s, state %s)\n",
 			 drbg->pr ? "true" : "false",
 			 drbg->seeded ? "seeded" : "unseeded");
 		/* 9.3.1 steps 7.1 through 7.3 */
-		len = drbg_seed(shadow, addtl, true);
+		len = drbg_seed(drbg, addtl, true);
 		if (len)
 			goto err;
 		/* 9.3.1 step 7.4 */
 		addtl = NULL;
 	}
 
-	/*
-	 * Mix the time stamp into the DRBG state if the DRBG is not in
-	 * test mode. If there are two callers invoking the DRBG at the same
-	 * time, i.e. before the first caller merges its shadow state back,
-	 * both callers would obtain the same random number stream without
-	 * changing the state here.
-	 */
-	if (!drbg->test_data) {
-		now.cycles = random_get_entropy();
-		drbg_string_fill(&timestamp, now.char_cycles, sizeof(cycles_t));
-		list_add_tail(&timestamp.list, &addtllist);
-	}
 	if (addtl && 0 < addtl->len)
 		list_add_tail(&addtl->list, &addtllist);
 	/* 9.3.1 step 8 and 10 */
-	len = shadow->d_ops->generate(shadow, buf, buflen, &addtllist);
+	len = drbg->d_ops->generate(drbg, buf, buflen, &addtllist);
 
 	/* 10.1.1.4 step 6, 10.1.2.5 step 7, 10.2.1.5.2 step 7 */
-	shadow->reseed_ctr++;
+	drbg->reseed_ctr++;
 	if (0 >= len)
 		goto err;
 
@@ -1391,7 +1379,7 @@ static int drbg_generate(struct drbg_state *drbg,
 	 * case somebody has a need to implement the test of 11.3.3.
 	 */
 #if 0
-	if (shadow->reseed_ctr && !(shadow->reseed_ctr % 4096)) {
+	if (drbg->reseed_ctr && !(drbg->reseed_ctr % 4096)) {
 		int err = 0;
 		pr_devel("DRBG: start to perform self test\n");
 		if (drbg->core->flags & DRBG_HMAC)
@@ -1410,8 +1398,6 @@ static int drbg_generate(struct drbg_state *drbg,
 			 * are returned when reusing this DRBG cipher handle
 			 */
 			drbg_uninstantiate(drbg);
-			drbg_dealloc_state(shadow);
-			kzfree(shadow);
 			return 0;
 		} else {
 			pr_devel("DRBG: self test successful\n");
@@ -1425,8 +1411,6 @@ static int drbg_generate(struct drbg_state *drbg,
 	 */
 	len = 0;
 err:
-	shadow->d_ops->crypto_fini(shadow);
-	drbg_restore_shadow(drbg, &shadow);
 	return len;
 }
 
@@ -1442,19 +1426,68 @@ static int drbg_generate_long(struct drbg_state *drbg,
 			      unsigned char *buf, unsigned int buflen,
 			      struct drbg_string *addtl)
 {
-	int len = 0;
+	unsigned int len = 0;
 	unsigned int slice = 0;
 	do {
-		int tmplen = 0;
+		int err = 0;
 		unsigned int chunk = 0;
 		slice = ((buflen - len) / drbg_max_request_bytes(drbg));
 		chunk = slice ? drbg_max_request_bytes(drbg) : (buflen - len);
-		tmplen = drbg_generate(drbg, buf + len, chunk, addtl);
-		if (0 >= tmplen)
-			return tmplen;
-		len += tmplen;
+		mutex_lock(&drbg->drbg_mutex);
+		err = drbg_generate(drbg, buf + len, chunk, addtl);
+		mutex_unlock(&drbg->drbg_mutex);
+		if (0 > err)
+			return err;
+		len += chunk;
 	} while (slice > 0 && (len < buflen));
-	return len;
+	return 0;
+}
+
+static void drbg_schedule_async_seed(struct random_ready_callback *rdy)
+{
+	struct drbg_state *drbg = container_of(rdy, struct drbg_state,
+					       random_ready);
+
+	schedule_work(&drbg->seed_work);
+}
+
+static int drbg_prepare_hrng(struct drbg_state *drbg)
+{
+	int err;
+
+	/* We do not need an HRNG in test mode. */
+	if (list_empty(&drbg->test_data.list))
+		return 0;
+
+	INIT_WORK(&drbg->seed_work, drbg_async_seed);
+
+	drbg->random_ready.owner = THIS_MODULE;
+	drbg->random_ready.func = drbg_schedule_async_seed;
+
+	err = add_random_ready_callback(&drbg->random_ready);
+
+	switch (err) {
+	case 0:
+		break;
+
+	case -EALREADY:
+		err = 0;
+		/* fall through */
+
+	default:
+		drbg->random_ready.func = NULL;
+		return err;
+	}
+
+	drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0);
+
+	/*
+	 * Require frequent reseeds until the seed source is fully
+	 * initialized.
+	 */
+	drbg->reseed_threshold = 50;
+
+	return err;
 }
 
 /*
@@ -1477,32 +1510,12 @@ static int drbg_generate_long(struct drbg_state *drbg,
 static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 			    int coreref, bool pr)
 {
-	int ret = -ENOMEM;
+	int ret;
+	bool reseed = true;
 
 	pr_devel("DRBG: Initializing DRBG core %d with prediction resistance "
 		 "%s\n", coreref, pr ? "enabled" : "disabled");
-	drbg->core = &drbg_cores[coreref];
-	drbg->pr = pr;
-	drbg->seeded = false;
-	switch (drbg->core->flags & DRBG_TYPE_MASK) {
-#ifdef CONFIG_CRYPTO_DRBG_HMAC
-	case DRBG_HMAC:
-		drbg->d_ops = &drbg_hmac_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_HMAC */
-#ifdef CONFIG_CRYPTO_DRBG_HASH
-	case DRBG_HASH:
-		drbg->d_ops = &drbg_hash_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_HASH */
-#ifdef CONFIG_CRYPTO_DRBG_CTR
-	case DRBG_CTR:
-		drbg->d_ops = &drbg_ctr_ops;
-		break;
-#endif /* CONFIG_CRYPTO_DRBG_CTR */
-	default:
-		return -EOPNOTSUPP;
-	}
+	mutex_lock(&drbg->drbg_mutex);
 
 	/* 9.1 step 1 is implicit with the selected DRBG type */
 
@@ -1514,22 +1527,52 @@ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
 
 	/* 9.1 step 4 is implicit in  drbg_sec_strength */
 
-	ret = drbg_alloc_state(drbg);
-	if (ret)
-		return ret;
+	if (!drbg->core) {
+		drbg->core = &drbg_cores[coreref];
+		drbg->pr = pr;
+		drbg->seeded = false;
+		drbg->reseed_threshold = drbg_max_requests(drbg);
 
-	ret = -EFAULT;
-	if (drbg->d_ops->crypto_init(drbg))
-		goto err;
-	ret = drbg_seed(drbg, pers, false);
-	drbg->d_ops->crypto_fini(drbg);
-	if (ret)
-		goto err;
+		ret = drbg_alloc_state(drbg);
+		if (ret)
+			goto unlock;
 
-	return 0;
+		ret = -EFAULT;
+		if (drbg->d_ops->crypto_init(drbg))
+			goto err;
+
+		ret = drbg_prepare_hrng(drbg);
+		if (ret)
+			goto free_everything;
+
+		if (IS_ERR(drbg->jent)) {
+			ret = PTR_ERR(drbg->jent);
+			drbg->jent = NULL;
+			if (fips_enabled || ret != -ENOENT)
+				goto free_everything;
+			pr_info("DRBG: Continuing without Jitter RNG\n");
+		}
+
+		reseed = false;
+	}
+
+	ret = drbg_seed(drbg, pers, reseed);
+
+	if (ret && !reseed)
+		goto free_everything;
+
+	mutex_unlock(&drbg->drbg_mutex);
+	return ret;
 
 err:
 	drbg_dealloc_state(drbg);
+unlock:
+	mutex_unlock(&drbg->drbg_mutex);
+	return ret;
+
+free_everything:
+	mutex_unlock(&drbg->drbg_mutex);
+	drbg_uninstantiate(drbg);
 	return ret;
 }
 
@@ -1544,10 +1587,17 @@ err:
  */
 static int drbg_uninstantiate(struct drbg_state *drbg)
 {
-	spin_lock_bh(&drbg->drbg_lock);
+	if (drbg->random_ready.func) {
+		del_random_ready_callback(&drbg->random_ready);
+		cancel_work_sync(&drbg->seed_work);
+		crypto_free_rng(drbg->jent);
+		drbg->jent = NULL;
+	}
+
+	if (drbg->d_ops)
+		drbg->d_ops->crypto_fini(drbg);
 	drbg_dealloc_state(drbg);
 	/* no scrubbing of test_data -- this shall survive an uninstantiate */
-	spin_unlock_bh(&drbg->drbg_lock);
 	return 0;
 }
 
@@ -1555,16 +1605,17 @@ static int drbg_uninstantiate(struct drbg_state *drbg)
  * Helper function for setting the test data in the DRBG
  *
  * @drbg DRBG state handle
- * @test_data test data to sets
+ * @data test data
+ * @len test data length
  */
-static inline void drbg_set_testdata(struct drbg_state *drbg,
-				     struct drbg_test_data *test_data)
+static void drbg_kcapi_set_entropy(struct crypto_rng *tfm,
+				   const u8 *data, unsigned int len)
 {
-	if (!test_data || !test_data->testentropy)
-		return;
-	spin_lock_bh(&drbg->drbg_lock);
-	drbg->test_data = test_data;
-	spin_unlock_bh(&drbg->drbg_lock);
+	struct drbg_state *drbg = crypto_rng_ctx(tfm);
+
+	mutex_lock(&drbg->drbg_mutex);
+	drbg_string_fill(&drbg->test_data, data, len);
+	mutex_unlock(&drbg->drbg_mutex);
 }
 
 /***************************************************************
@@ -1584,7 +1635,8 @@ static int drbg_init_hash_kernel(struct drbg_state *drbg)
 
 	tfm = crypto_alloc_shash(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
-		pr_info("DRBG: could not allocate digest TFM handle\n");
+		pr_info("DRBG: could not allocate digest TFM handle: %s\n",
+				drbg->core->backend_cra_name);
 		return PTR_ERR(tfm);
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_shash_digestsize(tfm));
@@ -1635,7 +1687,8 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 
 	tfm = crypto_alloc_cipher(drbg->core->backend_cra_name, 0, 0);
 	if (IS_ERR(tfm)) {
-		pr_info("DRBG: could not allocate cipher TFM handle\n");
+		pr_info("DRBG: could not allocate cipher TFM handle: %s\n",
+				drbg->core->backend_cra_name);
 		return PTR_ERR(tfm);
 	}
 	BUG_ON(drbg_blocklen(drbg) != crypto_cipher_blocksize(tfm));
@@ -1714,15 +1767,10 @@ static inline void drbg_convert_tfm_core(const char *cra_driver_name,
 static int drbg_kcapi_init(struct crypto_tfm *tfm)
 {
 	struct drbg_state *drbg = crypto_tfm_ctx(tfm);
-	bool pr = false;
-	int coreref = 0;
 
-	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm), &coreref, &pr);
-	/*
-	 * when personalization string is needed, the caller must call reset
-	 * and provide the personalization string as seed information
-	 */
-	return drbg_instantiate(drbg, NULL, coreref, pr);
+	mutex_init(&drbg->drbg_mutex);
+
+	return 0;
 }
 
 static void drbg_kcapi_cleanup(struct crypto_tfm *tfm)
@@ -1734,65 +1782,49 @@ static void drbg_kcapi_cleanup(struct crypto_tfm *tfm)
  * Generate random numbers invoked by the kernel crypto API:
  * The API of the kernel crypto API is extended as follows:
  *
- * If dlen is larger than zero, rdata is interpreted as the output buffer
- * where random data is to be stored.
- *
- * If dlen is zero, rdata is interpreted as a pointer to a struct drbg_gen
- * which holds the additional information string that is used for the
- * DRBG generation process. The output buffer that is to be used to store
- * data is also pointed to by struct drbg_gen.
+ * src is additional input supplied to the RNG.
+ * slen is the length of src.
+ * dst is the output buffer where random data is to be stored.
+ * dlen is the length of dst.
  */
-static int drbg_kcapi_random(struct crypto_rng *tfm, u8 *rdata,
-			     unsigned int dlen)
+static int drbg_kcapi_random(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *dst, unsigned int dlen)
 {
 	struct drbg_state *drbg = crypto_rng_ctx(tfm);
-	if (0 < dlen) {
-		return drbg_generate_long(drbg, rdata, dlen, NULL);
-	} else {
-		struct drbg_gen *data = (struct drbg_gen *)rdata;
-		struct drbg_string addtl;
-		/* catch NULL pointer */
-		if (!data)
-			return 0;
-		drbg_set_testdata(drbg, data->test_data);
+	struct drbg_string *addtl = NULL;
+	struct drbg_string string;
+
+	if (slen) {
 		/* linked list variable is now local to allow modification */
-		drbg_string_fill(&addtl, data->addtl->buf, data->addtl->len);
-		return drbg_generate_long(drbg, data->outbuf, data->outlen,
-					  &addtl);
+		drbg_string_fill(&string, src, slen);
+		addtl = &string;
 	}
+
+	return drbg_generate_long(drbg, dst, dlen, addtl);
 }
 
 /*
- * Reset the DRBG invoked by the kernel crypto API
- * The reset implies a full re-initialization of the DRBG. Similar to the
- * generate function of drbg_kcapi_random, this function extends the
- * kernel crypto API interface with struct drbg_gen
+ * Seed the DRBG invoked by the kernel crypto API
  */
-static int drbg_kcapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static int drbg_kcapi_seed(struct crypto_rng *tfm,
+			   const u8 *seed, unsigned int slen)
 {
 	struct drbg_state *drbg = crypto_rng_ctx(tfm);
 	struct crypto_tfm *tfm_base = crypto_rng_tfm(tfm);
 	bool pr = false;
-	struct drbg_string seed_string;
+	struct drbg_string string;
+	struct drbg_string *seed_string = NULL;
 	int coreref = 0;
 
-	drbg_uninstantiate(drbg);
 	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm_base), &coreref,
 			      &pr);
 	if (0 < slen) {
-		drbg_string_fill(&seed_string, seed, slen);
-		return drbg_instantiate(drbg, &seed_string, coreref, pr);
-	} else {
-		struct drbg_gen *data = (struct drbg_gen *)seed;
-		/* allow invocation of API call with NULL, 0 */
-		if (!data)
-			return drbg_instantiate(drbg, NULL, coreref, pr);
-		drbg_set_testdata(drbg, data->test_data);
-		/* linked list variable is now local to allow modification */
-		drbg_string_fill(&seed_string, data->addtl->buf,
-				 data->addtl->len);
-		return drbg_instantiate(drbg, &seed_string, coreref, pr);
+		drbg_string_fill(&string, seed, slen);
+		seed_string = &string;
 	}
+
+	return drbg_instantiate(drbg, seed_string, coreref, pr);
 }
 
 /***************************************************************
@@ -1811,7 +1843,6 @@ static int drbg_kcapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
  */
 static inline int __init drbg_healthcheck_sanity(void)
 {
-#ifdef CONFIG_CRYPTO_FIPS
 	int len = 0;
 #define OUTBUFLEN 16
 	unsigned char buf[OUTBUFLEN];
@@ -1839,6 +1870,8 @@ static inline int __init drbg_healthcheck_sanity(void)
 	if (!drbg)
 		return -ENOMEM;
 
+	mutex_init(&drbg->drbg_mutex);
+
 	/*
 	 * if the following tests fail, it is likely that there is a buffer
 	 * overflow as buf is much smaller than the requested or provided
@@ -1877,37 +1910,33 @@ static inline int __init drbg_healthcheck_sanity(void)
 outbuf:
 	kzfree(drbg);
 	return rc;
-#else /* CONFIG_CRYPTO_FIPS */
-	return 0;
-#endif /* CONFIG_CRYPTO_FIPS */
 }
 
-static struct crypto_alg drbg_algs[22];
+static struct rng_alg drbg_algs[22];
 
 /*
  * Fill the array drbg_algs used to register the different DRBGs
  * with the kernel crypto API. To fill the array, the information
  * from drbg_cores[] is used.
  */
-static inline void __init drbg_fill_array(struct crypto_alg *alg,
+static inline void __init drbg_fill_array(struct rng_alg *alg,
 					  const struct drbg_core *core, int pr)
 {
 	int pos = 0;
-	static int priority = 100;
+	static int priority = 200;
 
-	memset(alg, 0, sizeof(struct crypto_alg));
-	memcpy(alg->cra_name, "stdrng", 6);
+	memcpy(alg->base.cra_name, "stdrng", 6);
 	if (pr) {
-		memcpy(alg->cra_driver_name, "drbg_pr_", 8);
+		memcpy(alg->base.cra_driver_name, "drbg_pr_", 8);
 		pos = 8;
 	} else {
-		memcpy(alg->cra_driver_name, "drbg_nopr_", 10);
+		memcpy(alg->base.cra_driver_name, "drbg_nopr_", 10);
 		pos = 10;
 	}
-	memcpy(alg->cra_driver_name + pos, core->cra_name,
+	memcpy(alg->base.cra_driver_name + pos, core->cra_name,
 	       strlen(core->cra_name));
 
-	alg->cra_priority = priority;
+	alg->base.cra_priority = priority;
 	priority++;
 	/*
 	 * If FIPS mode enabled, the selected DRBG shall have the
@@ -1915,17 +1944,16 @@ static inline void __init drbg_fill_array(struct crypto_alg *alg,
 	 * it is selected.
 	 */
 	if (fips_enabled)
-		alg->cra_priority += 200;
-
-	alg->cra_flags		= CRYPTO_ALG_TYPE_RNG;
-	alg->cra_ctxsize 	= sizeof(struct drbg_state);
-	alg->cra_type		= &crypto_rng_type;
-	alg->cra_module		= THIS_MODULE;
-	alg->cra_init		= drbg_kcapi_init;
-	alg->cra_exit		= drbg_kcapi_cleanup;
-	alg->cra_u.rng.rng_make_random	= drbg_kcapi_random;
-	alg->cra_u.rng.rng_reset	= drbg_kcapi_reset;
-	alg->cra_u.rng.seedsize	= 0;
+		alg->base.cra_priority += 200;
+
+	alg->base.cra_ctxsize 	= sizeof(struct drbg_state);
+	alg->base.cra_module	= THIS_MODULE;
+	alg->base.cra_init	= drbg_kcapi_init;
+	alg->base.cra_exit	= drbg_kcapi_cleanup;
+	alg->generate		= drbg_kcapi_random;
+	alg->seed		= drbg_kcapi_seed;
+	alg->set_ent		= drbg_kcapi_set_entropy;
+	alg->seedsize		= 0;
 }
 
 static int __init drbg_init(void)
@@ -1958,12 +1986,12 @@ static int __init drbg_init(void)
 		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 1);
 	for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++)
 		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 0);
-	return crypto_register_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+	return crypto_register_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
 }
 
 static void __exit drbg_exit(void)
 {
-	crypto_unregister_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+	crypto_unregister_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
 }
 
 module_init(drbg_init);
@@ -1984,3 +2012,4 @@ MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) "
 		   CRYPTO_DRBG_HASH_STRING
 		   CRYPTO_DRBG_HMAC_STRING
 		   CRYPTO_DRBG_CTR_STRING);
+MODULE_ALIAS_CRYPTO("stdrng");
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
new file mode 100644
index 000000000000..b6e43dc61356
--- /dev/null
+++ b/crypto/echainiv.c
@@ -0,0 +1,312 @@
+/*
+ * echainiv: Encrypted Chain IV Generator
+ *
+ * This generator generates an IV based on a sequence number by xoring it
+ * with a salt and then encrypting it with the same key as used to encrypt
+ * the plain text.  This algorithm requires that the block size be equal
+ * to the IV size.  It is mainly useful for CBC.
+ *
+ * This generator can only be used by algorithms where authentication
+ * is performed after encryption (i.e., authenc).
+ *
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/internal/geniv.h>
+#include <crypto/null.h>
+#include <crypto/rng.h>
+#include <crypto/scatterwalk.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+
+#define MAX_IV_SIZE 16
+
+struct echainiv_ctx {
+	/* aead_geniv_ctx must be first the element */
+	struct aead_geniv_ctx geniv;
+	struct crypto_blkcipher *null;
+	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
+};
+
+static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
+
+/* We don't care if we get preempted and read/write IVs from the next CPU. */
+static void echainiv_read_iv(u8 *dst, unsigned size)
+{
+	u32 *a = (u32 *)dst;
+	u32 __percpu *b = echainiv_iv;
+
+	for (; size >= 4; size -= 4) {
+		*a++ = this_cpu_read(*b);
+		b++;
+	}
+}
+
+static void echainiv_write_iv(const u8 *src, unsigned size)
+{
+	const u32 *a = (const u32 *)src;
+	u32 __percpu *b = echainiv_iv;
+
+	for (; size >= 4; size -= 4) {
+		this_cpu_write(*b, *a);
+		a++;
+		b++;
+	}
+}
+
+static void echainiv_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_aead *geniv;
+	unsigned int ivsize;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	ivsize = crypto_aead_ivsize(geniv);
+
+	echainiv_write_iv(subreq->iv, ivsize);
+
+	if (req->iv != subreq->iv)
+		memcpy(req->iv, subreq->iv, ivsize);
+
+out:
+	if (req->iv != subreq->iv)
+		kzfree(subreq->iv);
+}
+
+static void echainiv_encrypt_complete(struct crypto_async_request *base,
+					 int err)
+{
+	struct aead_request *req = base->data;
+
+	echainiv_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static int echainiv_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+	int err;
+
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = echainiv_encrypt_complete;
+	data = req;
+	info = req->iv;
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(
+			&desc, req->dst, req->src,
+			req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	if (unlikely(!IS_ALIGNED((unsigned long)info,
+				 crypto_aead_alignmask(geniv) + 1))) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		memcpy(info, req->iv, ivsize);
+	}
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->dst, req->dst,
+			       req->cryptlen - ivsize, info);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	crypto_xor(info, ctx->salt, ivsize);
+	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
+	echainiv_read_iv(info, ivsize);
+
+	err = crypto_aead_encrypt(subreq);
+	echainiv_encrypt_complete2(req, err);
+	return err;
+}
+
+static int echainiv_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = crypto_aead_ivsize(geniv);
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+	if (req->src != req->dst)
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->assoclen, ivsize, 1);
+
+	return crypto_aead_decrypt(subreq);
+}
+
+static int echainiv_init(struct crypto_tfm *tfm)
+{
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct echainiv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
+
+	spin_lock_init(&ctx->geniv.lock);
+
+	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
+
+	err = crypto_get_default_rng();
+	if (err)
+		goto out;
+
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(geniv));
+	crypto_put_default_rng();
+	if (err)
+		goto out;
+
+	ctx->null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->null);
+	if (IS_ERR(ctx->null))
+		goto out;
+
+	err = aead_geniv_init(tfm);
+	if (err)
+		goto drop_null;
+
+	ctx->geniv.child = geniv->child;
+	geniv->child = geniv;
+
+out:
+	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
+}
+
+static void echainiv_exit(struct crypto_tfm *tfm)
+{
+	struct echainiv_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->geniv.child);
+	crypto_put_default_null_skcipher();
+}
+
+static int echainiv_aead_create(struct crypto_template *tmpl,
+				struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize & (sizeof(u32) - 1) ||
+	    inst->alg.ivsize > MAX_IV_SIZE)
+		goto free_inst;
+
+	inst->alg.encrypt = echainiv_encrypt;
+	inst->alg.decrypt = echainiv_decrypt;
+
+	inst->alg.base.cra_init = echainiv_init;
+	inst->alg.base.cra_exit = echainiv_exit;
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_ctxsize = sizeof(struct echainiv_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
+
+out:
+	return err;
+
+free_inst:
+	aead_geniv_free(inst);
+	goto out;
+}
+
+static void echainiv_free(struct crypto_instance *inst)
+{
+	aead_geniv_free(aead_instance(inst));
+}
+
+static struct crypto_template echainiv_tmpl = {
+	.name = "echainiv",
+	.create = echainiv_aead_create,
+	.free = echainiv_free,
+	.module = THIS_MODULE,
+};
+
+static int __init echainiv_module_init(void)
+{
+	return crypto_register_template(&echainiv_tmpl);
+}
+
+static void __exit echainiv_module_exit(void)
+{
+	crypto_unregister_template(&echainiv_tmpl);
+}
+
+module_init(echainiv_module_init);
+module_exit(echainiv_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Encrypted Chain IV Generator");
+MODULE_ALIAS_CRYPTO("echainiv");
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
index f116fae766f8..16dda72fc4f8 100644
--- a/crypto/eseqiv.c
+++ b/crypto/eseqiv.c
@@ -146,35 +146,13 @@ out:
 	return err;
 }
 
-static int eseqiv_givencrypt_first(struct skcipher_givcrypt_request *req)
-{
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
-
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt != eseqiv_givencrypt_first)
-		goto unlock;
-
-	crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_ablkcipher_ivsize(geniv));
-
-unlock:
-	spin_unlock_bh(&ctx->lock);
-
-	if (err)
-		return err;
-
-	return eseqiv_givencrypt(req);
-}
-
 static int eseqiv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
 	unsigned long alignmask;
 	unsigned int reqsize;
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
@@ -198,7 +176,15 @@ static int eseqiv_init(struct crypto_tfm *tfm)
 	tfm->crt_ablkcipher.reqsize = reqsize +
 				      sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = eseqiv_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
 static struct crypto_template eseqiv_tmpl;
@@ -208,20 +194,14 @@ static struct crypto_instance *eseqiv_alloc(struct rtattr **tb)
 	struct crypto_instance *inst;
 	int err;
 
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
-
 	inst = skcipher_geniv_alloc(&eseqiv_tmpl, tb, 0, 0);
 	if (IS_ERR(inst))
-		goto put_rng;
+		goto out;
 
 	err = -EINVAL;
 	if (inst->alg.cra_ablkcipher.ivsize != inst->alg.cra_blocksize)
 		goto free_inst;
 
-	inst->alg.cra_ablkcipher.givencrypt = eseqiv_givencrypt_first;
-
 	inst->alg.cra_init = eseqiv_init;
 	inst->alg.cra_exit = skcipher_geniv_exit;
 
@@ -234,21 +214,13 @@ out:
 free_inst:
 	skcipher_geniv_free(inst);
 	inst = ERR_PTR(err);
-put_rng:
-	crypto_put_default_rng();
 	goto out;
 }
 
-static void eseqiv_free(struct crypto_instance *inst)
-{
-	skcipher_geniv_free(inst);
-	crypto_put_default_rng();
-}
-
 static struct crypto_template eseqiv_tmpl = {
 	.name = "eseqiv",
 	.alloc = eseqiv_alloc,
-	.free = eseqiv_free,
+	.free = skcipher_geniv_free,
 	.module = THIS_MODULE,
 };
 
diff --git a/crypto/fips.c b/crypto/fips.c
index 553970081c62..9d627c1cf8bc 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -10,7 +10,12 @@
  *
  */
 
-#include "internal.h"
+#include <linux/export.h>
+#include <linux/fips.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/sysctl.h>
 
 int fips_enabled;
 EXPORT_SYMBOL_GPL(fips_enabled);
@@ -25,3 +30,49 @@ static int fips_enable(char *str)
 }
 
 __setup("fips=", fips_enable);
+
+static struct ctl_table crypto_sysctl_table[] = {
+	{
+		.procname       = "fips_enabled",
+		.data           = &fips_enabled,
+		.maxlen         = sizeof(int),
+		.mode           = 0444,
+		.proc_handler   = proc_dointvec
+	},
+	{}
+};
+
+static struct ctl_table crypto_dir_table[] = {
+	{
+		.procname       = "crypto",
+		.mode           = 0555,
+		.child          = crypto_sysctl_table
+	},
+	{}
+};
+
+static struct ctl_table_header *crypto_sysctls;
+
+static void crypto_proc_fips_init(void)
+{
+	crypto_sysctls = register_sysctl_table(crypto_dir_table);
+}
+
+static void crypto_proc_fips_exit(void)
+{
+	unregister_sysctl_table(crypto_sysctls);
+}
+
+static int __init fips_init(void)
+{
+	crypto_proc_fips_init();
+	return 0;
+}
+
+static void __exit fips_exit(void)
+{
+	crypto_proc_fips_exit();
+}
+
+module_init(fips_init);
+module_exit(fips_exit);
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 2e403f6138c1..7d32d4720564 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -12,6 +12,7 @@
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/internal/hash.h>
+#include <crypto/null.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/hash.h>
 #include "internal.h"
@@ -39,7 +40,6 @@ struct crypto_rfc4106_ctx {
 
 struct crypto_rfc4543_instance_ctx {
 	struct crypto_aead_spawn aead;
-	struct crypto_skcipher_spawn null;
 };
 
 struct crypto_rfc4543_ctx {
@@ -49,25 +49,22 @@ struct crypto_rfc4543_ctx {
 };
 
 struct crypto_rfc4543_req_ctx {
-	u8 auth_tag[16];
-	u8 assocbuf[32];
-	struct scatterlist cipher[1];
-	struct scatterlist payload[2];
-	struct scatterlist assoc[2];
 	struct aead_request subreq;
 };
 
 struct crypto_gcm_ghash_ctx {
 	unsigned int cryptlen;
 	struct scatterlist *src;
-	void (*complete)(struct aead_request *req, int err);
+	int (*complete)(struct aead_request *req, u32 flags);
 };
 
 struct crypto_gcm_req_priv_ctx {
+	u8 iv[16];
 	u8 auth_tag[16];
 	u8 iauth_tag[16];
-	struct scatterlist src[2];
-	struct scatterlist dst[2];
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	struct scatterlist sg;
 	struct crypto_gcm_ghash_ctx ghash_ctx;
 	union {
 		struct ahash_request ahreq;
@@ -80,7 +77,12 @@ struct crypto_gcm_setkey_result {
 	struct completion completion;
 };
 
-static void *gcm_zeroes;
+static struct {
+	u8 buf[16];
+	struct scatterlist sg;
+} *gcm_zeroes;
+
+static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc);
 
 static inline struct crypto_gcm_req_priv_ctx *crypto_gcm_reqctx(
 	struct aead_request *req)
@@ -120,15 +122,13 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 
 	crypto_ablkcipher_clear_flags(ctr, CRYPTO_TFM_REQ_MASK);
 	crypto_ablkcipher_set_flags(ctr, crypto_aead_get_flags(aead) &
-				   CRYPTO_TFM_REQ_MASK);
-
+					 CRYPTO_TFM_REQ_MASK);
 	err = crypto_ablkcipher_setkey(ctr, key, keylen);
+	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
+				    CRYPTO_TFM_RES_MASK);
 	if (err)
 		return err;
 
-	crypto_aead_set_flags(aead, crypto_ablkcipher_get_flags(ctr) &
-				       CRYPTO_TFM_RES_MASK);
-
 	data = kzalloc(sizeof(*data) + crypto_ablkcipher_reqsize(ctr),
 		       GFP_KERNEL);
 	if (!data)
@@ -163,7 +163,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 			      CRYPTO_TFM_RES_MASK);
 
 out:
-	kfree(data);
+	kzfree(data);
 	return err;
 }
 
@@ -186,35 +186,46 @@ static int crypto_gcm_setauthsize(struct crypto_aead *tfm,
 	return 0;
 }
 
-static void crypto_gcm_init_crypt(struct ablkcipher_request *ablk_req,
-				  struct aead_request *req,
-				  unsigned int cryptlen)
+static void crypto_gcm_init_common(struct aead_request *req)
 {
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct scatterlist *dst;
 	__be32 counter = cpu_to_be32(1);
+	struct scatterlist *sg;
 
 	memset(pctx->auth_tag, 0, sizeof(pctx->auth_tag));
-	memcpy(req->iv + 12, &counter, 4);
+	memcpy(pctx->iv, req->iv, 12);
+	memcpy(pctx->iv + 12, &counter, 4);
 
-	sg_init_table(pctx->src, 2);
+	sg_init_table(pctx->src, 3);
 	sg_set_buf(pctx->src, pctx->auth_tag, sizeof(pctx->auth_tag));
-	scatterwalk_sg_chain(pctx->src, 2, req->src);
+	sg = scatterwalk_ffwd(pctx->src + 1, req->src, req->assoclen);
+	if (sg != pctx->src + 1)
+		scatterwalk_sg_chain(pctx->src, 2, sg);
 
-	dst = pctx->src;
 	if (req->src != req->dst) {
-		sg_init_table(pctx->dst, 2);
+		sg_init_table(pctx->dst, 3);
 		sg_set_buf(pctx->dst, pctx->auth_tag, sizeof(pctx->auth_tag));
-		scatterwalk_sg_chain(pctx->dst, 2, req->dst);
-		dst = pctx->dst;
+		sg = scatterwalk_ffwd(pctx->dst + 1, req->dst, req->assoclen);
+		if (sg != pctx->dst + 1)
+			scatterwalk_sg_chain(pctx->dst, 2, sg);
 	}
+}
+
+static void crypto_gcm_init_crypt(struct aead_request *req,
+				  unsigned int cryptlen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(aead);
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
+	struct ablkcipher_request *ablk_req = &pctx->u.abreq;
+	struct scatterlist *dst;
+
+	dst = req->src == req->dst ? pctx->src : pctx->dst;
 
 	ablkcipher_request_set_tfm(ablk_req, ctx->ctr);
 	ablkcipher_request_set_crypt(ablk_req, pctx->src, dst,
 				     cryptlen + sizeof(pctx->auth_tag),
-				     req->iv);
+				     pctx->iv);
 }
 
 static inline unsigned int gcm_remain(unsigned int len)
@@ -224,41 +235,31 @@ static inline unsigned int gcm_remain(unsigned int len)
 }
 
 static void gcm_hash_len_done(struct crypto_async_request *areq, int err);
-static void gcm_hash_final_done(struct crypto_async_request *areq, int err);
 
 static int gcm_hash_update(struct aead_request *req,
-			   struct crypto_gcm_req_priv_ctx *pctx,
 			   crypto_completion_t compl,
 			   struct scatterlist *src,
-			   unsigned int len)
+			   unsigned int len, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   compl, req);
+	ahash_request_set_callback(ahreq, flags, compl, req);
 	ahash_request_set_crypt(ahreq, src, NULL, len);
 
 	return crypto_ahash_update(ahreq);
 }
 
 static int gcm_hash_remain(struct aead_request *req,
-			   struct crypto_gcm_req_priv_ctx *pctx,
 			   unsigned int remain,
-			   crypto_completion_t compl)
+			   crypto_completion_t compl, u32 flags)
 {
-	struct ahash_request *ahreq = &pctx->u.ahreq;
-
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   compl, req);
-	sg_init_one(pctx->src, gcm_zeroes, remain);
-	ahash_request_set_crypt(ahreq, pctx->src, NULL, remain);
-
-	return crypto_ahash_update(ahreq);
+	return gcm_hash_update(req, compl, &gcm_zeroes->sg, remain, flags);
 }
 
-static int gcm_hash_len(struct aead_request *req,
-			struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_hash_len(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	u128 lengths;
@@ -266,76 +267,41 @@ static int gcm_hash_len(struct aead_request *req,
 	lengths.a = cpu_to_be64(req->assoclen * 8);
 	lengths.b = cpu_to_be64(gctx->cryptlen * 8);
 	memcpy(pctx->iauth_tag, &lengths, 16);
-	sg_init_one(pctx->src, pctx->iauth_tag, 16);
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_len_done, req);
-	ahash_request_set_crypt(ahreq, pctx->src,
-				NULL, sizeof(lengths));
+	sg_init_one(&pctx->sg, pctx->iauth_tag, 16);
+	ahash_request_set_callback(ahreq, flags, gcm_hash_len_done, req);
+	ahash_request_set_crypt(ahreq, &pctx->sg,
+				pctx->iauth_tag, sizeof(lengths));
 
-	return crypto_ahash_update(ahreq);
-}
-
-static int gcm_hash_final(struct aead_request *req,
-			  struct crypto_gcm_req_priv_ctx *pctx)
-{
-	struct ahash_request *ahreq = &pctx->u.ahreq;
-
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_final_done, req);
-	ahash_request_set_crypt(ahreq, NULL, pctx->iauth_tag, 0);
-
-	return crypto_ahash_final(ahreq);
+	return crypto_ahash_finup(ahreq);
 }
 
-static void __gcm_hash_final_done(struct aead_request *req, int err)
+static int gcm_hash_len_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err)
-		crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-
-	gctx->complete(req, err);
+	return gctx->complete(req, flags);
 }
 
-static void gcm_hash_final_done(struct crypto_async_request *areq, int err)
+static void gcm_hash_len_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_final_done(req, err);
-}
-
-static void __gcm_hash_len_done(struct aead_request *req, int err)
-{
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-
-	if (!err) {
-		err = gcm_hash_final(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
-
-	__gcm_hash_final_done(req, err);
-}
+	if (err)
+		goto out;
 
-static void gcm_hash_len_done(struct crypto_async_request *areq, int err)
-{
-	struct aead_request *req = areq->data;
+	err = gcm_hash_len_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
 
-	__gcm_hash_len_done(req, err);
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_crypt_remain_done(struct aead_request *req, int err)
+static int gcm_hash_crypt_remain_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-
-	if (!err) {
-		err = gcm_hash_len(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
-
-	__gcm_hash_len_done(req, err);
+	return gcm_hash_len(req, flags) ?:
+	       gcm_hash_len_continue(req, flags);
 }
 
 static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq,
@@ -343,55 +309,58 @@ static void gcm_hash_crypt_remain_done(struct crypto_async_request *areq,
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_crypt_remain_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_crypt_remain_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_crypt_done(struct aead_request *req, int err)
+static int gcm_hash_crypt_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	unsigned int remain;
 
-	if (!err) {
-		remain = gcm_remain(gctx->cryptlen);
-		BUG_ON(!remain);
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_crypt_remain_done);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	remain = gcm_remain(gctx->cryptlen);
+	if (remain)
+		return gcm_hash_remain(req, remain,
+				       gcm_hash_crypt_remain_done, flags) ?:
+		       gcm_hash_crypt_remain_continue(req, flags);
 
-	__gcm_hash_crypt_remain_done(req, err);
+	return gcm_hash_crypt_remain_continue(req, flags);
 }
 
 static void gcm_hash_crypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_crypt_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_crypt_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_assoc_remain_done(struct aead_request *req, int err)
+static int gcm_hash_assoc_remain_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	crypto_completion_t compl;
-	unsigned int remain = 0;
-
-	if (!err && gctx->cryptlen) {
-		remain = gcm_remain(gctx->cryptlen);
-		compl = remain ? gcm_hash_crypt_done :
-			gcm_hash_crypt_remain_done;
-		err = gcm_hash_update(req, pctx, compl,
-				      gctx->src, gctx->cryptlen);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
 
-	if (remain)
-		__gcm_hash_crypt_done(req, err);
-	else
-		__gcm_hash_crypt_remain_done(req, err);
+	if (gctx->cryptlen)
+		return gcm_hash_update(req, gcm_hash_crypt_done,
+				       gctx->src, gctx->cryptlen, flags) ?:
+		       gcm_hash_crypt_continue(req, flags);
+
+	return gcm_hash_crypt_remain_continue(req, flags);
 }
 
 static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq,
@@ -399,146 +368,120 @@ static void gcm_hash_assoc_remain_done(struct crypto_async_request *areq,
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_assoc_remain_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_assoc_remain_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_assoc_done(struct aead_request *req, int err)
+static int gcm_hash_assoc_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	unsigned int remain;
 
-	if (!err) {
-		remain = gcm_remain(req->assoclen);
-		BUG_ON(!remain);
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_assoc_remain_done);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	remain = gcm_remain(req->assoclen);
+	if (remain)
+		return gcm_hash_remain(req, remain,
+				       gcm_hash_assoc_remain_done, flags) ?:
+		       gcm_hash_assoc_remain_continue(req, flags);
 
-	__gcm_hash_assoc_remain_done(req, err);
+	return gcm_hash_assoc_remain_continue(req, flags);
 }
 
 static void gcm_hash_assoc_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_assoc_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_assoc_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static void __gcm_hash_init_done(struct aead_request *req, int err)
+static int gcm_hash_init_continue(struct aead_request *req, u32 flags)
 {
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	crypto_completion_t compl;
-	unsigned int remain = 0;
-
-	if (!err && req->assoclen) {
-		remain = gcm_remain(req->assoclen);
-		compl = remain ? gcm_hash_assoc_done :
-			gcm_hash_assoc_remain_done;
-		err = gcm_hash_update(req, pctx, compl,
-				      req->assoc, req->assoclen);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-	}
+	if (req->assoclen)
+		return gcm_hash_update(req, gcm_hash_assoc_done,
+				       req->src, req->assoclen, flags) ?:
+		       gcm_hash_assoc_continue(req, flags);
 
-	if (remain)
-		__gcm_hash_assoc_done(req, err);
-	else
-		__gcm_hash_assoc_remain_done(req, err);
+	return gcm_hash_assoc_remain_continue(req, flags);
 }
 
 static void gcm_hash_init_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
 
-	__gcm_hash_init_done(req, err);
+	if (err)
+		goto out;
+
+	err = gcm_hash_init_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
+
+out:
+	aead_request_complete(req, err);
 }
 
-static int gcm_hash(struct aead_request *req,
-		    struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_hash(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ahash_request *ahreq = &pctx->u.ahreq;
-	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
-	unsigned int remain;
-	crypto_completion_t compl;
-	int err;
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(crypto_aead_reqtfm(req));
 
 	ahash_request_set_tfm(ahreq, ctx->ghash);
 
-	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   gcm_hash_init_done, req);
-	err = crypto_ahash_init(ahreq);
-	if (err)
-		return err;
-	remain = gcm_remain(req->assoclen);
-	compl = remain ? gcm_hash_assoc_done : gcm_hash_assoc_remain_done;
-	err = gcm_hash_update(req, pctx, compl, req->assoc, req->assoclen);
-	if (err)
-		return err;
-	if (remain) {
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_assoc_remain_done);
-		if (err)
-			return err;
-	}
-	remain = gcm_remain(gctx->cryptlen);
-	compl = remain ? gcm_hash_crypt_done : gcm_hash_crypt_remain_done;
-	err = gcm_hash_update(req, pctx, compl, gctx->src, gctx->cryptlen);
-	if (err)
-		return err;
-	if (remain) {
-		err = gcm_hash_remain(req, pctx, remain,
-				      gcm_hash_crypt_remain_done);
-		if (err)
-			return err;
-	}
-	err = gcm_hash_len(req, pctx);
-	if (err)
-		return err;
-	err = gcm_hash_final(req, pctx);
-	if (err)
-		return err;
-
-	return 0;
+	ahash_request_set_callback(ahreq, flags, gcm_hash_init_done, req);
+	return crypto_ahash_init(ahreq) ?:
+	       gcm_hash_init_continue(req, flags);
 }
 
-static void gcm_enc_copy_hash(struct aead_request *req,
-			      struct crypto_gcm_req_priv_ctx *pctx)
+static int gcm_enc_copy_hash(struct aead_request *req, u32 flags)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	u8 *auth_tag = pctx->auth_tag;
 
-	scatterwalk_map_and_copy(auth_tag, req->dst, req->cryptlen,
+	crypto_xor(auth_tag, pctx->iauth_tag, 16);
+	scatterwalk_map_and_copy(auth_tag, req->dst,
+				 req->assoclen + req->cryptlen,
 				 crypto_aead_authsize(aead), 1);
+	return 0;
 }
 
-static void gcm_enc_hash_done(struct aead_request *req, int err)
+static int gcm_encrypt_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
+	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err)
-		gcm_enc_copy_hash(req, pctx);
+	gctx->src = sg_next(req->src == req->dst ? pctx->src : pctx->dst);
+	gctx->cryptlen = req->cryptlen;
+	gctx->complete = gcm_enc_copy_hash;
 
-	aead_request_complete(req, err);
+	return gcm_hash(req, flags);
 }
 
 static void gcm_encrypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 
-	if (!err) {
-		err = gcm_hash(req, pctx);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-		else if (!err) {
-			crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-			gcm_enc_copy_hash(req, pctx);
-		}
-	}
+	if (err)
+		goto out;
+
+	err = gcm_encrypt_continue(req, 0);
+	if (err == -EINPROGRESS)
+		return;
 
+out:
 	aead_request_complete(req, err);
 }
 
@@ -546,34 +489,19 @@ static int crypto_gcm_encrypt(struct aead_request *req)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ablkcipher_request *abreq = &pctx->u.abreq;
-	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	int err;
-
-	crypto_gcm_init_crypt(abreq, req, req->cryptlen);
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					gcm_encrypt_done, req);
-
-	gctx->src = req->dst;
-	gctx->cryptlen = req->cryptlen;
-	gctx->complete = gcm_enc_hash_done;
-
-	err = crypto_ablkcipher_encrypt(abreq);
-	if (err)
-		return err;
-
-	err = gcm_hash(req, pctx);
-	if (err)
-		return err;
+	u32 flags = aead_request_flags(req);
 
-	crypto_xor(pctx->auth_tag, pctx->iauth_tag, 16);
-	gcm_enc_copy_hash(req, pctx);
+	crypto_gcm_init_common(req);
+	crypto_gcm_init_crypt(req, req->cryptlen);
+	ablkcipher_request_set_callback(abreq, flags, gcm_encrypt_done, req);
 
-	return 0;
+	return crypto_ablkcipher_encrypt(abreq) ?:
+	       gcm_encrypt_continue(req, flags);
 }
 
-static int crypto_gcm_verify(struct aead_request *req,
-			     struct crypto_gcm_req_priv_ctx *pctx)
+static int crypto_gcm_verify(struct aead_request *req)
 {
+	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	u8 *auth_tag = pctx->auth_tag;
 	u8 *iauth_tag = pctx->iauth_tag;
@@ -581,78 +509,57 @@ static int crypto_gcm_verify(struct aead_request *req,
 	unsigned int cryptlen = req->cryptlen - authsize;
 
 	crypto_xor(auth_tag, iauth_tag, 16);
-	scatterwalk_map_and_copy(iauth_tag, req->src, cryptlen, authsize, 0);
+	scatterwalk_map_and_copy(iauth_tag, req->src,
+				 req->assoclen + cryptlen, authsize, 0);
 	return crypto_memneq(iauth_tag, auth_tag, authsize) ? -EBADMSG : 0;
 }
 
 static void gcm_decrypt_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
-	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 
 	if (!err)
-		err = crypto_gcm_verify(req, pctx);
+		err = crypto_gcm_verify(req);
 
 	aead_request_complete(req, err);
 }
 
-static void gcm_dec_hash_done(struct aead_request *req, int err)
+static int gcm_dec_hash_continue(struct aead_request *req, u32 flags)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct ablkcipher_request *abreq = &pctx->u.abreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 
-	if (!err) {
-		ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-						gcm_decrypt_done, req);
-		crypto_gcm_init_crypt(abreq, req, gctx->cryptlen);
-		err = crypto_ablkcipher_decrypt(abreq);
-		if (err == -EINPROGRESS || err == -EBUSY)
-			return;
-		else if (!err)
-			err = crypto_gcm_verify(req, pctx);
-	}
-
-	aead_request_complete(req, err);
+	crypto_gcm_init_crypt(req, gctx->cryptlen);
+	ablkcipher_request_set_callback(abreq, flags, gcm_decrypt_done, req);
+	return crypto_ablkcipher_decrypt(abreq) ?: crypto_gcm_verify(req);
 }
 
 static int crypto_gcm_decrypt(struct aead_request *req)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	struct ablkcipher_request *abreq = &pctx->u.abreq;
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	unsigned int authsize = crypto_aead_authsize(aead);
 	unsigned int cryptlen = req->cryptlen;
-	int err;
+	u32 flags = aead_request_flags(req);
 
-	if (cryptlen < authsize)
-		return -EINVAL;
 	cryptlen -= authsize;
 
-	gctx->src = req->src;
-	gctx->cryptlen = cryptlen;
-	gctx->complete = gcm_dec_hash_done;
-
-	err = gcm_hash(req, pctx);
-	if (err)
-		return err;
+	crypto_gcm_init_common(req);
 
-	ablkcipher_request_set_callback(abreq, aead_request_flags(req),
-					gcm_decrypt_done, req);
-	crypto_gcm_init_crypt(abreq, req, cryptlen);
-	err = crypto_ablkcipher_decrypt(abreq);
-	if (err)
-		return err;
+	gctx->src = sg_next(pctx->src);
+	gctx->cryptlen = cryptlen;
+	gctx->complete = gcm_dec_hash_continue;
 
-	return crypto_gcm_verify(req, pctx);
+	return gcm_hash(req, flags);
 }
 
-static int crypto_gcm_init_tfm(struct crypto_tfm *tfm)
+static int crypto_gcm_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct gcm_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct gcm_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_ablkcipher *ctr;
 	struct crypto_ahash *ghash;
 	unsigned long align;
@@ -670,14 +577,14 @@ static int crypto_gcm_init_tfm(struct crypto_tfm *tfm)
 	ctx->ctr = ctr;
 	ctx->ghash = ghash;
 
-	align = crypto_tfm_alg_alignmask(tfm);
+	align = crypto_aead_alignmask(tfm);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = align +
-		offsetof(struct crypto_gcm_req_priv_ctx, u) +
+	crypto_aead_set_reqsize(tfm,
+		align + offsetof(struct crypto_gcm_req_priv_ctx, u) +
 		max(sizeof(struct ablkcipher_request) +
 		    crypto_ablkcipher_reqsize(ctr),
 		    sizeof(struct ahash_request) +
-		    crypto_ahash_reqsize(ghash));
+		    crypto_ahash_reqsize(ghash)));
 
 	return 0;
 
@@ -686,53 +593,59 @@ err_free_hash:
 	return err;
 }
 
-static void crypto_gcm_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_gcm_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_gcm_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_ahash(ctx->ghash);
 	crypto_free_ablkcipher(ctx->ctr);
 }
 
-static struct crypto_instance *crypto_gcm_alloc_common(struct rtattr **tb,
-						       const char *full_name,
-						       const char *ctr_name,
-						       const char *ghash_name)
+static int crypto_gcm_create_common(struct crypto_template *tmpl,
+				    struct rtattr **tb,
+				    const char *full_name,
+				    const char *ctr_name,
+				    const char *ghash_name)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_alg *ctr;
 	struct crypto_alg *ghash_alg;
-	struct ahash_alg *ghash_ahash_alg;
+	struct hash_alg_common *ghash;
 	struct gcm_instance_ctx *ctx;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
 				    CRYPTO_ALG_TYPE_HASH,
 				    CRYPTO_ALG_TYPE_AHASH_MASK);
 	if (IS_ERR(ghash_alg))
-		return ERR_CAST(ghash_alg);
+		return PTR_ERR(ghash_alg);
+
+	ghash = __crypto_hash_alg_common(ghash_alg);
 
 	err = -ENOMEM;
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
 		goto out_put_ghash;
 
-	ctx = crypto_instance_ctx(inst);
-	ghash_ahash_alg = container_of(ghash_alg, struct ahash_alg, halg.base);
-	err = crypto_init_ahash_spawn(&ctx->ghash, &ghash_ahash_alg->halg,
-				      inst);
+	ctx = aead_instance_ctx(inst);
+	err = crypto_init_ahash_spawn(&ctx->ghash, ghash,
+				      aead_crypto_instance(inst));
 	if (err)
 		goto err_free_inst;
 
-	crypto_set_skcipher_spawn(&ctx->ctr, inst);
+	err = -EINVAL;
+	if (ghash->digestsize != 16)
+		goto err_drop_ghash;
+
+	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
 	err = crypto_grab_skcipher(&ctx->ctr, ctr_name, 0,
 				   crypto_requires_sync(algt->type,
 							algt->mask));
@@ -751,33 +664,38 @@ static struct crypto_instance *crypto_gcm_alloc_common(struct rtattr **tb,
 		goto out_put_ctr;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "gcm_base(%s,%s)", ctr->cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
-	memcpy(inst->alg.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= ctr->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = ctr->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = ctr->cra_alignmask | (__alignof__(u64) - 1);
-	inst->alg.cra_type = &crypto_aead_type;
-	inst->alg.cra_aead.ivsize = 16;
-	inst->alg.cra_aead.maxauthsize = 16;
-	inst->alg.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
-	inst->alg.cra_init = crypto_gcm_init_tfm;
-	inst->alg.cra_exit = crypto_gcm_exit_tfm;
-	inst->alg.cra_aead.setkey = crypto_gcm_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_gcm_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_gcm_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_gcm_decrypt;
+	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
+
+	inst->alg.base.cra_flags = (ghash->base.cra_flags | ctr->cra_flags) &
+				   CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = (ghash->base.cra_priority +
+				       ctr->cra_priority) / 2;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = ghash->base.cra_alignmask |
+				       ctr->cra_alignmask;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_gcm_ctx);
+	inst->alg.ivsize = 12;
+	inst->alg.maxauthsize = 16;
+	inst->alg.init = crypto_gcm_init_tfm;
+	inst->alg.exit = crypto_gcm_exit_tfm;
+	inst->alg.setkey = crypto_gcm_setkey;
+	inst->alg.setauthsize = crypto_gcm_setauthsize;
+	inst->alg.encrypt = crypto_gcm_encrypt;
+	inst->alg.decrypt = crypto_gcm_decrypt;
+
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_put_ctr;
 
-out:
+out_put_ghash:
 	crypto_mod_put(ghash_alg);
-	return inst;
+	return err;
 
 out_put_ctr:
 	crypto_drop_skcipher(&ctx->ctr);
@@ -785,12 +703,10 @@ err_drop_ghash:
 	crypto_drop_ahash(&ctx->ghash);
 err_free_inst:
 	kfree(inst);
-out_put_ghash:
-	inst = ERR_PTR(err);
-	goto out;
+	goto out_put_ghash;
 }
 
-static struct crypto_instance *crypto_gcm_alloc(struct rtattr **tb)
+static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
@@ -798,17 +714,18 @@ static struct crypto_instance *crypto_gcm_alloc(struct rtattr **tb)
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
-		return ERR_CAST(cipher_name);
+		return PTR_ERR(cipher_name);
 
 	if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", cipher_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_gcm_alloc_common(tb, full_name, ctr_name, "ghash");
+	return crypto_gcm_create_common(tmpl, tb, full_name,
+					ctr_name, "ghash");
 }
 
 static void crypto_gcm_free(struct crypto_instance *inst)
@@ -817,17 +734,18 @@ static void crypto_gcm_free(struct crypto_instance *inst)
 
 	crypto_drop_skcipher(&ctx->ctr);
 	crypto_drop_ahash(&ctx->ghash);
-	kfree(inst);
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_gcm_tmpl = {
 	.name = "gcm",
-	.alloc = crypto_gcm_alloc,
+	.create = crypto_gcm_create,
 	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
 
-static struct crypto_instance *crypto_gcm_base_alloc(struct rtattr **tb)
+static int crypto_gcm_base_create(struct crypto_template *tmpl,
+				  struct rtattr **tb)
 {
 	const char *ctr_name;
 	const char *ghash_name;
@@ -835,22 +753,23 @@ static struct crypto_instance *crypto_gcm_base_alloc(struct rtattr **tb)
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
-		return ERR_CAST(ctr_name);
+		return PTR_ERR(ctr_name);
 
 	ghash_name = crypto_attr_alg_name(tb[2]);
 	if (IS_ERR(ghash_name))
-		return ERR_CAST(ghash_name);
+		return PTR_ERR(ghash_name);
 
 	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)",
 		     ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-ENAMETOOLONG);
+		return -ENAMETOOLONG;
 
-	return crypto_gcm_alloc_common(tb, full_name, ctr_name, ghash_name);
+	return crypto_gcm_create_common(tmpl, tb, full_name,
+					ctr_name, ghash_name);
 }
 
 static struct crypto_template crypto_gcm_base_tmpl = {
 	.name = "gcm_base",
-	.alloc = crypto_gcm_base_alloc,
+	.create = crypto_gcm_base_create,
 	.free = crypto_gcm_free,
 	.module = THIS_MODULE,
 };
@@ -911,7 +830,7 @@ static struct aead_request *crypto_rfc4106_crypt(struct aead_request *req)
 	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
 				  req->base.data);
 	aead_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, iv);
-	aead_request_set_assoc(subreq, req->assoc, req->assoclen);
+	aead_request_set_ad(subreq, req->assoclen);
 
 	return subreq;
 }
@@ -930,11 +849,11 @@ static int crypto_rfc4106_decrypt(struct aead_request *req)
 	return crypto_aead_decrypt(req);
 }
 
-static int crypto_rfc4106_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc4106_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_aead_spawn *spawn = crypto_instance_ctx(inst);
-	struct crypto_rfc4106_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct crypto_aead_spawn *spawn = aead_instance_ctx(inst);
+	struct crypto_rfc4106_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
 	unsigned long align;
 
@@ -946,126 +865,120 @@ static int crypto_rfc4106_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(
+		tfm,
+		sizeof(struct aead_request) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 12);
 
 	return 0;
 }
 
-static void crypto_rfc4106_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc4106_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_rfc4106_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4106_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
 }
 
-static struct crypto_instance *crypto_rfc4106_alloc(struct rtattr **tb)
+static int crypto_rfc4106_create(struct crypto_template *tmpl,
+				 struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_aead_spawn *spawn;
-	struct crypto_alg *alg;
+	struct aead_alg *alg;
 	const char *ccm_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ccm_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ccm_name))
-		return ERR_CAST(ccm_name);
+		return PTR_ERR(ccm_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	spawn = crypto_instance_ctx(inst);
-	crypto_set_aead_spawn(spawn, inst);
+	spawn = aead_instance_ctx(inst);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
 	err = crypto_grab_aead(spawn, ccm_name, 0,
 			       crypto_requires_sync(algt->type, algt->mask));
 	if (err)
 		goto out_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
+	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
 
-	/* We only support 16-byte blocks. */
-	if (alg->cra_aead.ivsize != 16)
+	/* Underlying IV size must be 12. */
+	if (crypto_aead_alg_ivsize(alg) != 12)
 		goto out_drop_alg;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
+	if (alg->base.cra_blocksize != 1)
 		goto out_drop_alg;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4106(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
-	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4106(%s)", alg->cra_driver_name) >=
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4106(%s)", alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4106(%s)", alg->base.cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_drop_alg;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.base.cra_flags |= alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_aead.ivsize = 8;
-	inst->alg.cra_aead.maxauthsize = 16;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4106_ctx);
+	inst->alg.ivsize = 8;
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_init = crypto_rfc4106_init_tfm;
-	inst->alg.cra_exit = crypto_rfc4106_exit_tfm;
+	inst->alg.init = crypto_rfc4106_init_tfm;
+	inst->alg.exit = crypto_rfc4106_exit_tfm;
 
-	inst->alg.cra_aead.setkey = crypto_rfc4106_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_rfc4106_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_rfc4106_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_rfc4106_decrypt;
+	inst->alg.setkey = crypto_rfc4106_setkey;
+	inst->alg.setauthsize = crypto_rfc4106_setauthsize;
+	inst->alg.encrypt = crypto_rfc4106_encrypt;
+	inst->alg.decrypt = crypto_rfc4106_decrypt;
 
-	inst->alg.cra_aead.geniv = "seqiv";
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
 
 out:
-	return inst;
+	return err;
 
 out_drop_alg:
 	crypto_drop_aead(spawn);
 out_free_inst:
 	kfree(inst);
-	inst = ERR_PTR(err);
 	goto out;
 }
 
 static void crypto_rfc4106_free(struct crypto_instance *inst)
 {
-	crypto_drop_spawn(crypto_instance_ctx(inst));
-	kfree(inst);
+	crypto_drop_aead(crypto_instance_ctx(inst));
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_rfc4106_tmpl = {
 	.name = "rfc4106",
-	.alloc = crypto_rfc4106_alloc,
+	.create = crypto_rfc4106_create,
 	.free = crypto_rfc4106_free,
 	.module = THIS_MODULE,
 };
 
-static inline struct crypto_rfc4543_req_ctx *crypto_rfc4543_reqctx(
-	struct aead_request *req)
-{
-	unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req));
-
-	return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1);
-}
-
 static int crypto_rfc4543_setkey(struct crypto_aead *parent, const u8 *key,
 				 unsigned int keylen)
 {
@@ -1100,83 +1013,35 @@ static int crypto_rfc4543_setauthsize(struct crypto_aead *parent,
 	return crypto_aead_setauthsize(ctx->child, authsize);
 }
 
-static void crypto_rfc4543_done(struct crypto_async_request *areq, int err)
-{
-	struct aead_request *req = areq->data;
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
-
-	if (!err) {
-		scatterwalk_map_and_copy(rctx->auth_tag, req->dst,
-					 req->cryptlen,
-					 crypto_aead_authsize(aead), 1);
-	}
-
-	aead_request_complete(req, err);
-}
-
-static struct aead_request *crypto_rfc4543_crypt(struct aead_request *req,
-						 bool enc)
+static int crypto_rfc4543_crypt(struct aead_request *req, bool enc)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(aead);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
+	struct crypto_rfc4543_req_ctx *rctx = aead_request_ctx(req);
 	struct aead_request *subreq = &rctx->subreq;
-	struct scatterlist *src = req->src;
-	struct scatterlist *cipher = rctx->cipher;
-	struct scatterlist *payload = rctx->payload;
-	struct scatterlist *assoc = rctx->assoc;
 	unsigned int authsize = crypto_aead_authsize(aead);
-	unsigned int assoclen = req->assoclen;
-	struct page *srcp;
-	u8 *vsrc;
 	u8 *iv = PTR_ALIGN((u8 *)(rctx + 1) + crypto_aead_reqsize(ctx->child),
 			   crypto_aead_alignmask(ctx->child) + 1);
+	int err;
+
+	if (req->src != req->dst) {
+		err = crypto_rfc4543_copy_src_to_dst(req, enc);
+		if (err)
+			return err;
+	}
 
 	memcpy(iv, ctx->nonce, 4);
 	memcpy(iv + 4, req->iv, 8);
 
-	/* construct cipher/plaintext */
-	if (enc)
-		memset(rctx->auth_tag, 0, authsize);
-	else
-		scatterwalk_map_and_copy(rctx->auth_tag, src,
-					 req->cryptlen - authsize,
-					 authsize, 0);
-
-	sg_init_one(cipher, rctx->auth_tag, authsize);
-
-	/* construct the aad */
-	srcp = sg_page(src);
-	vsrc = PageHighMem(srcp) ? NULL : page_address(srcp) + src->offset;
-
-	sg_init_table(payload, 2);
-	sg_set_buf(payload, req->iv, 8);
-	scatterwalk_crypto_chain(payload, src, vsrc == req->iv + 8, 2);
-	assoclen += 8 + req->cryptlen - (enc ? 0 : authsize);
-
-	if (req->assoc->length == req->assoclen) {
-		sg_init_table(assoc, 2);
-		sg_set_page(assoc, sg_page(req->assoc), req->assoc->length,
-			    req->assoc->offset);
-	} else {
-		BUG_ON(req->assoclen > sizeof(rctx->assocbuf));
-
-		scatterwalk_map_and_copy(rctx->assocbuf, req->assoc, 0,
-					 req->assoclen, 0);
-
-		sg_init_table(assoc, 2);
-		sg_set_buf(assoc, rctx->assocbuf, req->assoclen);
-	}
-	scatterwalk_crypto_chain(assoc, payload, 0, 2);
-
 	aead_request_set_tfm(subreq, ctx->child);
-	aead_request_set_callback(subreq, req->base.flags, crypto_rfc4543_done,
-				  req);
-	aead_request_set_crypt(subreq, cipher, cipher, enc ? 0 : authsize, iv);
-	aead_request_set_assoc(subreq, assoc, assoclen);
-
-	return subreq;
+	aead_request_set_callback(subreq, req->base.flags,
+				  req->base.complete, req->base.data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       enc ? 0 : authsize, iv);
+	aead_request_set_ad(subreq, req->assoclen + req->cryptlen -
+				    subreq->cryptlen);
+
+	return enc ? crypto_aead_encrypt(subreq) : crypto_aead_decrypt(subreq);
 }
 
 static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
@@ -1184,7 +1049,8 @@ static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(aead);
 	unsigned int authsize = crypto_aead_authsize(aead);
-	unsigned int nbytes = req->cryptlen - (enc ? 0 : authsize);
+	unsigned int nbytes = req->assoclen + req->cryptlen -
+			      (enc ? 0 : authsize);
 	struct blkcipher_desc desc = {
 		.tfm = ctx->null,
 	};
@@ -1194,49 +1060,20 @@ static int crypto_rfc4543_copy_src_to_dst(struct aead_request *req, bool enc)
 
 static int crypto_rfc4543_encrypt(struct aead_request *req)
 {
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
-	struct aead_request *subreq;
-	int err;
-
-	if (req->src != req->dst) {
-		err = crypto_rfc4543_copy_src_to_dst(req, true);
-		if (err)
-			return err;
-	}
-
-	subreq = crypto_rfc4543_crypt(req, true);
-	err = crypto_aead_encrypt(subreq);
-	if (err)
-		return err;
-
-	scatterwalk_map_and_copy(rctx->auth_tag, req->dst, req->cryptlen,
-				 crypto_aead_authsize(aead), 1);
-
-	return 0;
+	return crypto_rfc4543_crypt(req, true);
 }
 
 static int crypto_rfc4543_decrypt(struct aead_request *req)
 {
-	int err;
-
-	if (req->src != req->dst) {
-		err = crypto_rfc4543_copy_src_to_dst(req, false);
-		if (err)
-			return err;
-	}
-
-	req = crypto_rfc4543_crypt(req, false);
-
-	return crypto_aead_decrypt(req);
+	return crypto_rfc4543_crypt(req, false);
 }
 
-static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
+static int crypto_rfc4543_init_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
-	struct crypto_rfc4543_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct crypto_rfc4543_instance_ctx *ictx = aead_instance_ctx(inst);
 	struct crypto_aead_spawn *spawn = &ictx->aead;
-	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *aead;
 	struct crypto_blkcipher *null;
 	unsigned long align;
@@ -1246,7 +1083,7 @@ static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(aead))
 		return PTR_ERR(aead);
 
-	null = crypto_spawn_blkcipher(&ictx->null.base);
+	null = crypto_get_default_null_skcipher();
 	err = PTR_ERR(null);
 	if (IS_ERR(null))
 		goto err_free_aead;
@@ -1256,10 +1093,11 @@ static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
 
 	align = crypto_aead_alignmask(aead);
 	align &= ~(crypto_tfm_ctx_alignment() - 1);
-	tfm->crt_aead.reqsize = sizeof(struct crypto_rfc4543_req_ctx) +
-				ALIGN(crypto_aead_reqsize(aead),
-				      crypto_tfm_ctx_alignment()) +
-				align + 16;
+	crypto_aead_set_reqsize(
+		tfm,
+		sizeof(struct crypto_rfc4543_req_ctx) +
+		ALIGN(crypto_aead_reqsize(aead), crypto_tfm_ctx_alignment()) +
+		align + 12);
 
 	return 0;
 
@@ -1268,107 +1106,98 @@ err_free_aead:
 	return err;
 }
 
-static void crypto_rfc4543_exit_tfm(struct crypto_tfm *tfm)
+static void crypto_rfc4543_exit_tfm(struct crypto_aead *tfm)
 {
-	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
-	crypto_free_blkcipher(ctx->null);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *crypto_rfc4543_alloc(struct rtattr **tb)
+static int crypto_rfc4543_create(struct crypto_template *tmpl,
+				struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
+	struct aead_instance *inst;
 	struct crypto_aead_spawn *spawn;
-	struct crypto_alg *alg;
+	struct aead_alg *alg;
 	struct crypto_rfc4543_instance_ctx *ctx;
 	const char *ccm_name;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ccm_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ccm_name))
-		return ERR_CAST(ccm_name);
+		return PTR_ERR(ccm_name);
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
 	if (!inst)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	ctx = crypto_instance_ctx(inst);
+	ctx = aead_instance_ctx(inst);
 	spawn = &ctx->aead;
-	crypto_set_aead_spawn(spawn, inst);
+	crypto_set_aead_spawn(spawn, aead_crypto_instance(inst));
 	err = crypto_grab_aead(spawn, ccm_name, 0,
 			       crypto_requires_sync(algt->type, algt->mask));
 	if (err)
 		goto out_free_inst;
 
-	alg = crypto_aead_spawn_alg(spawn);
-
-	crypto_set_skcipher_spawn(&ctx->null, inst);
-	err = crypto_grab_skcipher(&ctx->null, "ecb(cipher_null)", 0,
-				   CRYPTO_ALG_ASYNC);
-	if (err)
-		goto out_drop_alg;
-
-	crypto_skcipher_spawn_alg(&ctx->null);
+	alg = crypto_spawn_aead_alg(spawn);
 
 	err = -EINVAL;
 
-	/* We only support 16-byte blocks. */
-	if (alg->cra_aead.ivsize != 16)
-		goto out_drop_ecbnull;
+	/* Underlying IV size must be 12. */
+	if (crypto_aead_alg_ivsize(alg) != 12)
+		goto out_drop_alg;
 
 	/* Not a stream cipher? */
-	if (alg->cra_blocksize != 1)
-		goto out_drop_ecbnull;
+	if (alg->base.cra_blocksize != 1)
+		goto out_drop_alg;
 
 	err = -ENAMETOOLONG;
-	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4543(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
-	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
-		     "rfc4543(%s)", alg->cra_driver_name) >=
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->base.cra_name) >=
+	    CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->base.cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
-		goto out_drop_ecbnull;
+		goto out_drop_alg;
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
-	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
-	inst->alg.cra_priority = alg->cra_priority;
-	inst->alg.cra_blocksize = 1;
-	inst->alg.cra_alignmask = alg->cra_alignmask;
-	inst->alg.cra_type = &crypto_nivaead_type;
+	inst->alg.base.cra_flags = alg->base.cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.base.cra_priority = alg->base.cra_priority;
+	inst->alg.base.cra_blocksize = 1;
+	inst->alg.base.cra_alignmask = alg->base.cra_alignmask;
 
-	inst->alg.cra_aead.ivsize = 8;
-	inst->alg.cra_aead.maxauthsize = 16;
+	inst->alg.base.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
 
-	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
+	inst->alg.ivsize = 8;
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_init = crypto_rfc4543_init_tfm;
-	inst->alg.cra_exit = crypto_rfc4543_exit_tfm;
+	inst->alg.init = crypto_rfc4543_init_tfm;
+	inst->alg.exit = crypto_rfc4543_exit_tfm;
 
-	inst->alg.cra_aead.setkey = crypto_rfc4543_setkey;
-	inst->alg.cra_aead.setauthsize = crypto_rfc4543_setauthsize;
-	inst->alg.cra_aead.encrypt = crypto_rfc4543_encrypt;
-	inst->alg.cra_aead.decrypt = crypto_rfc4543_decrypt;
+	inst->alg.setkey = crypto_rfc4543_setkey;
+	inst->alg.setauthsize = crypto_rfc4543_setauthsize;
+	inst->alg.encrypt = crypto_rfc4543_encrypt;
+	inst->alg.decrypt = crypto_rfc4543_decrypt;
 
-	inst->alg.cra_aead.geniv = "seqiv";
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_alg;
 
 out:
-	return inst;
+	return err;
 
-out_drop_ecbnull:
-	crypto_drop_skcipher(&ctx->null);
 out_drop_alg:
 	crypto_drop_aead(spawn);
 out_free_inst:
 	kfree(inst);
-	inst = ERR_PTR(err);
 	goto out;
 }
 
@@ -1377,14 +1206,13 @@ static void crypto_rfc4543_free(struct crypto_instance *inst)
 	struct crypto_rfc4543_instance_ctx *ctx = crypto_instance_ctx(inst);
 
 	crypto_drop_aead(&ctx->aead);
-	crypto_drop_skcipher(&ctx->null);
 
-	kfree(inst);
+	kfree(aead_instance(inst));
 }
 
 static struct crypto_template crypto_rfc4543_tmpl = {
 	.name = "rfc4543",
-	.alloc = crypto_rfc4543_alloc,
+	.create = crypto_rfc4543_create,
 	.free = crypto_rfc4543_free,
 	.module = THIS_MODULE,
 };
@@ -1393,10 +1221,12 @@ static int __init crypto_gcm_module_init(void)
 {
 	int err;
 
-	gcm_zeroes = kzalloc(16, GFP_KERNEL);
+	gcm_zeroes = kzalloc(sizeof(*gcm_zeroes), GFP_KERNEL);
 	if (!gcm_zeroes)
 		return -ENOMEM;
 
+	sg_init_one(&gcm_zeroes->sg, gcm_zeroes->buf, sizeof(gcm_zeroes->buf));
+
 	err = crypto_register_template(&crypto_gcm_base_tmpl);
 	if (err)
 		goto out;
diff --git a/crypto/internal.h b/crypto/internal.h
index bd39bfc92eab..00e42a3ed814 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -25,7 +25,6 @@
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
-#include <linux/fips.h>
 
 /* Crypto notification events. */
 enum {
@@ -103,6 +102,8 @@ int crypto_register_notifier(struct notifier_block *nb);
 int crypto_unregister_notifier(struct notifier_block *nb);
 int crypto_probing_notify(unsigned long val, void *v);
 
+unsigned int crypto_alg_extsize(struct crypto_alg *alg);
+
 static inline struct crypto_alg *crypto_alg_get(struct crypto_alg *alg)
 {
 	atomic_inc(&alg->cra_refcnt);
diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c
new file mode 100644
index 000000000000..d3c30452edee
--- /dev/null
+++ b/crypto/jitterentropy.c
@@ -0,0 +1,928 @@
+/*
+ * Non-physical true random number generator based on timing jitter.
+ *
+ * Copyright Stephan Mueller <smueller@chronox.de>, 2014
+ *
+ * Design
+ * ======
+ *
+ * See http://www.chronox.de/jent.html
+ *
+ * License
+ * =======
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, and the entire permission notice in its entirety,
+ *    including the disclaimer of warranties.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote
+ *    products derived from this software without specific prior
+ *    written permission.
+ *
+ * ALTERNATIVELY, this product may be distributed under the terms of
+ * the GNU General Public License, in which case the provisions of the GPL2 are
+ * required INSTEAD OF the above restrictions.  (This clause is
+ * necessary due to a potential bad interaction between the GPL and
+ * the restrictions contained in a BSD-style copyright.)
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
+ * WHICH ARE HEREBY DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
+ * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+/*
+ * This Jitterentropy RNG is based on the jitterentropy library
+ * version 1.1.0 provided at http://www.chronox.de/jent.html
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/fips.h>
+#include <linux/time.h>
+#include <linux/crypto.h>
+#include <crypto/internal/rng.h>
+
+/* The entropy pool */
+struct rand_data {
+	/* all data values that are vital to maintain the security
+	 * of the RNG are marked as SENSITIVE. A user must not
+	 * access that information while the RNG executes its loops to
+	 * calculate the next random value. */
+	__u64 data;		/* SENSITIVE Actual random number */
+	__u64 old_data;		/* SENSITIVE Previous random number */
+	__u64 prev_time;	/* SENSITIVE Previous time stamp */
+#define DATA_SIZE_BITS ((sizeof(__u64)) * 8)
+	__u64 last_delta;	/* SENSITIVE stuck test */
+	__s64 last_delta2;	/* SENSITIVE stuck test */
+	unsigned int stuck:1;	/* Time measurement stuck */
+	unsigned int osr;	/* Oversample rate */
+	unsigned int stir:1;		/* Post-processing stirring */
+	unsigned int disable_unbias:1;	/* Deactivate Von-Neuman unbias */
+#define JENT_MEMORY_BLOCKS 64
+#define JENT_MEMORY_BLOCKSIZE 32
+#define JENT_MEMORY_ACCESSLOOPS 128
+#define JENT_MEMORY_SIZE (JENT_MEMORY_BLOCKS*JENT_MEMORY_BLOCKSIZE)
+	unsigned char *mem;	/* Memory access location with size of
+				 * memblocks * memblocksize */
+	unsigned int memlocation; /* Pointer to byte in *mem */
+	unsigned int memblocks;	/* Number of memory blocks in *mem */
+	unsigned int memblocksize; /* Size of one memory block in bytes */
+	unsigned int memaccessloops; /* Number of memory accesses per random
+				      * bit generation */
+};
+
+/* Flags that can be used to initialize the RNG */
+#define JENT_DISABLE_STIR (1<<0) /* Disable stirring the entropy pool */
+#define JENT_DISABLE_UNBIAS (1<<1) /* Disable the Von-Neuman Unbiaser */
+#define JENT_DISABLE_MEMORY_ACCESS (1<<2) /* Disable memory access for more
+					   * entropy, saves MEMORY_SIZE RAM for
+					   * entropy collector */
+
+#define DRIVER_NAME     "jitterentropy"
+
+/* -- error codes for init function -- */
+#define JENT_ENOTIME		1 /* Timer service not available */
+#define JENT_ECOARSETIME	2 /* Timer too coarse for RNG */
+#define JENT_ENOMONOTONIC	3 /* Timer is not monotonic increasing */
+#define JENT_EMINVARIATION	4 /* Timer variations too small for RNG */
+#define JENT_EVARVAR		5 /* Timer does not produce variations of
+				   * variations (2nd derivation of time is
+				   * zero). */
+#define JENT_EMINVARVAR		6 /* Timer variations of variations is tooi
+				   * small. */
+
+/***************************************************************************
+ * Helper functions
+ ***************************************************************************/
+
+static inline void jent_get_nstime(__u64 *out)
+{
+	struct timespec ts;
+	__u64 tmp = 0;
+
+	tmp = random_get_entropy();
+
+	/*
+	 * If random_get_entropy does not return a value (which is possible on,
+	 * for example, MIPS), invoke __getnstimeofday
+	 * hoping that there are timers we can work with.
+	 *
+	 * The list of available timers can be obtained from
+	 * /sys/devices/system/clocksource/clocksource0/available_clocksource
+	 * and are registered with clocksource_register()
+	 */
+	if ((0 == tmp) &&
+	   (0 == __getnstimeofday(&ts))) {
+		tmp = ts.tv_sec;
+		tmp = tmp << 32;
+		tmp = tmp | ts.tv_nsec;
+	}
+
+	*out = tmp;
+}
+
+
+/**
+ * Update of the loop count used for the next round of
+ * an entropy collection.
+ *
+ * Input:
+ * @ec entropy collector struct -- may be NULL
+ * @bits is the number of low bits of the timer to consider
+ * @min is the number of bits we shift the timer value to the right at
+ *	the end to make sure we have a guaranteed minimum value
+ *
+ * @return Newly calculated loop counter
+ */
+static __u64 jent_loop_shuffle(struct rand_data *ec,
+			       unsigned int bits, unsigned int min)
+{
+	__u64 time = 0;
+	__u64 shuffle = 0;
+	unsigned int i = 0;
+	unsigned int mask = (1<<bits) - 1;
+
+	jent_get_nstime(&time);
+	/*
+	 * mix the current state of the random number into the shuffle
+	 * calculation to balance that shuffle a bit more
+	 */
+	if (ec)
+		time ^= ec->data;
+	/*
+	 * we fold the time value as much as possible to ensure that as many
+	 * bits of the time stamp are included as possible
+	 */
+	for (i = 0; (DATA_SIZE_BITS / bits) > i; i++) {
+		shuffle ^= time & mask;
+		time = time >> bits;
+	}
+
+	/*
+	 * We add a lower boundary value to ensure we have a minimum
+	 * RNG loop count.
+	 */
+	return (shuffle + (1<<min));
+}
+
+/***************************************************************************
+ * Noise sources
+ ***************************************************************************/
+
+/*
+ * The disabling of the optimizations is performed as documented and assessed
+ * thoroughly in http://www.chronox.de/jent.html. However, instead of disabling
+ * the optimization of the entire C file, only the main functions the jitter is
+ * measured for are not optimized. These functions include the noise sources as
+ * well as the main functions triggering the noise sources. As the time
+ * measurement is done from one invocation of the jitter noise source to the
+ * next, even the execution jitter of the code invoking the noise sources
+ * contribute to the overall randomness as well. The behavior of the RNG and the
+ * statistical characteristics when only the mentioned functions are not
+ * optimized is almost equal to the a completely non-optimized RNG compilation
+ * as tested with the test tools provided at the initially mentioned web site.
+ */
+
+/**
+ * CPU Jitter noise source -- this is the noise source based on the CPU
+ *			      execution time jitter
+ *
+ * This function folds the time into one bit units by iterating
+ * through the DATA_SIZE_BITS bit time value as follows: assume our time value
+ * is 0xabcd
+ * 1st loop, 1st shift generates 0xd000
+ * 1st loop, 2nd shift generates 0x000d
+ * 2nd loop, 1st shift generates 0xcd00
+ * 2nd loop, 2nd shift generates 0x000c
+ * 3rd loop, 1st shift generates 0xbcd0
+ * 3rd loop, 2nd shift generates 0x000b
+ * 4th loop, 1st shift generates 0xabcd
+ * 4th loop, 2nd shift generates 0x000a
+ * Now, the values at the end of the 2nd shifts are XORed together.
+ *
+ * The code is deliberately inefficient and shall stay that way. This function
+ * is the root cause why the code shall be compiled without optimization. This
+ * function not only acts as folding operation, but this function's execution
+ * is used to measure the CPU execution time jitter. Any change to the loop in
+ * this function implies that careful retesting must be done.
+ *
+ * Input:
+ * @ec entropy collector struct -- may be NULL
+ * @time time stamp to be folded
+ * @loop_cnt if a value not equal to 0 is set, use the given value as number of
+ *	     loops to perform the folding
+ *
+ * Output:
+ * @folded result of folding operation
+ *
+ * @return Number of loops the folding operation is performed
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static __u64 jent_fold_time(struct rand_data *ec, __u64 time,
+			    __u64 *folded, __u64 loop_cnt)
+{
+	unsigned int i;
+	__u64 j = 0;
+	__u64 new = 0;
+#define MAX_FOLD_LOOP_BIT 4
+#define MIN_FOLD_LOOP_BIT 0
+	__u64 fold_loop_cnt =
+		jent_loop_shuffle(ec, MAX_FOLD_LOOP_BIT, MIN_FOLD_LOOP_BIT);
+
+	/*
+	 * testing purposes -- allow test app to set the counter, not
+	 * needed during runtime
+	 */
+	if (loop_cnt)
+		fold_loop_cnt = loop_cnt;
+	for (j = 0; j < fold_loop_cnt; j++) {
+		new = 0;
+		for (i = 1; (DATA_SIZE_BITS) >= i; i++) {
+			__u64 tmp = time << (DATA_SIZE_BITS - i);
+
+			tmp = tmp >> (DATA_SIZE_BITS - 1);
+			new ^= tmp;
+		}
+	}
+	*folded = new;
+	return fold_loop_cnt;
+}
+#pragma GCC pop_options
+
+/**
+ * Memory Access noise source -- this is a noise source based on variations in
+ *				 memory access times
+ *
+ * This function performs memory accesses which will add to the timing
+ * variations due to an unknown amount of CPU wait states that need to be
+ * added when accessing memory. The memory size should be larger than the L1
+ * caches as outlined in the documentation and the associated testing.
+ *
+ * The L1 cache has a very high bandwidth, albeit its access rate is  usually
+ * slower than accessing CPU registers. Therefore, L1 accesses only add minimal
+ * variations as the CPU has hardly to wait. Starting with L2, significant
+ * variations are added because L2 typically does not belong to the CPU any more
+ * and therefore a wider range of CPU wait states is necessary for accesses.
+ * L3 and real memory accesses have even a wider range of wait states. However,
+ * to reliably access either L3 or memory, the ec->mem memory must be quite
+ * large which is usually not desirable.
+ *
+ * Input:
+ * @ec Reference to the entropy collector with the memory access data -- if
+ *     the reference to the memory block to be accessed is NULL, this noise
+ *     source is disabled
+ * @loop_cnt if a value not equal to 0 is set, use the given value as number of
+ *	     loops to perform the folding
+ *
+ * @return Number of memory access operations
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static unsigned int jent_memaccess(struct rand_data *ec, __u64 loop_cnt)
+{
+	unsigned char *tmpval = NULL;
+	unsigned int wrap = 0;
+	__u64 i = 0;
+#define MAX_ACC_LOOP_BIT 7
+#define MIN_ACC_LOOP_BIT 0
+	__u64 acc_loop_cnt =
+		jent_loop_shuffle(ec, MAX_ACC_LOOP_BIT, MIN_ACC_LOOP_BIT);
+
+	if (NULL == ec || NULL == ec->mem)
+		return 0;
+	wrap = ec->memblocksize * ec->memblocks;
+
+	/*
+	 * testing purposes -- allow test app to set the counter, not
+	 * needed during runtime
+	 */
+	if (loop_cnt)
+		acc_loop_cnt = loop_cnt;
+
+	for (i = 0; i < (ec->memaccessloops + acc_loop_cnt); i++) {
+		tmpval = ec->mem + ec->memlocation;
+		/*
+		 * memory access: just add 1 to one byte,
+		 * wrap at 255 -- memory access implies read
+		 * from and write to memory location
+		 */
+		*tmpval = (*tmpval + 1) & 0xff;
+		/*
+		 * Addition of memblocksize - 1 to pointer
+		 * with wrap around logic to ensure that every
+		 * memory location is hit evenly
+		 */
+		ec->memlocation = ec->memlocation + ec->memblocksize - 1;
+		ec->memlocation = ec->memlocation % wrap;
+	}
+	return i;
+}
+#pragma GCC pop_options
+
+/***************************************************************************
+ * Start of entropy processing logic
+ ***************************************************************************/
+
+/**
+ * Stuck test by checking the:
+ *	1st derivation of the jitter measurement (time delta)
+ *	2nd derivation of the jitter measurement (delta of time deltas)
+ *	3rd derivation of the jitter measurement (delta of delta of time deltas)
+ *
+ * All values must always be non-zero.
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ * @current_delta Jitter time delta
+ *
+ * @return
+ *	0 jitter measurement not stuck (good bit)
+ *	1 jitter measurement stuck (reject bit)
+ */
+static void jent_stuck(struct rand_data *ec, __u64 current_delta)
+{
+	__s64 delta2 = ec->last_delta - current_delta;
+	__s64 delta3 = delta2 - ec->last_delta2;
+
+	ec->last_delta = current_delta;
+	ec->last_delta2 = delta2;
+
+	if (!current_delta || !delta2 || !delta3)
+		ec->stuck = 1;
+}
+
+/**
+ * This is the heart of the entropy generation: calculate time deltas and
+ * use the CPU jitter in the time deltas. The jitter is folded into one
+ * bit. You can call this function the "random bit generator" as it
+ * produces one random bit per invocation.
+ *
+ * WARNING: ensure that ->prev_time is primed before using the output
+ *	    of this function! This can be done by calling this function
+ *	    and not using its result.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ *
+ * @return One random bit
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static __u64 jent_measure_jitter(struct rand_data *ec)
+{
+	__u64 time = 0;
+	__u64 data = 0;
+	__u64 current_delta = 0;
+
+	/* Invoke one noise source before time measurement to add variations */
+	jent_memaccess(ec, 0);
+
+	/*
+	 * Get time stamp and calculate time delta to previous
+	 * invocation to measure the timing variations
+	 */
+	jent_get_nstime(&time);
+	current_delta = time - ec->prev_time;
+	ec->prev_time = time;
+
+	/* Now call the next noise sources which also folds the data */
+	jent_fold_time(ec, current_delta, &data, 0);
+
+	/*
+	 * Check whether we have a stuck measurement. The enforcement
+	 * is performed after the stuck value has been mixed into the
+	 * entropy pool.
+	 */
+	jent_stuck(ec, current_delta);
+
+	return data;
+}
+#pragma GCC pop_options
+
+/**
+ * Von Neuman unbias as explained in RFC 4086 section 4.2. As shown in the
+ * documentation of that RNG, the bits from jent_measure_jitter are considered
+ * independent which implies that the Von Neuman unbias operation is applicable.
+ * A proof of the Von-Neumann unbias operation to remove skews is given in the
+ * document "A proposal for: Functionality classes for random number
+ * generators", version 2.0 by Werner Schindler, section 5.4.1.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ *
+ * @return One random bit
+ */
+static __u64 jent_unbiased_bit(struct rand_data *entropy_collector)
+{
+	do {
+		__u64 a = jent_measure_jitter(entropy_collector);
+		__u64 b = jent_measure_jitter(entropy_collector);
+
+		if (a == b)
+			continue;
+		if (1 == a)
+			return 1;
+		else
+			return 0;
+	} while (1);
+}
+
+/**
+ * Shuffle the pool a bit by mixing some value with a bijective function (XOR)
+ * into the pool.
+ *
+ * The function generates a mixer value that depends on the bits set and the
+ * location of the set bits in the random number generated by the entropy
+ * source. Therefore, based on the generated random number, this mixer value
+ * can have 2**64 different values. That mixer value is initialized with the
+ * first two SHA-1 constants. After obtaining the mixer value, it is XORed into
+ * the random number.
+ *
+ * The mixer value is not assumed to contain any entropy. But due to the XOR
+ * operation, it can also not destroy any entropy present in the entropy pool.
+ *
+ * Input:
+ * @entropy_collector Reference to entropy collector
+ */
+static void jent_stir_pool(struct rand_data *entropy_collector)
+{
+	/*
+	 * to shut up GCC on 32 bit, we have to initialize the 64 variable
+	 * with two 32 bit variables
+	 */
+	union c {
+		__u64 u64;
+		__u32 u32[2];
+	};
+	/*
+	 * This constant is derived from the first two 32 bit initialization
+	 * vectors of SHA-1 as defined in FIPS 180-4 section 5.3.1
+	 */
+	union c constant;
+	/*
+	 * The start value of the mixer variable is derived from the third
+	 * and fourth 32 bit initialization vector of SHA-1 as defined in
+	 * FIPS 180-4 section 5.3.1
+	 */
+	union c mixer;
+	unsigned int i = 0;
+
+	/*
+	 * Store the SHA-1 constants in reverse order to make up the 64 bit
+	 * value -- this applies to a little endian system, on a big endian
+	 * system, it reverses as expected. But this really does not matter
+	 * as we do not rely on the specific numbers. We just pick the SHA-1
+	 * constants as they have a good mix of bit set and unset.
+	 */
+	constant.u32[1] = 0x67452301;
+	constant.u32[0] = 0xefcdab89;
+	mixer.u32[1] = 0x98badcfe;
+	mixer.u32[0] = 0x10325476;
+
+	for (i = 0; i < DATA_SIZE_BITS; i++) {
+		/*
+		 * get the i-th bit of the input random number and only XOR
+		 * the constant into the mixer value when that bit is set
+		 */
+		if ((entropy_collector->data >> i) & 1)
+			mixer.u64 ^= constant.u64;
+		mixer.u64 = rol64(mixer.u64, 1);
+	}
+	entropy_collector->data ^= mixer.u64;
+}
+
+/**
+ * Generator of one 64 bit random number
+ * Function fills rand_data->data
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ */
+#pragma GCC push_options
+#pragma GCC optimize ("-O0")
+static void jent_gen_entropy(struct rand_data *ec)
+{
+	unsigned int k = 0;
+
+	/* priming of the ->prev_time value */
+	jent_measure_jitter(ec);
+
+	while (1) {
+		__u64 data = 0;
+
+		if (ec->disable_unbias == 1)
+			data = jent_measure_jitter(ec);
+		else
+			data = jent_unbiased_bit(ec);
+
+		/* enforcement of the jent_stuck test */
+		if (ec->stuck) {
+			/*
+			 * We only mix in the bit considered not appropriate
+			 * without the LSFR. The reason is that if we apply
+			 * the LSFR and we do not rotate, the 2nd bit with LSFR
+			 * will cancel out the first LSFR application on the
+			 * bad bit.
+			 *
+			 * And we do not rotate as we apply the next bit to the
+			 * current bit location again.
+			 */
+			ec->data ^= data;
+			ec->stuck = 0;
+			continue;
+		}
+
+		/*
+		 * Fibonacci LSFR with polynom of
+		 *  x^64 + x^61 + x^56 + x^31 + x^28 + x^23 + 1 which is
+		 *  primitive according to
+		 *   http://poincare.matf.bg.ac.rs/~ezivkovm/publications/primpol1.pdf
+		 * (the shift values are the polynom values minus one
+		 * due to counting bits from 0 to 63). As the current
+		 * position is always the LSB, the polynom only needs
+		 * to shift data in from the left without wrap.
+		 */
+		ec->data ^= data;
+		ec->data ^= ((ec->data >> 63) & 1);
+		ec->data ^= ((ec->data >> 60) & 1);
+		ec->data ^= ((ec->data >> 55) & 1);
+		ec->data ^= ((ec->data >> 30) & 1);
+		ec->data ^= ((ec->data >> 27) & 1);
+		ec->data ^= ((ec->data >> 22) & 1);
+		ec->data = rol64(ec->data, 1);
+
+		/*
+		 * We multiply the loop value with ->osr to obtain the
+		 * oversampling rate requested by the caller
+		 */
+		if (++k >= (DATA_SIZE_BITS * ec->osr))
+			break;
+	}
+	if (ec->stir)
+		jent_stir_pool(ec);
+}
+#pragma GCC pop_options
+
+/**
+ * The continuous test required by FIPS 140-2 -- the function automatically
+ * primes the test if needed.
+ *
+ * Return:
+ * 0 if FIPS test passed
+ * < 0 if FIPS test failed
+ */
+static void jent_fips_test(struct rand_data *ec)
+{
+	if (!fips_enabled)
+		return;
+
+	/* prime the FIPS test */
+	if (!ec->old_data) {
+		ec->old_data = ec->data;
+		jent_gen_entropy(ec);
+	}
+
+	if (ec->data == ec->old_data)
+		panic(DRIVER_NAME ": Duplicate output detected\n");
+
+	ec->old_data = ec->data;
+}
+
+
+/**
+ * Entry function: Obtain entropy for the caller.
+ *
+ * This function invokes the entropy gathering logic as often to generate
+ * as many bytes as requested by the caller. The entropy gathering logic
+ * creates 64 bit per invocation.
+ *
+ * This function truncates the last 64 bit entropy value output to the exact
+ * size specified by the caller.
+ *
+ * Input:
+ * @ec Reference to entropy collector
+ * @data pointer to buffer for storing random data -- buffer must already
+ *	 exist
+ * @len size of the buffer, specifying also the requested number of random
+ *	in bytes
+ *
+ * @return 0 when request is fulfilled or an error
+ *
+ * The following error codes can occur:
+ *	-1	entropy_collector is NULL
+ */
+static ssize_t jent_read_entropy(struct rand_data *ec, u8 *data, size_t len)
+{
+	u8 *p = data;
+
+	if (!ec)
+		return -EINVAL;
+
+	while (0 < len) {
+		size_t tocopy;
+
+		jent_gen_entropy(ec);
+		jent_fips_test(ec);
+		if ((DATA_SIZE_BITS / 8) < len)
+			tocopy = (DATA_SIZE_BITS / 8);
+		else
+			tocopy = len;
+		memcpy(p, &ec->data, tocopy);
+
+		len -= tocopy;
+		p += tocopy;
+	}
+
+	return 0;
+}
+
+/***************************************************************************
+ * Initialization logic
+ ***************************************************************************/
+
+static struct rand_data *jent_entropy_collector_alloc(unsigned int osr,
+						      unsigned int flags)
+{
+	struct rand_data *entropy_collector;
+
+	entropy_collector = kzalloc(sizeof(struct rand_data), GFP_KERNEL);
+	if (!entropy_collector)
+		return NULL;
+
+	if (!(flags & JENT_DISABLE_MEMORY_ACCESS)) {
+		/* Allocate memory for adding variations based on memory
+		 * access
+		 */
+		entropy_collector->mem = kzalloc(JENT_MEMORY_SIZE, GFP_KERNEL);
+		if (!entropy_collector->mem) {
+			kfree(entropy_collector);
+			return NULL;
+		}
+		entropy_collector->memblocksize = JENT_MEMORY_BLOCKSIZE;
+		entropy_collector->memblocks = JENT_MEMORY_BLOCKS;
+		entropy_collector->memaccessloops = JENT_MEMORY_ACCESSLOOPS;
+	}
+
+	/* verify and set the oversampling rate */
+	if (0 == osr)
+		osr = 1; /* minimum sampling rate is 1 */
+	entropy_collector->osr = osr;
+
+	entropy_collector->stir = 1;
+	if (flags & JENT_DISABLE_STIR)
+		entropy_collector->stir = 0;
+	if (flags & JENT_DISABLE_UNBIAS)
+		entropy_collector->disable_unbias = 1;
+
+	/* fill the data pad with non-zero values */
+	jent_gen_entropy(entropy_collector);
+
+	return entropy_collector;
+}
+
+static void jent_entropy_collector_free(struct rand_data *entropy_collector)
+{
+	if (entropy_collector->mem)
+		kzfree(entropy_collector->mem);
+	entropy_collector->mem = NULL;
+	if (entropy_collector)
+		kzfree(entropy_collector);
+	entropy_collector = NULL;
+}
+
+static int jent_entropy_init(void)
+{
+	int i;
+	__u64 delta_sum = 0;
+	__u64 old_delta = 0;
+	int time_backwards = 0;
+	int count_var = 0;
+	int count_mod = 0;
+
+	/* We could perform statistical tests here, but the problem is
+	 * that we only have a few loop counts to do testing. These
+	 * loop counts may show some slight skew and we produce
+	 * false positives.
+	 *
+	 * Moreover, only old systems show potentially problematic
+	 * jitter entropy that could potentially be caught here. But
+	 * the RNG is intended for hardware that is available or widely
+	 * used, but not old systems that are long out of favor. Thus,
+	 * no statistical tests.
+	 */
+
+	/*
+	 * We could add a check for system capabilities such as clock_getres or
+	 * check for CONFIG_X86_TSC, but it does not make much sense as the
+	 * following sanity checks verify that we have a high-resolution
+	 * timer.
+	 */
+	/*
+	 * TESTLOOPCOUNT needs some loops to identify edge systems. 100 is
+	 * definitely too little.
+	 */
+#define TESTLOOPCOUNT 300
+#define CLEARCACHE 100
+	for (i = 0; (TESTLOOPCOUNT + CLEARCACHE) > i; i++) {
+		__u64 time = 0;
+		__u64 time2 = 0;
+		__u64 folded = 0;
+		__u64 delta = 0;
+		unsigned int lowdelta = 0;
+
+		jent_get_nstime(&time);
+		jent_fold_time(NULL, time, &folded, 1<<MIN_FOLD_LOOP_BIT);
+		jent_get_nstime(&time2);
+
+		/* test whether timer works */
+		if (!time || !time2)
+			return JENT_ENOTIME;
+		delta = time2 - time;
+		/*
+		 * test whether timer is fine grained enough to provide
+		 * delta even when called shortly after each other -- this
+		 * implies that we also have a high resolution timer
+		 */
+		if (!delta)
+			return JENT_ECOARSETIME;
+
+		/*
+		 * up to here we did not modify any variable that will be
+		 * evaluated later, but we already performed some work. Thus we
+		 * already have had an impact on the caches, branch prediction,
+		 * etc. with the goal to clear it to get the worst case
+		 * measurements.
+		 */
+		if (CLEARCACHE > i)
+			continue;
+
+		/* test whether we have an increasing timer */
+		if (!(time2 > time))
+			time_backwards++;
+
+		/*
+		 * Avoid modulo of 64 bit integer to allow code to compile
+		 * on 32 bit architectures.
+		 */
+		lowdelta = time2 - time;
+		if (!(lowdelta % 100))
+			count_mod++;
+
+		/*
+		 * ensure that we have a varying delta timer which is necessary
+		 * for the calculation of entropy -- perform this check
+		 * only after the first loop is executed as we need to prime
+		 * the old_data value
+		 */
+		if (i) {
+			if (delta != old_delta)
+				count_var++;
+			if (delta > old_delta)
+				delta_sum += (delta - old_delta);
+			else
+				delta_sum += (old_delta - delta);
+		}
+		old_delta = delta;
+	}
+
+	/*
+	 * we allow up to three times the time running backwards.
+	 * CLOCK_REALTIME is affected by adjtime and NTP operations. Thus,
+	 * if such an operation just happens to interfere with our test, it
+	 * should not fail. The value of 3 should cover the NTP case being
+	 * performed during our test run.
+	 */
+	if (3 < time_backwards)
+		return JENT_ENOMONOTONIC;
+	/* Error if the time variances are always identical */
+	if (!delta_sum)
+		return JENT_EVARVAR;
+
+	/*
+	 * Variations of deltas of time must on average be larger
+	 * than 1 to ensure the entropy estimation
+	 * implied with 1 is preserved
+	 */
+	if (delta_sum <= 1)
+		return JENT_EMINVARVAR;
+
+	/*
+	 * Ensure that we have variations in the time stamp below 10 for at
+	 * least 10% of all checks -- on some platforms, the counter
+	 * increments in multiples of 100, but not always
+	 */
+	if ((TESTLOOPCOUNT/10 * 9) < count_mod)
+		return JENT_ECOARSETIME;
+
+	return 0;
+}
+
+/***************************************************************************
+ * Kernel crypto API interface
+ ***************************************************************************/
+
+struct jitterentropy {
+	spinlock_t jent_lock;
+	struct rand_data *entropy_collector;
+};
+
+static int jent_kcapi_init(struct crypto_tfm *tfm)
+{
+	struct jitterentropy *rng = crypto_tfm_ctx(tfm);
+	int ret = 0;
+
+	rng->entropy_collector = jent_entropy_collector_alloc(1, 0);
+	if (!rng->entropy_collector)
+		ret = -ENOMEM;
+
+	spin_lock_init(&rng->jent_lock);
+	return ret;
+}
+
+static void jent_kcapi_cleanup(struct crypto_tfm *tfm)
+{
+	struct jitterentropy *rng = crypto_tfm_ctx(tfm);
+
+	spin_lock(&rng->jent_lock);
+	if (rng->entropy_collector)
+		jent_entropy_collector_free(rng->entropy_collector);
+	rng->entropy_collector = NULL;
+	spin_unlock(&rng->jent_lock);
+}
+
+static int jent_kcapi_random(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *rdata, unsigned int dlen)
+{
+	struct jitterentropy *rng = crypto_rng_ctx(tfm);
+	int ret = 0;
+
+	spin_lock(&rng->jent_lock);
+	ret = jent_read_entropy(rng->entropy_collector, rdata, dlen);
+	spin_unlock(&rng->jent_lock);
+
+	return ret;
+}
+
+static int jent_kcapi_reset(struct crypto_rng *tfm,
+			    const u8 *seed, unsigned int slen)
+{
+	return 0;
+}
+
+static struct rng_alg jent_alg = {
+	.generate		= jent_kcapi_random,
+	.seed			= jent_kcapi_reset,
+	.seedsize		= 0,
+	.base			= {
+		.cra_name               = "jitterentropy_rng",
+		.cra_driver_name        = "jitterentropy_rng",
+		.cra_priority           = 100,
+		.cra_ctxsize            = sizeof(struct jitterentropy),
+		.cra_module             = THIS_MODULE,
+		.cra_init               = jent_kcapi_init,
+		.cra_exit               = jent_kcapi_cleanup,
+
+	}
+};
+
+static int __init jent_mod_init(void)
+{
+	int ret = 0;
+
+	ret = jent_entropy_init();
+	if (ret) {
+		pr_info(DRIVER_NAME ": Initialization failed with host not compliant with requirements: %d\n", ret);
+		return -EFAULT;
+	}
+	return crypto_register_rng(&jent_alg);
+}
+
+static void __exit jent_mod_exit(void)
+{
+	crypto_unregister_rng(&jent_alg);
+}
+
+module_init(jent_mod_init);
+module_exit(jent_mod_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>");
+MODULE_DESCRIPTION("Non-physical True Random Number Generator based on CPU Jitter");
+MODULE_ALIAS_CRYPTO("jitterentropy_rng");
diff --git a/crypto/krng.c b/crypto/krng.c
deleted file mode 100644
index 0224841b6579..000000000000
--- a/crypto/krng.c
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * RNG implementation using standard kernel RNG.
- *
- * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * any later version.
- *
- */
-
-#include <crypto/internal/rng.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/random.h>
-
-static int krng_get_random(struct crypto_rng *tfm, u8 *rdata, unsigned int dlen)
-{
-	get_random_bytes(rdata, dlen);
-	return 0;
-}
-
-static int krng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
-{
-	return 0;
-}
-
-static struct crypto_alg krng_alg = {
-	.cra_name		= "stdrng",
-	.cra_driver_name	= "krng",
-	.cra_priority		= 200,
-	.cra_flags		= CRYPTO_ALG_TYPE_RNG,
-	.cra_ctxsize		= 0,
-	.cra_type		= &crypto_rng_type,
-	.cra_module		= THIS_MODULE,
-	.cra_u			= {
-		.rng = {
-			.rng_make_random	= krng_get_random,
-			.rng_reset		= krng_reset,
-			.seedsize		= 0,
-		}
-	}
-};
-
-
-/* Module initalization */
-static int __init krng_mod_init(void)
-{
-	return crypto_register_alg(&krng_alg);
-}
-
-static void __exit krng_mod_fini(void)
-{
-	crypto_unregister_alg(&krng_alg);
-	return;
-}
-
-module_init(krng_mod_init);
-module_exit(krng_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS_CRYPTO("stdrng");
-MODULE_ALIAS_CRYPTO("krng");
diff --git a/crypto/md5.c b/crypto/md5.c
index 36f5e5b103f3..33d17e9a8702 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -51,10 +51,10 @@ static int md5_init(struct shash_desc *desc)
 {
 	struct md5_state *mctx = shash_desc_ctx(desc);
 
-	mctx->hash[0] = 0x67452301;
-	mctx->hash[1] = 0xefcdab89;
-	mctx->hash[2] = 0x98badcfe;
-	mctx->hash[3] = 0x10325476;
+	mctx->hash[0] = MD5_H0;
+	mctx->hash[1] = MD5_H1;
+	mctx->hash[2] = MD5_H2;
+	mctx->hash[3] = MD5_H3;
 	mctx->byte_count = 0;
 
 	return 0;
diff --git a/crypto/pcompress.c b/crypto/pcompress.c
index 7140fe70c7af..7a13b4088857 100644
--- a/crypto/pcompress.c
+++ b/crypto/pcompress.c
@@ -38,11 +38,6 @@ static int crypto_pcomp_init(struct crypto_tfm *tfm, u32 type, u32 mask)
 	return 0;
 }
 
-static unsigned int crypto_pcomp_extsize(struct crypto_alg *alg)
-{
-	return alg->cra_ctxsize;
-}
-
 static int crypto_pcomp_init_tfm(struct crypto_tfm *tfm)
 {
 	return 0;
@@ -77,7 +72,7 @@ static void crypto_pcomp_show(struct seq_file *m, struct crypto_alg *alg)
 }
 
 static const struct crypto_type crypto_pcomp_type = {
-	.extsize	= crypto_pcomp_extsize,
+	.extsize	= crypto_alg_extsize,
 	.init		= crypto_pcomp_init,
 	.init_tfm	= crypto_pcomp_init_tfm,
 #ifdef CONFIG_PROC_FS
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index c305d4112735..45e7d5155672 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -20,6 +20,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/aead.h>
+#include <linux/atomic.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -60,8 +61,8 @@ static struct padata_pcrypt pdecrypt;
 static struct kset           *pcrypt_kset;
 
 struct pcrypt_instance_ctx {
-	struct crypto_spawn spawn;
-	unsigned int tfm_count;
+	struct crypto_aead_spawn spawn;
+	atomic_t tfm_count;
 };
 
 struct pcrypt_aead_ctx {
@@ -122,14 +123,6 @@ static void pcrypt_aead_serial(struct padata_priv *padata)
 	aead_request_complete(req->base.data, padata->info);
 }
 
-static void pcrypt_aead_giv_serial(struct padata_priv *padata)
-{
-	struct pcrypt_request *preq = pcrypt_padata_request(padata);
-	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
-
-	aead_request_complete(req->areq.base.data, padata->info);
-}
-
 static void pcrypt_aead_done(struct crypto_async_request *areq, int err)
 {
 	struct aead_request *req = areq->data;
@@ -175,7 +168,7 @@ static int pcrypt_aead_encrypt(struct aead_request *req)
 				  pcrypt_aead_done, req);
 	aead_request_set_crypt(creq, req->src, req->dst,
 			       req->cryptlen, req->iv);
-	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+	aead_request_set_ad(creq, req->assoclen);
 
 	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pencrypt);
 	if (!err)
@@ -217,7 +210,7 @@ static int pcrypt_aead_decrypt(struct aead_request *req)
 				  pcrypt_aead_done, req);
 	aead_request_set_crypt(creq, req->src, req->dst,
 			       req->cryptlen, req->iv);
-	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+	aead_request_set_ad(creq, req->assoclen);
 
 	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pdecrypt);
 	if (!err)
@@ -226,182 +219,134 @@ static int pcrypt_aead_decrypt(struct aead_request *req)
 	return err;
 }
 
-static void pcrypt_aead_givenc(struct padata_priv *padata)
-{
-	struct pcrypt_request *preq = pcrypt_padata_request(padata);
-	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
-
-	padata->info = crypto_aead_givencrypt(req);
-
-	if (padata->info == -EINPROGRESS)
-		return;
-
-	padata_do_serial(padata);
-}
-
-static int pcrypt_aead_givencrypt(struct aead_givcrypt_request *req)
-{
-	int err;
-	struct aead_request *areq = &req->areq;
-	struct pcrypt_request *preq = aead_request_ctx(areq);
-	struct aead_givcrypt_request *creq = pcrypt_request_ctx(preq);
-	struct padata_priv *padata = pcrypt_request_padata(preq);
-	struct crypto_aead *aead = aead_givcrypt_reqtfm(req);
-	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
-	u32 flags = aead_request_flags(areq);
-
-	memset(padata, 0, sizeof(struct padata_priv));
-
-	padata->parallel = pcrypt_aead_givenc;
-	padata->serial = pcrypt_aead_giv_serial;
-
-	aead_givcrypt_set_tfm(creq, ctx->child);
-	aead_givcrypt_set_callback(creq, flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
-				   pcrypt_aead_done, areq);
-	aead_givcrypt_set_crypt(creq, areq->src, areq->dst,
-				areq->cryptlen, areq->iv);
-	aead_givcrypt_set_assoc(creq, areq->assoc, areq->assoclen);
-	aead_givcrypt_set_giv(creq, req->giv, req->seq);
-
-	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, &pencrypt);
-	if (!err)
-		return -EINPROGRESS;
-
-	return err;
-}
-
-static int pcrypt_aead_init_tfm(struct crypto_tfm *tfm)
+static int pcrypt_aead_init_tfm(struct crypto_aead *tfm)
 {
 	int cpu, cpu_index;
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct pcrypt_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct aead_instance *inst = aead_alg_instance(tfm);
+	struct pcrypt_instance_ctx *ictx = aead_instance_ctx(inst);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct crypto_aead *cipher;
 
-	ictx->tfm_count++;
-
-	cpu_index = ictx->tfm_count % cpumask_weight(cpu_online_mask);
+	cpu_index = (unsigned int)atomic_inc_return(&ictx->tfm_count) %
+		    cpumask_weight(cpu_online_mask);
 
 	ctx->cb_cpu = cpumask_first(cpu_online_mask);
 	for (cpu = 0; cpu < cpu_index; cpu++)
 		ctx->cb_cpu = cpumask_next(ctx->cb_cpu, cpu_online_mask);
 
-	cipher = crypto_spawn_aead(crypto_instance_ctx(inst));
+	cipher = crypto_spawn_aead(&ictx->spawn);
 
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
 	ctx->child = cipher;
-	tfm->crt_aead.reqsize = sizeof(struct pcrypt_request)
-		+ sizeof(struct aead_givcrypt_request)
-		+ crypto_aead_reqsize(cipher);
+	crypto_aead_set_reqsize(tfm, sizeof(struct pcrypt_request) +
+				     sizeof(struct aead_request) +
+				     crypto_aead_reqsize(cipher));
 
 	return 0;
 }
 
-static void pcrypt_aead_exit_tfm(struct crypto_tfm *tfm)
+static void pcrypt_aead_exit_tfm(struct crypto_aead *tfm)
 {
-	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(tfm);
 
 	crypto_free_aead(ctx->child);
 }
 
-static struct crypto_instance *pcrypt_alloc_instance(struct crypto_alg *alg)
+static int pcrypt_init_instance(struct crypto_instance *inst,
+				struct crypto_alg *alg)
 {
-	struct crypto_instance *inst;
-	struct pcrypt_instance_ctx *ctx;
-	int err;
-
-	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
-	if (!inst) {
-		inst = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "pcrypt(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
-		goto out_free_inst;
+		return -ENAMETOOLONG;
 
 	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
 
-	ctx = crypto_instance_ctx(inst);
-	err = crypto_init_spawn(&ctx->spawn, alg, inst,
-				CRYPTO_ALG_TYPE_MASK);
-	if (err)
-		goto out_free_inst;
-
 	inst->alg.cra_priority = alg->cra_priority + 100;
 	inst->alg.cra_blocksize = alg->cra_blocksize;
 	inst->alg.cra_alignmask = alg->cra_alignmask;
 
-out:
-	return inst;
-
-out_free_inst:
-	kfree(inst);
-	inst = ERR_PTR(err);
-	goto out;
+	return 0;
 }
 
-static struct crypto_instance *pcrypt_alloc_aead(struct rtattr **tb,
-						 u32 type, u32 mask)
+static int pcrypt_create_aead(struct crypto_template *tmpl, struct rtattr **tb,
+			      u32 type, u32 mask)
 {
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
+	struct pcrypt_instance_ctx *ctx;
+	struct aead_instance *inst;
+	struct aead_alg *alg;
+	const char *name;
+	int err;
+
+	name = crypto_attr_alg_name(tb[1]);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	ctx = aead_instance_ctx(inst);
+	crypto_set_aead_spawn(&ctx->spawn, aead_crypto_instance(inst));
+
+	err = crypto_grab_aead(&ctx->spawn, name, 0, 0);
+	if (err)
+		goto out_free_inst;
 
-	alg = crypto_get_attr_alg(tb, type, (mask & CRYPTO_ALG_TYPE_MASK));
-	if (IS_ERR(alg))
-		return ERR_CAST(alg);
+	alg = crypto_spawn_aead_alg(&ctx->spawn);
+	err = pcrypt_init_instance(aead_crypto_instance(inst), &alg->base);
+	if (err)
+		goto out_drop_aead;
 
-	inst = pcrypt_alloc_instance(alg);
-	if (IS_ERR(inst))
-		goto out_put_alg;
+	inst->alg.ivsize = crypto_aead_alg_ivsize(alg);
+	inst->alg.maxauthsize = crypto_aead_alg_maxauthsize(alg);
 
-	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
-	inst->alg.cra_type = &crypto_aead_type;
+	inst->alg.base.cra_ctxsize = sizeof(struct pcrypt_aead_ctx);
 
-	inst->alg.cra_aead.ivsize = alg->cra_aead.ivsize;
-	inst->alg.cra_aead.geniv = alg->cra_aead.geniv;
-	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
+	inst->alg.init = pcrypt_aead_init_tfm;
+	inst->alg.exit = pcrypt_aead_exit_tfm;
 
-	inst->alg.cra_ctxsize = sizeof(struct pcrypt_aead_ctx);
+	inst->alg.setkey = pcrypt_aead_setkey;
+	inst->alg.setauthsize = pcrypt_aead_setauthsize;
+	inst->alg.encrypt = pcrypt_aead_encrypt;
+	inst->alg.decrypt = pcrypt_aead_decrypt;
 
-	inst->alg.cra_init = pcrypt_aead_init_tfm;
-	inst->alg.cra_exit = pcrypt_aead_exit_tfm;
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto out_drop_aead;
 
-	inst->alg.cra_aead.setkey = pcrypt_aead_setkey;
-	inst->alg.cra_aead.setauthsize = pcrypt_aead_setauthsize;
-	inst->alg.cra_aead.encrypt = pcrypt_aead_encrypt;
-	inst->alg.cra_aead.decrypt = pcrypt_aead_decrypt;
-	inst->alg.cra_aead.givencrypt = pcrypt_aead_givencrypt;
+out:
+	return err;
 
-out_put_alg:
-	crypto_mod_put(alg);
-	return inst;
+out_drop_aead:
+	crypto_drop_aead(&ctx->spawn);
+out_free_inst:
+	kfree(inst);
+	goto out;
 }
 
-static struct crypto_instance *pcrypt_alloc(struct rtattr **tb)
+static int pcrypt_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
+		return PTR_ERR(algt);
 
 	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
 	case CRYPTO_ALG_TYPE_AEAD:
-		return pcrypt_alloc_aead(tb, algt->type, algt->mask);
+		return pcrypt_create_aead(tmpl, tb, algt->type, algt->mask);
 	}
 
-	return ERR_PTR(-EINVAL);
+	return -EINVAL;
 }
 
 static void pcrypt_free(struct crypto_instance *inst)
 {
 	struct pcrypt_instance_ctx *ctx = crypto_instance_ctx(inst);
 
-	crypto_drop_spawn(&ctx->spawn);
+	crypto_drop_aead(&ctx->spawn);
 	kfree(inst);
 }
 
@@ -516,7 +461,7 @@ static void pcrypt_fini_padata(struct padata_pcrypt *pcrypt)
 
 static struct crypto_template pcrypt_tmpl = {
 	.name = "pcrypt",
-	.alloc = pcrypt_alloc,
+	.create = pcrypt_create,
 	.free = pcrypt_free,
 	.module = THIS_MODULE,
 };
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
new file mode 100644
index 000000000000..387b5c887a80
--- /dev/null
+++ b/crypto/poly1305_generic.c
@@ -0,0 +1,321 @@
+/*
+ * Poly1305 authenticator algorithm, RFC7539
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * Based on public domain code by Andrew Moon and Daniel J. Bernstein.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#define POLY1305_BLOCK_SIZE	16
+#define POLY1305_KEY_SIZE	32
+#define POLY1305_DIGEST_SIZE	16
+
+struct poly1305_desc_ctx {
+	/* key */
+	u32 r[5];
+	/* finalize key */
+	u32 s[4];
+	/* accumulator */
+	u32 h[5];
+	/* partial buffer */
+	u8 buf[POLY1305_BLOCK_SIZE];
+	/* bytes used in partial buffer */
+	unsigned int buflen;
+	/* r key has been set */
+	bool rset;
+	/* s key has been set */
+	bool sset;
+};
+
+static inline u64 mlt(u64 a, u64 b)
+{
+	return a * b;
+}
+
+static inline u32 sr(u64 v, u_char n)
+{
+	return v >> n;
+}
+
+static inline u32 and(u32 v, u32 mask)
+{
+	return v & mask;
+}
+
+static inline u32 le32_to_cpuvp(const void *p)
+{
+	return le32_to_cpup(p);
+}
+
+static int poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memset(dctx->h, 0, sizeof(dctx->h));
+	dctx->buflen = 0;
+	dctx->rset = false;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static int poly1305_setkey(struct crypto_shash *tfm,
+			   const u8 *key, unsigned int keylen)
+{
+	/* Poly1305 requires a unique key for each tag, which implies that
+	 * we can't set it on the tfm that gets accessed by multiple users
+	 * simultaneously. Instead we expect the key as the first 32 bytes in
+	 * the update() call. */
+	return -ENOTSUPP;
+}
+
+static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+	dctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
+	dctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
+	dctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
+	dctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
+	dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+}
+
+static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
+{
+	dctx->s[0] = le32_to_cpuvp(key +  0);
+	dctx->s[1] = le32_to_cpuvp(key +  4);
+	dctx->s[2] = le32_to_cpuvp(key +  8);
+	dctx->s[3] = le32_to_cpuvp(key + 12);
+}
+
+static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, unsigned int srclen,
+				    u32 hibit)
+{
+	u32 r0, r1, r2, r3, r4;
+	u32 s1, s2, s3, s4;
+	u32 h0, h1, h2, h3, h4;
+	u64 d0, d1, d2, d3, d4;
+
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_setrkey(dctx, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->rset = true;
+		}
+		if (srclen >= POLY1305_BLOCK_SIZE) {
+			poly1305_setskey(dctx, src);
+			src += POLY1305_BLOCK_SIZE;
+			srclen -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+	}
+
+	r0 = dctx->r[0];
+	r1 = dctx->r[1];
+	r2 = dctx->r[2];
+	r3 = dctx->r[3];
+	r4 = dctx->r[4];
+
+	s1 = r1 * 5;
+	s2 = r2 * 5;
+	s3 = r3 * 5;
+	s4 = r4 * 5;
+
+	h0 = dctx->h[0];
+	h1 = dctx->h[1];
+	h2 = dctx->h[2];
+	h3 = dctx->h[3];
+	h4 = dctx->h[4];
+
+	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+
+		/* h += m[i] */
+		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
+		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
+		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
+		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
+		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+
+		/* h *= r */
+		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
+		     mlt(h3, s2) + mlt(h4, s1);
+		d1 = mlt(h0, r1) + mlt(h1, r0) + mlt(h2, s4) +
+		     mlt(h3, s3) + mlt(h4, s2);
+		d2 = mlt(h0, r2) + mlt(h1, r1) + mlt(h2, r0) +
+		     mlt(h3, s4) + mlt(h4, s3);
+		d3 = mlt(h0, r3) + mlt(h1, r2) + mlt(h2, r1) +
+		     mlt(h3, r0) + mlt(h4, s4);
+		d4 = mlt(h0, r4) + mlt(h1, r3) + mlt(h2, r2) +
+		     mlt(h3, r1) + mlt(h4, r0);
+
+		/* (partial) h %= p */
+		d1 += sr(d0, 26);     h0 = and(d0, 0x3ffffff);
+		d2 += sr(d1, 26);     h1 = and(d1, 0x3ffffff);
+		d3 += sr(d2, 26);     h2 = and(d2, 0x3ffffff);
+		d4 += sr(d3, 26);     h3 = and(d3, 0x3ffffff);
+		h0 += sr(d4, 26) * 5; h4 = and(d4, 0x3ffffff);
+		h1 += h0 >> 26;       h0 = h0 & 0x3ffffff;
+
+		src += POLY1305_BLOCK_SIZE;
+		srclen -= POLY1305_BLOCK_SIZE;
+	}
+
+	dctx->h[0] = h0;
+	dctx->h[1] = h1;
+	dctx->h[2] = h2;
+	dctx->h[3] = h3;
+	dctx->h[4] = h4;
+
+	return srclen;
+}
+
+static int poly1305_update(struct shash_desc *desc,
+			   const u8 *src, unsigned int srclen)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	if (unlikely(dctx->buflen)) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		srclen -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks(dctx, dctx->buf,
+					POLY1305_BLOCK_SIZE, 1 << 24);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
+		bytes = poly1305_blocks(dctx, src, srclen, 1 << 24);
+		src += srclen - bytes;
+		srclen = bytes;
+	}
+
+	if (unlikely(srclen)) {
+		dctx->buflen = srclen;
+		memcpy(dctx->buf, src, srclen);
+	}
+
+	return 0;
+}
+
+static int poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+	__le32 *mac = (__le32 *)dst;
+	u32 h0, h1, h2, h3, h4;
+	u32 g0, g1, g2, g3, g4;
+	u32 mask;
+	u64 f = 0;
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	/* fully carry h */
+	h0 = dctx->h[0];
+	h1 = dctx->h[1];
+	h2 = dctx->h[2];
+	h3 = dctx->h[3];
+	h4 = dctx->h[4];
+
+	h2 += (h1 >> 26);     h1 = h1 & 0x3ffffff;
+	h3 += (h2 >> 26);     h2 = h2 & 0x3ffffff;
+	h4 += (h3 >> 26);     h3 = h3 & 0x3ffffff;
+	h0 += (h4 >> 26) * 5; h4 = h4 & 0x3ffffff;
+	h1 += (h0 >> 26);     h0 = h0 & 0x3ffffff;
+
+	/* compute h + -p */
+	g0 = h0 + 5;
+	g1 = h1 + (g0 >> 26);             g0 &= 0x3ffffff;
+	g2 = h2 + (g1 >> 26);             g1 &= 0x3ffffff;
+	g3 = h3 + (g2 >> 26);             g2 &= 0x3ffffff;
+	g4 = h4 + (g3 >> 26) - (1 << 26); g3 &= 0x3ffffff;
+
+	/* select h if h < p, or h + -p if h >= p */
+	mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+	g0 &= mask;
+	g1 &= mask;
+	g2 &= mask;
+	g3 &= mask;
+	g4 &= mask;
+	mask = ~mask;
+	h0 = (h0 & mask) | g0;
+	h1 = (h1 & mask) | g1;
+	h2 = (h2 & mask) | g2;
+	h3 = (h3 & mask) | g3;
+	h4 = (h4 & mask) | g4;
+
+	/* h = h % (2^128) */
+	h0 = (h0 >>  0) | (h1 << 26);
+	h1 = (h1 >>  6) | (h2 << 20);
+	h2 = (h2 >> 12) | (h3 << 14);
+	h3 = (h3 >> 18) | (h4 <<  8);
+
+	/* mac = (h + s) % (2^128) */
+	f = (f >> 32) + h0 + dctx->s[0]; mac[0] = cpu_to_le32(f);
+	f = (f >> 32) + h1 + dctx->s[1]; mac[1] = cpu_to_le32(f);
+	f = (f >> 32) + h2 + dctx->s[2]; mac[2] = cpu_to_le32(f);
+	f = (f >> 32) + h3 + dctx->s[3]; mac[3] = cpu_to_le32(f);
+
+	return 0;
+}
+
+static struct shash_alg poly1305_alg = {
+	.digestsize	= POLY1305_DIGEST_SIZE,
+	.init		= poly1305_init,
+	.update		= poly1305_update,
+	.final		= poly1305_final,
+	.setkey		= poly1305_setkey,
+	.descsize	= sizeof(struct poly1305_desc_ctx),
+	.base		= {
+		.cra_name		= "poly1305",
+		.cra_driver_name	= "poly1305-generic",
+		.cra_priority		= 100,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_alignmask		= sizeof(u32) - 1,
+		.cra_blocksize		= POLY1305_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int __init poly1305_mod_init(void)
+{
+	return crypto_register_shash(&poly1305_alg);
+}
+
+static void __exit poly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&poly1305_alg);
+}
+
+module_init(poly1305_mod_init);
+module_exit(poly1305_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
+MODULE_DESCRIPTION("Poly1305 authenticator");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-generic");
diff --git a/crypto/proc.c b/crypto/proc.c
index 4ffe73b51612..2cc10c96d753 100644
--- a/crypto/proc.c
+++ b/crypto/proc.c
@@ -20,47 +20,8 @@
 #include <linux/rwsem.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/sysctl.h>
 #include "internal.h"
 
-#ifdef CONFIG_CRYPTO_FIPS
-static struct ctl_table crypto_sysctl_table[] = {
-	{
-		.procname       = "fips_enabled",
-		.data           = &fips_enabled,
-		.maxlen         = sizeof(int),
-		.mode           = 0444,
-		.proc_handler   = proc_dointvec
-	},
-	{}
-};
-
-static struct ctl_table crypto_dir_table[] = {
-	{
-		.procname       = "crypto",
-		.mode           = 0555,
-		.child          = crypto_sysctl_table
-	},
-	{}
-};
-
-static struct ctl_table_header *crypto_sysctls;
-
-static void crypto_proc_fips_init(void)
-{
-	crypto_sysctls = register_sysctl_table(crypto_dir_table);
-}
-
-static void crypto_proc_fips_exit(void)
-{
-	if (crypto_sysctls)
-		unregister_sysctl_table(crypto_sysctls);
-}
-#else
-#define crypto_proc_fips_init()
-#define crypto_proc_fips_exit()
-#endif
-
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	down_read(&crypto_alg_sem);
@@ -148,11 +109,9 @@ static const struct file_operations proc_crypto_ops = {
 void __init crypto_init_proc(void)
 {
 	proc_create("crypto", 0, NULL, &proc_crypto_ops);
-	crypto_proc_fips_init();
 }
 
 void __exit crypto_exit_proc(void)
 {
-	crypto_proc_fips_exit();
 	remove_proc_entry("crypto", NULL);
 }
diff --git a/crypto/rng.c b/crypto/rng.c
index e0a25c2456de..b81cffb13bab 100644
--- a/crypto/rng.c
+++ b/crypto/rng.c
@@ -4,6 +4,7 @@
  * RNG operations.
  *
  * Copyright (c) 2008 Neil Horman <nhorman@tuxdriver.com>
+ * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the Free
@@ -24,12 +25,19 @@
 #include <linux/cryptouser.h>
 #include <net/netlink.h>
 
+#include "internal.h"
+
 static DEFINE_MUTEX(crypto_default_rng_lock);
 struct crypto_rng *crypto_default_rng;
 EXPORT_SYMBOL_GPL(crypto_default_rng);
 static int crypto_default_rng_refcnt;
 
-static int rngapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+static inline struct crypto_rng *__crypto_rng_cast(struct crypto_tfm *tfm)
+{
+	return container_of(tfm, struct crypto_rng, base);
+}
+
+int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen)
 {
 	u8 *buf = NULL;
 	int err;
@@ -43,21 +51,23 @@ static int rngapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 		seed = buf;
 	}
 
-	err = crypto_rng_alg(tfm)->rng_reset(tfm, seed, slen);
+	err = crypto_rng_alg(tfm)->seed(tfm, seed, slen);
 
-	kfree(buf);
+	kzfree(buf);
 	return err;
 }
+EXPORT_SYMBOL_GPL(crypto_rng_reset);
 
-static int crypto_init_rng_ops(struct crypto_tfm *tfm, u32 type, u32 mask)
+static int crypto_rng_init_tfm(struct crypto_tfm *tfm)
 {
-	struct rng_alg *alg = &tfm->__crt_alg->cra_rng;
-	struct rng_tfm *ops = &tfm->crt_rng;
+	return 0;
+}
 
-	ops->rng_gen_random = alg->rng_make_random;
-	ops->rng_reset = rngapi_reset;
+static unsigned int seedsize(struct crypto_alg *alg)
+{
+	struct rng_alg *ralg = container_of(alg, struct rng_alg, base);
 
-	return 0;
+	return ralg->seedsize;
 }
 
 #ifdef CONFIG_NET
@@ -67,7 +77,7 @@ static int crypto_rng_report(struct sk_buff *skb, struct crypto_alg *alg)
 
 	strncpy(rrng.type, "rng", sizeof(rrng.type));
 
-	rrng.seedsize = alg->cra_rng.seedsize;
+	rrng.seedsize = seedsize(alg);
 
 	if (nla_put(skb, CRYPTOCFGA_REPORT_RNG,
 		    sizeof(struct crypto_report_rng), &rrng))
@@ -89,24 +99,27 @@ static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 static void crypto_rng_show(struct seq_file *m, struct crypto_alg *alg)
 {
 	seq_printf(m, "type         : rng\n");
-	seq_printf(m, "seedsize     : %u\n", alg->cra_rng.seedsize);
-}
-
-static unsigned int crypto_rng_ctxsize(struct crypto_alg *alg, u32 type,
-				       u32 mask)
-{
-	return alg->cra_ctxsize;
+	seq_printf(m, "seedsize     : %u\n", seedsize(alg));
 }
 
-const struct crypto_type crypto_rng_type = {
-	.ctxsize = crypto_rng_ctxsize,
-	.init = crypto_init_rng_ops,
+static const struct crypto_type crypto_rng_type = {
+	.extsize = crypto_alg_extsize,
+	.init_tfm = crypto_rng_init_tfm,
 #ifdef CONFIG_PROC_FS
 	.show = crypto_rng_show,
 #endif
 	.report = crypto_rng_report,
+	.maskclear = ~CRYPTO_ALG_TYPE_MASK,
+	.maskset = CRYPTO_ALG_TYPE_MASK,
+	.type = CRYPTO_ALG_TYPE_RNG,
+	.tfmsize = offsetof(struct crypto_rng, base),
 };
-EXPORT_SYMBOL_GPL(crypto_rng_type);
+
+struct crypto_rng *crypto_alloc_rng(const char *alg_name, u32 type, u32 mask)
+{
+	return crypto_alloc_tfm(alg_name, &crypto_rng_type, type, mask);
+}
+EXPORT_SYMBOL_GPL(crypto_alloc_rng);
 
 int crypto_get_default_rng(void)
 {
@@ -142,13 +155,82 @@ EXPORT_SYMBOL_GPL(crypto_get_default_rng);
 void crypto_put_default_rng(void)
 {
 	mutex_lock(&crypto_default_rng_lock);
-	if (!--crypto_default_rng_refcnt) {
-		crypto_free_rng(crypto_default_rng);
-		crypto_default_rng = NULL;
-	}
+	crypto_default_rng_refcnt--;
 	mutex_unlock(&crypto_default_rng_lock);
 }
 EXPORT_SYMBOL_GPL(crypto_put_default_rng);
 
+#if defined(CONFIG_CRYPTO_RNG) || defined(CONFIG_CRYPTO_RNG_MODULE)
+int crypto_del_default_rng(void)
+{
+	int err = -EBUSY;
+
+	mutex_lock(&crypto_default_rng_lock);
+	if (crypto_default_rng_refcnt)
+		goto out;
+
+	crypto_free_rng(crypto_default_rng);
+	crypto_default_rng = NULL;
+
+	err = 0;
+
+out:
+	mutex_unlock(&crypto_default_rng_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(crypto_del_default_rng);
+#endif
+
+int crypto_register_rng(struct rng_alg *alg)
+{
+	struct crypto_alg *base = &alg->base;
+
+	if (alg->seedsize > PAGE_SIZE / 8)
+		return -EINVAL;
+
+	base->cra_type = &crypto_rng_type;
+	base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK;
+	base->cra_flags |= CRYPTO_ALG_TYPE_RNG;
+
+	return crypto_register_alg(base);
+}
+EXPORT_SYMBOL_GPL(crypto_register_rng);
+
+void crypto_unregister_rng(struct rng_alg *alg)
+{
+	crypto_unregister_alg(&alg->base);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_rng);
+
+int crypto_register_rngs(struct rng_alg *algs, int count)
+{
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		ret = crypto_register_rng(algs + i);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	for (--i; i >= 0; --i)
+		crypto_unregister_rng(algs + i);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(crypto_register_rngs);
+
+void crypto_unregister_rngs(struct rng_alg *algs, int count)
+{
+	int i;
+
+	for (i = count - 1; i >= 0; --i)
+		crypto_unregister_rng(algs + i);
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_rngs);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Random Number Generator");
diff --git a/crypto/rsa.c b/crypto/rsa.c
new file mode 100644
index 000000000000..752af0656f2e
--- /dev/null
+++ b/crypto/rsa.c
@@ -0,0 +1,315 @@
+/* RSA asymmetric public-key algorithm [RFC3447]
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/rsa.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+
+/*
+ * RSAEP function [RFC3447 sec 5.1.1]
+ * c = m^e mod n;
+ */
+static int _rsa_enc(const struct rsa_key *key, MPI c, MPI m)
+{
+	/* (1) Validate 0 <= m < n */
+	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) c = m^e mod n */
+	return mpi_powm(c, m, key->e, key->n);
+}
+
+/*
+ * RSADP function [RFC3447 sec 5.1.2]
+ * m = c^d mod n;
+ */
+static int _rsa_dec(const struct rsa_key *key, MPI m, MPI c)
+{
+	/* (1) Validate 0 <= c < n */
+	if (mpi_cmp_ui(c, 0) < 0 || mpi_cmp(c, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) m = c^d mod n */
+	return mpi_powm(m, c, key->d, key->n);
+}
+
+/*
+ * RSASP1 function [RFC3447 sec 5.2.1]
+ * s = m^d mod n
+ */
+static int _rsa_sign(const struct rsa_key *key, MPI s, MPI m)
+{
+	/* (1) Validate 0 <= m < n */
+	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) s = m^d mod n */
+	return mpi_powm(s, m, key->d, key->n);
+}
+
+/*
+ * RSAVP1 function [RFC3447 sec 5.2.2]
+ * m = s^e mod n;
+ */
+static int _rsa_verify(const struct rsa_key *key, MPI m, MPI s)
+{
+	/* (1) Validate 0 <= s < n */
+	if (mpi_cmp_ui(s, 0) < 0 || mpi_cmp(s, key->n) >= 0)
+		return -EINVAL;
+
+	/* (2) m = s^e mod n */
+	return mpi_powm(m, s, key->e, key->n);
+}
+
+static inline struct rsa_key *rsa_get_key(struct crypto_akcipher *tfm)
+{
+	return akcipher_tfm_ctx(tfm);
+}
+
+static int rsa_enc(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI m, c = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!c)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->e)) {
+		ret = -EINVAL;
+		goto err_free_c;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_c;
+	}
+
+	m = mpi_read_raw_data(req->src, req->src_len);
+	if (!m) {
+		ret = -ENOMEM;
+		goto err_free_c;
+	}
+
+	ret = _rsa_enc(pkey, c, m);
+	if (ret)
+		goto err_free_m;
+
+	ret = mpi_read_buffer(c, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_m;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_m;
+	}
+
+err_free_m:
+	mpi_free(m);
+err_free_c:
+	mpi_free(c);
+	return ret;
+}
+
+static int rsa_dec(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI c, m = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!m)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->d)) {
+		ret = -EINVAL;
+		goto err_free_m;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_m;
+	}
+
+	c = mpi_read_raw_data(req->src, req->src_len);
+	if (!c) {
+		ret = -ENOMEM;
+		goto err_free_m;
+	}
+
+	ret = _rsa_dec(pkey, m, c);
+	if (ret)
+		goto err_free_c;
+
+	ret = mpi_read_buffer(m, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_c;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_c;
+	}
+
+err_free_c:
+	mpi_free(c);
+err_free_m:
+	mpi_free(m);
+	return ret;
+}
+
+static int rsa_sign(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI m, s = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!s)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->d)) {
+		ret = -EINVAL;
+		goto err_free_s;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_s;
+	}
+
+	m = mpi_read_raw_data(req->src, req->src_len);
+	if (!m) {
+		ret = -ENOMEM;
+		goto err_free_s;
+	}
+
+	ret = _rsa_sign(pkey, s, m);
+	if (ret)
+		goto err_free_m;
+
+	ret = mpi_read_buffer(s, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_m;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_m;
+	}
+
+err_free_m:
+	mpi_free(m);
+err_free_s:
+	mpi_free(s);
+	return ret;
+}
+
+static int rsa_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	const struct rsa_key *pkey = rsa_get_key(tfm);
+	MPI s, m = mpi_alloc(0);
+	int ret = 0;
+	int sign;
+
+	if (!m)
+		return -ENOMEM;
+
+	if (unlikely(!pkey->n || !pkey->e)) {
+		ret = -EINVAL;
+		goto err_free_m;
+	}
+
+	if (req->dst_len < mpi_get_size(pkey->n)) {
+		req->dst_len = mpi_get_size(pkey->n);
+		ret = -EOVERFLOW;
+		goto err_free_m;
+	}
+
+	s = mpi_read_raw_data(req->src, req->src_len);
+	if (!s) {
+		ret = -ENOMEM;
+		goto err_free_m;
+	}
+
+	ret = _rsa_verify(pkey, m, s);
+	if (ret)
+		goto err_free_s;
+
+	ret = mpi_read_buffer(m, req->dst, req->dst_len, &req->dst_len, &sign);
+	if (ret)
+		goto err_free_s;
+
+	if (sign < 0) {
+		ret = -EBADMSG;
+		goto err_free_s;
+	}
+
+err_free_s:
+	mpi_free(s);
+err_free_m:
+	mpi_free(m);
+	return ret;
+}
+
+static int rsa_setkey(struct crypto_akcipher *tfm, const void *key,
+		      unsigned int keylen)
+{
+	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+
+	return rsa_parse_key(pkey, key, keylen);
+}
+
+static void rsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+	struct rsa_key *pkey = akcipher_tfm_ctx(tfm);
+
+	rsa_free_key(pkey);
+}
+
+static struct akcipher_alg rsa = {
+	.encrypt = rsa_enc,
+	.decrypt = rsa_dec,
+	.sign = rsa_sign,
+	.verify = rsa_verify,
+	.setkey = rsa_setkey,
+	.exit = rsa_exit_tfm,
+	.base = {
+		.cra_name = "rsa",
+		.cra_driver_name = "rsa-generic",
+		.cra_priority = 100,
+		.cra_module = THIS_MODULE,
+		.cra_ctxsize = sizeof(struct rsa_key),
+	},
+};
+
+static int rsa_init(void)
+{
+	return crypto_register_akcipher(&rsa);
+}
+
+static void rsa_exit(void)
+{
+	crypto_unregister_akcipher(&rsa);
+}
+
+module_init(rsa_init);
+module_exit(rsa_exit);
+MODULE_ALIAS_CRYPTO("rsa");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RSA generic algorithm");
diff --git a/crypto/rsa_helper.c b/crypto/rsa_helper.c
new file mode 100644
index 000000000000..3e8e0a9e5a8e
--- /dev/null
+++ b/crypto/rsa_helper.c
@@ -0,0 +1,121 @@
+/*
+ * RSA key extract helper
+ *
+ * Copyright (c) 2015, Intel Corporation
+ * Authors: Tadeusz Struk <tadeusz.struk@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/err.h>
+#include <linux/fips.h>
+#include <crypto/internal/rsa.h>
+#include "rsakey-asn1.h"
+
+int rsa_get_n(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->n = mpi_read_raw_data(value, vlen);
+
+	if (!key->n)
+		return -ENOMEM;
+
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (mpi_get_size(key->n) != 256 ||
+			     mpi_get_size(key->n) != 384)) {
+		pr_err("RSA: key size not allowed in FIPS mode\n");
+		mpi_free(key->n);
+		key->n = NULL;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int rsa_get_e(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->e = mpi_read_raw_data(value, vlen);
+
+	if (!key->e)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int rsa_get_d(void *context, size_t hdrlen, unsigned char tag,
+	      const void *value, size_t vlen)
+{
+	struct rsa_key *key = context;
+
+	key->d = mpi_read_raw_data(value, vlen);
+
+	if (!key->d)
+		return -ENOMEM;
+
+	/* In FIPS mode only allow key size 2K & 3K */
+	if (fips_enabled && (mpi_get_size(key->d) != 256 ||
+			     mpi_get_size(key->d) != 384)) {
+		pr_err("RSA: key size not allowed in FIPS mode\n");
+		mpi_free(key->d);
+		key->d = NULL;
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void free_mpis(struct rsa_key *key)
+{
+	mpi_free(key->n);
+	mpi_free(key->e);
+	mpi_free(key->d);
+	key->n = NULL;
+	key->e = NULL;
+	key->d = NULL;
+}
+
+/**
+ * rsa_free_key() - frees rsa key allocated by rsa_parse_key()
+ *
+ * @rsa_key:	struct rsa_key key representation
+ */
+void rsa_free_key(struct rsa_key *key)
+{
+	free_mpis(key);
+}
+EXPORT_SYMBOL_GPL(rsa_free_key);
+
+/**
+ * rsa_parse_key() - extracts an rsa key from BER encoded buffer
+ *		     and stores it in the provided struct rsa_key
+ *
+ * @rsa_key:	struct rsa_key key representation
+ * @key:	key in BER format
+ * @key_len:	length of key
+ *
+ * Return:	0 on success or error code in case of error
+ */
+int rsa_parse_key(struct rsa_key *rsa_key, const void *key,
+		  unsigned int key_len)
+{
+	int ret;
+
+	free_mpis(rsa_key);
+	ret = asn1_ber_decoder(&rsakey_decoder, rsa_key, key, key_len);
+	if (ret < 0)
+		goto error;
+
+	return 0;
+error:
+	free_mpis(rsa_key);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rsa_parse_key);
diff --git a/crypto/rsakey.asn1 b/crypto/rsakey.asn1
new file mode 100644
index 000000000000..3c7b5df7b428
--- /dev/null
+++ b/crypto/rsakey.asn1
@@ -0,0 +1,5 @@
+RsaKey ::= SEQUENCE {
+	n INTEGER ({ rsa_get_n }),
+	e INTEGER ({ rsa_get_e }),
+	d INTEGER ({ rsa_get_d })
+}
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index 3bd749c7bb70..ea5815c5e128 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -54,7 +54,11 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
 		struct page *page;
 
 		page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT);
-		if (!PageSlab(page))
+		/* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as
+		 * PageSlab cannot be optimised away per se due to
+		 * use of volatile pointer.
+		 */
+		if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page))
 			flush_dcache_page(page);
 	}
 
@@ -104,22 +108,18 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 			      unsigned int start, unsigned int nbytes, int out)
 {
 	struct scatter_walk walk;
-	unsigned int offset = 0;
+	struct scatterlist tmp[2];
 
 	if (!nbytes)
 		return;
 
-	for (;;) {
-		scatterwalk_start(&walk, sg);
-
-		if (start < offset + sg->length)
-			break;
+	sg = scatterwalk_ffwd(tmp, sg, start);
 
-		offset += sg->length;
-		sg = sg_next(sg);
-	}
+	if (sg_page(sg) == virt_to_page(buf) &&
+	    sg->offset == offset_in_page(buf))
+		return;
 
-	scatterwalk_advance(&walk, start - offset);
+	scatterwalk_start(&walk, sg);
 	scatterwalk_copychunks(buf, &walk, nbytes, out);
 	scatterwalk_done(&walk, out, 0);
 }
@@ -146,3 +146,26 @@ int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
 	return n;
 }
 EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
+
+struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
+				     struct scatterlist *src,
+				     unsigned int len)
+{
+	for (;;) {
+		if (!len)
+			return src;
+
+		if (src->length > len)
+			break;
+
+		len -= src->length;
+		src = sg_next(src);
+	}
+
+	sg_init_table(dst, 2);
+	sg_set_page(dst, sg_page(src), src->length - len, src->offset + len);
+	scatterwalk_crypto_chain(dst, sg_next(src), 0, 2);
+
+	return dst;
+}
+EXPORT_SYMBOL_GPL(scatterwalk_ffwd);
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index b7bb9a2f4a31..122c56e3491b 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -13,9 +13,11 @@
  *
  */
 
-#include <crypto/internal/aead.h>
+#include <crypto/internal/geniv.h>
 #include <crypto/internal/skcipher.h>
+#include <crypto/null.h>
 #include <crypto/rng.h>
+#include <crypto/scatterwalk.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -24,11 +26,25 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
+struct seqniv_request_ctx {
+	struct scatterlist dst[2];
+	struct aead_request subreq;
+};
+
 struct seqiv_ctx {
 	spinlock_t lock;
 	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
 };
 
+struct seqiv_aead_ctx {
+	/* aead_geniv_ctx must be first the element */
+	struct aead_geniv_ctx geniv;
+	struct crypto_blkcipher *null;
+	u8 salt[] __attribute__ ((aligned(__alignof__(u32))));
+};
+
+static void seqiv_free(struct crypto_instance *inst);
+
 static void seqiv_complete2(struct skcipher_givcrypt_request *req, int err)
 {
 	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
@@ -81,6 +97,77 @@ static void seqiv_aead_complete(struct crypto_async_request *base, int err)
 	aead_givcrypt_complete(req, err);
 }
 
+static void seqiv_aead_encrypt_complete2(struct aead_request *req, int err)
+{
+	struct aead_request *subreq = aead_request_ctx(req);
+	struct crypto_aead *geniv;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	if (err)
+		goto out;
+
+	geniv = crypto_aead_reqtfm(req);
+	memcpy(req->iv, subreq->iv, crypto_aead_ivsize(geniv));
+
+out:
+	kzfree(subreq->iv);
+}
+
+static void seqiv_aead_encrypt_complete(struct crypto_async_request *base,
+					int err)
+{
+	struct aead_request *req = base->data;
+
+	seqiv_aead_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static void seqniv_aead_encrypt_complete2(struct aead_request *req, int err)
+{
+	unsigned int ivsize = 8;
+	u8 data[20];
+
+	if (err == -EINPROGRESS)
+		return;
+
+	/* Swap IV and ESP header back to correct order. */
+	scatterwalk_map_and_copy(data, req->dst, 0, req->assoclen + ivsize, 0);
+	scatterwalk_map_and_copy(data + ivsize, req->dst, 0, req->assoclen, 1);
+	scatterwalk_map_and_copy(data, req->dst, req->assoclen, ivsize, 1);
+}
+
+static void seqniv_aead_encrypt_complete(struct crypto_async_request *base,
+					int err)
+{
+	struct aead_request *req = base->data;
+
+	seqniv_aead_encrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
+static void seqniv_aead_decrypt_complete2(struct aead_request *req, int err)
+{
+	u8 data[4];
+
+	if (err == -EINPROGRESS)
+		return;
+
+	/* Move ESP header back to correct location. */
+	scatterwalk_map_and_copy(data, req->dst, 16, req->assoclen - 8, 0);
+	scatterwalk_map_and_copy(data, req->dst, 8, req->assoclen - 8, 1);
+}
+
+static void seqniv_aead_decrypt_complete(struct crypto_async_request *base,
+					 int err)
+{
+	struct aead_request *req = base->data;
+
+	seqniv_aead_decrypt_complete2(req, err);
+	aead_request_complete(req, err);
+}
+
 static void seqiv_geniv(struct seqiv_ctx *ctx, u8 *info, u64 seq,
 			unsigned int ivsize)
 {
@@ -186,160 +273,477 @@ static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
 	return err;
 }
 
-static int seqiv_givencrypt_first(struct skcipher_givcrypt_request *req)
+static int seqniv_aead_encrypt(struct aead_request *req)
 {
-	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
-	int err = 0;
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq;
+	struct scatterlist *dst;
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+	u8 buf[20] __attribute__ ((aligned(__alignof__(u32))));
+	int err;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_ablkcipher_crt(geniv)->givencrypt != seqiv_givencrypt_first)
-		goto unlock;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_ablkcipher_ivsize(geniv));
+	/* ESP AD is at most 12 bytes (ESN). */
+	if (req->assoclen > 12)
+		return -EINVAL;
 
-unlock:
-	spin_unlock_bh(&ctx->lock);
+	aead_request_set_tfm(subreq, ctx->geniv.child);
 
-	if (err)
-		return err;
+	compl = seqniv_aead_encrypt_complete;
+	data = req;
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
 
-	return seqiv_givencrypt(req);
+	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, dst, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	memcpy(buf, req->iv, ivsize);
+	crypto_xor(buf, ctx->salt, ivsize);
+	memcpy(req->iv, buf, ivsize);
+
+	/* Swap order of IV and ESP AD for ICV generation. */
+	scatterwalk_map_and_copy(buf + ivsize, req->dst, 0, req->assoclen, 0);
+	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 1);
+
+	err = crypto_aead_encrypt(subreq);
+	seqniv_aead_encrypt_complete2(req, err);
+	return err;
 }
 
-static int seqiv_aead_givencrypt_first(struct aead_givcrypt_request *req)
+static int seqiv_aead_encrypt(struct aead_request *req)
 {
-	struct crypto_aead *geniv = aead_givcrypt_reqtfm(req);
-	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
-	int err = 0;
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	u8 *info;
+	unsigned int ivsize = 8;
+	int err;
 
-	spin_lock_bh(&ctx->lock);
-	if (crypto_aead_crt(geniv)->givencrypt != seqiv_aead_givencrypt_first)
-		goto unlock;
+	if (req->cryptlen < ivsize)
+		return -EINVAL;
 
-	crypto_aead_crt(geniv)->givencrypt = seqiv_aead_givencrypt;
-	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
-				   crypto_aead_ivsize(geniv));
+	aead_request_set_tfm(subreq, ctx->geniv.child);
 
-unlock:
-	spin_unlock_bh(&ctx->lock);
+	compl = req->base.complete;
+	data = req->base.data;
+	info = req->iv;
 
-	if (err)
-		return err;
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
 
-	return seqiv_aead_givencrypt(req);
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	if (unlikely(!IS_ALIGNED((unsigned long)info,
+				 crypto_aead_alignmask(geniv) + 1))) {
+		info = kmalloc(ivsize, req->base.flags &
+				       CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
+								  GFP_ATOMIC);
+		if (!info)
+			return -ENOMEM;
+
+		memcpy(info, req->iv, ivsize);
+		compl = seqiv_aead_encrypt_complete;
+		data = req;
+	}
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->dst, req->dst,
+			       req->cryptlen - ivsize, info);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	crypto_xor(info, ctx->salt, ivsize);
+	scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
+
+	err = crypto_aead_encrypt(subreq);
+	if (unlikely(info != req->iv))
+		seqiv_aead_encrypt_complete2(req, err);
+	return err;
+}
+
+static int seqniv_aead_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct seqniv_request_ctx *rctx = aead_request_ctx(req);
+	struct aead_request *subreq = &rctx->subreq;
+	struct scatterlist *dst;
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+	u8 buf[20];
+	int err;
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	if (req->assoclen > 12)
+		return -EINVAL;
+	else if (req->assoclen > 8) {
+		compl = seqniv_aead_decrypt_complete;
+		data = req;
+	}
+
+	if (req->src != req->dst) {
+		struct blkcipher_desc desc = {
+			.tfm = ctx->null,
+		};
+
+		err = crypto_blkcipher_encrypt(&desc, req->dst, req->src,
+					       req->assoclen + req->cryptlen);
+		if (err)
+			return err;
+	}
+
+	/* Move ESP AD forward for ICV generation. */
+	scatterwalk_map_and_copy(buf, req->dst, 0, req->assoclen + ivsize, 0);
+	memcpy(req->iv, buf + req->assoclen, ivsize);
+	scatterwalk_map_and_copy(buf, req->dst, ivsize, req->assoclen, 1);
+
+	dst = scatterwalk_ffwd(rctx->dst, req->dst, ivsize);
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, dst, dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen);
+
+	err = crypto_aead_decrypt(subreq);
+	if (req->assoclen > 8)
+		seqniv_aead_decrypt_complete2(req, err);
+	return err;
+}
+
+static int seqiv_aead_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *geniv = crypto_aead_reqtfm(req);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	struct aead_request *subreq = aead_request_ctx(req);
+	crypto_completion_t compl;
+	void *data;
+	unsigned int ivsize = 8;
+
+	if (req->cryptlen < ivsize + crypto_aead_authsize(geniv))
+		return -EINVAL;
+
+	aead_request_set_tfm(subreq, ctx->geniv.child);
+
+	compl = req->base.complete;
+	data = req->base.data;
+
+	aead_request_set_callback(subreq, req->base.flags, compl, data);
+	aead_request_set_crypt(subreq, req->src, req->dst,
+			       req->cryptlen - ivsize, req->iv);
+	aead_request_set_ad(subreq, req->assoclen + ivsize);
+
+	scatterwalk_map_and_copy(req->iv, req->src, req->assoclen, ivsize, 0);
+	if (req->src != req->dst)
+		scatterwalk_map_and_copy(req->iv, req->dst,
+					 req->assoclen, ivsize, 1);
+
+	return crypto_aead_decrypt(subreq);
 }
 
 static int seqiv_init(struct crypto_tfm *tfm)
 {
 	struct crypto_ablkcipher *geniv = __crypto_ablkcipher_cast(tfm);
 	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
 	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request);
 
-	return skcipher_geniv_init(tfm);
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		crypto_ablkcipher_crt(geniv)->givencrypt = seqiv_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_ablkcipher_ivsize(geniv));
+		crypto_put_default_rng();
+	}
+
+	return err ?: skcipher_geniv_init(tfm);
 }
 
-static int seqiv_aead_init(struct crypto_tfm *tfm)
+static int seqiv_old_aead_init(struct crypto_tfm *tfm)
 {
 	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
 	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
 
 	spin_lock_init(&ctx->lock);
 
-	tfm->crt_aead.reqsize = sizeof(struct aead_request);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct aead_request));
+	err = 0;
+	if (!crypto_get_default_rng()) {
+		geniv->givencrypt = seqiv_aead_givencrypt;
+		err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+					   crypto_aead_ivsize(geniv));
+		crypto_put_default_rng();
+	}
 
-	return aead_geniv_init(tfm);
+	return err ?: aead_geniv_init(tfm);
 }
 
-static struct crypto_template seqiv_tmpl;
-
-static struct crypto_instance *seqiv_ablkcipher_alloc(struct rtattr **tb)
+static int seqiv_aead_init_common(struct crypto_tfm *tfm, unsigned int reqsize)
 {
-	struct crypto_instance *inst;
+	struct crypto_aead *geniv = __crypto_aead_cast(tfm);
+	struct seqiv_aead_ctx *ctx = crypto_aead_ctx(geniv);
+	int err;
 
-	inst = skcipher_geniv_alloc(&seqiv_tmpl, tb, 0, 0);
+	spin_lock_init(&ctx->geniv.lock);
 
-	if (IS_ERR(inst))
+	crypto_aead_set_reqsize(geniv, sizeof(struct aead_request));
+
+	err = crypto_get_default_rng();
+	if (err)
 		goto out;
 
-	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64)) {
-		skcipher_geniv_free(inst);
-		inst = ERR_PTR(-EINVAL);
+	err = crypto_rng_get_bytes(crypto_default_rng, ctx->salt,
+				   crypto_aead_ivsize(geniv));
+	crypto_put_default_rng();
+	if (err)
 		goto out;
-	}
 
-	inst->alg.cra_ablkcipher.givencrypt = seqiv_givencrypt_first;
+	ctx->null = crypto_get_default_null_skcipher();
+	err = PTR_ERR(ctx->null);
+	if (IS_ERR(ctx->null))
+		goto out;
 
-	inst->alg.cra_init = seqiv_init;
-	inst->alg.cra_exit = skcipher_geniv_exit;
+	err = aead_geniv_init(tfm);
+	if (err)
+		goto drop_null;
 
-	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
+	ctx->geniv.child = geniv->child;
+	geniv->child = geniv;
 
 out:
-	return inst;
+	return err;
+
+drop_null:
+	crypto_put_default_null_skcipher();
+	goto out;
+}
+
+static int seqiv_aead_init(struct crypto_tfm *tfm)
+{
+	return seqiv_aead_init_common(tfm, sizeof(struct aead_request));
+}
+
+static int seqniv_aead_init(struct crypto_tfm *tfm)
+{
+	return seqiv_aead_init_common(tfm, sizeof(struct seqniv_request_ctx));
+}
+
+static void seqiv_aead_exit(struct crypto_tfm *tfm)
+{
+	struct seqiv_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->geniv.child);
+	crypto_put_default_null_skcipher();
 }
 
-static struct crypto_instance *seqiv_aead_alloc(struct rtattr **tb)
+static int seqiv_ablkcipher_create(struct crypto_template *tmpl,
+				   struct rtattr **tb)
 {
 	struct crypto_instance *inst;
+	int err;
 
-	inst = aead_geniv_alloc(&seqiv_tmpl, tb, 0, 0);
+	inst = skcipher_geniv_alloc(tmpl, tb, 0, 0);
 
 	if (IS_ERR(inst))
-		goto out;
+		return PTR_ERR(inst);
 
-	if (inst->alg.cra_aead.ivsize < sizeof(u64)) {
-		aead_geniv_free(inst);
-		inst = ERR_PTR(-EINVAL);
-		goto out;
-	}
+	err = -EINVAL;
+	if (inst->alg.cra_ablkcipher.ivsize < sizeof(u64))
+		goto free_inst;
+
+	inst->alg.cra_init = seqiv_init;
+	inst->alg.cra_exit = skcipher_geniv_exit;
+
+	inst->alg.cra_ctxsize += inst->alg.cra_ablkcipher.ivsize;
+	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+
+	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
 
-	inst->alg.cra_aead.givencrypt = seqiv_aead_givencrypt_first;
+	err = crypto_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
-	inst->alg.cra_init = seqiv_aead_init;
+out:
+	return err;
+
+free_inst:
+	skcipher_geniv_free(inst);
+	goto out;
+}
+
+static int seqiv_old_aead_create(struct crypto_template *tmpl,
+				 struct aead_instance *aead)
+{
+	struct crypto_instance *inst = aead_crypto_instance(aead);
+	int err = -EINVAL;
+
+	if (inst->alg.cra_aead.ivsize < sizeof(u64))
+		goto free_inst;
+
+	inst->alg.cra_init = seqiv_old_aead_init;
 	inst->alg.cra_exit = aead_geniv_exit;
 
 	inst->alg.cra_ctxsize = inst->alg.cra_aead.ivsize;
+	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+
+	err = crypto_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
 out:
-	return inst;
+	return err;
+
+free_inst:
+	aead_geniv_free(aead);
+	goto out;
 }
 
-static struct crypto_instance *seqiv_alloc(struct rtattr **tb)
+static int seqiv_aead_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+
+	if (IS_ERR(inst))
+		return PTR_ERR(inst);
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+
+	if (inst->alg.base.cra_aead.encrypt)
+		return seqiv_old_aead_create(tmpl, inst);
+
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize != sizeof(u64))
+		goto free_inst;
+
+	inst->alg.encrypt = seqiv_aead_encrypt;
+	inst->alg.decrypt = seqiv_aead_decrypt;
+
+	inst->alg.base.cra_init = seqiv_aead_init;
+	inst->alg.base.cra_exit = seqiv_aead_exit;
+
+	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.base.cra_aead.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
+
+out:
+	return err;
+
+free_inst:
+	aead_geniv_free(inst);
+	goto out;
+}
+
+static int seqiv_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct crypto_attr_type *algt;
-	struct crypto_instance *inst;
 	int err;
 
 	algt = crypto_get_attr_type(tb);
 	if (IS_ERR(algt))
-		return ERR_CAST(algt);
-
-	err = crypto_get_default_rng();
-	if (err)
-		return ERR_PTR(err);
+		return PTR_ERR(algt);
 
 	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
-		inst = seqiv_ablkcipher_alloc(tb);
+		err = seqiv_ablkcipher_create(tmpl, tb);
 	else
-		inst = seqiv_aead_alloc(tb);
+		err = seqiv_aead_create(tmpl, tb);
 
+	return err;
+}
+
+static int seqniv_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	struct aead_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct aead_alg *alg;
+	int err;
+
+	inst = aead_geniv_alloc(tmpl, tb, 0, 0);
+	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
-		goto put_rng;
+		goto out;
 
-	inst->alg.cra_alignmask |= __alignof__(u32) - 1;
-	inst->alg.cra_ctxsize += sizeof(struct seqiv_ctx);
+	spawn = aead_instance_ctx(inst);
+	alg = crypto_spawn_aead_alg(spawn);
+
+	if (alg->base.cra_aead.encrypt)
+		goto done;
+
+	err = -EINVAL;
+	if (inst->alg.ivsize != sizeof(u64))
+		goto free_inst;
+
+	inst->alg.encrypt = seqniv_aead_encrypt;
+	inst->alg.decrypt = seqniv_aead_decrypt;
+
+	inst->alg.base.cra_init = seqniv_aead_init;
+	inst->alg.base.cra_exit = seqiv_aead_exit;
+
+	inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
+	inst->alg.base.cra_ctxsize = sizeof(struct seqiv_aead_ctx);
+	inst->alg.base.cra_ctxsize += inst->alg.ivsize;
+
+done:
+	err = aead_register_instance(tmpl, inst);
+	if (err)
+		goto free_inst;
 
 out:
-	return inst;
+	return err;
 
-put_rng:
-	crypto_put_default_rng();
+free_inst:
+	aead_geniv_free(inst);
 	goto out;
 }
 
@@ -348,24 +752,46 @@ static void seqiv_free(struct crypto_instance *inst)
 	if ((inst->alg.cra_flags ^ CRYPTO_ALG_TYPE_AEAD) & CRYPTO_ALG_TYPE_MASK)
 		skcipher_geniv_free(inst);
 	else
-		aead_geniv_free(inst);
-	crypto_put_default_rng();
+		aead_geniv_free(aead_instance(inst));
 }
 
 static struct crypto_template seqiv_tmpl = {
 	.name = "seqiv",
-	.alloc = seqiv_alloc,
+	.create = seqiv_create,
+	.free = seqiv_free,
+	.module = THIS_MODULE,
+};
+
+static struct crypto_template seqniv_tmpl = {
+	.name = "seqniv",
+	.create = seqniv_create,
 	.free = seqiv_free,
 	.module = THIS_MODULE,
 };
 
 static int __init seqiv_module_init(void)
 {
-	return crypto_register_template(&seqiv_tmpl);
+	int err;
+
+	err = crypto_register_template(&seqiv_tmpl);
+	if (err)
+		goto out;
+
+	err = crypto_register_template(&seqniv_tmpl);
+	if (err)
+		goto out_undo_niv;
+
+out:
+	return err;
+
+out_undo_niv:
+	crypto_unregister_template(&seqiv_tmpl);
+	goto out;
 }
 
 static void __exit seqiv_module_exit(void)
 {
+	crypto_unregister_template(&seqniv_tmpl);
 	crypto_unregister_template(&seqiv_tmpl);
 }
 
@@ -375,3 +801,4 @@ module_exit(seqiv_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Sequence Number IV Generator");
 MODULE_ALIAS_CRYPTO("seqiv");
+MODULE_ALIAS_CRYPTO("seqniv");
diff --git a/crypto/shash.c b/crypto/shash.c
index 47c713954bf3..ecb1e3d39bf0 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -520,11 +520,6 @@ static int crypto_shash_init_tfm(struct crypto_tfm *tfm)
 	return 0;
 }
 
-static unsigned int crypto_shash_extsize(struct crypto_alg *alg)
-{
-	return alg->cra_ctxsize;
-}
-
 #ifdef CONFIG_NET
 static int crypto_shash_report(struct sk_buff *skb, struct crypto_alg *alg)
 {
@@ -564,7 +559,7 @@ static void crypto_shash_show(struct seq_file *m, struct crypto_alg *alg)
 
 static const struct crypto_type crypto_shash_type = {
 	.ctxsize = crypto_shash_ctxsize,
-	.extsize = crypto_shash_extsize,
+	.extsize = crypto_alg_extsize,
 	.init = crypto_init_shash_ops,
 	.init_tfm = crypto_shash_init_tfm,
 #ifdef CONFIG_PROC_FS
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 1a2800107fc8..9f6f10b498ba 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -22,8 +22,10 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/hash.h>
 #include <linux/err.h>
+#include <linux/fips.h>
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
@@ -34,7 +36,6 @@
 #include <linux/timex.h>
 #include <linux/interrupt.h>
 #include "tcrypt.h"
-#include "internal.h"
 
 /*
  * Need slab memory for testing (size in number of pages).
@@ -257,12 +258,12 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE],
 		rem = buflen % PAGE_SIZE;
 	}
 
-	sg_init_table(sg, np);
+	sg_init_table(sg, np + 1);
 	np--;
 	for (k = 0; k < np; k++)
-		sg_set_buf(&sg[k], xbuf[k], PAGE_SIZE);
+		sg_set_buf(&sg[k + 1], xbuf[k], PAGE_SIZE);
 
-	sg_set_buf(&sg[k], xbuf[k], rem);
+	sg_set_buf(&sg[k + 1], xbuf[k], rem);
 }
 
 static void test_aead_speed(const char *algo, int enc, unsigned int secs,
@@ -276,7 +277,6 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 	const char *key;
 	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct scatterlist *sgout;
 	const char *e;
 	void *assoc;
@@ -308,11 +308,10 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 	if (testmgr_alloc_buf(xoutbuf))
 		goto out_nooutbuf;
 
-	sg = kmalloc(sizeof(*sg) * 8 * 3, GFP_KERNEL);
+	sg = kmalloc(sizeof(*sg) * 9 * 2, GFP_KERNEL);
 	if (!sg)
 		goto out_nosg;
-	asg = &sg[8];
-	sgout = &asg[8];
+	sgout = &sg[9];
 
 	tfm = crypto_alloc_aead(algo, 0, 0);
 
@@ -338,7 +337,6 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 		do {
 			assoc = axbuf[0];
 			memset(assoc, 0xff, aad_size);
-			sg_init_one(&asg[0], assoc, aad_size);
 
 			if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
 				pr_err("template (%u) too big for tvmem (%lu)\n",
@@ -374,14 +372,17 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 				goto out;
 			}
 
-			sg_init_aead(&sg[0], xbuf,
+			sg_init_aead(sg, xbuf,
 				    *b_size + (enc ? authsize : 0));
 
-			sg_init_aead(&sgout[0], xoutbuf,
+			sg_init_aead(sgout, xoutbuf,
 				    *b_size + (enc ? authsize : 0));
 
+			sg_set_buf(&sg[0], assoc, aad_size);
+			sg_set_buf(&sgout[0], assoc, aad_size);
+
 			aead_request_set_crypt(req, sg, sgout, *b_size, iv);
-			aead_request_set_assoc(req, asg, aad_size);
+			aead_request_set_ad(req, aad_size);
 
 			if (secs)
 				ret = test_aead_jiffies(req, enc, *b_size,
@@ -808,7 +809,7 @@ static int test_ahash_jiffies(struct ahash_request *req, int blen,
 
 	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			return ret;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -877,7 +878,7 @@ static int test_ahash_cycles(struct ahash_request *req, int blen,
 
 	/* Warm-up run. */
 	for (i = 0; i < 4; i++) {
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			goto out;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -896,7 +897,7 @@ static int test_ahash_cycles(struct ahash_request *req, int blen,
 
 		start = get_cycles();
 
-		ret = crypto_ahash_init(req);
+		ret = do_one_ahash_op(req, crypto_ahash_init(req));
 		if (ret)
 			goto out;
 		for (pcount = 0; pcount < blen; pcount += plen) {
@@ -1761,6 +1762,11 @@ static int do_test(const char *alg, u32 type, u32 mask, int m)
 				NULL, 0, 16, 8, aead_speed_template_20);
 		break;
 
+	case 212:
+		test_aead_speed("rfc4309(ccm(aes))", ENCRYPT, sec,
+				NULL, 0, 16, 8, aead_speed_template_19);
+		break;
+
 	case 300:
 		if (alg) {
 			test_hash_speed(alg, sec, generic_hash_speed_template);
diff --git a/crypto/tcrypt.h b/crypto/tcrypt.h
index 6c7e21a09f78..6cc1b856871b 100644
--- a/crypto/tcrypt.h
+++ b/crypto/tcrypt.h
@@ -65,6 +65,7 @@ static u8 speed_template_32_64[] = {32, 64, 0};
 /*
  * AEAD speed tests
  */
+static u8 aead_speed_template_19[] = {19, 0};
 static u8 aead_speed_template_20[] = {20, 0};
 
 /*
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f9bce3d7ee7f..975e1eac3e2d 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -20,14 +20,17 @@
  *
  */
 
+#include <crypto/aead.h>
 #include <crypto/hash.h>
 #include <linux/err.h>
+#include <linux/fips.h>
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <crypto/rng.h>
 #include <crypto/drbg.h>
+#include <crypto/akcipher.h>
 
 #include "internal.h"
 
@@ -114,6 +117,11 @@ struct drbg_test_suite {
 	unsigned int count;
 };
 
+struct akcipher_test_suite {
+	struct akcipher_testvec *vecs;
+	unsigned int count;
+};
+
 struct alg_test_desc {
 	const char *alg;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
@@ -128,6 +136,7 @@ struct alg_test_desc {
 		struct hash_test_suite hash;
 		struct cprng_test_suite cprng;
 		struct drbg_test_suite drbg;
+		struct akcipher_test_suite akcipher;
 	} suite;
 };
 
@@ -425,7 +434,6 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 	char *key;
 	struct aead_request *req;
 	struct scatterlist *sg;
-	struct scatterlist *asg;
 	struct scatterlist *sgout;
 	const char *e, *d;
 	struct tcrypt_result result;
@@ -452,11 +460,10 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		goto out_nooutbuf;
 
 	/* avoid "the frame size is larger than 1024 bytes" compiler warning */
-	sg = kmalloc(sizeof(*sg) * 8 * (diff_dst ? 3 : 2), GFP_KERNEL);
+	sg = kmalloc(sizeof(*sg) * 8 * (diff_dst ? 4 : 2), GFP_KERNEL);
 	if (!sg)
 		goto out_nosg;
-	asg = &sg[8];
-	sgout = &asg[8];
+	sgout = &sg[16];
 
 	if (diff_dst)
 		d = "-ddst";
@@ -535,23 +542,27 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 			goto out;
 		}
 
+		k = !!template[i].alen;
+		sg_init_table(sg, k + 1);
+		sg_set_buf(&sg[0], assoc, template[i].alen);
+		sg_set_buf(&sg[k], input,
+			   template[i].ilen + (enc ? authsize : 0));
+		output = input;
+
 		if (diff_dst) {
+			sg_init_table(sgout, k + 1);
+			sg_set_buf(&sgout[0], assoc, template[i].alen);
+
 			output = xoutbuf[0];
 			output += align_offset;
-			sg_init_one(&sg[0], input, template[i].ilen);
-			sg_init_one(&sgout[0], output, template[i].rlen);
-		} else {
-			sg_init_one(&sg[0], input,
-				    template[i].ilen + (enc ? authsize : 0));
-			output = input;
+			sg_set_buf(&sgout[k], output,
+				   template[i].rlen + (enc ? 0 : authsize));
 		}
 
-		sg_init_one(&asg[0], assoc, template[i].alen);
-
 		aead_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
 				       template[i].ilen, iv);
 
-		aead_request_set_assoc(req, asg, template[i].alen);
+		aead_request_set_ad(req, template[i].alen);
 
 		ret = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
 
@@ -631,9 +642,29 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		authsize = abs(template[i].rlen - template[i].ilen);
 
 		ret = -EINVAL;
-		sg_init_table(sg, template[i].np);
+		sg_init_table(sg, template[i].anp + template[i].np);
 		if (diff_dst)
-			sg_init_table(sgout, template[i].np);
+			sg_init_table(sgout, template[i].anp + template[i].np);
+
+		ret = -EINVAL;
+		for (k = 0, temp = 0; k < template[i].anp; k++) {
+			if (WARN_ON(offset_in_page(IDX[k]) +
+				    template[i].atap[k] > PAGE_SIZE))
+				goto out;
+			sg_set_buf(&sg[k],
+				   memcpy(axbuf[IDX[k] >> PAGE_SHIFT] +
+					  offset_in_page(IDX[k]),
+					  template[i].assoc + temp,
+					  template[i].atap[k]),
+				   template[i].atap[k]);
+			if (diff_dst)
+				sg_set_buf(&sgout[k],
+					   axbuf[IDX[k] >> PAGE_SHIFT] +
+					   offset_in_page(IDX[k]),
+					   template[i].atap[k]);
+			temp += template[i].atap[k];
+		}
+
 		for (k = 0, temp = 0; k < template[i].np; k++) {
 			if (WARN_ON(offset_in_page(IDX[k]) +
 				    template[i].tap[k] > PAGE_SIZE))
@@ -641,7 +672,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 			q = xbuf[IDX[k] >> PAGE_SHIFT] + offset_in_page(IDX[k]);
 			memcpy(q, template[i].input + temp, template[i].tap[k]);
-			sg_set_buf(&sg[k], q, template[i].tap[k]);
+			sg_set_buf(&sg[template[i].anp + k],
+				   q, template[i].tap[k]);
 
 			if (diff_dst) {
 				q = xoutbuf[IDX[k] >> PAGE_SHIFT] +
@@ -649,7 +681,8 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 
 				memset(q, 0, template[i].tap[k]);
 
-				sg_set_buf(&sgout[k], q, template[i].tap[k]);
+				sg_set_buf(&sgout[template[i].anp + k],
+					   q, template[i].tap[k]);
 			}
 
 			n = template[i].tap[k];
@@ -669,39 +702,24 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 		}
 
 		if (enc) {
-			if (WARN_ON(sg[k - 1].offset +
-				    sg[k - 1].length + authsize >
-				    PAGE_SIZE)) {
+			if (WARN_ON(sg[template[i].anp + k - 1].offset +
+				    sg[template[i].anp + k - 1].length +
+				    authsize > PAGE_SIZE)) {
 				ret = -EINVAL;
 				goto out;
 			}
 
 			if (diff_dst)
-				sgout[k - 1].length += authsize;
-			else
-				sg[k - 1].length += authsize;
-		}
-
-		sg_init_table(asg, template[i].anp);
-		ret = -EINVAL;
-		for (k = 0, temp = 0; k < template[i].anp; k++) {
-			if (WARN_ON(offset_in_page(IDX[k]) +
-				    template[i].atap[k] > PAGE_SIZE))
-				goto out;
-			sg_set_buf(&asg[k],
-				   memcpy(axbuf[IDX[k] >> PAGE_SHIFT] +
-					  offset_in_page(IDX[k]),
-					  template[i].assoc + temp,
-					  template[i].atap[k]),
-				   template[i].atap[k]);
-			temp += template[i].atap[k];
+				sgout[template[i].anp + k - 1].length +=
+					authsize;
+			sg[template[i].anp + k - 1].length += authsize;
 		}
 
 		aead_request_set_crypt(req, sg, (diff_dst) ? sgout : sg,
 				       template[i].ilen,
 				       iv);
 
-		aead_request_set_assoc(req, asg, template[i].alen);
+		aead_request_set_ad(req, template[i].alen);
 
 		ret = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
 
@@ -1814,6 +1832,147 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
 
 }
 
+static int do_test_rsa(struct crypto_akcipher *tfm,
+		       struct akcipher_testvec *vecs)
+{
+	struct akcipher_request *req;
+	void *outbuf_enc = NULL;
+	void *outbuf_dec = NULL;
+	struct tcrypt_result result;
+	unsigned int out_len_max, out_len = 0;
+	int err = -ENOMEM;
+
+	req = akcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		return err;
+
+	init_completion(&result.completion);
+	err = crypto_akcipher_setkey(tfm, vecs->key, vecs->key_len);
+	if (err)
+		goto free_req;
+
+	akcipher_request_set_crypt(req, vecs->m, outbuf_enc, vecs->m_size,
+				   out_len);
+	/* expect this to fail, and update the required buf len */
+	crypto_akcipher_encrypt(req);
+	out_len = req->dst_len;
+	if (!out_len) {
+		err = -EINVAL;
+		goto free_req;
+	}
+
+	out_len_max = out_len;
+	err = -ENOMEM;
+	outbuf_enc = kzalloc(out_len_max, GFP_KERNEL);
+	if (!outbuf_enc)
+		goto free_req;
+
+	akcipher_request_set_crypt(req, vecs->m, outbuf_enc, vecs->m_size,
+				   out_len);
+	akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				      tcrypt_complete, &result);
+
+	/* Run RSA encrypt - c = m^e mod n;*/
+	err = wait_async_op(&result, crypto_akcipher_encrypt(req));
+	if (err) {
+		pr_err("alg: rsa: encrypt test failed. err %d\n", err);
+		goto free_all;
+	}
+	if (out_len != vecs->c_size) {
+		pr_err("alg: rsa: encrypt test failed. Invalid output len\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* verify that encrypted message is equal to expected */
+	if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) {
+		pr_err("alg: rsa: encrypt test failed. Invalid output\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* Don't invoke decrypt for vectors with public key */
+	if (vecs->public_key_vec) {
+		err = 0;
+		goto free_all;
+	}
+	outbuf_dec = kzalloc(out_len_max, GFP_KERNEL);
+	if (!outbuf_dec) {
+		err = -ENOMEM;
+		goto free_all;
+	}
+	init_completion(&result.completion);
+	akcipher_request_set_crypt(req, outbuf_enc, outbuf_dec, vecs->c_size,
+				   out_len);
+
+	/* Run RSA decrypt - m = c^d mod n;*/
+	err = wait_async_op(&result, crypto_akcipher_decrypt(req));
+	if (err) {
+		pr_err("alg: rsa: decrypt test failed. err %d\n", err);
+		goto free_all;
+	}
+	out_len = req->dst_len;
+	if (out_len != vecs->m_size) {
+		pr_err("alg: rsa: decrypt test failed. Invalid output len\n");
+		err = -EINVAL;
+		goto free_all;
+	}
+	/* verify that decrypted message is equal to the original msg */
+	if (memcmp(vecs->m, outbuf_dec, vecs->m_size)) {
+		pr_err("alg: rsa: decrypt test failed. Invalid output\n");
+		err = -EINVAL;
+	}
+free_all:
+	kfree(outbuf_dec);
+	kfree(outbuf_enc);
+free_req:
+	akcipher_request_free(req);
+	return err;
+}
+
+static int test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs,
+		    unsigned int tcount)
+{
+	int ret, i;
+
+	for (i = 0; i < tcount; i++) {
+		ret = do_test_rsa(tfm, vecs++);
+		if (ret) {
+			pr_err("alg: rsa: test failed on vector %d, err=%d\n",
+			       i + 1, ret);
+			return ret;
+		}
+	}
+	return 0;
+}
+
+static int test_akcipher(struct crypto_akcipher *tfm, const char *alg,
+			 struct akcipher_testvec *vecs, unsigned int tcount)
+{
+	if (strncmp(alg, "rsa", 3) == 0)
+		return test_rsa(tfm, vecs, tcount);
+
+	return 0;
+}
+
+static int alg_test_akcipher(const struct alg_test_desc *desc,
+			     const char *driver, u32 type, u32 mask)
+{
+	struct crypto_akcipher *tfm;
+	int err = 0;
+
+	tfm = crypto_alloc_akcipher(driver, type | CRYPTO_ALG_INTERNAL, mask);
+	if (IS_ERR(tfm)) {
+		pr_err("alg: akcipher: Failed to load tfm for %s: %ld\n",
+		       driver, PTR_ERR(tfm));
+		return PTR_ERR(tfm);
+	}
+	if (desc->suite.akcipher.vecs)
+		err = test_akcipher(tfm, desc->alg, desc->suite.akcipher.vecs,
+				    desc->suite.akcipher.count);
+
+	crypto_free_akcipher(tfm);
+	return err;
+}
+
 static int alg_test_null(const struct alg_test_desc *desc,
 			     const char *driver, u32 type, u32 mask)
 {
@@ -2297,6 +2456,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "chacha20",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = chacha20_enc_tv_template,
+					.count = CHACHA20_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = chacha20_enc_tv_template,
+					.count = CHACHA20_ENC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
 		.alg = "cmac(aes)",
 		.test = alg_test_hash,
 		.suite = {
@@ -2318,6 +2492,15 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "compress_null",
 		.test = alg_test_null,
 	}, {
+		.alg = "crc32",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = {
+				.vecs = crc32_tv_template,
+				.count = CRC32_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "crc32c",
 		.test = alg_test_crc32c,
 		.fips_allowed = 1,
@@ -3095,6 +3278,10 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "jitterentropy_rng",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
 		.alg = "lrw(aes)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -3276,6 +3463,15 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "poly1305",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = {
+				.vecs = poly1305_tv_template,
+				.count = POLY1305_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "rfc3686(ctr(aes))",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
@@ -3339,6 +3535,36 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "rfc7539(chacha20,poly1305)",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = rfc7539_enc_tv_template,
+					.count = RFC7539_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = rfc7539_dec_tv_template,
+					.count = RFC7539_DEC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
+		.alg = "rfc7539esp(chacha20,poly1305)",
+		.test = alg_test_aead,
+		.suite = {
+			.aead = {
+				.enc = {
+					.vecs = rfc7539esp_enc_tv_template,
+					.count = RFC7539ESP_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = rfc7539esp_dec_tv_template,
+					.count = RFC7539ESP_DEC_TEST_VECTORS
+				},
+			}
+		}
+	}, {
 		.alg = "rmd128",
 		.test = alg_test_hash,
 		.suite = {
@@ -3375,6 +3601,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "rsa",
+		.test = alg_test_akcipher,
+		.fips_allowed = 1,
+		.suite = {
+			.akcipher = {
+				.vecs = rsa_tv_template,
+				.count = RSA_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "salsa20",
 		.test = alg_test_skcipher,
 		.suite = {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 62e2485bb428..868edf117041 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -46,6 +46,24 @@ struct hash_testvec {
 	unsigned char ksize;
 };
 
+/*
+ * cipher_testvec:	structure to describe a cipher test
+ * @key:	A pointer to a key used by the test
+ * @klen:	The length of @key
+ * @iv:		A pointer to the IV used by the test
+ * @input:	A pointer to data used as input
+ * @ilen	The length of data in @input
+ * @result:	A pointer to what the test need to produce
+ * @rlen:	The length of data in @result
+ * @fail:	If set to one, the test need to fail
+ * @wk:		Does the test need CRYPTO_TFM_REQ_WEAK_KEY
+ * 		( e.g. test needs to fail due to a weak key )
+ * @np: 	numbers of SG to distribute data in (from 1 to MAX_TAP)
+ * @tap:	How to distribute data in @np SGs
+ * @also_non_np: 	if set to 1, the test will be also done without
+ * 			splitting data in @np SGs
+ */
+
 struct cipher_testvec {
 	char *key;
 	char *iv;
@@ -54,7 +72,7 @@ struct cipher_testvec {
 	unsigned short tap[MAX_TAP];
 	int np;
 	unsigned char also_non_np;
-	unsigned char fail;
+	bool fail;
 	unsigned char wk; /* weak key flag */
 	unsigned char klen;
 	unsigned short ilen;
@@ -71,7 +89,7 @@ struct aead_testvec {
 	unsigned char atap[MAX_TAP];
 	int np;
 	int anp;
-	unsigned char fail;
+	bool fail;
 	unsigned char novrfy;	/* ccm dec verification failure expected */
 	unsigned char wk; /* weak key flag */
 	unsigned char klen;
@@ -107,9 +125,196 @@ struct drbg_testvec {
 	size_t expectedlen;
 };
 
+struct akcipher_testvec {
+	unsigned char *key;
+	unsigned char *m;
+	unsigned char *c;
+	unsigned int key_len;
+	unsigned int m_size;
+	unsigned int c_size;
+	bool public_key_vec;
+};
+
 static char zeroed_string[48];
 
 /*
+ * RSA test vectors. Borrowed from openSSL.
+ */
+#ifdef CONFIG_CRYPTO_FIPS
+#define RSA_TEST_VECTORS	2
+#else
+#define RSA_TEST_VECTORS	4
+#endif
+static struct akcipher_testvec rsa_tv_template[] = {
+	{
+#ifndef CONFIG_CRYPTO_FIPS
+	.key =
+	"\x30\x81\x88" /* sequence of 136 bytes */
+	"\x02\x41" /* modulus - integer of 65 bytes */
+	"\x00\xAA\x36\xAB\xCE\x88\xAC\xFD\xFF\x55\x52\x3C\x7F\xC4\x52\x3F"
+	"\x90\xEF\xA0\x0D\xF3\x77\x4A\x25\x9F\x2E\x62\xB4\xC5\xD9\x9C\xB5"
+	"\xAD\xB3\x00\xA0\x28\x5E\x53\x01\x93\x0E\x0C\x70\xFB\x68\x76\x93"
+	"\x9C\xE6\x16\xCE\x62\x4A\x11\xE0\x08\x6D\x34\x1E\xBC\xAC\xA0\xA1"
+	"\xF5"
+	"\x02\x01\x11" /* public key - integer of 1 byte */
+	"\x02\x40" /* private key - integer of 64 bytes */
+	"\x0A\x03\x37\x48\x62\x64\x87\x69\x5F\x5F\x30\xBC\x38\xB9\x8B\x44"
+	"\xC2\xCD\x2D\xFF\x43\x40\x98\xCD\x20\xD8\xA1\x38\xD0\x90\xBF\x64"
+	"\x79\x7C\x3F\xA7\xA2\xCD\xCB\x3C\xD1\xE0\xBD\xBA\x26\x54\xB4\xF9"
+	"\xDF\x8E\x8A\xE5\x9D\x73\x3D\x9F\x33\xB3\x01\x62\x4A\xFD\x1D\x51",
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x63\x1c\xcd\x7b\xe1\x7e\xe4\xde\xc9\xa8\x89\xa1\x74\xcb\x3c\x63"
+	"\x7d\x24\xec\x83\xc3\x15\xe4\x7f\x73\x05\x34\xd1\xec\x22\xbb\x8a"
+	"\x5e\x32\x39\x6d\xc1\x1d\x7d\x50\x3b\x9f\x7a\xad\xf0\x2e\x25\x53"
+	"\x9f\x6e\xbd\x4c\x55\x84\x0c\x9b\xcf\x1a\x4b\x51\x1e\x9e\x0c\x06",
+	.key_len = 139,
+	.m_size = 8,
+	.c_size = 64,
+	}, {
+	.key =
+	"\x30\x82\x01\x0B" /* sequence of 267 bytes */
+	"\x02\x81\x81" /* modulus - integer of 129 bytes */
+	"\x00\xBB\xF8\x2F\x09\x06\x82\xCE\x9C\x23\x38\xAC\x2B\x9D\xA8\x71"
+	"\xF7\x36\x8D\x07\xEE\xD4\x10\x43\xA4\x40\xD6\xB6\xF0\x74\x54\xF5"
+	"\x1F\xB8\xDF\xBA\xAF\x03\x5C\x02\xAB\x61\xEA\x48\xCE\xEB\x6F\xCD"
+	"\x48\x76\xED\x52\x0D\x60\xE1\xEC\x46\x19\x71\x9D\x8A\x5B\x8B\x80"
+	"\x7F\xAF\xB8\xE0\xA3\xDF\xC7\x37\x72\x3E\xE6\xB4\xB7\xD9\x3A\x25"
+	"\x84\xEE\x6A\x64\x9D\x06\x09\x53\x74\x88\x34\xB2\x45\x45\x98\x39"
+	"\x4E\xE0\xAA\xB1\x2D\x7B\x61\xA5\x1F\x52\x7A\x9A\x41\xF6\xC1\x68"
+	"\x7F\xE2\x53\x72\x98\xCA\x2A\x8F\x59\x46\xF8\xE5\xFD\x09\x1D\xBD"
+	"\xCB"
+	"\x02\x01\x11" /* public key - integer of 1 byte */
+	"\x02\x81\x81"  /* private key - integer of 129 bytes */
+	"\x00\xA5\xDA\xFC\x53\x41\xFA\xF2\x89\xC4\xB9\x88\xDB\x30\xC1\xCD"
+	"\xF8\x3F\x31\x25\x1E\x06\x68\xB4\x27\x84\x81\x38\x01\x57\x96\x41"
+	"\xB2\x94\x10\xB3\xC7\x99\x8D\x6B\xC4\x65\x74\x5E\x5C\x39\x26\x69"
+	"\xD6\x87\x0D\xA2\xC0\x82\xA9\x39\xE3\x7F\xDC\xB8\x2E\xC9\x3E\xDA"
+	"\xC9\x7F\xF3\xAD\x59\x50\xAC\xCF\xBC\x11\x1C\x76\xF1\xA9\x52\x94"
+	"\x44\xE5\x6A\xAF\x68\xC5\x6C\x09\x2C\xD3\x8D\xC3\xBE\xF5\xD2\x0A"
+	"\x93\x99\x26\xED\x4F\x74\xA1\x3E\xDD\xFB\xE1\xA1\xCE\xCC\x48\x94"
+	"\xAF\x94\x28\xC2\xB7\xB8\x88\x3F\xE4\x46\x3A\x4B\xC8\x5B\x1C\xB3"
+	"\xC1",
+	.key_len = 271,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\x74\x1b\x55\xac\x47\xb5\x08\x0a\x6e\x2b\x2d\xf7\x94\xb8\x8a\x95"
+	"\xed\xa3\x6b\xc9\x29\xee\xb2\x2c\x80\xc3\x39\x3b\x8c\x62\x45\x72"
+	"\xc2\x7f\x74\x81\x91\x68\x44\x48\x5a\xdc\xa0\x7e\xa7\x0b\x05\x7f"
+	"\x0e\xa0\x6c\xe5\x8f\x19\x4d\xce\x98\x47\x5f\xbd\x5f\xfe\xe5\x34"
+	"\x59\x89\xaf\xf0\xba\x44\xd7\xf1\x1a\x50\x72\xef\x5e\x4a\xb6\xb7"
+	"\x54\x34\xd1\xc4\x83\x09\xdf\x0f\x91\x5f\x7d\x91\x70\x2f\xd4\x13"
+	"\xcc\x5e\xa4\x6c\xc3\x4d\x28\xef\xda\xaf\xec\x14\x92\xfc\xa3\x75"
+	"\x13\xb4\xc1\xa1\x11\xfc\x40\x2f\x4c\x9d\xdf\x16\x76\x11\x20\x6b",
+	.m_size = 8,
+	.c_size = 128,
+	}, {
+#endif
+	.key =
+	"\x30\x82\x02\x0D" /* sequence of 525 bytes */
+	"\x02\x82\x01\x00" /* modulus - integer of 256 bytes */
+	"\xDB\x10\x1A\xC2\xA3\xF1\xDC\xFF\x13\x6B\xED\x44\xDF\xF0\x02\x6D"
+	"\x13\xC7\x88\xDA\x70\x6B\x54\xF1\xE8\x27\xDC\xC3\x0F\x99\x6A\xFA"
+	"\xC6\x67\xFF\x1D\x1E\x3C\x1D\xC1\xB5\x5F\x6C\xC0\xB2\x07\x3A\x6D"
+	"\x41\xE4\x25\x99\xAC\xFC\xD2\x0F\x02\xD3\xD1\x54\x06\x1A\x51\x77"
+	"\xBD\xB6\xBF\xEA\xA7\x5C\x06\xA9\x5D\x69\x84\x45\xD7\xF5\x05\xBA"
+	"\x47\xF0\x1B\xD7\x2B\x24\xEC\xCB\x9B\x1B\x10\x8D\x81\xA0\xBE\xB1"
+	"\x8C\x33\xE4\x36\xB8\x43\xEB\x19\x2A\x81\x8D\xDE\x81\x0A\x99\x48"
+	"\xB6\xF6\xBC\xCD\x49\x34\x3A\x8F\x26\x94\xE3\x28\x82\x1A\x7C\x8F"
+	"\x59\x9F\x45\xE8\x5D\x1A\x45\x76\x04\x56\x05\xA1\xD0\x1B\x8C\x77"
+	"\x6D\xAF\x53\xFA\x71\xE2\x67\xE0\x9A\xFE\x03\xA9\x85\xD2\xC9\xAA"
+	"\xBA\x2A\xBC\xF4\xA0\x08\xF5\x13\x98\x13\x5D\xF0\xD9\x33\x34\x2A"
+	"\x61\xC3\x89\x55\xF0\xAE\x1A\x9C\x22\xEE\x19\x05\x8D\x32\xFE\xEC"
+	"\x9C\x84\xBA\xB7\xF9\x6C\x3A\x4F\x07\xFC\x45\xEB\x12\xE5\x7B\xFD"
+	"\x55\xE6\x29\x69\xD1\xC2\xE8\xB9\x78\x59\xF6\x79\x10\xC6\x4E\xEB"
+	"\x6A\x5E\xB9\x9A\xC7\xC4\x5B\x63\xDA\xA3\x3F\x5E\x92\x7A\x81\x5E"
+	"\xD6\xB0\xE2\x62\x8F\x74\x26\xC2\x0C\xD3\x9A\x17\x47\xE6\x8E\xAB"
+	"\x02\x03\x01\x00\x01" /* public key - integer of 3 bytes */
+	"\x02\x82\x01\x00" /* private key - integer of 256 bytes */
+	"\x52\x41\xF4\xDA\x7B\xB7\x59\x55\xCA\xD4\x2F\x0F\x3A\xCB\xA4\x0D"
+	"\x93\x6C\xCC\x9D\xC1\xB2\xFB\xFD\xAE\x40\x31\xAC\x69\x52\x21\x92"
+	"\xB3\x27\xDF\xEA\xEE\x2C\x82\xBB\xF7\x40\x32\xD5\x14\xC4\x94\x12"
+	"\xEC\xB8\x1F\xCA\x59\xE3\xC1\x78\xF3\x85\xD8\x47\xA5\xD7\x02\x1A"
+	"\x65\x79\x97\x0D\x24\xF4\xF0\x67\x6E\x75\x2D\xBF\x10\x3D\xA8\x7D"
+	"\xEF\x7F\x60\xE4\xE6\x05\x82\x89\x5D\xDF\xC6\xD2\x6C\x07\x91\x33"
+	"\x98\x42\xF0\x02\x00\x25\x38\xC5\x85\x69\x8A\x7D\x2F\x95\x6C\x43"
+	"\x9A\xB8\x81\xE2\xD0\x07\x35\xAA\x05\x41\xC9\x1E\xAF\xE4\x04\x3B"
+	"\x19\xB8\x73\xA2\xAC\x4B\x1E\x66\x48\xD8\x72\x1F\xAC\xF6\xCB\xBC"
+	"\x90\x09\xCA\xEC\x0C\xDC\xF9\x2C\xD7\xEB\xAE\xA3\xA4\x47\xD7\x33"
+	"\x2F\x8A\xCA\xBC\x5E\xF0\x77\xE4\x97\x98\x97\xC7\x10\x91\x7D\x2A"
+	"\xA6\xFF\x46\x83\x97\xDE\xE9\xE2\x17\x03\x06\x14\xE2\xD7\xB1\x1D"
+	"\x77\xAF\x51\x27\x5B\x5E\x69\xB8\x81\xE6\x11\xC5\x43\x23\x81\x04"
+	"\x62\xFF\xE9\x46\xB8\xD8\x44\xDB\xA5\xCC\x31\x54\x34\xCE\x3E\x82"
+	"\xD6\xBF\x7A\x0B\x64\x21\x6D\x88\x7E\x5B\x45\x12\x1E\x63\x8D\x49"
+	"\xA7\x1D\xD9\x1E\x06\xCD\xE8\xBA\x2C\x8C\x69\x32\xEA\xBE\x60\x71",
+	.key_len = 529,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\xb2\x97\x76\xb4\xae\x3e\x38\x3c\x7e\x64\x1f\xcc\xa2\x7f\xf6\xbe"
+	"\xcf\x49\xbc\x48\xd3\x6c\x8f\x0a\x0e\xc1\x73\xbd\x7b\x55\x79\x36"
+	"\x0e\xa1\x87\x88\xb9\x2c\x90\xa6\x53\x5e\xe9\xef\xc4\xe2\x4d\xdd"
+	"\xf7\xa6\x69\x82\x3f\x56\xa4\x7b\xfb\x62\xe0\xae\xb8\xd3\x04\xb3"
+	"\xac\x5a\x15\x2a\xe3\x19\x9b\x03\x9a\x0b\x41\xda\x64\xec\x0a\x69"
+	"\xfc\xf2\x10\x92\xf3\xc1\xbf\x84\x7f\xfd\x2c\xae\xc8\xb5\xf6\x41"
+	"\x70\xc5\x47\x03\x8a\xf8\xff\x6f\x3f\xd2\x6f\x09\xb4\x22\xf3\x30"
+	"\xbe\xa9\x85\xcb\x9c\x8d\xf9\x8f\xeb\x32\x91\xa2\x25\x84\x8f\xf5"
+	"\xdc\xc7\x06\x9c\x2d\xe5\x11\x2c\x09\x09\x87\x09\xa9\xf6\x33\x73"
+	"\x90\xf1\x60\xf2\x65\xdd\x30\xa5\x66\xce\x62\x7b\xd0\xf8\x2d\x3d"
+	"\x19\x82\x77\xe3\x0a\x5f\x75\x2f\x8e\xb1\xe5\xe8\x91\x35\x1b\x3b"
+	"\x33\xb7\x66\x92\xd1\xf2\x8e\x6f\xe5\x75\x0c\xad\x36\xfb\x4e\xd0"
+	"\x66\x61\xbd\x49\xfe\xf4\x1a\xa2\x2b\x49\xfe\x03\x4c\x74\x47\x8d"
+	"\x9a\x66\xb2\x49\x46\x4d\x77\xea\x33\x4d\x6b\x3c\xb4\x49\x4a\xc6"
+	"\x7d\x3d\xb5\xb9\x56\x41\x15\x67\x0f\x94\x3c\x93\x65\x27\xe0\x21"
+	"\x5d\x59\xc3\x62\xd5\xa6\xda\x38\x26\x22\x5e\x34\x1c\x94\xaf\x98",
+	.m_size = 8,
+	.c_size = 256,
+	}, {
+	.key =
+	"\x30\x82\x01\x09" /* sequence of 265 bytes */
+	"\x02\x82\x01\x00" /* modulus - integer of 256 bytes */
+	"\xDB\x10\x1A\xC2\xA3\xF1\xDC\xFF\x13\x6B\xED\x44\xDF\xF0\x02\x6D"
+	"\x13\xC7\x88\xDA\x70\x6B\x54\xF1\xE8\x27\xDC\xC3\x0F\x99\x6A\xFA"
+	"\xC6\x67\xFF\x1D\x1E\x3C\x1D\xC1\xB5\x5F\x6C\xC0\xB2\x07\x3A\x6D"
+	"\x41\xE4\x25\x99\xAC\xFC\xD2\x0F\x02\xD3\xD1\x54\x06\x1A\x51\x77"
+	"\xBD\xB6\xBF\xEA\xA7\x5C\x06\xA9\x5D\x69\x84\x45\xD7\xF5\x05\xBA"
+	"\x47\xF0\x1B\xD7\x2B\x24\xEC\xCB\x9B\x1B\x10\x8D\x81\xA0\xBE\xB1"
+	"\x8C\x33\xE4\x36\xB8\x43\xEB\x19\x2A\x81\x8D\xDE\x81\x0A\x99\x48"
+	"\xB6\xF6\xBC\xCD\x49\x34\x3A\x8F\x26\x94\xE3\x28\x82\x1A\x7C\x8F"
+	"\x59\x9F\x45\xE8\x5D\x1A\x45\x76\x04\x56\x05\xA1\xD0\x1B\x8C\x77"
+	"\x6D\xAF\x53\xFA\x71\xE2\x67\xE0\x9A\xFE\x03\xA9\x85\xD2\xC9\xAA"
+	"\xBA\x2A\xBC\xF4\xA0\x08\xF5\x13\x98\x13\x5D\xF0\xD9\x33\x34\x2A"
+	"\x61\xC3\x89\x55\xF0\xAE\x1A\x9C\x22\xEE\x19\x05\x8D\x32\xFE\xEC"
+	"\x9C\x84\xBA\xB7\xF9\x6C\x3A\x4F\x07\xFC\x45\xEB\x12\xE5\x7B\xFD"
+	"\x55\xE6\x29\x69\xD1\xC2\xE8\xB9\x78\x59\xF6\x79\x10\xC6\x4E\xEB"
+	"\x6A\x5E\xB9\x9A\xC7\xC4\x5B\x63\xDA\xA3\x3F\x5E\x92\x7A\x81\x5E"
+	"\xD6\xB0\xE2\x62\x8F\x74\x26\xC2\x0C\xD3\x9A\x17\x47\xE6\x8E\xAB"
+	"\x02\x03\x01\x00\x01", /* public key - integer of 3 bytes */
+	.key_len = 269,
+	.m = "\x54\x85\x9b\x34\x2c\x49\xea\x2a",
+	.c =
+	"\xb2\x97\x76\xb4\xae\x3e\x38\x3c\x7e\x64\x1f\xcc\xa2\x7f\xf6\xbe"
+	"\xcf\x49\xbc\x48\xd3\x6c\x8f\x0a\x0e\xc1\x73\xbd\x7b\x55\x79\x36"
+	"\x0e\xa1\x87\x88\xb9\x2c\x90\xa6\x53\x5e\xe9\xef\xc4\xe2\x4d\xdd"
+	"\xf7\xa6\x69\x82\x3f\x56\xa4\x7b\xfb\x62\xe0\xae\xb8\xd3\x04\xb3"
+	"\xac\x5a\x15\x2a\xe3\x19\x9b\x03\x9a\x0b\x41\xda\x64\xec\x0a\x69"
+	"\xfc\xf2\x10\x92\xf3\xc1\xbf\x84\x7f\xfd\x2c\xae\xc8\xb5\xf6\x41"
+	"\x70\xc5\x47\x03\x8a\xf8\xff\x6f\x3f\xd2\x6f\x09\xb4\x22\xf3\x30"
+	"\xbe\xa9\x85\xcb\x9c\x8d\xf9\x8f\xeb\x32\x91\xa2\x25\x84\x8f\xf5"
+	"\xdc\xc7\x06\x9c\x2d\xe5\x11\x2c\x09\x09\x87\x09\xa9\xf6\x33\x73"
+	"\x90\xf1\x60\xf2\x65\xdd\x30\xa5\x66\xce\x62\x7b\xd0\xf8\x2d\x3d"
+	"\x19\x82\x77\xe3\x0a\x5f\x75\x2f\x8e\xb1\xe5\xe8\x91\x35\x1b\x3b"
+	"\x33\xb7\x66\x92\xd1\xf2\x8e\x6f\xe5\x75\x0c\xad\x36\xfb\x4e\xd0"
+	"\x66\x61\xbd\x49\xfe\xf4\x1a\xa2\x2b\x49\xfe\x03\x4c\x74\x47\x8d"
+	"\x9a\x66\xb2\x49\x46\x4d\x77\xea\x33\x4d\x6b\x3c\xb4\x49\x4a\xc6"
+	"\x7d\x3d\xb5\xb9\x56\x41\x15\x67\x0f\x94\x3c\x93\x65\x27\xe0\x21"
+	"\x5d\x59\xc3\x62\xd5\xa6\xda\x38\x26\x22\x5e\x34\x1c\x94\xaf\x98",
+	.m_size = 8,
+	.c_size = 256,
+	.public_key_vec = true,
+	}
+};
+
+/*
  * MD4 test vectors from RFC1320
  */
 #define MD4_TEST_VECTORS	7
@@ -1822,7 +2027,7 @@ static struct hash_testvec tgr128_tv_template[] = {
 	},
 };
 
-#define GHASH_TEST_VECTORS 5
+#define GHASH_TEST_VECTORS 6
 
 static struct hash_testvec ghash_tv_template[] =
 {
@@ -1875,6 +2080,63 @@ static struct hash_testvec ghash_tv_template[] =
 		.psize	= 20,
 		.digest	= "\xf8\x94\x87\x2a\x4b\x63\x99\x28"
 			  "\x23\xf7\x93\xf7\x19\xf5\x96\xd9",
+	}, {
+		.key	= "\x0a\x1b\x2c\x3d\x4e\x5f\x64\x71"
+			"\x82\x93\xa4\xb5\xc6\xd7\xe8\xf9",
+		.ksize	= 16,
+		.plaintext = "\x56\x6f\x72\x20\x6c\x61\x75\x74"
+			"\x65\x72\x20\x4c\x61\x75\x73\x63"
+			"\x68\x65\x6e\x20\x75\x6e\x64\x20"
+			"\x53\x74\x61\x75\x6e\x65\x6e\x20"
+			"\x73\x65\x69\x20\x73\x74\x69\x6c"
+			"\x6c\x2c\x0a\x64\x75\x20\x6d\x65"
+			"\x69\x6e\x20\x74\x69\x65\x66\x74"
+			"\x69\x65\x66\x65\x73\x20\x4c\x65"
+			"\x62\x65\x6e\x3b\x0a\x64\x61\x73"
+			"\x73\x20\x64\x75\x20\x77\x65\x69"
+			"\xc3\x9f\x74\x20\x77\x61\x73\x20"
+			"\x64\x65\x72\x20\x57\x69\x6e\x64"
+			"\x20\x64\x69\x72\x20\x77\x69\x6c"
+			"\x6c\x2c\x0a\x65\x68\x20\x6e\x6f"
+			"\x63\x68\x20\x64\x69\x65\x20\x42"
+			"\x69\x72\x6b\x65\x6e\x20\x62\x65"
+			"\x62\x65\x6e\x2e\x0a\x0a\x55\x6e"
+			"\x64\x20\x77\x65\x6e\x6e\x20\x64"
+			"\x69\x72\x20\x65\x69\x6e\x6d\x61"
+			"\x6c\x20\x64\x61\x73\x20\x53\x63"
+			"\x68\x77\x65\x69\x67\x65\x6e\x20"
+			"\x73\x70\x72\x61\x63\x68\x2c\x0a"
+			"\x6c\x61\x73\x73\x20\x64\x65\x69"
+			"\x6e\x65\x20\x53\x69\x6e\x6e\x65"
+			"\x20\x62\x65\x73\x69\x65\x67\x65"
+			"\x6e\x2e\x0a\x4a\x65\x64\x65\x6d"
+			"\x20\x48\x61\x75\x63\x68\x65\x20"
+			"\x67\x69\x62\x74\x20\x64\x69\x63"
+			"\x68\x2c\x20\x67\x69\x62\x20\x6e"
+			"\x61\x63\x68\x2c\x0a\x65\x72\x20"
+			"\x77\x69\x72\x64\x20\x64\x69\x63"
+			"\x68\x20\x6c\x69\x65\x62\x65\x6e"
+			"\x20\x75\x6e\x64\x20\x77\x69\x65"
+			"\x67\x65\x6e\x2e\x0a\x0a\x55\x6e"
+			"\x64\x20\x64\x61\x6e\x6e\x20\x6d"
+			"\x65\x69\x6e\x65\x20\x53\x65\x65"
+			"\x6c\x65\x20\x73\x65\x69\x74\x20"
+			"\x77\x65\x69\x74\x2c\x20\x73\x65"
+			"\x69\x20\x77\x65\x69\x74\x2c\x0a"
+			"\x64\x61\x73\x73\x20\x64\x69\x72"
+			"\x20\x64\x61\x73\x20\x4c\x65\x62"
+			"\x65\x6e\x20\x67\x65\x6c\x69\x6e"
+			"\x67\x65\x2c\x0a\x62\x72\x65\x69"
+			"\x74\x65\x20\x64\x69\x63\x68\x20"
+			"\x77\x69\x65\x20\x65\x69\x6e\x20"
+			"\x46\x65\x69\x65\x72\x6b\x6c\x65"
+			"\x69\x64\x0a\xc3\xbc\x62\x65\x72"
+			"\x20\x64\x69\x65\x20\x73\x69\x6e"
+			"\x6e\x65\x6e\x64\x65\x6e\x20\x44"
+			"\x69\x6e\x67\x65\x2e\x2e\x2e\x0a",
+		.psize	= 400,
+		.digest = "\xad\xb1\xc1\xe9\x56\x70\x31\x1d"
+			"\xbb\x5b\xdf\x5e\x70\x72\x1a\x57",
 	},
 };
 
@@ -2969,6 +3231,254 @@ static struct hash_testvec hmac_sha512_tv_template[] = {
 };
 
 /*
+ * Poly1305 test vectors from RFC7539 A.3.
+ */
+
+#define POLY1305_TEST_VECTORS	11
+
+static struct hash_testvec poly1305_tv_template[] = {
+	{ /* Test Vector #1 */
+		.plaintext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 96,
+		.digest		= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #2 */
+		.plaintext	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e"
+				  "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+				  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+				  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+				  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+				  "\x64\x65\x64\x20\x62\x79\x20\x74"
+				  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+				  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+				  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+				  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+				  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+				  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+				  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+				  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+				  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+				  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+				  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+				  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+				  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+				  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+				  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+				  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+				  "\x45\x54\x46\x20\x61\x63\x74\x69"
+				  "\x76\x69\x74\x79\x20\x69\x73\x20"
+				  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+				  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+				  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+				  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+				  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+				  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+				  "\x54\x46\x20\x73\x65\x73\x73\x69"
+				  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+				  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+				  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+				  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+				  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+				  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+				  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+				  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+				  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+				  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+				  "\x20\x77\x68\x69\x63\x68\x20\x61"
+				  "\x72\x65\x20\x61\x64\x64\x72\x65"
+				  "\x73\x73\x65\x64\x20\x74\x6f",
+		.psize		= 407,
+		.digest		= "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e",
+	}, { /* Test Vector #3 */
+		.plaintext	= "\x36\xe5\xf6\xb5\xc5\xe0\x60\x70"
+				  "\xf0\xef\xca\x96\x22\x7a\x86\x3e"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+				  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+				  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+				  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+				  "\x64\x65\x64\x20\x62\x79\x20\x74"
+				  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+				  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+				  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+				  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+				  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+				  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+				  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+				  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+				  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+				  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+				  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+				  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+				  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+				  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+				  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+				  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+				  "\x45\x54\x46\x20\x61\x63\x74\x69"
+				  "\x76\x69\x74\x79\x20\x69\x73\x20"
+				  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+				  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+				  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+				  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+				  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+				  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+				  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+				  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+				  "\x54\x46\x20\x73\x65\x73\x73\x69"
+				  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+				  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+				  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+				  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+				  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+				  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+				  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+				  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+				  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+				  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+				  "\x20\x77\x68\x69\x63\x68\x20\x61"
+				  "\x72\x65\x20\x61\x64\x64\x72\x65"
+				  "\x73\x73\x65\x64\x20\x74\x6f",
+		.psize		= 407,
+		.digest		= "\xf3\x47\x7e\x7c\xd9\x54\x17\xaf"
+				  "\x89\xa6\xb8\x79\x4c\x31\x0c\xf0",
+	}, { /* Test Vector #4 */
+		.plaintext	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+				  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+				  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+				  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+				  "\x27\x54\x77\x61\x73\x20\x62\x72"
+				  "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+				  "\x6e\x64\x20\x74\x68\x65\x20\x73"
+				  "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+				  "\x76\x65\x73\x0a\x44\x69\x64\x20"
+				  "\x67\x79\x72\x65\x20\x61\x6e\x64"
+				  "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+				  "\x69\x6e\x20\x74\x68\x65\x20\x77"
+				  "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+				  "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+				  "\x65\x72\x65\x20\x74\x68\x65\x20"
+				  "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+				  "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+				  "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+				  "\x72\x61\x74\x68\x73\x20\x6f\x75"
+				  "\x74\x67\x72\x61\x62\x65\x2e",
+		.psize		= 159,
+		.digest		= "\x45\x41\x66\x9a\x7e\xaa\xee\x61"
+				  "\xe7\x08\xdc\x7c\xbc\xc5\xeb\x62",
+	}, { /* Test Vector #5 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.psize		= 48,
+		.digest		= "\x03\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #6 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 48,
+		.digest		= "\x03\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #7 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xf0\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\x11\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 80,
+		.digest		= "\x05\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #8 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xfb\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+				  "\xfe\xfe\xfe\xfe\xfe\xfe\xfe\xfe"
+				  "\x01\x01\x01\x01\x01\x01\x01\x01"
+				  "\x01\x01\x01\x01\x01\x01\x01\x01",
+		.psize		= 80,
+		.digest		= "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #9 */
+		.plaintext	= "\x02\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xfd\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+		.psize		= 48,
+		.digest		= "\xfa\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff",
+	}, { /* Test Vector #10 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x04\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xe3\x35\x94\xd7\x50\x5e\x43\xb9"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x33\x94\xd7\x50\x5e\x43\x79\xcd"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 96,
+		.digest		= "\x14\x00\x00\x00\x00\x00\x00\x00"
+				  "\x55\x00\x00\x00\x00\x00\x00\x00",
+	}, { /* Test Vector #11 */
+		.plaintext	= "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x04\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\xe3\x35\x94\xd7\x50\x5e\x43\xb9"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x33\x94\xd7\x50\x5e\x43\x79\xcd"
+				  "\x01\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize		= 80,
+		.digest		= "\x13\x00\x00\x00\x00\x00\x00\x00"
+				  "\x00\x00\x00\x00\x00\x00\x00\x00",
+	},
+};
+
+/*
  * DES test vectors.
  */
 #define DES_ENC_TEST_VECTORS		11
@@ -3018,7 +3528,7 @@ static struct cipher_testvec des_enc_tv_template[] = {
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90",
 		.rlen	= 24,
 	}, { /* Weak key */
-		.fail	= 1,
+		.fail	= true,
 		.wk	= 1,
 		.key	= "\x01\x01\x01\x01\x01\x01\x01\x01",
 		.klen	= 8,
@@ -13629,8 +14139,8 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = {
 #define AES_CTR_3686_DEC_TEST_VECTORS 6
 #define AES_GCM_ENC_TEST_VECTORS 9
 #define AES_GCM_DEC_TEST_VECTORS 8
-#define AES_GCM_4106_ENC_TEST_VECTORS 7
-#define AES_GCM_4106_DEC_TEST_VECTORS 7
+#define AES_GCM_4106_ENC_TEST_VECTORS 23
+#define AES_GCM_4106_DEC_TEST_VECTORS 23
 #define AES_GCM_4543_ENC_TEST_VECTORS 1
 #define AES_GCM_4543_DEC_TEST_VECTORS 2
 #define AES_CCM_ENC_TEST_VECTORS 8
@@ -19789,6 +20299,428 @@ static struct aead_testvec aes_gcm_rfc4106_enc_tv_template[] = {
 			  "\x37\x08\x1C\xCF\xBA\x5D\x71\x46"
 			  "\x80\x72\xB0\x4C\x82\x0D\x60\x3C",
 		.rlen	= 208,
+	}, { /* From draft-mcgrew-gcm-test-01 */
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B\x68",
+		.klen	= 20,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.input	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00",
+		.alen	= 12,
+		.result	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
+			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
+			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
+			  "\x34\x85\x09\xFA\x13\xCE\xAC\x34"
+			  "\xCF\xA2\x43\x6F\x14\xA3\xF3\xCF"
+			  "\x65\x92\x5B\xF1\xF4\xA1\x3C\x5D"
+			  "\x15\xB2\x1E\x18\x84\xF5\xFF\x62"
+			  "\x47\xAE\xAB\xB7\x86\xB9\x3B\xCE"
+			  "\x61\xBC\x17\xD7\x68\xFD\x97\x32"
+			  "\x45\x90\x18\x14\x8F\x6C\xBE\x72"
+			  "\x2F\xD0\x47\x96\x56\x2D\xFD\xB4",
+		.rlen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 20,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.result	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
+			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
+			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
+			  "\x1B\xA7\x6D\x5D\x11\x4D\x2A\x5C"
+			  "\x3D\xE8\x18\x27\xC1\x0E\x9A\x4F"
+			  "\x51\x33\x0D\x0E\xEC\x41\x66\x42"
+			  "\xCF\xBB\x85\xA5\xB4\x7E\x48\xA4"
+			  "\xEC\x3B\x9B\xA9\x5D\x91\x8B\xD1"
+			  "\x83\xB7\x0D\x3A\xA8\xBC\x6E\xE4"
+			  "\xC3\x09\xE9\xD8\x5A\x41\xAD\x4A",
+		.rlen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33\x44",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.input	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
+		.alen	= 8,
+		.result	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
+			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
+			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
+			  "\x06\xEF\xAE\x9D\x65\xA5\xD7\x63"
+			  "\x74\x8A\x63\x79\x85\x77\x1D\x34"
+			  "\x7F\x05\x45\x65\x9F\x14\xE9\x9D"
+			  "\xEF\x84\x2D\x8E\xB3\x35\xF4\xEE"
+			  "\xCF\xDB\xF8\x31\x82\x4B\x4C\x49"
+			  "\x15\x95\x6C\x96",
+		.rlen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen	= 20,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 8,
+		.result	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
+			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
+			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
+			  "\xF5\xFD\xCD\xFF\xF5\xE9\xA2\x84"
+			  "\x45\x64\x76\x49\x27\x19\xFF\xB6"
+			  "\x4D\xE7\xD9\xDC\xA1\xE1\xD8\x94"
+			  "\xBC\x3B\xD5\x78\x73\xED\x4D\x18"
+			  "\x1D\x19\xD4\xD5\xC8\xC1\x8A\xF3"
+			  "\xF8\x21\xD4\x96\xEE\xB0\x96\xE9"
+			  "\x8A\xD2\xB6\x9E\x47\x99\xC7\x1D",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.ilen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
+			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
+			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
+			  "\x0D\x11\x38\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x17\x55\xE6\x66\x2B\x4C\x8D\x0D"
+			  "\x1F\x5E\x22\x73\x95\x30\x32\x0A"
+			  "\xE0\xD7\x31\xCC\x97\x8E\xCA\xFA"
+			  "\xEA\xE8\x8F\x00\xE8\x0D\x6E\x48",
+		.rlen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.ilen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
+			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
+			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
+			  "\x0E\x13\x79\xED\x36\x9F\x07\x1F"
+			  "\x35\xE0\x34\xBE\x95\xF1\x12\xE4"
+			  "\xE7\xD0\x5D\x35",
+		.rlen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 28,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.input	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.result	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
+			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
+			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
+			  "\x87\xB8\x85\x8B\x5B\xFB\xDB\xD0"
+			  "\x31\x5B\x27\x45\x21\x44\xCC\x77"
+			  "\x95\x45\x7B\x96\x52\x03\x7F\x53"
+			  "\x18\x02\x7B\x5B\x4C\xD7\xA6\x36",
+		.rlen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.result	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
+			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
+			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
+			  "\xC3\x49\xC1\xD2\xFB\xEC\x16\x8F"
+			  "\x91\x90\xFE\xEB\xAF\x2C\xB0\x19"
+			  "\x84\xE6\x58\x63\x96\x5D\x74\x72"
+			  "\xB7\x9D\xA3\x45\xE0\xE7\x80\x19"
+			  "\x1F\x0D\x2F\x0E\x0F\x49\x6C\x22"
+			  "\x6F\x21\x27\xB2\x7D\xB3\x57\x24"
+			  "\xE7\x84\x5D\x68\x65\x1F\x57\xE6"
+			  "\x5F\x35\x4F\x75\xFF\x17\x01\x57"
+			  "\x69\x62\x34\x36",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.ilen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.result	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
+			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
+			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
+			  "\x9D\x52\x4A\x30\x18\xD9\xA5\x7F"
+			  "\xF4\xD3\xA3\x1C\xE6\x73\x11\x9E"
+			  "\x45\x16\x26\xC2\x41\x57\x71\xE3"
+			  "\xB7\xEE\xBC\xA6\x14\xC8\x9B\x35",
+		.rlen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.ilen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
+			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
+			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
+			  "\x0F\x24\xB0\xA9\x7D\x54\x18\x28"
+			  "\x00\xCA\xDB\x0F\x68\xD9\x9E\xF0"
+			  "\xE0\xC0\xC8\x9A\xE9\xBE\xA8\x88"
+			  "\x4E\x52\xD6\x5B\xC1\xAF\xD0\x74"
+			  "\x0F\x74\x24\x44\x74\x7B\x5B\x39"
+			  "\xAB\x53\x31\x63\xAA\xD4\x55\x0E"
+			  "\xE5\x16\x09\x75\xCD\xB6\x08\xC5"
+			  "\x76\x91\x89\x60\x97\x63\xB8\xE1"
+			  "\x8C\xAA\x81\xE2",
+		.rlen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.input	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.ilen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.result	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
+			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
+			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
+			  "\x26\x50\x8B\xEB\xD2\xDC\xEB\x18"
+			  "\xD0\xA6\xDF\x10\xE5\x48\x7D\xF0"
+			  "\x74\x11\x3E\x14\xC6\x41\x02\x4E"
+			  "\x3E\x67\x73\xD9\x1A\x62\xEE\x42"
+			  "\x9B\x04\x3A\x10\xE3\xEF\xE6\xB0"
+			  "\x12\xA4\x93\x63\x41\x23\x64\xF8"
+			  "\xC0\xCA\xC5\x87\xF2\x49\xE5\x6B"
+			  "\x11\xE2\x4F\x30\xE4\x4C\xCC\x76",
+		.rlen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42\x67",
+		.klen	= 20,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.input	= "\x01\x02\x02\x01",
+		.ilen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
+		.alen	= 8,
+		.result	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
+			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
+			  "\x04\xBE\xF2\x70",
+		.rlen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.input	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.ilen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.result	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
+			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
+			  "\x43\x33\x21\x64\x41\x25\x03\x52"
+			  "\x43\x03\xED\x3C\x6C\x5F\x28\x38"
+			  "\x43\xAF\x8C\x3E",
+		.rlen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72\x6E",
+		.klen	= 36,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF",
+		.alen	= 12,
+		.result	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
+			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
+			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
+			  "\x4A\x27\x4B\x39\xB4\x9C\x3A\x86"
+			  "\x4C\xD3\xD7\x8C\xA4\xAE\x68\xA3"
+			  "\x2B\x42\x45\x8F\xB5\x7D\xBE\x82"
+			  "\x1D\xCC\x63\xB9\xD0\x93\x7B\xA2"
+			  "\x94\x5F\x66\x93\x68\x66\x1A\x32"
+			  "\x9F\xB4\xC0\x53",
+		.rlen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.input	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.ilen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.result	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
+			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
+			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
+			  "\x0D\x11\x7C\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x63\x21\x93\x06\x84\xEE\xCA\xDB"
+			  "\x56\x91\x25\x46\xE7\xA9\x5C\x97"
+			  "\x40\xD7\xCB\x05",
+		.rlen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C\x64",
+		.klen	= 20,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.input	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.ilen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07",
+		.alen	= 12,
+		.result	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
+			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
+			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
+			  "\xAC\xDA\x68\x94\xBC\x61\x90\x69"
+			  "\xEF\x9C\xBC\x28\xFE\x1B\x56\xA7"
+			  "\xC4\xE0\xD5\x8C\x86\xCD\x2B\xC0",
+		.rlen	= 48,
 	}
 };
 
@@ -19964,7 +20896,428 @@ static struct aead_testvec aes_gcm_rfc4106_dec_tv_template[] = {
                           "\xff\xff\xff\xff\xff\xff\xff\xff"
                           "\xff\xff\xff\xff\xff\xff\xff\xff",
                 .rlen   = 192,
-
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x2E\x44\x3B\x68",
+		.klen	= 20,
+		.iv	= "\x49\x56\xED\x7E\x3B\x24\x4C\xFE",
+		.result	= "\x45\x00\x00\x48\x69\x9A\x00\x00"
+			  "\x80\x11\x4D\xB7\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x9B\xF1\x56"
+			  "\x38\xD3\x01\x00\x00\x01\x00\x00"
+			  "\x00\x00\x00\x00\x04\x5F\x73\x69"
+			  "\x70\x04\x5F\x75\x64\x70\x03\x73"
+			  "\x69\x70\x09\x63\x79\x62\x65\x72"
+			  "\x63\x69\x74\x79\x02\x64\x6B\x00"
+			  "\x00\x21\x00\x01\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x00",
+		.alen	= 12,
+		.input	= "\xFE\xCF\x53\x7E\x72\x9D\x5B\x07"
+			  "\xDC\x30\xDF\x52\x8D\xD2\x2B\x76"
+			  "\x8D\x1B\x98\x73\x66\x96\xA6\xFD"
+			  "\x34\x85\x09\xFA\x13\xCE\xAC\x34"
+			  "\xCF\xA2\x43\x6F\x14\xA3\xF3\xCF"
+			  "\x65\x92\x5B\xF1\xF4\xA1\x3C\x5D"
+			  "\x15\xB2\x1E\x18\x84\xF5\xFF\x62"
+			  "\x47\xAE\xAB\xB7\x86\xB9\x3B\xCE"
+			  "\x61\xBC\x17\xD7\x68\xFD\x97\x32"
+			  "\x45\x90\x18\x14\x8F\x6C\xBE\x72"
+			  "\x2F\xD0\x47\x96\x56\x2D\xFD\xB4",
+		.ilen	= 88,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 20,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x3E\x69\x8F\x00\x00"
+			  "\x80\x11\x4D\xCC\xC0\xA8\x01\x02"
+			  "\xC0\xA8\x01\x01\x0A\x98\x00\x35"
+			  "\x00\x2A\x23\x43\xB2\xD0\x01\x00"
+			  "\x00\x01\x00\x00\x00\x00\x00\x00"
+			  "\x03\x73\x69\x70\x09\x63\x79\x62"
+			  "\x65\x72\x63\x69\x74\x79\x02\x64"
+			  "\x6B\x00\x00\x01\x00\x01\x00\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.input	= "\xDE\xB2\x2C\xD9\xB0\x7C\x72\xC1"
+			  "\x6E\x3A\x65\xBE\xEB\x8D\xF3\x04"
+			  "\xA5\xA5\x89\x7D\x33\xAE\x53\x0F"
+			  "\x1B\xA7\x6D\x5D\x11\x4D\x2A\x5C"
+			  "\x3D\xE8\x18\x27\xC1\x0E\x9A\x4F"
+			  "\x51\x33\x0D\x0E\xEC\x41\x66\x42"
+			  "\xCF\xBB\x85\xA5\xB4\x7E\x48\xA4"
+			  "\xEC\x3B\x9B\xA9\x5D\x91\x8B\xD1"
+			  "\x83\xB7\x0D\x3A\xA8\xBC\x6E\xE4"
+			  "\xC3\x09\xE9\xD8\x5A\x41\xAD\x4A",
+		.ilen	= 80,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x11\x22\x33\x44",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.result	= "\x45\x00\x00\x30\x69\xA6\x40\x00"
+			  "\x80\x06\x26\x90\xC0\xA8\x01\x02"
+			  "\x93\x89\x15\x5E\x0A\x9E\x00\x8B"
+			  "\x2D\xC5\x7E\xE0\x00\x00\x00\x00"
+			  "\x70\x02\x40\x00\x20\xBF\x00\x00"
+			  "\x02\x04\x05\xB4\x01\x01\x04\x02"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x4A\x2C\xBF\xE3\x00\x00\x00\x02",
+		.alen	= 8,
+		.input	= "\xFF\x42\x5C\x9B\x72\x45\x99\xDF"
+			  "\x7A\x3B\xCD\x51\x01\x94\xE0\x0D"
+			  "\x6A\x78\x10\x7F\x1B\x0B\x1C\xBF"
+			  "\x06\xEF\xAE\x9D\x65\xA5\xD7\x63"
+			  "\x74\x8A\x63\x79\x85\x77\x1D\x34"
+			  "\x7F\x05\x45\x65\x9F\x14\xE9\x9D"
+			  "\xEF\x84\x2D\x8E\xB3\x35\xF4\xEE"
+			  "\xCF\xDB\xF8\x31\x82\x4B\x4C\x49"
+			  "\x15\x95\x6C\x96",
+		.ilen	= 68,
+	}, {
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00",
+		.klen	= 20,
+		.iv	= "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.result	= "\x45\x00\x00\x3C\x99\xC5\x00\x00"
+			  "\x80\x01\xCB\x7A\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x07\x5C"
+			  "\x02\x00\x44\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.alen	= 8,
+		.input	= "\x46\x88\xDA\xF2\xF9\x73\xA3\x92"
+			  "\x73\x29\x09\xC3\x31\xD5\x6D\x60"
+			  "\xF6\x94\xAB\xAA\x41\x4B\x5E\x7F"
+			  "\xF5\xFD\xCD\xFF\xF5\xE9\xA2\x84"
+			  "\x45\x64\x76\x49\x27\x19\xFF\xB6"
+			  "\x4D\xE7\xD9\xDC\xA1\xE1\xD8\x94"
+			  "\xBC\x3B\xD5\x78\x73\xED\x4D\x18"
+			  "\x1D\x19\xD4\xD5\xC8\xC1\x8A\xF3"
+			  "\xF8\x21\xD4\x96\xEE\xB0\x96\xE9"
+			  "\x8A\xD2\xB6\x9E\x47\x99\xC7\x1D",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x3C\x99\xC3\x00\x00"
+			  "\x80\x01\xCB\x7C\x40\x67\x93\x18"
+			  "\x01\x01\x01\x01\x08\x00\x08\x5C"
+			  "\x02\x00\x43\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x75\x76\x77\x61\x62\x63\x64\x65"
+			  "\x66\x67\x68\x69\x01\x02\x02\x01",
+		.rlen	= 64,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xA4\x85\x3C\xF9\xF0"
+			  "\xF2\x2C\xB1\x0D\x86\xDD\x83\xB0"
+			  "\xFE\xC7\x56\x91\xCF\x1A\x04\xB0"
+			  "\x0D\x11\x38\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x17\x55\xE6\x66\x2B\x4C\x8D\x0D"
+			  "\x1F\x5E\x22\x73\x95\x30\x32\x0A"
+			  "\xE0\xD7\x31\xCC\x97\x8E\xCA\xFA"
+			  "\xEA\xE8\x8F\x00\xE8\x0D\x6E\x48",
+		.ilen	= 80,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x1C\x42\xA2\x00\x00"
+			  "\x80\x01\x44\x1F\x40\x67\x93\xB6"
+			  "\xE0\x00\x00\x02\x0A\x00\xF5\xFF"
+			  "\x01\x02\x02\x01",
+		.rlen	= 28,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\x84\x5E\x5D\xF9\xF0"
+			  "\xF2\x2C\x3E\x6E\x86\xDD\x83\x1E"
+			  "\x1F\xC6\x57\x92\xCD\x1A\xF9\x13"
+			  "\x0E\x13\x79\xED\x36\x9F\x07\x1F"
+			  "\x35\xE0\x34\xBE\x95\xF1\x12\xE4"
+			  "\xE7\xD0\x5D\x35",
+		.ilen	= 44,
+	}, {
+		.key	= "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\x6D\x6A\x8F\x94\x67\x30\x83\x08"
+			  "\xFE\xFF\xE9\x92\x86\x65\x73\x1C"
+			  "\xCA\xFE\xBA\xBE",
+		.klen	= 28,
+		.iv	= "\xFA\xCE\xDB\xAD\xDE\xCA\xF8\x88",
+		.result	= "\x45\x00\x00\x28\xA4\xAD\x40\x00"
+			  "\x40\x06\x78\x80\x0A\x01\x03\x8F"
+			  "\x0A\x01\x06\x12\x80\x23\x06\xB8"
+			  "\xCB\x71\x26\x02\xDD\x6B\xB0\x3E"
+			  "\x50\x10\x16\xD0\x75\x68\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x00\x00\xA5\xF8\x00\x00\x00\x0A",
+		.alen	= 8,
+		.input	= "\xA5\xB1\xF8\x06\x60\x29\xAE\xA4"
+			  "\x0E\x59\x8B\x81\x22\xDE\x02\x42"
+			  "\x09\x38\xB3\xAB\x33\xF8\x28\xE6"
+			  "\x87\xB8\x85\x8B\x5B\xFB\xDB\xD0"
+			  "\x31\x5B\x27\x45\x21\x44\xCC\x77"
+			  "\x95\x45\x7B\x96\x52\x03\x7F\x53"
+			  "\x18\x02\x7B\x5B\x4C\xD7\xA6\x36",
+		.ilen	= 56,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x45\x00\x00\x49\x33\xBA\x00\x00"
+			  "\x7F\x11\x91\x06\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xDD\x7B\x80\x03\x02\xD5"
+			  "\x00\x00\x4E\x20\x00\x1E\x8C\x18"
+			  "\xD7\x5B\x81\xDC\x91\xBA\xA0\x47"
+			  "\x6B\x91\xB9\x24\xB2\x80\x38\x9D"
+			  "\x92\xC9\x63\xBA\xC0\x46\xEC\x95"
+			  "\x9B\x62\x66\xC0\x47\x22\xB1\x49"
+			  "\x23\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.input	= "\x18\xA6\xFD\x42\xF7\x2C\xBF\x4A"
+			  "\xB2\xA2\xEA\x90\x1F\x73\xD8\x14"
+			  "\xE3\xE7\xF2\x43\xD9\x54\x12\xE1"
+			  "\xC3\x49\xC1\xD2\xFB\xEC\x16\x8F"
+			  "\x91\x90\xFE\xEB\xAF\x2C\xB0\x19"
+			  "\x84\xE6\x58\x63\x96\x5D\x74\x72"
+			  "\xB7\x9D\xA3\x45\xE0\xE7\x80\x19"
+			  "\x1F\x0D\x2F\x0E\x0F\x49\x6C\x22"
+			  "\x6F\x21\x27\xB2\x7D\xB3\x57\x24"
+			  "\xE7\x84\x5D\x68\x65\x1F\x57\xE6"
+			  "\x5F\x35\x4F\x75\xFF\x17\x01\x57"
+			  "\x69\x62\x34\x36",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x45\x08\x00\x28\x73\x2C\x00\x00"
+			  "\x40\x06\xE9\xF9\x0A\x01\x06\x12"
+			  "\x0A\x01\x03\x8F\x06\xB8\x80\x23"
+			  "\xDD\x6B\xAF\xBE\xCB\x71\x26\x02"
+			  "\x50\x10\x1F\x64\x6D\x54\x00\x01",
+		.rlen	= 40,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.input	= "\xF2\xD6\x9E\xCD\xBD\x5A\x0D\x5B"
+			  "\x8D\x5E\xF3\x8B\xAD\x4D\xA5\x8D"
+			  "\x1F\x27\x8F\xDE\x98\xEF\x67\x54"
+			  "\x9D\x52\x4A\x30\x18\xD9\xA5\x7F"
+			  "\xF4\xD3\xA3\x1C\xE6\x73\x11\x9E"
+			  "\x45\x16\x26\xC2\x41\x57\x71\xE3"
+			  "\xB7\xEE\xBC\xA6\x14\xC8\x9B\x35",
+		.ilen	= 56,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x49\x33\x3E\x00\x00"
+			  "\x7F\x11\x91\x82\xC3\xFB\x1D\x10"
+			  "\xC2\xB1\xD3\x26\xC0\x28\x31\xCE"
+			  "\x00\x35\xCB\x45\x80\x03\x02\x5B"
+			  "\x00\x00\x01\xE0\x00\x1E\x8C\x18"
+			  "\xD6\x57\x59\xD5\x22\x84\xA0\x35"
+			  "\x2C\x71\x47\x5C\x88\x80\x39\x1C"
+			  "\x76\x4D\x6E\x5E\xE0\x49\x6B\x32"
+			  "\x5A\xE2\x70\xC0\x38\x99\x49\x39"
+			  "\x15\x01\x01\x01",
+		.rlen	= 76,
+		.assoc	= "\x42\xF6\x7E\x3F\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xD1\x2F\xC1\xF9\xF0"
+			  "\x0D\x3C\xEB\xF3\x05\x41\x0D\xB8"
+			  "\x3D\x77\x84\xB6\x07\x32\x3D\x22"
+			  "\x0F\x24\xB0\xA9\x7D\x54\x18\x28"
+			  "\x00\xCA\xDB\x0F\x68\xD9\x9E\xF0"
+			  "\xE0\xC0\xC8\x9A\xE9\xBE\xA8\x88"
+			  "\x4E\x52\xD6\x5B\xC1\xAF\xD0\x74"
+			  "\x0F\x74\x24\x44\x74\x7B\x5B\x39"
+			  "\xAB\x53\x31\x63\xAA\xD4\x55\x0E"
+			  "\xE5\x16\x09\x75\xCD\xB6\x08\xC5"
+			  "\x76\x91\x89\x60\x97\x63\xB8\xE1"
+			  "\x8C\xAA\x81\xE2",
+		.ilen	= 92,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\x73\x61\x6C\x74",
+		.klen	= 36,
+		.iv	= "\x61\x6E\x64\x01\x69\x76\x65\x63",
+		.result	= "\x63\x69\x73\x63\x6F\x01\x72\x75"
+			  "\x6C\x65\x73\x01\x74\x68\x65\x01"
+			  "\x6E\x65\x74\x77\x65\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x01\x74\x68\x65"
+			  "\x74\x65\x63\x68\x6E\x6F\x6C\x6F"
+			  "\x67\x69\x65\x73\x01\x74\x68\x61"
+			  "\x74\x77\x69\x6C\x6C\x01\x64\x65"
+			  "\x66\x69\x6E\x65\x74\x6F\x6D\x6F"
+			  "\x72\x72\x6F\x77\x01\x02\x02\x01",
+		.rlen	= 72,
+		.assoc	= "\x17\x40\x5E\x67\x15\x6F\x31\x26"
+			  "\xDD\x0D\xB9\x9B",
+		.alen	= 12,
+		.input	= "\xD4\xB7\xED\x86\xA1\x77\x7F\x2E"
+			  "\xA1\x3D\x69\x73\xD3\x24\xC6\x9E"
+			  "\x7B\x43\xF8\x26\xFB\x56\x83\x12"
+			  "\x26\x50\x8B\xEB\xD2\xDC\xEB\x18"
+			  "\xD0\xA6\xDF\x10\xE5\x48\x7D\xF0"
+			  "\x74\x11\x3E\x14\xC6\x41\x02\x4E"
+			  "\x3E\x67\x73\xD9\x1A\x62\xEE\x42"
+			  "\x9B\x04\x3A\x10\xE3\xEF\xE6\xB0"
+			  "\x12\xA4\x93\x63\x41\x23\x64\xF8"
+			  "\xC0\xCA\xC5\x87\xF2\x49\xE5\x6B"
+			  "\x11\xE2\x4F\x30\xE4\x4C\xCC\x76",
+		.ilen	= 88,
+	}, {
+		.key	= "\x7D\x77\x3D\x00\xC1\x44\xC5\x25"
+			  "\xAC\x61\x9D\x18\xC8\x4A\x3F\x47"
+			  "\xD9\x66\x42\x67",
+		.klen	= 20,
+		.iv	= "\x43\x45\x7E\x91\x82\x44\x3B\xC6",
+		.result	= "\x01\x02\x02\x01",
+		.rlen	= 4,
+		.assoc	= "\x33\x54\x67\xAE\xFF\xFF\xFF\xFF",
+		.alen	= 8,
+		.input	= "\x43\x7F\x86\x6B\xCB\x3F\x69\x9F"
+			  "\xE9\xB0\x82\x2B\xAC\x96\x1C\x45"
+			  "\x04\xBE\xF2\x70",
+		.ilen	= 20,
+	}, {
+		.key	= "\xAB\xBC\xCD\xDE\xF0\x01\x12\x23"
+			  "\x34\x45\x56\x67\x78\x89\x9A\xAB"
+			  "\xDE\xCA\xF8\x88",
+		.klen	= 20,
+		.iv	= "\xCA\xFE\xDE\xBA\xCE\xFA\xCE\x74",
+		.result	= "\x74\x6F\x01\x62\x65\x01\x6F\x72"
+			  "\x01\x6E\x6F\x74\x01\x74\x6F\x01"
+			  "\x62\x65\x00\x01",
+		.rlen	= 20,
+		.assoc	= "\x00\x00\x01\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x01",
+		.alen	= 12,
+		.input	= "\x29\xC9\xFC\x69\xA1\x97\xD0\x38"
+			  "\xCC\xDD\x14\xE2\xDD\xFC\xAA\x05"
+			  "\x43\x33\x21\x64\x41\x25\x03\x52"
+			  "\x43\x03\xED\x3C\x6C\x5F\x28\x38"
+			  "\x43\xAF\x8C\x3E",
+		.ilen	= 36,
+	}, {
+		.key	= "\x6C\x65\x67\x61\x6C\x69\x7A\x65"
+			  "\x6D\x61\x72\x69\x6A\x75\x61\x6E"
+			  "\x61\x61\x6E\x64\x64\x6F\x69\x74"
+			  "\x62\x65\x66\x6F\x72\x65\x69\x61"
+			  "\x74\x75\x72\x6E",
+		.klen	= 36,
+		.iv	= "\x33\x30\x21\x69\x67\x65\x74\x6D",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x79\x6B\x69\x63\xFF\xFF\xFF\xFF"
+			  "\xFF\xFF\xFF\xFF",
+		.alen	= 12,
+		.input	= "\xF9\x7A\xB2\xAA\x35\x6D\x8E\xDC"
+			  "\xE1\x76\x44\xAC\x8C\x78\xE2\x5D"
+			  "\xD2\x4D\xED\xBB\x29\xEB\xF1\xB6"
+			  "\x4A\x27\x4B\x39\xB4\x9C\x3A\x86"
+			  "\x4C\xD3\xD7\x8C\xA4\xAE\x68\xA3"
+			  "\x2B\x42\x45\x8F\xB5\x7D\xBE\x82"
+			  "\x1D\xCC\x63\xB9\xD0\x93\x7B\xA2"
+			  "\x94\x5F\x66\x93\x68\x66\x1A\x32"
+			  "\x9F\xB4\xC0\x53",
+		.ilen	= 68,
+	}, {
+		.key	= "\x3D\xE0\x98\x74\xB3\x88\xE6\x49"
+			  "\x19\x88\xD0\xC3\x60\x7E\xAE\x1F"
+			  "\x57\x69\x0E\x43",
+		.klen	= 20,
+		.iv	= "\x4E\x28\x00\x00\xA2\xFC\xA1\xA3",
+		.result	= "\x45\x00\x00\x30\xDA\x3A\x00\x00"
+			  "\x80\x01\xDF\x3B\xC0\xA8\x00\x05"
+			  "\xC0\xA8\x00\x01\x08\x00\xC6\xCD"
+			  "\x02\x00\x07\x00\x61\x62\x63\x64"
+			  "\x65\x66\x67\x68\x69\x6A\x6B\x6C"
+			  "\x6D\x6E\x6F\x70\x71\x72\x73\x74"
+			  "\x01\x02\x02\x01",
+		.rlen	= 52,
+		.assoc	= "\x3F\x7E\xF6\x42\x10\x10\x10\x10"
+			  "\x10\x10\x10\x10",
+		.alen	= 12,
+		.input	= "\xFB\xA2\xCA\xA8\xC6\xC5\xF9\xF0"
+			  "\xF2\x2C\xA5\x4A\x06\x12\x10\xAD"
+			  "\x3F\x6E\x57\x91\xCF\x1A\xCA\x21"
+			  "\x0D\x11\x7C\xEC\x9C\x35\x79\x17"
+			  "\x65\xAC\xBD\x87\x01\xAD\x79\x84"
+			  "\x5B\xF9\xFE\x3F\xBA\x48\x7B\xC9"
+			  "\x63\x21\x93\x06\x84\xEE\xCA\xDB"
+			  "\x56\x91\x25\x46\xE7\xA9\x5C\x97"
+			  "\x40\xD7\xCB\x05",
+		.ilen	= 68,
+	}, {
+		.key	= "\x4C\x80\xCD\xEF\xBB\x5D\x10\xDA"
+			  "\x90\x6A\xC7\x3C\x36\x13\xA6\x34"
+			  "\x22\x43\x3C\x64",
+		.klen	= 20,
+		.iv	= "\x48\x55\xEC\x7D\x3A\x23\x4B\xFD",
+		.result	= "\x08\x00\xC6\xCD\x02\x00\x07\x00"
+			  "\x61\x62\x63\x64\x65\x66\x67\x68"
+			  "\x69\x6A\x6B\x6C\x6D\x6E\x6F\x70"
+			  "\x71\x72\x73\x74\x01\x02\x02\x01",
+		.rlen	= 32,
+		.assoc	= "\x00\x00\x43\x21\x87\x65\x43\x21"
+			  "\x00\x00\x00\x07",
+		.alen	= 12,
+		.input	= "\x74\x75\x2E\x8A\xEB\x5D\x87\x3C"
+			  "\xD7\xC0\xF4\xAC\xC3\x6C\x4B\xFF"
+			  "\x84\xB7\xD7\xB9\x8F\x0C\xA8\xB6"
+			  "\xAC\xDA\x68\x94\xBC\x61\x90\x69"
+			  "\xEF\x9C\xBC\x28\xFE\x1B\x56\xA7"
+			  "\xC4\xE0\xD5\x8C\x86\xCD\x2B\xC0",
+		.ilen	= 48,
 	}
 };
 
@@ -19975,8 +21328,9 @@ static struct aead_testvec aes_gcm_rfc4543_enc_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20005,8 +21359,9 @@ static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20031,8 +21386,9 @@ static struct aead_testvec aes_gcm_rfc4543_dec_tv_template[] = {
 			  "\x22\x43\x3c\x64",
 		.klen	= 20,
 		.iv	= zeroed_string,
-		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07",
-		.alen	= 8,
+		.assoc	= "\x00\x00\x43\x21\x00\x00\x00\x07"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.alen	= 16,
 		.input	= "\x45\x00\x00\x30\xda\x3a\x00\x00"
 			  "\x80\x01\xdf\x3b\xc0\xa8\x00\x05"
 			  "\xc0\xa8\x00\x01\x08\x00\xc6\xcd"
@@ -20704,6 +22060,454 @@ static struct aead_testvec aes_ccm_rfc4309_dec_tv_template[] = {
 };
 
 /*
+ * ChaCha20-Poly1305 AEAD test vectors from RFC7539 2.8.2./A.5.
+ */
+#define RFC7539_ENC_TEST_VECTORS 2
+#define RFC7539_DEC_TEST_VECTORS 2
+static struct aead_testvec rfc7539_enc_tv_template[] = {
+	{
+		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f",
+		.klen	= 32,
+		.iv	= "\x07\x00\x00\x00\x40\x41\x42\x43"
+			  "\x44\x45\x46\x47",
+		.assoc	= "\x50\x51\x52\x53\xc0\xc1\xc2\xc3"
+			  "\xc4\xc5\xc6\xc7",
+		.alen	= 12,
+		.input	= "\x4c\x61\x64\x69\x65\x73\x20\x61"
+			  "\x6e\x64\x20\x47\x65\x6e\x74\x6c"
+			  "\x65\x6d\x65\x6e\x20\x6f\x66\x20"
+			  "\x74\x68\x65\x20\x63\x6c\x61\x73"
+			  "\x73\x20\x6f\x66\x20\x27\x39\x39"
+			  "\x3a\x20\x49\x66\x20\x49\x20\x63"
+			  "\x6f\x75\x6c\x64\x20\x6f\x66\x66"
+			  "\x65\x72\x20\x79\x6f\x75\x20\x6f"
+			  "\x6e\x6c\x79\x20\x6f\x6e\x65\x20"
+			  "\x74\x69\x70\x20\x66\x6f\x72\x20"
+			  "\x74\x68\x65\x20\x66\x75\x74\x75"
+			  "\x72\x65\x2c\x20\x73\x75\x6e\x73"
+			  "\x63\x72\x65\x65\x6e\x20\x77\x6f"
+			  "\x75\x6c\x64\x20\x62\x65\x20\x69"
+			  "\x74\x2e",
+		.ilen	= 114,
+		.result	= "\xd3\x1a\x8d\x34\x64\x8e\x60\xdb"
+			  "\x7b\x86\xaf\xbc\x53\xef\x7e\xc2"
+			  "\xa4\xad\xed\x51\x29\x6e\x08\xfe"
+			  "\xa9\xe2\xb5\xa7\x36\xee\x62\xd6"
+			  "\x3d\xbe\xa4\x5e\x8c\xa9\x67\x12"
+			  "\x82\xfa\xfb\x69\xda\x92\x72\x8b"
+			  "\x1a\x71\xde\x0a\x9e\x06\x0b\x29"
+			  "\x05\xd6\xa5\xb6\x7e\xcd\x3b\x36"
+			  "\x92\xdd\xbd\x7f\x2d\x77\x8b\x8c"
+			  "\x98\x03\xae\xe3\x28\x09\x1b\x58"
+			  "\xfa\xb3\x24\xe4\xfa\xd6\x75\x94"
+			  "\x55\x85\x80\x8b\x48\x31\xd7\xbc"
+			  "\x3f\xf4\xde\xf0\x8e\x4b\x7a\x9d"
+			  "\xe5\x76\xd2\x65\x86\xce\xc6\x4b"
+			  "\x61\x16\x1a\xe1\x0b\x59\x4f\x09"
+			  "\xe2\x6a\x7e\x90\x2e\xcb\xd0\x60"
+			  "\x06\x91",
+		.rlen	= 130,
+	}, {
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.ilen	= 265,
+		.result	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.rlen	= 281,
+	},
+};
+
+static struct aead_testvec rfc7539_dec_tv_template[] = {
+	{
+		.key	= "\x80\x81\x82\x83\x84\x85\x86\x87"
+			  "\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"
+			  "\x90\x91\x92\x93\x94\x95\x96\x97"
+			  "\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f",
+		.klen	= 32,
+		.iv	= "\x07\x00\x00\x00\x40\x41\x42\x43"
+			  "\x44\x45\x46\x47",
+		.assoc	= "\x50\x51\x52\x53\xc0\xc1\xc2\xc3"
+			  "\xc4\xc5\xc6\xc7",
+		.alen	= 12,
+		.input	= "\xd3\x1a\x8d\x34\x64\x8e\x60\xdb"
+			  "\x7b\x86\xaf\xbc\x53\xef\x7e\xc2"
+			  "\xa4\xad\xed\x51\x29\x6e\x08\xfe"
+			  "\xa9\xe2\xb5\xa7\x36\xee\x62\xd6"
+			  "\x3d\xbe\xa4\x5e\x8c\xa9\x67\x12"
+			  "\x82\xfa\xfb\x69\xda\x92\x72\x8b"
+			  "\x1a\x71\xde\x0a\x9e\x06\x0b\x29"
+			  "\x05\xd6\xa5\xb6\x7e\xcd\x3b\x36"
+			  "\x92\xdd\xbd\x7f\x2d\x77\x8b\x8c"
+			  "\x98\x03\xae\xe3\x28\x09\x1b\x58"
+			  "\xfa\xb3\x24\xe4\xfa\xd6\x75\x94"
+			  "\x55\x85\x80\x8b\x48\x31\xd7\xbc"
+			  "\x3f\xf4\xde\xf0\x8e\x4b\x7a\x9d"
+			  "\xe5\x76\xd2\x65\x86\xce\xc6\x4b"
+			  "\x61\x16\x1a\xe1\x0b\x59\x4f\x09"
+			  "\xe2\x6a\x7e\x90\x2e\xcb\xd0\x60"
+			  "\x06\x91",
+		.ilen	= 130,
+		.result	= "\x4c\x61\x64\x69\x65\x73\x20\x61"
+			  "\x6e\x64\x20\x47\x65\x6e\x74\x6c"
+			  "\x65\x6d\x65\x6e\x20\x6f\x66\x20"
+			  "\x74\x68\x65\x20\x63\x6c\x61\x73"
+			  "\x73\x20\x6f\x66\x20\x27\x39\x39"
+			  "\x3a\x20\x49\x66\x20\x49\x20\x63"
+			  "\x6f\x75\x6c\x64\x20\x6f\x66\x66"
+			  "\x65\x72\x20\x79\x6f\x75\x20\x6f"
+			  "\x6e\x6c\x79\x20\x6f\x6e\x65\x20"
+			  "\x74\x69\x70\x20\x66\x6f\x72\x20"
+			  "\x74\x68\x65\x20\x66\x75\x74\x75"
+			  "\x72\x65\x2c\x20\x73\x75\x6e\x73"
+			  "\x63\x72\x65\x65\x6e\x20\x77\x6f"
+			  "\x75\x6c\x64\x20\x62\x65\x20\x69"
+			  "\x74\x2e",
+		.rlen	= 114,
+	}, {
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv	= "\x00\x00\x00\x00\x01\x02\x03\x04"
+			  "\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.ilen	= 281,
+		.result	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.rlen	= 265,
+	},
+};
+
+/*
+ * draft-irtf-cfrg-chacha20-poly1305
+ */
+#define RFC7539ESP_DEC_TEST_VECTORS 1
+#define RFC7539ESP_ENC_TEST_VECTORS 1
+static struct aead_testvec rfc7539esp_enc_tv_template[] = {
+	{
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+			  "\x00\x00\x00\x00",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.ilen	= 265,
+		.result	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.rlen	= 281,
+	},
+};
+
+static struct aead_testvec rfc7539esp_dec_tv_template[] = {
+	{
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0"
+			  "\x00\x00\x00\x00",
+		.klen	= 36,
+		.iv	= "\x01\x02\x03\x04\x05\x06\x07\x08",
+		.assoc	= "\xf3\x33\x88\x86\x00\x00\x00\x00"
+			  "\x00\x00\x4e\x91",
+		.alen	= 12,
+		.input	= "\x64\xa0\x86\x15\x75\x86\x1a\xf4"
+			  "\x60\xf0\x62\xc7\x9b\xe6\x43\xbd"
+			  "\x5e\x80\x5c\xfd\x34\x5c\xf3\x89"
+			  "\xf1\x08\x67\x0a\xc7\x6c\x8c\xb2"
+			  "\x4c\x6c\xfc\x18\x75\x5d\x43\xee"
+			  "\xa0\x9e\xe9\x4e\x38\x2d\x26\xb0"
+			  "\xbd\xb7\xb7\x3c\x32\x1b\x01\x00"
+			  "\xd4\xf0\x3b\x7f\x35\x58\x94\xcf"
+			  "\x33\x2f\x83\x0e\x71\x0b\x97\xce"
+			  "\x98\xc8\xa8\x4a\xbd\x0b\x94\x81"
+			  "\x14\xad\x17\x6e\x00\x8d\x33\xbd"
+			  "\x60\xf9\x82\xb1\xff\x37\xc8\x55"
+			  "\x97\x97\xa0\x6e\xf4\xf0\xef\x61"
+			  "\xc1\x86\x32\x4e\x2b\x35\x06\x38"
+			  "\x36\x06\x90\x7b\x6a\x7c\x02\xb0"
+			  "\xf9\xf6\x15\x7b\x53\xc8\x67\xe4"
+			  "\xb9\x16\x6c\x76\x7b\x80\x4d\x46"
+			  "\xa5\x9b\x52\x16\xcd\xe7\xa4\xe9"
+			  "\x90\x40\xc5\xa4\x04\x33\x22\x5e"
+			  "\xe2\x82\xa1\xb0\xa0\x6c\x52\x3e"
+			  "\xaf\x45\x34\xd7\xf8\x3f\xa1\x15"
+			  "\x5b\x00\x47\x71\x8c\xbc\x54\x6a"
+			  "\x0d\x07\x2b\x04\xb3\x56\x4e\xea"
+			  "\x1b\x42\x22\x73\xf5\x48\x27\x1a"
+			  "\x0b\xb2\x31\x60\x53\xfa\x76\x99"
+			  "\x19\x55\xeb\xd6\x31\x59\x43\x4e"
+			  "\xce\xbb\x4e\x46\x6d\xae\x5a\x10"
+			  "\x73\xa6\x72\x76\x27\x09\x7a\x10"
+			  "\x49\xe6\x17\xd9\x1d\x36\x10\x94"
+			  "\xfa\x68\xf0\xff\x77\x98\x71\x30"
+			  "\x30\x5b\xea\xba\x2e\xda\x04\xdf"
+			  "\x99\x7b\x71\x4d\x6c\x6f\x2c\x29"
+			  "\xa6\xad\x5c\xb4\x02\x2b\x02\x70"
+			  "\x9b\xee\xad\x9d\x67\x89\x0c\xbb"
+			  "\x22\x39\x23\x36\xfe\xa1\x85\x1f"
+			  "\x38",
+		.ilen	= 281,
+		.result	= "\x49\x6e\x74\x65\x72\x6e\x65\x74"
+			  "\x2d\x44\x72\x61\x66\x74\x73\x20"
+			  "\x61\x72\x65\x20\x64\x72\x61\x66"
+			  "\x74\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x76\x61\x6c\x69"
+			  "\x64\x20\x66\x6f\x72\x20\x61\x20"
+			  "\x6d\x61\x78\x69\x6d\x75\x6d\x20"
+			  "\x6f\x66\x20\x73\x69\x78\x20\x6d"
+			  "\x6f\x6e\x74\x68\x73\x20\x61\x6e"
+			  "\x64\x20\x6d\x61\x79\x20\x62\x65"
+			  "\x20\x75\x70\x64\x61\x74\x65\x64"
+			  "\x2c\x20\x72\x65\x70\x6c\x61\x63"
+			  "\x65\x64\x2c\x20\x6f\x72\x20\x6f"
+			  "\x62\x73\x6f\x6c\x65\x74\x65\x64"
+			  "\x20\x62\x79\x20\x6f\x74\x68\x65"
+			  "\x72\x20\x64\x6f\x63\x75\x6d\x65"
+			  "\x6e\x74\x73\x20\x61\x74\x20\x61"
+			  "\x6e\x79\x20\x74\x69\x6d\x65\x2e"
+			  "\x20\x49\x74\x20\x69\x73\x20\x69"
+			  "\x6e\x61\x70\x70\x72\x6f\x70\x72"
+			  "\x69\x61\x74\x65\x20\x74\x6f\x20"
+			  "\x75\x73\x65\x20\x49\x6e\x74\x65"
+			  "\x72\x6e\x65\x74\x2d\x44\x72\x61"
+			  "\x66\x74\x73\x20\x61\x73\x20\x72"
+			  "\x65\x66\x65\x72\x65\x6e\x63\x65"
+			  "\x20\x6d\x61\x74\x65\x72\x69\x61"
+			  "\x6c\x20\x6f\x72\x20\x74\x6f\x20"
+			  "\x63\x69\x74\x65\x20\x74\x68\x65"
+			  "\x6d\x20\x6f\x74\x68\x65\x72\x20"
+			  "\x74\x68\x61\x6e\x20\x61\x73\x20"
+			  "\x2f\xe2\x80\x9c\x77\x6f\x72\x6b"
+			  "\x20\x69\x6e\x20\x70\x72\x6f\x67"
+			  "\x72\x65\x73\x73\x2e\x2f\xe2\x80"
+			  "\x9d",
+		.rlen	= 265,
+	},
+};
+
+/*
  * ANSI X9.31 Continuous Pseudo-Random Number Generator (AES mode)
  * test vectors, taken from Appendix B.2.9 and B.2.10:
  *     http://csrc.nist.gov/groups/STM/cavp/documents/rng/RNGVS.pdf
@@ -28370,6 +30174,183 @@ static struct cipher_testvec salsa20_stream_enc_tv_template[] = {
 	},
 };
 
+#define CHACHA20_ENC_TEST_VECTORS 3
+static struct cipher_testvec chacha20_enc_tv_template[] = {
+	{ /* RFC7539 A.2. Test Vector #1 */
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.klen	= 32,
+		.iv     = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.input	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.ilen	= 64,
+		.result	= "\x76\xb8\xe0\xad\xa0\xf1\x3d\x90"
+			  "\x40\x5d\x6a\xe5\x53\x86\xbd\x28"
+			  "\xbd\xd2\x19\xb8\xa0\x8d\xed\x1a"
+			  "\xa8\x36\xef\xcc\x8b\x77\x0d\xc7"
+			  "\xda\x41\x59\x7c\x51\x57\x48\x8d"
+			  "\x77\x24\xe0\x3f\xb8\xd8\x4a\x37"
+			  "\x6a\x43\xb8\xf4\x15\x18\xa1\x1c"
+			  "\xc3\x87\xb6\x69\xb2\xee\x65\x86",
+		.rlen	= 64,
+	}, { /* RFC7539 A.2. Test Vector #2 */
+		.key	= "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x01",
+		.klen	= 32,
+		.iv     = "\x01\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x02",
+		.input	= "\x41\x6e\x79\x20\x73\x75\x62\x6d"
+			  "\x69\x73\x73\x69\x6f\x6e\x20\x74"
+			  "\x6f\x20\x74\x68\x65\x20\x49\x45"
+			  "\x54\x46\x20\x69\x6e\x74\x65\x6e"
+			  "\x64\x65\x64\x20\x62\x79\x20\x74"
+			  "\x68\x65\x20\x43\x6f\x6e\x74\x72"
+			  "\x69\x62\x75\x74\x6f\x72\x20\x66"
+			  "\x6f\x72\x20\x70\x75\x62\x6c\x69"
+			  "\x63\x61\x74\x69\x6f\x6e\x20\x61"
+			  "\x73\x20\x61\x6c\x6c\x20\x6f\x72"
+			  "\x20\x70\x61\x72\x74\x20\x6f\x66"
+			  "\x20\x61\x6e\x20\x49\x45\x54\x46"
+			  "\x20\x49\x6e\x74\x65\x72\x6e\x65"
+			  "\x74\x2d\x44\x72\x61\x66\x74\x20"
+			  "\x6f\x72\x20\x52\x46\x43\x20\x61"
+			  "\x6e\x64\x20\x61\x6e\x79\x20\x73"
+			  "\x74\x61\x74\x65\x6d\x65\x6e\x74"
+			  "\x20\x6d\x61\x64\x65\x20\x77\x69"
+			  "\x74\x68\x69\x6e\x20\x74\x68\x65"
+			  "\x20\x63\x6f\x6e\x74\x65\x78\x74"
+			  "\x20\x6f\x66\x20\x61\x6e\x20\x49"
+			  "\x45\x54\x46\x20\x61\x63\x74\x69"
+			  "\x76\x69\x74\x79\x20\x69\x73\x20"
+			  "\x63\x6f\x6e\x73\x69\x64\x65\x72"
+			  "\x65\x64\x20\x61\x6e\x20\x22\x49"
+			  "\x45\x54\x46\x20\x43\x6f\x6e\x74"
+			  "\x72\x69\x62\x75\x74\x69\x6f\x6e"
+			  "\x22\x2e\x20\x53\x75\x63\x68\x20"
+			  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+			  "\x74\x73\x20\x69\x6e\x63\x6c\x75"
+			  "\x64\x65\x20\x6f\x72\x61\x6c\x20"
+			  "\x73\x74\x61\x74\x65\x6d\x65\x6e"
+			  "\x74\x73\x20\x69\x6e\x20\x49\x45"
+			  "\x54\x46\x20\x73\x65\x73\x73\x69"
+			  "\x6f\x6e\x73\x2c\x20\x61\x73\x20"
+			  "\x77\x65\x6c\x6c\x20\x61\x73\x20"
+			  "\x77\x72\x69\x74\x74\x65\x6e\x20"
+			  "\x61\x6e\x64\x20\x65\x6c\x65\x63"
+			  "\x74\x72\x6f\x6e\x69\x63\x20\x63"
+			  "\x6f\x6d\x6d\x75\x6e\x69\x63\x61"
+			  "\x74\x69\x6f\x6e\x73\x20\x6d\x61"
+			  "\x64\x65\x20\x61\x74\x20\x61\x6e"
+			  "\x79\x20\x74\x69\x6d\x65\x20\x6f"
+			  "\x72\x20\x70\x6c\x61\x63\x65\x2c"
+			  "\x20\x77\x68\x69\x63\x68\x20\x61"
+			  "\x72\x65\x20\x61\x64\x64\x72\x65"
+			  "\x73\x73\x65\x64\x20\x74\x6f",
+		.ilen	= 375,
+		.result	= "\xa3\xfb\xf0\x7d\xf3\xfa\x2f\xde"
+			  "\x4f\x37\x6c\xa2\x3e\x82\x73\x70"
+			  "\x41\x60\x5d\x9f\x4f\x4f\x57\xbd"
+			  "\x8c\xff\x2c\x1d\x4b\x79\x55\xec"
+			  "\x2a\x97\x94\x8b\xd3\x72\x29\x15"
+			  "\xc8\xf3\xd3\x37\xf7\xd3\x70\x05"
+			  "\x0e\x9e\x96\xd6\x47\xb7\xc3\x9f"
+			  "\x56\xe0\x31\xca\x5e\xb6\x25\x0d"
+			  "\x40\x42\xe0\x27\x85\xec\xec\xfa"
+			  "\x4b\x4b\xb5\xe8\xea\xd0\x44\x0e"
+			  "\x20\xb6\xe8\xdb\x09\xd8\x81\xa7"
+			  "\xc6\x13\x2f\x42\x0e\x52\x79\x50"
+			  "\x42\xbd\xfa\x77\x73\xd8\xa9\x05"
+			  "\x14\x47\xb3\x29\x1c\xe1\x41\x1c"
+			  "\x68\x04\x65\x55\x2a\xa6\xc4\x05"
+			  "\xb7\x76\x4d\x5e\x87\xbe\xa8\x5a"
+			  "\xd0\x0f\x84\x49\xed\x8f\x72\xd0"
+			  "\xd6\x62\xab\x05\x26\x91\xca\x66"
+			  "\x42\x4b\xc8\x6d\x2d\xf8\x0e\xa4"
+			  "\x1f\x43\xab\xf9\x37\xd3\x25\x9d"
+			  "\xc4\xb2\xd0\xdf\xb4\x8a\x6c\x91"
+			  "\x39\xdd\xd7\xf7\x69\x66\xe9\x28"
+			  "\xe6\x35\x55\x3b\xa7\x6c\x5c\x87"
+			  "\x9d\x7b\x35\xd4\x9e\xb2\xe6\x2b"
+			  "\x08\x71\xcd\xac\x63\x89\x39\xe2"
+			  "\x5e\x8a\x1e\x0e\xf9\xd5\x28\x0f"
+			  "\xa8\xca\x32\x8b\x35\x1c\x3c\x76"
+			  "\x59\x89\xcb\xcf\x3d\xaa\x8b\x6c"
+			  "\xcc\x3a\xaf\x9f\x39\x79\xc9\x2b"
+			  "\x37\x20\xfc\x88\xdc\x95\xed\x84"
+			  "\xa1\xbe\x05\x9c\x64\x99\xb9\xfd"
+			  "\xa2\x36\xe7\xe8\x18\xb0\x4b\x0b"
+			  "\xc3\x9c\x1e\x87\x6b\x19\x3b\xfe"
+			  "\x55\x69\x75\x3f\x88\x12\x8c\xc0"
+			  "\x8a\xaa\x9b\x63\xd1\xa1\x6f\x80"
+			  "\xef\x25\x54\xd7\x18\x9c\x41\x1f"
+			  "\x58\x69\xca\x52\xc5\xb8\x3f\xa3"
+			  "\x6f\xf2\x16\xb9\xc1\xd3\x00\x62"
+			  "\xbe\xbc\xfd\x2d\xc5\xbc\xe0\x91"
+			  "\x19\x34\xfd\xa7\x9a\x86\xf6\xe6"
+			  "\x98\xce\xd7\x59\xc3\xff\x9b\x64"
+			  "\x77\x33\x8f\x3d\xa4\xf9\xcd\x85"
+			  "\x14\xea\x99\x82\xcc\xaf\xb3\x41"
+			  "\xb2\x38\x4d\xd9\x02\xf3\xd1\xab"
+			  "\x7a\xc6\x1d\xd2\x9c\x6f\x21\xba"
+			  "\x5b\x86\x2f\x37\x30\xe3\x7c\xfd"
+			  "\xc4\xfd\x80\x6c\x22\xf2\x21",
+		.rlen	= 375,
+	}, { /* RFC7539 A.2. Test Vector #3 */
+		.key	= "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a"
+			  "\xf3\x33\x88\x86\x04\xf6\xb5\xf0"
+			  "\x47\x39\x17\xc1\x40\x2b\x80\x09"
+			  "\x9d\xca\x5c\xbc\x20\x70\x75\xc0",
+		.klen	= 32,
+		.iv     = "\x2a\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x02",
+		.input	= "\x27\x54\x77\x61\x73\x20\x62\x72"
+			  "\x69\x6c\x6c\x69\x67\x2c\x20\x61"
+			  "\x6e\x64\x20\x74\x68\x65\x20\x73"
+			  "\x6c\x69\x74\x68\x79\x20\x74\x6f"
+			  "\x76\x65\x73\x0a\x44\x69\x64\x20"
+			  "\x67\x79\x72\x65\x20\x61\x6e\x64"
+			  "\x20\x67\x69\x6d\x62\x6c\x65\x20"
+			  "\x69\x6e\x20\x74\x68\x65\x20\x77"
+			  "\x61\x62\x65\x3a\x0a\x41\x6c\x6c"
+			  "\x20\x6d\x69\x6d\x73\x79\x20\x77"
+			  "\x65\x72\x65\x20\x74\x68\x65\x20"
+			  "\x62\x6f\x72\x6f\x67\x6f\x76\x65"
+			  "\x73\x2c\x0a\x41\x6e\x64\x20\x74"
+			  "\x68\x65\x20\x6d\x6f\x6d\x65\x20"
+			  "\x72\x61\x74\x68\x73\x20\x6f\x75"
+			  "\x74\x67\x72\x61\x62\x65\x2e",
+		.ilen	= 127,
+		.result	= "\x62\xe6\x34\x7f\x95\xed\x87\xa4"
+			  "\x5f\xfa\xe7\x42\x6f\x27\xa1\xdf"
+			  "\x5f\xb6\x91\x10\x04\x4c\x0d\x73"
+			  "\x11\x8e\xff\xa9\x5b\x01\xe5\xcf"
+			  "\x16\x6d\x3d\xf2\xd7\x21\xca\xf9"
+			  "\xb2\x1e\x5f\xb1\x4c\x61\x68\x71"
+			  "\xfd\x84\xc5\x4f\x9d\x65\xb2\x83"
+			  "\x19\x6c\x7f\xe4\xf6\x05\x53\xeb"
+			  "\xf3\x9c\x64\x02\xc4\x22\x34\xe3"
+			  "\x2a\x35\x6b\x3e\x76\x43\x12\xa6"
+			  "\x1a\x55\x32\x05\x57\x16\xea\xd6"
+			  "\x96\x25\x68\xf8\x7d\x3f\x3f\x77"
+			  "\x04\xc6\xa8\xd1\xbc\xd1\xbf\x4d"
+			  "\x50\xd6\x15\x4b\x6d\xa7\x31\xb1"
+			  "\x87\xb5\x8d\xfd\x72\x8a\xfa\x36"
+			  "\x75\x7a\x79\x7a\xc1\x88\xd1",
+		.rlen	= 127,
+	},
+};
+
 /*
  * CTS (Cipher Text Stealing) mode tests
  */
@@ -28591,7 +30572,7 @@ struct comp_testvec {
 };
 
 struct pcomp_testvec {
-	void *params;
+	const void *params;
 	unsigned int paramsize;
 	int inlen, outlen;
 	char input[COMP_BUF_SIZE];
@@ -28946,6 +30927,440 @@ static struct hash_testvec michael_mic_tv_template[] = {
 };
 
 /*
+ * CRC32 test vectors
+ */
+#define CRC32_TEST_VECTORS 14
+
+static struct hash_testvec crc32_tv_template[] = {
+	{
+		.key = "\x87\xa9\xcb\xed",
+		.ksize = 4,
+		.psize = 0,
+		.digest = "\x87\xa9\xcb\xed",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
+			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			     "\x11\x12\x13\x14\x15\x16\x17\x18"
+			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
+			     "\x21\x22\x23\x24\x25\x26\x27\x28",
+		.psize = 40,
+		.digest = "\x3a\xdf\x4b\xb0",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50",
+		.psize = 40,
+		.digest = "\xa9\x7a\x7f\x7b",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78",
+		.psize = 40,
+		.digest = "\xba\xd3\xf8\x1c",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0",
+		.psize = 40,
+		.digest = "\xa8\xa9\xc2\x02",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8",
+		.psize = 40,
+		.digest = "\x27\xf0\x57\xe2",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 40,
+		.digest = "\x49\x78\x10\x08",
+	},
+	{
+		.key = "\x80\xea\xd3\xf1",
+		.ksize = 4,
+		.plaintext = "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50",
+		.psize = 40,
+		.digest = "\x9a\xb1\xdc\xf0",
+	},
+	{
+		.key = "\xf3\x4a\x1d\x5d",
+		.ksize = 4,
+		.plaintext = "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78",
+		.psize = 40,
+		.digest = "\xb4\x97\xcc\xd4",
+	},
+	{
+		.key = "\x2e\x80\x04\x59",
+		.ksize = 4,
+		.plaintext = "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0",
+		.psize = 40,
+		.digest = "\x67\x9b\xfa\x79",
+	},
+	{
+		.key = "\xa6\xcc\x19\x85",
+		.ksize = 4,
+		.plaintext = "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8",
+		.psize = 40,
+		.digest = "\x24\xb5\x16\xef",
+	},
+	{
+		.key = "\x41\xfc\xfe\x2d",
+		.ksize = 4,
+		.plaintext = "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 40,
+		.digest = "\x15\x94\x80\x39",
+	},
+	{
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext = "\x01\x02\x03\x04\x05\x06\x07\x08"
+			     "\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10"
+			     "\x11\x12\x13\x14\x15\x16\x17\x18"
+			     "\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20"
+			     "\x21\x22\x23\x24\x25\x26\x27\x28"
+			     "\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30"
+			     "\x31\x32\x33\x34\x35\x36\x37\x38"
+			     "\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40"
+			     "\x41\x42\x43\x44\x45\x46\x47\x48"
+			     "\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50"
+			     "\x51\x52\x53\x54\x55\x56\x57\x58"
+			     "\x59\x5a\x5b\x5c\x5d\x5e\x5f\x60"
+			     "\x61\x62\x63\x64\x65\x66\x67\x68"
+			     "\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70"
+			     "\x71\x72\x73\x74\x75\x76\x77\x78"
+			     "\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80"
+			     "\x81\x82\x83\x84\x85\x86\x87\x88"
+			     "\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90"
+			     "\x91\x92\x93\x94\x95\x96\x97\x98"
+			     "\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0"
+			     "\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8"
+			     "\xa9\xaa\xab\xac\xad\xae\xaf\xb0"
+			     "\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8"
+			     "\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0"
+			     "\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8"
+			     "\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0"
+			     "\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8"
+			     "\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0"
+			     "\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8"
+			     "\xe9\xea\xeb\xec\xed\xee\xef\xf0",
+		.psize = 240,
+		.digest = "\x6c\xc6\x56\xde",
+		.np = 2,
+		.tap = { 31, 209 }
+	}, {
+		.key = "\xff\xff\xff\xff",
+		.ksize = 4,
+		.plaintext =	"\x6e\x05\x79\x10\xa7\x1b\xb2\x49"
+				"\xe0\x54\xeb\x82\x19\x8d\x24\xbb"
+				"\x2f\xc6\x5d\xf4\x68\xff\x96\x0a"
+				"\xa1\x38\xcf\x43\xda\x71\x08\x7c"
+				"\x13\xaa\x1e\xb5\x4c\xe3\x57\xee"
+				"\x85\x1c\x90\x27\xbe\x32\xc9\x60"
+				"\xf7\x6b\x02\x99\x0d\xa4\x3b\xd2"
+				"\x46\xdd\x74\x0b\x7f\x16\xad\x21"
+				"\xb8\x4f\xe6\x5a\xf1\x88\x1f\x93"
+				"\x2a\xc1\x35\xcc\x63\xfa\x6e\x05"
+				"\x9c\x10\xa7\x3e\xd5\x49\xe0\x77"
+				"\x0e\x82\x19\xb0\x24\xbb\x52\xe9"
+				"\x5d\xf4\x8b\x22\x96\x2d\xc4\x38"
+				"\xcf\x66\xfd\x71\x08\x9f\x13\xaa"
+				"\x41\xd8\x4c\xe3\x7a\x11\x85\x1c"
+				"\xb3\x27\xbe\x55\xec\x60\xf7\x8e"
+				"\x02\x99\x30\xc7\x3b\xd2\x69\x00"
+				"\x74\x0b\xa2\x16\xad\x44\xdb\x4f"
+				"\xe6\x7d\x14\x88\x1f\xb6\x2a\xc1"
+				"\x58\xef\x63\xfa\x91\x05\x9c\x33"
+				"\xca\x3e\xd5\x6c\x03\x77\x0e\xa5"
+				"\x19\xb0\x47\xde\x52\xe9\x80\x17"
+				"\x8b\x22\xb9\x2d\xc4\x5b\xf2\x66"
+				"\xfd\x94\x08\x9f\x36\xcd\x41\xd8"
+				"\x6f\x06\x7a\x11\xa8\x1c\xb3\x4a"
+				"\xe1\x55\xec\x83\x1a\x8e\x25\xbc"
+				"\x30\xc7\x5e\xf5\x69\x00\x97\x0b"
+				"\xa2\x39\xd0\x44\xdb\x72\x09\x7d"
+				"\x14\xab\x1f\xb6\x4d\xe4\x58\xef"
+				"\x86\x1d\x91\x28\xbf\x33\xca\x61"
+				"\xf8\x6c\x03\x9a\x0e\xa5\x3c\xd3"
+				"\x47\xde\x75\x0c\x80\x17\xae\x22"
+				"\xb9\x50\xe7\x5b\xf2\x89\x20\x94"
+				"\x2b\xc2\x36\xcd\x64\xfb\x6f\x06"
+				"\x9d\x11\xa8\x3f\xd6\x4a\xe1\x78"
+				"\x0f\x83\x1a\xb1\x25\xbc\x53\xea"
+				"\x5e\xf5\x8c\x00\x97\x2e\xc5\x39"
+				"\xd0\x67\xfe\x72\x09\xa0\x14\xab"
+				"\x42\xd9\x4d\xe4\x7b\x12\x86\x1d"
+				"\xb4\x28\xbf\x56\xed\x61\xf8\x8f"
+				"\x03\x9a\x31\xc8\x3c\xd3\x6a\x01"
+				"\x75\x0c\xa3\x17\xae\x45\xdc\x50"
+				"\xe7\x7e\x15\x89\x20\xb7\x2b\xc2"
+				"\x59\xf0\x64\xfb\x92\x06\x9d\x34"
+				"\xcb\x3f\xd6\x6d\x04\x78\x0f\xa6"
+				"\x1a\xb1\x48\xdf\x53\xea\x81\x18"
+				"\x8c\x23\xba\x2e\xc5\x5c\xf3\x67"
+				"\xfe\x95\x09\xa0\x37\xce\x42\xd9"
+				"\x70\x07\x7b\x12\xa9\x1d\xb4\x4b"
+				"\xe2\x56\xed\x84\x1b\x8f\x26\xbd"
+				"\x31\xc8\x5f\xf6\x6a\x01\x98\x0c"
+				"\xa3\x3a\xd1\x45\xdc\x73\x0a\x7e"
+				"\x15\xac\x20\xb7\x4e\xe5\x59\xf0"
+				"\x87\x1e\x92\x29\xc0\x34\xcb\x62"
+				"\xf9\x6d\x04\x9b\x0f\xa6\x3d\xd4"
+				"\x48\xdf\x76\x0d\x81\x18\xaf\x23"
+				"\xba\x51\xe8\x5c\xf3\x8a\x21\x95"
+				"\x2c\xc3\x37\xce\x65\xfc\x70\x07"
+				"\x9e\x12\xa9\x40\xd7\x4b\xe2\x79"
+				"\x10\x84\x1b\xb2\x26\xbd\x54\xeb"
+				"\x5f\xf6\x8d\x01\x98\x2f\xc6\x3a"
+				"\xd1\x68\xff\x73\x0a\xa1\x15\xac"
+				"\x43\xda\x4e\xe5\x7c\x13\x87\x1e"
+				"\xb5\x29\xc0\x57\xee\x62\xf9\x90"
+				"\x04\x9b\x32\xc9\x3d\xd4\x6b\x02"
+				"\x76\x0d\xa4\x18\xaf\x46\xdd\x51"
+				"\xe8\x7f\x16\x8a\x21\xb8\x2c\xc3"
+				"\x5a\xf1\x65\xfc\x93\x07\x9e\x35"
+				"\xcc\x40\xd7\x6e\x05\x79\x10\xa7"
+				"\x1b\xb2\x49\xe0\x54\xeb\x82\x19"
+				"\x8d\x24\xbb\x2f\xc6\x5d\xf4\x68"
+				"\xff\x96\x0a\xa1\x38\xcf\x43\xda"
+				"\x71\x08\x7c\x13\xaa\x1e\xb5\x4c"
+				"\xe3\x57\xee\x85\x1c\x90\x27\xbe"
+				"\x32\xc9\x60\xf7\x6b\x02\x99\x0d"
+				"\xa4\x3b\xd2\x46\xdd\x74\x0b\x7f"
+				"\x16\xad\x21\xb8\x4f\xe6\x5a\xf1"
+				"\x88\x1f\x93\x2a\xc1\x35\xcc\x63"
+				"\xfa\x6e\x05\x9c\x10\xa7\x3e\xd5"
+				"\x49\xe0\x77\x0e\x82\x19\xb0\x24"
+				"\xbb\x52\xe9\x5d\xf4\x8b\x22\x96"
+				"\x2d\xc4\x38\xcf\x66\xfd\x71\x08"
+				"\x9f\x13\xaa\x41\xd8\x4c\xe3\x7a"
+				"\x11\x85\x1c\xb3\x27\xbe\x55\xec"
+				"\x60\xf7\x8e\x02\x99\x30\xc7\x3b"
+				"\xd2\x69\x00\x74\x0b\xa2\x16\xad"
+				"\x44\xdb\x4f\xe6\x7d\x14\x88\x1f"
+				"\xb6\x2a\xc1\x58\xef\x63\xfa\x91"
+				"\x05\x9c\x33\xca\x3e\xd5\x6c\x03"
+				"\x77\x0e\xa5\x19\xb0\x47\xde\x52"
+				"\xe9\x80\x17\x8b\x22\xb9\x2d\xc4"
+				"\x5b\xf2\x66\xfd\x94\x08\x9f\x36"
+				"\xcd\x41\xd8\x6f\x06\x7a\x11\xa8"
+				"\x1c\xb3\x4a\xe1\x55\xec\x83\x1a"
+				"\x8e\x25\xbc\x30\xc7\x5e\xf5\x69"
+				"\x00\x97\x0b\xa2\x39\xd0\x44\xdb"
+				"\x72\x09\x7d\x14\xab\x1f\xb6\x4d"
+				"\xe4\x58\xef\x86\x1d\x91\x28\xbf"
+				"\x33\xca\x61\xf8\x6c\x03\x9a\x0e"
+				"\xa5\x3c\xd3\x47\xde\x75\x0c\x80"
+				"\x17\xae\x22\xb9\x50\xe7\x5b\xf2"
+				"\x89\x20\x94\x2b\xc2\x36\xcd\x64"
+				"\xfb\x6f\x06\x9d\x11\xa8\x3f\xd6"
+				"\x4a\xe1\x78\x0f\x83\x1a\xb1\x25"
+				"\xbc\x53\xea\x5e\xf5\x8c\x00\x97"
+				"\x2e\xc5\x39\xd0\x67\xfe\x72\x09"
+				"\xa0\x14\xab\x42\xd9\x4d\xe4\x7b"
+				"\x12\x86\x1d\xb4\x28\xbf\x56\xed"
+				"\x61\xf8\x8f\x03\x9a\x31\xc8\x3c"
+				"\xd3\x6a\x01\x75\x0c\xa3\x17\xae"
+				"\x45\xdc\x50\xe7\x7e\x15\x89\x20"
+				"\xb7\x2b\xc2\x59\xf0\x64\xfb\x92"
+				"\x06\x9d\x34\xcb\x3f\xd6\x6d\x04"
+				"\x78\x0f\xa6\x1a\xb1\x48\xdf\x53"
+				"\xea\x81\x18\x8c\x23\xba\x2e\xc5"
+				"\x5c\xf3\x67\xfe\x95\x09\xa0\x37"
+				"\xce\x42\xd9\x70\x07\x7b\x12\xa9"
+				"\x1d\xb4\x4b\xe2\x56\xed\x84\x1b"
+				"\x8f\x26\xbd\x31\xc8\x5f\xf6\x6a"
+				"\x01\x98\x0c\xa3\x3a\xd1\x45\xdc"
+				"\x73\x0a\x7e\x15\xac\x20\xb7\x4e"
+				"\xe5\x59\xf0\x87\x1e\x92\x29\xc0"
+				"\x34\xcb\x62\xf9\x6d\x04\x9b\x0f"
+				"\xa6\x3d\xd4\x48\xdf\x76\x0d\x81"
+				"\x18\xaf\x23\xba\x51\xe8\x5c\xf3"
+				"\x8a\x21\x95\x2c\xc3\x37\xce\x65"
+				"\xfc\x70\x07\x9e\x12\xa9\x40\xd7"
+				"\x4b\xe2\x79\x10\x84\x1b\xb2\x26"
+				"\xbd\x54\xeb\x5f\xf6\x8d\x01\x98"
+				"\x2f\xc6\x3a\xd1\x68\xff\x73\x0a"
+				"\xa1\x15\xac\x43\xda\x4e\xe5\x7c"
+				"\x13\x87\x1e\xb5\x29\xc0\x57\xee"
+				"\x62\xf9\x90\x04\x9b\x32\xc9\x3d"
+				"\xd4\x6b\x02\x76\x0d\xa4\x18\xaf"
+				"\x46\xdd\x51\xe8\x7f\x16\x8a\x21"
+				"\xb8\x2c\xc3\x5a\xf1\x65\xfc\x93"
+				"\x07\x9e\x35\xcc\x40\xd7\x6e\x05"
+				"\x79\x10\xa7\x1b\xb2\x49\xe0\x54"
+				"\xeb\x82\x19\x8d\x24\xbb\x2f\xc6"
+				"\x5d\xf4\x68\xff\x96\x0a\xa1\x38"
+				"\xcf\x43\xda\x71\x08\x7c\x13\xaa"
+				"\x1e\xb5\x4c\xe3\x57\xee\x85\x1c"
+				"\x90\x27\xbe\x32\xc9\x60\xf7\x6b"
+				"\x02\x99\x0d\xa4\x3b\xd2\x46\xdd"
+				"\x74\x0b\x7f\x16\xad\x21\xb8\x4f"
+				"\xe6\x5a\xf1\x88\x1f\x93\x2a\xc1"
+				"\x35\xcc\x63\xfa\x6e\x05\x9c\x10"
+				"\xa7\x3e\xd5\x49\xe0\x77\x0e\x82"
+				"\x19\xb0\x24\xbb\x52\xe9\x5d\xf4"
+				"\x8b\x22\x96\x2d\xc4\x38\xcf\x66"
+				"\xfd\x71\x08\x9f\x13\xaa\x41\xd8"
+				"\x4c\xe3\x7a\x11\x85\x1c\xb3\x27"
+				"\xbe\x55\xec\x60\xf7\x8e\x02\x99"
+				"\x30\xc7\x3b\xd2\x69\x00\x74\x0b"
+				"\xa2\x16\xad\x44\xdb\x4f\xe6\x7d"
+				"\x14\x88\x1f\xb6\x2a\xc1\x58\xef"
+				"\x63\xfa\x91\x05\x9c\x33\xca\x3e"
+				"\xd5\x6c\x03\x77\x0e\xa5\x19\xb0"
+				"\x47\xde\x52\xe9\x80\x17\x8b\x22"
+				"\xb9\x2d\xc4\x5b\xf2\x66\xfd\x94"
+				"\x08\x9f\x36\xcd\x41\xd8\x6f\x06"
+				"\x7a\x11\xa8\x1c\xb3\x4a\xe1\x55"
+				"\xec\x83\x1a\x8e\x25\xbc\x30\xc7"
+				"\x5e\xf5\x69\x00\x97\x0b\xa2\x39"
+				"\xd0\x44\xdb\x72\x09\x7d\x14\xab"
+				"\x1f\xb6\x4d\xe4\x58\xef\x86\x1d"
+				"\x91\x28\xbf\x33\xca\x61\xf8\x6c"
+				"\x03\x9a\x0e\xa5\x3c\xd3\x47\xde"
+				"\x75\x0c\x80\x17\xae\x22\xb9\x50"
+				"\xe7\x5b\xf2\x89\x20\x94\x2b\xc2"
+				"\x36\xcd\x64\xfb\x6f\x06\x9d\x11"
+				"\xa8\x3f\xd6\x4a\xe1\x78\x0f\x83"
+				"\x1a\xb1\x25\xbc\x53\xea\x5e\xf5"
+				"\x8c\x00\x97\x2e\xc5\x39\xd0\x67"
+				"\xfe\x72\x09\xa0\x14\xab\x42\xd9"
+				"\x4d\xe4\x7b\x12\x86\x1d\xb4\x28"
+				"\xbf\x56\xed\x61\xf8\x8f\x03\x9a"
+				"\x31\xc8\x3c\xd3\x6a\x01\x75\x0c"
+				"\xa3\x17\xae\x45\xdc\x50\xe7\x7e"
+				"\x15\x89\x20\xb7\x2b\xc2\x59\xf0"
+				"\x64\xfb\x92\x06\x9d\x34\xcb\x3f"
+				"\xd6\x6d\x04\x78\x0f\xa6\x1a\xb1"
+				"\x48\xdf\x53\xea\x81\x18\x8c\x23"
+				"\xba\x2e\xc5\x5c\xf3\x67\xfe\x95"
+				"\x09\xa0\x37\xce\x42\xd9\x70\x07"
+				"\x7b\x12\xa9\x1d\xb4\x4b\xe2\x56"
+				"\xed\x84\x1b\x8f\x26\xbd\x31\xc8"
+				"\x5f\xf6\x6a\x01\x98\x0c\xa3\x3a"
+				"\xd1\x45\xdc\x73\x0a\x7e\x15\xac"
+				"\x20\xb7\x4e\xe5\x59\xf0\x87\x1e"
+				"\x92\x29\xc0\x34\xcb\x62\xf9\x6d"
+				"\x04\x9b\x0f\xa6\x3d\xd4\x48\xdf"
+				"\x76\x0d\x81\x18\xaf\x23\xba\x51"
+				"\xe8\x5c\xf3\x8a\x21\x95\x2c\xc3"
+				"\x37\xce\x65\xfc\x70\x07\x9e\x12"
+				"\xa9\x40\xd7\x4b\xe2\x79\x10\x84"
+				"\x1b\xb2\x26\xbd\x54\xeb\x5f\xf6"
+				"\x8d\x01\x98\x2f\xc6\x3a\xd1\x68"
+				"\xff\x73\x0a\xa1\x15\xac\x43\xda"
+				"\x4e\xe5\x7c\x13\x87\x1e\xb5\x29"
+				"\xc0\x57\xee\x62\xf9\x90\x04\x9b"
+				"\x32\xc9\x3d\xd4\x6b\x02\x76\x0d"
+				"\xa4\x18\xaf\x46\xdd\x51\xe8\x7f"
+				"\x16\x8a\x21\xb8\x2c\xc3\x5a\xf1"
+				"\x65\xfc\x93\x07\x9e\x35\xcc\x40"
+				"\xd7\x6e\x05\x79\x10\xa7\x1b\xb2"
+				"\x49\xe0\x54\xeb\x82\x19\x8d\x24"
+				"\xbb\x2f\xc6\x5d\xf4\x68\xff\x96"
+				"\x0a\xa1\x38\xcf\x43\xda\x71\x08"
+				"\x7c\x13\xaa\x1e\xb5\x4c\xe3\x57"
+				"\xee\x85\x1c\x90\x27\xbe\x32\xc9"
+				"\x60\xf7\x6b\x02\x99\x0d\xa4\x3b"
+				"\xd2\x46\xdd\x74\x0b\x7f\x16\xad"
+				"\x21\xb8\x4f\xe6\x5a\xf1\x88\x1f"
+				"\x93\x2a\xc1\x35\xcc\x63\xfa\x6e"
+				"\x05\x9c\x10\xa7\x3e\xd5\x49\xe0"
+				"\x77\x0e\x82\x19\xb0\x24\xbb\x52"
+				"\xe9\x5d\xf4\x8b\x22\x96\x2d\xc4"
+				"\x38\xcf\x66\xfd\x71\x08\x9f\x13"
+				"\xaa\x41\xd8\x4c\xe3\x7a\x11\x85"
+				"\x1c\xb3\x27\xbe\x55\xec\x60\xf7"
+				"\x8e\x02\x99\x30\xc7\x3b\xd2\x69"
+				"\x00\x74\x0b\xa2\x16\xad\x44\xdb"
+				"\x4f\xe6\x7d\x14\x88\x1f\xb6\x2a"
+				"\xc1\x58\xef\x63\xfa\x91\x05\x9c"
+				"\x33\xca\x3e\xd5\x6c\x03\x77\x0e"
+				"\xa5\x19\xb0\x47\xde\x52\xe9\x80"
+				"\x17\x8b\x22\xb9\x2d\xc4\x5b\xf2"
+				"\x66\xfd\x94\x08\x9f\x36\xcd\x41"
+				"\xd8\x6f\x06\x7a\x11\xa8\x1c\xb3"
+				"\x4a\xe1\x55\xec\x83\x1a\x8e\x25"
+				"\xbc\x30\xc7\x5e\xf5\x69\x00\x97"
+				"\x0b\xa2\x39\xd0\x44\xdb\x72\x09"
+				"\x7d\x14\xab\x1f\xb6\x4d\xe4\x58"
+				"\xef\x86\x1d\x91\x28\xbf\x33\xca"
+				"\x61\xf8\x6c\x03\x9a\x0e\xa5\x3c"
+				"\xd3\x47\xde\x75\x0c\x80\x17\xae"
+				"\x22\xb9\x50\xe7\x5b\xf2\x89\x20"
+				"\x94\x2b\xc2\x36\xcd\x64\xfb\x6f"
+				"\x06\x9d\x11\xa8\x3f\xd6\x4a\xe1"
+				"\x78\x0f\x83\x1a\xb1\x25\xbc\x53"
+				"\xea\x5e\xf5\x8c\x00\x97\x2e\xc5"
+				"\x39\xd0\x67\xfe\x72\x09\xa0\x14"
+				"\xab\x42\xd9\x4d\xe4\x7b\x12\x86"
+				"\x1d\xb4\x28\xbf\x56\xed\x61\xf8"
+				"\x8f\x03\x9a\x31\xc8\x3c\xd3\x6a"
+				"\x01\x75\x0c\xa3\x17\xae\x45\xdc"
+				"\x50\xe7\x7e\x15\x89\x20\xb7\x2b"
+				"\xc2\x59\xf0\x64\xfb\x92\x06\x9d"
+				"\x34\xcb\x3f\xd6\x6d\x04\x78\x0f"
+				"\xa6\x1a\xb1\x48\xdf\x53\xea\x81"
+				"\x18\x8c\x23\xba\x2e\xc5\x5c\xf3"
+				"\x67\xfe\x95\x09\xa0\x37\xce\x42"
+				"\xd9\x70\x07\x7b\x12\xa9\x1d\xb4"
+				"\x4b\xe2\x56\xed\x84\x1b\x8f\x26"
+				"\xbd\x31\xc8\x5f\xf6\x6a\x01\x98",
+		.psize = 2048,
+		.digest = "\xfb\x3a\x7a\xda",
+	}
+};
+
+/*
  * CRC32C test vectors
  */
 #define CRC32C_TEST_VECTORS 15
diff --git a/crypto/zlib.c b/crypto/zlib.c
index 0eefa9d237ac..d51a30a29e42 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -78,7 +78,7 @@ static void zlib_exit(struct crypto_tfm *tfm)
 }
 
 
-static int zlib_compress_setup(struct crypto_pcomp *tfm, void *params,
+static int zlib_compress_setup(struct crypto_pcomp *tfm, const void *params,
 			       unsigned int len)
 {
 	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
@@ -209,7 +209,7 @@ static int zlib_compress_final(struct crypto_pcomp *tfm,
 }
 
 
-static int zlib_decompress_setup(struct crypto_pcomp *tfm, void *params,
+static int zlib_decompress_setup(struct crypto_pcomp *tfm, const void *params,
 				 unsigned int len)
 {
 	struct zlib_ctx *ctx = crypto_tfm_ctx(crypto_pcomp_tfm(tfm));
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ab2cbb51c6aa..35da507411a0 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -54,6 +54,9 @@ config ACPI_GENERIC_GSI
 config ACPI_SYSTEM_POWER_STATES_SUPPORT
 	bool
 
+config ACPI_CCA_REQUIRED
+	bool
+
 config ACPI_SLEEP
 	bool
 	depends on SUSPEND || HIBERNATION
@@ -62,7 +65,7 @@ config ACPI_SLEEP
 
 config ACPI_PROCFS_POWER
 	bool "Deprecated power /proc/acpi directories"
-	depends on PROC_FS
+	depends on X86 && PROC_FS
 	help
 	  For backwards compatibility, this option allows
           deprecated power /proc/acpi/ directories to exist, even when
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 8a063e276530..73d840bef455 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -52,9 +52,6 @@ acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
 acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
-ifdef CONFIG_ACPI_VIDEO
-acpi-y				+= video_detect.o
-endif
 acpi-y				+= acpi_lpat.o
 acpi-$(CONFIG_ACPI_GENERIC_GSI) += gsi.o
 
@@ -95,3 +92,5 @@ obj-$(CONFIG_ACPI_EXTLOG)	+= acpi_extlog.o
 obj-$(CONFIG_PMIC_OPREGION)	+= pmic/intel_pmic.o
 obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
 obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
+
+video-objs			+= acpi_video.o video_detect.o
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index bbcc2b5a70d4..9b5354a2cd08 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -308,7 +308,7 @@ static int thinkpad_e530_quirk(const struct dmi_system_id *d)
 	return 0;
 }
 
-static struct dmi_system_id ac_dmi_table[] = {
+static const struct dmi_system_id ac_dmi_table[] = {
 	{
 	.callback = thinkpad_e530_quirk,
 	.ident = "thinkpad e530",
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 37fb19047603..569ee090343f 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -129,50 +129,50 @@ static void byt_i2c_setup(struct lpss_private_data *pdata)
 	writel(0, pdata->mmio_base + LPSS_I2C_ENABLE);
 }
 
-static struct lpss_device_desc lpt_dev_desc = {
+static const struct lpss_device_desc lpt_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
 	.prv_offset = 0x800,
 };
 
-static struct lpss_device_desc lpt_i2c_dev_desc = {
+static const struct lpss_device_desc lpt_i2c_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_LTR,
 	.prv_offset = 0x800,
 };
 
-static struct lpss_device_desc lpt_uart_dev_desc = {
+static const struct lpss_device_desc lpt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_LTR,
 	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
 
-static struct lpss_device_desc lpt_sdio_dev_desc = {
+static const struct lpss_device_desc lpt_sdio_dev_desc = {
 	.flags = LPSS_LTR,
 	.prv_offset = 0x1000,
 	.prv_size_override = 0x1018,
 };
 
-static struct lpss_device_desc byt_pwm_dev_desc = {
+static const struct lpss_device_desc byt_pwm_dev_desc = {
 	.flags = LPSS_SAVE_CTX,
 };
 
-static struct lpss_device_desc byt_uart_dev_desc = {
+static const struct lpss_device_desc byt_uart_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.clk_con_id = "baudclk",
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
 
-static struct lpss_device_desc byt_spi_dev_desc = {
+static const struct lpss_device_desc byt_spi_dev_desc = {
 	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x400,
 };
 
-static struct lpss_device_desc byt_sdio_dev_desc = {
+static const struct lpss_device_desc byt_sdio_dev_desc = {
 	.flags = LPSS_CLK,
 };
 
-static struct lpss_device_desc byt_i2c_dev_desc = {
+static const struct lpss_device_desc byt_i2c_dev_desc = {
 	.flags = LPSS_CLK | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = byt_i2c_setup,
@@ -323,14 +323,14 @@ out:
 static int acpi_lpss_create_device(struct acpi_device *adev,
 				   const struct acpi_device_id *id)
 {
-	struct lpss_device_desc *dev_desc;
+	const struct lpss_device_desc *dev_desc;
 	struct lpss_private_data *pdata;
 	struct resource_entry *rentry;
 	struct list_head resource_list;
 	struct platform_device *pdev;
 	int ret;
 
-	dev_desc = (struct lpss_device_desc *)id->driver_data;
+	dev_desc = (const struct lpss_device_desc *)id->driver_data;
 	if (!dev_desc) {
 		pdev = acpi_create_platform_device(adev);
 		return IS_ERR_OR_NULL(pdev) ? PTR_ERR(pdev) : 1;
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6bc9cbc01ad6..00b39802d7ec 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -105,7 +105,7 @@ static void round_robin_cpu(unsigned int tsk_index)
 	mutex_lock(&round_robin_lock);
 	cpumask_clear(tmp);
 	for_each_cpu(cpu, pad_busy_cpus)
-		cpumask_or(tmp, tmp, topology_thread_cpumask(cpu));
+		cpumask_or(tmp, tmp, topology_sibling_cpumask(cpu));
 	cpumask_andnot(tmp, cpu_online_mask, tmp);
 	/* avoid HT sibilings if possible */
 	if (cpumask_empty(tmp))
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 4bf75597f732..06a67d5f2846 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -103,7 +103,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	pdevinfo.res = resources;
 	pdevinfo.num_res = count;
 	pdevinfo.fwnode = acpi_fwnode_handle(adev);
-	pdevinfo.dma_mask = DMA_BIT_MASK(32);
+	pdevinfo.dma_mask = acpi_check_dma(adev, NULL) ? DMA_BIT_MASK(32) : 0;
 	pdev = platform_device_register_full(&pdevinfo);
 	if (IS_ERR(pdev))
 		dev_err(&adev->dev, "platform device creation failed: %ld\n",
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index b193f8425999..ff6d8adc9cda 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -304,6 +304,8 @@ static const struct acpi_device_id acpi_pnp_device_ids[] = {
 	{"PNPb006"},
 	/* cs423x-pnpbios */
 	{"CSC0100"},
+	{"CSC0103"},
+	{"CSC0110"},
 	{"CSC0000"},
 	{"GIM0100"},		/* Guillemot Turtlebeach something appears to be cs4232 compatible */
 	/* es18xx-pnpbios */
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 58f335ca2e75..92a5f738e370 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,7 +170,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
-	if (pr->phys_id == PHYS_CPUID_INVALID)
+	if (invalid_phys_cpuid(pr->phys_id))
 		return -ENODEV;
 
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
@@ -215,8 +215,7 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	union acpi_object object = { 0 };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
-	phys_cpuid_t phys_id;
-	int cpu_index, device_declaration = 0;
+	int device_declaration = 0;
 	acpi_status status = AE_OK;
 	static int cpu0_initialized;
 	unsigned long long value;
@@ -263,29 +262,28 @@ static int acpi_processor_get_info(struct acpi_device *device)
 		pr->acpi_id = value;
 	}
 
-	phys_id = acpi_get_phys_id(pr->handle, device_declaration, pr->acpi_id);
-	if (phys_id == PHYS_CPUID_INVALID)
+	pr->phys_id = acpi_get_phys_id(pr->handle, device_declaration,
+					pr->acpi_id);
+	if (invalid_phys_cpuid(pr->phys_id))
 		acpi_handle_debug(pr->handle, "failed to get CPU physical ID.\n");
-	pr->phys_id = phys_id;
 
-	cpu_index = acpi_map_cpuid(pr->phys_id, pr->acpi_id);
+	pr->id = acpi_map_cpuid(pr->phys_id, pr->acpi_id);
 	if (!cpu0_initialized && !acpi_has_cpu_in_madt()) {
 		cpu0_initialized = 1;
 		/*
 		 * Handle UP system running SMP kernel, with no CPU
 		 * entry in MADT
 		 */
-		if ((cpu_index == -1) && (num_online_cpus() == 1))
-			cpu_index = 0;
+		if (invalid_logical_cpuid(pr->id) && (num_online_cpus() == 1))
+			pr->id = 0;
 	}
-	pr->id = cpu_index;
 
 	/*
 	 *  Extra Processor objects may be enumerated on MP systems with
 	 *  less than the max # of CPUs. They should be ignored _iff
 	 *  they are physically not present.
 	 */
-	if (pr->id == -1) {
+	if (invalid_logical_cpuid(pr->id)) {
 		int ret = acpi_processor_hotadd_init(pr);
 		if (ret)
 			return ret;
diff --git a/drivers/acpi/video.c b/drivers/acpi/acpi_video.c
index cc79d3fedfb2..8c2fe2f2f9fd 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/acpi_video.c
@@ -43,7 +43,7 @@
 #include <acpi/video.h>
 #include <asm/uaccess.h>
 
-#include "internal.h"
+#define PREFIX "ACPI: "
 
 #define ACPI_VIDEO_BUS_NAME		"Video Bus"
 #define ACPI_VIDEO_DEVICE_NAME		"Video Device"
@@ -78,26 +78,17 @@ module_param(brightness_switch_enabled, bool, 0644);
 static bool allow_duplicates;
 module_param(allow_duplicates, bool, 0644);
 
-/*
- * For Windows 8 systems: used to decide if video module
- * should skip registering backlight interface of its own.
- */
-enum {
-	NATIVE_BACKLIGHT_NOT_SET = -1,
-	NATIVE_BACKLIGHT_OFF,
-	NATIVE_BACKLIGHT_ON,
-};
-
-static int use_native_backlight_param = NATIVE_BACKLIGHT_NOT_SET;
-module_param_named(use_native_backlight, use_native_backlight_param, int, 0444);
-static int use_native_backlight_dmi = NATIVE_BACKLIGHT_NOT_SET;
+static int disable_backlight_sysfs_if = -1;
+module_param(disable_backlight_sysfs_if, int, 0444);
 
 static int register_count;
+static DEFINE_MUTEX(register_count_mutex);
 static struct mutex video_list_lock;
 static struct list_head video_bus_head;
 static int acpi_video_bus_add(struct acpi_device *device);
 static int acpi_video_bus_remove(struct acpi_device *device);
 static void acpi_video_bus_notify(struct acpi_device *device, u32 event);
+void acpi_video_detect_exit(void);
 
 static const struct acpi_device_id video_device_ids[] = {
 	{ACPI_VIDEO_HID, 0},
@@ -157,7 +148,6 @@ struct acpi_video_enumerated_device {
 struct acpi_video_bus {
 	struct acpi_device *device;
 	bool backlight_registered;
-	bool backlight_notifier_registered;
 	u8 dos_setting;
 	struct acpi_video_enumerated_device *attached_array;
 	u8 attached_count;
@@ -170,7 +160,6 @@ struct acpi_video_bus {
 	struct input_dev *input;
 	char phys[32];	/* for input device */
 	struct notifier_block pm_nb;
-	struct notifier_block backlight_nb;
 };
 
 struct acpi_video_device_flags {
@@ -241,24 +230,6 @@ static int acpi_video_get_next_level(struct acpi_video_device *device,
 				     u32 level_current, u32 event);
 static void acpi_video_switch_brightness(struct work_struct *work);
 
-static bool acpi_video_use_native_backlight(void)
-{
-	if (use_native_backlight_param != NATIVE_BACKLIGHT_NOT_SET)
-		return use_native_backlight_param;
-	else if (use_native_backlight_dmi != NATIVE_BACKLIGHT_NOT_SET)
-		return use_native_backlight_dmi;
-	return acpi_osi_is_win8();
-}
-
-bool acpi_video_verify_backlight_support(void)
-{
-	if (acpi_video_use_native_backlight() &&
-	    backlight_device_registered(BACKLIGHT_RAW))
-		return false;
-	return acpi_video_backlight_support();
-}
-EXPORT_SYMBOL_GPL(acpi_video_verify_backlight_support);
-
 /* backlight device sysfs support */
 static int acpi_video_get_brightness(struct backlight_device *bd)
 {
@@ -413,25 +384,21 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level)
  */
 
 static int bqc_offset_aml_bug_workaround;
-static int __init video_set_bqc_offset(const struct dmi_system_id *d)
+static int video_set_bqc_offset(const struct dmi_system_id *d)
 {
 	bqc_offset_aml_bug_workaround = 9;
 	return 0;
 }
 
-static int __init video_disable_native_backlight(const struct dmi_system_id *d)
-{
-	use_native_backlight_dmi = NATIVE_BACKLIGHT_OFF;
-	return 0;
-}
-
-static int __init video_enable_native_backlight(const struct dmi_system_id *d)
+static int video_disable_backlight_sysfs_if(
+	const struct dmi_system_id *d)
 {
-	use_native_backlight_dmi = NATIVE_BACKLIGHT_ON;
+	if (disable_backlight_sysfs_if == -1)
+		disable_backlight_sysfs_if = 1;
 	return 0;
 }
 
-static struct dmi_system_id video_dmi_table[] __initdata = {
+static struct dmi_system_id video_dmi_table[] = {
 	/*
 	 * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121
 	 */
@@ -477,110 +444,19 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 
 	/*
-	 * These models have a working acpi_video backlight control, and using
-	 * native backlight causes a regression where backlight does not work
-	 * when userspace is not handling brightness key events. Disable
-	 * native_backlight on these to fix this:
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=81691
+	 * Some machines have a broken acpi-video interface for brightness
+	 * control, but still need an acpi_video_device_lcd_set_level() call
+	 * on resume to turn the backlight power on.  We Enable backlight
+	 * control on these systems, but do not register a backlight sysfs
+	 * as brightness control does not work.
 	 */
 	{
-	 .callback = video_disable_native_backlight,
-	 .ident = "ThinkPad T420",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T420"),
-		},
-	},
-	{
-	 .callback = video_disable_native_backlight,
-	 .ident = "ThinkPad T520",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T520"),
-		},
-	},
-	{
-	 .callback = video_disable_native_backlight,
-	 .ident = "ThinkPad X201s",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
-		},
-	},
-
-	/* The native backlight controls do not work on some older machines */
-	{
-	 /* https://bugs.freedesktop.org/show_bug.cgi?id=81515 */
-	 .callback = video_disable_native_backlight,
-	 .ident = "HP ENVY 15 Notebook",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"),
-		},
-	},
-
-	{
-	 .callback = video_disable_native_backlight,
-	 .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"),
-		},
-	},
-	{
-	 .callback = video_disable_native_backlight,
-	 .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "370R4E/370R4V/370R5E/3570RE/370R5V"),
-		},
-	},
-	{
-	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1186097 */
-	 .callback = video_disable_native_backlight,
-	 .ident = "SAMSUNG 3570R/370R/470R/450R/510R/4450RV",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "3570R/370R/470R/450R/510R/4450RV"),
-		},
-	},
-	{
-	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1094948 */
-	 .callback = video_disable_native_backlight,
-	 .ident = "SAMSUNG 730U3E/740U3E",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "730U3E/740U3E"),
-		},
-	},
-	{
-	 /* https://bugs.freedesktop.org/show_bug.cgi?id=87286 */
-	 .callback = video_disable_native_backlight,
-	 .ident = "SAMSUNG 900X3C/900X3D/900X3E/900X4C/900X4D",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "900X3C/900X3D/900X3E/900X4C/900X4D"),
-		},
-	},
-
-	{
-	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */
-	 .callback = video_disable_native_backlight,
-	 .ident = "Dell XPS15 L521X",
+	 /* https://bugs.freedesktop.org/show_bug.cgi?id=82634 */
+	 .callback = video_disable_backlight_sysfs_if,
+	 .ident = "Toshiba Portege R830",
 	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "XPS L521X"),
-		},
-	},
-
-	/* Non win8 machines which need native backlight nevertheless */
-	{
-	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1187004 */
-	 .callback = video_enable_native_backlight,
-	 .ident = "Lenovo Ideapad Z570",
-	 .matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "102434U"),
+		DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R830"),
 		},
 	},
 	{}
@@ -1382,7 +1258,7 @@ acpi_video_switch_brightness(struct work_struct *work)
 	int result = -EINVAL;
 
 	/* no warning message if acpi_backlight=vendor or a quirk is used */
-	if (!acpi_video_verify_backlight_support())
+	if (!device->backlight)
 		return;
 
 	if (!device->brightness)
@@ -1657,8 +1533,9 @@ static int acpi_video_resume(struct notifier_block *nb,
 
 	for (i = 0; i < video->attached_count; i++) {
 		video_device = video->attached_array[i].bind_info;
-		if (video_device && video_device->backlight)
-			acpi_video_set_brightness(video_device->backlight);
+		if (video_device && video_device->brightness)
+			acpi_video_device_lcd_set_level(video_device,
+					video_device->brightness->curr);
 	}
 
 	return NOTIFY_OK;
@@ -1707,6 +1584,10 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 	result = acpi_video_init_brightness(device);
 	if (result)
 		return;
+
+	if (disable_backlight_sysfs_if > 0)
+		return;
+
 	name = kasprintf(GFP_KERNEL, "acpi_video%d", count);
 	if (!name)
 		return;
@@ -1729,8 +1610,10 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device)
 						      &acpi_backlight_ops,
 						      &props);
 	kfree(name);
-	if (IS_ERR(device->backlight))
+	if (IS_ERR(device->backlight)) {
+		device->backlight = NULL;
 		return;
+	}
 
 	/*
 	 * Save current brightness level in case we have to restore it
@@ -1787,7 +1670,7 @@ static int acpi_video_bus_register_backlight(struct acpi_video_bus *video)
 
 	acpi_video_run_bcl_for_osi(video);
 
-	if (!acpi_video_verify_backlight_support())
+	if (acpi_video_get_backlight_type() != acpi_backlight_video)
 		return 0;
 
 	mutex_lock(&video->device_list_lock);
@@ -1931,56 +1814,6 @@ static void acpi_video_bus_remove_notify_handler(struct acpi_video_bus *video)
 	video->input = NULL;
 }
 
-static int acpi_video_backlight_notify(struct notifier_block *nb,
-					unsigned long val, void *bd)
-{
-	struct backlight_device *backlight = bd;
-	struct acpi_video_bus *video;
-
-	/* acpi_video_verify_backlight_support only cares about raw devices */
-	if (backlight->props.type != BACKLIGHT_RAW)
-		return NOTIFY_DONE;
-
-	video = container_of(nb, struct acpi_video_bus, backlight_nb);
-
-	switch (val) {
-	case BACKLIGHT_REGISTERED:
-		if (!acpi_video_verify_backlight_support())
-			acpi_video_bus_unregister_backlight(video);
-		break;
-	case BACKLIGHT_UNREGISTERED:
-		acpi_video_bus_register_backlight(video);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static int acpi_video_bus_add_backlight_notify_handler(
-						struct acpi_video_bus *video)
-{
-	int error;
-
-	video->backlight_nb.notifier_call = acpi_video_backlight_notify;
-	video->backlight_nb.priority = 0;
-	error = backlight_register_notifier(&video->backlight_nb);
-	if (error == 0)
-		video->backlight_notifier_registered = true;
-
-	return error;
-}
-
-static int acpi_video_bus_remove_backlight_notify_handler(
-						struct acpi_video_bus *video)
-{
-	if (!video->backlight_notifier_registered)
-		return 0;
-
-	video->backlight_notifier_registered = false;
-
-	return backlight_unregister_notifier(&video->backlight_nb);
-}
-
 static int acpi_video_bus_put_devices(struct acpi_video_bus *video)
 {
 	struct acpi_video_device *dev, *next;
@@ -2062,7 +1895,6 @@ static int acpi_video_bus_add(struct acpi_device *device)
 
 	acpi_video_bus_register_backlight(video);
 	acpi_video_bus_add_notify_handler(video);
-	acpi_video_bus_add_backlight_notify_handler(video);
 
 	return 0;
 
@@ -2086,7 +1918,6 @@ static int acpi_video_bus_remove(struct acpi_device *device)
 
 	video = acpi_driver_data(device);
 
-	acpi_video_bus_remove_backlight_notify_handler(video);
 	acpi_video_bus_remove_notify_handler(video);
 	acpi_video_bus_unregister_backlight(video);
 	acpi_video_bus_put_devices(video);
@@ -2134,22 +1965,25 @@ static int __init intel_opregion_present(void)
 
 int acpi_video_register(void)
 {
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&register_count_mutex);
 	if (register_count) {
 		/*
 		 * if the function of acpi_video_register is already called,
 		 * don't register the acpi_vide_bus again and return no error.
 		 */
-		return 0;
+		goto leave;
 	}
 
 	mutex_init(&video_list_lock);
 	INIT_LIST_HEAD(&video_bus_head);
 
+	dmi_check_system(video_dmi_table);
+
 	ret = acpi_bus_register_driver(&acpi_video_bus);
 	if (ret)
-		return ret;
+		goto leave;
 
 	/*
 	 * When the acpi_video_bus is loaded successfully, increase
@@ -2157,24 +1991,20 @@ int acpi_video_register(void)
 	 */
 	register_count = 1;
 
-	return 0;
+leave:
+	mutex_unlock(&register_count_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(acpi_video_register);
 
 void acpi_video_unregister(void)
 {
-	if (!register_count) {
-		/*
-		 * If the acpi video bus is already unloaded, don't
-		 * unload it again and return directly.
-		 */
-		return;
+	mutex_lock(&register_count_mutex);
+	if (register_count) {
+		acpi_bus_unregister_driver(&acpi_video_bus);
+		register_count = 0;
 	}
-	acpi_bus_unregister_driver(&acpi_video_bus);
-
-	register_count = 0;
-
-	return;
+	mutex_unlock(&register_count_mutex);
 }
 EXPORT_SYMBOL(acpi_video_unregister);
 
@@ -2182,15 +2012,15 @@ void acpi_video_unregister_backlight(void)
 {
 	struct acpi_video_bus *video;
 
-	if (!register_count)
-		return;
-
-	mutex_lock(&video_list_lock);
-	list_for_each_entry(video, &video_bus_head, entry)
-		acpi_video_bus_unregister_backlight(video);
-	mutex_unlock(&video_list_lock);
+	mutex_lock(&register_count_mutex);
+	if (register_count) {
+		mutex_lock(&video_list_lock);
+		list_for_each_entry(video, &video_bus_head, entry)
+			acpi_video_bus_unregister_backlight(video);
+		mutex_unlock(&video_list_lock);
+	}
+	mutex_unlock(&register_count_mutex);
 }
-EXPORT_SYMBOL(acpi_video_unregister_backlight);
 
 /*
  * This is kind of nasty. Hardware using Intel chipsets may require
@@ -2212,8 +2042,6 @@ static int __init acpi_video_init(void)
 	if (acpi_disabled)
 		return 0;
 
-	dmi_check_system(video_dmi_table);
-
 	if (intel_opregion_present())
 		return 0;
 
@@ -2222,6 +2050,7 @@ static int __init acpi_video_init(void)
 
 static void __exit acpi_video_exit(void)
 {
+	acpi_video_detect_exit();
 	acpi_video_unregister();
 
 	return;
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 4169bb87a996..43685dd36c77 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -231,7 +231,9 @@ void acpi_db_open_debug_file(char *name);
 acpi_status acpi_db_load_acpi_table(char *filename);
 
 acpi_status
-acpi_db_get_table_from_file(char *filename, struct acpi_table_header **table);
+acpi_db_get_table_from_file(char *filename,
+			    struct acpi_table_header **table,
+			    u8 must_be_aml_table);
 
 /*
  * dbhistry - debugger HISTORY command
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 87b27521fcac..ffdb956391f6 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -352,11 +352,21 @@ struct acpi_package_info3 {
 	u16 reserved;
 };
 
+struct acpi_package_info4 {
+	u8 type;
+	u8 object_type1;
+	u8 count1;
+	u8 sub_object_types;
+	u8 pkg_count;
+	u16 reserved;
+};
+
 union acpi_predefined_info {
 	struct acpi_name_info info;
 	struct acpi_package_info ret_info;
 	struct acpi_package_info2 ret_info2;
 	struct acpi_package_info3 ret_info3;
+	struct acpi_package_info4 ret_info4;
 };
 
 /* Reset to default packing */
@@ -1165,4 +1175,9 @@ struct ah_uuid {
 	char *string;
 };
 
+struct ah_table {
+	char *signature;
+	char *description;
+};
+
 #endif				/* __ACLOCAL_H__ */
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index 74a390c6db16..0cdd2fce493a 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -70,6 +70,9 @@
  *
  *****************************************************************************/
 
+extern const u8 acpi_gbl_short_op_index[];
+extern const u8 acpi_gbl_long_op_index[];
+
 /*
  * psxface - Parser external interfaces
  */
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index a972d11c97c9..b9474b529fcb 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -105,6 +105,11 @@
  *      count = 0 (optional)
  *      (Used for _DLM)
  *
+ * ACPI_PTYPE2_VAR_VAR: Variable number of subpackages, each of either a
+ *      constant or variable length. The subpackages are preceded by a
+ *      constant number of objects.
+ *      (Used for _LPI, _RDI)
+ *
  * ACPI_PTYPE2_UUID_PAIR: Each subpackage is preceded by a UUID Buffer. The UUID
  *      defines the format of the package. Zero-length parent package is
  *      allowed.
@@ -123,7 +128,8 @@ enum acpi_return_package_types {
 	ACPI_PTYPE2_MIN = 8,
 	ACPI_PTYPE2_REV_FIXED = 9,
 	ACPI_PTYPE2_FIX_VAR = 10,
-	ACPI_PTYPE2_UUID_PAIR = 11
+	ACPI_PTYPE2_VAR_VAR = 11,
+	ACPI_PTYPE2_UUID_PAIR = 12
 };
 
 /* Support macros for users of the predefined info table */
@@ -172,7 +178,7 @@ enum acpi_return_package_types {
  * These are the names that can actually be evaluated via acpi_evaluate_object.
  * Not present in this table are the following:
  *
- *      1) Predefined/Reserved names that are never evaluated via
+ *      1) Predefined/Reserved names that are not usually evaluated via
  *         acpi_evaluate_object:
  *              _Lxx and _Exx GPE methods
  *              _Qxx EC methods
@@ -361,6 +367,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Fixed-length (4 Int) */
 	PACKAGE_INFO(ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 4, 0, 0, 0),
 
+	{{"_BTH", METHOD_1ARGS(ACPI_TYPE_INTEGER),	/* ACPI 6.0 */
+	  METHOD_NO_RETURN_VALUE}},
+
 	{{"_BTM", METHOD_1ARGS(ACPI_TYPE_INTEGER),
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
@@ -390,6 +399,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	PACKAGE_INFO(ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER, 0,
 		     0, 0, 0),
 
+	{{"_CR3", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
+
 	{{"_CRS", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_BUFFER)}},
 
@@ -445,7 +457,7 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	{{"_DOS", METHOD_1ARGS(ACPI_TYPE_INTEGER),
 	  METHOD_NO_RETURN_VALUE}},
 
-	{{"_DSD", METHOD_0ARGS,
+	{{"_DSD", METHOD_0ARGS,	/* ACPI 6.0 */
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (Pkgs) each: 1 Buf, 1 Pkg */
 	PACKAGE_INFO(ACPI_PTYPE2_UUID_PAIR, ACPI_RTYPE_BUFFER, 1,
 		     ACPI_RTYPE_PACKAGE, 1, 0),
@@ -604,6 +616,12 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (1 Int(rev), n Pkg (2 Int) */
 	PACKAGE_INFO(ACPI_PTYPE2_REV_FIXED, ACPI_RTYPE_INTEGER, 2, 0, 0, 0),
 
+	{{"_LPI", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (3 Int, n Pkg (10 Int/Buf) */
+	PACKAGE_INFO(ACPI_PTYPE2_VAR_VAR, ACPI_RTYPE_INTEGER, 3,
+		     ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER | ACPI_RTYPE_STRING,
+		     10, 0),
+
 	{{"_MAT", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_BUFFER)}},
 
@@ -624,6 +642,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 		       ACPI_TYPE_INTEGER),
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
+	{{"_MTL", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
+
 	{{"_NTT", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
@@ -716,6 +737,10 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (Refs) */
 	PACKAGE_INFO(ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0),
 
+	{{"_PRR", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Fixed-length (1 Ref) */
+	PACKAGE_INFO(ACPI_PTYPE1_FIXED, ACPI_RTYPE_REFERENCE, 1, 0, 0, 0),
+
 	{{"_PRS", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_BUFFER)}},
 
@@ -796,6 +821,11 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	{{"_PXM", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
+	{{"_RDI", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (1 Int, n Pkg (m Ref)) */
+	PACKAGE_INFO(ACPI_PTYPE2_VAR_VAR, ACPI_RTYPE_INTEGER, 1,
+		     ACPI_RTYPE_REFERENCE, 0, 0),
+
 	{{"_REG", METHOD_2ARGS(ACPI_TYPE_INTEGER, ACPI_TYPE_INTEGER),
 	  METHOD_NO_RETURN_VALUE}},
 
@@ -808,6 +838,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	{{"_ROM", METHOD_2ARGS(ACPI_TYPE_INTEGER, ACPI_TYPE_INTEGER),
 	  METHOD_RETURNS(ACPI_RTYPE_BUFFER)}},
 
+	{{"_RST", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_NO_RETURN_VALUE}},
+
 	{{"_RTV", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
@@ -935,6 +968,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	{{"_TDL", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
+	{{"_TFP", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
+
 	{{"_TIP", METHOD_1ARGS(ACPI_TYPE_INTEGER),
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
@@ -959,6 +995,9 @@ const union acpi_predefined_info acpi_gbl_predefined_methods[] = {
 	  METHOD_RETURNS(ACPI_RTYPE_PACKAGE)}},	/* Variable-length (Pkgs) each 5 Int with count */
 	PACKAGE_INFO(ACPI_PTYPE2_COUNT, ACPI_RTYPE_INTEGER, 5, 0, 0, 0),
 
+	{{"_TSN", METHOD_0ARGS,	/* ACPI 6.0 */
+	  METHOD_RETURNS(ACPI_RTYPE_REFERENCE)}},
+
 	{{"_TSP", METHOD_0ARGS,
 	  METHOD_RETURNS(ACPI_RTYPE_INTEGER)}},
 
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 2b3c5bd222f1..d49f5c7a20d9 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -251,7 +251,7 @@ extern const u8 _acpi_ctype[];
 #define _ACPI_DI     0x04	/* '0'-'9' */
 #define _ACPI_LO     0x02	/* 'a'-'z' */
 #define _ACPI_PU     0x10	/* punctuation */
-#define _ACPI_SP     0x08	/* space */
+#define _ACPI_SP     0x08	/* space, tab, CR, LF, VT, FF */
 #define _ACPI_UP     0x01	/* 'A'-'Z' */
 #define _ACPI_XD     0x80	/* '0'-'9', 'A'-'F', 'a'-'f' */
 
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index d72565a3c646..85bb951430d9 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -116,6 +116,7 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 	walk_state =
 	    acpi_ds_create_walk_state(node->owner_id, NULL, NULL, NULL);
 	if (!walk_state) {
+		acpi_ps_free_op(op);
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
 
@@ -125,6 +126,7 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 				  obj_desc->method.aml_length, NULL, 0);
 	if (ACPI_FAILURE(status)) {
 		acpi_ds_delete_walk_state(walk_state);
+		acpi_ps_free_op(op);
 		return_ACPI_STATUS(status);
 	}
 
@@ -133,9 +135,6 @@ acpi_ds_auto_serialize_method(struct acpi_namespace_node *node,
 	/* Parse the method, scan for creation of named objects */
 
 	status = acpi_ps_parse_aml(walk_state);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
 
 	acpi_ps_delete_parse_tree(op);
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/hwpci.c b/drivers/acpi/acpica/hwpci.c
index c5214dec4988..f785ea788356 100644
--- a/drivers/acpi/acpica/hwpci.c
+++ b/drivers/acpi/acpica/hwpci.c
@@ -123,7 +123,7 @@ acpi_hw_derive_pci_id(struct acpi_pci_id *pci_id,
 		      acpi_handle root_pci_device, acpi_handle pci_region)
 {
 	acpi_status status;
-	struct acpi_pci_device *list_head = NULL;
+	struct acpi_pci_device *list_head;
 
 	ACPI_FUNCTION_TRACE(hw_derive_pci_id);
 
@@ -177,13 +177,13 @@ acpi_hw_build_pci_list(acpi_handle root_pci_device,
 	acpi_handle parent_device;
 	acpi_status status;
 	struct acpi_pci_device *list_element;
-	struct acpi_pci_device *list_head = NULL;
 
 	/*
 	 * Ascend namespace branch until the root_pci_device is reached, building
 	 * a list of device nodes. Loop will exit when either the PCI device is
 	 * found, or the root of the namespace is reached.
 	 */
+	*return_list_head = NULL;
 	current_device = pci_region;
 	while (1) {
 		status = acpi_get_parent(current_device, &parent_device);
@@ -198,7 +198,6 @@ acpi_hw_build_pci_list(acpi_handle root_pci_device,
 		/* Finished when we reach the PCI root device (PNP0A03 or PNP0A08) */
 
 		if (parent_device == root_pci_device) {
-			*return_list_head = list_head;
 			return (AE_OK);
 		}
 
@@ -213,9 +212,9 @@ acpi_hw_build_pci_list(acpi_handle root_pci_device,
 
 		/* Put new element at the head of the list */
 
-		list_element->next = list_head;
+		list_element->next = *return_list_head;
 		list_element->device = parent_device;
-		list_head = list_element;
+		*return_list_head = list_element;
 
 		current_device = parent_device;
 	}
diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c
index 8b79958b7aca..9bb251932b45 100644
--- a/drivers/acpi/acpica/nsprepkg.c
+++ b/drivers/acpi/acpica/nsprepkg.c
@@ -316,6 +316,13 @@ acpi_ns_check_package(struct acpi_evaluate_info *info,
 		    acpi_ns_check_package_list(info, package, elements, count);
 		break;
 
+	case ACPI_PTYPE2_VAR_VAR:
+		/*
+		 * Returns a variable list of packages, each with a variable list
+		 * of objects.
+		 */
+		break;
+
 	case ACPI_PTYPE2_UUID_PAIR:
 
 		/* The package must contain pairs of (UUID + type) */
@@ -487,6 +494,12 @@ acpi_ns_check_package_list(struct acpi_evaluate_info *info,
 			}
 			break;
 
+		case ACPI_PTYPE2_VAR_VAR:
+			/*
+			 * Each subpackage has a fixed or variable number of elements
+			 */
+			break;
+
 		case ACPI_PTYPE2_FIXED:
 
 			/* Each subpackage has a fixed length */
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 151fcd95ba84..77d8103d0094 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -497,10 +497,10 @@ acpi_ns_remove_null_elements(struct acpi_evaluate_info *info,
 	case ACPI_PTYPE2_MIN:
 	case ACPI_PTYPE2_REV_FIXED:
 	case ACPI_PTYPE2_FIX_VAR:
-
 		break;
 
 	default:
+	case ACPI_PTYPE2_VAR_VAR:
 	case ACPI_PTYPE1_FIXED:
 	case ACPI_PTYPE1_OPTION:
 		return;
diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c
index 20e1a35169fc..58310907fa7b 100644
--- a/drivers/acpi/acpica/psopinfo.c
+++ b/drivers/acpi/acpica/psopinfo.c
@@ -50,9 +50,6 @@
 #define _COMPONENT          ACPI_PARSER
 ACPI_MODULE_NAME("psopinfo")
 
-extern const u8 acpi_gbl_short_op_index[];
-extern const u8 acpi_gbl_long_op_index[];
-
 static const u8 acpi_gbl_argument_count[] =
     { 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 6 };
 
diff --git a/drivers/acpi/acpica/utfileio.c b/drivers/acpi/acpica/utfileio.c
index 7e1168be39fa..857af824337b 100644
--- a/drivers/acpi/acpica/utfileio.c
+++ b/drivers/acpi/acpica/utfileio.c
@@ -198,11 +198,8 @@ acpi_ut_read_table(FILE * fp,
 			     table_header.length, file_size);
 
 #ifdef ACPI_ASL_COMPILER
-			status = fl_check_for_ascii(fp, NULL, FALSE);
-			if (ACPI_SUCCESS(status)) {
-				acpi_os_printf
-				    ("File appears to be ASCII only, must be binary\n");
-			}
+			acpi_os_printf("File is corrupt or is ASCII text -- "
+				       "it must be a binary file\n");
 #endif
 			return (AE_BAD_HEADER);
 		}
@@ -315,7 +312,7 @@ acpi_ut_read_table_from_file(char *filename, struct acpi_table_header ** table)
 	/* Get the entire file */
 
 	fprintf(stderr,
-		"Loading Acpi table from file %10s - Length %.8u (%06X)\n",
+		"Reading ACPI table from file %10s - Length %.8u (0x%06X)\n",
 		filename, file_size, file_size);
 
 	status = acpi_ut_read_table(file, table, &table_length);
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index a72685c1e819..5e8df9177da4 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -102,19 +102,12 @@ const struct acpi_predefined_names acpi_gbl_pre_defined_names[] = {
 	{"_SB_", ACPI_TYPE_DEVICE, NULL},
 	{"_SI_", ACPI_TYPE_LOCAL_SCOPE, NULL},
 	{"_TZ_", ACPI_TYPE_DEVICE, NULL},
-	/*
-	 * March, 2015:
-	 * The _REV object is in the process of being deprecated, because
-	 * other ACPI implementations permanently return 2. Thus, it
-	 * has little or no value. Return 2 for compatibility with
-	 * other ACPI implementations.
-	 */
-	{"_REV", ACPI_TYPE_INTEGER, ACPI_CAST_PTR(char, 2)},
+	{"_REV", ACPI_TYPE_INTEGER, (char *)ACPI_CA_SUPPORT_LEVEL},
 	{"_OS_", ACPI_TYPE_STRING, ACPI_OS_NAME},
-	{"_GL_", ACPI_TYPE_MUTEX, ACPI_CAST_PTR(char, 1)},
+	{"_GL_", ACPI_TYPE_MUTEX, (char *)1},
 
 #if !defined (ACPI_NO_METHOD_EXECUTION) || defined (ACPI_CONSTANT_EVAL_ONLY)
-	{"_OSI", ACPI_TYPE_METHOD, ACPI_CAST_PTR(char, 1)},
+	{"_OSI", ACPI_TYPE_METHOD, (char *)1},
 #endif
 
 	/* Table terminator */
diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c
index aa448278ba28..fda8b3def81c 100644
--- a/drivers/acpi/acpica/uthex.c
+++ b/drivers/acpi/acpica/uthex.c
@@ -75,9 +75,9 @@ char acpi_ut_hex_to_ascii_char(u64 integer, u32 position)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_ut_hex_char_to_value
+ * FUNCTION:    acpi_ut_ascii_char_to_hex
  *
- * PARAMETERS:  ascii_char            - Hex character in Ascii
+ * PARAMETERS:  hex_char                - Hex character in Ascii
  *
  * RETURN:      The binary value of the ascii/hex character
  *
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index 306e785f9418..98d578753101 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -107,9 +107,16 @@ acpi_exception(const char *module_name,
 	va_list arg_list;
 
 	ACPI_MSG_REDIRECT_BEGIN;
-	acpi_os_printf(ACPI_MSG_EXCEPTION "%s, ",
-		       acpi_format_exception(status));
 
+	/* For AE_OK, just print the message */
+
+	if (ACPI_SUCCESS(status)) {
+		acpi_os_printf(ACPI_MSG_EXCEPTION);
+
+	} else {
+		acpi_os_printf(ACPI_MSG_EXCEPTION "%s, ",
+			       acpi_format_exception(status));
+	}
 	va_start(arg_list, format);
 	acpi_os_vprintf(format, arg_list);
 	ACPI_MSG_SUFFIX;
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index ed65e9c4b5b0..3670bbab57a3 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -35,6 +35,7 @@
 #include <linux/nmi.h>
 #include <linux/hardirq.h>
 #include <linux/pstore.h>
+#include <linux/vmalloc.h>
 #include <acpi/apei.h>
 
 #include "apei-internal.h"
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index e82d0976a5d0..2bfd53cbfe80 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -729,10 +729,10 @@ static struct llist_head ghes_estatus_llist;
 static struct irq_work ghes_proc_irq_work;
 
 /*
- * NMI may be triggered on any CPU, so ghes_nmi_lock is used for
- * mutual exclusion.
+ * NMI may be triggered on any CPU, so ghes_in_nmi is used for
+ * having only one concurrent reader.
  */
-static DEFINE_RAW_SPINLOCK(ghes_nmi_lock);
+static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
 
 static LIST_HEAD(ghes_nmi);
 
@@ -797,73 +797,75 @@ static void ghes_print_queued_estatus(void)
 	}
 }
 
+/* Save estatus for further processing in IRQ context */
+static void __process_error(struct ghes *ghes)
+{
+#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+	u32 len, node_len;
+	struct ghes_estatus_node *estatus_node;
+	struct acpi_hest_generic_status *estatus;
+
+	if (ghes_estatus_cached(ghes->estatus))
+		return;
+
+	len = cper_estatus_len(ghes->estatus);
+	node_len = GHES_ESTATUS_NODE_LEN(len);
+
+	estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool, node_len);
+	if (!estatus_node)
+		return;
+
+	estatus_node->ghes = ghes;
+	estatus_node->generic = ghes->generic;
+	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
+	memcpy(estatus, ghes->estatus, len);
+	llist_add(&estatus_node->llnode, &ghes_estatus_llist);
+#endif
+}
+
+static void __ghes_panic(struct ghes *ghes)
+{
+	oops_begin();
+	ghes_print_queued_estatus();
+	__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
+
+	/* reboot to log the error! */
+	if (panic_timeout == 0)
+		panic_timeout = ghes_panic_timeout;
+	panic("Fatal hardware error!");
+}
+
 static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 {
-	struct ghes *ghes, *ghes_global = NULL;
-	int sev, sev_global = -1;
-	int ret = NMI_DONE;
+	struct ghes *ghes;
+	int sev, ret = NMI_DONE;
+
+	if (!atomic_add_unless(&ghes_in_nmi, 1, 1))
+		return ret;
 
-	raw_spin_lock(&ghes_nmi_lock);
 	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
 		if (ghes_read_estatus(ghes, 1)) {
 			ghes_clear_estatus(ghes);
 			continue;
 		}
-		sev = ghes_severity(ghes->estatus->error_severity);
-		if (sev > sev_global) {
-			sev_global = sev;
-			ghes_global = ghes;
-		}
-		ret = NMI_HANDLED;
-	}
-
-	if (ret == NMI_DONE)
-		goto out;
 
-	if (sev_global >= GHES_SEV_PANIC) {
-		oops_begin();
-		ghes_print_queued_estatus();
-		__ghes_print_estatus(KERN_EMERG, ghes_global->generic,
-				     ghes_global->estatus);
-		/* reboot to log the error! */
-		if (panic_timeout == 0)
-			panic_timeout = ghes_panic_timeout;
-		panic("Fatal hardware error!");
-	}
+		sev = ghes_severity(ghes->estatus->error_severity);
+		if (sev >= GHES_SEV_PANIC)
+			__ghes_panic(ghes);
 
-	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-		u32 len, node_len;
-		struct ghes_estatus_node *estatus_node;
-		struct acpi_hest_generic_status *estatus;
-#endif
 		if (!(ghes->flags & GHES_TO_CLEAR))
 			continue;
-#ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-		if (ghes_estatus_cached(ghes->estatus))
-			goto next;
-		/* Save estatus for further processing in IRQ context */
-		len = cper_estatus_len(ghes->estatus);
-		node_len = GHES_ESTATUS_NODE_LEN(len);
-		estatus_node = (void *)gen_pool_alloc(ghes_estatus_pool,
-						      node_len);
-		if (estatus_node) {
-			estatus_node->ghes = ghes;
-			estatus_node->generic = ghes->generic;
-			estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-			memcpy(estatus, ghes->estatus, len);
-			llist_add(&estatus_node->llnode, &ghes_estatus_llist);
-		}
-next:
-#endif
+
+		__process_error(ghes);
 		ghes_clear_estatus(ghes);
+
+		ret = NMI_HANDLED;
 	}
+
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
 	irq_work_queue(&ghes_proc_irq_work);
 #endif
-
-out:
-	raw_spin_unlock(&ghes_nmi_lock);
+	atomic_dec(&ghes_in_nmi);
 	return ret;
 }
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 63d43677f644..b3628cc01a53 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -70,6 +70,7 @@ MODULE_AUTHOR("Alexey Starikovskiy <astarikovskiy@suse.de>");
 MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
+static async_cookie_t async_cookie;
 static int battery_bix_broken_package;
 static int battery_notification_delay_ms;
 static unsigned int cache_time = 1000;
@@ -338,14 +339,6 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
-#ifdef CONFIG_ACPI_PROCFS_POWER
-inline char *acpi_battery_units(struct acpi_battery *battery)
-{
-	return (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) ?
-		"mA" : "mW";
-}
-#endif
-
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -354,14 +347,14 @@ struct acpi_offsets {
 	u8 mode;		/* int or string? */
 };
 
-static struct acpi_offsets state_offsets[] = {
+static const struct acpi_offsets state_offsets[] = {
 	{offsetof(struct acpi_battery, state), 0},
 	{offsetof(struct acpi_battery, rate_now), 0},
 	{offsetof(struct acpi_battery, capacity_now), 0},
 	{offsetof(struct acpi_battery, voltage_now), 0},
 };
 
-static struct acpi_offsets info_offsets[] = {
+static const struct acpi_offsets info_offsets[] = {
 	{offsetof(struct acpi_battery, power_unit), 0},
 	{offsetof(struct acpi_battery, design_capacity), 0},
 	{offsetof(struct acpi_battery, full_charge_capacity), 0},
@@ -377,7 +370,7 @@ static struct acpi_offsets info_offsets[] = {
 	{offsetof(struct acpi_battery, oem_info), 1},
 };
 
-static struct acpi_offsets extended_info_offsets[] = {
+static const struct acpi_offsets extended_info_offsets[] = {
 	{offsetof(struct acpi_battery, revision), 0},
 	{offsetof(struct acpi_battery, power_unit), 0},
 	{offsetof(struct acpi_battery, design_capacity), 0},
@@ -402,7 +395,7 @@ static struct acpi_offsets extended_info_offsets[] = {
 
 static int extract_package(struct acpi_battery *battery,
 			   union acpi_object *package,
-			   struct acpi_offsets *offsets, int num)
+			   const struct acpi_offsets *offsets, int num)
 {
 	int i;
 	union acpi_object *element;
@@ -792,6 +785,12 @@ static void acpi_battery_refresh(struct acpi_battery *battery)
 #ifdef CONFIG_ACPI_PROCFS_POWER
 static struct proc_dir_entry *acpi_battery_dir;
 
+static const char *acpi_battery_units(const struct acpi_battery *battery)
+{
+	return (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) ?
+		"mA" : "mW";
+}
+
 static int acpi_battery_print_info(struct seq_file *seq, int result)
 {
 	struct acpi_battery *battery = seq->private;
@@ -1125,19 +1124,21 @@ static int battery_notify(struct notifier_block *nb,
 	return 0;
 }
 
-static int battery_bix_broken_package_quirk(const struct dmi_system_id *d)
+static int __init
+battery_bix_broken_package_quirk(const struct dmi_system_id *d)
 {
 	battery_bix_broken_package = 1;
 	return 0;
 }
 
-static int battery_notification_delay_quirk(const struct dmi_system_id *d)
+static int __init
+battery_notification_delay_quirk(const struct dmi_system_id *d)
 {
 	battery_notification_delay_ms = 1000;
 	return 0;
 }
 
-static struct dmi_system_id bat_dmi_table[] = {
+static const struct dmi_system_id bat_dmi_table[] __initconst = {
 	{
 		.callback = battery_bix_broken_package_quirk,
 		.ident = "NEC LZ750/LS",
@@ -1292,33 +1293,34 @@ static struct acpi_driver acpi_battery_driver = {
 
 static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 {
-	if (acpi_disabled)
-		return;
+	int result;
 
 	dmi_check_system(bat_dmi_table);
-	
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_battery_dir = acpi_lock_battery_dir();
 	if (!acpi_battery_dir)
 		return;
 #endif
-	if (acpi_bus_register_driver(&acpi_battery_driver) < 0) {
+	result = acpi_bus_register_driver(&acpi_battery_driver);
 #ifdef CONFIG_ACPI_PROCFS_POWER
+	if (result < 0)
 		acpi_unlock_battery_dir(acpi_battery_dir);
 #endif
-		return;
-	}
-	return;
 }
 
 static int __init acpi_battery_init(void)
 {
-	async_schedule(acpi_battery_init_async, NULL);
+	if (acpi_disabled)
+		return -ENODEV;
+
+	async_cookie = async_schedule(acpi_battery_init_async, NULL);
 	return 0;
 }
 
 static void __exit acpi_battery_exit(void)
 {
+	async_synchronize_cookie(async_cookie);
 	acpi_bus_unregister_driver(&acpi_battery_driver);
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_unlock_battery_dir(acpi_battery_dir);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index c412fdb28d34..513e7230e3d0 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -470,6 +470,16 @@ static int __init acpi_bus_init_irq(void)
 	return 0;
 }
 
+/**
+ * acpi_early_init - Initialize ACPICA and populate the ACPI namespace.
+ *
+ * The ACPI tables are accessible after this, but the handling of events has not
+ * been initialized and the global lock is not available yet, so AML should not
+ * be executed at this point.
+ *
+ * Doing this before switching the EFI runtime services to virtual mode allows
+ * the EfiBootServices memory to be freed slightly earlier on boot.
+ */
 void __init acpi_early_init(void)
 {
 	acpi_status status;
@@ -533,26 +543,42 @@ void __init acpi_early_init(void)
 		acpi_gbl_FADT.sci_interrupt = acpi_sci_override_gsi;
 	}
 #endif
+	return;
+
+ error0:
+	disable_acpi();
+}
+
+/**
+ * acpi_subsystem_init - Finalize the early initialization of ACPI.
+ *
+ * Switch over the platform to the ACPI mode (if possible), initialize the
+ * handling of ACPI events, install the interrupt and global lock handlers.
+ *
+ * Doing this too early is generally unsafe, but at the same time it needs to be
+ * done before all things that really depend on ACPI.  The right spot appears to
+ * be before finalizing the EFI initialization.
+ */
+void __init acpi_subsystem_init(void)
+{
+	acpi_status status;
+
+	if (acpi_disabled)
+		return;
 
 	status = acpi_enable_subsystem(~ACPI_NO_ACPI_ENABLE);
 	if (ACPI_FAILURE(status)) {
 		printk(KERN_ERR PREFIX "Unable to enable ACPI\n");
-		goto error0;
+		disable_acpi();
+	} else {
+		/*
+		 * If the system is using ACPI then we can be reasonably
+		 * confident that any regulators are managed by the firmware
+		 * so tell the regulator core it has everything it needs to
+		 * know.
+		 */
+		regulator_has_full_constraints();
 	}
-
-	/*
-	 * If the system is using ACPI then we can be reasonably
-	 * confident that any regulators are managed by the firmware
-	 * so tell the regulator core it has everything it needs to
-	 * know.
-	 */
-	regulator_has_full_constraints();
-
-	return;
-
-      error0:
-	disable_acpi();
-	return;
 }
 
 static int __init acpi_bus_init(void)
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 735db11a9b00..717afcdb5f4a 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -98,17 +98,16 @@ int acpi_device_get_power(struct acpi_device *device, int *state)
 
 		/*
 		 * The power resources settings may indicate a power state
-		 * shallower than the actual power state of the device.
+		 * shallower than the actual power state of the device, because
+		 * the same power resources may be referenced by other devices.
 		 *
-		 * Moreover, on systems predating ACPI 4.0, if the device
-		 * doesn't depend on any power resources and _PSC returns 3,
-		 * that means "power off".  We need to maintain compatibility
-		 * with those systems.
+		 * For systems predating ACPI 4.0 we assume that D3hot is the
+		 * deepest state that can be supported.
 		 */
 		if (psc > result && psc < ACPI_STATE_D3_COLD)
 			result = psc;
 		else if (result == ACPI_STATE_UNKNOWN)
-			result = psc > ACPI_STATE_D2 ? ACPI_STATE_D3_COLD : psc;
+			result = psc > ACPI_STATE_D2 ? ACPI_STATE_D3_HOT : psc;
 	}
 
 	/*
@@ -153,8 +152,8 @@ static int acpi_dev_pm_explicit_set(struct acpi_device *adev, int state)
  */
 int acpi_device_set_power(struct acpi_device *device, int state)
 {
+	int target_state = state;
 	int result = 0;
-	bool cut_power = false;
 
 	if (!device || !device->flags.power_manageable
 	    || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
@@ -169,11 +168,21 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		return 0;
 	}
 
-	if (!device->power.states[state].flags.valid) {
+	if (state == ACPI_STATE_D3_COLD) {
+		/*
+		 * For transitions to D3cold we need to execute _PS3 and then
+		 * possibly drop references to the power resources in use.
+		 */
+		state = ACPI_STATE_D3_HOT;
+		/* If _PR3 is not available, use D3hot as the target state. */
+		if (!device->power.states[ACPI_STATE_D3_COLD].flags.valid)
+			target_state = state;
+	} else if (!device->power.states[state].flags.valid) {
 		dev_warn(&device->dev, "Power state %s not supported\n",
 			 acpi_power_state_string(state));
 		return -ENODEV;
 	}
+
 	if (!device->power.flags.ignore_parent &&
 	    device->parent && (state < device->parent->power.state)) {
 		dev_warn(&device->dev,
@@ -183,39 +192,38 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		return -ENODEV;
 	}
 
-	/* For D3cold we should first transition into D3hot. */
-	if (state == ACPI_STATE_D3_COLD
-	    && device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible) {
-		state = ACPI_STATE_D3_HOT;
-		cut_power = true;
-	}
-
-	if (state < device->power.state && state != ACPI_STATE_D0
-	    && device->power.state >= ACPI_STATE_D3_HOT) {
-		dev_warn(&device->dev,
-			 "Cannot transition to non-D0 state from D3\n");
-		return -ENODEV;
-	}
-
 	/*
 	 * Transition Power
 	 * ----------------
-	 * In accordance with the ACPI specification first apply power (via
-	 * power resources) and then evaluate _PSx.
+	 * In accordance with ACPI 6, _PSx is executed before manipulating power
+	 * resources, unless the target state is D0, in which case _PS0 is
+	 * supposed to be executed after turning the power resources on.
 	 */
-	if (device->power.flags.power_resources) {
-		result = acpi_power_transition(device, state);
+	if (state > ACPI_STATE_D0) {
+		/*
+		 * According to ACPI 6, devices cannot go from lower-power
+		 * (deeper) states to higher-power (shallower) states.
+		 */
+		if (state < device->power.state) {
+			dev_warn(&device->dev, "Cannot transition from %s to %s\n",
+				 acpi_power_state_string(device->power.state),
+				 acpi_power_state_string(state));
+			return -ENODEV;
+		}
+
+		result = acpi_dev_pm_explicit_set(device, state);
 		if (result)
 			goto end;
-	}
-	result = acpi_dev_pm_explicit_set(device, state);
-	if (result)
-		goto end;
 
-	if (cut_power) {
-		device->power.state = state;
-		state = ACPI_STATE_D3_COLD;
-		result = acpi_power_transition(device, state);
+		if (device->power.flags.power_resources)
+			result = acpi_power_transition(device, target_state);
+	} else {
+		if (device->power.flags.power_resources) {
+			result = acpi_power_transition(device, ACPI_STATE_D0);
+			if (result)
+				goto end;
+		}
+		result = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0);
 	}
 
  end:
@@ -264,13 +272,24 @@ int acpi_bus_init_power(struct acpi_device *device)
 		return result;
 
 	if (state < ACPI_STATE_D3_COLD && device->power.flags.power_resources) {
+		/* Reference count the power resources. */
 		result = acpi_power_on_resources(device, state);
 		if (result)
 			return result;
 
-		result = acpi_dev_pm_explicit_set(device, state);
-		if (result)
-			return result;
+		if (state == ACPI_STATE_D0) {
+			/*
+			 * If _PSC is not present and the state inferred from
+			 * power resources appears to be D0, it still may be
+			 * necessary to execute _PS0 at this point, because
+			 * another device using the same power resources may
+			 * have been put into D0 previously and that's why we
+			 * see D0 here.
+			 */
+			result = acpi_dev_pm_explicit_set(device, state);
+			if (result)
+				return result;
+		}
 	} else if (state == ACPI_STATE_UNKNOWN) {
 		/*
 		 * No power resources and missing _PSC?  Cross fingers and make
@@ -603,12 +622,12 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p, int d_max_in)
 	if (d_max_in < ACPI_STATE_D0 || d_max_in > ACPI_STATE_D3_COLD)
 		return -EINVAL;
 
-	if (d_max_in > ACPI_STATE_D3_HOT) {
+	if (d_max_in > ACPI_STATE_D2) {
 		enum pm_qos_flags_status stat;
 
 		stat = dev_pm_qos_flags(dev, PM_QOS_FLAG_NO_POWER_OFF);
 		if (stat == PM_QOS_FLAGS_ALL)
-			d_max_in = ACPI_STATE_D3_HOT;
+			d_max_in = ACPI_STATE_D2;
 	}
 
 	adev = ACPI_COMPANION(dev);
@@ -953,6 +972,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_prepare);
  */
 void acpi_subsys_complete(struct device *dev)
 {
+	pm_generic_complete(dev);
 	/*
 	 * If the device had been runtime-suspended before the system went into
 	 * the sleep state it is going out of and it has never been resumed till
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 5e8fed448850..9d4761d2f6b7 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -59,6 +59,38 @@
 #define ACPI_EC_FLAG_BURST	0x10	/* burst mode */
 #define ACPI_EC_FLAG_SCI	0x20	/* EC-SCI occurred */
 
+/*
+ * The SCI_EVT clearing timing is not defined by the ACPI specification.
+ * This leads to lots of practical timing issues for the host EC driver.
+ * The following variations are defined (from the target EC firmware's
+ * perspective):
+ * STATUS: After indicating SCI_EVT edge triggered IRQ to the host, the
+ *         target can clear SCI_EVT at any time so long as the host can see
+ *         the indication by reading the status register (EC_SC). So the
+ *         host should re-check SCI_EVT after the first time the SCI_EVT
+ *         indication is seen, which is the same time the query request
+ *         (QR_EC) is written to the command register (EC_CMD). SCI_EVT set
+ *         at any later time could indicate another event. Normally such
+ *         kind of EC firmware has implemented an event queue and will
+ *         return 0x00 to indicate "no outstanding event".
+ * QUERY: After seeing the query request (QR_EC) written to the command
+ *        register (EC_CMD) by the host and having prepared the responding
+ *        event value in the data register (EC_DATA), the target can safely
+ *        clear SCI_EVT because the target can confirm that the current
+ *        event is being handled by the host. The host then should check
+ *        SCI_EVT right after reading the event response from the data
+ *        register (EC_DATA).
+ * EVENT: After seeing the event response read from the data register
+ *        (EC_DATA) by the host, the target can clear SCI_EVT. As the
+ *        target requires time to notice the change in the data register
+ *        (EC_DATA), the host may be required to wait additional guarding
+ *        time before checking the SCI_EVT again. Such guarding may not be
+ *        necessary if the host is notified via another IRQ.
+ */
+#define ACPI_EC_EVT_TIMING_STATUS	0x00
+#define ACPI_EC_EVT_TIMING_QUERY	0x01
+#define ACPI_EC_EVT_TIMING_EVENT	0x02
+
 /* EC commands */
 enum ec_command {
 	ACPI_EC_COMMAND_READ = 0x80,
@@ -70,13 +102,13 @@ enum ec_command {
 
 #define ACPI_EC_DELAY		500	/* Wait 500ms max. during EC ops */
 #define ACPI_EC_UDELAY_GLK	1000	/* Wait 1ms max. to get global lock */
-#define ACPI_EC_MSI_UDELAY	550	/* Wait 550us for MSI EC */
-#define ACPI_EC_UDELAY_POLL	1000	/* Wait 1ms for EC transaction polling */
+#define ACPI_EC_UDELAY_POLL	550	/* Wait 1ms for EC transaction polling */
 #define ACPI_EC_CLEAR_MAX	100	/* Maximum number of events to query
 					 * when trying to clear the EC */
 
 enum {
 	EC_FLAGS_QUERY_PENDING,		/* Query is pending */
+	EC_FLAGS_QUERY_GUARDING,	/* Guard for SCI_EVT check */
 	EC_FLAGS_HANDLERS_INSTALLED,	/* Handlers for GPE and
 					 * OpReg are installed */
 	EC_FLAGS_STARTED,		/* Driver is started */
@@ -93,6 +125,16 @@ static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY;
 module_param(ec_delay, uint, 0644);
 MODULE_PARM_DESC(ec_delay, "Timeout(ms) waited until an EC command completes");
 
+static bool ec_busy_polling __read_mostly;
+module_param(ec_busy_polling, bool, 0644);
+MODULE_PARM_DESC(ec_busy_polling, "Use busy polling to advance EC transaction");
+
+static unsigned int ec_polling_guard __read_mostly = ACPI_EC_UDELAY_POLL;
+module_param(ec_polling_guard, uint, 0644);
+MODULE_PARM_DESC(ec_polling_guard, "Guard time(us) between EC accesses in polling modes");
+
+static unsigned int ec_event_clearing __read_mostly = ACPI_EC_EVT_TIMING_QUERY;
+
 /*
  * If the number of false interrupts per one transaction exceeds
  * this threshold, will think there is a GPE storm happened and
@@ -121,7 +163,6 @@ struct transaction {
 	u8 wlen;
 	u8 rlen;
 	u8 flags;
-	unsigned long timestamp;
 };
 
 static int acpi_ec_query(struct acpi_ec *ec, u8 *data);
@@ -130,7 +171,6 @@ static void advance_transaction(struct acpi_ec *ec);
 struct acpi_ec *boot_ec, *first_ec;
 EXPORT_SYMBOL(first_ec);
 
-static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */
 static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
 static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
 static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
@@ -218,7 +258,7 @@ static inline u8 acpi_ec_read_data(struct acpi_ec *ec)
 {
 	u8 x = inb(ec->data_addr);
 
-	ec->curr->timestamp = jiffies;
+	ec->timestamp = jiffies;
 	ec_dbg_raw("EC_DATA(R) = 0x%2.2x", x);
 	return x;
 }
@@ -227,14 +267,14 @@ static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command)
 {
 	ec_dbg_raw("EC_SC(W) = 0x%2.2x", command);
 	outb(command, ec->command_addr);
-	ec->curr->timestamp = jiffies;
+	ec->timestamp = jiffies;
 }
 
 static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data)
 {
 	ec_dbg_raw("EC_DATA(W) = 0x%2.2x", data);
 	outb(data, ec->data_addr);
-	ec->curr->timestamp = jiffies;
+	ec->timestamp = jiffies;
 }
 
 #ifdef DEBUG
@@ -267,7 +307,7 @@ static inline bool acpi_ec_is_gpe_raised(struct acpi_ec *ec)
 	acpi_event_status gpe_status = 0;
 
 	(void)acpi_get_gpe_status(NULL, ec->gpe, &gpe_status);
-	return (gpe_status & ACPI_EVENT_FLAG_SET) ? true : false;
+	return (gpe_status & ACPI_EVENT_FLAG_STATUS_SET) ? true : false;
 }
 
 static inline void acpi_ec_enable_gpe(struct acpi_ec *ec, bool open)
@@ -379,19 +419,49 @@ static bool acpi_ec_submit_flushable_request(struct acpi_ec *ec)
 static void acpi_ec_submit_query(struct acpi_ec *ec)
 {
 	if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) {
-		ec_dbg_req("Event started");
+		ec_dbg_evt("Command(%s) submitted/blocked",
+			   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
+		ec->nr_pending_queries++;
 		schedule_work(&ec->work);
 	}
 }
 
 static void acpi_ec_complete_query(struct acpi_ec *ec)
 {
-	if (ec->curr->command == ACPI_EC_COMMAND_QUERY) {
+	if (test_bit(EC_FLAGS_QUERY_PENDING, &ec->flags)) {
 		clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags);
-		ec_dbg_req("Event stopped");
+		ec_dbg_evt("Command(%s) unblocked",
+			   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
 	}
 }
 
+static bool acpi_ec_guard_event(struct acpi_ec *ec)
+{
+	if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS ||
+	    ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY ||
+	    !test_bit(EC_FLAGS_QUERY_PENDING, &ec->flags) ||
+	    (ec->curr && ec->curr->command == ACPI_EC_COMMAND_QUERY))
+		return false;
+
+	/*
+	 * Postpone the query submission to allow the firmware to proceed,
+	 * we shouldn't check SCI_EVT before the firmware reflagging it.
+	 */
+	return true;
+}
+
+static int ec_transaction_polled(struct acpi_ec *ec)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&ec->lock, flags);
+	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_POLL))
+		ret = 1;
+	spin_unlock_irqrestore(&ec->lock, flags);
+	return ret;
+}
+
 static int ec_transaction_completed(struct acpi_ec *ec)
 {
 	unsigned long flags;
@@ -404,6 +474,22 @@ static int ec_transaction_completed(struct acpi_ec *ec)
 	return ret;
 }
 
+static inline void ec_transaction_transition(struct acpi_ec *ec, unsigned long flag)
+{
+	ec->curr->flags |= flag;
+	if (ec->curr->command == ACPI_EC_COMMAND_QUERY) {
+		if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS &&
+		    flag == ACPI_EC_COMMAND_POLL)
+			acpi_ec_complete_query(ec);
+		if (ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY &&
+		    flag == ACPI_EC_COMMAND_COMPLETE)
+			acpi_ec_complete_query(ec);
+		if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT &&
+		    flag == ACPI_EC_COMMAND_COMPLETE)
+			set_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags);
+	}
+}
+
 static void advance_transaction(struct acpi_ec *ec)
 {
 	struct transaction *t;
@@ -420,6 +506,18 @@ static void advance_transaction(struct acpi_ec *ec)
 	acpi_ec_clear_gpe(ec);
 	status = acpi_ec_read_status(ec);
 	t = ec->curr;
+	/*
+	 * Another IRQ or a guarded polling mode advancement is detected,
+	 * the next QR_EC submission is then allowed.
+	 */
+	if (!t || !(t->flags & ACPI_EC_COMMAND_POLL)) {
+		if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT &&
+		    (!ec->nr_pending_queries ||
+		     test_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags))) {
+			clear_bit(EC_FLAGS_QUERY_GUARDING, &ec->flags);
+			acpi_ec_complete_query(ec);
+		}
+	}
 	if (!t)
 		goto err;
 	if (t->flags & ACPI_EC_COMMAND_POLL) {
@@ -432,17 +530,17 @@ static void advance_transaction(struct acpi_ec *ec)
 			if ((status & ACPI_EC_FLAG_OBF) == 1) {
 				t->rdata[t->ri++] = acpi_ec_read_data(ec);
 				if (t->rlen == t->ri) {
-					t->flags |= ACPI_EC_COMMAND_COMPLETE;
+					ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE);
 					if (t->command == ACPI_EC_COMMAND_QUERY)
-						ec_dbg_req("Command(%s) hardware completion",
-							   acpi_ec_cmd_string(t->command));
+						ec_dbg_evt("Command(%s) completed by hardware",
+							   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
 					wakeup = true;
 				}
 			} else
 				goto err;
 		} else if (t->wlen == t->wi &&
 			   (status & ACPI_EC_FLAG_IBF) == 0) {
-			t->flags |= ACPI_EC_COMMAND_COMPLETE;
+			ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE);
 			wakeup = true;
 		}
 		goto out;
@@ -450,17 +548,15 @@ static void advance_transaction(struct acpi_ec *ec)
 		if (EC_FLAGS_QUERY_HANDSHAKE &&
 		    !(status & ACPI_EC_FLAG_SCI) &&
 		    (t->command == ACPI_EC_COMMAND_QUERY)) {
-			t->flags |= ACPI_EC_COMMAND_POLL;
-			acpi_ec_complete_query(ec);
+			ec_transaction_transition(ec, ACPI_EC_COMMAND_POLL);
 			t->rdata[t->ri++] = 0x00;
-			t->flags |= ACPI_EC_COMMAND_COMPLETE;
-			ec_dbg_req("Command(%s) software completion",
-				   acpi_ec_cmd_string(t->command));
+			ec_transaction_transition(ec, ACPI_EC_COMMAND_COMPLETE);
+			ec_dbg_evt("Command(%s) completed by software",
+				   acpi_ec_cmd_string(ACPI_EC_COMMAND_QUERY));
 			wakeup = true;
 		} else if ((status & ACPI_EC_FLAG_IBF) == 0) {
 			acpi_ec_write_cmd(ec, t->command);
-			t->flags |= ACPI_EC_COMMAND_POLL;
-			acpi_ec_complete_query(ec);
+			ec_transaction_transition(ec, ACPI_EC_COMMAND_POLL);
 		} else
 			goto err;
 		goto out;
@@ -490,8 +586,39 @@ static void start_transaction(struct acpi_ec *ec)
 {
 	ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0;
 	ec->curr->flags = 0;
-	ec->curr->timestamp = jiffies;
-	advance_transaction(ec);
+}
+
+static int ec_guard(struct acpi_ec *ec)
+{
+	unsigned long guard = usecs_to_jiffies(ec_polling_guard);
+	unsigned long timeout = ec->timestamp + guard;
+
+	do {
+		if (ec_busy_polling) {
+			/* Perform busy polling */
+			if (ec_transaction_completed(ec))
+				return 0;
+			udelay(jiffies_to_usecs(guard));
+		} else {
+			/*
+			 * Perform wait polling
+			 *
+			 * For SCI_EVT clearing timing of "event",
+			 * performing guarding before re-checking the
+			 * SCI_EVT. Otherwise, such guarding is not needed
+			 * due to the old practices.
+			 */
+			if (!ec_transaction_polled(ec) &&
+			    !acpi_ec_guard_event(ec))
+				break;
+			if (wait_event_timeout(ec->wait,
+					       ec_transaction_completed(ec),
+					       guard))
+				return 0;
+		}
+		/* Guard the register accesses for the polling modes */
+	} while (time_before(jiffies, timeout));
+	return -ETIME;
 }
 
 static int ec_poll(struct acpi_ec *ec)
@@ -502,25 +629,11 @@ static int ec_poll(struct acpi_ec *ec)
 	while (repeat--) {
 		unsigned long delay = jiffies +
 			msecs_to_jiffies(ec_delay);
-		unsigned long usecs = ACPI_EC_UDELAY_POLL;
 		do {
-			/* don't sleep with disabled interrupts */
-			if (EC_FLAGS_MSI || irqs_disabled()) {
-				usecs = ACPI_EC_MSI_UDELAY;
-				udelay(usecs);
-				if (ec_transaction_completed(ec))
-					return 0;
-			} else {
-				if (wait_event_timeout(ec->wait,
-						ec_transaction_completed(ec),
-						usecs_to_jiffies(usecs)))
-					return 0;
-			}
+			if (!ec_guard(ec))
+				return 0;
 			spin_lock_irqsave(&ec->lock, flags);
-			if (time_after(jiffies,
-					ec->curr->timestamp +
-					usecs_to_jiffies(usecs)))
-				advance_transaction(ec);
+			advance_transaction(ec);
 			spin_unlock_irqrestore(&ec->lock, flags);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
@@ -537,8 +650,6 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	unsigned long tmp;
 	int ret = 0;
 
-	if (EC_FLAGS_MSI)
-		udelay(ACPI_EC_MSI_UDELAY);
 	/* start transaction */
 	spin_lock_irqsave(&ec->lock, tmp);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */
@@ -552,7 +663,9 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	ec_dbg_req("Command(%s) started", acpi_ec_cmd_string(t->command));
 	start_transaction(ec);
 	spin_unlock_irqrestore(&ec->lock, tmp);
+
 	ret = ec_poll(ec);
+
 	spin_lock_irqsave(&ec->lock, tmp);
 	if (t->irq_count == ec_storm_threshold)
 		acpi_ec_clear_storm(ec, EC_FLAGS_COMMAND_STORM);
@@ -575,6 +688,7 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 		return -EINVAL;
 	if (t->rdata)
 		memset(t->rdata, 0, t->rlen);
+
 	mutex_lock(&ec->mutex);
 	if (ec->global_lock) {
 		status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
@@ -586,8 +700,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 
 	status = acpi_ec_transaction_unlocked(ec, t);
 
-	if (test_bit(EC_FLAGS_COMMAND_STORM, &ec->flags))
-		msleep(1);
 	if (ec->global_lock)
 		acpi_release_global_lock(glk);
 unlock:
@@ -923,11 +1035,54 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
 	return result;
 }
 
-static void acpi_ec_gpe_poller(struct work_struct *work)
+static void acpi_ec_check_event(struct acpi_ec *ec)
 {
+	unsigned long flags;
+
+	if (ec_event_clearing == ACPI_EC_EVT_TIMING_EVENT) {
+		if (ec_guard(ec)) {
+			spin_lock_irqsave(&ec->lock, flags);
+			/*
+			 * Take care of the SCI_EVT unless no one else is
+			 * taking care of it.
+			 */
+			if (!ec->curr)
+				advance_transaction(ec);
+			spin_unlock_irqrestore(&ec->lock, flags);
+		}
+	}
+}
+
+static void acpi_ec_event_handler(struct work_struct *work)
+{
+	unsigned long flags;
 	struct acpi_ec *ec = container_of(work, struct acpi_ec, work);
 
-	acpi_ec_query(ec, NULL);
+	ec_dbg_evt("Event started");
+
+	spin_lock_irqsave(&ec->lock, flags);
+	while (ec->nr_pending_queries) {
+		spin_unlock_irqrestore(&ec->lock, flags);
+		(void)acpi_ec_query(ec, NULL);
+		spin_lock_irqsave(&ec->lock, flags);
+		ec->nr_pending_queries--;
+		/*
+		 * Before exit, make sure that this work item can be
+		 * scheduled again. There might be QR_EC failures, leaving
+		 * EC_FLAGS_QUERY_PENDING uncleared and preventing this work
+		 * item from being scheduled again.
+		 */
+		if (!ec->nr_pending_queries) {
+			if (ec_event_clearing == ACPI_EC_EVT_TIMING_STATUS ||
+			    ec_event_clearing == ACPI_EC_EVT_TIMING_QUERY)
+				acpi_ec_complete_query(ec);
+		}
+	}
+	spin_unlock_irqrestore(&ec->lock, flags);
+
+	ec_dbg_evt("Event stopped");
+
+	acpi_ec_check_event(ec);
 }
 
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
@@ -961,7 +1116,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (function != ACPI_READ && function != ACPI_WRITE)
 		return AE_BAD_PARAMETER;
 
-	if (EC_FLAGS_MSI || bits > 8)
+	if (ec_busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);
 
 	for (i = 0; i < bytes; ++i, ++address, ++value)
@@ -969,7 +1124,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 			acpi_ec_read(ec, address, value) :
 			acpi_ec_write(ec, address, *value);
 
-	if (EC_FLAGS_MSI || bits > 8)
+	if (ec_busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
 
 	switch (result) {
@@ -1002,7 +1157,8 @@ static struct acpi_ec *make_acpi_ec(void)
 	init_waitqueue_head(&ec->wait);
 	INIT_LIST_HEAD(&ec->list);
 	spin_lock_init(&ec->lock);
-	INIT_WORK(&ec->work, acpi_ec_gpe_poller);
+	INIT_WORK(&ec->work, acpi_ec_event_handler);
+	ec->timestamp = jiffies;
 	return ec;
 }
 
@@ -1237,30 +1393,13 @@ static int ec_validate_ecdt(const struct dmi_system_id *id)
 	return 0;
 }
 
-/* MSI EC needs special treatment, enable it */
-static int ec_flag_msi(const struct dmi_system_id *id)
-{
-	pr_debug("Detected MSI hardware, enabling workarounds.\n");
-	EC_FLAGS_MSI = 1;
-	EC_FLAGS_VALIDATE_ECDT = 1;
-	return 0;
-}
-
-/*
- * Clevo M720 notebook actually works ok with IRQ mode, if we lifted
- * the GPE storm threshold back to 20
- */
-static int ec_enlarge_storm_threshold(const struct dmi_system_id *id)
-{
-	pr_debug("Setting the EC GPE storm threshold to 20\n");
-	ec_storm_threshold  = 20;
-	return 0;
-}
-
+#if 0
 /*
- * Acer EC firmware refuses to respond QR_EC when SCI_EVT is not set, for
- * which case, we complete the QR_EC without issuing it to the firmware.
- * https://bugzilla.kernel.org/show_bug.cgi?id=86211
+ * Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not
+ * set, for which case, we complete the QR_EC without issuing it to the
+ * firmware.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=82611
+ * https://bugzilla.kernel.org/show_bug.cgi?id=97381
  */
 static int ec_flag_query_handshake(const struct dmi_system_id *id)
 {
@@ -1268,6 +1407,7 @@ static int ec_flag_query_handshake(const struct dmi_system_id *id)
 	EC_FLAGS_QUERY_HANDSHAKE = 1;
 	return 0;
 }
+#endif
 
 /*
  * On some hardware it is necessary to clear events accumulated by the EC during
@@ -1290,6 +1430,7 @@ static int ec_clear_on_resume(const struct dmi_system_id *id)
 {
 	pr_debug("Detected system needing EC poll on resume.\n");
 	EC_FLAGS_CLEAR_ON_RESUME = 1;
+	ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS;
 	return 0;
 }
 
@@ -1299,29 +1440,9 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
 	DMI_MATCH(DMI_BIOS_VENDOR, "COMPAL"),
 	DMI_MATCH(DMI_BOARD_NAME, "JFL92") }, NULL},
 	{
-	ec_flag_msi, "MSI hardware", {
-	DMI_MATCH(DMI_BIOS_VENDOR, "Micro-Star")}, NULL},
-	{
-	ec_flag_msi, "MSI hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star")}, NULL},
-	{
-	ec_flag_msi, "MSI hardware", {
-	DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-Star")}, NULL},
-	{
-	ec_flag_msi, "MSI hardware", {
-	DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-STAR")}, NULL},
-	{
-	ec_flag_msi, "Quanta hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
-	DMI_MATCH(DMI_PRODUCT_NAME, "TW8/SW8/DW8"),}, NULL},
-	{
-	ec_flag_msi, "Quanta hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
-	DMI_MATCH(DMI_PRODUCT_NAME, "TW9/SW9"),}, NULL},
-	{
-	ec_flag_msi, "Clevo W350etq", {
-	DMI_MATCH(DMI_SYS_VENDOR, "CLEVO CO."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "W35_37ET"),}, NULL},
+	ec_validate_ecdt, "MSI MS-171F", {
+	DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"),
+	DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"),}, NULL},
 	{
 	ec_validate_ecdt, "ASUS hardware", {
 	DMI_MATCH(DMI_BIOS_VENDOR, "ASUS") }, NULL},
@@ -1329,10 +1450,6 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
 	ec_validate_ecdt, "ASUS hardware", {
 	DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc.") }, NULL},
 	{
-	ec_enlarge_storm_threshold, "CLEVO hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "CLEVO Co."),
-	DMI_MATCH(DMI_PRODUCT_NAME, "M720T/M730T"),}, NULL},
-	{
 	ec_skip_dsdt_scan, "HP Folio 13", {
 	DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
 	DMI_MATCH(DMI_PRODUCT_NAME, "HP Folio 13"),}, NULL},
@@ -1343,9 +1460,6 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
 	{
 	ec_clear_on_resume, "Samsung hardware", {
 	DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
-	{
-	ec_flag_query_handshake, "Acer hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "Acer"), }, NULL},
 	{},
 };
 
@@ -1427,6 +1541,43 @@ error:
 	return -ENODEV;
 }
 
+static int param_set_event_clearing(const char *val, struct kernel_param *kp)
+{
+	int result = 0;
+
+	if (!strncmp(val, "status", sizeof("status") - 1)) {
+		ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS;
+		pr_info("Assuming SCI_EVT clearing on EC_SC accesses\n");
+	} else if (!strncmp(val, "query", sizeof("query") - 1)) {
+		ec_event_clearing = ACPI_EC_EVT_TIMING_QUERY;
+		pr_info("Assuming SCI_EVT clearing on QR_EC writes\n");
+	} else if (!strncmp(val, "event", sizeof("event") - 1)) {
+		ec_event_clearing = ACPI_EC_EVT_TIMING_EVENT;
+		pr_info("Assuming SCI_EVT clearing on event reads\n");
+	} else
+		result = -EINVAL;
+	return result;
+}
+
+static int param_get_event_clearing(char *buffer, struct kernel_param *kp)
+{
+	switch (ec_event_clearing) {
+	case ACPI_EC_EVT_TIMING_STATUS:
+		return sprintf(buffer, "status");
+	case ACPI_EC_EVT_TIMING_QUERY:
+		return sprintf(buffer, "query");
+	case ACPI_EC_EVT_TIMING_EVENT:
+		return sprintf(buffer, "event");
+	default:
+		return sprintf(buffer, "invalid");
+	}
+	return 0;
+}
+
+module_param_call(ec_event_clearing, param_set_event_clearing, param_get_event_clearing,
+		  NULL, 0644);
+MODULE_PARM_DESC(ec_event_clearing, "Assumed SCI_EVT clearing timing");
+
 static struct acpi_driver acpi_ec_driver = {
 	.name = "ec",
 	.class = ACPI_EC_CLASS,
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 7a36f02598a6..bea0bbaafa97 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -158,8 +158,9 @@ static int fan_get_state(struct acpi_device *device, unsigned long *state)
 	if (result)
 		return result;
 
-	*state = (acpi_state == ACPI_STATE_D3_COLD ? 0 :
-		 (acpi_state == ACPI_STATE_D0 ? 1 : -1));
+	*state = acpi_state == ACPI_STATE_D3_COLD
+			|| acpi_state == ACPI_STATE_D3_HOT ?
+		0 : (acpi_state == ACPI_STATE_D0 ? 1 : -1);
 	return 0;
 }
 
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 39c485b0c25c..b9657af751d1 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/rwsem.h>
 #include <linux/acpi.h>
+#include <linux/dma-mapping.h>
 
 #include "internal.h"
 
@@ -167,6 +168,7 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 	struct list_head *physnode_list;
 	unsigned int node_id;
 	int retval = -EINVAL;
+	bool coherent;
 
 	if (has_acpi_companion(dev)) {
 		if (acpi_dev) {
@@ -223,6 +225,9 @@ int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev)
 	if (!has_acpi_companion(dev))
 		ACPI_COMPANION_SET(dev, acpi_dev);
 
+	if (acpi_check_dma(acpi_dev, &coherent))
+		arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+
 	acpi_physnode_link_name(physical_node_name, node_id);
 	retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
 				   physical_node_name);
diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c
index aafe3ca829c2..a322710b5ba4 100644
--- a/drivers/acpi/hed.c
+++ b/drivers/acpi/hed.c
@@ -27,7 +27,7 @@
 #include <linux/acpi.h>
 #include <acpi/hed.h>
 
-static struct acpi_device_id acpi_hed_ids[] = {
+static const struct acpi_device_id acpi_hed_ids[] = {
 	{"PNP0C33", 0},
 	{"", 0},
 };
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index ba4a61e964be..787c629bc9b4 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -138,6 +138,8 @@ struct acpi_ec {
 	struct transaction *curr;
 	spinlock_t lock;
 	struct work_struct work;
+	unsigned long timestamp;
+	unsigned long nr_pending_queries;
 };
 
 extern struct acpi_ec *first_ec;
@@ -182,15 +184,10 @@ static inline void suspend_nvs_restore(void) {}
 #endif
 
 /*--------------------------------------------------------------------------
-					Video
-  -------------------------------------------------------------------------- */
-#if defined(CONFIG_ACPI_VIDEO) || defined(CONFIG_ACPI_VIDEO_MODULE)
-bool acpi_osi_is_win8(void);
-#endif
-
-/*--------------------------------------------------------------------------
 				Device properties
   -------------------------------------------------------------------------- */
+#define ACPI_DT_NAMESPACE_HID	"PRP0001"
+
 void acpi_init_properties(struct acpi_device *adev);
 void acpi_free_properties(struct acpi_device *adev);
 
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 39748bb3a543..a5dc9034efee 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -175,14 +175,10 @@ static void __init acpi_request_region (struct acpi_generic_address *gas,
 	if (!addr || !length)
 		return;
 
-	/* Resources are never freed */
-	if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
-		request_region(addr, length, desc);
-	else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		request_mem_region(addr, length, desc);
+	acpi_reserve_region(addr, length, gas->space_id, 0, desc);
 }
 
-static int __init acpi_reserve_resources(void)
+static void __init acpi_reserve_resources(void)
 {
 	acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
 		"ACPI PM1a_EVT_BLK");
@@ -211,10 +207,7 @@ static int __init acpi_reserve_resources(void)
 	if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
 		acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
 			       acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
-
-	return 0;
 }
-device_initcall(acpi_reserve_resources);
 
 void acpi_os_printf(const char *fmt, ...)
 {
@@ -543,7 +536,7 @@ static char acpi_os_name[ACPI_MAX_OVERRIDE_LEN];
 
 acpi_status
 acpi_os_predefined_override(const struct acpi_predefined_names *init_val,
-			    acpi_string * new_val)
+			    char **new_val)
 {
 	if (!init_val || !new_val)
 		return AE_BAD_PARAMETER;
@@ -1687,6 +1680,12 @@ int acpi_resources_are_enforced(void)
 }
 EXPORT_SYMBOL(acpi_resources_are_enforced);
 
+bool acpi_osi_is_win8(void)
+{
+	return acpi_gbl_osi_data >= ACPI_OSI_WIN_8;
+}
+EXPORT_SYMBOL(acpi_osi_is_win8);
+
 /*
  * Deallocate the memory for a spinlock.
  */
@@ -1845,6 +1844,7 @@ acpi_status __init acpi_os_initialize(void)
 
 acpi_status __init acpi_os_initialize1(void)
 {
+	acpi_reserve_resources();
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
 	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index b1def411c0b8..304eccb0ae5c 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -44,7 +44,6 @@
 ACPI_MODULE_NAME("pci_irq");
 
 struct acpi_prt_entry {
-	struct list_head	list;
 	struct acpi_pci_id	id;
 	u8			pin;
 	acpi_handle		link;
@@ -163,7 +162,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev,
 {
 	int segment = pci_domain_nr(dev->bus);
 	int bus = dev->bus->number;
-	int device = PCI_SLOT(dev->devfn);
+	int device = pci_ari_enabled(dev->bus) ? 0 : PCI_SLOT(dev->devfn);
 	struct acpi_prt_entry *entry;
 
 	if (((prt->address >> 16) & 0xffff) != device ||
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index e0bcfb642b52..93eac53b5110 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -684,7 +684,8 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state)
 		}
 	}
 
-	*state = ACPI_STATE_D3_COLD;
+	*state = device->power.states[ACPI_STATE_D3_COLD].flags.valid ?
+		ACPI_STATE_D3_COLD : ACPI_STATE_D3_HOT;
 	return 0;
 }
 
@@ -710,8 +711,6 @@ int acpi_power_transition(struct acpi_device *device, int state)
 	    || (device->power.state > ACPI_STATE_D3_COLD))
 		return -ENODEV;
 
-	/* TBD: Resources must be ordered. */
-
 	/*
 	 * First we reference all power resources required in the target list
 	 * (e.g. so the device doesn't lose power while transitioning).  Then,
@@ -761,6 +760,25 @@ static void acpi_power_sysfs_remove(struct acpi_device *device)
 	device_remove_file(&device->dev, &dev_attr_resource_in_use);
 }
 
+static void acpi_power_add_resource_to_list(struct acpi_power_resource *resource)
+{
+	mutex_lock(&power_resource_list_lock);
+
+	if (!list_empty(&acpi_power_resource_list)) {
+		struct acpi_power_resource *r;
+
+		list_for_each_entry(r, &acpi_power_resource_list, list_node)
+			if (r->order > resource->order) {
+				list_add_tail(&resource->list_node, &r->list_node);
+				goto out;
+			}
+	}
+	list_add_tail(&resource->list_node, &acpi_power_resource_list);
+
+ out:
+	mutex_unlock(&power_resource_list_lock);
+}
+
 int acpi_add_power_resource(acpi_handle handle)
 {
 	struct acpi_power_resource *resource;
@@ -811,9 +829,7 @@ int acpi_add_power_resource(acpi_handle handle)
 	if (!device_create_file(&device->dev, &dev_attr_resource_in_use))
 		device->remove = acpi_power_sysfs_remove;
 
-	mutex_lock(&power_resource_list_lock);
-	list_add(&resource->list_node, &acpi_power_resource_list);
-	mutex_unlock(&power_resource_list_lock);
+	acpi_power_add_resource_to_list(resource);
 	acpi_device_add_finalize(device);
 	return 0;
 
@@ -844,7 +860,22 @@ void acpi_resume_power_resources(void)
 		    && resource->ref_count) {
 			dev_info(&resource->device.dev, "Turning ON\n");
 			__acpi_power_on(resource);
-		} else if (state == ACPI_POWER_RESOURCE_STATE_ON
+		}
+
+		mutex_unlock(&resource->resource_lock);
+	}
+	list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) {
+		int result, state;
+
+		mutex_lock(&resource->resource_lock);
+
+		result = acpi_power_get_state(resource->device.handle, &state);
+		if (result) {
+			mutex_unlock(&resource->resource_lock);
+			continue;
+		}
+
+		if (state == ACPI_POWER_RESOURCE_STATE_ON
 		    && !resource->ref_count) {
 			dev_info(&resource->device.dev, "Turning OFF\n");
 			__acpi_power_off(resource);
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index b1ec78b8a645..33a38d604630 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -184,7 +184,7 @@ phys_cpuid_t acpi_get_phys_id(acpi_handle handle, int type, u32 acpi_id)
 	phys_cpuid_t phys_id;
 
 	phys_id = map_mat_entry(handle, type, acpi_id);
-	if (phys_id == PHYS_CPUID_INVALID)
+	if (invalid_phys_cpuid(phys_id))
 		phys_id = map_madt_entry(type, acpi_id);
 
 	return phys_id;
@@ -196,7 +196,7 @@ int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id)
 	int i;
 #endif
 
-	if (phys_id == PHYS_CPUID_INVALID) {
+	if (invalid_phys_cpuid(phys_id)) {
 		/*
 		 * On UP processor, there is no _MAT or MADT table.
 		 * So above phys_id is always set to PHYS_CPUID_INVALID.
@@ -215,12 +215,12 @@ int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id)
 		 * Ignores phys_id and always returns 0 for the processor
 		 * handle with acpi id 0 if nr_cpu_ids is 1.
 		 * This should be the case if SMP tables are not found.
-		 * Return -1 for other CPU's handle.
+		 * Return -EINVAL for other CPU's handle.
 		 */
 		if (nr_cpu_ids <= 1 && acpi_id == 0)
 			return acpi_id;
 		else
-			return -1;
+			return -EINVAL;
 	}
 
 #ifdef CONFIG_SMP
@@ -233,7 +233,7 @@ int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id)
 	if (phys_id == 0)
 		return phys_id;
 #endif
-	return -1;
+	return -ENODEV;
 }
 
 int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 39e0c8e36244..d540f42c9232 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -94,7 +94,7 @@ static int set_max_cstate(const struct dmi_system_id *id)
 	return 0;
 }
 
-static struct dmi_system_id processor_power_dmi_table[] = {
+static const struct dmi_system_id processor_power_dmi_table[] = {
 	{ set_max_cstate, "Clevo 5600D", {
 	  DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"),
 	  DMI_MATCH(DMI_BIOS_VERSION,"SHE845M0.86C.0013.D.0302131307")},
diff --git a/drivers/acpi/processor_pdc.c b/drivers/acpi/processor_pdc.c
index e5dd80800930..7cfbda4d7c51 100644
--- a/drivers/acpi/processor_pdc.c
+++ b/drivers/acpi/processor_pdc.c
@@ -52,10 +52,7 @@ static bool __init processor_physically_present(acpi_handle handle)
 	type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
 	cpuid = acpi_get_cpuid(handle, type, acpi_id);
 
-	if (cpuid == -1)
-		return false;
-
-	return true;
+	return !invalid_logical_cpuid(cpuid);
 }
 
 static void acpi_set_pdc_bits(u32 *buf)
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 0d083736e25b..7836e2e980f4 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -79,50 +79,51 @@ static bool acpi_properties_format_valid(const union acpi_object *properties)
 static void acpi_init_of_compatible(struct acpi_device *adev)
 {
 	const union acpi_object *of_compatible;
-	struct acpi_hardware_id *hwid;
-	bool acpi_of = false;
 	int ret;
 
-	/*
-	 * Check if the special PRP0001 ACPI ID is present and in that
-	 * case we fill in Device Tree compatible properties for this
-	 * device.
-	 */
-	list_for_each_entry(hwid, &adev->pnp.ids, list) {
-		if (!strcmp(hwid->id, "PRP0001")) {
-			acpi_of = true;
-			break;
-		}
-	}
-
-	if (!acpi_of)
-		return;
-
 	ret = acpi_dev_get_property_array(adev, "compatible", ACPI_TYPE_STRING,
 					  &of_compatible);
 	if (ret) {
 		ret = acpi_dev_get_property(adev, "compatible",
 					    ACPI_TYPE_STRING, &of_compatible);
 		if (ret) {
-			acpi_handle_warn(adev->handle,
-					 "PRP0001 requires compatible property\n");
+			if (adev->parent
+			    && adev->parent->flags.of_compatible_ok)
+				goto out;
+
 			return;
 		}
 	}
 	adev->data.of_compatible = of_compatible;
+
+ out:
+	adev->flags.of_compatible_ok = 1;
 }
 
 void acpi_init_properties(struct acpi_device *adev)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
+	bool acpi_of = false;
+	struct acpi_hardware_id *hwid;
 	const union acpi_object *desc;
 	acpi_status status;
 	int i;
 
+	/*
+	 * Check if ACPI_DT_NAMESPACE_HID is present and inthat case we fill in
+	 * Device Tree compatible properties for this device.
+	 */
+	list_for_each_entry(hwid, &adev->pnp.ids, list) {
+		if (!strcmp(hwid->id, ACPI_DT_NAMESPACE_HID)) {
+			acpi_of = true;
+			break;
+		}
+	}
+
 	status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf,
 					    ACPI_TYPE_PACKAGE);
 	if (ACPI_FAILURE(status))
-		return;
+		goto out;
 
 	desc = buf.pointer;
 	if (desc->package.count % 2)
@@ -156,13 +157,20 @@ void acpi_init_properties(struct acpi_device *adev)
 		adev->data.pointer = buf.pointer;
 		adev->data.properties = properties;
 
-		acpi_init_of_compatible(adev);
-		return;
+		if (acpi_of)
+			acpi_init_of_compatible(adev);
+
+		goto out;
 	}
 
  fail:
-	dev_warn(&adev->dev, "Returned _DSD data is not valid, skipping\n");
+	dev_dbg(&adev->dev, "Returned _DSD data is not valid, skipping\n");
 	ACPI_FREE(buf.pointer);
+
+ out:
+	if (acpi_of && !adev->flags.of_compatible_ok)
+		acpi_handle_info(adev->handle,
+			 ACPI_DT_NAMESPACE_HID " requires 'compatible' property\n");
 }
 
 void acpi_free_properties(struct acpi_device *adev)
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 5589a6e2a023..fcb7807ea8b7 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -26,6 +26,7 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/ioport.h>
+#include <linux/list.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_X86
@@ -573,7 +574,7 @@ EXPORT_SYMBOL_GPL(acpi_dev_get_resources);
  * @ares: Input ACPI resource object.
  * @types: Valid resource types of IORESOURCE_XXX
  *
- * This is a hepler function to support acpi_dev_get_resources(), which filters
+ * This is a helper function to support acpi_dev_get_resources(), which filters
  * ACPI resource objects according to resource types.
  */
 int acpi_dev_filter_resource_type(struct acpi_resource *ares,
@@ -621,3 +622,162 @@ int acpi_dev_filter_resource_type(struct acpi_resource *ares,
 	return (type & types) ? 0 : 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
+
+struct reserved_region {
+	struct list_head node;
+	u64 start;
+	u64 end;
+};
+
+static LIST_HEAD(reserved_io_regions);
+static LIST_HEAD(reserved_mem_regions);
+
+static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags,
+			 char *desc)
+{
+	unsigned int length = end - start + 1;
+	struct resource *res;
+
+	res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ?
+		request_region(start, length, desc) :
+		request_mem_region(start, length, desc);
+	if (!res)
+		return -EIO;
+
+	res->flags &= ~flags;
+	return 0;
+}
+
+static int add_region_before(u64 start, u64 end, u8 space_id,
+			     unsigned long flags, char *desc,
+			     struct list_head *head)
+{
+	struct reserved_region *reg;
+	int error;
+
+	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
+	if (!reg)
+		return -ENOMEM;
+
+	error = request_range(start, end, space_id, flags, desc);
+	if (error)
+		return error;
+
+	reg->start = start;
+	reg->end = end;
+	list_add_tail(&reg->node, head);
+	return 0;
+}
+
+/**
+ * acpi_reserve_region - Reserve an I/O or memory region as a system resource.
+ * @start: Starting address of the region.
+ * @length: Length of the region.
+ * @space_id: Identifier of address space to reserve the region from.
+ * @flags: Resource flags to clear for the region after requesting it.
+ * @desc: Region description (for messages).
+ *
+ * Reserve an I/O or memory region as a system resource to prevent others from
+ * using it.  If the new region overlaps with one of the regions (in the given
+ * address space) already reserved by this routine, only the non-overlapping
+ * parts of it will be reserved.
+ *
+ * Returned is either 0 (success) or a negative error code indicating a resource
+ * reservation problem.  It is the code of the first encountered error, but the
+ * routine doesn't abort until it has attempted to request all of the parts of
+ * the new region that don't overlap with other regions reserved previously.
+ *
+ * The resources requested by this routine are never released.
+ */
+int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
+			unsigned long flags, char *desc)
+{
+	struct list_head *regions;
+	struct reserved_region *reg;
+	u64 end = start + length - 1;
+	int ret = 0, error = 0;
+
+	if (space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+		regions = &reserved_io_regions;
+	else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		regions = &reserved_mem_regions;
+	else
+		return -EINVAL;
+
+	if (list_empty(regions))
+		return add_region_before(start, end, space_id, flags, desc, regions);
+
+	list_for_each_entry(reg, regions, node)
+		if (reg->start == end + 1) {
+			/* The new region can be prepended to this one. */
+			ret = request_range(start, end, space_id, flags, desc);
+			if (!ret)
+				reg->start = start;
+
+			return ret;
+		} else if (reg->start > end) {
+			/* No overlap.  Add the new region here and get out. */
+			return add_region_before(start, end, space_id, flags,
+						 desc, &reg->node);
+		} else if (reg->end == start - 1) {
+			goto combine;
+		} else if (reg->end >= start) {
+			goto overlap;
+		}
+
+	/* The new region goes after the last existing one. */
+	return add_region_before(start, end, space_id, flags, desc, regions);
+
+ overlap:
+	/*
+	 * The new region overlaps an existing one.
+	 *
+	 * The head part of the new region immediately preceding the existing
+	 * overlapping one can be combined with it right away.
+	 */
+	if (reg->start > start) {
+		error = request_range(start, reg->start - 1, space_id, flags, desc);
+		if (error)
+			ret = error;
+		else
+			reg->start = start;
+	}
+
+ combine:
+	/*
+	 * The new region is adjacent to an existing one.  If it extends beyond
+	 * that region all the way to the next one, it is possible to combine
+	 * all three of them.
+	 */
+	while (reg->end < end) {
+		struct reserved_region *next = NULL;
+		u64 a = reg->end + 1, b = end;
+
+		if (!list_is_last(&reg->node, regions)) {
+			next = list_next_entry(reg, node);
+			if (next->start <= end)
+				b = next->start - 1;
+		}
+		error = request_range(a, b, space_id, flags, desc);
+		if (!error) {
+			if (next && next->start == b + 1) {
+				reg->end = next->end;
+				list_del(&next->node);
+				kfree(next);
+			} else {
+				reg->end = end;
+				break;
+			}
+		} else if (next) {
+			if (!ret)
+				ret = error;
+
+			reg = next;
+		} else {
+			break;
+		}
+	}
+
+	return ret ? ret : error;
+}
+EXPORT_SYMBOL_GPL(acpi_reserve_region);
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index 26e5b5060523..bf034f8b7c1a 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,6 +14,7 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/dmi.h>
 #include "sbshc.h"
 
 #define PREFIX "ACPI: "
@@ -87,6 +88,8 @@ enum acpi_smb_offset {
 	ACPI_SMB_ALARM_DATA = 0x26,	/* 2 bytes alarm data */
 };
 
+static bool macbook;
+
 static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
 {
 	return ec_read(hc->offset + address, data);
@@ -132,6 +135,8 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
 	}
 
 	mutex_lock(&hc->lock);
+	if (macbook)
+		udelay(5);
 	if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
 		goto end;
 	if (temp) {
@@ -257,12 +262,29 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 
+static int macbook_dmi_match(const struct dmi_system_id *d)
+{
+	pr_debug("Detected MacBook, enabling workaround\n");
+	macbook = true;
+	return 0;
+}
+
+static struct dmi_system_id acpi_smbus_dmi_table[] = {
+	{ macbook_dmi_match, "Apple MacBook", {
+	  DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
+	  DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
+	},
+	{ },
+};
+
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
 	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
+	dmi_check_system(acpi_smbus_dmi_table);
+
 	if (!device)
 		return -EINVAL;
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 03141aa4ea95..2649a068671d 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -11,6 +11,7 @@
 #include <linux/kthread.h>
 #include <linux/dmi.h>
 #include <linux/nls.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/pgtable.h>
 
@@ -135,12 +136,13 @@ static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
 	struct acpi_hardware_id *id;
 
 	/*
-	 * Since we skip PRP0001 from the modalias below, 0 should be returned
-	 * if PRP0001 is the only ACPI/PNP ID in the device's list.
+	 * Since we skip ACPI_DT_NAMESPACE_HID from the modalias below, 0 should
+	 * be returned if ACPI_DT_NAMESPACE_HID is the only ACPI/PNP ID in the
+	 * device's list.
 	 */
 	count = 0;
 	list_for_each_entry(id, &acpi_dev->pnp.ids, list)
-		if (strcmp(id->id, "PRP0001"))
+		if (strcmp(id->id, ACPI_DT_NAMESPACE_HID))
 			count++;
 
 	if (!count)
@@ -153,7 +155,7 @@ static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
 	size -= len;
 
 	list_for_each_entry(id, &acpi_dev->pnp.ids, list) {
-		if (!strcmp(id->id, "PRP0001"))
+		if (!strcmp(id->id, ACPI_DT_NAMESPACE_HID))
 			continue;
 
 		count = snprintf(&modalias[len], size, "%s:", id->id);
@@ -177,7 +179,8 @@ static int create_pnp_modalias(struct acpi_device *acpi_dev, char *modalias,
  * @size: Size of the buffer.
  *
  * Expose DT compatible modalias as of:NnameTCcompatible.  This function should
- * only be called for devices having PRP0001 in their list of ACPI/PNP IDs.
+ * only be called for devices having ACPI_DT_NAMESPACE_HID in their list of
+ * ACPI/PNP IDs.
  */
 static int create_of_modalias(struct acpi_device *acpi_dev, char *modalias,
 			      int size)
@@ -980,9 +983,9 @@ static void acpi_device_remove_files(struct acpi_device *dev)
  * @adev: ACPI device object to match.
  * @of_match_table: List of device IDs to match against.
  *
- * If @dev has an ACPI companion which has the special PRP0001 device ID in its
- * list of identifiers and a _DSD object with the "compatible" property, use
- * that property to match against the given list of identifiers.
+ * If @dev has an ACPI companion which has ACPI_DT_NAMESPACE_HID in its list of
+ * identifiers and a _DSD object with the "compatible" property, use that
+ * property to match against the given list of identifiers.
  */
 static bool acpi_of_match_device(struct acpi_device *adev,
 				 const struct of_device_id *of_match_table)
@@ -1038,14 +1041,14 @@ static const struct acpi_device_id *__acpi_match_device(
 				return id;
 
 		/*
-		 * Next, check the special "PRP0001" ID and try to match the
+		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
 		 * "compatible" property if found.
 		 *
 		 * The id returned by the below is not valid, but the only
 		 * caller passing non-NULL of_ids here is only interested in
 		 * whether or not the return value is NULL.
 		 */
-		if (!strcmp("PRP0001", hwid->id)
+		if (!strcmp(ACPI_DT_NAMESPACE_HID, hwid->id)
 		    && acpi_of_match_device(device, of_ids))
 			return id;
 	}
@@ -1671,7 +1674,7 @@ static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
 
 static void acpi_wakeup_gpe_init(struct acpi_device *device)
 {
-	struct acpi_device_id button_device_ids[] = {
+	static const struct acpi_device_id button_device_ids[] = {
 		{"PNP0C0C", 0},
 		{"PNP0C0D", 0},
 		{"PNP0C0E", 0},
@@ -1766,15 +1769,9 @@ static void acpi_bus_init_power_state(struct acpi_device *device, int state)
 	if (acpi_has_method(device->handle, pathname))
 		ps->flags.explicit_set = 1;
 
-	/*
-	 * State is valid if there are means to put the device into it.
-	 * D3hot is only valid if _PR3 present.
-	 */
-	if (!list_empty(&ps->resources)
-	    || (ps->flags.explicit_set && state < ACPI_STATE_D3_HOT)) {
+	/* State is valid if there are means to put the device into it. */
+	if (!list_empty(&ps->resources) || ps->flags.explicit_set)
 		ps->flags.valid = 1;
-		ps->flags.os_accessible = 1;
-	}
 
 	ps->power = -1;		/* Unknown - driver assigned */
 	ps->latency = -1;	/* Unknown - driver assigned */
@@ -1810,21 +1807,13 @@ static void acpi_bus_get_power_flags(struct acpi_device *device)
 		acpi_bus_init_power_state(device, i);
 
 	INIT_LIST_HEAD(&device->power.states[ACPI_STATE_D3_COLD].resources);
+	if (!list_empty(&device->power.states[ACPI_STATE_D3_HOT].resources))
+		device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
 
-	/* Set defaults for D0 and D3 states (always valid) */
+	/* Set defaults for D0 and D3hot states (always valid) */
 	device->power.states[ACPI_STATE_D0].flags.valid = 1;
 	device->power.states[ACPI_STATE_D0].power = 100;
-	device->power.states[ACPI_STATE_D3_COLD].flags.valid = 1;
-	device->power.states[ACPI_STATE_D3_COLD].power = 0;
-
-	/* Set D3cold's explicit_set flag if _PS3 exists. */
-	if (device->power.states[ACPI_STATE_D3_HOT].flags.explicit_set)
-		device->power.states[ACPI_STATE_D3_COLD].flags.explicit_set = 1;
-
-	/* Presence of _PS3 or _PRx means we can put the device into D3 cold */
-	if (device->power.states[ACPI_STATE_D3_HOT].flags.explicit_set ||
-			device->power.flags.power_resources)
-		device->power.states[ACPI_STATE_D3_COLD].flags.os_accessible = 1;
+	device->power.states[ACPI_STATE_D3_HOT].flags.valid = 1;
 
 	if (acpi_bus_init_power(device))
 		device->flags.power_manageable = 0;
@@ -1947,6 +1936,62 @@ bool acpi_dock_match(acpi_handle handle)
 	return acpi_has_method(handle, "_DCK");
 }
 
+static acpi_status
+acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
+			  void **return_value)
+{
+	long *cap = context;
+
+	if (acpi_has_method(handle, "_BCM") &&
+	    acpi_has_method(handle, "_BCL")) {
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight "
+				  "support\n"));
+		*cap |= ACPI_VIDEO_BACKLIGHT;
+		if (!acpi_has_method(handle, "_BQC"))
+			printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, "
+				"cannot determine initial brightness\n");
+		/* We have backlight support, no need to scan further */
+		return AE_CTRL_TERMINATE;
+	}
+	return 0;
+}
+
+/* Returns true if the ACPI object is a video device which can be
+ * handled by video.ko.
+ * The device will get a Linux specific CID added in scan.c to
+ * identify the device as an ACPI graphics device
+ * Be aware that the graphics device may not be physically present
+ * Use acpi_video_get_capabilities() to detect general ACPI video
+ * capabilities of present cards
+ */
+long acpi_is_video_device(acpi_handle handle)
+{
+	long video_caps = 0;
+
+	/* Is this device able to support video switching ? */
+	if (acpi_has_method(handle, "_DOD") || acpi_has_method(handle, "_DOS"))
+		video_caps |= ACPI_VIDEO_OUTPUT_SWITCHING;
+
+	/* Is this device able to retrieve a video ROM ? */
+	if (acpi_has_method(handle, "_ROM"))
+		video_caps |= ACPI_VIDEO_ROM_AVAILABLE;
+
+	/* Is this device able to configure which video head to be POSTed ? */
+	if (acpi_has_method(handle, "_VPO") &&
+	    acpi_has_method(handle, "_GPD") &&
+	    acpi_has_method(handle, "_SPD"))
+		video_caps |= ACPI_VIDEO_DEVICE_POSTING;
+
+	/* Only check for backlight functionality if one of the above hit. */
+	if (video_caps)
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
+				    ACPI_UINT32_MAX, acpi_backlight_cap_match, NULL,
+				    &video_caps, NULL);
+
+	return video_caps;
+}
+EXPORT_SYMBOL(acpi_is_video_device);
+
 const char *acpi_device_hid(struct acpi_device *device)
 {
 	struct acpi_hardware_id *hid;
@@ -2109,6 +2154,39 @@ void acpi_free_pnp_ids(struct acpi_device_pnp *pnp)
 	kfree(pnp->unique_id);
 }
 
+static void acpi_init_coherency(struct acpi_device *adev)
+{
+	unsigned long long cca = 0;
+	acpi_status status;
+	struct acpi_device *parent = adev->parent;
+
+	if (parent && parent->flags.cca_seen) {
+		/*
+		 * From ACPI spec, OSPM will ignore _CCA if an ancestor
+		 * already saw one.
+		 */
+		adev->flags.cca_seen = 1;
+		cca = parent->flags.coherent_dma;
+	} else {
+		status = acpi_evaluate_integer(adev->handle, "_CCA",
+					       NULL, &cca);
+		if (ACPI_SUCCESS(status))
+			adev->flags.cca_seen = 1;
+		else if (!IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED))
+			/*
+			 * If architecture does not specify that _CCA is
+			 * required for DMA-able devices (e.g. x86),
+			 * we default to _CCA=1.
+			 */
+			cca = 1;
+		else
+			acpi_handle_debug(adev->handle,
+					  "ACPI device is missing _CCA.\n");
+	}
+
+	adev->flags.coherent_dma = cca;
+}
+
 void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 			     int type, unsigned long long sta)
 {
@@ -2127,6 +2205,7 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle,
 	device->flags.visited = false;
 	device_initialize(&device->dev);
 	dev_set_uevent_suppress(&device->dev, true);
+	acpi_init_coherency(device);
 }
 
 void acpi_device_add_finalize(struct acpi_device *device)
@@ -2405,7 +2484,7 @@ static void acpi_default_enumeration(struct acpi_device *device)
 }
 
 static const struct acpi_device_id generic_device_ids[] = {
-	{"PRP0001", },
+	{ACPI_DT_NAMESPACE_HID, },
 	{"", },
 };
 
@@ -2413,8 +2492,8 @@ static int acpi_generic_device_attach(struct acpi_device *adev,
 				      const struct acpi_device_id *not_used)
 {
 	/*
-	 * Since PRP0001 is the only ID handled here, the test below can be
-	 * unconditional.
+	 * Since ACPI_DT_NAMESPACE_HID is the only ID handled here, the test
+	 * below can be unconditional.
 	 */
 	if (adev->data.of_compatible)
 		acpi_default_enumeration(adev);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index cd49a3982b6a..67c548ad3764 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -712,3 +712,18 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, int rev, u64 funcs)
 	return false;
 }
 EXPORT_SYMBOL(acpi_check_dsm);
+
+/*
+ * acpi_backlight= handling, this is done here rather then in video_detect.c
+ * because __setup cannot be used in modules.
+ */
+char acpi_video_backlight_string[16];
+EXPORT_SYMBOL(acpi_video_backlight_string);
+
+static int __init acpi_backlight(char *str)
+{
+	strlcpy(acpi_video_backlight_string, str,
+		sizeof(acpi_video_backlight_string));
+	return 1;
+}
+__setup("acpi_backlight=", acpi_backlight);
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index c42feb2bacd0..815f75ef2411 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -1,106 +1,61 @@
 /*
+ *  Copyright (C) 2015       Red Hat Inc.
+ *                           Hans de Goede <hdegoede@redhat.com>
  *  Copyright (C) 2008       SuSE Linux Products GmbH
  *                           Thomas Renninger <trenn@suse.de>
  *
  *  May be copied or modified under the terms of the GNU General Public License
  *
  * video_detect.c:
- * Provides acpi_is_video_device() for early scanning of ACPI devices in scan.c
- * There a Linux specific (Spec does not provide a HID for video devices) is
- * assigned
- *
  * After PCI devices are glued with ACPI devices
  * acpi_get_pci_dev() can be called to identify ACPI graphics
  * devices for which a real graphics card is plugged in
  *
- * Now acpi_video_get_capabilities() can be called to check which
- * capabilities the graphics cards plugged in support. The check for general
- * video capabilities will be triggered by the first caller of
- * acpi_video_get_capabilities(NULL); which will happen when the first
- * backlight switching supporting driver calls:
- * acpi_video_backlight_support();
- *
  * Depending on whether ACPI graphics extensions (cmp. ACPI spec Appendix B)
  * are available, video.ko should be used to handle the device.
  *
  * Otherwise vendor specific drivers like thinkpad_acpi, asus-laptop,
  * sony_acpi,... can take care about backlight brightness.
  *
- * If CONFIG_ACPI_VIDEO is neither set as "compiled in" (y) nor as a module (m)
- * this file will not be compiled, acpi_video_get_capabilities() and
- * acpi_video_backlight_support() will always return 0 and vendor specific
- * drivers always can handle backlight.
+ * Backlight drivers can use acpi_video_get_backlight_type() to determine
+ * which driver should handle the backlight.
  *
+ * If CONFIG_ACPI_VIDEO is neither set as "compiled in" (y) nor as a module (m)
+ * this file will not be compiled and acpi_video_get_backlight_type() will
+ * always return acpi_backlight_vendor.
  */
 
 #include <linux/export.h>
 #include <linux/acpi.h>
+#include <linux/backlight.h>
 #include <linux/dmi.h>
+#include <linux/module.h>
 #include <linux/pci.h>
-
-#include "internal.h"
+#include <linux/types.h>
+#include <acpi/video.h>
 
 ACPI_MODULE_NAME("video");
 #define _COMPONENT		ACPI_VIDEO_COMPONENT
 
-static long acpi_video_support;
-static bool acpi_video_caps_checked;
+void acpi_video_unregister_backlight(void);
 
-static acpi_status
-acpi_backlight_cap_match(acpi_handle handle, u32 level, void *context,
-			  void **return_value)
-{
-	long *cap = context;
+static bool backlight_notifier_registered;
+static struct notifier_block backlight_nb;
 
-	if (acpi_has_method(handle, "_BCM") &&
-	    acpi_has_method(handle, "_BCL")) {
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found generic backlight "
-				  "support\n"));
-		*cap |= ACPI_VIDEO_BACKLIGHT;
-		if (!acpi_has_method(handle, "_BQC"))
-			printk(KERN_WARNING FW_BUG PREFIX "No _BQC method, "
-				"cannot determine initial brightness\n");
-		/* We have backlight support, no need to scan further */
-		return AE_CTRL_TERMINATE;
-	}
-	return 0;
-}
+static enum acpi_backlight_type acpi_backlight_cmdline = acpi_backlight_undef;
+static enum acpi_backlight_type acpi_backlight_dmi = acpi_backlight_undef;
 
-/* Returns true if the ACPI object is a video device which can be
- * handled by video.ko.
- * The device will get a Linux specific CID added in scan.c to
- * identify the device as an ACPI graphics device
- * Be aware that the graphics device may not be physically present
- * Use acpi_video_get_capabilities() to detect general ACPI video
- * capabilities of present cards
- */
-long acpi_is_video_device(acpi_handle handle)
+static void acpi_video_parse_cmdline(void)
 {
-	long video_caps = 0;
-
-	/* Is this device able to support video switching ? */
-	if (acpi_has_method(handle, "_DOD") || acpi_has_method(handle, "_DOS"))
-		video_caps |= ACPI_VIDEO_OUTPUT_SWITCHING;
-
-	/* Is this device able to retrieve a video ROM ? */
-	if (acpi_has_method(handle, "_ROM"))
-		video_caps |= ACPI_VIDEO_ROM_AVAILABLE;
-
-	/* Is this device able to configure which video head to be POSTed ? */
-	if (acpi_has_method(handle, "_VPO") &&
-	    acpi_has_method(handle, "_GPD") &&
-	    acpi_has_method(handle, "_SPD"))
-		video_caps |= ACPI_VIDEO_DEVICE_POSTING;
-
-	/* Only check for backlight functionality if one of the above hit. */
-	if (video_caps)
-		acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
-				    ACPI_UINT32_MAX, acpi_backlight_cap_match, NULL,
-				    &video_caps, NULL);
-
-	return video_caps;
+	if (!strcmp("vendor", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_vendor;
+	if (!strcmp("video", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_video;
+	if (!strcmp("native", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_native;
+	if (!strcmp("none", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_none;
 }
-EXPORT_SYMBOL(acpi_is_video_device);
 
 static acpi_status
 find_video(acpi_handle handle, u32 lvl, void *context, void **rv)
@@ -109,7 +64,7 @@ find_video(acpi_handle handle, u32 lvl, void *context, void **rv)
 	struct pci_dev *dev;
 	struct acpi_device *acpi_dev;
 
-	const struct acpi_device_id video_ids[] = {
+	static const struct acpi_device_id video_ids[] = {
 		{ACPI_VIDEO_HID, 0},
 		{"", 0},
 	};
@@ -130,11 +85,23 @@ find_video(acpi_handle handle, u32 lvl, void *context, void **rv)
  * buggy */
 static int video_detect_force_vendor(const struct dmi_system_id *d)
 {
-	acpi_video_support |= ACPI_VIDEO_BACKLIGHT_DMI_VENDOR;
+	acpi_backlight_dmi = acpi_backlight_vendor;
+	return 0;
+}
+
+static int video_detect_force_video(const struct dmi_system_id *d)
+{
+	acpi_backlight_dmi = acpi_backlight_video;
 	return 0;
 }
 
-static struct dmi_system_id video_detect_dmi_table[] = {
+static int video_detect_force_native(const struct dmi_system_id *d)
+{
+	acpi_backlight_dmi = acpi_backlight_native;
+	return 0;
+}
+
+static const struct dmi_system_id video_detect_dmi_table[] = {
 	/* On Samsung X360, the BIOS will set a flag (VDRV) if generic
 	 * ACPI backlight device is used. This flag will definitively break
 	 * the backlight interface (even the vendor interface) untill next
@@ -174,137 +141,209 @@ static struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"),
 		},
 	},
+
+	/*
+	 * These models have a working acpi_video backlight control, and using
+	 * native backlight causes a regression where backlight does not work
+	 * when userspace is not handling brightness key events. Disable
+	 * native_backlight on these to fix this:
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=81691
+	 */
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "ThinkPad T420",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T420"),
+		},
+	},
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "ThinkPad T520",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T520"),
+		},
+	},
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "ThinkPad X201s",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"),
+		},
+	},
+
+	/* The native backlight controls do not work on some older machines */
+	{
+	 /* https://bugs.freedesktop.org/show_bug.cgi?id=81515 */
+	 .callback = video_detect_force_video,
+	 .ident = "HP ENVY 15 Notebook",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY 15 Notebook PC"),
+		},
+	},
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 870Z5E/880Z5E/680Z5E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "870Z5E/880Z5E/680Z5E"),
+		},
+	},
+	{
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 370R4E/370R4V/370R5E/3570RE/370R5V",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME,
+			  "370R4E/370R4V/370R5E/3570RE/370R5V"),
+		},
+	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1186097 */
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 3570R/370R/470R/450R/510R/4450RV",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME,
+			  "3570R/370R/470R/450R/510R/4450RV"),
+		},
+	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1094948 */
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 730U3E/740U3E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "730U3E/740U3E"),
+		},
+	},
+	{
+	 /* https://bugs.freedesktop.org/show_bug.cgi?id=87286 */
+	 .callback = video_detect_force_video,
+	 .ident = "SAMSUNG 900X3C/900X3D/900X3E/900X4C/900X4D",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME,
+			  "900X3C/900X3D/900X3E/900X4C/900X4D"),
+		},
+	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1163574 */
+	 .callback = video_detect_force_video,
+	 .ident = "Dell XPS15 L521X",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "XPS L521X"),
+		},
+	},
+
+	/* Non win8 machines which need native backlight nevertheless */
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1187004 */
+	 .callback = video_detect_force_native,
+	 .ident = "Lenovo Ideapad Z570",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "102434U"),
+		},
+	},
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */
+	 .callback = video_detect_force_native,
+	 .ident = "Apple MacBook Pro 12,1",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro12,1"),
+		},
+	},
 	{ },
 };
 
+static int acpi_video_backlight_notify(struct notifier_block *nb,
+				       unsigned long val, void *bd)
+{
+	struct backlight_device *backlight = bd;
+
+	/* A raw bl registering may change video -> native */
+	if (backlight->props.type == BACKLIGHT_RAW &&
+	    val == BACKLIGHT_REGISTERED &&
+	    acpi_video_get_backlight_type() != acpi_backlight_video)
+		acpi_video_unregister_backlight();
+
+	return NOTIFY_OK;
+}
+
 /*
- * Returns the video capabilities of a specific ACPI graphics device
+ * Determine which type of backlight interface to use on this system,
+ * First check cmdline, then dmi quirks, then do autodetect.
  *
- * if NULL is passed as argument all ACPI devices are enumerated and
- * all graphics capabilities of physically present devices are
- * summarized and returned. This is cached and done only once.
+ * The autodetect order is:
+ * 1) Is the acpi-video backlight interface supported ->
+ *  no, use a vendor interface
+ * 2) Is this a win8 "ready" BIOS and do we have a native interface ->
+ *  yes, use a native interface
+ * 3) Else use the acpi-video interface
+ *
+ * Arguably the native on win8 check should be done first, but that would
+ * be a behavior change, which may causes issues.
  */
-long acpi_video_get_capabilities(acpi_handle graphics_handle)
+enum acpi_backlight_type acpi_video_get_backlight_type(void)
 {
-	long caps = 0;
-	struct acpi_device *tmp_dev;
-	acpi_status status;
-
-	if (acpi_video_caps_checked && graphics_handle == NULL)
-		return acpi_video_support;
-
-	if (!graphics_handle) {
-		/* Only do the global walk through all graphics devices once */
-		acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
-				    ACPI_UINT32_MAX, find_video, NULL,
-				    &caps, NULL);
-		/* There might be boot param flags set already... */
-		acpi_video_support |= caps;
-		acpi_video_caps_checked = 1;
-		/* Add blacklists here. Be careful to use the right *DMI* bits
-		 * to still be able to override logic via boot params, e.g.:
-		 *
-		 *   if (dmi_name_in_vendors("XY")) {
-		 *	acpi_video_support |=
-		 *		ACPI_VIDEO_BACKLIGHT_DMI_VENDOR;
-		 *}
-		 */
+	static DEFINE_MUTEX(init_mutex);
+	static bool init_done;
+	static long video_caps;
 
+	/* Parse cmdline, dmi and acpi only once */
+	mutex_lock(&init_mutex);
+	if (!init_done) {
+		acpi_video_parse_cmdline();
 		dmi_check_system(video_detect_dmi_table);
-	} else {
-		status = acpi_bus_get_device(graphics_handle, &tmp_dev);
-		if (ACPI_FAILURE(status)) {
-			ACPI_EXCEPTION((AE_INFO, status, "Invalid device"));
-			return 0;
-		}
-		acpi_walk_namespace(ACPI_TYPE_DEVICE, graphics_handle,
+		acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
 				    ACPI_UINT32_MAX, find_video, NULL,
-				    &caps, NULL);
+				    &video_caps, NULL);
+		backlight_nb.notifier_call = acpi_video_backlight_notify;
+		backlight_nb.priority = 0;
+		if (backlight_register_notifier(&backlight_nb) == 0)
+			backlight_notifier_registered = true;
+		init_done = true;
 	}
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "We have 0x%lX video support %s %s\n",
-			  graphics_handle ? caps : acpi_video_support,
-			  graphics_handle ? "on device " : "in general",
-			  graphics_handle ? acpi_device_bid(tmp_dev) : ""));
-	return caps;
-}
-EXPORT_SYMBOL(acpi_video_get_capabilities);
+	mutex_unlock(&init_mutex);
 
-static void acpi_video_caps_check(void)
-{
-	/*
-	 * We must check whether the ACPI graphics device is physically plugged
-	 * in. Therefore this must be called after binding PCI and ACPI devices
-	 */
-	if (!acpi_video_caps_checked)
-		acpi_video_get_capabilities(NULL);
-}
+	if (acpi_backlight_cmdline != acpi_backlight_undef)
+		return acpi_backlight_cmdline;
 
-bool acpi_osi_is_win8(void)
-{
-	return acpi_gbl_osi_data >= ACPI_OSI_WIN_8;
-}
-EXPORT_SYMBOL(acpi_osi_is_win8);
+	if (acpi_backlight_dmi != acpi_backlight_undef)
+		return acpi_backlight_dmi;
 
-/* Promote the vendor interface instead of the generic video module.
- * This function allow DMI blacklists to be implemented by externals
- * platform drivers instead of putting a big blacklist in video_detect.c
- * After calling this function you will probably want to call
- * acpi_video_unregister() to make sure the video module is not loaded
- */
-void acpi_video_dmi_promote_vendor(void)
-{
-	acpi_video_caps_check();
-	acpi_video_support |= ACPI_VIDEO_BACKLIGHT_DMI_VENDOR;
-}
-EXPORT_SYMBOL(acpi_video_dmi_promote_vendor);
-
-/* To be called when a driver who previously promoted the vendor
- * interface */
-void acpi_video_dmi_demote_vendor(void)
-{
-	acpi_video_caps_check();
-	acpi_video_support &= ~ACPI_VIDEO_BACKLIGHT_DMI_VENDOR;
-}
-EXPORT_SYMBOL(acpi_video_dmi_demote_vendor);
-
-/* Returns true if video.ko can do backlight switching */
-int acpi_video_backlight_support(void)
-{
-	acpi_video_caps_check();
-
-	/* First check for boot param -> highest prio */
-	if (acpi_video_support & ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR)
-		return 0;
-	else if (acpi_video_support & ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO)
-		return 1;
+	if (!(video_caps & ACPI_VIDEO_BACKLIGHT))
+		return acpi_backlight_vendor;
 
-	/* Then check for DMI blacklist -> second highest prio */
-	if (acpi_video_support & ACPI_VIDEO_BACKLIGHT_DMI_VENDOR)
-		return 0;
-	else if (acpi_video_support & ACPI_VIDEO_BACKLIGHT_DMI_VIDEO)
-		return 1;
+	if (acpi_osi_is_win8() && backlight_device_registered(BACKLIGHT_RAW))
+		return acpi_backlight_native;
 
-	/* Then go the default way */
-	return acpi_video_support & ACPI_VIDEO_BACKLIGHT;
+	return acpi_backlight_video;
 }
-EXPORT_SYMBOL(acpi_video_backlight_support);
+EXPORT_SYMBOL(acpi_video_get_backlight_type);
 
 /*
- * Use acpi_backlight=vendor/video to force that backlight switching
- * is processed by vendor specific acpi drivers or video.ko driver.
+ * Set the preferred backlight interface type based on DMI info.
+ * This function allows DMI blacklists to be implemented by external
+ * platform drivers instead of putting a big blacklist in video_detect.c
  */
-static int __init acpi_backlight(char *str)
+void acpi_video_set_dmi_backlight_type(enum acpi_backlight_type type)
 {
-	if (str == NULL || *str == '\0')
-		return 1;
-	else {
-		if (!strcmp("vendor", str))
-			acpi_video_support |=
-				ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR;
-		if (!strcmp("video", str))
-			acpi_video_support |=
-				ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO;
-	}
-	return 1;
+	acpi_backlight_dmi = type;
+	/* Remove acpi-video backlight interface if it is no longer desired */
+	if (acpi_video_get_backlight_type() != acpi_backlight_video)
+		acpi_video_unregister_backlight();
+}
+EXPORT_SYMBOL(acpi_video_set_dmi_backlight_type);
+
+void __exit acpi_video_detect_exit(void)
+{
+	if (backlight_notifier_registered)
+		backlight_unregister_notifier(&backlight_nb);
 }
-__setup("acpi_backlight=", acpi_backlight);
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 5f601553b9b0..9dca4b995be0 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -270,6 +270,7 @@ config ATA_PIIX
 config SATA_DWC
 	tristate "DesignWare Cores SATA support"
 	depends on 460EX
+	select DW_DMAC
 	help
 	  This option enables support for the on-chip SATA controller of the
 	  AppliedMicro processor 460EX.
@@ -729,15 +730,6 @@ config PATA_SC1200
 
 	  If unsure, say N.
 
-config PATA_SCC
-	tristate "Toshiba's Cell Reference Set IDE support"
-	depends on PCI && PPC_CELLEB
-	help
-	  This option enables support for the built-in IDE controller on
-	  Toshiba Cell Reference Board.
-
-	  If unsure, say N.
-
 config PATA_SCH
 	tristate "Intel SCH PATA support"
 	depends on PCI
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index b67e995179a9..40f7865f20a1 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -75,7 +75,6 @@ obj-$(CONFIG_PATA_PDC_OLD)	+= pata_pdc202xx_old.o
 obj-$(CONFIG_PATA_RADISYS)	+= pata_radisys.o
 obj-$(CONFIG_PATA_RDC)		+= pata_rdc.o
 obj-$(CONFIG_PATA_SC1200)	+= pata_sc1200.o
-obj-$(CONFIG_PATA_SCC)		+= pata_scc.o
 obj-$(CONFIG_PATA_SCH)		+= pata_sch.o
 obj-$(CONFIG_PATA_SERVERWORKS)	+= pata_serverworks.o
 obj-$(CONFIG_PATA_SIL680)	+= pata_sil680.o
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c7a92a743ed0..65ee94454bbd 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -66,6 +66,7 @@ enum board_ids {
 	board_ahci_yes_fbs,
 
 	/* board IDs for specific chipsets in alphabetical order */
+	board_ahci_avn,
 	board_ahci_mcp65,
 	board_ahci_mcp77,
 	board_ahci_mcp89,
@@ -84,6 +85,8 @@ enum board_ids {
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+			      unsigned long deadline);
 static void ahci_mcp89_apple_enable(struct pci_dev *pdev);
 static bool is_mcp89_apple(struct pci_dev *pdev);
 static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
@@ -107,6 +110,11 @@ static struct ata_port_operations ahci_p5wdh_ops = {
 	.hardreset		= ahci_p5wdh_hardreset,
 };
 
+static struct ata_port_operations ahci_avn_ops = {
+	.inherits		= &ahci_ops,
+	.hardreset		= ahci_avn_hardreset,
+};
+
 static const struct ata_port_info ahci_port_info[] = {
 	/* by features */
 	[board_ahci] = {
@@ -151,6 +159,12 @@ static const struct ata_port_info ahci_port_info[] = {
 		.port_ops	= &ahci_ops,
 	},
 	/* by chipsets */
+	[board_ahci_avn] = {
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= ATA_PIO4,
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_avn_ops,
+	},
 	[board_ahci_mcp65] = {
 		AHCI_HFLAGS	(AHCI_HFLAG_NO_FPDMA_AA | AHCI_HFLAG_NO_PMP |
 				 AHCI_HFLAG_YES_NCQ),
@@ -290,14 +304,14 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x1f27), board_ahci }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f2e), board_ahci }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f2f), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f32), board_ahci }, /* Avoton AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1f33), board_ahci }, /* Avoton AHCI */
-	{ PCI_VDEVICE(INTEL, 0x1f34), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f35), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f36), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f32), board_ahci_avn }, /* Avoton AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1f33), board_ahci_avn }, /* Avoton AHCI */
+	{ PCI_VDEVICE(INTEL, 0x1f34), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f35), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f36), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
+	{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
@@ -670,6 +684,79 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class,
 	return rc;
 }
 
+/*
+ * ahci_avn_hardreset - attempt more aggressive recovery of Avoton ports.
+ *
+ * It has been observed with some SSDs that the timing of events in the
+ * link synchronization phase can leave the port in a state that can not
+ * be recovered by a SATA-hard-reset alone.  The failing signature is
+ * SStatus.DET stuck at 1 ("Device presence detected but Phy
+ * communication not established").  It was found that unloading and
+ * reloading the driver when this problem occurs allows the drive
+ * connection to be recovered (DET advanced to 0x3).  The critical
+ * component of reloading the driver is that the port state machines are
+ * reset by bouncing "port enable" in the AHCI PCS configuration
+ * register.  So, reproduce that effect by bouncing a port whenever we
+ * see DET==1 after a reset.
+ */
+static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
+			      unsigned long deadline)
+{
+	const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
+	struct ata_port *ap = link->ap;
+	struct ahci_port_priv *pp = ap->private_data;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
+	unsigned long tmo = deadline - jiffies;
+	struct ata_taskfile tf;
+	bool online;
+	int rc, i;
+
+	DPRINTK("ENTER\n");
+
+	ahci_stop_engine(ap);
+
+	for (i = 0; i < 2; i++) {
+		u16 val;
+		u32 sstatus;
+		int port = ap->port_no;
+		struct ata_host *host = ap->host;
+		struct pci_dev *pdev = to_pci_dev(host->dev);
+
+		/* clear D2H reception area to properly wait for D2H FIS */
+		ata_tf_init(link->device, &tf);
+		tf.command = ATA_BUSY;
+		ata_tf_to_fis(&tf, 0, 0, d2h_fis);
+
+		rc = sata_link_hardreset(link, timing, deadline, &online,
+				ahci_check_ready);
+
+		if (sata_scr_read(link, SCR_STATUS, &sstatus) != 0 ||
+				(sstatus & 0xf) != 1)
+			break;
+
+		ata_link_printk(link, KERN_INFO, "avn bounce port%d\n",
+				port);
+
+		pci_read_config_word(pdev, 0x92, &val);
+		val &= ~(1 << port);
+		pci_write_config_word(pdev, 0x92, val);
+		ata_msleep(ap, 1000);
+		val |= 1 << port;
+		pci_write_config_word(pdev, 0x92, val);
+		deadline += tmo;
+	}
+
+	hpriv->start_engine(ap);
+
+	if (online)
+		*class = ahci_dev_classify(ap);
+
+	DPRINTK("EXIT, rc=%d, class=%u\n", rc, *class);
+	return rc;
+}
+
+
 #ifdef CONFIG_PM
 static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 23716dd8a7ec..5928d0746a27 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -45,7 +45,7 @@ static void ahci_mvebu_mbus_config(struct ahci_host_priv *hpriv,
 		writel((cs->mbus_attr << 8) |
 		       (dram->mbus_dram_target_id << 4) | 1,
 		       hpriv->mmio + AHCI_WINDOW_CTRL(i));
-		writel(cs->base, hpriv->mmio + AHCI_WINDOW_BASE(i));
+		writel(cs->base >> 16, hpriv->mmio + AHCI_WINDOW_BASE(i));
 		writel(((cs->size - 1) & 0xffff0000),
 		       hpriv->mmio + AHCI_WINDOW_SIZE(i));
 	}
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index ea0ff005b86c..8ff428fe8e0f 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -37,7 +37,6 @@ struct st_ahci_drv_data {
 	struct reset_control *pwr;
 	struct reset_control *sw_rst;
 	struct reset_control *pwr_rst;
-	struct ahci_host_priv *hpriv;
 };
 
 static void st_ahci_configure_oob(void __iomem *mmio)
@@ -55,9 +54,10 @@ static void st_ahci_configure_oob(void __iomem *mmio)
 	writel(new_val, mmio + ST_AHCI_OOBR);
 }
 
-static int st_ahci_deassert_resets(struct device *dev)
+static int st_ahci_deassert_resets(struct ahci_host_priv *hpriv,
+				struct device *dev)
 {
-	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
+	struct st_ahci_drv_data *drv_data = hpriv->plat_data;
 	int err;
 
 	if (drv_data->pwr) {
@@ -90,8 +90,8 @@ static int st_ahci_deassert_resets(struct device *dev)
 static void st_ahci_host_stop(struct ata_host *host)
 {
 	struct ahci_host_priv *hpriv = host->private_data;
+	struct st_ahci_drv_data *drv_data = hpriv->plat_data;
 	struct device *dev = host->dev;
-	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
 	int err;
 
 	if (drv_data->pwr) {
@@ -103,29 +103,30 @@ static void st_ahci_host_stop(struct ata_host *host)
 	ahci_platform_disable_resources(hpriv);
 }
 
-static int st_ahci_probe_resets(struct platform_device *pdev)
+static int st_ahci_probe_resets(struct ahci_host_priv *hpriv,
+				struct device *dev)
 {
-	struct st_ahci_drv_data *drv_data = platform_get_drvdata(pdev);
+	struct st_ahci_drv_data *drv_data = hpriv->plat_data;
 
-	drv_data->pwr = devm_reset_control_get(&pdev->dev, "pwr-dwn");
+	drv_data->pwr = devm_reset_control_get(dev, "pwr-dwn");
 	if (IS_ERR(drv_data->pwr)) {
-		dev_info(&pdev->dev, "power reset control not defined\n");
+		dev_info(dev, "power reset control not defined\n");
 		drv_data->pwr = NULL;
 	}
 
-	drv_data->sw_rst = devm_reset_control_get(&pdev->dev, "sw-rst");
+	drv_data->sw_rst = devm_reset_control_get(dev, "sw-rst");
 	if (IS_ERR(drv_data->sw_rst)) {
-		dev_info(&pdev->dev, "soft reset control not defined\n");
+		dev_info(dev, "soft reset control not defined\n");
 		drv_data->sw_rst = NULL;
 	}
 
-	drv_data->pwr_rst = devm_reset_control_get(&pdev->dev, "pwr-rst");
+	drv_data->pwr_rst = devm_reset_control_get(dev, "pwr-rst");
 	if (IS_ERR(drv_data->pwr_rst)) {
-		dev_dbg(&pdev->dev, "power soft reset control not defined\n");
+		dev_dbg(dev, "power soft reset control not defined\n");
 		drv_data->pwr_rst = NULL;
 	}
 
-	return st_ahci_deassert_resets(&pdev->dev);
+	return st_ahci_deassert_resets(hpriv, dev);
 }
 
 static struct ata_port_operations st_ahci_port_ops = {
@@ -154,15 +155,12 @@ static int st_ahci_probe(struct platform_device *pdev)
 	if (!drv_data)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, drv_data);
-
 	hpriv = ahci_platform_get_resources(pdev);
 	if (IS_ERR(hpriv))
 		return PTR_ERR(hpriv);
+	hpriv->plat_data = drv_data;
 
-	drv_data->hpriv = hpriv;
-
-	err = st_ahci_probe_resets(pdev);
+	err = st_ahci_probe_resets(hpriv, &pdev->dev);
 	if (err)
 		return err;
 
@@ -170,7 +168,7 @@ static int st_ahci_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	st_ahci_configure_oob(drv_data->hpriv->mmio);
+	st_ahci_configure_oob(hpriv->mmio);
 
 	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info,
 				      &ahci_platform_sht);
@@ -185,8 +183,9 @@ static int st_ahci_probe(struct platform_device *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int st_ahci_suspend(struct device *dev)
 {
-	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
-	struct ahci_host_priv *hpriv = drv_data->hpriv;
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	struct st_ahci_drv_data *drv_data = hpriv->plat_data;
 	int err;
 
 	err = ahci_platform_suspend_host(dev);
@@ -208,21 +207,21 @@ static int st_ahci_suspend(struct device *dev)
 
 static int st_ahci_resume(struct device *dev)
 {
-	struct st_ahci_drv_data *drv_data = dev_get_drvdata(dev);
-	struct ahci_host_priv *hpriv = drv_data->hpriv;
+	struct ata_host *host = dev_get_drvdata(dev);
+	struct ahci_host_priv *hpriv = host->private_data;
 	int err;
 
 	err = ahci_platform_enable_resources(hpriv);
 	if (err)
 		return err;
 
-	err = st_ahci_deassert_resets(dev);
+	err = st_ahci_deassert_resets(hpriv, dev);
 	if (err) {
 		ahci_platform_disable_resources(hpriv);
 		return err;
 	}
 
-	st_ahci_configure_oob(drv_data->hpriv->mmio);
+	st_ahci_configure_oob(hpriv->mmio);
 
 	return ahci_platform_resume_host(dev);
 }
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 61a9c07e0dff..287c4ba0219f 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1707,8 +1707,7 @@ static void ahci_handle_port_interrupt(struct ata_port *ap,
 	if (unlikely(resetting))
 		status &= ~PORT_IRQ_BAD_PMP;
 
-	/* if LPM is enabled, PHYRDY doesn't mean anything */
-	if (ap->link.lpm_policy > ATA_LPM_MAX_POWER) {
+	if (sata_lpm_ignore_phy_events(&ap->link)) {
 		status &= ~PORT_IRQ_PHYRDY;
 		ahci_scr_write(&ap->link, SCR_ERROR, SERR_PHYRDY_CHG);
 	}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index f6cb1f1b30b7..577849c6611a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4235,7 +4235,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*MX100*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
-	{ "Samsung SSD 850 PRO*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
+	{ "Samsung SSD 8*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 
 	/*
@@ -6752,6 +6752,38 @@ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val,
 	return tmp;
 }
 
+/**
+ *	sata_lpm_ignore_phy_events - test if PHY event should be ignored
+ *	@link: Link receiving the event
+ *
+ *	Test whether the received PHY event has to be ignored or not.
+ *
+ *	LOCKING:
+ *	None:
+ *
+ *	RETURNS:
+ *	True if the event has to be ignored.
+ */
+bool sata_lpm_ignore_phy_events(struct ata_link *link)
+{
+	unsigned long lpm_timeout = link->last_lpm_change +
+				    msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY);
+
+	/* if LPM is enabled, PHYRDY doesn't mean anything */
+	if (link->lpm_policy > ATA_LPM_MAX_POWER)
+		return true;
+
+	/* ignore the first PHY event after the LPM policy changed
+	 * as it is might be spurious
+	 */
+	if ((link->flags & ATA_LFLAG_CHANGED) &&
+	    time_before(jiffies, lpm_timeout))
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
+
 /*
  * Dummy port_ops
  */
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 07f41be38fbe..cf0022ec07f2 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -3597,6 +3597,9 @@ static int ata_eh_set_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 		}
 	}
 
+	link->last_lpm_change = jiffies;
+	link->flags |= ATA_LFLAG_CHANGED;
+
 	return 0;
 
 fail:
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 80a80548ad0a..27245957eee3 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -1053,7 +1053,7 @@ static struct of_device_id octeon_cf_match[] = {
 	},
 	{},
 };
-MODULE_DEVICE_TABLE(of, octeon_i2c_match);
+MODULE_DEVICE_TABLE(of, octeon_cf_match);
 
 static struct platform_driver octeon_cf_driver = {
 	.probe		= octeon_cf_probe,
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
deleted file mode 100644
index 5cd60d6388ec..000000000000
--- a/drivers/ata/pata_scc.c
+++ /dev/null
@@ -1,1110 +0,0 @@
-/*
- * Support for IDE interfaces on Celleb platform
- *
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * This code is based on drivers/ata/ata_piix.c:
- *  Copyright 2003-2005 Red Hat Inc
- *  Copyright 2003-2005 Jeff Garzik
- *  Copyright (C) 1998-1999 Andrzej Krzysztofowicz, Author and Maintainer
- *  Copyright (C) 1998-2000 Andre Hedrick <andre@linux-ide.org>
- *  Copyright (C) 2003 Red Hat Inc
- *
- * and drivers/ata/ahci.c:
- *  Copyright 2004-2005 Red Hat, Inc.
- *
- * and drivers/ata/libata-core.c:
- *  Copyright 2003-2004 Red Hat, Inc.  All rights reserved.
- *  Copyright 2003-2004 Jeff Garzik
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/device.h>
-#include <scsi/scsi_host.h>
-#include <linux/libata.h>
-
-#define DRV_NAME		"pata_scc"
-#define DRV_VERSION		"0.3"
-
-#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA		0x01b4
-
-/* PCI BARs */
-#define SCC_CTRL_BAR		0
-#define SCC_BMID_BAR		1
-
-/* offset of CTRL registers */
-#define SCC_CTL_PIOSHT		0x000
-#define SCC_CTL_PIOCT		0x004
-#define SCC_CTL_MDMACT		0x008
-#define SCC_CTL_MCRCST		0x00C
-#define SCC_CTL_SDMACT		0x010
-#define SCC_CTL_SCRCST		0x014
-#define SCC_CTL_UDENVT		0x018
-#define SCC_CTL_TDVHSEL 	0x020
-#define SCC_CTL_MODEREG 	0x024
-#define SCC_CTL_ECMODE		0xF00
-#define SCC_CTL_MAEA0		0xF50
-#define SCC_CTL_MAEC0		0xF54
-#define SCC_CTL_CCKCTRL 	0xFF0
-
-/* offset of BMID registers */
-#define SCC_DMA_CMD		0x000
-#define SCC_DMA_STATUS		0x004
-#define SCC_DMA_TABLE_OFS	0x008
-#define SCC_DMA_INTMASK 	0x010
-#define SCC_DMA_INTST		0x014
-#define SCC_DMA_PTERADD 	0x018
-#define SCC_REG_CMD_ADDR	0x020
-#define SCC_REG_DATA		0x000
-#define SCC_REG_ERR		0x004
-#define SCC_REG_FEATURE 	0x004
-#define SCC_REG_NSECT		0x008
-#define SCC_REG_LBAL		0x00C
-#define SCC_REG_LBAM		0x010
-#define SCC_REG_LBAH		0x014
-#define SCC_REG_DEVICE		0x018
-#define SCC_REG_STATUS		0x01C
-#define SCC_REG_CMD		0x01C
-#define SCC_REG_ALTSTATUS	0x020
-
-/* register value */
-#define TDVHSEL_MASTER		0x00000001
-#define TDVHSEL_SLAVE		0x00000004
-
-#define MODE_JCUSFEN		0x00000080
-
-#define ECMODE_VALUE		0x01
-
-#define CCKCTRL_ATARESET	0x00040000
-#define CCKCTRL_BUFCNT		0x00020000
-#define CCKCTRL_CRST		0x00010000
-#define CCKCTRL_OCLKEN		0x00000100
-#define CCKCTRL_ATACLKOEN	0x00000002
-#define CCKCTRL_LCLKEN		0x00000001
-
-#define QCHCD_IOS_SS		0x00000001
-
-#define QCHSD_STPDIAG		0x00020000
-
-#define INTMASK_MSK		0xD1000012
-#define INTSTS_SERROR		0x80000000
-#define INTSTS_PRERR		0x40000000
-#define INTSTS_RERR		0x10000000
-#define INTSTS_ICERR		0x01000000
-#define INTSTS_BMSINT		0x00000010
-#define INTSTS_BMHE		0x00000008
-#define INTSTS_IOIRQS		0x00000004
-#define INTSTS_INTRQ		0x00000002
-#define INTSTS_ACTEINT		0x00000001
-
-
-/* PIO transfer mode table */
-/* JCHST */
-static const unsigned long JCHSTtbl[2][7] = {
-	{0x0E, 0x05, 0x02, 0x03, 0x02, 0x00, 0x00},	/* 100MHz */
-	{0x13, 0x07, 0x04, 0x04, 0x03, 0x00, 0x00}	/* 133MHz */
-};
-
-/* JCHHT */
-static const unsigned long JCHHTtbl[2][7] = {
-	{0x0E, 0x02, 0x02, 0x02, 0x02, 0x00, 0x00},	/* 100MHz */
-	{0x13, 0x03, 0x03, 0x03, 0x03, 0x00, 0x00}	/* 133MHz */
-};
-
-/* JCHCT */
-static const unsigned long JCHCTtbl[2][7] = {
-	{0x1D, 0x1D, 0x1C, 0x0B, 0x06, 0x00, 0x00},	/* 100MHz */
-	{0x27, 0x26, 0x26, 0x0E, 0x09, 0x00, 0x00}	/* 133MHz */
-};
-
-/* DMA transfer mode  table */
-/* JCHDCTM/JCHDCTS */
-static const unsigned long JCHDCTxtbl[2][7] = {
-	{0x0A, 0x06, 0x04, 0x03, 0x01, 0x00, 0x00},	/* 100MHz */
-	{0x0E, 0x09, 0x06, 0x04, 0x02, 0x01, 0x00}	/* 133MHz */
-};
-
-/* JCSTWTM/JCSTWTS  */
-static const unsigned long JCSTWTxtbl[2][7] = {
-	{0x06, 0x04, 0x03, 0x02, 0x02, 0x02, 0x00},	/* 100MHz */
-	{0x09, 0x06, 0x04, 0x02, 0x02, 0x02, 0x02}	/* 133MHz */
-};
-
-/* JCTSS */
-static const unsigned long JCTSStbl[2][7] = {
-	{0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x00},	/* 100MHz */
-	{0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05}	/* 133MHz */
-};
-
-/* JCENVT */
-static const unsigned long JCENVTtbl[2][7] = {
-	{0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00},	/* 100MHz */
-	{0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02}	/* 133MHz */
-};
-
-/* JCACTSELS/JCACTSELM */
-static const unsigned long JCACTSELtbl[2][7] = {
-	{0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x00},	/* 100MHz */
-	{0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}	/* 133MHz */
-};
-
-static const struct pci_device_id scc_pci_tbl[] = {
-	{ PCI_VDEVICE(TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA), 0},
-	{ }	/* terminate list */
-};
-
-/**
- *	scc_set_piomode - Initialize host controller PATA PIO timings
- *	@ap: Port whose timings we are configuring
- *	@adev: um
- *
- *	Set PIO mode for device.
- *
- *	LOCKING:
- *	None (inherited from caller).
- */
-
-static void scc_set_piomode (struct ata_port *ap, struct ata_device *adev)
-{
-	unsigned int pio = adev->pio_mode - XFER_PIO_0;
-	void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
-	void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
-	void __iomem *piosht_port = ctrl_base + SCC_CTL_PIOSHT;
-	void __iomem *pioct_port = ctrl_base + SCC_CTL_PIOCT;
-	unsigned long reg;
-	int offset;
-
-	reg = in_be32(cckctrl_port);
-	if (reg & CCKCTRL_ATACLKOEN)
-		offset = 1;	/* 133MHz */
-	else
-		offset = 0;	/* 100MHz */
-
-	reg = JCHSTtbl[offset][pio] << 16 | JCHHTtbl[offset][pio];
-	out_be32(piosht_port, reg);
-	reg = JCHCTtbl[offset][pio];
-	out_be32(pioct_port, reg);
-}
-
-/**
- *	scc_set_dmamode - Initialize host controller PATA DMA timings
- *	@ap: Port whose timings we are configuring
- *	@adev: um
- *
- *	Set UDMA mode for device.
- *
- *	LOCKING:
- *	None (inherited from caller).
- */
-
-static void scc_set_dmamode (struct ata_port *ap, struct ata_device *adev)
-{
-	unsigned int udma = adev->dma_mode;
-	unsigned int is_slave = (adev->devno != 0);
-	u8 speed = udma;
-	void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
-	void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
-	void __iomem *mdmact_port = ctrl_base + SCC_CTL_MDMACT;
-	void __iomem *mcrcst_port = ctrl_base + SCC_CTL_MCRCST;
-	void __iomem *sdmact_port = ctrl_base + SCC_CTL_SDMACT;
-	void __iomem *scrcst_port = ctrl_base + SCC_CTL_SCRCST;
-	void __iomem *udenvt_port = ctrl_base + SCC_CTL_UDENVT;
-	void __iomem *tdvhsel_port = ctrl_base + SCC_CTL_TDVHSEL;
-	int offset, idx;
-
-	if (in_be32(cckctrl_port) & CCKCTRL_ATACLKOEN)
-		offset = 1;	/* 133MHz */
-	else
-		offset = 0;	/* 100MHz */
-
-	if (speed >= XFER_UDMA_0)
-		idx = speed - XFER_UDMA_0;
-	else
-		return;
-
-	if (is_slave) {
-		out_be32(sdmact_port, JCHDCTxtbl[offset][idx]);
-		out_be32(scrcst_port, JCSTWTxtbl[offset][idx]);
-		out_be32(tdvhsel_port,
-			 (in_be32(tdvhsel_port) & ~TDVHSEL_SLAVE) | (JCACTSELtbl[offset][idx] << 2));
-	} else {
-		out_be32(mdmact_port, JCHDCTxtbl[offset][idx]);
-		out_be32(mcrcst_port, JCSTWTxtbl[offset][idx]);
-		out_be32(tdvhsel_port,
-			 (in_be32(tdvhsel_port) & ~TDVHSEL_MASTER) | JCACTSELtbl[offset][idx]);
-	}
-	out_be32(udenvt_port,
-		 JCTSStbl[offset][idx] << 16 | JCENVTtbl[offset][idx]);
-}
-
-unsigned long scc_mode_filter(struct ata_device *adev, unsigned long mask)
-{
-	/* errata A308 workaround: limit ATAPI UDMA mode to UDMA4 */
-	if (adev->class == ATA_DEV_ATAPI &&
-	    (mask & (0xE0 << ATA_SHIFT_UDMA))) {
-		printk(KERN_INFO "%s: limit ATAPI UDMA to UDMA4\n", DRV_NAME);
-		mask &= ~(0xE0 << ATA_SHIFT_UDMA);
-	}
-	return mask;
-}
-
-/**
- *	scc_tf_load - send taskfile registers to host controller
- *	@ap: Port to which output is sent
- *	@tf: ATA taskfile register set
- *
- *	Note: Original code is ata_sff_tf_load().
- */
-
-static void scc_tf_load (struct ata_port *ap, const struct ata_taskfile *tf)
-{
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-	unsigned int is_addr = tf->flags & ATA_TFLAG_ISADDR;
-
-	if (tf->ctl != ap->last_ctl) {
-		out_be32(ioaddr->ctl_addr, tf->ctl);
-		ap->last_ctl = tf->ctl;
-		ata_wait_idle(ap);
-	}
-
-	if (is_addr && (tf->flags & ATA_TFLAG_LBA48)) {
-		out_be32(ioaddr->feature_addr, tf->hob_feature);
-		out_be32(ioaddr->nsect_addr, tf->hob_nsect);
-		out_be32(ioaddr->lbal_addr, tf->hob_lbal);
-		out_be32(ioaddr->lbam_addr, tf->hob_lbam);
-		out_be32(ioaddr->lbah_addr, tf->hob_lbah);
-		VPRINTK("hob: feat 0x%X nsect 0x%X, lba 0x%X 0x%X 0x%X\n",
-			tf->hob_feature,
-			tf->hob_nsect,
-			tf->hob_lbal,
-			tf->hob_lbam,
-			tf->hob_lbah);
-	}
-
-	if (is_addr) {
-		out_be32(ioaddr->feature_addr, tf->feature);
-		out_be32(ioaddr->nsect_addr, tf->nsect);
-		out_be32(ioaddr->lbal_addr, tf->lbal);
-		out_be32(ioaddr->lbam_addr, tf->lbam);
-		out_be32(ioaddr->lbah_addr, tf->lbah);
-		VPRINTK("feat 0x%X nsect 0x%X lba 0x%X 0x%X 0x%X\n",
-			tf->feature,
-			tf->nsect,
-			tf->lbal,
-			tf->lbam,
-			tf->lbah);
-	}
-
-	if (tf->flags & ATA_TFLAG_DEVICE) {
-		out_be32(ioaddr->device_addr, tf->device);
-		VPRINTK("device 0x%X\n", tf->device);
-	}
-
-	ata_wait_idle(ap);
-}
-
-/**
- *	scc_check_status - Read device status reg & clear interrupt
- *	@ap: port where the device is
- *
- *	Note: Original code is ata_check_status().
- */
-
-static u8 scc_check_status (struct ata_port *ap)
-{
-	return in_be32(ap->ioaddr.status_addr);
-}
-
-/**
- *	scc_tf_read - input device's ATA taskfile shadow registers
- *	@ap: Port from which input is read
- *	@tf: ATA taskfile register set for storing input
- *
- *	Note: Original code is ata_sff_tf_read().
- */
-
-static void scc_tf_read (struct ata_port *ap, struct ata_taskfile *tf)
-{
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-
-	tf->command = scc_check_status(ap);
-	tf->feature = in_be32(ioaddr->error_addr);
-	tf->nsect = in_be32(ioaddr->nsect_addr);
-	tf->lbal = in_be32(ioaddr->lbal_addr);
-	tf->lbam = in_be32(ioaddr->lbam_addr);
-	tf->lbah = in_be32(ioaddr->lbah_addr);
-	tf->device = in_be32(ioaddr->device_addr);
-
-	if (tf->flags & ATA_TFLAG_LBA48) {
-		out_be32(ioaddr->ctl_addr, tf->ctl | ATA_HOB);
-		tf->hob_feature = in_be32(ioaddr->error_addr);
-		tf->hob_nsect = in_be32(ioaddr->nsect_addr);
-		tf->hob_lbal = in_be32(ioaddr->lbal_addr);
-		tf->hob_lbam = in_be32(ioaddr->lbam_addr);
-		tf->hob_lbah = in_be32(ioaddr->lbah_addr);
-		out_be32(ioaddr->ctl_addr, tf->ctl);
-		ap->last_ctl = tf->ctl;
-	}
-}
-
-/**
- *	scc_exec_command - issue ATA command to host controller
- *	@ap: port to which command is being issued
- *	@tf: ATA taskfile register set
- *
- *	Note: Original code is ata_sff_exec_command().
- */
-
-static void scc_exec_command (struct ata_port *ap,
-			      const struct ata_taskfile *tf)
-{
-	DPRINTK("ata%u: cmd 0x%X\n", ap->print_id, tf->command);
-
-	out_be32(ap->ioaddr.command_addr, tf->command);
-	ata_sff_pause(ap);
-}
-
-/**
- *	scc_check_altstatus - Read device alternate status reg
- *	@ap: port where the device is
- */
-
-static u8 scc_check_altstatus (struct ata_port *ap)
-{
-	return in_be32(ap->ioaddr.altstatus_addr);
-}
-
-/**
- *	scc_dev_select - Select device 0/1 on ATA bus
- *	@ap: ATA channel to manipulate
- *	@device: ATA device (numbered from zero) to select
- *
- *	Note: Original code is ata_sff_dev_select().
- */
-
-static void scc_dev_select (struct ata_port *ap, unsigned int device)
-{
-	u8 tmp;
-
-	if (device == 0)
-		tmp = ATA_DEVICE_OBS;
-	else
-		tmp = ATA_DEVICE_OBS | ATA_DEV1;
-
-	out_be32(ap->ioaddr.device_addr, tmp);
-	ata_sff_pause(ap);
-}
-
-/**
- *	scc_set_devctl - Write device control reg
- *	@ap: port where the device is
- *	@ctl: value to write
- */
-
-static void scc_set_devctl(struct ata_port *ap, u8 ctl)
-{
-	out_be32(ap->ioaddr.ctl_addr, ctl);
-}
-
-/**
- *	scc_bmdma_setup - Set up PCI IDE BMDMA transaction
- *	@qc: Info associated with this ATA transaction.
- *
- *	Note: Original code is ata_bmdma_setup().
- */
-
-static void scc_bmdma_setup (struct ata_queued_cmd *qc)
-{
-	struct ata_port *ap = qc->ap;
-	unsigned int rw = (qc->tf.flags & ATA_TFLAG_WRITE);
-	u8 dmactl;
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
-	/* load PRD table addr */
-	out_be32(mmio + SCC_DMA_TABLE_OFS, ap->bmdma_prd_dma);
-
-	/* specify data direction, triple-check start bit is clear */
-	dmactl = in_be32(mmio + SCC_DMA_CMD);
-	dmactl &= ~(ATA_DMA_WR | ATA_DMA_START);
-	if (!rw)
-		dmactl |= ATA_DMA_WR;
-	out_be32(mmio + SCC_DMA_CMD, dmactl);
-
-	/* issue r/w command */
-	ap->ops->sff_exec_command(ap, &qc->tf);
-}
-
-/**
- *	scc_bmdma_start - Start a PCI IDE BMDMA transaction
- *	@qc: Info associated with this ATA transaction.
- *
- *	Note: Original code is ata_bmdma_start().
- */
-
-static void scc_bmdma_start (struct ata_queued_cmd *qc)
-{
-	struct ata_port *ap = qc->ap;
-	u8 dmactl;
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
-	/* start host DMA transaction */
-	dmactl = in_be32(mmio + SCC_DMA_CMD);
-	out_be32(mmio + SCC_DMA_CMD, dmactl | ATA_DMA_START);
-}
-
-/**
- *	scc_devchk - PATA device presence detection
- *	@ap: ATA channel to examine
- *	@device: Device to examine (starting at zero)
- *
- *	Note: Original code is ata_devchk().
- */
-
-static unsigned int scc_devchk (struct ata_port *ap,
-				unsigned int device)
-{
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-	u8 nsect, lbal;
-
-	ap->ops->sff_dev_select(ap, device);
-
-	out_be32(ioaddr->nsect_addr, 0x55);
-	out_be32(ioaddr->lbal_addr, 0xaa);
-
-	out_be32(ioaddr->nsect_addr, 0xaa);
-	out_be32(ioaddr->lbal_addr, 0x55);
-
-	out_be32(ioaddr->nsect_addr, 0x55);
-	out_be32(ioaddr->lbal_addr, 0xaa);
-
-	nsect = in_be32(ioaddr->nsect_addr);
-	lbal = in_be32(ioaddr->lbal_addr);
-
-	if ((nsect == 0x55) && (lbal == 0xaa))
-		return 1;	/* we found a device */
-
-	return 0;		/* nothing found */
-}
-
-/**
- *	scc_wait_after_reset - wait for devices to become ready after reset
- *
- *	Note: Original code is ata_sff_wait_after_reset
- */
-
-static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask,
-				unsigned long deadline)
-{
-	struct ata_port *ap = link->ap;
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-	unsigned int dev0 = devmask & (1 << 0);
-	unsigned int dev1 = devmask & (1 << 1);
-	int rc, ret = 0;
-
-	/* Spec mandates ">= 2ms" before checking status.  We wait
-	 * 150ms, because that was the magic delay used for ATAPI
-	 * devices in Hale Landis's ATADRVR, for the period of time
-	 * between when the ATA command register is written, and then
-	 * status is checked.  Because waiting for "a while" before
-	 * checking status is fine, post SRST, we perform this magic
-	 * delay here as well.
-	 *
-	 * Old drivers/ide uses the 2mS rule and then waits for ready.
-	 */
-	ata_msleep(ap, 150);
-
-	/* always check readiness of the master device */
-	rc = ata_sff_wait_ready(link, deadline);
-	/* -ENODEV means the odd clown forgot the D7 pulldown resistor
-	 * and TF status is 0xff, bail out on it too.
-	 */
-	if (rc)
-		return rc;
-
-	/* if device 1 was found in ata_devchk, wait for register
-	 * access briefly, then wait for BSY to clear.
-	 */
-	if (dev1) {
-		int i;
-
-		ap->ops->sff_dev_select(ap, 1);
-
-		/* Wait for register access.  Some ATAPI devices fail
-		 * to set nsect/lbal after reset, so don't waste too
-		 * much time on it.  We're gonna wait for !BSY anyway.
-		 */
-		for (i = 0; i < 2; i++) {
-			u8 nsect, lbal;
-
-			nsect = in_be32(ioaddr->nsect_addr);
-			lbal = in_be32(ioaddr->lbal_addr);
-			if ((nsect == 1) && (lbal == 1))
-				break;
-			ata_msleep(ap, 50);	/* give drive a breather */
-		}
-
-		rc = ata_sff_wait_ready(link, deadline);
-		if (rc) {
-			if (rc != -ENODEV)
-				return rc;
-			ret = rc;
-		}
-	}
-
-	/* is all this really necessary? */
-	ap->ops->sff_dev_select(ap, 0);
-	if (dev1)
-		ap->ops->sff_dev_select(ap, 1);
-	if (dev0)
-		ap->ops->sff_dev_select(ap, 0);
-
-	return ret;
-}
-
-/**
- *	scc_bus_softreset - PATA device software reset
- *
- *	Note: Original code is ata_bus_softreset().
- */
-
-static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
-                                      unsigned long deadline)
-{
-	struct ata_ioports *ioaddr = &ap->ioaddr;
-
-	DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
-
-	/* software reset.  causes dev0 to be selected */
-	out_be32(ioaddr->ctl_addr, ap->ctl);
-	udelay(20);
-	out_be32(ioaddr->ctl_addr, ap->ctl | ATA_SRST);
-	udelay(20);
-	out_be32(ioaddr->ctl_addr, ap->ctl);
-
-	return scc_wait_after_reset(&ap->link, devmask, deadline);
-}
-
-/**
- *	scc_softreset - reset host port via ATA SRST
- *	@ap: port to reset
- *	@classes: resulting classes of attached devices
- *	@deadline: deadline jiffies for the operation
- *
- *	Note: Original code is ata_sff_softreset().
- */
-
-static int scc_softreset(struct ata_link *link, unsigned int *classes,
-			 unsigned long deadline)
-{
-	struct ata_port *ap = link->ap;
-	unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS;
-	unsigned int devmask = 0;
-	int rc;
-	u8 err;
-
-	DPRINTK("ENTER\n");
-
-	/* determine if device 0/1 are present */
-	if (scc_devchk(ap, 0))
-		devmask |= (1 << 0);
-	if (slave_possible && scc_devchk(ap, 1))
-		devmask |= (1 << 1);
-
-	/* select device 0 again */
-	ap->ops->sff_dev_select(ap, 0);
-
-	/* issue bus reset */
-	DPRINTK("about to softreset, devmask=%x\n", devmask);
-	rc = scc_bus_softreset(ap, devmask, deadline);
-	if (rc) {
-		ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc);
-		return -EIO;
-	}
-
-	/* determine by signature whether we have ATA or ATAPI devices */
-	classes[0] = ata_sff_dev_classify(&ap->link.device[0],
-					  devmask & (1 << 0), &err);
-	if (slave_possible && err != 0x81)
-		classes[1] = ata_sff_dev_classify(&ap->link.device[1],
-						  devmask & (1 << 1), &err);
-
-	DPRINTK("EXIT, classes[0]=%u [1]=%u\n", classes[0], classes[1]);
-	return 0;
-}
-
-/**
- *	scc_bmdma_stop - Stop PCI IDE BMDMA transfer
- *	@qc: Command we are ending DMA for
- */
-
-static void scc_bmdma_stop (struct ata_queued_cmd *qc)
-{
-	struct ata_port *ap = qc->ap;
-	void __iomem *ctrl_base = ap->host->iomap[SCC_CTRL_BAR];
-	void __iomem *bmid_base = ap->host->iomap[SCC_BMID_BAR];
-	u32 reg;
-
-	while (1) {
-		reg = in_be32(bmid_base + SCC_DMA_INTST);
-
-		if (reg & INTSTS_SERROR) {
-			printk(KERN_WARNING "%s: SERROR\n", DRV_NAME);
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_SERROR|INTSTS_BMSINT);
-			out_be32(bmid_base + SCC_DMA_CMD,
-				 in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-			continue;
-		}
-
-		if (reg & INTSTS_PRERR) {
-			u32 maea0, maec0;
-			maea0 = in_be32(ctrl_base + SCC_CTL_MAEA0);
-			maec0 = in_be32(ctrl_base + SCC_CTL_MAEC0);
-			printk(KERN_WARNING "%s: PRERR [addr:%x cmd:%x]\n", DRV_NAME, maea0, maec0);
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_PRERR|INTSTS_BMSINT);
-			out_be32(bmid_base + SCC_DMA_CMD,
-				 in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-			continue;
-		}
-
-		if (reg & INTSTS_RERR) {
-			printk(KERN_WARNING "%s: Response Error\n", DRV_NAME);
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_RERR|INTSTS_BMSINT);
-			out_be32(bmid_base + SCC_DMA_CMD,
-				 in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-			continue;
-		}
-
-		if (reg & INTSTS_ICERR) {
-			out_be32(bmid_base + SCC_DMA_CMD,
-				 in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-			printk(KERN_WARNING "%s: Illegal Configuration\n", DRV_NAME);
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_ICERR|INTSTS_BMSINT);
-			continue;
-		}
-
-		if (reg & INTSTS_BMSINT) {
-			unsigned int classes;
-			unsigned long deadline = ata_deadline(jiffies, ATA_TMOUT_BOOT);
-			printk(KERN_WARNING "%s: Internal Bus Error\n", DRV_NAME);
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_BMSINT);
-			/* TBD: SW reset */
-			scc_softreset(&ap->link, &classes, deadline);
-			continue;
-		}
-
-		if (reg & INTSTS_BMHE) {
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_BMHE);
-			continue;
-		}
-
-		if (reg & INTSTS_ACTEINT) {
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_ACTEINT);
-			continue;
-		}
-
-		if (reg & INTSTS_IOIRQS) {
-			out_be32(bmid_base + SCC_DMA_INTST, INTSTS_IOIRQS);
-			continue;
-		}
-		break;
-	}
-
-	/* clear start/stop bit */
-	out_be32(bmid_base + SCC_DMA_CMD,
-		 in_be32(bmid_base + SCC_DMA_CMD) & ~ATA_DMA_START);
-
-	/* one-PIO-cycle guaranteed wait, per spec, for HDMA1:0 transition */
-	ata_sff_dma_pause(ap);	/* dummy read */
-}
-
-/**
- *	scc_bmdma_status - Read PCI IDE BMDMA status
- *	@ap: Port associated with this ATA transaction.
- */
-
-static u8 scc_bmdma_status (struct ata_port *ap)
-{
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-	u8 host_stat = in_be32(mmio + SCC_DMA_STATUS);
-	u32 int_status = in_be32(mmio + SCC_DMA_INTST);
-	struct ata_queued_cmd *qc = ata_qc_from_tag(ap, ap->link.active_tag);
-	static int retry = 0;
-
-	/* return if IOS_SS is cleared */
-	if (!(in_be32(mmio + SCC_DMA_CMD) & ATA_DMA_START))
-		return host_stat;
-
-	/* errata A252,A308 workaround: Step4 */
-	if ((scc_check_altstatus(ap) & ATA_ERR)
-					&& (int_status & INTSTS_INTRQ))
-		return (host_stat | ATA_DMA_INTR);
-
-	/* errata A308 workaround Step5 */
-	if (int_status & INTSTS_IOIRQS) {
-		host_stat |= ATA_DMA_INTR;
-
-		/* We don't check ATAPI DMA because it is limited to UDMA4 */
-		if ((qc->tf.protocol == ATA_PROT_DMA &&
-		     qc->dev->xfer_mode > XFER_UDMA_4)) {
-			if (!(int_status & INTSTS_ACTEINT)) {
-				printk(KERN_WARNING "ata%u: operation failed (transfer data loss)\n",
-				       ap->print_id);
-				host_stat |= ATA_DMA_ERR;
-				if (retry++)
-					ap->udma_mask &= ~(1 << qc->dev->xfer_mode);
-			} else
-				retry = 0;
-		}
-	}
-
-	return host_stat;
-}
-
-/**
- *	scc_data_xfer - Transfer data by PIO
- *	@dev: device for this I/O
- *	@buf: data buffer
- *	@buflen: buffer length
- *	@rw: read/write
- *
- *	Note: Original code is ata_sff_data_xfer().
- */
-
-static unsigned int scc_data_xfer (struct ata_device *dev, unsigned char *buf,
-				   unsigned int buflen, int rw)
-{
-	struct ata_port *ap = dev->link->ap;
-	unsigned int words = buflen >> 1;
-	unsigned int i;
-	__le16 *buf16 = (__le16 *) buf;
-	void __iomem *mmio = ap->ioaddr.data_addr;
-
-	/* Transfer multiple of 2 bytes */
-	if (rw == READ)
-		for (i = 0; i < words; i++)
-			buf16[i] = cpu_to_le16(in_be32(mmio));
-	else
-		for (i = 0; i < words; i++)
-			out_be32(mmio, le16_to_cpu(buf16[i]));
-
-	/* Transfer trailing 1 byte, if any. */
-	if (unlikely(buflen & 0x01)) {
-		__le16 align_buf[1] = { 0 };
-		unsigned char *trailing_buf = buf + buflen - 1;
-
-		if (rw == READ) {
-			align_buf[0] = cpu_to_le16(in_be32(mmio));
-			memcpy(trailing_buf, align_buf, 1);
-		} else {
-			memcpy(align_buf, trailing_buf, 1);
-			out_be32(mmio, le16_to_cpu(align_buf[0]));
-		}
-		words++;
-	}
-
-	return words << 1;
-}
-
-/**
- *	scc_postreset - standard postreset callback
- *	@ap: the target ata_port
- *	@classes: classes of attached devices
- *
- *	Note: Original code is ata_sff_postreset().
- */
-
-static void scc_postreset(struct ata_link *link, unsigned int *classes)
-{
-	struct ata_port *ap = link->ap;
-
-	DPRINTK("ENTER\n");
-
-	/* is double-select really necessary? */
-	if (classes[0] != ATA_DEV_NONE)
-		ap->ops->sff_dev_select(ap, 1);
-	if (classes[1] != ATA_DEV_NONE)
-		ap->ops->sff_dev_select(ap, 0);
-
-	/* bail out if no device is present */
-	if (classes[0] == ATA_DEV_NONE && classes[1] == ATA_DEV_NONE) {
-		DPRINTK("EXIT, no device\n");
-		return;
-	}
-
-	/* set up device control */
-	out_be32(ap->ioaddr.ctl_addr, ap->ctl);
-
-	DPRINTK("EXIT\n");
-}
-
-/**
- *	scc_irq_clear - Clear PCI IDE BMDMA interrupt.
- *	@ap: Port associated with this ATA transaction.
- *
- *	Note: Original code is ata_bmdma_irq_clear().
- */
-
-static void scc_irq_clear (struct ata_port *ap)
-{
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
-	if (!mmio)
-		return;
-
-	out_be32(mmio + SCC_DMA_STATUS, in_be32(mmio + SCC_DMA_STATUS));
-}
-
-/**
- *	scc_port_start - Set port up for dma.
- *	@ap: Port to initialize
- *
- *	Allocate space for PRD table using ata_bmdma_port_start().
- *	Set PRD table address for PTERADD. (PRD Transfer End Read)
- */
-
-static int scc_port_start (struct ata_port *ap)
-{
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-	int rc;
-
-	rc = ata_bmdma_port_start(ap);
-	if (rc)
-		return rc;
-
-	out_be32(mmio + SCC_DMA_PTERADD, ap->bmdma_prd_dma);
-	return 0;
-}
-
-/**
- *	scc_port_stop - Undo scc_port_start()
- *	@ap: Port to shut down
- *
- *	Reset PTERADD.
- */
-
-static void scc_port_stop (struct ata_port *ap)
-{
-	void __iomem *mmio = ap->ioaddr.bmdma_addr;
-
-	out_be32(mmio + SCC_DMA_PTERADD, 0);
-}
-
-static struct scsi_host_template scc_sht = {
-	ATA_BMDMA_SHT(DRV_NAME),
-};
-
-static struct ata_port_operations scc_pata_ops = {
-	.inherits		= &ata_bmdma_port_ops,
-
-	.set_piomode		= scc_set_piomode,
-	.set_dmamode		= scc_set_dmamode,
-	.mode_filter		= scc_mode_filter,
-
-	.sff_tf_load		= scc_tf_load,
-	.sff_tf_read		= scc_tf_read,
-	.sff_exec_command	= scc_exec_command,
-	.sff_check_status	= scc_check_status,
-	.sff_check_altstatus	= scc_check_altstatus,
-	.sff_dev_select		= scc_dev_select,
-	.sff_set_devctl		= scc_set_devctl,
-
-	.bmdma_setup		= scc_bmdma_setup,
-	.bmdma_start		= scc_bmdma_start,
-	.bmdma_stop		= scc_bmdma_stop,
-	.bmdma_status		= scc_bmdma_status,
-	.sff_data_xfer		= scc_data_xfer,
-
-	.cable_detect		= ata_cable_80wire,
-	.softreset		= scc_softreset,
-	.postreset		= scc_postreset,
-
-	.sff_irq_clear		= scc_irq_clear,
-
-	.port_start		= scc_port_start,
-	.port_stop		= scc_port_stop,
-};
-
-static struct ata_port_info scc_port_info[] = {
-	{
-		.flags		= ATA_FLAG_SLAVE_POSS,
-		.pio_mask	= ATA_PIO4,
-		/* No MWDMA */
-		.udma_mask	= ATA_UDMA6,
-		.port_ops	= &scc_pata_ops,
-	},
-};
-
-/**
- *	scc_reset_controller - initialize SCC PATA controller.
- */
-
-static int scc_reset_controller(struct ata_host *host)
-{
-	void __iomem *ctrl_base = host->iomap[SCC_CTRL_BAR];
-	void __iomem *bmid_base = host->iomap[SCC_BMID_BAR];
-	void __iomem *cckctrl_port = ctrl_base + SCC_CTL_CCKCTRL;
-	void __iomem *mode_port = ctrl_base + SCC_CTL_MODEREG;
-	void __iomem *ecmode_port = ctrl_base + SCC_CTL_ECMODE;
-	void __iomem *intmask_port = bmid_base + SCC_DMA_INTMASK;
-	void __iomem *dmastatus_port = bmid_base + SCC_DMA_STATUS;
-	u32 reg = 0;
-
-	out_be32(cckctrl_port, reg);
-	reg |= CCKCTRL_ATACLKOEN;
-	out_be32(cckctrl_port, reg);
-	reg |= CCKCTRL_LCLKEN | CCKCTRL_OCLKEN;
-	out_be32(cckctrl_port, reg);
-	reg |= CCKCTRL_CRST;
-	out_be32(cckctrl_port, reg);
-
-	for (;;) {
-		reg = in_be32(cckctrl_port);
-		if (reg & CCKCTRL_CRST)
-			break;
-		udelay(5000);
-	}
-
-	reg |= CCKCTRL_ATARESET;
-	out_be32(cckctrl_port, reg);
-	out_be32(ecmode_port, ECMODE_VALUE);
-	out_be32(mode_port, MODE_JCUSFEN);
-	out_be32(intmask_port, INTMASK_MSK);
-
-	if (in_be32(dmastatus_port) & QCHSD_STPDIAG) {
-		printk(KERN_WARNING "%s: failed to detect 80c cable. (PDIAG# is high)\n", DRV_NAME);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/**
- *	scc_setup_ports - initialize ioaddr with SCC PATA port offsets.
- *	@ioaddr: IO address structure to be initialized
- *	@base: base address of BMID region
- */
-
-static void scc_setup_ports (struct ata_ioports *ioaddr, void __iomem *base)
-{
-	ioaddr->cmd_addr = base + SCC_REG_CMD_ADDR;
-	ioaddr->altstatus_addr = ioaddr->cmd_addr + SCC_REG_ALTSTATUS;
-	ioaddr->ctl_addr = ioaddr->cmd_addr + SCC_REG_ALTSTATUS;
-	ioaddr->bmdma_addr = base;
-	ioaddr->data_addr = ioaddr->cmd_addr + SCC_REG_DATA;
-	ioaddr->error_addr = ioaddr->cmd_addr + SCC_REG_ERR;
-	ioaddr->feature_addr = ioaddr->cmd_addr + SCC_REG_FEATURE;
-	ioaddr->nsect_addr = ioaddr->cmd_addr + SCC_REG_NSECT;
-	ioaddr->lbal_addr = ioaddr->cmd_addr + SCC_REG_LBAL;
-	ioaddr->lbam_addr = ioaddr->cmd_addr + SCC_REG_LBAM;
-	ioaddr->lbah_addr = ioaddr->cmd_addr + SCC_REG_LBAH;
-	ioaddr->device_addr = ioaddr->cmd_addr + SCC_REG_DEVICE;
-	ioaddr->status_addr = ioaddr->cmd_addr + SCC_REG_STATUS;
-	ioaddr->command_addr = ioaddr->cmd_addr + SCC_REG_CMD;
-}
-
-static int scc_host_init(struct ata_host *host)
-{
-	struct pci_dev *pdev = to_pci_dev(host->dev);
-	int rc;
-
-	rc = scc_reset_controller(host);
-	if (rc)
-		return rc;
-
-	rc = dma_set_mask(&pdev->dev, ATA_DMA_MASK);
-	if (rc)
-		return rc;
-	rc = dma_set_coherent_mask(&pdev->dev, ATA_DMA_MASK);
-	if (rc)
-		return rc;
-
-	scc_setup_ports(&host->ports[0]->ioaddr, host->iomap[SCC_BMID_BAR]);
-
-	pci_set_master(pdev);
-
-	return 0;
-}
-
-/**
- *	scc_init_one - Register SCC PATA device with kernel services
- *	@pdev: PCI device to register
- *	@ent: Entry in scc_pci_tbl matching with @pdev
- *
- *	LOCKING:
- *	Inherited from PCI layer (may sleep).
- *
- *	RETURNS:
- *	Zero on success, or -ERRNO value.
- */
-
-static int scc_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
-{
-	unsigned int board_idx = (unsigned int) ent->driver_data;
-	const struct ata_port_info *ppi[] = { &scc_port_info[board_idx], NULL };
-	struct ata_host *host;
-	int rc;
-
-	ata_print_version_once(&pdev->dev, DRV_VERSION);
-
-	host = ata_host_alloc_pinfo(&pdev->dev, ppi, 1);
-	if (!host)
-		return -ENOMEM;
-
-	rc = pcim_enable_device(pdev);
-	if (rc)
-		return rc;
-
-	rc = pcim_iomap_regions(pdev, (1 << SCC_CTRL_BAR) | (1 << SCC_BMID_BAR), DRV_NAME);
-	if (rc == -EBUSY)
-		pcim_pin_device(pdev);
-	if (rc)
-		return rc;
-	host->iomap = pcim_iomap_table(pdev);
-
-	ata_port_pbar_desc(host->ports[0], SCC_CTRL_BAR, -1, "ctrl");
-	ata_port_pbar_desc(host->ports[0], SCC_BMID_BAR, -1, "bmid");
-
-	rc = scc_host_init(host);
-	if (rc)
-		return rc;
-
-	return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt,
-				 IRQF_SHARED, &scc_sht);
-}
-
-static struct pci_driver scc_pci_driver = {
-	.name			= DRV_NAME,
-	.id_table		= scc_pci_tbl,
-	.probe			= scc_init_one,
-	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM_SLEEP
-	.suspend		= ata_pci_device_suspend,
-	.resume			= ata_pci_device_resume,
-#endif
-};
-
-module_pci_driver(scc_pci_driver);
-
-MODULE_AUTHOR("Toshiba corp");
-MODULE_DESCRIPTION("SCSI low-level driver for Toshiba SCC PATA controller");
-MODULE_LICENSE("GPL");
-MODULE_DEVICE_TABLE(pci, scc_pci_tbl);
-MODULE_VERSION(DRV_VERSION);
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 93dca2e73bf5..a8da3a50e374 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -116,8 +116,8 @@ static bool disable64;
 static short nvpibits = -1;
 static short nvcibits = -1;
 static short rx_skb_reserve = 16;
-static bool irq_coalesce = 1;
-static bool sdh = 0;
+static bool irq_coalesce = true;
+static bool sdh;
 
 /* Read from EEPROM = 0000 0011b */
 static unsigned int readtab[] = {
diff --git a/drivers/atm/idt77105.c b/drivers/atm/idt77105.c
index 909c95bd7be2..feb023d7eebd 100644
--- a/drivers/atm/idt77105.c
+++ b/drivers/atm/idt77105.c
@@ -306,14 +306,12 @@ static int idt77105_start(struct atm_dev *dev)
 	if (start_timer) {
 		start_timer = 0;
                 
-		init_timer(&stats_timer);
+		setup_timer(&stats_timer, idt77105_stats_timer_func, 0UL);
 		stats_timer.expires = jiffies+IDT77105_STATS_TIMER_PERIOD;
-		stats_timer.function = idt77105_stats_timer_func;
 		add_timer(&stats_timer);
                 
-		init_timer(&restart_timer);
+		setup_timer(&restart_timer, idt77105_restart_timer_func, 0UL);
 		restart_timer.expires = jiffies+IDT77105_RESTART_TIMER_PERIOD;
-		restart_timer.function = idt77105_restart_timer_func;
 		add_timer(&restart_timer);
 	}
 	spin_unlock_irqrestore(&idt77105_priv_lock, flags);
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 924f8e26789d..65e65903faa0 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -2618,7 +2618,7 @@ static void ia_close(struct atm_vcc *vcc)
         if (vcc->qos.txtp.traffic_class != ATM_NONE) {
            iadev->close_pending++;
 	   prepare_to_wait(&iadev->timeout_wait, &wait, TASK_UNINTERRUPTIBLE);
-	   schedule_timeout(50);
+	   schedule_timeout(msecs_to_jiffies(500));
 	   finish_wait(&iadev->timeout_wait, &wait);
            spin_lock_irqsave(&iadev->tx_lock, flags); 
            while((skb = skb_dequeue(&iadev->tx_backlog))) {
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 9c2ba1c97c42..df0c66cb7ad3 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -179,7 +179,7 @@ static int detect_cache_attributes(unsigned int cpu)
 {
 	int ret;
 
-	if (init_cache_level(cpu))
+	if (init_cache_level(cpu) || !cache_leaves(cpu))
 		return -ENOENT;
 
 	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
diff --git a/drivers/base/init.c b/drivers/base/init.c
index da033d3bab3c..48c0e220acc0 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -8,6 +8,7 @@
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/memory.h>
+#include <linux/of.h>
 
 #include "base.h"
 
@@ -34,4 +35,5 @@ void __init driver_init(void)
 	cpu_dev_init();
 	memory_dev_init();
 	container_dev_init();
+	of_core_init();
 }
diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index 1cb8544598d5..f94a6ccfe787 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o wakeirq.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_OPP)	+= opp.o
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 7fdd0172605a..acef9f9f759a 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -15,6 +15,7 @@
 #include <linux/clkdev.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/pm_runtime.h>
 
 #ifdef CONFIG_PM
 
@@ -67,7 +68,8 @@ static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
 	} else {
 		clk_prepare(ce->clk);
 		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+		dev_dbg(dev, "Clock %pC con_id %s managed by runtime PM.\n",
+			ce->clk, ce->con_id);
 	}
 }
 
@@ -93,7 +95,7 @@ static int __pm_clk_add(struct device *dev, const char *con_id,
 			return -ENOMEM;
 		}
 	} else {
-		if (IS_ERR(ce->clk) || !__clk_get(clk)) {
+		if (IS_ERR(clk) || !__clk_get(clk)) {
 			kfree(ce);
 			return -ENOENT;
 		}
@@ -367,6 +369,43 @@ static int pm_clk_notify(struct notifier_block *nb,
 	return 0;
 }
 
+int pm_clk_runtime_suspend(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_generic_runtime_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend device\n");
+		return ret;
+	}
+
+	ret = pm_clk_suspend(dev);
+	if (ret) {
+		dev_err(dev, "failed to suspend clock\n");
+		pm_generic_runtime_resume(dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+int pm_clk_runtime_resume(struct device *dev)
+{
+	int ret;
+
+	dev_dbg(dev, "%s\n", __func__);
+
+	ret = pm_clk_resume(dev);
+	if (ret) {
+		dev_err(dev, "failed to resume clock\n");
+		return ret;
+	}
+
+	return pm_generic_runtime_resume(dev);
+}
+
 #else /* !CONFIG_PM */
 
 /**
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2327613d4539..cdd547bd67df 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -181,7 +181,7 @@ static void genpd_recalc_cpu_exit_latency(struct generic_pm_domain *genpd)
 	genpd->cpuidle_data->idle_state->exit_latency = usecs64;
 }
 
-static int genpd_power_on(struct generic_pm_domain *genpd)
+static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -190,6 +190,9 @@ static int genpd_power_on(struct generic_pm_domain *genpd)
 	if (!genpd->power_on)
 		return 0;
 
+	if (!timed)
+		return genpd->power_on(genpd);
+
 	time_start = ktime_get();
 	ret = genpd->power_on(genpd);
 	if (ret)
@@ -208,7 +211,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd)
 	return ret;
 }
 
-static int genpd_power_off(struct generic_pm_domain *genpd)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 {
 	ktime_t time_start;
 	s64 elapsed_ns;
@@ -217,6 +220,9 @@ static int genpd_power_off(struct generic_pm_domain *genpd)
 	if (!genpd->power_off)
 		return 0;
 
+	if (!timed)
+		return genpd->power_off(genpd);
+
 	time_start = ktime_get();
 	ret = genpd->power_off(genpd);
 	if (ret == -EBUSY)
@@ -305,7 +311,7 @@ static int __pm_genpd_poweron(struct generic_pm_domain *genpd)
 		}
 	}
 
-	ret = genpd_power_on(genpd);
+	ret = genpd_power_on(genpd, true);
 	if (ret)
 		goto err;
 
@@ -615,7 +621,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd)
 		 * the pm_genpd_poweron() restore power for us (this shouldn't
 		 * happen very often).
 		 */
-		ret = genpd_power_off(genpd);
+		ret = genpd_power_off(genpd, true);
 		if (ret == -EBUSY) {
 			genpd_set_active(genpd);
 			goto out;
@@ -827,6 +833,7 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 /**
  * pm_genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
+ * @timed: True if latency measurements are allowed.
  *
  * Check if the given PM domain can be powered off (during system suspend or
  * hibernation) and do that if so.  Also, in that case propagate to its masters.
@@ -836,7 +843,8 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
  * executed sequentially, so it is guaranteed that it will never run twice in
  * parallel).
  */
-static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
+static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd,
+				   bool timed)
 {
 	struct gpd_link *link;
 
@@ -847,26 +855,28 @@ static void pm_genpd_sync_poweroff(struct generic_pm_domain *genpd)
 	    || atomic_read(&genpd->sd_count) > 0)
 		return;
 
-	genpd_power_off(genpd);
+	genpd_power_off(genpd, timed);
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
-		pm_genpd_sync_poweroff(link->master);
+		pm_genpd_sync_poweroff(link->master, timed);
 	}
 }
 
 /**
  * pm_genpd_sync_poweron - Synchronously power on a PM domain and its masters.
  * @genpd: PM domain to power on.
+ * @timed: True if latency measurements are allowed.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
  * transitions, so it need not acquire locks (all of the "noirq" callbacks are
  * executed sequentially, so it is guaranteed that it will never run twice in
  * parallel).
  */
-static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd)
+static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd,
+				  bool timed)
 {
 	struct gpd_link *link;
 
@@ -874,11 +884,11 @@ static void pm_genpd_sync_poweron(struct generic_pm_domain *genpd)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		pm_genpd_sync_poweron(link->master);
+		pm_genpd_sync_poweron(link->master, timed);
 		genpd_sd_counter_inc(link->master);
 	}
 
-	genpd_power_on(genpd);
+	genpd_power_on(genpd, timed);
 
 	genpd->status = GPD_STATE_ACTIVE;
 }
@@ -1056,7 +1066,7 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 	 * the same PM domain, so it is not necessary to use locking here.
 	 */
 	genpd->suspended_count++;
-	pm_genpd_sync_poweroff(genpd);
+	pm_genpd_sync_poweroff(genpd, true);
 
 	return 0;
 }
@@ -1086,7 +1096,7 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	 * guaranteed that this function will never run twice in parallel for
 	 * the same PM domain, so it is not necessary to use locking here.
 	 */
-	pm_genpd_sync_poweron(genpd);
+	pm_genpd_sync_poweron(genpd, true);
 	genpd->suspended_count--;
 
 	return genpd_start_dev(genpd, dev);
@@ -1300,7 +1310,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 			 * If the domain was off before the hibernation, make
 			 * sure it will be off going forward.
 			 */
-			genpd_power_off(genpd);
+			genpd_power_off(genpd, true);
 
 			return 0;
 		}
@@ -1309,7 +1319,7 @@ static int pm_genpd_restore_noirq(struct device *dev)
 	if (genpd->suspend_power_off)
 		return 0;
 
-	pm_genpd_sync_poweron(genpd);
+	pm_genpd_sync_poweron(genpd, true);
 
 	return genpd_start_dev(genpd, dev);
 }
@@ -1367,9 +1377,9 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 
 	if (suspend) {
 		genpd->suspended_count++;
-		pm_genpd_sync_poweroff(genpd);
+		pm_genpd_sync_poweroff(genpd, false);
 	} else {
-		pm_genpd_sync_poweron(genpd);
+		pm_genpd_sync_poweron(genpd, false);
 		genpd->suspended_count--;
 	}
 }
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 3d874eca7104..30b7bbfdc558 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -24,6 +24,7 @@
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm-trace.h>
+#include <linux/pm_wakeirq.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/async.h>
@@ -587,6 +588,7 @@ void dpm_resume_noirq(pm_message_t state)
 	async_synchronize_full();
 	dpm_show_time(starttime, state, "noirq");
 	resume_device_irqs();
+	device_wakeup_disarm_wake_irqs();
 	cpuidle_resume();
 	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
 }
@@ -920,9 +922,7 @@ static void device_complete(struct device *dev, pm_message_t state)
 
 	if (callback) {
 		pm_dev_dbg(dev, state, info);
-		trace_device_pm_callback_start(dev, info, state.event);
 		callback(dev);
-		trace_device_pm_callback_end(dev, 0);
 	}
 
 	device_unlock(dev);
@@ -954,7 +954,9 @@ void dpm_complete(pm_message_t state)
 		list_move(&dev->power.entry, &list);
 		mutex_unlock(&dpm_list_mtx);
 
+		trace_device_pm_callback_start(dev, "", state.event);
 		device_complete(dev, state);
+		trace_device_pm_callback_end(dev, 0);
 
 		mutex_lock(&dpm_list_mtx);
 		put_device(dev);
@@ -1104,6 +1106,7 @@ int dpm_suspend_noirq(pm_message_t state)
 
 	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
 	cpuidle_pause();
+	device_wakeup_arm_wake_irqs();
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
@@ -1585,11 +1588,8 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		callback = dev->driver->pm->prepare;
 	}
 
-	if (callback) {
-		trace_device_pm_callback_start(dev, info, state.event);
+	if (callback)
 		ret = callback(dev);
-		trace_device_pm_callback_end(dev, ret);
-	}
 
 	device_unlock(dev);
 
@@ -1631,7 +1631,9 @@ int dpm_prepare(pm_message_t state)
 		get_device(dev);
 		mutex_unlock(&dpm_list_mtx);
 
+		trace_device_pm_callback_start(dev, "", state.event);
 		error = device_prepare(dev, state);
+		trace_device_pm_callback_end(dev, error);
 
 		mutex_lock(&dpm_list_mtx);
 		if (error) {
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index b6b8a273c5da..f1a5d95e7b20 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -20,6 +20,46 @@ static inline void pm_runtime_early_init(struct device *dev)
 extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
+struct wake_irq {
+	struct device *dev;
+	int irq;
+	bool dedicated_irq:1;
+};
+
+extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+
+#ifdef CONFIG_PM_SLEEP
+
+extern int device_wakeup_attach_irq(struct device *dev,
+				    struct wake_irq *wakeirq);
+extern void device_wakeup_detach_irq(struct device *dev);
+extern void device_wakeup_arm_wake_irqs(void);
+extern void device_wakeup_disarm_wake_irqs(void);
+
+#else
+
+static inline int
+device_wakeup_attach_irq(struct device *dev,
+			 struct wake_irq *wakeirq)
+{
+	return 0;
+}
+
+static inline void device_wakeup_detach_irq(struct device *dev)
+{
+}
+
+static inline void device_wakeup_arm_wake_irqs(void)
+{
+}
+
+static inline void device_wakeup_disarm_wake_irqs(void)
+{
+}
+
+#endif /* CONFIG_PM_SLEEP */
+
 /*
  * sysfs.c
  */
@@ -52,6 +92,14 @@ static inline void wakeup_sysfs_remove(struct device *dev) {}
 static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
 static inline void pm_qos_sysfs_remove(struct device *dev) {}
 
+static inline void dev_pm_arm_wake_irq(struct wake_irq *wirq)
+{
+}
+
+static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
+{
+}
+
 #endif
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 5070c4fe8542..e1a10a03df8e 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <linux/export.h>
 #include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
 #include <trace/events/rpm.h>
 #include "power.h"
 
@@ -514,6 +515,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
+	dev_pm_enable_wake_irq(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval)
 		goto fail;
@@ -552,6 +554,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	return retval;
 
  fail:
+	dev_pm_disable_wake_irq(dev);
 	__update_runtime_status(dev, RPM_ACTIVE);
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -734,13 +737,16 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
+	dev_pm_disable_wake_irq(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
+		dev_pm_enable_wake_irq(dev);
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);
+		pm_runtime_mark_last_busy(dev);
 		if (parent)
 			atomic_inc(&parent->power.child_count);
 	}
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
new file mode 100644
index 000000000000..7470004ca810
--- /dev/null
+++ b/drivers/base/power/wakeirq.c
@@ -0,0 +1,273 @@
+/*
+ * wakeirq.c - Device wakeirq helper functions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_wakeirq.h>
+
+#include "power.h"
+
+/**
+ * dev_pm_attach_wake_irq - Attach device interrupt as a wake IRQ
+ * @dev: Device entry
+ * @irq: Device wake-up capable interrupt
+ * @wirq: Wake irq specific data
+ *
+ * Internal function to attach either a device IO interrupt or a
+ * dedicated wake-up interrupt as a wake IRQ.
+ */
+static int dev_pm_attach_wake_irq(struct device *dev, int irq,
+				  struct wake_irq *wirq)
+{
+	unsigned long flags;
+	int err;
+
+	if (!dev || !wirq)
+		return -EINVAL;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	if (dev_WARN_ONCE(dev, dev->power.wakeirq,
+			  "wake irq already initialized\n")) {
+		spin_unlock_irqrestore(&dev->power.lock, flags);
+		return -EEXIST;
+	}
+
+	dev->power.wakeirq = wirq;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	err = device_wakeup_attach_irq(dev, wirq);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+/**
+ * dev_pm_set_wake_irq - Attach device IO interrupt as wake IRQ
+ * @dev: Device entry
+ * @irq: Device IO interrupt
+ *
+ * Attach a device IO interrupt as a wake IRQ. The wake IRQ gets
+ * automatically configured for wake-up from suspend  based
+ * on the device specific sysfs wakeup entry. Typically called
+ * during driver probe after calling device_init_wakeup().
+ */
+int dev_pm_set_wake_irq(struct device *dev, int irq)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+
+	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	if (err)
+		kfree(wirq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_wake_irq);
+
+/**
+ * dev_pm_clear_wake_irq - Detach a device IO interrupt wake IRQ
+ * @dev: Device entry
+ *
+ * Detach a device wake IRQ and free resources.
+ *
+ * Note that it's OK for drivers to call this without calling
+ * dev_pm_set_wake_irq() as all the driver instances may not have
+ * a wake IRQ configured. This avoid adding wake IRQ specific
+ * checks into the drivers.
+ */
+void dev_pm_clear_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+	unsigned long flags;
+
+	if (!wirq)
+		return;
+
+	spin_lock_irqsave(&dev->power.lock, flags);
+	dev->power.wakeirq = NULL;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+
+	device_wakeup_detach_irq(dev);
+	if (wirq->dedicated_irq)
+		free_irq(wirq->irq, wirq);
+	kfree(wirq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
+
+/**
+ * handle_threaded_wake_irq - Handler for dedicated wake-up interrupts
+ * @irq: Device specific dedicated wake-up interrupt
+ * @_wirq: Wake IRQ data
+ *
+ * Some devices have a separate wake-up interrupt in addition to the
+ * device IO interrupt. The wake-up interrupt signals that a device
+ * should be woken up from it's idle state. This handler uses device
+ * specific pm_runtime functions to wake the device, and then it's
+ * up to the device to do whatever it needs to. Note that as the
+ * device may need to restore context and start up regulators, we
+ * use a threaded IRQ.
+ *
+ * Also note that we are not resending the lost device interrupts.
+ * We assume that the wake-up interrupt just needs to wake-up the
+ * device, and then device's pm_runtime_resume() can deal with the
+ * situation.
+ */
+static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq)
+{
+	struct wake_irq *wirq = _wirq;
+	int res;
+
+	/* We don't want RPM_ASYNC or RPM_NOWAIT here */
+	res = pm_runtime_resume(wirq->dev);
+	if (res < 0)
+		dev_warn(wirq->dev,
+			 "wake IRQ with no resume: %i\n", res);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt
+ * @dev: Device entry
+ * @irq: Device wake-up interrupt
+ *
+ * Unless your hardware has separate wake-up interrupts in addition
+ * to the device IO interrupts, you don't need this.
+ *
+ * Sets up a threaded interrupt handler for a device that has
+ * a dedicated wake-up interrupt in addition to the device IO
+ * interrupt.
+ *
+ * The interrupt starts disabled, and needs to be managed for
+ * the device by the bus code or the device driver using
+ * dev_pm_enable_wake_irq() and dev_pm_disable_wake_irq()
+ * functions.
+ */
+int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
+{
+	struct wake_irq *wirq;
+	int err;
+
+	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
+	if (!wirq)
+		return -ENOMEM;
+
+	wirq->dev = dev;
+	wirq->irq = irq;
+	wirq->dedicated_irq = true;
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
+
+	/*
+	 * Consumer device may need to power up and restore state
+	 * so we use a threaded irq.
+	 */
+	err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq,
+				   IRQF_ONESHOT, dev_name(dev), wirq);
+	if (err)
+		goto err_free;
+
+	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	if (err)
+		goto err_free_irq;
+
+	return err;
+
+err_free_irq:
+	free_irq(irq, wirq);
+err_free:
+	kfree(wirq);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
+
+/**
+ * dev_pm_enable_wake_irq - Enable device wake-up interrupt
+ * @dev: Device
+ *
+ * Called from the bus code or the device driver for
+ * runtime_suspend() to enable the wake-up interrupt while
+ * the device is running.
+ *
+ * Note that for runtime_suspend()) the wake-up interrupts
+ * should be unconditionally enabled unlike for suspend()
+ * that is conditional.
+ */
+void dev_pm_enable_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (wirq && wirq->dedicated_irq)
+		enable_irq(wirq->irq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
+
+/**
+ * dev_pm_disable_wake_irq - Disable device wake-up interrupt
+ * @dev: Device
+ *
+ * Called from the bus code or the device driver for
+ * runtime_resume() to disable the wake-up interrupt while
+ * the device is running.
+ */
+void dev_pm_disable_wake_irq(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (wirq && wirq->dedicated_irq)
+		disable_irq_nosync(wirq->irq);
+}
+EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq);
+
+/**
+ * dev_pm_arm_wake_irq - Arm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Sets up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_arm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev))
+		enable_irq_wake(wirq->irq);
+}
+
+/**
+ * dev_pm_disarm_wake_irq - Disarm device wake-up
+ * @wirq: Device wake-up interrupt
+ *
+ * Clears up the wake-up event conditionally based on the
+ * device_may_wake().
+ */
+void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
+{
+	if (!wirq)
+		return;
+
+	if (device_may_wakeup(wirq->dev))
+		disable_irq_wake(wirq->irq);
+}
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 77262009f89d..40f71603378c 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -14,6 +14,7 @@
 #include <linux/suspend.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/pm_wakeirq.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -56,6 +57,11 @@ static LIST_HEAD(wakeup_sources);
 
 static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue);
 
+static struct wakeup_source deleted_ws = {
+	.name = "deleted",
+	.lock =  __SPIN_LOCK_UNLOCKED(deleted_ws.lock),
+};
+
 /**
  * wakeup_source_prepare - Prepare a new wakeup source for initialization.
  * @ws: Wakeup source to prepare.
@@ -107,6 +113,34 @@ void wakeup_source_drop(struct wakeup_source *ws)
 }
 EXPORT_SYMBOL_GPL(wakeup_source_drop);
 
+/*
+ * Record wakeup_source statistics being deleted into a dummy wakeup_source.
+ */
+static void wakeup_source_record(struct wakeup_source *ws)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&deleted_ws.lock, flags);
+
+	if (ws->event_count) {
+		deleted_ws.total_time =
+			ktime_add(deleted_ws.total_time, ws->total_time);
+		deleted_ws.prevent_sleep_time =
+			ktime_add(deleted_ws.prevent_sleep_time,
+				  ws->prevent_sleep_time);
+		deleted_ws.max_time =
+			ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ?
+				deleted_ws.max_time : ws->max_time;
+		deleted_ws.event_count += ws->event_count;
+		deleted_ws.active_count += ws->active_count;
+		deleted_ws.relax_count += ws->relax_count;
+		deleted_ws.expire_count += ws->expire_count;
+		deleted_ws.wakeup_count += ws->wakeup_count;
+	}
+
+	spin_unlock_irqrestore(&deleted_ws.lock, flags);
+}
+
 /**
  * wakeup_source_destroy - Destroy a struct wakeup_source object.
  * @ws: Wakeup source to destroy.
@@ -119,6 +153,7 @@ void wakeup_source_destroy(struct wakeup_source *ws)
 		return;
 
 	wakeup_source_drop(ws);
+	wakeup_source_record(ws);
 	kfree(ws->name);
 	kfree(ws);
 }
@@ -239,6 +274,97 @@ int device_wakeup_enable(struct device *dev)
 EXPORT_SYMBOL_GPL(device_wakeup_enable);
 
 /**
+ * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source
+ * @dev: Device to handle
+ * @wakeirq: Device specific wakeirq entry
+ *
+ * Attach a device wakeirq to the wakeup source so the device
+ * wake IRQ can be configured automatically for suspend and
+ * resume.
+ */
+int device_wakeup_attach_irq(struct device *dev,
+			     struct wake_irq *wakeirq)
+{
+	struct wakeup_source *ws;
+	int ret = 0;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	if (!ws) {
+		dev_err(dev, "forgot to call call device_init_wakeup?\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (ws->wakeirq) {
+		ret = -EEXIST;
+		goto unlock;
+	}
+
+	ws->wakeirq = wakeirq;
+
+unlock:
+	spin_unlock_irq(&dev->power.lock);
+
+	return ret;
+}
+
+/**
+ * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source
+ * @dev: Device to handle
+ *
+ * Removes a device wakeirq from the wakeup source.
+ */
+void device_wakeup_detach_irq(struct device *dev)
+{
+	struct wakeup_source *ws;
+
+	spin_lock_irq(&dev->power.lock);
+	ws = dev->power.wakeup;
+	if (!ws)
+		goto unlock;
+
+	ws->wakeirq = NULL;
+
+unlock:
+	spin_unlock_irq(&dev->power.lock);
+}
+
+/**
+ * device_wakeup_arm_wake_irqs(void)
+ *
+ * Itereates over the list of device wakeirqs to arm them.
+ */
+void device_wakeup_arm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->wakeirq)
+			dev_pm_arm_wake_irq(ws->wakeirq);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * device_wakeup_disarm_wake_irqs(void)
+ *
+ * Itereates over the list of device wakeirqs to disarm them.
+ */
+void device_wakeup_disarm_wake_irqs(void)
+{
+	struct wakeup_source *ws;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (ws->wakeirq)
+			dev_pm_disarm_wake_irq(ws->wakeirq);
+	}
+	rcu_read_unlock();
+}
+
+/**
  * device_wakeup_detach - Detach a device's wakeup source object from it.
  * @dev: Device to detach the wakeup source object from.
  *
@@ -351,6 +477,20 @@ int device_set_wakeup_enable(struct device *dev, bool enable)
 }
 EXPORT_SYMBOL_GPL(device_set_wakeup_enable);
 
+/**
+ * wakeup_source_not_registered - validate the given wakeup source.
+ * @ws: Wakeup source to be validated.
+ */
+static bool wakeup_source_not_registered(struct wakeup_source *ws)
+{
+	/*
+	 * Use timer struct to check if the given source is initialized
+	 * by wakeup_source_add.
+	 */
+	return ws->timer.function != pm_wakeup_timer_fn ||
+		   ws->timer.data != (unsigned long)ws;
+}
+
 /*
  * The functions below use the observation that each wakeup event starts a
  * period in which the system should not be suspended.  The moment this period
@@ -391,6 +531,10 @@ static void wakeup_source_activate(struct wakeup_source *ws)
 {
 	unsigned int cec;
 
+	if (WARN_ONCE(wakeup_source_not_registered(ws),
+			"unregistered wakeup source\n"))
+		return;
+
 	/*
 	 * active wakeup source should bring the system
 	 * out of PM_SUSPEND_FREEZE state
@@ -894,6 +1038,8 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
 		print_wakeup_source_stats(m, ws);
 	rcu_read_unlock();
 
+	print_wakeup_source_stats(m, &deleted_ws);
+
 	return 0;
 }
 
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 1d0b116cae95..e645852396ba 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/property.h>
 
 /**
@@ -519,3 +520,16 @@ unsigned int device_get_child_node_count(struct device *dev)
 	return count;
 }
 EXPORT_SYMBOL_GPL(device_get_child_node_count);
+
+bool device_dma_is_coherent(struct device *dev)
+{
+	bool coherent = false;
+
+	if (IS_ENABLED(CONFIG_OF) && dev->of_node)
+		coherent = of_dma_is_coherent(dev->of_node);
+	else
+		acpi_check_dma(ACPI_COMPANION(dev), &coherent);
+
+	return coherent;
+}
+EXPORT_SYMBOL_GPL(device_dma_is_coherent);
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index a13587b5c2be..b2b2849fc6d3 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -131,7 +131,10 @@ struct regmap {
 	struct reg_default *reg_defaults;
 	const void *reg_defaults_raw;
 	void *cache;
+	/* if set, the cache contains newer data than the HW */
 	u32 cache_dirty;
+	/* if set, the HW registers are known to match map->reg_defaults */
+	bool no_sync_defaults;
 
 	struct reg_default *patch;
 	int patch_regs;
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 7eb7b3b98794..b9862d741a56 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -249,6 +249,22 @@ int regcache_write(struct regmap *map,
 	return 0;
 }
 
+static bool regcache_reg_needs_sync(struct regmap *map, unsigned int reg,
+				    unsigned int val)
+{
+	int ret;
+
+	/* If we don't know the chip just got reset, then sync everything. */
+	if (!map->no_sync_defaults)
+		return true;
+
+	/* Is this the hardware default?  If so skip. */
+	ret = regcache_lookup_reg(map, reg);
+	if (ret >= 0 && val == map->reg_defaults[ret].def)
+		return false;
+	return true;
+}
+
 static int regcache_default_sync(struct regmap *map, unsigned int min,
 				 unsigned int max)
 {
@@ -266,9 +282,7 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
 		if (ret)
 			return ret;
 
-		/* Is this the hardware default?  If so skip. */
-		ret = regcache_lookup_reg(map, reg);
-		if (ret >= 0 && val == map->reg_defaults[ret].def)
+		if (!regcache_reg_needs_sync(map, reg, val))
 			continue;
 
 		map->cache_bypass = 1;
@@ -342,6 +356,7 @@ out:
 	/* Restore the bypass state */
 	map->async = false;
 	map->cache_bypass = bypass;
+	map->no_sync_defaults = false;
 	map->unlock(map->lock_arg);
 
 	regmap_async_complete(map);
@@ -397,6 +412,7 @@ out:
 	/* Restore the bypass state */
 	map->cache_bypass = bypass;
 	map->async = false;
+	map->no_sync_defaults = false;
 	map->unlock(map->lock_arg);
 
 	regmap_async_complete(map);
@@ -461,18 +477,23 @@ void regcache_cache_only(struct regmap *map, bool enable)
 EXPORT_SYMBOL_GPL(regcache_cache_only);
 
 /**
- * regcache_mark_dirty: Mark the register cache as dirty
+ * regcache_mark_dirty: Indicate that HW registers were reset to default values
  *
  * @map: map to mark
  *
- * Mark the register cache as dirty, for example due to the device
- * having been powered down for suspend.  If the cache is not marked
- * as dirty then the cache sync will be suppressed.
+ * Inform regcache that the device has been powered down or reset, so that
+ * on resume, regcache_sync() knows to write out all non-default values
+ * stored in the cache.
+ *
+ * If this function is not called, regcache_sync() will assume that
+ * the hardware state still matches the cache state, modulo any writes that
+ * happened when cache_only was true.
  */
 void regcache_mark_dirty(struct regmap *map)
 {
 	map->lock(map->lock_arg);
 	map->cache_dirty = true;
+	map->no_sync_defaults = true;
 	map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_mark_dirty);
@@ -613,10 +634,7 @@ static int regcache_sync_block_single(struct regmap *map, void *block,
 			continue;
 
 		val = regcache_get_val(map, block, i);
-
-		/* Is this the hardware default?  If so skip. */
-		ret = regcache_lookup_reg(map, regtmp);
-		if (ret >= 0 && val == map->reg_defaults[ret].def)
+		if (!regcache_reg_needs_sync(map, regtmp, val))
 			continue;
 
 		map->cache_bypass = 1;
@@ -688,10 +706,7 @@ static int regcache_sync_block_raw(struct regmap *map, void *block,
 		}
 
 		val = regcache_get_val(map, block, i);
-
-		/* Is this the hardware default?  If so skip. */
-		ret = regcache_lookup_reg(map, regtmp);
-		if (ret >= 0 && val == map->reg_defaults[ret].def) {
+		if (!regcache_reg_needs_sync(map, regtmp, val)) {
 			ret = regcache_sync_block_raw_flush(map, &data,
 							    base, regtmp);
 			if (ret != 0)
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index a6c3f75b4b01..2597600a5d26 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -109,7 +109,7 @@ static void regmap_irq_sync_unlock(struct irq_data *data)
 		if (!d->chip->init_ack_masked)
 			continue;
 		/*
-		 * Ack all the masked interrupts uncondictionly,
+		 * Ack all the masked interrupts unconditionally,
 		 * OR if there is masked interrupt which hasn't been Acked,
 		 * it'll be ignored in irq handler, then may introduce irq storm
 		 */
@@ -306,19 +306,12 @@ static int regmap_irq_map(struct irq_domain *h, unsigned int virq,
 	irq_set_chip_data(virq, data);
 	irq_set_chip(virq, &data->irq_chip);
 	irq_set_nested_thread(virq, 1);
-
-	/* ARM needs us to explicitly flag the IRQ as valid
-	 * and will set them noprobe when we do so. */
-#ifdef CONFIG_ARM
-	set_irq_flags(virq, IRQF_VALID);
-#else
 	irq_set_noprobe(virq);
-#endif
 
 	return 0;
 }
 
-static struct irq_domain_ops regmap_domain_ops = {
+static const struct irq_domain_ops regmap_domain_ops = {
 	.map	= regmap_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 6273ff072f3e..7111d04f2621 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -945,11 +945,10 @@ EXPORT_SYMBOL_GPL(devm_regmap_init);
 static void regmap_field_init(struct regmap_field *rm_field,
 	struct regmap *regmap, struct reg_field reg_field)
 {
-	int field_bits = reg_field.msb - reg_field.lsb + 1;
 	rm_field->regmap = regmap;
 	rm_field->reg = reg_field.reg;
 	rm_field->shift = reg_field.lsb;
-	rm_field->mask = ((BIT(field_bits) - 1) << reg_field.lsb);
+	rm_field->mask = GENMASK(reg_field.msb, reg_field.lsb);
 	rm_field->id_size = reg_field.id_size;
 	rm_field->id_offset = reg_field.id_offset;
 }
@@ -2318,7 +2317,7 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 					  &ival);
 			if (ret != 0)
 				return ret;
-			memcpy(val + (i * val_bytes), &ival, val_bytes);
+			map->format.format_val(val + (i * val_bytes), ival, 0);
 		}
 	}
 
@@ -2583,10 +2582,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 	map->async = true;
 
 	ret = _regmap_multi_reg_write(map, regs, num_regs);
-	if (ret != 0)
-		goto out;
 
-out:
 	map->async = false;
 	map->cache_bypass = bypass;
 
@@ -2613,6 +2609,30 @@ int regmap_get_val_bytes(struct regmap *map)
 }
 EXPORT_SYMBOL_GPL(regmap_get_val_bytes);
 
+/**
+ * regmap_get_max_register(): Report the max register value
+ *
+ * Report the max register value, mainly intended to for use by
+ * generic infrastructure built on top of regmap.
+ */
+int regmap_get_max_register(struct regmap *map)
+{
+	return map->max_register ? map->max_register : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(regmap_get_max_register);
+
+/**
+ * regmap_get_reg_stride(): Report the register address stride
+ *
+ * Report the register address stride, mainly intended to for use by
+ * generic infrastructure built on top of regmap.
+ */
+int regmap_get_reg_stride(struct regmap *map)
+{
+	return map->reg_stride;
+}
+EXPORT_SYMBOL_GPL(regmap_get_reg_stride);
+
 int regmap_parse_val(struct regmap *map, const void *buf,
 			unsigned int *val)
 {
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 6491f45200a7..8b7d7f8e5851 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -61,7 +61,7 @@ static DEVICE_ATTR_RO(physical_package_id);
 define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
-define_siblings_show_func(thread_siblings, thread_cpumask);
+define_siblings_show_func(thread_siblings, sibling_cpumask);
 static DEVICE_ATTR_RO(thread_siblings);
 static DEVICE_ATTR_RO(thread_siblings_list);
 
diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index fc6ffcfa8061..be5fffb6da24 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -29,12 +29,6 @@ config BCMA_HOST_PCI
 	select BCMA_DRIVER_PCI
 	default y
 
-config BCMA_DRIVER_PCI_HOSTMODE
-	bool "Driver for PCI core working in hostmode"
-	depends on BCMA && MIPS && BCMA_HOST_PCI
-	help
-	  PCI core hostmode operation (external PCI bus).
-
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
 	depends on BCMA
@@ -61,6 +55,12 @@ config BCMA_DRIVER_PCI
 	  This driver is also prerequisite for a hostmode PCIe core
 	  support.
 
+config BCMA_DRIVER_PCI_HOSTMODE
+	bool "Driver for PCI core working in hostmode"
+	depends on BCMA && MIPS && BCMA_DRIVER_PCI
+	help
+	  PCI core hostmode operation (external PCI bus).
+
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
 	depends on BCMA && MIPS
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index 74ccb02e0f10..5f6018e7cd4c 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -226,6 +226,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 		chip->of_node	= cc->core->dev.of_node;
 #endif
 	switch (bus->chipinfo.id) {
+	case BCMA_CHIP_ID_BCM4707:
 	case BCMA_CHIP_ID_BCM5357:
 	case BCMA_CHIP_ID_BCM53572:
 		chip->ngpio	= 32;
@@ -235,16 +236,17 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	}
 
 	/*
-	 * On MIPS we register GPIO devices (LEDs, buttons) using absolute GPIO
-	 * pin numbers. We don't have Device Tree there and we can't really use
-	 * relative (per chip) numbers.
-	 * So let's use predictable base for BCM47XX and "random" for all other.
+	 * Register SoC GPIO devices with absolute GPIO pin base.
+	 * On MIPS, we don't have Device Tree and we can't use relative (per chip)
+	 * GPIO numbers.
+	 * On some ARM devices, user space may want to access some system GPIO
+	 * pins directly, which is easier to do with a predictable GPIO base.
 	 */
-#if IS_BUILTIN(CONFIG_BCM47XX)
-	chip->base		= bus->num * BCMA_GPIO_MAX_PINS;
-#else
-	chip->base		= -1;
-#endif
+	if (IS_BUILTIN(CONFIG_BCM47XX) ||
+	    cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC)
+		chip->base		= bus->num * BCMA_GPIO_MAX_PINS;
+	else
+		chip->base		= -1;
 
 	err = bcma_gpio_irq_domain_init(cc);
 	if (err)
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index eb1fed5bd516..3ccef9eba6f9 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -406,6 +406,7 @@ config BLK_DEV_RAM_DAX
 
 config BLK_DEV_PMEM
 	tristate "Persistent memory block device support"
+	depends on HAS_IOMEM
 	help
 	  Saying Y here will allow you to use a contiguous range of reserved
 	  memory as one or more persistent block devices.
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index ff20f192b0f6..0422c47261c3 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -139,8 +139,6 @@ static struct board_type products[] = {
 	{0x3214103C, "Smart Array E200i", &SA5_access},
 	{0x3215103C, "Smart Array E200i", &SA5_access},
 	{0x3237103C, "Smart Array E500", &SA5_access},
-	{0x3223103C, "Smart Array P800", &SA5_access},
-	{0x3234103C, "Smart Array P400", &SA5_access},
 	{0x323D103C, "Smart Array P700m", &SA5_access},
 };
 
@@ -574,8 +572,6 @@ static void cciss_procinit(ctlr_info_t *h)
 
 /* List of controllers which cannot be hard reset on kexec with reset_devices */
 static u32 unresettable_controller[] = {
-	0x324a103C, /* Smart Array P712m */
-	0x324b103C, /* SmartArray P711m */
 	0x3223103C, /* Smart Array P800 */
 	0x3234103C, /* Smart Array P400 */
 	0x3235103C, /* Smart Array P400i */
@@ -586,12 +582,32 @@ static u32 unresettable_controller[] = {
 	0x3215103C, /* Smart Array E200i */
 	0x3237103C, /* Smart Array E500 */
 	0x323D103C, /* Smart Array P700m */
+	0x40800E11, /* Smart Array 5i */
 	0x409C0E11, /* Smart Array 6400 */
 	0x409D0E11, /* Smart Array 6400 EM */
+	0x40700E11, /* Smart Array 5300 */
+	0x40820E11, /* Smart Array 532 */
+	0x40830E11, /* Smart Array 5312 */
+	0x409A0E11, /* Smart Array 641 */
+	0x409B0E11, /* Smart Array 642 */
+	0x40910E11, /* Smart Array 6i */
 };
 
 /* List of controllers which cannot even be soft reset */
 static u32 soft_unresettable_controller[] = {
+	0x40800E11, /* Smart Array 5i */
+	0x40700E11, /* Smart Array 5300 */
+	0x40820E11, /* Smart Array 532 */
+	0x40830E11, /* Smart Array 5312 */
+	0x409A0E11, /* Smart Array 641 */
+	0x409B0E11, /* Smart Array 642 */
+	0x40910E11, /* Smart Array 6i */
+	/* Exclude 640x boards.  These are two pci devices in one slot
+	 * which share a battery backed cache module.  One controls the
+	 * cache, the other accesses the cache through the one that controls
+	 * it.  If we reset the one controlling the cache, the other will
+	 * likely not be happy.  Just forbid resetting this conjoined mess.
+	 */
 	0x409C0E11, /* Smart Array 6400 */
 	0x409D0E11, /* Smart Array 6400 EM */
 };
@@ -4667,8 +4683,7 @@ static int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
 	 */
 	cciss_lookup_board_id(pdev, &board_id);
 	if (!ctlr_is_resettable(board_id)) {
-		dev_warn(&pdev->dev, "Cannot reset Smart Array 640x "
-				"due to shared cache module.");
+		dev_warn(&pdev->dev, "Controller not resettable\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index ecd845cd28d8..1537302e56e3 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -84,7 +84,6 @@ static struct scsi_host_template cciss_driver_template = {
 	.show_info		= cciss_scsi_show_info,
 	.queuecommand		= cciss_scsi_queue_command,
 	.this_id		= 7,
-	.cmd_per_lun		= 1,
 	.use_clustering		= DISABLE_CLUSTERING,
 	/* Can't have eh_bus_reset_handler or eh_host_reset_handler for cciss */
 	.eh_device_reset_handler= cciss_eh_device_reset_handler,
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index cee20354ac37..c097909c589c 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -598,7 +598,7 @@ static struct socket *drbd_try_connect(struct drbd_connection *connection)
 	memcpy(&peer_in6, &connection->peer_addr, peer_addr_len);
 
 	what = "sock_create_kern";
-	err = sock_create_kern(((struct sockaddr *)&src_in6)->sa_family,
+	err = sock_create_kern(&init_net, ((struct sockaddr *)&src_in6)->sa_family,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (err < 0) {
 		sock = NULL;
@@ -693,7 +693,7 @@ static int prepare_listen_socket(struct drbd_connection *connection, struct acce
 	memcpy(&my_addr, &connection->my_addr, my_addr_len);
 
 	what = "sock_create_kern";
-	err = sock_create_kern(((struct sockaddr *)&my_addr)->sa_family,
+	err = sock_create_kern(&init_net, ((struct sockaddr *)&my_addr)->sa_family,
 			       SOCK_STREAM, IPPROTO_TCP, &s_listen);
 	if (err) {
 		s_listen = NULL;
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index ae3fcb4199e9..40580dc7f41c 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -86,8 +86,6 @@ static DEFINE_MUTEX(loop_index_mutex);
 static int max_part;
 static int part_shift;
 
-static struct workqueue_struct *loop_wq;
-
 static int transfer_xor(struct loop_device *lo, int cmd,
 			struct page *raw_page, unsigned raw_off,
 			struct page *loop_page, unsigned loop_off,
@@ -476,6 +474,28 @@ static int loop_flush(struct loop_device *lo)
 	return loop_switch(lo, NULL);
 }
 
+static void loop_reread_partitions(struct loop_device *lo,
+				   struct block_device *bdev)
+{
+	int rc;
+
+	/*
+	 * bd_mutex has been held already in release path, so don't
+	 * acquire it if this function is called in such case.
+	 *
+	 * If the reread partition isn't from release path, lo_refcnt
+	 * must be at least one and it can only become zero when the
+	 * current holder is released.
+	 */
+	if (!atomic_read(&lo->lo_refcnt))
+		rc = __blkdev_reread_part(bdev);
+	else
+		rc = blkdev_reread_part(bdev);
+	if (rc)
+		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
+			__func__, lo->lo_number, lo->lo_file_name, rc);
+}
+
 /*
  * loop_change_fd switched the backing store of a loopback device to
  * a new file. This is useful for operating system installers to free up
@@ -524,7 +544,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 
 	fput(old_file);
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
-		ioctl_by_bdev(bdev, BLKRRPART, 0);
+		loop_reread_partitions(lo, bdev);
 	return 0;
 
  out_putf:
@@ -725,6 +745,12 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	size = get_loop_size(lo, file);
 	if ((loff_t)(sector_t)size != size)
 		goto out_putf;
+	error = -ENOMEM;
+	lo->wq = alloc_workqueue("kloopd%d",
+			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16,
+			lo->lo_number);
+	if (!lo->wq)
+		goto out_putf;
 
 	error = 0;
 
@@ -755,7 +781,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (part_shift)
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
-		ioctl_by_bdev(bdev, BLKRRPART, 0);
+		loop_reread_partitions(lo, bdev);
 
 	/* Grab the block_device to prevent its destruction after we
 	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
@@ -827,7 +853,7 @@ static int loop_clr_fd(struct loop_device *lo)
 	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
 	 * command to fail with EBUSY.
 	 */
-	if (lo->lo_refcnt > 1) {
+	if (atomic_read(&lo->lo_refcnt) > 1) {
 		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
 		mutex_unlock(&lo->lo_ctl_mutex);
 		return 0;
@@ -836,6 +862,9 @@ static int loop_clr_fd(struct loop_device *lo)
 	if (filp == NULL)
 		return -EINVAL;
 
+	/* freeze request queue during the transition */
+	blk_mq_freeze_queue(lo->lo_queue);
+
 	spin_lock_irq(&lo->lo_lock);
 	lo->lo_state = Lo_rundown;
 	lo->lo_backing_file = NULL;
@@ -867,11 +896,15 @@ static int loop_clr_fd(struct loop_device *lo)
 	lo->lo_state = Lo_unbound;
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
+	blk_mq_unfreeze_queue(lo->lo_queue);
+
 	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
-		ioctl_by_bdev(bdev, BLKRRPART, 0);
+		loop_reread_partitions(lo, bdev);
 	lo->lo_flags = 0;
 	if (!part_shift)
 		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
+	destroy_workqueue(lo->wq);
+	lo->wq = NULL;
 	mutex_unlock(&lo->lo_ctl_mutex);
 	/*
 	 * Need not hold lo_ctl_mutex to fput backing file.
@@ -943,7 +976,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
 		lo->lo_flags |= LO_FLAGS_PARTSCAN;
 		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
-		ioctl_by_bdev(lo->lo_device, BLKRRPART, 0);
+		loop_reread_partitions(lo, lo->lo_device);
 	}
 
 	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
@@ -1324,9 +1357,7 @@ static int lo_open(struct block_device *bdev, fmode_t mode)
 		goto out;
 	}
 
-	mutex_lock(&lo->lo_ctl_mutex);
-	lo->lo_refcnt++;
-	mutex_unlock(&lo->lo_ctl_mutex);
+	atomic_inc(&lo->lo_refcnt);
 out:
 	mutex_unlock(&loop_index_mutex);
 	return err;
@@ -1337,11 +1368,10 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 	struct loop_device *lo = disk->private_data;
 	int err;
 
-	mutex_lock(&lo->lo_ctl_mutex);
-
-	if (--lo->lo_refcnt)
-		goto out;
+	if (atomic_dec_return(&lo->lo_refcnt))
+		return;
 
+	mutex_lock(&lo->lo_ctl_mutex);
 	if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
 		/*
 		 * In autoclear mode, stop the loop thread
@@ -1358,7 +1388,6 @@ static void lo_release(struct gendisk *disk, fmode_t mode)
 		loop_flush(lo);
 	}
 
-out:
 	mutex_unlock(&lo->lo_ctl_mutex);
 }
 
@@ -1425,9 +1454,13 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+	struct loop_device *lo = cmd->rq->q->queuedata;
 
 	blk_mq_start_request(bd->rq);
 
+	if (lo->lo_state != Lo_bound)
+		return -EIO;
+
 	if (cmd->rq->cmd_flags & REQ_WRITE) {
 		struct loop_device *lo = cmd->rq->q->queuedata;
 		bool need_sched = true;
@@ -1441,9 +1474,9 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		spin_unlock_irq(&lo->lo_lock);
 
 		if (need_sched)
-			queue_work(loop_wq, &lo->write_work);
+			queue_work(lo->wq, &lo->write_work);
 	} else {
-		queue_work(loop_wq, &cmd->read_work);
+		queue_work(lo->wq, &cmd->read_work);
 	}
 
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -1455,9 +1488,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	struct loop_device *lo = cmd->rq->q->queuedata;
 	int ret = -EIO;
 
-	if (lo->lo_state != Lo_bound)
-		goto failed;
-
 	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY))
 		goto failed;
 
@@ -1594,6 +1624,7 @@ static int loop_add(struct loop_device **l, int i)
 		disk->flags |= GENHD_FL_NO_PART_SCAN;
 	disk->flags |= GENHD_FL_EXT_DEVT;
 	mutex_init(&lo->lo_ctl_mutex);
+	atomic_set(&lo->lo_refcnt, 0);
 	lo->lo_number		= i;
 	spin_lock_init(&lo->lo_lock);
 	disk->major		= LOOP_MAJOR;
@@ -1620,8 +1651,8 @@ out:
 
 static void loop_remove(struct loop_device *lo)
 {
-	del_gendisk(lo->lo_disk);
 	blk_cleanup_queue(lo->lo_queue);
+	del_gendisk(lo->lo_disk);
 	blk_mq_free_tag_set(&lo->tag_set);
 	put_disk(lo->lo_disk);
 	kfree(lo);
@@ -1711,7 +1742,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
 			mutex_unlock(&lo->lo_ctl_mutex);
 			break;
 		}
-		if (lo->lo_refcnt > 0) {
+		if (atomic_read(&lo->lo_refcnt) > 0) {
 			ret = -EBUSY;
 			mutex_unlock(&lo->lo_ctl_mutex);
 			break;
@@ -1806,13 +1837,6 @@ static int __init loop_init(void)
 		goto misc_out;
 	}
 
-	loop_wq = alloc_workqueue("kloopd",
-			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0);
-	if (!loop_wq) {
-		err = -ENOMEM;
-		goto misc_out;
-	}
-
 	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
 				  THIS_MODULE, loop_probe, NULL, NULL);
 
@@ -1850,8 +1874,6 @@ static void __exit loop_exit(void)
 	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
 	unregister_blkdev(LOOP_MAJOR, "loop");
 
-	destroy_workqueue(loop_wq);
-
 	misc_deregister(&loop_misc);
 }
 
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 301c27f8323f..25e8997ed246 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -28,7 +28,7 @@ struct loop_func_table;
 
 struct loop_device {
 	int		lo_number;
-	int		lo_refcnt;
+	atomic_t	lo_refcnt;
 	loff_t		lo_offset;
 	loff_t		lo_sizelimit;
 	int		lo_flags;
@@ -54,6 +54,7 @@ struct loop_device {
 	gfp_t		old_gfp_mask;
 
 	spinlock_t		lo_lock;
+	struct workqueue_struct *wq;
 	struct list_head	write_cmd_head;
 	struct work_struct	write_work;
 	bool			write_started;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 3bd7ca9853a8..4a2ef09e6704 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -163,12 +163,6 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 		else
 			dev_warn(&dd->pdev->dev,
 				"%s: dd->queue is NULL\n", __func__);
-		if (dd->port) {
-			set_bit(MTIP_PF_SR_CLEANUP_BIT, &dd->port->flags);
-			wake_up_interruptible(&dd->port->svc_wait);
-		} else
-			dev_warn(&dd->pdev->dev,
-				"%s: dd->port is NULL\n", __func__);
 		return true; /* device removed */
 	}
 
@@ -269,8 +263,11 @@ static int mtip_hba_reset(struct driver_data *dd)
 	/* Flush */
 	readl(dd->mmio + HOST_CTL);
 
-	/* Spin for up to 2 seconds, waiting for reset acknowledgement */
-	timeout = jiffies + msecs_to_jiffies(2000);
+	/*
+	 * Spin for up to 10 seconds waiting for reset acknowledgement. Spec
+	 * is 1 sec but in LUN failure conditions, up to 10 secs are required
+	 */
+	timeout = jiffies + msecs_to_jiffies(10000);
 	do {
 		mdelay(10);
 		if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag))
@@ -623,8 +620,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 
 	set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags);
 
-	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags) &&
-			test_bit(MTIP_TAG_INTERNAL, port->allocated)) {
+	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
 
@@ -896,6 +892,10 @@ static inline irqreturn_t mtip_handle_irq(struct driver_data *data)
 
 		/* Acknowledge the interrupt status on the port.*/
 		port_stat = readl(port->mmio + PORT_IRQ_STAT);
+		if (unlikely(port_stat == 0xFFFFFFFF)) {
+			mtip_check_surprise_removal(dd->pdev);
+			return IRQ_HANDLED;
+		}
 		writel(port_stat, port->mmio + PORT_IRQ_STAT);
 
 		/* Demux port status */
@@ -991,15 +991,10 @@ static bool mtip_pause_ncq(struct mtip_port *port,
 	reply = port->rxfis + RX_FIS_D2H_REG;
 	task_file_data = readl(port->mmio+PORT_TFDATA);
 
-	if (fis->command == ATA_CMD_SEC_ERASE_UNIT)
-		clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
-
 	if ((task_file_data & 1))
 		return false;
 
 	if (fis->command == ATA_CMD_SEC_ERASE_PREP) {
-		set_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
-		set_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
 		port->ic_pause_timer = jiffies;
 		return true;
 	} else if ((fis->command == ATA_CMD_DOWNLOAD_MICRO) &&
@@ -1011,8 +1006,10 @@ static bool mtip_pause_ncq(struct mtip_port *port,
 		((fis->command == 0xFC) &&
 			(fis->features == 0x27 || fis->features == 0x72 ||
 			 fis->features == 0x62 || fis->features == 0x26))) {
+		clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag);
 		/* Com reset after secure erase or lowlevel format */
 		mtip_restart_port(port);
+		clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
 		return false;
 	}
 
@@ -1112,9 +1109,10 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	int_cmd = mtip_get_int_command(dd);
 
 	set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
-	port->ic_pause_timer = 0;
 
-	clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
+	if (fis->command == ATA_CMD_SEC_ERASE_PREP)
+		set_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags);
+
 	clear_bit(MTIP_PF_DM_ACTIVE_BIT, &port->flags);
 
 	if (atomic == GFP_KERNEL) {
@@ -1251,11 +1249,11 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 exec_ic_exit:
 	/* Clear the allocated and active bits for the internal command. */
 	mtip_put_int_command(dd, int_cmd);
+	clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 	if (rv >= 0 && mtip_pause_ncq(port, fis)) {
 		/* NCQ paused */
 		return rv;
 	}
-	clear_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags);
 	wake_up_interruptible(&port->svc_wait);
 
 	return rv;
@@ -2625,18 +2623,6 @@ static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
 				readl(dd->mmio + HOST_IRQ_STAT));
 	size += sprintf(&buf[size], "\n");
 
-	size += sprintf(&buf[size], "L/ Allocated     : [ 0x");
-
-	for (n = dd->slot_groups-1; n >= 0; n--) {
-		if (sizeof(long) > sizeof(u32))
-			group_allocated =
-				dd->port->allocated[n/2] >> (32*(n&1));
-		else
-			group_allocated = dd->port->allocated[n];
-		size += sprintf(&buf[size], "%08X ", group_allocated);
-	}
-	size += sprintf(&buf[size], "]\n");
-
 	size += sprintf(&buf[size], "L/ Commands in Q : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--) {
@@ -2780,48 +2766,6 @@ static void mtip_hw_debugfs_exit(struct driver_data *dd)
 		debugfs_remove_recursive(dd->dfs_node);
 }
 
-static int mtip_free_orphan(struct driver_data *dd)
-{
-	struct kobject *kobj;
-
-	if (dd->bdev) {
-		if (dd->bdev->bd_holders >= 1)
-			return -2;
-
-		bdput(dd->bdev);
-		dd->bdev = NULL;
-	}
-
-	mtip_hw_debugfs_exit(dd);
-
-	spin_lock(&rssd_index_lock);
-	ida_remove(&rssd_index_ida, dd->index);
-	spin_unlock(&rssd_index_lock);
-
-	if (!test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag) &&
-			test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)) {
-		put_disk(dd->disk);
-	} else {
-		if (dd->disk) {
-			kobj = kobject_get(&disk_to_dev(dd->disk)->kobj);
-			if (kobj) {
-				mtip_hw_sysfs_exit(dd, kobj);
-				kobject_put(kobj);
-			}
-			del_gendisk(dd->disk);
-			dd->disk = NULL;
-		}
-		if (dd->queue) {
-			dd->queue->queuedata = NULL;
-			blk_cleanup_queue(dd->queue);
-			blk_mq_free_tag_set(&dd->tags);
-			dd->queue = NULL;
-		}
-	}
-	kfree(dd);
-	return 0;
-}
-
 /*
  * Perform any init/resume time hardware setup
  *
@@ -2944,7 +2888,6 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd)
 			mtip_block_initialize(dd);
 			return 0;
 		}
-		ssleep(10);
 	} while (time_before(jiffies, timeout));
 
 	/* Check for timeout */
@@ -2969,7 +2912,6 @@ static int mtip_service_thread(void *data)
 	unsigned long slot, slot_start, slot_wrap;
 	unsigned int num_cmd_slots = dd->slot_groups * 32;
 	struct mtip_port *port = dd->port;
-	int ret;
 
 	while (1) {
 		if (kthread_should_stop() ||
@@ -2990,10 +2932,6 @@ static int mtip_service_thread(void *data)
 			test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags))
 			goto st_out;
 
-		/* If I am an orphan, start self cleanup */
-		if (test_bit(MTIP_PF_SR_CLEANUP_BIT, &port->flags))
-			break;
-
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
 				&dd->dd_flag)))
 			goto st_out;
@@ -3047,26 +2985,6 @@ restart_eh:
 		}
 	}
 
-	/* wait for pci remove to exit */
-	while (1) {
-		if (test_bit(MTIP_DDF_REMOVE_DONE_BIT, &dd->dd_flag))
-			break;
-		msleep_interruptible(1000);
-		if (kthread_should_stop())
-			goto st_out;
-	}
-
-	while (1) {
-		ret = mtip_free_orphan(dd);
-		if (!ret) {
-			/* NOTE: All data structures are invalid, do not
-			 * access any here */
-			return 0;
-		}
-		msleep_interruptible(1000);
-		if (kthread_should_stop())
-			goto st_out;
-	}
 st_out:
 	return 0;
 }
@@ -3394,6 +3312,7 @@ static int mtip_hw_exit(struct driver_data *dd)
 	/* Release the IRQ. */
 	irq_set_affinity_hint(dd->pdev->irq, NULL);
 	devm_free_irq(&dd->pdev->dev, dd->pdev->irq, dd);
+	msleep(1000);
 
 	/* Free dma regions */
 	mtip_dma_free(dd);
@@ -3699,6 +3618,26 @@ static const struct block_device_operations mtip_block_ops = {
 	.owner		= THIS_MODULE
 };
 
+static inline bool is_se_active(struct driver_data *dd)
+{
+	if (unlikely(test_bit(MTIP_PF_SE_ACTIVE_BIT, &dd->port->flags))) {
+		if (dd->port->ic_pause_timer) {
+			unsigned long to = dd->port->ic_pause_timer +
+							msecs_to_jiffies(1000);
+			if (time_after(jiffies, to)) {
+				clear_bit(MTIP_PF_SE_ACTIVE_BIT,
+							&dd->port->flags);
+				clear_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag);
+				dd->port->ic_pause_timer = 0;
+				wake_up_interruptible(&dd->port->svc_wait);
+				return false;
+			}
+		}
+		return true;
+	}
+	return false;
+}
+
 /*
  * Block layer make request function.
  *
@@ -3716,6 +3655,9 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	unsigned int nents;
 
+	if (is_se_active(dd))
+		return -ENODATA;
+
 	if (unlikely(dd->dd_flag & MTIP_DDF_STOP_IO)) {
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
 							&dd->dd_flag))) {
@@ -3900,7 +3842,8 @@ static int mtip_block_initialize(struct driver_data *dd)
 
 	dd->disk->driverfs_dev	= &dd->pdev->dev;
 	dd->disk->major		= dd->major;
-	dd->disk->first_minor	= dd->instance * MTIP_MAX_MINORS;
+	dd->disk->first_minor	= index * MTIP_MAX_MINORS;
+	dd->disk->minors 	= MTIP_MAX_MINORS;
 	dd->disk->fops		= &mtip_block_ops;
 	dd->disk->private_data	= dd;
 	dd->index		= index;
@@ -4066,52 +4009,51 @@ static int mtip_block_remove(struct driver_data *dd)
 {
 	struct kobject *kobj;
 
-	if (!dd->sr) {
-		mtip_hw_debugfs_exit(dd);
+	mtip_hw_debugfs_exit(dd);
 
-		if (dd->mtip_svc_handler) {
-			set_bit(MTIP_PF_SVC_THD_STOP_BIT, &dd->port->flags);
-			wake_up_interruptible(&dd->port->svc_wait);
-			kthread_stop(dd->mtip_svc_handler);
-		}
+	if (dd->mtip_svc_handler) {
+		set_bit(MTIP_PF_SVC_THD_STOP_BIT, &dd->port->flags);
+		wake_up_interruptible(&dd->port->svc_wait);
+		kthread_stop(dd->mtip_svc_handler);
+	}
 
-		/* Clean up the sysfs attributes, if created */
-		if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) {
-			kobj = kobject_get(&disk_to_dev(dd->disk)->kobj);
-			if (kobj) {
-				mtip_hw_sysfs_exit(dd, kobj);
-				kobject_put(kobj);
-			}
+	/* Clean up the sysfs attributes, if created */
+	if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) {
+		kobj = kobject_get(&disk_to_dev(dd->disk)->kobj);
+		if (kobj) {
+			mtip_hw_sysfs_exit(dd, kobj);
+			kobject_put(kobj);
 		}
+	}
 
+	if (!dd->sr)
 		mtip_standby_drive(dd);
-
-		/*
-		 * Delete our gendisk structure. This also removes the device
-		 * from /dev
-		 */
-		if (dd->bdev) {
-			bdput(dd->bdev);
-			dd->bdev = NULL;
-		}
-		if (dd->disk) {
-			if (dd->disk->queue) {
-				del_gendisk(dd->disk);
-				blk_cleanup_queue(dd->queue);
-				blk_mq_free_tag_set(&dd->tags);
-				dd->queue = NULL;
-			} else
-				put_disk(dd->disk);
-		}
-		dd->disk  = NULL;
-
-		spin_lock(&rssd_index_lock);
-		ida_remove(&rssd_index_ida, dd->index);
-		spin_unlock(&rssd_index_lock);
-	} else {
+	else
 		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
 						dd->disk->disk_name);
+
+	/*
+	 * Delete our gendisk structure. This also removes the device
+	 * from /dev
+	 */
+	if (dd->bdev) {
+		bdput(dd->bdev);
+		dd->bdev = NULL;
 	}
+	if (dd->disk) {
+		del_gendisk(dd->disk);
+		if (dd->disk->queue) {
+			blk_cleanup_queue(dd->queue);
+			blk_mq_free_tag_set(&dd->tags);
+			dd->queue = NULL;
+		}
+		put_disk(dd->disk);
+	}
+	dd->disk  = NULL;
+
+	spin_lock(&rssd_index_lock);
+	ida_remove(&rssd_index_ida, dd->index);
+	spin_unlock(&rssd_index_lock);
 
 	/* De-initialize the protocol layer. */
 	mtip_hw_exit(dd);
@@ -4140,12 +4082,12 @@ static int mtip_block_shutdown(struct driver_data *dd)
 		dev_info(&dd->pdev->dev,
 			"Shutting down %s ...\n", dd->disk->disk_name);
 
+		del_gendisk(dd->disk);
 		if (dd->disk->queue) {
-			del_gendisk(dd->disk);
 			blk_cleanup_queue(dd->queue);
 			blk_mq_free_tag_set(&dd->tags);
-		} else
-			put_disk(dd->disk);
+		}
+		put_disk(dd->disk);
 		dd->disk  = NULL;
 		dd->queue = NULL;
 	}
@@ -4507,6 +4449,7 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 			"Completion workers still active!\n");
 	}
 
+	blk_mq_stop_hw_queues(dd->queue);
 	/* Clean up the block layer. */
 	mtip_block_remove(dd);
 
@@ -4524,10 +4467,7 @@ static void mtip_pci_remove(struct pci_dev *pdev)
 	list_del_init(&dd->remove_list);
 	spin_unlock_irqrestore(&dev_lock, flags);
 
-	if (!dd->sr)
-		kfree(dd);
-	else
-		set_bit(MTIP_DDF_REMOVE_DONE_BIT, &dd->dd_flag);
+	kfree(dd);
 
 	pcim_iounmap_regions(pdev, 1 << MTIP_ABAR);
 	pci_set_drvdata(pdev, NULL);
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index ba1b31ee22ec..3274784008eb 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -142,7 +142,6 @@ enum {
 	MTIP_PF_SVC_THD_ACTIVE_BIT  = 4,
 	MTIP_PF_ISSUE_CMDS_BIT      = 5,
 	MTIP_PF_REBUILD_BIT         = 6,
-	MTIP_PF_SR_CLEANUP_BIT      = 7,
 	MTIP_PF_SVC_THD_STOP_BIT    = 8,
 
 	/* below are bit numbers in 'dd_flag' defined in driver_data */
@@ -150,7 +149,6 @@ enum {
 	MTIP_DDF_REMOVE_PENDING_BIT = 1,
 	MTIP_DDF_OVER_TEMP_BIT      = 2,
 	MTIP_DDF_WRITE_PROTECT_BIT  = 3,
-	MTIP_DDF_REMOVE_DONE_BIT    = 4,
 	MTIP_DDF_CLEANUP_BIT        = 5,
 	MTIP_DDF_RESUME_BIT         = 6,
 	MTIP_DDF_INIT_DONE_BIT      = 7,
@@ -412,19 +410,13 @@ struct mtip_port {
 	 * by the DMA when the driver issues internal commands.
 	 */
 	dma_addr_t sector_buffer_dma;
-	/*
-	 * Bit significant, used to determine if a command slot has
-	 * been allocated. i.e. the slot is in use.  Bits are cleared
-	 * when the command slot and all associated data structures
-	 * are no longer needed.
-	 */
+
 	u16 *log_buf;
 	dma_addr_t log_buf_dma;
 
 	u8 *smart_buf;
 	dma_addr_t smart_buf_dma;
 
-	unsigned long allocated[SLOTBITS_IN_LONGS];
 	/*
 	 * used to queue commands when an internal command is in progress
 	 * or error handling is active
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 39e5f7fae3ef..0e385d8e9b86 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -230,29 +230,40 @@ static int nbd_send_req(struct nbd_device *nbd, struct request *req)
 	int result, flags;
 	struct nbd_request request;
 	unsigned long size = blk_rq_bytes(req);
+	u32 type;
+
+	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		type = NBD_CMD_DISC;
+	else if (req->cmd_flags & REQ_DISCARD)
+		type = NBD_CMD_TRIM;
+	else if (req->cmd_flags & REQ_FLUSH)
+		type = NBD_CMD_FLUSH;
+	else if (rq_data_dir(req) == WRITE)
+		type = NBD_CMD_WRITE;
+	else
+		type = NBD_CMD_READ;
 
 	memset(&request, 0, sizeof(request));
 	request.magic = htonl(NBD_REQUEST_MAGIC);
-	request.type = htonl(nbd_cmd(req));
-
-	if (nbd_cmd(req) != NBD_CMD_FLUSH && nbd_cmd(req) != NBD_CMD_DISC) {
+	request.type = htonl(type);
+	if (type != NBD_CMD_FLUSH && type != NBD_CMD_DISC) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
 	}
 	memcpy(request.handle, &req, sizeof(req));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
-		req, nbdcmd_to_ascii(nbd_cmd(req)),
+		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, 1, &request, sizeof(request),
-			(nbd_cmd(req) == NBD_CMD_WRITE) ? MSG_MORE : 0);
+			(type == NBD_CMD_WRITE) ? MSG_MORE : 0);
 	if (result <= 0) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
 		return -EIO;
 	}
 
-	if (nbd_cmd(req) == NBD_CMD_WRITE) {
+	if (type == NBD_CMD_WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
 		/*
@@ -352,7 +363,7 @@ static struct request *nbd_read_stat(struct nbd_device *nbd)
 	}
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
-	if (nbd_cmd(req) == NBD_CMD_READ) {
+	if (rq_data_dir(req) != WRITE) {
 		struct req_iterator iter;
 		struct bio_vec bvec;
 
@@ -452,23 +463,11 @@ static void nbd_handle_req(struct nbd_device *nbd, struct request *req)
 	if (req->cmd_type != REQ_TYPE_FS)
 		goto error_out;
 
-	nbd_cmd(req) = NBD_CMD_READ;
-	if (rq_data_dir(req) == WRITE) {
-		if ((req->cmd_flags & REQ_DISCARD)) {
-			WARN_ON(!(nbd->flags & NBD_FLAG_SEND_TRIM));
-			nbd_cmd(req) = NBD_CMD_TRIM;
-		} else
-			nbd_cmd(req) = NBD_CMD_WRITE;
-		if (nbd->flags & NBD_FLAG_READ_ONLY) {
-			dev_err(disk_to_dev(nbd->disk),
-				"Write on read-only\n");
-			goto error_out;
-		}
-	}
-
-	if (req->cmd_flags & REQ_FLUSH) {
-		BUG_ON(unlikely(blk_rq_sectors(req)));
-		nbd_cmd(req) = NBD_CMD_FLUSH;
+	if (rq_data_dir(req) == WRITE &&
+	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
+		dev_err(disk_to_dev(nbd->disk),
+			"Write on read-only\n");
+		goto error_out;
 	}
 
 	req->errors = 0;
@@ -592,8 +591,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		fsync_bdev(bdev);
 		mutex_lock(&nbd->tx_lock);
 		blk_rq_init(NULL, &sreq);
-		sreq.cmd_type = REQ_TYPE_SPECIAL;
-		nbd_cmd(&sreq) = NBD_CMD_DISC;
+		sreq.cmd_type = REQ_TYPE_DRV_PRIV;
 
 		/* Check again after getting mutex back.  */
 		if (!nbd->sock)
@@ -713,7 +711,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		bdev->bd_inode->i_size = 0;
 		set_capacity(nbd->disk, 0);
 		if (max_part > 0)
-			ioctl_by_bdev(bdev, BLKRRPART, 0);
+			blkdev_reread_part(bdev);
 		if (nbd->disconnect) /* user requested, ignore socket errors */
 			return 0;
 		return nbd->harderror;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 65cd61a4145e..6f9b7534928e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -243,6 +243,17 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
 			entry = entry->next;
 			end_cmd(cmd);
+
+			if (cmd->rq) {
+				struct request_queue *q = cmd->rq->q;
+
+				if (!q->mq_ops && blk_queue_stopped(q)) {
+					spin_lock(q->queue_lock);
+					if (blk_queue_stopped(q))
+						blk_start_queue(q);
+					spin_unlock(q->queue_lock);
+				}
+			}
 		} while (entry);
 	}
 
@@ -257,7 +268,7 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 	if (llist_add(&cmd->ll_list, &cq->list)) {
 		ktime_t kt = ktime_set(0, completion_nsec);
 
-		hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL);
+		hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL_PINNED);
 	}
 
 	put_cpu();
@@ -334,6 +345,7 @@ static int null_rq_prep_fn(struct request_queue *q, struct request *req)
 		req->special = cmd;
 		return BLKPREP_OK;
 	}
+	blk_stop_queue(q);
 
 	return BLKPREP_DEFER;
 }
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 85b8036deaa3..e5112714188f 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -29,6 +29,7 @@
 #include <linux/kdev_t.h>
 #include <linux/kthread.h>
 #include <linux/kernel.h>
+#include <linux/list_sort.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -80,6 +81,7 @@ static wait_queue_head_t nvme_kthread_wait;
 static struct class *nvme_class;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
+static int nvme_reset(struct nvme_dev *dev);
 static int nvme_process_cq(struct nvme_queue *nvmeq);
 
 struct async_cmd_info {
@@ -102,6 +104,7 @@ struct nvme_queue {
 	spinlock_t q_lock;
 	struct nvme_command *sq_cmds;
 	volatile struct nvme_completion *cqes;
+	struct blk_mq_tags **tags;
 	dma_addr_t sq_dma_addr;
 	dma_addr_t cq_dma_addr;
 	u32 __iomem *q_db;
@@ -114,7 +117,6 @@ struct nvme_queue {
 	u8 cq_phase;
 	u8 cqe_seen;
 	struct async_cmd_info cmdinfo;
-	struct blk_mq_hw_ctx *hctx;
 };
 
 /*
@@ -182,9 +184,12 @@ static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	struct nvme_dev *dev = data;
 	struct nvme_queue *nvmeq = dev->queues[0];
 
-	WARN_ON(nvmeq->hctx);
-	nvmeq->hctx = hctx;
+	WARN_ON(hctx_idx != 0);
+	WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
+	WARN_ON(nvmeq->tags);
+
 	hctx->driver_data = nvmeq;
+	nvmeq->tags = &dev->admin_tagset.tags[0];
 	return 0;
 }
 
@@ -201,27 +206,16 @@ static int nvme_admin_init_request(void *data, struct request *req,
 	return 0;
 }
 
-static void nvme_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
-	struct nvme_queue *nvmeq = hctx->driver_data;
-
-	nvmeq->hctx = NULL;
-}
-
 static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 			  unsigned int hctx_idx)
 {
 	struct nvme_dev *dev = data;
-	struct nvme_queue *nvmeq = dev->queues[
-					(hctx_idx % dev->queue_count) + 1];
-
-	if (!nvmeq->hctx)
-		nvmeq->hctx = hctx;
+	struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
 
-	/* nvmeq queues are shared between namespaces. We assume here that
-	 * blk-mq map the tags so they match up with the nvme queue tags. */
-	WARN_ON(nvmeq->hctx->tags != hctx->tags);
+	if (!nvmeq->tags)
+		nvmeq->tags = &dev->tagset.tags[hctx_idx];
 
+	WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
 	hctx->driver_data = nvmeq;
 	return 0;
 }
@@ -307,9 +301,16 @@ static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
 
 	if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
 		++nvmeq->dev->event_limit;
-	if (status == NVME_SC_SUCCESS)
-		dev_warn(nvmeq->q_dmadev,
-			"async event result %08x\n", result);
+	if (status != NVME_SC_SUCCESS)
+		return;
+
+	switch (result & 0xff07) {
+	case NVME_AER_NOTICE_NS_CHANGED:
+		dev_info(nvmeq->q_dmadev, "rescanning\n");
+		schedule_work(&nvmeq->dev->scan_work);
+	default:
+		dev_warn(nvmeq->q_dmadev, "async event result %08x\n", result);
+	}
 }
 
 static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
@@ -320,7 +321,7 @@ static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
 	u32 result = le32_to_cpup(&cqe->result);
 
-	blk_mq_free_hctx_request(nvmeq->hctx, req);
+	blk_mq_free_request(req);
 
 	dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status, result);
 	++nvmeq->dev->abort_limit;
@@ -333,14 +334,13 @@ static void async_completion(struct nvme_queue *nvmeq, void *ctx,
 	cmdinfo->result = le32_to_cpup(&cqe->result);
 	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
 	queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
-	blk_mq_free_hctx_request(nvmeq->hctx, cmdinfo->req);
+	blk_mq_free_request(cmdinfo->req);
 }
 
 static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,
 				  unsigned int tag)
 {
-	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
-	struct request *req = blk_mq_tag_to_rq(hctx->tags, tag);
+	struct request *req = blk_mq_tag_to_rq(*nvmeq->tags, tag);
 
 	return blk_mq_rq_to_pdu(req);
 }
@@ -445,7 +445,7 @@ static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct nvme_dev *dev,
 				(unsigned long) rq, gfp);
 }
 
-void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
+static void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 {
 	const int last_prp = dev->page_size / 8 - 1;
 	int i;
@@ -605,22 +605,30 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 			spin_unlock_irqrestore(req->q->queue_lock, flags);
 			return;
 		}
-		req->errors = nvme_error_status(status);
+		if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+			req->errors = status;
+		} else {
+			req->errors = nvme_error_status(status);
+		}
 	} else
 		req->errors = 0;
+	if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+		u32 result = le32_to_cpup(&cqe->result);
+		req->special = (void *)(uintptr_t)result;
+	}
 
 	if (cmd_rq->aborted)
-		dev_warn(&nvmeq->dev->pci_dev->dev,
+		dev_warn(nvmeq->dev->dev,
 			"completing aborted command with status:%04x\n",
 			status);
 
 	if (iod->nents) {
-		dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg, iod->nents,
+		dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
 			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		if (blk_integrity_rq(req)) {
 			if (!rq_data_dir(req))
 				nvme_dif_remap(req, nvme_dif_complete);
-			dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->meta_sg, 1,
+			dma_unmap_sg(nvmeq->dev->dev, iod->meta_sg, 1,
 				rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		}
 	}
@@ -630,8 +638,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
-int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
-								gfp_t gfp)
+static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
+		int total_len, gfp_t gfp)
 {
 	struct dma_pool *pool;
 	int length = total_len;
@@ -709,6 +717,23 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
 	return total_len;
 }
 
+static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request *req,
+		struct nvme_iod *iod)
+{
+	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
+
+	memcpy(cmnd, req->cmd, sizeof(struct nvme_command));
+	cmnd->rw.command_id = req->tag;
+	if (req->nr_phys_segments) {
+		cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
+	}
+
+	if (++nvmeq->sq_tail == nvmeq->q_depth)
+		nvmeq->sq_tail = 0;
+	writel(nvmeq->sq_tail, nvmeq->q_db);
+}
+
 /*
  * We reuse the small pool to allocate the 16-byte range here as it is not
  * worth having a special pool for these or additional cases to handle freeing
@@ -807,11 +832,15 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 	return 0;
 }
 
+/*
+ * NOTE: ns is NULL when called on the admin queue.
+ */
 static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
 	struct nvme_ns *ns = hctx->queue->queuedata;
 	struct nvme_queue *nvmeq = hctx->driver_data;
+	struct nvme_dev *dev = nvmeq->dev;
 	struct request *req = bd->rq;
 	struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
 	struct nvme_iod *iod;
@@ -822,15 +851,16 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * unless this namespace is formated such that the metadata can be
 	 * stripped/generated by the controller with PRACT=1.
 	 */
-	if (ns->ms && !blk_integrity_rq(req)) {
-		if (!(ns->pi_type && ns->ms == 8)) {
+	if (ns && ns->ms && !blk_integrity_rq(req)) {
+		if (!(ns->pi_type && ns->ms == 8) &&
+					req->cmd_type != REQ_TYPE_DRV_PRIV) {
 			req->errors = -EFAULT;
 			blk_mq_complete_request(req);
 			return BLK_MQ_RQ_QUEUE_OK;
 		}
 	}
 
-	iod = nvme_alloc_iod(req, ns->dev, GFP_ATOMIC);
+	iod = nvme_alloc_iod(req, dev, GFP_ATOMIC);
 	if (!iod)
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
@@ -841,8 +871,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 		 * as it is not worth having a special pool for these or
 		 * additional cases to handle freeing the iod.
 		 */
-		range = dma_pool_alloc(nvmeq->dev->prp_small_pool,
-						GFP_ATOMIC,
+		range = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC,
 						&iod->first_dma);
 		if (!range)
 			goto retry_cmd;
@@ -860,9 +889,8 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 			goto retry_cmd;
 
 		if (blk_rq_bytes(req) !=
-                    nvme_setup_prps(nvmeq->dev, iod, blk_rq_bytes(req), GFP_ATOMIC)) {
-			dma_unmap_sg(&nvmeq->dev->pci_dev->dev, iod->sg,
-					iod->nents, dma_dir);
+                    nvme_setup_prps(dev, iod, blk_rq_bytes(req), GFP_ATOMIC)) {
+			dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
 			goto retry_cmd;
 		}
 		if (blk_integrity_rq(req)) {
@@ -884,7 +912,9 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	nvme_set_info(cmd, iod, req_completion);
 	spin_lock_irq(&nvmeq->q_lock);
-	if (req->cmd_flags & REQ_DISCARD)
+	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		nvme_submit_priv(nvmeq, req, iod);
+	else if (req->cmd_flags & REQ_DISCARD)
 		nvme_submit_discard(nvmeq, ns, req, iod);
 	else if (req->cmd_flags & REQ_FLUSH)
 		nvme_submit_flush(nvmeq, ns, req->tag);
@@ -896,10 +926,10 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_MQ_RQ_QUEUE_OK;
 
  error_cmd:
-	nvme_free_iod(nvmeq->dev, iod);
+	nvme_free_iod(dev, iod);
 	return BLK_MQ_RQ_QUEUE_ERROR;
  retry_cmd:
-	nvme_free_iod(nvmeq->dev, iod);
+	nvme_free_iod(dev, iod);
 	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
@@ -942,15 +972,6 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 	return 1;
 }
 
-/* Admin queue isn't initialized as a request queue. If at some point this
- * happens anyway, make sure to notify the user */
-static int nvme_admin_queue_rq(struct blk_mq_hw_ctx *hctx,
-			       const struct blk_mq_queue_data *bd)
-{
-	WARN_ON_ONCE(1);
-	return BLK_MQ_RQ_QUEUE_ERROR;
-}
-
 static irqreturn_t nvme_irq(int irq, void *data)
 {
 	irqreturn_t result;
@@ -972,46 +993,61 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
 	return IRQ_WAKE_THREAD;
 }
 
-struct sync_cmd_info {
-	struct task_struct *task;
-	u32 result;
-	int status;
-};
-
-static void sync_completion(struct nvme_queue *nvmeq, void *ctx,
-						struct nvme_completion *cqe)
-{
-	struct sync_cmd_info *cmdinfo = ctx;
-	cmdinfo->result = le32_to_cpup(&cqe->result);
-	cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
-	wake_up_process(cmdinfo->task);
-}
-
 /*
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code
  */
-static int nvme_submit_sync_cmd(struct request *req, struct nvme_command *cmd,
-						u32 *result, unsigned timeout)
+int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buffer, void __user *ubuffer, unsigned bufflen,
+		u32 *result, unsigned timeout)
 {
-	struct sync_cmd_info cmdinfo;
-	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
-	struct nvme_queue *nvmeq = cmd_rq->nvmeq;
+	bool write = cmd->common.opcode & 1;
+	struct bio *bio = NULL;
+	struct request *req;
+	int ret;
 
-	cmdinfo.task = current;
-	cmdinfo.status = -EINTR;
+	req = blk_mq_alloc_request(q, write, GFP_KERNEL, false);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
-	cmd->common.command_id = req->tag;
+	req->cmd_type = REQ_TYPE_DRV_PRIV;
+	req->cmd_flags |= REQ_FAILFAST_DRIVER;
+	req->__data_len = 0;
+	req->__sector = (sector_t) -1;
+	req->bio = req->biotail = NULL;
 
-	nvme_set_info(cmd_rq, &cmdinfo, sync_completion);
+	req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
 
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	nvme_submit_cmd(nvmeq, cmd);
-	schedule();
+	req->cmd = (unsigned char *)cmd;
+	req->cmd_len = sizeof(struct nvme_command);
+	req->special = (void *)0;
 
+	if (buffer && bufflen) {
+		ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT);
+		if (ret)
+			goto out;
+	} else if (ubuffer && bufflen) {
+		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT);
+		if (ret)
+			goto out;
+		bio = req->bio;
+	}
+
+	blk_execute_rq(req->q, NULL, req, 0);
+	if (bio)
+		blk_rq_unmap_user(bio);
 	if (result)
-		*result = cmdinfo.result;
-	return cmdinfo.status;
+		*result = (u32)(uintptr_t)req->special;
+	ret = req->errors;
+ out:
+	blk_mq_free_request(req);
+	return ret;
+}
+
+int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
+		void *buffer, unsigned bufflen)
+{
+	return __nvme_submit_sync_cmd(q, cmd, buffer, NULL, bufflen, NULL, 0);
 }
 
 static int nvme_submit_async_admin_req(struct nvme_dev *dev)
@@ -1033,7 +1069,7 @@ static int nvme_submit_async_admin_req(struct nvme_dev *dev)
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = req->tag;
 
-	blk_mq_free_hctx_request(nvmeq->hctx, req);
+	blk_mq_free_request(req);
 	return __nvme_submit_cmd(nvmeq, &c);
 }
 
@@ -1060,41 +1096,6 @@ static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
 	return nvme_submit_cmd(nvmeq, cmd);
 }
 
-static int __nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
-						u32 *result, unsigned timeout)
-{
-	int res;
-	struct request *req;
-
-	req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-	res = nvme_submit_sync_cmd(req, cmd, result, timeout);
-	blk_mq_free_request(req);
-	return res;
-}
-
-int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
-								u32 *result)
-{
-	return __nvme_submit_admin_cmd(dev, cmd, result, ADMIN_TIMEOUT);
-}
-
-int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
-					struct nvme_command *cmd, u32 *result)
-{
-	int res;
-	struct request *req;
-
-	req = blk_mq_alloc_request(ns->queue, WRITE, (GFP_KERNEL|__GFP_WAIT),
-									false);
-	if (IS_ERR(req))
-		return PTR_ERR(req);
-	res = nvme_submit_sync_cmd(req, cmd, result, NVME_IO_TIMEOUT);
-	blk_mq_free_request(req);
-	return res;
-}
-
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
 	struct nvme_command c;
@@ -1103,7 +1104,7 @@ static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 	c.delete_queue.opcode = opcode;
 	c.delete_queue.qid = cpu_to_le16(id);
 
-	return nvme_submit_admin_cmd(dev, &c, NULL);
+	return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
 }
 
 static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
@@ -1112,6 +1113,10 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
 
+	/*
+	 * Note: we (ab)use the fact the the prp fields survive if no data
+	 * is attached to the request.
+	 */
 	memset(&c, 0, sizeof(c));
 	c.create_cq.opcode = nvme_admin_create_cq;
 	c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
@@ -1120,7 +1125,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 	c.create_cq.cq_flags = cpu_to_le16(flags);
 	c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
 
-	return nvme_submit_admin_cmd(dev, &c, NULL);
+	return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
 }
 
 static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
@@ -1129,6 +1134,10 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 	struct nvme_command c;
 	int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
 
+	/*
+	 * Note: we (ab)use the fact the the prp fields survive if no data
+	 * is attached to the request.
+	 */
 	memset(&c, 0, sizeof(c));
 	c.create_sq.opcode = nvme_admin_create_sq;
 	c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
@@ -1137,7 +1146,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
 	c.create_sq.sq_flags = cpu_to_le16(flags);
 	c.create_sq.cqid = cpu_to_le16(qid);
 
-	return nvme_submit_admin_cmd(dev, &c, NULL);
+	return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
 }
 
 static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
@@ -1150,18 +1159,43 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
 	return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
 }
 
-int nvme_identify(struct nvme_dev *dev, unsigned nsid, unsigned cns,
-							dma_addr_t dma_addr)
+int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id)
 {
-	struct nvme_command c;
+	struct nvme_command c = {
+		.identify.opcode = nvme_admin_identify,
+		.identify.cns = cpu_to_le32(1),
+	};
+	int error;
 
-	memset(&c, 0, sizeof(c));
-	c.identify.opcode = nvme_admin_identify;
-	c.identify.nsid = cpu_to_le32(nsid);
-	c.identify.prp1 = cpu_to_le64(dma_addr);
-	c.identify.cns = cpu_to_le32(cns);
+	*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
+
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
+			sizeof(struct nvme_id_ctrl));
+	if (error)
+		kfree(*id);
+	return error;
+}
+
+int nvme_identify_ns(struct nvme_dev *dev, unsigned nsid,
+		struct nvme_id_ns **id)
+{
+	struct nvme_command c = {
+		.identify.opcode = nvme_admin_identify,
+		.identify.nsid = cpu_to_le32(nsid),
+	};
+	int error;
+
+	*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
+	if (!*id)
+		return -ENOMEM;
 
-	return nvme_submit_admin_cmd(dev, &c, NULL);
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
+			sizeof(struct nvme_id_ns));
+	if (error)
+		kfree(*id);
+	return error;
 }
 
 int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
@@ -1175,7 +1209,8 @@ int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
 	c.features.prp1 = cpu_to_le64(dma_addr);
 	c.features.fid = cpu_to_le32(fid);
 
-	return nvme_submit_admin_cmd(dev, &c, result);
+	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, NULL, 0,
+			result, 0);
 }
 
 int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
@@ -1189,7 +1224,30 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
 
-	return nvme_submit_admin_cmd(dev, &c, result);
+	return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, NULL, 0,
+			result, 0);
+}
+
+int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log)
+{
+	struct nvme_command c = {
+		.common.opcode = nvme_admin_get_log_page,
+		.common.nsid = cpu_to_le32(0xFFFFFFFF),
+		.common.cdw10[0] = cpu_to_le32(
+			(((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
+			 NVME_LOG_SMART),
+	};
+	int error;
+
+	*log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
+	if (!*log)
+		return -ENOMEM;
+
+	error = nvme_submit_sync_cmd(dev->admin_q, &c, *log,
+			sizeof(struct nvme_smart_log));
+	if (error)
+		kfree(*log);
+	return error;
 }
 
 /**
@@ -1214,8 +1272,7 @@ static void nvme_abort_req(struct request *req)
 		if (work_busy(&dev->reset_work))
 			goto out;
 		list_del_init(&dev->node);
-		dev_warn(&dev->pci_dev->dev,
-			"I/O %d QID %d timeout, reset controller\n",
+		dev_warn(dev->dev, "I/O %d QID %d timeout, reset controller\n",
 							req->tag, nvmeq->qid);
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
@@ -1254,8 +1311,7 @@ static void nvme_abort_req(struct request *req)
 	}
 }
 
-static void nvme_cancel_queue_ios(struct blk_mq_hw_ctx *hctx,
-				struct request *req, void *data, bool reserved)
+static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved)
 {
 	struct nvme_queue *nvmeq = data;
 	void *ctx;
@@ -1352,11 +1408,9 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 
 static void nvme_clear_queue(struct nvme_queue *nvmeq)
 {
-	struct blk_mq_hw_ctx *hctx = nvmeq->hctx;
-
 	spin_lock_irq(&nvmeq->q_lock);
-	if (hctx && hctx->tags)
-		blk_mq_tag_busy_iter(hctx, nvme_cancel_queue_ios, nvmeq);
+	if (nvmeq->tags && *nvmeq->tags)
+		blk_mq_all_tag_busy_iter(*nvmeq->tags, nvme_cancel_queue_ios, nvmeq);
 	spin_unlock_irq(&nvmeq->q_lock);
 }
 
@@ -1384,22 +1438,21 @@ static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 							int depth)
 {
-	struct device *dmadev = &dev->pci_dev->dev;
 	struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
 	if (!nvmeq)
 		return NULL;
 
-	nvmeq->cqes = dma_zalloc_coherent(dmadev, CQ_SIZE(depth),
+	nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
 					  &nvmeq->cq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->cqes)
 		goto free_nvmeq;
 
-	nvmeq->sq_cmds = dma_alloc_coherent(dmadev, SQ_SIZE(depth),
+	nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
 					&nvmeq->sq_dma_addr, GFP_KERNEL);
 	if (!nvmeq->sq_cmds)
 		goto free_cqdma;
 
-	nvmeq->q_dmadev = dmadev;
+	nvmeq->q_dmadev = dev->dev;
 	nvmeq->dev = dev;
 	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
 			dev->instance, qid);
@@ -1409,13 +1462,16 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->qid = qid;
-	dev->queue_count++;
 	dev->queues[qid] = nvmeq;
 
+	/* make sure queue descriptor is set before queue count, for kthread */
+	mb();
+	dev->queue_count++;
+
 	return nvmeq;
 
  free_cqdma:
-	dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
+	dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq->cqes,
 							nvmeq->cq_dma_addr);
  free_nvmeq:
 	kfree(nvmeq);
@@ -1487,7 +1543,7 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
 		if (fatal_signal_pending(current))
 			return -EINTR;
 		if (time_after(jiffies, timeout)) {
-			dev_err(&dev->pci_dev->dev,
+			dev_err(dev->dev,
 				"Device not ready; aborting %s\n", enabled ?
 						"initialisation" : "reset");
 			return -ENODEV;
@@ -1537,7 +1593,7 @@ static int nvme_shutdown_ctrl(struct nvme_dev *dev)
 		if (fatal_signal_pending(current))
 			return -EINTR;
 		if (time_after(jiffies, timeout)) {
-			dev_err(&dev->pci_dev->dev,
+			dev_err(dev->dev,
 				"Device shutdown incomplete; abort shutdown\n");
 			return -ENODEV;
 		}
@@ -1547,10 +1603,9 @@ static int nvme_shutdown_ctrl(struct nvme_dev *dev)
 }
 
 static struct blk_mq_ops nvme_mq_admin_ops = {
-	.queue_rq	= nvme_admin_queue_rq,
+	.queue_rq	= nvme_queue_rq,
 	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_admin_init_hctx,
-	.exit_hctx	= nvme_exit_hctx,
 	.init_request	= nvme_admin_init_request,
 	.timeout	= nvme_timeout,
 };
@@ -1559,7 +1614,6 @@ static struct blk_mq_ops nvme_mq_ops = {
 	.queue_rq	= nvme_queue_rq,
 	.map_queue	= blk_mq_map_queue,
 	.init_hctx	= nvme_init_hctx,
-	.exit_hctx	= nvme_exit_hctx,
 	.init_request	= nvme_init_request,
 	.timeout	= nvme_timeout,
 };
@@ -1580,7 +1634,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
 		dev->admin_tagset.reserved_tags = 1;
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
-		dev->admin_tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
 		dev->admin_tagset.driver_data = dev;
 
@@ -1613,14 +1667,14 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
 
 	if (page_shift < dev_page_min) {
-		dev_err(&dev->pci_dev->dev,
+		dev_err(dev->dev,
 				"Minimum device page size (%u) too large for "
 				"host (%u)\n", 1 << dev_page_min,
 				1 << page_shift);
 		return -ENODEV;
 	}
 	if (page_shift > dev_page_max) {
-		dev_info(&dev->pci_dev->dev,
+		dev_info(dev->dev,
 				"Device maximum page size (%u) smaller than "
 				"host (%u); enabling work-around\n",
 				1 << dev_page_max, 1 << page_shift);
@@ -1668,131 +1722,51 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	return result;
 }
 
-struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
-				unsigned long addr, unsigned length)
-{
-	int i, err, count, nents, offset;
-	struct scatterlist *sg;
-	struct page **pages;
-	struct nvme_iod *iod;
-
-	if (addr & 3)
-		return ERR_PTR(-EINVAL);
-	if (!length || length > INT_MAX - PAGE_SIZE)
-		return ERR_PTR(-EINVAL);
-
-	offset = offset_in_page(addr);
-	count = DIV_ROUND_UP(offset + length, PAGE_SIZE);
-	pages = kcalloc(count, sizeof(*pages), GFP_KERNEL);
-	if (!pages)
-		return ERR_PTR(-ENOMEM);
-
-	err = get_user_pages_fast(addr, count, 1, pages);
-	if (err < count) {
-		count = err;
-		err = -EFAULT;
-		goto put_pages;
-	}
-
-	err = -ENOMEM;
-	iod = __nvme_alloc_iod(count, length, dev, 0, GFP_KERNEL);
-	if (!iod)
-		goto put_pages;
-
-	sg = iod->sg;
-	sg_init_table(sg, count);
-	for (i = 0; i < count; i++) {
-		sg_set_page(&sg[i], pages[i],
-			    min_t(unsigned, length, PAGE_SIZE - offset),
-			    offset);
-		length -= (PAGE_SIZE - offset);
-		offset = 0;
-	}
-	sg_mark_end(&sg[i - 1]);
-	iod->nents = count;
-
-	nents = dma_map_sg(&dev->pci_dev->dev, sg, count,
-				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-	if (!nents)
-		goto free_iod;
-
-	kfree(pages);
-	return iod;
-
- free_iod:
-	kfree(iod);
- put_pages:
-	for (i = 0; i < count; i++)
-		put_page(pages[i]);
-	kfree(pages);
-	return ERR_PTR(err);
-}
-
-void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
-			struct nvme_iod *iod)
-{
-	int i;
-
-	dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
-				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-
-	for (i = 0; i < iod->nents; i++)
-		put_page(sg_page(&iod->sg[i]));
-}
-
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_user_io io;
 	struct nvme_command c;
-	unsigned length, meta_len, prp_len;
+	unsigned length, meta_len;
 	int status, write;
-	struct nvme_iod *iod;
 	dma_addr_t meta_dma = 0;
 	void *meta = NULL;
+	void __user *metadata;
 
 	if (copy_from_user(&io, uio, sizeof(io)))
 		return -EFAULT;
-	length = (io.nblocks + 1) << ns->lba_shift;
-	meta_len = (io.nblocks + 1) * ns->ms;
-
-	if (meta_len && ((io.metadata & 3) || !io.metadata) && !ns->ext)
-		return -EINVAL;
-	else if (meta_len && ns->ext) {
-		length += meta_len;
-		meta_len = 0;
-	}
-
-	write = io.opcode & 1;
 
 	switch (io.opcode) {
 	case nvme_cmd_write:
 	case nvme_cmd_read:
 	case nvme_cmd_compare:
-		iod = nvme_map_user_pages(dev, write, io.addr, length);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	if (IS_ERR(iod))
-		return PTR_ERR(iod);
+	length = (io.nblocks + 1) << ns->lba_shift;
+	meta_len = (io.nblocks + 1) * ns->ms;
+	metadata = (void __user *)(unsigned long)io.metadata;
+	write = io.opcode & 1;
 
-	prp_len = nvme_setup_prps(dev, iod, length, GFP_KERNEL);
-	if (length != prp_len) {
-		status = -ENOMEM;
-		goto unmap;
+	if (ns->ext) {
+		length += meta_len;
+		meta_len = 0;
 	}
 	if (meta_len) {
-		meta = dma_alloc_coherent(&dev->pci_dev->dev, meta_len,
+		if (((io.metadata & 3) || !io.metadata) && !ns->ext)
+			return -EINVAL;
+
+		meta = dma_alloc_coherent(dev->dev, meta_len,
 						&meta_dma, GFP_KERNEL);
+
 		if (!meta) {
 			status = -ENOMEM;
 			goto unmap;
 		}
 		if (write) {
-			if (copy_from_user(meta, (void __user *)io.metadata,
-								meta_len)) {
+			if (copy_from_user(meta, metadata, meta_len)) {
 				status = -EFAULT;
 				goto unmap;
 			}
@@ -1810,20 +1784,17 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.reftag = cpu_to_le32(io.reftag);
 	c.rw.apptag = cpu_to_le16(io.apptag);
 	c.rw.appmask = cpu_to_le16(io.appmask);
-	c.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-	c.rw.prp2 = cpu_to_le64(iod->first_dma);
 	c.rw.metadata = cpu_to_le64(meta_dma);
-	status = nvme_submit_io_cmd(dev, ns, &c, NULL);
+
+	status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
+			(void __user *)io.addr, length, NULL, 0);
  unmap:
-	nvme_unmap_user_pages(dev, write, iod);
-	nvme_free_iod(dev, iod);
 	if (meta) {
 		if (status == NVME_SC_SUCCESS && !write) {
-			if (copy_to_user((void __user *)io.metadata, meta,
-								meta_len))
+			if (copy_to_user(metadata, meta, meta_len))
 				status = -EFAULT;
 		}
-		dma_free_coherent(&dev->pci_dev->dev, meta_len, meta, meta_dma);
+		dma_free_coherent(dev->dev, meta_len, meta, meta_dma);
 	}
 	return status;
 }
@@ -1833,9 +1804,8 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
 {
 	struct nvme_passthru_cmd cmd;
 	struct nvme_command c;
-	int status, length;
-	struct nvme_iod *uninitialized_var(iod);
-	unsigned timeout;
+	unsigned timeout = 0;
+	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
@@ -1855,46 +1825,17 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
 	c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
 	c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);
 
-	length = cmd.data_len;
-	if (cmd.data_len) {
-		iod = nvme_map_user_pages(dev, cmd.opcode & 1, cmd.addr,
-								length);
-		if (IS_ERR(iod))
-			return PTR_ERR(iod);
-		length = nvme_setup_prps(dev, iod, length, GFP_KERNEL);
-		c.common.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-		c.common.prp2 = cpu_to_le64(iod->first_dma);
-	}
-
-	timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
-								ADMIN_TIMEOUT;
-
-	if (length != cmd.data_len)
-		status = -ENOMEM;
-	else if (ns) {
-		struct request *req;
-
-		req = blk_mq_alloc_request(ns->queue, WRITE,
-						(GFP_KERNEL|__GFP_WAIT), false);
-		if (IS_ERR(req))
-			status = PTR_ERR(req);
-		else {
-			status = nvme_submit_sync_cmd(req, &c, &cmd.result,
-								timeout);
-			blk_mq_free_request(req);
-		}
-	} else
-		status = __nvme_submit_admin_cmd(dev, &c, &cmd.result, timeout);
+	if (cmd.timeout_ms)
+		timeout = msecs_to_jiffies(cmd.timeout_ms);
 
-	if (cmd.data_len) {
-		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
-		nvme_free_iod(dev, iod);
+	status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c,
+			NULL, (void __user *)cmd.addr, cmd.data_len,
+			&cmd.result, timeout);
+	if (status >= 0) {
+		if (put_user(cmd.result, &ucmd->result))
+			return -EFAULT;
 	}
 
-	if ((status >= 0) && copy_to_user(&ucmd->result, &cmd.result,
-							sizeof(cmd.result)))
-		status = -EFAULT;
-
 	return status;
 }
 
@@ -1986,23 +1927,18 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_id_ns *id;
-	dma_addr_t dma_addr;
 	u8 lbaf, pi_type;
 	u16 old_ms;
 	unsigned short bs;
 
-	id = dma_alloc_coherent(&dev->pci_dev->dev, 4096, &dma_addr,
-								GFP_KERNEL);
-	if (!id) {
-		dev_warn(&dev->pci_dev->dev, "%s: Memory alocation failure\n",
-								__func__);
-		return 0;
+	if (nvme_identify_ns(dev, ns->ns_id, &id)) {
+		dev_warn(dev->dev, "%s: Identify failure nvme%dn%d\n", __func__,
+						dev->instance, ns->ns_id);
+		return -ENODEV;
 	}
-	if (nvme_identify(dev, ns->ns_id, 0, dma_addr)) {
-		dev_warn(&dev->pci_dev->dev,
-			"identify failed ns:%d, setting capacity to 0\n",
-			ns->ns_id);
-		memset(id, 0, sizeof(*id));
+	if (id->ncap == 0) {
+		kfree(id);
+		return -ENODEV;
 	}
 
 	old_ms = ns->ms;
@@ -2036,7 +1972,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 								!ns->ext)
 		nvme_init_integrity(ns);
 
-	if (id->ncap == 0 || (ns->ms && !blk_get_integrity(disk)))
+	if (ns->ms && !blk_get_integrity(disk))
 		set_capacity(disk, 0);
 	else
 		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
@@ -2044,7 +1980,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	if (dev->oncs & NVME_CTRL_ONCS_DSM)
 		nvme_config_discard(ns);
 
-	dma_free_coherent(&dev->pci_dev->dev, 4096, id, dma_addr);
+	kfree(id);
 	return 0;
 }
 
@@ -2071,7 +2007,7 @@ static int nvme_kthread(void *data)
 				if (work_busy(&dev->reset_work))
 					continue;
 				list_del_init(&dev->node);
-				dev_warn(&dev->pci_dev->dev,
+				dev_warn(dev->dev,
 					"Failed status: %x, reset controller\n",
 					readl(&dev->bar->csts));
 				dev->reset_workfn = nvme_reset_failed_dev;
@@ -2103,7 +2039,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 {
 	struct nvme_ns *ns;
 	struct gendisk *disk;
-	int node = dev_to_node(&dev->pci_dev->dev);
+	int node = dev_to_node(dev->dev);
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
@@ -2151,11 +2087,16 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
 	 * requires it.
 	 */
 	set_capacity(disk, 0);
-	nvme_revalidate_disk(ns->disk);
+	if (nvme_revalidate_disk(ns->disk))
+		goto out_free_disk;
+
 	add_disk(ns->disk);
 	if (ns->ms)
 		revalidate_disk(ns->disk);
 	return;
+ out_free_disk:
+	kfree(disk);
+	list_del(&ns->list);
  out_free_queue:
 	blk_cleanup_queue(ns->queue);
  out_free_ns:
@@ -2186,8 +2127,7 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 	if (status < 0)
 		return status;
 	if (status > 0) {
-		dev_err(&dev->pci_dev->dev, "Could not set queue count (%d)\n",
-									status);
+		dev_err(dev->dev, "Could not set queue count (%d)\n", status);
 		return 0;
 	}
 	return min(result & 0xffff, result >> 16) + 1;
@@ -2201,7 +2141,7 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = dev->queues[0];
-	struct pci_dev *pdev = dev->pci_dev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int result, i, vecs, nr_io_queues, size;
 
 	nr_io_queues = num_possible_cpus();
@@ -2273,6 +2213,99 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	return result;
 }
 
+static void nvme_free_namespace(struct nvme_ns *ns)
+{
+	list_del(&ns->list);
+
+	spin_lock(&dev_list_lock);
+	ns->disk->private_data = NULL;
+	spin_unlock(&dev_list_lock);
+
+	put_disk(ns->disk);
+	kfree(ns);
+}
+
+static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
+	struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
+
+	return nsa->ns_id - nsb->ns_id;
+}
+
+static struct nvme_ns *nvme_find_ns(struct nvme_dev *dev, unsigned nsid)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry(ns, &dev->namespaces, list) {
+		if (ns->ns_id == nsid)
+			return ns;
+		if (ns->ns_id > nsid)
+			break;
+	}
+	return NULL;
+}
+
+static inline bool nvme_io_incapable(struct nvme_dev *dev)
+{
+	return (!dev->bar || readl(&dev->bar->csts) & NVME_CSTS_CFS ||
+							dev->online_queues < 2);
+}
+
+static void nvme_ns_remove(struct nvme_ns *ns)
+{
+	bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue);
+
+	if (kill)
+		blk_set_queue_dying(ns->queue);
+	if (ns->disk->flags & GENHD_FL_UP) {
+		if (blk_get_integrity(ns->disk))
+			blk_integrity_unregister(ns->disk);
+		del_gendisk(ns->disk);
+	}
+	if (kill || !blk_queue_dying(ns->queue)) {
+		blk_mq_abort_requeue_list(ns->queue);
+		blk_cleanup_queue(ns->queue);
+        }
+}
+
+static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
+{
+	struct nvme_ns *ns, *next;
+	unsigned i;
+
+	for (i = 1; i <= nn; i++) {
+		ns = nvme_find_ns(dev, i);
+		if (ns) {
+			if (revalidate_disk(ns->disk)) {
+				nvme_ns_remove(ns);
+				nvme_free_namespace(ns);
+			}
+		} else
+			nvme_alloc_ns(dev, i);
+	}
+	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
+		if (ns->ns_id > nn) {
+			nvme_ns_remove(ns);
+			nvme_free_namespace(ns);
+		}
+	}
+	list_sort(NULL, &dev->namespaces, ns_cmp);
+}
+
+static void nvme_dev_scan(struct work_struct *work)
+{
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work);
+	struct nvme_id_ctrl *ctrl;
+
+	if (!dev->tagset.tags)
+		return;
+	if (nvme_identify_ctrl(dev, &ctrl))
+		return;
+	nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
+	kfree(ctrl);
+}
+
 /*
  * Return: error value if an error occurred setting up the queues or calling
  * Identify Device.  0 if these succeeded, even if adding some of the
@@ -2281,26 +2314,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
  */
 static int nvme_dev_add(struct nvme_dev *dev)
 {
-	struct pci_dev *pdev = dev->pci_dev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	int res;
-	unsigned nn, i;
+	unsigned nn;
 	struct nvme_id_ctrl *ctrl;
-	void *mem;
-	dma_addr_t dma_addr;
 	int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
 
-	mem = dma_alloc_coherent(&pdev->dev, 4096, &dma_addr, GFP_KERNEL);
-	if (!mem)
-		return -ENOMEM;
-
-	res = nvme_identify(dev, 0, 1, dma_addr);
+	res = nvme_identify_ctrl(dev, &ctrl);
 	if (res) {
-		dev_err(&pdev->dev, "Identify Controller failed (%d)\n", res);
-		dma_free_coherent(&dev->pci_dev->dev, 4096, mem, dma_addr);
+		dev_err(dev->dev, "Identify Controller failed (%d)\n", res);
 		return -EIO;
 	}
 
-	ctrl = mem;
 	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
@@ -2322,12 +2347,12 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		} else
 			dev->max_hw_sectors = max_hw_sectors;
 	}
-	dma_free_coherent(&dev->pci_dev->dev, 4096, mem, dma_addr);
+	kfree(ctrl);
 
 	dev->tagset.ops = &nvme_mq_ops;
 	dev->tagset.nr_hw_queues = dev->online_queues - 1;
 	dev->tagset.timeout = NVME_IO_TIMEOUT;
-	dev->tagset.numa_node = dev_to_node(&dev->pci_dev->dev);
+	dev->tagset.numa_node = dev_to_node(dev->dev);
 	dev->tagset.queue_depth =
 				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
 	dev->tagset.cmd_size = nvme_cmd_size(dev);
@@ -2337,9 +2362,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	if (blk_mq_alloc_tag_set(&dev->tagset))
 		return 0;
 
-	for (i = 1; i <= nn; i++)
-		nvme_alloc_ns(dev, i);
-
+	schedule_work(&dev->scan_work);
 	return 0;
 }
 
@@ -2347,7 +2370,7 @@ static int nvme_dev_map(struct nvme_dev *dev)
 {
 	u64 cap;
 	int bars, result = -ENOMEM;
-	struct pci_dev *pdev = dev->pci_dev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pci_enable_device_mem(pdev))
 		return result;
@@ -2361,8 +2384,8 @@ static int nvme_dev_map(struct nvme_dev *dev)
 	if (pci_request_selected_regions(pdev, bars, "nvme"))
 		goto disable_pci;
 
-	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) &&
-	    dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))
+	if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
+	    dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
 		goto disable;
 
 	dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
@@ -2403,19 +2426,21 @@ static int nvme_dev_map(struct nvme_dev *dev)
 
 static void nvme_dev_unmap(struct nvme_dev *dev)
 {
-	if (dev->pci_dev->msi_enabled)
-		pci_disable_msi(dev->pci_dev);
-	else if (dev->pci_dev->msix_enabled)
-		pci_disable_msix(dev->pci_dev);
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
+
+	if (pdev->msi_enabled)
+		pci_disable_msi(pdev);
+	else if (pdev->msix_enabled)
+		pci_disable_msix(pdev);
 
 	if (dev->bar) {
 		iounmap(dev->bar);
 		dev->bar = NULL;
-		pci_release_regions(dev->pci_dev);
+		pci_release_regions(pdev);
 	}
 
-	if (pci_is_enabled(dev->pci_dev))
-		pci_disable_device(dev->pci_dev);
+	if (pci_is_enabled(pdev))
+		pci_disable_device(pdev);
 }
 
 struct nvme_delq_ctx {
@@ -2534,7 +2559,7 @@ static void nvme_disable_io_queues(struct nvme_dev *dev)
 					&worker, "nvme%d", dev->instance);
 
 	if (IS_ERR(kworker_task)) {
-		dev_err(&dev->pci_dev->dev,
+		dev_err(dev->dev,
 			"Failed to create queue del task\n");
 		for (i = dev->queue_count - 1; i > 0; i--)
 			nvme_disable_queue(dev, i);
@@ -2585,9 +2610,9 @@ static void nvme_freeze_queues(struct nvme_dev *dev)
 	list_for_each_entry(ns, &dev->namespaces, list) {
 		blk_mq_freeze_queue_start(ns->queue);
 
-		spin_lock(ns->queue->queue_lock);
+		spin_lock_irq(ns->queue->queue_lock);
 		queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
-		spin_unlock(ns->queue->queue_lock);
+		spin_unlock_irq(ns->queue->queue_lock);
 
 		blk_mq_cancel_requeue_work(ns->queue);
 		blk_mq_stop_hw_queues(ns->queue);
@@ -2637,29 +2662,19 @@ static void nvme_dev_remove(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns;
 
-	list_for_each_entry(ns, &dev->namespaces, list) {
-		if (ns->disk->flags & GENHD_FL_UP) {
-			if (blk_get_integrity(ns->disk))
-				blk_integrity_unregister(ns->disk);
-			del_gendisk(ns->disk);
-		}
-		if (!blk_queue_dying(ns->queue)) {
-			blk_mq_abort_requeue_list(ns->queue);
-			blk_cleanup_queue(ns->queue);
-		}
-	}
+	list_for_each_entry(ns, &dev->namespaces, list)
+		nvme_ns_remove(ns);
 }
 
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
-	struct device *dmadev = &dev->pci_dev->dev;
-	dev->prp_page_pool = dma_pool_create("prp list page", dmadev,
+	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
 						PAGE_SIZE, PAGE_SIZE, 0);
 	if (!dev->prp_page_pool)
 		return -ENOMEM;
 
 	/* Optimisation for I/Os between 4k and 128k */
-	dev->prp_small_pool = dma_pool_create("prp list 256", dmadev,
+	dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev,
 						256, 256, 0);
 	if (!dev->prp_small_pool) {
 		dma_pool_destroy(dev->prp_page_pool);
@@ -2707,23 +2722,15 @@ static void nvme_free_namespaces(struct nvme_dev *dev)
 {
 	struct nvme_ns *ns, *next;
 
-	list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
-		list_del(&ns->list);
-
-		spin_lock(&dev_list_lock);
-		ns->disk->private_data = NULL;
-		spin_unlock(&dev_list_lock);
-
-		put_disk(ns->disk);
-		kfree(ns);
-	}
+	list_for_each_entry_safe(ns, next, &dev->namespaces, list)
+		nvme_free_namespace(ns);
 }
 
 static void nvme_free_dev(struct kref *kref)
 {
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 
-	pci_dev_put(dev->pci_dev);
+	put_device(dev->dev);
 	put_device(dev->device);
 	nvme_free_namespaces(dev);
 	nvme_release_instance(dev);
@@ -2779,6 +2786,9 @@ static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 			return -ENOTTY;
 		ns = list_first_entry(&dev->namespaces, struct nvme_ns, list);
 		return nvme_user_cmd(dev, ns, (void __user *)arg);
+	case NVME_IOCTL_RESET:
+		dev_warn(dev->dev, "resetting controller\n");
+		return nvme_reset(dev);
 	default:
 		return -ENOTTY;
 	}
@@ -2800,11 +2810,11 @@ static void nvme_set_irq_hints(struct nvme_dev *dev)
 	for (i = 0; i < dev->online_queues; i++) {
 		nvmeq = dev->queues[i];
 
-		if (!nvmeq->hctx)
+		if (!nvmeq->tags || !(*nvmeq->tags))
 			continue;
 
 		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
-							nvmeq->hctx->cpumask);
+					blk_mq_tags_cpumask(*nvmeq->tags));
 	}
 }
 
@@ -2867,7 +2877,7 @@ static int nvme_dev_start(struct nvme_dev *dev)
 static int nvme_remove_dead_ctrl(void *arg)
 {
 	struct nvme_dev *dev = (struct nvme_dev *)arg;
-	struct pci_dev *pdev = dev->pci_dev;
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 
 	if (pci_get_drvdata(pdev))
 		pci_stop_and_remove_bus_device_locked(pdev);
@@ -2897,6 +2907,7 @@ static int nvme_dev_resume(struct nvme_dev *dev)
 		spin_unlock(&dev_list_lock);
 	} else {
 		nvme_unfreeze_queues(dev);
+		schedule_work(&dev->scan_work);
 		nvme_set_irq_hints(dev);
 	}
 	return 0;
@@ -2906,11 +2917,11 @@ static void nvme_dev_reset(struct nvme_dev *dev)
 {
 	nvme_dev_shutdown(dev);
 	if (nvme_dev_resume(dev)) {
-		dev_warn(&dev->pci_dev->dev, "Device failed to resume\n");
+		dev_warn(dev->dev, "Device failed to resume\n");
 		kref_get(&dev->kref);
 		if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
 							dev->instance))) {
-			dev_err(&dev->pci_dev->dev,
+			dev_err(dev->dev,
 				"Failed to start controller remove task\n");
 			kref_put(&dev->kref, nvme_free_dev);
 		}
@@ -2929,6 +2940,44 @@ static void nvme_reset_workfn(struct work_struct *work)
 	dev->reset_workfn(work);
 }
 
+static int nvme_reset(struct nvme_dev *dev)
+{
+	int ret = -EBUSY;
+
+	if (!dev->admin_q || blk_queue_dying(dev->admin_q))
+		return -ENODEV;
+
+	spin_lock(&dev_list_lock);
+	if (!work_pending(&dev->reset_work)) {
+		dev->reset_workfn = nvme_reset_failed_dev;
+		queue_work(nvme_workq, &dev->reset_work);
+		ret = 0;
+	}
+	spin_unlock(&dev_list_lock);
+
+	if (!ret) {
+		flush_work(&dev->reset_work);
+		return 0;
+	}
+
+	return ret;
+}
+
+static ssize_t nvme_sysfs_reset(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	struct nvme_dev *ndev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = nvme_reset(ndev);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
+
 static void nvme_async_probe(struct work_struct *work);
 static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
@@ -2954,7 +3003,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->reset_workfn = nvme_reset_failed_dev;
 	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
-	dev->pci_dev = pci_dev_get(pdev);
+	dev->dev = get_device(&pdev->dev);
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
 	if (result)
@@ -2973,18 +3022,27 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release_pools;
 	}
 	get_device(dev->device);
+	dev_set_drvdata(dev->device, dev);
+
+	result = device_create_file(dev->device, &dev_attr_reset_controller);
+	if (result)
+		goto put_dev;
 
 	INIT_LIST_HEAD(&dev->node);
+	INIT_WORK(&dev->scan_work, nvme_dev_scan);
 	INIT_WORK(&dev->probe_work, nvme_async_probe);
 	schedule_work(&dev->probe_work);
 	return 0;
 
+ put_dev:
+	device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
+	put_device(dev->device);
  release_pools:
 	nvme_release_prp_pools(dev);
  release:
 	nvme_release_instance(dev);
  put_pci:
-	pci_dev_put(dev->pci_dev);
+	put_device(dev->dev);
  free:
 	kfree(dev->queues);
 	kfree(dev->entry);
@@ -3009,10 +3067,12 @@ static void nvme_async_probe(struct work_struct *work)
 	nvme_set_irq_hints(dev);
 	return;
  reset:
+	spin_lock(&dev_list_lock);
 	if (!work_busy(&dev->reset_work)) {
 		dev->reset_workfn = nvme_reset_failed_dev;
 		queue_work(nvme_workq, &dev->reset_work);
 	}
+	spin_unlock(&dev_list_lock);
 }
 
 static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
@@ -3042,6 +3102,8 @@ static void nvme_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->probe_work);
 	flush_work(&dev->reset_work);
+	flush_work(&dev->scan_work);
+	device_remove_file(dev->device, &dev_attr_reset_controller);
 	nvme_dev_shutdown(dev);
 	nvme_dev_remove(dev);
 	nvme_dev_remove_admin(dev);
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 6b736b00f63e..e5a63f06fb0f 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -41,15 +41,13 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <asm/unaligned.h>
 #include <scsi/sg.h>
 #include <scsi/scsi.h>
 
 
 static int sg_version_num = 30534;	/* 2 digits for each component */
 
-#define SNTI_TRANSLATION_SUCCESS			0
-#define SNTI_INTERNAL_ERROR				1
-
 /* VPD Page Codes */
 #define VPD_SUPPORTED_PAGES				0x00
 #define VPD_SERIAL_NUMBER				0x80
@@ -58,49 +56,14 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define VPD_BLOCK_LIMITS				0xB0
 #define VPD_BLOCK_DEV_CHARACTERISTICS			0xB1
 
-/* CDB offsets */
-#define REPORT_LUNS_CDB_ALLOC_LENGTH_OFFSET		6
-#define REPORT_LUNS_SR_OFFSET				2
-#define READ_CAP_16_CDB_ALLOC_LENGTH_OFFSET		10
-#define REQUEST_SENSE_CDB_ALLOC_LENGTH_OFFSET		4
-#define REQUEST_SENSE_DESC_OFFSET			1
-#define REQUEST_SENSE_DESC_MASK				0x01
-#define DESCRIPTOR_FORMAT_SENSE_DATA_TYPE		1
-#define INQUIRY_EVPD_BYTE_OFFSET			1
-#define INQUIRY_PAGE_CODE_BYTE_OFFSET			2
-#define INQUIRY_EVPD_BIT_MASK				1
-#define INQUIRY_CDB_ALLOCATION_LENGTH_OFFSET		3
-#define START_STOP_UNIT_CDB_IMMED_OFFSET		1
-#define START_STOP_UNIT_CDB_IMMED_MASK			0x1
-#define START_STOP_UNIT_CDB_POWER_COND_MOD_OFFSET	3
-#define START_STOP_UNIT_CDB_POWER_COND_MOD_MASK		0xF
-#define START_STOP_UNIT_CDB_POWER_COND_OFFSET		4
-#define START_STOP_UNIT_CDB_POWER_COND_MASK		0xF0
-#define START_STOP_UNIT_CDB_NO_FLUSH_OFFSET		4
-#define START_STOP_UNIT_CDB_NO_FLUSH_MASK		0x4
-#define START_STOP_UNIT_CDB_START_OFFSET		4
-#define START_STOP_UNIT_CDB_START_MASK			0x1
-#define WRITE_BUFFER_CDB_MODE_OFFSET			1
-#define WRITE_BUFFER_CDB_MODE_MASK			0x1F
-#define WRITE_BUFFER_CDB_BUFFER_ID_OFFSET		2
-#define WRITE_BUFFER_CDB_BUFFER_OFFSET_OFFSET		3
-#define WRITE_BUFFER_CDB_PARM_LIST_LENGTH_OFFSET	6
-#define FORMAT_UNIT_CDB_FORMAT_PROT_INFO_OFFSET		1
-#define FORMAT_UNIT_CDB_FORMAT_PROT_INFO_MASK		0xC0
-#define FORMAT_UNIT_CDB_FORMAT_PROT_INFO_SHIFT		6
-#define FORMAT_UNIT_CDB_LONG_LIST_OFFSET		1
-#define FORMAT_UNIT_CDB_LONG_LIST_MASK			0x20
-#define FORMAT_UNIT_CDB_FORMAT_DATA_OFFSET		1
-#define FORMAT_UNIT_CDB_FORMAT_DATA_MASK		0x10
+/* format unit paramter list offsets */
 #define FORMAT_UNIT_SHORT_PARM_LIST_LEN			4
 #define FORMAT_UNIT_LONG_PARM_LIST_LEN			8
 #define FORMAT_UNIT_PROT_INT_OFFSET			3
 #define FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET		0
 #define FORMAT_UNIT_PROT_FIELD_USAGE_MASK		0x07
-#define UNMAP_CDB_PARAM_LIST_LENGTH_OFFSET		7
 
 /* Misc. defines */
-#define NIBBLE_SHIFT					4
 #define FIXED_SENSE_DATA				0x70
 #define DESC_FORMAT_SENSE_DATA				0x72
 #define FIXED_SENSE_DATA_ADD_LENGTH			10
@@ -144,27 +107,6 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define EXTENDED_INQUIRY_DATA_PAGE_LENGTH		0x3C
 #define RESERVED_FIELD					0
 
-/* SCSI READ/WRITE Defines */
-#define IO_CDB_WP_MASK					0xE0
-#define IO_CDB_WP_SHIFT					5
-#define IO_CDB_FUA_MASK					0x8
-#define IO_6_CDB_LBA_OFFSET				0
-#define IO_6_CDB_LBA_MASK				0x001FFFFF
-#define IO_6_CDB_TX_LEN_OFFSET				4
-#define IO_6_DEFAULT_TX_LEN				256
-#define IO_10_CDB_LBA_OFFSET				2
-#define IO_10_CDB_TX_LEN_OFFSET				7
-#define IO_10_CDB_WP_OFFSET				1
-#define IO_10_CDB_FUA_OFFSET				1
-#define IO_12_CDB_LBA_OFFSET				2
-#define IO_12_CDB_TX_LEN_OFFSET				6
-#define IO_12_CDB_WP_OFFSET				1
-#define IO_12_CDB_FUA_OFFSET				1
-#define IO_16_CDB_FUA_OFFSET				1
-#define IO_16_CDB_WP_OFFSET				1
-#define IO_16_CDB_LBA_OFFSET				2
-#define IO_16_CDB_TX_LEN_OFFSET				10
-
 /* Mode Sense/Select defines */
 #define MODE_PAGE_INFO_EXCEP				0x1C
 #define MODE_PAGE_CACHING				0x08
@@ -179,23 +121,14 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define MODE_PAGE_INF_EXC_LEN				0x0C
 #define MODE_PAGE_ALL_LEN				0x54
 #define MODE_SENSE6_MPH_SIZE				4
-#define MODE_SENSE6_ALLOC_LEN_OFFSET			4
-#define MODE_SENSE_PAGE_CONTROL_OFFSET			2
 #define MODE_SENSE_PAGE_CONTROL_MASK			0xC0
 #define MODE_SENSE_PAGE_CODE_OFFSET			2
 #define MODE_SENSE_PAGE_CODE_MASK			0x3F
-#define MODE_SENSE_LLBAA_OFFSET				1
 #define MODE_SENSE_LLBAA_MASK				0x10
 #define MODE_SENSE_LLBAA_SHIFT				4
-#define MODE_SENSE_DBD_OFFSET				1
 #define MODE_SENSE_DBD_MASK				8
 #define MODE_SENSE_DBD_SHIFT				3
 #define MODE_SENSE10_MPH_SIZE				8
-#define MODE_SENSE10_ALLOC_LEN_OFFSET			7
-#define MODE_SELECT_CDB_PAGE_FORMAT_OFFSET		1
-#define MODE_SELECT_CDB_SAVE_PAGES_OFFSET		1
-#define MODE_SELECT_6_CDB_PARAM_LIST_LENGTH_OFFSET	4
-#define MODE_SELECT_10_CDB_PARAM_LIST_LENGTH_OFFSET	7
 #define MODE_SELECT_CDB_PAGE_FORMAT_MASK		0x10
 #define MODE_SELECT_CDB_SAVE_PAGES_MASK			0x1
 #define MODE_SELECT_6_BD_OFFSET				3
@@ -221,14 +154,11 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH		0x07
 #define LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE		0x2F
 #define LOG_PAGE_TEMPERATURE_PAGE			0x0D
-#define LOG_SENSE_CDB_SP_OFFSET				1
 #define LOG_SENSE_CDB_SP_NOT_ENABLED			0
-#define LOG_SENSE_CDB_PC_OFFSET				2
 #define LOG_SENSE_CDB_PC_MASK				0xC0
 #define LOG_SENSE_CDB_PC_SHIFT				6
 #define LOG_SENSE_CDB_PC_CUMULATIVE_VALUES		1
 #define LOG_SENSE_CDB_PAGE_CODE_MASK			0x3F
-#define LOG_SENSE_CDB_ALLOC_LENGTH_OFFSET		7
 #define REMAINING_INFO_EXCP_PAGE_LENGTH			0x8
 #define LOG_INFO_EXCP_PAGE_LENGTH			0xC
 #define REMAINING_TEMP_PAGE_LENGTH			0xC
@@ -278,77 +208,11 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define SCSI_ASCQ_POWER_LOSS_EXPECTED			0x08
 #define SCSI_ASCQ_INVALID_LUN_ID			0x09
 
-/**
- * DEVICE_SPECIFIC_PARAMETER in mode parameter header (see sbc2r16) to
- * enable DPOFUA support type 0x10 value.
- */
-#define DEVICE_SPECIFIC_PARAMETER			0
-#define VPD_ID_DESCRIPTOR_LENGTH sizeof(VPD_IDENTIFICATION_DESCRIPTOR)
-
-/* MACROs to extract information from CDBs */
-
-#define GET_OPCODE(cdb)		cdb[0]
-
-#define GET_U8_FROM_CDB(cdb, index) (cdb[index] << 0)
-
-#define GET_U16_FROM_CDB(cdb, index) ((cdb[index] << 8) | (cdb[index + 1] << 0))
-
-#define GET_U24_FROM_CDB(cdb, index) ((cdb[index] << 16) | \
-(cdb[index + 1] <<  8) | \
-(cdb[index + 2] <<  0))
-
-#define GET_U32_FROM_CDB(cdb, index) ((cdb[index] << 24) | \
-(cdb[index + 1] << 16) | \
-(cdb[index + 2] <<  8) | \
-(cdb[index + 3] <<  0))
-
-#define GET_U64_FROM_CDB(cdb, index) ((((u64)cdb[index]) << 56) | \
-(((u64)cdb[index + 1]) << 48) | \
-(((u64)cdb[index + 2]) << 40) | \
-(((u64)cdb[index + 3]) << 32) | \
-(((u64)cdb[index + 4]) << 24) | \
-(((u64)cdb[index + 5]) << 16) | \
-(((u64)cdb[index + 6]) <<  8) | \
-(((u64)cdb[index + 7]) <<  0))
-
-/* Inquiry Helper Macros */
-#define GET_INQ_EVPD_BIT(cdb) \
-((GET_U8_FROM_CDB(cdb, INQUIRY_EVPD_BYTE_OFFSET) &		\
-INQUIRY_EVPD_BIT_MASK) ? 1 : 0)
-
-#define GET_INQ_PAGE_CODE(cdb)					\
-(GET_U8_FROM_CDB(cdb, INQUIRY_PAGE_CODE_BYTE_OFFSET))
-
-#define GET_INQ_ALLOC_LENGTH(cdb)				\
-(GET_U16_FROM_CDB(cdb, INQUIRY_CDB_ALLOCATION_LENGTH_OFFSET))
-
-/* Report LUNs Helper Macros */
-#define GET_REPORT_LUNS_ALLOC_LENGTH(cdb)			\
-(GET_U32_FROM_CDB(cdb, REPORT_LUNS_CDB_ALLOC_LENGTH_OFFSET))
-
-/* Read Capacity Helper Macros */
-#define GET_READ_CAP_16_ALLOC_LENGTH(cdb)			\
-(GET_U32_FROM_CDB(cdb, READ_CAP_16_CDB_ALLOC_LENGTH_OFFSET))
-
-#define IS_READ_CAP_16(cdb)					\
-((cdb[0] == SERVICE_ACTION_IN_16 && cdb[1] == SAI_READ_CAPACITY_16) ? 1 : 0)
-
-/* Request Sense Helper Macros */
-#define GET_REQUEST_SENSE_ALLOC_LENGTH(cdb)			\
-(GET_U8_FROM_CDB(cdb, REQUEST_SENSE_CDB_ALLOC_LENGTH_OFFSET))
-
-/* Mode Sense Helper Macros */
-#define GET_MODE_SENSE_DBD(cdb)					\
-((GET_U8_FROM_CDB(cdb, MODE_SENSE_DBD_OFFSET) & MODE_SENSE_DBD_MASK) >>	\
-MODE_SENSE_DBD_SHIFT)
-
-#define GET_MODE_SENSE_LLBAA(cdb)				\
-((GET_U8_FROM_CDB(cdb, MODE_SENSE_LLBAA_OFFSET) &		\
-MODE_SENSE_LLBAA_MASK) >> MODE_SENSE_LLBAA_SHIFT)
-
-#define GET_MODE_SENSE_MPH_SIZE(cdb10)				\
-(cdb10 ? MODE_SENSE10_MPH_SIZE : MODE_SENSE6_MPH_SIZE)
-
+/* copied from drivers/usb/gadget/function/storage_common.h */
+static inline u32 get_unaligned_be24(u8 *buf)
+{
+	return 0xffffff & (u32) get_unaligned_be32(buf - 1);
+}
 
 /* Struct to gather data that needs to be extracted from a SCSI CDB.
    Not conforming to any particular CDB variant, but compatible with all. */
@@ -369,8 +233,6 @@ struct nvme_trans_io_cdb {
 static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
 								unsigned long n)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-	unsigned long not_copied;
 	int i;
 	void *index = from;
 	size_t remaining = n;
@@ -380,29 +242,25 @@ static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
 		struct sg_iovec sgl;
 
 		for (i = 0; i < hdr->iovec_count; i++) {
-			not_copied = copy_from_user(&sgl, hdr->dxferp +
+			if (copy_from_user(&sgl, hdr->dxferp +
 						i * sizeof(struct sg_iovec),
-						sizeof(struct sg_iovec));
-			if (not_copied)
+						sizeof(struct sg_iovec)))
 				return -EFAULT;
 			xfer_len = min(remaining, sgl.iov_len);
-			not_copied = copy_to_user(sgl.iov_base, index,
-								xfer_len);
-			if (not_copied) {
-				res = -EFAULT;
-				break;
-			}
+			if (copy_to_user(sgl.iov_base, index, xfer_len))
+				return -EFAULT;
+
 			index += xfer_len;
 			remaining -= xfer_len;
 			if (remaining == 0)
 				break;
 		}
-		return res;
+		return 0;
 	}
-	not_copied = copy_to_user(hdr->dxferp, from, n);
-	if (not_copied)
-		res = -EFAULT;
-	return res;
+
+	if (copy_to_user(hdr->dxferp, from, n))
+		return -EFAULT;
+	return 0;
 }
 
 /* Copy data from userspace memory */
@@ -410,8 +268,6 @@ static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
 static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
 								unsigned long n)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-	unsigned long not_copied;
 	int i;
 	void *index = to;
 	size_t remaining = n;
@@ -421,30 +277,24 @@ static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
 		struct sg_iovec sgl;
 
 		for (i = 0; i < hdr->iovec_count; i++) {
-			not_copied = copy_from_user(&sgl, hdr->dxferp +
+			if (copy_from_user(&sgl, hdr->dxferp +
 						i * sizeof(struct sg_iovec),
-						sizeof(struct sg_iovec));
-			if (not_copied)
+						sizeof(struct sg_iovec)))
 				return -EFAULT;
 			xfer_len = min(remaining, sgl.iov_len);
-			not_copied = copy_from_user(index, sgl.iov_base,
-								xfer_len);
-			if (not_copied) {
-				res = -EFAULT;
-				break;
-			}
+			if (copy_from_user(index, sgl.iov_base, xfer_len))
+				return -EFAULT;
 			index += xfer_len;
 			remaining -= xfer_len;
 			if (remaining == 0)
 				break;
 		}
-		return res;
+		return 0;
 	}
 
-	not_copied = copy_from_user(to, hdr->dxferp, n);
-	if (not_copied)
-		res = -EFAULT;
-	return res;
+	if (copy_from_user(to, hdr->dxferp, n))
+		return -EFAULT;
+	return 0;
 }
 
 /* Status/Sense Buffer Writeback */
@@ -452,7 +302,6 @@ static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
 static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8 sense_key,
 				 u8 asc, u8 ascq)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	u8 xfer_len;
 	u8 resp[DESC_FMT_SENSE_DATA_SIZE];
 
@@ -477,25 +326,29 @@ static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8 sense_key,
 		xfer_len = min_t(u8, hdr->mx_sb_len, DESC_FMT_SENSE_DATA_SIZE);
 		hdr->sb_len_wr = xfer_len;
 		if (copy_to_user(hdr->sbp, resp, xfer_len) > 0)
-			res = -EFAULT;
+			return -EFAULT;
 	}
 
-	return res;
+	return 0;
 }
 
+/*
+ * Take a status code from a lowlevel routine, and if it was a positive NVMe
+ * error code update the sense data based on it.  In either case the passed
+ * in value is returned again, unless an -EFAULT from copy_to_user overrides
+ * it.
+ */
 static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc)
 {
 	u8 status, sense_key, asc, ascq;
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 
 	/* For non-nvme (Linux) errors, simply return the error code */
 	if (nvme_sc < 0)
 		return nvme_sc;
 
 	/* Mask DNR, More, and reserved fields */
-	nvme_sc &= 0x7FF;
-
-	switch (nvme_sc) {
+	switch (nvme_sc & 0x7FF) {
 	/* Generic Command Status */
 	case NVME_SC_SUCCESS:
 		status = SAM_STAT_GOOD;
@@ -662,8 +515,7 @@ static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc)
 	}
 
 	res = nvme_trans_completion(hdr, status, sense_key, asc, ascq);
-
-	return res;
+	return res ? res : nvme_sc;
 }
 
 /* INQUIRY Helper Functions */
@@ -673,10 +525,8 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
 					int alloc_len)
 {
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ns *id_ns;
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	int xfer_len;
 	u8 resp_data_format = 0x02;
@@ -684,31 +534,17 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
 	u8 cmdque = 0x01 << 1;
 	u8 fw_offset = sizeof(dev->firmware_rev);
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-				&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out_dma;
-	}
-
 	/* nvme ns identify - use DPS value for PROTECT field */
-	nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+	nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 	res = nvme_trans_status_code(hdr, nvme_sc);
-	/*
-	 * If nvme_sc was -ve, res will be -ve here.
-	 * If nvme_sc was +ve, the status would bace been translated, and res
-	 *  can only be 0 or -ve.
-	 *    - If 0 && nvme_sc > 0, then go into next if where res gets nvme_sc
-	 *    - If -ve, return because its a Linux error.
-	 */
 	if (res)
-		goto out_free;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_free;
-	}
-	id_ns = mem;
-	(id_ns->dps) ? (protect = 0x01) : (protect = 0);
+		return res;
+
+	if (id_ns->dps)
+		protect = 0x01;
+	else
+		protect = 0;
+	kfree(id_ns);
 
 	memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
 	inq_response[2] = VERSION_SPC_4;
@@ -725,20 +561,13 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
 	strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
 
 	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
-	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- out_free:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out_dma:
-	return res;
+	return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 }
 
 static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr, u8 *inq_response,
 					int alloc_len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	int xfer_len;
 
 	memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
@@ -752,9 +581,7 @@ static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns,
 	inq_response[9] = INQ_BDEV_LIMITS_PAGE;
 
 	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
-	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
-	return res;
+	return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 }
 
 static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
@@ -762,7 +589,6 @@ static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
 					int alloc_len)
 {
 	struct nvme_dev *dev = ns->dev;
-	int res = SNTI_TRANSLATION_SUCCESS;
 	int xfer_len;
 
 	memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
@@ -771,53 +597,42 @@ static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
 	strncpy(&inq_response[4], dev->serial, INQ_SERIAL_NUMBER_LENGTH);
 
 	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
-	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
-	return res;
+	return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 }
 
 static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					u8 *inq_response, int alloc_len)
 {
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	int xfer_len;
 	__be32 tmp_id = cpu_to_be32(ns->ns_id);
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-					&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out_dma;
-	}
-
 	memset(inq_response, 0, alloc_len);
 	inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE;    /* Page Code */
 	if (readl(&dev->bar->vs) >= NVME_VS(1, 1)) {
-		struct nvme_id_ns *id_ns = mem;
-		void *eui = id_ns->eui64;
-		int len = sizeof(id_ns->eui64);
+		struct nvme_id_ns *id_ns;
+		void *eui;
+		int len;
 
-		nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+		nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 		res = nvme_trans_status_code(hdr, nvme_sc);
 		if (res)
-			goto out_free;
-		if (nvme_sc) {
-			res = nvme_sc;
-			goto out_free;
-		}
+			return res;
 
+		eui = id_ns->eui64;
+		len = sizeof(id_ns->eui64);
 		if (readl(&dev->bar->vs) >= NVME_VS(1, 2)) {
 			if (bitmap_empty(eui, len * 8)) {
 				eui = id_ns->nguid;
 				len = sizeof(id_ns->nguid);
 			}
 		}
-		if (bitmap_empty(eui, len * 8))
+		if (bitmap_empty(eui, len * 8)) {
+			kfree(id_ns);
 			goto scsi_string;
+		}
 
 		inq_response[3] = 4 + len; /* Page Length */
 		/* Designation Descriptor start */
@@ -826,14 +641,14 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		inq_response[6] = 0x00;    /* Rsvd */
 		inq_response[7] = len;     /* Designator Length */
 		memcpy(&inq_response[8], eui, len);
+		kfree(id_ns);
 	} else {
  scsi_string:
 		if (alloc_len < 72) {
-			res = nvme_trans_completion(hdr,
+			return nvme_trans_completion(hdr,
 					SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-			goto out_free;
 		}
 		inq_response[3] = 0x48;    /* Page Length */
 		/* Designation Descriptor start */
@@ -842,30 +657,22 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		inq_response[6] = 0x00;    /* Rsvd */
 		inq_response[7] = 0x44;    /* Designator Length */
 
-		sprintf(&inq_response[8], "%04x", dev->pci_dev->vendor);
+		sprintf(&inq_response[8], "%04x", to_pci_dev(dev->dev)->vendor);
 		memcpy(&inq_response[12], dev->model, sizeof(dev->model));
 		sprintf(&inq_response[52], "%04x", tmp_id);
 		memcpy(&inq_response[56], dev->serial, sizeof(dev->serial));
 	}
 	xfer_len = alloc_len;
-	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- out_free:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out_dma:
-	return res;
+	return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 }
 
 static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					int alloc_len)
 {
 	u8 *inq_response;
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ctrl *id_ctrl;
 	struct nvme_id_ns *id_ns;
 	int xfer_len;
@@ -878,45 +685,32 @@ static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	u8 luiclr = 0x01;
 
 	inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
-	if (inq_response == NULL) {
-		res = -ENOMEM;
-		goto out_mem;
-	}
-
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-							&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out_dma;
-	}
+	if (inq_response == NULL)
+		return -ENOMEM;
 
-	/* nvme ns identify */
-	nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+	nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_free;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_free;
-	}
-	id_ns = mem;
-	spt = spt_lut[(id_ns->dpc) & 0x07] << 3;
-	(id_ns->dps) ? (protect = 0x01) : (protect = 0);
+		goto out_free_inq;
+
+	spt = spt_lut[id_ns->dpc & 0x07] << 3;
+	if (id_ns->dps)
+		protect = 0x01;
+	else
+		protect = 0;
+	kfree(id_ns);
+
 	grd_chk = protect << 2;
 	app_chk = protect << 1;
 	ref_chk = protect;
 
-	/* nvme controller identify */
-	nvme_sc = nvme_identify(dev, 0, 1, dma_addr);
+	nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_free;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_free;
-	}
-	id_ctrl = mem;
+		goto out_free_inq;
+
 	v_sup = id_ctrl->vwc;
+	kfree(id_ctrl);
 
 	memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
 	inq_response[1] = INQ_EXTENDED_INQUIRY_DATA_PAGE;    /* Page Code */
@@ -932,19 +726,16 @@ static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
 	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
 
- out_free:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out_dma:
+ out_free_inq:
 	kfree(inq_response);
- out_mem:
 	return res;
 }
 
 static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					u8 *inq_response, int alloc_len)
 {
-	__be32 max_sectors = cpu_to_be32(queue_max_hw_sectors(ns->queue));
+	__be32 max_sectors = cpu_to_be32(
+		nvme_block_nr(ns, queue_max_hw_sectors(ns->queue)));
 	__be32 max_discard = cpu_to_be32(ns->queue->limits.max_discard_sectors);
 	__be32 discard_desc_count = cpu_to_be32(0x100);
 
@@ -964,7 +755,7 @@ static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					int alloc_len)
 {
 	u8 *inq_response;
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int xfer_len;
 
 	inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
@@ -993,7 +784,7 @@ static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					int alloc_len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int xfer_len;
 	u8 *log_response;
 
@@ -1021,47 +812,30 @@ static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr, int alloc_len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int xfer_len;
 	u8 *log_response;
-	struct nvme_command c;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_smart_log *smart_log;
-	dma_addr_t dma_addr;
-	void *mem;
 	u8 temp_c;
 	u16 temp_k;
 
 	log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
-	if (log_response == NULL) {
-		res = -ENOMEM;
-		goto out_mem;
-	}
+	if (log_response == NULL)
+		return -ENOMEM;
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev,
-					sizeof(struct nvme_smart_log),
-					&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out_dma;
-	}
+	res = nvme_get_log_page(dev, &smart_log);
+	if (res < 0)
+		goto out_free_response;
 
-	/* Get SMART Log Page */
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = nvme_admin_get_log_page;
-	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
-	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
-	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c = LOG_TEMP_UNKNOWN;
 	} else {
-		smart_log = mem;
 		temp_k = (smart_log->temperature[1] << 8) +
 				(smart_log->temperature[0]);
 		temp_c = temp_k - KELVIN_TEMP_FACTOR;
 	}
+	kfree(smart_log);
 
 	log_response[0] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
 	/* Subpage=0x00, Page Length MSB=0 */
@@ -1077,59 +851,39 @@ static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
 	xfer_len = min(alloc_len, LOG_INFO_EXCP_PAGE_LENGTH);
 	res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
 
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_smart_log),
-			  mem, dma_addr);
- out_dma:
+ out_free_response:
 	kfree(log_response);
- out_mem:
 	return res;
 }
 
 static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					int alloc_len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int xfer_len;
 	u8 *log_response;
-	struct nvme_command c;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_smart_log *smart_log;
-	dma_addr_t dma_addr;
-	void *mem;
 	u32 feature_resp;
 	u8 temp_c_cur, temp_c_thresh;
 	u16 temp_k;
 
 	log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
-	if (log_response == NULL) {
-		res = -ENOMEM;
-		goto out_mem;
-	}
+	if (log_response == NULL)
+		return -ENOMEM;
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev,
-					sizeof(struct nvme_smart_log),
-					&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out_dma;
-	}
+	res = nvme_get_log_page(dev, &smart_log);
+	if (res < 0)
+		goto out_free_response;
 
-	/* Get SMART Log Page */
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = nvme_admin_get_log_page;
-	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
-	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
-	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c_cur = LOG_TEMP_UNKNOWN;
 	} else {
-		smart_log = mem;
 		temp_k = (smart_log->temperature[1] << 8) +
 				(smart_log->temperature[0]);
 		temp_c_cur = temp_k - KELVIN_TEMP_FACTOR;
 	}
+	kfree(smart_log);
 
 	/* Get Features for Temp Threshold */
 	res = nvme_get_features(dev, NVME_FEAT_TEMP_THRESH, 0, 0,
@@ -1158,11 +912,8 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	xfer_len = min(alloc_len, LOG_TEMP_PAGE_LENGTH);
 	res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
 
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_smart_log),
-			  mem, dma_addr);
- out_dma:
+ out_free_response:
 	kfree(log_response);
- out_mem:
 	return res;
 }
 
@@ -1173,59 +924,45 @@ static int nvme_trans_fill_mode_parm_hdr(u8 *resp, int len, u8 cdb10, u8 llbaa,
 {
 	/* Quick check to make sure I don't stomp on my own memory... */
 	if ((cdb10 && len < 8) || (!cdb10 && len < 4))
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 
 	if (cdb10) {
 		resp[0] = (mode_data_length & 0xFF00) >> 8;
 		resp[1] = (mode_data_length & 0x00FF);
-		/* resp[2] and [3] are zero */
+		resp[3] = 0x10 /* DPOFUA */;
 		resp[4] = llbaa;
 		resp[5] = RESERVED_FIELD;
 		resp[6] = (blk_desc_len & 0xFF00) >> 8;
 		resp[7] = (blk_desc_len & 0x00FF);
 	} else {
 		resp[0] = (mode_data_length & 0x00FF);
-		/* resp[1] and [2] are zero */
+		resp[2] = 0x10 /* DPOFUA */;
 		resp[3] = (blk_desc_len & 0x00FF);
 	}
 
-	return SNTI_TRANSLATION_SUCCESS;
+	return 0;
 }
 
 static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 				    u8 *resp, int len, u8 llbaa)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ns *id_ns;
 	u8 flbas;
 	u32 lba_length;
 
 	if (llbaa == 0 && len < MODE_PAGE_BLK_DES_LEN)
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 	else if (llbaa > 0 && len < MODE_PAGE_LLBAA_BLK_DES_LEN)
-		return SNTI_INTERNAL_ERROR;
-
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-							&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out;
-	}
+		return -EINVAL;
 
-	/* nvme ns identify */
-	nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+	nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_dma;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_dma;
-	}
-	id_ns = mem;
+		return res;
+
 	flbas = (id_ns->flbas) & 0x0F;
 	lba_length = (1 << (id_ns->lbaf[flbas].ds));
 
@@ -1245,10 +982,7 @@ static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		memcpy(&resp[12], &tmp_len, sizeof(u32));
 	}
 
- out_dma:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out:
+	kfree(id_ns);
 	return res;
 }
 
@@ -1257,7 +991,7 @@ static int nvme_trans_fill_control_page(struct nvme_ns *ns,
 					int len)
 {
 	if (len < MODE_PAGE_CONTROL_LEN)
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 
 	resp[0] = MODE_PAGE_CONTROL;
 	resp[1] = MODE_PAGE_CONTROL_LEN_FIELD;
@@ -1271,78 +1005,69 @@ static int nvme_trans_fill_control_page(struct nvme_ns *ns,
 	resp[9] = 0xFF;
 	/* Bytes 10,11: Extended selftest completion time = 0x0000 */
 
-	return SNTI_TRANSLATION_SUCCESS;
+	return 0;
 }
 
 static int nvme_trans_fill_caching_page(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr,
 					u8 *resp, int len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
 	u32 feature_resp;
 	u8 vwc;
 
 	if (len < MODE_PAGE_CACHING_LEN)
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 
 	nvme_sc = nvme_get_features(dev, NVME_FEAT_VOLATILE_WC, 0, 0,
 								&feature_resp);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out;
-	}
+		return res;
+
 	vwc = feature_resp & 0x00000001;
 
 	resp[0] = MODE_PAGE_CACHING;
 	resp[1] = MODE_PAGE_CACHING_LEN_FIELD;
 	resp[2] = vwc << 2;
-
- out:
-	return res;
+	return 0;
 }
 
 static int nvme_trans_fill_pow_cnd_page(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr, u8 *resp,
 					int len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-
 	if (len < MODE_PAGE_POW_CND_LEN)
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 
 	resp[0] = MODE_PAGE_POWER_CONDITION;
 	resp[1] = MODE_PAGE_POW_CND_LEN_FIELD;
 	/* All other bytes are zero */
 
-	return res;
+	return 0;
 }
 
 static int nvme_trans_fill_inf_exc_page(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr, u8 *resp,
 					int len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-
 	if (len < MODE_PAGE_INF_EXC_LEN)
-		return SNTI_INTERNAL_ERROR;
+		return -EINVAL;
 
 	resp[0] = MODE_PAGE_INFO_EXCEP;
 	resp[1] = MODE_PAGE_INF_EXC_LEN_FIELD;
 	resp[2] = 0x88;
 	/* All other bytes are zero */
 
-	return res;
+	return 0;
 }
 
 static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 				     u8 *resp, int len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u16 mode_pages_offset_1 = 0;
 	u16 mode_pages_offset_2, mode_pages_offset_3, mode_pages_offset_4;
 
@@ -1352,23 +1077,18 @@ static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 	res = nvme_trans_fill_caching_page(ns, hdr, &resp[mode_pages_offset_1],
 					MODE_PAGE_CACHING_LEN);
-	if (res != SNTI_TRANSLATION_SUCCESS)
-		goto out;
+	if (res)
+		return res;
 	res = nvme_trans_fill_control_page(ns, hdr, &resp[mode_pages_offset_2],
 					MODE_PAGE_CONTROL_LEN);
-	if (res != SNTI_TRANSLATION_SUCCESS)
-		goto out;
+	if (res)
+		return res;
 	res = nvme_trans_fill_pow_cnd_page(ns, hdr, &resp[mode_pages_offset_3],
 					MODE_PAGE_POW_CND_LEN);
-	if (res != SNTI_TRANSLATION_SUCCESS)
-		goto out;
-	res = nvme_trans_fill_inf_exc_page(ns, hdr, &resp[mode_pages_offset_4],
+	if (res)
+		return res;
+	return nvme_trans_fill_inf_exc_page(ns, hdr, &resp[mode_pages_offset_4],
 					MODE_PAGE_INF_EXC_LEN);
-	if (res != SNTI_TRANSLATION_SUCCESS)
-		goto out;
-
- out:
-	return res;
 }
 
 static inline int nvme_trans_get_blk_desc_len(u8 dbd, u8 llbaa)
@@ -1389,7 +1109,7 @@ static int nvme_trans_mode_page_create(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr, u8 *, int),
 					u16 mode_pages_tot_len)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int xfer_len;
 	u8 *response;
 	u8 dbd, llbaa;
@@ -1398,9 +1118,10 @@ static int nvme_trans_mode_page_create(struct nvme_ns *ns,
 	u16 mode_pages_offset_1;
 	u16 blk_desc_len, blk_desc_offset, mode_data_length;
 
-	dbd = GET_MODE_SENSE_DBD(cmd);
-	llbaa = GET_MODE_SENSE_LLBAA(cmd);
-	mph_size = GET_MODE_SENSE_MPH_SIZE(cdb10);
+	dbd = (cmd[1] & MODE_SENSE_DBD_MASK) >> MODE_SENSE_DBD_SHIFT;
+	llbaa = (cmd[1] & MODE_SENSE_LLBAA_MASK) >> MODE_SENSE_LLBAA_SHIFT;
+	mph_size = cdb10 ? MODE_SENSE10_MPH_SIZE : MODE_SENSE6_MPH_SIZE;
+
 	blk_desc_len = nvme_trans_get_blk_desc_len(dbd, llbaa);
 
 	resp_size = mph_size + blk_desc_len + mode_pages_tot_len;
@@ -1418,18 +1139,18 @@ static int nvme_trans_mode_page_create(struct nvme_ns *ns,
 
 	res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size, cdb10,
 					llbaa, mode_data_length, blk_desc_len);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out_free;
 	if (blk_desc_len > 0) {
 		res = nvme_trans_fill_blk_desc(ns, hdr,
 					       &response[blk_desc_offset],
 					       blk_desc_len, llbaa);
-		if (res != SNTI_TRANSLATION_SUCCESS)
+		if (res)
 			goto out_free;
 	}
 	res = mode_page_fill_func(ns, hdr, &response[mode_pages_offset_1],
 					mode_pages_tot_len);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out_free;
 
 	xfer_len = min(alloc_len, resp_size);
@@ -1484,33 +1205,20 @@ static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns,
 static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 						u8 pc, u8 pcmod, u8 start)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ctrl *id_ctrl;
 	int lowest_pow_st;	/* max npss = lowest power consumption */
 	unsigned ps_desired = 0;
 
-	/* NVMe Controller Identify */
-	mem = dma_alloc_coherent(&dev->pci_dev->dev,
-				sizeof(struct nvme_id_ctrl),
-				&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out;
-	}
-	nvme_sc = nvme_identify(dev, 0, 1, dma_addr);
+	nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_dma;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_dma;
-	}
-	id_ctrl = mem;
+		return res;
+
 	lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
+	kfree(id_ctrl);
 
 	switch (pc) {
 	case NVME_POWER_STATE_START_VALID:
@@ -1550,79 +1258,48 @@ static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	}
 	nvme_sc = nvme_set_features(dev, NVME_FEAT_POWER_MGMT, ps_desired, 0,
 				    NULL);
-	res = nvme_trans_status_code(hdr, nvme_sc);
-	if (res)
-		goto out_dma;
-	if (nvme_sc)
-		res = nvme_sc;
- out_dma:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ctrl), mem,
-			  dma_addr);
- out:
-	return res;
+	return nvme_trans_status_code(hdr, nvme_sc);
 }
 
-/* Write Buffer Helper Functions */
-/* Also using this for Format Unit with hdr passed as NULL, and buffer_id, 0 */
+static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
+					u8 buffer_id)
+{
+	struct nvme_command c;
+	int nvme_sc;
 
-static int nvme_trans_send_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_activate_fw;
+	c.common.cdw10[0] = cpu_to_le32(buffer_id | NVME_FWACT_REPL_ACTV);
+
+	nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
+	return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+static int nvme_trans_send_download_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					u8 opcode, u32 tot_len, u32 offset,
 					u8 buffer_id)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
 	struct nvme_command c;
-	struct nvme_iod *iod = NULL;
-	unsigned length;
 
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = opcode;
-	if (opcode == nvme_admin_download_fw) {
-		if (hdr->iovec_count > 0) {
-			/* Assuming SGL is not allowed for this command */
-			res = nvme_trans_completion(hdr,
-						SAM_STAT_CHECK_CONDITION,
-						ILLEGAL_REQUEST,
-						SCSI_ASC_INVALID_CDB,
-						SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-			goto out;
-		}
-		iod = nvme_map_user_pages(dev, DMA_TO_DEVICE,
-				(unsigned long)hdr->dxferp, tot_len);
-		if (IS_ERR(iod)) {
-			res = PTR_ERR(iod);
-			goto out;
-		}
-		length = nvme_setup_prps(dev, iod, tot_len, GFP_KERNEL);
-		if (length != tot_len) {
-			res = -ENOMEM;
-			goto out_unmap;
-		}
-
-		c.dlfw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-		c.dlfw.prp2 = cpu_to_le64(iod->first_dma);
-		c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
-		c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
-	} else if (opcode == nvme_admin_activate_fw) {
-		u32 cdw10 = buffer_id | NVME_FWACT_REPL_ACTV;
-		c.common.cdw10[0] = cpu_to_le32(cdw10);
+	if (hdr->iovec_count > 0) {
+		/* Assuming SGL is not allowed for this command */
+		return nvme_trans_completion(hdr,
+					SAM_STAT_CHECK_CONDITION,
+					ILLEGAL_REQUEST,
+					SCSI_ASC_INVALID_CDB,
+					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 	}
 
-	nvme_sc = nvme_submit_admin_cmd(dev, &c, NULL);
-	res = nvme_trans_status_code(hdr, nvme_sc);
-	if (res)
-		goto out_unmap;
-	if (nvme_sc)
-		res = nvme_sc;
-
- out_unmap:
-	if (opcode == nvme_admin_download_fw) {
-		nvme_unmap_user_pages(dev, DMA_TO_DEVICE, iod);
-		nvme_free_iod(dev, iod);
-	}
- out:
-	return res;
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_admin_download_fw;
+	c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
+	c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
+
+	nvme_sc = __nvme_submit_sync_cmd(dev->admin_q, &c, NULL,
+			hdr->dxferp, tot_len, NULL, 0);
+	return nvme_trans_status_code(hdr, nvme_sc);
 }
 
 /* Mode Select Helper Functions */
@@ -1685,7 +1362,7 @@ static void nvme_trans_modesel_save_bd(struct nvme_ns *ns, u8 *parm_list,
 static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					u8 *mode_page, u8 page_code)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
 	unsigned dword11;
@@ -1696,12 +1373,6 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		nvme_sc = nvme_set_features(dev, NVME_FEAT_VOLATILE_WC, dword11,
 					    0, NULL);
 		res = nvme_trans_status_code(hdr, nvme_sc);
-		if (res)
-			break;
-		if (nvme_sc) {
-			res = nvme_sc;
-			break;
-		}
 		break;
 	case MODE_PAGE_CONTROL:
 		break;
@@ -1713,8 +1384,6 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 						ILLEGAL_REQUEST,
 						SCSI_ASC_INVALID_PARAMETER,
 						SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-			if (!res)
-				res = SNTI_INTERNAL_ERROR;
 			break;
 		}
 		break;
@@ -1722,8 +1391,6 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-		if (!res)
-			res = SNTI_INTERNAL_ERROR;
 		break;
 	}
 
@@ -1734,7 +1401,7 @@ static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					u8 *cmd, u16 parm_list_len, u8 pf,
 					u8 sp, u8 cdb10)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u8 *parm_list;
 	u16 bd_len;
 	u8 llbaa = 0;
@@ -1750,7 +1417,7 @@ static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	}
 
 	res = nvme_trans_copy_from_user(hdr, parm_list, parm_list_len);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out_mem;
 
 	nvme_trans_modesel_get_bd_len(parm_list, cdb10, &bd_len, &llbaa);
@@ -1788,7 +1455,7 @@ static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		mp_size = parm_list[index + 1] + 2;
 		res = nvme_trans_modesel_get_mp(ns, hdr, &parm_list[index],
 								page_code);
-		if (res != SNTI_TRANSLATION_SUCCESS)
+		if (res)
 			break;
 		index += mp_size;
 	} while (index < parm_list_len);
@@ -1804,12 +1471,9 @@ static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
 					     struct sg_io_hdr *hdr)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
-	struct nvme_id_ns *id_ns;
 	u8 flbas;
 
 	/*
@@ -1820,22 +1484,12 @@ static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
 	 */
 
 	if (ns->mode_select_num_blocks == 0 || ns->mode_select_block_len == 0) {
-		mem = dma_alloc_coherent(&dev->pci_dev->dev,
-			sizeof(struct nvme_id_ns), &dma_addr, GFP_KERNEL);
-		if (mem == NULL) {
-			res = -ENOMEM;
-			goto out;
-		}
-		/* nvme ns identify */
-		nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+		struct nvme_id_ns *id_ns;
+
+		nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 		res = nvme_trans_status_code(hdr, nvme_sc);
 		if (res)
-			goto out_dma;
-		if (nvme_sc) {
-			res = nvme_sc;
-			goto out_dma;
-		}
-		id_ns = mem;
+			return res;
 
 		if (ns->mode_select_num_blocks == 0)
 			ns->mode_select_num_blocks = le64_to_cpu(id_ns->ncap);
@@ -1844,18 +1498,17 @@ static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
 			ns->mode_select_block_len =
 						(1 << (id_ns->lbaf[flbas].ds));
 		}
- out_dma:
-		dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-				  mem, dma_addr);
+
+		kfree(id_ns);
 	}
- out:
-	return res;
+
+	return 0;
 }
 
 static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8 len,
 					u8 format_prot_info, u8 *nvme_pf_code)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u8 *parm_list;
 	u8 pf_usage, pf_code;
 
@@ -1865,7 +1518,7 @@ static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8 len,
 		goto out;
 	}
 	res = nvme_trans_copy_from_user(hdr, parm_list, len);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out_mem;
 
 	if ((parm_list[FORMAT_UNIT_IMMED_OFFSET] &
@@ -1915,11 +1568,9 @@ static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8 len,
 static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 				   u8 prot_info)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ns *id_ns;
 	u8 i;
 	u8 flbas, nlbaf;
@@ -1928,22 +1579,11 @@ static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	struct nvme_command c;
 
 	/* Loop thru LBAF's in id_ns to match reqd lbaf, put in cdw10 */
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-							&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out;
-	}
-	/* nvme ns identify */
-	nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+	nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_dma;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_dma;
-	}
-	id_ns = mem;
+		return res;
+
 	flbas = (id_ns->flbas) & 0x0F;
 	nlbaf = id_ns->nlbaf;
 
@@ -1971,69 +1611,13 @@ static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	c.format.nsid = cpu_to_le32(ns->ns_id);
 	c.format.cdw10 = cpu_to_le32(cdw10);
 
-	nvme_sc = nvme_submit_admin_cmd(dev, &c, NULL);
+	nvme_sc = nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
 	res = nvme_trans_status_code(hdr, nvme_sc);
-	if (res)
-		goto out_dma;
-	if (nvme_sc)
-		res = nvme_sc;
 
- out_dma:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out:
+	kfree(id_ns);
 	return res;
 }
 
-/* Read/Write Helper Functions */
-
-static inline void nvme_trans_get_io_cdb6(u8 *cmd,
-					struct nvme_trans_io_cdb *cdb_info)
-{
-	cdb_info->fua = 0;
-	cdb_info->prot_info = 0;
-	cdb_info->lba = GET_U32_FROM_CDB(cmd, IO_6_CDB_LBA_OFFSET) &
-					IO_6_CDB_LBA_MASK;
-	cdb_info->xfer_len = GET_U8_FROM_CDB(cmd, IO_6_CDB_TX_LEN_OFFSET);
-
-	/* sbc3r27 sec 5.32 - TRANSFER LEN of 0 implies a 256 Block transfer */
-	if (cdb_info->xfer_len == 0)
-		cdb_info->xfer_len = IO_6_DEFAULT_TX_LEN;
-}
-
-static inline void nvme_trans_get_io_cdb10(u8 *cmd,
-					struct nvme_trans_io_cdb *cdb_info)
-{
-	cdb_info->fua = GET_U8_FROM_CDB(cmd, IO_10_CDB_FUA_OFFSET) &
-					IO_CDB_FUA_MASK;
-	cdb_info->prot_info = GET_U8_FROM_CDB(cmd, IO_10_CDB_WP_OFFSET) &
-					IO_CDB_WP_MASK >> IO_CDB_WP_SHIFT;
-	cdb_info->lba = GET_U32_FROM_CDB(cmd, IO_10_CDB_LBA_OFFSET);
-	cdb_info->xfer_len = GET_U16_FROM_CDB(cmd, IO_10_CDB_TX_LEN_OFFSET);
-}
-
-static inline void nvme_trans_get_io_cdb12(u8 *cmd,
-					struct nvme_trans_io_cdb *cdb_info)
-{
-	cdb_info->fua = GET_U8_FROM_CDB(cmd, IO_12_CDB_FUA_OFFSET) &
-					IO_CDB_FUA_MASK;
-	cdb_info->prot_info = GET_U8_FROM_CDB(cmd, IO_12_CDB_WP_OFFSET) &
-					IO_CDB_WP_MASK >> IO_CDB_WP_SHIFT;
-	cdb_info->lba = GET_U32_FROM_CDB(cmd, IO_12_CDB_LBA_OFFSET);
-	cdb_info->xfer_len = GET_U32_FROM_CDB(cmd, IO_12_CDB_TX_LEN_OFFSET);
-}
-
-static inline void nvme_trans_get_io_cdb16(u8 *cmd,
-					struct nvme_trans_io_cdb *cdb_info)
-{
-	cdb_info->fua = GET_U8_FROM_CDB(cmd, IO_16_CDB_FUA_OFFSET) &
-					IO_CDB_FUA_MASK;
-	cdb_info->prot_info = GET_U8_FROM_CDB(cmd, IO_16_CDB_WP_OFFSET) &
-					IO_CDB_WP_MASK >> IO_CDB_WP_SHIFT;
-	cdb_info->lba = GET_U64_FROM_CDB(cmd, IO_16_CDB_LBA_OFFSET);
-	cdb_info->xfer_len = GET_U32_FROM_CDB(cmd, IO_16_CDB_TX_LEN_OFFSET);
-}
-
 static inline u32 nvme_trans_io_get_num_cmds(struct sg_io_hdr *hdr,
 					struct nvme_trans_io_cdb *cdb_info,
 					u32 max_blocks)
@@ -2063,11 +1647,8 @@ static u16 nvme_trans_io_get_control(struct nvme_ns *ns,
 static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 				struct nvme_trans_io_cdb *cdb_info, u8 is_write)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-	int nvme_sc;
-	struct nvme_dev *dev = ns->dev;
+	int nvme_sc = NVME_SC_SUCCESS;
 	u32 num_cmds;
-	struct nvme_iod *iod;
 	u64 unit_len;
 	u64 unit_num_blocks;	/* Number of blocks to xfer in each nvme cmd */
 	u32 retcode;
@@ -2118,45 +1699,20 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		control = nvme_trans_io_get_control(ns, cdb_info);
 		c.rw.control = cpu_to_le16(control);
 
-		iod = nvme_map_user_pages(dev,
-			(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-			(unsigned long)next_mapping_addr, unit_len);
-		if (IS_ERR(iod)) {
-			res = PTR_ERR(iod);
-			goto out;
-		}
-		retcode = nvme_setup_prps(dev, iod, unit_len, GFP_KERNEL);
-		if (retcode != unit_len) {
-			nvme_unmap_user_pages(dev,
-				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-				iod);
-			nvme_free_iod(dev, iod);
-			res = -ENOMEM;
-			goto out;
+		if (get_capacity(ns->disk) - unit_num_blocks <
+				cdb_info->lba + nvme_offset) {
+			nvme_sc = NVME_SC_LBA_RANGE;
+			break;
 		}
-		c.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
-		c.rw.prp2 = cpu_to_le64(iod->first_dma);
+		nvme_sc = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
+				next_mapping_addr, unit_len, NULL, 0);
+		if (nvme_sc)
+			break;
 
 		nvme_offset += unit_num_blocks;
-
-		nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
-		if (nvme_sc != NVME_SC_SUCCESS) {
-			nvme_unmap_user_pages(dev,
-				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-				iod);
-			nvme_free_iod(dev, iod);
-			res = nvme_trans_status_code(hdr, nvme_sc);
-			goto out;
-		}
-		nvme_unmap_user_pages(dev,
-				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
-				iod);
-		nvme_free_iod(dev, iod);
 	}
-	res = nvme_trans_status_code(hdr, NVME_SC_SUCCESS);
 
- out:
-	return res;
+	return nvme_trans_status_code(hdr, nvme_sc);
 }
 
 
@@ -2165,8 +1721,8 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
-	struct nvme_trans_io_cdb cdb_info;
+	int res = 0;
+	struct nvme_trans_io_cdb cdb_info = { 0, };
 	u8 opcode = cmd[0];
 	u64 xfer_bytes;
 	u64 sum_iov_len = 0;
@@ -2174,27 +1730,52 @@ static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write,
 	int i;
 	size_t not_copied;
 
-	/* Extract Fields from CDB */
+	/*
+	 * The FUA and WPROTECT fields are not supported in 6-byte CDBs,
+	 * but always in the same place for all others.
+	 */
+	switch (opcode) {
+	case WRITE_6:
+	case READ_6:
+		break;
+	default:
+		cdb_info.fua = cmd[1] & 0x8;
+		cdb_info.prot_info = (cmd[1] & 0xe0) >> 5;
+		if (cdb_info.prot_info && !ns->pi_type) {
+			return nvme_trans_completion(hdr,
+					SAM_STAT_CHECK_CONDITION,
+					ILLEGAL_REQUEST,
+					SCSI_ASC_INVALID_CDB,
+					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
+		}
+	}
+
 	switch (opcode) {
 	case WRITE_6:
 	case READ_6:
-		nvme_trans_get_io_cdb6(cmd, &cdb_info);
+		cdb_info.lba = get_unaligned_be24(&cmd[1]);
+		cdb_info.xfer_len = cmd[4];
+		if (cdb_info.xfer_len == 0)
+			cdb_info.xfer_len = 256;
 		break;
 	case WRITE_10:
 	case READ_10:
-		nvme_trans_get_io_cdb10(cmd, &cdb_info);
+		cdb_info.lba = get_unaligned_be32(&cmd[2]);
+		cdb_info.xfer_len = get_unaligned_be16(&cmd[7]);
 		break;
 	case WRITE_12:
 	case READ_12:
-		nvme_trans_get_io_cdb12(cmd, &cdb_info);
+		cdb_info.lba = get_unaligned_be32(&cmd[2]);
+		cdb_info.xfer_len = get_unaligned_be32(&cmd[6]);
 		break;
 	case WRITE_16:
 	case READ_16:
-		nvme_trans_get_io_cdb16(cmd, &cdb_info);
+		cdb_info.lba = get_unaligned_be64(&cmd[2]);
+		cdb_info.xfer_len = get_unaligned_be32(&cmd[10]);
 		break;
 	default:
 		/* Will never really reach here */
-		res = SNTI_INTERNAL_ERROR;
+		res = -EIO;
 		goto out;
 	}
 
@@ -2236,7 +1817,7 @@ static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write,
 
 	/* Send NVMe IO Command(s) */
 	res = nvme_trans_do_nvme_io(ns, hdr, &cdb_info, is_write);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out;
 
  out:
@@ -2246,17 +1827,18 @@ static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write,
 static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	u8 evpd;
 	u8 page_code;
 	int alloc_len;
 	u8 *inq_response;
 
-	evpd = GET_INQ_EVPD_BIT(cmd);
-	page_code = GET_INQ_PAGE_CODE(cmd);
-	alloc_len = GET_INQ_ALLOC_LENGTH(cmd);
+	evpd = cmd[1] & 0x01;
+	page_code = cmd[2];
+	alloc_len = get_unaligned_be16(&cmd[3]);
 
-	inq_response = kmalloc(alloc_len, GFP_KERNEL);
+	inq_response = kmalloc(max(alloc_len, STANDARD_INQUIRY_LENGTH),
+				GFP_KERNEL);
 	if (inq_response == NULL) {
 		res = -ENOMEM;
 		goto out_mem;
@@ -2314,29 +1896,27 @@ static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u16 alloc_len;
-	u8 sp;
 	u8 pc;
 	u8 page_code;
 
-	sp = GET_U8_FROM_CDB(cmd, LOG_SENSE_CDB_SP_OFFSET);
-	if (sp != LOG_SENSE_CDB_SP_NOT_ENABLED) {
+	if (cmd[1] != LOG_SENSE_CDB_SP_NOT_ENABLED) {
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 		goto out;
 	}
-	pc = GET_U8_FROM_CDB(cmd, LOG_SENSE_CDB_PC_OFFSET);
-	page_code = pc & LOG_SENSE_CDB_PAGE_CODE_MASK;
-	pc = (pc & LOG_SENSE_CDB_PC_MASK) >> LOG_SENSE_CDB_PC_SHIFT;
+
+	page_code = cmd[2] & LOG_SENSE_CDB_PAGE_CODE_MASK;
+	pc = (cmd[2] & LOG_SENSE_CDB_PC_MASK) >> LOG_SENSE_CDB_PC_SHIFT;
 	if (pc != LOG_SENSE_CDB_PC_CUMULATIVE_VALUES) {
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 		goto out;
 	}
-	alloc_len = GET_U16_FROM_CDB(cmd, LOG_SENSE_CDB_ALLOC_LENGTH_OFFSET);
+	alloc_len = get_unaligned_be16(&cmd[7]);
 	switch (page_code) {
 	case LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE:
 		res = nvme_trans_log_supp_pages(ns, hdr, alloc_len);
@@ -2361,24 +1941,18 @@ static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	u8 cdb10 = 0;
 	u16 parm_list_len;
 	u8 page_format;
 	u8 save_pages;
 
-	page_format = GET_U8_FROM_CDB(cmd, MODE_SELECT_CDB_PAGE_FORMAT_OFFSET);
-	page_format &= MODE_SELECT_CDB_PAGE_FORMAT_MASK;
+	page_format = cmd[1] & MODE_SELECT_CDB_PAGE_FORMAT_MASK;
+	save_pages = cmd[1] & MODE_SELECT_CDB_SAVE_PAGES_MASK;
 
-	save_pages = GET_U8_FROM_CDB(cmd, MODE_SELECT_CDB_SAVE_PAGES_OFFSET);
-	save_pages &= MODE_SELECT_CDB_SAVE_PAGES_MASK;
-
-	if (GET_OPCODE(cmd) == MODE_SELECT) {
-		parm_list_len = GET_U8_FROM_CDB(cmd,
-				MODE_SELECT_6_CDB_PARAM_LIST_LENGTH_OFFSET);
+	if (cmd[0] == MODE_SELECT) {
+		parm_list_len = cmd[4];
 	} else {
-		parm_list_len = GET_U16_FROM_CDB(cmd,
-				MODE_SELECT_10_CDB_PARAM_LIST_LENGTH_OFFSET);
+		parm_list_len = cmd[7];
 		cdb10 = 1;
 	}
 
@@ -2387,42 +1961,36 @@ static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		 * According to SPC-4 r24, a paramter list length field of 0
 		 * shall not be considered an error
 		 */
-		res = nvme_trans_modesel_data(ns, hdr, cmd, parm_list_len,
+		return nvme_trans_modesel_data(ns, hdr, cmd, parm_list_len,
 						page_format, save_pages, cdb10);
 	}
 
-	return res;
+	return 0;
 }
 
 static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	u16 alloc_len;
 	u8 cdb10 = 0;
-	u8 page_code;
-	u8 pc;
 
-	if (GET_OPCODE(cmd) == MODE_SENSE) {
-		alloc_len = GET_U8_FROM_CDB(cmd, MODE_SENSE6_ALLOC_LEN_OFFSET);
+	if (cmd[0] == MODE_SENSE) {
+		alloc_len = cmd[4];
 	} else {
-		alloc_len = GET_U16_FROM_CDB(cmd,
-						MODE_SENSE10_ALLOC_LEN_OFFSET);
+		alloc_len = get_unaligned_be16(&cmd[7]);
 		cdb10 = 1;
 	}
 
-	pc = GET_U8_FROM_CDB(cmd, MODE_SENSE_PAGE_CONTROL_OFFSET) &
-						MODE_SENSE_PAGE_CONTROL_MASK;
-	if (pc != MODE_SENSE_PC_CURRENT_VALUES) {
+	if ((cmd[2] & MODE_SENSE_PAGE_CONTROL_MASK) !=
+			MODE_SENSE_PC_CURRENT_VALUES) {
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 		goto out;
 	}
 
-	page_code = GET_U8_FROM_CDB(cmd, MODE_SENSE_PAGE_CODE_OFFSET) &
-					MODE_SENSE_PAGE_CODE_MASK;
-	switch (page_code) {
+	switch (cmd[2] & MODE_SENSE_PAGE_CODE_MASK) {
 	case MODE_PAGE_CACHING:
 		res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
 						cdb10,
@@ -2465,47 +2033,34 @@ static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 }
 
 static int nvme_trans_read_capacity(struct nvme_ns *ns, struct sg_io_hdr *hdr,
-							u8 *cmd)
+							u8 *cmd, u8 cdb16)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
-	u32 alloc_len = READ_CAP_10_RESP_SIZE;
-	u32 resp_size = READ_CAP_10_RESP_SIZE;
+	u32 alloc_len;
+	u32 resp_size;
 	u32 xfer_len;
-	u8 cdb16;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ns *id_ns;
 	u8 *response;
 
-	cdb16 = IS_READ_CAP_16(cmd);
 	if (cdb16) {
-		alloc_len = GET_READ_CAP_16_ALLOC_LENGTH(cmd);
+		alloc_len = get_unaligned_be32(&cmd[10]);
 		resp_size = READ_CAP_16_RESP_SIZE;
+	} else {
+		alloc_len = READ_CAP_10_RESP_SIZE;
+		resp_size = READ_CAP_10_RESP_SIZE;
 	}
 
-	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
-							&dma_addr, GFP_KERNEL);
-	if (mem == NULL) {
-		res = -ENOMEM;
-		goto out;
-	}
-	/* nvme ns identify */
-	nvme_sc = nvme_identify(dev, ns->ns_id, 0, dma_addr);
+	nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
-		goto out_dma;
-	if (nvme_sc) {
-		res = nvme_sc;
-		goto out_dma;
-	}
-	id_ns = mem;
+		return res;	
 
 	response = kzalloc(resp_size, GFP_KERNEL);
 	if (response == NULL) {
 		res = -ENOMEM;
-		goto out_dma;
+		goto out_free_id;
 	}
 	nvme_trans_fill_read_cap(response, id_ns, cdb16);
 
@@ -2513,72 +2068,53 @@ static int nvme_trans_read_capacity(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	res = nvme_trans_copy_to_user(hdr, response, xfer_len);
 
 	kfree(response);
- out_dma:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns), mem,
-			  dma_addr);
- out:
+ out_free_id:
+	kfree(id_ns);
 	return res;
 }
 
 static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	int nvme_sc;
 	u32 alloc_len, xfer_len, resp_size;
-	u8 select_report;
 	u8 *response;
 	struct nvme_dev *dev = ns->dev;
-	dma_addr_t dma_addr;
-	void *mem;
 	struct nvme_id_ctrl *id_ctrl;
 	u32 ll_length, lun_id;
 	u8 lun_id_offset = REPORT_LUNS_FIRST_LUN_OFFSET;
 	__be32 tmp_len;
 
-	alloc_len = GET_REPORT_LUNS_ALLOC_LENGTH(cmd);
-	select_report = GET_U8_FROM_CDB(cmd, REPORT_LUNS_SR_OFFSET);
-
-	if ((select_report != ALL_LUNS_RETURNED) &&
-	    (select_report != ALL_WELL_KNOWN_LUNS_RETURNED) &&
-	    (select_report != RESTRICTED_LUNS_RETURNED)) {
-		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
+	switch (cmd[2]) {
+	default:
+		return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-		goto out;
-	} else {
-		/* NVMe Controller Identify */
-		mem = dma_alloc_coherent(&dev->pci_dev->dev,
-					sizeof(struct nvme_id_ctrl),
-					&dma_addr, GFP_KERNEL);
-		if (mem == NULL) {
-			res = -ENOMEM;
-			goto out;
-		}
-		nvme_sc = nvme_identify(dev, 0, 1, dma_addr);
+	case ALL_LUNS_RETURNED:
+	case ALL_WELL_KNOWN_LUNS_RETURNED:
+	case RESTRICTED_LUNS_RETURNED:
+		nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
 		res = nvme_trans_status_code(hdr, nvme_sc);
 		if (res)
-			goto out_dma;
-		if (nvme_sc) {
-			res = nvme_sc;
-			goto out_dma;
-		}
-		id_ctrl = mem;
+			return res;
+
 		ll_length = le32_to_cpu(id_ctrl->nn) * LUN_ENTRY_SIZE;
 		resp_size = ll_length + LUN_DATA_HEADER_SIZE;
 
+		alloc_len = get_unaligned_be32(&cmd[6]);
 		if (alloc_len < resp_size) {
 			res = nvme_trans_completion(hdr,
 					SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-			goto out_dma;
+			goto out_free_id;
 		}
 
 		response = kzalloc(resp_size, GFP_KERNEL);
 		if (response == NULL) {
 			res = -ENOMEM;
-			goto out_dma;
+			goto out_free_id;
 		}
 
 		/* The first LUN ID will always be 0 per the SAM spec */
@@ -2599,24 +2135,21 @@ static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	res = nvme_trans_copy_to_user(hdr, response, xfer_len);
 
 	kfree(response);
- out_dma:
-	dma_free_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ctrl), mem,
-			  dma_addr);
- out:
+ out_free_id:
+	kfree(id_ctrl);
 	return res;
 }
 
 static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u8 alloc_len, xfer_len, resp_size;
 	u8 desc_format;
 	u8 *response;
 
-	alloc_len = GET_REQUEST_SENSE_ALLOC_LENGTH(cmd);
-	desc_format = GET_U8_FROM_CDB(cmd, REQUEST_SENSE_DESC_OFFSET);
-	desc_format &= REQUEST_SENSE_DESC_MASK;
+	desc_format = cmd[1] & 0x01;
+	alloc_len = cmd[4];
 
 	resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
 					(FIXED_FMT_SENSE_DATA_SIZE));
@@ -2626,7 +2159,7 @@ static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		goto out;
 	}
 
-	if (desc_format == DESCRIPTOR_FORMAT_SENSE_DATA_TYPE) {
+	if (desc_format) {
 		/* Descriptor Format Sense Data */
 		response[0] = DESC_FORMAT_SENSE_DATA;
 		response[1] = NO_SENSE;
@@ -2665,95 +2198,58 @@ static int nvme_trans_security_protocol(struct nvme_ns *ns,
 				SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 }
 
-static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
-							u8 *cmd)
+static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
+					struct sg_io_hdr *hdr)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
 	struct nvme_command c;
-	u8 immed, pcmod, pc, no_flush, start;
 
-	immed = GET_U8_FROM_CDB(cmd, START_STOP_UNIT_CDB_IMMED_OFFSET);
-	pcmod = GET_U8_FROM_CDB(cmd, START_STOP_UNIT_CDB_POWER_COND_MOD_OFFSET);
-	pc = GET_U8_FROM_CDB(cmd, START_STOP_UNIT_CDB_POWER_COND_OFFSET);
-	no_flush = GET_U8_FROM_CDB(cmd, START_STOP_UNIT_CDB_NO_FLUSH_OFFSET);
-	start = GET_U8_FROM_CDB(cmd, START_STOP_UNIT_CDB_START_OFFSET);
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = nvme_cmd_flush;
+	c.common.nsid = cpu_to_le32(ns->ns_id);
 
-	immed &= START_STOP_UNIT_CDB_IMMED_MASK;
-	pcmod &= START_STOP_UNIT_CDB_POWER_COND_MOD_MASK;
-	pc = (pc & START_STOP_UNIT_CDB_POWER_COND_MASK) >> NIBBLE_SHIFT;
-	no_flush &= START_STOP_UNIT_CDB_NO_FLUSH_MASK;
-	start &= START_STOP_UNIT_CDB_START_MASK;
+	nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
+	return nvme_trans_status_code(hdr, nvme_sc);
+}
+
+static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
+							u8 *cmd)
+{
+	u8 immed, pcmod, pc, no_flush, start;
+
+	immed = cmd[1] & 0x01;
+	pcmod = cmd[3] & 0x0f;
+	pc = (cmd[4] & 0xf0) >> 4;
+	no_flush = cmd[4] & 0x04;
+	start = cmd[4] & 0x01;
 
 	if (immed != 0) {
-		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
+		return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 	} else {
 		if (no_flush == 0) {
 			/* Issue NVME FLUSH command prior to START STOP UNIT */
-			memset(&c, 0, sizeof(c));
-			c.common.opcode = nvme_cmd_flush;
-			c.common.nsid = cpu_to_le32(ns->ns_id);
-
-			nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
-			res = nvme_trans_status_code(hdr, nvme_sc);
+			int res = nvme_trans_synchronize_cache(ns, hdr);
 			if (res)
-				goto out;
-			if (nvme_sc) {
-				res = nvme_sc;
-				goto out;
-			}
+				return res;
 		}
 		/* Setup the expected power state transition */
-		res = nvme_trans_power_state(ns, hdr, pc, pcmod, start);
+		return nvme_trans_power_state(ns, hdr, pc, pcmod, start);
 	}
-
- out:
-	return res;
-}
-
-static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
-					struct sg_io_hdr *hdr, u8 *cmd)
-{
-	int res = SNTI_TRANSLATION_SUCCESS;
-	int nvme_sc;
-	struct nvme_command c;
-
-	memset(&c, 0, sizeof(c));
-	c.common.opcode = nvme_cmd_flush;
-	c.common.nsid = cpu_to_le32(ns->ns_id);
-
-	nvme_sc = nvme_submit_io_cmd(ns->dev, ns, &c, NULL);
-
-	res = nvme_trans_status_code(hdr, nvme_sc);
-	if (res)
-		goto out;
-	if (nvme_sc)
-		res = nvme_sc;
-
- out:
-	return res;
 }
 
 static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res;
 	u8 parm_hdr_len = 0;
 	u8 nvme_pf_code = 0;
 	u8 format_prot_info, long_list, format_data;
 
-	format_prot_info = GET_U8_FROM_CDB(cmd,
-				FORMAT_UNIT_CDB_FORMAT_PROT_INFO_OFFSET);
-	long_list = GET_U8_FROM_CDB(cmd, FORMAT_UNIT_CDB_LONG_LIST_OFFSET);
-	format_data = GET_U8_FROM_CDB(cmd, FORMAT_UNIT_CDB_FORMAT_DATA_OFFSET);
-
-	format_prot_info = (format_prot_info &
-				FORMAT_UNIT_CDB_FORMAT_PROT_INFO_MASK) >>
-				FORMAT_UNIT_CDB_FORMAT_PROT_INFO_SHIFT;
-	long_list &= FORMAT_UNIT_CDB_LONG_LIST_MASK;
-	format_data &= FORMAT_UNIT_CDB_FORMAT_DATA_MASK;
+	format_prot_info = (cmd[1] & 0xc0) >> 6;
+	long_list = cmd[1] & 0x20;
+	format_data = cmd[1] & 0x10;
 
 	if (format_data != 0) {
 		if (format_prot_info != 0) {
@@ -2777,16 +2273,16 @@ static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	if (parm_hdr_len > 0) {
 		res = nvme_trans_fmt_get_parm_header(hdr, parm_hdr_len,
 					format_prot_info, &nvme_pf_code);
-		if (res != SNTI_TRANSLATION_SUCCESS)
+		if (res)
 			goto out;
 	}
 
 	/* Attempt to activate any previously downloaded firmware image */
-	res = nvme_trans_send_fw_cmd(ns, hdr, nvme_admin_activate_fw, 0, 0, 0);
+	res = nvme_trans_send_activate_fw_cmd(ns, hdr, 0);
 
 	/* Determine Block size and count and send format command */
 	res = nvme_trans_fmt_set_blk_size_count(ns, hdr);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out;
 
 	res = nvme_trans_fmt_send_cmd(ns, hdr, nvme_pf_code);
@@ -2799,28 +2295,24 @@ static int nvme_trans_test_unit_ready(struct nvme_ns *ns,
 					struct sg_io_hdr *hdr,
 					u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
 	struct nvme_dev *dev = ns->dev;
 
 	if (!(readl(&dev->bar->csts) & NVME_CSTS_RDY))
-		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
+		return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					    NOT_READY, SCSI_ASC_LUN_NOT_READY,
 					    SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 	else
-		res = nvme_trans_completion(hdr, SAM_STAT_GOOD, NO_SENSE, 0, 0);
-
-	return res;
+		return nvme_trans_completion(hdr, SAM_STAT_GOOD, NO_SENSE, 0, 0);
 }
 
 static int nvme_trans_write_buffer(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	int res = SNTI_TRANSLATION_SUCCESS;
+	int res = 0;
 	u32 buffer_offset, parm_list_length;
 	u8 buffer_id, mode;
 
-	parm_list_length =
-		GET_U24_FROM_CDB(cmd, WRITE_BUFFER_CDB_PARM_LIST_LENGTH_OFFSET);
+	parm_list_length = get_unaligned_be24(&cmd[6]);
 	if (parm_list_length % BYTES_TO_DWORDS != 0) {
 		/* NVMe expects Firmware file to be a whole number of DWORDS */
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
@@ -2828,38 +2320,32 @@ static int nvme_trans_write_buffer(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 		goto out;
 	}
-	buffer_id = GET_U8_FROM_CDB(cmd, WRITE_BUFFER_CDB_BUFFER_ID_OFFSET);
+	buffer_id = cmd[2];
 	if (buffer_id > NVME_MAX_FIRMWARE_SLOT) {
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
 					ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
 					SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
 		goto out;
 	}
-	mode = GET_U8_FROM_CDB(cmd, WRITE_BUFFER_CDB_MODE_OFFSET) &
-						WRITE_BUFFER_CDB_MODE_MASK;
-	buffer_offset =
-		GET_U24_FROM_CDB(cmd, WRITE_BUFFER_CDB_BUFFER_OFFSET_OFFSET);
+	mode = cmd[1] & 0x1f;
+	buffer_offset = get_unaligned_be24(&cmd[3]);
 
 	switch (mode) {
 	case DOWNLOAD_SAVE_ACTIVATE:
-		res = nvme_trans_send_fw_cmd(ns, hdr, nvme_admin_download_fw,
+		res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw,
 						parm_list_length, buffer_offset,
 						buffer_id);
-		if (res != SNTI_TRANSLATION_SUCCESS)
+		if (res)
 			goto out;
-		res = nvme_trans_send_fw_cmd(ns, hdr, nvme_admin_activate_fw,
-						parm_list_length, buffer_offset,
-						buffer_id);
+		res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id);
 		break;
 	case DOWNLOAD_SAVE_DEFER_ACTIVATE:
-		res = nvme_trans_send_fw_cmd(ns, hdr, nvme_admin_download_fw,
+		res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw,
 						parm_list_length, buffer_offset,
 						buffer_id);
 		break;
 	case ACTIVATE_DEFERRED_MICROCODE:
-		res = nvme_trans_send_fw_cmd(ns, hdr, nvme_admin_activate_fw,
-						parm_list_length, buffer_offset,
-						buffer_id);
+		res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id);
 		break;
 	default:
 		res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
@@ -2888,15 +2374,13 @@ struct scsi_unmap_parm_list {
 static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 							u8 *cmd)
 {
-	struct nvme_dev *dev = ns->dev;
 	struct scsi_unmap_parm_list *plist;
 	struct nvme_dsm_range *range;
 	struct nvme_command c;
-	int i, nvme_sc, res = -ENOMEM;
+	int i, nvme_sc, res;
 	u16 ndesc, list_len;
-	dma_addr_t dma_addr;
 
-	list_len = GET_U16_FROM_CDB(cmd, UNMAP_CDB_PARAM_LIST_LENGTH_OFFSET);
+	list_len = get_unaligned_be16(&cmd[7]);
 	if (!list_len)
 		return -EINVAL;
 
@@ -2905,7 +2389,7 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		return -ENOMEM;
 
 	res = nvme_trans_copy_from_user(hdr, plist, list_len);
-	if (res != SNTI_TRANSLATION_SUCCESS)
+	if (res)
 		goto out;
 
 	ndesc = be16_to_cpu(plist->unmap_blk_desc_data_len) >> 4;
@@ -2914,10 +2398,11 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		goto out;
 	}
 
-	range = dma_alloc_coherent(&dev->pci_dev->dev, ndesc * sizeof(*range),
-							&dma_addr, GFP_KERNEL);
-	if (!range)
+	range = kcalloc(ndesc, sizeof(*range), GFP_KERNEL);
+	if (!range) {
+		res = -ENOMEM;
 		goto out;
+	}
 
 	for (i = 0; i < ndesc; i++) {
 		range[i].nlb = cpu_to_le32(be32_to_cpu(plist->desc[i].nlb));
@@ -2928,15 +2413,14 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	memset(&c, 0, sizeof(c));
 	c.dsm.opcode = nvme_cmd_dsm;
 	c.dsm.nsid = cpu_to_le32(ns->ns_id);
-	c.dsm.prp1 = cpu_to_le64(dma_addr);
 	c.dsm.nr = cpu_to_le32(ndesc - 1);
 	c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	nvme_sc = nvme_submit_io_cmd(dev, ns, &c, NULL);
+	nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, range,
+			ndesc * sizeof(*range));
 	res = nvme_trans_status_code(hdr, nvme_sc);
 
-	dma_free_coherent(&dev->pci_dev->dev, ndesc * sizeof(*range),
-							range, dma_addr);
+	kfree(range);
  out:
 	kfree(plist);
 	return res;
@@ -2991,13 +2475,16 @@ static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 		retcode = nvme_trans_mode_sense(ns, hdr, cmd);
 		break;
 	case READ_CAPACITY:
-		retcode = nvme_trans_read_capacity(ns, hdr, cmd);
+		retcode = nvme_trans_read_capacity(ns, hdr, cmd, 0);
 		break;
 	case SERVICE_ACTION_IN_16:
-		if (IS_READ_CAP_16(cmd))
-			retcode = nvme_trans_read_capacity(ns, hdr, cmd);
-		else
+		switch (cmd[1]) {
+		case SAI_READ_CAPACITY_16:
+			retcode = nvme_trans_read_capacity(ns, hdr, cmd, 1);
+			break;
+		default:
 			goto out;
+		}
 		break;
 	case REPORT_LUNS:
 		retcode = nvme_trans_report_luns(ns, hdr, cmd);
@@ -3013,7 +2500,7 @@ static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 		retcode = nvme_trans_start_stop(ns, hdr, cmd);
 		break;
 	case SYNCHRONIZE_CACHE:
-		retcode = nvme_trans_synchronize_cache(ns, hdr, cmd);
+		retcode = nvme_trans_synchronize_cache(ns, hdr);
 		break;
 	case FORMAT_UNIT:
 		retcode = nvme_trans_format_unit(ns, hdr, cmd);
@@ -3051,15 +2538,16 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
 	if (hdr.cmd_len > BLK_MAX_CDB)
 		return -EINVAL;
 
+	/*
+	 * A positive return code means a NVMe status, which has been
+	 * translated to sense data.
+	 */
 	retcode = nvme_scsi_translate(ns, &hdr);
 	if (retcode < 0)
 		return retcode;
-	if (retcode > 0)
-		retcode = SNTI_TRANSLATION_SUCCESS;
 	if (copy_to_user(u_hdr, &hdr, sizeof(sg_io_hdr_t)) > 0)
 		return -EFAULT;
-
-	return retcode;
+	return 0;
 }
 
 int nvme_sg_get_version_num(int __user *ip)
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index d48715b287e6..dbb4da1cdca8 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -442,7 +442,7 @@ static char *pd_buf;		/* buffer for request in progress */
 
 static enum action do_pd_io_start(void)
 {
-	if (pd_req->cmd_type == REQ_TYPE_SPECIAL) {
+	if (pd_req->cmd_type == REQ_TYPE_DRV_PRIV) {
 		phase = pd_special;
 		return pd_special();
 	}
@@ -725,7 +725,7 @@ static int pd_special_command(struct pd_unit *disk,
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = func;
 
 	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c
index eabf4a8d0085..095dfaadcaa5 100644
--- a/drivers/block/pmem.c
+++ b/drivers/block/pmem.c
@@ -139,11 +139,11 @@ static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res)
 	}
 
 	/*
-	 * Map the memory as non-cachable, as we can't write back the contents
+	 * Map the memory as write-through, as we can't write back the contents
 	 * of the CPU caches in case of a crash.
 	 */
 	err = -ENOMEM;
-	pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
+	pmem->virt_addr = ioremap_wt(pmem->phys_addr, pmem->size);
 	if (!pmem->virt_addr)
 		goto out_release_region;
 
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index ef45cfb98fd2..b1612eb16172 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -1,5 +1,5 @@
 /*
- * ps3vram - Use extra PS3 video ram as MTD block device.
+ * ps3vram - Use extra PS3 video ram as block device.
  *
  * Copyright 2009 Sony Corporation
  *
@@ -73,8 +73,8 @@ struct ps3vram_priv {
 
 	u64 memory_handle;
 	u64 context_handle;
-	u32 *ctrl;
-	void *reports;
+	u32 __iomem *ctrl;
+	void __iomem *reports;
 	u8 *xdr_buf;
 
 	u32 *fifo_base;
@@ -104,7 +104,7 @@ static char *size = "256M";
 module_param(size, charp, 0);
 MODULE_PARM_DESC(size, "memory size");
 
-static u32 *ps3vram_get_notifier(void *reports, int notifier)
+static u32 __iomem *ps3vram_get_notifier(void __iomem *reports, int notifier)
 {
 	return reports + DMA_NOTIFIER_OFFSET_BASE +
 	       DMA_NOTIFIER_SIZE * notifier;
@@ -113,22 +113,22 @@ static u32 *ps3vram_get_notifier(void *reports, int notifier)
 static void ps3vram_notifier_reset(struct ps3_system_bus_device *dev)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
-	u32 *notify = ps3vram_get_notifier(priv->reports, NOTIFIER);
+	u32 __iomem *notify = ps3vram_get_notifier(priv->reports, NOTIFIER);
 	int i;
 
 	for (i = 0; i < 4; i++)
-		notify[i] = 0xffffffff;
+		iowrite32be(0xffffffff, notify + i);
 }
 
 static int ps3vram_notifier_wait(struct ps3_system_bus_device *dev,
 				 unsigned int timeout_ms)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
-	u32 *notify = ps3vram_get_notifier(priv->reports, NOTIFIER);
+	u32 __iomem *notify = ps3vram_get_notifier(priv->reports, NOTIFIER);
 	unsigned long timeout;
 
 	for (timeout = 20; timeout; timeout--) {
-		if (!notify[3])
+		if (!ioread32be(notify + 3))
 			return 0;
 		udelay(10);
 	}
@@ -136,7 +136,7 @@ static int ps3vram_notifier_wait(struct ps3_system_bus_device *dev,
 	timeout = jiffies + msecs_to_jiffies(timeout_ms);
 
 	do {
-		if (!notify[3])
+		if (!ioread32be(notify + 3))
 			return 0;
 		msleep(1);
 	} while (time_before(jiffies, timeout));
@@ -148,8 +148,8 @@ static void ps3vram_init_ring(struct ps3_system_bus_device *dev)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 
-	priv->ctrl[CTRL_PUT] = FIFO_BASE + FIFO_OFFSET;
-	priv->ctrl[CTRL_GET] = FIFO_BASE + FIFO_OFFSET;
+	iowrite32be(FIFO_BASE + FIFO_OFFSET, priv->ctrl + CTRL_PUT);
+	iowrite32be(FIFO_BASE + FIFO_OFFSET, priv->ctrl + CTRL_GET);
 }
 
 static int ps3vram_wait_ring(struct ps3_system_bus_device *dev,
@@ -159,14 +159,14 @@ static int ps3vram_wait_ring(struct ps3_system_bus_device *dev,
 	unsigned long timeout = jiffies + msecs_to_jiffies(timeout_ms);
 
 	do {
-		if (priv->ctrl[CTRL_PUT] == priv->ctrl[CTRL_GET])
+		if (ioread32be(priv->ctrl + CTRL_PUT) == ioread32be(priv->ctrl + CTRL_GET))
 			return 0;
 		msleep(1);
 	} while (time_before(jiffies, timeout));
 
 	dev_warn(&dev->core, "FIFO timeout (%08x/%08x/%08x)\n",
-		 priv->ctrl[CTRL_PUT], priv->ctrl[CTRL_GET],
-		 priv->ctrl[CTRL_TOP]);
+		 ioread32be(priv->ctrl + CTRL_PUT), ioread32be(priv->ctrl + CTRL_GET),
+		 ioread32be(priv->ctrl + CTRL_TOP));
 
 	return -ETIMEDOUT;
 }
@@ -189,7 +189,7 @@ static void ps3vram_rewind_ring(struct ps3_system_bus_device *dev)
 
 	ps3vram_out_ring(priv, 0x20000000 | (FIFO_BASE + FIFO_OFFSET));
 
-	priv->ctrl[CTRL_PUT] = FIFO_BASE + FIFO_OFFSET;
+	iowrite32be(FIFO_BASE + FIFO_OFFSET, priv->ctrl + CTRL_PUT);
 
 	/* asking the HV for a blit will kick the FIFO */
 	status = lv1_gpu_fb_blit(priv->context_handle, 0, 0, 0, 0);
@@ -207,8 +207,8 @@ static void ps3vram_fire_ring(struct ps3_system_bus_device *dev)
 
 	mutex_lock(&ps3_gpu_mutex);
 
-	priv->ctrl[CTRL_PUT] = FIFO_BASE + FIFO_OFFSET +
-			       (priv->fifo_ptr - priv->fifo_base) * sizeof(u32);
+	iowrite32be(FIFO_BASE + FIFO_OFFSET + (priv->fifo_ptr - priv->fifo_base)
+		* sizeof(u32), priv->ctrl + CTRL_PUT);
 
 	/* asking the HV for a blit will kick the FIFO */
 	status = lv1_gpu_fb_blit(priv->context_handle, 0, 0, 0, 0);
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 5d552857de41..59c91d49b14b 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -620,7 +620,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
@@ -661,7 +661,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_SPECIAL;
+	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 5ea2f0bbbc7c..d4d05f064d39 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -124,7 +124,7 @@ static inline void virtblk_request_done(struct request *req)
 		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
 		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
 		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
-	} else if (req->cmd_type == REQ_TYPE_SPECIAL) {
+	} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
 		req->errors = (error != 0);
 	}
 
@@ -188,7 +188,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			vbr->out_hdr.sector = 0;
 			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
 			break;
-		case REQ_TYPE_SPECIAL:
+		case REQ_TYPE_DRV_PRIV:
 			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
 			vbr->out_hdr.sector = 0;
 			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
@@ -251,7 +251,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 		return PTR_ERR(req);
 	}
 
-	req->cmd_type = REQ_TYPE_SPECIAL;
+	req->cmd_type = REQ_TYPE_DRV_PRIV;
 	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
 	blk_put_request(req);
 
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index bd2b3bbbb22c..713fc9ff1149 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -265,17 +265,6 @@ static void put_persistent_gnt(struct xen_blkif *blkif,
 	atomic_dec(&blkif->persistent_gnt_in_use);
 }
 
-static void free_persistent_gnts_unmap_callback(int result,
-						struct gntab_unmap_queue_data *data)
-{
-	struct completion *c = data->data;
-
-	/* BUG_ON used to reproduce existing behaviour,
-	   but is this the best way to deal with this? */
-	BUG_ON(result);
-	complete(c);
-}
-
 static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
                                  unsigned int num)
 {
@@ -285,12 +274,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 	struct rb_node *n;
 	int segs_to_unmap = 0;
 	struct gntab_unmap_queue_data unmap_data;
-	struct completion unmap_completion;
 
-	init_completion(&unmap_completion);
-
-	unmap_data.data = &unmap_completion;
-	unmap_data.done = &free_persistent_gnts_unmap_callback;
 	unmap_data.pages = pages;
 	unmap_data.unmap_ops = unmap;
 	unmap_data.kunmap_ops = NULL;
@@ -310,8 +294,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
 			!rb_next(&persistent_gnt->node)) {
 
 			unmap_data.count = segs_to_unmap;
-			gnttab_unmap_refs_async(&unmap_data);
-			wait_for_completion(&unmap_completion);
+			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 
 			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
@@ -329,8 +312,13 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
 	struct persistent_gnt *persistent_gnt;
-	int ret, segs_to_unmap = 0;
+	int segs_to_unmap = 0;
 	struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work);
+	struct gntab_unmap_queue_data unmap_data;
+
+	unmap_data.pages = pages;
+	unmap_data.unmap_ops = unmap;
+	unmap_data.kunmap_ops = NULL;
 
 	while(!list_empty(&blkif->persistent_purge_list)) {
 		persistent_gnt = list_first_entry(&blkif->persistent_purge_list,
@@ -346,17 +334,16 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
 		pages[segs_to_unmap] = persistent_gnt->page;
 
 		if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
-			ret = gnttab_unmap_refs(unmap, NULL, pages,
-				segs_to_unmap);
-			BUG_ON(ret);
+			unmap_data.count = segs_to_unmap;
+			BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 			put_free_pages(blkif, pages, segs_to_unmap);
 			segs_to_unmap = 0;
 		}
 		kfree(persistent_gnt);
 	}
 	if (segs_to_unmap > 0) {
-		ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap);
-		BUG_ON(ret);
+		unmap_data.count = segs_to_unmap;
+		BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
 		put_free_pages(blkif, pages, segs_to_unmap);
 	}
 }
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index c94386aa563d..6e134f4759c0 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -74,6 +74,27 @@ static inline struct zram *dev_to_zram(struct device *dev)
 	return (struct zram *)dev_to_disk(dev)->private_data;
 }
 
+static ssize_t compact_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	unsigned long nr_migrated;
+	struct zram *zram = dev_to_zram(dev);
+	struct zram_meta *meta;
+
+	down_read(&zram->init_lock);
+	if (!init_done(zram)) {
+		up_read(&zram->init_lock);
+		return -EINVAL;
+	}
+
+	meta = zram->meta;
+	nr_migrated = zs_compact(meta->mem_pool);
+	atomic64_add(nr_migrated, &zram->stats.num_migrated);
+	up_read(&zram->init_lock);
+
+	return len;
+}
+
 static ssize_t disksize_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -784,7 +805,9 @@ static void zram_reset_device(struct zram *zram)
 	memset(&zram->stats, 0, sizeof(zram->stats));
 	zram->disksize = 0;
 	zram->max_comp_streams = 1;
+
 	set_capacity(zram->disk, 0);
+	part_stat_set_all(&zram->disk->part0, 0);
 
 	up_write(&zram->init_lock);
 	/* I/O operation under all of CPU are done so let's free */
@@ -1038,6 +1061,7 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
+static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);
 static DEVICE_ATTR_RO(initstate);
 static DEVICE_ATTR_WO(reset);
@@ -1114,6 +1138,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_num_writes.attr,
 	&dev_attr_failed_reads.attr,
 	&dev_attr_failed_writes.attr,
+	&dev_attr_compact.attr,
 	&dev_attr_invalid_io.attr,
 	&dev_attr_notify_free.attr,
 	&dev_attr_zero_pages.attr,
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index ed5c2738bea2..2e777071e1dc 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -9,6 +9,10 @@ config BT_BCM
 	tristate
 	select FW_LOADER
 
+config BT_RTL
+	tristate
+	select FW_LOADER
+
 config BT_HCIBTUSB
 	tristate "HCI USB driver"
 	depends on USB
@@ -32,6 +36,17 @@ config BT_HCIBTUSB_BCM
 
 	  Say Y here to compile support for Broadcom protocol.
 
+config BT_HCIBTUSB_RTL
+	bool "Realtek protocol support"
+	depends on BT_HCIBTUSB
+	select BT_RTL
+	default y
+	help
+	  The Realtek protocol support enables firmware and configuration
+	  download support for Realtek Bluetooth controllers.
+
+	  Say Y here to compile support for Realtek protocol.
+
 config BT_HCIBTSDIO
 	tristate "HCI SDIO driver"
 	depends on MMC
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index dd0d9c40b999..f40e194e7080 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_BT_MRVL)		+= btmrvl.o
 obj-$(CONFIG_BT_MRVL_SDIO)	+= btmrvl_sdio.o
 obj-$(CONFIG_BT_WILINK)		+= btwilink.o
 obj-$(CONFIG_BT_BCM)		+= btbcm.o
+obj-$(CONFIG_BT_RTL)		+= btrtl.o
 
 btmrvl-y			:= btmrvl_main.o
 btmrvl-$(CONFIG_DEBUG_FS)	+= btmrvl_debugfs.o
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 288547a3c566..e527a3e13939 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -80,6 +80,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x0489, 0xe056) },
 	{ USB_DEVICE(0x0489, 0xe05f) },
+	{ USB_DEVICE(0x0489, 0xe076) },
 	{ USB_DEVICE(0x0489, 0xe078) },
 	{ USB_DEVICE(0x04c5, 0x1330) },
 	{ USB_DEVICE(0x04CA, 0x3004) },
@@ -88,6 +89,8 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x04CA, 0x3007) },
 	{ USB_DEVICE(0x04CA, 0x3008) },
 	{ USB_DEVICE(0x04CA, 0x300b) },
+	{ USB_DEVICE(0x04CA, 0x300d) },
+	{ USB_DEVICE(0x04CA, 0x300f) },
 	{ USB_DEVICE(0x04CA, 0x3010) },
 	{ USB_DEVICE(0x0930, 0x0219) },
 	{ USB_DEVICE(0x0930, 0x0220) },
@@ -104,6 +107,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0cf3, 0xe003) },
 	{ USB_DEVICE(0x0CF3, 0xE004) },
 	{ USB_DEVICE(0x0CF3, 0xE005) },
+	{ USB_DEVICE(0x0CF3, 0xE006) },
 	{ USB_DEVICE(0x13d3, 0x3362) },
 	{ USB_DEVICE(0x13d3, 0x3375) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
@@ -111,6 +115,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3408) },
 	{ USB_DEVICE(0x13d3, 0x3423) },
 	{ USB_DEVICE(0x13d3, 0x3432) },
+	{ USB_DEVICE(0x13d3, 0x3474) },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE02C) },
@@ -135,6 +140,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
@@ -143,6 +149,8 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
@@ -158,6 +166,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
@@ -166,6 +175,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU22 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xE036), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c
index 4f7e8d400bc0..7aab65427d38 100644
--- a/drivers/bluetooth/bt3c_cs.c
+++ b/drivers/bluetooth/bt3c_cs.c
@@ -202,9 +202,8 @@ static void bt3c_write_wakeup(struct bt3c_info *info)
 		/* Send frame */
 		len = bt3c_write(iobase, 256, skb->data, skb->len);
 
-		if (len != skb->len) {
+		if (len != skb->len)
 			BT_ERR("Very strange");
-		}
 
 		kfree_skb(skb);
 
@@ -227,7 +226,6 @@ static void bt3c_receive(struct bt3c_info *info)
 	iobase = info->p_dev->resource[0]->start;
 
 	avail = bt3c_read(iobase, 0x7006);
-	//printk("bt3c_cs: receiving %d bytes\n", avail);
 
 	bt3c_address(iobase, 0x7480);
 	while (size < avail) {
@@ -250,7 +248,6 @@ static void bt3c_receive(struct bt3c_info *info)
 
 			bt_cb(info->rx_skb)->pkt_type = inb(iobase + DATA_L);
 			inb(iobase + DATA_H);
-			//printk("bt3c: PACKET_TYPE=%02x\n", bt_cb(info->rx_skb)->pkt_type);
 
 			switch (bt_cb(info->rx_skb)->pkt_type) {
 
@@ -364,7 +361,6 @@ static irqreturn_t bt3c_interrupt(int irq, void *dev_inst)
 			if (stat & 0x0001)
 				bt3c_receive(info);
 			if (stat & 0x0002) {
-				//BT_ERR("Ack (stat=0x%04x)", stat);
 				clear_bit(XMIT_SENDING, &(info->tx_state));
 				bt3c_write_wakeup(info);
 			}
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index d0741f3ed7ec..1e1a4323a71f 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -33,6 +33,7 @@
 #define VERSION "0.1"
 
 #define BDADDR_BCM20702A0 (&(bdaddr_t) {{0x00, 0xa0, 0x02, 0x70, 0x20, 0x00}})
+#define BDADDR_BCM4324B3 (&(bdaddr_t) {{0x00, 0x00, 0x00, 0xb3, 0x24, 0x43}})
 
 int btbcm_check_bdaddr(struct hci_dev *hdev)
 {
@@ -55,17 +56,19 @@ int btbcm_check_bdaddr(struct hci_dev *hdev)
 	}
 
 	bda = (struct hci_rp_read_bd_addr *)skb->data;
-	if (bda->status) {
-		BT_ERR("%s: BCM: Device address result failed (%02x)",
-		       hdev->name, bda->status);
-		kfree_skb(skb);
-		return -bt_to_errno(bda->status);
-	}
 
-	/* The address 00:20:70:02:A0:00 indicates a BCM20702A0 controller
+	/* Check if the address indicates a controller with either an
+	 * invalid or default address. In both cases the device needs
+	 * to be marked as not having a valid address.
+	 *
+	 * The address 00:20:70:02:A0:00 indicates a BCM20702A0 controller
 	 * with no configured address.
+	 *
+	 * The address 43:24:B3:00:00:00 indicates a BCM4324B3 controller
+	 * with waiting for configuration state.
 	 */
-	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0)) {
+	if (!bacmp(&bda->bdaddr, BDADDR_BCM20702A0) ||
+	    !bacmp(&bda->bdaddr, BDADDR_BCM4324B3)) {
 		BT_INFO("%s: BCM: Using default device address (%pMR)",
 			hdev->name, &bda->bdaddr);
 		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
@@ -95,6 +98,69 @@ int btbcm_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(btbcm_set_bdaddr);
 
+int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw)
+{
+	const struct hci_command_hdr *cmd;
+	const u8 *fw_ptr;
+	size_t fw_size;
+	struct sk_buff *skb;
+	u16 opcode;
+	int err = 0;
+
+	/* Start Download */
+	skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: BCM: Download Minidrv command failed (%d)",
+		       hdev->name, err);
+		goto done;
+	}
+	kfree_skb(skb);
+
+	/* 50 msec delay after Download Minidrv completes */
+	msleep(50);
+
+	fw_ptr = fw->data;
+	fw_size = fw->size;
+
+	while (fw_size >= sizeof(*cmd)) {
+		const u8 *cmd_param;
+
+		cmd = (struct hci_command_hdr *)fw_ptr;
+		fw_ptr += sizeof(*cmd);
+		fw_size -= sizeof(*cmd);
+
+		if (fw_size < cmd->plen) {
+			BT_ERR("%s: BCM: Patch is corrupted", hdev->name);
+			err = -EINVAL;
+			goto done;
+		}
+
+		cmd_param = fw_ptr;
+		fw_ptr += cmd->plen;
+		fw_size -= cmd->plen;
+
+		opcode = le16_to_cpu(cmd->opcode);
+
+		skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param,
+				     HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb)) {
+			err = PTR_ERR(skb);
+			BT_ERR("%s: BCM: Patch command %04x failed (%d)",
+			       hdev->name, opcode, err);
+			goto done;
+		}
+		kfree_skb(skb);
+	}
+
+	/* 250 msec delay after Launch Ram completes */
+	msleep(250);
+
+done:
+	return err;
+}
+EXPORT_SYMBOL(btbcm_patchram);
+
 static int btbcm_reset(struct hci_dev *hdev)
 {
 	struct sk_buff *skb;
@@ -176,9 +242,101 @@ static const struct {
 	const char *name;
 } bcm_uart_subver_table[] = {
 	{ 0x410e, "BCM43341B0"	},	/* 002.001.014 */
+	{ 0x4406, "BCM4324B3"	},	/* 002.004.006 */
+	{ 0x610c, "BCM4354"	},	/* 003.001.012 */
 	{ }
 };
 
+int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len)
+{
+	u16 subver, rev;
+	const char *hw_name = NULL;
+	struct sk_buff *skb;
+	struct hci_rp_read_local_version *ver;
+	int i, err;
+
+	/* Reset */
+	err = btbcm_reset(hdev);
+	if (err)
+		return err;
+
+	/* Read Local Version Info */
+	skb = btbcm_read_local_version(hdev);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	ver = (struct hci_rp_read_local_version *)skb->data;
+	rev = le16_to_cpu(ver->hci_rev);
+	subver = le16_to_cpu(ver->lmp_subver);
+	kfree_skb(skb);
+
+	/* Read Verbose Config Version Info */
+	skb = btbcm_read_verbose_config(hdev);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	BT_INFO("%s: BCM: chip id %u", hdev->name, skb->data[1]);
+	kfree_skb(skb);
+
+	switch ((rev & 0xf000) >> 12) {
+	case 0:
+	case 1:
+	case 3:
+		for (i = 0; bcm_uart_subver_table[i].name; i++) {
+			if (subver == bcm_uart_subver_table[i].subver) {
+				hw_name = bcm_uart_subver_table[i].name;
+				break;
+			}
+		}
+
+		snprintf(fw_name, len, "brcm/%s.hcd", hw_name ? : "BCM");
+		break;
+	default:
+		return 0;
+	}
+
+	BT_INFO("%s: %s (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
+		hw_name ? : "BCM", (subver & 0x7000) >> 13,
+		(subver & 0x1f00) >> 8, (subver & 0x00ff), rev & 0x0fff);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btbcm_initialize);
+
+int btbcm_finalize(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	struct hci_rp_read_local_version *ver;
+	u16 subver, rev;
+	int err;
+
+	/* Reset */
+	err = btbcm_reset(hdev);
+	if (err)
+		return err;
+
+	/* Read Local Version Info */
+	skb = btbcm_read_local_version(hdev);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	ver = (struct hci_rp_read_local_version *)skb->data;
+	rev = le16_to_cpu(ver->hci_rev);
+	subver = le16_to_cpu(ver->lmp_subver);
+	kfree_skb(skb);
+
+	BT_INFO("%s: BCM (%3.3u.%3.3u.%3.3u) build %4.4u", hdev->name,
+		(subver & 0x7000) >> 13, (subver & 0x1f00) >> 8,
+		(subver & 0x00ff), rev & 0x0fff);
+
+	btbcm_check_bdaddr(hdev);
+
+	set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btbcm_finalize);
+
 static const struct {
 	u16 subver;
 	const char *name;
@@ -198,12 +356,9 @@ static const struct {
 
 int btbcm_setup_patchram(struct hci_dev *hdev)
 {
-	const struct hci_command_hdr *cmd;
-	const struct firmware *fw;
-	const u8 *fw_ptr;
-	size_t fw_size;
 	char fw_name[64];
-	u16 opcode, subver, rev, pid, vid;
+	const struct firmware *fw;
+	u16 subver, rev, pid, vid;
 	const char *hw_name = NULL;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *ver;
@@ -234,6 +389,7 @@ int btbcm_setup_patchram(struct hci_dev *hdev)
 
 	switch ((rev & 0xf000) >> 12) {
 	case 0:
+	case 3:
 		for (i = 0; bcm_uart_subver_table[i].name; i++) {
 			if (subver == bcm_uart_subver_table[i].subver) {
 				hw_name = bcm_uart_subver_table[i].name;
@@ -275,72 +431,23 @@ int btbcm_setup_patchram(struct hci_dev *hdev)
 
 	err = request_firmware(&fw, fw_name, &hdev->dev);
 	if (err < 0) {
-		BT_INFO("%s: BCM: patch %s not found", hdev->name, fw_name);
+		BT_INFO("%s: BCM: Patch %s not found", hdev->name, fw_name);
 		return 0;
 	}
 
-	/* Start Download */
-	skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		err = PTR_ERR(skb);
-		BT_ERR("%s: BCM: Download Minidrv command failed (%d)",
-		       hdev->name, err);
-		goto reset;
-	}
-	kfree_skb(skb);
-
-	/* 50 msec delay after Download Minidrv completes */
-	msleep(50);
-
-	fw_ptr = fw->data;
-	fw_size = fw->size;
+	btbcm_patchram(hdev, fw);
 
-	while (fw_size >= sizeof(*cmd)) {
-		const u8 *cmd_param;
-
-		cmd = (struct hci_command_hdr *)fw_ptr;
-		fw_ptr += sizeof(*cmd);
-		fw_size -= sizeof(*cmd);
-
-		if (fw_size < cmd->plen) {
-			BT_ERR("%s: BCM: patch %s is corrupted", hdev->name,
-			       fw_name);
-			err = -EINVAL;
-			goto reset;
-		}
-
-		cmd_param = fw_ptr;
-		fw_ptr += cmd->plen;
-		fw_size -= cmd->plen;
-
-		opcode = le16_to_cpu(cmd->opcode);
-
-		skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param,
-				     HCI_INIT_TIMEOUT);
-		if (IS_ERR(skb)) {
-			err = PTR_ERR(skb);
-			BT_ERR("%s: BCM: patch command %04x failed (%d)",
-			       hdev->name, opcode, err);
-			goto reset;
-		}
-		kfree_skb(skb);
-	}
-
-	/* 250 msec delay after Launch Ram completes */
-	msleep(250);
+	release_firmware(fw);
 
-reset:
 	/* Reset */
 	err = btbcm_reset(hdev);
 	if (err)
-		goto done;
+		return err;
 
 	/* Read Local Version Info */
 	skb = btbcm_read_local_version(hdev);
-	if (IS_ERR(skb)) {
-		err = PTR_ERR(skb);
-		goto done;
-	}
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
 
 	ver = (struct hci_rp_read_local_version *)skb->data;
 	rev = le16_to_cpu(ver->hci_rev);
@@ -355,10 +462,7 @@ reset:
 
 	set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
 
-done:
-	release_firmware(fw);
-
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(btbcm_setup_patchram);
 
diff --git a/drivers/bluetooth/btbcm.h b/drivers/bluetooth/btbcm.h
index 34268ae3eb46..d9e6b41658e5 100644
--- a/drivers/bluetooth/btbcm.h
+++ b/drivers/bluetooth/btbcm.h
@@ -21,14 +21,61 @@
  *
  */
 
+#define BCM_UART_CLOCK_48MHZ	0x01
+#define BCM_UART_CLOCK_24MHZ	0x02
+
+struct bcm_update_uart_baud_rate {
+	__le16 zero;
+	__le32 baud_rate;
+} __packed;
+
+struct bcm_write_uart_clock_setting {
+	__u8 type;
+} __packed;
+
+struct bcm_set_sleep_mode {
+	__u8 sleep_mode;
+	__u8 idle_host;
+	__u8 idle_dev;
+	__u8 bt_wake_active;
+	__u8 host_wake_active;
+	__u8 allow_host_sleep;
+	__u8 combine_modes;
+	__u8 tristate_control;
+	__u8 usb_auto_sleep;
+	__u8 usb_resume_timeout;
+	__u8 pulsed_host_wake;
+	__u8 break_to_host;
+} __packed;
+
+struct bcm_set_pcm_int_params {
+	__u8 routing;
+	__u8 rate;
+	__u8 frame_sync;
+	__u8 sync_mode;
+	__u8 clock_mode;
+} __packed;
+
+struct bcm_set_pcm_format_params {
+	__u8 lsb_first;
+	__u8 fill_value;
+	__u8 fill_method;
+	__u8 fill_num;
+	__u8 right_justify;
+} __packed;
+
 #if IS_ENABLED(CONFIG_BT_BCM)
 
 int btbcm_check_bdaddr(struct hci_dev *hdev);
 int btbcm_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
+int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw);
 
 int btbcm_setup_patchram(struct hci_dev *hdev);
 int btbcm_setup_apple(struct hci_dev *hdev);
 
+int btbcm_initialize(struct hci_dev *hdev, char *fw_name, size_t len);
+int btbcm_finalize(struct hci_dev *hdev);
+
 #else
 
 static inline int btbcm_check_bdaddr(struct hci_dev *hdev)
@@ -41,6 +88,11 @@ static inline int btbcm_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	return -EOPNOTSUPP;
 }
 
+static inline int btbcm_patchram(struct hci_dev *hdev, const struct firmware *fw)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int btbcm_setup_patchram(struct hci_dev *hdev)
 {
 	return 0;
@@ -51,4 +103,15 @@ static inline int btbcm_setup_apple(struct hci_dev *hdev)
 	return 0;
 }
 
+static inline int btbcm_initialize(struct hci_dev *hdev, char *fw_name,
+				   size_t len)
+{
+	return 0;
+}
+
+static inline int btbcm_finalize(struct hci_dev *hdev)
+{
+	return 0;
+}
+
 #endif
diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 2d43d4279b00..828f2f8d1568 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -53,12 +53,6 @@ int btintel_check_bdaddr(struct hci_dev *hdev)
 	}
 
 	bda = (struct hci_rp_read_bd_addr *)skb->data;
-	if (bda->status) {
-		BT_ERR("%s: Intel device address result failed (%02x)",
-		       hdev->name, bda->status);
-		kfree_skb(skb);
-		return -bt_to_errno(bda->status);
-	}
 
 	/* For some Intel based controllers, the default Bluetooth device
 	 * address 00:03:19:9E:8B:00 can be found. These controllers are
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 01d6da577eeb..b9a811900f6a 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -1217,7 +1217,7 @@ static void btmrvl_sdio_dump_firmware(struct btmrvl_private *priv)
 	unsigned int reg, reg_start, reg_end;
 	enum rdwr_status stat;
 	u8 *dbg_ptr, *end_ptr, *fw_dump_data, *fw_dump_ptr;
-	u8 dump_num, idx, i, read_reg, doneflag = 0;
+	u8 dump_num = 0, idx, i, read_reg, doneflag = 0;
 	u32 memory_size, fw_dump_len = 0;
 
 	/* dump sdio register first */
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
new file mode 100644
index 000000000000..84288938f7f2
--- /dev/null
+++ b/drivers/bluetooth/btrtl.c
@@ -0,0 +1,390 @@
+/*
+ *  Bluetooth support for Realtek devices
+ *
+ *  Copyright (C) 2015 Endless Mobile, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/firmware.h>
+#include <asm/unaligned.h>
+#include <linux/usb.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "btrtl.h"
+
+#define VERSION "0.1"
+
+#define RTL_EPATCH_SIGNATURE	"Realtech"
+#define RTL_ROM_LMP_3499	0x3499
+#define RTL_ROM_LMP_8723A	0x1200
+#define RTL_ROM_LMP_8723B	0x8723
+#define RTL_ROM_LMP_8821A	0x8821
+#define RTL_ROM_LMP_8761A	0x8761
+
+static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
+{
+	struct rtl_rom_version_evt *rom_version;
+	struct sk_buff *skb;
+
+	/* Read RTL ROM version command */
+	skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: Read ROM version failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->len != sizeof(*rom_version)) {
+		BT_ERR("%s: RTL version event length mismatch", hdev->name);
+		kfree_skb(skb);
+		return -EIO;
+	}
+
+	rom_version = (struct rtl_rom_version_evt *)skb->data;
+	BT_INFO("%s: rom_version status=%x version=%x",
+		hdev->name, rom_version->status, rom_version->version);
+
+	*version = rom_version->version;
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int rtl8723b_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
+				   const struct firmware *fw,
+				   unsigned char **_buf)
+{
+	const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 };
+	struct rtl_epatch_header *epatch_info;
+	unsigned char *buf;
+	int i, ret, len;
+	size_t min_size;
+	u8 opcode, length, data, rom_version = 0;
+	int project_id = -1;
+	const unsigned char *fwptr, *chip_id_base;
+	const unsigned char *patch_length_base, *patch_offset_base;
+	u32 patch_offset = 0;
+	u16 patch_length, num_patches;
+	const u16 project_id_to_lmp_subver[] = {
+		RTL_ROM_LMP_8723A,
+		RTL_ROM_LMP_8723B,
+		RTL_ROM_LMP_8821A,
+		RTL_ROM_LMP_8761A
+	};
+
+	ret = rtl_read_rom_version(hdev, &rom_version);
+	if (ret)
+		return ret;
+
+	min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3;
+	if (fw->size < min_size)
+		return -EINVAL;
+
+	fwptr = fw->data + fw->size - sizeof(extension_sig);
+	if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) {
+		BT_ERR("%s: extension section signature mismatch", hdev->name);
+		return -EINVAL;
+	}
+
+	/* Loop from the end of the firmware parsing instructions, until
+	 * we find an instruction that identifies the "project ID" for the
+	 * hardware supported by this firwmare file.
+	 * Once we have that, we double-check that that project_id is suitable
+	 * for the hardware we are working with.
+	 */
+	while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) {
+		opcode = *--fwptr;
+		length = *--fwptr;
+		data = *--fwptr;
+
+		BT_DBG("check op=%x len=%x data=%x", opcode, length, data);
+
+		if (opcode == 0xff) /* EOF */
+			break;
+
+		if (length == 0) {
+			BT_ERR("%s: found instruction with length 0",
+			       hdev->name);
+			return -EINVAL;
+		}
+
+		if (opcode == 0 && length == 1) {
+			project_id = data;
+			break;
+		}
+
+		fwptr -= length;
+	}
+
+	if (project_id < 0) {
+		BT_ERR("%s: failed to find version instruction", hdev->name);
+		return -EINVAL;
+	}
+
+	if (project_id >= ARRAY_SIZE(project_id_to_lmp_subver)) {
+		BT_ERR("%s: unknown project id %d", hdev->name, project_id);
+		return -EINVAL;
+	}
+
+	if (lmp_subver != project_id_to_lmp_subver[project_id]) {
+		BT_ERR("%s: firmware is for %x but this is a %x", hdev->name,
+		       project_id_to_lmp_subver[project_id], lmp_subver);
+		return -EINVAL;
+	}
+
+	epatch_info = (struct rtl_epatch_header *)fw->data;
+	if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) {
+		BT_ERR("%s: bad EPATCH signature", hdev->name);
+		return -EINVAL;
+	}
+
+	num_patches = le16_to_cpu(epatch_info->num_patches);
+	BT_DBG("fw_version=%x, num_patches=%d",
+	       le32_to_cpu(epatch_info->fw_version), num_patches);
+
+	/* After the rtl_epatch_header there is a funky patch metadata section.
+	 * Assuming 2 patches, the layout is:
+	 * ChipID1 ChipID2 PatchLength1 PatchLength2 PatchOffset1 PatchOffset2
+	 *
+	 * Find the right patch for this chip.
+	 */
+	min_size += 8 * num_patches;
+	if (fw->size < min_size)
+		return -EINVAL;
+
+	chip_id_base = fw->data + sizeof(struct rtl_epatch_header);
+	patch_length_base = chip_id_base + (sizeof(u16) * num_patches);
+	patch_offset_base = patch_length_base + (sizeof(u16) * num_patches);
+	for (i = 0; i < num_patches; i++) {
+		u16 chip_id = get_unaligned_le16(chip_id_base +
+						 (i * sizeof(u16)));
+		if (chip_id == rom_version + 1) {
+			patch_length = get_unaligned_le16(patch_length_base +
+							  (i * sizeof(u16)));
+			patch_offset = get_unaligned_le32(patch_offset_base +
+							  (i * sizeof(u32)));
+			break;
+		}
+	}
+
+	if (!patch_offset) {
+		BT_ERR("%s: didn't find patch for chip id %d",
+		       hdev->name, rom_version);
+		return -EINVAL;
+	}
+
+	BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i);
+	min_size = patch_offset + patch_length;
+	if (fw->size < min_size)
+		return -EINVAL;
+
+	/* Copy the firmware into a new buffer and write the version at
+	 * the end.
+	 */
+	len = patch_length;
+	buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4);
+
+	*_buf = buf;
+	return len;
+}
+
+static int rtl_download_firmware(struct hci_dev *hdev,
+				 const unsigned char *data, int fw_len)
+{
+	struct rtl_download_cmd *dl_cmd;
+	int frag_num = fw_len / RTL_FRAG_LEN + 1;
+	int frag_len = RTL_FRAG_LEN;
+	int ret = 0;
+	int i;
+
+	dl_cmd = kmalloc(sizeof(struct rtl_download_cmd), GFP_KERNEL);
+	if (!dl_cmd)
+		return -ENOMEM;
+
+	for (i = 0; i < frag_num; i++) {
+		struct sk_buff *skb;
+
+		BT_DBG("download fw (%d/%d)", i, frag_num);
+
+		dl_cmd->index = i;
+		if (i == (frag_num - 1)) {
+			dl_cmd->index |= 0x80; /* data end */
+			frag_len = fw_len % RTL_FRAG_LEN;
+		}
+		memcpy(dl_cmd->data, data, frag_len);
+
+		/* Send download command */
+		skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd,
+				     HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb)) {
+			BT_ERR("%s: download fw command failed (%ld)",
+			       hdev->name, PTR_ERR(skb));
+			ret = -PTR_ERR(skb);
+			goto out;
+		}
+
+		if (skb->len != sizeof(struct rtl_download_response)) {
+			BT_ERR("%s: download fw event length mismatch",
+			       hdev->name);
+			kfree_skb(skb);
+			ret = -EIO;
+			goto out;
+		}
+
+		kfree_skb(skb);
+		data += RTL_FRAG_LEN;
+	}
+
+out:
+	kfree(dl_cmd);
+	return ret;
+}
+
+static int btrtl_setup_rtl8723a(struct hci_dev *hdev)
+{
+	const struct firmware *fw;
+	int ret;
+
+	BT_INFO("%s: rtl: loading rtl_bt/rtl8723a_fw.bin", hdev->name);
+	ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev);
+	if (ret < 0) {
+		BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name);
+		return ret;
+	}
+
+	if (fw->size < 8) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Check that the firmware doesn't have the epatch signature
+	 * (which is only for RTL8723B and newer).
+	 */
+	if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) {
+		BT_ERR("%s: unexpected EPATCH signature!", hdev->name);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = rtl_download_firmware(hdev, fw->data, fw->size);
+
+out:
+	release_firmware(fw);
+	return ret;
+}
+
+static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 lmp_subver,
+				const char *fw_name)
+{
+	unsigned char *fw_data = NULL;
+	const struct firmware *fw;
+	int ret;
+
+	BT_INFO("%s: rtl: loading %s", hdev->name, fw_name);
+	ret = request_firmware(&fw, fw_name, &hdev->dev);
+	if (ret < 0) {
+		BT_ERR("%s: Failed to load %s", hdev->name, fw_name);
+		return ret;
+	}
+
+	ret = rtl8723b_parse_firmware(hdev, lmp_subver, fw, &fw_data);
+	if (ret < 0)
+		goto out;
+
+	ret = rtl_download_firmware(hdev, fw_data, ret);
+	kfree(fw_data);
+	if (ret < 0)
+		goto out;
+
+out:
+	release_firmware(fw);
+	return ret;
+}
+
+static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
+		       hdev->name, PTR_ERR(skb));
+		return skb;
+	}
+
+	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
+		       hdev->name);
+		kfree_skb(skb);
+		return ERR_PTR(-EIO);
+	}
+
+	return skb;
+}
+
+int btrtl_setup_realtek(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	struct hci_rp_read_local_version *resp;
+	u16 lmp_subver;
+
+	skb = btrtl_read_local_version(hdev);
+	if (IS_ERR(skb))
+		return -PTR_ERR(skb);
+
+	resp = (struct hci_rp_read_local_version *)skb->data;
+	BT_INFO("%s: rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x "
+		"lmp_subver=%04x", hdev->name, resp->hci_ver, resp->hci_rev,
+		resp->lmp_ver, resp->lmp_subver);
+
+	lmp_subver = le16_to_cpu(resp->lmp_subver);
+	kfree_skb(skb);
+
+	/* Match a set of subver values that correspond to stock firmware,
+	 * which is not compatible with standard btusb.
+	 * If matched, upload an alternative firmware that does conform to
+	 * standard btusb. Once that firmware is uploaded, the subver changes
+	 * to a different value.
+	 */
+	switch (lmp_subver) {
+	case RTL_ROM_LMP_8723A:
+	case RTL_ROM_LMP_3499:
+		return btrtl_setup_rtl8723a(hdev);
+	case RTL_ROM_LMP_8723B:
+		return btrtl_setup_rtl8723b(hdev, lmp_subver,
+					    "rtl_bt/rtl8723b_fw.bin");
+	case RTL_ROM_LMP_8821A:
+		return btrtl_setup_rtl8723b(hdev, lmp_subver,
+					    "rtl_bt/rtl8821a_fw.bin");
+	case RTL_ROM_LMP_8761A:
+		return btrtl_setup_rtl8723b(hdev, lmp_subver,
+					    "rtl_bt/rtl8761a_fw.bin");
+	default:
+		BT_INFO("rtl: assuming no firmware upload needed.");
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(btrtl_setup_realtek);
+
+MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>");
+MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
new file mode 100644
index 000000000000..38ffe4890cd1
--- /dev/null
+++ b/drivers/bluetooth/btrtl.h
@@ -0,0 +1,52 @@
+/*
+ *  Bluetooth support for Realtek devices
+ *
+ *  Copyright (C) 2015 Endless Mobile, Inc.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ */
+
+#define RTL_FRAG_LEN 252
+
+struct rtl_download_cmd {
+	__u8 index;
+	__u8 data[RTL_FRAG_LEN];
+} __packed;
+
+struct rtl_download_response {
+	__u8 status;
+	__u8 index;
+} __packed;
+
+struct rtl_rom_version_evt {
+	__u8 status;
+	__u8 version;
+} __packed;
+
+struct rtl_epatch_header {
+	__u8 signature[8];
+	__le32 fw_version;
+	__le16 num_patches;
+} __packed;
+
+#if IS_ENABLED(CONFIG_BT_RTL)
+
+int btrtl_setup_realtek(struct hci_dev *hdev);
+
+#else
+
+static inline int btrtl_setup_realtek(struct hci_dev *hdev)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index de7b236eeae7..b4cf8d9c9dac 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -24,19 +24,21 @@
 #include <linux/module.h>
 #include <linux/usb.h>
 #include <linux/firmware.h>
+#include <asm/unaligned.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
 #include "btintel.h"
 #include "btbcm.h"
+#include "btrtl.h"
 
 #define VERSION "0.8"
 
 static bool disable_scofix;
 static bool force_scofix;
 
-static bool reset = 1;
+static bool reset = true;
 
 static struct usb_driver btusb_driver;
 
@@ -57,6 +59,7 @@ static struct usb_driver btusb_driver;
 #define BTUSB_AMP		0x4000
 #define BTUSB_QCA_ROME		0x8000
 #define BTUSB_BCM_APPLE		0x10000
+#define BTUSB_REALTEK		0x20000
 
 static const struct usb_device_id btusb_table[] = {
 	/* Generic Bluetooth USB device */
@@ -176,6 +179,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
@@ -184,6 +188,8 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
@@ -200,6 +206,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
@@ -207,6 +214,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 },
 
 	/* Atheros AR5BBU12 with sflash firmware */
 	{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
@@ -216,6 +224,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 },
 
 	/* QCA ROME chipset */
+	{ USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME },
 	{ USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME },
 
@@ -260,7 +269,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0e5e, 0x6622), .driver_info = BTUSB_BROKEN_ISOC },
 
 	/* Roper Class 1 Bluetooth Dongle (Silicon Wave based) */
-	{ USB_DEVICE(0x1300, 0x0001), .driver_info = BTUSB_SWAVE },
+	{ USB_DEVICE(0x1310, 0x0001), .driver_info = BTUSB_SWAVE },
 
 	/* Digianswer devices */
 	{ USB_DEVICE(0x08fd, 0x0001), .driver_info = BTUSB_DIGIANSWER },
@@ -288,6 +297,28 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01),
 	  .driver_info = BTUSB_IGNORE },
 
+	/* Realtek Bluetooth devices */
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01),
+	  .driver_info = BTUSB_REALTEK },
+
+	/* Additional Realtek 8723AE Bluetooth devices */
+	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3394), .driver_info = BTUSB_REALTEK },
+
+	/* Additional Realtek 8723BE Bluetooth devices */
+	{ USB_DEVICE(0x0489, 0xe085), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x0489, 0xe08b), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3410), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3416), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3459), .driver_info = BTUSB_REALTEK },
+
+	/* Additional Realtek 8821AE Bluetooth devices */
+	{ USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3414), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3458), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3461), .driver_info = BTUSB_REALTEK },
+	{ USB_DEVICE(0x13d3, 0x3462), .driver_info = BTUSB_REALTEK },
+
 	{ }	/* Terminating entry */
 };
 
@@ -303,6 +334,7 @@ static const struct usb_device_id blacklist_table[] = {
 #define BTUSB_FIRMWARE_LOADED	7
 #define BTUSB_FIRMWARE_FAILED	8
 #define BTUSB_BOOTING		9
+#define BTUSB_RESET_RESUME	10
 
 struct btusb_data {
 	struct hci_dev       *hdev;
@@ -892,7 +924,7 @@ static int btusb_open(struct hci_dev *hdev)
 	 */
 	if (data->setup_on_usb) {
 		err = data->setup_on_usb(hdev);
-		if (err <0)
+		if (err < 0)
 			return err;
 	}
 
@@ -1271,28 +1303,6 @@ static void btusb_waker(struct work_struct *work)
 	usb_autopm_put_interface(data->intf);
 }
 
-static struct sk_buff *btusb_read_local_version(struct hci_dev *hdev)
-{
-	struct sk_buff *skb;
-
-	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
-			     HCI_INIT_TIMEOUT);
-	if (IS_ERR(skb)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
-		return skb;
-	}
-
-	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
-		       hdev->name);
-		kfree_skb(skb);
-		return ERR_PTR(-EIO);
-	}
-
-	return skb;
-}
-
 static int btusb_setup_bcm92035(struct hci_dev *hdev)
 {
 	struct sk_buff *skb;
@@ -1313,36 +1323,40 @@ static int btusb_setup_csr(struct hci_dev *hdev)
 {
 	struct hci_rp_read_local_version *rp;
 	struct sk_buff *skb;
-	int ret;
 
 	BT_DBG("%s", hdev->name);
 
-	skb = btusb_read_local_version(hdev);
-	if (IS_ERR(skb))
-		return -PTR_ERR(skb);
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		int err = PTR_ERR(skb);
+		BT_ERR("%s: CSR: Local version failed (%d)", hdev->name, err);
+		return err;
+	}
+
+	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
+		BT_ERR("%s: CSR: Local version length mismatch", hdev->name);
+		kfree_skb(skb);
+		return -EIO;
+	}
 
 	rp = (struct hci_rp_read_local_version *)skb->data;
 
-	if (!rp->status) {
-		if (le16_to_cpu(rp->manufacturer) != 10) {
-			/* Clear the reset quirk since this is not an actual
-			 * early Bluetooth 1.1 device from CSR.
-			 */
-			clear_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
+	if (le16_to_cpu(rp->manufacturer) != 10) {
+		/* Clear the reset quirk since this is not an actual
+		 * early Bluetooth 1.1 device from CSR.
+		 */
+		clear_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
 
-			/* These fake CSR controllers have all a broken
-			 * stored link key handling and so just disable it.
-			 */
-			set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY,
-				&hdev->quirks);
-		}
+		/* These fake CSR controllers have all a broken
+		 * stored link key handling and so just disable it.
+		 */
+		set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks);
 	}
 
-	ret = -bt_to_errno(rp->status);
-
 	kfree_skb(skb);
 
-	return ret;
+	return 0;
 }
 
 static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
@@ -1552,12 +1566,6 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	}
 
 	ver = (struct intel_version *)skb->data;
-	if (ver->status) {
-		BT_ERR("%s Intel fw version event failed (%02x)", hdev->name,
-		       ver->status);
-		kfree_skb(skb);
-		return -bt_to_errno(ver->status);
-	}
 
 	BT_INFO("%s: read Intel version: %02x%02x%02x%02x%02x%02x%02x%02x%02x",
 		hdev->name, ver->hw_platform, ver->hw_variant,
@@ -1591,6 +1599,8 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	}
 	fw_ptr = fw->data;
 
+	kfree_skb(skb);
+
 	/* This Intel specific command enables the manufacturer mode of the
 	 * controller.
 	 *
@@ -1605,15 +1615,6 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 		return PTR_ERR(skb);
 	}
 
-	if (skb->data[0]) {
-		u8 evt_status = skb->data[0];
-
-		BT_ERR("%s enable Intel manufacturer mode event failed (%02x)",
-		       hdev->name, evt_status);
-		kfree_skb(skb);
-		release_firmware(fw);
-		return -bt_to_errno(evt_status);
-	}
 	kfree_skb(skb);
 
 	disable_patch = 1;
@@ -1932,6 +1933,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	struct intel_boot_params *params;
 	const struct firmware *fw;
 	const u8 *fw_ptr;
+	u32 frag_len;
 	char fwname[64];
 	ktime_t calltime, delta, rettime;
 	unsigned long long duration;
@@ -1959,13 +1961,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	}
 
 	ver = (struct intel_version *)skb->data;
-	if (ver->status) {
-		BT_ERR("%s: Intel version command failure (%02x)",
-		       hdev->name, ver->status);
-		err = -bt_to_errno(ver->status);
-		kfree_skb(skb);
-		return err;
-	}
 
 	/* The hardware platform number has a fixed value of 0x37 and
 	 * for now only accept this single value.
@@ -2040,13 +2035,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	}
 
 	params = (struct intel_boot_params *)skb->data;
-	if (params->status) {
-		BT_ERR("%s: Intel boot parameters command failure (%02x)",
-		       hdev->name, params->status);
-		err = -bt_to_errno(params->status);
-		kfree_skb(skb);
-		return err;
-	}
 
 	BT_INFO("%s: Device revision is %u", hdev->name,
 		le16_to_cpu(params->dev_revid));
@@ -2096,6 +2084,12 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 
 	BT_INFO("%s: Found device firmware: %s", hdev->name, fwname);
 
+	/* Save the DDC file name for later use to apply once the firmware
+	 * downloading is done.
+	 */
+	snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.ddc",
+		 le16_to_cpu(params->dev_revid));
+
 	kfree_skb(skb);
 
 	if (fw->size < 644) {
@@ -2138,24 +2132,33 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	}
 
 	fw_ptr = fw->data + 644;
+	frag_len = 0;
 
 	while (fw_ptr - fw->data < fw->size) {
-		struct hci_command_hdr *cmd = (void *)fw_ptr;
-		u8 cmd_len;
+		struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len);
 
-		cmd_len = sizeof(*cmd) + cmd->plen;
+		frag_len += sizeof(*cmd) + cmd->plen;
 
-		/* Send each command from the firmware data buffer as
-		 * a single Data fragment.
+		/* The paramter length of the secure send command requires
+		 * a 4 byte alignment. It happens so that the firmware file
+		 * contains proper Intel_NOP commands to align the fragments
+		 * as needed.
+		 *
+		 * Send set of commands with 4 byte alignment from the
+		 * firmware data buffer as a single Data fragement.
 		 */
-		err = btusb_intel_secure_send(hdev, 0x01, cmd_len, fw_ptr);
-		if (err < 0) {
-			BT_ERR("%s: Failed to send firmware data (%d)",
-			       hdev->name, err);
-			goto done;
-		}
+		if (!(frag_len % 4)) {
+			err = btusb_intel_secure_send(hdev, 0x01, frag_len,
+						      fw_ptr);
+			if (err < 0) {
+				BT_ERR("%s: Failed to send firmware data (%d)",
+				       hdev->name, err);
+				goto done;
+			}
 
-		fw_ptr += cmd_len;
+			fw_ptr += frag_len;
+			frag_len = 0;
+		}
 	}
 
 	set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
@@ -2248,6 +2251,43 @@ done:
 
 	clear_bit(BTUSB_BOOTLOADER, &data->flags);
 
+	/* Once the device is running in operational mode, it needs to apply
+	 * the device configuration (DDC) parameters.
+	 *
+	 * The device can work without DDC parameters, so even if it fails
+	 * to load the file, no need to fail the setup.
+	 */
+	err = request_firmware_direct(&fw, fwname, &hdev->dev);
+	if (err < 0)
+		return 0;
+
+	BT_INFO("%s: Found Intel DDC parameters: %s", hdev->name, fwname);
+
+	fw_ptr = fw->data;
+
+	/* DDC file contains one or more DDC structure which has
+	 * Length (1 byte), DDC ID (2 bytes), and DDC value (Length - 2).
+	 */
+	while (fw->size > fw_ptr - fw->data) {
+		u8 cmd_plen = fw_ptr[0] + sizeof(u8);
+
+		skb = __hci_cmd_sync(hdev, 0xfc8b, cmd_plen, fw_ptr,
+				     HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb)) {
+			BT_ERR("%s: Failed to send Intel_Write_DDC (%ld)",
+			       hdev->name, PTR_ERR(skb));
+			release_firmware(fw);
+			return PTR_ERR(skb);
+		}
+
+		fw_ptr += cmd_plen;
+		kfree_skb(skb);
+	}
+
+	release_firmware(fw);
+
+	BT_INFO("%s: Applying Intel DDC parameters completed", hdev->name);
+
 	return 0;
 }
 
@@ -2279,13 +2319,6 @@ static void btusb_hw_error_intel(struct hci_dev *hdev, u8 code)
 		return;
 	}
 
-	if (skb->data[0] != 0x00) {
-		BT_ERR("%s: Exception info command failure (%02x)",
-		       hdev->name, skb->data[0]);
-		kfree_skb(skb);
-		return;
-	}
-
 	BT_ERR("%s: Exception info %s", hdev->name, (char *)(skb->data + 1));
 
 	kfree_skb(skb);
@@ -2393,6 +2426,7 @@ struct qca_device_info {
 static const struct qca_device_info qca_devices_table[] = {
 	{ 0x00000100, 20, 4, 10 }, /* Rome 1.0 */
 	{ 0x00000101, 20, 4, 10 }, /* Rome 1.1 */
+	{ 0x00000200, 28, 4, 18 }, /* Rome 2.0 */
 	{ 0x00000201, 28, 4, 18 }, /* Rome 2.1 */
 	{ 0x00000300, 28, 4, 18 }, /* Rome 3.0 */
 	{ 0x00000302, 28, 4, 18 }, /* Rome 3.2 */
@@ -2577,7 +2611,7 @@ static int btusb_setup_qca(struct hci_dev *hdev)
 	int i, err;
 
 	err = btusb_qca_send_vendor_req(hdev, QCA_GET_TARGET_VERSION, &ver,
-				        sizeof(ver));
+					sizeof(ver));
 	if (err < 0)
 		return err;
 
@@ -2776,6 +2810,18 @@ static int btusb_probe(struct usb_interface *intf,
 		hdev->set_bdaddr = btusb_set_bdaddr_ath3012;
 	}
 
+#ifdef CONFIG_BT_HCIBTUSB_RTL
+	if (id->driver_info & BTUSB_REALTEK) {
+		hdev->setup = btrtl_setup_realtek;
+
+		/* Realtek devices lose their updated firmware over suspend,
+		 * but the USB hub doesn't notice any status change.
+		 * Explicitly request a device reset on resume.
+		 */
+		set_bit(BTUSB_RESET_RESUME, &data->flags);
+	}
+#endif
+
 	if (id->driver_info & BTUSB_AMP) {
 		/* AMP controllers do not support SCO packets */
 		data->isoc = NULL;
@@ -2906,6 +2952,14 @@ static int btusb_suspend(struct usb_interface *intf, pm_message_t message)
 	btusb_stop_traffic(data);
 	usb_kill_anchored_urbs(&data->tx_anchor);
 
+	/* Optionally request a device reset on resume, but only when
+	 * wakeups are disabled. If wakeups are enabled we assume the
+	 * device will stay powered up throughout suspend.
+	 */
+	if (test_bit(BTUSB_RESET_RESUME, &data->flags) &&
+	    !device_may_wakeup(&data->udev->dev))
+		data->udev->reset_resume = 1;
+
 	return 0;
 }
 
diff --git a/drivers/bluetooth/btwilink.c b/drivers/bluetooth/btwilink.c
index 55c135b7757a..7a722df97343 100644
--- a/drivers/bluetooth/btwilink.c
+++ b/drivers/bluetooth/btwilink.c
@@ -22,7 +22,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  *
  */
-#define DEBUG
+
 #include <linux/platform_device.h>
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c
index 1b3f8647ea2f..6da5e4ca13ea 100644
--- a/drivers/bluetooth/hci_ath.c
+++ b/drivers/bluetooth/hci_ath.c
@@ -95,7 +95,6 @@ static void ath_hci_uart_work(struct work_struct *work)
 	hci_uart_tx_wakeup(hu);
 }
 
-/* Initialize protocol */
 static int ath_open(struct hci_uart *hu)
 {
 	struct ath_struct *ath;
@@ -116,8 +115,7 @@ static int ath_open(struct hci_uart *hu)
 	return 0;
 }
 
-/* Flush protocol data */
-static int ath_flush(struct hci_uart *hu)
+static int ath_close(struct hci_uart *hu)
 {
 	struct ath_struct *ath = hu->priv;
 
@@ -125,11 +123,17 @@ static int ath_flush(struct hci_uart *hu)
 
 	skb_queue_purge(&ath->txq);
 
+	kfree_skb(ath->rx_skb);
+
+	cancel_work_sync(&ath->ctxtsw);
+
+	hu->priv = NULL;
+	kfree(ath);
+
 	return 0;
 }
 
-/* Close protocol */
-static int ath_close(struct hci_uart *hu)
+static int ath_flush(struct hci_uart *hu)
 {
 	struct ath_struct *ath = hu->priv;
 
@@ -137,19 +141,66 @@ static int ath_close(struct hci_uart *hu)
 
 	skb_queue_purge(&ath->txq);
 
-	kfree_skb(ath->rx_skb);
+	return 0;
+}
 
-	cancel_work_sync(&ath->ctxtsw);
+static int ath_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	struct sk_buff *skb;
+	u8 buf[10];
+	int err;
+
+	buf[0] = 0x01;
+	buf[1] = 0x01;
+	buf[2] = 0x00;
+	buf[3] = sizeof(bdaddr_t);
+	memcpy(buf + 4, bdaddr, sizeof(bdaddr_t));
+
+	skb = __hci_cmd_sync(hdev, 0xfc0b, sizeof(buf), buf, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		BT_ERR("%s: Change address command failed (%d)",
+		       hdev->name, err);
+		return err;
+	}
+	kfree_skb(skb);
 
-	hu->priv = NULL;
-	kfree(ath);
+	return 0;
+}
+
+static int ath_setup(struct hci_uart *hu)
+{
+	BT_DBG("hu %p", hu);
+
+	hu->hdev->set_bdaddr = ath_set_bdaddr;
 
 	return 0;
 }
 
+static const struct h4_recv_pkt ath_recv_pkts[] = {
+	{ H4_RECV_ACL,   .recv = hci_recv_frame },
+	{ H4_RECV_SCO,   .recv = hci_recv_frame },
+	{ H4_RECV_EVENT, .recv = hci_recv_frame },
+};
+
+static int ath_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct ath_struct *ath = hu->priv;
+
+	ath->rx_skb = h4_recv_buf(hu->hdev, ath->rx_skb, data, count,
+				  ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
+	if (IS_ERR(ath->rx_skb)) {
+		int err = PTR_ERR(ath->rx_skb);
+		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		ath->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
 #define HCI_OP_ATH_SLEEP 0xFC04
 
-/* Enqueue frame for transmittion */
 static int ath_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 {
 	struct ath_struct *ath = hu->priv;
@@ -159,8 +210,7 @@ static int ath_enqueue(struct hci_uart *hu, struct sk_buff *skb)
 		return 0;
 	}
 
-	/*
-	 * Update power management enable flag with parameters of
+	/* Update power management enable flag with parameters of
 	 * HCI sleep enable vendor specific HCI command.
 	 */
 	if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
@@ -190,37 +240,16 @@ static struct sk_buff *ath_dequeue(struct hci_uart *hu)
 	return skb_dequeue(&ath->txq);
 }
 
-static const struct h4_recv_pkt ath_recv_pkts[] = {
-	{ H4_RECV_ACL,   .recv = hci_recv_frame },
-	{ H4_RECV_SCO,   .recv = hci_recv_frame },
-	{ H4_RECV_EVENT, .recv = hci_recv_frame },
-};
-
-/* Recv data */
-static int ath_recv(struct hci_uart *hu, const void *data, int count)
-{
-	struct ath_struct *ath = hu->priv;
-
-	ath->rx_skb = h4_recv_buf(hu->hdev, ath->rx_skb, data, count,
-				  ath_recv_pkts, ARRAY_SIZE(ath_recv_pkts));
-	if (IS_ERR(ath->rx_skb)) {
-		int err = PTR_ERR(ath->rx_skb);
-		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
-		return err;
-	}
-
-	return count;
-}
-
 static const struct hci_uart_proto athp = {
 	.id		= HCI_UART_ATH3K,
 	.name		= "ATH3K",
 	.open		= ath_open,
 	.close		= ath_close,
+	.flush		= ath_flush,
+	.setup		= ath_setup,
 	.recv		= ath_recv,
 	.enqueue	= ath_enqueue,
 	.dequeue	= ath_dequeue,
-	.flush		= ath_flush,
 };
 
 int __init ath_init(void)
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 1ec0b4a5ffa6..23523e140a9a 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/skbuff.h>
+#include <linux/firmware.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -36,6 +37,55 @@ struct bcm_data {
 	struct sk_buff_head txq;
 };
 
+static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed)
+{
+	struct hci_dev *hdev = hu->hdev;
+	struct sk_buff *skb;
+	struct bcm_update_uart_baud_rate param;
+
+	if (speed > 3000000) {
+		struct bcm_write_uart_clock_setting clock;
+
+		clock.type = BCM_UART_CLOCK_48MHZ;
+
+		BT_DBG("%s: Set Controller clock (%d)", hdev->name, clock.type);
+
+		/* This Broadcom specific command changes the UART's controller
+		 * clock for baud rate > 3000000.
+		 */
+		skb = __hci_cmd_sync(hdev, 0xfc45, 1, &clock, HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb)) {
+			int err = PTR_ERR(skb);
+			BT_ERR("%s: BCM: failed to write clock command (%d)",
+			       hdev->name, err);
+			return err;
+		}
+
+		kfree_skb(skb);
+	}
+
+	BT_DBG("%s: Set Controller UART speed to %d bit/s", hdev->name, speed);
+
+	param.zero = cpu_to_le16(0);
+	param.baud_rate = cpu_to_le32(speed);
+
+	/* This Broadcom specific command changes the UART's controller baud
+	 * rate.
+	 */
+	skb = __hci_cmd_sync(hdev, 0xfc18, sizeof(param), &param,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		int err = PTR_ERR(skb);
+		BT_ERR("%s: BCM: failed to write update baudrate command (%d)",
+		       hdev->name, err);
+		return err;
+	}
+
+	kfree_skb(skb);
+
+	return 0;
+}
+
 static int bcm_open(struct hci_uart *hu)
 {
 	struct bcm_data *bcm;
@@ -79,11 +129,62 @@ static int bcm_flush(struct hci_uart *hu)
 
 static int bcm_setup(struct hci_uart *hu)
 {
+	char fw_name[64];
+	const struct firmware *fw;
+	unsigned int speed;
+	int err;
+
 	BT_DBG("hu %p", hu);
 
 	hu->hdev->set_bdaddr = btbcm_set_bdaddr;
 
-	return btbcm_setup_patchram(hu->hdev);
+	err = btbcm_initialize(hu->hdev, fw_name, sizeof(fw_name));
+	if (err)
+		return err;
+
+	err = request_firmware(&fw, fw_name, &hu->hdev->dev);
+	if (err < 0) {
+		BT_INFO("%s: BCM: Patch %s not found", hu->hdev->name, fw_name);
+		return 0;
+	}
+
+	err = btbcm_patchram(hu->hdev, fw);
+	if (err) {
+		BT_INFO("%s: BCM: Patch failed (%d)", hu->hdev->name, err);
+		goto finalize;
+	}
+
+	/* Init speed if any */
+	if (hu->init_speed)
+		speed = hu->init_speed;
+	else if (hu->proto->init_speed)
+		speed = hu->proto->init_speed;
+	else
+		speed = 0;
+
+	if (speed)
+		hci_uart_set_baudrate(hu, speed);
+
+	/* Operational speed if any */
+	if (hu->oper_speed)
+		speed = hu->oper_speed;
+	else if (hu->proto->oper_speed)
+		speed = hu->proto->oper_speed;
+	else
+		speed = 0;
+
+	if (speed) {
+		err = bcm_set_baudrate(hu, speed);
+		if (!err)
+			hci_uart_set_baudrate(hu, speed);
+	}
+
+finalize:
+	release_firmware(fw);
+
+	err = btbcm_finalize(hu->hdev);
+
+	return err;
 }
 
 static const struct h4_recv_pkt bcm_recv_pkts[] = {
@@ -104,6 +205,7 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count)
 	if (IS_ERR(bcm->rx_skb)) {
 		int err = PTR_ERR(bcm->rx_skb);
 		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		bcm->rx_skb = NULL;
 		return err;
 	}
 
@@ -133,10 +235,13 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu)
 static const struct hci_uart_proto bcm_proto = {
 	.id		= HCI_UART_BCM,
 	.name		= "BCM",
+	.init_speed	= 115200,
+	.oper_speed	= 4000000,
 	.open		= bcm_open,
 	.close		= bcm_close,
 	.flush		= bcm_flush,
 	.setup		= bcm_setup,
+	.set_baudrate	= bcm_set_baudrate,
 	.recv		= bcm_recv,
 	.enqueue	= bcm_enqueue,
 	.dequeue	= bcm_dequeue,
diff --git a/drivers/bluetooth/hci_bcsp.c b/drivers/bluetooth/hci_bcsp.c
index dc8e3d4356a0..d0b615a932d1 100644
--- a/drivers/bluetooth/hci_bcsp.c
+++ b/drivers/bluetooth/hci_bcsp.c
@@ -47,8 +47,8 @@
 
 #include "hci_uart.h"
 
-static bool txcrc = 1;
-static bool hciextn = 1;
+static bool txcrc = true;
+static bool hciextn = true;
 
 #define BCSP_TXWINSIZE	4
 
@@ -436,7 +436,7 @@ static inline void bcsp_unslip_one_byte(struct bcsp_struct *bcsp, unsigned char
 			break;
 		default:
 			memcpy(skb_put(bcsp->rx_skb, 1), &byte, 1);
-			if ((bcsp->rx_skb-> data[0] & 0x40) != 0 && 
+			if ((bcsp->rx_skb->data[0] & 0x40) != 0 &&
 					bcsp->rx_state != BCSP_W4_CRC)
 				bcsp_crc_update(&bcsp->message_crc, byte);
 			bcsp->rx_count--;
@@ -447,24 +447,24 @@ static inline void bcsp_unslip_one_byte(struct bcsp_struct *bcsp, unsigned char
 		switch (byte) {
 		case 0xdc:
 			memcpy(skb_put(bcsp->rx_skb, 1), &c0, 1);
-			if ((bcsp->rx_skb-> data[0] & 0x40) != 0 && 
+			if ((bcsp->rx_skb->data[0] & 0x40) != 0 &&
 					bcsp->rx_state != BCSP_W4_CRC)
-				bcsp_crc_update(&bcsp-> message_crc, 0xc0);
+				bcsp_crc_update(&bcsp->message_crc, 0xc0);
 			bcsp->rx_esc_state = BCSP_ESCSTATE_NOESC;
 			bcsp->rx_count--;
 			break;
 
 		case 0xdd:
 			memcpy(skb_put(bcsp->rx_skb, 1), &db, 1);
-			if ((bcsp->rx_skb-> data[0] & 0x40) != 0 && 
+			if ((bcsp->rx_skb->data[0] & 0x40) != 0 &&
 					bcsp->rx_state != BCSP_W4_CRC) 
-				bcsp_crc_update(&bcsp-> message_crc, 0xdb);
+				bcsp_crc_update(&bcsp->message_crc, 0xdb);
 			bcsp->rx_esc_state = BCSP_ESCSTATE_NOESC;
 			bcsp->rx_count--;
 			break;
 
 		default:
-			BT_ERR ("Invalid byte %02x after esc byte", byte);
+			BT_ERR("Invalid byte %02x after esc byte", byte);
 			kfree_skb(bcsp->rx_skb);
 			bcsp->rx_skb = NULL;
 			bcsp->rx_state = BCSP_W4_PKT_DELIMITER;
@@ -527,7 +527,7 @@ static void bcsp_complete_rx_pkt(struct hci_uart *hu)
 
 				hci_recv_frame(hu->hdev, bcsp->rx_skb);
 			} else {
-				BT_ERR ("Packet for unknown channel (%u %s)",
+				BT_ERR("Packet for unknown channel (%u %s)",
 					bcsp->rx_skb->data[1] & 0x0f,
 					bcsp->rx_skb->data[0] & 0x80 ? 
 					"reliable" : "unreliable");
@@ -587,7 +587,7 @@ static int bcsp_recv(struct hci_uart *hu, const void *data, int count)
 			}
 			if (bcsp->rx_skb->data[0] & 0x80	/* reliable pkt */
 			    		&& (bcsp->rx_skb->data[0] & 0x07) != bcsp->rxseq_txack) {
-				BT_ERR ("Out-of-order packet arrived, got %u expected %u",
+				BT_ERR("Out-of-order packet arrived, got %u expected %u",
 					bcsp->rx_skb->data[0] & 0x07, bcsp->rxseq_txack);
 
 				kfree_skb(bcsp->rx_skb);
diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index f7190f01e135..57faddc53645 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -133,6 +133,7 @@ static int h4_recv(struct hci_uart *hu, const void *data, int count)
 	if (IS_ERR(h4->rx_skb)) {
 		int err = PTR_ERR(h4->rx_skb);
 		BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err);
+		h4->rx_skb = NULL;
 		return err;
 	}
 
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 5c9a73f02664..177dd69fdd95 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -40,6 +40,7 @@
 #include <linux/signal.h>
 #include <linux/ioctl.h>
 #include <linux/skbuff.h>
+#include <linux/firmware.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -265,11 +266,133 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	return 0;
 }
 
+/* Flow control or un-flow control the device */
+void hci_uart_set_flow_control(struct hci_uart *hu, bool enable)
+{
+	struct tty_struct *tty = hu->tty;
+	struct ktermios ktermios;
+	int status;
+	unsigned int set = 0;
+	unsigned int clear = 0;
+
+	if (enable) {
+		/* Disable hardware flow control */
+		ktermios = tty->termios;
+		ktermios.c_cflag &= ~CRTSCTS;
+		status = tty_set_termios(tty, &ktermios);
+		BT_DBG("Disabling hardware flow control: %s",
+		       status ? "failed" : "success");
+
+		/* Clear RTS to prevent the device from sending */
+		/* Most UARTs need OUT2 to enable interrupts */
+		status = tty->driver->ops->tiocmget(tty);
+		BT_DBG("Current tiocm 0x%x", status);
+
+		set &= ~(TIOCM_OUT2 | TIOCM_RTS);
+		clear = ~set;
+		set &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 |
+		       TIOCM_OUT2 | TIOCM_LOOP;
+		clear &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 |
+			 TIOCM_OUT2 | TIOCM_LOOP;
+		status = tty->driver->ops->tiocmset(tty, set, clear);
+		BT_DBG("Clearing RTS: %s", status ? "failed" : "success");
+	} else {
+		/* Set RTS to allow the device to send again */
+		status = tty->driver->ops->tiocmget(tty);
+		BT_DBG("Current tiocm 0x%x", status);
+
+		set |= (TIOCM_OUT2 | TIOCM_RTS);
+		clear = ~set;
+		set &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 |
+		       TIOCM_OUT2 | TIOCM_LOOP;
+		clear &= TIOCM_DTR | TIOCM_RTS | TIOCM_OUT1 |
+			 TIOCM_OUT2 | TIOCM_LOOP;
+		status = tty->driver->ops->tiocmset(tty, set, clear);
+		BT_DBG("Setting RTS: %s", status ? "failed" : "success");
+
+		/* Re-enable hardware flow control */
+		ktermios = tty->termios;
+		ktermios.c_cflag |= CRTSCTS;
+		status = tty_set_termios(tty, &ktermios);
+		BT_DBG("Enabling hardware flow control: %s",
+		       status ? "failed" : "success");
+	}
+}
+
+void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
+			 unsigned int oper_speed)
+{
+	hu->init_speed = init_speed;
+	hu->oper_speed = oper_speed;
+}
+
+void hci_uart_init_tty(struct hci_uart *hu)
+{
+	struct tty_struct *tty = hu->tty;
+	struct ktermios ktermios;
+
+	/* Bring the UART into a known 8 bits no parity hw fc state */
+	ktermios = tty->termios;
+	ktermios.c_iflag &= ~(IGNBRK | BRKINT | PARMRK | ISTRIP |
+			      INLCR | IGNCR | ICRNL | IXON);
+	ktermios.c_oflag &= ~OPOST;
+	ktermios.c_lflag &= ~(ECHO | ECHONL | ICANON | ISIG | IEXTEN);
+	ktermios.c_cflag &= ~(CSIZE | PARENB);
+	ktermios.c_cflag |= CS8;
+	ktermios.c_cflag |= CRTSCTS;
+
+	/* tty_set_termios() return not checked as it is always 0 */
+	tty_set_termios(tty, &ktermios);
+}
+
+void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed)
+{
+	struct tty_struct *tty = hu->tty;
+	struct ktermios ktermios;
+
+	ktermios = tty->termios;
+	ktermios.c_cflag &= ~CBAUD;
+	tty_termios_encode_baud_rate(&ktermios, speed, speed);
+
+	/* tty_set_termios() return not checked as it is always 0 */
+	tty_set_termios(tty, &ktermios);
+
+	BT_DBG("%s: New tty speeds: %d/%d", hu->hdev->name,
+	       tty->termios.c_ispeed, tty->termios.c_ospeed);
+}
+
 static int hci_uart_setup(struct hci_dev *hdev)
 {
 	struct hci_uart *hu = hci_get_drvdata(hdev);
 	struct hci_rp_read_local_version *ver;
 	struct sk_buff *skb;
+	unsigned int speed;
+	int err;
+
+	/* Init speed if any */
+	if (hu->init_speed)
+		speed = hu->init_speed;
+	else if (hu->proto->init_speed)
+		speed = hu->proto->init_speed;
+	else
+		speed = 0;
+
+	if (speed)
+		hci_uart_set_baudrate(hu, speed);
+
+	/* Operational speed if any */
+	if (hu->oper_speed)
+		speed = hu->oper_speed;
+	else if (hu->proto->oper_speed)
+		speed = hu->proto->oper_speed;
+	else
+		speed = 0;
+
+	if (hu->proto->set_baudrate && speed) {
+		err = hu->proto->set_baudrate(hu, speed);
+		if (!err)
+			hci_uart_set_baudrate(hu, speed);
+	}
 
 	if (hu->proto->setup)
 		return hu->proto->setup(hu);
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index 72120a5ba13c..ce9c670956f5 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -58,10 +58,13 @@ struct hci_uart;
 struct hci_uart_proto {
 	unsigned int id;
 	const char *name;
+	unsigned int init_speed;
+	unsigned int oper_speed;
 	int (*open)(struct hci_uart *hu);
 	int (*close)(struct hci_uart *hu);
 	int (*flush)(struct hci_uart *hu);
 	int (*setup)(struct hci_uart *hu);
+	int (*set_baudrate)(struct hci_uart *hu, unsigned int speed);
 	int (*recv)(struct hci_uart *hu, const void *data, int len);
 	int (*enqueue)(struct hci_uart *hu, struct sk_buff *skb);
 	struct sk_buff *(*dequeue)(struct hci_uart *hu);
@@ -82,6 +85,9 @@ struct hci_uart {
 	struct sk_buff		*tx_skb;
 	unsigned long		tx_state;
 	spinlock_t		rx_lock;
+
+	unsigned int init_speed;
+	unsigned int oper_speed;
 };
 
 /* HCI_UART proto flag bits */
@@ -96,6 +102,11 @@ int hci_uart_register_proto(const struct hci_uart_proto *p);
 int hci_uart_unregister_proto(const struct hci_uart_proto *p);
 int hci_uart_tx_wakeup(struct hci_uart *hu);
 int hci_uart_init_ready(struct hci_uart *hu);
+void hci_uart_init_tty(struct hci_uart *hu);
+void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed);
+void hci_uart_set_flow_control(struct hci_uart *hu, bool enable);
+void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
+			 unsigned int oper_speed);
 
 #ifdef CONFIG_BT_HCIUART_H4
 int h4_init(void);
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 6653473f2757..78653db2ef2b 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -366,7 +366,7 @@ static const struct file_operations vhci_fops = {
 	.llseek		= no_llseek,
 };
 
-static struct miscdevice vhci_miscdev= {
+static struct miscdevice vhci_miscdev = {
 	.name	= "vhci",
 	.fops	= &vhci_fops,
 	.minor	= VHCI_MINOR,
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index b854125e4831..5340604b23a4 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -660,7 +660,7 @@ validate_group(struct perf_event *event)
 		 * Initialise the fake PMU. We only need to populate the
 		 * used_mask for the purposes of validation.
 		 */
-		.used_mask = CPU_BITS_NONE,
+		.used_mask = { 0 },
 	};
 
 	if (!validate_event(event->pmu, &fake_pmu, leader))
diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c
index 5bd792c68f9b..ab3bde16ecb4 100644
--- a/drivers/bus/mips_cdmm.c
+++ b/drivers/bus/mips_cdmm.c
@@ -453,7 +453,7 @@ void __iomem *mips_cdmm_early_probe(unsigned int dev_type)
 
 	/* Look for a specific device type */
 	for (; drb < bus->drbs; drb += size + 1) {
-		acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+		acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
 		type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
 		if (type == dev_type)
 			return cdmm + drb * CDMM_DRB_SIZE;
@@ -500,7 +500,7 @@ static void mips_cdmm_bus_discover(struct mips_cdmm_bus *bus)
 	bus->discovered = true;
 	pr_info("cdmm%u discovery (%u blocks)\n", cpu, bus->drbs);
 	for (; drb < bus->drbs; drb += size + 1) {
-		acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+		acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
 		type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
 		size = (acsr & CDMM_ACSR_DEVSIZE) >> CDMM_ACSR_DEVSIZE_SHIFT;
 		rev  = (acsr & CDMM_ACSR_DEVREV)  >> CDMM_ACSR_DEVREV_SHIFT;
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index fb9ec6221730..c43c3d2baf73 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -57,8 +57,8 @@
 #include <linux/of_address.h>
 #include <linux/debugfs.h>
 #include <linux/log2.h>
-#include <linux/syscore_ops.h>
 #include <linux/memblock.h>
+#include <linux/syscore_ops.h>
 
 /*
  * DDR target is the same on all platforms.
@@ -70,6 +70,7 @@
  */
 #define WIN_CTRL_OFF		0x0000
 #define   WIN_CTRL_ENABLE       BIT(0)
+/* Only on HW I/O coherency capable platforms */
 #define   WIN_CTRL_SYNCBARRIER  BIT(1)
 #define   WIN_CTRL_TGT_MASK     0xf0
 #define   WIN_CTRL_TGT_SHIFT    4
@@ -102,9 +103,7 @@
 
 /* Relative to mbusbridge_base */
 #define MBUS_BRIDGE_CTRL_OFF	0x0
-#define  MBUS_BRIDGE_SIZE_MASK  0xffff0000
 #define MBUS_BRIDGE_BASE_OFF	0x4
-#define  MBUS_BRIDGE_BASE_MASK  0xffff0000
 
 /* Maximum number of windows, for all known platforms */
 #define MBUS_WINS_MAX           20
@@ -154,13 +153,39 @@ struct mvebu_mbus_state {
 
 static struct mvebu_mbus_state mbus_state;
 
+/*
+ * We provide two variants of the mv_mbus_dram_info() function:
+ *
+ * - The normal one, where the described DRAM ranges may overlap with
+ *   the I/O windows, but for which the DRAM ranges are guaranteed to
+ *   have a power of two size. Such ranges are suitable for the DMA
+ *   masters that only DMA between the RAM and the device, which is
+ *   actually all devices except the crypto engines.
+ *
+ * - The 'nooverlap' one, where the described DRAM ranges are
+ *   guaranteed to not overlap with the I/O windows, but for which the
+ *   DRAM ranges will not have power of two sizes. They will only be
+ *   aligned on a 64 KB boundary, and have a size multiple of 64
+ *   KB. Such ranges are suitable for the DMA masters that DMA between
+ *   the crypto SRAM (which is mapped through an I/O window) and a
+ *   device. This is the case for the crypto engines.
+ */
+
 static struct mbus_dram_target_info mvebu_mbus_dram_info;
+static struct mbus_dram_target_info mvebu_mbus_dram_info_nooverlap;
+
 const struct mbus_dram_target_info *mv_mbus_dram_info(void)
 {
 	return &mvebu_mbus_dram_info;
 }
 EXPORT_SYMBOL_GPL(mv_mbus_dram_info);
 
+const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(void)
+{
+	return &mvebu_mbus_dram_info_nooverlap;
+}
+EXPORT_SYMBOL_GPL(mv_mbus_dram_info_nooverlap);
+
 /* Checks whether the given window has remap capability */
 static bool mvebu_mbus_window_is_remappable(struct mvebu_mbus_state *mbus,
 					    const int win)
@@ -323,8 +348,9 @@ static int mvebu_mbus_setup_window(struct mvebu_mbus_state *mbus,
 	ctrl = ((size - 1) & WIN_CTRL_SIZE_MASK) |
 		(attr << WIN_CTRL_ATTR_SHIFT)    |
 		(target << WIN_CTRL_TGT_SHIFT)   |
-		WIN_CTRL_SYNCBARRIER             |
 		WIN_CTRL_ENABLE;
+	if (mbus->hw_io_coherency)
+		ctrl |= WIN_CTRL_SYNCBARRIER;
 
 	writel(base & WIN_BASE_LOW, addr + WIN_BASE_OFF);
 	writel(ctrl, addr + WIN_CTRL_OFF);
@@ -592,7 +618,7 @@ mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
 		 * This part of the memory is above 4 GB, so we don't
 		 * care for the MBus bridge hole.
 		 */
-		if (r->base >= 0x100000000)
+		if (r->base >= 0x100000000ULL)
 			continue;
 
 		/*
@@ -604,50 +630,33 @@ mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end)
 	}
 
 	*start = s;
-	*end = 0x100000000;
+	*end = 0x100000000ULL;
 }
 
+/*
+ * This function fills in the mvebu_mbus_dram_info_nooverlap data
+ * structure, by looking at the mvebu_mbus_dram_info data, and
+ * removing the parts of it that overlap with I/O windows.
+ */
 static void __init
-mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
+mvebu_mbus_setup_cpu_target_nooverlap(struct mvebu_mbus_state *mbus)
 {
-	int i;
-	int cs;
 	uint64_t mbus_bridge_base, mbus_bridge_end;
-
-	mvebu_mbus_dram_info.mbus_dram_target_id = TARGET_DDR;
+	int cs_nooverlap = 0;
+	int i;
 
 	mvebu_mbus_find_bridge_hole(&mbus_bridge_base, &mbus_bridge_end);
 
-	for (i = 0, cs = 0; i < 4; i++) {
-		u64 base = readl(mbus->sdramwins_base + DDR_BASE_CS_OFF(i));
-		u64 size = readl(mbus->sdramwins_base + DDR_SIZE_CS_OFF(i));
-		u64 end;
+	for (i = 0; i < mvebu_mbus_dram_info.num_cs; i++) {
 		struct mbus_dram_window *w;
+		u64 base, size, end;
 
-		/* Ignore entries that are not enabled */
-		if (!(size & DDR_SIZE_ENABLED))
-			continue;
-
-		/*
-		 * Ignore entries whose base address is above 2^32,
-		 * since devices cannot DMA to such high addresses
-		 */
-		if (base & DDR_BASE_CS_HIGH_MASK)
-			continue;
-
-		base = base & DDR_BASE_CS_LOW_MASK;
-		size = (size | ~DDR_SIZE_MASK) + 1;
+		w = &mvebu_mbus_dram_info.cs[i];
+		base = w->base;
+		size = w->size;
 		end = base + size;
 
 		/*
-		 * Adjust base/size of the current CS to make sure it
-		 * doesn't overlap with the MBus bridge hole. This is
-		 * particularly important for devices that do DMA from
-		 * DRAM to a SRAM mapped in a MBus window, such as the
-		 * CESA cryptographic engine.
-		 */
-
-		/*
 		 * The CS is fully enclosed inside the MBus bridge
 		 * area, so ignore it.
 		 */
@@ -670,7 +679,7 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
 		if (base < mbus_bridge_base && end > mbus_bridge_base)
 			size -= end - mbus_bridge_base;
 
-		w = &mvebu_mbus_dram_info.cs[cs++];
+		w = &mvebu_mbus_dram_info_nooverlap.cs[cs_nooverlap++];
 		w->cs_index = i;
 		w->mbus_attr = 0xf & ~(1 << i);
 		if (mbus->hw_io_coherency)
@@ -678,6 +687,42 @@ mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
 		w->base = base;
 		w->size = size;
 	}
+
+	mvebu_mbus_dram_info_nooverlap.mbus_dram_target_id = TARGET_DDR;
+	mvebu_mbus_dram_info_nooverlap.num_cs = cs_nooverlap;
+}
+
+static void __init
+mvebu_mbus_default_setup_cpu_target(struct mvebu_mbus_state *mbus)
+{
+	int i;
+	int cs;
+
+	mvebu_mbus_dram_info.mbus_dram_target_id = TARGET_DDR;
+
+	for (i = 0, cs = 0; i < 4; i++) {
+		u32 base = readl(mbus->sdramwins_base + DDR_BASE_CS_OFF(i));
+		u32 size = readl(mbus->sdramwins_base + DDR_SIZE_CS_OFF(i));
+
+		/*
+		 * We only take care of entries for which the chip
+		 * select is enabled, and that don't have high base
+		 * address bits set (devices can only access the first
+		 * 32 bits of the memory).
+		 */
+		if ((size & DDR_SIZE_ENABLED) &&
+		    !(base & DDR_BASE_CS_HIGH_MASK)) {
+			struct mbus_dram_window *w;
+
+			w = &mvebu_mbus_dram_info.cs[cs++];
+			w->cs_index = i;
+			w->mbus_attr = 0xf & ~(1 << i);
+			if (mbus->hw_io_coherency)
+				w->mbus_attr |= ATTR_HW_COHERENCY;
+			w->base = base & DDR_BASE_CS_LOW_MASK;
+			w->size = (size | ~DDR_SIZE_MASK) + 1;
+		}
+	}
 	mvebu_mbus_dram_info.num_cs = cs;
 }
 
@@ -1035,6 +1080,7 @@ static int __init mvebu_mbus_common_init(struct mvebu_mbus_state *mbus,
 		mvebu_mbus_disable_window(mbus, win);
 
 	mbus->soc->setup_cpu_target(mbus);
+	mvebu_mbus_setup_cpu_target_nooverlap(mbus);
 
 	if (is_coherent)
 		writel(UNIT_SYNC_BARRIER_ALL,
diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c
index 11f7982cbdb3..5012e3ad1225 100644
--- a/drivers/bus/omap_l3_noc.c
+++ b/drivers/bus/omap_l3_noc.c
@@ -1,7 +1,7 @@
 /*
  * OMAP L3 Interconnect error handling driver
  *
- * Copyright (C) 2011-2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011-2015 Texas Instruments Incorporated - http://www.ti.com/
  *	Santosh Shilimkar <santosh.shilimkar@ti.com>
  *	Sricharan <r.sricharan@ti.com>
  *
@@ -233,7 +233,8 @@ static irqreturn_t l3_interrupt_handler(int irq, void *_l3)
 }
 
 static const struct of_device_id l3_noc_match[] = {
-	{.compatible = "ti,omap4-l3-noc", .data = &omap_l3_data},
+	{.compatible = "ti,omap4-l3-noc", .data = &omap4_l3_data},
+	{.compatible = "ti,omap5-l3-noc", .data = &omap5_l3_data},
 	{.compatible = "ti,dra7-l3-noc", .data = &dra_l3_data},
 	{.compatible = "ti,am4372-l3-noc", .data = &am4372_l3_data},
 	{},
@@ -300,7 +301,7 @@ static int omap_l3_probe(struct platform_device *pdev)
 	return ret;
 }
 
-#ifdef	CONFIG_PM
+#ifdef	CONFIG_PM_SLEEP
 
 /**
  * l3_resume_noirq() - resume function for l3_noc
@@ -346,7 +347,7 @@ static int l3_resume_noirq(struct device *dev)
 }
 
 static const struct dev_pm_ops l3_dev_pm_ops = {
-	.resume_noirq		= l3_resume_noirq,
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(NULL, l3_resume_noirq)
 };
 
 #define L3_DEV_PM_OPS (&l3_dev_pm_ops)
diff --git a/drivers/bus/omap_l3_noc.h b/drivers/bus/omap_l3_noc.h
index 95254585db86..73431f81da28 100644
--- a/drivers/bus/omap_l3_noc.h
+++ b/drivers/bus/omap_l3_noc.h
@@ -1,7 +1,7 @@
 /*
  * OMAP L3 Interconnect  error handling driver header
  *
- * Copyright (C) 2011-2014 Texas Instruments Incorporated - http://www.ti.com/
+ * Copyright (C) 2011-2015 Texas Instruments Incorporated - http://www.ti.com/
  *	Santosh Shilimkar <santosh.shilimkar@ti.com>
  *	sricharan <r.sricharan@ti.com>
  *
@@ -175,16 +175,14 @@ static struct l3_flagmux_data omap_l3_flagmux_clk2 = {
 };
 
 
-static struct l3_target_data omap_l3_target_data_clk3[] = {
-	{0x0100, "EMUSS",},
-	{0x0300, "DEBUG SOURCE",},
-	{0x0,	"HOST CLK3",},
+static struct l3_target_data omap4_l3_target_data_clk3[] = {
+	{0x0100, "DEBUGSS",},
 };
 
-static struct l3_flagmux_data omap_l3_flagmux_clk3 = {
+static struct l3_flagmux_data omap4_l3_flagmux_clk3 = {
 	.offset = 0x0200,
-	.l3_targ = omap_l3_target_data_clk3,
-	.num_targ_data = ARRAY_SIZE(omap_l3_target_data_clk3),
+	.l3_targ = omap4_l3_target_data_clk3,
+	.num_targ_data = ARRAY_SIZE(omap4_l3_target_data_clk3),
 };
 
 static struct l3_masters_data omap_l3_masters[] = {
@@ -215,21 +213,49 @@ static struct l3_masters_data omap_l3_masters[] = {
 	{ 0x32, "USBHOSTFS"}
 };
 
-static struct l3_flagmux_data *omap_l3_flagmux[] = {
+static struct l3_flagmux_data *omap4_l3_flagmux[] = {
 	&omap_l3_flagmux_clk1,
 	&omap_l3_flagmux_clk2,
-	&omap_l3_flagmux_clk3,
+	&omap4_l3_flagmux_clk3,
 };
 
-static const struct omap_l3 omap_l3_data = {
-	.l3_flagmux = omap_l3_flagmux,
-	.num_modules = ARRAY_SIZE(omap_l3_flagmux),
+static const struct omap_l3 omap4_l3_data = {
+	.l3_flagmux = omap4_l3_flagmux,
+	.num_modules = ARRAY_SIZE(omap4_l3_flagmux),
 	.l3_masters = omap_l3_masters,
 	.num_masters = ARRAY_SIZE(omap_l3_masters),
 	/* The 6 MSBs of register field used to distinguish initiator */
 	.mst_addr_mask = 0xFC,
 };
 
+/* OMAP5 data */
+static struct l3_target_data omap5_l3_target_data_clk3[] = {
+	{0x0100, "L3INSTR",},
+	{0x0300, "DEBUGSS",},
+	{0x0,	 "HOSTCLK3",},
+};
+
+static struct l3_flagmux_data omap5_l3_flagmux_clk3 = {
+	.offset = 0x0200,
+	.l3_targ = omap5_l3_target_data_clk3,
+	.num_targ_data = ARRAY_SIZE(omap5_l3_target_data_clk3),
+};
+
+static struct l3_flagmux_data *omap5_l3_flagmux[] = {
+	&omap_l3_flagmux_clk1,
+	&omap_l3_flagmux_clk2,
+	&omap5_l3_flagmux_clk3,
+};
+
+static const struct omap_l3 omap5_l3_data = {
+	.l3_flagmux = omap5_l3_flagmux,
+	.num_modules = ARRAY_SIZE(omap5_l3_flagmux),
+	.l3_masters = omap_l3_masters,
+	.num_masters = ARRAY_SIZE(omap_l3_masters),
+	/* The 6 MSBs of register field used to distinguish initiator */
+	.mst_addr_mask = 0x7E0,
+};
+
 /* DRA7 data */
 static struct l3_target_data dra_l3_target_data_clk1[] = {
 	{0x2a00, "AES1",},
@@ -274,7 +300,7 @@ static struct l3_flagmux_data dra_l3_flagmux_clk1 = {
 
 static struct l3_target_data dra_l3_target_data_clk2[] = {
 	{0x0,	"HOST CLK1",},
-	{0x0,	"HOST CLK2",},
+	{0x800000, "HOST CLK2",},
 	{0xdead, L3_TARGET_NOT_SUPPORTED,},
 	{0x3400, "SHA2_2",},
 	{0x0900, "BB2D",},
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index a3bebef255ad..0c98a9d51a24 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -33,7 +33,7 @@
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 
 
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index 9bb592872532..bf75f6361773 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -2000,7 +2000,7 @@ static int smi_ipmb_proc_show(struct seq_file *m, void *v)
 		seq_printf(m, " %x", intf->channels[i].address);
 	seq_putc(m, '\n');
 
-	return seq_has_overflowed(m);
+	return 0;
 }
 
 static int smi_ipmb_proc_open(struct inode *inode, struct file *file)
@@ -2023,7 +2023,7 @@ static int smi_version_proc_show(struct seq_file *m, void *v)
 		   ipmi_version_major(&intf->bmc->id),
 		   ipmi_version_minor(&intf->bmc->id));
 
-	return seq_has_overflowed(m);
+	return 0;
 }
 
 static int smi_version_proc_open(struct inode *inode, struct file *file)
diff --git a/drivers/char/ipmi/ipmi_powernv.c b/drivers/char/ipmi/ipmi_powernv.c
index 8753b0f6a317..9b409c0f14f7 100644
--- a/drivers/char/ipmi/ipmi_powernv.c
+++ b/drivers/char/ipmi/ipmi_powernv.c
@@ -15,6 +15,8 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/interrupt.h>
 
 #include <asm/opal.h>
 
@@ -23,8 +25,7 @@ struct ipmi_smi_powernv {
 	u64			interface_id;
 	struct ipmi_device_id	ipmi_id;
 	ipmi_smi_t		intf;
-	u64			event;
-	struct notifier_block	event_nb;
+	unsigned int		irq;
 
 	/**
 	 * We assume that there can only be one outstanding request, so
@@ -197,15 +198,12 @@ static struct ipmi_smi_handlers ipmi_powernv_smi_handlers = {
 	.poll			= ipmi_powernv_poll,
 };
 
-static int ipmi_opal_event(struct notifier_block *nb,
-			  unsigned long events, void *change)
+static irqreturn_t ipmi_opal_event(int irq, void *data)
 {
-	struct ipmi_smi_powernv *smi = container_of(nb,
-					struct ipmi_smi_powernv, event_nb);
+	struct ipmi_smi_powernv *smi = data;
 
-	if (events & smi->event)
-		ipmi_powernv_recv(smi);
-	return 0;
+	ipmi_powernv_recv(smi);
+	return IRQ_HANDLED;
 }
 
 static int ipmi_powernv_probe(struct platform_device *pdev)
@@ -240,13 +238,16 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 		goto err_free;
 	}
 
-	ipmi->event = 1ull << prop;
-	ipmi->event_nb.notifier_call = ipmi_opal_event;
+	ipmi->irq = irq_of_parse_and_map(dev->of_node, 0);
+	if (!ipmi->irq) {
+		dev_info(dev, "Unable to map irq from device tree\n");
+		ipmi->irq = opal_event_request(prop);
+	}
 
-	rc = opal_notifier_register(&ipmi->event_nb);
-	if (rc) {
-		dev_warn(dev, "OPAL notifier registration failed (%d)\n", rc);
-		goto err_free;
+	if (request_irq(ipmi->irq, ipmi_opal_event, IRQ_TYPE_LEVEL_HIGH,
+				"opal-ipmi", ipmi)) {
+		dev_warn(dev, "Unable to request irq\n");
+		goto err_dispose;
 	}
 
 	ipmi->opal_msg = devm_kmalloc(dev,
@@ -271,7 +272,9 @@ static int ipmi_powernv_probe(struct platform_device *pdev)
 err_free_msg:
 	devm_kfree(dev, ipmi->opal_msg);
 err_unregister:
-	opal_notifier_unregister(&ipmi->event_nb);
+	free_irq(ipmi->irq, ipmi);
+err_dispose:
+	irq_dispose_mapping(ipmi->irq);
 err_free:
 	devm_kfree(dev, ipmi);
 	return rc;
@@ -282,7 +285,9 @@ static int ipmi_powernv_remove(struct platform_device *pdev)
 	struct ipmi_smi_powernv *smi = dev_get_drvdata(&pdev->dev);
 
 	ipmi_unregister_smi(smi->intf);
-	opal_notifier_unregister(&smi->event_nb);
+	free_irq(smi->irq, smi);
+	irq_dispose_mapping(smi->irq);
+
 	return 0;
 }
 
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 5e90a18afbaf..8a45e92ff60c 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -942,8 +942,7 @@ static void sender(void                *send_info,
 		 * If we are running to completion, start it and run
 		 * transactions until everything is clear.
 		 */
-		smi_info->curr_msg = msg;
-		smi_info->waiting_msg = NULL;
+		smi_info->waiting_msg = msg;
 
 		/*
 		 * Run to completion means we are single-threaded, no
@@ -2244,7 +2243,7 @@ static int ipmi_pnp_probe(struct pnp_dev *dev,
 	acpi_handle handle;
 	acpi_status status;
 	unsigned long long tmp;
-	int rv;
+	int rv = -EINVAL;
 
 	acpi_dev = pnp_acpi_device(dev);
 	if (!acpi_dev)
@@ -2262,8 +2261,10 @@ static int ipmi_pnp_probe(struct pnp_dev *dev,
 
 	/* _IFT tells us the interface type: KCS, BT, etc */
 	status = acpi_evaluate_integer(handle, "_IFT", NULL, &tmp);
-	if (ACPI_FAILURE(status))
+	if (ACPI_FAILURE(status)) {
+		dev_err(&dev->dev, "Could not find ACPI IPMI interface type\n");
 		goto err_free;
+	}
 
 	switch (tmp) {
 	case 1:
@@ -2276,6 +2277,7 @@ static int ipmi_pnp_probe(struct pnp_dev *dev,
 		info->si_type = SI_BT;
 		break;
 	case 4: /* SSIF, just ignore */
+		rv = -ENODEV;
 		goto err_free;
 	default:
 		dev_info(&dev->dev, "unknown IPMI type %lld\n", tmp);
@@ -2336,7 +2338,7 @@ static int ipmi_pnp_probe(struct pnp_dev *dev,
 
 err_free:
 	kfree(info);
-	return -EINVAL;
+	return rv;
 }
 
 static void ipmi_pnp_remove(struct pnp_dev *dev)
@@ -3080,7 +3082,7 @@ static int smi_type_proc_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "%s\n", si_to_str[smi->si_type]);
 
-	return seq_has_overflowed(m);
+	return 0;
 }
 
 static int smi_type_proc_open(struct inode *inode, struct file *file)
@@ -3153,7 +3155,7 @@ static int smi_params_proc_show(struct seq_file *m, void *v)
 		   smi->irq,
 		   smi->slave_addr);
 
-	return seq_has_overflowed(m);
+	return 0;
 }
 
 static int smi_params_proc_open(struct inode *inode, struct file *file)
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index f40e3bd2c69c..207689c444a8 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -31,7 +31,6 @@
  * interface into the I2C driver, I believe.
  */
 
-#include <linux/version.h>
 #if defined(MODVERSIONS)
 #include <linux/modversions.h>
 #endif
@@ -166,6 +165,9 @@ enum ssif_stat_indexes {
 	/* Number of watchdog pretimeouts. */
 	SSIF_STAT_watchdog_pretimeouts,
 
+	/* Number of alers received. */
+	SSIF_STAT_alerts,
+
 	/* Always add statistics before this value, it must be last. */
 	SSIF_NUM_STATS
 };
@@ -214,7 +216,16 @@ struct ssif_info {
 #define WDT_PRE_TIMEOUT_INT	0x08
 	unsigned char       msg_flags;
 
+	u8		    global_enables;
 	bool		    has_event_buffer;
+	bool		    supports_alert;
+
+	/*
+	 * Used to tell what we should do with alerts.  If we are
+	 * waiting on a response, read the data immediately.
+	 */
+	bool		    got_alert;
+	bool		    waiting_alert;
 
 	/*
 	 * If set to true, this will request events the next time the
@@ -478,13 +489,13 @@ static int ipmi_ssif_thread(void *data)
 
 		if (ssif_info->i2c_read_write == I2C_SMBUS_WRITE) {
 			result = i2c_smbus_write_block_data(
-				ssif_info->client, SSIF_IPMI_REQUEST,
+				ssif_info->client, ssif_info->i2c_command,
 				ssif_info->i2c_data[0],
 				ssif_info->i2c_data + 1);
 			ssif_info->done_handler(ssif_info, result, NULL, 0);
 		} else {
 			result = i2c_smbus_read_block_data(
-				ssif_info->client, SSIF_IPMI_RESPONSE,
+				ssif_info->client, ssif_info->i2c_command,
 				ssif_info->i2c_data);
 			if (result < 0)
 				ssif_info->done_handler(ssif_info, result,
@@ -518,15 +529,12 @@ static int ssif_i2c_send(struct ssif_info *ssif_info,
 static void msg_done_handler(struct ssif_info *ssif_info, int result,
 			     unsigned char *data, unsigned int len);
 
-static void retry_timeout(unsigned long data)
+static void start_get(struct ssif_info *ssif_info)
 {
-	struct ssif_info *ssif_info = (void *) data;
 	int rv;
 
-	if (ssif_info->stopping)
-		return;
-
 	ssif_info->rtc_us_timer = 0;
+	ssif_info->multi_pos = 0;
 
 	rv = ssif_i2c_send(ssif_info, msg_done_handler, I2C_SMBUS_READ,
 			  SSIF_IPMI_RESPONSE,
@@ -540,6 +548,46 @@ static void retry_timeout(unsigned long data)
 	}
 }
 
+static void retry_timeout(unsigned long data)
+{
+	struct ssif_info *ssif_info = (void *) data;
+	unsigned long oflags, *flags;
+	bool waiting;
+
+	if (ssif_info->stopping)
+		return;
+
+	flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
+	waiting = ssif_info->waiting_alert;
+	ssif_info->waiting_alert = false;
+	ipmi_ssif_unlock_cond(ssif_info, flags);
+
+	if (waiting)
+		start_get(ssif_info);
+}
+
+
+static void ssif_alert(struct i2c_client *client, unsigned int data)
+{
+	struct ssif_info *ssif_info = i2c_get_clientdata(client);
+	unsigned long oflags, *flags;
+	bool do_get = false;
+
+	ssif_inc_stat(ssif_info, alerts);
+
+	flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
+	if (ssif_info->waiting_alert) {
+		ssif_info->waiting_alert = false;
+		del_timer(&ssif_info->retry_timer);
+		do_get = true;
+	} else if (ssif_info->curr_msg) {
+		ssif_info->got_alert = true;
+	}
+	ipmi_ssif_unlock_cond(ssif_info, flags);
+	if (do_get)
+		start_get(ssif_info);
+}
+
 static int start_resend(struct ssif_info *ssif_info);
 
 static void msg_done_handler(struct ssif_info *ssif_info, int result,
@@ -559,9 +607,12 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 		if (ssif_info->retries_left > 0) {
 			ssif_inc_stat(ssif_info, receive_retries);
 
+			flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
+			ssif_info->waiting_alert = true;
+			ssif_info->rtc_us_timer = SSIF_MSG_USEC;
 			mod_timer(&ssif_info->retry_timer,
 				  jiffies + SSIF_MSG_JIFFIES);
-			ssif_info->rtc_us_timer = SSIF_MSG_USEC;
+			ipmi_ssif_unlock_cond(ssif_info, flags);
 			return;
 		}
 
@@ -581,9 +632,9 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 		ssif_inc_stat(ssif_info, received_message_parts);
 
 		/* Remove the multi-part read marker. */
-		for (i = 0; i < (len-2); i++)
-			ssif_info->data[i] = data[i+2];
 		len -= 2;
+		for (i = 0; i < len; i++)
+			ssif_info->data[i] = data[i+2];
 		ssif_info->multi_len = len;
 		ssif_info->multi_pos = 1;
 
@@ -610,9 +661,9 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 			goto continue_op;
 		}
 
-		blocknum = data[ssif_info->multi_len];
+		blocknum = data[0];
 
-		if (ssif_info->multi_len+len-1 > IPMI_MAX_MSG_LENGTH) {
+		if (ssif_info->multi_len + len - 1 > IPMI_MAX_MSG_LENGTH) {
 			/* Received message too big, abort the operation. */
 			result = -E2BIG;
 			if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
@@ -622,15 +673,15 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 		}
 
 		/* Remove the blocknum from the data. */
-		for (i = 0; i < (len-1); i++)
-			ssif_info->data[i+ssif_info->multi_len] = data[i+1];
 		len--;
+		for (i = 0; i < len; i++)
+			ssif_info->data[i + ssif_info->multi_len] = data[i + 1];
 		ssif_info->multi_len += len;
 		if (blocknum == 0xff) {
 			/* End of read */
 			len = ssif_info->multi_len;
 			data = ssif_info->data;
-		} else if ((blocknum+1) != ssif_info->multi_pos) {
+		} else if (blocknum + 1 != ssif_info->multi_pos) {
 			/*
 			 * Out of sequence block, just abort.  Block
 			 * numbers start at zero for the second block,
@@ -650,7 +701,7 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 			if (rv < 0) {
 				if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
 					pr_info(PFX
-						"Error from i2c_non_blocking_op(2)\n");
+						"Error from ssif_i2c_send\n");
 
 				result = -EIO;
 			} else
@@ -830,7 +881,11 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 	}
 
 	if (ssif_info->multi_data) {
-		/* In the middle of a multi-data write. */
+		/*
+		 * In the middle of a multi-data write.  See the comment
+		 * in the SSIF_MULTI_n_PART case in the probe function
+		 * for details on the intricacies of this.
+		 */
 		int left;
 
 		ssif_inc_stat(ssif_info, sent_messages_parts);
@@ -864,15 +919,32 @@ static void msg_written_handler(struct ssif_info *ssif_info, int result,
 			msg_done_handler(ssif_info, -EIO, NULL, 0);
 		}
 	} else {
+		unsigned long oflags, *flags;
+		bool got_alert;
+
 		ssif_inc_stat(ssif_info, sent_messages);
 		ssif_inc_stat(ssif_info, sent_messages_parts);
 
-		/* Wait a jiffie then request the next message */
-		ssif_info->retries_left = SSIF_RECV_RETRIES;
-		ssif_info->rtc_us_timer = SSIF_MSG_PART_USEC;
-		mod_timer(&ssif_info->retry_timer,
-			  jiffies + SSIF_MSG_PART_JIFFIES);
-		return;
+		flags = ipmi_ssif_lock_cond(ssif_info, &oflags);
+		got_alert = ssif_info->got_alert;
+		if (got_alert) {
+			ssif_info->got_alert = false;
+			ssif_info->waiting_alert = false;
+		}
+
+		if (got_alert) {
+			ipmi_ssif_unlock_cond(ssif_info, flags);
+			/* The alert already happened, try now. */
+			retry_timeout((unsigned long) ssif_info);
+		} else {
+			/* Wait a jiffie then request the next message */
+			ssif_info->waiting_alert = true;
+			ssif_info->retries_left = SSIF_RECV_RETRIES;
+			ssif_info->rtc_us_timer = SSIF_MSG_PART_USEC;
+			mod_timer(&ssif_info->retry_timer,
+				  jiffies + SSIF_MSG_PART_JIFFIES);
+			ipmi_ssif_unlock_cond(ssif_info, flags);
+		}
 	}
 }
 
@@ -881,6 +953,8 @@ static int start_resend(struct ssif_info *ssif_info)
 	int rv;
 	int command;
 
+	ssif_info->got_alert = false;
+
 	if (ssif_info->data_len > 32) {
 		command = SSIF_IPMI_MULTI_PART_REQUEST_START;
 		ssif_info->multi_data = ssif_info->data;
@@ -915,7 +989,7 @@ static int start_send(struct ssif_info *ssif_info,
 		return -E2BIG;
 
 	ssif_info->retries_left = SSIF_SEND_RETRIES;
-	memcpy(ssif_info->data+1, data, len);
+	memcpy(ssif_info->data + 1, data, len);
 	ssif_info->data_len = len;
 	return start_resend(ssif_info);
 }
@@ -1200,7 +1274,7 @@ static int smi_type_proc_show(struct seq_file *m, void *v)
 {
 	seq_puts(m, "ssif\n");
 
-	return seq_has_overflowed(m);
+	return 0;
 }
 
 static int smi_type_proc_open(struct inode *inode, struct file *file)
@@ -1243,6 +1317,8 @@ static int smi_stats_proc_show(struct seq_file *m, void *v)
 		   ssif_get_stat(ssif_info, events));
 	seq_printf(m, "watchdog_pretimeouts:   %u\n",
 		   ssif_get_stat(ssif_info, watchdog_pretimeouts));
+	seq_printf(m, "alerts:                 %u\n",
+		   ssif_get_stat(ssif_info, alerts));
 	return 0;
 }
 
@@ -1258,6 +1334,23 @@ static const struct file_operations smi_stats_proc_ops = {
 	.release	= single_release,
 };
 
+static int strcmp_nospace(char *s1, char *s2)
+{
+	while (*s1 && *s2) {
+		while (isspace(*s1))
+			s1++;
+		while (isspace(*s2))
+			s2++;
+		if (*s1 > *s2)
+			return 1;
+		if (*s1 < *s2)
+			return -1;
+		s1++;
+		s2++;
+	}
+	return 0;
+}
+
 static struct ssif_addr_info *ssif_info_find(unsigned short addr,
 					     char *adapter_name,
 					     bool match_null_name)
@@ -1272,8 +1365,10 @@ restart:
 					/* One is NULL and one is not */
 					continue;
 				}
-				if (strcmp(info->adapter_name, adapter_name))
-					/* Names to not match */
+				if (adapter_name &&
+				    strcmp_nospace(info->adapter_name,
+						   adapter_name))
+					/* Names do not match */
 					continue;
 			}
 			found = info;
@@ -1306,6 +1401,12 @@ static bool check_acpi(struct ssif_info *ssif_info, struct device *dev)
 	return false;
 }
 
+/*
+ * Global enables we care about.
+ */
+#define GLOBAL_ENABLES_MASK (IPMI_BMC_EVT_MSG_BUFF | IPMI_BMC_RCV_MSG_INTR | \
+			     IPMI_BMC_EVT_MSG_INTR)
+
 static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
 	unsigned char     msg[3];
@@ -1391,13 +1492,33 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 			break;
 
 		case SSIF_MULTI_2_PART:
-			if (ssif_info->max_xmit_msg_size > 64)
-				ssif_info->max_xmit_msg_size = 64;
+			if (ssif_info->max_xmit_msg_size > 63)
+				ssif_info->max_xmit_msg_size = 63;
 			if (ssif_info->max_recv_msg_size > 62)
 				ssif_info->max_recv_msg_size = 62;
 			break;
 
 		case SSIF_MULTI_n_PART:
+			/*
+			 * The specification is rather confusing at
+			 * this point, but I think I understand what
+			 * is meant.  At least I have a workable
+			 * solution.  With multi-part messages, you
+			 * cannot send a message that is a multiple of
+			 * 32-bytes in length, because the start and
+			 * middle messages are 32-bytes and the end
+			 * message must be at least one byte.  You
+			 * can't fudge on an extra byte, that would
+			 * screw up things like fru data writes.  So
+			 * we limit the length to 63 bytes.  That way
+			 * a 32-byte message gets sent as a single
+			 * part.  A larger message will be a 32-byte
+			 * start and the next message is always going
+			 * to be 1-31 bytes in length.  Not ideal, but
+			 * it should work.
+			 */
+			if (ssif_info->max_xmit_msg_size > 63)
+				ssif_info->max_xmit_msg_size = 63;
 			break;
 
 		default:
@@ -1407,7 +1528,7 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	} else {
  no_support:
 		/* Assume no multi-part or PEC support */
-		pr_info(PFX "Error fetching SSIF: %d %d %2.2x, your system probably doesn't support this command so  using defaults\n",
+		pr_info(PFX "Error fetching SSIF: %d %d %2.2x, your system probably doesn't support this command so using defaults\n",
 		       rv, len, resp[2]);
 
 		ssif_info->max_xmit_msg_size = 32;
@@ -1436,6 +1557,8 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		goto found;
 	}
 
+	ssif_info->global_enables = resp[3];
+
 	if (resp[3] & IPMI_BMC_EVT_MSG_BUFF) {
 		ssif_info->has_event_buffer = true;
 		/* buffer is already enabled, nothing to do. */
@@ -1444,18 +1567,37 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD;
-	msg[2] = resp[3] | IPMI_BMC_EVT_MSG_BUFF;
+	msg[2] = ssif_info->global_enables | IPMI_BMC_EVT_MSG_BUFF;
 	rv = do_cmd(client, 3, msg, &len, resp);
 	if (rv || (len < 2)) {
-		pr_warn(PFX "Error getting global enables: %d %d %2.2x\n",
+		pr_warn(PFX "Error setting global enables: %d %d %2.2x\n",
 			rv, len, resp[2]);
 		rv = 0; /* Not fatal */
 		goto found;
 	}
 
-	if (resp[2] == 0)
+	if (resp[2] == 0) {
 		/* A successful return means the event buffer is supported. */
 		ssif_info->has_event_buffer = true;
+		ssif_info->global_enables |= IPMI_BMC_EVT_MSG_BUFF;
+	}
+
+	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
+	msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD;
+	msg[2] = ssif_info->global_enables | IPMI_BMC_RCV_MSG_INTR;
+	rv = do_cmd(client, 3, msg, &len, resp);
+	if (rv || (len < 2)) {
+		pr_warn(PFX "Error setting global enables: %d %d %2.2x\n",
+			rv, len, resp[2]);
+		rv = 0; /* Not fatal */
+		goto found;
+	}
+
+	if (resp[2] == 0) {
+		/* A successful return means the alert is supported. */
+		ssif_info->supports_alert = true;
+		ssif_info->global_enables |= IPMI_BMC_RCV_MSG_INTR;
+	}
 
  found:
 	ssif_info->intf_num = atomic_inc_return(&next_intf);
@@ -1813,6 +1955,7 @@ static struct i2c_driver ssif_i2c_driver = {
 	},
 	.probe		= ssif_probe,
 	.remove		= ssif_remove,
+	.alert		= ssif_alert,
 	.id_table	= ssif_id,
 	.detect		= ssif_detect
 };
@@ -1832,7 +1975,7 @@ static int init_ipmi_ssif(void)
 		rv = new_ssif_client(addr[i], adapter_name[i],
 				     dbg[i], slave_addrs[i],
 				     SI_HARDCODED);
-		if (!rv)
+		if (rv)
 			pr_err(PFX
 			       "Couldn't add hardcoded device at addr 0x%x\n",
 			       addr[i]);
diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c
index 8dd48a2be911..fc061f7c2bd1 100644
--- a/drivers/char/pcmcia/cm4040_cs.c
+++ b/drivers/char/pcmcia/cm4040_cs.c
@@ -532,9 +532,8 @@ static int reader_config(struct pcmcia_device *link, int devno)
 
 	fail_rc = pcmcia_enable_device(link);
 	if (fail_rc != 0) {
-		dev_printk(KERN_INFO, &link->dev,
-			   "pcmcia_enable_device failed 0x%x\n",
-			   fail_rc);
+		dev_info(&link->dev, "pcmcia_enable_device failed 0x%x\n",
+			 fail_rc);
 		goto cs_release;
 	}
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 9cd6968e2f92..d0da5d852d41 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -409,6 +409,9 @@ static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static DECLARE_WAIT_QUEUE_HEAD(urandom_init_wait);
 static struct fasync_struct *fasync;
 
+static DEFINE_SPINLOCK(random_ready_list_lock);
+static LIST_HEAD(random_ready_list);
+
 /**********************************************************************
  *
  * OS independent entropy store.   Here are the functions which handle
@@ -589,6 +592,22 @@ static void fast_mix(struct fast_pool *f)
 	f->count++;
 }
 
+static void process_random_ready_list(void)
+{
+	unsigned long flags;
+	struct random_ready_callback *rdy, *tmp;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	list_for_each_entry_safe(rdy, tmp, &random_ready_list, list) {
+		struct module *owner = rdy->owner;
+
+		list_del_init(&rdy->list);
+		rdy->func(rdy);
+		module_put(owner);
+	}
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+}
+
 /*
  * Credit (or debit) the entropy store with n bits of entropy.
  * Use credit_entropy_bits_safe() if the value comes from userspace
@@ -660,7 +679,8 @@ retry:
 		r->entropy_total = 0;
 		if (r == &nonblocking_pool) {
 			prandom_reseed_late();
-			wake_up_interruptible(&urandom_init_wait);
+			process_random_ready_list();
+			wake_up_all(&urandom_init_wait);
 			pr_notice("random: %s pool is initialized\n", r->name);
 		}
 	}
@@ -1245,6 +1265,64 @@ void get_random_bytes(void *buf, int nbytes)
 EXPORT_SYMBOL(get_random_bytes);
 
 /*
+ * Add a callback function that will be invoked when the nonblocking
+ * pool is initialised.
+ *
+ * returns: 0 if callback is successfully added
+ *	    -EALREADY if pool is already initialised (callback not called)
+ *	    -ENOENT if module for callback is not alive
+ */
+int add_random_ready_callback(struct random_ready_callback *rdy)
+{
+	struct module *owner;
+	unsigned long flags;
+	int err = -EALREADY;
+
+	if (likely(nonblocking_pool.initialized))
+		return err;
+
+	owner = rdy->owner;
+	if (!try_module_get(owner))
+		return -ENOENT;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	if (nonblocking_pool.initialized)
+		goto out;
+
+	owner = NULL;
+
+	list_add(&rdy->list, &random_ready_list);
+	err = 0;
+
+out:
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+
+	module_put(owner);
+
+	return err;
+}
+EXPORT_SYMBOL(add_random_ready_callback);
+
+/*
+ * Delete a previously registered readiness callback function.
+ */
+void del_random_ready_callback(struct random_ready_callback *rdy)
+{
+	unsigned long flags;
+	struct module *owner = NULL;
+
+	spin_lock_irqsave(&random_ready_list_lock, flags);
+	if (!list_empty(&rdy->list)) {
+		list_del_init(&rdy->list);
+		owner = rdy->owner;
+	}
+	spin_unlock_irqrestore(&random_ready_list_lock, flags);
+
+	module_put(owner);
+}
+EXPORT_SYMBOL(del_random_ready_callback);
+
+/*
  * This function will use the architecture-specific hardware random
  * number generator if it is available.  The arch-specific hw RNG will
  * almost certainly be faster than what we can do in software, but it
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 3d00c25382c5..9df871d53c6e 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -73,3 +73,4 @@ obj-$(CONFIG_ARCH_U8500)		+= ux500/
 obj-$(CONFIG_COMMON_CLK_VERSATILE)	+= versatile/
 obj-$(CONFIG_X86)			+= x86/
 obj-$(CONFIG_ARCH_ZYNQ)			+= zynq/
+obj-$(CONFIG_H8300)		+= h8300/
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index 597fed423d7d..df2c1afa52b4 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -29,7 +29,7 @@
 #define PERIPHERAL_RSHIFT_MASK	0x3
 #define PERIPHERAL_RSHIFT(val)	(((val) >> 16) & PERIPHERAL_RSHIFT_MASK)
 
-#define PERIPHERAL_MAX_SHIFT	4
+#define PERIPHERAL_MAX_SHIFT	3
 
 struct clk_peripheral {
 	struct clk_hw hw;
@@ -242,7 +242,7 @@ static long clk_sam9x5_peripheral_round_rate(struct clk_hw *hw,
 		return *parent_rate;
 
 	if (periph->range.max) {
-		for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+		for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 			cur_rate = *parent_rate >> shift;
 			if (cur_rate <= periph->range.max)
 				break;
@@ -254,7 +254,7 @@ static long clk_sam9x5_peripheral_round_rate(struct clk_hw *hw,
 
 	best_diff = cur_rate - rate;
 	best_rate = cur_rate;
-	for (; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+	for (; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 		cur_rate = *parent_rate >> shift;
 		if (cur_rate < rate)
 			cur_diff = rate - cur_rate;
@@ -289,7 +289,7 @@ static int clk_sam9x5_peripheral_set_rate(struct clk_hw *hw,
 	if (periph->range.max && rate > periph->range.max)
 		return -EINVAL;
 
-	for (shift = 0; shift < PERIPHERAL_MAX_SHIFT; shift++) {
+	for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) {
 		if (parent_rate >> shift == rate) {
 			periph->auto_div = false;
 			periph->div = shift;
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index 6ec79dbc0840..cbbe40377ad6 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -173,8 +173,7 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	int i = 0;
 
 	/* Check if parent_rate is a valid input rate */
-	if (parent_rate < characteristics->input.min ||
-	    parent_rate > characteristics->input.max)
+	if (parent_rate < characteristics->input.min)
 		return -ERANGE;
 
 	/*
@@ -187,6 +186,15 @@ static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
 	if (!mindiv)
 		mindiv = 1;
 
+	if (parent_rate > characteristics->input.max) {
+		tmpdiv = DIV_ROUND_UP(parent_rate, characteristics->input.max);
+		if (tmpdiv > PLL_DIV_MAX)
+			return -ERANGE;
+
+		if (tmpdiv > mindiv)
+			mindiv = tmpdiv;
+	}
+
 	/*
 	 * Calculate the maximum divider which is limited by PLL register
 	 * layout (limited by the MUL or DIV field size).
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 69abb08cf146..eb8e5dc9076d 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -121,7 +121,7 @@ extern void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 					       struct at91_pmc *pmc);
 #endif
 
-#if defined(CONFIG_HAVE_AT91_SMD)
+#if defined(CONFIG_HAVE_AT91_H32MX)
 extern void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 					      struct at91_pmc *pmc);
 #endif
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index bfa1e64e267d..9b13a303d3f8 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -242,14 +242,12 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 			goto err_reg;
 		}
 
-		s2mps11_clk->lookup = clkdev_alloc(s2mps11_clk->clk,
+		s2mps11_clk->lookup = clkdev_create(s2mps11_clk->clk,
 					s2mps11_name(s2mps11_clk), NULL);
 		if (!s2mps11_clk->lookup) {
 			ret = -ENOMEM;
 			goto err_lup;
 		}
-
-		clkdev_add(s2mps11_clk->lookup);
 	}
 
 	for (i = 0; i < S2MPS11_CLKS_NUM; i++) {
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 44ea107cfc67..30335d3b99af 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -1128,13 +1128,6 @@ static int si5351_dt_parse(struct i2c_client *client,
 	if (!pdata)
 		return -ENOMEM;
 
-	pdata->clk_xtal = of_clk_get(np, 0);
-	if (!IS_ERR(pdata->clk_xtal))
-		clk_put(pdata->clk_xtal);
-	pdata->clk_clkin = of_clk_get(np, 1);
-	if (!IS_ERR(pdata->clk_clkin))
-		clk_put(pdata->clk_clkin);
-
 	/*
 	 * property silabs,pll-source : <num src>, [<..>]
 	 * allow to selectively set pll source
@@ -1328,8 +1321,22 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	i2c_set_clientdata(client, drvdata);
 	drvdata->client = client;
 	drvdata->variant = variant;
-	drvdata->pxtal = pdata->clk_xtal;
-	drvdata->pclkin = pdata->clk_clkin;
+	drvdata->pxtal = devm_clk_get(&client->dev, "xtal");
+	drvdata->pclkin = devm_clk_get(&client->dev, "clkin");
+
+	if (PTR_ERR(drvdata->pxtal) == -EPROBE_DEFER ||
+	    PTR_ERR(drvdata->pclkin) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	/*
+	 * Check for valid parent clock: VARIANT_A and VARIANT_B need XTAL,
+	 *   VARIANT_C can have CLKIN instead.
+	 */
+	if (IS_ERR(drvdata->pxtal) &&
+	    (drvdata->variant != SI5351_VARIANT_C || IS_ERR(drvdata->pclkin))) {
+		dev_err(&client->dev, "missing parent clock\n");
+		return -EINVAL;
+	}
 
 	drvdata->regmap = devm_regmap_init_i2c(client, &si5351_regmap_config);
 	if (IS_ERR(drvdata->regmap)) {
@@ -1393,6 +1400,11 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		}
 	}
 
+	if (!IS_ERR(drvdata->pxtal))
+		clk_prepare_enable(drvdata->pxtal);
+	if (!IS_ERR(drvdata->pclkin))
+		clk_prepare_enable(drvdata->pclkin);
+
 	/* register xtal input clock gate */
 	memset(&init, 0, sizeof(init));
 	init.name = si5351_input_names[0];
@@ -1407,7 +1419,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	clk = devm_clk_register(&client->dev, &drvdata->xtal);
 	if (IS_ERR(clk)) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		return PTR_ERR(clk);
+		ret = PTR_ERR(clk);
+		goto err_clk;
 	}
 
 	/* register clkin input clock gate */
@@ -1425,7 +1438,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (IS_ERR(clk)) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			return PTR_ERR(clk);
+			ret = PTR_ERR(clk);
+			goto err_clk;
 		}
 	}
 
@@ -1447,7 +1461,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	clk = devm_clk_register(&client->dev, &drvdata->pll[0].hw);
 	if (IS_ERR(clk)) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		return -EINVAL;
+		ret = PTR_ERR(clk);
+		goto err_clk;
 	}
 
 	/* register PLLB or VXCO (Si5351B) */
@@ -1471,7 +1486,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 	clk = devm_clk_register(&client->dev, &drvdata->pll[1].hw);
 	if (IS_ERR(clk)) {
 		dev_err(&client->dev, "unable to register %s\n", init.name);
-		return -EINVAL;
+		ret = PTR_ERR(clk);
+		goto err_clk;
 	}
 
 	/* register clk multisync and clk out divider */
@@ -1492,8 +1508,10 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		num_clocks * sizeof(*drvdata->onecell.clks), GFP_KERNEL);
 
 	if (WARN_ON(!drvdata->msynth || !drvdata->clkout ||
-		    !drvdata->onecell.clks))
-		return -ENOMEM;
+		    !drvdata->onecell.clks)) {
+		ret = -ENOMEM;
+		goto err_clk;
+	}
 
 	for (n = 0; n < num_clocks; n++) {
 		drvdata->msynth[n].num = n;
@@ -1511,7 +1529,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (IS_ERR(clk)) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			return -EINVAL;
+			ret = PTR_ERR(clk);
+			goto err_clk;
 		}
 	}
 
@@ -1538,7 +1557,8 @@ static int si5351_i2c_probe(struct i2c_client *client,
 		if (IS_ERR(clk)) {
 			dev_err(&client->dev, "unable to register %s\n",
 				init.name);
-			return -EINVAL;
+			ret = PTR_ERR(clk);
+			goto err_clk;
 		}
 		drvdata->onecell.clks[n] = clk;
 
@@ -1557,10 +1577,17 @@ static int si5351_i2c_probe(struct i2c_client *client,
 				  &drvdata->onecell);
 	if (ret) {
 		dev_err(&client->dev, "unable to add clk provider\n");
-		return ret;
+		goto err_clk;
 	}
 
 	return 0;
+
+err_clk:
+	if (!IS_ERR(drvdata->pxtal))
+		clk_disable_unprepare(drvdata->pxtal);
+	if (!IS_ERR(drvdata->pclkin))
+		clk_disable_unprepare(drvdata->pclkin);
+	return ret;
 }
 
 static const struct i2c_device_id si5351_i2c_ids[] = {
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 459ce9da13e0..5b0f41868b42 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1475,8 +1475,10 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *clk,
 	 */
 	if (clk->prepare_count) {
 		clk_core_prepare(parent);
+		flags = clk_enable_lock();
 		clk_core_enable(parent);
 		clk_core_enable(clk);
+		clk_enable_unlock(flags);
 	}
 
 	/* update the clk tree topology */
@@ -1491,13 +1493,17 @@ static void __clk_set_parent_after(struct clk_core *core,
 				   struct clk_core *parent,
 				   struct clk_core *old_parent)
 {
+	unsigned long flags;
+
 	/*
 	 * Finish the migration of prepare state and undo the changes done
 	 * for preventing a race with clk_enable().
 	 */
 	if (core->prepare_count) {
+		flags = clk_enable_lock();
 		clk_core_disable(core);
 		clk_core_disable(old_parent);
+		clk_enable_unlock(flags);
 		clk_core_unprepare(old_parent);
 	}
 }
@@ -1525,8 +1531,10 @@ static int __clk_set_parent(struct clk_core *clk, struct clk_core *parent,
 		clk_enable_unlock(flags);
 
 		if (clk->prepare_count) {
+			flags = clk_enable_lock();
 			clk_core_disable(clk);
 			clk_core_disable(parent);
+			clk_enable_unlock(flags);
 			clk_core_unprepare(parent);
 		}
 		return ret;
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 1fcb6ef2cdac..c0eaf0973bd2 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -177,7 +177,7 @@ struct clk *clk_get_sys(const char *dev_id, const char *con_id)
 	if (!cl)
 		goto out;
 
-	clk = __clk_create_clk(__clk_get_hw(cl->clk), dev_id, con_id);
+	clk = __clk_create_clk(cl->clk_hw, dev_id, con_id);
 	if (IS_ERR(clk))
 		goto out;
 
@@ -215,18 +215,26 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_put);
 
-void clkdev_add(struct clk_lookup *cl)
+static void __clkdev_add(struct clk_lookup *cl)
 {
 	mutex_lock(&clocks_mutex);
 	list_add_tail(&cl->node, &clocks);
 	mutex_unlock(&clocks_mutex);
 }
+
+void clkdev_add(struct clk_lookup *cl)
+{
+	if (!cl->clk_hw)
+		cl->clk_hw = __clk_get_hw(cl->clk);
+	__clkdev_add(cl);
+}
 EXPORT_SYMBOL(clkdev_add);
 
-void __init clkdev_add_table(struct clk_lookup *cl, size_t num)
+void clkdev_add_table(struct clk_lookup *cl, size_t num)
 {
 	mutex_lock(&clocks_mutex);
 	while (num--) {
+		cl->clk_hw = __clk_get_hw(cl->clk);
 		list_add_tail(&cl->node, &clocks);
 		cl++;
 	}
@@ -243,7 +251,7 @@ struct clk_lookup_alloc {
 };
 
 static struct clk_lookup * __init_refok
-vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
+vclkdev_alloc(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
 	va_list ap)
 {
 	struct clk_lookup_alloc *cla;
@@ -252,7 +260,7 @@ vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
 	if (!cla)
 		return NULL;
 
-	cla->cl.clk = clk;
+	cla->cl.clk_hw = hw;
 	if (con_id) {
 		strlcpy(cla->con_id, con_id, sizeof(cla->con_id));
 		cla->cl.con_id = cla->con_id;
@@ -266,6 +274,19 @@ vclkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt,
 	return &cla->cl;
 }
 
+static struct clk_lookup *
+vclkdev_create(struct clk_hw *hw, const char *con_id, const char *dev_fmt,
+	va_list ap)
+{
+	struct clk_lookup *cl;
+
+	cl = vclkdev_alloc(hw, con_id, dev_fmt, ap);
+	if (cl)
+		__clkdev_add(cl);
+
+	return cl;
+}
+
 struct clk_lookup * __init_refok
 clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...)
 {
@@ -273,28 +294,49 @@ clkdev_alloc(struct clk *clk, const char *con_id, const char *dev_fmt, ...)
 	va_list ap;
 
 	va_start(ap, dev_fmt);
-	cl = vclkdev_alloc(clk, con_id, dev_fmt, ap);
+	cl = vclkdev_alloc(__clk_get_hw(clk), con_id, dev_fmt, ap);
 	va_end(ap);
 
 	return cl;
 }
 EXPORT_SYMBOL(clkdev_alloc);
 
-int clk_add_alias(const char *alias, const char *alias_dev_name, char *id,
-	struct device *dev)
+/**
+ * clkdev_create - allocate and add a clkdev lookup structure
+ * @clk: struct clk to associate with all clk_lookups
+ * @con_id: connection ID string on device
+ * @dev_fmt: format string describing device name
+ *
+ * Returns a clk_lookup structure, which can be later unregistered and
+ * freed.
+ */
+struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id,
+	const char *dev_fmt, ...)
 {
-	struct clk *r = clk_get(dev, id);
+	struct clk_lookup *cl;
+	va_list ap;
+
+	va_start(ap, dev_fmt);
+	cl = vclkdev_create(__clk_get_hw(clk), con_id, dev_fmt, ap);
+	va_end(ap);
+
+	return cl;
+}
+EXPORT_SYMBOL_GPL(clkdev_create);
+
+int clk_add_alias(const char *alias, const char *alias_dev_name,
+	const char *con_id, struct device *dev)
+{
+	struct clk *r = clk_get(dev, con_id);
 	struct clk_lookup *l;
 
 	if (IS_ERR(r))
 		return PTR_ERR(r);
 
-	l = clkdev_alloc(r, alias, alias_dev_name);
+	l = clkdev_create(r, alias, "%s", alias_dev_name);
 	clk_put(r);
-	if (!l)
-		return -ENODEV;
-	clkdev_add(l);
-	return 0;
+
+	return l ? 0 : -ENODEV;
 }
 EXPORT_SYMBOL(clk_add_alias);
 
@@ -334,15 +376,10 @@ int clk_register_clkdev(struct clk *clk, const char *con_id,
 		return PTR_ERR(clk);
 
 	va_start(ap, dev_fmt);
-	cl = vclkdev_alloc(clk, con_id, dev_fmt, ap);
+	cl = vclkdev_create(__clk_get_hw(clk), con_id, dev_fmt, ap);
 	va_end(ap);
 
-	if (!cl)
-		return -ENOMEM;
-
-	clkdev_add(cl);
-
-	return 0;
+	return cl ? 0 : -ENOMEM;
 }
 EXPORT_SYMBOL(clk_register_clkdev);
 
@@ -365,8 +402,8 @@ int clk_register_clkdevs(struct clk *clk, struct clk_lookup *cl, size_t num)
 		return PTR_ERR(clk);
 
 	for (i = 0; i < num; i++, cl++) {
-		cl->clk = clk;
-		clkdev_add(cl);
+		cl->clk_hw = __clk_get_hw(clk);
+		__clkdev_add(cl);
 	}
 
 	return 0;
diff --git a/drivers/clk/h8300/Makefile b/drivers/clk/h8300/Makefile
new file mode 100644
index 000000000000..b86427c31fca
--- /dev/null
+++ b/drivers/clk/h8300/Makefile
@@ -0,0 +1,2 @@
+obj-y += clk-div.o
+obj-$(CONFIG_H8S2678) += clk-h8s2678.o
diff --git a/drivers/clk/h8300/clk-div.c b/drivers/clk/h8300/clk-div.c
new file mode 100644
index 000000000000..56f9eba91b83
--- /dev/null
+++ b/drivers/clk/h8300/clk-div.c
@@ -0,0 +1,53 @@
+/*
+ * H8/300 divide clock driver
+ *
+ * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+static DEFINE_SPINLOCK(clklock);
+
+static void __init h8300_div_clk_setup(struct device_node *node)
+{
+	unsigned int num_parents;
+	struct clk *clk;
+	const char *clk_name = node->name;
+	const char *parent_name;
+	void __iomem *divcr = NULL;
+	int width;
+
+	num_parents = of_clk_get_parent_count(node);
+	if (num_parents < 1) {
+		pr_err("%s: no parent found", clk_name);
+		return;
+	}
+
+	divcr = of_iomap(node, 0);
+	if (divcr == NULL) {
+		pr_err("%s: failed to map divide register", clk_name);
+		goto error;
+	}
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	of_property_read_u32(node, "renesas,width", &width);
+	clk = clk_register_divider(NULL, clk_name, parent_name,
+				   CLK_SET_RATE_GATE, divcr, 0, width,
+				   CLK_DIVIDER_POWER_OF_TWO, &clklock);
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		return;
+	}
+	pr_err("%s: failed to register %s div clock (%ld)\n",
+	       __func__, clk_name, PTR_ERR(clk));
+error:
+	if (divcr)
+		iounmap(divcr);
+}
+
+CLK_OF_DECLARE(h8300_div_clk, "renesas,h8300-div-clock", h8300_div_clk_setup);
diff --git a/drivers/clk/h8300/clk-h8s2678.c b/drivers/clk/h8300/clk-h8s2678.c
new file mode 100644
index 000000000000..4701b093e497
--- /dev/null
+++ b/drivers/clk/h8300/clk-h8s2678.c
@@ -0,0 +1,146 @@
+/*
+ * H8S2678 clock driver
+ *
+ * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/device.h>
+#include <linux/of_address.h>
+
+static DEFINE_SPINLOCK(clklock);
+
+#define MAX_FREQ 33333333
+#define MIN_FREQ  8000000
+
+struct pll_clock {
+	struct clk_hw hw;
+	void __iomem *sckcr;
+	void __iomem *pllcr;
+};
+
+#define to_pll_clock(_hw) container_of(_hw, struct pll_clock, hw)
+
+static unsigned long pll_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct pll_clock *pll_clock = to_pll_clock(hw);
+	int mul = 1 << (ctrl_inb((unsigned long)pll_clock->pllcr) & 3);
+
+	return parent_rate * mul;
+}
+
+static long pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	int i, m = -1;
+	long offset[3];
+
+	if (rate > MAX_FREQ)
+		rate = MAX_FREQ;
+	if (rate < MIN_FREQ)
+		rate = MIN_FREQ;
+
+	for (i = 0; i < 3; i++)
+		offset[i] = abs(rate - (*prate * (1 << i)));
+	for (i = 0; i < 3; i++)
+		if (m < 0)
+			m = i;
+		else
+			m = (offset[i] < offset[m])?i:m;
+
+	return *prate * (1 << m);
+}
+
+static int pll_set_rate(struct clk_hw *hw, unsigned long rate,
+			unsigned long parent_rate)
+{
+	int pll;
+	unsigned char val;
+	unsigned long flags;
+	struct pll_clock *pll_clock = to_pll_clock(hw);
+
+	pll = ((rate / parent_rate) / 2) & 0x03;
+	spin_lock_irqsave(&clklock, flags);
+	val = ctrl_inb((unsigned long)pll_clock->sckcr);
+	val |= 0x08;
+	ctrl_outb(val, (unsigned long)pll_clock->sckcr);
+	val = ctrl_inb((unsigned long)pll_clock->pllcr);
+	val &= ~0x03;
+	val |= pll;
+	ctrl_outb(val, (unsigned long)pll_clock->pllcr);
+	spin_unlock_irqrestore(&clklock, flags);
+	return 0;
+}
+
+static const struct clk_ops pll_ops = {
+	.recalc_rate = pll_recalc_rate,
+	.round_rate = pll_round_rate,
+	.set_rate = pll_set_rate,
+};
+
+static void __init h8s2678_pll_clk_setup(struct device_node *node)
+{
+	unsigned int num_parents;
+	struct clk *clk;
+	const char *clk_name = node->name;
+	const char *parent_name;
+	struct pll_clock *pll_clock;
+	struct clk_init_data init;
+
+	num_parents = of_clk_get_parent_count(node);
+	if (num_parents < 1) {
+		pr_err("%s: no parent found", clk_name);
+		return;
+	}
+
+
+	pll_clock = kzalloc(sizeof(struct pll_clock), GFP_KERNEL);
+	if (!pll_clock) {
+		pr_err("%s: failed to alloc memory", clk_name);
+		return;
+	}
+
+	pll_clock->sckcr = of_iomap(node, 0);
+	if (pll_clock->sckcr == NULL) {
+		pr_err("%s: failed to map divide register", clk_name);
+		goto free_clock;
+	}
+
+	pll_clock->pllcr = of_iomap(node, 1);
+	if (pll_clock->pllcr == NULL) {
+		pr_err("%s: failed to map multiply register", clk_name);
+		goto unmap_sckcr;
+	}
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	init.name = clk_name;
+	init.ops = &pll_ops;
+	init.flags = CLK_IS_BASIC;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	pll_clock->hw.init = &init;
+
+	clk = clk_register(NULL, &pll_clock->hw);
+	if (IS_ERR(clk)) {
+		pr_err("%s: failed to register %s div clock (%ld)\n",
+		       __func__, clk_name, PTR_ERR(clk));
+		goto unmap_pllcr;
+	}
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	return;
+
+unmap_pllcr:
+	iounmap(pll_clock->pllcr);
+unmap_sckcr:
+	iounmap(pll_clock->sckcr);
+free_clock:
+	kfree(pll_clock);
+}
+
+CLK_OF_DECLARE(h8s2678_div_clk, "renesas,h8s2678-pll-clock",
+	       h8s2678_pll_clk_setup);
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index a50936a17376..563969942a1d 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -140,12 +140,47 @@ static struct clk_regmap pll14_vote = {
 	},
 };
 
+#define NSS_PLL_RATE(f, _l, _m, _n, i) \
+	{  \
+		.freq = f,  \
+		.l = _l, \
+		.m = _m, \
+		.n = _n, \
+		.ibits = i, \
+	}
+
+static struct pll_freq_tbl pll18_freq_tbl[] = {
+	NSS_PLL_RATE(550000000, 44, 0, 1, 0x01495625),
+	NSS_PLL_RATE(733000000, 58, 16, 25, 0x014b5625),
+};
+
+static struct clk_pll pll18 = {
+	.l_reg = 0x31a4,
+	.m_reg = 0x31a8,
+	.n_reg = 0x31ac,
+	.config_reg = 0x31b4,
+	.mode_reg = 0x31a0,
+	.status_reg = 0x31b8,
+	.status_bit = 16,
+	.post_div_shift = 16,
+	.post_div_width = 1,
+	.freq_tbl = pll18_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll18",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
 enum {
 	P_PXO,
 	P_PLL8,
 	P_PLL3,
 	P_PLL0,
 	P_CXO,
+	P_PLL14,
+	P_PLL18,
 };
 
 static const struct parent_map gcc_pxo_pll8_map[] = {
@@ -197,6 +232,22 @@ static const char *gcc_pxo_pll8_pll0_map[] = {
 	"pll0_vote",
 };
 
+static const struct parent_map gcc_pxo_pll8_pll14_pll18_pll0_map[] = {
+	{ P_PXO, 0 },
+	{ P_PLL8, 4 },
+	{ P_PLL0, 2 },
+	{ P_PLL14, 5 },
+	{ P_PLL18, 1 }
+};
+
+static const char *gcc_pxo_pll8_pll14_pll18_pll0[] = {
+	"pxo",
+	"pll8_vote",
+	"pll0_vote",
+	"pll14",
+	"pll18",
+};
+
 static struct freq_tbl clk_tbl_gsbi_uart[] = {
 	{  1843200, P_PLL8, 2,  6, 625 },
 	{  3686400, P_PLL8, 2, 12, 625 },
@@ -2202,6 +2253,472 @@ static struct clk_branch ebi2_aon_clk = {
 	},
 };
 
+static const struct freq_tbl clk_tbl_gmac[] = {
+	{ 133000000, P_PLL0, 1,  50, 301 },
+	{ 266000000, P_PLL0, 1, 127, 382 },
+	{ }
+};
+
+static struct clk_dyn_rcg gmac_core1_src = {
+	.ns_reg[0] = 0x3cac,
+	.ns_reg[1] = 0x3cb0,
+	.md_reg[0] = 0x3ca4,
+	.md_reg[1] = 0x3ca8,
+	.bank_reg = 0x3ca0,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_gmac,
+	.clkr = {
+		.enable_reg = 0x3ca0,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core1_src",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch gmac_core1_clk = {
+	.halt_reg = 0x3c20,
+	.halt_bit = 4,
+	.hwcg_reg = 0x3cb4,
+	.hwcg_bit = 6,
+	.clkr = {
+		.enable_reg = 0x3cb4,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core1_clk",
+			.parent_names = (const char *[]){
+				"gmac_core1_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_dyn_rcg gmac_core2_src = {
+	.ns_reg[0] = 0x3ccc,
+	.ns_reg[1] = 0x3cd0,
+	.md_reg[0] = 0x3cc4,
+	.md_reg[1] = 0x3cc8,
+	.bank_reg = 0x3ca0,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_gmac,
+	.clkr = {
+		.enable_reg = 0x3cc0,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core2_src",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch gmac_core2_clk = {
+	.halt_reg = 0x3c20,
+	.halt_bit = 5,
+	.hwcg_reg = 0x3cd4,
+	.hwcg_bit = 6,
+	.clkr = {
+		.enable_reg = 0x3cd4,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core2_clk",
+			.parent_names = (const char *[]){
+				"gmac_core2_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_dyn_rcg gmac_core3_src = {
+	.ns_reg[0] = 0x3cec,
+	.ns_reg[1] = 0x3cf0,
+	.md_reg[0] = 0x3ce4,
+	.md_reg[1] = 0x3ce8,
+	.bank_reg = 0x3ce0,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_gmac,
+	.clkr = {
+		.enable_reg = 0x3ce0,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core3_src",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch gmac_core3_clk = {
+	.halt_reg = 0x3c20,
+	.halt_bit = 6,
+	.hwcg_reg = 0x3cf4,
+	.hwcg_bit = 6,
+	.clkr = {
+		.enable_reg = 0x3cf4,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core3_clk",
+			.parent_names = (const char *[]){
+				"gmac_core3_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_dyn_rcg gmac_core4_src = {
+	.ns_reg[0] = 0x3d0c,
+	.ns_reg[1] = 0x3d10,
+	.md_reg[0] = 0x3d04,
+	.md_reg[1] = 0x3d08,
+	.bank_reg = 0x3d00,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_gmac,
+	.clkr = {
+		.enable_reg = 0x3d00,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core4_src",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch gmac_core4_clk = {
+	.halt_reg = 0x3c20,
+	.halt_bit = 7,
+	.hwcg_reg = 0x3d14,
+	.hwcg_bit = 6,
+	.clkr = {
+		.enable_reg = 0x3d14,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gmac_core4_clk",
+			.parent_names = (const char *[]){
+				"gmac_core4_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_nss_tcm[] = {
+	{ 266000000, P_PLL0, 3, 0, 0 },
+	{ 400000000, P_PLL0, 2, 0, 0 },
+	{ }
+};
+
+static struct clk_dyn_rcg nss_tcm_src = {
+	.ns_reg[0] = 0x3dc4,
+	.ns_reg[1] = 0x3dc8,
+	.bank_reg = 0x3dc0,
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_nss_tcm,
+	.clkr = {
+		.enable_reg = 0x3dc0,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_tcm_src",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch nss_tcm_clk = {
+	.halt_reg = 0x3c20,
+	.halt_bit = 14,
+	.clkr = {
+		.enable_reg = 0x3dd0,
+		.enable_mask = BIT(6) | BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_tcm_clk",
+			.parent_names = (const char *[]){
+				"nss_tcm_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_nss[] = {
+	{ 110000000, P_PLL18, 1, 1, 5 },
+	{ 275000000, P_PLL18, 2, 0, 0 },
+	{ 550000000, P_PLL18, 1, 0, 0 },
+	{ 733000000, P_PLL18, 1, 0, 0 },
+	{ }
+};
+
+static struct clk_dyn_rcg ubi32_core1_src_clk = {
+	.ns_reg[0] = 0x3d2c,
+	.ns_reg[1] = 0x3d30,
+	.md_reg[0] = 0x3d24,
+	.md_reg[1] = 0x3d28,
+	.bank_reg = 0x3d20,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_nss,
+	.clkr = {
+		.enable_reg = 0x3d20,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "ubi32_core1_src_clk",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+			.flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE,
+		},
+	},
+};
+
+static struct clk_dyn_rcg ubi32_core2_src_clk = {
+	.ns_reg[0] = 0x3d4c,
+	.ns_reg[1] = 0x3d50,
+	.md_reg[0] = 0x3d44,
+	.md_reg[1] = 0x3d48,
+	.bank_reg = 0x3d40,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.s[0] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll14_pll18_pll0_map,
+	},
+	.p[0] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.p[1] = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.mux_sel_bit = 0,
+	.freq_tbl = clk_tbl_nss,
+	.clkr = {
+		.enable_reg = 0x3d40,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "ubi32_core2_src_clk",
+			.parent_names = gcc_pxo_pll8_pll14_pll18_pll0,
+			.num_parents = 5,
+			.ops = &clk_dyn_rcg_ops,
+			.flags = CLK_SET_RATE_PARENT | CLK_GET_RATE_NOCACHE,
+		},
+	},
+};
+
 static struct clk_regmap *gcc_ipq806x_clks[] = {
 	[PLL0] = &pll0.clkr,
 	[PLL0_VOTE] = &pll0_vote,
@@ -2211,6 +2728,7 @@ static struct clk_regmap *gcc_ipq806x_clks[] = {
 	[PLL8_VOTE] = &pll8_vote,
 	[PLL14] = &pll14.clkr,
 	[PLL14_VOTE] = &pll14_vote,
+	[PLL18] = &pll18.clkr,
 	[GSBI1_UART_SRC] = &gsbi1_uart_src.clkr,
 	[GSBI1_UART_CLK] = &gsbi1_uart_clk.clkr,
 	[GSBI2_UART_SRC] = &gsbi2_uart_src.clkr,
@@ -2307,6 +2825,18 @@ static struct clk_regmap *gcc_ipq806x_clks[] = {
 	[USB_FS1_SYSTEM_CLK] = &usb_fs1_sys_clk.clkr,
 	[EBI2_CLK] = &ebi2_clk.clkr,
 	[EBI2_AON_CLK] = &ebi2_aon_clk.clkr,
+	[GMAC_CORE1_CLK_SRC] = &gmac_core1_src.clkr,
+	[GMAC_CORE1_CLK] = &gmac_core1_clk.clkr,
+	[GMAC_CORE2_CLK_SRC] = &gmac_core2_src.clkr,
+	[GMAC_CORE2_CLK] = &gmac_core2_clk.clkr,
+	[GMAC_CORE3_CLK_SRC] = &gmac_core3_src.clkr,
+	[GMAC_CORE3_CLK] = &gmac_core3_clk.clkr,
+	[GMAC_CORE4_CLK_SRC] = &gmac_core4_src.clkr,
+	[GMAC_CORE4_CLK] = &gmac_core4_clk.clkr,
+	[UBI32_CORE1_CLK_SRC] = &ubi32_core1_src_clk.clkr,
+	[UBI32_CORE2_CLK_SRC] = &ubi32_core2_src_clk.clkr,
+	[NSSTCM_CLK_SRC] = &nss_tcm_src.clkr,
+	[NSSTCM_CLK] = &nss_tcm_clk.clkr,
 };
 
 static const struct qcom_reset_map gcc_ipq806x_resets[] = {
@@ -2425,6 +2955,48 @@ static const struct qcom_reset_map gcc_ipq806x_resets[] = {
 	[USB30_1_PHY_RESET] = { 0x3b58, 0 },
 	[NSSFB0_RESET] = { 0x3b60, 6 },
 	[NSSFB1_RESET] = { 0x3b60, 7 },
+	[UBI32_CORE1_CLKRST_CLAMP_RESET] = { 0x3d3c, 3},
+	[UBI32_CORE1_CLAMP_RESET] = { 0x3d3c, 2 },
+	[UBI32_CORE1_AHB_RESET] = { 0x3d3c, 1 },
+	[UBI32_CORE1_AXI_RESET] = { 0x3d3c, 0 },
+	[UBI32_CORE2_CLKRST_CLAMP_RESET] = { 0x3d5c, 3 },
+	[UBI32_CORE2_CLAMP_RESET] = { 0x3d5c, 2 },
+	[UBI32_CORE2_AHB_RESET] = { 0x3d5c, 1 },
+	[UBI32_CORE2_AXI_RESET] = { 0x3d5c, 0 },
+	[GMAC_CORE1_RESET] = { 0x3cbc, 0 },
+	[GMAC_CORE2_RESET] = { 0x3cdc, 0 },
+	[GMAC_CORE3_RESET] = { 0x3cfc, 0 },
+	[GMAC_CORE4_RESET] = { 0x3d1c, 0 },
+	[GMAC_AHB_RESET] = { 0x3e24, 0 },
+	[NSS_CH0_RST_RX_CLK_N_RESET] = { 0x3b60, 0 },
+	[NSS_CH0_RST_TX_CLK_N_RESET] = { 0x3b60, 1 },
+	[NSS_CH0_RST_RX_125M_N_RESET] = { 0x3b60, 2 },
+	[NSS_CH0_HW_RST_RX_125M_N_RESET] = { 0x3b60, 3 },
+	[NSS_CH0_RST_TX_125M_N_RESET] = { 0x3b60, 4 },
+	[NSS_CH1_RST_RX_CLK_N_RESET] = { 0x3b60, 5 },
+	[NSS_CH1_RST_TX_CLK_N_RESET] = { 0x3b60, 6 },
+	[NSS_CH1_RST_RX_125M_N_RESET] = { 0x3b60, 7 },
+	[NSS_CH1_HW_RST_RX_125M_N_RESET] = { 0x3b60, 8 },
+	[NSS_CH1_RST_TX_125M_N_RESET] = { 0x3b60, 9 },
+	[NSS_CH2_RST_RX_CLK_N_RESET] = { 0x3b60, 10 },
+	[NSS_CH2_RST_TX_CLK_N_RESET] = { 0x3b60, 11 },
+	[NSS_CH2_RST_RX_125M_N_RESET] = { 0x3b60, 12 },
+	[NSS_CH2_HW_RST_RX_125M_N_RESET] = { 0x3b60, 13 },
+	[NSS_CH2_RST_TX_125M_N_RESET] = { 0x3b60, 14 },
+	[NSS_CH3_RST_RX_CLK_N_RESET] = { 0x3b60, 15 },
+	[NSS_CH3_RST_TX_CLK_N_RESET] = { 0x3b60, 16 },
+	[NSS_CH3_RST_RX_125M_N_RESET] = { 0x3b60, 17 },
+	[NSS_CH3_HW_RST_RX_125M_N_RESET] = { 0x3b60, 18 },
+	[NSS_CH3_RST_TX_125M_N_RESET] = { 0x3b60, 19 },
+	[NSS_RST_RX_250M_125M_N_RESET] = { 0x3b60, 20 },
+	[NSS_RST_TX_250M_125M_N_RESET] = { 0x3b60, 21 },
+	[NSS_QSGMII_TXPI_RST_N_RESET] = { 0x3b60, 22 },
+	[NSS_QSGMII_CDR_RST_N_RESET] = { 0x3b60, 23 },
+	[NSS_SGMII2_CDR_RST_N_RESET] = { 0x3b60, 24 },
+	[NSS_SGMII3_CDR_RST_N_RESET] = { 0x3b60, 25 },
+	[NSS_CAL_PRBS_RST_N_RESET] = { 0x3b60, 26 },
+	[NSS_LCKDT_RST_N_RESET] = { 0x3b60, 27 },
+	[NSS_SRDS_N_RESET] = { 0x3b60, 28 },
 };
 
 static const struct regmap_config gcc_ipq806x_regmap_config = {
@@ -2453,6 +3025,8 @@ static int gcc_ipq806x_probe(struct platform_device *pdev)
 {
 	struct clk *clk;
 	struct device *dev = &pdev->dev;
+	struct regmap *regmap;
+	int ret;
 
 	/* Temporary until RPM clocks supported */
 	clk = clk_register_fixed_rate(dev, "cxo", NULL, CLK_IS_ROOT, 25000000);
@@ -2463,7 +3037,25 @@ static int gcc_ipq806x_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
-	return qcom_cc_probe(pdev, &gcc_ipq806x_desc);
+	ret = qcom_cc_probe(pdev, &gcc_ipq806x_desc);
+	if (ret)
+		return ret;
+
+	regmap = dev_get_regmap(dev, NULL);
+	if (!regmap)
+		return -ENODEV;
+
+	/* Setup PLL18 static bits */
+	regmap_update_bits(regmap, 0x31a4, 0xffffffc0, 0x40000400);
+	regmap_write(regmap, 0x31b0, 0x3080);
+
+	/* Set GMAC footswitch sleep/wakeup values */
+	regmap_write(regmap, 0x3cb8, 8);
+	regmap_write(regmap, 0x3cd8, 8);
+	regmap_write(regmap, 0x3cf8, 8);
+	regmap_write(regmap, 0x3d18, 8);
+
+	return 0;
 }
 
 static int gcc_ipq806x_remove(struct platform_device *pdev)
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index d3458474eb3a..c66f7bc2ae87 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -71,8 +71,8 @@ static const char *gcc_xo_gpll0_bimc[] = {
 static const struct parent_map gcc_xo_gpll0a_gpll1_gpll2a_map[] = {
 	{ P_XO, 0 },
 	{ P_GPLL0_AUX, 3 },
-	{ P_GPLL2_AUX, 2 },
 	{ P_GPLL1, 1 },
+	{ P_GPLL2_AUX, 2 },
 };
 
 static const char *gcc_xo_gpll0a_gpll1_gpll2a[] = {
@@ -1115,7 +1115,7 @@ static struct clk_rcg2 usb_hs_system_clk_src = {
 static const struct freq_tbl ftbl_gcc_venus0_vcodec0_clk[] = {
 	F(100000000, P_GPLL0, 8, 0, 0),
 	F(160000000, P_GPLL0, 5, 0, 0),
-	F(228570000, P_GPLL0, 5, 0, 0),
+	F(228570000, P_GPLL0, 3.5, 0, 0),
 	{ }
 };
 
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 17e9af7fe81f..a17683b2cf27 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_SOC_EXYNOS5250)	+= clk-exynos5250.o
 obj-$(CONFIG_SOC_EXYNOS5260)	+= clk-exynos5260.o
 obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
 obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
-obj-$(CONFIG_ARCH_EXYNOS5433)	+= clk-exynos5433.o
+obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos5433.o
 obj-$(CONFIG_SOC_EXYNOS5440)	+= clk-exynos5440.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-audss.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-clkout.o
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 07d666cc6a29..bea4a173eef5 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -271,6 +271,7 @@ static const struct samsung_clk_reg_dump exynos5420_set_clksrc[] = {
 	{ .offset = SRC_MASK_PERIC0,		.value = 0x11111110, },
 	{ .offset = SRC_MASK_PERIC1,		.value = 0x11111100, },
 	{ .offset = SRC_MASK_ISP,		.value = 0x11111000, },
+	{ .offset = GATE_BUS_TOP,		.value = 0xffffffff, },
 	{ .offset = GATE_BUS_DISP1,		.value = 0xffffffff, },
 	{ .offset = GATE_IP_PERIC,		.value = 0xffffffff, },
 };
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 387e3e39e635..9e04ae2bb4d7 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -748,7 +748,7 @@ static struct samsung_pll_rate_table exynos5443_pll_rates[] = {
 	PLL_35XX_RATE(825000000U,  275, 4,  1),
 	PLL_35XX_RATE(800000000U,  400, 6,  1),
 	PLL_35XX_RATE(733000000U,  733, 12, 1),
-	PLL_35XX_RATE(700000000U,  360, 6,  1),
+	PLL_35XX_RATE(700000000U,  175, 3,  1),
 	PLL_35XX_RATE(667000000U,  222, 4,  1),
 	PLL_35XX_RATE(633000000U,  211, 4,  1),
 	PLL_35XX_RATE(600000000U,  500, 5,  2),
@@ -760,14 +760,14 @@ static struct samsung_pll_rate_table exynos5443_pll_rates[] = {
 	PLL_35XX_RATE(444000000U,  370, 5,  2),
 	PLL_35XX_RATE(420000000U,  350, 5,  2),
 	PLL_35XX_RATE(400000000U,  400, 6,  2),
-	PLL_35XX_RATE(350000000U,  360, 6,  2),
+	PLL_35XX_RATE(350000000U,  350, 6,  2),
 	PLL_35XX_RATE(333000000U,  222, 4,  2),
 	PLL_35XX_RATE(300000000U,  500, 5,  3),
 	PLL_35XX_RATE(266000000U,  532, 6,  3),
 	PLL_35XX_RATE(200000000U,  400, 6,  3),
 	PLL_35XX_RATE(166000000U,  332, 6,  3),
 	PLL_35XX_RATE(160000000U,  320, 6,  3),
-	PLL_35XX_RATE(133000000U,  552, 6,  4),
+	PLL_35XX_RATE(133000000U,  532, 6,  4),
 	PLL_35XX_RATE(100000000U,  400, 6,  4),
 	{ /* sentinel */ }
 };
@@ -1490,7 +1490,7 @@ static struct samsung_gate_clock mif_gate_clks[] __initdata = {
 
 	/* ENABLE_PCLK_MIF_SECURE_MONOTONIC_CNT */
 	GATE(CLK_PCLK_MONOTONIC_CNT, "pclk_monotonic_cnt", "div_aclk_mif_133",
-			ENABLE_PCLK_MIF_SECURE_RTC, 0, 0, 0),
+			ENABLE_PCLK_MIF_SECURE_MONOTONIC_CNT, 0, 0, 0),
 
 	/* ENABLE_PCLK_MIF_SECURE_RTC */
 	GATE(CLK_PCLK_RTC, "pclk_rtc", "div_aclk_mif_133",
@@ -3665,7 +3665,7 @@ static struct samsung_gate_clock apollo_gate_clks[] __initdata = {
 			ENABLE_SCLK_APOLLO, 3, CLK_IGNORE_UNUSED, 0),
 	GATE(CLK_SCLK_HPM_APOLLO, "sclk_hpm_apollo", "div_sclk_hpm_apollo",
 			ENABLE_SCLK_APOLLO, 1, CLK_IGNORE_UNUSED, 0),
-	GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo_pll",
+	GATE(CLK_SCLK_APOLLO, "sclk_apollo", "div_apollo2",
 			ENABLE_SCLK_APOLLO, 0, CLK_IGNORE_UNUSED, 0),
 };
 
@@ -3927,7 +3927,7 @@ CLK_OF_DECLARE(exynos5433_cmu_atlas, "samsung,exynos5433-cmu-atlas",
 #define ENABLE_PCLK_MSCL				0x0900
 #define ENABLE_PCLK_MSCL_SECURE_SMMU_M2MSCALER0		0x0904
 #define ENABLE_PCLK_MSCL_SECURE_SMMU_M2MSCALER1		0x0908
-#define ENABLE_PCLK_MSCL_SECURE_SMMU_JPEG		0x000c
+#define ENABLE_PCLK_MSCL_SECURE_SMMU_JPEG		0x090c
 #define ENABLE_SCLK_MSCL				0x0a00
 #define ENABLE_IP_MSCL0					0x0b00
 #define ENABLE_IP_MSCL1					0x0b04
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 5d2217ae4478..63b8323df918 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -305,13 +305,14 @@ static struct ti_dt_clk dra7xx_clks[] = {
 	DT_CLK("4882c000.timer", "timer_sys_ck", "timer_sys_clk_div"),
 	DT_CLK("4882e000.timer", "timer_sys_ck", "timer_sys_clk_div"),
 	DT_CLK(NULL, "sys_clkin", "sys_clkin1"),
+	DT_CLK(NULL, "dss_deshdcp_clk", "dss_deshdcp_clk"),
 	{ .node_name = NULL },
 };
 
 int __init dra7xx_dt_clk_init(void)
 {
 	int rc;
-	struct clk *abe_dpll_mux, *sys_clkin2, *dpll_ck;
+	struct clk *abe_dpll_mux, *sys_clkin2, *dpll_ck, *hdcp_ck;
 
 	ti_dt_clocks_register(dra7xx_clks);
 
@@ -347,5 +348,10 @@ int __init dra7xx_dt_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to set USB_DPLL M2 OUT\n", __func__);
 
+	hdcp_ck = clk_get_sys(NULL, "dss_deshdcp_clk");
+	rc = clk_prepare_enable(hdcp_ck);
+	if (rc)
+		pr_err("%s: failed to set dss_deshdcp_clk\n", __func__);
+
 	return rc;
 }
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 51d7865fdddb..d1bd53f2f360 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -106,6 +106,16 @@ config CLKSRC_EFM32
 	  Support to use the timers of EFM32 SoCs as clock source and clock
 	  event device.
 
+config CLKSRC_LPC32XX
+	bool
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+
+config CLKSRC_STM32
+	bool "Clocksource for STM32 SoCs" if !ARCH_STM32
+	depends on OF && ARM && (ARCH_STM32 || COMPILE_TEST)
+	select CLKSRC_MMIO
+
 config ARM_ARCH_TIMER
 	bool
 	select CLKSRC_OF if OF
@@ -139,6 +149,13 @@ config CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
 	help
 	 Use ARM global timer clock source as sched_clock
 
+config ARMV7M_SYSTICK
+	bool
+	select CLKSRC_OF if OF
+	select CLKSRC_MMIO
+	help
+	  This options enables support for the ARMv7M system timer unit
+
 config ATMEL_PIT
 	select CLKSRC_OF if OF
 	def_bool SOC_AT91SAM9 || SOC_SAMA5
@@ -258,4 +275,11 @@ config CLKSRC_PXA
 	help
 	  This enables OST0 support available on PXA and SA-11x0
 	  platforms.
+
+config H8300_TMR16
+        bool
+
+config H8300_TPU
+        bool
+
 endmenu
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 5b85f6adb258..2b344232262c 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -36,7 +36,9 @@ obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
 obj-$(CONFIG_ARCH_BCM_MOBILE)	+= bcm_kona_timer.o
 obj-$(CONFIG_CADENCE_TTC_TIMER)	+= cadence_ttc_timer.o
 obj-$(CONFIG_CLKSRC_EFM32)	+= time-efm32.o
+obj-$(CONFIG_CLKSRC_STM32)	+= timer-stm32.o
 obj-$(CONFIG_CLKSRC_EXYNOS_MCT)	+= exynos_mct.o
+obj-$(CONFIG_CLKSRC_LPC32XX)	+= time-lpc32xx.o
 obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
@@ -45,6 +47,7 @@ obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
 
 obj-$(CONFIG_ARM_ARCH_TIMER)		+= arm_arch_timer.o
 obj-$(CONFIG_ARM_GLOBAL_TIMER)		+= arm_global_timer.o
+obj-$(CONFIG_ARMV7M_SYSTICK)		+= armv7m_systick.o
 obj-$(CONFIG_CLKSRC_METAG_GENERIC)	+= metag_generic.o
 obj-$(CONFIG_ARCH_HAS_TICK_BROADCAST)	+= dummy_timer.o
 obj-$(CONFIG_ARCH_KEYSTONE)		+= timer-keystone.o
@@ -52,3 +55,6 @@ obj-$(CONFIG_ARCH_INTEGRATOR_AP)	+= timer-integrator-ap.o
 obj-$(CONFIG_CLKSRC_VERSATILE)		+= versatile.o
 obj-$(CONFIG_CLKSRC_MIPS_GIC)		+= mips-gic-timer.o
 obj-$(CONFIG_ASM9260_TIMER)		+= asm9260_timer.o
+obj-$(CONFIG_H8300)			+= h8300_timer8.o
+obj-$(CONFIG_H8300_TMR16)		+= h8300_timer16.o
+obj-$(CONFIG_H8300_TPU)			+= h8300_tpu.o
diff --git a/drivers/clocksource/armv7m_systick.c b/drivers/clocksource/armv7m_systick.c
new file mode 100644
index 000000000000..addfd2c64f54
--- /dev/null
+++ b/drivers/clocksource/armv7m_systick.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define SYST_CSR	0x00
+#define SYST_RVR	0x04
+#define SYST_CVR	0x08
+#define SYST_CALIB	0x0c
+
+#define SYST_CSR_ENABLE BIT(0)
+
+#define SYSTICK_LOAD_RELOAD_MASK 0x00FFFFFF
+
+static void __init system_timer_of_register(struct device_node *np)
+{
+	struct clk *clk = NULL;
+	void __iomem *base;
+	u32 rate;
+	int ret;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_warn("system-timer: invalid base address\n");
+		return;
+	}
+
+	ret = of_property_read_u32(np, "clock-frequency", &rate);
+	if (ret) {
+		clk = of_clk_get(np, 0);
+		if (IS_ERR(clk))
+			goto out_unmap;
+
+		ret = clk_prepare_enable(clk);
+		if (ret)
+			goto out_clk_put;
+
+		rate = clk_get_rate(clk);
+		if (!rate)
+			goto out_clk_disable;
+	}
+
+	writel_relaxed(SYSTICK_LOAD_RELOAD_MASK, base + SYST_RVR);
+	writel_relaxed(SYST_CSR_ENABLE, base + SYST_CSR);
+
+	ret = clocksource_mmio_init(base + SYST_CVR, "arm_system_timer", rate,
+			200, 24, clocksource_mmio_readl_down);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		if (clk)
+			goto out_clk_disable;
+		else
+			goto out_unmap;
+	}
+
+	pr_info("ARM System timer initialized as clocksource\n");
+
+	return;
+
+out_clk_disable:
+	clk_disable_unprepare(clk);
+out_clk_put:
+	clk_put(clk);
+out_unmap:
+	iounmap(base);
+	pr_warn("ARM System timer register failed (%d)\n", ret);
+}
+
+CLOCKSOURCE_OF_DECLARE(arm_systick, "arm,armv7m-systick",
+			system_timer_of_register);
diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c
index 2c9c993727c8..4c2ba59897e8 100644
--- a/drivers/clocksource/asm9260_timer.c
+++ b/drivers/clocksource/asm9260_timer.c
@@ -178,7 +178,7 @@ static void __init asm9260_timer_init(struct device_node *np)
 	unsigned long rate;
 
 	priv.base = of_io_request_and_map(np, 0, np->name);
-	if (!priv.base)
+	if (IS_ERR(priv.base))
 		panic("%s: unable to map resource", np->name);
 
 	clk = of_clk_get(np, 0);
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 83564c9cfdbe..935b05936dbd 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -209,7 +209,7 @@ static void exynos4_frc_resume(struct clocksource *cs)
 	exynos4_mct_frc_start();
 }
 
-struct clocksource mct_frc = {
+static struct clocksource mct_frc = {
 	.name		= "mct-frc",
 	.rating		= 400,
 	.read		= exynos4_frc_read,
@@ -413,7 +413,7 @@ static inline void exynos4_tick_set_mode(enum clock_event_mode mode,
 	}
 }
 
-static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 {
 	struct clock_event_device *evt = &mevt->evt;
 
@@ -426,12 +426,8 @@ static int exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
 		exynos4_mct_tick_stop(mevt);
 
 	/* Clear the MCT tick interrupt */
-	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1) {
+	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
 		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
-		return 1;
-	} else {
-		return 0;
-	}
 }
 
 static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
@@ -564,18 +560,6 @@ out_irq:
 	free_percpu_irq(mct_irqs[MCT_L0_IRQ], &percpu_mct_tick);
 }
 
-void __init mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1)
-{
-	mct_irqs[MCT_G0_IRQ] = irq_g0;
-	mct_irqs[MCT_L0_IRQ] = irq_l0;
-	mct_irqs[MCT_L1_IRQ] = irq_l1;
-	mct_int_type = MCT_INT_SPI;
-
-	exynos4_timer_resources(NULL, base);
-	exynos4_clocksource_init();
-	exynos4_clockevent_init();
-}
-
 static void __init mct_init_dt(struct device_node *np, unsigned int int_type)
 {
 	u32 nr_irqs, i;
diff --git a/drivers/clocksource/h8300_timer16.c b/drivers/clocksource/h8300_timer16.c
new file mode 100644
index 000000000000..82941c1e9e33
--- /dev/null
+++ b/drivers/clocksource/h8300_timer16.c
@@ -0,0 +1,254 @@
+/*
+ *  H8/300 16bit Timer driver
+ *
+ *  Copyright 2015 Yoshinori Sato <ysato@users.sourcefoge.jp>
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/param.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/clocksource.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <asm/segment.h>
+#include <asm/irq.h>
+
+#define TSTR	0
+#define TSNC	1
+#define TMDR	2
+#define TOLR	3
+#define TISRA	4
+#define TISRB	5
+#define TISRC	6
+
+#define TCR	0
+#define TIOR	1
+#define TCNT	2
+#define GRA	4
+#define GRB	6
+
+#define FLAG_REPROGRAM (1 << 0)
+#define FLAG_SKIPEVENT (1 << 1)
+#define FLAG_IRQCONTEXT (1 << 2)
+#define FLAG_STARTED (1 << 3)
+
+#define ONESHOT  0
+#define PERIODIC 1
+
+#define RELATIVE 0
+#define ABSOLUTE 1
+
+struct timer16_priv {
+	struct platform_device *pdev;
+	struct clocksource cs;
+	struct irqaction irqaction;
+	unsigned long total_cycles;
+	unsigned long mapbase;
+	unsigned long mapcommon;
+	unsigned long flags;
+	unsigned short gra;
+	unsigned short cs_enabled;
+	unsigned char enb;
+	unsigned char imfa;
+	unsigned char imiea;
+	unsigned char ovf;
+	raw_spinlock_t lock;
+	struct clk *clk;
+};
+
+static unsigned long timer16_get_counter(struct timer16_priv *p)
+{
+	unsigned long v1, v2, v3;
+	int o1, o2;
+
+	o1 = ctrl_inb(p->mapcommon + TISRC) & p->ovf;
+
+	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
+	do {
+		o2 = o1;
+		v1 = ctrl_inw(p->mapbase + TCNT);
+		v2 = ctrl_inw(p->mapbase + TCNT);
+		v3 = ctrl_inw(p->mapbase + TCNT);
+		o1 = ctrl_inb(p->mapcommon + TISRC) & p->ovf;
+	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
+			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
+
+	v2 |= 0x10000;
+	return v2;
+}
+
+
+static irqreturn_t timer16_interrupt(int irq, void *dev_id)
+{
+	struct timer16_priv *p = (struct timer16_priv *)dev_id;
+
+	ctrl_outb(ctrl_inb(p->mapcommon + TISRA) & ~p->imfa,
+		  p->mapcommon + TISRA);
+	p->total_cycles += 0x10000;
+
+	return IRQ_HANDLED;
+}
+
+static inline struct timer16_priv *cs_to_priv(struct clocksource *cs)
+{
+	return container_of(cs, struct timer16_priv, cs);
+}
+
+static cycle_t timer16_clocksource_read(struct clocksource *cs)
+{
+	struct timer16_priv *p = cs_to_priv(cs);
+	unsigned long flags, raw;
+	unsigned long value;
+
+	raw_spin_lock_irqsave(&p->lock, flags);
+	value = p->total_cycles;
+	raw = timer16_get_counter(p);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
+
+	return value + raw;
+}
+
+static int timer16_enable(struct clocksource *cs)
+{
+	struct timer16_priv *p = cs_to_priv(cs);
+
+	WARN_ON(p->cs_enabled);
+
+	p->total_cycles = 0;
+	ctrl_outw(0x0000, p->mapbase + TCNT);
+	ctrl_outb(0x83, p->mapbase + TCR);
+	ctrl_outb(ctrl_inb(p->mapcommon + TSTR) | p->enb,
+		  p->mapcommon + TSTR);
+
+	p->cs_enabled = true;
+	return 0;
+}
+
+static void timer16_disable(struct clocksource *cs)
+{
+	struct timer16_priv *p = cs_to_priv(cs);
+
+	WARN_ON(!p->cs_enabled);
+
+	ctrl_outb(ctrl_inb(p->mapcommon + TSTR) & ~p->enb,
+		  p->mapcommon + TSTR);
+
+	p->cs_enabled = false;
+}
+
+#define REG_CH   0
+#define REG_COMM 1
+
+static int timer16_setup(struct timer16_priv *p, struct platform_device *pdev)
+{
+	struct resource *res[2];
+	int ret, irq;
+	unsigned int ch;
+
+	memset(p, 0, sizeof(*p));
+	p->pdev = pdev;
+
+	res[REG_CH] = platform_get_resource(p->pdev,
+					    IORESOURCE_MEM, REG_CH);
+	res[REG_COMM] = platform_get_resource(p->pdev,
+					      IORESOURCE_MEM, REG_COMM);
+	if (!res[REG_CH] || !res[REG_COMM]) {
+		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
+		return -ENXIO;
+	}
+	irq = platform_get_irq(p->pdev, 0);
+	if (irq < 0) {
+		dev_err(&p->pdev->dev, "failed to get irq\n");
+		return irq;
+	}
+
+	p->clk = clk_get(&p->pdev->dev, "fck");
+	if (IS_ERR(p->clk)) {
+		dev_err(&p->pdev->dev, "can't get clk\n");
+		return PTR_ERR(p->clk);
+	}
+	of_property_read_u32(p->pdev->dev.of_node, "renesas,channel", &ch);
+
+	p->pdev = pdev;
+	p->mapbase = res[REG_CH]->start;
+	p->mapcommon = res[REG_COMM]->start;
+	p->enb = 1 << ch;
+	p->imfa = 1 << ch;
+	p->imiea = 1 << (4 + ch);
+	p->cs.name = pdev->name;
+	p->cs.rating = 200;
+	p->cs.read = timer16_clocksource_read;
+	p->cs.enable = timer16_enable;
+	p->cs.disable = timer16_disable;
+	p->cs.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8);
+	p->cs.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+	ret = request_irq(irq, timer16_interrupt,
+			  IRQF_TIMER, pdev->name, p);
+	if (ret < 0) {
+		dev_err(&p->pdev->dev, "failed to request irq %d\n", irq);
+		return ret;
+	}
+
+	clocksource_register_hz(&p->cs, clk_get_rate(p->clk) / 8);
+
+	return 0;
+}
+
+static int timer16_probe(struct platform_device *pdev)
+{
+	struct timer16_priv *p = platform_get_drvdata(pdev);
+
+	if (p) {
+		dev_info(&pdev->dev, "kept as earlytimer\n");
+		return 0;
+	}
+
+	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	return timer16_setup(p, pdev);
+}
+
+static int timer16_remove(struct platform_device *pdev)
+{
+	return -EBUSY;
+}
+
+static const struct of_device_id timer16_of_table[] = {
+	{ .compatible = "renesas,16bit-timer" },
+	{ }
+};
+static struct platform_driver timer16_driver = {
+	.probe		= timer16_probe,
+	.remove		= timer16_remove,
+	.driver		= {
+		.name	= "h8300h-16timer",
+		.of_match_table = of_match_ptr(timer16_of_table),
+	}
+};
+
+static int __init timer16_init(void)
+{
+	return platform_driver_register(&timer16_driver);
+}
+
+static void __exit timer16_exit(void)
+{
+	platform_driver_unregister(&timer16_driver);
+}
+
+subsys_initcall(timer16_init);
+module_exit(timer16_exit);
+MODULE_AUTHOR("Yoshinori Sato");
+MODULE_DESCRIPTION("H8/300H 16bit Timer Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c
new file mode 100644
index 000000000000..0214cb3a7f5e
--- /dev/null
+++ b/drivers/clocksource/h8300_timer8.c
@@ -0,0 +1,313 @@
+/*
+ *  linux/arch/h8300/kernel/cpu/timer/timer8.c
+ *
+ *  Yoshinori Sato <ysato@users.sourcefoge.jp>
+ *
+ *  8bit Timer driver
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/clockchips.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <asm/irq.h>
+
+#define _8TCR	0
+#define _8TCSR	2
+#define TCORA	4
+#define TCORB	6
+#define _8TCNT	8
+
+#define FLAG_REPROGRAM (1 << 0)
+#define FLAG_SKIPEVENT (1 << 1)
+#define FLAG_IRQCONTEXT (1 << 2)
+#define FLAG_STARTED (1 << 3)
+
+#define ONESHOT  0
+#define PERIODIC 1
+
+#define RELATIVE 0
+#define ABSOLUTE 1
+
+struct timer8_priv {
+	struct platform_device *pdev;
+	struct clock_event_device ced;
+	struct irqaction irqaction;
+	unsigned long mapbase;
+	raw_spinlock_t lock;
+	unsigned long flags;
+	unsigned int rate;
+	unsigned int tcora;
+	struct clk *pclk;
+};
+
+static unsigned long timer8_get_counter(struct timer8_priv *p)
+{
+	unsigned long v1, v2, v3;
+	int o1, o2;
+
+	o1 = ctrl_inb(p->mapbase + _8TCSR) & 0x20;
+
+	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
+	do {
+		o2 = o1;
+		v1 = ctrl_inw(p->mapbase + _8TCNT);
+		v2 = ctrl_inw(p->mapbase + _8TCNT);
+		v3 = ctrl_inw(p->mapbase + _8TCNT);
+		o1 = ctrl_inb(p->mapbase + _8TCSR) & 0x20;
+	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
+			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
+
+	v2 |= o1 << 10;
+	return v2;
+}
+
+static irqreturn_t timer8_interrupt(int irq, void *dev_id)
+{
+	struct timer8_priv *p = dev_id;
+
+	ctrl_outb(ctrl_inb(p->mapbase + _8TCSR) & ~0x40,
+		  p->mapbase + _8TCSR);
+	p->flags |= FLAG_IRQCONTEXT;
+	ctrl_outw(p->tcora, p->mapbase + TCORA);
+	if (!(p->flags & FLAG_SKIPEVENT)) {
+		if (p->ced.mode == CLOCK_EVT_MODE_ONESHOT)
+			ctrl_outw(0x0000, p->mapbase + _8TCR);
+		p->ced.event_handler(&p->ced);
+	}
+	p->flags &= ~(FLAG_SKIPEVENT | FLAG_IRQCONTEXT);
+
+	return IRQ_HANDLED;
+}
+
+static void timer8_set_next(struct timer8_priv *p, unsigned long delta)
+{
+	unsigned long flags;
+	unsigned long now;
+
+	raw_spin_lock_irqsave(&p->lock, flags);
+	if (delta >= 0x10000)
+		dev_warn(&p->pdev->dev, "delta out of range\n");
+	now = timer8_get_counter(p);
+	p->tcora = delta;
+	ctrl_outb(ctrl_inb(p->mapbase + _8TCR) | 0x40, p->mapbase + _8TCR);
+	if (delta > now)
+		ctrl_outw(delta, p->mapbase + TCORA);
+	else
+		ctrl_outw(now + 1, p->mapbase + TCORA);
+
+	raw_spin_unlock_irqrestore(&p->lock, flags);
+}
+
+static int timer8_enable(struct timer8_priv *p)
+{
+	p->rate = clk_get_rate(p->pclk) / 64;
+	ctrl_outw(0xffff, p->mapbase + TCORA);
+	ctrl_outw(0x0000, p->mapbase + _8TCNT);
+	ctrl_outw(0x0c02, p->mapbase + _8TCR);
+
+	return 0;
+}
+
+static int timer8_start(struct timer8_priv *p)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&p->lock, flags);
+
+	if (!(p->flags & FLAG_STARTED))
+		ret = timer8_enable(p);
+
+	if (ret)
+		goto out;
+	p->flags |= FLAG_STARTED;
+
+ out:
+	raw_spin_unlock_irqrestore(&p->lock, flags);
+
+	return ret;
+}
+
+static void timer8_stop(struct timer8_priv *p)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&p->lock, flags);
+
+	ctrl_outw(0x0000, p->mapbase + _8TCR);
+
+	raw_spin_unlock_irqrestore(&p->lock, flags);
+}
+
+static inline struct timer8_priv *ced_to_priv(struct clock_event_device *ced)
+{
+	return container_of(ced, struct timer8_priv, ced);
+}
+
+static void timer8_clock_event_start(struct timer8_priv *p, int periodic)
+{
+	struct clock_event_device *ced = &p->ced;
+
+	timer8_start(p);
+
+	ced->shift = 32;
+	ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
+	ced->max_delta_ns = clockevent_delta2ns(0xffff, ced);
+	ced->min_delta_ns = clockevent_delta2ns(0x0001, ced);
+
+	timer8_set_next(p, periodic?(p->rate + HZ/2) / HZ:0x10000);
+}
+
+static void timer8_clock_event_mode(enum clock_event_mode mode,
+				    struct clock_event_device *ced)
+{
+	struct timer8_priv *p = ced_to_priv(ced);
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		dev_info(&p->pdev->dev, "used for periodic clock events\n");
+		timer8_stop(p);
+		timer8_clock_event_start(p, PERIODIC);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+		timer8_stop(p);
+		timer8_clock_event_start(p, ONESHOT);
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		timer8_stop(p);
+		break;
+	default:
+		break;
+	}
+}
+
+static int timer8_clock_event_next(unsigned long delta,
+				   struct clock_event_device *ced)
+{
+	struct timer8_priv *p = ced_to_priv(ced);
+
+	BUG_ON(ced->mode != CLOCK_EVT_MODE_ONESHOT);
+	timer8_set_next(p, delta - 1);
+
+	return 0;
+}
+
+static int timer8_setup(struct timer8_priv *p,
+			struct platform_device *pdev)
+{
+	struct resource *res;
+	int irq;
+	int ret;
+
+	memset(p, 0, sizeof(*p));
+	p->pdev = pdev;
+
+	res = platform_get_resource(p->pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
+		return -ENXIO;
+	}
+
+	irq = platform_get_irq(p->pdev, 0);
+	if (irq < 0) {
+		dev_err(&p->pdev->dev, "failed to get irq\n");
+		return -ENXIO;
+	}
+
+	p->mapbase = res->start;
+
+	p->irqaction.name = dev_name(&p->pdev->dev);
+	p->irqaction.handler = timer8_interrupt;
+	p->irqaction.dev_id = p;
+	p->irqaction.flags = IRQF_TIMER;
+
+	p->pclk = clk_get(&p->pdev->dev, "fck");
+	if (IS_ERR(p->pclk)) {
+		dev_err(&p->pdev->dev, "can't get clk\n");
+		return PTR_ERR(p->pclk);
+	}
+
+	p->ced.name = pdev->name;
+	p->ced.features = CLOCK_EVT_FEAT_PERIODIC |
+		CLOCK_EVT_FEAT_ONESHOT;
+	p->ced.rating = 200;
+	p->ced.cpumask = cpumask_of(0);
+	p->ced.set_next_event = timer8_clock_event_next;
+	p->ced.set_mode = timer8_clock_event_mode;
+
+	ret = setup_irq(irq, &p->irqaction);
+	if (ret < 0) {
+		dev_err(&p->pdev->dev,
+			"failed to request irq %d\n", irq);
+		return ret;
+	}
+	clockevents_register_device(&p->ced);
+	platform_set_drvdata(pdev, p);
+
+	return 0;
+}
+
+static int timer8_probe(struct platform_device *pdev)
+{
+	struct timer8_priv *p = platform_get_drvdata(pdev);
+
+	if (p) {
+		dev_info(&pdev->dev, "kept as earlytimer\n");
+		return 0;
+	}
+
+	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	return timer8_setup(p, pdev);
+}
+
+static int timer8_remove(struct platform_device *pdev)
+{
+	return -EBUSY;
+}
+
+static const struct of_device_id timer8_of_table[] __maybe_unused = {
+	{ .compatible = "renesas,8bit-timer" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, timer8_of_table);
+static struct platform_driver timer8_driver = {
+	.probe		= timer8_probe,
+	.remove		= timer8_remove,
+	.driver		= {
+		.name	= "h8300-8timer",
+		.of_match_table = of_match_ptr(timer8_of_table),
+	}
+};
+
+static int __init timer8_init(void)
+{
+	return platform_driver_register(&timer8_driver);
+}
+
+static void __exit timer8_exit(void)
+{
+	platform_driver_unregister(&timer8_driver);
+}
+
+subsys_initcall(timer8_init);
+module_exit(timer8_exit);
+MODULE_AUTHOR("Yoshinori Sato");
+MODULE_DESCRIPTION("H8/300 8bit Timer Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clocksource/h8300_tpu.c b/drivers/clocksource/h8300_tpu.c
new file mode 100644
index 000000000000..64195fdd78bf
--- /dev/null
+++ b/drivers/clocksource/h8300_tpu.c
@@ -0,0 +1,207 @@
+/*
+ *  H8/300 TPU Driver
+ *
+ *  Copyright 2015 Yoshinori Sato <ysato@users.sourcefoge.jp>
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/clocksource.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/of.h>
+
+#include <asm/irq.h>
+
+#define TCR	0
+#define TMDR	1
+#define TIOR	2
+#define TER	4
+#define TSR	5
+#define TCNT	6
+#define TGRA	8
+#define TGRB	10
+#define TGRC	12
+#define TGRD	14
+
+struct tpu_priv {
+	struct platform_device *pdev;
+	struct clocksource cs;
+	struct clk *clk;
+	unsigned long mapbase1;
+	unsigned long mapbase2;
+	raw_spinlock_t lock;
+	unsigned int cs_enabled;
+};
+
+static inline unsigned long read_tcnt32(struct tpu_priv *p)
+{
+	unsigned long tcnt;
+
+	tcnt = ctrl_inw(p->mapbase1 + TCNT) << 16;
+	tcnt |= ctrl_inw(p->mapbase2 + TCNT);
+	return tcnt;
+}
+
+static int tpu_get_counter(struct tpu_priv *p, unsigned long long *val)
+{
+	unsigned long v1, v2, v3;
+	int o1, o2;
+
+	o1 = ctrl_inb(p->mapbase1 + TSR) & 0x10;
+
+	/* Make sure the timer value is stable. Stolen from acpi_pm.c */
+	do {
+		o2 = o1;
+		v1 = read_tcnt32(p);
+		v2 = read_tcnt32(p);
+		v3 = read_tcnt32(p);
+		o1 = ctrl_inb(p->mapbase1 + TSR) & 0x10;
+	} while (unlikely((o1 != o2) || (v1 > v2 && v1 < v3)
+			  || (v2 > v3 && v2 < v1) || (v3 > v1 && v3 < v2)));
+
+	*val = v2;
+	return o1;
+}
+
+static inline struct tpu_priv *cs_to_priv(struct clocksource *cs)
+{
+	return container_of(cs, struct tpu_priv, cs);
+}
+
+static cycle_t tpu_clocksource_read(struct clocksource *cs)
+{
+	struct tpu_priv *p = cs_to_priv(cs);
+	unsigned long flags;
+	unsigned long long value;
+
+	raw_spin_lock_irqsave(&p->lock, flags);
+	if (tpu_get_counter(p, &value))
+		value += 0x100000000;
+	raw_spin_unlock_irqrestore(&p->lock, flags);
+
+	return value;
+}
+
+static int tpu_clocksource_enable(struct clocksource *cs)
+{
+	struct tpu_priv *p = cs_to_priv(cs);
+
+	WARN_ON(p->cs_enabled);
+
+	ctrl_outw(0, p->mapbase1 + TCNT);
+	ctrl_outw(0, p->mapbase2 + TCNT);
+	ctrl_outb(0x0f, p->mapbase1 + TCR);
+	ctrl_outb(0x03, p->mapbase2 + TCR);
+
+	p->cs_enabled = true;
+	return 0;
+}
+
+static void tpu_clocksource_disable(struct clocksource *cs)
+{
+	struct tpu_priv *p = cs_to_priv(cs);
+
+	WARN_ON(!p->cs_enabled);
+
+	ctrl_outb(0, p->mapbase1 + TCR);
+	ctrl_outb(0, p->mapbase2 + TCR);
+	p->cs_enabled = false;
+}
+
+#define CH_L 0
+#define CH_H 1
+
+static int __init tpu_setup(struct tpu_priv *p, struct platform_device *pdev)
+{
+	struct resource *res[2];
+
+	memset(p, 0, sizeof(*p));
+	p->pdev = pdev;
+
+	res[CH_L] = platform_get_resource(p->pdev, IORESOURCE_MEM, CH_L);
+	res[CH_H] = platform_get_resource(p->pdev, IORESOURCE_MEM, CH_H);
+	if (!res[CH_L] || !res[CH_H]) {
+		dev_err(&p->pdev->dev, "failed to get I/O memory\n");
+		return -ENXIO;
+	}
+
+	p->clk = clk_get(&p->pdev->dev, "fck");
+	if (IS_ERR(p->clk)) {
+		dev_err(&p->pdev->dev, "can't get clk\n");
+		return PTR_ERR(p->clk);
+	}
+
+	p->mapbase1 = res[CH_L]->start;
+	p->mapbase2 = res[CH_H]->start;
+
+	p->cs.name = pdev->name;
+	p->cs.rating = 200;
+	p->cs.read = tpu_clocksource_read;
+	p->cs.enable = tpu_clocksource_enable;
+	p->cs.disable = tpu_clocksource_disable;
+	p->cs.mask = CLOCKSOURCE_MASK(sizeof(unsigned long) * 8);
+	p->cs.flags = CLOCK_SOURCE_IS_CONTINUOUS;
+	clocksource_register_hz(&p->cs, clk_get_rate(p->clk) / 64);
+	platform_set_drvdata(pdev, p);
+
+	return 0;
+}
+
+static int tpu_probe(struct platform_device *pdev)
+{
+	struct tpu_priv *p = platform_get_drvdata(pdev);
+
+	if (p) {
+		dev_info(&pdev->dev, "kept as earlytimer\n");
+		return 0;
+	}
+
+	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	return tpu_setup(p, pdev);
+}
+
+static int tpu_remove(struct platform_device *pdev)
+{
+	return -EBUSY;
+}
+
+static const struct of_device_id tpu_of_table[] = {
+	{ .compatible = "renesas,tpu" },
+	{ }
+};
+
+static struct platform_driver tpu_driver = {
+	.probe		= tpu_probe,
+	.remove		= tpu_remove,
+	.driver		= {
+		.name	= "h8s-tpu",
+		.of_match_table = of_match_ptr(tpu_of_table),
+	}
+};
+
+static int __init tpu_init(void)
+{
+	return platform_driver_register(&tpu_driver);
+}
+
+static void __exit tpu_exit(void)
+{
+	platform_driver_unregister(&tpu_driver);
+}
+
+subsys_initcall(tpu_init);
+module_exit(tpu_exit);
+MODULE_AUTHOR("Yoshinori Sato");
+MODULE_DESCRIPTION("H8S Timer Pulse Unit Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c
index 098c542e5c53..cba2d015564c 100644
--- a/drivers/clocksource/qcom-timer.c
+++ b/drivers/clocksource/qcom-timer.c
@@ -40,8 +40,6 @@
 
 #define GPT_HZ 32768
 
-#define MSM_DGT_SHIFT 5
-
 static void __iomem *event_base;
 static void __iomem *sts_base;
 
@@ -232,7 +230,6 @@ err:
 	register_current_timer_delay(&msm_delay_timer);
 }
 
-#ifdef CONFIG_ARCH_QCOM
 static void __init msm_dt_timer_init(struct device_node *np)
 {
 	u32 freq;
@@ -285,59 +282,3 @@ static void __init msm_dt_timer_init(struct device_node *np)
 }
 CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
 CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
-#else
-
-static int __init msm_timer_map(phys_addr_t addr, u32 event, u32 source,
-				u32 sts)
-{
-	void __iomem *base;
-
-	base = ioremap(addr, SZ_256);
-	if (!base) {
-		pr_err("Failed to map timer base\n");
-		return -ENOMEM;
-	}
-	event_base = base + event;
-	source_base = base + source;
-	if (sts)
-		sts_base = base + sts;
-
-	return 0;
-}
-
-static notrace cycle_t msm_read_timer_count_shift(struct clocksource *cs)
-{
-	/*
-	 * Shift timer count down by a constant due to unreliable lower bits
-	 * on some targets.
-	 */
-	return msm_read_timer_count(cs) >> MSM_DGT_SHIFT;
-}
-
-void __init msm7x01_timer_init(void)
-{
-	struct clocksource *cs = &msm_clocksource;
-
-	if (msm_timer_map(0xc0100000, 0x0, 0x10, 0x0))
-		return;
-	cs->read = msm_read_timer_count_shift;
-	cs->mask = CLOCKSOURCE_MASK((32 - MSM_DGT_SHIFT));
-	/* 600 KHz */
-	msm_timer_init(19200000 >> MSM_DGT_SHIFT, 32 - MSM_DGT_SHIFT, 7,
-			false);
-}
-
-void __init msm7x30_timer_init(void)
-{
-	if (msm_timer_map(0xc0100000, 0x4, 0x24, 0x80))
-		return;
-	msm_timer_init(24576000 / 4, 32, 1, false);
-}
-
-void __init qsd8x50_timer_init(void)
-{
-	if (msm_timer_map(0xAC100000, 0x0, 0x10, 0x34))
-		return;
-	msm_timer_init(19200000 / 4, 32, 7, false);
-}
-#endif
diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c
new file mode 100644
index 000000000000..a1c06a2bc77c
--- /dev/null
+++ b/drivers/clocksource/time-lpc32xx.c
@@ -0,0 +1,272 @@
+/*
+ * Clocksource driver for NXP LPC32xx/18xx/43xx timer
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * Based on:
+ * time-efm32 Copyright (C) 2013 Pengutronix
+ * mach-lpc32xx/timer.c Copyright (C) 2009 - 2010 NXP Semiconductors
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+
+#define LPC32XX_TIMER_IR		0x000
+#define  LPC32XX_TIMER_IR_MR0INT	BIT(0)
+#define LPC32XX_TIMER_TCR		0x004
+#define  LPC32XX_TIMER_TCR_CEN		BIT(0)
+#define  LPC32XX_TIMER_TCR_CRST		BIT(1)
+#define LPC32XX_TIMER_TC		0x008
+#define LPC32XX_TIMER_PR		0x00c
+#define LPC32XX_TIMER_MCR		0x014
+#define  LPC32XX_TIMER_MCR_MR0I		BIT(0)
+#define  LPC32XX_TIMER_MCR_MR0R		BIT(1)
+#define  LPC32XX_TIMER_MCR_MR0S		BIT(2)
+#define LPC32XX_TIMER_MR0		0x018
+#define LPC32XX_TIMER_CTCR		0x070
+
+struct lpc32xx_clock_event_ddata {
+	struct clock_event_device evtdev;
+	void __iomem *base;
+};
+
+/* Needed for the sched clock */
+static void __iomem *clocksource_timer_counter;
+
+static u64 notrace lpc32xx_read_sched_clock(void)
+{
+	return readl(clocksource_timer_counter);
+}
+
+static int lpc32xx_clkevt_next_event(unsigned long delta,
+				     struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/*
+	 * Place timer in reset and program the delta in the prescale
+	 * register (PR). When the prescale counter matches the value
+	 * in PR the counter register is incremented and the compare
+	 * match will trigger. After setup the timer is released from
+	 * reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, ddata->base + LPC32XX_TIMER_TCR);
+	writel_relaxed(delta, ddata->base + LPC32XX_TIMER_PR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_shutdown(struct clock_event_device *evtdev)
+{
+	struct lpc32xx_clock_event_ddata *ddata =
+		container_of(evtdev, struct lpc32xx_clock_event_ddata, evtdev);
+
+	/* Disable the timer */
+	writel_relaxed(0, ddata->base + LPC32XX_TIMER_TCR);
+
+	return 0;
+}
+
+static int lpc32xx_clkevt_oneshot(struct clock_event_device *evtdev)
+{
+	/*
+	 * When using oneshot, we must also disable the timer
+	 * to wait for the first call to set_next_event().
+	 */
+	return lpc32xx_clkevt_shutdown(evtdev);
+}
+
+static irqreturn_t lpc32xx_clock_event_handler(int irq, void *dev_id)
+{
+	struct lpc32xx_clock_event_ddata *ddata = dev_id;
+
+	/* Clear match on channel 0 */
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, ddata->base + LPC32XX_TIMER_IR);
+
+	ddata->evtdev.event_handler(&ddata->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct lpc32xx_clock_event_ddata lpc32xx_clk_event_ddata = {
+	.evtdev = {
+		.name			= "lpc3220 clockevent",
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.rating			= 300,
+		.set_next_event		= lpc32xx_clkevt_next_event,
+		.set_state_shutdown	= lpc32xx_clkevt_shutdown,
+		.set_state_oneshot	= lpc32xx_clkevt_oneshot,
+	},
+};
+
+static int __init lpc32xx_clocksource_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	/*
+	 * Disable and reset timer then set it to free running timer
+	 * mode (CTCR) with no prescaler (PR) or match operations (MCR).
+	 * After setup the timer is released from reset and enabled.
+	 */
+	writel_relaxed(LPC32XX_TIMER_TCR_CRST, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_PR);
+	writel_relaxed(0, base + LPC32XX_TIMER_MCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_TCR_CEN, base + LPC32XX_TIMER_TCR);
+
+	rate = clk_get_rate(clk);
+	ret = clocksource_mmio_init(base + LPC32XX_TIMER_TC, "lpc3220 timer",
+				    rate, 300, 32, clocksource_mmio_readl_up);
+	if (ret) {
+		pr_err("failed to init clocksource (%d)\n", ret);
+		goto err_clocksource_init;
+	}
+
+	clocksource_timer_counter = base + LPC32XX_TIMER_TC;
+	sched_clock_register(lpc32xx_read_sched_clock, 32, rate);
+
+	return 0;
+
+err_clocksource_init:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+static int __init lpc32xx_clockevent_init(struct device_node *np)
+{
+	void __iomem *base;
+	unsigned long rate;
+	struct clk *clk;
+	int ret, irq;
+
+	clk = of_clk_get_by_name(np, "timerclk");
+	if (IS_ERR(clk)) {
+		pr_err("clock get failed (%lu)\n", PTR_ERR(clk));
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("clock enable failed (%d)\n", ret);
+		goto err_clk_enable;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("unable to map registers\n");
+		ret = -EADDRNOTAVAIL;
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("get irq failed\n");
+		ret = -ENOENT;
+		goto err_irq;
+	}
+
+	/*
+	 * Disable timer and clear any pending interrupt (IR) on match
+	 * channel 0 (MR0). Configure a compare match value of 1 on MR0
+	 * and enable interrupt, reset on match and stop on match (MCR).
+	 */
+	writel_relaxed(0, base + LPC32XX_TIMER_TCR);
+	writel_relaxed(0, base + LPC32XX_TIMER_CTCR);
+	writel_relaxed(LPC32XX_TIMER_IR_MR0INT, base + LPC32XX_TIMER_IR);
+	writel_relaxed(1, base + LPC32XX_TIMER_MR0);
+	writel_relaxed(LPC32XX_TIMER_MCR_MR0I | LPC32XX_TIMER_MCR_MR0R |
+		       LPC32XX_TIMER_MCR_MR0S, base + LPC32XX_TIMER_MCR);
+
+	rate = clk_get_rate(clk);
+	lpc32xx_clk_event_ddata.base = base;
+	clockevents_config_and_register(&lpc32xx_clk_event_ddata.evtdev,
+					rate, 1, -1);
+
+	ret = request_irq(irq, lpc32xx_clock_event_handler,
+			  IRQF_TIMER | IRQF_IRQPOLL, "lpc3220 clockevent",
+			  &lpc32xx_clk_event_ddata);
+	if (ret) {
+		pr_err("request irq failed\n");
+		goto err_irq;
+	}
+
+	return 0;
+
+err_irq:
+	iounmap(base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+	return ret;
+}
+
+/*
+ * This function asserts that we have exactly one clocksource and one
+ * clock_event_device in the end.
+ */
+static void __init lpc32xx_timer_init(struct device_node *np)
+{
+	static int has_clocksource, has_clockevent;
+	int ret;
+
+	if (!has_clocksource) {
+		ret = lpc32xx_clocksource_init(np);
+		if (!ret) {
+			has_clocksource = 1;
+			return;
+		}
+	}
+
+	if (!has_clockevent) {
+		ret = lpc32xx_clockevent_init(np);
+		if (!ret) {
+			has_clockevent = 1;
+			return;
+		}
+	}
+}
+CLOCKSOURCE_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init);
diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c
index b9efd30513d5..c97d1980c0f8 100644
--- a/drivers/clocksource/timer-integrator-ap.c
+++ b/drivers/clocksource/timer-integrator-ap.c
@@ -166,7 +166,7 @@ static void __init integrator_ap_timer_init_of(struct device_node *node)
 	struct device_node *sec_node;
 
 	base = of_io_request_and_map(node, 0, "integrator-timer");
-	if (!base)
+	if (IS_ERR(base))
 		return;
 
 	clk = of_clk_get(node, 0);
diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c
new file mode 100644
index 000000000000..a97e8b50701c
--- /dev/null
+++ b/drivers/clocksource/timer-stm32.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) Maxime Coquelin 2015
+ * Author:  Maxime Coquelin <mcoquelin.stm32@gmail.com>
+ * License terms:  GNU General Public License (GPL), version 2
+ *
+ * Inspired by time-efm32.c from Uwe Kleine-Koenig
+ */
+
+#include <linux/kernel.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+
+#define TIM_CR1		0x00
+#define TIM_DIER	0x0c
+#define TIM_SR		0x10
+#define TIM_EGR		0x14
+#define TIM_PSC		0x28
+#define TIM_ARR		0x2c
+
+#define TIM_CR1_CEN	BIT(0)
+#define TIM_CR1_OPM	BIT(3)
+#define TIM_CR1_ARPE	BIT(7)
+
+#define TIM_DIER_UIE	BIT(0)
+
+#define TIM_SR_UIF	BIT(0)
+
+#define TIM_EGR_UG	BIT(0)
+
+struct stm32_clock_event_ddata {
+	struct clock_event_device evtdev;
+	unsigned periodic_top;
+	void __iomem *base;
+};
+
+static void stm32_clock_event_set_mode(enum clock_event_mode mode,
+				       struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+	void *base = data->base;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		writel_relaxed(data->periodic_top, base + TIM_ARR);
+		writel_relaxed(TIM_CR1_ARPE | TIM_CR1_CEN, base + TIM_CR1);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+	default:
+		writel_relaxed(0, base + TIM_CR1);
+		break;
+	}
+}
+
+static int stm32_clock_event_set_next_event(unsigned long evt,
+					    struct clock_event_device *evtdev)
+{
+	struct stm32_clock_event_ddata *data =
+		container_of(evtdev, struct stm32_clock_event_ddata, evtdev);
+
+	writel_relaxed(evt, data->base + TIM_ARR);
+	writel_relaxed(TIM_CR1_ARPE | TIM_CR1_OPM | TIM_CR1_CEN,
+		       data->base + TIM_CR1);
+
+	return 0;
+}
+
+static irqreturn_t stm32_clock_event_handler(int irq, void *dev_id)
+{
+	struct stm32_clock_event_ddata *data = dev_id;
+
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->evtdev.event_handler(&data->evtdev);
+
+	return IRQ_HANDLED;
+}
+
+static struct stm32_clock_event_ddata clock_event_ddata = {
+	.evtdev = {
+		.name = "stm32 clockevent",
+		.features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
+		.set_mode = stm32_clock_event_set_mode,
+		.set_next_event = stm32_clock_event_set_next_event,
+		.rating = 200,
+	},
+};
+
+static void __init stm32_clockevent_init(struct device_node *np)
+{
+	struct stm32_clock_event_ddata *data = &clock_event_ddata;
+	struct clk *clk;
+	struct reset_control *rstc;
+	unsigned long rate, max_delta;
+	int irq, ret, bits, prescaler = 1;
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		pr_err("failed to get clock for clockevent (%d)\n", ret);
+		goto err_clk_get;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		pr_err("failed to enable timer clock for clockevent (%d)\n",
+		       ret);
+		goto err_clk_enable;
+	}
+
+	rate = clk_get_rate(clk);
+
+	rstc = of_reset_control_get(np, NULL);
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		reset_control_deassert(rstc);
+	}
+
+	data->base = of_iomap(np, 0);
+	if (!data->base) {
+		pr_err("failed to map registers for clockevent\n");
+		goto err_iomap;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("%s: failed to get irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	/* Detect whether the timer is 16 or 32 bits */
+	writel_relaxed(~0U, data->base + TIM_ARR);
+	max_delta = readl_relaxed(data->base + TIM_ARR);
+	if (max_delta == ~0U) {
+		prescaler = 1;
+		bits = 32;
+	} else {
+		prescaler = 1024;
+		bits = 16;
+	}
+	writel_relaxed(0, data->base + TIM_ARR);
+
+	writel_relaxed(prescaler - 1, data->base + TIM_PSC);
+	writel_relaxed(TIM_EGR_UG, data->base + TIM_EGR);
+	writel_relaxed(TIM_DIER_UIE, data->base + TIM_DIER);
+	writel_relaxed(0, data->base + TIM_SR);
+
+	data->periodic_top = DIV_ROUND_CLOSEST(rate, prescaler * HZ);
+
+	clockevents_config_and_register(&data->evtdev,
+					DIV_ROUND_CLOSEST(rate, prescaler),
+					0x1, max_delta);
+
+	ret = request_irq(irq, stm32_clock_event_handler, IRQF_TIMER,
+			"stm32 clockevent", data);
+	if (ret) {
+		pr_err("%s: failed to request irq.\n", np->full_name);
+		goto err_get_irq;
+	}
+
+	pr_info("%s: STM32 clockevent driver initialized (%d bits)\n",
+			np->full_name, bits);
+
+	return;
+
+err_get_irq:
+	iounmap(data->base);
+err_iomap:
+	clk_disable_unprepare(clk);
+err_clk_enable:
+	clk_put(clk);
+err_clk_get:
+	return;
+}
+
+CLOCKSOURCE_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init);
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 28aa4b7bb602..0ffb4ea7c925 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -324,7 +324,7 @@ static void __init sun5i_timer_init(struct device_node *node)
 	int irq;
 
 	timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
-	if (!timer_base)
+	if (IS_ERR(timer_base))
 		panic("Can't map registers");
 
 	irq = irq_of_parse_and_map(node, 0);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 4f3dbc8cf729..611cb09239eb 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -5,7 +5,7 @@
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on (ARM_CPU_TOPOLOGY || ARM64) && HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index b0c18ed8d83f..0136dfcdabf0 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -699,13 +699,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	dmi_check_system(sw_any_bug_dmi_table);
 	if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
+		cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
 	}
 
 	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
 		cpumask_clear(policy->cpus);
 		cpumask_set_cpu(cpu, policy->cpus);
-		cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
+		cpumask_copy(data->freqdomain_cpus,
+			     topology_sibling_cpumask(cpu));
 		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
 		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
 	}
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index e1a6ba66a7f5..f1e42f8ce0fc 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
-#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
@@ -41,12 +40,16 @@
 #define MAX_CLUSTERS	2
 
 #ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
 static bool bL_switching_enabled;
 #define is_bL_switching_enabled()	bL_switching_enabled
 #define set_switching_enabled(x)	(bL_switching_enabled = (x))
 #else
 #define is_bL_switching_enabled()	false
 #define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
 #endif
 
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
@@ -186,6 +189,15 @@ bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
 		mutex_unlock(&cluster_lock[old_cluster]);
 	}
 
+	/*
+	 * FIXME: clk_set_rate has to handle the case where clk_change_rate
+	 * can fail due to hardware or firmware issues. Until the clk core
+	 * layer is fixed, we can check here. In most of the cases we will
+	 * be reading only the cached value anyway. This needs to  be removed
+	 * once clk core is fixed.
+	 */
+	if (bL_cpufreq_get_rate(cpu) != new_rate)
+		return -EIO;
 	return 0;
 }
 
@@ -322,7 +334,6 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
 	int ret;
 
 	if (freq_table[cluster])
@@ -342,8 +353,7 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		goto free_opp_table;
 	}
 
-	name[12] = cluster + '0';
-	clk[cluster] = clk_get(cpu_dev, name);
+	clk[cluster] = clk_get(cpu_dev, NULL);
 	if (!IS_ERR(clk[cluster])) {
 		dev_dbg(cpu_dev, "%s: clk: %p & freq table: %p, cluster: %d\n",
 				__func__, clk[cluster], freq_table[cluster],
@@ -506,6 +516,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.attr			= cpufreq_generic_attr,
 };
 
+#ifdef CONFIG_BL_SWITCHER
 static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
 					unsigned long action, void *_arg)
 {
@@ -538,6 +549,20 @@ static struct notifier_block bL_switcher_notifier = {
 	.notifier_call = bL_cpufreq_switcher_notifier,
 };
 
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
 	int ret, i;
@@ -555,8 +580,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
-	ret = bL_switcher_get_enabled();
-	set_switching_enabled(ret);
+	set_switching_enabled(bL_switcher_get_enabled());
 
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
@@ -567,7 +591,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		ret = __bLs_register_notifier();
 		if (ret) {
 			cpufreq_unregister_driver(&bL_cpufreq_driver);
 			arm_bL_ops = NULL;
@@ -591,7 +615,7 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 	}
 
 	bL_switcher_get_enabled();
-	bL_switcher_unregister_notifier(&bL_switcher_notifier);
+	__bLs_unregister_notifier();
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
 	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index bab67db54b7e..528a82bf5038 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -416,6 +416,7 @@ static struct platform_driver dt_cpufreq_platdrv = {
 };
 module_platform_driver(dt_cpufreq_platdrv);
 
+MODULE_ALIAS("platform:cpufreq-dt");
 MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
 MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
 MODULE_DESCRIPTION("Generic cpufreq driver");
diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index a2258090b58b..db69eeb501a7 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -414,7 +414,7 @@ static int nforce2_detect_chipset(void)
  * nforce2_init - initializes the nForce2 CPUFreq driver
  *
  * Initializes the nForce2 FSB support. Returns -ENODEV on unsupported
- * devices, -EINVAL on problems during initiatization, and zero on
+ * devices, -EINVAL on problems during initialization, and zero on
  * success.
  */
 static int __init nforce2_init(void)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 8ae655c364f4..b612411655f9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -31,10 +31,62 @@
 #include <linux/tick.h>
 #include <trace/events/power.h>
 
-/* Macros to iterate over lists */
-/* Iterate over online CPUs policies */
 static LIST_HEAD(cpufreq_policy_list);
-#define for_each_policy(__policy)				\
+
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
+static bool suitable_policy(struct cpufreq_policy *policy, bool active)
+{
+	return active == !policy_is_inactive(policy);
+}
+
+/* Finds Next Acive/Inactive policy */
+static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
+					  bool active)
+{
+	do {
+		policy = list_next_entry(policy, policy_list);
+
+		/* No more policies in the list */
+		if (&policy->policy_list == &cpufreq_policy_list)
+			return NULL;
+	} while (!suitable_policy(policy, active));
+
+	return policy;
+}
+
+static struct cpufreq_policy *first_policy(bool active)
+{
+	struct cpufreq_policy *policy;
+
+	/* No policies in the list */
+	if (list_empty(&cpufreq_policy_list))
+		return NULL;
+
+	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
+				  policy_list);
+
+	if (!suitable_policy(policy, active))
+		policy = next_policy(policy, active);
+
+	return policy;
+}
+
+/* Macros to iterate over CPU policies */
+#define for_each_suitable_policy(__policy, __active)	\
+	for (__policy = first_policy(__active);		\
+	     __policy;					\
+	     __policy = next_policy(__policy, __active))
+
+#define for_each_active_policy(__policy)		\
+	for_each_suitable_policy(__policy, true)
+#define for_each_inactive_policy(__policy)		\
+	for_each_suitable_policy(__policy, false)
+
+#define for_each_policy(__policy)			\
 	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)
 
 /* Iterate over governors */
@@ -49,13 +101,9 @@ static LIST_HEAD(cpufreq_governor_list);
  */
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
-static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 DEFINE_MUTEX(cpufreq_governor_lock);
 
-/* This one keeps track of the previously set governor of a removed CPU */
-static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
-
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -178,7 +226,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 	policy->cpuinfo.transition_latency = transition_latency;
 
 	/*
-	 * The driver only supports the SMP configuartion where all processors
+	 * The driver only supports the SMP configuration where all processors
 	 * share the clock and voltage and clock.
 	 */
 	cpumask_setall(policy->cpus);
@@ -187,10 +235,18 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
-unsigned int cpufreq_generic_get(unsigned int cpu)
+/* Only for cpufreq core internal use */
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
+	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
+}
+
+unsigned int cpufreq_generic_get(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+
 	if (!policy || IS_ERR(policy->clk)) {
 		pr_err("%s: No %s associated to cpu: %d\n",
 		       __func__, policy ? "clk" : "policy", cpu);
@@ -201,18 +257,29 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_get);
 
-/* Only for cpufreq core internal use */
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
-{
-	return per_cpu(cpufreq_cpu_data, cpu);
-}
-
+/**
+ * cpufreq_cpu_get: returns policy for a cpu and marks it busy.
+ *
+ * @cpu: cpu to find policy for.
+ *
+ * This returns policy for 'cpu', returns NULL if it doesn't exist.
+ * It also increments the kobject reference count to mark it busy and so would
+ * require a corresponding call to cpufreq_cpu_put() to decrement it back.
+ * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
+ * freed as that depends on the kobj count.
+ *
+ * It also takes a read-lock of 'cpufreq_rwsem' and doesn't put it back if a
+ * valid policy is found. This is done to make sure the driver doesn't get
+ * unregistered while the policy is being used.
+ *
+ * Return: A valid policy on success, otherwise NULL on failure.
+ */
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
 	unsigned long flags;
 
-	if (cpu >= nr_cpu_ids)
+	if (WARN_ON(cpu >= nr_cpu_ids))
 		return NULL;
 
 	if (!down_read_trylock(&cpufreq_rwsem))
@@ -223,7 +290,7 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 
 	if (cpufreq_driver) {
 		/* get the CPU */
-		policy = per_cpu(cpufreq_cpu_data, cpu);
+		policy = cpufreq_cpu_get_raw(cpu);
 		if (policy)
 			kobject_get(&policy->kobj);
 	}
@@ -237,6 +304,16 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
 
+/**
+ * cpufreq_cpu_put: Decrements the usage count of a policy
+ *
+ * @policy: policy earlier returned by cpufreq_cpu_get().
+ *
+ * This decrements the kobject reference count incremented earlier by calling
+ * cpufreq_cpu_get().
+ *
+ * It also drops the read-lock of 'cpufreq_rwsem' taken at cpufreq_cpu_get().
+ */
 void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	kobject_put(&policy->kobj);
@@ -798,11 +875,18 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 	down_write(&policy->rwsem);
 
+	/* Updating inactive policies is invalid, so avoid doing that. */
+	if (unlikely(policy_is_inactive(policy))) {
+		ret = -EBUSY;
+		goto unlock_policy_rwsem;
+	}
+
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
 	else
 		ret = -EIO;
 
+unlock_policy_rwsem:
 	up_write(&policy->rwsem);
 
 	up_read(&cpufreq_rwsem);
@@ -873,28 +957,67 @@ void cpufreq_sysfs_remove_file(const struct attribute *attr)
 }
 EXPORT_SYMBOL(cpufreq_sysfs_remove_file);
 
-/* symlink affected CPUs */
+static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+{
+	struct device *cpu_dev;
+
+	pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);
+
+	if (!policy)
+		return 0;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return 0;
+
+	return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
+}
+
+static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+{
+	struct device *cpu_dev;
+
+	pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);
+
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return;
+
+	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
+}
+
+/* Add/remove symlinks for all related CPUs */
 static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
 
-	for_each_cpu(j, policy->cpus) {
-		struct device *cpu_dev;
-
-		if (j == policy->cpu)
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+		if (j == policy->kobj_cpu)
 			continue;
 
-		pr_debug("Adding link for CPU: %u\n", j);
-		cpu_dev = get_cpu_device(j);
-		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					"cpufreq");
+		ret = add_cpu_dev_symlink(policy, j);
 		if (ret)
 			break;
 	}
+
 	return ret;
 }
 
+static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
+{
+	unsigned int j;
+
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+		if (j == policy->kobj_cpu)
+			continue;
+
+		remove_cpu_dev_symlink(policy, j);
+	}
+}
+
 static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 				     struct device *dev)
 {
@@ -937,7 +1060,7 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)
 	memcpy(&new_policy, policy, sizeof(*policy));
 
 	/* Update governor of new_policy to the governor used before hotplug */
-	gov = find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu));
+	gov = find_governor(policy->last_governor);
 	if (gov)
 		pr_debug("Restoring governor %s for cpu %d\n",
 				policy->governor->name, policy->cpu);
@@ -963,7 +1086,10 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 				  unsigned int cpu, struct device *dev)
 {
 	int ret = 0;
-	unsigned long flags;
+
+	/* Has this CPU been taken care of already? */
+	if (cpumask_test_cpu(cpu, policy->cpus))
+		return 0;
 
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
@@ -974,13 +1100,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	}
 
 	down_write(&policy->rwsem);
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-
 	cpumask_set_cpu(cpu, policy->cpus);
-	per_cpu(cpufreq_cpu_data, cpu) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	up_write(&policy->rwsem);
 
 	if (has_target()) {
@@ -994,7 +1114,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 		}
 	}
 
-	return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+	return 0;
 }
 
 static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
@@ -1003,20 +1123,25 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
 	unsigned long flags;
 
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
-
-	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
-
+	policy = per_cpu(cpufreq_cpu_data, cpu);
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (policy)
-		policy->governor = NULL;
+	if (likely(policy)) {
+		/* Policy should be inactive here */
+		WARN_ON(!policy_is_inactive(policy));
+
+		down_write(&policy->rwsem);
+		policy->cpu = cpu;
+		up_write(&policy->rwsem);
+	}
 
 	return policy;
 }
 
-static struct cpufreq_policy *cpufreq_policy_alloc(void)
+static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
@@ -1028,6 +1153,13 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj,
+				   "cpufreq");
+	if (ret) {
+		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		goto err_free_rcpumask;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1035,8 +1167,15 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
+	policy->cpu = dev->id;
+
+	/* Set this once on allocation */
+	policy->kobj_cpu = dev->id;
+
 	return policy;
 
+err_free_rcpumask:
+	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
 	free_cpumask_var(policy->cpus);
 err_free_policy:
@@ -1045,18 +1184,20 @@ err_free_policy:
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 {
 	struct kobject *kobj;
 	struct completion *cmp;
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_REMOVE_POLICY, policy);
+	if (notify)
+		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+					     CPUFREQ_REMOVE_POLICY, policy);
 
-	down_read(&policy->rwsem);
+	down_write(&policy->rwsem);
+	cpufreq_remove_dev_symlink(policy);
 	kobj = &policy->kobj;
 	cmp = &policy->kobj_unregister;
-	up_read(&policy->rwsem);
+	up_write(&policy->rwsem);
 	kobject_put(kobj);
 
 	/*
@@ -1069,68 +1210,64 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
 	pr_debug("wait complete\n");
 }
 
-static void cpufreq_policy_free(struct cpufreq_policy *policy)
-{
-	free_cpumask_var(policy->related_cpus);
-	free_cpumask_var(policy->cpus);
-	kfree(policy);
-}
-
-static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu,
-			     struct device *cpu_dev)
+static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 {
-	int ret;
-
-	if (WARN_ON(cpu == policy->cpu))
-		return 0;
+	unsigned long flags;
+	int cpu;
 
-	/* Move kobject to the new policy->cpu */
-	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
-	if (ret) {
-		pr_err("%s: Failed to move kobj: %d\n", __func__, ret);
-		return ret;
-	}
+	/* Remove policy from list */
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	list_del(&policy->policy_list);
 
-	down_write(&policy->rwsem);
-	policy->cpu = cpu;
-	up_write(&policy->rwsem);
+	for_each_cpu(cpu, policy->related_cpus)
+		per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	return 0;
+	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->related_cpus);
+	free_cpumask_var(policy->cpus);
+	kfree(policy);
 }
 
-static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+/**
+ * cpufreq_add_dev - add a CPU device
+ *
+ * Adds the cpufreq interface for a CPU device.
+ *
+ * The Oracle says: try running cpufreq registration/unregistration concurrently
+ * with with cpu hotplugging and all hell will break loose. Tried to clean this
+ * mess up, but more thorough testing is needed. - Mathieu
+ */
+static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int j, cpu = dev->id;
 	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
-	bool recover_policy = cpufreq_suspended;
-
-	if (cpu_is_offline(cpu))
-		return 0;
+	bool recover_policy = !sif;
 
 	pr_debug("adding CPU %u\n", cpu);
 
-	/* check whether a different CPU already registered this
-	 * CPU because it is in the same boat. */
-	policy = cpufreq_cpu_get_raw(cpu);
-	if (unlikely(policy))
-		return 0;
+	/*
+	 * Only possible if 'cpu' wasn't physically present earlier and we are
+	 * here from subsys_interface add callback. A hotplug notifier will
+	 * follow and we will handle it like logical CPU hotplug then. For now,
+	 * just create the sysfs link.
+	 */
+	if (cpu_is_offline(cpu))
+		return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu);
 
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
 
-	/* Check if this cpu was hot-unplugged earlier and has siblings */
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_policy(policy) {
-		if (cpumask_test_cpu(cpu, policy->related_cpus)) {
-			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-			ret = cpufreq_add_policy_cpu(policy, cpu, dev);
-			up_read(&cpufreq_rwsem);
-			return ret;
-		}
+	/* Check if this CPU already has a policy to manage it */
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+	if (policy && !policy_is_inactive(policy)) {
+		WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus));
+		ret = cpufreq_add_policy_cpu(policy, cpu, dev);
+		up_read(&cpufreq_rwsem);
+		return ret;
 	}
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	/*
 	 * Restore the saved policy when doing light-weight init and fall back
@@ -1139,22 +1276,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL;
 	if (!policy) {
 		recover_policy = false;
-		policy = cpufreq_policy_alloc();
+		policy = cpufreq_policy_alloc(dev);
 		if (!policy)
 			goto nomem_out;
 	}
 
-	/*
-	 * In the resume path, since we restore a saved policy, the assignment
-	 * to policy->cpu is like an update of the existing policy, rather than
-	 * the creation of a brand new one. So we need to perform this update
-	 * by invoking update_policy_cpu().
-	 */
-	if (recover_policy && cpu != policy->cpu)
-		WARN_ON(update_policy_cpu(policy, cpu, dev));
-	else
-		policy->cpu = cpu;
-
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	/* call driver. From then on the cpufreq must be able
@@ -1181,21 +1307,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		policy->user_policy.min = policy->min;
 		policy->user_policy.max = policy->max;
 
-		/* prepare interface data */
-		ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
-					   &dev->kobj, "cpufreq");
-		if (ret) {
-			pr_err("%s: failed to init policy->kobj: %d\n",
-			       __func__, ret);
-			goto err_init_policy_kobj;
-		}
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		for_each_cpu(j, policy->related_cpus)
+			per_cpu(cpufreq_cpu_data, j) = policy;
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
@@ -1253,11 +1370,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 			goto err_out_unregister;
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
-	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	list_add(&policy->policy_list, &cpufreq_policy_list);
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		list_add(&policy->policy_list, &cpufreq_policy_list);
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	}
 
 	cpufreq_init_policy(policy);
 
@@ -1281,68 +1398,28 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 err_out_unregister:
 err_get_freq:
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	if (!recover_policy) {
-		kobject_put(&policy->kobj);
-		wait_for_completion(&policy->kobj_unregister);
-	}
-err_init_policy_kobj:
 	up_write(&policy->rwsem);
 
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 err_set_policy_cpu:
-	if (recover_policy) {
-		/* Do not leave stale fallback data behind. */
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
-		cpufreq_policy_put_kobj(policy);
-	}
-	cpufreq_policy_free(policy);
-
+	cpufreq_policy_free(policy, recover_policy);
 nomem_out:
 	up_read(&cpufreq_rwsem);
 
 	return ret;
 }
 
-/**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
- */
-static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
-{
-	return __cpufreq_add_dev(dev, sif);
-}
-
 static int __cpufreq_remove_dev_prepare(struct device *dev,
 					struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id, cpus;
-	int ret;
-	unsigned long flags;
+	unsigned int cpu = dev->id;
+	int ret = 0;
 	struct cpufreq_policy *policy;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	/* Save the policy somewhere when doing a light-weight tear-down */
-	if (cpufreq_suspended)
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
-
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
+	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
@@ -1354,108 +1431,75 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 			pr_err("%s: Failed to stop governor\n", __func__);
 			return ret;
 		}
-
-		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
-			policy->governor->name, CPUFREQ_NAME_LEN);
 	}
 
-	down_read(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-	up_read(&policy->rwsem);
+	down_write(&policy->rwsem);
+	cpumask_clear_cpu(cpu, policy->cpus);
 
-	if (cpu != policy->cpu) {
-		sysfs_remove_link(&dev->kobj, "cpufreq");
-	} else if (cpus > 1) {
+	if (policy_is_inactive(policy)) {
+		if (has_target())
+			strncpy(policy->last_governor, policy->governor->name,
+				CPUFREQ_NAME_LEN);
+	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
-		int new_cpu = cpumask_any_but(policy->cpus, cpu);
-		struct device *cpu_dev = get_cpu_device(new_cpu);
+		policy->cpu = cpumask_any(policy->cpus);
+	}
+	up_write(&policy->rwsem);
 
-		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-		ret = update_policy_cpu(policy, new_cpu, cpu_dev);
-		if (ret) {
-			if (sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					      "cpufreq"))
-				pr_err("%s: Failed to restore kobj link to cpu:%d\n",
-				       __func__, cpu_dev->id);
-			return ret;
-		}
+	/* Start governor again for active policy */
+	if (!policy_is_inactive(policy)) {
+		if (has_target()) {
+			ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (!cpufreq_suspended)
-			pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-				 __func__, new_cpu, cpu);
+			if (ret)
+				pr_err("%s: Failed to start governor\n", __func__);
+		}
 	} else if (cpufreq_driver->stop_cpu) {
 		cpufreq_driver->stop_cpu(policy);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int __cpufreq_remove_dev_finish(struct device *dev,
 				       struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id, cpus;
+	unsigned int cpu = dev->id;
 	int ret;
-	unsigned long flags;
-	struct cpufreq_policy *policy;
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
 	}
 
-	down_write(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-
-	if (cpus > 1)
-		cpumask_clear_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
+	/* Only proceed for inactive policies */
+	if (!policy_is_inactive(policy))
+		return 0;
 
 	/* If cpu is last user of policy, free policy */
-	if (cpus == 1) {
-		if (has_target()) {
-			ret = __cpufreq_governor(policy,
-					CPUFREQ_GOV_POLICY_EXIT);
-			if (ret) {
-				pr_err("%s: Failed to exit governor\n",
-				       __func__);
-				return ret;
-			}
-		}
-
-		if (!cpufreq_suspended)
-			cpufreq_policy_put_kobj(policy);
-
-		/*
-		 * Perform the ->exit() even during light-weight tear-down,
-		 * since this is a core component, and is essential for the
-		 * subsequent light-weight ->init() to succeed.
-		 */
-		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(policy);
-
-		/* Remove policy from list of active policies */
-		write_lock_irqsave(&cpufreq_driver_lock, flags);
-		list_del(&policy->policy_list);
-		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-		if (!cpufreq_suspended)
-			cpufreq_policy_free(policy);
-	} else if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
-		if (!ret)
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-
+	if (has_target()) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		if (ret) {
-			pr_err("%s: Failed to start governor\n", __func__);
+			pr_err("%s: Failed to exit governor\n", __func__);
 			return ret;
 		}
 	}
 
+	/*
+	 * Perform the ->exit() even during light-weight tear-down,
+	 * since this is a core component, and is essential for the
+	 * subsequent light-weight ->init() to succeed.
+	 */
+	if (cpufreq_driver->exit)
+		cpufreq_driver->exit(policy);
+
+	/* Free the policy only if the driver is getting removed. */
+	if (sif)
+		cpufreq_policy_free(policy, true);
+
 	return 0;
 }
 
@@ -1469,8 +1513,33 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	unsigned int cpu = dev->id;
 	int ret;
 
-	if (cpu_is_offline(cpu))
+	/*
+	 * Only possible if 'cpu' is getting physically removed now. A hotplug
+	 * notifier should have already been called and we just need to remove
+	 * link or free policy here.
+	 */
+	if (cpu_is_offline(cpu)) {
+		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+		struct cpumask mask;
+
+		if (!policy)
+			return 0;
+
+		cpumask_copy(&mask, policy->related_cpus);
+		cpumask_clear_cpu(cpu, &mask);
+
+		/*
+		 * Free policy only if all policy->related_cpus are removed
+		 * physically.
+		 */
+		if (cpumask_intersects(&mask, cpu_present_mask)) {
+			remove_cpu_dev_symlink(policy, cpu);
+			return 0;
+		}
+
+		cpufreq_policy_free(policy, true);
 		return 0;
+	}
 
 	ret = __cpufreq_remove_dev_prepare(dev, sif);
 
@@ -1567,6 +1636,10 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
 
+	/* Updating inactive policies is invalid, so avoid doing that. */
+	if (unlikely(policy_is_inactive(policy)))
+		return ret_freq;
+
 	if (ret_freq && policy->cur &&
 		!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
 		/* verify no discrepancy between actual and
@@ -1656,7 +1729,7 @@ void cpufreq_suspend(void)
 
 	pr_debug("%s: Suspending Governors\n", __func__);
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
 			pr_err("%s: Failed to stop governor for policy: %p\n",
 				__func__, policy);
@@ -1690,7 +1763,7 @@ void cpufreq_resume(void)
 
 	pr_debug("%s: Resuming Governors\n", __func__);
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
 			pr_err("%s: Failed to resume driver: %p\n", __func__,
 				policy);
@@ -1891,7 +1964,7 @@ static int __target_index(struct cpufreq_policy *policy,
 		 * Failed after setting to intermediate freq? Driver should have
 		 * reverted back to initial frequency and so should we. Check
 		 * here for intermediate_freq instead of get_intermediate, in
-		 * case we have't switched to intermediate freq at all.
+		 * case we haven't switched to intermediate freq at all.
 		 */
 		if (unlikely(retval && intermediate_freq)) {
 			freqs.old = intermediate_freq;
@@ -2092,7 +2165,8 @@ EXPORT_SYMBOL_GPL(cpufreq_register_governor);
 
 void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 {
-	int cpu;
+	struct cpufreq_policy *policy;
+	unsigned long flags;
 
 	if (!governor)
 		return;
@@ -2100,12 +2174,15 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 	if (cpufreq_disabled())
 		return;
 
-	for_each_present_cpu(cpu) {
-		if (cpu_online(cpu))
-			continue;
-		if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name))
-			strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0");
+	/* clear last_governor for all inactive policies */
+	read_lock_irqsave(&cpufreq_driver_lock, flags);
+	for_each_inactive_policy(policy) {
+		if (!strcmp(policy->last_governor, governor->name)) {
+			policy->governor = NULL;
+			strcpy(policy->last_governor, "\0");
+		}
 	}
+	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	mutex_lock(&cpufreq_governor_mutex);
 	list_del(&governor->governor_list);
@@ -2304,7 +2381,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 	if (dev) {
 		switch (action & ~CPU_TASKS_FROZEN) {
 		case CPU_ONLINE:
-			__cpufreq_add_dev(dev, NULL);
+			cpufreq_add_dev(dev, NULL);
 			break;
 
 		case CPU_DOWN_PREPARE:
@@ -2316,7 +2393,7 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 			break;
 
 		case CPU_DOWN_FAILED:
-			__cpufreq_add_dev(dev, NULL);
+			cpufreq_add_dev(dev, NULL);
 			break;
 		}
 	}
@@ -2336,7 +2413,7 @@ static int cpufreq_boost_set_sw(int state)
 	struct cpufreq_policy *policy;
 	int ret = -EINVAL;
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		freq_table = cpufreq_frequency_get_table(policy->cpu);
 		if (freq_table) {
 			ret = cpufreq_frequency_table_cpuinfo(policy,
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 25a70d06c5bf..c86a10c30912 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -148,6 +148,10 @@ static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	return 0;
 }
 
+static struct notifier_block cs_cpufreq_notifier_block = {
+	.notifier_call = dbs_cpufreq_notifier,
+};
+
 /************************** sysfs interface ************************/
 static struct common_dbs_data cs_dbs_cdata;
 
@@ -317,7 +321,7 @@ static struct attribute_group cs_attr_group_gov_pol = {
 
 /************************** sysfs end ************************/
 
-static int cs_init(struct dbs_data *dbs_data)
+static int cs_init(struct dbs_data *dbs_data, bool notify)
 {
 	struct cs_dbs_tuners *tuners;
 
@@ -336,25 +340,25 @@ static int cs_init(struct dbs_data *dbs_data)
 	dbs_data->tuners = tuners;
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 		jiffies_to_usecs(10);
-	mutex_init(&dbs_data->mutex);
+
+	if (notify)
+		cpufreq_register_notifier(&cs_cpufreq_notifier_block,
+					  CPUFREQ_TRANSITION_NOTIFIER);
+
 	return 0;
 }
 
-static void cs_exit(struct dbs_data *dbs_data)
+static void cs_exit(struct dbs_data *dbs_data, bool notify)
 {
+	if (notify)
+		cpufreq_unregister_notifier(&cs_cpufreq_notifier_block,
+					    CPUFREQ_TRANSITION_NOTIFIER);
+
 	kfree(dbs_data->tuners);
 }
 
 define_get_cpu_dbs_routines(cs_cpu_dbs_info);
 
-static struct notifier_block cs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier,
-};
-
-static struct cs_ops cs_ops = {
-	.notifier_block = &cs_cpufreq_notifier_block,
-};
-
 static struct common_dbs_data cs_dbs_cdata = {
 	.governor = GOV_CONSERVATIVE,
 	.attr_group_gov_sys = &cs_attr_group_gov_sys,
@@ -363,9 +367,9 @@ static struct common_dbs_data cs_dbs_cdata = {
 	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
 	.gov_dbs_timer = cs_dbs_timer,
 	.gov_check_cpu = cs_check_cpu,
-	.gov_ops = &cs_ops,
 	.init = cs_init,
 	.exit = cs_exit,
+	.mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex),
 };
 
 static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 1b44496b2d2b..57a39f8a92b7 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -239,211 +239,242 @@ static void set_sampling_rate(struct dbs_data *dbs_data,
 	}
 }
 
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		struct common_dbs_data *cdata, unsigned int event)
+static int cpufreq_governor_init(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data,
+				 struct common_dbs_data *cdata)
 {
-	struct dbs_data *dbs_data;
-	struct od_cpu_dbs_info_s *od_dbs_info = NULL;
-	struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
-	struct od_ops *od_ops = NULL;
-	struct od_dbs_tuners *od_tuners = NULL;
-	struct cs_dbs_tuners *cs_tuners = NULL;
-	struct cpu_dbs_common_info *cpu_cdbs;
-	unsigned int sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
-	int io_busy = 0;
-	int rc;
-
-	if (have_governor_per_policy())
-		dbs_data = policy->governor_data;
-	else
-		dbs_data = cdata->gdbs_data;
-
-	WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT));
-
-	switch (event) {
-	case CPUFREQ_GOV_POLICY_INIT:
-		if (have_governor_per_policy()) {
-			WARN_ON(dbs_data);
-		} else if (dbs_data) {
-			dbs_data->usage_count++;
-			policy->governor_data = dbs_data;
-			return 0;
-		}
-
-		dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
-		if (!dbs_data) {
-			pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
-			return -ENOMEM;
-		}
+	unsigned int latency;
+	int ret;
 
-		dbs_data->cdata = cdata;
-		dbs_data->usage_count = 1;
-		rc = cdata->init(dbs_data);
-		if (rc) {
-			pr_err("%s: POLICY_INIT: init() failed\n", __func__);
-			kfree(dbs_data);
-			return rc;
-		}
+	if (dbs_data) {
+		if (WARN_ON(have_governor_per_policy()))
+			return -EINVAL;
+		dbs_data->usage_count++;
+		policy->governor_data = dbs_data;
+		return 0;
+	}
 
-		if (!have_governor_per_policy())
-			WARN_ON(cpufreq_get_global_kobject());
+	dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
+	if (!dbs_data)
+		return -ENOMEM;
 
-		rc = sysfs_create_group(get_governor_parent_kobj(policy),
-				get_sysfs_attr(dbs_data));
-		if (rc) {
-			cdata->exit(dbs_data);
-			kfree(dbs_data);
-			return rc;
-		}
+	dbs_data->cdata = cdata;
+	dbs_data->usage_count = 1;
 
-		policy->governor_data = dbs_data;
+	ret = cdata->init(dbs_data, !policy->governor->initialized);
+	if (ret)
+		goto free_dbs_data;
 
-		/* policy latency is in ns. Convert it to us first */
-		latency = policy->cpuinfo.transition_latency / 1000;
-		if (latency == 0)
-			latency = 1;
+	/* policy latency is in ns. Convert it to us first */
+	latency = policy->cpuinfo.transition_latency / 1000;
+	if (latency == 0)
+		latency = 1;
 
-		/* Bring kernel and HW constraints together */
-		dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
-				MIN_LATENCY_MULTIPLIER * latency);
-		set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
+	/* Bring kernel and HW constraints together */
+	dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
+					  MIN_LATENCY_MULTIPLIER * latency);
+	set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
 					latency * LATENCY_MULTIPLIER));
 
-		if ((cdata->governor == GOV_CONSERVATIVE) &&
-				(!policy->governor->initialized)) {
-			struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
-
-			cpufreq_register_notifier(cs_ops->notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
+	if (!have_governor_per_policy()) {
+		if (WARN_ON(cpufreq_get_global_kobject())) {
+			ret = -EINVAL;
+			goto cdata_exit;
 		}
+		cdata->gdbs_data = dbs_data;
+	}
 
-		if (!have_governor_per_policy())
-			cdata->gdbs_data = dbs_data;
+	ret = sysfs_create_group(get_governor_parent_kobj(policy),
+				 get_sysfs_attr(dbs_data));
+	if (ret)
+		goto put_kobj;
 
-		return 0;
-	case CPUFREQ_GOV_POLICY_EXIT:
-		if (!--dbs_data->usage_count) {
-			sysfs_remove_group(get_governor_parent_kobj(policy),
-					get_sysfs_attr(dbs_data));
+	policy->governor_data = dbs_data;
 
-			if (!have_governor_per_policy())
-				cpufreq_put_global_kobject();
+	return 0;
 
-			if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
-				(policy->governor->initialized == 1)) {
-				struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
+put_kobj:
+	if (!have_governor_per_policy()) {
+		cdata->gdbs_data = NULL;
+		cpufreq_put_global_kobject();
+	}
+cdata_exit:
+	cdata->exit(dbs_data, !policy->governor->initialized);
+free_dbs_data:
+	kfree(dbs_data);
+	return ret;
+}
+
+static void cpufreq_governor_exit(struct cpufreq_policy *policy,
+				  struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
 
-				cpufreq_unregister_notifier(cs_ops->notifier_block,
-						CPUFREQ_TRANSITION_NOTIFIER);
-			}
+	policy->governor_data = NULL;
+	if (!--dbs_data->usage_count) {
+		sysfs_remove_group(get_governor_parent_kobj(policy),
+				   get_sysfs_attr(dbs_data));
 
-			cdata->exit(dbs_data);
-			kfree(dbs_data);
+		if (!have_governor_per_policy()) {
 			cdata->gdbs_data = NULL;
+			cpufreq_put_global_kobject();
 		}
 
-		policy->governor_data = NULL;
-		return 0;
+		cdata->exit(dbs_data, policy->governor->initialized == 1);
+		kfree(dbs_data);
 	}
+}
 
-	cpu_cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+static int cpufreq_governor_start(struct cpufreq_policy *policy,
+				  struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu;
+	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
+	int io_busy = 0;
+
+	if (!policy->cur)
+		return -EINVAL;
+
+	if (cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		cs_tuners = dbs_data->tuners;
-		cs_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
 		sampling_rate = cs_tuners->sampling_rate;
 		ignore_nice = cs_tuners->ignore_nice_load;
 	} else {
-		od_tuners = dbs_data->tuners;
-		od_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+
 		sampling_rate = od_tuners->sampling_rate;
 		ignore_nice = od_tuners->ignore_nice_load;
-		od_ops = dbs_data->cdata->gov_ops;
 		io_busy = od_tuners->io_is_busy;
 	}
 
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if (!policy->cur)
-			return -EINVAL;
+	for_each_cpu(j, policy->cpus) {
+		struct cpu_dbs_common_info *j_cdbs = cdata->get_cpu_cdbs(j);
+		unsigned int prev_load;
 
-		mutex_lock(&dbs_data->mutex);
+		j_cdbs->cpu = j;
+		j_cdbs->cur_policy = policy;
+		j_cdbs->prev_cpu_idle =
+			get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
 
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_common_info *j_cdbs =
-				dbs_data->cdata->get_cpu_cdbs(j);
-			unsigned int prev_load;
+		prev_load = (unsigned int)(j_cdbs->prev_cpu_wall -
+					    j_cdbs->prev_cpu_idle);
+		j_cdbs->prev_load = 100 * prev_load /
+				    (unsigned int)j_cdbs->prev_cpu_wall;
 
-			j_cdbs->cpu = j;
-			j_cdbs->cur_policy = policy;
-			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
-					       &j_cdbs->prev_cpu_wall, io_busy);
+		if (ignore_nice)
+			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			prev_load = (unsigned int)
-				(j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle);
-			j_cdbs->prev_load = 100 * prev_load /
-					(unsigned int) j_cdbs->prev_cpu_wall;
+		mutex_init(&j_cdbs->timer_mutex);
+		INIT_DEFERRABLE_WORK(&j_cdbs->work, cdata->gov_dbs_timer);
+	}
 
-			if (ignore_nice)
-				j_cdbs->prev_cpu_nice =
-					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+	if (cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_cpu_dbs_info_s *cs_dbs_info =
+			cdata->get_cpu_dbs_info_s(cpu);
 
-			mutex_init(&j_cdbs->timer_mutex);
-			INIT_DEFERRABLE_WORK(&j_cdbs->work,
-					     dbs_data->cdata->gov_dbs_timer);
-		}
+		cs_dbs_info->down_skip = 0;
+		cs_dbs_info->enable = 1;
+		cs_dbs_info->requested_freq = policy->cur;
+	} else {
+		struct od_ops *od_ops = cdata->gov_ops;
+		struct od_cpu_dbs_info_s *od_dbs_info = cdata->get_cpu_dbs_info_s(cpu);
 
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-			cs_dbs_info->down_skip = 0;
-			cs_dbs_info->enable = 1;
-			cs_dbs_info->requested_freq = policy->cur;
-		} else {
-			od_dbs_info->rate_mult = 1;
-			od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
-			od_ops->powersave_bias_init_cpu(cpu);
-		}
+		od_dbs_info->rate_mult = 1;
+		od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+		od_ops->powersave_bias_init_cpu(cpu);
+	}
 
-		mutex_unlock(&dbs_data->mutex);
+	/* Initiate timer time stamp */
+	cpu_cdbs->time_stamp = ktime_get();
 
-		/* Initiate timer time stamp */
-		cpu_cdbs->time_stamp = ktime_get();
+	gov_queue_work(dbs_data, policy, delay_for_sampling_rate(sampling_rate),
+		       true);
+	return 0;
+}
 
-		gov_queue_work(dbs_data, policy,
-				delay_for_sampling_rate(sampling_rate), true);
-		break;
+static void cpufreq_governor_stop(struct cpufreq_policy *policy,
+				  struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
 
-	case CPUFREQ_GOV_STOP:
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE)
-			cs_dbs_info->enable = 0;
+	if (cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_cpu_dbs_info_s *cs_dbs_info =
+			cdata->get_cpu_dbs_info_s(cpu);
 
-		gov_cancel_work(dbs_data, policy);
+		cs_dbs_info->enable = 0;
+	}
 
-		mutex_lock(&dbs_data->mutex);
-		mutex_destroy(&cpu_cdbs->timer_mutex);
-		cpu_cdbs->cur_policy = NULL;
+	gov_cancel_work(dbs_data, policy);
 
-		mutex_unlock(&dbs_data->mutex);
+	mutex_destroy(&cpu_cdbs->timer_mutex);
+	cpu_cdbs->cur_policy = NULL;
+}
 
-		break;
+static void cpufreq_governor_limits(struct cpufreq_policy *policy,
+				    struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_common_info *cpu_cdbs = cdata->get_cpu_cdbs(cpu);
+
+	if (!cpu_cdbs->cur_policy)
+		return;
+
+	mutex_lock(&cpu_cdbs->timer_mutex);
+	if (policy->max < cpu_cdbs->cur_policy->cur)
+		__cpufreq_driver_target(cpu_cdbs->cur_policy, policy->max,
+					CPUFREQ_RELATION_H);
+	else if (policy->min > cpu_cdbs->cur_policy->cur)
+		__cpufreq_driver_target(cpu_cdbs->cur_policy, policy->min,
+					CPUFREQ_RELATION_L);
+	dbs_check_cpu(dbs_data, cpu);
+	mutex_unlock(&cpu_cdbs->timer_mutex);
+}
+
+int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+			 struct common_dbs_data *cdata, unsigned int event)
+{
+	struct dbs_data *dbs_data;
+	int ret = 0;
 
+	/* Lock governor to block concurrent initialization of governor */
+	mutex_lock(&cdata->mutex);
+
+	if (have_governor_per_policy())
+		dbs_data = policy->governor_data;
+	else
+		dbs_data = cdata->gdbs_data;
+
+	if (WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT))) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	switch (event) {
+	case CPUFREQ_GOV_POLICY_INIT:
+		ret = cpufreq_governor_init(policy, dbs_data, cdata);
+		break;
+	case CPUFREQ_GOV_POLICY_EXIT:
+		cpufreq_governor_exit(policy, dbs_data);
+		break;
+	case CPUFREQ_GOV_START:
+		ret = cpufreq_governor_start(policy, dbs_data);
+		break;
+	case CPUFREQ_GOV_STOP:
+		cpufreq_governor_stop(policy, dbs_data);
+		break;
 	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&dbs_data->mutex);
-		if (!cpu_cdbs->cur_policy) {
-			mutex_unlock(&dbs_data->mutex);
-			break;
-		}
-		mutex_lock(&cpu_cdbs->timer_mutex);
-		if (policy->max < cpu_cdbs->cur_policy->cur)
-			__cpufreq_driver_target(cpu_cdbs->cur_policy,
-					policy->max, CPUFREQ_RELATION_H);
-		else if (policy->min > cpu_cdbs->cur_policy->cur)
-			__cpufreq_driver_target(cpu_cdbs->cur_policy,
-					policy->min, CPUFREQ_RELATION_L);
-		dbs_check_cpu(dbs_data, cpu);
-		mutex_unlock(&cpu_cdbs->timer_mutex);
-		mutex_unlock(&dbs_data->mutex);
+		cpufreq_governor_limits(policy, dbs_data);
 		break;
 	}
-	return 0;
+
+unlock:
+	mutex_unlock(&cdata->mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index cc401d147e72..34736f5e869d 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -208,11 +208,16 @@ struct common_dbs_data {
 	void *(*get_cpu_dbs_info_s)(int cpu);
 	void (*gov_dbs_timer)(struct work_struct *work);
 	void (*gov_check_cpu)(int cpu, unsigned int load);
-	int (*init)(struct dbs_data *dbs_data);
-	void (*exit)(struct dbs_data *dbs_data);
+	int (*init)(struct dbs_data *dbs_data, bool notify);
+	void (*exit)(struct dbs_data *dbs_data, bool notify);
 
 	/* Governor specific ops, see below */
 	void *gov_ops;
+
+	/*
+	 * Protects governor's data (struct dbs_data and struct common_dbs_data)
+	 */
+	struct mutex mutex;
 };
 
 /* Governor Per policy data */
@@ -221,9 +226,6 @@ struct dbs_data {
 	unsigned int min_sampling_rate;
 	int usage_count;
 	void *tuners;
-
-	/* dbs_mutex protects dbs_enable in governor start/stop */
-	struct mutex mutex;
 };
 
 /* Governor specific ops, will be passed to dbs_data->gov_ops */
@@ -234,10 +236,6 @@ struct od_ops {
 	void (*freq_increase)(struct cpufreq_policy *policy, unsigned int freq);
 };
 
-struct cs_ops {
-	struct notifier_block *notifier_block;
-};
-
 static inline int delay_for_sampling_rate(unsigned int sampling_rate)
 {
 	int delay = usecs_to_jiffies(sampling_rate);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index ad3f38fd3eb9..3c1e10f2304c 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -475,7 +475,7 @@ static struct attribute_group od_attr_group_gov_pol = {
 
 /************************** sysfs end ************************/
 
-static int od_init(struct dbs_data *dbs_data)
+static int od_init(struct dbs_data *dbs_data, bool notify)
 {
 	struct od_dbs_tuners *tuners;
 	u64 idle_time;
@@ -513,11 +513,10 @@ static int od_init(struct dbs_data *dbs_data)
 	tuners->io_is_busy = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
-	mutex_init(&dbs_data->mutex);
 	return 0;
 }
 
-static void od_exit(struct dbs_data *dbs_data)
+static void od_exit(struct dbs_data *dbs_data, bool notify)
 {
 	kfree(dbs_data->tuners);
 }
@@ -541,6 +540,7 @@ static struct common_dbs_data od_dbs_cdata = {
 	.gov_ops = &od_ops,
 	.init = od_init,
 	.exit = od_exit,
+	.mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex),
 };
 
 static void od_set_powersave_bias(unsigned int powersave_bias)
diff --git a/drivers/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c
index 1d723dc8880c..3488c9c175eb 100644
--- a/drivers/cpufreq/gx-suspmod.c
+++ b/drivers/cpufreq/gx-suspmod.c
@@ -144,7 +144,7 @@ module_param(max_duration, int, 0444);
 
 
 /**
- * we can detect a core multipiler from dir0_lsb
+ * we can detect a core multiplier from dir0_lsb
  * from GX1 datasheet p.56,
  *	MULT[3:0]:
  *	0000 = SYSCLK multiplied by 4 (test only)
@@ -346,7 +346,7 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy)
 
 	/* it needs to be assured that at least one supported frequency is
 	 * within policy->min and policy->max. If it is not, policy->max
-	 * needs to be increased until one freuqency is supported.
+	 * needs to be increased until one frequency is supported.
 	 * policy->min may not be decreased, though. This way we guarantee a
 	 * specific processing capacity.
 	 */
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6414661ac1c4..15ada47bb720 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/debugfs.h>
 #include <linux/acpi.h>
+#include <linux/vmalloc.h>
 #include <trace/events/power.h>
 
 #include <asm/div64.h>
@@ -48,9 +49,9 @@ static inline int32_t mul_fp(int32_t x, int32_t y)
 	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
 }
 
-static inline int32_t div_fp(int32_t x, int32_t y)
+static inline int32_t div_fp(s64 x, s64 y)
 {
-	return div_s64((int64_t)x << FRAC_BITS, y);
+	return div64_s64((int64_t)x << FRAC_BITS, y);
 }
 
 static inline int ceiling_fp(int32_t x)
@@ -68,6 +69,7 @@ struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
+	u64 tsc;
 	int freq;
 	ktime_t time;
 };
@@ -109,6 +111,7 @@ struct cpudata {
 	ktime_t last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
+	u64	prev_tsc;
 	struct sample sample;
 };
 
@@ -396,7 +399,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	update_turbo_state();
 	if (limits.turbo_disabled) {
-		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+		pr_warn("intel_pstate: Turbo disabled by BIOS or unavailable on processor\n");
 		return -EPERM;
 	}
 
@@ -484,7 +487,7 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(void)
 {
 	hwp_active++;
-	pr_info("intel_pstate HWP enabled\n");
+	pr_info("intel_pstate: HWP enabled\n");
 
 	wrmsrl( MSR_PM_ENABLE, 0x1);
 }
@@ -535,7 +538,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 
 	val |= vid;
 
-	wrmsrl(MSR_IA32_PERF_CTL, val);
+	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
 #define BYT_BCLK_FREQS 5
@@ -704,19 +707,20 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
 {
 	int max_perf, min_perf;
 
-	update_turbo_state();
-
-	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
+	if (force) {
+		update_turbo_state();
 
-	pstate = clamp_t(int, pstate, min_perf, max_perf);
+		intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
-	if (pstate == cpu->pstate.current_pstate)
-		return;
+		pstate = clamp_t(int, pstate, min_perf, max_perf);
 
+		if (pstate == cpu->pstate.current_pstate)
+			return;
+	}
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
@@ -733,7 +737,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu)
@@ -756,23 +760,28 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
+	u64 tsc;
 
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	tsc = native_read_tsc();
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
 	cpu->sample.time = ktime_get();
 	cpu->sample.aperf = aperf;
 	cpu->sample.mperf = mperf;
+	cpu->sample.tsc =  tsc;
 	cpu->sample.aperf -= cpu->prev_aperf;
 	cpu->sample.mperf -= cpu->prev_mperf;
+	cpu->sample.tsc -= cpu->prev_tsc;
 
 	intel_pstate_calc_busy(cpu);
 
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
+	cpu->prev_tsc = tsc;
 }
 
 static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
@@ -794,7 +803,7 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
-	u32 duration_us;
+	s64 duration_us;
 	u32 sample_time;
 
 	/*
@@ -821,8 +830,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 	 * to adjust our busyness.
 	 */
 	sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-	duration_us = (u32) ktime_us_delta(cpu->sample.time,
-					   cpu->last_sample_time);
+	duration_us = ktime_us_delta(cpu->sample.time,
+				     cpu->last_sample_time);
 	if (duration_us > sample_time * 3) {
 		sample_ratio = div_fp(int_tofp(sample_time),
 				      int_tofp(duration_us));
@@ -837,6 +846,10 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 	int32_t busy_scaled;
 	struct _pid *pid;
 	signed int ctl;
+	int from;
+	struct sample *sample;
+
+	from = cpu->pstate.current_pstate;
 
 	pid = &cpu->pid;
 	busy_scaled = intel_pstate_get_scaled_busy(cpu);
@@ -844,7 +857,17 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 	ctl = pid_calc(pid, busy_scaled);
 
 	/* Negative values of ctl increase the pstate and vice versa */
-	intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl);
+	intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl, true);
+
+	sample = &cpu->sample;
+	trace_pstate_sample(fp_toint(sample->core_pct_busy),
+		fp_toint(busy_scaled),
+		from,
+		cpu->pstate.current_pstate,
+		sample->mperf,
+		sample->aperf,
+		sample->tsc,
+		sample->freq);
 }
 
 static void intel_hwp_timer_func(unsigned long __data)
@@ -858,21 +881,11 @@ static void intel_hwp_timer_func(unsigned long __data)
 static void intel_pstate_timer_func(unsigned long __data)
 {
 	struct cpudata *cpu = (struct cpudata *) __data;
-	struct sample *sample;
 
 	intel_pstate_sample(cpu);
 
-	sample = &cpu->sample;
-
 	intel_pstate_adjust_busy_pstate(cpu);
 
-	trace_pstate_sample(fp_toint(sample->core_pct_busy),
-			fp_toint(intel_pstate_get_scaled_busy(cpu)),
-			cpu->pstate.current_pstate,
-			sample->mperf,
-			sample->aperf,
-			sample->freq);
-
 	intel_pstate_set_sample_time(cpu);
 }
 
@@ -935,7 +948,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	add_timer_on(&cpu->timer, cpunum);
 
-	pr_debug("Intel pstate controlling: cpu %d\n", cpunum);
+	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
 	return 0;
 }
@@ -1001,13 +1014,13 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	int cpu_num = policy->cpu;
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	pr_info("intel_pstate CPU %d exiting\n", cpu_num);
+	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
 	del_timer_sync(&all_cpu_data[cpu_num]->timer);
 	if (hwp_active)
 		return;
 
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 529cfd92158f..5dd95dab580d 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -172,7 +172,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index f9ce7e4bf0fe..5c035d04d827 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -57,13 +57,6 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static struct cpufreq_driver cpufreq_amd64_driver;
 
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
-	return cpumask_of(0);
-}
-#endif
-
 /* Return a frequency in MHz, given an input fid */
 static u32 find_freq_from_fid(u32 fid)
 {
@@ -620,7 +613,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -784,7 +777,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		CPUFREQ_TABLE_END;
 	data->powernow_table = powernow_table;
 
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	/* notify BIOS that we exist */
@@ -1090,7 +1083,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc != 0)
 		goto err_out_exit_acpi;
 
-	cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
+	cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	/* min/max the cpu is capable of */
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index e24269ab4e9b..1d99c97defa9 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -56,7 +56,7 @@ module_param(pxa27x_maxfreq, uint, 0);
 MODULE_PARM_DESC(pxa27x_maxfreq, "Set the pxa27x maxfreq in MHz"
 		 "(typically 624=>pxa270, 416=>pxa271, 520=>pxa272)");
 
-typedef struct {
+struct pxa_freqs {
 	unsigned int khz;
 	unsigned int membus;
 	unsigned int cccr;
@@ -64,7 +64,7 @@ typedef struct {
 	unsigned int cclkcfg;
 	int vmin;
 	int vmax;
-} pxa_freqs_t;
+};
 
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
@@ -86,7 +86,7 @@ static unsigned int sdram_rows;
 /* Use the run mode frequencies for the CPUFREQ_POLICY_PERFORMANCE policy */
 #define CCLKCFG			CCLKCFG_TURBO | CCLKCFG_FCS
 
-static pxa_freqs_t pxa255_run_freqs[] =
+static const struct pxa_freqs pxa255_run_freqs[] =
 {
 	/* CPU   MEMBUS  CCCR  DIV2 CCLKCFG	           run  turbo PXbus SDRAM */
 	{ 99500,  99500, 0x121, 1,  CCLKCFG, -1, -1},	/*  99,   99,   50,   50  */
@@ -98,7 +98,7 @@ static pxa_freqs_t pxa255_run_freqs[] =
 };
 
 /* Use the turbo mode frequencies for the CPUFREQ_POLICY_POWERSAVE policy */
-static pxa_freqs_t pxa255_turbo_freqs[] =
+static const struct pxa_freqs pxa255_turbo_freqs[] =
 {
 	/* CPU   MEMBUS  CCCR  DIV2 CCLKCFG	   run  turbo PXbus SDRAM */
 	{ 99500, 99500,  0x121, 1,  CCLKCFG, -1, -1},	/*  99,   99,   50,   50  */
@@ -153,7 +153,7 @@ MODULE_PARM_DESC(pxa255_turbo_table, "Selects the frequency table (0 = run table
    ((HT) ? CCLKCFG_HALFTURBO : 0) | \
    ((T)  ? CCLKCFG_TURBO : 0))
 
-static pxa_freqs_t pxa27x_freqs[] = {
+static struct pxa_freqs pxa27x_freqs[] = {
 	{104000, 104000, PXA27x_CCCR(1,	 8, 2), 0, CCLKCFG2(1, 0, 1),  900000, 1705000 },
 	{156000, 104000, PXA27x_CCCR(1,	 8, 3), 0, CCLKCFG2(1, 0, 1), 1000000, 1705000 },
 	{208000, 208000, PXA27x_CCCR(0, 16, 2), 1, CCLKCFG2(0, 0, 1), 1180000, 1705000 },
@@ -171,7 +171,7 @@ extern unsigned get_clk_frequency_khz(int info);
 
 #ifdef CONFIG_REGULATOR
 
-static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
+static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq)
 {
 	int ret = 0;
 	int vmin, vmax;
@@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void)
 	}
 }
 #else
-static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
+static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq)
 {
 	return 0;
 }
@@ -211,7 +211,7 @@ static void __init pxa_cpufreq_init_voltages(void) { }
 #endif
 
 static void find_freq_tables(struct cpufreq_frequency_table **freq_table,
-			     pxa_freqs_t **pxa_freqs)
+			     const struct pxa_freqs **pxa_freqs)
 {
 	if (cpu_is_pxa25x()) {
 		if (!pxa255_turbo_table) {
@@ -270,7 +270,7 @@ static unsigned int pxa_cpufreq_get(unsigned int cpu)
 static int pxa_set_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	struct cpufreq_frequency_table *pxa_freqs_table;
-	pxa_freqs_t *pxa_freq_settings;
+	const struct pxa_freqs *pxa_freq_settings;
 	unsigned long flags;
 	unsigned int new_freq_cpu, new_freq_mem;
 	unsigned int unused, preset_mdrefr, postset_mdrefr, cclkcfg;
@@ -361,7 +361,7 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 	int i;
 	unsigned int freq;
 	struct cpufreq_frequency_table *pxa255_freq_table;
-	pxa_freqs_t *pxa255_freqs;
+	const struct pxa_freqs *pxa255_freqs;
 
 	/* try to guess pxa27x cpu */
 	if (cpu_is_pxa27x())
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 88b21ae0d6b0..358f0752c31e 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -27,11 +27,11 @@
 
 /**
  * struct cpu_data
- * @parent: the parent node of cpu clock
+ * @pclk: the parent clock of cpu
  * @table: frequency table
  */
 struct cpu_data {
-	struct device_node *parent;
+	struct clk **pclk;
 	struct cpufreq_frequency_table *table;
 };
 
@@ -196,7 +196,7 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table,
 
 static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	struct device_node *np;
+	struct device_node *np, *pnode;
 	int i, count, ret;
 	u32 freq, mask;
 	struct clk *clk;
@@ -219,17 +219,23 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_nomem2;
 	}
 
-	data->parent = of_parse_phandle(np, "clocks", 0);
-	if (!data->parent) {
+	pnode = of_parse_phandle(np, "clocks", 0);
+	if (!pnode) {
 		pr_err("%s: could not get clock information\n", __func__);
 		goto err_nomem2;
 	}
 
-	count = of_property_count_strings(data->parent, "clock-names");
+	count = of_property_count_strings(pnode, "clock-names");
+	data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL);
+	if (!data->pclk) {
+		pr_err("%s: no memory\n", __func__);
+		goto err_node;
+	}
+
 	table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL);
 	if (!table) {
 		pr_err("%s: no memory\n", __func__);
-		goto err_node;
+		goto err_pclk;
 	}
 
 	if (fmask)
@@ -238,7 +244,8 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		mask = 0x0;
 
 	for (i = 0; i < count; i++) {
-		clk = of_clk_get(data->parent, i);
+		clk = of_clk_get(pnode, i);
+		data->pclk[i] = clk;
 		freq = clk_get_rate(clk);
 		/*
 		 * the clock is valid if its frequency is not masked
@@ -273,13 +280,16 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = u64temp + 1;
 
 	of_node_put(np);
+	of_node_put(pnode);
 
 	return 0;
 
 err_nomem1:
 	kfree(table);
+err_pclk:
+	kfree(data->pclk);
 err_node:
-	of_node_put(data->parent);
+	of_node_put(pnode);
 err_nomem2:
 	policy->driver_data = NULL;
 	kfree(data);
@@ -293,7 +303,7 @@ static int __exit qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct cpu_data *data = policy->driver_data;
 
-	of_node_put(data->parent);
+	kfree(data->pclk);
 	kfree(data->table);
 	kfree(data);
 	policy->driver_data = NULL;
@@ -307,7 +317,7 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy,
 	struct clk *parent;
 	struct cpu_data *data = policy->driver_data;
 
-	parent = of_clk_get(data->parent, data->table[index].driver_data);
+	parent = data->pclk[data->table[index].driver_data];
 	return clk_set_parent(policy->clk, parent);
 }
 
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index e56d632a8b21..37555c6b86a7 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 59372077ec7c..1e3ef5ec4784 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -29,18 +29,25 @@ struct cpuidle_driver powernv_idle_driver = {
 
 static int max_idle_state;
 static struct cpuidle_state *cpuidle_state_table;
+static u64 snooze_timeout;
+static bool snooze_timeout_en;
 
 static int snooze_loop(struct cpuidle_device *dev,
 			struct cpuidle_driver *drv,
 			int index)
 {
+	u64 snooze_exit_time;
+
 	local_irq_enable();
 	set_thread_flag(TIF_POLLING_NRFLAG);
 
+	snooze_exit_time = get_tb() + snooze_timeout;
 	ppc64_runlatch_off();
 	while (!need_resched()) {
 		HMT_low();
 		HMT_very_low();
+		if (snooze_timeout_en && get_tb() > snooze_exit_time)
+			break;
 	}
 
 	HMT_medium();
@@ -252,6 +259,11 @@ static int powernv_idle_probe(void)
 		cpuidle_state_table = powernv_states;
 		/* Device tree can indicate more idle states */
 		max_idle_state = powernv_add_idle_states();
+		if (max_idle_state > 1) {
+			snooze_timeout_en = true;
+			snooze_timeout = powernv_states[1].target_residency *
+					 tb_ticks_per_usec;
+		}
  	} else
  		return -ENODEV;
 
diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c
index bb9e2b6f3ecc..07135e009d8b 100644
--- a/drivers/cpuidle/cpuidle-pseries.c
+++ b/drivers/cpuidle/cpuidle-pseries.c
@@ -27,6 +27,8 @@ struct cpuidle_driver pseries_idle_driver = {
 
 static int max_idle_state;
 static struct cpuidle_state *cpuidle_state_table;
+static u64 snooze_timeout;
+static bool snooze_timeout_en;
 
 static inline void idle_loop_prolog(unsigned long *in_purr)
 {
@@ -58,14 +60,18 @@ static int snooze_loop(struct cpuidle_device *dev,
 			int index)
 {
 	unsigned long in_purr;
+	u64 snooze_exit_time;
 
 	idle_loop_prolog(&in_purr);
 	local_irq_enable();
 	set_thread_flag(TIF_POLLING_NRFLAG);
+	snooze_exit_time = get_tb() + snooze_timeout;
 
 	while (!need_resched()) {
 		HMT_low();
 		HMT_very_low();
+		if (snooze_timeout_en && get_tb() > snooze_exit_time)
+			break;
 	}
 
 	HMT_medium();
@@ -244,6 +250,11 @@ static int pseries_idle_probe(void)
 	} else
 		return -ENODEV;
 
+	if (max_idle_state > 1) {
+		snooze_timeout_en = true;
+		snooze_timeout = cpuidle_state_table[1].target_residency *
+				 tb_ticks_per_usec;
+	}
 	return 0;
 }
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 61c417b9e53f..e8e2775c3821 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -65,7 +65,7 @@ int cpuidle_play_dead(void)
 		return -ENODEV;
 
 	/* Find lowest-power state that supports long-term idle */
-	for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
+	for (i = drv->state_count - 1; i >= 0; i--)
 		if (drv->states[i].enter_dead)
 			return drv->states[i].enter_dead(dev, i);
 
@@ -73,16 +73,21 @@ int cpuidle_play_dead(void)
 }
 
 static int find_deepest_state(struct cpuidle_driver *drv,
-			      struct cpuidle_device *dev, bool freeze)
+			      struct cpuidle_device *dev,
+			      unsigned int max_latency,
+			      unsigned int forbidden_flags,
+			      bool freeze)
 {
 	unsigned int latency_req = 0;
-	int i, ret = freeze ? -1 : CPUIDLE_DRIVER_STATE_START - 1;
+	int i, ret = -ENXIO;
 
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
 		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
 		if (s->disabled || su->disable || s->exit_latency <= latency_req
+		    || s->exit_latency > max_latency
+		    || (s->flags & forbidden_flags)
 		    || (freeze && !s->enter_freeze))
 			continue;
 
@@ -92,6 +97,7 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 	return ret;
 }
 
+#ifdef CONFIG_SUSPEND
 /**
  * cpuidle_find_deepest_state - Find the deepest available idle state.
  * @drv: cpuidle driver for the given CPU.
@@ -100,7 +106,7 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev)
 {
-	return find_deepest_state(drv, dev, false);
+	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
 }
 
 static void enter_freeze_proper(struct cpuidle_driver *drv,
@@ -139,18 +145,19 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * that interrupts won't be enabled when it exits and allows the tick to
 	 * be frozen safely.
 	 */
-	index = find_deepest_state(drv, dev, true);
+	index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
 	if (index >= 0)
 		enter_freeze_proper(drv, dev, index);
 
 	return index;
 }
+#endif /* CONFIG_SUSPEND */
 
 /**
  * cpuidle_enter_state - enter the state and update stats
  * @dev: cpuidle device for this cpu
  * @drv: cpuidle driver for this cpu
- * @next_state: index into drv->states of the state to enter
+ * @index: index into the states table in @drv of the state to enter
  */
 int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 			int index)
@@ -167,8 +174,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	 * local timer will be shut down.  If a local timer is used from another
 	 * CPU as a broadcast timer, this call may fail if it is not available.
 	 */
-	if (broadcast && tick_broadcast_enter())
-		return -EBUSY;
+	if (broadcast && tick_broadcast_enter()) {
+		index = find_deepest_state(drv, dev, target_state->exit_latency,
+					   CPUIDLE_FLAG_TIMER_STOP, false);
+		if (index < 0) {
+			default_idle_call();
+			return -EBUSY;
+		}
+		target_state = &drv->states[index];
+	}
+
+	/* Take note of the planned idle state. */
+	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
 	time_start = ktime_get();
@@ -178,6 +195,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	time_end = ktime_get();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
+	/* The cpu is no longer idle or about to enter idle. */
+	sched_idle_set_state(NULL);
+
 	if (broadcast) {
 		if (WARN_ON_ONCE(!irqs_disabled()))
 			local_irq_disable();
@@ -249,7 +269,7 @@ int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 void cpuidle_reflect(struct cpuidle_device *dev, int index)
 {
-	if (cpuidle_curr_governor->reflect)
+	if (cpuidle_curr_governor->reflect && index >= 0)
 		cpuidle_curr_governor->reflect(dev, index);
 }
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index b8a5fa15ca24..22e4463d1787 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -367,9 +367,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 static void menu_reflect(struct cpuidle_device *dev, int index)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
+
 	data->last_state_idx = index;
-	if (index >= 0)
-		data->needs_update = 1;
+	data->needs_update = 1;
 }
 
 /**
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 033c0c86f6ec..4044125fb5d5 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -162,10 +162,10 @@ config CRYPTO_GHASH_S390
 config CRYPTO_DEV_MV_CESA
 	tristate "Marvell's Cryptographic Engine"
 	depends on PLAT_ORION
-	select CRYPTO_ALGAPI
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_HASH
+	select SRAM
 	help
 	  This driver allows you to utilize the Cryptographic Engines and
 	  Security Accelerator (CESA) which can be found on the Marvell Orion
@@ -173,10 +173,27 @@ config CRYPTO_DEV_MV_CESA
 
 	  Currently the driver supports AES in ECB and CBC mode without DMA.
 
+config CRYPTO_DEV_MARVELL_CESA
+	tristate "New Marvell's Cryptographic Engine driver"
+	depends on PLAT_ORION || ARCH_MVEBU
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
+	select SRAM
+	help
+	  This driver allows you to utilize the Cryptographic Engines and
+	  Security Accelerator (CESA) which can be found on the Armada 370.
+	  This driver supports CPU offload through DMA transfers.
+
+	  This driver is aimed at replacing the mv_cesa driver. This will only
+	  happen once it has received proper testing.
+
 config CRYPTO_DEV_NIAGARA2
        tristate "Niagara2 Stream Processing Unit driver"
        select CRYPTO_DES
-       select CRYPTO_ALGAPI
+       select CRYPTO_BLKCIPHER
+       select CRYPTO_HASH
        depends on SPARC64
        help
 	  Each core of a Niagara2 processor contains a Stream
@@ -189,7 +206,6 @@ config CRYPTO_DEV_NIAGARA2
 config CRYPTO_DEV_HIFN_795X
 	tristate "Driver HIFN 795x crypto accelerator chips"
 	select CRYPTO_DES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	select HW_RANDOM if CRYPTO_DEV_HIFN_795X_RNG
 	depends on PCI
@@ -208,8 +224,10 @@ source drivers/crypto/caam/Kconfig
 
 config CRYPTO_DEV_TALITOS
 	tristate "Talitos Freescale Security Engine (SEC)"
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HASH
 	select HW_RANDOM
 	depends on FSL_SOC
 	help
@@ -222,11 +240,29 @@ config CRYPTO_DEV_TALITOS
 	  To compile this driver as a module, choose M here: the module
 	  will be called talitos.
 
+config CRYPTO_DEV_TALITOS1
+	bool "SEC1 (SEC 1.0 and SEC Lite 1.2)"
+	depends on CRYPTO_DEV_TALITOS
+	depends on PPC_8xx || PPC_82xx
+	default y
+	help
+	  Say 'Y' here to use the Freescale Security Engine (SEC) version 1.0
+	  found on MPC82xx or the Freescale Security Engine (SEC Lite)
+	  version 1.2 found on MPC8xx
+
+config CRYPTO_DEV_TALITOS2
+	bool "SEC2+ (SEC version 2.0 or upper)"
+	depends on CRYPTO_DEV_TALITOS
+	default y if !PPC_8xx
+	help
+	  Say 'Y' here to use the Freescale Security Engine (SEC)
+	  version 2 and following as found on MPC83xx, MPC85xx, etc ...
+
 config CRYPTO_DEV_IXP4XX
 	tristate "Driver for IXP4xx crypto hardware acceleration"
 	depends on ARCH_IXP4XX && IXP4XX_QMGR && IXP4XX_NPE
 	select CRYPTO_DES
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
 	help
@@ -236,7 +272,6 @@ config CRYPTO_DEV_PPC4XX
 	tristate "Driver AMCC PPC4xx crypto accelerator"
 	depends on PPC && 4xx
 	select CRYPTO_HASH
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This option allows you to have support for AMCC crypto acceleration.
@@ -257,7 +292,7 @@ config CRYPTO_DEV_OMAP_AES
 	tristate "Support for OMAP AES hw engine"
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || ARCH_OMAP2PLUS
 	select CRYPTO_AES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	help
 	  OMAP processors have AES module accelerator. Select this if you
 	  want to use the OMAP module for AES algorithms.
@@ -266,7 +301,7 @@ config CRYPTO_DEV_OMAP_DES
 	tristate "Support for OMAP DES3DES hw engine"
 	depends on ARCH_OMAP2PLUS
 	select CRYPTO_DES
-	select CRYPTO_BLKCIPHER2
+	select CRYPTO_BLKCIPHER
 	help
 	  OMAP processors have DES/3DES module accelerator. Select this if you
 	  want to use the OMAP module for DES and 3DES algorithms. Currently
@@ -276,9 +311,10 @@ config CRYPTO_DEV_OMAP_DES
 config CRYPTO_DEV_PICOXCELL
 	tristate "Support for picoXcell IPSEC and Layer2 crypto engines"
 	depends on ARCH_PICOXCELL && HAVE_CLK
+	select CRYPTO_AEAD
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
-	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_DES
 	select CRYPTO_CBC
 	select CRYPTO_ECB
@@ -304,7 +340,6 @@ config CRYPTO_DEV_S5P
 	tristate "Support for Samsung S5PV210/Exynos crypto accelerator"
 	depends on ARCH_S5PV210 || ARCH_EXYNOS
 	select CRYPTO_AES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This option allows you to have support for S5P crypto acceleration.
@@ -312,11 +347,13 @@ config CRYPTO_DEV_S5P
 	  algorithms execution.
 
 config CRYPTO_DEV_NX
-	bool "Support for IBM Power7+ in-Nest cryptographic acceleration"
-	depends on PPC64 && IBMVIO && !CPU_LITTLE_ENDIAN
-	default n
+	bool "Support for IBM PowerPC Nest (NX) cryptographic acceleration"
+	depends on PPC64
 	help
-	  Support for Power7+ in-Nest cryptographic acceleration.
+	  This enables support for the NX hardware cryptographic accelerator
+	  coprocessor that is in IBM PowerPC P7+ or later processors.  This
+	  does not actually enable any drivers, it only allows you to select
+	  which acceleration type (encryption and/or compression) to enable.
 
 if CRYPTO_DEV_NX
 	source "drivers/crypto/nx/Kconfig"
@@ -325,7 +362,6 @@ endif
 config CRYPTO_DEV_UX500
 	tristate "Driver for ST-Ericsson UX500 crypto hardware acceleration"
 	depends on ARCH_U8500
-	select CRYPTO_ALGAPI
 	help
 	  Driver for ST-Ericsson UX500 crypto engine.
 
@@ -343,10 +379,7 @@ config CRYPTO_DEV_BFIN_CRC
 config CRYPTO_DEV_ATMEL_AES
 	tristate "Support for Atmel AES hw accelerator"
 	depends on ARCH_AT91
-	select CRYPTO_CBC
-	select CRYPTO_ECB
 	select CRYPTO_AES
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	select AT_HDMAC
 	help
@@ -361,9 +394,6 @@ config CRYPTO_DEV_ATMEL_TDES
 	tristate "Support for Atmel DES/TDES hw accelerator"
 	depends on ARCH_AT91
 	select CRYPTO_DES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  Some Atmel processors have DES/TDES hw accelerator.
@@ -376,10 +406,7 @@ config CRYPTO_DEV_ATMEL_TDES
 config CRYPTO_DEV_ATMEL_SHA
 	tristate "Support for Atmel SHA hw accelerator"
 	depends on ARCH_AT91
-	select CRYPTO_SHA1
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
-	select CRYPTO_ALGAPI
+	select CRYPTO_HASH
 	help
 	  Some Atmel processors have SHA1/SHA224/SHA256/SHA384/SHA512
 	  hw accelerator.
@@ -392,7 +419,6 @@ config CRYPTO_DEV_ATMEL_SHA
 config CRYPTO_DEV_CCP
 	bool "Support for AMD Cryptographic Coprocessor"
 	depends on ((X86 && PCI) || (ARM64 && (OF_ADDRESS || ACPI))) && HAS_IOMEM
-	default n
 	help
 	  The AMD Cryptographic Coprocessor provides hardware support
 	  for encryption, hashing and related operations.
@@ -404,13 +430,11 @@ endif
 config CRYPTO_DEV_MXS_DCP
 	tristate "Support for Freescale MXS DCP"
 	depends on ARCH_MXS
-	select CRYPTO_SHA1
-	select CRYPTO_SHA256
 	select CRYPTO_CBC
 	select CRYPTO_ECB
 	select CRYPTO_AES
 	select CRYPTO_BLKCIPHER
-	select CRYPTO_ALGAPI
+	select CRYPTO_HASH
 	help
 	  The Freescale i.MX23/i.MX28 has SHA1/SHA256 and AES128 CBC/ECB
 	  co-processor on the die.
@@ -429,7 +453,6 @@ config CRYPTO_DEV_QCE
 	select CRYPTO_CBC
 	select CRYPTO_XTS
 	select CRYPTO_CTR
-	select CRYPTO_ALGAPI
 	select CRYPTO_BLKCIPHER
 	help
 	  This driver supports Qualcomm crypto engine accelerator
@@ -439,7 +462,6 @@ config CRYPTO_DEV_QCE
 config CRYPTO_DEV_VMX
 	bool "Support for VMX cryptographic acceleration instructions"
 	depends on PPC64
-	default n
 	help
 	  Support for VMX cryptographic acceleration instructions.
 
@@ -449,7 +471,6 @@ config CRYPTO_DEV_IMGTEC_HASH
 	tristate "Imagination Technologies hardware hash accelerator"
 	depends on MIPS || COMPILE_TEST
 	depends on HAS_DMA
-	select CRYPTO_ALGAPI
 	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index fb84be7e6be5..e35c07a8da85 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_CRYPTO_DEV_HIFN_795X) += hifn_795x.o
 obj-$(CONFIG_CRYPTO_DEV_IMGTEC_HASH) += img-hash.o
 obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_MV_CESA) += mv_cesa.o
+obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell/
 obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
 n2_crypto-y := n2_core.o n2_asm.o
diff --git a/drivers/crypto/caam/Kconfig b/drivers/crypto/caam/Kconfig
index e7555ff4cafd..e286e285aa8a 100644
--- a/drivers/crypto/caam/Kconfig
+++ b/drivers/crypto/caam/Kconfig
@@ -45,7 +45,6 @@ config CRYPTO_DEV_FSL_CAAM_RINGSIZE
 config CRYPTO_DEV_FSL_CAAM_INTC
 	bool "Job Ring interrupt coalescing"
 	depends on CRYPTO_DEV_FSL_CAAM_JR
-	default n
 	help
 	  Enable the Job Ring's interrupt coalescing feature.
 
@@ -77,8 +76,9 @@ config CRYPTO_DEV_FSL_CAAM_CRYPTO_API
 	tristate "Register algorithm implementations with the Crypto API"
 	depends on CRYPTO_DEV_FSL_CAAM && CRYPTO_DEV_FSL_CAAM_JR
 	default y
-	select CRYPTO_ALGAPI
+	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
+	select CRYPTO_BLKCIPHER
 	help
 	  Selecting this will offload crypto for users of the
 	  scatterlist crypto API (such as the linux native IPSec
@@ -115,7 +115,6 @@ config CRYPTO_DEV_FSL_CAAM_RNG_API
 config CRYPTO_DEV_FSL_CAAM_DEBUG
 	bool "Enable debug output in CAAM driver"
 	depends on CRYPTO_DEV_FSL_CAAM
-	default n
 	help
 	  Selecting this will enable printing of various debug
 	  information in the CAAM driver.
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 29071a156cbe..daca933a82ec 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -65,6 +65,10 @@
 /* max IV is max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
 #define CAAM_MAX_IV_LENGTH		16
 
+#define AEAD_DESC_JOB_IO_LEN		(DESC_JOB_IO_LEN + CAAM_CMD_SZ * 2)
+#define GCM_DESC_JOB_IO_LEN		(AEAD_DESC_JOB_IO_LEN + \
+					 CAAM_CMD_SZ * 4)
+
 /* length of descriptors text */
 #define DESC_AEAD_BASE			(4 * CAAM_CMD_SZ)
 #define DESC_AEAD_ENC_LEN		(DESC_AEAD_BASE + 15 * CAAM_CMD_SZ)
@@ -79,18 +83,16 @@
 #define DESC_AEAD_NULL_DEC_LEN		(DESC_AEAD_NULL_BASE + 17 * CAAM_CMD_SZ)
 
 #define DESC_GCM_BASE			(3 * CAAM_CMD_SZ)
-#define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 23 * CAAM_CMD_SZ)
-#define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 19 * CAAM_CMD_SZ)
+#define DESC_GCM_ENC_LEN		(DESC_GCM_BASE + 16 * CAAM_CMD_SZ)
+#define DESC_GCM_DEC_LEN		(DESC_GCM_BASE + 12 * CAAM_CMD_SZ)
 
 #define DESC_RFC4106_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 15 * CAAM_CMD_SZ)
-#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 14 * CAAM_CMD_SZ)
-#define DESC_RFC4106_GIVENC_LEN		(DESC_RFC4106_BASE + 21 * CAAM_CMD_SZ)
+#define DESC_RFC4106_ENC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
+#define DESC_RFC4106_DEC_LEN		(DESC_RFC4106_BASE + 10 * CAAM_CMD_SZ)
 
 #define DESC_RFC4543_BASE		(3 * CAAM_CMD_SZ)
-#define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 25 * CAAM_CMD_SZ)
-#define DESC_RFC4543_DEC_LEN		(DESC_RFC4543_BASE + 27 * CAAM_CMD_SZ)
-#define DESC_RFC4543_GIVENC_LEN		(DESC_RFC4543_BASE + 30 * CAAM_CMD_SZ)
+#define DESC_RFC4543_ENC_LEN		(DESC_RFC4543_BASE + 11 * CAAM_CMD_SZ)
+#define DESC_RFC4543_DEC_LEN		(DESC_RFC4543_BASE + 12 * CAAM_CMD_SZ)
 
 #define DESC_ABLKCIPHER_BASE		(3 * CAAM_CMD_SZ)
 #define DESC_ABLKCIPHER_ENC_LEN		(DESC_ABLKCIPHER_BASE + \
@@ -98,8 +100,7 @@
 #define DESC_ABLKCIPHER_DEC_LEN		(DESC_ABLKCIPHER_BASE + \
 					 15 * CAAM_CMD_SZ)
 
-#define DESC_MAX_USED_BYTES		(DESC_RFC4543_GIVENC_LEN + \
-					 CAAM_MAX_KEY_SIZE)
+#define DESC_MAX_USED_BYTES		(CAAM_DESC_BYTES_MAX - DESC_JOB_IO_LEN)
 #define DESC_MAX_USED_LEN		(DESC_MAX_USED_BYTES / CAAM_CMD_SZ)
 
 #ifdef DEBUG
@@ -258,7 +259,7 @@ static void init_sh_desc_key_aead(u32 *desc, struct caam_ctx *ctx,
 
 static int aead_null_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
@@ -273,7 +274,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 	    ctx->split_key_pad_len <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_encrypt shared descriptor */
+	/* old_aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
@@ -362,7 +363,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	desc = ctx->sh_desc_dec;
 
-	/* aead_decrypt shared descriptor */
+	/* old_aead_decrypt shared descriptor */
 	init_sh_desc(desc, HDR_SHARE_SERIAL);
 
 	/* Skip if already shared */
@@ -383,7 +384,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
 	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
+				ctx->authsize + ivsize);
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
@@ -449,7 +450,7 @@ static int aead_null_set_sh_desc(struct crypto_aead *aead)
 
 static int aead_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
+	unsigned int ivsize = crypto_aead_ivsize(aead);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct crypto_tfm *ctfm = crypto_aead_tfm(aead);
 	const char *alg_name = crypto_tfm_alg_name(ctfm);
@@ -496,7 +497,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_encrypt shared descriptor */
+	/* old_aead_encrypt shared descriptor */
 	desc = ctx->sh_desc_enc;
 
 	/* Note: Context registers are saved. */
@@ -510,7 +511,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
 
 	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
+	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, ivsize);
 
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, VARSEQINLEN, REG2, REG3, CAAM_CMD_SZ);
@@ -518,7 +519,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* read assoc before reading payload */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
-	aead_append_ld_iv(desc, tfm->ivsize, ctx1_iv_off);
+	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
 
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
@@ -565,7 +566,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	    CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
-	/* aead_decrypt shared descriptor */
+	/* old_aead_decrypt shared descriptor */
 	desc = ctx->sh_desc_dec;
 
 	/* Note: Context registers are saved. */
@@ -577,7 +578,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	/* assoclen + cryptlen = seqinlen - ivsize - authsize */
 	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
+				ctx->authsize + ivsize);
 	/* assoclen = (assoclen + cryptlen) - cryptlen */
 	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
@@ -586,7 +587,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
 			     KEY_VLF);
 
-	aead_append_ld_iv(desc, tfm->ivsize, ctx1_iv_off);
+	aead_append_ld_iv(desc, ivsize, ctx1_iv_off);
 
 	/* Load Counter into CONTEXT1 reg */
 	if (is_rfc3686)
@@ -645,20 +646,20 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* Generate IV */
 	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
 		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
+		NFIFOENTRY_PTYPE_RND | (ivsize << NFIFOENTRY_DLEN_SHIFT);
 	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
 			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
 	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
 	append_move(desc, MOVE_WAITCOMP |
 		    MOVE_SRC_INFIFO | MOVE_DEST_CLASS1CTX |
 		    (ctx1_iv_off << MOVE_OFFSET_SHIFT) |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
+		    (ivsize << MOVE_LEN_SHIFT));
 	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
 
 	/* Copy IV to class 1 context */
 	append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_OUTFIFO |
 		    (ctx1_iv_off << MOVE_OFFSET_SHIFT) |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
+		    (ivsize << MOVE_LEN_SHIFT));
 
 	/* Return to encryption */
 	append_operation(desc, ctx->class2_alg_type |
@@ -676,10 +677,10 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 
 	/* Copy iv from outfifo to class 2 fifo */
 	moveiv = NFIFOENTRY_STYPE_OFIFO | NFIFOENTRY_DEST_CLASS2 |
-		 NFIFOENTRY_DTYPE_MSG | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
+		 NFIFOENTRY_DTYPE_MSG | (ivsize << NFIFOENTRY_DLEN_SHIFT);
 	append_load_imm_u32(desc, moveiv, LDST_CLASS_IND_CCB |
 			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_load_imm_u32(desc, tfm->ivsize, LDST_CLASS_2_CCB |
+	append_load_imm_u32(desc, ivsize, LDST_CLASS_2_CCB |
 			    LDST_SRCDST_WORD_DATASZ_REG | LDST_IMM);
 
 	/* Load Counter into CONTEXT1 reg */
@@ -698,7 +699,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	append_math_add(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* Not need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize,
+	append_seq_fifo_load(desc, ivsize,
 			     FIFOLD_CLASS_SKIP);
 
 	/* Will read cryptlen */
@@ -738,7 +739,6 @@ static int aead_setauthsize(struct crypto_aead *authenc,
 
 static int gcm_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
@@ -754,7 +754,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_GCM_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_GCM_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -777,34 +777,34 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+	/* if assoclen + cryptlen is ZERO, skip to ICV write */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
+	/* if assoclen is ZERO, skip reading the assoc data */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG1, REG2, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+
+	/* skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
+
+	/* cryptlen = seqinlen - assoclen */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
 
 	/* if cryptlen is ZERO jump to zero-payload commands */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
 					    JUMP_COND_MATH_Z);
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
-
-	/* if assoclen is ZERO, skip reading the assoc data */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
 
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd1);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* write encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -814,31 +814,17 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
 
 	/* jump the zero-payload commands */
-	append_jump(desc, JUMP_TEST_ALL | 7);
+	append_jump(desc, JUMP_TEST_ALL | 2);
 
 	/* zero-payload commands */
 	set_jump_tgt_here(desc, zero_payload_jump_cmd);
 
-	/* if assoclen is ZERO, jump to IV reading - is the only input data */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
-
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_LAST1);
 
-	/* jump to ICV writing */
-	append_jump(desc, JUMP_TEST_ALL | 2);
-
-	/* read IV - is the only input data */
+	/* There is no input data */
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd2);
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 |
-			     FIFOLD_TYPE_LAST1);
 
 	/* write ICV */
 	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
@@ -862,7 +848,7 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_GCM_DEC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_GCM_DEC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -886,33 +872,30 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, REG1, REG3, REG2, CAAM_CMD_SZ);
+	/* if assoclen is ZERO, skip reading the assoc data */
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
+						 JUMP_COND_MATH_Z);
 
-	/* read IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* jump to zero-payload command if cryptlen is zero */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
-	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
-					    JUMP_COND_MATH_Z);
+	/* skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	/* if asoclen is ZERO, skip reading assoc data */
-	zero_assoc_jump_cmd1 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
 	/* read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
+
 	set_jump_tgt_here(desc, zero_assoc_jump_cmd1);
 
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	/* cryptlen = seqoutlen - assoclen */
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+
+	/* jump to zero-payload command if cryptlen is zero */
+	zero_payload_jump_cmd = append_jump(desc, JUMP_TEST_ALL |
+					    JUMP_COND_MATH_Z);
+
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* store encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -921,21 +904,9 @@ static int gcm_set_sh_desc(struct crypto_aead *aead)
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_FLUSH1);
 
-	/* jump the zero-payload commands */
-	append_jump(desc, JUMP_TEST_ALL | 4);
-
 	/* zero-payload command */
 	set_jump_tgt_here(desc, zero_payload_jump_cmd);
 
-	/* if assoclen is ZERO, jump to ICV reading */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG1, CAAM_CMD_SZ);
-	zero_assoc_jump_cmd2 = append_jump(desc, JUMP_TEST_ALL |
-					   JUMP_COND_MATH_Z);
-	/* read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
-	set_jump_tgt_here(desc, zero_assoc_jump_cmd2);
-
 	/* read ICV */
 	append_seq_fifo_load(desc, ctx->authsize, FIFOLD_CLASS_CLASS1 |
 			     FIFOLD_TYPE_ICV | FIFOLD_TYPE_LAST1);
@@ -968,13 +939,11 @@ static int gcm_setauthsize(struct crypto_aead *authenc, unsigned int authsize)
 
 static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
-	u32 *key_jump_cmd, *move_cmd, *write_iv_cmd;
+	u32 *key_jump_cmd;
 	u32 *desc;
-	u32 geniv;
 
 	if (!ctx->enckeylen || !ctx->authsize)
 		return 0;
@@ -984,7 +953,7 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_RFC4106_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4106_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1007,29 +976,21 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
 	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* assoclen + cryptlen = seqinlen - ivsize */
-	append_math_sub_imm_u32(desc, REG2, SEQINLEN, IMM, tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, VARSEQINLEN, REG2, REG3, CAAM_CMD_SZ);
-
-	/* Read Salt */
-	append_fifo_load_as_imm(desc, (void *)(ctx->key + ctx->enckeylen),
-				4, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV);
-	/* Read AES-GCM-ESP IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
+	/* cryptlen = seqoutlen - assoclen */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
 	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/* Write encrypted data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -1083,30 +1044,21 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* assoclen + cryptlen = seqinlen - ivsize - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM,
-				ctx->authsize + tfm->ivsize);
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
-
-	/* Will write cryptlen bytes */
-	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
+	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
 
-	/* Read Salt */
-	append_fifo_load_as_imm(desc, (void *)(ctx->key + ctx->enckeylen),
-				4, FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV);
-	/* Read AES-GCM-ESP IV */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_CLASS1 |
-			     FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1);
+	/* Skip assoc data */
+	append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
 
 	/* Read assoc data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
 
+	/* Will write cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
+
 	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* Store payload data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
@@ -1132,107 +1084,6 @@ static int rfc4106_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
-	/*
-	 * Job Descriptor and Shared Descriptors
-	 * must all fit into the 64-word Descriptor h/w Buffer
-	 */
-	keys_fit_inline = false;
-	if (DESC_RFC4106_GIVENC_LEN + DESC_JOB_IO_LEN +
-	    ctx->split_key_pad_len + ctx->enckeylen <=
-	    CAAM_DESC_BYTES_MAX)
-		keys_fit_inline = true;
-
-	/* rfc4106_givencrypt shared descriptor */
-	desc = ctx->sh_desc_givenc;
-
-	init_sh_desc(desc, HDR_SHARE_SERIAL);
-
-	/* Skip key loading if it is loaded due to sharing */
-	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
-				   JUMP_COND_SHRD);
-	if (keys_fit_inline)
-		append_key_as_imm(desc, (void *)ctx->key, ctx->enckeylen,
-				  ctx->enckeylen, CLASS_1 | KEY_DEST_CLASS_REG);
-	else
-		append_key(desc, ctx->key_dma, ctx->enckeylen,
-			   CLASS_1 | KEY_DEST_CLASS_REG);
-	set_jump_tgt_here(desc, key_jump_cmd);
-
-	/* Generate IV */
-	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
-		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
-	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
-			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	move_cmd = append_move(desc, MOVE_SRC_INFIFO | MOVE_DEST_DESCBUF |
-			       (tfm->ivsize << MOVE_LEN_SHIFT));
-	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
-
-	/* Copy generated IV to OFIFO */
-	write_iv_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_OUTFIFO |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Class 1 operation */
-	append_operation(desc, ctx->class1_alg_type |
-			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
-
-	/* ivsize + cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = seqinlen - (ivsize + cryptlen) */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Will write ivsize + cryptlen */
-	append_math_add(desc, VARSEQOUTLEN, REG3, REG0, CAAM_CMD_SZ);
-
-	/* Read Salt and generated IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | FIFOLD_TYPE_IV |
-		   FIFOLD_TYPE_FLUSH1 | IMMEDIATE | 12);
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, move_cmd);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by generated IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* No need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_SKIP);
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_FLUSH1);
-
-	/* Will read cryptlen */
-	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
-
-	/* Store generated IV and encrypted data */
-	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
-
-	/* Read payload data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_MSG | FIFOLD_TYPE_LAST1);
-
-	/* Write ICV */
-	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
-			 LDST_SRCDST_BYTE_CONTEXT);
-
-	ctx->sh_desc_givenc_dma = dma_map_single(jrdev, desc,
-						 desc_bytes(desc),
-						 DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
-		dev_err(jrdev, "unable to map shared descriptor\n");
-		return -ENOMEM;
-	}
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "rfc4106 givenc shdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
-		       desc_bytes(desc), 1);
-#endif
-
 	return 0;
 }
 
@@ -1249,14 +1100,12 @@ static int rfc4106_setauthsize(struct crypto_aead *authenc,
 
 static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 {
-	struct aead_tfm *tfm = &aead->base.crt_aead;
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
 	struct device *jrdev = ctx->jrdev;
 	bool keys_fit_inline = false;
-	u32 *key_jump_cmd, *write_iv_cmd, *write_aad_cmd;
+	u32 *key_jump_cmd;
 	u32 *read_move_cmd, *write_move_cmd;
 	u32 *desc;
-	u32 geniv;
 
 	if (!ctx->enckeylen || !ctx->authsize)
 		return 0;
@@ -1266,7 +1115,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	 * Job Descriptor and Shared Descriptor
 	 * must fit into the 64-word Descriptor h/w Buffer
 	 */
-	if (DESC_RFC4543_ENC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4543_ENC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1289,48 +1138,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
 
-	/* Load AES-GMAC ESP IV into Math1 register */
-	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_WORD_DECO_MATH1 |
-		   LDST_CLASS_DECO | tfm->ivsize);
-
-	/* Wait the DMA transaction to finish */
-	append_jump(desc, JUMP_TEST_ALL | JUMP_COND_CALM |
-		    (1 << JUMP_OFFSET_SHIFT));
-
-	/* Overwrite blank immediate AES-GMAC ESP IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = (seqinlen - ivsize) - cryptlen */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Read Salt and AES-GMAC ESP IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
-
-	/* Will write cryptlen bytes */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+	/* assoclen + cryptlen = seqinlen */
+	append_math_sub(desc, REG3, SEQINLEN, REG0, CAAM_CMD_SZ);
 
 	/*
 	 * MOVE_LEN opcode is not available in all SEC HW revisions,
@@ -1342,16 +1151,13 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
 				     (0x8 << MOVE_LEN_SHIFT));
 
-	/* Authenticate AES-GMAC ESP IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
+	/* Will read assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
 
-	/* Read and write cryptlen bytes */
+	/* Will write assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
+
+	/* Read and write assoclen + cryptlen bytes */
 	aead_append_src_dst(desc, FIFOLD_TYPE_AAD);
 
 	set_move_tgt_here(desc, read_move_cmd);
@@ -1382,7 +1188,7 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	 * must all fit into the 64-word Descriptor h/w Buffer
 	 */
 	keys_fit_inline = false;
-	if (DESC_RFC4543_DEC_LEN + DESC_JOB_IO_LEN +
+	if (DESC_RFC4543_DEC_LEN + GCM_DESC_JOB_IO_LEN +
 	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
 		keys_fit_inline = true;
 
@@ -1405,28 +1211,8 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	append_operation(desc, ctx->class1_alg_type |
 			 OP_ALG_AS_INITFINAL | OP_ALG_DECRYPT | OP_ALG_ICV_ON);
 
-	/* Load AES-GMAC ESP IV into Math1 register */
-	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_WORD_DECO_MATH1 |
-		   LDST_CLASS_DECO | tfm->ivsize);
-
-	/* Wait the DMA transaction to finish */
-	append_jump(desc, JUMP_TEST_ALL | JUMP_COND_CALM |
-		    (1 << JUMP_OFFSET_SHIFT));
-
-	/* assoclen + cryptlen = (seqinlen - ivsize) - icvsize */
-	append_math_sub_imm_u32(desc, REG3, SEQINLEN, IMM, ctx->authsize);
-
-	/* Overwrite blank immediate AES-GMAC ESP IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* assoclen = (assoclen + cryptlen) - cryptlen */
-	append_math_sub(desc, REG2, SEQOUTLEN, REG0, CAAM_CMD_SZ);
-	append_math_sub(desc, VARSEQINLEN, REG3, REG2, CAAM_CMD_SZ);
+	/* assoclen + cryptlen = seqoutlen */
+	append_math_sub(desc, REG3, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/*
 	 * MOVE_LEN opcode is not available in all SEC HW revisions,
@@ -1438,40 +1224,16 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
 				     (0x8 << MOVE_LEN_SHIFT));
 
-	/* Read Salt and AES-GMAC ESP IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen bytes */
-	append_math_add(desc, VARSEQINLEN, ZERO, REG2, CAAM_CMD_SZ);
+	/* Will read assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQINLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
-	/* Will write cryptlen bytes */
-	append_math_add(desc, VARSEQOUTLEN, ZERO, REG2, CAAM_CMD_SZ);
-
-	/* Authenticate AES-GMAC ESP IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC ESP IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
+	/* Will write assoclen + cryptlen bytes */
+	append_math_sub(desc, VARSEQOUTLEN, SEQOUTLEN, REG0, CAAM_CMD_SZ);
 
 	/* Store payload data */
 	append_seq_fifo_store(desc, 0, FIFOST_TYPE_MESSAGE_DATA | FIFOLDST_VLF);
 
-	/* In-snoop cryptlen data */
+	/* In-snoop assoclen + cryptlen data */
 	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_BOTH | FIFOLDST_VLF |
 			     FIFOLD_TYPE_AAD | FIFOLD_TYPE_LAST2FLUSH1);
 
@@ -1499,135 +1261,6 @@ static int rfc4543_set_sh_desc(struct crypto_aead *aead)
 		       desc_bytes(desc), 1);
 #endif
 
-	/*
-	 * Job Descriptor and Shared Descriptors
-	 * must all fit into the 64-word Descriptor h/w Buffer
-	 */
-	keys_fit_inline = false;
-	if (DESC_RFC4543_GIVENC_LEN + DESC_JOB_IO_LEN +
-	    ctx->enckeylen <= CAAM_DESC_BYTES_MAX)
-		keys_fit_inline = true;
-
-	/* rfc4543_givencrypt shared descriptor */
-	desc = ctx->sh_desc_givenc;
-
-	init_sh_desc(desc, HDR_SHARE_SERIAL);
-
-	/* Skip key loading if it is loaded due to sharing */
-	key_jump_cmd = append_jump(desc, JUMP_JSL | JUMP_TEST_ALL |
-				   JUMP_COND_SHRD);
-	if (keys_fit_inline)
-		append_key_as_imm(desc, (void *)ctx->key, ctx->enckeylen,
-				  ctx->enckeylen, CLASS_1 | KEY_DEST_CLASS_REG);
-	else
-		append_key(desc, ctx->key_dma, ctx->enckeylen,
-			   CLASS_1 | KEY_DEST_CLASS_REG);
-	set_jump_tgt_here(desc, key_jump_cmd);
-
-	/* Generate IV */
-	geniv = NFIFOENTRY_STYPE_PAD | NFIFOENTRY_DEST_DECO |
-		NFIFOENTRY_DTYPE_MSG | NFIFOENTRY_LC1 |
-		NFIFOENTRY_PTYPE_RND | (tfm->ivsize << NFIFOENTRY_DLEN_SHIFT);
-	append_load_imm_u32(desc, geniv, LDST_CLASS_IND_CCB |
-			    LDST_SRCDST_WORD_INFO_FIFO | LDST_IMM);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	/* Move generated IV to Math1 register */
-	append_move(desc, MOVE_SRC_INFIFO | MOVE_DEST_MATH1 |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
-	append_cmd(desc, CMD_LOAD | ENABLE_AUTO_INFO_FIFO);
-
-	/* Overwrite blank immediate AES-GMAC IV data */
-	write_iv_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				   (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Overwrite blank immediate AAD data */
-	write_aad_cmd = append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_DESCBUF |
-				    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Copy generated IV to OFIFO */
-	append_move(desc, MOVE_SRC_MATH1 | MOVE_DEST_OUTFIFO |
-		    (tfm->ivsize << MOVE_LEN_SHIFT));
-
-	/* Class 1 operation */
-	append_operation(desc, ctx->class1_alg_type |
-			 OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
-
-	/* ivsize + cryptlen = seqoutlen - authsize */
-	append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
-	/* assoclen = seqinlen - (ivsize + cryptlen) */
-	append_math_sub(desc, VARSEQINLEN, SEQINLEN, REG3, CAAM_CMD_SZ);
-
-	/* Will write ivsize + cryptlen */
-	append_math_add(desc, VARSEQOUTLEN, REG3, REG0, CAAM_CMD_SZ);
-
-	/*
-	 * MOVE_LEN opcode is not available in all SEC HW revisions,
-	 * thus need to do some magic, i.e. self-patch the descriptor
-	 * buffer.
-	 */
-	read_move_cmd = append_move(desc, MOVE_SRC_DESCBUF | MOVE_DEST_MATH3 |
-				    (0x6 << MOVE_LEN_SHIFT));
-	write_move_cmd = append_move(desc, MOVE_SRC_MATH3 | MOVE_DEST_DESCBUF |
-				     (0x8 << MOVE_LEN_SHIFT));
-
-	/* Read Salt and AES-GMAC generated IV */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | (4 + tfm->ivsize));
-	/* Append Salt */
-	append_data(desc, (void *)(ctx->key + ctx->enckeylen), 4);
-	set_move_tgt_here(desc, write_iv_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC generated IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* No need to reload iv */
-	append_seq_fifo_load(desc, tfm->ivsize, FIFOLD_CLASS_SKIP);
-
-	/* Read assoc data */
-	append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS1 | FIFOLDST_VLF |
-			     FIFOLD_TYPE_AAD);
-
-	/* Will read cryptlen */
-	append_math_add(desc, VARSEQINLEN, SEQINLEN, REG0, CAAM_CMD_SZ);
-
-	/* Authenticate AES-GMAC IV  */
-	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
-		   FIFOLD_TYPE_AAD | tfm->ivsize);
-	set_move_tgt_here(desc, write_aad_cmd);
-	/* Blank commands. Will be overwritten by AES-GMAC IV. */
-	append_cmd(desc, 0x00000000);
-	append_cmd(desc, 0x00000000);
-	/* End of blank commands */
-
-	/* Read and write cryptlen bytes */
-	aead_append_src_dst(desc, FIFOLD_TYPE_AAD);
-
-	set_move_tgt_here(desc, read_move_cmd);
-	set_move_tgt_here(desc, write_move_cmd);
-	append_cmd(desc, CMD_LOAD | DISABLE_AUTO_INFO_FIFO);
-	/* Move payload data to OFIFO */
-	append_move(desc, MOVE_SRC_INFIFO_CL | MOVE_DEST_OUTFIFO);
-
-	/* Write ICV */
-	append_seq_store(desc, ctx->authsize, LDST_CLASS_1_CCB |
-			 LDST_SRCDST_BYTE_CONTEXT);
-
-	ctx->sh_desc_givenc_dma = dma_map_single(jrdev, desc,
-						 desc_bytes(desc),
-						 DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
-		dev_err(jrdev, "unable to map shared descriptor\n");
-		return -ENOMEM;
-	}
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "rfc4543 givenc shdesc@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4, desc,
-		       desc_bytes(desc), 1);
-#endif
-
 	return 0;
 }
 
@@ -2100,7 +1733,7 @@ struct aead_edesc {
 	int sec4_sg_bytes;
 	dma_addr_t sec4_sg_dma;
 	struct sec4_sg_entry *sec4_sg;
-	u32 hw_desc[0];
+	u32 hw_desc[];
 };
 
 /*
@@ -2154,6 +1787,16 @@ static void aead_unmap(struct device *dev,
 		       struct aead_edesc *edesc,
 		       struct aead_request *req)
 {
+	caam_unmap(dev, req->src, req->dst,
+		   edesc->src_nents, edesc->src_chained, edesc->dst_nents,
+		   edesc->dst_chained, 0, 0,
+		   edesc->sec4_sg_dma, edesc->sec4_sg_bytes);
+}
+
+static void old_aead_unmap(struct device *dev,
+			   struct aead_edesc *edesc,
+			   struct aead_request *req)
+{
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	int ivsize = crypto_aead_ivsize(aead);
 
@@ -2184,6 +1827,28 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 {
 	struct aead_request *req = context;
 	struct aead_edesc *edesc;
+
+#ifdef DEBUG
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = container_of(desc, struct aead_edesc, hw_desc[0]);
+
+	if (err)
+		caam_jr_strstatus(jrdev, err);
+
+	aead_unmap(jrdev, edesc, req);
+
+	kfree(edesc);
+
+	aead_request_complete(req, err);
+}
+
+static void old_aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
+				  void *context)
+{
+	struct aead_request *req = context;
+	struct aead_edesc *edesc;
 #ifdef DEBUG
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2198,7 +1863,7 @@ static void aead_encrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	aead_unmap(jrdev, edesc, req);
+	old_aead_unmap(jrdev, edesc, req);
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "assoc  @"__stringify(__LINE__)": ",
@@ -2223,6 +1888,34 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 {
 	struct aead_request *req = context;
 	struct aead_edesc *edesc;
+
+#ifdef DEBUG
+	dev_err(jrdev, "%s %d: err 0x%x\n", __func__, __LINE__, err);
+#endif
+
+	edesc = container_of(desc, struct aead_edesc, hw_desc[0]);
+
+	if (err)
+		caam_jr_strstatus(jrdev, err);
+
+	aead_unmap(jrdev, edesc, req);
+
+	/*
+	 * verify hw auth check passed else return -EBADMSG
+	 */
+	if ((err & JRSTA_CCBERR_ERRID_MASK) == JRSTA_CCBERR_ERRID_ICVCHK)
+		err = -EBADMSG;
+
+	kfree(edesc);
+
+	aead_request_complete(req, err);
+}
+
+static void old_aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
+				  void *context)
+{
+	struct aead_request *req = context;
+	struct aead_edesc *edesc;
 #ifdef DEBUG
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2246,7 +1939,7 @@ static void aead_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	aead_unmap(jrdev, edesc, req);
+	old_aead_unmap(jrdev, edesc, req);
 
 	/*
 	 * verify hw auth check passed else return -EBADMSG
@@ -2342,10 +2035,10 @@ static void ablkcipher_decrypt_done(struct device *jrdev, u32 *desc, u32 err,
 /*
  * Fill in aead job descriptor
  */
-static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
-			  struct aead_edesc *edesc,
-			  struct aead_request *req,
-			  bool all_contig, bool encrypt)
+static void old_init_aead_job(u32 *sh_desc, dma_addr_t ptr,
+			      struct aead_edesc *edesc,
+			      struct aead_request *req,
+			      bool all_contig, bool encrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2425,6 +2118,97 @@ static void init_aead_job(u32 *sh_desc, dma_addr_t ptr,
 }
 
 /*
+ * Fill in aead job descriptor
+ */
+static void init_aead_job(struct aead_request *req,
+			  struct aead_edesc *edesc,
+			  bool all_contig, bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	int authsize = ctx->authsize;
+	u32 *desc = edesc->hw_desc;
+	u32 out_options, in_options;
+	dma_addr_t dst_dma, src_dma;
+	int len, sec4_sg_index = 0;
+	dma_addr_t ptr;
+	u32 *sh_desc;
+
+	sh_desc = encrypt ? ctx->sh_desc_enc : ctx->sh_desc_dec;
+	ptr = encrypt ? ctx->sh_desc_enc_dma : ctx->sh_desc_dec_dma;
+
+	len = desc_len(sh_desc);
+	init_job_desc_shared(desc, ptr, len, HDR_SHARE_DEFER | HDR_REVERSE);
+
+	if (all_contig) {
+		src_dma = sg_dma_address(req->src);
+		in_options = 0;
+	} else {
+		src_dma = edesc->sec4_sg_dma;
+		sec4_sg_index += edesc->src_nents;
+		in_options = LDST_SGF;
+	}
+
+	append_seq_in_ptr(desc, src_dma, req->assoclen + req->cryptlen,
+			  in_options);
+
+	dst_dma = src_dma;
+	out_options = in_options;
+
+	if (unlikely(req->src != req->dst)) {
+		if (!edesc->dst_nents) {
+			dst_dma = sg_dma_address(req->dst);
+		} else {
+			dst_dma = edesc->sec4_sg_dma +
+				  sec4_sg_index *
+				  sizeof(struct sec4_sg_entry);
+			out_options = LDST_SGF;
+		}
+	}
+
+	if (encrypt)
+		append_seq_out_ptr(desc, dst_dma,
+				   req->assoclen + req->cryptlen + authsize,
+				   out_options);
+	else
+		append_seq_out_ptr(desc, dst_dma,
+				   req->assoclen + req->cryptlen - authsize,
+				   out_options);
+
+	/* REG3 = assoclen */
+	append_math_add_imm_u32(desc, REG3, ZERO, IMM, req->assoclen);
+}
+
+static void init_gcm_job(struct aead_request *req,
+			 struct aead_edesc *edesc,
+			 bool all_contig, bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int ivsize = crypto_aead_ivsize(aead);
+	u32 *desc = edesc->hw_desc;
+	bool generic_gcm = (ivsize == 12);
+	unsigned int last;
+
+	init_aead_job(req, edesc, all_contig, encrypt);
+
+	/* BUG This should not be specific to generic GCM. */
+	last = 0;
+	if (encrypt && generic_gcm && !(req->assoclen + req->cryptlen))
+		last = FIFOLD_TYPE_LAST1;
+
+	/* Read GCM IV */
+	append_cmd(desc, CMD_FIFO_LOAD | FIFOLD_CLASS_CLASS1 | IMMEDIATE |
+			 FIFOLD_TYPE_IV | FIFOLD_TYPE_FLUSH1 | 12 | last);
+	/* Append Salt */
+	if (!generic_gcm)
+		append_data(desc, ctx->key + ctx->enckeylen, 4);
+	/* Append IV */
+	append_data(desc, req->iv, ivsize);
+	/* End of blank commands */
+}
+
+/*
  * Fill in aead givencrypt job descriptor
  */
 static void init_aead_giv_job(u32 *sh_desc, dma_addr_t ptr,
@@ -2608,9 +2392,10 @@ static void init_ablkcipher_giv_job(u32 *sh_desc, dma_addr_t ptr,
 /*
  * allocate and map the aead extended descriptor
  */
-static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
-					   int desc_bytes, bool *all_contig_ptr,
-					   bool encrypt)
+static struct aead_edesc *old_aead_edesc_alloc(struct aead_request *req,
+					       int desc_bytes,
+					       bool *all_contig_ptr,
+					       bool encrypt)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -2713,10 +2498,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	sec4_sg_index = 0;
 	if (!all_contig) {
 		if (!is_gcm) {
-			sg_to_sec4_sg(req->assoc,
-				      assoc_nents,
-				      edesc->sec4_sg +
-				      sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2725,10 +2508,8 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 		sec4_sg_index += 1;
 
 		if (is_gcm) {
-			sg_to_sec4_sg(req->assoc,
-				      assoc_nents,
-				      edesc->sec4_sg +
-				      sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2752,7 +2533,124 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	return edesc;
 }
 
-static int aead_encrypt(struct aead_request *req)
+/*
+ * allocate and map the aead extended descriptor
+ */
+static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
+					   int desc_bytes, bool *all_contig_ptr,
+					   bool encrypt)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	gfp_t flags = (req->base.flags & (CRYPTO_TFM_REQ_MAY_BACKLOG |
+		       CRYPTO_TFM_REQ_MAY_SLEEP)) ? GFP_KERNEL : GFP_ATOMIC;
+	int src_nents, dst_nents = 0;
+	struct aead_edesc *edesc;
+	int sgc;
+	bool all_contig = true;
+	bool src_chained = false, dst_chained = false;
+	int sec4_sg_index, sec4_sg_len = 0, sec4_sg_bytes;
+	unsigned int authsize = ctx->authsize;
+
+	if (unlikely(req->dst != req->src)) {
+		src_nents = sg_count(req->src, req->assoclen + req->cryptlen,
+				     &src_chained);
+		dst_nents = sg_count(req->dst,
+				     req->assoclen + req->cryptlen +
+					(encrypt ? authsize : (-authsize)),
+				     &dst_chained);
+	} else {
+		src_nents = sg_count(req->src,
+				     req->assoclen + req->cryptlen +
+					(encrypt ? authsize : 0),
+				     &src_chained);
+	}
+
+	/* Check if data are contiguous. */
+	all_contig = !src_nents;
+	if (!all_contig) {
+		src_nents = src_nents ? : 1;
+		sec4_sg_len = src_nents;
+	}
+
+	sec4_sg_len += dst_nents;
+
+	sec4_sg_bytes = sec4_sg_len * sizeof(struct sec4_sg_entry);
+
+	/* allocate space for base edesc and hw desc commands, link tables */
+	edesc = kzalloc(sizeof(struct aead_edesc) + desc_bytes +
+			sec4_sg_bytes, GFP_DMA | flags);
+	if (!edesc) {
+		dev_err(jrdev, "could not allocate extended descriptor\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (likely(req->src == req->dst)) {
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_BIDIRECTIONAL, src_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map source\n");
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	} else {
+		sgc = dma_map_sg_chained(jrdev, req->src, src_nents ? : 1,
+					 DMA_TO_DEVICE, src_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map source\n");
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		sgc = dma_map_sg_chained(jrdev, req->dst, dst_nents ? : 1,
+					 DMA_FROM_DEVICE, dst_chained);
+		if (unlikely(!sgc)) {
+			dev_err(jrdev, "unable to map destination\n");
+			dma_unmap_sg_chained(jrdev, req->src, src_nents ? : 1,
+					     DMA_TO_DEVICE, src_chained);
+			kfree(edesc);
+			return ERR_PTR(-ENOMEM);
+		}
+	}
+
+	edesc->src_nents = src_nents;
+	edesc->src_chained = src_chained;
+	edesc->dst_nents = dst_nents;
+	edesc->dst_chained = dst_chained;
+	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
+			 desc_bytes;
+	*all_contig_ptr = all_contig;
+
+	sec4_sg_index = 0;
+	if (!all_contig) {
+		sg_to_sec4_sg_last(req->src, src_nents,
+			      edesc->sec4_sg + sec4_sg_index, 0);
+		sec4_sg_index += src_nents;
+	}
+	if (dst_nents) {
+		sg_to_sec4_sg_last(req->dst, dst_nents,
+				   edesc->sec4_sg + sec4_sg_index, 0);
+	}
+
+	if (!sec4_sg_bytes)
+		return edesc;
+
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
+
+	return edesc;
+}
+
+static int gcm_encrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2763,14 +2661,12 @@ static int aead_encrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				 CAAM_CMD_SZ, &all_contig, true);
+	edesc = aead_edesc_alloc(req, GCM_DESC_JOB_IO_LEN, &all_contig, true);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
 	/* Create and submit job descriptor */
-	init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
-		      all_contig, true);
+	init_gcm_job(req, edesc, all_contig, true);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2789,7 +2685,7 @@ static int aead_encrypt(struct aead_request *req)
 	return ret;
 }
 
-static int aead_decrypt(struct aead_request *req)
+static int old_aead_encrypt(struct aead_request *req)
 {
 	struct aead_edesc *edesc;
 	struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -2800,8 +2696,80 @@ static int aead_decrypt(struct aead_request *req)
 	int ret = 0;
 
 	/* allocate extended descriptor */
-	edesc = aead_edesc_alloc(req, DESC_JOB_IO_LEN *
-				 CAAM_CMD_SZ, &all_contig, false);
+	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
+				     CAAM_CMD_SZ, &all_contig, true);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Create and submit job descriptor */
+	old_init_aead_job(ctx->sh_desc_enc, ctx->sh_desc_enc_dma, edesc, req,
+			  all_contig, true);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
+		       desc_bytes(edesc->hw_desc), 1);
+#endif
+
+	desc = edesc->hw_desc;
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		old_aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int gcm_decrypt(struct aead_request *req)
+{
+	struct aead_edesc *edesc;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	bool all_contig;
+	u32 *desc;
+	int ret = 0;
+
+	/* allocate extended descriptor */
+	edesc = aead_edesc_alloc(req, GCM_DESC_JOB_IO_LEN, &all_contig, false);
+	if (IS_ERR(edesc))
+		return PTR_ERR(edesc);
+
+	/* Create and submit job descriptor*/
+	init_gcm_job(req, edesc, all_contig, false);
+#ifdef DEBUG
+	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
+		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
+		       desc_bytes(edesc->hw_desc), 1);
+#endif
+
+	desc = edesc->hw_desc;
+	ret = caam_jr_enqueue(jrdev, desc, aead_decrypt_done, req);
+	if (!ret) {
+		ret = -EINPROGRESS;
+	} else {
+		aead_unmap(jrdev, edesc, req);
+		kfree(edesc);
+	}
+
+	return ret;
+}
+
+static int old_aead_decrypt(struct aead_request *req)
+{
+	struct aead_edesc *edesc;
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct caam_ctx *ctx = crypto_aead_ctx(aead);
+	struct device *jrdev = ctx->jrdev;
+	bool all_contig;
+	u32 *desc;
+	int ret = 0;
+
+	/* allocate extended descriptor */
+	edesc = old_aead_edesc_alloc(req, DESC_JOB_IO_LEN *
+				     CAAM_CMD_SZ, &all_contig, false);
 	if (IS_ERR(edesc))
 		return PTR_ERR(edesc);
 
@@ -2812,8 +2780,8 @@ static int aead_decrypt(struct aead_request *req)
 #endif
 
 	/* Create and submit job descriptor*/
-	init_aead_job(ctx->sh_desc_dec,
-		      ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
+	old_init_aead_job(ctx->sh_desc_dec,
+			  ctx->sh_desc_dec_dma, edesc, req, all_contig, false);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "aead jobdesc@"__stringify(__LINE__)": ",
 		       DUMP_PREFIX_ADDRESS, 16, 4, edesc->hw_desc,
@@ -2821,11 +2789,11 @@ static int aead_decrypt(struct aead_request *req)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, aead_decrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_decrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		aead_unmap(jrdev, edesc, req);
+		old_aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
@@ -2953,8 +2921,8 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	sec4_sg_index = 0;
 	if (!(contig & GIV_SRC_CONTIG)) {
 		if (!is_gcm) {
-			sg_to_sec4_sg(req->assoc, assoc_nents,
-				      edesc->sec4_sg + sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2963,8 +2931,8 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 		sec4_sg_index += 1;
 
 		if (is_gcm) {
-			sg_to_sec4_sg(req->assoc, assoc_nents,
-				      edesc->sec4_sg + sec4_sg_index, 0);
+			sg_to_sec4_sg_len(req->assoc, req->assoclen,
+					  edesc->sec4_sg + sec4_sg_index);
 			sec4_sg_index += assoc_nents;
 		}
 
@@ -2999,7 +2967,7 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	return edesc;
 }
 
-static int aead_givencrypt(struct aead_givcrypt_request *areq)
+static int old_aead_givencrypt(struct aead_givcrypt_request *areq)
 {
 	struct aead_request *req = &areq->areq;
 	struct aead_edesc *edesc;
@@ -3033,11 +3001,11 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 #endif
 
 	desc = edesc->hw_desc;
-	ret = caam_jr_enqueue(jrdev, desc, aead_encrypt_done, req);
+	ret = caam_jr_enqueue(jrdev, desc, old_aead_encrypt_done, req);
 	if (!ret) {
 		ret = -EINPROGRESS;
 	} else {
-		aead_unmap(jrdev, edesc, req);
+		old_aead_unmap(jrdev, edesc, req);
 		kfree(edesc);
 	}
 
@@ -3046,7 +3014,7 @@ static int aead_givencrypt(struct aead_givcrypt_request *areq)
 
 static int aead_null_givencrypt(struct aead_givcrypt_request *areq)
 {
-	return aead_encrypt(&areq->areq);
+	return old_aead_encrypt(&areq->areq);
 }
 
 /*
@@ -3379,11 +3347,7 @@ struct caam_alg_template {
 	u32 type;
 	union {
 		struct ablkcipher_alg ablkcipher;
-		struct aead_alg aead;
-		struct blkcipher_alg blkcipher;
-		struct cipher_alg cipher;
-		struct compress_alg compress;
-		struct rng_alg rng;
+		struct old_aead_alg aead;
 	} template_u;
 	u32 class1_alg_type;
 	u32 class2_alg_type;
@@ -3400,8 +3364,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3419,8 +3383,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3438,8 +3402,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3458,8 +3422,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3478,8 +3442,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3498,8 +3462,8 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
 			.givencrypt = aead_null_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = NULL_IV_SIZE,
@@ -3518,9 +3482,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3537,9 +3501,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3556,9 +3520,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3576,9 +3540,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3596,9 +3560,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3617,9 +3581,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = AES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3637,9 +3601,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3656,9 +3620,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3675,9 +3639,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3695,9 +3659,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3715,9 +3679,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3735,9 +3699,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3755,9 +3719,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3774,9 +3738,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3793,9 +3757,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3813,9 +3777,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3833,9 +3797,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3853,9 +3817,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = DES_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3873,9 +3837,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
@@ -3892,9 +3856,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
@@ -3911,9 +3875,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
@@ -3931,9 +3895,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
@@ -3951,9 +3915,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
@@ -3971,9 +3935,9 @@ static struct caam_alg_template driver_algs[] = {
 		.template_aead = {
 			.setkey = aead_setkey,
 			.setauthsize = aead_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
+			.encrypt = old_aead_encrypt,
+			.decrypt = old_aead_decrypt,
+			.givencrypt = old_aead_givencrypt,
 			.geniv = "<built-in>",
 			.ivsize = CTR_RFC3686_IV_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
@@ -3983,58 +3947,6 @@ static struct caam_alg_template driver_algs[] = {
 				   OP_ALG_AAI_HMAC_PRECOMP,
 		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
 	},
-	{
-		.name = "rfc4106(gcm(aes))",
-		.driver_name = "rfc4106-gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = rfc4106_setkey,
-			.setauthsize = rfc4106_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
-			.geniv = "<built-in>",
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
-	{
-		.name = "rfc4543(gcm(aes))",
-		.driver_name = "rfc4543-gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = rfc4543_setkey,
-			.setauthsize = rfc4543_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = aead_givencrypt,
-			.geniv = "<built-in>",
-			.ivsize = 8,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
-	/* Galois Counter Mode */
-	{
-		.name = "gcm(aes)",
-		.driver_name = "gcm-aes-caam",
-		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
-		.template_aead = {
-			.setkey = gcm_setkey,
-			.setauthsize = gcm_setauthsize,
-			.encrypt = aead_encrypt,
-			.decrypt = aead_decrypt,
-			.givencrypt = NULL,
-			.geniv = "<built-in>",
-			.ivsize = 12,
-			.maxauthsize = AES_BLOCK_SIZE,
-			},
-		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
-	},
 	/* ablkcipher descriptor */
 	{
 		.name = "cbc(aes)",
@@ -4124,21 +4036,84 @@ static struct caam_alg_template driver_algs[] = {
 	}
 };
 
-struct caam_crypto_alg {
-	struct list_head entry;
+struct caam_alg_entry {
 	int class1_alg_type;
 	int class2_alg_type;
 	int alg_op;
+};
+
+struct caam_aead_alg {
+	struct aead_alg aead;
+	struct caam_alg_entry caam;
+	bool registered;
+};
+
+static struct caam_aead_alg driver_aeads[] = {
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4106(gcm(aes))",
+				.cra_driver_name = "rfc4106-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4106_setkey,
+			.setauthsize = rfc4106_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	{
+		.aead = {
+			.base = {
+				.cra_name = "rfc4543(gcm(aes))",
+				.cra_driver_name = "rfc4543-gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = rfc4543_setkey,
+			.setauthsize = rfc4543_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 8,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+	/* Galois Counter Mode */
+	{
+		.aead = {
+			.base = {
+				.cra_name = "gcm(aes)",
+				.cra_driver_name = "gcm-aes-caam",
+				.cra_blocksize = 1,
+			},
+			.setkey = gcm_setkey,
+			.setauthsize = gcm_setauthsize,
+			.encrypt = gcm_encrypt,
+			.decrypt = gcm_decrypt,
+			.ivsize = 12,
+			.maxauthsize = AES_BLOCK_SIZE,
+		},
+		.caam = {
+			.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_GCM,
+		},
+	},
+};
+
+struct caam_crypto_alg {
 	struct crypto_alg crypto_alg;
+	struct list_head entry;
+	struct caam_alg_entry caam;
 };
 
-static int caam_cra_init(struct crypto_tfm *tfm)
+static int caam_init_common(struct caam_ctx *ctx, struct caam_alg_entry *caam)
 {
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct caam_crypto_alg *caam_alg =
-		 container_of(alg, struct caam_crypto_alg, crypto_alg);
-	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
-
 	ctx->jrdev = caam_jr_alloc();
 	if (IS_ERR(ctx->jrdev)) {
 		pr_err("Job Ring Device allocation for transform failed\n");
@@ -4146,17 +4121,35 @@ static int caam_cra_init(struct crypto_tfm *tfm)
 	}
 
 	/* copy descriptor header template value */
-	ctx->class1_alg_type = OP_TYPE_CLASS1_ALG | caam_alg->class1_alg_type;
-	ctx->class2_alg_type = OP_TYPE_CLASS2_ALG | caam_alg->class2_alg_type;
-	ctx->alg_op = OP_TYPE_CLASS2_ALG | caam_alg->alg_op;
+	ctx->class1_alg_type = OP_TYPE_CLASS1_ALG | caam->class1_alg_type;
+	ctx->class2_alg_type = OP_TYPE_CLASS2_ALG | caam->class2_alg_type;
+	ctx->alg_op = OP_TYPE_CLASS2_ALG | caam->alg_op;
 
 	return 0;
 }
 
-static void caam_cra_exit(struct crypto_tfm *tfm)
+static int caam_cra_init(struct crypto_tfm *tfm)
 {
+	struct crypto_alg *alg = tfm->__crt_alg;
+	struct caam_crypto_alg *caam_alg =
+		 container_of(alg, struct caam_crypto_alg, crypto_alg);
 	struct caam_ctx *ctx = crypto_tfm_ctx(tfm);
 
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static int caam_aead_init(struct crypto_aead *tfm)
+{
+	struct aead_alg *alg = crypto_aead_alg(tfm);
+	struct caam_aead_alg *caam_alg =
+		 container_of(alg, struct caam_aead_alg, aead);
+	struct caam_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return caam_init_common(ctx, &caam_alg->caam);
+}
+
+static void caam_exit_common(struct caam_ctx *ctx)
+{
 	if (ctx->sh_desc_enc_dma &&
 	    !dma_mapping_error(ctx->jrdev, ctx->sh_desc_enc_dma))
 		dma_unmap_single(ctx->jrdev, ctx->sh_desc_enc_dma,
@@ -4179,10 +4172,28 @@ static void caam_cra_exit(struct crypto_tfm *tfm)
 	caam_jr_free(ctx->jrdev);
 }
 
+static void caam_cra_exit(struct crypto_tfm *tfm)
+{
+	caam_exit_common(crypto_tfm_ctx(tfm));
+}
+
+static void caam_aead_exit(struct crypto_aead *tfm)
+{
+	caam_exit_common(crypto_aead_ctx(tfm));
+}
+
 static void __exit caam_algapi_exit(void)
 {
 
 	struct caam_crypto_alg *t_alg, *n;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+
+		if (t_alg->registered)
+			crypto_unregister_aead(&t_alg->aead);
+	}
 
 	if (!alg_list.next)
 		return;
@@ -4235,13 +4246,26 @@ static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
 		break;
 	}
 
-	t_alg->class1_alg_type = template->class1_alg_type;
-	t_alg->class2_alg_type = template->class2_alg_type;
-	t_alg->alg_op = template->alg_op;
+	t_alg->caam.class1_alg_type = template->class1_alg_type;
+	t_alg->caam.class2_alg_type = template->class2_alg_type;
+	t_alg->caam.alg_op = template->alg_op;
 
 	return t_alg;
 }
 
+static void caam_aead_alg_init(struct caam_aead_alg *t_alg)
+{
+	struct aead_alg *alg = &t_alg->aead;
+
+	alg->base.cra_module = THIS_MODULE;
+	alg->base.cra_priority = CAAM_CRA_PRIORITY;
+	alg->base.cra_ctxsize = sizeof(struct caam_ctx);
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
+
+	alg->init = caam_aead_init;
+	alg->exit = caam_aead_exit;
+}
+
 static int __init caam_algapi_init(void)
 {
 	struct device_node *dev_node;
@@ -4249,6 +4273,7 @@ static int __init caam_algapi_init(void)
 	struct device *ctrldev;
 	void *priv;
 	int i = 0, err = 0;
+	bool registered = false;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
 	if (!dev_node) {
@@ -4295,10 +4320,30 @@ static int __init caam_algapi_init(void)
 			pr_warn("%s alg registration failed\n",
 				t_alg->crypto_alg.cra_driver_name);
 			kfree(t_alg);
-		} else
-			list_add_tail(&t_alg->entry, &alg_list);
+			continue;
+		}
+
+		list_add_tail(&t_alg->entry, &alg_list);
+		registered = true;
 	}
-	if (!list_empty(&alg_list))
+
+	for (i = 0; i < ARRAY_SIZE(driver_aeads); i++) {
+		struct caam_aead_alg *t_alg = driver_aeads + i;
+
+		caam_aead_alg_init(t_alg);
+
+		err = crypto_register_aead(&t_alg->aead);
+		if (err) {
+			pr_warn("%s alg registration failed\n",
+				t_alg->aead.base.cra_driver_name);
+			continue;
+		}
+
+		t_alg->registered = true;
+		registered = true;
+	}
+
+	if (registered)
 		pr_info("caam algorithms registered in /proc/crypto\n");
 
 	return err;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index ba0532efd3ae..dae1e8099969 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -835,17 +835,17 @@ static int ahash_update_ctx(struct ahash_request *req)
 			src_map_to_sec4_sg(jrdev, req->src, src_nents,
 					   edesc->sec4_sg + sec4_sg_src_index,
 					   chained);
-			if (*next_buflen) {
+			if (*next_buflen)
 				scatterwalk_map_and_copy(next_buf, req->src,
 							 to_hash - *buflen,
 							 *next_buflen, 0);
-				state->current_buf = !state->current_buf;
-			}
 		} else {
 			(edesc->sec4_sg + sec4_sg_src_index - 1)->len |=
 							SEC4_SG_LEN_FIN;
 		}
 
+		state->current_buf = !state->current_buf;
+
 		sh_len = desc_len(sh_desc);
 		desc = edesc->hw_desc;
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
@@ -1268,9 +1268,10 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 			scatterwalk_map_and_copy(next_buf, req->src,
 						 to_hash - *buflen,
 						 *next_buflen, 0);
-			state->current_buf = !state->current_buf;
 		}
 
+		state->current_buf = !state->current_buf;
+
 		sh_len = desc_len(sh_desc);
 		desc = edesc->hw_desc;
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
@@ -1544,6 +1545,8 @@ static int ahash_init(struct ahash_request *req)
 
 	state->current_buf = 0;
 	state->buf_dma = 0;
+	state->buflen_0 = 0;
+	state->buflen_1 = 0;
 
 	return 0;
 }
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index 26a544b505f1..5095337205b8 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -56,7 +56,7 @@
 
 /* Buffer, its dma address and lock */
 struct buf_data {
-	u8 buf[RN_BUF_SIZE];
+	u8 buf[RN_BUF_SIZE] ____cacheline_aligned;
 	dma_addr_t addr;
 	struct completion filled;
 	u32 hw_desc[DESC_JOB_O_LEN];
diff --git a/drivers/crypto/caam/compat.h b/drivers/crypto/caam/compat.h
index acd7743e2603..f57f395db33f 100644
--- a/drivers/crypto/caam/compat.h
+++ b/drivers/crypto/caam/compat.h
@@ -32,7 +32,7 @@
 #include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/md5.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/skcipher.h>
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index efba4ccd4fac..efacab7539ef 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -301,7 +301,7 @@ static int caam_remove(struct platform_device *pdev)
 #endif
 
 	/* Unmap controller region */
-	iounmap(&ctrl);
+	iounmap(ctrl);
 
 	return ret;
 }
@@ -496,7 +496,7 @@ static int caam_probe(struct platform_device *pdev)
 					sizeof(struct platform_device *) * rspec,
 					GFP_KERNEL);
 	if (ctrlpriv->jrpdev == NULL) {
-		iounmap(&ctrl);
+		iounmap(ctrl);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 378ddc17f60e..672c97489505 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -83,35 +83,35 @@
 #endif
 #endif
 
+/*
+ * The only users of these wr/rd_reg64 functions is the Job Ring (JR).
+ * The DMA address registers in the JR are a pair of 32-bit registers.
+ * The layout is:
+ *
+ *    base + 0x0000 : most-significant 32 bits
+ *    base + 0x0004 : least-significant 32 bits
+ *
+ * The 32-bit version of this core therefore has to write to base + 0x0004
+ * to set the 32-bit wide DMA address. This seems to be independent of the
+ * endianness of the written/read data.
+ */
+
 #ifndef CONFIG_64BIT
-#ifdef __BIG_ENDIAN
-static inline void wr_reg64(u64 __iomem *reg, u64 data)
-{
-	wr_reg32((u32 __iomem *)reg, (data & 0xffffffff00000000ull) >> 32);
-	wr_reg32((u32 __iomem *)reg + 1, data & 0x00000000ffffffffull);
-}
+#define REG64_MS32(reg) ((u32 __iomem *)(reg))
+#define REG64_LS32(reg) ((u32 __iomem *)(reg) + 1)
 
-static inline u64 rd_reg64(u64 __iomem *reg)
-{
-	return (((u64)rd_reg32((u32 __iomem *)reg)) << 32) |
-		((u64)rd_reg32((u32 __iomem *)reg + 1));
-}
-#else
-#ifdef __LITTLE_ENDIAN
 static inline void wr_reg64(u64 __iomem *reg, u64 data)
 {
-	wr_reg32((u32 __iomem *)reg + 1, (data & 0xffffffff00000000ull) >> 32);
-	wr_reg32((u32 __iomem *)reg, data & 0x00000000ffffffffull);
+	wr_reg32(REG64_MS32(reg), data >> 32);
+	wr_reg32(REG64_LS32(reg), data);
 }
 
 static inline u64 rd_reg64(u64 __iomem *reg)
 {
-	return (((u64)rd_reg32((u32 __iomem *)reg + 1)) << 32) |
-		((u64)rd_reg32((u32 __iomem *)reg));
+	return ((u64)rd_reg32(REG64_MS32(reg)) << 32 |
+		(u64)rd_reg32(REG64_LS32(reg)));
 }
 #endif
-#endif
-#endif
 
 /*
  * jr_outentry
diff --git a/drivers/crypto/caam/sg_sw_sec4.h b/drivers/crypto/caam/sg_sw_sec4.h
index 3b918218aa4c..b68b74cc7b77 100644
--- a/drivers/crypto/caam/sg_sw_sec4.h
+++ b/drivers/crypto/caam/sg_sw_sec4.h
@@ -55,6 +55,21 @@ static inline void sg_to_sec4_sg_last(struct scatterlist *sg, int sg_count,
 	sec4_sg_ptr->len |= SEC4_SG_LEN_FIN;
 }
 
+static inline struct sec4_sg_entry *sg_to_sec4_sg_len(
+	struct scatterlist *sg, unsigned int total,
+	struct sec4_sg_entry *sec4_sg_ptr)
+{
+	do {
+		unsigned int len = min(sg_dma_len(sg), total);
+
+		dma_to_sec4_sg_one(sec4_sg_ptr, sg_dma_address(sg), len, 0);
+		sec4_sg_ptr++;
+		sg = sg_next(sg);
+		total -= len;
+	} while (total);
+	return sec4_sg_ptr - 1;
+}
+
 /* count number of elements in scatterlist */
 static inline int __sg_count(struct scatterlist *sg_list, int nbytes,
 			     bool *chained)
@@ -85,34 +100,41 @@ static inline int sg_count(struct scatterlist *sg_list, int nbytes,
 	return sg_nents;
 }
 
-static int dma_map_sg_chained(struct device *dev, struct scatterlist *sg,
-			      unsigned int nents, enum dma_data_direction dir,
-			      bool chained)
+static inline void dma_unmap_sg_chained(
+	struct device *dev, struct scatterlist *sg, unsigned int nents,
+	enum dma_data_direction dir, bool chained)
 {
 	if (unlikely(chained)) {
 		int i;
 		for (i = 0; i < nents; i++) {
-			dma_map_sg(dev, sg, 1, dir);
+			dma_unmap_sg(dev, sg, 1, dir);
 			sg = sg_next(sg);
 		}
-	} else {
-		dma_map_sg(dev, sg, nents, dir);
+	} else if (nents) {
+		dma_unmap_sg(dev, sg, nents, dir);
 	}
-	return nents;
 }
 
-static int dma_unmap_sg_chained(struct device *dev, struct scatterlist *sg,
-				unsigned int nents, enum dma_data_direction dir,
-				bool chained)
+static inline int dma_map_sg_chained(
+	struct device *dev, struct scatterlist *sg, unsigned int nents,
+	enum dma_data_direction dir, bool chained)
 {
+	struct scatterlist *first = sg;
+
 	if (unlikely(chained)) {
 		int i;
 		for (i = 0; i < nents; i++) {
-			dma_unmap_sg(dev, sg, 1, dir);
+			if (!dma_map_sg(dev, sg, 1, dir)) {
+				dma_unmap_sg_chained(dev, first, i, dir,
+						     chained);
+				nents = 0;
+				break;
+			}
+
 			sg = sg_next(sg);
 		}
-	} else {
-		dma_unmap_sg(dev, sg, nents, dir);
-	}
+	} else
+		nents = dma_map_sg(dev, sg, nents, dir);
+
 	return nents;
 }
diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig
index 7639ffc36c68..ae38f6b6cc10 100644
--- a/drivers/crypto/ccp/Kconfig
+++ b/drivers/crypto/ccp/Kconfig
@@ -13,7 +13,6 @@ config CRYPTO_DEV_CCP_CRYPTO
 	tristate "Encryption and hashing acceleration support"
 	depends on CRYPTO_DEV_CCP_DD
 	default m
-	select CRYPTO_ALGAPI
 	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AUTHENC
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 71f2e3c89424..d09c6c4af4aa 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -52,8 +52,7 @@ struct ccp_dm_workarea {
 
 struct ccp_sg_workarea {
 	struct scatterlist *sg;
-	unsigned int nents;
-	unsigned int length;
+	int nents;
 
 	struct scatterlist *dma_sg;
 	struct device *dma_dev;
@@ -496,8 +495,10 @@ static int ccp_init_sg_workarea(struct ccp_sg_workarea *wa, struct device *dev,
 	if (!sg)
 		return 0;
 
-	wa->nents = sg_nents(sg);
-	wa->length = sg->length;
+	wa->nents = sg_nents_for_len(sg, len);
+	if (wa->nents < 0)
+		return wa->nents;
+
 	wa->bytes_left = len;
 	wa->sg_used = 0;
 
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
index b1c20b2b5647..f2e6de361fd1 100644
--- a/drivers/crypto/ccp/ccp-platform.c
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -90,58 +90,6 @@ static struct resource *ccp_find_mmio_area(struct ccp_device *ccp)
 	return NULL;
 }
 
-#ifdef CONFIG_ACPI
-static int ccp_acpi_support(struct ccp_device *ccp)
-{
-	struct ccp_platform *ccp_platform = ccp->dev_specific;
-	struct acpi_device *adev = ACPI_COMPANION(ccp->dev);
-	acpi_handle handle;
-	acpi_status status;
-	unsigned long long data;
-	int cca;
-
-	/* Retrieve the device cache coherency value */
-	handle = adev->handle;
-	do {
-		status = acpi_evaluate_integer(handle, "_CCA", NULL, &data);
-		if (!ACPI_FAILURE(status)) {
-			cca = data;
-			break;
-		}
-	} while (!ACPI_FAILURE(status));
-
-	if (ACPI_FAILURE(status)) {
-		dev_err(ccp->dev, "error obtaining acpi coherency value\n");
-		return -EINVAL;
-	}
-
-	ccp_platform->coherent = !!cca;
-
-	return 0;
-}
-#else	/* CONFIG_ACPI */
-static int ccp_acpi_support(struct ccp_device *ccp)
-{
-	return -EINVAL;
-}
-#endif
-
-#ifdef CONFIG_OF
-static int ccp_of_support(struct ccp_device *ccp)
-{
-	struct ccp_platform *ccp_platform = ccp->dev_specific;
-
-	ccp_platform->coherent = of_dma_is_coherent(ccp->dev->of_node);
-
-	return 0;
-}
-#else
-static int ccp_of_support(struct ccp_device *ccp)
-{
-	return -EINVAL;
-}
-#endif
-
 static int ccp_platform_probe(struct platform_device *pdev)
 {
 	struct ccp_device *ccp;
@@ -174,21 +122,13 @@ static int ccp_platform_probe(struct platform_device *pdev)
 	}
 	ccp->io_regs = ccp->io_map;
 
-	if (!dev->dma_mask)
-		dev->dma_mask = &dev->coherent_dma_mask;
 	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
 	if (ret) {
 		dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n", ret);
 		goto e_err;
 	}
 
-	if (ccp_platform->use_acpi)
-		ret = ccp_acpi_support(ccp);
-	else
-		ret = ccp_of_support(ccp);
-	if (ret)
-		goto e_err;
-
+	ccp_platform->coherent = device_dma_is_coherent(ccp->dev);
 	if (ccp_platform->coherent)
 		ccp->axcache = CACHE_WB_NO_ALLOC;
 	else
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 48f453555f1f..7ba495f75370 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -25,7 +25,7 @@
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/algapi.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>
 
@@ -575,7 +575,8 @@ static int init_tfm_ablk(struct crypto_tfm *tfm)
 
 static int init_tfm_aead(struct crypto_tfm *tfm)
 {
-	tfm->crt_aead.reqsize = sizeof(struct aead_ctx);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct aead_ctx));
 	return init_tfm(tfm);
 }
 
@@ -1096,7 +1097,7 @@ static int aead_setup(struct crypto_aead *tfm, unsigned int authsize)
 {
 	struct ixp_ctx *ctx = crypto_aead_ctx(tfm);
 	u32 *flags = &tfm->base.crt_flags;
-	unsigned digest_len = crypto_aead_alg(tfm)->maxauthsize;
+	unsigned digest_len = crypto_aead_maxauthsize(tfm);
 	int ret;
 
 	if (!ctx->enckey_len && !ctx->authkey_len)
@@ -1138,7 +1139,7 @@ out:
 
 static int aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
 {
-	int max = crypto_aead_alg(tfm)->maxauthsize >> 2;
+	int max = crypto_aead_maxauthsize(tfm) >> 2;
 
 	if ((authsize>>2) < 1 || (authsize>>2) > max || (authsize & 3))
 		return -EINVAL;
diff --git a/drivers/crypto/marvell/Makefile b/drivers/crypto/marvell/Makefile
new file mode 100644
index 000000000000..0c12b13574dc
--- /dev/null
+++ b/drivers/crypto/marvell/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell-cesa.o
+marvell-cesa-objs := cesa.o cipher.o hash.o tdma.o
diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c
new file mode 100644
index 000000000000..a432633bced4
--- /dev/null
+++ b/drivers/crypto/marvell/cesa.c
@@ -0,0 +1,548 @@
+/*
+ * Support for Marvell's Cryptographic Engine and Security Accelerator (CESA)
+ * that can be found on the following platform: Orion, Kirkwood, Armada. This
+ * driver supports the TDMA engine on platforms on which it is available.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/genalloc.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kthread.h>
+#include <linux/mbus.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+
+#include "cesa.h"
+
+static int allhwsupport = !IS_ENABLED(CONFIG_CRYPTO_DEV_MV_CESA);
+module_param_named(allhwsupport, allhwsupport, int, 0444);
+MODULE_PARM_DESC(allhwsupport, "Enable support for all hardware (even it if overlaps with the mv_cesa driver)");
+
+struct mv_cesa_dev *cesa_dev;
+
+static void mv_cesa_dequeue_req_unlocked(struct mv_cesa_engine *engine)
+{
+	struct crypto_async_request *req, *backlog;
+	struct mv_cesa_ctx *ctx;
+
+	spin_lock_bh(&cesa_dev->lock);
+	backlog = crypto_get_backlog(&cesa_dev->queue);
+	req = crypto_dequeue_request(&cesa_dev->queue);
+	engine->req = req;
+	spin_unlock_bh(&cesa_dev->lock);
+
+	if (!req)
+		return;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	ctx = crypto_tfm_ctx(req->tfm);
+	ctx->ops->prepare(req, engine);
+	ctx->ops->step(req);
+}
+
+static irqreturn_t mv_cesa_int(int irq, void *priv)
+{
+	struct mv_cesa_engine *engine = priv;
+	struct crypto_async_request *req;
+	struct mv_cesa_ctx *ctx;
+	u32 status, mask;
+	irqreturn_t ret = IRQ_NONE;
+
+	while (true) {
+		int res;
+
+		mask = mv_cesa_get_int_mask(engine);
+		status = readl(engine->regs + CESA_SA_INT_STATUS);
+
+		if (!(status & mask))
+			break;
+
+		/*
+		 * TODO: avoid clearing the FPGA_INT_STATUS if this not
+		 * relevant on some platforms.
+		 */
+		writel(~status, engine->regs + CESA_SA_FPGA_INT_STATUS);
+		writel(~status, engine->regs + CESA_SA_INT_STATUS);
+
+		ret = IRQ_HANDLED;
+		spin_lock_bh(&engine->lock);
+		req = engine->req;
+		spin_unlock_bh(&engine->lock);
+		if (req) {
+			ctx = crypto_tfm_ctx(req->tfm);
+			res = ctx->ops->process(req, status & mask);
+			if (res != -EINPROGRESS) {
+				spin_lock_bh(&engine->lock);
+				engine->req = NULL;
+				mv_cesa_dequeue_req_unlocked(engine);
+				spin_unlock_bh(&engine->lock);
+				ctx->ops->cleanup(req);
+				local_bh_disable();
+				req->complete(req, res);
+				local_bh_enable();
+			} else {
+				ctx->ops->step(req);
+			}
+		}
+	}
+
+	return ret;
+}
+
+int mv_cesa_queue_req(struct crypto_async_request *req)
+{
+	int ret;
+	int i;
+
+	spin_lock_bh(&cesa_dev->lock);
+	ret = crypto_enqueue_request(&cesa_dev->queue, req);
+	spin_unlock_bh(&cesa_dev->lock);
+
+	if (ret != -EINPROGRESS)
+		return ret;
+
+	for (i = 0; i < cesa_dev->caps->nengines; i++) {
+		spin_lock_bh(&cesa_dev->engines[i].lock);
+		if (!cesa_dev->engines[i].req)
+			mv_cesa_dequeue_req_unlocked(&cesa_dev->engines[i]);
+		spin_unlock_bh(&cesa_dev->engines[i].lock);
+	}
+
+	return -EINPROGRESS;
+}
+
+static int mv_cesa_add_algs(struct mv_cesa_dev *cesa)
+{
+	int ret;
+	int i, j;
+
+	for (i = 0; i < cesa->caps->ncipher_algs; i++) {
+		ret = crypto_register_alg(cesa->caps->cipher_algs[i]);
+		if (ret)
+			goto err_unregister_crypto;
+	}
+
+	for (i = 0; i < cesa->caps->nahash_algs; i++) {
+		ret = crypto_register_ahash(cesa->caps->ahash_algs[i]);
+		if (ret)
+			goto err_unregister_ahash;
+	}
+
+	return 0;
+
+err_unregister_ahash:
+	for (j = 0; j < i; j++)
+		crypto_unregister_ahash(cesa->caps->ahash_algs[j]);
+	i = cesa->caps->ncipher_algs;
+
+err_unregister_crypto:
+	for (j = 0; j < i; j++)
+		crypto_unregister_alg(cesa->caps->cipher_algs[j]);
+
+	return ret;
+}
+
+static void mv_cesa_remove_algs(struct mv_cesa_dev *cesa)
+{
+	int i;
+
+	for (i = 0; i < cesa->caps->nahash_algs; i++)
+		crypto_unregister_ahash(cesa->caps->ahash_algs[i]);
+
+	for (i = 0; i < cesa->caps->ncipher_algs; i++)
+		crypto_unregister_alg(cesa->caps->cipher_algs[i]);
+}
+
+static struct crypto_alg *orion_cipher_algs[] = {
+	&mv_cesa_ecb_des_alg,
+	&mv_cesa_cbc_des_alg,
+	&mv_cesa_ecb_des3_ede_alg,
+	&mv_cesa_cbc_des3_ede_alg,
+	&mv_cesa_ecb_aes_alg,
+	&mv_cesa_cbc_aes_alg,
+};
+
+static struct ahash_alg *orion_ahash_algs[] = {
+	&mv_md5_alg,
+	&mv_sha1_alg,
+	&mv_ahmac_md5_alg,
+	&mv_ahmac_sha1_alg,
+};
+
+static struct crypto_alg *armada_370_cipher_algs[] = {
+	&mv_cesa_ecb_des_alg,
+	&mv_cesa_cbc_des_alg,
+	&mv_cesa_ecb_des3_ede_alg,
+	&mv_cesa_cbc_des3_ede_alg,
+	&mv_cesa_ecb_aes_alg,
+	&mv_cesa_cbc_aes_alg,
+};
+
+static struct ahash_alg *armada_370_ahash_algs[] = {
+	&mv_md5_alg,
+	&mv_sha1_alg,
+	&mv_sha256_alg,
+	&mv_ahmac_md5_alg,
+	&mv_ahmac_sha1_alg,
+	&mv_ahmac_sha256_alg,
+};
+
+static const struct mv_cesa_caps orion_caps = {
+	.nengines = 1,
+	.cipher_algs = orion_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(orion_cipher_algs),
+	.ahash_algs = orion_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(orion_ahash_algs),
+	.has_tdma = false,
+};
+
+static const struct mv_cesa_caps kirkwood_caps = {
+	.nengines = 1,
+	.cipher_algs = orion_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(orion_cipher_algs),
+	.ahash_algs = orion_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(orion_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct mv_cesa_caps armada_370_caps = {
+	.nengines = 1,
+	.cipher_algs = armada_370_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(armada_370_cipher_algs),
+	.ahash_algs = armada_370_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(armada_370_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct mv_cesa_caps armada_xp_caps = {
+	.nengines = 2,
+	.cipher_algs = armada_370_cipher_algs,
+	.ncipher_algs = ARRAY_SIZE(armada_370_cipher_algs),
+	.ahash_algs = armada_370_ahash_algs,
+	.nahash_algs = ARRAY_SIZE(armada_370_ahash_algs),
+	.has_tdma = true,
+};
+
+static const struct of_device_id mv_cesa_of_match_table[] = {
+	{ .compatible = "marvell,orion-crypto", .data = &orion_caps },
+	{ .compatible = "marvell,kirkwood-crypto", .data = &kirkwood_caps },
+	{ .compatible = "marvell,dove-crypto", .data = &kirkwood_caps },
+	{ .compatible = "marvell,armada-370-crypto", .data = &armada_370_caps },
+	{ .compatible = "marvell,armada-xp-crypto", .data = &armada_xp_caps },
+	{ .compatible = "marvell,armada-375-crypto", .data = &armada_xp_caps },
+	{ .compatible = "marvell,armada-38x-crypto", .data = &armada_xp_caps },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mv_cesa_of_match_table);
+
+static void
+mv_cesa_conf_mbus_windows(struct mv_cesa_engine *engine,
+			  const struct mbus_dram_target_info *dram)
+{
+	void __iomem *iobase = engine->regs;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		writel(0, iobase + CESA_TDMA_WINDOW_CTRL(i));
+		writel(0, iobase + CESA_TDMA_WINDOW_BASE(i));
+	}
+
+	for (i = 0; i < dram->num_cs; i++) {
+		const struct mbus_dram_window *cs = dram->cs + i;
+
+		writel(((cs->size - 1) & 0xffff0000) |
+		       (cs->mbus_attr << 8) |
+		       (dram->mbus_dram_target_id << 4) | 1,
+		       iobase + CESA_TDMA_WINDOW_CTRL(i));
+		writel(cs->base, iobase + CESA_TDMA_WINDOW_BASE(i));
+	}
+}
+
+static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa)
+{
+	struct device *dev = cesa->dev;
+	struct mv_cesa_dev_dma *dma;
+
+	if (!cesa->caps->has_tdma)
+		return 0;
+
+	dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL);
+	if (!dma)
+		return -ENOMEM;
+
+	dma->tdma_desc_pool = dmam_pool_create("tdma_desc", dev,
+					sizeof(struct mv_cesa_tdma_desc),
+					16, 0);
+	if (!dma->tdma_desc_pool)
+		return -ENOMEM;
+
+	dma->op_pool = dmam_pool_create("cesa_op", dev,
+					sizeof(struct mv_cesa_op_ctx), 16, 0);
+	if (!dma->op_pool)
+		return -ENOMEM;
+
+	dma->cache_pool = dmam_pool_create("cesa_cache", dev,
+					   CESA_MAX_HASH_BLOCK_SIZE, 1, 0);
+	if (!dma->cache_pool)
+		return -ENOMEM;
+
+	dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0);
+	if (!dma->cache_pool)
+		return -ENOMEM;
+
+	cesa->dma = dma;
+
+	return 0;
+}
+
+static int mv_cesa_get_sram(struct platform_device *pdev, int idx)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	struct mv_cesa_engine *engine = &cesa->engines[idx];
+	const char *res_name = "sram";
+	struct resource *res;
+
+	engine->pool = of_get_named_gen_pool(cesa->dev->of_node,
+					     "marvell,crypto-srams",
+					     idx);
+	if (engine->pool) {
+		engine->sram = gen_pool_dma_alloc(engine->pool,
+						  cesa->sram_size,
+						  &engine->sram_dma);
+		if (engine->sram)
+			return 0;
+
+		engine->pool = NULL;
+		return -ENOMEM;
+	}
+
+	if (cesa->caps->nengines > 1) {
+		if (!idx)
+			res_name = "sram0";
+		else
+			res_name = "sram1";
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					   res_name);
+	if (!res || resource_size(res) < cesa->sram_size)
+		return -EINVAL;
+
+	engine->sram = devm_ioremap_resource(cesa->dev, res);
+	if (IS_ERR(engine->sram))
+		return PTR_ERR(engine->sram);
+
+	engine->sram_dma = phys_to_dma(cesa->dev,
+				       (phys_addr_t)res->start);
+
+	return 0;
+}
+
+static void mv_cesa_put_sram(struct platform_device *pdev, int idx)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	struct mv_cesa_engine *engine = &cesa->engines[idx];
+
+	if (!engine->pool)
+		return;
+
+	gen_pool_free(engine->pool, (unsigned long)engine->sram,
+		      cesa->sram_size);
+}
+
+static int mv_cesa_probe(struct platform_device *pdev)
+{
+	const struct mv_cesa_caps *caps = &orion_caps;
+	const struct mbus_dram_target_info *dram;
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct mv_cesa_dev *cesa;
+	struct mv_cesa_engine *engines;
+	struct resource *res;
+	int irq, ret, i;
+	u32 sram_size;
+
+	if (cesa_dev) {
+		dev_err(&pdev->dev, "Only one CESA device authorized\n");
+		return -EEXIST;
+	}
+
+	if (dev->of_node) {
+		match = of_match_node(mv_cesa_of_match_table, dev->of_node);
+		if (!match || !match->data)
+			return -ENOTSUPP;
+
+		caps = match->data;
+	}
+
+	if ((caps == &orion_caps || caps == &kirkwood_caps) && !allhwsupport)
+		return -ENOTSUPP;
+
+	cesa = devm_kzalloc(dev, sizeof(*cesa), GFP_KERNEL);
+	if (!cesa)
+		return -ENOMEM;
+
+	cesa->caps = caps;
+	cesa->dev = dev;
+
+	sram_size = CESA_SA_DEFAULT_SRAM_SIZE;
+	of_property_read_u32(cesa->dev->of_node, "marvell,crypto-sram-size",
+			     &sram_size);
+	if (sram_size < CESA_SA_MIN_SRAM_SIZE)
+		sram_size = CESA_SA_MIN_SRAM_SIZE;
+
+	cesa->sram_size = sram_size;
+	cesa->engines = devm_kzalloc(dev, caps->nengines * sizeof(*engines),
+				     GFP_KERNEL);
+	if (!cesa->engines)
+		return -ENOMEM;
+
+	spin_lock_init(&cesa->lock);
+	crypto_init_queue(&cesa->queue, 50);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
+	cesa->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cesa->regs))
+		return -ENOMEM;
+
+	ret = mv_cesa_dev_dma_init(cesa);
+	if (ret)
+		return ret;
+
+	dram = mv_mbus_dram_info_nooverlap();
+
+	platform_set_drvdata(pdev, cesa);
+
+	for (i = 0; i < caps->nengines; i++) {
+		struct mv_cesa_engine *engine = &cesa->engines[i];
+		char res_name[7];
+
+		engine->id = i;
+		spin_lock_init(&engine->lock);
+
+		ret = mv_cesa_get_sram(pdev, i);
+		if (ret)
+			goto err_cleanup;
+
+		irq = platform_get_irq(pdev, i);
+		if (irq < 0) {
+			ret = irq;
+			goto err_cleanup;
+		}
+
+		/*
+		 * Not all platforms can gate the CESA clocks: do not complain
+		 * if the clock does not exist.
+		 */
+		snprintf(res_name, sizeof(res_name), "cesa%d", i);
+		engine->clk = devm_clk_get(dev, res_name);
+		if (IS_ERR(engine->clk)) {
+			engine->clk = devm_clk_get(dev, NULL);
+			if (IS_ERR(engine->clk))
+				engine->clk = NULL;
+		}
+
+		snprintf(res_name, sizeof(res_name), "cesaz%d", i);
+		engine->zclk = devm_clk_get(dev, res_name);
+		if (IS_ERR(engine->zclk))
+			engine->zclk = NULL;
+
+		ret = clk_prepare_enable(engine->clk);
+		if (ret)
+			goto err_cleanup;
+
+		ret = clk_prepare_enable(engine->zclk);
+		if (ret)
+			goto err_cleanup;
+
+		engine->regs = cesa->regs + CESA_ENGINE_OFF(i);
+
+		if (dram && cesa->caps->has_tdma)
+			mv_cesa_conf_mbus_windows(&cesa->engines[i], dram);
+
+		writel(0, cesa->engines[i].regs + CESA_SA_INT_STATUS);
+		writel(CESA_SA_CFG_STOP_DIG_ERR,
+		       cesa->engines[i].regs + CESA_SA_CFG);
+		writel(engine->sram_dma & CESA_SA_SRAM_MSK,
+		       cesa->engines[i].regs + CESA_SA_DESC_P0);
+
+		ret = devm_request_threaded_irq(dev, irq, NULL, mv_cesa_int,
+						IRQF_ONESHOT,
+						dev_name(&pdev->dev),
+						&cesa->engines[i]);
+		if (ret)
+			goto err_cleanup;
+	}
+
+	cesa_dev = cesa;
+
+	ret = mv_cesa_add_algs(cesa);
+	if (ret) {
+		cesa_dev = NULL;
+		goto err_cleanup;
+	}
+
+	dev_info(dev, "CESA device successfully registered\n");
+
+	return 0;
+
+err_cleanup:
+	for (i = 0; i < caps->nengines; i++) {
+		clk_disable_unprepare(cesa->engines[i].zclk);
+		clk_disable_unprepare(cesa->engines[i].clk);
+		mv_cesa_put_sram(pdev, i);
+	}
+
+	return ret;
+}
+
+static int mv_cesa_remove(struct platform_device *pdev)
+{
+	struct mv_cesa_dev *cesa = platform_get_drvdata(pdev);
+	int i;
+
+	mv_cesa_remove_algs(cesa);
+
+	for (i = 0; i < cesa->caps->nengines; i++) {
+		clk_disable_unprepare(cesa->engines[i].zclk);
+		clk_disable_unprepare(cesa->engines[i].clk);
+		mv_cesa_put_sram(pdev, i);
+	}
+
+	return 0;
+}
+
+static struct platform_driver marvell_cesa = {
+	.probe		= mv_cesa_probe,
+	.remove		= mv_cesa_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "marvell-cesa",
+		.of_match_table = mv_cesa_of_match_table,
+	},
+};
+module_platform_driver(marvell_cesa);
+
+MODULE_ALIAS("platform:mv_crypto");
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_AUTHOR("Arnaud Ebalard <arno@natisbad.org>");
+MODULE_DESCRIPTION("Support for Marvell's cryptographic engine");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
new file mode 100644
index 000000000000..b60698b30d30
--- /dev/null
+++ b/drivers/crypto/marvell/cesa.h
@@ -0,0 +1,791 @@
+#ifndef __MARVELL_CESA_H__
+#define __MARVELL_CESA_H__
+
+#include <crypto/algapi.h>
+#include <crypto/hash.h>
+#include <crypto/internal/hash.h>
+
+#include <linux/crypto.h>
+#include <linux/dmapool.h>
+
+#define CESA_ENGINE_OFF(i)			(((i) * 0x2000))
+
+#define CESA_TDMA_BYTE_CNT			0x800
+#define CESA_TDMA_SRC_ADDR			0x810
+#define CESA_TDMA_DST_ADDR			0x820
+#define CESA_TDMA_NEXT_ADDR			0x830
+
+#define CESA_TDMA_CONTROL			0x840
+#define CESA_TDMA_DST_BURST			GENMASK(2, 0)
+#define CESA_TDMA_DST_BURST_32B			3
+#define CESA_TDMA_DST_BURST_128B		4
+#define CESA_TDMA_OUT_RD_EN			BIT(4)
+#define CESA_TDMA_SRC_BURST			GENMASK(8, 6)
+#define CESA_TDMA_SRC_BURST_32B			(3 << 6)
+#define CESA_TDMA_SRC_BURST_128B		(4 << 6)
+#define CESA_TDMA_CHAIN				BIT(9)
+#define CESA_TDMA_BYTE_SWAP			BIT(11)
+#define CESA_TDMA_NO_BYTE_SWAP			BIT(11)
+#define CESA_TDMA_EN				BIT(12)
+#define CESA_TDMA_FETCH_ND			BIT(13)
+#define CESA_TDMA_ACT				BIT(14)
+
+#define CESA_TDMA_CUR				0x870
+#define CESA_TDMA_ERROR_CAUSE			0x8c8
+#define CESA_TDMA_ERROR_MSK			0x8cc
+
+#define CESA_TDMA_WINDOW_BASE(x)		(((x) * 0x8) + 0xa00)
+#define CESA_TDMA_WINDOW_CTRL(x)		(((x) * 0x8) + 0xa04)
+
+#define CESA_IVDIG(x)				(0xdd00 + ((x) * 4) +	\
+						 (((x) < 5) ? 0 : 0x14))
+
+#define CESA_SA_CMD				0xde00
+#define CESA_SA_CMD_EN_CESA_SA_ACCL0		BIT(0)
+#define CESA_SA_CMD_EN_CESA_SA_ACCL1		BIT(1)
+#define CESA_SA_CMD_DISABLE_SEC			BIT(2)
+
+#define CESA_SA_DESC_P0				0xde04
+
+#define CESA_SA_DESC_P1				0xde14
+
+#define CESA_SA_CFG				0xde08
+#define CESA_SA_CFG_STOP_DIG_ERR		GENMASK(1, 0)
+#define CESA_SA_CFG_DIG_ERR_CONT		0
+#define CESA_SA_CFG_DIG_ERR_SKIP		1
+#define CESA_SA_CFG_DIG_ERR_STOP		3
+#define CESA_SA_CFG_CH0_W_IDMA			BIT(7)
+#define CESA_SA_CFG_CH1_W_IDMA			BIT(8)
+#define CESA_SA_CFG_ACT_CH0_IDMA		BIT(9)
+#define CESA_SA_CFG_ACT_CH1_IDMA		BIT(10)
+#define CESA_SA_CFG_MULTI_PKT			BIT(11)
+#define CESA_SA_CFG_PARA_DIS			BIT(13)
+
+#define CESA_SA_ACCEL_STATUS			0xde0c
+#define CESA_SA_ST_ACT_0			BIT(0)
+#define CESA_SA_ST_ACT_1			BIT(1)
+
+/*
+ * CESA_SA_FPGA_INT_STATUS looks like a FPGA leftover and is documented only
+ * in Errata 4.12. It looks like that it was part of an IRQ-controller in FPGA
+ * and someone forgot to remove  it while switching to the core and moving to
+ * CESA_SA_INT_STATUS.
+ */
+#define CESA_SA_FPGA_INT_STATUS			0xdd68
+#define CESA_SA_INT_STATUS			0xde20
+#define CESA_SA_INT_AUTH_DONE			BIT(0)
+#define CESA_SA_INT_DES_E_DONE			BIT(1)
+#define CESA_SA_INT_AES_E_DONE			BIT(2)
+#define CESA_SA_INT_AES_D_DONE			BIT(3)
+#define CESA_SA_INT_ENC_DONE			BIT(4)
+#define CESA_SA_INT_ACCEL0_DONE			BIT(5)
+#define CESA_SA_INT_ACCEL1_DONE			BIT(6)
+#define CESA_SA_INT_ACC0_IDMA_DONE		BIT(7)
+#define CESA_SA_INT_ACC1_IDMA_DONE		BIT(8)
+#define CESA_SA_INT_IDMA_DONE			BIT(9)
+#define CESA_SA_INT_IDMA_OWN_ERR		BIT(10)
+
+#define CESA_SA_INT_MSK				0xde24
+
+#define CESA_SA_DESC_CFG_OP_MAC_ONLY		0
+#define CESA_SA_DESC_CFG_OP_CRYPT_ONLY		1
+#define CESA_SA_DESC_CFG_OP_MAC_CRYPT		2
+#define CESA_SA_DESC_CFG_OP_CRYPT_MAC		3
+#define CESA_SA_DESC_CFG_OP_MSK			GENMASK(1, 0)
+#define CESA_SA_DESC_CFG_MACM_SHA256		(1 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_SHA256	(3 << 4)
+#define CESA_SA_DESC_CFG_MACM_MD5		(4 << 4)
+#define CESA_SA_DESC_CFG_MACM_SHA1		(5 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_MD5		(6 << 4)
+#define CESA_SA_DESC_CFG_MACM_HMAC_SHA1		(7 << 4)
+#define CESA_SA_DESC_CFG_MACM_MSK		GENMASK(6, 4)
+#define CESA_SA_DESC_CFG_CRYPTM_DES		(1 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_3DES		(2 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_AES		(3 << 8)
+#define CESA_SA_DESC_CFG_CRYPTM_MSK		GENMASK(9, 8)
+#define CESA_SA_DESC_CFG_DIR_ENC		(0 << 12)
+#define CESA_SA_DESC_CFG_DIR_DEC		(1 << 12)
+#define CESA_SA_DESC_CFG_CRYPTCM_ECB		(0 << 16)
+#define CESA_SA_DESC_CFG_CRYPTCM_CBC		(1 << 16)
+#define CESA_SA_DESC_CFG_CRYPTCM_MSK		BIT(16)
+#define CESA_SA_DESC_CFG_3DES_EEE		(0 << 20)
+#define CESA_SA_DESC_CFG_3DES_EDE		(1 << 20)
+#define CESA_SA_DESC_CFG_AES_LEN_128		(0 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_192		(1 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_256		(2 << 24)
+#define CESA_SA_DESC_CFG_AES_LEN_MSK		GENMASK(25, 24)
+#define CESA_SA_DESC_CFG_NOT_FRAG		(0 << 30)
+#define CESA_SA_DESC_CFG_FIRST_FRAG		(1 << 30)
+#define CESA_SA_DESC_CFG_LAST_FRAG		(2 << 30)
+#define CESA_SA_DESC_CFG_MID_FRAG		(3 << 30)
+#define CESA_SA_DESC_CFG_FRAG_MSK		GENMASK(31, 30)
+
+/*
+ * /-----------\ 0
+ * | ACCEL CFG |	4 * 8
+ * |-----------| 0x20
+ * | CRYPT KEY |	8 * 4
+ * |-----------| 0x40
+ * |  IV   IN  |	4 * 4
+ * |-----------| 0x40 (inplace)
+ * |  IV BUF   |	4 * 4
+ * |-----------| 0x80
+ * |  DATA IN  |	16 * x (max ->max_req_size)
+ * |-----------| 0x80 (inplace operation)
+ * |  DATA OUT |	16 * x (max ->max_req_size)
+ * \-----------/ SRAM size
+ */
+
+/*
+ * Hashing memory map:
+ * /-----------\ 0
+ * | ACCEL CFG |        4 * 8
+ * |-----------| 0x20
+ * | Inner IV  |        8 * 4
+ * |-----------| 0x40
+ * | Outer IV  |        8 * 4
+ * |-----------| 0x60
+ * | Output BUF|        8 * 4
+ * |-----------| 0x80
+ * |  DATA IN  |        64 * x (max ->max_req_size)
+ * \-----------/ SRAM size
+ */
+
+#define CESA_SA_CFG_SRAM_OFFSET			0x00
+#define CESA_SA_DATA_SRAM_OFFSET		0x80
+
+#define CESA_SA_CRYPT_KEY_SRAM_OFFSET		0x20
+#define CESA_SA_CRYPT_IV_SRAM_OFFSET		0x40
+
+#define CESA_SA_MAC_IIV_SRAM_OFFSET		0x20
+#define CESA_SA_MAC_OIV_SRAM_OFFSET		0x40
+#define CESA_SA_MAC_DIG_SRAM_OFFSET		0x60
+
+#define CESA_SA_DESC_CRYPT_DATA(offset)					\
+	cpu_to_le32((CESA_SA_DATA_SRAM_OFFSET + (offset)) |		\
+		    ((CESA_SA_DATA_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_DESC_CRYPT_IV(offset)					\
+	cpu_to_le32((CESA_SA_CRYPT_IV_SRAM_OFFSET + (offset)) |	\
+		    ((CESA_SA_CRYPT_IV_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_DESC_CRYPT_KEY(offset)					\
+	cpu_to_le32(CESA_SA_CRYPT_KEY_SRAM_OFFSET + (offset))
+
+#define CESA_SA_DESC_MAC_DATA(offset)					\
+	cpu_to_le32(CESA_SA_DATA_SRAM_OFFSET + (offset))
+#define CESA_SA_DESC_MAC_DATA_MSK		GENMASK(15, 0)
+
+#define CESA_SA_DESC_MAC_TOTAL_LEN(total_len)	cpu_to_le32((total_len) << 16)
+#define CESA_SA_DESC_MAC_TOTAL_LEN_MSK		GENMASK(31, 16)
+
+#define CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX	0xffff
+
+#define CESA_SA_DESC_MAC_DIGEST(offset)					\
+	cpu_to_le32(CESA_SA_MAC_DIG_SRAM_OFFSET + (offset))
+#define CESA_SA_DESC_MAC_DIGEST_MSK		GENMASK(15, 0)
+
+#define CESA_SA_DESC_MAC_FRAG_LEN(frag_len)	cpu_to_le32((frag_len) << 16)
+#define CESA_SA_DESC_MAC_FRAG_LEN_MSK		GENMASK(31, 16)
+
+#define CESA_SA_DESC_MAC_IV(offset)					\
+	cpu_to_le32((CESA_SA_MAC_IIV_SRAM_OFFSET + (offset)) |		\
+		    ((CESA_SA_MAC_OIV_SRAM_OFFSET + (offset)) << 16))
+
+#define CESA_SA_SRAM_SIZE			2048
+#define CESA_SA_SRAM_PAYLOAD_SIZE		(cesa_dev->sram_size - \
+						 CESA_SA_DATA_SRAM_OFFSET)
+
+#define CESA_SA_DEFAULT_SRAM_SIZE		2048
+#define CESA_SA_MIN_SRAM_SIZE			1024
+
+#define CESA_SA_SRAM_MSK			(2048 - 1)
+
+#define CESA_MAX_HASH_BLOCK_SIZE		64
+#define CESA_HASH_BLOCK_SIZE_MSK		(CESA_MAX_HASH_BLOCK_SIZE - 1)
+
+/**
+ * struct mv_cesa_sec_accel_desc - security accelerator descriptor
+ * @config:	engine config
+ * @enc_p:	input and output data pointers for a cipher operation
+ * @enc_len:	cipher operation length
+ * @enc_key_p:	cipher key pointer
+ * @enc_iv:	cipher IV pointers
+ * @mac_src_p:	input pointer and total hash length
+ * @mac_digest:	digest pointer and hash operation length
+ * @mac_iv:	hmac IV pointers
+ *
+ * Structure passed to the CESA engine to describe the crypto operation
+ * to be executed.
+ */
+struct mv_cesa_sec_accel_desc {
+	u32 config;
+	u32 enc_p;
+	u32 enc_len;
+	u32 enc_key_p;
+	u32 enc_iv;
+	u32 mac_src_p;
+	u32 mac_digest;
+	u32 mac_iv;
+};
+
+/**
+ * struct mv_cesa_blkcipher_op_ctx - cipher operation context
+ * @key:	cipher key
+ * @iv:		cipher IV
+ *
+ * Context associated to a cipher operation.
+ */
+struct mv_cesa_blkcipher_op_ctx {
+	u32 key[8];
+	u32 iv[4];
+};
+
+/**
+ * struct mv_cesa_hash_op_ctx - hash or hmac operation context
+ * @key:	cipher key
+ * @iv:		cipher IV
+ *
+ * Context associated to an hash or hmac operation.
+ */
+struct mv_cesa_hash_op_ctx {
+	u32 iv[16];
+	u32 hash[8];
+};
+
+/**
+ * struct mv_cesa_op_ctx - crypto operation context
+ * @desc:	CESA descriptor
+ * @ctx:	context associated to the crypto operation
+ *
+ * Context associated to a crypto operation.
+ */
+struct mv_cesa_op_ctx {
+	struct mv_cesa_sec_accel_desc desc;
+	union {
+		struct mv_cesa_blkcipher_op_ctx blkcipher;
+		struct mv_cesa_hash_op_ctx hash;
+	} ctx;
+};
+
+/* TDMA descriptor flags */
+#define CESA_TDMA_DST_IN_SRAM			BIT(31)
+#define CESA_TDMA_SRC_IN_SRAM			BIT(30)
+#define CESA_TDMA_TYPE_MSK			GENMASK(29, 0)
+#define CESA_TDMA_DUMMY				0
+#define CESA_TDMA_DATA				1
+#define CESA_TDMA_OP				2
+
+/**
+ * struct mv_cesa_tdma_desc - TDMA descriptor
+ * @byte_cnt:	number of bytes to transfer
+ * @src:	DMA address of the source
+ * @dst:	DMA address of the destination
+ * @next_dma:	DMA address of the next TDMA descriptor
+ * @cur_dma:	DMA address of this TDMA descriptor
+ * @next:	pointer to the next TDMA descriptor
+ * @op:		CESA operation attached to this TDMA descriptor
+ * @data:	raw data attached to this TDMA descriptor
+ * @flags:	flags describing the TDMA transfer. See the
+ *		"TDMA descriptor flags" section above
+ *
+ * TDMA descriptor used to create a transfer chain describing a crypto
+ * operation.
+ */
+struct mv_cesa_tdma_desc {
+	u32 byte_cnt;
+	u32 src;
+	u32 dst;
+	u32 next_dma;
+	u32 cur_dma;
+	struct mv_cesa_tdma_desc *next;
+	union {
+		struct mv_cesa_op_ctx *op;
+		void *data;
+	};
+	u32 flags;
+};
+
+/**
+ * struct mv_cesa_sg_dma_iter - scatter-gather iterator
+ * @dir:	transfer direction
+ * @sg:		scatter list
+ * @offset:	current position in the scatter list
+ * @op_offset:	current position in the crypto operation
+ *
+ * Iterator used to iterate over a scatterlist while creating a TDMA chain for
+ * a crypto operation.
+ */
+struct mv_cesa_sg_dma_iter {
+	enum dma_data_direction dir;
+	struct scatterlist *sg;
+	unsigned int offset;
+	unsigned int op_offset;
+};
+
+/**
+ * struct mv_cesa_dma_iter - crypto operation iterator
+ * @len:	the crypto operation length
+ * @offset:	current position in the crypto operation
+ * @op_len:	sub-operation length (the crypto engine can only act on 2kb
+ *		chunks)
+ *
+ * Iterator used to create a TDMA chain for a given crypto operation.
+ */
+struct mv_cesa_dma_iter {
+	unsigned int len;
+	unsigned int offset;
+	unsigned int op_len;
+};
+
+/**
+ * struct mv_cesa_tdma_chain - TDMA chain
+ * @first:	first entry in the TDMA chain
+ * @last:	last entry in the TDMA chain
+ *
+ * Stores a TDMA chain for a specific crypto operation.
+ */
+struct mv_cesa_tdma_chain {
+	struct mv_cesa_tdma_desc *first;
+	struct mv_cesa_tdma_desc *last;
+};
+
+struct mv_cesa_engine;
+
+/**
+ * struct mv_cesa_caps - CESA device capabilities
+ * @engines:		number of engines
+ * @has_tdma:		whether this device has a TDMA block
+ * @cipher_algs:	supported cipher algorithms
+ * @ncipher_algs:	number of supported cipher algorithms
+ * @ahash_algs:		supported hash algorithms
+ * @nahash_algs:	number of supported hash algorithms
+ *
+ * Structure used to describe CESA device capabilities.
+ */
+struct mv_cesa_caps {
+	int nengines;
+	bool has_tdma;
+	struct crypto_alg **cipher_algs;
+	int ncipher_algs;
+	struct ahash_alg **ahash_algs;
+	int nahash_algs;
+};
+
+/**
+ * struct mv_cesa_dev_dma - DMA pools
+ * @tdma_desc_pool:	TDMA desc pool
+ * @op_pool:		crypto operation pool
+ * @cache_pool:		data cache pool (used by hash implementation when the
+ *			hash request is smaller than the hash block size)
+ * @padding_pool:	padding pool (used by hash implementation when hardware
+ *			padding cannot be used)
+ *
+ * Structure containing the different DMA pools used by this driver.
+ */
+struct mv_cesa_dev_dma {
+	struct dma_pool *tdma_desc_pool;
+	struct dma_pool *op_pool;
+	struct dma_pool *cache_pool;
+	struct dma_pool *padding_pool;
+};
+
+/**
+ * struct mv_cesa_dev - CESA device
+ * @caps:	device capabilities
+ * @regs:	device registers
+ * @sram_size:	usable SRAM size
+ * @lock:	device lock
+ * @queue:	crypto request queue
+ * @engines:	array of engines
+ * @dma:	dma pools
+ *
+ * Structure storing CESA device information.
+ */
+struct mv_cesa_dev {
+	const struct mv_cesa_caps *caps;
+	void __iomem *regs;
+	struct device *dev;
+	unsigned int sram_size;
+	spinlock_t lock;
+	struct crypto_queue queue;
+	struct mv_cesa_engine *engines;
+	struct mv_cesa_dev_dma *dma;
+};
+
+/**
+ * struct mv_cesa_engine - CESA engine
+ * @id:			engine id
+ * @regs:		engine registers
+ * @sram:		SRAM memory region
+ * @sram_dma:		DMA address of the SRAM memory region
+ * @lock:		engine lock
+ * @req:		current crypto request
+ * @clk:		engine clk
+ * @zclk:		engine zclk
+ * @max_req_len:	maximum chunk length (useful to create the TDMA chain)
+ * @int_mask:		interrupt mask cache
+ * @pool:		memory pool pointing to the memory region reserved in
+ *			SRAM
+ *
+ * Structure storing CESA engine information.
+ */
+struct mv_cesa_engine {
+	int id;
+	void __iomem *regs;
+	void __iomem *sram;
+	dma_addr_t sram_dma;
+	spinlock_t lock;
+	struct crypto_async_request *req;
+	struct clk *clk;
+	struct clk *zclk;
+	size_t max_req_len;
+	u32 int_mask;
+	struct gen_pool *pool;
+};
+
+/**
+ * struct mv_cesa_req_ops - CESA request operations
+ * @prepare:	prepare a request to be executed on the specified engine
+ * @process:	process a request chunk result (should return 0 if the
+ *		operation, -EINPROGRESS if it needs more steps or an error
+ *		code)
+ * @step:	launch the crypto operation on the next chunk
+ * @cleanup:	cleanup the crypto request (release associated data)
+ */
+struct mv_cesa_req_ops {
+	void (*prepare)(struct crypto_async_request *req,
+			struct mv_cesa_engine *engine);
+	int (*process)(struct crypto_async_request *req, u32 status);
+	void (*step)(struct crypto_async_request *req);
+	void (*cleanup)(struct crypto_async_request *req);
+};
+
+/**
+ * struct mv_cesa_ctx - CESA operation context
+ * @ops:	crypto operations
+ *
+ * Base context structure inherited by operation specific ones.
+ */
+struct mv_cesa_ctx {
+	const struct mv_cesa_req_ops *ops;
+};
+
+/**
+ * struct mv_cesa_hash_ctx - CESA hash operation context
+ * @base:	base context structure
+ *
+ * Hash context structure.
+ */
+struct mv_cesa_hash_ctx {
+	struct mv_cesa_ctx base;
+};
+
+/**
+ * struct mv_cesa_hash_ctx - CESA hmac operation context
+ * @base:	base context structure
+ * @iv:		initialization vectors
+ *
+ * HMAC context structure.
+ */
+struct mv_cesa_hmac_ctx {
+	struct mv_cesa_ctx base;
+	u32 iv[16];
+};
+
+/**
+ * enum mv_cesa_req_type - request type definitions
+ * @CESA_STD_REQ:	standard request
+ * @CESA_DMA_REQ:	DMA request
+ */
+enum mv_cesa_req_type {
+	CESA_STD_REQ,
+	CESA_DMA_REQ,
+};
+
+/**
+ * struct mv_cesa_req - CESA request
+ * @type:	request type
+ * @engine:	engine associated with this request
+ */
+struct mv_cesa_req {
+	enum mv_cesa_req_type type;
+	struct mv_cesa_engine *engine;
+};
+
+/**
+ * struct mv_cesa_tdma_req - CESA TDMA request
+ * @base:	base information
+ * @chain:	TDMA chain
+ */
+struct mv_cesa_tdma_req {
+	struct mv_cesa_req base;
+	struct mv_cesa_tdma_chain chain;
+};
+
+/**
+ * struct mv_cesa_sg_std_iter - CESA scatter-gather iterator for standard
+ *				requests
+ * @iter:	sg mapping iterator
+ * @offset:	current offset in the SG entry mapped in memory
+ */
+struct mv_cesa_sg_std_iter {
+	struct sg_mapping_iter iter;
+	unsigned int offset;
+};
+
+/**
+ * struct mv_cesa_ablkcipher_std_req - cipher standard request
+ * @base:	base information
+ * @op:		operation context
+ * @offset:	current operation offset
+ * @size:	size of the crypto operation
+ */
+struct mv_cesa_ablkcipher_std_req {
+	struct mv_cesa_req base;
+	struct mv_cesa_op_ctx op;
+	unsigned int offset;
+	unsigned int size;
+	bool skip_ctx;
+};
+
+/**
+ * struct mv_cesa_ablkcipher_req - cipher request
+ * @req:	type specific request information
+ * @src_nents:	number of entries in the src sg list
+ * @dst_nents:	number of entries in the dest sg list
+ */
+struct mv_cesa_ablkcipher_req {
+	union {
+		struct mv_cesa_req base;
+		struct mv_cesa_tdma_req dma;
+		struct mv_cesa_ablkcipher_std_req std;
+	} req;
+	int src_nents;
+	int dst_nents;
+};
+
+/**
+ * struct mv_cesa_ahash_std_req - standard hash request
+ * @base:	base information
+ * @offset:	current operation offset
+ */
+struct mv_cesa_ahash_std_req {
+	struct mv_cesa_req base;
+	unsigned int offset;
+};
+
+/**
+ * struct mv_cesa_ahash_dma_req - DMA hash request
+ * @base:		base information
+ * @padding:		padding buffer
+ * @padding_dma:	DMA address of the padding buffer
+ * @cache_dma:		DMA address of the cache buffer
+ */
+struct mv_cesa_ahash_dma_req {
+	struct mv_cesa_tdma_req base;
+	u8 *padding;
+	dma_addr_t padding_dma;
+	dma_addr_t cache_dma;
+};
+
+/**
+ * struct mv_cesa_ahash_req - hash request
+ * @req:		type specific request information
+ * @cache:		cache buffer
+ * @cache_ptr:		write pointer in the cache buffer
+ * @len:		hash total length
+ * @src_nents:		number of entries in the scatterlist
+ * @last_req:		define whether the current operation is the last one
+ *			or not
+ * @state:		hash state
+ */
+struct mv_cesa_ahash_req {
+	union {
+		struct mv_cesa_req base;
+		struct mv_cesa_ahash_dma_req dma;
+		struct mv_cesa_ahash_std_req std;
+	} req;
+	struct mv_cesa_op_ctx op_tmpl;
+	u8 *cache;
+	unsigned int cache_ptr;
+	u64 len;
+	int src_nents;
+	bool last_req;
+	__be32 state[8];
+};
+
+/* CESA functions */
+
+extern struct mv_cesa_dev *cesa_dev;
+
+static inline void mv_cesa_update_op_cfg(struct mv_cesa_op_ctx *op,
+					 u32 cfg, u32 mask)
+{
+	op->desc.config &= cpu_to_le32(~mask);
+	op->desc.config |= cpu_to_le32(cfg);
+}
+
+static inline u32 mv_cesa_get_op_cfg(struct mv_cesa_op_ctx *op)
+{
+	return le32_to_cpu(op->desc.config);
+}
+
+static inline void mv_cesa_set_op_cfg(struct mv_cesa_op_ctx *op, u32 cfg)
+{
+	op->desc.config = cpu_to_le32(cfg);
+}
+
+static inline void mv_cesa_adjust_op(struct mv_cesa_engine *engine,
+				     struct mv_cesa_op_ctx *op)
+{
+	u32 offset = engine->sram_dma & CESA_SA_SRAM_MSK;
+
+	op->desc.enc_p = CESA_SA_DESC_CRYPT_DATA(offset);
+	op->desc.enc_key_p = CESA_SA_DESC_CRYPT_KEY(offset);
+	op->desc.enc_iv = CESA_SA_DESC_CRYPT_IV(offset);
+	op->desc.mac_src_p &= ~CESA_SA_DESC_MAC_DATA_MSK;
+	op->desc.mac_src_p |= CESA_SA_DESC_MAC_DATA(offset);
+	op->desc.mac_digest &= ~CESA_SA_DESC_MAC_DIGEST_MSK;
+	op->desc.mac_digest |= CESA_SA_DESC_MAC_DIGEST(offset);
+	op->desc.mac_iv = CESA_SA_DESC_MAC_IV(offset);
+}
+
+static inline void mv_cesa_set_crypt_op_len(struct mv_cesa_op_ctx *op, int len)
+{
+	op->desc.enc_len = cpu_to_le32(len);
+}
+
+static inline void mv_cesa_set_mac_op_total_len(struct mv_cesa_op_ctx *op,
+						int len)
+{
+	op->desc.mac_src_p &= ~CESA_SA_DESC_MAC_TOTAL_LEN_MSK;
+	op->desc.mac_src_p |= CESA_SA_DESC_MAC_TOTAL_LEN(len);
+}
+
+static inline void mv_cesa_set_mac_op_frag_len(struct mv_cesa_op_ctx *op,
+					       int len)
+{
+	op->desc.mac_digest &= ~CESA_SA_DESC_MAC_FRAG_LEN_MSK;
+	op->desc.mac_digest |= CESA_SA_DESC_MAC_FRAG_LEN(len);
+}
+
+static inline void mv_cesa_set_int_mask(struct mv_cesa_engine *engine,
+					u32 int_mask)
+{
+	if (int_mask == engine->int_mask)
+		return;
+
+	writel(int_mask, engine->regs + CESA_SA_INT_MSK);
+	engine->int_mask = int_mask;
+}
+
+static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
+{
+	return engine->int_mask;
+}
+
+int mv_cesa_queue_req(struct crypto_async_request *req);
+
+/* TDMA functions */
+
+static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
+					     unsigned int len)
+{
+	iter->len = len;
+	iter->op_len = min(len, CESA_SA_SRAM_PAYLOAD_SIZE);
+	iter->offset = 0;
+}
+
+static inline void mv_cesa_sg_dma_iter_init(struct mv_cesa_sg_dma_iter *iter,
+					    struct scatterlist *sg,
+					    enum dma_data_direction dir)
+{
+	iter->op_offset = 0;
+	iter->offset = 0;
+	iter->sg = sg;
+	iter->dir = dir;
+}
+
+static inline unsigned int
+mv_cesa_req_dma_iter_transfer_len(struct mv_cesa_dma_iter *iter,
+				  struct mv_cesa_sg_dma_iter *sgiter)
+{
+	return min(iter->op_len - sgiter->op_offset,
+		   sg_dma_len(sgiter->sg) - sgiter->offset);
+}
+
+bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *chain,
+					struct mv_cesa_sg_dma_iter *sgiter,
+					unsigned int len);
+
+static inline bool mv_cesa_req_dma_iter_next_op(struct mv_cesa_dma_iter *iter)
+{
+	iter->offset += iter->op_len;
+	iter->op_len = min(iter->len - iter->offset,
+			   CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	return iter->op_len;
+}
+
+void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq);
+
+static inline int mv_cesa_dma_process(struct mv_cesa_tdma_req *dreq,
+				      u32 status)
+{
+	if (!(status & CESA_SA_INT_ACC0_IDMA_DONE))
+		return -EINPROGRESS;
+
+	if (status & CESA_SA_INT_IDMA_OWN_ERR)
+		return -EINVAL;
+
+	return 0;
+}
+
+void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+			 struct mv_cesa_engine *engine);
+
+void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq);
+
+static inline void
+mv_cesa_tdma_desc_iter_init(struct mv_cesa_tdma_chain *chain)
+{
+	memset(chain, 0, sizeof(*chain));
+}
+
+struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
+					const struct mv_cesa_op_ctx *op_templ,
+					bool skip_ctx,
+					gfp_t flags);
+
+int mv_cesa_dma_add_data_transfer(struct mv_cesa_tdma_chain *chain,
+				  dma_addr_t dst, dma_addr_t src, u32 size,
+				  u32 flags, gfp_t gfp_flags);
+
+int mv_cesa_dma_add_dummy_launch(struct mv_cesa_tdma_chain *chain,
+				 u32 flags);
+
+int mv_cesa_dma_add_dummy_end(struct mv_cesa_tdma_chain *chain, u32 flags);
+
+int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
+				 struct mv_cesa_dma_iter *dma_iter,
+				 struct mv_cesa_sg_dma_iter *sgiter,
+				 gfp_t gfp_flags);
+
+/* Algorithm definitions */
+
+extern struct ahash_alg mv_md5_alg;
+extern struct ahash_alg mv_sha1_alg;
+extern struct ahash_alg mv_sha256_alg;
+extern struct ahash_alg mv_ahmac_md5_alg;
+extern struct ahash_alg mv_ahmac_sha1_alg;
+extern struct ahash_alg mv_ahmac_sha256_alg;
+
+extern struct crypto_alg mv_cesa_ecb_des_alg;
+extern struct crypto_alg mv_cesa_cbc_des_alg;
+extern struct crypto_alg mv_cesa_ecb_des3_ede_alg;
+extern struct crypto_alg mv_cesa_cbc_des3_ede_alg;
+extern struct crypto_alg mv_cesa_ecb_aes_alg;
+extern struct crypto_alg mv_cesa_cbc_aes_alg;
+
+#endif /* __MARVELL_CESA_H__ */
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
new file mode 100644
index 000000000000..0745cf3b9c0e
--- /dev/null
+++ b/drivers/crypto/marvell/cipher.c
@@ -0,0 +1,797 @@
+/*
+ * Cipher algorithms supported by the CESA: DES, 3DES and AES.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/des.h>
+
+#include "cesa.h"
+
+struct mv_cesa_des_ctx {
+	struct mv_cesa_ctx base;
+	u8 key[DES_KEY_SIZE];
+};
+
+struct mv_cesa_des3_ctx {
+	struct mv_cesa_ctx base;
+	u8 key[DES3_EDE_KEY_SIZE];
+};
+
+struct mv_cesa_aes_ctx {
+	struct mv_cesa_ctx base;
+	struct crypto_aes_ctx aes;
+};
+
+struct mv_cesa_ablkcipher_dma_iter {
+	struct mv_cesa_dma_iter base;
+	struct mv_cesa_sg_dma_iter src;
+	struct mv_cesa_sg_dma_iter dst;
+};
+
+static inline void
+mv_cesa_ablkcipher_req_iter_init(struct mv_cesa_ablkcipher_dma_iter *iter,
+				 struct ablkcipher_request *req)
+{
+	mv_cesa_req_dma_iter_init(&iter->base, req->nbytes);
+	mv_cesa_sg_dma_iter_init(&iter->src, req->src, DMA_TO_DEVICE);
+	mv_cesa_sg_dma_iter_init(&iter->dst, req->dst, DMA_FROM_DEVICE);
+}
+
+static inline bool
+mv_cesa_ablkcipher_req_iter_next_op(struct mv_cesa_ablkcipher_dma_iter *iter)
+{
+	iter->src.op_offset = 0;
+	iter->dst.op_offset = 0;
+
+	return mv_cesa_req_dma_iter_next_op(&iter->base);
+}
+
+static inline void
+mv_cesa_ablkcipher_dma_cleanup(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+
+	if (req->dst != req->src) {
+		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+			     DMA_FROM_DEVICE);
+		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+			     DMA_TO_DEVICE);
+	} else {
+		dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+			     DMA_BIDIRECTIONAL);
+	}
+	mv_cesa_dma_cleanup(&creq->req.dma);
+}
+
+static inline void mv_cesa_ablkcipher_cleanup(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ablkcipher_dma_cleanup(req);
+}
+
+static void mv_cesa_ablkcipher_std_step(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	size_t  len = min_t(size_t, req->nbytes - sreq->offset,
+			    CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	len = sg_pcopy_to_buffer(req->src, creq->src_nents,
+				 engine->sram + CESA_SA_DATA_SRAM_OFFSET,
+				 len, sreq->offset);
+
+	sreq->size = len;
+	mv_cesa_set_crypt_op_len(&sreq->op, len);
+
+	/* FIXME: only update enc_len field */
+	if (!sreq->skip_ctx) {
+		memcpy(engine->sram, &sreq->op, sizeof(sreq->op));
+		sreq->skip_ctx = true;
+	} else {
+		memcpy(engine->sram, &sreq->op, sizeof(sreq->op.desc));
+	}
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
+	writel(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+static int mv_cesa_ablkcipher_std_process(struct ablkcipher_request *req,
+					  u32 status)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	size_t len;
+
+	len = sg_pcopy_from_buffer(req->dst, creq->dst_nents,
+				   engine->sram + CESA_SA_DATA_SRAM_OFFSET,
+				   sreq->size, sreq->offset);
+
+	sreq->offset += len;
+	if (sreq->offset < req->nbytes)
+		return -EINPROGRESS;
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_process(struct crypto_async_request *req,
+				      u32 status)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	int ret;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_dma_process(&creq->req.dma, status);
+	else
+		ret = mv_cesa_ablkcipher_std_process(ablkreq, status);
+
+	if (ret)
+		return ret;
+
+	memcpy(ablkreq->info, engine->sram + CESA_SA_CRYPT_IV_SRAM_OFFSET,
+	       crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(ablkreq)));
+
+	return 0;
+}
+
+static void mv_cesa_ablkcipher_step(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->req.dma);
+	else
+		mv_cesa_ablkcipher_std_step(ablkreq);
+}
+
+static inline void
+mv_cesa_ablkcipher_dma_prepare(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+
+	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+}
+
+static inline void
+mv_cesa_ablkcipher_std_prepare(struct ablkcipher_request *req)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+
+	sreq->size = 0;
+	sreq->offset = 0;
+	mv_cesa_adjust_op(engine, &sreq->op);
+	memcpy(engine->sram, &sreq->op, sizeof(sreq->op));
+}
+
+static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
+					      struct mv_cesa_engine *engine)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
+
+	creq->req.base.engine = engine;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ablkcipher_dma_prepare(ablkreq);
+	else
+		mv_cesa_ablkcipher_std_prepare(ablkreq);
+}
+
+static inline void
+mv_cesa_ablkcipher_req_cleanup(struct crypto_async_request *req)
+{
+	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
+
+	mv_cesa_ablkcipher_cleanup(ablkreq);
+}
+
+static const struct mv_cesa_req_ops mv_cesa_ablkcipher_req_ops = {
+	.step = mv_cesa_ablkcipher_step,
+	.process = mv_cesa_ablkcipher_process,
+	.prepare = mv_cesa_ablkcipher_prepare,
+	.cleanup = mv_cesa_ablkcipher_req_cleanup,
+};
+
+static int mv_cesa_ablkcipher_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ablkcipher_req_ops;
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct mv_cesa_ablkcipher_req);
+
+	return 0;
+}
+
+static int mv_cesa_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			      unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int remaining;
+	int offset;
+	int ret;
+	int i;
+
+	ret = crypto_aes_expand_key(&ctx->aes, key, len);
+	if (ret) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return ret;
+	}
+
+	remaining = (ctx->aes.key_length - 16) / 4;
+	offset = ctx->aes.key_length + 24 - remaining;
+	for (i = 0; i < remaining; i++)
+		ctx->aes.key_dec[4 + i] =
+			cpu_to_le32(ctx->aes.key_enc[offset + i]);
+
+	return 0;
+}
+
+static int mv_cesa_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			      unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 tmp[DES_EXPKEY_WORDS];
+	int ret;
+
+	if (len != DES_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	ret = des_ekey(tmp, key);
+	if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, DES_KEY_SIZE);
+
+	return 0;
+}
+
+static int mv_cesa_des3_ede_setkey(struct crypto_ablkcipher *cipher,
+				   const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (len != DES3_EDE_KEY_SIZE) {
+		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	memcpy(ctx->key, key, DES3_EDE_KEY_SIZE);
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_dma_req_init(struct ablkcipher_request *req,
+				const struct mv_cesa_op_ctx *op_templ)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma;
+	struct mv_cesa_ablkcipher_dma_iter iter;
+	struct mv_cesa_tdma_chain chain;
+	bool skip_ctx = false;
+	int ret;
+
+	dreq->base.type = CESA_DMA_REQ;
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+
+	if (req->src != req->dst) {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_TO_DEVICE);
+		if (!ret)
+			return -ENOMEM;
+
+		ret = dma_map_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+				 DMA_FROM_DEVICE);
+		if (!ret) {
+			ret = -ENOMEM;
+			goto err_unmap_src;
+		}
+	} else {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_BIDIRECTIONAL);
+		if (!ret)
+			return -ENOMEM;
+	}
+
+	mv_cesa_tdma_desc_iter_init(&chain);
+	mv_cesa_ablkcipher_req_iter_init(&iter, req);
+
+	do {
+		struct mv_cesa_op_ctx *op;
+
+		op = mv_cesa_dma_add_op(&chain, op_templ, skip_ctx, flags);
+		if (IS_ERR(op)) {
+			ret = PTR_ERR(op);
+			goto err_free_tdma;
+		}
+		skip_ctx = true;
+
+		mv_cesa_set_crypt_op_len(op, iter.base.op_len);
+
+		/* Add input transfers */
+		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+						   &iter.src, flags);
+		if (ret)
+			goto err_free_tdma;
+
+		/* Add dummy desc to launch the crypto operation */
+		ret = mv_cesa_dma_add_dummy_launch(&chain, flags);
+		if (ret)
+			goto err_free_tdma;
+
+		/* Add output transfers */
+		ret = mv_cesa_dma_add_op_transfers(&chain, &iter.base,
+						   &iter.dst, flags);
+		if (ret)
+			goto err_free_tdma;
+
+	} while (mv_cesa_ablkcipher_req_iter_next_op(&iter));
+
+	dreq->chain = chain;
+
+	return 0;
+
+err_free_tdma:
+	mv_cesa_dma_cleanup(dreq);
+	if (req->dst != req->src)
+		dma_unmap_sg(cesa_dev->dev, req->dst, creq->dst_nents,
+			     DMA_FROM_DEVICE);
+
+err_unmap_src:
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents,
+		     req->dst != req->src ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL);
+
+	return ret;
+}
+
+static inline int
+mv_cesa_ablkcipher_std_req_init(struct ablkcipher_request *req,
+				const struct mv_cesa_op_ctx *op_templ)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct mv_cesa_ablkcipher_std_req *sreq = &creq->req.std;
+
+	sreq->base.type = CESA_STD_REQ;
+	sreq->op = *op_templ;
+	sreq->skip_ctx = false;
+
+	return 0;
+}
+
+static int mv_cesa_ablkcipher_req_init(struct ablkcipher_request *req,
+				       struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(req);
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	unsigned int blksize = crypto_ablkcipher_blocksize(tfm);
+	int ret;
+
+	if (!IS_ALIGNED(req->nbytes, blksize))
+		return -EINVAL;
+
+	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+	creq->dst_nents = sg_nents_for_len(req->dst, req->nbytes);
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_OP_CRYPT_ONLY,
+			      CESA_SA_DESC_CFG_OP_MSK);
+
+	/* TODO: add a threshold for DMA usage */
+	if (cesa_dev->caps->has_tdma)
+		ret = mv_cesa_ablkcipher_dma_req_init(req, tmpl);
+	else
+		ret = mv_cesa_ablkcipher_std_req_init(req, tmpl);
+
+	return ret;
+}
+
+static int mv_cesa_des_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret;
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES_KEY_SIZE);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_des_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_des_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_des_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_des_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_des_alg = {
+	.cra_name = "ecb(des)",
+	.cra_driver_name = "mv-ecb-des",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.setkey = mv_cesa_des_setkey,
+			.encrypt = mv_cesa_ecb_des_encrypt,
+			.decrypt = mv_cesa_ecb_des_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_des_op(struct ablkcipher_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
+			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, DES_BLOCK_SIZE);
+
+	return mv_cesa_des_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_des_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_des_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_des_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_des_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_des_alg = {
+	.cra_name = "cbc(des)",
+	.cra_driver_name = "mv-cbc-des",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES_KEY_SIZE,
+			.max_keysize = DES_KEY_SIZE,
+			.ivsize	     = DES_BLOCK_SIZE,
+			.setkey = mv_cesa_des_setkey,
+			.encrypt = mv_cesa_cbc_des_encrypt,
+			.decrypt = mv_cesa_cbc_des_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_des3_op(struct ablkcipher_request *req,
+			   struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_des3_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret;
+
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTM_3DES,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK);
+
+	memcpy(tmpl->ctx.blkcipher.key, ctx->key, DES3_EDE_KEY_SIZE);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_des3_ede_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_des3_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_des3_ede_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_des3_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_des3_ede_alg = {
+	.cra_name = "ecb(des3_ede)",
+	.cra_driver_name = "mv-ecb-des3-ede",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des3_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize	     = DES3_EDE_BLOCK_SIZE,
+			.setkey = mv_cesa_des3_ede_setkey,
+			.encrypt = mv_cesa_ecb_des3_ede_encrypt,
+			.decrypt = mv_cesa_ecb_des3_ede_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_des3_op(struct ablkcipher_request *req,
+			       struct mv_cesa_op_ctx *tmpl)
+{
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, DES3_EDE_BLOCK_SIZE);
+
+	return mv_cesa_des3_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_des3_ede_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_CBC |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_des3_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_des3_ede_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_CBC |
+			   CESA_SA_DESC_CFG_3DES_EDE |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_des3_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_des3_ede_alg = {
+	.cra_name = "cbc(des3_ede)",
+	.cra_driver_name = "mv-cbc-des3-ede",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_des3_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = DES3_EDE_KEY_SIZE,
+			.max_keysize = DES3_EDE_KEY_SIZE,
+			.ivsize	     = DES3_EDE_BLOCK_SIZE,
+			.setkey = mv_cesa_des3_ede_setkey,
+			.encrypt = mv_cesa_cbc_des3_ede_encrypt,
+			.decrypt = mv_cesa_cbc_des3_ede_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_aes_op(struct ablkcipher_request *req,
+			  struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_aes_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	int ret, i;
+	u32 *key;
+	u32 cfg;
+
+	cfg = CESA_SA_DESC_CFG_CRYPTM_AES;
+
+	if (mv_cesa_get_op_cfg(tmpl) & CESA_SA_DESC_CFG_DIR_DEC)
+		key = ctx->aes.key_dec;
+	else
+		key = ctx->aes.key_enc;
+
+	for (i = 0; i < ctx->aes.key_length / sizeof(u32); i++)
+		tmpl->ctx.blkcipher.key[i] = cpu_to_le32(key[i]);
+
+	if (ctx->aes.key_length == 24)
+		cfg |= CESA_SA_DESC_CFG_AES_LEN_192;
+	else if (ctx->aes.key_length == 32)
+		cfg |= CESA_SA_DESC_CFG_AES_LEN_256;
+
+	mv_cesa_update_op_cfg(tmpl, cfg,
+			      CESA_SA_DESC_CFG_CRYPTM_MSK |
+			      CESA_SA_DESC_CFG_AES_LEN_MSK);
+
+	ret = mv_cesa_ablkcipher_req_init(req, tmpl);
+	if (ret)
+		return ret;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ablkcipher_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ecb_aes_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_aes_op(req, &tmpl);
+}
+
+static int mv_cesa_ecb_aes_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl,
+			   CESA_SA_DESC_CFG_CRYPTCM_ECB |
+			   CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_aes_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_ecb_aes_alg = {
+	.cra_name = "ecb(aes)",
+	.cra_driver_name = "mv-ecb-aes",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_aes_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.setkey = mv_cesa_aes_setkey,
+			.encrypt = mv_cesa_ecb_aes_encrypt,
+			.decrypt = mv_cesa_ecb_aes_decrypt,
+		},
+	},
+};
+
+static int mv_cesa_cbc_aes_op(struct ablkcipher_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	mv_cesa_update_op_cfg(tmpl, CESA_SA_DESC_CFG_CRYPTCM_CBC,
+			      CESA_SA_DESC_CFG_CRYPTCM_MSK);
+	memcpy(tmpl->ctx.blkcipher.iv, req->info, AES_BLOCK_SIZE);
+
+	return mv_cesa_aes_op(req, tmpl);
+}
+
+static int mv_cesa_cbc_aes_encrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_ENC);
+
+	return mv_cesa_cbc_aes_op(req, &tmpl);
+}
+
+static int mv_cesa_cbc_aes_decrypt(struct ablkcipher_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_DIR_DEC);
+
+	return mv_cesa_cbc_aes_op(req, &tmpl);
+}
+
+struct crypto_alg mv_cesa_cbc_aes_alg = {
+	.cra_name = "cbc(aes)",
+	.cra_driver_name = "mv-cbc-aes",
+	.cra_priority = 300,
+	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
+		     CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct mv_cesa_aes_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_ablkcipher_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = mv_cesa_ablkcipher_cra_init,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize = AES_MIN_KEY_SIZE,
+			.max_keysize = AES_MAX_KEY_SIZE,
+			.ivsize = AES_BLOCK_SIZE,
+			.setkey = mv_cesa_aes_setkey,
+			.encrypt = mv_cesa_cbc_aes_encrypt,
+			.decrypt = mv_cesa_cbc_aes_decrypt,
+		},
+	},
+};
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
new file mode 100644
index 000000000000..ae9272eb9c1a
--- /dev/null
+++ b/drivers/crypto/marvell/hash.c
@@ -0,0 +1,1441 @@
+/*
+ * Hash algorithms supported by the CESA: MD5, SHA1 and SHA256.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <crypto/md5.h>
+#include <crypto/sha.h>
+
+#include "cesa.h"
+
+struct mv_cesa_ahash_dma_iter {
+	struct mv_cesa_dma_iter base;
+	struct mv_cesa_sg_dma_iter src;
+};
+
+static inline void
+mv_cesa_ahash_req_iter_init(struct mv_cesa_ahash_dma_iter *iter,
+			    struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int len = req->nbytes;
+
+	if (!creq->last_req)
+		len = (len + creq->cache_ptr) & ~CESA_HASH_BLOCK_SIZE_MSK;
+
+	mv_cesa_req_dma_iter_init(&iter->base, len);
+	mv_cesa_sg_dma_iter_init(&iter->src, req->src, DMA_TO_DEVICE);
+	iter->src.op_offset = creq->cache_ptr;
+}
+
+static inline bool
+mv_cesa_ahash_req_iter_next_op(struct mv_cesa_ahash_dma_iter *iter)
+{
+	iter->src.op_offset = 0;
+
+	return mv_cesa_req_dma_iter_next_op(&iter->base);
+}
+
+static inline int mv_cesa_ahash_dma_alloc_cache(struct mv_cesa_ahash_req *creq,
+						gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *dreq = &creq->req.dma;
+
+	creq->cache = dma_pool_alloc(cesa_dev->dma->cache_pool, flags,
+				     &dreq->cache_dma);
+	if (!creq->cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline int mv_cesa_ahash_std_alloc_cache(struct mv_cesa_ahash_req *creq,
+						gfp_t flags)
+{
+	creq->cache = kzalloc(CESA_MAX_HASH_BLOCK_SIZE, flags);
+	if (!creq->cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int mv_cesa_ahash_alloc_cache(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	int ret;
+
+	if (creq->cache)
+		return 0;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_ahash_dma_alloc_cache(creq, flags);
+	else
+		ret = mv_cesa_ahash_std_alloc_cache(creq, flags);
+
+	return ret;
+}
+
+static inline void mv_cesa_ahash_dma_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	dma_pool_free(cesa_dev->dma->cache_pool, creq->cache,
+		      creq->req.dma.cache_dma);
+}
+
+static inline void mv_cesa_ahash_std_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	kfree(creq->cache);
+}
+
+static void mv_cesa_ahash_free_cache(struct mv_cesa_ahash_req *creq)
+{
+	if (!creq->cache)
+		return;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_free_cache(creq);
+	else
+		mv_cesa_ahash_std_free_cache(creq);
+
+	creq->cache = NULL;
+}
+
+static int mv_cesa_ahash_dma_alloc_padding(struct mv_cesa_ahash_dma_req *req,
+					   gfp_t flags)
+{
+	if (req->padding)
+		return 0;
+
+	req->padding = dma_pool_alloc(cesa_dev->dma->padding_pool, flags,
+				      &req->padding_dma);
+	if (!req->padding)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mv_cesa_ahash_dma_free_padding(struct mv_cesa_ahash_dma_req *req)
+{
+	if (!req->padding)
+		return;
+
+	dma_pool_free(cesa_dev->dma->padding_pool, req->padding,
+		      req->padding_dma);
+	req->padding = NULL;
+}
+
+static inline void mv_cesa_ahash_dma_last_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	mv_cesa_ahash_dma_free_padding(&creq->req.dma);
+}
+
+static inline void mv_cesa_ahash_dma_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
+	mv_cesa_dma_cleanup(&creq->req.dma.base);
+}
+
+static inline void mv_cesa_ahash_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_cleanup(req);
+}
+
+static void mv_cesa_ahash_last_cleanup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	mv_cesa_ahash_free_cache(creq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_last_cleanup(req);
+}
+
+static int mv_cesa_ahash_pad_len(struct mv_cesa_ahash_req *creq)
+{
+	unsigned int index, padlen;
+
+	index = creq->len & CESA_HASH_BLOCK_SIZE_MSK;
+	padlen = (index < 56) ? (56 - index) : (64 + 56 - index);
+
+	return padlen;
+}
+
+static int mv_cesa_ahash_pad_req(struct mv_cesa_ahash_req *creq, u8 *buf)
+{
+	__be64 bits = cpu_to_be64(creq->len << 3);
+	unsigned int index, padlen;
+
+	buf[0] = 0x80;
+	/* Pad out to 56 mod 64 */
+	index = creq->len & CESA_HASH_BLOCK_SIZE_MSK;
+	padlen = mv_cesa_ahash_pad_len(creq);
+	memset(buf + 1, 0, padlen - 1);
+	memcpy(buf + padlen, &bits, sizeof(bits));
+
+	return padlen + 8;
+}
+
+static void mv_cesa_ahash_std_step(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+	struct mv_cesa_op_ctx *op;
+	unsigned int new_cache_ptr = 0;
+	u32 frag_mode;
+	size_t  len;
+
+	if (creq->cache_ptr)
+		memcpy(engine->sram + CESA_SA_DATA_SRAM_OFFSET, creq->cache,
+		       creq->cache_ptr);
+
+	len = min_t(size_t, req->nbytes + creq->cache_ptr - sreq->offset,
+		    CESA_SA_SRAM_PAYLOAD_SIZE);
+
+	if (!creq->last_req) {
+		new_cache_ptr = len & CESA_HASH_BLOCK_SIZE_MSK;
+		len &= ~CESA_HASH_BLOCK_SIZE_MSK;
+	}
+
+	if (len - creq->cache_ptr)
+		sreq->offset += sg_pcopy_to_buffer(req->src, creq->src_nents,
+						   engine->sram +
+						   CESA_SA_DATA_SRAM_OFFSET +
+						   creq->cache_ptr,
+						   len - creq->cache_ptr,
+						   sreq->offset);
+
+	op = &creq->op_tmpl;
+
+	frag_mode = mv_cesa_get_op_cfg(op) & CESA_SA_DESC_CFG_FRAG_MSK;
+
+	if (creq->last_req && sreq->offset == req->nbytes &&
+	    creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+		if (frag_mode == CESA_SA_DESC_CFG_FIRST_FRAG)
+			frag_mode = CESA_SA_DESC_CFG_NOT_FRAG;
+		else if (frag_mode == CESA_SA_DESC_CFG_MID_FRAG)
+			frag_mode = CESA_SA_DESC_CFG_LAST_FRAG;
+	}
+
+	if (frag_mode == CESA_SA_DESC_CFG_NOT_FRAG ||
+	    frag_mode == CESA_SA_DESC_CFG_LAST_FRAG) {
+		if (len &&
+		    creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+			mv_cesa_set_mac_op_total_len(op, creq->len);
+		} else {
+			int trailerlen = mv_cesa_ahash_pad_len(creq) + 8;
+
+			if (len + trailerlen > CESA_SA_SRAM_PAYLOAD_SIZE) {
+				len &= CESA_HASH_BLOCK_SIZE_MSK;
+				new_cache_ptr = 64 - trailerlen;
+				memcpy(creq->cache,
+				       engine->sram +
+				       CESA_SA_DATA_SRAM_OFFSET + len,
+				       new_cache_ptr);
+			} else {
+				len += mv_cesa_ahash_pad_req(creq,
+						engine->sram + len +
+						CESA_SA_DATA_SRAM_OFFSET);
+			}
+
+			if (frag_mode == CESA_SA_DESC_CFG_LAST_FRAG)
+				frag_mode = CESA_SA_DESC_CFG_MID_FRAG;
+			else
+				frag_mode = CESA_SA_DESC_CFG_FIRST_FRAG;
+		}
+	}
+
+	mv_cesa_set_mac_op_frag_len(op, len);
+	mv_cesa_update_op_cfg(op, frag_mode, CESA_SA_DESC_CFG_FRAG_MSK);
+
+	/* FIXME: only update enc_len field */
+	memcpy(engine->sram, op, sizeof(*op));
+
+	if (frag_mode == CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(op, CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	creq->cache_ptr = new_cache_ptr;
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACCEL0_DONE);
+	writel(CESA_SA_CFG_PARA_DIS, engine->regs + CESA_SA_CFG);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+static int mv_cesa_ahash_std_process(struct ahash_request *req, u32 status)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+
+	if (sreq->offset < (req->nbytes - creq->cache_ptr))
+		return -EINPROGRESS;
+
+	return 0;
+}
+
+static inline void mv_cesa_ahash_dma_prepare(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_tdma_req *dreq = &creq->req.dma.base;
+
+	mv_cesa_dma_prepare(dreq, dreq->base.engine);
+}
+
+static void mv_cesa_ahash_std_prepare(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_ahash_std_req *sreq = &creq->req.std;
+	struct mv_cesa_engine *engine = sreq->base.engine;
+
+	sreq->offset = 0;
+	mv_cesa_adjust_op(engine, &creq->op_tmpl);
+	memcpy(engine->sram, &creq->op_tmpl, sizeof(creq->op_tmpl));
+}
+
+static void mv_cesa_ahash_step(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_dma_step(&creq->req.dma.base);
+	else
+		mv_cesa_ahash_std_step(ahashreq);
+}
+
+static int mv_cesa_ahash_process(struct crypto_async_request *req, u32 status)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	struct mv_cesa_engine *engine = creq->req.base.engine;
+	unsigned int digsize;
+	int ret, i;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_dma_process(&creq->req.dma.base, status);
+	else
+		ret = mv_cesa_ahash_std_process(ahashreq, status);
+
+	if (ret == -EINPROGRESS)
+		return ret;
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
+	for (i = 0; i < digsize / 4; i++)
+		creq->state[i] = readl(engine->regs + CESA_IVDIG(i));
+
+	if (creq->cache_ptr)
+		sg_pcopy_to_buffer(ahashreq->src, creq->src_nents,
+				   creq->cache,
+				   creq->cache_ptr,
+				   ahashreq->nbytes - creq->cache_ptr);
+
+	if (creq->last_req) {
+		for (i = 0; i < digsize / 4; i++) {
+			/*
+			 * Hardware provides MD5 digest in a different
+			 * endianness than SHA-1 and SHA-256 ones.
+			 */
+			if (digsize == MD5_DIGEST_SIZE)
+				creq->state[i] = cpu_to_le32(creq->state[i]);
+			else
+				creq->state[i] = cpu_to_be32(creq->state[i]);
+		}
+
+		memcpy(ahashreq->result, creq->state, digsize);
+	}
+
+	return ret;
+}
+
+static void mv_cesa_ahash_prepare(struct crypto_async_request *req,
+				  struct mv_cesa_engine *engine)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+	unsigned int digsize;
+	int i;
+
+	creq->req.base.engine = engine;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		mv_cesa_ahash_dma_prepare(ahashreq);
+	else
+		mv_cesa_ahash_std_prepare(ahashreq);
+
+	digsize = crypto_ahash_digestsize(crypto_ahash_reqtfm(ahashreq));
+	for (i = 0; i < digsize / 4; i++)
+		writel(creq->state[i],
+		       engine->regs + CESA_IVDIG(i));
+}
+
+static void mv_cesa_ahash_req_cleanup(struct crypto_async_request *req)
+{
+	struct ahash_request *ahashreq = ahash_request_cast(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(ahashreq);
+
+	if (creq->last_req)
+		mv_cesa_ahash_last_cleanup(ahashreq);
+
+	mv_cesa_ahash_cleanup(ahashreq);
+}
+
+static const struct mv_cesa_req_ops mv_cesa_ahash_req_ops = {
+	.step = mv_cesa_ahash_step,
+	.process = mv_cesa_ahash_process,
+	.prepare = mv_cesa_ahash_prepare,
+	.cleanup = mv_cesa_ahash_req_cleanup,
+};
+
+static int mv_cesa_ahash_init(struct ahash_request *req,
+			      struct mv_cesa_op_ctx *tmpl)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+
+	memset(creq, 0, sizeof(*creq));
+	mv_cesa_update_op_cfg(tmpl,
+			      CESA_SA_DESC_CFG_OP_MAC_ONLY |
+			      CESA_SA_DESC_CFG_FIRST_FRAG,
+			      CESA_SA_DESC_CFG_OP_MSK |
+			      CESA_SA_DESC_CFG_FRAG_MSK);
+	mv_cesa_set_mac_op_total_len(tmpl, 0);
+	mv_cesa_set_mac_op_frag_len(tmpl, 0);
+	creq->op_tmpl = *tmpl;
+	creq->len = 0;
+
+	return 0;
+}
+
+static inline int mv_cesa_ahash_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_hash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ahash_req_ops;
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct mv_cesa_ahash_req));
+	return 0;
+}
+
+static int mv_cesa_ahash_cache_req(struct ahash_request *req, bool *cached)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	int ret;
+
+	if (((creq->cache_ptr + req->nbytes) & CESA_HASH_BLOCK_SIZE_MSK) &&
+	    !creq->last_req) {
+		ret = mv_cesa_ahash_alloc_cache(req);
+		if (ret)
+			return ret;
+	}
+
+	if (creq->cache_ptr + req->nbytes < 64 && !creq->last_req) {
+		*cached = true;
+
+		if (!req->nbytes)
+			return 0;
+
+		sg_pcopy_to_buffer(req->src, creq->src_nents,
+				   creq->cache + creq->cache_ptr,
+				   req->nbytes, 0);
+
+		creq->cache_ptr += req->nbytes;
+	}
+
+	return 0;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_add_cache(struct mv_cesa_tdma_chain *chain,
+			    struct mv_cesa_ahash_dma_iter *dma_iter,
+			    struct mv_cesa_ahash_req *creq,
+			    gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	struct mv_cesa_op_ctx *op = NULL;
+	int ret;
+
+	if (!creq->cache_ptr)
+		return NULL;
+
+	ret = mv_cesa_dma_add_data_transfer(chain,
+					    CESA_SA_DATA_SRAM_OFFSET,
+					    ahashdreq->cache_dma,
+					    creq->cache_ptr,
+					    CESA_TDMA_DST_IN_SRAM,
+					    flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (!dma_iter->base.op_len) {
+		op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+		if (IS_ERR(op))
+			return op;
+
+		mv_cesa_set_mac_op_frag_len(op, creq->cache_ptr);
+
+		/* Add dummy desc to launch crypto operation */
+		ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	return op;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_add_data(struct mv_cesa_tdma_chain *chain,
+			   struct mv_cesa_ahash_dma_iter *dma_iter,
+			   struct mv_cesa_ahash_req *creq,
+			   gfp_t flags)
+{
+	struct mv_cesa_op_ctx *op;
+	int ret;
+
+	op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+	if (IS_ERR(op))
+		return op;
+
+	mv_cesa_set_mac_op_frag_len(op, dma_iter->base.op_len);
+
+	if ((mv_cesa_get_op_cfg(&creq->op_tmpl) & CESA_SA_DESC_CFG_FRAG_MSK) ==
+	    CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(&creq->op_tmpl,
+				      CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	/* Add input transfers */
+	ret = mv_cesa_dma_add_op_transfers(chain, &dma_iter->base,
+					   &dma_iter->src, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Add dummy desc to launch crypto operation */
+	ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return op;
+}
+
+static struct mv_cesa_op_ctx *
+mv_cesa_ahash_dma_last_req(struct mv_cesa_tdma_chain *chain,
+			   struct mv_cesa_ahash_dma_iter *dma_iter,
+			   struct mv_cesa_ahash_req *creq,
+			   struct mv_cesa_op_ctx *op,
+			   gfp_t flags)
+{
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	unsigned int len, trailerlen, padoff = 0;
+	int ret;
+
+	if (!creq->last_req)
+		return op;
+
+	if (op && creq->len <= CESA_SA_DESC_MAC_SRC_TOTAL_LEN_MAX) {
+		u32 frag = CESA_SA_DESC_CFG_NOT_FRAG;
+
+		if ((mv_cesa_get_op_cfg(op) & CESA_SA_DESC_CFG_FRAG_MSK) !=
+		    CESA_SA_DESC_CFG_FIRST_FRAG)
+			frag = CESA_SA_DESC_CFG_LAST_FRAG;
+
+		mv_cesa_update_op_cfg(op, frag, CESA_SA_DESC_CFG_FRAG_MSK);
+
+		return op;
+	}
+
+	ret = mv_cesa_ahash_dma_alloc_padding(ahashdreq, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	trailerlen = mv_cesa_ahash_pad_req(creq, ahashdreq->padding);
+
+	if (op) {
+		len = min(CESA_SA_SRAM_PAYLOAD_SIZE - dma_iter->base.op_len,
+			  trailerlen);
+		if (len) {
+			ret = mv_cesa_dma_add_data_transfer(chain,
+						CESA_SA_DATA_SRAM_OFFSET +
+						dma_iter->base.op_len,
+						ahashdreq->padding_dma,
+						len, CESA_TDMA_DST_IN_SRAM,
+						flags);
+			if (ret)
+				return ERR_PTR(ret);
+
+			mv_cesa_update_op_cfg(op, CESA_SA_DESC_CFG_MID_FRAG,
+					      CESA_SA_DESC_CFG_FRAG_MSK);
+			mv_cesa_set_mac_op_frag_len(op,
+					dma_iter->base.op_len + len);
+			padoff += len;
+		}
+	}
+
+	if (padoff >= trailerlen)
+		return op;
+
+	if ((mv_cesa_get_op_cfg(&creq->op_tmpl) & CESA_SA_DESC_CFG_FRAG_MSK) !=
+	    CESA_SA_DESC_CFG_FIRST_FRAG)
+		mv_cesa_update_op_cfg(&creq->op_tmpl,
+				      CESA_SA_DESC_CFG_MID_FRAG,
+				      CESA_SA_DESC_CFG_FRAG_MSK);
+
+	op = mv_cesa_dma_add_op(chain, &creq->op_tmpl, false, flags);
+	if (IS_ERR(op))
+		return op;
+
+	mv_cesa_set_mac_op_frag_len(op, trailerlen - padoff);
+
+	ret = mv_cesa_dma_add_data_transfer(chain,
+					    CESA_SA_DATA_SRAM_OFFSET,
+					    ahashdreq->padding_dma +
+					    padoff,
+					    trailerlen - padoff,
+					    CESA_TDMA_DST_IN_SRAM,
+					    flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Add dummy desc to launch crypto operation */
+	ret = mv_cesa_dma_add_dummy_launch(chain, flags);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return op;
+}
+
+static int mv_cesa_ahash_dma_req_init(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	gfp_t flags = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+		      GFP_KERNEL : GFP_ATOMIC;
+	struct mv_cesa_ahash_dma_req *ahashdreq = &creq->req.dma;
+	struct mv_cesa_tdma_req *dreq = &ahashdreq->base;
+	struct mv_cesa_tdma_chain chain;
+	struct mv_cesa_ahash_dma_iter iter;
+	struct mv_cesa_op_ctx *op = NULL;
+	int ret;
+
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+
+	if (creq->src_nents) {
+		ret = dma_map_sg(cesa_dev->dev, req->src, creq->src_nents,
+				 DMA_TO_DEVICE);
+		if (!ret) {
+			ret = -ENOMEM;
+			goto err;
+		}
+	}
+
+	mv_cesa_tdma_desc_iter_init(&chain);
+	mv_cesa_ahash_req_iter_init(&iter, req);
+
+	op = mv_cesa_ahash_dma_add_cache(&chain, &iter,
+					 creq, flags);
+	if (IS_ERR(op)) {
+		ret = PTR_ERR(op);
+		goto err_free_tdma;
+	}
+
+	do {
+		if (!iter.base.op_len)
+			break;
+
+		op = mv_cesa_ahash_dma_add_data(&chain, &iter,
+						creq, flags);
+		if (IS_ERR(op)) {
+			ret = PTR_ERR(op);
+			goto err_free_tdma;
+		}
+	} while (mv_cesa_ahash_req_iter_next_op(&iter));
+
+	op = mv_cesa_ahash_dma_last_req(&chain, &iter, creq, op, flags);
+	if (IS_ERR(op)) {
+		ret = PTR_ERR(op);
+		goto err_free_tdma;
+	}
+
+	if (op) {
+		/* Add dummy desc to wait for crypto operation end */
+		ret = mv_cesa_dma_add_dummy_end(&chain, flags);
+		if (ret)
+			goto err_free_tdma;
+	}
+
+	if (!creq->last_req)
+		creq->cache_ptr = req->nbytes + creq->cache_ptr -
+				  iter.base.len;
+	else
+		creq->cache_ptr = 0;
+
+	dreq->chain = chain;
+
+	return 0;
+
+err_free_tdma:
+	mv_cesa_dma_cleanup(dreq);
+	dma_unmap_sg(cesa_dev->dev, req->src, creq->src_nents, DMA_TO_DEVICE);
+
+err:
+	mv_cesa_ahash_last_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_req_init(struct ahash_request *req, bool *cached)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	int ret;
+
+	if (cesa_dev->caps->has_tdma)
+		creq->req.base.type = CESA_DMA_REQ;
+	else
+		creq->req.base.type = CESA_STD_REQ;
+
+	creq->src_nents = sg_nents_for_len(req->src, req->nbytes);
+
+	ret = mv_cesa_ahash_cache_req(req, cached);
+	if (ret)
+		return ret;
+
+	if (*cached)
+		return 0;
+
+	if (creq->req.base.type == CESA_DMA_REQ)
+		ret = mv_cesa_ahash_dma_req_init(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_update(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	bool cached = false;
+	int ret;
+
+	creq->len += req->nbytes;
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS) {
+		mv_cesa_ahash_cleanup(req);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int mv_cesa_ahash_final(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
+	bool cached = false;
+	int ret;
+
+	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
+	creq->last_req = true;
+	req->nbytes = 0;
+
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ahash_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_ahash_finup(struct ahash_request *req)
+{
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	struct mv_cesa_op_ctx *tmpl = &creq->op_tmpl;
+	bool cached = false;
+	int ret;
+
+	creq->len += req->nbytes;
+	mv_cesa_set_mac_op_total_len(tmpl, creq->len);
+	creq->last_req = true;
+
+	ret = mv_cesa_ahash_req_init(req, &cached);
+	if (ret)
+		return ret;
+
+	if (cached)
+		return 0;
+
+	ret = mv_cesa_queue_req(&req->base);
+	if (ret && ret != -EINPROGRESS)
+		mv_cesa_ahash_cleanup(req);
+
+	return ret;
+}
+
+static int mv_cesa_md5_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_MD5);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_md5_export(struct ahash_request *req, void *out)
+{
+	struct md5_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+
+	out_state->byte_count = creq->len;
+	memcpy(out_state->hash, creq->state, digsize);
+	memset(out_state->block, 0, sizeof(out_state->block));
+	if (creq->cache)
+		memcpy(out_state->block, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_md5_import(struct ahash_request *req, const void *in)
+{
+	const struct md5_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->byte_count;
+	memcpy(creq->state, in_state->hash, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % sizeof(in_state->block);
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->block, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+static int mv_cesa_md5_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_md5_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_md5_alg = {
+	.init = mv_cesa_md5_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_md5_digest,
+	.export = mv_cesa_md5_export,
+	.import = mv_cesa_md5_import,
+	.halg = {
+		.digestsize = MD5_DIGEST_SIZE,
+		.base = {
+			.cra_name = "md5",
+			.cra_driver_name = "mv-md5",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_sha1_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA1);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_sha1_export(struct ahash_request *req, void *out)
+{
+	struct sha1_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+
+	out_state->count = creq->len;
+	memcpy(out_state->state, creq->state, digsize);
+	memset(out_state->buffer, 0, sizeof(out_state->buffer));
+	if (creq->cache)
+		memcpy(out_state->buffer, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_sha1_import(struct ahash_request *req, const void *in)
+{
+	const struct sha1_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->count;
+	memcpy(creq->state, in_state->state, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % SHA1_BLOCK_SIZE;
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->buffer, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+static int mv_cesa_sha1_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_sha1_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_sha1_alg = {
+	.init = mv_cesa_sha1_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_sha1_digest,
+	.export = mv_cesa_sha1_export,
+	.import = mv_cesa_sha1_import,
+	.halg = {
+		.digestsize = SHA1_DIGEST_SIZE,
+		.base = {
+			.cra_name = "sha1",
+			.cra_driver_name = "mv-sha1",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA1_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_sha256_init(struct ahash_request *req)
+{
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_SHA256);
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_sha256_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_sha256_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+static int mv_cesa_sha256_export(struct ahash_request *req, void *out)
+{
+	struct sha256_state *out_state = out;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int ds = crypto_ahash_digestsize(ahash);
+
+	out_state->count = creq->len;
+	memcpy(out_state->state, creq->state, ds);
+	memset(out_state->buf, 0, sizeof(out_state->buf));
+	if (creq->cache)
+		memcpy(out_state->buf, creq->cache, creq->cache_ptr);
+
+	return 0;
+}
+
+static int mv_cesa_sha256_import(struct ahash_request *req, const void *in)
+{
+	const struct sha256_state *in_state = in;
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct mv_cesa_ahash_req *creq = ahash_request_ctx(req);
+	unsigned int digsize = crypto_ahash_digestsize(ahash);
+	unsigned int cache_ptr;
+	int ret;
+
+	creq->len = in_state->count;
+	memcpy(creq->state, in_state->state, digsize);
+	creq->cache_ptr = 0;
+
+	cache_ptr = creq->len % SHA256_BLOCK_SIZE;
+	if (!cache_ptr)
+		return 0;
+
+	ret = mv_cesa_ahash_alloc_cache(req);
+	if (ret)
+		return ret;
+
+	memcpy(creq->cache, in_state->buf, cache_ptr);
+	creq->cache_ptr = cache_ptr;
+
+	return 0;
+}
+
+struct ahash_alg mv_sha256_alg = {
+	.init = mv_cesa_sha256_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_sha256_digest,
+	.export = mv_cesa_sha256_export,
+	.import = mv_cesa_sha256_import,
+	.halg = {
+		.digestsize = SHA256_DIGEST_SIZE,
+		.base = {
+			.cra_name = "sha256",
+			.cra_driver_name = "mv-sha256",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA256_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hash_ctx),
+			.cra_init = mv_cesa_ahash_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+struct mv_cesa_ahash_result {
+	struct completion completion;
+	int error;
+};
+
+static void mv_cesa_hmac_ahash_complete(struct crypto_async_request *req,
+					int error)
+{
+	struct mv_cesa_ahash_result *result = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+
+	result->error = error;
+	complete(&result->completion);
+}
+
+static int mv_cesa_ahmac_iv_state_init(struct ahash_request *req, u8 *pad,
+				       void *state, unsigned int blocksize)
+{
+	struct mv_cesa_ahash_result result;
+	struct scatterlist sg;
+	int ret;
+
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   mv_cesa_hmac_ahash_complete, &result);
+	sg_init_one(&sg, pad, blocksize);
+	ahash_request_set_crypt(req, &sg, pad, blocksize);
+	init_completion(&result.completion);
+
+	ret = crypto_ahash_init(req);
+	if (ret)
+		return ret;
+
+	ret = crypto_ahash_update(req);
+	if (ret && ret != -EINPROGRESS)
+		return ret;
+
+	wait_for_completion_interruptible(&result.completion);
+	if (result.error)
+		return result.error;
+
+	ret = crypto_ahash_export(req, state);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_pad_init(struct ahash_request *req,
+				  const u8 *key, unsigned int keylen,
+				  u8 *ipad, u8 *opad,
+				  unsigned int blocksize)
+{
+	struct mv_cesa_ahash_result result;
+	struct scatterlist sg;
+	int ret;
+	int i;
+
+	if (keylen <= blocksize) {
+		memcpy(ipad, key, keylen);
+	} else {
+		u8 *keydup = kmemdup(key, keylen, GFP_KERNEL);
+
+		if (!keydup)
+			return -ENOMEM;
+
+		ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					   mv_cesa_hmac_ahash_complete,
+					   &result);
+		sg_init_one(&sg, keydup, keylen);
+		ahash_request_set_crypt(req, &sg, ipad, keylen);
+		init_completion(&result.completion);
+
+		ret = crypto_ahash_digest(req);
+		if (ret == -EINPROGRESS) {
+			wait_for_completion_interruptible(&result.completion);
+			ret = result.error;
+		}
+
+		/* Set the memory region to 0 to avoid any leak. */
+		memset(keydup, 0, keylen);
+		kfree(keydup);
+
+		if (ret)
+			return ret;
+
+		keylen = crypto_ahash_digestsize(crypto_ahash_reqtfm(req));
+	}
+
+	memset(ipad + keylen, 0, blocksize - keylen);
+	memcpy(opad, ipad, blocksize);
+
+	for (i = 0; i < blocksize; i++) {
+		ipad[i] ^= 0x36;
+		opad[i] ^= 0x5c;
+	}
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_setkey(const char *hash_alg_name,
+				const u8 *key, unsigned int keylen,
+				void *istate, void *ostate)
+{
+	struct ahash_request *req;
+	struct crypto_ahash *tfm;
+	unsigned int blocksize;
+	u8 *ipad = NULL;
+	u8 *opad;
+	int ret;
+
+	tfm = crypto_alloc_ahash(hash_alg_name, CRYPTO_ALG_TYPE_AHASH,
+				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		ret = -ENOMEM;
+		goto free_ahash;
+	}
+
+	crypto_ahash_clear_flags(tfm, ~0);
+
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
+
+	ipad = kzalloc(2 * blocksize, GFP_KERNEL);
+	if (!ipad) {
+		ret = -ENOMEM;
+		goto free_req;
+	}
+
+	opad = ipad + blocksize;
+
+	ret = mv_cesa_ahmac_pad_init(req, key, keylen, ipad, opad, blocksize);
+	if (ret)
+		goto free_ipad;
+
+	ret = mv_cesa_ahmac_iv_state_init(req, ipad, istate, blocksize);
+	if (ret)
+		goto free_ipad;
+
+	ret = mv_cesa_ahmac_iv_state_init(req, opad, ostate, blocksize);
+
+free_ipad:
+	kfree(ipad);
+free_req:
+	ahash_request_free(req);
+free_ahash:
+	crypto_free_ahash(tfm);
+
+	return ret;
+}
+
+static int mv_cesa_ahmac_cra_init(struct crypto_tfm *tfm)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->base.ops = &mv_cesa_ahash_req_ops;
+
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct mv_cesa_ahash_req));
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_MD5);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_setkey(struct crypto_ahash *tfm, const u8 *key,
+				    unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct md5_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-md5", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.hash); i++)
+		ctx->iv[i] = be32_to_cpu(istate.hash[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.hash); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.hash[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_md5_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_md5_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_md5_alg = {
+	.init = mv_cesa_ahmac_md5_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_md5_digest,
+	.setkey = mv_cesa_ahmac_md5_setkey,
+	.export = mv_cesa_md5_export,
+	.import = mv_cesa_md5_import,
+	.halg = {
+		.digestsize = MD5_DIGEST_SIZE,
+		.statesize = sizeof(struct md5_state),
+		.base = {
+			.cra_name = "hmac(md5)",
+			.cra_driver_name = "mv-hmac-md5",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_ahmac_sha1_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_SHA1);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct sha1_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-sha1", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.state); i++)
+		ctx->iv[i] = be32_to_cpu(istate.state[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.state); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.state[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha1_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_sha1_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_sha1_alg = {
+	.init = mv_cesa_ahmac_sha1_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_sha1_digest,
+	.setkey = mv_cesa_ahmac_sha1_setkey,
+	.export = mv_cesa_sha1_export,
+	.import = mv_cesa_sha1_import,
+	.halg = {
+		.digestsize = SHA1_DIGEST_SIZE,
+		.statesize = sizeof(struct sha1_state),
+		.base = {
+			.cra_name = "hmac(sha1)",
+			.cra_driver_name = "mv-hmac-sha1",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA1_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
+
+static int mv_cesa_ahmac_sha256_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
+	struct sha256_state istate, ostate;
+	int ret, i;
+
+	ret = mv_cesa_ahmac_setkey("mv-sha256", key, keylen, &istate, &ostate);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(istate.state); i++)
+		ctx->iv[i] = be32_to_cpu(istate.state[i]);
+
+	for (i = 0; i < ARRAY_SIZE(ostate.state); i++)
+		ctx->iv[i + 8] = be32_to_cpu(ostate.state[i]);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha256_init(struct ahash_request *req)
+{
+	struct mv_cesa_hmac_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
+	struct mv_cesa_op_ctx tmpl;
+
+	mv_cesa_set_op_cfg(&tmpl, CESA_SA_DESC_CFG_MACM_HMAC_SHA256);
+	memcpy(tmpl.ctx.hash.iv, ctx->iv, sizeof(ctx->iv));
+
+	mv_cesa_ahash_init(req, &tmpl);
+
+	return 0;
+}
+
+static int mv_cesa_ahmac_sha256_digest(struct ahash_request *req)
+{
+	int ret;
+
+	ret = mv_cesa_ahmac_sha256_init(req);
+	if (ret)
+		return ret;
+
+	return mv_cesa_ahash_finup(req);
+}
+
+struct ahash_alg mv_ahmac_sha256_alg = {
+	.init = mv_cesa_ahmac_sha256_init,
+	.update = mv_cesa_ahash_update,
+	.final = mv_cesa_ahash_final,
+	.finup = mv_cesa_ahash_finup,
+	.digest = mv_cesa_ahmac_sha256_digest,
+	.setkey = mv_cesa_ahmac_sha256_setkey,
+	.export = mv_cesa_sha256_export,
+	.import = mv_cesa_sha256_import,
+	.halg = {
+		.digestsize = SHA256_DIGEST_SIZE,
+		.statesize = sizeof(struct sha256_state),
+		.base = {
+			.cra_name = "hmac(sha256)",
+			.cra_driver_name = "mv-hmac-sha256",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = SHA256_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct mv_cesa_hmac_ctx),
+			.cra_init = mv_cesa_ahmac_cra_init,
+			.cra_module = THIS_MODULE,
+		 }
+	}
+};
diff --git a/drivers/crypto/marvell/tdma.c b/drivers/crypto/marvell/tdma.c
new file mode 100644
index 000000000000..64a366c50174
--- /dev/null
+++ b/drivers/crypto/marvell/tdma.c
@@ -0,0 +1,224 @@
+/*
+ * Provide TDMA helper functions used by cipher and hash algorithm
+ * implementations.
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ * Author: Arnaud Ebalard <arno@natisbad.org>
+ *
+ * This work is based on an initial version written by
+ * Sebastian Andrzej Siewior < sebastian at breakpoint dot cc >
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "cesa.h"
+
+bool mv_cesa_req_dma_iter_next_transfer(struct mv_cesa_dma_iter *iter,
+					struct mv_cesa_sg_dma_iter *sgiter,
+					unsigned int len)
+{
+	if (!sgiter->sg)
+		return false;
+
+	sgiter->op_offset += len;
+	sgiter->offset += len;
+	if (sgiter->offset == sg_dma_len(sgiter->sg)) {
+		if (sg_is_last(sgiter->sg))
+			return false;
+		sgiter->offset = 0;
+		sgiter->sg = sg_next(sgiter->sg);
+	}
+
+	if (sgiter->op_offset == iter->op_len)
+		return false;
+
+	return true;
+}
+
+void mv_cesa_dma_step(struct mv_cesa_tdma_req *dreq)
+{
+	struct mv_cesa_engine *engine = dreq->base.engine;
+
+	writel(0, engine->regs + CESA_SA_CFG);
+
+	mv_cesa_set_int_mask(engine, CESA_SA_INT_ACC0_IDMA_DONE);
+	writel(CESA_TDMA_DST_BURST_128B | CESA_TDMA_SRC_BURST_128B |
+	       CESA_TDMA_NO_BYTE_SWAP | CESA_TDMA_EN,
+	       engine->regs + CESA_TDMA_CONTROL);
+
+	writel(CESA_SA_CFG_ACT_CH0_IDMA | CESA_SA_CFG_MULTI_PKT |
+	       CESA_SA_CFG_CH0_W_IDMA | CESA_SA_CFG_PARA_DIS,
+	       engine->regs + CESA_SA_CFG);
+	writel(dreq->chain.first->cur_dma,
+	       engine->regs + CESA_TDMA_NEXT_ADDR);
+	writel(CESA_SA_CMD_EN_CESA_SA_ACCL0, engine->regs + CESA_SA_CMD);
+}
+
+void mv_cesa_dma_cleanup(struct mv_cesa_tdma_req *dreq)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	for (tdma = dreq->chain.first; tdma;) {
+		struct mv_cesa_tdma_desc *old_tdma = tdma;
+
+		if (tdma->flags & CESA_TDMA_OP)
+			dma_pool_free(cesa_dev->dma->op_pool, tdma->op,
+				      le32_to_cpu(tdma->src));
+
+		tdma = tdma->next;
+		dma_pool_free(cesa_dev->dma->tdma_desc_pool, old_tdma,
+			      le32_to_cpu(old_tdma->cur_dma));
+	}
+
+	dreq->chain.first = NULL;
+	dreq->chain.last = NULL;
+}
+
+void mv_cesa_dma_prepare(struct mv_cesa_tdma_req *dreq,
+			 struct mv_cesa_engine *engine)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	for (tdma = dreq->chain.first; tdma; tdma = tdma->next) {
+		if (tdma->flags & CESA_TDMA_DST_IN_SRAM)
+			tdma->dst = cpu_to_le32(tdma->dst + engine->sram_dma);
+
+		if (tdma->flags & CESA_TDMA_SRC_IN_SRAM)
+			tdma->src = cpu_to_le32(tdma->src + engine->sram_dma);
+
+		if (tdma->flags & CESA_TDMA_OP)
+			mv_cesa_adjust_op(engine, tdma->op);
+	}
+}
+
+static struct mv_cesa_tdma_desc *
+mv_cesa_dma_add_desc(struct mv_cesa_tdma_chain *chain, gfp_t flags)
+{
+	struct mv_cesa_tdma_desc *new_tdma = NULL;
+	dma_addr_t dma_handle;
+
+	new_tdma = dma_pool_alloc(cesa_dev->dma->tdma_desc_pool, flags,
+				  &dma_handle);
+	if (!new_tdma)
+		return ERR_PTR(-ENOMEM);
+
+	memset(new_tdma, 0, sizeof(*new_tdma));
+	new_tdma->cur_dma = cpu_to_le32(dma_handle);
+	if (chain->last) {
+		chain->last->next_dma = new_tdma->cur_dma;
+		chain->last->next = new_tdma;
+	} else {
+		chain->first = new_tdma;
+	}
+
+	chain->last = new_tdma;
+
+	return new_tdma;
+}
+
+struct mv_cesa_op_ctx *mv_cesa_dma_add_op(struct mv_cesa_tdma_chain *chain,
+					const struct mv_cesa_op_ctx *op_templ,
+					bool skip_ctx,
+					gfp_t flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+	struct mv_cesa_op_ctx *op;
+	dma_addr_t dma_handle;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return ERR_CAST(tdma);
+
+	op = dma_pool_alloc(cesa_dev->dma->op_pool, flags, &dma_handle);
+	if (!op)
+		return ERR_PTR(-ENOMEM);
+
+	*op = *op_templ;
+
+	tdma = chain->last;
+	tdma->op = op;
+	tdma->byte_cnt = (skip_ctx ? sizeof(op->desc) : sizeof(*op)) | BIT(31);
+	tdma->src = dma_handle;
+	tdma->flags = CESA_TDMA_DST_IN_SRAM | CESA_TDMA_OP;
+
+	return op;
+}
+
+int mv_cesa_dma_add_data_transfer(struct mv_cesa_tdma_chain *chain,
+				  dma_addr_t dst, dma_addr_t src, u32 size,
+				  u32 flags, gfp_t gfp_flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, gfp_flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	tdma->byte_cnt = size | BIT(31);
+	tdma->src = src;
+	tdma->dst = dst;
+
+	flags &= (CESA_TDMA_DST_IN_SRAM | CESA_TDMA_SRC_IN_SRAM);
+	tdma->flags = flags | CESA_TDMA_DATA;
+
+	return 0;
+}
+
+int mv_cesa_dma_add_dummy_launch(struct mv_cesa_tdma_chain *chain,
+				 u32 flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	return 0;
+}
+
+int mv_cesa_dma_add_dummy_end(struct mv_cesa_tdma_chain *chain, u32 flags)
+{
+	struct mv_cesa_tdma_desc *tdma;
+
+	tdma = mv_cesa_dma_add_desc(chain, flags);
+	if (IS_ERR(tdma))
+		return PTR_ERR(tdma);
+
+	tdma->byte_cnt = BIT(31);
+
+	return 0;
+}
+
+int mv_cesa_dma_add_op_transfers(struct mv_cesa_tdma_chain *chain,
+				 struct mv_cesa_dma_iter *dma_iter,
+				 struct mv_cesa_sg_dma_iter *sgiter,
+				 gfp_t gfp_flags)
+{
+	u32 flags = sgiter->dir == DMA_TO_DEVICE ?
+		    CESA_TDMA_DST_IN_SRAM : CESA_TDMA_SRC_IN_SRAM;
+	unsigned int len;
+
+	do {
+		dma_addr_t dst, src;
+		int ret;
+
+		len = mv_cesa_req_dma_iter_transfer_len(dma_iter, sgiter);
+		if (sgiter->dir == DMA_TO_DEVICE) {
+			dst = CESA_SA_DATA_SRAM_OFFSET + sgiter->op_offset;
+			src = sg_dma_address(sgiter->sg) + sgiter->offset;
+		} else {
+			dst = sg_dma_address(sgiter->sg) + sgiter->offset;
+			src = CESA_SA_DATA_SRAM_OFFSET + sgiter->op_offset;
+		}
+
+		ret = mv_cesa_dma_add_data_transfer(chain, dst, src, len,
+						    flags, gfp_flags);
+		if (ret)
+			return ret;
+
+	} while (mv_cesa_req_dma_iter_next_transfer(dma_iter, sgiter, len));
+
+	return 0;
+}
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index f91f15ddee92..5bcd575fa96f 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -9,6 +9,7 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <linux/crypto.h>
+#include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/kthread.h>
@@ -29,6 +30,8 @@
 #define MAX_HW_HASH_SIZE	0xFFFF
 #define MV_CESA_EXPIRE		500 /* msec */
 
+#define MV_CESA_DEFAULT_SRAM_SIZE	2048
+
 /*
  * STM:
  *   /---------------------------------------\
@@ -83,6 +86,8 @@ struct req_progress {
 struct crypto_priv {
 	void __iomem *reg;
 	void __iomem *sram;
+	struct gen_pool *sram_pool;
+	dma_addr_t sram_dma;
 	int irq;
 	struct clk *clk;
 	struct task_struct *queue_th;
@@ -595,7 +600,7 @@ static int queue_manag(void *data)
 	cpg->eng_st = ENGINE_IDLE;
 	do {
 		struct crypto_async_request *async_req = NULL;
-		struct crypto_async_request *backlog;
+		struct crypto_async_request *backlog = NULL;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
 
@@ -1019,6 +1024,39 @@ static struct ahash_alg mv_hmac_sha1_alg = {
 		 }
 };
 
+static int mv_cesa_get_sram(struct platform_device *pdev,
+			    struct crypto_priv *cp)
+{
+	struct resource *res;
+	u32 sram_size = MV_CESA_DEFAULT_SRAM_SIZE;
+
+	of_property_read_u32(pdev->dev.of_node, "marvell,crypto-sram-size",
+			     &sram_size);
+
+	cp->sram_size = sram_size;
+	cp->sram_pool = of_get_named_gen_pool(pdev->dev.of_node,
+					      "marvell,crypto-srams", 0);
+	if (cp->sram_pool) {
+		cp->sram = gen_pool_dma_alloc(cp->sram_pool, sram_size,
+					      &cp->sram_dma);
+		if (cp->sram)
+			return 0;
+
+		return -ENOMEM;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					   "sram");
+	if (!res || resource_size(res) < cp->sram_size)
+		return -EINVAL;
+
+	cp->sram = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(cp->sram))
+		return PTR_ERR(cp->sram);
+
+	return 0;
+}
+
 static int mv_probe(struct platform_device *pdev)
 {
 	struct crypto_priv *cp;
@@ -1041,24 +1079,17 @@ static int mv_probe(struct platform_device *pdev)
 
 	spin_lock_init(&cp->lock);
 	crypto_init_queue(&cp->queue, 50);
-	cp->reg = ioremap(res->start, resource_size(res));
-	if (!cp->reg) {
-		ret = -ENOMEM;
+	cp->reg = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(cp->reg)) {
+		ret = PTR_ERR(cp->reg);
 		goto err;
 	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sram");
-	if (!res) {
-		ret = -ENXIO;
-		goto err_unmap_reg;
-	}
-	cp->sram_size = resource_size(res);
+	ret = mv_cesa_get_sram(pdev, cp);
+	if (ret)
+		goto err;
+
 	cp->max_req_size = cp->sram_size - SRAM_CFG_SPACE;
-	cp->sram = ioremap(res->start, cp->sram_size);
-	if (!cp->sram) {
-		ret = -ENOMEM;
-		goto err_unmap_reg;
-	}
 
 	if (pdev->dev.of_node)
 		irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
@@ -1066,7 +1097,7 @@ static int mv_probe(struct platform_device *pdev)
 		irq = platform_get_irq(pdev, 0);
 	if (irq < 0 || irq == NO_IRQ) {
 		ret = irq;
-		goto err_unmap_sram;
+		goto err;
 	}
 	cp->irq = irq;
 
@@ -1076,7 +1107,7 @@ static int mv_probe(struct platform_device *pdev)
 	cp->queue_th = kthread_run(queue_manag, cp, "mv_crypto");
 	if (IS_ERR(cp->queue_th)) {
 		ret = PTR_ERR(cp->queue_th);
-		goto err_unmap_sram;
+		goto err;
 	}
 
 	ret = request_irq(irq, crypto_int, 0, dev_name(&pdev->dev),
@@ -1134,10 +1165,6 @@ err_irq:
 	}
 err_thread:
 	kthread_stop(cp->queue_th);
-err_unmap_sram:
-	iounmap(cp->sram);
-err_unmap_reg:
-	iounmap(cp->reg);
 err:
 	kfree(cp);
 	cpg = NULL;
@@ -1157,8 +1184,6 @@ static int mv_remove(struct platform_device *pdev)
 	kthread_stop(cp->queue_th);
 	free_irq(cp->irq, cp);
 	memset(cp->sram, 0, cp->sram_size);
-	iounmap(cp->sram);
-	iounmap(cp->reg);
 
 	if (!IS_ERR(cp->clk)) {
 		clk_disable_unprepare(cp->clk);
@@ -1172,6 +1197,8 @@ static int mv_remove(struct platform_device *pdev)
 
 static const struct of_device_id mv_cesa_of_match_table[] = {
 	{ .compatible = "marvell,orion-crypto", },
+	{ .compatible = "marvell,kirkwood-crypto", },
+	{ .compatible = "marvell,dove-crypto", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mv_cesa_of_match_table);
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 10a9aeff1666..2e8dab9d4263 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1281,10 +1281,10 @@ static const char md5_zero[MD5_DIGEST_SIZE] = {
 	0xe9, 0x80, 0x09, 0x98, 0xec, 0xf8, 0x42, 0x7e,
 };
 static const u32 md5_init[MD5_HASH_WORDS] = {
-	cpu_to_le32(0x67452301),
-	cpu_to_le32(0xefcdab89),
-	cpu_to_le32(0x98badcfe),
-	cpu_to_le32(0x10325476),
+	cpu_to_le32(MD5_H0),
+	cpu_to_le32(MD5_H1),
+	cpu_to_le32(MD5_H2),
+	cpu_to_le32(MD5_H3),
 };
 static const char sha1_zero[SHA1_DIGEST_SIZE] = {
 	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d, 0x32,
diff --git a/drivers/crypto/nx/Kconfig b/drivers/crypto/nx/Kconfig
index f82616621ae1..e421c96c763a 100644
--- a/drivers/crypto/nx/Kconfig
+++ b/drivers/crypto/nx/Kconfig
@@ -1,26 +1,55 @@
+
 config CRYPTO_DEV_NX_ENCRYPT
-	tristate "Encryption acceleration support"
-	depends on PPC64 && IBMVIO
+	tristate "Encryption acceleration support on pSeries platform"
+	depends on PPC_PSERIES && IBMVIO && !CPU_LITTLE_ENDIAN
 	default y
 	select CRYPTO_AES
-	select CRYPTO_CBC
-	select CRYPTO_ECB
 	select CRYPTO_CCM
-	select CRYPTO_GCM
-	select CRYPTO_AUTHENC
-	select CRYPTO_XCBC
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
 	help
-	  Support for Power7+ in-Nest encryption acceleration. This
-	  module supports acceleration for AES and SHA2 algorithms. If you
-	  choose 'M' here, this module will be called nx_crypto.
+	  Support for PowerPC Nest (NX) encryption acceleration. This
+	  module supports acceleration for AES and SHA2 algorithms on
+	  the pSeries platform.  If you choose 'M' here, this module
+	  will be called nx_crypto.
 
 config CRYPTO_DEV_NX_COMPRESS
 	tristate "Compression acceleration support"
-	depends on PPC64 && IBMVIO
 	default y
 	help
-	  Support for Power7+ in-Nest compression acceleration. This
-	  module supports acceleration for AES and SHA2 algorithms. If you
-	  choose 'M' here, this module will be called nx_compress.
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  One of the platform drivers must be selected also.
+	  If you choose 'M' here, this module will be called nx_compress.
+
+if CRYPTO_DEV_NX_COMPRESS
+
+config CRYPTO_DEV_NX_COMPRESS_PSERIES
+	tristate "Compression acceleration support on pSeries platform"
+	depends on PPC_PSERIES && IBMVIO
+	default y
+	help
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  This supports NX hardware on the pSeries platform.
+	  If you choose 'M' here, this module will be called nx_compress_pseries.
+
+config CRYPTO_DEV_NX_COMPRESS_POWERNV
+	tristate "Compression acceleration support on PowerNV platform"
+	depends on PPC_POWERNV
+	default y
+	help
+	  Support for PowerPC Nest (NX) compression acceleration. This
+	  module supports acceleration for compressing memory with the 842
+	  algorithm.  This supports NX hardware on the PowerNV platform.
+	  If you choose 'M' here, this module will be called nx_compress_powernv.
+
+config CRYPTO_DEV_NX_COMPRESS_CRYPTO
+	tristate "Compression acceleration cryptographic interface"
+	select CRYPTO_ALGAPI
+	select 842_DECOMPRESS
+	default y
+	help
+	  Support for PowerPC Nest (NX) accelerators using the cryptographic
+	  API.  If you choose 'M' here, this module will be called
+	  nx_compress_crypto.
+
+endif
diff --git a/drivers/crypto/nx/Makefile b/drivers/crypto/nx/Makefile
index bb770ea45ce9..e1684f5adb11 100644
--- a/drivers/crypto/nx/Makefile
+++ b/drivers/crypto/nx/Makefile
@@ -10,5 +10,12 @@ nx-crypto-objs := nx.o \
 		  nx-sha256.o \
 		  nx-sha512.o
 
-obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS) += nx-compress.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS) += nx-compress.o nx-compress-platform.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_PSERIES) += nx-compress-pseries.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_POWERNV) += nx-compress-powernv.o
+obj-$(CONFIG_CRYPTO_DEV_NX_COMPRESS_CRYPTO) += nx-compress-crypto.o
 nx-compress-objs := nx-842.o
+nx-compress-platform-objs := nx-842-platform.o
+nx-compress-pseries-objs := nx-842-pseries.o
+nx-compress-powernv-objs := nx-842-powernv.o
+nx-compress-crypto-objs := nx-842-crypto.o
diff --git a/drivers/crypto/nx/nx-842-crypto.c b/drivers/crypto/nx/nx-842-crypto.c
new file mode 100644
index 000000000000..d53a1dcd7b4e
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-crypto.c
@@ -0,0 +1,580 @@
+/*
+ * Cryptographic API for the NX-842 hardware compression.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) IBM Corporation, 2011-2015
+ *
+ * Original Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *                   Seth Jennings <sjenning@linux.vnet.ibm.com>
+ *
+ * Rewrite: Dan Streetman <ddstreet@ieee.org>
+ *
+ * This is an interface to the NX-842 compression hardware in PowerPC
+ * processors.  Most of the complexity of this drvier is due to the fact that
+ * the NX-842 compression hardware requires the input and output data buffers
+ * to be specifically aligned, to be a specific multiple in length, and within
+ * specific minimum and maximum lengths.  Those restrictions, provided by the
+ * nx-842 driver via nx842_constraints, mean this driver must use bounce
+ * buffers and headers to correct misaligned in or out buffers, and to split
+ * input buffers that are too large.
+ *
+ * This driver will fall back to software decompression if the hardware
+ * decompression fails, so this driver's decompression should never fail as
+ * long as the provided compressed buffer is valid.  Any compressed buffer
+ * created by this driver will have a header (except ones where the input
+ * perfectly matches the constraints); so users of this driver cannot simply
+ * pass a compressed buffer created by this driver over to the 842 software
+ * decompression library.  Instead, users must use this driver to decompress;
+ * if the hardware fails or is unavailable, the compressed buffer will be
+ * parsed and the header removed, and the raw 842 buffer(s) passed to the 842
+ * software decompression library.
+ *
+ * This does not fall back to software compression, however, since the caller
+ * of this function is specifically requesting hardware compression; if the
+ * hardware compression fails, the caller can fall back to software
+ * compression, and the raw 842 compressed buffer that the software compressor
+ * creates can be passed to this driver for hardware decompression; any
+ * buffer without our specific header magic is assumed to be a raw 842 buffer
+ * and passed directly to the hardware.  Note that the software compression
+ * library will produce a compressed buffer that is incompatible with the
+ * hardware decompressor if the original input buffer length is not a multiple
+ * of 8; if such a compressed buffer is passed to this driver for
+ * decompression, the hardware will reject it and this driver will then pass
+ * it over to the software library for decompression.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/sw842.h>
+#include <linux/ratelimit.h>
+
+#include "nx-842.h"
+
+/* The first 5 bits of this magic are 0x1f, which is an invalid 842 5-bit
+ * template (see lib/842/842.h), so this magic number will never appear at
+ * the start of a raw 842 compressed buffer.  That is important, as any buffer
+ * passed to us without this magic is assumed to be a raw 842 compressed
+ * buffer, and passed directly to the hardware to decompress.
+ */
+#define NX842_CRYPTO_MAGIC	(0xf842)
+#define NX842_CRYPTO_GROUP_MAX	(0x20)
+#define NX842_CRYPTO_HEADER_SIZE(g)				\
+	(sizeof(struct nx842_crypto_header) +			\
+	 sizeof(struct nx842_crypto_header_group) * (g))
+#define NX842_CRYPTO_HEADER_MAX_SIZE				\
+	NX842_CRYPTO_HEADER_SIZE(NX842_CRYPTO_GROUP_MAX)
+
+/* bounce buffer size */
+#define BOUNCE_BUFFER_ORDER	(2)
+#define BOUNCE_BUFFER_SIZE					\
+	((unsigned int)(PAGE_SIZE << BOUNCE_BUFFER_ORDER))
+
+/* try longer on comp because we can fallback to sw decomp if hw is busy */
+#define COMP_BUSY_TIMEOUT	(250) /* ms */
+#define DECOMP_BUSY_TIMEOUT	(50) /* ms */
+
+struct nx842_crypto_header_group {
+	__be16 padding;			/* unused bytes at start of group */
+	__be32 compressed_length;	/* compressed bytes in group */
+	__be32 uncompressed_length;	/* bytes after decompression */
+} __packed;
+
+struct nx842_crypto_header {
+	__be16 magic;		/* NX842_CRYPTO_MAGIC */
+	__be16 ignore;		/* decompressed end bytes to ignore */
+	u8 groups;		/* total groups in this header */
+	struct nx842_crypto_header_group group[];
+} __packed;
+
+struct nx842_crypto_param {
+	u8 *in;
+	unsigned int iremain;
+	u8 *out;
+	unsigned int oremain;
+	unsigned int ototal;
+};
+
+static int update_param(struct nx842_crypto_param *p,
+			unsigned int slen, unsigned int dlen)
+{
+	if (p->iremain < slen)
+		return -EOVERFLOW;
+	if (p->oremain < dlen)
+		return -ENOSPC;
+
+	p->in += slen;
+	p->iremain -= slen;
+	p->out += dlen;
+	p->oremain -= dlen;
+	p->ototal += dlen;
+
+	return 0;
+}
+
+struct nx842_crypto_ctx {
+	u8 *wmem;
+	u8 *sbounce, *dbounce;
+
+	struct nx842_crypto_header header;
+	struct nx842_crypto_header_group group[NX842_CRYPTO_GROUP_MAX];
+};
+
+static int nx842_crypto_init(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->wmem = kmalloc(nx842_workmem_size(), GFP_KERNEL);
+	ctx->sbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	ctx->dbounce = (u8 *)__get_free_pages(GFP_KERNEL, BOUNCE_BUFFER_ORDER);
+	if (!ctx->wmem || !ctx->sbounce || !ctx->dbounce) {
+		kfree(ctx->wmem);
+		free_page((unsigned long)ctx->sbounce);
+		free_page((unsigned long)ctx->dbounce);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void nx842_crypto_exit(struct crypto_tfm *tfm)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	kfree(ctx->wmem);
+	free_page((unsigned long)ctx->sbounce);
+	free_page((unsigned long)ctx->dbounce);
+}
+
+static int read_constraints(struct nx842_constraints *c)
+{
+	int ret;
+
+	ret = nx842_constraints(c);
+	if (ret) {
+		pr_err_ratelimited("could not get nx842 constraints : %d\n",
+				   ret);
+		return ret;
+	}
+
+	/* limit maximum, to always have enough bounce buffer to decompress */
+	if (c->maximum > BOUNCE_BUFFER_SIZE) {
+		c->maximum = BOUNCE_BUFFER_SIZE;
+		pr_info_once("limiting nx842 maximum to %x\n", c->maximum);
+	}
+
+	return 0;
+}
+
+static int nx842_crypto_add_header(struct nx842_crypto_header *hdr, u8 *buf)
+{
+	int s = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
+
+	/* compress should have added space for header */
+	if (s > be16_to_cpu(hdr->group[0].padding)) {
+		pr_err("Internal error: no space for header\n");
+		return -EINVAL;
+	}
+
+	memcpy(buf, hdr, s);
+
+	print_hex_dump_debug("header ", DUMP_PREFIX_OFFSET, 16, 1, buf, s, 0);
+
+	return 0;
+}
+
+static int compress(struct nx842_crypto_ctx *ctx,
+		    struct nx842_crypto_param *p,
+		    struct nx842_crypto_header_group *g,
+		    struct nx842_constraints *c,
+		    u16 *ignore,
+		    unsigned int hdrsize)
+{
+	unsigned int slen = p->iremain, dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	int ret, dskip = 0;
+	ktime_t timeout;
+
+	if (p->iremain == 0)
+		return -EOVERFLOW;
+
+	if (p->oremain == 0 || hdrsize + c->minimum > dlen)
+		return -ENOSPC;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		adj_slen = slen = c->maximum;
+	if (adj_slen > slen || (u64)src % c->alignment) {
+		adj_slen = min(adj_slen, BOUNCE_BUFFER_SIZE);
+		slen = min(slen, BOUNCE_BUFFER_SIZE);
+		if (adj_slen > slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		slen = adj_slen;
+		pr_debug("using comp sbounce buffer, len %x\n", slen);
+	}
+
+	dst += hdrsize;
+	dlen -= hdrsize;
+
+	if ((u64)dst % c->alignment) {
+		dskip = (int)(PTR_ALIGN(dst, c->alignment) - dst);
+		dst += dskip;
+		dlen -= dskip;
+	}
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < c->minimum) {
+nospc:
+		dst = ctx->dbounce;
+		dlen = min(p->oremain, BOUNCE_BUFFER_SIZE);
+		dlen = round_down(dlen, c->multiple);
+		dskip = 0;
+		pr_debug("using comp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), COMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = nx842_compress(src, slen, dst, &dlen, ctx->wmem);
+		/* possibly we should reduce the slen here, instead of
+		 * retrying with the dbounce buffer?
+		 */
+		if (ret == -ENOSPC && dst != ctx->dbounce)
+			goto nospc;
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret)
+		return ret;
+
+	dskip += hdrsize;
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out + dskip, dst, dlen);
+
+	g->padding = cpu_to_be16(dskip);
+	g->compressed_length = cpu_to_be32(dlen);
+	g->uncompressed_length = cpu_to_be32(slen);
+
+	if (p->iremain < slen) {
+		*ignore = slen - p->iremain;
+		slen = p->iremain;
+	}
+
+	pr_debug("compress slen %x ignore %x dlen %x padding %x\n",
+		 slen, *ignore, dlen, dskip);
+
+	return update_param(p, slen, dskip + dlen);
+}
+
+static int nx842_crypto_compress(struct crypto_tfm *tfm,
+				 const u8 *src, unsigned int slen,
+				 u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr = &ctx->header;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c;
+	unsigned int groups, hdrsize, h;
+	int ret, n;
+	bool add_header;
+	u16 ignore = 0;
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	ret = read_constraints(&c);
+	if (ret)
+		return ret;
+
+	groups = min_t(unsigned int, NX842_CRYPTO_GROUP_MAX,
+		       DIV_ROUND_UP(p.iremain, c.maximum));
+	hdrsize = NX842_CRYPTO_HEADER_SIZE(groups);
+
+	/* skip adding header if the buffers meet all constraints */
+	add_header = (p.iremain % c.multiple	||
+		      p.iremain < c.minimum	||
+		      p.iremain > c.maximum	||
+		      (u64)p.in % c.alignment	||
+		      p.oremain % c.multiple	||
+		      p.oremain < c.minimum	||
+		      p.oremain > c.maximum	||
+		      (u64)p.out % c.alignment);
+
+	hdr->magic = cpu_to_be16(NX842_CRYPTO_MAGIC);
+	hdr->groups = 0;
+	hdr->ignore = 0;
+
+	while (p.iremain > 0) {
+		n = hdr->groups++;
+		if (hdr->groups > NX842_CRYPTO_GROUP_MAX)
+			return -ENOSPC;
+
+		/* header goes before first group */
+		h = !n && add_header ? hdrsize : 0;
+
+		if (ignore)
+			pr_warn("interal error, ignore is set %x\n", ignore);
+
+		ret = compress(ctx, &p, &hdr->group[n], &c, &ignore, h);
+		if (ret)
+			return ret;
+	}
+
+	if (!add_header && hdr->groups > 1) {
+		pr_err("Internal error: No header but multiple groups\n");
+		return -EINVAL;
+	}
+
+	/* ignore indicates the input stream needed to be padded */
+	hdr->ignore = cpu_to_be16(ignore);
+	if (ignore)
+		pr_debug("marked %d bytes as ignore\n", ignore);
+
+	if (add_header)
+		ret = nx842_crypto_add_header(hdr, dst);
+	if (ret)
+		return ret;
+
+	*dlen = p.ototal;
+
+	pr_debug("compress total slen %x dlen %x\n", slen, *dlen);
+
+	return 0;
+}
+
+static int decompress(struct nx842_crypto_ctx *ctx,
+		      struct nx842_crypto_param *p,
+		      struct nx842_crypto_header_group *g,
+		      struct nx842_constraints *c,
+		      u16 ignore,
+		      bool usehw)
+{
+	unsigned int slen = be32_to_cpu(g->compressed_length);
+	unsigned int required_len = be32_to_cpu(g->uncompressed_length);
+	unsigned int dlen = p->oremain, tmplen;
+	unsigned int adj_slen = slen;
+	u8 *src = p->in, *dst = p->out;
+	u16 padding = be16_to_cpu(g->padding);
+	int ret, spadding = 0, dpadding = 0;
+	ktime_t timeout;
+
+	if (!slen || !required_len)
+		return -EINVAL;
+
+	if (p->iremain <= 0 || padding + slen > p->iremain)
+		return -EOVERFLOW;
+
+	if (p->oremain <= 0 || required_len - ignore > p->oremain)
+		return -ENOSPC;
+
+	src += padding;
+
+	if (!usehw)
+		goto usesw;
+
+	if (slen % c->multiple)
+		adj_slen = round_up(slen, c->multiple);
+	if (slen < c->minimum)
+		adj_slen = c->minimum;
+	if (slen > c->maximum)
+		goto usesw;
+	if (slen < adj_slen || (u64)src % c->alignment) {
+		/* we can append padding bytes because the 842 format defines
+		 * an "end" template (see lib/842/842_decompress.c) and will
+		 * ignore any bytes following it.
+		 */
+		if (slen < adj_slen)
+			memset(ctx->sbounce + slen, 0, adj_slen - slen);
+		memcpy(ctx->sbounce, src, slen);
+		src = ctx->sbounce;
+		spadding = adj_slen - slen;
+		slen = adj_slen;
+		pr_debug("using decomp sbounce buffer, len %x\n", slen);
+	}
+
+	if (dlen % c->multiple)
+		dlen = round_down(dlen, c->multiple);
+	if (dlen < required_len || (u64)dst % c->alignment) {
+		dst = ctx->dbounce;
+		dlen = min(required_len, BOUNCE_BUFFER_SIZE);
+		pr_debug("using decomp dbounce buffer, len %x\n", dlen);
+	}
+	if (dlen < c->minimum)
+		goto usesw;
+	if (dlen > c->maximum)
+		dlen = c->maximum;
+
+	tmplen = dlen;
+	timeout = ktime_add_ms(ktime_get(), DECOMP_BUSY_TIMEOUT);
+	do {
+		dlen = tmplen; /* reset dlen, if we're retrying */
+		ret = nx842_decompress(src, slen, dst, &dlen, ctx->wmem);
+	} while (ret == -EBUSY && ktime_before(ktime_get(), timeout));
+	if (ret) {
+usesw:
+		/* reset everything, sw doesn't have constraints */
+		src = p->in + padding;
+		slen = be32_to_cpu(g->compressed_length);
+		spadding = 0;
+		dst = p->out;
+		dlen = p->oremain;
+		dpadding = 0;
+		if (dlen < required_len) { /* have ignore bytes */
+			dst = ctx->dbounce;
+			dlen = BOUNCE_BUFFER_SIZE;
+		}
+		pr_info_ratelimited("using software 842 decompression\n");
+		ret = sw842_decompress(src, slen, dst, &dlen);
+	}
+	if (ret)
+		return ret;
+
+	slen -= spadding;
+
+	dlen -= ignore;
+	if (ignore)
+		pr_debug("ignoring last %x bytes\n", ignore);
+
+	if (dst == ctx->dbounce)
+		memcpy(p->out, dst, dlen);
+
+	pr_debug("decompress slen %x padding %x dlen %x ignore %x\n",
+		 slen, padding, dlen, ignore);
+
+	return update_param(p, slen + padding, dlen);
+}
+
+static int nx842_crypto_decompress(struct crypto_tfm *tfm,
+				   const u8 *src, unsigned int slen,
+				   u8 *dst, unsigned int *dlen)
+{
+	struct nx842_crypto_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct nx842_crypto_header *hdr;
+	struct nx842_crypto_param p;
+	struct nx842_constraints c;
+	int n, ret, hdr_len;
+	u16 ignore = 0;
+	bool usehw = true;
+
+	p.in = (u8 *)src;
+	p.iremain = slen;
+	p.out = dst;
+	p.oremain = *dlen;
+	p.ototal = 0;
+
+	*dlen = 0;
+
+	if (read_constraints(&c))
+		usehw = false;
+
+	hdr = (struct nx842_crypto_header *)src;
+
+	/* If it doesn't start with our header magic number, assume it's a raw
+	 * 842 compressed buffer and pass it directly to the hardware driver
+	 */
+	if (be16_to_cpu(hdr->magic) != NX842_CRYPTO_MAGIC) {
+		struct nx842_crypto_header_group g = {
+			.padding =		0,
+			.compressed_length =	cpu_to_be32(p.iremain),
+			.uncompressed_length =	cpu_to_be32(p.oremain),
+		};
+
+		ret = decompress(ctx, &p, &g, &c, 0, usehw);
+		if (ret)
+			return ret;
+
+		*dlen = p.ototal;
+
+		return 0;
+	}
+
+	if (!hdr->groups) {
+		pr_err("header has no groups\n");
+		return -EINVAL;
+	}
+	if (hdr->groups > NX842_CRYPTO_GROUP_MAX) {
+		pr_err("header has too many groups %x, max %x\n",
+		       hdr->groups, NX842_CRYPTO_GROUP_MAX);
+		return -EINVAL;
+	}
+
+	hdr_len = NX842_CRYPTO_HEADER_SIZE(hdr->groups);
+	if (hdr_len > slen)
+		return -EOVERFLOW;
+
+	memcpy(&ctx->header, src, hdr_len);
+	hdr = &ctx->header;
+
+	for (n = 0; n < hdr->groups; n++) {
+		/* ignore applies to last group */
+		if (n + 1 == hdr->groups)
+			ignore = be16_to_cpu(hdr->ignore);
+
+		ret = decompress(ctx, &p, &hdr->group[n], &c, ignore, usehw);
+		if (ret)
+			return ret;
+	}
+
+	*dlen = p.ototal;
+
+	pr_debug("decompress total slen %x dlen %x\n", slen, *dlen);
+
+	return 0;
+}
+
+static struct crypto_alg alg = {
+	.cra_name		= "842",
+	.cra_driver_name	= "842-nx",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_COMPRESS,
+	.cra_ctxsize		= sizeof(struct nx842_crypto_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_init		= nx842_crypto_init,
+	.cra_exit		= nx842_crypto_exit,
+	.cra_u			= { .compress = {
+	.coa_compress		= nx842_crypto_compress,
+	.coa_decompress		= nx842_crypto_decompress } }
+};
+
+static int __init nx842_crypto_mod_init(void)
+{
+	return crypto_register_alg(&alg);
+}
+module_init(nx842_crypto_mod_init);
+
+static void __exit nx842_crypto_mod_exit(void)
+{
+	crypto_unregister_alg(&alg);
+}
+module_exit(nx842_crypto_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IBM PowerPC Nest (NX) 842 Hardware Compression Interface");
+MODULE_ALIAS_CRYPTO("842");
+MODULE_ALIAS_CRYPTO("842-nx");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
diff --git a/drivers/crypto/nx/nx-842-platform.c b/drivers/crypto/nx/nx-842-platform.c
new file mode 100644
index 000000000000..664f13dd06ed
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-platform.c
@@ -0,0 +1,84 @@
+
+#include "nx-842.h"
+
+/* this is needed, separate from the main nx-842.c driver, because that main
+ * driver loads the platform drivers during its init(), and it expects one
+ * (or none) of the platform drivers to set this pointer to its driver.
+ * That means this pointer can't be in the main nx-842 driver, because it
+ * wouldn't be accessible until after the main driver loaded, which wouldn't
+ * be possible as it's waiting for the platform driver to load.  So place it
+ * here.
+ */
+static struct nx842_driver *driver;
+static DEFINE_SPINLOCK(driver_lock);
+
+struct nx842_driver *nx842_platform_driver(void)
+{
+	return driver;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver);
+
+bool nx842_platform_driver_set(struct nx842_driver *_driver)
+{
+	bool ret = false;
+
+	spin_lock(&driver_lock);
+
+	if (!driver) {
+		driver = _driver;
+		ret = true;
+	} else
+		WARN(1, "can't set platform driver, already set to %s\n",
+		     driver->name);
+
+	spin_unlock(&driver_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_set);
+
+/* only call this from the platform driver exit function */
+void nx842_platform_driver_unset(struct nx842_driver *_driver)
+{
+	spin_lock(&driver_lock);
+
+	if (driver == _driver)
+		driver = NULL;
+	else if (driver)
+		WARN(1, "can't unset platform driver %s, currently set to %s\n",
+		     _driver->name, driver->name);
+	else
+		WARN(1, "can't unset platform driver, already unset\n");
+
+	spin_unlock(&driver_lock);
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_unset);
+
+bool nx842_platform_driver_get(void)
+{
+	bool ret = false;
+
+	spin_lock(&driver_lock);
+
+	if (driver)
+		ret = try_module_get(driver->owner);
+
+	spin_unlock(&driver_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_get);
+
+void nx842_platform_driver_put(void)
+{
+	spin_lock(&driver_lock);
+
+	if (driver)
+		module_put(driver->owner);
+
+	spin_unlock(&driver_lock);
+}
+EXPORT_SYMBOL_GPL(nx842_platform_driver_put);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("842 H/W Compression platform driver");
diff --git a/drivers/crypto/nx/nx-842-powernv.c b/drivers/crypto/nx/nx-842-powernv.c
new file mode 100644
index 000000000000..33b3b0abf4ae
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-powernv.c
@@ -0,0 +1,637 @@
+/*
+ * Driver for IBM PowerNV 842 compression accelerator
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include "nx-842.h"
+
+#include <linux/timer.h>
+
+#include <asm/prom.h>
+#include <asm/icswx.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("842 H/W Compression driver for IBM PowerNV processors");
+
+#define WORKMEM_ALIGN	(CRB_ALIGN)
+#define CSB_WAIT_MAX	(5000) /* ms */
+
+struct nx842_workmem {
+	/* Below fields must be properly aligned */
+	struct coprocessor_request_block crb; /* CRB_ALIGN align */
+	struct data_descriptor_entry ddl_in[DDL_LEN_MAX]; /* DDE_ALIGN align */
+	struct data_descriptor_entry ddl_out[DDL_LEN_MAX]; /* DDE_ALIGN align */
+	/* Above fields must be properly aligned */
+
+	ktime_t start;
+
+	char padding[WORKMEM_ALIGN]; /* unused, to allow alignment */
+} __packed __aligned(WORKMEM_ALIGN);
+
+struct nx842_coproc {
+	unsigned int chip_id;
+	unsigned int ct;
+	unsigned int ci;
+	struct list_head list;
+};
+
+/* no cpu hotplug on powernv, so this list never changes after init */
+static LIST_HEAD(nx842_coprocs);
+static unsigned int nx842_ct;
+
+/**
+ * setup_indirect_dde - Setup an indirect DDE
+ *
+ * The DDE is setup with the the DDE count, byte count, and address of
+ * first direct DDE in the list.
+ */
+static void setup_indirect_dde(struct data_descriptor_entry *dde,
+			       struct data_descriptor_entry *ddl,
+			       unsigned int dde_count, unsigned int byte_count)
+{
+	dde->flags = 0;
+	dde->count = dde_count;
+	dde->index = 0;
+	dde->length = cpu_to_be32(byte_count);
+	dde->address = cpu_to_be64(nx842_get_pa(ddl));
+}
+
+/**
+ * setup_direct_dde - Setup single DDE from buffer
+ *
+ * The DDE is setup with the buffer and length.  The buffer must be properly
+ * aligned.  The used length is returned.
+ * Returns:
+ *   N    Successfully set up DDE with N bytes
+ */
+static unsigned int setup_direct_dde(struct data_descriptor_entry *dde,
+				     unsigned long pa, unsigned int len)
+{
+	unsigned int l = min_t(unsigned int, len, LEN_ON_PAGE(pa));
+
+	dde->flags = 0;
+	dde->count = 0;
+	dde->index = 0;
+	dde->length = cpu_to_be32(l);
+	dde->address = cpu_to_be64(pa);
+
+	return l;
+}
+
+/**
+ * setup_ddl - Setup DDL from buffer
+ *
+ * Returns:
+ *   0		Successfully set up DDL
+ */
+static int setup_ddl(struct data_descriptor_entry *dde,
+		     struct data_descriptor_entry *ddl,
+		     unsigned char *buf, unsigned int len,
+		     bool in)
+{
+	unsigned long pa = nx842_get_pa(buf);
+	int i, ret, total_len = len;
+
+	if (!IS_ALIGNED(pa, DDE_BUFFER_ALIGN)) {
+		pr_debug("%s buffer pa 0x%lx not 0x%x-byte aligned\n",
+			 in ? "input" : "output", pa, DDE_BUFFER_ALIGN);
+		return -EINVAL;
+	}
+
+	/* only need to check last mult; since buffer must be
+	 * DDE_BUFFER_ALIGN aligned, and that is a multiple of
+	 * DDE_BUFFER_SIZE_MULT, and pre-last page DDE buffers
+	 * are guaranteed a multiple of DDE_BUFFER_SIZE_MULT.
+	 */
+	if (len % DDE_BUFFER_LAST_MULT) {
+		pr_debug("%s buffer len 0x%x not a multiple of 0x%x\n",
+			 in ? "input" : "output", len, DDE_BUFFER_LAST_MULT);
+		if (in)
+			return -EINVAL;
+		len = round_down(len, DDE_BUFFER_LAST_MULT);
+	}
+
+	/* use a single direct DDE */
+	if (len <= LEN_ON_PAGE(pa)) {
+		ret = setup_direct_dde(dde, pa, len);
+		WARN_ON(ret < len);
+		return 0;
+	}
+
+	/* use the DDL */
+	for (i = 0; i < DDL_LEN_MAX && len > 0; i++) {
+		ret = setup_direct_dde(&ddl[i], pa, len);
+		buf += ret;
+		len -= ret;
+		pa = nx842_get_pa(buf);
+	}
+
+	if (len > 0) {
+		pr_debug("0x%x total %s bytes 0x%x too many for DDL.\n",
+			 total_len, in ? "input" : "output", len);
+		if (in)
+			return -EMSGSIZE;
+		total_len -= len;
+	}
+	setup_indirect_dde(dde, ddl, i, total_len);
+
+	return 0;
+}
+
+#define CSB_ERR(csb, msg, ...)					\
+	pr_err("ERROR: " msg " : %02x %02x %02x %02x %08x\n",	\
+	       ##__VA_ARGS__, (csb)->flags,			\
+	       (csb)->cs, (csb)->cc, (csb)->ce,			\
+	       be32_to_cpu((csb)->count))
+
+#define CSB_ERR_ADDR(csb, msg, ...)				\
+	CSB_ERR(csb, msg " at %lx", ##__VA_ARGS__,		\
+		(unsigned long)be64_to_cpu((csb)->address))
+
+/**
+ * wait_for_csb
+ */
+static int wait_for_csb(struct nx842_workmem *wmem,
+			struct coprocessor_status_block *csb)
+{
+	ktime_t start = wmem->start, now = ktime_get();
+	ktime_t timeout = ktime_add_ms(start, CSB_WAIT_MAX);
+
+	while (!(ACCESS_ONCE(csb->flags) & CSB_V)) {
+		cpu_relax();
+		now = ktime_get();
+		if (ktime_after(now, timeout))
+			break;
+	}
+
+	/* hw has updated csb and output buffer */
+	barrier();
+
+	/* check CSB flags */
+	if (!(csb->flags & CSB_V)) {
+		CSB_ERR(csb, "CSB still not valid after %ld us, giving up",
+			(long)ktime_us_delta(now, start));
+		return -ETIMEDOUT;
+	}
+	if (csb->flags & CSB_F) {
+		CSB_ERR(csb, "Invalid CSB format");
+		return -EPROTO;
+	}
+	if (csb->flags & CSB_CH) {
+		CSB_ERR(csb, "Invalid CSB chaining state");
+		return -EPROTO;
+	}
+
+	/* verify CSB completion sequence is 0 */
+	if (csb->cs) {
+		CSB_ERR(csb, "Invalid CSB completion sequence");
+		return -EPROTO;
+	}
+
+	/* check CSB Completion Code */
+	switch (csb->cc) {
+	/* no error */
+	case CSB_CC_SUCCESS:
+		break;
+	case CSB_CC_TPBC_GT_SPBC:
+		/* not an error, but the compressed data is
+		 * larger than the uncompressed data :(
+		 */
+		break;
+
+	/* input data errors */
+	case CSB_CC_OPERAND_OVERLAP:
+		/* input and output buffers overlap */
+		CSB_ERR(csb, "Operand Overlap error");
+		return -EINVAL;
+	case CSB_CC_INVALID_OPERAND:
+		CSB_ERR(csb, "Invalid operand");
+		return -EINVAL;
+	case CSB_CC_NOSPC:
+		/* output buffer too small */
+		return -ENOSPC;
+	case CSB_CC_ABORT:
+		CSB_ERR(csb, "Function aborted");
+		return -EINTR;
+	case CSB_CC_CRC_MISMATCH:
+		CSB_ERR(csb, "CRC mismatch");
+		return -EINVAL;
+	case CSB_CC_TEMPL_INVALID:
+		CSB_ERR(csb, "Compressed data template invalid");
+		return -EINVAL;
+	case CSB_CC_TEMPL_OVERFLOW:
+		CSB_ERR(csb, "Compressed data template shows data past end");
+		return -EINVAL;
+
+	/* these should not happen */
+	case CSB_CC_INVALID_ALIGN:
+		/* setup_ddl should have detected this */
+		CSB_ERR_ADDR(csb, "Invalid alignment");
+		return -EINVAL;
+	case CSB_CC_DATA_LENGTH:
+		/* setup_ddl should have detected this */
+		CSB_ERR(csb, "Invalid data length");
+		return -EINVAL;
+	case CSB_CC_WR_TRANSLATION:
+	case CSB_CC_TRANSLATION:
+	case CSB_CC_TRANSLATION_DUP1:
+	case CSB_CC_TRANSLATION_DUP2:
+	case CSB_CC_TRANSLATION_DUP3:
+	case CSB_CC_TRANSLATION_DUP4:
+	case CSB_CC_TRANSLATION_DUP5:
+	case CSB_CC_TRANSLATION_DUP6:
+		/* should not happen, we use physical addrs */
+		CSB_ERR_ADDR(csb, "Translation error");
+		return -EPROTO;
+	case CSB_CC_WR_PROTECTION:
+	case CSB_CC_PROTECTION:
+	case CSB_CC_PROTECTION_DUP1:
+	case CSB_CC_PROTECTION_DUP2:
+	case CSB_CC_PROTECTION_DUP3:
+	case CSB_CC_PROTECTION_DUP4:
+	case CSB_CC_PROTECTION_DUP5:
+	case CSB_CC_PROTECTION_DUP6:
+		/* should not happen, we use physical addrs */
+		CSB_ERR_ADDR(csb, "Protection error");
+		return -EPROTO;
+	case CSB_CC_PRIVILEGE:
+		/* shouldn't happen, we're in HYP mode */
+		CSB_ERR(csb, "Insufficient Privilege error");
+		return -EPROTO;
+	case CSB_CC_EXCESSIVE_DDE:
+		/* shouldn't happen, setup_ddl doesn't use many dde's */
+		CSB_ERR(csb, "Too many DDEs in DDL");
+		return -EINVAL;
+	case CSB_CC_TRANSPORT:
+		/* shouldn't happen, we setup CRB correctly */
+		CSB_ERR(csb, "Invalid CRB");
+		return -EINVAL;
+	case CSB_CC_SEGMENTED_DDL:
+		/* shouldn't happen, setup_ddl creates DDL right */
+		CSB_ERR(csb, "Segmented DDL error");
+		return -EINVAL;
+	case CSB_CC_DDE_OVERFLOW:
+		/* shouldn't happen, setup_ddl creates DDL right */
+		CSB_ERR(csb, "DDE overflow error");
+		return -EINVAL;
+	case CSB_CC_SESSION:
+		/* should not happen with ICSWX */
+		CSB_ERR(csb, "Session violation error");
+		return -EPROTO;
+	case CSB_CC_CHAIN:
+		/* should not happen, we don't use chained CRBs */
+		CSB_ERR(csb, "Chained CRB error");
+		return -EPROTO;
+	case CSB_CC_SEQUENCE:
+		/* should not happen, we don't use chained CRBs */
+		CSB_ERR(csb, "CRB seqeunce number error");
+		return -EPROTO;
+	case CSB_CC_UNKNOWN_CODE:
+		CSB_ERR(csb, "Unknown subfunction code");
+		return -EPROTO;
+
+	/* hardware errors */
+	case CSB_CC_RD_EXTERNAL:
+	case CSB_CC_RD_EXTERNAL_DUP1:
+	case CSB_CC_RD_EXTERNAL_DUP2:
+	case CSB_CC_RD_EXTERNAL_DUP3:
+		CSB_ERR_ADDR(csb, "Read error outside coprocessor");
+		return -EPROTO;
+	case CSB_CC_WR_EXTERNAL:
+		CSB_ERR_ADDR(csb, "Write error outside coprocessor");
+		return -EPROTO;
+	case CSB_CC_INTERNAL:
+		CSB_ERR(csb, "Internal error in coprocessor");
+		return -EPROTO;
+	case CSB_CC_PROVISION:
+		CSB_ERR(csb, "Storage provision error");
+		return -EPROTO;
+	case CSB_CC_HW:
+		CSB_ERR(csb, "Correctable hardware error");
+		return -EPROTO;
+
+	default:
+		CSB_ERR(csb, "Invalid CC %d", csb->cc);
+		return -EPROTO;
+	}
+
+	/* check Completion Extension state */
+	if (csb->ce & CSB_CE_TERMINATION) {
+		CSB_ERR(csb, "CSB request was terminated");
+		return -EPROTO;
+	}
+	if (csb->ce & CSB_CE_INCOMPLETE) {
+		CSB_ERR(csb, "CSB request not complete");
+		return -EPROTO;
+	}
+	if (!(csb->ce & CSB_CE_TPBC)) {
+		CSB_ERR(csb, "TPBC not provided, unknown target length");
+		return -EPROTO;
+	}
+
+	/* successful completion */
+	pr_debug_ratelimited("Processed %u bytes in %lu us\n", csb->count,
+			     (unsigned long)ktime_us_delta(now, start));
+
+	return 0;
+}
+
+/**
+ * nx842_powernv_function - compress/decompress data using the 842 algorithm
+ *
+ * (De)compression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * This compresses or decompresses the provided input buffer into the provided
+ * output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * output data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * The @workmem buffer should only be used by one function call at a time.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ * @fc: function code, see CCW Function Codes in nx-842.h
+ *
+ * Returns:
+ *   0		Success, output of length @outlenp stored in the buffer at @out
+ *   -ENODEV	Hardware unavailable
+ *   -ENOSPC	Output buffer is to small
+ *   -EMSGSIZE	Input buffer too large
+ *   -EINVAL	buffer constraints do not fix nx842_constraints
+ *   -EPROTO	hardware error during operation
+ *   -ETIMEDOUT	hardware did not complete operation in reasonable time
+ *   -EINTR	operation was aborted
+ */
+static int nx842_powernv_function(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlenp,
+				  void *workmem, int fc)
+{
+	struct coprocessor_request_block *crb;
+	struct coprocessor_status_block *csb;
+	struct nx842_workmem *wmem;
+	int ret;
+	u64 csb_addr;
+	u32 ccw;
+	unsigned int outlen = *outlenp;
+
+	wmem = PTR_ALIGN(workmem, WORKMEM_ALIGN);
+
+	*outlenp = 0;
+
+	/* shoudn't happen, we don't load without a coproc */
+	if (!nx842_ct) {
+		pr_err_ratelimited("coprocessor CT is 0");
+		return -ENODEV;
+	}
+
+	crb = &wmem->crb;
+	csb = &crb->csb;
+
+	/* Clear any previous values */
+	memset(crb, 0, sizeof(*crb));
+
+	/* set up DDLs */
+	ret = setup_ddl(&crb->source, wmem->ddl_in,
+			(unsigned char *)in, inlen, true);
+	if (ret)
+		return ret;
+	ret = setup_ddl(&crb->target, wmem->ddl_out,
+			out, outlen, false);
+	if (ret)
+		return ret;
+
+	/* set up CCW */
+	ccw = 0;
+	ccw = SET_FIELD(ccw, CCW_CT, nx842_ct);
+	ccw = SET_FIELD(ccw, CCW_CI_842, 0); /* use 0 for hw auto-selection */
+	ccw = SET_FIELD(ccw, CCW_FC_842, fc);
+
+	/* set up CRB's CSB addr */
+	csb_addr = nx842_get_pa(csb) & CRB_CSB_ADDRESS;
+	csb_addr |= CRB_CSB_AT; /* Addrs are phys */
+	crb->csb_addr = cpu_to_be64(csb_addr);
+
+	wmem->start = ktime_get();
+
+	/* do ICSWX */
+	ret = icswx(cpu_to_be32(ccw), crb);
+
+	pr_debug_ratelimited("icswx CR %x ccw %x crb->ccw %x\n", ret,
+			     (unsigned int)ccw,
+			     (unsigned int)be32_to_cpu(crb->ccw));
+
+	switch (ret) {
+	case ICSWX_INITIATED:
+		ret = wait_for_csb(wmem, csb);
+		break;
+	case ICSWX_BUSY:
+		pr_debug_ratelimited("842 Coprocessor busy\n");
+		ret = -EBUSY;
+		break;
+	case ICSWX_REJECTED:
+		pr_err_ratelimited("ICSWX rejected\n");
+		ret = -EPROTO;
+		break;
+	default:
+		pr_err_ratelimited("Invalid ICSWX return code %x\n", ret);
+		ret = -EPROTO;
+		break;
+	}
+
+	if (!ret)
+		*outlenp = be32_to_cpu(csb->count);
+
+	return ret;
+}
+
+/**
+ * nx842_powernv_compress - Compress data using the 842 algorithm
+ *
+ * Compression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * The input buffer is compressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * compressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ *
+ * Returns: see @nx842_powernv_function()
+ */
+static int nx842_powernv_compress(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlenp,
+				  void *wmem)
+{
+	return nx842_powernv_function(in, inlen, out, outlenp,
+				      wmem, CCW_FC_842_COMP_NOCRC);
+}
+
+/**
+ * nx842_powernv_decompress - Decompress data using the 842 algorithm
+ *
+ * Decompression provided by the NX842 coprocessor on IBM PowerNV systems.
+ * The input buffer is decompressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * decompressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: input buffer pointer
+ * @inlen: input buffer size
+ * @out: output buffer pointer
+ * @outlenp: output buffer size pointer
+ * @workmem: working memory buffer pointer, size determined by
+ *           nx842_powernv_driver.workmem_size
+ *
+ * Returns: see @nx842_powernv_function()
+ */
+static int nx842_powernv_decompress(const unsigned char *in, unsigned int inlen,
+				    unsigned char *out, unsigned int *outlenp,
+				    void *wmem)
+{
+	return nx842_powernv_function(in, inlen, out, outlenp,
+				      wmem, CCW_FC_842_DECOMP_NOCRC);
+}
+
+static int __init nx842_powernv_probe(struct device_node *dn)
+{
+	struct nx842_coproc *coproc;
+	struct property *ct_prop, *ci_prop;
+	unsigned int ct, ci;
+	int chip_id;
+
+	chip_id = of_get_ibm_chip_id(dn);
+	if (chip_id < 0) {
+		pr_err("ibm,chip-id missing\n");
+		return -EINVAL;
+	}
+	ct_prop = of_find_property(dn, "ibm,842-coprocessor-type", NULL);
+	if (!ct_prop) {
+		pr_err("ibm,842-coprocessor-type missing\n");
+		return -EINVAL;
+	}
+	ct = be32_to_cpu(*(unsigned int *)ct_prop->value);
+	ci_prop = of_find_property(dn, "ibm,842-coprocessor-instance", NULL);
+	if (!ci_prop) {
+		pr_err("ibm,842-coprocessor-instance missing\n");
+		return -EINVAL;
+	}
+	ci = be32_to_cpu(*(unsigned int *)ci_prop->value);
+
+	coproc = kmalloc(sizeof(*coproc), GFP_KERNEL);
+	if (!coproc)
+		return -ENOMEM;
+
+	coproc->chip_id = chip_id;
+	coproc->ct = ct;
+	coproc->ci = ci;
+	INIT_LIST_HEAD(&coproc->list);
+	list_add(&coproc->list, &nx842_coprocs);
+
+	pr_info("coprocessor found on chip %d, CT %d CI %d\n", chip_id, ct, ci);
+
+	if (!nx842_ct)
+		nx842_ct = ct;
+	else if (nx842_ct != ct)
+		pr_err("NX842 chip %d, CT %d != first found CT %d\n",
+		       chip_id, ct, nx842_ct);
+
+	return 0;
+}
+
+static struct nx842_constraints nx842_powernv_constraints = {
+	.alignment =	DDE_BUFFER_ALIGN,
+	.multiple =	DDE_BUFFER_LAST_MULT,
+	.minimum =	DDE_BUFFER_LAST_MULT,
+	.maximum =	(DDL_LEN_MAX - 1) * PAGE_SIZE,
+};
+
+static struct nx842_driver nx842_powernv_driver = {
+	.name =		KBUILD_MODNAME,
+	.owner =	THIS_MODULE,
+	.workmem_size =	sizeof(struct nx842_workmem),
+	.constraints =	&nx842_powernv_constraints,
+	.compress =	nx842_powernv_compress,
+	.decompress =	nx842_powernv_decompress,
+};
+
+static __init int nx842_powernv_init(void)
+{
+	struct device_node *dn;
+
+	/* verify workmem size/align restrictions */
+	BUILD_BUG_ON(WORKMEM_ALIGN % CRB_ALIGN);
+	BUILD_BUG_ON(CRB_ALIGN % DDE_ALIGN);
+	BUILD_BUG_ON(CRB_SIZE % DDE_ALIGN);
+	/* verify buffer size/align restrictions */
+	BUILD_BUG_ON(PAGE_SIZE % DDE_BUFFER_ALIGN);
+	BUILD_BUG_ON(DDE_BUFFER_ALIGN % DDE_BUFFER_SIZE_MULT);
+	BUILD_BUG_ON(DDE_BUFFER_SIZE_MULT % DDE_BUFFER_LAST_MULT);
+
+	pr_info("loading\n");
+
+	for_each_compatible_node(dn, NULL, "ibm,power-nx")
+		nx842_powernv_probe(dn);
+
+	if (!nx842_ct) {
+		pr_err("no coprocessors found\n");
+		return -ENODEV;
+	}
+
+	if (!nx842_platform_driver_set(&nx842_powernv_driver)) {
+		struct nx842_coproc *coproc, *n;
+
+		list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
+			list_del(&coproc->list);
+			kfree(coproc);
+		}
+
+		return -EEXIST;
+	}
+
+	pr_info("loaded\n");
+
+	return 0;
+}
+module_init(nx842_powernv_init);
+
+static void __exit nx842_powernv_exit(void)
+{
+	struct nx842_coproc *coproc, *n;
+
+	nx842_platform_driver_unset(&nx842_powernv_driver);
+
+	list_for_each_entry_safe(coproc, n, &nx842_coprocs, list) {
+		list_del(&coproc->list);
+		kfree(coproc);
+	}
+
+	pr_info("unloaded\n");
+}
+module_exit(nx842_powernv_exit);
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
new file mode 100644
index 000000000000..3040a6091bf2
--- /dev/null
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -0,0 +1,1140 @@
+/*
+ * Driver for IBM Power 842 compression accelerator
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
+ *          Seth Jennings <sjenning@linux.vnet.ibm.com>
+ */
+
+#include <asm/vio.h>
+
+#include "nx-842.h"
+#include "nx_csbcpb.h" /* struct nx_csbcpb */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Robert Jennings <rcj@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
+
+static struct nx842_constraints nx842_pseries_constraints = {
+	.alignment =	DDE_BUFFER_ALIGN,
+	.multiple =	DDE_BUFFER_LAST_MULT,
+	.minimum =	DDE_BUFFER_LAST_MULT,
+	.maximum =	PAGE_SIZE, /* dynamic, max_sync_size */
+};
+
+static int check_constraints(unsigned long buf, unsigned int *len, bool in)
+{
+	if (!IS_ALIGNED(buf, nx842_pseries_constraints.alignment)) {
+		pr_debug("%s buffer 0x%lx not aligned to 0x%x\n",
+			 in ? "input" : "output", buf,
+			 nx842_pseries_constraints.alignment);
+		return -EINVAL;
+	}
+	if (*len % nx842_pseries_constraints.multiple) {
+		pr_debug("%s buffer len 0x%x not multiple of 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.multiple);
+		if (in)
+			return -EINVAL;
+		*len = round_down(*len, nx842_pseries_constraints.multiple);
+	}
+	if (*len < nx842_pseries_constraints.minimum) {
+		pr_debug("%s buffer len 0x%x under minimum 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.minimum);
+		return -EINVAL;
+	}
+	if (*len > nx842_pseries_constraints.maximum) {
+		pr_debug("%s buffer len 0x%x over maximum 0x%x\n",
+			 in ? "input" : "output", *len,
+			 nx842_pseries_constraints.maximum);
+		if (in)
+			return -EINVAL;
+		*len = nx842_pseries_constraints.maximum;
+	}
+	return 0;
+}
+
+/* I assume we need to align the CSB? */
+#define WORKMEM_ALIGN	(256)
+
+struct nx842_workmem {
+	/* scatterlist */
+	char slin[4096];
+	char slout[4096];
+	/* coprocessor status/parameter block */
+	struct nx_csbcpb csbcpb;
+
+	char padding[WORKMEM_ALIGN];
+} __aligned(WORKMEM_ALIGN);
+
+/* Macros for fields within nx_csbcpb */
+/* Check the valid bit within the csbcpb valid field */
+#define NX842_CSBCBP_VALID_CHK(x) (x & BIT_MASK(7))
+
+/* CE macros operate on the completion_extension field bits in the csbcpb.
+ * CE0 0=full completion, 1=partial completion
+ * CE1 0=CE0 indicates completion, 1=termination (output may be modified)
+ * CE2 0=processed_bytes is source bytes, 1=processed_bytes is target bytes */
+#define NX842_CSBCPB_CE0(x)	(x & BIT_MASK(7))
+#define NX842_CSBCPB_CE1(x)	(x & BIT_MASK(6))
+#define NX842_CSBCPB_CE2(x)	(x & BIT_MASK(5))
+
+/* The NX unit accepts data only on 4K page boundaries */
+#define NX842_HW_PAGE_SIZE	(4096)
+#define NX842_HW_PAGE_MASK	(~(NX842_HW_PAGE_SIZE-1))
+
+enum nx842_status {
+	UNAVAILABLE,
+	AVAILABLE
+};
+
+struct ibm_nx842_counters {
+	atomic64_t comp_complete;
+	atomic64_t comp_failed;
+	atomic64_t decomp_complete;
+	atomic64_t decomp_failed;
+	atomic64_t swdecomp;
+	atomic64_t comp_times[32];
+	atomic64_t decomp_times[32];
+};
+
+static struct nx842_devdata {
+	struct vio_dev *vdev;
+	struct device *dev;
+	struct ibm_nx842_counters *counters;
+	unsigned int max_sg_len;
+	unsigned int max_sync_size;
+	unsigned int max_sync_sg;
+	enum nx842_status status;
+} __rcu *devdata;
+static DEFINE_SPINLOCK(devdata_mutex);
+
+#define NX842_COUNTER_INC(_x) \
+static inline void nx842_inc_##_x( \
+	const struct nx842_devdata *dev) { \
+	if (dev) \
+		atomic64_inc(&dev->counters->_x); \
+}
+NX842_COUNTER_INC(comp_complete);
+NX842_COUNTER_INC(comp_failed);
+NX842_COUNTER_INC(decomp_complete);
+NX842_COUNTER_INC(decomp_failed);
+NX842_COUNTER_INC(swdecomp);
+
+#define NX842_HIST_SLOTS 16
+
+static void ibm_nx842_incr_hist(atomic64_t *times, unsigned int time)
+{
+	int bucket = fls(time);
+
+	if (bucket)
+		bucket = min((NX842_HIST_SLOTS - 1), bucket - 1);
+
+	atomic64_inc(&times[bucket]);
+}
+
+/* NX unit operation flags */
+#define NX842_OP_COMPRESS	0x0
+#define NX842_OP_CRC		0x1
+#define NX842_OP_DECOMPRESS	0x2
+#define NX842_OP_COMPRESS_CRC   (NX842_OP_COMPRESS | NX842_OP_CRC)
+#define NX842_OP_DECOMPRESS_CRC (NX842_OP_DECOMPRESS | NX842_OP_CRC)
+#define NX842_OP_ASYNC		(1<<23)
+#define NX842_OP_NOTIFY		(1<<22)
+#define NX842_OP_NOTIFY_INT(x)	((x & 0xff)<<8)
+
+static unsigned long nx842_get_desired_dma(struct vio_dev *viodev)
+{
+	/* No use of DMA mappings within the driver. */
+	return 0;
+}
+
+struct nx842_slentry {
+	__be64 ptr; /* Real address (use __pa()) */
+	__be64 len;
+};
+
+/* pHyp scatterlist entry */
+struct nx842_scatterlist {
+	int entry_nr; /* number of slentries */
+	struct nx842_slentry *entries; /* ptr to array of slentries */
+};
+
+/* Does not include sizeof(entry_nr) in the size */
+static inline unsigned long nx842_get_scatterlist_size(
+				struct nx842_scatterlist *sl)
+{
+	return sl->entry_nr * sizeof(struct nx842_slentry);
+}
+
+static int nx842_build_scatterlist(unsigned long buf, int len,
+			struct nx842_scatterlist *sl)
+{
+	unsigned long entrylen;
+	struct nx842_slentry *entry;
+
+	sl->entry_nr = 0;
+
+	entry = sl->entries;
+	while (len) {
+		entry->ptr = cpu_to_be64(nx842_get_pa((void *)buf));
+		entrylen = min_t(int, len,
+				 LEN_ON_SIZE(buf, NX842_HW_PAGE_SIZE));
+		entry->len = cpu_to_be64(entrylen);
+
+		len -= entrylen;
+		buf += entrylen;
+
+		sl->entry_nr++;
+		entry++;
+	}
+
+	return 0;
+}
+
+static int nx842_validate_result(struct device *dev,
+	struct cop_status_block *csb)
+{
+	/* The csb must be valid after returning from vio_h_cop_sync */
+	if (!NX842_CSBCBP_VALID_CHK(csb->valid)) {
+		dev_err(dev, "%s: cspcbp not valid upon completion.\n",
+				__func__);
+		dev_dbg(dev, "valid:0x%02x cs:0x%02x cc:0x%02x ce:0x%02x\n",
+				csb->valid,
+				csb->crb_seq_number,
+				csb->completion_code,
+				csb->completion_extension);
+		dev_dbg(dev, "processed_bytes:%d address:0x%016lx\n",
+				be32_to_cpu(csb->processed_byte_count),
+				(unsigned long)be64_to_cpu(csb->address));
+		return -EIO;
+	}
+
+	/* Check return values from the hardware in the CSB */
+	switch (csb->completion_code) {
+	case 0:	/* Completed without error */
+		break;
+	case 64: /* Target bytes > Source bytes during compression */
+	case 13: /* Output buffer too small */
+		dev_dbg(dev, "%s: Compression output larger than input\n",
+					__func__);
+		return -ENOSPC;
+	case 66: /* Input data contains an illegal template field */
+	case 67: /* Template indicates data past the end of the input stream */
+		dev_dbg(dev, "%s: Bad data for decompression (code:%d)\n",
+					__func__, csb->completion_code);
+		return -EINVAL;
+	default:
+		dev_dbg(dev, "%s: Unspecified error (code:%d)\n",
+					__func__, csb->completion_code);
+		return -EIO;
+	}
+
+	/* Hardware sanity check */
+	if (!NX842_CSBCPB_CE2(csb->completion_extension)) {
+		dev_err(dev, "%s: No error returned by hardware, but "
+				"data returned is unusable, contact support.\n"
+				"(Additional info: csbcbp->processed bytes "
+				"does not specify processed bytes for the "
+				"target buffer.)\n", __func__);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * nx842_pseries_compress - Compress data using the 842 algorithm
+ *
+ * Compression provide by the NX842 coprocessor on IBM Power systems.
+ * The input buffer is compressed and the result is stored in the
+ * provided output buffer.
+ *
+ * Upon return from this function @outlen contains the length of the
+ * compressed data.  If there is an error then @outlen will be 0 and an
+ * error will be specified by the return code from this function.
+ *
+ * @in: Pointer to input buffer
+ * @inlen: Length of input buffer
+ * @out: Pointer to output buffer
+ * @outlen: Length of output buffer
+ * @wrkmem: ptr to buffer for working memory, size determined by
+ *          nx842_pseries_driver.workmem_size
+ *
+ * Returns:
+ *   0		Success, output of length @outlen stored in the buffer at @out
+ *   -ENOMEM	Unable to allocate internal buffers
+ *   -ENOSPC	Output buffer is to small
+ *   -EIO	Internal error
+ *   -ENODEV	Hardware unavailable
+ */
+static int nx842_pseries_compress(const unsigned char *in, unsigned int inlen,
+				  unsigned char *out, unsigned int *outlen,
+				  void *wmem)
+{
+	struct nx842_devdata *local_devdata;
+	struct device *dev = NULL;
+	struct nx842_workmem *workmem;
+	struct nx842_scatterlist slin, slout;
+	struct nx_csbcpb *csbcpb;
+	int ret = 0, max_sync_size;
+	unsigned long inbuf, outbuf;
+	struct vio_pfo_op op = {
+		.done = NULL,
+		.handle = 0,
+		.timeout = 0,
+	};
+	unsigned long start = get_tb();
+
+	inbuf = (unsigned long)in;
+	if (check_constraints(inbuf, &inlen, true))
+		return -EINVAL;
+
+	outbuf = (unsigned long)out;
+	if (check_constraints(outbuf, outlen, false))
+		return -EINVAL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata || !local_devdata->dev) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
+	max_sync_size = local_devdata->max_sync_size;
+	dev = local_devdata->dev;
+
+	/* Init scatterlist */
+	workmem = PTR_ALIGN(wmem, WORKMEM_ALIGN);
+	slin.entries = (struct nx842_slentry *)workmem->slin;
+	slout.entries = (struct nx842_slentry *)workmem->slout;
+
+	/* Init operation */
+	op.flags = NX842_OP_COMPRESS;
+	csbcpb = &workmem->csbcpb;
+	memset(csbcpb, 0, sizeof(*csbcpb));
+	op.csbcpb = nx842_get_pa(csbcpb);
+
+	if ((inbuf & NX842_HW_PAGE_MASK) ==
+	    ((inbuf + inlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.in = nx842_get_pa((void *)inbuf);
+		op.inlen = inlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(inbuf, inlen, &slin);
+		op.in = nx842_get_pa(slin.entries);
+		op.inlen = -nx842_get_scatterlist_size(&slin);
+	}
+
+	if ((outbuf & NX842_HW_PAGE_MASK) ==
+	    ((outbuf + *outlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.out = nx842_get_pa((void *)outbuf);
+		op.outlen = *outlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(outbuf, *outlen, &slout);
+		op.out = nx842_get_pa(slout.entries);
+		op.outlen = -nx842_get_scatterlist_size(&slout);
+	}
+
+	dev_dbg(dev, "%s: op.in %lx op.inlen %ld op.out %lx op.outlen %ld\n",
+		__func__, (unsigned long)op.in, (long)op.inlen,
+		(unsigned long)op.out, (long)op.outlen);
+
+	/* Send request to pHyp */
+	ret = vio_h_cop_sync(local_devdata->vdev, &op);
+
+	/* Check for pHyp error */
+	if (ret) {
+		dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
+			__func__, ret, op.hcall_err);
+		ret = -EIO;
+		goto unlock;
+	}
+
+	/* Check for hardware error */
+	ret = nx842_validate_result(dev, &csbcpb->csb);
+	if (ret)
+		goto unlock;
+
+	*outlen = be32_to_cpu(csbcpb->csb.processed_byte_count);
+	dev_dbg(dev, "%s: processed_bytes=%d\n", __func__, *outlen);
+
+unlock:
+	if (ret)
+		nx842_inc_comp_failed(local_devdata);
+	else {
+		nx842_inc_comp_complete(local_devdata);
+		ibm_nx842_incr_hist(local_devdata->counters->comp_times,
+			(get_tb() - start) / tb_ticks_per_usec);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * nx842_pseries_decompress - Decompress data using the 842 algorithm
+ *
+ * Decompression provide by the NX842 coprocessor on IBM Power systems.
+ * The input buffer is decompressed and the result is stored in the
+ * provided output buffer.  The size allocated to the output buffer is
+ * provided by the caller of this function in @outlen.  Upon return from
+ * this function @outlen contains the length of the decompressed data.
+ * If there is an error then @outlen will be 0 and an error will be
+ * specified by the return code from this function.
+ *
+ * @in: Pointer to input buffer
+ * @inlen: Length of input buffer
+ * @out: Pointer to output buffer
+ * @outlen: Length of output buffer
+ * @wrkmem: ptr to buffer for working memory, size determined by
+ *          nx842_pseries_driver.workmem_size
+ *
+ * Returns:
+ *   0		Success, output of length @outlen stored in the buffer at @out
+ *   -ENODEV	Hardware decompression device is unavailable
+ *   -ENOMEM	Unable to allocate internal buffers
+ *   -ENOSPC	Output buffer is to small
+ *   -EINVAL	Bad input data encountered when attempting decompress
+ *   -EIO	Internal error
+ */
+static int nx842_pseries_decompress(const unsigned char *in, unsigned int inlen,
+				    unsigned char *out, unsigned int *outlen,
+				    void *wmem)
+{
+	struct nx842_devdata *local_devdata;
+	struct device *dev = NULL;
+	struct nx842_workmem *workmem;
+	struct nx842_scatterlist slin, slout;
+	struct nx_csbcpb *csbcpb;
+	int ret = 0, max_sync_size;
+	unsigned long inbuf, outbuf;
+	struct vio_pfo_op op = {
+		.done = NULL,
+		.handle = 0,
+		.timeout = 0,
+	};
+	unsigned long start = get_tb();
+
+	/* Ensure page alignment and size */
+	inbuf = (unsigned long)in;
+	if (check_constraints(inbuf, &inlen, true))
+		return -EINVAL;
+
+	outbuf = (unsigned long)out;
+	if (check_constraints(outbuf, outlen, false))
+		return -EINVAL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata || !local_devdata->dev) {
+		rcu_read_unlock();
+		return -ENODEV;
+	}
+	max_sync_size = local_devdata->max_sync_size;
+	dev = local_devdata->dev;
+
+	workmem = PTR_ALIGN(wmem, WORKMEM_ALIGN);
+
+	/* Init scatterlist */
+	slin.entries = (struct nx842_slentry *)workmem->slin;
+	slout.entries = (struct nx842_slentry *)workmem->slout;
+
+	/* Init operation */
+	op.flags = NX842_OP_DECOMPRESS;
+	csbcpb = &workmem->csbcpb;
+	memset(csbcpb, 0, sizeof(*csbcpb));
+	op.csbcpb = nx842_get_pa(csbcpb);
+
+	if ((inbuf & NX842_HW_PAGE_MASK) ==
+	    ((inbuf + inlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.in = nx842_get_pa((void *)inbuf);
+		op.inlen = inlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(inbuf, inlen, &slin);
+		op.in = nx842_get_pa(slin.entries);
+		op.inlen = -nx842_get_scatterlist_size(&slin);
+	}
+
+	if ((outbuf & NX842_HW_PAGE_MASK) ==
+	    ((outbuf + *outlen - 1) & NX842_HW_PAGE_MASK)) {
+		/* Create direct DDE */
+		op.out = nx842_get_pa((void *)outbuf);
+		op.outlen = *outlen;
+	} else {
+		/* Create indirect DDE (scatterlist) */
+		nx842_build_scatterlist(outbuf, *outlen, &slout);
+		op.out = nx842_get_pa(slout.entries);
+		op.outlen = -nx842_get_scatterlist_size(&slout);
+	}
+
+	dev_dbg(dev, "%s: op.in %lx op.inlen %ld op.out %lx op.outlen %ld\n",
+		__func__, (unsigned long)op.in, (long)op.inlen,
+		(unsigned long)op.out, (long)op.outlen);
+
+	/* Send request to pHyp */
+	ret = vio_h_cop_sync(local_devdata->vdev, &op);
+
+	/* Check for pHyp error */
+	if (ret) {
+		dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
+			__func__, ret, op.hcall_err);
+		goto unlock;
+	}
+
+	/* Check for hardware error */
+	ret = nx842_validate_result(dev, &csbcpb->csb);
+	if (ret)
+		goto unlock;
+
+	*outlen = be32_to_cpu(csbcpb->csb.processed_byte_count);
+
+unlock:
+	if (ret)
+		/* decompress fail */
+		nx842_inc_decomp_failed(local_devdata);
+	else {
+		nx842_inc_decomp_complete(local_devdata);
+		ibm_nx842_incr_hist(local_devdata->counters->decomp_times,
+			(get_tb() - start) / tb_ticks_per_usec);
+	}
+
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * nx842_OF_set_defaults -- Set default (disabled) values for devdata
+ *
+ * @devdata - struct nx842_devdata to update
+ *
+ * Returns:
+ *  0 on success
+ *  -ENOENT if @devdata ptr is NULL
+ */
+static int nx842_OF_set_defaults(struct nx842_devdata *devdata)
+{
+	if (devdata) {
+		devdata->max_sync_size = 0;
+		devdata->max_sync_sg = 0;
+		devdata->max_sg_len = 0;
+		devdata->status = UNAVAILABLE;
+		return 0;
+	} else
+		return -ENOENT;
+}
+
+/**
+ * nx842_OF_upd_status -- Update the device info from OF status prop
+ *
+ * The status property indicates if the accelerator is enabled.  If the
+ * device is in the OF tree it indicates that the hardware is present.
+ * The status field indicates if the device is enabled when the status
+ * is 'okay'.  Otherwise the device driver will be disabled.
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 - Device is available
+ *  -EINVAL - Device is not available
+ */
+static int nx842_OF_upd_status(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	const char *status = (const char *)prop->value;
+
+	if (!strncmp(status, "okay", (size_t)prop->length)) {
+		devdata->status = AVAILABLE;
+	} else {
+		dev_info(devdata->dev, "%s: status '%s' is not 'okay'\n",
+				__func__, status);
+		devdata->status = UNAVAILABLE;
+	}
+
+	return ret;
+}
+
+/**
+ * nx842_OF_upd_maxsglen -- Update the device info from OF maxsglen prop
+ *
+ * Definition of the 'ibm,max-sg-len' OF property:
+ *  This field indicates the maximum byte length of a scatter list
+ *  for the platform facility. It is a single cell encoded as with encode-int.
+ *
+ * Example:
+ *  # od -x ibm,max-sg-len
+ *  0000000 0000 0ff0
+ *
+ *  In this example, the maximum byte length of a scatter list is
+ *  0x0ff0 (4,080).
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL on failure
+ */
+static int nx842_OF_upd_maxsglen(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	const unsigned int maxsglen = of_read_number(prop->value, 1);
+
+	if (prop->length != sizeof(maxsglen)) {
+		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sg-len property\n", __func__);
+		dev_dbg(devdata->dev, "%s: ibm,max-sg-len is %d bytes long, expected %lu bytes\n", __func__,
+				prop->length, sizeof(maxsglen));
+		ret = -EINVAL;
+	} else {
+		devdata->max_sg_len = min_t(unsigned int,
+					    maxsglen, NX842_HW_PAGE_SIZE);
+	}
+
+	return ret;
+}
+
+/**
+ * nx842_OF_upd_maxsyncop -- Update the device info from OF maxsyncop prop
+ *
+ * Definition of the 'ibm,max-sync-cop' OF property:
+ *  Two series of cells.  The first series of cells represents the maximums
+ *  that can be synchronously compressed. The second series of cells
+ *  represents the maximums that can be synchronously decompressed.
+ *  1. The first cell in each series contains the count of the number of
+ *     data length, scatter list elements pairs that follow – each being
+ *     of the form
+ *    a. One cell data byte length
+ *    b. One cell total number of scatter list elements
+ *
+ * Example:
+ *  # od -x ibm,max-sync-cop
+ *  0000000 0000 0001 0000 1000 0000 01fe 0000 0001
+ *  0000020 0000 1000 0000 01fe
+ *
+ *  In this example, compression supports 0x1000 (4,096) data byte length
+ *  and 0x1fe (510) total scatter list elements.  Decompression supports
+ *  0x1000 (4,096) data byte length and 0x1f3 (510) total scatter list
+ *  elements.
+ *
+ * @devdata - struct nx842_devdata to update
+ * @prop - struct property point containing the maxsyncop for the update
+ *
+ * Returns:
+ *  0 on success
+ *  -EINVAL on failure
+ */
+static int nx842_OF_upd_maxsyncop(struct nx842_devdata *devdata,
+					struct property *prop) {
+	int ret = 0;
+	unsigned int comp_data_limit, decomp_data_limit;
+	unsigned int comp_sg_limit, decomp_sg_limit;
+	const struct maxsynccop_t {
+		__be32 comp_elements;
+		__be32 comp_data_limit;
+		__be32 comp_sg_limit;
+		__be32 decomp_elements;
+		__be32 decomp_data_limit;
+		__be32 decomp_sg_limit;
+	} *maxsynccop;
+
+	if (prop->length != sizeof(*maxsynccop)) {
+		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sync-cop property\n", __func__);
+		dev_dbg(devdata->dev, "%s: ibm,max-sync-cop is %d bytes long, expected %lu bytes\n", __func__, prop->length,
+				sizeof(*maxsynccop));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	maxsynccop = (const struct maxsynccop_t *)prop->value;
+	comp_data_limit = be32_to_cpu(maxsynccop->comp_data_limit);
+	comp_sg_limit = be32_to_cpu(maxsynccop->comp_sg_limit);
+	decomp_data_limit = be32_to_cpu(maxsynccop->decomp_data_limit);
+	decomp_sg_limit = be32_to_cpu(maxsynccop->decomp_sg_limit);
+
+	/* Use one limit rather than separate limits for compression and
+	 * decompression. Set a maximum for this so as not to exceed the
+	 * size that the header can support and round the value down to
+	 * the hardware page size (4K) */
+	devdata->max_sync_size = min(comp_data_limit, decomp_data_limit);
+
+	devdata->max_sync_size = min_t(unsigned int, devdata->max_sync_size,
+					65536);
+
+	if (devdata->max_sync_size < 4096) {
+		dev_err(devdata->dev, "%s: hardware max data size (%u) is "
+				"less than the driver minimum, unable to use "
+				"the hardware device\n",
+				__func__, devdata->max_sync_size);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nx842_pseries_constraints.maximum = devdata->max_sync_size;
+
+	devdata->max_sync_sg = min(comp_sg_limit, decomp_sg_limit);
+	if (devdata->max_sync_sg < 1) {
+		dev_err(devdata->dev, "%s: hardware max sg size (%u) is "
+				"less than the driver minimum, unable to use "
+				"the hardware device\n",
+				__func__, devdata->max_sync_sg);
+		ret = -EINVAL;
+		goto out;
+	}
+
+out:
+	return ret;
+}
+
+/**
+ *
+ * nx842_OF_upd -- Handle OF properties updates for the device.
+ *
+ * Set all properties from the OF tree.  Optionally, a new property
+ * can be provided by the @new_prop pointer to overwrite an existing value.
+ * The device will remain disabled until all values are valid, this function
+ * will return an error for updates unless all values are valid.
+ *
+ * @new_prop: If not NULL, this property is being updated.  If NULL, update
+ *  all properties from the current values in the OF tree.
+ *
+ * Returns:
+ *  0 - Success
+ *  -ENOMEM - Could not allocate memory for new devdata structure
+ *  -EINVAL - property value not found, new_prop is not a recognized
+ *	property for the device or property value is not valid.
+ *  -ENODEV - Device is not available
+ */
+static int nx842_OF_upd(struct property *new_prop)
+{
+	struct nx842_devdata *old_devdata = NULL;
+	struct nx842_devdata *new_devdata = NULL;
+	struct device_node *of_node = NULL;
+	struct property *status = NULL;
+	struct property *maxsglen = NULL;
+	struct property *maxsyncop = NULL;
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	if (old_devdata)
+		of_node = old_devdata->dev->of_node;
+
+	if (!old_devdata || !of_node) {
+		pr_err("%s: device is not available\n", __func__);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+		return -ENODEV;
+	}
+
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata) {
+		dev_err(old_devdata->dev, "%s: Could not allocate memory for device data\n", __func__);
+		ret = -ENOMEM;
+		goto error_out;
+	}
+
+	memcpy(new_devdata, old_devdata, sizeof(*old_devdata));
+	new_devdata->counters = old_devdata->counters;
+
+	/* Set ptrs for existing properties */
+	status = of_find_property(of_node, "status", NULL);
+	maxsglen = of_find_property(of_node, "ibm,max-sg-len", NULL);
+	maxsyncop = of_find_property(of_node, "ibm,max-sync-cop", NULL);
+	if (!status || !maxsglen || !maxsyncop) {
+		dev_err(old_devdata->dev, "%s: Could not locate device properties\n", __func__);
+		ret = -EINVAL;
+		goto error_out;
+	}
+
+	/*
+	 * If this is a property update, there are only certain properties that
+	 * we care about. Bail if it isn't in the below list
+	 */
+	if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) ||
+		         strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) ||
+		         strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length)))
+		goto out;
+
+	/* Perform property updates */
+	ret = nx842_OF_upd_status(new_devdata, status);
+	if (ret)
+		goto error_out;
+
+	ret = nx842_OF_upd_maxsglen(new_devdata, maxsglen);
+	if (ret)
+		goto error_out;
+
+	ret = nx842_OF_upd_maxsyncop(new_devdata, maxsyncop);
+	if (ret)
+		goto error_out;
+
+out:
+	dev_info(old_devdata->dev, "%s: max_sync_size new:%u old:%u\n",
+			__func__, new_devdata->max_sync_size,
+			old_devdata->max_sync_size);
+	dev_info(old_devdata->dev, "%s: max_sync_sg new:%u old:%u\n",
+			__func__, new_devdata->max_sync_sg,
+			old_devdata->max_sync_sg);
+	dev_info(old_devdata->dev, "%s: max_sg_len new:%u old:%u\n",
+			__func__, new_devdata->max_sg_len,
+			old_devdata->max_sg_len);
+
+	rcu_assign_pointer(devdata, new_devdata);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	dev_set_drvdata(new_devdata->dev, new_devdata);
+	kfree(old_devdata);
+	return 0;
+
+error_out:
+	if (new_devdata) {
+		dev_info(old_devdata->dev, "%s: device disabled\n", __func__);
+		nx842_OF_set_defaults(new_devdata);
+		rcu_assign_pointer(devdata, new_devdata);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+		synchronize_rcu();
+		dev_set_drvdata(new_devdata->dev, new_devdata);
+		kfree(old_devdata);
+	} else {
+		dev_err(old_devdata->dev, "%s: could not update driver from hardware\n", __func__);
+		spin_unlock_irqrestore(&devdata_mutex, flags);
+	}
+
+	if (!ret)
+		ret = -EINVAL;
+	return ret;
+}
+
+/**
+ * nx842_OF_notifier - Process updates to OF properties for the device
+ *
+ * @np: notifier block
+ * @action: notifier action
+ * @update: struct pSeries_reconfig_prop_update pointer if action is
+ *	PSERIES_UPDATE_PROPERTY
+ *
+ * Returns:
+ *	NOTIFY_OK on success
+ *	NOTIFY_BAD encoded with error number on failure, use
+ *		notifier_to_errno() to decode this value
+ */
+static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
+			     void *data)
+{
+	struct of_reconfig_data *upd = data;
+	struct nx842_devdata *local_devdata;
+	struct device_node *node = NULL;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (local_devdata)
+		node = local_devdata->dev->of_node;
+
+	if (local_devdata &&
+			action == OF_RECONFIG_UPDATE_PROPERTY &&
+			!strcmp(upd->dn->name, node->name)) {
+		rcu_read_unlock();
+		nx842_OF_upd(upd->prop);
+	} else
+		rcu_read_unlock();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block nx842_of_nb = {
+	.notifier_call = nx842_OF_notifier,
+};
+
+#define nx842_counter_read(_name)					\
+static ssize_t nx842_##_name##_show(struct device *dev,		\
+		struct device_attribute *attr,				\
+		char *buf) {						\
+	struct nx842_devdata *local_devdata;			\
+	int p = 0;							\
+	rcu_read_lock();						\
+	local_devdata = rcu_dereference(devdata);			\
+	if (local_devdata)						\
+		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
+		       atomic64_read(&local_devdata->counters->_name));	\
+	rcu_read_unlock();						\
+	return p;							\
+}
+
+#define NX842DEV_COUNTER_ATTR_RO(_name)					\
+	nx842_counter_read(_name);					\
+	static struct device_attribute dev_attr_##_name = __ATTR(_name,	\
+						0444,			\
+						nx842_##_name##_show,\
+						NULL);
+
+NX842DEV_COUNTER_ATTR_RO(comp_complete);
+NX842DEV_COUNTER_ATTR_RO(comp_failed);
+NX842DEV_COUNTER_ATTR_RO(decomp_complete);
+NX842DEV_COUNTER_ATTR_RO(decomp_failed);
+NX842DEV_COUNTER_ATTR_RO(swdecomp);
+
+static ssize_t nx842_timehist_show(struct device *,
+		struct device_attribute *, char *);
+
+static struct device_attribute dev_attr_comp_times = __ATTR(comp_times, 0444,
+		nx842_timehist_show, NULL);
+static struct device_attribute dev_attr_decomp_times = __ATTR(decomp_times,
+		0444, nx842_timehist_show, NULL);
+
+static ssize_t nx842_timehist_show(struct device *dev,
+		struct device_attribute *attr, char *buf) {
+	char *p = buf;
+	struct nx842_devdata *local_devdata;
+	atomic64_t *times;
+	int bytes_remain = PAGE_SIZE;
+	int bytes;
+	int i;
+
+	rcu_read_lock();
+	local_devdata = rcu_dereference(devdata);
+	if (!local_devdata) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	if (attr == &dev_attr_comp_times)
+		times = local_devdata->counters->comp_times;
+	else if (attr == &dev_attr_decomp_times)
+		times = local_devdata->counters->decomp_times;
+	else {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
+		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
+			       i ? (2<<(i-1)) : 0, (2<<i)-1,
+			       atomic64_read(&times[i]));
+		bytes_remain -= bytes;
+		p += bytes;
+	}
+	/* The last bucket holds everything over
+	 * 2<<(NX842_HIST_SLOTS - 2) us */
+	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
+			2<<(NX842_HIST_SLOTS - 2),
+			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
+	p += bytes;
+
+	rcu_read_unlock();
+	return p - buf;
+}
+
+static struct attribute *nx842_sysfs_entries[] = {
+	&dev_attr_comp_complete.attr,
+	&dev_attr_comp_failed.attr,
+	&dev_attr_decomp_complete.attr,
+	&dev_attr_decomp_failed.attr,
+	&dev_attr_swdecomp.attr,
+	&dev_attr_comp_times.attr,
+	&dev_attr_decomp_times.attr,
+	NULL,
+};
+
+static struct attribute_group nx842_attribute_group = {
+	.name = NULL,		/* put in device directory */
+	.attrs = nx842_sysfs_entries,
+};
+
+static struct nx842_driver nx842_pseries_driver = {
+	.name =		KBUILD_MODNAME,
+	.owner =	THIS_MODULE,
+	.workmem_size =	sizeof(struct nx842_workmem),
+	.constraints =	&nx842_pseries_constraints,
+	.compress =	nx842_pseries_compress,
+	.decompress =	nx842_pseries_decompress,
+};
+
+static int __init nx842_probe(struct vio_dev *viodev,
+				  const struct vio_device_id *id)
+{
+	struct nx842_devdata *old_devdata, *new_devdata = NULL;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+
+	if (old_devdata && old_devdata->vdev != NULL) {
+		dev_err(&viodev->dev, "%s: Attempt to register more than one instance of the hardware\n", __func__);
+		ret = -1;
+		goto error_unlock;
+	}
+
+	dev_set_drvdata(&viodev->dev, NULL);
+
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
+	if (!new_devdata) {
+		dev_err(&viodev->dev, "%s: Could not allocate memory for device data\n", __func__);
+		ret = -ENOMEM;
+		goto error_unlock;
+	}
+
+	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
+			GFP_NOFS);
+	if (!new_devdata->counters) {
+		dev_err(&viodev->dev, "%s: Could not allocate memory for performance counters\n", __func__);
+		ret = -ENOMEM;
+		goto error_unlock;
+	}
+
+	new_devdata->vdev = viodev;
+	new_devdata->dev = &viodev->dev;
+	nx842_OF_set_defaults(new_devdata);
+
+	rcu_assign_pointer(devdata, new_devdata);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	kfree(old_devdata);
+
+	of_reconfig_notifier_register(&nx842_of_nb);
+
+	ret = nx842_OF_upd(NULL);
+	if (ret && ret != -ENODEV) {
+		dev_err(&viodev->dev, "could not parse device tree. %d\n", ret);
+		ret = -1;
+		goto error;
+	}
+
+	rcu_read_lock();
+	dev_set_drvdata(&viodev->dev, rcu_dereference(devdata));
+	rcu_read_unlock();
+
+	if (sysfs_create_group(&viodev->dev.kobj, &nx842_attribute_group)) {
+		dev_err(&viodev->dev, "could not create sysfs device attributes\n");
+		ret = -1;
+		goto error;
+	}
+
+	return 0;
+
+error_unlock:
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	if (new_devdata)
+		kfree(new_devdata->counters);
+	kfree(new_devdata);
+error:
+	return ret;
+}
+
+static int __exit nx842_remove(struct vio_dev *viodev)
+{
+	struct nx842_devdata *old_devdata;
+	unsigned long flags;
+
+	pr_info("Removing IBM Power 842 compression device\n");
+	sysfs_remove_group(&viodev->dev.kobj, &nx842_attribute_group);
+
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	of_reconfig_notifier_unregister(&nx842_of_nb);
+	RCU_INIT_POINTER(devdata, NULL);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	dev_set_drvdata(&viodev->dev, NULL);
+	if (old_devdata)
+		kfree(old_devdata->counters);
+	kfree(old_devdata);
+
+	return 0;
+}
+
+static struct vio_device_id nx842_vio_driver_ids[] = {
+	{"ibm,compression-v1", "ibm,compression"},
+	{"", ""},
+};
+
+static struct vio_driver nx842_vio_driver = {
+	.name = KBUILD_MODNAME,
+	.probe = nx842_probe,
+	.remove = __exit_p(nx842_remove),
+	.get_desired_dma = nx842_get_desired_dma,
+	.id_table = nx842_vio_driver_ids,
+};
+
+static int __init nx842_init(void)
+{
+	struct nx842_devdata *new_devdata;
+	int ret;
+
+	pr_info("Registering IBM Power 842 compression driver\n");
+
+	if (!of_find_compatible_node(NULL, NULL, "ibm,compression"))
+		return -ENODEV;
+
+	RCU_INIT_POINTER(devdata, NULL);
+	new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL);
+	if (!new_devdata) {
+		pr_err("Could not allocate memory for device data\n");
+		return -ENOMEM;
+	}
+	new_devdata->status = UNAVAILABLE;
+	RCU_INIT_POINTER(devdata, new_devdata);
+
+	ret = vio_register_driver(&nx842_vio_driver);
+	if (ret) {
+		pr_err("Could not register VIO driver %d\n", ret);
+
+		kfree(new_devdata);
+		return ret;
+	}
+
+	if (!nx842_platform_driver_set(&nx842_pseries_driver)) {
+		vio_unregister_driver(&nx842_vio_driver);
+		kfree(new_devdata);
+		return -EEXIST;
+	}
+
+	return 0;
+}
+
+module_init(nx842_init);
+
+static void __exit nx842_exit(void)
+{
+	struct nx842_devdata *old_devdata;
+	unsigned long flags;
+
+	pr_info("Exiting IBM Power 842 compression driver\n");
+	nx842_platform_driver_unset(&nx842_pseries_driver);
+	spin_lock_irqsave(&devdata_mutex, flags);
+	old_devdata = rcu_dereference_check(devdata,
+			lockdep_is_held(&devdata_mutex));
+	RCU_INIT_POINTER(devdata, NULL);
+	spin_unlock_irqrestore(&devdata_mutex, flags);
+	synchronize_rcu();
+	if (old_devdata && old_devdata->dev)
+		dev_set_drvdata(old_devdata->dev, NULL);
+	kfree(old_devdata);
+	vio_unregister_driver(&nx842_vio_driver);
+}
+
+module_exit(nx842_exit);
+
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 887196e9b50c..6e5e0d60d0c8 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -1,5 +1,10 @@
 /*
- * Driver for IBM Power 842 compression accelerator
+ * Driver frontend for IBM Power 842 compression accelerator
+ *
+ * Copyright (C) 2015 Dan Streetman, IBM Corp
+ *
+ * Designer of the Power data compression engine:
+ *   Bulent Abali <abali@us.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -10,1594 +15,89 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
- * Copyright (C) IBM Corporation, 2012
- *
- * Authors: Robert Jennings <rcj@linux.vnet.ibm.com>
- *          Seth Jennings <sjenning@linux.vnet.ibm.com>
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/nx842.h>
-#include <linux/of.h>
-#include <linux/slab.h>
-
-#include <asm/page.h>
-#include <asm/vio.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include "nx_csbcpb.h" /* struct nx_csbcpb */
+#include "nx-842.h"
 
-#define MODULE_NAME "nx-compress"
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Robert Jennings <rcj@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
 MODULE_DESCRIPTION("842 H/W Compression driver for IBM Power processors");
 
-#define SHIFT_4K 12
-#define SHIFT_64K 16
-#define SIZE_4K (1UL << SHIFT_4K)
-#define SIZE_64K (1UL << SHIFT_64K)
-
-/* IO buffer must be 128 byte aligned */
-#define IO_BUFFER_ALIGN 128
-
-struct nx842_header {
-	int blocks_nr; /* number of compressed blocks */
-	int offset; /* offset of the first block (from beginning of header) */
-	int sizes[0]; /* size of compressed blocks */
-};
-
-static inline int nx842_header_size(const struct nx842_header *hdr)
-{
-	return sizeof(struct nx842_header) +
-			hdr->blocks_nr * sizeof(hdr->sizes[0]);
-}
-
-/* Macros for fields within nx_csbcpb */
-/* Check the valid bit within the csbcpb valid field */
-#define NX842_CSBCBP_VALID_CHK(x) (x & BIT_MASK(7))
-
-/* CE macros operate on the completion_extension field bits in the csbcpb.
- * CE0 0=full completion, 1=partial completion
- * CE1 0=CE0 indicates completion, 1=termination (output may be modified)
- * CE2 0=processed_bytes is source bytes, 1=processed_bytes is target bytes */
-#define NX842_CSBCPB_CE0(x)	(x & BIT_MASK(7))
-#define NX842_CSBCPB_CE1(x)	(x & BIT_MASK(6))
-#define NX842_CSBCPB_CE2(x)	(x & BIT_MASK(5))
-
-/* The NX unit accepts data only on 4K page boundaries */
-#define NX842_HW_PAGE_SHIFT	SHIFT_4K
-#define NX842_HW_PAGE_SIZE	(ASM_CONST(1) << NX842_HW_PAGE_SHIFT)
-#define NX842_HW_PAGE_MASK	(~(NX842_HW_PAGE_SIZE-1))
-
-enum nx842_status {
-	UNAVAILABLE,
-	AVAILABLE
-};
-
-struct ibm_nx842_counters {
-	atomic64_t comp_complete;
-	atomic64_t comp_failed;
-	atomic64_t decomp_complete;
-	atomic64_t decomp_failed;
-	atomic64_t swdecomp;
-	atomic64_t comp_times[32];
-	atomic64_t decomp_times[32];
-};
-
-static struct nx842_devdata {
-	struct vio_dev *vdev;
-	struct device *dev;
-	struct ibm_nx842_counters *counters;
-	unsigned int max_sg_len;
-	unsigned int max_sync_size;
-	unsigned int max_sync_sg;
-	enum nx842_status status;
-} __rcu *devdata;
-static DEFINE_SPINLOCK(devdata_mutex);
-
-#define NX842_COUNTER_INC(_x) \
-static inline void nx842_inc_##_x( \
-	const struct nx842_devdata *dev) { \
-	if (dev) \
-		atomic64_inc(&dev->counters->_x); \
-}
-NX842_COUNTER_INC(comp_complete);
-NX842_COUNTER_INC(comp_failed);
-NX842_COUNTER_INC(decomp_complete);
-NX842_COUNTER_INC(decomp_failed);
-NX842_COUNTER_INC(swdecomp);
-
-#define NX842_HIST_SLOTS 16
-
-static void ibm_nx842_incr_hist(atomic64_t *times, unsigned int time)
-{
-	int bucket = fls(time);
-
-	if (bucket)
-		bucket = min((NX842_HIST_SLOTS - 1), bucket - 1);
-
-	atomic64_inc(&times[bucket]);
-}
-
-/* NX unit operation flags */
-#define NX842_OP_COMPRESS	0x0
-#define NX842_OP_CRC		0x1
-#define NX842_OP_DECOMPRESS	0x2
-#define NX842_OP_COMPRESS_CRC   (NX842_OP_COMPRESS | NX842_OP_CRC)
-#define NX842_OP_DECOMPRESS_CRC (NX842_OP_DECOMPRESS | NX842_OP_CRC)
-#define NX842_OP_ASYNC		(1<<23)
-#define NX842_OP_NOTIFY		(1<<22)
-#define NX842_OP_NOTIFY_INT(x)	((x & 0xff)<<8)
-
-static unsigned long nx842_get_desired_dma(struct vio_dev *viodev)
-{
-	/* No use of DMA mappings within the driver. */
-	return 0;
-}
-
-struct nx842_slentry {
-	unsigned long ptr; /* Real address (use __pa()) */
-	unsigned long len;
-};
-
-/* pHyp scatterlist entry */
-struct nx842_scatterlist {
-	int entry_nr; /* number of slentries */
-	struct nx842_slentry *entries; /* ptr to array of slentries */
-};
-
-/* Does not include sizeof(entry_nr) in the size */
-static inline unsigned long nx842_get_scatterlist_size(
-				struct nx842_scatterlist *sl)
-{
-	return sl->entry_nr * sizeof(struct nx842_slentry);
-}
-
-static inline unsigned long nx842_get_pa(void *addr)
-{
-	if (is_vmalloc_addr(addr))
-		return page_to_phys(vmalloc_to_page(addr))
-		       + offset_in_page(addr);
-	else
-		return __pa(addr);
-}
-
-static int nx842_build_scatterlist(unsigned long buf, int len,
-			struct nx842_scatterlist *sl)
-{
-	unsigned long nextpage;
-	struct nx842_slentry *entry;
-
-	sl->entry_nr = 0;
-
-	entry = sl->entries;
-	while (len) {
-		entry->ptr = nx842_get_pa((void *)buf);
-		nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE);
-		if (nextpage < buf + len) {
-			/* we aren't at the end yet */
-			if (IS_ALIGNED(buf, NX842_HW_PAGE_SIZE))
-				/* we are in the middle (or beginning) */
-				entry->len = NX842_HW_PAGE_SIZE;
-			else
-				/* we are at the beginning */
-				entry->len = nextpage - buf;
-		} else {
-			/* at the end */
-			entry->len = len;
-		}
-
-		len -= entry->len;
-		buf += entry->len;
-		sl->entry_nr++;
-		entry++;
-	}
-
-	return 0;
-}
-
-/*
- * Working memory for software decompression
- */
-struct sw842_fifo {
-	union {
-		char f8[256][8];
-		char f4[512][4];
-	};
-	char f2[256][2];
-	unsigned char f84_full;
-	unsigned char f2_full;
-	unsigned char f8_count;
-	unsigned char f2_count;
-	unsigned int f4_count;
-};
-
-/*
- * Working memory for crypto API
+/**
+ * nx842_constraints
+ *
+ * This provides the driver's constraints.  Different nx842 implementations
+ * may have varying requirements.  The constraints are:
+ *   @alignment:	All buffers should be aligned to this
+ *   @multiple:		All buffer lengths should be a multiple of this
+ *   @minimum:		Buffer lengths must not be less than this amount
+ *   @maximum:		Buffer lengths must not be more than this amount
+ *
+ * The constraints apply to all buffers and lengths, both input and output,
+ * for both compression and decompression, except for the minimum which
+ * only applies to compression input and decompression output; the
+ * compressed data can be less than the minimum constraint.  It can be
+ * assumed that compressed data will always adhere to the multiple
+ * constraint.
+ *
+ * The driver may succeed even if these constraints are violated;
+ * however the driver can return failure or suffer reduced performance
+ * if any constraint is not met.
  */
-struct nx842_workmem {
-	char bounce[PAGE_SIZE]; /* bounce buffer for decompression input */
-	union {
-		/* hardware working memory */
-		struct {
-			/* scatterlist */
-			char slin[SIZE_4K];
-			char slout[SIZE_4K];
-			/* coprocessor status/parameter block */
-			struct nx_csbcpb csbcpb;
-		};
-		/* software working memory */
-		struct sw842_fifo swfifo; /* software decompression fifo */
-	};
-};
-
-int nx842_get_workmem_size(void)
-{
-	return sizeof(struct nx842_workmem) + NX842_HW_PAGE_SIZE;
-}
-EXPORT_SYMBOL_GPL(nx842_get_workmem_size);
-
-int nx842_get_workmem_size_aligned(void)
-{
-	return sizeof(struct nx842_workmem);
-}
-EXPORT_SYMBOL_GPL(nx842_get_workmem_size_aligned);
-
-static int nx842_validate_result(struct device *dev,
-	struct cop_status_block *csb)
+int nx842_constraints(struct nx842_constraints *c)
 {
-	/* The csb must be valid after returning from vio_h_cop_sync */
-	if (!NX842_CSBCBP_VALID_CHK(csb->valid)) {
-		dev_err(dev, "%s: cspcbp not valid upon completion.\n",
-				__func__);
-		dev_dbg(dev, "valid:0x%02x cs:0x%02x cc:0x%02x ce:0x%02x\n",
-				csb->valid,
-				csb->crb_seq_number,
-				csb->completion_code,
-				csb->completion_extension);
-		dev_dbg(dev, "processed_bytes:%d address:0x%016lx\n",
-				csb->processed_byte_count,
-				(unsigned long)csb->address);
-		return -EIO;
-	}
-
-	/* Check return values from the hardware in the CSB */
-	switch (csb->completion_code) {
-	case 0:	/* Completed without error */
-		break;
-	case 64: /* Target bytes > Source bytes during compression */
-	case 13: /* Output buffer too small */
-		dev_dbg(dev, "%s: Compression output larger than input\n",
-					__func__);
-		return -ENOSPC;
-	case 66: /* Input data contains an illegal template field */
-	case 67: /* Template indicates data past the end of the input stream */
-		dev_dbg(dev, "%s: Bad data for decompression (code:%d)\n",
-					__func__, csb->completion_code);
-		return -EINVAL;
-	default:
-		dev_dbg(dev, "%s: Unspecified error (code:%d)\n",
-					__func__, csb->completion_code);
-		return -EIO;
-	}
-
-	/* Hardware sanity check */
-	if (!NX842_CSBCPB_CE2(csb->completion_extension)) {
-		dev_err(dev, "%s: No error returned by hardware, but "
-				"data returned is unusable, contact support.\n"
-				"(Additional info: csbcbp->processed bytes "
-				"does not specify processed bytes for the "
-				"target buffer.)\n", __func__);
-		return -EIO;
-	}
-
+	memcpy(c, nx842_platform_driver()->constraints, sizeof(*c));
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nx842_constraints);
 
 /**
- * nx842_compress - Compress data using the 842 algorithm
- *
- * Compression provide by the NX842 coprocessor on IBM Power systems.
- * The input buffer is compressed and the result is stored in the
- * provided output buffer.
- *
- * Upon return from this function @outlen contains the length of the
- * compressed data.  If there is an error then @outlen will be 0 and an
- * error will be specified by the return code from this function.
- *
- * @in: Pointer to input buffer, must be page aligned
- * @inlen: Length of input buffer, must be PAGE_SIZE
- * @out: Pointer to output buffer
- * @outlen: Length of output buffer
- * @wrkmem: ptr to buffer for working memory, size determined by
- *          nx842_get_workmem_size()
+ * nx842_workmem_size
  *
- * Returns:
- *   0		Success, output of length @outlen stored in the buffer at @out
- *   -ENOMEM	Unable to allocate internal buffers
- *   -ENOSPC	Output buffer is to small
- *   -EMSGSIZE	XXX Difficult to describe this limitation
- *   -EIO	Internal error
- *   -ENODEV	Hardware unavailable
+ * Get the amount of working memory the driver requires.
  */
-int nx842_compress(const unsigned char *in, unsigned int inlen,
-		       unsigned char *out, unsigned int *outlen, void *wmem)
+size_t nx842_workmem_size(void)
 {
-	struct nx842_header *hdr;
-	struct nx842_devdata *local_devdata;
-	struct device *dev = NULL;
-	struct nx842_workmem *workmem;
-	struct nx842_scatterlist slin, slout;
-	struct nx_csbcpb *csbcpb;
-	int ret = 0, max_sync_size, i, bytesleft, size, hdrsize;
-	unsigned long inbuf, outbuf, padding;
-	struct vio_pfo_op op = {
-		.done = NULL,
-		.handle = 0,
-		.timeout = 0,
-	};
-	unsigned long start_time = get_tb();
-
-	/*
-	 * Make sure input buffer is 64k page aligned.  This is assumed since
-	 * this driver is designed for page compression only (for now).  This
-	 * is very nice since we can now use direct DDE(s) for the input and
-	 * the alignment is guaranteed.
-	*/
-	inbuf = (unsigned long)in;
-	if (!IS_ALIGNED(inbuf, PAGE_SIZE) || inlen != PAGE_SIZE)
-		return -EINVAL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (!local_devdata || !local_devdata->dev) {
-		rcu_read_unlock();
-		return -ENODEV;
-	}
-	max_sync_size = local_devdata->max_sync_size;
-	dev = local_devdata->dev;
-
-	/* Create the header */
-	hdr = (struct nx842_header *)out;
-	hdr->blocks_nr = PAGE_SIZE / max_sync_size;
-	hdrsize = nx842_header_size(hdr);
-	outbuf = (unsigned long)out + hdrsize;
-	bytesleft = *outlen - hdrsize;
-
-	/* Init scatterlist */
-	workmem = (struct nx842_workmem *)ALIGN((unsigned long)wmem,
-		NX842_HW_PAGE_SIZE);
-	slin.entries = (struct nx842_slentry *)workmem->slin;
-	slout.entries = (struct nx842_slentry *)workmem->slout;
-
-	/* Init operation */
-	op.flags = NX842_OP_COMPRESS;
-	csbcpb = &workmem->csbcpb;
-	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = nx842_get_pa(csbcpb);
-	op.out = nx842_get_pa(slout.entries);
-
-	for (i = 0; i < hdr->blocks_nr; i++) {
-		/*
-		 * Aligning the output blocks to 128 bytes does waste space,
-		 * but it prevents the need for bounce buffers and memory
-		 * copies.  It also simplifies the code a lot.  In the worst
-		 * case (64k page, 4k max_sync_size), you lose up to
-		 * (128*16)/64k = ~3% the compression factor. For 64k
-		 * max_sync_size, the loss would be at most 128/64k = ~0.2%.
-		 */
-		padding = ALIGN(outbuf, IO_BUFFER_ALIGN) - outbuf;
-		outbuf += padding;
-		bytesleft -= padding;
-		if (i == 0)
-			/* save offset into first block in header */
-			hdr->offset = padding + hdrsize;
-
-		if (bytesleft <= 0) {
-			ret = -ENOSPC;
-			goto unlock;
-		}
-
-		/*
-		 * NOTE: If the default max_sync_size is changed from 4k
-		 * to 64k, remove the "likely" case below, since a
-		 * scatterlist will always be needed.
-		 */
-		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
-			/* Create direct DDE */
-			op.in = nx842_get_pa((void *)inbuf);
-			op.inlen = max_sync_size;
-
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(inbuf, max_sync_size, &slin);
-			op.in = nx842_get_pa(slin.entries);
-			op.inlen = -nx842_get_scatterlist_size(&slin);
-		}
-
-		/*
-		 * If max_sync_size != NX842_HW_PAGE_SIZE, an indirect
-		 * DDE is required for the outbuf.
-		 * If max_sync_size == NX842_HW_PAGE_SIZE, outbuf must
-		 * also be page aligned (1 in 128/4k=32 chance) in order
-		 * to use a direct DDE.
-		 * This is unlikely, just use an indirect DDE always.
-		 */
-		nx842_build_scatterlist(outbuf,
-			min(bytesleft, max_sync_size), &slout);
-		/* op.out set before loop */
-		op.outlen = -nx842_get_scatterlist_size(&slout);
-
-		/* Send request to pHyp */
-		ret = vio_h_cop_sync(local_devdata->vdev, &op);
-
-		/* Check for pHyp error */
-		if (ret) {
-			dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
-				__func__, ret, op.hcall_err);
-			ret = -EIO;
-			goto unlock;
-		}
-
-		/* Check for hardware error */
-		ret = nx842_validate_result(dev, &csbcpb->csb);
-		if (ret && ret != -ENOSPC)
-			goto unlock;
-
-		/* Handle incompressible data */
-		if (unlikely(ret == -ENOSPC)) {
-			if (bytesleft < max_sync_size) {
-				/*
-				 * Not enough space left in the output buffer
-				 * to store uncompressed block
-				 */
-				goto unlock;
-			} else {
-				/* Store incompressible block */
-				memcpy((void *)outbuf, (void *)inbuf,
-					max_sync_size);
-				hdr->sizes[i] = -max_sync_size;
-				outbuf += max_sync_size;
-				bytesleft -= max_sync_size;
-				/* Reset ret, incompressible data handled */
-				ret = 0;
-			}
-		} else {
-			/* Normal case, compression was successful */
-			size = csbcpb->csb.processed_byte_count;
-			dev_dbg(dev, "%s: processed_bytes=%d\n",
-				__func__, size);
-			hdr->sizes[i] = size;
-			outbuf += size;
-			bytesleft -= size;
-		}
-
-		inbuf += max_sync_size;
-	}
-
-	*outlen = (unsigned int)(outbuf - (unsigned long)out);
-
-unlock:
-	if (ret)
-		nx842_inc_comp_failed(local_devdata);
-	else {
-		nx842_inc_comp_complete(local_devdata);
-		ibm_nx842_incr_hist(local_devdata->counters->comp_times,
-			(get_tb() - start_time) / tb_ticks_per_usec);
-	}
-	rcu_read_unlock();
-	return ret;
+	return nx842_platform_driver()->workmem_size;
 }
-EXPORT_SYMBOL_GPL(nx842_compress);
-
-static int sw842_decompress(const unsigned char *, int, unsigned char *, int *,
-			const void *);
+EXPORT_SYMBOL_GPL(nx842_workmem_size);
 
-/**
- * nx842_decompress - Decompress data using the 842 algorithm
- *
- * Decompression provide by the NX842 coprocessor on IBM Power systems.
- * The input buffer is decompressed and the result is stored in the
- * provided output buffer.  The size allocated to the output buffer is
- * provided by the caller of this function in @outlen.  Upon return from
- * this function @outlen contains the length of the decompressed data.
- * If there is an error then @outlen will be 0 and an error will be
- * specified by the return code from this function.
- *
- * @in: Pointer to input buffer, will use bounce buffer if not 128 byte
- *      aligned
- * @inlen: Length of input buffer
- * @out: Pointer to output buffer, must be page aligned
- * @outlen: Length of output buffer, must be PAGE_SIZE
- * @wrkmem: ptr to buffer for working memory, size determined by
- *          nx842_get_workmem_size()
- *
- * Returns:
- *   0		Success, output of length @outlen stored in the buffer at @out
- *   -ENODEV	Hardware decompression device is unavailable
- *   -ENOMEM	Unable to allocate internal buffers
- *   -ENOSPC	Output buffer is to small
- *   -EINVAL	Bad input data encountered when attempting decompress
- *   -EIO	Internal error
- */
-int nx842_decompress(const unsigned char *in, unsigned int inlen,
-			 unsigned char *out, unsigned int *outlen, void *wmem)
+int nx842_compress(const unsigned char *in, unsigned int ilen,
+		   unsigned char *out, unsigned int *olen, void *wmem)
 {
-	struct nx842_header *hdr;
-	struct nx842_devdata *local_devdata;
-	struct device *dev = NULL;
-	struct nx842_workmem *workmem;
-	struct nx842_scatterlist slin, slout;
-	struct nx_csbcpb *csbcpb;
-	int ret = 0, i, size, max_sync_size;
-	unsigned long inbuf, outbuf;
-	struct vio_pfo_op op = {
-		.done = NULL,
-		.handle = 0,
-		.timeout = 0,
-	};
-	unsigned long start_time = get_tb();
-
-	/* Ensure page alignment and size */
-	outbuf = (unsigned long)out;
-	if (!IS_ALIGNED(outbuf, PAGE_SIZE) || *outlen != PAGE_SIZE)
-		return -EINVAL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (local_devdata)
-		dev = local_devdata->dev;
-
-	/* Get header */
-	hdr = (struct nx842_header *)in;
-
-	workmem = (struct nx842_workmem *)ALIGN((unsigned long)wmem,
-		NX842_HW_PAGE_SIZE);
-
-	inbuf = (unsigned long)in + hdr->offset;
-	if (likely(!IS_ALIGNED(inbuf, IO_BUFFER_ALIGN))) {
-		/* Copy block(s) into bounce buffer for alignment */
-		memcpy(workmem->bounce, in + hdr->offset, inlen - hdr->offset);
-		inbuf = (unsigned long)workmem->bounce;
-	}
-
-	/* Init scatterlist */
-	slin.entries = (struct nx842_slentry *)workmem->slin;
-	slout.entries = (struct nx842_slentry *)workmem->slout;
-
-	/* Init operation */
-	op.flags = NX842_OP_DECOMPRESS;
-	csbcpb = &workmem->csbcpb;
-	memset(csbcpb, 0, sizeof(*csbcpb));
-	op.csbcpb = nx842_get_pa(csbcpb);
-
-	/*
-	 * max_sync_size may have changed since compression,
-	 * so we can't read it from the device info. We need
-	 * to derive it from hdr->blocks_nr.
-	 */
-	max_sync_size = PAGE_SIZE / hdr->blocks_nr;
-
-	for (i = 0; i < hdr->blocks_nr; i++) {
-		/* Skip padding */
-		inbuf = ALIGN(inbuf, IO_BUFFER_ALIGN);
-
-		if (hdr->sizes[i] < 0) {
-			/* Negative sizes indicate uncompressed data blocks */
-			size = abs(hdr->sizes[i]);
-			memcpy((void *)outbuf, (void *)inbuf, size);
-			outbuf += size;
-			inbuf += size;
-			continue;
-		}
-
-		if (!dev)
-			goto sw;
-
-		/*
-		 * The better the compression, the more likely the "likely"
-		 * case becomes.
-		 */
-		if (likely((inbuf & NX842_HW_PAGE_MASK) ==
-			((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) {
-			/* Create direct DDE */
-			op.in = nx842_get_pa((void *)inbuf);
-			op.inlen = hdr->sizes[i];
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin);
-			op.in = nx842_get_pa(slin.entries);
-			op.inlen = -nx842_get_scatterlist_size(&slin);
-		}
-
-		/*
-		 * NOTE: If the default max_sync_size is changed from 4k
-		 * to 64k, remove the "likely" case below, since a
-		 * scatterlist will always be needed.
-		 */
-		if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) {
-			/* Create direct DDE */
-			op.out = nx842_get_pa((void *)outbuf);
-			op.outlen = max_sync_size;
-		} else {
-			/* Create indirect DDE (scatterlist) */
-			nx842_build_scatterlist(outbuf, max_sync_size, &slout);
-			op.out = nx842_get_pa(slout.entries);
-			op.outlen = -nx842_get_scatterlist_size(&slout);
-		}
-
-		/* Send request to pHyp */
-		ret = vio_h_cop_sync(local_devdata->vdev, &op);
-
-		/* Check for pHyp error */
-		if (ret) {
-			dev_dbg(dev, "%s: vio_h_cop_sync error (ret=%d, hret=%ld)\n",
-				__func__, ret, op.hcall_err);
-			dev = NULL;
-			goto sw;
-		}
-
-		/* Check for hardware error */
-		ret = nx842_validate_result(dev, &csbcpb->csb);
-		if (ret) {
-			dev = NULL;
-			goto sw;
-		}
-
-		/* HW decompression success */
-		inbuf += hdr->sizes[i];
-		outbuf += csbcpb->csb.processed_byte_count;
-		continue;
-
-sw:
-		/* software decompression */
-		size = max_sync_size;
-		ret = sw842_decompress(
-			(unsigned char *)inbuf, hdr->sizes[i],
-			(unsigned char *)outbuf, &size, wmem);
-		if (ret)
-			pr_debug("%s: sw842_decompress failed with %d\n",
-				__func__, ret);
-
-		if (ret) {
-			if (ret != -ENOSPC && ret != -EINVAL &&
-					ret != -EMSGSIZE)
-				ret = -EIO;
-			goto unlock;
-		}
-
-		/* SW decompression success */
-		inbuf += hdr->sizes[i];
-		outbuf += size;
-	}
-
-	*outlen = (unsigned int)(outbuf - (unsigned long)out);
-
-unlock:
-	if (ret)
-		/* decompress fail */
-		nx842_inc_decomp_failed(local_devdata);
-	else {
-		if (!dev)
-			/* software decompress */
-			nx842_inc_swdecomp(local_devdata);
-		nx842_inc_decomp_complete(local_devdata);
-		ibm_nx842_incr_hist(local_devdata->counters->decomp_times,
-			(get_tb() - start_time) / tb_ticks_per_usec);
-	}
-
-	rcu_read_unlock();
-	return ret;
+	return nx842_platform_driver()->compress(in, ilen, out, olen, wmem);
 }
-EXPORT_SYMBOL_GPL(nx842_decompress);
+EXPORT_SYMBOL_GPL(nx842_compress);
 
-/**
- * nx842_OF_set_defaults -- Set default (disabled) values for devdata
- *
- * @devdata - struct nx842_devdata to update
- *
- * Returns:
- *  0 on success
- *  -ENOENT if @devdata ptr is NULL
- */
-static int nx842_OF_set_defaults(struct nx842_devdata *devdata)
+int nx842_decompress(const unsigned char *in, unsigned int ilen,
+		     unsigned char *out, unsigned int *olen, void *wmem)
 {
-	if (devdata) {
-		devdata->max_sync_size = 0;
-		devdata->max_sync_sg = 0;
-		devdata->max_sg_len = 0;
-		devdata->status = UNAVAILABLE;
-		return 0;
-	} else
-		return -ENOENT;
-}
-
-/**
- * nx842_OF_upd_status -- Update the device info from OF status prop
- *
- * The status property indicates if the accelerator is enabled.  If the
- * device is in the OF tree it indicates that the hardware is present.
- * The status field indicates if the device is enabled when the status
- * is 'okay'.  Otherwise the device driver will be disabled.
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 - Device is available
- *  -EINVAL - Device is not available
- */
-static int nx842_OF_upd_status(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const char *status = (const char *)prop->value;
-
-	if (!strncmp(status, "okay", (size_t)prop->length)) {
-		devdata->status = AVAILABLE;
-	} else {
-		dev_info(devdata->dev, "%s: status '%s' is not 'okay'\n",
-				__func__, status);
-		devdata->status = UNAVAILABLE;
-	}
-
-	return ret;
-}
-
-/**
- * nx842_OF_upd_maxsglen -- Update the device info from OF maxsglen prop
- *
- * Definition of the 'ibm,max-sg-len' OF property:
- *  This field indicates the maximum byte length of a scatter list
- *  for the platform facility. It is a single cell encoded as with encode-int.
- *
- * Example:
- *  # od -x ibm,max-sg-len
- *  0000000 0000 0ff0
- *
- *  In this example, the maximum byte length of a scatter list is
- *  0x0ff0 (4,080).
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 on success
- *  -EINVAL on failure
- */
-static int nx842_OF_upd_maxsglen(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const int *maxsglen = prop->value;
-
-	if (prop->length != sizeof(*maxsglen)) {
-		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sg-len property\n", __func__);
-		dev_dbg(devdata->dev, "%s: ibm,max-sg-len is %d bytes long, expected %lu bytes\n", __func__,
-				prop->length, sizeof(*maxsglen));
-		ret = -EINVAL;
-	} else {
-		devdata->max_sg_len = (unsigned int)min(*maxsglen,
-				(int)NX842_HW_PAGE_SIZE);
-	}
-
-	return ret;
-}
-
-/**
- * nx842_OF_upd_maxsyncop -- Update the device info from OF maxsyncop prop
- *
- * Definition of the 'ibm,max-sync-cop' OF property:
- *  Two series of cells.  The first series of cells represents the maximums
- *  that can be synchronously compressed. The second series of cells
- *  represents the maximums that can be synchronously decompressed.
- *  1. The first cell in each series contains the count of the number of
- *     data length, scatter list elements pairs that follow – each being
- *     of the form
- *    a. One cell data byte length
- *    b. One cell total number of scatter list elements
- *
- * Example:
- *  # od -x ibm,max-sync-cop
- *  0000000 0000 0001 0000 1000 0000 01fe 0000 0001
- *  0000020 0000 1000 0000 01fe
- *
- *  In this example, compression supports 0x1000 (4,096) data byte length
- *  and 0x1fe (510) total scatter list elements.  Decompression supports
- *  0x1000 (4,096) data byte length and 0x1f3 (510) total scatter list
- *  elements.
- *
- * @devdata - struct nx842_devdata to update
- * @prop - struct property point containing the maxsyncop for the update
- *
- * Returns:
- *  0 on success
- *  -EINVAL on failure
- */
-static int nx842_OF_upd_maxsyncop(struct nx842_devdata *devdata,
-					struct property *prop) {
-	int ret = 0;
-	const struct maxsynccop_t {
-		int comp_elements;
-		int comp_data_limit;
-		int comp_sg_limit;
-		int decomp_elements;
-		int decomp_data_limit;
-		int decomp_sg_limit;
-	} *maxsynccop;
-
-	if (prop->length != sizeof(*maxsynccop)) {
-		dev_err(devdata->dev, "%s: unexpected format for ibm,max-sync-cop property\n", __func__);
-		dev_dbg(devdata->dev, "%s: ibm,max-sync-cop is %d bytes long, expected %lu bytes\n", __func__, prop->length,
-				sizeof(*maxsynccop));
-		ret = -EINVAL;
-		goto out;
-	}
-
-	maxsynccop = (const struct maxsynccop_t *)prop->value;
-
-	/* Use one limit rather than separate limits for compression and
-	 * decompression. Set a maximum for this so as not to exceed the
-	 * size that the header can support and round the value down to
-	 * the hardware page size (4K) */
-	devdata->max_sync_size =
-			(unsigned int)min(maxsynccop->comp_data_limit,
-					maxsynccop->decomp_data_limit);
-
-	devdata->max_sync_size = min_t(unsigned int, devdata->max_sync_size,
-					SIZE_64K);
-
-	if (devdata->max_sync_size < SIZE_4K) {
-		dev_err(devdata->dev, "%s: hardware max data size (%u) is "
-				"less than the driver minimum, unable to use "
-				"the hardware device\n",
-				__func__, devdata->max_sync_size);
-		ret = -EINVAL;
-		goto out;
-	}
-
-	devdata->max_sync_sg = (unsigned int)min(maxsynccop->comp_sg_limit,
-						maxsynccop->decomp_sg_limit);
-	if (devdata->max_sync_sg < 1) {
-		dev_err(devdata->dev, "%s: hardware max sg size (%u) is "
-				"less than the driver minimum, unable to use "
-				"the hardware device\n",
-				__func__, devdata->max_sync_sg);
-		ret = -EINVAL;
-		goto out;
-	}
-
-out:
-	return ret;
+	return nx842_platform_driver()->decompress(in, ilen, out, olen, wmem);
 }
+EXPORT_SYMBOL_GPL(nx842_decompress);
 
-/**
- *
- * nx842_OF_upd -- Handle OF properties updates for the device.
- *
- * Set all properties from the OF tree.  Optionally, a new property
- * can be provided by the @new_prop pointer to overwrite an existing value.
- * The device will remain disabled until all values are valid, this function
- * will return an error for updates unless all values are valid.
- *
- * @new_prop: If not NULL, this property is being updated.  If NULL, update
- *  all properties from the current values in the OF tree.
- *
- * Returns:
- *  0 - Success
- *  -ENOMEM - Could not allocate memory for new devdata structure
- *  -EINVAL - property value not found, new_prop is not a recognized
- *	property for the device or property value is not valid.
- *  -ENODEV - Device is not available
- */
-static int nx842_OF_upd(struct property *new_prop)
+static __init int nx842_init(void)
 {
-	struct nx842_devdata *old_devdata = NULL;
-	struct nx842_devdata *new_devdata = NULL;
-	struct device_node *of_node = NULL;
-	struct property *status = NULL;
-	struct property *maxsglen = NULL;
-	struct property *maxsyncop = NULL;
-	int ret = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	if (old_devdata)
-		of_node = old_devdata->dev->of_node;
+	request_module("nx-compress-powernv");
+	request_module("nx-compress-pseries");
 
-	if (!old_devdata || !of_node) {
-		pr_err("%s: device is not available\n", __func__);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-		return -ENODEV;
-	}
-
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(old_devdata->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_out;
-	}
-
-	memcpy(new_devdata, old_devdata, sizeof(*old_devdata));
-	new_devdata->counters = old_devdata->counters;
-
-	/* Set ptrs for existing properties */
-	status = of_find_property(of_node, "status", NULL);
-	maxsglen = of_find_property(of_node, "ibm,max-sg-len", NULL);
-	maxsyncop = of_find_property(of_node, "ibm,max-sync-cop", NULL);
-	if (!status || !maxsglen || !maxsyncop) {
-		dev_err(old_devdata->dev, "%s: Could not locate device properties\n", __func__);
-		ret = -EINVAL;
-		goto error_out;
-	}
-
-	/*
-	 * If this is a property update, there are only certain properties that
-	 * we care about. Bail if it isn't in the below list
+	/* we prevent loading if there's no platform driver, and we get the
+	 * module that set it so it won't unload, so we don't need to check
+	 * if it's set in any of the above functions
 	 */
-	if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) ||
-		         strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) ||
-		         strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length)))
-		goto out;
-
-	/* Perform property updates */
-	ret = nx842_OF_upd_status(new_devdata, status);
-	if (ret)
-		goto error_out;
-
-	ret = nx842_OF_upd_maxsglen(new_devdata, maxsglen);
-	if (ret)
-		goto error_out;
-
-	ret = nx842_OF_upd_maxsyncop(new_devdata, maxsyncop);
-	if (ret)
-		goto error_out;
-
-out:
-	dev_info(old_devdata->dev, "%s: max_sync_size new:%u old:%u\n",
-			__func__, new_devdata->max_sync_size,
-			old_devdata->max_sync_size);
-	dev_info(old_devdata->dev, "%s: max_sync_sg new:%u old:%u\n",
-			__func__, new_devdata->max_sync_sg,
-			old_devdata->max_sync_sg);
-	dev_info(old_devdata->dev, "%s: max_sg_len new:%u old:%u\n",
-			__func__, new_devdata->max_sg_len,
-			old_devdata->max_sg_len);
-
-	rcu_assign_pointer(devdata, new_devdata);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	dev_set_drvdata(new_devdata->dev, new_devdata);
-	kfree(old_devdata);
-	return 0;
-
-error_out:
-	if (new_devdata) {
-		dev_info(old_devdata->dev, "%s: device disabled\n", __func__);
-		nx842_OF_set_defaults(new_devdata);
-		rcu_assign_pointer(devdata, new_devdata);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-		synchronize_rcu();
-		dev_set_drvdata(new_devdata->dev, new_devdata);
-		kfree(old_devdata);
-	} else {
-		dev_err(old_devdata->dev, "%s: could not update driver from hardware\n", __func__);
-		spin_unlock_irqrestore(&devdata_mutex, flags);
-	}
-
-	if (!ret)
-		ret = -EINVAL;
-	return ret;
-}
-
-/**
- * nx842_OF_notifier - Process updates to OF properties for the device
- *
- * @np: notifier block
- * @action: notifier action
- * @update: struct pSeries_reconfig_prop_update pointer if action is
- *	PSERIES_UPDATE_PROPERTY
- *
- * Returns:
- *	NOTIFY_OK on success
- *	NOTIFY_BAD encoded with error number on failure, use
- *		notifier_to_errno() to decode this value
- */
-static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
-			     void *data)
-{
-	struct of_reconfig_data *upd = data;
-	struct nx842_devdata *local_devdata;
-	struct device_node *node = NULL;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (local_devdata)
-		node = local_devdata->dev->of_node;
-
-	if (local_devdata &&
-			action == OF_RECONFIG_UPDATE_PROPERTY &&
-			!strcmp(upd->dn->name, node->name)) {
-		rcu_read_unlock();
-		nx842_OF_upd(upd->prop);
-	} else
-		rcu_read_unlock();
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block nx842_of_nb = {
-	.notifier_call = nx842_OF_notifier,
-};
-
-#define nx842_counter_read(_name)					\
-static ssize_t nx842_##_name##_show(struct device *dev,		\
-		struct device_attribute *attr,				\
-		char *buf) {						\
-	struct nx842_devdata *local_devdata;			\
-	int p = 0;							\
-	rcu_read_lock();						\
-	local_devdata = rcu_dereference(devdata);			\
-	if (local_devdata)						\
-		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
-		       atomic64_read(&local_devdata->counters->_name));	\
-	rcu_read_unlock();						\
-	return p;							\
-}
-
-#define NX842DEV_COUNTER_ATTR_RO(_name)					\
-	nx842_counter_read(_name);					\
-	static struct device_attribute dev_attr_##_name = __ATTR(_name,	\
-						0444,			\
-						nx842_##_name##_show,\
-						NULL);
-
-NX842DEV_COUNTER_ATTR_RO(comp_complete);
-NX842DEV_COUNTER_ATTR_RO(comp_failed);
-NX842DEV_COUNTER_ATTR_RO(decomp_complete);
-NX842DEV_COUNTER_ATTR_RO(decomp_failed);
-NX842DEV_COUNTER_ATTR_RO(swdecomp);
-
-static ssize_t nx842_timehist_show(struct device *,
-		struct device_attribute *, char *);
-
-static struct device_attribute dev_attr_comp_times = __ATTR(comp_times, 0444,
-		nx842_timehist_show, NULL);
-static struct device_attribute dev_attr_decomp_times = __ATTR(decomp_times,
-		0444, nx842_timehist_show, NULL);
-
-static ssize_t nx842_timehist_show(struct device *dev,
-		struct device_attribute *attr, char *buf) {
-	char *p = buf;
-	struct nx842_devdata *local_devdata;
-	atomic64_t *times;
-	int bytes_remain = PAGE_SIZE;
-	int bytes;
-	int i;
-
-	rcu_read_lock();
-	local_devdata = rcu_dereference(devdata);
-	if (!local_devdata) {
-		rcu_read_unlock();
-		return 0;
-	}
-
-	if (attr == &dev_attr_comp_times)
-		times = local_devdata->counters->comp_times;
-	else if (attr == &dev_attr_decomp_times)
-		times = local_devdata->counters->decomp_times;
-	else {
-		rcu_read_unlock();
-		return 0;
-	}
-
-	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
-		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
-			       i ? (2<<(i-1)) : 0, (2<<i)-1,
-			       atomic64_read(&times[i]));
-		bytes_remain -= bytes;
-		p += bytes;
-	}
-	/* The last bucket holds everything over
-	 * 2<<(NX842_HIST_SLOTS - 2) us */
-	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
-			2<<(NX842_HIST_SLOTS - 2),
-			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
-	p += bytes;
-
-	rcu_read_unlock();
-	return p - buf;
-}
-
-static struct attribute *nx842_sysfs_entries[] = {
-	&dev_attr_comp_complete.attr,
-	&dev_attr_comp_failed.attr,
-	&dev_attr_decomp_complete.attr,
-	&dev_attr_decomp_failed.attr,
-	&dev_attr_swdecomp.attr,
-	&dev_attr_comp_times.attr,
-	&dev_attr_decomp_times.attr,
-	NULL,
-};
-
-static struct attribute_group nx842_attribute_group = {
-	.name = NULL,		/* put in device directory */
-	.attrs = nx842_sysfs_entries,
-};
-
-static int __init nx842_probe(struct vio_dev *viodev,
-				  const struct vio_device_id *id)
-{
-	struct nx842_devdata *old_devdata, *new_devdata = NULL;
-	unsigned long flags;
-	int ret = 0;
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-
-	if (old_devdata && old_devdata->vdev != NULL) {
-		dev_err(&viodev->dev, "%s: Attempt to register more than one instance of the hardware\n", __func__);
-		ret = -1;
-		goto error_unlock;
-	}
-
-	dev_set_drvdata(&viodev->dev, NULL);
-
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_NOFS);
-	if (!new_devdata) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for device data\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
-	new_devdata->counters = kzalloc(sizeof(*new_devdata->counters),
-			GFP_NOFS);
-	if (!new_devdata->counters) {
-		dev_err(&viodev->dev, "%s: Could not allocate memory for performance counters\n", __func__);
-		ret = -ENOMEM;
-		goto error_unlock;
-	}
-
-	new_devdata->vdev = viodev;
-	new_devdata->dev = &viodev->dev;
-	nx842_OF_set_defaults(new_devdata);
-
-	rcu_assign_pointer(devdata, new_devdata);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	kfree(old_devdata);
-
-	of_reconfig_notifier_register(&nx842_of_nb);
-
-	ret = nx842_OF_upd(NULL);
-	if (ret && ret != -ENODEV) {
-		dev_err(&viodev->dev, "could not parse device tree. %d\n", ret);
-		ret = -1;
-		goto error;
-	}
-
-	rcu_read_lock();
-	dev_set_drvdata(&viodev->dev, rcu_dereference(devdata));
-	rcu_read_unlock();
-
-	if (sysfs_create_group(&viodev->dev.kobj, &nx842_attribute_group)) {
-		dev_err(&viodev->dev, "could not create sysfs device attributes\n");
-		ret = -1;
-		goto error;
+	if (!nx842_platform_driver_get()) {
+		pr_err("no nx842 driver found.\n");
+		return -ENODEV;
 	}
 
 	return 0;
-
-error_unlock:
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	if (new_devdata)
-		kfree(new_devdata->counters);
-	kfree(new_devdata);
-error:
-	return ret;
-}
-
-static int __exit nx842_remove(struct vio_dev *viodev)
-{
-	struct nx842_devdata *old_devdata;
-	unsigned long flags;
-
-	pr_info("Removing IBM Power 842 compression device\n");
-	sysfs_remove_group(&viodev->dev.kobj, &nx842_attribute_group);
-
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	of_reconfig_notifier_unregister(&nx842_of_nb);
-	RCU_INIT_POINTER(devdata, NULL);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	dev_set_drvdata(&viodev->dev, NULL);
-	if (old_devdata)
-		kfree(old_devdata->counters);
-	kfree(old_devdata);
-	return 0;
-}
-
-static struct vio_device_id nx842_driver_ids[] = {
-	{"ibm,compression-v1", "ibm,compression"},
-	{"", ""},
-};
-
-static struct vio_driver nx842_driver = {
-	.name = MODULE_NAME,
-	.probe = nx842_probe,
-	.remove = __exit_p(nx842_remove),
-	.get_desired_dma = nx842_get_desired_dma,
-	.id_table = nx842_driver_ids,
-};
-
-static int __init nx842_init(void)
-{
-	struct nx842_devdata *new_devdata;
-	pr_info("Registering IBM Power 842 compression driver\n");
-
-	RCU_INIT_POINTER(devdata, NULL);
-	new_devdata = kzalloc(sizeof(*new_devdata), GFP_KERNEL);
-	if (!new_devdata) {
-		pr_err("Could not allocate memory for device data\n");
-		return -ENOMEM;
-	}
-	new_devdata->status = UNAVAILABLE;
-	RCU_INIT_POINTER(devdata, new_devdata);
-
-	return vio_register_driver(&nx842_driver);
 }
-
 module_init(nx842_init);
 
 static void __exit nx842_exit(void)
 {
-	struct nx842_devdata *old_devdata;
-	unsigned long flags;
-
-	pr_info("Exiting IBM Power 842 compression driver\n");
-	spin_lock_irqsave(&devdata_mutex, flags);
-	old_devdata = rcu_dereference_check(devdata,
-			lockdep_is_held(&devdata_mutex));
-	RCU_INIT_POINTER(devdata, NULL);
-	spin_unlock_irqrestore(&devdata_mutex, flags);
-	synchronize_rcu();
-	if (old_devdata)
-		dev_set_drvdata(old_devdata->dev, NULL);
-	kfree(old_devdata);
-	vio_unregister_driver(&nx842_driver);
+	nx842_platform_driver_put();
 }
-
 module_exit(nx842_exit);
-
-/*********************************
- * 842 software decompressor
-*********************************/
-typedef int (*sw842_template_op)(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-
-static int sw842_data8(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_data4(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_data2(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr8(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr4(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-static int sw842_ptr2(const char **, int *, unsigned char **,
-						struct sw842_fifo *);
-
-/* special templates */
-#define SW842_TMPL_REPEAT 0x1B
-#define SW842_TMPL_ZEROS 0x1C
-#define SW842_TMPL_EOF 0x1E
-
-static sw842_template_op sw842_tmpl_ops[26][4] = {
-	{ sw842_data8, NULL}, /* 0 (00000) */
-	{ sw842_data4, sw842_data2, sw842_ptr2,  NULL},
-	{ sw842_data4, sw842_ptr2,  sw842_data2, NULL},
-	{ sw842_data4, sw842_ptr2,  sw842_ptr2,  NULL},
-	{ sw842_data4, sw842_ptr4,  NULL},
-	{ sw842_data2, sw842_ptr2,  sw842_data4, NULL},
-	{ sw842_data2, sw842_ptr2,  sw842_data2, sw842_ptr2},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr2,  sw842_data2},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr2,  sw842_ptr2,},
-	{ sw842_data2, sw842_ptr2,  sw842_ptr4,  NULL},
-	{ sw842_ptr2,  sw842_data2, sw842_data4, NULL}, /* 10 (01010) */
-	{ sw842_ptr2,  sw842_data4, sw842_ptr2,  NULL},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr2,  sw842_data2},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr2,  sw842_ptr2},
-	{ sw842_ptr2,  sw842_data2, sw842_ptr4,  NULL},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_data4, NULL},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_data2, sw842_ptr2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr2,  sw842_data2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr2,  sw842_ptr2},
-	{ sw842_ptr2,  sw842_ptr2,  sw842_ptr4,  NULL},
-	{ sw842_ptr4,  sw842_data4, NULL}, /* 20 (10100) */
-	{ sw842_ptr4,  sw842_data2, sw842_ptr2,  NULL},
-	{ sw842_ptr4,  sw842_ptr2,  sw842_data2, NULL},
-	{ sw842_ptr4,  sw842_ptr2,  sw842_ptr2,  NULL},
-	{ sw842_ptr4,  sw842_ptr4,  NULL},
-	{ sw842_ptr8,  NULL}
-};
-
-/* Software decompress helpers */
-
-static uint8_t sw842_get_byte(const char *buf, int bit)
-{
-	uint8_t tmpl;
-	uint16_t tmp;
-	tmp = htons(*(uint16_t *)(buf));
-	tmp = (uint16_t)(tmp << bit);
-	tmp = ntohs(tmp);
-	memcpy(&tmpl, &tmp, 1);
-	return tmpl;
-}
-
-static uint8_t sw842_get_template(const char **buf, int *bit)
-{
-	uint8_t byte;
-	byte = sw842_get_byte(*buf, *bit);
-	byte = byte >> 3;
-	byte &= 0x1F;
-	*buf += (*bit + 5) / 8;
-	*bit = (*bit + 5) % 8;
-	return byte;
-}
-
-/* repeat_count happens to be 5-bit too (like the template) */
-static uint8_t sw842_get_repeat_count(const char **buf, int *bit)
-{
-	uint8_t byte;
-	byte = sw842_get_byte(*buf, *bit);
-	byte = byte >> 2;
-	byte &= 0x3F;
-	*buf += (*bit + 6) / 8;
-	*bit = (*bit + 6) % 8;
-	return byte;
-}
-
-static uint8_t sw842_get_ptr2(const char **buf, int *bit)
-{
-	uint8_t ptr;
-	ptr = sw842_get_byte(*buf, *bit);
-	(*buf)++;
-	return ptr;
-}
-
-static uint16_t sw842_get_ptr4(const char **buf, int *bit,
-		struct sw842_fifo *fifo)
-{
-	uint16_t ptr;
-	ptr = htons(*(uint16_t *)(*buf));
-	ptr = (uint16_t)(ptr << *bit);
-	ptr = ptr >> 7;
-	ptr &= 0x01FF;
-	*buf += (*bit + 9) / 8;
-	*bit = (*bit + 9) % 8;
-	return ptr;
-}
-
-static uint8_t sw842_get_ptr8(const char **buf, int *bit,
-		struct sw842_fifo *fifo)
-{
-	return sw842_get_ptr2(buf, bit);
-}
-
-/* Software decompress template ops */
-
-static int sw842_data8(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	int ret;
-
-	ret = sw842_data4(inbuf, inbit, outbuf, fifo);
-	if (ret)
-		return ret;
-	ret = sw842_data4(inbuf, inbit, outbuf, fifo);
-	return ret;
-}
-
-static int sw842_data4(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	int ret;
-
-	ret = sw842_data2(inbuf, inbit, outbuf, fifo);
-	if (ret)
-		return ret;
-	ret = sw842_data2(inbuf, inbit, outbuf, fifo);
-	return ret;
-}
-
-static int sw842_data2(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	**outbuf = sw842_get_byte(*inbuf, *inbit);
-	(*inbuf)++;
-	(*outbuf)++;
-	**outbuf = sw842_get_byte(*inbuf, *inbit);
-	(*inbuf)++;
-	(*outbuf)++;
-	return 0;
-}
-
-static int sw842_ptr8(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint8_t ptr;
-	ptr = sw842_get_ptr8(inbuf, inbit, fifo);
-	if (!fifo->f84_full && (ptr >= fifo->f8_count))
-		return 1;
-	memcpy(*outbuf, fifo->f8[ptr], 8);
-	*outbuf += 8;
-	return 0;
-}
-
-static int sw842_ptr4(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint16_t ptr;
-	ptr = sw842_get_ptr4(inbuf, inbit, fifo);
-	if (!fifo->f84_full && (ptr >= fifo->f4_count))
-		return 1;
-	memcpy(*outbuf, fifo->f4[ptr], 4);
-	*outbuf += 4;
-	return 0;
-}
-
-static int sw842_ptr2(const char **inbuf, int *inbit,
-		unsigned char **outbuf, struct sw842_fifo *fifo)
-{
-	uint8_t ptr;
-	ptr = sw842_get_ptr2(inbuf, inbit);
-	if (!fifo->f2_full && (ptr >= fifo->f2_count))
-		return 1;
-	memcpy(*outbuf, fifo->f2[ptr], 2);
-	*outbuf += 2;
-	return 0;
-}
-
-static void sw842_copy_to_fifo(const char *buf, struct sw842_fifo *fifo)
-{
-	unsigned char initial_f2count = fifo->f2_count;
-
-	memcpy(fifo->f8[fifo->f8_count], buf, 8);
-	fifo->f4_count += 2;
-	fifo->f8_count += 1;
-
-	if (!fifo->f84_full && fifo->f4_count >= 512) {
-		fifo->f84_full = 1;
-		fifo->f4_count /= 512;
-	}
-
-	memcpy(fifo->f2[fifo->f2_count++], buf, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 2, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 4, 2);
-	memcpy(fifo->f2[fifo->f2_count++], buf + 6, 2);
-	if (fifo->f2_count < initial_f2count)
-		fifo->f2_full = 1;
-}
-
-static int sw842_decompress(const unsigned char *src, int srclen,
-			unsigned char *dst, int *destlen,
-			const void *wrkmem)
-{
-	uint8_t tmpl;
-	const char *inbuf;
-	int inbit = 0;
-	unsigned char *outbuf, *outbuf_end, *origbuf, *prevbuf;
-	const char *inbuf_end;
-	sw842_template_op op;
-	int opindex;
-	int i, repeat_count;
-	struct sw842_fifo *fifo;
-	int ret = 0;
-
-	fifo = &((struct nx842_workmem *)(wrkmem))->swfifo;
-	memset(fifo, 0, sizeof(*fifo));
-
-	origbuf = NULL;
-	inbuf = src;
-	inbuf_end = src + srclen;
-	outbuf = dst;
-	outbuf_end = dst + *destlen;
-
-	while ((tmpl = sw842_get_template(&inbuf, &inbit)) != SW842_TMPL_EOF) {
-		if (inbuf >= inbuf_end) {
-			ret = -EINVAL;
-			goto out;
-		}
-
-		opindex = 0;
-		prevbuf = origbuf;
-		origbuf = outbuf;
-		switch (tmpl) {
-		case SW842_TMPL_REPEAT:
-			if (prevbuf == NULL) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			repeat_count = sw842_get_repeat_count(&inbuf,
-								&inbit) + 1;
-
-			/* Did the repeat count advance past the end of input */
-			if (inbuf > inbuf_end) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			for (i = 0; i < repeat_count; i++) {
-				/* Would this overflow the output buffer */
-				if ((outbuf + 8) > outbuf_end) {
-					ret = -ENOSPC;
-					goto out;
-				}
-
-				memcpy(outbuf, prevbuf, 8);
-				sw842_copy_to_fifo(outbuf, fifo);
-				outbuf += 8;
-			}
-			break;
-
-		case SW842_TMPL_ZEROS:
-			/* Would this overflow the output buffer */
-			if ((outbuf + 8) > outbuf_end) {
-				ret = -ENOSPC;
-				goto out;
-			}
-
-			memset(outbuf, 0, 8);
-			sw842_copy_to_fifo(outbuf, fifo);
-			outbuf += 8;
-			break;
-
-		default:
-			if (tmpl > 25) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			/* Does this go past the end of the input buffer */
-			if ((inbuf + 2) > inbuf_end) {
-				ret = -EINVAL;
-				goto out;
-			}
-
-			/* Would this overflow the output buffer */
-			if ((outbuf + 8) > outbuf_end) {
-				ret = -ENOSPC;
-				goto out;
-			}
-
-			while (opindex < 4 &&
-				(op = sw842_tmpl_ops[tmpl][opindex++])
-					!= NULL) {
-				ret = (*op)(&inbuf, &inbit, &outbuf, fifo);
-				if (ret) {
-					ret = -EINVAL;
-					goto out;
-				}
-				sw842_copy_to_fifo(origbuf, fifo);
-			}
-		}
-	}
-
-out:
-	if (!ret)
-		*destlen = (unsigned int)(outbuf - dst);
-	else
-		*destlen = 0;
-
-	return ret;
-}
diff --git a/drivers/crypto/nx/nx-842.h b/drivers/crypto/nx/nx-842.h
new file mode 100644
index 000000000000..ac0ea79d0f8b
--- /dev/null
+++ b/drivers/crypto/nx/nx-842.h
@@ -0,0 +1,144 @@
+
+#ifndef __NX_842_H__
+#define __NX_842_H__
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sw842.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/ratelimit.h>
+
+/* Restrictions on Data Descriptor List (DDL) and Entry (DDE) buffers
+ *
+ * From NX P8 workbook, sec 4.9.1 "842 details"
+ *   Each DDE buffer is 128 byte aligned
+ *   Each DDE buffer size is a multiple of 32 bytes (except the last)
+ *   The last DDE buffer size is a multiple of 8 bytes
+ */
+#define DDE_BUFFER_ALIGN	(128)
+#define DDE_BUFFER_SIZE_MULT	(32)
+#define DDE_BUFFER_LAST_MULT	(8)
+
+/* Arbitrary DDL length limit
+ * Allows max buffer size of MAX-1 to MAX pages
+ * (depending on alignment)
+ */
+#define DDL_LEN_MAX		(17)
+
+/* CCW 842 CI/FC masks
+ * NX P8 workbook, section 4.3.1, figure 4-6
+ * "CI/FC Boundary by NX CT type"
+ */
+#define CCW_CI_842		(0x00003ff8)
+#define CCW_FC_842		(0x00000007)
+
+/* CCW Function Codes (FC) for 842
+ * NX P8 workbook, section 4.9, table 4-28
+ * "Function Code Definitions for 842 Memory Compression"
+ */
+#define CCW_FC_842_COMP_NOCRC	(0)
+#define CCW_FC_842_COMP_CRC	(1)
+#define CCW_FC_842_DECOMP_NOCRC	(2)
+#define CCW_FC_842_DECOMP_CRC	(3)
+#define CCW_FC_842_MOVE		(4)
+
+/* CSB CC Error Types for 842
+ * NX P8 workbook, section 4.10.3, table 4-30
+ * "Reported Error Types Summary Table"
+ */
+/* These are all duplicates of existing codes defined in icswx.h. */
+#define CSB_CC_TRANSLATION_DUP1	(80)
+#define CSB_CC_TRANSLATION_DUP2	(82)
+#define CSB_CC_TRANSLATION_DUP3	(84)
+#define CSB_CC_TRANSLATION_DUP4	(86)
+#define CSB_CC_TRANSLATION_DUP5	(92)
+#define CSB_CC_TRANSLATION_DUP6	(94)
+#define CSB_CC_PROTECTION_DUP1	(81)
+#define CSB_CC_PROTECTION_DUP2	(83)
+#define CSB_CC_PROTECTION_DUP3	(85)
+#define CSB_CC_PROTECTION_DUP4	(87)
+#define CSB_CC_PROTECTION_DUP5	(93)
+#define CSB_CC_PROTECTION_DUP6	(95)
+#define CSB_CC_RD_EXTERNAL_DUP1	(89)
+#define CSB_CC_RD_EXTERNAL_DUP2	(90)
+#define CSB_CC_RD_EXTERNAL_DUP3	(91)
+/* These are specific to NX */
+/* 842 codes */
+#define CSB_CC_TPBC_GT_SPBC	(64) /* no error, but >1 comp ratio */
+#define CSB_CC_CRC_MISMATCH	(65) /* decomp crc mismatch */
+#define CSB_CC_TEMPL_INVALID	(66) /* decomp invalid template value */
+#define CSB_CC_TEMPL_OVERFLOW	(67) /* decomp template shows data after end */
+/* sym crypt codes */
+#define CSB_CC_DECRYPT_OVERFLOW	(64)
+/* asym crypt codes */
+#define CSB_CC_MINV_OVERFLOW	(128)
+/* These are reserved for hypervisor use */
+#define CSB_CC_HYP_RESERVE_START	(240)
+#define CSB_CC_HYP_RESERVE_END		(253)
+#define CSB_CC_HYP_NO_HW		(254)
+#define CSB_CC_HYP_HANG_ABORTED		(255)
+
+/* CCB Completion Modes (CM) for 842
+ * NX P8 workbook, section 4.3, figure 4-5
+ * "CRB Details - Normal Cop_Req (CL=00, C=1)"
+ */
+#define CCB_CM_EXTRA_WRITE	(CCB_CM0_ALL_COMPLETIONS & CCB_CM12_STORE)
+#define CCB_CM_INTERRUPT	(CCB_CM0_ALL_COMPLETIONS & CCB_CM12_INTERRUPT)
+
+#define LEN_ON_SIZE(pa, size)	((size) - ((pa) & ((size) - 1)))
+#define LEN_ON_PAGE(pa)		LEN_ON_SIZE(pa, PAGE_SIZE)
+
+static inline unsigned long nx842_get_pa(void *addr)
+{
+	if (!is_vmalloc_addr(addr))
+		return __pa(addr);
+
+	return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr);
+}
+
+/* Get/Set bit fields */
+#define MASK_LSH(m)		(__builtin_ffsl(m) - 1)
+#define GET_FIELD(v, m)		(((v) & (m)) >> MASK_LSH(m))
+#define SET_FIELD(v, m, val)	(((v) & ~(m)) | (((val) << MASK_LSH(m)) & (m)))
+
+struct nx842_constraints {
+	int alignment;
+	int multiple;
+	int minimum;
+	int maximum;
+};
+
+struct nx842_driver {
+	char *name;
+	struct module *owner;
+	size_t workmem_size;
+
+	struct nx842_constraints *constraints;
+
+	int (*compress)(const unsigned char *in, unsigned int in_len,
+			unsigned char *out, unsigned int *out_len,
+			void *wrkmem);
+	int (*decompress)(const unsigned char *in, unsigned int in_len,
+			  unsigned char *out, unsigned int *out_len,
+			  void *wrkmem);
+};
+
+struct nx842_driver *nx842_platform_driver(void);
+bool nx842_platform_driver_set(struct nx842_driver *driver);
+void nx842_platform_driver_unset(struct nx842_driver *driver);
+bool nx842_platform_driver_get(void);
+void nx842_platform_driver_put(void);
+
+size_t nx842_workmem_size(void);
+
+int nx842_constraints(struct nx842_constraints *constraints);
+
+int nx842_compress(const unsigned char *in, unsigned int in_len,
+		   unsigned char *out, unsigned int *out_len, void *wrkmem);
+int nx842_decompress(const unsigned char *in, unsigned int in_len,
+		     unsigned char *out, unsigned int *out_len, void *wrkmem);
+
+#endif /* __NX_842_H__ */
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 88c562434bc0..08ac6d48688c 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -93,17 +93,6 @@ out:
 	return rc;
 }
 
-static int gcm_aes_nx_setauthsize(struct crypto_aead *tfm,
-				  unsigned int authsize)
-{
-	if (authsize > crypto_aead_alg(tfm)->maxauthsize)
-		return -EINVAL;
-
-	crypto_aead_crt(tfm)->authsize = authsize;
-
-	return 0;
-}
-
 static int gcm4106_aes_nx_setauthsize(struct crypto_aead *tfm,
 				      unsigned int authsize)
 {
@@ -116,8 +105,6 @@ static int gcm4106_aes_nx_setauthsize(struct crypto_aead *tfm,
 		return -EINVAL;
 	}
 
-	crypto_aead_crt(tfm)->authsize = authsize;
-
 	return 0;
 }
 
@@ -134,7 +121,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 	unsigned int max_sg_len;
 
 	if (nbytes <= AES_BLOCK_SIZE) {
-		scatterwalk_start(&walk, req->assoc);
+		scatterwalk_start(&walk, req->src);
 		scatterwalk_copychunks(out, &walk, nbytes, SCATTERWALK_FROM_SG);
 		scatterwalk_done(&walk, SCATTERWALK_FROM_SG, 0);
 		return 0;
@@ -159,7 +146,7 @@ static int nx_gca(struct nx_crypto_ctx  *nx_ctx,
 				   NX_PAGE_SIZE * (max_sg_len - 1));
 
 		nx_sg = nx_walk_and_build(nx_ctx->in_sg, max_sg_len,
-					  req->assoc, processed, &to_process);
+					  req->src, processed, &to_process);
 
 		if ((to_process + processed) < nbytes)
 			NX_CPB_FDM(csbcpb_aead) |= NX_FDM_INTERMEDIATE;
@@ -225,7 +212,7 @@ static int gmac(struct aead_request *req, struct blkcipher_desc *desc)
 				   NX_PAGE_SIZE * (max_sg_len - 1));
 
 		nx_sg = nx_walk_and_build(nx_ctx->in_sg, max_sg_len,
-					  req->assoc, processed, &to_process);
+					  req->src, processed, &to_process);
 
 		if ((to_process + processed) < nbytes)
 			NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
@@ -377,7 +364,8 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 		csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
 		desc.tfm = (struct crypto_blkcipher *) req->base.tfm;
 		rc = nx_build_sg_lists(nx_ctx, &desc, req->dst,
-				       req->src, &to_process, processed,
+				       req->src, &to_process,
+				       processed + req->assoclen,
 				       csbcpb->cpb.aes_gcm.iv_or_cnt);
 
 		if (rc)
@@ -412,17 +400,19 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 mac:
 	if (enc) {
 		/* copy out the auth tag */
-		scatterwalk_map_and_copy(csbcpb->cpb.aes_gcm.out_pat_or_mac,
-				 req->dst, nbytes,
-				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
-				 SCATTERWALK_TO_SG);
+		scatterwalk_map_and_copy(
+			csbcpb->cpb.aes_gcm.out_pat_or_mac,
+			req->dst, req->assoclen + nbytes,
+			crypto_aead_authsize(crypto_aead_reqtfm(req)),
+			SCATTERWALK_TO_SG);
 	} else {
 		u8 *itag = nx_ctx->priv.gcm.iauth_tag;
 		u8 *otag = csbcpb->cpb.aes_gcm.out_pat_or_mac;
 
-		scatterwalk_map_and_copy(itag, req->src, nbytes,
-				 crypto_aead_authsize(crypto_aead_reqtfm(req)),
-				 SCATTERWALK_FROM_SG);
+		scatterwalk_map_and_copy(
+			itag, req->src, req->assoclen + nbytes,
+			crypto_aead_authsize(crypto_aead_reqtfm(req)),
+			SCATTERWALK_FROM_SG);
 		rc = memcmp(itag, otag,
 			    crypto_aead_authsize(crypto_aead_reqtfm(req))) ?
 		     -EBADMSG : 0;
@@ -481,45 +471,39 @@ static int gcm4106_aes_nx_decrypt(struct aead_request *req)
  * during encrypt/decrypt doesn't solve this problem, because it calls
  * blkcipher_walk_done under the covers, which doesn't use walk->blocksize,
  * but instead uses this tfm->blocksize. */
-struct crypto_alg nx_gcm_aes_alg = {
-	.cra_name        = "gcm(aes)",
-	.cra_driver_name = "gcm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_aead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_gcm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = AES_BLOCK_SIZE,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.setkey      = gcm_aes_nx_set_key,
-		.setauthsize = gcm_aes_nx_setauthsize,
-		.encrypt     = gcm_aes_nx_encrypt,
-		.decrypt     = gcm_aes_nx_decrypt,
-	}
+struct aead_alg nx_gcm_aes_alg = {
+	.base = {
+		.cra_name        = "gcm(aes)",
+		.cra_driver_name = "gcm-aes-nx",
+		.cra_priority    = 300,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_gcm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = 12,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = gcm_aes_nx_set_key,
+	.encrypt     = gcm_aes_nx_encrypt,
+	.decrypt     = gcm_aes_nx_decrypt,
 };
 
-struct crypto_alg nx_gcm4106_aes_alg = {
-	.cra_name        = "rfc4106(gcm(aes))",
-	.cra_driver_name = "rfc4106-gcm-aes-nx",
-	.cra_priority    = 300,
-	.cra_flags       = CRYPTO_ALG_TYPE_AEAD,
-	.cra_blocksize   = 1,
-	.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-	.cra_type        = &crypto_nivaead_type,
-	.cra_module      = THIS_MODULE,
-	.cra_init        = nx_crypto_ctx_aes_gcm_init,
-	.cra_exit        = nx_crypto_ctx_exit,
-	.cra_aead = {
-		.ivsize      = 8,
-		.maxauthsize = AES_BLOCK_SIZE,
-		.geniv       = "seqiv",
-		.setkey      = gcm4106_aes_nx_set_key,
-		.setauthsize = gcm4106_aes_nx_setauthsize,
-		.encrypt     = gcm4106_aes_nx_encrypt,
-		.decrypt     = gcm4106_aes_nx_decrypt,
-	}
+struct aead_alg nx_gcm4106_aes_alg = {
+	.base = {
+		.cra_name        = "rfc4106(gcm(aes))",
+		.cra_driver_name = "rfc4106-gcm-aes-nx",
+		.cra_priority    = 300,
+		.cra_blocksize   = 1,
+		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
+		.cra_module      = THIS_MODULE,
+	},
+	.init        = nx_crypto_ctx_aes_gcm_init,
+	.exit        = nx_crypto_ctx_aead_exit,
+	.ivsize      = 8,
+	.maxauthsize = AES_BLOCK_SIZE,
+	.setkey      = gcm4106_aes_nx_set_key,
+	.setauthsize = gcm4106_aes_nx_setauthsize,
+	.encrypt     = gcm4106_aes_nx_encrypt,
+	.decrypt     = gcm4106_aes_nx_decrypt,
 };
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 23621da624c3..4e91bdb83c59 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -33,8 +33,9 @@ static int nx_sha256_init(struct shash_desc *desc)
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_sg *out_sg;
 	int len;
-	int rc;
+	u32 max_sg_len;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
@@ -44,15 +45,18 @@ static int nx_sha256_init(struct shash_desc *desc)
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	len = SHA256_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  (u8 *) sctx->state,
-				  NX_DS_SHA256);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	if (rc)
-		goto out;
+	if (len != SHA256_DIGEST_SIZE)
+		return -EINVAL;
 
 	sctx->state[0] = __cpu_to_be32(SHA256_H0);
 	sctx->state[1] = __cpu_to_be32(SHA256_H1);
@@ -64,7 +68,6 @@ static int nx_sha256_init(struct shash_desc *desc)
 	sctx->state[7] = __cpu_to_be32(SHA256_H7);
 	sctx->count = 0;
 
-out:
 	return 0;
 }
 
@@ -74,10 +77,12 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg;
 	u64 to_process = 0, leftover, total;
 	unsigned long irq_flags;
 	int rc = 0;
 	int data_len;
+	u32 max_sg_len;
 	u64 buf_len = (sctx->count % SHA256_BLOCK_SIZE);
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
@@ -97,6 +102,12 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	do {
 		/*
 		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
@@ -108,25 +119,22 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 
 		if (buf_len) {
 			data_len = buf_len;
-			rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-						  &nx_ctx->op.inlen,
-						  &data_len,
-						  (u8 *) sctx->buf,
-						  NX_DS_SHA256);
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 &data_len,
+						 max_sg_len);
 
-			if (rc || data_len != buf_len)
+			if (data_len != buf_len) {
+				rc = -EINVAL;
 				goto out;
+			}
 		}
 
 		data_len = to_process - buf_len;
-		rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-					  &nx_ctx->op.inlen,
-					  &data_len,
-					  (u8 *) data,
-					  NX_DS_SHA256);
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
+					 &data_len, max_sg_len);
 
-		if (rc)
-			goto out;
+		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 
 		to_process = (data_len + buf_len);
 		leftover = total - to_process;
@@ -173,12 +181,19 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg, *out_sg;
 	unsigned long irq_flags;
-	int rc;
+	u32 max_sg_len;
+	int rc = 0;
 	int len;
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	/* final is represented by continuing the operation and indicating that
 	 * this is not an intermediate operation */
 	if (sctx->count >= SHA256_BLOCK_SIZE) {
@@ -195,25 +210,24 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 	csbcpb->cpb.sha256.message_bit_length = (u64) (sctx->count * 8);
 
 	len = sctx->count & (SHA256_BLOCK_SIZE - 1);
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-				  &nx_ctx->op.inlen,
-				  &len,
-				  (u8 *) sctx->buf,
-				  NX_DS_SHA256);
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *) sctx->buf,
+				 &len, max_sg_len);
 
-	if (rc || len != (sctx->count & (SHA256_BLOCK_SIZE - 1)))
+	if (len != (sctx->count & (SHA256_BLOCK_SIZE - 1))) {
+		rc = -EINVAL;
 		goto out;
+	}
 
 	len = SHA256_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  out,
-				  NX_DS_SHA256);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len, max_sg_len);
 
-	if (rc || len != SHA256_DIGEST_SIZE)
+	if (len != SHA256_DIGEST_SIZE) {
+		rc = -EINVAL;
 		goto out;
+	}
 
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 	if (!nx_ctx->op.outlen) {
 		rc = -EINVAL;
 		goto out;
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index b3adf1022673..e6a58d2ee628 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -32,8 +32,9 @@ static int nx_sha512_init(struct shash_desc *desc)
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_sg *out_sg;
 	int len;
-	int rc;
+	u32 max_sg_len;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
@@ -43,15 +44,18 @@ static int nx_sha512_init(struct shash_desc *desc)
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA512);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	len = SHA512_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  (u8 *)sctx->state,
-				  NX_DS_SHA512);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	if (rc || len != SHA512_DIGEST_SIZE)
-		goto out;
+	if (len != SHA512_DIGEST_SIZE)
+		return -EINVAL;
 
 	sctx->state[0] = __cpu_to_be64(SHA512_H0);
 	sctx->state[1] = __cpu_to_be64(SHA512_H1);
@@ -63,7 +67,6 @@ static int nx_sha512_init(struct shash_desc *desc)
 	sctx->state[7] = __cpu_to_be64(SHA512_H7);
 	sctx->count[0] = 0;
 
-out:
 	return 0;
 }
 
@@ -73,10 +76,12 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg;
 	u64 to_process, leftover = 0, total;
 	unsigned long irq_flags;
 	int rc = 0;
 	int data_len;
+	u32 max_sg_len;
 	u64 buf_len = (sctx->count[0] % SHA512_BLOCK_SIZE);
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
@@ -96,6 +101,12 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
+	in_sg = nx_ctx->in_sg;
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	do {
 		/*
 		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
@@ -108,25 +119,26 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 
 		if (buf_len) {
 			data_len = buf_len;
-			rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-						  &nx_ctx->op.inlen,
-						  &data_len,
-						  (u8 *) sctx->buf,
-						  NX_DS_SHA512);
+			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+						 (u8 *) sctx->buf,
+						 &data_len, max_sg_len);
 
-			if (rc || data_len != buf_len)
+			if (data_len != buf_len) {
+				rc = -EINVAL;
 				goto out;
+			}
 		}
 
 		data_len = to_process - buf_len;
-		rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-					  &nx_ctx->op.inlen,
-					  &data_len,
-					  (u8 *) data,
-					  NX_DS_SHA512);
+		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
+					 &data_len, max_sg_len);
 
-		if (rc || data_len != (to_process - buf_len))
+		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+
+		if (data_len != (to_process - buf_len)) {
+			rc = -EINVAL;
 			goto out;
+		}
 
 		to_process = (data_len + buf_len);
 		leftover = total - to_process;
@@ -172,13 +184,20 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
+	struct nx_sg *in_sg, *out_sg;
+	u32 max_sg_len;
 	u64 count0;
 	unsigned long irq_flags;
-	int rc;
+	int rc = 0;
 	int len;
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
+	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
+			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
+	max_sg_len = min_t(u64, max_sg_len,
+			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+
 	/* final is represented by continuing the operation and indicating that
 	 * this is not an intermediate operation */
 	if (sctx->count[0] >= SHA512_BLOCK_SIZE) {
@@ -200,24 +219,20 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 	csbcpb->cpb.sha512.message_bit_length_lo = count0;
 
 	len = sctx->count[0] & (SHA512_BLOCK_SIZE - 1);
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->in_sg,
-				  &nx_ctx->op.inlen,
-				  &len,
-				  (u8 *)sctx->buf,
-				  NX_DS_SHA512);
+	in_sg = nx_build_sg_list(nx_ctx->in_sg, sctx->buf, &len,
+				 max_sg_len);
 
-	if (rc || len != (sctx->count[0] & (SHA512_BLOCK_SIZE - 1)))
+	if (len != (sctx->count[0] & (SHA512_BLOCK_SIZE - 1))) {
+		rc = -EINVAL;
 		goto out;
+	}
 
 	len = SHA512_DIGEST_SIZE;
-	rc = nx_sha_build_sg_list(nx_ctx, nx_ctx->out_sg,
-				  &nx_ctx->op.outlen,
-				  &len,
-				  out,
-				  NX_DS_SHA512);
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len,
+				 max_sg_len);
 
-	if (rc)
-		goto out;
+	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
 	if (!nx_ctx->op.outlen) {
 		rc = -EINVAL;
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index 1da6dc59d0dd..f6198f29a4a8 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -19,8 +19,8 @@
  * Author: Kent Yoder <yoder1@us.ibm.com>
  */
 
+#include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
-#include <crypto/hash.h>
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/algapi.h>
@@ -29,10 +29,10 @@
 #include <linux/moduleparam.h>
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <linux/device.h>
 #include <linux/of.h>
+#include <linux/types.h>
 #include <asm/hvcall.h>
 #include <asm/vio.h>
 
@@ -215,8 +215,15 @@ struct nx_sg *nx_walk_and_build(struct nx_sg       *nx_dst,
  * @delta:  is the amount we need to crop in order to bound the list.
  *
  */
-static long int trim_sg_list(struct nx_sg *sg, struct nx_sg *end, unsigned int delta)
+static long int trim_sg_list(struct nx_sg *sg,
+			     struct nx_sg *end,
+			     unsigned int delta,
+			     unsigned int *nbytes)
 {
+	long int oplen;
+	long int data_back;
+	unsigned int is_delta = delta;
+
 	while (delta && end > sg) {
 		struct nx_sg *last = end - 1;
 
@@ -228,54 +235,20 @@ static long int trim_sg_list(struct nx_sg *sg, struct nx_sg *end, unsigned int d
 			delta -= last->len;
 		}
 	}
-	return (sg - end) * sizeof(struct nx_sg);
-}
 
-/**
- * nx_sha_build_sg_list - walk and build sg list to sha modes
- *			  using right bounds and limits.
- * @nx_ctx: NX crypto context for the lists we're building
- * @nx_sg: current sg list in or out list
- * @op_len: current op_len to be used in order to build a sg list
- * @nbytes:  number or bytes to be processed
- * @offset: buf offset
- * @mode: SHA256 or SHA512
- */
-int nx_sha_build_sg_list(struct nx_crypto_ctx *nx_ctx,
-			  struct nx_sg 	      *nx_in_outsg,
-			  s64		      *op_len,
-			  unsigned int        *nbytes,
-			  u8 		      *offset,
-			  u32		      mode)
-{
-	unsigned int delta = 0;
-	unsigned int total = *nbytes;
-	struct nx_sg *nx_insg = nx_in_outsg;
-	unsigned int max_sg_len;
-
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
-
-	*nbytes = min_t(u64, *nbytes, nx_ctx->ap->databytelen);
-	nx_insg = nx_build_sg_list(nx_insg, offset, nbytes, max_sg_len);
-
-	switch (mode) {
-	case NX_DS_SHA256:
-		if (*nbytes < total)
-			delta = *nbytes - (*nbytes & ~(SHA256_BLOCK_SIZE - 1));
-		break;
-	case NX_DS_SHA512:
-		if (*nbytes < total)
-			delta = *nbytes - (*nbytes & ~(SHA512_BLOCK_SIZE - 1));
-		break;
-	default:
-		return -EINVAL;
+	/* There are cases where we need to crop list in order to make it
+	 * a block size multiple, but we also need to align data. In order to
+	 * that we need to calculate how much we need to put back to be
+	 * processed
+	 */
+	oplen = (sg - end) * sizeof(struct nx_sg);
+	if (is_delta) {
+		data_back = (abs(oplen) / AES_BLOCK_SIZE) *  sg->len;
+		data_back = *nbytes - (data_back & ~(AES_BLOCK_SIZE - 1));
+		*nbytes -= data_back;
 	}
-	*op_len = trim_sg_list(nx_in_outsg, nx_insg, delta);
 
-	return 0;
+	return oplen;
 }
 
 /**
@@ -330,8 +303,8 @@ int nx_build_sg_lists(struct nx_crypto_ctx  *nx_ctx,
 	/* these lengths should be negative, which will indicate to phyp that
 	 * the input and output parameters are scatterlists, not linear
 	 * buffers */
-	nx_ctx->op.inlen = trim_sg_list(nx_ctx->in_sg, nx_insg, delta);
-	nx_ctx->op.outlen = trim_sg_list(nx_ctx->out_sg, nx_outsg, delta);
+	nx_ctx->op.inlen = trim_sg_list(nx_ctx->in_sg, nx_insg, delta, nbytes);
+	nx_ctx->op.outlen = trim_sg_list(nx_ctx->out_sg, nx_outsg, delta, nbytes);
 
 	return 0;
 }
@@ -426,6 +399,13 @@ static void nx_of_update_msc(struct device   *dev,
 				goto next_loop;
 			}
 
+			if (!trip->sglen || trip->databytelen < NX_PAGE_SIZE) {
+				dev_warn(dev, "bogus sglen/databytelen: "
+					 "%u/%u (ignored)\n", trip->sglen,
+					 trip->databytelen);
+				goto next_loop;
+			}
+
 			switch (trip->keybitlen) {
 			case 128:
 			case 160:
@@ -518,6 +498,72 @@ static void nx_of_init(struct device *dev, struct nx_of *props)
 		nx_of_update_msc(dev, p, props);
 }
 
+static bool nx_check_prop(struct device *dev, u32 fc, u32 mode, int slot)
+{
+	struct alg_props *props = &nx_driver.of.ap[fc][mode][slot];
+
+	if (!props->sglen || props->databytelen < NX_PAGE_SIZE) {
+		if (dev)
+			dev_warn(dev, "bogus sglen/databytelen for %u/%u/%u: "
+				 "%u/%u (ignored)\n", fc, mode, slot,
+				 props->sglen, props->databytelen);
+		return false;
+	}
+
+	return true;
+}
+
+static bool nx_check_props(struct device *dev, u32 fc, u32 mode)
+{
+	int i;
+
+	for (i = 0; i < 3; i++)
+		if (!nx_check_prop(dev, fc, mode, i))
+			return false;
+
+	return true;
+}
+
+static int nx_register_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+{
+	return nx_check_props(&nx_driver.viodev->dev, fc, mode) ?
+	       crypto_register_alg(alg) : 0;
+}
+
+static int nx_register_aead(struct aead_alg *alg, u32 fc, u32 mode)
+{
+	return nx_check_props(&nx_driver.viodev->dev, fc, mode) ?
+	       crypto_register_aead(alg) : 0;
+}
+
+static int nx_register_shash(struct shash_alg *alg, u32 fc, u32 mode, int slot)
+{
+	return (slot >= 0 ? nx_check_prop(&nx_driver.viodev->dev,
+					  fc, mode, slot) :
+			    nx_check_props(&nx_driver.viodev->dev, fc, mode)) ?
+	       crypto_register_shash(alg) : 0;
+}
+
+static void nx_unregister_alg(struct crypto_alg *alg, u32 fc, u32 mode)
+{
+	if (nx_check_props(NULL, fc, mode))
+		crypto_unregister_alg(alg);
+}
+
+static void nx_unregister_aead(struct aead_alg *alg, u32 fc, u32 mode)
+{
+	if (nx_check_props(NULL, fc, mode))
+		crypto_unregister_aead(alg);
+}
+
+static void nx_unregister_shash(struct shash_alg *alg, u32 fc, u32 mode,
+				int slot)
+{
+	if (slot >= 0 ? nx_check_prop(NULL, fc, mode, slot) :
+			nx_check_props(NULL, fc, mode))
+		crypto_unregister_shash(alg);
+}
+
 /**
  * nx_register_algs - register algorithms with the crypto API
  *
@@ -542,72 +588,77 @@ static int nx_register_algs(void)
 
 	nx_driver.of.status = NX_OKAY;
 
-	rc = crypto_register_alg(&nx_ecb_aes_alg);
+	rc = nx_register_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	if (rc)
 		goto out;
 
-	rc = crypto_register_alg(&nx_cbc_aes_alg);
+	rc = nx_register_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 	if (rc)
 		goto out_unreg_ecb;
 
-	rc = crypto_register_alg(&nx_ctr_aes_alg);
+	rc = nx_register_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 	if (rc)
 		goto out_unreg_cbc;
 
-	rc = crypto_register_alg(&nx_ctr3686_aes_alg);
+	rc = nx_register_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 	if (rc)
 		goto out_unreg_ctr;
 
-	rc = crypto_register_alg(&nx_gcm_aes_alg);
+	rc = nx_register_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 	if (rc)
 		goto out_unreg_ctr3686;
 
-	rc = crypto_register_alg(&nx_gcm4106_aes_alg);
+	rc = nx_register_aead(&nx_gcm4106_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 	if (rc)
 		goto out_unreg_gcm;
 
-	rc = crypto_register_alg(&nx_ccm_aes_alg);
+	rc = nx_register_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_gcm4106;
 
-	rc = crypto_register_alg(&nx_ccm4309_aes_alg);
+	rc = nx_register_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 	if (rc)
 		goto out_unreg_ccm;
 
-	rc = crypto_register_shash(&nx_shash_sha256_alg);
+	rc = nx_register_shash(&nx_shash_sha256_alg, NX_FC_SHA, NX_MODE_SHA,
+			       NX_PROPS_SHA256);
 	if (rc)
 		goto out_unreg_ccm4309;
 
-	rc = crypto_register_shash(&nx_shash_sha512_alg);
+	rc = nx_register_shash(&nx_shash_sha512_alg, NX_FC_SHA, NX_MODE_SHA,
+			       NX_PROPS_SHA512);
 	if (rc)
 		goto out_unreg_s256;
 
-	rc = crypto_register_shash(&nx_shash_aes_xcbc_alg);
+	rc = nx_register_shash(&nx_shash_aes_xcbc_alg,
+			       NX_FC_AES, NX_MODE_AES_XCBC_MAC, -1);
 	if (rc)
 		goto out_unreg_s512;
 
 	goto out;
 
 out_unreg_s512:
-	crypto_unregister_shash(&nx_shash_sha512_alg);
+	nx_unregister_shash(&nx_shash_sha512_alg, NX_FC_SHA, NX_MODE_SHA,
+			    NX_PROPS_SHA512);
 out_unreg_s256:
-	crypto_unregister_shash(&nx_shash_sha256_alg);
+	nx_unregister_shash(&nx_shash_sha256_alg, NX_FC_SHA, NX_MODE_SHA,
+			    NX_PROPS_SHA256);
 out_unreg_ccm4309:
-	crypto_unregister_alg(&nx_ccm4309_aes_alg);
+	nx_unregister_alg(&nx_ccm4309_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_ccm:
-	crypto_unregister_alg(&nx_ccm_aes_alg);
+	nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
 out_unreg_gcm4106:
-	crypto_unregister_alg(&nx_gcm4106_aes_alg);
+	nx_unregister_aead(&nx_gcm4106_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_gcm:
-	crypto_unregister_alg(&nx_gcm_aes_alg);
+	nx_unregister_aead(&nx_gcm_aes_alg, NX_FC_AES, NX_MODE_AES_GCM);
 out_unreg_ctr3686:
-	crypto_unregister_alg(&nx_ctr3686_aes_alg);
+	nx_unregister_alg(&nx_ctr3686_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_ctr:
-	crypto_unregister_alg(&nx_ctr_aes_alg);
+	nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
 out_unreg_cbc:
-	crypto_unregister_alg(&nx_cbc_aes_alg);
+	nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
 out_unreg_ecb:
-	crypto_unregister_alg(&nx_ecb_aes_alg);
+	nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 out:
 	return rc;
 }
@@ -666,9 +717,9 @@ int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm)
 				  NX_MODE_AES_CCM);
 }
 
-int nx_crypto_ctx_aes_gcm_init(struct crypto_tfm *tfm)
+int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 {
-	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
+	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_GCM);
 }
 
@@ -720,6 +771,13 @@ void nx_crypto_ctx_exit(struct crypto_tfm *tfm)
 	nx_ctx->out_sg = NULL;
 }
 
+void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm)
+{
+	struct nx_crypto_ctx *nx_ctx = crypto_aead_ctx(tfm);
+
+	kzfree(nx_ctx->kmem);
+}
+
 static int nx_probe(struct vio_dev *viodev, const struct vio_device_id *id)
 {
 	dev_dbg(&viodev->dev, "driver probed: %s resource id: 0x%x\n",
@@ -746,17 +804,24 @@ static int nx_remove(struct vio_dev *viodev)
 	if (nx_driver.of.status == NX_OKAY) {
 		NX_DEBUGFS_FINI(&nx_driver);
 
-		crypto_unregister_alg(&nx_ccm_aes_alg);
-		crypto_unregister_alg(&nx_ccm4309_aes_alg);
-		crypto_unregister_alg(&nx_gcm_aes_alg);
-		crypto_unregister_alg(&nx_gcm4106_aes_alg);
-		crypto_unregister_alg(&nx_ctr_aes_alg);
-		crypto_unregister_alg(&nx_ctr3686_aes_alg);
-		crypto_unregister_alg(&nx_cbc_aes_alg);
-		crypto_unregister_alg(&nx_ecb_aes_alg);
-		crypto_unregister_shash(&nx_shash_sha256_alg);
-		crypto_unregister_shash(&nx_shash_sha512_alg);
-		crypto_unregister_shash(&nx_shash_aes_xcbc_alg);
+		nx_unregister_shash(&nx_shash_aes_xcbc_alg,
+				    NX_FC_AES, NX_MODE_AES_XCBC_MAC, -1);
+		nx_unregister_shash(&nx_shash_sha512_alg,
+				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA256);
+		nx_unregister_shash(&nx_shash_sha256_alg,
+				    NX_FC_SHA, NX_MODE_SHA, NX_PROPS_SHA512);
+		nx_unregister_alg(&nx_ccm4309_aes_alg,
+				  NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_alg(&nx_ccm_aes_alg, NX_FC_AES, NX_MODE_AES_CCM);
+		nx_unregister_aead(&nx_gcm4106_aes_alg,
+				   NX_FC_AES, NX_MODE_AES_GCM);
+		nx_unregister_aead(&nx_gcm_aes_alg,
+				   NX_FC_AES, NX_MODE_AES_GCM);
+		nx_unregister_alg(&nx_ctr3686_aes_alg,
+				  NX_FC_AES, NX_MODE_AES_CTR);
+		nx_unregister_alg(&nx_ctr_aes_alg, NX_FC_AES, NX_MODE_AES_CTR);
+		nx_unregister_alg(&nx_cbc_aes_alg, NX_FC_AES, NX_MODE_AES_CBC);
+		nx_unregister_alg(&nx_ecb_aes_alg, NX_FC_AES, NX_MODE_AES_ECB);
 	}
 
 	return 0;
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index 6c9ecaaead52..de3ea8738146 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -143,18 +143,17 @@ struct nx_crypto_ctx {
 
 /* prototypes */
 int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm);
-int nx_crypto_ctx_aes_gcm_init(struct crypto_tfm *tfm);
+int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm);
 int nx_crypto_ctx_aes_xcbc_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_ctr_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_cbc_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_aes_ecb_init(struct crypto_tfm *tfm);
 int nx_crypto_ctx_sha_init(struct crypto_tfm *tfm);
 void nx_crypto_ctx_exit(struct crypto_tfm *tfm);
+void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm);
 void nx_ctx_init(struct nx_crypto_ctx *nx_ctx, unsigned int function);
 int nx_hcall_sync(struct nx_crypto_ctx *ctx, struct vio_pfo_op *op,
 		  u32 may_sleep);
-int nx_sha_build_sg_list(struct nx_crypto_ctx *, struct nx_sg *,
-			 s64 *, unsigned int *, u8 *, u32);
 struct nx_sg *nx_build_sg_list(struct nx_sg *, u8 *, unsigned int *, u32);
 int nx_build_sg_lists(struct nx_crypto_ctx *, struct blkcipher_desc *,
 		      struct scatterlist *, struct scatterlist *, unsigned int *,
@@ -178,8 +177,8 @@ void nx_debugfs_fini(struct nx_crypto_driver *);
 
 extern struct crypto_alg nx_cbc_aes_alg;
 extern struct crypto_alg nx_ecb_aes_alg;
-extern struct crypto_alg nx_gcm_aes_alg;
-extern struct crypto_alg nx_gcm4106_aes_alg;
+extern struct aead_alg nx_gcm_aes_alg;
+extern struct aead_alg nx_gcm4106_aes_alg;
 extern struct crypto_alg nx_ctr_aes_alg;
 extern struct crypto_alg nx_ctr3686_aes_alg;
 extern struct crypto_alg nx_ccm_aes_alg;
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 4d63e0d4da9a..b2024c95a3cf 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -362,7 +362,13 @@ static void omap_sham_copy_ready_hash(struct ahash_request *req)
 
 static int omap_sham_hw_init(struct omap_sham_dev *dd)
 {
-	pm_runtime_get_sync(dd->dev);
+	int err;
+
+	err = pm_runtime_get_sync(dd->dev);
+	if (err < 0) {
+		dev_err(dd->dev, "failed to get sync: %d\n", err);
+		return err;
+	}
 
 	if (!test_bit(FLAGS_INIT, &dd->flags)) {
 		set_bit(FLAGS_INIT, &dd->flags);
@@ -1793,6 +1799,10 @@ static const struct of_device_id omap_sham_of_match[] = {
 		.data		= &omap_sham_pdata_omap2,
 	},
 	{
+		.compatible	= "ti,omap3-sham",
+		.data		= &omap_sham_pdata_omap2,
+	},
+	{
 		.compatible	= "ti,omap4-sham",
 		.data		= &omap_sham_pdata_omap4,
 	},
@@ -1947,7 +1957,13 @@ static int omap_sham_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 	pm_runtime_irq_safe(dev);
-	pm_runtime_get_sync(dev);
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get sync: %d\n", err);
+		goto err_pm;
+	}
+
 	rev = omap_sham_read(dd, SHA_REG_REV(dd));
 	pm_runtime_put_sync(&pdev->dev);
 
@@ -1977,6 +1993,7 @@ err_algs:
 		for (j = dd->pdata->algs_info[i].registered - 1; j >= 0; j--)
 			crypto_unregister_ahash(
 					&dd->pdata->algs_info[i].algs_list[j]);
+err_pm:
 	pm_runtime_disable(dev);
 	if (dd->dma_lch)
 		dma_release_channel(dd->dma_lch);
@@ -2019,7 +2036,11 @@ static int omap_sham_suspend(struct device *dev)
 
 static int omap_sham_resume(struct device *dev)
 {
-	pm_runtime_get_sync(dev);
+	int err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get sync: %d\n", err);
+		return err;
+	}
 	return 0;
 }
 #endif
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index c178ed8c3908..da2d6777bd09 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -22,7 +22,7 @@
 #include <asm/cpu_device_id.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 /*
  * Number of data blocks actually fetched for each xcrypt insn.
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 95f7d27ce491..4e154c9b9206 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -23,7 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/scatterlist.h>
 #include <asm/cpu_device_id.h>
-#include <asm/i387.h>
+#include <asm/fpu/api.h>
 
 struct padlock_sha_desc {
 	struct shash_desc fallback;
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 5da5b98b8f29..4f56f3681abd 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -15,7 +15,7 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/authenc.h>
@@ -40,6 +40,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
 
@@ -261,18 +262,9 @@ static unsigned spacc_load_ctx(struct spacc_generic_ctx *ctx,
 }
 
 /* Count the number of scatterlist entries in a scatterlist. */
-static int sg_count(struct scatterlist *sg_list, int nbytes)
+static inline int sg_count(struct scatterlist *sg_list, int nbytes)
 {
-	struct scatterlist *sg = sg_list;
-	int sg_nents = 0;
-
-	while (nbytes > 0) {
-		++sg_nents;
-		nbytes -= sg->length;
-		sg = sg_next(sg);
-	}
-
-	return sg_nents;
+	return sg_nents_for_len(sg_list, nbytes);
 }
 
 static inline void ddt_set(struct spacc_ddt *ddt, dma_addr_t phys, size_t len)
@@ -326,6 +318,7 @@ static int spacc_aead_make_ddts(struct spacc_req *req, u8 *giv)
 	struct spacc_ddt *src_ddt, *dst_ddt;
 	unsigned ivsize = crypto_aead_ivsize(crypto_aead_reqtfm(areq));
 	unsigned nents = sg_count(areq->src, areq->cryptlen);
+	unsigned total;
 	dma_addr_t iv_addr;
 	struct scatterlist *cur;
 	int i, dst_ents, src_ents, assoc_ents;
@@ -369,11 +362,18 @@ static int spacc_aead_make_ddts(struct spacc_req *req, u8 *giv)
 	 * Map the associated data. For decryption we don't copy the
 	 * associated data.
 	 */
+	total = areq->assoclen;
 	for_each_sg(areq->assoc, cur, assoc_ents, i) {
-		ddt_set(src_ddt++, sg_dma_address(cur), sg_dma_len(cur));
+		unsigned len = sg_dma_len(cur);
+
+		if (len > total)
+			len = total;
+
+		total -= len;
+
+		ddt_set(src_ddt++, sg_dma_address(cur), len);
 		if (req->is_encrypt)
-			ddt_set(dst_ddt++, sg_dma_address(cur),
-				sg_dma_len(cur));
+			ddt_set(dst_ddt++, sg_dma_address(cur), len);
 	}
 	ddt_set(src_ddt++, iv_addr, ivsize);
 
@@ -790,7 +790,8 @@ static int spacc_aead_cra_init(struct crypto_tfm *tfm)
 
 	get_random_bytes(ctx->salt, sizeof(ctx->salt));
 
-	tfm->crt_aead.reqsize = sizeof(struct spacc_req);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct spacc_req));
 
 	return 0;
 }
@@ -1754,15 +1755,15 @@ static int spacc_probe(struct platform_device *pdev)
 		return PTR_ERR(engine->clk);
 	}
 
-	if (clk_enable(engine->clk)) {
-		dev_info(&pdev->dev, "unable to enable clk\n");
+	if (clk_prepare_enable(engine->clk)) {
+		dev_info(&pdev->dev, "unable to prepare/enable clk\n");
 		clk_put(engine->clk);
 		return -EIO;
 	}
 
 	err = device_create_file(&pdev->dev, &dev_attr_stat_irq_thresh);
 	if (err) {
-		clk_disable(engine->clk);
+		clk_disable_unprepare(engine->clk);
 		clk_put(engine->clk);
 		return err;
 	}
@@ -1830,7 +1831,7 @@ static int spacc_remove(struct platform_device *pdev)
 		crypto_unregister_alg(&alg->alg);
 	}
 
-	clk_disable(engine->clk);
+	clk_disable_unprepare(engine->clk);
 	clk_put(engine->clk);
 
 	return 0;
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
index 49bede2a9f77..6fdb9e8b22a7 100644
--- a/drivers/crypto/qat/Kconfig
+++ b/drivers/crypto/qat/Kconfig
@@ -2,9 +2,8 @@ config CRYPTO_DEV_QAT
 	tristate
 	select CRYPTO_AEAD
 	select CRYPTO_AUTHENC
-	select CRYPTO_ALGAPI
-	select CRYPTO_AES
-	select CRYPTO_CBC
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
@@ -13,7 +12,6 @@ config CRYPTO_DEV_QAT
 config CRYPTO_DEV_QAT_DH895xCC
 	tristate "Support for Intel(R) DH895xCC"
 	depends on X86 && PCI
-	default n
 	select CRYPTO_DEV_QAT
 	help
 	  Support for Intel(R) DH895xcc with Intel(R) QuickAssist Technology
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index f22ce7169fa5..5fe902967620 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -48,7 +48,6 @@
 #define ADF_ACCEL_DEVICES_H_
 #include <linux/module.h>
 #include <linux/list.h>
-#include <linux/proc_fs.h>
 #include <linux/io.h>
 #include "adf_cfg_common.h"
 
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/qat/qat_common/adf_cfg_user.h
index 0c38a155a865..ef5988afd4c6 100644
--- a/drivers/crypto/qat/qat_common/adf_cfg_user.h
+++ b/drivers/crypto/qat/qat_common/adf_cfg_user.h
@@ -54,14 +54,6 @@ struct adf_user_cfg_key_val {
 	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
 	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
 	union {
-		char *user_val_ptr;
-		uint64_t padding1;
-	};
-	union {
-		struct adf_user_cfg_key_val *prev;
-		uint64_t padding2;
-	};
-	union {
 		struct adf_user_cfg_key_val *next;
 		uint64_t padding3;
 	};
@@ -75,10 +67,6 @@ struct adf_user_cfg_section {
 		uint64_t padding1;
 	};
 	union {
-		struct adf_user_cfg_section *prev;
-		uint64_t padding2;
-	};
-	union {
 		struct adf_user_cfg_section *next;
 		uint64_t padding3;
 	};
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
index 0666ee6a3360..27e16c09230b 100644
--- a/drivers/crypto/qat/qat_common/adf_common_drv.h
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -53,6 +53,13 @@
 #include "icp_qat_fw_loader_handle.h"
 #include "icp_qat_hal.h"
 
+#define ADF_MAJOR_VERSION	0
+#define ADF_MINOR_VERSION	1
+#define ADF_BUILD_VERSION	3
+#define ADF_DRV_VERSION		__stringify(ADF_MAJOR_VERSION) "." \
+				__stringify(ADF_MINOR_VERSION) "." \
+				__stringify(ADF_BUILD_VERSION)
+
 #define ADF_STATUS_RESTARTING 0
 #define ADF_STATUS_STARTING 1
 #define ADF_STATUS_CONFIGURED 2
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
index cb5f066e93a6..e056b9e9bf8a 100644
--- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -504,3 +504,4 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
 MODULE_ALIAS_CRYPTO("intel_qat");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 1dc5b0a17cf7..067402c7c2a9 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -47,7 +47,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/crypto.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/aes.h>
 #include <crypto/sha.h>
 #include <crypto/hash.h>
@@ -653,7 +653,7 @@ static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
 }
 
 static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
-			       struct scatterlist *assoc,
+			       struct scatterlist *assoc, int assoclen,
 			       struct scatterlist *sgl,
 			       struct scatterlist *sglout, uint8_t *iv,
 			       uint8_t ivlen,
@@ -685,15 +685,21 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
 	for_each_sg(assoc, sg, assoc_n, i) {
 		if (!sg->length)
 			continue;
-		bufl->bufers[bufs].addr = dma_map_single(dev,
-							 sg_virt(sg),
-							 sg->length,
-							 DMA_BIDIRECTIONAL);
-		bufl->bufers[bufs].len = sg->length;
+
+		if (!(assoclen > 0))
+			break;
+
+		bufl->bufers[bufs].addr =
+			dma_map_single(dev, sg_virt(sg),
+				       min_t(int, assoclen, sg->length),
+				       DMA_BIDIRECTIONAL);
+		bufl->bufers[bufs].len = min_t(int, assoclen, sg->length);
 		if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
 			goto err;
 		bufs++;
+		assoclen -= sg->length;
 	}
+
 	if (ivlen) {
 		bufl->bufers[bufs].addr = dma_map_single(dev, iv, ivlen,
 							 DMA_BIDIRECTIONAL);
@@ -845,8 +851,9 @@ static int qat_alg_aead_dec(struct aead_request *areq)
 	int digst_size = crypto_aead_crt(aead_tfm)->authsize;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
-				  areq->iv, AES_BLOCK_SIZE, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
+				  areq->src, areq->dst, areq->iv,
+				  AES_BLOCK_SIZE, qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -889,8 +896,9 @@ static int qat_alg_aead_enc_internal(struct aead_request *areq, uint8_t *iv,
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
-				  iv, AES_BLOCK_SIZE, qat_req);
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->assoclen,
+				  areq->src, areq->dst, iv, AES_BLOCK_SIZE,
+				  qat_req);
 	if (unlikely(ret))
 		return ret;
 
@@ -1017,7 +1025,7 @@ static int qat_alg_ablkcipher_encrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, req->src, req->dst,
+	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
 				  NULL, 0, qat_req);
 	if (unlikely(ret))
 		return ret;
@@ -1055,7 +1063,7 @@ static int qat_alg_ablkcipher_decrypt(struct ablkcipher_request *req)
 	struct icp_qat_fw_la_bulk_req *msg;
 	int ret, ctr = 0;
 
-	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, req->src, req->dst,
+	ret = qat_alg_sgl_to_bufl(ctx->inst, NULL, 0, req->src, req->dst,
 				  NULL, 0, qat_req);
 	if (unlikely(ret))
 		return ret;
@@ -1094,8 +1102,9 @@ static int qat_alg_aead_init(struct crypto_tfm *tfm,
 		return -EFAULT;
 	spin_lock_init(&ctx->lock);
 	ctx->qat_hash_alg = hash;
-	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
-				sizeof(struct qat_crypto_request);
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+		sizeof(struct aead_request) +
+		sizeof(struct qat_crypto_request));
 	ctx->tfm = tfm;
 	return 0;
 }
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index 9decea2779c6..1bde45b7a3c5 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -300,6 +300,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto out_err;
 
+	pcie_set_readrq(pdev, 1024);
+
 	/* enable PCI device */
 	if (pci_enable_device(pdev)) {
 		ret = -EFAULT;
@@ -417,5 +419,6 @@ module_exit(adfdrv_release);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Intel");
-MODULE_FIRMWARE("qat_895xcc.bin");
+MODULE_FIRMWARE(ADF_DH895XCC_FW);
 MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_VERSION(ADF_DRV_VERSION);
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 6be377f6b9e7..397a500b3d8a 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1578,8 +1578,12 @@ static int sahara_probe(struct platform_device *pdev)
 
 	init_completion(&dev->dma_completion);
 
-	clk_prepare_enable(dev->clk_ipg);
-	clk_prepare_enable(dev->clk_ahb);
+	err = clk_prepare_enable(dev->clk_ipg);
+	if (err)
+		goto err_link;
+	err = clk_prepare_enable(dev->clk_ahb);
+	if (err)
+		goto clk_ipg_disable;
 
 	version = sahara_read(dev, SAHARA_REG_VERSION);
 	if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx27-sahara")) {
@@ -1619,10 +1623,11 @@ err_algs:
 	dma_free_coherent(&pdev->dev,
 			  SAHARA_MAX_HW_LINK * sizeof(struct sahara_hw_link),
 			  dev->hw_link[0], dev->hw_phys_link[0]);
-	clk_disable_unprepare(dev->clk_ipg);
-	clk_disable_unprepare(dev->clk_ahb);
 	kthread_stop(dev->kthread);
 	dev_ptr = NULL;
+	clk_disable_unprepare(dev->clk_ahb);
+clk_ipg_disable:
+	clk_disable_unprepare(dev->clk_ipg);
 err_link:
 	dma_free_coherent(&pdev->dev,
 			  2 * AES_KEYSIZE_128,
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 857414afa29a..83aca95a95bc 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -46,7 +46,7 @@
 #include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/md5.h>
-#include <crypto/aead.h>
+#include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/skcipher.h>
 #include <crypto/hash.h>
@@ -55,49 +55,92 @@
 
 #include "talitos.h"
 
-static void to_talitos_ptr(struct talitos_ptr *talitos_ptr, dma_addr_t dma_addr)
+static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr,
+			   bool is_sec1)
 {
-	talitos_ptr->ptr = cpu_to_be32(lower_32_bits(dma_addr));
-	talitos_ptr->eptr = upper_32_bits(dma_addr);
+	ptr->ptr = cpu_to_be32(lower_32_bits(dma_addr));
+	if (!is_sec1)
+		ptr->eptr = upper_32_bits(dma_addr);
+}
+
+static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len,
+			       bool is_sec1)
+{
+	if (is_sec1) {
+		ptr->res = 0;
+		ptr->len1 = cpu_to_be16(len);
+	} else {
+		ptr->len = cpu_to_be16(len);
+	}
+}
+
+static unsigned short from_talitos_ptr_len(struct talitos_ptr *ptr,
+					   bool is_sec1)
+{
+	if (is_sec1)
+		return be16_to_cpu(ptr->len1);
+	else
+		return be16_to_cpu(ptr->len);
+}
+
+static void to_talitos_ptr_extent_clear(struct talitos_ptr *ptr, bool is_sec1)
+{
+	if (!is_sec1)
+		ptr->j_extent = 0;
 }
 
 /*
  * map virtual single (contiguous) pointer to h/w descriptor pointer
  */
 static void map_single_talitos_ptr(struct device *dev,
-				   struct talitos_ptr *talitos_ptr,
-				   unsigned short len, void *data,
-				   unsigned char extent,
+				   struct talitos_ptr *ptr,
+				   unsigned int len, void *data,
 				   enum dma_data_direction dir)
 {
 	dma_addr_t dma_addr = dma_map_single(dev, data, len, dir);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
-	talitos_ptr->len = cpu_to_be16(len);
-	to_talitos_ptr(talitos_ptr, dma_addr);
-	talitos_ptr->j_extent = extent;
+	to_talitos_ptr_len(ptr, len, is_sec1);
+	to_talitos_ptr(ptr, dma_addr, is_sec1);
+	to_talitos_ptr_extent_clear(ptr, is_sec1);
 }
 
 /*
  * unmap bus single (contiguous) h/w descriptor pointer
  */
 static void unmap_single_talitos_ptr(struct device *dev,
-				     struct talitos_ptr *talitos_ptr,
+				     struct talitos_ptr *ptr,
 				     enum dma_data_direction dir)
 {
-	dma_unmap_single(dev, be32_to_cpu(talitos_ptr->ptr),
-			 be16_to_cpu(talitos_ptr->len), dir);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	dma_unmap_single(dev, be32_to_cpu(ptr->ptr),
+			 from_talitos_ptr_len(ptr, is_sec1), dir);
 }
 
 static int reset_channel(struct device *dev, int ch)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
+	bool is_sec1 = has_ftr_sec1(priv);
 
-	setbits32(priv->chan[ch].reg + TALITOS_CCCR, TALITOS_CCCR_RESET);
+	if (is_sec1) {
+		setbits32(priv->chan[ch].reg + TALITOS_CCCR_LO,
+			  TALITOS1_CCCR_LO_RESET);
 
-	while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) & TALITOS_CCCR_RESET)
-	       && --timeout)
-		cpu_relax();
+		while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR_LO) &
+			TALITOS1_CCCR_LO_RESET) && --timeout)
+			cpu_relax();
+	} else {
+		setbits32(priv->chan[ch].reg + TALITOS_CCCR,
+			  TALITOS2_CCCR_RESET);
+
+		while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) &
+			TALITOS2_CCCR_RESET) && --timeout)
+			cpu_relax();
+	}
 
 	if (timeout == 0) {
 		dev_err(dev, "failed to reset channel %d\n", ch);
@@ -120,11 +163,12 @@ static int reset_device(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
-	u32 mcr = TALITOS_MCR_SWR;
+	bool is_sec1 = has_ftr_sec1(priv);
+	u32 mcr = is_sec1 ? TALITOS1_MCR_SWR : TALITOS2_MCR_SWR;
 
 	setbits32(priv->reg + TALITOS_MCR, mcr);
 
-	while ((in_be32(priv->reg + TALITOS_MCR) & TALITOS_MCR_SWR)
+	while ((in_be32(priv->reg + TALITOS_MCR) & mcr)
 	       && --timeout)
 		cpu_relax();
 
@@ -148,6 +192,7 @@ static int init_device(struct device *dev)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	int ch, err;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/*
 	 * Master reset
@@ -171,12 +216,19 @@ static int init_device(struct device *dev)
 	}
 
 	/* enable channel done and error interrupts */
-	setbits32(priv->reg + TALITOS_IMR, TALITOS_IMR_INIT);
-	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS_IMR_LO_INIT);
+	if (is_sec1) {
+		clrbits32(priv->reg + TALITOS_IMR, TALITOS1_IMR_INIT);
+		clrbits32(priv->reg + TALITOS_IMR_LO, TALITOS1_IMR_LO_INIT);
+		/* disable parity error check in DEU (erroneous? test vect.) */
+		setbits32(priv->reg_deu + TALITOS_EUICR, TALITOS1_DEUICR_KPE);
+	} else {
+		setbits32(priv->reg + TALITOS_IMR, TALITOS2_IMR_INIT);
+		setbits32(priv->reg + TALITOS_IMR_LO, TALITOS2_IMR_LO_INIT);
+	}
 
 	/* disable integrity check error interrupts (use writeback instead) */
 	if (priv->features & TALITOS_FTR_HW_AUTH_CHECK)
-		setbits32(priv->reg + TALITOS_MDEUICR_LO,
+		setbits32(priv->reg_mdeu + TALITOS_EUICR_LO,
 		          TALITOS_MDEUICR_LO_ICE);
 
 	return 0;
@@ -204,6 +256,7 @@ int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 	struct talitos_request *request;
 	unsigned long flags;
 	int head;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	spin_lock_irqsave(&priv->chan[ch].head_lock, flags);
 
@@ -217,8 +270,17 @@ int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 	request = &priv->chan[ch].fifo[head];
 
 	/* map descriptor and save caller data */
-	request->dma_desc = dma_map_single(dev, desc, sizeof(*desc),
-					   DMA_BIDIRECTIONAL);
+	if (is_sec1) {
+		desc->hdr1 = desc->hdr;
+		desc->next_desc = 0;
+		request->dma_desc = dma_map_single(dev, &desc->hdr1,
+						   TALITOS_DESC_SIZE,
+						   DMA_BIDIRECTIONAL);
+	} else {
+		request->dma_desc = dma_map_single(dev, desc,
+						   TALITOS_DESC_SIZE,
+						   DMA_BIDIRECTIONAL);
+	}
 	request->callback = callback;
 	request->context = context;
 
@@ -250,16 +312,21 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 	struct talitos_request *request, saved_req;
 	unsigned long flags;
 	int tail, status;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	spin_lock_irqsave(&priv->chan[ch].tail_lock, flags);
 
 	tail = priv->chan[ch].tail;
 	while (priv->chan[ch].fifo[tail].desc) {
+		__be32 hdr;
+
 		request = &priv->chan[ch].fifo[tail];
 
 		/* descriptors with their done bits set don't get the error */
 		rmb();
-		if ((request->desc->hdr & DESC_HDR_DONE) == DESC_HDR_DONE)
+		hdr = is_sec1 ? request->desc->hdr1 : request->desc->hdr;
+
+		if ((hdr & DESC_HDR_DONE) == DESC_HDR_DONE)
 			status = 0;
 		else
 			if (!error)
@@ -268,7 +335,7 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 				status = error;
 
 		dma_unmap_single(dev, request->dma_desc,
-				 sizeof(struct talitos_desc),
+				 TALITOS_DESC_SIZE,
 				 DMA_BIDIRECTIONAL);
 
 		/* copy entries so we can call callback outside lock */
@@ -302,8 +369,37 @@ static void flush_channel(struct device *dev, int ch, int error, int reset_ch)
 /*
  * process completed requests for channels that have done status
  */
-#define DEF_TALITOS_DONE(name, ch_done_mask)				\
-static void talitos_done_##name(unsigned long data)			\
+#define DEF_TALITOS1_DONE(name, ch_done_mask)				\
+static void talitos1_done_##name(unsigned long data)			\
+{									\
+	struct device *dev = (struct device *)data;			\
+	struct talitos_private *priv = dev_get_drvdata(dev);		\
+	unsigned long flags;						\
+									\
+	if (ch_done_mask & 0x10000000)					\
+		flush_channel(dev, 0, 0, 0);			\
+	if (priv->num_channels == 1)					\
+		goto out;						\
+	if (ch_done_mask & 0x40000000)					\
+		flush_channel(dev, 1, 0, 0);			\
+	if (ch_done_mask & 0x00010000)					\
+		flush_channel(dev, 2, 0, 0);			\
+	if (ch_done_mask & 0x00040000)					\
+		flush_channel(dev, 3, 0, 0);			\
+									\
+out:									\
+	/* At this point, all completed channels have been processed */	\
+	/* Unmask done interrupts for channels completed later on. */	\
+	spin_lock_irqsave(&priv->reg_lock, flags);			\
+	clrbits32(priv->reg + TALITOS_IMR, ch_done_mask);		\
+	clrbits32(priv->reg + TALITOS_IMR_LO, TALITOS1_IMR_LO_INIT);	\
+	spin_unlock_irqrestore(&priv->reg_lock, flags);			\
+}
+
+DEF_TALITOS1_DONE(4ch, TALITOS1_ISR_4CHDONE)
+
+#define DEF_TALITOS2_DONE(name, ch_done_mask)				\
+static void talitos2_done_##name(unsigned long data)			\
 {									\
 	struct device *dev = (struct device *)data;			\
 	struct talitos_private *priv = dev_get_drvdata(dev);		\
@@ -325,12 +421,13 @@ out:									\
 	/* Unmask done interrupts for channels completed later on. */	\
 	spin_lock_irqsave(&priv->reg_lock, flags);			\
 	setbits32(priv->reg + TALITOS_IMR, ch_done_mask);		\
-	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS_IMR_LO_INIT);	\
+	setbits32(priv->reg + TALITOS_IMR_LO, TALITOS2_IMR_LO_INIT);	\
 	spin_unlock_irqrestore(&priv->reg_lock, flags);			\
 }
-DEF_TALITOS_DONE(4ch, TALITOS_ISR_4CHDONE)
-DEF_TALITOS_DONE(ch0_2, TALITOS_ISR_CH_0_2_DONE)
-DEF_TALITOS_DONE(ch1_3, TALITOS_ISR_CH_1_3_DONE)
+
+DEF_TALITOS2_DONE(4ch, TALITOS2_ISR_4CHDONE)
+DEF_TALITOS2_DONE(ch0_2, TALITOS2_ISR_CH_0_2_DONE)
+DEF_TALITOS2_DONE(ch1_3, TALITOS2_ISR_CH_1_3_DONE)
 
 /*
  * locate current (offending) descriptor
@@ -377,44 +474,44 @@ static void report_eu_error(struct device *dev, int ch, u32 desc_hdr)
 	switch (desc_hdr & DESC_HDR_SEL0_MASK) {
 	case DESC_HDR_SEL0_AFEU:
 		dev_err(dev, "AFEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_AFEUISR),
-			in_be32(priv->reg + TALITOS_AFEUISR_LO));
+			in_be32(priv->reg_afeu + TALITOS_EUISR),
+			in_be32(priv->reg_afeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_DEU:
 		dev_err(dev, "DEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_DEUISR),
-			in_be32(priv->reg + TALITOS_DEUISR_LO));
+			in_be32(priv->reg_deu + TALITOS_EUISR),
+			in_be32(priv->reg_deu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_MDEUA:
 	case DESC_HDR_SEL0_MDEUB:
 		dev_err(dev, "MDEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_MDEUISR),
-			in_be32(priv->reg + TALITOS_MDEUISR_LO));
+			in_be32(priv->reg_mdeu + TALITOS_EUISR),
+			in_be32(priv->reg_mdeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_RNG:
 		dev_err(dev, "RNGUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_RNGUISR),
-			in_be32(priv->reg + TALITOS_RNGUISR_LO));
+			in_be32(priv->reg_rngu + TALITOS_ISR),
+			in_be32(priv->reg_rngu + TALITOS_ISR_LO));
 		break;
 	case DESC_HDR_SEL0_PKEU:
 		dev_err(dev, "PKEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_PKEUISR),
-			in_be32(priv->reg + TALITOS_PKEUISR_LO));
+			in_be32(priv->reg_pkeu + TALITOS_EUISR),
+			in_be32(priv->reg_pkeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_AESU:
 		dev_err(dev, "AESUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_AESUISR),
-			in_be32(priv->reg + TALITOS_AESUISR_LO));
+			in_be32(priv->reg_aesu + TALITOS_EUISR),
+			in_be32(priv->reg_aesu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_CRCU:
 		dev_err(dev, "CRCUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_CRCUISR),
-			in_be32(priv->reg + TALITOS_CRCUISR_LO));
+			in_be32(priv->reg_crcu + TALITOS_EUISR),
+			in_be32(priv->reg_crcu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL0_KEU:
 		dev_err(dev, "KEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_KEUISR),
-			in_be32(priv->reg + TALITOS_KEUISR_LO));
+			in_be32(priv->reg_pkeu + TALITOS_EUISR),
+			in_be32(priv->reg_pkeu + TALITOS_EUISR_LO));
 		break;
 	}
 
@@ -422,13 +519,13 @@ static void report_eu_error(struct device *dev, int ch, u32 desc_hdr)
 	case DESC_HDR_SEL1_MDEUA:
 	case DESC_HDR_SEL1_MDEUB:
 		dev_err(dev, "MDEUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_MDEUISR),
-			in_be32(priv->reg + TALITOS_MDEUISR_LO));
+			in_be32(priv->reg_mdeu + TALITOS_EUISR),
+			in_be32(priv->reg_mdeu + TALITOS_EUISR_LO));
 		break;
 	case DESC_HDR_SEL1_CRCU:
 		dev_err(dev, "CRCUISR 0x%08x_%08x\n",
-			in_be32(priv->reg + TALITOS_CRCUISR),
-			in_be32(priv->reg + TALITOS_CRCUISR_LO));
+			in_be32(priv->reg_crcu + TALITOS_EUISR),
+			in_be32(priv->reg_crcu + TALITOS_EUISR_LO));
 		break;
 	}
 
@@ -445,17 +542,24 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 {
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
-	int ch, error, reset_dev = 0, reset_ch = 0;
-	u32 v, v_lo;
+	int ch, error, reset_dev = 0;
+	u32 v_lo;
+	bool is_sec1 = has_ftr_sec1(priv);
+	int reset_ch = is_sec1 ? 1 : 0; /* only SEC2 supports continuation */
 
 	for (ch = 0; ch < priv->num_channels; ch++) {
 		/* skip channels without errors */
-		if (!(isr & (1 << (ch * 2 + 1))))
-			continue;
+		if (is_sec1) {
+			/* bits 29, 31, 17, 19 */
+			if (!(isr & (1 << (29 + (ch & 1) * 2 - (ch & 2) * 6))))
+				continue;
+		} else {
+			if (!(isr & (1 << (ch * 2 + 1))))
+				continue;
+		}
 
 		error = -EINVAL;
 
-		v = in_be32(priv->chan[ch].reg + TALITOS_CCPSR);
 		v_lo = in_be32(priv->chan[ch].reg + TALITOS_CCPSR_LO);
 
 		if (v_lo & TALITOS_CCPSR_LO_DOF) {
@@ -471,23 +575,28 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 		if (v_lo & TALITOS_CCPSR_LO_MDTE)
 			dev_err(dev, "master data transfer error\n");
 		if (v_lo & TALITOS_CCPSR_LO_SGDLZ)
-			dev_err(dev, "s/g data length zero error\n");
+			dev_err(dev, is_sec1 ? "pointeur not complete error\n"
+					     : "s/g data length zero error\n");
 		if (v_lo & TALITOS_CCPSR_LO_FPZ)
-			dev_err(dev, "fetch pointer zero error\n");
+			dev_err(dev, is_sec1 ? "parity error\n"
+					     : "fetch pointer zero error\n");
 		if (v_lo & TALITOS_CCPSR_LO_IDH)
 			dev_err(dev, "illegal descriptor header error\n");
 		if (v_lo & TALITOS_CCPSR_LO_IEU)
-			dev_err(dev, "invalid execution unit error\n");
+			dev_err(dev, is_sec1 ? "static assignment error\n"
+					     : "invalid exec unit error\n");
 		if (v_lo & TALITOS_CCPSR_LO_EU)
 			report_eu_error(dev, ch, current_desc_hdr(dev, ch));
-		if (v_lo & TALITOS_CCPSR_LO_GB)
-			dev_err(dev, "gather boundary error\n");
-		if (v_lo & TALITOS_CCPSR_LO_GRL)
-			dev_err(dev, "gather return/length error\n");
-		if (v_lo & TALITOS_CCPSR_LO_SB)
-			dev_err(dev, "scatter boundary error\n");
-		if (v_lo & TALITOS_CCPSR_LO_SRL)
-			dev_err(dev, "scatter return/length error\n");
+		if (!is_sec1) {
+			if (v_lo & TALITOS_CCPSR_LO_GB)
+				dev_err(dev, "gather boundary error\n");
+			if (v_lo & TALITOS_CCPSR_LO_GRL)
+				dev_err(dev, "gather return/length error\n");
+			if (v_lo & TALITOS_CCPSR_LO_SB)
+				dev_err(dev, "scatter boundary error\n");
+			if (v_lo & TALITOS_CCPSR_LO_SRL)
+				dev_err(dev, "scatter return/length error\n");
+		}
 
 		flush_channel(dev, ch, error, reset_ch);
 
@@ -495,10 +604,10 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 			reset_channel(dev, ch);
 		} else {
 			setbits32(priv->chan[ch].reg + TALITOS_CCCR,
-				  TALITOS_CCCR_CONT);
+				  TALITOS2_CCCR_CONT);
 			setbits32(priv->chan[ch].reg + TALITOS_CCCR_LO, 0);
 			while ((in_be32(priv->chan[ch].reg + TALITOS_CCCR) &
-			       TALITOS_CCCR_CONT) && --timeout)
+			       TALITOS2_CCCR_CONT) && --timeout)
 				cpu_relax();
 			if (timeout == 0) {
 				dev_err(dev, "failed to restart channel %d\n",
@@ -507,9 +616,14 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 			}
 		}
 	}
-	if (reset_dev || isr & ~TALITOS_ISR_4CHERR || isr_lo) {
-		dev_err(dev, "done overflow, internal time out, or rngu error: "
-		        "ISR 0x%08x_%08x\n", isr, isr_lo);
+	if (reset_dev || (is_sec1 && isr & ~TALITOS1_ISR_4CHERR) ||
+	    (!is_sec1 && isr & ~TALITOS2_ISR_4CHERR) || isr_lo) {
+		if (is_sec1 && (isr_lo & TALITOS1_ISR_TEA_ERR))
+			dev_err(dev, "TEA error: ISR 0x%08x_%08x\n",
+				isr, isr_lo);
+		else
+			dev_err(dev, "done overflow, internal time out, or "
+				"rngu error: ISR 0x%08x_%08x\n", isr, isr_lo);
 
 		/* purge request queues */
 		for (ch = 0; ch < priv->num_channels; ch++)
@@ -520,8 +634,43 @@ static void talitos_error(struct device *dev, u32 isr, u32 isr_lo)
 	}
 }
 
-#define DEF_TALITOS_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
-static irqreturn_t talitos_interrupt_##name(int irq, void *data)	       \
+#define DEF_TALITOS1_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
+static irqreturn_t talitos1_interrupt_##name(int irq, void *data)	       \
+{									       \
+	struct device *dev = data;					       \
+	struct talitos_private *priv = dev_get_drvdata(dev);		       \
+	u32 isr, isr_lo;						       \
+	unsigned long flags;						       \
+									       \
+	spin_lock_irqsave(&priv->reg_lock, flags);			       \
+	isr = in_be32(priv->reg + TALITOS_ISR);				       \
+	isr_lo = in_be32(priv->reg + TALITOS_ISR_LO);			       \
+	/* Acknowledge interrupt */					       \
+	out_be32(priv->reg + TALITOS_ICR, isr & (ch_done_mask | ch_err_mask)); \
+	out_be32(priv->reg + TALITOS_ICR_LO, isr_lo);			       \
+									       \
+	if (unlikely(isr & ch_err_mask || isr_lo & TALITOS1_IMR_LO_INIT)) {    \
+		spin_unlock_irqrestore(&priv->reg_lock, flags);		       \
+		talitos_error(dev, isr & ch_err_mask, isr_lo);		       \
+	}								       \
+	else {								       \
+		if (likely(isr & ch_done_mask)) {			       \
+			/* mask further done interrupts. */		       \
+			setbits32(priv->reg + TALITOS_IMR, ch_done_mask);      \
+			/* done_task will unmask done interrupts at exit */    \
+			tasklet_schedule(&priv->done_task[tlet]);	       \
+		}							       \
+		spin_unlock_irqrestore(&priv->reg_lock, flags);		       \
+	}								       \
+									       \
+	return (isr & (ch_done_mask | ch_err_mask) || isr_lo) ? IRQ_HANDLED :  \
+								IRQ_NONE;      \
+}
+
+DEF_TALITOS1_INTERRUPT(4ch, TALITOS1_ISR_4CHDONE, TALITOS1_ISR_4CHERR, 0)
+
+#define DEF_TALITOS2_INTERRUPT(name, ch_done_mask, ch_err_mask, tlet)	       \
+static irqreturn_t talitos2_interrupt_##name(int irq, void *data)	       \
 {									       \
 	struct device *dev = data;					       \
 	struct talitos_private *priv = dev_get_drvdata(dev);		       \
@@ -552,9 +701,12 @@ static irqreturn_t talitos_interrupt_##name(int irq, void *data)	       \
 	return (isr & (ch_done_mask | ch_err_mask) || isr_lo) ? IRQ_HANDLED :  \
 								IRQ_NONE;      \
 }
-DEF_TALITOS_INTERRUPT(4ch, TALITOS_ISR_4CHDONE, TALITOS_ISR_4CHERR, 0)
-DEF_TALITOS_INTERRUPT(ch0_2, TALITOS_ISR_CH_0_2_DONE, TALITOS_ISR_CH_0_2_ERR, 0)
-DEF_TALITOS_INTERRUPT(ch1_3, TALITOS_ISR_CH_1_3_DONE, TALITOS_ISR_CH_1_3_ERR, 1)
+
+DEF_TALITOS2_INTERRUPT(4ch, TALITOS2_ISR_4CHDONE, TALITOS2_ISR_4CHERR, 0)
+DEF_TALITOS2_INTERRUPT(ch0_2, TALITOS2_ISR_CH_0_2_DONE, TALITOS2_ISR_CH_0_2_ERR,
+		       0)
+DEF_TALITOS2_INTERRUPT(ch1_3, TALITOS2_ISR_CH_1_3_DONE, TALITOS2_ISR_CH_1_3_ERR,
+		       1)
 
 /*
  * hwrng
@@ -567,7 +719,7 @@ static int talitos_rng_data_present(struct hwrng *rng, int wait)
 	int i;
 
 	for (i = 0; i < 20; i++) {
-		ofl = in_be32(priv->reg + TALITOS_RNGUSR_LO) &
+		ofl = in_be32(priv->reg_rngu + TALITOS_EUSR_LO) &
 		      TALITOS_RNGUSR_LO_OFL;
 		if (ofl || !wait)
 			break;
@@ -583,8 +735,8 @@ static int talitos_rng_data_read(struct hwrng *rng, u32 *data)
 	struct talitos_private *priv = dev_get_drvdata(dev);
 
 	/* rng fifo requires 64-bit accesses */
-	*data = in_be32(priv->reg + TALITOS_RNGU_FIFO);
-	*data = in_be32(priv->reg + TALITOS_RNGU_FIFO_LO);
+	*data = in_be32(priv->reg_rngu + TALITOS_EU_FIFO);
+	*data = in_be32(priv->reg_rngu + TALITOS_EU_FIFO_LO);
 
 	return sizeof(u32);
 }
@@ -595,8 +747,9 @@ static int talitos_rng_init(struct hwrng *rng)
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	unsigned int timeout = TALITOS_TIMEOUT;
 
-	setbits32(priv->reg + TALITOS_RNGURCR_LO, TALITOS_RNGURCR_LO_SR);
-	while (!(in_be32(priv->reg + TALITOS_RNGUSR_LO) & TALITOS_RNGUSR_LO_RD)
+	setbits32(priv->reg_rngu + TALITOS_EURCR_LO, TALITOS_RNGURCR_LO_SR);
+	while (!(in_be32(priv->reg_rngu + TALITOS_EUSR_LO)
+		 & TALITOS_RNGUSR_LO_RD)
 	       && --timeout)
 		cpu_relax();
 	if (timeout == 0) {
@@ -605,7 +758,7 @@ static int talitos_rng_init(struct hwrng *rng)
 	}
 
 	/* start generating */
-	setbits32(priv->reg + TALITOS_RNGUDSR_LO, 0);
+	setbits32(priv->reg_rngu + TALITOS_EUDSR_LO, 0);
 
 	return 0;
 }
@@ -661,7 +814,7 @@ struct talitos_ahash_req_ctx {
 	unsigned int first;
 	unsigned int last;
 	unsigned int to_hash_later;
-	u64 nbuf;
+	unsigned int nbuf;
 	struct scatterlist bufsl[2];
 	struct scatterlist *psrc;
 };
@@ -712,9 +865,10 @@ badkey:
  * @dst_chained: whether dst is chained or not
  * @iv_dma: dma address of iv for checking continuity and link table
  * @dma_len: length of dma mapped link_tbl space
- * @dma_link_tbl: bus physical address of link_tbl
+ * @dma_link_tbl: bus physical address of link_tbl/buf
  * @desc: h/w descriptor
- * @link_tbl: input and output h/w link tables (if {src,dst}_nents > 1)
+ * @link_tbl: input and output h/w link tables (if {src,dst}_nents > 1) (SEC2)
+ * @buf: input and output buffeur (if {src,dst}_nents > 1) (SEC1)
  *
  * if decrypting (with authcheck), or either one of src_nents or dst_nents
  * is greater than 1, an integrity check value is concatenated to the end
@@ -731,7 +885,10 @@ struct talitos_edesc {
 	int dma_len;
 	dma_addr_t dma_link_tbl;
 	struct talitos_desc desc;
-	struct talitos_ptr link_tbl[0];
+	union {
+		struct talitos_ptr link_tbl[0];
+		u8 buf[0];
+	};
 };
 
 static int talitos_map_sg(struct device *dev, struct scatterlist *sg,
@@ -907,8 +1064,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
 {
 	int n_sg = sg_count;
 
-	while (n_sg--) {
-		to_talitos_ptr(link_tbl_ptr, sg_dma_address(sg));
+	while (sg && n_sg--) {
+		to_talitos_ptr(link_tbl_ptr, sg_dma_address(sg), 0);
 		link_tbl_ptr->len = cpu_to_be16(sg_dma_len(sg));
 		link_tbl_ptr->j_extent = 0;
 		link_tbl_ptr++;
@@ -925,7 +1082,8 @@ static int sg_to_link_tbl(struct scatterlist *sg, int sg_count,
 		sg_count--;
 		link_tbl_ptr--;
 	}
-	be16_add_cpu(&link_tbl_ptr->len, cryptlen);
+	link_tbl_ptr->len = cpu_to_be16(be16_to_cpu(link_tbl_ptr->len)
+					+ cryptlen);
 
 	/* tag end of link table */
 	link_tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
@@ -953,7 +1111,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	/* hmac key */
 	map_single_talitos_ptr(dev, &desc->ptr[0], ctx->authkeylen, &ctx->key,
-			       0, DMA_TO_DEVICE);
+			       DMA_TO_DEVICE);
 
 	/* hmac data */
 	desc->ptr[1].len = cpu_to_be16(areq->assoclen + ivsize);
@@ -962,7 +1120,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off *
-			       sizeof(struct talitos_ptr));
+			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP;
 
 		/* assoc_nents - 1 entries for assoc, 1 for IV */
@@ -973,7 +1131,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		tbl_ptr += sg_count - 1;
 		tbl_ptr->j_extent = 0;
 		tbl_ptr++;
-		to_talitos_ptr(tbl_ptr, edesc->iv_dma);
+		to_talitos_ptr(tbl_ptr, edesc->iv_dma, 0);
 		tbl_ptr->len = cpu_to_be16(ivsize);
 		tbl_ptr->j_extent = DESC_PTR_LNKTBL_RETURN;
 
@@ -982,14 +1140,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 	} else {
 		if (areq->assoclen)
 			to_talitos_ptr(&desc->ptr[1],
-				       sg_dma_address(areq->assoc));
+				       sg_dma_address(areq->assoc), 0);
 		else
-			to_talitos_ptr(&desc->ptr[1], edesc->iv_dma);
+			to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, 0);
 		desc->ptr[1].j_extent = 0;
 	}
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma);
+	to_talitos_ptr(&desc->ptr[2], edesc->iv_dma, 0);
 	desc->ptr[2].len = cpu_to_be16(ivsize);
 	desc->ptr[2].j_extent = 0;
 	/* Sync needed for the aead_givencrypt case */
@@ -997,7 +1155,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[3], ctx->enckeylen,
-			       (char *)&ctx->key + ctx->authkeylen, 0,
+			       (char *)&ctx->key + ctx->authkeylen,
 			       DMA_TO_DEVICE);
 
 	/*
@@ -1015,7 +1173,7 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 				  edesc->src_chained);
 
 	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src));
+		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0);
 	} else {
 		sg_link_tbl_len = cryptlen;
 
@@ -1026,14 +1184,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					  &edesc->link_tbl[0]);
 		if (sg_count > 1) {
 			desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl);
+			to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl, 0);
 			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
 						   edesc->dma_len,
 						   DMA_BIDIRECTIONAL);
 		} else {
 			/* Only one segment now, so no link tbl needed */
 			to_talitos_ptr(&desc->ptr[4],
-				       sg_dma_address(areq->src));
+				       sg_dma_address(areq->src), 0);
 		}
 	}
 
@@ -1047,13 +1205,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 					  DMA_FROM_DEVICE, edesc->dst_chained);
 
 	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst));
+		to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0);
 	} else {
 		int tbl_off = edesc->src_nents + 1;
 		struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off];
 
 		to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl +
-			       tbl_off * sizeof(struct talitos_ptr));
+			       tbl_off * sizeof(struct talitos_ptr), 0);
 		sg_count = sg_to_link_tbl(areq->dst, sg_count, cryptlen,
 					  tbl_ptr);
 
@@ -1068,14 +1226,14 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq,
 		to_talitos_ptr(tbl_ptr, edesc->dma_link_tbl +
 			       (tbl_off + edesc->dst_nents + 1 +
 				edesc->assoc_nents) *
-			       sizeof(struct talitos_ptr));
+			       sizeof(struct talitos_ptr), 0);
 		desc->ptr[5].j_extent |= DESC_PTR_LNKTBL_JUMP;
 		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
 					   edesc->dma_len, DMA_BIDIRECTIONAL);
 	}
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, 0,
+	map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv,
 			       DMA_FROM_DEVICE);
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
@@ -1095,7 +1253,7 @@ static int sg_count(struct scatterlist *sg_list, int nbytes, bool *chained)
 	int sg_nents = 0;
 
 	*chained = false;
-	while (nbytes > 0) {
+	while (nbytes > 0 && sg) {
 		sg_nents++;
 		nbytes -= sg->length;
 		if (!sg_is_last(sg) && (sg + 1)->length == 0)
@@ -1128,8 +1286,11 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	dma_addr_t iv_dma = 0;
 	gfp_t flags = cryptoflags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL :
 		      GFP_ATOMIC;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+	int max_len = is_sec1 ? TALITOS1_MAX_DATA_LEN : TALITOS2_MAX_DATA_LEN;
 
-	if (cryptlen + authsize > TALITOS_MAX_DATA_LEN) {
+	if (cryptlen + authsize > max_len) {
 		dev_err(dev, "length exceeds h/w max limit\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1173,8 +1334,12 @@ static struct talitos_edesc *talitos_edesc_alloc(struct device *dev,
 	 */
 	alloc_len = sizeof(struct talitos_edesc);
 	if (assoc_nents || src_nents || dst_nents) {
-		dma_len = (src_nents + dst_nents + 2 + assoc_nents) *
-			  sizeof(struct talitos_ptr) + authsize;
+		if (is_sec1)
+			dma_len = (src_nents ? cryptlen : 0) +
+				  (dst_nents ? cryptlen : 0);
+		else
+			dma_len = (src_nents + dst_nents + 2 + assoc_nents) *
+				  sizeof(struct talitos_ptr) + authsize;
 		alloc_len += dma_len;
 	} else {
 		dma_len = 0;
@@ -1327,16 +1492,43 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
+static void unmap_sg_talitos_ptr(struct device *dev, struct scatterlist *src,
+				 struct scatterlist *dst, unsigned int len,
+				 struct talitos_edesc *edesc)
+{
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	if (is_sec1) {
+		if (!edesc->src_nents) {
+			dma_unmap_sg(dev, src, 1,
+				     dst != src ? DMA_TO_DEVICE
+						: DMA_BIDIRECTIONAL);
+		}
+		if (dst && edesc->dst_nents) {
+			dma_sync_single_for_device(dev,
+						   edesc->dma_link_tbl + len,
+						   len, DMA_FROM_DEVICE);
+			sg_copy_from_buffer(dst, edesc->dst_nents ? : 1,
+					    edesc->buf + len, len);
+		} else if (dst && dst != src) {
+			dma_unmap_sg(dev, dst, 1, DMA_FROM_DEVICE);
+		}
+	} else {
+		talitos_sg_unmap(dev, edesc, src, dst);
+	}
+}
+
 static void common_nonsnoop_unmap(struct device *dev,
 				  struct talitos_edesc *edesc,
 				  struct ablkcipher_request *areq)
 {
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
+
+	unmap_sg_talitos_ptr(dev, areq->src, areq->dst, areq->nbytes, edesc);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2], DMA_TO_DEVICE);
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1], DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, areq->src, areq->dst);
-
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
@@ -1358,6 +1550,102 @@ static void ablkcipher_done(struct device *dev,
 	areq->base.complete(&areq->base, err);
 }
 
+int map_sg_in_talitos_ptr(struct device *dev, struct scatterlist *src,
+			  unsigned int len, struct talitos_edesc *edesc,
+			  enum dma_data_direction dir, struct talitos_ptr *ptr)
+{
+	int sg_count;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+
+	if (is_sec1) {
+		sg_count = edesc->src_nents ? : 1;
+
+		if (sg_count == 1) {
+			dma_map_sg(dev, src, 1, dir);
+			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
+		} else {
+			sg_copy_to_buffer(src, sg_count, edesc->buf, len);
+			to_talitos_ptr(ptr, edesc->dma_link_tbl, is_sec1);
+			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+						   len, DMA_TO_DEVICE);
+		}
+	} else {
+		to_talitos_ptr_extent_clear(ptr, is_sec1);
+
+		sg_count = talitos_map_sg(dev, src, edesc->src_nents ? : 1, dir,
+					  edesc->src_chained);
+
+		if (sg_count == 1) {
+			to_talitos_ptr(ptr, sg_dma_address(src), is_sec1);
+		} else {
+			sg_count = sg_to_link_tbl(src, sg_count, len,
+						  &edesc->link_tbl[0]);
+			if (sg_count > 1) {
+				to_talitos_ptr(ptr, edesc->dma_link_tbl, 0);
+				ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
+				dma_sync_single_for_device(dev,
+							   edesc->dma_link_tbl,
+							   edesc->dma_len,
+							   DMA_BIDIRECTIONAL);
+			} else {
+				/* Only one segment now, so no link tbl needed*/
+				to_talitos_ptr(ptr, sg_dma_address(src),
+					       is_sec1);
+			}
+		}
+	}
+	return sg_count;
+}
+
+void map_sg_out_talitos_ptr(struct device *dev, struct scatterlist *dst,
+			    unsigned int len, struct talitos_edesc *edesc,
+			    enum dma_data_direction dir,
+			    struct talitos_ptr *ptr, int sg_count)
+{
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
+
+	if (dir != DMA_NONE)
+		sg_count = talitos_map_sg(dev, dst, edesc->dst_nents ? : 1,
+					  dir, edesc->dst_chained);
+
+	to_talitos_ptr_len(ptr, len, is_sec1);
+
+	if (is_sec1) {
+		if (sg_count == 1) {
+			if (dir != DMA_NONE)
+				dma_map_sg(dev, dst, 1, dir);
+			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
+		} else {
+			to_talitos_ptr(ptr, edesc->dma_link_tbl + len, is_sec1);
+			dma_sync_single_for_device(dev,
+						   edesc->dma_link_tbl + len,
+						   len, DMA_FROM_DEVICE);
+		}
+	} else {
+		to_talitos_ptr_extent_clear(ptr, is_sec1);
+
+		if (sg_count == 1) {
+			to_talitos_ptr(ptr, sg_dma_address(dst), is_sec1);
+		} else {
+			struct talitos_ptr *link_tbl_ptr =
+				&edesc->link_tbl[edesc->src_nents + 1];
+
+			to_talitos_ptr(ptr, edesc->dma_link_tbl +
+					    (edesc->src_nents + 1) *
+					     sizeof(struct talitos_ptr), 0);
+			ptr->j_extent |= DESC_PTR_LNKTBL_JUMP;
+			sg_to_link_tbl(dst, sg_count, len, link_tbl_ptr);
+			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
+						   edesc->dma_len,
+						   DMA_BIDIRECTIONAL);
+		}
+	}
+}
+
 static int common_nonsnoop(struct talitos_edesc *edesc,
 			   struct ablkcipher_request *areq,
 			   void (*callback) (struct device *dev,
@@ -1371,83 +1659,41 @@ static int common_nonsnoop(struct talitos_edesc *edesc,
 	unsigned int cryptlen = areq->nbytes;
 	unsigned int ivsize = crypto_ablkcipher_ivsize(cipher);
 	int sg_count, ret;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* first DWORD empty */
-	desc->ptr[0].len = 0;
-	to_talitos_ptr(&desc->ptr[0], 0);
-	desc->ptr[0].j_extent = 0;
+	desc->ptr[0] = zero_entry;
 
 	/* cipher iv */
-	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma);
-	desc->ptr[1].len = cpu_to_be16(ivsize);
-	desc->ptr[1].j_extent = 0;
+	to_talitos_ptr(&desc->ptr[1], edesc->iv_dma, is_sec1);
+	to_talitos_ptr_len(&desc->ptr[1], ivsize, is_sec1);
+	to_talitos_ptr_extent_clear(&desc->ptr[1], is_sec1);
 
 	/* cipher key */
 	map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
-			       (char *)&ctx->key, 0, DMA_TO_DEVICE);
+			       (char *)&ctx->key, DMA_TO_DEVICE);
 
 	/*
 	 * cipher in
 	 */
-	desc->ptr[3].len = cpu_to_be16(cryptlen);
-	desc->ptr[3].j_extent = 0;
-
-	sg_count = talitos_map_sg(dev, areq->src, edesc->src_nents ? : 1,
-				  (areq->src == areq->dst) ? DMA_BIDIRECTIONAL
-							   : DMA_TO_DEVICE,
-				  edesc->src_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[3], sg_dma_address(areq->src));
-	} else {
-		sg_count = sg_to_link_tbl(areq->src, sg_count, cryptlen,
-					  &edesc->link_tbl[0]);
-		if (sg_count > 1) {
-			to_talitos_ptr(&desc->ptr[3], edesc->dma_link_tbl);
-			desc->ptr[3].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			dma_sync_single_for_device(dev, edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		} else {
-			/* Only one segment now, so no link tbl needed */
-			to_talitos_ptr(&desc->ptr[3],
-				       sg_dma_address(areq->src));
-		}
-	}
+	sg_count = map_sg_in_talitos_ptr(dev, areq->src, cryptlen, edesc,
+					 (areq->src == areq->dst) ?
+					  DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+					  &desc->ptr[3]);
 
 	/* cipher out */
-	desc->ptr[4].len = cpu_to_be16(cryptlen);
-	desc->ptr[4].j_extent = 0;
-
-	if (areq->src != areq->dst)
-		sg_count = talitos_map_sg(dev, areq->dst,
-					  edesc->dst_nents ? : 1,
-					  DMA_FROM_DEVICE, edesc->dst_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->dst));
-	} else {
-		struct talitos_ptr *link_tbl_ptr =
-			&edesc->link_tbl[edesc->src_nents + 1];
-
-		to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl +
-					      (edesc->src_nents + 1) *
-					      sizeof(struct talitos_ptr));
-		desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP;
-		sg_count = sg_to_link_tbl(areq->dst, sg_count, cryptlen,
-					  link_tbl_ptr);
-		dma_sync_single_for_device(ctx->dev, edesc->dma_link_tbl,
-					   edesc->dma_len, DMA_BIDIRECTIONAL);
-	}
+	map_sg_out_talitos_ptr(dev, areq->dst, cryptlen, edesc,
+			       (areq->src == areq->dst) ? DMA_NONE
+							: DMA_FROM_DEVICE,
+			       &desc->ptr[4], sg_count);
 
 	/* iv out */
-	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv, 0,
+	map_single_talitos_ptr(dev, &desc->ptr[5], ivsize, ctx->iv,
 			       DMA_FROM_DEVICE);
 
 	/* last DWORD empty */
-	desc->ptr[6].len = 0;
-	to_talitos_ptr(&desc->ptr[6], 0);
-	desc->ptr[6].j_extent = 0;
+	desc->ptr[6] = zero_entry;
 
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
@@ -1507,20 +1753,22 @@ static void common_nonsnoop_hash_unmap(struct device *dev,
 				       struct ahash_request *areq)
 {
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	unmap_single_talitos_ptr(dev, &edesc->desc.ptr[5], DMA_FROM_DEVICE);
 
+	unmap_sg_talitos_ptr(dev, req_ctx->psrc, NULL, 0, edesc);
+
 	/* When using hashctx-in, must unmap it. */
-	if (edesc->desc.ptr[1].len)
+	if (from_talitos_ptr_len(&edesc->desc.ptr[1], is_sec1))
 		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[1],
 					 DMA_TO_DEVICE);
 
-	if (edesc->desc.ptr[2].len)
+	if (from_talitos_ptr_len(&edesc->desc.ptr[2], is_sec1))
 		unmap_single_talitos_ptr(dev, &edesc->desc.ptr[2],
 					 DMA_TO_DEVICE);
 
-	talitos_sg_unmap(dev, edesc, req_ctx->psrc, NULL);
-
 	if (edesc->dma_len)
 		dma_unmap_single(dev, edesc->dma_link_tbl, edesc->dma_len,
 				 DMA_BIDIRECTIONAL);
@@ -1548,6 +1796,27 @@ static void ahash_done(struct device *dev,
 	areq->base.complete(&areq->base, err);
 }
 
+/*
+ * SEC1 doesn't like hashing of 0 sized message, so we do the padding
+ * ourself and submit a padded block
+ */
+void talitos_handle_buggy_hash(struct talitos_ctx *ctx,
+			       struct talitos_edesc *edesc,
+			       struct talitos_ptr *ptr)
+{
+	static u8 padded_hash[64] = {
+		0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	};
+
+	pr_err_once("Bug in SEC1, padding ourself\n");
+	edesc->desc.hdr &= ~DESC_HDR_MODE0_MDEU_PAD;
+	map_single_talitos_ptr(ctx->dev, ptr, sizeof(padded_hash),
+			       (char *)padded_hash, DMA_TO_DEVICE);
+}
+
 static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 				struct ahash_request *areq, unsigned int length,
 				void (*callback) (struct device *dev,
@@ -1559,7 +1828,9 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq);
 	struct device *dev = ctx->dev;
 	struct talitos_desc *desc = &edesc->desc;
-	int sg_count, ret;
+	int ret;
+	struct talitos_private *priv = dev_get_drvdata(dev);
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	/* first DWORD empty */
 	desc->ptr[0] = zero_entry;
@@ -1568,7 +1839,7 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (!req_ctx->first || req_ctx->swinit) {
 		map_single_talitos_ptr(dev, &desc->ptr[1],
 				       req_ctx->hw_context_size,
-				       (char *)req_ctx->hw_context, 0,
+				       (char *)req_ctx->hw_context,
 				       DMA_TO_DEVICE);
 		req_ctx->swinit = 0;
 	} else {
@@ -1580,38 +1851,15 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	/* HMAC key */
 	if (ctx->keylen)
 		map_single_talitos_ptr(dev, &desc->ptr[2], ctx->keylen,
-				       (char *)&ctx->key, 0, DMA_TO_DEVICE);
+				       (char *)&ctx->key, DMA_TO_DEVICE);
 	else
 		desc->ptr[2] = zero_entry;
 
 	/*
 	 * data in
 	 */
-	desc->ptr[3].len = cpu_to_be16(length);
-	desc->ptr[3].j_extent = 0;
-
-	sg_count = talitos_map_sg(dev, req_ctx->psrc,
-				  edesc->src_nents ? : 1,
-				  DMA_TO_DEVICE, edesc->src_chained);
-
-	if (sg_count == 1) {
-		to_talitos_ptr(&desc->ptr[3], sg_dma_address(req_ctx->psrc));
-	} else {
-		sg_count = sg_to_link_tbl(req_ctx->psrc, sg_count, length,
-					  &edesc->link_tbl[0]);
-		if (sg_count > 1) {
-			desc->ptr[3].j_extent |= DESC_PTR_LNKTBL_JUMP;
-			to_talitos_ptr(&desc->ptr[3], edesc->dma_link_tbl);
-			dma_sync_single_for_device(ctx->dev,
-						   edesc->dma_link_tbl,
-						   edesc->dma_len,
-						   DMA_BIDIRECTIONAL);
-		} else {
-			/* Only one segment now, so no link tbl needed */
-			to_talitos_ptr(&desc->ptr[3],
-				       sg_dma_address(req_ctx->psrc));
-		}
-	}
+	map_sg_in_talitos_ptr(dev, req_ctx->psrc, length, edesc,
+			      DMA_TO_DEVICE, &desc->ptr[3]);
 
 	/* fifth DWORD empty */
 	desc->ptr[4] = zero_entry;
@@ -1620,15 +1868,18 @@ static int common_nonsnoop_hash(struct talitos_edesc *edesc,
 	if (req_ctx->last)
 		map_single_talitos_ptr(dev, &desc->ptr[5],
 				       crypto_ahash_digestsize(tfm),
-				       areq->result, 0, DMA_FROM_DEVICE);
+				       areq->result, DMA_FROM_DEVICE);
 	else
 		map_single_talitos_ptr(dev, &desc->ptr[5],
 				       req_ctx->hw_context_size,
-				       req_ctx->hw_context, 0, DMA_FROM_DEVICE);
+				       req_ctx->hw_context, DMA_FROM_DEVICE);
 
 	/* last DWORD empty */
 	desc->ptr[6] = zero_entry;
 
+	if (is_sec1 && from_talitos_ptr_len(&desc->ptr[3], true) == 0)
+		talitos_handle_buggy_hash(ctx, edesc, &desc->ptr[3]);
+
 	ret = talitos_submit(dev, ctx->ch, desc, callback, areq);
 	if (ret != -EINPROGRESS) {
 		common_nonsnoop_hash_unmap(dev, edesc, areq);
@@ -2561,6 +2812,7 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		break;
 	default:
 		dev_err(dev, "unknown algorithm type %d\n", t_alg->algt.type);
+		kfree(t_alg);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -2581,29 +2833,35 @@ static int talitos_probe_irq(struct platform_device *ofdev)
 	struct device_node *np = ofdev->dev.of_node;
 	struct talitos_private *priv = dev_get_drvdata(dev);
 	int err;
+	bool is_sec1 = has_ftr_sec1(priv);
 
 	priv->irq[0] = irq_of_parse_and_map(np, 0);
 	if (!priv->irq[0]) {
 		dev_err(dev, "failed to map irq\n");
 		return -EINVAL;
 	}
+	if (is_sec1) {
+		err = request_irq(priv->irq[0], talitos1_interrupt_4ch, 0,
+				  dev_driver_string(dev), dev);
+		goto primary_out;
+	}
 
 	priv->irq[1] = irq_of_parse_and_map(np, 1);
 
 	/* get the primary irq line */
 	if (!priv->irq[1]) {
-		err = request_irq(priv->irq[0], talitos_interrupt_4ch, 0,
+		err = request_irq(priv->irq[0], talitos2_interrupt_4ch, 0,
 				  dev_driver_string(dev), dev);
 		goto primary_out;
 	}
 
-	err = request_irq(priv->irq[0], talitos_interrupt_ch0_2, 0,
+	err = request_irq(priv->irq[0], talitos2_interrupt_ch0_2, 0,
 			  dev_driver_string(dev), dev);
 	if (err)
 		goto primary_out;
 
 	/* get the secondary irq line */
-	err = request_irq(priv->irq[1], talitos_interrupt_ch1_3, 0,
+	err = request_irq(priv->irq[1], talitos2_interrupt_ch1_3, 0,
 			  dev_driver_string(dev), dev);
 	if (err) {
 		dev_err(dev, "failed to request secondary irq\n");
@@ -2630,6 +2888,7 @@ static int talitos_probe(struct platform_device *ofdev)
 	struct talitos_private *priv;
 	const unsigned int *prop;
 	int i, err;
+	int stride;
 
 	priv = kzalloc(sizeof(struct talitos_private), GFP_KERNEL);
 	if (!priv)
@@ -2643,20 +2902,6 @@ static int talitos_probe(struct platform_device *ofdev)
 
 	spin_lock_init(&priv->reg_lock);
 
-	err = talitos_probe_irq(ofdev);
-	if (err)
-		goto err_out;
-
-	if (!priv->irq[1]) {
-		tasklet_init(&priv->done_task[0], talitos_done_4ch,
-			     (unsigned long)dev);
-	} else {
-		tasklet_init(&priv->done_task[0], talitos_done_ch0_2,
-			     (unsigned long)dev);
-		tasklet_init(&priv->done_task[1], talitos_done_ch1_3,
-			     (unsigned long)dev);
-	}
-
 	priv->reg = of_iomap(np, 0);
 	if (!priv->reg) {
 		dev_err(dev, "failed to of_iomap\n");
@@ -2696,6 +2941,53 @@ static int talitos_probe(struct platform_device *ofdev)
 				  TALITOS_FTR_SHA224_HWINIT |
 				  TALITOS_FTR_HMAC_OK;
 
+	if (of_device_is_compatible(np, "fsl,sec1.0"))
+		priv->features |= TALITOS_FTR_SEC1;
+
+	if (of_device_is_compatible(np, "fsl,sec1.2")) {
+		priv->reg_deu = priv->reg + TALITOS12_DEU;
+		priv->reg_aesu = priv->reg + TALITOS12_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS12_MDEU;
+		stride = TALITOS1_CH_STRIDE;
+	} else if (of_device_is_compatible(np, "fsl,sec1.0")) {
+		priv->reg_deu = priv->reg + TALITOS10_DEU;
+		priv->reg_aesu = priv->reg + TALITOS10_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS10_MDEU;
+		priv->reg_afeu = priv->reg + TALITOS10_AFEU;
+		priv->reg_rngu = priv->reg + TALITOS10_RNGU;
+		priv->reg_pkeu = priv->reg + TALITOS10_PKEU;
+		stride = TALITOS1_CH_STRIDE;
+	} else {
+		priv->reg_deu = priv->reg + TALITOS2_DEU;
+		priv->reg_aesu = priv->reg + TALITOS2_AESU;
+		priv->reg_mdeu = priv->reg + TALITOS2_MDEU;
+		priv->reg_afeu = priv->reg + TALITOS2_AFEU;
+		priv->reg_rngu = priv->reg + TALITOS2_RNGU;
+		priv->reg_pkeu = priv->reg + TALITOS2_PKEU;
+		priv->reg_keu = priv->reg + TALITOS2_KEU;
+		priv->reg_crcu = priv->reg + TALITOS2_CRCU;
+		stride = TALITOS2_CH_STRIDE;
+	}
+
+	err = talitos_probe_irq(ofdev);
+	if (err)
+		goto err_out;
+
+	if (of_device_is_compatible(np, "fsl,sec1.0")) {
+		tasklet_init(&priv->done_task[0], talitos1_done_4ch,
+			     (unsigned long)dev);
+	} else {
+		if (!priv->irq[1]) {
+			tasklet_init(&priv->done_task[0], talitos2_done_4ch,
+				     (unsigned long)dev);
+		} else {
+			tasklet_init(&priv->done_task[0], talitos2_done_ch0_2,
+				     (unsigned long)dev);
+			tasklet_init(&priv->done_task[1], talitos2_done_ch1_3,
+				     (unsigned long)dev);
+		}
+	}
+
 	priv->chan = kzalloc(sizeof(struct talitos_channel) *
 			     priv->num_channels, GFP_KERNEL);
 	if (!priv->chan) {
@@ -2707,7 +2999,7 @@ static int talitos_probe(struct platform_device *ofdev)
 	priv->fifo_len = roundup_pow_of_two(priv->chfifo_len);
 
 	for (i = 0; i < priv->num_channels; i++) {
-		priv->chan[i].reg = priv->reg + TALITOS_CH_STRIDE * (i + 1);
+		priv->chan[i].reg = priv->reg + stride * (i + 1);
 		if (!priv->irq[1] || !(i & 1))
 			priv->chan[i].reg += TALITOS_CH_BASE_OFFSET;
 
@@ -2794,9 +3086,16 @@ err_out:
 }
 
 static const struct of_device_id talitos_match[] = {
+#ifdef CONFIG_CRYPTO_DEV_TALITOS1
+	{
+		.compatible = "fsl,sec1.0",
+	},
+#endif
+#ifdef CONFIG_CRYPTO_DEV_TALITOS2
 	{
 		.compatible = "fsl,sec2.0",
 	},
+#endif
 	{},
 };
 MODULE_DEVICE_TABLE(of, talitos_match);
diff --git a/drivers/crypto/talitos.h b/drivers/crypto/talitos.h
index 61a14054aa39..314daf55e7f7 100644
--- a/drivers/crypto/talitos.h
+++ b/drivers/crypto/talitos.h
@@ -29,7 +29,8 @@
  */
 
 #define TALITOS_TIMEOUT 100000
-#define TALITOS_MAX_DATA_LEN 65535
+#define TALITOS1_MAX_DATA_LEN 32768
+#define TALITOS2_MAX_DATA_LEN 65535
 
 #define DESC_TYPE(desc_hdr) ((be32_to_cpu(desc_hdr) >> 3) & 0x1f)
 #define PRIMARY_EU(desc_hdr) ((be32_to_cpu(desc_hdr) >> 28) & 0xf)
@@ -37,9 +38,17 @@
 
 /* descriptor pointer entry */
 struct talitos_ptr {
-	__be16 len;     /* length */
-	u8 j_extent;    /* jump to sg link table and/or extent */
-	u8 eptr;        /* extended address */
+	union {
+		struct {		/* SEC2 format */
+			__be16 len;     /* length */
+			u8 j_extent;    /* jump to sg link table and/or extent*/
+			u8 eptr;        /* extended address */
+		};
+		struct {			/* SEC1 format */
+			__be16 res;
+			__be16 len1;	/* length */
+		};
+	};
 	__be32 ptr;     /* address */
 };
 
@@ -53,10 +62,16 @@ static const struct talitos_ptr zero_entry = {
 /* descriptor */
 struct talitos_desc {
 	__be32 hdr;                     /* header high bits */
-	__be32 hdr_lo;                  /* header low bits */
+	union {
+		__be32 hdr_lo;		/* header low bits */
+		__be32 hdr1;		/* header for SEC1 */
+	};
 	struct talitos_ptr ptr[7];      /* ptr/len pair array */
+	__be32 next_desc;		/* next descriptor (SEC1) */
 };
 
+#define TALITOS_DESC_SIZE	(sizeof(struct talitos_desc) - sizeof(__be32))
+
 /**
  * talitos_request - descriptor submission request
  * @desc: descriptor pointer (kernel virtual)
@@ -97,6 +112,14 @@ struct talitos_private {
 	struct device *dev;
 	struct platform_device *ofdev;
 	void __iomem *reg;
+	void __iomem *reg_deu;
+	void __iomem *reg_aesu;
+	void __iomem *reg_mdeu;
+	void __iomem *reg_afeu;
+	void __iomem *reg_rngu;
+	void __iomem *reg_pkeu;
+	void __iomem *reg_keu;
+	void __iomem *reg_crcu;
 	int irq[2];
 
 	/* SEC global registers lock  */
@@ -144,49 +167,80 @@ extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 #define TALITOS_FTR_HW_AUTH_CHECK 0x00000002
 #define TALITOS_FTR_SHA224_HWINIT 0x00000004
 #define TALITOS_FTR_HMAC_OK 0x00000008
+#define TALITOS_FTR_SEC1 0x00000010
+
+/*
+ * If both CONFIG_CRYPTO_DEV_TALITOS1 and CONFIG_CRYPTO_DEV_TALITOS2 are
+ * defined, we check the features which are set according to the device tree.
+ * Otherwise, we answer true or false directly
+ */
+static inline bool has_ftr_sec1(struct talitos_private *priv)
+{
+#if defined(CONFIG_CRYPTO_DEV_TALITOS1) && defined(CONFIG_CRYPTO_DEV_TALITOS2)
+	return priv->features & TALITOS_FTR_SEC1 ? true : false;
+#elif defined(CONFIG_CRYPTO_DEV_TALITOS1)
+	return true;
+#else
+	return false;
+#endif
+}
 
 /*
  * TALITOS_xxx_LO addresses point to the low data bits (32-63) of the register
  */
 
+#define ISR1_FORMAT(x)			(((x) << 28) | ((x) << 16))
+#define ISR2_FORMAT(x)			(((x) << 4) | (x))
+
 /* global register offset addresses */
 #define TALITOS_MCR			0x1030  /* master control register */
 #define   TALITOS_MCR_RCA0		(1 << 15) /* remap channel 0 */
 #define   TALITOS_MCR_RCA1		(1 << 14) /* remap channel 1 */
 #define   TALITOS_MCR_RCA2		(1 << 13) /* remap channel 2 */
 #define   TALITOS_MCR_RCA3		(1 << 12) /* remap channel 3 */
-#define   TALITOS_MCR_SWR		0x1     /* s/w reset */
+#define   TALITOS1_MCR_SWR		0x1000000     /* s/w reset */
+#define   TALITOS2_MCR_SWR		0x1     /* s/w reset */
 #define TALITOS_MCR_LO			0x1034
 #define TALITOS_IMR			0x1008  /* interrupt mask register */
-#define   TALITOS_IMR_INIT		0x100ff /* enable channel IRQs */
-#define   TALITOS_IMR_DONE		0x00055 /* done IRQs */
+/* enable channel IRQs */
+#define   TALITOS1_IMR_INIT		ISR1_FORMAT(0xf)
+#define   TALITOS1_IMR_DONE		ISR1_FORMAT(0x5) /* done IRQs */
+/* enable channel IRQs */
+#define   TALITOS2_IMR_INIT		(ISR2_FORMAT(0xf) | 0x10000)
+#define   TALITOS2_IMR_DONE		ISR1_FORMAT(0x5) /* done IRQs */
 #define TALITOS_IMR_LO			0x100C
-#define   TALITOS_IMR_LO_INIT		0x20000 /* allow RNGU error IRQs */
+#define   TALITOS1_IMR_LO_INIT		0x2000000 /* allow RNGU error IRQs */
+#define   TALITOS2_IMR_LO_INIT		0x20000 /* allow RNGU error IRQs */
 #define TALITOS_ISR			0x1010  /* interrupt status register */
-#define   TALITOS_ISR_4CHERR		0xaa    /* 4 channel errors mask */
-#define   TALITOS_ISR_4CHDONE		0x55    /* 4 channel done mask */
-#define   TALITOS_ISR_CH_0_2_ERR	0x22    /* channels 0, 2 errors mask */
-#define   TALITOS_ISR_CH_0_2_DONE	0x11    /* channels 0, 2 done mask */
-#define   TALITOS_ISR_CH_1_3_ERR	0x88    /* channels 1, 3 errors mask */
-#define   TALITOS_ISR_CH_1_3_DONE	0x44    /* channels 1, 3 done mask */
+#define   TALITOS1_ISR_4CHERR		ISR1_FORMAT(0xa) /* 4 ch errors mask */
+#define   TALITOS1_ISR_4CHDONE		ISR1_FORMAT(0x5) /* 4 ch done mask */
+#define   TALITOS1_ISR_TEA_ERR		0x00000040
+#define   TALITOS2_ISR_4CHERR		ISR2_FORMAT(0xa) /* 4 ch errors mask */
+#define   TALITOS2_ISR_4CHDONE		ISR2_FORMAT(0x5) /* 4 ch done mask */
+#define   TALITOS2_ISR_CH_0_2_ERR	ISR2_FORMAT(0x2) /* ch 0, 2 err mask */
+#define   TALITOS2_ISR_CH_0_2_DONE	ISR2_FORMAT(0x1) /* ch 0, 2 done mask */
+#define   TALITOS2_ISR_CH_1_3_ERR	ISR2_FORMAT(0x8) /* ch 1, 3 err mask */
+#define   TALITOS2_ISR_CH_1_3_DONE	ISR2_FORMAT(0x4) /* ch 1, 3 done mask */
 #define TALITOS_ISR_LO			0x1014
 #define TALITOS_ICR			0x1018  /* interrupt clear register */
 #define TALITOS_ICR_LO			0x101C
 
 /* channel register address stride */
 #define TALITOS_CH_BASE_OFFSET		0x1000	/* default channel map base */
-#define TALITOS_CH_STRIDE		0x100
+#define TALITOS1_CH_STRIDE		0x1000
+#define TALITOS2_CH_STRIDE		0x100
 
 /* channel configuration register  */
 #define TALITOS_CCCR			0x8
-#define   TALITOS_CCCR_CONT		0x2    /* channel continue */
-#define   TALITOS_CCCR_RESET		0x1    /* channel reset */
+#define   TALITOS2_CCCR_CONT		0x2    /* channel continue on SEC2 */
+#define   TALITOS2_CCCR_RESET		0x1    /* channel reset on SEC2 */
 #define TALITOS_CCCR_LO			0xc
 #define   TALITOS_CCCR_LO_IWSE		0x80   /* chan. ICCR writeback enab. */
 #define   TALITOS_CCCR_LO_EAE		0x20   /* extended address enable */
 #define   TALITOS_CCCR_LO_CDWE		0x10   /* chan. done writeback enab. */
 #define   TALITOS_CCCR_LO_NT		0x4    /* notification type */
 #define   TALITOS_CCCR_LO_CDIE		0x2    /* channel done IRQ enable */
+#define   TALITOS1_CCCR_LO_RESET	0x1    /* channel reset on SEC1 */
 
 /* CCPSR: channel pointer status register */
 #define TALITOS_CCPSR			0x10
@@ -224,37 +278,48 @@ extern int talitos_submit(struct device *dev, int ch, struct talitos_desc *desc,
 #define TALITOS_SCATTER			0xe0
 #define TALITOS_SCATTER_LO		0xe4
 
+/* execution unit registers base */
+#define TALITOS2_DEU			0x2000
+#define TALITOS2_AESU			0x4000
+#define TALITOS2_MDEU			0x6000
+#define TALITOS2_AFEU			0x8000
+#define TALITOS2_RNGU			0xa000
+#define TALITOS2_PKEU			0xc000
+#define TALITOS2_KEU			0xe000
+#define TALITOS2_CRCU			0xf000
+
+#define TALITOS12_AESU			0x4000
+#define TALITOS12_DEU			0x5000
+#define TALITOS12_MDEU			0x6000
+
+#define TALITOS10_AFEU			0x8000
+#define TALITOS10_DEU			0xa000
+#define TALITOS10_MDEU			0xc000
+#define TALITOS10_RNGU			0xe000
+#define TALITOS10_PKEU			0x10000
+#define TALITOS10_AESU			0x12000
+
 /* execution unit interrupt status registers */
-#define TALITOS_DEUISR			0x2030 /* DES unit */
-#define TALITOS_DEUISR_LO		0x2034
-#define TALITOS_AESUISR			0x4030 /* AES unit */
-#define TALITOS_AESUISR_LO		0x4034
-#define TALITOS_MDEUISR			0x6030 /* message digest unit */
-#define TALITOS_MDEUISR_LO		0x6034
-#define TALITOS_MDEUICR			0x6038 /* interrupt control */
-#define TALITOS_MDEUICR_LO		0x603c
+#define TALITOS_EUDSR			0x10	/* data size */
+#define TALITOS_EUDSR_LO		0x14
+#define TALITOS_EURCR			0x18 /* reset control*/
+#define TALITOS_EURCR_LO		0x1c
+#define TALITOS_EUSR			0x28 /* rng status */
+#define TALITOS_EUSR_LO			0x2c
+#define TALITOS_EUISR			0x30
+#define TALITOS_EUISR_LO		0x34
+#define TALITOS_EUICR			0x38 /* int. control */
+#define TALITOS_EUICR_LO		0x3c
+#define TALITOS_EU_FIFO			0x800 /* output FIFO */
+#define TALITOS_EU_FIFO_LO		0x804 /* output FIFO */
+/* DES unit */
+#define   TALITOS1_DEUICR_KPE		0x00200000 /* Key Parity Error */
+/* message digest unit */
 #define   TALITOS_MDEUICR_LO_ICE	0x4000 /* integrity check IRQ enable */
-#define TALITOS_AFEUISR			0x8030 /* arc4 unit */
-#define TALITOS_AFEUISR_LO		0x8034
-#define TALITOS_RNGUISR			0xa030 /* random number unit */
-#define TALITOS_RNGUISR_LO		0xa034
-#define TALITOS_RNGUSR			0xa028 /* rng status */
-#define TALITOS_RNGUSR_LO		0xa02c
+/* random number unit */
 #define   TALITOS_RNGUSR_LO_RD		0x1	/* reset done */
 #define   TALITOS_RNGUSR_LO_OFL		0xff0000/* output FIFO length */
-#define TALITOS_RNGUDSR			0xa010	/* data size */
-#define TALITOS_RNGUDSR_LO		0xa014
-#define TALITOS_RNGU_FIFO		0xa800	/* output FIFO */
-#define TALITOS_RNGU_FIFO_LO		0xa804	/* output FIFO */
-#define TALITOS_RNGURCR			0xa018	/* reset control */
-#define TALITOS_RNGURCR_LO		0xa01c
 #define   TALITOS_RNGURCR_LO_SR		0x1	/* software reset */
-#define TALITOS_PKEUISR			0xc030 /* public key unit */
-#define TALITOS_PKEUISR_LO		0xc034
-#define TALITOS_KEUISR			0xe030 /* kasumi unit */
-#define TALITOS_KEUISR_LO		0xe034
-#define TALITOS_CRCUISR			0xf030 /* cyclic redundancy check unit*/
-#define TALITOS_CRCUISR_LO		0xf034
 
 #define TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256	0x28
 #define TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512		0x48
diff --git a/drivers/crypto/ux500/Kconfig b/drivers/crypto/ux500/Kconfig
index b35e5c4b025a..30796441b0a6 100644
--- a/drivers/crypto/ux500/Kconfig
+++ b/drivers/crypto/ux500/Kconfig
@@ -7,6 +7,8 @@
 config CRYPTO_DEV_UX500_CRYP
 	tristate "UX500 crypto driver for CRYP block"
 	depends on CRYPTO_DEV_UX500
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
 	select CRYPTO_DES
 	help
         This selects the crypto driver for the UX500_CRYP hardware. It supports
@@ -16,7 +18,6 @@ config CRYPTO_DEV_UX500_HASH
         tristate "UX500 crypto driver for HASH block"
         depends on CRYPTO_DEV_UX500
         select CRYPTO_HASH
-        select CRYPTO_HMAC
         help
           This selects the hash driver for the UX500_HASH hardware.
           Depends on UX500/STM DMA if running in DMA mode.
@@ -24,7 +25,6 @@ config CRYPTO_DEV_UX500_HASH
 config CRYPTO_DEV_UX500_DEBUG
 	bool "Activate ux500 platform debug-mode for crypto and hash block"
 	depends on CRYPTO_DEV_UX500_CRYP || CRYPTO_DEV_UX500_HASH
-	default n
 	help
 	  Say Y if you want to add debug prints to ux500_hash and
 	  ux500_cryp devices.
diff --git a/drivers/crypto/vmx/Kconfig b/drivers/crypto/vmx/Kconfig
index 771babf16aa0..89d8208d9851 100644
--- a/drivers/crypto/vmx/Kconfig
+++ b/drivers/crypto/vmx/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_VMX_ENCRYPT
 	tristate "Encryption acceleration support on P8 CPU"
-	depends on PPC64 && CRYPTO_DEV_VMX
+	depends on CRYPTO_DEV_VMX
 	default y
 	help
 	  Support for VMX cryptographic acceleration instructions on Power8 CPU.
diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile
index c699c6e6c82e..d28ab96a2475 100644
--- a/drivers/crypto/vmx/Makefile
+++ b/drivers/crypto/vmx/Makefile
@@ -4,7 +4,7 @@ vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o gha
 ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
 TARGET := linux-ppc64le
 else
-TARGET := linux-pcc64
+TARGET := linux-ppc64
 endif
 
 quiet_cmd_perl = PERL $@
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index ab300ea19434..e79e567e43aa 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -30,110 +30,118 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_ctx {
-    struct crypto_cipher *fallback;
-    struct aes_key enc_key;
-    struct aes_key dec_key;
+	struct crypto_cipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
 };
 
 static int p8_aes_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_cipher *fallback;
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_cipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_cipher_set_flags(fallback,
-            crypto_cipher_get_flags((struct crypto_cipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_cipher *fallback;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback = crypto_alloc_cipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_cipher_set_flags(fallback,
+				crypto_cipher_get_flags((struct
+							 crypto_cipher *)
+							tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_cipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_cipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			 unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
-    pagefault_enable();
-    
-    ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	int ret;
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (in_interrupt()) {
-        crypto_cipher_encrypt_one(ctx->fallback, dst, src);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-        aes_p8_encrypt(src, dst, &ctx->enc_key);
-        pagefault_enable();
-    }
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (in_interrupt()) {
+		crypto_cipher_encrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		aes_p8_encrypt(src, dst, &ctx->enc_key);
+		pagefault_enable();
+		preempt_enable();
+	}
 }
 
 static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
-    struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (in_interrupt()) {
-        crypto_cipher_decrypt_one(ctx->fallback, dst, src);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-        aes_p8_decrypt(src, dst, &ctx->dec_key);
-        pagefault_enable();
-    }
+	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (in_interrupt()) {
+		crypto_cipher_decrypt_one(ctx->fallback, dst, src);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+		aes_p8_decrypt(src, dst, &ctx->dec_key);
+		pagefault_enable();
+		preempt_enable();
+	}
 }
 
 struct crypto_alg p8_aes_alg = {
-    .cra_name = "aes",
-    .cra_driver_name = "p8_aes",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = NULL,
-    .cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = AES_BLOCK_SIZE,
-    .cra_ctxsize = sizeof(struct p8_aes_ctx),
-    .cra_init = p8_aes_init,
-    .cra_exit = p8_aes_exit,
-    .cra_cipher = {
-        .cia_min_keysize = AES_MIN_KEY_SIZE,
-        .cia_max_keysize = AES_MAX_KEY_SIZE,
-        .cia_setkey = p8_aes_setkey,
-        .cia_encrypt = p8_aes_encrypt,
-        .cia_decrypt = p8_aes_decrypt,
-    },
+	.cra_name = "aes",
+	.cra_driver_name = "p8_aes",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = NULL,
+	.cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_ctx),
+	.cra_init = p8_aes_init,
+	.cra_exit = p8_aes_exit,
+	.cra_cipher = {
+		       .cia_min_keysize = AES_MIN_KEY_SIZE,
+		       .cia_max_keysize = AES_MAX_KEY_SIZE,
+		       .cia_setkey = p8_aes_setkey,
+		       .cia_encrypt = p8_aes_encrypt,
+		       .cia_decrypt = p8_aes_decrypt,
+	},
 };
-
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index 1a559b7dddb5..7299995c78ec 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -31,154 +31,168 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_cbc_ctx {
-    struct crypto_blkcipher *fallback;
-    struct aes_key enc_key;
-    struct aes_key dec_key;
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
+	struct aes_key dec_key;
 };
 
 static int p8_aes_cbc_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_blkcipher *fallback;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_blkcipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_blkcipher_set_flags(fallback,
-            crypto_blkcipher_get_flags((struct crypto_blkcipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+	    crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_cbc_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_blkcipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			     unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
-    pagefault_enable();
-
-    ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	int ret;
+	struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	pagefault_enable();
+	preempt_enable();
+
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt(desc, &walk);
-        while ((nbytes = walk.nbytes)) {
-			aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
-				nbytes & AES_BLOCK_MASK, &ctx->enc_key, walk.iv, 1);
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_cbc_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt(desc, &walk);
+		while ((nbytes = walk.nbytes)) {
+			aes_p8_cbc_encrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   nbytes & AES_BLOCK_MASK,
+					   &ctx->enc_key, walk.iv, 1);
 			nbytes &= AES_BLOCK_SIZE - 1;
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+		}
 
-        pagefault_enable();
-    }
+		pagefault_enable();
+		preempt_enable();
+	}
 
-    return ret;
+	return ret;
 }
 
 static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			      struct scatterlist *dst,
+			      struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_cbc_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        pagefault_disable();
-        enable_kernel_altivec();
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt(desc, &walk);
-        while ((nbytes = walk.nbytes)) {
-			aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
-				nbytes & AES_BLOCK_MASK, &ctx->dec_key, walk.iv, 0);
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_cbc_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_decrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		preempt_disable();
+		pagefault_disable();
+		enable_kernel_altivec();
+
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt(desc, &walk);
+		while ((nbytes = walk.nbytes)) {
+			aes_p8_cbc_encrypt(walk.src.virt.addr,
+					   walk.dst.virt.addr,
+					   nbytes & AES_BLOCK_MASK,
+					   &ctx->dec_key, walk.iv, 0);
 			nbytes &= AES_BLOCK_SIZE - 1;
 			ret = blkcipher_walk_done(desc, &walk, nbytes);
 		}
 
-        pagefault_enable();
-    }
+		pagefault_enable();
+		preempt_enable();
+	}
 
-    return ret;
+	return ret;
 }
 
 
 struct crypto_alg p8_aes_cbc_alg = {
-    .cra_name = "cbc(aes)",
-    .cra_driver_name = "p8_aes_cbc",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = &crypto_blkcipher_type,
-    .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = AES_BLOCK_SIZE,
-    .cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
-    .cra_init = p8_aes_cbc_init,
-    .cra_exit = p8_aes_cbc_exit,
-    .cra_blkcipher = {
-        .ivsize = 0,
-        .min_keysize = AES_MIN_KEY_SIZE,
-        .max_keysize = AES_MAX_KEY_SIZE,
-        .setkey = p8_aes_cbc_setkey,
-        .encrypt = p8_aes_cbc_encrypt,
-        .decrypt = p8_aes_cbc_decrypt,
-    },
+	.cra_name = "cbc(aes)",
+	.cra_driver_name = "p8_aes_cbc",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct p8_aes_cbc_ctx),
+	.cra_init = p8_aes_cbc_init,
+	.cra_exit = p8_aes_cbc_exit,
+	.cra_blkcipher = {
+			  .ivsize = 0,
+			  .min_keysize = AES_MIN_KEY_SIZE,
+			  .max_keysize = AES_MAX_KEY_SIZE,
+			  .setkey = p8_aes_cbc_setkey,
+			  .encrypt = p8_aes_cbc_encrypt,
+			  .decrypt = p8_aes_cbc_decrypt,
+	},
 };
-
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 96dbee4bf4a6..7adae42a7b79 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -30,138 +30,147 @@
 #include "aesp8-ppc.h"
 
 struct p8_aes_ctr_ctx {
-    struct crypto_blkcipher *fallback;
-    struct aes_key enc_key;
+	struct crypto_blkcipher *fallback;
+	struct aes_key enc_key;
 };
 
 static int p8_aes_ctr_init(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_blkcipher *fallback;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_blkcipher(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
-
-    crypto_blkcipher_set_flags(fallback,
-            crypto_blkcipher_get_flags((struct crypto_blkcipher *) tfm));
-    ctx->fallback = fallback;
-
-    return 0;
+	const char *alg;
+	struct crypto_blkcipher *fallback;
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback =
+	    crypto_alloc_blkcipher(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name((struct crypto_tfm *) fallback));
+
+	crypto_blkcipher_set_flags(
+		fallback,
+		crypto_blkcipher_get_flags((struct crypto_blkcipher *)tfm));
+	ctx->fallback = fallback;
+
+	return 0;
 }
 
 static void p8_aes_ctr_exit(struct crypto_tfm *tfm)
 {
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_blkcipher(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_blkcipher(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key,
-    unsigned int keylen)
+			     unsigned int keylen)
 {
-    int ret;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+	struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    pagefault_disable();
-    enable_kernel_altivec();
-    ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-    pagefault_enable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
+	pagefault_enable();
 
-    ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
-    return ret;
+	ret += crypto_blkcipher_setkey(ctx->fallback, key, keylen);
+	return ret;
 }
 
 static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx,
-                struct blkcipher_walk *walk)
+			     struct blkcipher_walk *walk)
 {
-    u8 *ctrblk = walk->iv;
-    u8 keystream[AES_BLOCK_SIZE];
-    u8 *src = walk->src.virt.addr;
-    u8 *dst = walk->dst.virt.addr;
-    unsigned int nbytes = walk->nbytes;
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
-    pagefault_enable();
-
-    crypto_xor(keystream, src, nbytes);
-    memcpy(dst, keystream, nbytes);
-    crypto_inc(ctrblk, AES_BLOCK_SIZE);
+	u8 *ctrblk = walk->iv;
+	u8 keystream[AES_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	pagefault_disable();
+	enable_kernel_altivec();
+	aes_p8_encrypt(ctrblk, keystream, &ctx->enc_key);
+	pagefault_enable();
+
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
 static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
-    struct scatterlist *dst, struct scatterlist *src,
-    unsigned int nbytes)
+			    struct scatterlist *dst,
+			    struct scatterlist *src, unsigned int nbytes)
 {
-    int ret;
-    struct blkcipher_walk walk;
-    struct p8_aes_ctr_ctx *ctx = crypto_tfm_ctx(
-            crypto_blkcipher_tfm(desc->tfm));
-    struct blkcipher_desc fallback_desc = {
-        .tfm = ctx->fallback,
-        .info = desc->info,
-        .flags = desc->flags
-    };
-
-    if (in_interrupt()) {
-        ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src, nbytes);
-    } else {
-        blkcipher_walk_init(&walk, dst, src, nbytes);
-        ret = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
-        while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-            pagefault_disable();
-            enable_kernel_altivec();
-            aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr, walk.dst.virt.addr,
-                (nbytes & AES_BLOCK_MASK)/AES_BLOCK_SIZE, &ctx->enc_key, walk.iv);
-            pagefault_enable();
-
-            crypto_inc(walk.iv, AES_BLOCK_SIZE);
-            nbytes &= AES_BLOCK_SIZE - 1;
-            ret = blkcipher_walk_done(desc, &walk, nbytes);
-        }
-        if (walk.nbytes) {
-            p8_aes_ctr_final(ctx, &walk);
-            ret = blkcipher_walk_done(desc, &walk, 0);
-        }
-    }
-
-    return ret;
+	int ret;
+	struct blkcipher_walk walk;
+	struct p8_aes_ctr_ctx *ctx =
+		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
+	struct blkcipher_desc fallback_desc = {
+		.tfm = ctx->fallback,
+		.info = desc->info,
+		.flags = desc->flags
+	};
+
+	if (in_interrupt()) {
+		ret = crypto_blkcipher_encrypt(&fallback_desc, dst, src,
+					       nbytes);
+	} else {
+		blkcipher_walk_init(&walk, dst, src, nbytes);
+		ret = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+		while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+			pagefault_disable();
+			enable_kernel_altivec();
+			aes_p8_ctr32_encrypt_blocks(walk.src.virt.addr,
+						    walk.dst.virt.addr,
+						    (nbytes &
+						     AES_BLOCK_MASK) /
+						    AES_BLOCK_SIZE,
+						    &ctx->enc_key,
+						    walk.iv);
+			pagefault_enable();
+
+			crypto_inc(walk.iv, AES_BLOCK_SIZE);
+			nbytes &= AES_BLOCK_SIZE - 1;
+			ret = blkcipher_walk_done(desc, &walk, nbytes);
+		}
+		if (walk.nbytes) {
+			p8_aes_ctr_final(ctx, &walk);
+			ret = blkcipher_walk_done(desc, &walk, 0);
+		}
+	}
+
+	return ret;
 }
 
 struct crypto_alg p8_aes_ctr_alg = {
-    .cra_name = "ctr(aes)",
-    .cra_driver_name = "p8_aes_ctr",
-    .cra_module = THIS_MODULE,
-    .cra_priority = 1000,
-    .cra_type = &crypto_blkcipher_type,
-    .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
-    .cra_alignmask = 0,
-    .cra_blocksize = 1,
-    .cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
-    .cra_init = p8_aes_ctr_init,
-    .cra_exit = p8_aes_ctr_exit,
-    .cra_blkcipher = {
-        .ivsize = 0,
-        .min_keysize = AES_MIN_KEY_SIZE,
-        .max_keysize = AES_MAX_KEY_SIZE,
-        .setkey = p8_aes_ctr_setkey,
-        .encrypt = p8_aes_ctr_crypt,
-        .decrypt = p8_aes_ctr_crypt,
-    },
+	.cra_name = "ctr(aes)",
+	.cra_driver_name = "p8_aes_ctr",
+	.cra_module = THIS_MODULE,
+	.cra_priority = 1000,
+	.cra_type = &crypto_blkcipher_type,
+	.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK,
+	.cra_alignmask = 0,
+	.cra_blocksize = 1,
+	.cra_ctxsize = sizeof(struct p8_aes_ctr_ctx),
+	.cra_init = p8_aes_ctr_init,
+	.cra_exit = p8_aes_ctr_exit,
+	.cra_blkcipher = {
+			  .ivsize = 0,
+			  .min_keysize = AES_MIN_KEY_SIZE,
+			  .max_keysize = AES_MAX_KEY_SIZE,
+			  .setkey = p8_aes_ctr_setkey,
+			  .encrypt = p8_aes_ctr_crypt,
+			  .decrypt = p8_aes_ctr_crypt,
+	},
 };
diff --git a/drivers/crypto/vmx/aesp8-ppc.h b/drivers/crypto/vmx/aesp8-ppc.h
index e963945a83e1..4cd34ee54a94 100644
--- a/drivers/crypto/vmx/aesp8-ppc.h
+++ b/drivers/crypto/vmx/aesp8-ppc.h
@@ -4,17 +4,18 @@
 #define AES_BLOCK_MASK  (~(AES_BLOCK_SIZE-1))
 
 struct aes_key {
-    u8 key[AES_MAX_KEYLENGTH];
-    int rounds;
+	u8 key[AES_MAX_KEYLENGTH];
+	int rounds;
 };
 
 int aes_p8_set_encrypt_key(const u8 *userKey, const int bits,
-        struct aes_key *key);
+			   struct aes_key *key);
 int aes_p8_set_decrypt_key(const u8 *userKey, const int bits,
-        struct aes_key *key);
+			   struct aes_key *key);
 void aes_p8_encrypt(const u8 *in, u8 *out, const struct aes_key *key);
-void aes_p8_decrypt(const u8 *in, u8 *out,const struct aes_key *key);
+void aes_p8_decrypt(const u8 *in, u8 *out, const struct aes_key *key);
 void aes_p8_cbc_encrypt(const u8 *in, u8 *out, size_t len,
-		const struct aes_key *key, u8 *iv, const int enc);
+			const struct aes_key *key, u8 *iv, const int enc);
 void aes_p8_ctr32_encrypt_blocks(const u8 *in, u8 *out,
-        size_t len, const struct aes_key *key, const u8 *iv);
+				 size_t len, const struct aes_key *key,
+				 const u8 *iv);
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index d0ffe277af5c..b5e29002b666 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -39,176 +39,188 @@
 void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
 void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
 void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
-        const u8 *in,size_t len);
+		  const u8 *in, size_t len);
 
 struct p8_ghash_ctx {
-    u128 htable[16];
-    struct crypto_shash *fallback;
+	u128 htable[16];
+	struct crypto_shash *fallback;
 };
 
 struct p8_ghash_desc_ctx {
-    u64 shash[2];
-    u8 buffer[GHASH_DIGEST_SIZE];
-    int bytes;
-    struct shash_desc fallback_desc;
+	u64 shash[2];
+	u8 buffer[GHASH_DIGEST_SIZE];
+	int bytes;
+	struct shash_desc fallback_desc;
 };
 
 static int p8_ghash_init_tfm(struct crypto_tfm *tfm)
 {
-    const char *alg;
-    struct crypto_shash *fallback;
-    struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm);
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
-
-    if (!(alg = crypto_tfm_alg_name(tfm))) {
-        printk(KERN_ERR "Failed to get algorithm name.\n");
-        return -ENOENT;
-    }
-
-    fallback = crypto_alloc_shash(alg, 0 ,CRYPTO_ALG_NEED_FALLBACK);
-    if (IS_ERR(fallback)) {
-        printk(KERN_ERR "Failed to allocate transformation for '%s': %ld\n",
-                alg, PTR_ERR(fallback));
-        return PTR_ERR(fallback);
-    }
-    printk(KERN_INFO "Using '%s' as fallback implementation.\n",
-            crypto_tfm_alg_driver_name(crypto_shash_tfm(fallback)));
-
-    crypto_shash_set_flags(fallback,
-            crypto_shash_get_flags((struct crypto_shash *) tfm));
-    ctx->fallback = fallback;
-
-    shash_tfm->descsize = sizeof(struct p8_ghash_desc_ctx)
-        + crypto_shash_descsize(fallback);
-
-    return 0;
+	const char *alg;
+	struct crypto_shash *fallback;
+	struct crypto_shash *shash_tfm = __crypto_shash_cast(tfm);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!(alg = crypto_tfm_alg_name(tfm))) {
+		printk(KERN_ERR "Failed to get algorithm name.\n");
+		return -ENOENT;
+	}
+
+	fallback = crypto_alloc_shash(alg, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(fallback)) {
+		printk(KERN_ERR
+		       "Failed to allocate transformation for '%s': %ld\n",
+		       alg, PTR_ERR(fallback));
+		return PTR_ERR(fallback);
+	}
+	printk(KERN_INFO "Using '%s' as fallback implementation.\n",
+	       crypto_tfm_alg_driver_name(crypto_shash_tfm(fallback)));
+
+	crypto_shash_set_flags(fallback,
+			       crypto_shash_get_flags((struct crypto_shash
+						       *) tfm));
+	ctx->fallback = fallback;
+
+	shash_tfm->descsize = sizeof(struct p8_ghash_desc_ctx)
+	    + crypto_shash_descsize(fallback);
+
+	return 0;
 }
 
 static void p8_ghash_exit_tfm(struct crypto_tfm *tfm)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(tfm);
 
-    if (ctx->fallback) {
-        crypto_free_shash(ctx->fallback);
-        ctx->fallback = NULL;
-    }
+	if (ctx->fallback) {
+		crypto_free_shash(ctx->fallback);
+		ctx->fallback = NULL;
+	}
 }
 
 static int p8_ghash_init(struct shash_desc *desc)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    dctx->bytes = 0;
-    memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
-    dctx->fallback_desc.tfm = ctx->fallback;
-    dctx->fallback_desc.flags = desc->flags;
-    return crypto_shash_init(&dctx->fallback_desc);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->bytes = 0;
+	memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
+	dctx->fallback_desc.tfm = ctx->fallback;
+	dctx->fallback_desc.flags = desc->flags;
+	return crypto_shash_init(&dctx->fallback_desc);
 }
 
 static int p8_ghash_setkey(struct crypto_shash *tfm, const u8 *key,
-    unsigned int keylen)
+			   unsigned int keylen)
 {
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
-
-    if (keylen != GHASH_KEY_LEN)
-        return -EINVAL;
-
-    pagefault_disable();
-    enable_kernel_altivec();
-    enable_kernel_fp();
-    gcm_init_p8(ctx->htable, (const u64 *) key);
-    pagefault_enable();
-    return crypto_shash_setkey(ctx->fallback, key, keylen);
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(tfm));
+
+	if (keylen != GHASH_KEY_LEN)
+		return -EINVAL;
+
+	preempt_disable();
+	pagefault_disable();
+	enable_kernel_altivec();
+	enable_kernel_fp();
+	gcm_init_p8(ctx->htable, (const u64 *) key);
+	pagefault_enable();
+	preempt_enable();
+	return crypto_shash_setkey(ctx->fallback, key, keylen);
 }
 
 static int p8_ghash_update(struct shash_desc *desc,
-        const u8 *src, unsigned int srclen)
+			   const u8 *src, unsigned int srclen)
 {
-    unsigned int len;
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    if (IN_INTERRUPT) {
-        return crypto_shash_update(&dctx->fallback_desc, src, srclen);
-    } else {
-        if (dctx->bytes) {
-            if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
-                memcpy(dctx->buffer + dctx->bytes, src, srclen);
-                dctx->bytes += srclen;
-                return 0;
-            }
-            memcpy(dctx->buffer + dctx->bytes, src,
-                    GHASH_DIGEST_SIZE - dctx->bytes);
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
-                    GHASH_DIGEST_SIZE);
-            pagefault_enable();
-            src += GHASH_DIGEST_SIZE - dctx->bytes;
-            srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
-            dctx->bytes = 0;
-        }
-        len = srclen & ~(GHASH_DIGEST_SIZE - 1);
-        if (len) {
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
-            pagefault_enable();
-            src += len;
-            srclen -= len;
-        }
-        if (srclen) {
-            memcpy(dctx->buffer, src, srclen);
-            dctx->bytes = srclen;
-        }
-        return 0;
-    }
+	unsigned int len;
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (IN_INTERRUPT) {
+		return crypto_shash_update(&dctx->fallback_desc, src,
+					   srclen);
+	} else {
+		if (dctx->bytes) {
+			if (dctx->bytes + srclen < GHASH_DIGEST_SIZE) {
+				memcpy(dctx->buffer + dctx->bytes, src,
+				       srclen);
+				dctx->bytes += srclen;
+				return 0;
+			}
+			memcpy(dctx->buffer + dctx->bytes, src,
+			       GHASH_DIGEST_SIZE - dctx->bytes);
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable,
+				     dctx->buffer, GHASH_DIGEST_SIZE);
+			pagefault_enable();
+			preempt_enable();
+			src += GHASH_DIGEST_SIZE - dctx->bytes;
+			srclen -= GHASH_DIGEST_SIZE - dctx->bytes;
+			dctx->bytes = 0;
+		}
+		len = srclen & ~(GHASH_DIGEST_SIZE - 1);
+		if (len) {
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable, src, len);
+			pagefault_enable();
+			preempt_enable();
+			src += len;
+			srclen -= len;
+		}
+		if (srclen) {
+			memcpy(dctx->buffer, src, srclen);
+			dctx->bytes = srclen;
+		}
+		return 0;
+	}
 }
 
 static int p8_ghash_final(struct shash_desc *desc, u8 *out)
 {
-    int i;
-    struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
-    struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
-    if (IN_INTERRUPT) {
-        return crypto_shash_final(&dctx->fallback_desc, out);
-    } else {
-        if (dctx->bytes) {
-            for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
-                dctx->buffer[i] = 0;
-            pagefault_disable();
-            enable_kernel_altivec();
-            enable_kernel_fp();
-            gcm_ghash_p8(dctx->shash, ctx->htable, dctx->buffer,
-                    GHASH_DIGEST_SIZE);
-            pagefault_enable();
-            dctx->bytes = 0;
-        }
-        memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
-        return 0;
-    }
+	int i;
+	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
+	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (IN_INTERRUPT) {
+		return crypto_shash_final(&dctx->fallback_desc, out);
+	} else {
+		if (dctx->bytes) {
+			for (i = dctx->bytes; i < GHASH_DIGEST_SIZE; i++)
+				dctx->buffer[i] = 0;
+			preempt_disable();
+			pagefault_disable();
+			enable_kernel_altivec();
+			enable_kernel_fp();
+			gcm_ghash_p8(dctx->shash, ctx->htable,
+				     dctx->buffer, GHASH_DIGEST_SIZE);
+			pagefault_enable();
+			preempt_enable();
+			dctx->bytes = 0;
+		}
+		memcpy(out, dctx->shash, GHASH_DIGEST_SIZE);
+		return 0;
+	}
 }
 
 struct shash_alg p8_ghash_alg = {
-    .digestsize = GHASH_DIGEST_SIZE,
-    .init       = p8_ghash_init,
-    .update     = p8_ghash_update,
-    .final      = p8_ghash_final,
-    .setkey     = p8_ghash_setkey,
-    .descsize   = sizeof(struct p8_ghash_desc_ctx),
-    .base       = {
-        .cra_name = "ghash",
-        .cra_driver_name = "p8_ghash",
-        .cra_priority = 1000,
-        .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
-        .cra_blocksize = GHASH_BLOCK_SIZE,
-        .cra_ctxsize = sizeof(struct p8_ghash_ctx),
-        .cra_module = THIS_MODULE,
-        .cra_init = p8_ghash_init_tfm,
-        .cra_exit = p8_ghash_exit_tfm,
-    },
+	.digestsize = GHASH_DIGEST_SIZE,
+	.init = p8_ghash_init,
+	.update = p8_ghash_update,
+	.final = p8_ghash_final,
+	.setkey = p8_ghash_setkey,
+	.descsize = sizeof(struct p8_ghash_desc_ctx),
+	.base = {
+		 .cra_name = "ghash",
+		 .cra_driver_name = "p8_ghash",
+		 .cra_priority = 1000,
+		 .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
+		 .cra_blocksize = GHASH_BLOCK_SIZE,
+		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
+		 .cra_module = THIS_MODULE,
+		 .cra_init = p8_ghash_init_tfm,
+		 .cra_exit = p8_ghash_exit_tfm,
+	},
 };
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index 44d8d5cfe40d..e163d5770438 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -32,57 +32,57 @@ extern struct crypto_alg p8_aes_alg;
 extern struct crypto_alg p8_aes_cbc_alg;
 extern struct crypto_alg p8_aes_ctr_alg;
 static struct crypto_alg *algs[] = {
-    &p8_aes_alg,
-    &p8_aes_cbc_alg,
-    &p8_aes_ctr_alg,
-    NULL,
+	&p8_aes_alg,
+	&p8_aes_cbc_alg,
+	&p8_aes_ctr_alg,
+	NULL,
 };
 
 int __init p8_init(void)
 {
-    int ret = 0;
-    struct crypto_alg **alg_it;
+	int ret = 0;
+	struct crypto_alg **alg_it;
 
-    if (!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
-        return -ENODEV;
+	if (!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_VEC_CRYPTO))
+		return -ENODEV;
 
-    for (alg_it = algs; *alg_it; alg_it++) {
-        ret = crypto_register_alg(*alg_it);
-        printk(KERN_INFO "crypto_register_alg '%s' = %d\n",
-                (*alg_it)->cra_name, ret);
-        if (ret) {
-            for (alg_it--; alg_it >= algs; alg_it--)
-                crypto_unregister_alg(*alg_it);
-            break;
-        }
-    }
-    if (ret)
-        return ret;
+	for (alg_it = algs; *alg_it; alg_it++) {
+		ret = crypto_register_alg(*alg_it);
+		printk(KERN_INFO "crypto_register_alg '%s' = %d\n",
+		       (*alg_it)->cra_name, ret);
+		if (ret) {
+			for (alg_it--; alg_it >= algs; alg_it--)
+				crypto_unregister_alg(*alg_it);
+			break;
+		}
+	}
+	if (ret)
+		return ret;
 
-    ret = crypto_register_shash(&p8_ghash_alg);
-    if (ret) {
-        for (alg_it = algs; *alg_it; alg_it++)
-            crypto_unregister_alg(*alg_it);
-    }
-    return ret;
+	ret = crypto_register_shash(&p8_ghash_alg);
+	if (ret) {
+		for (alg_it = algs; *alg_it; alg_it++)
+			crypto_unregister_alg(*alg_it);
+	}
+	return ret;
 }
 
 void __exit p8_exit(void)
 {
-    struct crypto_alg **alg_it;
+	struct crypto_alg **alg_it;
 
-    for (alg_it = algs; *alg_it; alg_it++) {
-        printk(KERN_INFO "Removing '%s'\n", (*alg_it)->cra_name);
-        crypto_unregister_alg(*alg_it);
-    }
-    crypto_unregister_shash(&p8_ghash_alg);
+	for (alg_it = algs; *alg_it; alg_it++) {
+		printk(KERN_INFO "Removing '%s'\n", (*alg_it)->cra_name);
+		crypto_unregister_alg(*alg_it);
+	}
+	crypto_unregister_shash(&p8_ghash_alg);
 }
 
 module_init(p8_init);
 module_exit(p8_exit);
 
 MODULE_AUTHOR("Marcelo Cerri<mhcerri@br.ibm.com>");
-MODULE_DESCRIPTION("IBM VMX cryptogaphic acceleration instructions support on Power 8");
+MODULE_DESCRIPTION("IBM VMX cryptographic acceleration instructions "
+		   "support on Power 8");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("1.0.0");
-
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 933e4b338459..7992164ea9ec 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -174,6 +174,8 @@
 #define AT_XDMAC_MBR_UBC_NDV3		(0x3 << 27)	/* Next Descriptor View 3 */
 
 #define AT_XDMAC_MAX_CHAN	0x20
+#define AT_XDMAC_MAX_CSIZE	16	/* 16 data */
+#define AT_XDMAC_MAX_DWIDTH	8	/* 64 bits */
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
 	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -192,20 +194,17 @@ struct at_xdmac_chan {
 	struct dma_chan			chan;
 	void __iomem			*ch_regs;
 	u32				mask;		/* Channel Mask */
-	u32				cfg[2];		/* Channel Configuration Register */
-	#define	AT_XDMAC_DEV_TO_MEM_CFG	0		/* Predifined dev to mem channel conf */
-	#define	AT_XDMAC_MEM_TO_DEV_CFG	1		/* Predifined mem to dev channel conf */
+	u32				cfg;		/* Channel Configuration Register */
 	u8				perid;		/* Peripheral ID */
 	u8				perif;		/* Peripheral Interface */
 	u8				memif;		/* Memory Interface */
-	u32				per_src_addr;
-	u32				per_dst_addr;
 	u32				save_cc;
 	u32				save_cim;
 	u32				save_cnda;
 	u32				save_cndc;
 	unsigned long			status;
 	struct tasklet_struct		tasklet;
+	struct dma_slave_config		sconfig;
 
 	spinlock_t			lock;
 
@@ -415,8 +414,9 @@ static dma_cookie_t at_xdmac_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct at_xdmac_desc	*desc = txd_to_at_desc(tx);
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(tx->chan);
 	dma_cookie_t		cookie;
+	unsigned long		irqflags;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, irqflags);
 	cookie = dma_cookie_assign(tx);
 
 	dev_vdbg(chan2dev(tx->chan), "%s: atchan 0x%p, add desc 0x%p to xfers_list\n",
@@ -425,7 +425,7 @@ static dma_cookie_t at_xdmac_tx_submit(struct dma_async_tx_descriptor *tx)
 	if (list_is_singular(&atchan->xfers_list))
 		at_xdmac_start_xfer(atchan, desc);
 
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, irqflags);
 	return cookie;
 }
 
@@ -494,61 +494,94 @@ static struct dma_chan *at_xdmac_xlate(struct of_phandle_args *dma_spec,
 	return chan;
 }
 
+static int at_xdmac_compute_chan_conf(struct dma_chan *chan,
+				      enum dma_transfer_direction direction)
+{
+	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
+	int			csize, dwidth;
+
+	if (direction == DMA_DEV_TO_MEM) {
+		atchan->cfg =
+			AT91_XDMAC_DT_PERID(atchan->perid)
+			| AT_XDMAC_CC_DAM_INCREMENTED_AM
+			| AT_XDMAC_CC_SAM_FIXED_AM
+			| AT_XDMAC_CC_DIF(atchan->memif)
+			| AT_XDMAC_CC_SIF(atchan->perif)
+			| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+			| AT_XDMAC_CC_DSYNC_PER2MEM
+			| AT_XDMAC_CC_MBSIZE_SIXTEEN
+			| AT_XDMAC_CC_TYPE_PER_TRAN;
+		csize = ffs(atchan->sconfig.src_maxburst) - 1;
+		if (csize < 0) {
+			dev_err(chan2dev(chan), "invalid src maxburst value\n");
+			return -EINVAL;
+		}
+		atchan->cfg |= AT_XDMAC_CC_CSIZE(csize);
+		dwidth = ffs(atchan->sconfig.src_addr_width) - 1;
+		if (dwidth < 0) {
+			dev_err(chan2dev(chan), "invalid src addr width value\n");
+			return -EINVAL;
+		}
+		atchan->cfg |= AT_XDMAC_CC_DWIDTH(dwidth);
+	} else if (direction == DMA_MEM_TO_DEV) {
+		atchan->cfg =
+			AT91_XDMAC_DT_PERID(atchan->perid)
+			| AT_XDMAC_CC_DAM_FIXED_AM
+			| AT_XDMAC_CC_SAM_INCREMENTED_AM
+			| AT_XDMAC_CC_DIF(atchan->perif)
+			| AT_XDMAC_CC_SIF(atchan->memif)
+			| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
+			| AT_XDMAC_CC_DSYNC_MEM2PER
+			| AT_XDMAC_CC_MBSIZE_SIXTEEN
+			| AT_XDMAC_CC_TYPE_PER_TRAN;
+		csize = ffs(atchan->sconfig.dst_maxburst) - 1;
+		if (csize < 0) {
+			dev_err(chan2dev(chan), "invalid src maxburst value\n");
+			return -EINVAL;
+		}
+		atchan->cfg |= AT_XDMAC_CC_CSIZE(csize);
+		dwidth = ffs(atchan->sconfig.dst_addr_width) - 1;
+		if (dwidth < 0) {
+			dev_err(chan2dev(chan), "invalid dst addr width value\n");
+			return -EINVAL;
+		}
+		atchan->cfg |= AT_XDMAC_CC_DWIDTH(dwidth);
+	}
+
+	dev_dbg(chan2dev(chan),	"%s: cfg=0x%08x\n", __func__, atchan->cfg);
+
+	return 0;
+}
+
+/*
+ * Only check that maxburst and addr width values are supported by the
+ * the controller but not that the configuration is good to perform the
+ * transfer since we don't know the direction at this stage.
+ */
+static int at_xdmac_check_slave_config(struct dma_slave_config *sconfig)
+{
+	if ((sconfig->src_maxburst > AT_XDMAC_MAX_CSIZE)
+	    || (sconfig->dst_maxburst > AT_XDMAC_MAX_CSIZE))
+		return -EINVAL;
+
+	if ((sconfig->src_addr_width > AT_XDMAC_MAX_DWIDTH)
+	    || (sconfig->dst_addr_width > AT_XDMAC_MAX_DWIDTH))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int at_xdmac_set_slave_config(struct dma_chan *chan,
 				      struct dma_slave_config *sconfig)
 {
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
-	u8 dwidth;
-	int csize;
 
-	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] =
-		AT91_XDMAC_DT_PERID(atchan->perid)
-		| AT_XDMAC_CC_DAM_INCREMENTED_AM
-		| AT_XDMAC_CC_SAM_FIXED_AM
-		| AT_XDMAC_CC_DIF(atchan->memif)
-		| AT_XDMAC_CC_SIF(atchan->perif)
-		| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
-		| AT_XDMAC_CC_DSYNC_PER2MEM
-		| AT_XDMAC_CC_MBSIZE_SIXTEEN
-		| AT_XDMAC_CC_TYPE_PER_TRAN;
-	csize = at_xdmac_csize(sconfig->src_maxburst);
-	if (csize < 0) {
-		dev_err(chan2dev(chan), "invalid src maxburst value\n");
+	if (at_xdmac_check_slave_config(sconfig)) {
+		dev_err(chan2dev(chan), "invalid slave configuration\n");
 		return -EINVAL;
 	}
-	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_CSIZE(csize);
-	dwidth = ffs(sconfig->src_addr_width) - 1;
-	atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
-
-
-	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] =
-		AT91_XDMAC_DT_PERID(atchan->perid)
-		| AT_XDMAC_CC_DAM_FIXED_AM
-		| AT_XDMAC_CC_SAM_INCREMENTED_AM
-		| AT_XDMAC_CC_DIF(atchan->perif)
-		| AT_XDMAC_CC_SIF(atchan->memif)
-		| AT_XDMAC_CC_SWREQ_HWR_CONNECTED
-		| AT_XDMAC_CC_DSYNC_MEM2PER
-		| AT_XDMAC_CC_MBSIZE_SIXTEEN
-		| AT_XDMAC_CC_TYPE_PER_TRAN;
-	csize = at_xdmac_csize(sconfig->dst_maxburst);
-	if (csize < 0) {
-		dev_err(chan2dev(chan), "invalid src maxburst value\n");
-		return -EINVAL;
-	}
-	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_CSIZE(csize);
-	dwidth = ffs(sconfig->dst_addr_width) - 1;
-	atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG] |= AT_XDMAC_CC_DWIDTH(dwidth);
-
-	/* Src and dst addr are needed to configure the link list descriptor. */
-	atchan->per_src_addr = sconfig->src_addr;
-	atchan->per_dst_addr = sconfig->dst_addr;
 
-	dev_dbg(chan2dev(chan),
-		"%s: cfg[dev2mem]=0x%08x, cfg[mem2dev]=0x%08x, per_src_addr=0x%08x, per_dst_addr=0x%08x\n",
-		__func__, atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG],
-		atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG],
-		atchan->per_src_addr, atchan->per_dst_addr);
+	memcpy(&atchan->sconfig, sconfig, sizeof(atchan->sconfig));
 
 	return 0;
 }
@@ -563,6 +596,8 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct scatterlist	*sg;
 	int			i;
 	unsigned int		xfer_size = 0;
+	unsigned long		irqflags;
+	struct dma_async_tx_descriptor	*ret = NULL;
 
 	if (!sgl)
 		return NULL;
@@ -578,7 +613,10 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		 flags);
 
 	/* Protect dma_sconfig field that can be modified by set_slave_conf. */
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, irqflags);
+
+	if (at_xdmac_compute_chan_conf(chan, direction))
+		goto spin_unlock;
 
 	/* Prepare descriptors. */
 	for_each_sg(sgl, sg, sg_len, i) {
@@ -589,8 +627,7 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		mem = sg_dma_address(sg);
 		if (unlikely(!len)) {
 			dev_err(chan2dev(chan), "sg data length is zero\n");
-			spin_unlock_bh(&atchan->lock);
-			return NULL;
+			goto spin_unlock;
 		}
 		dev_dbg(chan2dev(chan), "%s: * sg%d len=%u, mem=0x%08x\n",
 			 __func__, i, len, mem);
@@ -600,20 +637,18 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			dev_err(chan2dev(chan), "can't get descriptor\n");
 			if (first)
 				list_splice_init(&first->descs_list, &atchan->free_descs_list);
-			spin_unlock_bh(&atchan->lock);
-			return NULL;
+			goto spin_unlock;
 		}
 
 		/* Linked list descriptor setup. */
 		if (direction == DMA_DEV_TO_MEM) {
-			desc->lld.mbr_sa = atchan->per_src_addr;
+			desc->lld.mbr_sa = atchan->sconfig.src_addr;
 			desc->lld.mbr_da = mem;
-			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
 		} else {
 			desc->lld.mbr_sa = mem;
-			desc->lld.mbr_da = atchan->per_dst_addr;
-			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
+		desc->lld.mbr_cfg = atchan->cfg;
 		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
 		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
 			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
@@ -645,13 +680,15 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		xfer_size += len;
 	}
 
-	spin_unlock_bh(&atchan->lock);
 
 	first->tx_dma_desc.flags = flags;
 	first->xfer_size = xfer_size;
 	first->direction = direction;
+	ret = &first->tx_dma_desc;
 
-	return &first->tx_dma_desc;
+spin_unlock:
+	spin_unlock_irqrestore(&atchan->lock, irqflags);
+	return ret;
 }
 
 static struct dma_async_tx_descriptor *
@@ -664,6 +701,7 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 	struct at_xdmac_desc	*first = NULL, *prev = NULL;
 	unsigned int		periods = buf_len / period_len;
 	int			i;
+	unsigned long		irqflags;
 
 	dev_dbg(chan2dev(chan), "%s: buf_addr=%pad, buf_len=%zd, period_len=%zd, dir=%s, flags=0x%lx\n",
 		__func__, &buf_addr, buf_len, period_len,
@@ -679,32 +717,34 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		return NULL;
 	}
 
+	if (at_xdmac_compute_chan_conf(chan, direction))
+		return NULL;
+
 	for (i = 0; i < periods; i++) {
 		struct at_xdmac_desc	*desc = NULL;
 
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, irqflags);
 		desc = at_xdmac_get_desc(atchan);
 		if (!desc) {
 			dev_err(chan2dev(chan), "can't get descriptor\n");
 			if (first)
 				list_splice_init(&first->descs_list, &atchan->free_descs_list);
-			spin_unlock_bh(&atchan->lock);
+			spin_unlock_irqrestore(&atchan->lock, irqflags);
 			return NULL;
 		}
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, irqflags);
 		dev_dbg(chan2dev(chan),
 			"%s: desc=0x%p, tx_dma_desc.phys=%pad\n",
 			__func__, desc, &desc->tx_dma_desc.phys);
 
 		if (direction == DMA_DEV_TO_MEM) {
-			desc->lld.mbr_sa = atchan->per_src_addr;
+			desc->lld.mbr_sa = atchan->sconfig.src_addr;
 			desc->lld.mbr_da = buf_addr + i * period_len;
-			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG];
 		} else {
 			desc->lld.mbr_sa = buf_addr + i * period_len;
-			desc->lld.mbr_da = atchan->per_dst_addr;
-			desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG];
+			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
+		desc->lld.mbr_cfg = atchan->cfg;
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1
 			| AT_XDMAC_MBR_UBC_NDEN
 			| AT_XDMAC_MBR_UBC_NSEN
@@ -766,6 +806,7 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 					| AT_XDMAC_CC_SIF(0)
 					| AT_XDMAC_CC_MBSIZE_SIXTEEN
 					| AT_XDMAC_CC_TYPE_MEM_TRAN;
+	unsigned long		irqflags;
 
 	dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, len=%zd, flags=0x%lx\n",
 		__func__, &src, &dest, len, flags);
@@ -798,9 +839,9 @@ at_xdmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
 		dev_dbg(chan2dev(chan), "%s: remaining_size=%zu\n", __func__, remaining_size);
 
-		spin_lock_bh(&atchan->lock);
+		spin_lock_irqsave(&atchan->lock, irqflags);
 		desc = at_xdmac_get_desc(atchan);
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, irqflags);
 		if (!desc) {
 			dev_err(chan2dev(chan), "can't get descriptor\n");
 			if (first)
@@ -886,6 +927,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	int			residue;
 	u32			cur_nda, mask, value;
 	u8			dwidth = 0;
+	unsigned long		flags;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -894,7 +936,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	if (!txstate)
 		return ret;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 
 	desc = list_first_entry(&atchan->xfers_list, struct at_xdmac_desc, xfer_node);
 
@@ -904,8 +946,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	 */
 	if (!desc->active_xfer) {
 		dma_set_residue(txstate, desc->xfer_size);
-		spin_unlock_bh(&atchan->lock);
-		return ret;
+		goto spin_unlock;
 	}
 
 	residue = desc->xfer_size;
@@ -936,14 +977,14 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	}
 	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
 
-	spin_unlock_bh(&atchan->lock);
-
 	dma_set_residue(txstate, residue);
 
 	dev_dbg(chan2dev(chan),
 		 "%s: desc=0x%p, tx_dma_desc.phys=%pad, tx_status=%d, cookie=%d, residue=%d\n",
 		 __func__, desc, &desc->tx_dma_desc.phys, ret, cookie, residue);
 
+spin_unlock:
+	spin_unlock_irqrestore(&atchan->lock, flags);
 	return ret;
 }
 
@@ -964,8 +1005,9 @@ static void at_xdmac_remove_xfer(struct at_xdmac_chan *atchan,
 static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
 {
 	struct at_xdmac_desc	*desc;
+	unsigned long		flags;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 
 	/*
 	 * If channel is enabled, do nothing, advance_work will be triggered
@@ -980,7 +1022,7 @@ static void at_xdmac_advance_work(struct at_xdmac_chan *atchan)
 			at_xdmac_start_xfer(atchan, desc);
 	}
 
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
 static void at_xdmac_handle_cyclic(struct at_xdmac_chan *atchan)
@@ -1116,12 +1158,13 @@ static int at_xdmac_device_config(struct dma_chan *chan,
 {
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	int ret;
+	unsigned long		flags;
 
 	dev_dbg(chan2dev(chan), "%s\n", __func__);
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	ret = at_xdmac_set_slave_config(chan, config);
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return ret;
 }
@@ -1130,18 +1173,19 @@ static int at_xdmac_device_pause(struct dma_chan *chan)
 {
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	unsigned long		flags;
 
 	dev_dbg(chan2dev(chan), "%s\n", __func__);
 
 	if (test_and_set_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status))
 		return 0;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	at_xdmac_write(atxdmac, AT_XDMAC_GRWS, atchan->mask);
 	while (at_xdmac_chan_read(atchan, AT_XDMAC_CC)
 	       & (AT_XDMAC_CC_WRIP | AT_XDMAC_CC_RDIP))
 		cpu_relax();
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return 0;
 }
@@ -1150,18 +1194,19 @@ static int at_xdmac_device_resume(struct dma_chan *chan)
 {
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	unsigned long		flags;
 
 	dev_dbg(chan2dev(chan), "%s\n", __func__);
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	if (!at_xdmac_chan_is_paused(atchan)) {
-		spin_unlock_bh(&atchan->lock);
+		spin_unlock_irqrestore(&atchan->lock, flags);
 		return 0;
 	}
 
 	at_xdmac_write(atxdmac, AT_XDMAC_GRWR, atchan->mask);
 	clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status);
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return 0;
 }
@@ -1171,10 +1216,11 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan)
 	struct at_xdmac_desc	*desc, *_desc;
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac		*atxdmac = to_at_xdmac(atchan->chan.device);
+	unsigned long		flags;
 
 	dev_dbg(chan2dev(chan), "%s\n", __func__);
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 	at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask);
 	while (at_xdmac_read(atxdmac, AT_XDMAC_GS) & atchan->mask)
 		cpu_relax();
@@ -1184,7 +1230,7 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan)
 		at_xdmac_remove_xfer(atchan, desc);
 
 	clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status);
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	return 0;
 }
@@ -1194,8 +1240,9 @@ static int at_xdmac_alloc_chan_resources(struct dma_chan *chan)
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac_desc	*desc;
 	int			i;
+	unsigned long		flags;
 
-	spin_lock_bh(&atchan->lock);
+	spin_lock_irqsave(&atchan->lock, flags);
 
 	if (at_xdmac_chan_is_enabled(atchan)) {
 		dev_err(chan2dev(chan),
@@ -1226,7 +1273,7 @@ static int at_xdmac_alloc_chan_resources(struct dma_chan *chan)
 	dev_dbg(chan2dev(chan), "%s: allocated %d descriptors\n", __func__, i);
 
 spin_unlock:
-	spin_unlock_bh(&atchan->lock);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 	return i;
 }
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 2890d744bb1b..3ddfd1f6c23c 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -487,7 +487,11 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->directions = device->directions;
 	caps->residue_granularity = device->residue_granularity;
 
-	caps->cmd_pause = !!device->device_pause;
+	/*
+	 * Some devices implement only pause (e.g. to get residuum) but no
+	 * resume. However cmd_pause is advertised as pause AND resume.
+	 */
+	caps->cmd_pause = !!(device->device_pause && device->device_resume);
 	caps->cmd_terminate = !!device->device_terminate_all;
 
 	return 0;
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 9b84def7a353..f42f71e37e73 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -384,7 +384,10 @@ static int hsu_dma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&hsuc->vchan.lock, flags);
 
 	hsu_dma_stop_channel(hsuc);
-	hsuc->desc = NULL;
+	if (hsuc->desc) {
+		hsu_dma_desc_free(&hsuc->desc->vdesc);
+		hsuc->desc = NULL;
+	}
 
 	vchan_get_all_descriptors(&hsuc->vchan, &head);
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 6de2e677be04..74d9db05a5ad 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 
 #include "mic_x100_dma.h"
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index a7d9d3029b14..340f9e607cd8 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2127,6 +2127,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
 
+	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
 	spin_lock(&pl330->lock);
 	_stop(pch->thread);
@@ -2151,6 +2152,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->work_list, &pl330->desc_pool);
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
+	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
 }
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index cb59619df23f..8677ead2a8e1 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -2,15 +2,16 @@
 #	EDAC Kconfig
 #	Copyright (c) 2008 Doug Thompson www.softwarebitmaker.com
 #	Licensed and distributed under the GPL
-#
+
+config EDAC_ATOMIC_SCRUB
+	bool
 
 config EDAC_SUPPORT
 	bool
 
 menuconfig EDAC
 	bool "EDAC (Error Detection And Correction) reporting"
-	depends on HAS_IOMEM
-	depends on X86 || PPC || TILE || ARM || EDAC_SUPPORT
+	depends on HAS_IOMEM && EDAC_SUPPORT
 	help
 	  EDAC is designed to report errors in the core system.
 	  These are low-level errors that are reported in the CPU or
@@ -262,10 +263,10 @@ config EDAC_SBRIDGE
 
 config EDAC_MPC85XX
 	tristate "Freescale MPC83xx / MPC85xx"
-	depends on EDAC_MM_EDAC && FSL_SOC && (PPC_83xx || PPC_85xx)
+	depends on EDAC_MM_EDAC && FSL_SOC
 	help
 	  Support for error detection and correction on the Freescale
-	  MPC8349, MPC8560, MPC8540, MPC8548
+	  MPC8349, MPC8560, MPC8540, MPC8548, T4240
 
 config EDAC_MV64X60
 	tristate "Marvell MV64x60"
@@ -377,8 +378,8 @@ config EDAC_OCTEON_PCI
 	  Cavium Octeon family of SOCs.
 
 config EDAC_ALTERA_MC
-	tristate "Altera SDRAM Memory Controller EDAC"
-	depends on EDAC_MM_EDAC && ARCH_SOCFPGA
+	bool "Altera SDRAM Memory Controller EDAC"
+	depends on EDAC_MM_EDAC=y && ARCH_SOCFPGA
 	help
 	  Support for error detection and correction on the
 	  Altera SDRAM memory controller. Note that the
@@ -392,4 +393,11 @@ config EDAC_SYNOPSYS
 	  Support for error detection and correction on the Synopsys DDR
 	  memory controller.
 
+config EDAC_XGENE
+	tristate "APM X-Gene SoC"
+	depends on EDAC_MM_EDAC && (ARM64 || COMPILE_TEST)
+	help
+	  Support for error detection and correction on the
+	  APM X-Gene family of SOCs.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index b255f362b1db..28ef2a519f65 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -68,3 +68,4 @@ obj-$(CONFIG_EDAC_OCTEON_PCI)		+= octeon_edac-pci.o
 
 obj-$(CONFIG_EDAC_ALTERA_MC)		+= altera_edac.o
 obj-$(CONFIG_EDAC_SYNOPSYS)		+= synopsys_edac.o
+obj-$(CONFIG_EDAC_XGENE)		+= xgene_edac.o
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 3c4929fda9d5..23ef0917483c 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -1,5 +1,5 @@
 /*
- *  Copyright Altera Corporation (C) 2014. All rights reserved.
+ *  Copyright Altera Corporation (C) 2014-2015. All rights reserved.
  *  Copyright 2011-2012 Calxeda, Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -28,113 +28,92 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 
+#include "altera_edac.h"
 #include "edac_core.h"
 #include "edac_module.h"
 
 #define EDAC_MOD_STR		"altera_edac"
 #define EDAC_VERSION		"1"
 
-/* SDRAM Controller CtrlCfg Register */
-#define CTLCFG_OFST             0x00
-
-/* SDRAM Controller CtrlCfg Register Bit Masks */
-#define CTLCFG_ECC_EN           0x400
-#define CTLCFG_ECC_CORR_EN      0x800
-#define CTLCFG_GEN_SB_ERR       0x2000
-#define CTLCFG_GEN_DB_ERR       0x4000
-
-#define CTLCFG_ECC_AUTO_EN	(CTLCFG_ECC_EN | \
-				 CTLCFG_ECC_CORR_EN)
-
-/* SDRAM Controller Address Width Register */
-#define DRAMADDRW_OFST          0x2C
-
-/* SDRAM Controller Address Widths Field Register */
-#define DRAMADDRW_COLBIT_MASK   0x001F
-#define DRAMADDRW_COLBIT_SHIFT  0
-#define DRAMADDRW_ROWBIT_MASK   0x03E0
-#define DRAMADDRW_ROWBIT_SHIFT  5
-#define DRAMADDRW_BANKBIT_MASK	0x1C00
-#define DRAMADDRW_BANKBIT_SHIFT 10
-#define DRAMADDRW_CSBIT_MASK	0xE000
-#define DRAMADDRW_CSBIT_SHIFT   13
-
-/* SDRAM Controller Interface Data Width Register */
-#define DRAMIFWIDTH_OFST        0x30
-
-/* SDRAM Controller Interface Data Width Defines */
-#define DRAMIFWIDTH_16B_ECC     24
-#define DRAMIFWIDTH_32B_ECC     40
-
-/* SDRAM Controller DRAM Status Register */
-#define DRAMSTS_OFST            0x38
-
-/* SDRAM Controller DRAM Status Register Bit Masks */
-#define DRAMSTS_SBEERR          0x04
-#define DRAMSTS_DBEERR          0x08
-#define DRAMSTS_CORR_DROP       0x10
-
-/* SDRAM Controller DRAM IRQ Register */
-#define DRAMINTR_OFST           0x3C
-
-/* SDRAM Controller DRAM IRQ Register Bit Masks */
-#define DRAMINTR_INTREN         0x01
-#define DRAMINTR_SBEMASK        0x02
-#define DRAMINTR_DBEMASK        0x04
-#define DRAMINTR_CORRDROPMASK   0x08
-#define DRAMINTR_INTRCLR        0x10
-
-/* SDRAM Controller Single Bit Error Count Register */
-#define SBECOUNT_OFST           0x40
-
-/* SDRAM Controller Single Bit Error Count Register Bit Masks */
-#define SBECOUNT_MASK           0x0F
-
-/* SDRAM Controller Double Bit Error Count Register */
-#define DBECOUNT_OFST           0x44
-
-/* SDRAM Controller Double Bit Error Count Register Bit Masks */
-#define DBECOUNT_MASK           0x0F
-
-/* SDRAM Controller ECC Error Address Register */
-#define ERRADDR_OFST            0x48
-
-/* SDRAM Controller ECC Error Address Register Bit Masks */
-#define ERRADDR_MASK            0xFFFFFFFF
+static const struct altr_sdram_prv_data c5_data = {
+	.ecc_ctrl_offset    = CV_CTLCFG_OFST,
+	.ecc_ctl_en_mask    = CV_CTLCFG_ECC_AUTO_EN,
+	.ecc_stat_offset    = CV_DRAMSTS_OFST,
+	.ecc_stat_ce_mask   = CV_DRAMSTS_SBEERR,
+	.ecc_stat_ue_mask   = CV_DRAMSTS_DBEERR,
+	.ecc_saddr_offset   = CV_ERRADDR_OFST,
+	.ecc_daddr_offset   = CV_ERRADDR_OFST,
+	.ecc_cecnt_offset   = CV_SBECOUNT_OFST,
+	.ecc_uecnt_offset   = CV_DBECOUNT_OFST,
+	.ecc_irq_en_offset  = CV_DRAMINTR_OFST,
+	.ecc_irq_en_mask    = CV_DRAMINTR_INTREN,
+	.ecc_irq_clr_offset = CV_DRAMINTR_OFST,
+	.ecc_irq_clr_mask   = (CV_DRAMINTR_INTRCLR | CV_DRAMINTR_INTREN),
+	.ecc_cnt_rst_offset = CV_DRAMINTR_OFST,
+	.ecc_cnt_rst_mask   = CV_DRAMINTR_INTRCLR,
+#ifdef CONFIG_EDAC_DEBUG
+	.ce_ue_trgr_offset  = CV_CTLCFG_OFST,
+	.ce_set_mask        = CV_CTLCFG_GEN_SB_ERR,
+	.ue_set_mask        = CV_CTLCFG_GEN_DB_ERR,
+#endif
+};
 
-/* Altera SDRAM Memory Controller data */
-struct altr_sdram_mc_data {
-	struct regmap *mc_vbase;
+static const struct altr_sdram_prv_data a10_data = {
+	.ecc_ctrl_offset    = A10_ECCCTRL1_OFST,
+	.ecc_ctl_en_mask    = A10_ECCCTRL1_ECC_EN,
+	.ecc_stat_offset    = A10_INTSTAT_OFST,
+	.ecc_stat_ce_mask   = A10_INTSTAT_SBEERR,
+	.ecc_stat_ue_mask   = A10_INTSTAT_DBEERR,
+	.ecc_saddr_offset   = A10_SERRADDR_OFST,
+	.ecc_daddr_offset   = A10_DERRADDR_OFST,
+	.ecc_irq_en_offset  = A10_ERRINTEN_OFST,
+	.ecc_irq_en_mask    = A10_ECC_IRQ_EN_MASK,
+	.ecc_irq_clr_offset = A10_INTSTAT_OFST,
+	.ecc_irq_clr_mask   = (A10_INTSTAT_SBEERR | A10_INTSTAT_DBEERR),
+	.ecc_cnt_rst_offset = A10_ECCCTRL1_OFST,
+	.ecc_cnt_rst_mask   = A10_ECC_CNT_RESET_MASK,
+#ifdef CONFIG_EDAC_DEBUG
+	.ce_ue_trgr_offset  = A10_DIAGINTTEST_OFST,
+	.ce_set_mask        = A10_DIAGINT_TSERRA_MASK,
+	.ue_set_mask        = A10_DIAGINT_TDERRA_MASK,
+#endif
 };
 
 static irqreturn_t altr_sdram_mc_err_handler(int irq, void *dev_id)
 {
 	struct mem_ctl_info *mci = dev_id;
 	struct altr_sdram_mc_data *drvdata = mci->pvt_info;
-	u32 status, err_count, err_addr;
+	const struct altr_sdram_prv_data *priv = drvdata->data;
+	u32 status, err_count = 1, err_addr;
 
-	/* Error Address is shared by both SBE & DBE */
-	regmap_read(drvdata->mc_vbase, ERRADDR_OFST, &err_addr);
+	regmap_read(drvdata->mc_vbase, priv->ecc_stat_offset, &status);
 
-	regmap_read(drvdata->mc_vbase, DRAMSTS_OFST, &status);
-
-	if (status & DRAMSTS_DBEERR) {
-		regmap_read(drvdata->mc_vbase, DBECOUNT_OFST, &err_count);
+	if (status & priv->ecc_stat_ue_mask) {
+		regmap_read(drvdata->mc_vbase, priv->ecc_daddr_offset,
+			    &err_addr);
+		if (priv->ecc_uecnt_offset)
+			regmap_read(drvdata->mc_vbase, priv->ecc_uecnt_offset,
+				    &err_count);
 		panic("\nEDAC: [%d Uncorrectable errors @ 0x%08X]\n",
 		      err_count, err_addr);
 	}
-	if (status & DRAMSTS_SBEERR) {
-		regmap_read(drvdata->mc_vbase, SBECOUNT_OFST, &err_count);
+	if (status & priv->ecc_stat_ce_mask) {
+		regmap_read(drvdata->mc_vbase, priv->ecc_saddr_offset,
+			    &err_addr);
+		if (priv->ecc_uecnt_offset)
+			regmap_read(drvdata->mc_vbase,  priv->ecc_cecnt_offset,
+				    &err_count);
 		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, err_count,
 				     err_addr >> PAGE_SHIFT,
 				     err_addr & ~PAGE_MASK, 0,
 				     0, 0, -1, mci->ctl_name, "");
-	}
-
-	regmap_write(drvdata->mc_vbase,	DRAMINTR_OFST,
-		     (DRAMINTR_INTRCLR | DRAMINTR_INTREN));
+		/* Clear IRQ to resume */
+		regmap_write(drvdata->mc_vbase,	priv->ecc_irq_clr_offset,
+			     priv->ecc_irq_clr_mask);
 
-	return IRQ_HANDLED;
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
 }
 
 #ifdef CONFIG_EDAC_DEBUG
@@ -144,6 +123,7 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
 {
 	struct mem_ctl_info *mci = file->private_data;
 	struct altr_sdram_mc_data *drvdata = mci->pvt_info;
+	const struct altr_sdram_prv_data *priv = drvdata->data;
 	u32 *ptemp;
 	dma_addr_t dma_handle;
 	u32 reg, read_reg;
@@ -156,8 +136,9 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
 		return -ENOMEM;
 	}
 
-	regmap_read(drvdata->mc_vbase, CTLCFG_OFST, &read_reg);
-	read_reg &= ~(CTLCFG_GEN_SB_ERR | CTLCFG_GEN_DB_ERR);
+	regmap_read(drvdata->mc_vbase, priv->ce_ue_trgr_offset,
+		    &read_reg);
+	read_reg &= ~(priv->ce_set_mask | priv->ue_set_mask);
 
 	/* Error are injected by writing a word while the SBE or DBE
 	 * bit in the CTLCFG register is set. Reading the word will
@@ -166,20 +147,20 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
 	if (count == 3) {
 		edac_printk(KERN_ALERT, EDAC_MC,
 			    "Inject Double bit error\n");
-		regmap_write(drvdata->mc_vbase, CTLCFG_OFST,
-			     (read_reg | CTLCFG_GEN_DB_ERR));
+		regmap_write(drvdata->mc_vbase, priv->ce_ue_trgr_offset,
+			     (read_reg | priv->ue_set_mask));
 	} else {
 		edac_printk(KERN_ALERT, EDAC_MC,
 			    "Inject Single bit error\n");
-		regmap_write(drvdata->mc_vbase,	CTLCFG_OFST,
-			     (read_reg | CTLCFG_GEN_SB_ERR));
+		regmap_write(drvdata->mc_vbase,	priv->ce_ue_trgr_offset,
+			     (read_reg | priv->ce_set_mask));
 	}
 
 	ptemp[0] = 0x5A5A5A5A;
 	ptemp[1] = 0xA5A5A5A5;
 
 	/* Clear the error injection bits */
-	regmap_write(drvdata->mc_vbase,	CTLCFG_OFST, read_reg);
+	regmap_write(drvdata->mc_vbase,	priv->ce_ue_trgr_offset, read_reg);
 	/* Ensure it has been written out */
 	wmb();
 
@@ -219,50 +200,106 @@ static void altr_sdr_mc_create_debugfs_nodes(struct mem_ctl_info *mci)
 {}
 #endif
 
-/* Get total memory size in bytes */
-static u32 altr_sdram_get_total_mem_size(struct regmap *mc_vbase)
+/* Get total memory size from Open Firmware DTB */
+static unsigned long get_total_mem(void)
 {
-	u32 size, read_reg, row, bank, col, cs, width;
-
-	if (regmap_read(mc_vbase, DRAMADDRW_OFST, &read_reg) < 0)
-		return 0;
-
-	if (regmap_read(mc_vbase, DRAMIFWIDTH_OFST, &width) < 0)
-		return 0;
-
-	col = (read_reg & DRAMADDRW_COLBIT_MASK) >>
-		DRAMADDRW_COLBIT_SHIFT;
-	row = (read_reg & DRAMADDRW_ROWBIT_MASK) >>
-		DRAMADDRW_ROWBIT_SHIFT;
-	bank = (read_reg & DRAMADDRW_BANKBIT_MASK) >>
-		DRAMADDRW_BANKBIT_SHIFT;
-	cs = (read_reg & DRAMADDRW_CSBIT_MASK) >>
-		DRAMADDRW_CSBIT_SHIFT;
-
-	/* Correct for ECC as its not addressible */
-	if (width == DRAMIFWIDTH_32B_ECC)
-		width = 32;
-	if (width == DRAMIFWIDTH_16B_ECC)
-		width = 16;
-
-	/* calculate the SDRAM size base on this info */
-	size = 1 << (row + bank + col);
-	size = size * cs * (width / 8);
-	return size;
+	struct device_node *np = NULL;
+	const unsigned int *reg, *reg_end;
+	int len, sw, aw;
+	unsigned long start, size, total_mem = 0;
+
+	for_each_node_by_type(np, "memory") {
+		aw = of_n_addr_cells(np);
+		sw = of_n_size_cells(np);
+		reg = (const unsigned int *)of_get_property(np, "reg", &len);
+		reg_end = reg + (len / sizeof(u32));
+
+		total_mem = 0;
+		do {
+			start = of_read_number(reg, aw);
+			reg += aw;
+			size = of_read_number(reg, sw);
+			reg += sw;
+			total_mem += size;
+		} while (reg < reg_end);
+	}
+	edac_dbg(0, "total_mem 0x%lx\n", total_mem);
+	return total_mem;
+}
+
+static const struct of_device_id altr_sdram_ctrl_of_match[] = {
+	{ .compatible = "altr,sdram-edac", .data = (void *)&c5_data},
+	{ .compatible = "altr,sdram-edac-a10", .data = (void *)&a10_data},
+	{},
+};
+MODULE_DEVICE_TABLE(of, altr_sdram_ctrl_of_match);
+
+static int a10_init(struct regmap *mc_vbase)
+{
+	if (regmap_update_bits(mc_vbase, A10_INTMODE_OFST,
+			       A10_INTMODE_SB_INT, A10_INTMODE_SB_INT)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error setting SB IRQ mode\n");
+		return -ENODEV;
+	}
+
+	if (regmap_write(mc_vbase, A10_SERRCNTREG_OFST, 1)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error setting trigger count\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int a10_unmask_irq(struct platform_device *pdev, u32 mask)
+{
+	void __iomem  *sm_base;
+	int  ret = 0;
+
+	if (!request_mem_region(A10_SYMAN_INTMASK_CLR, sizeof(u32),
+				dev_name(&pdev->dev))) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Unable to request mem region\n");
+		return -EBUSY;
+	}
+
+	sm_base = ioremap(A10_SYMAN_INTMASK_CLR, sizeof(u32));
+	if (!sm_base) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Unable to ioremap device\n");
+
+		ret = -ENOMEM;
+		goto release;
+	}
+
+	iowrite32(mask, sm_base);
+
+	iounmap(sm_base);
+
+release:
+	release_mem_region(A10_SYMAN_INTMASK_CLR, sizeof(u32));
+
+	return ret;
 }
 
 static int altr_sdram_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *id;
 	struct edac_mc_layer layers[2];
 	struct mem_ctl_info *mci;
 	struct altr_sdram_mc_data *drvdata;
+	const struct altr_sdram_prv_data *priv;
 	struct regmap *mc_vbase;
 	struct dimm_info *dimm;
-	u32 read_reg, mem_size;
-	int irq;
-	int res = 0;
+	u32 read_reg;
+	int irq, irq2, res = 0;
+	unsigned long mem_size, irqflags = 0;
+
+	id = of_match_device(altr_sdram_ctrl_of_match, &pdev->dev);
+	if (!id)
+		return -ENODEV;
 
-	/* Validate the SDRAM controller has ECC enabled */
 	/* Grab the register range from the sdr controller in device tree */
 	mc_vbase = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
 						   "altr,sdr-syscon");
@@ -272,25 +309,46 @@ static int altr_sdram_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	if (regmap_read(mc_vbase, CTLCFG_OFST, &read_reg) ||
-	    ((read_reg & CTLCFG_ECC_AUTO_EN) !=	CTLCFG_ECC_AUTO_EN)) {
+	/* Check specific dependencies for the module */
+	priv = of_match_node(altr_sdram_ctrl_of_match,
+			     pdev->dev.of_node)->data;
+
+	/* Validate the SDRAM controller has ECC enabled */
+	if (regmap_read(mc_vbase, priv->ecc_ctrl_offset, &read_reg) ||
+	    ((read_reg & priv->ecc_ctl_en_mask) != priv->ecc_ctl_en_mask)) {
 		edac_printk(KERN_ERR, EDAC_MC,
 			    "No ECC/ECC disabled [0x%08X]\n", read_reg);
 		return -ENODEV;
 	}
 
 	/* Grab memory size from device tree. */
-	mem_size = altr_sdram_get_total_mem_size(mc_vbase);
+	mem_size = get_total_mem();
 	if (!mem_size) {
+		edac_printk(KERN_ERR, EDAC_MC, "Unable to calculate memory size\n");
+		return -ENODEV;
+	}
+
+	/* Ensure the SDRAM Interrupt is disabled */
+	if (regmap_update_bits(mc_vbase, priv->ecc_irq_en_offset,
+			       priv->ecc_irq_en_mask, 0)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Error disabling SDRAM ECC IRQ\n");
+		return -ENODEV;
+	}
+
+	/* Toggle to clear the SDRAM Error count */
+	if (regmap_update_bits(mc_vbase, priv->ecc_cnt_rst_offset,
+			       priv->ecc_cnt_rst_mask,
+			       priv->ecc_cnt_rst_mask)) {
 		edac_printk(KERN_ERR, EDAC_MC,
-			    "Unable to calculate memory size\n");
+			    "Error clearing SDRAM ECC count\n");
 		return -ENODEV;
 	}
 
-	/* Ensure the SDRAM Interrupt is disabled and cleared */
-	if (regmap_write(mc_vbase, DRAMINTR_OFST, DRAMINTR_INTRCLR)) {
+	if (regmap_update_bits(mc_vbase, priv->ecc_cnt_rst_offset,
+			       priv->ecc_cnt_rst_mask, 0)) {
 		edac_printk(KERN_ERR, EDAC_MC,
-			    "Error clearing SDRAM ECC IRQ\n");
+			    "Error clearing SDRAM ECC count\n");
 		return -ENODEV;
 	}
 
@@ -301,6 +359,9 @@ static int altr_sdram_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	/* Arria10 has a 2nd IRQ */
+	irq2 = platform_get_irq(pdev, 1);
+
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
 	layers[0].size = 1;
 	layers[0].is_virt_csrow = true;
@@ -315,9 +376,12 @@ static int altr_sdram_probe(struct platform_device *pdev)
 	mci->pdev = &pdev->dev;
 	drvdata = mci->pvt_info;
 	drvdata->mc_vbase = mc_vbase;
+	drvdata->data = priv;
 	platform_set_drvdata(pdev, mci);
 
 	if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+		edac_printk(KERN_ERR, EDAC_MC,
+			    "Unable to get managed device resource\n");
 		res = -ENOMEM;
 		goto free;
 	}
@@ -342,8 +406,32 @@ static int altr_sdram_probe(struct platform_device *pdev)
 	if (res < 0)
 		goto err;
 
+	/* Only the Arria10 has separate IRQs */
+	if (irq2 > 0) {
+		/* Arria10 specific initialization */
+		res = a10_init(mc_vbase);
+		if (res < 0)
+			goto err2;
+
+		res = devm_request_irq(&pdev->dev, irq2,
+				       altr_sdram_mc_err_handler,
+				       IRQF_SHARED, dev_name(&pdev->dev), mci);
+		if (res < 0) {
+			edac_mc_printk(mci, KERN_ERR,
+				       "Unable to request irq %d\n", irq2);
+			res = -ENODEV;
+			goto err2;
+		}
+
+		res = a10_unmask_irq(pdev, A10_DDR0_IRQ_MASK);
+		if (res < 0)
+			goto err2;
+
+		irqflags = IRQF_SHARED;
+	}
+
 	res = devm_request_irq(&pdev->dev, irq, altr_sdram_mc_err_handler,
-			       0, dev_name(&pdev->dev), mci);
+			       irqflags, dev_name(&pdev->dev), mci);
 	if (res < 0) {
 		edac_mc_printk(mci, KERN_ERR,
 			       "Unable to request irq %d\n", irq);
@@ -351,8 +439,9 @@ static int altr_sdram_probe(struct platform_device *pdev)
 		goto err2;
 	}
 
-	if (regmap_write(drvdata->mc_vbase, DRAMINTR_OFST,
-			 (DRAMINTR_INTRCLR | DRAMINTR_INTREN))) {
+	/* Infrastructure ready - enable the IRQ */
+	if (regmap_update_bits(drvdata->mc_vbase, priv->ecc_irq_en_offset,
+			       priv->ecc_irq_en_mask, priv->ecc_irq_en_mask)) {
 		edac_mc_printk(mci, KERN_ERR,
 			       "Error enabling SDRAM ECC IRQ\n");
 		res = -ENODEV;
@@ -388,17 +477,31 @@ static int altr_sdram_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id altr_sdram_ctrl_of_match[] = {
-	{ .compatible = "altr,sdram-edac", },
-	{},
+/*
+ * If you want to suspend, need to disable EDAC by removing it
+ * from the device tree or defconfig.
+ */
+#ifdef CONFIG_PM
+static int altr_sdram_prepare(struct device *dev)
+{
+	pr_err("Suspend not allowed when EDAC is enabled.\n");
+
+	return -EPERM;
+}
+
+static const struct dev_pm_ops altr_sdram_pm_ops = {
+	.prepare = altr_sdram_prepare,
 };
-MODULE_DEVICE_TABLE(of, altr_sdram_ctrl_of_match);
+#endif
 
 static struct platform_driver altr_sdram_edac_driver = {
 	.probe = altr_sdram_probe,
 	.remove = altr_sdram_remove,
 	.driver = {
 		.name = "altr_sdram_edac",
+#ifdef CONFIG_PM
+		.pm = &altr_sdram_pm_ops,
+#endif
 		.of_match_table = altr_sdram_ctrl_of_match,
 	},
 };
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
new file mode 100644
index 000000000000..7b64dc7c4eb7
--- /dev/null
+++ b/drivers/edac/altera_edac.h
@@ -0,0 +1,201 @@
+/*
+ *
+ * Copyright (C) 2015 Altera Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ALTERA_EDAC_H
+#define _ALTERA_EDAC_H
+
+#include <linux/edac.h>
+#include <linux/types.h>
+
+/* SDRAM Controller CtrlCfg Register */
+#define CV_CTLCFG_OFST             0x00
+
+/* SDRAM Controller CtrlCfg Register Bit Masks */
+#define CV_CTLCFG_ECC_EN           0x400
+#define CV_CTLCFG_ECC_CORR_EN      0x800
+#define CV_CTLCFG_GEN_SB_ERR       0x2000
+#define CV_CTLCFG_GEN_DB_ERR       0x4000
+
+#define CV_CTLCFG_ECC_AUTO_EN     (CV_CTLCFG_ECC_EN | \
+				   CV_CTLCFG_ECC_CORR_EN)
+
+/* SDRAM Controller Address Width Register */
+#define CV_DRAMADDRW_OFST          0x2C
+
+/* SDRAM Controller Address Widths Field Register */
+#define DRAMADDRW_COLBIT_MASK      0x001F
+#define DRAMADDRW_COLBIT_SHIFT     0
+#define DRAMADDRW_ROWBIT_MASK      0x03E0
+#define DRAMADDRW_ROWBIT_SHIFT     5
+#define CV_DRAMADDRW_BANKBIT_MASK  0x1C00
+#define CV_DRAMADDRW_BANKBIT_SHIFT 10
+#define CV_DRAMADDRW_CSBIT_MASK    0xE000
+#define CV_DRAMADDRW_CSBIT_SHIFT   13
+
+/* SDRAM Controller Interface Data Width Register */
+#define CV_DRAMIFWIDTH_OFST        0x30
+
+/* SDRAM Controller Interface Data Width Defines */
+#define CV_DRAMIFWIDTH_16B_ECC     24
+#define CV_DRAMIFWIDTH_32B_ECC     40
+
+/* SDRAM Controller DRAM Status Register */
+#define CV_DRAMSTS_OFST            0x38
+
+/* SDRAM Controller DRAM Status Register Bit Masks */
+#define CV_DRAMSTS_SBEERR          0x04
+#define CV_DRAMSTS_DBEERR          0x08
+#define CV_DRAMSTS_CORR_DROP       0x10
+
+/* SDRAM Controller DRAM IRQ Register */
+#define CV_DRAMINTR_OFST           0x3C
+
+/* SDRAM Controller DRAM IRQ Register Bit Masks */
+#define CV_DRAMINTR_INTREN         0x01
+#define CV_DRAMINTR_SBEMASK        0x02
+#define CV_DRAMINTR_DBEMASK        0x04
+#define CV_DRAMINTR_CORRDROPMASK   0x08
+#define CV_DRAMINTR_INTRCLR        0x10
+
+/* SDRAM Controller Single Bit Error Count Register */
+#define CV_SBECOUNT_OFST           0x40
+
+/* SDRAM Controller Double Bit Error Count Register */
+#define CV_DBECOUNT_OFST           0x44
+
+/* SDRAM Controller ECC Error Address Register */
+#define CV_ERRADDR_OFST            0x48
+
+/*-----------------------------------------*/
+
+/* SDRAM Controller EccCtrl Register */
+#define A10_ECCCTRL1_OFST          0x00
+
+/* SDRAM Controller EccCtrl Register Bit Masks */
+#define A10_ECCCTRL1_ECC_EN        0x001
+#define A10_ECCCTRL1_CNT_RST       0x010
+#define A10_ECCCTRL1_AWB_CNT_RST   0x100
+#define A10_ECC_CNT_RESET_MASK     (A10_ECCCTRL1_CNT_RST | \
+				    A10_ECCCTRL1_AWB_CNT_RST)
+
+/* SDRAM Controller Address Width Register */
+#define CV_DRAMADDRW               0xFFC2502C
+#define A10_DRAMADDRW              0xFFCFA0A8
+
+/* SDRAM Controller Address Widths Field Register */
+#define DRAMADDRW_COLBIT_MASK      0x001F
+#define DRAMADDRW_COLBIT_SHIFT     0
+#define DRAMADDRW_ROWBIT_MASK      0x03E0
+#define DRAMADDRW_ROWBIT_SHIFT     5
+#define CV_DRAMADDRW_BANKBIT_MASK  0x1C00
+#define CV_DRAMADDRW_BANKBIT_SHIFT 10
+#define CV_DRAMADDRW_CSBIT_MASK    0xE000
+#define CV_DRAMADDRW_CSBIT_SHIFT   13
+
+#define A10_DRAMADDRW_BANKBIT_MASK  0x3C00
+#define A10_DRAMADDRW_BANKBIT_SHIFT 10
+#define A10_DRAMADDRW_GRPBIT_MASK   0xC000
+#define A10_DRAMADDRW_GRPBIT_SHIFT  14
+#define A10_DRAMADDRW_CSBIT_MASK    0x70000
+#define A10_DRAMADDRW_CSBIT_SHIFT   16
+
+/* SDRAM Controller Interface Data Width Register */
+#define CV_DRAMIFWIDTH             0xFFC25030
+#define A10_DRAMIFWIDTH            0xFFCFB008
+
+/* SDRAM Controller Interface Data Width Defines */
+#define CV_DRAMIFWIDTH_16B_ECC     24
+#define CV_DRAMIFWIDTH_32B_ECC     40
+
+#define A10_DRAMIFWIDTH_16B        0x0
+#define A10_DRAMIFWIDTH_32B        0x1
+#define A10_DRAMIFWIDTH_64B        0x2
+
+/* SDRAM Controller DRAM IRQ Register */
+#define A10_ERRINTEN_OFST          0x10
+
+/* SDRAM Controller DRAM IRQ Register Bit Masks */
+#define A10_ERRINTEN_SERRINTEN     0x01
+#define A10_ERRINTEN_DERRINTEN     0x02
+#define A10_ECC_IRQ_EN_MASK        (A10_ERRINTEN_SERRINTEN | \
+				    A10_ERRINTEN_DERRINTEN)
+
+/* SDRAM Interrupt Mode Register */
+#define A10_INTMODE_OFST           0x1C
+#define A10_INTMODE_SB_INT         1
+
+/* SDRAM Controller Error Status Register */
+#define A10_INTSTAT_OFST           0x20
+
+/* SDRAM Controller Error Status Register Bit Masks */
+#define A10_INTSTAT_SBEERR         0x01
+#define A10_INTSTAT_DBEERR         0x02
+
+/* SDRAM Controller ECC Error Address Register */
+#define A10_DERRADDR_OFST          0x2C
+#define A10_SERRADDR_OFST          0x30
+
+/* SDRAM Controller ECC Diagnostic Register */
+#define A10_DIAGINTTEST_OFST       0x24
+
+#define A10_DIAGINT_TSERRA_MASK    0x0001
+#define A10_DIAGINT_TDERRA_MASK    0x0100
+
+#define A10_SBERR_IRQ              34
+#define A10_DBERR_IRQ              32
+
+/* SDRAM Single Bit Error Count Compare Set Register */
+#define A10_SERRCNTREG_OFST        0x3C
+
+#define A10_SYMAN_INTMASK_CLR      0xFFD06098
+#define A10_INTMASK_CLR_OFST       0x10
+#define A10_DDR0_IRQ_MASK          BIT(17)
+
+struct altr_sdram_prv_data {
+	int ecc_ctrl_offset;
+	int ecc_ctl_en_mask;
+	int ecc_cecnt_offset;
+	int ecc_uecnt_offset;
+	int ecc_stat_offset;
+	int ecc_stat_ce_mask;
+	int ecc_stat_ue_mask;
+	int ecc_saddr_offset;
+	int ecc_daddr_offset;
+	int ecc_irq_en_offset;
+	int ecc_irq_en_mask;
+	int ecc_irq_clr_offset;
+	int ecc_irq_clr_mask;
+	int ecc_cnt_rst_offset;
+	int ecc_cnt_rst_mask;
+#ifdef CONFIG_EDAC_DEBUG
+	struct edac_dev_sysfs_attribute *eccmgr_sysfs_attr;
+	int ecc_enable_mask;
+	int ce_set_mask;
+	int ue_set_mask;
+	int ce_ue_trgr_offset;
+#endif
+};
+
+/* Altera SDRAM Memory Controller data */
+struct altr_sdram_mc_data {
+	struct regmap *mc_vbase;
+	int sb_irq;
+	int db_irq;
+	const struct altr_sdram_prv_data *data;
+};
+
+#endif	/* #ifndef _ALTERA_EDAC_H */
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index af3be1914dbb..943ed8cf71b9 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -30,11 +30,16 @@
 #include <linux/bitops.h>
 #include <asm/uaccess.h>
 #include <asm/page.h>
-#include <asm/edac.h>
 #include "edac_core.h"
 #include "edac_module.h"
 #include <ras/ras_event.h>
 
+#ifdef CONFIG_EDAC_ATOMIC_SCRUB
+#include <asm/edac.h>
+#else
+#define edac_atomic_scrub(va, size) do { } while (0)
+#endif
+
 /* lock to memory controller's control array */
 static DEFINE_MUTEX(mem_ctls_mutex);
 static LIST_HEAD(mc_devices);
@@ -874,7 +879,7 @@ static void edac_mc_scrub_block(unsigned long page, unsigned long offset,
 	virt_addr = kmap_atomic(pg);
 
 	/* Perform architecture specific atomic scrub operation */
-	atomic_scrub(virt_addr + offset, size);
+	edac_atomic_scrub(virt_addr + offset, size);
 
 	/* Unmap and complete */
 	kunmap_atomic(virt_addr);
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index 9d9e18aefaaa..ff07aae5b7fb 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -16,7 +16,6 @@
 #include <linux/edac.h>
 #include <linux/atomic.h>
 #include <linux/device.h>
-#include <asm/edac.h>
 
 int edac_op_state = EDAC_OPSTATE_INVAL;
 EXPORT_SYMBOL_GPL(edac_op_state);
diff --git a/drivers/edac/mce_amd_inj.c b/drivers/edac/mce_amd_inj.c
index f7681b553fd5..4c73e4d03d46 100644
--- a/drivers/edac/mce_amd_inj.c
+++ b/drivers/edac/mce_amd_inj.c
@@ -15,6 +15,8 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
 #include <asm/mce.h>
 
 #include "mce_amd.h"
@@ -25,6 +27,25 @@
 static struct mce i_mce;
 static struct dentry *dfs_inj;
 
+static u8 n_banks;
+
+#define MAX_FLAG_OPT_SIZE	3
+
+enum injection_type {
+	SW_INJ = 0,	/* SW injection, simply decode the error */
+	HW_INJ,		/* Trigger a #MC */
+	N_INJ_TYPES,
+};
+
+static const char * const flags_options[] = {
+	[SW_INJ] = "sw",
+	[HW_INJ] = "hw",
+	NULL
+};
+
+/* Set default injection to SW_INJ */
+static enum injection_type inj_type = SW_INJ;
+
 #define MCE_INJECT_SET(reg)						\
 static int inj_##reg##_set(void *data, u64 val)				\
 {									\
@@ -79,24 +100,66 @@ static int toggle_hw_mce_inject(unsigned int cpu, bool enable)
 	return err;
 }
 
-static int flags_get(void *data, u64 *val)
+static int __set_inj(const char *buf)
 {
-	struct mce *m = (struct mce *)data;
+	int i;
 
-	*val = m->inject_flags;
+	for (i = 0; i < N_INJ_TYPES; i++) {
+		if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) {
+			inj_type = i;
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
 
-	return 0;
+static ssize_t flags_read(struct file *filp, char __user *ubuf,
+			  size_t cnt, loff_t *ppos)
+{
+	char buf[MAX_FLAG_OPT_SIZE];
+	int n;
+
+	n = sprintf(buf, "%s\n", flags_options[inj_type]);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, n);
 }
 
-static int flags_set(void *data, u64 val)
+static ssize_t flags_write(struct file *filp, const char __user *ubuf,
+			   size_t cnt, loff_t *ppos)
 {
-	struct mce *m = (struct mce *)data;
+	char buf[MAX_FLAG_OPT_SIZE], *__buf;
+	int err;
+	size_t ret;
 
-	m->inject_flags = (u8)val;
-	return 0;
+	if (cnt > MAX_FLAG_OPT_SIZE)
+		cnt = MAX_FLAG_OPT_SIZE;
+
+	ret = cnt;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt - 1] = 0;
+
+	/* strip whitespace */
+	__buf = strstrip(buf);
+
+	err = __set_inj(__buf);
+	if (err) {
+		pr_err("%s: Invalid flags value: %s\n", __func__, __buf);
+		return err;
+	}
+
+	*ppos += ret;
+
+	return ret;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(flags_fops, flags_get, flags_set, "%llu\n");
+static const struct file_operations flags_fops = {
+	.read           = flags_read,
+	.write          = flags_write,
+	.llseek         = generic_file_llseek,
+};
 
 /*
  * On which CPU to inject?
@@ -128,21 +191,24 @@ static void do_inject(void)
 	unsigned int cpu = i_mce.extcpu;
 	u8 b = i_mce.bank;
 
-	if (!(i_mce.inject_flags & MCJ_EXCEPTION)) {
+	if (i_mce.misc)
+		i_mce.status |= MCI_STATUS_MISCV;
+
+	if (inj_type == SW_INJ) {
 		amd_decode_mce(NULL, 0, &i_mce);
 		return;
 	}
 
-	get_online_cpus();
-	if (!cpu_online(cpu))
-		goto err;
-
 	/* prep MCE global settings for the injection */
 	mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV;
 
 	if (!(i_mce.status & MCI_STATUS_PCC))
 		mcg_status |= MCG_STATUS_RIPV;
 
+	get_online_cpus();
+	if (!cpu_online(cpu))
+		goto err;
+
 	toggle_hw_mce_inject(cpu, true);
 
 	wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS,
@@ -174,11 +240,9 @@ static int inj_bank_set(void *data, u64 val)
 {
 	struct mce *m = (struct mce *)data;
 
-	if (val > 5) {
-		if (boot_cpu_data.x86 != 0x15 || val > 6) {
-			pr_err("Non-existent MCE bank: %llu\n", val);
-			return -EINVAL;
-		}
+	if (val >= n_banks) {
+		pr_err("Non-existent MCE bank: %llu\n", val);
+		return -EINVAL;
 	}
 
 	m->bank = val;
@@ -187,32 +251,81 @@ static int inj_bank_set(void *data, u64 val)
 	return 0;
 }
 
-static int inj_bank_get(void *data, u64 *val)
-{
-	struct mce *m = (struct mce *)data;
+MCE_INJECT_GET(bank);
 
-	*val = m->bank;
-	return 0;
+DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n");
+
+static const char readme_msg[] =
+"Description of the files and their usages:\n"
+"\n"
+"Note1: i refers to the bank number below.\n"
+"Note2: See respective BKDGs for the exact bit definitions of the files below\n"
+"as they mirror the hardware registers.\n"
+"\n"
+"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n"
+"\t attributes of the error which caused the MCE.\n"
+"\n"
+"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n"
+"\t used for error thresholding purposes and its validity is indicated by\n"
+"\t MCi_STATUS[MiscV].\n"
+"\n"
+"addr:\t Error address value to be written to MCi_ADDR. Log address information\n"
+"\t associated with the error.\n"
+"\n"
+"cpu:\t The CPU to inject the error on.\n"
+"\n"
+"bank:\t Specify the bank you want to inject the error into: the number of\n"
+"\t banks in a processor varies and is family/model-specific, therefore, the\n"
+"\t supplied value is sanity-checked. Setting the bank value also triggers the\n"
+"\t injection.\n"
+"\n"
+"flags:\t Injection type to be performed. Writing to this file will trigger a\n"
+"\t real machine check, an APIC interrupt or invoke the error decoder routines\n"
+"\t for AMD processors.\n"
+"\n"
+"\t Allowed error injection types:\n"
+"\t  - \"sw\": Software error injection. Decode error to a human-readable \n"
+"\t    format only. Safe to use.\n"
+"\t  - \"hw\": Hardware error injection. Causes the #MC exception handler to \n"
+"\t    handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n"
+"\t    is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n"
+"\t    before injecting.\n"
+"\n";
+
+static ssize_t
+inj_readme_read(struct file *filp, char __user *ubuf,
+		       size_t cnt, loff_t *ppos)
+{
+	return simple_read_from_buffer(ubuf, cnt, ppos,
+					readme_msg, strlen(readme_msg));
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n");
+static const struct file_operations readme_fops = {
+	.read		= inj_readme_read,
+};
 
 static struct dfs_node {
 	char *name;
 	struct dentry *d;
 	const struct file_operations *fops;
+	umode_t perm;
 } dfs_fls[] = {
-	{ .name = "status",	.fops = &status_fops },
-	{ .name = "misc",	.fops = &misc_fops },
-	{ .name = "addr",	.fops = &addr_fops },
-	{ .name = "bank",	.fops = &bank_fops },
-	{ .name = "flags",	.fops = &flags_fops },
-	{ .name = "cpu",	.fops = &extcpu_fops },
+	{ .name = "status",	.fops = &status_fops, .perm = S_IRUSR | S_IWUSR },
+	{ .name = "misc",	.fops = &misc_fops,   .perm = S_IRUSR | S_IWUSR },
+	{ .name = "addr",	.fops = &addr_fops,   .perm = S_IRUSR | S_IWUSR },
+	{ .name = "bank",	.fops = &bank_fops,   .perm = S_IRUSR | S_IWUSR },
+	{ .name = "flags",	.fops = &flags_fops,  .perm = S_IRUSR | S_IWUSR },
+	{ .name = "cpu",	.fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR },
+	{ .name = "README",	.fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH },
 };
 
 static int __init init_mce_inject(void)
 {
 	int i;
+	u64 cap;
+
+	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	n_banks = cap & MCG_BANKCNT_MASK;
 
 	dfs_inj = debugfs_create_dir("mce-inject", NULL);
 	if (!dfs_inj)
@@ -220,7 +333,7 @@ static int __init init_mce_inject(void)
 
 	for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) {
 		dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name,
-						    S_IRUSR | S_IWUSR,
+						    dfs_fls[i].perm,
 						    dfs_inj,
 						    &i_mce,
 						    dfs_fls[i].fops);
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 68bf234bdfe6..23ef8e9f2c9a 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -811,6 +811,8 @@ static void sbe_ecc_decode(u32 cap_high, u32 cap_low, u32 cap_ecc,
 	}
 }
 
+#define make64(high, low) (((u64)(high) << 32) | (low))
+
 static void mpc85xx_mc_check(struct mem_ctl_info *mci)
 {
 	struct mpc85xx_mc_pdata *pdata = mci->pvt_info;
@@ -818,7 +820,7 @@ static void mpc85xx_mc_check(struct mem_ctl_info *mci)
 	u32 bus_width;
 	u32 err_detect;
 	u32 syndrome;
-	u32 err_addr;
+	u64 err_addr;
 	u32 pfn;
 	int row_index;
 	u32 cap_high;
@@ -849,7 +851,9 @@ static void mpc85xx_mc_check(struct mem_ctl_info *mci)
 	else
 		syndrome &= 0xffff;
 
-	err_addr = in_be32(pdata->mc_vbase + MPC85XX_MC_CAPTURE_ADDRESS);
+	err_addr = make64(
+		in_be32(pdata->mc_vbase + MPC85XX_MC_CAPTURE_EXT_ADDRESS),
+		in_be32(pdata->mc_vbase + MPC85XX_MC_CAPTURE_ADDRESS));
 	pfn = err_addr >> PAGE_SHIFT;
 
 	for (row_index = 0; row_index < mci->nr_csrows; row_index++) {
@@ -886,7 +890,7 @@ static void mpc85xx_mc_check(struct mem_ctl_info *mci)
 	mpc85xx_mc_printk(mci, KERN_ERR,
 			"Captured Data / ECC:\t%#8.8x_%08x / %#2.2x\n",
 			cap_high, cap_low, syndrome);
-	mpc85xx_mc_printk(mci, KERN_ERR, "Err addr: %#8.8x\n", err_addr);
+	mpc85xx_mc_printk(mci, KERN_ERR, "Err addr: %#8.8llx\n", err_addr);
 	mpc85xx_mc_printk(mci, KERN_ERR, "PFN: %#8.8x\n", pfn);
 
 	/* we are out of range */
diff --git a/drivers/edac/mpc85xx_edac.h b/drivers/edac/mpc85xx_edac.h
index 4498baf9ce05..9352e88d53e5 100644
--- a/drivers/edac/mpc85xx_edac.h
+++ b/drivers/edac/mpc85xx_edac.h
@@ -43,6 +43,7 @@
 #define MPC85XX_MC_ERR_INT_EN		0x0e48
 #define MPC85XX_MC_CAPTURE_ATRIBUTES	0x0e4c
 #define MPC85XX_MC_CAPTURE_ADDRESS	0x0e50
+#define MPC85XX_MC_CAPTURE_EXT_ADDRESS	0x0e54
 #define MPC85XX_MC_ERR_SBE		0x0e58
 
 #define DSC_MEM_EN	0x80000000
diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c
new file mode 100644
index 000000000000..14636e4b6a08
--- /dev/null
+++ b/drivers/edac/xgene_edac.c
@@ -0,0 +1,1215 @@
+/*
+ * APM X-Gene SoC EDAC (error detection and correction)
+ *
+ * Copyright (c) 2015, Applied Micro Circuits Corporation
+ * Author: Feng Kan <fkan@apm.com>
+ *         Loc Ho <lho@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/ctype.h>
+#include <linux/edac.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/regmap.h>
+
+#include "edac_core.h"
+
+#define EDAC_MOD_STR			"xgene_edac"
+
+/* Global error configuration status registers (CSR) */
+#define PCPHPERRINTSTS			0x0000
+#define PCPHPERRINTMSK			0x0004
+#define  MCU_CTL_ERR_MASK		BIT(12)
+#define  IOB_PA_ERR_MASK		BIT(11)
+#define  IOB_BA_ERR_MASK		BIT(10)
+#define  IOB_XGIC_ERR_MASK		BIT(9)
+#define  IOB_RB_ERR_MASK		BIT(8)
+#define  L3C_UNCORR_ERR_MASK		BIT(5)
+#define  MCU_UNCORR_ERR_MASK		BIT(4)
+#define  PMD3_MERR_MASK			BIT(3)
+#define  PMD2_MERR_MASK			BIT(2)
+#define  PMD1_MERR_MASK			BIT(1)
+#define  PMD0_MERR_MASK			BIT(0)
+#define PCPLPERRINTSTS			0x0008
+#define PCPLPERRINTMSK			0x000C
+#define  CSW_SWITCH_TRACE_ERR_MASK	BIT(2)
+#define  L3C_CORR_ERR_MASK		BIT(1)
+#define  MCU_CORR_ERR_MASK		BIT(0)
+#define MEMERRINTSTS			0x0010
+#define MEMERRINTMSK			0x0014
+
+struct xgene_edac {
+	struct device		*dev;
+	struct regmap		*csw_map;
+	struct regmap		*mcba_map;
+	struct regmap		*mcbb_map;
+	struct regmap		*efuse_map;
+	void __iomem		*pcp_csr;
+	spinlock_t		lock;
+	struct dentry		*dfs;
+
+	struct list_head	mcus;
+	struct list_head	pmds;
+
+	struct mutex		mc_lock;
+	int			mc_active_mask;
+	int			mc_registered_mask;
+};
+
+static void xgene_edac_pcp_rd(struct xgene_edac *edac, u32 reg, u32 *val)
+{
+	*val = readl(edac->pcp_csr + reg);
+}
+
+static void xgene_edac_pcp_clrbits(struct xgene_edac *edac, u32 reg,
+				   u32 bits_mask)
+{
+	u32 val;
+
+	spin_lock(&edac->lock);
+	val = readl(edac->pcp_csr + reg);
+	val &= ~bits_mask;
+	writel(val, edac->pcp_csr + reg);
+	spin_unlock(&edac->lock);
+}
+
+static void xgene_edac_pcp_setbits(struct xgene_edac *edac, u32 reg,
+				   u32 bits_mask)
+{
+	u32 val;
+
+	spin_lock(&edac->lock);
+	val = readl(edac->pcp_csr + reg);
+	val |= bits_mask;
+	writel(val, edac->pcp_csr + reg);
+	spin_unlock(&edac->lock);
+}
+
+/* Memory controller error CSR */
+#define MCU_MAX_RANK			8
+#define MCU_RANK_STRIDE			0x40
+
+#define MCUGECR				0x0110
+#define  MCU_GECR_DEMANDUCINTREN_MASK	BIT(0)
+#define  MCU_GECR_BACKUCINTREN_MASK	BIT(1)
+#define  MCU_GECR_CINTREN_MASK		BIT(2)
+#define  MUC_GECR_MCUADDRERREN_MASK	BIT(9)
+#define MCUGESR				0x0114
+#define  MCU_GESR_ADDRNOMATCH_ERR_MASK	BIT(7)
+#define  MCU_GESR_ADDRMULTIMATCH_ERR_MASK	BIT(6)
+#define  MCU_GESR_PHYP_ERR_MASK		BIT(3)
+#define MCUESRR0			0x0314
+#define  MCU_ESRR_MULTUCERR_MASK	BIT(3)
+#define  MCU_ESRR_BACKUCERR_MASK	BIT(2)
+#define  MCU_ESRR_DEMANDUCERR_MASK	BIT(1)
+#define  MCU_ESRR_CERR_MASK		BIT(0)
+#define MCUESRRA0			0x0318
+#define MCUEBLRR0			0x031c
+#define  MCU_EBLRR_ERRBANK_RD(src)	(((src) & 0x00000007) >> 0)
+#define MCUERCRR0			0x0320
+#define  MCU_ERCRR_ERRROW_RD(src)	(((src) & 0xFFFF0000) >> 16)
+#define  MCU_ERCRR_ERRCOL_RD(src)	((src) & 0x00000FFF)
+#define MCUSBECNT0			0x0324
+#define MCU_SBECNT_COUNT(src)		((src) & 0xFFFF)
+
+#define CSW_CSWCR			0x0000
+#define  CSW_CSWCR_DUALMCB_MASK		BIT(0)
+
+#define MCBADDRMR			0x0000
+#define  MCBADDRMR_MCU_INTLV_MODE_MASK	BIT(3)
+#define  MCBADDRMR_DUALMCU_MODE_MASK	BIT(2)
+#define  MCBADDRMR_MCB_INTLV_MODE_MASK	BIT(1)
+#define  MCBADDRMR_ADDRESS_MODE_MASK	BIT(0)
+
+struct xgene_edac_mc_ctx {
+	struct list_head	next;
+	char			*name;
+	struct mem_ctl_info	*mci;
+	struct xgene_edac	*edac;
+	void __iomem		*mcu_csr;
+	u32			mcu_id;
+};
+
+static ssize_t xgene_edac_mc_err_inject_write(struct file *file,
+					      const char __user *data,
+					      size_t count, loff_t *ppos)
+{
+	struct mem_ctl_info *mci = file->private_data;
+	struct xgene_edac_mc_ctx *ctx = mci->pvt_info;
+	int i;
+
+	for (i = 0; i < MCU_MAX_RANK; i++) {
+		writel(MCU_ESRR_MULTUCERR_MASK | MCU_ESRR_BACKUCERR_MASK |
+		       MCU_ESRR_DEMANDUCERR_MASK | MCU_ESRR_CERR_MASK,
+		       ctx->mcu_csr + MCUESRRA0 + i * MCU_RANK_STRIDE);
+	}
+	return count;
+}
+
+static const struct file_operations xgene_edac_mc_debug_inject_fops = {
+	.open = simple_open,
+	.write = xgene_edac_mc_err_inject_write,
+	.llseek = generic_file_llseek,
+};
+
+static void xgene_edac_mc_create_debugfs_node(struct mem_ctl_info *mci)
+{
+	if (!IS_ENABLED(CONFIG_EDAC_DEBUG))
+		return;
+#ifdef CONFIG_EDAC_DEBUG
+	if (!mci->debugfs)
+		return;
+	debugfs_create_file("inject_ctrl", S_IWUSR, mci->debugfs, mci,
+			    &xgene_edac_mc_debug_inject_fops);
+#endif
+}
+
+static void xgene_edac_mc_check(struct mem_ctl_info *mci)
+{
+	struct xgene_edac_mc_ctx *ctx = mci->pvt_info;
+	unsigned int pcp_hp_stat;
+	unsigned int pcp_lp_stat;
+	u32 reg;
+	u32 rank;
+	u32 bank;
+	u32 count;
+	u32 col_row;
+
+	xgene_edac_pcp_rd(ctx->edac, PCPHPERRINTSTS, &pcp_hp_stat);
+	xgene_edac_pcp_rd(ctx->edac, PCPLPERRINTSTS, &pcp_lp_stat);
+	if (!((MCU_UNCORR_ERR_MASK & pcp_hp_stat) ||
+	      (MCU_CTL_ERR_MASK & pcp_hp_stat) ||
+	      (MCU_CORR_ERR_MASK & pcp_lp_stat)))
+		return;
+
+	for (rank = 0; rank < MCU_MAX_RANK; rank++) {
+		reg = readl(ctx->mcu_csr + MCUESRR0 + rank * MCU_RANK_STRIDE);
+
+		/* Detect uncorrectable memory error */
+		if (reg & (MCU_ESRR_DEMANDUCERR_MASK |
+			   MCU_ESRR_BACKUCERR_MASK)) {
+			/* Detected uncorrectable memory error */
+			edac_mc_chipset_printk(mci, KERN_ERR, "X-Gene",
+				"MCU uncorrectable error at rank %d\n", rank);
+
+			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+				1, 0, 0, 0, 0, 0, -1, mci->ctl_name, "");
+		}
+
+		/* Detect correctable memory error */
+		if (reg & MCU_ESRR_CERR_MASK) {
+			bank = readl(ctx->mcu_csr + MCUEBLRR0 +
+				     rank * MCU_RANK_STRIDE);
+			col_row = readl(ctx->mcu_csr + MCUERCRR0 +
+					rank * MCU_RANK_STRIDE);
+			count = readl(ctx->mcu_csr + MCUSBECNT0 +
+				      rank * MCU_RANK_STRIDE);
+			edac_mc_chipset_printk(mci, KERN_WARNING, "X-Gene",
+				"MCU correctable error at rank %d bank %d column %d row %d count %d\n",
+				rank, MCU_EBLRR_ERRBANK_RD(bank),
+				MCU_ERCRR_ERRCOL_RD(col_row),
+				MCU_ERCRR_ERRROW_RD(col_row),
+				MCU_SBECNT_COUNT(count));
+
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+				1, 0, 0, 0, 0, 0, -1, mci->ctl_name, "");
+		}
+
+		/* Clear all error registers */
+		writel(0x0, ctx->mcu_csr + MCUEBLRR0 + rank * MCU_RANK_STRIDE);
+		writel(0x0, ctx->mcu_csr + MCUERCRR0 + rank * MCU_RANK_STRIDE);
+		writel(0x0, ctx->mcu_csr + MCUSBECNT0 +
+		       rank * MCU_RANK_STRIDE);
+		writel(reg, ctx->mcu_csr + MCUESRR0 + rank * MCU_RANK_STRIDE);
+	}
+
+	/* Detect memory controller error */
+	reg = readl(ctx->mcu_csr + MCUGESR);
+	if (reg) {
+		if (reg & MCU_GESR_ADDRNOMATCH_ERR_MASK)
+			edac_mc_chipset_printk(mci, KERN_WARNING, "X-Gene",
+				"MCU address miss-match error\n");
+		if (reg & MCU_GESR_ADDRMULTIMATCH_ERR_MASK)
+			edac_mc_chipset_printk(mci, KERN_WARNING, "X-Gene",
+				"MCU address multi-match error\n");
+
+		writel(reg, ctx->mcu_csr + MCUGESR);
+	}
+}
+
+static void xgene_edac_mc_irq_ctl(struct mem_ctl_info *mci, bool enable)
+{
+	struct xgene_edac_mc_ctx *ctx = mci->pvt_info;
+	unsigned int val;
+
+	if (edac_op_state != EDAC_OPSTATE_INT)
+		return;
+
+	mutex_lock(&ctx->edac->mc_lock);
+
+	/*
+	 * As there is only single bit for enable error and interrupt mask,
+	 * we must only enable top level interrupt after all MCUs are
+	 * registered. Otherwise, if there is an error and the corresponding
+	 * MCU has not registered, the interrupt will never get cleared. To
+	 * determine all MCU have registered, we will keep track of active
+	 * MCUs and registered MCUs.
+	 */
+	if (enable) {
+		/* Set registered MCU bit */
+		ctx->edac->mc_registered_mask |= 1 << ctx->mcu_id;
+
+		/* Enable interrupt after all active MCU registered */
+		if (ctx->edac->mc_registered_mask ==
+		    ctx->edac->mc_active_mask) {
+			/* Enable memory controller top level interrupt */
+			xgene_edac_pcp_clrbits(ctx->edac, PCPHPERRINTMSK,
+					       MCU_UNCORR_ERR_MASK |
+					       MCU_CTL_ERR_MASK);
+			xgene_edac_pcp_clrbits(ctx->edac, PCPLPERRINTMSK,
+					       MCU_CORR_ERR_MASK);
+		}
+
+		/* Enable MCU interrupt and error reporting */
+		val = readl(ctx->mcu_csr + MCUGECR);
+		val |= MCU_GECR_DEMANDUCINTREN_MASK |
+		       MCU_GECR_BACKUCINTREN_MASK |
+		       MCU_GECR_CINTREN_MASK |
+		       MUC_GECR_MCUADDRERREN_MASK;
+		writel(val, ctx->mcu_csr + MCUGECR);
+	} else {
+		/* Disable MCU interrupt */
+		val = readl(ctx->mcu_csr + MCUGECR);
+		val &= ~(MCU_GECR_DEMANDUCINTREN_MASK |
+			 MCU_GECR_BACKUCINTREN_MASK |
+			 MCU_GECR_CINTREN_MASK |
+			 MUC_GECR_MCUADDRERREN_MASK);
+		writel(val, ctx->mcu_csr + MCUGECR);
+
+		/* Disable memory controller top level interrupt */
+		xgene_edac_pcp_setbits(ctx->edac, PCPHPERRINTMSK,
+				       MCU_UNCORR_ERR_MASK | MCU_CTL_ERR_MASK);
+		xgene_edac_pcp_setbits(ctx->edac, PCPLPERRINTMSK,
+				       MCU_CORR_ERR_MASK);
+
+		/* Clear registered MCU bit */
+		ctx->edac->mc_registered_mask &= ~(1 << ctx->mcu_id);
+	}
+
+	mutex_unlock(&ctx->edac->mc_lock);
+}
+
+static int xgene_edac_mc_is_active(struct xgene_edac_mc_ctx *ctx, int mc_idx)
+{
+	unsigned int reg;
+	u32 mcu_mask;
+
+	if (regmap_read(ctx->edac->csw_map, CSW_CSWCR, &reg))
+		return 0;
+
+	if (reg & CSW_CSWCR_DUALMCB_MASK) {
+		/*
+		 * Dual MCB active - Determine if all 4 active or just MCU0
+		 * and MCU2 active
+		 */
+		if (regmap_read(ctx->edac->mcbb_map, MCBADDRMR, &reg))
+			return 0;
+		mcu_mask = (reg & MCBADDRMR_DUALMCU_MODE_MASK) ? 0xF : 0x5;
+	} else {
+		/*
+		 * Single MCB active - Determine if MCU0/MCU1 or just MCU0
+		 * active
+		 */
+		if (regmap_read(ctx->edac->mcba_map, MCBADDRMR, &reg))
+			return 0;
+		mcu_mask = (reg & MCBADDRMR_DUALMCU_MODE_MASK) ? 0x3 : 0x1;
+	}
+
+	/* Save active MC mask if hasn't set already */
+	if (!ctx->edac->mc_active_mask)
+		ctx->edac->mc_active_mask = mcu_mask;
+
+	return (mcu_mask & (1 << mc_idx)) ? 1 : 0;
+}
+
+static int xgene_edac_mc_add(struct xgene_edac *edac, struct device_node *np)
+{
+	struct mem_ctl_info *mci;
+	struct edac_mc_layer layers[2];
+	struct xgene_edac_mc_ctx tmp_ctx;
+	struct xgene_edac_mc_ctx *ctx;
+	struct resource res;
+	int rc;
+
+	memset(&tmp_ctx, 0, sizeof(tmp_ctx));
+	tmp_ctx.edac = edac;
+
+	if (!devres_open_group(edac->dev, xgene_edac_mc_add, GFP_KERNEL))
+		return -ENOMEM;
+
+	rc = of_address_to_resource(np, 0, &res);
+	if (rc < 0) {
+		dev_err(edac->dev, "no MCU resource address\n");
+		goto err_group;
+	}
+	tmp_ctx.mcu_csr = devm_ioremap_resource(edac->dev, &res);
+	if (IS_ERR(tmp_ctx.mcu_csr)) {
+		dev_err(edac->dev, "unable to map MCU resource\n");
+		rc = PTR_ERR(tmp_ctx.mcu_csr);
+		goto err_group;
+	}
+
+	/* Ignore non-active MCU */
+	if (of_property_read_u32(np, "memory-controller", &tmp_ctx.mcu_id)) {
+		dev_err(edac->dev, "no memory-controller property\n");
+		rc = -ENODEV;
+		goto err_group;
+	}
+	if (!xgene_edac_mc_is_active(&tmp_ctx, tmp_ctx.mcu_id)) {
+		rc = -ENODEV;
+		goto err_group;
+	}
+
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = 4;
+	layers[0].is_virt_csrow = true;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = 2;
+	layers[1].is_virt_csrow = false;
+	mci = edac_mc_alloc(tmp_ctx.mcu_id, ARRAY_SIZE(layers), layers,
+			    sizeof(*ctx));
+	if (!mci) {
+		rc = -ENOMEM;
+		goto err_group;
+	}
+
+	ctx = mci->pvt_info;
+	*ctx = tmp_ctx;		/* Copy over resource value */
+	ctx->name = "xgene_edac_mc_err";
+	ctx->mci = mci;
+	mci->pdev = &mci->dev;
+	mci->ctl_name = ctx->name;
+	mci->dev_name = ctx->name;
+
+	mci->mtype_cap = MEM_FLAG_RDDR | MEM_FLAG_RDDR2 | MEM_FLAG_RDDR3 |
+			 MEM_FLAG_DDR | MEM_FLAG_DDR2 | MEM_FLAG_DDR3;
+	mci->edac_ctl_cap = EDAC_FLAG_SECDED;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+	mci->mod_name = EDAC_MOD_STR;
+	mci->mod_ver = "0.1";
+	mci->ctl_page_to_phys = NULL;
+	mci->scrub_cap = SCRUB_FLAG_HW_SRC;
+	mci->scrub_mode = SCRUB_HW_SRC;
+
+	if (edac_op_state == EDAC_OPSTATE_POLL)
+		mci->edac_check = xgene_edac_mc_check;
+
+	if (edac_mc_add_mc(mci)) {
+		dev_err(edac->dev, "edac_mc_add_mc failed\n");
+		rc = -EINVAL;
+		goto err_free;
+	}
+
+	xgene_edac_mc_create_debugfs_node(mci);
+
+	list_add(&ctx->next, &edac->mcus);
+
+	xgene_edac_mc_irq_ctl(mci, true);
+
+	devres_remove_group(edac->dev, xgene_edac_mc_add);
+
+	dev_info(edac->dev, "X-Gene EDAC MC registered\n");
+	return 0;
+
+err_free:
+	edac_mc_free(mci);
+err_group:
+	devres_release_group(edac->dev, xgene_edac_mc_add);
+	return rc;
+}
+
+static int xgene_edac_mc_remove(struct xgene_edac_mc_ctx *mcu)
+{
+	xgene_edac_mc_irq_ctl(mcu->mci, false);
+	edac_mc_del_mc(&mcu->mci->dev);
+	edac_mc_free(mcu->mci);
+	return 0;
+}
+
+/* CPU L1/L2 error CSR */
+#define MAX_CPU_PER_PMD				2
+#define CPU_CSR_STRIDE				0x00100000
+#define CPU_L2C_PAGE				0x000D0000
+#define CPU_MEMERR_L2C_PAGE			0x000E0000
+#define CPU_MEMERR_CPU_PAGE			0x000F0000
+
+#define MEMERR_CPU_ICFECR_PAGE_OFFSET		0x0000
+#define MEMERR_CPU_ICFESR_PAGE_OFFSET		0x0004
+#define  MEMERR_CPU_ICFESR_ERRWAY_RD(src)	(((src) & 0xFF000000) >> 24)
+#define  MEMERR_CPU_ICFESR_ERRINDEX_RD(src)	(((src) & 0x003F0000) >> 16)
+#define  MEMERR_CPU_ICFESR_ERRINFO_RD(src)	(((src) & 0x0000FF00) >> 8)
+#define  MEMERR_CPU_ICFESR_ERRTYPE_RD(src)	(((src) & 0x00000070) >> 4)
+#define  MEMERR_CPU_ICFESR_MULTCERR_MASK	BIT(2)
+#define  MEMERR_CPU_ICFESR_CERR_MASK		BIT(0)
+#define MEMERR_CPU_LSUESR_PAGE_OFFSET		0x000c
+#define  MEMERR_CPU_LSUESR_ERRWAY_RD(src)	(((src) & 0xFF000000) >> 24)
+#define  MEMERR_CPU_LSUESR_ERRINDEX_RD(src)	(((src) & 0x003F0000) >> 16)
+#define  MEMERR_CPU_LSUESR_ERRINFO_RD(src)	(((src) & 0x0000FF00) >> 8)
+#define  MEMERR_CPU_LSUESR_ERRTYPE_RD(src)	(((src) & 0x00000070) >> 4)
+#define  MEMERR_CPU_LSUESR_MULTCERR_MASK	BIT(2)
+#define  MEMERR_CPU_LSUESR_CERR_MASK		BIT(0)
+#define MEMERR_CPU_LSUECR_PAGE_OFFSET		0x0008
+#define MEMERR_CPU_MMUECR_PAGE_OFFSET		0x0010
+#define MEMERR_CPU_MMUESR_PAGE_OFFSET		0x0014
+#define  MEMERR_CPU_MMUESR_ERRWAY_RD(src)	(((src) & 0xFF000000) >> 24)
+#define  MEMERR_CPU_MMUESR_ERRINDEX_RD(src)	(((src) & 0x007F0000) >> 16)
+#define  MEMERR_CPU_MMUESR_ERRINFO_RD(src)	(((src) & 0x0000FF00) >> 8)
+#define  MEMERR_CPU_MMUESR_ERRREQSTR_LSU_MASK	BIT(7)
+#define  MEMERR_CPU_MMUESR_ERRTYPE_RD(src)	(((src) & 0x00000070) >> 4)
+#define  MEMERR_CPU_MMUESR_MULTCERR_MASK	BIT(2)
+#define  MEMERR_CPU_MMUESR_CERR_MASK		BIT(0)
+#define MEMERR_CPU_ICFESRA_PAGE_OFFSET		0x0804
+#define MEMERR_CPU_LSUESRA_PAGE_OFFSET		0x080c
+#define MEMERR_CPU_MMUESRA_PAGE_OFFSET		0x0814
+
+#define MEMERR_L2C_L2ECR_PAGE_OFFSET		0x0000
+#define MEMERR_L2C_L2ESR_PAGE_OFFSET		0x0004
+#define  MEMERR_L2C_L2ESR_ERRSYN_RD(src)	(((src) & 0xFF000000) >> 24)
+#define  MEMERR_L2C_L2ESR_ERRWAY_RD(src)	(((src) & 0x00FC0000) >> 18)
+#define  MEMERR_L2C_L2ESR_ERRCPU_RD(src)	(((src) & 0x00020000) >> 17)
+#define  MEMERR_L2C_L2ESR_ERRGROUP_RD(src)	(((src) & 0x0000E000) >> 13)
+#define  MEMERR_L2C_L2ESR_ERRACTION_RD(src)	(((src) & 0x00001C00) >> 10)
+#define  MEMERR_L2C_L2ESR_ERRTYPE_RD(src)	(((src) & 0x00000300) >> 8)
+#define  MEMERR_L2C_L2ESR_MULTUCERR_MASK	BIT(3)
+#define  MEMERR_L2C_L2ESR_MULTICERR_MASK	BIT(2)
+#define  MEMERR_L2C_L2ESR_UCERR_MASK		BIT(1)
+#define  MEMERR_L2C_L2ESR_ERR_MASK		BIT(0)
+#define MEMERR_L2C_L2EALR_PAGE_OFFSET		0x0008
+#define CPUX_L2C_L2RTOCR_PAGE_OFFSET		0x0010
+#define MEMERR_L2C_L2EAHR_PAGE_OFFSET		0x000c
+#define CPUX_L2C_L2RTOSR_PAGE_OFFSET		0x0014
+#define  MEMERR_L2C_L2RTOSR_MULTERR_MASK	BIT(1)
+#define  MEMERR_L2C_L2RTOSR_ERR_MASK		BIT(0)
+#define CPUX_L2C_L2RTOALR_PAGE_OFFSET		0x0018
+#define CPUX_L2C_L2RTOAHR_PAGE_OFFSET		0x001c
+#define MEMERR_L2C_L2ESRA_PAGE_OFFSET		0x0804
+
+/*
+ * Processor Module Domain (PMD) context - Context for a pair of processsors.
+ * Each PMD consists of 2 CPUs and a shared L2 cache. Each CPU consists of
+ * its own L1 cache.
+ */
+struct xgene_edac_pmd_ctx {
+	struct list_head	next;
+	struct device		ddev;
+	char			*name;
+	struct xgene_edac	*edac;
+	struct edac_device_ctl_info *edac_dev;
+	void __iomem		*pmd_csr;
+	u32			pmd;
+	int			version;
+};
+
+static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev,
+				    int cpu_idx)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *pg_f;
+	u32 val;
+
+	pg_f = ctx->pmd_csr + cpu_idx * CPU_CSR_STRIDE + CPU_MEMERR_CPU_PAGE;
+
+	val = readl(pg_f + MEMERR_CPU_ICFESR_PAGE_OFFSET);
+	if (val) {
+		dev_err(edac_dev->dev,
+			"CPU%d L1 memory error ICF 0x%08X Way 0x%02X Index 0x%02X Info 0x%02X\n",
+			ctx->pmd * MAX_CPU_PER_PMD + cpu_idx, val,
+			MEMERR_CPU_ICFESR_ERRWAY_RD(val),
+			MEMERR_CPU_ICFESR_ERRINDEX_RD(val),
+			MEMERR_CPU_ICFESR_ERRINFO_RD(val));
+		if (val & MEMERR_CPU_ICFESR_CERR_MASK)
+			dev_err(edac_dev->dev,
+				"One or more correctable error\n");
+		if (val & MEMERR_CPU_ICFESR_MULTCERR_MASK)
+			dev_err(edac_dev->dev, "Multiple correctable error\n");
+		switch (MEMERR_CPU_ICFESR_ERRTYPE_RD(val)) {
+		case 1:
+			dev_err(edac_dev->dev, "L1 TLB multiple hit\n");
+			break;
+		case 2:
+			dev_err(edac_dev->dev, "Way select multiple hit\n");
+			break;
+		case 3:
+			dev_err(edac_dev->dev, "Physical tag parity error\n");
+			break;
+		case 4:
+		case 5:
+			dev_err(edac_dev->dev, "L1 data parity error\n");
+			break;
+		case 6:
+			dev_err(edac_dev->dev, "L1 pre-decode parity error\n");
+			break;
+		}
+
+		/* Clear any HW errors */
+		writel(val, pg_f + MEMERR_CPU_ICFESR_PAGE_OFFSET);
+
+		if (val & (MEMERR_CPU_ICFESR_CERR_MASK |
+			   MEMERR_CPU_ICFESR_MULTCERR_MASK))
+			edac_device_handle_ce(edac_dev, 0, 0,
+					      edac_dev->ctl_name);
+	}
+
+	val = readl(pg_f + MEMERR_CPU_LSUESR_PAGE_OFFSET);
+	if (val) {
+		dev_err(edac_dev->dev,
+			"CPU%d memory error LSU 0x%08X Way 0x%02X Index 0x%02X Info 0x%02X\n",
+			ctx->pmd * MAX_CPU_PER_PMD + cpu_idx, val,
+			MEMERR_CPU_LSUESR_ERRWAY_RD(val),
+			MEMERR_CPU_LSUESR_ERRINDEX_RD(val),
+			MEMERR_CPU_LSUESR_ERRINFO_RD(val));
+		if (val & MEMERR_CPU_LSUESR_CERR_MASK)
+			dev_err(edac_dev->dev,
+				"One or more correctable error\n");
+		if (val & MEMERR_CPU_LSUESR_MULTCERR_MASK)
+			dev_err(edac_dev->dev, "Multiple correctable error\n");
+		switch (MEMERR_CPU_LSUESR_ERRTYPE_RD(val)) {
+		case 0:
+			dev_err(edac_dev->dev, "Load tag error\n");
+			break;
+		case 1:
+			dev_err(edac_dev->dev, "Load data error\n");
+			break;
+		case 2:
+			dev_err(edac_dev->dev, "WSL multihit error\n");
+			break;
+		case 3:
+			dev_err(edac_dev->dev, "Store tag error\n");
+			break;
+		case 4:
+			dev_err(edac_dev->dev,
+				"DTB multihit from load pipeline error\n");
+			break;
+		case 5:
+			dev_err(edac_dev->dev,
+				"DTB multihit from store pipeline error\n");
+			break;
+		}
+
+		/* Clear any HW errors */
+		writel(val, pg_f + MEMERR_CPU_LSUESR_PAGE_OFFSET);
+
+		if (val & (MEMERR_CPU_LSUESR_CERR_MASK |
+			   MEMERR_CPU_LSUESR_MULTCERR_MASK))
+			edac_device_handle_ce(edac_dev, 0, 0,
+					      edac_dev->ctl_name);
+	}
+
+	val = readl(pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET);
+	if (val) {
+		dev_err(edac_dev->dev,
+			"CPU%d memory error MMU 0x%08X Way 0x%02X Index 0x%02X Info 0x%02X %s\n",
+			ctx->pmd * MAX_CPU_PER_PMD + cpu_idx, val,
+			MEMERR_CPU_MMUESR_ERRWAY_RD(val),
+			MEMERR_CPU_MMUESR_ERRINDEX_RD(val),
+			MEMERR_CPU_MMUESR_ERRINFO_RD(val),
+			val & MEMERR_CPU_MMUESR_ERRREQSTR_LSU_MASK ? "LSU" :
+								     "ICF");
+		if (val & MEMERR_CPU_MMUESR_CERR_MASK)
+			dev_err(edac_dev->dev,
+				"One or more correctable error\n");
+		if (val & MEMERR_CPU_MMUESR_MULTCERR_MASK)
+			dev_err(edac_dev->dev, "Multiple correctable error\n");
+		switch (MEMERR_CPU_MMUESR_ERRTYPE_RD(val)) {
+		case 0:
+			dev_err(edac_dev->dev, "Stage 1 UTB hit error\n");
+			break;
+		case 1:
+			dev_err(edac_dev->dev, "Stage 1 UTB miss error\n");
+			break;
+		case 2:
+			dev_err(edac_dev->dev, "Stage 1 UTB allocate error\n");
+			break;
+		case 3:
+			dev_err(edac_dev->dev,
+				"TMO operation single bank error\n");
+			break;
+		case 4:
+			dev_err(edac_dev->dev, "Stage 2 UTB error\n");
+			break;
+		case 5:
+			dev_err(edac_dev->dev, "Stage 2 UTB miss error\n");
+			break;
+		case 6:
+			dev_err(edac_dev->dev, "Stage 2 UTB allocate error\n");
+			break;
+		case 7:
+			dev_err(edac_dev->dev,
+				"TMO operation multiple bank error\n");
+			break;
+		}
+
+		/* Clear any HW errors */
+		writel(val, pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET);
+
+		edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name);
+	}
+}
+
+static void xgene_edac_pmd_l2_check(struct edac_device_ctl_info *edac_dev)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *pg_d;
+	void __iomem *pg_e;
+	u32 val_hi;
+	u32 val_lo;
+	u32 val;
+
+	/* Check L2 */
+	pg_e = ctx->pmd_csr + CPU_MEMERR_L2C_PAGE;
+	val = readl(pg_e + MEMERR_L2C_L2ESR_PAGE_OFFSET);
+	if (val) {
+		val_lo = readl(pg_e + MEMERR_L2C_L2EALR_PAGE_OFFSET);
+		val_hi = readl(pg_e + MEMERR_L2C_L2EAHR_PAGE_OFFSET);
+		dev_err(edac_dev->dev,
+			"PMD%d memory error L2C L2ESR 0x%08X @ 0x%08X.%08X\n",
+			ctx->pmd, val, val_hi, val_lo);
+		dev_err(edac_dev->dev,
+			"ErrSyndrome 0x%02X ErrWay 0x%02X ErrCpu %d ErrGroup 0x%02X ErrAction 0x%02X\n",
+			MEMERR_L2C_L2ESR_ERRSYN_RD(val),
+			MEMERR_L2C_L2ESR_ERRWAY_RD(val),
+			MEMERR_L2C_L2ESR_ERRCPU_RD(val),
+			MEMERR_L2C_L2ESR_ERRGROUP_RD(val),
+			MEMERR_L2C_L2ESR_ERRACTION_RD(val));
+
+		if (val & MEMERR_L2C_L2ESR_ERR_MASK)
+			dev_err(edac_dev->dev,
+				"One or more correctable error\n");
+		if (val & MEMERR_L2C_L2ESR_MULTICERR_MASK)
+			dev_err(edac_dev->dev, "Multiple correctable error\n");
+		if (val & MEMERR_L2C_L2ESR_UCERR_MASK)
+			dev_err(edac_dev->dev,
+				"One or more uncorrectable error\n");
+		if (val & MEMERR_L2C_L2ESR_MULTUCERR_MASK)
+			dev_err(edac_dev->dev,
+				"Multiple uncorrectable error\n");
+
+		switch (MEMERR_L2C_L2ESR_ERRTYPE_RD(val)) {
+		case 0:
+			dev_err(edac_dev->dev, "Outbound SDB parity error\n");
+			break;
+		case 1:
+			dev_err(edac_dev->dev, "Inbound SDB parity error\n");
+			break;
+		case 2:
+			dev_err(edac_dev->dev, "Tag ECC error\n");
+			break;
+		case 3:
+			dev_err(edac_dev->dev, "Data ECC error\n");
+			break;
+		}
+
+		/* Clear any HW errors */
+		writel(val, pg_e + MEMERR_L2C_L2ESR_PAGE_OFFSET);
+
+		if (val & (MEMERR_L2C_L2ESR_ERR_MASK |
+			   MEMERR_L2C_L2ESR_MULTICERR_MASK))
+			edac_device_handle_ce(edac_dev, 0, 0,
+					      edac_dev->ctl_name);
+		if (val & (MEMERR_L2C_L2ESR_UCERR_MASK |
+			   MEMERR_L2C_L2ESR_MULTUCERR_MASK))
+			edac_device_handle_ue(edac_dev, 0, 0,
+					      edac_dev->ctl_name);
+	}
+
+	/* Check if any memory request timed out on L2 cache */
+	pg_d = ctx->pmd_csr + CPU_L2C_PAGE;
+	val = readl(pg_d + CPUX_L2C_L2RTOSR_PAGE_OFFSET);
+	if (val) {
+		val_lo = readl(pg_d + CPUX_L2C_L2RTOALR_PAGE_OFFSET);
+		val_hi = readl(pg_d + CPUX_L2C_L2RTOAHR_PAGE_OFFSET);
+		dev_err(edac_dev->dev,
+			"PMD%d L2C error L2C RTOSR 0x%08X @ 0x%08X.%08X\n",
+			ctx->pmd, val, val_hi, val_lo);
+		writel(val, pg_d + CPUX_L2C_L2RTOSR_PAGE_OFFSET);
+	}
+}
+
+static void xgene_edac_pmd_check(struct edac_device_ctl_info *edac_dev)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	unsigned int pcp_hp_stat;
+	int i;
+
+	xgene_edac_pcp_rd(ctx->edac, PCPHPERRINTSTS, &pcp_hp_stat);
+	if (!((PMD0_MERR_MASK << ctx->pmd) & pcp_hp_stat))
+		return;
+
+	/* Check CPU L1 error */
+	for (i = 0; i < MAX_CPU_PER_PMD; i++)
+		xgene_edac_pmd_l1_check(edac_dev, i);
+
+	/* Check CPU L2 error */
+	xgene_edac_pmd_l2_check(edac_dev);
+}
+
+static void xgene_edac_pmd_cpu_hw_cfg(struct edac_device_ctl_info *edac_dev,
+				      int cpu)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *pg_f = ctx->pmd_csr + cpu * CPU_CSR_STRIDE +
+			     CPU_MEMERR_CPU_PAGE;
+
+	/*
+	 * Enable CPU memory error:
+	 *  MEMERR_CPU_ICFESRA, MEMERR_CPU_LSUESRA, and MEMERR_CPU_MMUESRA
+	 */
+	writel(0x00000301, pg_f + MEMERR_CPU_ICFECR_PAGE_OFFSET);
+	writel(0x00000301, pg_f + MEMERR_CPU_LSUECR_PAGE_OFFSET);
+	writel(0x00000101, pg_f + MEMERR_CPU_MMUECR_PAGE_OFFSET);
+}
+
+static void xgene_edac_pmd_hw_cfg(struct edac_device_ctl_info *edac_dev)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *pg_d = ctx->pmd_csr + CPU_L2C_PAGE;
+	void __iomem *pg_e = ctx->pmd_csr + CPU_MEMERR_L2C_PAGE;
+
+	/* Enable PMD memory error - MEMERR_L2C_L2ECR and L2C_L2RTOCR */
+	writel(0x00000703, pg_e + MEMERR_L2C_L2ECR_PAGE_OFFSET);
+	/* Configure L2C HW request time out feature if supported */
+	if (ctx->version > 1)
+		writel(0x00000119, pg_d + CPUX_L2C_L2RTOCR_PAGE_OFFSET);
+}
+
+static void xgene_edac_pmd_hw_ctl(struct edac_device_ctl_info *edac_dev,
+				  bool enable)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	int i;
+
+	/* Enable PMD error interrupt */
+	if (edac_dev->op_state == OP_RUNNING_INTERRUPT) {
+		if (enable)
+			xgene_edac_pcp_clrbits(ctx->edac, PCPHPERRINTMSK,
+					       PMD0_MERR_MASK << ctx->pmd);
+		else
+			xgene_edac_pcp_setbits(ctx->edac, PCPHPERRINTMSK,
+					       PMD0_MERR_MASK << ctx->pmd);
+	}
+
+	if (enable) {
+		xgene_edac_pmd_hw_cfg(edac_dev);
+
+		/* Two CPUs per a PMD */
+		for (i = 0; i < MAX_CPU_PER_PMD; i++)
+			xgene_edac_pmd_cpu_hw_cfg(edac_dev, i);
+	}
+}
+
+static ssize_t xgene_edac_pmd_l1_inject_ctrl_write(struct file *file,
+						   const char __user *data,
+						   size_t count, loff_t *ppos)
+{
+	struct edac_device_ctl_info *edac_dev = file->private_data;
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *cpux_pg_f;
+	int i;
+
+	for (i = 0; i < MAX_CPU_PER_PMD; i++) {
+		cpux_pg_f = ctx->pmd_csr + i * CPU_CSR_STRIDE +
+			    CPU_MEMERR_CPU_PAGE;
+
+		writel(MEMERR_CPU_ICFESR_MULTCERR_MASK |
+		       MEMERR_CPU_ICFESR_CERR_MASK,
+		       cpux_pg_f + MEMERR_CPU_ICFESRA_PAGE_OFFSET);
+		writel(MEMERR_CPU_LSUESR_MULTCERR_MASK |
+		       MEMERR_CPU_LSUESR_CERR_MASK,
+		       cpux_pg_f + MEMERR_CPU_LSUESRA_PAGE_OFFSET);
+		writel(MEMERR_CPU_MMUESR_MULTCERR_MASK |
+		       MEMERR_CPU_MMUESR_CERR_MASK,
+		       cpux_pg_f + MEMERR_CPU_MMUESRA_PAGE_OFFSET);
+	}
+	return count;
+}
+
+static ssize_t xgene_edac_pmd_l2_inject_ctrl_write(struct file *file,
+						   const char __user *data,
+						   size_t count, loff_t *ppos)
+{
+	struct edac_device_ctl_info *edac_dev = file->private_data;
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	void __iomem *pg_e = ctx->pmd_csr + CPU_MEMERR_L2C_PAGE;
+
+	writel(MEMERR_L2C_L2ESR_MULTUCERR_MASK |
+	       MEMERR_L2C_L2ESR_MULTICERR_MASK |
+	       MEMERR_L2C_L2ESR_UCERR_MASK |
+	       MEMERR_L2C_L2ESR_ERR_MASK,
+	       pg_e + MEMERR_L2C_L2ESRA_PAGE_OFFSET);
+	return count;
+}
+
+static const struct file_operations xgene_edac_pmd_debug_inject_fops[] = {
+	{
+	.open = simple_open,
+	.write = xgene_edac_pmd_l1_inject_ctrl_write,
+	.llseek = generic_file_llseek, },
+	{
+	.open = simple_open,
+	.write = xgene_edac_pmd_l2_inject_ctrl_write,
+	.llseek = generic_file_llseek, },
+	{ }
+};
+
+static void xgene_edac_pmd_create_debugfs_nodes(
+	struct edac_device_ctl_info *edac_dev)
+{
+	struct xgene_edac_pmd_ctx *ctx = edac_dev->pvt_info;
+	struct dentry *edac_debugfs;
+	char name[30];
+
+	if (!IS_ENABLED(CONFIG_EDAC_DEBUG))
+		return;
+
+	/*
+	 * Todo: Switch to common EDAC debug file system for edac device
+	 *       when available.
+	 */
+	if (!ctx->edac->dfs) {
+		ctx->edac->dfs = debugfs_create_dir(edac_dev->dev->kobj.name,
+						    NULL);
+		if (!ctx->edac->dfs)
+			return;
+	}
+	sprintf(name, "PMD%d", ctx->pmd);
+	edac_debugfs = debugfs_create_dir(name, ctx->edac->dfs);
+	if (!edac_debugfs)
+		return;
+
+	debugfs_create_file("l1_inject_ctrl", S_IWUSR, edac_debugfs, edac_dev,
+			    &xgene_edac_pmd_debug_inject_fops[0]);
+	debugfs_create_file("l2_inject_ctrl", S_IWUSR, edac_debugfs, edac_dev,
+			    &xgene_edac_pmd_debug_inject_fops[1]);
+}
+
+static int xgene_edac_pmd_available(u32 efuse, int pmd)
+{
+	return (efuse & (1 << pmd)) ? 0 : 1;
+}
+
+static int xgene_edac_pmd_add(struct xgene_edac *edac, struct device_node *np,
+			      int version)
+{
+	struct edac_device_ctl_info *edac_dev;
+	struct xgene_edac_pmd_ctx *ctx;
+	struct resource res;
+	char edac_name[10];
+	u32 pmd;
+	int rc;
+	u32 val;
+
+	if (!devres_open_group(edac->dev, xgene_edac_pmd_add, GFP_KERNEL))
+		return -ENOMEM;
+
+	/* Determine if this PMD is disabled */
+	if (of_property_read_u32(np, "pmd-controller", &pmd)) {
+		dev_err(edac->dev, "no pmd-controller property\n");
+		rc = -ENODEV;
+		goto err_group;
+	}
+	rc = regmap_read(edac->efuse_map, 0, &val);
+	if (rc)
+		goto err_group;
+	if (!xgene_edac_pmd_available(val, pmd)) {
+		rc = -ENODEV;
+		goto err_group;
+	}
+
+	sprintf(edac_name, "l2c%d", pmd);
+	edac_dev = edac_device_alloc_ctl_info(sizeof(*ctx),
+					      edac_name, 1, "l2c", 1, 2, NULL,
+					      0, edac_device_alloc_index());
+	if (!edac_dev) {
+		rc = -ENOMEM;
+		goto err_group;
+	}
+
+	ctx = edac_dev->pvt_info;
+	ctx->name = "xgene_pmd_err";
+	ctx->pmd = pmd;
+	ctx->edac = edac;
+	ctx->edac_dev = edac_dev;
+	ctx->ddev = *edac->dev;
+	ctx->version = version;
+	edac_dev->dev = &ctx->ddev;
+	edac_dev->ctl_name = ctx->name;
+	edac_dev->dev_name = ctx->name;
+	edac_dev->mod_name = EDAC_MOD_STR;
+
+	rc = of_address_to_resource(np, 0, &res);
+	if (rc < 0) {
+		dev_err(edac->dev, "no PMD resource address\n");
+		goto err_free;
+	}
+	ctx->pmd_csr = devm_ioremap_resource(edac->dev, &res);
+	if (IS_ERR(ctx->pmd_csr)) {
+		dev_err(edac->dev,
+			"devm_ioremap_resource failed for PMD resource address\n");
+		rc = PTR_ERR(ctx->pmd_csr);
+		goto err_free;
+	}
+
+	if (edac_op_state == EDAC_OPSTATE_POLL)
+		edac_dev->edac_check = xgene_edac_pmd_check;
+
+	xgene_edac_pmd_create_debugfs_nodes(edac_dev);
+
+	rc = edac_device_add_device(edac_dev);
+	if (rc > 0) {
+		dev_err(edac->dev, "edac_device_add_device failed\n");
+		rc = -ENOMEM;
+		goto err_free;
+	}
+
+	if (edac_op_state == EDAC_OPSTATE_INT)
+		edac_dev->op_state = OP_RUNNING_INTERRUPT;
+
+	list_add(&ctx->next, &edac->pmds);
+
+	xgene_edac_pmd_hw_ctl(edac_dev, 1);
+
+	devres_remove_group(edac->dev, xgene_edac_pmd_add);
+
+	dev_info(edac->dev, "X-Gene EDAC PMD%d registered\n", ctx->pmd);
+	return 0;
+
+err_free:
+	edac_device_free_ctl_info(edac_dev);
+err_group:
+	devres_release_group(edac->dev, xgene_edac_pmd_add);
+	return rc;
+}
+
+static int xgene_edac_pmd_remove(struct xgene_edac_pmd_ctx *pmd)
+{
+	struct edac_device_ctl_info *edac_dev = pmd->edac_dev;
+
+	xgene_edac_pmd_hw_ctl(edac_dev, 0);
+	edac_device_del_device(edac_dev->dev);
+	edac_device_free_ctl_info(edac_dev);
+	return 0;
+}
+
+static irqreturn_t xgene_edac_isr(int irq, void *dev_id)
+{
+	struct xgene_edac *ctx = dev_id;
+	struct xgene_edac_pmd_ctx *pmd;
+	unsigned int pcp_hp_stat;
+	unsigned int pcp_lp_stat;
+
+	xgene_edac_pcp_rd(ctx, PCPHPERRINTSTS, &pcp_hp_stat);
+	xgene_edac_pcp_rd(ctx, PCPLPERRINTSTS, &pcp_lp_stat);
+	if ((MCU_UNCORR_ERR_MASK & pcp_hp_stat) ||
+	    (MCU_CTL_ERR_MASK & pcp_hp_stat) ||
+	    (MCU_CORR_ERR_MASK & pcp_lp_stat)) {
+		struct xgene_edac_mc_ctx *mcu;
+
+		list_for_each_entry(mcu, &ctx->mcus, next) {
+			xgene_edac_mc_check(mcu->mci);
+		}
+	}
+
+	list_for_each_entry(pmd, &ctx->pmds, next) {
+		if ((PMD0_MERR_MASK << pmd->pmd) & pcp_hp_stat)
+			xgene_edac_pmd_check(pmd->edac_dev);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xgene_edac_probe(struct platform_device *pdev)
+{
+	struct xgene_edac *edac;
+	struct device_node *child;
+	struct resource *res;
+	int rc;
+
+	edac = devm_kzalloc(&pdev->dev, sizeof(*edac), GFP_KERNEL);
+	if (!edac)
+		return -ENOMEM;
+
+	edac->dev = &pdev->dev;
+	platform_set_drvdata(pdev, edac);
+	INIT_LIST_HEAD(&edac->mcus);
+	INIT_LIST_HEAD(&edac->pmds);
+	spin_lock_init(&edac->lock);
+	mutex_init(&edac->mc_lock);
+
+	edac->csw_map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							"regmap-csw");
+	if (IS_ERR(edac->csw_map)) {
+		dev_err(edac->dev, "unable to get syscon regmap csw\n");
+		rc = PTR_ERR(edac->csw_map);
+		goto out_err;
+	}
+
+	edac->mcba_map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							 "regmap-mcba");
+	if (IS_ERR(edac->mcba_map)) {
+		dev_err(edac->dev, "unable to get syscon regmap mcba\n");
+		rc = PTR_ERR(edac->mcba_map);
+		goto out_err;
+	}
+
+	edac->mcbb_map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							 "regmap-mcbb");
+	if (IS_ERR(edac->mcbb_map)) {
+		dev_err(edac->dev, "unable to get syscon regmap mcbb\n");
+		rc = PTR_ERR(edac->mcbb_map);
+		goto out_err;
+	}
+	edac->efuse_map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
+							  "regmap-efuse");
+	if (IS_ERR(edac->efuse_map)) {
+		dev_err(edac->dev, "unable to get syscon regmap efuse\n");
+		rc = PTR_ERR(edac->efuse_map);
+		goto out_err;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	edac->pcp_csr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(edac->pcp_csr)) {
+		dev_err(&pdev->dev, "no PCP resource address\n");
+		rc = PTR_ERR(edac->pcp_csr);
+		goto out_err;
+	}
+
+	if (edac_op_state == EDAC_OPSTATE_INT) {
+		int irq;
+		int i;
+
+		for (i = 0; i < 3; i++) {
+			irq = platform_get_irq(pdev, i);
+			if (irq < 0) {
+				dev_err(&pdev->dev, "No IRQ resource\n");
+				rc = -EINVAL;
+				goto out_err;
+			}
+			rc = devm_request_irq(&pdev->dev, irq,
+					      xgene_edac_isr, IRQF_SHARED,
+					      dev_name(&pdev->dev), edac);
+			if (rc) {
+				dev_err(&pdev->dev,
+					"Could not request IRQ %d\n", irq);
+				goto out_err;
+			}
+		}
+	}
+
+	for_each_child_of_node(pdev->dev.of_node, child) {
+		if (!of_device_is_available(child))
+			continue;
+		if (of_device_is_compatible(child, "apm,xgene-edac-mc"))
+			xgene_edac_mc_add(edac, child);
+		if (of_device_is_compatible(child, "apm,xgene-edac-pmd"))
+			xgene_edac_pmd_add(edac, child, 1);
+		if (of_device_is_compatible(child, "apm,xgene-edac-pmd-v2"))
+			xgene_edac_pmd_add(edac, child, 2);
+	}
+
+	return 0;
+
+out_err:
+	return rc;
+}
+
+static int xgene_edac_remove(struct platform_device *pdev)
+{
+	struct xgene_edac *edac = dev_get_drvdata(&pdev->dev);
+	struct xgene_edac_mc_ctx *mcu;
+	struct xgene_edac_mc_ctx *temp_mcu;
+	struct xgene_edac_pmd_ctx *pmd;
+	struct xgene_edac_pmd_ctx *temp_pmd;
+
+	list_for_each_entry_safe(mcu, temp_mcu, &edac->mcus, next) {
+		xgene_edac_mc_remove(mcu);
+	}
+
+	list_for_each_entry_safe(pmd, temp_pmd, &edac->pmds, next) {
+		xgene_edac_pmd_remove(pmd);
+	}
+	return 0;
+}
+
+static const struct of_device_id xgene_edac_of_match[] = {
+	{ .compatible = "apm,xgene-edac" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgene_edac_of_match);
+
+static struct platform_driver xgene_edac_driver = {
+	.probe = xgene_edac_probe,
+	.remove = xgene_edac_remove,
+	.driver = {
+		.name = "xgene-edac",
+		.owner = THIS_MODULE,
+		.of_match_table = xgene_edac_of_match,
+	},
+};
+
+static int __init xgene_edac_init(void)
+{
+	int rc;
+
+	/* Make sure error reporting method is sane */
+	switch (edac_op_state) {
+	case EDAC_OPSTATE_POLL:
+	case EDAC_OPSTATE_INT:
+		break;
+	default:
+		edac_op_state = EDAC_OPSTATE_INT;
+		break;
+	}
+
+	rc = platform_driver_register(&xgene_edac_driver);
+	if (rc) {
+		edac_printk(KERN_ERR, EDAC_MOD_STR,
+			    "EDAC fails to register\n");
+		goto reg_failed;
+	}
+
+	return 0;
+
+reg_failed:
+	return rc;
+}
+module_init(xgene_edac_init);
+
+static void __exit xgene_edac_exit(void)
+{
+	platform_driver_unregister(&xgene_edac_driver);
+}
+module_exit(xgene_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Feng Kan <fkan@apm.com>");
+MODULE_DESCRIPTION("APM X-Gene EDAC driver");
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state,
+		 "EDAC error reporting state: 0=Poll, 2=Interrupt");
diff --git a/drivers/extcon/extcon-usb-gpio.c b/drivers/extcon/extcon-usb-gpio.c
index de67fce18984..e45d1f13f445 100644
--- a/drivers/extcon/extcon-usb-gpio.c
+++ b/drivers/extcon/extcon-usb-gpio.c
@@ -119,6 +119,18 @@ static int usb_extcon_probe(struct platform_device *pdev)
 		return PTR_ERR(info->id_gpiod);
 	}
 
+	info->edev = devm_extcon_dev_allocate(dev, usb_extcon_cable);
+	if (IS_ERR(info->edev)) {
+		dev_err(dev, "failed to allocate extcon device\n");
+		return -ENOMEM;
+	}
+
+	ret = devm_extcon_dev_register(dev, info->edev);
+	if (ret < 0) {
+		dev_err(dev, "failed to register extcon device\n");
+		return ret;
+	}
+
 	ret = gpiod_set_debounce(info->id_gpiod,
 				 USB_GPIO_DEBOUNCE_MS * 1000);
 	if (ret < 0)
@@ -142,18 +154,6 @@ static int usb_extcon_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	info->edev = devm_extcon_dev_allocate(dev, usb_extcon_cable);
-	if (IS_ERR(info->edev)) {
-		dev_err(dev, "failed to allocate extcon device\n");
-		return -ENOMEM;
-	}
-
-	ret = devm_extcon_dev_register(dev, info->edev);
-	if (ret < 0) {
-		dev_err(dev, "failed to register extcon device\n");
-		return ret;
-	}
-
 	platform_set_drvdata(pdev, info);
 	device_init_wakeup(dev, 1);
 
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index c22606fe3d44..6bac03999fd4 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1611,7 +1611,6 @@ static struct scsi_host_template scsi_driver_template = {
 	.this_id		= -1,
 	.sg_tablesize		= SG_ALL,
 	.use_clustering		= ENABLE_CLUSTERING,
-	.cmd_per_lun		= 1,
 	.can_queue		= 1,
 	.sdev_attrs		= sbp2_scsi_sysfs_attrs,
 };
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 6e45a43ffe84..97b1616aa391 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -499,19 +499,19 @@ static int __init dmi_present(const u8 *buf)
 	buf += 16;
 
 	if (memcmp(buf, "_DMI_", 5) == 0 && dmi_checksum(buf, 15)) {
+		if (smbios_ver)
+			dmi_ver = smbios_ver;
+		else
+			dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F);
 		dmi_num = get_unaligned_le16(buf + 12);
 		dmi_len = get_unaligned_le16(buf + 6);
 		dmi_base = get_unaligned_le32(buf + 8);
 
 		if (dmi_walk_early(dmi_decode) == 0) {
 			if (smbios_ver) {
-				dmi_ver = smbios_ver;
-				pr_info("SMBIOS %d.%d%s present.\n",
-					dmi_ver >> 8, dmi_ver & 0xFF,
-					(dmi_ver < 0x0300) ? "" : ".x");
+				pr_info("SMBIOS %d.%d present.\n",
+				       dmi_ver >> 8, dmi_ver & 0xFF);
 			} else {
-				dmi_ver = (buf[14] & 0xF0) << 4 |
-					   (buf[14] & 0x0F);
 				pr_info("Legacy DMI %d.%d present.\n",
 				       dmi_ver >> 8, dmi_ver & 0xFF);
 			}
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 8de4da5c9ab6..54071c148340 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -18,6 +18,11 @@ config EFI_VARS
 	  Subsequent efibootmgr releases may be found at:
 	  <http://github.com/vathpela/efibootmgr>
 
+config EFI_ESRT
+	bool
+	depends on EFI && !IA64
+	default y
+
 config EFI_VARS_PSTORE
 	tristate "Register efivars backend for pstore"
 	depends on EFI_VARS && PSTORE
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index d8be608a9f3b..6fd3da938717 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -3,6 +3,7 @@
 #
 obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
+obj-$(CONFIG_EFI_ESRT)			+= esrt.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
 obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 3061bb8629dc..ca617f40574a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -39,6 +39,7 @@ struct efi __read_mostly efi = {
 	.fw_vendor  = EFI_INVALID_TABLE_ADDR,
 	.runtime    = EFI_INVALID_TABLE_ADDR,
 	.config_table  = EFI_INVALID_TABLE_ADDR,
+	.esrt       = EFI_INVALID_TABLE_ADDR,
 };
 EXPORT_SYMBOL(efi);
 
@@ -64,7 +65,7 @@ static int __init parse_efi_cmdline(char *str)
 }
 early_param("efi", parse_efi_cmdline);
 
-static struct kobject *efi_kobj;
+struct kobject *efi_kobj;
 static struct kobject *efivars_kobj;
 
 /*
@@ -85,10 +86,15 @@ static ssize_t systab_show(struct kobject *kobj,
 		str += sprintf(str, "ACPI20=0x%lx\n", efi.acpi20);
 	if (efi.acpi != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "ACPI=0x%lx\n", efi.acpi);
-	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
-		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
+	/*
+	 * If both SMBIOS and SMBIOS3 entry points are implemented, the
+	 * SMBIOS3 entry point shall be preferred, so we list it first to
+	 * let applications stop parsing after the first match.
+	 */
 	if (efi.smbios3 != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "SMBIOS3=0x%lx\n", efi.smbios3);
+	if (efi.smbios != EFI_INVALID_TABLE_ADDR)
+		str += sprintf(str, "SMBIOS=0x%lx\n", efi.smbios);
 	if (efi.hcdp != EFI_INVALID_TABLE_ADDR)
 		str += sprintf(str, "HCDP=0x%lx\n", efi.hcdp);
 	if (efi.boot_info != EFI_INVALID_TABLE_ADDR)
@@ -232,6 +238,84 @@ err_put:
 
 subsys_initcall(efisubsys_init);
 
+/*
+ * Find the efi memory descriptor for a given physical address.  Given a
+ * physicall address, determine if it exists within an EFI Memory Map entry,
+ * and if so, populate the supplied memory descriptor with the appropriate
+ * data.
+ */
+int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+{
+	struct efi_memory_map *map = efi.memmap;
+	void *p, *e;
+
+	if (!efi_enabled(EFI_MEMMAP)) {
+		pr_err_once("EFI_MEMMAP is not enabled.\n");
+		return -EINVAL;
+	}
+
+	if (!map) {
+		pr_err_once("efi.memmap is not set.\n");
+		return -EINVAL;
+	}
+	if (!out_md) {
+		pr_err_once("out_md is null.\n");
+		return -EINVAL;
+        }
+	if (WARN_ON_ONCE(!map->phys_map))
+		return -EINVAL;
+	if (WARN_ON_ONCE(map->nr_map == 0) || WARN_ON_ONCE(map->desc_size == 0))
+		return -EINVAL;
+
+	e = map->phys_map + map->nr_map * map->desc_size;
+	for (p = map->phys_map; p < e; p += map->desc_size) {
+		efi_memory_desc_t *md;
+		u64 size;
+		u64 end;
+
+		/*
+		 * If a driver calls this after efi_free_boot_services,
+		 * ->map will be NULL, and the target may also not be mapped.
+		 * So just always get our own virtual map on the CPU.
+		 *
+		 */
+		md = early_memremap((phys_addr_t)p, sizeof (*md));
+		if (!md) {
+			pr_err_once("early_memremap(%p, %zu) failed.\n",
+				    p, sizeof (*md));
+			return -ENOMEM;
+		}
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+		    md->type != EFI_BOOT_SERVICES_DATA &&
+		    md->type != EFI_RUNTIME_SERVICES_DATA) {
+			early_memunmap(md, sizeof (*md));
+			continue;
+		}
+
+		size = md->num_pages << EFI_PAGE_SHIFT;
+		end = md->phys_addr + size;
+		if (phys_addr >= md->phys_addr && phys_addr < end) {
+			memcpy(out_md, md, sizeof(*out_md));
+			early_memunmap(md, sizeof (*md));
+			return 0;
+		}
+
+		early_memunmap(md, sizeof (*md));
+	}
+	pr_err_once("requested map not found.\n");
+	return -ENOENT;
+}
+
+/*
+ * Calculate the highest address of an efi memory descriptor.
+ */
+u64 __init efi_mem_desc_end(efi_memory_desc_t *md)
+{
+	u64 size = md->num_pages << EFI_PAGE_SHIFT;
+	u64 end = md->phys_addr + size;
+	return end;
+}
 
 /*
  * We can't ioremap data in EFI boot services RAM, because we've already mapped
@@ -274,6 +358,7 @@ static __initdata efi_config_table_type_t common_tables[] = {
 	{SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
 	{SMBIOS3_TABLE_GUID, "SMBIOS 3.0", &efi.smbios3},
 	{UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+	{EFI_SYSTEM_RESOURCE_TABLE_GUID, "ESRT", &efi.esrt},
 	{NULL_GUID, NULL, NULL},
 };
 
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 7b2e0496e0c0..756eca8c4cf8 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -535,7 +535,7 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
  * efivar_create_sysfs_entry - create a new entry in sysfs
  * @new_var: efivar entry to create
  *
- * Returns 1 on failure, 0 on success
+ * Returns 0 on success, negative error code on failure
  */
 static int
 efivar_create_sysfs_entry(struct efivar_entry *new_var)
@@ -544,6 +544,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	char *short_name;
 	unsigned long variable_name_size;
 	efi_char16_t *variable_name;
+	int ret;
 
 	variable_name = new_var->var.VariableName;
 	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
@@ -558,7 +559,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	short_name = kzalloc(short_name_size, GFP_KERNEL);
 
 	if (!short_name)
-		return 1;
+		return -ENOMEM;
 
 	/* Convert Unicode to normal chars (assume top bits are 0),
 	   ala UTF-8 */
@@ -574,11 +575,11 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 
 	new_var->kobj.kset = efivars_kset;
 
-	i = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
+	ret = kobject_init_and_add(&new_var->kobj, &efivar_ktype,
 				   NULL, "%s", short_name);
 	kfree(short_name);
-	if (i)
-		return 1;
+	if (ret)
+		return ret;
 
 	kobject_uevent(&new_var->kobj, KOBJ_ADD);
 	efivar_entry_add(new_var, &efivar_sysfs_list);
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
new file mode 100644
index 000000000000..a5b95d61ae71
--- /dev/null
+++ b/drivers/firmware/efi/esrt.c
@@ -0,0 +1,471 @@
+/*
+ * esrt.c
+ *
+ * This module exports EFI System Resource Table (ESRT) entries into userspace
+ * through the sysfs file system. The ESRT provides a read-only catalog of
+ * system components for which the system accepts firmware upgrades via UEFI's
+ * "Capsule Update" feature. This module allows userland utilities to evaluate
+ * what firmware updates can be applied to this system, and potentially arrange
+ * for those updates to occur.
+ *
+ * Data is currently found below /sys/firmware/efi/esrt/...
+ */
+#define pr_fmt(fmt) "esrt: " fmt
+
+#include <linux/capability.h>
+#include <linux/device.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <asm/io.h>
+#include <asm/early_ioremap.h>
+
+struct efi_system_resource_entry_v1 {
+	efi_guid_t	fw_class;
+	u32		fw_type;
+	u32		fw_version;
+	u32		lowest_supported_fw_version;
+	u32		capsule_flags;
+	u32		last_attempt_version;
+	u32		last_attempt_status;
+};
+
+/*
+ * _count and _version are what they seem like.  _max is actually just
+ * accounting info for the firmware when creating the table; it should never
+ * have been exposed to us.  To wit, the spec says:
+ * The maximum number of resource array entries that can be within the
+ * table without reallocating the table, must not be zero.
+ * Since there's no guidance about what that means in terms of memory layout,
+ * it means nothing to us.
+ */
+struct efi_system_resource_table {
+	u32	fw_resource_count;
+	u32	fw_resource_count_max;
+	u64	fw_resource_version;
+	u8	entries[];
+};
+
+static phys_addr_t esrt_data;
+static size_t esrt_data_size;
+
+static struct efi_system_resource_table *esrt;
+
+struct esre_entry {
+	union {
+		struct efi_system_resource_entry_v1 *esre1;
+	} esre;
+
+	struct kobject kobj;
+	struct list_head list;
+};
+
+/* global list of esre_entry. */
+static LIST_HEAD(entry_list);
+
+/* entry attribute */
+struct esre_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct esre_entry *entry, char *buf);
+	ssize_t (*store)(struct esre_entry *entry,
+			 const char *buf, size_t count);
+};
+
+static struct esre_entry *to_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct esre_entry, kobj);
+}
+
+static struct esre_attribute *to_attr(struct attribute *attr)
+{
+	return container_of(attr, struct esre_attribute, attr);
+}
+
+static ssize_t esre_attr_show(struct kobject *kobj,
+			      struct attribute *_attr, char *buf)
+{
+	struct esre_entry *entry = to_entry(kobj);
+	struct esre_attribute *attr = to_attr(_attr);
+
+	/* Don't tell normal users what firmware versions we've got... */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return attr->show(entry, buf);
+}
+
+static const struct sysfs_ops esre_attr_ops = {
+	.show = esre_attr_show,
+};
+
+/* Generic ESRT Entry ("ESRE") support. */
+static ssize_t esre_fw_class_show(struct esre_entry *entry, char *buf)
+{
+	char *str = buf;
+
+	efi_guid_to_str(&entry->esre.esre1->fw_class, str);
+	str += strlen(str);
+	str += sprintf(str, "\n");
+
+	return str - buf;
+}
+
+static struct esre_attribute esre_fw_class = __ATTR(fw_class, 0400,
+	esre_fw_class_show, NULL);
+
+#define esre_attr_decl(name, size, fmt) \
+static ssize_t esre_##name##_show(struct esre_entry *entry, char *buf) \
+{ \
+	return sprintf(buf, fmt "\n", \
+		       le##size##_to_cpu(entry->esre.esre1->name)); \
+} \
+\
+static struct esre_attribute esre_##name = __ATTR(name, 0400, \
+	esre_##name##_show, NULL)
+
+esre_attr_decl(fw_type, 32, "%u");
+esre_attr_decl(fw_version, 32, "%u");
+esre_attr_decl(lowest_supported_fw_version, 32, "%u");
+esre_attr_decl(capsule_flags, 32, "0x%x");
+esre_attr_decl(last_attempt_version, 32, "%u");
+esre_attr_decl(last_attempt_status, 32, "%u");
+
+static struct attribute *esre1_attrs[] = {
+	&esre_fw_class.attr,
+	&esre_fw_type.attr,
+	&esre_fw_version.attr,
+	&esre_lowest_supported_fw_version.attr,
+	&esre_capsule_flags.attr,
+	&esre_last_attempt_version.attr,
+	&esre_last_attempt_status.attr,
+	NULL
+};
+static void esre_release(struct kobject *kobj)
+{
+	struct esre_entry *entry = to_entry(kobj);
+
+	list_del(&entry->list);
+	kfree(entry);
+}
+
+static struct kobj_type esre1_ktype = {
+	.release = esre_release,
+	.sysfs_ops = &esre_attr_ops,
+	.default_attrs = esre1_attrs,
+};
+
+
+static struct kobject *esrt_kobj;
+static struct kset *esrt_kset;
+
+static int esre_create_sysfs_entry(void *esre, int entry_num)
+{
+	struct esre_entry *entry;
+	char name[20];
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	sprintf(name, "entry%d", entry_num);
+
+	entry->kobj.kset = esrt_kset;
+
+	if (esrt->fw_resource_version == 1) {
+		int rc = 0;
+
+		entry->esre.esre1 = esre;
+		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
+					  "%s", name);
+		if (rc) {
+			kfree(entry);
+			return rc;
+		}
+	}
+
+	list_add_tail(&entry->list, &entry_list);
+	return 0;
+}
+
+/* support for displaying ESRT fields at the top level */
+#define esrt_attr_decl(name, size, fmt) \
+static ssize_t esrt_##name##_show(struct kobject *kobj, \
+				  struct kobj_attribute *attr, char *buf)\
+{ \
+	return sprintf(buf, fmt "\n", le##size##_to_cpu(esrt->name)); \
+} \
+\
+static struct kobj_attribute esrt_##name = __ATTR(name, 0400, \
+	esrt_##name##_show, NULL)
+
+esrt_attr_decl(fw_resource_count, 32, "%u");
+esrt_attr_decl(fw_resource_count_max, 32, "%u");
+esrt_attr_decl(fw_resource_version, 64, "%llu");
+
+static struct attribute *esrt_attrs[] = {
+	&esrt_fw_resource_count.attr,
+	&esrt_fw_resource_count_max.attr,
+	&esrt_fw_resource_version.attr,
+	NULL,
+};
+
+static inline int esrt_table_exists(void)
+{
+	if (!efi_enabled(EFI_CONFIG_TABLES))
+		return 0;
+	if (efi.esrt == EFI_INVALID_TABLE_ADDR)
+		return 0;
+	return 1;
+}
+
+static umode_t esrt_attr_is_visible(struct kobject *kobj,
+				    struct attribute *attr, int n)
+{
+	if (!esrt_table_exists())
+		return 0;
+	return attr->mode;
+}
+
+static struct attribute_group esrt_attr_group = {
+	.attrs = esrt_attrs,
+	.is_visible = esrt_attr_is_visible,
+};
+
+/*
+ * remap the table, copy it to kmalloced pages, and unmap it.
+ */
+void __init efi_esrt_init(void)
+{
+	void *va;
+	struct efi_system_resource_table tmpesrt;
+	struct efi_system_resource_entry_v1 *v1_entries;
+	size_t size, max, entry_size, entries_size;
+	efi_memory_desc_t md;
+	int rc;
+	phys_addr_t end;
+
+	pr_debug("esrt-init: loading.\n");
+	if (!esrt_table_exists())
+		return;
+
+	rc = efi_mem_desc_lookup(efi.esrt, &md);
+	if (rc < 0) {
+		pr_err("ESRT header is not in the memory map.\n");
+		return;
+	}
+
+	max = efi_mem_desc_end(&md);
+	if (max < efi.esrt) {
+		pr_err("EFI memory descriptor is invalid. (esrt: %p max: %p)\n",
+		       (void *)efi.esrt, (void *)max);
+		return;
+	}
+
+	size = sizeof(*esrt);
+	max -= efi.esrt;
+
+	if (max < size) {
+		pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n",
+		       size, max);
+		return;
+	}
+
+	va = early_memremap(efi.esrt, size);
+	if (!va) {
+		pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+		       size);
+		return;
+	}
+
+	memcpy(&tmpesrt, va, sizeof(tmpesrt));
+
+	if (tmpesrt.fw_resource_version == 1) {
+		entry_size = sizeof (*v1_entries);
+	} else {
+		pr_err("Unsupported ESRT version %lld.\n",
+		       tmpesrt.fw_resource_version);
+		return;
+	}
+
+	if (tmpesrt.fw_resource_count > 0 && max - size < entry_size) {
+		pr_err("ESRT memory map entry can only hold the header. (max: %zu size: %zu)\n",
+		       max - size, entry_size);
+		goto err_memunmap;
+	}
+
+	/*
+	 * The format doesn't really give us any boundary to test here,
+	 * so I'm making up 128 as the max number of individually updatable
+	 * components we support.
+	 * 128 should be pretty excessive, but there's still some chance
+	 * somebody will do that someday and we'll need to raise this.
+	 */
+	if (tmpesrt.fw_resource_count > 128) {
+		pr_err("ESRT says fw_resource_count has very large value %d.\n",
+		       tmpesrt.fw_resource_count);
+		goto err_memunmap;
+	}
+
+	/*
+	 * We know it can't be larger than N * sizeof() here, and N is limited
+	 * by the previous test to a small number, so there's no overflow.
+	 */
+	entries_size = tmpesrt.fw_resource_count * entry_size;
+	if (max < size + entries_size) {
+		pr_err("ESRT does not fit on single memory map entry (size: %zu max: %zu)\n",
+		       size, max);
+		goto err_memunmap;
+	}
+
+	/* remap it with our (plausible) new pages */
+	early_memunmap(va, size);
+	size += entries_size;
+	va = early_memremap(efi.esrt, size);
+	if (!va) {
+		pr_err("early_memremap(%p, %zu) failed.\n", (void *)efi.esrt,
+		       size);
+		return;
+	}
+
+	esrt_data = (phys_addr_t)efi.esrt;
+	esrt_data_size = size;
+
+	end = esrt_data + size;
+	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
+	memblock_reserve(esrt_data, esrt_data_size);
+
+	pr_debug("esrt-init: loaded.\n");
+err_memunmap:
+	early_memunmap(va, size);
+}
+
+static int __init register_entries(void)
+{
+	struct efi_system_resource_entry_v1 *v1_entries = (void *)esrt->entries;
+	int i, rc;
+
+	if (!esrt_table_exists())
+		return 0;
+
+	for (i = 0; i < le32_to_cpu(esrt->fw_resource_count); i++) {
+		void *esre = NULL;
+		if (esrt->fw_resource_version == 1) {
+			esre = &v1_entries[i];
+		} else {
+			pr_err("Unsupported ESRT version %lld.\n",
+			       esrt->fw_resource_version);
+			return -EINVAL;
+		}
+
+		rc = esre_create_sysfs_entry(esre, i);
+		if (rc < 0) {
+			pr_err("ESRT entry creation failed with error %d.\n",
+			       rc);
+			return rc;
+		}
+	}
+	return 0;
+}
+
+static void cleanup_entry_list(void)
+{
+	struct esre_entry *entry, *next;
+
+	list_for_each_entry_safe(entry, next, &entry_list, list) {
+		kobject_put(&entry->kobj);
+	}
+}
+
+static int __init esrt_sysfs_init(void)
+{
+	int error;
+	struct efi_system_resource_table __iomem *ioesrt;
+
+	pr_debug("esrt-sysfs: loading.\n");
+	if (!esrt_data || !esrt_data_size)
+		return -ENOSYS;
+
+	ioesrt = ioremap(esrt_data, esrt_data_size);
+	if (!ioesrt) {
+		pr_err("ioremap(%pa, %zu) failed.\n", &esrt_data,
+		       esrt_data_size);
+		return -ENOMEM;
+	}
+
+	esrt = kmalloc(esrt_data_size, GFP_KERNEL);
+	if (!esrt) {
+		pr_err("kmalloc failed. (wanted %zu bytes)\n", esrt_data_size);
+		iounmap(ioesrt);
+		return -ENOMEM;
+	}
+
+	memcpy_fromio(esrt, ioesrt, esrt_data_size);
+
+	esrt_kobj = kobject_create_and_add("esrt", efi_kobj);
+	if (!esrt_kobj) {
+		pr_err("Firmware table registration failed.\n");
+		error = -ENOMEM;
+		goto err;
+	}
+
+	error = sysfs_create_group(esrt_kobj, &esrt_attr_group);
+	if (error) {
+		pr_err("Sysfs attribute export failed with error %d.\n",
+		       error);
+		goto err_remove_esrt;
+	}
+
+	esrt_kset = kset_create_and_add("entries", NULL, esrt_kobj);
+	if (!esrt_kset) {
+		pr_err("kset creation failed.\n");
+		error = -ENOMEM;
+		goto err_remove_group;
+	}
+
+	error = register_entries();
+	if (error)
+		goto err_cleanup_list;
+
+	memblock_remove(esrt_data, esrt_data_size);
+
+	pr_debug("esrt-sysfs: loaded.\n");
+
+	return 0;
+err_cleanup_list:
+	cleanup_entry_list();
+	kset_unregister(esrt_kset);
+err_remove_group:
+	sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+err_remove_esrt:
+	kobject_put(esrt_kobj);
+err:
+	kfree(esrt);
+	esrt = NULL;
+	return error;
+}
+
+static void __exit esrt_sysfs_exit(void)
+{
+	pr_debug("esrt-sysfs: unloading.\n");
+	cleanup_entry_list();
+	kset_unregister(esrt_kset);
+	sysfs_remove_group(esrt_kobj, &esrt_attr_group);
+	kfree(esrt);
+	esrt = NULL;
+	kobject_del(esrt_kobj);
+	kobject_put(esrt_kobj);
+}
+
+module_init(esrt_sysfs_init);
+module_exit(esrt_sysfs_exit);
+
+MODULE_AUTHOR("Peter Jones <pjones@redhat.com>");
+MODULE_DESCRIPTION("EFI System Resource Table support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c
index 87b8e3b900d2..5c55227a34c8 100644
--- a/drivers/firmware/efi/runtime-map.c
+++ b/drivers/firmware/efi/runtime-map.c
@@ -120,7 +120,8 @@ add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
 		kset_unregister(map_kset);
-		return entry;
+		map_kset = NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
@@ -132,6 +133,7 @@ add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
 	if (ret) {
 		kobject_put(&entry->kobj);
 		kset_unregister(map_kset);
+		map_kset = NULL;
 		return ERR_PTR(ret);
 	}
 
@@ -195,8 +197,6 @@ out_add_entry:
 		entry = *(map_entries + j);
 		kobject_put(&entry->kobj);
 	}
-	if (map_kset)
-		kset_unregister(map_kset);
 out:
 	return ret;
 }
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 071c2c969eec..72791232e46b 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -186,8 +186,20 @@ struct ibft_kobject {
 
 static struct iscsi_boot_kset *boot_kset;
 
+/* fully null address */
 static const char nulls[16];
 
+/* IPv4-mapped IPv6 ::ffff:0.0.0.0 */
+static const char mapped_nulls[16] = { 0x00, 0x00, 0x00, 0x00,
+                                       0x00, 0x00, 0x00, 0x00,
+                                       0x00, 0x00, 0xff, 0xff,
+                                       0x00, 0x00, 0x00, 0x00 };
+
+static int address_not_null(u8 *ip)
+{
+	return (memcmp(ip, nulls, 16) && memcmp(ip, mapped_nulls, 16));
+}
+
 /*
  * Helper functions to parse data properly.
  */
@@ -445,7 +457,7 @@ static umode_t ibft_check_nic_for(void *data, int type)
 		rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_IP_ADDR:
-		if (memcmp(nic->ip_addr, nulls, sizeof(nic->ip_addr)))
+		if (address_not_null(nic->ip_addr))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
@@ -456,21 +468,19 @@ static umode_t ibft_check_nic_for(void *data, int type)
 		rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_GATEWAY:
-		if (memcmp(nic->gateway, nulls, sizeof(nic->gateway)))
+		if (address_not_null(nic->gateway))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_PRIMARY_DNS:
-		if (memcmp(nic->primary_dns, nulls,
-			   sizeof(nic->primary_dns)))
+		if (address_not_null(nic->primary_dns))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_SECONDARY_DNS:
-		if (memcmp(nic->secondary_dns, nulls,
-			   sizeof(nic->secondary_dns)))
+		if (address_not_null(nic->secondary_dns))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_DHCP:
-		if (memcmp(nic->dhcp, nulls, sizeof(nic->dhcp)))
+		if (address_not_null(nic->dhcp))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_ETH_VLAN:
@@ -536,23 +546,19 @@ static umode_t __init ibft_check_initiator_for(void *data, int type)
 		rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_INI_ISNS_SERVER:
-		if (memcmp(init->isns_server, nulls,
-			   sizeof(init->isns_server)))
+		if (address_not_null(init->isns_server))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_INI_SLP_SERVER:
-		if (memcmp(init->slp_server, nulls,
-			   sizeof(init->slp_server)))
+		if (address_not_null(init->slp_server))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_INI_PRI_RADIUS_SERVER:
-		if (memcmp(init->pri_radius_server, nulls,
-			   sizeof(init->pri_radius_server)))
+		if (address_not_null(init->pri_radius_server))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_INI_SEC_RADIUS_SERVER:
-		if (memcmp(init->sec_radius_server, nulls,
-			   sizeof(init->sec_radius_server)))
+		if (address_not_null(init->sec_radius_server))
 			rc = S_IRUGO;
 		break;
 	case ISCSI_BOOT_INI_INITIATOR_NAME:
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index caefe806db5e..8f1fe739c985 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -126,6 +126,14 @@ config GPIO_BCM_KONA
 	help
 	  Turn on GPIO support for Broadcom "Kona" chips.
 
+config GPIO_BRCMSTB
+	tristate "BRCMSTB GPIO support"
+	default y if ARCH_BRCMSTB
+	depends on OF_GPIO && (ARCH_BRCMSTB || COMPILE_TEST)
+	select GPIO_GENERIC
+	help
+	  Say yes here to enable GPIO support for Broadcom STB (BCM7XXX) SoCs.
+
 config GPIO_CLPS711X
 	tristate "CLPS711X GPIO support"
 	depends on ARCH_CLPS711X || COMPILE_TEST
@@ -159,6 +167,14 @@ config GPIO_EP93XX
 	depends on ARCH_EP93XX
 	select GPIO_GENERIC
 
+config GPIO_ETRAXFS
+	bool "Axis ETRAX FS General I/O"
+	depends on CRIS || COMPILE_TEST
+	depends on OF
+	select GPIO_GENERIC
+	help
+	  Say yes here to support the GPIO controller on Axis ETRAX FS SoCs.
+
 config GPIO_F7188X
 	tristate "F71869, F71869A, F71882FG and F71889F GPIO support"
 	depends on X86
@@ -230,6 +246,14 @@ config GPIO_LOONGSON
 	help
 	  driver for GPIO functionality on Loongson-2F/3A/3B processors.
 
+config GPIO_LPC18XX
+	bool "NXP LPC18XX/43XX GPIO support"
+	default y if ARCH_LPC18XX
+	depends on OF_GPIO && (ARCH_LPC18XX || COMPILE_TEST)
+	help
+	  Select this option to enable GPIO driver for
+	  NXP LPC18XX/43XX devices.
+
 config GPIO_LYNXPOINT
 	tristate "Intel Lynxpoint GPIO support"
 	depends on ACPI && X86
@@ -308,7 +332,7 @@ config GPIO_OCTEON
 	  family of SOCs.
 
 config GPIO_OMAP
-	bool "TI OMAP GPIO support" if COMPILE_TEST && !ARCH_OMAP2PLUS
+	tristate "TI OMAP GPIO support" if ARCH_OMAP2PLUS || COMPILE_TEST
 	default y if ARCH_OMAP
 	depends on ARM
 	select GENERIC_IRQ_CHIP
@@ -488,6 +512,17 @@ config GPIO_XILINX
 	help
 	  Say yes here to support the Xilinx FPGA GPIO device
 
+config GPIO_XLP
+	tristate "Netlogic XLP GPIO support"
+	depends on CPU_XLP
+	select GPIOLIB_IRQCHIP
+	help
+	  This driver provides support for GPIO interface on Netlogic XLP MIPS64
+	  SoCs. Currently supported XLP variants are XLP8XX, XLP3XX, XLP2XX,
+	  XLP9XX and XLP5XX.
+
+	  If unsure, say N.
+
 config GPIO_XTENSA
 	bool "Xtensa GPIO32 support"
 	depends on XTENSA
@@ -505,7 +540,7 @@ config GPIO_ZEVIO
 
 config GPIO_ZYNQ
 	tristate "Xilinx Zynq GPIO support"
-	depends on ARCH_ZYNQ
+	depends on ARCH_ZYNQ || ARCH_ZYNQMP
 	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to support Xilinx Zynq GPIO controller.
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index f71bb971329c..f82cd678ce08 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_GPIO_ALTERA)  	+= gpio-altera.o
 obj-$(CONFIG_GPIO_AMD8111)	+= gpio-amd8111.o
 obj-$(CONFIG_GPIO_ARIZONA)	+= gpio-arizona.o
 obj-$(CONFIG_GPIO_BCM_KONA)	+= gpio-bcm-kona.o
+obj-$(CONFIG_GPIO_BRCMSTB)	+= gpio-brcmstb.o
 obj-$(CONFIG_GPIO_BT8XX)	+= gpio-bt8xx.o
 obj-$(CONFIG_GPIO_CLPS711X)	+= gpio-clps711x.o
 obj-$(CONFIG_GPIO_CS5535)	+= gpio-cs5535.o
@@ -32,6 +33,7 @@ obj-$(CONFIG_GPIO_DLN2)		+= gpio-dln2.o
 obj-$(CONFIG_GPIO_DWAPB)	+= gpio-dwapb.o
 obj-$(CONFIG_GPIO_EM)		+= gpio-em.o
 obj-$(CONFIG_GPIO_EP93XX)	+= gpio-ep93xx.o
+obj-$(CONFIG_GPIO_ETRAXFS)	+= gpio-etraxfs.o
 obj-$(CONFIG_GPIO_F7188X)	+= gpio-f7188x.o
 obj-$(CONFIG_GPIO_GE_FPGA)	+= gpio-ge.o
 obj-$(CONFIG_GPIO_GRGPIO)	+= gpio-grgpio.o
@@ -44,6 +46,7 @@ obj-$(CONFIG_ARCH_KS8695)	+= gpio-ks8695.o
 obj-$(CONFIG_GPIO_INTEL_MID)	+= gpio-intel-mid.o
 obj-$(CONFIG_GPIO_LOONGSON)	+= gpio-loongson.o
 obj-$(CONFIG_GPIO_LP3943)	+= gpio-lp3943.o
+obj-$(CONFIG_GPIO_LPC18XX)	+= gpio-lpc18xx.o
 obj-$(CONFIG_ARCH_LPC32XX)	+= gpio-lpc32xx.o
 obj-$(CONFIG_GPIO_LYNXPOINT)	+= gpio-lynxpoint.o
 obj-$(CONFIG_GPIO_MAX730X)	+= gpio-max730x.o
@@ -109,6 +112,7 @@ obj-$(CONFIG_GPIO_WM8994)	+= gpio-wm8994.o
 obj-$(CONFIG_GPIO_XGENE)	+= gpio-xgene.o
 obj-$(CONFIG_GPIO_XGENE_SB)	+= gpio-xgene-sb.o
 obj-$(CONFIG_GPIO_XILINX)	+= gpio-xilinx.o
+obj-$(CONFIG_GPIO_XLP)		+= gpio-xlp.o
 obj-$(CONFIG_GPIO_XTENSA)	+= gpio-xtensa.o
 obj-$(CONFIG_GPIO_ZEVIO)	+= gpio-zevio.o
 obj-$(CONFIG_GPIO_ZYNQ)		+= gpio-zynq.o
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 449fb46cb8a0..0f3d336d6303 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -107,7 +107,8 @@ static int altera_gpio_irq_set_type(struct irq_data *d,
 	return -EINVAL;
 }
 
-static unsigned int altera_gpio_irq_startup(struct irq_data *d) {
+static unsigned int altera_gpio_irq_startup(struct irq_data *d)
+{
 	altera_gpio_irq_unmask(d);
 
 	return 0;
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index b164ce837b43..8333f878919c 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -122,6 +122,16 @@ static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio,
 	spin_unlock_irqrestore(&kona_gpio->lock, flags);
 }
 
+static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio)
+{
+	struct bcm_kona_gpio *kona_gpio = to_kona_gpio(chip);
+	void __iomem *reg_base = kona_gpio->reg_base;
+	u32 val;
+
+	val = readl(reg_base + GPIO_CONTROL(gpio)) & GPIO_GPCTR0_IOTR_MASK;
+	return val ? GPIOF_DIR_IN : GPIOF_DIR_OUT;
+}
+
 static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
 {
 	struct bcm_kona_gpio *kona_gpio;
@@ -135,12 +145,8 @@ static void bcm_kona_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
 	reg_base = kona_gpio->reg_base;
 	spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	/* determine the GPIO pin direction */
-	val = readl(reg_base + GPIO_CONTROL(gpio));
-	val &= GPIO_GPCTR0_IOTR_MASK;
-
 	/* this function only applies to output pin */
-	if (GPIO_GPCTR0_IOTR_CMD_INPUT == val)
+	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
 		goto out;
 
 	reg_offset = value ? GPIO_OUT_SET(bank_id) : GPIO_OUT_CLEAR(bank_id);
@@ -166,13 +172,12 @@ static int bcm_kona_gpio_get(struct gpio_chip *chip, unsigned gpio)
 	reg_base = kona_gpio->reg_base;
 	spin_lock_irqsave(&kona_gpio->lock, flags);
 
-	/* determine the GPIO pin direction */
-	val = readl(reg_base + GPIO_CONTROL(gpio));
-	val &= GPIO_GPCTR0_IOTR_MASK;
+	if (bcm_kona_gpio_get_dir(chip, gpio) == GPIOF_DIR_IN)
+		reg_offset = GPIO_IN_STATUS(bank_id);
+	else
+		reg_offset = GPIO_OUT_STATUS(bank_id);
 
 	/* read the GPIO bank status */
-	reg_offset = (GPIO_GPCTR0_IOTR_CMD_INPUT == val) ?
-	    GPIO_IN_STATUS(bank_id) : GPIO_OUT_STATUS(bank_id);
 	val = readl(reg_base + reg_offset);
 
 	spin_unlock_irqrestore(&kona_gpio->lock, flags);
@@ -310,6 +315,7 @@ static struct gpio_chip template_chip = {
 	.owner = THIS_MODULE,
 	.request = bcm_kona_gpio_request,
 	.free = bcm_kona_gpio_free,
+	.get_direction = bcm_kona_gpio_get_dir,
 	.direction_input = bcm_kona_gpio_direction_input,
 	.get = bcm_kona_gpio_get,
 	.direction_output = bcm_kona_gpio_direction_output,
@@ -534,7 +540,7 @@ static void bcm_kona_gpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 	irq_set_chip_data(irq, NULL);
 }
 
-static struct irq_domain_ops bcm_kona_irq_ops = {
+static const struct irq_domain_ops bcm_kona_irq_ops = {
 	.map = bcm_kona_gpio_irq_map,
 	.unmap = bcm_kona_gpio_irq_unmap,
 	.xlate = irq_domain_xlate_twocell,
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
new file mode 100644
index 000000000000..7a3cb1fa0a76
--- /dev/null
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/gpio/driver.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/module.h>
+#include <linux/basic_mmio_gpio.h>
+
+#define GIO_BANK_SIZE           0x20
+#define GIO_ODEN(bank)          (((bank) * GIO_BANK_SIZE) + 0x00)
+#define GIO_DATA(bank)          (((bank) * GIO_BANK_SIZE) + 0x04)
+#define GIO_IODIR(bank)         (((bank) * GIO_BANK_SIZE) + 0x08)
+#define GIO_EC(bank)            (((bank) * GIO_BANK_SIZE) + 0x0c)
+#define GIO_EI(bank)            (((bank) * GIO_BANK_SIZE) + 0x10)
+#define GIO_MASK(bank)          (((bank) * GIO_BANK_SIZE) + 0x14)
+#define GIO_LEVEL(bank)         (((bank) * GIO_BANK_SIZE) + 0x18)
+#define GIO_STAT(bank)          (((bank) * GIO_BANK_SIZE) + 0x1c)
+
+struct brcmstb_gpio_bank {
+	struct list_head node;
+	int id;
+	struct bgpio_chip bgc;
+	struct brcmstb_gpio_priv *parent_priv;
+	u32 width;
+};
+
+struct brcmstb_gpio_priv {
+	struct list_head bank_list;
+	void __iomem *reg_base;
+	int num_banks;
+	struct platform_device *pdev;
+	int gpio_base;
+};
+
+#define MAX_GPIO_PER_BANK           32
+#define GPIO_BANK(gpio)         ((gpio) >> 5)
+/* assumes MAX_GPIO_PER_BANK is a multiple of 2 */
+#define GPIO_BIT(gpio)          ((gpio) & (MAX_GPIO_PER_BANK - 1))
+
+static inline struct brcmstb_gpio_bank *
+brcmstb_gpio_gc_to_bank(struct gpio_chip *gc)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+	return container_of(bgc, struct brcmstb_gpio_bank, bgc);
+}
+
+static inline struct brcmstb_gpio_priv *
+brcmstb_gpio_gc_to_priv(struct gpio_chip *gc)
+{
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+	return bank->parent_priv;
+}
+
+/* Make sure that the number of banks matches up between properties */
+static int brcmstb_gpio_sanity_check_banks(struct device *dev,
+		struct device_node *np, struct resource *res)
+{
+	int res_num_banks = resource_size(res) / GIO_BANK_SIZE;
+	int num_banks =
+		of_property_count_u32_elems(np, "brcm,gpio-bank-widths");
+
+	if (res_num_banks != num_banks) {
+		dev_err(dev, "Mismatch in banks: res had %d, bank-widths had %d\n",
+				res_num_banks, num_banks);
+		return -EINVAL;
+	} else {
+		return 0;
+	}
+}
+
+static int brcmstb_gpio_remove(struct platform_device *pdev)
+{
+	struct brcmstb_gpio_priv *priv = platform_get_drvdata(pdev);
+	struct list_head *pos;
+	struct brcmstb_gpio_bank *bank;
+	int ret = 0;
+
+	list_for_each(pos, &priv->bank_list) {
+		bank = list_entry(pos, struct brcmstb_gpio_bank, node);
+		ret = bgpio_remove(&bank->bgc);
+		if (ret)
+			dev_err(&pdev->dev, "gpiochip_remove fail in cleanup");
+	}
+	return ret;
+}
+
+static int brcmstb_gpio_of_xlate(struct gpio_chip *gc,
+		const struct of_phandle_args *gpiospec, u32 *flags)
+{
+	struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc);
+	struct brcmstb_gpio_bank *bank = brcmstb_gpio_gc_to_bank(gc);
+	int offset;
+
+	if (gc->of_gpio_n_cells != 2) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(gpiospec->args_count < gc->of_gpio_n_cells))
+		return -EINVAL;
+
+	offset = gpiospec->args[0] - (gc->base - priv->gpio_base);
+	if (offset >= gc->ngpio)
+		return -EINVAL;
+
+	if (unlikely(offset >= bank->width)) {
+		dev_warn_ratelimited(&priv->pdev->dev,
+			"Received request for invalid GPIO offset %d\n",
+			gpiospec->args[0]);
+	}
+
+	if (flags)
+		*flags = gpiospec->args[1];
+
+	return offset;
+}
+
+static int brcmstb_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	void __iomem *reg_base;
+	struct brcmstb_gpio_priv *priv;
+	struct resource *res;
+	struct property *prop;
+	const __be32 *p;
+	u32 bank_width;
+	int err;
+	static int gpio_base;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(reg_base))
+		return PTR_ERR(reg_base);
+
+	priv->gpio_base = gpio_base;
+	priv->reg_base = reg_base;
+	priv->pdev = pdev;
+
+	INIT_LIST_HEAD(&priv->bank_list);
+	if (brcmstb_gpio_sanity_check_banks(dev, np, res))
+		return -EINVAL;
+
+	of_property_for_each_u32(np, "brcm,gpio-bank-widths", prop, p,
+			bank_width) {
+		struct brcmstb_gpio_bank *bank;
+		struct bgpio_chip *bgc;
+		struct gpio_chip *gc;
+
+		bank = devm_kzalloc(dev, sizeof(*bank), GFP_KERNEL);
+		if (!bank) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		bank->parent_priv = priv;
+		bank->id = priv->num_banks;
+		if (bank_width <= 0 || bank_width > MAX_GPIO_PER_BANK) {
+			dev_err(dev, "Invalid bank width %d\n", bank_width);
+			goto fail;
+		} else {
+			bank->width = bank_width;
+		}
+
+		/*
+		 * Regs are 4 bytes wide, have data reg, no set/clear regs,
+		 * and direction bits have 0 = output and 1 = input
+		 */
+		bgc = &bank->bgc;
+		err = bgpio_init(bgc, dev, 4,
+				reg_base + GIO_DATA(bank->id),
+				NULL, NULL, NULL,
+				reg_base + GIO_IODIR(bank->id), 0);
+		if (err) {
+			dev_err(dev, "bgpio_init() failed\n");
+			goto fail;
+		}
+
+		gc = &bgc->gc;
+		gc->of_node = np;
+		gc->owner = THIS_MODULE;
+		gc->label = np->full_name;
+		gc->base = gpio_base;
+		gc->of_gpio_n_cells = 2;
+		gc->of_xlate = brcmstb_gpio_of_xlate;
+		/* not all ngpio lines are valid, will use bank width later */
+		gc->ngpio = MAX_GPIO_PER_BANK;
+
+		err = gpiochip_add(gc);
+		if (err) {
+			dev_err(dev, "Could not add gpiochip for bank %d\n",
+					bank->id);
+			goto fail;
+		}
+		gpio_base += gc->ngpio;
+		dev_dbg(dev, "bank=%d, base=%d, ngpio=%d, width=%d\n", bank->id,
+			gc->base, gc->ngpio, bank->width);
+
+		/* Everything looks good, so add bank to list */
+		list_add(&bank->node, &priv->bank_list);
+
+		priv->num_banks++;
+	}
+
+	dev_info(dev, "Registered %d banks (GPIO(s): %d-%d)\n",
+			priv->num_banks, priv->gpio_base, gpio_base - 1);
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+fail:
+	(void) brcmstb_gpio_remove(pdev);
+	return err;
+}
+
+static const struct of_device_id brcmstb_gpio_of_match[] = {
+	{ .compatible = "brcm,brcmstb-gpio" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, brcmstb_gpio_of_match);
+
+static struct platform_driver brcmstb_gpio_driver = {
+	.driver = {
+		.name = "brcmstb-gpio",
+		.of_match_table = brcmstb_gpio_of_match,
+	},
+	.probe = brcmstb_gpio_probe,
+	.remove = brcmstb_gpio_remove,
+};
+module_platform_driver(brcmstb_gpio_driver);
+
+MODULE_AUTHOR("Gregory Fong");
+MODULE_DESCRIPTION("Driver for Broadcom BRCMSTB SoC UPG GPIO");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 91a7ffe83135..fddd204dc9b6 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/seq_file.h>
@@ -94,9 +95,8 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type)
 {
 	int reg;
 
-	if (gpio == 94) {
+	if (gpio == 94)
 		return GPIOPANELCTL;
-	}
 
 	if (reg_type == CTRL_IN) {
 		if (gpio < 8)
@@ -255,6 +255,7 @@ static struct irq_chip crystalcove_irqchip = {
 	.irq_set_type		= crystalcove_irq_type,
 	.irq_bus_lock		= crystalcove_bus_lock,
 	.irq_bus_sync_unlock	= crystalcove_bus_sync_unlock,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
 static irqreturn_t crystalcove_gpio_irq_handler(int irq, void *data)
diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c
index dbdb4de82c6d..6685712c15cf 100644
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@@ -466,7 +466,6 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	dln2->gpio.owner = THIS_MODULE;
 	dln2->gpio.base = -1;
 	dln2->gpio.ngpio = pins;
-	dln2->gpio.exported = true;
 	dln2->gpio.can_sleep = true;
 	dln2->gpio.irq_not_threaded = true;
 	dln2->gpio.set = dln2_gpio_set;
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index 3cfcfc620c8e..fbf287307c4c 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -266,7 +266,7 @@ static int em_gio_irq_domain_map(struct irq_domain *h, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops em_gio_irq_domain_ops = {
+static const struct irq_domain_ops em_gio_irq_domain_ops = {
 	.map	= em_gio_irq_domain_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/gpio/gpio-etraxfs.c b/drivers/gpio/gpio-etraxfs.c
new file mode 100644
index 000000000000..28071f4a5672
--- /dev/null
+++ b/drivers/gpio/gpio-etraxfs.c
@@ -0,0 +1,176 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/basic_mmio_gpio.h>
+
+#define ETRAX_FS_rw_pa_dout	0
+#define ETRAX_FS_r_pa_din	4
+#define ETRAX_FS_rw_pa_oe	8
+#define ETRAX_FS_rw_intr_cfg	12
+#define ETRAX_FS_rw_intr_mask	16
+#define ETRAX_FS_rw_ack_intr	20
+#define ETRAX_FS_r_intr		24
+#define ETRAX_FS_rw_pb_dout	32
+#define ETRAX_FS_r_pb_din	36
+#define ETRAX_FS_rw_pb_oe	40
+#define ETRAX_FS_rw_pc_dout	48
+#define ETRAX_FS_r_pc_din	52
+#define ETRAX_FS_rw_pc_oe	56
+#define ETRAX_FS_rw_pd_dout	64
+#define ETRAX_FS_r_pd_din	68
+#define ETRAX_FS_rw_pd_oe	72
+#define ETRAX_FS_rw_pe_dout	80
+#define ETRAX_FS_r_pe_din	84
+#define ETRAX_FS_rw_pe_oe	88
+
+struct etraxfs_gpio_port {
+	const char *label;
+	unsigned int oe;
+	unsigned int dout;
+	unsigned int din;
+	unsigned int ngpio;
+};
+
+struct etraxfs_gpio_info {
+	unsigned int num_ports;
+	const struct etraxfs_gpio_port *ports;
+};
+
+static const struct etraxfs_gpio_port etraxfs_gpio_etraxfs_ports[] = {
+	{
+		.label	= "A",
+		.ngpio	= 8,
+		.oe	= ETRAX_FS_rw_pa_oe,
+		.dout	= ETRAX_FS_rw_pa_dout,
+		.din	= ETRAX_FS_r_pa_din,
+	},
+	{
+		.label	= "B",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pb_oe,
+		.dout	= ETRAX_FS_rw_pb_dout,
+		.din	= ETRAX_FS_r_pb_din,
+	},
+	{
+		.label	= "C",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pc_oe,
+		.dout	= ETRAX_FS_rw_pc_dout,
+		.din	= ETRAX_FS_r_pc_din,
+	},
+	{
+		.label	= "D",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pd_oe,
+		.dout	= ETRAX_FS_rw_pd_dout,
+		.din	= ETRAX_FS_r_pd_din,
+	},
+	{
+		.label	= "E",
+		.ngpio	= 18,
+		.oe	= ETRAX_FS_rw_pe_oe,
+		.dout	= ETRAX_FS_rw_pe_dout,
+		.din	= ETRAX_FS_r_pe_din,
+	},
+};
+
+static const struct etraxfs_gpio_info etraxfs_gpio_etraxfs = {
+	.num_ports = ARRAY_SIZE(etraxfs_gpio_etraxfs_ports),
+	.ports = etraxfs_gpio_etraxfs_ports,
+};
+
+static int etraxfs_gpio_of_xlate(struct gpio_chip *gc,
+			       const struct of_phandle_args *gpiospec,
+			       u32 *flags)
+{
+	/*
+	 * Port numbers are A to E, and the properties are integers, so we
+	 * specify them as 0xA - 0xE.
+	 */
+	if (gc->label[0] - 'A' + 0xA != gpiospec->args[2])
+		return -EINVAL;
+
+	return of_gpio_simple_xlate(gc, gpiospec, flags);
+}
+
+static const struct of_device_id etraxfs_gpio_of_table[] = {
+	{
+		.compatible = "axis,etraxfs-gio",
+		.data = &etraxfs_gpio_etraxfs,
+	},
+	{},
+};
+
+static int etraxfs_gpio_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct etraxfs_gpio_info *info;
+	const struct of_device_id *match;
+	struct bgpio_chip *chips;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+	int i;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (!regs)
+		return -ENOMEM;
+
+	match = of_match_node(etraxfs_gpio_of_table, dev->of_node);
+	if (!match)
+		return -EINVAL;
+
+	info = match->data;
+
+	chips = devm_kzalloc(dev, sizeof(*chips) * info->num_ports, GFP_KERNEL);
+	if (!chips)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_ports; i++) {
+		struct bgpio_chip *bgc = &chips[i];
+		const struct etraxfs_gpio_port *port = &info->ports[i];
+
+		ret = bgpio_init(bgc, dev, 4,
+				 regs + port->din,	/* dat */
+				 regs + port->dout,	/* set */
+				 NULL,			/* clr */
+				 regs + port->oe,	/* dirout */
+				 NULL,			/* dirin */
+				 BGPIOF_UNREADABLE_REG_SET);
+		if (ret)
+			return ret;
+
+		bgc->gc.ngpio = port->ngpio;
+		bgc->gc.label = port->label;
+
+		bgc->gc.of_node = dev->of_node;
+		bgc->gc.of_gpio_n_cells = 3;
+		bgc->gc.of_xlate = etraxfs_gpio_of_xlate;
+
+		ret = gpiochip_add(&bgc->gc);
+		if (ret)
+			dev_err(dev, "Unable to register port %s\n",
+				bgc->gc.label);
+	}
+
+	return 0;
+}
+
+static struct platform_driver etraxfs_gpio_driver = {
+	.driver = {
+		.name		= "etraxfs-gpio",
+		.of_match_table = of_match_ptr(etraxfs_gpio_of_table),
+	},
+	.probe	= etraxfs_gpio_probe,
+};
+
+static int __init etraxfs_gpio_init(void)
+{
+	return platform_driver_register(&etraxfs_gpio_driver);
+}
+
+device_initcall(etraxfs_gpio_init);
diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c
index dbda8433c4f7..5e3c4fa67d82 100644
--- a/drivers/gpio/gpio-f7188x.c
+++ b/drivers/gpio/gpio-f7188x.c
@@ -172,7 +172,7 @@ static struct f7188x_gpio_bank f71869a_gpio_bank[] = {
 };
 
 static struct f7188x_gpio_bank f71882_gpio_bank[] = {
-	F7188X_GPIO_BANK(0 , 8, 0xF0),
+	F7188X_GPIO_BANK(0, 8, 0xF0),
 	F7188X_GPIO_BANK(10, 8, 0xE0),
 	F7188X_GPIO_BANK(20, 8, 0xD0),
 	F7188X_GPIO_BANK(30, 4, 0xC0),
@@ -180,7 +180,7 @@ static struct f7188x_gpio_bank f71882_gpio_bank[] = {
 };
 
 static struct f7188x_gpio_bank f71889_gpio_bank[] = {
-	F7188X_GPIO_BANK(0 , 7, 0xF0),
+	F7188X_GPIO_BANK(0, 7, 0xF0),
 	F7188X_GPIO_BANK(10, 7, 0xE0),
 	F7188X_GPIO_BANK(20, 8, 0xD0),
 	F7188X_GPIO_BANK(30, 8, 0xC0),
diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c
index b92a690f5765..9bda3727fac1 100644
--- a/drivers/gpio/gpio-generic.c
+++ b/drivers/gpio/gpio-generic.c
@@ -135,6 +135,17 @@ static unsigned long bgpio_pin2mask_be(struct bgpio_chip *bgc,
 	return 1 << (bgc->bits - 1 - pin);
 }
 
+static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct bgpio_chip *bgc = to_bgpio_chip(gc);
+	unsigned long pinmask = bgc->pin2mask(bgc, gpio);
+
+	if (bgc->dir & pinmask)
+		return bgc->read_reg(bgc->reg_set) & pinmask;
+	else
+		return bgc->read_reg(bgc->reg_dat) & pinmask;
+}
+
 static int bgpio_get(struct gpio_chip *gc, unsigned int gpio)
 {
 	struct bgpio_chip *bgc = to_bgpio_chip(gc);
@@ -416,7 +427,8 @@ static int bgpio_setup_accessors(struct device *dev,
 static int bgpio_setup_io(struct bgpio_chip *bgc,
 			  void __iomem *dat,
 			  void __iomem *set,
-			  void __iomem *clr)
+			  void __iomem *clr,
+			  unsigned long flags)
 {
 
 	bgc->reg_dat = dat;
@@ -437,7 +449,11 @@ static int bgpio_setup_io(struct bgpio_chip *bgc,
 		bgc->gc.set_multiple = bgpio_set_multiple;
 	}
 
-	bgc->gc.get = bgpio_get;
+	if (!(flags & BGPIOF_UNREADABLE_REG_SET) &&
+	    (flags & BGPIOF_READ_OUTPUT_REG_SET))
+		bgc->gc.get = bgpio_get_set;
+	else
+		bgc->gc.get = bgpio_get;
 
 	return 0;
 }
@@ -500,7 +516,7 @@ int bgpio_init(struct bgpio_chip *bgc, struct device *dev,
 	bgc->gc.ngpio = bgc->bits;
 	bgc->gc.request = bgpio_request;
 
-	ret = bgpio_setup_io(bgc, dat, set, clr);
+	ret = bgpio_setup_io(bgc, dat, set, clr, flags);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpio/gpio-grgpio.c b/drivers/gpio/gpio-grgpio.c
index 35a02770c8b0..0a8f7617e72e 100644
--- a/drivers/gpio/gpio-grgpio.c
+++ b/drivers/gpio/gpio-grgpio.c
@@ -332,7 +332,7 @@ static void grgpio_irq_unmap(struct irq_domain *d, unsigned int irq)
 	spin_unlock_irqrestore(&priv->bgc.lock, flags);
 }
 
-static struct irq_domain_ops grgpio_irq_domain_ops = {
+static const struct irq_domain_ops grgpio_irq_domain_ops = {
 	.map	= grgpio_irq_map,
 	.unmap	= grgpio_irq_unmap,
 };
diff --git a/drivers/gpio/gpio-it8761e.c b/drivers/gpio/gpio-it8761e.c
index dadfc245cf09..30a8f24c92c5 100644
--- a/drivers/gpio/gpio-it8761e.c
+++ b/drivers/gpio/gpio-it8761e.c
@@ -123,7 +123,7 @@ static void it8761e_gpio_set(struct gpio_chip *gc,
 
 	curr_vals = inb(reg);
 	if (val)
-		outb(curr_vals | (1 << bit) , reg);
+		outb(curr_vals | (1 << bit), reg);
 	else
 		outb(curr_vals & ~(1 << bit), reg);
 
diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c
index 6b8115f34208..83f281dda1e0 100644
--- a/drivers/gpio/gpio-kempld.c
+++ b/drivers/gpio/gpio-kempld.c
@@ -117,7 +117,7 @@ static int kempld_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 		= container_of(chip, struct kempld_gpio_data, chip);
 	struct kempld_device_data *pld = gpio->pld;
 
-	return kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
+	return !kempld_gpio_get_bit(pld, KEMPLD_GPIO_DIR_NUM(offset), offset);
 }
 
 static int kempld_gpio_pincount(struct kempld_device_data *pld)
diff --git a/drivers/gpio/gpio-lpc18xx.c b/drivers/gpio/gpio-lpc18xx.c
new file mode 100644
index 000000000000..eb68603136b0
--- /dev/null
+++ b/drivers/gpio/gpio-lpc18xx.c
@@ -0,0 +1,180 @@
+/*
+ * GPIO driver for NXP LPC18xx/43xx.
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/clk.h>
+#include <linux/gpio/driver.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+
+/* LPC18xx GPIO register offsets */
+#define LPC18XX_REG_DIR(n)	(0x2000 + n * sizeof(u32))
+
+#define LPC18XX_MAX_PORTS	8
+#define LPC18XX_PINS_PER_PORT	32
+
+struct lpc18xx_gpio_chip {
+	struct gpio_chip gpio;
+	void __iomem *base;
+	struct clk *clk;
+	spinlock_t lock;
+};
+
+static inline struct lpc18xx_gpio_chip *to_lpc18xx_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct lpc18xx_gpio_chip, gpio);
+}
+
+static int lpc18xx_gpio_request(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_request_gpio(offset);
+}
+
+static void lpc18xx_gpio_free(struct gpio_chip *chip, unsigned offset)
+{
+	pinctrl_free_gpio(offset);
+}
+
+static void lpc18xx_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	writeb(value ? 1 : 0, gc->base + offset);
+}
+
+static int lpc18xx_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	return !!readb(gc->base + offset);
+}
+
+static int lpc18xx_gpio_direction(struct gpio_chip *chip, unsigned offset,
+				  bool out)
+{
+	struct lpc18xx_gpio_chip *gc = to_lpc18xx_gpio(chip);
+	unsigned long flags;
+	u32 port, pin, dir;
+
+	port = offset / LPC18XX_PINS_PER_PORT;
+	pin  = offset % LPC18XX_PINS_PER_PORT;
+
+	spin_lock_irqsave(&gc->lock, flags);
+	dir = readl(gc->base + LPC18XX_REG_DIR(port));
+	if (out)
+		dir |= BIT(pin);
+	else
+		dir &= ~BIT(pin);
+	writel(dir, gc->base + LPC18XX_REG_DIR(port));
+	spin_unlock_irqrestore(&gc->lock, flags);
+
+	return 0;
+}
+
+static int lpc18xx_gpio_direction_input(struct gpio_chip *chip,
+					unsigned offset)
+{
+	return lpc18xx_gpio_direction(chip, offset, false);
+}
+
+static int lpc18xx_gpio_direction_output(struct gpio_chip *chip,
+					 unsigned offset, int value)
+{
+	lpc18xx_gpio_set(chip, offset, value);
+	return lpc18xx_gpio_direction(chip, offset, true);
+}
+
+static struct gpio_chip lpc18xx_chip = {
+	.label			= "lpc18xx/43xx-gpio",
+	.request		= lpc18xx_gpio_request,
+	.free			= lpc18xx_gpio_free,
+	.direction_input	= lpc18xx_gpio_direction_input,
+	.direction_output	= lpc18xx_gpio_direction_output,
+	.set			= lpc18xx_gpio_set,
+	.get			= lpc18xx_gpio_get,
+	.ngpio			= LPC18XX_MAX_PORTS * LPC18XX_PINS_PER_PORT,
+	.owner			= THIS_MODULE,
+};
+
+static int lpc18xx_gpio_probe(struct platform_device *pdev)
+{
+	struct lpc18xx_gpio_chip *gc;
+	struct resource *res;
+	int ret;
+
+	gc = devm_kzalloc(&pdev->dev, sizeof(*gc), GFP_KERNEL);
+	if (!gc)
+		return -ENOMEM;
+
+	gc->gpio = lpc18xx_chip;
+	platform_set_drvdata(pdev, gc);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	gc->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(gc->base))
+		return PTR_ERR(gc->base);
+
+	gc->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(gc->clk)) {
+		dev_err(&pdev->dev, "input clock not found\n");
+		return PTR_ERR(gc->clk);
+	}
+
+	ret = clk_prepare_enable(gc->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to enable clock\n");
+		return ret;
+	}
+
+	spin_lock_init(&gc->lock);
+
+	gc->gpio.dev = &pdev->dev;
+
+	ret = gpiochip_add(&gc->gpio);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to add gpio chip\n");
+		clk_disable_unprepare(gc->clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int lpc18xx_gpio_remove(struct platform_device *pdev)
+{
+	struct lpc18xx_gpio_chip *gc = platform_get_drvdata(pdev);
+
+	gpiochip_remove(&gc->gpio);
+	clk_disable_unprepare(gc->clk);
+
+	return 0;
+}
+
+static const struct of_device_id lpc18xx_gpio_match[] = {
+	{ .compatible = "nxp,lpc1850-gpio" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpc18xx_gpio_match);
+
+static struct platform_driver lpc18xx_gpio_driver = {
+	.probe	= lpc18xx_gpio_probe,
+	.remove	= lpc18xx_gpio_remove,
+	.driver	= {
+		.name		= "lpc18xx-gpio",
+		.of_match_table	= lpc18xx_gpio_match,
+	},
+};
+module_platform_driver(lpc18xx_gpio_driver);
+
+MODULE_AUTHOR("Joachim Eastwood <manabian@gmail.com>");
+MODULE_DESCRIPTION("GPIO driver for LPC18xx/43xx");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 127c755b38dc..153af464c7a7 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -72,7 +72,7 @@ struct lp_gpio {
  *
  * per gpio specific registers consist of two 32bit registers per gpio
  * (LP_CONFIG1 and LP_CONFIG2), with 94 gpios there's a total of
- * 188 config registes.
+ * 188 config registers.
  *
  * A simplified view of the register layout look like this:
  *
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index 0fa4543c5e02..aed4ca9338bc 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -429,6 +429,14 @@ static int max732x_irq_set_type(struct irq_data *d, unsigned int type)
 	return 0;
 }
 
+static int max732x_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct max732x_chip *chip = irq_data_get_irq_chip_data(data);
+
+	irq_set_irq_wake(chip->client->irq, on);
+	return 0;
+}
+
 static struct irq_chip max732x_irq_chip = {
 	.name			= "max732x",
 	.irq_mask		= max732x_irq_mask,
@@ -436,6 +444,7 @@ static struct irq_chip max732x_irq_chip = {
 	.irq_bus_lock		= max732x_irq_bus_lock,
 	.irq_bus_sync_unlock	= max732x_irq_bus_sync_unlock,
 	.irq_set_type		= max732x_irq_set_type,
+	.irq_set_wake		= max732x_irq_set_wake,
 };
 
 static uint8_t max732x_irq_pending(struct max732x_chip *chip)
@@ -507,12 +516,10 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 		chip->irq_features = has_irq;
 		mutex_init(&chip->irq_lock);
 
-		ret = devm_request_threaded_irq(&client->dev,
-					client->irq,
-					NULL,
-					max732x_irq_handler,
-					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-					dev_name(&client->dev), chip);
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+				NULL, max732x_irq_handler, IRQF_ONESHOT |
+				IRQF_TRIGGER_FALLING | IRQF_SHARED,
+				dev_name(&client->dev), chip);
 		if (ret) {
 			dev_err(&client->dev, "failed to request irq %d\n",
 				client->irq);
@@ -521,7 +528,7 @@ static int max732x_irq_setup(struct max732x_chip *chip,
 		ret =  gpiochip_irqchip_add(&chip->gpio_chip,
 					    &max732x_irq_chip,
 					    irq_base,
-					    handle_edge_irq,
+					    handle_simple_irq,
 					    IRQ_TYPE_NONE);
 		if (ret) {
 			dev_err(&client->dev,
diff --git a/drivers/gpio/gpio-moxart.c b/drivers/gpio/gpio-moxart.c
index c3ab46e595da..abd8676ce2b6 100644
--- a/drivers/gpio/gpio-moxart.c
+++ b/drivers/gpio/gpio-moxart.c
@@ -39,17 +39,6 @@ static void moxart_gpio_free(struct gpio_chip *chip, unsigned offset)
 	pinctrl_free_gpio(offset);
 }
 
-static int moxart_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	struct bgpio_chip *bgc = to_bgpio_chip(chip);
-	u32 ret = bgc->read_reg(bgc->reg_dir);
-
-	if (ret & BIT(offset))
-		return !!(bgc->read_reg(bgc->reg_set) & BIT(offset));
-	else
-		return !!(bgc->read_reg(bgc->reg_dat) & BIT(offset));
-}
-
 static int moxart_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -68,8 +57,9 @@ static int moxart_gpio_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	ret = bgpio_init(bgc, dev, 4, base + GPIO_DATA_IN,
-		    base + GPIO_DATA_OUT, NULL,
-		    base + GPIO_PIN_DIRECTION, NULL, 0);
+			 base + GPIO_DATA_OUT, NULL,
+			 base + GPIO_PIN_DIRECTION, NULL,
+			 BGPIOF_READ_OUTPUT_REG_SET);
 	if (ret) {
 		dev_err(&pdev->dev, "bgpio_init failed\n");
 		return ret;
@@ -78,7 +68,6 @@ static int moxart_gpio_probe(struct platform_device *pdev)
 	bgc->gc.label = "moxart-gpio";
 	bgc->gc.request = moxart_gpio_request;
 	bgc->gc.free = moxart_gpio_free;
-	bgc->gc.get = moxart_gpio_get;
 	bgc->data = bgc->read_reg(bgc->reg_set);
 	bgc->gc.base = 0;
 	bgc->gc.ngpio = 32;
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index a65b75161aa4..20aa66f34f6e 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -329,7 +329,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops mpc8xxx_gpio_irq_ops = {
+static const struct irq_domain_ops mpc8xxx_gpio_irq_ops = {
 	.map	= mpc8xxx_gpio_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 9f7446a7ac64..ec1eb1b7250f 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -131,7 +131,7 @@ static struct mxc_gpio_hwdata *mxc_gpio_hwdata;
 #define GPIO_INT_FALL_EDGE	(mxc_gpio_hwdata->fall_edge)
 #define GPIO_INT_BOTH_EDGES	0x4
 
-static struct platform_device_id mxc_gpio_devtype[] = {
+static const struct platform_device_id mxc_gpio_devtype[] = {
 	{
 		.name = "imx1-gpio",
 		.driver_data = IMX1_GPIO,
@@ -437,20 +437,20 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 		irq_set_chained_handler(port->irq, mx2_gpio_irq_handler);
 	} else {
 		/* setup one handler for each entry */
-		irq_set_chained_handler(port->irq, mx3_gpio_irq_handler);
-		irq_set_handler_data(port->irq, port);
-		if (port->irq_high > 0) {
+		irq_set_chained_handler_and_data(port->irq,
+						 mx3_gpio_irq_handler, port);
+		if (port->irq_high > 0)
 			/* setup handler for GPIO 16 to 31 */
-			irq_set_chained_handler(port->irq_high,
-						mx3_gpio_irq_handler);
-			irq_set_handler_data(port->irq_high, port);
-		}
+			irq_set_chained_handler_and_data(port->irq_high,
+							 mx3_gpio_irq_handler,
+							 port);
 	}
 
 	err = bgpio_init(&port->bgc, &pdev->dev, 4,
 			 port->base + GPIO_PSR,
 			 port->base + GPIO_DR, NULL,
-			 port->base + GPIO_GDIR, NULL, 0);
+			 port->base + GPIO_GDIR, NULL,
+			 BGPIOF_READ_OUTPUT_REG_SET);
 	if (err)
 		goto out_bgio;
 
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index 84cbda6acdda..551d15d7c369 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -239,7 +239,7 @@ static int mxs_gpio_get_direction(struct gpio_chip *gc, unsigned offset)
 	return !(dir & mask);
 }
 
-static struct platform_device_id mxs_gpio_ids[] = {
+static const struct platform_device_id mxs_gpio_ids[] = {
 	{
 		.name = "imx23-gpio",
 		.driver_data = IMX23_GPIO,
@@ -320,8 +320,8 @@ static int mxs_gpio_probe(struct platform_device *pdev)
 	mxs_gpio_init_gc(port, irq_base);
 
 	/* setup one handler for each entry */
-	irq_set_chained_handler(port->irq, mxs_gpio_irq_handler);
-	irq_set_handler_data(port->irq, port);
+	irq_set_chained_handler_and_data(port->irq, mxs_gpio_irq_handler,
+					 port);
 
 	err = bgpio_init(&port->bgc, &pdev->dev, 4,
 			 port->base + PINCTRL_DIN(port),
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index cd1d5bf48f36..b0c57d505be7 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -488,9 +488,6 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 	unsigned long flags;
 	unsigned offset = d->hwirq;
 
-	if (!BANK_USED(bank))
-		pm_runtime_get_sync(bank->dev);
-
 	if (type & ~IRQ_TYPE_SENSE_MASK)
 		return -EINVAL;
 
@@ -498,12 +495,18 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 		(type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH)))
 		return -EINVAL;
 
+	if (!BANK_USED(bank))
+		pm_runtime_get_sync(bank->dev);
+
 	spin_lock_irqsave(&bank->lock, flags);
 	retval = omap_set_gpio_triggering(bank, offset, type);
+	if (retval)
+		goto error;
 	omap_gpio_init_irq(bank, offset);
 	if (!omap_gpio_is_input(bank, offset)) {
 		spin_unlock_irqrestore(&bank->lock, flags);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto error;
 	}
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -512,6 +515,11 @@ static int omap_gpio_irq_type(struct irq_data *d, unsigned type)
 	else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		__irq_set_handler_locked(d->irq, handle_edge_irq);
 
+	return 0;
+
+error:
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
 	return retval;
 }
 
@@ -638,15 +646,6 @@ static int omap_set_gpio_wakeup(struct gpio_bank *bank, unsigned offset,
 	return 0;
 }
 
-static void omap_reset_gpio(struct gpio_bank *bank, unsigned offset)
-{
-	omap_set_gpio_direction(bank, offset, 1);
-	omap_set_gpio_irqenable(bank, offset, 0);
-	omap_clear_gpio_irqstatus(bank, offset);
-	omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-	omap_clear_gpio_debounce(bank, offset);
-}
-
 /* Use disable_irq_wake() and enable_irq_wake() functions from drivers */
 static int omap_gpio_wake_enable(struct irq_data *d, unsigned int enable)
 {
@@ -669,14 +668,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
-	/* Set trigger to none. You need to enable the desired trigger with
-	 * request_irq() or set_irq_type(). Only do this if the IRQ line has
-	 * not already been requested.
-	 */
-	if (!LINE_USED(bank->irq_usage, offset)) {
-		omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-		omap_enable_gpio_module(bank, offset);
-	}
+	omap_enable_gpio_module(bank, offset);
 	bank->mod_usage |= BIT(offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
@@ -690,8 +682,11 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 
 	spin_lock_irqsave(&bank->lock, flags);
 	bank->mod_usage &= ~(BIT(offset));
+	if (!LINE_USED(bank->irq_usage, offset)) {
+		omap_set_gpio_direction(bank, offset, 1);
+		omap_clear_gpio_debounce(bank, offset);
+	}
 	omap_disable_gpio_module(bank, offset);
-	omap_reset_gpio(bank, offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
@@ -795,11 +790,23 @@ static unsigned int omap_gpio_irq_startup(struct irq_data *d)
 		pm_runtime_get_sync(bank->dev);
 
 	spin_lock_irqsave(&bank->lock, flags);
-	omap_gpio_init_irq(bank, offset);
+
+	if (!LINE_USED(bank->mod_usage, offset))
+		omap_set_gpio_direction(bank, offset, 1);
+	else if (!omap_gpio_is_input(bank, offset))
+		goto err;
+	omap_enable_gpio_module(bank, offset);
+	bank->irq_usage |= BIT(offset);
+
 	spin_unlock_irqrestore(&bank->lock, flags);
 	omap_gpio_unmask_irq(d);
 
 	return 0;
+err:
+	spin_unlock_irqrestore(&bank->lock, flags);
+	if (!BANK_USED(bank))
+		pm_runtime_put(bank->dev);
+	return -EINVAL;
 }
 
 static void omap_gpio_irq_shutdown(struct irq_data *d)
@@ -810,8 +817,12 @@ static void omap_gpio_irq_shutdown(struct irq_data *d)
 
 	spin_lock_irqsave(&bank->lock, flags);
 	bank->irq_usage &= ~(BIT(offset));
+	omap_set_gpio_irqenable(bank, offset, 0);
+	omap_clear_gpio_irqstatus(bank, offset);
+	omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+	if (!LINE_USED(bank->mod_usage, offset))
+		omap_clear_gpio_debounce(bank, offset);
 	omap_disable_gpio_module(bank, offset);
-	omap_reset_gpio(bank, offset);
 	spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
@@ -1054,38 +1065,8 @@ static void omap_gpio_mod_init(struct gpio_bank *bank)
 		dev_err(bank->dev, "Could not get gpio dbck\n");
 }
 
-static void
-omap_mpuio_alloc_gc(struct gpio_bank *bank, unsigned int irq_start,
-		    unsigned int num)
-{
-	struct irq_chip_generic *gc;
-	struct irq_chip_type *ct;
-
-	gc = irq_alloc_generic_chip("MPUIO", 1, irq_start, bank->base,
-				    handle_simple_irq);
-	if (!gc) {
-		dev_err(bank->dev, "Memory alloc failed for gc\n");
-		return;
-	}
-
-	ct = gc->chip_types;
-
-	/* NOTE: No ack required, reading IRQ status clears it. */
-	ct->chip.irq_mask = irq_gc_mask_set_bit;
-	ct->chip.irq_unmask = irq_gc_mask_clr_bit;
-	ct->chip.irq_set_type = omap_gpio_irq_type;
-
-	if (bank->regs->wkup_en)
-		ct->chip.irq_set_wake = omap_gpio_wake_enable;
-
-	ct->regs.mask = OMAP_MPUIO_GPIO_INT / bank->stride;
-	irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
-			       IRQ_NOREQUEST | IRQ_NOPROBE, 0);
-}
-
 static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 {
-	int j;
 	static int gpio;
 	int irq_base = 0;
 	int ret;
@@ -1132,6 +1113,15 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 	}
 #endif
 
+	/* MPUIO is a bit different, reading IRQ status clears it */
+	if (bank->is_mpuio) {
+		irqc->irq_ack = dummy_irq_chip.irq_ack;
+		irqc->irq_mask = irq_gc_mask_set_bit;
+		irqc->irq_unmask = irq_gc_mask_clr_bit;
+		if (!bank->regs->wkup_en)
+			irqc->irq_set_wake = NULL;
+	}
+
 	ret = gpiochip_irqchip_add(&bank->chip, irqc,
 				   irq_base, omap_gpio_irq_handler,
 				   IRQ_TYPE_NONE);
@@ -1145,15 +1135,6 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 	gpiochip_set_chained_irqchip(&bank->chip, irqc,
 				     bank->irq, omap_gpio_irq_handler);
 
-	for (j = 0; j < bank->width; j++) {
-		int irq = irq_find_mapping(bank->chip.irqdomain, j);
-		if (bank->is_mpuio) {
-			omap_mpuio_alloc_gc(bank, irq, bank->width);
-			irq_set_chip_and_handler(irq, NULL, NULL);
-			set_irq_flags(irq, 0);
-		}
-	}
-
 	return 0;
 }
 
@@ -1263,6 +1244,17 @@ static int omap_gpio_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int omap_gpio_remove(struct platform_device *pdev)
+{
+	struct gpio_bank *bank = platform_get_drvdata(pdev);
+
+	list_del(&bank->node);
+	gpiochip_remove(&bank->chip);
+	pm_runtime_disable(bank->dev);
+
+	return 0;
+}
+
 #ifdef CONFIG_ARCH_OMAP2PLUS
 
 #if defined(CONFIG_PM)
@@ -1448,6 +1440,7 @@ static int omap_gpio_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
+#if IS_BUILTIN(CONFIG_GPIO_OMAP)
 void omap2_gpio_prepare_for_idle(int pwr_mode)
 {
 	struct gpio_bank *bank;
@@ -1473,6 +1466,7 @@ void omap2_gpio_resume_after_idle(void)
 		pm_runtime_get_sync(bank->dev);
 	}
 }
+#endif
 
 #if defined(CONFIG_PM)
 static void omap_gpio_init_context(struct gpio_bank *p)
@@ -1628,6 +1622,7 @@ MODULE_DEVICE_TABLE(of, omap_gpio_match);
 
 static struct platform_driver omap_gpio_driver = {
 	.probe		= omap_gpio_probe,
+	.remove		= omap_gpio_remove,
 	.driver		= {
 		.name	= "omap_gpio",
 		.pm	= &gpio_pm_ops,
@@ -1645,3 +1640,13 @@ static int __init omap_gpio_drv_reg(void)
 	return platform_driver_register(&omap_gpio_driver);
 }
 postcore_initcall(omap_gpio_drv_reg);
+
+static void __exit omap_gpio_exit(void)
+{
+	platform_driver_unregister(&omap_gpio_driver);
+}
+module_exit(omap_gpio_exit);
+
+MODULE_DESCRIPTION("omap gpio driver");
+MODULE_ALIAS("platform:gpio-omap");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index e2da64abbccd..d233eb3b8132 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -443,12 +443,13 @@ static struct irq_chip pca953x_irq_chip = {
 	.irq_set_type		= pca953x_irq_set_type,
 };
 
-static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
+static bool pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 {
 	u8 cur_stat[MAX_BANK];
 	u8 old_stat[MAX_BANK];
-	u8 pendings = 0;
-	u8 trigger[MAX_BANK], triggers = 0;
+	bool pending_seen = false;
+	bool trigger_seen = false;
+	u8 trigger[MAX_BANK];
 	int ret, i, offset = 0;
 
 	switch (chip->chip_type) {
@@ -461,7 +462,7 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 	}
 	ret = pca953x_read_regs(chip, offset, cur_stat);
 	if (ret)
-		return 0;
+		return false;
 
 	/* Remove output pins from the equation */
 	for (i = 0; i < NBANK(chip); i++)
@@ -471,11 +472,12 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 
 	for (i = 0; i < NBANK(chip); i++) {
 		trigger[i] = (cur_stat[i] ^ old_stat[i]) & chip->irq_mask[i];
-		triggers += trigger[i];
+		if (trigger[i])
+			trigger_seen = true;
 	}
 
-	if (!triggers)
-		return 0;
+	if (!trigger_seen)
+		return false;
 
 	memcpy(chip->irq_stat, cur_stat, NBANK(chip));
 
@@ -483,10 +485,11 @@ static u8 pca953x_irq_pending(struct pca953x_chip *chip, u8 *pending)
 		pending[i] = (old_stat[i] & chip->irq_trig_fall[i]) |
 			(cur_stat[i] & chip->irq_trig_raise[i]);
 		pending[i] &= trigger[i];
-		pendings += pending[i];
+		if (pending[i])
+			pending_seen = true;
 	}
 
-	return pendings;
+	return pending_seen;
 }
 
 static irqreturn_t pca953x_irq_handler(int irq, void *devid)
@@ -630,7 +633,7 @@ static int device_pca957x_init(struct pca953x_chip *chip, u32 invert)
 		memset(val, 0, NBANK(chip));
 	pca953x_write_regs(chip, PCA957X_INVRT, val);
 
-	/* To enable register 6, 7 to controll pull up and pull down */
+	/* To enable register 6, 7 to control pull up and pull down */
 	memset(val, 0x02, NBANK(chip));
 	pca953x_write_regs(chip, PCA957X_BKEN, val);
 
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index 945f0cda8529..404f3c61ef9b 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -91,6 +91,8 @@ struct pcf857x {
 	spinlock_t		slock;		/* protect irq demux */
 	unsigned		out;		/* software latch */
 	unsigned		status;		/* current status */
+	unsigned int		irq_parent;
+	unsigned		irq_enabled;	/* enabled irqs */
 
 	int (*write)(struct i2c_client *client, unsigned data);
 	int (*read)(struct i2c_client *client);
@@ -194,7 +196,7 @@ static irqreturn_t pcf857x_irq(int irq, void *data)
 	 * interrupt source, just to avoid bad irqs
 	 */
 
-	change = (gpio->status ^ status);
+	change = (gpio->status ^ status) & gpio->irq_enabled;
 	for_each_set_bit(i, &change, gpio->chip.ngpio)
 		handle_nested_irq(irq_find_mapping(gpio->chip.irqdomain, i));
 	gpio->status = status;
@@ -209,29 +211,62 @@ static irqreturn_t pcf857x_irq(int irq, void *data)
  */
 static void noop(struct irq_data *data) { }
 
-static unsigned int noop_ret(struct irq_data *data)
+static int pcf857x_irq_set_wake(struct irq_data *data, unsigned int on)
 {
-	return 0;
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	int error = 0;
+
+	if (gpio->irq_parent) {
+		error = irq_set_irq_wake(gpio->irq_parent, on);
+		if (error) {
+			dev_dbg(&gpio->client->dev,
+				"irq %u doesn't support irq_set_wake\n",
+				gpio->irq_parent);
+			gpio->irq_parent = 0;
+		}
+	}
+	return error;
 }
 
-static int pcf857x_irq_set_wake(struct irq_data *data, unsigned int on)
+static void pcf857x_irq_enable(struct irq_data *data)
 {
 	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
 
-	irq_set_irq_wake(gpio->client->irq, on);
-	return 0;
+	gpio->irq_enabled |= (1 << data->hwirq);
+}
+
+static void pcf857x_irq_disable(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	gpio->irq_enabled &= ~(1 << data->hwirq);
+}
+
+static void pcf857x_irq_bus_lock(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&gpio->lock);
+}
+
+static void pcf857x_irq_bus_sync_unlock(struct irq_data *data)
+{
+	struct pcf857x *gpio = irq_data_get_irq_chip_data(data);
+
+	mutex_unlock(&gpio->lock);
 }
 
 static struct irq_chip pcf857x_irq_chip = {
 	.name		= "pcf857x",
-	.irq_startup	= noop_ret,
-	.irq_shutdown	= noop,
-	.irq_enable	= noop,
-	.irq_disable	= noop,
+	.irq_enable	= pcf857x_irq_enable,
+	.irq_disable	= pcf857x_irq_disable,
 	.irq_ack	= noop,
 	.irq_mask	= noop,
 	.irq_unmask	= noop,
 	.irq_set_wake	= pcf857x_irq_set_wake,
+	.irq_bus_lock		= pcf857x_irq_bus_lock,
+	.irq_bus_sync_unlock	= pcf857x_irq_bus_sync_unlock,
 };
 
 /*-------------------------------------------------------------------------*/
@@ -364,6 +399,7 @@ static int pcf857x_probe(struct i2c_client *client,
 
 		gpiochip_set_chained_irqchip(&gpio->chip, &pcf857x_irq_chip,
 					     client->irq, NULL);
+		gpio->irq_parent = client->irq;
 	}
 
 	/* Let platform code set up the GPIOs and their users.
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index fd3977465948..1e14a6c74ed1 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -177,8 +177,17 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct gpio_rcar_priv *p = container_of(gc, struct gpio_rcar_priv,
 						gpio_chip);
-
-	irq_set_irq_wake(p->irq_parent, on);
+	int error;
+
+	if (p->irq_parent) {
+		error = irq_set_irq_wake(p->irq_parent, on);
+		if (error) {
+			dev_dbg(&p->pdev->dev,
+				"irq %u doesn't support irq_set_wake\n",
+				p->irq_parent);
+			p->irq_parent = 0;
+		}
+	}
 
 	if (!p->clk)
 		return 0;
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index bec397a60204..3fa22dade243 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -160,7 +160,7 @@ static int sa1100_gpio_irqdomain_map(struct irq_domain *d,
 	return 0;
 }
 
-static struct irq_domain_ops sa1100_gpio_irqdomain_ops = {
+static const struct irq_domain_ops sa1100_gpio_irqdomain_ops = {
 	.map = sa1100_gpio_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/gpio/gpio-sodaville.c b/drivers/gpio/gpio-sodaville.c
index d8da36cd8123..65bc9f47a68e 100644
--- a/drivers/gpio/gpio-sodaville.c
+++ b/drivers/gpio/gpio-sodaville.c
@@ -125,7 +125,7 @@ static int sdv_xlate(struct irq_domain *h, struct device_node *node,
 	return 0;
 }
 
-static struct irq_domain_ops irq_domain_sdv_ops = {
+static const struct irq_domain_ops irq_domain_sdv_ops = {
 	.xlate = sdv_xlate,
 };
 
diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index 202361eb7279..81bdbe7ba2a4 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -58,7 +58,7 @@
 #define XWAY_STP_ADSL_MASK	0x3
 
 /* 2 groups of 3 bits can be driven by the phys */
-#define XWAY_STP_PHY_MASK	0x3
+#define XWAY_STP_PHY_MASK	0x7
 #define XWAY_STP_PHY1_SHIFT	27
 #define XWAY_STP_PHY2_SHIFT	15
 
@@ -200,7 +200,7 @@ static int xway_stp_hw_init(struct xway_stp *chip)
 static int xway_stp_probe(struct platform_device *pdev)
 {
 	struct resource *res;
-	const __be32 *shadow, *groups, *dsl, *phy;
+	u32 shadow, groups, dsl, phy;
 	struct xway_stp *chip;
 	struct clk *clk;
 	int ret = 0;
@@ -223,33 +223,28 @@ static int xway_stp_probe(struct platform_device *pdev)
 	chip->gc.owner = THIS_MODULE;
 
 	/* store the shadow value if one was passed by the devicetree */
-	shadow = of_get_property(pdev->dev.of_node, "lantiq,shadow", NULL);
-	if (shadow)
-		chip->shadow = be32_to_cpu(*shadow);
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,shadow", &shadow))
+		chip->shadow = shadow;
 
 	/* find out which gpio groups should be enabled */
-	groups = of_get_property(pdev->dev.of_node, "lantiq,groups", NULL);
-	if (groups)
-		chip->groups = be32_to_cpu(*groups) & XWAY_STP_GROUP_MASK;
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,groups", &groups))
+		chip->groups = groups & XWAY_STP_GROUP_MASK;
 	else
 		chip->groups = XWAY_STP_GROUP0;
 	chip->gc.ngpio = fls(chip->groups) * 8;
 
 	/* find out which gpios are controlled by the dsl core */
-	dsl = of_get_property(pdev->dev.of_node, "lantiq,dsl", NULL);
-	if (dsl)
-		chip->dsl = be32_to_cpu(*dsl) & XWAY_STP_ADSL_MASK;
+	if (!of_property_read_u32(pdev->dev.of_node, "lantiq,dsl", &dsl))
+		chip->dsl = dsl & XWAY_STP_ADSL_MASK;
 
 	/* find out which gpios are controlled by the phys */
 	if (of_machine_is_compatible("lantiq,ar9") ||
 			of_machine_is_compatible("lantiq,gr9") ||
 			of_machine_is_compatible("lantiq,vr9")) {
-		phy = of_get_property(pdev->dev.of_node, "lantiq,phy1", NULL);
-		if (phy)
-			chip->phy1 = be32_to_cpu(*phy) & XWAY_STP_PHY_MASK;
-		phy = of_get_property(pdev->dev.of_node, "lantiq,phy2", NULL);
-		if (phy)
-			chip->phy2 = be32_to_cpu(*phy) & XWAY_STP_PHY_MASK;
+		if (!of_property_read_u32(pdev->dev.of_node, "lantiq,phy1", &phy))
+			chip->phy1 = phy & XWAY_STP_PHY_MASK;
+		if (!of_property_read_u32(pdev->dev.of_node, "lantiq,phy2", &phy))
+			chip->phy2 = phy & XWAY_STP_PHY_MASK;
 	}
 
 	/* check which edge trigger we should use, default to a falling edge */
diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index 46b89614aa91..12c99d969b98 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -292,7 +292,6 @@ static int tb10x_gpio_remove(struct platform_device *pdev)
 					BIT(tb10x_gpio->gc.ngpio) - 1, 0, 0);
 		kfree(tb10x_gpio->domain->gc);
 		irq_domain_remove(tb10x_gpio->domain);
-		free_irq(tb10x_gpio->irq, tb10x_gpio);
 	}
 	gpiochip_remove(&tb10x_gpio->gc);
 
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 1741981d53c8..9b25c90f725c 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -288,7 +288,7 @@ static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
 			tegra_gpio_writel(1 << pin, GPIO_INT_CLR(gpio));
 
 			/* if gpio is edge triggered, clear condition
-			 * before executing the hander so that we don't
+			 * before executing the handler so that we don't
 			 * miss edges
 			 */
 			if (lvl & (0x100 << pin)) {
@@ -515,8 +515,8 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 	for (i = 0; i < tegra_gpio_bank_count; i++) {
 		bank = &tegra_gpio_banks[i];
 
-		irq_set_chained_handler(bank->irq, tegra_gpio_irq_handler);
-		irq_set_handler_data(bank->irq, bank);
+		irq_set_chained_handler_and_data(bank->irq,
+						 tegra_gpio_irq_handler, bank);
 
 		for (j = 0; j < 4; j++)
 			spin_lock_init(&bank->lvl_lock[j]);
diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c
index 92fbabd82879..b29a102d136b 100644
--- a/drivers/gpio/gpio-ts5500.c
+++ b/drivers/gpio/gpio-ts5500.c
@@ -440,7 +440,7 @@ static int ts5500_dio_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id ts5500_dio_ids[] = {
+static const struct platform_device_id ts5500_dio_ids[] = {
 	{ "ts5500-dio1", TS5500_DIO1 },
 	{ "ts5500-dio2", TS5500_DIO2 },
 	{ "ts5500-dio-lcd", TS5500_LCD },
diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c
index fb9d29a5d584..d57068b9083e 100644
--- a/drivers/gpio/gpio-xgene-sb.c
+++ b/drivers/gpio/gpio-xgene-sb.c
@@ -25,8 +25,11 @@
 #include <linux/of_gpio.h>
 #include <linux/gpio.h>
 #include <linux/gpio/driver.h>
+#include <linux/acpi.h>
 #include <linux/basic_mmio_gpio.h>
 
+#include "gpiolib.h"
+
 #define XGENE_MAX_GPIO_DS		22
 #define XGENE_MAX_GPIO_DS_IRQ		6
 
@@ -112,7 +115,6 @@ static int xgene_gpio_sb_probe(struct platform_device *pdev)
 				   GFP_KERNEL);
 	if (!priv->irq)
 		return -ENOMEM;
-	memset(priv->irq, 0, sizeof(u32) * XGENE_MAX_GPIO_DS);
 
 	for (i = 0; i < priv->nirq; i++) {
 		priv->irq[default_lines[i]] = platform_get_irq(pdev, i);
@@ -129,6 +131,11 @@ static int xgene_gpio_sb_probe(struct platform_device *pdev)
 	else
 		dev_info(&pdev->dev, "X-Gene GPIO Standby driver registered\n");
 
+	if (priv->nirq > 0) {
+		/* Register interrupt handlers for gpio signaled acpi events */
+		acpi_gpiochip_request_interrupts(&priv->bgc.gc);
+	}
+
 	return ret;
 }
 
@@ -136,6 +143,10 @@ static int xgene_gpio_sb_remove(struct platform_device *pdev)
 {
 	struct xgene_gpio_sb *priv = platform_get_drvdata(pdev);
 
+	if (priv->nirq > 0) {
+		acpi_gpiochip_free_interrupts(&priv->bgc.gc);
+	}
+
 	return bgpio_remove(&priv->bgc);
 }
 
@@ -145,10 +156,19 @@ static const struct of_device_id xgene_gpio_sb_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, xgene_gpio_sb_of_match);
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id xgene_gpio_sb_acpi_match[] = {
+	{"APMC0D15", 0},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, xgene_gpio_sb_acpi_match);
+#endif
+
 static struct platform_driver xgene_gpio_sb_driver = {
 	.driver = {
 		   .name = "xgene-gpio-sb",
 		   .of_match_table = xgene_gpio_sb_of_match,
+		   .acpi_match_table = ACPI_PTR(xgene_gpio_sb_acpi_match),
 		   },
 	.probe = xgene_gpio_sb_probe,
 	.remove = xgene_gpio_sb_remove,
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 61243d177740..77fe5d3cb105 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -41,10 +41,10 @@
 /**
  * struct xgpio_instance - Stores information about GPIO device
  * @mmchip: OF GPIO chip for memory mapped banks
+ * @gpio_width: GPIO width for every channel
  * @gpio_state: GPIO state shadow register
  * @gpio_dir: GPIO direction shadow register
  * @gpio_lock: Lock used for synchronization
- * @inited: True if the port has been inited
  */
 struct xgpio_instance {
 	struct of_mm_gpio_chip mmchip;
@@ -231,6 +231,8 @@ static void xgpio_save_regs(struct of_mm_gpio_chip *mm_gc)
  * @pdev: pointer to the platform device
  *
  * This function remove gpiochips and frees all the allocated resources.
+ *
+ * Return: 0 always
  */
 static int xgpio_remove(struct platform_device *pdev)
 {
diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c
new file mode 100644
index 000000000000..9bdab7203d65
--- /dev/null
+++ b/drivers/gpio/gpio-xlp.c
@@ -0,0 +1,427 @@
+/*
+ * Copyright (C) 2003-2015 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+/*
+ * XLP GPIO has multiple 32 bit registers for each feature where each register
+ * controls 32 pins. So, pins up to 64 require 2 32-bit registers and up to 96
+ * require 3 32-bit registers for each feature.
+ * Here we only define offset of the first register for each feature. Offset of
+ * the registers for pins greater than 32 can be calculated as following(Use
+ * GPIO_INT_STAT as example):
+ *
+ * offset = (gpio / XLP_GPIO_REGSZ) * 4;
+ * reg_addr = addr + offset;
+ *
+ * where addr is base address of the that feature register and gpio is the pin.
+ */
+#define GPIO_OUTPUT_EN		0x00
+#define GPIO_PADDRV		0x08
+#define GPIO_INT_EN00		0x18
+#define GPIO_INT_EN10		0x20
+#define GPIO_INT_EN20		0x28
+#define GPIO_INT_EN30		0x30
+#define GPIO_INT_POL		0x38
+#define GPIO_INT_TYPE		0x40
+#define GPIO_INT_STAT		0x48
+
+#define GPIO_9XX_BYTESWAP	0X00
+#define GPIO_9XX_CTRL		0X04
+#define GPIO_9XX_OUTPUT_EN	0x14
+#define GPIO_9XX_PADDRV		0x24
+/*
+ * Only for 4 interrupt enable reg are defined for now,
+ * total reg available are 12.
+ */
+#define GPIO_9XX_INT_EN00	0x44
+#define GPIO_9XX_INT_EN10	0x54
+#define GPIO_9XX_INT_EN20	0x64
+#define GPIO_9XX_INT_EN30	0x74
+#define GPIO_9XX_INT_POL	0x104
+#define GPIO_9XX_INT_TYPE	0x114
+#define GPIO_9XX_INT_STAT	0x124
+
+#define GPIO_3XX_INT_EN00	0x18
+#define GPIO_3XX_INT_EN10	0x20
+#define GPIO_3XX_INT_EN20	0x28
+#define GPIO_3XX_INT_EN30	0x30
+#define GPIO_3XX_INT_POL	0x78
+#define GPIO_3XX_INT_TYPE	0x80
+#define GPIO_3XX_INT_STAT	0x88
+
+/* Interrupt type register mask */
+#define XLP_GPIO_IRQ_TYPE_LVL	0x0
+#define XLP_GPIO_IRQ_TYPE_EDGE	0x1
+
+/* Interrupt polarity register mask */
+#define XLP_GPIO_IRQ_POL_HIGH	0x0
+#define XLP_GPIO_IRQ_POL_LOW	0x1
+
+#define XLP_GPIO_REGSZ		32
+#define XLP_GPIO_IRQ_BASE	768
+#define XLP_MAX_NR_GPIO		96
+
+/* XLP variants supported by this driver */
+enum {
+	XLP_GPIO_VARIANT_XLP832 = 1,
+	XLP_GPIO_VARIANT_XLP316,
+	XLP_GPIO_VARIANT_XLP208,
+	XLP_GPIO_VARIANT_XLP980,
+	XLP_GPIO_VARIANT_XLP532
+};
+
+struct xlp_gpio_priv {
+	struct gpio_chip chip;
+	DECLARE_BITMAP(gpio_enabled_mask, XLP_MAX_NR_GPIO);
+	void __iomem *gpio_intr_en;	/* pointer to first intr enable reg */
+	void __iomem *gpio_intr_stat;	/* pointer to first intr status reg */
+	void __iomem *gpio_intr_type;	/* pointer to first intr type reg */
+	void __iomem *gpio_intr_pol;	/* pointer to first intr polarity reg */
+	void __iomem *gpio_out_en;	/* pointer to first output enable reg */
+	void __iomem *gpio_paddrv;	/* pointer to first pad drive reg */
+	spinlock_t lock;
+};
+
+static struct xlp_gpio_priv *gpio_chip_to_xlp_priv(struct gpio_chip *gc)
+{
+	return container_of(gc, struct xlp_gpio_priv, chip);
+}
+
+static int xlp_gpio_get_reg(void __iomem *addr, unsigned gpio)
+{
+	u32 pos, regset;
+
+	pos = gpio % XLP_GPIO_REGSZ;
+	regset = (gpio / XLP_GPIO_REGSZ) * 4;
+	return !!(readl(addr + regset) & BIT(pos));
+}
+
+static void xlp_gpio_set_reg(void __iomem *addr, unsigned gpio, int state)
+{
+	u32 value, pos, regset;
+
+	pos = gpio % XLP_GPIO_REGSZ;
+	regset = (gpio / XLP_GPIO_REGSZ) * 4;
+	value = readl(addr + regset);
+
+	if (state)
+		value |= BIT(pos);
+	else
+		value &= ~BIT(pos);
+
+	writel(value, addr + regset);
+}
+
+static void xlp_gpio_irq_disable(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x0);
+	__clear_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void xlp_gpio_irq_mask_ack(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x0);
+	xlp_gpio_set_reg(priv->gpio_intr_stat, d->hwirq, 0x1);
+	__clear_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static void xlp_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	xlp_gpio_set_reg(priv->gpio_intr_en, d->hwirq, 0x1);
+	__set_bit(d->hwirq, priv->gpio_enabled_mask);
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+static int xlp_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc  = irq_data_get_irq_chip_data(d);
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+	int pol, irq_type;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+		irq_type = XLP_GPIO_IRQ_TYPE_EDGE;
+		pol = XLP_GPIO_IRQ_POL_HIGH;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		irq_type = XLP_GPIO_IRQ_TYPE_EDGE;
+		pol = XLP_GPIO_IRQ_POL_LOW;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		irq_type = XLP_GPIO_IRQ_TYPE_LVL;
+		pol = XLP_GPIO_IRQ_POL_HIGH;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		irq_type = XLP_GPIO_IRQ_TYPE_LVL;
+		pol = XLP_GPIO_IRQ_POL_LOW;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	xlp_gpio_set_reg(priv->gpio_intr_type, d->hwirq, irq_type);
+	xlp_gpio_set_reg(priv->gpio_intr_pol, d->hwirq, pol);
+
+	return 0;
+}
+
+static struct irq_chip xlp_gpio_irq_chip = {
+	.name		= "XLP-GPIO",
+	.irq_mask_ack	= xlp_gpio_irq_mask_ack,
+	.irq_disable	= xlp_gpio_irq_disable,
+	.irq_set_type	= xlp_gpio_set_irq_type,
+	.irq_unmask	= xlp_gpio_irq_unmask,
+	.flags		= IRQCHIP_ONESHOT_SAFE,
+};
+
+static irqreturn_t xlp_gpio_generic_handler(int irq, void *data)
+{
+	struct xlp_gpio_priv *priv = data;
+	int gpio, regoff;
+	u32 gpio_stat;
+
+	regoff = -1;
+	gpio_stat = 0;
+	for_each_set_bit(gpio, priv->gpio_enabled_mask, XLP_MAX_NR_GPIO) {
+		if (regoff != gpio / XLP_GPIO_REGSZ) {
+			regoff = gpio / XLP_GPIO_REGSZ;
+			gpio_stat = readl(priv->gpio_intr_stat + regoff * 4);
+		}
+		if (gpio_stat & BIT(gpio % XLP_GPIO_REGSZ))
+			generic_handle_irq(irq_find_mapping(
+						priv->chip.irqdomain, gpio));
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int xlp_gpio_dir_output(struct gpio_chip *gc, unsigned gpio, int state)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_out_en, gpio, 0x1);
+
+	return 0;
+}
+
+static int xlp_gpio_dir_input(struct gpio_chip *gc, unsigned gpio)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_out_en, gpio, 0x0);
+
+	return 0;
+}
+
+static int xlp_gpio_get(struct gpio_chip *gc, unsigned gpio)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	return xlp_gpio_get_reg(priv->gpio_paddrv, gpio);
+}
+
+static void xlp_gpio_set(struct gpio_chip *gc, unsigned gpio, int state)
+{
+	struct xlp_gpio_priv *priv = gpio_chip_to_xlp_priv(gc);
+
+	BUG_ON(gpio >= gc->ngpio);
+	xlp_gpio_set_reg(priv->gpio_paddrv, gpio, state);
+}
+
+static const struct of_device_id xlp_gpio_of_ids[] = {
+	{
+		.compatible = "netlogic,xlp832-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP832,
+	},
+	{
+		.compatible = "netlogic,xlp316-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP316,
+	},
+	{
+		.compatible = "netlogic,xlp208-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP208,
+	},
+	{
+		.compatible = "netlogic,xlp980-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP980,
+	},
+	{
+		.compatible = "netlogic,xlp532-gpio",
+		.data	    = (void *)XLP_GPIO_VARIANT_XLP532,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, xlp_gpio_of_ids);
+
+static int xlp_gpio_probe(struct platform_device *pdev)
+{
+	struct gpio_chip *gc;
+	struct resource *iores;
+	struct xlp_gpio_priv *priv;
+	const struct of_device_id *of_id;
+	void __iomem *gpio_base;
+	int irq_base, irq, err;
+	int ngpio;
+	u32 soc_type;
+
+	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!iores)
+		return -ENODEV;
+
+	priv = devm_kzalloc(&pdev->dev,	sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	gpio_base = devm_ioremap_resource(&pdev->dev, iores);
+	if (IS_ERR(gpio_base))
+		return PTR_ERR(gpio_base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	of_id = of_match_device(xlp_gpio_of_ids, &pdev->dev);
+	if (!of_id) {
+		dev_err(&pdev->dev, "Failed to get soc type!\n");
+		return -ENODEV;
+	}
+
+	soc_type = (uintptr_t) of_id->data;
+
+	switch (soc_type) {
+	case XLP_GPIO_VARIANT_XLP832:
+		priv->gpio_out_en = gpio_base + GPIO_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_INT_EN00;
+		ngpio = 41;
+		break;
+	case XLP_GPIO_VARIANT_XLP208:
+	case XLP_GPIO_VARIANT_XLP316:
+		priv->gpio_out_en = gpio_base + GPIO_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_3XX_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_3XX_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_3XX_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_3XX_INT_EN00;
+
+		ngpio = (soc_type == XLP_GPIO_VARIANT_XLP208) ? 42 : 57;
+		break;
+	case XLP_GPIO_VARIANT_XLP980:
+	case XLP_GPIO_VARIANT_XLP532:
+		priv->gpio_out_en = gpio_base + GPIO_9XX_OUTPUT_EN;
+		priv->gpio_paddrv = gpio_base + GPIO_9XX_PADDRV;
+		priv->gpio_intr_stat = gpio_base + GPIO_9XX_INT_STAT;
+		priv->gpio_intr_type = gpio_base + GPIO_9XX_INT_TYPE;
+		priv->gpio_intr_pol = gpio_base + GPIO_9XX_INT_POL;
+		priv->gpio_intr_en = gpio_base + GPIO_9XX_INT_EN00;
+
+		ngpio = (soc_type == XLP_GPIO_VARIANT_XLP980) ? 66 : 67;
+		break;
+	default:
+		dev_err(&pdev->dev, "Unknown Processor type!\n");
+		return -ENODEV;
+	}
+
+	bitmap_zero(priv->gpio_enabled_mask, XLP_MAX_NR_GPIO);
+
+	gc = &priv->chip;
+
+	gc->owner = THIS_MODULE;
+	gc->label = dev_name(&pdev->dev);
+	gc->base = 0;
+	gc->dev = &pdev->dev;
+	gc->ngpio = ngpio;
+	gc->of_node = pdev->dev.of_node;
+	gc->direction_output = xlp_gpio_dir_output;
+	gc->direction_input = xlp_gpio_dir_input;
+	gc->set = xlp_gpio_set;
+	gc->get = xlp_gpio_get;
+
+	spin_lock_init(&priv->lock);
+
+	err = devm_request_irq(&pdev->dev, irq, xlp_gpio_generic_handler,
+			IRQ_TYPE_NONE, pdev->name, priv);
+	if (err)
+		return err;
+
+	irq_base = irq_alloc_descs(-1, XLP_GPIO_IRQ_BASE, gc->ngpio, 0);
+	if (irq_base < 0) {
+		dev_err(&pdev->dev, "Failed to allocate IRQ numbers\n");
+		return err;
+	}
+
+	err = gpiochip_add(gc);
+	if (err < 0)
+		goto out_free_desc;
+
+	err = gpiochip_irqchip_add(gc, &xlp_gpio_irq_chip, irq_base,
+				handle_level_irq, IRQ_TYPE_NONE);
+	if (err) {
+		dev_err(&pdev->dev, "Could not connect irqchip to gpiochip!\n");
+		goto out_gpio_remove;
+	}
+
+	dev_info(&pdev->dev, "registered %d GPIOs\n", gc->ngpio);
+
+	return 0;
+
+out_gpio_remove:
+	gpiochip_remove(gc);
+out_free_desc:
+	irq_free_descs(irq_base, gc->ngpio);
+	return err;
+}
+
+static struct platform_driver xlp_gpio_driver = {
+	.driver		= {
+		.name	= "xlp-gpio",
+		.of_match_table = xlp_gpio_of_ids,
+	},
+	.probe		= xlp_gpio_probe,
+};
+module_platform_driver(xlp_gpio_driver);
+
+MODULE_AUTHOR("Kamlakant Patel <kamlakant.patel@broadcom.com>");
+MODULE_AUTHOR("Ganesan Ramalingam <ganesanr@broadcom.com>");
+MODULE_DESCRIPTION("Netlogic XLP GPIO Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 184c4b1b2558..2e87c4b8da26 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -18,34 +18,47 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/of.h>
 
 #define DRIVER_NAME "zynq-gpio"
 
 /* Maximum banks */
 #define ZYNQ_GPIO_MAX_BANK	4
+#define ZYNQMP_GPIO_MAX_BANK	6
 
 #define ZYNQ_GPIO_BANK0_NGPIO	32
 #define ZYNQ_GPIO_BANK1_NGPIO	22
 #define ZYNQ_GPIO_BANK2_NGPIO	32
 #define ZYNQ_GPIO_BANK3_NGPIO	32
 
-#define ZYNQ_GPIO_NR_GPIOS	(ZYNQ_GPIO_BANK0_NGPIO + \
-				 ZYNQ_GPIO_BANK1_NGPIO + \
-				 ZYNQ_GPIO_BANK2_NGPIO + \
-				 ZYNQ_GPIO_BANK3_NGPIO)
-
-#define ZYNQ_GPIO_BANK0_PIN_MIN	0
-#define ZYNQ_GPIO_BANK0_PIN_MAX	(ZYNQ_GPIO_BANK0_PIN_MIN + \
-					ZYNQ_GPIO_BANK0_NGPIO - 1)
-#define ZYNQ_GPIO_BANK1_PIN_MIN	(ZYNQ_GPIO_BANK0_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK1_PIN_MAX	(ZYNQ_GPIO_BANK1_PIN_MIN + \
-					ZYNQ_GPIO_BANK1_NGPIO - 1)
-#define ZYNQ_GPIO_BANK2_PIN_MIN	(ZYNQ_GPIO_BANK1_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK2_PIN_MAX	(ZYNQ_GPIO_BANK2_PIN_MIN + \
-					ZYNQ_GPIO_BANK2_NGPIO - 1)
-#define ZYNQ_GPIO_BANK3_PIN_MIN	(ZYNQ_GPIO_BANK2_PIN_MAX + 1)
-#define ZYNQ_GPIO_BANK3_PIN_MAX	(ZYNQ_GPIO_BANK3_PIN_MIN + \
-					ZYNQ_GPIO_BANK3_NGPIO - 1)
+#define ZYNQMP_GPIO_BANK0_NGPIO 26
+#define ZYNQMP_GPIO_BANK1_NGPIO 26
+#define ZYNQMP_GPIO_BANK2_NGPIO 26
+#define ZYNQMP_GPIO_BANK3_NGPIO 32
+#define ZYNQMP_GPIO_BANK4_NGPIO 32
+#define ZYNQMP_GPIO_BANK5_NGPIO 32
+
+#define	ZYNQ_GPIO_NR_GPIOS	118
+#define	ZYNQMP_GPIO_NR_GPIOS	174
+
+#define ZYNQ_GPIO_BANK0_PIN_MIN(str)	0
+#define ZYNQ_GPIO_BANK0_PIN_MAX(str)	(ZYNQ_GPIO_BANK0_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK0_NGPIO - 1)
+#define ZYNQ_GPIO_BANK1_PIN_MIN(str)	(ZYNQ_GPIO_BANK0_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK1_PIN_MAX(str)	(ZYNQ_GPIO_BANK1_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK1_NGPIO - 1)
+#define ZYNQ_GPIO_BANK2_PIN_MIN(str)	(ZYNQ_GPIO_BANK1_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK2_PIN_MAX(str)	(ZYNQ_GPIO_BANK2_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK2_NGPIO - 1)
+#define ZYNQ_GPIO_BANK3_PIN_MIN(str)	(ZYNQ_GPIO_BANK2_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK3_PIN_MAX(str)	(ZYNQ_GPIO_BANK3_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK3_NGPIO - 1)
+#define ZYNQ_GPIO_BANK4_PIN_MIN(str)	(ZYNQ_GPIO_BANK3_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK4_PIN_MAX(str)	(ZYNQ_GPIO_BANK4_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK4_NGPIO - 1)
+#define ZYNQ_GPIO_BANK5_PIN_MIN(str)	(ZYNQ_GPIO_BANK4_PIN_MAX(str) + 1)
+#define ZYNQ_GPIO_BANK5_PIN_MAX(str)	(ZYNQ_GPIO_BANK5_PIN_MIN(str) + \
+					ZYNQ##str##_GPIO_BANK5_NGPIO - 1)
 
 
 /* Register offsets for the GPIO device */
@@ -89,12 +102,30 @@
  * @base_addr:	base address of the GPIO device
  * @clk:	clock resource for this controller
  * @irq:	interrupt for the GPIO device
+ * @p_data:	pointer to platform data
  */
 struct zynq_gpio {
 	struct gpio_chip chip;
 	void __iomem *base_addr;
 	struct clk *clk;
 	int irq;
+	const struct zynq_platform_data *p_data;
+};
+
+/**
+ * struct zynq_platform_data -  zynq gpio platform data structure
+ * @label:	string to store in gpio->label
+ * @ngpio:	max number of gpio pins
+ * @max_bank:	maximum number of gpio banks
+ * @bank_min:	this array represents bank's min pin
+ * @bank_max:	this array represents bank's max pin
+*/
+struct zynq_platform_data {
+	const char *label;
+	u16 ngpio;
+	int max_bank;
+	int bank_min[ZYNQMP_GPIO_MAX_BANK];
+	int bank_max[ZYNQMP_GPIO_MAX_BANK];
 };
 
 static struct irq_chip zynq_gpio_level_irqchip;
@@ -112,39 +143,26 @@ static struct irq_chip zynq_gpio_edge_irqchip;
  */
 static inline void zynq_gpio_get_bank_pin(unsigned int pin_num,
 					  unsigned int *bank_num,
-					  unsigned int *bank_pin_num)
+					  unsigned int *bank_pin_num,
+					  struct zynq_gpio *gpio)
 {
-	switch (pin_num) {
-	case ZYNQ_GPIO_BANK0_PIN_MIN ... ZYNQ_GPIO_BANK0_PIN_MAX:
-		*bank_num = 0;
-		*bank_pin_num = pin_num;
-		break;
-	case ZYNQ_GPIO_BANK1_PIN_MIN ... ZYNQ_GPIO_BANK1_PIN_MAX:
-		*bank_num = 1;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK1_PIN_MIN;
-		break;
-	case ZYNQ_GPIO_BANK2_PIN_MIN ... ZYNQ_GPIO_BANK2_PIN_MAX:
-		*bank_num = 2;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK2_PIN_MIN;
-		break;
-	case ZYNQ_GPIO_BANK3_PIN_MIN ... ZYNQ_GPIO_BANK3_PIN_MAX:
-		*bank_num = 3;
-		*bank_pin_num = pin_num - ZYNQ_GPIO_BANK3_PIN_MIN;
-		break;
-	default:
-		WARN(true, "invalid GPIO pin number: %u", pin_num);
-		*bank_num = 0;
-		*bank_pin_num = 0;
-		break;
+	int bank;
+
+	for (bank = 0; bank < gpio->p_data->max_bank; bank++) {
+		if ((pin_num >= gpio->p_data->bank_min[bank]) &&
+			(pin_num <= gpio->p_data->bank_max[bank])) {
+				*bank_num = bank;
+				*bank_pin_num = pin_num -
+						gpio->p_data->bank_min[bank];
+				return;
+		}
 	}
-}
 
-static const unsigned int zynq_gpio_bank_offset[] = {
-	ZYNQ_GPIO_BANK0_PIN_MIN,
-	ZYNQ_GPIO_BANK1_PIN_MIN,
-	ZYNQ_GPIO_BANK2_PIN_MIN,
-	ZYNQ_GPIO_BANK3_PIN_MIN,
-};
+	/* default */
+	WARN(true, "invalid GPIO pin number: %u", pin_num);
+	*bank_num = 0;
+	*bank_pin_num = 0;
+}
 
 /**
  * zynq_gpio_get_value - Get the state of the specified pin of GPIO device
@@ -161,7 +179,7 @@ static int zynq_gpio_get_value(struct gpio_chip *chip, unsigned int pin)
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	data = readl_relaxed(gpio->base_addr +
 			     ZYNQ_GPIO_DATA_RO_OFFSET(bank_num));
@@ -185,7 +203,7 @@ static void zynq_gpio_set_value(struct gpio_chip *chip, unsigned int pin,
 	unsigned int reg_offset, bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	if (bank_pin_num >= ZYNQ_GPIO_MID_PIN_NUM) {
 		/* only 16 data bits in bit maskable reg */
@@ -222,7 +240,7 @@ static int zynq_gpio_dir_in(struct gpio_chip *chip, unsigned int pin)
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	/* bank 0 pins 7 and 8 are special and cannot be used as inputs */
 	if (bank_num == 0 && (bank_pin_num == 7 || bank_pin_num == 8))
@@ -255,7 +273,7 @@ static int zynq_gpio_dir_out(struct gpio_chip *chip, unsigned int pin,
 	unsigned int bank_num, bank_pin_num;
 	struct zynq_gpio *gpio = container_of(chip, struct zynq_gpio, chip);
 
-	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(pin, &bank_num, &bank_pin_num, gpio);
 
 	/* set the GPIO pin as output */
 	reg = readl_relaxed(gpio->base_addr + ZYNQ_GPIO_DIRM_OFFSET(bank_num));
@@ -286,7 +304,7 @@ static void zynq_gpio_irq_mask(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
 }
@@ -306,7 +324,7 @@ static void zynq_gpio_irq_unmask(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTEN_OFFSET(bank_num));
 }
@@ -325,7 +343,7 @@ static void zynq_gpio_irq_ack(struct irq_data *irq_data)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 	writel_relaxed(BIT(bank_pin_num),
 		       gpio->base_addr + ZYNQ_GPIO_INTSTS_OFFSET(bank_num));
 }
@@ -335,7 +353,7 @@ static void zynq_gpio_irq_ack(struct irq_data *irq_data)
  * @irq_data:	irq data containing irq number of gpio pin for the interrupt
  *		to enable
  *
- * Clears the INTSTS bit and unmasks the given interrrupt.
+ * Clears the INTSTS bit and unmasks the given interrupt.
  */
 static void zynq_gpio_irq_enable(struct irq_data *irq_data)
 {
@@ -375,7 +393,7 @@ static int zynq_gpio_set_irq_type(struct irq_data *irq_data, unsigned int type)
 	struct zynq_gpio *gpio = irq_data_get_irq_chip_data(irq_data);
 
 	device_pin_num = irq_data->hwirq;
-	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num);
+	zynq_gpio_get_bank_pin(device_pin_num, &bank_num, &bank_pin_num, gpio);
 
 	int_type = readl_relaxed(gpio->base_addr +
 				 ZYNQ_GPIO_INTTYPE_OFFSET(bank_num));
@@ -470,7 +488,7 @@ static void zynq_gpio_handle_bank_irq(struct zynq_gpio *gpio,
 				      unsigned int bank_num,
 				      unsigned long pending)
 {
-	unsigned int bank_offset = zynq_gpio_bank_offset[bank_num];
+	unsigned int bank_offset = gpio->p_data->bank_min[bank_num];
 	struct irq_domain *irqdomain = gpio->chip.irqdomain;
 	int offset;
 
@@ -505,7 +523,7 @@ static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc)
 
 	chained_irq_enter(irqchip, desc);
 
-	for (bank_num = 0; bank_num < ZYNQ_GPIO_MAX_BANK; bank_num++) {
+	for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++) {
 		int_sts = readl_relaxed(gpio->base_addr +
 					ZYNQ_GPIO_INTSTS_OFFSET(bank_num));
 		int_enb = readl_relaxed(gpio->base_addr +
@@ -582,6 +600,46 @@ static const struct dev_pm_ops zynq_gpio_dev_pm_ops = {
 			zynq_gpio_runtime_resume, NULL)
 };
 
+static const struct zynq_platform_data zynqmp_gpio_def = {
+	.label = "zynqmp_gpio",
+	.ngpio = ZYNQMP_GPIO_NR_GPIOS,
+	.max_bank = ZYNQMP_GPIO_MAX_BANK,
+	.bank_min[0] = ZYNQ_GPIO_BANK0_PIN_MIN(MP),
+	.bank_max[0] = ZYNQ_GPIO_BANK0_PIN_MAX(MP),
+	.bank_min[1] = ZYNQ_GPIO_BANK1_PIN_MIN(MP),
+	.bank_max[1] = ZYNQ_GPIO_BANK1_PIN_MAX(MP),
+	.bank_min[2] = ZYNQ_GPIO_BANK2_PIN_MIN(MP),
+	.bank_max[2] = ZYNQ_GPIO_BANK2_PIN_MAX(MP),
+	.bank_min[3] = ZYNQ_GPIO_BANK3_PIN_MIN(MP),
+	.bank_max[3] = ZYNQ_GPIO_BANK3_PIN_MAX(MP),
+	.bank_min[4] = ZYNQ_GPIO_BANK4_PIN_MIN(MP),
+	.bank_max[4] = ZYNQ_GPIO_BANK4_PIN_MAX(MP),
+	.bank_min[5] = ZYNQ_GPIO_BANK5_PIN_MIN(MP),
+	.bank_max[5] = ZYNQ_GPIO_BANK5_PIN_MAX(MP),
+};
+
+static const struct zynq_platform_data zynq_gpio_def = {
+	.label = "zynq_gpio",
+	.ngpio = ZYNQ_GPIO_NR_GPIOS,
+	.max_bank = ZYNQ_GPIO_MAX_BANK,
+	.bank_min[0] = ZYNQ_GPIO_BANK0_PIN_MIN(),
+	.bank_max[0] = ZYNQ_GPIO_BANK0_PIN_MAX(),
+	.bank_min[1] = ZYNQ_GPIO_BANK1_PIN_MIN(),
+	.bank_max[1] = ZYNQ_GPIO_BANK1_PIN_MAX(),
+	.bank_min[2] = ZYNQ_GPIO_BANK2_PIN_MIN(),
+	.bank_max[2] = ZYNQ_GPIO_BANK2_PIN_MAX(),
+	.bank_min[3] = ZYNQ_GPIO_BANK3_PIN_MIN(),
+	.bank_max[3] = ZYNQ_GPIO_BANK3_PIN_MAX(),
+};
+
+static const struct of_device_id zynq_gpio_of_match[] = {
+	{ .compatible = "xlnx,zynq-gpio-1.0", .data = (void *)&zynq_gpio_def },
+	{ .compatible = "xlnx,zynqmp-gpio-1.0",
+					.data = (void *)&zynqmp_gpio_def },
+	{ /* end of table */ }
+};
+MODULE_DEVICE_TABLE(of, zynq_gpio_of_match);
+
 /**
  * zynq_gpio_probe - Initialization method for a zynq_gpio device
  * @pdev:	platform device instance
@@ -599,11 +657,18 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	struct zynq_gpio *gpio;
 	struct gpio_chip *chip;
 	struct resource *res;
+	const struct of_device_id *match;
 
 	gpio = devm_kzalloc(&pdev->dev, sizeof(*gpio), GFP_KERNEL);
 	if (!gpio)
 		return -ENOMEM;
 
+	match = of_match_node(zynq_gpio_of_match, pdev->dev.of_node);
+	if (!match) {
+		dev_err(&pdev->dev, "of_match_node() failed\n");
+		return -EINVAL;
+	}
+	gpio->p_data = match->data;
 	platform_set_drvdata(pdev, gpio);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -619,7 +684,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 
 	/* configure the gpio chip */
 	chip = &gpio->chip;
-	chip->label = "zynq_gpio";
+	chip->label = gpio->p_data->label;
 	chip->owner = THIS_MODULE;
 	chip->dev = &pdev->dev;
 	chip->get = zynq_gpio_get_value;
@@ -629,7 +694,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	chip->direction_input = zynq_gpio_dir_in;
 	chip->direction_output = zynq_gpio_dir_out;
 	chip->base = -1;
-	chip->ngpio = ZYNQ_GPIO_NR_GPIOS;
+	chip->ngpio = gpio->p_data->ngpio;
 
 	/* Enable GPIO clock */
 	gpio->clk = devm_clk_get(&pdev->dev, NULL);
@@ -651,7 +716,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	}
 
 	/* disable interrupts for all banks */
-	for (bank_num = 0; bank_num < ZYNQ_GPIO_MAX_BANK; bank_num++)
+	for (bank_num = 0; bank_num < gpio->p_data->max_bank; bank_num++)
 		writel_relaxed(ZYNQ_GPIO_IXR_DISABLE_ALL, gpio->base_addr +
 			       ZYNQ_GPIO_INTDIS_OFFSET(bank_num));
 
@@ -695,12 +760,6 @@ static int zynq_gpio_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id zynq_gpio_of_match[] = {
-	{ .compatible = "xlnx,zynq-gpio-1.0", },
-	{ /* end of table */ }
-};
-MODULE_DEVICE_TABLE(of, zynq_gpio_of_match);
-
 static struct platform_driver zynq_gpio_driver = {
 	.driver	= {
 		.name = DRIVER_NAME,
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index d2303d50f561..533fe5dbe6f8 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -114,10 +114,11 @@ static inline int acpi_gpiochip_pin_to_gpio_offset(struct gpio_chip *chip,
  * @path:	ACPI GPIO controller full path name, (e.g. "\\_SB.GPO1")
  * @pin:	ACPI GPIO pin number (0-based, controller-relative)
  *
- * Returns GPIO descriptor to use with Linux generic GPIO API, or ERR_PTR
- * error value
+ * Return: GPIO descriptor to use with Linux generic GPIO API, or ERR_PTR
+ * error value. Specifically returns %-EPROBE_DEFER if the referenced GPIO
+ * controller does not have gpiochip registered at the moment. This is to
+ * support probe deferral.
  */
-
 static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 {
 	struct gpio_chip *chip;
@@ -131,7 +132,7 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin)
 
 	chip = gpiochip_find(handle, acpi_gpiochip_find);
 	if (!chip)
-		return ERR_PTR(-ENODEV);
+		return ERR_PTR(-EPROBE_DEFER);
 
 	offset = acpi_gpiochip_pin_to_gpio_offset(chip, pin);
 	if (offset < 0)
@@ -307,6 +308,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip)
 	acpi_walk_resources(handle, "_AEI",
 			    acpi_gpiochip_request_interrupt, acpi_gpio);
 }
+EXPORT_SYMBOL_GPL(acpi_gpiochip_request_interrupts);
 
 /**
  * acpi_gpiochip_free_interrupts() - Free GPIO ACPI event interrupts.
@@ -346,6 +348,7 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip)
 		kfree(event);
 	}
 }
+EXPORT_SYMBOL_GPL(acpi_gpiochip_free_interrupts);
 
 int acpi_dev_add_driver_gpios(struct acpi_device *adev,
 			      const struct acpi_gpio_mapping *gpios)
@@ -514,6 +517,35 @@ struct gpio_desc *acpi_get_gpiod_by_index(struct acpi_device *adev,
 	return lookup.desc ? lookup.desc : ERR_PTR(-ENOENT);
 }
 
+/**
+ * acpi_dev_gpio_irq_get() - Find GpioInt and translate it to Linux IRQ number
+ * @adev: pointer to a ACPI device to get IRQ from
+ * @index: index of GpioInt resource (starting from %0)
+ *
+ * If the device has one or more GpioInt resources, this function can be
+ * used to translate from the GPIO offset in the resource to the Linux IRQ
+ * number.
+ *
+ * Return: Linux IRQ number (>%0) on success, negative errno on failure.
+ */
+int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+{
+	int idx, i;
+
+	for (i = 0, idx = 0; idx <= index; i++) {
+		struct acpi_gpio_info info;
+		struct gpio_desc *desc;
+
+		desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
+		if (IS_ERR(desc))
+			break;
+		if (info.gpioint && idx++ == index)
+			return gpiod_to_irq(desc);
+	}
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
+
 static acpi_status
 acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 			    u32 bits, u64 *value, void *handler_context,
@@ -550,7 +582,7 @@ acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
 
 	length = min(agpio->pin_table_length, (u16)(pin_index + bits));
 	for (i = pin_index; i < length; ++i) {
-		unsigned pin = agpio->pin_table[i];
+		int pin = agpio->pin_table[i];
 		struct acpi_gpio_connection *conn;
 		struct gpio_desc *desc;
 		bool found;
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index a6c67c6b4680..9a0ec48a4737 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -242,7 +242,7 @@ int of_gpio_simple_xlate(struct gpio_chip *gc,
 {
 	/*
 	 * We're discouraging gpio_cells < 2, since that way you'll have to
-	 * write your own xlate function (that will have to retrive the GPIO
+	 * write your own xlate function (that will have to retrieve the GPIO
 	 * number and the flags from a single gpio cell -- this is possible,
 	 * but not recommended).
 	 */
diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c
index 7722ed53bd65..b57ed8e55ab5 100644
--- a/drivers/gpio/gpiolib-sysfs.c
+++ b/drivers/gpio/gpiolib-sysfs.c
@@ -6,14 +6,29 @@
 #include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/kdev_t.h>
+#include <linux/slab.h>
 
 #include "gpiolib.h"
 
-static DEFINE_IDR(dirent_idr);
+#define GPIO_IRQF_TRIGGER_FALLING	BIT(0)
+#define GPIO_IRQF_TRIGGER_RISING	BIT(1)
+#define GPIO_IRQF_TRIGGER_BOTH		(GPIO_IRQF_TRIGGER_FALLING | \
+					 GPIO_IRQF_TRIGGER_RISING)
 
+struct gpiod_data {
+	struct gpio_desc *desc;
 
-/* lock protects against unexport_gpio() being called while
- * sysfs files are active.
+	struct mutex mutex;
+	struct kernfs_node *value_kn;
+	int irq;
+	unsigned char irq_flags;
+
+	bool direction_can_change;
+};
+
+/*
+ * Lock to serialise gpiod export and unexport, and prevent re-export of
+ * gpiod whose chip is being unregistered.
  */
 static DEFINE_MUTEX(sysfs_lock);
 
@@ -38,38 +53,35 @@ static DEFINE_MUTEX(sysfs_lock);
  *        /edge configuration
  */
 
-static ssize_t gpio_direction_show(struct device *dev,
+static ssize_t direction_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags)) {
-		status = -EIO;
-	} else {
-		gpiod_get_direction(desc);
-		status = sprintf(buf, "%s\n",
+	gpiod_get_direction(desc);
+	status = sprintf(buf, "%s\n",
 			test_bit(FLAG_IS_OUT, &desc->flags)
 				? "out" : "in");
-	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
 
-static ssize_t gpio_direction_store(struct device *dev,
+static ssize_t direction_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else if (sysfs_streq(buf, "high"))
+	if (sysfs_streq(buf, "high"))
 		status = gpiod_direction_output_raw(desc, 1);
 	else if (sysfs_streq(buf, "out") || sysfs_streq(buf, "low"))
 		status = gpiod_direction_output_raw(desc, 0);
@@ -78,43 +90,40 @@ static ssize_t gpio_direction_store(struct device *dev,
 	else
 		status = -EINVAL;
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status ? : size;
 }
+static DEVICE_ATTR_RW(direction);
 
-static /* const */ DEVICE_ATTR(direction, 0644,
-		gpio_direction_show, gpio_direction_store);
-
-static ssize_t gpio_value_show(struct device *dev,
+static ssize_t value_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else
-		status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
+	status = sprintf(buf, "%d\n", gpiod_get_value_cansleep(desc));
+
+	mutex_unlock(&data->mutex);
 
-	mutex_unlock(&sysfs_lock);
 	return status;
 }
 
-static ssize_t gpio_value_store(struct device *dev,
+static ssize_t value_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else if (!test_bit(FLAG_IS_OUT, &desc->flags))
+	if (!test_bit(FLAG_IS_OUT, &desc->flags)) {
 		status = -EPERM;
-	else {
+	} else {
 		long		value;
 
 		status = kstrtol(buf, 0, &value);
@@ -124,172 +133,168 @@ static ssize_t gpio_value_store(struct device *dev,
 		}
 	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
-
-static DEVICE_ATTR(value, 0644,
-		gpio_value_show, gpio_value_store);
+static DEVICE_ATTR_RW(value);
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
 {
-	struct kernfs_node	*value_sd = priv;
+	struct gpiod_data *data = priv;
+
+	sysfs_notify_dirent(data->value_kn);
 
-	sysfs_notify_dirent(value_sd);
 	return IRQ_HANDLED;
 }
 
-static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
-		unsigned long gpio_flags)
+/* Caller holds gpiod-data mutex. */
+static int gpio_sysfs_request_irq(struct device *dev, unsigned char flags)
 {
-	struct kernfs_node	*value_sd;
+	struct gpiod_data	*data = dev_get_drvdata(dev);
+	struct gpio_desc	*desc = data->desc;
 	unsigned long		irq_flags;
-	int			ret, irq, id;
+	int			ret;
 
-	if ((desc->flags & GPIO_TRIGGER_MASK) == gpio_flags)
-		return 0;
-
-	irq = gpiod_to_irq(desc);
-	if (irq < 0)
+	data->irq = gpiod_to_irq(desc);
+	if (data->irq < 0)
 		return -EIO;
 
-	id = desc->flags >> ID_SHIFT;
-	value_sd = idr_find(&dirent_idr, id);
-	if (value_sd)
-		free_irq(irq, value_sd);
-
-	desc->flags &= ~GPIO_TRIGGER_MASK;
-
-	if (!gpio_flags) {
-		gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
-		ret = 0;
-		goto free_id;
-	}
+	data->value_kn = sysfs_get_dirent(dev->kobj.sd, "value");
+	if (!data->value_kn)
+		return -ENODEV;
 
 	irq_flags = IRQF_SHARED;
-	if (test_bit(FLAG_TRIG_FALL, &gpio_flags))
+	if (flags & GPIO_IRQF_TRIGGER_FALLING)
 		irq_flags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
 			IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING;
-	if (test_bit(FLAG_TRIG_RISE, &gpio_flags))
+	if (flags & GPIO_IRQF_TRIGGER_RISING)
 		irq_flags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
 			IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING;
 
-	if (!value_sd) {
-		value_sd = sysfs_get_dirent(dev->kobj.sd, "value");
-		if (!value_sd) {
-			ret = -ENODEV;
-			goto err_out;
-		}
-
-		ret = idr_alloc(&dirent_idr, value_sd, 1, 0, GFP_KERNEL);
-		if (ret < 0)
-			goto free_sd;
-		id = ret;
-
-		desc->flags &= GPIO_FLAGS_MASK;
-		desc->flags |= (unsigned long)id << ID_SHIFT;
-
-		if (desc->flags >> ID_SHIFT != id) {
-			ret = -ERANGE;
-			goto free_id;
-		}
-	}
+	/*
+	 * FIXME: This should be done in the irq_request_resources callback
+	 *        when the irq is requested, but a few drivers currently fail
+	 *        to do so.
+	 *
+	 *        Remove this redundant call (along with the corresponding
+	 *        unlock) when those drivers have been fixed.
+	 */
+	ret = gpiochip_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+	if (ret < 0)
+		goto err_put_kn;
 
-	ret = request_any_context_irq(irq, gpio_sysfs_irq, irq_flags,
-				"gpiolib", value_sd);
+	ret = request_any_context_irq(data->irq, gpio_sysfs_irq, irq_flags,
+				"gpiolib", data);
 	if (ret < 0)
-		goto free_id;
+		goto err_unlock;
 
-	ret = gpiochip_lock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
-	if (ret < 0) {
-		gpiod_warn(desc, "failed to flag the GPIO for IRQ\n");
-		goto free_id;
-	}
+	data->irq_flags = flags;
 
-	desc->flags |= gpio_flags;
 	return 0;
 
-free_id:
-	idr_remove(&dirent_idr, id);
-	desc->flags &= GPIO_FLAGS_MASK;
-free_sd:
-	if (value_sd)
-		sysfs_put(value_sd);
-err_out:
+err_unlock:
+	gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+err_put_kn:
+	sysfs_put(data->value_kn);
+
 	return ret;
 }
 
+/*
+ * Caller holds gpiod-data mutex (unless called after class-device
+ * deregistration).
+ */
+static void gpio_sysfs_free_irq(struct device *dev)
+{
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
+
+	data->irq_flags = 0;
+	free_irq(data->irq, data);
+	gpiochip_unlock_as_irq(desc->chip, gpio_chip_hwgpio(desc));
+	sysfs_put(data->value_kn);
+}
+
 static const struct {
 	const char *name;
-	unsigned long flags;
+	unsigned char flags;
 } trigger_types[] = {
 	{ "none",    0 },
-	{ "falling", BIT(FLAG_TRIG_FALL) },
-	{ "rising",  BIT(FLAG_TRIG_RISE) },
-	{ "both",    BIT(FLAG_TRIG_FALL) | BIT(FLAG_TRIG_RISE) },
+	{ "falling", GPIO_IRQF_TRIGGER_FALLING },
+	{ "rising",  GPIO_IRQF_TRIGGER_RISING },
+	{ "both",    GPIO_IRQF_TRIGGER_BOTH },
 };
 
-static ssize_t gpio_edge_show(struct device *dev,
+static ssize_t edge_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	const struct gpio_desc	*desc = dev_get_drvdata(dev);
-	ssize_t			status;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	ssize_t	status = 0;
+	int i;
 
-	mutex_lock(&sysfs_lock);
-
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else {
-		int i;
+	mutex_lock(&data->mutex);
 
-		status = 0;
-		for (i = 0; i < ARRAY_SIZE(trigger_types); i++)
-			if ((desc->flags & GPIO_TRIGGER_MASK)
-					== trigger_types[i].flags) {
-				status = sprintf(buf, "%s\n",
-						 trigger_types[i].name);
-				break;
-			}
+	for (i = 0; i < ARRAY_SIZE(trigger_types); i++) {
+		if (data->irq_flags == trigger_types[i].flags) {
+			status = sprintf(buf, "%s\n", trigger_types[i].name);
+			break;
+		}
 	}
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
+
 	return status;
 }
 
-static ssize_t gpio_edge_store(struct device *dev,
+static ssize_t edge_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
-	ssize_t			status;
-	int			i;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	unsigned char flags;
+	ssize_t	status = size;
+	int i;
 
-	for (i = 0; i < ARRAY_SIZE(trigger_types); i++)
+	for (i = 0; i < ARRAY_SIZE(trigger_types); i++) {
 		if (sysfs_streq(trigger_types[i].name, buf))
-			goto found;
-	return -EINVAL;
+			break;
+	}
 
-found:
-	mutex_lock(&sysfs_lock);
+	if (i == ARRAY_SIZE(trigger_types))
+		return -EINVAL;
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else {
-		status = gpio_setup_irq(desc, dev, trigger_types[i].flags);
+	flags = trigger_types[i].flags;
+
+	mutex_lock(&data->mutex);
+
+	if (flags == data->irq_flags) {
+		status = size;
+		goto out_unlock;
+	}
+
+	if (data->irq_flags)
+		gpio_sysfs_free_irq(dev);
+
+	if (flags) {
+		status = gpio_sysfs_request_irq(dev, flags);
 		if (!status)
 			status = size;
 	}
 
-	mutex_unlock(&sysfs_lock);
+out_unlock:
+	mutex_unlock(&data->mutex);
 
 	return status;
 }
+static DEVICE_ATTR_RW(edge);
 
-static DEVICE_ATTR(edge, 0644, gpio_edge_show, gpio_edge_store);
-
-static int sysfs_set_active_low(struct gpio_desc *desc, struct device *dev,
-				int value)
+/* Caller holds gpiod-data mutex. */
+static int gpio_sysfs_set_active_low(struct device *dev, int value)
 {
+	struct gpiod_data	*data = dev_get_drvdata(dev);
+	struct gpio_desc	*desc = data->desc;
 	int			status = 0;
+	unsigned int		flags = data->irq_flags;
 
 	if (!!test_bit(FLAG_ACTIVE_LOW, &desc->flags) == !!value)
 		return 0;
@@ -300,69 +305,59 @@ static int sysfs_set_active_low(struct gpio_desc *desc, struct device *dev,
 		clear_bit(FLAG_ACTIVE_LOW, &desc->flags);
 
 	/* reconfigure poll(2) support if enabled on one edge only */
-	if (dev != NULL && (!!test_bit(FLAG_TRIG_RISE, &desc->flags) ^
-				!!test_bit(FLAG_TRIG_FALL, &desc->flags))) {
-		unsigned long trigger_flags = desc->flags & GPIO_TRIGGER_MASK;
-
-		gpio_setup_irq(desc, dev, 0);
-		status = gpio_setup_irq(desc, dev, trigger_flags);
+	if (flags == GPIO_IRQF_TRIGGER_FALLING ||
+					flags == GPIO_IRQF_TRIGGER_RISING) {
+		gpio_sysfs_free_irq(dev);
+		status = gpio_sysfs_request_irq(dev, flags);
 	}
 
 	return status;
 }
 
-static ssize_t gpio_active_low_show(struct device *dev,
+static ssize_t active_low_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	const struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	ssize_t			status;
 
-	mutex_lock(&sysfs_lock);
+	mutex_lock(&data->mutex);
 
-	if (!test_bit(FLAG_EXPORT, &desc->flags))
-		status = -EIO;
-	else
-		status = sprintf(buf, "%d\n",
+	status = sprintf(buf, "%d\n",
 				!!test_bit(FLAG_ACTIVE_LOW, &desc->flags));
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
 
 	return status;
 }
 
-static ssize_t gpio_active_low_store(struct device *dev,
+static ssize_t active_low_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct gpio_desc	*desc = dev_get_drvdata(dev);
+	struct gpiod_data	*data = dev_get_drvdata(dev);
 	ssize_t			status;
+	long			value;
 
-	mutex_lock(&sysfs_lock);
-
-	if (!test_bit(FLAG_EXPORT, &desc->flags)) {
-		status = -EIO;
-	} else {
-		long		value;
+	mutex_lock(&data->mutex);
 
-		status = kstrtol(buf, 0, &value);
-		if (status == 0)
-			status = sysfs_set_active_low(desc, dev, value != 0);
-	}
+	status = kstrtol(buf, 0, &value);
+	if (status == 0)
+		status = gpio_sysfs_set_active_low(dev, value);
 
-	mutex_unlock(&sysfs_lock);
+	mutex_unlock(&data->mutex);
 
 	return status ? : size;
 }
-
-static DEVICE_ATTR(active_low, 0644,
-		gpio_active_low_show, gpio_active_low_store);
+static DEVICE_ATTR_RW(active_low);
 
 static umode_t gpio_is_visible(struct kobject *kobj, struct attribute *attr,
 			       int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
-	struct gpio_desc *desc = dev_get_drvdata(dev);
+	struct gpiod_data *data = dev_get_drvdata(dev);
+	struct gpio_desc *desc = data->desc;
 	umode_t mode = attr->mode;
-	bool show_direction = test_bit(FLAG_SYSFS_DIR, &desc->flags);
+	bool show_direction = data->direction_can_change;
 
 	if (attr == &dev_attr_direction.attr) {
 		if (!show_direction)
@@ -402,32 +397,32 @@ static const struct attribute_group *gpio_groups[] = {
  *   /ngpio ... matching gpio_chip.ngpio
  */
 
-static ssize_t chip_base_show(struct device *dev,
+static ssize_t base_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", chip->base);
 }
-static DEVICE_ATTR(base, 0444, chip_base_show, NULL);
+static DEVICE_ATTR_RO(base);
 
-static ssize_t chip_label_show(struct device *dev,
+static ssize_t label_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", chip->label ? : "");
 }
-static DEVICE_ATTR(label, 0444, chip_label_show, NULL);
+static DEVICE_ATTR_RO(label);
 
-static ssize_t chip_ngpio_show(struct device *dev,
+static ssize_t ngpio_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	const struct gpio_chip	*chip = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", chip->ngpio);
 }
-static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL);
+static DEVICE_ATTR_RO(ngpio);
 
 static struct attribute *gpiochip_attrs[] = {
 	&dev_attr_base.attr,
@@ -551,6 +546,8 @@ static struct class gpio_class = {
  */
 int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 {
+	struct gpio_chip	*chip;
+	struct gpiod_data	*data;
 	unsigned long		flags;
 	int			status;
 	const char		*ioname = NULL;
@@ -568,8 +565,16 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 		return -EINVAL;
 	}
 
+	chip = desc->chip;
+
 	mutex_lock(&sysfs_lock);
 
+	/* check if chip is being removed */
+	if (!chip || !chip->cdev) {
+		status = -ENODEV;
+		goto err_unlock;
+	}
+
 	spin_lock_irqsave(&gpio_lock, flags);
 	if (!test_bit(FLAG_REQUESTED, &desc->flags) ||
 	     test_bit(FLAG_EXPORT, &desc->flags)) {
@@ -579,43 +584,54 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change)
 				test_bit(FLAG_REQUESTED, &desc->flags),
 				test_bit(FLAG_EXPORT, &desc->flags));
 		status = -EPERM;
-		goto fail_unlock;
+		goto err_unlock;
 	}
+	spin_unlock_irqrestore(&gpio_lock, flags);
 
-	if (desc->chip->direction_input && desc->chip->direction_output &&
-			direction_may_change) {
-		set_bit(FLAG_SYSFS_DIR, &desc->flags);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		status = -ENOMEM;
+		goto err_unlock;
 	}
 
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	data->desc = desc;
+	mutex_init(&data->mutex);
+	if (chip->direction_input && chip->direction_output)
+		data->direction_can_change = direction_may_change;
+	else
+		data->direction_can_change = false;
 
 	offset = gpio_chip_hwgpio(desc);
-	if (desc->chip->names && desc->chip->names[offset])
-		ioname = desc->chip->names[offset];
+	if (chip->names && chip->names[offset])
+		ioname = chip->names[offset];
 
-	dev = device_create_with_groups(&gpio_class, desc->chip->dev,
-					MKDEV(0, 0), desc, gpio_groups,
+	dev = device_create_with_groups(&gpio_class, chip->dev,
+					MKDEV(0, 0), data, gpio_groups,
 					ioname ? ioname : "gpio%u",
 					desc_to_gpio(desc));
 	if (IS_ERR(dev)) {
 		status = PTR_ERR(dev);
-		goto fail_unlock;
+		goto err_free_data;
 	}
 
 	set_bit(FLAG_EXPORT, &desc->flags);
 	mutex_unlock(&sysfs_lock);
 	return 0;
 
-fail_unlock:
+err_free_data:
+	kfree(data);
+err_unlock:
 	mutex_unlock(&sysfs_lock);
 	gpiod_dbg(desc, "%s: status %d\n", __func__, status);
 	return status;
 }
 EXPORT_SYMBOL_GPL(gpiod_export);
 
-static int match_export(struct device *dev, const void *data)
+static int match_export(struct device *dev, const void *desc)
 {
-	return dev_get_drvdata(dev) == data;
+	struct gpiod_data *data = dev_get_drvdata(dev);
+
+	return data->desc == desc;
 }
 
 /**
@@ -632,82 +648,26 @@ static int match_export(struct device *dev, const void *data)
 int gpiod_export_link(struct device *dev, const char *name,
 		      struct gpio_desc *desc)
 {
-	int			status = -EINVAL;
+	struct device *cdev;
+	int ret;
 
 	if (!desc) {
 		pr_warn("%s: invalid GPIO\n", __func__);
 		return -EINVAL;
 	}
 
-	mutex_lock(&sysfs_lock);
+	cdev = class_find_device(&gpio_class, NULL, desc, match_export);
+	if (!cdev)
+		return -ENODEV;
 
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
-		struct device *tdev;
+	ret = sysfs_create_link(&dev->kobj, &cdev->kobj, name);
+	put_device(cdev);
 
-		tdev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (tdev != NULL) {
-			status = sysfs_create_link(&dev->kobj, &tdev->kobj,
-						name);
-			put_device(tdev);
-		} else {
-			status = -ENODEV;
-		}
-	}
-
-	mutex_unlock(&sysfs_lock);
-
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
-
-	return status;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(gpiod_export_link);
 
 /**
- * gpiod_sysfs_set_active_low - set the polarity of gpio sysfs value
- * @gpio: gpio to change
- * @value: non-zero to use active low, i.e. inverted values
- *
- * Set the polarity of /sys/class/gpio/gpioN/value sysfs attribute.
- * The GPIO does not have to be exported yet.  If poll(2) support has
- * been enabled for either rising or falling edge, it will be
- * reconfigured to follow the new polarity.
- *
- * Returns zero on success, else an error.
- */
-int gpiod_sysfs_set_active_low(struct gpio_desc *desc, int value)
-{
-	struct device		*dev = NULL;
-	int			status = -EINVAL;
-
-	if (!desc) {
-		pr_warn("%s: invalid GPIO\n", __func__);
-		return -EINVAL;
-	}
-
-	mutex_lock(&sysfs_lock);
-
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
-		dev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (dev == NULL) {
-			status = -ENODEV;
-			goto unlock;
-		}
-	}
-
-	status = sysfs_set_active_low(desc, dev, value);
-	put_device(dev);
-unlock:
-	mutex_unlock(&sysfs_lock);
-
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
-
-	return status;
-}
-EXPORT_SYMBOL_GPL(gpiod_sysfs_set_active_low);
-
-/**
  * gpiod_unexport - reverse effect of gpio_export()
  * @gpio: gpio to make unavailable
  *
@@ -715,8 +675,8 @@ EXPORT_SYMBOL_GPL(gpiod_sysfs_set_active_low);
  */
 void gpiod_unexport(struct gpio_desc *desc)
 {
-	int			status = 0;
-	struct device		*dev = NULL;
+	struct gpiod_data *data;
+	struct device *dev;
 
 	if (!desc) {
 		pr_warn("%s: invalid GPIO\n", __func__);
@@ -725,78 +685,85 @@ void gpiod_unexport(struct gpio_desc *desc)
 
 	mutex_lock(&sysfs_lock);
 
-	if (test_bit(FLAG_EXPORT, &desc->flags)) {
+	if (!test_bit(FLAG_EXPORT, &desc->flags))
+		goto err_unlock;
 
-		dev = class_find_device(&gpio_class, NULL, desc, match_export);
-		if (dev) {
-			gpio_setup_irq(desc, dev, 0);
-			clear_bit(FLAG_SYSFS_DIR, &desc->flags);
-			clear_bit(FLAG_EXPORT, &desc->flags);
-		} else
-			status = -ENODEV;
-	}
+	dev = class_find_device(&gpio_class, NULL, desc, match_export);
+	if (!dev)
+		goto err_unlock;
+
+	data = dev_get_drvdata(dev);
+
+	clear_bit(FLAG_EXPORT, &desc->flags);
+
+	device_unregister(dev);
+
+	/*
+	 * Release irq after deregistration to prevent race with edge_store.
+	 */
+	if (data->irq_flags)
+		gpio_sysfs_free_irq(dev);
 
 	mutex_unlock(&sysfs_lock);
 
-	if (dev) {
-		device_unregister(dev);
-		put_device(dev);
-	}
+	put_device(dev);
+	kfree(data);
 
-	if (status)
-		gpiod_dbg(desc, "%s: status %d\n", __func__, status);
+	return;
+
+err_unlock:
+	mutex_unlock(&sysfs_lock);
 }
 EXPORT_SYMBOL_GPL(gpiod_unexport);
 
-int gpiochip_export(struct gpio_chip *chip)
+int gpiochip_sysfs_register(struct gpio_chip *chip)
 {
-	int		status;
 	struct device	*dev;
 
-	/* Many systems register gpio chips for SOC support very early,
+	/*
+	 * Many systems add gpio chips for SOC support very early,
 	 * before driver model support is available.  In those cases we
-	 * export this later, in gpiolib_sysfs_init() ... here we just
+	 * register later, in gpiolib_sysfs_init() ... here we just
 	 * verify that _some_ field of gpio_class got initialized.
 	 */
 	if (!gpio_class.p)
 		return 0;
 
 	/* use chip->base for the ID; it's already known to be unique */
-	mutex_lock(&sysfs_lock);
 	dev = device_create_with_groups(&gpio_class, chip->dev, MKDEV(0, 0),
 					chip, gpiochip_groups,
 					"gpiochip%d", chip->base);
 	if (IS_ERR(dev))
-		status = PTR_ERR(dev);
-	else
-		status = 0;
-	chip->exported = (status == 0);
-	mutex_unlock(&sysfs_lock);
+		return PTR_ERR(dev);
 
-	if (status)
-		chip_dbg(chip, "%s: status %d\n", __func__, status);
+	mutex_lock(&sysfs_lock);
+	chip->cdev = dev;
+	mutex_unlock(&sysfs_lock);
 
-	return status;
+	return 0;
 }
 
-void gpiochip_unexport(struct gpio_chip *chip)
+void gpiochip_sysfs_unregister(struct gpio_chip *chip)
 {
-	int			status;
-	struct device		*dev;
+	struct gpio_desc *desc;
+	unsigned int i;
+
+	if (!chip->cdev)
+		return;
 
+	device_unregister(chip->cdev);
+
+	/* prevent further gpiod exports */
 	mutex_lock(&sysfs_lock);
-	dev = class_find_device(&gpio_class, NULL, chip, match_export);
-	if (dev) {
-		put_device(dev);
-		device_unregister(dev);
-		chip->exported = false;
-		status = 0;
-	} else
-		status = -ENODEV;
+	chip->cdev = NULL;
 	mutex_unlock(&sysfs_lock);
 
-	if (status)
-		chip_dbg(chip, "%s: status %d\n", __func__, status);
+	/* unregister gpiod class devices owned by sysfs */
+	for (i = 0; i < chip->ngpio; i++) {
+		desc = &chip->desc[i];
+		if (test_and_clear_bit(FLAG_SYSFS, &desc->flags))
+			gpiod_free(desc);
+	}
 }
 
 static int __init gpiolib_sysfs_init(void)
@@ -817,19 +784,20 @@ static int __init gpiolib_sysfs_init(void)
 	 */
 	spin_lock_irqsave(&gpio_lock, flags);
 	list_for_each_entry(chip, &gpio_chips, list) {
-		if (chip->exported)
+		if (chip->cdev)
 			continue;
 
 		/*
-		 * TODO we yield gpio_lock here because gpiochip_export()
-		 * acquires a mutex. This is unsafe and needs to be fixed.
+		 * TODO we yield gpio_lock here because
+		 * gpiochip_sysfs_register() acquires a mutex. This is unsafe
+		 * and needs to be fixed.
 		 *
 		 * Also it would be nice to use gpiochip_find() here so we
 		 * can keep gpio_chips local to gpiolib.c, but the yield of
 		 * gpio_lock prevents us from doing this.
 		 */
 		spin_unlock_irqrestore(&gpio_lock, flags);
-		status = gpiochip_export(chip);
+		status = gpiochip_sysfs_register(chip);
 		spin_lock_irqsave(&gpio_lock, flags);
 	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 59eaa23767d8..be42ab368a80 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -53,6 +53,11 @@ static DEFINE_MUTEX(gpio_lookup_lock);
 static LIST_HEAD(gpio_lookup_list);
 LIST_HEAD(gpio_chips);
 
+
+static void gpiochip_free_hogs(struct gpio_chip *chip);
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+
+
 static inline void desc_set_label(struct gpio_desc *d, const char *label)
 {
 	d->label = label;
@@ -285,7 +290,7 @@ int gpiochip_add(struct gpio_chip *chip)
 	of_gpiochip_add(chip);
 	acpi_gpiochip_add(chip);
 
-	status = gpiochip_export(chip);
+	status = gpiochip_sysfs_register(chip);
 	if (status)
 		goto err_remove_chip;
 
@@ -297,6 +302,7 @@ int gpiochip_add(struct gpio_chip *chip)
 
 err_remove_chip:
 	acpi_gpiochip_remove(chip);
+	gpiochip_free_hogs(chip);
 	of_gpiochip_remove(chip);
 	spin_lock_irqsave(&gpio_lock, flags);
 	list_del(&chip->list);
@@ -313,10 +319,6 @@ err_free_descs:
 }
 EXPORT_SYMBOL_GPL(gpiochip_add);
 
-/* Forward-declaration */
-static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
-static void gpiochip_free_hogs(struct gpio_chip *chip);
-
 /**
  * gpiochip_remove() - unregister a gpio_chip
  * @chip: the chip to unregister
@@ -325,10 +327,12 @@ static void gpiochip_free_hogs(struct gpio_chip *chip);
  */
 void gpiochip_remove(struct gpio_chip *chip)
 {
+	struct gpio_desc *desc;
 	unsigned long	flags;
 	unsigned	id;
+	bool		requested = false;
 
-	gpiochip_unexport(chip);
+	gpiochip_sysfs_unregister(chip);
 
 	gpiochip_irqchip_remove(chip);
 
@@ -339,15 +343,17 @@ void gpiochip_remove(struct gpio_chip *chip)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 	for (id = 0; id < chip->ngpio; id++) {
-		if (test_bit(FLAG_REQUESTED, &chip->desc[id].flags))
-			dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
+		desc = &chip->desc[id];
+		desc->chip = NULL;
+		if (test_bit(FLAG_REQUESTED, &desc->flags))
+			requested = true;
 	}
-	for (id = 0; id < chip->ngpio; id++)
-		chip->desc[id].chip = NULL;
-
 	list_del(&chip->list);
 	spin_unlock_irqrestore(&gpio_lock, flags);
 
+	if (requested)
+		dev_crit(chip->dev, "REMOVING GPIOCHIP WITH GPIOS STILL REQUESTED\n");
+
 	kfree(chip->desc);
 	chip->desc = NULL;
 }
@@ -439,6 +445,8 @@ void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip,
 		 */
 		irq_set_handler_data(parent_irq, gpiochip);
 		irq_set_chained_handler(parent_irq, parent_handler);
+
+		gpiochip->irq_parent = parent_irq;
 	}
 
 	/* Set the parent IRQ for all affected IRQs */
@@ -547,6 +555,11 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
 
 	acpi_gpiochip_free_interrupts(gpiochip);
 
+	if (gpiochip->irq_parent) {
+		irq_set_chained_handler(gpiochip->irq_parent, NULL);
+		irq_set_handler_data(gpiochip->irq_parent, NULL);
+	}
+
 	/* Remove all IRQ mappings and delete the domain */
 	if (gpiochip->irqdomain) {
 		for (offset = 0; offset < gpiochip->ngpio; offset++)
@@ -606,7 +619,7 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 	of_node = gpiochip->dev->of_node;
 #ifdef CONFIG_OF_GPIO
 	/*
-	 * If the gpiochip has an assigned OF node this takes precendence
+	 * If the gpiochip has an assigned OF node this takes precedence
 	 * FIXME: get rid of this and use gpiochip->dev->of_node everywhere
 	 */
 	if (gpiochip->of_node)
@@ -1209,7 +1222,7 @@ EXPORT_SYMBOL_GPL(gpiod_get_value);
 /*
  *  _gpio_set_open_drain_value() - Set the open drain gpio's value.
  * @desc: gpio descriptor whose state need to be set.
- * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ * @value: Non-zero for setting it HIGH otherwise it will set to LOW.
  */
 static void _gpio_set_open_drain_value(struct gpio_desc *desc, bool value)
 {
@@ -1236,7 +1249,7 @@ static void _gpio_set_open_drain_value(struct gpio_desc *desc, bool value)
 /*
  *  _gpio_set_open_source_value() - Set the open source gpio's value.
  * @desc: gpio descriptor whose state need to be set.
- * @value: Non-zero for setting it HIGH otherise it will set to LOW.
+ * @value: Non-zero for setting it HIGH otherwise it will set to LOW.
  */
 static void _gpio_set_open_source_value(struct gpio_desc *desc, bool value)
 {
@@ -1298,17 +1311,16 @@ static void gpio_chip_set_multiple(struct gpio_chip *chip,
 				continue;
 			}
 			/* set outputs if the corresponding mask bit is set */
-			if (__test_and_clear_bit(i, mask)) {
+			if (__test_and_clear_bit(i, mask))
 				chip->set(chip, i, test_bit(i, bits));
-			}
 		}
 	}
 }
 
-static void gpiod_set_array_priv(bool raw, bool can_sleep,
-				 unsigned int array_size,
-				 struct gpio_desc **desc_array,
-				 int *value_array)
+static void gpiod_set_array_value_priv(bool raw, bool can_sleep,
+				       unsigned int array_size,
+				       struct gpio_desc **desc_array,
+				       int *value_array)
 {
 	int i = 0;
 
@@ -1318,9 +1330,9 @@ static void gpiod_set_array_priv(bool raw, bool can_sleep,
 		unsigned long bits[BITS_TO_LONGS(chip->ngpio)];
 		int count = 0;
 
-		if (!can_sleep) {
+		if (!can_sleep)
 			WARN_ON(chip->can_sleep);
-		}
+
 		memset(mask, 0, sizeof(mask));
 		do {
 			struct gpio_desc *desc = desc_array[i];
@@ -1335,24 +1347,22 @@ static void gpiod_set_array_priv(bool raw, bool can_sleep,
 			 * open drain and open source outputs are set individually
 			 */
 			if (test_bit(FLAG_OPEN_DRAIN, &desc->flags)) {
-				_gpio_set_open_drain_value(desc,value);
+				_gpio_set_open_drain_value(desc, value);
 			} else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) {
 				_gpio_set_open_source_value(desc, value);
 			} else {
 				__set_bit(hwgpio, mask);
-				if (value) {
+				if (value)
 					__set_bit(hwgpio, bits);
-				} else {
+				else
 					__clear_bit(hwgpio, bits);
-				}
 				count++;
 			}
 			i++;
 		} while ((i < array_size) && (desc_array[i]->chip == chip));
 		/* push collected bits to outputs */
-		if (count != 0) {
+		if (count != 0)
 			gpio_chip_set_multiple(chip, mask, bits);
-		}
 	}
 }
 
@@ -1401,7 +1411,7 @@ void gpiod_set_value(struct gpio_desc *desc, int value)
 EXPORT_SYMBOL_GPL(gpiod_set_value);
 
 /**
- * gpiod_set_raw_array() - assign values to an array of GPIOs
+ * gpiod_set_raw_array_value() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1412,17 +1422,18 @@ EXPORT_SYMBOL_GPL(gpiod_set_value);
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
  */
-void gpiod_set_raw_array(unsigned int array_size,
+void gpiod_set_raw_array_value(unsigned int array_size,
 			 struct gpio_desc **desc_array, int *value_array)
 {
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(true, false, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(true, false, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_raw_array);
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value);
 
 /**
- * gpiod_set_array() - assign values to an array of GPIOs
+ * gpiod_set_array_value() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1433,14 +1444,15 @@ EXPORT_SYMBOL_GPL(gpiod_set_raw_array);
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
  */
-void gpiod_set_array(unsigned int array_size,
-		     struct gpio_desc **desc_array, int *value_array)
+void gpiod_set_array_value(unsigned int array_size,
+			   struct gpio_desc **desc_array, int *value_array)
 {
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(false, false, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(false, false, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_array);
+EXPORT_SYMBOL_GPL(gpiod_set_array_value);
 
 /**
  * gpiod_cansleep() - report whether gpio value access may sleep
@@ -1602,7 +1614,7 @@ void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
 
 /**
- * gpiod_set_raw_array_cansleep() - assign values to an array of GPIOs
+ * gpiod_set_raw_array_value_cansleep() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1612,19 +1624,20 @@ EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep);
  *
  * This function is to be called from contexts that can sleep.
  */
-void gpiod_set_raw_array_cansleep(unsigned int array_size,
-				  struct gpio_desc **desc_array,
-				  int *value_array)
+void gpiod_set_raw_array_value_cansleep(unsigned int array_size,
+					struct gpio_desc **desc_array,
+					int *value_array)
 {
 	might_sleep_if(extra_checks);
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(true, true, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(true, true, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_raw_array_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value_cansleep);
 
 /**
- * gpiod_set_array_cansleep() - assign values to an array of GPIOs
+ * gpiod_set_array_value_cansleep() - assign values to an array of GPIOs
  * @array_size: number of elements in the descriptor / value arrays
  * @desc_array: array of GPIO descriptors whose values will be assigned
  * @value_array: array of values to assign
@@ -1634,16 +1647,17 @@ EXPORT_SYMBOL_GPL(gpiod_set_raw_array_cansleep);
  *
  * This function is to be called from contexts that can sleep.
  */
-void gpiod_set_array_cansleep(unsigned int array_size,
-			      struct gpio_desc **desc_array,
-			      int *value_array)
+void gpiod_set_array_value_cansleep(unsigned int array_size,
+				    struct gpio_desc **desc_array,
+				    int *value_array)
 {
 	might_sleep_if(extra_checks);
 	if (!desc_array)
 		return;
-	gpiod_set_array_priv(false, true, array_size, desc_array, value_array);
+	gpiod_set_array_value_priv(false, true, array_size, desc_array,
+				   value_array);
 }
-EXPORT_SYMBOL_GPL(gpiod_set_array_cansleep);
+EXPORT_SYMBOL_GPL(gpiod_set_array_value_cansleep);
 
 /**
  * gpiod_add_lookup_table() - register GPIO device consumers
@@ -1878,7 +1892,7 @@ EXPORT_SYMBOL_GPL(gpiod_count);
  *
  * Return the GPIO descriptor corresponding to the function con_id of device
  * dev, -ENOENT if no GPIO has been assigned to the requested function, or
- * another IS_ERR() code if an error occured while trying to acquire the GPIO.
+ * another IS_ERR() code if an error occurred while trying to acquire the GPIO.
  */
 struct gpio_desc *__must_check __gpiod_get(struct device *dev, const char *con_id,
 					 enum gpiod_flags flags)
@@ -1958,7 +1972,7 @@ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id,
  *
  * Return a valid GPIO descriptor, -ENOENT if no GPIO has been assigned to the
  * requested function and/or index, or another IS_ERR() code if an error
- * occured while trying to acquire the GPIO.
+ * occurred while trying to acquire the GPIO.
  */
 struct gpio_desc *__must_check __gpiod_get_index(struct device *dev,
 					       const char *con_id,
@@ -2116,13 +2130,15 @@ int gpiod_hog(struct gpio_desc *desc, const char *name,
 
 	local_desc = gpiochip_request_own_desc(chip, hwnum, name);
 	if (IS_ERR(local_desc)) {
-		pr_debug("requesting own GPIO %s failed\n", name);
+		pr_err("requesting hog GPIO %s (chip %s, offset %d) failed\n",
+		       name, chip->label, hwnum);
 		return PTR_ERR(local_desc);
 	}
 
 	status = gpiod_configure_flags(desc, name, lflags, dflags);
 	if (status < 0) {
-		pr_debug("setup of GPIO %s failed\n", name);
+		pr_err("setup of hog GPIO %s (chip %s, offset %d) failed\n",
+		       name, chip->label, hwnum);
 		gpiochip_free_own_desc(desc);
 		return status;
 	}
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 594b1798c0e7..bf343004b008 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -83,20 +83,12 @@ struct gpio_desc {
 #define FLAG_IS_OUT	1
 #define FLAG_EXPORT	2	/* protected by sysfs_lock */
 #define FLAG_SYSFS	3	/* exported via /sys/class/gpio/control */
-#define FLAG_TRIG_FALL	4	/* trigger on falling edge */
-#define FLAG_TRIG_RISE	5	/* trigger on rising edge */
 #define FLAG_ACTIVE_LOW	6	/* value has active low */
 #define FLAG_OPEN_DRAIN	7	/* Gpio is open drain type */
 #define FLAG_OPEN_SOURCE 8	/* Gpio is open source type */
 #define FLAG_USED_AS_IRQ 9	/* GPIO is connected to an IRQ */
-#define FLAG_SYSFS_DIR	10	/* show sysfs direction attribute */
 #define FLAG_IS_HOGGED	11	/* GPIO is hogged */
 
-#define ID_SHIFT	16	/* add new flags before this one */
-
-#define GPIO_FLAGS_MASK		((1 << ID_SHIFT) - 1)
-#define GPIO_TRIGGER_MASK	(BIT(FLAG_TRIG_FALL) | BIT(FLAG_TRIG_RISE))
-
 	const char		*label;
 };
 
@@ -151,17 +143,17 @@ static int __maybe_unused gpio_chip_hwgpio(const struct gpio_desc *desc)
 
 #ifdef CONFIG_GPIO_SYSFS
 
-int gpiochip_export(struct gpio_chip *chip);
-void gpiochip_unexport(struct gpio_chip *chip);
+int gpiochip_sysfs_register(struct gpio_chip *chip);
+void gpiochip_sysfs_unregister(struct gpio_chip *chip);
 
 #else
 
-static inline int gpiochip_export(struct gpio_chip *chip)
+static inline int gpiochip_sysfs_register(struct gpio_chip *chip)
 {
 	return 0;
 }
 
-static inline void gpiochip_unexport(struct gpio_chip *chip)
+static inline void gpiochip_sysfs_unregister(struct gpio_chip *chip)
 {
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 69af73f15310..596ee5cd3b84 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -430,9 +430,10 @@ static int unregister_process_nocpsch(struct device_queue_manager *dqm,
 
 	BUG_ON(!dqm || !qpd);
 
-	BUG_ON(!list_empty(&qpd->queues_list));
+	pr_debug("In func %s\n", __func__);
 
-	pr_debug("kfd: In func %s\n", __func__);
+	pr_debug("qpd->queues_list is %s\n",
+			list_empty(&qpd->queues_list) ? "empty" : "not empty");
 
 	retval = 0;
 	mutex_lock(&dqm->lock);
@@ -882,6 +883,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		return -ENOMEM;
 	}
 
+	init_sdma_vm(dqm, q, qpd);
+
 	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval != 0)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 661c6605d31b..c25728bc388a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -684,8 +684,6 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.cpu_core_id_base);
 	sysfs_show_32bit_prop(buffer, "simd_id_base",
 			dev->node_props.simd_id_base);
-	sysfs_show_32bit_prop(buffer, "capability",
-			dev->node_props.capability);
 	sysfs_show_32bit_prop(buffer, "max_waves_per_simd",
 			dev->node_props.max_waves_per_simd);
 	sysfs_show_32bit_prop(buffer, "lds_size_in_kb",
@@ -728,14 +726,16 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 		sysfs_show_32bit_prop(buffer, "max_engine_clk_fcompute",
 			dev->gpu->kfd2kgd->get_max_engine_clock_in_mhz(
 					dev->gpu->kgd));
+
 		sysfs_show_64bit_prop(buffer, "local_mem_size",
-			dev->gpu->kfd2kgd->get_vmem_size(
-					dev->gpu->kgd));
+				(unsigned long long int) 0);
 
 		sysfs_show_32bit_prop(buffer, "fw_version",
 			dev->gpu->kfd2kgd->get_fw_version(
 						dev->gpu->kgd,
 						KGD_ENGINE_MEC1));
+		sysfs_show_32bit_prop(buffer, "capability",
+				dev->node_props.capability);
 	}
 
 	return sysfs_show_32bit_prop(buffer, "max_engine_clk_ccompute",
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 266dcd6cdf3b..0a957828b3bd 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -36,9 +36,6 @@
 
 #include <linux/pci.h>
 #include <linux/export.h>
-#ifdef CONFIG_X86
-#include <asm/mtrr.h>
-#endif
 
 static int drm_version(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
@@ -197,16 +194,7 @@ static int drm_getmap(struct drm_device *dev, void *data,
 	map->type = r_list->map->type;
 	map->flags = r_list->map->flags;
 	map->handle = (void *)(unsigned long) r_list->user_token;
-
-#ifdef CONFIG_X86
-	/*
-	 * There appears to be exactly one user of the mtrr index: dritest.
-	 * It's easy enough to keep it working on non-PAT systems.
-	 */
-	map->mtrr = phys_wc_to_mtrr_index(r_list->map->mtrr);
-#else
-	map->mtrr = -1;
-#endif
+	map->mtrr = arch_phys_wc_index(r_list->map->mtrr);
 
 	mutex_unlock(&dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index c8a34476570a..af9662e58272 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -131,12 +131,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 
 	/* Reinitialize corresponding vblank timestamp if high-precision query
 	 * available. Skip this step if query unsupported or failed. Will
-	 * reinitialize delayed at next vblank interrupt in that case.
+	 * reinitialize delayed at next vblank interrupt in that case and
+	 * assign 0 for now, to mark the vblanktimestamp as invalid.
 	 */
-	if (rc) {
-		tslot = atomic_read(&vblank->count) + diff;
-		vblanktimestamp(dev, crtc, tslot) = t_vblank;
-	}
+	tslot = atomic_read(&vblank->count) + diff;
+	vblanktimestamp(dev, crtc, tslot) = rc ? t_vblank : (struct timeval) {0, 0};
 
 	smp_mb__before_atomic();
 	atomic_add(diff, &vblank->count);
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 40c1db9ad7c3..2f0ed11024eb 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -465,6 +465,9 @@ int drm_plane_helper_commit(struct drm_plane *plane,
 		if (!crtc[i])
 			continue;
 
+		if (crtc[i]->cursor == plane)
+			continue;
+
 		/* There's no other way to figure out whether the crtc is running. */
 		ret = drm_crtc_vblank_get(crtc[i]);
 		if (ret == 0) {
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index ffc305fc2076..eb7e61078a5b 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -217,7 +217,7 @@ static ssize_t status_store(struct device *device,
 
 	mutex_unlock(&dev->mode_config.mutex);
 
-	return ret;
+	return ret ? ret : count;
 }
 
 static ssize_t status_show(struct device *device,
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 1f7e33f59de6..6714e5b193ea 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -91,7 +91,7 @@ static void decon_wait_for_vblank(struct exynos_drm_crtc *crtc)
 
 static void decon_clear_channel(struct decon_context *ctx)
 {
-	int win, ch_enabled = 0;
+	unsigned int win, ch_enabled = 0;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -710,7 +710,7 @@ static void decon_dpms(struct exynos_drm_crtc *crtc, int mode)
 	}
 }
 
-static struct exynos_drm_crtc_ops decon_crtc_ops = {
+static const struct exynos_drm_crtc_ops decon_crtc_ops = {
 	.dpms = decon_dpms,
 	.mode_fixup = decon_mode_fixup,
 	.commit = decon_commit,
diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c
index 1dbfba58f909..30feb7d06624 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_core.c
+++ b/drivers/gpu/drm/exynos/exynos_dp_core.c
@@ -32,7 +32,6 @@
 #include <drm/bridge/ptn3460.h>
 
 #include "exynos_dp_core.h"
-#include "exynos_drm_fimd.h"
 
 #define ctx_from_connector(c)	container_of(c, struct exynos_dp_device, \
 					connector)
@@ -196,7 +195,7 @@ static int exynos_dp_read_edid(struct exynos_dp_device *dp)
 		}
 	}
 
-	dev_err(dp->dev, "EDID Read success!\n");
+	dev_dbg(dp->dev, "EDID Read success!\n");
 	return 0;
 }
 
@@ -1066,6 +1065,8 @@ static void exynos_dp_phy_exit(struct exynos_dp_device *dp)
 
 static void exynos_dp_poweron(struct exynos_dp_device *dp)
 {
+	struct exynos_drm_crtc *crtc = dp_to_crtc(dp);
+
 	if (dp->dpms_mode == DRM_MODE_DPMS_ON)
 		return;
 
@@ -1076,7 +1077,8 @@ static void exynos_dp_poweron(struct exynos_dp_device *dp)
 		}
 	}
 
-	fimd_dp_clock_enable(dp_to_crtc(dp), true);
+	if (crtc->ops->clock_enable)
+		crtc->ops->clock_enable(dp_to_crtc(dp), true);
 
 	clk_prepare_enable(dp->clock);
 	exynos_dp_phy_init(dp);
@@ -1087,6 +1089,8 @@ static void exynos_dp_poweron(struct exynos_dp_device *dp)
 
 static void exynos_dp_poweroff(struct exynos_dp_device *dp)
 {
+	struct exynos_drm_crtc *crtc = dp_to_crtc(dp);
+
 	if (dp->dpms_mode != DRM_MODE_DPMS_ON)
 		return;
 
@@ -1102,7 +1106,8 @@ static void exynos_dp_poweroff(struct exynos_dp_device *dp)
 	exynos_dp_phy_exit(dp);
 	clk_disable_unprepare(dp->clock);
 
-	fimd_dp_clock_enable(dp_to_crtc(dp), false);
+	if (crtc->ops->clock_enable)
+		crtc->ops->clock_enable(dp_to_crtc(dp), false);
 
 	if (dp->panel) {
 		if (drm_panel_unprepare(dp->panel))
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index eb49195cec5c..9006b947e03c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -238,11 +238,11 @@ static struct drm_crtc_funcs exynos_crtc_funcs = {
 };
 
 struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev,
-					       struct drm_plane *plane,
-					       int pipe,
-					       enum exynos_drm_output_type type,
-					       struct exynos_drm_crtc_ops *ops,
-					       void *ctx)
+					struct drm_plane *plane,
+					int pipe,
+					enum exynos_drm_output_type type,
+					const struct exynos_drm_crtc_ops *ops,
+					void *ctx)
 {
 	struct exynos_drm_crtc *exynos_crtc;
 	struct exynos_drm_private *private = drm_dev->dev_private;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index 0ecd8fc45cff..0f3aa70818e3 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -18,11 +18,11 @@
 #include "exynos_drm_drv.h"
 
 struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev,
-					       struct drm_plane *plane,
-					       int pipe,
-					       enum exynos_drm_output_type type,
-					       struct exynos_drm_crtc_ops *ops,
-					       void *context);
+					struct drm_plane *plane,
+					int pipe,
+					enum exynos_drm_output_type type,
+					const struct exynos_drm_crtc_ops *ops,
+					void *context);
 int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int pipe);
 void exynos_drm_crtc_disable_vblank(struct drm_device *dev, int pipe);
 void exynos_drm_crtc_finish_pageflip(struct drm_device *dev, int pipe);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index e12ecb5d5d9a..29e3fb78c615 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -71,13 +71,6 @@ enum exynos_drm_output_type {
  * @dma_addr: array of bus(accessed by dma) address to the memory region
  *	      allocated for a overlay.
  * @zpos: order of overlay layer(z position).
- * @index_color: if using color key feature then this value would be used
- *			as index color.
- * @default_win: a window to be enabled.
- * @color_key: color key on or off.
- * @local_path: in case of lcd type, local path mode on or off.
- * @transparency: transparency on or off.
- * @activated: activated or not.
  * @enabled: enabled or not.
  * @resume: to resume or not.
  *
@@ -108,13 +101,7 @@ struct exynos_drm_plane {
 	uint32_t pixel_format;
 	dma_addr_t dma_addr[MAX_FB_BUFFER];
 	unsigned int zpos;
-	unsigned int index_color;
 
-	bool default_win:1;
-	bool color_key:1;
-	bool local_path:1;
-	bool transparency:1;
-	bool activated:1;
 	bool enabled:1;
 	bool resume:1;
 };
@@ -181,6 +168,10 @@ struct exynos_drm_display {
  * @win_disable: disable hardware specific overlay.
  * @te_handler: trigger to transfer video image at the tearing effect
  *	synchronization signal if there is a page flip request.
+ * @clock_enable: optional function enabling/disabling display domain clock,
+ *	called from exynos-dp driver before powering up (with
+ *	'enable' argument as true) and after powering down (with
+ *	'enable' as false).
  */
 struct exynos_drm_crtc;
 struct exynos_drm_crtc_ops {
@@ -195,6 +186,7 @@ struct exynos_drm_crtc_ops {
 	void (*win_commit)(struct exynos_drm_crtc *crtc, unsigned int zpos);
 	void (*win_disable)(struct exynos_drm_crtc *crtc, unsigned int zpos);
 	void (*te_handler)(struct exynos_drm_crtc *crtc);
+	void (*clock_enable)(struct exynos_drm_crtc *crtc, bool enable);
 };
 
 /*
@@ -221,7 +213,7 @@ struct exynos_drm_crtc {
 	unsigned int			dpms;
 	wait_queue_head_t		pending_flip_queue;
 	struct drm_pending_vblank_event	*event;
-	struct exynos_drm_crtc_ops	*ops;
+	const struct exynos_drm_crtc_ops	*ops;
 	void				*ctx;
 };
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 929cb03a8eab..142eb4e3f59e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -171,43 +171,6 @@ exynos_drm_framebuffer_init(struct drm_device *dev,
 	return &exynos_fb->fb;
 }
 
-static u32 exynos_drm_format_num_buffers(struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	unsigned int cnt = 0;
-
-	if (mode_cmd->pixel_format != DRM_FORMAT_NV12)
-		return drm_format_num_planes(mode_cmd->pixel_format);
-
-	while (cnt != MAX_FB_BUFFER) {
-		if (!mode_cmd->handles[cnt])
-			break;
-		cnt++;
-	}
-
-	/*
-	 * check if NV12 or NV12M.
-	 *
-	 * NV12
-	 * handles[0] = base1, offsets[0] = 0
-	 * handles[1] = base1, offsets[1] = Y_size
-	 *
-	 * NV12M
-	 * handles[0] = base1, offsets[0] = 0
-	 * handles[1] = base2, offsets[1] = 0
-	 */
-	if (cnt == 2) {
-		/*
-		 * in case of NV12 format, offsets[1] is not 0 and
-		 * handles[0] is same as handles[1].
-		 */
-		if (mode_cmd->offsets[1] &&
-			mode_cmd->handles[0] == mode_cmd->handles[1])
-			cnt = 1;
-	}
-
-	return cnt;
-}
-
 static struct drm_framebuffer *
 exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		      struct drm_mode_fb_cmd2 *mode_cmd)
@@ -230,7 +193,7 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 
 	drm_helper_mode_fill_fb_struct(&exynos_fb->fb, mode_cmd);
 	exynos_fb->exynos_gem_obj[0] = to_exynos_gem_obj(obj);
-	exynos_fb->buf_cnt = exynos_drm_format_num_buffers(mode_cmd);
+	exynos_fb->buf_cnt = drm_format_num_planes(mode_cmd->pixel_format);
 
 	DRM_DEBUG_KMS("buf_cnt = %d\n", exynos_fb->buf_cnt);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 9819fa6a9e2a..a0edab833148 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -33,7 +33,6 @@
 #include "exynos_drm_crtc.h"
 #include "exynos_drm_plane.h"
 #include "exynos_drm_iommu.h"
-#include "exynos_drm_fimd.h"
 
 /*
  * FIMD stands for Fully Interactive Mobile Display and
@@ -216,7 +215,7 @@ static void fimd_wait_for_vblank(struct exynos_drm_crtc *crtc)
 		DRM_DEBUG_KMS("vblank wait timed out.\n");
 }
 
-static void fimd_enable_video_output(struct fimd_context *ctx, int win,
+static void fimd_enable_video_output(struct fimd_context *ctx, unsigned int win,
 					bool enable)
 {
 	u32 val = readl(ctx->regs + WINCON(win));
@@ -229,7 +228,8 @@ static void fimd_enable_video_output(struct fimd_context *ctx, int win,
 	writel(val, ctx->regs + WINCON(win));
 }
 
-static void fimd_enable_shadow_channel_path(struct fimd_context *ctx, int win,
+static void fimd_enable_shadow_channel_path(struct fimd_context *ctx,
+						unsigned int win,
 						bool enable)
 {
 	u32 val = readl(ctx->regs + SHADOWCON);
@@ -244,7 +244,7 @@ static void fimd_enable_shadow_channel_path(struct fimd_context *ctx, int win,
 
 static void fimd_clear_channel(struct fimd_context *ctx)
 {
-	int win, ch_enabled = 0;
+	unsigned int win, ch_enabled = 0;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
@@ -946,7 +946,24 @@ static void fimd_te_handler(struct exynos_drm_crtc *crtc)
 		drm_handle_vblank(ctx->drm_dev, ctx->pipe);
 }
 
-static struct exynos_drm_crtc_ops fimd_crtc_ops = {
+static void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable)
+{
+	struct fimd_context *ctx = crtc->ctx;
+	u32 val;
+
+	/*
+	 * Only Exynos 5250, 5260, 5410 and 542x requires enabling DP/MIE
+	 * clock. On these SoCs the bootloader may enable it but any
+	 * power domain off/on will reset it to disable state.
+	 */
+	if (ctx->driver_data != &exynos5_fimd_driver_data)
+		return;
+
+	val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
+	writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON);
+}
+
+static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
 	.dpms = fimd_dpms,
 	.mode_fixup = fimd_mode_fixup,
 	.commit = fimd_commit,
@@ -956,6 +973,7 @@ static struct exynos_drm_crtc_ops fimd_crtc_ops = {
 	.win_commit = fimd_win_commit,
 	.win_disable = fimd_win_disable,
 	.te_handler = fimd_te_handler,
+	.clock_enable = fimd_dp_clock_enable,
 };
 
 static irqreturn_t fimd_irq_handler(int irq, void *dev_id)
@@ -1025,12 +1043,7 @@ static int fimd_bind(struct device *dev, struct device *master, void *data)
 	if (ctx->display)
 		exynos_drm_create_enc_conn(drm_dev, ctx->display);
 
-	ret = fimd_iommu_attach_devices(ctx, drm_dev);
-	if (ret)
-		return ret;
-
-	return 0;
-
+	return fimd_iommu_attach_devices(ctx, drm_dev);
 }
 
 static void fimd_unbind(struct device *dev, struct device *master,
@@ -1192,24 +1205,6 @@ static int fimd_remove(struct platform_device *pdev)
 	return 0;
 }
 
-void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable)
-{
-	struct fimd_context *ctx = crtc->ctx;
-	u32 val;
-
-	/*
-	 * Only Exynos 5250, 5260, 5410 and 542x requires enabling DP/MIE
-	 * clock. On these SoCs the bootloader may enable it but any
-	 * power domain off/on will reset it to disable state.
-	 */
-	if (ctx->driver_data != &exynos5_fimd_driver_data)
-		return;
-
-	val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
-	writel(DP_MIE_CLK_DP_ENABLE, ctx->regs + DP_MIE_CLKCON);
-}
-EXPORT_SYMBOL_GPL(fimd_dp_clock_enable);
-
 struct platform_driver fimd_driver = {
 	.probe		= fimd_probe,
 	.remove		= fimd_remove,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.h b/drivers/gpu/drm/exynos/exynos_drm_fimd.h
deleted file mode 100644
index b4fcaa568456..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Copyright (c) 2015 Samsung Electronics Co., Ltd.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_DRM_FIMD_H_
-#define _EXYNOS_DRM_FIMD_H_
-
-extern void fimd_dp_clock_enable(struct exynos_drm_crtc *crtc, bool enable);
-
-#endif /* _EXYNOS_DRM_FIMD_H_ */
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index 13ea3349363b..b1180fbe7546 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -76,7 +76,7 @@ int exynos_check_plane(struct drm_plane *plane, struct drm_framebuffer *fb)
 			return -EFAULT;
 		}
 
-		exynos_plane->dma_addr[i] = buffer->dma_addr;
+		exynos_plane->dma_addr[i] = buffer->dma_addr + fb->offsets[i];
 
 		DRM_DEBUG_KMS("buffer: %d, dma_addr = 0x%lx\n",
 				i, (unsigned long)exynos_plane->dma_addr[i]);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 27e84ec21694..1b3479a8db5f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -217,7 +217,7 @@ static int vidi_ctx_initialize(struct vidi_context *ctx,
 	return 0;
 }
 
-static struct exynos_drm_crtc_ops vidi_crtc_ops = {
+static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
 	.dpms = vidi_dpms,
 	.enable_vblank = vidi_enable_vblank,
 	.disable_vblank = vidi_disable_vblank,
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index fbec750574e6..8874c1fcb3ab 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -44,6 +44,12 @@
 #define MIXER_WIN_NR		3
 #define MIXER_DEFAULT_WIN	0
 
+/* The pixelformats that are natively supported by the mixer. */
+#define MXR_FORMAT_RGB565	4
+#define MXR_FORMAT_ARGB1555	5
+#define MXR_FORMAT_ARGB4444	6
+#define MXR_FORMAT_ARGB8888	7
+
 struct mixer_resources {
 	int			irq;
 	void __iomem		*mixer_regs;
@@ -327,7 +333,8 @@ static void mixer_cfg_rgb_fmt(struct mixer_context *ctx, unsigned int height)
 	mixer_reg_writemask(res, MXR_CFG, val, MXR_CFG_RGB_FMT_MASK);
 }
 
-static void mixer_cfg_layer(struct mixer_context *ctx, int win, bool enable)
+static void mixer_cfg_layer(struct mixer_context *ctx, unsigned int win,
+				bool enable)
 {
 	struct mixer_resources *res = &ctx->mixer_res;
 	u32 val = enable ? ~0 : 0;
@@ -359,8 +366,6 @@ static void mixer_run(struct mixer_context *ctx)
 	struct mixer_resources *res = &ctx->mixer_res;
 
 	mixer_reg_writemask(res, MXR_STATUS, ~0, MXR_STATUS_REG_RUN);
-
-	mixer_regs_dump(ctx);
 }
 
 static void mixer_stop(struct mixer_context *ctx)
@@ -373,16 +378,13 @@ static void mixer_stop(struct mixer_context *ctx)
 	while (!(mixer_reg_read(res, MXR_STATUS) & MXR_STATUS_REG_IDLE) &&
 			--timeout)
 		usleep_range(10000, 12000);
-
-	mixer_regs_dump(ctx);
 }
 
-static void vp_video_buffer(struct mixer_context *ctx, int win)
+static void vp_video_buffer(struct mixer_context *ctx, unsigned int win)
 {
 	struct mixer_resources *res = &ctx->mixer_res;
 	unsigned long flags;
 	struct exynos_drm_plane *plane;
-	unsigned int buf_num = 1;
 	dma_addr_t luma_addr[2], chroma_addr[2];
 	bool tiled_mode = false;
 	bool crcb_mode = false;
@@ -393,27 +395,18 @@ static void vp_video_buffer(struct mixer_context *ctx, int win)
 	switch (plane->pixel_format) {
 	case DRM_FORMAT_NV12:
 		crcb_mode = false;
-		buf_num = 2;
 		break;
-	/* TODO: single buffer format NV12, NV21 */
+	case DRM_FORMAT_NV21:
+		crcb_mode = true;
+		break;
 	default:
-		/* ignore pixel format at disable time */
-		if (!plane->dma_addr[0])
-			break;
-
 		DRM_ERROR("pixel format for vp is wrong [%d].\n",
 				plane->pixel_format);
 		return;
 	}
 
-	if (buf_num == 2) {
-		luma_addr[0] = plane->dma_addr[0];
-		chroma_addr[0] = plane->dma_addr[1];
-	} else {
-		luma_addr[0] = plane->dma_addr[0];
-		chroma_addr[0] = plane->dma_addr[0]
-			+ (plane->pitch * plane->fb_height);
-	}
+	luma_addr[0] = plane->dma_addr[0];
+	chroma_addr[0] = plane->dma_addr[1];
 
 	if (plane->scan_flag & DRM_MODE_FLAG_INTERLACE) {
 		ctx->interlace = true;
@@ -484,6 +477,7 @@ static void vp_video_buffer(struct mixer_context *ctx, int win)
 	mixer_vsync_set_update(ctx, true);
 	spin_unlock_irqrestore(&res->reg_slock, flags);
 
+	mixer_regs_dump(ctx);
 	vp_regs_dump(ctx);
 }
 
@@ -518,7 +512,7 @@ fail:
 	return -ENOTSUPP;
 }
 
-static void mixer_graph_buffer(struct mixer_context *ctx, int win)
+static void mixer_graph_buffer(struct mixer_context *ctx, unsigned int win)
 {
 	struct mixer_resources *res = &ctx->mixer_res;
 	unsigned long flags;
@@ -531,20 +525,27 @@ static void mixer_graph_buffer(struct mixer_context *ctx, int win)
 
 	plane = &ctx->planes[win];
 
-	#define RGB565 4
-	#define ARGB1555 5
-	#define ARGB4444 6
-	#define ARGB8888 7
+	switch (plane->pixel_format) {
+	case DRM_FORMAT_XRGB4444:
+		fmt = MXR_FORMAT_ARGB4444;
+		break;
 
-	switch (plane->bpp) {
-	case 16:
-		fmt = ARGB4444;
+	case DRM_FORMAT_XRGB1555:
+		fmt = MXR_FORMAT_ARGB1555;
 		break;
-	case 32:
-		fmt = ARGB8888;
+
+	case DRM_FORMAT_RGB565:
+		fmt = MXR_FORMAT_RGB565;
+		break;
+
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+		fmt = MXR_FORMAT_ARGB8888;
 		break;
+
 	default:
-		fmt = ARGB8888;
+		DRM_DEBUG_KMS("pixelformat unsupported by mixer\n");
+		return;
 	}
 
 	/* check if mixer supports requested scaling setup */
@@ -617,6 +618,8 @@ static void mixer_graph_buffer(struct mixer_context *ctx, int win)
 
 	mixer_vsync_set_update(ctx, true);
 	spin_unlock_irqrestore(&res->reg_slock, flags);
+
+	mixer_regs_dump(ctx);
 }
 
 static void vp_win_reset(struct mixer_context *ctx)
@@ -1070,6 +1073,7 @@ static void mixer_poweroff(struct mixer_context *ctx)
 	mutex_unlock(&ctx->mixer_mutex);
 
 	mixer_stop(ctx);
+	mixer_regs_dump(ctx);
 	mixer_window_suspend(ctx);
 
 	ctx->int_en = mixer_reg_read(res, MXR_INT_EN);
@@ -1126,7 +1130,7 @@ int mixer_check_mode(struct drm_display_mode *mode)
 	return -EINVAL;
 }
 
-static struct exynos_drm_crtc_ops mixer_crtc_ops = {
+static const struct exynos_drm_crtc_ops mixer_crtc_ops = {
 	.dpms			= mixer_dpms,
 	.enable_vblank		= mixer_enable_vblank,
 	.disable_vblank		= mixer_disable_vblank,
@@ -1156,7 +1160,7 @@ static struct mixer_drv_data exynos4210_mxr_drv_data = {
 	.has_sclk = 1,
 };
 
-static struct platform_device_id mixer_driver_types[] = {
+static const struct platform_device_id mixer_driver_types[] = {
 	{
 		.name		= "s5p-mixer",
 		.driver_data	= (unsigned long)&exynos4210_mxr_drv_data,
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 007c7d7d8295..dc55c51964ab 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1667,12 +1667,15 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 
 	if (HAS_PCH_SPLIT(dev))
 		sr_enabled = I915_READ(WM1_LP_ILK) & WM1_LP_SR_EN;
-	else if (IS_CRESTLINE(dev) || IS_I945G(dev) || IS_I945GM(dev))
+	else if (IS_CRESTLINE(dev) || IS_G4X(dev) ||
+		 IS_I945G(dev) || IS_I945GM(dev))
 		sr_enabled = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
 	else if (IS_I915GM(dev))
 		sr_enabled = I915_READ(INSTPM) & INSTPM_SELF_EN;
 	else if (IS_PINEVIEW(dev))
 		sr_enabled = I915_READ(DSPFW3) & PINEVIEW_SELF_REFRESH_EN;
+	else if (IS_VALLEYVIEW(dev))
+		sr_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
 
 	intel_runtime_pm_put(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c302ffb5a168..a19d2c71e205 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -699,6 +699,16 @@ static int i915_drm_resume(struct drm_device *dev)
 	intel_init_pch_refclk(dev);
 	drm_mode_config_reset(dev);
 
+	/*
+	 * Interrupts have to be enabled before any batches are run. If not the
+	 * GPU will hang. i915_gem_init_hw() will initiate batches to
+	 * update/restore the context.
+	 *
+	 * Modeset enabling in intel_modeset_init_hw() also needs working
+	 * interrupts.
+	 */
+	intel_runtime_pm_enable_interrupts(dev_priv);
+
 	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_init_hw(dev)) {
 		DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
@@ -706,9 +716,6 @@ static int i915_drm_resume(struct drm_device *dev)
 	}
 	mutex_unlock(&dev->struct_mutex);
 
-	/* We need working interrupts for modeset enabling ... */
-	intel_runtime_pm_enable_interrupts(dev_priv);
-
 	intel_modeset_init_hw(dev);
 
 	spin_lock_irq(&dev_priv->irq_lock);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 53394f998a1f..2d0995e7afc3 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3003,8 +3003,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 		} else if (vma->ggtt_view.pages) {
 			sg_free_table(vma->ggtt_view.pages);
 			kfree(vma->ggtt_view.pages);
-			vma->ggtt_view.pages = NULL;
 		}
+		vma->ggtt_view.pages = NULL;
 	}
 
 	drm_mm_remove_node(&vma->node);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a3190e793ed4..cc552a4c1f3b 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -32,6 +32,7 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 #include <linux/dma_remapping.h>
+#include <linux/uaccess.h>
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
 #define  __EXEC_OBJECT_HAS_FENCE (1<<30)
@@ -465,7 +466,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	}
 
 	/* We can't wait for rendering with pagefaults disabled */
-	if (obj->active && in_atomic())
+	if (obj->active && pagefault_disabled())
 		return -EFAULT;
 
 	if (use_cpu_reloc(obj))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d547d9c8dda2..d0f3cbc87474 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13635,9 +13635,6 @@ static const struct intel_dmi_quirk intel_dmi_quirks[] = {
 };
 
 static struct intel_quirk intel_quirks[] = {
-	/* HP Mini needs pipe A force quirk (LP: #322104) */
-	{ 0x27ae, 0x103c, 0x361a, quirk_pipea_force },
-
 	/* Toshiba Protege R-205, S-209 needs pipe A force quirk */
 	{ 0x2592, 0x1179, 0x0001, quirk_pipea_force },
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index d0237102c27e..d714a4b5711e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -880,10 +880,8 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 				      DP_AUX_CH_CTL_RECEIVE_ERROR))
 				continue;
 			if (status & DP_AUX_CH_CTL_DONE)
-				break;
+				goto done;
 		}
-		if (status & DP_AUX_CH_CTL_DONE)
-			break;
 	}
 
 	if ((status & DP_AUX_CH_CTL_DONE) == 0) {
@@ -892,6 +890,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 		goto out;
 	}
 
+done:
 	/* Check for timeout or receive error.
 	 * Timeouts occur when the sink is not connected
 	 */
@@ -1348,7 +1347,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 	pipe_config->has_dp_encoder = true;
 	pipe_config->has_drrs = false;
-	pipe_config->has_audio = intel_dp->has_audio;
+	pipe_config->has_audio = intel_dp->has_audio && port != PORT_A;
 
 	if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
 		intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
@@ -2211,8 +2210,8 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	int dotclock;
 
 	tmp = I915_READ(intel_dp->output_reg);
-	if (tmp & DP_AUDIO_OUTPUT_ENABLE)
-		pipe_config->has_audio = true;
+
+	pipe_config->has_audio = tmp & DP_AUDIO_OUTPUT_ENABLE && port != PORT_A;
 
 	if ((port == PORT_A) || !HAS_PCH_CPT(dev)) {
 		if (tmp & DP_SYNC_HS_HIGH)
@@ -3812,7 +3811,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
 			if (val == 0)
 				break;
 
-			intel_dp->sink_rates[i] = val * 200;
+			/* Value read is in kHz while drm clock is saved in deca-kHz */
+			intel_dp->sink_rates[i] = (val * 200) / 10;
 		}
 		intel_dp->num_sink_rates = i;
 	}
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 56e437e31580..ae628001fd97 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -435,7 +435,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
 					       struct intel_gmbus,
 					       adapter);
 	struct drm_i915_private *dev_priv = bus->dev_priv;
-	int i, reg_offset;
+	int i = 0, inc, try = 0, reg_offset;
 	int ret = 0;
 
 	intel_aux_display_runtime_get(dev_priv);
@@ -448,12 +448,14 @@ gmbus_xfer(struct i2c_adapter *adapter,
 
 	reg_offset = dev_priv->gpio_mmio_base;
 
+retry:
 	I915_WRITE(GMBUS0 + reg_offset, bus->reg0);
 
-	for (i = 0; i < num; i++) {
+	for (; i < num; i += inc) {
+		inc = 1;
 		if (gmbus_is_index_read(msgs, i, num)) {
 			ret = gmbus_xfer_index_read(dev_priv, &msgs[i]);
-			i += 1;  /* set i to the index of the read xfer */
+			inc = 2; /* an index read is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
 			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
 		} else {
@@ -525,6 +527,18 @@ clear_err:
 			 adapter->name, msgs[i].addr,
 			 (msgs[i].flags & I2C_M_RD) ? 'r' : 'w', msgs[i].len);
 
+	/*
+	 * Passive adapters sometimes NAK the first probe. Retry the first
+	 * message once on -ENXIO for GMBUS transfers; the bit banging algorithm
+	 * has retries internally. See also the retry loop in
+	 * drm_do_probe_ddc_edid, which bails out on the first -ENXIO.
+	 */
+	if (ret == -ENXIO && i == 0 && try++ == 0) {
+		DRM_DEBUG_KMS("GMBUS [%s] NAK on first message, retry\n",
+			      adapter->name);
+		goto retry;
+	}
+
 	goto out;
 
 timeout:
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 09df74b8e917..424e62197787 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1134,6 +1134,12 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring)
 	I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask));
 	I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff);
 
+	if (ring->status_page.obj) {
+		I915_WRITE(RING_HWS_PGA(ring->mmio_base),
+			   (u32)ring->status_page.gfx_addr);
+		POSTING_READ(RING_HWS_PGA(ring->mmio_base));
+	}
+
 	I915_WRITE(RING_MODE_GEN7(ring),
 		   _MASKED_BIT_DISABLE(GFX_REPLAY_MODE) |
 		   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 5abda1d2c018..fbcc7dff0d63 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -813,12 +813,28 @@ static int intel_dual_link_lvds_callback(const struct dmi_system_id *id)
 static const struct dmi_system_id intel_dual_link_lvds[] = {
 	{
 		.callback = intel_dual_link_lvds_callback,
-		.ident = "Apple MacBook Pro (Core i5/i7 Series)",
+		.ident = "Apple MacBook Pro 15\" (2010)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro6,2"),
+		},
+	},
+	{
+		.callback = intel_dual_link_lvds_callback,
+		.ident = "Apple MacBook Pro 15\" (2011)",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro8,2"),
 		},
 	},
+	{
+		.callback = intel_dual_link_lvds_callback,
+		.ident = "Apple MacBook Pro 15\" (2012)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,1"),
+		},
+	},
 	{ }	/* terminating entry */
 };
 
@@ -848,6 +864,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
 	if (i915.lvds_channel_mode > 0)
 		return i915.lvds_channel_mode == 2;
 
+	/* single channel LVDS is limited to 112 MHz */
+	if (lvds_encoder->attached_connector->base.panel.fixed_mode->clock
+	    > 112999)
+		return true;
+
 	if (dmi_check_system(intel_dual_link_lvds))
 		return true;
 
@@ -1111,6 +1132,8 @@ void intel_lvds_init(struct drm_device *dev)
 out:
 	mutex_unlock(&dev->mode_config.mutex);
 
+	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
+
 	lvds_encoder->is_dual_link = compute_is_dual_link_lvds(lvds_encoder);
 	DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
 		      lvds_encoder->is_dual_link ? "dual" : "single");
@@ -1125,7 +1148,6 @@ out:
 	}
 	drm_connector_register(connector);
 
-	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
 	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	return;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index 71e87abdcae7..481337436f72 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -396,16 +396,6 @@ int intel_opregion_notify_adapter(struct drm_device *dev, pci_power_t state)
 	return -EINVAL;
 }
 
-/*
- * If the vendor backlight interface is not in use and ACPI backlight interface
- * is broken, do not bother processing backlight change requests from firmware.
- */
-static bool should_ignore_backlight_request(void)
-{
-	return acpi_video_backlight_support() &&
-	       !acpi_video_verify_backlight_support();
-}
-
 static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -414,7 +404,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
-	if (should_ignore_backlight_request()) {
+	if (acpi_video_get_backlight_type() == acpi_backlight_native) {
 		DRM_DEBUG_KMS("opregion backlight request ignored\n");
 		return 0;
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index fa4ccb346389..555b896d2bda 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2045,22 +2045,20 @@ static void ilk_compute_wm_parameters(struct drm_crtc *crtc,
 	p->pipe_htotal = intel_crtc->config->base.adjusted_mode.crtc_htotal;
 	p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
 
-	if (crtc->primary->state->fb) {
-		p->pri.enabled = true;
+	if (crtc->primary->state->fb)
 		p->pri.bytes_per_pixel =
 			crtc->primary->state->fb->bits_per_pixel / 8;
-	} else {
-		p->pri.enabled = false;
-		p->pri.bytes_per_pixel = 0;
-	}
+	else
+		p->pri.bytes_per_pixel = 4;
+
+	p->cur.bytes_per_pixel = 4;
+	/*
+	 * TODO: for now, assume primary and cursor planes are always enabled.
+	 * Setting them to false makes the screen flicker.
+	 */
+	p->pri.enabled = true;
+	p->cur.enabled = true;
 
-	if (crtc->cursor->state->fb) {
-		p->cur.enabled = true;
-		p->cur.bytes_per_pixel = 4;
-	} else {
-		p->cur.enabled = false;
-		p->cur.bytes_per_pixel = 0;
-	}
 	p->pri.horiz_pixels = intel_crtc->config->pipe_src_w;
 	p->cur.horiz_pixels = intel_crtc->base.cursor->state->crtc_w;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 441e2502b889..005b5e04de4d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -901,13 +901,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			    GEN6_WIZ_HASHING_MASK,
 			    GEN6_WIZ_HASHING_16x4);
 
-	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
-	    INTEL_REVID(dev) == SKL_REVID_D0)
-		/* WaBarrierPerformanceFixDisable:skl */
-		WA_SET_BIT_MASKED(HDC_CHICKEN0,
-				  HDC_FENCE_DEST_SLM_DISABLE |
-				  HDC_BARRIER_PERFORMANCE_DISABLE);
-
 	return 0;
 }
 
@@ -1024,6 +1017,13 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
+	if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+	    INTEL_REVID(dev) == SKL_REVID_D0)
+		/* WaBarrierPerformanceFixDisable:skl */
+		WA_SET_BIT_MASKED(HDC_CHICKEN0,
+				  HDC_FENCE_DEST_SLM_DISABLE |
+				  HDC_BARRIER_PERFORMANCE_DISABLE);
+
 	return skl_tune_iz_hashing(ring);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index e87d2f418de4..987b81f31b0e 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2550,7 +2550,7 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
 
 	DRM_DEBUG_KMS("initialising analog device %d\n", device);
 
-	intel_sdvo_connector = kzalloc(sizeof(*intel_sdvo_connector), GFP_KERNEL);
+	intel_sdvo_connector = intel_sdvo_connector_alloc();
 	if (!intel_sdvo_connector)
 		return false;
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 6e84df9369a6..ad4b9010dfb0 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1526,6 +1526,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		return MODE_BANDWIDTH;
 	}
 
+	if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 ||
+	    (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) {
+		return MODE_H_ILLEGAL;
+	}
+
 	if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
 	    mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
 	    mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 ||
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 94a5bee69fe7..bbdcab0a56c1 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -384,7 +384,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *gpu)
 	if (gpu->memptrs_bo) {
 		if (gpu->memptrs_iova)
 			msm_gem_put_iova(gpu->memptrs_bo, gpu->base.id);
-		drm_gem_object_unreference(gpu->memptrs_bo);
+		drm_gem_object_unreference_unlocked(gpu->memptrs_bo);
 	}
 	release_firmware(gpu->pm4);
 	release_firmware(gpu->pfp);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 28d1f95a90cc..ad50b80225f5 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -177,6 +177,11 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
+	for (i = 0; i < MSM_DSI_ENCODER_NUM; i++) {
+		encoders[i]->bridge = msm_dsi->bridge;
+		msm_dsi->encoders[i] = encoders[i];
+	}
+
 	msm_dsi->connector = msm_dsi_manager_connector_init(msm_dsi->id);
 	if (IS_ERR(msm_dsi->connector)) {
 		ret = PTR_ERR(msm_dsi->connector);
@@ -185,11 +190,6 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
-	for (i = 0; i < MSM_DSI_ENCODER_NUM; i++) {
-		encoders[i]->bridge = msm_dsi->bridge;
-		msm_dsi->encoders[i] = encoders[i];
-	}
-
 	priv->bridges[priv->num_bridges++]       = msm_dsi->bridge;
 	priv->connectors[priv->num_connectors++] = msm_dsi->connector;
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 956b22492c9a..649d20d29f92 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1023,7 +1023,7 @@ static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 		*data = buf[1]; /* strip out dcs type */
 		return 1;
 	} else {
-		pr_err("%s: read data does not match with rx_buf len %d\n",
+		pr_err("%s: read data does not match with rx_buf len %zu\n",
 			__func__, msg->rx_len);
 		return -EINVAL;
 	}
@@ -1040,7 +1040,7 @@ static int dsi_short_read2_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 		data[1] = buf[2];
 		return 2;
 	} else {
-		pr_err("%s: read data does not match with rx_buf len %d\n",
+		pr_err("%s: read data does not match with rx_buf len %zu\n",
 			__func__, msg->rx_len);
 		return -EINVAL;
 	}
@@ -1093,7 +1093,6 @@ static int dsi_cmd_dma_rx(struct msm_dsi_host *msm_host,
 {
 	u32 *lp, *temp, data;
 	int i, j = 0, cnt;
-	bool ack_error = false;
 	u32 read_cnt;
 	u8 reg[16];
 	int repeated_bytes = 0;
@@ -1105,15 +1104,10 @@ static int dsi_cmd_dma_rx(struct msm_dsi_host *msm_host,
 	if (cnt > 4)
 		cnt = 4; /* 4 x 32 bits registers only */
 
-	/* Calculate real read data count */
-	read_cnt = dsi_read(msm_host, 0x1d4) >> 16;
-
-	ack_error = (rx_byte == 4) ?
-		(read_cnt == 8) : /* short pkt + 4-byte error pkt */
-		(read_cnt == (pkt_size + 6 + 4)); /* long pkt+4-byte error pkt*/
-
-	if (ack_error)
-		read_cnt -= 4; /* Remove 4 byte error pkt */
+	if (rx_byte == 4)
+		read_cnt = 4;
+	else
+		read_cnt = pkt_size + 6;
 
 	/*
 	 * In case of multiple reads from the panel, after the first read, there
@@ -1215,7 +1209,7 @@ static void dsi_err_worker(struct work_struct *work)
 		container_of(work, struct msm_dsi_host, err_work);
 	u32 status = msm_host->err_work_state;
 
-	pr_err("%s: status=%x\n", __func__, status);
+	pr_err_ratelimited("%s: status=%x\n", __func__, status);
 	if (status & DSI_ERR_STATE_MDP_FIFO_UNDERFLOW)
 		dsi_sw_reset_restore(msm_host);
 
@@ -1797,6 +1791,7 @@ int msm_dsi_host_cmd_rx(struct mipi_dsi_host *host,
 	case MIPI_DSI_RX_ACKNOWLEDGE_AND_ERROR_REPORT:
 		pr_err("%s: rx ACK_ERR_PACLAGE\n", __func__);
 		ret = 0;
+		break;
 	case MIPI_DSI_RX_GENERIC_SHORT_READ_RESPONSE_1BYTE:
 	case MIPI_DSI_RX_DCS_SHORT_READ_RESPONSE_1BYTE:
 		ret = dsi_short_read1_resp(buf, msg);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index ee3ebcaa33f5..0a40f3c64e8b 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -462,7 +462,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_connector *connector = NULL;
 	struct dsi_connector *dsi_connector;
-	int ret;
+	int ret, i;
 
 	dsi_connector = devm_kzalloc(msm_dsi->dev->dev,
 				sizeof(*dsi_connector), GFP_KERNEL);
@@ -495,6 +495,10 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	if (ret)
 		goto fail;
 
+	for (i = 0; i < MSM_DSI_ENCODER_NUM; i++)
+		drm_mode_connector_attach_encoder(connector,
+						msm_dsi->encoders[i]);
+
 	return connector;
 
 fail:
diff --git a/drivers/gpu/drm/msm/edp/edp_aux.c b/drivers/gpu/drm/msm/edp/edp_aux.c
index 5f5a84f6074c..208f9d47f82e 100644
--- a/drivers/gpu/drm/msm/edp/edp_aux.c
+++ b/drivers/gpu/drm/msm/edp/edp_aux.c
@@ -132,7 +132,7 @@ ssize_t edp_aux_transfer(struct drm_dp_aux *drm_aux, struct drm_dp_aux_msg *msg)
 	/* msg sanity check */
 	if ((native && (msg->size > AUX_CMD_NATIVE_MAX)) ||
 		(msg->size > AUX_CMD_I2C_MAX)) {
-		pr_err("%s: invalid msg: size(%d), request(%x)\n",
+		pr_err("%s: invalid msg: size(%zu), request(%x)\n",
 			__func__, msg->size, msg->request);
 		return -EINVAL;
 	}
@@ -155,7 +155,7 @@ ssize_t edp_aux_transfer(struct drm_dp_aux *drm_aux, struct drm_dp_aux_msg *msg)
 		 */
 		edp_write(aux->base + REG_EDP_AUX_TRANS_CTRL, 0);
 		msm_edp_aux_ctrl(aux, 1);
-		pr_err("%s: aux timeout, %d\n", __func__, ret);
+		pr_err("%s: aux timeout, %zd\n", __func__, ret);
 		goto unlock_exit;
 	}
 	DBG("completion");
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index d8812e84da54..b4d1b469862a 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -151,6 +151,8 @@ struct drm_connector *msm_edp_connector_init(struct msm_edp *edp)
 	if (ret)
 		goto fail;
 
+	drm_mode_connector_attach_encoder(connector, edp->encoder);
+
 	return connector;
 
 fail:
diff --git a/drivers/gpu/drm/msm/edp/edp_ctrl.c b/drivers/gpu/drm/msm/edp/edp_ctrl.c
index 0ec5abdba5c4..29e52d7c61c0 100644
--- a/drivers/gpu/drm/msm/edp/edp_ctrl.c
+++ b/drivers/gpu/drm/msm/edp/edp_ctrl.c
@@ -1149,12 +1149,13 @@ int msm_edp_ctrl_init(struct msm_edp *edp)
 	ctrl->aux = msm_edp_aux_init(dev, ctrl->base, &ctrl->drm_aux);
 	if (!ctrl->aux || !ctrl->drm_aux) {
 		pr_err("%s:failed to init aux\n", __func__);
-		return ret;
+		return -ENOMEM;
 	}
 
 	ctrl->phy = msm_edp_phy_init(dev, ctrl->base);
 	if (!ctrl->phy) {
 		pr_err("%s:failed to init phy\n", __func__);
+		ret = -ENOMEM;
 		goto err_destory_aux;
 	}
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
index e001e6b2296a..8b9a7931b162 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.c
@@ -72,14 +72,13 @@ const struct mdp5_cfg_hw msm8x74_config = {
 		.base = { 0x12d00, 0x12e00, 0x12f00 },
 	},
 	.intf = {
-		.count = 4,
 		.base = { 0x12500, 0x12700, 0x12900, 0x12b00 },
-	},
-	.intfs = {
-		[0] = INTF_eDP,
-		[1] = INTF_DSI,
-		[2] = INTF_DSI,
-		[3] = INTF_HDMI,
+		.connect = {
+			[0] = INTF_eDP,
+			[1] = INTF_DSI,
+			[2] = INTF_DSI,
+			[3] = INTF_HDMI,
+		},
 	},
 	.max_clk = 200000000,
 };
@@ -142,14 +141,13 @@ const struct mdp5_cfg_hw apq8084_config = {
 		.base = { 0x12f00, 0x13000, 0x13100, 0x13200 },
 	},
 	.intf = {
-		.count = 5,
 		.base = { 0x12500, 0x12700, 0x12900, 0x12b00, 0x12d00 },
-	},
-	.intfs = {
-		[0] = INTF_eDP,
-		[1] = INTF_DSI,
-		[2] = INTF_DSI,
-		[3] = INTF_HDMI,
+		.connect = {
+			[0] = INTF_eDP,
+			[1] = INTF_DSI,
+			[2] = INTF_DSI,
+			[3] = INTF_HDMI,
+		},
 	},
 	.max_clk = 320000000,
 };
@@ -196,10 +194,12 @@ const struct mdp5_cfg_hw msm8x16_config = {
 
 	},
 	.intf = {
-		.count = 1, /* INTF_1 */
-		.base = { 0x6B800 },
+		.base = { 0x00000, 0x6b800 },
+		.connect = {
+			[0] = INTF_DISABLED,
+			[1] = INTF_DSI,
+		},
 	},
-	/* TODO enable .intfs[] with [1] = INTF_DSI, once DSI is implemented */
 	.max_clk = 320000000,
 };
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.h
index 3a551b0892d8..69349abe59f2 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_cfg.h
@@ -59,6 +59,11 @@ struct mdp5_smp_block {
 
 #define MDP5_INTF_NUM_MAX	5
 
+struct mdp5_intf_block {
+	uint32_t base[MAX_BASES];
+	u32 connect[MDP5_INTF_NUM_MAX]; /* array of enum mdp5_intf_type */
+};
+
 struct mdp5_cfg_hw {
 	char  *name;
 
@@ -72,9 +77,7 @@ struct mdp5_cfg_hw {
 	struct mdp5_sub_block dspp;
 	struct mdp5_sub_block ad;
 	struct mdp5_sub_block pp;
-	struct mdp5_sub_block intf;
-
-	u32 intfs[MDP5_INTF_NUM_MAX]; /* array of enum mdp5_intf_type */
+	struct mdp5_intf_block intf;
 
 	uint32_t max_clk;
 };
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index dfa8beb9343a..bbacf9d2b738 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -206,8 +206,8 @@ static struct drm_encoder *construct_encoder(struct mdp5_kms *mdp5_kms,
 
 static int get_dsi_id_from_intf(const struct mdp5_cfg_hw *hw_cfg, int intf_num)
 {
-	const int intf_cnt = hw_cfg->intf.count;
-	const u32 *intfs = hw_cfg->intfs;
+	const enum mdp5_intf_type *intfs = hw_cfg->intf.connect;
+	const int intf_cnt = ARRAY_SIZE(hw_cfg->intf.connect);
 	int id = 0, i;
 
 	for (i = 0; i < intf_cnt; i++) {
@@ -228,7 +228,7 @@ static int modeset_init_intf(struct mdp5_kms *mdp5_kms, int intf_num)
 	struct msm_drm_private *priv = dev->dev_private;
 	const struct mdp5_cfg_hw *hw_cfg =
 					mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-	enum mdp5_intf_type intf_type = hw_cfg->intfs[intf_num];
+	enum mdp5_intf_type intf_type = hw_cfg->intf.connect[intf_num];
 	struct drm_encoder *encoder;
 	int ret = 0;
 
@@ -365,7 +365,7 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 	/* Construct encoders and modeset initialize connector devices
 	 * for each external display interface.
 	 */
-	for (i = 0; i < ARRAY_SIZE(hw_cfg->intfs); i++) {
+	for (i = 0; i < ARRAY_SIZE(hw_cfg->intf.connect); i++) {
 		ret = modeset_init_intf(mdp5_kms, i);
 		if (ret)
 			goto fail;
@@ -514,8 +514,8 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	 */
 	mdp5_enable(mdp5_kms);
 	for (i = 0; i < MDP5_INTF_NUM_MAX; i++) {
-		if (!config->hw->intf.base[i] ||
-				mdp5_cfg_intf_is_virtual(config->hw->intfs[i]))
+		if (mdp5_cfg_intf_is_virtual(config->hw->intf.connect[i]) ||
+				!config->hw->intf.base[i])
 			continue;
 		mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(i), 0);
 	}
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 18a3d203b174..57b8f56ae9d0 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -273,7 +273,7 @@ static void set_scanout_locked(struct drm_plane *plane,
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC2_ADDR(pipe),
 			msm_framebuffer_iova(fb, mdp5_kms->id, 2));
 	mdp5_write(mdp5_kms, REG_MDP5_PIPE_SRC3_ADDR(pipe),
-			msm_framebuffer_iova(fb, mdp5_kms->id, 4));
+			msm_framebuffer_iova(fb, mdp5_kms->id, 3));
 
 	plane->fb = fb;
 }
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 47f4dd407671..c80a6bee2b18 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -21,9 +21,11 @@
 
 static void msm_fb_output_poll_changed(struct drm_device *dev)
 {
+#ifdef CONFIG_DRM_MSM_FBDEV
 	struct msm_drm_private *priv = dev->dev_private;
 	if (priv->fbdev)
 		drm_fb_helper_hotplug_event(priv->fbdev);
+#endif
 }
 
 static const struct drm_mode_config_funcs mode_config_funcs = {
@@ -94,7 +96,7 @@ void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
 	}
 
 	if (reglog)
-		printk(KERN_DEBUG "IO:region %s %08x %08lx\n", dbgname, (u32)ptr, size);
+		printk(KERN_DEBUG "IO:region %s %p %08lx\n", dbgname, ptr, size);
 
 	return ptr;
 }
@@ -102,7 +104,7 @@ void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
 void msm_writel(u32 data, void __iomem *addr)
 {
 	if (reglog)
-		printk(KERN_DEBUG "IO:W %08x %08x\n", (u32)addr, data);
+		printk(KERN_DEBUG "IO:W %p %08x\n", addr, data);
 	writel(data, addr);
 }
 
@@ -110,7 +112,7 @@ u32 msm_readl(const void __iomem *addr)
 {
 	u32 val = readl(addr);
 	if (reglog)
-		printk(KERN_ERR "IO:R %08x %08x\n", (u32)addr, val);
+		printk(KERN_ERR "IO:R %p %08x\n", addr, val);
 	return val;
 }
 
@@ -143,8 +145,8 @@ static int msm_unload(struct drm_device *dev)
 	if (gpu) {
 		mutex_lock(&dev->struct_mutex);
 		gpu->funcs->pm_suspend(gpu);
-		gpu->funcs->destroy(gpu);
 		mutex_unlock(&dev->struct_mutex);
+		gpu->funcs->destroy(gpu);
 	}
 
 	if (priv->vram.paddr) {
@@ -177,7 +179,7 @@ static int get_mdp_ver(struct platform_device *pdev)
 	const struct of_device_id *match;
 	match = of_match_node(match_types, dev->of_node);
 	if (match)
-		return (int)match->data;
+		return (int)(unsigned long)match->data;
 #endif
 	return 4;
 }
@@ -216,7 +218,7 @@ static int msm_init_vram(struct drm_device *dev)
 		if (ret)
 			return ret;
 		size = r.end - r.start;
-		DRM_INFO("using VRAM carveout: %lx@%08x\n", size, r.start);
+		DRM_INFO("using VRAM carveout: %lx@%pa\n", size, &r.start);
 	} else
 #endif
 
@@ -283,10 +285,6 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 
 	drm_mode_config_init(dev);
 
-	ret = msm_init_vram(dev);
-	if (ret)
-		goto fail;
-
 	platform_set_drvdata(pdev, dev);
 
 	/* Bind all our sub-components: */
@@ -294,6 +292,10 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		return ret;
 
+	ret = msm_init_vram(dev);
+	if (ret)
+		goto fail;
+
 	switch (get_mdp_ver(pdev)) {
 	case 4:
 		kms = mdp4_kms_init(dev);
@@ -419,9 +421,11 @@ static void msm_preclose(struct drm_device *dev, struct drm_file *file)
 
 static void msm_lastclose(struct drm_device *dev)
 {
+#ifdef CONFIG_DRM_MSM_FBDEV
 	struct msm_drm_private *priv = dev->dev_private;
 	if (priv->fbdev)
 		drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev);
+#endif
 }
 
 static irqreturn_t msm_irq(int irq, void *arg)
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 6b573e612f27..121713281417 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -172,8 +172,8 @@ struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_kms *kms = priv->kms;
-	struct msm_framebuffer *msm_fb;
-	struct drm_framebuffer *fb = NULL;
+	struct msm_framebuffer *msm_fb = NULL;
+	struct drm_framebuffer *fb;
 	const struct msm_format *format;
 	int ret, i, n;
 	unsigned int hsub, vsub;
@@ -239,8 +239,7 @@ struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 	return fb;
 
 fail:
-	if (fb)
-		msm_framebuffer_destroy(fb);
+	kfree(msm_fb);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 479d8af72bcb..52839769eb6c 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -483,7 +483,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	uint64_t off = drm_vma_node_start(&obj->vma_node);
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-	seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %d\n",
+	seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %zu\n",
 			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
 			msm_obj->read_fence, msm_obj->write_fence,
 			obj->name, obj->refcount.refcount.counter,
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 7acdaa5688b7..7ac2f1997e4a 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -60,7 +60,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint32_t iova,
 		u32 pa = sg_phys(sg) - sg->offset;
 		size_t bytes = sg->length + sg->offset;
 
-		VERB("map[%d]: %08x %08x(%x)", i, iova, pa, bytes);
+		VERB("map[%d]: %08x %08x(%zx)", i, iova, pa, bytes);
 
 		ret = iommu_map(domain, da, pa, bytes, prot);
 		if (ret)
@@ -99,7 +99,7 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint32_t iova,
 		if (unmapped < bytes)
 			return unmapped;
 
-		VERB("unmap[%d]: %08x(%x)", i, iova, bytes);
+		VERB("unmap[%d]: %08x(%zx)", i, iova, bytes);
 
 		BUG_ON(!PAGE_ALIGNED(bytes));
 
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 8171537dd7d1..1f14b908b221 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -56,6 +56,6 @@ fail:
 void msm_ringbuffer_destroy(struct msm_ringbuffer *ring)
 {
 	if (ring->bo)
-		drm_gem_object_unreference(ring->bo);
+		drm_gem_object_unreference_unlocked(ring->bo);
 	kfree(ring);
 }
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 0b5af0fe8659..64f8b2f687d2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -14,7 +14,7 @@
 
 #define FERMI_TWOD_A                                                 0x0000902d
 
-#define FERMI_MEMORY_TO_MEMORY_FORMAT_A                              0x0000903d
+#define FERMI_MEMORY_TO_MEMORY_FORMAT_A                              0x00009039
 
 #define KEPLER_INLINE_TO_MEMORY_A                                    0x0000a040
 #define KEPLER_INLINE_TO_MEMORY_B                                    0x0000a140
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
index 2f5eadd12a9b..fdb1dcf16a59 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
@@ -329,7 +329,6 @@ gm204_gr_init(struct nvkm_object *object)
 	nv_mask(priv, 0x419cc0, 0x00000008, 0x00000008);
 
 	for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
-	printk(KERN_ERR "ppc %d %d\n", gpc, priv->ppc_nr[gpc]);
 		for (ppc = 0; ppc < priv->ppc_nr[gpc]; ppc++)
 			nv_wr32(priv, PPC_UNIT(gpc, ppc, 0x038), 0xc0000000);
 		nv_wr32(priv, GPC_UNIT(gpc, 0x0420), 0xc0000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
index e8778c67578e..c61102f70805 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
@@ -90,12 +90,14 @@ gf100_devinit_disable(struct nvkm_devinit *devinit)
 	return disable;
 }
 
-static int
+int
 gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
 		   struct nvkm_oclass *oclass, void *data, u32 size,
 		   struct nvkm_object **pobject)
 {
+	struct nvkm_devinit_impl *impl = (void *)oclass;
 	struct nv50_devinit_priv *priv;
+	u64 disable;
 	int ret;
 
 	ret = nvkm_devinit_create(parent, engine, oclass, &priv);
@@ -103,7 +105,8 @@ gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
 	if (ret)
 		return ret;
 
-	if (nv_rd32(priv, 0x022500) & 0x00000001)
+	disable = impl->disable(&priv->base);
+	if (disable & (1ULL << NVDEV_ENGINE_DISP))
 		priv->base.post = true;
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index b345a53e881d..87ca0ece37b4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -48,7 +48,7 @@ struct nvkm_oclass *
 gm107_devinit_oclass = &(struct nvkm_devinit_impl) {
 	.base.handle = NV_SUBDEV(DEVINIT, 0x07),
 	.base.ofuncs = &(struct nvkm_ofuncs) {
-		.ctor = nv50_devinit_ctor,
+		.ctor = gf100_devinit_ctor,
 		.dtor = _nvkm_devinit_dtor,
 		.init = nv50_devinit_init,
 		.fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
index 535172c5f1ad..1076fcf0d716 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
@@ -161,7 +161,7 @@ struct nvkm_oclass *
 gm204_devinit_oclass = &(struct nvkm_devinit_impl) {
 	.base.handle = NV_SUBDEV(DEVINIT, 0x07),
 	.base.ofuncs = &(struct nvkm_ofuncs) {
-		.ctor = nv50_devinit_ctor,
+		.ctor = gf100_devinit_ctor,
 		.dtor = _nvkm_devinit_dtor,
 		.init = nv50_devinit_init,
 		.fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
index b882b65ff3cd..9243521c80ac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
@@ -15,6 +15,9 @@ int  nv50_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
 int  gt215_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
+int  gf100_devinit_ctor(struct nvkm_object *, struct nvkm_object *,
+			struct nvkm_oclass *, void *, u32,
+			struct nvkm_object **);
 int  gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
 u64  gm107_devinit_disable(struct nvkm_devinit *);
diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h
index 92be50c39ffd..ab89eed9ddd9 100644
--- a/drivers/gpu/drm/radeon/atombios.h
+++ b/drivers/gpu/drm/radeon/atombios.h
@@ -7944,8 +7944,8 @@ typedef struct {
 typedef struct {
   AMD_ACPI_DESCRIPTION_HEADER SHeader;
   UCHAR TableUUID[16];    //0x24
-  ULONG VBIOSImageOffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the stucture.
-  ULONG Lib1ImageOffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the stucture.
+  ULONG VBIOSImageOffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the structure.
+  ULONG Lib1ImageOffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the structure.
   ULONG Reserved[4];      //0x3C
 }UEFI_ACPI_VFCT;
 
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 42b2ea3fdcf3..dac78ad24b31 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -580,9 +580,6 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 		else
 			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_LOW_REF_DIV;
 
-		/* if there is no audio, set MINM_OVER_MAXP  */
-		if (!drm_detect_monitor_audio(radeon_connector_edid(connector)))
-			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
 		if (rdev->family < CHIP_RV770)
 			radeon_crtc->pll_flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP;
 		/* use frac fb div on APUs */
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 3e3290c203c6..b435c859dcbc 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -421,19 +421,21 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
 	u8 msg[DP_DPCD_SIZE];
-	int ret;
+	int ret, i;
 
-	ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
-			       DP_DPCD_SIZE);
-	if (ret > 0) {
-		memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
+	for (i = 0; i < 7; i++) {
+		ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
+				       DP_DPCD_SIZE);
+		if (ret == DP_DPCD_SIZE) {
+			memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
 
-		DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
-			      dig_connector->dpcd);
+			DRM_DEBUG_KMS("DPCD: %*ph\n", (int)sizeof(dig_connector->dpcd),
+				      dig_connector->dpcd);
 
-		radeon_dp_probe_oui(radeon_connector);
+			radeon_dp_probe_oui(radeon_connector);
 
-		return true;
+			return true;
+		}
 	}
 	dig_connector->dpcd[0] = 0;
 	return false;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 28faea9996f9..ba50f3c1c2e0 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5837,7 +5837,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 	/* restore context1-15 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
index f04205170b8a..cfa3a84a2af0 100644
--- a/drivers/gpu/drm/radeon/dce3_1_afmt.c
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -173,7 +173,7 @@ void dce3_2_hdmi_update_acr(struct drm_encoder *encoder, long offset,
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
 
-	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
+	WREG32(DCE3_HDMI0_ACR_PACKET_CONTROL + offset,
 		HDMI0_ACR_SOURCE |		/* select SW CTS value */
 		HDMI0_ACR_AUTO_SEND);	/* allow hw to sent ACR packets when required */
 
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0926739c9fa7..9953356fe263 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -400,7 +400,7 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	if (enable) {
 		struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
-		if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
 			WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset,
 			       HDMI_AVI_INFO_SEND | /* enable AVI info frames */
 			       HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */
@@ -438,7 +438,8 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable)
 	if (!dig || !dig->afmt)
 		return;
 
-	if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+	if (enable && connector &&
+	    drm_detect_monitor_audio(radeon_connector_edid(connector))) {
 		struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 		struct radeon_connector_atom_dig *dig_connector;
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index e8a496ff007e..64d3a771920d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1301,7 +1301,8 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	 */
 	for (i = 1; i < 8; i++) {
 		WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR + (i << 2), 0);
-		WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2), rdev->vm_manager.max_pfn);
+		WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR + (i << 2),
+			rdev->vm_manager.max_pfn - 1);
 		WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),
 		       rdev->vm_manager.saved_table_addr[i]);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index d2abe481954f..46eb0fa75a61 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1673,7 +1673,6 @@ struct radeon_uvd {
 	struct radeon_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
-	void			*saved_bo;
 	atomic_t		handles[RADEON_MAX_UVD_HANDLES];
 	struct drm_file		*filp[RADEON_MAX_UVD_HANDLES];
 	unsigned		img_size[RADEON_MAX_UVD_HANDLES];
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index fafd8ce4d58f..8dbf5083c4ff 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1202,7 +1202,7 @@ static struct radeon_asic rs780_asic = {
 static struct radeon_asic_ring rv770_uvd_ring = {
 	.ib_execute = &uvd_v1_0_ib_execute,
 	.emit_fence = &uvd_v2_2_fence_emit,
-	.emit_semaphore = &uvd_v1_0_semaphore_emit,
+	.emit_semaphore = &uvd_v2_2_semaphore_emit,
 	.cs_parse = &radeon_uvd_cs_parse,
 	.ring_test = &uvd_v1_0_ring_test,
 	.ib_test = &uvd_v1_0_ib_test,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index cf0a90bb61ca..a3ca8cd305c5 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -949,6 +949,10 @@ void uvd_v1_0_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int uvd_v2_2_resume(struct radeon_device *rdev);
 void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 			 struct radeon_fence *fence);
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait);
 
 /* uvd v3.1 */
 bool uvd_v3_1_semaphore_emit(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index 8b82abb78df1..25191f126f3b 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -460,33 +460,34 @@ void radeon_audio_detect(struct drm_connector *connector,
 	if (!connector || !connector->encoder)
 		return;
 
-	if (!radeon_encoder_is_digital(connector->encoder))
+	rdev = connector->encoder->dev->dev_private;
+
+	if (!radeon_audio_chipset_supported(rdev))
 		return;
 
-	rdev = connector->encoder->dev->dev_private;
 	radeon_encoder = to_radeon_encoder(connector->encoder);
 	dig = radeon_encoder->enc_priv;
 
-	if (!dig->afmt)
-		return;
-
 	if (status == connector_status_connected) {
-		struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+		struct radeon_connector *radeon_connector;
+		int sink_type;
+
+		if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+			radeon_encoder->audio = NULL;
+			return;
+		}
+
+		radeon_connector = to_radeon_connector(connector);
+		sink_type = radeon_dp_getsinktype(radeon_connector);
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
-		    radeon_dp_getsinktype(radeon_connector) ==
-		    CONNECTOR_OBJECT_ID_DISPLAYPORT)
+			sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT)
 			radeon_encoder->audio = rdev->audio.dp_funcs;
 		else
 			radeon_encoder->audio = rdev->audio.hdmi_funcs;
 
 		dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
-		if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
-			radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
-		} else {
-			radeon_audio_enable(rdev, dig->afmt->pin, 0);
-			dig->afmt->pin = NULL;
-		}
+		radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
 	} else {
 		radeon_audio_enable(rdev, dig->afmt->pin, 0);
 		dig->afmt->pin = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index d17d251dbd4f..cebb65e07e1d 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,10 +1379,8 @@ out:
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0) {
-		radeon_connector_get_edid(connector);
+	if (radeon_audio != 0)
 		radeon_audio_detect(connector, ret);
-	}
 
 exit:
 	pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1719,10 +1717,8 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0) {
-		radeon_connector_get_edid(connector);
+	if (radeon_audio != 0)
 		radeon_audio_detect(connector, ret);
-	}
 
 out:
 	pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b7ca4c514621..a7fdfa4f0857 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1463,6 +1463,21 @@ int radeon_device_init(struct radeon_device *rdev,
 	if (r)
 		DRM_ERROR("ib ring test failed (%d).\n", r);
 
+	/*
+	 * Turks/Thames GPU will freeze whole laptop if DPM is not restarted
+	 * after the CP ring have chew one packet at least. Hence here we stop
+	 * and restart DPM after the radeon_ib_ring_tests().
+	 */
+	if (rdev->pm.dpm_enabled &&
+	    (rdev->pm.pm_method == PM_METHOD_DPM) &&
+	    (rdev->family == CHIP_TURKS) &&
+	    (rdev->flags & RADEON_IS_MOBILITY)) {
+		mutex_lock(&rdev->pm.mutex);
+		radeon_dpm_disable(rdev);
+		radeon_dpm_enable(rdev);
+		mutex_unlock(&rdev->pm.mutex);
+	}
+
 	if ((radeon_testing & 1)) {
 		if (rdev->accel_working)
 			radeon_test_moves(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_dp_auxch.c b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
index bf1fecc6cceb..fcbd60bb0349 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_auxch.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_auxch.c
@@ -30,8 +30,6 @@
 			    AUX_SW_RX_HPD_DISCON |	     \
 			    AUX_SW_RX_PARTIAL_BYTE |	     \
 			    AUX_SW_NON_AUX_MODE |	     \
-			    AUX_SW_RX_MIN_COUNT_VIOL |	     \
-			    AUX_SW_RX_INVALID_STOP |	     \
 			    AUX_SW_RX_SYNC_INVALID_L |	     \
 			    AUX_SW_RX_SYNC_INVALID_H |	     \
 			    AUX_SW_RX_INVALID_START |	     \
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 1017338a49d9..257b10be5cda 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -663,9 +663,17 @@ int
 radeon_dp_mst_probe(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
+	struct drm_device *dev = radeon_connector->base.dev;
+	struct radeon_device *rdev = dev->dev_private;
 	int ret;
 	u8 msg[1];
 
+	if (!radeon_mst)
+		return 0;
+
+	if (!ASIC_IS_DCE5(rdev))
+		return 0;
+
 	if (dig_connector->dpcd[DP_DPCD_REV] < 0x12)
 		return 0;
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 7b2a7335cc5d..b0acf50d9558 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -576,6 +576,9 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (radeon_get_allowed_info_register(rdev, *value, value))
 			return -EINVAL;
 		break;
+	case RADEON_INFO_VA_UNMAP_WORKING:
+		*value = true;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index 535bf404b725..eef006c48584 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -142,6 +142,9 @@ static void radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 
 		list_for_each_entry(bo, &node->bos, mn_list) {
 
+			if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound)
+				continue;
+
 			r = radeon_bo_reserve(bo, true);
 			if (r) {
 				DRM_ERROR("(%ld) failed to reserve user bo\n", r);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index b292aca0f342..edafd3c2b170 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -591,8 +591,7 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 {
 	struct radeon_device *rdev = radeon_get_rdev(ttm->bdev);
 	struct radeon_ttm_tt *gtt = (void *)ttm;
-	struct scatterlist *sg;
-	int i;
+	struct sg_page_iter sg_iter;
 
 	int write = !(gtt->userflags & RADEON_GEM_USERPTR_READONLY);
 	enum dma_data_direction direction = write ?
@@ -605,9 +604,8 @@ static void radeon_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
 	/* free the sg table and pages again */
 	dma_unmap_sg(rdev->dev, ttm->sg->sgl, ttm->sg->nents, direction);
 
-	for_each_sg(ttm->sg->sgl, sg, ttm->sg->nents, i) {
-		struct page *page = sg_page(sg);
-
+	for_each_sg_page(ttm->sg->sgl, &sg_iter, ttm->sg->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
 		if (!(gtt->userflags & RADEON_GEM_USERPTR_READONLY))
 			set_page_dirty(page);
 
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index c10b2aec6450..6edcb5485092 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -204,28 +204,32 @@ void radeon_uvd_fini(struct radeon_device *rdev)
 
 int radeon_uvd_suspend(struct radeon_device *rdev)
 {
-	unsigned size;
-	void *ptr;
-	int i;
+	int i, r;
 
 	if (rdev->uvd.vcpu_bo == NULL)
 		return 0;
 
-	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
-		if (atomic_read(&rdev->uvd.handles[i]))
-			break;
+	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+		uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+		if (handle != 0) {
+			struct radeon_fence *fence;
 
-	if (i == RADEON_MAX_UVD_HANDLES)
-		return 0;
+			radeon_uvd_note_usage(rdev);
 
-	size = radeon_bo_size(rdev->uvd.vcpu_bo);
-	size -= rdev->uvd_fw->size;
+			r = radeon_uvd_get_destroy_msg(rdev,
+				R600_RING_TYPE_UVD_INDEX, handle, &fence);
+			if (r) {
+				DRM_ERROR("Error destroying UVD (%d)!\n", r);
+				continue;
+			}
 
-	ptr = rdev->uvd.cpu_addr;
-	ptr += rdev->uvd_fw->size;
+			radeon_fence_wait(fence, false);
+			radeon_fence_unref(&fence);
 
-	rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
-	memcpy(rdev->uvd.saved_bo, ptr, size);
+			rdev->uvd.filp[i] = NULL;
+			atomic_set(&rdev->uvd.handles[i], 0);
+		}
+	}
 
 	return 0;
 }
@@ -246,12 +250,7 @@ int radeon_uvd_resume(struct radeon_device *rdev)
 	ptr = rdev->uvd.cpu_addr;
 	ptr += rdev->uvd_fw->size;
 
-	if (rdev->uvd.saved_bo != NULL) {
-		memcpy(ptr, rdev->uvd.saved_bo, size);
-		kfree(rdev->uvd.saved_bo);
-		rdev->uvd.saved_bo = NULL;
-	} else
-		memset(ptr, 0, size);
+	memset(ptr, 0, size);
 
 	return 0;
 }
@@ -396,6 +395,29 @@ static int radeon_uvd_cs_msg_decode(uint32_t *msg, unsigned buf_sizes[])
 	return 0;
 }
 
+static int radeon_uvd_validate_codec(struct radeon_cs_parser *p,
+				     unsigned stream_type)
+{
+	switch (stream_type) {
+	case 0: /* H264 */
+	case 1: /* VC1 */
+		/* always supported */
+		return 0;
+
+	case 3: /* MPEG2 */
+	case 4: /* MPEG4 */
+		/* only since UVD 3 */
+		if (p->rdev->family >= CHIP_PALM)
+			return 0;
+
+		/* fall through */
+	default:
+		DRM_ERROR("UVD codec not supported by hardware %d!\n",
+			  stream_type);
+		return -EINVAL;
+	}
+}
+
 static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 			     unsigned offset, unsigned buf_sizes[])
 {
@@ -436,50 +458,70 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo,
 		return -EINVAL;
 	}
 
-	if (msg_type == 1) {
-		/* it's a decode msg, calc buffer sizes */
-		r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
-		/* calc image size (width * height) */
-		img_size = msg[6] * msg[7];
+	switch (msg_type) {
+	case 0:
+		/* it's a create msg, calc image size (width * height) */
+		img_size = msg[7] * msg[8];
+
+		r = radeon_uvd_validate_codec(p, msg[4]);
 		radeon_bo_kunmap(bo);
 		if (r)
 			return r;
 
-	} else if (msg_type == 2) {
+		/* try to alloc a new handle */
+		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+				return -EINVAL;
+			}
+
+			if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
+				p->rdev->uvd.filp[i] = p->filp;
+				p->rdev->uvd.img_size[i] = img_size;
+				return 0;
+			}
+		}
+
+		DRM_ERROR("No more free UVD handles!\n");
+		return -EINVAL;
+
+	case 1:
+		/* it's a decode msg, validate codec and calc buffer sizes */
+		r = radeon_uvd_validate_codec(p, msg[4]);
+		if (!r)
+			r = radeon_uvd_cs_msg_decode(msg, buf_sizes);
+		radeon_bo_kunmap(bo);
+		if (r)
+			return r;
+
+		/* validate the handle */
+		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&p->rdev->uvd.handles[i]) == handle) {
+				if (p->rdev->uvd.filp[i] != p->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
+					return -EINVAL;
+				}
+				return 0;
+			}
+		}
+
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		return -ENOENT;
+
+	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
 			atomic_cmpxchg(&p->rdev->uvd.handles[i], handle, 0);
 		radeon_bo_kunmap(bo);
 		return 0;
-	} else {
-		/* it's a create msg, calc image size (width * height) */
-		img_size = msg[7] * msg[8];
-		radeon_bo_kunmap(bo);
 
-		if (msg_type != 0) {
-			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
-			return -EINVAL;
-		}
-
-		/* it's a create msg, no special handling needed */
-	}
-
-	/* create or decode, validate the handle */
-	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
-		if (atomic_read(&p->rdev->uvd.handles[i]) == handle)
-			return 0;
-	}
+	default:
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&p->rdev->uvd.handles[i], 0, handle)) {
-			p->rdev->uvd.filp[i] = p->filp;
-			p->rdev->uvd.img_size[i] = img_size;
-			return 0;
-		}
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
 
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 24f849f888bb..0de5711ac508 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -493,18 +493,27 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi,
  *
  * @p: parser context
  * @handle: handle to validate
+ * @allocated: allocated a new handle?
  *
  * Validates the handle and return the found session index or -EINVAL
  * we we don't have another free session index.
  */
-int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
+static int radeon_vce_validate_handle(struct radeon_cs_parser *p,
+				      uint32_t handle, bool *allocated)
 {
 	unsigned i;
 
+	*allocated = false;
+
 	/* validate the handle */
 	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
-		if (atomic_read(&p->rdev->vce.handles[i]) == handle)
+		if (atomic_read(&p->rdev->vce.handles[i]) == handle) {
+			if (p->rdev->vce.filp[i] != p->filp) {
+				DRM_ERROR("VCE handle collision detected!\n");
+				return -EINVAL;
+			}
 			return i;
+		}
 	}
 
 	/* handle not found try to alloc a new one */
@@ -512,6 +521,7 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
 		if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
 			p->rdev->vce.filp[i] = p->filp;
 			p->rdev->vce.img_size[i] = 0;
+			*allocated = true;
 			return i;
 		}
 	}
@@ -529,10 +539,10 @@ int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
 int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 {
 	int session_idx = -1;
-	bool destroyed = false;
+	bool destroyed = false, created = false, allocated = false;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
-	int i, r;
+	int i, r = 0;
 
 	while (p->idx < p->chunk_ib->length_dw) {
 		uint32_t len = radeon_get_ib_value(p, p->idx);
@@ -540,18 +550,21 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 
 		if ((len < 8) || (len & 3)) {
 			DRM_ERROR("invalid VCE command length (%d)!\n", len);
-                	return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		if (destroyed) {
 			DRM_ERROR("No other command allowed after destroy!\n");
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		switch (cmd) {
 		case 0x00000001: // session
 			handle = radeon_get_ib_value(p, p->idx + 2);
-			session_idx = radeon_vce_validate_handle(p, handle);
+			session_idx = radeon_vce_validate_handle(p, handle,
+								 &allocated);
 			if (session_idx < 0)
 				return session_idx;
 			size = &p->rdev->vce.img_size[session_idx];
@@ -561,6 +574,13 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			break;
 
 		case 0x01000001: // create
+			created = true;
+			if (!allocated) {
+				DRM_ERROR("Handle already in use!\n");
+				r = -EINVAL;
+				goto out;
+			}
+
 			*size = radeon_get_ib_value(p, p->idx + 8) *
 				radeon_get_ib_value(p, p->idx + 10) *
 				8 * 3 / 2;
@@ -578,12 +598,12 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9,
 						*size);
 			if (r)
-				return r;
+				goto out;
 
 			r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11,
 						*size / 3);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x02000001: // destroy
@@ -594,7 +614,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						*size * 2);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x05000004: // video bitstream buffer
@@ -602,36 +622,47 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						tmp);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		case 0x05000005: // feedback buffer
 			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
 						4096);
 			if (r)
-				return r;
+				goto out;
 			break;
 
 		default:
 			DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		if (session_idx == -1) {
 			DRM_ERROR("no session command at start of IB\n");
-			return -EINVAL;
+			r = -EINVAL;
+			goto out;
 		}
 
 		p->idx += len / 4;
 	}
 
-	if (destroyed) {
-		/* IB contains a destroy msg, free the handle */
+	if (allocated && !created) {
+		DRM_ERROR("New session without create command!\n");
+		r = -ENOENT;
+	}
+
+out:
+	if ((!r && destroyed) || (r && allocated)) {
+		/*
+		 * IB contains a destroy msg or we have allocated an
+		 * handle and got an error, anyway free the handle
+		 */
 		for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
 			atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
 	}
 
-	return 0;
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index de42fc4a22b8..9c3377ca17b7 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -458,14 +458,16 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 		/* make sure object fit at this offset */
 		eoffset = soffset + size;
 		if (soffset >= eoffset) {
-			return -EINVAL;
+			r = -EINVAL;
+			goto error_unreserve;
 		}
 
 		last_pfn = eoffset / RADEON_GPU_PAGE_SIZE;
 		if (last_pfn > rdev->vm_manager.max_pfn) {
 			dev_err(rdev->dev, "va above limit (0x%08X > 0x%08X)\n",
 				last_pfn, rdev->vm_manager.max_pfn);
-			return -EINVAL;
+			r = -EINVAL;
+			goto error_unreserve;
 		}
 
 	} else {
@@ -486,7 +488,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 				"(bo %p 0x%010lx 0x%010lx)\n", bo_va->bo,
 				soffset, tmp->bo, tmp->it.start, tmp->it.last);
 			mutex_unlock(&vm->mutex);
-			return -EINVAL;
+			r = -EINVAL;
+			goto error_unreserve;
 		}
 	}
 
@@ -497,7 +500,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 			tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
 			if (!tmp) {
 				mutex_unlock(&vm->mutex);
-				return -ENOMEM;
+				r = -ENOMEM;
+				goto error_unreserve;
 			}
 			tmp->it.start = bo_va->it.start;
 			tmp->it.last = bo_va->it.last;
@@ -555,7 +559,6 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 		r = radeon_vm_clear_bo(rdev, pt);
 		if (r) {
 			radeon_bo_unref(&pt);
-			radeon_bo_reserve(bo_va->bo, false);
 			return r;
 		}
 
@@ -575,6 +578,10 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 
 	mutex_unlock(&vm->mutex);
 	return 0;
+
+error_unreserve:
+	radeon_bo_unreserve(bo_va->bo);
+	return r;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h
index 3cf1e2921545..9ef2064b1c9c 100644
--- a/drivers/gpu/drm/radeon/rv770d.h
+++ b/drivers/gpu/drm/radeon/rv770d.h
@@ -989,6 +989,9 @@
 			 ((n) & 0x3FFF) << 16)
 
 /* UVD */
+#define UVD_SEMA_ADDR_LOW				0xef00
+#define UVD_SEMA_ADDR_HIGH				0xef04
+#define UVD_SEMA_CMD					0xef08
 #define UVD_GPCOM_VCPU_CMD				0xef0c
 #define UVD_GPCOM_VCPU_DATA0				0xef10
 #define UVD_GPCOM_VCPU_DATA1				0xef14
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index b1d74bc375d8..4c679b802bc8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4318,7 +4318,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
 	/* empty context1-15 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn - 1);
 	/* Assign the pt base to something valid for now; the pts used for
 	 * the VMs are determined by the application and setup and assigned
 	 * on the fly in the vm part of radeon_gart.c
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index e72b3cb59358..c6b1cbca47fc 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -466,18 +466,8 @@ bool uvd_v1_0_semaphore_emit(struct radeon_device *rdev,
 			     struct radeon_semaphore *semaphore,
 			     bool emit_wait)
 {
-	uint64_t addr = semaphore->gpu_addr;
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
-	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
-	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-
-	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
-	radeon_ring_write(ring, emit_wait ? 1 : 0);
-
-	return true;
+	/* disable semaphores for UVD V1 hardware */
+	return false;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index 89193519f8a1..7ed778cec7c6 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -60,6 +60,35 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 }
 
 /**
+ * uvd_v2_2_semaphore_emit - emit semaphore command
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring pointer
+ * @semaphore: semaphore to emit commands for
+ * @emit_wait: true if we should emit a wait command
+ *
+ * Emit a semaphore command (either wait or signal) to the UVD ring.
+ */
+bool uvd_v2_2_semaphore_emit(struct radeon_device *rdev,
+			     struct radeon_ring *ring,
+			     struct radeon_semaphore *semaphore,
+			     bool emit_wait)
+{
+	uint64_t addr = semaphore->gpu_addr;
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_LOW, 0));
+	radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_ADDR_HIGH, 0));
+	radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
+
+	radeon_ring_write(ring, PACKET0(UVD_SEMA_CMD, 0));
+	radeon_ring_write(ring, emit_wait ? 1 : 0);
+
+	return true;
+}
+
+/**
  * uvd_v2_2_resume - memory controller programming
  *
  * @rdev: radeon_device pointer
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 1833abd7d3aa..bfad15a913a0 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -173,7 +173,6 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 	drm->irq_enabled = true;
 
 	/* syncpoints are used for full 32-bit hardware VBLANK counters */
-	drm->vblank_disable_immediate = true;
 	drm->max_vblank_count = 0xffffffff;
 
 	err = drm_vblank_init(drm, drm->mode_config.num_crtc);
diff --git a/drivers/gpu/drm/vgem/Makefile b/drivers/gpu/drm/vgem/Makefile
index 1055cb79096c..3f4c7b842028 100644
--- a/drivers/gpu/drm/vgem/Makefile
+++ b/drivers/gpu/drm/vgem/Makefile
@@ -1,4 +1,4 @@
 ccflags-y := -Iinclude/drm
-vgem-y := vgem_drv.o vgem_dma_buf.o
+vgem-y := vgem_drv.o
 
 obj-$(CONFIG_DRM_VGEM)	+= vgem.o
diff --git a/drivers/gpu/drm/vgem/vgem_dma_buf.c b/drivers/gpu/drm/vgem/vgem_dma_buf.c
deleted file mode 100644
index 0254438ad1a6..000000000000
--- a/drivers/gpu/drm/vgem/vgem_dma_buf.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright © 2012 Intel Corporation
- * Copyright © 2014 The Chromium OS Authors
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- * Authors:
- *    Ben Widawsky <ben@bwidawsk.net>
- *
- */
-
-#include <linux/dma-buf.h>
-#include "vgem_drv.h"
-
-struct sg_table *vgem_gem_prime_get_sg_table(struct drm_gem_object *gobj)
-{
-	struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-	BUG_ON(obj->pages == NULL);
-
-	return drm_prime_pages_to_sg(obj->pages, obj->base.size / PAGE_SIZE);
-}
-
-int vgem_gem_prime_pin(struct drm_gem_object *gobj)
-{
-	struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-	return vgem_gem_get_pages(obj);
-}
-
-void vgem_gem_prime_unpin(struct drm_gem_object *gobj)
-{
-	struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-	vgem_gem_put_pages(obj);
-}
-
-void *vgem_gem_prime_vmap(struct drm_gem_object *gobj)
-{
-	struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-	BUG_ON(obj->pages == NULL);
-
-	return vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL);
-}
-
-void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
-{
-	vunmap(vaddr);
-}
-
-struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
-					     struct dma_buf *dma_buf)
-{
-	struct drm_vgem_gem_object *obj = NULL;
-	int ret;
-
-	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
-	if (obj == NULL) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-
-	ret = drm_gem_object_init(dev, &obj->base, dma_buf->size);
-	if (ret) {
-		ret = -ENOMEM;
-		goto fail_free;
-	}
-
-	get_dma_buf(dma_buf);
-
-	obj->base.dma_buf = dma_buf;
-	obj->use_dma_buf = true;
-
-	return &obj->base;
-
-fail_free:
-	kfree(obj);
-fail:
-	return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index cb3b43525b2d..7a207ca547be 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -302,22 +302,13 @@ static const struct file_operations vgem_driver_fops = {
 };
 
 static struct drm_driver vgem_driver = {
-	.driver_features		= DRIVER_GEM | DRIVER_PRIME,
+	.driver_features		= DRIVER_GEM,
 	.gem_free_object		= vgem_gem_free_object,
 	.gem_vm_ops			= &vgem_gem_vm_ops,
 	.ioctls				= vgem_ioctls,
 	.fops				= &vgem_driver_fops,
 	.dumb_create			= vgem_gem_dumb_create,
 	.dumb_map_offset		= vgem_gem_dumb_map,
-	.prime_handle_to_fd		= drm_gem_prime_handle_to_fd,
-	.prime_fd_to_handle		= drm_gem_prime_fd_to_handle,
-	.gem_prime_export		= drm_gem_prime_export,
-	.gem_prime_import		= vgem_gem_prime_import,
-	.gem_prime_pin			= vgem_gem_prime_pin,
-	.gem_prime_unpin		= vgem_gem_prime_unpin,
-	.gem_prime_get_sg_table		= vgem_gem_prime_get_sg_table,
-	.gem_prime_vmap			= vgem_gem_prime_vmap,
-	.gem_prime_vunmap		= vgem_gem_prime_vunmap,
 	.name	= DRIVER_NAME,
 	.desc	= DRIVER_DESC,
 	.date	= DRIVER_DATE,
diff --git a/drivers/gpu/drm/vgem/vgem_drv.h b/drivers/gpu/drm/vgem/vgem_drv.h
index 57ab4d8f41f9..e9f92f7ee275 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.h
+++ b/drivers/gpu/drm/vgem/vgem_drv.h
@@ -43,15 +43,4 @@ struct drm_vgem_gem_object {
 extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj);
 extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj);
 
-/* vgem_dma_buf.c */
-extern struct sg_table *vgem_gem_prime_get_sg_table(
-			struct drm_gem_object *gobj);
-extern int vgem_gem_prime_pin(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_unpin(struct drm_gem_object *gobj);
-extern void *vgem_gem_prime_vmap(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
-extern struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
-						    struct dma_buf *dma_buf);
-
-
 #endif
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 67bab5c36056..6d2f39d36e44 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1119,10 +1119,9 @@ static int ipu_irq_init(struct ipu_soc *ipu)
 		ct->regs.mask = IPU_INT_CTRL(i / 32);
 	}
 
-	irq_set_chained_handler(ipu->irq_sync, ipu_irq_handler);
-	irq_set_handler_data(ipu->irq_sync, ipu);
-	irq_set_chained_handler(ipu->irq_err, ipu_err_irq_handler);
-	irq_set_handler_data(ipu->irq_err, ipu);
+	irq_set_chained_handler_and_data(ipu->irq_sync, ipu_irq_handler, ipu);
+	irq_set_chained_handler_and_data(ipu->irq_err, ipu_err_irq_handler,
+					 ipu);
 
 	return 0;
 }
@@ -1131,10 +1130,8 @@ static void ipu_irq_exit(struct ipu_soc *ipu)
 {
 	int i, irq;
 
-	irq_set_chained_handler(ipu->irq_err, NULL);
-	irq_set_handler_data(ipu->irq_err, NULL);
-	irq_set_chained_handler(ipu->irq_sync, NULL);
-	irq_set_handler_data(ipu->irq_sync, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_err, NULL, NULL);
+	irq_set_chained_handler_and_data(ipu->irq_sync, NULL, NULL);
 
 	/* TODO: remove irq_domain_generic_chips */
 
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 15338afdf7f9..cc4c6649d195 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -634,7 +634,12 @@ config HID_PLANTRONICS
 	tristate "Plantronics USB HID Driver"
 	depends on HID
 	---help---
-	Provides HID support for Plantronics telephony devices.
+	  Provides HID support for Plantronics USB audio devices.
+	  Correctly maps vendor unique volume up/down HID usages to
+	  KEY_VOLUMEUP and KEY_VOLUMEDOWN events and prevents core mapping
+	  of other vendor unique HID usages to random mouse events.
+
+	  Say M here if you may ever plug in a Plantronics USB audio device.
 
 config HID_PRIMAX
 	tristate "Primax non-fully HID-compliant devices"
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index e4a21dfd7ef3..2f8a41dc3cc8 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -24,7 +24,7 @@ obj-$(CONFIG_HID_A4TECH)	+= hid-a4tech.o
 obj-$(CONFIG_HID_ACRUX)		+= hid-axff.o
 obj-$(CONFIG_HID_APPLE)		+= hid-apple.o
 obj-$(CONFIG_HID_APPLEIR)	+= hid-appleir.o
-obj-$(CONFIG_HID_AUREAL)        += hid-aureal.o
+obj-$(CONFIG_HID_AUREAL)	+= hid-aureal.o
 obj-$(CONFIG_HID_BELKIN)	+= hid-belkin.o
 obj-$(CONFIG_HID_BETOP_FF)	+= hid-betopff.o
 obj-$(CONFIG_HID_CHERRY)	+= hid-cherry.o
@@ -46,12 +46,12 @@ obj-$(CONFIG_HID_ICADE)		+= hid-icade.o
 obj-$(CONFIG_HID_KENSINGTON)	+= hid-kensington.o
 obj-$(CONFIG_HID_KEYTOUCH)	+= hid-keytouch.o
 obj-$(CONFIG_HID_KYE)		+= hid-kye.o
-obj-$(CONFIG_HID_LCPOWER)       += hid-lcpower.o
+obj-$(CONFIG_HID_LCPOWER)	+= hid-lcpower.o
 obj-$(CONFIG_HID_LENOVO)	+= hid-lenovo.o
 obj-$(CONFIG_HID_LOGITECH)	+= hid-logitech.o
 obj-$(CONFIG_HID_LOGITECH_DJ)	+= hid-logitech-dj.o
 obj-$(CONFIG_HID_LOGITECH_HIDPP)	+= hid-logitech-hidpp.o
-obj-$(CONFIG_HID_MAGICMOUSE)    += hid-magicmouse.o
+obj-$(CONFIG_HID_MAGICMOUSE)	+= hid-magicmouse.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
 obj-$(CONFIG_HID_MULTITOUCH)	+= hid-multitouch.o
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 722a925795a2..157c62775053 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -706,7 +706,8 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 
 	if (hid->vendor == USB_VENDOR_ID_MICROSOFT &&
 	    (hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3_JP) &&
+	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3_JP ||
+	     hid->product == USB_DEVICE_ID_MS_POWER_COVER) &&
 	    hid->group == HID_GROUP_MULTITOUCH)
 		hid->group = HID_GROUP_GENERIC;
 
@@ -1061,13 +1062,13 @@ static u32 s32ton(__s32 value, unsigned n)
  * Search linux-kernel and linux-usb-devel archives for "hid-core extract".
  */
 
-static __u32 extract(const struct hid_device *hid, __u8 *report,
+__u32 hid_field_extract(const struct hid_device *hid, __u8 *report,
 		     unsigned offset, unsigned n)
 {
 	u64 x;
 
 	if (n > 32)
-		hid_warn(hid, "extract() called with n (%d) > 32! (%s)\n",
+		hid_warn(hid, "hid_field_extract() called with n (%d) > 32! (%s)\n",
 			 n, current->comm);
 
 	report += offset >> 3;  /* adjust byte index */
@@ -1076,6 +1077,7 @@ static __u32 extract(const struct hid_device *hid, __u8 *report,
 	x = (x >> offset) & ((1ULL << n) - 1);  /* extract bit field */
 	return (u32) x;
 }
+EXPORT_SYMBOL_GPL(hid_field_extract);
 
 /*
  * "implement" : set bits in a little endian bit stream.
@@ -1221,9 +1223,9 @@ static void hid_input_field(struct hid_device *hid, struct hid_field *field,
 	for (n = 0; n < count; n++) {
 
 		value[n] = min < 0 ?
-			snto32(extract(hid, data, offset + n * size, size),
-			       size) :
-			extract(hid, data, offset + n * size, size);
+			snto32(hid_field_extract(hid, data, offset + n * size,
+			       size), size) :
+			hid_field_extract(hid, data, offset + n * size, size);
 
 		/* Ignore report if ErrorRollOver */
 		if (!(field->flags & HID_MAIN_ITEM_VARIABLE) &&
@@ -1851,6 +1853,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
@@ -1901,6 +1904,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_OFFICE_KB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
@@ -1959,9 +1963,12 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SMK, USB_DEVICE_ID_SMK_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_BUZZ_CONTROLLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_BDREMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS4_CONTROLLER) },
@@ -1997,6 +2004,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_3_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_DUAL_BOX_PRO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP_LTD, USB_DEVICE_ID_SUPER_JOY_BOX_5_PRO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_5_8_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_SLIM_TABLET_12_1_INCH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WALTOP, USB_DEVICE_ID_WALTOP_Q_PAD) },
@@ -2265,14 +2273,6 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0001) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0002) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0004) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_4_PHIDGETSERVO_30) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_1_PHIDGETSERVO_30) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_0_4_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_16_16_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_8_8_8_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_8_7_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_0_8_8_IF_KIT) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_PHIDGET_MOTORCONTROL) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_SUPER_Q2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_GOGOPEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GOTOP, USB_DEVICE_ID_PENPOWER) },
@@ -2399,14 +2399,6 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_WTP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DPAD) },
 #endif
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_LABPRO) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_GOTEMP) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_SKIP) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_CYCLOPS) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_VERNIER, USB_DEVICE_ID_VERNIER_LCSPEC) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_4_PHIDGETSERVO_20) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_1_PHIDGETSERVO_20) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_8_8_4_IF_KIT) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_RISO_KAGAKU, USB_DEVICE_ID_RI_KA_WEBMAIL) },
 	{ }
diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c
index c4ef3bc726e3..1b764d1745f3 100644
--- a/drivers/hid/hid-cypress.c
+++ b/drivers/hid/hid-cypress.c
@@ -41,13 +41,9 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 
 	for (i = 0; i < *rsize - 4; i++)
 		if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) {
-			__u8 tmp;
-
 			rdesc[i] = 0x19;
 			rdesc[i + 2] = 0x29;
-			tmp = rdesc[i + 3];
-			rdesc[i + 3] = rdesc[i + 1];
-			rdesc[i + 1] = tmp;
+			swap(rdesc[i + 3], rdesc[i + 1]);
 		}
 	return rdesc;
 }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 41f167e4d75f..b04b0820d816 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -164,6 +164,7 @@
 #define USB_DEVICE_ID_ATEN_2PORTKVM	0x2204
 #define USB_DEVICE_ID_ATEN_4PORTKVM	0x2205
 #define USB_DEVICE_ID_ATEN_4PORTKVMC	0x2208
+#define USB_DEVICE_ID_ATEN_CS682	0x2213
 
 #define USB_VENDOR_ID_ATMEL		0x03eb
 #define USB_DEVICE_ID_ATMEL_MULTITOUCH	0x211c
@@ -226,6 +227,7 @@
 #define USB_DEVICE_ID_CHICONY_TACTICAL_PAD	0x0418
 #define USB_DEVICE_ID_CHICONY_MULTI_TOUCH	0xb19d
 #define USB_DEVICE_ID_CHICONY_WIRELESS	0x0618
+#define USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE	0x1053
 #define USB_DEVICE_ID_CHICONY_WIRELESS2	0x1123
 #define USB_DEVICE_ID_CHICONY_AK1D	0x1125
 
@@ -362,16 +364,6 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
 
-#define USB_VENDOR_ID_GLAB		0x06c2
-#define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
-#define USB_DEVICE_ID_1_PHIDGETSERVO_30	0x0039
-#define USB_DEVICE_ID_0_0_4_IF_KIT	0x0040
-#define USB_DEVICE_ID_0_16_16_IF_KIT	0x0044
-#define USB_DEVICE_ID_8_8_8_IF_KIT	0x0045
-#define USB_DEVICE_ID_0_8_7_IF_KIT	0x0051
-#define USB_DEVICE_ID_0_8_8_IF_KIT	0x0053
-#define USB_DEVICE_ID_PHIDGET_MOTORCONTROL	0x0058
-
 #define USB_VENDOR_ID_GOODTOUCH		0x1aad
 #define USB_DEVICE_ID_GOODTOUCH_000f	0x000f
 
@@ -585,6 +577,7 @@
 #define USB_DEVICE_ID_LENOVO_TPKBD	0x6009
 #define USB_DEVICE_ID_LENOVO_CUSBKBD	0x6047
 #define USB_DEVICE_ID_LENOVO_CBTKBD	0x6048
+#define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
@@ -672,6 +665,7 @@
 #define USB_DEVICE_ID_MS_TYPE_COVER_2    0x07a9
 #define USB_DEVICE_ID_MS_TYPE_COVER_3    0x07dc
 #define USB_DEVICE_ID_MS_TYPE_COVER_3_JP 0x07dd
+#define USB_DEVICE_ID_MS_POWER_COVER     0x07da
 
 #define USB_VENDOR_ID_MOJO		0x8282
 #define USB_DEVICE_ID_RETRO_ADAPTER	0x3201
@@ -851,6 +845,7 @@
 #define USB_DEVICE_ID_SONY_PS3_BDREMOTE		0x0306
 #define USB_DEVICE_ID_SONY_PS3_CONTROLLER	0x0268
 #define USB_DEVICE_ID_SONY_PS4_CONTROLLER	0x05c4
+#define USB_DEVICE_ID_SONY_MOTION_CONTROLLER	0x03d5
 #define USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER	0x042f
 #define USB_DEVICE_ID_SONY_BUZZ_CONTROLLER		0x0002
 #define USB_DEVICE_ID_SONY_WIRELESS_BUZZ_CONTROLLER	0x1000
@@ -957,13 +952,6 @@
 #define USB_DEVICE_ID_VELLEMAN_K8061_FIRST	0x8061
 #define USB_DEVICE_ID_VELLEMAN_K8061_LAST	0x8068
 
-#define USB_VENDOR_ID_VERNIER		0x08f7
-#define USB_DEVICE_ID_VERNIER_LABPRO	0x0001
-#define USB_DEVICE_ID_VERNIER_GOTEMP	0x0002
-#define USB_DEVICE_ID_VERNIER_SKIP	0x0003
-#define USB_DEVICE_ID_VERNIER_CYCLOPS	0x0004
-#define USB_DEVICE_ID_VERNIER_LCSPEC	0x0006
-
 #define USB_VENDOR_ID_VTL		0x0306
 #define USB_DEVICE_ID_VTL_MULTITOUCH_FF3F	0xff3f
 
@@ -982,9 +970,6 @@
 
 #define USB_VENDOR_ID_WISEGROUP		0x0925
 #define USB_DEVICE_ID_SMARTJOY_PLUS	0x0005
-#define USB_DEVICE_ID_1_PHIDGETSERVO_20	0x8101
-#define USB_DEVICE_ID_4_PHIDGETSERVO_20	0x8104
-#define USB_DEVICE_ID_8_8_4_IF_KIT	0x8201
 #define USB_DEVICE_ID_SUPER_JOY_BOX_3	0x8888
 #define USB_DEVICE_ID_QUAD_USB_JOYPAD	0x8800
 #define USB_DEVICE_ID_DUAL_USB_JOYPAD	0x8866
@@ -1038,4 +1023,11 @@
 #define USB_VENDOR_ID_RISO_KAGAKU	0x1294	/* Riso Kagaku Corp. */
 #define USB_DEVICE_ID_RI_KA_WEBMAIL	0x1320	/* Webmail Notifier */
 
+#define USB_VENDOR_ID_MULTIPLE_1781	0x1781
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD	0x0a8d
+
+#define USB_VENDOR_ID_DRACAL_RAPHNET	0x289b
+#define USB_DEVICE_ID_RAPHNET_2NES2SNES	0x0002
+#define USB_DEVICE_ID_RAPHNET_4NES4SNES	0x0003
+
 #endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 008e89bf6f3c..3511bbaba505 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1157,7 +1157,8 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 
 	/* report the usage code as scancode if the key status has changed */
-	if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value)
+	if (usage->type == EV_KEY &&
+	    (!test_bit(usage->code, input->key)) == value)
 		input_event(input, EV_MSC, MSC_SCAN, usage->hid);
 
 	input_event(input, usage->type, usage->code, value);
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index c4c3f0952521..4f59bffd0205 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -43,6 +43,35 @@ struct lenovo_drvdata_cptkbd {
 
 #define map_key_clear(c) hid_map_usage_clear(hi, usage, bit, max, EV_KEY, (c))
 
+static const __u8 lenovo_pro_dock_need_fixup_collection[] = {
+	0x05, 0x88,		/* Usage Page (Vendor Usage Page 0x88)	*/
+	0x09, 0x01,		/* Usage (Vendor Usage 0x01)		*/
+	0xa1, 0x01,		/* Collection (Application)		*/
+	0x85, 0x04,		/*  Report ID (4)			*/
+	0x19, 0x00,		/*  Usage Minimum (0)			*/
+	0x2a, 0xff, 0xff,	/*  Usage Maximum (65535)		*/
+};
+
+static __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize)
+{
+	switch (hdev->product) {
+	case USB_DEVICE_ID_LENOVO_TPPRODOCK:
+		/* the fixups that need to be done:
+		 *   - get a reasonable usage max for the vendor collection
+		 *     0x8801 from the report ID 4
+		 */
+		if (*rsize >= 153 &&
+		    memcmp(&rdesc[140], lenovo_pro_dock_need_fixup_collection,
+			  sizeof(lenovo_pro_dock_need_fixup_collection)) == 0) {
+			rdesc[151] = 0x01;
+			rdesc[152] = 0x00;
+		}
+		break;
+	}
+	return rdesc;
+}
+
 static int lenovo_input_mapping_tpkbd(struct hid_device *hdev,
 		struct hid_input *hi, struct hid_field *field,
 		struct hid_usage *usage, unsigned long **bit, int *max)
@@ -599,7 +628,8 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 				    GFP_KERNEL);
 	if (data_pointer == NULL) {
 		hid_err(hdev, "Could not allocate memory for driver data\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 
 	// set same default values as windows driver
@@ -610,7 +640,8 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 	name_micmute = devm_kzalloc(&hdev->dev, name_sz, GFP_KERNEL);
 	if (name_mute == NULL || name_micmute == NULL) {
 		hid_err(hdev, "Could not allocate memory for led data\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err;
 	}
 	snprintf(name_mute, name_sz, "%s:amber:mute", dev_name(dev));
 	snprintf(name_micmute, name_sz, "%s:amber:micmute", dev_name(dev));
@@ -634,6 +665,9 @@ static int lenovo_probe_tpkbd(struct hid_device *hdev)
 	lenovo_features_set_tpkbd(hdev);
 
 	return 0;
+err:
+	sysfs_remove_group(&hdev->dev.kobj, &lenovo_attr_group_tpkbd);
+	return ret;
 }
 
 static int lenovo_probe_cptkbd(struct hid_device *hdev)
@@ -762,10 +796,29 @@ static void lenovo_remove(struct hid_device *hdev)
 	hid_hw_stop(hdev);
 }
 
+static void lenovo_input_configured(struct hid_device *hdev,
+		struct hid_input *hi)
+{
+	switch (hdev->product) {
+		case USB_DEVICE_ID_LENOVO_TPKBD:
+		case USB_DEVICE_ID_LENOVO_CUSBKBD:
+		case USB_DEVICE_ID_LENOVO_CBTKBD:
+			if (test_bit(EV_REL, hi->input->evbit)) {
+				/* set only for trackpoint device */
+				__set_bit(INPUT_PROP_POINTER, hi->input->propbit);
+				__set_bit(INPUT_PROP_POINTING_STICK,
+						hi->input->propbit);
+			}
+			break;
+	}
+}
+
+
 static const struct hid_device_id lenovo_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
 	{ }
 };
 
@@ -774,10 +827,12 @@ MODULE_DEVICE_TABLE(hid, lenovo_devices);
 static struct hid_driver lenovo_driver = {
 	.name = "lenovo",
 	.id_table = lenovo_devices,
+	.input_configured = lenovo_input_configured,
 	.input_mapping = lenovo_input_mapping,
 	.probe = lenovo_probe,
 	.remove = lenovo_remove,
 	.raw_event = lenovo_raw_event,
+	.report_fixup = lenovo_report_fixup,
 };
 module_hid_driver(lenovo_driver);
 
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index b86c18e651ed..429340d809b5 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -700,7 +700,8 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 			/* insert a little delay of 10 jiffies ~ 40ms */
 			wait_queue_head_t wait;
 			init_waitqueue_head (&wait);
-			wait_event_interruptible_timeout(wait, 0, 10);
+			wait_event_interruptible_timeout(wait, 0,
+							 msecs_to_jiffies(40));
 
 			/* Select random Address */
 			buf[1] = 0xB2;
@@ -712,13 +713,16 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 
 	if (drv_data->quirks & LG_FF)
-		lgff_init(hdev);
-	if (drv_data->quirks & LG_FF2)
-		lg2ff_init(hdev);
-	if (drv_data->quirks & LG_FF3)
-		lg3ff_init(hdev);
-	if (drv_data->quirks & LG_FF4)
-		lg4ff_init(hdev);
+		ret = lgff_init(hdev);
+	else if (drv_data->quirks & LG_FF2)
+		ret = lg2ff_init(hdev);
+	else if (drv_data->quirks & LG_FF3)
+		ret = lg3ff_init(hdev);
+	else if (drv_data->quirks & LG_FF4)
+		ret = lg4ff_init(hdev);
+
+	if (ret)
+		goto err_free;
 
 	return 0;
 err_free:
@@ -731,8 +735,8 @@ static void lg_remove(struct hid_device *hdev)
 	struct lg_drv_data *drv_data = hid_get_drvdata(hdev);
 	if (drv_data->quirks & LG_FF4)
 		lg4ff_deinit(hdev);
-
-	hid_hw_stop(hdev);
+	else
+		hid_hw_stop(hdev);
 	kfree(drv_data);
 }
 
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 1232210b1cc5..02cec83caac3 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -68,26 +68,32 @@
 #define LG4FF_FFEX_REV_MAJ 0x21
 #define LG4FF_FFEX_REV_MIN 0x00
 
-static void hid_lg4ff_set_range_dfp(struct hid_device *hid, u16 range);
-static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range);
-
-struct lg4ff_device_entry {
-	__u32 product_id;
-	__u16 range;
-	__u16 min_range;
-	__u16 max_range;
+static void lg4ff_set_range_dfp(struct hid_device *hid, u16 range);
+static void lg4ff_set_range_g25(struct hid_device *hid, u16 range);
+
+struct lg4ff_wheel_data {
+	const u32 product_id;
+	u16 range;
+	const u16 min_range;
+	const u16 max_range;
 #ifdef CONFIG_LEDS_CLASS
-	__u8  led_state;
+	u8  led_state;
 	struct led_classdev *led[5];
 #endif
-	u32 alternate_modes;
-	const char *real_tag;
-	const char *real_name;
-	u16 real_product_id;
-	struct list_head list;
+	const u32 alternate_modes;
+	const char * const real_tag;
+	const char * const real_name;
+	const u16 real_product_id;
+
 	void (*set_range)(struct hid_device *hid, u16 range);
 };
 
+struct lg4ff_device_entry {
+	spinlock_t report_lock; /* Protect output HID report */
+	struct hid_report *report;
+	struct lg4ff_wheel_data wdata;
+};
+
 static const signed short lg4ff_wheel_effects[] = {
 	FF_CONSTANT,
 	FF_AUTOCENTER,
@@ -95,16 +101,16 @@ static const signed short lg4ff_wheel_effects[] = {
 };
 
 struct lg4ff_wheel {
-	const __u32 product_id;
+	const u32 product_id;
 	const signed short *ff_effects;
-	const __u16 min_range;
-	const __u16 max_range;
+	const u16 min_range;
+	const u16 max_range;
 	void (*set_range)(struct hid_device *hid, u16 range);
 };
 
 struct lg4ff_compat_mode_switch {
-	const __u8 cmd_count;	/* Number of commands to send */
-	const __u8 cmd[];
+	const u8 cmd_count;	/* Number of commands to send */
+	const u8 cmd[];
 };
 
 struct lg4ff_wheel_ident_info {
@@ -134,10 +140,10 @@ struct lg4ff_alternate_mode {
 static const struct lg4ff_wheel lg4ff_devices[] = {
 	{USB_DEVICE_ID_LOGITECH_WHEEL,       lg4ff_wheel_effects, 40, 270, NULL},
 	{USB_DEVICE_ID_LOGITECH_MOMO_WHEEL,  lg4ff_wheel_effects, 40, 270, NULL},
-	{USB_DEVICE_ID_LOGITECH_DFP_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_dfp},
-	{USB_DEVICE_ID_LOGITECH_G25_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
-	{USB_DEVICE_ID_LOGITECH_DFGT_WHEEL,  lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
-	{USB_DEVICE_ID_LOGITECH_G27_WHEEL,   lg4ff_wheel_effects, 40, 900, hid_lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_DFP_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_dfp},
+	{USB_DEVICE_ID_LOGITECH_G25_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_DFGT_WHEEL,  lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
+	{USB_DEVICE_ID_LOGITECH_G27_WHEEL,   lg4ff_wheel_effects, 40, 900, lg4ff_set_range_g25},
 	{USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2, lg4ff_wheel_effects, 40, 270, NULL},
 	{USB_DEVICE_ID_LOGITECH_WII_WHEEL,   lg4ff_wheel_effects, 40, 270, NULL}
 };
@@ -245,10 +251,10 @@ static const struct lg4ff_compat_mode_switch lg4ff_mode_switch_ext16_g25 = {
 };
 
 /* Recalculates X axis value accordingly to currently selected range */
-static __s32 lg4ff_adjust_dfp_x_axis(__s32 value, __u16 range)
+static s32 lg4ff_adjust_dfp_x_axis(s32 value, u16 range)
 {
-	__u16 max_range;
-	__s32 new_value;
+	u16 max_range;
+	s32 new_value;
 
 	if (range == 900)
 		return value;
@@ -269,21 +275,21 @@ static __s32 lg4ff_adjust_dfp_x_axis(__s32 value, __u16 range)
 }
 
 int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-			     struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data)
+			     struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data)
 {
 	struct lg4ff_device_entry *entry = drv_data->device_props;
-	__s32 new_value = 0;
+	s32 new_value = 0;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found");
 		return 0;
 	}
 
-	switch (entry->product_id) {
+	switch (entry->wdata.product_id) {
 	case USB_DEVICE_ID_LOGITECH_DFP_WHEEL:
 		switch (usage->code) {
 		case ABS_X:
-			new_value = lg4ff_adjust_dfp_x_axis(value, entry->range);
+			new_value = lg4ff_adjust_dfp_x_axis(value, entry->wdata.range);
 			input_event(field->hidinput->input, usage->type, usage->code, new_value);
 			return 1;
 		default:
@@ -294,14 +300,56 @@ int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
 	}
 }
 
-static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *effect)
+static void lg4ff_init_wheel_data(struct lg4ff_wheel_data * const wdata, const struct lg4ff_wheel *wheel,
+				  const struct lg4ff_multimode_wheel *mmode_wheel,
+				  const u16 real_product_id)
+{
+	u32 alternate_modes = 0;
+	const char *real_tag = NULL;
+	const char *real_name = NULL;
+
+	if (mmode_wheel) {
+		alternate_modes = mmode_wheel->alternate_modes;
+		real_tag = mmode_wheel->real_tag;
+		real_name = mmode_wheel->real_name;
+	}
+
+	{
+		struct lg4ff_wheel_data t_wdata =  { .product_id = wheel->product_id,
+						     .real_product_id = real_product_id,
+						     .min_range = wheel->min_range,
+						     .max_range = wheel->max_range,
+						     .set_range = wheel->set_range,
+						     .alternate_modes = alternate_modes,
+						     .real_tag = real_tag,
+						     .real_name = real_name };
+
+		memcpy(wdata, &t_wdata, sizeof(t_wdata));
+	}
+}
+
+static int lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *effect)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	int x;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return -EINVAL;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return -EINVAL;
+	}
+	value = entry->report->field[0]->value;
+
 #define CLAMP(x) do { if (x < 0) x = 0; else if (x > 0xff) x = 0xff; } while (0)
 
 	switch (effect->type) {
@@ -309,6 +357,7 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 		x = effect->u.ramp.start_level + 0x80;	/* 0x80 is no force */
 		CLAMP(x);
 
+		spin_lock_irqsave(&entry->report_lock, flags);
 		if (x == 0x80) {
 			/* De-activate force in slot-1*/
 			value[0] = 0x13;
@@ -319,7 +368,8 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 			value[5] = 0x00;
 			value[6] = 0x00;
 
-			hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+			hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+			spin_unlock_irqrestore(&entry->report_lock, flags);
 			return 0;
 		}
 
@@ -331,7 +381,8 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 		value[5] = 0x00;
 		value[6] = 0x00;
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		break;
 	}
 	return 0;
@@ -339,15 +390,16 @@ static int hid_lg4ff_play(struct input_dev *dev, void *data, struct ff_effect *e
 
 /* Sends default autocentering command compatible with
  * all wheels except Formula Force EX */
-static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitude)
+static void lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitude)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
 	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
-	__u32 expand_a, expand_b;
+	s32 *value = report->field[0]->value;
+	u32 expand_a, expand_b;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
+	unsigned long flags;
 
 	drv_data = hid_get_drvdata(hid);
 	if (!drv_data) {
@@ -360,8 +412,10 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 		hid_err(hid, "Device properties not found!\n");
 		return;
 	}
+	value = entry->report->field[0]->value;
 
 	/* De-activate Auto-Center */
+	spin_lock_irqsave(&entry->report_lock, flags);
 	if (magnitude == 0) {
 		value[0] = 0xf5;
 		value[1] = 0x00;
@@ -371,7 +425,8 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 		value[5] = 0x00;
 		value[6] = 0x00;
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		return;
 	}
 
@@ -384,7 +439,7 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	}
 
 	/* Adjust for non-MOMO wheels */
-	switch (entry->product_id) {
+	switch (entry->wdata.product_id) {
 	case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL:
 	case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
 		break;
@@ -401,7 +456,7 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 
 	/* Activate Auto-Center */
 	value[0] = 0x14;
@@ -412,18 +467,34 @@ static void hid_lg4ff_set_autocenter_default(struct input_dev *dev, u16 magnitud
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends autocentering command compatible with Formula Force EX */
-static void hid_lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
+static void lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	magnitude = magnitude * 90 / 65535;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
+
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xfe;
 	value[1] = 0x03;
 	value[2] = magnitude >> 14;
@@ -432,18 +503,33 @@ static void hid_lg4ff_set_autocenter_ffex(struct input_dev *dev, u16 magnitude)
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends command to set range compatible with G25/G27/Driving Force GT */
-static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range)
+static void lg4ff_set_range_g25(struct hid_device *hid, u16 range)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 	dbg_hid("G25/G27/DFGT: setting range to %u\n", range);
 
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x81;
 	value[2] = range & 0x00ff;
@@ -452,20 +538,35 @@ static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range)
 	value[5] = 0x00;
 	value[6] = 0x00;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 /* Sends commands to set range compatible with Driving Force Pro wheel */
-static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
+static void lg4ff_set_range_dfp(struct hid_device *hid, u16 range)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
 	int start_left, start_right, full_range;
-	__s32 *value = report->field[0]->value;
+	s32 *value;
+
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
 
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 	dbg_hid("Driving Force Pro: setting range to %u\n", range);
 
 	/* Prepare "coarse" limit command */
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x00;	/* Set later */
 	value[2] = 0x00;
@@ -475,13 +576,13 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[6] = 0x00;
 
 	if (range > 200) {
-		report->field[0]->value[1] = 0x03;
+		value[1] = 0x03;
 		full_range = 900;
 	} else {
-		report->field[0]->value[1] = 0x02;
+		value[1] = 0x02;
 		full_range = 200;
 	}
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 
 	/* Prepare "fine" limit command */
 	value[0] = 0x81;
@@ -493,7 +594,8 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[6] = 0x00;
 
 	if (range == 200 || range == 900) {	/* Do not apply any fine limit */
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+		spin_unlock_irqrestore(&entry->report_lock, flags);
 		return;
 	}
 
@@ -507,7 +609,8 @@ static void hid_lg4ff_set_range_dfp(struct hid_device *hid, __u16 range)
 	value[5] = (start_right & 0xe) << 4 | (start_left & 0xe);
 	value[6] = 0xff;
 
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 static const struct lg4ff_compat_mode_switch *lg4ff_get_mode_switch_command(const u16 real_product_id, const u16 target_product_id)
@@ -569,19 +672,35 @@ static const struct lg4ff_compat_mode_switch *lg4ff_get_mode_switch_command(cons
 
 static int lg4ff_switch_compatibility_mode(struct hid_device *hid, const struct lg4ff_compat_mode_switch *s)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg4ff_device_entry *entry;
+	struct lg_drv_data *drv_data;
+	unsigned long flags;
+	s32 *value;
 	u8 i;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return -EINVAL;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return -EINVAL;
+	}
+	value = entry->report->field[0]->value;
+
+	spin_lock_irqsave(&entry->report_lock, flags);
 	for (i = 0; i < s->cmd_count; i++) {
 		u8 j;
 
 		for (j = 0; j < 7; j++)
 			value[j] = s->cmd[j + (7*i)];
 
-		hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+		hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
 	}
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 	hid_hw_wait(hid);
 	return 0;
 }
@@ -606,23 +725,23 @@ static ssize_t lg4ff_alternate_modes_show(struct device *dev, struct device_attr
 		return 0;
 	}
 
-	if (!entry->real_name) {
+	if (!entry->wdata.real_name) {
 		hid_err(hid, "NULL pointer to string\n");
 		return 0;
 	}
 
 	for (i = 0; i < LG4FF_MODE_MAX_IDX; i++) {
-		if (entry->alternate_modes & BIT(i)) {
+		if (entry->wdata.alternate_modes & BIT(i)) {
 			/* Print tag and full name */
 			count += scnprintf(buf + count, PAGE_SIZE - count, "%s: %s",
 					   lg4ff_alternate_modes[i].tag,
-					   !lg4ff_alternate_modes[i].product_id ? entry->real_name : lg4ff_alternate_modes[i].name);
+					   !lg4ff_alternate_modes[i].product_id ? entry->wdata.real_name : lg4ff_alternate_modes[i].name);
 			if (count >= PAGE_SIZE - 1)
 				return count;
 
 			/* Mark the currently active mode with an asterisk */
-			if (lg4ff_alternate_modes[i].product_id == entry->product_id ||
-			    (lg4ff_alternate_modes[i].product_id == 0 && entry->product_id == entry->real_product_id))
+			if (lg4ff_alternate_modes[i].product_id == entry->wdata.product_id ||
+			    (lg4ff_alternate_modes[i].product_id == 0 && entry->wdata.product_id == entry->wdata.real_product_id))
 				count += scnprintf(buf + count, PAGE_SIZE - count, " *\n");
 			else
 				count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
@@ -675,10 +794,10 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 		const u16 mode_product_id = lg4ff_alternate_modes[i].product_id;
 		const char *tag = lg4ff_alternate_modes[i].tag;
 
-		if (entry->alternate_modes & BIT(i)) {
+		if (entry->wdata.alternate_modes & BIT(i)) {
 			if (!strcmp(tag, lbuf)) {
 				if (!mode_product_id)
-					target_product_id = entry->real_product_id;
+					target_product_id = entry->wdata.real_product_id;
 				else
 					target_product_id = mode_product_id;
 				break;
@@ -693,24 +812,24 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 	}
 	kfree(lbuf); /* Not needed anymore */
 
-	if (target_product_id == entry->product_id) /* Nothing to do */
+	if (target_product_id == entry->wdata.product_id) /* Nothing to do */
 		return count;
 
 	/* Automatic switching has to be disabled for the switch to DF-EX mode to work correctly */
 	if (target_product_id == USB_DEVICE_ID_LOGITECH_WHEEL && !lg4ff_no_autoswitch) {
 		hid_info(hid, "\"%s\" cannot be switched to \"DF-EX\" mode. Load the \"hid_logitech\" module with \"lg4ff_no_autoswitch=1\" parameter set and try again\n",
-			 entry->real_name);
+			 entry->wdata.real_name);
 		return -EINVAL;
 	}
 
 	/* Take care of hardware limitations */
-	if ((entry->real_product_id == USB_DEVICE_ID_LOGITECH_DFP_WHEEL || entry->real_product_id == USB_DEVICE_ID_LOGITECH_G25_WHEEL) &&
-	    entry->product_id > target_product_id) {
-		hid_info(hid, "\"%s\" cannot be switched back into \"%s\" mode\n", entry->real_name, lg4ff_alternate_modes[i].name);
+	if ((entry->wdata.real_product_id == USB_DEVICE_ID_LOGITECH_DFP_WHEEL || entry->wdata.real_product_id == USB_DEVICE_ID_LOGITECH_G25_WHEEL) &&
+	    entry->wdata.product_id > target_product_id) {
+		hid_info(hid, "\"%s\" cannot be switched back into \"%s\" mode\n", entry->wdata.real_name, lg4ff_alternate_modes[i].name);
 		return -EINVAL;
 	}
 
-	s = lg4ff_get_mode_switch_command(entry->real_product_id, target_product_id);
+	s = lg4ff_get_mode_switch_command(entry->wdata.real_product_id, target_product_id);
 	if (!s) {
 		hid_err(hid, "Invalid target product ID %X\n", target_product_id);
 		return -EINVAL;
@@ -721,9 +840,9 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att
 }
 static DEVICE_ATTR(alternate_modes, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, lg4ff_alternate_modes_show, lg4ff_alternate_modes_store);
 
-/* Read current range and display it in terminal */
-static ssize_t range_show(struct device *dev, struct device_attribute *attr,
-			  char *buf)
+/* Export the currently set range of the wheel */
+static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
 {
 	struct hid_device *hid = to_hid_device(dev);
 	struct lg4ff_device_entry *entry;
@@ -742,19 +861,19 @@ static ssize_t range_show(struct device *dev, struct device_attribute *attr,
 		return 0;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%u\n", entry->range);
+	count = scnprintf(buf, PAGE_SIZE, "%u\n", entry->wdata.range);
 	return count;
 }
 
 /* Set range to user specified value, call appropriate function
  * according to the type of the wheel */
-static ssize_t range_store(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct hid_device *hid = to_hid_device(dev);
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
-	__u16 range = simple_strtoul(buf, NULL, 10);
+	u16 range = simple_strtoul(buf, NULL, 10);
 
 	drv_data = hid_get_drvdata(hid);
 	if (!drv_data) {
@@ -769,18 +888,18 @@ static ssize_t range_store(struct device *dev, struct device_attribute *attr,
 	}
 
 	if (range == 0)
-		range = entry->max_range;
+		range = entry->wdata.max_range;
 
 	/* Check if the wheel supports range setting
 	 * and that the range is within limits for the wheel */
-	if (entry->set_range != NULL && range >= entry->min_range && range <= entry->max_range) {
-		entry->set_range(hid, range);
-		entry->range = range;
+	if (entry->wdata.set_range && range >= entry->wdata.min_range && range <= entry->wdata.max_range) {
+		entry->wdata.set_range(hid, range);
+		entry->wdata.range = range;
 	}
 
 	return count;
 }
-static DEVICE_ATTR_RW(range);
+static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, lg4ff_range_show, lg4ff_range_store);
 
 static ssize_t lg4ff_real_id_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -801,12 +920,12 @@ static ssize_t lg4ff_real_id_show(struct device *dev, struct device_attribute *a
 		return 0;
 	}
 
-	if (!entry->real_tag || !entry->real_name) {
+	if (!entry->wdata.real_tag || !entry->wdata.real_name) {
 		hid_err(hid, "NULL pointer to string\n");
 		return 0;
 	}
 
-	count = scnprintf(buf, PAGE_SIZE, "%s: %s\n", entry->real_tag, entry->real_name);
+	count = scnprintf(buf, PAGE_SIZE, "%s: %s\n", entry->wdata.real_tag, entry->wdata.real_name);
 	return count;
 }
 
@@ -818,12 +937,27 @@ static ssize_t lg4ff_real_id_store(struct device *dev, struct device_attribute *
 static DEVICE_ATTR(real_id, S_IRUGO, lg4ff_real_id_show, lg4ff_real_id_store);
 
 #ifdef CONFIG_LEDS_CLASS
-static void lg4ff_set_leds(struct hid_device *hid, __u8 leds)
+static void lg4ff_set_leds(struct hid_device *hid, u8 leds)
 {
-	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
-	__s32 *value = report->field[0]->value;
+	struct lg_drv_data *drv_data;
+	struct lg4ff_device_entry *entry;
+	unsigned long flags;
+	s32 *value;
+
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Private driver data not found!\n");
+		return;
+	}
+
+	entry = drv_data->device_props;
+	if (!entry) {
+		hid_err(hid, "Device properties not found!\n");
+		return;
+	}
+	value = entry->report->field[0]->value;
 
+	spin_lock_irqsave(&entry->report_lock, flags);
 	value[0] = 0xf8;
 	value[1] = 0x12;
 	value[2] = leds;
@@ -831,7 +965,8 @@ static void lg4ff_set_leds(struct hid_device *hid, __u8 leds)
 	value[4] = 0x00;
 	value[5] = 0x00;
 	value[6] = 0x00;
-	hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+	hid_hw_request(hid, entry->report, HID_REQ_SET_REPORT);
+	spin_unlock_irqrestore(&entry->report_lock, flags);
 }
 
 static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
@@ -848,7 +983,7 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
 		return;
 	}
 
-	entry = (struct lg4ff_device_entry *)drv_data->device_props;
+	entry = drv_data->device_props;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found.");
@@ -856,15 +991,15 @@ static void lg4ff_led_set_brightness(struct led_classdev *led_cdev,
 	}
 
 	for (i = 0; i < 5; i++) {
-		if (led_cdev != entry->led[i])
+		if (led_cdev != entry->wdata.led[i])
 			continue;
-		state = (entry->led_state >> i) & 1;
+		state = (entry->wdata.led_state >> i) & 1;
 		if (value == LED_OFF && state) {
-			entry->led_state &= ~(1 << i);
-			lg4ff_set_leds(hid, entry->led_state);
+			entry->wdata.led_state &= ~(1 << i);
+			lg4ff_set_leds(hid, entry->wdata.led_state);
 		} else if (value != LED_OFF && !state) {
-			entry->led_state |= 1 << i;
-			lg4ff_set_leds(hid, entry->led_state);
+			entry->wdata.led_state |= 1 << i;
+			lg4ff_set_leds(hid, entry->wdata.led_state);
 		}
 		break;
 	}
@@ -883,7 +1018,7 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 		return LED_OFF;
 	}
 
-	entry = (struct lg4ff_device_entry *)drv_data->device_props;
+	entry = drv_data->device_props;
 
 	if (!entry) {
 		hid_err(hid, "Device properties not found.");
@@ -891,8 +1026,8 @@ static enum led_brightness lg4ff_led_get_brightness(struct led_classdev *led_cde
 	}
 
 	for (i = 0; i < 5; i++)
-		if (led_cdev == entry->led[i]) {
-			value = (entry->led_state >> i) & 1;
+		if (led_cdev == entry->wdata.led[i]) {
+			value = (entry->wdata.led_state >> i) & 1;
 			break;
 		}
 
@@ -991,8 +1126,11 @@ int lg4ff_init(struct hid_device *hid)
 {
 	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
 	struct input_dev *dev = hidinput->input;
+	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
+	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
 	const u16 bcdDevice = le16_to_cpu(udesc->bcdDevice);
+	const struct lg4ff_multimode_wheel *mmode_wheel = NULL;
 	struct lg4ff_device_entry *entry;
 	struct lg_drv_data *drv_data;
 	int error, i, j;
@@ -1003,6 +1141,18 @@ int lg4ff_init(struct hid_device *hid)
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
 
+	drv_data = hid_get_drvdata(hid);
+	if (!drv_data) {
+		hid_err(hid, "Cannot add device, private driver data not allocated\n");
+		return -1;
+	}
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+	spin_lock_init(&entry->report_lock);
+	entry->report = report;
+	drv_data->device_props = entry;
+
 	/* Check if a multimode wheel has been connected and
 	 * handle it appropriately */
 	mmode_ret = lg4ff_handle_multimode_wheel(hid, &real_product_id, bcdDevice);
@@ -1012,6 +1162,11 @@ int lg4ff_init(struct hid_device *hid)
 	 */
 	if (mmode_ret == LG4FF_MMODE_SWITCHED)
 		return 0;
+	else if (mmode_ret < 0) {
+		hid_err(hid, "Unable to switch device mode during initialization, errno %d\n", mmode_ret);
+		error = mmode_ret;
+		goto err_init;
+	}
 
 	/* Check what wheel has been connected */
 	for (i = 0; i < ARRAY_SIZE(lg4ff_devices); i++) {
@@ -1022,9 +1177,11 @@ int lg4ff_init(struct hid_device *hid)
 	}
 
 	if (i == ARRAY_SIZE(lg4ff_devices)) {
-		hid_err(hid, "Device is not supported by lg4ff driver. If you think it should be, consider reporting a bug to"
-			     "LKML, Simon Wood <simon@mungewell.org> or Michal Maly <madcatxster@gmail.com>\n");
-		return -1;
+		hid_err(hid, "This device is flagged to be handled by the lg4ff module but this module does not know how to handle it. "
+			     "Please report this as a bug to LKML, Simon Wood <simon@mungewell.org> or "
+			     "Michal Maly <madcatxster@devoid-pointer.net>\n");
+		error = -1;
+		goto err_init;
 	}
 
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
@@ -1035,7 +1192,8 @@ int lg4ff_init(struct hid_device *hid)
 
 		if (mmode_idx == ARRAY_SIZE(lg4ff_multimode_wheels)) {
 			hid_err(hid, "Device product ID %X is not listed as a multimode wheel", real_product_id);
-			return -1;
+			error = -1;
+			goto err_init;
 		}
 	}
 
@@ -1043,37 +1201,17 @@ int lg4ff_init(struct hid_device *hid)
 	for (j = 0; lg4ff_devices[i].ff_effects[j] >= 0; j++)
 		set_bit(lg4ff_devices[i].ff_effects[j], dev->ffbit);
 
-	error = input_ff_create_memless(dev, NULL, hid_lg4ff_play);
+	error = input_ff_create_memless(dev, NULL, lg4ff_play);
 
 	if (error)
-		return error;
-
-	/* Get private driver data */
-	drv_data = hid_get_drvdata(hid);
-	if (!drv_data) {
-		hid_err(hid, "Cannot add device, private driver data not allocated\n");
-		return -1;
-	}
+		goto err_init;
 
 	/* Initialize device properties */
-	entry = kzalloc(sizeof(struct lg4ff_device_entry), GFP_KERNEL);
-	if (!entry) {
-		hid_err(hid, "Cannot add device, insufficient memory to allocate device properties.\n");
-		return -ENOMEM;
-	}
-	drv_data->device_props = entry;
-
-	entry->product_id = lg4ff_devices[i].product_id;
-	entry->real_product_id = real_product_id;
-	entry->min_range = lg4ff_devices[i].min_range;
-	entry->max_range = lg4ff_devices[i].max_range;
-	entry->set_range = lg4ff_devices[i].set_range;
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
 		BUG_ON(mmode_idx == -1);
-		entry->alternate_modes = lg4ff_multimode_wheels[mmode_idx].alternate_modes;
-		entry->real_tag = lg4ff_multimode_wheels[mmode_idx].real_tag;
-		entry->real_name = lg4ff_multimode_wheels[mmode_idx].real_name;
+		mmode_wheel = &lg4ff_multimode_wheels[mmode_idx];
 	}
+	lg4ff_init_wheel_data(&entry->wdata, &lg4ff_devices[i], mmode_wheel, real_product_id);
 
 	/* Check if autocentering is available and
 	 * set the centering force to zero by default */
@@ -1081,9 +1219,9 @@ int lg4ff_init(struct hid_device *hid)
 		/* Formula Force EX expects different autocentering command */
 		if ((bcdDevice >> 8) == LG4FF_FFEX_REV_MAJ &&
 		    (bcdDevice & 0xff) == LG4FF_FFEX_REV_MIN)
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
+			dev->ff->set_autocenter = lg4ff_set_autocenter_ffex;
 		else
-			dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
+			dev->ff->set_autocenter = lg4ff_set_autocenter_default;
 
 		dev->ff->set_autocenter(dev, 0);
 	}
@@ -1091,27 +1229,27 @@ int lg4ff_init(struct hid_device *hid)
 	/* Create sysfs interface */
 	error = device_create_file(&hid->dev, &dev_attr_range);
 	if (error)
-		return error;
+		hid_warn(hid, "Unable to create sysfs interface for \"range\", errno %d\n", error);
 	if (mmode_ret == LG4FF_MMODE_IS_MULTIMODE) {
 		error = device_create_file(&hid->dev, &dev_attr_real_id);
 		if (error)
-			return error;
+			hid_warn(hid, "Unable to create sysfs interface for \"real_id\", errno %d\n", error);
 		error = device_create_file(&hid->dev, &dev_attr_alternate_modes);
 		if (error)
-			return error;
+			hid_warn(hid, "Unable to create sysfs interface for \"alternate_modes\", errno %d\n", error);
 	}
 	dbg_hid("sysfs interface created\n");
 
 	/* Set the maximum range to start with */
-	entry->range = entry->max_range;
-	if (entry->set_range != NULL)
-		entry->set_range(hid, entry->range);
+	entry->wdata.range = entry->wdata.max_range;
+	if (entry->wdata.set_range)
+		entry->wdata.set_range(hid, entry->wdata.range);
 
 #ifdef CONFIG_LEDS_CLASS
 	/* register led subsystem - G27 only */
-	entry->led_state = 0;
+	entry->wdata.led_state = 0;
 	for (j = 0; j < 5; j++)
-		entry->led[j] = NULL;
+		entry->wdata.led[j] = NULL;
 
 	if (lg4ff_devices[i].product_id == USB_DEVICE_ID_LOGITECH_G27_WHEEL) {
 		struct led_classdev *led;
@@ -1126,7 +1264,7 @@ int lg4ff_init(struct hid_device *hid)
 			led = kzalloc(sizeof(struct led_classdev)+name_sz, GFP_KERNEL);
 			if (!led) {
 				hid_err(hid, "can't allocate memory for LED %d\n", j);
-				goto err;
+				goto err_leds;
 			}
 
 			name = (void *)(&led[1]);
@@ -1137,16 +1275,16 @@ int lg4ff_init(struct hid_device *hid)
 			led->brightness_get = lg4ff_led_get_brightness;
 			led->brightness_set = lg4ff_led_set_brightness;
 
-			entry->led[j] = led;
+			entry->wdata.led[j] = led;
 			error = led_classdev_register(&hid->dev, led);
 
 			if (error) {
 				hid_err(hid, "failed to register LED %d. Aborting.\n", j);
-err:
+err_leds:
 				/* Deregister LEDs (if any) */
 				for (j = 0; j < 5; j++) {
-					led = entry->led[j];
-					entry->led[j] = NULL;
+					led = entry->wdata.led[j];
+					entry->wdata.led[j] = NULL;
 					if (!led)
 						continue;
 					led_classdev_unregister(led);
@@ -1160,6 +1298,11 @@ out:
 #endif
 	hid_info(hid, "Force feedback support for Logitech Gaming Wheels\n");
 	return 0;
+
+err_init:
+	drv_data->device_props = NULL;
+	kfree(entry);
+	return error;
 }
 
 int lg4ff_deinit(struct hid_device *hid)
@@ -1176,14 +1319,13 @@ int lg4ff_deinit(struct hid_device *hid)
 	if (!entry)
 		goto out; /* Nothing more to do */
 
-	device_remove_file(&hid->dev, &dev_attr_range);
-
 	/* Multimode devices will have at least the "MODE_NATIVE" bit set */
-	if (entry->alternate_modes) {
+	if (entry->wdata.alternate_modes) {
 		device_remove_file(&hid->dev, &dev_attr_real_id);
 		device_remove_file(&hid->dev, &dev_attr_alternate_modes);
 	}
 
+	device_remove_file(&hid->dev, &dev_attr_range);
 #ifdef CONFIG_LEDS_CLASS
 	{
 		int j;
@@ -1192,8 +1334,8 @@ int lg4ff_deinit(struct hid_device *hid)
 		/* Deregister LEDs (if any) */
 		for (j = 0; j < 5; j++) {
 
-			led = entry->led[j];
-			entry->led[j] = NULL;
+			led = entry->wdata.led[j];
+			entry->wdata.led[j] = NULL;
 			if (!led)
 				continue;
 			led_classdev_unregister(led);
@@ -1201,10 +1343,10 @@ int lg4ff_deinit(struct hid_device *hid)
 		}
 	}
 #endif
+	hid_hw_stop(hid);
+	drv_data->device_props = NULL;
 
-	/* Deallocate memory */
 	kfree(entry);
-
 out:
 	dbg_hid("Device successfully unregistered\n");
 	return 0;
diff --git a/drivers/hid/hid-lg4ff.h b/drivers/hid/hid-lg4ff.h
index 5b6a5086c47f..66201af44da3 100644
--- a/drivers/hid/hid-lg4ff.h
+++ b/drivers/hid/hid-lg4ff.h
@@ -5,12 +5,12 @@
 extern int lg4ff_no_autoswitch; /* From hid-lg.c */
 
 int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-			     struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data);
+			     struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data);
 int lg4ff_init(struct hid_device *hdev);
 int lg4ff_deinit(struct hid_device *hdev);
 #else
 static inline int lg4ff_adjust_input_event(struct hid_device *hid, struct hid_field *field,
-					   struct hid_usage *usage, __s32 value, struct lg_drv_data *drv_data) { return 0; }
+					   struct hid_usage *usage, s32 value, struct lg_drv_data *drv_data) { return 0; }
 static inline int lg4ff_init(struct hid_device *hdev) { return -1; }
 static inline int lg4ff_deinit(struct hid_device *hdev) { return -1; }
 #endif
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index b3cf6fd4be96..484196459305 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -40,11 +40,11 @@ MODULE_PARM_DESC(disable_raw_mode,
 #define HIDPP_REPORT_LONG_LENGTH		20
 
 #define HIDPP_QUIRK_CLASS_WTP			BIT(0)
+#define HIDPP_QUIRK_CLASS_M560			BIT(1)
 
-/* bits 1..20 are reserved for classes */
+/* bits 2..20 are reserved for classes */
 #define HIDPP_QUIRK_DELAYED_INIT		BIT(21)
 #define HIDPP_QUIRK_WTP_PHYSICAL_BUTTONS	BIT(22)
-#define HIDPP_QUIRK_MULTI_INPUT			BIT(23)
 
 /*
  * There are two hidpp protocols in use, the first version hidpp10 is known
@@ -706,12 +706,6 @@ static int wtp_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
 {
-	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
-
-	if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) &&
-	    (field->application == HID_GD_KEYBOARD))
-		return 0;
-
 	return -1;
 }
 
@@ -720,10 +714,6 @@ static void wtp_populate_input(struct hidpp_device *hidpp,
 {
 	struct wtp_data *wd = hidpp->private_data;
 
-	if ((hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT) && origin_is_hid_core)
-		/* this is the generic hid-input call */
-		return;
-
 	__set_bit(EV_ABS, input_dev->evbit);
 	__set_bit(EV_KEY, input_dev->evbit);
 	__clear_bit(EV_REL, input_dev->evbit);
@@ -941,6 +931,207 @@ static int wtp_connect(struct hid_device *hdev, bool connected)
 			true, true);
 }
 
+/* ------------------------------------------------------------------------- */
+/* Logitech M560 devices                                                     */
+/* ------------------------------------------------------------------------- */
+
+/*
+ * Logitech M560 protocol overview
+ *
+ * The Logitech M560 mouse, is designed for windows 8. When the middle and/or
+ * the sides buttons are pressed, it sends some keyboard keys events
+ * instead of buttons ones.
+ * To complicate things further, the middle button keys sequence
+ * is different from the odd press and the even press.
+ *
+ * forward button -> Super_R
+ * backward button -> Super_L+'d' (press only)
+ * middle button -> 1st time: Alt_L+SuperL+XF86TouchpadOff (press only)
+ *                  2nd time: left-click (press only)
+ * NB: press-only means that when the button is pressed, the
+ * KeyPress/ButtonPress and KeyRelease/ButtonRelease events are generated
+ * together sequentially; instead when the button is released, no event is
+ * generated !
+ *
+ * With the command
+ *	10<xx>0a 3500af03 (where <xx> is the mouse id),
+ * the mouse reacts differently:
+ * - it never sends a keyboard key event
+ * - for the three mouse button it sends:
+ *	middle button               press   11<xx>0a 3500af00...
+ *	side 1 button (forward)     press   11<xx>0a 3500b000...
+ *	side 2 button (backward)    press   11<xx>0a 3500ae00...
+ *	middle/side1/side2 button   release 11<xx>0a 35000000...
+ */
+
+static const u8 m560_config_parameter[] = {0x00, 0xaf, 0x03};
+
+struct m560_private_data {
+	struct input_dev *input;
+};
+
+/* how buttons are mapped in the report */
+#define M560_MOUSE_BTN_LEFT		0x01
+#define M560_MOUSE_BTN_RIGHT		0x02
+#define M560_MOUSE_BTN_WHEEL_LEFT	0x08
+#define M560_MOUSE_BTN_WHEEL_RIGHT	0x10
+
+#define M560_SUB_ID			0x0a
+#define M560_BUTTON_MODE_REGISTER	0x35
+
+static int m560_send_config_command(struct hid_device *hdev, bool connected)
+{
+	struct hidpp_report response;
+	struct hidpp_device *hidpp_dev;
+
+	hidpp_dev = hid_get_drvdata(hdev);
+
+	if (!connected)
+		return -ENODEV;
+
+	return hidpp_send_rap_command_sync(
+		hidpp_dev,
+		REPORT_ID_HIDPP_SHORT,
+		M560_SUB_ID,
+		M560_BUTTON_MODE_REGISTER,
+		(u8 *)m560_config_parameter,
+		sizeof(m560_config_parameter),
+		&response
+	);
+}
+
+static int m560_allocate(struct hid_device *hdev)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct m560_private_data *d;
+
+	d = devm_kzalloc(&hdev->dev, sizeof(struct m560_private_data),
+			GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	hidpp->private_data = d;
+
+	return 0;
+};
+
+static int m560_raw_event(struct hid_device *hdev, u8 *data, int size)
+{
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	struct m560_private_data *mydata = hidpp->private_data;
+
+	/* sanity check */
+	if (!mydata || !mydata->input) {
+		hid_err(hdev, "error in parameter\n");
+		return -EINVAL;
+	}
+
+	if (size < 7) {
+		hid_err(hdev, "error in report\n");
+		return 0;
+	}
+
+	if (data[0] == REPORT_ID_HIDPP_LONG &&
+	    data[2] == M560_SUB_ID && data[6] == 0x00) {
+		/*
+		 * m560 mouse report for middle, forward and backward button
+		 *
+		 * data[0] = 0x11
+		 * data[1] = device-id
+		 * data[2] = 0x0a
+		 * data[5] = 0xaf -> middle
+		 *	     0xb0 -> forward
+		 *	     0xae -> backward
+		 *	     0x00 -> release all
+		 * data[6] = 0x00
+		 */
+
+		switch (data[5]) {
+		case 0xaf:
+			input_report_key(mydata->input, BTN_MIDDLE, 1);
+			break;
+		case 0xb0:
+			input_report_key(mydata->input, BTN_FORWARD, 1);
+			break;
+		case 0xae:
+			input_report_key(mydata->input, BTN_BACK, 1);
+			break;
+		case 0x00:
+			input_report_key(mydata->input, BTN_BACK, 0);
+			input_report_key(mydata->input, BTN_FORWARD, 0);
+			input_report_key(mydata->input, BTN_MIDDLE, 0);
+			break;
+		default:
+			hid_err(hdev, "error in report\n");
+			return 0;
+		}
+		input_sync(mydata->input);
+
+	} else if (data[0] == 0x02) {
+		/*
+		 * Logitech M560 mouse report
+		 *
+		 * data[0] = type (0x02)
+		 * data[1..2] = buttons
+		 * data[3..5] = xy
+		 * data[6] = wheel
+		 */
+
+		int v;
+
+		input_report_key(mydata->input, BTN_LEFT,
+			!!(data[1] & M560_MOUSE_BTN_LEFT));
+		input_report_key(mydata->input, BTN_RIGHT,
+			!!(data[1] & M560_MOUSE_BTN_RIGHT));
+
+		if (data[1] & M560_MOUSE_BTN_WHEEL_LEFT)
+			input_report_rel(mydata->input, REL_HWHEEL, -1);
+		else if (data[1] & M560_MOUSE_BTN_WHEEL_RIGHT)
+			input_report_rel(mydata->input, REL_HWHEEL, 1);
+
+		v = hid_snto32(hid_field_extract(hdev, data+3, 0, 12), 12);
+		input_report_rel(mydata->input, REL_X, v);
+
+		v = hid_snto32(hid_field_extract(hdev, data+3, 12, 12), 12);
+		input_report_rel(mydata->input, REL_Y, v);
+
+		v = hid_snto32(data[6], 8);
+		input_report_rel(mydata->input, REL_WHEEL, v);
+
+		input_sync(mydata->input);
+	}
+
+	return 1;
+}
+
+static void m560_populate_input(struct hidpp_device *hidpp,
+		struct input_dev *input_dev, bool origin_is_hid_core)
+{
+	struct m560_private_data *mydata = hidpp->private_data;
+
+	mydata->input = input_dev;
+
+	__set_bit(EV_KEY, mydata->input->evbit);
+	__set_bit(BTN_MIDDLE, mydata->input->keybit);
+	__set_bit(BTN_RIGHT, mydata->input->keybit);
+	__set_bit(BTN_LEFT, mydata->input->keybit);
+	__set_bit(BTN_BACK, mydata->input->keybit);
+	__set_bit(BTN_FORWARD, mydata->input->keybit);
+
+	__set_bit(EV_REL, mydata->input->evbit);
+	__set_bit(REL_X, mydata->input->relbit);
+	__set_bit(REL_Y, mydata->input->relbit);
+	__set_bit(REL_WHEEL, mydata->input->relbit);
+	__set_bit(REL_HWHEEL, mydata->input->relbit);
+}
+
+static int m560_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	return -1;
+}
+
 /* -------------------------------------------------------------------------- */
 /* Generic HID++ devices                                                      */
 /* -------------------------------------------------------------------------- */
@@ -953,6 +1144,9 @@ static int hidpp_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		return wtp_input_mapping(hdev, hi, field, usage, bit, max);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560 &&
+			field->application != HID_GD_MOUSE)
+		return m560_input_mapping(hdev, hi, field, usage, bit, max);
 
 	return 0;
 }
@@ -962,6 +1156,8 @@ static void hidpp_populate_input(struct hidpp_device *hidpp,
 {
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		wtp_populate_input(hidpp, input, origin_is_hid_core);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560)
+		m560_populate_input(hidpp, input, origin_is_hid_core);
 }
 
 static void hidpp_input_configured(struct hid_device *hdev,
@@ -1049,6 +1245,8 @@ static int hidpp_raw_event(struct hid_device *hdev, struct hid_report *report,
 
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP)
 		return wtp_raw_event(hdev, data, size);
+	else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560)
+		return m560_raw_event(hdev, data, size);
 
 	return 0;
 }
@@ -1126,6 +1324,10 @@ static void hidpp_connect_event(struct hidpp_device *hidpp)
 		ret = wtp_connect(hdev, connected);
 		if (ret)
 			return;
+	} else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560) {
+		ret = m560_send_config_command(hdev, connected);
+		if (ret)
+			return;
 	}
 
 	if (!connected || hidpp->delayed_input)
@@ -1201,7 +1403,11 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (hidpp->quirks & HIDPP_QUIRK_CLASS_WTP) {
 		ret = wtp_allocate(hdev, id);
 		if (ret)
-			goto wtp_allocate_fail;
+			goto allocate_fail;
+	} else if (hidpp->quirks & HIDPP_QUIRK_CLASS_M560) {
+		ret = m560_allocate(hdev);
+		if (ret)
+			goto allocate_fail;
 	}
 
 	INIT_WORK(&hidpp->work, delayed_work_cb);
@@ -1245,10 +1451,6 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (hidpp->quirks & HIDPP_QUIRK_DELAYED_INIT)
 		connect_mask &= ~HID_CONNECT_HIDINPUT;
 
-	/* Re-enable hidinput for multi-input devices */
-	if (hidpp->quirks & HIDPP_QUIRK_MULTI_INPUT)
-		connect_mask |= HID_CONNECT_HIDINPUT;
-
 	ret = hid_hw_start(hdev, connect_mask);
 	if (ret) {
 		hid_err(hdev, "%s:hid_hw_start returned error\n", __func__);
@@ -1268,7 +1470,7 @@ hid_hw_start_fail:
 hid_parse_fail:
 	cancel_work_sync(&hidpp->work);
 	mutex_destroy(&hidpp->send_mutex);
-wtp_allocate_fail:
+allocate_fail:
 	hid_set_drvdata(hdev, NULL);
 	return ret;
 }
@@ -1296,11 +1498,10 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_T651),
 	  .driver_data = HIDPP_QUIRK_CLASS_WTP },
-	{ /* Keyboard TK820 */
+	{ /* Mouse logitech M560 */
 	  HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
-		USB_VENDOR_ID_LOGITECH, 0x4102),
-	  .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_MULTI_INPUT |
-			 HIDPP_QUIRK_CLASS_WTP },
+		USB_VENDOR_ID_LOGITECH, 0x402d),
+	  .driver_data = HIDPP_QUIRK_DELAYED_INIT | HIDPP_QUIRK_CLASS_M560 },
 
 	{ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE,
 		USB_VENDOR_ID_LOGITECH, HID_ANY_ID)},
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index af935eb198c9..32a596f554af 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -280,6 +280,8 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_HIDINPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP),
 		.driver_data = MS_HIDINPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER),
+		.driver_data = MS_HIDINPUT },
 
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT),
 		.driver_data = MS_PRESENTER },
diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c
index 2180e0789b76..febb21ee190e 100644
--- a/drivers/hid/hid-plantronics.c
+++ b/drivers/hid/hid-plantronics.c
@@ -2,7 +2,7 @@
  *  Plantronics USB HID Driver
  *
  *  Copyright (c) 2014 JD Cole <jd.cole@plantronics.com>
- *  Copyright (c) 2014 Terry Junge <terry.junge@plantronics.com>
+ *  Copyright (c) 2015 Terry Junge <terry.junge@plantronics.com>
  */
 
 /*
@@ -17,23 +17,138 @@
 #include <linux/hid.h>
 #include <linux/module.h>
 
+#define PLT_HID_1_0_PAGE	0xffa00000
+#define PLT_HID_2_0_PAGE	0xffa20000
+
+#define PLT_BASIC_TELEPHONY	0x0003
+#define PLT_BASIC_EXCEPTION	0x0005
+
+#define PLT_VOL_UP		0x00b1
+#define PLT_VOL_DOWN		0x00b2
+
+#define PLT1_VOL_UP		(PLT_HID_1_0_PAGE | PLT_VOL_UP)
+#define PLT1_VOL_DOWN		(PLT_HID_1_0_PAGE | PLT_VOL_DOWN)
+#define PLT2_VOL_UP		(PLT_HID_2_0_PAGE | PLT_VOL_UP)
+#define PLT2_VOL_DOWN		(PLT_HID_2_0_PAGE | PLT_VOL_DOWN)
+
+#define PLT_DA60		0xda60
+#define PLT_BT300_MIN		0x0413
+#define PLT_BT300_MAX		0x0418
+
+
+#define PLT_ALLOW_CONSUMER (field->application == HID_CP_CONSUMERCONTROL && \
+			    (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER)
+
 static int plantronics_input_mapping(struct hid_device *hdev,
 				     struct hid_input *hi,
 				     struct hid_field *field,
 				     struct hid_usage *usage,
 				     unsigned long **bit, int *max)
 {
-	if (field->application == HID_CP_CONSUMERCONTROL
-	    && (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER) {
-		hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n",
-			 usage->hid, field->application);
-		return 0;
+	unsigned short mapped_key;
+	unsigned long plt_type = (unsigned long)hid_get_drvdata(hdev);
+
+	/* handle volume up/down mapping */
+	/* non-standard types or multi-HID interfaces - plt_type is PID */
+	if (!(plt_type & HID_USAGE_PAGE)) {
+		switch (plt_type) {
+		case PLT_DA60:
+			if (PLT_ALLOW_CONSUMER)
+				goto defaulted;
+			goto ignored;
+		default:
+			if (PLT_ALLOW_CONSUMER)
+				goto defaulted;
+		}
+	}
+	/* handle standard types - plt_type is 0xffa0uuuu or 0xffa2uuuu */
+	/* 'basic telephony compliant' - allow default consumer page map */
+	else if ((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY &&
+		 (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) {
+		if (PLT_ALLOW_CONSUMER)
+			goto defaulted;
+	}
+	/* not 'basic telephony' - apply legacy mapping */
+	/* only map if the field is in the device's primary vendor page */
+	else if (!((field->application ^ plt_type) & HID_USAGE_PAGE)) {
+		switch (usage->hid) {
+		case PLT1_VOL_UP:
+		case PLT2_VOL_UP:
+			mapped_key = KEY_VOLUMEUP;
+			goto mapped;
+		case PLT1_VOL_DOWN:
+		case PLT2_VOL_DOWN:
+			mapped_key = KEY_VOLUMEDOWN;
+			goto mapped;
+		}
 	}
 
-	hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n",
-		usage->hid, field->application);
+/*
+ * Future mapping of call control or other usages,
+ * if and when keys are defined would go here
+ * otherwise, ignore everything else that was not mapped
+ */
 
+ignored:
 	return -1;
+
+defaulted:
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - defaulted\n",
+		usage->hid, field->application);
+	return 0;
+
+mapped:
+	hid_map_usage_clear(hi, usage, bit, max, EV_KEY, mapped_key);
+	hid_dbg(hdev, "usage: %08x (appl: %08x) - mapped to key %d\n",
+		usage->hid, field->application, mapped_key);
+	return 1;
+}
+
+static unsigned long plantronics_device_type(struct hid_device *hdev)
+{
+	unsigned i, col_page;
+	unsigned long plt_type = hdev->product;
+
+	/* multi-HID interfaces? - plt_type is PID */
+	if (plt_type >= PLT_BT300_MIN && plt_type <= PLT_BT300_MAX)
+		goto exit;
+
+	/* determine primary vendor page */
+	for (i = 0; i < hdev->maxcollection; i++) {
+		col_page = hdev->collection[i].usage & HID_USAGE_PAGE;
+		if (col_page == PLT_HID_2_0_PAGE) {
+			plt_type = hdev->collection[i].usage;
+			break;
+		}
+		if (col_page == PLT_HID_1_0_PAGE)
+			plt_type = hdev->collection[i].usage;
+	}
+
+exit:
+	hid_dbg(hdev, "plt_type decoded as: %08lx\n", plt_type);
+	return plt_type;
+}
+
+static int plantronics_probe(struct hid_device *hdev,
+			     const struct hid_device_id *id)
+{
+	int ret;
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		hid_err(hdev, "parse failed\n");
+		goto err;
+	}
+
+	hid_set_drvdata(hdev, (void *)plantronics_device_type(hdev));
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT |
+		HID_CONNECT_HIDINPUT_FORCE | HID_CONNECT_HIDDEV_FORCE);
+	if (ret)
+		hid_err(hdev, "hw start failed\n");
+
+err:
+	return ret;
 }
 
 static const struct hid_device_id plantronics_devices[] = {
@@ -46,6 +161,7 @@ static struct hid_driver plantronics_driver = {
 	.name = "plantronics",
 	.id_table = plantronics_devices,
 	.input_mapping = plantronics_input_mapping,
+	.probe = plantronics_probe,
 };
 module_hid_driver(plantronics_driver);
 
diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c
index 91fab975063c..e3e98ccf137b 100644
--- a/drivers/hid/hid-prodikeys.c
+++ b/drivers/hid/hid-prodikeys.c
@@ -395,11 +395,10 @@ static int pcmidi_handle_report4(struct pcmidi_snd *pm, u8 *data)
 
 	/* break keys */
 	for (bit_index = 0; bit_index < 24; bit_index++) {
-		key = pm->last_key[bit_index];
 		if (!((0x01 << bit_index) & bit_mask)) {
 			input_event(pm->input_ep82, EV_KEY,
 				pm->last_key[bit_index], 0);
-				pm->last_key[bit_index] = 0;
+			pm->last_key[bit_index] = 0;
 		}
 	}
 
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 368ffdf2c0a3..4cf80bb276dc 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -29,9 +29,9 @@
 #define RMI_SET_RMI_MODE_REPORT_ID	0x0f /* Feature Report */
 
 /* flags */
-#define RMI_READ_REQUEST_PENDING	BIT(0)
-#define RMI_READ_DATA_PENDING		BIT(1)
-#define RMI_STARTED			BIT(2)
+#define RMI_READ_REQUEST_PENDING	0
+#define RMI_READ_DATA_PENDING		1
+#define RMI_STARTED			2
 
 /* device flags */
 #define RMI_DEVICE			BIT(0)
@@ -1013,6 +1013,7 @@ static int rmi_populate_f30(struct hid_device *hdev)
 
 static int rmi_populate(struct hid_device *hdev)
 {
+	struct rmi_data *data = hid_get_drvdata(hdev);
 	int ret;
 
 	ret = rmi_scan_pdt(hdev);
@@ -1033,9 +1034,11 @@ static int rmi_populate(struct hid_device *hdev)
 		return ret;
 	}
 
-	ret = rmi_populate_f30(hdev);
-	if (ret)
-		hid_warn(hdev, "Error while initializing F30 (%d).\n", ret);
+	if (!(data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS)) {
+		ret = rmi_populate_f30(hdev);
+		if (ret)
+			hid_warn(hdev, "Error while initializing F30 (%d).\n", ret);
+	}
 
 	return 0;
 }
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index c3f6f1e311ea..090a1ba0abb6 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -294,7 +294,7 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev,
 	if (!report)
 		return -EINVAL;
 
-	mutex_lock(&hsdev->mutex);
+	mutex_lock(hsdev->mutex_ptr);
 	if (flag == SENSOR_HUB_SYNC) {
 		memset(&hsdev->pending, 0, sizeof(hsdev->pending));
 		init_completion(&hsdev->pending.ready);
@@ -328,7 +328,7 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev,
 		kfree(hsdev->pending.raw_data);
 		hsdev->pending.status = false;
 	}
-	mutex_unlock(&hsdev->mutex);
+	mutex_unlock(hsdev->mutex_ptr);
 
 	return ret_val;
 }
@@ -667,7 +667,14 @@ static int sensor_hub_probe(struct hid_device *hdev,
 			hsdev->vendor_id = hdev->vendor;
 			hsdev->product_id = hdev->product;
 			hsdev->usage = collection->usage;
-			mutex_init(&hsdev->mutex);
+			hsdev->mutex_ptr = devm_kzalloc(&hdev->dev,
+							sizeof(struct mutex),
+							GFP_KERNEL);
+			if (!hsdev->mutex_ptr) {
+				ret = -ENOMEM;
+				goto err_stop_hw;
+			}
+			mutex_init(hsdev->mutex_ptr);
 			hsdev->start_collection_index = i;
 			if (last_hsdev)
 				last_hsdev->end_collection_index = i;
diff --git a/drivers/hid/hid-sjoy.c b/drivers/hid/hid-sjoy.c
index 37845eccddb5..36b6470af947 100644
--- a/drivers/hid/hid-sjoy.c
+++ b/drivers/hid/hid-sjoy.c
@@ -166,6 +166,9 @@ static const struct hid_device_id sjoy_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD),
 		.driver_data = HID_QUIRK_MULTI_INPUT |
 			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII),
+		.driver_data = HID_QUIRK_MULTI_INPUT |
+			       HID_QUIRK_SKIP_OUTPUT_REPORTS },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, sjoy_devices);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 6ca96cebb44c..ed2f008f8403 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -46,20 +46,37 @@
 #define PS3REMOTE                 BIT(4)
 #define DUALSHOCK4_CONTROLLER_USB BIT(5)
 #define DUALSHOCK4_CONTROLLER_BT  BIT(6)
+#define MOTION_CONTROLLER_USB     BIT(7)
+#define MOTION_CONTROLLER_BT      BIT(8)
+#define NAVIGATION_CONTROLLER_USB BIT(9)
+#define NAVIGATION_CONTROLLER_BT  BIT(10)
 
 #define SIXAXIS_CONTROLLER (SIXAXIS_CONTROLLER_USB | SIXAXIS_CONTROLLER_BT)
+#define MOTION_CONTROLLER (MOTION_CONTROLLER_USB | MOTION_CONTROLLER_BT)
+#define NAVIGATION_CONTROLLER (NAVIGATION_CONTROLLER_USB |\
+				NAVIGATION_CONTROLLER_BT)
 #define DUALSHOCK4_CONTROLLER (DUALSHOCK4_CONTROLLER_USB |\
 				DUALSHOCK4_CONTROLLER_BT)
 #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER | BUZZ_CONTROLLER |\
-				DUALSHOCK4_CONTROLLER)
-#define SONY_BATTERY_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER)
-#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER)
+				DUALSHOCK4_CONTROLLER | MOTION_CONTROLLER |\
+				NAVIGATION_CONTROLLER)
+#define SONY_BATTERY_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER |\
+				MOTION_CONTROLLER_BT | NAVIGATION_CONTROLLER)
+#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER | DUALSHOCK4_CONTROLLER |\
+				MOTION_CONTROLLER)
 
 #define MAX_LEDS 4
 
+/*
+ * The Sixaxis reports both digital and analog values for each button on the
+ * controller except for Start, Select and the PS button.  The controller ends
+ * up reporting 27 axes which causes them to spill over into the multi-touch
+ * axis values.  Additionally, the controller only has 20 actual, physical axes
+ * so there are several unused axes in between the used ones.
+ */
 static __u8 sixaxis_rdesc[] = {
 	0x05, 0x01,         /*  Usage Page (Desktop),               */
-	0x09, 0x04,         /*  Usage (Joystik),                    */
+	0x09, 0x04,         /*  Usage (Joystick),                   */
 	0xA1, 0x01,         /*  Collection (Application),           */
 	0xA1, 0x02,         /*      Collection (Logical),           */
 	0x85, 0x01,         /*          Report ID (1),              */
@@ -134,6 +151,186 @@ static __u8 sixaxis_rdesc[] = {
 	0xC0                /*  End Collection                      */
 };
 
+/* PS/3 Motion controller */
+static __u8 motion_rdesc[] = {
+	0x05, 0x01,         /*  Usage Page (Desktop),               */
+	0x09, 0x04,         /*  Usage (Joystick),                   */
+	0xA1, 0x01,         /*  Collection (Application),           */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x01,         /*          Report ID (1),              */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x15,         /*          Report Count (21),          */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x25, 0x01,         /*          Logical Maximum (1),        */
+	0x35, 0x00,         /*          Physical Minimum (0),       */
+	0x45, 0x01,         /*          Physical Maximum (1),       */
+	0x05, 0x09,         /*          Usage Page (Button),        */
+	0x19, 0x01,         /*          Usage Minimum (01h),        */
+	0x29, 0x15,         /*          Usage Maximum (15h),        */
+	0x81, 0x02,         /*          Input (Variable),           * Buttons */
+	0x95, 0x0B,         /*          Report Count (11),          */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x81, 0x03,         /*          Input (Constant, Variable), * Padding */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0xA1, 0x00,         /*          Collection (Physical),      */
+	0x75, 0x08,         /*              Report Size (8),        */
+	0x95, 0x01,         /*              Report Count (1),       */
+	0x35, 0x00,         /*              Physical Minimum (0),   */
+	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
+	0x09, 0x30,         /*              Usage (X),              */
+	0x81, 0x02,         /*              Input (Variable),       * Trigger */
+	0xC0,               /*          End Collection,             */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x07,         /*          Report Count (7),           * skip 7 bytes */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x75, 0x10,         /*          Report Size (16),           */
+	0x46, 0xFF, 0xFF,   /*          Physical Maximum (65535),   */
+	0x27, 0xFF, 0xFF, 0x00, 0x00, /*      Logical Maximum (65535),    */
+	0x95, 0x03,         /*          Report Count (3),           * 3x Accels */
+	0x09, 0x33,         /*              Usage (rX),             */
+	0x09, 0x34,         /*              Usage (rY),             */
+	0x09, 0x35,         /*              Usage (rZ),             */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x03,         /*          Report Count (3),           * Skip Accels 2nd frame */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x95, 0x03,         /*          Report Count (3),           * 3x Gyros */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x03,         /*          Report Count (3),           * Skip Gyros 2nd frame */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x0C,         /*          Report Size (12),           */
+	0x46, 0xFF, 0x0F,   /*          Physical Maximum (4095),    */
+	0x26, 0xFF, 0x0F,   /*          Logical Maximum (4095),     */
+	0x95, 0x04,         /*          Report Count (4),           * Skip Temp and Magnetometers */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x46, 0xFF, 0x00,   /*          Physical Maximum (255),     */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x95, 0x06,         /*          Report Count (6),           * Skip Timestamp and Extension Bytes */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x91, 0x02,         /*          Output (Variable),          */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x02,         /*          Report ID (2),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEE,         /*          Report ID (238),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEF,         /*          Report ID (239),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xC0                /*  End Collection                      */
+};
+
+/* PS/3 Navigation controller */
+static __u8 navigation_rdesc[] = {
+	0x05, 0x01,         /*  Usage Page (Desktop),               */
+	0x09, 0x04,         /*  Usage (Joystik),                    */
+	0xA1, 0x01,         /*  Collection (Application),           */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x01,         /*          Report ID (1),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x01,         /*          Report Count (1),           */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x13,         /*          Report Count (19),          */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x25, 0x01,         /*          Logical Maximum (1),        */
+	0x35, 0x00,         /*          Physical Minimum (0),       */
+	0x45, 0x01,         /*          Physical Maximum (1),       */
+	0x05, 0x09,         /*          Usage Page (Button),        */
+	0x19, 0x01,         /*          Usage Minimum (01h),        */
+	0x29, 0x13,         /*          Usage Maximum (13h),        */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x01,         /*          Report Size (1),            */
+	0x95, 0x0D,         /*          Report Count (13),          */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x15, 0x00,         /*          Logical Minimum (0),        */
+	0x26, 0xFF, 0x00,   /*          Logical Maximum (255),      */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xA1, 0x00,         /*          Collection (Physical),      */
+	0x75, 0x08,         /*              Report Size (8),        */
+	0x95, 0x02,         /*              Report Count (2),       */
+	0x35, 0x00,         /*              Physical Minimum (0),   */
+	0x46, 0xFF, 0x00,   /*              Physical Maximum (255), */
+	0x09, 0x30,         /*              Usage (X),              */
+	0x09, 0x31,         /*              Usage (Y),              */
+	0x81, 0x02,         /*              Input (Variable),       */
+	0xC0,               /*          End Collection,             */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x06,         /*          Report Count (6),           */
+	0x81, 0x03,         /*          Input (Constant, Variable), */
+	0x05, 0x01,         /*          Usage Page (Desktop),       */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x05,         /*          Report Count (5),           */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x06, 0x00, 0xFF,   /*          Usage Page (FF00h),         */
+	0x95, 0x20,         /*          Report Count (26),          */
+	0x81, 0x02,         /*          Input (Variable),           */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0x91, 0x02,         /*          Output (Variable),          */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0x02,         /*          Report ID (2),              */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEE,         /*          Report ID (238),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xA1, 0x02,         /*      Collection (Logical),           */
+	0x85, 0xEF,         /*          Report ID (239),            */
+	0x75, 0x08,         /*          Report Size (8),            */
+	0x95, 0x30,         /*          Report Count (48),          */
+	0x09, 0x01,         /*          Usage (Pointer),            */
+	0xB1, 0x02,         /*          Feature (Variable),         */
+	0xC0,               /*      End Collection,                 */
+	0xC0                /*  End Collection                      */
+};
+
 /*
  * The default descriptor doesn't provide mapping for the accelerometers
  * or orientation sensors.  This fixed descriptor maps the accelerometers
@@ -798,12 +995,20 @@ union sixaxis_output_report_01 {
 	__u8 buf[36];
 };
 
+struct motion_output_report_02 {
+	u8 type, zero;
+	u8 r, g, b;
+	u8 zero2;
+	u8 rumble;
+};
+
 #define DS4_REPORT_0x02_SIZE 37
 #define DS4_REPORT_0x05_SIZE 32
 #define DS4_REPORT_0x11_SIZE 78
 #define DS4_REPORT_0x81_SIZE 7
 #define SIXAXIS_REPORT_0xF2_SIZE 17
 #define SIXAXIS_REPORT_0xF5_SIZE 8
+#define MOTION_REPORT_0x02_SIZE 49
 
 static DEFINE_SPINLOCK(sony_dev_list_lock);
 static LIST_HEAD(sony_device_list);
@@ -844,6 +1049,20 @@ static __u8 *sixaxis_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return sixaxis_rdesc;
 }
 
+static u8 *motion_fixup(struct hid_device *hdev, u8 *rdesc,
+			     unsigned int *rsize)
+{
+	*rsize = sizeof(motion_rdesc);
+	return motion_rdesc;
+}
+
+static u8 *navigation_fixup(struct hid_device *hdev, u8 *rdesc,
+			     unsigned int *rsize)
+{
+	*rsize = sizeof(navigation_rdesc);
+	return navigation_rdesc;
+}
+
 static __u8 *ps3remote_fixup(struct hid_device *hdev, __u8 *rdesc,
 			     unsigned int *rsize)
 {
@@ -924,6 +1143,12 @@ static __u8 *sony_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (sc->quirks & SIXAXIS_CONTROLLER)
 		return sixaxis_fixup(hdev, rdesc, rsize);
 
+	if (sc->quirks & MOTION_CONTROLLER)
+		return motion_fixup(hdev, rdesc, rsize);
+
+	if (sc->quirks & NAVIGATION_CONTROLLER)
+		return navigation_fixup(hdev, rdesc, rsize);
+
 	if (sc->quirks & PS3REMOTE)
 		return ps3remote_fixup(hdev, rdesc, rsize);
 
@@ -934,6 +1159,7 @@ static void sixaxis_parse_report(struct sony_sc *sc, __u8 *rd, int size)
 {
 	static const __u8 sixaxis_battery_capacity[] = { 0, 1, 25, 50, 75, 100 };
 	unsigned long flags;
+	int offset;
 	__u8 cable_state, battery_capacity, battery_charging;
 
 	/*
@@ -942,12 +1168,14 @@ static void sixaxis_parse_report(struct sony_sc *sc, __u8 *rd, int size)
 	 * It does not report the actual level while charging so it
 	 * is set to 100% while charging is in progress.
 	 */
-	if (rd[30] >= 0xee) {
+	offset = (sc->quirks & MOTION_CONTROLLER) ? 12 : 30;
+
+	if (rd[offset] >= 0xee) {
 		battery_capacity = 100;
-		battery_charging = !(rd[30] & 0x01);
+		battery_charging = !(rd[offset] & 0x01);
 		cable_state = 1;
 	} else {
-		__u8 index = rd[30] <= 5 ? rd[30] : 5;
+		__u8 index = rd[offset] <= 5 ? rd[offset] : 5;
 		battery_capacity = sixaxis_battery_capacity[index];
 		battery_charging = 0;
 		cable_state = 0;
@@ -1048,6 +1276,11 @@ static int sony_raw_event(struct hid_device *hdev, struct hid_report *report,
 		swap(rd[47], rd[48]);
 
 		sixaxis_parse_report(sc, rd, size);
+	} else if ((sc->quirks & MOTION_CONTROLLER_BT) && rd[0] == 0x01 && size == 49) {
+		sixaxis_parse_report(sc, rd, size);
+	} else if ((sc->quirks & NAVIGATION_CONTROLLER) && rd[0] == 0x01 &&
+			size == 49) {
+		sixaxis_parse_report(sc, rd, size);
 	} else if (((sc->quirks & DUALSHOCK4_CONTROLLER_USB) && rd[0] == 0x01 &&
 			size == 64) || ((sc->quirks & DUALSHOCK4_CONTROLLER_BT)
 			&& rd[0] == 0x11 && size == 78)) {
@@ -1208,7 +1441,7 @@ static int dualshock4_set_operational_bt(struct hid_device *hdev)
 	return ret;
 }
 
-static void sixaxis_set_leds_from_id(int id, __u8 values[MAX_LEDS])
+static void sixaxis_set_leds_from_id(struct sony_sc *sc)
 {
 	static const __u8 sixaxis_leds[10][4] = {
 				{ 0x01, 0x00, 0x00, 0x00 },
@@ -1223,16 +1456,18 @@ static void sixaxis_set_leds_from_id(int id, __u8 values[MAX_LEDS])
 				{ 0x01, 0x01, 0x01, 0x01 }
 	};
 
-	BUG_ON(MAX_LEDS < ARRAY_SIZE(sixaxis_leds[0]));
+	int id = sc->device_id;
+
+	BUILD_BUG_ON(MAX_LEDS < ARRAY_SIZE(sixaxis_leds[0]));
 
 	if (id < 0)
 		return;
 
 	id %= 10;
-	memcpy(values, sixaxis_leds[id], sizeof(sixaxis_leds[id]));
+	memcpy(sc->led_state, sixaxis_leds[id], sizeof(sixaxis_leds[id]));
 }
 
-static void dualshock4_set_leds_from_id(int id, __u8 values[MAX_LEDS])
+static void dualshock4_set_leds_from_id(struct sony_sc *sc)
 {
 	/* The first 4 color/index entries match what the PS4 assigns */
 	static const __u8 color_code[7][3] = {
@@ -1245,46 +1480,44 @@ static void dualshock4_set_leds_from_id(int id, __u8 values[MAX_LEDS])
 			/* White  */	{ 0x01, 0x01, 0x01 }
 	};
 
-	BUG_ON(MAX_LEDS < ARRAY_SIZE(color_code[0]));
+	int id = sc->device_id;
+
+	BUILD_BUG_ON(MAX_LEDS < ARRAY_SIZE(color_code[0]));
 
 	if (id < 0)
 		return;
 
 	id %= 7;
-	memcpy(values, color_code[id], sizeof(color_code[id]));
+	memcpy(sc->led_state, color_code[id], sizeof(color_code[id]));
 }
 
-static void buzz_set_leds(struct hid_device *hdev, const __u8 *leds)
+static void buzz_set_leds(struct sony_sc *sc)
 {
+	struct hid_device *hdev = sc->hdev;
 	struct list_head *report_list =
 		&hdev->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next,
 		struct hid_report, list);
 	__s32 *value = report->field[0]->value;
 
+	BUILD_BUG_ON(MAX_LEDS < 4);
+
 	value[0] = 0x00;
-	value[1] = leds[0] ? 0xff : 0x00;
-	value[2] = leds[1] ? 0xff : 0x00;
-	value[3] = leds[2] ? 0xff : 0x00;
-	value[4] = leds[3] ? 0xff : 0x00;
+	value[1] = sc->led_state[0] ? 0xff : 0x00;
+	value[2] = sc->led_state[1] ? 0xff : 0x00;
+	value[3] = sc->led_state[2] ? 0xff : 0x00;
+	value[4] = sc->led_state[3] ? 0xff : 0x00;
 	value[5] = 0x00;
 	value[6] = 0x00;
 	hid_hw_request(hdev, report, HID_REQ_SET_REPORT);
 }
 
-static void sony_set_leds(struct sony_sc *sc, const __u8 *leds, int count)
+static void sony_set_leds(struct sony_sc *sc)
 {
-	int n;
-
-	BUG_ON(count > MAX_LEDS);
-
-	if (sc->quirks & BUZZ_CONTROLLER && count == 4) {
-		buzz_set_leds(sc->hdev, leds);
-	} else {
-		for (n = 0; n < count; n++)
-			sc->led_state[n] = leds[n];
+	if (!(sc->quirks & BUZZ_CONTROLLER))
 		schedule_work(&sc->state_worker);
-	}
+	else
+		buzz_set_leds(sc);
 }
 
 static void sony_led_set_brightness(struct led_classdev *led,
@@ -1324,8 +1557,7 @@ static void sony_led_set_brightness(struct led_classdev *led,
 			drv_data->led_delay_on[n] = 0;
 			drv_data->led_delay_off[n] = 0;
 
-			sony_set_leds(drv_data, drv_data->led_state,
-					drv_data->led_count);
+			sony_set_leds(drv_data);
 			break;
 		}
 	}
@@ -1431,7 +1663,6 @@ static int sony_leds_init(struct sony_sc *sc)
 	const char *name_fmt;
 	static const char * const ds4_name_str[] = { "red", "green", "blue",
 						  "global" };
-	__u8 initial_values[MAX_LEDS] = { 0 };
 	__u8 max_brightness[MAX_LEDS] = { [0 ... (MAX_LEDS - 1)] = 1 };
 	__u8 use_hw_blink[MAX_LEDS] = { 0 };
 
@@ -1446,16 +1677,31 @@ static int sony_leds_init(struct sony_sc *sc)
 		if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 7))
 			return -ENODEV;
 	} else if (sc->quirks & DUALSHOCK4_CONTROLLER) {
-		dualshock4_set_leds_from_id(sc->device_id, initial_values);
-		initial_values[3] = 1;
+		dualshock4_set_leds_from_id(sc);
+		sc->led_state[3] = 1;
 		sc->led_count = 4;
 		memset(max_brightness, 255, 3);
 		use_hw_blink[3] = 1;
 		use_ds4_names = 1;
 		name_len = 0;
 		name_fmt = "%s:%s";
+	} else if (sc->quirks & MOTION_CONTROLLER) {
+		sc->led_count = 3;
+		memset(max_brightness, 255, 3);
+		use_ds4_names = 1;
+		name_len = 0;
+		name_fmt = "%s:%s";
+	} else if (sc->quirks & NAVIGATION_CONTROLLER) {
+		static const __u8 navigation_leds[4] = {0x01, 0x00, 0x00, 0x00};
+
+		memcpy(sc->led_state, navigation_leds, sizeof(navigation_leds));
+		sc->led_count = 1;
+		memset(use_hw_blink, 1, 4);
+		use_ds4_names = 0;
+		name_len = strlen("::sony#");
+		name_fmt = "%s::sony%d";
 	} else {
-		sixaxis_set_leds_from_id(sc->device_id, initial_values);
+		sixaxis_set_leds_from_id(sc);
 		sc->led_count = 4;
 		memset(use_hw_blink, 1, 4);
 		use_ds4_names = 0;
@@ -1468,7 +1714,7 @@ static int sony_leds_init(struct sony_sc *sc)
 	 * only relevant if the driver is loaded after somebody actively set the
 	 * LEDs to on
 	 */
-	sony_set_leds(sc, initial_values, sc->led_count);
+	sony_set_leds(sc);
 
 	name_sz = strlen(dev_name(&hdev->dev)) + name_len + 1;
 
@@ -1491,7 +1737,7 @@ static int sony_leds_init(struct sony_sc *sc)
 		else
 			snprintf(name, name_sz, name_fmt, dev_name(&hdev->dev), n + 1);
 		led->name = name;
-		led->brightness = initial_values[n];
+		led->brightness = sc->led_state[n];
 		led->max_brightness = max_brightness[n];
 		led->brightness_get = sony_led_get_brightness;
 		led->brightness_set = sony_led_set_brightness;
@@ -1622,9 +1868,31 @@ static void dualshock4_state_worker(struct work_struct *work)
 				HID_OUTPUT_REPORT, HID_REQ_SET_REPORT);
 }
 
+static void motion_state_worker(struct work_struct *work)
+{
+	struct sony_sc *sc = container_of(work, struct sony_sc, state_worker);
+	struct hid_device *hdev = sc->hdev;
+	struct motion_output_report_02 *report =
+		(struct motion_output_report_02 *)sc->output_report_dmabuf;
+
+	memset(report, 0, MOTION_REPORT_0x02_SIZE);
+
+	report->type = 0x02; /* set leds */
+	report->r = sc->led_state[0];
+	report->g = sc->led_state[1];
+	report->b = sc->led_state[2];
+
+#ifdef CONFIG_SONY_FF
+	report->rumble = max(sc->right, sc->left);
+#endif
+
+	hid_hw_output_report(hdev, (__u8 *)report, MOTION_REPORT_0x02_SIZE);
+}
+
 static int sony_allocate_output_report(struct sony_sc *sc)
 {
-	if (sc->quirks & SIXAXIS_CONTROLLER)
+	if ((sc->quirks & SIXAXIS_CONTROLLER) ||
+			(sc->quirks & NAVIGATION_CONTROLLER))
 		sc->output_report_dmabuf =
 			kmalloc(sizeof(union sixaxis_output_report_01),
 				GFP_KERNEL);
@@ -1634,6 +1902,9 @@ static int sony_allocate_output_report(struct sony_sc *sc)
 	else if (sc->quirks & DUALSHOCK4_CONTROLLER_USB)
 		sc->output_report_dmabuf = kmalloc(DS4_REPORT_0x05_SIZE,
 						GFP_KERNEL);
+	else if (sc->quirks & MOTION_CONTROLLER)
+		sc->output_report_dmabuf = kmalloc(MOTION_REPORT_0x02_SIZE,
+						GFP_KERNEL);
 	else
 		return 0;
 
@@ -1839,6 +2110,8 @@ static int sony_check_add(struct sony_sc *sc)
 	int n, ret;
 
 	if ((sc->quirks & DUALSHOCK4_CONTROLLER_BT) ||
+	    (sc->quirks & MOTION_CONTROLLER_BT) ||
+	    (sc->quirks & NAVIGATION_CONTROLLER_BT) ||
 	    (sc->quirks & SIXAXIS_CONTROLLER_BT)) {
 		/*
 		 * sony_get_bt_devaddr() attempts to parse the Bluetooth MAC
@@ -1871,7 +2144,8 @@ static int sony_check_add(struct sony_sc *sc)
 		}
 
 		memcpy(sc->mac_address, &buf[1], sizeof(sc->mac_address));
-	} else if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+	} else if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
 		buf = kmalloc(SIXAXIS_REPORT_0xF2_SIZE, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
@@ -1993,19 +2267,20 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return ret;
 	}
 
-	ret = sony_allocate_output_report(sc);
+	ret = sony_set_device_id(sc);
 	if (ret < 0) {
-		hid_err(hdev, "failed to allocate the output report buffer\n");
+		hid_err(hdev, "failed to allocate the device id\n");
 		goto err_stop;
 	}
 
-	ret = sony_set_device_id(sc);
+	ret = sony_allocate_output_report(sc);
 	if (ret < 0) {
-		hid_err(hdev, "failed to allocate the device id\n");
+		hid_err(hdev, "failed to allocate the output report buffer\n");
 		goto err_stop;
 	}
 
-	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
+	if ((sc->quirks & SIXAXIS_CONTROLLER_USB) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_USB)) {
 		/*
 		 * The Sony Sixaxis does not handle HID Output Reports on the
 		 * Interrupt EP like it could, so we need to force HID Output
@@ -2020,7 +2295,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
 		ret = sixaxis_set_operational_usb(hdev);
 		sony_init_work(sc, sixaxis_state_worker);
-	} else if (sc->quirks & SIXAXIS_CONTROLLER_BT) {
+	} else if ((sc->quirks & SIXAXIS_CONTROLLER_BT) ||
+			(sc->quirks & NAVIGATION_CONTROLLER_BT)) {
 		/*
 		 * The Sixaxis wants output reports sent on the ctrl endpoint
 		 * when connected via Bluetooth.
@@ -2043,6 +2319,8 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		}
 
 		sony_init_work(sc, dualshock4_state_worker);
+	} else if (sc->quirks & MOTION_CONTROLLER) {
+		sony_init_work(sc, motion_state_worker);
 	} else {
 		ret = 0;
 	}
@@ -2122,7 +2400,13 @@ static const struct hid_device_id sony_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER),
 		.driver_data = SIXAXIS_CONTROLLER_USB },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER),
-		.driver_data = SIXAXIS_CONTROLLER_USB },
+		.driver_data = NAVIGATION_CONTROLLER_USB },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_NAVIGATION_CONTROLLER),
+		.driver_data = NAVIGATION_CONTROLLER_BT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER),
+		.driver_data = MOTION_CONTROLLER_USB },
+	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_MOTION_CONTROLLER),
+		.driver_data = MOTION_CONTROLLER_BT },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER),
 		.driver_data = SIXAXIS_CONTROLLER_BT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_VAIO_VGX_MOUSE),
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index ab4dd952b6ba..f77469d4edfb 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -42,9 +42,9 @@
 #include <linux/i2c/i2c-hid.h>
 
 /* flags */
-#define I2C_HID_STARTED		(1 << 0)
-#define I2C_HID_RESET_PENDING	(1 << 1)
-#define I2C_HID_READ_PENDING	(1 << 2)
+#define I2C_HID_STARTED		0
+#define I2C_HID_RESET_PENDING	1
+#define I2C_HID_READ_PENDING	2
 
 #define I2C_HID_PWR_ON		0x00
 #define I2C_HID_PWR_SLEEP	0x01
@@ -862,6 +862,7 @@ static int i2c_hid_acpi_pdata(struct i2c_client *client,
 	union acpi_object *obj;
 	struct acpi_device *adev;
 	acpi_handle handle;
+	int ret;
 
 	handle = ACPI_HANDLE(&client->dev);
 	if (!handle || acpi_bus_get_device(handle, &adev))
@@ -877,7 +878,9 @@ static int i2c_hid_acpi_pdata(struct i2c_client *client,
 	pdata->hid_descriptor_address = obj->integer.value;
 	ACPI_FREE(obj);
 
-	return acpi_dev_add_driver_gpios(adev, i2c_hid_acpi_gpios);
+	/* GPIOs are optional */
+	ret = acpi_dev_add_driver_gpios(adev, i2c_hid_acpi_gpios);
+	return ret < 0 && ret != -ENXIO ? ret : 0;
 }
 
 static const struct acpi_device_id i2c_hid_acpi_match[] = {
@@ -1016,7 +1019,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 	hid->driver_data = client;
 	hid->ll_driver = &i2c_hid_ll_driver;
 	hid->dev.parent = &client->dev;
-	ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
 	hid->bus = BUS_I2C;
 	hid->version = le16_to_cpu(ihid->hdesc.bcdVersion);
 	hid->vendor = le16_to_cpu(ihid->hdesc.wVendorID);
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index a775143e6265..53e7de7cb9e2 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -52,7 +52,6 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ETURBOTOUCH, USB_DEVICE_ID_ETURBOTOUCH_2968, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_PANTHERLORD, USB_DEVICE_ID_PANTHERLORD_TWIN_USB_JOYSTICK, HID_QUIRK_MULTI_INPUT | HID_QUIRK_SKIP_OUTPUT_REPORTS },
-	{ USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS, HID_QUIRK_MULTI_INPUT },
 
 	{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
@@ -61,6 +60,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS682, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FIGHTERSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_COMBATSTICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_ECLIPSE_YOKE, HID_QUIRK_NOGET },
@@ -69,6 +69,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
@@ -88,6 +89,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
@@ -140,6 +142,9 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_KEYBOARD_A096, HID_QUIRK_NO_INIT_INPUT_REPORTS },
+	{ USB_VENDOR_ID_MULTIPLE_1781, USB_DEVICE_ID_RAPHNET_4NES4SNES_OLD, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_2NES2SNES, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_4NES4SNES, HID_QUIRK_MULTI_INPUT },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 024f4d89d579..a533787a6d85 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -134,8 +134,10 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac)
 extern const struct hid_device_id wacom_ids[];
 
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len);
-void wacom_setup_device_quirks(struct wacom_features *features);
-int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
+void wacom_setup_device_quirks(struct wacom *wacom);
+int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
+				   struct wacom_wac *wacom_wac);
+int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 				   struct wacom_wac *wacom_wac);
 int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 				       struct wacom_wac *wacom_wac);
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index e8607d096138..4c0ffca97bef 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -35,7 +35,11 @@ static int wacom_get_report(struct hid_device *hdev, u8 type, u8 *buf,
 	do {
 		retval = hid_hw_raw_request(hdev, buf[0], buf, size, type,
 				HID_REQ_GET_REPORT);
-	} while ((retval == -ETIMEDOUT || retval == -EPIPE) && --retries);
+	} while ((retval == -ETIMEDOUT || retval == -EAGAIN) && --retries);
+
+	if (retval < 0)
+		hid_err(hdev, "wacom_get_report: ran out of retries "
+			"(last error = %d)\n", retval);
 
 	return retval;
 }
@@ -48,7 +52,11 @@ static int wacom_set_report(struct hid_device *hdev, u8 type, u8 *buf,
 	do {
 		retval = hid_hw_raw_request(hdev, buf[0], buf, size, type,
 				HID_REQ_SET_REPORT);
-	} while ((retval == -ETIMEDOUT || retval == -EPIPE) && --retries);
+	} while ((retval == -ETIMEDOUT || retval == -EAGAIN) && --retries);
+
+	if (retval < 0)
+		hid_err(hdev, "wacom_set_report: ran out of retries "
+			"(last error = %d)\n", retval);
 
 	return retval;
 }
@@ -117,9 +125,16 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 				break;
 			data[0] = field->report->id;
 			ret = wacom_get_report(hdev, HID_FEATURE_REPORT,
-						data, 2, 0);
-			if (ret == 2)
+						data, 2, WAC_CMD_RETRIES);
+			if (ret == 2) {
 				features->touch_max = data[1];
+			} else {
+				features->touch_max = 16;
+				hid_warn(hdev, "wacom_feature_mapping: "
+					 "could not get HID_DG_CONTACTMAX, "
+					 "defaulting to %d\n",
+					  features->touch_max);
+			}
 			kfree(data);
 		}
 		break;
@@ -181,7 +196,11 @@ static void wacom_usage_mapping(struct hid_device *hdev,
 	* X/Y values and some cases of invalid Digitizer X/Y
 	* values commonly reported.
 	*/
-	if (!pen && !finger)
+	if (pen)
+		features->device_type |= WACOM_DEVICETYPE_PEN;
+	else if (finger)
+		features->device_type |= WACOM_DEVICETYPE_TOUCH;
+	else
 		return;
 
 	/*
@@ -198,14 +217,11 @@ static void wacom_usage_mapping(struct hid_device *hdev,
 	case HID_GD_X:
 		features->x_max = field->logical_maximum;
 		if (finger) {
-			features->device_type = BTN_TOOL_FINGER;
 			features->x_phy = field->physical_maximum;
 			if (features->type != BAMBOO_PT) {
 				features->unit = field->unit;
 				features->unitExpo = field->unit_exponent;
 			}
-		} else {
-			features->device_type = BTN_TOOL_PEN;
 		}
 		break;
 	case HID_GD_Y:
@@ -237,7 +253,7 @@ static void wacom_post_parse_hid(struct hid_device *hdev,
 	if (features->type == HID_GENERIC) {
 		/* Any last-minute generic device setup */
 		if (features->touch_max > 1) {
-			input_mt_init_slots(wacom_wac->input, wacom_wac->features.touch_max,
+			input_mt_init_slots(wacom_wac->touch_input, wacom_wac->features.touch_max,
 				    INPUT_MT_DIRECT);
 		}
 	}
@@ -395,7 +411,7 @@ static int wacom_query_tablet_data(struct hid_device *hdev,
 	if (features->type == HID_GENERIC)
 		return wacom_hid_set_device_mode(hdev);
 
-	if (features->device_type == BTN_TOOL_FINGER) {
+	if (features->device_type & WACOM_DEVICETYPE_TOUCH) {
 		if (features->type > TABLETPC) {
 			/* MT Tablet PC touch */
 			return wacom_set_device_mode(hdev, 3, 4, 4);
@@ -409,7 +425,7 @@ static int wacom_query_tablet_data(struct hid_device *hdev,
 		else if (features->type == BAMBOO_PAD) {
 			return wacom_set_device_mode(hdev, 2, 2, 2);
 		}
-	} else if (features->device_type == BTN_TOOL_PEN) {
+	} else if (features->device_type & WACOM_DEVICETYPE_PEN) {
 		if (features->type <= BAMBOO_PT && features->type != WIRELESS) {
 			return wacom_set_device_mode(hdev, 2, 2, 2);
 		}
@@ -425,7 +441,6 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev,
 	struct usb_interface *intf = wacom->intf;
 
 	/* default features */
-	features->device_type = BTN_TOOL_PEN;
 	features->x_fuzz = 4;
 	features->y_fuzz = 4;
 	features->pressure_fuzz = 0;
@@ -439,17 +454,13 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev,
 	 */
 	if (features->type == WIRELESS) {
 		if (intf->cur_altsetting->desc.bInterfaceNumber == 0) {
-			features->device_type = 0;
+			features->device_type = WACOM_DEVICETYPE_NONE;
 		} else if (intf->cur_altsetting->desc.bInterfaceNumber == 2) {
-			features->device_type = BTN_TOOL_FINGER;
+			features->device_type |= WACOM_DEVICETYPE_TOUCH;
 			features->pktlen = WACOM_PKGLEN_BBTOUCH3;
 		}
 	}
 
-	/* only devices that support touch need to retrieve the info */
-	if (features->type < BAMBOO_PT)
-		return;
-
 	wacom_parse_hid(hdev, features);
 }
 
@@ -527,9 +538,9 @@ static int wacom_add_shared_data(struct hid_device *hdev)
 
 	wacom_wac->shared = &data->shared;
 
-	if (wacom_wac->features.device_type == BTN_TOOL_FINGER)
+	if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)
 		wacom_wac->shared->touch = hdev;
-	else if (wacom_wac->features.device_type == BTN_TOOL_PEN)
+	else if (wacom_wac->features.device_type & WACOM_DEVICETYPE_PEN)
 		wacom_wac->shared->pen = hdev;
 
 out:
@@ -848,6 +859,9 @@ static int wacom_initialize_leds(struct wacom *wacom)
 {
 	int error;
 
+	if (!(wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD))
+		return 0;
+
 	/* Initialize default values */
 	switch (wacom->wacom_wac.features.type) {
 	case INTUOS4S:
@@ -881,17 +895,14 @@ static int wacom_initialize_leds(struct wacom *wacom)
 	case INTUOSPS:
 	case INTUOSPM:
 	case INTUOSPL:
-		if (wacom->wacom_wac.features.device_type == BTN_TOOL_PEN) {
-			wacom->led.select[0] = 0;
-			wacom->led.select[1] = 0;
-			wacom->led.llv = 32;
-			wacom->led.hlv = 0;
-			wacom->led.img_lum = 0;
-
-			error = sysfs_create_group(&wacom->hdev->dev.kobj,
-						  &intuos5_led_attr_group);
-		} else
-			return 0;
+		wacom->led.select[0] = 0;
+		wacom->led.select[1] = 0;
+		wacom->led.llv = 32;
+		wacom->led.hlv = 0;
+		wacom->led.img_lum = 0;
+
+		error = sysfs_create_group(&wacom->hdev->dev.kobj,
+					  &intuos5_led_attr_group);
 		break;
 
 	default:
@@ -914,6 +925,9 @@ static void wacom_destroy_leds(struct wacom *wacom)
 	if (!wacom->led_initialized)
 		return;
 
+	if (!(wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD))
+		return;
+
 	wacom->led_initialized = false;
 
 	switch (wacom->wacom_wac.features.type) {
@@ -937,9 +951,8 @@ static void wacom_destroy_leds(struct wacom *wacom)
 	case INTUOSPS:
 	case INTUOSPM:
 	case INTUOSPL:
-		if (wacom->wacom_wac.features.device_type == BTN_TOOL_PEN)
-			sysfs_remove_group(&wacom->hdev->dev.kobj,
-					   &intuos5_led_attr_group);
+		sysfs_remove_group(&wacom->hdev->dev.kobj,
+				   &intuos5_led_attr_group);
 		break;
 	}
 }
@@ -1117,7 +1130,7 @@ static struct input_dev *wacom_allocate_input(struct wacom *wacom)
 	if (!input_dev)
 		return NULL;
 
-	input_dev->name = wacom_wac->name;
+	input_dev->name = wacom_wac->pen_name;
 	input_dev->phys = hdev->phys;
 	input_dev->dev.parent = &hdev->dev;
 	input_dev->open = wacom_open;
@@ -1136,27 +1149,33 @@ static void wacom_free_inputs(struct wacom *wacom)
 {
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
 
-	if (wacom_wac->input)
-		input_free_device(wacom_wac->input);
+	if (wacom_wac->pen_input)
+		input_free_device(wacom_wac->pen_input);
+	if (wacom_wac->touch_input)
+		input_free_device(wacom_wac->touch_input);
 	if (wacom_wac->pad_input)
 		input_free_device(wacom_wac->pad_input);
-	wacom_wac->input = NULL;
+	wacom_wac->pen_input = NULL;
+	wacom_wac->touch_input = NULL;
 	wacom_wac->pad_input = NULL;
 }
 
 static int wacom_allocate_inputs(struct wacom *wacom)
 {
-	struct input_dev *input_dev, *pad_input_dev;
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
 
-	input_dev = wacom_allocate_input(wacom);
+	pen_input_dev = wacom_allocate_input(wacom);
+	touch_input_dev = wacom_allocate_input(wacom);
 	pad_input_dev = wacom_allocate_input(wacom);
-	if (!input_dev || !pad_input_dev) {
+	if (!pen_input_dev || !touch_input_dev || !pad_input_dev) {
 		wacom_free_inputs(wacom);
 		return -ENOMEM;
 	}
 
-	wacom_wac->input = input_dev;
+	wacom_wac->pen_input = pen_input_dev;
+	wacom_wac->touch_input = touch_input_dev;
+	wacom_wac->touch_input->name = wacom_wac->touch_name;
 	wacom_wac->pad_input = pad_input_dev;
 	wacom_wac->pad_input->name = wacom_wac->pad_name;
 
@@ -1165,11 +1184,17 @@ static int wacom_allocate_inputs(struct wacom *wacom)
 
 static void wacom_clean_inputs(struct wacom *wacom)
 {
-	if (wacom->wacom_wac.input) {
-		if (wacom->wacom_wac.input_registered)
-			input_unregister_device(wacom->wacom_wac.input);
+	if (wacom->wacom_wac.pen_input) {
+		if (wacom->wacom_wac.pen_registered)
+			input_unregister_device(wacom->wacom_wac.pen_input);
 		else
-			input_free_device(wacom->wacom_wac.input);
+			input_free_device(wacom->wacom_wac.pen_input);
+	}
+	if (wacom->wacom_wac.touch_input) {
+		if (wacom->wacom_wac.touch_registered)
+			input_unregister_device(wacom->wacom_wac.touch_input);
+		else
+			input_free_device(wacom->wacom_wac.touch_input);
 	}
 	if (wacom->wacom_wac.pad_input) {
 		if (wacom->wacom_wac.pad_registered)
@@ -1177,29 +1202,49 @@ static void wacom_clean_inputs(struct wacom *wacom)
 		else
 			input_free_device(wacom->wacom_wac.pad_input);
 	}
-	wacom->wacom_wac.input = NULL;
+	wacom->wacom_wac.pen_input = NULL;
+	wacom->wacom_wac.touch_input = NULL;
 	wacom->wacom_wac.pad_input = NULL;
 	wacom_destroy_leds(wacom);
 }
 
 static int wacom_register_inputs(struct wacom *wacom)
 {
-	struct input_dev *input_dev, *pad_input_dev;
+	struct input_dev *pen_input_dev, *touch_input_dev, *pad_input_dev;
 	struct wacom_wac *wacom_wac = &(wacom->wacom_wac);
-	int error;
+	int error = 0;
 
-	input_dev = wacom_wac->input;
+	pen_input_dev = wacom_wac->pen_input;
+	touch_input_dev = wacom_wac->touch_input;
 	pad_input_dev = wacom_wac->pad_input;
 
-	if (!input_dev || !pad_input_dev)
+	if (!pen_input_dev || !touch_input_dev || !pad_input_dev)
 		return -EINVAL;
 
-	error = wacom_setup_pentouch_input_capabilities(input_dev, wacom_wac);
-	if (!error) {
-		error = input_register_device(input_dev);
+	error = wacom_setup_pen_input_capabilities(pen_input_dev, wacom_wac);
+	if (error) {
+		/* no pen in use on this interface */
+		input_free_device(pen_input_dev);
+		wacom_wac->pen_input = NULL;
+		pen_input_dev = NULL;
+	} else {
+		error = input_register_device(pen_input_dev);
+		if (error)
+			goto fail_register_pen_input;
+		wacom_wac->pen_registered = true;
+	}
+
+	error = wacom_setup_touch_input_capabilities(touch_input_dev, wacom_wac);
+	if (error) {
+		/* no touch in use on this interface */
+		input_free_device(touch_input_dev);
+		wacom_wac->touch_input = NULL;
+		touch_input_dev = NULL;
+	} else {
+		error = input_register_device(touch_input_dev);
 		if (error)
-			return error;
-		wacom_wac->input_registered = true;
+			goto fail_register_touch_input;
+		wacom_wac->touch_registered = true;
 	}
 
 	error = wacom_setup_pad_input_capabilities(pad_input_dev, wacom_wac);
@@ -1226,9 +1271,14 @@ fail_leds:
 	pad_input_dev = NULL;
 	wacom_wac->pad_registered = false;
 fail_register_pad_input:
-	input_unregister_device(input_dev);
-	wacom_wac->input = NULL;
-	wacom_wac->input_registered = false;
+	input_unregister_device(touch_input_dev);
+	wacom_wac->touch_input = NULL;
+	wacom_wac->touch_registered = false;
+fail_register_touch_input:
+	input_unregister_device(pen_input_dev);
+	wacom_wac->pen_input = NULL;
+	wacom_wac->pen_registered = false;
+fail_register_pen_input:
 	return error;
 }
 
@@ -1285,8 +1335,11 @@ static void wacom_wireless_work(struct work_struct *work)
 		/* Stylus interface */
 		wacom_wac1->features =
 			*((struct wacom_features *)id->driver_data);
-		wacom_wac1->features.device_type = BTN_TOOL_PEN;
-		snprintf(wacom_wac1->name, WACOM_NAME_MAX, "%s (WL) Pen",
+		wacom_wac1->features.device_type |= WACOM_DEVICETYPE_PEN;
+		if (wacom_wac1->features.type != INTUOSHT &&
+		    wacom_wac1->features.type != BAMBOO_PT)
+			wacom_wac1->features.device_type |= WACOM_DEVICETYPE_PAD;
+		snprintf(wacom_wac1->pen_name, WACOM_NAME_MAX, "%s (WL) Pen",
 			 wacom_wac1->features.name);
 		snprintf(wacom_wac1->pad_name, WACOM_NAME_MAX, "%s (WL) Pad",
 			 wacom_wac1->features.name);
@@ -1304,16 +1357,16 @@ static void wacom_wireless_work(struct work_struct *work)
 			wacom_wac2->features =
 				*((struct wacom_features *)id->driver_data);
 			wacom_wac2->features.pktlen = WACOM_PKGLEN_BBTOUCH3;
-			wacom_wac2->features.device_type = BTN_TOOL_FINGER;
 			wacom_wac2->features.x_max = wacom_wac2->features.y_max = 4096;
-			if (wacom_wac2->features.touch_max)
-				snprintf(wacom_wac2->name, WACOM_NAME_MAX,
-					 "%s (WL) Finger",wacom_wac2->features.name);
-			else
-				snprintf(wacom_wac2->name, WACOM_NAME_MAX,
-					 "%s (WL) Pad",wacom_wac2->features.name);
+			snprintf(wacom_wac2->touch_name, WACOM_NAME_MAX,
+				 "%s (WL) Finger",wacom_wac2->features.name);
 			snprintf(wacom_wac2->pad_name, WACOM_NAME_MAX,
-				 "%s (WL) Pad", wacom_wac2->features.name);
+				 "%s (WL) Pad",wacom_wac2->features.name);
+			if (wacom_wac1->features.touch_max)
+				wacom_wac2->features.device_type |= WACOM_DEVICETYPE_TOUCH;
+			if (wacom_wac1->features.type == INTUOSHT ||
+			    wacom_wac1->features.type == BAMBOO_PT)
+				wacom_wac2->features.device_type |= WACOM_DEVICETYPE_PAD;
 			wacom_wac2->pid = wacom_wac->pid;
 			error = wacom_allocate_inputs(wacom2) ||
 				wacom_register_inputs(wacom2);
@@ -1322,7 +1375,7 @@ static void wacom_wireless_work(struct work_struct *work)
 
 			if (wacom_wac1->features.type == INTUOSHT &&
 			    wacom_wac1->features.touch_max)
-				wacom_wac->shared->touch_input = wacom_wac2->input;
+				wacom_wac->shared->touch_input = wacom_wac2->touch_input;
 		}
 
 		error = wacom_initialize_battery(wacom);
@@ -1369,6 +1422,12 @@ static void wacom_set_default_phy(struct wacom_features *features)
 
 static void wacom_calculate_res(struct wacom_features *features)
 {
+	/* set unit to "100th of a mm" for devices not reported by HID */
+	if (!features->unit) {
+		features->unit = 0x11;
+		features->unitExpo = -3;
+	}
+
 	features->x_resolution = wacom_calc_hid_res(features->x_max,
 						    features->x_phy,
 						    features->unit,
@@ -1396,6 +1455,49 @@ static size_t wacom_compute_pktlen(struct hid_device *hdev)
 	return size;
 }
 
+static void wacom_update_name(struct wacom *wacom)
+{
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct wacom_features *features = &wacom_wac->features;
+	char name[WACOM_NAME_MAX];
+
+	/* Generic devices name unspecified */
+	if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) {
+		if (strstr(wacom->hdev->name, "Wacom") ||
+		    strstr(wacom->hdev->name, "wacom") ||
+		    strstr(wacom->hdev->name, "WACOM")) {
+			/* name is in HID descriptor, use it */
+			strlcpy(name, wacom->hdev->name, sizeof(name));
+
+			/* strip out excess whitespaces */
+			while (1) {
+				char *gap = strstr(name, "  ");
+				if (gap == NULL)
+					break;
+				/* shift everything including the terminator */
+				memmove(gap, gap+1, strlen(gap));
+			}
+			/* get rid of trailing whitespace */
+			if (name[strlen(name)-1] == ' ')
+				name[strlen(name)-1] = '\0';
+		} else {
+			/* no meaningful name retrieved. use product ID */
+			snprintf(name, sizeof(name),
+				 "%s %X", features->name, wacom->hdev->product);
+		}
+	} else {
+		strlcpy(name, features->name, sizeof(name));
+	}
+
+	/* Append the device type to the name */
+	snprintf(wacom_wac->pen_name, sizeof(wacom_wac->pen_name),
+		"%s Pen", name);
+	snprintf(wacom_wac->touch_name, sizeof(wacom_wac->touch_name),
+		"%s Finger", name);
+	snprintf(wacom_wac->pad_name, sizeof(wacom_wac->pad_name),
+		"%s Pad", name);
+}
+
 static int wacom_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
@@ -1474,64 +1576,25 @@ static int wacom_probe(struct hid_device *hdev,
 
 	/* Retrieve the physical and logical size for touch devices */
 	wacom_retrieve_hid_descriptor(hdev, features);
+	wacom_setup_device_quirks(wacom);
 
-	/*
-	 * Intuos5 has no useful data about its touch interface in its
-	 * HID descriptor. If this is the touch interface (PacketSize
-	 * of WACOM_PKGLEN_BBTOUCH3), override the table values.
-	 */
-	if (features->type >= INTUOS5S && features->type <= INTUOSHT) {
-		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
-			features->device_type = BTN_TOOL_FINGER;
+	if (features->device_type == WACOM_DEVICETYPE_NONE &&
+	    features->type != WIRELESS) {
+		error = features->type == HID_GENERIC ? -ENODEV : 0;
 
-			features->x_max = 4096;
-			features->y_max = 4096;
-		} else {
-			features->device_type = BTN_TOOL_PEN;
-		}
-	}
+		dev_warn(&hdev->dev, "Unknown device_type for '%s'. %s.",
+			 hdev->name,
+			 error ? "Ignoring" : "Assuming pen");
 
-	/*
-	 * Same thing for Bamboo 3rd gen.
-	 */
-	if ((features->type == BAMBOO_PT) &&
-	    (features->pktlen == WACOM_PKGLEN_BBTOUCH3) &&
-	    (features->device_type == BTN_TOOL_PEN)) {
-		features->device_type = BTN_TOOL_FINGER;
+		if (error)
+			goto fail_shared_data;
 
-		features->x_max = 4096;
-		features->y_max = 4096;
+		features->device_type |= WACOM_DEVICETYPE_PEN;
 	}
 
-	/*
-	 * Same thing for Bamboo PAD
-	 */
-	if (features->type == BAMBOO_PAD)
-		features->device_type = BTN_TOOL_FINGER;
-
-	if (hdev->bus == BUS_BLUETOOTH)
-		features->quirks |= WACOM_QUIRK_BATTERY;
-
-	wacom_setup_device_quirks(features);
-
-	/* set unit to "100th of a mm" for devices not reported by HID */
-	if (!features->unit) {
-		features->unit = 0x11;
-		features->unitExpo = -3;
-	}
 	wacom_calculate_res(features);
 
-	strlcpy(wacom_wac->name, features->name, sizeof(wacom_wac->name));
-	snprintf(wacom_wac->pad_name, sizeof(wacom_wac->pad_name),
-		"%s Pad", features->name);
-
-	/* Append the device type to the name */
-	if (features->device_type != BTN_TOOL_FINGER)
-		strlcat(wacom_wac->name, " Pen", WACOM_NAME_MAX);
-	else if (features->touch_max)
-		strlcat(wacom_wac->name, " Finger", WACOM_NAME_MAX);
-	else
-		strlcat(wacom_wac->name, " Pad", WACOM_NAME_MAX);
+	wacom_update_name(wacom);
 
 	error = wacom_add_shared_data(hdev);
 	if (error)
@@ -1574,9 +1637,9 @@ static int wacom_probe(struct hid_device *hdev,
 	if (features->quirks & WACOM_QUIRK_MONITOR)
 		error = hid_hw_open(hdev);
 
-	if (wacom_wac->features.type == INTUOSHT && wacom_wac->features.touch_max) {
-		if (wacom_wac->features.device_type == BTN_TOOL_FINGER)
-			wacom_wac->shared->touch_input = wacom_wac->input;
+	if (wacom_wac->features.type == INTUOSHT && 
+	    wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH) {
+			wacom_wac->shared->touch_input = wacom_wac->touch_input;
 	}
 
 	return 0;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index fa54d3290659..232da89f4e88 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -69,7 +69,7 @@ static void wacom_notify_battery(struct wacom_wac *wacom_wac,
 static int wacom_penpartner_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 
 	switch (data[0]) {
 	case 1:
@@ -114,7 +114,7 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int prox, pressure;
 
 	if (data[0] != WACOM_REPORT_PENABLED) {
@@ -186,7 +186,7 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 static int wacom_ptu_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 
 	if (data[0] != WACOM_REPORT_PENABLED) {
 		dev_dbg(input->dev.parent,
@@ -215,7 +215,7 @@ static int wacom_ptu_irq(struct wacom_wac *wacom)
 static int wacom_dtu_irq(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int prox = data[1] & 0x20;
 
 	dev_dbg(input->dev.parent,
@@ -245,7 +245,7 @@ static int wacom_dtu_irq(struct wacom_wac *wacom)
 static int wacom_dtus_irq(struct wacom_wac *wacom)
 {
 	char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned short prox, pressure = 0;
 
 	if (data[0] != WACOM_REPORT_DTUS && data[0] != WACOM_REPORT_DTUSPAD) {
@@ -297,7 +297,7 @@ static int wacom_graphire_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	struct input_dev *pad_input = wacom->pad_input;
 	int battery_capacity, ps_connected;
 	int prox;
@@ -464,7 +464,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	int idx = 0;
 
 	/* tool number */
@@ -649,7 +649,7 @@ static void wacom_intuos_general(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned int t;
 
 	/* general pen packet */
@@ -681,7 +681,7 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned int t;
 	int idx = 0, result;
 
@@ -1025,7 +1025,7 @@ static void wacom_intuos_bt_process_data(struct wacom_wac *wacom,
 	memcpy(wacom->data, data, 10);
 	wacom_intuos_irq(wacom);
 
-	input_sync(wacom->input);
+	input_sync(wacom->pen_input);
 	if (wacom->pad_input)
 		input_sync(wacom->pad_input);
 }
@@ -1057,7 +1057,7 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 				     ps_connected);
 		break;
 	default:
-		dev_dbg(wacom->input->dev.parent,
+		dev_dbg(wacom->pen_input->dev.parent,
 				"Unknown report: %d,%d size:%zu\n",
 				data[0], data[1], len);
 		return 0;
@@ -1067,14 +1067,16 @@ static int wacom_intuos_bt_irq(struct wacom_wac *wacom, size_t len)
 
 static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned touch_max = wacom->features.touch_max;
 	int count = 0;
 	int i;
 
-	/* non-HID_GENERIC single touch input doesn't call this routine */
-	if ((touch_max == 1) && (wacom->features.type == HID_GENERIC))
-		return wacom->hid_data.tipswitch &&
+	if (!touch_max)
+		return 0;
+
+	if (touch_max == 1)
+		return test_bit(BTN_TOUCH, input->key) &&
 		       !wacom->shared->stylus_in_proximity;
 
 	for (i = 0; i < input->mt->num_slots; i++) {
@@ -1089,7 +1091,7 @@ static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 
 static int wacom_24hdt_irq(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 	int current_num_contacts = data[61];
@@ -1157,7 +1159,7 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 
 static int wacom_mt_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 	int current_num_contacts = data[2];
@@ -1208,7 +1210,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom)
 
 static int wacom_tpc_mt_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *data = wacom->data;
 	int i;
 
@@ -1237,7 +1239,7 @@ static int wacom_tpc_mt_touch(struct wacom_wac *wacom)
 static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	bool prox = !wacom->shared->stylus_in_proximity;
 	int x = 0, y = 0;
 
@@ -1273,7 +1275,7 @@ static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len)
 static int wacom_tpc_pen(struct wacom_wac *wacom)
 {
 	unsigned char *data = wacom->data;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	bool prox = data[1] & 0x20;
 
 	if (!wacom->shared->stylus_in_proximity) /* first in prox */
@@ -1302,8 +1304,12 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 {
 	unsigned char *data = wacom->data;
 
-	dev_dbg(wacom->input->dev.parent,
-		"%s: received report #%d\n", __func__, data[0]);
+	if (wacom->pen_input)
+		dev_dbg(wacom->pen_input->dev.parent,
+			"%s: received report #%d\n", __func__, data[0]);
+	else if (wacom->touch_input)
+		dev_dbg(wacom->touch_input->dev.parent,
+			"%s: received report #%d\n", __func__, data[0]);
 
 	switch (len) {
 	case WACOM_PKGLEN_TPC1FG:
@@ -1335,11 +1341,9 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 	return 0;
 }
 
-static void wacom_map_usage(struct wacom *wacom, struct hid_usage *usage,
+static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage,
 		struct hid_field *field, __u8 type, __u16 code, int fuzz)
 {
-	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
 	int fmin = field->logical_minimum;
 	int fmax = field->logical_maximum;
 
@@ -1367,36 +1371,38 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
 		struct hid_field *field, struct hid_usage *usage)
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct input_dev *input = wacom_wac->pen_input;
 
 	switch (usage->hid) {
 	case HID_GD_X:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_X, 4);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_X, 4);
 		break;
 	case HID_GD_Y:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_Y, 4);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_Y, 4);
 		break;
 	case HID_DG_TIPPRESSURE:
-		wacom_map_usage(wacom, usage, field, EV_ABS, ABS_PRESSURE, 0);
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_PRESSURE, 0);
 		break;
 	case HID_DG_INRANGE:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOOL_PEN, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOOL_PEN, 0);
 		break;
 	case HID_DG_INVERT:
-		wacom_map_usage(wacom, usage, field, EV_KEY,
+		wacom_map_usage(input, usage, field, EV_KEY,
 				BTN_TOOL_RUBBER, 0);
 		break;
 	case HID_DG_ERASER:
 	case HID_DG_TIPSWITCH:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOUCH, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOUCH, 0);
 		break;
 	case HID_DG_BARRELSWITCH:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS, 0);
 		break;
 	case HID_DG_BARRELSWITCH2:
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_STYLUS2, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS2, 0);
 		break;
 	case HID_DG_TOOLSERIALNUMBER:
-		wacom_map_usage(wacom, usage, field, EV_MSC, MSC_SERIAL, 0);
+		wacom_map_usage(input, usage, field, EV_MSC, MSC_SERIAL, 0);
 		break;
 	}
 }
@@ -1406,7 +1412,7 @@ static int wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->pen_input;
 
 	/* checking which Tool / tip switch to send */
 	switch (usage->hid) {
@@ -1436,7 +1442,7 @@ static void wacom_wac_pen_report(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->pen_input;
 	bool prox = wacom_wac->hid_data.inrange_state;
 
 	if (!wacom_wac->shared->stylus_in_proximity) /* first in prox */
@@ -1465,23 +1471,24 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev,
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
 	struct wacom_features *features = &wacom_wac->features;
+	struct input_dev *input = wacom_wac->touch_input;
 	unsigned touch_max = wacom_wac->features.touch_max;
 
 	switch (usage->hid) {
 	case HID_GD_X:
 		features->last_slot_field = usage->hid;
 		if (touch_max == 1)
-			wacom_map_usage(wacom, usage, field, EV_ABS, ABS_X, 4);
+			wacom_map_usage(input, usage, field, EV_ABS, ABS_X, 4);
 		else
-			wacom_map_usage(wacom, usage, field, EV_ABS,
+			wacom_map_usage(input, usage, field, EV_ABS,
 					ABS_MT_POSITION_X, 4);
 		break;
 	case HID_GD_Y:
 		features->last_slot_field = usage->hid;
 		if (touch_max == 1)
-			wacom_map_usage(wacom, usage, field, EV_ABS, ABS_Y, 4);
+			wacom_map_usage(input, usage, field, EV_ABS, ABS_Y, 4);
 		else
-			wacom_map_usage(wacom, usage, field, EV_ABS,
+			wacom_map_usage(input, usage, field, EV_ABS,
 					ABS_MT_POSITION_Y, 4);
 		break;
 	case HID_DG_CONTACTID:
@@ -1495,7 +1502,7 @@ static void wacom_wac_finger_usage_mapping(struct hid_device *hdev,
 		break;
 	case HID_DG_TIPSWITCH:
 		features->last_slot_field = usage->hid;
-		wacom_map_usage(wacom, usage, field, EV_KEY, BTN_TOUCH, 0);
+		wacom_map_usage(input, usage, field, EV_KEY, BTN_TOUCH, 0);
 		break;
 	}
 }
@@ -1551,7 +1558,7 @@ static int wacom_wac_finger_event(struct hid_device *hdev,
 
 	if (usage->usage_index + 1 == field->report_count) {
 		if (usage->hid == wacom_wac->features.last_slot_field)
-			wacom_wac_finger_slot(wacom_wac, wacom_wac->input);
+			wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
 	}
 
 	return 0;
@@ -1562,7 +1569,7 @@ static void wacom_wac_finger_report(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
+	struct input_dev *input = wacom_wac->touch_input;
 	unsigned touch_max = wacom_wac->features.touch_max;
 
 	if (touch_max > 1)
@@ -1579,10 +1586,10 @@ void wacom_wac_usage_mapping(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct input_dev *input = wacom_wac->input;
 
 	/* currently, only direct devices have proper hid report descriptors */
-	__set_bit(INPUT_PROP_DIRECT, input->propbit);
+	__set_bit(INPUT_PROP_DIRECT, wacom_wac->pen_input->propbit);
+	__set_bit(INPUT_PROP_DIRECT, wacom_wac->touch_input->propbit);
 
 	if (WACOM_PEN_FIELD(field))
 		return wacom_wac_pen_usage_mapping(hdev, field, usage);
@@ -1627,7 +1634,7 @@ void wacom_wac_report(struct hid_device *hdev, struct hid_report *report)
 static int wacom_bpt_touch(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	struct input_dev *pad_input = wacom->pad_input;
 	unsigned char *data = wacom->data;
 	int i;
@@ -1675,7 +1682,7 @@ static int wacom_bpt_touch(struct wacom_wac *wacom)
 static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	bool touch = data[1] & 0x80;
 	int slot = input_mt_get_slot_by_key(input, data[0]);
 
@@ -1733,7 +1740,6 @@ static void wacom_bpt3_button_msg(struct wacom_wac *wacom, unsigned char *data)
 
 static int wacom_bpt3_touch(struct wacom_wac *wacom)
 {
-	struct input_dev *input = wacom->input;
 	unsigned char *data = wacom->data;
 	int count = data[1] & 0x07;
 	int i;
@@ -1752,8 +1758,12 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom)
 			wacom_bpt3_button_msg(wacom, data + offset);
 
 	}
-	input_mt_sync_frame(input);
-	wacom->shared->touch_down = wacom_wac_finger_count_touches(wacom);
+
+	/* only update the touch if we actually have a touchpad */
+	if (wacom->touch_registered) {
+		input_mt_sync_frame(wacom->touch_input);
+		wacom->shared->touch_down = wacom_wac_finger_count_touches(wacom);
+	}
 
 	return 1;
 }
@@ -1761,7 +1771,7 @@ static int wacom_bpt3_touch(struct wacom_wac *wacom)
 static int wacom_bpt_pen(struct wacom_wac *wacom)
 {
 	struct wacom_features *features = &wacom->features;
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->pen_input;
 	unsigned char *data = wacom->data;
 	int prox = 0, x = 0, y = 0, p = 0, d = 0, pen = 0, btn1 = 0, btn2 = 0;
 
@@ -1870,7 +1880,7 @@ static void wacom_bamboo_pad_pen_event(struct wacom_wac *wacom,
 static int wacom_bamboo_pad_touch_event(struct wacom_wac *wacom,
 		unsigned char *data)
 {
-	struct input_dev *input = wacom->input;
+	struct input_dev *input = wacom->touch_input;
 	unsigned char *finger_data, prefix;
 	unsigned id;
 	int x, y;
@@ -2114,7 +2124,10 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 	}
 
 	if (sync) {
-		input_sync(wacom_wac->input);
+		if (wacom_wac->pen_input)
+			input_sync(wacom_wac->pen_input);
+		if (wacom_wac->touch_input)
+			input_sync(wacom_wac->touch_input);
 		if (wacom_wac->pad_input)
 			input_sync(wacom_wac->pad_input);
 	}
@@ -2122,7 +2135,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 
 static void wacom_setup_cintiq(struct wacom_wac *wacom_wac)
 {
-	struct input_dev *input_dev = wacom_wac->input;
+	struct input_dev *input_dev = wacom_wac->pen_input;
 
 	input_set_capability(input_dev, EV_MSC, MSC_SERIAL);
 
@@ -2145,7 +2158,7 @@ static void wacom_setup_cintiq(struct wacom_wac *wacom_wac)
 
 static void wacom_setup_intuos(struct wacom_wac *wacom_wac)
 {
-	struct input_dev *input_dev = wacom_wac->input;
+	struct input_dev *input_dev = wacom_wac->pen_input;
 
 	input_set_capability(input_dev, EV_REL, REL_WHEEL);
 
@@ -2164,15 +2177,57 @@ static void wacom_setup_intuos(struct wacom_wac *wacom_wac)
 	input_set_abs_params(input_dev, ABS_THROTTLE, -1023, 1023, 0, 0);
 }
 
-void wacom_setup_device_quirks(struct wacom_features *features)
+void wacom_setup_device_quirks(struct wacom *wacom)
 {
+	struct wacom_features *features = &wacom->wacom_wac.features;
+
+	/* The pen and pad share the same interface on most devices */
+	if (features->type == GRAPHIRE_BT || features->type == WACOM_G4 ||
+	    features->type == DTUS || features->type == WACOM_MO ||
+	    (features->type >= INTUOS3S && features->type <= WACOM_13HD && 
+	     features->type != INTUOSHT)) {
+		if (features->device_type & WACOM_DEVICETYPE_PEN)
+			features->device_type |= WACOM_DEVICETYPE_PAD;
+	}
 
 	/* touch device found but size is not defined. use default */
-	if (features->device_type == BTN_TOOL_FINGER && !features->x_max) {
+	if (features->device_type & WACOM_DEVICETYPE_TOUCH && !features->x_max) {
 		features->x_max = 1023;
 		features->y_max = 1023;
 	}
 
+	/*
+	 * Intuos5/Pro and Bamboo 3rd gen have no useful data about its
+	 * touch interface in its HID descriptor. If this is the touch
+	 * interface (PacketSize of WACOM_PKGLEN_BBTOUCH3), override the
+	 * tablet values.
+	 */
+	if ((features->type >= INTUOS5S && features->type <= INTUOSHT) ||
+		(features->type == BAMBOO_PT)) {
+		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
+			if (features->touch_max)
+				features->device_type |= WACOM_DEVICETYPE_TOUCH;
+			if (features->type == BAMBOO_PT || features->type == INTUOSHT)
+				features->device_type |= WACOM_DEVICETYPE_PAD;
+
+			features->x_max = 4096;
+			features->y_max = 4096;
+		}
+	}
+
+	/*
+	 * Raw Wacom-mode pen and touch events both come from interface
+	 * 0, whose HID descriptor has an application usage of 0xFF0D
+	 * (i.e., WACOM_VENDORDEFINED_PEN). We route pen packets back
+	 * out through the HID_GENERIC device created for interface 1,
+	 * so rewrite this one to be of type BTN_TOOL_FINGER.
+	 */
+	if (features->type == BAMBOO_PAD)
+		features->device_type |= WACOM_DEVICETYPE_TOUCH;
+
+	if (wacom->hdev->bus == BUS_BLUETOOTH)
+		features->quirks |= WACOM_QUIRK_BATTERY;
+
 	/* quirk for bamboo touch with 2 low res touches */
 	if (features->type == BAMBOO_PT &&
 	    features->pktlen == WACOM_PKGLEN_BBTOUCH) {
@@ -2189,61 +2244,23 @@ void wacom_setup_device_quirks(struct wacom_features *features)
 		features->quirks |= WACOM_QUIRK_NO_INPUT;
 
 		/* must be monitor interface if no device_type set */
-		if (!features->device_type) {
+		if (features->device_type == WACOM_DEVICETYPE_NONE) {
 			features->quirks |= WACOM_QUIRK_MONITOR;
 			features->quirks |= WACOM_QUIRK_BATTERY;
 		}
 	}
 }
 
-static void wacom_abs_set_axis(struct input_dev *input_dev,
-			       struct wacom_wac *wacom_wac)
-{
-	struct wacom_features *features = &wacom_wac->features;
-
-	if (features->device_type == BTN_TOOL_PEN) {
-		input_set_abs_params(input_dev, ABS_X, features->x_min,
-				     features->x_max, features->x_fuzz, 0);
-		input_set_abs_params(input_dev, ABS_Y, features->y_min,
-				     features->y_max, features->y_fuzz, 0);
-		input_set_abs_params(input_dev, ABS_PRESSURE, 0,
-			features->pressure_max, features->pressure_fuzz, 0);
-
-		/* penabled devices have fixed resolution for each model */
-		input_abs_set_res(input_dev, ABS_X, features->x_resolution);
-		input_abs_set_res(input_dev, ABS_Y, features->y_resolution);
-	} else {
-		if (features->touch_max == 1) {
-			input_set_abs_params(input_dev, ABS_X, 0,
-				features->x_max, features->x_fuzz, 0);
-			input_set_abs_params(input_dev, ABS_Y, 0,
-				features->y_max, features->y_fuzz, 0);
-			input_abs_set_res(input_dev, ABS_X,
-					  features->x_resolution);
-			input_abs_set_res(input_dev, ABS_Y,
-					  features->y_resolution);
-		}
-
-		if (features->touch_max > 1) {
-			input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0,
-				features->x_max, features->x_fuzz, 0);
-			input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
-				features->y_max, features->y_fuzz, 0);
-			input_abs_set_res(input_dev, ABS_MT_POSITION_X,
-					  features->x_resolution);
-			input_abs_set_res(input_dev, ABS_MT_POSITION_Y,
-					  features->y_resolution);
-		}
-	}
-}
-
-int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
+int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 				   struct wacom_wac *wacom_wac)
 {
 	struct wacom_features *features = &wacom_wac->features;
 
 	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 
+	if (!(features->device_type & WACOM_DEVICETYPE_PEN))
+		return -ENODEV;
+
 	if (features->type == HID_GENERIC)
 		/* setup has already been done */
 		return 0;
@@ -2251,7 +2268,17 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 	__set_bit(ABS_MISC, input_dev->absbit);
 
-	wacom_abs_set_axis(input_dev, wacom_wac);
+	input_set_abs_params(input_dev, ABS_X, features->x_min,
+			     features->x_max, features->x_fuzz, 0);
+	input_set_abs_params(input_dev, ABS_Y, features->y_min,
+			     features->y_max, features->y_fuzz, 0);
+	input_set_abs_params(input_dev, ABS_PRESSURE, 0,
+		features->pressure_max, features->pressure_fuzz, 0);
+
+	/* penabled devices have fixed resolution for each model */
+	input_abs_set_res(input_dev, ABS_X, features->x_resolution);
+	input_abs_set_res(input_dev, ABS_Y, features->y_resolution);
+
 
 	switch (features->type) {
 	case GRAPHIRE_BT:
@@ -2320,53 +2347,25 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 	case INTUOSPS:
 		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
 
-		if (features->device_type == BTN_TOOL_PEN) {
-			input_set_abs_params(input_dev, ABS_DISTANCE, 0,
-					      features->distance_max,
-					      0, 0);
-
-			input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0);
-			input_abs_set_res(input_dev, ABS_Z, 287);
+		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
+				      features->distance_max,
+				      0, 0);
 
-			wacom_setup_intuos(wacom_wac);
-		} else if (features->device_type == BTN_TOOL_FINGER) {
-			__clear_bit(ABS_MISC, input_dev->absbit);
+		input_set_abs_params(input_dev, ABS_Z, -900, 899, 0, 0);
+		input_abs_set_res(input_dev, ABS_Z, 287);
 
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR,
-			                     0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR,
-			                     0, features->y_max, 0, 0);
-			input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
-		}
+		wacom_setup_intuos(wacom_wac);
 		break;
 
 	case WACOM_24HDT:
-		if (features->device_type == BTN_TOOL_FINGER) {
-			input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0);
-			input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
-		}
-		/* fall through */
-
 	case WACOM_27QHDT:
 	case MTSCREEN:
 	case MTTPC:
 	case MTTPC_B:
 	case TABLETPC2FG:
-		if (features->device_type == BTN_TOOL_FINGER && features->touch_max > 1)
-			input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
-		/* fall through */
-
 	case TABLETPC:
 	case TABLETPCE:
 		__clear_bit(ABS_MISC, input_dev->absbit);
-
-		__set_bit(INPUT_PROP_DIRECT, input_dev->propbit);
-
-		if (features->device_type != BTN_TOOL_PEN)
-			break;  /* no need to process stylus stuff */
-
 		/* fall through */
 
 	case DTUS:
@@ -2394,50 +2393,114 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 		break;
 
 	case INTUOSHT:
-		if (features->touch_max &&
-		    features->device_type == BTN_TOOL_FINGER) {
-			input_dev->evbit[0] |= BIT_MASK(EV_SW);
-			__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
-		}
-		/* fall through */
-
 	case BAMBOO_PT:
 		__clear_bit(ABS_MISC, input_dev->absbit);
 
-		if (features->device_type == BTN_TOOL_FINGER) {
+		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
+		__set_bit(BTN_TOOL_RUBBER, input_dev->keybit);
+		__set_bit(BTN_TOOL_PEN, input_dev->keybit);
+		__set_bit(BTN_STYLUS, input_dev->keybit);
+		__set_bit(BTN_STYLUS2, input_dev->keybit);
+		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
+				      features->distance_max,
+				      0, 0);
+		break;
+	case BAMBOO_PAD:
+		__clear_bit(ABS_MISC, input_dev->absbit);
+		break;
+	}
+	return 0;
+}
 
-			if (features->touch_max) {
-				if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
-					input_set_abs_params(input_dev,
-						     ABS_MT_TOUCH_MAJOR,
-						     0, features->x_max, 0, 0);
-					input_set_abs_params(input_dev,
-						     ABS_MT_TOUCH_MINOR,
-						     0, features->y_max, 0, 0);
-				}
-				input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
-			} else {
-				/* buttons/keys only interface */
-				__clear_bit(ABS_X, input_dev->absbit);
-				__clear_bit(ABS_Y, input_dev->absbit);
-				__clear_bit(BTN_TOUCH, input_dev->keybit);
+int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
+					 struct wacom_wac *wacom_wac)
+{
+	struct wacom_features *features = &wacom_wac->features;
 
-				/* PAD is setup by wacom_setup_pad_input_capabilities later */
-				return 1;
-			}
-		} else if (features->device_type == BTN_TOOL_PEN) {
-			__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
-			__set_bit(BTN_TOOL_RUBBER, input_dev->keybit);
-			__set_bit(BTN_TOOL_PEN, input_dev->keybit);
-			__set_bit(BTN_STYLUS, input_dev->keybit);
-			__set_bit(BTN_STYLUS2, input_dev->keybit);
-			input_set_abs_params(input_dev, ABS_DISTANCE, 0,
-					      features->distance_max,
-					      0, 0);
+	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
+
+	if (!(features->device_type & WACOM_DEVICETYPE_TOUCH))
+		return -ENODEV;
+
+	if (features->type == HID_GENERIC)
+		/* setup has already been done */
+		return 0;
+
+	__set_bit(BTN_TOUCH, input_dev->keybit);
+
+	if (features->touch_max == 1) {
+		input_set_abs_params(input_dev, ABS_X, 0,
+			features->x_max, features->x_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_Y, 0,
+			features->y_max, features->y_fuzz, 0);
+		input_abs_set_res(input_dev, ABS_X,
+				  features->x_resolution);
+		input_abs_set_res(input_dev, ABS_Y,
+				  features->y_resolution);
+	}
+	else if (features->touch_max > 1) {
+		input_set_abs_params(input_dev, ABS_MT_POSITION_X, 0,
+			features->x_max, features->x_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_MT_POSITION_Y, 0,
+			features->y_max, features->y_fuzz, 0);
+		input_abs_set_res(input_dev, ABS_MT_POSITION_X,
+				  features->x_resolution);
+		input_abs_set_res(input_dev, ABS_MT_POSITION_Y,
+				  features->y_resolution);
+	}
+
+	switch (features->type) {
+	case INTUOS5:
+	case INTUOS5L:
+	case INTUOSPM:
+	case INTUOSPL:
+	case INTUOS5S:
+	case INTUOSPS:
+		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
+
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MINOR, 0, features->y_max, 0, 0);
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
+		break;
+
+	case WACOM_24HDT:
+		input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_WIDTH_MAJOR, 0, features->x_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_WIDTH_MINOR, 0, features->y_max, 0, 0);
+		input_set_abs_params(input_dev, ABS_MT_ORIENTATION, 0, 1, 0, 0);
+		/* fall through */
+
+	case WACOM_27QHDT:
+	case MTSCREEN:
+	case MTTPC:
+	case MTTPC_B:
+	case TABLETPC2FG:
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
+		/*fall through */
+
+	case TABLETPC:
+	case TABLETPCE:
+		__set_bit(INPUT_PROP_DIRECT, input_dev->propbit);
+		break;
+
+	case INTUOSHT:
+		input_dev->evbit[0] |= BIT_MASK(EV_SW);
+		__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
+		/* fall through */
+
+	case BAMBOO_PT:
+		if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
+			input_set_abs_params(input_dev,
+				     ABS_MT_TOUCH_MAJOR,
+				     0, features->x_max, 0, 0);
+			input_set_abs_params(input_dev,
+				     ABS_MT_TOUCH_MINOR,
+				     0, features->y_max, 0, 0);
 		}
+		input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
 		break;
+
 	case BAMBOO_PAD:
-		__clear_bit(ABS_MISC, input_dev->absbit);
 		input_mt_init_slots(input_dev, features->touch_max,
 				    INPUT_MT_POINTER);
 		__set_bit(BTN_LEFT, input_dev->keybit);
@@ -2453,6 +2516,9 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 	struct wacom_features *features = &wacom_wac->features;
 	int i;
 
+	if (!(features->device_type & WACOM_DEVICETYPE_PAD))
+		return -ENODEV;
+
 	input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
 
 	/* kept for making legacy xf86-input-wacom working with the wheels */
@@ -2589,10 +2655,6 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 
 	case INTUOS5S:
 	case INTUOSPS:
-		/* touch interface does not have the pad device */
-		if (features->device_type != BTN_TOOL_PEN)
-			return -ENODEV;
-
 		for (i = 0; i < 7; i++)
 			__set_bit(BTN_0 + i, input_dev->keybit);
 
@@ -2634,12 +2696,6 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 
 	case INTUOSHT:
 	case BAMBOO_PT:
-		/* pad device is on the touch interface */
-		if ((features->device_type != BTN_TOOL_FINGER) ||
-		    /* Bamboo Pen only tablet does not have pad */
-		    ((features->type == BAMBOO_PT) && !features->touch_max))
-			return -ENODEV;
-
 		__clear_bit(ABS_MISC, input_dev->absbit);
 
 		__set_bit(BTN_LEFT, input_dev->keybit);
@@ -2919,6 +2975,9 @@ static const struct wacom_features wacom_features_0x32F =
 	{ "Wacom DTU1031X", 22472, 12728, 511, 0,
 	  DTUSX, WACOM_INTUOS_RES, WACOM_INTUOS_RES,
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
+static const struct wacom_features wacom_features_0x336 =
+	{ "Wacom DTU1141", 23472, 13203, 1023, 0,
+	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x57 =
 	{ "Wacom DTK2241", 95640, 54060, 2047, 63,
 	  DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
@@ -3272,6 +3331,7 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x32F) },
 	{ USB_DEVICE_WACOM(0x333) },
 	{ USB_DEVICE_WACOM(0x335) },
+	{ USB_DEVICE_WACOM(0x336) },
 	{ USB_DEVICE_WACOM(0x4001) },
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 4700ac994a3b..2978c303909d 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -18,10 +18,7 @@
 #define WACOM_NAME_MAX		64
 
 /* packet length for individual models */
-#define WACOM_PKGLEN_PENPRTN	 7
-#define WACOM_PKGLEN_GRAPHIRE	 8
 #define WACOM_PKGLEN_BBFUN	 9
-#define WACOM_PKGLEN_INTUOS	10
 #define WACOM_PKGLEN_TPC1FG	 5
 #define WACOM_PKGLEN_TPC1FG_B	10
 #define WACOM_PKGLEN_TPC2FG	14
@@ -29,9 +26,6 @@
 #define WACOM_PKGLEN_BBTOUCH3	64
 #define WACOM_PKGLEN_BBPEN	10
 #define WACOM_PKGLEN_WIRELESS	32
-#define WACOM_PKGLEN_MTOUCH	62
-#define WACOM_PKGLEN_MTTPC	40
-#define WACOM_PKGLEN_DTUS	68
 #define WACOM_PKGLEN_PENABLED	 8
 #define WACOM_PKGLEN_BPAD_TOUCH	32
 #define WACOM_PKGLEN_BPAD_TOUCH_USB	64
@@ -78,10 +72,20 @@
 #define WACOM_QUIRK_MONITOR		0x0004
 #define WACOM_QUIRK_BATTERY		0x0008
 
+/* device types */
+#define WACOM_DEVICETYPE_NONE           0x0000
+#define WACOM_DEVICETYPE_PEN            0x0001
+#define WACOM_DEVICETYPE_TOUCH          0x0002
+#define WACOM_DEVICETYPE_PAD            0x0004
+
+#define WACOM_VENDORDEFINED_PEN		0xff0d0001
+
 #define WACOM_PEN_FIELD(f)	(((f)->logical == HID_DG_STYLUS) || \
 				 ((f)->physical == HID_DG_STYLUS) || \
 				 ((f)->physical == HID_DG_PEN) || \
-				 ((f)->application == HID_DG_PEN))
+				 ((f)->application == HID_DG_PEN) || \
+				 ((f)->application == HID_DG_DIGITIZER) || \
+				 ((f)->application == WACOM_VENDORDEFINED_PEN))
 #define WACOM_FINGER_FIELD(f)	(((f)->logical == HID_DG_FINGER) || \
 				 ((f)->physical == HID_DG_FINGER) || \
 				 ((f)->application == HID_DG_TOUCHSCREEN))
@@ -192,7 +196,8 @@ struct hid_data {
 };
 
 struct wacom_wac {
-	char name[WACOM_NAME_MAX];
+	char pen_name[WACOM_NAME_MAX];
+	char touch_name[WACOM_NAME_MAX];
 	char pad_name[WACOM_NAME_MAX];
 	char bat_name[WACOM_NAME_MAX];
 	char ac_name[WACOM_NAME_MAX];
@@ -203,9 +208,11 @@ struct wacom_wac {
 	bool reporting_data;
 	struct wacom_features features;
 	struct wacom_shared *shared;
-	struct input_dev *input;
+	struct input_dev *pen_input;
+	struct input_dev *touch_input;
 	struct input_dev *pad_input;
-	bool input_registered;
+	bool pen_registered;
+	bool touch_registered;
 	bool pad_registered;
 	int pid;
 	int battery_capacity;
diff --git a/drivers/hsi/clients/cmt_speech.c b/drivers/hsi/clients/cmt_speech.c
index 4983529a9c6c..d04643f9548b 100644
--- a/drivers/hsi/clients/cmt_speech.c
+++ b/drivers/hsi/clients/cmt_speech.c
@@ -451,9 +451,14 @@ static void cs_hsi_read_on_control_complete(struct hsi_msg *msg)
 	dev_dbg(&hi->cl->device, "Read on control: %08X\n", cmd);
 	cs_release_cmd(msg);
 	if (hi->flags & CS_FEAT_TSTAMP_RX_CTRL) {
-		struct timespec *tstamp =
+		struct timespec tspec;
+		struct cs_timestamp *tstamp =
 			&hi->mmap_cfg->tstamp_rx_ctrl;
-		do_posix_clock_monotonic_gettime(tstamp);
+
+		ktime_get_ts(&tspec);
+
+		tstamp->tv_sec = (__u32) tspec.tv_sec;
+		tstamp->tv_nsec = (__u32) tspec.tv_nsec;
 	}
 	spin_unlock(&hi->lock);
 
diff --git a/drivers/hsi/clients/nokia-modem.c b/drivers/hsi/clients/nokia-modem.c
index bbb19231fa82..7f82c911ad74 100644
--- a/drivers/hsi/clients/nokia-modem.c
+++ b/drivers/hsi/clients/nokia-modem.c
@@ -112,7 +112,8 @@ static int nokia_modem_gpio_probe(struct device *dev)
 	modem->gpio_amount = gpio_count;
 
 	for (i = 0; i < gpio_count; i++) {
-		modem->gpios[i].gpio = devm_gpiod_get_index(dev, NULL, i);
+		modem->gpios[i].gpio = devm_gpiod_get_index(dev, NULL, i,
+							    GPIOD_OUT_LOW);
 		if (IS_ERR(modem->gpios[i].gpio)) {
 			dev_err(dev, "Could not get gpio %d\n", i);
 			return PTR_ERR(modem->gpios[i].gpio);
@@ -125,10 +126,6 @@ static int nokia_modem_gpio_probe(struct device *dev)
 			return err;
 		}
 
-		err = gpiod_direction_output(modem->gpios[i].gpio, 0);
-		if (err)
-			return err;
-
 		err = gpiod_export(modem->gpios[i].gpio, 0);
 		if (err)
 			return err;
@@ -208,7 +205,7 @@ static int nokia_modem_probe(struct device *dev)
 
 	err = device_attach(&modem->ssi_protocol->device);
 	if (err == 0) {
-		dev_err(dev, "Missing ssi-protocol driver\n");
+		dev_dbg(dev, "Missing ssi-protocol driver\n");
 		err = -EPROBE_DEFER;
 		goto error3;
 	} else if (err < 0) {
@@ -231,7 +228,7 @@ static int nokia_modem_probe(struct device *dev)
 
 	err = device_attach(&modem->cmt_speech->device);
 	if (err == 0) {
-		dev_err(dev, "Missing cmt-speech driver\n");
+		dev_dbg(dev, "Missing cmt-speech driver\n");
 		err = -EPROBE_DEFER;
 		goto error4;
 	} else if (err < 0) {
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 25d9e72627e9..54075a07d2a1 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -509,7 +509,7 @@ config SENSORS_G762
 
 config SENSORS_GPIO_FAN
 	tristate "GPIO fan"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	depends on THERMAL || THERMAL=n
 	help
 	  If you say yes here you get support for fans connected to GPIO lines.
@@ -1106,8 +1106,8 @@ config SENSORS_NTC_THERMISTOR
 	  send notifications about the temperature.
 
 	  Currently, this driver supports
-	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, and NCP15WL333
-	  from Murata and B57330V2103 from EPCOS.
+	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333,
+	  and NCP03WF104 from Murata and B57330V2103 from EPCOS.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called ntc-thermistor.
@@ -1186,7 +1186,7 @@ config SENSORS_PWM_FAN
 
 config SENSORS_SHT15
 	tristate "Sensiron humidity and temperature sensors. SHT15 and compat."
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  If you say yes here you get support for the Sensiron SHT10, SHT11,
 	  SHT15, SHT71, SHT75 humidity and temperature sensors.
@@ -1452,6 +1452,16 @@ config SENSORS_INA2XX
 	  This driver can also be built as a module.  If so, the module
 	  will be called ina2xx.
 
+config SENSORS_TC74
+	tristate "Microchip TC74"
+	depends on I2C
+	help
+	  If you say yes here you get support for Microchip TC74 single
+	  input temperature sensor chips.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called tc74.
+
 config SENSORS_THMC50
 	tristate "Texas Instruments THMC50 / Analog Devices ADM1022"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index b4a40f17e2aa..ab904027f074 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -140,6 +140,7 @@ obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
 obj-$(CONFIG_SENSORS_SMSC47M1)	+= smsc47m1.o
 obj-$(CONFIG_SENSORS_SMSC47M192)+= smsc47m192.o
 obj-$(CONFIG_SENSORS_AMC6821)	+= amc6821.o
+obj-$(CONFIG_SENSORS_TC74)	+= tc74.o
 obj-$(CONFIG_SENSORS_THMC50)	+= thmc50.o
 obj-$(CONFIG_SENSORS_TMP102)	+= tmp102.o
 obj-$(CONFIG_SENSORS_TMP103)	+= tmp103.o
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index 4c829bb2f9db..f2f2f2fc755a 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -12,10 +12,9 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
+ * The ATXP1 can reside on I2C addresses 0x37 or 0x4e. The chip is
+ * not auto-detected by the driver and must be instantiated explicitly.
+ * See Documentation/i2c/instantiating-devices for more information.
  */
 
 #include <linux/kernel.h>
@@ -43,8 +42,6 @@ MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
 #define ATXP1_VIDMASK	0x1f
 #define ATXP1_GPIO1MASK	0x0f
 
-static const unsigned short normal_i2c[] = { 0x37, 0x4e, I2C_CLIENT_END };
-
 struct atxp1_data {
 	struct i2c_client *client;
 	struct mutex update_lock;
@@ -259,48 +256,6 @@ static struct attribute *atxp1_attrs[] = {
 };
 ATTRIBUTE_GROUPS(atxp1);
 
-/* Return 0 if detection is successful, -ENODEV otherwise */
-static int atxp1_detect(struct i2c_client *new_client,
-			struct i2c_board_info *info)
-{
-	struct i2c_adapter *adapter = new_client->adapter;
-
-	u8 temp;
-
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
-		return -ENODEV;
-
-	/* Detect ATXP1, checking if vendor ID registers are all zero */
-	if (!((i2c_smbus_read_byte_data(new_client, 0x3e) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0x3f) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0xfe) == 0) &&
-	     (i2c_smbus_read_byte_data(new_client, 0xff) == 0)))
-		return -ENODEV;
-
-	/*
-	 * No vendor ID, now checking if registers 0x10,0x11 (non-existent)
-	 * showing the same as register 0x00
-	 */
-	temp = i2c_smbus_read_byte_data(new_client, 0x00);
-
-	if (!((i2c_smbus_read_byte_data(new_client, 0x10) == temp) &&
-	      (i2c_smbus_read_byte_data(new_client, 0x11) == temp)))
-		return -ENODEV;
-
-	/* Get VRM */
-	temp = vid_which_vrm();
-
-	if ((temp != 90) && (temp != 91)) {
-		dev_err(&adapter->dev, "atxp1: Not supporting VRM %d.%d\n",
-				temp / 10, temp % 10);
-		return -ENODEV;
-	}
-
-	strlcpy(info->type, "atxp1", I2C_NAME_SIZE);
-
-	return 0;
-}
-
 static int atxp1_probe(struct i2c_client *client,
 		       const struct i2c_device_id *id)
 {
@@ -314,6 +269,11 @@ static int atxp1_probe(struct i2c_client *client,
 
 	/* Get VRM */
 	data->vrm = vid_which_vrm();
+	if (data->vrm != 90 && data->vrm != 91) {
+		dev_err(dev, "atxp1: Not supporting VRM %d.%d\n",
+			data->vrm / 10, data->vrm % 10);
+		return -ENODEV;
+	}
 
 	data->client = client;
 	mutex_init(&data->update_lock);
@@ -342,8 +302,6 @@ static struct i2c_driver atxp1_driver = {
 	},
 	.probe		= atxp1_probe,
 	.id_table	= atxp1_id,
-	.detect		= atxp1_detect,
-	.address_list	= normal_i2c,
 };
 
 module_i2c_driver(atxp1_driver);
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index ed303ba3a593..3e03379e7c5d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -63,7 +63,8 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 #define TO_ATTR_NO(cpu)		(TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)
 
 #ifdef CONFIG_SMP
-#define for_each_sibling(i, cpu)	for_each_cpu(i, cpu_sibling_mask(cpu))
+#define for_each_sibling(i, cpu) \
+	for_each_cpu(i, topology_sibling_cpumask(cpu))
 #else
 #define for_each_sibling(i, cpu)	for (i = 0; false; )
 #endif
diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c
index cb0dcfda958c..07628569547a 100644
--- a/drivers/hwmon/max197.c
+++ b/drivers/hwmon/max197.c
@@ -324,7 +324,7 @@ static int max197_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id max197_device_ids[] = {
+static const struct platform_device_id max197_device_ids[] = {
 	{ "max197", max197 },
 	{ "max199", max199 },
 	{ }
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index f3830db02d46..37f01702d081 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -439,6 +439,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				 (*t)->dev_attr.attr.name, tg->base + i);
 			if ((*t)->s2) {
 				a2 = &su->u.a2;
+				sysfs_attr_init(&a2->dev_attr.attr);
 				a2->dev_attr.attr.name = su->name;
 				a2->nr = (*t)->u.s.nr + i;
 				a2->index = (*t)->u.s.index;
@@ -449,6 +450,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				*attrs = &a2->dev_attr.attr;
 			} else {
 				a = &su->u.a1;
+				sysfs_attr_init(&a->dev_attr.attr);
 				a->dev_attr.attr.name = su->name;
 				a->index = (*t)->u.index + i;
 				a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 4fcb48103299..bd1c99deac71 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -995,6 +995,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				 (*t)->dev_attr.attr.name, tg->base + i);
 			if ((*t)->s2) {
 				a2 = &su->u.a2;
+				sysfs_attr_init(&a2->dev_attr.attr);
 				a2->dev_attr.attr.name = su->name;
 				a2->nr = (*t)->u.s.nr + i;
 				a2->index = (*t)->u.s.index;
@@ -1005,6 +1006,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
 				*attrs = &a2->dev_attr.attr;
 			} else {
 				a = &su->u.a1;
+				sysfs_attr_init(&a->dev_attr.attr);
 				a->dev_attr.attr.name = su->name;
 				a->index = (*t)->u.index + i;
 				a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 112e4d45e4a0..dc0b76c5e302 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -53,6 +53,7 @@ static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp03wb473", TYPE_NCPXXWB473 },
 	{ "ncp15wl333", TYPE_NCPXXWL333 },
 	{ "b57330v2103", TYPE_B57330V2103},
+	{ "ncp03wf104", TYPE_NCPXXWF104 },
 	{ },
 };
 
@@ -135,6 +136,43 @@ static const struct ntc_compensation ncpXXwl333[] = {
 	{ .temp_c	= 125, .ohm	= 707 },
 };
 
+static const struct ntc_compensation ncpXXwf104[] = {
+	{ .temp_c	= -40, .ohm	= 4397119 },
+	{ .temp_c	= -35, .ohm	= 3088599 },
+	{ .temp_c	= -30, .ohm	= 2197225 },
+	{ .temp_c	= -25, .ohm	= 1581881 },
+	{ .temp_c	= -20, .ohm	= 1151037 },
+	{ .temp_c	= -15, .ohm	= 846579 },
+	{ .temp_c	= -10, .ohm	= 628988 },
+	{ .temp_c	= -5, .ohm	= 471632 },
+	{ .temp_c	= 0, .ohm	= 357012 },
+	{ .temp_c	= 5, .ohm	= 272500 },
+	{ .temp_c	= 10, .ohm	= 209710 },
+	{ .temp_c	= 15, .ohm	= 162651 },
+	{ .temp_c	= 20, .ohm	= 127080 },
+	{ .temp_c	= 25, .ohm	= 100000 },
+	{ .temp_c	= 30, .ohm	= 79222 },
+	{ .temp_c	= 35, .ohm	= 63167 },
+	{ .temp_c	= 40, .ohm	= 50677 },
+	{ .temp_c	= 45, .ohm	= 40904 },
+	{ .temp_c	= 50, .ohm	= 33195 },
+	{ .temp_c	= 55, .ohm	= 27091 },
+	{ .temp_c	= 60, .ohm	= 22224 },
+	{ .temp_c	= 65, .ohm	= 18323 },
+	{ .temp_c	= 70, .ohm	= 15184 },
+	{ .temp_c	= 75, .ohm	= 12635 },
+	{ .temp_c	= 80, .ohm	= 10566 },
+	{ .temp_c	= 85, .ohm	= 8873 },
+	{ .temp_c	= 90, .ohm	= 7481 },
+	{ .temp_c	= 95, .ohm	= 6337 },
+	{ .temp_c	= 100, .ohm	= 5384 },
+	{ .temp_c	= 105, .ohm	= 4594 },
+	{ .temp_c	= 110, .ohm	= 3934 },
+	{ .temp_c	= 115, .ohm	= 3380 },
+	{ .temp_c	= 120, .ohm	= 2916 },
+	{ .temp_c	= 125, .ohm	= 2522 },
+};
+
 /*
  * The following compensation table is from the specification of EPCOS NTC
  * Thermistors Datasheet
@@ -190,20 +228,21 @@ struct ntc_data {
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
-	s64 result;
-	int val, ret;
+	int raw, uv, ret;
 
-	ret = iio_read_channel_raw(channel, &val);
+	ret = iio_read_channel_raw(channel, &raw);
 	if (ret < 0) {
 		pr_err("read channel() error: %d\n", ret);
 		return ret;
 	}
 
-	/* unit: mV */
-	result = pdata->pullup_uv * (s64) val;
-	result >>= 12;
+	ret = iio_convert_raw_to_processed(channel, raw, &uv, 1000);
+	if (ret < 0) {
+		/* Assume 12 bit ADC with vref at pullup_uv */
+		uv = (pdata->pullup_uv * (s64)raw) >> 12;
+	}
 
-	return (int)result;
+	return uv;
 }
 
 static const struct of_device_id ntc_match[] = {
@@ -219,6 +258,8 @@ static const struct of_device_id ntc_match[] = {
 		.data = &ntc_thermistor_id[4] },
 	{ .compatible = "epcos,b57330v2103",
 		.data = &ntc_thermistor_id[5]},
+	{ .compatible = "murata,ncp03wf104",
+		.data = &ntc_thermistor_id[6] },
 
 	/* Usage of vendor name "ntc" is deprecated */
 	{ .compatible = "ntc,ncp15wb473",
@@ -239,8 +280,10 @@ static struct ntc_thermistor_platform_data *
 ntc_thermistor_parse_dt(struct platform_device *pdev)
 {
 	struct iio_channel *chan;
+	enum iio_chan_type type;
 	struct device_node *np = pdev->dev.of_node;
 	struct ntc_thermistor_platform_data *pdata;
+	int ret;
 
 	if (!np)
 		return NULL;
@@ -253,6 +296,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
 	if (IS_ERR(chan))
 		return ERR_CAST(chan);
 
+	ret = iio_get_channel_type(chan, &type);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	if (type != IIO_VOLTAGE)
+		return ERR_PTR(-EINVAL);
+
 	if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv))
 		return ERR_PTR(-ENODEV);
 	if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm))
@@ -300,30 +350,27 @@ static inline u64 div64_u64_safe(u64 dividend, u64 divisor)
 static int get_ohm_of_thermistor(struct ntc_data *data, unsigned int uv)
 {
 	struct ntc_thermistor_platform_data *pdata = data->pdata;
-	u64 mv = uv / 1000;
-	u64 pmv = pdata->pullup_uv / 1000;
+	u32 puv = pdata->pullup_uv;
 	u64 n, puo, pdo;
 	puo = pdata->pullup_ohm;
 	pdo = pdata->pulldown_ohm;
 
-	if (mv == 0) {
-		if (pdata->connect == NTC_CONNECTED_POSITIVE)
-			return INT_MAX;
-		return 0;
-	}
-	if (mv >= pmv)
+	if (uv == 0)
+		return (pdata->connect == NTC_CONNECTED_POSITIVE) ?
+			INT_MAX : 0;
+	if (uv >= puv)
 		return (pdata->connect == NTC_CONNECTED_POSITIVE) ?
 			0 : INT_MAX;
 
 	if (pdata->connect == NTC_CONNECTED_POSITIVE && puo == 0)
-		n = div64_u64_safe(pdo * (pmv - mv), mv);
+		n = div_u64(pdo * (puv - uv), uv);
 	else if (pdata->connect == NTC_CONNECTED_GROUND && pdo == 0)
-		n = div64_u64_safe(puo * mv, pmv - mv);
+		n = div_u64(puo * uv, puv - uv);
 	else if (pdata->connect == NTC_CONNECTED_POSITIVE)
-		n = div64_u64_safe(pdo * puo * (pmv - mv),
-				puo * mv - pdo * (pmv - mv));
+		n = div64_u64_safe(pdo * puo * (puv - uv),
+				puo * uv - pdo * (puv - uv));
 	else
-		n = div64_u64_safe(pdo * puo * mv, pdo * (pmv - mv) - puo * mv);
+		n = div64_u64_safe(pdo * puo * uv, pdo * (puv - uv) - puo * uv);
 
 	if (n > INT_MAX)
 		n = INT_MAX;
@@ -558,6 +605,10 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 		data->comp = b57330v2103;
 		data->n_comp = ARRAY_SIZE(b57330v2103);
 		break;
+	case TYPE_NCPXXWF104:
+		data->comp = ncpXXwf104;
+		data->n_comp = ARRAY_SIZE(ncpXXwf104);
+		break;
 	default:
 		dev_err(&pdev->dev, "Unknown device type: %lu(%s)\n",
 				pdev_id->driver_data, pdev_id->name);
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index d4f0935daaa1..497a7f822a12 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -1074,7 +1074,7 @@ static int sht15_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id sht15_device_ids[] = {
+static const struct platform_device_id sht15_device_ids[] = {
 	{ "sht10", sht10 },
 	{ "sht11", sht11 },
 	{ "sht15", sht15 },
diff --git a/drivers/hwmon/tc74.c b/drivers/hwmon/tc74.c
new file mode 100644
index 000000000000..d95165158800
--- /dev/null
+++ b/drivers/hwmon/tc74.c
@@ -0,0 +1,177 @@
+/*
+ * An hwmon driver for the Microchip TC74
+ *
+ * Copyright 2015 Maciej Szmigiero <mail@maciej.szmigiero.name>
+ *
+ * Based on ad7414.c:
+ *	Copyright 2006 Stefan Roese, DENX Software Engineering
+ *	Copyright 2008 Sean MacLennan, PIKA Technologies
+ *	Copyright 2008 Frank Edelhaeuser, Spansion Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+/* TC74 registers */
+#define TC74_REG_TEMP		0x00
+#define TC74_REG_CONFIG		0x01
+
+struct tc74_data {
+	struct i2c_client	*client;
+	struct mutex		lock;	/* atomic read data updates */
+	bool			valid;	/* validity of fields below */
+	unsigned long		next_update;	/* In jiffies */
+	s8			temp_input;	/* Temp value in dC */
+};
+
+static int tc74_update_device(struct device *dev)
+{
+	struct tc74_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int ret;
+
+	ret = mutex_lock_interruptible(&data->lock);
+	if (ret)
+		return ret;
+
+	if (time_after(jiffies, data->next_update) || !data->valid) {
+		s32 value;
+
+		value = i2c_smbus_read_byte_data(client, TC74_REG_CONFIG);
+		if (value < 0) {
+			dev_dbg(&client->dev, "TC74_REG_CONFIG read err %d\n",
+				(int)value);
+
+			ret = value;
+			goto ret_unlock;
+		}
+
+		if (!(value & BIT(6))) {
+			/* not ready yet */
+
+			ret = -EAGAIN;
+			goto ret_unlock;
+		}
+
+		value = i2c_smbus_read_byte_data(client, TC74_REG_TEMP);
+		if (value < 0) {
+			dev_dbg(&client->dev, "TC74_REG_TEMP read err %d\n",
+				(int)value);
+
+			ret = value;
+			goto ret_unlock;
+		}
+
+		data->temp_input = value;
+		data->next_update = jiffies + HZ / 4;
+		data->valid = true;
+	}
+
+ret_unlock:
+	mutex_unlock(&data->lock);
+
+	return ret;
+}
+
+static ssize_t show_temp_input(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct tc74_data *data = dev_get_drvdata(dev);
+	int ret;
+
+	ret = tc74_update_device(dev);
+	if (ret)
+		return ret;
+
+	return sprintf(buf, "%d\n", data->temp_input * 1000);
+}
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp_input, NULL, 0);
+
+static struct attribute *tc74_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(tc74);
+
+static int tc74_probe(struct i2c_client *client,
+		      const struct i2c_device_id *dev_id)
+{
+	struct device *dev = &client->dev;
+	struct tc74_data *data;
+	struct device *hwmon_dev;
+	s32 conf;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -EOPNOTSUPP;
+
+	data = devm_kzalloc(dev, sizeof(struct tc74_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	mutex_init(&data->lock);
+
+	/* Make sure the chip is powered up. */
+	conf = i2c_smbus_read_byte_data(client, TC74_REG_CONFIG);
+	if (conf < 0) {
+		dev_err(dev, "unable to read config register\n");
+
+		return conf;
+	}
+
+	if (conf & 0x3f) {
+		dev_err(dev, "invalid config register value\n");
+
+		return -ENODEV;
+	}
+
+	if (conf & BIT(7)) {
+		s32 ret;
+
+		conf &= ~BIT(7);
+
+		ret = i2c_smbus_write_byte_data(client, TC74_REG_CONFIG, conf);
+		if (ret)
+			dev_warn(dev, "unable to disable STANDBY\n");
+	}
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
+							   client->name,
+							   data, tc74_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct i2c_device_id tc74_id[] = {
+	{ "tc74", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, tc74_id);
+
+static struct i2c_driver tc74_driver = {
+	.driver = {
+		.name	= "tc74",
+	},
+	.probe	= tc74_probe,
+	.id_table = tc74_id,
+};
+
+module_i2c_driver(tc74_driver);
+
+MODULE_AUTHOR("Maciej Szmigiero <mail@maciej.szmigiero.name>");
+
+MODULE_DESCRIPTION("TC74 driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c
index 99664ebc738d..ccf4cffe0ee1 100644
--- a/drivers/hwmon/tmp401.c
+++ b/drivers/hwmon/tmp401.c
@@ -44,7 +44,7 @@
 #include <linux/sysfs.h>
 
 /* Addresses to scan */
-static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d,
+static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d,
 	0x4e, 0x4f, I2C_CLIENT_END };
 
 enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 };
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 2255af23b9c7..5f1c1c4f5d87 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -1103,7 +1103,7 @@ config I2C_SIBYTE
 
 config I2C_CROS_EC_TUNNEL
 	tristate "ChromeOS EC tunnel I2C bus"
-	depends on MFD_CROS_EC
+	depends on CROS_EC_PROTO
 	help
 	  If you say yes here you get an I2C bus that will tunnel i2c commands
 	  through to the other side of the ChromeOS EC to the i2c bus
diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
index fa8dedd8c3a2..a0d95ff682ae 100644
--- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c
+++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c
@@ -182,8 +182,9 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 	const u16 bus_num = bus->remote_bus;
 	int request_len;
 	int response_len;
+	int alloc_size;
 	int result;
-	struct cros_ec_command msg = { };
+	struct cros_ec_command *msg;
 
 	request_len = ec_i2c_count_message(i2c_msgs, num);
 	if (request_len < 0) {
@@ -198,25 +199,39 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[],
 		return response_len;
 	}
 
-	result = ec_i2c_construct_message(msg.outdata, i2c_msgs, num, bus_num);
-	if (result)
-		return result;
+	alloc_size = max(request_len, response_len);
+	msg = kmalloc(sizeof(*msg) + alloc_size, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
 
-	msg.version = 0;
-	msg.command = EC_CMD_I2C_PASSTHRU;
-	msg.outsize = request_len;
-	msg.insize = response_len;
+	result = ec_i2c_construct_message(msg->data, i2c_msgs, num, bus_num);
+	if (result) {
+		dev_err(dev, "Error constructing EC i2c message %d\n", result);
+		goto exit;
+	}
 
-	result = cros_ec_cmd_xfer(bus->ec, &msg);
-	if (result < 0)
-		return result;
+	msg->version = 0;
+	msg->command = EC_CMD_I2C_PASSTHRU;
+	msg->outsize = request_len;
+	msg->insize = response_len;
 
-	result = ec_i2c_parse_response(msg.indata, i2c_msgs, &num);
-	if (result < 0)
-		return result;
+	result = cros_ec_cmd_xfer(bus->ec, msg);
+	if (result < 0) {
+		dev_err(dev, "Error transferring EC i2c message %d\n", result);
+		goto exit;
+	}
+
+	result = ec_i2c_parse_response(msg->data, i2c_msgs, &num);
+	if (result < 0) {
+		dev_err(dev, "Error parsing EC i2c message %d\n", result);
+		goto exit;
+	}
 
 	/* Indicate success by saying how many messages were sent */
-	return num;
+	result = num;
+exit:
+	kfree(msg);
+	return result;
 }
 
 static u32 ec_i2c_functionality(struct i2c_adapter *adap)
diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c
index 8fe78d08e01c..7c6966434ee7 100644
--- a/drivers/i2c/busses/i2c-hix5hd2.c
+++ b/drivers/i2c/busses/i2c-hix5hd2.c
@@ -554,4 +554,4 @@ module_platform_driver(hix5hd2_i2c_driver);
 MODULE_DESCRIPTION("Hix5hd2 I2C Bus driver");
 MODULE_AUTHOR("Wei Yan <sledge.yanwei@huawei.com>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:i2c-hix5hd2");
+MODULE_ALIAS("platform:hix5hd2-i2c");
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 67cbec6796a0..630bce68bf38 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -245,7 +245,7 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev,
 	     PIIX4_dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS &&
 	     PIIX4_dev->revision >= 0x41) ||
 	    (PIIX4_dev->vendor == PCI_VENDOR_ID_AMD &&
-	     PIIX4_dev->device == 0x790b &&
+	     PIIX4_dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS &&
 	     PIIX4_dev->revision >= 0x49))
 		smb_en = 0x00;
 	else
@@ -545,7 +545,7 @@ static const struct pci_device_id piix4_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x790b) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
 		     PCI_DEVICE_ID_SERVERWORKS_OSB4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 958c8db4ec30..297e9c9ac943 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1143,6 +1143,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	i2c->quirks = s3c24xx_get_device_quirks(pdev);
+	i2c->sysreg = ERR_PTR(-ENOENT);
 	if (pdata)
 		memcpy(i2c->pdata, pdata, sizeof(*pdata));
 	else
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 987c124432c5..fc2ee8213fb6 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -107,7 +107,7 @@ static int acpi_i2c_add_resource(struct acpi_resource *ares, void *data)
 			if (sb->access_mode == ACPI_I2C_10BIT_MODE)
 				info->flags |= I2C_CLIENT_TEN;
 		}
-	} else if (info->irq < 0) {
+	} else if (!info->irq) {
 		struct resource r;
 
 		if (acpi_dev_resource_interrupt(ares, 0, &r))
@@ -134,7 +134,6 @@ static acpi_status acpi_i2c_add_device(acpi_handle handle, u32 level,
 
 	memset(&info, 0, sizeof(info));
 	info.fwnode = acpi_fwnode_handle(adev);
-	info.irq = -1;
 
 	INIT_LIST_HEAD(&resource_list);
 	ret = acpi_dev_get_resources(adev, &resource_list,
@@ -632,8 +631,13 @@ static int i2c_device_probe(struct device *dev)
 	if (!client)
 		return 0;
 
-	if (!client->irq && dev->of_node) {
-		int irq = of_irq_get(dev->of_node, 0);
+	if (!client->irq) {
+		int irq = -ENOENT;
+
+		if (dev->of_node)
+			irq = of_irq_get(dev->of_node, 0);
+		else if (ACPI_COMPANION(dev))
+			irq = acpi_dev_gpio_irq_get(ACPI_COMPANION(dev), 0);
 
 		if (irq == -EPROBE_DEFER)
 			return irq;
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index a04c49f2a011..39ea67f9b066 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -643,15 +643,6 @@ config BLK_DEV_TC86C001
 	help
 	This driver adds support for Toshiba TC86C001 GOKU-S chip.
 
-config BLK_DEV_CELLEB
-	tristate "Toshiba's Cell Reference Set IDE support"
-	depends on PPC_CELLEB
-	select BLK_DEV_IDEDMA_PCI
-	help
-	  This driver provides support for the on-board IDE controller on
-	  Toshiba Cell Reference Board.
-	  If unsure, say Y.
-
 endif
 
 # TODO: BLK_DEV_IDEDMA_PCI -> BLK_DEV_IDEDMA_SFF
diff --git a/drivers/ide/Makefile b/drivers/ide/Makefile
index a04ee82f1c8f..2a8c417d4081 100644
--- a/drivers/ide/Makefile
+++ b/drivers/ide/Makefile
@@ -38,7 +38,6 @@ obj-$(CONFIG_BLK_DEV_AEC62XX)		+= aec62xx.o
 obj-$(CONFIG_BLK_DEV_ALI15X3)		+= alim15x3.o
 obj-$(CONFIG_BLK_DEV_AMD74XX)		+= amd74xx.o
 obj-$(CONFIG_BLK_DEV_ATIIXP)		+= atiixp.o
-obj-$(CONFIG_BLK_DEV_CELLEB)		+= scc_pata.o
 obj-$(CONFIG_BLK_DEV_CMD64X)		+= cmd64x.o
 obj-$(CONFIG_BLK_DEV_CS5520)		+= cs5520.o
 obj-$(CONFIG_BLK_DEV_CS5530)		+= cs5530.o
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index fac3d9da2e07..1362ad80a76c 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -93,7 +93,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	int error;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = (char *)pc;
 
 	if (buf && bufflen) {
@@ -191,7 +191,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 
 	BUG_ON(sense_len > sizeof(*sense));
 
-	if (rq->cmd_type == REQ_TYPE_SENSE || drive->sense_rq_armed)
+	if (rq->cmd_type == REQ_TYPE_ATA_SENSE || drive->sense_rq_armed)
 		return;
 
 	memset(sense, 0, sizeof(*sense));
@@ -210,7 +210,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	sense_rq->rq_disk = rq->rq_disk;
 	sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
 	sense_rq->cmd[4] = cmd_len;
-	sense_rq->cmd_type = REQ_TYPE_SENSE;
+	sense_rq->cmd_type = REQ_TYPE_ATA_SENSE;
 	sense_rq->cmd_flags |= REQ_PREEMPT;
 
 	if (drive->media == ide_tape)
@@ -310,7 +310,7 @@ int ide_cd_get_xferlen(struct request *rq)
 	switch (rq->cmd_type) {
 	case REQ_TYPE_FS:
 		return 32768;
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_ATA_SENSE:
 	case REQ_TYPE_BLOCK_PC:
 	case REQ_TYPE_ATA_PC:
 		return blk_rq_bytes(rq);
@@ -477,7 +477,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		if (uptodate == 0)
 			drive->failed_pc = NULL;
 
-		if (rq->cmd_type == REQ_TYPE_SPECIAL) {
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
 			rq->errors = 0;
 			error = 0;
 		} else {
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 0b510bafd90e..64a6b827b3dd 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -210,7 +210,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For REQ_TYPE_SENSE, "rq->special" points to the original
+	 * For REQ_TYPE_ATA_SENSE, "rq->special" points to the original
 	 * failed request.  Also, the sense data should be read
 	 * directly from rq which might be different from the original
 	 * sense buffer if it got copied during mapping.
@@ -285,7 +285,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 				  "stat 0x%x",
 				  rq->cmd[0], rq->cmd_type, err, stat);
 
-	if (rq->cmd_type == REQ_TYPE_SENSE) {
+	if (rq->cmd_type == REQ_TYPE_ATA_SENSE) {
 		/*
 		 * We got an error trying to get sense info from the drive
 		 * (probably while trying to recover from a former error).
@@ -526,7 +526,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
 	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
-	int sense = (rq->cmd_type == REQ_TYPE_SENSE);
+	int sense = (rq->cmd_type == REQ_TYPE_ATA_SENSE);
 	unsigned int timeout;
 	u16 len;
 	u8 ireason, stat;
@@ -791,7 +791,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 		if (cdrom_start_rw(drive, rq) == ide_stopped)
 			goto out_end;
 		break;
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_ATA_SENSE:
 	case REQ_TYPE_BLOCK_PC:
 	case REQ_TYPE_ATA_PC:
 		if (!rq->timeout)
@@ -799,7 +799,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 		cdrom_do_block_pc(drive, rq);
 		break;
-	case REQ_TYPE_SPECIAL:
+	case REQ_TYPE_DRV_PRIV:
 		/* right now this can only be a reset... */
 		uptodate = 1;
 		goto out_end;
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 02caa7dd51c8..066e39036518 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -304,7 +304,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	int ret;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_flags = REQ_QUIET;
 	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
 	blk_put_request(rq);
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 9e98122f646e..b05a74d78ef5 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -166,7 +166,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 		return setting->set(drive, arg);
 
 	rq = blk_get_request(q, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 5;
 	rq->cmd[0] = REQ_DEVSET_EXEC;
 	*(int *)&rq->cmd[1] = arg;
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index 32970664c275..d6da011299f5 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -129,7 +129,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 
 			if (cmd)
 				ide_complete_cmd(drive, cmd, stat, err);
-		} else if (blk_pm_request(rq)) {
+		} else if (ata_pm_request(rq)) {
 			rq->errors = 1;
 			ide_complete_pm_rq(drive, rq);
 			return ide_stopped;
@@ -147,7 +147,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 {
 	struct request *rq = drive->hwif->rq;
 
-	if (rq && rq->cmd_type == REQ_TYPE_SPECIAL &&
+	if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV &&
 	    rq->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && rq->errors == 0)
 			rq->errors = -EIO;
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 8c6363cdd208..2fb5350c5410 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -97,7 +97,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 			       "Aborting request!\n");
 	}
 
-	if (rq->cmd_type == REQ_TYPE_SPECIAL)
+	if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
 		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
@@ -246,7 +246,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		} else
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
-		if (rq->cmd_type == REQ_TYPE_SPECIAL) {
+		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
 			rq->errors = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
@@ -265,8 +265,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		pc = &floppy->queued_pc;
 		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
 		break;
-	case REQ_TYPE_SPECIAL:
-	case REQ_TYPE_SENSE:
+	case REQ_TYPE_DRV_PRIV:
+	case REQ_TYPE_ATA_SENSE:
 		pc = (struct ide_atapi_pc *)rq->special;
 		break;
 	case REQ_TYPE_BLOCK_PC:
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 177db6d5b2f5..669ea1e45795 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq);
 
 void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 drv_req = (rq->cmd_type == REQ_TYPE_SPECIAL) && rq->rq_disk;
+	u8 drv_req = (rq->cmd_type == REQ_TYPE_DRV_PRIV) && rq->rq_disk;
 	u8 media = drive->media;
 
 	drive->failed_pc = NULL;
@@ -320,7 +320,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		goto kill_rq;
 	}
 
-	if (blk_pm_request(rq))
+	if (ata_pm_request(rq))
 		ide_check_pm_state(drive, rq);
 
 	drive->hwif->tp_ops->dev_select(drive);
@@ -342,8 +342,8 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 
 		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
 			return execute_drive_cmd(drive, rq);
-		else if (blk_pm_request(rq)) {
-			struct request_pm_state *pm = rq->special;
+		else if (ata_pm_request(rq)) {
+			struct ide_pm_state *pm = rq->special;
 #ifdef DEBUG_PM
 			printk("%s: start_power_step(step: %d)\n",
 				drive->name, pm->pm_step);
@@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 			    pm->pm_step == IDE_PM_COMPLETED)
 				ide_complete_pm_rq(drive, rq);
 			return startstop;
-		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_SPECIAL)
+		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_DRV_PRIV)
 			/*
 			 * TODO: Once all ULDs have been modified to
 			 * check for specific op codes rather than
@@ -538,7 +538,7 @@ repeat:
 		 * state machine.
 		 */
 		if ((drive->dev_flags & IDE_DFLAG_BLOCKED) &&
-		    blk_pm_request(rq) == 0 &&
+		    ata_pm_request(rq) == 0 &&
 		    (rq->cmd_flags & REQ_PREEMPT) == 0) {
 			/* there should be no pending command at this point */
 			ide_unlock_port(hwif);
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 6233fa2cb8a9..aa2e9b77b20d 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -222,7 +222,7 @@ static int generic_drive_reset(ide_drive_t *drive)
 	int ret = 0;
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 1;
 	rq->cmd[0] = REQ_DRIVE_RESET;
 	if (blk_execute_rq(drive->queue, NULL, rq, 1))
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index ca958604cda2..c80868520488 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -34,7 +34,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	rq = blk_get_request(q, READ, __GFP_WAIT);
 	rq->cmd[0] = REQ_PARK_HEADS;
 	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = &timeout;
 	rc = blk_execute_rq(q, NULL, rq, 1);
 	blk_put_request(rq);
@@ -51,7 +51,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 
 	rq->cmd[0] = REQ_UNPARK_HEADS;
 	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
 
 out:
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index 8d1e32d7cd97..081e43458d50 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -8,7 +8,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	ide_drive_t *pair = ide_get_pair_dev(drive);
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
-	struct request_pm_state rqpm;
+	struct ide_pm_state rqpm;
 	int ret;
 
 	if (ide_port_acpi(hwif)) {
@@ -19,7 +19,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_PM_SUSPEND;
+	rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
@@ -38,13 +38,43 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	return ret;
 }
 
+static void ide_end_sync_rq(struct request *rq, int error)
+{
+	complete(rq->end_io_data);
+}
+
+static int ide_pm_execute_rq(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	DECLARE_COMPLETION_ONSTACK(wait);
+
+	rq->end_io_data = &wait;
+	rq->end_io = ide_end_sync_rq;
+
+	spin_lock_irq(q->queue_lock);
+	if (unlikely(blk_queue_dying(q))) {
+		rq->cmd_flags |= REQ_QUIET;
+		rq->errors = -ENXIO;
+		__blk_end_request_all(rq, rq->errors);
+		spin_unlock_irq(q->queue_lock);
+		return -ENXIO;
+	}
+	__elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
+	__blk_run_queue_uncond(q);
+	spin_unlock_irq(q->queue_lock);
+
+	wait_for_completion_io(&wait);
+
+	return rq->errors ? -EIO : 0;
+}
+
 int generic_ide_resume(struct device *dev)
 {
 	ide_drive_t *drive = to_ide_device(dev);
 	ide_drive_t *pair = ide_get_pair_dev(drive);
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq;
-	struct request_pm_state rqpm;
+	struct ide_pm_state rqpm;
 	int err;
 
 	if (ide_port_acpi(hwif)) {
@@ -59,13 +89,13 @@ int generic_ide_resume(struct device *dev)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_PM_RESUME;
+	rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
 	rq->cmd_flags |= REQ_PREEMPT;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
 	rqpm.pm_state = PM_EVENT_ON;
 
-	err = blk_execute_rq(drive->queue, NULL, rq, 1);
+	err = ide_pm_execute_rq(rq);
 	blk_put_request(rq);
 
 	if (err == 0 && dev->driver) {
@@ -80,7 +110,7 @@ int generic_ide_resume(struct device *dev)
 
 void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 
 #ifdef DEBUG_PM
 	printk(KERN_INFO "%s: complete_power_step(step: %d)\n",
@@ -110,7 +140,7 @@ void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 
 ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 	struct ide_cmd cmd = { };
 
 	switch (pm->pm_step) {
@@ -182,7 +212,7 @@ out_do_tf:
 void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 	unsigned long flags;
 
 	ide_complete_power_step(drive, rq);
@@ -191,10 +221,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 #ifdef DEBUG_PM
 	printk("%s: completing PM request, %s\n", drive->name,
-	       (rq->cmd_type == REQ_TYPE_PM_SUSPEND) ? "suspend" : "resume");
+	       (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND) ? "suspend" : "resume");
 #endif
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (rq->cmd_type == REQ_TYPE_PM_SUSPEND)
+	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND)
 		blk_stop_queue(q);
 	else
 		drive->dev_flags &= ~IDE_DFLAG_BLOCKED;
@@ -208,13 +238,13 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
-	struct request_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = rq->special;
 
-	if (rq->cmd_type == REQ_TYPE_PM_SUSPEND &&
+	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND &&
 	    pm->pm_step == IDE_PM_START_SUSPEND)
 		/* Mark drive blocked when starting the suspend sequence. */
 		drive->dev_flags |= IDE_DFLAG_BLOCKED;
-	else if (rq->cmd_type == REQ_TYPE_PM_RESUME &&
+	else if (rq->cmd_type == REQ_TYPE_ATA_PM_RESUME &&
 		 pm->pm_step == IDE_PM_START_RESUME) {
 		/*
 		 * The first thing we do on wakeup is to wait for BSY bit to
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 6eb738ca6d2f..f5d51d1d09ee 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -576,8 +576,8 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		      rq->cmd[0], (unsigned long long)blk_rq_pos(rq),
 		      blk_rq_sectors(rq));
 
-	BUG_ON(!(rq->cmd_type == REQ_TYPE_SPECIAL ||
-		 rq->cmd_type == REQ_TYPE_SENSE));
+	BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV ||
+		 rq->cmd_type == REQ_TYPE_ATA_SENSE));
 
 	/* Retry a failed packet command */
 	if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) {
@@ -853,7 +853,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(size < 0 || size % tape->blk_size);
 
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_SPECIAL;
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
 	rq->__sector = tape->first_frame;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index dabb88b1cbec..0979e126fff1 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -186,7 +186,7 @@ static ide_startstop_t task_no_data_intr(ide_drive_t *drive)
 	    tf->command == ATA_CMD_CHK_POWER) {
 		struct request *rq = hwif->rq;
 
-		if (blk_pm_request(rq))
+		if (ata_pm_request(rq))
 			ide_complete_pm_rq(drive, rq);
 		else
 			ide_finish_cmd(drive, cmd, stat);
diff --git a/drivers/ide/scc_pata.c b/drivers/ide/scc_pata.c
deleted file mode 100644
index 2a2d188b5d5b..000000000000
--- a/drivers/ide/scc_pata.c
+++ /dev/null
@@ -1,887 +0,0 @@
-/*
- * Support for IDE interfaces on Celleb platform
- *
- * (C) Copyright 2006 TOSHIBA CORPORATION
- *
- * This code is based on drivers/ide/pci/siimage.c:
- * Copyright (C) 2001-2002	Andre Hedrick <andre@linux-ide.org>
- * Copyright (C) 2003		Red Hat
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/ide.h>
-#include <linux/init.h>
-
-#define PCI_DEVICE_ID_TOSHIBA_SCC_ATA            0x01b4
-
-#define SCC_PATA_NAME           "scc IDE"
-
-#define TDVHSEL_MASTER          0x00000001
-#define TDVHSEL_SLAVE           0x00000004
-
-#define MODE_JCUSFEN            0x00000080
-
-#define CCKCTRL_ATARESET        0x00040000
-#define CCKCTRL_BUFCNT          0x00020000
-#define CCKCTRL_CRST            0x00010000
-#define CCKCTRL_OCLKEN          0x00000100
-#define CCKCTRL_ATACLKOEN       0x00000002
-#define CCKCTRL_LCLKEN          0x00000001
-
-#define QCHCD_IOS_SS		0x00000001
-
-#define QCHSD_STPDIAG		0x00020000
-
-#define INTMASK_MSK             0xD1000012
-#define INTSTS_SERROR		0x80000000
-#define INTSTS_PRERR		0x40000000
-#define INTSTS_RERR		0x10000000
-#define INTSTS_ICERR		0x01000000
-#define INTSTS_BMSINT		0x00000010
-#define INTSTS_BMHE		0x00000008
-#define INTSTS_IOIRQS           0x00000004
-#define INTSTS_INTRQ            0x00000002
-#define INTSTS_ACTEINT          0x00000001
-
-#define ECMODE_VALUE 0x01
-
-static struct scc_ports {
-	unsigned long ctl, dma;
-	struct ide_host *host;	/* for removing port from system */
-} scc_ports[MAX_HWIFS];
-
-/* PIO transfer mode  table */
-/* JCHST */
-static unsigned long JCHSTtbl[2][7] = {
-	{0x0E, 0x05, 0x02, 0x03, 0x02, 0x00, 0x00},   /* 100MHz */
-	{0x13, 0x07, 0x04, 0x04, 0x03, 0x00, 0x00}    /* 133MHz */
-};
-
-/* JCHHT */
-static unsigned long JCHHTtbl[2][7] = {
-	{0x0E, 0x02, 0x02, 0x02, 0x02, 0x00, 0x00},   /* 100MHz */
-	{0x13, 0x03, 0x03, 0x03, 0x03, 0x00, 0x00}    /* 133MHz */
-};
-
-/* JCHCT */
-static unsigned long JCHCTtbl[2][7] = {
-	{0x1D, 0x1D, 0x1C, 0x0B, 0x06, 0x00, 0x00},   /* 100MHz */
-	{0x27, 0x26, 0x26, 0x0E, 0x09, 0x00, 0x00}    /* 133MHz */
-};
-
-
-/* DMA transfer mode  table */
-/* JCHDCTM/JCHDCTS */
-static unsigned long JCHDCTxtbl[2][7] = {
-	{0x0A, 0x06, 0x04, 0x03, 0x01, 0x00, 0x00},   /* 100MHz */
-	{0x0E, 0x09, 0x06, 0x04, 0x02, 0x01, 0x00}    /* 133MHz */
-};
-
-/* JCSTWTM/JCSTWTS  */
-static unsigned long JCSTWTxtbl[2][7] = {
-	{0x06, 0x04, 0x03, 0x02, 0x02, 0x02, 0x00},   /* 100MHz */
-	{0x09, 0x06, 0x04, 0x02, 0x02, 0x02, 0x02}    /* 133MHz */
-};
-
-/* JCTSS */
-static unsigned long JCTSStbl[2][7] = {
-	{0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x00},   /* 100MHz */
-	{0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05}    /* 133MHz */
-};
-
-/* JCENVT */
-static unsigned long JCENVTtbl[2][7] = {
-	{0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00},   /* 100MHz */
-	{0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02}    /* 133MHz */
-};
-
-/* JCACTSELS/JCACTSELM */
-static unsigned long JCACTSELtbl[2][7] = {
-	{0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x00},   /* 100MHz */
-	{0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}    /* 133MHz */
-};
-
-
-static u8 scc_ide_inb(unsigned long port)
-{
-	u32 data = in_be32((void*)port);
-	return (u8)data;
-}
-
-static void scc_exec_command(ide_hwif_t *hwif, u8 cmd)
-{
-	out_be32((void *)hwif->io_ports.command_addr, cmd);
-	eieio();
-	in_be32((void *)(hwif->dma_base + 0x01c));
-	eieio();
-}
-
-static u8 scc_read_status(ide_hwif_t *hwif)
-{
-	return (u8)in_be32((void *)hwif->io_ports.status_addr);
-}
-
-static u8 scc_read_altstatus(ide_hwif_t *hwif)
-{
-	return (u8)in_be32((void *)hwif->io_ports.ctl_addr);
-}
-
-static u8 scc_dma_sff_read_status(ide_hwif_t *hwif)
-{
-	return (u8)in_be32((void *)(hwif->dma_base + 4));
-}
-
-static void scc_write_devctl(ide_hwif_t *hwif, u8 ctl)
-{
-	out_be32((void *)hwif->io_ports.ctl_addr, ctl);
-	eieio();
-	in_be32((void *)(hwif->dma_base + 0x01c));
-	eieio();
-}
-
-static void scc_ide_insw(unsigned long port, void *addr, u32 count)
-{
-	u16 *ptr = (u16 *)addr;
-	while (count--) {
-		*ptr++ = le16_to_cpu(in_be32((void*)port));
-	}
-}
-
-static void scc_ide_insl(unsigned long port, void *addr, u32 count)
-{
-	u16 *ptr = (u16 *)addr;
-	while (count--) {
-		*ptr++ = le16_to_cpu(in_be32((void*)port));
-		*ptr++ = le16_to_cpu(in_be32((void*)port));
-	}
-}
-
-static void scc_ide_outb(u8 addr, unsigned long port)
-{
-	out_be32((void*)port, addr);
-}
-
-static void
-scc_ide_outsw(unsigned long port, void *addr, u32 count)
-{
-	u16 *ptr = (u16 *)addr;
-	while (count--) {
-		out_be32((void*)port, cpu_to_le16(*ptr++));
-	}
-}
-
-static void
-scc_ide_outsl(unsigned long port, void *addr, u32 count)
-{
-	u16 *ptr = (u16 *)addr;
-	while (count--) {
-		out_be32((void*)port, cpu_to_le16(*ptr++));
-		out_be32((void*)port, cpu_to_le16(*ptr++));
-	}
-}
-
-/**
- *	scc_set_pio_mode	-	set host controller for PIO mode
- *	@hwif: port
- *	@drive: drive
- *
- *	Load the timing settings for this device mode into the
- *	controller.
- */
-
-static void scc_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
-{
-	struct scc_ports *ports = ide_get_hwifdata(hwif);
-	unsigned long ctl_base = ports->ctl;
-	unsigned long cckctrl_port = ctl_base + 0xff0;
-	unsigned long piosht_port = ctl_base + 0x000;
-	unsigned long pioct_port = ctl_base + 0x004;
-	unsigned long reg;
-	int offset;
-	const u8 pio = drive->pio_mode - XFER_PIO_0;
-
-	reg = in_be32((void __iomem *)cckctrl_port);
-	if (reg & CCKCTRL_ATACLKOEN) {
-		offset = 1; /* 133MHz */
-	} else {
-		offset = 0; /* 100MHz */
-	}
-	reg = JCHSTtbl[offset][pio] << 16 | JCHHTtbl[offset][pio];
-	out_be32((void __iomem *)piosht_port, reg);
-	reg = JCHCTtbl[offset][pio];
-	out_be32((void __iomem *)pioct_port, reg);
-}
-
-/**
- *	scc_set_dma_mode	-	set host controller for DMA mode
- *	@hwif: port
- *	@drive: drive
- *
- *	Load the timing settings for this device mode into the
- *	controller.
- */
-
-static void scc_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive)
-{
-	struct scc_ports *ports = ide_get_hwifdata(hwif);
-	unsigned long ctl_base = ports->ctl;
-	unsigned long cckctrl_port = ctl_base + 0xff0;
-	unsigned long mdmact_port = ctl_base + 0x008;
-	unsigned long mcrcst_port = ctl_base + 0x00c;
-	unsigned long sdmact_port = ctl_base + 0x010;
-	unsigned long scrcst_port = ctl_base + 0x014;
-	unsigned long udenvt_port = ctl_base + 0x018;
-	unsigned long tdvhsel_port   = ctl_base + 0x020;
-	int is_slave = drive->dn & 1;
-	int offset, idx;
-	unsigned long reg;
-	unsigned long jcactsel;
-	const u8 speed = drive->dma_mode;
-
-	reg = in_be32((void __iomem *)cckctrl_port);
-	if (reg & CCKCTRL_ATACLKOEN) {
-		offset = 1; /* 133MHz */
-	} else {
-		offset = 0; /* 100MHz */
-	}
-
-	idx = speed - XFER_UDMA_0;
-
-	jcactsel = JCACTSELtbl[offset][idx];
-	if (is_slave) {
-		out_be32((void __iomem *)sdmact_port, JCHDCTxtbl[offset][idx]);
-		out_be32((void __iomem *)scrcst_port, JCSTWTxtbl[offset][idx]);
-		jcactsel = jcactsel << 2;
-		out_be32((void __iomem *)tdvhsel_port, (in_be32((void __iomem *)tdvhsel_port) & ~TDVHSEL_SLAVE) | jcactsel);
-	} else {
-		out_be32((void __iomem *)mdmact_port, JCHDCTxtbl[offset][idx]);
-		out_be32((void __iomem *)mcrcst_port, JCSTWTxtbl[offset][idx]);
-		out_be32((void __iomem *)tdvhsel_port, (in_be32((void __iomem *)tdvhsel_port) & ~TDVHSEL_MASTER) | jcactsel);
-	}
-	reg = JCTSStbl[offset][idx] << 16 | JCENVTtbl[offset][idx];
-	out_be32((void __iomem *)udenvt_port, reg);
-}
-
-static void scc_dma_host_set(ide_drive_t *drive, int on)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u8 unit = drive->dn & 1;
-	u8 dma_stat = scc_dma_sff_read_status(hwif);
-
-	if (on)
-		dma_stat |= (1 << (5 + unit));
-	else
-		dma_stat &= ~(1 << (5 + unit));
-
-	scc_ide_outb(dma_stat, hwif->dma_base + 4);
-}
-
-/**
- *	scc_dma_setup	-	begin a DMA phase
- *	@drive: target device
- *	@cmd: command
- *
- *	Build an IDE DMA PRD (IDE speak for scatter gather table)
- *	and then set up the DMA transfer registers.
- *
- *	Returns 0 on success. If a PIO fallback is required then 1
- *	is returned.
- */
-
-static int scc_dma_setup(ide_drive_t *drive, struct ide_cmd *cmd)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u32 rw = (cmd->tf_flags & IDE_TFLAG_WRITE) ? 0 : ATA_DMA_WR;
-	u8 dma_stat;
-
-	/* fall back to pio! */
-	if (ide_build_dmatable(drive, cmd) == 0)
-		return 1;
-
-	/* PRD table */
-	out_be32((void __iomem *)(hwif->dma_base + 8), hwif->dmatable_dma);
-
-	/* specify r/w */
-	out_be32((void __iomem *)hwif->dma_base, rw);
-
-	/* read DMA status for INTR & ERROR flags */
-	dma_stat = scc_dma_sff_read_status(hwif);
-
-	/* clear INTR & ERROR flags */
-	out_be32((void __iomem *)(hwif->dma_base + 4), dma_stat | 6);
-
-	return 0;
-}
-
-static void scc_dma_start(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u8 dma_cmd = scc_ide_inb(hwif->dma_base);
-
-	/* start DMA */
-	scc_ide_outb(dma_cmd | 1, hwif->dma_base);
-}
-
-static int __scc_dma_end(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u8 dma_stat, dma_cmd;
-
-	/* get DMA command mode */
-	dma_cmd = scc_ide_inb(hwif->dma_base);
-	/* stop DMA */
-	scc_ide_outb(dma_cmd & ~1, hwif->dma_base);
-	/* get DMA status */
-	dma_stat = scc_dma_sff_read_status(hwif);
-	/* clear the INTR & ERROR bits */
-	scc_ide_outb(dma_stat | 6, hwif->dma_base + 4);
-	/* verify good DMA status */
-	return (dma_stat & 7) != 4 ? (0x10 | dma_stat) : 0;
-}
-
-/**
- *	scc_dma_end	-	Stop DMA
- *	@drive: IDE drive
- *
- *	Check and clear INT Status register.
- *	Then call __scc_dma_end().
- */
-
-static int scc_dma_end(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	void __iomem *dma_base = (void __iomem *)hwif->dma_base;
-	unsigned long intsts_port = hwif->dma_base + 0x014;
-	u32 reg;
-	int dma_stat, data_loss = 0;
-	static int retry = 0;
-
-	/* errata A308 workaround: Step5 (check data loss) */
-	/* We don't check non ide_disk because it is limited to UDMA4 */
-	if (!(in_be32((void __iomem *)hwif->io_ports.ctl_addr)
-	      & ATA_ERR) &&
-	    drive->media == ide_disk && drive->current_speed > XFER_UDMA_4) {
-		reg = in_be32((void __iomem *)intsts_port);
-		if (!(reg & INTSTS_ACTEINT)) {
-			printk(KERN_WARNING "%s: operation failed (transfer data loss)\n",
-			       drive->name);
-			data_loss = 1;
-			if (retry++) {
-				struct request *rq = hwif->rq;
-				ide_drive_t *drive;
-				int i;
-
-				/* ERROR_RESET and drive->crc_count are needed
-				 * to reduce DMA transfer mode in retry process.
-				 */
-				if (rq)
-					rq->errors |= ERROR_RESET;
-
-				ide_port_for_each_dev(i, drive, hwif)
-					drive->crc_count++;
-			}
-		}
-	}
-
-	while (1) {
-		reg = in_be32((void __iomem *)intsts_port);
-
-		if (reg & INTSTS_SERROR) {
-			printk(KERN_WARNING "%s: SERROR\n", SCC_PATA_NAME);
-			out_be32((void __iomem *)intsts_port, INTSTS_SERROR|INTSTS_BMSINT);
-
-			out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
-			continue;
-		}
-
-		if (reg & INTSTS_PRERR) {
-			u32 maea0, maec0;
-			unsigned long ctl_base = hwif->config_data;
-
-			maea0 = in_be32((void __iomem *)(ctl_base + 0xF50));
-			maec0 = in_be32((void __iomem *)(ctl_base + 0xF54));
-
-			printk(KERN_WARNING "%s: PRERR [addr:%x cmd:%x]\n", SCC_PATA_NAME, maea0, maec0);
-
-			out_be32((void __iomem *)intsts_port, INTSTS_PRERR|INTSTS_BMSINT);
-
-			out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
-			continue;
-		}
-
-		if (reg & INTSTS_RERR) {
-			printk(KERN_WARNING "%s: Response Error\n", SCC_PATA_NAME);
-			out_be32((void __iomem *)intsts_port, INTSTS_RERR|INTSTS_BMSINT);
-
-			out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
-			continue;
-		}
-
-		if (reg & INTSTS_ICERR) {
-			out_be32(dma_base, in_be32(dma_base) & ~QCHCD_IOS_SS);
-
-			printk(KERN_WARNING "%s: Illegal Configuration\n", SCC_PATA_NAME);
-			out_be32((void __iomem *)intsts_port, INTSTS_ICERR|INTSTS_BMSINT);
-			continue;
-		}
-
-		if (reg & INTSTS_BMSINT) {
-			printk(KERN_WARNING "%s: Internal Bus Error\n", SCC_PATA_NAME);
-			out_be32((void __iomem *)intsts_port, INTSTS_BMSINT);
-
-			ide_do_reset(drive);
-			continue;
-		}
-
-		if (reg & INTSTS_BMHE) {
-			out_be32((void __iomem *)intsts_port, INTSTS_BMHE);
-			continue;
-		}
-
-		if (reg & INTSTS_ACTEINT) {
-			out_be32((void __iomem *)intsts_port, INTSTS_ACTEINT);
-			continue;
-		}
-
-		if (reg & INTSTS_IOIRQS) {
-			out_be32((void __iomem *)intsts_port, INTSTS_IOIRQS);
-			continue;
-		}
-		break;
-	}
-
-	dma_stat = __scc_dma_end(drive);
-	if (data_loss)
-		dma_stat |= 2; /* emulate DMA error (to retry command) */
-	return dma_stat;
-}
-
-/* returns 1 if dma irq issued, 0 otherwise */
-static int scc_dma_test_irq(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u32 int_stat = in_be32((void __iomem *)hwif->dma_base + 0x014);
-
-	/* SCC errata A252,A308 workaround: Step4 */
-	if ((in_be32((void __iomem *)hwif->io_ports.ctl_addr)
-	     & ATA_ERR) &&
-	    (int_stat & INTSTS_INTRQ))
-		return 1;
-
-	/* SCC errata A308 workaround: Step5 (polling IOIRQS) */
-	if (int_stat & INTSTS_IOIRQS)
-		return 1;
-
-	return 0;
-}
-
-static u8 scc_udma_filter(ide_drive_t *drive)
-{
-	ide_hwif_t *hwif = drive->hwif;
-	u8 mask = hwif->ultra_mask;
-
-	/* errata A308 workaround: limit non ide_disk drive to UDMA4 */
-	if ((drive->media != ide_disk) && (mask & 0xE0)) {
-		printk(KERN_INFO "%s: limit %s to UDMA4\n",
-		       SCC_PATA_NAME, drive->name);
-		mask = ATA_UDMA4;
-	}
-
-	return mask;
-}
-
-/**
- *	setup_mmio_scc	-	map CTRL/BMID region
- *	@dev: PCI device we are configuring
- *	@name: device name
- *
- */
-
-static int setup_mmio_scc (struct pci_dev *dev, const char *name)
-{
-	void __iomem *ctl_addr;
-	void __iomem *dma_addr;
-	int i, ret;
-
-	for (i = 0; i < MAX_HWIFS; i++) {
-		if (scc_ports[i].ctl == 0)
-			break;
-	}
-	if (i >= MAX_HWIFS)
-		return -ENOMEM;
-
-	ret = pci_request_selected_regions(dev, (1 << 2) - 1, name);
-	if (ret < 0) {
-		printk(KERN_ERR "%s: can't reserve resources\n", name);
-		return ret;
-	}
-
-	ctl_addr = pci_ioremap_bar(dev, 0);
-	if (!ctl_addr)
-		goto fail_0;
-
-	dma_addr = pci_ioremap_bar(dev, 1);
-	if (!dma_addr)
-		goto fail_1;
-
-	pci_set_master(dev);
-	scc_ports[i].ctl = (unsigned long)ctl_addr;
-	scc_ports[i].dma = (unsigned long)dma_addr;
-	pci_set_drvdata(dev, (void *) &scc_ports[i]);
-
-	return 1;
-
- fail_1:
-	iounmap(ctl_addr);
- fail_0:
-	return -ENOMEM;
-}
-
-static int scc_ide_setup_pci_device(struct pci_dev *dev,
-				    const struct ide_port_info *d)
-{
-	struct scc_ports *ports = pci_get_drvdata(dev);
-	struct ide_host *host;
-	struct ide_hw hw, *hws[] = { &hw };
-	int i, rc;
-
-	memset(&hw, 0, sizeof(hw));
-	for (i = 0; i <= 8; i++)
-		hw.io_ports_array[i] = ports->dma + 0x20 + i * 4;
-	hw.irq = dev->irq;
-	hw.dev = &dev->dev;
-
-	rc = ide_host_add(d, hws, 1, &host);
-	if (rc)
-		return rc;
-
-	ports->host = host;
-
-	return 0;
-}
-
-/**
- *	init_setup_scc	-	set up an SCC PATA Controller
- *	@dev: PCI device
- *	@d: IDE port info
- *
- *	Perform the initial set up for this device.
- */
-
-static int init_setup_scc(struct pci_dev *dev, const struct ide_port_info *d)
-{
-	unsigned long ctl_base;
-	unsigned long dma_base;
-	unsigned long cckctrl_port;
-	unsigned long intmask_port;
-	unsigned long mode_port;
-	unsigned long ecmode_port;
-	u32 reg = 0;
-	struct scc_ports *ports;
-	int rc;
-
-	rc = pci_enable_device(dev);
-	if (rc)
-		goto end;
-
-	rc = setup_mmio_scc(dev, d->name);
-	if (rc < 0)
-		goto end;
-
-	ports = pci_get_drvdata(dev);
-	ctl_base = ports->ctl;
-	dma_base = ports->dma;
-	cckctrl_port = ctl_base + 0xff0;
-	intmask_port = dma_base + 0x010;
-	mode_port = ctl_base + 0x024;
-	ecmode_port = ctl_base + 0xf00;
-
-	/* controller initialization */
-	reg = 0;
-	out_be32((void*)cckctrl_port, reg);
-	reg |= CCKCTRL_ATACLKOEN;
-	out_be32((void*)cckctrl_port, reg);
-	reg |= CCKCTRL_LCLKEN | CCKCTRL_OCLKEN;
-	out_be32((void*)cckctrl_port, reg);
-	reg |= CCKCTRL_CRST;
-	out_be32((void*)cckctrl_port, reg);
-
-	for (;;) {
-		reg = in_be32((void*)cckctrl_port);
-		if (reg & CCKCTRL_CRST)
-			break;
-		udelay(5000);
-	}
-
-	reg |= CCKCTRL_ATARESET;
-	out_be32((void*)cckctrl_port, reg);
-
-	out_be32((void*)ecmode_port, ECMODE_VALUE);
-	out_be32((void*)mode_port, MODE_JCUSFEN);
-	out_be32((void*)intmask_port, INTMASK_MSK);
-
-	rc = scc_ide_setup_pci_device(dev, d);
-
- end:
-	return rc;
-}
-
-static void scc_tf_load(ide_drive_t *drive, struct ide_taskfile *tf, u8 valid)
-{
-	struct ide_io_ports *io_ports = &drive->hwif->io_ports;
-
-	if (valid & IDE_VALID_FEATURE)
-		scc_ide_outb(tf->feature, io_ports->feature_addr);
-	if (valid & IDE_VALID_NSECT)
-		scc_ide_outb(tf->nsect, io_ports->nsect_addr);
-	if (valid & IDE_VALID_LBAL)
-		scc_ide_outb(tf->lbal, io_ports->lbal_addr);
-	if (valid & IDE_VALID_LBAM)
-		scc_ide_outb(tf->lbam, io_ports->lbam_addr);
-	if (valid & IDE_VALID_LBAH)
-		scc_ide_outb(tf->lbah, io_ports->lbah_addr);
-	if (valid & IDE_VALID_DEVICE)
-		scc_ide_outb(tf->device, io_ports->device_addr);
-}
-
-static void scc_tf_read(ide_drive_t *drive, struct ide_taskfile *tf, u8 valid)
-{
-	struct ide_io_ports *io_ports = &drive->hwif->io_ports;
-
-	if (valid & IDE_VALID_ERROR)
-		tf->error  = scc_ide_inb(io_ports->feature_addr);
-	if (valid & IDE_VALID_NSECT)
-		tf->nsect  = scc_ide_inb(io_ports->nsect_addr);
-	if (valid & IDE_VALID_LBAL)
-		tf->lbal   = scc_ide_inb(io_ports->lbal_addr);
-	if (valid & IDE_VALID_LBAM)
-		tf->lbam   = scc_ide_inb(io_ports->lbam_addr);
-	if (valid & IDE_VALID_LBAH)
-		tf->lbah   = scc_ide_inb(io_ports->lbah_addr);
-	if (valid & IDE_VALID_DEVICE)
-		tf->device = scc_ide_inb(io_ports->device_addr);
-}
-
-static void scc_input_data(ide_drive_t *drive, struct ide_cmd *cmd,
-			   void *buf, unsigned int len)
-{
-	unsigned long data_addr = drive->hwif->io_ports.data_addr;
-
-	len++;
-
-	if (drive->io_32bit) {
-		scc_ide_insl(data_addr, buf, len / 4);
-
-		if ((len & 3) >= 2)
-			scc_ide_insw(data_addr, (u8 *)buf + (len & ~3), 1);
-	} else
-		scc_ide_insw(data_addr, buf, len / 2);
-}
-
-static void scc_output_data(ide_drive_t *drive,  struct ide_cmd *cmd,
-			    void *buf, unsigned int len)
-{
-	unsigned long data_addr = drive->hwif->io_ports.data_addr;
-
-	len++;
-
-	if (drive->io_32bit) {
-		scc_ide_outsl(data_addr, buf, len / 4);
-
-		if ((len & 3) >= 2)
-			scc_ide_outsw(data_addr, (u8 *)buf + (len & ~3), 1);
-	} else
-		scc_ide_outsw(data_addr, buf, len / 2);
-}
-
-/**
- *	init_mmio_iops_scc	-	set up the iops for MMIO
- *	@hwif: interface to set up
- *
- */
-
-static void init_mmio_iops_scc(ide_hwif_t *hwif)
-{
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-	struct scc_ports *ports = pci_get_drvdata(dev);
-	unsigned long dma_base = ports->dma;
-
-	ide_set_hwifdata(hwif, ports);
-
-	hwif->dma_base = dma_base;
-	hwif->config_data = ports->ctl;
-}
-
-/**
- *	init_iops_scc	-	set up iops
- *	@hwif: interface to set up
- *
- *	Do the basic setup for the SCC hardware interface
- *	and then do the MMIO setup.
- */
-
-static void init_iops_scc(ide_hwif_t *hwif)
-{
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-
-	hwif->hwif_data = NULL;
-	if (pci_get_drvdata(dev) == NULL)
-		return;
-	init_mmio_iops_scc(hwif);
-}
-
-static int scc_init_dma(ide_hwif_t *hwif, const struct ide_port_info *d)
-{
-	return ide_allocate_dma_engine(hwif);
-}
-
-static u8 scc_cable_detect(ide_hwif_t *hwif)
-{
-	return ATA_CBL_PATA80;
-}
-
-/**
- *	init_hwif_scc	-	set up hwif
- *	@hwif: interface to set up
- *
- *	We do the basic set up of the interface structure. The SCC
- *	requires several custom handlers so we override the default
- *	ide DMA handlers appropriately.
- */
-
-static void init_hwif_scc(ide_hwif_t *hwif)
-{
-	/* PTERADD */
-	out_be32((void __iomem *)(hwif->dma_base + 0x018), hwif->dmatable_dma);
-
-	if (in_be32((void __iomem *)(hwif->config_data + 0xff0)) & CCKCTRL_ATACLKOEN)
-		hwif->ultra_mask = ATA_UDMA6; /* 133MHz */
-	else
-		hwif->ultra_mask = ATA_UDMA5; /* 100MHz */
-}
-
-static const struct ide_tp_ops scc_tp_ops = {
-	.exec_command		= scc_exec_command,
-	.read_status		= scc_read_status,
-	.read_altstatus		= scc_read_altstatus,
-	.write_devctl		= scc_write_devctl,
-
-	.dev_select		= ide_dev_select,
-	.tf_load		= scc_tf_load,
-	.tf_read		= scc_tf_read,
-
-	.input_data		= scc_input_data,
-	.output_data		= scc_output_data,
-};
-
-static const struct ide_port_ops scc_port_ops = {
-	.set_pio_mode		= scc_set_pio_mode,
-	.set_dma_mode		= scc_set_dma_mode,
-	.udma_filter		= scc_udma_filter,
-	.cable_detect		= scc_cable_detect,
-};
-
-static const struct ide_dma_ops scc_dma_ops = {
-	.dma_host_set		= scc_dma_host_set,
-	.dma_setup		= scc_dma_setup,
-	.dma_start		= scc_dma_start,
-	.dma_end		= scc_dma_end,
-	.dma_test_irq		= scc_dma_test_irq,
-	.dma_lost_irq		= ide_dma_lost_irq,
-	.dma_timer_expiry	= ide_dma_sff_timer_expiry,
-	.dma_sff_read_status	= scc_dma_sff_read_status,
-};
-
-static const struct ide_port_info scc_chipset = {
-	.name		= "sccIDE",
-	.init_iops	= init_iops_scc,
-	.init_dma	= scc_init_dma,
-	.init_hwif	= init_hwif_scc,
-	.tp_ops		= &scc_tp_ops,
-	.port_ops	= &scc_port_ops,
-	.dma_ops	= &scc_dma_ops,
-	.host_flags	= IDE_HFLAG_SINGLE,
-	.irq_flags	= IRQF_SHARED,
-	.pio_mask	= ATA_PIO4,
-	.chipset	= ide_pci,
-};
-
-/**
- *	scc_init_one	-	pci layer discovery entry
- *	@dev: PCI device
- *	@id: ident table entry
- *
- *	Called by the PCI code when it finds an SCC PATA controller.
- *	We then use the IDE PCI generic helper to do most of the work.
- */
-
-static int scc_init_one(struct pci_dev *dev, const struct pci_device_id *id)
-{
-	return init_setup_scc(dev, &scc_chipset);
-}
-
-/**
- *	scc_remove	-	pci layer remove entry
- *	@dev: PCI device
- *
- *	Called by the PCI code when it removes an SCC PATA controller.
- */
-
-static void scc_remove(struct pci_dev *dev)
-{
-	struct scc_ports *ports = pci_get_drvdata(dev);
-	struct ide_host *host = ports->host;
-
-	ide_host_remove(host);
-
-	iounmap((void*)ports->dma);
-	iounmap((void*)ports->ctl);
-	pci_release_selected_regions(dev, (1 << 2) - 1);
-	memset(ports, 0, sizeof(*ports));
-}
-
-static const struct pci_device_id scc_pci_tbl[] = {
-	{ PCI_VDEVICE(TOSHIBA_2, PCI_DEVICE_ID_TOSHIBA_SCC_ATA), 0 },
-	{ 0, },
-};
-MODULE_DEVICE_TABLE(pci, scc_pci_tbl);
-
-static struct pci_driver scc_pci_driver = {
-	.name = "SCC IDE",
-	.id_table = scc_pci_tbl,
-	.probe = scc_init_one,
-	.remove = scc_remove,
-};
-
-static int __init scc_ide_init(void)
-{
-	return ide_pci_register_driver(&scc_pci_driver);
-}
-
-static void __exit scc_ide_exit(void)
-{
-	pci_unregister_driver(&scc_pci_driver);
-}
-
-module_init(scc_ide_init);
-module_exit(scc_ide_exit);
-
-MODULE_DESCRIPTION("PCI driver module for Toshiba SCC IDE");
-MODULE_LICENSE("GPL");
diff --git a/drivers/iio/accel/mma9551_core.c b/drivers/iio/accel/mma9551_core.c
index 7f55a6d7cd03..c6d5a3a40b60 100644
--- a/drivers/iio/accel/mma9551_core.c
+++ b/drivers/iio/accel/mma9551_core.c
@@ -389,7 +389,12 @@ int mma9551_read_config_words(struct i2c_client *client, u8 app_id,
 {
 	int ret, i;
 	int len_words = len / sizeof(u16);
-	__be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+	__be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS / 2];
+
+	if (len_words > ARRAY_SIZE(be_buf)) {
+		dev_err(&client->dev, "Invalid buffer size %d\n", len);
+		return -EINVAL;
+	}
 
 	ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_CONFIG,
 			       reg, NULL, 0, (u8 *) be_buf, len);
@@ -424,7 +429,12 @@ int mma9551_read_status_words(struct i2c_client *client, u8 app_id,
 {
 	int ret, i;
 	int len_words = len / sizeof(u16);
-	__be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+	__be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS / 2];
+
+	if (len_words > ARRAY_SIZE(be_buf)) {
+		dev_err(&client->dev, "Invalid buffer size %d\n", len);
+		return -EINVAL;
+	}
 
 	ret = mma9551_transfer(client, app_id, MMA9551_CMD_READ_STATUS,
 			       reg, NULL, 0, (u8 *) be_buf, len);
@@ -459,7 +469,12 @@ int mma9551_write_config_words(struct i2c_client *client, u8 app_id,
 {
 	int i;
 	int len_words = len / sizeof(u16);
-	__be16 be_buf[MMA9551_MAX_MAILBOX_DATA_REGS];
+	__be16 be_buf[(MMA9551_MAX_MAILBOX_DATA_REGS - 1) / 2];
+
+	if (len_words > ARRAY_SIZE(be_buf)) {
+		dev_err(&client->dev, "Invalid buffer size %d\n", len);
+		return -EINVAL;
+	}
 
 	for (i = 0; i < len_words; i++)
 		be_buf[i] = cpu_to_be16(buf[i]);
diff --git a/drivers/iio/accel/mma9553.c b/drivers/iio/accel/mma9553.c
index 2df1af7d43fc..365a109aaaef 100644
--- a/drivers/iio/accel/mma9553.c
+++ b/drivers/iio/accel/mma9553.c
@@ -54,6 +54,7 @@
 #define MMA9553_MASK_CONF_STEPCOALESCE		GENMASK(7, 0)
 
 #define MMA9553_REG_CONF_ACTTHD			0x0E
+#define MMA9553_MAX_ACTTHD			GENMASK(15, 0)
 
 /* Pedometer status registers (R-only) */
 #define MMA9553_REG_STATUS			0x00
@@ -316,22 +317,19 @@ static int mma9553_set_config(struct mma9553_data *data, u16 reg,
 static int mma9553_read_activity_stepcnt(struct mma9553_data *data,
 					 u8 *activity, u16 *stepcnt)
 {
-	u32 status_stepcnt;
-	u16 status;
+	u16 buf[2];
 	int ret;
 
 	ret = mma9551_read_status_words(data->client, MMA9551_APPID_PEDOMETER,
-					MMA9553_REG_STATUS, sizeof(u32),
-					(u16 *) &status_stepcnt);
+					MMA9553_REG_STATUS, sizeof(u32), buf);
 	if (ret < 0) {
 		dev_err(&data->client->dev,
 			"error reading status and stepcnt\n");
 		return ret;
 	}
 
-	status = status_stepcnt & MMA9553_MASK_CONF_WORD;
-	*activity = mma9553_get_bits(status, MMA9553_MASK_STATUS_ACTIVITY);
-	*stepcnt = status_stepcnt >> 16;
+	*activity = mma9553_get_bits(buf[0], MMA9553_MASK_STATUS_ACTIVITY);
+	*stepcnt = buf[1];
 
 	return 0;
 }
@@ -872,6 +870,9 @@ static int mma9553_write_event_value(struct iio_dev *indio_dev,
 	case IIO_EV_INFO_PERIOD:
 		switch (chan->type) {
 		case IIO_ACTIVITY:
+			if (val < 0 || val > MMA9553_ACTIVITY_THD_TO_SEC(
+			    MMA9553_MAX_ACTTHD))
+				return -EINVAL;
 			mutex_lock(&data->mutex);
 			ret = mma9553_set_config(data, MMA9553_REG_CONF_ACTTHD,
 						 &data->conf.actthd,
@@ -971,7 +972,8 @@ static const struct iio_chan_spec_ext_info mma9553_ext_info[] = {
 	.modified = 1,							\
 	.channel2 = _chan2,						\
 	.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),		\
-	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_CALIBHEIGHT),	\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_CALIBHEIGHT) |	\
+				    BIT(IIO_CHAN_INFO_ENABLE),		\
 	.event_spec = mma9553_activity_events,				\
 	.num_event_specs = ARRAY_SIZE(mma9553_activity_events),		\
 	.ext_info = mma9553_ext_info,					\
diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c
index 58d1d13d552a..211b13271c61 100644
--- a/drivers/iio/accel/st_accel_core.c
+++ b/drivers/iio/accel/st_accel_core.c
@@ -546,6 +546,7 @@ int st_accel_common_probe(struct iio_dev *indio_dev)
 
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &accel_info;
+	mutex_init(&adata->tb.buf_lock);
 
 	st_sensors_power_enable(indio_dev);
 
diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c
index 08bcfb061ca5..56008a86b78f 100644
--- a/drivers/iio/adc/axp288_adc.c
+++ b/drivers/iio/adc/axp288_adc.c
@@ -53,39 +53,42 @@ static const struct iio_chan_spec const axp288_adc_channels[] = {
 		.channel = 0,
 		.address = AXP288_TS_ADC_H,
 		.datasheet_name = "TS_PIN",
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	}, {
 		.indexed = 1,
 		.type = IIO_TEMP,
 		.channel = 1,
 		.address = AXP288_PMIC_ADC_H,
 		.datasheet_name = "PMIC_TEMP",
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	}, {
 		.indexed = 1,
 		.type = IIO_TEMP,
 		.channel = 2,
 		.address = AXP288_GP_ADC_H,
 		.datasheet_name = "GPADC",
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	}, {
 		.indexed = 1,
 		.type = IIO_CURRENT,
 		.channel = 3,
 		.address = AXP20X_BATT_CHRG_I_H,
 		.datasheet_name = "BATT_CHG_I",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	}, {
 		.indexed = 1,
 		.type = IIO_CURRENT,
 		.channel = 4,
 		.address = AXP20X_BATT_DISCHRG_I_H,
 		.datasheet_name = "BATT_DISCHRG_I",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	}, {
 		.indexed = 1,
 		.type = IIO_VOLTAGE,
 		.channel = 5,
 		.address = AXP20X_BATT_V_H,
 		.datasheet_name = "BATT_V",
-		.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 	},
 };
 
@@ -151,9 +154,6 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev,
 						chan->address))
 			dev_err(&indio_dev->dev, "TS pin restore\n");
 		break;
-	case IIO_CHAN_INFO_PROCESSED:
-		ret = axp288_adc_read_channel(val, chan->address, info->regmap);
-		break;
 	default:
 		ret = -EINVAL;
 	}
diff --git a/drivers/iio/adc/cc10001_adc.c b/drivers/iio/adc/cc10001_adc.c
index 51e2a83c9404..115f6e99a7fa 100644
--- a/drivers/iio/adc/cc10001_adc.c
+++ b/drivers/iio/adc/cc10001_adc.c
@@ -35,8 +35,9 @@
 #define CC10001_ADC_EOC_SET		BIT(0)
 
 #define CC10001_ADC_CHSEL_SAMPLED	0x0c
-#define CC10001_ADC_POWER_UP		0x10
-#define CC10001_ADC_POWER_UP_SET	BIT(0)
+#define CC10001_ADC_POWER_DOWN		0x10
+#define CC10001_ADC_POWER_DOWN_SET	BIT(0)
+
 #define CC10001_ADC_DEBUG		0x14
 #define CC10001_ADC_DATA_COUNT		0x20
 
@@ -62,7 +63,6 @@ struct cc10001_adc_device {
 	u16 *buf;
 
 	struct mutex lock;
-	unsigned long channel_map;
 	unsigned int start_delay_ns;
 	unsigned int eoc_delay_ns;
 };
@@ -79,6 +79,18 @@ static inline u32 cc10001_adc_read_reg(struct cc10001_adc_device *adc_dev,
 	return readl(adc_dev->reg_base + reg);
 }
 
+static void cc10001_adc_power_up(struct cc10001_adc_device *adc_dev)
+{
+	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN, 0);
+	ndelay(adc_dev->start_delay_ns);
+}
+
+static void cc10001_adc_power_down(struct cc10001_adc_device *adc_dev)
+{
+	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_DOWN,
+			      CC10001_ADC_POWER_DOWN_SET);
+}
+
 static void cc10001_adc_start(struct cc10001_adc_device *adc_dev,
 			      unsigned int channel)
 {
@@ -88,6 +100,7 @@ static void cc10001_adc_start(struct cc10001_adc_device *adc_dev,
 	val = (channel & CC10001_ADC_CH_MASK) | CC10001_ADC_MODE_SINGLE_CONV;
 	cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val);
 
+	udelay(1);
 	val = cc10001_adc_read_reg(adc_dev, CC10001_ADC_CONFIG);
 	val = val | CC10001_ADC_START_CONV;
 	cc10001_adc_write_reg(adc_dev, CC10001_ADC_CONFIG, val);
@@ -129,6 +142,7 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p)
 	struct iio_dev *indio_dev;
 	unsigned int delay_ns;
 	unsigned int channel;
+	unsigned int scan_idx;
 	bool sample_invalid;
 	u16 *data;
 	int i;
@@ -139,20 +153,17 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p)
 
 	mutex_lock(&adc_dev->lock);
 
-	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP,
-			      CC10001_ADC_POWER_UP_SET);
-
-	/* Wait for 8 (6+2) clock cycles before activating START */
-	ndelay(adc_dev->start_delay_ns);
+	cc10001_adc_power_up(adc_dev);
 
 	/* Calculate delay step for eoc and sampled data */
 	delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT;
 
 	i = 0;
 	sample_invalid = false;
-	for_each_set_bit(channel, indio_dev->active_scan_mask,
+	for_each_set_bit(scan_idx, indio_dev->active_scan_mask,
 				  indio_dev->masklength) {
 
+		channel = indio_dev->channels[scan_idx].channel;
 		cc10001_adc_start(adc_dev, channel);
 
 		data[i] = cc10001_adc_poll_done(indio_dev, channel, delay_ns);
@@ -166,7 +177,7 @@ static irqreturn_t cc10001_adc_trigger_h(int irq, void *p)
 	}
 
 done:
-	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0);
+	cc10001_adc_power_down(adc_dev);
 
 	mutex_unlock(&adc_dev->lock);
 
@@ -185,11 +196,7 @@ static u16 cc10001_adc_read_raw_voltage(struct iio_dev *indio_dev,
 	unsigned int delay_ns;
 	u16 val;
 
-	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP,
-			      CC10001_ADC_POWER_UP_SET);
-
-	/* Wait for 8 (6+2) clock cycles before activating START */
-	ndelay(adc_dev->start_delay_ns);
+	cc10001_adc_power_up(adc_dev);
 
 	/* Calculate delay step for eoc and sampled data */
 	delay_ns = adc_dev->eoc_delay_ns / CC10001_MAX_POLL_COUNT;
@@ -198,7 +205,7 @@ static u16 cc10001_adc_read_raw_voltage(struct iio_dev *indio_dev,
 
 	val = cc10001_adc_poll_done(indio_dev, chan->channel, delay_ns);
 
-	cc10001_adc_write_reg(adc_dev, CC10001_ADC_POWER_UP, 0);
+	cc10001_adc_power_down(adc_dev);
 
 	return val;
 }
@@ -224,7 +231,7 @@ static int cc10001_adc_read_raw(struct iio_dev *indio_dev,
 
 	case IIO_CHAN_INFO_SCALE:
 		ret = regulator_get_voltage(adc_dev->reg);
-		if (ret)
+		if (ret < 0)
 			return ret;
 
 		*val = ret / 1000;
@@ -255,22 +262,22 @@ static const struct iio_info cc10001_adc_info = {
 	.update_scan_mode = &cc10001_update_scan_mode,
 };
 
-static int cc10001_adc_channel_init(struct iio_dev *indio_dev)
+static int cc10001_adc_channel_init(struct iio_dev *indio_dev,
+				    unsigned long channel_map)
 {
-	struct cc10001_adc_device *adc_dev = iio_priv(indio_dev);
 	struct iio_chan_spec *chan_array, *timestamp;
 	unsigned int bit, idx = 0;
 
-	indio_dev->num_channels = bitmap_weight(&adc_dev->channel_map,
-						CC10001_ADC_NUM_CHANNELS);
+	indio_dev->num_channels = bitmap_weight(&channel_map,
+						CC10001_ADC_NUM_CHANNELS) + 1;
 
-	chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels + 1,
+	chan_array = devm_kcalloc(&indio_dev->dev, indio_dev->num_channels,
 				  sizeof(struct iio_chan_spec),
 				  GFP_KERNEL);
 	if (!chan_array)
 		return -ENOMEM;
 
-	for_each_set_bit(bit, &adc_dev->channel_map, CC10001_ADC_NUM_CHANNELS) {
+	for_each_set_bit(bit, &channel_map, CC10001_ADC_NUM_CHANNELS) {
 		struct iio_chan_spec *chan = &chan_array[idx];
 
 		chan->type = IIO_VOLTAGE;
@@ -305,6 +312,7 @@ static int cc10001_adc_probe(struct platform_device *pdev)
 	unsigned long adc_clk_rate;
 	struct resource *res;
 	struct iio_dev *indio_dev;
+	unsigned long channel_map;
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc_dev));
@@ -313,9 +321,9 @@ static int cc10001_adc_probe(struct platform_device *pdev)
 
 	adc_dev = iio_priv(indio_dev);
 
-	adc_dev->channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0);
+	channel_map = GENMASK(CC10001_ADC_NUM_CHANNELS - 1, 0);
 	if (!of_property_read_u32(node, "adc-reserved-channels", &ret))
-		adc_dev->channel_map &= ~ret;
+		channel_map &= ~ret;
 
 	adc_dev->reg = devm_regulator_get(&pdev->dev, "vref");
 	if (IS_ERR(adc_dev->reg))
@@ -361,7 +369,7 @@ static int cc10001_adc_probe(struct platform_device *pdev)
 	adc_dev->start_delay_ns = adc_dev->eoc_delay_ns * CC10001_WAIT_CYCLES;
 
 	/* Setup the ADC channels available on the device */
-	ret = cc10001_adc_channel_init(indio_dev);
+	ret = cc10001_adc_channel_init(indio_dev, channel_map);
 	if (ret < 0)
 		goto err_disable_clk;
 
diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c
index efbfd12a4bfd..8d9c9b9215dd 100644
--- a/drivers/iio/adc/mcp320x.c
+++ b/drivers/iio/adc/mcp320x.c
@@ -60,12 +60,12 @@ struct mcp320x {
 	struct spi_message msg;
 	struct spi_transfer transfer[2];
 
-	u8 tx_buf;
-	u8 rx_buf[2];
-
 	struct regulator *reg;
 	struct mutex lock;
 	const struct mcp320x_chip_info *chip_info;
+
+	u8 tx_buf ____cacheline_aligned;
+	u8 rx_buf[2];
 };
 
 static int mcp320x_channel_to_tx_data(int device_index,
diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c
index 3211729bcb0b..0c4618b4d515 100644
--- a/drivers/iio/adc/qcom-spmi-vadc.c
+++ b/drivers/iio/adc/qcom-spmi-vadc.c
@@ -18,6 +18,7 @@
 #include <linux/iio/iio.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -471,11 +472,11 @@ static s32 vadc_calibrate(struct vadc_priv *vadc,
 			  const struct vadc_channel_prop *prop, u16 adc_code)
 {
 	const struct vadc_prescale_ratio *prescale;
-	s32 voltage;
+	s64 voltage;
 
 	voltage = adc_code - vadc->graph[prop->calibration].gnd;
 	voltage *= vadc->graph[prop->calibration].dx;
-	voltage = voltage / vadc->graph[prop->calibration].dy;
+	voltage = div64_s64(voltage, vadc->graph[prop->calibration].dy);
 
 	if (prop->calibration == VADC_CALIB_ABSOLUTE)
 		voltage += vadc->graph[prop->calibration].dx;
@@ -487,7 +488,7 @@ static s32 vadc_calibrate(struct vadc_priv *vadc,
 
 	voltage = voltage * prescale->den;
 
-	return voltage / prescale->num;
+	return div64_s64(voltage, prescale->num);
 }
 
 static int vadc_decimation_from_dt(u32 value)
diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c
index 89d8aa1d2818..df12c57e6ce0 100644
--- a/drivers/iio/adc/twl6030-gpadc.c
+++ b/drivers/iio/adc/twl6030-gpadc.c
@@ -1001,7 +1001,7 @@ static struct platform_driver twl6030_gpadc_driver = {
 
 module_platform_driver(twl6030_gpadc_driver);
 
-MODULE_ALIAS("platform: " DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
 MODULE_AUTHOR("Balaji T K <balajitk@ti.com>");
 MODULE_AUTHOR("Graeme Gregory <gg@slimlogic.co.uk>");
 MODULE_AUTHOR("Oleksandr Kozaruk <oleksandr.kozaruk@ti.com");
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index a221f7329b79..ce93bd8e3f68 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -856,6 +856,7 @@ static int xadc_read_raw(struct iio_dev *indio_dev,
 			switch (chan->address) {
 			case XADC_REG_VCCINT:
 			case XADC_REG_VCCAUX:
+			case XADC_REG_VREFP:
 			case XADC_REG_VCCBRAM:
 			case XADC_REG_VCCPINT:
 			case XADC_REG_VCCPAUX:
@@ -996,7 +997,7 @@ static const struct iio_event_spec xadc_voltage_events[] = {
 	.num_event_specs = (_alarm) ? ARRAY_SIZE(xadc_voltage_events) : 0, \
 	.scan_index = (_scan_index), \
 	.scan_type = { \
-		.sign = 'u', \
+		.sign = ((_addr) == XADC_REG_VREFN) ? 's' : 'u', \
 		.realbits = 12, \
 		.storagebits = 16, \
 		.shift = 4, \
@@ -1008,7 +1009,7 @@ static const struct iio_event_spec xadc_voltage_events[] = {
 static const struct iio_chan_spec xadc_channels[] = {
 	XADC_CHAN_TEMP(0, 8, XADC_REG_TEMP),
 	XADC_CHAN_VOLTAGE(0, 9, XADC_REG_VCCINT, "vccint", true),
-	XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCINT, "vccaux", true),
+	XADC_CHAN_VOLTAGE(1, 10, XADC_REG_VCCAUX, "vccaux", true),
 	XADC_CHAN_VOLTAGE(2, 14, XADC_REG_VCCBRAM, "vccbram", true),
 	XADC_CHAN_VOLTAGE(3, 5, XADC_REG_VCCPINT, "vccpint", true),
 	XADC_CHAN_VOLTAGE(4, 6, XADC_REG_VCCPAUX, "vccpaux", true),
diff --git a/drivers/iio/adc/xilinx-xadc.h b/drivers/iio/adc/xilinx-xadc.h
index c7487e8d7f80..54adc5087210 100644
--- a/drivers/iio/adc/xilinx-xadc.h
+++ b/drivers/iio/adc/xilinx-xadc.h
@@ -145,9 +145,9 @@ static inline int xadc_write_adc_reg(struct xadc *xadc, unsigned int reg,
 #define XADC_REG_MAX_VCCPINT	0x28
 #define XADC_REG_MAX_VCCPAUX	0x29
 #define XADC_REG_MAX_VCCO_DDR	0x2a
-#define XADC_REG_MIN_VCCPINT	0x2b
-#define XADC_REG_MIN_VCCPAUX	0x2c
-#define XADC_REG_MIN_VCCO_DDR	0x2d
+#define XADC_REG_MIN_VCCPINT	0x2c
+#define XADC_REG_MIN_VCCPAUX	0x2d
+#define XADC_REG_MIN_VCCO_DDR	0x2e
 
 #define XADC_REG_CONF0		0x40
 #define XADC_REG_CONF1		0x41
diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c
index edd13d2b4121..8dd0477e201c 100644
--- a/drivers/iio/common/st_sensors/st_sensors_core.c
+++ b/drivers/iio/common/st_sensors/st_sensors_core.c
@@ -304,8 +304,6 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 	struct st_sensors_platform_data *of_pdata;
 	int err = 0;
 
-	mutex_init(&sdata->tb.buf_lock);
-
 	/* If OF/DT pdata exists, it will take precedence of anything else */
 	of_pdata = st_sensors_of_probe(indio_dev->dev.parent, pdata);
 	if (of_pdata)
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index 21395f26d227..ffe96642b6d0 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -400,6 +400,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev)
 
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &gyro_info;
+	mutex_init(&gdata->tb.buf_lock);
 
 	st_sensors_power_enable(indio_dev);
 
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 0916bf6b6c31..73b189c1c0fb 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -139,6 +139,7 @@
 #define ADIS16400_NO_BURST		BIT(1)
 #define ADIS16400_HAS_SLOW_MODE		BIT(2)
 #define ADIS16400_HAS_SERIAL_NUMBER	BIT(3)
+#define ADIS16400_BURST_DIAG_STAT	BIT(4)
 
 struct adis16400_state;
 
@@ -165,6 +166,7 @@ struct adis16400_state {
 	int				filt_int;
 
 	struct adis adis;
+	unsigned long avail_scan_mask[2];
 };
 
 /* At the moment triggers are only used for ring buffer
diff --git a/drivers/iio/imu/adis16400_buffer.c b/drivers/iio/imu/adis16400_buffer.c
index 6e727ffe5262..90c24a23c679 100644
--- a/drivers/iio/imu/adis16400_buffer.c
+++ b/drivers/iio/imu/adis16400_buffer.c
@@ -18,7 +18,8 @@ int adis16400_update_scan_mode(struct iio_dev *indio_dev,
 {
 	struct adis16400_state *st = iio_priv(indio_dev);
 	struct adis *adis = &st->adis;
-	uint16_t *tx;
+	unsigned int burst_length;
+	u8 *tx;
 
 	if (st->variant->flags & ADIS16400_NO_BURST)
 		return adis_update_scan_mode(indio_dev, scan_mask);
@@ -26,26 +27,29 @@ int adis16400_update_scan_mode(struct iio_dev *indio_dev,
 	kfree(adis->xfer);
 	kfree(adis->buffer);
 
+	/* All but the timestamp channel */
+	burst_length = (indio_dev->num_channels - 1) * sizeof(u16);
+	if (st->variant->flags & ADIS16400_BURST_DIAG_STAT)
+		burst_length += sizeof(u16);
+
 	adis->xfer = kcalloc(2, sizeof(*adis->xfer), GFP_KERNEL);
 	if (!adis->xfer)
 		return -ENOMEM;
 
-	adis->buffer = kzalloc(indio_dev->scan_bytes + sizeof(u16),
-		GFP_KERNEL);
+	adis->buffer = kzalloc(burst_length + sizeof(u16), GFP_KERNEL);
 	if (!adis->buffer)
 		return -ENOMEM;
 
-	tx = adis->buffer + indio_dev->scan_bytes;
-
+	tx = adis->buffer + burst_length;
 	tx[0] = ADIS_READ_REG(ADIS16400_GLOB_CMD);
 	tx[1] = 0;
 
 	adis->xfer[0].tx_buf = tx;
 	adis->xfer[0].bits_per_word = 8;
 	adis->xfer[0].len = 2;
-	adis->xfer[1].tx_buf = tx;
+	adis->xfer[1].rx_buf = adis->buffer;
 	adis->xfer[1].bits_per_word = 8;
-	adis->xfer[1].len = indio_dev->scan_bytes;
+	adis->xfer[1].len = burst_length;
 
 	spi_message_init(&adis->msg);
 	spi_message_add_tail(&adis->xfer[0], &adis->msg);
@@ -61,6 +65,7 @@ irqreturn_t adis16400_trigger_handler(int irq, void *p)
 	struct adis16400_state *st = iio_priv(indio_dev);
 	struct adis *adis = &st->adis;
 	u32 old_speed_hz = st->adis.spi->max_speed_hz;
+	void *buffer;
 	int ret;
 
 	if (!adis->buffer)
@@ -81,7 +86,12 @@ irqreturn_t adis16400_trigger_handler(int irq, void *p)
 		spi_setup(st->adis.spi);
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, adis->buffer,
+	if (st->variant->flags & ADIS16400_BURST_DIAG_STAT)
+		buffer = adis->buffer + sizeof(u16);
+	else
+		buffer = adis->buffer;
+
+	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
 		pf->timestamp);
 
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index fa795dcd5f75..2fd68f2219a7 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -405,6 +405,11 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 			*val = st->variant->temp_scale_nano / 1000000;
 			*val2 = (st->variant->temp_scale_nano % 1000000);
 			return IIO_VAL_INT_PLUS_MICRO;
+		case IIO_PRESSURE:
+			/* 20 uBar = 0.002kPascal */
+			*val = 0;
+			*val2 = 2000;
+			return IIO_VAL_INT_PLUS_MICRO;
 		default:
 			return -EINVAL;
 		}
@@ -454,10 +459,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 	}
 }
 
-#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si) { \
+#define ADIS16400_VOLTAGE_CHAN(addr, bits, name, si, chn) { \
 	.type = IIO_VOLTAGE, \
 	.indexed = 1, \
-	.channel = 0, \
+	.channel = chn, \
 	.extend_name = name, \
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
 		BIT(IIO_CHAN_INFO_SCALE), \
@@ -474,10 +479,10 @@ static int adis16400_read_raw(struct iio_dev *indio_dev,
 }
 
 #define ADIS16400_SUPPLY_CHAN(addr, bits) \
-	ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY)
+	ADIS16400_VOLTAGE_CHAN(addr, bits, "supply", ADIS16400_SCAN_SUPPLY, 0)
 
 #define ADIS16400_AUX_ADC_CHAN(addr, bits) \
-	ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC)
+	ADIS16400_VOLTAGE_CHAN(addr, bits, NULL, ADIS16400_SCAN_ADC, 1)
 
 #define ADIS16400_GYRO_CHAN(mod, addr, bits) { \
 	.type = IIO_ANGL_VEL, \
@@ -773,7 +778,8 @@ static struct adis16400_chip_info adis16400_chips[] = {
 		.channels = adis16448_channels,
 		.num_channels = ARRAY_SIZE(adis16448_channels),
 		.flags = ADIS16400_HAS_PROD_ID |
-				ADIS16400_HAS_SERIAL_NUMBER,
+				ADIS16400_HAS_SERIAL_NUMBER |
+				ADIS16400_BURST_DIAG_STAT,
 		.gyro_scale_micro = IIO_DEGREE_TO_RAD(10000), /* 0.01 deg/s */
 		.accel_scale_micro = IIO_G_TO_M_S_2(833), /* 1/1200 g */
 		.temp_scale_nano = 73860000, /* 0.07386 C */
@@ -791,11 +797,6 @@ static const struct iio_info adis16400_info = {
 	.debugfs_reg_access = adis_debugfs_reg_access,
 };
 
-static const unsigned long adis16400_burst_scan_mask[] = {
-	~0UL,
-	0,
-};
-
 static const char * const adis16400_status_error_msgs[] = {
 	[ADIS16400_DIAG_STAT_ZACCL_FAIL] = "Z-axis accelerometer self-test failure",
 	[ADIS16400_DIAG_STAT_YACCL_FAIL] = "Y-axis accelerometer self-test failure",
@@ -843,6 +844,20 @@ static const struct adis_data adis16400_data = {
 		BIT(ADIS16400_DIAG_STAT_POWER_LOW),
 };
 
+static void adis16400_setup_chan_mask(struct adis16400_state *st)
+{
+	const struct adis16400_chip_info *chip_info = st->variant;
+	unsigned i;
+
+	for (i = 0; i < chip_info->num_channels; i++) {
+		const struct iio_chan_spec *ch = &chip_info->channels[i];
+
+		if (ch->scan_index >= 0 &&
+		    ch->scan_index != ADIS16400_SCAN_TIMESTAMP)
+			st->avail_scan_mask[0] |= BIT(ch->scan_index);
+	}
+}
+
 static int adis16400_probe(struct spi_device *spi)
 {
 	struct adis16400_state *st;
@@ -866,8 +881,10 @@ static int adis16400_probe(struct spi_device *spi)
 	indio_dev->info = &adis16400_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 
-	if (!(st->variant->flags & ADIS16400_NO_BURST))
-		indio_dev->available_scan_masks = adis16400_burst_scan_mask;
+	if (!(st->variant->flags & ADIS16400_NO_BURST)) {
+		adis16400_setup_chan_mask(st);
+		indio_dev->available_scan_masks = st->avail_scan_mask;
+	}
 
 	ret = adis_init(&st->adis, indio_dev, spi, &adis16400_data);
 	if (ret)
diff --git a/drivers/iio/kfifo_buf.c b/drivers/iio/kfifo_buf.c
index 847ca561afe0..55c267bbfd2f 100644
--- a/drivers/iio/kfifo_buf.c
+++ b/drivers/iio/kfifo_buf.c
@@ -38,7 +38,8 @@ static int iio_request_update_kfifo(struct iio_buffer *r)
 		kfifo_free(&buf->kf);
 		ret = __iio_allocate_kfifo(buf, buf->buffer.bytes_per_datum,
 				   buf->buffer.length);
-		buf->update_needed = false;
+		if (ret >= 0)
+			buf->update_needed = false;
 	} else {
 		kfifo_reset_out(&buf->kf);
 	}
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 91ecc46ffeaa..ef60bae738e3 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -43,8 +43,6 @@ struct prox_state {
 static const struct iio_chan_spec prox_channels[] = {
 	{
 		.type = IIO_PROXIMITY,
-		.modified = 1,
-		.channel2 = IIO_NO_MOD,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
 		BIT(IIO_CHAN_INFO_SCALE) |
@@ -253,7 +251,6 @@ static int hid_prox_probe(struct platform_device *pdev)
 	struct iio_dev *indio_dev;
 	struct prox_state *prox_state;
 	struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
-	struct iio_chan_spec *channels;
 
 	indio_dev = devm_iio_device_alloc(&pdev->dev,
 				sizeof(struct prox_state));
@@ -272,20 +269,21 @@ static int hid_prox_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	channels = kmemdup(prox_channels, sizeof(prox_channels), GFP_KERNEL);
-	if (!channels) {
+	indio_dev->channels = kmemdup(prox_channels, sizeof(prox_channels),
+				      GFP_KERNEL);
+	if (!indio_dev->channels) {
 		dev_err(&pdev->dev, "failed to duplicate channels\n");
 		return -ENOMEM;
 	}
 
-	ret = prox_parse_report(pdev, hsdev, channels,
+	ret = prox_parse_report(pdev, hsdev,
+				(struct iio_chan_spec *)indio_dev->channels,
 				HID_USAGE_SENSOR_PROX, prox_state);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to setup attributes\n");
 		goto error_free_dev_mem;
 	}
 
-	indio_dev->channels = channels;
 	indio_dev->num_channels =
 				ARRAY_SIZE(prox_channels);
 	indio_dev->dev.parent = &pdev->dev;
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 8ade473f99fe..2e56f812a644 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -369,6 +369,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev)
 
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &magn_info;
+	mutex_init(&mdata->tb.buf_lock);
 
 	st_sensors_power_enable(indio_dev);
 
diff --git a/drivers/iio/pressure/bmp280.c b/drivers/iio/pressure/bmp280.c
index 7c623e2bd633..a2602d8dd6d5 100644
--- a/drivers/iio/pressure/bmp280.c
+++ b/drivers/iio/pressure/bmp280.c
@@ -172,6 +172,7 @@ static s32 bmp280_compensate_temp(struct bmp280_data *data,
 	var2 = (((((adc_temp >> 4) - ((s32)le16_to_cpu(buf[T1]))) *
 		  ((adc_temp >> 4) - ((s32)le16_to_cpu(buf[T1])))) >> 12) *
 		((s32)(s16)le16_to_cpu(buf[T3]))) >> 14;
+	data->t_fine = var1 + var2;
 
 	return (data->t_fine * 5 + 128) >> 8;
 }
diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
index 7bb8d4c1f7df..3cf0bd67d24c 100644
--- a/drivers/iio/pressure/hid-sensor-press.c
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -47,8 +47,6 @@ struct press_state {
 static const struct iio_chan_spec press_channels[] = {
 	{
 		.type = IIO_PRESSURE,
-		.modified = 1,
-		.channel2 = IIO_NO_MOD,
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
 		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
 		BIT(IIO_CHAN_INFO_SCALE) |
diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c
index 97baf40d424b..e881fa6291e9 100644
--- a/drivers/iio/pressure/st_pressure_core.c
+++ b/drivers/iio/pressure/st_pressure_core.c
@@ -417,6 +417,7 @@ int st_press_common_probe(struct iio_dev *indio_dev)
 
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->info = &press_info;
+	mutex_init(&press_data->tb.buf_lock);
 
 	st_sensors_power_enable(indio_dev);
 
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index f80da50d84a5..746cdf56bc76 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -457,8 +457,8 @@ static void resolve_cb(int status, struct sockaddr *src_addr,
 	complete(&((struct resolve_cb_context *)context)->comp);
 }
 
-int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
-			       u16 *vlan_id)
+int rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgid,
+			       u8 *dmac, u16 *vlan_id)
 {
 	int ret = 0;
 	struct rdma_dev_addr dev_addr;
@@ -472,13 +472,8 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
 	} sgid_addr, dgid_addr;
 
 
-	ret = rdma_gid2ip(&sgid_addr._sockaddr, sgid);
-	if (ret)
-		return ret;
-
-	ret = rdma_gid2ip(&dgid_addr._sockaddr, dgid);
-	if (ret)
-		return ret;
+	rdma_gid2ip(&sgid_addr._sockaddr, sgid);
+	rdma_gid2ip(&dgid_addr._sockaddr, dgid);
 
 	memset(&dev_addr, 0, sizeof(dev_addr));
 
@@ -512,10 +507,8 @@ int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
 		struct sockaddr_in6 _sockaddr_in6;
 	} gid_addr;
 
-	ret = rdma_gid2ip(&gid_addr._sockaddr, sgid);
+	rdma_gid2ip(&gid_addr._sockaddr, sgid);
 
-	if (ret)
-		return ret;
 	memset(&dev_addr, 0, sizeof(dev_addr));
 	ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
 	if (ret)
diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c
index f6d29614cb01..c7dcfe4ca5f1 100644
--- a/drivers/infiniband/core/agent.c
+++ b/drivers/infiniband/core/agent.c
@@ -54,7 +54,7 @@ static DEFINE_SPINLOCK(ib_agent_port_list_lock);
 static LIST_HEAD(ib_agent_port_list);
 
 static struct ib_agent_port_private *
-__ib_get_agent_port(struct ib_device *device, int port_num)
+__ib_get_agent_port(const struct ib_device *device, int port_num)
 {
 	struct ib_agent_port_private *entry;
 
@@ -67,7 +67,7 @@ __ib_get_agent_port(struct ib_device *device, int port_num)
 }
 
 static struct ib_agent_port_private *
-ib_get_agent_port(struct ib_device *device, int port_num)
+ib_get_agent_port(const struct ib_device *device, int port_num)
 {
 	struct ib_agent_port_private *entry;
 	unsigned long flags;
@@ -78,9 +78,9 @@ ib_get_agent_port(struct ib_device *device, int port_num)
 	return entry;
 }
 
-void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
-			 struct ib_wc *wc, struct ib_device *device,
-			 int port_num, int qpn)
+void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
+			 const struct ib_wc *wc, const struct ib_device *device,
+			 int port_num, int qpn, size_t resp_mad_len, bool opa)
 {
 	struct ib_agent_port_private *port_priv;
 	struct ib_mad_agent *agent;
@@ -106,15 +106,20 @@ void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
 		return;
 	}
 
+	if (opa && mad_hdr->base_version != OPA_MGMT_BASE_VERSION)
+		resp_mad_len = IB_MGMT_MAD_SIZE;
+
 	send_buf = ib_create_send_mad(agent, wc->src_qp, wc->pkey_index, 0,
-				      IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-				      GFP_KERNEL);
+				      IB_MGMT_MAD_HDR,
+				      resp_mad_len - IB_MGMT_MAD_HDR,
+				      GFP_KERNEL,
+				      mad_hdr->base_version);
 	if (IS_ERR(send_buf)) {
 		dev_err(&device->dev, "ib_create_send_mad error\n");
 		goto err1;
 	}
 
-	memcpy(send_buf->mad, mad, sizeof *mad);
+	memcpy(send_buf->mad, mad_hdr, resp_mad_len);
 	send_buf->ah = ah;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
@@ -156,7 +161,7 @@ int ib_agent_port_open(struct ib_device *device, int port_num)
 		goto error1;
 	}
 
-	if (rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND) {
+	if (rdma_cap_ib_smi(device, port_num)) {
 		/* Obtain send only MAD agent for SMI QP */
 		port_priv->agent[0] = ib_register_mad_agent(device, port_num,
 							    IB_QPT_SMI, NULL, 0,
diff --git a/drivers/infiniband/core/agent.h b/drivers/infiniband/core/agent.h
index 6669287009c2..65f92bedae44 100644
--- a/drivers/infiniband/core/agent.h
+++ b/drivers/infiniband/core/agent.h
@@ -44,8 +44,8 @@ extern int ib_agent_port_open(struct ib_device *device, int port_num);
 
 extern int ib_agent_port_close(struct ib_device *device, int port_num);
 
-extern void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
-				struct ib_wc *wc, struct ib_device *device,
-				int port_num, int qpn);
+extern void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
+				const struct ib_wc *wc, const struct ib_device *device,
+				int port_num, int qpn, size_t resp_mad_len, bool opa);
 
 #endif	/* __AGENT_H_ */
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 80f6cf2449fb..871da832d016 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -58,17 +58,6 @@ struct ib_update_work {
 	u8                 port_num;
 };
 
-static inline int start_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
-}
-
-static inline int end_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
-		0 : device->phys_port_cnt;
-}
-
 int ib_get_cached_gid(struct ib_device *device,
 		      u8                port_num,
 		      int               index,
@@ -78,12 +67,12 @@ int ib_get_cached_gid(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.gid_cache[port_num - start_port(device)];
+	cache = device->cache.gid_cache[port_num - rdma_start_port(device)];
 
 	if (index < 0 || index >= cache->table_len)
 		ret = -EINVAL;
@@ -96,10 +85,10 @@ int ib_get_cached_gid(struct ib_device *device,
 }
 EXPORT_SYMBOL(ib_get_cached_gid);
 
-int ib_find_cached_gid(struct ib_device *device,
-		       union ib_gid	*gid,
-		       u8               *port_num,
-		       u16              *index)
+int ib_find_cached_gid(struct ib_device   *device,
+		       const union ib_gid *gid,
+		       u8                 *port_num,
+		       u16                *index)
 {
 	struct ib_gid_cache *cache;
 	unsigned long flags;
@@ -112,11 +101,11 @@ int ib_find_cached_gid(struct ib_device *device,
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		cache = device->cache.gid_cache[p];
 		for (i = 0; i < cache->table_len; ++i) {
 			if (!memcmp(gid, &cache->table[i], sizeof *gid)) {
-				*port_num = p + start_port(device);
+				*port_num = p + rdma_start_port(device);
 				if (index)
 					*index = i;
 				ret = 0;
@@ -140,12 +129,12 @@ int ib_get_cached_pkey(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	if (index < 0 || index >= cache->table_len)
 		ret = -EINVAL;
@@ -169,12 +158,12 @@ int ib_find_cached_pkey(struct ib_device *device,
 	int ret = -ENOENT;
 	int partial_ix = -1;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	*index = -1;
 
@@ -209,12 +198,12 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 	int i;
 	int ret = -ENOENT;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	*index = -1;
 
@@ -238,11 +227,11 @@ int ib_get_cached_lmc(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
-	*lmc = device->cache.lmc_cache[port_num - start_port(device)];
+	*lmc = device->cache.lmc_cache[port_num - rdma_start_port(device)];
 	read_unlock_irqrestore(&device->cache.lock, flags);
 
 	return ret;
@@ -303,13 +292,13 @@ static void ib_cache_update(struct ib_device *device,
 
 	write_lock_irq(&device->cache.lock);
 
-	old_pkey_cache = device->cache.pkey_cache[port - start_port(device)];
-	old_gid_cache  = device->cache.gid_cache [port - start_port(device)];
+	old_pkey_cache = device->cache.pkey_cache[port - rdma_start_port(device)];
+	old_gid_cache  = device->cache.gid_cache [port - rdma_start_port(device)];
 
-	device->cache.pkey_cache[port - start_port(device)] = pkey_cache;
-	device->cache.gid_cache [port - start_port(device)] = gid_cache;
+	device->cache.pkey_cache[port - rdma_start_port(device)] = pkey_cache;
+	device->cache.gid_cache [port - rdma_start_port(device)] = gid_cache;
 
-	device->cache.lmc_cache[port - start_port(device)] = tprops->lmc;
+	device->cache.lmc_cache[port - rdma_start_port(device)] = tprops->lmc;
 
 	write_unlock_irq(&device->cache.lock);
 
@@ -363,14 +352,14 @@ static void ib_cache_setup_one(struct ib_device *device)
 
 	device->cache.pkey_cache =
 		kmalloc(sizeof *device->cache.pkey_cache *
-			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
+			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
 	device->cache.gid_cache =
 		kmalloc(sizeof *device->cache.gid_cache *
-			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
+			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
 
 	device->cache.lmc_cache = kmalloc(sizeof *device->cache.lmc_cache *
-					  (end_port(device) -
-					   start_port(device) + 1),
+					  (rdma_end_port(device) -
+					   rdma_start_port(device) + 1),
 					  GFP_KERNEL);
 
 	if (!device->cache.pkey_cache || !device->cache.gid_cache ||
@@ -380,10 +369,10 @@ static void ib_cache_setup_one(struct ib_device *device)
 		goto err;
 	}
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		device->cache.pkey_cache[p] = NULL;
 		device->cache.gid_cache [p] = NULL;
-		ib_cache_update(device, p + start_port(device));
+		ib_cache_update(device, p + rdma_start_port(device));
 	}
 
 	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
@@ -394,7 +383,7 @@ static void ib_cache_setup_one(struct ib_device *device)
 	return;
 
 err_cache:
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		kfree(device->cache.pkey_cache[p]);
 		kfree(device->cache.gid_cache[p]);
 	}
@@ -412,7 +401,7 @@ static void ib_cache_cleanup_one(struct ib_device *device)
 	ib_unregister_event_handler(&device->cache.event_handler);
 	flush_workqueue(ib_wq);
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		kfree(device->cache.pkey_cache[p]);
 		kfree(device->cache.gid_cache[p]);
 	}
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index e28a494e2a3a..dbddddd6fb5d 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -267,7 +267,8 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
 			       cm_id_priv->av.pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC);
+			       GFP_ATOMIC,
+			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
 		return PTR_ERR(m);
@@ -297,7 +298,8 @@ static int cm_alloc_response_msg(struct cm_port *port,
 
 	m = ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC);
+			       GFP_ATOMIC,
+			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
 		return PTR_ERR(m);
@@ -437,39 +439,38 @@ static struct cm_id_private * cm_acquire_id(__be32 local_id, __be32 remote_id)
 	return cm_id_priv;
 }
 
-static void cm_mask_copy(u8 *dst, u8 *src, u8 *mask)
+static void cm_mask_copy(u32 *dst, const u32 *src, const u32 *mask)
 {
 	int i;
 
-	for (i = 0; i < IB_CM_COMPARE_SIZE / sizeof(unsigned long); i++)
-		((unsigned long *) dst)[i] = ((unsigned long *) src)[i] &
-					     ((unsigned long *) mask)[i];
+	for (i = 0; i < IB_CM_COMPARE_SIZE; i++)
+		dst[i] = src[i] & mask[i];
 }
 
 static int cm_compare_data(struct ib_cm_compare_data *src_data,
 			   struct ib_cm_compare_data *dst_data)
 {
-	u8 src[IB_CM_COMPARE_SIZE];
-	u8 dst[IB_CM_COMPARE_SIZE];
+	u32 src[IB_CM_COMPARE_SIZE];
+	u32 dst[IB_CM_COMPARE_SIZE];
 
 	if (!src_data || !dst_data)
 		return 0;
 
 	cm_mask_copy(src, src_data->data, dst_data->mask);
 	cm_mask_copy(dst, dst_data->data, src_data->mask);
-	return memcmp(src, dst, IB_CM_COMPARE_SIZE);
+	return memcmp(src, dst, sizeof(src));
 }
 
-static int cm_compare_private_data(u8 *private_data,
+static int cm_compare_private_data(u32 *private_data,
 				   struct ib_cm_compare_data *dst_data)
 {
-	u8 src[IB_CM_COMPARE_SIZE];
+	u32 src[IB_CM_COMPARE_SIZE];
 
 	if (!dst_data)
 		return 0;
 
 	cm_mask_copy(src, private_data, dst_data->mask);
-	return memcmp(src, dst_data->data, IB_CM_COMPARE_SIZE);
+	return memcmp(src, dst_data->data, sizeof(src));
 }
 
 /*
@@ -538,7 +539,7 @@ static struct cm_id_private * cm_insert_listen(struct cm_id_private *cm_id_priv)
 
 static struct cm_id_private * cm_find_listen(struct ib_device *device,
 					     __be64 service_id,
-					     u8 *private_data)
+					     u32 *private_data)
 {
 	struct rb_node *node = cm.listen_service_table.rb_node;
 	struct cm_id_private *cm_id_priv;
@@ -862,6 +863,7 @@ retest:
 		cm_reject_sidr_req(cm_id_priv, IB_SIDR_REJECT);
 		break;
 	case IB_CM_REQ_SENT:
+	case IB_CM_MRA_REQ_RCVD:
 		ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
 		spin_unlock_irq(&cm_id_priv->lock);
 		ib_send_cm_rej(cm_id, IB_CM_REJ_TIMEOUT,
@@ -880,7 +882,6 @@ retest:
 				       NULL, 0, NULL, 0);
 		}
 		break;
-	case IB_CM_MRA_REQ_RCVD:
 	case IB_CM_REP_SENT:
 	case IB_CM_MRA_REP_RCVD:
 		ib_cancel_mad(cm_id_priv->av.port->mad_agent, cm_id_priv->msg);
@@ -953,7 +954,7 @@ int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask,
 		cm_mask_copy(cm_id_priv->compare_data->data,
 			     compare_data->data, compare_data->mask);
 		memcpy(cm_id_priv->compare_data->mask, compare_data->mask,
-		       IB_CM_COMPARE_SIZE);
+		       sizeof(compare_data->mask));
 	}
 
 	cm_id->state = IB_CM_LISTEN;
@@ -3760,11 +3761,9 @@ static void cm_add_one(struct ib_device *ib_device)
 	};
 	unsigned long flags;
 	int ret;
+	int count = 0;
 	u8 i;
 
-	if (rdma_node_get_transport(ib_device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	cm_dev = kzalloc(sizeof(*cm_dev) + sizeof(*port) *
 			 ib_device->phys_port_cnt, GFP_KERNEL);
 	if (!cm_dev)
@@ -3783,6 +3782,9 @@ static void cm_add_one(struct ib_device *ib_device)
 
 	set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask);
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = kzalloc(sizeof *port, GFP_KERNEL);
 		if (!port)
 			goto error1;
@@ -3809,7 +3811,13 @@ static void cm_add_one(struct ib_device *ib_device)
 		ret = ib_modify_port(ib_device, i, 0, &port_modify);
 		if (ret)
 			goto error3;
+
+		count++;
 	}
+
+	if (!count)
+		goto free;
+
 	ib_set_client_data(ib_device, &cm_client, cm_dev);
 
 	write_lock_irqsave(&cm.device_lock, flags);
@@ -3825,11 +3833,15 @@ error1:
 	port_modify.set_port_cap_mask = 0;
 	port_modify.clr_port_cap_mask = IB_PORT_CM_SUP;
 	while (--i) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		ib_unregister_mad_agent(port->mad_agent);
 		cm_remove_port_fs(port);
 	}
+free:
 	device_unregister(cm_dev->device);
 	kfree(cm_dev);
 }
@@ -3853,6 +3865,9 @@ static void cm_remove_one(struct ib_device *ib_device)
 	write_unlock_irqrestore(&cm.device_lock, flags);
 
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		ib_unregister_mad_agent(port->mad_agent);
diff --git a/drivers/infiniband/core/cm_msgs.h b/drivers/infiniband/core/cm_msgs.h
index be068f47e47e..8b76f0ef965e 100644
--- a/drivers/infiniband/core/cm_msgs.h
+++ b/drivers/infiniband/core/cm_msgs.h
@@ -103,7 +103,7 @@ struct cm_req_msg {
 	/* local ACK timeout:5, rsvd:3 */
 	u8 alt_offset139;
 
-	u8 private_data[IB_CM_REQ_PRIVATE_DATA_SIZE];
+	u32 private_data[IB_CM_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
 
 } __attribute__ ((packed));
 
@@ -801,7 +801,7 @@ struct cm_sidr_req_msg {
 	__be16 rsvd;
 	__be64 service_id;
 
-	u8 private_data[IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE];
+	u32 private_data[IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
 } __attribute__ ((packed));
 
 struct cm_sidr_rep_msg {
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index d570030d899c..143ded2bbe7c 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -65,6 +65,34 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
 
+static const char * const cma_events[] = {
+	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
+	[RDMA_CM_EVENT_ADDR_ERROR]	 = "address error",
+	[RDMA_CM_EVENT_ROUTE_RESOLVED]	 = "route resolved ",
+	[RDMA_CM_EVENT_ROUTE_ERROR]	 = "route error",
+	[RDMA_CM_EVENT_CONNECT_REQUEST]	 = "connect request",
+	[RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response",
+	[RDMA_CM_EVENT_CONNECT_ERROR]	 = "connect error",
+	[RDMA_CM_EVENT_UNREACHABLE]	 = "unreachable",
+	[RDMA_CM_EVENT_REJECTED]	 = "rejected",
+	[RDMA_CM_EVENT_ESTABLISHED]	 = "established",
+	[RDMA_CM_EVENT_DISCONNECTED]	 = "disconnected",
+	[RDMA_CM_EVENT_DEVICE_REMOVAL]	 = "device removal",
+	[RDMA_CM_EVENT_MULTICAST_JOIN]	 = "multicast join",
+	[RDMA_CM_EVENT_MULTICAST_ERROR]	 = "multicast error",
+	[RDMA_CM_EVENT_ADDR_CHANGE]	 = "address change",
+	[RDMA_CM_EVENT_TIMEWAIT_EXIT]	 = "timewait exit",
+};
+
+const char *rdma_event_msg(enum rdma_cm_event_type event)
+{
+	size_t index = event;
+
+	return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ?
+			cma_events[index] : "unrecognized event";
+}
+EXPORT_SYMBOL(rdma_event_msg);
+
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device);
 
@@ -349,18 +377,35 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
 	return ret;
 }
 
+static inline int cma_validate_port(struct ib_device *device, u8 port,
+				      union ib_gid *gid, int dev_type)
+{
+	u8 found_port;
+	int ret = -ENODEV;
+
+	if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port))
+		return ret;
+
+	if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port))
+		return ret;
+
+	ret = ib_find_cached_gid(device, gid, &found_port, NULL);
+	if (port != found_port)
+		return -ENODEV;
+
+	return ret;
+}
+
 static int cma_acquire_dev(struct rdma_id_private *id_priv,
 			   struct rdma_id_private *listen_id_priv)
 {
 	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
 	struct cma_device *cma_dev;
-	union ib_gid gid, iboe_gid;
+	union ib_gid gid, iboe_gid, *gidp;
 	int ret = -ENODEV;
-	u8 port, found_port;
-	enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ?
-		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
+	u8 port;
 
-	if (dev_ll != IB_LINK_LAYER_INFINIBAND &&
+	if (dev_addr->dev_type != ARPHRD_INFINIBAND &&
 	    id_priv->id.ps == RDMA_PS_IPOIB)
 		return -EINVAL;
 
@@ -370,41 +415,36 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
 
 	memcpy(&gid, dev_addr->src_dev_addr +
 	       rdma_addr_gid_offset(dev_addr), sizeof gid);
-	if (listen_id_priv &&
-	    rdma_port_get_link_layer(listen_id_priv->id.device,
-				     listen_id_priv->id.port_num) == dev_ll) {
+
+	if (listen_id_priv) {
 		cma_dev = listen_id_priv->cma_dev;
 		port = listen_id_priv->id.port_num;
-		if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&
-		    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)
-			ret = ib_find_cached_gid(cma_dev->device, &iboe_gid,
-						 &found_port, NULL);
-		else
-			ret = ib_find_cached_gid(cma_dev->device, &gid,
-						 &found_port, NULL);
+		gidp = rdma_protocol_roce(cma_dev->device, port) ?
+		       &iboe_gid : &gid;
 
-		if (!ret && (port  == found_port)) {
-			id_priv->id.port_num = found_port;
+		ret = cma_validate_port(cma_dev->device, port, gidp,
+					dev_addr->dev_type);
+		if (!ret) {
+			id_priv->id.port_num = port;
 			goto out;
 		}
 	}
+
 	list_for_each_entry(cma_dev, &dev_list, list) {
 		for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) {
 			if (listen_id_priv &&
 			    listen_id_priv->cma_dev == cma_dev &&
 			    listen_id_priv->id.port_num == port)
 				continue;
-			if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) {
-				if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&
-				    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)
-					ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, &found_port, NULL);
-				else
-					ret = ib_find_cached_gid(cma_dev->device, &gid, &found_port, NULL);
-
-				if (!ret && (port == found_port)) {
-					id_priv->id.port_num = found_port;
-					goto out;
-				}
+
+			gidp = rdma_protocol_roce(cma_dev->device, port) ?
+			       &iboe_gid : &gid;
+
+			ret = cma_validate_port(cma_dev->device, port, gidp,
+						dev_addr->dev_type);
+			if (!ret) {
+				id_priv->id.port_num = port;
+				goto out;
 			}
 		}
 	}
@@ -435,10 +475,10 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	pkey = ntohs(addr->sib_pkey);
 
 	list_for_each_entry(cur_dev, &dev_list, list) {
-		if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
-			continue;
-
 		for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
+			if (!rdma_cap_af_ib(cur_dev->device, p))
+				continue;
+
 			if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index))
 				continue;
 
@@ -633,10 +673,9 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	if (ret)
 		goto out;
 
-	if (rdma_node_get_transport(id_priv->cma_dev->device->node_type)
-	    == RDMA_TRANSPORT_IB &&
-	    rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
-	    == IB_LINK_LAYER_ETHERNET) {
+	BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
+
+	if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) {
 		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
 
 		if (ret)
@@ -700,11 +739,10 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
 	int ret;
 	u16 pkey;
 
-	if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) ==
-	    IB_LINK_LAYER_INFINIBAND)
-		pkey = ib_addr_get_pkey(dev_addr);
-	else
+	if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num))
 		pkey = 0xffff;
+	else
+		pkey = ib_addr_get_pkey(dev_addr);
 
 	ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num,
 				  pkey, &qp_attr->pkey_index);
@@ -735,8 +773,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 	int ret = 0;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
-	switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD))
 			ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask);
 		else
@@ -745,19 +782,15 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 
 		if (qp_attr->qp_state == IB_QPS_RTR)
 			qp_attr->rq_psn = id_priv->seq_num;
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		if (!id_priv->cm_id.iw) {
 			qp_attr->qp_access_flags = 0;
 			*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS;
 		} else
 			ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr,
 						 qp_attr_mask);
-		break;
-	default:
+	} else
 		ret = -ENOSYS;
-		break;
-	}
 
 	return ret;
 }
@@ -845,33 +878,49 @@ static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id
 	listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr;
 	ib = (struct sockaddr_ib *) &id->route.addr.src_addr;
 	ib->sib_family = listen_ib->sib_family;
-	ib->sib_pkey = path->pkey;
-	ib->sib_flowinfo = path->flow_label;
-	memcpy(&ib->sib_addr, &path->sgid, 16);
+	if (path) {
+		ib->sib_pkey = path->pkey;
+		ib->sib_flowinfo = path->flow_label;
+		memcpy(&ib->sib_addr, &path->sgid, 16);
+	} else {
+		ib->sib_pkey = listen_ib->sib_pkey;
+		ib->sib_flowinfo = listen_ib->sib_flowinfo;
+		ib->sib_addr = listen_ib->sib_addr;
+	}
 	ib->sib_sid = listen_ib->sib_sid;
 	ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL);
 	ib->sib_scope_id = listen_ib->sib_scope_id;
 
-	ib = (struct sockaddr_ib *) &id->route.addr.dst_addr;
-	ib->sib_family = listen_ib->sib_family;
-	ib->sib_pkey = path->pkey;
-	ib->sib_flowinfo = path->flow_label;
-	memcpy(&ib->sib_addr, &path->dgid, 16);
+	if (path) {
+		ib = (struct sockaddr_ib *) &id->route.addr.dst_addr;
+		ib->sib_family = listen_ib->sib_family;
+		ib->sib_pkey = path->pkey;
+		ib->sib_flowinfo = path->flow_label;
+		memcpy(&ib->sib_addr, &path->dgid, 16);
+	}
+}
+
+static __be16 ss_get_port(const struct sockaddr_storage *ss)
+{
+	if (ss->ss_family == AF_INET)
+		return ((struct sockaddr_in *)ss)->sin_port;
+	else if (ss->ss_family == AF_INET6)
+		return ((struct sockaddr_in6 *)ss)->sin6_port;
+	BUG();
 }
 
 static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
 			      struct cma_hdr *hdr)
 {
-	struct sockaddr_in *listen4, *ip4;
+	struct sockaddr_in *ip4;
 
-	listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr;
 	ip4 = (struct sockaddr_in *) &id->route.addr.src_addr;
-	ip4->sin_family = listen4->sin_family;
+	ip4->sin_family = AF_INET;
 	ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr;
-	ip4->sin_port = listen4->sin_port;
+	ip4->sin_port = ss_get_port(&listen_id->route.addr.src_addr);
 
 	ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr;
-	ip4->sin_family = listen4->sin_family;
+	ip4->sin_family = AF_INET;
 	ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr;
 	ip4->sin_port = hdr->port;
 }
@@ -879,16 +928,15 @@ static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_i
 static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id,
 			      struct cma_hdr *hdr)
 {
-	struct sockaddr_in6 *listen6, *ip6;
+	struct sockaddr_in6 *ip6;
 
-	listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr;
 	ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr;
-	ip6->sin6_family = listen6->sin6_family;
+	ip6->sin6_family = AF_INET6;
 	ip6->sin6_addr = hdr->dst_addr.ip6;
-	ip6->sin6_port = listen6->sin6_port;
+	ip6->sin6_port = ss_get_port(&listen_id->route.addr.src_addr);
 
 	ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr;
-	ip6->sin6_family = listen6->sin6_family;
+	ip6->sin6_family = AF_INET6;
 	ip6->sin6_addr = hdr->src_addr.ip6;
 	ip6->sin6_port = hdr->port;
 }
@@ -898,9 +946,11 @@ static int cma_save_net_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id
 {
 	struct cma_hdr *hdr;
 
-	if ((listen_id->route.addr.src_addr.ss_family == AF_IB) &&
-	    (ib_event->event == IB_CM_REQ_RECEIVED)) {
-		cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
+	if (listen_id->route.addr.src_addr.ss_family == AF_IB) {
+		if (ib_event->event == IB_CM_REQ_RECEIVED)
+			cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
+		else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED)
+			cma_save_ib_info(id, listen_id, NULL);
 		return 0;
 	}
 
@@ -928,13 +978,9 @@ static inline int cma_user_data_offset(struct rdma_id_private *id_priv)
 
 static void cma_cancel_route(struct rdma_id_private *id_priv)
 {
-	switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) {
-	case IB_LINK_LAYER_INFINIBAND:
+	if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) {
 		if (id_priv->query)
 			ib_sa_cancel_query(id_priv->query_id, id_priv->query);
-		break;
-	default:
-		break;
 	}
 }
 
@@ -1006,17 +1052,12 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv)
 		mc = container_of(id_priv->mc_list.next,
 				  struct cma_multicast, list);
 		list_del(&mc->list);
-		switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
+		if (rdma_cap_ib_mcast(id_priv->cma_dev->device,
+				      id_priv->id.port_num)) {
 			ib_sa_free_multicast(mc->multicast.ib);
 			kfree(mc);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
+		} else
 			kref_put(&mc->mcref, release_mc);
-			break;
-		default:
-			break;
-		}
 	}
 }
 
@@ -1037,17 +1078,12 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 	mutex_unlock(&id_priv->handler_mutex);
 
 	if (id_priv->cma_dev) {
-		switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
-		case RDMA_TRANSPORT_IB:
+		if (rdma_cap_ib_cm(id_priv->id.device, 1)) {
 			if (id_priv->cm_id.ib)
 				ib_destroy_cm_id(id_priv->cm_id.ib);
-			break;
-		case RDMA_TRANSPORT_IWARP:
+		} else if (rdma_cap_iw_cm(id_priv->id.device, 1)) {
 			if (id_priv->cm_id.iw)
 				iw_destroy_cm_id(id_priv->cm_id.iw);
-			break;
-		default:
-			break;
 		}
 		cma_leave_mc_groups(id_priv);
 		cma_release_dev(id_priv);
@@ -1593,6 +1629,7 @@ static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog)
 	if (IS_ERR(id))
 		return PTR_ERR(id);
 
+	id->tos = id_priv->tos;
 	id_priv->cm_id.iw = id;
 
 	memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv),
@@ -1625,8 +1662,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct rdma_cm_id *id;
 	int ret;
 
-	if (cma_family(id_priv) == AF_IB &&
-	    rdma_node_get_transport(cma_dev->device->node_type) != RDMA_TRANSPORT_IB)
+	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
 	id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
@@ -1967,26 +2003,15 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms)
 		return -EINVAL;
 
 	atomic_inc(&id_priv->refcount);
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ret = cma_resolve_ib_route(id_priv, timeout_ms);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			ret = cma_resolve_iboe_route(id_priv);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	if (rdma_cap_ib_sa(id->device, id->port_num))
+		ret = cma_resolve_ib_route(id_priv, timeout_ms);
+	else if (rdma_protocol_roce(id->device, id->port_num))
+		ret = cma_resolve_iboe_route(id_priv);
+	else if (rdma_protocol_iwarp(id->device, id->port_num))
 		ret = cma_resolve_iw_route(id_priv, timeout_ms);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
+
 	if (ret)
 		goto err;
 
@@ -2028,7 +2053,7 @@ static int cma_bind_loopback(struct rdma_id_private *id_priv)
 	mutex_lock(&lock);
 	list_for_each_entry(cur_dev, &dev_list, list) {
 		if (cma_family(id_priv) == AF_IB &&
-		    rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
+		    !rdma_cap_ib_cm(cur_dev->device, 1))
 			continue;
 
 		if (!cma_dev)
@@ -2060,7 +2085,7 @@ port_found:
 		goto out;
 
 	id_priv->id.route.addr.dev_addr.dev_type =
-		(rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ?
+		(rdma_protocol_ib(cma_dev->device, p)) ?
 		ARPHRD_INFINIBAND : ARPHRD_ETHER;
 
 	rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid);
@@ -2537,18 +2562,15 @@ int rdma_listen(struct rdma_cm_id *id, int backlog)
 
 	id_priv->backlog = backlog;
 	if (id->device) {
-		switch (rdma_node_get_transport(id->device->node_type)) {
-		case RDMA_TRANSPORT_IB:
+		if (rdma_cap_ib_cm(id->device, 1)) {
 			ret = cma_ib_listen(id_priv);
 			if (ret)
 				goto err;
-			break;
-		case RDMA_TRANSPORT_IWARP:
+		} else if (rdma_cap_iw_cm(id->device, 1)) {
 			ret = cma_iw_listen(id_priv, backlog);
 			if (ret)
 				goto err;
-			break;
-		default:
+		} else {
 			ret = -ENOSYS;
 			goto err;
 		}
@@ -2840,6 +2862,7 @@ static int cma_connect_iw(struct rdma_id_private *id_priv,
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 
+	cm_id->tos = id_priv->tos;
 	id_priv->cm_id.iw = cm_id;
 
 	memcpy(&cm_id->local_addr, cma_src_addr(id_priv),
@@ -2884,20 +2907,15 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 		id_priv->srq = conn_param->srq;
 	}
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD)
 			ret = cma_resolve_ib_udp(id_priv, conn_param);
 		else
 			ret = cma_connect_ib(id_priv, conn_param);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num))
 		ret = cma_connect_iw(id_priv, conn_param);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
 	if (ret)
 		goto err;
 
@@ -3000,8 +3018,7 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 		id_priv->srq = conn_param->srq;
 	}
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD) {
 			if (conn_param)
 				ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS,
@@ -3017,14 +3034,10 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 			else
 				ret = cma_rep_recv(id_priv);
 		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num))
 		ret = cma_accept_iw(id_priv, conn_param);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
 
 	if (ret)
 		goto reject;
@@ -3068,8 +3081,7 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 	if (!id_priv->cm_id.ib)
 		return -EINVAL;
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD)
 			ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0,
 						private_data, private_data_len);
@@ -3077,15 +3089,12 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 			ret = ib_send_cm_rej(id_priv->cm_id.ib,
 					     IB_CM_REJ_CONSUMER_DEFINED, NULL,
 					     0, private_data, private_data_len);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_reject(id_priv->cm_id.iw,
 				   private_data, private_data_len);
-		break;
-	default:
+	} else
 		ret = -ENOSYS;
-		break;
-	}
+
 	return ret;
 }
 EXPORT_SYMBOL(rdma_reject);
@@ -3099,22 +3108,18 @@ int rdma_disconnect(struct rdma_cm_id *id)
 	if (!id_priv->cm_id.ib)
 		return -EINVAL;
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		ret = cma_modify_qp_err(id_priv);
 		if (ret)
 			goto out;
 		/* Initiate or respond to a disconnect. */
 		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0))
 			ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
-		break;
-	default:
+	} else
 		ret = -EINVAL;
-		break;
-	}
+
 out:
 	return ret;
 }
@@ -3360,24 +3365,13 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
 	list_add(&mc->list, &id_priv->mc_list);
 	spin_unlock(&id_priv->lock);
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ret = cma_join_ib_multicast(id_priv, mc);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			kref_init(&mc->mcref);
-			ret = cma_iboe_join_multicast(id_priv, mc);
-			break;
-		default:
-			ret = -EINVAL;
-		}
-		break;
-	default:
+	if (rdma_protocol_roce(id->device, id->port_num)) {
+		kref_init(&mc->mcref);
+		ret = cma_iboe_join_multicast(id_priv, mc);
+	} else if (rdma_cap_ib_mcast(id->device, id->port_num))
+		ret = cma_join_ib_multicast(id_priv, mc);
+	else
 		ret = -ENOSYS;
-		break;
-	}
 
 	if (ret) {
 		spin_lock_irq(&id_priv->lock);
@@ -3405,19 +3399,15 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
 				ib_detach_mcast(id->qp,
 						&mc->multicast.ib->rec.mgid,
 						be16_to_cpu(mc->multicast.ib->rec.mlid));
-			if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) {
-				switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-				case IB_LINK_LAYER_INFINIBAND:
-					ib_sa_free_multicast(mc->multicast.ib);
-					kfree(mc);
-					break;
-				case IB_LINK_LAYER_ETHERNET:
-					kref_put(&mc->mcref, release_mc);
-					break;
-				default:
-					break;
-				}
-			}
+
+			BUG_ON(id_priv->cma_dev->device != id->device);
+
+			if (rdma_cap_ib_mcast(id->device, id->port_num)) {
+				ib_sa_free_multicast(mc->multicast.ib);
+				kfree(mc);
+			} else if (rdma_protocol_roce(id->device, id->port_num))
+				kref_put(&mc->mcref, release_mc);
+
 			return;
 		}
 	}
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 18c1ece765f2..9567756ca4f9 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -92,7 +92,8 @@ static int ib_device_check_mandatory(struct ib_device *device)
 		IB_MANDATORY_FUNC(poll_cq),
 		IB_MANDATORY_FUNC(req_notify_cq),
 		IB_MANDATORY_FUNC(get_dma_mr),
-		IB_MANDATORY_FUNC(dereg_mr)
+		IB_MANDATORY_FUNC(dereg_mr),
+		IB_MANDATORY_FUNC(get_port_immutable)
 	};
 	int i;
 
@@ -151,18 +152,6 @@ static int alloc_name(char *name)
 	return 0;
 }
 
-static int start_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
-}
-
-
-static int end_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
-		0 : device->phys_port_cnt;
-}
-
 /**
  * ib_alloc_device - allocate an IB device struct
  * @size:size of structure to allocate
@@ -222,42 +211,49 @@ static int add_client_context(struct ib_device *device, struct ib_client *client
 	return 0;
 }
 
-static int read_port_table_lengths(struct ib_device *device)
+static int verify_immutable(const struct ib_device *dev, u8 port)
 {
-	struct ib_port_attr *tprops = NULL;
-	int num_ports, ret = -ENOMEM;
-	u8 port_index;
-
-	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
-	if (!tprops)
-		goto out;
-
-	num_ports = end_port(device) - start_port(device) + 1;
+	return WARN_ON(!rdma_cap_ib_mad(dev, port) &&
+			    rdma_max_mad_size(dev, port) != 0);
+}
 
-	device->pkey_tbl_len = kmalloc(sizeof *device->pkey_tbl_len * num_ports,
-				       GFP_KERNEL);
-	device->gid_tbl_len = kmalloc(sizeof *device->gid_tbl_len * num_ports,
-				      GFP_KERNEL);
-	if (!device->pkey_tbl_len || !device->gid_tbl_len)
+static int read_port_immutable(struct ib_device *device)
+{
+	int ret = -ENOMEM;
+	u8 start_port = rdma_start_port(device);
+	u8 end_port = rdma_end_port(device);
+	u8 port;
+
+	/**
+	 * device->port_immutable is indexed directly by the port number to make
+	 * access to this data as efficient as possible.
+	 *
+	 * Therefore port_immutable is declared as a 1 based array with
+	 * potential empty slots at the beginning.
+	 */
+	device->port_immutable = kzalloc(sizeof(*device->port_immutable)
+					 * (end_port + 1),
+					 GFP_KERNEL);
+	if (!device->port_immutable)
 		goto err;
 
-	for (port_index = 0; port_index < num_ports; ++port_index) {
-		ret = ib_query_port(device, port_index + start_port(device),
-					tprops);
+	for (port = start_port; port <= end_port; ++port) {
+		ret = device->get_port_immutable(device, port,
+						 &device->port_immutable[port]);
 		if (ret)
 			goto err;
-		device->pkey_tbl_len[port_index] = tprops->pkey_tbl_len;
-		device->gid_tbl_len[port_index]  = tprops->gid_tbl_len;
+
+		if (verify_immutable(device, port)) {
+			ret = -EINVAL;
+			goto err;
+		}
 	}
 
 	ret = 0;
 	goto out;
-
 err:
-	kfree(device->gid_tbl_len);
-	kfree(device->pkey_tbl_len);
+	kfree(device->port_immutable);
 out:
-	kfree(tprops);
 	return ret;
 }
 
@@ -294,9 +290,9 @@ int ib_register_device(struct ib_device *device,
 	spin_lock_init(&device->event_handler_lock);
 	spin_lock_init(&device->client_data_lock);
 
-	ret = read_port_table_lengths(device);
+	ret = read_port_immutable(device);
 	if (ret) {
-		printk(KERN_WARNING "Couldn't create table lengths cache for device %s\n",
+		printk(KERN_WARNING "Couldn't create per port immutable data %s\n",
 		       device->name);
 		goto out;
 	}
@@ -305,8 +301,7 @@ int ib_register_device(struct ib_device *device,
 	if (ret) {
 		printk(KERN_WARNING "Couldn't register device %s with driver model\n",
 		       device->name);
-		kfree(device->gid_tbl_len);
-		kfree(device->pkey_tbl_len);
+		kfree(device->port_immutable);
 		goto out;
 	}
 
@@ -348,9 +343,6 @@ void ib_unregister_device(struct ib_device *device)
 
 	list_del(&device->core_list);
 
-	kfree(device->gid_tbl_len);
-	kfree(device->pkey_tbl_len);
-
 	mutex_unlock(&device_mutex);
 
 	ib_device_unregister_sysfs(device);
@@ -558,7 +550,11 @@ EXPORT_SYMBOL(ib_dispatch_event);
 int ib_query_device(struct ib_device *device,
 		    struct ib_device_attr *device_attr)
 {
-	return device->query_device(device, device_attr);
+	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
+
+	memset(device_attr, 0, sizeof(*device_attr));
+
+	return device->query_device(device, device_attr, &uhw);
 }
 EXPORT_SYMBOL(ib_query_device);
 
@@ -575,7 +571,7 @@ int ib_query_port(struct ib_device *device,
 		  u8 port_num,
 		  struct ib_port_attr *port_attr)
 {
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	return device->query_port(device, port_num, port_attr);
@@ -653,7 +649,7 @@ int ib_modify_port(struct ib_device *device,
 	if (!device->modify_port)
 		return -ENOSYS;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	return device->modify_port(device, port_num, port_modify_mask,
@@ -676,8 +672,8 @@ int ib_find_gid(struct ib_device *device, union ib_gid *gid,
 	union ib_gid tmp_gid;
 	int ret, port, i;
 
-	for (port = start_port(device); port <= end_port(device); ++port) {
-		for (i = 0; i < device->gid_tbl_len[port - start_port(device)]; ++i) {
+	for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) {
+		for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) {
 			ret = ib_query_gid(device, port, i, &tmp_gid);
 			if (ret)
 				return ret;
@@ -709,7 +705,7 @@ int ib_find_pkey(struct ib_device *device,
 	u16 tmp_pkey;
 	int partial_ix = -1;
 
-	for (i = 0; i < device->pkey_tbl_len[port_num - start_port(device)]; ++i) {
+	for (i = 0; i < device->port_immutable[port_num].pkey_tbl_len; ++i) {
 		ret = ib_query_pkey(device, port_num, i, &tmp_pkey);
 		if (ret)
 			return ret;
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index b85ddbc979e0..e6ffa2e66c1a 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -33,7 +33,7 @@
 
 #include "iwpm_util.h"
 
-static const char iwpm_ulib_name[] = "iWarpPortMapperUser";
+static const char iwpm_ulib_name[IWPM_ULIBNAME_SIZE] = "iWarpPortMapperUser";
 static int iwpm_ulib_version = 3;
 static int iwpm_user_pid = IWPM_PID_UNDEFINED;
 static atomic_t echo_nlmsg_seq;
@@ -468,7 +468,8 @@ add_mapping_response_exit:
 }
 EXPORT_SYMBOL(iwpm_add_mapping_cb);
 
-/* netlink attribute policy for the response to add and query mapping request */
+/* netlink attribute policy for the response to add and query mapping request
+ * and response with remote address info */
 static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = {
 	[IWPM_NLA_QUERY_MAPPING_SEQ]      = { .type = NLA_U32 },
 	[IWPM_NLA_QUERY_LOCAL_ADDR]       = { .len = sizeof(struct sockaddr_storage) },
@@ -559,6 +560,76 @@ query_mapping_response_exit:
 }
 EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
 
+/*
+ * iwpm_remote_info_cb - Process a port mapper message, containing
+ *			  the remote connecting peer address info
+ */
+int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX];
+	struct sockaddr_storage *local_sockaddr, *remote_sockaddr;
+	struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr;
+	struct iwpm_remote_info *rem_info;
+	const char *msg_type;
+	u8 nl_client;
+	int ret = -EINVAL;
+
+	msg_type = "Remote Mapping info";
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX,
+				resp_query_policy, nltb, msg_type))
+		return ret;
+
+	nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type);
+	if (!iwpm_valid_client(nl_client)) {
+		pr_info("%s: Invalid port mapper client = %d\n",
+				__func__, nl_client);
+		return ret;
+	}
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+
+	local_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_QUERY_LOCAL_ADDR]);
+	remote_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_QUERY_REMOTE_ADDR]);
+	mapped_loc_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]);
+	mapped_rem_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]);
+
+	if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family ||
+		mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) {
+		pr_info("%s: Sockaddr family doesn't match the requested one\n",
+				__func__);
+		return ret;
+	}
+	rem_info = kzalloc(sizeof(struct iwpm_remote_info), GFP_ATOMIC);
+	if (!rem_info) {
+		pr_err("%s: Unable to allocate a remote info\n", __func__);
+		ret = -ENOMEM;
+		return ret;
+	}
+	memcpy(&rem_info->mapped_loc_sockaddr, mapped_loc_sockaddr,
+	       sizeof(struct sockaddr_storage));
+	memcpy(&rem_info->remote_sockaddr, remote_sockaddr,
+	       sizeof(struct sockaddr_storage));
+	memcpy(&rem_info->mapped_rem_sockaddr, mapped_rem_sockaddr,
+	       sizeof(struct sockaddr_storage));
+	rem_info->nl_client = nl_client;
+
+	iwpm_add_remote_info(rem_info);
+
+	iwpm_print_sockaddr(local_sockaddr,
+			"remote_info: Local sockaddr:");
+	iwpm_print_sockaddr(mapped_loc_sockaddr,
+			"remote_info: Mapped local sockaddr:");
+	iwpm_print_sockaddr(remote_sockaddr,
+			"remote_info: Remote sockaddr:");
+	iwpm_print_sockaddr(mapped_rem_sockaddr,
+			"remote_info: Mapped remote sockaddr:");
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_remote_info_cb);
+
 /* netlink attribute policy for the received request for mapping info */
 static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {
 	[IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING,
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 69e9f84c1605..a626795bf9c7 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -33,8 +33,10 @@
 
 #include "iwpm_util.h"
 
-#define IWPM_HASH_BUCKET_SIZE	512
-#define IWPM_HASH_BUCKET_MASK	(IWPM_HASH_BUCKET_SIZE - 1)
+#define IWPM_MAPINFO_HASH_SIZE	512
+#define IWPM_MAPINFO_HASH_MASK	(IWPM_MAPINFO_HASH_SIZE - 1)
+#define IWPM_REMINFO_HASH_SIZE	64
+#define IWPM_REMINFO_HASH_MASK	(IWPM_REMINFO_HASH_SIZE - 1)
 
 static LIST_HEAD(iwpm_nlmsg_req_list);
 static DEFINE_SPINLOCK(iwpm_nlmsg_req_lock);
@@ -42,31 +44,49 @@ static DEFINE_SPINLOCK(iwpm_nlmsg_req_lock);
 static struct hlist_head *iwpm_hash_bucket;
 static DEFINE_SPINLOCK(iwpm_mapinfo_lock);
 
+static struct hlist_head *iwpm_reminfo_bucket;
+static DEFINE_SPINLOCK(iwpm_reminfo_lock);
+
 static DEFINE_MUTEX(iwpm_admin_lock);
 static struct iwpm_admin_data iwpm_admin;
 
 int iwpm_init(u8 nl_client)
 {
+	int ret = 0;
 	if (iwpm_valid_client(nl_client))
 		return -EINVAL;
 	mutex_lock(&iwpm_admin_lock);
 	if (atomic_read(&iwpm_admin.refcount) == 0) {
-		iwpm_hash_bucket = kzalloc(IWPM_HASH_BUCKET_SIZE *
+		iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE *
 					sizeof(struct hlist_head), GFP_KERNEL);
 		if (!iwpm_hash_bucket) {
-			mutex_unlock(&iwpm_admin_lock);
+			ret = -ENOMEM;
 			pr_err("%s Unable to create mapinfo hash table\n", __func__);
-			return -ENOMEM;
+			goto init_exit;
+		}
+		iwpm_reminfo_bucket = kzalloc(IWPM_REMINFO_HASH_SIZE *
+					sizeof(struct hlist_head), GFP_KERNEL);
+		if (!iwpm_reminfo_bucket) {
+			kfree(iwpm_hash_bucket);
+			ret = -ENOMEM;
+			pr_err("%s Unable to create reminfo hash table\n", __func__);
+			goto init_exit;
 		}
 	}
 	atomic_inc(&iwpm_admin.refcount);
+init_exit:
 	mutex_unlock(&iwpm_admin_lock);
-	iwpm_set_valid(nl_client, 1);
-	return 0;
+	if (!ret) {
+		iwpm_set_valid(nl_client, 1);
+		pr_debug("%s: Mapinfo and reminfo tables are created\n",
+				__func__);
+	}
+	return ret;
 }
 EXPORT_SYMBOL(iwpm_init);
 
 static void free_hash_bucket(void);
+static void free_reminfo_bucket(void);
 
 int iwpm_exit(u8 nl_client)
 {
@@ -81,7 +101,8 @@ int iwpm_exit(u8 nl_client)
 	}
 	if (atomic_dec_and_test(&iwpm_admin.refcount)) {
 		free_hash_bucket();
-		pr_debug("%s: Mapinfo hash table is destroyed\n", __func__);
+		free_reminfo_bucket();
+		pr_debug("%s: Resources are destroyed\n", __func__);
 	}
 	mutex_unlock(&iwpm_admin_lock);
 	iwpm_set_valid(nl_client, 0);
@@ -89,7 +110,7 @@ int iwpm_exit(u8 nl_client)
 }
 EXPORT_SYMBOL(iwpm_exit);
 
-static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage *,
+static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *,
 					       struct sockaddr_storage *);
 
 int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
@@ -99,9 +120,10 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 	struct hlist_head *hash_bucket_head;
 	struct iwpm_mapping_info *map_info;
 	unsigned long flags;
+	int ret = -EINVAL;
 
 	if (!iwpm_valid_client(nl_client))
-		return -EINVAL;
+		return ret;
 	map_info = kzalloc(sizeof(struct iwpm_mapping_info), GFP_KERNEL);
 	if (!map_info) {
 		pr_err("%s: Unable to allocate a mapping info\n", __func__);
@@ -115,13 +137,16 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 
 	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
 	if (iwpm_hash_bucket) {
-		hash_bucket_head = get_hash_bucket_head(
+		hash_bucket_head = get_mapinfo_hash_bucket(
 					&map_info->local_sockaddr,
 					&map_info->mapped_sockaddr);
-		hlist_add_head(&map_info->hlist_node, hash_bucket_head);
+		if (hash_bucket_head) {
+			hlist_add_head(&map_info->hlist_node, hash_bucket_head);
+			ret = 0;
+		}
 	}
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(iwpm_create_mapinfo);
 
@@ -136,9 +161,12 @@ int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 
 	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
 	if (iwpm_hash_bucket) {
-		hash_bucket_head = get_hash_bucket_head(
+		hash_bucket_head = get_mapinfo_hash_bucket(
 					local_sockaddr,
 					mapped_local_addr);
+		if (!hash_bucket_head)
+			goto remove_mapinfo_exit;
+
 		hlist_for_each_entry_safe(map_info, tmp_hlist_node,
 					hash_bucket_head, hlist_node) {
 
@@ -152,6 +180,7 @@ int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 			}
 		}
 	}
+remove_mapinfo_exit:
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
@@ -166,7 +195,7 @@ static void free_hash_bucket(void)
 
 	/* remove all the mapinfo data from the list */
 	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
-	for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+	for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
 		hlist_for_each_entry_safe(map_info, tmp_hlist_node,
 			&iwpm_hash_bucket[i], hlist_node) {
 
@@ -180,6 +209,96 @@ static void free_hash_bucket(void)
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 }
 
+static void free_reminfo_bucket(void)
+{
+	struct hlist_node *tmp_hlist_node;
+	struct iwpm_remote_info *rem_info;
+	unsigned long flags;
+	int i;
+
+	/* remove all the remote info from the list */
+	spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+	for (i = 0; i < IWPM_REMINFO_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(rem_info, tmp_hlist_node,
+			&iwpm_reminfo_bucket[i], hlist_node) {
+
+				hlist_del_init(&rem_info->hlist_node);
+				kfree(rem_info);
+			}
+	}
+	/* free the hash list */
+	kfree(iwpm_reminfo_bucket);
+	iwpm_reminfo_bucket = NULL;
+	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+}
+
+static struct hlist_head *get_reminfo_hash_bucket(struct sockaddr_storage *,
+						struct sockaddr_storage *);
+
+void iwpm_add_remote_info(struct iwpm_remote_info *rem_info)
+{
+	struct hlist_head *hash_bucket_head;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+	if (iwpm_reminfo_bucket) {
+		hash_bucket_head = get_reminfo_hash_bucket(
+					&rem_info->mapped_loc_sockaddr,
+					&rem_info->mapped_rem_sockaddr);
+		if (hash_bucket_head)
+			hlist_add_head(&rem_info->hlist_node, hash_bucket_head);
+	}
+	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+}
+
+int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr,
+				struct sockaddr_storage *mapped_rem_addr,
+				struct sockaddr_storage *remote_addr,
+				u8 nl_client)
+{
+	struct hlist_node *tmp_hlist_node;
+	struct hlist_head *hash_bucket_head;
+	struct iwpm_remote_info *rem_info = NULL;
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	if (!iwpm_valid_client(nl_client)) {
+		pr_info("%s: Invalid client = %d\n", __func__, nl_client);
+		return ret;
+	}
+	spin_lock_irqsave(&iwpm_reminfo_lock, flags);
+	if (iwpm_reminfo_bucket) {
+		hash_bucket_head = get_reminfo_hash_bucket(
+					mapped_loc_addr,
+					mapped_rem_addr);
+		if (!hash_bucket_head)
+			goto get_remote_info_exit;
+		hlist_for_each_entry_safe(rem_info, tmp_hlist_node,
+					hash_bucket_head, hlist_node) {
+
+			if (!iwpm_compare_sockaddr(&rem_info->mapped_loc_sockaddr,
+				mapped_loc_addr) &&
+				!iwpm_compare_sockaddr(&rem_info->mapped_rem_sockaddr,
+				mapped_rem_addr)) {
+
+				memcpy(remote_addr, &rem_info->remote_sockaddr,
+					sizeof(struct sockaddr_storage));
+				iwpm_print_sockaddr(remote_addr,
+						"get_remote_info: Remote sockaddr:");
+
+				hlist_del_init(&rem_info->hlist_node);
+				kfree(rem_info);
+				ret = 0;
+				break;
+			}
+		}
+	}
+get_remote_info_exit:
+	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_get_remote_info);
+
 struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 					u8 nl_client, gfp_t gfp)
 {
@@ -409,31 +528,54 @@ static u32 iwpm_ipv4_jhash(struct sockaddr_in *ipv4_sockaddr)
 	return hash;
 }
 
-static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage
-					       *local_sockaddr,
-					       struct sockaddr_storage
-					       *mapped_sockaddr)
+static int get_hash_bucket(struct sockaddr_storage *a_sockaddr,
+				struct sockaddr_storage *b_sockaddr, u32 *hash)
 {
-	u32 local_hash, mapped_hash, hash;
+	u32 a_hash, b_hash;
 
-	if (local_sockaddr->ss_family == AF_INET) {
-		local_hash = iwpm_ipv4_jhash((struct sockaddr_in *) local_sockaddr);
-		mapped_hash = iwpm_ipv4_jhash((struct sockaddr_in *) mapped_sockaddr);
+	if (a_sockaddr->ss_family == AF_INET) {
+		a_hash = iwpm_ipv4_jhash((struct sockaddr_in *) a_sockaddr);
+		b_hash = iwpm_ipv4_jhash((struct sockaddr_in *) b_sockaddr);
 
-	} else if (local_sockaddr->ss_family == AF_INET6) {
-		local_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) local_sockaddr);
-		mapped_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) mapped_sockaddr);
+	} else if (a_sockaddr->ss_family == AF_INET6) {
+		a_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) a_sockaddr);
+		b_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) b_sockaddr);
 	} else {
 		pr_err("%s: Invalid sockaddr family\n", __func__);
-		return NULL;
+		return -EINVAL;
 	}
 
-	if (local_hash == mapped_hash) /* if port mapper isn't available */
-		hash = local_hash;
+	if (a_hash == b_hash) /* if port mapper isn't available */
+		*hash = a_hash;
 	else
-		hash = jhash_2words(local_hash, mapped_hash, 0);
+		*hash = jhash_2words(a_hash, b_hash, 0);
+	return 0;
+}
+
+static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage
+				*local_sockaddr, struct sockaddr_storage
+				*mapped_sockaddr)
+{
+	u32 hash;
+	int ret;
 
-	return &iwpm_hash_bucket[hash & IWPM_HASH_BUCKET_MASK];
+	ret = get_hash_bucket(local_sockaddr, mapped_sockaddr, &hash);
+	if (ret)
+		return NULL;
+	return &iwpm_hash_bucket[hash & IWPM_MAPINFO_HASH_MASK];
+}
+
+static struct hlist_head *get_reminfo_hash_bucket(struct sockaddr_storage
+				*mapped_loc_sockaddr, struct sockaddr_storage
+				*mapped_rem_sockaddr)
+{
+	u32 hash;
+	int ret;
+
+	ret = get_hash_bucket(mapped_loc_sockaddr, mapped_rem_sockaddr, &hash);
+	if (ret)
+		return NULL;
+	return &iwpm_reminfo_bucket[hash & IWPM_REMINFO_HASH_MASK];
 }
 
 static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
@@ -512,7 +654,7 @@ int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid)
 	}
 	skb_num++;
 	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
-	for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+	for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
 		hlist_for_each_entry(map_info, &iwpm_hash_bucket[i],
 				     hlist_node) {
 			if (map_info->nl_client != nl_client)
@@ -595,7 +737,7 @@ int iwpm_mapinfo_available(void)
 
 	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
 	if (iwpm_hash_bucket) {
-		for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+		for (i = 0; i < IWPM_MAPINFO_HASH_SIZE; i++) {
 			if (!hlist_empty(&iwpm_hash_bucket[i])) {
 				full_bucket = 1;
 				break;
diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h
index 9777c869a140..ee2d9ff095be 100644
--- a/drivers/infiniband/core/iwpm_util.h
+++ b/drivers/infiniband/core/iwpm_util.h
@@ -76,6 +76,14 @@ struct iwpm_mapping_info {
 	u8     nl_client;
 };
 
+struct iwpm_remote_info {
+	struct hlist_node hlist_node;
+	struct sockaddr_storage remote_sockaddr;
+	struct sockaddr_storage mapped_loc_sockaddr;
+	struct sockaddr_storage mapped_rem_sockaddr;
+	u8     nl_client;
+};
+
 struct iwpm_admin_data {
 	atomic_t refcount;
 	atomic_t nlmsg_seq;
@@ -128,6 +136,13 @@ int iwpm_wait_complete_req(struct iwpm_nlmsg_request *nlmsg_request);
 int iwpm_get_nlmsg_seq(void);
 
 /**
+ * iwpm_add_reminfo - Add remote address info of the connecting peer
+ *                    to the remote info hash table
+ * @reminfo: The remote info to be added
+ */
+void iwpm_add_remote_info(struct iwpm_remote_info *reminfo);
+
+/**
  * iwpm_valid_client - Check if the port mapper client is valid
  * @nl_client: The index of the netlink client
  *
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 74c30f4c557e..a4b1466c1bf6 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2005 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Mellanox Technologies Ltd.  All rights reserved.
  * Copyright (c) 2009 HNR Consulting. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -44,6 +45,7 @@
 #include "mad_priv.h"
 #include "mad_rmpp.h"
 #include "smi.h"
+#include "opa_smi.h"
 #include "agent.h"
 
 MODULE_LICENSE("Dual BSD/GPL");
@@ -59,8 +61,6 @@ MODULE_PARM_DESC(send_queue_size, "Size of send queue in number of work requests
 module_param_named(recv_queue_size, mad_recvq_size, int, 0444);
 MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
 
-static struct kmem_cache *ib_mad_cache;
-
 static struct list_head ib_mad_port_list;
 static u32 ib_mad_client_id = 0;
 
@@ -73,7 +73,7 @@ static int method_in_use(struct ib_mad_mgmt_method_table **method,
 static void remove_mad_reg_req(struct ib_mad_agent_private *priv);
 static struct ib_mad_agent_private *find_mad_agent(
 					struct ib_mad_port_private *port_priv,
-					struct ib_mad *mad);
+					const struct ib_mad_hdr *mad);
 static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				    struct ib_mad_private *mad);
 static void cancel_mads(struct ib_mad_agent_private *mad_agent_priv);
@@ -179,12 +179,12 @@ static int is_vendor_method_in_use(
 	return 0;
 }
 
-int ib_response_mad(struct ib_mad *mad)
+int ib_response_mad(const struct ib_mad_hdr *hdr)
 {
-	return ((mad->mad_hdr.method & IB_MGMT_METHOD_RESP) ||
-		(mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS) ||
-		((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_BM) &&
-		 (mad->mad_hdr.attr_mod & IB_BM_ATTR_MOD_RESP)));
+	return ((hdr->method & IB_MGMT_METHOD_RESP) ||
+		(hdr->method == IB_MGMT_METHOD_TRAP_REPRESS) ||
+		((hdr->mgmt_class == IB_MGMT_CLASS_BM) &&
+		 (hdr->attr_mod & IB_BM_ATTR_MOD_RESP)));
 }
 EXPORT_SYMBOL(ib_response_mad);
 
@@ -717,6 +717,32 @@ static void build_smp_wc(struct ib_qp *qp,
 	wc->port_num = port_num;
 }
 
+static size_t mad_priv_size(const struct ib_mad_private *mp)
+{
+	return sizeof(struct ib_mad_private) + mp->mad_size;
+}
+
+static struct ib_mad_private *alloc_mad_private(size_t mad_size, gfp_t flags)
+{
+	size_t size = sizeof(struct ib_mad_private) + mad_size;
+	struct ib_mad_private *ret = kzalloc(size, flags);
+
+	if (ret)
+		ret->mad_size = mad_size;
+
+	return ret;
+}
+
+static size_t port_mad_size(const struct ib_mad_port_private *port_priv)
+{
+	return rdma_max_mad_size(port_priv->device, port_priv->port_num);
+}
+
+static size_t mad_priv_dma_size(const struct ib_mad_private *mp)
+{
+	return sizeof(struct ib_grh) + mp->mad_size;
+}
+
 /*
  * Return 0 if SMP is to be sent
  * Return 1 if SMP was consumed locally (whether or not solicited)
@@ -727,6 +753,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 {
 	int ret = 0;
 	struct ib_smp *smp = mad_send_wr->send_buf.mad;
+	struct opa_smp *opa_smp = (struct opa_smp *)smp;
 	unsigned long flags;
 	struct ib_mad_local_private *local;
 	struct ib_mad_private *mad_priv;
@@ -736,6 +763,11 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	u8 port_num;
 	struct ib_wc mad_wc;
 	struct ib_send_wr *send_wr = &mad_send_wr->send_wr;
+	size_t mad_size = port_mad_size(mad_agent_priv->qp_info->port_priv);
+	u16 out_mad_pkey_index = 0;
+	u16 drslid;
+	bool opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
+				    mad_agent_priv->qp_info->port_priv->port_num);
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
@@ -749,19 +781,48 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	 * If we are at the start of the LID routed part, don't update the
 	 * hop_ptr or hop_cnt.  See section 14.2.2, Vol 1 IB spec.
 	 */
-	if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
-	     IB_LID_PERMISSIVE &&
-	     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
-	     IB_SMI_DISCARD) {
-		ret = -EINVAL;
-		dev_err(&device->dev, "Invalid directed route\n");
-		goto out;
-	}
+	if (opa && smp->class_version == OPA_SMP_CLASS_VERSION) {
+		u32 opa_drslid;
+
+		if ((opa_get_smp_direction(opa_smp)
+		     ? opa_smp->route.dr.dr_dlid : opa_smp->route.dr.dr_slid) ==
+		     OPA_LID_PERMISSIVE &&
+		     opa_smi_handle_dr_smp_send(opa_smp, device->node_type,
+						port_num) == IB_SMI_DISCARD) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "OPA Invalid directed route\n");
+			goto out;
+		}
+		opa_drslid = be32_to_cpu(opa_smp->route.dr.dr_slid);
+		if (opa_drslid != OPA_LID_PERMISSIVE &&
+		    opa_drslid & 0xffff0000) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "OPA Invalid dr_slid 0x%x\n",
+			       opa_drslid);
+			goto out;
+		}
+		drslid = (u16)(opa_drslid & 0x0000ffff);
 
-	/* Check to post send on QP or process locally */
-	if (smi_check_local_smp(smp, device) == IB_SMI_DISCARD &&
-	    smi_check_local_returning_smp(smp, device) == IB_SMI_DISCARD)
-		goto out;
+		/* Check to post send on QP or process locally */
+		if (opa_smi_check_local_smp(opa_smp, device) == IB_SMI_DISCARD &&
+		    opa_smi_check_local_returning_smp(opa_smp, device) == IB_SMI_DISCARD)
+			goto out;
+	} else {
+		if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
+		     IB_LID_PERMISSIVE &&
+		     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
+		     IB_SMI_DISCARD) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "Invalid directed route\n");
+			goto out;
+		}
+		drslid = be16_to_cpu(smp->dr_slid);
+
+		/* Check to post send on QP or process locally */
+		if (smi_check_local_smp(smp, device) == IB_SMI_DISCARD &&
+		    smi_check_local_returning_smp(smp, device) == IB_SMI_DISCARD)
+			goto out;
+	}
 
 	local = kmalloc(sizeof *local, GFP_ATOMIC);
 	if (!local) {
@@ -771,7 +832,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	}
 	local->mad_priv = NULL;
 	local->recv_mad_agent = NULL;
-	mad_priv = kmem_cache_alloc(ib_mad_cache, GFP_ATOMIC);
+	mad_priv = alloc_mad_private(mad_size, GFP_ATOMIC);
 	if (!mad_priv) {
 		ret = -ENOMEM;
 		dev_err(&device->dev, "No memory for local response MAD\n");
@@ -780,18 +841,25 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	}
 
 	build_smp_wc(mad_agent_priv->agent.qp,
-		     send_wr->wr_id, be16_to_cpu(smp->dr_slid),
+		     send_wr->wr_id, drslid,
 		     send_wr->wr.ud.pkey_index,
 		     send_wr->wr.ud.port_num, &mad_wc);
 
+	if (opa && smp->base_version == OPA_MGMT_BASE_VERSION) {
+		mad_wc.byte_len = mad_send_wr->send_buf.hdr_len
+					+ mad_send_wr->send_buf.data_len
+					+ sizeof(struct ib_grh);
+	}
+
 	/* No GRH for DR SMP */
 	ret = device->process_mad(device, 0, port_num, &mad_wc, NULL,
-				  (struct ib_mad *)smp,
-				  (struct ib_mad *)&mad_priv->mad);
+				  (const struct ib_mad_hdr *)smp, mad_size,
+				  (struct ib_mad_hdr *)mad_priv->mad,
+				  &mad_size, &out_mad_pkey_index);
 	switch (ret)
 	{
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY:
-		if (ib_response_mad(&mad_priv->mad.mad) &&
+		if (ib_response_mad((const struct ib_mad_hdr *)mad_priv->mad) &&
 		    mad_agent_priv->agent.recv_handler) {
 			local->mad_priv = mad_priv;
 			local->recv_mad_agent = mad_agent_priv;
@@ -801,39 +869,43 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 			 */
 			atomic_inc(&mad_agent_priv->refcount);
 		} else
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 		break;
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED:
-		kmem_cache_free(ib_mad_cache, mad_priv);
+		kfree(mad_priv);
 		break;
 	case IB_MAD_RESULT_SUCCESS:
 		/* Treat like an incoming receive MAD */
 		port_priv = ib_get_mad_port(mad_agent_priv->agent.device,
 					    mad_agent_priv->agent.port_num);
 		if (port_priv) {
-			memcpy(&mad_priv->mad.mad, smp, sizeof(struct ib_mad));
+			memcpy(mad_priv->mad, smp, mad_priv->mad_size);
 			recv_mad_agent = find_mad_agent(port_priv,
-						        &mad_priv->mad.mad);
+						        (const struct ib_mad_hdr *)mad_priv->mad);
 		}
 		if (!port_priv || !recv_mad_agent) {
 			/*
 			 * No receiving agent so drop packet and
 			 * generate send completion.
 			 */
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 			break;
 		}
 		local->mad_priv = mad_priv;
 		local->recv_mad_agent = recv_mad_agent;
 		break;
 	default:
-		kmem_cache_free(ib_mad_cache, mad_priv);
+		kfree(mad_priv);
 		kfree(local);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	local->mad_send_wr = mad_send_wr;
+	if (opa) {
+		local->mad_send_wr->send_wr.wr.ud.pkey_index = out_mad_pkey_index;
+		local->return_wc_byte_len = mad_size;
+	}
 	/* Reference MAD agent until send side of local completion handled */
 	atomic_inc(&mad_agent_priv->refcount);
 	/* Queue local completion to local list */
@@ -847,11 +919,11 @@ out:
 	return ret;
 }
 
-static int get_pad_size(int hdr_len, int data_len)
+static int get_pad_size(int hdr_len, int data_len, size_t mad_size)
 {
 	int seg_size, pad;
 
-	seg_size = sizeof(struct ib_mad) - hdr_len;
+	seg_size = mad_size - hdr_len;
 	if (data_len && seg_size) {
 		pad = seg_size - data_len % seg_size;
 		return pad == seg_size ? 0 : pad;
@@ -870,14 +942,15 @@ static void free_send_rmpp_list(struct ib_mad_send_wr_private *mad_send_wr)
 }
 
 static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
-				gfp_t gfp_mask)
+				size_t mad_size, gfp_t gfp_mask)
 {
 	struct ib_mad_send_buf *send_buf = &send_wr->send_buf;
 	struct ib_rmpp_mad *rmpp_mad = send_buf->mad;
 	struct ib_rmpp_segment *seg = NULL;
 	int left, seg_size, pad;
 
-	send_buf->seg_size = sizeof (struct ib_mad) - send_buf->hdr_len;
+	send_buf->seg_size = mad_size - send_buf->hdr_len;
+	send_buf->seg_rmpp_size = mad_size - IB_MGMT_RMPP_HDR;
 	seg_size = send_buf->seg_size;
 	pad = send_wr->pad;
 
@@ -910,7 +983,7 @@ static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
 	return 0;
 }
 
-int ib_mad_kernel_rmpp_agent(struct ib_mad_agent *agent)
+int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent)
 {
 	return agent->rmpp_version && !(agent->flags & IB_MAD_USER_RMPP);
 }
@@ -920,26 +993,37 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 					    u32 remote_qpn, u16 pkey_index,
 					    int rmpp_active,
 					    int hdr_len, int data_len,
-					    gfp_t gfp_mask)
+					    gfp_t gfp_mask,
+					    u8 base_version)
 {
 	struct ib_mad_agent_private *mad_agent_priv;
 	struct ib_mad_send_wr_private *mad_send_wr;
 	int pad, message_size, ret, size;
 	void *buf;
+	size_t mad_size;
+	bool opa;
 
 	mad_agent_priv = container_of(mad_agent, struct ib_mad_agent_private,
 				      agent);
-	pad = get_pad_size(hdr_len, data_len);
+
+	opa = rdma_cap_opa_mad(mad_agent->device, mad_agent->port_num);
+
+	if (opa && base_version == OPA_MGMT_BASE_VERSION)
+		mad_size = sizeof(struct opa_mad);
+	else
+		mad_size = sizeof(struct ib_mad);
+
+	pad = get_pad_size(hdr_len, data_len, mad_size);
 	message_size = hdr_len + data_len + pad;
 
 	if (ib_mad_kernel_rmpp_agent(mad_agent)) {
-		if (!rmpp_active && message_size > sizeof(struct ib_mad))
+		if (!rmpp_active && message_size > mad_size)
 			return ERR_PTR(-EINVAL);
 	} else
-		if (rmpp_active || message_size > sizeof(struct ib_mad))
+		if (rmpp_active || message_size > mad_size)
 			return ERR_PTR(-EINVAL);
 
-	size = rmpp_active ? hdr_len : sizeof(struct ib_mad);
+	size = rmpp_active ? hdr_len : mad_size;
 	buf = kzalloc(sizeof *mad_send_wr + size, gfp_mask);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
@@ -954,7 +1038,14 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 	mad_send_wr->mad_agent_priv = mad_agent_priv;
 	mad_send_wr->sg_list[0].length = hdr_len;
 	mad_send_wr->sg_list[0].lkey = mad_agent->mr->lkey;
-	mad_send_wr->sg_list[1].length = sizeof(struct ib_mad) - hdr_len;
+
+	/* OPA MADs don't have to be the full 2048 bytes */
+	if (opa && base_version == OPA_MGMT_BASE_VERSION &&
+	    data_len < mad_size - hdr_len)
+		mad_send_wr->sg_list[1].length = data_len;
+	else
+		mad_send_wr->sg_list[1].length = mad_size - hdr_len;
+
 	mad_send_wr->sg_list[1].lkey = mad_agent->mr->lkey;
 
 	mad_send_wr->send_wr.wr_id = (unsigned long) mad_send_wr;
@@ -967,7 +1058,7 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 	mad_send_wr->send_wr.wr.ud.pkey_index = pkey_index;
 
 	if (rmpp_active) {
-		ret = alloc_send_rmpp_list(mad_send_wr, gfp_mask);
+		ret = alloc_send_rmpp_list(mad_send_wr, mad_size, gfp_mask);
 		if (ret) {
 			kfree(buf);
 			return ERR_PTR(ret);
@@ -1237,7 +1328,7 @@ void ib_free_recv_mad(struct ib_mad_recv_wc *mad_recv_wc)
 					    recv_wc);
 		priv = container_of(mad_priv_hdr, struct ib_mad_private,
 				    header);
-		kmem_cache_free(ib_mad_cache, priv);
+		kfree(priv);
 	}
 }
 EXPORT_SYMBOL(ib_free_recv_mad);
@@ -1324,7 +1415,7 @@ static int check_vendor_class(struct ib_mad_mgmt_vendor_class *vendor_class)
 }
 
 static int find_vendor_oui(struct ib_mad_mgmt_vendor_class *vendor_class,
-			   char *oui)
+			   const char *oui)
 {
 	int i;
 
@@ -1622,13 +1713,13 @@ out:
 
 static struct ib_mad_agent_private *
 find_mad_agent(struct ib_mad_port_private *port_priv,
-	       struct ib_mad *mad)
+	       const struct ib_mad_hdr *mad_hdr)
 {
 	struct ib_mad_agent_private *mad_agent = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&port_priv->reg_lock, flags);
-	if (ib_response_mad(mad)) {
+	if (ib_response_mad(mad_hdr)) {
 		u32 hi_tid;
 		struct ib_mad_agent_private *entry;
 
@@ -1636,7 +1727,7 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 		 * Routing is based on high 32 bits of transaction ID
 		 * of MAD.
 		 */
-		hi_tid = be64_to_cpu(mad->mad_hdr.tid) >> 32;
+		hi_tid = be64_to_cpu(mad_hdr->tid) >> 32;
 		list_for_each_entry(entry, &port_priv->agent_list, agent_list) {
 			if (entry->agent.hi_tid == hi_tid) {
 				mad_agent = entry;
@@ -1648,45 +1739,45 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 		struct ib_mad_mgmt_method_table *method;
 		struct ib_mad_mgmt_vendor_class_table *vendor;
 		struct ib_mad_mgmt_vendor_class *vendor_class;
-		struct ib_vendor_mad *vendor_mad;
+		const struct ib_vendor_mad *vendor_mad;
 		int index;
 
 		/*
 		 * Routing is based on version, class, and method
 		 * For "newer" vendor MADs, also based on OUI
 		 */
-		if (mad->mad_hdr.class_version >= MAX_MGMT_VERSION)
+		if (mad_hdr->class_version >= MAX_MGMT_VERSION)
 			goto out;
-		if (!is_vendor_class(mad->mad_hdr.mgmt_class)) {
+		if (!is_vendor_class(mad_hdr->mgmt_class)) {
 			class = port_priv->version[
-					mad->mad_hdr.class_version].class;
+					mad_hdr->class_version].class;
 			if (!class)
 				goto out;
-			if (convert_mgmt_class(mad->mad_hdr.mgmt_class) >=
+			if (convert_mgmt_class(mad_hdr->mgmt_class) >=
 			    IB_MGMT_MAX_METHODS)
 				goto out;
 			method = class->method_table[convert_mgmt_class(
-							mad->mad_hdr.mgmt_class)];
+							mad_hdr->mgmt_class)];
 			if (method)
-				mad_agent = method->agent[mad->mad_hdr.method &
+				mad_agent = method->agent[mad_hdr->method &
 							  ~IB_MGMT_METHOD_RESP];
 		} else {
 			vendor = port_priv->version[
-					mad->mad_hdr.class_version].vendor;
+					mad_hdr->class_version].vendor;
 			if (!vendor)
 				goto out;
 			vendor_class = vendor->vendor_class[vendor_class_index(
-						mad->mad_hdr.mgmt_class)];
+						mad_hdr->mgmt_class)];
 			if (!vendor_class)
 				goto out;
 			/* Find matching OUI */
-			vendor_mad = (struct ib_vendor_mad *)mad;
+			vendor_mad = (const struct ib_vendor_mad *)mad_hdr;
 			index = find_vendor_oui(vendor_class, vendor_mad->oui);
 			if (index == -1)
 				goto out;
 			method = vendor_class->method_table[index];
 			if (method) {
-				mad_agent = method->agent[mad->mad_hdr.method &
+				mad_agent = method->agent[mad_hdr->method &
 							  ~IB_MGMT_METHOD_RESP];
 			}
 		}
@@ -1708,20 +1799,24 @@ out:
 	return mad_agent;
 }
 
-static int validate_mad(struct ib_mad *mad, u32 qp_num)
+static int validate_mad(const struct ib_mad_hdr *mad_hdr,
+			const struct ib_mad_qp_info *qp_info,
+			bool opa)
 {
 	int valid = 0;
+	u32 qp_num = qp_info->qp->qp_num;
 
 	/* Make sure MAD base version is understood */
-	if (mad->mad_hdr.base_version != IB_MGMT_BASE_VERSION) {
-		pr_err("MAD received with unsupported base version %d\n",
-			mad->mad_hdr.base_version);
+	if (mad_hdr->base_version != IB_MGMT_BASE_VERSION &&
+	    (!opa || mad_hdr->base_version != OPA_MGMT_BASE_VERSION)) {
+		pr_err("MAD received with unsupported base version %d %s\n",
+		       mad_hdr->base_version, opa ? "(opa)" : "");
 		goto out;
 	}
 
 	/* Filter SMI packets sent to other than QP0 */
-	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) ||
-	    (mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) {
+	if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) ||
+	    (mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) {
 		if (qp_num == 0)
 			valid = 1;
 	} else {
@@ -1734,8 +1829,8 @@ out:
 	return valid;
 }
 
-static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv,
-		       struct ib_mad_hdr *mad_hdr)
+static int is_rmpp_data_mad(const struct ib_mad_agent_private *mad_agent_priv,
+			    const struct ib_mad_hdr *mad_hdr)
 {
 	struct ib_rmpp_mad *rmpp_mad;
 
@@ -1747,16 +1842,16 @@ static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv,
 		(rmpp_mad->rmpp_hdr.rmpp_type == IB_MGMT_RMPP_TYPE_DATA);
 }
 
-static inline int rcv_has_same_class(struct ib_mad_send_wr_private *wr,
-				     struct ib_mad_recv_wc *rwc)
+static inline int rcv_has_same_class(const struct ib_mad_send_wr_private *wr,
+				     const struct ib_mad_recv_wc *rwc)
 {
-	return ((struct ib_mad *)(wr->send_buf.mad))->mad_hdr.mgmt_class ==
+	return ((struct ib_mad_hdr *)(wr->send_buf.mad))->mgmt_class ==
 		rwc->recv_buf.mad->mad_hdr.mgmt_class;
 }
 
-static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv,
-				   struct ib_mad_send_wr_private *wr,
-				   struct ib_mad_recv_wc *rwc )
+static inline int rcv_has_same_gid(const struct ib_mad_agent_private *mad_agent_priv,
+				   const struct ib_mad_send_wr_private *wr,
+				   const struct ib_mad_recv_wc *rwc )
 {
 	struct ib_ah_attr attr;
 	u8 send_resp, rcv_resp;
@@ -1765,8 +1860,8 @@ static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv,
 	u8 port_num = mad_agent_priv->agent.port_num;
 	u8 lmc;
 
-	send_resp = ib_response_mad((struct ib_mad *)wr->send_buf.mad);
-	rcv_resp = ib_response_mad(rwc->recv_buf.mad);
+	send_resp = ib_response_mad((struct ib_mad_hdr *)wr->send_buf.mad);
+	rcv_resp = ib_response_mad(&rwc->recv_buf.mad->mad_hdr);
 
 	if (send_resp == rcv_resp)
 		/* both requests, or both responses. GIDs different */
@@ -1811,22 +1906,22 @@ static inline int is_direct(u8 class)
 }
 
 struct ib_mad_send_wr_private*
-ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
-		 struct ib_mad_recv_wc *wc)
+ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv,
+		 const struct ib_mad_recv_wc *wc)
 {
 	struct ib_mad_send_wr_private *wr;
-	struct ib_mad *mad;
+	const struct ib_mad_hdr *mad_hdr;
 
-	mad = (struct ib_mad *)wc->recv_buf.mad;
+	mad_hdr = &wc->recv_buf.mad->mad_hdr;
 
 	list_for_each_entry(wr, &mad_agent_priv->wait_list, agent_list) {
-		if ((wr->tid == mad->mad_hdr.tid) &&
+		if ((wr->tid == mad_hdr->tid) &&
 		    rcv_has_same_class(wr, wc) &&
 		    /*
 		     * Don't check GID for direct routed MADs.
 		     * These might have permissive LIDs.
 		     */
-		    (is_direct(wc->recv_buf.mad->mad_hdr.mgmt_class) ||
+		    (is_direct(mad_hdr->mgmt_class) ||
 		     rcv_has_same_gid(mad_agent_priv, wr, wc)))
 			return (wr->status == IB_WC_SUCCESS) ? wr : NULL;
 	}
@@ -1836,15 +1931,15 @@ ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
 	 * been notified that the send has completed
 	 */
 	list_for_each_entry(wr, &mad_agent_priv->send_list, agent_list) {
-		if (is_data_mad(mad_agent_priv, wr->send_buf.mad) &&
-		    wr->tid == mad->mad_hdr.tid &&
+		if (is_rmpp_data_mad(mad_agent_priv, wr->send_buf.mad) &&
+		    wr->tid == mad_hdr->tid &&
 		    wr->timeout &&
 		    rcv_has_same_class(wr, wc) &&
 		    /*
 		     * Don't check GID for direct routed MADs.
 		     * These might have permissive LIDs.
 		     */
-		    (is_direct(wc->recv_buf.mad->mad_hdr.mgmt_class) ||
+		    (is_direct(mad_hdr->mgmt_class) ||
 		     rcv_has_same_gid(mad_agent_priv, wr, wc)))
 			/* Verify request has not been canceled */
 			return (wr->status == IB_WC_SUCCESS) ? wr : NULL;
@@ -1879,7 +1974,7 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 	}
 
 	/* Complete corresponding request */
-	if (ib_response_mad(mad_recv_wc->recv_buf.mad)) {
+	if (ib_response_mad(&mad_recv_wc->recv_buf.mad->mad_hdr)) {
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
 		mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc);
 		if (!mad_send_wr) {
@@ -1924,26 +2019,163 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 	}
 }
 
-static bool generate_unmatched_resp(struct ib_mad_private *recv,
-				    struct ib_mad_private *response)
+static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv,
+				     const struct ib_mad_qp_info *qp_info,
+				     const struct ib_wc *wc,
+				     int port_num,
+				     struct ib_mad_private *recv,
+				     struct ib_mad_private *response)
+{
+	enum smi_forward_action retsmi;
+	struct ib_smp *smp = (struct ib_smp *)recv->mad;
+
+	if (smi_handle_dr_smp_recv(smp,
+				   port_priv->device->node_type,
+				   port_num,
+				   port_priv->device->phys_port_cnt) ==
+				   IB_SMI_DISCARD)
+		return IB_SMI_DISCARD;
+
+	retsmi = smi_check_forward_dr_smp(smp);
+	if (retsmi == IB_SMI_LOCAL)
+		return IB_SMI_HANDLE;
+
+	if (retsmi == IB_SMI_SEND) { /* don't forward */
+		if (smi_handle_dr_smp_send(smp,
+					   port_priv->device->node_type,
+					   port_num) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+		if (smi_check_local_smp(smp, port_priv->device) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+		/* forward case for switches */
+		memcpy(response, recv, mad_priv_size(response));
+		response->header.recv_wc.wc = &response->header.wc;
+		response->header.recv_wc.recv_buf.mad = (struct ib_mad *)response->mad;
+		response->header.recv_wc.recv_buf.grh = &response->grh;
+
+		agent_send_response((const struct ib_mad_hdr *)response->mad,
+				    &response->grh, wc,
+				    port_priv->device,
+				    smi_get_fwd_port(smp),
+				    qp_info->qp->qp_num,
+				    response->mad_size,
+				    false);
+
+		return IB_SMI_DISCARD;
+	}
+	return IB_SMI_HANDLE;
+}
+
+static bool generate_unmatched_resp(const struct ib_mad_private *recv,
+				    struct ib_mad_private *response,
+				    size_t *resp_len, bool opa)
 {
-	if (recv->mad.mad.mad_hdr.method == IB_MGMT_METHOD_GET ||
-	    recv->mad.mad.mad_hdr.method == IB_MGMT_METHOD_SET) {
-		memcpy(response, recv, sizeof *response);
+	const struct ib_mad_hdr *recv_hdr = (const struct ib_mad_hdr *)recv->mad;
+	struct ib_mad_hdr *resp_hdr = (struct ib_mad_hdr *)response->mad;
+
+	if (recv_hdr->method == IB_MGMT_METHOD_GET ||
+	    recv_hdr->method == IB_MGMT_METHOD_SET) {
+		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
-		response->header.recv_wc.recv_buf.mad = &response->mad.mad;
+		response->header.recv_wc.recv_buf.mad = (struct ib_mad *)response->mad;
 		response->header.recv_wc.recv_buf.grh = &response->grh;
-		response->mad.mad.mad_hdr.method = IB_MGMT_METHOD_GET_RESP;
-		response->mad.mad.mad_hdr.status =
-			cpu_to_be16(IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB);
-		if (recv->mad.mad.mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
-			response->mad.mad.mad_hdr.status |= IB_SMP_DIRECTION;
+		resp_hdr->method = IB_MGMT_METHOD_GET_RESP;
+		resp_hdr->status = cpu_to_be16(IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB);
+		if (recv_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+			resp_hdr->status |= IB_SMP_DIRECTION;
+
+		if (opa && recv_hdr->base_version == OPA_MGMT_BASE_VERSION) {
+			if (recv_hdr->mgmt_class ==
+			    IB_MGMT_CLASS_SUBN_LID_ROUTED ||
+			    recv_hdr->mgmt_class ==
+			    IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+				*resp_len = opa_get_smp_header_size(
+							(struct opa_smp *)recv->mad);
+			else
+				*resp_len = sizeof(struct ib_mad_hdr);
+		}
 
 		return true;
 	} else {
 		return false;
 	}
 }
+
+static enum smi_action
+handle_opa_smi(struct ib_mad_port_private *port_priv,
+	       struct ib_mad_qp_info *qp_info,
+	       struct ib_wc *wc,
+	       int port_num,
+	       struct ib_mad_private *recv,
+	       struct ib_mad_private *response)
+{
+	enum smi_forward_action retsmi;
+	struct opa_smp *smp = (struct opa_smp *)recv->mad;
+
+	if (opa_smi_handle_dr_smp_recv(smp,
+				   port_priv->device->node_type,
+				   port_num,
+				   port_priv->device->phys_port_cnt) ==
+				   IB_SMI_DISCARD)
+		return IB_SMI_DISCARD;
+
+	retsmi = opa_smi_check_forward_dr_smp(smp);
+	if (retsmi == IB_SMI_LOCAL)
+		return IB_SMI_HANDLE;
+
+	if (retsmi == IB_SMI_SEND) { /* don't forward */
+		if (opa_smi_handle_dr_smp_send(smp,
+					   port_priv->device->node_type,
+					   port_num) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+		if (opa_smi_check_local_smp(smp, port_priv->device) ==
+		    IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+		/* forward case for switches */
+		memcpy(response, recv, mad_priv_size(response));
+		response->header.recv_wc.wc = &response->header.wc;
+		response->header.recv_wc.recv_buf.opa_mad =
+				(struct opa_mad *)response->mad;
+		response->header.recv_wc.recv_buf.grh = &response->grh;
+
+		agent_send_response((const struct ib_mad_hdr *)response->mad,
+				    &response->grh, wc,
+				    port_priv->device,
+				    opa_smi_get_fwd_port(smp),
+				    qp_info->qp->qp_num,
+				    recv->header.wc.byte_len,
+				    true);
+
+		return IB_SMI_DISCARD;
+	}
+
+	return IB_SMI_HANDLE;
+}
+
+static enum smi_action
+handle_smi(struct ib_mad_port_private *port_priv,
+	   struct ib_mad_qp_info *qp_info,
+	   struct ib_wc *wc,
+	   int port_num,
+	   struct ib_mad_private *recv,
+	   struct ib_mad_private *response,
+	   bool opa)
+{
+	struct ib_mad_hdr *mad_hdr = (struct ib_mad_hdr *)recv->mad;
+
+	if (opa && mad_hdr->base_version == OPA_MGMT_BASE_VERSION &&
+	    mad_hdr->class_version == OPA_SMI_CLASS_VERSION)
+		return handle_opa_smi(port_priv, qp_info, wc, port_num, recv,
+				      response);
+
+	return handle_ib_smi(port_priv, qp_info, wc, port_num, recv, response);
+}
+
 static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 				     struct ib_wc *wc)
 {
@@ -1954,35 +2186,49 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 	struct ib_mad_agent_private *mad_agent;
 	int port_num;
 	int ret = IB_MAD_RESULT_SUCCESS;
+	size_t mad_size;
+	u16 resp_mad_pkey_index = 0;
+	bool opa;
 
 	mad_list = (struct ib_mad_list_head *)(unsigned long)wc->wr_id;
 	qp_info = mad_list->mad_queue->qp_info;
 	dequeue_mad(mad_list);
 
+	opa = rdma_cap_opa_mad(qp_info->port_priv->device,
+			       qp_info->port_priv->port_num);
+
 	mad_priv_hdr = container_of(mad_list, struct ib_mad_private_header,
 				    mad_list);
 	recv = container_of(mad_priv_hdr, struct ib_mad_private, header);
 	ib_dma_unmap_single(port_priv->device,
 			    recv->header.mapping,
-			    sizeof(struct ib_mad_private) -
-			      sizeof(struct ib_mad_private_header),
+			    mad_priv_dma_size(recv),
 			    DMA_FROM_DEVICE);
 
 	/* Setup MAD receive work completion from "normal" work completion */
 	recv->header.wc = *wc;
 	recv->header.recv_wc.wc = &recv->header.wc;
-	recv->header.recv_wc.mad_len = sizeof(struct ib_mad);
-	recv->header.recv_wc.recv_buf.mad = &recv->mad.mad;
+
+	if (opa && ((struct ib_mad_hdr *)(recv->mad))->base_version == OPA_MGMT_BASE_VERSION) {
+		recv->header.recv_wc.mad_len = wc->byte_len - sizeof(struct ib_grh);
+		recv->header.recv_wc.mad_seg_size = sizeof(struct opa_mad);
+	} else {
+		recv->header.recv_wc.mad_len = sizeof(struct ib_mad);
+		recv->header.recv_wc.mad_seg_size = sizeof(struct ib_mad);
+	}
+
+	recv->header.recv_wc.recv_buf.mad = (struct ib_mad *)recv->mad;
 	recv->header.recv_wc.recv_buf.grh = &recv->grh;
 
 	if (atomic_read(&qp_info->snoop_count))
 		snoop_recv(qp_info, &recv->header.recv_wc, IB_MAD_SNOOP_RECVS);
 
 	/* Validate MAD */
-	if (!validate_mad(&recv->mad.mad, qp_info->qp->qp_num))
+	if (!validate_mad((const struct ib_mad_hdr *)recv->mad, qp_info, opa))
 		goto out;
 
-	response = kmem_cache_alloc(ib_mad_cache, GFP_KERNEL);
+	mad_size = recv->mad_size;
+	response = alloc_mad_private(mad_size, GFP_KERNEL);
 	if (!response) {
 		dev_err(&port_priv->device->dev,
 			"ib_mad_recv_done_handler no memory for response buffer\n");
@@ -1994,69 +2240,43 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 	else
 		port_num = port_priv->port_num;
 
-	if (recv->mad.mad.mad_hdr.mgmt_class ==
+	if (((struct ib_mad_hdr *)recv->mad)->mgmt_class ==
 	    IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
-		enum smi_forward_action retsmi;
-
-		if (smi_handle_dr_smp_recv(&recv->mad.smp,
-					   port_priv->device->node_type,
-					   port_num,
-					   port_priv->device->phys_port_cnt) ==
-					   IB_SMI_DISCARD)
+		if (handle_smi(port_priv, qp_info, wc, port_num, recv,
+			       response, opa)
+		    == IB_SMI_DISCARD)
 			goto out;
-
-		retsmi = smi_check_forward_dr_smp(&recv->mad.smp);
-		if (retsmi == IB_SMI_LOCAL)
-			goto local;
-
-		if (retsmi == IB_SMI_SEND) { /* don't forward */
-			if (smi_handle_dr_smp_send(&recv->mad.smp,
-						   port_priv->device->node_type,
-						   port_num) == IB_SMI_DISCARD)
-				goto out;
-
-			if (smi_check_local_smp(&recv->mad.smp, port_priv->device) == IB_SMI_DISCARD)
-				goto out;
-		} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
-			/* forward case for switches */
-			memcpy(response, recv, sizeof(*response));
-			response->header.recv_wc.wc = &response->header.wc;
-			response->header.recv_wc.recv_buf.mad = &response->mad.mad;
-			response->header.recv_wc.recv_buf.grh = &response->grh;
-
-			agent_send_response(&response->mad.mad,
-					    &response->grh, wc,
-					    port_priv->device,
-					    smi_get_fwd_port(&recv->mad.smp),
-					    qp_info->qp->qp_num);
-
-			goto out;
-		}
 	}
 
-local:
 	/* Give driver "right of first refusal" on incoming MAD */
 	if (port_priv->device->process_mad) {
 		ret = port_priv->device->process_mad(port_priv->device, 0,
 						     port_priv->port_num,
 						     wc, &recv->grh,
-						     &recv->mad.mad,
-						     &response->mad.mad);
+						     (const struct ib_mad_hdr *)recv->mad,
+						     recv->mad_size,
+						     (struct ib_mad_hdr *)response->mad,
+						     &mad_size, &resp_mad_pkey_index);
+
+		if (opa)
+			wc->pkey_index = resp_mad_pkey_index;
+
 		if (ret & IB_MAD_RESULT_SUCCESS) {
 			if (ret & IB_MAD_RESULT_CONSUMED)
 				goto out;
 			if (ret & IB_MAD_RESULT_REPLY) {
-				agent_send_response(&response->mad.mad,
+				agent_send_response((const struct ib_mad_hdr *)response->mad,
 						    &recv->grh, wc,
 						    port_priv->device,
 						    port_num,
-						    qp_info->qp->qp_num);
+						    qp_info->qp->qp_num,
+						    mad_size, opa);
 				goto out;
 			}
 		}
 	}
 
-	mad_agent = find_mad_agent(port_priv, &recv->mad.mad);
+	mad_agent = find_mad_agent(port_priv, (const struct ib_mad_hdr *)recv->mad);
 	if (mad_agent) {
 		ib_mad_complete_recv(mad_agent, &recv->header.recv_wc);
 		/*
@@ -2065,17 +2285,17 @@ local:
 		 */
 		recv = NULL;
 	} else if ((ret & IB_MAD_RESULT_SUCCESS) &&
-		   generate_unmatched_resp(recv, response)) {
-		agent_send_response(&response->mad.mad, &recv->grh, wc,
-				    port_priv->device, port_num, qp_info->qp->qp_num);
+		   generate_unmatched_resp(recv, response, &mad_size, opa)) {
+		agent_send_response((const struct ib_mad_hdr *)response->mad, &recv->grh, wc,
+				    port_priv->device, port_num,
+				    qp_info->qp->qp_num, mad_size, opa);
 	}
 
 out:
 	/* Post another receive request for this QP */
 	if (response) {
 		ib_mad_post_receive_mads(qp_info, response);
-		if (recv)
-			kmem_cache_free(ib_mad_cache, recv);
+		kfree(recv);
 	} else
 		ib_mad_post_receive_mads(qp_info, recv);
 }
@@ -2411,7 +2631,8 @@ find_send_wr(struct ib_mad_agent_private *mad_agent_priv,
 
 	list_for_each_entry(mad_send_wr, &mad_agent_priv->send_list,
 			    agent_list) {
-		if (is_data_mad(mad_agent_priv, mad_send_wr->send_buf.mad) &&
+		if (is_rmpp_data_mad(mad_agent_priv,
+				     mad_send_wr->send_buf.mad) &&
 		    &mad_send_wr->send_buf == send_buf)
 			return mad_send_wr;
 	}
@@ -2468,10 +2689,14 @@ static void local_completions(struct work_struct *work)
 	int free_mad;
 	struct ib_wc wc;
 	struct ib_mad_send_wc mad_send_wc;
+	bool opa;
 
 	mad_agent_priv =
 		container_of(work, struct ib_mad_agent_private, local_work);
 
+	opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
+			       mad_agent_priv->qp_info->port_priv->port_num);
+
 	spin_lock_irqsave(&mad_agent_priv->lock, flags);
 	while (!list_empty(&mad_agent_priv->local_list)) {
 		local = list_entry(mad_agent_priv->local_list.next,
@@ -2481,6 +2706,7 @@ static void local_completions(struct work_struct *work)
 		spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
 		free_mad = 0;
 		if (local->mad_priv) {
+			u8 base_version;
 			recv_mad_agent = local->recv_mad_agent;
 			if (!recv_mad_agent) {
 				dev_err(&mad_agent_priv->agent.device->dev,
@@ -2496,17 +2722,26 @@ static void local_completions(struct work_struct *work)
 			build_smp_wc(recv_mad_agent->agent.qp,
 				     (unsigned long) local->mad_send_wr,
 				     be16_to_cpu(IB_LID_PERMISSIVE),
-				     0, recv_mad_agent->agent.port_num, &wc);
+				     local->mad_send_wr->send_wr.wr.ud.pkey_index,
+				     recv_mad_agent->agent.port_num, &wc);
 
 			local->mad_priv->header.recv_wc.wc = &wc;
-			local->mad_priv->header.recv_wc.mad_len =
-						sizeof(struct ib_mad);
+
+			base_version = ((struct ib_mad_hdr *)(local->mad_priv->mad))->base_version;
+			if (opa && base_version == OPA_MGMT_BASE_VERSION) {
+				local->mad_priv->header.recv_wc.mad_len = local->return_wc_byte_len;
+				local->mad_priv->header.recv_wc.mad_seg_size = sizeof(struct opa_mad);
+			} else {
+				local->mad_priv->header.recv_wc.mad_len = sizeof(struct ib_mad);
+				local->mad_priv->header.recv_wc.mad_seg_size = sizeof(struct ib_mad);
+			}
+
 			INIT_LIST_HEAD(&local->mad_priv->header.recv_wc.rmpp_list);
 			list_add(&local->mad_priv->header.recv_wc.recv_buf.list,
 				 &local->mad_priv->header.recv_wc.rmpp_list);
 			local->mad_priv->header.recv_wc.recv_buf.grh = NULL;
 			local->mad_priv->header.recv_wc.recv_buf.mad =
-						&local->mad_priv->mad.mad;
+						(struct ib_mad *)local->mad_priv->mad;
 			if (atomic_read(&recv_mad_agent->qp_info->snoop_count))
 				snoop_recv(recv_mad_agent->qp_info,
 					  &local->mad_priv->header.recv_wc,
@@ -2534,7 +2769,7 @@ local_send_completion:
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
 		atomic_dec(&mad_agent_priv->refcount);
 		if (free_mad)
-			kmem_cache_free(ib_mad_cache, local->mad_priv);
+			kfree(local->mad_priv);
 		kfree(local);
 	}
 	spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
@@ -2649,7 +2884,6 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 	struct ib_mad_queue *recv_queue = &qp_info->recv_queue;
 
 	/* Initialize common scatter list fields */
-	sg_list.length = sizeof *mad_priv - sizeof mad_priv->header;
 	sg_list.lkey = (*qp_info->port_priv->mr).lkey;
 
 	/* Initialize common receive WR fields */
@@ -2663,7 +2897,8 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 			mad_priv = mad;
 			mad = NULL;
 		} else {
-			mad_priv = kmem_cache_alloc(ib_mad_cache, GFP_KERNEL);
+			mad_priv = alloc_mad_private(port_mad_size(qp_info->port_priv),
+						     GFP_ATOMIC);
 			if (!mad_priv) {
 				dev_err(&qp_info->port_priv->device->dev,
 					"No memory for receive buffer\n");
@@ -2671,10 +2906,10 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				break;
 			}
 		}
+		sg_list.length = mad_priv_dma_size(mad_priv);
 		sg_list.addr = ib_dma_map_single(qp_info->port_priv->device,
 						 &mad_priv->grh,
-						 sizeof *mad_priv -
-						   sizeof mad_priv->header,
+						 mad_priv_dma_size(mad_priv),
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
@@ -2698,10 +2933,9 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 			spin_unlock_irqrestore(&recv_queue->lock, flags);
 			ib_dma_unmap_single(qp_info->port_priv->device,
 					    mad_priv->header.mapping,
-					    sizeof *mad_priv -
-					      sizeof mad_priv->header,
+					    mad_priv_dma_size(mad_priv),
 					    DMA_FROM_DEVICE);
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 			dev_err(&qp_info->port_priv->device->dev,
 				"ib_post_recv failed: %d\n", ret);
 			break;
@@ -2738,10 +2972,9 @@ static void cleanup_recv_queue(struct ib_mad_qp_info *qp_info)
 
 		ib_dma_unmap_single(qp_info->port_priv->device,
 				    recv->header.mapping,
-				    sizeof(struct ib_mad_private) -
-				      sizeof(struct ib_mad_private_header),
+				    mad_priv_dma_size(recv),
 				    DMA_FROM_DEVICE);
-		kmem_cache_free(ib_mad_cache, recv);
+		kfree(recv);
 	}
 
 	qp_info->recv_queue.count = 0;
@@ -2922,6 +3155,14 @@ static int ib_mad_port_open(struct ib_device *device,
 	unsigned long flags;
 	char name[sizeof "ib_mad123"];
 	int has_smi;
+	struct ib_cq_init_attr cq_attr = {};
+
+	if (WARN_ON(rdma_max_mad_size(device, port_num) < IB_MGMT_MAD_SIZE))
+		return -EFAULT;
+
+	if (WARN_ON(rdma_cap_opa_mad(device, port_num) &&
+		    rdma_max_mad_size(device, port_num) < OPA_MGMT_MAD_SIZE))
+		return -EFAULT;
 
 	/* Create new device info */
 	port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL);
@@ -2938,13 +3179,14 @@ static int ib_mad_port_open(struct ib_device *device,
 	init_mad_qp(port_priv, &port_priv->qp_info[1]);
 
 	cq_size = mad_sendq_size + mad_recvq_size;
-	has_smi = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND;
+	has_smi = rdma_cap_ib_smi(device, port_num);
 	if (has_smi)
 		cq_size *= 2;
 
+	cq_attr.cqe = cq_size;
 	port_priv->cq = ib_create_cq(port_priv->device,
 				     ib_mad_thread_completion_handler,
-				     NULL, port_priv, cq_size, 0);
+				     NULL, port_priv, &cq_attr);
 	if (IS_ERR(port_priv->cq)) {
 		dev_err(&device->dev, "Couldn't create ib_mad CQ\n");
 		ret = PTR_ERR(port_priv->cq);
@@ -3057,9 +3299,6 @@ static void ib_mad_init_device(struct ib_device *device)
 {
 	int start, end, i;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
 		start = 0;
 		end   = 0;
@@ -3069,6 +3308,9 @@ static void ib_mad_init_device(struct ib_device *device)
 	}
 
 	for (i = start; i <= end; i++) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
 		if (ib_mad_port_open(device, i)) {
 			dev_err(&device->dev, "Couldn't open port %d\n", i);
 			goto error;
@@ -3086,40 +3328,39 @@ error_agent:
 		dev_err(&device->dev, "Couldn't close port %d\n", i);
 
 error:
-	i--;
+	while (--i >= start) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
 
-	while (i >= start) {
 		if (ib_agent_port_close(device, i))
 			dev_err(&device->dev,
 				"Couldn't close port %d for agents\n", i);
 		if (ib_mad_port_close(device, i))
 			dev_err(&device->dev, "Couldn't close port %d\n", i);
-		i--;
 	}
 }
 
 static void ib_mad_remove_device(struct ib_device *device)
 {
-	int i, num_ports, cur_port;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int start, end, i;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		num_ports = 1;
-		cur_port = 0;
+		start = 0;
+		end   = 0;
 	} else {
-		num_ports = device->phys_port_cnt;
-		cur_port = 1;
+		start = 1;
+		end   = device->phys_port_cnt;
 	}
-	for (i = 0; i < num_ports; i++, cur_port++) {
-		if (ib_agent_port_close(device, cur_port))
+
+	for (i = start; i <= end; i++) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
+		if (ib_agent_port_close(device, i))
 			dev_err(&device->dev,
-				"Couldn't close port %d for agents\n",
-				cur_port);
-		if (ib_mad_port_close(device, cur_port))
-			dev_err(&device->dev, "Couldn't close port %d\n",
-				cur_port);
+				"Couldn't close port %d for agents\n", i);
+		if (ib_mad_port_close(device, i))
+			dev_err(&device->dev, "Couldn't close port %d\n", i);
 	}
 }
 
@@ -3131,45 +3372,25 @@ static struct ib_client mad_client = {
 
 static int __init ib_mad_init_module(void)
 {
-	int ret;
-
 	mad_recvq_size = min(mad_recvq_size, IB_MAD_QP_MAX_SIZE);
 	mad_recvq_size = max(mad_recvq_size, IB_MAD_QP_MIN_SIZE);
 
 	mad_sendq_size = min(mad_sendq_size, IB_MAD_QP_MAX_SIZE);
 	mad_sendq_size = max(mad_sendq_size, IB_MAD_QP_MIN_SIZE);
 
-	ib_mad_cache = kmem_cache_create("ib_mad",
-					 sizeof(struct ib_mad_private),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!ib_mad_cache) {
-		pr_err("Couldn't create ib_mad cache\n");
-		ret = -ENOMEM;
-		goto error1;
-	}
-
 	INIT_LIST_HEAD(&ib_mad_port_list);
 
 	if (ib_register_client(&mad_client)) {
 		pr_err("Couldn't register ib_mad client\n");
-		ret = -EINVAL;
-		goto error2;
+		return -EINVAL;
 	}
 
 	return 0;
-
-error2:
-	kmem_cache_destroy(ib_mad_cache);
-error1:
-	return ret;
 }
 
 static void __exit ib_mad_cleanup_module(void)
 {
 	ib_unregister_client(&mad_client);
-	kmem_cache_destroy(ib_mad_cache);
 }
 
 module_init(ib_mad_init_module);
diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h
index d1a0b0ee9444..5be89f98928f 100644
--- a/drivers/infiniband/core/mad_priv.h
+++ b/drivers/infiniband/core/mad_priv.h
@@ -41,6 +41,7 @@
 #include <linux/workqueue.h>
 #include <rdma/ib_mad.h>
 #include <rdma/ib_smi.h>
+#include <rdma/opa_smi.h>
 
 #define IB_MAD_QPS_CORE		2 /* Always QP0 and QP1 as a minimum */
 
@@ -56,7 +57,7 @@
 
 /* Registration table sizes */
 #define MAX_MGMT_CLASS		80
-#define MAX_MGMT_VERSION	8
+#define MAX_MGMT_VERSION	0x83
 #define MAX_MGMT_OUI		8
 #define MAX_MGMT_VENDOR_RANGE2	(IB_MGMT_CLASS_VENDOR_RANGE2_END - \
 				IB_MGMT_CLASS_VENDOR_RANGE2_START + 1)
@@ -75,12 +76,9 @@ struct ib_mad_private_header {
 
 struct ib_mad_private {
 	struct ib_mad_private_header header;
+	size_t mad_size;
 	struct ib_grh grh;
-	union {
-		struct ib_mad mad;
-		struct ib_rmpp_mad rmpp_mad;
-		struct ib_smp smp;
-	} mad;
+	u8 mad[0];
 } __attribute__ ((packed));
 
 struct ib_rmpp_segment {
@@ -150,6 +148,7 @@ struct ib_mad_local_private {
 	struct ib_mad_private *mad_priv;
 	struct ib_mad_agent_private *recv_mad_agent;
 	struct ib_mad_send_wr_private *mad_send_wr;
+	size_t return_wc_byte_len;
 };
 
 struct ib_mad_mgmt_method_table {
@@ -213,8 +212,8 @@ struct ib_mad_port_private {
 int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr);
 
 struct ib_mad_send_wr_private *
-ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
-		 struct ib_mad_recv_wc *mad_recv_wc);
+ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv,
+		 const struct ib_mad_recv_wc *mad_recv_wc);
 
 void ib_mad_complete_send_wr(struct ib_mad_send_wr_private *mad_send_wr,
 			     struct ib_mad_send_wc *mad_send_wc);
diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c
index f37878c9c06e..382941b46e43 100644
--- a/drivers/infiniband/core/mad_rmpp.c
+++ b/drivers/infiniband/core/mad_rmpp.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2005 Intel Inc. All rights reserved.
  * Copyright (c) 2005-2006 Voltaire, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -67,6 +68,7 @@ struct mad_rmpp_recv {
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;
+	u8 base_version;
 };
 
 static inline void deref_rmpp_recv(struct mad_rmpp_recv *rmpp_recv)
@@ -139,7 +141,8 @@ static void ack_recv(struct mad_rmpp_recv *rmpp_recv,
 	hdr_len = ib_get_mad_data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
 	msg = ib_create_send_mad(&rmpp_recv->agent->agent, recv_wc->wc->src_qp,
 				 recv_wc->wc->pkey_index, 1, hdr_len,
-				 0, GFP_KERNEL);
+				 0, GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(msg))
 		return;
 
@@ -165,7 +168,8 @@ static struct ib_mad_send_buf *alloc_response_msg(struct ib_mad_agent *agent,
 	hdr_len = ib_get_mad_data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
 	msg = ib_create_send_mad(agent, recv_wc->wc->src_qp,
 				 recv_wc->wc->pkey_index, 1,
-				 hdr_len, 0, GFP_KERNEL);
+				 hdr_len, 0, GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(msg))
 		ib_destroy_ah(ah);
 	else {
@@ -316,6 +320,7 @@ create_rmpp_recv(struct ib_mad_agent_private *agent,
 	rmpp_recv->mgmt_class = mad_hdr->mgmt_class;
 	rmpp_recv->class_version = mad_hdr->class_version;
 	rmpp_recv->method  = mad_hdr->method;
+	rmpp_recv->base_version  = mad_hdr->base_version;
 	return rmpp_recv;
 
 error:	kfree(rmpp_recv);
@@ -431,14 +436,23 @@ static inline int get_mad_len(struct mad_rmpp_recv *rmpp_recv)
 {
 	struct ib_rmpp_mad *rmpp_mad;
 	int hdr_size, data_size, pad;
+	bool opa = rdma_cap_opa_mad(rmpp_recv->agent->qp_info->port_priv->device,
+				    rmpp_recv->agent->qp_info->port_priv->port_num);
 
 	rmpp_mad = (struct ib_rmpp_mad *)rmpp_recv->cur_seg_buf->mad;
 
 	hdr_size = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
-	data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
-	pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
-	if (pad > IB_MGMT_RMPP_DATA || pad < 0)
-		pad = 0;
+	if (opa && rmpp_recv->base_version == OPA_MGMT_BASE_VERSION) {
+		data_size = sizeof(struct opa_rmpp_mad) - hdr_size;
+		pad = OPA_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > OPA_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	} else {
+		data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
+		pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > IB_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	}
 
 	return hdr_size + rmpp_recv->seg_num * data_size - pad;
 }
@@ -570,13 +584,14 @@ static int send_next_seg(struct ib_mad_send_wr_private *mad_send_wr)
 
 	if (mad_send_wr->seg_num == 1) {
 		rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_FIRST;
-		paylen = mad_send_wr->send_buf.seg_count * IB_MGMT_RMPP_DATA -
-			 mad_send_wr->pad;
+		paylen = (mad_send_wr->send_buf.seg_count *
+			  mad_send_wr->send_buf.seg_rmpp_size) -
+			  mad_send_wr->pad;
 	}
 
 	if (mad_send_wr->seg_num == mad_send_wr->send_buf.seg_count) {
 		rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_LAST;
-		paylen = IB_MGMT_RMPP_DATA - mad_send_wr->pad;
+		paylen = mad_send_wr->send_buf.seg_rmpp_size - mad_send_wr->pad;
 	}
 	rmpp_mad->rmpp_hdr.paylen_newwin = cpu_to_be32(paylen);
 
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index fa17b552ff78..1244f02a5c6d 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -780,8 +780,7 @@ static void mcast_event_handler(struct ib_event_handler *handler,
 	int index;
 
 	dev = container_of(handler, struct mcast_device, event_handler);
-	if (rdma_port_get_link_layer(dev->device, event->element.port_num) !=
-	    IB_LINK_LAYER_INFINIBAND)
+	if (!rdma_cap_ib_mcast(dev->device, event->element.port_num))
 		return;
 
 	index = event->element.port_num - dev->start_port;
@@ -808,9 +807,6 @@ static void mcast_add_one(struct ib_device *device)
 	int i;
 	int count = 0;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	dev = kmalloc(sizeof *dev + device->phys_port_cnt * sizeof *port,
 		      GFP_KERNEL);
 	if (!dev)
@@ -824,8 +820,7 @@ static void mcast_add_one(struct ib_device *device)
 	}
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
-		if (rdma_port_get_link_layer(device, dev->start_port + i) !=
-		    IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_mcast(device, dev->start_port + i))
 			continue;
 		port = &dev->port[i];
 		port->dev = dev;
@@ -863,8 +858,7 @@ static void mcast_remove_one(struct ib_device *device)
 	flush_workqueue(mcast_wq);
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
-		if (rdma_port_get_link_layer(device, dev->start_port + i) ==
-		    IB_LINK_LAYER_INFINIBAND) {
+		if (rdma_cap_ib_mcast(device, dev->start_port + i)) {
 			port = &dev->port[i];
 			deref_port(port);
 			wait_for_completion(&port->comp);
diff --git a/drivers/infiniband/core/opa_smi.h b/drivers/infiniband/core/opa_smi.h
new file mode 100644
index 000000000000..62d91bfa4cb7
--- /dev/null
+++ b/drivers/infiniband/core/opa_smi.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2014 Intel Corporation.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef __OPA_SMI_H_
+#define __OPA_SMI_H_
+
+#include <rdma/ib_smi.h>
+#include <rdma/opa_smi.h>
+
+#include "smi.h"
+
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+				       int port_num, int phys_port_cnt);
+int opa_smi_get_fwd_port(struct opa_smp *smp);
+extern enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp);
+extern enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
+					      u8 node_type, int port_num);
+
+/*
+ * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
+ * via process_mad
+ */
+static inline enum smi_action opa_smi_check_local_smp(struct opa_smp *smp,
+						      struct ib_device *device)
+{
+	/* C14-9:3 -- We're at the end of the DR segment of path */
+	/* C14-9:4 -- Hop Pointer = Hop Count + 1 -> give to SMA/SM */
+	return (device->process_mad &&
+		!opa_get_smp_direction(smp) &&
+		(smp->hop_ptr == smp->hop_cnt + 1)) ?
+		IB_SMI_HANDLE : IB_SMI_DISCARD;
+}
+
+/*
+ * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
+ * via process_mad
+ */
+static inline enum smi_action opa_smi_check_local_returning_smp(struct opa_smp *smp,
+								struct ib_device *device)
+{
+	/* C14-13:3 -- We're at the end of the DR segment of path */
+	/* C14-13:4 -- Hop Pointer == 0 -> give to SM */
+	return (device->process_mad &&
+		opa_get_smp_direction(smp) &&
+		!smp->hop_ptr) ? IB_SMI_HANDLE : IB_SMI_DISCARD;
+}
+
+#endif	/* __OPA_SMI_H_ */
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index c38f030f0dc9..0fae85062a65 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -450,7 +450,7 @@ static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event
 		struct ib_sa_port *port =
 			&sa_dev->port[event->element.port_num - sa_dev->start_port];
 
-		if (rdma_port_get_link_layer(handler->device, port->port_num) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_sa(handler->device, port->port_num))
 			return;
 
 		spin_lock_irqsave(&port->ah_lock, flags);
@@ -540,7 +540,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 	ah_attr->port_num = port_num;
 	ah_attr->static_rate = rec->rate;
 
-	force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET;
+	force_grh = rdma_cap_eth_ah(device, port_num);
 
 	if (rec->hop_limit > 1 || force_grh) {
 		ah_attr->ah_flags = IB_AH_GRH;
@@ -583,7 +583,8 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
 	query->mad_buf = ib_create_send_mad(query->port->agent, 1,
 					    query->sm_ah->pkey_index,
 					    0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
-					    gfp_mask);
+					    gfp_mask,
+					    IB_MGMT_BASE_VERSION);
 	if (IS_ERR(query->mad_buf)) {
 		kref_put(&query->sm_ah->ref, free_sm_ah);
 		return -ENOMEM;
@@ -1153,9 +1154,7 @@ static void ib_sa_add_one(struct ib_device *device)
 {
 	struct ib_sa_device *sa_dev;
 	int s, e, i;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int count = 0;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH)
 		s = e = 0;
@@ -1175,7 +1174,7 @@ static void ib_sa_add_one(struct ib_device *device)
 
 	for (i = 0; i <= e - s; ++i) {
 		spin_lock_init(&sa_dev->port[i].ah_lock);
-		if (rdma_port_get_link_layer(device, i + 1) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_sa(device, i + 1))
 			continue;
 
 		sa_dev->port[i].sm_ah    = NULL;
@@ -1189,8 +1188,13 @@ static void ib_sa_add_one(struct ib_device *device)
 			goto err;
 
 		INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah);
+
+		count++;
 	}
 
+	if (!count)
+		goto free;
+
 	ib_set_client_data(device, &sa_client, sa_dev);
 
 	/*
@@ -1204,19 +1208,20 @@ static void ib_sa_add_one(struct ib_device *device)
 	if (ib_register_event_handler(&sa_dev->event_handler))
 		goto err;
 
-	for (i = 0; i <= e - s; ++i)
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+	for (i = 0; i <= e - s; ++i) {
+		if (rdma_cap_ib_sa(device, i + 1))
 			update_sm_ah(&sa_dev->port[i].update_task);
+	}
 
 	return;
 
 err:
-	while (--i >= 0)
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+	while (--i >= 0) {
+		if (rdma_cap_ib_sa(device, i + 1))
 			ib_unregister_mad_agent(sa_dev->port[i].agent);
-
+	}
+free:
 	kfree(sa_dev);
-
 	return;
 }
 
@@ -1233,7 +1238,7 @@ static void ib_sa_remove_one(struct ib_device *device)
 	flush_workqueue(ib_wq);
 
 	for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) {
+		if (rdma_cap_ib_sa(device, i + 1)) {
 			ib_unregister_mad_agent(sa_dev->port[i].agent);
 			if (sa_dev->port[i].sm_ah)
 				kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
diff --git a/drivers/infiniband/core/smi.c b/drivers/infiniband/core/smi.c
index 5855e4405d9b..368a561d1a5d 100644
--- a/drivers/infiniband/core/smi.c
+++ b/drivers/infiniband/core/smi.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2004, 2005 Topspin Corporation.  All rights reserved.
  * Copyright (c) 2004-2007 Voltaire Corporation.  All rights reserved.
  * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -38,85 +39,82 @@
 
 #include <rdma/ib_smi.h>
 #include "smi.h"
-
-/*
- * Fixup a directed route SMP for sending
- * Return 0 if the SMP should be discarded
- */
-enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-				       u8 node_type, int port_num)
+#include "opa_smi.h"
+
+static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
+						u8 *hop_ptr, u8 hop_cnt,
+						const u8 *initial_path,
+						const u8 *return_path,
+						u8 direction,
+						bool dr_dlid_is_permissive,
+						bool dr_slid_is_permissive)
 {
-	u8 hop_ptr, hop_cnt;
-
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
-
 	/* See section 14.2.2.2, Vol 1 IB spec */
 	/* C14-6 -- valid hop_cnt values are from 0 to 63 */
 	if (hop_cnt >= IB_SMP_MAX_PATH_HOPS)
 		return IB_SMI_DISCARD;
 
-	if (!ib_get_smp_direction(smp)) {
+	if (!direction) {
 		/* C14-9:1 */
-		if (hop_cnt && hop_ptr == 0) {
-			smp->hop_ptr++;
-			return (smp->initial_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == 0) {
+			(*hop_ptr)++;
+			return (initial_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:2 */
-		if (hop_ptr && hop_ptr < hop_cnt) {
+		if (*hop_ptr && *hop_ptr < hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			/* smp->return_path set when received */
-			smp->hop_ptr++;
-			return (smp->initial_path[smp->hop_ptr] ==
+			/* return_path set when received */
+			(*hop_ptr)++;
+			return (initial_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == hop_cnt) {
-			/* smp->return_path set when received */
-			smp->hop_ptr++;
+		if (*hop_ptr == hop_cnt) {
+			/* return_path set when received */
+			(*hop_ptr)++;
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_dlid == IB_LID_PERMISSIVE ?
+				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
 		/* C14-9:5 -- Fail unreasonable hop pointer */
-		return (hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 
 	} else {
 		/* C14-13:1 */
-		if (hop_cnt && hop_ptr == hop_cnt + 1) {
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == hop_cnt + 1) {
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:2 */
-		if (2 <= hop_ptr && hop_ptr <= hop_cnt) {
+		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:3 -- at the end of the DR segment of path */
-		if (hop_ptr == 1) {
-			smp->hop_ptr--;
+		if (*hop_ptr == 1) {
+			(*hop_ptr)--;
 			/* C14-13:3 -- SMPs destined for SM shouldn't be here */
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_slid == IB_LID_PERMISSIVE ?
+				dr_slid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> should have gone to SM */
-		if (hop_ptr == 0)
+		if (*hop_ptr == 0)
 			return IB_SMI_HANDLE;
 
 		/* C14-13:5 -- Check for unreasonable hop pointer */
@@ -125,105 +123,164 @@ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
 }
 
 /*
- * Adjust information for a received SMP
- * Return 0 if the SMP should be dropped
+ * Fixup a directed route SMP for sending
+ * Return IB_SMI_DISCARD if the SMP should be discarded
  */
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
-				       int port_num, int phys_port_cnt)
+enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
+				       u8 node_type, int port_num)
 {
-	u8 hop_ptr, hop_cnt;
+	return __smi_handle_dr_smp_send(node_type, port_num,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->initial_path,
+					smp->return_path,
+					ib_get_smp_direction(smp),
+					smp->dr_dlid == IB_LID_PERMISSIVE,
+					smp->dr_slid == IB_LID_PERMISSIVE);
+}
 
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
+enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
+				       u8 node_type, int port_num)
+{
+	return __smi_handle_dr_smp_send(node_type, port_num,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->route.dr.initial_path,
+					smp->route.dr.return_path,
+					opa_get_smp_direction(smp),
+					smp->route.dr.dr_dlid ==
+					OPA_LID_PERMISSIVE,
+					smp->route.dr.dr_slid ==
+					OPA_LID_PERMISSIVE);
+}
 
+static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
+						int phys_port_cnt,
+						u8 *hop_ptr, u8 hop_cnt,
+						const u8 *initial_path,
+						u8 *return_path,
+						u8 direction,
+						bool dr_dlid_is_permissive,
+						bool dr_slid_is_permissive)
+{
 	/* See section 14.2.2.2, Vol 1 IB spec */
 	/* C14-6 -- valid hop_cnt values are from 0 to 63 */
 	if (hop_cnt >= IB_SMP_MAX_PATH_HOPS)
 		return IB_SMI_DISCARD;
 
-	if (!ib_get_smp_direction(smp)) {
+	if (!direction) {
 		/* C14-9:1 -- sender should have incremented hop_ptr */
-		if (hop_cnt && hop_ptr == 0)
+		if (hop_cnt && *hop_ptr == 0)
 			return IB_SMI_DISCARD;
 
 		/* C14-9:2 -- intermediate hop */
-		if (hop_ptr && hop_ptr < hop_cnt) {
+		if (*hop_ptr && *hop_ptr < hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			smp->return_path[hop_ptr] = port_num;
-			/* smp->hop_ptr updated when sending */
-			return (smp->initial_path[hop_ptr+1] <= phys_port_cnt ?
+			return_path[*hop_ptr] = port_num;
+			/* hop_ptr updated when sending */
+			return (initial_path[*hop_ptr+1] <= phys_port_cnt ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == hop_cnt) {
+		if (*hop_ptr == hop_cnt) {
 			if (hop_cnt)
-				smp->return_path[hop_ptr] = port_num;
-			/* smp->hop_ptr updated when sending */
+				return_path[*hop_ptr] = port_num;
+			/* hop_ptr updated when sending */
 
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_dlid == IB_LID_PERMISSIVE ?
+				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
 		/* C14-9:5 -- fail unreasonable hop pointer */
-		return (hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 
 	} else {
 
 		/* C14-13:1 */
-		if (hop_cnt && hop_ptr == hop_cnt + 1) {
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == hop_cnt + 1) {
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:2 */
-		if (2 <= hop_ptr && hop_ptr <= hop_cnt) {
+		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			/* smp->hop_ptr updated when sending */
-			return (smp->return_path[hop_ptr-1] <= phys_port_cnt ?
+			/* hop_ptr updated when sending */
+			return (return_path[*hop_ptr-1] <= phys_port_cnt ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == 1) {
-			if (smp->dr_slid == IB_LID_PERMISSIVE) {
+		if (*hop_ptr == 1) {
+			if (dr_slid_is_permissive) {
 				/* giving SMP to SM - update hop_ptr */
-				smp->hop_ptr--;
+				(*hop_ptr)--;
 				return IB_SMI_HANDLE;
 			}
-			/* smp->hop_ptr updated when sending */
+			/* hop_ptr updated when sending */
 			return (node_type == RDMA_NODE_IB_SWITCH ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> give to SM */
 		/* C14-13:5 -- Check for unreasonable hop pointer */
-		return (hop_ptr == 0 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == 0 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 	}
 }
 
-enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
+/*
+ * Adjust information for a received SMP
+ * Return IB_SMI_DISCARD if the SMP should be dropped
+ */
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+				       int port_num, int phys_port_cnt)
 {
-	u8 hop_ptr, hop_cnt;
+	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->initial_path,
+					smp->return_path,
+					ib_get_smp_direction(smp),
+					smp->dr_dlid == IB_LID_PERMISSIVE,
+					smp->dr_slid == IB_LID_PERMISSIVE);
+}
 
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
+/*
+ * Adjust information for a received SMP
+ * Return IB_SMI_DISCARD if the SMP should be dropped
+ */
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+					   int port_num, int phys_port_cnt)
+{
+	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->route.dr.initial_path,
+					smp->route.dr.return_path,
+					opa_get_smp_direction(smp),
+					smp->route.dr.dr_dlid ==
+					OPA_LID_PERMISSIVE,
+					smp->route.dr.dr_slid ==
+					OPA_LID_PERMISSIVE);
+}
 
-	if (!ib_get_smp_direction(smp)) {
+static enum smi_forward_action __smi_check_forward_dr_smp(u8 hop_ptr, u8 hop_cnt,
+							  u8 direction,
+							  bool dr_dlid_is_permissive,
+							  bool dr_slid_is_permissive)
+{
+	if (!direction) {
 		/* C14-9:2 -- intermediate hop */
 		if (hop_ptr && hop_ptr < hop_cnt)
 			return IB_SMI_FORWARD;
 
 		/* C14-9:3 -- at the end of the DR segment of path */
 		if (hop_ptr == hop_cnt)
-			return (smp->dr_dlid == IB_LID_PERMISSIVE ?
+			return (dr_dlid_is_permissive ?
 				IB_SMI_SEND : IB_SMI_LOCAL);
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
@@ -236,10 +293,29 @@ enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
 
 		/* C14-13:3 -- at the end of the DR segment of path */
 		if (hop_ptr == 1)
-			return (smp->dr_slid != IB_LID_PERMISSIVE ?
+			return (!dr_slid_is_permissive ?
 				IB_SMI_SEND : IB_SMI_LOCAL);
 	}
 	return IB_SMI_LOCAL;
+
+}
+
+enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
+{
+	return __smi_check_forward_dr_smp(smp->hop_ptr, smp->hop_cnt,
+					  ib_get_smp_direction(smp),
+					  smp->dr_dlid == IB_LID_PERMISSIVE,
+					  smp->dr_slid == IB_LID_PERMISSIVE);
+}
+
+enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp)
+{
+	return __smi_check_forward_dr_smp(smp->hop_ptr, smp->hop_cnt,
+					  opa_get_smp_direction(smp),
+					  smp->route.dr.dr_dlid ==
+					  OPA_LID_PERMISSIVE,
+					  smp->route.dr.dr_slid ==
+					  OPA_LID_PERMISSIVE);
 }
 
 /*
@@ -251,3 +327,13 @@ int smi_get_fwd_port(struct ib_smp *smp)
 	return (!ib_get_smp_direction(smp) ? smp->initial_path[smp->hop_ptr+1] :
 		smp->return_path[smp->hop_ptr-1]);
 }
+
+/*
+ * Return the forwarding port number from initial_path for outgoing SMP and
+ * from return_path for returning SMP
+ */
+int opa_smi_get_fwd_port(struct opa_smp *smp)
+{
+	return !opa_get_smp_direction(smp) ? smp->route.dr.initial_path[smp->hop_ptr+1] :
+		smp->route.dr.return_path[smp->hop_ptr-1];
+}
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index cbd0383f622e..ed6b6c85c334 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -326,6 +326,8 @@ static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
 	int width  = (tab_attr->index >> 16) & 0xff;
 	struct ib_mad *in_mad  = NULL;
 	struct ib_mad *out_mad = NULL;
+	size_t mad_size = sizeof(*out_mad);
+	u16 out_mad_pkey_index = 0;
 	ssize_t ret;
 
 	if (!p->ibdev->process_mad)
@@ -347,7 +349,10 @@ static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
 	in_mad->data[41] = p->port_num;	/* PortSelect field */
 
 	if ((p->ibdev->process_mad(p->ibdev, IB_MAD_IGNORE_MKEY,
-		 p->port_num, NULL, NULL, in_mad, out_mad) &
+		 p->port_num, NULL, NULL,
+		 (const struct ib_mad_hdr *)in_mad, mad_size,
+		 (struct ib_mad_hdr *)out_mad, &mad_size,
+		 &out_mad_pkey_index) &
 	     (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
 	    (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
 		ret = -EINVAL;
@@ -456,6 +461,7 @@ static void ib_device_release(struct device *device)
 {
 	struct ib_device *dev = container_of(device, struct ib_device, dev);
 
+	kfree(dev->port_immutable);
 	kfree(dev);
 }
 
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index f2f63933e8a9..62c24b1452b8 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -1253,8 +1253,7 @@ static void ib_ucm_add_one(struct ib_device *device)
 	dev_t base;
 	struct ib_ucm_device *ucm_dev;
 
-	if (!device->alloc_ucontext ||
-	    rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
+	if (!device->alloc_ucontext || !rdma_cap_ib_cm(device, 1))
 		return;
 
 	ucm_dev = kzalloc(sizeof *ucm_dev, GFP_KERNEL);
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 45d67e9228d7..ad45469f7582 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -722,26 +722,13 @@ static ssize_t ucma_query_route(struct ucma_file *file,
 
 	resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid;
 	resp.port_num = ctx->cm_id->port_num;
-	switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(ctx->cm_id->device,
-			ctx->cm_id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ucma_copy_ib_route(&resp, &ctx->cm_id->route);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
-			break;
-		default:
-			break;
-		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+
+	if (rdma_cap_ib_sa(ctx->cm_id->device, ctx->cm_id->port_num))
+		ucma_copy_ib_route(&resp, &ctx->cm_id->route);
+	else if (rdma_protocol_roce(ctx->cm_id->device, ctx->cm_id->port_num))
+		ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
+	else if (rdma_protocol_iwarp(ctx->cm_id->device, ctx->cm_id->port_num))
 		ucma_copy_iw_route(&resp, &ctx->cm_id->route);
-		break;
-	default:
-		break;
-	}
 
 out:
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 8b8cc6fa0ab0..40becdb3196e 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -446,7 +446,6 @@ static int ib_umem_odp_map_dma_single_page(
 	int remove_existing_mapping = 0;
 	int ret = 0;
 
-	mutex_lock(&umem->odp_data->umem_mutex);
 	/*
 	 * Note: we avoid writing if seq is different from the initial seq, to
 	 * handle case of a racing notifier. This check also allows us to bail
@@ -479,8 +478,6 @@ static int ib_umem_odp_map_dma_single_page(
 	}
 
 out:
-	mutex_unlock(&umem->odp_data->umem_mutex);
-
 	/* On Demand Paging - avoid pinning the page */
 	if (umem->context->invalidate_range || !stored_page)
 		put_page(page);
@@ -586,6 +583,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 
 		bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
 		user_virt += npages << PAGE_SHIFT;
+		mutex_lock(&umem->odp_data->umem_mutex);
 		for (j = 0; j < npages; ++j) {
 			ret = ib_umem_odp_map_dma_single_page(
 				umem, k, base_virt_addr, local_page_list[j],
@@ -594,6 +592,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 				break;
 			k++;
 		}
+		mutex_unlock(&umem->odp_data->umem_mutex);
 
 		if (ret < 0) {
 			/* Release left over pages when handling errors. */
@@ -633,12 +632,11 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 	 * faults from completion. We might be racing with other
 	 * invalidations, so we must make sure we free each page only
 	 * once. */
+	mutex_lock(&umem->odp_data->umem_mutex);
 	for (addr = virt; addr < bound; addr += (u64)umem->page_size) {
 		idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
-		mutex_lock(&umem->odp_data->umem_mutex);
 		if (umem->odp_data->page_list[idx]) {
 			struct page *page = umem->odp_data->page_list[idx];
-			struct page *head_page = compound_head(page);
 			dma_addr_t dma = umem->odp_data->dma_list[idx];
 			dma_addr_t dma_addr = dma & ODP_DMA_ADDR_MASK;
 
@@ -646,7 +644,8 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 
 			ib_dma_unmap_page(dev, dma_addr, PAGE_SIZE,
 					  DMA_BIDIRECTIONAL);
-			if (dma & ODP_WRITE_ALLOWED_BIT)
+			if (dma & ODP_WRITE_ALLOWED_BIT) {
+				struct page *head_page = compound_head(page);
 				/*
 				 * set_page_dirty prefers being called with
 				 * the page lock. However, MMU notifiers are
@@ -657,13 +656,14 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 				 * be removed.
 				 */
 				set_page_dirty(head_page);
+			}
 			/* on demand pinning support */
 			if (!umem->context->invalidate_range)
 				put_page(page);
 			umem->odp_data->page_list[idx] = NULL;
 			umem->odp_data->dma_list[idx] = 0;
 		}
-		mutex_unlock(&umem->odp_data->umem_mutex);
 	}
+	mutex_unlock(&umem->odp_data->umem_mutex);
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 928cdd20e2d1..35567fffaa4e 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -99,7 +99,6 @@ struct ib_umad_port {
 };
 
 struct ib_umad_device {
-	int                  start_port, end_port;
 	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
@@ -263,20 +262,23 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 {
 	struct ib_mad_recv_buf *recv_buf;
 	int left, seg_payload, offset, max_seg_payload;
+	size_t seg_size;
 
-	/* We need enough room to copy the first (or only) MAD segment. */
 	recv_buf = &packet->recv_wc->recv_buf;
-	if ((packet->length <= sizeof (*recv_buf->mad) &&
+	seg_size = packet->recv_wc->mad_seg_size;
+
+	/* We need enough room to copy the first (or only) MAD segment. */
+	if ((packet->length <= seg_size &&
 	     count < hdr_size(file) + packet->length) ||
-	    (packet->length > sizeof (*recv_buf->mad) &&
-	     count < hdr_size(file) + sizeof (*recv_buf->mad)))
+	    (packet->length > seg_size &&
+	     count < hdr_size(file) + seg_size))
 		return -EINVAL;
 
 	if (copy_to_user(buf, &packet->mad, hdr_size(file)))
 		return -EFAULT;
 
 	buf += hdr_size(file);
-	seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
+	seg_payload = min_t(int, packet->length, seg_size);
 	if (copy_to_user(buf, recv_buf->mad, seg_payload))
 		return -EFAULT;
 
@@ -293,7 +295,7 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 			return -ENOSPC;
 		}
 		offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class);
-		max_seg_payload = sizeof (struct ib_mad) - offset;
+		max_seg_payload = seg_size - offset;
 
 		for (left = packet->length - seg_payload, buf += seg_payload;
 		     left; left -= seg_payload, buf += seg_payload) {
@@ -426,11 +428,11 @@ static int is_duplicate(struct ib_umad_file *file,
 		 * the same TID, reject the second as a duplicate.  This is more
 		 * restrictive than required by the spec.
 		 */
-		if (!ib_response_mad((struct ib_mad *) hdr)) {
-			if (!ib_response_mad((struct ib_mad *) sent_hdr))
+		if (!ib_response_mad(hdr)) {
+			if (!ib_response_mad(sent_hdr))
 				return 1;
 			continue;
-		} else if (!ib_response_mad((struct ib_mad *) sent_hdr))
+		} else if (!ib_response_mad(sent_hdr))
 			continue;
 
 		if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr))
@@ -451,6 +453,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 	struct ib_rmpp_mad *rmpp_mad;
 	__be64 *tid;
 	int ret, data_len, hdr_len, copy_offset, rmpp_active;
+	u8 base_version;
 
 	if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
 		return -EINVAL;
@@ -517,11 +520,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 		rmpp_active = 0;
 	}
 
+	base_version = ((struct ib_mad_hdr *)&packet->mad.data)->base_version;
 	data_len = count - hdr_size(file) - hdr_len;
 	packet->msg = ib_create_send_mad(agent,
 					 be32_to_cpu(packet->mad.hdr.qpn),
 					 packet->mad.hdr.pkey_index, rmpp_active,
-					 hdr_len, data_len, GFP_KERNEL);
+					 hdr_len, data_len, GFP_KERNEL,
+					 base_version);
 	if (IS_ERR(packet->msg)) {
 		ret = PTR_ERR(packet->msg);
 		goto err_ah;
@@ -1273,16 +1278,10 @@ static void ib_umad_add_one(struct ib_device *device)
 {
 	struct ib_umad_device *umad_dev;
 	int s, e, i;
+	int count = 0;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		s = e = 0;
-	else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
+	s = rdma_start_port(device);
+	e = rdma_end_port(device);
 
 	umad_dev = kzalloc(sizeof *umad_dev +
 			   (e - s + 1) * sizeof (struct ib_umad_port),
@@ -1292,25 +1291,34 @@ static void ib_umad_add_one(struct ib_device *device)
 
 	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
-	umad_dev->start_port = s;
-	umad_dev->end_port   = e;
-
 	for (i = s; i <= e; ++i) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
 		if (ib_umad_init_port(device, i, umad_dev,
 				      &umad_dev->port[i - s]))
 			goto err;
+
+		count++;
 	}
 
+	if (!count)
+		goto free;
+
 	ib_set_client_data(device, &umad_client, umad_dev);
 
 	return;
 
 err:
-	while (--i >= s)
-		ib_umad_kill_port(&umad_dev->port[i - s]);
+	while (--i >= s) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
 
+		ib_umad_kill_port(&umad_dev->port[i - s]);
+	}
+free:
 	kobject_put(&umad_dev->kobj);
 }
 
@@ -1322,8 +1330,10 @@ static void ib_umad_remove_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
-		ib_umad_kill_port(&umad_dev->port[i]);
+	for (i = 0; i <= rdma_end_port(device) - rdma_start_port(device); ++i) {
+		if (rdma_cap_ib_mad(device, i + rdma_start_port(device)))
+			ib_umad_kill_port(&umad_dev->port[i]);
+	}
 
 	kobject_put(&umad_dev->kobj);
 }
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index b716b0815644..ba365b6d1e8d 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -259,5 +259,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
 IB_UVERBS_DECLARE_EX_CMD(query_device);
+IB_UVERBS_DECLARE_EX_CMD(create_cq);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index a9f048990dfc..bbb02ffe87df 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1330,40 +1330,37 @@ ssize_t ib_uverbs_create_comp_channel(struct ib_uverbs_file *file,
 	return in_len;
 }
 
-ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
-			    const char __user *buf, int in_len,
-			    int out_len)
+static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
+				       struct ib_udata *ucore,
+				       struct ib_udata *uhw,
+				       struct ib_uverbs_ex_create_cq *cmd,
+				       size_t cmd_sz,
+				       int (*cb)(struct ib_uverbs_file *file,
+						 struct ib_ucq_object *obj,
+						 struct ib_uverbs_ex_create_cq_resp *resp,
+						 struct ib_udata *udata,
+						 void *context),
+				       void *context)
 {
-	struct ib_uverbs_create_cq      cmd;
-	struct ib_uverbs_create_cq_resp resp;
-	struct ib_udata                 udata;
 	struct ib_ucq_object           *obj;
 	struct ib_uverbs_event_file    *ev_file = NULL;
 	struct ib_cq                   *cq;
 	int                             ret;
+	struct ib_uverbs_ex_create_cq_resp resp;
+	struct ib_cq_init_attr attr = {};
 
-	if (out_len < sizeof resp)
-		return -ENOSPC;
-
-	if (copy_from_user(&cmd, buf, sizeof cmd))
-		return -EFAULT;
-
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
-
-	if (cmd.comp_vector >= file->device->num_comp_vectors)
-		return -EINVAL;
+	if (cmd->comp_vector >= file->device->num_comp_vectors)
+		return ERR_PTR(-EINVAL);
 
 	obj = kmalloc(sizeof *obj, GFP_KERNEL);
 	if (!obj)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	init_uobj(&obj->uobject, cmd.user_handle, file->ucontext, &cq_lock_class);
+	init_uobj(&obj->uobject, cmd->user_handle, file->ucontext, &cq_lock_class);
 	down_write(&obj->uobject.mutex);
 
-	if (cmd.comp_channel >= 0) {
-		ev_file = ib_uverbs_lookup_comp_file(cmd.comp_channel);
+	if (cmd->comp_channel >= 0) {
+		ev_file = ib_uverbs_lookup_comp_file(cmd->comp_channel);
 		if (!ev_file) {
 			ret = -EINVAL;
 			goto err;
@@ -1376,9 +1373,14 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 	INIT_LIST_HEAD(&obj->comp_list);
 	INIT_LIST_HEAD(&obj->async_list);
 
-	cq = file->device->ib_dev->create_cq(file->device->ib_dev, cmd.cqe,
-					     cmd.comp_vector,
-					     file->ucontext, &udata);
+	attr.cqe = cmd->cqe;
+	attr.comp_vector = cmd->comp_vector;
+
+	if (cmd_sz > offsetof(typeof(*cmd), flags) + sizeof(cmd->flags))
+		attr.flags = cmd->flags;
+
+	cq = file->device->ib_dev->create_cq(file->device->ib_dev, &attr,
+					     file->ucontext, uhw);
 	if (IS_ERR(cq)) {
 		ret = PTR_ERR(cq);
 		goto err_file;
@@ -1397,14 +1399,15 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 		goto err_free;
 
 	memset(&resp, 0, sizeof resp);
-	resp.cq_handle = obj->uobject.id;
-	resp.cqe       = cq->cqe;
+	resp.base.cq_handle = obj->uobject.id;
+	resp.base.cqe       = cq->cqe;
 
-	if (copy_to_user((void __user *) (unsigned long) cmd.response,
-			 &resp, sizeof resp)) {
-		ret = -EFAULT;
-		goto err_copy;
-	}
+	resp.response_length = offsetof(typeof(resp), response_length) +
+		sizeof(resp.response_length);
+
+	ret = cb(file, obj, &resp, ucore, context);
+	if (ret)
+		goto err_cb;
 
 	mutex_lock(&file->mutex);
 	list_add_tail(&obj->uobject.list, &file->ucontext->cq_list);
@@ -1414,9 +1417,9 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 
 	up_write(&obj->uobject.mutex);
 
-	return in_len;
+	return obj;
 
-err_copy:
+err_cb:
 	idr_remove_uobj(&ib_uverbs_cq_idr, &obj->uobject);
 
 err_free:
@@ -1428,7 +1431,106 @@ err_file:
 
 err:
 	put_uobj_write(&obj->uobject);
-	return ret;
+
+	return ERR_PTR(ret);
+}
+
+static int ib_uverbs_create_cq_cb(struct ib_uverbs_file *file,
+				  struct ib_ucq_object *obj,
+				  struct ib_uverbs_ex_create_cq_resp *resp,
+				  struct ib_udata *ucore, void *context)
+{
+	if (ib_copy_to_udata(ucore, &resp->base, sizeof(resp->base)))
+		return -EFAULT;
+
+	return 0;
+}
+
+ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
+			    const char __user *buf, int in_len,
+			    int out_len)
+{
+	struct ib_uverbs_create_cq      cmd;
+	struct ib_uverbs_ex_create_cq	cmd_ex;
+	struct ib_uverbs_create_cq_resp resp;
+	struct ib_udata                 ucore;
+	struct ib_udata                 uhw;
+	struct ib_ucq_object           *obj;
+
+	if (out_len < sizeof(resp))
+		return -ENOSPC;
+
+	if (copy_from_user(&cmd, buf, sizeof(cmd)))
+		return -EFAULT;
+
+	INIT_UDATA(&ucore, buf, cmd.response, sizeof(cmd), sizeof(resp));
+
+	INIT_UDATA(&uhw, buf + sizeof(cmd),
+		   (unsigned long)cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd), out_len - sizeof(resp));
+
+	memset(&cmd_ex, 0, sizeof(cmd_ex));
+	cmd_ex.user_handle = cmd.user_handle;
+	cmd_ex.cqe = cmd.cqe;
+	cmd_ex.comp_vector = cmd.comp_vector;
+	cmd_ex.comp_channel = cmd.comp_channel;
+
+	obj = create_cq(file, &ucore, &uhw, &cmd_ex,
+			offsetof(typeof(cmd_ex), comp_channel) +
+			sizeof(cmd.comp_channel), ib_uverbs_create_cq_cb,
+			NULL);
+
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	return in_len;
+}
+
+static int ib_uverbs_ex_create_cq_cb(struct ib_uverbs_file *file,
+				     struct ib_ucq_object *obj,
+				     struct ib_uverbs_ex_create_cq_resp *resp,
+				     struct ib_udata *ucore, void *context)
+{
+	if (ib_copy_to_udata(ucore, resp, resp->response_length))
+		return -EFAULT;
+
+	return 0;
+}
+
+int ib_uverbs_ex_create_cq(struct ib_uverbs_file *file,
+			   struct ib_udata *ucore,
+			   struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_create_cq_resp resp;
+	struct ib_uverbs_ex_create_cq  cmd;
+	struct ib_ucq_object           *obj;
+	int err;
+
+	if (ucore->inlen < sizeof(cmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	if (cmd.comp_mask)
+		return -EINVAL;
+
+	if (cmd.reserved)
+		return -EINVAL;
+
+	if (ucore->outlen < (offsetof(typeof(resp), response_length) +
+			     sizeof(resp.response_length)))
+		return -ENOSPC;
+
+	obj = create_cq(file, ucore, uhw, &cmd,
+			min(ucore->inlen, sizeof(cmd)),
+			ib_uverbs_ex_create_cq_cb, NULL);
+
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	return 0;
 }
 
 ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
@@ -3324,7 +3426,9 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	if (ucore->outlen < resp.response_length)
 		return -ENOSPC;
 
-	err = device->query_device(device, &attr);
+	memset(&attr, 0, sizeof(attr));
+
+	err = device->query_device(device, &attr, uhw);
 	if (err)
 		return err;
 
@@ -3348,6 +3452,18 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 #endif
 	resp.response_length += sizeof(resp.odp_caps);
 
+	if (ucore->outlen < resp.response_length + sizeof(resp.timestamp_mask))
+		goto end;
+
+	resp.timestamp_mask = attr.timestamp_mask;
+	resp.response_length += sizeof(resp.timestamp_mask);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.hca_core_clock))
+		goto end;
+
+	resp.hca_core_clock = attr.hca_core_clock;
+	resp.response_length += sizeof(resp.hca_core_clock);
+
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	if (err)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 88cce9bb72fe..f6eef2da7097 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -124,6 +124,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
 	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device,
+	[IB_USER_VERBS_EX_CMD_CREATE_CQ]	= ib_uverbs_ex_create_cq,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index f93eb8da7b5a..bac3fb406a74 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -48,6 +48,71 @@
 
 #include "core_priv.h"
 
+static const char * const ib_events[] = {
+	[IB_EVENT_CQ_ERR]		= "CQ error",
+	[IB_EVENT_QP_FATAL]		= "QP fatal error",
+	[IB_EVENT_QP_REQ_ERR]		= "QP request error",
+	[IB_EVENT_QP_ACCESS_ERR]	= "QP access error",
+	[IB_EVENT_COMM_EST]		= "communication established",
+	[IB_EVENT_SQ_DRAINED]		= "send queue drained",
+	[IB_EVENT_PATH_MIG]		= "path migration successful",
+	[IB_EVENT_PATH_MIG_ERR]		= "path migration error",
+	[IB_EVENT_DEVICE_FATAL]		= "device fatal error",
+	[IB_EVENT_PORT_ACTIVE]		= "port active",
+	[IB_EVENT_PORT_ERR]		= "port error",
+	[IB_EVENT_LID_CHANGE]		= "LID change",
+	[IB_EVENT_PKEY_CHANGE]		= "P_key change",
+	[IB_EVENT_SM_CHANGE]		= "SM change",
+	[IB_EVENT_SRQ_ERR]		= "SRQ error",
+	[IB_EVENT_SRQ_LIMIT_REACHED]	= "SRQ limit reached",
+	[IB_EVENT_QP_LAST_WQE_REACHED]	= "last WQE reached",
+	[IB_EVENT_CLIENT_REREGISTER]	= "client reregister",
+	[IB_EVENT_GID_CHANGE]		= "GID changed",
+};
+
+const char *ib_event_msg(enum ib_event_type event)
+{
+	size_t index = event;
+
+	return (index < ARRAY_SIZE(ib_events) && ib_events[index]) ?
+			ib_events[index] : "unrecognized event";
+}
+EXPORT_SYMBOL(ib_event_msg);
+
+static const char * const wc_statuses[] = {
+	[IB_WC_SUCCESS]			= "success",
+	[IB_WC_LOC_LEN_ERR]		= "local length error",
+	[IB_WC_LOC_QP_OP_ERR]		= "local QP operation error",
+	[IB_WC_LOC_EEC_OP_ERR]		= "local EE context operation error",
+	[IB_WC_LOC_PROT_ERR]		= "local protection error",
+	[IB_WC_WR_FLUSH_ERR]		= "WR flushed",
+	[IB_WC_MW_BIND_ERR]		= "memory management operation error",
+	[IB_WC_BAD_RESP_ERR]		= "bad response error",
+	[IB_WC_LOC_ACCESS_ERR]		= "local access error",
+	[IB_WC_REM_INV_REQ_ERR]		= "invalid request error",
+	[IB_WC_REM_ACCESS_ERR]		= "remote access error",
+	[IB_WC_REM_OP_ERR]		= "remote operation error",
+	[IB_WC_RETRY_EXC_ERR]		= "transport retry counter exceeded",
+	[IB_WC_RNR_RETRY_EXC_ERR]	= "RNR retry counter exceeded",
+	[IB_WC_LOC_RDD_VIOL_ERR]	= "local RDD violation error",
+	[IB_WC_REM_INV_RD_REQ_ERR]	= "remote invalid RD request",
+	[IB_WC_REM_ABORT_ERR]		= "operation aborted",
+	[IB_WC_INV_EECN_ERR]		= "invalid EE context number",
+	[IB_WC_INV_EEC_STATE_ERR]	= "invalid EE context state",
+	[IB_WC_FATAL_ERR]		= "fatal error",
+	[IB_WC_RESP_TIMEOUT_ERR]	= "response timeout error",
+	[IB_WC_GENERAL_ERR]		= "general error",
+};
+
+const char *ib_wc_status_msg(enum ib_wc_status status)
+{
+	size_t index = status;
+
+	return (index < ARRAY_SIZE(wc_statuses) && wc_statuses[index]) ?
+			wc_statuses[index] : "unrecognized status";
+}
+EXPORT_SYMBOL(ib_wc_status_msg);
+
 __attribute_const__ int ib_rate_to_mult(enum ib_rate rate)
 {
 	switch (rate) {
@@ -192,17 +257,16 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 }
 EXPORT_SYMBOL(ib_create_ah);
 
-int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
-		       struct ib_grh *grh, struct ib_ah_attr *ah_attr)
+int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
+		       const struct ib_wc *wc, const struct ib_grh *grh,
+		       struct ib_ah_attr *ah_attr)
 {
 	u32 flow_class;
 	u16 gid_index;
 	int ret;
-	int is_eth = (rdma_port_get_link_layer(device, port_num) ==
-			IB_LINK_LAYER_ETHERNET);
 
 	memset(ah_attr, 0, sizeof *ah_attr);
-	if (is_eth) {
+	if (rdma_cap_eth_ah(device, port_num)) {
 		if (!(wc->wc_flags & IB_WC_GRH))
 			return -EPROTOTYPE;
 
@@ -244,8 +308,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
 }
 EXPORT_SYMBOL(ib_init_ah_from_wc);
 
-struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
-				   struct ib_grh *grh, u8 port_num)
+struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
+				   const struct ib_grh *grh, u8 port_num)
 {
 	struct ib_ah_attr ah_attr;
 	int ret;
@@ -871,7 +935,7 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
 	union ib_gid  sgid;
 
 	if ((*qp_attr_mask & IB_QP_AV)  &&
-	    (rdma_port_get_link_layer(qp->device, qp_attr->ah_attr.port_num) == IB_LINK_LAYER_ETHERNET)) {
+	    (rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))) {
 		ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num,
 				   qp_attr->ah_attr.grh.sgid_index, &sgid);
 		if (ret)
@@ -1012,11 +1076,12 @@ EXPORT_SYMBOL(ib_destroy_qp);
 struct ib_cq *ib_create_cq(struct ib_device *device,
 			   ib_comp_handler comp_handler,
 			   void (*event_handler)(struct ib_event *, void *),
-			   void *cq_context, int cqe, int comp_vector)
+			   void *cq_context,
+			   const struct ib_cq_init_attr *cq_attr)
 {
 	struct ib_cq *cq;
 
-	cq = device->create_cq(device, cqe, comp_vector, NULL, NULL);
+	cq = device->create_cq(device, cq_attr, NULL, NULL);
 
 	if (!IS_ERR(cq)) {
 		cq->device        = device;
diff --git a/drivers/infiniband/hw/amso1100/c2_provider.c b/drivers/infiniband/hw/amso1100/c2_provider.c
index bdf3507810cb..25c3f0085563 100644
--- a/drivers/infiniband/hw/amso1100/c2_provider.c
+++ b/drivers/infiniband/hw/amso1100/c2_provider.c
@@ -63,13 +63,16 @@
 #include "c2_provider.h"
 #include "c2_user.h"
 
-static int c2_query_device(struct ib_device *ibdev,
-			   struct ib_device_attr *props)
+static int c2_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			   struct ib_udata *uhw)
 {
 	struct c2_dev *c2dev = to_c2dev(ibdev);
 
 	pr_debug("%s:%u\n", __func__, __LINE__);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	*props = c2dev->props;
 	return 0;
 }
@@ -286,13 +289,18 @@ static int c2_destroy_qp(struct ib_qp *ib_qp)
 	return 0;
 }
 
-static struct ib_cq *c2_create_cq(struct ib_device *ibdev, int entries, int vector,
+static struct ib_cq *c2_create_cq(struct ib_device *ibdev,
+				  const struct ib_cq_init_attr *attr,
 				  struct ib_ucontext *context,
 				  struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct c2_cq *cq;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	cq = kmalloc(sizeof(*cq), GFP_KERNEL);
 	if (!cq) {
 		pr_debug("%s: Unable to allocate CQ\n", __func__);
@@ -582,9 +590,13 @@ static int c2_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 static int c2_process_mad(struct ib_device *ibdev,
 			  int mad_flags,
 			  u8 port_num,
-			  struct ib_wc *in_wc,
-			  struct ib_grh *in_grh,
-			  struct ib_mad *in_mad, struct ib_mad *out_mad)
+			  const struct ib_wc *in_wc,
+			  const struct ib_grh *in_grh,
+			  const struct ib_mad_hdr *in_mad,
+			  size_t in_mad_size,
+			  struct ib_mad_hdr *out_mad,
+			  size_t *out_mad_size,
+			  u16 *out_mad_pkey_index)
 {
 	pr_debug("%s:%u\n", __func__, __LINE__);
 	return -ENOSYS;
@@ -757,6 +769,23 @@ static struct net_device *c2_pseudo_netdev_init(struct c2_dev *c2dev)
 	return netdev;
 }
 
+static int c2_port_immutable(struct ib_device *ibdev, u8 port_num,
+			     struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = c2_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int c2_register_device(struct c2_dev *dev)
 {
 	int ret = -ENOMEM;
@@ -820,6 +849,7 @@ int c2_register_device(struct c2_dev *dev)
 	dev->ibdev.reg_phys_mr = c2_reg_phys_mr;
 	dev->ibdev.reg_user_mr = c2_reg_user_mr;
 	dev->ibdev.dereg_mr = c2_dereg_mr;
+	dev->ibdev.get_port_immutable = c2_port_immutable;
 
 	dev->ibdev.alloc_fmr = NULL;
 	dev->ibdev.unmap_fmr = NULL;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 811b24a539c0..b1b73232f217 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -85,9 +85,13 @@ static int iwch_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 static int iwch_process_mad(struct ib_device *ibdev,
 			    int mad_flags,
 			    u8 port_num,
-			    struct ib_wc *in_wc,
-			    struct ib_grh *in_grh,
-			    struct ib_mad *in_mad, struct ib_mad *out_mad)
+			    const struct ib_wc *in_wc,
+			    const struct ib_grh *in_grh,
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }
@@ -138,10 +142,12 @@ static int iwch_destroy_cq(struct ib_cq *ib_cq)
 	return 0;
 }
 
-static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int vector,
-			     struct ib_ucontext *ib_context,
-			     struct ib_udata *udata)
+static struct ib_cq *iwch_create_cq(struct ib_device *ibdev,
+				    const struct ib_cq_init_attr *attr,
+				    struct ib_ucontext *ib_context,
+				    struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct iwch_dev *rhp;
 	struct iwch_cq *chp;
 	struct iwch_create_cq_resp uresp;
@@ -151,6 +157,9 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 	size_t resplen;
 
 	PDBG("%s ib_dev %p entries %d\n", __func__, ibdev, entries);
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	rhp = to_iwch_dev(ibdev);
 	chp = kzalloc(sizeof(*chp), GFP_KERNEL);
 	if (!chp)
@@ -1145,13 +1154,17 @@ static u64 fw_vers_string_to_u64(struct iwch_dev *iwch_dev)
 	       (fw_mic & 0xffff);
 }
 
-static int iwch_query_device(struct ib_device *ibdev,
-			     struct ib_device_attr *props)
+static int iwch_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			     struct ib_udata *uhw)
 {
 
 	struct iwch_dev *dev;
+
 	PDBG("%s ibdev %p\n", __func__, ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	dev = to_iwch_dev(ibdev);
 	memset(props, 0, sizeof *props);
 	memcpy(&props->sys_image_guid, dev->rdev.t3cdev_p->lldev->dev_addr, 6);
@@ -1343,6 +1356,23 @@ static struct device_attribute *iwch_class_attributes[] = {
 	&dev_attr_board_id,
 };
 
+static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = iwch_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int iwch_register_device(struct iwch_dev *dev)
 {
 	int ret;
@@ -1420,6 +1450,7 @@ int iwch_register_device(struct iwch_dev *dev)
 	dev->ibdev.post_recv = iwch_post_receive;
 	dev->ibdev.get_protocol_stats = iwch_get_mib;
 	dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION;
+	dev->ibdev.get_port_immutable = iwch_port_immutable;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 57176ddd4c50..3ad8dc798f52 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -583,6 +583,22 @@ static void c4iw_record_pm_msg(struct c4iw_ep *ep,
 		sizeof(ep->com.mapped_remote_addr));
 }
 
+static int get_remote_addr(struct c4iw_ep *parent_ep, struct c4iw_ep *child_ep)
+{
+	int ret;
+
+	print_addr(&parent_ep->com, __func__, "get_remote_addr parent_ep ");
+	print_addr(&child_ep->com, __func__, "get_remote_addr child_ep ");
+
+	ret = iwpm_get_remote_info(&parent_ep->com.mapped_local_addr,
+				   &child_ep->com.mapped_remote_addr,
+				   &child_ep->com.remote_addr, RDMA_NL_C4IW);
+	if (ret)
+		PDBG("Unable to find remote peer addr info - err %d\n", ret);
+
+	return ret;
+}
+
 static void best_mtu(const unsigned short *mtus, unsigned short mtu,
 		     unsigned int *idx, int use_ts, int ipv6)
 {
@@ -675,7 +691,7 @@ static int send_connect(struct c4iw_ep *ep)
 	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
-		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		opt2 |= T5_ISS_F;
 	}
 	t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
 
@@ -2042,9 +2058,12 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	     status, status2errno(status));
 
 	if (is_neg_adv(status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Connection problems for atid %u status %u (%s)\n",
-			 atid, status, neg_adv_str(status));
+		PDBG("%s Connection problems for atid %u status %u (%s)\n",
+		     __func__, atid, status, neg_adv_str(status));
+		ep->stats.connect_neg_adv++;
+		mutex_lock(&dev->rdev.stats.lock);
+		dev->rdev.stats.neg_adv++;
+		mutex_unlock(&dev->rdev.stats.lock);
 		return 0;
 	}
 
@@ -2214,7 +2233,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 		u32 isn = (prandom_u32() & ~7UL) - 1;
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
-		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		opt2 |= T5_ISS_F;
 		rpl5 = (void *)rpl;
 		memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
 		if (peer2peer)
@@ -2352,27 +2371,57 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	state_set(&child_ep->com, CONNECTING);
 	child_ep->com.dev = dev;
 	child_ep->com.cm_id = NULL;
+
+	/*
+	 * The mapped_local and mapped_remote addresses get setup with
+	 * the actual 4-tuple.  The local address will be based on the
+	 * actual local address of the connection, but on the port number
+	 * of the parent listening endpoint.  The remote address is
+	 * setup based on a query to the IWPM since we don't know what it
+	 * originally was before mapping.  If no mapping was done, then
+	 * mapped_remote == remote, and mapped_local == local.
+	 */
 	if (iptype == 4) {
 		struct sockaddr_in *sin = (struct sockaddr_in *)
-			&child_ep->com.local_addr;
+			&child_ep->com.mapped_local_addr;
+
 		sin->sin_family = PF_INET;
 		sin->sin_port = local_port;
 		sin->sin_addr.s_addr = *(__be32 *)local_ip;
-		sin = (struct sockaddr_in *)&child_ep->com.remote_addr;
+
+		sin = (struct sockaddr_in *)&child_ep->com.local_addr;
+		sin->sin_family = PF_INET;
+		sin->sin_port = ((struct sockaddr_in *)
+				 &parent_ep->com.local_addr)->sin_port;
+		sin->sin_addr.s_addr = *(__be32 *)local_ip;
+
+		sin = (struct sockaddr_in *)&child_ep->com.mapped_remote_addr;
 		sin->sin_family = PF_INET;
 		sin->sin_port = peer_port;
 		sin->sin_addr.s_addr = *(__be32 *)peer_ip;
 	} else {
 		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
-			&child_ep->com.local_addr;
+			&child_ep->com.mapped_local_addr;
+
 		sin6->sin6_family = PF_INET6;
 		sin6->sin6_port = local_port;
 		memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
-		sin6 = (struct sockaddr_in6 *)&child_ep->com.remote_addr;
+
+		sin6 = (struct sockaddr_in6 *)&child_ep->com.local_addr;
+		sin6->sin6_family = PF_INET6;
+		sin6->sin6_port = ((struct sockaddr_in6 *)
+				   &parent_ep->com.local_addr)->sin6_port;
+		memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
+
+		sin6 = (struct sockaddr_in6 *)&child_ep->com.mapped_remote_addr;
 		sin6->sin6_family = PF_INET6;
 		sin6->sin6_port = peer_port;
 		memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16);
 	}
+	memcpy(&child_ep->com.remote_addr, &child_ep->com.mapped_remote_addr,
+	       sizeof(child_ep->com.remote_addr));
+	get_remote_addr(parent_ep, child_ep);
+
 	c4iw_get_ep(&parent_ep->com);
 	child_ep->parent_ep = parent_ep;
 	child_ep->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid));
@@ -2520,9 +2569,13 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 
 	ep = lookup_tid(t, tid);
 	if (is_neg_adv(req->status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Negative advice on abort - tid %u status %d (%s)\n",
-			 ep->hwtid, req->status, neg_adv_str(req->status));
+		PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+		     __func__, ep->hwtid, req->status,
+		     neg_adv_str(req->status));
+		ep->stats.abort_neg_adv++;
+		mutex_lock(&dev->rdev.stats.lock);
+		dev->rdev.stats.neg_adv++;
+		mutex_unlock(&dev->rdev.stats.lock);
 		return 0;
 	}
 	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
@@ -3571,7 +3624,7 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
 	 * TP will ignore any value > 0 for MSS index.
 	 */
 	req->tcb.opt0 = cpu_to_be64(MSS_IDX_V(0xF));
-	req->cookie = (unsigned long)skb;
+	req->cookie = (uintptr_t)skb;
 
 	set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
 	ret = cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
@@ -3931,9 +3984,11 @@ static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb)
 		return 0;
 	}
 	if (is_neg_adv(req->status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Negative advice on abort - tid %u status %d (%s)\n",
-			 ep->hwtid, req->status, neg_adv_str(req->status));
+		PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+		     __func__, ep->hwtid, req->status,
+		     neg_adv_str(req->status));
+		ep->stats.abort_neg_adv++;
+		dev->rdev.stats.neg_adv++;
 		kfree_skb(skb);
 		return 0;
 	}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index ab7692ac2044..c7aab48f07cd 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -55,7 +55,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			FW_RI_RES_WR_NRES_V(1) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_RESET;
@@ -125,7 +125,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			FW_RI_RES_WR_NRES_V(1) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_WRITE;
@@ -158,10 +158,15 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	cq->gen = 1;
 	cq->gts = rdev->lldi.gts_reg;
 	cq->rdev = rdev;
-	if (user) {
-		cq->ugts = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
-					(cq->cqid << rdev->cqshift);
-		cq->ugts &= PAGE_MASK;
+
+	cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS,
+				      &cq->bar2_qid,
+				      user ? &cq->bar2_pa : NULL);
+	if (user && !cq->bar2_va) {
+		pr_warn(MOD "%s: cqid %u not in BAR2 range.\n",
+			pci_name(rdev->lldi.pdev), cq->cqid);
+		ret = -EINVAL;
+		goto err4;
 	}
 	return 0;
 err4:
@@ -859,10 +864,13 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq)
 	return 0;
 }
 
-struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
-			     int vector, struct ib_ucontext *ib_context,
+struct ib_cq *c4iw_create_cq(struct ib_device *ibdev,
+			     const struct ib_cq_init_attr *attr,
+			     struct ib_ucontext *ib_context,
 			     struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct c4iw_dev *rhp;
 	struct c4iw_cq *chp;
 	struct c4iw_create_cq_resp uresp;
@@ -872,6 +880,8 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	struct c4iw_mm_entry *mm, *mm2;
 
 	PDBG("%s ib_dev %p entries %d\n", __func__, ibdev, entries);
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
 
 	rhp = to_c4iw_dev(ibdev);
 
@@ -964,14 +974,13 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 		insert_mmap(ucontext, mm);
 
 		mm2->key = uresp.gts_key;
-		mm2->addr = chp->cq.ugts;
+		mm2->addr = chp->cq.bar2_pa;
 		mm2->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm2);
 	}
 	PDBG("%s cqid 0x%0x chp %p size %u memsize %zu, dma_addr 0x%0llx\n",
 	     __func__, chp->cq.cqid, chp, chp->cq.size,
-	     chp->cq.memsize,
-	     (unsigned long long) chp->cq.dma_addr);
+	     chp->cq.memsize, (unsigned long long) chp->cq.dma_addr);
 	return &chp->ibcq;
 err5:
 	kfree(mm2);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 8fb295e4a9ab..1a297391b54c 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -93,6 +93,7 @@ static struct ibnl_client_cbs c4iw_nl_cb_table[] = {
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
 	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
+	[RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
 	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
 	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
 };
@@ -151,7 +152,7 @@ static int wr_log_show(struct seq_file *seq, void *v)
 	int prev_ts_set = 0;
 	int idx, end;
 
-#define ts2ns(ts) div64_ul((ts) * dev->rdev.lldi.cclk_ps, 1000)
+#define ts2ns(ts) div64_u64((ts) * dev->rdev.lldi.cclk_ps, 1000)
 
 	idx = atomic_read(&dev->rdev.wr_log_idx) &
 		(dev->rdev.wr_log_size - 1);
@@ -489,6 +490,7 @@ static int stats_show(struct seq_file *seq, void *v)
 		   dev->rdev.stats.act_ofld_conn_fails);
 	seq_printf(seq, "PAS_OFLD_CONN_FAILS: %10llu\n",
 		   dev->rdev.stats.pas_ofld_conn_fails);
+	seq_printf(seq, "NEG_ADV_RCVD: %10llu\n", dev->rdev.stats.neg_adv);
 	seq_printf(seq, "AVAILABLE IRD: %10u\n", dev->avail_ird);
 	return 0;
 }
@@ -560,10 +562,13 @@ static int dump_ep(int id, void *p, void *data)
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
+			      "conn_na %u abort_na %u "
 			      "%pI4:%d/%d <-> %pI4:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
+			      ep->stats.connect_neg_adv,
+			      ep->stats.abort_neg_adv,
 			      &lsin->sin_addr, ntohs(lsin->sin_port),
 			      ntohs(mapped_lsin->sin_port),
 			      &rsin->sin_addr, ntohs(rsin->sin_port),
@@ -581,10 +586,13 @@ static int dump_ep(int id, void *p, void *data)
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
+			      "conn_na %u abort_na %u "
 			      "%pI6:%d/%d <-> %pI6:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
+			      ep->stats.connect_neg_adv,
+			      ep->stats.abort_neg_adv,
 			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
 			      ntohs(mapped_lsin6->sin6_port),
 			      &rsin6->sin6_addr, ntohs(rsin6->sin6_port),
@@ -765,12 +773,29 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	c4iw_init_dev_ucontext(rdev, &rdev->uctx);
 
 	/*
-	 * qpshift is the number of bits to shift the qpid left in order
-	 * to get the correct address of the doorbell for that qp.
+	 * This implementation assumes udb_density == ucq_density!  Eventually
+	 * we might need to support this but for now fail the open. Also the
+	 * cqid and qpid range must match for now.
 	 */
-	rdev->qpshift = PAGE_SHIFT - ilog2(rdev->lldi.udb_density);
+	if (rdev->lldi.udb_density != rdev->lldi.ucq_density) {
+		pr_err(MOD "%s: unsupported udb/ucq densities %u/%u\n",
+		       pci_name(rdev->lldi.pdev), rdev->lldi.udb_density,
+		       rdev->lldi.ucq_density);
+		err = -EINVAL;
+		goto err1;
+	}
+	if (rdev->lldi.vr->qp.start != rdev->lldi.vr->cq.start ||
+	    rdev->lldi.vr->qp.size != rdev->lldi.vr->cq.size) {
+		pr_err(MOD "%s: unsupported qp and cq id ranges "
+		       "qp start %u size %u cq start %u size %u\n",
+		       pci_name(rdev->lldi.pdev), rdev->lldi.vr->qp.start,
+		       rdev->lldi.vr->qp.size, rdev->lldi.vr->cq.size,
+		       rdev->lldi.vr->cq.size);
+		err = -EINVAL;
+		goto err1;
+	}
+
 	rdev->qpmask = rdev->lldi.udb_density - 1;
-	rdev->cqshift = PAGE_SHIFT - ilog2(rdev->lldi.ucq_density);
 	rdev->cqmask = rdev->lldi.ucq_density - 1;
 	PDBG("%s dev %s stag start 0x%0x size 0x%0x num stags %d "
 	     "pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x "
@@ -784,14 +809,12 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	     rdev->lldi.vr->qp.size,
 	     rdev->lldi.vr->cq.start,
 	     rdev->lldi.vr->cq.size);
-	PDBG("udb len 0x%x udb base %llx db_reg %p gts_reg %p qpshift %lu "
-	     "qpmask 0x%x cqshift %lu cqmask 0x%x\n",
+	PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p "
+	     "qpmask 0x%x cqmask 0x%x\n",
 	     (unsigned)pci_resource_len(rdev->lldi.pdev, 2),
-	     (u64)pci_resource_start(rdev->lldi.pdev, 2),
-	     rdev->lldi.db_reg,
-	     rdev->lldi.gts_reg,
-	     rdev->qpshift, rdev->qpmask,
-	     rdev->cqshift, rdev->cqmask);
+	     (void *)pci_resource_start(rdev->lldi.pdev, 2),
+	     rdev->lldi.db_reg, rdev->lldi.gts_reg,
+	     rdev->qpmask, rdev->cqmask);
 
 	if (c4iw_num_stags(rdev) == 0) {
 		err = -EINVAL;
@@ -1355,7 +1378,7 @@ static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
 					  t4_sq_host_wq_pidx(&qp->wq),
 					  t4_sq_wq_size(&qp->wq));
 		if (ret) {
-			pr_err(KERN_ERR MOD "%s: Fatal error - "
+			pr_err(MOD "%s: Fatal error - "
 			       "DB overflow recovery failed - "
 			       "error syncing SQ qid %u\n",
 			       pci_name(ctx->lldi.pdev), qp->wq.sq.qid);
@@ -1371,7 +1394,7 @@ static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
 					  t4_rq_wq_size(&qp->wq));
 
 		if (ret) {
-			pr_err(KERN_ERR MOD "%s: Fatal error - "
+			pr_err(MOD "%s: Fatal error - "
 			       "DB overflow recovery failed - "
 			       "error syncing RQ qid %u\n",
 			       pci_name(ctx->lldi.pdev), qp->wq.rq.qid);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index d87e1650f643..cc77844fada3 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -137,6 +137,7 @@ struct c4iw_stats {
 	u64  tcam_full;
 	u64  act_ofld_conn_fails;
 	u64  pas_ofld_conn_fails;
+	u64  neg_adv;
 };
 
 struct c4iw_hw_queue {
@@ -164,9 +165,7 @@ struct wr_log_entry {
 
 struct c4iw_rdev {
 	struct c4iw_resource resource;
-	unsigned long qpshift;
 	u32 qpmask;
-	unsigned long cqshift;
 	u32 cqmask;
 	struct c4iw_dev_ucontext uctx;
 	struct gen_pool *pbl_pool;
@@ -814,6 +813,11 @@ struct c4iw_listen_ep {
 	int backlog;
 };
 
+struct c4iw_ep_stats {
+	unsigned connect_neg_adv;
+	unsigned abort_neg_adv;
+};
+
 struct c4iw_ep {
 	struct c4iw_ep_common com;
 	struct c4iw_ep *parent_ep;
@@ -846,6 +850,7 @@ struct c4iw_ep {
 	unsigned int retry_count;
 	int snd_win;
 	int rcv_win;
+	struct c4iw_ep_stats stats;
 };
 
 static inline void print_addr(struct c4iw_ep_common *epc, const char *func,
@@ -985,10 +990,10 @@ int c4iw_reregister_phys_mem(struct ib_mr *mr,
 				     int acc, u64 *iova_start);
 int c4iw_dereg_mr(struct ib_mr *ib_mr);
 int c4iw_destroy_cq(struct ib_cq *ib_cq);
-struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
-					int vector,
-					struct ib_ucontext *ib_context,
-					struct ib_udata *udata);
+struct ib_cq *c4iw_create_cq(struct ib_device *ibdev,
+			     const struct ib_cq_init_attr *attr,
+			     struct ib_ucontext *ib_context,
+			     struct ib_udata *udata);
 int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata);
 int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int c4iw_destroy_qp(struct ib_qp *ib_qp);
@@ -1025,6 +1030,9 @@ void c4iw_ev_dispatch(struct c4iw_dev *dev, struct t4_cqe *err_cqe);
 
 extern struct cxgb4_client t4c_client;
 extern c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS];
+void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid,
+			      enum cxgb4_bar2_qtype qtype,
+			      unsigned int *pbar2_qid, u64 *pbar2_pa);
 extern void c4iw_log_wr_stats(struct t4_wq *wq, struct t4_cqe *cqe);
 extern int c4iw_wr_log;
 extern int db_fc_threshold;
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 3ef0cf9f5c44..cff815b91707 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -144,7 +144,7 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		if (i == (num_wqe-1)) {
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
 						    FW_WR_COMPL_F);
-			req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
+			req->wr.wr_lo = (__force __be64)&wr_wait;
 		} else
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR));
 		req->wr.wr_mid = cpu_to_be32(
@@ -676,12 +676,12 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
 	mhp->attr.zbva = 0;
 	mhp->attr.va_fbo = 0;
 	mhp->attr.page_size = 0;
-	mhp->attr.len = ~0UL;
+	mhp->attr.len = ~0ULL;
 	mhp->attr.pbl_size = 0;
 
 	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, php->pdid,
 			      FW_RI_STAG_NSMR, mhp->attr.perms,
-			      mhp->attr.mw_bind_enable, 0, 0, ~0UL, 0, 0, 0);
+			      mhp->attr.mw_bind_enable, 0, 0, ~0ULL, 0, 0, 0);
 	if (ret)
 		goto err1;
 
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 66bd6a2ad83b..6eee3d385541 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -80,9 +80,13 @@ static int c4iw_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 }
 
 static int c4iw_process_mad(struct ib_device *ibdev, int mad_flags,
-			    u8 port_num, struct ib_wc *in_wc,
-			    struct ib_grh *in_grh, struct ib_mad *in_mad,
-			    struct ib_mad *out_mad)
+			    u8 port_num, const struct ib_wc *in_wc,
+			    const struct ib_grh *in_grh,
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }
@@ -301,13 +305,17 @@ static int c4iw_query_gid(struct ib_device *ibdev, u8 port, int index,
 	return 0;
 }
 
-static int c4iw_query_device(struct ib_device *ibdev,
-			     struct ib_device_attr *props)
+static int c4iw_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			     struct ib_udata *uhw)
 {
 
 	struct c4iw_dev *dev;
+
 	PDBG("%s ibdev %p\n", __func__, ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	dev = to_c4iw_dev(ibdev);
 	memset(props, 0, sizeof *props);
 	memcpy(&props->sys_image_guid, dev->rdev.lldi.ports[0]->dev_addr, 6);
@@ -445,10 +453,10 @@ static int c4iw_get_mib(struct ib_device *ibdev,
 
 	cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6);
 	memset(stats, 0, sizeof *stats);
-	stats->iw.tcpInSegs = v4.tcpInSegs + v6.tcpInSegs;
-	stats->iw.tcpOutSegs = v4.tcpOutSegs + v6.tcpOutSegs;
-	stats->iw.tcpRetransSegs = v4.tcpRetransSegs + v6.tcpRetransSegs;
-	stats->iw.tcpOutRsts = v4.tcpOutRsts + v6.tcpOutSegs;
+	stats->iw.tcpInSegs = v4.tcp_in_segs + v6.tcp_in_segs;
+	stats->iw.tcpOutSegs = v4.tcp_out_segs + v6.tcp_out_segs;
+	stats->iw.tcpRetransSegs = v4.tcp_retrans_segs + v6.tcp_retrans_segs;
+	stats->iw.tcpOutRsts = v4.tcp_out_rsts + v6.tcp_out_rsts;
 
 	return 0;
 }
@@ -465,6 +473,23 @@ static struct device_attribute *c4iw_class_attributes[] = {
 	&dev_attr_board_id,
 };
 
+static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = c4iw_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int c4iw_register_device(struct c4iw_dev *dev)
 {
 	int ret;
@@ -542,6 +567,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.post_recv = c4iw_post_receive;
 	dev->ibdev.get_protocol_stats = c4iw_get_mib;
 	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
+	dev->ibdev.get_port_immutable = c4iw_port_immutable;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 15cae5a31018..6517e1208ccb 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -165,6 +165,29 @@ static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	return 0;
 }
 
+/*
+ * Determine the BAR2 virtual address and qid. If pbar2_pa is not NULL,
+ * then this is a user mapping so compute the page-aligned physical address
+ * for mapping.
+ */
+void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid,
+			      enum cxgb4_bar2_qtype qtype,
+			      unsigned int *pbar2_qid, u64 *pbar2_pa)
+{
+	u64 bar2_qoffset;
+	int ret;
+
+	ret = cxgb4_bar2_sge_qregs(rdev->lldi.ports[0], qid, qtype,
+				   pbar2_pa ? 1 : 0,
+				   &bar2_qoffset, pbar2_qid);
+	if (ret)
+		return NULL;
+
+	if (pbar2_pa)
+		*pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK;
+	return rdev->bar2_kva + bar2_qoffset;
+}
+
 static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		     struct t4_cq *rcq, struct t4_cq *scq,
 		     struct c4iw_dev_ucontext *uctx)
@@ -236,25 +259,23 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	dma_unmap_addr_set(&wq->rq, mapping, wq->rq.dma_addr);
 
 	wq->db = rdev->lldi.db_reg;
-	wq->gts = rdev->lldi.gts_reg;
-	if (user || is_t5(rdev->lldi.adapter_type)) {
-		u32 off;
 
-		off = (wq->sq.qid << rdev->qpshift) & PAGE_MASK;
-		if (user) {
-			wq->sq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
-		} else {
-			off += 128 * (wq->sq.qid & rdev->qpmask) + 8;
-			wq->sq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
-		}
-		off = (wq->rq.qid << rdev->qpshift) & PAGE_MASK;
-		if (user) {
-			wq->rq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
-		} else {
-			off += 128 * (wq->rq.qid & rdev->qpmask) + 8;
-			wq->rq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
-		}
+	wq->sq.bar2_va = c4iw_bar2_addrs(rdev, wq->sq.qid, T4_BAR2_QTYPE_EGRESS,
+					 &wq->sq.bar2_qid,
+					 user ? &wq->sq.bar2_pa : NULL);
+	wq->rq.bar2_va = c4iw_bar2_addrs(rdev, wq->rq.qid, T4_BAR2_QTYPE_EGRESS,
+					 &wq->rq.bar2_qid,
+					 user ? &wq->rq.bar2_pa : NULL);
+
+	/*
+	 * User mode must have bar2 access.
+	 */
+	if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) {
+		pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n",
+			pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid);
+		goto free_dma;
 	}
+
 	wq->rdev = rdev;
 	wq->rq.msn = 1;
 
@@ -275,7 +296,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 			FW_RI_RES_WR_NRES_V(2) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.sqrq.restype = FW_RI_RES_TYPE_SQ;
 	res->u.sqrq.op = FW_RI_RES_OP_WRITE;
@@ -336,10 +357,9 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	if (ret)
 		goto free_dma;
 
-	PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p squdb 0x%lx rqudb 0x%lx\n",
+	PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p sq_bar2_addr %p rq_bar2_addr %p\n",
 	     __func__, wq->sq.qid, wq->rq.qid, wq->db,
-	     (__force unsigned long) wq->sq.udb,
-	     (__force unsigned long) wq->rq.udb);
+	     wq->sq.bar2_va, wq->rq.bar2_va);
 
 	return 0;
 free_dma:
@@ -1209,7 +1229,7 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	wqe->flowid_len16 = cpu_to_be32(
 		FW_WR_FLOWID_V(ep->hwtid) |
 		FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
-	wqe->cookie = (unsigned long) &ep->com.wr_wait;
+	wqe->cookie = (uintptr_t)&ep->com.wr_wait;
 
 	wqe->u.fini.type = FW_RI_TYPE_FINI;
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
@@ -1279,7 +1299,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 		FW_WR_FLOWID_V(qhp->ep->hwtid) |
 		FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
 
-	wqe->cookie = (unsigned long) &qhp->ep->com.wr_wait;
+	wqe->cookie = (uintptr_t)&qhp->ep->com.wr_wait;
 
 	wqe->u.init.type = FW_RI_TYPE_INIT;
 	wqe->u.init.mpareqbit_p2ptype =
@@ -1766,11 +1786,11 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		mm2->len = PAGE_ALIGN(qhp->wq.rq.memsize);
 		insert_mmap(ucontext, mm2);
 		mm3->key = uresp.sq_db_gts_key;
-		mm3->addr = (__force unsigned long) qhp->wq.sq.udb;
+		mm3->addr = (__force unsigned long)qhp->wq.sq.bar2_pa;
 		mm3->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm3);
 		mm4->key = uresp.rq_db_gts_key;
-		mm4->addr = (__force unsigned long) qhp->wq.rq.udb;
+		mm4->addr = (__force unsigned long)qhp->wq.rq.bar2_pa;
 		mm4->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm4);
 		if (mm5) {
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 871cdcac7be2..274a7ab13bef 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -33,6 +33,7 @@
 
 #include "t4_hw.h"
 #include "t4_regs.h"
+#include "t4_values.h"
 #include "t4_msg.h"
 #include "t4fw_ri_api.h"
 
@@ -290,8 +291,10 @@ struct t4_sq {
 	unsigned long phys_addr;
 	struct t4_swsqe *sw_sq;
 	struct t4_swsqe *oldest_read;
-	u64 __iomem *udb;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
 	size_t memsize;
+	u32 bar2_qid;
 	u32 qid;
 	u16 in_use;
 	u16 size;
@@ -314,8 +317,10 @@ struct t4_rq {
 	dma_addr_t dma_addr;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 	struct t4_swrqe *sw_rq;
-	u64 __iomem *udb;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
 	size_t memsize;
+	u32 bar2_qid;
 	u32 qid;
 	u32 msn;
 	u32 rqt_hwaddr;
@@ -332,7 +337,6 @@ struct t4_wq {
 	struct t4_sq sq;
 	struct t4_rq rq;
 	void __iomem *db;
-	void __iomem *gts;
 	struct c4iw_rdev *rdev;
 	int flushed;
 };
@@ -457,15 +461,18 @@ static inline void t4_ring_sq_db(struct t4_wq *wq, u16 inc, u8 t5,
 
 	/* Flush host queue memory writes. */
 	wmb();
-	if (t5) {
-		if (inc == 1 && wqe) {
+	if (wq->sq.bar2_va) {
+		if (inc == 1 && wq->sq.bar2_qid == 0 && wqe) {
 			PDBG("%s: WC wq->sq.pidx = %d\n",
 			     __func__, wq->sq.pidx);
-			pio_copy(wq->sq.udb + 7, (void *)wqe);
+			pio_copy((u64 __iomem *)
+				 (wq->sq.bar2_va + SGE_UDB_WCDOORBELL),
+				 (u64 *)wqe);
 		} else {
 			PDBG("%s: DB wq->sq.pidx = %d\n",
 			     __func__, wq->sq.pidx);
-			writel(PIDX_T5_V(inc), wq->sq.udb);
+			writel(PIDX_T5_V(inc) | QID_V(wq->sq.bar2_qid),
+			       wq->sq.bar2_va + SGE_UDB_KDOORBELL);
 		}
 
 		/* Flush user doorbell area writes. */
@@ -481,15 +488,18 @@ static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc, u8 t5,
 
 	/* Flush host queue memory writes. */
 	wmb();
-	if (t5) {
-		if (inc == 1 && wqe) {
+	if (wq->rq.bar2_va) {
+		if (inc == 1 && wq->rq.bar2_qid == 0 && wqe) {
 			PDBG("%s: WC wq->rq.pidx = %d\n",
 			     __func__, wq->rq.pidx);
-			pio_copy(wq->rq.udb + 7, (void *)wqe);
+			pio_copy((u64 __iomem *)
+				 (wq->rq.bar2_va + SGE_UDB_WCDOORBELL),
+				 (void *)wqe);
 		} else {
 			PDBG("%s: DB wq->rq.pidx = %d\n",
 			     __func__, wq->rq.pidx);
-			writel(PIDX_T5_V(inc), wq->rq.udb);
+			writel(PIDX_T5_V(inc) | QID_V(wq->rq.bar2_qid),
+			       wq->rq.bar2_va + SGE_UDB_KDOORBELL);
 		}
 
 		/* Flush user doorbell area writes. */
@@ -534,11 +544,14 @@ struct t4_cq {
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 	struct t4_cqe *sw_queue;
 	void __iomem *gts;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
+	u32 bar2_qid;
 	struct c4iw_rdev *rdev;
-	u64 ugts;
 	size_t memsize;
 	__be64 bits_type_ts;
 	u32 cqid;
+	u32 qid_mask;
 	int vector;
 	u16 size; /* including status page */
 	u16 cidx;
@@ -551,6 +564,15 @@ struct t4_cq {
 	unsigned long flags;
 };
 
+static inline void write_gts(struct t4_cq *cq, u32 val)
+{
+	if (cq->bar2_va)
+		writel(val | INGRESSQID_V(cq->bar2_qid),
+		       cq->bar2_va + SGE_UDB_GTS);
+	else
+		writel(val | INGRESSQID_V(cq->cqid), cq->gts);
+}
+
 static inline int t4_clear_cq_armed(struct t4_cq *cq)
 {
 	return test_and_clear_bit(CQ_ARMED, &cq->flags);
@@ -562,14 +584,12 @@ static inline int t4_arm_cq(struct t4_cq *cq, int se)
 
 	set_bit(CQ_ARMED, &cq->flags);
 	while (cq->cidx_inc > CIDXINC_M) {
-		val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid);
-		writel(val, cq->gts);
+		val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7);
+		write_gts(cq, val);
 		cq->cidx_inc -= CIDXINC_M;
 	}
-	val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6) |
-	      INGRESSQID_V(cq->cqid);
-	writel(val, cq->gts);
+	val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6);
+	write_gts(cq, val);
 	cq->cidx_inc = 0;
 	return 0;
 }
@@ -600,9 +620,8 @@ static inline void t4_hwcq_consume(struct t4_cq *cq)
 	if (++cq->cidx_inc == (cq->size >> 4) || cq->cidx_inc == CIDXINC_M) {
 		u32 val;
 
-		val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid);
-		writel(val, cq->gts);
+		val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7);
+		write_gts(cq, val);
 		cq->cidx_inc = 0;
 	}
 	if (++cq->cidx == cq->size) {
diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index 5e53327fc647..343e8daf2270 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -848,6 +848,8 @@ enum {                     /* TCP congestion control algorithms */
 #define CONG_CNTRL_V(x) ((x) << CONG_CNTRL_S)
 #define CONG_CNTRL_G(x) (((x) >> CONG_CNTRL_S) & CONG_CNTRL_M)
 
-#define CONG_CNTRL_VALID   (1 << 18)
+#define T5_ISS_S    18
+#define T5_ISS_V(x) ((x) << T5_ISS_S)
+#define T5_ISS_F    T5_ISS_V(1U)
 
 #endif /* _T4FW_RI_API_H_ */
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c
index 8cc837537768..9b68b175069b 100644
--- a/drivers/infiniband/hw/ehca/ehca_cq.c
+++ b/drivers/infiniband/hw/ehca/ehca_cq.c
@@ -113,10 +113,12 @@ struct ehca_qp *ehca_cq_get_qp(struct ehca_cq *cq, int real_qp_num)
 	return ret;
 }
 
-struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
+struct ib_cq *ehca_create_cq(struct ib_device *device,
+			     const struct ib_cq_init_attr *attr,
 			     struct ib_ucontext *context,
 			     struct ib_udata *udata)
 {
+	int cqe = attr->cqe;
 	static const u32 additional_cqe = 20;
 	struct ib_cq *cq;
 	struct ehca_cq *my_cq;
@@ -131,6 +133,9 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 	int ipz_rc, i;
 	unsigned long flags;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (cqe >= 0xFFFFFFFF - 64 - additional_cqe)
 		return ERR_PTR(-EINVAL);
 
diff --git a/drivers/infiniband/hw/ehca/ehca_hca.c b/drivers/infiniband/hw/ehca/ehca_hca.c
index 9ed4d2588304..e8b1bb65797a 100644
--- a/drivers/infiniband/hw/ehca/ehca_hca.c
+++ b/drivers/infiniband/hw/ehca/ehca_hca.c
@@ -50,7 +50,8 @@ static unsigned int limit_uint(unsigned int value)
 	return min_t(unsigned int, value, INT_MAX);
 }
 
-int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
+int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+		      struct ib_udata *uhw)
 {
 	int i, ret = 0;
 	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca,
@@ -71,6 +72,9 @@ int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
 		IB_DEVICE_PORT_ACTIVE_EVENT,  HCA_CAP_PORT_ACTIVE_EVENT,
 	};
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");
diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/infiniband/hw/ehca/ehca_iverbs.h
index 22f79afa7fc1..80e6a3d5df3e 100644
--- a/drivers/infiniband/hw/ehca/ehca_iverbs.h
+++ b/drivers/infiniband/hw/ehca/ehca_iverbs.h
@@ -44,11 +44,15 @@
 
 #include "ehca_classes.h"
 
-int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props);
+int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+		      struct ib_udata *uhw);
 
 int ehca_query_port(struct ib_device *ibdev, u8 port,
 		    struct ib_port_attr *props);
 
+enum rdma_protocol_type
+ehca_query_protocol(struct ib_device *device, u8 port_num);
+
 int ehca_query_sma_attr(struct ehca_shca *shca, u8 port,
 			struct ehca_sma_attr *attr);
 
@@ -126,7 +130,8 @@ int ehca_destroy_eq(struct ehca_shca *shca, struct ehca_eq *eq);
 void *ehca_poll_eq(struct ehca_shca *shca, struct ehca_eq *eq);
 
 
-struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
+struct ib_cq *ehca_create_cq(struct ib_device *device,
+			     const struct ib_cq_init_attr *attr,
 			     struct ib_ucontext *context,
 			     struct ib_udata *udata);
 
@@ -188,9 +193,10 @@ int ehca_dealloc_ucontext(struct ib_ucontext *context);
 int ehca_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		     struct ib_wc *in_wc, struct ib_grh *in_grh,
-		     struct ib_mad *in_mad,
-		     struct ib_mad *out_mad);
+		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index);
 
 void ehca_poll_eqs(unsigned long data);
 
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index cd8d290a09fc..8246418cd4e0 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -46,6 +46,7 @@
 
 #include <linux/notifier.h>
 #include <linux/memory.h>
+#include <rdma/ib_mad.h>
 #include "ehca_classes.h"
 #include "ehca_iverbs.h"
 #include "ehca_mrmw.h"
@@ -431,6 +432,24 @@ init_node_guid1:
 	return ret;
 }
 
+static int ehca_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ehca_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static int ehca_init_device(struct ehca_shca *shca)
 {
 	int ret;
@@ -510,6 +529,7 @@ static int ehca_init_device(struct ehca_shca *shca)
 	shca->ib_device.process_mad	    = ehca_process_mad;
 	shca->ib_device.mmap		    = ehca_mmap;
 	shca->ib_device.dma_ops		    = &ehca_dma_mapping_ops;
+	shca->ib_device.get_port_immutable  = ehca_port_immutable;
 
 	if (EHCA_BMASK_GET(HCA_CAP_SRQ, shca->hca_cap)) {
 		shca->ib_device.uverbs_cmd_mask |=
@@ -534,6 +554,7 @@ static int ehca_create_aqp1(struct ehca_shca *shca, u32 port)
 	struct ib_cq *ibcq;
 	struct ib_qp *ibqp;
 	struct ib_qp_init_attr qp_init_attr;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	if (sport->ibcq_aqp1) {
@@ -541,7 +562,9 @@ static int ehca_create_aqp1(struct ehca_shca *shca, u32 port)
 		return -EPERM;
 	}
 
-	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void *)(-1), 10, 0);
+	cq_attr.cqe = 10;
+	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void *)(-1),
+			    &cq_attr);
 	if (IS_ERR(ibcq)) {
 		ehca_err(&shca->ib_device, "Cannot create AQP1 CQ.");
 		return PTR_ERR(ibcq);
diff --git a/drivers/infiniband/hw/ehca/ehca_mcast.c b/drivers/infiniband/hw/ehca/ehca_mcast.c
index 120aedf9f989..cec181532924 100644
--- a/drivers/infiniband/hw/ehca/ehca_mcast.c
+++ b/drivers/infiniband/hw/ehca/ehca_mcast.c
@@ -77,7 +77,7 @@ int ehca_attach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 		return -EINVAL;
 	}
 
-	memcpy(&my_gid.raw, gid->raw, sizeof(union ib_gid));
+	memcpy(&my_gid, gid->raw, sizeof(union ib_gid));
 
 	subnet_prefix = be64_to_cpu(my_gid.global.subnet_prefix);
 	interface_id = be64_to_cpu(my_gid.global.interface_id);
@@ -114,7 +114,7 @@ int ehca_detach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 		return -EINVAL;
 	}
 
-	memcpy(&my_gid.raw, gid->raw, sizeof(union ib_gid));
+	memcpy(&my_gid, gid->raw, sizeof(union ib_gid));
 
 	subnet_prefix = be64_to_cpu(my_gid.global.subnet_prefix);
 	interface_id = be64_to_cpu(my_gid.global.interface_id);
diff --git a/drivers/infiniband/hw/ehca/ehca_sqp.c b/drivers/infiniband/hw/ehca/ehca_sqp.c
index dba8f9f8b996..12b5bc23832b 100644
--- a/drivers/infiniband/hw/ehca/ehca_sqp.c
+++ b/drivers/infiniband/hw/ehca/ehca_sqp.c
@@ -140,10 +140,10 @@ struct vertcfl {
 } __attribute__ ((packed));
 
 static int ehca_process_perf(struct ib_device *ibdev, u8 port_num,
-			     struct ib_wc *in_wc, struct ib_grh *in_grh,
-			     struct ib_mad *in_mad, struct ib_mad *out_mad)
+			     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			     const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
-	struct ib_perf *in_perf = (struct ib_perf *)in_mad;
+	const struct ib_perf *in_perf = (const struct ib_perf *)in_mad;
 	struct ib_perf *out_perf = (struct ib_perf *)out_mad;
 	struct ib_class_port_info *poi =
 		(struct ib_class_port_info *)out_perf->data;
@@ -187,8 +187,8 @@ static int ehca_process_perf(struct ib_device *ibdev, u8 port_num,
 
 		/* if request was globally routed, copy route info */
 		if (in_grh) {
-			struct vertcfl *vertcfl =
-				(struct vertcfl *)&in_grh->version_tclass_flow;
+			const struct vertcfl *vertcfl =
+				(const struct vertcfl *)&in_grh->version_tclass_flow;
 			memcpy(poi->redirect_gid, in_grh->dgid.raw,
 			       sizeof(poi->redirect_gid));
 			tcslfl->tc        = vertcfl->tc;
@@ -217,10 +217,17 @@ perf_reply:
 }
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		     struct ib_wc *in_wc, struct ib_grh *in_grh,
-		     struct ib_mad *in_mad, struct ib_mad *out_mad)
+		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc)
 		return IB_MAD_RESULT_FAILURE;
diff --git a/drivers/infiniband/hw/ipath/Kconfig b/drivers/infiniband/hw/ipath/Kconfig
index 1d9bb115cbf6..8fe54ff00580 100644
--- a/drivers/infiniband/hw/ipath/Kconfig
+++ b/drivers/infiniband/hw/ipath/Kconfig
@@ -9,3 +9,6 @@ config INFINIBAND_IPATH
 	as IP-over-InfiniBand as well as with userspace applications
 	(in conjunction with InfiniBand userspace access).
 	For QLogic PCIe QLE based cards, use the QIB driver instead.
+
+	If you have this hardware you will need to boot with PAT disabled
+	on your x86-64 systems, use the nopat kernel parameter.
diff --git a/drivers/infiniband/hw/ipath/ipath_cq.c b/drivers/infiniband/hw/ipath/ipath_cq.c
index 0416c6c0e126..e9dd9112e718 100644
--- a/drivers/infiniband/hw/ipath/ipath_cq.c
+++ b/drivers/infiniband/hw/ipath/ipath_cq.c
@@ -188,7 +188,7 @@ static void send_complete(unsigned long data)
 /**
  * ipath_create_cq - create a completion queue
  * @ibdev: the device this completion queue is attached to
- * @entries: the minimum size of the completion queue
+ * @attr: creation attributes
  * @context: unused by the InfiniPath driver
  * @udata: unused by the InfiniPath driver
  *
@@ -197,16 +197,21 @@ static void send_complete(unsigned long data)
  *
  * Called by ib_create_cq() in the generic verbs code.
  */
-struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries, int comp_vector,
+struct ib_cq *ipath_create_cq(struct ib_device *ibdev,
+			      const struct ib_cq_init_attr *attr,
 			      struct ib_ucontext *context,
 			      struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct ipath_ibdev *dev = to_idev(ibdev);
 	struct ipath_cq *cq;
 	struct ipath_cq_wc *wc;
 	struct ib_cq *ret;
 	u32 sz;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > ib_ipath_max_cqes) {
 		ret = ERR_PTR(-EINVAL);
 		goto done;
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index bd0caedafe99..2d7e503d13cb 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -42,6 +42,9 @@
 #include <linux/bitmap.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
+#endif
 
 #include "ipath_kernel.h"
 #include "ipath_verbs.h"
@@ -395,6 +398,14 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	unsigned long long addr;
 	u32 bar0 = 0, bar1 = 0;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+		ret = -ENODEV;
+		goto bail;
+	}
+#endif
+
 	dd = ipath_alloc_devdata(pdev);
 	if (IS_ERR(dd)) {
 		ret = PTR_ERR(dd);
@@ -542,6 +553,7 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dd->ipath_kregbase = __ioremap(addr, len,
 		(_PAGE_NO_CACHE|_PAGE_WRITETHRU));
 #else
+	/* XXX: split this properly to enable on PAT */
 	dd->ipath_kregbase = ioremap_nocache(addr, len);
 #endif
 
@@ -587,12 +599,8 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = ipath_enable_wc(dd);
 
-	if (ret) {
-		ipath_dev_err(dd, "Write combining not enabled "
-			      "(err %d): performance may be poor\n",
-			      -ret);
+	if (ret)
 		ret = 0;
-	}
 
 	ipath_verify_pioperf(dd);
 
diff --git a/drivers/infiniband/hw/ipath/ipath_kernel.h b/drivers/infiniband/hw/ipath/ipath_kernel.h
index e08db7020cd4..f0f947122779 100644
--- a/drivers/infiniband/hw/ipath/ipath_kernel.h
+++ b/drivers/infiniband/hw/ipath/ipath_kernel.h
@@ -463,9 +463,7 @@ struct ipath_devdata {
 	/* offset in HT config space of slave/primary interface block */
 	u8 ipath_ht_slave_off;
 	/* for write combining settings */
-	unsigned long ipath_wc_cookie;
-	unsigned long ipath_wc_base;
-	unsigned long ipath_wc_len;
+	int wc_cookie;
 	/* ref count for each pkey */
 	atomic_t ipath_pkeyrefs[4];
 	/* shadow copy of struct page *'s for exp tid pages */
diff --git a/drivers/infiniband/hw/ipath/ipath_mad.c b/drivers/infiniband/hw/ipath/ipath_mad.c
index e890e5ba0e01..948188e37f95 100644
--- a/drivers/infiniband/hw/ipath/ipath_mad.c
+++ b/drivers/infiniband/hw/ipath/ipath_mad.c
@@ -1257,7 +1257,7 @@ static int recv_pma_set_portcounters_ext(struct ib_pma_mad *pmp,
 }
 
 static int process_subn(struct ib_device *ibdev, int mad_flags,
-			u8 port_num, struct ib_mad *in_mad,
+			u8 port_num, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_smp *smp = (struct ib_smp *)out_mad;
@@ -1389,7 +1389,7 @@ bail:
 }
 
 static int process_perf(struct ib_device *ibdev, u8 port_num,
-			struct ib_mad *in_mad,
+			const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_pma_mad *pmp = (struct ib_pma_mad *)out_mad;
@@ -1490,10 +1490,17 @@ bail:
  * This is called by the ib_mad module.
  */
 int ipath_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		      struct ib_wc *in_wc, struct ib_grh *in_grh,
-		      struct ib_mad *in_mad, struct ib_mad *out_mad)
+		      const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c
index 44ea9390417c..48253b839a6f 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.c
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.c
@@ -1495,11 +1495,14 @@ bail:
 	return 0;
 }
 
-static int ipath_query_device(struct ib_device *ibdev,
-			      struct ib_device_attr *props)
+static int ipath_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			      struct ib_udata *uhw)
 {
 	struct ipath_ibdev *dev = to_idev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(props, 0, sizeof(*props));
 
 	props->device_cap_flags = IB_DEVICE_BAD_PKEY_CNTR |
@@ -1980,6 +1983,24 @@ static int disable_timer(struct ipath_devdata *dd)
 	return 0;
 }
 
+static int ipath_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ipath_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 /**
  * ipath_register_ib_device - register our device with the infiniband core
  * @dd: the device data structure
@@ -2179,6 +2200,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd)
 	dev->process_mad = ipath_process_mad;
 	dev->mmap = ipath_mmap;
 	dev->dma_ops = &ipath_dma_mapping_ops;
+	dev->get_port_immutable = ipath_port_immutable;
 
 	snprintf(dev->node_desc, sizeof(dev->node_desc),
 		 IPATH_IDSTR " %s", init_utsname()->nodename);
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.h b/drivers/infiniband/hw/ipath/ipath_verbs.h
index ae6cff4abffc..ec167e545e15 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.h
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.h
@@ -701,9 +701,11 @@ static inline void ipath_schedule_send(struct ipath_qp *qp)
 int ipath_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad, struct ib_mad *out_mad);
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 
 /*
  * Compare the lower 24 bits of the two values.
@@ -807,7 +809,8 @@ void ipath_cq_enter(struct ipath_cq *cq, struct ib_wc *entry, int sig);
 
 int ipath_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
 
-struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries, int comp_vector,
+struct ib_cq *ipath_create_cq(struct ib_device *ibdev,
+			      const struct ib_cq_init_attr *attr,
 			      struct ib_ucontext *context,
 			      struct ib_udata *udata);
 
diff --git a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
index 4ad0b932df1f..7b6e4c843e19 100644
--- a/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
+++ b/drivers/infiniband/hw/ipath/ipath_wc_x86_64.c
@@ -37,7 +37,6 @@
  */
 
 #include <linux/pci.h>
-#include <asm/mtrr.h>
 #include <asm/processor.h>
 
 #include "ipath_kernel.h"
@@ -122,27 +121,14 @@ int ipath_enable_wc(struct ipath_devdata *dd)
 	}
 
 	if (!ret) {
-		int cookie;
-		ipath_cdbg(VERBOSE, "Setting mtrr for chip to WC "
-			   "(addr %llx, len=0x%llx)\n",
-			   (unsigned long long) pioaddr,
-			   (unsigned long long) piolen);
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
-		if (cookie < 0) {
-			{
-				dev_info(&dd->pcidev->dev,
-					 "mtrr_add()  WC for PIO bufs "
-					 "failed (%d)\n",
-					 cookie);
-				ret = -EINVAL;
-			}
-		} else {
-			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC, "
-				   "cookie is %d\n", cookie);
-			dd->ipath_wc_cookie = cookie;
-			dd->ipath_wc_base = (unsigned long) pioaddr;
-			dd->ipath_wc_len = (unsigned long) piolen;
-		}
+		dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+		if (dd->wc_cookie < 0) {
+			ipath_dev_err(dd, "Seting mtrr failed on PIO buffers\n");
+			ret = -ENODEV;
+		} else if (dd->wc_cookie == 0)
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC not needed\n");
+		else
+			ipath_cdbg(VERBOSE, "Set mtrr for chip to WC\n");
 	}
 
 	return ret;
@@ -154,16 +140,5 @@ int ipath_enable_wc(struct ipath_devdata *dd)
  */
 void ipath_disable_wc(struct ipath_devdata *dd)
 {
-	if (dd->ipath_wc_cookie) {
-		int r;
-		ipath_cdbg(VERBOSE, "undoing WCCOMB on pio buffers\n");
-		r = mtrr_del(dd->ipath_wc_cookie, dd->ipath_wc_base,
-			     dd->ipath_wc_len);
-		if (r < 0)
-			dev_info(&dd->pcidev->dev,
-				 "mtrr_del(%lx, %lx, %lx) failed: %d\n",
-				 dd->ipath_wc_cookie, dd->ipath_wc_base,
-				 dd->ipath_wc_len, r);
-		dd->ipath_wc_cookie = 0; /* even on failure */
-	}
+	arch_phys_wc_del(dd->wc_cookie);
 }
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 0f00204d2ece..21cb41a60fe8 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -189,7 +189,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev,
 {
 	int i;
 	u64 guid_indexes;
-	int slave_id;
+	int slave_id, slave_port;
 	enum slave_port_state new_state;
 	enum slave_port_state prev_state;
 	__be64 tmp_cur_ag, form_cache_ag;
@@ -217,6 +217,11 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev,
 		slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ;
 		if (slave_id >= dev->dev->persist->num_vfs + 1)
 			return;
+
+		slave_port = mlx4_phys_to_slave_port(dev->dev, slave_id, port_num);
+		if (slave_port < 0) /* this port isn't available for the VF */
+			continue;
+
 		tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE];
 		form_cache_ag = get_cached_alias_guid(dev, port_num,
 					(NUM_ALIAS_GUID_IN_REC * block_num) + i);
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 0176caa5792c..36eb3d012b6d 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -166,10 +166,14 @@ err_buf:
 	return err;
 }
 
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector,
+#define CQ_CREATE_FLAGS_SUPPORTED IB_CQ_FLAGS_TIMESTAMP_COMPLETION
+struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
 				struct ib_ucontext *context,
 				struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_cq *cq;
 	struct mlx4_uar *uar;
@@ -178,6 +182,9 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	if (entries < 1 || entries > dev->dev->caps.max_cqes)
 		return ERR_PTR(-EINVAL);
 
+	if (attr->flags & ~CQ_CREATE_FLAGS_SUPPORTED)
+		return ERR_PTR(-EINVAL);
+
 	cq = kmalloc(sizeof *cq, GFP_KERNEL);
 	if (!cq)
 		return ERR_PTR(-ENOMEM);
@@ -188,6 +195,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	spin_lock_init(&cq->lock);
 	cq->resize_buf = NULL;
 	cq->resize_umem = NULL;
+	cq->create_flags = attr->flags;
 	INIT_LIST_HEAD(&cq->send_qp_list);
 	INIT_LIST_HEAD(&cq->recv_qp_list);
 
@@ -231,7 +239,8 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 		vector = dev->eq_table[vector % ibdev->num_comp_vectors];
 
 	err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
-			    cq->db.dma, &cq->mcq, vector, 0, 0);
+			    cq->db.dma, &cq->mcq, vector, 0,
+			    !!(cq->create_flags & IB_CQ_FLAGS_TIMESTAMP_COMPLETION));
 	if (err)
 		goto err_dbmap;
 
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 9cd2b002d7ae..85a50df2f203 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -64,14 +64,6 @@ enum {
 #define GUID_TBL_BLK_NUM_ENTRIES 8
 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES)
 
-/* Counters should be saturate once they reach their maximum value */
-#define ASSIGN_32BIT_COUNTER(counter, value) do {\
-	if ((value) > U32_MAX)			 \
-		counter = cpu_to_be32(U32_MAX); \
-	else					 \
-		counter = cpu_to_be32(value);	 \
-} while (0)
-
 struct mlx4_mad_rcv_buf {
 	struct ib_grh grh;
 	u8 payload[256];
@@ -111,8 +103,9 @@ __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx)
 }
 
 int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
-		 int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad)
+		 int port, const struct ib_wc *in_wc,
+		 const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad)
 {
 	struct mlx4_cmd_mailbox *inmailbox, *outmailbox;
 	void *inbox;
@@ -220,7 +213,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
  * Snoop SM MADs for port info, GUID info, and  P_Key table sets, so we can
  * synthesize LID change, Client-Rereg, GID change, and P_Key change events.
  */
-static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
+static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad *mad,
 		      u16 prev_lid)
 {
 	struct ib_port_info *pinfo;
@@ -356,7 +349,7 @@ static void node_desc_override(struct ib_device *dev,
 	}
 }
 
-static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *mad)
+static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, const struct ib_mad *mad)
 {
 	int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
 	struct ib_mad_send_buf *send_buf;
@@ -366,7 +359,8 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
-					      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+					      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+					      IB_MGMT_BASE_VERSION);
 		if (IS_ERR(send_buf))
 			return;
 		/*
@@ -722,8 +716,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 }
 
 static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
 	u16 slid, prev_lid = 0;
 	int err;
@@ -825,34 +819,28 @@ static void edit_counter(struct mlx4_counter *cnt,
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
-	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_counter counter_stats;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	int err;
-	u32 inmod = dev->counters[port_num - 1] & 0xffff;
-	u8 mode;
 
 	if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
 		return -EINVAL;
 
-	mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
-	if (IS_ERR(mailbox))
-		return IB_MAD_RESULT_FAILURE;
-
-	err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0,
-			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
-			   MLX4_CMD_WRAPPED);
+	memset(&counter_stats, 0, sizeof(counter_stats));
+	err = mlx4_get_counter_stats(dev->dev,
+				     dev->counters[port_num - 1].index,
+				     &counter_stats, 0);
 	if (err)
 		err = IB_MAD_RESULT_FAILURE;
 	else {
 		memset(out_mad->data, 0, sizeof out_mad->data);
-		mode = ((struct mlx4_counter *)mailbox->buf)->counter_mode;
-		switch (mode & 0xf) {
+		switch (counter_stats.counter_mode & 0xf) {
 		case 0:
-			edit_counter(mailbox->buf,
-						(void *)(out_mad->data + 40));
+			edit_counter(&counter_stats,
+				     (void *)(out_mad->data + 40));
 			err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
 			break;
 		default:
@@ -860,19 +848,27 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		}
 	}
 
-	mlx4_free_cmd_mailbox(dev->dev, mailbox);
-
 	return err;
 }
 
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
+	struct mlx4_ib_dev *dev = to_mdev(ibdev);
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
+
 	switch (rdma_port_get_link_layer(ibdev, port_num)) {
 	case IB_LINK_LAYER_INFINIBAND:
-		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
-				      in_grh, in_mad, out_mad);
+		if (!mlx4_is_slave(dev->dev))
+			return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
+					      in_grh, in_mad, out_mad);
 	case IB_LINK_LAYER_ETHERNET:
 		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
 					  in_grh, in_mad, out_mad);
@@ -1365,14 +1361,17 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	 * stadard address handle by decoding the tunnelled mlx4_ah fields */
 	memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av));
 	ah.ibah.device = ctx->ib_dev;
+
+	port = be32_to_cpu(ah.av.ib.port_pd) >> 24;
+	port = mlx4_slave_convert_port(dev->dev, slave, port);
+	if (port < 0)
+		return;
+	ah.av.ib.port_pd = cpu_to_be32(port << 24 | (be32_to_cpu(ah.av.ib.port_pd) & 0xffffff));
+
 	mlx4_ib_query_ah(&ah.ibah, &ah_attr);
 	if (ah_attr.ah_flags & IB_AH_GRH)
 		fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
 
-	port = mlx4_slave_convert_port(dev->dev, slave, ah_attr.port_num);
-	if (port < 0)
-		return;
-	ah_attr.port_num = port;
 	memcpy(ah_attr.dmac, tunnel->hdr.mac, 6);
 	ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan);
 	/* if slave have default vlan use it */
@@ -1773,6 +1772,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 			       int create_tun, struct mlx4_ib_demux_pv_ctx *ctx)
 {
 	int ret, cq_size;
+	struct ib_cq_init_attr cq_attr = {};
 
 	if (ctx->state != DEMUX_PV_STATE_DOWN)
 		return -EEXIST;
@@ -1801,8 +1801,9 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 	if (ctx->has_smi)
 		cq_size *= 2;
 
+	cq_attr.cqe = cq_size;
 	ctx->cq = ib_create_cq(ctx->ib_dev, mlx4_ib_tunnel_comp_handler,
-			       NULL, ctx, cq_size, 0);
+			       NULL, ctx, &cq_attr);
 	if (IS_ERR(ctx->cq)) {
 		ret = PTR_ERR(ctx->cq);
 		pr_err("Couldn't create tunnel CQ (%d)\n", ret);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 57070c529dfb..067a691ecbed 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -132,14 +132,35 @@ static int num_ib_ports(struct mlx4_dev *dev)
 }
 
 static int mlx4_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
 	int err = -ENOMEM;
 	int have_ib_ports;
+	struct mlx4_uverbs_ex_query_device cmd;
+	struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0};
+	struct mlx4_clock_params clock_params;
 
+	if (uhw->inlen) {
+		if (uhw->inlen < sizeof(cmd))
+			return -EINVAL;
+
+		err = ib_copy_from_udata(&cmd, uhw, sizeof(cmd));
+		if (err)
+			return err;
+
+		if (cmd.comp_mask)
+			return -EINVAL;
+
+		if (cmd.reserved)
+			return -EINVAL;
+	}
+
+	resp.response_length = offsetof(typeof(resp), response_length) +
+		sizeof(resp.response_length);
 	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
 	if (!in_mad || !out_mad)
@@ -229,7 +250,24 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
 					   props->max_mcast_grp;
 	props->max_map_per_fmr = dev->dev->caps.max_fmr_maps;
+	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
+	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
+
+	err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
+	if (err)
+		goto out;
+
+	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
+		resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
+		resp.response_length += sizeof(resp.hca_core_clock_offset);
+		resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+	}
 
+	if (uhw->outlen) {
+		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
+		if (err)
+			goto out;
+	}
 out:
 	kfree(in_mad);
 	kfree(out_mad);
@@ -712,8 +750,24 @@ static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 				       dev->dev->caps.num_uars,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
-	} else
+	} else if (vma->vm_pgoff == 3) {
+		struct mlx4_clock_params params;
+		int ret = mlx4_get_internal_clock_params(dev->dev, &params);
+
+		if (ret)
+			return ret;
+
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		if (io_remap_pfn_range(vma, vma->vm_start,
+				       (pci_resource_start(dev->dev->persist->pdev,
+							   params.bar) +
+					params.offset)
+				       >> PAGE_SHIFT,
+				       PAGE_SIZE, vma->vm_page_prot))
+			return -EAGAIN;
+	} else {
 		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -758,6 +812,7 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_udata *udata)
 {
 	struct mlx4_ib_xrcd *xrcd;
+	struct ib_cq_init_attr cq_attr = {};
 	int err;
 
 	if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
@@ -777,7 +832,8 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev,
 		goto err2;
 	}
 
-	xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, 1, 0);
+	cq_attr.cqe = 1;
+	xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, &cq_attr);
 	if (IS_ERR(xrcd->cq)) {
 		err = PTR_ERR(xrcd->cq);
 		goto err3;
@@ -1090,7 +1146,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 
 	ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
-			   MLX4_CMD_NATIVE);
+			   MLX4_CMD_WRAPPED);
 	if (ret == -ENOMEM)
 		pr_err("mcg table is full. Fail to register network rule.\n");
 	else if (ret == -ENXIO)
@@ -1107,7 +1163,7 @@ static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id)
 	int err;
 	err = mlx4_cmd(dev, reg_id, 0, 0,
 		       MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
-		       MLX4_CMD_NATIVE);
+		       MLX4_CMD_WRAPPED);
 	if (err)
 		pr_err("Fail to detach network rule. registration id = 0x%llx\n",
 		       reg_id);
@@ -1185,7 +1241,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 					    &mflow->reg_id[i].id);
 		if (err)
 			goto err_create_flow;
-		i++;
 		if (is_bonded) {
 			/* Application always sees one port so the mirror rule
 			 * must be on port #2
@@ -1200,6 +1255,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 			j++;
 		}
 
+		i++;
 	}
 
 	if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) {
@@ -1207,7 +1263,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 					       &mflow->reg_id[i].id);
 		if (err)
 			goto err_create_flow;
-		i++;
+
 		if (is_bonded) {
 			flow_attr->port = 2;
 			err = mlx4_ib_tunnel_steer_add(qp, flow_attr,
@@ -1218,6 +1274,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 			j++;
 		}
 		/* function to create mirror rule */
+		i++;
 	}
 
 	return &mflow->ibflow;
@@ -1569,8 +1626,7 @@ static void reset_gids_task(struct work_struct *work)
 			       MLX4_CMD_TIME_CLASS_B,
 			       MLX4_CMD_WRAPPED);
 		if (err)
-			pr_warn(KERN_WARNING
-				"set port %d command failed\n", gw->port);
+			pr_warn("set port %d command failed\n", gw->port);
 	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
@@ -2042,77 +2098,75 @@ static void init_pkeys(struct mlx4_ib_dev *ibdev)
 
 static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 {
-	char name[80];
-	int eq_per_port = 0;
-	int added_eqs = 0;
-	int total_eqs = 0;
-	int i, j, eq;
-
-	/* Legacy mode or comp_pool is not large enough */
-	if (dev->caps.comp_pool == 0 ||
-	    dev->caps.num_ports > dev->caps.comp_pool)
-		return;
-
-	eq_per_port = dev->caps.comp_pool / dev->caps.num_ports;
-
-	/* Init eq table */
-	added_eqs = 0;
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
-		added_eqs += eq_per_port;
-
-	total_eqs = dev->caps.num_comp_vectors + added_eqs;
+	int i, j, eq = 0, total_eqs = 0;
 
-	ibdev->eq_table = kzalloc(total_eqs * sizeof(int), GFP_KERNEL);
+	ibdev->eq_table = kcalloc(dev->caps.num_comp_vectors,
+				  sizeof(ibdev->eq_table[0]), GFP_KERNEL);
 	if (!ibdev->eq_table)
 		return;
 
-	ibdev->eq_added = added_eqs;
-
-	eq = 0;
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) {
-		for (j = 0; j < eq_per_port; j++) {
-			snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s",
-				 i, j, dev->persist->pdev->bus->name);
-			/* Set IRQ for specific name (per ring) */
-			if (mlx4_assign_eq(dev, name, NULL,
-					   &ibdev->eq_table[eq])) {
-				/* Use legacy (same as mlx4_en driver) */
-				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
-				ibdev->eq_table[eq] =
-					(eq % dev->caps.num_comp_vectors);
-			}
-			eq++;
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		for (j = 0; j < mlx4_get_eqs_per_port(dev, i);
+		     j++, total_eqs++) {
+			if (i > 1 &&  mlx4_is_eq_shared(dev, total_eqs))
+				continue;
+			ibdev->eq_table[eq] = total_eqs;
+			if (!mlx4_assign_eq(dev, i,
+					    &ibdev->eq_table[eq]))
+				eq++;
+			else
+				ibdev->eq_table[eq] = -1;
 		}
 	}
 
-	/* Fill the reset of the vector with legacy EQ */
-	for (i = 0, eq = added_eqs; i < dev->caps.num_comp_vectors; i++)
-		ibdev->eq_table[eq++] = i;
+	for (i = eq; i < dev->caps.num_comp_vectors;
+	     ibdev->eq_table[i++] = -1)
+		;
 
 	/* Advertise the new number of EQs to clients */
-	ibdev->ib_dev.num_comp_vectors = total_eqs;
+	ibdev->ib_dev.num_comp_vectors = eq;
 }
 
 static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 {
 	int i;
+	int total_eqs = ibdev->ib_dev.num_comp_vectors;
 
-	/* no additional eqs were added */
+	/* no eqs were allocated */
 	if (!ibdev->eq_table)
 		return;
 
 	/* Reset the advertised EQ number */
-	ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
+	ibdev->ib_dev.num_comp_vectors = 0;
 
-	/* Free only the added eqs */
-	for (i = 0; i < ibdev->eq_added; i++) {
-		/* Don't free legacy eqs if used */
-		if (ibdev->eq_table[i] <= dev->caps.num_comp_vectors)
-			continue;
+	for (i = 0; i < total_eqs; i++)
 		mlx4_release_eq(dev, ibdev->eq_table[i]);
-	}
 
 	kfree(ibdev->eq_table);
+	ibdev->eq_table = NULL;
+}
+
+static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mlx4_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+
+	if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND)
+		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	else
+		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
 }
 
 static void *mlx4_ib_add(struct mlx4_dev *dev)
@@ -2124,6 +2178,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	struct mlx4_ib_iboe *iboe;
 	int ib_num_ports = 0;
 	int num_req_counters;
+	int allocated;
+	u32 counter_index;
 
 	pr_info_once("%s", mlx4_ib_version);
 
@@ -2242,6 +2298,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.attach_mcast	= mlx4_ib_mcg_attach;
 	ibdev->ib_dev.detach_mcast	= mlx4_ib_mcg_detach;
 	ibdev->ib_dev.process_mad	= mlx4_ib_process_mad;
+	ibdev->ib_dev.get_port_immutable = mlx4_port_immutable;
 
 	if (!mlx4_is_slave(ibdev->dev)) {
 		ibdev->ib_dev.alloc_fmr		= mlx4_ib_fmr_alloc;
@@ -2279,6 +2336,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
 	}
 
+	ibdev->ib_dev.uverbs_ex_cmd_mask |=
+		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) |
+		(1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ);
+
 	mlx4_ib_alloc_eqs(dev, ibdev);
 
 	spin_lock_init(&iboe->lock);
@@ -2289,19 +2350,31 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports;
 	for (i = 0; i < num_req_counters; ++i) {
 		mutex_init(&ibdev->qp1_proxy_lock[i]);
+		allocated = 0;
 		if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
 						IB_LINK_LAYER_ETHERNET) {
-			err = mlx4_counter_alloc(ibdev->dev, &ibdev->counters[i]);
+			err = mlx4_counter_alloc(ibdev->dev, &counter_index);
+			/* if failed to allocate a new counter, use default */
 			if (err)
-				ibdev->counters[i] = -1;
-		} else {
-			ibdev->counters[i] = -1;
+				counter_index =
+					mlx4_get_default_counter_index(dev,
+								       i + 1);
+			else
+				allocated = 1;
+		} else { /* IB_LINK_LAYER_INFINIBAND use the default counter */
+			counter_index = mlx4_get_default_counter_index(dev,
+								       i + 1);
 		}
+		ibdev->counters[i].index = counter_index;
+		ibdev->counters[i].allocated = allocated;
+		pr_info("counter index %d for port %d allocated %d\n",
+			counter_index, i + 1, allocated);
 	}
 	if (mlx4_is_bonded(dev))
-		for (i = 1; i < ibdev->num_ports ; ++i)
-			ibdev->counters[i] = ibdev->counters[0];
-
+		for (i = 1; i < ibdev->num_ports ; ++i) {
+			ibdev->counters[i].index = ibdev->counters[0].index;
+			ibdev->counters[i].allocated = 0;
+		}
 
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
 		ib_num_ports++;
@@ -2441,10 +2514,12 @@ err_steer_qp_release:
 		mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
 				      ibdev->steer_qpn_count);
 err_counter:
-	for (; i; --i)
-		if (ibdev->counters[i - 1] != -1)
-			mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]);
-
+	for (i = 0; i < ibdev->num_ports; ++i) {
+		if (ibdev->counters[i].index != -1 &&
+		    ibdev->counters[i].allocated)
+			mlx4_counter_free(ibdev->dev,
+					  ibdev->counters[i].index);
+	}
 err_map:
 	iounmap(ibdev->uar_map);
 
@@ -2561,8 +2636,9 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)
-		if (ibdev->counters[p] != -1)
-			mlx4_counter_free(ibdev->dev, ibdev->counters[p]);
+		if (ibdev->counters[p].index != -1 &&
+		    ibdev->counters[p].allocated)
+			mlx4_counter_free(ibdev->dev, ibdev->counters[p].index);
 	mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB)
 		mlx4_CLOSE_PORT(dev, p);
 
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index fce3934372a1..334387f63358 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -110,6 +110,7 @@ struct mlx4_ib_cq {
 	struct mutex		resize_mutex;
 	struct ib_umem	       *umem;
 	struct ib_umem	       *resize_umem;
+	int			create_flags;
 	/* List of qps that it serves.*/
 	struct list_head		send_qp_list;
 	struct list_head		recv_qp_list;
@@ -503,6 +504,11 @@ struct mlx4_ib_iov_port {
 	struct mlx4_ib_iov_sysfs_attr mcg_dentry;
 };
 
+struct counter_index {
+	u32		index;
+	u8		allocated;
+};
+
 struct mlx4_ib_dev {
 	struct ib_device	ib_dev;
 	struct mlx4_dev	       *dev;
@@ -521,9 +527,8 @@ struct mlx4_ib_dev {
 	struct mutex		cap_mask_mutex;
 	bool			ib_active;
 	struct mlx4_ib_iboe	iboe;
-	int			counters[MLX4_MAX_PORTS];
+	struct counter_index    counters[MLX4_MAX_PORTS];
 	int		       *eq_table;
-	int			eq_added;
 	struct kobject	       *iov_parent;
 	struct kobject	       *ports_parent;
 	struct kobject	       *dev_ports_parent[MLX4_MFUNC_MAX];
@@ -555,6 +560,21 @@ struct mlx4_ib_qp_tunnel_init_attr {
 	u8 port;
 };
 
+struct mlx4_uverbs_ex_query_device {
+	__u32 comp_mask;
+	__u32 reserved;
+};
+
+enum query_device_resp_mask {
+	QUERY_DEVICE_RESP_MASK_TIMESTAMP = 1UL << 0,
+};
+
+struct mlx4_uverbs_ex_query_device_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u64 hca_core_clock_offset;
+};
+
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
 {
 	return container_of(ibdev, struct mlx4_ib_dev, ib_dev);
@@ -668,7 +688,8 @@ void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
 
 int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector,
+struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
 				struct ib_ucontext *context,
 				struct ib_udata *udata);
 int mlx4_ib_destroy_cq(struct ib_cq *cq);
@@ -706,11 +727,13 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		      struct ib_recv_wr **bad_wr);
 
 int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
-		 int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad);
+		 int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad);
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags,	u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 int mlx4_ib_mad_init(struct mlx4_ib_dev *dev);
 void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev);
 
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 02fc91c68027..c5a3a5f0de41 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1539,12 +1539,13 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
-		if (dev->counters[qp->port - 1] != -1) {
+		if (dev->counters[qp->port - 1].index != -1) {
 			context->pri_path.counter_index =
-						dev->counters[qp->port - 1];
+					dev->counters[qp->port - 1].index;
 			optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX;
 		} else
-			context->pri_path.counter_index = 0xff;
+			context->pri_path.counter_index =
+				MLX4_SINK_COUNTER_INDEX(dev->dev);
 
 		if (qp->flags & MLX4_IB_QP_NETIF) {
 			mlx4_ib_steer_qp_reg(dev, qp, 1);
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index 10df386c6344..bce263b92821 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,8 +1,6 @@
 config MLX5_INFINIBAND
 	tristate "Mellanox Connect-IB HCA support"
-	depends on NETDEVICES && ETHERNET && PCI
-	select NET_VENDOR_MELLANOX
-	select MLX5_CORE
+	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
 	---help---
 	  This driver provides low-level InfiniBand support for
 	  Mellanox Connect-IB PCI Express host channel adapters (HCAs).
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 2ee6b1051975..5c9eeea62805 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -590,8 +590,7 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf,
 {
 	int err;
 
-	err = mlx5_buf_alloc(dev->mdev, nent * cqe_size,
-			     PAGE_SIZE * 2, &buf->buf);
+	err = mlx5_buf_alloc(dev->mdev, nent * cqe_size, &buf->buf);
 	if (err)
 		return err;
 
@@ -736,10 +735,13 @@ static void destroy_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
 	mlx5_db_free(dev->mdev, &cq->db);
 }
 
-struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
-				int vector, struct ib_ucontext *context,
+struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
 				struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct mlx5_create_cq_mbox_in *cqb = NULL;
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_ib_cq *cq;
@@ -750,11 +752,14 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
 	int eqn;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 0)
 		return ERR_PTR(-EINVAL);
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries > dev->mdev->caps.gen.max_cqes)
+	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))
 		return ERR_PTR(-EINVAL);
 
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -921,7 +926,7 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 	int err;
 	u32 fsel;
 
-	if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
+	if (!MLX5_CAP_GEN(dev->mdev, cq_moderation))
 		return -ENOSYS;
 
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
@@ -1076,7 +1081,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 	int uninitialized_var(cqe_size);
 	unsigned long flags;
 
-	if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
+	if (!MLX5_CAP_GEN(dev->mdev, cq_resize)) {
 		pr_info("Firmware does not support resize CQ\n");
 		return -ENOSYS;
 	}
@@ -1085,7 +1090,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 		return -EINVAL;
 
 	entries = roundup_pow_of_two(entries + 1);
-	if (entries > dev->mdev->caps.gen.max_cqes + 1)
+	if (entries >  (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
 		return -EINVAL;
 
 	if (entries == ibcq->cqe + 1)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 9cf9a37bb5ff..01fc97db45d6 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -41,8 +41,8 @@ enum {
 };
 
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
-		 u8 port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad)
+		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad)
 {
 	u8 op_modifier = 0;
 
@@ -58,11 +58,18 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 }
 
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
 	u16 slid;
 	int err;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 
@@ -129,7 +136,7 @@ int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port)
 
 	packet_error = be16_to_cpu(out_mad->status);
 
-	dev->mdev->caps.gen.ext_port_cap[port - 1] = (!err && !packet_error) ?
+	dev->mdev->port_caps[port - 1].ext_port_cap = (!err && !packet_error) ?
 		MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO : 0;
 
 out:
@@ -137,3 +144,300 @@ out:
 	kfree(out_mad);
 	return err;
 }
+
+int mlx5_query_mad_ifc_smp_attr_node_info(struct ib_device *ibdev,
+					  struct ib_smp *out_mad)
+{
+	struct ib_smp *in_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	if (!in_mad)
+		return -ENOMEM;
+
+	init_query_mad(in_mad);
+	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+
+	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, 1, NULL, NULL, in_mad,
+			   out_mad);
+
+	kfree(in_mad);
+	return err;
+}
+
+int mlx5_query_mad_ifc_system_image_guid(struct ib_device *ibdev,
+					 __be64 *sys_image_guid)
+{
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!out_mad)
+		return -ENOMEM;
+
+	err = mlx5_query_mad_ifc_smp_attr_node_info(ibdev, out_mad);
+	if (err)
+		goto out;
+
+	memcpy(sys_image_guid, out_mad->data + 4, 8);
+
+out:
+	kfree(out_mad);
+
+	return err;
+}
+
+int mlx5_query_mad_ifc_max_pkeys(struct ib_device *ibdev,
+				 u16 *max_pkeys)
+{
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!out_mad)
+		return -ENOMEM;
+
+	err = mlx5_query_mad_ifc_smp_attr_node_info(ibdev, out_mad);
+	if (err)
+		goto out;
+
+	*max_pkeys = be16_to_cpup((__be16 *)(out_mad->data + 28));
+
+out:
+	kfree(out_mad);
+
+	return err;
+}
+
+int mlx5_query_mad_ifc_vendor_id(struct ib_device *ibdev,
+				 u32 *vendor_id)
+{
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!out_mad)
+		return -ENOMEM;
+
+	err = mlx5_query_mad_ifc_smp_attr_node_info(ibdev, out_mad);
+	if (err)
+		goto out;
+
+	*vendor_id = be32_to_cpup((__be32 *)(out_mad->data + 36)) & 0xffff;
+
+out:
+	kfree(out_mad);
+
+	return err;
+}
+
+int mlx5_query_mad_ifc_node_desc(struct mlx5_ib_dev *dev, char *node_desc)
+{
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	init_query_mad(in_mad);
+	in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
+
+	err = mlx5_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad);
+	if (err)
+		goto out;
+
+	memcpy(node_desc, out_mad->data, 64);
+out:
+	kfree(in_mad);
+	kfree(out_mad);
+	return err;
+}
+
+int mlx5_query_mad_ifc_node_guid(struct mlx5_ib_dev *dev, __be64 *node_guid)
+{
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	init_query_mad(in_mad);
+	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+
+	err = mlx5_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad);
+	if (err)
+		goto out;
+
+	memcpy(node_guid, out_mad->data + 12, 8);
+out:
+	kfree(in_mad);
+	kfree(out_mad);
+	return err;
+}
+
+int mlx5_query_mad_ifc_pkey(struct ib_device *ibdev, u8 port, u16 index,
+			    u16 *pkey)
+{
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	init_query_mad(in_mad);
+	in_mad->attr_id  = IB_SMP_ATTR_PKEY_TABLE;
+	in_mad->attr_mod = cpu_to_be32(index / 32);
+
+	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad,
+			   out_mad);
+	if (err)
+		goto out;
+
+	*pkey = be16_to_cpu(((__be16 *)out_mad->data)[index % 32]);
+
+out:
+	kfree(in_mad);
+	kfree(out_mad);
+	return err;
+}
+
+int mlx5_query_mad_ifc_gids(struct ib_device *ibdev, u8 port, int index,
+			    union ib_gid *gid)
+{
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	init_query_mad(in_mad);
+	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
+	in_mad->attr_mod = cpu_to_be32(port);
+
+	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad,
+			   out_mad);
+	if (err)
+		goto out;
+
+	memcpy(gid->raw, out_mad->data + 8, 8);
+
+	init_query_mad(in_mad);
+	in_mad->attr_id  = IB_SMP_ATTR_GUID_INFO;
+	in_mad->attr_mod = cpu_to_be32(index / 8);
+
+	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad,
+			   out_mad);
+	if (err)
+		goto out;
+
+	memcpy(gid->raw + 8, out_mad->data + (index % 8) * 8, 8);
+
+out:
+	kfree(in_mad);
+	kfree(out_mad);
+	return err;
+}
+
+int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u8 port,
+			    struct ib_port_attr *props)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int ext_active_speed;
+	int err = -ENOMEM;
+
+	if (port < 1 || port > MLX5_CAP_GEN(mdev, num_ports)) {
+		mlx5_ib_warn(dev, "invalid port number %d\n", port);
+		return -EINVAL;
+	}
+
+	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
+	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	memset(props, 0, sizeof(*props));
+
+	init_query_mad(in_mad);
+	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
+	in_mad->attr_mod = cpu_to_be32(port);
+
+	err = mlx5_MAD_IFC(dev, 1, 1, port, NULL, NULL, in_mad, out_mad);
+	if (err) {
+		mlx5_ib_warn(dev, "err %d\n", err);
+		goto out;
+	}
+
+	props->lid		= be16_to_cpup((__be16 *)(out_mad->data + 16));
+	props->lmc		= out_mad->data[34] & 0x7;
+	props->sm_lid		= be16_to_cpup((__be16 *)(out_mad->data + 18));
+	props->sm_sl		= out_mad->data[36] & 0xf;
+	props->state		= out_mad->data[32] & 0xf;
+	props->phys_state	= out_mad->data[33] >> 4;
+	props->port_cap_flags	= be32_to_cpup((__be32 *)(out_mad->data + 20));
+	props->gid_tbl_len	= out_mad->data[50];
+	props->max_msg_sz	= 1 << MLX5_CAP_GEN(mdev, log_max_msg);
+	props->pkey_tbl_len	= mdev->port_caps[port - 1].pkey_table_len;
+	props->bad_pkey_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 46));
+	props->qkey_viol_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 48));
+	props->active_width	= out_mad->data[31] & 0xf;
+	props->active_speed	= out_mad->data[35] >> 4;
+	props->max_mtu		= out_mad->data[41] & 0xf;
+	props->active_mtu	= out_mad->data[36] >> 4;
+	props->subnet_timeout	= out_mad->data[51] & 0x1f;
+	props->max_vl_num	= out_mad->data[37] >> 4;
+	props->init_type_reply	= out_mad->data[41] >> 4;
+
+	/* Check if extended speeds (EDR/FDR/...) are supported */
+	if (props->port_cap_flags & IB_PORT_EXTENDED_SPEEDS_SUP) {
+		ext_active_speed = out_mad->data[62] >> 4;
+
+		switch (ext_active_speed) {
+		case 1:
+			props->active_speed = 16; /* FDR */
+			break;
+		case 2:
+			props->active_speed = 32; /* EDR */
+			break;
+		}
+	}
+
+	/* If reported active speed is QDR, check if is FDR-10 */
+	if (props->active_speed == 4) {
+		if (mdev->port_caps[port - 1].ext_port_cap &
+		    MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO) {
+			init_query_mad(in_mad);
+			in_mad->attr_id = MLX5_ATTR_EXTENDED_PORT_INFO;
+			in_mad->attr_mod = cpu_to_be32(port);
+
+			err = mlx5_MAD_IFC(dev, 1, 1, port,
+					   NULL, NULL, in_mad, out_mad);
+			if (err)
+				goto out;
+
+			/* Checking LinkSpeedActive for FDR-10 */
+			if (out_mad->data[15] & 0x1)
+				props->active_speed = 8;
+		}
+	}
+
+out:
+	kfree(in_mad);
+	kfree(out_mad);
+
+	return err;
+}
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 57c9809e8b87..085c24b4b603 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -40,6 +40,7 @@
 #include <linux/io-mapping.h>
 #include <linux/sched.h>
 #include <rdma/ib_user_verbs.h>
+#include <linux/mlx5/vport.h>
 #include <rdma/ib_smi.h>
 #include <rdma/ib_umem.h>
 #include "user.h"
@@ -62,32 +63,172 @@ static char mlx5_version[] =
 	DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
 	DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
 
+static enum rdma_link_layer
+mlx5_ib_port_link_layer(struct ib_device *device)
+{
+	struct mlx5_ib_dev *dev = to_mdev(device);
+
+	switch (MLX5_CAP_GEN(dev->mdev, port_type)) {
+	case MLX5_CAP_PORT_TYPE_IB:
+		return IB_LINK_LAYER_INFINIBAND;
+	case MLX5_CAP_PORT_TYPE_ETH:
+		return IB_LINK_LAYER_ETHERNET;
+	default:
+		return IB_LINK_LAYER_UNSPECIFIED;
+	}
+}
+
+static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
+{
+	return !dev->mdev->issi;
+}
+
+enum {
+	MLX5_VPORT_ACCESS_METHOD_MAD,
+	MLX5_VPORT_ACCESS_METHOD_HCA,
+	MLX5_VPORT_ACCESS_METHOD_NIC,
+};
+
+static int mlx5_get_vport_access_method(struct ib_device *ibdev)
+{
+	if (mlx5_use_mad_ifc(to_mdev(ibdev)))
+		return MLX5_VPORT_ACCESS_METHOD_MAD;
+
+	if (mlx5_ib_port_link_layer(ibdev) ==
+	    IB_LINK_LAYER_ETHERNET)
+		return MLX5_VPORT_ACCESS_METHOD_NIC;
+
+	return MLX5_VPORT_ACCESS_METHOD_HCA;
+}
+
+static int mlx5_query_system_image_guid(struct ib_device *ibdev,
+					__be64 *sys_image_guid)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
+	u64 tmp;
+	int err;
+
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_system_image_guid(ibdev,
+							    sys_image_guid);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+		err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp);
+		if (!err)
+			*sys_image_guid = cpu_to_be64(tmp);
+		return err;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mlx5_query_max_pkeys(struct ib_device *ibdev,
+				u16 *max_pkeys)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
+
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_max_pkeys(ibdev, max_pkeys);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+	case MLX5_VPORT_ACCESS_METHOD_NIC:
+		*max_pkeys = mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(mdev,
+						pkey_table_size));
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mlx5_query_vendor_id(struct ib_device *ibdev,
+				u32 *vendor_id)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_vendor_id(ibdev, vendor_id);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+	case MLX5_VPORT_ACCESS_METHOD_NIC:
+		return mlx5_core_query_vendor_id(dev->mdev, vendor_id);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int mlx5_query_node_guid(struct mlx5_ib_dev *dev,
+				__be64 *node_guid)
+{
+	u64 tmp;
+	int err;
+
+	switch (mlx5_get_vport_access_method(&dev->ib_dev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_node_guid(dev, node_guid);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+		err = mlx5_query_hca_vport_node_guid(dev->mdev, &tmp);
+		if (!err)
+			*node_guid = cpu_to_be64(tmp);
+		return err;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+struct mlx5_reg_node_desc {
+	u8	desc[64];
+};
+
+static int mlx5_query_node_desc(struct mlx5_ib_dev *dev, char *node_desc)
+{
+	struct mlx5_reg_node_desc in;
+
+	if (mlx5_use_mad_ifc(dev))
+		return mlx5_query_mad_ifc_node_desc(dev, node_desc);
+
+	memset(&in, 0, sizeof(in));
+
+	return mlx5_core_access_reg(dev->mdev, &in, sizeof(in), node_desc,
+				    sizeof(struct mlx5_reg_node_desc),
+				    MLX5_REG_NODE_DESC, 0, 0);
+}
+
 static int mlx5_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	struct mlx5_general_caps *gen;
+	struct mlx5_core_dev *mdev = dev->mdev;
 	int err = -ENOMEM;
 	int max_rq_sg;
 	int max_sq_sg;
-	u64 flags;
 
-	gen = &dev->mdev->caps.gen;
-	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
-	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
-	if (!in_mad || !out_mad)
-		goto out;
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
 
-	init_query_mad(in_mad);
-	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+	memset(props, 0, sizeof(*props));
+	err = mlx5_query_system_image_guid(ibdev,
+					   &props->sys_image_guid);
+	if (err)
+		return err;
 
-	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, 1, NULL, NULL, in_mad, out_mad);
+	err = mlx5_query_max_pkeys(ibdev, &props->max_pkeys);
 	if (err)
-		goto out;
+		return err;
 
-	memset(props, 0, sizeof(*props));
+	err = mlx5_query_vendor_id(ibdev, &props->vendor_id);
+	if (err)
+		return err;
 
 	props->fw_ver = ((u64)fw_rev_maj(dev->mdev) << 32) |
 		(fw_rev_min(dev->mdev) << 16) |
@@ -96,18 +237,18 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		IB_DEVICE_PORT_ACTIVE_EVENT		|
 		IB_DEVICE_SYS_IMAGE_GUID		|
 		IB_DEVICE_RC_RNR_NAK_GEN;
-	flags = gen->flags;
-	if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR)
+
+	if (MLX5_CAP_GEN(mdev, pkv))
 		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
-	if (flags & MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR)
+	if (MLX5_CAP_GEN(mdev, qkv))
 		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
-	if (flags & MLX5_DEV_CAP_FLAG_APM)
+	if (MLX5_CAP_GEN(mdev, apm))
 		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
 	props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
-	if (flags & MLX5_DEV_CAP_FLAG_XRC)
+	if (MLX5_CAP_GEN(mdev, xrc))
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
-	if (flags & MLX5_DEV_CAP_FLAG_SIG_HAND_OVER) {
+	if (MLX5_CAP_GEN(mdev, sho)) {
 		props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
 		/* At this stage no support for signature handover */
 		props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
@@ -116,221 +257,270 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->sig_guard_cap = IB_GUARD_T10DIF_CRC |
 				       IB_GUARD_T10DIF_CSUM;
 	}
-	if (flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)
+	if (MLX5_CAP_GEN(mdev, block_lb_mc))
 		props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
 
-	props->vendor_id	   = be32_to_cpup((__be32 *)(out_mad->data + 36)) &
-		0xffffff;
-	props->vendor_part_id	   = be16_to_cpup((__be16 *)(out_mad->data + 30));
-	props->hw_ver		   = be32_to_cpup((__be32 *)(out_mad->data + 32));
-	memcpy(&props->sys_image_guid, out_mad->data +	4, 8);
+	props->vendor_part_id	   = mdev->pdev->device;
+	props->hw_ver		   = mdev->pdev->revision;
 
 	props->max_mr_size	   = ~0ull;
-	props->page_size_cap	   = gen->min_page_sz;
-	props->max_qp		   = 1 << gen->log_max_qp;
-	props->max_qp_wr	   = gen->max_wqes;
-	max_rq_sg = gen->max_rq_desc_sz / sizeof(struct mlx5_wqe_data_seg);
-	max_sq_sg = (gen->max_sq_desc_sz - sizeof(struct mlx5_wqe_ctrl_seg)) /
-		sizeof(struct mlx5_wqe_data_seg);
+	props->page_size_cap	   = 1ull << MLX5_CAP_GEN(mdev, log_pg_sz);
+	props->max_qp		   = 1 << MLX5_CAP_GEN(mdev, log_max_qp);
+	props->max_qp_wr	   = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
+	max_rq_sg =  MLX5_CAP_GEN(mdev, max_wqe_sz_rq) /
+		     sizeof(struct mlx5_wqe_data_seg);
+	max_sq_sg = (MLX5_CAP_GEN(mdev, max_wqe_sz_sq) -
+		     sizeof(struct mlx5_wqe_ctrl_seg)) /
+		     sizeof(struct mlx5_wqe_data_seg);
 	props->max_sge = min(max_rq_sg, max_sq_sg);
-	props->max_cq		   = 1 << gen->log_max_cq;
-	props->max_cqe		   = gen->max_cqes - 1;
-	props->max_mr		   = 1 << gen->log_max_mkey;
-	props->max_pd		   = 1 << gen->log_max_pd;
-	props->max_qp_rd_atom	   = 1 << gen->log_max_ra_req_qp;
-	props->max_qp_init_rd_atom = 1 << gen->log_max_ra_res_qp;
-	props->max_srq		   = 1 << gen->log_max_srq;
-	props->max_srq_wr	   = gen->max_srq_wqes - 1;
-	props->local_ca_ack_delay  = gen->local_ca_ack_delay;
+	props->max_cq		   = 1 << MLX5_CAP_GEN(mdev, log_max_cq);
+	props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_eq_sz)) - 1;
+	props->max_mr		   = 1 << MLX5_CAP_GEN(mdev, log_max_mkey);
+	props->max_pd		   = 1 << MLX5_CAP_GEN(mdev, log_max_pd);
+	props->max_qp_rd_atom	   = 1 << MLX5_CAP_GEN(mdev, log_max_ra_req_qp);
+	props->max_qp_init_rd_atom = 1 << MLX5_CAP_GEN(mdev, log_max_ra_res_qp);
+	props->max_srq		   = 1 << MLX5_CAP_GEN(mdev, log_max_srq);
+	props->max_srq_wr = (1 << MLX5_CAP_GEN(mdev, log_max_srq_sz)) - 1;
+	props->local_ca_ack_delay  = MLX5_CAP_GEN(mdev, local_ca_ack_delay);
 	props->max_res_rd_atom	   = props->max_qp_rd_atom * props->max_qp;
 	props->max_srq_sge	   = max_rq_sg - 1;
 	props->max_fast_reg_page_list_len = (unsigned int)-1;
-	props->local_ca_ack_delay  = gen->local_ca_ack_delay;
 	props->atomic_cap	   = IB_ATOMIC_NONE;
 	props->masked_atomic_cap   = IB_ATOMIC_NONE;
-	props->max_pkeys	   = be16_to_cpup((__be16 *)(out_mad->data + 28));
-	props->max_mcast_grp	   = 1 << gen->log_max_mcg;
-	props->max_mcast_qp_attach = gen->max_qp_mcg;
+	props->max_mcast_grp	   = 1 << MLX5_CAP_GEN(mdev, log_max_mcg);
+	props->max_mcast_qp_attach = MLX5_CAP_GEN(mdev, max_qp_mcg);
 	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
 					   props->max_mcast_grp;
 	props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */
 
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG)
+	if (MLX5_CAP_GEN(mdev, pg))
 		props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
 	props->odp_caps = dev->odp_caps;
 #endif
 
-out:
-	kfree(in_mad);
-	kfree(out_mad);
-
-	return err;
+	return 0;
 }
 
-int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
-		       struct ib_port_attr *props)
+enum mlx5_ib_width {
+	MLX5_IB_WIDTH_1X	= 1 << 0,
+	MLX5_IB_WIDTH_2X	= 1 << 1,
+	MLX5_IB_WIDTH_4X	= 1 << 2,
+	MLX5_IB_WIDTH_8X	= 1 << 3,
+	MLX5_IB_WIDTH_12X	= 1 << 4
+};
+
+static int translate_active_width(struct ib_device *ibdev, u8 active_width,
+				  u8 *ib_width)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	struct mlx5_general_caps *gen;
-	int ext_active_speed;
-	int err = -ENOMEM;
-
-	gen = &dev->mdev->caps.gen;
-	if (port < 1 || port > gen->num_ports) {
-		mlx5_ib_warn(dev, "invalid port number %d\n", port);
-		return -EINVAL;
+	int err = 0;
+
+	if (active_width & MLX5_IB_WIDTH_1X) {
+		*ib_width = IB_WIDTH_1X;
+	} else if (active_width & MLX5_IB_WIDTH_2X) {
+		mlx5_ib_dbg(dev, "active_width %d is not supported by IB spec\n",
+			    (int)active_width);
+		err = -EINVAL;
+	} else if (active_width & MLX5_IB_WIDTH_4X) {
+		*ib_width = IB_WIDTH_4X;
+	} else if (active_width & MLX5_IB_WIDTH_8X) {
+		*ib_width = IB_WIDTH_8X;
+	} else if (active_width & MLX5_IB_WIDTH_12X) {
+		*ib_width = IB_WIDTH_12X;
+	} else {
+		mlx5_ib_dbg(dev, "Invalid active_width %d\n",
+			    (int)active_width);
+		err = -EINVAL;
 	}
 
-	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
-	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
-	if (!in_mad || !out_mad)
-		goto out;
-
-	memset(props, 0, sizeof(*props));
-
-	init_query_mad(in_mad);
-	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
-	in_mad->attr_mod = cpu_to_be32(port);
+	return err;
+}
 
-	err = mlx5_MAD_IFC(dev, 1, 1, port, NULL, NULL, in_mad, out_mad);
-	if (err) {
-		mlx5_ib_warn(dev, "err %d\n", err);
-		goto out;
+static int mlx5_mtu_to_ib_mtu(int mtu)
+{
+	switch (mtu) {
+	case 256: return 1;
+	case 512: return 2;
+	case 1024: return 3;
+	case 2048: return 4;
+	case 4096: return 5;
+	default:
+		pr_warn("invalid mtu\n");
+		return -1;
 	}
+}
 
+enum ib_max_vl_num {
+	__IB_MAX_VL_0		= 1,
+	__IB_MAX_VL_0_1		= 2,
+	__IB_MAX_VL_0_3		= 3,
+	__IB_MAX_VL_0_7		= 4,
+	__IB_MAX_VL_0_14	= 5,
+};
 
-	props->lid		= be16_to_cpup((__be16 *)(out_mad->data + 16));
-	props->lmc		= out_mad->data[34] & 0x7;
-	props->sm_lid		= be16_to_cpup((__be16 *)(out_mad->data + 18));
-	props->sm_sl		= out_mad->data[36] & 0xf;
-	props->state		= out_mad->data[32] & 0xf;
-	props->phys_state	= out_mad->data[33] >> 4;
-	props->port_cap_flags	= be32_to_cpup((__be32 *)(out_mad->data + 20));
-	props->gid_tbl_len	= out_mad->data[50];
-	props->max_msg_sz	= 1 << gen->log_max_msg;
-	props->pkey_tbl_len	= gen->port[port - 1].pkey_table_len;
-	props->bad_pkey_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 46));
-	props->qkey_viol_cntr	= be16_to_cpup((__be16 *)(out_mad->data + 48));
-	props->active_width	= out_mad->data[31] & 0xf;
-	props->active_speed	= out_mad->data[35] >> 4;
-	props->max_mtu		= out_mad->data[41] & 0xf;
-	props->active_mtu	= out_mad->data[36] >> 4;
-	props->subnet_timeout	= out_mad->data[51] & 0x1f;
-	props->max_vl_num	= out_mad->data[37] >> 4;
-	props->init_type_reply	= out_mad->data[41] >> 4;
-
-	/* Check if extended speeds (EDR/FDR/...) are supported */
-	if (props->port_cap_flags & IB_PORT_EXTENDED_SPEEDS_SUP) {
-		ext_active_speed = out_mad->data[62] >> 4;
-
-		switch (ext_active_speed) {
-		case 1:
-			props->active_speed = 16; /* FDR */
-			break;
-		case 2:
-			props->active_speed = 32; /* EDR */
-			break;
-		}
-	}
+enum mlx5_vl_hw_cap {
+	MLX5_VL_HW_0	= 1,
+	MLX5_VL_HW_0_1	= 2,
+	MLX5_VL_HW_0_2	= 3,
+	MLX5_VL_HW_0_3	= 4,
+	MLX5_VL_HW_0_4	= 5,
+	MLX5_VL_HW_0_5	= 6,
+	MLX5_VL_HW_0_6	= 7,
+	MLX5_VL_HW_0_7	= 8,
+	MLX5_VL_HW_0_14	= 15
+};
 
-	/* If reported active speed is QDR, check if is FDR-10 */
-	if (props->active_speed == 4) {
-		if (gen->ext_port_cap[port - 1] &
-		    MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO) {
-			init_query_mad(in_mad);
-			in_mad->attr_id = MLX5_ATTR_EXTENDED_PORT_INFO;
-			in_mad->attr_mod = cpu_to_be32(port);
-
-			err = mlx5_MAD_IFC(dev, 1, 1, port,
-					   NULL, NULL, in_mad, out_mad);
-			if (err)
-				goto out;
-
-			/* Checking LinkSpeedActive for FDR-10 */
-			if (out_mad->data[15] & 0x1)
-				props->active_speed = 8;
-		}
-	}
+static int translate_max_vl_num(struct ib_device *ibdev, u8 vl_hw_cap,
+				u8 *max_vl_num)
+{
+	switch (vl_hw_cap) {
+	case MLX5_VL_HW_0:
+		*max_vl_num = __IB_MAX_VL_0;
+		break;
+	case MLX5_VL_HW_0_1:
+		*max_vl_num = __IB_MAX_VL_0_1;
+		break;
+	case MLX5_VL_HW_0_3:
+		*max_vl_num = __IB_MAX_VL_0_3;
+		break;
+	case MLX5_VL_HW_0_7:
+		*max_vl_num = __IB_MAX_VL_0_7;
+		break;
+	case MLX5_VL_HW_0_14:
+		*max_vl_num = __IB_MAX_VL_0_14;
+		break;
 
-out:
-	kfree(in_mad);
-	kfree(out_mad);
+	default:
+		return -EINVAL;
+	}
 
-	return err;
+	return 0;
 }
 
-static int mlx5_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
-			     union ib_gid *gid)
+static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port,
+			       struct ib_port_attr *props)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	int err = -ENOMEM;
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_hca_vport_context *rep;
+	int max_mtu;
+	int oper_mtu;
+	int err;
+	u8 ib_link_width_oper;
+	u8 vl_hw_cap;
 
-	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
-	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
-	if (!in_mad || !out_mad)
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (!rep) {
+		err = -ENOMEM;
 		goto out;
+	}
 
-	init_query_mad(in_mad);
-	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
-	in_mad->attr_mod = cpu_to_be32(port);
+	memset(props, 0, sizeof(*props));
 
-	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad);
+	err = mlx5_query_hca_vport_context(mdev, 0, port, 0, rep);
 	if (err)
 		goto out;
 
-	memcpy(gid->raw, out_mad->data + 8, 8);
-
-	init_query_mad(in_mad);
-	in_mad->attr_id  = IB_SMP_ATTR_GUID_INFO;
-	in_mad->attr_mod = cpu_to_be32(index / 8);
+	props->lid		= rep->lid;
+	props->lmc		= rep->lmc;
+	props->sm_lid		= rep->sm_lid;
+	props->sm_sl		= rep->sm_sl;
+	props->state		= rep->vport_state;
+	props->phys_state	= rep->port_physical_state;
+	props->port_cap_flags	= rep->cap_mask1;
+	props->gid_tbl_len	= mlx5_get_gid_table_len(MLX5_CAP_GEN(mdev, gid_table_size));
+	props->max_msg_sz	= 1 << MLX5_CAP_GEN(mdev, log_max_msg);
+	props->pkey_tbl_len	= mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(mdev, pkey_table_size));
+	props->bad_pkey_cntr	= rep->pkey_violation_counter;
+	props->qkey_viol_cntr	= rep->qkey_violation_counter;
+	props->subnet_timeout	= rep->subnet_timeout;
+	props->init_type_reply	= rep->init_type_reply;
+
+	err = mlx5_query_port_link_width_oper(mdev, &ib_link_width_oper, port);
+	if (err)
+		goto out;
 
-	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad);
+	err = translate_active_width(ibdev, ib_link_width_oper,
+				     &props->active_width);
+	if (err)
+		goto out;
+	err = mlx5_query_port_proto_oper(mdev, &props->active_speed, MLX5_PTYS_IB,
+					 port);
 	if (err)
 		goto out;
 
-	memcpy(gid->raw + 8, out_mad->data + (index % 8) * 8, 8);
+	mlx5_query_port_max_mtu(mdev, &max_mtu, port);
+
+	props->max_mtu = mlx5_mtu_to_ib_mtu(max_mtu);
+
+	mlx5_query_port_oper_mtu(mdev, &oper_mtu, port);
+
+	props->active_mtu = mlx5_mtu_to_ib_mtu(oper_mtu);
 
+	err = mlx5_query_port_vl_hw_cap(mdev, &vl_hw_cap, port);
+	if (err)
+		goto out;
+
+	err = translate_max_vl_num(ibdev, vl_hw_cap,
+				   &props->max_vl_num);
 out:
-	kfree(in_mad);
-	kfree(out_mad);
+	kfree(rep);
 	return err;
 }
 
-static int mlx5_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
-			      u16 *pkey)
+int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
+		       struct ib_port_attr *props)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	int err = -ENOMEM;
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_port(ibdev, port, props);
 
-	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
-	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
-	if (!in_mad || !out_mad)
-		goto out;
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+		return mlx5_query_hca_port(ibdev, port, props);
 
-	init_query_mad(in_mad);
-	in_mad->attr_id  = IB_SMP_ATTR_PKEY_TABLE;
-	in_mad->attr_mod = cpu_to_be32(index / 32);
+	default:
+		return -EINVAL;
+	}
+}
 
-	err = mlx5_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad);
-	if (err)
-		goto out;
+static int mlx5_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+			     union ib_gid *gid)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
 
-	*pkey = be16_to_cpu(((__be16 *)out_mad->data)[index % 32]);
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_gids(ibdev, port, index, gid);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+		return mlx5_query_hca_vport_gid(mdev, 0, port, 0, index, gid);
+
+	default:
+		return -EINVAL;
+	}
 
-out:
-	kfree(in_mad);
-	kfree(out_mad);
-	return err;
 }
 
-struct mlx5_reg_node_desc {
-	u8	desc[64];
-};
+static int mlx5_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
+			      u16 *pkey)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+	struct mlx5_core_dev *mdev = dev->mdev;
+
+	switch (mlx5_get_vport_access_method(ibdev)) {
+	case MLX5_VPORT_ACCESS_METHOD_MAD:
+		return mlx5_query_mad_ifc_pkey(ibdev, port, index, pkey);
+
+	case MLX5_VPORT_ACCESS_METHOD_HCA:
+	case MLX5_VPORT_ACCESS_METHOD_NIC:
+		return mlx5_query_hca_vport_pkey(mdev, 0, port,  0, index,
+						 pkey);
+	default:
+		return -EINVAL;
+	}
+}
 
 static int mlx5_ib_modify_device(struct ib_device *ibdev, int mask,
 				 struct ib_device_modify *props)
@@ -392,7 +582,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_alloc_ucontext_req_v2 req;
 	struct mlx5_ib_alloc_ucontext_resp resp;
 	struct mlx5_ib_ucontext *context;
-	struct mlx5_general_caps *gen;
 	struct mlx5_uuar_info *uuari;
 	struct mlx5_uar *uars;
 	int gross_uuars;
@@ -403,7 +592,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	int i;
 	size_t reqlen;
 
-	gen = &dev->mdev->caps.gen;
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
@@ -436,14 +624,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 
 	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
 	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
-	resp.qp_tab_size      = 1 << gen->log_max_qp;
-	resp.bf_reg_size      = gen->bf_reg_size;
-	resp.cache_line_size  = L1_CACHE_BYTES;
-	resp.max_sq_desc_sz = gen->max_sq_desc_sz;
-	resp.max_rq_desc_sz = gen->max_rq_desc_sz;
-	resp.max_send_wqebb = gen->max_wqes;
-	resp.max_recv_wr = gen->max_wqes;
-	resp.max_srq_recv_wr = gen->max_srq_wqes;
+	resp.qp_tab_size = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp);
+	resp.bf_reg_size = 1 << MLX5_CAP_GEN(dev->mdev, log_bf_reg_size);
+	resp.cache_line_size = L1_CACHE_BYTES;
+	resp.max_sq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq);
+	resp.max_rq_desc_sz = MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq);
+	resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
+	resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
+	resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
 
 	context = kzalloc(sizeof(*context), GFP_KERNEL);
 	if (!context)
@@ -493,7 +681,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	mutex_init(&context->db_page_mutex);
 
 	resp.tot_uuars = req.total_num_uuars;
-	resp.num_ports = gen->num_ports;
+	resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports);
 	err = ib_copy_to_udata(udata, &resp,
 			       sizeof(resp) - sizeof(resp.reserved));
 	if (err)
@@ -731,37 +919,15 @@ static int mlx5_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 static int init_node_data(struct mlx5_ib_dev *dev)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	int err = -ENOMEM;
-
-	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
-	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
-	if (!in_mad || !out_mad)
-		goto out;
-
-	init_query_mad(in_mad);
-	in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
-
-	err = mlx5_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad);
-	if (err)
-		goto out;
-
-	memcpy(dev->ib_dev.node_desc, out_mad->data, 64);
-
-	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
+	int err;
 
-	err = mlx5_MAD_IFC(dev, 1, 1, 1, NULL, NULL, in_mad, out_mad);
+	err = mlx5_query_node_desc(dev, dev->ib_dev.node_desc);
 	if (err)
-		goto out;
+		return err;
 
-	dev->mdev->rev_id = be32_to_cpup((__be32 *)(out_mad->data + 32));
-	memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8);
+	dev->mdev->rev_id = dev->mdev->pdev->revision;
 
-out:
-	kfree(in_mad);
-	kfree(out_mad);
-	return err;
+	return mlx5_query_node_guid(dev, &dev->ib_dev.node_guid);
 }
 
 static ssize_t show_fw_pages(struct device *device, struct device_attribute *attr,
@@ -895,11 +1061,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
 {
-	struct mlx5_general_caps *gen;
 	int port;
 
-	gen = &dev->mdev->caps.gen;
-	for (port = 1; port <= gen->num_ports; port++)
+	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++)
 		mlx5_query_ext_port_caps(dev, port);
 }
 
@@ -907,11 +1071,10 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 {
 	struct ib_device_attr *dprops = NULL;
 	struct ib_port_attr *pprops = NULL;
-	struct mlx5_general_caps *gen;
 	int err = -ENOMEM;
 	int port;
+	struct ib_udata uhw = {.inlen = 0, .outlen = 0};
 
-	gen = &dev->mdev->caps.gen;
 	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
 	if (!pprops)
 		goto out;
@@ -920,20 +1083,23 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	if (!dprops)
 		goto out;
 
-	err = mlx5_ib_query_device(&dev->ib_dev, dprops);
+	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
 		goto out;
 	}
 
-	for (port = 1; port <= gen->num_ports; port++) {
+	for (port = 1; port <= MLX5_CAP_GEN(dev->mdev, num_ports); port++) {
 		err = mlx5_ib_query_port(&dev->ib_dev, port, pprops);
 		if (err) {
-			mlx5_ib_warn(dev, "query_port %d failed %d\n", port, err);
+			mlx5_ib_warn(dev, "query_port %d failed %d\n",
+				     port, err);
 			break;
 		}
-		gen->port[port - 1].pkey_table_len = dprops->max_pkeys;
-		gen->port[port - 1].gid_table_len = pprops->gid_tbl_len;
+		dev->mdev->port_caps[port - 1].pkey_table_len =
+						dprops->max_pkeys;
+		dev->mdev->port_caps[port - 1].gid_table_len =
+						pprops->gid_tbl_len;
 		mlx5_ib_dbg(dev, "pkey_table_len %d, gid_table_len %d\n",
 			    dprops->max_pkeys, pprops->gid_tbl_len);
 	}
@@ -971,6 +1137,7 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 	struct ib_cq *cq;
 	struct ib_qp *qp;
 	struct ib_mr *mr;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
@@ -994,8 +1161,9 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 		goto error_1;
 	}
 
-	cq = ib_create_cq(&dev->ib_dev, mlx5_umr_cq_handler, NULL, NULL, 128,
-			  0);
+	cq_attr.cqe = 128;
+	cq = ib_create_cq(&dev->ib_dev, mlx5_umr_cq_handler, NULL, NULL,
+			  &cq_attr);
 	if (IS_ERR(cq)) {
 		mlx5_ib_dbg(dev, "Couldn't create CQ for sync UMR QP\n");
 		ret = PTR_ERR(cq);
@@ -1087,6 +1255,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 {
 	struct ib_srq_init_attr attr;
 	struct mlx5_ib_dev *dev;
+	struct ib_cq_init_attr cq_attr = {.cqe = 1};
 	int ret = 0;
 
 	dev = container_of(devr, struct mlx5_ib_dev, devr);
@@ -1100,7 +1269,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->p0->uobject = NULL;
 	atomic_set(&devr->p0->usecnt, 0);
 
-	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, 1, 0, NULL, NULL);
+	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL, NULL);
 	if (IS_ERR(devr->c0)) {
 		ret = PTR_ERR(devr->c0);
 		goto error1;
@@ -1159,8 +1328,29 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	atomic_inc(&devr->p0->usecnt);
 	atomic_set(&devr->s0->usecnt, 0);
 
+	memset(&attr, 0, sizeof(attr));
+	attr.attr.max_sge = 1;
+	attr.attr.max_wr = 1;
+	attr.srq_type = IB_SRQT_BASIC;
+	devr->s1 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
+	if (IS_ERR(devr->s1)) {
+		ret = PTR_ERR(devr->s1);
+		goto error5;
+	}
+	devr->s1->device	= &dev->ib_dev;
+	devr->s1->pd		= devr->p0;
+	devr->s1->uobject       = NULL;
+	devr->s1->event_handler = NULL;
+	devr->s1->srq_context   = NULL;
+	devr->s1->srq_type      = IB_SRQT_BASIC;
+	devr->s1->ext.xrc.cq	= devr->c0;
+	atomic_inc(&devr->p0->usecnt);
+	atomic_set(&devr->s0->usecnt, 0);
+
 	return 0;
 
+error5:
+	mlx5_ib_destroy_srq(devr->s0);
 error4:
 	mlx5_ib_dealloc_xrcd(devr->x1);
 error3:
@@ -1175,6 +1365,7 @@ error0:
 
 static void destroy_dev_resources(struct mlx5_ib_resources *devr)
 {
+	mlx5_ib_destroy_srq(devr->s1);
 	mlx5_ib_destroy_srq(devr->s0);
 	mlx5_ib_dealloc_xrcd(devr->x0);
 	mlx5_ib_dealloc_xrcd(devr->x1);
@@ -1182,12 +1373,34 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr)
 	mlx5_ib_dealloc_pd(devr->p0);
 }
 
+static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mlx5_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_dev *dev;
 	int err;
 	int i;
 
+	/* don't create IB instance over Eth ports, no RoCE yet! */
+	if (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH)
+		return NULL;
+
 	printk_once(KERN_INFO "%s", mlx5_version);
 
 	dev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*dev));
@@ -1200,15 +1413,16 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (err)
 		goto err_dealloc;
 
-	get_ext_port_caps(dev);
+	if (mlx5_use_mad_ifc(dev))
+		get_ext_port_caps(dev);
 
 	MLX5_INIT_DOORBELL_LOCK(&dev->uar_lock);
 
 	strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
 	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
-	dev->ib_dev.local_dma_lkey	= mdev->caps.gen.reserved_lkey;
-	dev->num_ports		= mdev->caps.gen.num_ports;
+	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
+	dev->num_ports		= MLX5_CAP_GEN(mdev, num_ports);
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors    =
 		dev->mdev->priv.eq_table.num_comp_vectors;
@@ -1285,10 +1499,11 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
 	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
+	dev->ib_dev.get_port_immutable  = mlx5_port_immutable;
 
-	mlx5_ib_internal_query_odp_caps(dev);
+	mlx5_ib_internal_fill_odp_caps(dev);
 
-	if (mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_XRC) {
+	if (MLX5_CAP_GEN(mdev, xrc)) {
 		dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;
 		dev->ib_dev.dealloc_xrcd = mlx5_ib_dealloc_xrcd;
 		dev->ib_dev.uverbs_cmd_mask |=
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index dff1cfcdf476..7cae09836481 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -415,6 +415,7 @@ struct mlx5_ib_resources {
 	struct ib_xrcd	*x1;
 	struct ib_pd	*p0;
 	struct ib_srq	*s0;
+	struct ib_srq	*s1;
 };
 
 struct mlx5_ib_dev {
@@ -525,8 +526,8 @@ void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
 void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq);
 void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index);
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
-		 u8 port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad);
+		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad);
 struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
 			   struct mlx5_ib_ah *ah);
 struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
@@ -556,8 +557,9 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n);
 int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
 			  void *buffer, u32 length);
-struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
-				int vector, struct ib_ucontext *context,
+struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
 				struct ib_udata *udata);
 int mlx5_ib_destroy_cq(struct ib_cq *cq);
 int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
@@ -586,14 +588,32 @@ int mlx5_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
 int mlx5_ib_unmap_fmr(struct list_head *fmr_list);
 int mlx5_ib_fmr_dealloc(struct ib_fmr *ibfmr);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_ucontext *context,
 					  struct ib_udata *udata);
 int mlx5_ib_dealloc_xrcd(struct ib_xrcd *xrcd);
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset);
 int mlx5_query_ext_port_caps(struct mlx5_ib_dev *dev, u8 port);
+int mlx5_query_mad_ifc_smp_attr_node_info(struct ib_device *ibdev,
+					  struct ib_smp *out_mad);
+int mlx5_query_mad_ifc_system_image_guid(struct ib_device *ibdev,
+					 __be64 *sys_image_guid);
+int mlx5_query_mad_ifc_max_pkeys(struct ib_device *ibdev,
+				 u16 *max_pkeys);
+int mlx5_query_mad_ifc_vendor_id(struct ib_device *ibdev,
+				 u32 *vendor_id);
+int mlx5_query_mad_ifc_node_desc(struct mlx5_ib_dev *dev, char *node_desc);
+int mlx5_query_mad_ifc_node_guid(struct mlx5_ib_dev *dev, __be64 *node_guid);
+int mlx5_query_mad_ifc_pkey(struct ib_device *ibdev, u8 port, u16 index,
+			    u16 *pkey);
+int mlx5_query_mad_ifc_gids(struct ib_device *ibdev, u8 port, int index,
+			    union ib_gid *gid);
+int mlx5_query_mad_ifc_port(struct ib_device *ibdev, u8 port,
+			    struct ib_port_attr *props);
 int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
 		       struct ib_port_attr *props);
 int mlx5_ib_init_fmr(struct mlx5_ib_dev *dev);
@@ -617,7 +637,7 @@ int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 extern struct workqueue_struct *mlx5_ib_page_fault_wq;
 
-int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev);
+void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
 void mlx5_ib_mr_pfault_handler(struct mlx5_ib_qp *qp,
 			       struct mlx5_ib_pfault *pfault);
 void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp);
@@ -631,9 +651,9 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			      unsigned long end);
 
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
-static inline int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev)
+static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 {
-	return 0;
+	return;
 }
 
 static inline void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)		{}
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 71c593583864..bc9a0de897cb 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -975,8 +975,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
 	struct mlx5_ib_mr *mr;
 	int inlen;
 	int err;
-	bool pg_cap = !!(dev->mdev->caps.gen.flags &
-			 MLX5_DEV_CAP_FLAG_ON_DMND_PG);
+	bool pg_cap = !!(MLX5_CAP_GEN(dev->mdev, pg));
 
 	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
 	if (!mr)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 5099db08afd2..aa8391e75385 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -109,40 +109,33 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 	ib_umem_odp_unmap_dma_pages(umem, start, end);
 }
 
-#define COPY_ODP_BIT_MLX_TO_IB(reg, ib_caps, field_name, bit_name) do {	\
-	if (be32_to_cpu(reg.field_name) & MLX5_ODP_SUPPORT_##bit_name)	\
-		ib_caps->field_name |= IB_ODP_SUPPORT_##bit_name;	\
-} while (0)
-
-int mlx5_ib_internal_query_odp_caps(struct mlx5_ib_dev *dev)
+void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 {
-	int err;
-	struct mlx5_odp_caps hw_caps;
 	struct ib_odp_caps *caps = &dev->odp_caps;
 
 	memset(caps, 0, sizeof(*caps));
 
-	if (!(dev->mdev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG))
-		return 0;
-
-	err = mlx5_query_odp_caps(dev->mdev, &hw_caps);
-	if (err)
-		goto out;
+	if (!MLX5_CAP_GEN(dev->mdev, pg))
+		return;
 
 	caps->general_caps = IB_ODP_SUPPORT;
-	COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.ud_odp_caps,
-			       SEND);
-	COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps,
-			       SEND);
-	COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps,
-			       RECV);
-	COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps,
-			       WRITE);
-	COPY_ODP_BIT_MLX_TO_IB(hw_caps, caps, per_transport_caps.rc_odp_caps,
-			       READ);
-
-out:
-	return err;
+
+	if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send))
+		caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.send))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.receive))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.write))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ;
+
+	return;
 }
 
 static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 4d7024b899cb..203c8a45e095 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -220,13 +220,11 @@ static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
 static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 		       int has_rq, struct mlx5_ib_qp *qp, struct mlx5_ib_create_qp *ucmd)
 {
-	struct mlx5_general_caps *gen;
 	int wqe_size;
 	int wq_size;
 
-	gen = &dev->mdev->caps.gen;
 	/* Sanity check RQ size before proceeding */
-	if (cap->max_recv_wr  > gen->max_wqes)
+	if (cap->max_recv_wr > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz)))
 		return -EINVAL;
 
 	if (!has_rq) {
@@ -246,10 +244,11 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 			wq_size = roundup_pow_of_two(cap->max_recv_wr) * wqe_size;
 			wq_size = max_t(int, wq_size, MLX5_SEND_WQE_BB);
 			qp->rq.wqe_cnt = wq_size / wqe_size;
-			if (wqe_size > gen->max_rq_desc_sz) {
+			if (wqe_size > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq)) {
 				mlx5_ib_dbg(dev, "wqe_size %d, max %d\n",
 					    wqe_size,
-					    gen->max_rq_desc_sz);
+					    MLX5_CAP_GEN(dev->mdev,
+							 max_wqe_sz_rq));
 				return -EINVAL;
 			}
 			qp->rq.wqe_shift = ilog2(wqe_size);
@@ -330,11 +329,9 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 			struct mlx5_ib_qp *qp)
 {
-	struct mlx5_general_caps *gen;
 	int wqe_size;
 	int wq_size;
 
-	gen = &dev->mdev->caps.gen;
 	if (!attr->cap.max_send_wr)
 		return 0;
 
@@ -343,9 +340,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 	if (wqe_size < 0)
 		return wqe_size;
 
-	if (wqe_size > gen->max_sq_desc_sz) {
+	if (wqe_size > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)) {
 		mlx5_ib_dbg(dev, "wqe_size(%d) > max_sq_desc_sz(%d)\n",
-			    wqe_size, gen->max_sq_desc_sz);
+			    wqe_size, MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq));
 		return -EINVAL;
 	}
 
@@ -358,9 +355,10 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
-	if (qp->sq.wqe_cnt > gen->max_wqes) {
+	if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) {
 		mlx5_ib_dbg(dev, "wqe count(%d) exceeds limits(%d)\n",
-			    qp->sq.wqe_cnt, gen->max_wqes);
+			    qp->sq.wqe_cnt,
+			    1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz));
 		return -ENOMEM;
 	}
 	qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
@@ -375,13 +373,11 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
 			    struct mlx5_ib_qp *qp,
 			    struct mlx5_ib_create_qp *ucmd)
 {
-	struct mlx5_general_caps *gen;
 	int desc_sz = 1 << qp->sq.wqe_shift;
 
-	gen = &dev->mdev->caps.gen;
-	if (desc_sz > gen->max_sq_desc_sz) {
+	if (desc_sz > MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq)) {
 		mlx5_ib_warn(dev, "desc_sz %d, max_sq_desc_sz %d\n",
-			     desc_sz, gen->max_sq_desc_sz);
+			     desc_sz, MLX5_CAP_GEN(dev->mdev, max_wqe_sz_sq));
 		return -EINVAL;
 	}
 
@@ -393,9 +389,10 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
 
 	qp->sq.wqe_cnt = ucmd->sq_wqe_count;
 
-	if (qp->sq.wqe_cnt > gen->max_wqes) {
+	if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) {
 		mlx5_ib_warn(dev, "wqe_cnt %d, max_wqes %d\n",
-			     qp->sq.wqe_cnt, gen->max_wqes);
+			     qp->sq.wqe_cnt,
+			     1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz));
 		return -EINVAL;
 	}
 
@@ -768,7 +765,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
 	qp->buf_size = err + (qp->rq.wqe_cnt << qp->rq.wqe_shift);
 
-	err = mlx5_buf_alloc(dev->mdev, qp->buf_size, PAGE_SIZE * 2, &qp->buf);
+	err = mlx5_buf_alloc(dev->mdev, qp->buf_size, &qp->buf);
 	if (err) {
 		mlx5_ib_dbg(dev, "err %d\n", err);
 		goto err_uuar;
@@ -866,22 +863,21 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			    struct ib_udata *udata, struct mlx5_ib_qp *qp)
 {
 	struct mlx5_ib_resources *devr = &dev->devr;
+	struct mlx5_core_dev *mdev = dev->mdev;
 	struct mlx5_ib_create_qp_resp resp;
 	struct mlx5_create_qp_mbox_in *in;
-	struct mlx5_general_caps *gen;
 	struct mlx5_ib_create_qp ucmd;
 	int inlen = sizeof(*in);
 	int err;
 
 	mlx5_ib_odp_create_qp(qp);
 
-	gen = &dev->mdev->caps.gen;
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 
 	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) {
-		if (!(gen->flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)) {
+		if (!MLX5_CAP_GEN(mdev, block_lb_mc)) {
 			mlx5_ib_dbg(dev, "block multicast loopback isn't supported\n");
 			return -EINVAL;
 		} else {
@@ -914,15 +910,17 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 
 	if (pd) {
 		if (pd->uobject) {
+			__u32 max_wqes =
+				1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
 			mlx5_ib_dbg(dev, "requested sq_wqe_count (%d)\n", ucmd.sq_wqe_count);
 			if (ucmd.rq_wqe_shift != qp->rq.wqe_shift ||
 			    ucmd.rq_wqe_count != qp->rq.wqe_cnt) {
 				mlx5_ib_dbg(dev, "invalid rq params\n");
 				return -EINVAL;
 			}
-			if (ucmd.sq_wqe_count > gen->max_wqes) {
+			if (ucmd.sq_wqe_count > max_wqes) {
 				mlx5_ib_dbg(dev, "requested sq_wqe_count (%d) > max allowed (%d)\n",
-					    ucmd.sq_wqe_count, gen->max_wqes);
+					    ucmd.sq_wqe_count, max_wqes);
 				return -EINVAL;
 			}
 			err = create_user_qp(dev, pd, qp, udata, &in, &resp, &inlen);
@@ -1014,7 +1012,8 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			in->ctx.rq_type_srqn |= cpu_to_be32(to_msrq(init_attr->srq)->msrq.srqn);
 		} else {
 			in->ctx.xrcd = cpu_to_be32(to_mxrcd(devr->x1)->xrcdn);
-			in->ctx.rq_type_srqn |= cpu_to_be32(to_msrq(devr->s0)->msrq.srqn);
+			in->ctx.rq_type_srqn |=
+				cpu_to_be32(to_msrq(devr->s1)->msrq.srqn);
 		}
 	}
 
@@ -1226,7 +1225,6 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 				struct ib_qp_init_attr *init_attr,
 				struct ib_udata *udata)
 {
-	struct mlx5_general_caps *gen;
 	struct mlx5_ib_dev *dev;
 	struct mlx5_ib_qp *qp;
 	u16 xrcdn = 0;
@@ -1244,12 +1242,11 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 		}
 		dev = to_mdev(to_mxrcd(init_attr->xrcd)->ibxrcd.device);
 	}
-	gen = &dev->mdev->caps.gen;
 
 	switch (init_attr->qp_type) {
 	case IB_QPT_XRC_TGT:
 	case IB_QPT_XRC_INI:
-		if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC)) {
+		if (!MLX5_CAP_GEN(dev->mdev, xrc)) {
 			mlx5_ib_dbg(dev, "XRC not supported\n");
 			return ERR_PTR(-ENOSYS);
 		}
@@ -1356,9 +1353,6 @@ enum {
 
 static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
 {
-	struct mlx5_general_caps *gen;
-
-	gen = &dev->mdev->caps.gen;
 	if (rate == IB_RATE_PORT_CURRENT) {
 		return 0;
 	} else if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_300_GBPS) {
@@ -1366,7 +1360,7 @@ static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
 	} else {
 		while (rate != IB_RATE_2_5_GBPS &&
 		       !(1 << (rate + MLX5_STAT_RATE_OFFSET) &
-			 gen->stat_rate_support))
+			 MLX5_CAP_GEN(dev->mdev, stat_rate_support)))
 			--rate;
 	}
 
@@ -1377,10 +1371,8 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
 			 struct mlx5_qp_path *path, u8 port, int attr_mask,
 			 u32 path_flags, const struct ib_qp_attr *attr)
 {
-	struct mlx5_general_caps *gen;
 	int err;
 
-	gen = &dev->mdev->caps.gen;
 	path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
 	path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : 0;
 
@@ -1391,9 +1383,11 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
 	path->rlid	= cpu_to_be16(ah->dlid);
 
 	if (ah->ah_flags & IB_AH_GRH) {
-		if (ah->grh.sgid_index >= gen->port[port - 1].gid_table_len) {
-			pr_err(KERN_ERR "sgid_index (%u) too large. max is %d\n",
-			       ah->grh.sgid_index, gen->port[port - 1].gid_table_len);
+		if (ah->grh.sgid_index >=
+		    dev->mdev->port_caps[port - 1].gid_table_len) {
+			pr_err("sgid_index (%u) too large. max is %d\n",
+			       ah->grh.sgid_index,
+			       dev->mdev->port_caps[port - 1].gid_table_len);
 			return -EINVAL;
 		}
 		path->grh_mlid |= 1 << 7;
@@ -1570,7 +1564,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	struct mlx5_ib_cq *send_cq, *recv_cq;
 	struct mlx5_qp_context *context;
-	struct mlx5_general_caps *gen;
 	struct mlx5_modify_qp_mbox_in *in;
 	struct mlx5_ib_pd *pd;
 	enum mlx5_qp_state mlx5_cur, mlx5_new;
@@ -1579,7 +1572,6 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	int mlx5_st;
 	int err;
 
-	gen = &dev->mdev->caps.gen;
 	in = kzalloc(sizeof(*in), GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1619,7 +1611,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			err = -EINVAL;
 			goto out;
 		}
-		context->mtu_msgmax = (attr->path_mtu << 5) | gen->log_max_msg;
+		context->mtu_msgmax = (attr->path_mtu << 5) |
+				      (u8)MLX5_CAP_GEN(dev->mdev, log_max_msg);
 	}
 
 	if (attr_mask & IB_QP_DEST_QPN)
@@ -1777,11 +1770,9 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
-	struct mlx5_general_caps *gen;
 	int err = -EINVAL;
 	int port;
 
-	gen = &dev->mdev->caps.gen;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
@@ -1793,21 +1784,25 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		goto out;
 
 	if ((attr_mask & IB_QP_PORT) &&
-	    (attr->port_num == 0 || attr->port_num > gen->num_ports))
+	    (attr->port_num == 0 ||
+	     attr->port_num > MLX5_CAP_GEN(dev->mdev, num_ports)))
 		goto out;
 
 	if (attr_mask & IB_QP_PKEY_INDEX) {
 		port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
-		if (attr->pkey_index >= gen->port[port - 1].pkey_table_len)
+		if (attr->pkey_index >=
+		    dev->mdev->port_caps[port - 1].pkey_table_len)
 			goto out;
 	}
 
 	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
-	    attr->max_rd_atomic > (1 << gen->log_max_ra_res_qp))
+	    attr->max_rd_atomic >
+	    (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp)))
 		goto out;
 
 	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
-	    attr->max_dest_rd_atomic > (1 << gen->log_max_ra_req_qp))
+	    attr->max_dest_rd_atomic >
+	    (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp)))
 		goto out;
 
 	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
@@ -3009,7 +3004,7 @@ static void to_ib_ah_attr(struct mlx5_ib_dev *ibdev, struct ib_ah_attr *ib_ah_at
 	ib_ah_attr->port_num	  = path->port;
 
 	if (ib_ah_attr->port_num == 0 ||
-	    ib_ah_attr->port_num > dev->caps.gen.num_ports)
+	    ib_ah_attr->port_num > MLX5_CAP_GEN(dev, num_ports))
 		return;
 
 	ib_ah_attr->sl = path->sl & 0xf;
@@ -3135,12 +3130,10 @@ struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
-	struct mlx5_general_caps *gen;
 	struct mlx5_ib_xrcd *xrcd;
 	int err;
 
-	gen = &dev->mdev->caps.gen;
-	if (!(gen->flags & MLX5_DEV_CAP_FLAG_XRC))
+	if (!MLX5_CAP_GEN(dev->mdev, xrc))
 		return ERR_PTR(-ENOSYS);
 
 	xrcd = kmalloc(sizeof(*xrcd), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 02d77a29764d..e008505e96e9 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -165,7 +165,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
 		return err;
 	}
 
-	if (mlx5_buf_alloc(dev->mdev, buf_size, PAGE_SIZE * 2, &srq->buf)) {
+	if (mlx5_buf_alloc(dev->mdev, buf_size, &srq->buf)) {
 		mlx5_ib_dbg(dev, "buf alloc failed\n");
 		err = -ENOMEM;
 		goto err_db;
@@ -236,7 +236,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 				  struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
-	struct mlx5_general_caps *gen;
 	struct mlx5_ib_srq *srq;
 	int desc_size;
 	int buf_size;
@@ -245,13 +244,13 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	int uninitialized_var(inlen);
 	int is_xrc;
 	u32 flgs, xrcdn;
+	__u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
 
-	gen = &dev->mdev->caps.gen;
 	/* Sanity check SRQ size before proceeding */
-	if (init_attr->attr.max_wr >= gen->max_srq_wqes) {
+	if (init_attr->attr.max_wr >= max_srq_wqes) {
 		mlx5_ib_dbg(dev, "max_wr %d, cap %d\n",
 			    init_attr->attr.max_wr,
-			    gen->max_srq_wqes);
+			    max_srq_wqes);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -303,7 +302,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 
 	in->ctx.pd = cpu_to_be32(to_mpd(pd)->pdn);
 	in->ctx.db_record = cpu_to_be64(srq->db.dma);
-	err = mlx5_core_create_srq(dev->mdev, &srq->msrq, in, inlen);
+	err = mlx5_core_create_srq(dev->mdev, &srq->msrq, in, inlen, is_xrc);
 	kvfree(in);
 	if (err) {
 		mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err);
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 9d3e5c1ac60e..c7f49bbb0c72 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1858,8 +1858,8 @@ int mthca_CONF_SPECIAL_QP(struct mthca_dev *dev, int type, u32 qpn)
 }
 
 int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
-		  int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		  void *in_mad, void *response_mad)
+		  int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		  const void *in_mad, void *response_mad)
 {
 	struct mthca_mailbox *inmailbox, *outmailbox;
 	void *inbox;
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.h b/drivers/infiniband/hw/mthca/mthca_cmd.h
index f952244c54de..d2e5b194b938 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.h
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.h
@@ -312,8 +312,8 @@ int mthca_QUERY_QP(struct mthca_dev *dev, u32 num, int is_ee,
 		   struct mthca_mailbox *mailbox);
 int mthca_CONF_SPECIAL_QP(struct mthca_dev *dev, int type, u32 qpn);
 int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
-		  int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		  void *in_mad, void *response_mad);
+		  int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		  const void *in_mad, void *response_mad);
 int mthca_READ_MGM(struct mthca_dev *dev, int index,
 		   struct mthca_mailbox *mailbox);
 int mthca_WRITE_MGM(struct mthca_dev *dev, int index,
diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h
index 7e6a6d64ad4e..4393a022867b 100644
--- a/drivers/infiniband/hw/mthca/mthca_dev.h
+++ b/drivers/infiniband/hw/mthca/mthca_dev.h
@@ -576,10 +576,11 @@ int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 int mthca_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad,
-		      struct ib_mad *out_mad);
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 int mthca_create_agents(struct mthca_dev *dev);
 void mthca_free_agents(struct mthca_dev *dev);
 
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 8881fa376e06..6b2418b74c99 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -104,7 +104,7 @@ static void update_sm_ah(struct mthca_dev *dev,
  */
 static void smp_snoop(struct ib_device *ibdev,
 		      u8 port_num,
-		      struct ib_mad *mad,
+		      const struct ib_mad *mad,
 		      u16 prev_lid)
 {
 	struct ib_event event;
@@ -160,7 +160,7 @@ static void node_desc_override(struct ib_device *dev,
 
 static void forward_trap(struct mthca_dev *dev,
 			 u8 port_num,
-			 struct ib_mad *mad)
+			 const struct ib_mad *mad)
 {
 	int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
 	struct ib_mad_send_buf *send_buf;
@@ -170,7 +170,8 @@ static void forward_trap(struct mthca_dev *dev,
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
-					      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+					      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+					      IB_MGMT_BASE_VERSION);
 		if (IS_ERR(send_buf))
 			return;
 		/*
@@ -195,15 +196,21 @@ static void forward_trap(struct mthca_dev *dev,
 int mthca_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad,
-		      struct ib_mad *out_mad)
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int err;
 	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	/* Forward locally generated traps to the SM */
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&
diff --git a/drivers/infiniband/hw/mthca/mthca_profile.c b/drivers/infiniband/hw/mthca/mthca_profile.c
index 8edb28a9a0e7..15d064479ef6 100644
--- a/drivers/infiniband/hw/mthca/mthca_profile.c
+++ b/drivers/infiniband/hw/mthca/mthca_profile.c
@@ -77,7 +77,6 @@ s64 mthca_make_profile(struct mthca_dev *dev,
 	u64 mem_base, mem_avail;
 	s64 total_size = 0;
 	struct mthca_resource *profile;
-	struct mthca_resource tmp;
 	int i, j;
 
 	profile = kzalloc(MTHCA_RES_NUM * sizeof *profile, GFP_KERNEL);
@@ -136,11 +135,8 @@ s64 mthca_make_profile(struct mthca_dev *dev,
 	 */
 	for (i = MTHCA_RES_NUM; i > 0; --i)
 		for (j = 1; j < i; ++j) {
-			if (profile[j].size > profile[j - 1].size) {
-				tmp            = profile[j];
-				profile[j]     = profile[j - 1];
-				profile[j - 1] = tmp;
-			}
+			if (profile[j].size > profile[j - 1].size)
+				swap(profile[j], profile[j - 1]);
 		}
 
 	for (i = 0; i < MTHCA_RES_NUM; ++i) {
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 415f8e1a54db..93ae51dcf2ff 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -57,14 +57,17 @@ static void init_query_mad(struct ib_smp *mad)
 	mad->method    	   = IB_MGMT_METHOD_GET;
 }
 
-static int mthca_query_device(struct ib_device *ibdev,
-			      struct ib_device_attr *props)
+static int mthca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			      struct ib_udata *uhw)
 {
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
 	int err = -ENOMEM;
 	struct mthca_dev *mdev = to_mdev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
 	if (!in_mad || !out_mad)
@@ -641,16 +644,20 @@ static int mthca_destroy_qp(struct ib_qp *qp)
 	return 0;
 }
 
-static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
-				     int comp_vector,
+static struct ib_cq *mthca_create_cq(struct ib_device *ibdev,
+				     const struct ib_cq_init_attr *attr,
 				     struct ib_ucontext *context,
 				     struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct mthca_create_cq ucmd;
 	struct mthca_cq *cq;
 	int nent;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > to_mdev(ibdev)->limits.max_cqes)
 		return ERR_PTR(-EINVAL);
 
@@ -1244,6 +1251,24 @@ out:
 	return err;
 }
 
+static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mthca_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 int mthca_register_device(struct mthca_dev *dev)
 {
 	int ret;
@@ -1323,6 +1348,7 @@ int mthca_register_device(struct mthca_dev *dev)
 	dev->ib_dev.reg_phys_mr          = mthca_reg_phys_mr;
 	dev->ib_dev.reg_user_mr          = mthca_reg_user_mr;
 	dev->ib_dev.dereg_mr             = mthca_dereg_mr;
+	dev->ib_dev.get_port_immutable   = mthca_port_immutable;
 
 	if (dev->mthca_flags & MTHCA_FLAG_FMR) {
 		dev->ib_dev.alloc_fmr            = mthca_alloc_fmr;
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 3b2a6dc8ea99..9f9d5c563a61 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -116,6 +116,7 @@ static struct ibnl_client_cbs nes_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
+	[RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
 	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
 	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
 	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 6f09a72e78d7..9047af429906 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -596,27 +596,52 @@ static void nes_form_reg_msg(struct nes_vnic *nesvnic,
 	memcpy(pm_msg->if_name, nesvnic->netdev->name, IWPM_IFNAME_SIZE);
 }
 
+static void record_sockaddr_info(struct sockaddr_storage *addr_info,
+					nes_addr_t *ip_addr, u16 *port_num)
+{
+	struct sockaddr_in *in_addr = (struct sockaddr_in *)addr_info;
+
+	if (in_addr->sin_family == AF_INET) {
+		*ip_addr = ntohl(in_addr->sin_addr.s_addr);
+		*port_num = ntohs(in_addr->sin_port);
+	}
+}
+
 /*
  * nes_record_pm_msg - Save the received mapping info
  */
 static void nes_record_pm_msg(struct nes_cm_info *cm_info,
 			struct iwpm_sa_data *pm_msg)
 {
-	struct sockaddr_in *mapped_loc_addr =
-			(struct sockaddr_in *)&pm_msg->mapped_loc_addr;
-	struct sockaddr_in *mapped_rem_addr =
-			(struct sockaddr_in *)&pm_msg->mapped_rem_addr;
-
-	if (mapped_loc_addr->sin_family == AF_INET) {
-		cm_info->mapped_loc_addr =
-			ntohl(mapped_loc_addr->sin_addr.s_addr);
-		cm_info->mapped_loc_port = ntohs(mapped_loc_addr->sin_port);
-	}
-	if (mapped_rem_addr->sin_family == AF_INET) {
-		cm_info->mapped_rem_addr =
-			ntohl(mapped_rem_addr->sin_addr.s_addr);
-		cm_info->mapped_rem_port = ntohs(mapped_rem_addr->sin_port);
-	}
+	record_sockaddr_info(&pm_msg->mapped_loc_addr,
+		&cm_info->mapped_loc_addr, &cm_info->mapped_loc_port);
+
+	record_sockaddr_info(&pm_msg->mapped_rem_addr,
+		&cm_info->mapped_rem_addr, &cm_info->mapped_rem_port);
+}
+
+/*
+ * nes_get_reminfo - Get the address info of the remote connecting peer
+ */
+static int nes_get_remote_addr(struct nes_cm_node *cm_node)
+{
+	struct sockaddr_storage mapped_loc_addr, mapped_rem_addr;
+	struct sockaddr_storage remote_addr;
+	int ret;
+
+	nes_create_sockaddr(htonl(cm_node->mapped_loc_addr),
+			htons(cm_node->mapped_loc_port), &mapped_loc_addr);
+	nes_create_sockaddr(htonl(cm_node->mapped_rem_addr),
+			htons(cm_node->mapped_rem_port), &mapped_rem_addr);
+
+	ret = iwpm_get_remote_info(&mapped_loc_addr, &mapped_rem_addr,
+				&remote_addr, RDMA_NL_NES);
+	if (ret)
+		nes_debug(NES_DBG_CM, "Unable to find remote peer address info\n");
+	else
+		record_sockaddr_info(&remote_addr, &cm_node->rem_addr,
+				&cm_node->rem_port);
+	return ret;
 }
 
 /**
@@ -1566,9 +1591,14 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 		return NULL;
 
 	/* set our node specific transport info */
-	cm_node->loc_addr = cm_info->loc_addr;
+	if (listener) {
+		cm_node->loc_addr = listener->loc_addr;
+		cm_node->loc_port = listener->loc_port;
+	} else {
+		cm_node->loc_addr = cm_info->loc_addr;
+		cm_node->loc_port = cm_info->loc_port;
+	}
 	cm_node->rem_addr = cm_info->rem_addr;
-	cm_node->loc_port = cm_info->loc_port;
 	cm_node->rem_port = cm_info->rem_port;
 
 	cm_node->mapped_loc_addr = cm_info->mapped_loc_addr;
@@ -1586,6 +1616,8 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 		  &cm_node->loc_addr, cm_node->loc_port,
 		  &cm_node->rem_addr, cm_node->rem_port);
 	cm_node->listener = listener;
+	if (listener)
+		cm_node->tos = listener->tos;
 	cm_node->netdev = nesvnic->netdev;
 	cm_node->cm_id = cm_info->cm_id;
 	memcpy(cm_node->loc_mac, nesvnic->netdev->dev_addr, ETH_ALEN);
@@ -2151,6 +2183,7 @@ static int handle_ack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		cm_node->state = NES_CM_STATE_ESTABLISHED;
 		if (datasize) {
 			cm_node->tcp_cntxt.rcv_nxt = inc_sequence + datasize;
+			nes_get_remote_addr(cm_node);
 			handle_rcv_mpa(cm_node, skb);
 		} else { /* rcvd ACK only */
 			dev_kfree_skb_any(skb);
@@ -2907,6 +2940,9 @@ static int nes_cm_init_tsa_conn(struct nes_qp *nesqp, struct nes_cm_node *cm_nod
 
 	nesqp->nesqp_context->misc2 |= cpu_to_le32(64 << NES_QPCONTEXT_MISC2_TTL_SHIFT);
 
+	nesqp->nesqp_context->misc2 |= cpu_to_le32(
+		cm_node->tos << NES_QPCONTEXT_MISC2_TOS_SHIFT);
+
 	nesqp->nesqp_context->mss |= cpu_to_le32(((u32)cm_node->tcp_cntxt.mss) << 16);
 
 	nesqp->nesqp_context->tcp_state_flow_label |= cpu_to_le32(
@@ -3581,6 +3617,7 @@ int nes_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		cm_node->ord_size = 1;
 
 	cm_node->apbvt_set = apbvt_set;
+	cm_node->tos = cm_id->tos;
 	nesqp->cm_node = cm_node;
 	cm_node->nesqp = nesqp;
 	nes_add_ref(&nesqp->ibqp);
@@ -3635,6 +3672,7 @@ int nes_create_listen(struct iw_cm_id *cm_id, int backlog)
 	}
 
 	cm_id->provider_data = cm_node;
+	cm_node->tos = cm_id->tos;
 
 	if (!cm_node->reused_node) {
 		if (nes_create_mapinfo(&cm_info))
diff --git a/drivers/infiniband/hw/nes/nes_cm.h b/drivers/infiniband/hw/nes/nes_cm.h
index f522cf639789..32a6420c2940 100644
--- a/drivers/infiniband/hw/nes/nes_cm.h
+++ b/drivers/infiniband/hw/nes/nes_cm.h
@@ -303,6 +303,7 @@ struct nes_cm_listener {
 	int                        backlog;
 	enum nes_cm_listener_state listener_state;
 	u32                        reused_node;
+	u8			   tos;
 };
 
 /* per connection node and node state information */
@@ -352,6 +353,7 @@ struct nes_cm_node {
 	struct list_head	reset_entry;
 	struct nes_qp		*nesqp;
 	atomic_t 		passive_state;
+	u8			tos;
 };
 
 /* structure for client or CM to fill when making CM api calls. */
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index c0d0296e7a00..fbc43e5f717b 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -512,12 +512,16 @@ static void nes_free_fast_reg_page_list(struct ib_fast_reg_page_list *pifrpl)
 /**
  * nes_query_device
  */
-static int nes_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
+static int nes_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			    struct ib_udata *uhw)
 {
 	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
 	struct nes_ib_device *nesibdev = nesvnic->nesibdev;
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(props, 0, sizeof(*props));
 	memcpy(&props->sys_image_guid, nesvnic->netdev->dev_addr, 6);
 
@@ -606,7 +610,6 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	return 0;
 }
 
-
 /**
  * nes_query_pkey
  */
@@ -1527,10 +1530,12 @@ static int nes_destroy_qp(struct ib_qp *ibqp)
 /**
  * nes_create_cq
  */
-static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
-		int comp_vector,
-		struct ib_ucontext *context, struct ib_udata *udata)
+static struct ib_cq *nes_create_cq(struct ib_device *ibdev,
+				   const struct ib_cq_init_attr *attr,
+				   struct ib_ucontext *context,
+				   struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	u64 u64temp;
 	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
@@ -1550,6 +1555,9 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 	unsigned long flags;
 	int ret;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries > nesadapter->max_cqe)
 		return ERR_PTR(-EINVAL);
 
@@ -3222,8 +3230,10 @@ static int nes_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
  * nes_process_mad
  */
 static int nes_process_mad(struct ib_device *ibdev, int mad_flags,
-		u8 port_num, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		struct ib_mad *in_mad, struct ib_mad *out_mad)
+		u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		const struct ib_mad_hdr *in, size_t in_mad_size,
+		struct ib_mad_hdr *out, size_t *out_mad_size,
+		u16 *out_mad_pkey_index)
 {
 	nes_debug(NES_DBG_INIT, "\n");
 	return -ENOSYS;
@@ -3828,6 +3838,22 @@ static int nes_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_
 	return 0;
 }
 
+static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
+			      struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = nes_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
 
 /**
  * nes_init_ofa_device
@@ -3928,6 +3954,7 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
 	nesibdev->ibdev.iwcm->reject = nes_reject;
 	nesibdev->ibdev.iwcm->create_listen = nes_create_listen;
 	nesibdev->ibdev.iwcm->destroy_listen = nes_destroy_listen;
+	nesibdev->ibdev.get_port_immutable   = nes_port_immutable;
 
 	return nesibdev;
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index c9780d919769..b396344fae16 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -40,7 +40,7 @@
 #include <be_roce.h>
 #include "ocrdma_sli.h"
 
-#define OCRDMA_ROCE_DRV_VERSION "10.4.205.0u"
+#define OCRDMA_ROCE_DRV_VERSION "10.6.0.0"
 
 #define OCRDMA_ROCE_DRV_DESC "Emulex OneConnect RoCE Driver"
 #define OCRDMA_NODE_DESC "Emulex OneConnect RoCE HCA"
@@ -515,6 +515,8 @@ static inline int ocrdma_resolve_dmac(struct ocrdma_dev *dev,
 	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
 	if (rdma_is_multicast_addr(&in6))
 		rdma_get_mcast_mac(&in6, mac_addr);
+	else if (rdma_link_local_addr(&in6))
+		rdma_get_ll_mac(&in6, mac_addr);
 	else
 		memcpy(mac_addr, ah_attr->dmac, ETH_ALEN);
 	return 0;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index d812904f3984..4bafa15708d0 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -56,7 +56,13 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 	vlan_tag = attr->vlan_id;
 	if (!vlan_tag || (vlan_tag > 0xFFF))
 		vlan_tag = dev->pvid;
-	if (vlan_tag && (vlan_tag < 0x1000)) {
+	if (vlan_tag || dev->pfc_state) {
+		if (!vlan_tag) {
+			pr_err("ocrdma%d:Using VLAN with PFC is recommended\n",
+				dev->id);
+			pr_err("ocrdma%d:Using VLAN 0 for this connection\n",
+				dev->id);
+		}
 		eth.eth_type = cpu_to_be16(0x8100);
 		eth.roce_eth_type = cpu_to_be16(OCRDMA_ROCE_ETH_TYPE);
 		vlan_tag |= (dev->sl & 0x07) << OCRDMA_VID_PCP_SHIFT;
@@ -121,7 +127,9 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
 		goto av_conf_err;
 	}
 
-	if (pd->uctx) {
+	if ((pd->uctx) &&
+	    (!rdma_is_multicast_addr((struct in6_addr *)attr->grh.dgid.raw)) &&
+	    (!rdma_link_local_addr((struct in6_addr *)attr->grh.dgid.raw))) {
 		status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid,
                                         attr->dmac, &attr->vlan_id);
 		if (status) {
@@ -196,12 +204,19 @@ int ocrdma_modify_ah(struct ib_ah *ibah, struct ib_ah_attr *attr)
 int ocrdma_process_mad(struct ib_device *ibdev,
 		       int process_mad_flags,
 		       u8 port_num,
-		       struct ib_wc *in_wc,
-		       struct ib_grh *in_grh,
-		       struct ib_mad *in_mad, struct ib_mad *out_mad)
+		       const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh,
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index)
 {
 	int status;
 	struct ocrdma_dev *dev;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_PERF_MGMT:
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index 726a87cf22dc..cf366fe03cb8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -42,7 +42,9 @@ int ocrdma_modify_ah(struct ib_ah *, struct ib_ah_attr *);
 int ocrdma_process_mad(struct ib_device *,
 		       int process_mad_flags,
 		       u8 port_num,
-		       struct ib_wc *in_wc,
-		       struct ib_grh *in_grh,
-		       struct ib_mad *in_mad, struct ib_mad *out_mad);
+		       const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh,
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index);
 #endif				/* __OCRDMA_AH_H__ */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 0c9e95909a64..47615ff33bc6 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -933,12 +933,18 @@ static irqreturn_t ocrdma_irq_handler(int irq, void *handle)
 	struct ocrdma_eqe eqe;
 	struct ocrdma_eqe *ptr;
 	u16 cq_id;
+	u8 mcode;
 	int budget = eq->cq_cnt;
 
 	do {
 		ptr = ocrdma_get_eqe(eq);
 		eqe = *ptr;
 		ocrdma_le32_to_cpu(&eqe, sizeof(eqe));
+		mcode = (eqe.id_valid & OCRDMA_EQE_MAJOR_CODE_MASK)
+				>> OCRDMA_EQE_MAJOR_CODE_SHIFT;
+		if (mcode == OCRDMA_MAJOR_CODE_SENTINAL)
+			pr_err("EQ full on eqid = 0x%x, eqe = 0x%x\n",
+			       eq->q.id, eqe.id_valid);
 		if ((eqe.id_valid & OCRDMA_EQE_VALID_MASK) == 0)
 			break;
 
@@ -1434,27 +1440,30 @@ static int ocrdma_mbx_alloc_pd_range(struct ocrdma_dev *dev)
 	struct ocrdma_alloc_pd_range_rsp *rsp;
 
 	/* Pre allocate the DPP PDs */
-	cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE, sizeof(*cmd));
-	if (!cmd)
-		return -ENOMEM;
-	cmd->pd_count = dev->attr.max_dpp_pds;
-	cmd->enable_dpp_rsvd |= OCRDMA_ALLOC_PD_ENABLE_DPP;
-	status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
-	if (status)
-		goto mbx_err;
-	rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
-
-	if ((rsp->dpp_page_pdid & OCRDMA_ALLOC_PD_RSP_DPP) && rsp->pd_count) {
-		dev->pd_mgr->dpp_page_index = rsp->dpp_page_pdid >>
-				OCRDMA_ALLOC_PD_RSP_DPP_PAGE_SHIFT;
-		dev->pd_mgr->pd_dpp_start = rsp->dpp_page_pdid &
-				OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
-		dev->pd_mgr->max_dpp_pd = rsp->pd_count;
-		pd_bitmap_size = BITS_TO_LONGS(rsp->pd_count) * sizeof(long);
-		dev->pd_mgr->pd_dpp_bitmap = kzalloc(pd_bitmap_size,
-						     GFP_KERNEL);
+	if (dev->attr.max_dpp_pds) {
+		cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE,
+					  sizeof(*cmd));
+		if (!cmd)
+			return -ENOMEM;
+		cmd->pd_count = dev->attr.max_dpp_pds;
+		cmd->enable_dpp_rsvd |= OCRDMA_ALLOC_PD_ENABLE_DPP;
+		status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
+		rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
+
+		if (!status && (rsp->dpp_page_pdid & OCRDMA_ALLOC_PD_RSP_DPP) &&
+		    rsp->pd_count) {
+			dev->pd_mgr->dpp_page_index = rsp->dpp_page_pdid >>
+					OCRDMA_ALLOC_PD_RSP_DPP_PAGE_SHIFT;
+			dev->pd_mgr->pd_dpp_start = rsp->dpp_page_pdid &
+					OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
+			dev->pd_mgr->max_dpp_pd = rsp->pd_count;
+			pd_bitmap_size =
+				BITS_TO_LONGS(rsp->pd_count) * sizeof(long);
+			dev->pd_mgr->pd_dpp_bitmap = kzalloc(pd_bitmap_size,
+							     GFP_KERNEL);
+		}
+		kfree(cmd);
 	}
-	kfree(cmd);
 
 	cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_ALLOC_PD_RANGE, sizeof(*cmd));
 	if (!cmd)
@@ -1462,10 +1471,8 @@ static int ocrdma_mbx_alloc_pd_range(struct ocrdma_dev *dev)
 
 	cmd->pd_count = dev->attr.max_pd - dev->attr.max_dpp_pds;
 	status = ocrdma_mbx_cmd(dev, (struct ocrdma_mqe *)cmd);
-	if (status)
-		goto mbx_err;
 	rsp = (struct ocrdma_alloc_pd_range_rsp *)cmd;
-	if (rsp->pd_count) {
+	if (!status && rsp->pd_count) {
 		dev->pd_mgr->pd_norm_start = rsp->dpp_page_pdid &
 					OCRDMA_ALLOC_PD_RNG_RSP_START_PDID_MASK;
 		dev->pd_mgr->max_normal_pd = rsp->pd_count;
@@ -1473,15 +1480,13 @@ static int ocrdma_mbx_alloc_pd_range(struct ocrdma_dev *dev)
 		dev->pd_mgr->pd_norm_bitmap = kzalloc(pd_bitmap_size,
 						      GFP_KERNEL);
 	}
+	kfree(cmd);
 
 	if (dev->pd_mgr->pd_norm_bitmap || dev->pd_mgr->pd_dpp_bitmap) {
 		/* Enable PD resource manager */
 		dev->pd_mgr->pd_prealloc_valid = true;
-	} else {
-		return -ENOMEM;
+		return 0;
 	}
-mbx_err:
-	kfree(cmd);
 	return status;
 }
 
@@ -2406,7 +2411,7 @@ int ocrdma_mbx_query_qp(struct ocrdma_dev *dev, struct ocrdma_qp *qp,
 	struct ocrdma_query_qp *cmd;
 	struct ocrdma_query_qp_rsp *rsp;
 
-	cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_QUERY_QP, sizeof(*cmd));
+	cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_QUERY_QP, sizeof(*rsp));
 	if (!cmd)
 		return status;
 	cmd->qp_id = qp->id;
@@ -2428,7 +2433,7 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp,
 	int status;
 	struct ib_ah_attr *ah_attr = &attrs->ah_attr;
 	union ib_gid sgid, zgid;
-	u32 vlan_id;
+	u32 vlan_id = 0xFFFF;
 	u8 mac_addr[6];
 	struct ocrdma_dev *dev = get_ocrdma_dev(qp->ibqp.device);
 
@@ -2468,12 +2473,22 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp,
 	cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8);
 	if (attr_mask & IB_QP_VID) {
 		vlan_id = attrs->vlan_id;
+	} else if (dev->pfc_state) {
+		vlan_id = 0;
+		pr_err("ocrdma%d:Using VLAN with PFC is recommended\n",
+			dev->id);
+		pr_err("ocrdma%d:Using VLAN 0 for this connection\n",
+			dev->id);
+	}
+
+	if (vlan_id < 0x1000) {
 		cmd->params.vlan_dmac_b4_to_b5 |=
 		    vlan_id << OCRDMA_QP_PARAMS_VLAN_SHIFT;
 		cmd->flags |= OCRDMA_QP_PARA_VLAN_EN_VALID;
 		cmd->params.rnt_rc_sl_fl |=
 			(dev->sl & 0x07) << OCRDMA_QP_PARAMS_SL_SHIFT;
 	}
+
 	return 0;
 }
 
@@ -2519,8 +2534,10 @@ static int ocrdma_set_qp_params(struct ocrdma_qp *qp,
 		cmd->flags |= OCRDMA_QP_PARA_DST_QPN_VALID;
 	}
 	if (attr_mask & IB_QP_PATH_MTU) {
-		if (attrs->path_mtu < IB_MTU_256 ||
+		if (attrs->path_mtu < IB_MTU_512 ||
 		    attrs->path_mtu > IB_MTU_4096) {
+			pr_err("ocrdma%d: IB MTU %d is not supported\n",
+			       dev->id, ib_mtu_enum_to_int(attrs->path_mtu));
 			status = -EINVAL;
 			goto pmtu_err;
 		}
@@ -3147,9 +3164,9 @@ void ocrdma_cleanup_hw(struct ocrdma_dev *dev)
 	ocrdma_free_pd_pool(dev);
 	ocrdma_mbx_delete_ah_tbl(dev);
 
-	/* cleanup the eqs */
-	ocrdma_destroy_eqs(dev);
-
 	/* cleanup the control path */
 	ocrdma_destroy_mq(dev);
+
+	/* cleanup the eqs */
+	ocrdma_destroy_eqs(dev);
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 7a2b59aca004..8a1398b253a2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -30,6 +30,7 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
+#include <rdma/ib_mad.h>
 
 #include <linux/netdevice.h>
 #include <net/addrconf.h>
@@ -202,6 +203,24 @@ static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device,
 	return IB_LINK_LAYER_ETHERNET;
 }
 
+static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
+			         struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ocrdma_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static int ocrdma_register_device(struct ocrdma_dev *dev)
 {
 	strlcpy(dev->ibdev.name, "ocrdma%d", IB_DEVICE_NAME_MAX);
@@ -286,6 +305,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	dev->ibdev.dma_device = &dev->nic_info.pdev->dev;
 
 	dev->ibdev.process_mad = ocrdma_process_mad;
+	dev->ibdev.get_port_immutable = ocrdma_port_immutable;
 
 	if (ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R) {
 		dev->ibdev.uverbs_cmd_mask |=
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 243c87c8bd65..02ad0aee99af 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -1176,6 +1176,8 @@ struct ocrdma_query_qp_rsp {
 	struct ocrdma_mqe_hdr hdr;
 	struct ocrdma_mbx_rsp rsp;
 	struct ocrdma_qp_params params;
+	u32 dpp_credits_cqid;
+	u32 rbq_id;
 };
 
 enum {
@@ -1624,12 +1626,19 @@ struct ocrdma_delete_ah_tbl_rsp {
 enum {
 	OCRDMA_EQE_VALID_SHIFT		= 0,
 	OCRDMA_EQE_VALID_MASK		= BIT(0),
+	OCRDMA_EQE_MAJOR_CODE_MASK      = 0x0E,
+	OCRDMA_EQE_MAJOR_CODE_SHIFT     = 0x01,
 	OCRDMA_EQE_FOR_CQE_MASK		= 0xFFFE,
 	OCRDMA_EQE_RESOURCE_ID_SHIFT	= 16,
 	OCRDMA_EQE_RESOURCE_ID_MASK	= 0xFFFF <<
 				OCRDMA_EQE_RESOURCE_ID_SHIFT,
 };
 
+enum major_code {
+	OCRDMA_MAJOR_CODE_COMPLETION    = 0x00,
+	OCRDMA_MAJOR_CODE_SENTINAL      = 0x01
+};
+
 struct ocrdma_eqe {
 	u32 id_valid;
 };
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 877175563634..5bb61eb58f2c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -61,10 +61,14 @@ int ocrdma_query_gid(struct ib_device *ibdev, u8 port,
 	return 0;
 }
 
-int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr)
+int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
+			struct ib_udata *uhw)
 {
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(attr, 0, sizeof *attr);
 	memcpy(&attr->fw_ver, &dev->attr.fw_ver[0],
 	       min(sizeof(dev->attr.fw_ver), sizeof(attr->fw_ver)));
@@ -365,7 +369,7 @@ static struct ocrdma_pd *_ocrdma_alloc_pd(struct ocrdma_dev *dev,
 	if (!pd)
 		return ERR_PTR(-ENOMEM);
 
-	if (udata && uctx) {
+	if (udata && uctx && dev->attr.max_dpp_pds) {
 		pd->dpp_enabled =
 			ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R;
 		pd->num_dpp_qp =
@@ -375,7 +379,12 @@ static struct ocrdma_pd *_ocrdma_alloc_pd(struct ocrdma_dev *dev,
 
 	if (dev->pd_mgr->pd_prealloc_valid) {
 		status = ocrdma_get_pd_num(dev, pd);
-		return (status == 0) ? pd : ERR_PTR(status);
+		if (status == 0) {
+			return pd;
+		} else {
+			kfree(pd);
+			return ERR_PTR(status);
+		}
 	}
 
 retry:
@@ -679,7 +688,6 @@ err:
 		ocrdma_release_ucontext_pd(uctx);
 	} else {
 		status = _ocrdma_dealloc_pd(dev, pd);
-		kfree(pd);
 	}
 exit:
 	return ERR_PTR(status);
@@ -1000,10 +1008,12 @@ err:
 	return status;
 }
 
-struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
+struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
+			       const struct ib_cq_init_attr *attr,
 			       struct ib_ucontext *ib_ctx,
 			       struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct ocrdma_cq *cq;
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
 	struct ocrdma_ucontext *uctx = NULL;
@@ -1011,6 +1021,9 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
 	int status;
 	struct ocrdma_create_cq_ureq ureq;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (udata) {
 		if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
 			return ERR_PTR(-EFAULT);
@@ -1721,18 +1734,20 @@ int ocrdma_destroy_qp(struct ib_qp *ibqp)
 	struct ocrdma_qp *qp;
 	struct ocrdma_dev *dev;
 	struct ib_qp_attr attrs;
-	int attr_mask = IB_QP_STATE;
+	int attr_mask;
 	unsigned long flags;
 
 	qp = get_ocrdma_qp(ibqp);
 	dev = get_ocrdma_dev(ibqp->device);
 
-	attrs.qp_state = IB_QPS_ERR;
 	pd = qp->pd;
 
 	/* change the QP state to ERROR */
-	_ocrdma_modify_qp(ibqp, &attrs, attr_mask);
-
+	if (qp->state != OCRDMA_QPS_RST) {
+		attrs.qp_state = IB_QPS_ERR;
+		attr_mask = IB_QP_STATE;
+		_ocrdma_modify_qp(ibqp, &attrs, attr_mask);
+	}
 	/* ensure that CQEs for newly created QP (whose id may be same with
 	 * one which just getting destroyed are same), dont get
 	 * discarded until the old CQEs are discarded.
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index b8f7853fd36c..b15c608efa7b 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -36,11 +36,15 @@ int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *,
 int ocrdma_poll_cq(struct ib_cq *, int num_entries, struct ib_wc *wc);
 int ocrdma_arm_cq(struct ib_cq *, enum ib_cq_notify_flags flags);
 
-int ocrdma_query_device(struct ib_device *, struct ib_device_attr *props);
+int ocrdma_query_device(struct ib_device *, struct ib_device_attr *props,
+			struct ib_udata *uhw);
 int ocrdma_query_port(struct ib_device *, u8 port, struct ib_port_attr *props);
 int ocrdma_modify_port(struct ib_device *, u8 port, int mask,
 		       struct ib_port_modify *props);
 
+enum rdma_protocol_type
+ocrdma_query_protocol(struct ib_device *device, u8 port_num);
+
 void ocrdma_get_guid(struct ocrdma_dev *, u8 *guid);
 int ocrdma_query_gid(struct ib_device *, u8 port,
 		     int index, union ib_gid *gid);
@@ -56,8 +60,10 @@ struct ib_pd *ocrdma_alloc_pd(struct ib_device *,
 			      struct ib_ucontext *, struct ib_udata *);
 int ocrdma_dealloc_pd(struct ib_pd *pd);
 
-struct ib_cq *ocrdma_create_cq(struct ib_device *, int entries, int vector,
-			       struct ib_ucontext *, struct ib_udata *);
+struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
+			       const struct ib_cq_init_attr *attr,
+			       struct ib_ucontext *ib_ctx,
+			       struct ib_udata *udata);
 int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
 int ocrdma_destroy_cq(struct ib_cq *);
 
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index ffd48bfc4923..7df16f74bb45 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -903,7 +903,7 @@ struct qib_devdata {
 	/* PCI Device ID (here for NodeInfo) */
 	u16 deviceid;
 	/* for write combining settings */
-	unsigned long wc_cookie;
+	int wc_cookie;
 	unsigned long wc_base;
 	unsigned long wc_len;
 
@@ -1136,7 +1136,6 @@ extern struct qib_devdata *qib_lookup(int unit);
 extern u32 qib_cpulist_count;
 extern unsigned long *qib_cpulist;
 
-extern unsigned qib_wc_pat;
 extern unsigned qib_cc_table_size;
 int qib_init(struct qib_devdata *, int);
 int init_chip_wc_pat(struct qib_devdata *dd, u32);
diff --git a/drivers/infiniband/hw/qib/qib_cq.c b/drivers/infiniband/hw/qib/qib_cq.c
index ab4e11cfab15..2b45d0b02300 100644
--- a/drivers/infiniband/hw/qib/qib_cq.c
+++ b/drivers/infiniband/hw/qib/qib_cq.c
@@ -203,7 +203,7 @@ static void send_complete(struct kthread_work *work)
 /**
  * qib_create_cq - create a completion queue
  * @ibdev: the device this completion queue is attached to
- * @entries: the minimum size of the completion queue
+ * @attr: creation attributes
  * @context: unused by the QLogic_IB driver
  * @udata: user data for libibverbs.so
  *
@@ -212,16 +212,21 @@ static void send_complete(struct kthread_work *work)
  *
  * Called by ib_create_cq() in the generic verbs code.
  */
-struct ib_cq *qib_create_cq(struct ib_device *ibdev, int entries,
-			    int comp_vector, struct ib_ucontext *context,
+struct ib_cq *qib_create_cq(struct ib_device *ibdev,
+			    const struct ib_cq_init_attr *attr,
+			    struct ib_ucontext *context,
 			    struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct qib_ibdev *dev = to_idev(ibdev);
 	struct qib_cq *cq;
 	struct qib_cq_wc *wc;
 	struct ib_cq *ret;
 	u32 sz;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > ib_qib_max_cqes) {
 		ret = ERR_PTR(-EINVAL);
 		goto done;
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 9ea6c440a00c..725881890c4a 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -835,7 +835,8 @@ static int mmap_piobufs(struct vm_area_struct *vma,
 	vma->vm_flags &= ~VM_MAYREAD;
 	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
 
-	if (qib_wc_pat)
+	/* We used PAT if wc_cookie == 0 */
+	if (!dd->wc_cookie)
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 
 	ret = io_remap_pfn_range(vma, vma->vm_start, phys >> PAGE_SHIFT,
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index 0d2ba59af30a..4b927809d1a1 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -3315,11 +3315,9 @@ static int init_6120_variables(struct qib_devdata *dd)
 	qib_6120_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);
 
-	if (qib_wc_pat) {
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
-	}
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 	set_6120_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 22affda8af88..00b2af211157 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -4126,11 +4126,9 @@ static int qib_init_7220_variables(struct qib_devdata *dd)
 	qib_7220_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);  /* needed for PAT setup */
 
-	if (qib_wc_pat) {
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
-	}
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 	set_7220_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index ef97b71c8f7d..6c8ff10101c0 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -5502,7 +5502,8 @@ static void try_7322_ipg(struct qib_pportdata *ppd)
 		goto retry;
 
 	send_buf = ib_create_send_mad(agent, 0, 0, 0, IB_MGMT_MAD_HDR,
-				      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+				      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+				      IB_MGMT_BASE_VERSION);
 	if (IS_ERR(send_buf))
 		goto retry;
 
@@ -6429,6 +6430,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 	unsigned features, pidx, sbufcnt;
 	int ret, mtu;
 	u32 sbufs, updthresh;
+	resource_size_t vl15off;
 
 	/* pport structs are contiguous, allocated after devdata */
 	ppd = (struct qib_pportdata *)(dd + 1);
@@ -6677,29 +6679,27 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 	qib_7322_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);
 
-	if (qib_wc_pat) {
-		resource_size_t vl15off;
-		/*
-		 * We do not set WC on the VL15 buffers to avoid
-		 * a rare problem with unaligned writes from
-		 * interrupt-flushed store buffers, so we need
-		 * to map those separately here.  We can't solve
-		 * this for the rarely used mtrr case.
-		 */
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
+	/*
+	 * We do not set WC on the VL15 buffers to avoid
+	 * a rare problem with unaligned writes from
+	 * interrupt-flushed store buffers, so we need
+	 * to map those separately here.  We can't solve
+	 * this for the rarely used mtrr case.
+	 */
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 
-		/* vl15 buffers start just after the 4k buffers */
-		vl15off = dd->physaddr + (dd->piobufbase >> 32) +
-			dd->piobcnt4k * dd->align4k;
-		dd->piovl15base	= ioremap_nocache(vl15off,
-						  NUM_VL15_BUFS * dd->align4k);
-		if (!dd->piovl15base) {
-			ret = -ENOMEM;
-			goto bail;
-		}
+	/* vl15 buffers start just after the 4k buffers */
+	vl15off = dd->physaddr + (dd->piobufbase >> 32) +
+		  dd->piobcnt4k * dd->align4k;
+	dd->piovl15base	= ioremap_nocache(vl15off,
+					  NUM_VL15_BUFS * dd->align4k);
+	if (!dd->piovl15base) {
+		ret = -ENOMEM;
+		goto bail;
 	}
+
 	qib_7322_set_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 2ee36953e234..7e00470adc30 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -91,15 +91,6 @@ MODULE_PARM_DESC(krcvqs, "number of kernel receive queues per IB port");
 unsigned qib_cc_table_size;
 module_param_named(cc_table_size, qib_cc_table_size, uint, S_IRUGO);
 MODULE_PARM_DESC(cc_table_size, "Congestion control table entries 0 (CCA disabled - default), min = 128, max = 1984");
-/*
- * qib_wc_pat parameter:
- *      0 is WC via MTRR
- *      1 is WC via PAT
- *      If PAT initialization fails, code reverts back to MTRR
- */
-unsigned qib_wc_pat = 1; /* default (1) is to use PAT, not MTRR */
-module_param_named(wc_pat, qib_wc_pat, uint, S_IRUGO);
-MODULE_PARM_DESC(wc_pat, "enable write-combining via PAT mechanism");
 
 static void verify_interrupt(unsigned long);
 
@@ -1377,8 +1368,7 @@ static void cleanup_device_data(struct qib_devdata *dd)
 		spin_unlock(&dd->pport[pidx].cc_shadow_lock);
 	}
 
-	if (!qib_wc_pat)
-		qib_disable_wc(dd);
+	qib_disable_wc(dd);
 
 	if (dd->pioavailregs_dma) {
 		dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
@@ -1547,14 +1537,12 @@ static int qib_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto bail;
 	}
 
-	if (!qib_wc_pat) {
-		ret = qib_enable_wc(dd);
-		if (ret) {
-			qib_dev_err(dd,
-				"Write combining not enabled (err %d): performance may be poor\n",
-				-ret);
-			ret = 0;
-		}
+	ret = qib_enable_wc(dd);
+	if (ret) {
+		qib_dev_err(dd,
+			"Write combining not enabled (err %d): performance may be poor\n",
+			-ret);
+		ret = 0;
 	}
 
 	qib_verify_pioperf(dd);
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 395f4046dba2..05e3242d8442 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -83,7 +83,8 @@ static void qib_send_trap(struct qib_ibport *ibp, void *data, unsigned len)
 		return;
 
 	send_buf = ib_create_send_mad(agent, 0, 0, 0, IB_MGMT_MAD_HDR,
-				      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+				      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+				      IB_MGMT_BASE_VERSION);
 	if (IS_ERR(send_buf))
 		return;
 
@@ -1854,7 +1855,7 @@ static int pma_set_portcounters_ext(struct ib_pma_mad *pmp,
 }
 
 static int process_subn(struct ib_device *ibdev, int mad_flags,
-			u8 port, struct ib_mad *in_mad,
+			u8 port, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_smp *smp = (struct ib_smp *)out_mad;
@@ -2006,7 +2007,7 @@ bail:
 }
 
 static int process_perf(struct ib_device *ibdev, u8 port,
-			struct ib_mad *in_mad,
+			const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_pma_mad *pmp = (struct ib_pma_mad *)out_mad;
@@ -2299,7 +2300,7 @@ static int check_cc_key(struct qib_ibport *ibp,
 }
 
 static int process_cc(struct ib_device *ibdev, int mad_flags,
-			u8 port, struct ib_mad *in_mad,
+			u8 port, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_cc_mad *ccp = (struct ib_cc_mad *)out_mad;
@@ -2400,12 +2401,19 @@ bail:
  * This is called by the ib_mad module.
  */
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
-		    struct ib_wc *in_wc, struct ib_grh *in_grh,
-		    struct ib_mad *in_mad, struct ib_mad *out_mad)
+		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index)
 {
 	int ret;
 	struct qib_ibport *ibp = to_iport(ibdev, port);
 	struct qib_pportdata *ppd = ppd_from_ibp(ibp);
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index 4a3599890ea5..a05d1a372208 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -1550,12 +1550,14 @@ full:
 	}
 }
 
-static int qib_query_device(struct ib_device *ibdev,
-			    struct ib_device_attr *props)
+static int qib_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			    struct ib_udata *uhw)
 {
 	struct qib_devdata *dd = dd_from_ibdev(ibdev);
 	struct qib_ibdev *dev = to_idev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
 	memset(props, 0, sizeof(*props));
 
 	props->device_cap_flags = IB_DEVICE_BAD_PKEY_CNTR |
@@ -2040,6 +2042,24 @@ static void init_ibport(struct qib_pportdata *ppd)
 	RCU_INIT_POINTER(ibp->qp1, NULL);
 }
 
+static int qib_port_immutable(struct ib_device *ibdev, u8 port_num,
+			      struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = qib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 /**
  * qib_register_ib_device - register our device with the infiniband core
  * @dd: the device data structure
@@ -2227,6 +2247,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	ibdev->process_mad = qib_process_mad;
 	ibdev->mmap = qib_mmap;
 	ibdev->dma_ops = &qib_dma_mapping_ops;
+	ibdev->get_port_immutable = qib_port_immutable;
 
 	snprintf(ibdev->node_desc, sizeof(ibdev->node_desc),
 		 "Intel Infiniband HCA %s", init_utsname()->nodename);
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index bfc8948fdd35..1635572752ce 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -872,8 +872,10 @@ void qib_cap_mask_chg(struct qib_ibport *ibp);
 void qib_sys_guid_chg(struct qib_ibport *ibp);
 void qib_node_desc_chg(struct qib_ibport *ibp);
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		    struct ib_wc *in_wc, struct ib_grh *in_grh,
-		    struct ib_mad *in_mad, struct ib_mad *out_mad);
+		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index);
 int qib_create_agents(struct qib_ibdev *dev);
 void qib_free_agents(struct qib_ibdev *dev);
 
@@ -1007,8 +1009,9 @@ void qib_cq_enter(struct qib_cq *cq, struct ib_wc *entry, int sig);
 
 int qib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
 
-struct ib_cq *qib_create_cq(struct ib_device *ibdev, int entries,
-			    int comp_vector, struct ib_ucontext *context,
+struct ib_cq *qib_create_cq(struct ib_device *ibdev,
+			    const struct ib_cq_init_attr *attr,
+			    struct ib_ucontext *context,
 			    struct ib_udata *udata);
 
 int qib_destroy_cq(struct ib_cq *ibcq);
diff --git a/drivers/infiniband/hw/qib/qib_wc_x86_64.c b/drivers/infiniband/hw/qib/qib_wc_x86_64.c
index 81b225f2300a..edd0ddbd4481 100644
--- a/drivers/infiniband/hw/qib/qib_wc_x86_64.c
+++ b/drivers/infiniband/hw/qib/qib_wc_x86_64.c
@@ -116,21 +116,10 @@ int qib_enable_wc(struct qib_devdata *dd)
 	}
 
 	if (!ret) {
-		int cookie;
-
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
-		if (cookie < 0) {
-			{
-				qib_devinfo(dd->pcidev,
-					 "mtrr_add()  WC for PIO bufs failed (%d)\n",
-					 cookie);
-				ret = -EINVAL;
-			}
-		} else {
-			dd->wc_cookie = cookie;
-			dd->wc_base = (unsigned long) pioaddr;
-			dd->wc_len = (unsigned long) piolen;
-		}
+		dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+		if (dd->wc_cookie < 0)
+			/* use error from routine */
+			ret = dd->wc_cookie;
 	}
 
 	return ret;
@@ -142,18 +131,7 @@ int qib_enable_wc(struct qib_devdata *dd)
  */
 void qib_disable_wc(struct qib_devdata *dd)
 {
-	if (dd->wc_cookie) {
-		int r;
-
-		r = mtrr_del(dd->wc_cookie, dd->wc_base,
-			     dd->wc_len);
-		if (r < 0)
-			qib_devinfo(dd->pcidev,
-				 "mtrr_del(%lx, %lx, %lx) failed: %d\n",
-				 dd->wc_cookie, dd->wc_base,
-				 dd->wc_len, r);
-		dd->wc_cookie = 0; /* even on failure */
-	}
+	arch_phys_wc_del(dd->wc_cookie);
 }
 
 /**
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index 0d0f98695d53..34c49b8105fe 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -300,6 +300,22 @@ static struct notifier_block usnic_ib_inetaddr_notifier = {
 };
 /* End of inet section*/
 
+static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = usnic_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+
+	return 0;
+}
+
 /* Start of PF discovery section */
 static void *usnic_ib_device_add(struct pci_dev *dev)
 {
@@ -383,6 +399,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	us_ibdev->ib_dev.poll_cq = usnic_ib_poll_cq;
 	us_ibdev->ib_dev.req_notify_cq = usnic_ib_req_notify_cq;
 	us_ibdev->ib_dev.get_dma_mr = usnic_ib_get_dma_mr;
+	us_ibdev->ib_dev.get_port_immutable = usnic_port_immutable;
 
 
 	if (ib_register_device(&us_ibdev->ib_dev, NULL))
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 53bd6a2d9cdb..7df43827cb29 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -248,7 +248,8 @@ enum rdma_link_layer usnic_ib_port_link_layer(struct ib_device *device,
 }
 
 int usnic_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+			  struct ib_device_attr *props,
+			  struct ib_udata *uhw)
 {
 	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
 	union ib_gid gid;
@@ -257,6 +258,9 @@ int usnic_ib_query_device(struct ib_device *ibdev,
 	int qp_per_vf;
 
 	usnic_dbg("\n");
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	mutex_lock(&us_ibdev->usdev_lock);
 	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
 	us_ibdev->netdev->ethtool_ops->get_settings(us_ibdev->netdev, &cmd);
@@ -570,13 +574,17 @@ int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	return status;
 }
 
-struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev, int entries,
-					int vector, struct ib_ucontext *context,
-					struct ib_udata *udata)
+struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev,
+				 const struct ib_cq_init_attr *attr,
+				 struct ib_ucontext *context,
+				 struct ib_udata *udata)
 {
 	struct ib_cq *cq;
 
 	usnic_dbg("\n");
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
 	if (!cq)
 		return ERR_PTR(-EBUSY);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index bb864f5aed70..0bd04efa16f3 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -24,9 +24,12 @@
 enum rdma_link_layer usnic_ib_port_link_layer(struct ib_device *device,
 						u8 port_num);
 int usnic_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props);
+				struct ib_device_attr *props,
+			  struct ib_udata *uhw);
 int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 				struct ib_port_attr *props);
+enum rdma_protocol_type
+usnic_ib_query_protocol(struct ib_device *device, u8 port_num);
 int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 				int qp_attr_mask,
 				struct ib_qp_init_attr *qp_init_attr);
@@ -44,9 +47,10 @@ struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
 int usnic_ib_destroy_qp(struct ib_qp *qp);
 int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 				int attr_mask, struct ib_udata *udata);
-struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev, int entries,
-					int vector, struct ib_ucontext *context,
-					struct ib_udata *udata);
+struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev,
+				 const struct ib_cq_init_attr *attr,
+				 struct ib_ucontext *context,
+				 struct ib_udata *udata);
 int usnic_ib_destroy_cq(struct ib_cq *cq);
 struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
 				u64 virt_addr, int access_flags,
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 417de1f32960..cb2337f0532b 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -472,11 +472,10 @@ struct usnic_uiom_pd *usnic_uiom_alloc_pd(void)
 		return ERR_PTR(-ENOMEM);
 
 	pd->domain = domain = iommu_domain_alloc(&pci_bus_type);
-	if (IS_ERR_OR_NULL(domain)) {
-		usnic_err("Failed to allocate IOMMU domain with err %ld\n",
-				PTR_ERR(pd->domain));
+	if (!domain) {
+		usnic_err("Failed to allocate IOMMU domain");
 		kfree(pd);
-		return ERR_PTR(domain ? PTR_ERR(domain) : -ENOMEM);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	iommu_set_fault_handler(pd->domain, usnic_uiom_dma_fault, NULL);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 56959adb6c7d..cf32a778e7d0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -386,8 +386,8 @@ static int ipoib_cm_nonsrq_init_rx(struct net_device *dev, struct ib_cm_id *cm_i
 					   rx->rx_ring[i].mapping,
 					   GFP_KERNEL)) {
 			ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
-				ret = -ENOMEM;
-				goto err_count;
+			ret = -ENOMEM;
+			goto err_count;
 		}
 		ret = ipoib_cm_post_receive_nonsrq(dev, rx, &t->wr, t->sge, i);
 		if (ret) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 9e1b203d756d..da149c278cb8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1128,7 +1128,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 {
 	struct ipoib_neigh_table *ntbl = &priv->ntbl;
 	struct ipoib_neigh_hash *htbl;
-	struct ipoib_neigh **buckets;
+	struct ipoib_neigh __rcu **buckets;
 	u32 size;
 
 	clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
@@ -1146,7 +1146,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 	htbl->size = size;
 	htbl->mask = (size - 1);
 	htbl->buckets = buckets;
-	ntbl->htbl = htbl;
+	RCU_INIT_POINTER(ntbl->htbl, htbl);
 	htbl->ntbl = ntbl;
 	atomic_set(&ntbl->entries, 0);
 
@@ -1685,9 +1685,7 @@ static void ipoib_add_one(struct ib_device *device)
 	struct net_device *dev;
 	struct ipoib_dev_priv *priv;
 	int s, e, p;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int count = 0;
 
 	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
 	if (!dev_list)
@@ -1704,15 +1702,21 @@ static void ipoib_add_one(struct ib_device *device)
 	}
 
 	for (p = s; p <= e; ++p) {
-		if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_protocol_ib(device, p))
 			continue;
 		dev = ipoib_add_port("ib%d", device, p);
 		if (!IS_ERR(dev)) {
 			priv = netdev_priv(dev);
 			list_add_tail(&priv->list, dev_list);
+			count++;
 		}
 	}
 
+	if (!count) {
+		kfree(dev_list);
+		return;
+	}
+
 	ib_set_client_data(device, &ipoib_client, dev_list);
 }
 
@@ -1721,9 +1725,6 @@ static void ipoib_remove_one(struct ib_device *device)
 	struct ipoib_dev_priv *priv, *tmp;
 	struct list_head *dev_list;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	dev_list = ib_get_client_data(device, &ipoib_client);
 	if (!dev_list)
 		return;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index e5cc43074196..9e6ee82a8fd7 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -141,6 +141,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		.sq_sig_type = IB_SIGNAL_ALL_WR,
 		.qp_type     = IB_QPT_UD
 	};
+	struct ib_cq_init_attr cq_attr = {};
 
 	int ret, size;
 	int i;
@@ -178,14 +179,17 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	} else
 		goto out_free_wq;
 
-	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0);
+	cq_attr.cqe = size;
+	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL,
+				     dev, &cq_attr);
 	if (IS_ERR(priv->recv_cq)) {
 		printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name);
 		goto out_cm_dev_cleanup;
 	}
 
+	cq_attr.cqe = ipoib_sendq_size;
 	priv->send_cq = ib_create_cq(priv->ca, ipoib_send_comp_handler, NULL,
-				     dev, ipoib_sendq_size, 0);
+				     dev, &cq_attr);
 	if (IS_ERR(priv->send_cq)) {
 		printk(KERN_WARNING "%s: failed to create send CQ\n", ca->name);
 		goto out_free_recv_cq;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index cc2dd35ffbc0..5c9f565ea0e8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -51,19 +51,22 @@ static void iser_cq_callback(struct ib_cq *cq, void *cq_context);
 
 static void iser_cq_event_callback(struct ib_event *cause, void *context)
 {
-	iser_err("got cq event %d \n", cause->event);
+	iser_err("cq event %s (%d)\n",
+		 ib_event_msg(cause->event), cause->event);
 }
 
 static void iser_qp_event_callback(struct ib_event *cause, void *context)
 {
-	iser_err("got qp event %d\n",cause->event);
+	iser_err("qp event %s (%d)\n",
+		 ib_event_msg(cause->event), cause->event);
 }
 
 static void iser_event_handler(struct ib_event_handler *handler,
 				struct ib_event *event)
 {
-	iser_err("async event %d on device %s port %d\n", event->event,
-		event->device->name, event->element.port_num);
+	iser_err("async event %s (%d) on device %s port %d\n",
+		 ib_event_msg(event->event), event->event,
+		 event->device->name, event->element.port_num);
 }
 
 /**
@@ -123,14 +126,17 @@ static int iser_create_device_ib_res(struct iser_device *device)
 		goto pd_err;
 
 	for (i = 0; i < device->comps_used; i++) {
+		struct ib_cq_init_attr cq_attr = {};
 		struct iser_comp *comp = &device->comps[i];
 
 		comp->device = device;
+		cq_attr.cqe = max_cqe;
+		cq_attr.comp_vector = i;
 		comp->cq = ib_create_cq(device->ib_device,
 					iser_cq_callback,
 					iser_cq_event_callback,
 					(void *)comp,
-					max_cqe, i);
+					&cq_attr);
 		if (IS_ERR(comp->cq)) {
 			comp->cq = NULL;
 			goto cq_err;
@@ -873,8 +879,9 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 	int ret = 0;
 
 	iser_conn = (struct iser_conn *)cma_id->context;
-	iser_info("event %d status %d conn %p id %p\n",
-		  event->event, event->status, cma_id->context, cma_id);
+	iser_info("%s (%d): status %d conn %p id %p\n",
+		  rdma_event_msg(event->event), event->event,
+		  event->status, cma_id->context, cma_id);
 
 	mutex_lock(&iser_conn->state_mutex);
 	switch (event->event) {
@@ -913,7 +920,8 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 		}
 		break;
 	default:
-		iser_err("Unexpected RDMA CM event (%d)\n", event->event);
+		iser_err("Unexpected RDMA CM event: %s (%d)\n",
+			 rdma_event_msg(event->event), event->event);
 		break;
 	}
 	mutex_unlock(&iser_conn->state_mutex);
@@ -1173,10 +1181,13 @@ static void iser_handle_wc(struct ib_wc *wc)
 		}
 	} else {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
-			iser_err("wr id %llx status %d vend_err %x\n",
-				 wc->wr_id, wc->status, wc->vendor_err);
+			iser_err("%s (%d): wr id %llx vend_err %x\n",
+				 ib_wc_status_msg(wc->status), wc->status,
+				 wc->wr_id, wc->vendor_err);
 		else
-			iser_dbg("flush error: wr id %llx\n", wc->wr_id);
+			iser_dbg("%s (%d): wr id %llx\n",
+				 ib_wc_status_msg(wc->status), wc->status,
+				 wc->wr_id);
 
 		if (wc->wr_id == ISER_BEACON_WRID)
 			/* all flush errors were consumed */
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 327529ee85eb..f3b7a34e10d8 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -65,6 +65,8 @@ static int
 isert_rdma_accept(struct isert_conn *isert_conn);
 struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
 
+static void isert_release_work(struct work_struct *work);
+
 static inline bool
 isert_prot_cmd(struct isert_conn *conn, struct se_cmd *cmd)
 {
@@ -78,7 +80,9 @@ isert_qp_event_callback(struct ib_event *e, void *context)
 {
 	struct isert_conn *isert_conn = context;
 
-	isert_err("conn %p event: %d\n", isert_conn, e->event);
+	isert_err("%s (%d): conn %p\n",
+		  ib_event_msg(e->event), e->event, isert_conn);
+
 	switch (e->event) {
 	case IB_EVENT_COMM_EST:
 		rdma_notify(isert_conn->cm_id, IB_EVENT_COMM_EST);
@@ -316,15 +320,18 @@ isert_alloc_comps(struct isert_device *device,
 	max_cqe = min(ISER_MAX_CQ_LEN, attr->max_cqe);
 
 	for (i = 0; i < device->comps_used; i++) {
+		struct ib_cq_init_attr cq_attr = {};
 		struct isert_comp *comp = &device->comps[i];
 
 		comp->device = device;
 		INIT_WORK(&comp->work, isert_cq_work);
+		cq_attr.cqe = max_cqe;
+		cq_attr.comp_vector = i;
 		comp->cq = ib_create_cq(device->ib_device,
 					isert_cq_callback,
 					isert_cq_event_callback,
 					(void *)comp,
-					max_cqe, i);
+					&cq_attr);
 		if (IS_ERR(comp->cq)) {
 			isert_err("Unable to allocate cq\n");
 			ret = PTR_ERR(comp->cq);
@@ -547,11 +554,11 @@ isert_create_pi_ctx(struct fast_reg_descriptor *desc,
 	return 0;
 
 err_prot_mr:
-	ib_dereg_mr(desc->pi_ctx->prot_mr);
+	ib_dereg_mr(pi_ctx->prot_mr);
 err_prot_frpl:
-	ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+	ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
 err_pi_ctx:
-	kfree(desc->pi_ctx);
+	kfree(pi_ctx);
 
 	return ret;
 }
@@ -648,6 +655,7 @@ isert_init_conn(struct isert_conn *isert_conn)
 	mutex_init(&isert_conn->mutex);
 	spin_lock_init(&isert_conn->pool_lock);
 	INIT_LIST_HEAD(&isert_conn->fr_pool);
+	INIT_WORK(&isert_conn->release_work, isert_release_work);
 }
 
 static void
@@ -897,7 +905,8 @@ static int
 isert_np_cma_handler(struct isert_np *isert_np,
 		     enum rdma_cm_event_type event)
 {
-	isert_dbg("isert np %p, handling event %d\n", isert_np, event);
+	isert_dbg("%s (%d): isert np %p\n",
+		  rdma_event_msg(event), event, isert_np);
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
@@ -925,6 +934,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 {
 	struct isert_np *isert_np = cma_id->context;
 	struct isert_conn *isert_conn;
+	bool terminating = false;
 
 	if (isert_np->np_cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
@@ -932,12 +942,25 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	isert_conn = cma_id->qp->qp_context;
 
 	mutex_lock(&isert_conn->mutex);
+	terminating = (isert_conn->state == ISER_CONN_TERMINATING);
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
 	isert_info("conn %p completing wait\n", isert_conn);
 	complete(&isert_conn->wait);
 
+	if (terminating)
+		goto out;
+
+	mutex_lock(&isert_np->np_accept_mutex);
+	if (!list_empty(&isert_conn->accept_node)) {
+		list_del_init(&isert_conn->accept_node);
+		isert_put_conn(isert_conn);
+		queue_work(isert_release_wq, &isert_conn->release_work);
+	}
+	mutex_unlock(&isert_np->np_accept_mutex);
+
+out:
 	return 0;
 }
 
@@ -957,7 +980,8 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
 
-	isert_info("event %d status %d id %p np %p\n", event->event,
+	isert_info("%s (%d): status %d id %p np %p\n",
+		   rdma_event_msg(event->event), event->event,
 		   event->status, cma_id, cma_id->context);
 
 	switch (event->event) {
@@ -2091,10 +2115,13 @@ isert_handle_wc(struct ib_wc *wc)
 		}
 	} else {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
-			isert_err("wr id %llx status %d vend_err %x\n",
-				  wc->wr_id, wc->status, wc->vendor_err);
+			isert_err("%s (%d): wr id %llx vend_err %x\n",
+				  ib_wc_status_msg(wc->status), wc->status,
+				  wc->wr_id, wc->vendor_err);
 		else
-			isert_dbg("flush error: wr id %llx\n", wc->wr_id);
+			isert_dbg("%s (%d): wr id %llx\n",
+				  ib_wc_status_msg(wc->status), wc->status,
+				  wc->wr_id);
 
 		if (wc->wr_id != ISER_FASTREG_LI_WRID)
 			isert_cq_comp_err(isert_conn, wc);
@@ -2380,7 +2407,6 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 	page_off = offset % PAGE_SIZE;
 
 	send_wr->sg_list = ib_sge;
-	send_wr->num_sge = sg_nents;
 	send_wr->wr_id = (uintptr_t)&isert_cmd->tx_desc;
 	/*
 	 * Perform mapping of TCM scatterlist memory ib_sge dma_addr.
@@ -2400,14 +2426,17 @@ isert_build_rdma_wr(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd,
 			  ib_sge->addr, ib_sge->length, ib_sge->lkey);
 		page_off = 0;
 		data_left -= ib_sge->length;
+		if (!data_left)
+			break;
 		ib_sge++;
 		isert_dbg("Incrementing ib_sge pointer to %p\n", ib_sge);
 	}
 
+	send_wr->num_sge = ++i;
 	isert_dbg("Set outgoing sg_list: %p num_sg: %u from TCM SGLs\n",
 		  send_wr->sg_list, send_wr->num_sge);
 
-	return sg_nents;
+	return send_wr->num_sge;
 }
 
 static int
@@ -3366,7 +3395,6 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_wait4flush(isert_conn);
 	isert_wait4logout(isert_conn);
 
-	INIT_WORK(&isert_conn->release_work, isert_release_work);
 	queue_work(isert_release_wq, &isert_conn->release_work);
 }
 
@@ -3374,6 +3402,7 @@ static void isert_free_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
 
+	isert_wait4flush(isert_conn);
 	isert_put_conn(isert_conn);
 }
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 918814cd0f80..eada8f758ad4 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -59,9 +59,10 @@
 #define DRV_RELDATE	"July 1, 2013"
 
 MODULE_AUTHOR("Roland Dreier");
-MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator "
-		   "v" DRV_VERSION " (" DRV_RELDATE ")");
+MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator");
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION);
+MODULE_INFO(release_date, DRV_RELDATE);
 
 static unsigned int srp_sg_tablesize;
 static unsigned int cmd_sg_entries;
@@ -253,7 +254,8 @@ static void srp_free_iu(struct srp_host *host, struct srp_iu *iu)
 
 static void srp_qp_event(struct ib_event *event, void *context)
 {
-	pr_debug("QP event %d\n", event->event);
+	pr_debug("QP event %s (%d)\n",
+		 ib_event_msg(event->event), event->event);
 }
 
 static int srp_init_qp(struct srp_target_port *target,
@@ -465,14 +467,13 @@ static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target)
  */
 static void srp_destroy_qp(struct srp_rdma_ch *ch)
 {
-	struct srp_target_port *target = ch->target;
 	static struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
 	static struct ib_recv_wr wr = { .wr_id = SRP_LAST_WR_ID };
 	struct ib_recv_wr *bad_wr;
 	int ret;
 
 	/* Destroying a QP and reusing ch->done is only safe if not connected */
-	WARN_ON_ONCE(target->connected);
+	WARN_ON_ONCE(ch->connected);
 
 	ret = ib_modify_qp(ch->qp, &attr, IB_QP_STATE);
 	WARN_ONCE(ret, "ib_cm_init_qp_attr() returned %d\n", ret);
@@ -499,6 +500,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 	struct ib_fmr_pool *fmr_pool = NULL;
 	struct srp_fr_pool *fr_pool = NULL;
 	const int m = 1 + dev->use_fast_reg;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	init_attr = kzalloc(sizeof *init_attr, GFP_KERNEL);
@@ -506,15 +508,19 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 		return -ENOMEM;
 
 	/* + 1 for SRP_LAST_WR_ID */
+	cq_attr.cqe = target->queue_size + 1;
+	cq_attr.comp_vector = ch->comp_vector;
 	recv_cq = ib_create_cq(dev->dev, srp_recv_completion, NULL, ch,
-			       target->queue_size + 1, ch->comp_vector);
+			       &cq_attr);
 	if (IS_ERR(recv_cq)) {
 		ret = PTR_ERR(recv_cq);
 		goto err;
 	}
 
+	cq_attr.cqe = m * target->queue_size;
+	cq_attr.comp_vector = ch->comp_vector;
 	send_cq = ib_create_cq(dev->dev, srp_send_completion, NULL, ch,
-			       m * target->queue_size, ch->comp_vector);
+			       &cq_attr);
 	if (IS_ERR(send_cq)) {
 		ret = PTR_ERR(send_cq);
 		goto err_recv_cq;
@@ -781,7 +787,7 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich)
 		shost_printk(KERN_DEBUG, target->scsi_host,
 			     PFX "Topspin/Cisco initiator port ID workaround "
 			     "activated for target GUID %016llx\n",
-			     (unsigned long long) be64_to_cpu(target->ioc_guid));
+			     be64_to_cpu(target->ioc_guid));
 		memset(req->priv.initiator_port_id, 0, 8);
 		memcpy(req->priv.initiator_port_id + 8,
 		       &target->srp_host->srp_dev->dev->node_guid, 8);
@@ -811,35 +817,19 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
 	return changed;
 }
 
-static bool srp_change_conn_state(struct srp_target_port *target,
-				  bool connected)
-{
-	bool changed = false;
-
-	spin_lock_irq(&target->lock);
-	if (target->connected != connected) {
-		target->connected = connected;
-		changed = true;
-	}
-	spin_unlock_irq(&target->lock);
-
-	return changed;
-}
-
 static void srp_disconnect_target(struct srp_target_port *target)
 {
 	struct srp_rdma_ch *ch;
 	int i;
 
-	if (srp_change_conn_state(target, false)) {
-		/* XXX should send SRP_I_LOGOUT request */
+	/* XXX should send SRP_I_LOGOUT request */
 
-		for (i = 0; i < target->ch_count; i++) {
-			ch = &target->ch[i];
-			if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
-				shost_printk(KERN_DEBUG, target->scsi_host,
-					     PFX "Sending CM DREQ failed\n");
-			}
+	for (i = 0; i < target->ch_count; i++) {
+		ch = &target->ch[i];
+		ch->connected = false;
+		if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
+			shost_printk(KERN_DEBUG, target->scsi_host,
+				     PFX "Sending CM DREQ failed\n");
 		}
 	}
 }
@@ -852,7 +842,7 @@ static void srp_free_req_data(struct srp_target_port *target,
 	struct srp_request *req;
 	int i;
 
-	if (!ch->target || !ch->req_ring)
+	if (!ch->req_ring)
 		return;
 
 	for (i = 0; i < target->req_ring_size; ++i) {
@@ -986,14 +976,26 @@ static void srp_rport_delete(struct srp_rport *rport)
 	srp_queue_remove_work(target);
 }
 
+/**
+ * srp_connected_ch() - number of connected channels
+ * @target: SRP target port.
+ */
+static int srp_connected_ch(struct srp_target_port *target)
+{
+	int i, c = 0;
+
+	for (i = 0; i < target->ch_count; i++)
+		c += target->ch[i].connected;
+
+	return c;
+}
+
 static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 {
 	struct srp_target_port *target = ch->target;
 	int ret;
 
-	WARN_ON_ONCE(!multich && target->connected);
-
-	target->qp_in_error = false;
+	WARN_ON_ONCE(!multich && srp_connected_ch(target) > 0);
 
 	ret = srp_lookup_path(ch);
 	if (ret)
@@ -1016,7 +1018,7 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 		 */
 		switch (ch->status) {
 		case 0:
-			srp_change_conn_state(target, true);
+			ch->connected = true;
 			return 0;
 
 		case SRP_PORT_REDIRECT:
@@ -1214,14 +1216,10 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 	 */
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		ret += srp_new_cm_id(ch);
 	}
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		for (j = 0; j < target->req_ring_size; ++j) {
 			struct srp_request *req = &ch->req_ring[j];
 
@@ -1230,8 +1228,6 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 	}
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		/*
 		 * Whether or not creating a new CM ID succeeded, create a new
 		 * QP. This guarantees that all completion callback function
@@ -1243,13 +1239,13 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 		for (j = 0; j < target->queue_size; ++j)
 			list_add(&ch->tx_ring[j]->list, &ch->free_tx);
 	}
+
+	target->qp_in_error = false;
+
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (ret || !ch->target) {
-			if (i > 1)
-				ret = 0;
+		if (ret)
 			break;
-		}
 		ret = srp_connect_ch(ch, multich);
 		multich = true;
 	}
@@ -1842,7 +1838,7 @@ static void srp_process_aer_req(struct srp_rdma_ch *ch,
 	s32 delta = be32_to_cpu(req->req_lim_delta);
 
 	shost_printk(KERN_ERR, target->scsi_host, PFX
-		     "ignoring AER for LUN %llu\n", be64_to_cpu(req->lun));
+		     "ignoring AER for LUN %llu\n", scsilun_to_int(&req->lun));
 
 	if (srp_response_common(ch, delta, &rsp, sizeof(rsp)))
 		shost_printk(KERN_ERR, target->scsi_host, PFX
@@ -1929,20 +1925,21 @@ static void srp_handle_qp_err(u64 wr_id, enum ib_wc_status wc_status,
 		return;
 	}
 
-	if (target->connected && !target->qp_in_error) {
+	if (ch->connected && !target->qp_in_error) {
 		if (wr_id & LOCAL_INV_WR_ID_MASK) {
 			shost_printk(KERN_ERR, target->scsi_host, PFX
-				     "LOCAL_INV failed with status %d\n",
-				     wc_status);
+				     "LOCAL_INV failed with status %s (%d)\n",
+				     ib_wc_status_msg(wc_status), wc_status);
 		} else if (wr_id & FAST_REG_WR_ID_MASK) {
 			shost_printk(KERN_ERR, target->scsi_host, PFX
-				     "FAST_REG_MR failed status %d\n",
-				     wc_status);
+				     "FAST_REG_MR failed status %s (%d)\n",
+				     ib_wc_status_msg(wc_status), wc_status);
 		} else {
 			shost_printk(KERN_ERR, target->scsi_host,
-				     PFX "failed %s status %d for iu %p\n",
+				     PFX "failed %s status %s (%d) for iu %p\n",
 				     send_err ? "send" : "receive",
-				     wc_status, (void *)(uintptr_t)wr_id);
+				     ib_wc_status_msg(wc_status), wc_status,
+				     (void *)(uintptr_t)wr_id);
 		}
 		queue_work(system_long_wq, &target->tl_err_work);
 	}
@@ -2034,7 +2031,7 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	memset(cmd, 0, sizeof *cmd);
 
 	cmd->opcode = SRP_CMD;
-	cmd->lun    = cpu_to_be64((u64) scmnd->device->lun << 48);
+	int_to_scsilun(scmnd->device->lun, &cmd->lun);
 	cmd->tag    = tag;
 	memcpy(cmd->cdb, scmnd->cmnd, scmnd->cmd_len);
 
@@ -2367,7 +2364,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 	case IB_CM_DREQ_RECEIVED:
 		shost_printk(KERN_WARNING, target->scsi_host,
 			     PFX "DREQ received - connection closed\n");
-		srp_change_conn_state(target, false);
+		ch->connected = false;
 		if (ib_send_cm_drep(cm_id, NULL, 0))
 			shost_printk(KERN_ERR, target->scsi_host,
 				     PFX "Sending CM DREP failed\n");
@@ -2414,8 +2411,8 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth)
 	return scsi_change_queue_depth(sdev, qdepth);
 }
 
-static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
-			     unsigned int lun, u8 func)
+static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
+			     u8 func)
 {
 	struct srp_target_port *target = ch->target;
 	struct srp_rport *rport = target->rport;
@@ -2423,7 +2420,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;
 
-	if (!target->connected || target->qp_in_error)
+	if (!ch->connected || target->qp_in_error)
 		return -1;
 
 	init_completion(&ch->tsk_mgmt_done);
@@ -2449,7 +2446,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
 	memset(tsk_mgmt, 0, sizeof *tsk_mgmt);
 
 	tsk_mgmt->opcode 	= SRP_TSK_MGMT;
-	tsk_mgmt->lun		= cpu_to_be64((u64) lun << 48);
+	int_to_scsilun(lun, &tsk_mgmt->lun);
 	tsk_mgmt->tag		= req_tag | SRP_TAG_TSK_MGMT;
 	tsk_mgmt->tsk_mgmt_func = func;
 	tsk_mgmt->task_tag	= req_tag;
@@ -2563,8 +2560,7 @@ static ssize_t show_id_ext(struct device *dev, struct device_attribute *attr,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->id_ext));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->id_ext));
 }
 
 static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr,
@@ -2572,8 +2568,7 @@ static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->ioc_guid));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->ioc_guid));
 }
 
 static ssize_t show_service_id(struct device *dev,
@@ -2581,8 +2576,7 @@ static ssize_t show_service_id(struct device *dev,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->service_id));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->service_id));
 }
 
 static ssize_t show_pkey(struct device *dev, struct device_attribute *attr,
@@ -2773,7 +2767,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 
 	target->state = SRP_TARGET_SCANNING;
 	sprintf(target->target_name, "SRP.T10:%016llX",
-		 (unsigned long long) be64_to_cpu(target->id_ext));
+		be64_to_cpu(target->id_ext));
 
 	if (scsi_add_host(target->scsi_host, host->srp_dev->dev->dma_device))
 		return -ENODEV;
@@ -2797,7 +2791,8 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	scsi_scan_target(&target->scsi_host->shost_gendev,
 			 0, target->scsi_id, SCAN_WILD_CARD, 0);
 
-	if (!target->connected || target->qp_in_error) {
+	if (srp_connected_ch(target) < target->ch_count ||
+	    target->qp_in_error) {
 		shost_printk(KERN_INFO, target->scsi_host,
 			     PFX "SCSI scan failed - removing SCSI host\n");
 		srp_queue_remove_work(target);
@@ -3146,7 +3141,7 @@ static ssize_t srp_create_target(struct device *dev,
 	target_host->transportt  = ib_srp_transport_template;
 	target_host->max_channel = 0;
 	target_host->max_id      = 1;
-	target_host->max_lun     = SRP_MAX_LUN;
+	target_host->max_lun     = -1LL;
 	target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb;
 
 	target = host_to_target(target_host);
@@ -3172,11 +3167,11 @@ static ssize_t srp_create_target(struct device *dev,
 
 	ret = srp_parse_options(buf, target);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = scsi_init_shared_tag_map(target_host, target_host->can_queue);
 	if (ret)
-		goto err;
+		goto out;
 
 	target->req_ring_size = target->queue_size - SRP_TSK_MGMT_SQ_SIZE;
 
@@ -3187,7 +3182,7 @@ static ssize_t srp_create_target(struct device *dev,
 			     be64_to_cpu(target->ioc_guid),
 			     be64_to_cpu(target->initiator_ext));
 		ret = -EEXIST;
-		goto err;
+		goto out;
 	}
 
 	if (!srp_dev->has_fmr && !srp_dev->has_fr && !target->allow_ext_sg &&
@@ -3208,7 +3203,7 @@ static ssize_t srp_create_target(struct device *dev,
 	spin_lock_init(&target->lock);
 	ret = ib_query_gid(ibdev, host->port, 0, &target->sgid);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = -ENOMEM;
 	target->ch_count = max_t(unsigned, num_online_nodes(),
@@ -3219,7 +3214,7 @@ static ssize_t srp_create_target(struct device *dev,
 	target->ch = kcalloc(target->ch_count, sizeof(*target->ch),
 			     GFP_KERNEL);
 	if (!target->ch)
-		goto err;
+		goto out;
 
 	node_idx = 0;
 	for_each_online_node(node) {
@@ -3315,9 +3310,6 @@ err_disconnect:
 	}
 
 	kfree(target->ch);
-
-err:
-	scsi_host_put(target_host);
 	goto out;
 }
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index a611556406ac..17ee3f80ba55 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -54,7 +54,6 @@ enum {
 	SRP_DLID_REDIRECT	= 2,
 	SRP_STALE_CONN		= 3,
 
-	SRP_MAX_LUN		= 512,
 	SRP_DEF_SG_TABLESIZE	= 12,
 
 	SRP_DEFAULT_QUEUE_SIZE	= 1 << 6,
@@ -170,6 +169,7 @@ struct srp_rdma_ch {
 
 	struct completion	tsk_mgmt_done;
 	u8			tsk_mgmt_status;
+	bool			connected;
 };
 
 /**
@@ -214,7 +214,6 @@ struct srp_target_port {
 	__be16			pkey;
 
 	u32			rq_tmo_jiffies;
-	bool			connected;
 
 	int			zero_req_lim;
 
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 9b84b4c0a000..4556cd11288e 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -41,6 +41,7 @@
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <scsi/scsi_proto.h>
 #include <scsi/scsi_tcq.h>
 #include <target/configfs_macros.h>
 #include <target/target_core_base.h>
@@ -476,7 +477,8 @@ static void srpt_mad_recv_handler(struct ib_mad_agent *mad_agent,
 	rsp = ib_create_send_mad(mad_agent, mad_wc->wc->src_qp,
 				 mad_wc->wc->pkey_index, 0,
 				 IB_MGMT_DEVICE_HDR, IB_MGMT_DEVICE_DATA,
-				 GFP_KERNEL);
+				 GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(rsp))
 		goto err_rsp;
 
@@ -2080,6 +2082,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	struct srpt_port *sport = ch->sport;
 	struct srpt_device *sdev = sport->sdev;
 	u32 srp_sq_size = sport->port_attrib.srp_sq_size;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	WARN_ON(ch->rq_size < 1);
@@ -2090,8 +2093,9 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 		goto out;
 
 retry:
+	cq_attr.cqe = ch->rq_size + srp_sq_size;
 	ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
-			      ch->rq_size + srp_sq_size, 0);
+			      &cq_attr);
 	if (IS_ERR(ch->cq)) {
 		ret = PTR_ERR(ch->cq);
 		pr_err("failed to create CQ cqe= %d ret= %d\n",
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.h b/drivers/infiniband/ulp/srpt/ib_srpt.h
index 3dae156905de..d85c0c205625 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.h
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.h
@@ -245,7 +245,7 @@ struct srpt_send_ioctx {
 	u8			n_rdma;
 	u8			n_rbuf;
 	bool			queue_status_only;
-	u8			sense_data[SCSI_SENSE_BUFFERSIZE];
+	u8			sense_data[TRANSPORT_SENSE_BUFFER];
 };
 
 /**
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a5127..a35532ec00e4 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -25,6 +25,19 @@ config INPUT
 
 if INPUT
 
+config INPUT_LEDS
+	tristate "Export input device LEDs in sysfs"
+	depends on LEDS_CLASS
+	default INPUT
+	help
+	  Say Y here if you would like to export LEDs on input devices
+	  as standard LED class devices in sysfs.
+
+	  If unsure, say Y.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called input-leds.
+
 config INPUT_FF_MEMLESS
 	tristate "Support for memoryless force-feedback devices"
 	help
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497f..0c9302ca9954 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_INPUT_POLLDEV)	+= input-polldev.o
 obj-$(CONFIG_INPUT_SPARSEKMAP)	+= sparse-keymap.o
 obj-$(CONFIG_INPUT_MATRIXKMAP)	+= matrix-keymap.o
 
+obj-$(CONFIG_INPUT_LEDS)	+= input-leds.o
 obj-$(CONFIG_INPUT_MOUSEDEV)	+= mousedev.o
 obj-$(CONFIG_INPUT_JOYDEV)	+= joydev.o
 obj-$(CONFIG_INPUT_EVDEV)	+= evdev.o
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index a18f41b89b6a..9d35499faca4 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -422,10 +422,7 @@ static int evdev_release(struct inode *inode, struct file *file)
 
 	evdev_detach_client(evdev, client);
 
-	if (is_vmalloc_addr(client))
-		vfree(client);
-	else
-		kfree(client);
+	kvfree(client);
 
 	evdev_close_device(evdev);
 
diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c
index b81c88c43452..8f4a30fccbb6 100644
--- a/drivers/input/ff-core.c
+++ b/drivers/input/ff-core.c
@@ -70,7 +70,7 @@ static int compat_effect(struct ff_device *ff, struct ff_effect *effect)
 			return -EINVAL;
 
 		/*
-		 * calculate manginude of sine wave as average of rumble's
+		 * calculate magnitude of sine wave as average of rumble's
 		 * 2/3 of strong magnitude and 1/3 of weak magnitude
 		 */
 		magnitude = effect->u.rumble.strong_magnitude / 3 +
@@ -213,7 +213,7 @@ static int erase_effect(struct input_dev *dev, int effect_id,
 /**
  * input_ff_erase - erase a force-feedback effect from device
  * @dev: input device to erase effect from
- * @effect_id: id of the ffect to be erased
+ * @effect_id: id of the effect to be erased
  * @file: purported owner of the request
  *
  * This function erases a force-feedback effect from specified device.
diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c
new file mode 100644
index 000000000000..074a65ed17bb
--- /dev/null
+++ b/drivers/input/input-leds.c
@@ -0,0 +1,212 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2015 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+#if IS_ENABLED(CONFIG_VT)
+#define VT_TRIGGER(_name)	.trigger = _name
+#else
+#define VT_TRIGGER(_name)	.trigger = NULL
+#endif
+
+static const struct {
+	const char *name;
+	const char *trigger;
+} input_led_info[LED_CNT] = {
+	[LED_NUML]	= { "numlock", VT_TRIGGER("kbd-numlock") },
+	[LED_CAPSL]	= { "capslock", VT_TRIGGER("kbd-capslock") },
+	[LED_SCROLLL]	= { "scrolllock", VT_TRIGGER("kbd-scrolllock") },
+	[LED_COMPOSE]	= { "compose" },
+	[LED_KANA]	= { "kana", VT_TRIGGER("kbd-kanalock") },
+	[LED_SLEEP]	= { "sleep" } ,
+	[LED_SUSPEND]	= { "suspend" },
+	[LED_MUTE]	= { "mute" },
+	[LED_MISC]	= { "misc" },
+	[LED_MAIL]	= { "mail" },
+	[LED_CHARGING]	= { "charging" },
+};
+
+struct input_led {
+	struct led_classdev cdev;
+	struct input_handle *handle;
+	unsigned int code; /* One of LED_* constants */
+};
+
+struct input_leds {
+	struct input_handle handle;
+	unsigned int num_leds;
+	struct input_led leds[];
+};
+
+static enum led_brightness input_leds_brightness_get(struct led_classdev *cdev)
+{
+	struct input_led *led = container_of(cdev, struct input_led, cdev);
+	struct input_dev *input = led->handle->dev;
+
+	return test_bit(led->code, input->led) ? cdev->max_brightness : 0;
+}
+
+static void input_leds_brightness_set(struct led_classdev *cdev,
+				      enum led_brightness brightness)
+{
+	struct input_led *led = container_of(cdev, struct input_led, cdev);
+
+	input_inject_event(led->handle, EV_LED, led->code, !!brightness);
+}
+
+static void input_leds_event(struct input_handle *handle, unsigned int type,
+			     unsigned int code, int value)
+{
+}
+
+static int input_leds_connect(struct input_handler *handler,
+			      struct input_dev *dev,
+			      const struct input_device_id *id)
+{
+	struct input_leds *leds;
+	unsigned int num_leds;
+	unsigned int led_code;
+	int led_no;
+	int error;
+
+	num_leds = bitmap_weight(dev->ledbit, LED_CNT);
+	if (!num_leds)
+		return -ENXIO;
+
+	leds = kzalloc(sizeof(*leds) + num_leds * sizeof(*leds->leds),
+		       GFP_KERNEL);
+	if (!leds)
+		return -ENOMEM;
+
+	leds->num_leds = num_leds;
+
+	leds->handle.dev = dev;
+	leds->handle.handler = handler;
+	leds->handle.name = "leds";
+	leds->handle.private = leds;
+
+	error = input_register_handle(&leds->handle);
+	if (error)
+		goto err_free_mem;
+
+	error = input_open_device(&leds->handle);
+	if (error)
+		goto err_unregister_handle;
+
+	led_no = 0;
+	for_each_set_bit(led_code, dev->ledbit, LED_CNT) {
+		struct input_led *led = &leds->leds[led_no];
+
+		led->handle = &leds->handle;
+		led->code = led_code;
+
+		if (WARN_ON(!input_led_info[led_code].name))
+			continue;
+
+		led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
+					   dev_name(&dev->dev),
+					   input_led_info[led_code].name);
+		if (!led->cdev.name) {
+			error = -ENOMEM;
+			goto err_unregister_leds;
+		}
+
+		led->cdev.max_brightness = 1;
+		led->cdev.brightness_get = input_leds_brightness_get;
+		led->cdev.brightness_set = input_leds_brightness_set;
+		led->cdev.default_trigger = input_led_info[led_code].trigger;
+
+		error = led_classdev_register(&dev->dev, &led->cdev);
+		if (error) {
+			dev_err(&dev->dev, "failed to register LED %s: %d\n",
+				led->cdev.name, error);
+			kfree(led->cdev.name);
+			goto err_unregister_leds;
+		}
+
+		led_no++;
+	}
+
+	return 0;
+
+err_unregister_leds:
+	while (--led_no >= 0) {
+		struct input_led *led = &leds->leds[led_no];
+
+		led_classdev_unregister(&led->cdev);
+		kfree(led->cdev.name);
+	}
+
+	input_close_device(&leds->handle);
+
+err_unregister_handle:
+	input_unregister_handle(&leds->handle);
+
+err_free_mem:
+	kfree(leds);
+	return error;
+}
+
+static void input_leds_disconnect(struct input_handle *handle)
+{
+	struct input_leds *leds = handle->private;
+	int i;
+
+	for (i = 0; i < leds->num_leds; i++) {
+		struct input_led *led = &leds->leds[i];
+
+		led_classdev_unregister(&led->cdev);
+		kfree(led->cdev.name);
+	}
+
+	input_close_device(handle);
+	input_unregister_handle(handle);
+
+	kfree(leds);
+}
+
+static const struct input_device_id input_leds_ids[] = {
+	{
+		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
+		.evbit = { BIT_MASK(EV_LED) },
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(input, input_leds_ids);
+
+static struct input_handler input_leds_handler = {
+	.event =	input_leds_event,
+	.connect =	input_leds_connect,
+	.disconnect =	input_leds_disconnect,
+	.name =		"leds",
+	.id_table =	input_leds_ids,
+};
+
+static int __init input_leds_init(void)
+{
+	return input_register_handler(&input_leds_handler);
+}
+module_init(input_leds_init);
+
+static void __exit input_leds_exit(void)
+{
+	input_unregister_handler(&input_leds_handler);
+}
+module_exit(input_leds_exit);
+
+MODULE_AUTHOR("Samuel Thibault <samuel.thibault@ens-lyon.org>");
+MODULE_AUTHOR("Dmitry Torokhov <dmitry.torokhov@gmail.com>");
+MODULE_DESCRIPTION("Input -> LEDs Bridge");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/input/input.c b/drivers/input/input.c
index cc357f1516a7..f31578423636 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -2262,7 +2262,7 @@ EXPORT_SYMBOL(input_unregister_handler);
  *
  * Iterate over @bus's list of devices, and call @fn for each, passing
  * it @data and stop when @fn returns a non-zero value. The function is
- * using RCU to traverse the list and therefore may be usind in atonic
+ * using RCU to traverse the list and therefore may be using in atomic
  * contexts. The @fn callback is invoked from RCU critical section and
  * thus must not sleep.
  */
diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c
index f362883c94e3..1d247bcf2ae2 100644
--- a/drivers/input/joydev.c
+++ b/drivers/input/joydev.c
@@ -747,6 +747,63 @@ static void joydev_cleanup(struct joydev *joydev)
 		input_close_device(handle);
 }
 
+static bool joydev_dev_is_absolute_mouse(struct input_dev *dev)
+{
+	DECLARE_BITMAP(jd_scratch, KEY_CNT);
+
+	BUILD_BUG_ON(ABS_CNT > KEY_CNT || EV_CNT > KEY_CNT);
+
+	/*
+	 * Virtualization (VMware, etc) and remote management (HP
+	 * ILO2) solutions use absolute coordinates for their virtual
+	 * pointing devices so that there is one-to-one relationship
+	 * between pointer position on the host screen and virtual
+	 * guest screen, and so their mice use ABS_X, ABS_Y and 3
+	 * primary button events. This clashes with what joydev
+	 * considers to be joysticks (a device with at minimum ABS_X
+	 * axis).
+	 *
+	 * Here we are trying to separate absolute mice from
+	 * joysticks. A device is, for joystick detection purposes,
+	 * considered to be an absolute mouse if the following is
+	 * true:
+	 *
+	 * 1) Event types are exactly EV_ABS, EV_KEY and EV_SYN.
+	 * 2) Absolute events are exactly ABS_X and ABS_Y.
+	 * 3) Keys are exactly BTN_LEFT, BTN_RIGHT and BTN_MIDDLE.
+	 * 4) Device is not on "Amiga" bus.
+	 */
+
+	bitmap_zero(jd_scratch, EV_CNT);
+	__set_bit(EV_ABS, jd_scratch);
+	__set_bit(EV_KEY, jd_scratch);
+	__set_bit(EV_SYN, jd_scratch);
+	if (!bitmap_equal(jd_scratch, dev->evbit, EV_CNT))
+		return false;
+
+	bitmap_zero(jd_scratch, ABS_CNT);
+	__set_bit(ABS_X, jd_scratch);
+	__set_bit(ABS_Y, jd_scratch);
+	if (!bitmap_equal(dev->absbit, jd_scratch, ABS_CNT))
+		return false;
+
+	bitmap_zero(jd_scratch, KEY_CNT);
+	__set_bit(BTN_LEFT, jd_scratch);
+	__set_bit(BTN_RIGHT, jd_scratch);
+	__set_bit(BTN_MIDDLE, jd_scratch);
+
+	if (!bitmap_equal(dev->keybit, jd_scratch, KEY_CNT))
+		return false;
+
+	/*
+	 * Amiga joystick (amijoy) historically uses left/middle/right
+	 * button events.
+	 */
+	if (dev->id.bustype == BUS_AMIGA)
+		return false;
+
+	return true;
+}
 
 static bool joydev_match(struct input_handler *handler, struct input_dev *dev)
 {
@@ -758,6 +815,10 @@ static bool joydev_match(struct input_handler *handler, struct input_dev *dev)
 	if (test_bit(EV_KEY, dev->evbit) && test_bit(BTN_DIGI, dev->keybit))
 		return false;
 
+	/* Avoid absolute mice */
+	if (joydev_dev_is_absolute_mouse(dev))
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 106fbac7f8c5..4cd94fd6cbad 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -367,6 +367,7 @@ config KEYBOARD_MAPLE
 
 config KEYBOARD_MAX7359
 	tristate "Maxim MAX7359 Key Switch Controller"
+	select INPUT_MATRIXKMAP
 	depends on I2C
 	help
 	  If you say yes here you get support for the Maxim MAX7359 Key
@@ -677,7 +678,7 @@ config KEYBOARD_W90P910
 config KEYBOARD_CROS_EC
 	tristate "ChromeOS EC keyboard"
 	select INPUT_MATRIXKMAP
-	depends on MFD_CROS_EC
+	depends on CROS_EC_PROTO
 	help
 	  Say Y here to enable the matrix keyboard used by ChromeOS devices
 	  and implemented on the ChromeOS EC. You must enable one bus option
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index a45267729dfc..6ed83cf8b74e 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -180,7 +180,7 @@
 #define LOGIC2_STAT	(1 << 7)	/* ADP5589 only */
 #define LOGIC1_STAT	(1 << 6)
 #define LOCK_STAT	(1 << 5)	/* ADP5589 only */
-#define KEC		0xF
+#define KEC		0x1F
 
 /* PIN_CONFIG_D Register */
 #define C4_EXTEND_CFG	(1 << 6)	/* RESET2 */
@@ -726,7 +726,7 @@ static int adp5589_setup(struct adp5589_kpad *kpad)
 
 		pull_mask |= val << (2 * (i & 0x3));
 
-		if (i == 3 || i == kpad->var->max_row_num) {
+		if (i % 4 == 3 || i == kpad->var->max_row_num) {
 			ret |= adp5589_write(client, reg(ADP5585_RPULL_CONFIG_A)
 					     + (i >> 2), pull_mask);
 			pull_mask = 0;
@@ -746,7 +746,7 @@ static int adp5589_setup(struct adp5589_kpad *kpad)
 
 		pull_mask |= val << (2 * (i & 0x3));
 
-		if (i == 3 || i == kpad->var->max_col_num) {
+		if (i % 4 == 3 || i == kpad->var->max_col_num) {
 			ret |= adp5589_write(client,
 					     reg(ADP5585_RPULL_CONFIG_C) +
 					     (i >> 2), pull_mask);
diff --git a/drivers/input/keyboard/clps711x-keypad.c b/drivers/input/keyboard/clps711x-keypad.c
index 27ef29f8fe6a..b637f1af842e 100644
--- a/drivers/input/keyboard/clps711x-keypad.c
+++ b/drivers/input/keyboard/clps711x-keypad.c
@@ -120,14 +120,9 @@ static int clps711x_keypad_probe(struct platform_device *pdev)
 	for (i = 0; i < priv->row_count; i++) {
 		struct clps711x_gpio_data *data = &priv->gpio_data[i];
 
-		data->desc = devm_gpiod_get_index(dev, "row", i);
-		if (!data->desc)
-			return -EINVAL;
-
+		data->desc = devm_gpiod_get_index(dev, "row", i, GPIOD_IN);
 		if (IS_ERR(data->desc))
 			return PTR_ERR(data->desc);
-
-		gpiod_direction_input(data->desc);
 	}
 
 	err = of_property_read_u32(np, "poll-interval", &poll_interval);
diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c
index b50c5b8b8a4d..b01966dc7eb3 100644
--- a/drivers/input/keyboard/cros_ec_keyb.c
+++ b/drivers/input/keyboard/cros_ec_keyb.c
@@ -148,19 +148,28 @@ static void cros_ec_keyb_process(struct cros_ec_keyb *ckdev,
 
 static int cros_ec_keyb_get_state(struct cros_ec_keyb *ckdev, uint8_t *kb_state)
 {
-	int ret;
-	struct cros_ec_command msg = {
-		.command = EC_CMD_MKBP_STATE,
-		.insize = ckdev->cols,
-	};
+	int ret = 0;
+	struct cros_ec_command *msg;
 
-	ret = cros_ec_cmd_xfer(ckdev->ec, &msg);
-	if (ret < 0)
-		return ret;
+	msg = kmalloc(sizeof(*msg) + ckdev->cols, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
 
-	memcpy(kb_state, msg.indata, ckdev->cols);
+	msg->version = 0;
+	msg->command = EC_CMD_MKBP_STATE;
+	msg->insize = ckdev->cols;
+	msg->outsize = 0;
 
-	return 0;
+	ret = cros_ec_cmd_xfer(ckdev->ec, msg);
+	if (ret < 0) {
+		dev_err(ckdev->dev, "Error transferring EC message %d\n", ret);
+		goto exit;
+	}
+
+	memcpy(kb_state, msg->data, ckdev->cols);
+exit:
+	kfree(msg);
+	return ret;
 }
 
 static irqreturn_t cros_ec_keyb_irq(int irq, void *data)
@@ -266,7 +275,7 @@ static int cros_ec_keyb_probe(struct platform_device *pdev)
 	ckdev->dev = dev;
 	dev_set_drvdata(&pdev->dev, ckdev);
 
-	idev->name = ec->ec_name;
+	idev->name = CROS_EC_DEV_NAME;
 	idev->phys = ec->phys_name;
 	__set_bit(EV_REP, idev->evbit);
 
diff --git a/drivers/input/keyboard/max7359_keypad.c b/drivers/input/keyboard/max7359_keypad.c
index faa6da53eba8..5091133b7b8e 100644
--- a/drivers/input/keyboard/max7359_keypad.c
+++ b/drivers/input/keyboard/max7359_keypad.c
@@ -84,26 +84,6 @@ static int max7359_read_reg(struct i2c_client *client, int reg)
 	return ret;
 }
 
-static void max7359_build_keycode(struct max7359_keypad *keypad,
-				const struct matrix_keymap_data *keymap_data)
-{
-	struct input_dev *input_dev = keypad->input_dev;
-	int i;
-
-	for (i = 0; i < keymap_data->keymap_size; i++) {
-		unsigned int key = keymap_data->keymap[i];
-		unsigned int row = KEY_ROW(key);
-		unsigned int col = KEY_COL(key);
-		unsigned int scancode = MATRIX_SCAN_CODE(row, col,
-						MAX7359_ROW_SHIFT);
-		unsigned short keycode = KEY_VAL(key);
-
-		keypad->keycodes[scancode] = keycode;
-		__set_bit(keycode, input_dev->keybit);
-	}
-	__clear_bit(KEY_RESERVED, input_dev->keybit);
-}
-
 /* runs in an IRQ thread -- can (and will!) sleep */
 static irqreturn_t max7359_interrupt(int irq, void *dev_id)
 {
@@ -166,7 +146,6 @@ static void max7359_close(struct input_dev *dev)
 static void max7359_initialize(struct i2c_client *client)
 {
 	max7359_write_reg(client, MAX7359_REG_CONFIG,
-		MAX7359_CFG_INTERRUPT | /* Irq clears after host read */
 		MAX7359_CFG_KEY_RELEASE | /* Key release enable */
 		MAX7359_CFG_WAKEUP); /* Key press wakeup enable */
 
@@ -233,7 +212,15 @@ static int max7359_probe(struct i2c_client *client,
 	input_set_capability(input_dev, EV_MSC, MSC_SCAN);
 	input_set_drvdata(input_dev, keypad);
 
-	max7359_build_keycode(keypad, keymap_data);
+	error = matrix_keypad_build_keymap(keymap_data, NULL,
+					   MAX7359_MAX_KEY_ROWS,
+					   MAX7359_MAX_KEY_COLS,
+					   keypad->keycodes,
+					   input_dev);
+	if (error) {
+		dev_err(&client->dev, "failed to build keymap\n");
+		return error;
+	}
 
 	error = devm_request_threaded_irq(&client->dev, client->irq, NULL,
 					  max7359_interrupt,
diff --git a/drivers/input/keyboard/samsung-keypad.c b/drivers/input/keyboard/samsung-keypad.c
index 6b9fdf6cf8e8..43e48dac7687 100644
--- a/drivers/input/keyboard/samsung-keypad.c
+++ b/drivers/input/keyboard/samsung-keypad.c
@@ -585,7 +585,7 @@ static const struct of_device_id samsung_keypad_dt_match[] = {
 MODULE_DEVICE_TABLE(of, samsung_keypad_dt_match);
 #endif
 
-static struct platform_device_id samsung_keypad_driver_ids[] = {
+static const struct platform_device_id samsung_keypad_driver_ids[] = {
 	{
 		.name		= "samsung-keypad",
 		.driver_data	= KEYPAD_TYPE_SAMSUNG,
diff --git a/drivers/input/keyboard/spear-keyboard.c b/drivers/input/keyboard/spear-keyboard.c
index f42a543db043..623d451767e3 100644
--- a/drivers/input/keyboard/spear-keyboard.c
+++ b/drivers/input/keyboard/spear-keyboard.c
@@ -3,7 +3,7 @@
  * Based on omap-keypad driver
  *
  * Copyright (C) 2010 ST Microelectronics
- * Rajeev Kumar<rajeev-dlh.kumar@st.com>
+ * Rajeev Kumar <rajeevkumar.linux@gmail.com>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 4436ab1b9735..d4f0a817e858 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -610,6 +610,16 @@ config INPUT_DA9055_ONKEY
 	  To compile this driver as a module, choose M here: the module
 	  will be called da9055_onkey.
 
+config INPUT_DA9063_ONKEY
+	tristate "Dialog DA9063 OnKey"
+	depends on MFD_DA9063
+	help
+	  Support the ONKEY of Dialog DA9063 Power Management IC as an
+	  input device reporting power button statue.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called da9063_onkey.
+
 config INPUT_DM355EVM
 	tristate "TI DaVinci DM355 EVM Keypad and IR Remote"
 	depends on MFD_DM355EVM_MSP
@@ -775,6 +785,17 @@ config INPUT_DRV260X_HAPTICS
 	  To compile this driver as a module, choose M here: the
 	  module will be called drv260x-haptics.
 
+config INPUT_DRV2665_HAPTICS
+	tristate "TI DRV2665 haptics support"
+	depends on INPUT && I2C
+	select INPUT_FF_MEMLESS
+	select REGMAP_I2C
+	help
+	  Say Y to enable support for the TI DRV2665 haptics driver.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called drv2665-haptics.
+
 config INPUT_DRV2667_HAPTICS
 	tristate "TI DRV2667 haptics support"
 	depends on INPUT && I2C
@@ -784,6 +805,6 @@ config INPUT_DRV2667_HAPTICS
 	  Say Y to enable support for the TI DRV2667 haptics driver.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called drv260x-haptics.
+	  module will be called drv2667-haptics.
 
 endif
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 78ba4c1b8532..53df07dcc23c 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -25,9 +25,11 @@ obj-$(CONFIG_INPUT_CMA3000_I2C)		+= cma3000_d0x_i2c.o
 obj-$(CONFIG_INPUT_COBALT_BTNS)		+= cobalt_btns.o
 obj-$(CONFIG_INPUT_DA9052_ONKEY)	+= da9052_onkey.o
 obj-$(CONFIG_INPUT_DA9055_ONKEY)	+= da9055_onkey.o
+obj-$(CONFIG_INPUT_DA9063_ONKEY)	+= da9063_onkey.o
 obj-$(CONFIG_INPUT_DM355EVM)		+= dm355evm_keys.o
 obj-$(CONFIG_INPUT_E3X0_BUTTON)		+= e3x0-button.o
 obj-$(CONFIG_INPUT_DRV260X_HAPTICS)	+= drv260x.o
+obj-$(CONFIG_INPUT_DRV2665_HAPTICS)	+= drv2665.o
 obj-$(CONFIG_INPUT_DRV2667_HAPTICS)	+= drv2667.o
 obj-$(CONFIG_INPUT_GP2A)		+= gp2ap002a00f.o
 obj-$(CONFIG_INPUT_GPIO_BEEPER)		+= gpio-beeper.o
diff --git a/drivers/input/misc/adxl34x-i2c.c b/drivers/input/misc/adxl34x-i2c.c
index 470bfd6f0830..bdb5d03b296e 100644
--- a/drivers/input/misc/adxl34x-i2c.c
+++ b/drivers/input/misc/adxl34x-i2c.c
@@ -10,6 +10,7 @@
 #include <linux/input.h>	/* BUS_I2C */
 #include <linux/i2c.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/types.h>
 #include <linux/pm.h>
 #include "adxl34x.h"
@@ -135,11 +136,31 @@ static const struct i2c_device_id adxl34x_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, adxl34x_id);
 
+#ifdef CONFIG_OF
+static const struct of_device_id adxl34x_of_id[] = {
+	/*
+	 * The ADXL346 is backward-compatible with the ADXL345. Differences are
+	 * handled by runtime detection of the device model, there's thus no
+	 * need for listing the "adi,adxl346" compatible value explicitly.
+	 */
+	{ .compatible = "adi,adxl345", },
+	/*
+	 * Deprecated, DT nodes should use one or more of the device-specific
+	 * compatible values "adi,adxl345" and "adi,adxl346".
+	 */
+	{ .compatible = "adi,adxl34x", },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, adxl34x_of_id);
+#endif
+
 static struct i2c_driver adxl34x_driver = {
 	.driver = {
 		.name = "adxl34x",
 		.owner = THIS_MODULE,
 		.pm = &adxl34x_i2c_pm,
+		.of_match_table = of_match_ptr(adxl34x_of_id),
 	},
 	.probe    = adxl34x_i2c_probe,
 	.remove   = adxl34x_i2c_remove,
diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
new file mode 100644
index 000000000000..f577585ef999
--- /dev/null
+++ b/drivers/input/misc/da9063_onkey.c
@@ -0,0 +1,226 @@
+/*
+ * OnKey device driver for DA9063
+ * Copyright (C) 2015  Dialog Semiconductor Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/regmap.h>
+#include <linux/of.h>
+#include <linux/mfd/da9063/core.h>
+#include <linux/mfd/da9063/pdata.h>
+#include <linux/mfd/da9063/registers.h>
+
+struct da9063_onkey {
+	struct da9063 *hw;
+	struct delayed_work work;
+	struct input_dev *input;
+	struct device *dev;
+	bool key_power;
+};
+
+static void da9063_poll_on(struct work_struct *work)
+{
+	struct da9063_onkey *onkey = container_of(work, struct da9063_onkey,
+						  work.work);
+	unsigned int val;
+	int fault_log = 0;
+	bool poll = true;
+	int error;
+
+	/* Poll to see when the pin is released */
+	error = regmap_read(onkey->hw->regmap, DA9063_REG_STATUS_A, &val);
+	if (error) {
+		dev_err(onkey->dev,
+			"Failed to read ON status: %d\n", error);
+		goto err_poll;
+	}
+
+	if (!(val & DA9063_NONKEY)) {
+		error = regmap_update_bits(onkey->hw->regmap,
+					   DA9063_REG_CONTROL_B,
+					   DA9063_NONKEY_LOCK, 0);
+		if (error) {
+			dev_err(onkey->dev,
+				"Failed to reset the Key Delay %d\n", error);
+			goto err_poll;
+		}
+
+		input_report_key(onkey->input, KEY_POWER, 0);
+		input_sync(onkey->input);
+
+		poll = false;
+	}
+
+	/*
+	 * If the fault log KEY_RESET is detected, then clear it
+	 * and shut down the system.
+	 */
+	error = regmap_read(onkey->hw->regmap,
+			    DA9063_REG_FAULT_LOG, &fault_log);
+	if (error) {
+		dev_warn(&onkey->input->dev,
+			 "Cannot read FAULT_LOG: %d\n", error);
+	} else if (fault_log & DA9063_KEY_RESET) {
+		error = regmap_write(onkey->hw->regmap,
+				     DA9063_REG_FAULT_LOG,
+				     DA9063_KEY_RESET);
+		if (error) {
+			dev_warn(&onkey->input->dev,
+				 "Cannot reset KEY_RESET fault log: %d\n",
+				 error);
+		} else {
+			/* at this point we do any S/W housekeeping
+			 * and then send shutdown command
+			 */
+			dev_dbg(&onkey->input->dev,
+				 "Sending SHUTDOWN to DA9063 ...\n");
+			error = regmap_write(onkey->hw->regmap,
+					     DA9063_REG_CONTROL_F,
+					     DA9063_SHUTDOWN);
+			if (error)
+				dev_err(&onkey->input->dev,
+					"Cannot SHUTDOWN DA9063: %d\n",
+					error);
+		}
+	}
+
+err_poll:
+	if (poll)
+		schedule_delayed_work(&onkey->work, msecs_to_jiffies(50));
+}
+
+static irqreturn_t da9063_onkey_irq_handler(int irq, void *data)
+{
+	struct da9063_onkey *onkey = data;
+	unsigned int val;
+	int error;
+
+	error = regmap_read(onkey->hw->regmap, DA9063_REG_STATUS_A, &val);
+	if (onkey->key_power && !error && (val & DA9063_NONKEY)) {
+		input_report_key(onkey->input, KEY_POWER, 1);
+		input_sync(onkey->input);
+		schedule_delayed_work(&onkey->work, 0);
+		dev_dbg(onkey->dev, "KEY_POWER pressed.\n");
+	} else {
+		input_report_key(onkey->input, KEY_SLEEP, 1);
+		input_sync(onkey->input);
+		input_report_key(onkey->input, KEY_SLEEP, 0);
+		input_sync(onkey->input);
+		dev_dbg(onkey->dev, "KEY_SLEEP pressed.\n");
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void da9063_cancel_poll(void *data)
+{
+	struct da9063_onkey *onkey = data;
+
+	cancel_delayed_work_sync(&onkey->work);
+}
+
+static int da9063_onkey_probe(struct platform_device *pdev)
+{
+	struct da9063 *da9063 = dev_get_drvdata(pdev->dev.parent);
+	struct da9063_pdata *pdata = dev_get_platdata(da9063->dev);
+	struct da9063_onkey *onkey;
+	int irq;
+	int error;
+
+	onkey = devm_kzalloc(&pdev->dev, sizeof(struct da9063_onkey),
+			     GFP_KERNEL);
+	if (!onkey) {
+		dev_err(&pdev->dev, "Failed to allocate memory.\n");
+		return -ENOMEM;
+	}
+
+	onkey->dev = &pdev->dev;
+	onkey->hw = da9063;
+
+	if (pdata)
+		onkey->key_power = pdata->key_power;
+	else
+		onkey->key_power =
+			!of_property_read_bool(pdev->dev.of_node,
+					       "dlg,disable-key-power");
+
+	onkey->input = devm_input_allocate_device(&pdev->dev);
+	if (!onkey->input) {
+		dev_err(&pdev->dev, "Failed to allocated input device.\n");
+		return -ENOMEM;
+	}
+
+	onkey->input->name = DA9063_DRVNAME_ONKEY;
+	onkey->input->phys = DA9063_DRVNAME_ONKEY "/input0";
+	onkey->input->dev.parent = &pdev->dev;
+
+	if (onkey->key_power)
+		input_set_capability(onkey->input, EV_KEY, KEY_POWER);
+
+	input_set_capability(onkey->input, EV_KEY, KEY_SLEEP);
+
+	INIT_DELAYED_WORK(&onkey->work, da9063_poll_on);
+
+	error = devm_add_action(&pdev->dev, da9063_cancel_poll, onkey);
+	if (error) {
+		dev_err(&pdev->dev,
+			"Failed to add cancel poll action: %d\n",
+			error);
+		return error;
+	}
+
+	irq = platform_get_irq_byname(pdev, "ONKEY");
+	if (irq < 0) {
+		error = irq;
+		dev_err(&pdev->dev, "Failed to get platform IRQ: %d\n", error);
+		return error;
+	}
+
+	error = devm_request_threaded_irq(&pdev->dev, irq,
+					  NULL, da9063_onkey_irq_handler,
+					  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+					  "ONKEY", onkey);
+	if (error) {
+		dev_err(&pdev->dev,
+			"Failed to request IRQ %d: %d\n", irq, error);
+		return error;
+	}
+
+	error = input_register_device(onkey->input);
+	if (error) {
+		dev_err(&pdev->dev,
+			"Failed to register input device: %d\n", error);
+		return error;
+	}
+
+	platform_set_drvdata(pdev, onkey);
+	return 0;
+}
+
+static struct platform_driver da9063_onkey_driver = {
+	.probe	= da9063_onkey_probe,
+	.driver	= {
+		.name	= DA9063_DRVNAME_ONKEY,
+	},
+};
+module_platform_driver(da9063_onkey_driver);
+
+MODULE_AUTHOR("S Twiss <stwiss.opensource@diasemi.com>");
+MODULE_DESCRIPTION("Onkey device driver for Dialog DA9063");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DA9063_DRVNAME_ONKEY);
diff --git a/drivers/input/misc/drv260x.c b/drivers/input/misc/drv260x.c
index 599578042ea0..e5d60ecd29a4 100644
--- a/drivers/input/misc/drv260x.c
+++ b/drivers/input/misc/drv260x.c
@@ -580,15 +580,10 @@ static int drv260x_probe(struct i2c_client *client,
 		return error;
 	}
 
-	haptics->enable_gpio = devm_gpiod_get(&client->dev, "enable");
-	if (IS_ERR(haptics->enable_gpio)) {
-		error = PTR_ERR(haptics->enable_gpio);
-		if (error != -ENOENT && error != -ENOSYS)
-			return error;
-		haptics->enable_gpio = NULL;
-	} else {
-		gpiod_direction_output(haptics->enable_gpio, 1);
-	}
+	haptics->enable_gpio = devm_gpiod_get_optional(&client->dev, "enable",
+						       GPIOD_OUT_HIGH);
+	if (IS_ERR(haptics->enable_gpio))
+		return PTR_ERR(haptics->enable_gpio);
 
 	haptics->input_dev = devm_input_allocate_device(&client->dev);
 	if (!haptics->input_dev) {
diff --git a/drivers/input/misc/drv2665.c b/drivers/input/misc/drv2665.c
new file mode 100644
index 000000000000..0afaa33de07d
--- /dev/null
+++ b/drivers/input/misc/drv2665.c
@@ -0,0 +1,322 @@
+/*
+ * DRV2665 haptics driver family
+ *
+ * Author: Dan Murphy <dmurphy@ti.com>
+ *
+ * Copyright: (C) 2015 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/regulator/consumer.h>
+
+/* Contol registers */
+#define DRV2665_STATUS	0x00
+#define DRV2665_CTRL_1	0x01
+#define DRV2665_CTRL_2	0x02
+#define DRV2665_FIFO	0x0b
+
+/* Status Register */
+#define DRV2665_FIFO_FULL		BIT(0)
+#define DRV2665_FIFO_EMPTY		BIT(1)
+
+/* Control 1 Register */
+#define DRV2665_25_VPP_GAIN		0x00
+#define DRV2665_50_VPP_GAIN		0x01
+#define DRV2665_75_VPP_GAIN		0x02
+#define DRV2665_100_VPP_GAIN		0x03
+#define DRV2665_DIGITAL_IN		0xfc
+#define DRV2665_ANALOG_IN		BIT(2)
+
+/* Control 2 Register */
+#define DRV2665_BOOST_EN		BIT(1)
+#define DRV2665_STANDBY			BIT(6)
+#define DRV2665_DEV_RST			BIT(7)
+#define DRV2665_5_MS_IDLE_TOUT		0x00
+#define DRV2665_10_MS_IDLE_TOUT		0x04
+#define DRV2665_15_MS_IDLE_TOUT		0x08
+#define DRV2665_20_MS_IDLE_TOUT		0x0c
+
+/**
+ * struct drv2665_data -
+ * @input_dev - Pointer to the input device
+ * @client - Pointer to the I2C client
+ * @regmap - Register map of the device
+ * @work - Work item used to off load the enable/disable of the vibration
+ * @regulator - Pointer to the regulator for the IC
+ */
+struct drv2665_data {
+	struct input_dev *input_dev;
+	struct i2c_client *client;
+	struct regmap *regmap;
+	struct work_struct work;
+	struct regulator *regulator;
+};
+
+/* 8kHz Sine wave to stream to the FIFO */
+static const u8 drv2665_sine_wave_form[] = {
+	0x00, 0x10, 0x20, 0x2e, 0x3c, 0x48, 0x53, 0x5b, 0x61, 0x65, 0x66,
+	0x65, 0x61, 0x5b, 0x53, 0x48, 0x3c, 0x2e, 0x20, 0x10,
+	0x00, 0xf0, 0xe0, 0xd2, 0xc4, 0xb8, 0xad, 0xa5, 0x9f, 0x9b, 0x9a,
+	0x9b, 0x9f, 0xa5, 0xad, 0xb8, 0xc4, 0xd2, 0xe0, 0xf0, 0x00,
+};
+
+static struct reg_default drv2665_reg_defs[] = {
+	{ DRV2665_STATUS, 0x02 },
+	{ DRV2665_CTRL_1, 0x28 },
+	{ DRV2665_CTRL_2, 0x40 },
+	{ DRV2665_FIFO, 0x00 },
+};
+
+static void drv2665_worker(struct work_struct *work)
+{
+	struct drv2665_data *haptics =
+				container_of(work, struct drv2665_data, work);
+	unsigned int read_buf;
+	int error;
+
+	error = regmap_read(haptics->regmap, DRV2665_STATUS, &read_buf);
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to read status: %d\n", error);
+		return;
+	}
+
+	if (read_buf & DRV2665_FIFO_EMPTY) {
+		error = regmap_bulk_write(haptics->regmap,
+					  DRV2665_FIFO,
+					  drv2665_sine_wave_form,
+					  ARRAY_SIZE(drv2665_sine_wave_form));
+		if (error) {
+			dev_err(&haptics->client->dev,
+				"Failed to write FIFO: %d\n", error);
+			return;
+		}
+	}
+}
+
+static int drv2665_haptics_play(struct input_dev *input, void *data,
+				struct ff_effect *effect)
+{
+	struct drv2665_data *haptics = input_get_drvdata(input);
+
+	schedule_work(&haptics->work);
+
+	return 0;
+}
+
+static void drv2665_close(struct input_dev *input)
+{
+	struct drv2665_data *haptics = input_get_drvdata(input);
+	int error;
+
+	cancel_work_sync(&haptics->work);
+
+	error = regmap_update_bits(haptics->regmap,
+				   DRV2665_CTRL_2, DRV2665_STANDBY, 1);
+	if (error)
+		dev_err(&haptics->client->dev,
+			"Failed to enter standby mode: %d\n", error);
+}
+
+static const struct reg_default drv2665_init_regs[] = {
+	{ DRV2665_CTRL_2, 0 | DRV2665_10_MS_IDLE_TOUT },
+	{ DRV2665_CTRL_1, DRV2665_25_VPP_GAIN },
+};
+
+static int drv2665_init(struct drv2665_data *haptics)
+{
+	int error;
+
+	error = regmap_register_patch(haptics->regmap,
+				      drv2665_init_regs,
+				      ARRAY_SIZE(drv2665_init_regs));
+	if (error) {
+		dev_err(&haptics->client->dev,
+			"Failed to write init registers: %d\n",
+			error);
+		return error;
+	}
+
+	return 0;
+}
+
+static const struct regmap_config drv2665_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = DRV2665_FIFO,
+	.reg_defaults = drv2665_reg_defs,
+	.num_reg_defaults = ARRAY_SIZE(drv2665_reg_defs),
+	.cache_type = REGCACHE_NONE,
+};
+
+static int drv2665_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct drv2665_data *haptics;
+	int error;
+
+	haptics = devm_kzalloc(&client->dev, sizeof(*haptics), GFP_KERNEL);
+	if (!haptics)
+		return -ENOMEM;
+
+	haptics->regulator = devm_regulator_get(&client->dev, "vbat");
+	if (IS_ERR(haptics->regulator)) {
+		error = PTR_ERR(haptics->regulator);
+		dev_err(&client->dev,
+			"unable to get regulator, error: %d\n", error);
+		return error;
+	}
+
+	haptics->input_dev = devm_input_allocate_device(&client->dev);
+	if (!haptics->input_dev) {
+		dev_err(&client->dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	haptics->input_dev->name = "drv2665:haptics";
+	haptics->input_dev->dev.parent = client->dev.parent;
+	haptics->input_dev->close = drv2665_close;
+	input_set_drvdata(haptics->input_dev, haptics);
+	input_set_capability(haptics->input_dev, EV_FF, FF_RUMBLE);
+
+	error = input_ff_create_memless(haptics->input_dev, NULL,
+					drv2665_haptics_play);
+	if (error) {
+		dev_err(&client->dev, "input_ff_create() failed: %d\n",
+			error);
+		return error;
+	}
+
+	INIT_WORK(&haptics->work, drv2665_worker);
+
+	haptics->client = client;
+	i2c_set_clientdata(client, haptics);
+
+	haptics->regmap = devm_regmap_init_i2c(client, &drv2665_regmap_config);
+	if (IS_ERR(haptics->regmap)) {
+		error = PTR_ERR(haptics->regmap);
+		dev_err(&client->dev, "Failed to allocate register map: %d\n",
+			error);
+		return error;
+	}
+
+	error = drv2665_init(haptics);
+	if (error) {
+		dev_err(&client->dev, "Device init failed: %d\n", error);
+		return error;
+	}
+
+	error = input_register_device(haptics->input_dev);
+	if (error) {
+		dev_err(&client->dev, "couldn't register input device: %d\n",
+			error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused drv2665_suspend(struct device *dev)
+{
+	struct drv2665_data *haptics = dev_get_drvdata(dev);
+	int ret = 0;
+
+	mutex_lock(&haptics->input_dev->mutex);
+
+	if (haptics->input_dev->users) {
+		ret = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
+				DRV2665_STANDBY, 1);
+		if (ret) {
+			dev_err(dev, "Failed to set standby mode\n");
+			regulator_disable(haptics->regulator);
+			goto out;
+		}
+
+		ret = regulator_disable(haptics->regulator);
+		if (ret) {
+			dev_err(dev, "Failed to disable regulator\n");
+			regmap_update_bits(haptics->regmap,
+					   DRV2665_CTRL_2,
+					   DRV2665_STANDBY, 0);
+		}
+	}
+out:
+	mutex_unlock(&haptics->input_dev->mutex);
+	return ret;
+}
+
+static int __maybe_unused drv2665_resume(struct device *dev)
+{
+	struct drv2665_data *haptics = dev_get_drvdata(dev);
+	int ret = 0;
+
+	mutex_lock(&haptics->input_dev->mutex);
+
+	if (haptics->input_dev->users) {
+		ret = regulator_enable(haptics->regulator);
+		if (ret) {
+			dev_err(dev, "Failed to enable regulator\n");
+			goto out;
+		}
+
+		ret = regmap_update_bits(haptics->regmap, DRV2665_CTRL_2,
+					 DRV2665_STANDBY, 0);
+		if (ret) {
+			dev_err(dev, "Failed to unset standby mode\n");
+			regulator_disable(haptics->regulator);
+			goto out;
+		}
+
+	}
+
+out:
+	mutex_unlock(&haptics->input_dev->mutex);
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(drv2665_pm_ops, drv2665_suspend, drv2665_resume);
+
+static const struct i2c_device_id drv2665_id[] = {
+	{ "drv2665", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, drv2665_id);
+
+#ifdef CONFIG_OF
+static const struct of_device_id drv2665_of_match[] = {
+	{ .compatible = "ti,drv2665", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, drv2665_of_match);
+#endif
+
+static struct i2c_driver drv2665_driver = {
+	.probe		= drv2665_probe,
+	.driver		= {
+		.name	= "drv2665-haptics",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(drv2665_of_match),
+		.pm	= &drv2665_pm_ops,
+	},
+	.id_table = drv2665_id,
+};
+module_i2c_driver(drv2665_driver);
+
+MODULE_DESCRIPTION("TI DRV2665 haptics driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com>");
diff --git a/drivers/input/misc/gpio-beeper.c b/drivers/input/misc/gpio-beeper.c
index 4817c5f0c3e4..16272fffeb7e 100644
--- a/drivers/input/misc/gpio-beeper.c
+++ b/drivers/input/misc/gpio-beeper.c
@@ -66,13 +66,12 @@ static int gpio_beeper_probe(struct platform_device *pdev)
 {
 	struct gpio_beeper *beep;
 	struct input_dev *input;
-	int err;
 
 	beep = devm_kzalloc(&pdev->dev, sizeof(*beep), GFP_KERNEL);
 	if (!beep)
 		return -ENOMEM;
 
-	beep->desc = devm_gpiod_get(&pdev->dev, NULL);
+	beep->desc = devm_gpiod_get(&pdev->dev, NULL, GPIOD_OUT_LOW);
 	if (IS_ERR(beep->desc))
 		return PTR_ERR(beep->desc);
 
@@ -92,10 +91,6 @@ static int gpio_beeper_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_SND, SND_BELL);
 
-	err = gpiod_direction_output(beep->desc, 0);
-	if (err)
-		return err;
-
 	input_set_drvdata(input, beep);
 
 	return input_register_device(input);
diff --git a/drivers/input/misc/retu-pwrbutton.c b/drivers/input/misc/retu-pwrbutton.c
index 0c8ac60e2639..30b459b6b344 100644
--- a/drivers/input/misc/retu-pwrbutton.c
+++ b/drivers/input/misc/retu-pwrbutton.c
@@ -63,7 +63,8 @@ static int retu_pwrbutton_probe(struct platform_device *pdev)
 	input_set_drvdata(idev, rdev);
 
 	error = devm_request_threaded_irq(&pdev->dev, irq,
-					  NULL, retu_pwrbutton_irq, 0,
+					  NULL, retu_pwrbutton_irq,
+					  IRQF_ONESHOT,
 					  "retu-pwrbutton", idev);
 	if (error)
 		return error;
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index e8e010a85484..c14b82709b0f 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -18,7 +18,6 @@
 #include <linux/gpio/consumer.h>
 #include <linux/gpio_keys.h>
 #include <linux/platform_device.h>
-#include <linux/acpi.h>
 
 /*
  * Definition of buttons on the tablet. The ACPI index of each button
diff --git a/drivers/input/misc/twl4030-pwrbutton.c b/drivers/input/misc/twl4030-pwrbutton.c
index e98cc81a84c6..603fc2fadf05 100644
--- a/drivers/input/misc/twl4030-pwrbutton.c
+++ b/drivers/input/misc/twl4030-pwrbutton.c
@@ -71,7 +71,8 @@ static int twl4030_pwrbutton_probe(struct platform_device *pdev)
 	pwr->dev.parent = &pdev->dev;
 
 	err = devm_request_threaded_irq(&pwr->dev, irq, NULL, powerbutton_irq,
-			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING |
+			IRQF_ONESHOT,
 			"twl4030_pwrbutton", pwr);
 	if (err < 0) {
 		dev_err(&pdev->dev, "Can't get IRQ for pwrbutton: %d\n", err);
diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index 0e0d094df2e6..ea63fad48de6 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -308,7 +308,8 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	mutex_init(&info->mutex);
 
 	error = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
-					  twl6040_vib_irq_handler, 0,
+					  twl6040_vib_irq_handler,
+					  IRQF_ONESHOT,
 					  "twl6040_irq_vib", info);
 	if (error) {
 		dev_err(info->dev, "VIB IRQ request failed: %d\n", error);
diff --git a/drivers/input/misc/wm831x-on.c b/drivers/input/misc/wm831x-on.c
index 59d4f7bcb4a3..1b44de265a0a 100644
--- a/drivers/input/misc/wm831x-on.c
+++ b/drivers/input/misc/wm831x-on.c
@@ -99,7 +99,8 @@ static int wm831x_on_probe(struct platform_device *pdev)
 	wm831x_on->dev->dev.parent = &pdev->dev;
 
 	ret = request_threaded_irq(irq, NULL, wm831x_on_irq,
-				   IRQF_TRIGGER_RISING, "wm831x_on",
+				   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				   "wm831x_on",
 				   wm831x_on);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to request IRQ: %d\n", ret);
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index 7462d2fc8cfe..d7820d1152d2 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -156,7 +156,7 @@ config MOUSE_PS2_VMMOUSE
 	  Say Y here if you are running under control of VMware hypervisor
 	  (ESXi, Workstation or Fusion). Also make sure that when you enable
 	  this option, you remove the xf86-input-vmmouse user-space driver
-	  or upgrade it to at least xf86-input-vmmouse 13.0.1, which doesn't
+	  or upgrade it to at least xf86-input-vmmouse 13.1.0, which doesn't
 	  load in the presence of an in-kernel vmmouse driver.
 
 	  If unsure, say N.
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index e6708f6efb4d..113d6f1516a5 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -159,8 +159,8 @@ static const struct alps_protocol_info alps_v8_protocol_data = {
 
 static void alps_set_abs_params_st(struct alps_data *priv,
 				   struct input_dev *dev1);
-static void alps_set_abs_params_mt(struct alps_data *priv,
-				   struct input_dev *dev1);
+static void alps_set_abs_params_semi_mt(struct alps_data *priv,
+					struct input_dev *dev1);
 static void alps_set_abs_params_v7(struct alps_data *priv,
 				   struct input_dev *dev1);
 static void alps_set_abs_params_ss4_v2(struct alps_data *priv,
@@ -310,53 +310,6 @@ static void alps_process_packet_v1_v2(struct psmouse *psmouse)
 	input_sync(dev);
 }
 
-/*
- * Process bitmap data for V5 protocols. Return value is null.
- *
- * The bitmaps don't have enough data to track fingers, so this function
- * only generates points representing a bounding box of at most two contacts.
- * These two points are returned in fields->mt.
- */
-static void alps_process_bitmap_dolphin(struct alps_data *priv,
-					struct alps_fields *fields)
-{
-	int box_middle_x, box_middle_y;
-	unsigned int x_map, y_map;
-	unsigned char start_bit, end_bit;
-	unsigned char x_msb, x_lsb, y_msb, y_lsb;
-
-	x_map = fields->x_map;
-	y_map = fields->y_map;
-
-	if (!x_map || !y_map)
-		return;
-
-	/* Get Most-significant and Least-significant bit */
-	x_msb = fls(x_map);
-	x_lsb = ffs(x_map);
-	y_msb = fls(y_map);
-	y_lsb = ffs(y_map);
-
-	/* Most-significant bit should never exceed max sensor line number */
-	if (x_msb > priv->x_bits || y_msb > priv->y_bits)
-		return;
-
-	if (fields->fingers > 1) {
-		start_bit = priv->x_bits - x_msb;
-		end_bit = priv->x_bits - x_lsb;
-		box_middle_x = (priv->x_max * (start_bit + end_bit)) /
-				(2 * (priv->x_bits - 1));
-
-		start_bit = y_lsb - 1;
-		end_bit = y_msb - 1;
-		box_middle_y = (priv->y_max * (start_bit + end_bit)) /
-				(2 * (priv->y_bits - 1));
-		fields->mt[0] = fields->st;
-		fields->mt[1].x = 2 * box_middle_x - fields->mt[0].x;
-		fields->mt[1].y = 2 * box_middle_y - fields->mt[0].y;
-	}
-}
-
 static void alps_get_bitmap_points(unsigned int map,
 				   struct alps_bitmap_point *low,
 				   struct alps_bitmap_point *high,
@@ -384,7 +337,7 @@ static void alps_get_bitmap_points(unsigned int map,
 }
 
 /*
- * Process bitmap data from v3 and v4 protocols. Returns the number of
+ * Process bitmap data from semi-mt protocols. Returns the number of
  * fingers detected. A return value of 0 means at least one of the
  * bitmaps was empty.
  *
@@ -396,9 +349,10 @@ static void alps_get_bitmap_points(unsigned int map,
 static int alps_process_bitmap(struct alps_data *priv,
 			       struct alps_fields *fields)
 {
-	int i, fingers_x = 0, fingers_y = 0, fingers;
+	int i, fingers_x = 0, fingers_y = 0, fingers, closest;
 	struct alps_bitmap_point x_low = {0,}, x_high = {0,};
 	struct alps_bitmap_point y_low = {0,}, y_high = {0,};
+	struct input_mt_pos corner[4];
 
 	if (!fields->x_map || !fields->y_map)
 		return 0;
@@ -429,26 +383,76 @@ static int alps_process_bitmap(struct alps_data *priv,
 		y_high.num_bits = max(i, 1);
 	}
 
-	fields->mt[0].x =
+	/* top-left corner */
+	corner[0].x =
 		(priv->x_max * (2 * x_low.start_bit + x_low.num_bits - 1)) /
 		(2 * (priv->x_bits - 1));
-	fields->mt[0].y =
+	corner[0].y =
 		(priv->y_max * (2 * y_low.start_bit + y_low.num_bits - 1)) /
 		(2 * (priv->y_bits - 1));
 
-	fields->mt[1].x =
+	/* top-right corner */
+	corner[1].x =
 		(priv->x_max * (2 * x_high.start_bit + x_high.num_bits - 1)) /
 		(2 * (priv->x_bits - 1));
-	fields->mt[1].y =
+	corner[1].y =
+		(priv->y_max * (2 * y_low.start_bit + y_low.num_bits - 1)) /
+		(2 * (priv->y_bits - 1));
+
+	/* bottom-right corner */
+	corner[2].x =
+		(priv->x_max * (2 * x_high.start_bit + x_high.num_bits - 1)) /
+		(2 * (priv->x_bits - 1));
+	corner[2].y =
+		(priv->y_max * (2 * y_high.start_bit + y_high.num_bits - 1)) /
+		(2 * (priv->y_bits - 1));
+
+	/* bottom-left corner */
+	corner[3].x =
+		(priv->x_max * (2 * x_low.start_bit + x_low.num_bits - 1)) /
+		(2 * (priv->x_bits - 1));
+	corner[3].y =
 		(priv->y_max * (2 * y_high.start_bit + y_high.num_bits - 1)) /
 		(2 * (priv->y_bits - 1));
 
-	/* y-bitmap order is reversed, except on rushmore */
-	if (priv->proto_version != ALPS_PROTO_V3_RUSHMORE) {
-		fields->mt[0].y = priv->y_max - fields->mt[0].y;
-		fields->mt[1].y = priv->y_max - fields->mt[1].y;
+	/* x-bitmap order is reversed on v5 touchpads  */
+	if (priv->proto_version == ALPS_PROTO_V5) {
+		for (i = 0; i < 4; i++)
+			corner[i].x = priv->x_max - corner[i].x;
+	}
+
+	/* y-bitmap order is reversed on v3 and v4 touchpads  */
+	if (priv->proto_version == ALPS_PROTO_V3 ||
+	    priv->proto_version == ALPS_PROTO_V4) {
+		for (i = 0; i < 4; i++)
+			corner[i].y = priv->y_max - corner[i].y;
+	}
+
+	/*
+	 * We only select a corner for the second touch once per 2 finger
+	 * touch sequence to avoid the chosen corner (and thus the coordinates)
+	 * jumping around when the first touch is in the middle.
+	 */
+	if (priv->second_touch == -1) {
+		/* Find corner closest to our st coordinates */
+		closest = 0x7fffffff;
+		for (i = 0; i < 4; i++) {
+			int dx = fields->st.x - corner[i].x;
+			int dy = fields->st.y - corner[i].y;
+			int distance = dx * dx + dy * dy;
+
+			if (distance < closest) {
+				priv->second_touch = i;
+				closest = distance;
+			}
+		}
+		/* And select the opposite corner to use for the 2nd touch */
+		priv->second_touch = (priv->second_touch + 2) % 4;
 	}
 
+	fields->mt[0] = fields->st;
+	fields->mt[1] = corner[priv->second_touch];
+
 	return fingers;
 }
 
@@ -485,9 +489,14 @@ static void alps_report_semi_mt_data(struct psmouse *psmouse, int fingers)
 		f->mt[0].x = f->st.x;
 		f->mt[0].y = f->st.y;
 		fingers = f->pressure > 0 ? 1 : 0;
+		priv->second_touch = -1;
 	}
 
-	alps_report_mt_data(psmouse, (fingers <= 2) ? fingers : 2);
+	if (fingers >= 1)
+		alps_set_slot(dev, 0, f->mt[0].x, f->mt[0].y);
+	if (fingers >= 2)
+		alps_set_slot(dev, 1, f->mt[1].x, f->mt[1].y);
+	input_mt_sync_frame(dev);
 
 	input_mt_report_finger_count(dev, fingers);
 
@@ -584,20 +593,22 @@ static int alps_decode_pinnacle(struct alps_fields *f, unsigned char *p,
 	f->first_mp = !!(p[4] & 0x40);
 	f->is_mp = !!(p[0] & 0x40);
 
-	f->fingers = (p[5] & 0x3) + 1;
-	f->x_map = ((p[4] & 0x7e) << 8) |
-		   ((p[1] & 0x7f) << 2) |
-		   ((p[0] & 0x30) >> 4);
-	f->y_map = ((p[3] & 0x70) << 4) |
-		   ((p[2] & 0x7f) << 1) |
-		   (p[4] & 0x01);
-
-	f->st.x = ((p[1] & 0x7f) << 4) | ((p[4] & 0x30) >> 2) |
-	       ((p[0] & 0x30) >> 4);
-	f->st.y = ((p[2] & 0x7f) << 4) | (p[4] & 0x0f);
-	f->pressure = p[5] & 0x7f;
+	if (f->is_mp) {
+		f->fingers = (p[5] & 0x3) + 1;
+		f->x_map = ((p[4] & 0x7e) << 8) |
+			   ((p[1] & 0x7f) << 2) |
+			   ((p[0] & 0x30) >> 4);
+		f->y_map = ((p[3] & 0x70) << 4) |
+			   ((p[2] & 0x7f) << 1) |
+			   (p[4] & 0x01);
+	} else {
+		f->st.x = ((p[1] & 0x7f) << 4) | ((p[4] & 0x30) >> 2) |
+		       ((p[0] & 0x30) >> 4);
+		f->st.y = ((p[2] & 0x7f) << 4) | (p[4] & 0x0f);
+		f->pressure = p[5] & 0x7f;
 
-	alps_decode_buttons_v3(f, p);
+		alps_decode_buttons_v3(f, p);
+	}
 
 	return 0;
 }
@@ -605,13 +616,27 @@ static int alps_decode_pinnacle(struct alps_fields *f, unsigned char *p,
 static int alps_decode_rushmore(struct alps_fields *f, unsigned char *p,
 				 struct psmouse *psmouse)
 {
-	alps_decode_pinnacle(f, p, psmouse);
-
-	/* Rushmore's packet decode has a bit difference with Pinnacle's */
+	f->first_mp = !!(p[4] & 0x40);
 	f->is_mp = !!(p[5] & 0x40);
-	f->fingers = max((p[5] & 0x3), ((p[5] >> 2) & 0x3)) + 1;
-	f->x_map |= (p[5] & 0x10) << 11;
-	f->y_map |= (p[5] & 0x20) << 6;
+
+	if (f->is_mp) {
+		f->fingers = max((p[5] & 0x3), ((p[5] >> 2) & 0x3)) + 1;
+		f->x_map = ((p[5] & 0x10) << 11) |
+			   ((p[4] & 0x7e) << 8) |
+			   ((p[1] & 0x7f) << 2) |
+			   ((p[0] & 0x30) >> 4);
+		f->y_map = ((p[5] & 0x20) << 6) |
+			   ((p[3] & 0x70) << 4) |
+			   ((p[2] & 0x7f) << 1) |
+			   (p[4] & 0x01);
+	} else {
+		f->st.x = ((p[1] & 0x7f) << 4) | ((p[4] & 0x30) >> 2) |
+		       ((p[0] & 0x30) >> 4);
+		f->st.y = ((p[2] & 0x7f) << 4) | (p[4] & 0x0f);
+		f->pressure = p[5] & 0x7f;
+
+		alps_decode_buttons_v3(f, p);
+	}
 
 	return 0;
 }
@@ -680,30 +705,13 @@ static void alps_process_touchpad_packet_v3_v5(struct psmouse *psmouse)
 		 */
 		if (f->is_mp) {
 			fingers = f->fingers;
-			if (priv->proto_version == ALPS_PROTO_V3 ||
-			    priv->proto_version == ALPS_PROTO_V3_RUSHMORE) {
-				if (alps_process_bitmap(priv, f) == 0)
-					fingers = 0; /* Use st data */
-
-				/* Now process position packet */
-				priv->decode_fields(f, priv->multi_data,
-						    psmouse);
-			} else {
-				/*
-				 * Because Dolphin uses position packet's
-				 * coordinate data as Pt1 and uses it to
-				 * calculate Pt2, so we need to do position
-				 * packet decode first.
-				 */
-				priv->decode_fields(f, priv->multi_data,
-						    psmouse);
-
-				/*
-				 * Since Dolphin's finger number is reliable,
-				 * there is no need to compare with bmap_fn.
-				 */
-				alps_process_bitmap_dolphin(priv, f);
-			}
+			/*
+			 * Bitmap processing uses position packet's coordinate
+			 * data, so we need to do decode it first.
+			 */
+			priv->decode_fields(f, priv->multi_data, psmouse);
+			if (alps_process_bitmap(priv, f) == 0)
+				fingers = 0; /* Use st data */
 		} else {
 			priv->multi_packet = 0;
 		}
@@ -865,6 +873,14 @@ static void alps_process_packet_v4(struct psmouse *psmouse)
 	priv->multi_data[offset] = packet[6];
 	priv->multi_data[offset + 1] = packet[7];
 
+	f->left = !!(packet[4] & 0x01);
+	f->right = !!(packet[4] & 0x02);
+
+	f->st.x = ((packet[1] & 0x7f) << 4) | ((packet[3] & 0x30) >> 2) |
+		  ((packet[0] & 0x30) >> 4);
+	f->st.y = ((packet[2] & 0x7f) << 4) | (packet[3] & 0x0f);
+	f->pressure = packet[5] & 0x7f;
+
 	if (++priv->multi_packet > 2) {
 		priv->multi_packet = 0;
 
@@ -879,14 +895,6 @@ static void alps_process_packet_v4(struct psmouse *psmouse)
 		f->fingers = alps_process_bitmap(priv, f);
 	}
 
-	f->left = !!(packet[4] & 0x01);
-	f->right = !!(packet[4] & 0x02);
-
-	f->st.x = ((packet[1] & 0x7f) << 4) | ((packet[3] & 0x30) >> 2) |
-		  ((packet[0] & 0x30) >> 4);
-	f->st.y = ((packet[2] & 0x7f) << 4) | (packet[3] & 0x0f);
-	f->pressure = packet[5] & 0x7f;
-
 	alps_report_semi_mt_data(psmouse, f->fingers);
 }
 
@@ -941,6 +949,11 @@ static void alps_get_finger_coordinate_v7(struct input_mt_pos *mt,
 	case V7_PACKET_ID_TWO:
 		mt[1].x &= ~0x000F;
 		mt[1].y |= 0x000F;
+		/* Detect false-postive touches where x & y report max value */
+		if (mt[1].y == 0x7ff && mt[1].x == 0xff0) {
+			mt[1].x = 0;
+			/* y gets set to 0 at the end of this function */
+		}
 		break;
 
 	case V7_PACKET_ID_MULTI:
@@ -1058,9 +1071,8 @@ static void alps_process_trackstick_packet_v7(struct psmouse *psmouse)
 	right = (packet[1] & 0x02) >> 1;
 	middle = (packet[1] & 0x04) >> 2;
 
-	/* Divide 2 since trackpoint's speed is too fast */
-	input_report_rel(dev2, REL_X, (char)x / 2);
-	input_report_rel(dev2, REL_Y, -((char)y / 2));
+	input_report_rel(dev2, REL_X, (char)x);
+	input_report_rel(dev2, REL_Y, -((char)y));
 
 	input_report_key(dev2, BTN_LEFT, left);
 	input_report_key(dev2, BTN_RIGHT, right);
@@ -2557,7 +2569,7 @@ static int alps_set_protocol(struct psmouse *psmouse,
 	case ALPS_PROTO_V3:
 		priv->hw_init = alps_hw_init_v3;
 		priv->process_packet = alps_process_packet_v3;
-		priv->set_abs_params = alps_set_abs_params_mt;
+		priv->set_abs_params = alps_set_abs_params_semi_mt;
 		priv->decode_fields = alps_decode_pinnacle;
 		priv->nibble_commands = alps_v3_nibble_commands;
 		priv->addr_command = PSMOUSE_CMD_RESET_WRAP;
@@ -2566,7 +2578,7 @@ static int alps_set_protocol(struct psmouse *psmouse,
 	case ALPS_PROTO_V3_RUSHMORE:
 		priv->hw_init = alps_hw_init_rushmore_v3;
 		priv->process_packet = alps_process_packet_v3;
-		priv->set_abs_params = alps_set_abs_params_mt;
+		priv->set_abs_params = alps_set_abs_params_semi_mt;
 		priv->decode_fields = alps_decode_rushmore;
 		priv->nibble_commands = alps_v3_nibble_commands;
 		priv->addr_command = PSMOUSE_CMD_RESET_WRAP;
@@ -2582,7 +2594,7 @@ static int alps_set_protocol(struct psmouse *psmouse,
 	case ALPS_PROTO_V4:
 		priv->hw_init = alps_hw_init_v4;
 		priv->process_packet = alps_process_packet_v4;
-		priv->set_abs_params = alps_set_abs_params_mt;
+		priv->set_abs_params = alps_set_abs_params_semi_mt;
 		priv->nibble_commands = alps_v4_nibble_commands;
 		priv->addr_command = PSMOUSE_CMD_DISABLE;
 		break;
@@ -2591,7 +2603,7 @@ static int alps_set_protocol(struct psmouse *psmouse,
 		priv->hw_init = alps_hw_init_dolphin_v1;
 		priv->process_packet = alps_process_touchpad_packet_v3_v5;
 		priv->decode_fields = alps_decode_dolphin;
-		priv->set_abs_params = alps_set_abs_params_mt;
+		priv->set_abs_params = alps_set_abs_params_semi_mt;
 		priv->nibble_commands = alps_v3_nibble_commands;
 		priv->addr_command = PSMOUSE_CMD_RESET_WRAP;
 		priv->x_bits = 23;
@@ -2773,15 +2785,15 @@ static void alps_set_abs_params_mt_common(struct alps_data *priv,
 	set_bit(BTN_TOOL_QUADTAP, dev1->keybit);
 }
 
-static void alps_set_abs_params_mt(struct alps_data *priv,
-				   struct input_dev *dev1)
+static void alps_set_abs_params_semi_mt(struct alps_data *priv,
+					struct input_dev *dev1)
 {
 	alps_set_abs_params_mt_common(priv, dev1);
 	input_set_abs_params(dev1, ABS_PRESSURE, 0, 127, 0, 0);
 
 	input_mt_init_slots(dev1, MAX_TOUCHES,
 			    INPUT_MT_POINTER | INPUT_MT_DROP_UNUSED |
-				INPUT_MT_TRACK | INPUT_MT_SEMI_MT);
+				INPUT_MT_SEMI_MT);
 }
 
 static void alps_set_abs_params_v7(struct alps_data *priv,
diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h
index 6dfdccc3a7c6..d37f814dc447 100644
--- a/drivers/input/mouse/alps.h
+++ b/drivers/input/mouse/alps.h
@@ -278,6 +278,7 @@ struct alps_data {
 
 	int prev_fin;
 	int multi_packet;
+	int second_touch;
 	unsigned char multi_data[6];
 	struct alps_fields f;
 	u8 quirks;
diff --git a/drivers/input/mouse/cyapa_gen3.c b/drivers/input/mouse/cyapa_gen3.c
index 1e2291c378fe..3faf01c1b191 100644
--- a/drivers/input/mouse/cyapa_gen3.c
+++ b/drivers/input/mouse/cyapa_gen3.c
@@ -950,14 +950,13 @@ static u16 cyapa_get_wait_time_for_pwr_cmd(u8 pwr_mode)
  * Device power mode can only be set when device is in operational mode.
  */
 static int cyapa_gen3_set_power_mode(struct cyapa *cyapa, u8 power_mode,
-		u16 always_unused)
+				     u16 always_unused)
 {
 	int ret;
 	u8 power;
 	int tries;
 	u16 sleep_time;
 
-	always_unused = 0;
 	if (cyapa->state != CYAPA_STATE_OP)
 		return 0;
 
diff --git a/drivers/input/mouse/cyapa_gen5.c b/drivers/input/mouse/cyapa_gen5.c
index 5b611dd71e79..afc39e799da2 100644
--- a/drivers/input/mouse/cyapa_gen5.c
+++ b/drivers/input/mouse/cyapa_gen5.c
@@ -352,7 +352,7 @@ struct gen5_app_cmd_head {
 	u8 parameter_data[0];  /* Parameter data variable based on cmd_code */
 } __packed;
 
-/* Applicaton get/set parameter command data structure */
+/* Application get/set parameter command data structure */
 struct gen5_app_set_parameter_data {
 	u8 parameter_id;
 	u8 parameter_size;
@@ -832,7 +832,7 @@ static int gen5_hid_description_header_parse(struct cyapa *cyapa, u8 *reg_data)
 	int ret;
 
 	/* 0x20 0x00 0xF7 is Gen5 Application HID Description Header;
-	 * 0x20 0x00 0xFF is Gen5 Booloader HID Description Header.
+	 * 0x20 0x00 0xFF is Gen5 Bootloader HID Description Header.
 	 *
 	 * Must read HID Description content through out,
 	 * otherwise Gen5 trackpad cannot response next command
@@ -1654,8 +1654,8 @@ static int cyapa_gen5_set_power_mode(struct cyapa *cyapa,
 		 * that trackpad unable to report signal to wake system up
 		 * in the special situation that system is in suspending, and
 		 * at the same time, user touch trackpad to wake system up.
-		 * This function can avoid the data to be buffured when system
-		 * is suspending which may cause interrput line unable to be
+		 * This function can avoid the data to be buffered when system
+		 * is suspending which may cause interrupt line unable to be
 		 * asserted again.
 		 */
 		cyapa_empty_pip_output_data(cyapa, NULL, NULL, NULL);
@@ -2546,16 +2546,11 @@ static bool cyapa_gen5_irq_cmd_handler(struct cyapa *cyapa)
 			gen5_pip->resp_sort_func(cyapa,
 				gen5_pip->irq_cmd_buf, length))) {
 			/*
-			 * Cover the Gen5 V1 firmware issue.
-			 * The issue is there is no interrut will be
-			 * asserted to notityf host to read a command
-			 * data out when always has finger touch on
-			 * trackpad during the command is issued to
-			 * trackad device.
-			 * This issue has the scenario is that,
-			 * user always has his fingers touched on
-			 * trackpad device when booting/rebooting
-			 * their chrome book.
+			 * Work around the Gen5 V1 firmware
+			 * that does not assert interrupt signalling
+			 * that command response is ready if user
+			 * keeps touching the trackpad while command
+			 * is sent to the device.
 			 */
 			length = 0;
 			if (gen5_pip->resp_len)
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index 6d5f8a4c1748..73670f2aebfd 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -28,14 +28,13 @@
 #define ETP_PRESSURE_OFFSET	25
 
 /* IAP Firmware handling */
-#define ETP_FW_NAME		"elan_i2c.bin"
+#define ETP_PRODUCT_ID_FORMAT_STRING	"%d.0"
+#define ETP_FW_NAME		"elan_i2c_" ETP_PRODUCT_ID_FORMAT_STRING ".bin"
 #define ETP_IAP_START_ADDR	0x0083
 #define ETP_FW_IAP_PAGE_ERR	(1 << 5)
 #define ETP_FW_IAP_INTF_ERR	(1 << 4)
 #define ETP_FW_PAGE_SIZE	64
-#define ETP_FW_VAILDPAGE_COUNT	768
 #define ETP_FW_SIGNATURE_SIZE	6
-#define ETP_FW_SIGNATURE_ADDRESS	0xBFFA
 
 struct i2c_client;
 struct completion;
@@ -58,7 +57,8 @@ struct elan_transport_ops {
 				 bool max_baseliune, u8 *value);
 
 	int (*get_version)(struct i2c_client *client, bool iap, u8 *version);
-	int (*get_sm_version)(struct i2c_client *client, u8 *version);
+	int (*get_sm_version)(struct i2c_client *client,
+			      u8* ic_type, u8 *version);
 	int (*get_checksum)(struct i2c_client *client, bool iap, u16 *csum);
 	int (*get_product_id)(struct i2c_client *client, u8 *id);
 
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index fd5068b2542d..62641f2adaf7 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2013 ELAN Microelectronics Corp.
  *
  * Author: 林政維 (Duson Lin) <dusonlin@emc.com.tw>
- * Version: 1.5.7
+ * Version: 1.5.9
  *
  * Based on cyapa driver:
  * copyright (c) 2011-2012 Cypress Semiconductor, Inc.
@@ -40,7 +40,7 @@
 #include "elan_i2c.h"
 
 #define DRIVER_NAME		"elan_i2c"
-#define ELAN_DRIVER_VERSION	"1.5.7"
+#define ELAN_DRIVER_VERSION	"1.5.9"
 #define ETP_MAX_PRESSURE	255
 #define ETP_FWIDTH_REDUCE	90
 #define ETP_FINGER_WIDTH	15
@@ -83,6 +83,9 @@ struct elan_tp_data {
 	u16			fw_checksum;
 	int			pressure_adjustment;
 	u8			mode;
+	u8			ic_type;
+	u16			fw_vaildpage_count;
+	u16			fw_signature_address;
 
 	bool			irq_wake;
 
@@ -91,6 +94,29 @@ struct elan_tp_data {
 	bool			baseline_ready;
 };
 
+static int elan_get_fwinfo(u8 ic_type, u16 *vaildpage_count,
+			   u16 *signature_address)
+{
+	switch(ic_type) {
+	case 0x09:
+		*vaildpage_count = 768;
+		break;
+	case 0x0D:
+		*vaildpage_count = 896;
+		break;
+	default:
+		/* unknown ic type clear value */
+		*vaildpage_count = 0;
+		*signature_address = 0;
+		return -ENXIO;
+	}
+
+	*signature_address =
+		(*vaildpage_count * ETP_FW_PAGE_SIZE) - ETP_FW_SIGNATURE_SIZE;
+
+	return 0;
+}
+
 static int elan_enable_power(struct elan_tp_data *data)
 {
 	int repeat = ETP_RETRY_COUNT;
@@ -221,7 +247,8 @@ static int elan_query_device_info(struct elan_tp_data *data)
 	if (error)
 		return error;
 
-	error = data->ops->get_sm_version(data->client, &data->sm_version);
+	error = data->ops->get_sm_version(data->client, &data->ic_type,
+					  &data->sm_version);
 	if (error)
 		return error;
 
@@ -234,6 +261,14 @@ static int elan_query_device_info(struct elan_tp_data *data)
 	if (error)
 		return error;
 
+	error = elan_get_fwinfo(data->ic_type, &data->fw_vaildpage_count,
+				&data->fw_signature_address);
+	if (error) {
+		dev_err(&data->client->dev,
+			"unknown ic type %d\n", data->ic_type);
+		return error;
+	}
+
 	return 0;
 }
 
@@ -318,7 +353,7 @@ static int __elan_update_firmware(struct elan_tp_data *data,
 	iap_start_addr = get_unaligned_le16(&fw->data[ETP_IAP_START_ADDR * 2]);
 
 	boot_page_count = (iap_start_addr * 2) / ETP_FW_PAGE_SIZE;
-	for (i = boot_page_count; i < ETP_FW_VAILDPAGE_COUNT; i++) {
+	for (i = boot_page_count; i < data->fw_vaildpage_count; i++) {
 		u16 checksum = 0;
 		const u8 *page = &fw->data[i * ETP_FW_PAGE_SIZE];
 
@@ -403,7 +438,8 @@ static ssize_t elan_sysfs_read_product_id(struct device *dev,
 	struct i2c_client *client = to_i2c_client(dev);
 	struct elan_tp_data *data = i2c_get_clientdata(client);
 
-	return sprintf(buf, "%d.0\n", data->product_id);
+	return sprintf(buf, ETP_PRODUCT_ID_FORMAT_STRING "\n",
+		       data->product_id);
 }
 
 static ssize_t elan_sysfs_read_fw_ver(struct device *dev,
@@ -442,19 +478,28 @@ static ssize_t elan_sysfs_update_fw(struct device *dev,
 {
 	struct elan_tp_data *data = dev_get_drvdata(dev);
 	const struct firmware *fw;
+	char *fw_name;
 	int error;
 	const u8 *fw_signature;
 	static const u8 signature[] = {0xAA, 0x55, 0xCC, 0x33, 0xFF, 0xFF};
 
-	error = request_firmware(&fw, ETP_FW_NAME, dev);
+	/* Look for a firmware with the product id appended. */
+	fw_name = kasprintf(GFP_KERNEL, ETP_FW_NAME, data->product_id);
+	if (!fw_name) {
+		dev_err(dev, "failed to allocate memory for firmware name\n");
+		return -ENOMEM;
+	}
+
+	dev_info(dev, "requesting fw '%s'\n", fw_name);
+	error = request_firmware(&fw, fw_name, dev);
+	kfree(fw_name);
 	if (error) {
-		dev_err(dev, "cannot load firmware %s: %d\n",
-			ETP_FW_NAME, error);
+		dev_err(dev, "failed to request firmware: %d\n", error);
 		return error;
 	}
 
 	/* Firmware file must match signature data */
-	fw_signature = &fw->data[ETP_FW_SIGNATURE_ADDRESS];
+	fw_signature = &fw->data[data->fw_signature_address];
 	if (memcmp(fw_signature, signature, sizeof(signature)) != 0) {
 		dev_err(dev, "signature mismatch (expected %*ph, got %*ph)\n",
 			(int)sizeof(signature), signature,
diff --git a/drivers/input/mouse/elan_i2c_i2c.c b/drivers/input/mouse/elan_i2c_i2c.c
index a0acbbf83bfd..683c840c9dd7 100644
--- a/drivers/input/mouse/elan_i2c_i2c.c
+++ b/drivers/input/mouse/elan_i2c_i2c.c
@@ -259,7 +259,8 @@ static int elan_i2c_get_version(struct i2c_client *client,
 	return 0;
 }
 
-static int elan_i2c_get_sm_version(struct i2c_client *client, u8 *version)
+static int elan_i2c_get_sm_version(struct i2c_client *client,
+				   u8 *ic_type, u8 *version)
 {
 	int error;
 	u8 val[3];
@@ -271,6 +272,7 @@ static int elan_i2c_get_sm_version(struct i2c_client *client, u8 *version)
 	}
 
 	*version = val[0];
+	*ic_type = val[1];
 	return 0;
 }
 
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 30ab80dbcdd6..ff36a366b2aa 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -165,7 +165,8 @@ static int elan_smbus_get_version(struct i2c_client *client,
 	return 0;
 }
 
-static int elan_smbus_get_sm_version(struct i2c_client *client, u8 *version)
+static int elan_smbus_get_sm_version(struct i2c_client *client,
+				     u8 *ic_type, u8 *version)
 {
 	int error;
 	u8 val[3];
@@ -177,7 +178,8 @@ static int elan_smbus_get_sm_version(struct i2c_client *client, u8 *version)
 		return error;
 	}
 
-	*version = val[0]; /* XXX Why 0 and not 2 as in IAP/FW versions? */
+	*version = val[0];
+	*ic_type = val[1];
 	return 0;
 }
 
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 991dc6b20a58..ce3d40004458 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -315,7 +315,7 @@ static void elantech_report_semi_mt_data(struct input_dev *dev,
 					 unsigned int x2, unsigned int y2)
 {
 	elantech_set_slot(dev, 0, num_fingers != 0, x1, y1);
-	elantech_set_slot(dev, 1, num_fingers == 2, x2, y2);
+	elantech_set_slot(dev, 1, num_fingers >= 2, x2, y2);
 }
 
 /*
@@ -1376,10 +1376,11 @@ static bool elantech_is_signature_valid(const unsigned char *param)
 		return true;
 
 	/*
-	 * Some models have a revision higher then 20. Meaning param[2] may
-	 * be 10 or 20, skip the rates check for these.
+	 * Some hw_version >= 4 models have a revision higher then 20. Meaning
+	 * that param[2] may be 10 or 20, skip the rates check for these.
 	 */
-	if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+	if ((param[0] & 0x0f) >= 0x06 && (param[1] & 0xaf) == 0x0f &&
+	    param[2] < 40)
 		return true;
 
 	for (i = 0; i < ARRAY_SIZE(rates); i++)
@@ -1555,6 +1556,7 @@ static int elantech_set_properties(struct elantech_data *etd)
 		case 9:
 		case 10:
 		case 13:
+		case 14:
 			etd->hw_version = 4;
 			break;
 		default:
diff --git a/drivers/input/mouse/focaltech.c b/drivers/input/mouse/focaltech.c
index 23d259416f2f..4d5576de81be 100644
--- a/drivers/input/mouse/focaltech.c
+++ b/drivers/input/mouse/focaltech.c
@@ -103,6 +103,16 @@ struct focaltech_hw_state {
 	 */
 	struct focaltech_finger_state fingers[FOC_MAX_FINGERS];
 
+	/*
+	 * Finger width 0-7 and 15 for a very big contact area.
+	 * 15 value stays until the finger is released.
+	 * Width is reported only in absolute packets.
+	 * Since hardware reports width only for last touching finger,
+	 * there is no need to store width for every specific finger,
+	 * so we keep only last value reported.
+	 */
+	unsigned int width;
+
 	/* True if the clickpad has been pressed. */
 	bool pressed;
 };
@@ -137,6 +147,7 @@ static void focaltech_report_state(struct psmouse *psmouse)
 			input_report_abs(dev, ABS_MT_POSITION_X, clamped_x);
 			input_report_abs(dev, ABS_MT_POSITION_Y,
 					 priv->y_max - clamped_y);
+			input_report_abs(dev, ABS_TOOL_WIDTH, state->width);
 		}
 	}
 	input_mt_report_pointer_emulation(dev, true);
@@ -187,6 +198,7 @@ static void focaltech_process_abs_packet(struct psmouse *psmouse,
 
 	state->fingers[finger].x = ((packet[1] & 0xf) << 8) | packet[2];
 	state->fingers[finger].y = (packet[3] << 8) | packet[4];
+	state->width = packet[5] >> 4;
 	state->fingers[finger].valid = true;
 }
 
@@ -331,6 +343,7 @@ static void focaltech_set_input_params(struct psmouse *psmouse)
 	__set_bit(EV_ABS, dev->evbit);
 	input_set_abs_params(dev, ABS_MT_POSITION_X, 0, priv->x_max, 0, 0);
 	input_set_abs_params(dev, ABS_MT_POSITION_Y, 0, priv->y_max, 0, 0);
+	input_set_abs_params(dev, ABS_TOOL_WIDTH, 0, 15, 0, 0);
 	input_mt_init_slots(dev, 5, INPUT_MT_POINTER);
 	__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
 }
diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index 5bb1658f60c7..7c4ba43d253e 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -63,7 +63,7 @@ static unsigned int psmouse_rate = 100;
 module_param_named(rate, psmouse_rate, uint, 0644);
 MODULE_PARM_DESC(rate, "Report rate, in reports per second.");
 
-static bool psmouse_smartscroll = 1;
+static bool psmouse_smartscroll = true;
 module_param_named(smartscroll, psmouse_smartscroll, bool, 0644);
 MODULE_PARM_DESC(smartscroll, "Logitech Smartscroll autorepeat, 1 = enabled (default), 0 = disabled.");
 
diff --git a/drivers/input/mouse/sentelic.h b/drivers/input/mouse/sentelic.h
index aa697ece405b..42df9e3beae8 100644
--- a/drivers/input/mouse/sentelic.h
+++ b/drivers/input/mouse/sentelic.h
@@ -123,11 +123,11 @@ struct fsp_data {
 extern int fsp_detect(struct psmouse *psmouse, bool set_properties);
 extern int fsp_init(struct psmouse *psmouse);
 #else
-inline int fsp_detect(struct psmouse *psmouse, bool set_properties)
+static inline int fsp_detect(struct psmouse *psmouse, bool set_properties)
 {
 	return -ENOSYS;
 }
-inline int fsp_init(struct psmouse *psmouse)
+static inline int fsp_init(struct psmouse *psmouse)
 {
 	return -ENOSYS;
 }
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 630af73e98c4..35c8d0ceabee 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -151,6 +151,11 @@ static const struct min_max_quirk min_max_pnpid_table[] = {
 		1024, 5112, 2024, 4832
 	},
 	{
+		(const char * const []){"LEN2000", NULL},
+		{ANY_BOARD_ID, ANY_BOARD_ID},
+		1024, 5113, 2021, 4832
+	},
+	{
 		(const char * const []){"LEN2001", NULL},
 		{ANY_BOARD_ID, ANY_BOARD_ID},
 		1024, 5022, 2508, 4832
@@ -191,7 +196,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0045",
 	"LEN0047",
 	"LEN0049",
-	"LEN2000",
+	"LEN2000", /* S540 */
 	"LEN2001", /* Edge E431 */
 	"LEN2002", /* Edge E531 */
 	"LEN2003",
diff --git a/drivers/input/mouse/synaptics_i2c.c b/drivers/input/mouse/synaptics_i2c.c
index 878f18498f3b..ffceedcaf3c8 100644
--- a/drivers/input/mouse/synaptics_i2c.c
+++ b/drivers/input/mouse/synaptics_i2c.c
@@ -185,7 +185,7 @@
 #define NO_DATA_SLEEP_MSECS	(MSEC_PER_SEC / 4)
 
 /* Control touchpad's No Deceleration option */
-static bool no_decel = 1;
+static bool no_decel = true;
 module_param(no_decel, bool, 0644);
 MODULE_PARM_DESC(no_decel, "No Deceleration. Default = 1 (on)");
 
@@ -340,9 +340,9 @@ static bool synaptics_i2c_get_input(struct synaptics_i2c *touch)
 	s32 data;
 	s8 x_delta, y_delta;
 
-	/* Deal with spontanious resets and errors */
+	/* Deal with spontaneous resets and errors */
 	if (synaptics_i2c_check_error(touch->client))
-		return 0;
+		return false;
 
 	/* Get Gesture Bit */
 	data = synaptics_i2c_reg_get(touch->client, DATA_REG0);
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 80f6386709bf..7afa6a2b776c 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -958,6 +958,7 @@ config TOUCHSCREEN_ST1232
 config TOUCHSCREEN_STMPE
 	tristate "STMicroelectronics STMPE touchscreens"
 	depends on MFD_STMPE
+	depends on (OF || COMPILE_TEST)
 	help
 	  Say Y here if you want support for STMicroelectronics
 	  STMPE touchscreen controllers.
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 40b98dda8f38..dfc7309e3d38 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -726,15 +726,15 @@ static void mxt_input_button(struct mxt_data *data, u8 *message)
 {
 	struct input_dev *input = data->input_dev;
 	const struct mxt_platform_data *pdata = data->pdata;
-	bool button;
 	int i;
 
-	/* Active-low switch */
 	for (i = 0; i < pdata->t19_num_keys; i++) {
 		if (pdata->t19_keymap[i] == KEY_RESERVED)
 			continue;
-		button = !(message[1] & (1 << i));
-		input_report_key(input, pdata->t19_keymap[i], button);
+
+		/* Active-low switch */
+		input_report_key(input, pdata->t19_keymap[i],
+				 !(message[1] & BIT(i)));
 	}
 }
 
diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c
index 568a3d340c8a..5ed31057430c 100644
--- a/drivers/input/touchscreen/cyttsp4_core.c
+++ b/drivers/input/touchscreen/cyttsp4_core.c
@@ -775,7 +775,6 @@ static void cyttsp4_get_touch(struct cyttsp4_mt_data *md,
 	struct device *dev = &md->input->dev;
 	struct cyttsp4_sysinfo *si = md->si;
 	enum cyttsp4_tch_abs abs;
-	int tmp;
 	bool flipped;
 
 	for (abs = CY_TCH_X; abs < CY_TCH_NUM_ABS; abs++) {
@@ -790,9 +789,7 @@ static void cyttsp4_get_touch(struct cyttsp4_mt_data *md,
 	}
 
 	if (md->pdata->flags & CY_FLAG_FLIP) {
-		tmp = touch->abs[CY_TCH_X];
-		touch->abs[CY_TCH_X] = touch->abs[CY_TCH_Y];
-		touch->abs[CY_TCH_Y] = tmp;
+		swap(touch->abs[CY_TCH_X], touch->abs[CY_TCH_Y]);
 		flipped = true;
 	} else
 		flipped = false;
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 3af16984d57c..b4d12e29abff 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -47,7 +47,7 @@ struct goodix_ts_data {
 /* Register defines */
 #define GOODIX_READ_COOR_ADDR		0x814E
 #define GOODIX_REG_CONFIG_DATA		0x8047
-#define GOODIX_REG_VERSION		0x8140
+#define GOODIX_REG_ID			0x8140
 
 #define RESOLUTION_LOC		1
 #define MAX_CONTACTS_LOC	5
@@ -69,7 +69,7 @@ static const unsigned long goodix_irq_flags[] = {
  * @len: length of the buffer to write
  */
 static int goodix_i2c_read(struct i2c_client *client,
-				u16 reg, u8 *buf, int len)
+			   u16 reg, u8 *buf, int len)
 {
 	struct i2c_msg msgs[2];
 	u16 wbuf = cpu_to_be16(reg);
@@ -78,7 +78,7 @@ static int goodix_i2c_read(struct i2c_client *client,
 	msgs[0].flags = 0;
 	msgs[0].addr  = client->addr;
 	msgs[0].len   = 2;
-	msgs[0].buf   = (u8 *) &wbuf;
+	msgs[0].buf   = (u8 *)&wbuf;
 
 	msgs[1].flags = I2C_M_RD;
 	msgs[1].addr  = client->addr;
@@ -101,6 +101,9 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 		return error;
 	}
 
+	if (!(data[0] & 0x80))
+		return -EAGAIN;
+
 	touch_num = data[0] & 0x0f;
 	if (touch_num > ts->max_touch_num)
 		return -EPROTO;
@@ -144,7 +147,7 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
  */
 static void goodix_process_events(struct goodix_ts_data *ts)
 {
-	u8  point_data[1 + GOODIX_CONTACT_SIZE * ts->max_touch_num];
+	u8  point_data[1 + GOODIX_CONTACT_SIZE * GOODIX_MAX_CONTACTS];
 	int touch_num;
 	int i;
 
@@ -196,8 +199,8 @@ static void goodix_read_config(struct goodix_ts_data *ts)
 	int error;
 
 	error = goodix_i2c_read(ts->client, GOODIX_REG_CONFIG_DATA,
-			      config,
-			   GOODIX_CONFIG_MAX_LENGTH);
+				config,
+				GOODIX_CONFIG_MAX_LENGTH);
 	if (error) {
 		dev_warn(&ts->client->dev,
 			 "Error reading config (%d), using defaults\n",
@@ -227,22 +230,28 @@ static void goodix_read_config(struct goodix_ts_data *ts)
  *
  * @client: the i2c client
  * @version: output buffer containing the version on success
+ * @id: output buffer containing the id on success
  */
-static int goodix_read_version(struct i2c_client *client, u16 *version)
+static int goodix_read_version(struct i2c_client *client, u16 *version, u16 *id)
 {
 	int error;
 	u8 buf[6];
+	char id_str[5];
 
-	error = goodix_i2c_read(client, GOODIX_REG_VERSION, buf, sizeof(buf));
+	error = goodix_i2c_read(client, GOODIX_REG_ID, buf, sizeof(buf));
 	if (error) {
 		dev_err(&client->dev, "read version failed: %d\n", error);
 		return error;
 	}
 
-	if (version)
-		*version = get_unaligned_le16(&buf[4]);
+	memcpy(id_str, buf, 4);
+	id_str[4] = 0;
+	if (kstrtou16(id_str, 10, id))
+		*id = 0x1001;
+
+	*version = get_unaligned_le16(&buf[4]);
 
-	dev_info(&client->dev, "IC VERSION: %6ph\n", buf);
+	dev_info(&client->dev, "ID %d, version: %04x\n", *id, *version);
 
 	return 0;
 }
@@ -276,10 +285,13 @@ static int goodix_i2c_test(struct i2c_client *client)
  * goodix_request_input_dev - Allocate, populate and register the input device
  *
  * @ts: our goodix_ts_data pointer
+ * @version: device firmware version
+ * @id: device ID
  *
  * Must be called during probe
  */
-static int goodix_request_input_dev(struct goodix_ts_data *ts)
+static int goodix_request_input_dev(struct goodix_ts_data *ts, u16 version,
+				    u16 id)
 {
 	int error;
 
@@ -289,14 +301,10 @@ static int goodix_request_input_dev(struct goodix_ts_data *ts)
 		return -ENOMEM;
 	}
 
-	ts->input_dev->evbit[0] = BIT_MASK(EV_SYN) |
-				  BIT_MASK(EV_KEY) |
-				  BIT_MASK(EV_ABS);
-
-	input_set_abs_params(ts->input_dev, ABS_MT_POSITION_X, 0,
-				ts->abs_x_max, 0, 0);
-	input_set_abs_params(ts->input_dev, ABS_MT_POSITION_Y, 0,
-				ts->abs_y_max, 0, 0);
+	input_set_abs_params(ts->input_dev, ABS_MT_POSITION_X,
+			     0, ts->abs_x_max, 0, 0);
+	input_set_abs_params(ts->input_dev, ABS_MT_POSITION_Y,
+			     0, ts->abs_y_max, 0, 0);
 	input_set_abs_params(ts->input_dev, ABS_MT_WIDTH_MAJOR, 0, 255, 0, 0);
 	input_set_abs_params(ts->input_dev, ABS_MT_TOUCH_MAJOR, 0, 255, 0, 0);
 
@@ -307,8 +315,8 @@ static int goodix_request_input_dev(struct goodix_ts_data *ts)
 	ts->input_dev->phys = "input/ts";
 	ts->input_dev->id.bustype = BUS_I2C;
 	ts->input_dev->id.vendor = 0x0416;
-	ts->input_dev->id.product = 0x1001;
-	ts->input_dev->id.version = 10427;
+	ts->input_dev->id.product = id;
+	ts->input_dev->id.version = version;
 
 	error = input_register_device(ts->input_dev);
 	if (error) {
@@ -326,7 +334,7 @@ static int goodix_ts_probe(struct i2c_client *client,
 	struct goodix_ts_data *ts;
 	unsigned long irq_flags;
 	int error;
-	u16 version_info;
+	u16 version_info, id_info;
 
 	dev_dbg(&client->dev, "I2C Address: 0x%02x\n", client->addr);
 
@@ -348,7 +356,7 @@ static int goodix_ts_probe(struct i2c_client *client,
 		return error;
 	}
 
-	error = goodix_read_version(client, &version_info);
+	error = goodix_read_version(client, &version_info, &id_info);
 	if (error) {
 		dev_err(&client->dev, "Read version failed.\n");
 		return error;
@@ -356,7 +364,7 @@ static int goodix_ts_probe(struct i2c_client *client,
 
 	goodix_read_config(ts);
 
-	error = goodix_request_input_dev(ts);
+	error = goodix_request_input_dev(ts, version_info, id_info);
 	if (error)
 		return error;
 
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 2c2107147319..8f3e243a62bf 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -78,7 +78,7 @@ static void pixcir_ts_parse(struct pixcir_i2c_ts_data *tsdata,
 	}
 
 	ret = i2c_master_recv(tsdata->client, rdbuf, readsize);
-	if (ret != sizeof(rdbuf)) {
+	if (ret != readsize) {
 		dev_err(&tsdata->client->dev,
 			"%s: i2c_master_recv failed(), ret=%d\n",
 			__func__, ret);
diff --git a/drivers/input/touchscreen/s3c2410_ts.c b/drivers/input/touchscreen/s3c2410_ts.c
index bdfa27dc097b..a4a103e1d11b 100644
--- a/drivers/input/touchscreen/s3c2410_ts.c
+++ b/drivers/input/touchscreen/s3c2410_ts.c
@@ -411,7 +411,7 @@ static const struct dev_pm_ops s3c_ts_pmops = {
 };
 #endif
 
-static struct platform_device_id s3cts_driver_ids[] = {
+static const struct platform_device_id s3cts_driver_ids[] = {
 	{ "s3c2410-ts", 0 },
 	{ "s3c2440-ts", 0 },
 	{ "s3c64xx-ts", FEAT_PEN_IRQ },
diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c
index 2d5ff86b343f..e414d43e5159 100644
--- a/drivers/input/touchscreen/stmpe-ts.c
+++ b/drivers/input/touchscreen/stmpe-ts.c
@@ -164,7 +164,7 @@ static irqreturn_t stmpe_ts_handler(int irq, void *data)
 			STMPE_TSC_CTRL_TSC_EN, STMPE_TSC_CTRL_TSC_EN);
 
 	/* start polling for touch_det to detect release */
-	schedule_delayed_work(&ts->work, HZ / 50);
+	schedule_delayed_work(&ts->work, msecs_to_jiffies(50));
 
 	return IRQ_HANDLED;
 }
@@ -267,27 +267,10 @@ static void stmpe_ts_close(struct input_dev *dev)
 static void stmpe_ts_get_platform_info(struct platform_device *pdev,
 					struct stmpe_touch *ts)
 {
-	struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent);
 	struct device_node *np = pdev->dev.of_node;
-	struct stmpe_ts_platform_data *ts_pdata = NULL;
-
-	ts->stmpe = stmpe;
-
-	if (stmpe->pdata && stmpe->pdata->ts) {
-		ts_pdata = stmpe->pdata->ts;
-
-		ts->sample_time = ts_pdata->sample_time;
-		ts->mod_12b = ts_pdata->mod_12b;
-		ts->ref_sel = ts_pdata->ref_sel;
-		ts->adc_freq = ts_pdata->adc_freq;
-		ts->ave_ctrl = ts_pdata->ave_ctrl;
-		ts->touch_det_delay = ts_pdata->touch_det_delay;
-		ts->settling = ts_pdata->settling;
-		ts->fraction_z = ts_pdata->fraction_z;
-		ts->i_drive = ts_pdata->i_drive;
-	} else if (np) {
-		u32 val;
+	u32 val;
 
+	if (np) {
 		if (!of_property_read_u32(np, "st,sample-time", &val))
 			ts->sample_time = val;
 		if (!of_property_read_u32(np, "st,mod-12b", &val))
@@ -311,6 +294,7 @@ static void stmpe_ts_get_platform_info(struct platform_device *pdev,
 
 static int stmpe_input_probe(struct platform_device *pdev)
 {
+	struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent);
 	struct stmpe_touch *ts;
 	struct input_dev *idev;
 	int error;
@@ -329,6 +313,7 @@ static int stmpe_input_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, ts);
+	ts->stmpe = stmpe;
 	ts->idev = idev;
 	ts->dev = &pdev->dev;
 
@@ -351,14 +336,13 @@ static int stmpe_input_probe(struct platform_device *pdev)
 	idev->name = STMPE_TS_NAME;
 	idev->phys = STMPE_TS_NAME"/input0";
 	idev->id.bustype = BUS_I2C;
-	idev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-	idev->keybit[BIT_WORD(BTN_TOUCH)] = BIT_MASK(BTN_TOUCH);
 
 	idev->open = stmpe_ts_open;
 	idev->close = stmpe_ts_close;
 
 	input_set_drvdata(idev, ts);
 
+	input_set_capability(idev, EV_KEY, BTN_TOUCH);
 	input_set_abs_params(idev, ABS_X, 0, XY_MASK, 0, 0);
 	input_set_abs_params(idev, ABS_Y, 0, XY_MASK, 0, 0);
 	input_set_abs_params(idev, ABS_PRESSURE, 0x0, 0xff, 0, 0);
@@ -383,14 +367,19 @@ static int stmpe_ts_remove(struct platform_device *pdev)
 
 static struct platform_driver stmpe_ts_driver = {
 	.driver = {
-		   .name = STMPE_TS_NAME,
-		   },
+		.name = STMPE_TS_NAME,
+	},
 	.probe = stmpe_input_probe,
 	.remove = stmpe_ts_remove,
 };
 module_platform_driver(stmpe_ts_driver);
 
+static const struct of_device_id stmpe_ts_ids[] = {
+	{ .compatible = "st,stmpe-ts", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, stmpe_ts_ids);
+
 MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>");
 MODULE_DESCRIPTION("STMPEXXX touchscreen driver");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" STMPE_TS_NAME);
diff --git a/drivers/input/touchscreen/sx8654.c b/drivers/input/touchscreen/sx8654.c
index aecb9ad2e701..642f4a53de50 100644
--- a/drivers/input/touchscreen/sx8654.c
+++ b/drivers/input/touchscreen/sx8654.c
@@ -187,7 +187,7 @@ static int sx8654_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	input = devm_input_allocate_device(&client->dev);
-	if (!sx8654)
+	if (!input)
 		return -ENOMEM;
 
 	input->name = "SX8654 I2C Touchscreen";
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 19880c7385e3..f58a196521a9 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -30,7 +30,6 @@
 #include <linux/input/mt.h>
 #include <linux/platform_data/zforce_ts.h>
 #include <linux/regulator/consumer.h>
-#include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 1ae4e547b419..40f37a2b4a8a 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -339,6 +339,7 @@ config SPAPR_TCE_IOMMU
 	  Enables bits of IOMMU API required by VFIO. The iommu_ops
 	  is not implemented as it is not necessary for VFIO.
 
+# ARM IOMMU support
 config ARM_SMMU
 	bool "ARM Ltd. System MMU (SMMU) Support"
 	depends on (ARM64 || ARM) && MMU
@@ -352,4 +353,16 @@ config ARM_SMMU
 	  Say Y here if your SoC includes an IOMMU device implementing
 	  the ARM SMMU architecture.
 
+config ARM_SMMU_V3
+	bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
+	depends on ARM64 && PCI
+	select IOMMU_API
+	select IOMMU_IO_PGTABLE_LPAE
+	help
+	  Support for implementations of the ARM System MMU architecture
+	  version 3 providing translation support to a PCIe root complex.
+
+	  Say Y here if your system includes an IOMMU device implementing
+	  the ARM SMMUv3 architecture.
+
 endif # IOMMU_SUPPORT
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 080ffab4ed1c..c6dcc513d711 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
+obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index e43d48956dea..d3e5e9abe3b6 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -34,6 +34,7 @@
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/dma-contiguous.h>
+#include <linux/irqdomain.h>
 #include <asm/irq_remapping.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
@@ -64,10 +65,6 @@
 
 static DEFINE_RWLOCK(amd_iommu_devtable_lock);
 
-/* A list of preallocated protection domains */
-static LIST_HEAD(iommu_pd_list);
-static DEFINE_SPINLOCK(iommu_pd_list_lock);
-
 /* List of all available dev_data structures */
 static LIST_HEAD(dev_data_list);
 static DEFINE_SPINLOCK(dev_data_list_lock);
@@ -119,7 +116,7 @@ struct iommu_cmd {
 struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
-static int __init alloc_passthrough_domain(void);
+static int alloc_passthrough_domain(void);
 
 /****************************************************************************
  *
@@ -234,31 +231,38 @@ static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum)
 }
 
 /*
- * In this function the list of preallocated protection domains is traversed to
- * find the domain for a specific device
+ * This function actually applies the mapping to the page table of the
+ * dma_ops domain.
  */
-static struct dma_ops_domain *find_protection_domain(u16 devid)
+static void alloc_unity_mapping(struct dma_ops_domain *dma_dom,
+				struct unity_map_entry *e)
 {
-	struct dma_ops_domain *entry, *ret = NULL;
-	unsigned long flags;
-	u16 alias = amd_iommu_alias_table[devid];
-
-	if (list_empty(&iommu_pd_list))
-		return NULL;
-
-	spin_lock_irqsave(&iommu_pd_list_lock, flags);
+	u64 addr;
 
-	list_for_each_entry(entry, &iommu_pd_list, list) {
-		if (entry->target_dev == devid ||
-		    entry->target_dev == alias) {
-			ret = entry;
-			break;
-		}
+	for (addr = e->address_start; addr < e->address_end;
+	     addr += PAGE_SIZE) {
+		if (addr < dma_dom->aperture_size)
+			__set_bit(addr >> PAGE_SHIFT,
+				  dma_dom->aperture[0]->bitmap);
 	}
+}
+
+/*
+ * Inits the unity mappings required for a specific device
+ */
+static void init_unity_mappings_for_device(struct device *dev,
+					   struct dma_ops_domain *dma_dom)
+{
+	struct unity_map_entry *e;
+	u16 devid;
 
-	spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
+	devid = get_device_id(dev);
 
-	return ret;
+	list_for_each_entry(e, &amd_iommu_unity_map, list) {
+		if (!(devid >= e->devid_start && devid <= e->devid_end))
+			continue;
+		alloc_unity_mapping(dma_dom, e);
+	}
 }
 
 /*
@@ -290,11 +294,23 @@ static bool check_device(struct device *dev)
 
 static void init_iommu_group(struct device *dev)
 {
+	struct dma_ops_domain *dma_domain;
+	struct iommu_domain *domain;
 	struct iommu_group *group;
 
 	group = iommu_group_get_for_dev(dev);
-	if (!IS_ERR(group))
-		iommu_group_put(group);
+	if (IS_ERR(group))
+		return;
+
+	domain = iommu_group_default_domain(group);
+	if (!domain)
+		goto out;
+
+	dma_domain = to_pdomain(domain)->priv;
+
+	init_unity_mappings_for_device(dev, dma_domain);
+out:
+	iommu_group_put(group);
 }
 
 static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -434,64 +450,15 @@ static void iommu_uninit_device(struct device *dev)
 	/* Unlink from alias, it may change if another device is re-plugged */
 	dev_data->alias_data = NULL;
 
+	/* Remove dma-ops */
+	dev->archdata.dma_ops = NULL;
+
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
 	 */
 }
 
-void __init amd_iommu_uninit_devices(void)
-{
-	struct iommu_dev_data *dev_data, *n;
-	struct pci_dev *pdev = NULL;
-
-	for_each_pci_dev(pdev) {
-
-		if (!check_device(&pdev->dev))
-			continue;
-
-		iommu_uninit_device(&pdev->dev);
-	}
-
-	/* Free all of our dev_data structures */
-	list_for_each_entry_safe(dev_data, n, &dev_data_list, dev_data_list)
-		free_dev_data(dev_data);
-}
-
-int __init amd_iommu_init_devices(void)
-{
-	struct pci_dev *pdev = NULL;
-	int ret = 0;
-
-	for_each_pci_dev(pdev) {
-
-		if (!check_device(&pdev->dev))
-			continue;
-
-		ret = iommu_init_device(&pdev->dev);
-		if (ret == -ENOTSUPP)
-			iommu_ignore_device(&pdev->dev);
-		else if (ret)
-			goto out_free;
-	}
-
-	/*
-	 * Initialize IOMMU groups only after iommu_init_device() has
-	 * had a chance to populate any IVRS defined aliases.
-	 */
-	for_each_pci_dev(pdev) {
-		if (check_device(&pdev->dev))
-			init_iommu_group(&pdev->dev);
-	}
-
-	return 0;
-
-out_free:
-
-	amd_iommu_uninit_devices();
-
-	return ret;
-}
 #ifdef CONFIG_AMD_IOMMU_STATS
 
 /*
@@ -1463,94 +1430,6 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
 	return unmapped;
 }
 
-/*
- * This function checks if a specific unity mapping entry is needed for
- * this specific IOMMU.
- */
-static int iommu_for_unity_map(struct amd_iommu *iommu,
-			       struct unity_map_entry *entry)
-{
-	u16 bdf, i;
-
-	for (i = entry->devid_start; i <= entry->devid_end; ++i) {
-		bdf = amd_iommu_alias_table[i];
-		if (amd_iommu_rlookup_table[bdf] == iommu)
-			return 1;
-	}
-
-	return 0;
-}
-
-/*
- * This function actually applies the mapping to the page table of the
- * dma_ops domain.
- */
-static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
-			     struct unity_map_entry *e)
-{
-	u64 addr;
-	int ret;
-
-	for (addr = e->address_start; addr < e->address_end;
-	     addr += PAGE_SIZE) {
-		ret = iommu_map_page(&dma_dom->domain, addr, addr, e->prot,
-				     PAGE_SIZE);
-		if (ret)
-			return ret;
-		/*
-		 * if unity mapping is in aperture range mark the page
-		 * as allocated in the aperture
-		 */
-		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT,
-				  dma_dom->aperture[0]->bitmap);
-	}
-
-	return 0;
-}
-
-/*
- * Init the unity mappings for a specific IOMMU in the system
- *
- * Basically iterates over all unity mapping entries and applies them to
- * the default domain DMA of that IOMMU if necessary.
- */
-static int iommu_init_unity_mappings(struct amd_iommu *iommu)
-{
-	struct unity_map_entry *entry;
-	int ret;
-
-	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
-		if (!iommu_for_unity_map(iommu, entry))
-			continue;
-		ret = dma_ops_unity_map(iommu->default_dom, entry);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
- * Inits the unity mappings required for a specific device
- */
-static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
-					  u16 devid)
-{
-	struct unity_map_entry *e;
-	int ret;
-
-	list_for_each_entry(e, &amd_iommu_unity_map, list) {
-		if (!(devid >= e->devid_start && devid <= e->devid_end))
-			continue;
-		ret = dma_ops_unity_map(dma_dom, e);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 /****************************************************************************
  *
  * The next functions belong to the address allocator for the dma_ops
@@ -1704,14 +1583,16 @@ static unsigned long dma_ops_area_alloc(struct device *dev,
 	unsigned long next_bit = dom->next_address % APERTURE_RANGE_SIZE;
 	int max_index = dom->aperture_size >> APERTURE_RANGE_SHIFT;
 	int i = start >> APERTURE_RANGE_SHIFT;
-	unsigned long boundary_size;
+	unsigned long boundary_size, mask;
 	unsigned long address = -1;
 	unsigned long limit;
 
 	next_bit >>= PAGE_SHIFT;
 
-	boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-			PAGE_SIZE) >> PAGE_SHIFT;
+	mask = dma_get_seg_boundary(dev);
+
+	boundary_size = mask + 1 ? ALIGN(mask + 1, PAGE_SIZE) >> PAGE_SHIFT :
+				   1UL << (BITS_PER_LONG - PAGE_SHIFT);
 
 	for (;i < max_index; ++i) {
 		unsigned long offset = dom->aperture[i]->offset >> PAGE_SHIFT;
@@ -1869,9 +1750,15 @@ static void free_pt_##LVL (unsigned long __pt)			\
 	pt = (u64 *)__pt;					\
 								\
 	for (i = 0; i < 512; ++i) {				\
+		/* PTE present? */				\
 		if (!IOMMU_PTE_PRESENT(pt[i]))			\
 			continue;				\
 								\
+		/* Large PTE? */				\
+		if (PM_PTE_LEVEL(pt[i]) == 0 ||			\
+		    PM_PTE_LEVEL(pt[i]) == 7)			\
+			continue;				\
+								\
 		p = (unsigned long)IOMMU_PTE_PAGE(pt[i]);	\
 		FN(p);						\
 	}							\
@@ -2008,7 +1895,6 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
 		goto free_dma_dom;
 
 	dma_dom->need_flush = false;
-	dma_dom->target_dev = 0xffff;
 
 	add_domain_to_list(&dma_dom->domain);
 
@@ -2373,110 +2259,67 @@ static void detach_device(struct device *dev)
 	dev_data->ats.enabled = false;
 }
 
-/*
- * Find out the protection domain structure for a given PCI device. This
- * will give us the pointer to the page table root for example.
- */
-static struct protection_domain *domain_for_device(struct device *dev)
+static int amd_iommu_add_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
-	struct protection_domain *dom = NULL;
-	unsigned long flags;
-
-	dev_data   = get_dev_data(dev);
-
-	if (dev_data->domain)
-		return dev_data->domain;
-
-	if (dev_data->alias_data != NULL) {
-		struct iommu_dev_data *alias_data = dev_data->alias_data;
-
-		read_lock_irqsave(&amd_iommu_devtable_lock, flags);
-		if (alias_data->domain != NULL) {
-			__attach_device(dev_data, alias_data->domain);
-			dom = alias_data->domain;
-		}
-		read_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
-	}
-
-	return dom;
-}
-
-static int device_change_notifier(struct notifier_block *nb,
-				  unsigned long action, void *data)
-{
-	struct dma_ops_domain *dma_domain;
-	struct protection_domain *domain;
-	struct iommu_dev_data *dev_data;
-	struct device *dev = data;
+	struct iommu_domain *domain;
 	struct amd_iommu *iommu;
-	unsigned long flags;
 	u16 devid;
+	int ret;
 
-	if (!check_device(dev))
+	if (!check_device(dev) || get_dev_data(dev))
 		return 0;
 
-	devid    = get_device_id(dev);
-	iommu    = amd_iommu_rlookup_table[devid];
-	dev_data = get_dev_data(dev);
-
-	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
+	devid = get_device_id(dev);
+	iommu = amd_iommu_rlookup_table[devid];
 
-		iommu_init_device(dev);
-		init_iommu_group(dev);
+	ret = iommu_init_device(dev);
+	if (ret) {
+		if (ret != -ENOTSUPP)
+			pr_err("Failed to initialize device %s - trying to proceed anyway\n",
+				dev_name(dev));
 
-		/*
-		 * dev_data is still NULL and
-		 * got initialized in iommu_init_device
-		 */
-		dev_data = get_dev_data(dev);
+		iommu_ignore_device(dev);
+		dev->archdata.dma_ops = &nommu_dma_ops;
+		goto out;
+	}
+	init_iommu_group(dev);
 
-		if (iommu_pass_through || dev_data->iommu_v2) {
-			dev_data->passthrough = true;
-			attach_device(dev, pt_domain);
-			break;
-		}
+	dev_data = get_dev_data(dev);
 
-		domain = domain_for_device(dev);
+	BUG_ON(!dev_data);
 
-		/* allocate a protection domain if a device is added */
-		dma_domain = find_protection_domain(devid);
-		if (!dma_domain) {
-			dma_domain = dma_ops_domain_alloc();
-			if (!dma_domain)
-				goto out;
-			dma_domain->target_dev = devid;
-
-			spin_lock_irqsave(&iommu_pd_list_lock, flags);
-			list_add_tail(&dma_domain->list, &iommu_pd_list);
-			spin_unlock_irqrestore(&iommu_pd_list_lock, flags);
-		}
+	if (dev_data->iommu_v2)
+		iommu_request_dm_for_dev(dev);
 
+	/* Domains are initialized for this device - have a look what we ended up with */
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+		dev_data->passthrough = true;
+		dev->archdata.dma_ops = &nommu_dma_ops;
+	} else {
 		dev->archdata.dma_ops = &amd_iommu_dma_ops;
-
-		break;
-	case BUS_NOTIFY_REMOVED_DEVICE:
-
-		iommu_uninit_device(dev);
-
-	default:
-		goto out;
 	}
 
+out:
 	iommu_completion_wait(iommu);
 
-out:
 	return 0;
 }
 
-static struct notifier_block device_nb = {
-	.notifier_call = device_change_notifier,
-};
-
-void amd_iommu_init_notifier(void)
+static void amd_iommu_remove_device(struct device *dev)
 {
-	bus_register_notifier(&pci_bus_type, &device_nb);
+	struct amd_iommu *iommu;
+	u16 devid;
+
+	if (!check_device(dev))
+		return;
+
+	devid = get_device_id(dev);
+	iommu = amd_iommu_rlookup_table[devid];
+
+	iommu_uninit_device(dev);
+	iommu_completion_wait(iommu);
 }
 
 /*****************************************************************************
@@ -2495,28 +2338,20 @@ void amd_iommu_init_notifier(void)
 static struct protection_domain *get_domain(struct device *dev)
 {
 	struct protection_domain *domain;
-	struct dma_ops_domain *dma_dom;
-	u16 devid = get_device_id(dev);
+	struct iommu_domain *io_domain;
 
 	if (!check_device(dev))
 		return ERR_PTR(-EINVAL);
 
-	domain = domain_for_device(dev);
-	if (domain != NULL && !dma_ops_domain(domain))
-		return ERR_PTR(-EBUSY);
-
-	if (domain != NULL)
-		return domain;
+	io_domain = iommu_get_domain_for_dev(dev);
+	if (!io_domain)
+		return NULL;
 
-	/* Device not bound yet - bind it */
-	dma_dom = find_protection_domain(devid);
-	if (!dma_dom)
-		dma_dom = amd_iommu_rlookup_table[devid]->default_dom;
-	attach_device(dev, &dma_dom->domain);
-	DUMP_printk("Using protection domain %d for device %s\n",
-		    dma_dom->domain.id, dev_name(dev));
+	domain = to_pdomain(io_domain);
+	if (!dma_ops_domain(domain))
+		return ERR_PTR(-EBUSY);
 
-	return &dma_dom->domain;
+	return domain;
 }
 
 static void update_device_table(struct protection_domain *domain)
@@ -2930,6 +2765,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 	size	  = PAGE_ALIGN(size);
 	dma_mask  = dev->coherent_dma_mask;
 	flag     &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+	flag     |= __GFP_ZERO;
 
 	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
 	if (!page) {
@@ -3011,54 +2847,6 @@ static int amd_iommu_dma_supported(struct device *dev, u64 mask)
 	return check_device(dev);
 }
 
-/*
- * The function for pre-allocating protection domains.
- *
- * If the driver core informs the DMA layer if a driver grabs a device
- * we don't need to preallocate the protection domains anymore.
- * For now we have to.
- */
-static void __init prealloc_protection_domains(void)
-{
-	struct iommu_dev_data *dev_data;
-	struct dma_ops_domain *dma_dom;
-	struct pci_dev *dev = NULL;
-	u16 devid;
-
-	for_each_pci_dev(dev) {
-
-		/* Do we handle this device? */
-		if (!check_device(&dev->dev))
-			continue;
-
-		dev_data = get_dev_data(&dev->dev);
-		if (!amd_iommu_force_isolation && dev_data->iommu_v2) {
-			/* Make sure passthrough domain is allocated */
-			alloc_passthrough_domain();
-			dev_data->passthrough = true;
-			attach_device(&dev->dev, pt_domain);
-			pr_info("AMD-Vi: Using passthrough domain for device %s\n",
-				dev_name(&dev->dev));
-		}
-
-		/* Is there already any domain for it? */
-		if (domain_for_device(&dev->dev))
-			continue;
-
-		devid = get_device_id(&dev->dev);
-
-		dma_dom = dma_ops_domain_alloc();
-		if (!dma_dom)
-			continue;
-		init_unity_mappings_for_device(dma_dom, devid);
-		dma_dom->target_dev = devid;
-
-		attach_device(&dev->dev, &dma_dom->domain);
-
-		list_add_tail(&dma_dom->list, &iommu_pd_list);
-	}
-}
-
 static struct dma_map_ops amd_iommu_dma_ops = {
 	.alloc = alloc_coherent,
 	.free = free_coherent,
@@ -3069,76 +2857,16 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 	.dma_supported = amd_iommu_dma_supported,
 };
 
-static unsigned device_dma_ops_init(void)
+int __init amd_iommu_init_api(void)
 {
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *pdev = NULL;
-	unsigned unhandled = 0;
-
-	for_each_pci_dev(pdev) {
-		if (!check_device(&pdev->dev)) {
-
-			iommu_ignore_device(&pdev->dev);
-
-			unhandled += 1;
-			continue;
-		}
-
-		dev_data = get_dev_data(&pdev->dev);
-
-		if (!dev_data->passthrough)
-			pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
-		else
-			pdev->dev.archdata.dma_ops = &nommu_dma_ops;
-	}
-
-	return unhandled;
-}
-
-/*
- * The function which clues the AMD IOMMU driver into dma_ops.
- */
-
-void __init amd_iommu_init_api(void)
-{
-	bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
+	return bus_set_iommu(&pci_bus_type, &amd_iommu_ops);
 }
 
 int __init amd_iommu_init_dma_ops(void)
 {
-	struct amd_iommu *iommu;
-	int ret, unhandled;
-
-	/*
-	 * first allocate a default protection domain for every IOMMU we
-	 * found in the system. Devices not assigned to any other
-	 * protection domain will be assigned to the default one.
-	 */
-	for_each_iommu(iommu) {
-		iommu->default_dom = dma_ops_domain_alloc();
-		if (iommu->default_dom == NULL)
-			return -ENOMEM;
-		iommu->default_dom->domain.flags |= PD_DEFAULT_MASK;
-		ret = iommu_init_unity_mappings(iommu);
-		if (ret)
-			goto free_domains;
-	}
-
-	/*
-	 * Pre-allocate the protection domains for each device.
-	 */
-	prealloc_protection_domains();
-
 	iommu_detected = 1;
 	swiotlb = 0;
 
-	/* Make the driver finally visible to the drivers */
-	unhandled = device_dma_ops_init();
-	if (unhandled && max_pfn > MAX_DMA32_PFN) {
-		/* There are unhandled devices - initialize swiotlb for them */
-		swiotlb = 1;
-	}
-
 	amd_iommu_stats_init();
 
 	if (amd_iommu_unmap_flush)
@@ -3147,14 +2875,6 @@ int __init amd_iommu_init_dma_ops(void)
 		pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n");
 
 	return 0;
-
-free_domains:
-
-	for_each_iommu(iommu) {
-		dma_ops_domain_free(iommu->default_dom);
-	}
-
-	return ret;
 }
 
 /*****************************************************************************
@@ -3221,7 +2941,7 @@ out_err:
 	return NULL;
 }
 
-static int __init alloc_passthrough_domain(void)
+static int alloc_passthrough_domain(void)
 {
 	if (pt_domain != NULL)
 		return 0;
@@ -3239,30 +2959,46 @@ static int __init alloc_passthrough_domain(void)
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
+	struct dma_ops_domain *dma_domain;
 
-	/* We only support unmanaged domains for now */
-	if (type != IOMMU_DOMAIN_UNMANAGED)
-		return NULL;
-
-	pdomain = protection_domain_alloc();
-	if (!pdomain)
-		goto out_free;
+	switch (type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		pdomain = protection_domain_alloc();
+		if (!pdomain)
+			return NULL;
 
-	pdomain->mode    = PAGE_MODE_3_LEVEL;
-	pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!pdomain->pt_root)
-		goto out_free;
+		pdomain->mode    = PAGE_MODE_3_LEVEL;
+		pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pdomain->pt_root) {
+			protection_domain_free(pdomain);
+			return NULL;
+		}
 
-	pdomain->domain.geometry.aperture_start = 0;
-	pdomain->domain.geometry.aperture_end   = ~0ULL;
-	pdomain->domain.geometry.force_aperture = true;
+		pdomain->domain.geometry.aperture_start = 0;
+		pdomain->domain.geometry.aperture_end   = ~0ULL;
+		pdomain->domain.geometry.force_aperture = true;
 
-	return &pdomain->domain;
+		break;
+	case IOMMU_DOMAIN_DMA:
+		dma_domain = dma_ops_domain_alloc();
+		if (!dma_domain) {
+			pr_err("AMD-Vi: Failed to allocate\n");
+			return NULL;
+		}
+		pdomain = &dma_domain->domain;
+		break;
+	case IOMMU_DOMAIN_IDENTITY:
+		pdomain = protection_domain_alloc();
+		if (!pdomain)
+			return NULL;
 
-out_free:
-	protection_domain_free(pdomain);
+		pdomain->mode = PAGE_MODE_NONE;
+		break;
+	default:
+		return NULL;
+	}
 
-	return NULL;
+	return &pdomain->domain;
 }
 
 static void amd_iommu_domain_free(struct iommu_domain *dom)
@@ -3412,6 +3148,47 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 	return false;
 }
 
+static void amd_iommu_get_dm_regions(struct device *dev,
+				     struct list_head *head)
+{
+	struct unity_map_entry *entry;
+	u16 devid;
+
+	devid = get_device_id(dev);
+
+	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+		struct iommu_dm_region *region;
+
+		if (devid < entry->devid_start || devid > entry->devid_end)
+			continue;
+
+		region = kzalloc(sizeof(*region), GFP_KERNEL);
+		if (!region) {
+			pr_err("Out of memory allocating dm-regions for %s\n",
+				dev_name(dev));
+			return;
+		}
+
+		region->start = entry->address_start;
+		region->length = entry->address_end - entry->address_start;
+		if (entry->prot & IOMMU_PROT_IR)
+			region->prot |= IOMMU_READ;
+		if (entry->prot & IOMMU_PROT_IW)
+			region->prot |= IOMMU_WRITE;
+
+		list_add_tail(&region->list, head);
+	}
+}
+
+static void amd_iommu_put_dm_regions(struct device *dev,
+				     struct list_head *head)
+{
+	struct iommu_dm_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
+}
+
 static const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -3422,6 +3199,10 @@ static const struct iommu_ops amd_iommu_ops = {
 	.unmap = amd_iommu_unmap,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = amd_iommu_iova_to_phys,
+	.add_device = amd_iommu_add_device,
+	.remove_device = amd_iommu_remove_device,
+	.get_dm_regions = amd_iommu_get_dm_regions,
+	.put_dm_regions = amd_iommu_put_dm_regions,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
@@ -3851,6 +3632,21 @@ union irte {
 	} fields;
 };
 
+struct irq_2_irte {
+	u16 devid; /* Device ID for IRTE table */
+	u16 index; /* Index into IRTE table*/
+};
+
+struct amd_ir_data {
+	struct irq_2_irte			irq_2_irte;
+	union irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
+static struct irq_chip amd_ir_chip;
+
 #define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
 #define DTE_IRQ_TABLE_LEN       (8ULL << 1)
@@ -3944,7 +3740,7 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count)
 {
 	struct irq_remap_table *table;
 	unsigned long flags;
@@ -3966,18 +3762,10 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
 			c = 0;
 
 		if (c == count)	{
-			struct irq_2_irte *irte_info;
-
 			for (; c != 0; --c)
 				table->table[index - c + 1] = IRTE_ALLOCATED;
 
 			index -= count - 1;
-
-			cfg->remapped	      = 1;
-			irte_info             = &cfg->irq_2_irte;
-			irte_info->devid      = devid;
-			irte_info->index      = index;
-
 			goto out;
 		}
 	}
@@ -3990,22 +3778,6 @@ out:
 	return index;
 }
 
-static int get_irte(u16 devid, int index, union irte *irte)
-{
-	struct irq_remap_table *table;
-	unsigned long flags;
-
-	table = get_irq_table(devid, false);
-	if (!table)
-		return -ENOMEM;
-
-	spin_lock_irqsave(&table->lock, flags);
-	irte->val = table->table[index];
-	spin_unlock_irqrestore(&table->lock, flags);
-
-	return 0;
-}
-
 static int modify_irte(u16 devid, int index, union irte irte)
 {
 	struct irq_remap_table *table;
@@ -4052,243 +3824,316 @@ static void free_irte(u16 devid, int index)
 	iommu_completion_wait(iommu);
 }
 
-static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int vector,
-			      struct io_apic_irq_attr *attr)
+static int get_devid(struct irq_alloc_info *info)
 {
-	struct irq_remap_table *table;
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	union irte irte;
-	int ioapic_id;
-	int index;
-	int devid;
-	int ret;
+	int devid = -1;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
-
-	irte_info = &cfg->irq_2_irte;
-	ioapic_id = mpc_ioapic_id(attr->ioapic);
-	devid     = get_ioapic_devid(ioapic_id);
-
-	if (devid < 0)
-		return devid;
-
-	table = get_irq_table(devid, true);
-	if (table == NULL)
-		return -ENOMEM;
-
-	index = attr->ioapic_pin;
-
-	/* Setup IRQ remapping info */
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		devid     = get_ioapic_devid(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		devid     = get_hpet_devid(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
 
-	/* Setup IRTE for IOMMU */
-	irte.val		= 0;
-	irte.fields.vector      = vector;
-	irte.fields.int_type    = apic->irq_delivery_mode;
-	irte.fields.destination = destination;
-	irte.fields.dm          = apic->irq_dest_mode;
-	irte.fields.valid       = 1;
-
-	ret = modify_irte(devid, index, irte);
-	if (ret)
-		return ret;
+	return devid;
+}
 
-	/* Setup IOAPIC entry */
-	memset(entry, 0, sizeof(*entry));
+static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
+{
+	struct amd_iommu *iommu;
+	int devid;
 
-	entry->vector        = index;
-	entry->mask          = 0;
-	entry->trigger       = attr->trigger;
-	entry->polarity      = attr->polarity;
+	if (!info)
+		return NULL;
 
-	/*
-	 * Mask level triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
+	devid = get_devid(info);
+	if (devid >= 0) {
+		iommu = amd_iommu_rlookup_table[devid];
+		if (iommu)
+			return iommu->ir_domain;
+	}
 
-	return 0;
+	return NULL;
 }
 
-static int set_affinity(struct irq_data *data, const struct cpumask *mask,
-			bool force)
+static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
 {
-	struct irq_2_irte *irte_info;
-	unsigned int dest, irq;
-	struct irq_cfg *cfg;
-	union irte irte;
-	int err;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -1;
-
-	cfg       = irqd_cfg(data);
-	irq       = data->irq;
-	irte_info = &cfg->irq_2_irte;
+	struct amd_iommu *iommu;
+	int devid;
 
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
+	if (!info)
+		return NULL;
 
-	if (get_irte(irte_info->devid, irte_info->index, &irte))
-		return -EBUSY;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		if (devid >= 0) {
+			iommu = amd_iommu_rlookup_table[devid];
+			if (iommu)
+				return iommu->msi_domain;
+		}
+		break;
+	default:
+		break;
+	}
 
-	if (assign_irq_vector(irq, cfg, mask))
-		return -EBUSY;
+	return NULL;
+}
 
-	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
-	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
-			pr_err("AMD-Vi: Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
+struct irq_remap_ops amd_iommu_irq_ops = {
+	.prepare		= amd_iommu_prepare,
+	.enable			= amd_iommu_enable,
+	.disable		= amd_iommu_disable,
+	.reenable		= amd_iommu_reenable,
+	.enable_faulting	= amd_iommu_enable_faulting,
+	.get_ir_irq_domain	= get_ir_irq_domain,
+	.get_irq_domain		= get_irq_domain,
+};
 
-	irte.fields.vector      = cfg->vector;
-	irte.fields.destination = dest;
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+				       struct irq_cfg *irq_cfg,
+				       struct irq_alloc_info *info,
+				       int devid, int index, int sub_handle)
+{
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct msi_msg *msg = &data->msi_entry;
+	union irte *irte = &data->irte_entry;
+	struct IO_APIC_route_entry *entry;
 
-	modify_irte(irte_info->devid, irte_info->index, irte);
+	data->irq_2_irte.devid = devid;
+	data->irq_2_irte.index = index + sub_handle;
 
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+	/* Setup IRTE for IOMMU */
+	irte->val = 0;
+	irte->fields.vector      = irq_cfg->vector;
+	irte->fields.int_type    = apic->irq_delivery_mode;
+	irte->fields.destination = irq_cfg->dest_apicid;
+	irte->fields.dm          = apic->irq_dest_mode;
+	irte->fields.valid       = 1;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Setup IOAPIC entry */
+		entry = info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->vector        = index;
+		entry->mask          = 0;
+		entry->trigger       = info->ioapic_trigger;
+		entry->polarity      = info->ioapic_polarity;
+		/* Mask level triggered irqs. */
+		if (info->ioapic_trigger)
+			entry->mask = 1;
+		break;
 
-	cpumask_copy(data->affinity, mask);
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->address_lo = MSI_ADDR_BASE_LO;
+		msg->data = irte_info->index;
+		break;
 
-	return 0;
+	default:
+		BUG_ON(1);
+		break;
+	}
 }
 
-static int free_irq(int irq)
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs, void *arg)
 {
-	struct irq_2_irte *irte_info;
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
 	struct irq_cfg *cfg;
+	int i, ret, devid;
+	int index = -1;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
+	if (!info)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
 		return -EINVAL;
 
-	irte_info = &cfg->irq_2_irte;
-
-	free_irte(irte_info->devid, irte_info->index);
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
 
-	return 0;
-}
+	devid = get_devid(info);
+	if (devid < 0)
+		return -EINVAL;
 
-static void compose_msi_msg(struct pci_dev *pdev,
-			    unsigned int irq, unsigned int dest,
-			    struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	union irte irte;
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return;
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
 
-	irte_info = &cfg->irq_2_irte;
+	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+		if (get_irq_table(devid, true))
+			index = info->ioapic_pin;
+		else
+			ret = -ENOMEM;
+	} else {
+		index = alloc_irq_index(devid, nr_irqs);
+	}
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
 
-	irte.val		= 0;
-	irte.fields.vector	= cfg->vector;
-	irte.fields.int_type    = apic->irq_delivery_mode;
-	irte.fields.destination	= dest;
-	irte.fields.dm		= apic->irq_dest_mode;
-	irte.fields.valid	= 1;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		cfg = irqd_cfg(irq_data);
+		if (!irq_data || !cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
 
-	modify_irte(irte_info->devid, irte_info->index, irte);
+		if (i > 0) {
+			data = kzalloc(sizeof(*data), GFP_KERNEL);
+			if (!data)
+				goto out_free_data;
+		}
+		irq_data->hwirq = (devid << 16) + i;
+		irq_data->chip_data = data;
+		irq_data->chip = &amd_ir_chip;
+		irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
 
-	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->address_lo = MSI_ADDR_BASE_LO;
-	msg->data       = irte_info->index;
+out_free_data:
+	for (i--; i >= 0; i--) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		if (irq_data)
+			kfree(irq_data->chip_data);
+	}
+	for (i = 0; i < nr_irqs; i++)
+		free_irte(devid, index + i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
 }
 
-static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs)
 {
-	struct irq_cfg *cfg;
-	int index;
-	u16 devid;
-
-	if (!pdev)
-		return -EINVAL;
+	struct irq_2_irte *irte_info;
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
+	int i;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irte_info = &data->irq_2_irte;
+			free_irte(irte_info->devid, irte_info->index);
+			kfree(data);
+		}
+	}
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
 
-	devid = get_device_id(&pdev->dev);
-	index = alloc_irq_index(cfg, devid, nvec);
+static void irq_remapping_activate(struct irq_domain *domain,
+				   struct irq_data *irq_data)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
 
-	return index < 0 ? MAX_IRQS_PER_TABLE : index;
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
 }
 
-static int msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
-			 int index, int offset)
+static void irq_remapping_deactivate(struct irq_domain *domain,
+				     struct irq_data *irq_data)
 {
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	u16 devid;
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	union irte entry;
 
-	if (!pdev)
-		return -EINVAL;
+	entry.val = 0;
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+static struct irq_domain_ops amd_ir_domain_ops = {
+	.alloc = irq_remapping_alloc,
+	.free = irq_remapping_free,
+	.activate = irq_remapping_activate,
+	.deactivate = irq_remapping_deactivate,
+};
 
-	if (index >= MAX_IRQS_PER_TABLE)
-		return 0;
+static int amd_ir_set_affinity(struct irq_data *data,
+			       const struct cpumask *mask, bool force)
+{
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct irq_data *parent = data->parent_data;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
 
-	devid		= get_device_id(&pdev->dev);
-	irte_info	= &cfg->irq_2_irte;
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	ir_data->irte_entry.fields.vector = cfg->vector;
+	ir_data->irte_entry.fields.destination = cfg->dest_apicid;
+	modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
 
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index + offset;
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	send_cleanup_vector(cfg);
 
-	return 0;
+	return IRQ_SET_MASK_OK_DONE;
 }
 
-static int alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
 {
-	struct irq_2_irte *irte_info;
-	struct irq_cfg *cfg;
-	int index, devid;
+	struct amd_ir_data *ir_data = irq_data->chip_data;
 
-	cfg = irq_cfg(irq);
-	if (!cfg)
-		return -EINVAL;
+	*msg = ir_data->msi_entry;
+}
 
-	irte_info = &cfg->irq_2_irte;
-	devid     = get_hpet_devid(id);
-	if (devid < 0)
-		return devid;
+static struct irq_chip amd_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = amd_ir_set_affinity,
+	.irq_compose_msi_msg = ir_compose_msi_msg,
+};
 
-	index = alloc_irq_index(cfg, devid, 1);
-	if (index < 0)
-		return index;
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+	if (!iommu->ir_domain)
+		return -ENOMEM;
 
-	cfg->remapped	      = 1;
-	irte_info->devid      = devid;
-	irte_info->index      = index;
+	iommu->ir_domain->parent = arch_get_ir_parent_domain();
+	iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
 
 	return 0;
 }
-
-struct irq_remap_ops amd_iommu_irq_ops = {
-	.prepare		= amd_iommu_prepare,
-	.enable			= amd_iommu_enable,
-	.disable		= amd_iommu_disable,
-	.reenable		= amd_iommu_reenable,
-	.enable_faulting	= amd_iommu_enable_faulting,
-	.setup_ioapic_entry	= setup_ioapic_entry,
-	.set_affinity		= set_affinity,
-	.free_irq		= free_irq,
-	.compose_msi_msg	= compose_msi_msg,
-	.msi_alloc_irq		= msi_alloc_irq,
-	.msi_setup_irq		= msi_setup_irq,
-	.alloc_hpet_msi		= alloc_hpet_msi,
-};
 #endif
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 450ef5001a65..dbda9ae68c5d 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -226,6 +226,7 @@ static enum iommu_init_state init_state = IOMMU_START_STATE;
 
 static int amd_iommu_enable_interrupts(void);
 static int __init iommu_go_to_state(enum iommu_init_state state);
+static void init_device_table_dma(void);
 
 static inline void update_last_devid(u16 devid)
 {
@@ -1124,6 +1125,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (ret)
 		return ret;
 
+	ret = amd_iommu_create_irq_domain(iommu);
+	if (ret)
+		return ret;
+
 	/*
 	 * Make sure IOMMU is not considered to translate itself. The IVRS
 	 * table tells us so, but this is a lie!
@@ -1385,9 +1390,15 @@ static int __init amd_iommu_init_pci(void)
 			break;
 	}
 
-	ret = amd_iommu_init_devices();
+	init_device_table_dma();
+
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
 
-	print_iommu_info();
+	ret = amd_iommu_init_api();
+
+	if (!ret)
+		print_iommu_info();
 
 	return ret;
 }
@@ -1825,8 +1836,6 @@ static bool __init check_ioapic_information(void)
 
 static void __init free_dma_resources(void)
 {
-	amd_iommu_uninit_devices();
-
 	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
 		   get_order(MAX_DOMAIN_ID/8));
 
@@ -2019,27 +2028,10 @@ static bool detect_ivrs(void)
 
 static int amd_iommu_init_dma(void)
 {
-	struct amd_iommu *iommu;
-	int ret;
-
 	if (iommu_pass_through)
-		ret = amd_iommu_init_passthrough();
+		return amd_iommu_init_passthrough();
 	else
-		ret = amd_iommu_init_dma_ops();
-
-	if (ret)
-		return ret;
-
-	init_device_table_dma();
-
-	for_each_iommu(iommu)
-		iommu_flush_all_caches(iommu);
-
-	amd_iommu_init_api();
-
-	amd_iommu_init_notifier();
-
-	return 0;
+		return amd_iommu_init_dma_ops();
 }
 
 /****************************************************************************
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 72b0fd455e24..0bd9eb374462 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/drivers/iommu/amd_iommu_proto.h
@@ -30,7 +30,7 @@ extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);
 extern void amd_iommu_uninit_devices(void);
 extern void amd_iommu_init_notifier(void);
-extern void amd_iommu_init_api(void);
+extern int amd_iommu_init_api(void);
 
 /* Needed for interrupt remapping */
 extern int amd_iommu_prepare(void);
@@ -62,6 +62,15 @@ extern u8 amd_iommu_pc_get_max_counters(u16 devid);
 extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
 				    u64 *value, bool is_write);
 
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
 #define PPR_SUCCESS			0x0
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 05030e523771..f65908841be0 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -398,6 +398,7 @@ struct amd_iommu_fault {
 
 
 struct iommu_domain;
+struct irq_domain;
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -446,8 +447,6 @@ struct aperture_range {
  * Data container for a dma_ops specific protection domain
  */
 struct dma_ops_domain {
-	struct list_head list;
-
 	/* generic protection domain information */
 	struct protection_domain domain;
 
@@ -462,12 +461,6 @@ struct dma_ops_domain {
 
 	/* This will be set to true when TLB needs to be flushed */
 	bool need_flush;
-
-	/*
-	 * if this is a preallocated domain, keep the device for which it was
-	 * preallocated in this variable
-	 */
-	u16 target_dev;
 };
 
 /*
@@ -552,9 +545,6 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
-	/* default dma_ops domain for that IOMMU */
-	struct dma_ops_domain *default_dom;
-
 	/* IOMMU sysfs device */
 	struct device *iommu_dev;
 
@@ -579,6 +569,10 @@ struct amd_iommu {
 	/* The maximum PC banks and counters/bank (PCSup=1) */
 	u8 max_banks;
 	u8 max_counters;
+#ifdef CONFIG_IRQ_REMAP
+	struct irq_domain *ir_domain;
+	struct irq_domain *msi_domain;
+#endif
 };
 
 struct devid_map {
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index a1cbba9056fd..3465faf1809e 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -266,6 +266,7 @@ static void put_pasid_state(struct pasid_state *pasid_state)
 
 static void put_pasid_state_wait(struct pasid_state *pasid_state)
 {
+	atomic_dec(&pasid_state->count);
 	wait_event(pasid_state->wq, !atomic_read(&pasid_state->count));
 	free_pasid_state(pasid_state);
 }
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
new file mode 100644
index 000000000000..f14130121298
--- /dev/null
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -0,0 +1,2670 @@
+/*
+ * IOMMU API for ARM architected SMMUv3 implementations.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ *
+ * This driver is powered by bad coffee and bombay mix.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include "io-pgtable.h"
+
+/* MMIO registers */
+#define ARM_SMMU_IDR0			0x0
+#define IDR0_ST_LVL_SHIFT		27
+#define IDR0_ST_LVL_MASK		0x3
+#define IDR0_ST_LVL_2LVL		(1 << IDR0_ST_LVL_SHIFT)
+#define IDR0_STALL_MODEL		(3 << 24)
+#define IDR0_TTENDIAN_SHIFT		21
+#define IDR0_TTENDIAN_MASK		0x3
+#define IDR0_TTENDIAN_LE		(2 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_BE		(3 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_TTENDIAN_MIXED		(0 << IDR0_TTENDIAN_SHIFT)
+#define IDR0_CD2L			(1 << 19)
+#define IDR0_VMID16			(1 << 18)
+#define IDR0_PRI			(1 << 16)
+#define IDR0_SEV			(1 << 14)
+#define IDR0_MSI			(1 << 13)
+#define IDR0_ASID16			(1 << 12)
+#define IDR0_ATS			(1 << 10)
+#define IDR0_HYP			(1 << 9)
+#define IDR0_COHACC			(1 << 4)
+#define IDR0_TTF_SHIFT			2
+#define IDR0_TTF_MASK			0x3
+#define IDR0_TTF_AARCH64		(2 << IDR0_TTF_SHIFT)
+#define IDR0_S1P			(1 << 1)
+#define IDR0_S2P			(1 << 0)
+
+#define ARM_SMMU_IDR1			0x4
+#define IDR1_TABLES_PRESET		(1 << 30)
+#define IDR1_QUEUES_PRESET		(1 << 29)
+#define IDR1_REL			(1 << 28)
+#define IDR1_CMDQ_SHIFT			21
+#define IDR1_CMDQ_MASK			0x1f
+#define IDR1_EVTQ_SHIFT			16
+#define IDR1_EVTQ_MASK			0x1f
+#define IDR1_PRIQ_SHIFT			11
+#define IDR1_PRIQ_MASK			0x1f
+#define IDR1_SSID_SHIFT			6
+#define IDR1_SSID_MASK			0x1f
+#define IDR1_SID_SHIFT			0
+#define IDR1_SID_MASK			0x3f
+
+#define ARM_SMMU_IDR5			0x14
+#define IDR5_STALL_MAX_SHIFT		16
+#define IDR5_STALL_MAX_MASK		0xffff
+#define IDR5_GRAN64K			(1 << 6)
+#define IDR5_GRAN16K			(1 << 5)
+#define IDR5_GRAN4K			(1 << 4)
+#define IDR5_OAS_SHIFT			0
+#define IDR5_OAS_MASK			0x7
+#define IDR5_OAS_32_BIT			(0 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_36_BIT			(1 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_40_BIT			(2 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_42_BIT			(3 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_44_BIT			(4 << IDR5_OAS_SHIFT)
+#define IDR5_OAS_48_BIT			(5 << IDR5_OAS_SHIFT)
+
+#define ARM_SMMU_CR0			0x20
+#define CR0_CMDQEN			(1 << 3)
+#define CR0_EVTQEN			(1 << 2)
+#define CR0_PRIQEN			(1 << 1)
+#define CR0_SMMUEN			(1 << 0)
+
+#define ARM_SMMU_CR0ACK			0x24
+
+#define ARM_SMMU_CR1			0x28
+#define CR1_SH_NSH			0
+#define CR1_SH_OSH			2
+#define CR1_SH_ISH			3
+#define CR1_CACHE_NC			0
+#define CR1_CACHE_WB			1
+#define CR1_CACHE_WT			2
+#define CR1_TABLE_SH_SHIFT		10
+#define CR1_TABLE_OC_SHIFT		8
+#define CR1_TABLE_IC_SHIFT		6
+#define CR1_QUEUE_SH_SHIFT		4
+#define CR1_QUEUE_OC_SHIFT		2
+#define CR1_QUEUE_IC_SHIFT		0
+
+#define ARM_SMMU_CR2			0x2c
+#define CR2_PTM				(1 << 2)
+#define CR2_RECINVSID			(1 << 1)
+#define CR2_E2H				(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRL		0x50
+#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
+#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRLACK		0x54
+
+#define ARM_SMMU_GERROR			0x60
+#define GERROR_SFM_ERR			(1 << 8)
+#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
+#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
+#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
+#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
+#define GERROR_PRIQ_ABT_ERR		(1 << 3)
+#define GERROR_EVTQ_ABT_ERR		(1 << 2)
+#define GERROR_CMDQ_ERR			(1 << 0)
+#define GERROR_ERR_MASK			0xfd
+
+#define ARM_SMMU_GERRORN		0x64
+
+#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
+#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
+#define ARM_SMMU_GERROR_IRQ_CFG2	0x74
+
+#define ARM_SMMU_STRTAB_BASE		0x80
+#define STRTAB_BASE_RA			(1UL << 62)
+#define STRTAB_BASE_ADDR_SHIFT		6
+#define STRTAB_BASE_ADDR_MASK		0x3ffffffffffUL
+
+#define ARM_SMMU_STRTAB_BASE_CFG	0x88
+#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT	0
+#define STRTAB_BASE_CFG_LOG2SIZE_MASK	0x3f
+#define STRTAB_BASE_CFG_SPLIT_SHIFT	6
+#define STRTAB_BASE_CFG_SPLIT_MASK	0x1f
+#define STRTAB_BASE_CFG_FMT_SHIFT	16
+#define STRTAB_BASE_CFG_FMT_MASK	0x3
+#define STRTAB_BASE_CFG_FMT_LINEAR	(0 << STRTAB_BASE_CFG_FMT_SHIFT)
+#define STRTAB_BASE_CFG_FMT_2LVL	(1 << STRTAB_BASE_CFG_FMT_SHIFT)
+
+#define ARM_SMMU_CMDQ_BASE		0x90
+#define ARM_SMMU_CMDQ_PROD		0x98
+#define ARM_SMMU_CMDQ_CONS		0x9c
+
+#define ARM_SMMU_EVTQ_BASE		0xa0
+#define ARM_SMMU_EVTQ_PROD		0x100a8
+#define ARM_SMMU_EVTQ_CONS		0x100ac
+#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
+#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
+#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
+
+#define ARM_SMMU_PRIQ_BASE		0xc0
+#define ARM_SMMU_PRIQ_PROD		0x100c8
+#define ARM_SMMU_PRIQ_CONS		0x100cc
+#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
+#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
+#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
+
+/* Common MSI config fields */
+#define MSI_CFG0_SH_SHIFT		60
+#define MSI_CFG0_SH_NSH			(0UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_OSH			(2UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_SH_ISH			(3UL << MSI_CFG0_SH_SHIFT)
+#define MSI_CFG0_MEMATTR_SHIFT		56
+#define MSI_CFG0_MEMATTR_DEVICE_nGnRE	(0x1 << MSI_CFG0_MEMATTR_SHIFT)
+#define MSI_CFG0_ADDR_SHIFT		2
+#define MSI_CFG0_ADDR_MASK		0x3fffffffffffUL
+
+#define Q_IDX(q, p)			((p) & ((1 << (q)->max_n_shift) - 1))
+#define Q_WRP(q, p)			((p) & (1 << (q)->max_n_shift))
+#define Q_OVERFLOW_FLAG			(1 << 31)
+#define Q_OVF(q, p)			((p) & Q_OVERFLOW_FLAG)
+#define Q_ENT(q, p)			((q)->base +			\
+					 Q_IDX(q, p) * (q)->ent_dwords)
+
+#define Q_BASE_RWA			(1UL << 62)
+#define Q_BASE_ADDR_SHIFT		5
+#define Q_BASE_ADDR_MASK		0xfffffffffffUL
+#define Q_BASE_LOG2SIZE_SHIFT		0
+#define Q_BASE_LOG2SIZE_MASK		0x1fUL
+
+/*
+ * Stream table.
+ *
+ * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
+ * 2lvl: 8k L1 entries, 256 lazy entries per table (each table covers a PCI bus)
+ */
+#define STRTAB_L1_SZ_SHIFT		16
+#define STRTAB_SPLIT			8
+
+#define STRTAB_L1_DESC_DWORDS		1
+#define STRTAB_L1_DESC_SPAN_SHIFT	0
+#define STRTAB_L1_DESC_SPAN_MASK	0x1fUL
+#define STRTAB_L1_DESC_L2PTR_SHIFT	6
+#define STRTAB_L1_DESC_L2PTR_MASK	0x3ffffffffffUL
+
+#define STRTAB_STE_DWORDS		8
+#define STRTAB_STE_0_V			(1UL << 0)
+#define STRTAB_STE_0_CFG_SHIFT		1
+#define STRTAB_STE_0_CFG_MASK		0x7UL
+#define STRTAB_STE_0_CFG_ABORT		(0UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_BYPASS		(4UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S1_TRANS	(5UL << STRTAB_STE_0_CFG_SHIFT)
+#define STRTAB_STE_0_CFG_S2_TRANS	(6UL << STRTAB_STE_0_CFG_SHIFT)
+
+#define STRTAB_STE_0_S1FMT_SHIFT	4
+#define STRTAB_STE_0_S1FMT_LINEAR	(0UL << STRTAB_STE_0_S1FMT_SHIFT)
+#define STRTAB_STE_0_S1CTXPTR_SHIFT	6
+#define STRTAB_STE_0_S1CTXPTR_MASK	0x3ffffffffffUL
+#define STRTAB_STE_0_S1CDMAX_SHIFT	59
+#define STRTAB_STE_0_S1CDMAX_MASK	0x1fUL
+
+#define STRTAB_STE_1_S1C_CACHE_NC	0UL
+#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
+#define STRTAB_STE_1_S1C_CACHE_WT	2UL
+#define STRTAB_STE_1_S1C_CACHE_WB	3UL
+#define STRTAB_STE_1_S1C_SH_NSH		0UL
+#define STRTAB_STE_1_S1C_SH_OSH		2UL
+#define STRTAB_STE_1_S1C_SH_ISH		3UL
+#define STRTAB_STE_1_S1CIR_SHIFT	2
+#define STRTAB_STE_1_S1COR_SHIFT	4
+#define STRTAB_STE_1_S1CSH_SHIFT	6
+
+#define STRTAB_STE_1_S1STALLD		(1UL << 27)
+
+#define STRTAB_STE_1_EATS_ABT		0UL
+#define STRTAB_STE_1_EATS_TRANS		1UL
+#define STRTAB_STE_1_EATS_S1CHK		2UL
+#define STRTAB_STE_1_EATS_SHIFT		28
+
+#define STRTAB_STE_1_STRW_NSEL1		0UL
+#define STRTAB_STE_1_STRW_EL2		2UL
+#define STRTAB_STE_1_STRW_SHIFT		30
+
+#define STRTAB_STE_2_S2VMID_SHIFT	0
+#define STRTAB_STE_2_S2VMID_MASK	0xffffUL
+#define STRTAB_STE_2_VTCR_SHIFT		32
+#define STRTAB_STE_2_VTCR_MASK		0x7ffffUL
+#define STRTAB_STE_2_S2AA64		(1UL << 51)
+#define STRTAB_STE_2_S2ENDI		(1UL << 52)
+#define STRTAB_STE_2_S2PTW		(1UL << 54)
+#define STRTAB_STE_2_S2R		(1UL << 58)
+
+#define STRTAB_STE_3_S2TTB_SHIFT	4
+#define STRTAB_STE_3_S2TTB_MASK		0xfffffffffffUL
+
+/* Context descriptor (stage-1 only) */
+#define CTXDESC_CD_DWORDS		8
+#define CTXDESC_CD_0_TCR_T0SZ_SHIFT	0
+#define ARM64_TCR_T0SZ_SHIFT		0
+#define ARM64_TCR_T0SZ_MASK		0x1fUL
+#define CTXDESC_CD_0_TCR_TG0_SHIFT	6
+#define ARM64_TCR_TG0_SHIFT		14
+#define ARM64_TCR_TG0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_IRGN0_SHIFT	8
+#define ARM64_TCR_IRGN0_SHIFT		24
+#define ARM64_TCR_IRGN0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_ORGN0_SHIFT	10
+#define ARM64_TCR_ORGN0_SHIFT		26
+#define ARM64_TCR_ORGN0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_SH0_SHIFT	12
+#define ARM64_TCR_SH0_SHIFT		12
+#define ARM64_TCR_SH0_MASK		0x3UL
+#define CTXDESC_CD_0_TCR_EPD0_SHIFT	14
+#define ARM64_TCR_EPD0_SHIFT		7
+#define ARM64_TCR_EPD0_MASK		0x1UL
+#define CTXDESC_CD_0_TCR_EPD1_SHIFT	30
+#define ARM64_TCR_EPD1_SHIFT		23
+#define ARM64_TCR_EPD1_MASK		0x1UL
+
+#define CTXDESC_CD_0_ENDI		(1UL << 15)
+#define CTXDESC_CD_0_V			(1UL << 31)
+
+#define CTXDESC_CD_0_TCR_IPS_SHIFT	32
+#define ARM64_TCR_IPS_SHIFT		32
+#define ARM64_TCR_IPS_MASK		0x7UL
+#define CTXDESC_CD_0_TCR_TBI0_SHIFT	38
+#define ARM64_TCR_TBI0_SHIFT		37
+#define ARM64_TCR_TBI0_MASK		0x1UL
+
+#define CTXDESC_CD_0_AA64		(1UL << 41)
+#define CTXDESC_CD_0_R			(1UL << 45)
+#define CTXDESC_CD_0_A			(1UL << 46)
+#define CTXDESC_CD_0_ASET_SHIFT		47
+#define CTXDESC_CD_0_ASET_SHARED	(0UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASET_PRIVATE	(1UL << CTXDESC_CD_0_ASET_SHIFT)
+#define CTXDESC_CD_0_ASID_SHIFT		48
+#define CTXDESC_CD_0_ASID_MASK		0xffffUL
+
+#define CTXDESC_CD_1_TTB0_SHIFT		4
+#define CTXDESC_CD_1_TTB0_MASK		0xfffffffffffUL
+
+#define CTXDESC_CD_3_MAIR_SHIFT		0
+
+/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
+#define ARM_SMMU_TCR2CD(tcr, fld)					\
+	(((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK)	\
+	 << CTXDESC_CD_0_TCR_##fld##_SHIFT)
+
+/* Command queue */
+#define CMDQ_ENT_DWORDS			2
+#define CMDQ_MAX_SZ_SHIFT		8
+
+#define CMDQ_ERR_SHIFT			24
+#define CMDQ_ERR_MASK			0x7f
+#define CMDQ_ERR_CERROR_NONE_IDX	0
+#define CMDQ_ERR_CERROR_ILL_IDX		1
+#define CMDQ_ERR_CERROR_ABT_IDX		2
+
+#define CMDQ_0_OP_SHIFT			0
+#define CMDQ_0_OP_MASK			0xffUL
+#define CMDQ_0_SSV			(1UL << 11)
+
+#define CMDQ_PREFETCH_0_SID_SHIFT	32
+#define CMDQ_PREFETCH_1_SIZE_SHIFT	0
+#define CMDQ_PREFETCH_1_ADDR_MASK	~0xfffUL
+
+#define CMDQ_CFGI_0_SID_SHIFT		32
+#define CMDQ_CFGI_0_SID_MASK		0xffffffffUL
+#define CMDQ_CFGI_1_LEAF		(1UL << 0)
+#define CMDQ_CFGI_1_RANGE_SHIFT		0
+#define CMDQ_CFGI_1_RANGE_MASK		0x1fUL
+
+#define CMDQ_TLBI_0_VMID_SHIFT		32
+#define CMDQ_TLBI_0_ASID_SHIFT		48
+#define CMDQ_TLBI_1_LEAF		(1UL << 0)
+#define CMDQ_TLBI_1_ADDR_MASK		~0xfffUL
+
+#define CMDQ_PRI_0_SSID_SHIFT		12
+#define CMDQ_PRI_0_SSID_MASK		0xfffffUL
+#define CMDQ_PRI_0_SID_SHIFT		32
+#define CMDQ_PRI_0_SID_MASK		0xffffffffUL
+#define CMDQ_PRI_1_GRPID_SHIFT		0
+#define CMDQ_PRI_1_GRPID_MASK		0x1ffUL
+#define CMDQ_PRI_1_RESP_SHIFT		12
+#define CMDQ_PRI_1_RESP_DENY		(0UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_FAIL		(1UL << CMDQ_PRI_1_RESP_SHIFT)
+#define CMDQ_PRI_1_RESP_SUCC		(2UL << CMDQ_PRI_1_RESP_SHIFT)
+
+#define CMDQ_SYNC_0_CS_SHIFT		12
+#define CMDQ_SYNC_0_CS_NONE		(0UL << CMDQ_SYNC_0_CS_SHIFT)
+#define CMDQ_SYNC_0_CS_SEV		(2UL << CMDQ_SYNC_0_CS_SHIFT)
+
+/* Event queue */
+#define EVTQ_ENT_DWORDS			4
+#define EVTQ_MAX_SZ_SHIFT		7
+
+#define EVTQ_0_ID_SHIFT			0
+#define EVTQ_0_ID_MASK			0xffUL
+
+/* PRI queue */
+#define PRIQ_ENT_DWORDS			2
+#define PRIQ_MAX_SZ_SHIFT		8
+
+#define PRIQ_0_SID_SHIFT		0
+#define PRIQ_0_SID_MASK			0xffffffffUL
+#define PRIQ_0_SSID_SHIFT		32
+#define PRIQ_0_SSID_MASK		0xfffffUL
+#define PRIQ_0_OF			(1UL << 57)
+#define PRIQ_0_PERM_PRIV		(1UL << 58)
+#define PRIQ_0_PERM_EXEC		(1UL << 59)
+#define PRIQ_0_PERM_READ		(1UL << 60)
+#define PRIQ_0_PERM_WRITE		(1UL << 61)
+#define PRIQ_0_PRG_LAST			(1UL << 62)
+#define PRIQ_0_SSID_V			(1UL << 63)
+
+#define PRIQ_1_PRG_IDX_SHIFT		0
+#define PRIQ_1_PRG_IDX_MASK		0x1ffUL
+#define PRIQ_1_ADDR_SHIFT		12
+#define PRIQ_1_ADDR_MASK		0xfffffffffffffUL
+
+/* High-level queue structures */
+#define ARM_SMMU_POLL_TIMEOUT_US	100
+
+static bool disable_bypass;
+module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_bypass,
+	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
+
+enum pri_resp {
+	PRI_RESP_DENY,
+	PRI_RESP_FAIL,
+	PRI_RESP_SUCC,
+};
+
+struct arm_smmu_cmdq_ent {
+	/* Common fields */
+	u8				opcode;
+	bool				substream_valid;
+
+	/* Command-specific fields */
+	union {
+		#define CMDQ_OP_PREFETCH_CFG	0x1
+		struct {
+			u32			sid;
+			u8			size;
+			u64			addr;
+		} prefetch;
+
+		#define CMDQ_OP_CFGI_STE	0x3
+		#define CMDQ_OP_CFGI_ALL	0x4
+		struct {
+			u32			sid;
+			union {
+				bool		leaf;
+				u8		span;
+			};
+		} cfgi;
+
+		#define CMDQ_OP_TLBI_NH_ASID	0x11
+		#define CMDQ_OP_TLBI_NH_VA	0x12
+		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_S12_VMALL	0x28
+		#define CMDQ_OP_TLBI_S2_IPA	0x2a
+		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
+		struct {
+			u16			asid;
+			u16			vmid;
+			bool			leaf;
+			u64			addr;
+		} tlbi;
+
+		#define CMDQ_OP_PRI_RESP	0x41
+		struct {
+			u32			sid;
+			u32			ssid;
+			u16			grpid;
+			enum pri_resp		resp;
+		} pri;
+
+		#define CMDQ_OP_CMD_SYNC	0x46
+	};
+};
+
+struct arm_smmu_queue {
+	int				irq; /* Wired interrupt */
+
+	__le64				*base;
+	dma_addr_t			base_dma;
+	u64				q_base;
+
+	size_t				ent_dwords;
+	u32				max_n_shift;
+	u32				prod;
+	u32				cons;
+
+	u32 __iomem			*prod_reg;
+	u32 __iomem			*cons_reg;
+};
+
+struct arm_smmu_cmdq {
+	struct arm_smmu_queue		q;
+	spinlock_t			lock;
+};
+
+struct arm_smmu_evtq {
+	struct arm_smmu_queue		q;
+	u32				max_stalls;
+};
+
+struct arm_smmu_priq {
+	struct arm_smmu_queue		q;
+};
+
+/* High-level stream table and context descriptor structures */
+struct arm_smmu_strtab_l1_desc {
+	u8				span;
+
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_s1_cfg {
+	__le64				*cdptr;
+	dma_addr_t			cdptr_dma;
+
+	struct arm_smmu_ctx_desc {
+		u16	asid;
+		u64	ttbr;
+		u64	tcr;
+		u64	mair;
+	}				cd;
+};
+
+struct arm_smmu_s2_cfg {
+	u16				vmid;
+	u64				vttbr;
+	u64				vtcr;
+};
+
+struct arm_smmu_strtab_ent {
+	bool				valid;
+
+	bool				bypass;	/* Overrides s1/s2 config */
+	struct arm_smmu_s1_cfg		*s1_cfg;
+	struct arm_smmu_s2_cfg		*s2_cfg;
+};
+
+struct arm_smmu_strtab_cfg {
+	__le64				*strtab;
+	dma_addr_t			strtab_dma;
+	struct arm_smmu_strtab_l1_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+
+	u64				strtab_base;
+	u32				strtab_base_cfg;
+};
+
+/* An SMMUv3 instance */
+struct arm_smmu_device {
+	struct device			*dev;
+	void __iomem			*base;
+
+#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
+#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
+#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
+#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
+#define ARM_SMMU_FEAT_PRI		(1 << 4)
+#define ARM_SMMU_FEAT_ATS		(1 << 5)
+#define ARM_SMMU_FEAT_SEV		(1 << 6)
+#define ARM_SMMU_FEAT_MSI		(1 << 7)
+#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
+#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
+#define ARM_SMMU_FEAT_TRANS_S2		(1 << 10)
+#define ARM_SMMU_FEAT_STALLS		(1 << 11)
+#define ARM_SMMU_FEAT_HYP		(1 << 12)
+	u32				features;
+
+	struct arm_smmu_cmdq		cmdq;
+	struct arm_smmu_evtq		evtq;
+	struct arm_smmu_priq		priq;
+
+	int				gerr_irq;
+
+	unsigned long			ias; /* IPA */
+	unsigned long			oas; /* PA */
+
+#define ARM_SMMU_MAX_ASIDS		(1 << 16)
+	unsigned int			asid_bits;
+	DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS);
+
+#define ARM_SMMU_MAX_VMIDS		(1 << 16)
+	unsigned int			vmid_bits;
+	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+
+	unsigned int			ssid_bits;
+	unsigned int			sid_bits;
+
+	struct arm_smmu_strtab_cfg	strtab_cfg;
+	struct list_head		list;
+};
+
+/* SMMU private data for an IOMMU group */
+struct arm_smmu_group {
+	struct arm_smmu_device		*smmu;
+	struct arm_smmu_domain		*domain;
+	int				num_sids;
+	u32				*sids;
+	struct arm_smmu_strtab_ent	ste;
+};
+
+/* SMMU private data for an IOMMU domain */
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+};
+
+struct arm_smmu_domain {
+	struct arm_smmu_device		*smmu;
+	struct mutex			init_mutex; /* Protects smmu pointer */
+
+	struct io_pgtable_ops		*pgtbl_ops;
+	spinlock_t			pgtbl_lock;
+
+	enum arm_smmu_domain_stage	stage;
+	union {
+		struct arm_smmu_s1_cfg	s1_cfg;
+		struct arm_smmu_s2_cfg	s2_cfg;
+	};
+
+	struct iommu_domain		domain;
+};
+
+/* Our list of SMMU instances */
+static DEFINE_SPINLOCK(arm_smmu_devices_lock);
+static LIST_HEAD(arm_smmu_devices);
+
+static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
+{
+	return container_of(dom, struct arm_smmu_domain, domain);
+}
+
+/* Low-level queue manipulation functions */
+static bool queue_full(struct arm_smmu_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) != Q_WRP(q, q->cons);
+}
+
+static bool queue_empty(struct arm_smmu_queue *q)
+{
+	return Q_IDX(q, q->prod) == Q_IDX(q, q->cons) &&
+	       Q_WRP(q, q->prod) == Q_WRP(q, q->cons);
+}
+
+static void queue_sync_cons(struct arm_smmu_queue *q)
+{
+	q->cons = readl_relaxed(q->cons_reg);
+}
+
+static void queue_inc_cons(struct arm_smmu_queue *q)
+{
+	u32 cons = (Q_WRP(q, q->cons) | Q_IDX(q, q->cons)) + 1;
+
+	q->cons = Q_OVF(q, q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons);
+	writel(q->cons, q->cons_reg);
+}
+
+static int queue_sync_prod(struct arm_smmu_queue *q)
+{
+	int ret = 0;
+	u32 prod = readl_relaxed(q->prod_reg);
+
+	if (Q_OVF(q, prod) != Q_OVF(q, q->prod))
+		ret = -EOVERFLOW;
+
+	q->prod = prod;
+	return ret;
+}
+
+static void queue_inc_prod(struct arm_smmu_queue *q)
+{
+	u32 prod = (Q_WRP(q, q->prod) | Q_IDX(q, q->prod)) + 1;
+
+	q->prod = Q_OVF(q, q->prod) | Q_WRP(q, prod) | Q_IDX(q, prod);
+	writel(q->prod, q->prod_reg);
+}
+
+static bool __queue_cons_before(struct arm_smmu_queue *q, u32 until)
+{
+	if (Q_WRP(q, q->cons) == Q_WRP(q, until))
+		return Q_IDX(q, q->cons) < Q_IDX(q, until);
+
+	return Q_IDX(q, q->cons) >= Q_IDX(q, until);
+}
+
+static int queue_poll_cons(struct arm_smmu_queue *q, u32 until, bool wfe)
+{
+	ktime_t timeout = ktime_add_us(ktime_get(), ARM_SMMU_POLL_TIMEOUT_US);
+
+	while (queue_sync_cons(q), __queue_cons_before(q, until)) {
+		if (ktime_compare(ktime_get(), timeout) > 0)
+			return -ETIMEDOUT;
+
+		if (wfe) {
+			wfe();
+		} else {
+			cpu_relax();
+			udelay(1);
+		}
+	}
+
+	return 0;
+}
+
+static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = cpu_to_le64(*src++);
+}
+
+static int queue_insert_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+	if (queue_full(q))
+		return -ENOSPC;
+
+	queue_write(Q_ENT(q, q->prod), ent, q->ent_dwords);
+	queue_inc_prod(q);
+	return 0;
+}
+
+static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
+{
+	int i;
+
+	for (i = 0; i < n_dwords; ++i)
+		*dst++ = le64_to_cpu(*src++);
+}
+
+static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent)
+{
+	if (queue_empty(q))
+		return -EAGAIN;
+
+	queue_read(ent, Q_ENT(q, q->cons), q->ent_dwords);
+	queue_inc_cons(q);
+	return 0;
+}
+
+/* High-level queue accessors */
+static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
+{
+	memset(cmd, 0, CMDQ_ENT_DWORDS << 3);
+	cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT;
+
+	switch (ent->opcode) {
+	case CMDQ_OP_TLBI_EL2_ALL:
+	case CMDQ_OP_TLBI_NSNH_ALL:
+		break;
+	case CMDQ_OP_PREFETCH_CFG:
+		cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT;
+		cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT;
+		cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
+		break;
+	case CMDQ_OP_CFGI_STE:
+		cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT;
+		cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0;
+		break;
+	case CMDQ_OP_CFGI_ALL:
+		/* Cover the entire SID range */
+		cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT;
+		break;
+	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+		/* Fallthrough */
+	case CMDQ_OP_TLBI_S2_IPA:
+		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK;
+		break;
+	case CMDQ_OP_TLBI_NH_ASID:
+		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
+		/* Fallthrough */
+	case CMDQ_OP_TLBI_S12_VMALL:
+		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
+		break;
+	case CMDQ_OP_PRI_RESP:
+		cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0;
+		cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT;
+		cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT;
+		cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT;
+		switch (ent->pri.resp) {
+		case PRI_RESP_DENY:
+			cmd[1] |= CMDQ_PRI_1_RESP_DENY;
+			break;
+		case PRI_RESP_FAIL:
+			cmd[1] |= CMDQ_PRI_1_RESP_FAIL;
+			break;
+		case PRI_RESP_SUCC:
+			cmd[1] |= CMDQ_PRI_1_RESP_SUCC;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case CMDQ_OP_CMD_SYNC:
+		cmd[0] |= CMDQ_SYNC_0_CS_SEV;
+		break;
+	default:
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
+{
+	static const char *cerror_str[] = {
+		[CMDQ_ERR_CERROR_NONE_IDX]	= "No error",
+		[CMDQ_ERR_CERROR_ILL_IDX]	= "Illegal command",
+		[CMDQ_ERR_CERROR_ABT_IDX]	= "Abort on command fetch",
+	};
+
+	int i;
+	u64 cmd[CMDQ_ENT_DWORDS];
+	struct arm_smmu_queue *q = &smmu->cmdq.q;
+	u32 cons = readl_relaxed(q->cons_reg);
+	u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK;
+	struct arm_smmu_cmdq_ent cmd_sync = {
+		.opcode = CMDQ_OP_CMD_SYNC,
+	};
+
+	dev_err(smmu->dev, "CMDQ error (cons 0x%08x): %s\n", cons,
+		cerror_str[idx]);
+
+	switch (idx) {
+	case CMDQ_ERR_CERROR_ILL_IDX:
+		break;
+	case CMDQ_ERR_CERROR_ABT_IDX:
+		dev_err(smmu->dev, "retrying command fetch\n");
+	case CMDQ_ERR_CERROR_NONE_IDX:
+		return;
+	}
+
+	/*
+	 * We may have concurrent producers, so we need to be careful
+	 * not to touch any of the shadow cmdq state.
+	 */
+	queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+	dev_err(smmu->dev, "skipping command in error state:\n");
+	for (i = 0; i < ARRAY_SIZE(cmd); ++i)
+		dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
+
+	/* Convert the erroneous command into a CMD_SYNC */
+	if (arm_smmu_cmdq_build_cmd(cmd, &cmd_sync)) {
+		dev_err(smmu->dev, "failed to convert to CMD_SYNC\n");
+		return;
+	}
+
+	queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+}
+
+static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
+				    struct arm_smmu_cmdq_ent *ent)
+{
+	u32 until;
+	u64 cmd[CMDQ_ENT_DWORDS];
+	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+	struct arm_smmu_queue *q = &smmu->cmdq.q;
+
+	if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
+		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
+			 ent->opcode);
+		return;
+	}
+
+	spin_lock(&smmu->cmdq.lock);
+	while (until = q->prod + 1, queue_insert_raw(q, cmd) == -ENOSPC) {
+		/*
+		 * Keep the queue locked, otherwise the producer could wrap
+		 * twice and we could see a future consumer pointer that looks
+		 * like it's behind us.
+		 */
+		if (queue_poll_cons(q, until, wfe))
+			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+	}
+
+	if (ent->opcode == CMDQ_OP_CMD_SYNC && queue_poll_cons(q, until, wfe))
+		dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
+	spin_unlock(&smmu->cmdq.lock);
+}
+
+/* Context descriptor manipulation functions */
+static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
+{
+	u64 val = 0;
+
+	/* Repack the TCR. Just care about TTBR0 for now */
+	val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
+	val |= ARM_SMMU_TCR2CD(tcr, TG0);
+	val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
+	val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
+	val |= ARM_SMMU_TCR2CD(tcr, SH0);
+	val |= ARM_SMMU_TCR2CD(tcr, EPD0);
+	val |= ARM_SMMU_TCR2CD(tcr, EPD1);
+	val |= ARM_SMMU_TCR2CD(tcr, IPS);
+	val |= ARM_SMMU_TCR2CD(tcr, TBI0);
+
+	return val;
+}
+
+static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
+				    struct arm_smmu_s1_cfg *cfg)
+{
+	u64 val;
+
+	/*
+	 * We don't need to issue any invalidation here, as we'll invalidate
+	 * the STE when installing the new entry anyway.
+	 */
+	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+#ifdef __BIG_ENDIAN
+	      CTXDESC_CD_0_ENDI |
+#endif
+	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE |
+	      CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT |
+	      CTXDESC_CD_0_V;
+	cfg->cdptr[0] = cpu_to_le64(val);
+
+	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT;
+	cfg->cdptr[1] = cpu_to_le64(val);
+
+	cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT);
+}
+
+/* Stream table manipulation functions */
+static void
+arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
+{
+	u64 val = 0;
+
+	val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK)
+		<< STRTAB_L1_DESC_SPAN_SHIFT;
+	val |= desc->l2ptr_dma &
+	       STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT;
+
+	*dst = cpu_to_le64(val);
+}
+
+static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_STE,
+		.cfgi	= {
+			.sid	= sid,
+			.leaf	= true,
+		},
+	};
+
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	cmd.opcode = CMDQ_OP_CMD_SYNC;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
+				      __le64 *dst, struct arm_smmu_strtab_ent *ste)
+{
+	/*
+	 * This is hideously complicated, but we only really care about
+	 * three cases at the moment:
+	 *
+	 * 1. Invalid (all zero) -> bypass  (init)
+	 * 2. Bypass -> translation (attach)
+	 * 3. Translation -> bypass (detach)
+	 *
+	 * Given that we can't update the STE atomically and the SMMU
+	 * doesn't read the thing in a defined order, that leaves us
+	 * with the following maintenance requirements:
+	 *
+	 * 1. Update Config, return (init time STEs aren't live)
+	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
+	 * 3. Update Config, sync
+	 */
+	u64 val = le64_to_cpu(dst[0]);
+	bool ste_live = false;
+	struct arm_smmu_cmdq_ent prefetch_cmd = {
+		.opcode		= CMDQ_OP_PREFETCH_CFG,
+		.prefetch	= {
+			.sid	= sid,
+		},
+	};
+
+	if (val & STRTAB_STE_0_V) {
+		u64 cfg;
+
+		cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT;
+		switch (cfg) {
+		case STRTAB_STE_0_CFG_BYPASS:
+			break;
+		case STRTAB_STE_0_CFG_S1_TRANS:
+		case STRTAB_STE_0_CFG_S2_TRANS:
+			ste_live = true;
+			break;
+		default:
+			BUG(); /* STE corruption */
+		}
+	}
+
+	/* Nuke the existing Config, as we're going to rewrite it */
+	val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
+
+	if (ste->valid)
+		val |= STRTAB_STE_0_V;
+	else
+		val &= ~STRTAB_STE_0_V;
+
+	if (ste->bypass) {
+		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
+				      : STRTAB_STE_0_CFG_BYPASS;
+		dst[0] = cpu_to_le64(val);
+		dst[2] = 0; /* Nuke the VMID */
+		if (ste_live)
+			arm_smmu_sync_ste_for_sid(smmu, sid);
+		return;
+	}
+
+	if (ste->s1_cfg) {
+		BUG_ON(ste_live);
+		dst[1] = cpu_to_le64(
+			 STRTAB_STE_1_S1C_CACHE_WBRA
+			 << STRTAB_STE_1_S1CIR_SHIFT |
+			 STRTAB_STE_1_S1C_CACHE_WBRA
+			 << STRTAB_STE_1_S1COR_SHIFT |
+			 STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT |
+			 STRTAB_STE_1_S1STALLD |
+#ifdef CONFIG_PCI_ATS
+			 STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
+#endif
+			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
+
+		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
+		        << STRTAB_STE_0_S1CTXPTR_SHIFT) |
+			STRTAB_STE_0_CFG_S1_TRANS;
+
+	}
+
+	if (ste->s2_cfg) {
+		BUG_ON(ste_live);
+		dst[2] = cpu_to_le64(
+			 ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT |
+			 (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK)
+			  << STRTAB_STE_2_VTCR_SHIFT |
+#ifdef __BIG_ENDIAN
+			 STRTAB_STE_2_S2ENDI |
+#endif
+			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
+			 STRTAB_STE_2_S2R);
+
+		dst[3] = cpu_to_le64(ste->s2_cfg->vttbr &
+			 STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT);
+
+		val |= STRTAB_STE_0_CFG_S2_TRANS;
+	}
+
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+	dst[0] = cpu_to_le64(val);
+	arm_smmu_sync_ste_for_sid(smmu, sid);
+
+	/* It's likely that we'll want to use the new STE soon */
+	arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+}
+
+static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
+{
+	unsigned int i;
+	struct arm_smmu_strtab_ent ste = {
+		.valid	= true,
+		.bypass	= true,
+	};
+
+	for (i = 0; i < nent; ++i) {
+		arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
+		strtab += STRTAB_STE_DWORDS;
+	}
+}
+
+static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
+{
+	size_t size;
+	void *strtab;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[sid >> STRTAB_SPLIT];
+
+	if (desc->l2ptr)
+		return 0;
+
+	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
+	strtab = &cfg->strtab[sid >> STRTAB_SPLIT << STRTAB_L1_DESC_DWORDS];
+
+	desc->span = STRTAB_SPLIT + 1;
+	desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
+					  GFP_KERNEL);
+	if (!desc->l2ptr) {
+		dev_err(smmu->dev,
+			"failed to allocate l2 stream table for SID %u\n",
+			sid);
+		return -ENOMEM;
+	}
+
+	arm_smmu_init_bypass_stes(desc->l2ptr, 1 << STRTAB_SPLIT);
+	arm_smmu_write_strtab_l1_desc(strtab, desc);
+	return 0;
+}
+
+/* IRQ and event handlers */
+static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
+{
+	int i;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->evtq.q;
+	u64 evt[EVTQ_ENT_DWORDS];
+
+	while (!queue_remove_raw(q, evt)) {
+		u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK;
+
+		dev_info(smmu->dev, "event 0x%02x received:\n", id);
+		for (i = 0; i < ARRAY_SIZE(evt); ++i)
+			dev_info(smmu->dev, "\t0x%016llx\n",
+				 (unsigned long long)evt[i]);
+	}
+
+	/* Sync our overflow flag, as we believe we're up to speed */
+	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_evtq_handler(int irq, void *dev)
+{
+	irqreturn_t ret = IRQ_WAKE_THREAD;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->evtq.q;
+
+	/*
+	 * Not much we can do on overflow, so scream and pretend we're
+	 * trying harder.
+	 */
+	if (queue_sync_prod(q) == -EOVERFLOW)
+		dev_err(smmu->dev, "EVTQ overflow detected -- events lost\n");
+	else if (queue_empty(q))
+		ret = IRQ_NONE;
+
+	return ret;
+}
+
+static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
+{
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->priq.q;
+	u64 evt[PRIQ_ENT_DWORDS];
+
+	while (!queue_remove_raw(q, evt)) {
+		u32 sid, ssid;
+		u16 grpid;
+		bool ssv, last;
+
+		sid = evt[0] >> PRIQ_0_SID_SHIFT & PRIQ_0_SID_MASK;
+		ssv = evt[0] & PRIQ_0_SSID_V;
+		ssid = ssv ? evt[0] >> PRIQ_0_SSID_SHIFT & PRIQ_0_SSID_MASK : 0;
+		last = evt[0] & PRIQ_0_PRG_LAST;
+		grpid = evt[1] >> PRIQ_1_PRG_IDX_SHIFT & PRIQ_1_PRG_IDX_MASK;
+
+		dev_info(smmu->dev, "unexpected PRI request received:\n");
+		dev_info(smmu->dev,
+			 "\tsid 0x%08x.0x%05x: [%u%s] %sprivileged %s%s%s access at iova 0x%016llx\n",
+			 sid, ssid, grpid, last ? "L" : "",
+			 evt[0] & PRIQ_0_PERM_PRIV ? "" : "un",
+			 evt[0] & PRIQ_0_PERM_READ ? "R" : "",
+			 evt[0] & PRIQ_0_PERM_WRITE ? "W" : "",
+			 evt[0] & PRIQ_0_PERM_EXEC ? "X" : "",
+			 evt[1] & PRIQ_1_ADDR_MASK << PRIQ_1_ADDR_SHIFT);
+
+		if (last) {
+			struct arm_smmu_cmdq_ent cmd = {
+				.opcode			= CMDQ_OP_PRI_RESP,
+				.substream_valid	= ssv,
+				.pri			= {
+					.sid	= sid,
+					.ssid	= ssid,
+					.grpid	= grpid,
+					.resp	= PRI_RESP_DENY,
+				},
+			};
+
+			arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+		}
+	}
+
+	/* Sync our overflow flag, as we believe we're up to speed */
+	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t arm_smmu_priq_handler(int irq, void *dev)
+{
+	irqreturn_t ret = IRQ_WAKE_THREAD;
+	struct arm_smmu_device *smmu = dev;
+	struct arm_smmu_queue *q = &smmu->priq.q;
+
+	/* PRIQ overflow indicates a programming error */
+	if (queue_sync_prod(q) == -EOVERFLOW)
+		dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
+	else if (queue_empty(q))
+		ret = IRQ_NONE;
+
+	return ret;
+}
+
+static irqreturn_t arm_smmu_cmdq_sync_handler(int irq, void *dev)
+{
+	/* We don't actually use CMD_SYNC interrupts for anything */
+	return IRQ_HANDLED;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
+
+static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
+{
+	u32 gerror, gerrorn;
+	struct arm_smmu_device *smmu = dev;
+
+	gerror = readl_relaxed(smmu->base + ARM_SMMU_GERROR);
+	gerrorn = readl_relaxed(smmu->base + ARM_SMMU_GERRORN);
+
+	gerror ^= gerrorn;
+	if (!(gerror & GERROR_ERR_MASK))
+		return IRQ_NONE; /* No errors pending */
+
+	dev_warn(smmu->dev,
+		 "unexpected global error reported (0x%08x), this could be serious\n",
+		 gerror);
+
+	if (gerror & GERROR_SFM_ERR) {
+		dev_err(smmu->dev, "device has entered Service Failure Mode!\n");
+		arm_smmu_device_disable(smmu);
+	}
+
+	if (gerror & GERROR_MSI_GERROR_ABT_ERR)
+		dev_warn(smmu->dev, "GERROR MSI write aborted\n");
+
+	if (gerror & GERROR_MSI_PRIQ_ABT_ERR) {
+		dev_warn(smmu->dev, "PRIQ MSI write aborted\n");
+		arm_smmu_priq_handler(irq, smmu->dev);
+	}
+
+	if (gerror & GERROR_MSI_EVTQ_ABT_ERR) {
+		dev_warn(smmu->dev, "EVTQ MSI write aborted\n");
+		arm_smmu_evtq_handler(irq, smmu->dev);
+	}
+
+	if (gerror & GERROR_MSI_CMDQ_ABT_ERR) {
+		dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
+		arm_smmu_cmdq_sync_handler(irq, smmu->dev);
+	}
+
+	if (gerror & GERROR_PRIQ_ABT_ERR)
+		dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");
+
+	if (gerror & GERROR_EVTQ_ABT_ERR)
+		dev_err(smmu->dev, "EVTQ write aborted -- events may have been lost\n");
+
+	if (gerror & GERROR_CMDQ_ERR)
+		arm_smmu_cmdq_skip_err(smmu);
+
+	writel(gerror, smmu->base + ARM_SMMU_GERRORN);
+	return IRQ_HANDLED;
+}
+
+/* IO_PGTABLE API */
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+{
+	struct arm_smmu_cmdq_ent cmd;
+
+	cmd.opcode = CMDQ_OP_CMD_SYNC;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_tlb_sync(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	__arm_smmu_tlb_sync(smmu_domain->smmu);
+}
+
+static void arm_smmu_tlb_inv_context(void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd;
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		cmd.opcode	= CMDQ_OP_TLBI_NH_ASID;
+		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
+		cmd.tlbi.vmid	= 0;
+	} else {
+		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+	}
+
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	__arm_smmu_tlb_sync(smmu);
+}
+
+static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
+					  bool leaf, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd = {
+		.tlbi = {
+			.leaf	= leaf,
+			.addr	= iova,
+		},
+	};
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		cmd.opcode	= CMDQ_OP_TLBI_NH_VA;
+		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
+	} else {
+		cmd.opcode	= CMDQ_OP_TLBI_S2_IPA;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+	}
+
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+}
+
+static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
+{
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
+
+	if (smmu->features & ARM_SMMU_FEAT_COHERENCY) {
+		dsb(ishst);
+	} else {
+		dma_addr_t dma_addr;
+		struct device *dev = smmu->dev;
+
+		dma_addr = dma_map_page(dev, virt_to_page(addr), offset, size,
+					DMA_TO_DEVICE);
+
+		if (dma_mapping_error(dev, dma_addr))
+			dev_err(dev, "failed to flush pgtable at %p\n", addr);
+		else
+			dma_unmap_page(dev, dma_addr, size, DMA_TO_DEVICE);
+	}
+}
+
+static struct iommu_gather_ops arm_smmu_gather_ops = {
+	.tlb_flush_all	= arm_smmu_tlb_inv_context,
+	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
+	.tlb_sync	= arm_smmu_tlb_sync,
+	.flush_pgtable	= arm_smmu_flush_pgtable,
+};
+
+/* IOMMU API */
+static bool arm_smmu_capable(enum iommu_cap cap)
+{
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	case IOMMU_CAP_INTR_REMAP:
+		return true; /* MSIs are just memory writes */
+	case IOMMU_CAP_NOEXEC:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
+{
+	struct arm_smmu_domain *smmu_domain;
+
+	if (type != IOMMU_DOMAIN_UNMANAGED)
+		return NULL;
+
+	/*
+	 * Allocate the domain and initialise some of its data structures.
+	 * We can't really do anything meaningful until we've added a
+	 * master.
+	 */
+	smmu_domain = kzalloc(sizeof(*smmu_domain), GFP_KERNEL);
+	if (!smmu_domain)
+		return NULL;
+
+	mutex_init(&smmu_domain->init_mutex);
+	spin_lock_init(&smmu_domain->pgtbl_lock);
+	return &smmu_domain->domain;
+}
+
+static int arm_smmu_bitmap_alloc(unsigned long *map, int span)
+{
+	int idx, size = 1 << span;
+
+	do {
+		idx = find_first_zero_bit(map, size);
+		if (idx == size)
+			return -ENOSPC;
+	} while (test_and_set_bit(idx, map));
+
+	return idx;
+}
+
+static void arm_smmu_bitmap_free(unsigned long *map, int idx)
+{
+	clear_bit(idx, map);
+}
+
+static void arm_smmu_domain_free(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (smmu_domain->pgtbl_ops)
+		free_io_pgtable_ops(smmu_domain->pgtbl_ops);
+
+	/* Free the CD and ASID, if we allocated them */
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+
+		if (cfg->cdptr) {
+			dma_free_coherent(smmu_domain->smmu->dev,
+					  CTXDESC_CD_DWORDS << 3,
+					  cfg->cdptr,
+					  cfg->cdptr_dma);
+
+			arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
+		}
+	} else {
+		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+		if (cfg->vmid)
+			arm_smmu_bitmap_free(smmu->vmid_map, cfg->vmid);
+	}
+
+	kfree(smmu_domain);
+}
+
+static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	int ret;
+	u16 asid;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+
+	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
+	if (IS_ERR_VALUE(asid))
+		return asid;
+
+	cfg->cdptr = dma_zalloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
+					 &cfg->cdptr_dma, GFP_KERNEL);
+	if (!cfg->cdptr) {
+		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+		goto out_free_asid;
+	}
+
+	cfg->cd.asid	= asid;
+	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
+	return 0;
+
+out_free_asid:
+	arm_smmu_bitmap_free(smmu->asid_map, asid);
+	return ret;
+}
+
+static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
+				       struct io_pgtable_cfg *pgtbl_cfg)
+{
+	u16 vmid;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+
+	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
+	if (IS_ERR_VALUE(vmid))
+		return vmid;
+
+	cfg->vmid	= vmid;
+	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+	cfg->vtcr	= pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+	return 0;
+}
+
+static struct iommu_ops arm_smmu_ops;
+
+static int arm_smmu_domain_finalise(struct iommu_domain *domain)
+{
+	int ret;
+	unsigned long ias, oas;
+	enum io_pgtable_fmt fmt;
+	struct io_pgtable_cfg pgtbl_cfg;
+	struct io_pgtable_ops *pgtbl_ops;
+	int (*finalise_stage_fn)(struct arm_smmu_domain *,
+				 struct io_pgtable_cfg *);
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	/* Restrict the stage to what we can actually support */
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
+	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+	switch (smmu_domain->stage) {
+	case ARM_SMMU_DOMAIN_S1:
+		ias = VA_BITS;
+		oas = smmu->ias;
+		fmt = ARM_64_LPAE_S1;
+		finalise_stage_fn = arm_smmu_domain_finalise_s1;
+		break;
+	case ARM_SMMU_DOMAIN_NESTED:
+	case ARM_SMMU_DOMAIN_S2:
+		ias = smmu->ias;
+		oas = smmu->oas;
+		fmt = ARM_64_LPAE_S2;
+		finalise_stage_fn = arm_smmu_domain_finalise_s2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= arm_smmu_ops.pgsize_bitmap,
+		.ias		= ias,
+		.oas		= oas,
+		.tlb		= &arm_smmu_gather_ops,
+	};
+
+	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
+	if (!pgtbl_ops)
+		return -ENOMEM;
+
+	arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
+	smmu_domain->pgtbl_ops = pgtbl_ops;
+
+	ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
+	if (IS_ERR_VALUE(ret))
+		free_io_pgtable_ops(pgtbl_ops);
+
+	return ret;
+}
+
+static struct arm_smmu_group *arm_smmu_group_get(struct device *dev)
+{
+	struct iommu_group *group;
+	struct arm_smmu_group *smmu_group;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return NULL;
+
+	smmu_group = iommu_group_get_iommudata(group);
+	iommu_group_put(group);
+	return smmu_group;
+}
+
+static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+{
+	__le64 *step;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		struct arm_smmu_strtab_l1_desc *l1_desc;
+		int idx;
+
+		/* Two-level walk */
+		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		l1_desc = &cfg->l1_desc[idx];
+		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
+		step = &l1_desc->l2ptr[idx];
+	} else {
+		/* Simple linear lookup */
+		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+	}
+
+	return step;
+}
+
+static int arm_smmu_install_ste_for_group(struct arm_smmu_group *smmu_group)
+{
+	int i;
+	struct arm_smmu_domain *smmu_domain = smmu_group->domain;
+	struct arm_smmu_strtab_ent *ste = &smmu_group->ste;
+	struct arm_smmu_device *smmu = smmu_group->smmu;
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		ste->s1_cfg = &smmu_domain->s1_cfg;
+		ste->s2_cfg = NULL;
+		arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
+	} else {
+		ste->s1_cfg = NULL;
+		ste->s2_cfg = &smmu_domain->s2_cfg;
+	}
+
+	for (i = 0; i < smmu_group->num_sids; ++i) {
+		u32 sid = smmu_group->sids[i];
+		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+
+		arm_smmu_write_strtab_ent(smmu, sid, step, ste);
+	}
+
+	return 0;
+}
+
+static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	int ret = 0;
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_group *smmu_group = arm_smmu_group_get(dev);
+
+	if (!smmu_group)
+		return -ENOENT;
+
+	/* Already attached to a different domain? */
+	if (smmu_group->domain && smmu_group->domain != smmu_domain)
+		return -EEXIST;
+
+	smmu = smmu_group->smmu;
+	mutex_lock(&smmu_domain->init_mutex);
+
+	if (!smmu_domain->smmu) {
+		smmu_domain->smmu = smmu;
+		ret = arm_smmu_domain_finalise(domain);
+		if (ret) {
+			smmu_domain->smmu = NULL;
+			goto out_unlock;
+		}
+	} else if (smmu_domain->smmu != smmu) {
+		dev_err(dev,
+			"cannot attach to SMMU %s (upstream of %s)\n",
+			dev_name(smmu_domain->smmu->dev),
+			dev_name(smmu->dev));
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+
+	/* Group already attached to this domain? */
+	if (smmu_group->domain)
+		goto out_unlock;
+
+	smmu_group->domain	= smmu_domain;
+	smmu_group->ste.bypass	= false;
+
+	ret = arm_smmu_install_ste_for_group(smmu_group);
+	if (IS_ERR_VALUE(ret))
+		smmu_group->domain = NULL;
+
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_group *smmu_group = arm_smmu_group_get(dev);
+
+	BUG_ON(!smmu_domain);
+	BUG_ON(!smmu_group);
+
+	mutex_lock(&smmu_domain->init_mutex);
+	BUG_ON(smmu_group->domain != smmu_domain);
+
+	smmu_group->ste.bypass = true;
+	if (IS_ERR_VALUE(arm_smmu_install_ste_for_group(smmu_group)))
+		dev_warn(dev, "failed to install bypass STE\n");
+
+	smmu_group->domain = NULL;
+	mutex_unlock(&smmu_domain->init_mutex);
+}
+
+static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			phys_addr_t paddr, size_t size, int prot)
+{
+	int ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return -ENODEV;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->map(ops, iova, paddr, size, prot);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
+}
+
+static size_t
+arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
+{
+	size_t ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->unmap(ops, iova, size);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+	return ret;
+}
+
+static phys_addr_t
+arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
+{
+	phys_addr_t ret;
+	unsigned long flags;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	if (!ops)
+		return 0;
+
+	spin_lock_irqsave(&smmu_domain->pgtbl_lock, flags);
+	ret = ops->iova_to_phys(ops, iova);
+	spin_unlock_irqrestore(&smmu_domain->pgtbl_lock, flags);
+
+	return ret;
+}
+
+static int __arm_smmu_get_pci_sid(struct pci_dev *pdev, u16 alias, void *sidp)
+{
+	*(u32 *)sidp = alias;
+	return 0; /* Continue walking */
+}
+
+static void __arm_smmu_release_pci_iommudata(void *data)
+{
+	kfree(data);
+}
+
+static struct arm_smmu_device *arm_smmu_get_for_pci_dev(struct pci_dev *pdev)
+{
+	struct device_node *of_node;
+	struct arm_smmu_device *curr, *smmu = NULL;
+	struct pci_bus *bus = pdev->bus;
+
+	/* Walk up to the root bus */
+	while (!pci_is_root_bus(bus))
+		bus = bus->parent;
+
+	/* Follow the "iommus" phandle from the host controller */
+	of_node = of_parse_phandle(bus->bridge->parent->of_node, "iommus", 0);
+	if (!of_node)
+		return NULL;
+
+	/* See if we can find an SMMU corresponding to the phandle */
+	spin_lock(&arm_smmu_devices_lock);
+	list_for_each_entry(curr, &arm_smmu_devices, list) {
+		if (curr->dev->of_node == of_node) {
+			smmu = curr;
+			break;
+		}
+	}
+	spin_unlock(&arm_smmu_devices_lock);
+	of_node_put(of_node);
+	return smmu;
+}
+
+static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
+{
+	unsigned long limit = smmu->strtab_cfg.num_l1_ents;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		limit *= 1UL << STRTAB_SPLIT;
+
+	return sid < limit;
+}
+
+static int arm_smmu_add_device(struct device *dev)
+{
+	int i, ret;
+	u32 sid, *sids;
+	struct pci_dev *pdev;
+	struct iommu_group *group;
+	struct arm_smmu_group *smmu_group;
+	struct arm_smmu_device *smmu;
+
+	/* We only support PCI, for now */
+	if (!dev_is_pci(dev))
+		return -ENODEV;
+
+	pdev = to_pci_dev(dev);
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	smmu_group = iommu_group_get_iommudata(group);
+	if (!smmu_group) {
+		smmu = arm_smmu_get_for_pci_dev(pdev);
+		if (!smmu) {
+			ret = -ENOENT;
+			goto out_put_group;
+		}
+
+		smmu_group = kzalloc(sizeof(*smmu_group), GFP_KERNEL);
+		if (!smmu_group) {
+			ret = -ENOMEM;
+			goto out_put_group;
+		}
+
+		smmu_group->ste.valid	= true;
+		smmu_group->smmu	= smmu;
+		iommu_group_set_iommudata(group, smmu_group,
+					  __arm_smmu_release_pci_iommudata);
+	} else {
+		smmu = smmu_group->smmu;
+	}
+
+	/* Assume SID == RID until firmware tells us otherwise */
+	pci_for_each_dma_alias(pdev, __arm_smmu_get_pci_sid, &sid);
+	for (i = 0; i < smmu_group->num_sids; ++i) {
+		/* If we already know about this SID, then we're done */
+		if (smmu_group->sids[i] == sid)
+			return 0;
+	}
+
+	/* Check the SID is in range of the SMMU and our stream table */
+	if (!arm_smmu_sid_in_range(smmu, sid)) {
+		ret = -ERANGE;
+		goto out_put_group;
+	}
+
+	/* Ensure l2 strtab is initialised */
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		ret = arm_smmu_init_l2_strtab(smmu, sid);
+		if (ret)
+			goto out_put_group;
+	}
+
+	/* Resize the SID array for the group */
+	smmu_group->num_sids++;
+	sids = krealloc(smmu_group->sids, smmu_group->num_sids * sizeof(*sids),
+			GFP_KERNEL);
+	if (!sids) {
+		smmu_group->num_sids--;
+		ret = -ENOMEM;
+		goto out_put_group;
+	}
+
+	/* Add the new SID */
+	sids[smmu_group->num_sids - 1] = sid;
+	smmu_group->sids = sids;
+	return 0;
+
+out_put_group:
+	iommu_group_put(group);
+	return ret;
+}
+
+static void arm_smmu_remove_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+		return 0;
+	default:
+		return -ENODEV;
+	}
+}
+
+static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
+				    enum iommu_attr attr, void *data)
+{
+	int ret = 0;
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	mutex_lock(&smmu_domain->init_mutex);
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		if (smmu_domain->smmu) {
+			ret = -EPERM;
+			goto out_unlock;
+		}
+
+		if (*(int *)data)
+			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		else
+			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+
+		break;
+	default:
+		ret = -ENODEV;
+	}
+
+out_unlock:
+	mutex_unlock(&smmu_domain->init_mutex);
+	return ret;
+}
+
+static struct iommu_ops arm_smmu_ops = {
+	.capable		= arm_smmu_capable,
+	.domain_alloc		= arm_smmu_domain_alloc,
+	.domain_free		= arm_smmu_domain_free,
+	.attach_dev		= arm_smmu_attach_dev,
+	.detach_dev		= arm_smmu_detach_dev,
+	.map			= arm_smmu_map,
+	.unmap			= arm_smmu_unmap,
+	.iova_to_phys		= arm_smmu_iova_to_phys,
+	.add_device		= arm_smmu_add_device,
+	.remove_device		= arm_smmu_remove_device,
+	.domain_get_attr	= arm_smmu_domain_get_attr,
+	.domain_set_attr	= arm_smmu_domain_set_attr,
+	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
+};
+
+/* Probing and initialisation functions */
+static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
+				   struct arm_smmu_queue *q,
+				   unsigned long prod_off,
+				   unsigned long cons_off,
+				   size_t dwords)
+{
+	size_t qsz = ((1 << q->max_n_shift) * dwords) << 3;
+
+	q->base = dma_alloc_coherent(smmu->dev, qsz, &q->base_dma, GFP_KERNEL);
+	if (!q->base) {
+		dev_err(smmu->dev, "failed to allocate queue (0x%zx bytes)\n",
+			qsz);
+		return -ENOMEM;
+	}
+
+	q->prod_reg	= smmu->base + prod_off;
+	q->cons_reg	= smmu->base + cons_off;
+	q->ent_dwords	= dwords;
+
+	q->q_base  = Q_BASE_RWA;
+	q->q_base |= q->base_dma & Q_BASE_ADDR_MASK << Q_BASE_ADDR_SHIFT;
+	q->q_base |= (q->max_n_shift & Q_BASE_LOG2SIZE_MASK)
+		     << Q_BASE_LOG2SIZE_SHIFT;
+
+	q->prod = q->cons = 0;
+	return 0;
+}
+
+static void arm_smmu_free_one_queue(struct arm_smmu_device *smmu,
+				    struct arm_smmu_queue *q)
+{
+	size_t qsz = ((1 << q->max_n_shift) * q->ent_dwords) << 3;
+
+	dma_free_coherent(smmu->dev, qsz, q->base, q->base_dma);
+}
+
+static void arm_smmu_free_queues(struct arm_smmu_device *smmu)
+{
+	arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
+	arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
+
+	if (smmu->features & ARM_SMMU_FEAT_PRI)
+		arm_smmu_free_one_queue(smmu, &smmu->priq.q);
+}
+
+static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	/* cmdq */
+	spin_lock_init(&smmu->cmdq.lock);
+	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
+				      ARM_SMMU_CMDQ_CONS, CMDQ_ENT_DWORDS);
+	if (ret)
+		goto out;
+
+	/* evtq */
+	ret = arm_smmu_init_one_queue(smmu, &smmu->evtq.q, ARM_SMMU_EVTQ_PROD,
+				      ARM_SMMU_EVTQ_CONS, EVTQ_ENT_DWORDS);
+	if (ret)
+		goto out_free_cmdq;
+
+	/* priq */
+	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
+		return 0;
+
+	ret = arm_smmu_init_one_queue(smmu, &smmu->priq.q, ARM_SMMU_PRIQ_PROD,
+				      ARM_SMMU_PRIQ_CONS, PRIQ_ENT_DWORDS);
+	if (ret)
+		goto out_free_evtq;
+
+	return 0;
+
+out_free_evtq:
+	arm_smmu_free_one_queue(smmu, &smmu->evtq.q);
+out_free_cmdq:
+	arm_smmu_free_one_queue(smmu, &smmu->cmdq.q);
+out:
+	return ret;
+}
+
+static void arm_smmu_free_l2_strtab(struct arm_smmu_device *smmu)
+{
+	int i;
+	size_t size;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
+	for (i = 0; i < cfg->num_l1_ents; ++i) {
+		struct arm_smmu_strtab_l1_desc *desc = &cfg->l1_desc[i];
+
+		if (!desc->l2ptr)
+			continue;
+
+		dma_free_coherent(smmu->dev, size, desc->l2ptr,
+				  desc->l2ptr_dma);
+	}
+}
+
+static int arm_smmu_init_l1_strtab(struct arm_smmu_device *smmu)
+{
+	unsigned int i;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	size_t size = sizeof(*cfg->l1_desc) * cfg->num_l1_ents;
+	void *strtab = smmu->strtab_cfg.strtab;
+
+	cfg->l1_desc = devm_kzalloc(smmu->dev, size, GFP_KERNEL);
+	if (!cfg->l1_desc) {
+		dev_err(smmu->dev, "failed to allocate l1 stream table desc\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < cfg->num_l1_ents; ++i) {
+		arm_smmu_write_strtab_l1_desc(strtab, &cfg->l1_desc[i]);
+		strtab += STRTAB_L1_DESC_DWORDS << 3;
+	}
+
+	return 0;
+}
+
+static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
+{
+	void *strtab;
+	u64 reg;
+	u32 size;
+	int ret;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	/* Calculate the L1 size, capped to the SIDSIZE */
+	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
+	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
+	if (size + STRTAB_SPLIT < smmu->sid_bits)
+		dev_warn(smmu->dev,
+			 "2-level strtab only covers %u/%u bits of SID\n",
+			 size + STRTAB_SPLIT, smmu->sid_bits);
+
+	cfg->num_l1_ents = 1 << size;
+	size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
+	strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+				     GFP_KERNEL);
+	if (!strtab) {
+		dev_err(smmu->dev,
+			"failed to allocate l1 stream table (%u bytes)\n",
+			size);
+		return -ENOMEM;
+	}
+	cfg->strtab = strtab;
+
+	/* Configure strtab_base_cfg for 2 levels */
+	reg  = STRTAB_BASE_CFG_FMT_2LVL;
+	reg |= (size & STRTAB_BASE_CFG_LOG2SIZE_MASK)
+		<< STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
+	reg |= (STRTAB_SPLIT & STRTAB_BASE_CFG_SPLIT_MASK)
+		<< STRTAB_BASE_CFG_SPLIT_SHIFT;
+	cfg->strtab_base_cfg = reg;
+
+	ret = arm_smmu_init_l1_strtab(smmu);
+	if (ret)
+		dma_free_coherent(smmu->dev,
+				  cfg->num_l1_ents *
+				  (STRTAB_L1_DESC_DWORDS << 3),
+				  strtab,
+				  cfg->strtab_dma);
+	return ret;
+}
+
+static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
+{
+	void *strtab;
+	u64 reg;
+	u32 size;
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+
+	size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
+	strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+				     GFP_KERNEL);
+	if (!strtab) {
+		dev_err(smmu->dev,
+			"failed to allocate linear stream table (%u bytes)\n",
+			size);
+		return -ENOMEM;
+	}
+	cfg->strtab = strtab;
+	cfg->num_l1_ents = 1 << smmu->sid_bits;
+
+	/* Configure strtab_base_cfg for a linear table covering all SIDs */
+	reg  = STRTAB_BASE_CFG_FMT_LINEAR;
+	reg |= (smmu->sid_bits & STRTAB_BASE_CFG_LOG2SIZE_MASK)
+		<< STRTAB_BASE_CFG_LOG2SIZE_SHIFT;
+	cfg->strtab_base_cfg = reg;
+
+	arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents);
+	return 0;
+}
+
+static int arm_smmu_init_strtab(struct arm_smmu_device *smmu)
+{
+	u64 reg;
+	int ret;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB)
+		ret = arm_smmu_init_strtab_2lvl(smmu);
+	else
+		ret = arm_smmu_init_strtab_linear(smmu);
+
+	if (ret)
+		return ret;
+
+	/* Set the strtab base address */
+	reg  = smmu->strtab_cfg.strtab_dma &
+	       STRTAB_BASE_ADDR_MASK << STRTAB_BASE_ADDR_SHIFT;
+	reg |= STRTAB_BASE_RA;
+	smmu->strtab_cfg.strtab_base = reg;
+
+	/* Allocate the first VMID for stage-2 bypass STEs */
+	set_bit(0, smmu->vmid_map);
+	return 0;
+}
+
+static void arm_smmu_free_strtab(struct arm_smmu_device *smmu)
+{
+	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
+	u32 size = cfg->num_l1_ents;
+
+	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+		arm_smmu_free_l2_strtab(smmu);
+		size *= STRTAB_L1_DESC_DWORDS << 3;
+	} else {
+		size *= STRTAB_STE_DWORDS * 3;
+	}
+
+	dma_free_coherent(smmu->dev, size, cfg->strtab, cfg->strtab_dma);
+}
+
+static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	ret = arm_smmu_init_queues(smmu);
+	if (ret)
+		return ret;
+
+	ret = arm_smmu_init_strtab(smmu);
+	if (ret)
+		goto out_free_queues;
+
+	return 0;
+
+out_free_queues:
+	arm_smmu_free_queues(smmu);
+	return ret;
+}
+
+static void arm_smmu_free_structures(struct arm_smmu_device *smmu)
+{
+	arm_smmu_free_strtab(smmu);
+	arm_smmu_free_queues(smmu);
+}
+
+static int arm_smmu_write_reg_sync(struct arm_smmu_device *smmu, u32 val,
+				   unsigned int reg_off, unsigned int ack_off)
+{
+	u32 reg;
+
+	writel_relaxed(val, smmu->base + reg_off);
+	return readl_relaxed_poll_timeout(smmu->base + ack_off, reg, reg == val,
+					  1, ARM_SMMU_POLL_TIMEOUT_US);
+}
+
+static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
+{
+	int ret, irq;
+
+	/* Disable IRQs first */
+	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_IRQ_CTRL,
+				      ARM_SMMU_IRQ_CTRLACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to disable irqs\n");
+		return ret;
+	}
+
+	/* Clear the MSI address regs */
+	writeq_relaxed(0, smmu->base + ARM_SMMU_GERROR_IRQ_CFG0);
+	writeq_relaxed(0, smmu->base + ARM_SMMU_EVTQ_IRQ_CFG0);
+
+	/* Request wired interrupt lines */
+	irq = smmu->evtq.q.irq;
+	if (irq) {
+		ret = devm_request_threaded_irq(smmu->dev, irq,
+						arm_smmu_evtq_handler,
+						arm_smmu_evtq_thread,
+						0, "arm-smmu-v3-evtq", smmu);
+		if (IS_ERR_VALUE(ret))
+			dev_warn(smmu->dev, "failed to enable evtq irq\n");
+	}
+
+	irq = smmu->cmdq.q.irq;
+	if (irq) {
+		ret = devm_request_irq(smmu->dev, irq,
+				       arm_smmu_cmdq_sync_handler, 0,
+				       "arm-smmu-v3-cmdq-sync", smmu);
+		if (IS_ERR_VALUE(ret))
+			dev_warn(smmu->dev, "failed to enable cmdq-sync irq\n");
+	}
+
+	irq = smmu->gerr_irq;
+	if (irq) {
+		ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
+				       0, "arm-smmu-v3-gerror", smmu);
+		if (IS_ERR_VALUE(ret))
+			dev_warn(smmu->dev, "failed to enable gerror irq\n");
+	}
+
+	if (smmu->features & ARM_SMMU_FEAT_PRI) {
+		writeq_relaxed(0, smmu->base + ARM_SMMU_PRIQ_IRQ_CFG0);
+
+		irq = smmu->priq.q.irq;
+		if (irq) {
+			ret = devm_request_threaded_irq(smmu->dev, irq,
+							arm_smmu_priq_handler,
+							arm_smmu_priq_thread,
+							0, "arm-smmu-v3-priq",
+							smmu);
+			if (IS_ERR_VALUE(ret))
+				dev_warn(smmu->dev,
+					 "failed to enable priq irq\n");
+		}
+	}
+
+	/* Enable interrupt generation on the SMMU */
+	ret = arm_smmu_write_reg_sync(smmu,
+				      IRQ_CTRL_EVTQ_IRQEN |
+				      IRQ_CTRL_GERROR_IRQEN,
+				      ARM_SMMU_IRQ_CTRL, ARM_SMMU_IRQ_CTRLACK);
+	if (ret)
+		dev_warn(smmu->dev, "failed to enable irqs\n");
+
+	return 0;
+}
+
+static int arm_smmu_device_disable(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	ret = arm_smmu_write_reg_sync(smmu, 0, ARM_SMMU_CR0, ARM_SMMU_CR0ACK);
+	if (ret)
+		dev_err(smmu->dev, "failed to clear cr0\n");
+
+	return ret;
+}
+
+static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
+{
+	int ret;
+	u32 reg, enables;
+	struct arm_smmu_cmdq_ent cmd;
+
+	/* Clear CR0 and sync (disables SMMU and queue processing) */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_CR0);
+	if (reg & CR0_SMMUEN)
+		dev_warn(smmu->dev, "SMMU currently enabled! Resetting...\n");
+
+	ret = arm_smmu_device_disable(smmu);
+	if (ret)
+		return ret;
+
+	/* CR1 (table and queue memory attributes) */
+	reg = (CR1_SH_ISH << CR1_TABLE_SH_SHIFT) |
+	      (CR1_CACHE_WB << CR1_TABLE_OC_SHIFT) |
+	      (CR1_CACHE_WB << CR1_TABLE_IC_SHIFT) |
+	      (CR1_SH_ISH << CR1_QUEUE_SH_SHIFT) |
+	      (CR1_CACHE_WB << CR1_QUEUE_OC_SHIFT) |
+	      (CR1_CACHE_WB << CR1_QUEUE_IC_SHIFT);
+	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
+
+	/* CR2 (random crap) */
+	reg = CR2_PTM | CR2_RECINVSID | CR2_E2H;
+	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
+
+	/* Stream table */
+	writeq_relaxed(smmu->strtab_cfg.strtab_base,
+		       smmu->base + ARM_SMMU_STRTAB_BASE);
+	writel_relaxed(smmu->strtab_cfg.strtab_base_cfg,
+		       smmu->base + ARM_SMMU_STRTAB_BASE_CFG);
+
+	/* Command queue */
+	writeq_relaxed(smmu->cmdq.q.q_base, smmu->base + ARM_SMMU_CMDQ_BASE);
+	writel_relaxed(smmu->cmdq.q.prod, smmu->base + ARM_SMMU_CMDQ_PROD);
+	writel_relaxed(smmu->cmdq.q.cons, smmu->base + ARM_SMMU_CMDQ_CONS);
+
+	enables = CR0_CMDQEN;
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable command queue\n");
+		return ret;
+	}
+
+	/* Invalidate any cached configuration */
+	cmd.opcode = CMDQ_OP_CFGI_ALL;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	cmd.opcode = CMDQ_OP_CMD_SYNC;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+
+	/* Invalidate any stale TLB entries */
+	if (smmu->features & ARM_SMMU_FEAT_HYP) {
+		cmd.opcode = CMDQ_OP_TLBI_EL2_ALL;
+		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	}
+
+	cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	cmd.opcode = CMDQ_OP_CMD_SYNC;
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+
+	/* Event queue */
+	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
+	writel_relaxed(smmu->evtq.q.prod, smmu->base + ARM_SMMU_EVTQ_PROD);
+	writel_relaxed(smmu->evtq.q.cons, smmu->base + ARM_SMMU_EVTQ_CONS);
+
+	enables |= CR0_EVTQEN;
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable event queue\n");
+		return ret;
+	}
+
+	/* PRI queue */
+	if (smmu->features & ARM_SMMU_FEAT_PRI) {
+		writeq_relaxed(smmu->priq.q.q_base,
+			       smmu->base + ARM_SMMU_PRIQ_BASE);
+		writel_relaxed(smmu->priq.q.prod,
+			       smmu->base + ARM_SMMU_PRIQ_PROD);
+		writel_relaxed(smmu->priq.q.cons,
+			       smmu->base + ARM_SMMU_PRIQ_CONS);
+
+		enables |= CR0_PRIQEN;
+		ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+					      ARM_SMMU_CR0ACK);
+		if (ret) {
+			dev_err(smmu->dev, "failed to enable PRI queue\n");
+			return ret;
+		}
+	}
+
+	ret = arm_smmu_setup_irqs(smmu);
+	if (ret) {
+		dev_err(smmu->dev, "failed to setup irqs\n");
+		return ret;
+	}
+
+	/* Enable the SMMU interface */
+	enables |= CR0_SMMUEN;
+	ret = arm_smmu_write_reg_sync(smmu, enables, ARM_SMMU_CR0,
+				      ARM_SMMU_CR0ACK);
+	if (ret) {
+		dev_err(smmu->dev, "failed to enable SMMU interface\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
+{
+	u32 reg;
+	bool coherent;
+	unsigned long pgsize_bitmap = 0;
+
+	/* IDR0 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);
+
+	/* 2-level structures */
+	if ((reg & IDR0_ST_LVL_MASK << IDR0_ST_LVL_SHIFT) == IDR0_ST_LVL_2LVL)
+		smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB;
+
+	if (reg & IDR0_CD2L)
+		smmu->features |= ARM_SMMU_FEAT_2_LVL_CDTAB;
+
+	/*
+	 * Translation table endianness.
+	 * We currently require the same endianness as the CPU, but this
+	 * could be changed later by adding a new IO_PGTABLE_QUIRK.
+	 */
+	switch (reg & IDR0_TTENDIAN_MASK << IDR0_TTENDIAN_SHIFT) {
+	case IDR0_TTENDIAN_MIXED:
+		smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE;
+		break;
+#ifdef __BIG_ENDIAN
+	case IDR0_TTENDIAN_BE:
+		smmu->features |= ARM_SMMU_FEAT_TT_BE;
+		break;
+#else
+	case IDR0_TTENDIAN_LE:
+		smmu->features |= ARM_SMMU_FEAT_TT_LE;
+		break;
+#endif
+	default:
+		dev_err(smmu->dev, "unknown/unsupported TT endianness!\n");
+		return -ENXIO;
+	}
+
+	/* Boolean feature flags */
+	if (IS_ENABLED(CONFIG_PCI_PRI) && reg & IDR0_PRI)
+		smmu->features |= ARM_SMMU_FEAT_PRI;
+
+	if (IS_ENABLED(CONFIG_PCI_ATS) && reg & IDR0_ATS)
+		smmu->features |= ARM_SMMU_FEAT_ATS;
+
+	if (reg & IDR0_SEV)
+		smmu->features |= ARM_SMMU_FEAT_SEV;
+
+	if (reg & IDR0_MSI)
+		smmu->features |= ARM_SMMU_FEAT_MSI;
+
+	if (reg & IDR0_HYP)
+		smmu->features |= ARM_SMMU_FEAT_HYP;
+
+	/*
+	 * The dma-coherent property is used in preference to the ID
+	 * register, but warn on mismatch.
+	 */
+	coherent = of_dma_is_coherent(smmu->dev->of_node);
+	if (coherent)
+		smmu->features |= ARM_SMMU_FEAT_COHERENCY;
+
+	if (!!(reg & IDR0_COHACC) != coherent)
+		dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
+			 coherent ? "true" : "false");
+
+	if (reg & IDR0_STALL_MODEL)
+		smmu->features |= ARM_SMMU_FEAT_STALLS;
+
+	if (reg & IDR0_S1P)
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
+
+	if (reg & IDR0_S2P)
+		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+
+	if (!(reg & (IDR0_S1P | IDR0_S2P))) {
+		dev_err(smmu->dev, "no translation support!\n");
+		return -ENXIO;
+	}
+
+	/* We only support the AArch64 table format at present */
+	if ((reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) < IDR0_TTF_AARCH64) {
+		dev_err(smmu->dev, "AArch64 table format not supported!\n");
+		return -ENXIO;
+	}
+
+	/* ASID/VMID sizes */
+	smmu->asid_bits = reg & IDR0_ASID16 ? 16 : 8;
+	smmu->vmid_bits = reg & IDR0_VMID16 ? 16 : 8;
+
+	/* IDR1 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR1);
+	if (reg & (IDR1_TABLES_PRESET | IDR1_QUEUES_PRESET | IDR1_REL)) {
+		dev_err(smmu->dev, "embedded implementation not supported\n");
+		return -ENXIO;
+	}
+
+	/* Queue sizes, capped at 4k */
+	smmu->cmdq.q.max_n_shift = min((u32)CMDQ_MAX_SZ_SHIFT,
+				       reg >> IDR1_CMDQ_SHIFT & IDR1_CMDQ_MASK);
+	if (!smmu->cmdq.q.max_n_shift) {
+		/* Odd alignment restrictions on the base, so ignore for now */
+		dev_err(smmu->dev, "unit-length command queue not supported\n");
+		return -ENXIO;
+	}
+
+	smmu->evtq.q.max_n_shift = min((u32)EVTQ_MAX_SZ_SHIFT,
+				       reg >> IDR1_EVTQ_SHIFT & IDR1_EVTQ_MASK);
+	smmu->priq.q.max_n_shift = min((u32)PRIQ_MAX_SZ_SHIFT,
+				       reg >> IDR1_PRIQ_SHIFT & IDR1_PRIQ_MASK);
+
+	/* SID/SSID sizes */
+	smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
+	smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
+
+	/* IDR5 */
+	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
+
+	/* Maximum number of outstanding stalls */
+	smmu->evtq.max_stalls = reg >> IDR5_STALL_MAX_SHIFT
+				& IDR5_STALL_MAX_MASK;
+
+	/* Page sizes */
+	if (reg & IDR5_GRAN64K)
+		pgsize_bitmap |= SZ_64K | SZ_512M;
+	if (reg & IDR5_GRAN16K)
+		pgsize_bitmap |= SZ_16K | SZ_32M;
+	if (reg & IDR5_GRAN4K)
+		pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G;
+
+	arm_smmu_ops.pgsize_bitmap &= pgsize_bitmap;
+
+	/* Output address size */
+	switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) {
+	case IDR5_OAS_32_BIT:
+		smmu->oas = 32;
+		break;
+	case IDR5_OAS_36_BIT:
+		smmu->oas = 36;
+		break;
+	case IDR5_OAS_40_BIT:
+		smmu->oas = 40;
+		break;
+	case IDR5_OAS_42_BIT:
+		smmu->oas = 42;
+		break;
+	case IDR5_OAS_44_BIT:
+		smmu->oas = 44;
+		break;
+	case IDR5_OAS_48_BIT:
+		smmu->oas = 48;
+		break;
+	default:
+		dev_err(smmu->dev, "unknown output address size!\n");
+		return -ENXIO;
+	}
+
+	/* Set the DMA mask for our table walker */
+	if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas)))
+		dev_warn(smmu->dev,
+			 "failed to set DMA mask for table walker\n");
+
+	if (!smmu->ias)
+		smmu->ias = smmu->oas;
+
+	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
+		 smmu->ias, smmu->oas, smmu->features);
+	return 0;
+}
+
+static int arm_smmu_device_dt_probe(struct platform_device *pdev)
+{
+	int irq, ret;
+	struct resource *res;
+	struct arm_smmu_device *smmu;
+	struct device *dev = &pdev->dev;
+
+	smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL);
+	if (!smmu) {
+		dev_err(dev, "failed to allocate arm_smmu_device\n");
+		return -ENOMEM;
+	}
+	smmu->dev = dev;
+
+	/* Base address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (resource_size(res) + 1 < SZ_128K) {
+		dev_err(dev, "MMIO region too small (%pr)\n", res);
+		return -EINVAL;
+	}
+
+	smmu->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(smmu->base))
+		return PTR_ERR(smmu->base);
+
+	/* Interrupt lines */
+	irq = platform_get_irq_byname(pdev, "eventq");
+	if (irq > 0)
+		smmu->evtq.q.irq = irq;
+
+	irq = platform_get_irq_byname(pdev, "priq");
+	if (irq > 0)
+		smmu->priq.q.irq = irq;
+
+	irq = platform_get_irq_byname(pdev, "cmdq-sync");
+	if (irq > 0)
+		smmu->cmdq.q.irq = irq;
+
+	irq = platform_get_irq_byname(pdev, "gerror");
+	if (irq > 0)
+		smmu->gerr_irq = irq;
+
+	/* Probe the h/w */
+	ret = arm_smmu_device_probe(smmu);
+	if (ret)
+		return ret;
+
+	/* Initialise in-memory data structures */
+	ret = arm_smmu_init_structures(smmu);
+	if (ret)
+		return ret;
+
+	/* Reset the device */
+	ret = arm_smmu_device_reset(smmu);
+	if (ret)
+		goto out_free_structures;
+
+	/* Record our private device structure */
+	INIT_LIST_HEAD(&smmu->list);
+	spin_lock(&arm_smmu_devices_lock);
+	list_add(&smmu->list, &arm_smmu_devices);
+	spin_unlock(&arm_smmu_devices_lock);
+	return 0;
+
+out_free_structures:
+	arm_smmu_free_structures(smmu);
+	return ret;
+}
+
+static int arm_smmu_device_remove(struct platform_device *pdev)
+{
+	struct arm_smmu_device *curr, *smmu = NULL;
+	struct device *dev = &pdev->dev;
+
+	spin_lock(&arm_smmu_devices_lock);
+	list_for_each_entry(curr, &arm_smmu_devices, list) {
+		if (curr->dev == dev) {
+			smmu = curr;
+			list_del(&smmu->list);
+			break;
+		}
+	}
+	spin_unlock(&arm_smmu_devices_lock);
+
+	if (!smmu)
+		return -ENODEV;
+
+	arm_smmu_device_disable(smmu);
+	arm_smmu_free_structures(smmu);
+	return 0;
+}
+
+static struct of_device_id arm_smmu_of_match[] = {
+	{ .compatible = "arm,smmu-v3", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
+
+static struct platform_driver arm_smmu_driver = {
+	.driver	= {
+		.name		= "arm-smmu-v3",
+		.of_match_table	= of_match_ptr(arm_smmu_of_match),
+	},
+	.probe	= arm_smmu_device_dt_probe,
+	.remove	= arm_smmu_device_remove,
+};
+
+static int __init arm_smmu_init(void)
+{
+	struct device_node *np;
+	int ret;
+
+	np = of_find_matching_node(NULL, arm_smmu_of_match);
+	if (!np)
+		return 0;
+
+	of_node_put(np);
+
+	ret = platform_driver_register(&arm_smmu_driver);
+	if (ret)
+		return ret;
+
+	return bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+}
+
+static void __exit arm_smmu_exit(void)
+{
+	return platform_driver_unregister(&arm_smmu_driver);
+}
+
+subsys_initcall(arm_smmu_init);
+module_exit(arm_smmu_exit);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
+MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 9f7e1d34a32b..dce041b1c139 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -202,8 +202,7 @@
 #define ARM_SMMU_CB_S1_TLBIVAL		0x620
 #define ARM_SMMU_CB_S2_TLBIIPAS2	0x630
 #define ARM_SMMU_CB_S2_TLBIIPAS2L	0x638
-#define ARM_SMMU_CB_ATS1PR_LO		0x800
-#define ARM_SMMU_CB_ATS1PR_HI		0x804
+#define ARM_SMMU_CB_ATS1PR		0x800
 #define ARM_SMMU_CB_ATSR		0x8f0
 
 #define SCTLR_S1_ASIDPNE		(1 << 12)
@@ -224,14 +223,7 @@
 #define RESUME_TERMINATE		(1 << 0)
 
 #define TTBCR2_SEP_SHIFT		15
-#define TTBCR2_SEP_MASK			0x7
-
-#define TTBCR2_ADDR_32			0
-#define TTBCR2_ADDR_36			1
-#define TTBCR2_ADDR_40			2
-#define TTBCR2_ADDR_42			3
-#define TTBCR2_ADDR_44			4
-#define TTBCR2_ADDR_48			5
+#define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
 
 #define TTBRn_HI_ASID_SHIFT            16
 
@@ -254,7 +246,7 @@
 #define FSYNR0_WNR			(1 << 4)
 
 static int force_stage;
-module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+module_param_named(force_stage, force_stage, int, S_IRUGO);
 MODULE_PARM_DESC(force_stage,
 	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
 
@@ -793,26 +785,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
 		if (smmu->version > ARM_SMMU_V1) {
 			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
-			switch (smmu->va_size) {
-			case 32:
-				reg |= (TTBCR2_ADDR_32 << TTBCR2_SEP_SHIFT);
-				break;
-			case 36:
-				reg |= (TTBCR2_ADDR_36 << TTBCR2_SEP_SHIFT);
-				break;
-			case 40:
-				reg |= (TTBCR2_ADDR_40 << TTBCR2_SEP_SHIFT);
-				break;
-			case 42:
-				reg |= (TTBCR2_ADDR_42 << TTBCR2_SEP_SHIFT);
-				break;
-			case 44:
-				reg |= (TTBCR2_ADDR_44 << TTBCR2_SEP_SHIFT);
-				break;
-			case 48:
-				reg |= (TTBCR2_ADDR_48 << TTBCR2_SEP_SHIFT);
-				break;
-			}
+			reg |= TTBCR2_SEP_UPSTREAM;
 			writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR2);
 		}
 	} else {
@@ -1255,18 +1228,18 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 	void __iomem *cb_base;
 	u32 tmp;
 	u64 phys;
+	unsigned long va;
 
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
 
-	if (smmu->version == 1) {
-		u32 reg = iova & ~0xfff;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
-	} else {
-		u32 reg = iova & ~0xfff;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
-		reg = ((u64)iova & ~0xfff) >> 32;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_HI);
-	}
+	/* ATS1 registers can only be written atomically */
+	va = iova & ~0xfffUL;
+#ifdef CONFIG_64BIT
+	if (smmu->version == ARM_SMMU_V2)
+		writeq_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
+	else
+#endif
+		writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
 
 	if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
 				      !(tmp & ATSR_ACTIVE), 5, 50)) {
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 9847613085e1..c9db04d4ef39 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -26,7 +26,7 @@
  * These routines are used by both DMA-remapping and Interrupt-remapping
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* has to precede printk.h */
+#define pr_fmt(fmt)     "DMAR: " fmt
 
 #include <linux/pci.h>
 #include <linux/dmar.h>
@@ -555,7 +555,7 @@ static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
 			break;
 		} else if (next > end) {
 			/* Avoid passing table end */
-			pr_warn(FW_BUG "record passes table end\n");
+			pr_warn(FW_BUG "Record passes table end\n");
 			ret = -EINVAL;
 			break;
 		}
@@ -802,7 +802,7 @@ int __init dmar_table_init(void)
 		ret = parse_dmar_table();
 		if (ret < 0) {
 			if (ret != -ENODEV)
-				pr_info("parse DMAR table failure.\n");
+				pr_info("Parse DMAR table failure.\n");
 		} else  if (list_empty(&dmar_drhd_units)) {
 			pr_info("No DMAR devices found\n");
 			ret = -ENODEV;
@@ -847,7 +847,7 @@ dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
 	else
 		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
 	if (!addr) {
-		pr_warn("IOMMU: can't validate: %llx\n", drhd->address);
+		pr_warn("Can't validate DRHD address: %llx\n", drhd->address);
 		return -EINVAL;
 	}
 
@@ -921,14 +921,14 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 	iommu->reg_size = VTD_PAGE_SIZE;
 
 	if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) {
-		pr_err("IOMMU: can't reserve memory\n");
+		pr_err("Can't reserve memory\n");
 		err = -EBUSY;
 		goto out;
 	}
 
 	iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
 	if (!iommu->reg) {
-		pr_err("IOMMU: can't map the region\n");
+		pr_err("Can't map the region\n");
 		err = -ENOMEM;
 		goto release;
 	}
@@ -952,13 +952,13 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 		iommu->reg_size = map_size;
 		if (!request_mem_region(iommu->reg_phys, iommu->reg_size,
 					iommu->name)) {
-			pr_err("IOMMU: can't reserve memory\n");
+			pr_err("Can't reserve memory\n");
 			err = -EBUSY;
 			goto out;
 		}
 		iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
 		if (!iommu->reg) {
-			pr_err("IOMMU: can't map the region\n");
+			pr_err("Can't map the region\n");
 			err = -ENOMEM;
 			goto release;
 		}
@@ -1014,14 +1014,14 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 		return -ENOMEM;
 
 	if (dmar_alloc_seq_id(iommu) < 0) {
-		pr_err("IOMMU: failed to allocate seq_id\n");
+		pr_err("Failed to allocate seq_id\n");
 		err = -ENOSPC;
 		goto error;
 	}
 
 	err = map_iommu(iommu, drhd->reg_base_addr);
 	if (err) {
-		pr_err("IOMMU: failed to map %s\n", iommu->name);
+		pr_err("Failed to map %s\n", iommu->name);
 		goto error_free_seq_id;
 	}
 
@@ -1045,8 +1045,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	iommu->node = -1;
 
 	ver = readl(iommu->reg + DMAR_VER_REG);
-	pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
-		iommu->seq_id,
+	pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
+		iommu->name,
 		(unsigned long long)drhd->reg_base_addr,
 		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
 		(unsigned long long)iommu->cap,
@@ -1087,8 +1087,8 @@ static void free_iommu(struct intel_iommu *iommu)
 
 	if (iommu->irq) {
 		free_irq(iommu->irq, iommu);
-		irq_set_handler_data(iommu->irq, NULL);
 		dmar_free_hwirq(iommu->irq);
+		iommu->irq = 0;
 	}
 
 	if (iommu->qi) {
@@ -1642,26 +1642,17 @@ int dmar_set_interrupt(struct intel_iommu *iommu)
 	if (iommu->irq)
 		return 0;
 
-	irq = dmar_alloc_hwirq();
-	if (irq <= 0) {
-		pr_err("IOMMU: no free vectors\n");
+	irq = dmar_alloc_hwirq(iommu->seq_id, iommu->node, iommu);
+	if (irq > 0) {
+		iommu->irq = irq;
+	} else {
+		pr_err("No free IRQ vectors\n");
 		return -EINVAL;
 	}
 
-	irq_set_handler_data(irq, iommu);
-	iommu->irq = irq;
-
-	ret = arch_setup_dmar_msi(irq);
-	if (ret) {
-		irq_set_handler_data(irq, NULL);
-		iommu->irq = 0;
-		dmar_free_hwirq(irq);
-		return ret;
-	}
-
 	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
 	if (ret)
-		pr_err("IOMMU: can't request irq\n");
+		pr_err("Can't request irq\n");
 	return ret;
 }
 
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 3e898504a7c4..97c41b8ab5d9 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -12,21 +12,22 @@
 #define DEBUG
 #endif
 
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/pm_runtime.h>
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/mm.h>
+#include <linux/io.h>
 #include <linux/iommu.h>
-#include <linux/errno.h>
+#include <linux/interrupt.h>
 #include <linux/list.h>
-#include <linux/memblock.h>
-#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_iommu.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
 
 #include <asm/cacheflush.h>
+#include <asm/dma-iommu.h>
 #include <asm/pgtable.h>
 
 typedef u32 sysmmu_iova_t;
@@ -184,35 +185,50 @@ static char *sysmmu_fault_name[SYSMMU_FAULTS_NUM] = {
 	"UNKNOWN FAULT"
 };
 
-/* attached to dev.archdata.iommu of the master device */
+/*
+ * This structure is attached to dev.archdata.iommu of the master device
+ * on device add, contains a list of SYSMMU controllers defined by device tree,
+ * which are bound to given master device. It is usually referenced by 'owner'
+ * pointer.
+*/
 struct exynos_iommu_owner {
-	struct list_head client; /* entry of exynos_iommu_domain.clients */
-	struct device *dev;
-	struct device *sysmmu;
-	struct iommu_domain *domain;
-	void *vmm_data;         /* IO virtual memory manager's data */
-	spinlock_t lock;        /* Lock to preserve consistency of System MMU */
+	struct list_head controllers;	/* list of sysmmu_drvdata.owner_node */
 };
 
+/*
+ * This structure exynos specific generalization of struct iommu_domain.
+ * It contains list of SYSMMU controllers from all master devices, which has
+ * been attached to this domain and page tables of IO address space defined by
+ * it. It is usually referenced by 'domain' pointer.
+ */
 struct exynos_iommu_domain {
-	struct list_head clients; /* list of sysmmu_drvdata.node */
-	sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */
-	short *lv2entcnt; /* free lv2 entry counter for each section */
-	spinlock_t lock; /* lock for this structure */
-	spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */
+	struct list_head clients; /* list of sysmmu_drvdata.domain_node */
+	sysmmu_pte_t *pgtable;	/* lv1 page table, 16KB */
+	short *lv2entcnt;	/* free lv2 entry counter for each section */
+	spinlock_t lock;	/* lock for modyfying list of clients */
+	spinlock_t pgtablelock;	/* lock for modifying page table @ pgtable */
 	struct iommu_domain domain; /* generic domain data structure */
 };
 
+/*
+ * This structure hold all data of a single SYSMMU controller, this includes
+ * hw resources like registers and clocks, pointers and list nodes to connect
+ * it to all other structures, internal state and parameters read from device
+ * tree. It is usually referenced by 'data' pointer.
+ */
 struct sysmmu_drvdata {
-	struct device *sysmmu;	/* System MMU's device descriptor */
-	struct device *master;	/* Owner of system MMU */
-	void __iomem *sfrbase;
-	struct clk *clk;
-	struct clk *clk_master;
-	int activations;
-	spinlock_t lock;
-	struct iommu_domain *domain;
-	phys_addr_t pgtable;
+	struct device *sysmmu;		/* SYSMMU controller device */
+	struct device *master;		/* master device (owner) */
+	void __iomem *sfrbase;		/* our registers */
+	struct clk *clk;		/* SYSMMU's clock */
+	struct clk *clk_master;		/* master's device clock */
+	int activations;		/* number of calls to sysmmu_enable */
+	spinlock_t lock;		/* lock for modyfying state */
+	struct exynos_iommu_domain *domain; /* domain we belong to */
+	struct list_head domain_node;	/* node for domain clients list */
+	struct list_head owner_node;	/* node for owner controllers list */
+	phys_addr_t pgtable;		/* assigned page table structure */
+	unsigned int version;		/* our version */
 };
 
 static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
@@ -244,11 +260,6 @@ static void sysmmu_unblock(void __iomem *sfrbase)
 	__raw_writel(CTRL_ENABLE, sfrbase + REG_MMU_CTRL);
 }
 
-static unsigned int __raw_sysmmu_version(struct sysmmu_drvdata *data)
-{
-	return MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
-}
-
 static bool sysmmu_block(void __iomem *sfrbase)
 {
 	int i = 120;
@@ -345,7 +356,7 @@ static irqreturn_t exynos_sysmmu_irq(int irq, void *dev_id)
 		show_fault_information(dev_name(data->sysmmu),
 					itype, base, addr);
 		if (data->domain)
-			ret = report_iommu_fault(data->domain,
+			ret = report_iommu_fault(&data->domain->domain,
 					data->master, addr, itype);
 	}
 
@@ -408,7 +419,7 @@ static void __sysmmu_init_config(struct sysmmu_drvdata *data)
 	unsigned int cfg = CFG_LRU | CFG_QOS(15);
 	unsigned int ver;
 
-	ver = __raw_sysmmu_version(data);
+	ver = MMU_RAW_VER(__raw_readl(data->sfrbase + REG_MMU_VERSION));
 	if (MMU_MAJ_VER(ver) == 3) {
 		if (MMU_MIN_VER(ver) >= 2) {
 			cfg |= CFG_FLPDCACHE;
@@ -422,6 +433,7 @@ static void __sysmmu_init_config(struct sysmmu_drvdata *data)
 	}
 
 	__raw_writel(cfg, data->sfrbase + REG_MMU_CFG);
+	data->version = ver;
 }
 
 static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
@@ -442,8 +454,8 @@ static void __sysmmu_enable_nocount(struct sysmmu_drvdata *data)
 		clk_disable(data->clk_master);
 }
 
-static int __sysmmu_enable(struct sysmmu_drvdata *data,
-			phys_addr_t pgtable, struct iommu_domain *domain)
+static int __sysmmu_enable(struct sysmmu_drvdata *data, phys_addr_t pgtable,
+			   struct exynos_iommu_domain *domain)
 {
 	int ret = 0;
 	unsigned long flags;
@@ -470,77 +482,17 @@ static int __sysmmu_enable(struct sysmmu_drvdata *data,
 	return ret;
 }
 
-/* __exynos_sysmmu_enable: Enables System MMU
- *
- * returns -error if an error occurred and System MMU is not enabled,
- * 0 if the System MMU has been just enabled and 1 if System MMU was already
- * enabled before.
- */
-static int __exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable,
-				  struct iommu_domain *domain)
-{
-	int ret = 0;
-	unsigned long flags;
-	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	struct sysmmu_drvdata *data;
-
-	BUG_ON(!has_sysmmu(dev));
-
-	spin_lock_irqsave(&owner->lock, flags);
-
-	data = dev_get_drvdata(owner->sysmmu);
-
-	ret = __sysmmu_enable(data, pgtable, domain);
-	if (ret >= 0)
-		data->master = dev;
-
-	spin_unlock_irqrestore(&owner->lock, flags);
-
-	return ret;
-}
-
-int exynos_sysmmu_enable(struct device *dev, phys_addr_t pgtable)
-{
-	BUG_ON(!memblock_is_memory(pgtable));
-
-	return __exynos_sysmmu_enable(dev, pgtable, NULL);
-}
-
-static bool exynos_sysmmu_disable(struct device *dev)
-{
-	unsigned long flags;
-	bool disabled = true;
-	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	struct sysmmu_drvdata *data;
-
-	BUG_ON(!has_sysmmu(dev));
-
-	spin_lock_irqsave(&owner->lock, flags);
-
-	data = dev_get_drvdata(owner->sysmmu);
-
-	disabled = __sysmmu_disable(data);
-	if (disabled)
-		data->master = NULL;
-
-	spin_unlock_irqrestore(&owner->lock, flags);
-
-	return disabled;
-}
-
 static void __sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
 					      sysmmu_iova_t iova)
 {
-	if (__raw_sysmmu_version(data) == MAKE_MMU_VER(3, 3))
+	if (data->version == MAKE_MMU_VER(3, 3))
 		__raw_writel(iova | 0x1, data->sfrbase + REG_MMU_FLUSH_ENTRY);
 }
 
-static void sysmmu_tlb_invalidate_flpdcache(struct device *dev,
+static void sysmmu_tlb_invalidate_flpdcache(struct sysmmu_drvdata *data,
 					    sysmmu_iova_t iova)
 {
 	unsigned long flags;
-	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	struct sysmmu_drvdata *data = dev_get_drvdata(owner->sysmmu);
 
 	if (!IS_ERR(data->clk_master))
 		clk_enable(data->clk_master);
@@ -554,14 +506,10 @@ static void sysmmu_tlb_invalidate_flpdcache(struct device *dev,
 		clk_disable(data->clk_master);
 }
 
-static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
-					size_t size)
+static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
+					sysmmu_iova_t iova, size_t size)
 {
-	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	unsigned long flags;
-	struct sysmmu_drvdata *data;
-
-	data = dev_get_drvdata(owner->sysmmu);
 
 	spin_lock_irqsave(&data->lock, flags);
 	if (is_sysmmu_active(data)) {
@@ -580,7 +528,7 @@ static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
 		 * 1MB page can be cached in one of all sets.
 		 * 64KB page can be one of 16 consecutive sets.
 		 */
-		if (MMU_MAJ_VER(__raw_sysmmu_version(data)) == 2)
+		if (MMU_MAJ_VER(data->version) == 2)
 			num_inv = min_t(unsigned int, size / PAGE_SIZE, 64);
 
 		if (sysmmu_block(data->sfrbase)) {
@@ -591,32 +539,8 @@ static void sysmmu_tlb_invalidate_entry(struct device *dev, sysmmu_iova_t iova,
 		if (!IS_ERR(data->clk_master))
 			clk_disable(data->clk_master);
 	} else {
-		dev_dbg(dev, "disabled. Skipping TLB invalidation @ %#x\n",
-			iova);
-	}
-	spin_unlock_irqrestore(&data->lock, flags);
-}
-
-void exynos_sysmmu_tlb_invalidate(struct device *dev)
-{
-	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	unsigned long flags;
-	struct sysmmu_drvdata *data;
-
-	data = dev_get_drvdata(owner->sysmmu);
-
-	spin_lock_irqsave(&data->lock, flags);
-	if (is_sysmmu_active(data)) {
-		if (!IS_ERR(data->clk_master))
-			clk_enable(data->clk_master);
-		if (sysmmu_block(data->sfrbase)) {
-			__sysmmu_tlb_invalidate(data->sfrbase);
-			sysmmu_unblock(data->sfrbase);
-		}
-		if (!IS_ERR(data->clk_master))
-			clk_disable(data->clk_master);
-	} else {
-		dev_dbg(dev, "disabled. Skipping TLB invalidation\n");
+		dev_dbg(data->master,
+			"disabled. Skipping TLB invalidation @ %#x\n", iova);
 	}
 	spin_unlock_irqrestore(&data->lock, flags);
 }
@@ -682,6 +606,36 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int exynos_sysmmu_suspend(struct device *dev)
+{
+	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "suspend\n");
+	if (is_sysmmu_active(data)) {
+		__sysmmu_disable_nocount(data);
+		pm_runtime_put(dev);
+	}
+	return 0;
+}
+
+static int exynos_sysmmu_resume(struct device *dev)
+{
+	struct sysmmu_drvdata *data = dev_get_drvdata(dev);
+
+	dev_dbg(dev, "resume\n");
+	if (is_sysmmu_active(data)) {
+		pm_runtime_get_sync(dev);
+		__sysmmu_enable_nocount(data);
+	}
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops sysmmu_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(exynos_sysmmu_suspend, exynos_sysmmu_resume)
+};
+
 static const struct of_device_id sysmmu_of_match[] __initconst = {
 	{ .compatible	= "samsung,exynos-sysmmu", },
 	{ },
@@ -692,6 +646,7 @@ static struct platform_driver exynos_sysmmu_driver __refdata = {
 	.driver	= {
 		.name		= "exynos-sysmmu",
 		.of_match_table	= sysmmu_of_match,
+		.pm		= &sysmmu_pm_ops,
 	}
 };
 
@@ -704,104 +659,108 @@ static inline void pgtable_flush(void *vastart, void *vaend)
 
 static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 {
-	struct exynos_iommu_domain *exynos_domain;
+	struct exynos_iommu_domain *domain;
 	int i;
 
 	if (type != IOMMU_DOMAIN_UNMANAGED)
 		return NULL;
 
-	exynos_domain = kzalloc(sizeof(*exynos_domain), GFP_KERNEL);
-	if (!exynos_domain)
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
 		return NULL;
 
-	exynos_domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
-	if (!exynos_domain->pgtable)
+	domain->pgtable = (sysmmu_pte_t *)__get_free_pages(GFP_KERNEL, 2);
+	if (!domain->pgtable)
 		goto err_pgtable;
 
-	exynos_domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
-	if (!exynos_domain->lv2entcnt)
+	domain->lv2entcnt = (short *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+	if (!domain->lv2entcnt)
 		goto err_counter;
 
 	/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
 	for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
-		exynos_domain->pgtable[i + 0] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 1] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 2] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 3] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 4] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 5] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 6] = ZERO_LV2LINK;
-		exynos_domain->pgtable[i + 7] = ZERO_LV2LINK;
+		domain->pgtable[i + 0] = ZERO_LV2LINK;
+		domain->pgtable[i + 1] = ZERO_LV2LINK;
+		domain->pgtable[i + 2] = ZERO_LV2LINK;
+		domain->pgtable[i + 3] = ZERO_LV2LINK;
+		domain->pgtable[i + 4] = ZERO_LV2LINK;
+		domain->pgtable[i + 5] = ZERO_LV2LINK;
+		domain->pgtable[i + 6] = ZERO_LV2LINK;
+		domain->pgtable[i + 7] = ZERO_LV2LINK;
 	}
 
-	pgtable_flush(exynos_domain->pgtable, exynos_domain->pgtable + NUM_LV1ENTRIES);
+	pgtable_flush(domain->pgtable, domain->pgtable + NUM_LV1ENTRIES);
 
-	spin_lock_init(&exynos_domain->lock);
-	spin_lock_init(&exynos_domain->pgtablelock);
-	INIT_LIST_HEAD(&exynos_domain->clients);
+	spin_lock_init(&domain->lock);
+	spin_lock_init(&domain->pgtablelock);
+	INIT_LIST_HEAD(&domain->clients);
 
-	exynos_domain->domain.geometry.aperture_start = 0;
-	exynos_domain->domain.geometry.aperture_end   = ~0UL;
-	exynos_domain->domain.geometry.force_aperture = true;
+	domain->domain.geometry.aperture_start = 0;
+	domain->domain.geometry.aperture_end   = ~0UL;
+	domain->domain.geometry.force_aperture = true;
 
-	return &exynos_domain->domain;
+	return &domain->domain;
 
 err_counter:
-	free_pages((unsigned long)exynos_domain->pgtable, 2);
+	free_pages((unsigned long)domain->pgtable, 2);
 err_pgtable:
-	kfree(exynos_domain);
+	kfree(domain);
 	return NULL;
 }
 
-static void exynos_iommu_domain_free(struct iommu_domain *domain)
+static void exynos_iommu_domain_free(struct iommu_domain *iommu_domain)
 {
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
-	struct exynos_iommu_owner *owner;
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	struct sysmmu_drvdata *data, *next;
 	unsigned long flags;
 	int i;
 
-	WARN_ON(!list_empty(&priv->clients));
+	WARN_ON(!list_empty(&domain->clients));
 
-	spin_lock_irqsave(&priv->lock, flags);
+	spin_lock_irqsave(&domain->lock, flags);
 
-	list_for_each_entry(owner, &priv->clients, client) {
-		while (!exynos_sysmmu_disable(owner->dev))
-			; /* until System MMU is actually disabled */
+	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+		if (__sysmmu_disable(data))
+			data->master = NULL;
+		list_del_init(&data->domain_node);
 	}
 
-	while (!list_empty(&priv->clients))
-		list_del_init(priv->clients.next);
-
-	spin_unlock_irqrestore(&priv->lock, flags);
+	spin_unlock_irqrestore(&domain->lock, flags);
 
 	for (i = 0; i < NUM_LV1ENTRIES; i++)
-		if (lv1ent_page(priv->pgtable + i))
+		if (lv1ent_page(domain->pgtable + i))
 			kmem_cache_free(lv2table_kmem_cache,
-				phys_to_virt(lv2table_base(priv->pgtable + i)));
+				phys_to_virt(lv2table_base(domain->pgtable + i)));
 
-	free_pages((unsigned long)priv->pgtable, 2);
-	free_pages((unsigned long)priv->lv2entcnt, 1);
-	kfree(priv);
+	free_pages((unsigned long)domain->pgtable, 2);
+	free_pages((unsigned long)domain->lv2entcnt, 1);
+	kfree(domain);
 }
 
-static int exynos_iommu_attach_device(struct iommu_domain *domain,
+static int exynos_iommu_attach_device(struct iommu_domain *iommu_domain,
 				   struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
-	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	struct sysmmu_drvdata *data;
+	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
 	unsigned long flags;
-	int ret;
+	int ret = -ENODEV;
 
-	spin_lock_irqsave(&priv->lock, flags);
+	if (!has_sysmmu(dev))
+		return -ENODEV;
 
-	ret = __exynos_sysmmu_enable(dev, pagetable, domain);
-	if (ret == 0) {
-		list_add_tail(&owner->client, &priv->clients);
-		owner->domain = domain;
-	}
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		pm_runtime_get_sync(data->sysmmu);
+		ret = __sysmmu_enable(data, pagetable, domain);
+		if (ret >= 0) {
+			data->master = dev;
 
-	spin_unlock_irqrestore(&priv->lock, flags);
+			spin_lock_irqsave(&domain->lock, flags);
+			list_add_tail(&data->domain_node, &domain->clients);
+			spin_unlock_irqrestore(&domain->lock, flags);
+		}
+	}
 
 	if (ret < 0) {
 		dev_err(dev, "%s: Failed to attach IOMMU with pgtable %pa\n",
@@ -815,36 +774,39 @@ static int exynos_iommu_attach_device(struct iommu_domain *domain,
 	return ret;
 }
 
-static void exynos_iommu_detach_device(struct iommu_domain *domain,
+static void exynos_iommu_detach_device(struct iommu_domain *iommu_domain,
 				    struct device *dev)
 {
-	struct exynos_iommu_owner *owner;
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
-	phys_addr_t pagetable = virt_to_phys(priv->pgtable);
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
+	phys_addr_t pagetable = virt_to_phys(domain->pgtable);
+	struct sysmmu_drvdata *data, *next;
 	unsigned long flags;
+	bool found = false;
 
-	spin_lock_irqsave(&priv->lock, flags);
+	if (!has_sysmmu(dev))
+		return;
 
-	list_for_each_entry(owner, &priv->clients, client) {
-		if (owner == dev->archdata.iommu) {
-			if (exynos_sysmmu_disable(dev)) {
-				list_del_init(&owner->client);
-				owner->domain = NULL;
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry_safe(data, next, &domain->clients, domain_node) {
+		if (data->master == dev) {
+			if (__sysmmu_disable(data)) {
+				data->master = NULL;
+				list_del_init(&data->domain_node);
 			}
-			break;
+			pm_runtime_put(data->sysmmu);
+			found = true;
 		}
 	}
+	spin_unlock_irqrestore(&domain->lock, flags);
 
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	if (owner == dev->archdata.iommu)
+	if (found)
 		dev_dbg(dev, "%s: Detached IOMMU with pgtable %pa\n",
 					__func__, &pagetable);
 	else
 		dev_err(dev, "%s: No IOMMU is attached\n", __func__);
 }
 
-static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
+static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 		sysmmu_pte_t *sent, sysmmu_iova_t iova, short *pgcounter)
 {
 	if (lv1ent_section(sent)) {
@@ -862,6 +824,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
 			return ERR_PTR(-ENOMEM);
 
 		*sent = mk_lv1ent_page(virt_to_phys(pent));
+		kmemleak_ignore(pent);
 		*pgcounter = NUM_LV2ENTRIES;
 		pgtable_flush(pent, pent + NUM_LV2ENTRIES);
 		pgtable_flush(sent, sent + 1);
@@ -884,20 +847,19 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *priv,
 		 * not currently mapped.
 		 */
 		if (need_flush_flpd_cache) {
-			struct exynos_iommu_owner *owner;
+			struct sysmmu_drvdata *data;
 
-			spin_lock(&priv->lock);
-			list_for_each_entry(owner, &priv->clients, client)
-				sysmmu_tlb_invalidate_flpdcache(
-							owner->dev, iova);
-			spin_unlock(&priv->lock);
+			spin_lock(&domain->lock);
+			list_for_each_entry(data, &domain->clients, domain_node)
+				sysmmu_tlb_invalidate_flpdcache(data, iova);
+			spin_unlock(&domain->lock);
 		}
 	}
 
 	return page_entry(sent, iova);
 }
 
-static int lv1set_section(struct exynos_iommu_domain *priv,
+static int lv1set_section(struct exynos_iommu_domain *domain,
 			  sysmmu_pte_t *sent, sysmmu_iova_t iova,
 			  phys_addr_t paddr, short *pgcnt)
 {
@@ -922,17 +884,17 @@ static int lv1set_section(struct exynos_iommu_domain *priv,
 
 	pgtable_flush(sent, sent + 1);
 
-	spin_lock(&priv->lock);
+	spin_lock(&domain->lock);
 	if (lv1ent_page_zero(sent)) {
-		struct exynos_iommu_owner *owner;
+		struct sysmmu_drvdata *data;
 		/*
 		 * Flushing FLPD cache in System MMU v3.3 that may cache a FLPD
 		 * entry by speculative prefetch of SLPD which has no mapping.
 		 */
-		list_for_each_entry(owner, &priv->clients, client)
-			sysmmu_tlb_invalidate_flpdcache(owner->dev, iova);
+		list_for_each_entry(data, &domain->clients, domain_node)
+			sysmmu_tlb_invalidate_flpdcache(data, iova);
 	}
-	spin_unlock(&priv->lock);
+	spin_unlock(&domain->lock);
 
 	return 0;
 }
@@ -992,74 +954,75 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
  *   than or equal to 128KiB.
  * - Start address of an I/O virtual region must be aligned by 128KiB.
  */
-static int exynos_iommu_map(struct iommu_domain *domain, unsigned long l_iova,
-			 phys_addr_t paddr, size_t size, int prot)
+static int exynos_iommu_map(struct iommu_domain *iommu_domain,
+			    unsigned long l_iova, phys_addr_t paddr, size_t size,
+			    int prot)
 {
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_pte_t *entry;
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
 	unsigned long flags;
 	int ret = -ENOMEM;
 
-	BUG_ON(priv->pgtable == NULL);
+	BUG_ON(domain->pgtable == NULL);
 
-	spin_lock_irqsave(&priv->pgtablelock, flags);
+	spin_lock_irqsave(&domain->pgtablelock, flags);
 
-	entry = section_entry(priv->pgtable, iova);
+	entry = section_entry(domain->pgtable, iova);
 
 	if (size == SECT_SIZE) {
-		ret = lv1set_section(priv, entry, iova, paddr,
-					&priv->lv2entcnt[lv1ent_offset(iova)]);
+		ret = lv1set_section(domain, entry, iova, paddr,
+				     &domain->lv2entcnt[lv1ent_offset(iova)]);
 	} else {
 		sysmmu_pte_t *pent;
 
-		pent = alloc_lv2entry(priv, entry, iova,
-					&priv->lv2entcnt[lv1ent_offset(iova)]);
+		pent = alloc_lv2entry(domain, entry, iova,
+				      &domain->lv2entcnt[lv1ent_offset(iova)]);
 
 		if (IS_ERR(pent))
 			ret = PTR_ERR(pent);
 		else
 			ret = lv2set_page(pent, paddr, size,
-					&priv->lv2entcnt[lv1ent_offset(iova)]);
+				       &domain->lv2entcnt[lv1ent_offset(iova)]);
 	}
 
 	if (ret)
 		pr_err("%s: Failed(%d) to map %#zx bytes @ %#x\n",
 			__func__, ret, size, iova);
 
-	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
 
 	return ret;
 }
 
-static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *priv,
-						sysmmu_iova_t iova, size_t size)
+static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain,
+					      sysmmu_iova_t iova, size_t size)
 {
-	struct exynos_iommu_owner *owner;
+	struct sysmmu_drvdata *data;
 	unsigned long flags;
 
-	spin_lock_irqsave(&priv->lock, flags);
+	spin_lock_irqsave(&domain->lock, flags);
 
-	list_for_each_entry(owner, &priv->clients, client)
-		sysmmu_tlb_invalidate_entry(owner->dev, iova, size);
+	list_for_each_entry(data, &domain->clients, domain_node)
+		sysmmu_tlb_invalidate_entry(data, iova, size);
 
-	spin_unlock_irqrestore(&priv->lock, flags);
+	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
-static size_t exynos_iommu_unmap(struct iommu_domain *domain,
-					unsigned long l_iova, size_t size)
+static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
+				 unsigned long l_iova, size_t size)
 {
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;
 	sysmmu_pte_t *ent;
 	size_t err_pgsize;
 	unsigned long flags;
 
-	BUG_ON(priv->pgtable == NULL);
+	BUG_ON(domain->pgtable == NULL);
 
-	spin_lock_irqsave(&priv->pgtablelock, flags);
+	spin_lock_irqsave(&domain->pgtablelock, flags);
 
-	ent = section_entry(priv->pgtable, iova);
+	ent = section_entry(domain->pgtable, iova);
 
 	if (lv1ent_section(ent)) {
 		if (WARN_ON(size < SECT_SIZE)) {
@@ -1093,7 +1056,7 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 		*ent = 0;
 		size = SPAGE_SIZE;
 		pgtable_flush(ent, ent + 1);
-		priv->lv2entcnt[lv1ent_offset(iova)] += 1;
+		domain->lv2entcnt[lv1ent_offset(iova)] += 1;
 		goto done;
 	}
 
@@ -1107,15 +1070,15 @@ static size_t exynos_iommu_unmap(struct iommu_domain *domain,
 	pgtable_flush(ent, ent + SPAGES_PER_LPAGE);
 
 	size = LPAGE_SIZE;
-	priv->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
+	domain->lv2entcnt[lv1ent_offset(iova)] += SPAGES_PER_LPAGE;
 done:
-	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
 
-	exynos_iommu_tlb_invalidate_entry(priv, iova, size);
+	exynos_iommu_tlb_invalidate_entry(domain, iova, size);
 
 	return size;
 err:
-	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
 
 	pr_err("%s: Failed: size(%#zx) @ %#x is smaller than page size %#zx\n",
 		__func__, size, iova, err_pgsize);
@@ -1123,17 +1086,17 @@ err:
 	return 0;
 }
 
-static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
+static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
 					  dma_addr_t iova)
 {
-	struct exynos_iommu_domain *priv = to_exynos_domain(domain);
+	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_pte_t *entry;
 	unsigned long flags;
 	phys_addr_t phys = 0;
 
-	spin_lock_irqsave(&priv->pgtablelock, flags);
+	spin_lock_irqsave(&domain->pgtablelock, flags);
 
-	entry = section_entry(priv->pgtable, iova);
+	entry = section_entry(domain->pgtable, iova);
 
 	if (lv1ent_section(entry)) {
 		phys = section_phys(entry) + section_offs(iova);
@@ -1146,7 +1109,7 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *domain,
 			phys = spage_phys(entry) + spage_offs(iova);
 	}
 
-	spin_unlock_irqrestore(&priv->pgtablelock, flags);
+	spin_unlock_irqrestore(&domain->pgtablelock, flags);
 
 	return phys;
 }
@@ -1156,6 +1119,9 @@ static int exynos_iommu_add_device(struct device *dev)
 	struct iommu_group *group;
 	int ret;
 
+	if (!has_sysmmu(dev))
+		return -ENODEV;
+
 	group = iommu_group_get(dev);
 
 	if (!group) {
@@ -1174,10 +1140,40 @@ static int exynos_iommu_add_device(struct device *dev)
 
 static void exynos_iommu_remove_device(struct device *dev)
 {
+	if (!has_sysmmu(dev))
+		return;
+
 	iommu_group_remove_device(dev);
 }
 
-static const struct iommu_ops exynos_iommu_ops = {
+static int exynos_iommu_of_xlate(struct device *dev,
+				 struct of_phandle_args *spec)
+{
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct platform_device *sysmmu = of_find_device_by_node(spec->np);
+	struct sysmmu_drvdata *data;
+
+	if (!sysmmu)
+		return -ENODEV;
+
+	data = platform_get_drvdata(sysmmu);
+	if (!data)
+		return -ENODEV;
+
+	if (!owner) {
+		owner = kzalloc(sizeof(*owner), GFP_KERNEL);
+		if (!owner)
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&owner->controllers);
+		dev->archdata.iommu = owner;
+	}
+
+	list_add_tail(&data->owner_node, &owner->controllers);
+	return 0;
+}
+
+static struct iommu_ops exynos_iommu_ops = {
 	.domain_alloc = exynos_iommu_domain_alloc,
 	.domain_free = exynos_iommu_domain_free,
 	.attach_dev = exynos_iommu_attach_device,
@@ -1189,19 +1185,15 @@ static const struct iommu_ops exynos_iommu_ops = {
 	.add_device = exynos_iommu_add_device,
 	.remove_device = exynos_iommu_remove_device,
 	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
+	.of_xlate = exynos_iommu_of_xlate,
 };
 
+static bool init_done;
+
 static int __init exynos_iommu_init(void)
 {
-	struct device_node *np;
 	int ret;
 
-	np = of_find_matching_node(NULL, sysmmu_of_match);
-	if (!np)
-		return 0;
-
-	of_node_put(np);
-
 	lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table",
 				LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL);
 	if (!lv2table_kmem_cache) {
@@ -1230,6 +1222,8 @@ static int __init exynos_iommu_init(void)
 		goto err_set_iommu;
 	}
 
+	init_done = true;
+
 	return 0;
 err_set_iommu:
 	kmem_cache_free(lv2table_kmem_cache, zero_lv2_table);
@@ -1239,4 +1233,21 @@ err_reg_driver:
 	kmem_cache_destroy(lv2table_kmem_cache);
 	return ret;
 }
-subsys_initcall(exynos_iommu_init);
+
+static int __init exynos_iommu_of_setup(struct device_node *np)
+{
+	struct platform_device *pdev;
+
+	if (!init_done)
+		exynos_iommu_init();
+
+	pdev = of_platform_device_create(np, NULL, platform_bus_type.dev_root);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	of_iommu_set_ops(np, &exynos_iommu_ops);
+	return 0;
+}
+
+IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu",
+		 exynos_iommu_of_setup);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 68d43beccb7e..a98a7b27aca1 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -15,8 +15,11 @@
  *          Shaohua Li <shaohua.li@intel.com>,
  *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
  *          Fenghua Yu <fenghua.yu@intel.com>
+ *          Joerg Roedel <jroedel@suse.de>
  */
 
+#define pr_fmt(fmt)     "DMAR: " fmt
+
 #include <linux/init.h>
 #include <linux/bitmap.h>
 #include <linux/debugfs.h>
@@ -40,6 +43,7 @@
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
+#include <linux/crash_dump.h>
 #include <asm/irq_remapping.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
@@ -190,7 +194,29 @@ struct root_entry {
 };
 #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
 
+/*
+ * Take a root_entry and return the Lower Context Table Pointer (LCTP)
+ * if marked present.
+ */
+static phys_addr_t root_entry_lctp(struct root_entry *re)
+{
+	if (!(re->lo & 1))
+		return 0;
+
+	return re->lo & VTD_PAGE_MASK;
+}
+
+/*
+ * Take a root_entry and return the Upper Context Table Pointer (UCTP)
+ * if marked present.
+ */
+static phys_addr_t root_entry_uctp(struct root_entry *re)
+{
+	if (!(re->hi & 1))
+		return 0;
 
+	return re->hi & VTD_PAGE_MASK;
+}
 /*
  * low 64 bits:
  * 0: present
@@ -207,10 +233,38 @@ struct context_entry {
 	u64 hi;
 };
 
-static inline bool context_present(struct context_entry *context)
+static inline void context_clear_pasid_enable(struct context_entry *context)
+{
+	context->lo &= ~(1ULL << 11);
+}
+
+static inline bool context_pasid_enabled(struct context_entry *context)
+{
+	return !!(context->lo & (1ULL << 11));
+}
+
+static inline void context_set_copied(struct context_entry *context)
+{
+	context->hi |= (1ull << 3);
+}
+
+static inline bool context_copied(struct context_entry *context)
+{
+	return !!(context->hi & (1ULL << 3));
+}
+
+static inline bool __context_present(struct context_entry *context)
 {
 	return (context->lo & 1);
 }
+
+static inline bool context_present(struct context_entry *context)
+{
+	return context_pasid_enabled(context) ?
+	     __context_present(context) :
+	     __context_present(context) && !context_copied(context);
+}
+
 static inline void context_set_present(struct context_entry *context)
 {
 	context->lo |= 1;
@@ -247,6 +301,11 @@ static inline void context_set_domain_id(struct context_entry *context,
 	context->hi |= (value & ((1 << 16) - 1)) << 8;
 }
 
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
 static inline void context_clear_entry(struct context_entry *context)
 {
 	context->lo = 0;
@@ -422,6 +481,14 @@ static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
+static int intel_iommu_ecs = 1;
+
+/* We only actually use ECS when PASID support (on the new bit 40)
+ * is also advertised. Some early implementations — the ones with
+ * PASID support on bit 28 — have issues even when we *only* use
+ * extended root/context tables. */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+			    ecap_pasid(iommu->ecap))
 
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -432,6 +499,25 @@ static LIST_HEAD(device_domain_list);
 
 static const struct iommu_ops intel_iommu_ops;
 
+static bool translation_pre_enabled(struct intel_iommu *iommu)
+{
+	return (iommu->flags & VTD_FLAG_TRANS_PRE_ENABLED);
+}
+
+static void clear_translation_pre_enabled(struct intel_iommu *iommu)
+{
+	iommu->flags &= ~VTD_FLAG_TRANS_PRE_ENABLED;
+}
+
+static void init_translation_status(struct intel_iommu *iommu)
+{
+	u32 gsts;
+
+	gsts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (gsts & DMA_GSTS_TES)
+		iommu->flags |= VTD_FLAG_TRANS_PRE_ENABLED;
+}
+
 /* Convert generic 'struct iommu_domain to private struct dmar_domain */
 static struct dmar_domain *to_dmar_domain(struct iommu_domain *dom)
 {
@@ -445,26 +531,26 @@ static int __init intel_iommu_setup(char *str)
 	while (*str) {
 		if (!strncmp(str, "on", 2)) {
 			dmar_disabled = 0;
-			printk(KERN_INFO "Intel-IOMMU: enabled\n");
+			pr_info("IOMMU enabled\n");
 		} else if (!strncmp(str, "off", 3)) {
 			dmar_disabled = 1;
-			printk(KERN_INFO "Intel-IOMMU: disabled\n");
+			pr_info("IOMMU disabled\n");
 		} else if (!strncmp(str, "igfx_off", 8)) {
 			dmar_map_gfx = 0;
-			printk(KERN_INFO
-				"Intel-IOMMU: disable GFX device mapping\n");
+			pr_info("Disable GFX device mapping\n");
 		} else if (!strncmp(str, "forcedac", 8)) {
-			printk(KERN_INFO
-				"Intel-IOMMU: Forcing DAC for PCI devices\n");
+			pr_info("Forcing DAC for PCI devices\n");
 			dmar_forcedac = 1;
 		} else if (!strncmp(str, "strict", 6)) {
-			printk(KERN_INFO
-				"Intel-IOMMU: disable batched IOTLB flush\n");
+			pr_info("Disable batched IOTLB flush\n");
 			intel_iommu_strict = 1;
 		} else if (!strncmp(str, "sp_off", 6)) {
-			printk(KERN_INFO
-				"Intel-IOMMU: disable supported super page\n");
+			pr_info("Disable supported super page\n");
 			intel_iommu_superpage = 0;
+		} else if (!strncmp(str, "ecs_off", 7)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable extended context table support\n");
+			intel_iommu_ecs = 0;
 		}
 
 		str += strcspn(str, ",");
@@ -669,7 +755,7 @@ static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu
 	struct context_entry *context;
 	u64 *entry;
 
-	if (ecap_ecs(iommu->ecap)) {
+	if (ecs_enabled(iommu)) {
 		if (devfn >= 0x80) {
 			devfn -= 0x80;
 			entry = &root->hi;
@@ -696,6 +782,11 @@ static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu
 	return &context[devfn];
 }
 
+static int iommu_dummy(struct device *dev)
+{
+	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
+}
+
 static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
@@ -705,6 +796,9 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 	u16 segment = 0;
 	int i;
 
+	if (iommu_dummy(dev))
+		return NULL;
+
 	if (dev_is_pci(dev)) {
 		pdev = to_pci_dev(dev);
 		segment = pci_domain_nr(pdev->bus);
@@ -798,7 +892,7 @@ static void free_context_table(struct intel_iommu *iommu)
 		if (context)
 			free_pgtable_page(context);
 
-		if (!ecap_ecs(iommu->ecap))
+		if (!ecs_enabled(iommu))
 			continue;
 
 		context = iommu_context_addr(iommu, i, 0x80, 0);
@@ -1112,7 +1206,7 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 
 	root = (struct root_entry *)alloc_pgtable_page(iommu->node);
 	if (!root) {
-		pr_err("IOMMU: allocating root entry for %s failed\n",
+		pr_err("Allocating root entry for %s failed\n",
 			iommu->name);
 		return -ENOMEM;
 	}
@@ -1133,7 +1227,7 @@ static void iommu_set_root_entry(struct intel_iommu *iommu)
 	unsigned long flag;
 
 	addr = virt_to_phys(iommu->root_entry);
-	if (ecap_ecs(iommu->ecap))
+	if (ecs_enabled(iommu))
 		addr |= DMA_RTADDR_RTT;
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
@@ -1250,9 +1344,9 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 
 	/* check IOTLB invalidation granularity */
 	if (DMA_TLB_IAIG(val) == 0)
-		printk(KERN_ERR"IOMMU: flush IOTLB failed\n");
+		pr_err("Flush IOTLB failed\n");
 	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
-		pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
+		pr_debug("TLB flush request %Lx, actual %Lx\n",
 			(unsigned long long)DMA_TLB_IIRG(type),
 			(unsigned long long)DMA_TLB_IAIG(val));
 }
@@ -1423,8 +1517,8 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	unsigned long nlongs;
 
 	ndomains = cap_ndoms(iommu->cap);
-	pr_debug("IOMMU%d: Number of Domains supported <%ld>\n",
-		 iommu->seq_id, ndomains);
+	pr_debug("%s: Number of Domains supported <%ld>\n",
+		 iommu->name, ndomains);
 	nlongs = BITS_TO_LONGS(ndomains);
 
 	spin_lock_init(&iommu->lock);
@@ -1434,15 +1528,15 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	 */
 	iommu->domain_ids = kcalloc(nlongs, sizeof(unsigned long), GFP_KERNEL);
 	if (!iommu->domain_ids) {
-		pr_err("IOMMU%d: allocating domain id array failed\n",
-		       iommu->seq_id);
+		pr_err("%s: Allocating domain id array failed\n",
+		       iommu->name);
 		return -ENOMEM;
 	}
 	iommu->domains = kcalloc(ndomains, sizeof(struct dmar_domain *),
 			GFP_KERNEL);
 	if (!iommu->domains) {
-		pr_err("IOMMU%d: allocating domain array failed\n",
-		       iommu->seq_id);
+		pr_err("%s: Allocating domain array failed\n",
+		       iommu->name);
 		kfree(iommu->domain_ids);
 		iommu->domain_ids = NULL;
 		return -ENOMEM;
@@ -1547,7 +1641,7 @@ static int iommu_attach_domain(struct dmar_domain *domain,
 	num = __iommu_attach_domain(domain, iommu);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 	if (num < 0)
-		pr_err("IOMMU: no free domain ids\n");
+		pr_err("%s: No free domain ids\n", iommu->name);
 
 	return num;
 }
@@ -1639,7 +1733,7 @@ static int dmar_init_reserved_ranges(void)
 	iova = reserve_iova(&reserved_iova_list, IOVA_PFN(IOAPIC_RANGE_START),
 		IOVA_PFN(IOAPIC_RANGE_END));
 	if (!iova) {
-		printk(KERN_ERR "Reserve IOAPIC range failed\n");
+		pr_err("Reserve IOAPIC range failed\n");
 		return -ENODEV;
 	}
 
@@ -1655,7 +1749,7 @@ static int dmar_init_reserved_ranges(void)
 					    IOVA_PFN(r->start),
 					    IOVA_PFN(r->end));
 			if (!iova) {
-				printk(KERN_ERR "Reserve iova failed\n");
+				pr_err("Reserve iova failed\n");
 				return -ENODEV;
 			}
 		}
@@ -1702,7 +1796,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	sagaw = cap_sagaw(iommu->cap);
 	if (!test_bit(agaw, &sagaw)) {
 		/* hardware doesn't support it, choose a bigger one */
-		pr_debug("IOMMU: hardware doesn't support agaw %d\n", agaw);
+		pr_debug("Hardware doesn't support agaw %d\n", agaw);
 		agaw = find_next_bit(&sagaw, 5, agaw);
 		if (agaw >= 5)
 			return -ENODEV;
@@ -1795,6 +1889,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 		return 0;
 	}
 
+	context_clear_entry(context);
+
 	id = domain->id;
 	pgd = domain->pgd;
 
@@ -1803,7 +1899,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 			id = iommu_attach_vm_domain(domain, iommu);
 			if (id < 0) {
 				spin_unlock_irqrestore(&iommu->lock, flags);
-				pr_err("IOMMU: no free domain ids\n");
+				pr_err("%s: No free domain ids\n", iommu->name);
 				return -EFAULT;
 			}
 		}
@@ -2030,8 +2126,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		tmp = cmpxchg64_local(&pte->val, 0ULL, pteval);
 		if (tmp) {
 			static int dumps = 5;
-			printk(KERN_CRIT "ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n",
-			       iov_pfn, tmp, (unsigned long long)pteval);
+			pr_crit("ERROR: DMA PTE for vPFN 0x%lx already set (to %llx not %llx)\n",
+				iov_pfn, tmp, (unsigned long long)pteval);
 			if (dumps) {
 				dumps--;
 				debug_dma_dump_mappings(NULL);
@@ -2303,7 +2399,7 @@ static int iommu_domain_identity_map(struct dmar_domain *domain,
 
 	if (!reserve_iova(&domain->iovad, dma_to_mm_pfn(first_vpfn),
 			  dma_to_mm_pfn(last_vpfn))) {
-		printk(KERN_ERR "IOMMU: reserve iova failed\n");
+		pr_err("Reserving iova failed\n");
 		return -ENOMEM;
 	}
 
@@ -2336,15 +2432,14 @@ static int iommu_prepare_identity_map(struct device *dev,
 	   range which is reserved in E820, so which didn't get set
 	   up to start with in si_domain */
 	if (domain == si_domain && hw_pass_through) {
-		printk("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
-		       dev_name(dev), start, end);
+		pr_warn("Ignoring identity map for HW passthrough device %s [0x%Lx - 0x%Lx]\n",
+			dev_name(dev), start, end);
 		return 0;
 	}
 
-	printk(KERN_INFO
-	       "IOMMU: Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
-	       dev_name(dev), start, end);
-	
+	pr_info("Setting identity map for device %s [0x%Lx - 0x%Lx]\n",
+		dev_name(dev), start, end);
+
 	if (end < start) {
 		WARN(1, "Your BIOS is broken; RMRR ends before it starts!\n"
 			"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
@@ -2401,12 +2496,11 @@ static inline void iommu_prepare_isa(void)
 	if (!pdev)
 		return;
 
-	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
+	pr_info("Prepare 0-16MiB unity mapping for LPC\n");
 	ret = iommu_prepare_identity_map(&pdev->dev, 0, 16*1024*1024 - 1);
 
 	if (ret)
-		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
-		       "floppy might not work\n");
+		pr_err("Failed to create 0-16MiB identity map - floppy might not work\n");
 
 	pci_dev_put(pdev);
 }
@@ -2450,7 +2544,7 @@ static int __init si_domain_init(int hw)
 		return -EFAULT;
 	}
 
-	pr_debug("IOMMU: identity mapping domain is domain %d\n",
+	pr_debug("Identity mapping domain is domain %d\n",
 		 si_domain->id);
 
 	if (hw)
@@ -2650,8 +2744,8 @@ static int __init dev_prepare_static_identity_mapping(struct device *dev, int hw
 				  hw ? CONTEXT_TT_PASS_THROUGH :
 				       CONTEXT_TT_MULTI_LEVEL);
 	if (!ret)
-		pr_info("IOMMU: %s identity mapping for device %s\n",
-			hw ? "hardware" : "software", dev_name(dev));
+		pr_info("%s identity mapping for device %s\n",
+			hw ? "Hardware" : "Software", dev_name(dev));
 	else if (ret == -ENODEV)
 		/* device not associated with an iommu */
 		ret = 0;
@@ -2669,10 +2763,6 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 	int i;
 	int ret = 0;
 
-	ret = si_domain_init(hw);
-	if (ret)
-		return -EFAULT;
-
 	for_each_pci_dev(pdev) {
 		ret = dev_prepare_static_identity_mapping(&pdev->dev, hw);
 		if (ret)
@@ -2686,7 +2776,7 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 
 			if (dev->bus != &acpi_bus_type)
 				continue;
-				
+
 			adev= to_acpi_device(dev);
 			mutex_lock(&adev->physical_node_lock);
 			list_for_each_entry(pn, &adev->physical_node_list, node) {
@@ -2728,19 +2818,200 @@ static void intel_iommu_init_qi(struct intel_iommu *iommu)
 		 */
 		iommu->flush.flush_context = __iommu_flush_context;
 		iommu->flush.flush_iotlb = __iommu_flush_iotlb;
-		pr_info("IOMMU: %s using Register based invalidation\n",
+		pr_info("%s: Using Register based invalidation\n",
 			iommu->name);
 	} else {
 		iommu->flush.flush_context = qi_flush_context;
 		iommu->flush.flush_iotlb = qi_flush_iotlb;
-		pr_info("IOMMU: %s using Queued invalidation\n", iommu->name);
+		pr_info("%s: Using Queued invalidation\n", iommu->name);
 	}
 }
 
+static int copy_context_table(struct intel_iommu *iommu,
+			      struct root_entry *old_re,
+			      struct context_entry **tbl,
+			      int bus, bool ext)
+{
+	struct context_entry *old_ce = NULL, *new_ce = NULL, ce;
+	int tbl_idx, pos = 0, idx, devfn, ret = 0, did;
+	phys_addr_t old_ce_phys;
+
+	tbl_idx = ext ? bus * 2 : bus;
+
+	for (devfn = 0; devfn < 256; devfn++) {
+		/* First calculate the correct index */
+		idx = (ext ? devfn * 2 : devfn) % 256;
+
+		if (idx == 0) {
+			/* First save what we may have and clean up */
+			if (new_ce) {
+				tbl[tbl_idx] = new_ce;
+				__iommu_flush_cache(iommu, new_ce,
+						    VTD_PAGE_SIZE);
+				pos = 1;
+			}
+
+			if (old_ce)
+				iounmap(old_ce);
+
+			ret = 0;
+			if (devfn < 0x80)
+				old_ce_phys = root_entry_lctp(old_re);
+			else
+				old_ce_phys = root_entry_uctp(old_re);
+
+			if (!old_ce_phys) {
+				if (ext && devfn == 0) {
+					/* No LCTP, try UCTP */
+					devfn = 0x7f;
+					continue;
+				} else {
+					goto out;
+				}
+			}
+
+			ret = -ENOMEM;
+			old_ce = ioremap_cache(old_ce_phys, PAGE_SIZE);
+			if (!old_ce)
+				goto out;
+
+			new_ce = alloc_pgtable_page(iommu->node);
+			if (!new_ce)
+				goto out_unmap;
+
+			ret = 0;
+		}
+
+		/* Now copy the context entry */
+		ce = old_ce[idx];
+
+		if (!__context_present(&ce))
+			continue;
+
+		did = context_domain_id(&ce);
+		if (did >= 0 && did < cap_ndoms(iommu->cap))
+			set_bit(did, iommu->domain_ids);
+
+		/*
+		 * We need a marker for copied context entries. This
+		 * marker needs to work for the old format as well as
+		 * for extended context entries.
+		 *
+		 * Bit 67 of the context entry is used. In the old
+		 * format this bit is available to software, in the
+		 * extended format it is the PGE bit, but PGE is ignored
+		 * by HW if PASIDs are disabled (and thus still
+		 * available).
+		 *
+		 * So disable PASIDs first and then mark the entry
+		 * copied. This means that we don't copy PASID
+		 * translations from the old kernel, but this is fine as
+		 * faults there are not fatal.
+		 */
+		context_clear_pasid_enable(&ce);
+		context_set_copied(&ce);
+
+		new_ce[idx] = ce;
+	}
+
+	tbl[tbl_idx + pos] = new_ce;
+
+	__iommu_flush_cache(iommu, new_ce, VTD_PAGE_SIZE);
+
+out_unmap:
+	iounmap(old_ce);
+
+out:
+	return ret;
+}
+
+static int copy_translation_tables(struct intel_iommu *iommu)
+{
+	struct context_entry **ctxt_tbls;
+	struct root_entry *old_rt;
+	phys_addr_t old_rt_phys;
+	int ctxt_table_entries;
+	unsigned long flags;
+	u64 rtaddr_reg;
+	int bus, ret;
+	bool new_ext, ext;
+
+	rtaddr_reg = dmar_readq(iommu->reg + DMAR_RTADDR_REG);
+	ext        = !!(rtaddr_reg & DMA_RTADDR_RTT);
+	new_ext    = !!ecap_ecs(iommu->ecap);
+
+	/*
+	 * The RTT bit can only be changed when translation is disabled,
+	 * but disabling translation means to open a window for data
+	 * corruption. So bail out and don't copy anything if we would
+	 * have to change the bit.
+	 */
+	if (new_ext != ext)
+		return -EINVAL;
+
+	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
+	if (!old_rt_phys)
+		return -EINVAL;
+
+	old_rt = ioremap_cache(old_rt_phys, PAGE_SIZE);
+	if (!old_rt)
+		return -ENOMEM;
+
+	/* This is too big for the stack - allocate it from slab */
+	ctxt_table_entries = ext ? 512 : 256;
+	ret = -ENOMEM;
+	ctxt_tbls = kzalloc(ctxt_table_entries * sizeof(void *), GFP_KERNEL);
+	if (!ctxt_tbls)
+		goto out_unmap;
+
+	for (bus = 0; bus < 256; bus++) {
+		ret = copy_context_table(iommu, &old_rt[bus],
+					 ctxt_tbls, bus, ext);
+		if (ret) {
+			pr_err("%s: Failed to copy context table for bus %d\n",
+				iommu->name, bus);
+			continue;
+		}
+	}
+
+	spin_lock_irqsave(&iommu->lock, flags);
+
+	/* Context tables are copied, now write them to the root_entry table */
+	for (bus = 0; bus < 256; bus++) {
+		int idx = ext ? bus * 2 : bus;
+		u64 val;
+
+		if (ctxt_tbls[idx]) {
+			val = virt_to_phys(ctxt_tbls[idx]) | 1;
+			iommu->root_entry[bus].lo = val;
+		}
+
+		if (!ext || !ctxt_tbls[idx + 1])
+			continue;
+
+		val = virt_to_phys(ctxt_tbls[idx + 1]) | 1;
+		iommu->root_entry[bus].hi = val;
+	}
+
+	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	kfree(ctxt_tbls);
+
+	__iommu_flush_cache(iommu, iommu->root_entry, PAGE_SIZE);
+
+	ret = 0;
+
+out_unmap:
+	iounmap(old_rt);
+
+	return ret;
+}
+
 static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
+	bool copied_tables = false;
 	struct device *dev;
 	struct intel_iommu *iommu;
 	int i, ret;
@@ -2761,8 +3032,7 @@ static int __init init_dmars(void)
 			g_num_of_iommus++;
 			continue;
 		}
-		printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n",
-			  DMAR_UNITS_SUPPORTED);
+		pr_err_once("Exceeded %d IOMMUs\n", DMAR_UNITS_SUPPORTED);
 	}
 
 	/* Preallocate enough resources for IOMMU hot-addition */
@@ -2772,7 +3042,7 @@ static int __init init_dmars(void)
 	g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *),
 			GFP_KERNEL);
 	if (!g_iommus) {
-		printk(KERN_ERR "Allocating global iommu array failed\n");
+		pr_err("Allocating global iommu array failed\n");
 		ret = -ENOMEM;
 		goto error;
 	}
@@ -2787,10 +3057,21 @@ static int __init init_dmars(void)
 	for_each_active_iommu(iommu, drhd) {
 		g_iommus[iommu->seq_id] = iommu;
 
+		intel_iommu_init_qi(iommu);
+
 		ret = iommu_init_domains(iommu);
 		if (ret)
 			goto free_iommu;
 
+		init_translation_status(iommu);
+
+		if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
+			iommu_disable_translation(iommu);
+			clear_translation_pre_enabled(iommu);
+			pr_warn("Translation was enabled for %s but we are not in kdump mode\n",
+				iommu->name);
+		}
+
 		/*
 		 * TBD:
 		 * we could share the same root & context tables
@@ -2799,13 +3080,41 @@ static int __init init_dmars(void)
 		ret = iommu_alloc_root_entry(iommu);
 		if (ret)
 			goto free_iommu;
+
+		if (translation_pre_enabled(iommu)) {
+			pr_info("Translation already enabled - trying to copy translation structures\n");
+
+			ret = copy_translation_tables(iommu);
+			if (ret) {
+				/*
+				 * We found the IOMMU with translation
+				 * enabled - but failed to copy over the
+				 * old root-entry table. Try to proceed
+				 * by disabling translation now and
+				 * allocating a clean root-entry table.
+				 * This might cause DMAR faults, but
+				 * probably the dump will still succeed.
+				 */
+				pr_err("Failed to copy translation tables from previous kernel for %s\n",
+				       iommu->name);
+				iommu_disable_translation(iommu);
+				clear_translation_pre_enabled(iommu);
+			} else {
+				pr_info("Copied translation tables from previous kernel for %s\n",
+					iommu->name);
+				copied_tables = true;
+			}
+		}
+
+		iommu_flush_write_buffer(iommu);
+		iommu_set_root_entry(iommu);
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
 	}
 
-	for_each_active_iommu(iommu, drhd)
-		intel_iommu_init_qi(iommu);
-
 	if (iommu_pass_through)
 		iommu_identity_mapping |= IDENTMAP_ALL;
 
@@ -2813,9 +3122,24 @@ static int __init init_dmars(void)
 	iommu_identity_mapping |= IDENTMAP_GFX;
 #endif
 
+	if (iommu_identity_mapping) {
+		ret = si_domain_init(hw_pass_through);
+		if (ret)
+			goto free_iommu;
+	}
+
 	check_tylersburg_isoch();
 
 	/*
+	 * If we copied translations from a previous kernel in the kdump
+	 * case, we can not assign the devices to domains now, as that
+	 * would eliminate the old mappings. So skip this part and defer
+	 * the assignment to device driver initialization time.
+	 */
+	if (copied_tables)
+		goto domains_done;
+
+	/*
 	 * If pass through is not set or not enabled, setup context entries for
 	 * identity mappings for rmrr, gfx, and isa and may fall back to static
 	 * identity mapping if iommu_identity_mapping is set.
@@ -2823,7 +3147,7 @@ static int __init init_dmars(void)
 	if (iommu_identity_mapping) {
 		ret = iommu_prepare_static_identity_mapping(hw_pass_through);
 		if (ret) {
-			printk(KERN_CRIT "Failed to setup IOMMU pass-through\n");
+			pr_crit("Failed to setup IOMMU pass-through\n");
 			goto free_iommu;
 		}
 	}
@@ -2841,20 +3165,21 @@ static int __init init_dmars(void)
 	 *    endfor
 	 * endfor
 	 */
-	printk(KERN_INFO "IOMMU: Setting RMRR:\n");
+	pr_info("Setting RMRR:\n");
 	for_each_rmrr_units(rmrr) {
 		/* some BIOS lists non-exist devices in DMAR table. */
 		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
 					  i, dev) {
 			ret = iommu_prepare_rmrr_dev(rmrr, dev);
 			if (ret)
-				printk(KERN_ERR
-				       "IOMMU: mapping reserved region failed\n");
+				pr_err("Mapping reserved region failed\n");
 		}
 	}
 
 	iommu_prepare_isa();
 
+domains_done:
+
 	/*
 	 * for each drhd
 	 *   enable fault log
@@ -2879,11 +3204,9 @@ static int __init init_dmars(void)
 		if (ret)
 			goto free_iommu;
 
-		iommu_set_root_entry(iommu);
+		if (!translation_pre_enabled(iommu))
+			iommu_enable_translation(iommu);
 
-		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
-		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
-		iommu_enable_translation(iommu);
 		iommu_disable_protect_mem_regions(iommu);
 	}
 
@@ -2924,7 +3247,7 @@ static struct iova *intel_alloc_iova(struct device *dev,
 	}
 	iova = alloc_iova(&domain->iovad, nrpages, IOVA_PFN(dma_mask), 1);
 	if (unlikely(!iova)) {
-		printk(KERN_ERR "Allocating %ld-page iova for %s failed",
+		pr_err("Allocating %ld-page iova for %s failed",
 		       nrpages, dev_name(dev));
 		return NULL;
 	}
@@ -2939,7 +3262,7 @@ static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
 
 	domain = get_domain_for_dev(dev, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 	if (!domain) {
-		printk(KERN_ERR "Allocating domain for %s failed",
+		pr_err("Allocating domain for %s failed\n",
 		       dev_name(dev));
 		return NULL;
 	}
@@ -2948,7 +3271,7 @@ static struct dmar_domain *__get_valid_domain_for_dev(struct device *dev)
 	if (unlikely(!domain_context_mapped(dev))) {
 		ret = domain_context_mapping(domain, dev, CONTEXT_TT_MULTI_LEVEL);
 		if (ret) {
-			printk(KERN_ERR "Domain context map for %s failed",
+			pr_err("Domain context map for %s failed\n",
 			       dev_name(dev));
 			return NULL;
 		}
@@ -2969,11 +3292,6 @@ static inline struct dmar_domain *get_valid_domain_for_dev(struct device *dev)
 	return __get_valid_domain_for_dev(dev);
 }
 
-static int iommu_dummy(struct device *dev)
-{
-	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
-}
-
 /* Check if the dev needs to go through non-identity map and unmap process.*/
 static int iommu_no_mapping(struct device *dev)
 {
@@ -2995,8 +3313,8 @@ static int iommu_no_mapping(struct device *dev)
 			 * to non-identity mapping.
 			 */
 			domain_remove_one_dev_info(si_domain, dev);
-			printk(KERN_INFO "32bit %s uses non-identity mapping\n",
-			       dev_name(dev));
+			pr_info("32bit %s uses non-identity mapping\n",
+				dev_name(dev));
 			return 0;
 		}
 	} else {
@@ -3011,8 +3329,8 @@ static int iommu_no_mapping(struct device *dev)
 						  CONTEXT_TT_PASS_THROUGH :
 						  CONTEXT_TT_MULTI_LEVEL);
 			if (!ret) {
-				printk(KERN_INFO "64bit %s uses identity mapping\n",
-				       dev_name(dev));
+				pr_info("64bit %s uses identity mapping\n",
+					dev_name(dev));
 				return 1;
 			}
 		}
@@ -3081,7 +3399,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 error:
 	if (iova)
 		__free_iova(&domain->iovad, iova);
-	printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n",
+	pr_err("Device %s request: %zx@%llx dir %d --- failed\n",
 		dev_name(dev), size, (unsigned long long)paddr, dir);
 	return 0;
 }
@@ -3396,7 +3714,7 @@ static inline int iommu_domain_cache_init(void)
 
 					 NULL);
 	if (!iommu_domain_cache) {
-		printk(KERN_ERR "Couldn't create iommu_domain cache\n");
+		pr_err("Couldn't create iommu_domain cache\n");
 		ret = -ENOMEM;
 	}
 
@@ -3413,7 +3731,7 @@ static inline int iommu_devinfo_cache_init(void)
 					 SLAB_HWCACHE_ALIGN,
 					 NULL);
 	if (!iommu_devinfo_cache) {
-		printk(KERN_ERR "Couldn't create devinfo cache\n");
+		pr_err("Couldn't create devinfo cache\n");
 		ret = -ENOMEM;
 	}
 
@@ -3790,19 +4108,19 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 		return 0;
 
 	if (hw_pass_through && !ecap_pass_through(iommu->ecap)) {
-		pr_warn("IOMMU: %s doesn't support hardware pass through.\n",
+		pr_warn("%s: Doesn't support hardware pass through.\n",
 			iommu->name);
 		return -ENXIO;
 	}
 	if (!ecap_sc_support(iommu->ecap) &&
 	    domain_update_iommu_snooping(iommu)) {
-		pr_warn("IOMMU: %s doesn't support snooping.\n",
+		pr_warn("%s: Doesn't support snooping.\n",
 			iommu->name);
 		return -ENXIO;
 	}
 	sp = domain_update_iommu_superpage(iommu) - 1;
 	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
-		pr_warn("IOMMU: %s doesn't support large page.\n",
+		pr_warn("%s: Doesn't support large page.\n",
 			iommu->name);
 		return -ENXIO;
 	}
@@ -4033,7 +4351,7 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 		start = mhp->start_pfn << PAGE_SHIFT;
 		end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
 		if (iommu_domain_identity_map(si_domain, start, end)) {
-			pr_warn("dmar: failed to build identity map for [%llx-%llx]\n",
+			pr_warn("Failed to build identity map for [%llx-%llx]\n",
 				start, end);
 			return NOTIFY_BAD;
 		}
@@ -4051,7 +4369,7 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 
 			iova = find_iova(&si_domain->iovad, start_vpfn);
 			if (iova == NULL) {
-				pr_debug("dmar: failed get IOVA for PFN %lx\n",
+				pr_debug("Failed get IOVA for PFN %lx\n",
 					 start_vpfn);
 				break;
 			}
@@ -4059,7 +4377,7 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb,
 			iova = split_and_remove_iova(&si_domain->iovad, iova,
 						     start_vpfn, last_vpfn);
 			if (iova == NULL) {
-				pr_warn("dmar: failed to split IOVA PFN [%lx-%lx]\n",
+				pr_warn("Failed to split IOVA PFN [%lx-%lx]\n",
 					start_vpfn, last_vpfn);
 				return NOTIFY_BAD;
 			}
@@ -4168,13 +4486,6 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
-	/*
-	 * Disable translation if already enabled prior to OS handover.
-	 */
-	for_each_active_iommu(iommu, drhd)
-		if (iommu->gcmd & DMA_GCMD_TE)
-			iommu_disable_translation(iommu);
-
 	if (dmar_dev_scope_init() < 0) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR device scope\n");
@@ -4185,10 +4496,10 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 
 	if (list_empty(&dmar_rmrr_units))
-		printk(KERN_INFO "DMAR: No RMRR found\n");
+		pr_info("No RMRR found\n");
 
 	if (list_empty(&dmar_atsr_units))
-		printk(KERN_INFO "DMAR: No ATSR found\n");
+		pr_info("No ATSR found\n");
 
 	if (dmar_init_reserved_ranges()) {
 		if (force_on)
@@ -4202,12 +4513,11 @@ int __init intel_iommu_init(void)
 	if (ret) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMARs\n");
-		printk(KERN_ERR "IOMMU: dmar init failed\n");
+		pr_err("Initialization failed\n");
 		goto out_free_reserved_range;
 	}
 	up_write(&dmar_global_lock);
-	printk(KERN_INFO
-	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
+	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	init_timer(&unmap_timer);
 #ifdef CONFIG_SWIOTLB
@@ -4349,13 +4659,11 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 
 	dmar_domain = alloc_domain(DOMAIN_FLAG_VIRTUAL_MACHINE);
 	if (!dmar_domain) {
-		printk(KERN_ERR
-			"intel_iommu_domain_init: dmar_domain == NULL\n");
+		pr_err("Can't allocate dmar_domain\n");
 		return NULL;
 	}
 	if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
-		printk(KERN_ERR
-			"intel_iommu_domain_init() failed\n");
+		pr_err("Domain initialization failed\n");
 		domain_exit(dmar_domain);
 		return NULL;
 	}
@@ -4414,7 +4722,7 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		addr_width = cap_mgaw(iommu->cap);
 
 	if (dmar_domain->max_addr > (1LL << addr_width)) {
-		printk(KERN_ERR "%s: iommu width (%d) is not "
+		pr_err("%s: iommu width (%d) is not "
 		       "sufficient for the mapped address (%llx)\n",
 		       __func__, addr_width, dmar_domain->max_addr);
 		return -EFAULT;
@@ -4468,7 +4776,7 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		/* check if minimum agaw is sufficient for mapped address */
 		end = __DOMAIN_MAX_ADDR(dmar_domain->gaw) + 1;
 		if (end < max_addr) {
-			printk(KERN_ERR "%s: iommu width (%d) is not "
+			pr_err("%s: iommu width (%d) is not "
 			       "sufficient for the mapped address (%llx)\n",
 			       __func__, dmar_domain->gaw, max_addr);
 			return -EFAULT;
@@ -4609,7 +4917,7 @@ static const struct iommu_ops intel_iommu_ops = {
 static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
 {
 	/* G4x/GM45 integrated gfx dmar support is totally busted. */
-	printk(KERN_INFO "DMAR: Disabling IOMMU for graphics on this chipset\n");
+	pr_info("Disabling IOMMU for graphics on this chipset\n");
 	dmar_map_gfx = 0;
 }
 
@@ -4627,7 +4935,7 @@ static void quirk_iommu_rwbf(struct pci_dev *dev)
 	 * Mobile 4 Series Chipset neglects to set RWBF capability,
 	 * but needs it. Same seems to hold for the desktop versions.
 	 */
-	printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n");
+	pr_info("Forcing write-buffer flush capability\n");
 	rwbf_quirk = 1;
 }
 
@@ -4657,11 +4965,11 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 		return;
 
 	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
-		printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
+		pr_info("BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
 		dmar_map_gfx = 0;
 	} else if (dmar_map_gfx) {
 		/* we have to ensure the gfx device is idle before we flush */
-		printk(KERN_INFO "DMAR: Disabling batched IOTLB flush on Ironlake\n");
+		pr_info("Disabling batched IOTLB flush on Ironlake\n");
 		intel_iommu_strict = 1;
        }
 }
@@ -4723,7 +5031,7 @@ static void __init check_tylersburg_isoch(void)
 		iommu_identity_mapping |= IDENTMAP_AZALIA;
 		return;
 	}
-	
-	printk(KERN_WARNING "DMAR: Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
+
+	pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
 	       vtisochctrl);
 }
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5709ae9c3e77..f15692a410c7 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -1,3 +1,6 @@
+
+#define pr_fmt(fmt)     "DMAR-IR: " fmt
+
 #include <linux/interrupt.h>
 #include <linux/dmar.h>
 #include <linux/spinlock.h>
@@ -8,6 +11,8 @@
 #include <linux/irq.h>
 #include <linux/intel-iommu.h>
 #include <linux/acpi.h>
+#include <linux/irqdomain.h>
+#include <linux/crash_dump.h>
 #include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/cpu.h>
@@ -17,6 +22,11 @@
 
 #include "irq_remapping.h"
 
+enum irq_mode {
+	IRQ_REMAPPING,
+	IRQ_POSTING,
+};
+
 struct ioapic_scope {
 	struct intel_iommu *iommu;
 	unsigned int id;
@@ -31,6 +41,22 @@ struct hpet_scope {
 	unsigned int devfn;
 };
 
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+	enum irq_mode mode;
+};
+
+struct intel_ir_data {
+	struct irq_2_iommu			irq_2_iommu;
+	struct irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
 #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
 #define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
 
@@ -50,43 +76,34 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS];
  * the dmar_global_lock.
  */
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static struct irq_domain_ops intel_ir_domain_ops;
 
+static void iommu_disable_irq_remapping(struct intel_iommu *iommu);
 static int __init parse_ioapics_under_ir(void);
 
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+static bool ir_pre_enabled(struct intel_iommu *iommu)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
-	return cfg ? &cfg->irq_2_iommu : NULL;
+	return (iommu->flags & VTD_FLAG_IRQ_REMAP_PRE_ENABLED);
 }
 
-static int get_irte(int irq, struct irte *entry)
+static void clear_ir_pre_enabled(struct intel_iommu *iommu)
 {
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int index;
-
-	if (!entry || !irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	if (unlikely(!irq_iommu->iommu)) {
-		raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
+	iommu->flags &= ~VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
+}
 
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
-	*entry = *(irq_iommu->iommu->ir_table->base + index);
+static void init_ir_status(struct intel_iommu *iommu)
+{
+	u32 gsts;
 
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-	return 0;
+	gsts = readl(iommu->reg + DMAR_GSTS_REG);
+	if (gsts & DMA_GSTS_IRES)
+		iommu->flags |= VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
 }
 
-static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+static int alloc_irte(struct intel_iommu *iommu, int irq,
+		      struct irq_2_iommu *irq_iommu, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned int mask = 0;
 	unsigned long flags;
 	int index;
@@ -100,8 +117,7 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	}
 
 	if (mask > ecap_max_handle_mask(iommu->ecap)) {
-		printk(KERN_ERR
-		       "Requested mask %x exceeds the max invalidation handle"
+		pr_err("Requested mask %x exceeds the max invalidation handle"
 		       " mask value %Lx\n", mask,
 		       ecap_max_handle_mask(iommu->ecap));
 		return -1;
@@ -113,11 +129,11 @@ static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	if (index < 0) {
 		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
 	} else {
-		cfg->remapped = 1;
 		irq_iommu->iommu = iommu;
 		irq_iommu->irte_index =  index;
 		irq_iommu->sub_handle = 0;
 		irq_iommu->irte_mask = mask;
+		irq_iommu->mode = IRQ_REMAPPING;
 	}
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
@@ -135,47 +151,9 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 	return qi_submit_sync(&desc, iommu);
 }
 
-static int map_irq_to_irte_handle(int irq, u16 *sub_handle)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int index;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-	*sub_handle = irq_iommu->sub_handle;
-	index = irq_iommu->irte_index;
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-	return index;
-}
-
-static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned long flags;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	cfg->remapped = 1;
-	irq_iommu->iommu = iommu;
-	irq_iommu->irte_index = index;
-	irq_iommu->sub_handle = subhandle;
-	irq_iommu->irte_mask = 0;
-
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return 0;
-}
-
-static int modify_irte(int irq, struct irte *irte_modified)
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+		       struct irte *irte_modified)
 {
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct intel_iommu *iommu;
 	unsigned long flags;
 	struct irte *irte;
@@ -196,6 +174,9 @@ static int modify_irte(int irq, struct irte *irte_modified)
 	__iommu_flush_cache(iommu, irte, sizeof(*irte));
 
 	rc = qi_flush_iec(iommu, index, 0);
+
+	/* Update iommu mode according to the IRTE mode */
+	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
 	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
 
 	return rc;
@@ -242,7 +223,7 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 		return 0;
 
 	iommu = irq_iommu->iommu;
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
 
 	start = iommu->ir_table->base + index;
 	end = start + (1 << irq_iommu->irte_mask);
@@ -257,29 +238,6 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 }
 
-static int free_irte(int irq)
-{
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
-	unsigned long flags;
-	int rc;
-
-	if (!irq_iommu)
-		return -1;
-
-	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	rc = clear_entries(irq_iommu);
-
-	irq_iommu->iommu = NULL;
-	irq_iommu->irte_index = 0;
-	irq_iommu->sub_handle = 0;
-	irq_iommu->irte_mask = 0;
-
-	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return rc;
-}
-
 /*
  * source validation type
  */
@@ -333,7 +291,7 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
-		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
+		pr_warn("Failed to set source-id of IOAPIC (%d)\n", apic);
 		return -1;
 	}
 
@@ -360,7 +318,7 @@ static int set_hpet_sid(struct irte *irte, u8 id)
 	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
-		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
+		pr_warn("Failed to set source-id of HPET block (%d)\n", id);
 		return -1;
 	}
 
@@ -424,11 +382,59 @@ static int set_msi_sid(struct irte *irte, struct pci_dev *dev)
 	return 0;
 }
 
+static int iommu_load_old_irte(struct intel_iommu *iommu)
+{
+	struct irte *old_ir_table;
+	phys_addr_t irt_phys;
+	unsigned int i;
+	size_t size;
+	u64 irta;
+
+	if (!is_kdump_kernel()) {
+		pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
+			iommu->name);
+		clear_ir_pre_enabled(iommu);
+		iommu_disable_irq_remapping(iommu);
+		return -EINVAL;
+	}
+
+	/* Check whether the old ir-table has the same size as ours */
+	irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
+	if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
+	     != INTR_REMAP_TABLE_REG_SIZE)
+		return -EINVAL;
+
+	irt_phys = irta & VTD_PAGE_MASK;
+	size     = INTR_REMAP_TABLE_ENTRIES*sizeof(struct irte);
+
+	/* Map the old IR table */
+	old_ir_table = ioremap_cache(irt_phys, size);
+	if (!old_ir_table)
+		return -ENOMEM;
+
+	/* Copy data over */
+	memcpy(iommu->ir_table->base, old_ir_table, size);
+
+	__iommu_flush_cache(iommu, iommu->ir_table->base, size);
+
+	/*
+	 * Now check the table for used entries and mark those as
+	 * allocated in the bitmap
+	 */
+	for (i = 0; i < INTR_REMAP_TABLE_ENTRIES; i++) {
+		if (iommu->ir_table->base[i].present)
+			bitmap_set(iommu->ir_table->bitmap, i, 1);
+	}
+
+	return 0;
+}
+
+
 static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
 {
+	unsigned long flags;
 	u64 addr;
 	u32 sts;
-	unsigned long flags;
 
 	addr = virt_to_phys((void *)iommu->ir_table->base);
 
@@ -445,10 +451,16 @@ static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
 
 	/*
-	 * global invalidation of interrupt entry cache before enabling
-	 * interrupt-remapping.
+	 * Global invalidation of interrupt entry cache to make sure the
+	 * hardware uses the new irq remapping table.
 	 */
 	qi_global_iec(iommu);
+}
+
+static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	u32 sts;
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
@@ -488,7 +500,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 
 	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
 				 INTR_REMAP_PAGE_ORDER);
-
 	if (!pages) {
 		pr_err("IR%d: failed to allocate pages of order %d\n",
 		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
@@ -502,21 +513,75 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 		goto out_free_pages;
 	}
 
+	iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
+						    0, INTR_REMAP_TABLE_ENTRIES,
+						    NULL, &intel_ir_domain_ops,
+						    iommu);
+	if (!iommu->ir_domain) {
+		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+		goto out_free_bitmap;
+	}
+	iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
 	ir_table->base = page_address(pages);
 	ir_table->bitmap = bitmap;
 	iommu->ir_table = ir_table;
+
+	/*
+	 * If the queued invalidation is already initialized,
+	 * shouldn't disable it.
+	 */
+	if (!iommu->qi) {
+		/*
+		 * Clear previous faults.
+		 */
+		dmar_fault(-1, iommu);
+		dmar_disable_qi(iommu);
+
+		if (dmar_enable_qi(iommu)) {
+			pr_err("Failed to enable queued invalidation\n");
+			goto out_free_bitmap;
+		}
+	}
+
+	init_ir_status(iommu);
+
+	if (ir_pre_enabled(iommu)) {
+		if (iommu_load_old_irte(iommu))
+			pr_err("Failed to copy IR table for %s from previous kernel\n",
+			       iommu->name);
+		else
+			pr_info("Copied IR table for %s from previous kernel\n",
+				iommu->name);
+	}
+
+	iommu_set_irq_remapping(iommu, eim_mode);
+
 	return 0;
 
+out_free_bitmap:
+	kfree(bitmap);
 out_free_pages:
 	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
 out_free_table:
 	kfree(ir_table);
+
+	iommu->ir_table  = NULL;
+
 	return -ENOMEM;
 }
 
 static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
 {
 	if (iommu && iommu->ir_table) {
+		if (iommu->ir_msi_domain) {
+			irq_domain_remove(iommu->ir_msi_domain);
+			iommu->ir_msi_domain = NULL;
+		}
+		if (iommu->ir_domain) {
+			irq_domain_remove(iommu->ir_domain);
+			iommu->ir_domain = NULL;
+		}
 		free_pages((unsigned long)iommu->ir_table->base,
 			   INTR_REMAP_PAGE_ORDER);
 		kfree(iommu->ir_table->bitmap);
@@ -580,17 +645,17 @@ static void __init intel_cleanup_irq_remapping(void)
 	}
 
 	if (x2apic_supported())
-		pr_warn("Failed to enable irq remapping.  You are vulnerable to irq-injection attacks.\n");
+		pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n");
 }
 
 static int __init intel_prepare_irq_remapping(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
+	int eim = 0;
 
 	if (irq_remap_broken) {
-		printk(KERN_WARNING
-			"This system BIOS has enabled interrupt remapping\n"
+		pr_warn("This system BIOS has enabled interrupt remapping\n"
 			"on a chipset that contains an erratum making that\n"
 			"feature unstable.  To maintain system stability\n"
 			"interrupt remapping is being disabled.  Please\n"
@@ -606,7 +671,7 @@ static int __init intel_prepare_irq_remapping(void)
 		return -ENODEV;
 
 	if (parse_ioapics_under_ir() != 1) {
-		printk(KERN_INFO "Not enabling interrupt remapping\n");
+		pr_info("Not enabling interrupt remapping\n");
 		goto error;
 	}
 
@@ -615,85 +680,74 @@ static int __init intel_prepare_irq_remapping(void)
 		if (!ecap_ir_support(iommu->ecap))
 			goto error;
 
-	/* Do the allocations early */
-	for_each_iommu(iommu, drhd)
-		if (intel_setup_irq_remapping(iommu))
-			goto error;
-
-	return 0;
-
-error:
-	intel_cleanup_irq_remapping();
-	return -ENODEV;
-}
-
-static int __init intel_enable_irq_remapping(void)
-{
-	struct dmar_drhd_unit *drhd;
-	struct intel_iommu *iommu;
-	bool setup = false;
-	int eim = 0;
-
+	/* Detect remapping mode: lapic or x2apic */
 	if (x2apic_supported()) {
 		eim = !dmar_x2apic_optout();
-		if (!eim)
-			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit. You can use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
+		if (!eim) {
+			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit.");
+			pr_info("Use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
+		}
 	}
 
 	for_each_iommu(iommu, drhd) {
-		/*
-		 * If the queued invalidation is already initialized,
-		 * shouldn't disable it.
-		 */
-		if (iommu->qi)
-			continue;
-
-		/*
-		 * Clear previous faults.
-		 */
-		dmar_fault(-1, iommu);
-
-		/*
-		 * Disable intr remapping and queued invalidation, if already
-		 * enabled prior to OS handover.
-		 */
-		iommu_disable_irq_remapping(iommu);
-
-		dmar_disable_qi(iommu);
-	}
-
-	/*
-	 * check for the Interrupt-remapping support
-	 */
-	for_each_iommu(iommu, drhd)
 		if (eim && !ecap_eim_support(iommu->ecap)) {
-			printk(KERN_INFO "DRHD %Lx: EIM not supported by DRHD, "
-			       " ecap %Lx\n", drhd->reg_base_addr, iommu->ecap);
+			pr_info("%s does not support EIM\n", iommu->name);
 			eim = 0;
 		}
+	}
+
 	eim_mode = eim;
 	if (eim)
 		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");
 
-	/*
-	 * Enable queued invalidation for all the DRHD's.
-	 */
+	/* Do the initializations early */
 	for_each_iommu(iommu, drhd) {
-		int ret = dmar_enable_qi(iommu);
-
-		if (ret) {
-			printk(KERN_ERR "DRHD %Lx: failed to enable queued, "
-			       " invalidation, ecap %Lx, ret %d\n",
-			       drhd->reg_base_addr, iommu->ecap, ret);
+		if (intel_setup_irq_remapping(iommu)) {
+			pr_err("Failed to setup irq remapping for %s\n",
+			       iommu->name);
 			goto error;
 		}
 	}
 
+	return 0;
+
+error:
+	intel_cleanup_irq_remapping();
+	return -ENODEV;
+}
+
+/*
+ * Set Posted-Interrupts capability.
+ */
+static inline void set_irq_posting_cap(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	if (!disable_irq_post) {
+		intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;
+
+		for_each_iommu(iommu, drhd)
+			if (!cap_pi_support(iommu->cap)) {
+				intel_irq_remap_ops.capability &=
+						~(1 << IRQ_POSTING_CAP);
+				break;
+			}
+	}
+}
+
+static int __init intel_enable_irq_remapping(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool setup = false;
+
 	/*
 	 * Setup Interrupt-remapping for all the DRHD's now.
 	 */
 	for_each_iommu(iommu, drhd) {
-		iommu_set_irq_remapping(iommu, eim);
+		if (!ir_pre_enabled(iommu))
+			iommu_enable_irq_remapping(iommu);
 		setup = true;
 	}
 
@@ -702,16 +756,11 @@ static int __init intel_enable_irq_remapping(void)
 
 	irq_remapping_enabled = 1;
 
-	/*
-	 * VT-d has a different layout for IO-APIC entries when
-	 * interrupt remapping is enabled. So it needs a special routine
-	 * to print IO-APIC entries for debugging purposes too.
-	 */
-	x86_io_apic_ops.print_entries = intel_ir_io_apic_print_entries;
+	set_irq_posting_cap();
 
-	pr_info("Enabled IRQ remapping in %s mode\n", eim ? "x2apic" : "xapic");
+	pr_info("Enabled IRQ remapping in %s mode\n", eim_mode ? "x2apic" : "xapic");
 
-	return eim ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
+	return eim_mode ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;
 
 error:
 	intel_cleanup_irq_remapping();
@@ -909,6 +958,12 @@ static void disable_irq_remapping(void)
 
 		iommu_disable_irq_remapping(iommu);
 	}
+
+	/*
+	 * Clear Posted-Interrupts capability.
+	 */
+	if (!disable_irq_post)
+		intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
 }
 
 static int reenable_irq_remapping(int eim)
@@ -930,12 +985,15 @@ static int reenable_irq_remapping(int eim)
 
 		/* Set up interrupt remapping for iommu.*/
 		iommu_set_irq_remapping(iommu, eim);
+		iommu_enable_irq_remapping(iommu);
 		setup = true;
 	}
 
 	if (!setup)
 		goto error;
 
+	set_irq_posting_cap();
+
 	return 0;
 
 error:
@@ -945,8 +1003,7 @@ error:
 	return -1;
 }
 
-static void prepare_irte(struct irte *irte, int vector,
-			 unsigned int dest)
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 {
 	memset(irte, 0, sizeof(*irte));
 
@@ -966,76 +1023,63 @@ static void prepare_irte(struct irte *irte, int vector,
 	irte->redir_hint = 1;
 }
 
-static int intel_setup_ioapic_entry(int irq,
-				    struct IO_APIC_route_entry *route_entry,
-				    unsigned int destination, int vector,
-				    struct io_apic_irq_attr *attr)
+static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
 {
-	int ioapic_id = mpc_ioapic_id(attr->ioapic);
-	struct intel_iommu *iommu;
-	struct IR_IO_APIC_route_entry *entry;
-	struct irte irte;
-	int index;
-
-	down_read(&dmar_global_lock);
-	iommu = map_ioapic_to_ir(ioapic_id);
-	if (!iommu) {
-		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
-		index = -ENODEV;
-	} else {
-		index = alloc_irte(iommu, irq, 1);
-		if (index < 0) {
-			pr_warn("Failed to allocate IRTE for ioapic %d\n",
-				ioapic_id);
-			index = -ENOMEM;
-		}
-	}
-	up_read(&dmar_global_lock);
-	if (index < 0)
-		return index;
-
-	prepare_irte(&irte, vector, destination);
+	struct intel_iommu *iommu = NULL;
 
-	/* Set source-id of interrupt request */
-	set_ioapic_sid(&irte, ioapic_id);
+	if (!info)
+		return NULL;
 
-	modify_irte(irq, &irte);
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		iommu = map_ioapic_to_ir(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		iommu = map_hpet_to_ir(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
 
-	apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
-		"Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
-		"Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
-		"Avail:%X Vector:%02X Dest:%08X "
-		"SID:%04X SQ:%X SVT:%X)\n",
-		attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
-		irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
-		irte.avail, irte.vector, irte.dest_id,
-		irte.sid, irte.sq, irte.svt);
+	return iommu ? iommu->ir_domain : NULL;
+}
 
-	entry = (struct IR_IO_APIC_route_entry *)route_entry;
-	memset(entry, 0, sizeof(*entry));
+static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
+{
+	struct intel_iommu *iommu;
 
-	entry->index2	= (index >> 15) & 0x1;
-	entry->zero	= 0;
-	entry->format	= 1;
-	entry->index	= (index & 0x7fff);
-	/*
-	 * IO-APIC RTE will be configured with virtual vector.
-	 * irq handler will do the explicit EOI to the io-apic.
-	 */
-	entry->vector	= attr->ioapic_pin;
-	entry->mask	= 0;			/* enable IRQ */
-	entry->trigger	= attr->trigger;
-	entry->polarity	= attr->polarity;
+	if (!info)
+		return NULL;
 
-	/* Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		if (iommu)
+			return iommu->ir_msi_domain;
+		break;
+	default:
+		break;
+	}
 
-	return 0;
+	return NULL;
 }
 
+struct irq_remap_ops intel_irq_remap_ops = {
+	.prepare		= intel_prepare_irq_remapping,
+	.enable			= intel_enable_irq_remapping,
+	.disable		= disable_irq_remapping,
+	.reenable		= reenable_irq_remapping,
+	.enable_faulting	= enable_drhd_fault_handling,
+	.get_ir_irq_domain	= intel_get_ir_irq_domain,
+	.get_irq_domain		= intel_get_irq_domain,
+};
+
 /*
  * Migrate the IO-APIC irq in the presence of intr-remapping.
  *
@@ -1051,170 +1095,281 @@ static int intel_setup_ioapic_entry(int irq,
  * is used to migrate MSI irq's in the presence of interrupt-remapping.
  */
 static int
-intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-			  bool force)
+intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
 {
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct irte *irte = &ir_data->irte_entry;
 	struct irq_cfg *cfg = irqd_cfg(data);
-	unsigned int dest, irq = data->irq;
-	struct irte irte;
-	int err;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -EINVAL;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
-
-	if (get_irte(irq, &irte))
-		return -EBUSY;
-
-	err = assign_irq_vector(irq, cfg, mask);
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(cfg->domain, mask, &dest);
-	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
+	struct irq_data *parent = data->parent_data;
+	int ret;
 
-	irte.vector = cfg->vector;
-	irte.dest_id = IRTE_DEST(dest);
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
 
 	/*
 	 * Atomically updates the IRTE with the new destination, vector
 	 * and flushes the interrupt entry cache.
 	 */
-	modify_irte(irq, &irte);
+	irte->vector = cfg->vector;
+	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+
+	/* Update the hardware only if the interrupt is in remapped mode. */
+	if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
+		modify_irte(&ir_data->irq_2_iommu, irte);
 
 	/*
 	 * After this point, all the interrupts will start arriving
 	 * at the new destination. So, time to cleanup the previous
 	 * vector allocation.
 	 */
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
+	send_cleanup_vector(cfg);
 
-	cpumask_copy(data->affinity, mask);
-	return 0;
+	return IRQ_SET_MASK_OK_DONE;
 }
 
-static void intel_compose_msi_msg(struct pci_dev *pdev,
-				  unsigned int irq, unsigned int dest,
-				  struct msi_msg *msg, u8 hpet_id)
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+				     struct msi_msg *msg)
 {
-	struct irq_cfg *cfg;
-	struct irte irte;
-	u16 sub_handle = 0;
-	int ir_index;
-
-	cfg = irq_cfg(irq);
+	struct intel_ir_data *ir_data = irq_data->chip_data;
 
-	ir_index = map_irq_to_irte_handle(irq, &sub_handle);
-	BUG_ON(ir_index == -1);
+	*msg = ir_data->msi_entry;
+}
 
-	prepare_irte(&irte, cfg->vector, dest);
+static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
+{
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct vcpu_data *vcpu_pi_info = info;
 
-	/* Set source-id of interrupt request */
-	if (pdev)
-		set_msi_sid(&irte, pdev);
-	else
-		set_hpet_sid(&irte, hpet_id);
+	/* stop posting interrupts, back to remapping mode */
+	if (!vcpu_pi_info) {
+		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
+	} else {
+		struct irte irte_pi;
 
-	modify_irte(irq, &irte);
+		/*
+		 * We are not caching the posted interrupt entry. We
+		 * copy the data from the remapped entry and modify
+		 * the fields which are relevant for posted mode. The
+		 * cached remapped entry is used for switching back to
+		 * remapped mode.
+		 */
+		memset(&irte_pi, 0, sizeof(irte_pi));
+		dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);
+
+		/* Update the posted mode fields */
+		irte_pi.p_pst = 1;
+		irte_pi.p_urgent = 0;
+		irte_pi.p_vector = vcpu_pi_info->vector;
+		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
+		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+				~(-1UL << PDA_HIGH_BIT);
+
+		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
+	}
 
-	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->data = sub_handle;
-	msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
-			  MSI_ADDR_IR_SHV |
-			  MSI_ADDR_IR_INDEX1(ir_index) |
-			  MSI_ADDR_IR_INDEX2(ir_index);
+	return 0;
 }
 
-/*
- * Map the PCI dev to the corresponding remapping hardware unit
- * and allocate 'nvec' consecutive interrupt-remapping table entries
- * in it.
- */
-static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
+static struct irq_chip intel_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = intel_ir_set_affinity,
+	.irq_compose_msi_msg = intel_ir_compose_msi_msg,
+	.irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
+};
+
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+					     struct irq_cfg *irq_cfg,
+					     struct irq_alloc_info *info,
+					     int index, int sub_handle)
 {
-	struct intel_iommu *iommu;
-	int index;
+	struct IR_IO_APIC_route_entry *entry;
+	struct irte *irte = &data->irte_entry;
+	struct msi_msg *msg = &data->msi_entry;
+
+	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Set source-id of interrupt request */
+		set_ioapic_sid(irte, info->ioapic_id);
+		apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
+			info->ioapic_id, irte->present, irte->fpd,
+			irte->dst_mode, irte->redir_hint,
+			irte->trigger_mode, irte->dlvry_mode,
+			irte->avail, irte->vector, irte->dest_id,
+			irte->sid, irte->sq, irte->svt);
+
+		entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->index2	= (index >> 15) & 0x1;
+		entry->zero	= 0;
+		entry->format	= 1;
+		entry->index	= (index & 0x7fff);
+		/*
+		 * IO-APIC RTE will be configured with virtual vector.
+		 * irq handler will do the explicit EOI to the io-apic.
+		 */
+		entry->vector	= info->ioapic_pin;
+		entry->mask	= 0;			/* enable IRQ */
+		entry->trigger	= info->ioapic_trigger;
+		entry->polarity	= info->ioapic_polarity;
+		if (info->ioapic_trigger)
+			entry->mask = 1; /* Mask level triggered irqs. */
+		break;
+
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
+			set_hpet_sid(irte, info->hpet_id);
+		else
+			set_msi_sid(irte, info->msi_dev);
+
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->data = sub_handle;
+		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+				  MSI_ADDR_IR_SHV |
+				  MSI_ADDR_IR_INDEX1(index) |
+				  MSI_ADDR_IR_INDEX2(index);
+		break;
+
+	default:
+		BUG_ON(1);
+		break;
+	}
+}
 
-	down_read(&dmar_global_lock);
-	iommu = map_dev_to_ir(dev);
-	if (!iommu) {
-		printk(KERN_ERR
-		       "Unable to map PCI %s to iommu\n", pci_name(dev));
-		index = -ENOENT;
-	} else {
-		index = alloc_irte(iommu, irq, nvec);
-		if (index < 0) {
-			printk(KERN_ERR
-			       "Unable to allocate %d IRTE for PCI %s\n",
-			       nvec, pci_name(dev));
-			index = -ENOSPC;
+static void intel_free_irq_resources(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct intel_ir_data *data;
+	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
+	int i;
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irq_iommu = &data->irq_2_iommu;
+			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+			clear_entries(irq_iommu);
+			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			irq_domain_reset_irq_data(irq_data);
+			kfree(data);
 		}
 	}
-	up_read(&dmar_global_lock);
-
-	return index;
 }
 
-static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
-			       int index, int sub_handle)
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
 {
-	struct intel_iommu *iommu;
-	int ret = -ENOENT;
+	struct intel_iommu *iommu = domain->host_data;
+	struct irq_alloc_info *info = arg;
+	struct intel_ir_data *data, *ird;
+	struct irq_data *irq_data;
+	struct irq_cfg *irq_cfg;
+	int i, ret, index;
+
+	if (!info || !iommu)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contiguous CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
 
 	down_read(&dmar_global_lock);
-	iommu = map_dev_to_ir(pdev);
-	if (iommu) {
-		/*
-		 * setup the mapping between the irq and the IRTE
-		 * base index, the sub_handle pointing to the
-		 * appropriate interrupt remap table entry.
-		 */
-		set_irte_irq(irq, iommu, index, sub_handle);
-		ret = 0;
-	}
+	index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
 	up_read(&dmar_global_lock);
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		irq_cfg = irqd_cfg(irq_data);
+		if (!irq_data || !irq_cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		if (i > 0) {
+			ird = kzalloc(sizeof(*ird), GFP_KERNEL);
+			if (!ird)
+				goto out_free_data;
+			/* Initialize the common data */
+			ird->irq_2_iommu = data->irq_2_iommu;
+			ird->irq_2_iommu.sub_handle = i;
+		} else {
+			ird = data;
+		}
 
+		irq_data->hwirq = (index << 16) + i;
+		irq_data->chip_data = ird;
+		irq_data->chip = &intel_ir_chip;
+		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
+
+out_free_data:
+	intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 	return ret;
 }
 
-static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
+static void intel_irq_remapping_free(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
 {
-	int ret = -1;
-	struct intel_iommu *iommu;
-	int index;
+	intel_free_irq_resources(domain, virq, nr_irqs);
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
 
-	down_read(&dmar_global_lock);
-	iommu = map_hpet_to_ir(id);
-	if (iommu) {
-		index = alloc_irte(iommu, irq, 1);
-		if (index >= 0)
-			ret = 0;
-	}
-	up_read(&dmar_global_lock);
+static void intel_irq_remapping_activate(struct irq_domain *domain,
+					 struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
 
-	return ret;
+	modify_irte(&data->irq_2_iommu, &data->irte_entry);
 }
 
-struct irq_remap_ops intel_irq_remap_ops = {
-	.prepare		= intel_prepare_irq_remapping,
-	.enable			= intel_enable_irq_remapping,
-	.disable		= disable_irq_remapping,
-	.reenable		= reenable_irq_remapping,
-	.enable_faulting	= enable_drhd_fault_handling,
-	.setup_ioapic_entry	= intel_setup_ioapic_entry,
-	.set_affinity		= intel_ioapic_set_affinity,
-	.free_irq		= free_irte,
-	.compose_msi_msg	= intel_compose_msi_msg,
-	.msi_alloc_irq		= intel_msi_alloc_irq,
-	.msi_setup_irq		= intel_msi_setup_irq,
-	.alloc_hpet_msi		= intel_alloc_hpet_msi,
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+					   struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
+	struct irte entry;
+
+	memset(&entry, 0, sizeof(entry));
+	modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static struct irq_domain_ops intel_ir_domain_ops = {
+	.alloc = intel_irq_remapping_alloc,
+	.free = intel_irq_remapping_free,
+	.activate = intel_irq_remapping_activate,
+	.deactivate = intel_irq_remapping_deactivate,
 };
 
 /*
@@ -1242,28 +1397,12 @@ static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu)
 	/* Setup Interrupt-remapping now. */
 	ret = intel_setup_irq_remapping(iommu);
 	if (ret) {
-		pr_err("DRHD %Lx: failed to allocate resource\n",
-		       iommu->reg_phys);
-		ir_remove_ioapic_hpet_scope(iommu);
-		return ret;
-	}
-
-	if (!iommu->qi) {
-		/* Clear previous faults. */
-		dmar_fault(-1, iommu);
-		iommu_disable_irq_remapping(iommu);
-		dmar_disable_qi(iommu);
-	}
-
-	/* Enable queued invalidation */
-	ret = dmar_enable_qi(iommu);
-	if (!ret) {
-		iommu_set_irq_remapping(iommu, eim);
-	} else {
-		pr_err("DRHD %Lx: failed to enable queued invalidation, ecap %Lx, ret %d\n",
-		       iommu->reg_phys, iommu->ecap, ret);
+		pr_err("Failed to setup irq remapping for %s\n",
+		       iommu->name);
 		intel_teardown_irq_remapping(iommu);
 		ir_remove_ioapic_hpet_scope(iommu);
+	} else {
+		iommu_enable_irq_remapping(iommu);
 	}
 
 	return ret;
@@ -1280,6 +1419,9 @@ int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
 		return -EINVAL;
 	if (!ecap_ir_support(iommu->ecap))
 		return 0;
+	if (irq_remapping_cap(IRQ_POSTING_CAP) &&
+	    !cap_pi_support(iommu->cap))
+		return -EBUSY;
 
 	if (insert) {
 		if (!iommu->ir_table)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d4f527e56679..49e7542510d1 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -16,7 +16,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#define pr_fmt(fmt)    "%s: " fmt, __func__
+#define pr_fmt(fmt)    "iommu: " fmt
 
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -51,6 +51,8 @@ struct iommu_group {
 	void (*iommu_data_release)(void *iommu_data);
 	char *name;
 	int id;
+	struct iommu_domain *default_domain;
+	struct iommu_domain *domain;
 };
 
 struct iommu_device {
@@ -75,6 +77,15 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 #define to_iommu_group(_kobj)		\
 	container_of(_kobj, struct iommu_group, kobj)
 
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+						 unsigned type);
+static int __iommu_attach_device(struct iommu_domain *domain,
+				 struct device *dev);
+static int __iommu_attach_group(struct iommu_domain *domain,
+				struct iommu_group *group);
+static void __iommu_detach_group(struct iommu_domain *domain,
+				 struct iommu_group *group);
+
 static ssize_t iommu_group_attr_show(struct kobject *kobj,
 				     struct attribute *__attr, char *buf)
 {
@@ -128,6 +139,8 @@ static void iommu_group_release(struct kobject *kobj)
 {
 	struct iommu_group *group = to_iommu_group(kobj);
 
+	pr_debug("Releasing group %d\n", group->id);
+
 	if (group->iommu_data_release)
 		group->iommu_data_release(group->iommu_data);
 
@@ -135,6 +148,9 @@ static void iommu_group_release(struct kobject *kobj)
 	ida_remove(&iommu_group_ida, group->id);
 	mutex_unlock(&iommu_group_mutex);
 
+	if (group->default_domain)
+		iommu_domain_free(group->default_domain);
+
 	kfree(group->name);
 	kfree(group);
 }
@@ -207,6 +223,8 @@ again:
 	 */
 	kobject_put(&group->kobj);
 
+	pr_debug("Allocated group %d\n", group->id);
+
 	return group;
 }
 EXPORT_SYMBOL_GPL(iommu_group_alloc);
@@ -307,6 +325,52 @@ int iommu_group_set_name(struct iommu_group *group, const char *name)
 }
 EXPORT_SYMBOL_GPL(iommu_group_set_name);
 
+static int iommu_group_create_direct_mappings(struct iommu_group *group,
+					      struct device *dev)
+{
+	struct iommu_domain *domain = group->default_domain;
+	struct iommu_dm_region *entry;
+	struct list_head mappings;
+	unsigned long pg_size;
+	int ret = 0;
+
+	if (!domain || domain->type != IOMMU_DOMAIN_DMA)
+		return 0;
+
+	BUG_ON(!domain->ops->pgsize_bitmap);
+
+	pg_size = 1UL << __ffs(domain->ops->pgsize_bitmap);
+	INIT_LIST_HEAD(&mappings);
+
+	iommu_get_dm_regions(dev, &mappings);
+
+	/* We need to consider overlapping regions for different devices */
+	list_for_each_entry(entry, &mappings, list) {
+		dma_addr_t start, end, addr;
+
+		start = ALIGN(entry->start, pg_size);
+		end   = ALIGN(entry->start + entry->length, pg_size);
+
+		for (addr = start; addr < end; addr += pg_size) {
+			phys_addr_t phys_addr;
+
+			phys_addr = iommu_iova_to_phys(domain, addr);
+			if (phys_addr)
+				continue;
+
+			ret = iommu_map(domain, addr, addr, pg_size, entry->prot);
+			if (ret)
+				goto out;
+		}
+
+	}
+
+out:
+	iommu_put_dm_regions(dev, &mappings);
+
+	return ret;
+}
+
 /**
  * iommu_group_add_device - add a device to an iommu group
  * @group: the group into which to add the device (reference should be held)
@@ -363,8 +427,12 @@ rename:
 
 	dev->iommu_group = group;
 
+	iommu_group_create_direct_mappings(group, dev);
+
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
+	if (group->domain)
+		__iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
 
 	/* Notify any listeners about change to group. */
@@ -372,6 +440,9 @@ rename:
 				     IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev);
 
 	trace_add_device_to_group(group->id, dev);
+
+	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
@@ -388,6 +459,8 @@ void iommu_group_remove_device(struct device *dev)
 	struct iommu_group *group = dev->iommu_group;
 	struct iommu_device *tmp_device, *device = NULL;
 
+	pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);
+
 	/* Pre-notify listeners that a device is being removed. */
 	blocking_notifier_call_chain(&group->notifier,
 				     IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev);
@@ -417,6 +490,17 @@ void iommu_group_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
+static int iommu_group_device_count(struct iommu_group *group)
+{
+	struct iommu_device *entry;
+	int ret = 0;
+
+	list_for_each_entry(entry, &group->devices, list)
+		ret++;
+
+	return ret;
+}
+
 /**
  * iommu_group_for_each_dev - iterate over each device in the group
  * @group: the group
@@ -428,19 +512,30 @@ EXPORT_SYMBOL_GPL(iommu_group_remove_device);
  * The group->mutex is held across callbacks, which will block calls to
  * iommu_group_add/remove_device.
  */
-int iommu_group_for_each_dev(struct iommu_group *group, void *data,
-			     int (*fn)(struct device *, void *))
+static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
+				      int (*fn)(struct device *, void *))
 {
 	struct iommu_device *device;
 	int ret = 0;
 
-	mutex_lock(&group->mutex);
 	list_for_each_entry(device, &group->devices, list) {
 		ret = fn(device->dev, data);
 		if (ret)
 			break;
 	}
+	return ret;
+}
+
+
+int iommu_group_for_each_dev(struct iommu_group *group, void *data,
+			     int (*fn)(struct device *, void *))
+{
+	int ret;
+
+	mutex_lock(&group->mutex);
+	ret = __iommu_group_for_each_dev(group, data, fn);
 	mutex_unlock(&group->mutex);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_for_each_dev);
@@ -692,7 +787,19 @@ static struct iommu_group *iommu_group_get_for_pci_dev(struct pci_dev *pdev)
 		return group;
 
 	/* No shared group found, allocate new */
-	return iommu_group_alloc();
+	group = iommu_group_alloc();
+	if (IS_ERR(group))
+		return NULL;
+
+	/*
+	 * Try to allocate a default domain - needs support from the
+	 * IOMMU driver.
+	 */
+	group->default_domain = __iommu_domain_alloc(pdev->dev.bus,
+						     IOMMU_DOMAIN_DMA);
+	group->domain = group->default_domain;
+
+	return group;
 }
 
 /**
@@ -731,6 +838,11 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	return group;
 }
 
+struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
+{
+	return group->default_domain;
+}
+
 static int add_iommu_group(struct device *dev, void *data)
 {
 	struct iommu_callback_data *cb = data;
@@ -741,7 +853,16 @@ static int add_iommu_group(struct device *dev, void *data)
 
 	WARN_ON(dev->iommu_group);
 
-	ops->add_device(dev);
+	return ops->add_device(dev);
+}
+
+static int remove_iommu_group(struct device *dev, void *data)
+{
+	struct iommu_callback_data *cb = data;
+	const struct iommu_ops *ops = cb->ops;
+
+	if (ops->remove_device && dev->iommu_group)
+		ops->remove_device(dev);
 
 	return 0;
 }
@@ -761,7 +882,7 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 	if (action == BUS_NOTIFY_ADD_DEVICE) {
 		if (ops->add_device)
 			return ops->add_device(dev);
-	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
+	} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
 		if (ops->remove_device && dev->iommu_group) {
 			ops->remove_device(dev);
 			return 0;
@@ -814,19 +935,25 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
 	nb->notifier_call = iommu_bus_notifier;
 
 	err = bus_register_notifier(bus, nb);
-	if (err) {
-		kfree(nb);
-		return err;
-	}
+	if (err)
+		goto out_free;
 
 	err = bus_for_each_dev(bus, NULL, &cb, add_iommu_group);
-	if (err) {
-		bus_unregister_notifier(bus, nb);
-		kfree(nb);
-		return err;
-	}
+	if (err)
+		goto out_err;
+
 
 	return 0;
+
+out_err:
+	/* Clean up */
+	bus_for_each_dev(bus, NULL, &cb, remove_iommu_group);
+	bus_unregister_notifier(bus, nb);
+
+out_free:
+	kfree(nb);
+
+	return err;
 }
 
 /**
@@ -898,22 +1025,28 @@ void iommu_set_fault_handler(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_set_fault_handler);
 
-struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+						 unsigned type)
 {
 	struct iommu_domain *domain;
 
 	if (bus == NULL || bus->iommu_ops == NULL)
 		return NULL;
 
-	domain = bus->iommu_ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED);
+	domain = bus->iommu_ops->domain_alloc(type);
 	if (!domain)
 		return NULL;
 
 	domain->ops  = bus->iommu_ops;
-	domain->type = IOMMU_DOMAIN_UNMANAGED;
+	domain->type = type;
 
 	return domain;
 }
+
+struct iommu_domain *iommu_domain_alloc(struct bus_type *bus)
+{
+	return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED);
+}
 EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
 void iommu_domain_free(struct iommu_domain *domain)
@@ -922,7 +1055,8 @@ void iommu_domain_free(struct iommu_domain *domain)
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
 
-int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+static int __iommu_attach_device(struct iommu_domain *domain,
+				 struct device *dev)
 {
 	int ret;
 	if (unlikely(domain->ops->attach_dev == NULL))
@@ -933,9 +1067,38 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 		trace_attach_device_to_domain(dev);
 	return ret;
 }
+
+int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	group = iommu_group_get(dev);
+	/* FIXME: Remove this when groups a mandatory for iommu drivers */
+	if (group == NULL)
+		return __iommu_attach_device(domain, dev);
+
+	/*
+	 * We have a group - lock it to make sure the device-count doesn't
+	 * change while we are attaching
+	 */
+	mutex_lock(&group->mutex);
+	ret = -EINVAL;
+	if (iommu_group_device_count(group) != 1)
+		goto out_unlock;
+
+	ret = __iommu_attach_group(domain, group);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+static void __iommu_detach_device(struct iommu_domain *domain,
+				  struct device *dev)
 {
 	if (unlikely(domain->ops->detach_dev == NULL))
 		return;
@@ -943,8 +1106,48 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
 	domain->ops->detach_dev(domain, dev);
 	trace_detach_device_from_domain(dev);
 }
+
+void iommu_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	/* FIXME: Remove this when groups a mandatory for iommu drivers */
+	if (group == NULL)
+		return __iommu_detach_device(domain, dev);
+
+	mutex_lock(&group->mutex);
+	if (iommu_group_device_count(group) != 1) {
+		WARN_ON(1);
+		goto out_unlock;
+	}
+
+	__iommu_detach_group(domain, group);
+
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+}
 EXPORT_SYMBOL_GPL(iommu_detach_device);
 
+struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
+{
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	/* FIXME: Remove this when groups a mandatory for iommu drivers */
+	if (group == NULL)
+		return NULL;
+
+	domain = group->domain;
+
+	iommu_group_put(group);
+
+	return domain;
+}
+EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
+
 /*
  * IOMMU groups are really the natrual working unit of the IOMMU, but
  * the IOMMU API works on domains and devices.  Bridge that gap by
@@ -959,13 +1162,34 @@ static int iommu_group_do_attach_device(struct device *dev, void *data)
 {
 	struct iommu_domain *domain = data;
 
-	return iommu_attach_device(domain, dev);
+	return __iommu_attach_device(domain, dev);
+}
+
+static int __iommu_attach_group(struct iommu_domain *domain,
+				struct iommu_group *group)
+{
+	int ret;
+
+	if (group->default_domain && group->domain != group->default_domain)
+		return -EBUSY;
+
+	ret = __iommu_group_for_each_dev(group, domain,
+					 iommu_group_do_attach_device);
+	if (ret == 0)
+		group->domain = domain;
+
+	return ret;
 }
 
 int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
 {
-	return iommu_group_for_each_dev(group, domain,
-					iommu_group_do_attach_device);
+	int ret;
+
+	mutex_lock(&group->mutex);
+	ret = __iommu_attach_group(domain, group);
+	mutex_unlock(&group->mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_attach_group);
 
@@ -973,14 +1197,40 @@ static int iommu_group_do_detach_device(struct device *dev, void *data)
 {
 	struct iommu_domain *domain = data;
 
-	iommu_detach_device(domain, dev);
+	__iommu_detach_device(domain, dev);
 
 	return 0;
 }
 
+static void __iommu_detach_group(struct iommu_domain *domain,
+				 struct iommu_group *group)
+{
+	int ret;
+
+	if (!group->default_domain) {
+		__iommu_group_for_each_dev(group, domain,
+					   iommu_group_do_detach_device);
+		group->domain = NULL;
+		return;
+	}
+
+	if (group->domain == group->default_domain)
+		return;
+
+	/* Detach by re-attaching to the default domain */
+	ret = __iommu_group_for_each_dev(group, group->default_domain,
+					 iommu_group_do_attach_device);
+	if (ret != 0)
+		WARN_ON(1);
+	else
+		group->domain = group->default_domain;
+}
+
 void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group)
 {
-	iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device);
+	mutex_lock(&group->mutex);
+	__iommu_detach_group(domain, group);
+	mutex_unlock(&group->mutex);
 }
 EXPORT_SYMBOL_GPL(iommu_detach_group);
 
@@ -1207,7 +1457,7 @@ static int __init iommu_init(void)
 
 	return 0;
 }
-arch_initcall(iommu_init);
+core_initcall(iommu_init);
 
 int iommu_domain_get_attr(struct iommu_domain *domain,
 			  enum iommu_attr attr, void *data)
@@ -1273,3 +1523,72 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
+
+void iommu_get_dm_regions(struct device *dev, struct list_head *list)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->get_dm_regions)
+		ops->get_dm_regions(dev, list);
+}
+
+void iommu_put_dm_regions(struct device *dev, struct list_head *list)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->put_dm_regions)
+		ops->put_dm_regions(dev, list);
+}
+
+/* Request that a device is direct mapped by the IOMMU */
+int iommu_request_dm_for_dev(struct device *dev)
+{
+	struct iommu_domain *dm_domain;
+	struct iommu_group *group;
+	int ret;
+
+	/* Device must already be in a group before calling this function */
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
+
+	mutex_lock(&group->mutex);
+
+	/* Check if the default domain is already direct mapped */
+	ret = 0;
+	if (group->default_domain &&
+	    group->default_domain->type == IOMMU_DOMAIN_IDENTITY)
+		goto out;
+
+	/* Don't change mappings of existing devices */
+	ret = -EBUSY;
+	if (iommu_group_device_count(group) != 1)
+		goto out;
+
+	/* Allocate a direct mapped domain */
+	ret = -ENOMEM;
+	dm_domain = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_IDENTITY);
+	if (!dm_domain)
+		goto out;
+
+	/* Attach the device to the domain */
+	ret = __iommu_attach_group(dm_domain, group);
+	if (ret) {
+		iommu_domain_free(dm_domain);
+		goto out;
+	}
+
+	/* Make the direct mapped domain the default for this group */
+	if (group->default_domain)
+		iommu_domain_free(group->default_domain);
+	group->default_domain = dm_domain;
+
+	pr_info("Using direct mapping for device %s\n", dev_name(dev));
+
+	ret = 0;
+out:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 9dd8208312c2..b7c3d923f3e1 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -227,6 +227,7 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
 	/* Figure out where to put new node */
 	while (*new) {
 		struct iova *this = container_of(*new, struct iova, node);
+
 		parent = *new;
 
 		if (iova->pfn_lo < this->pfn_lo)
@@ -350,6 +351,7 @@ void
 free_iova(struct iova_domain *iovad, unsigned long pfn)
 {
 	struct iova *iova = find_iova(iovad, pfn);
+
 	if (iova)
 		__free_iova(iovad, iova);
 
@@ -369,6 +371,7 @@ void put_iova_domain(struct iova_domain *iovad)
 	node = rb_first(&iovad->rbroot);
 	while (node) {
 		struct iova *iova = container_of(node, struct iova, node);
+
 		rb_erase(node, &iovad->rbroot);
 		free_iova_mem(iova);
 		node = rb_first(&iovad->rbroot);
@@ -482,6 +485,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
 		struct iova *iova = container_of(node, struct iova, node);
 		struct iova *new_iova;
+
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
 		if (!new_iova)
 			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c
index 390079ee1350..2d9993062ded 100644
--- a/drivers/iommu/irq_remapping.c
+++ b/drivers/iommu/irq_remapping.c
@@ -6,6 +6,7 @@
 #include <linux/msi.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
+#include <linux/irqdomain.h>
 
 #include <asm/hw_irq.h>
 #include <asm/irq_remapping.h>
@@ -21,21 +22,11 @@ int irq_remap_broken;
 int disable_sourceid_checking;
 int no_x2apic_optout;
 
+int disable_irq_post = 1;
+
 static int disable_irq_remap;
 static struct irq_remap_ops *remap_ops;
 
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec);
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
-				  int index, int sub_handle);
-static int set_remapped_irq_affinity(struct irq_data *data,
-				     const struct cpumask *mask,
-				     bool force);
-
-static bool irq_remapped(struct irq_cfg *cfg)
-{
-	return (cfg->remapped == 1);
-}
-
 static void irq_remapping_disable_io_apic(void)
 {
 	/*
@@ -49,117 +40,9 @@ static void irq_remapping_disable_io_apic(void)
 		disconnect_bsp_APIC(0);
 }
 
-static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
-{
-	int ret, sub_handle, nvec_pow2, index = 0;
-	unsigned int irq;
-	struct msi_desc *msidesc;
-
-	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
-
-	irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev));
-	if (irq == 0)
-		return -ENOSPC;
-
-	nvec_pow2 = __roundup_pow_of_two(nvec);
-	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
-		if (!sub_handle) {
-			index = msi_alloc_remapped_irq(dev, irq, nvec_pow2);
-			if (index < 0) {
-				ret = index;
-				goto error;
-			}
-		} else {
-			ret = msi_setup_remapped_irq(dev, irq + sub_handle,
-						     index, sub_handle);
-			if (ret < 0)
-				goto error;
-		}
-		ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
-		if (ret < 0)
-			goto error;
-	}
-	return 0;
-
-error:
-	irq_free_hwirqs(irq, nvec);
-
-	/*
-	 * Restore altered MSI descriptor fields and prevent just destroyed
-	 * IRQs from tearing down again in default_teardown_msi_irqs()
-	 */
-	msidesc->irq = 0;
-
-	return ret;
-}
-
-static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
-{
-	int node, ret, sub_handle, index = 0;
-	struct msi_desc *msidesc;
-	unsigned int irq;
-
-	node		= dev_to_node(&dev->dev);
-	sub_handle	= 0;
-
-	list_for_each_entry(msidesc, &dev->msi_list, list) {
-
-		irq = irq_alloc_hwirq(node);
-		if (irq == 0)
-			return -1;
-
-		if (sub_handle == 0)
-			ret = index = msi_alloc_remapped_irq(dev, irq, nvec);
-		else
-			ret = msi_setup_remapped_irq(dev, irq, index, sub_handle);
-
-		if (ret < 0)
-			goto error;
-
-		ret = setup_msi_irq(dev, msidesc, irq, 0);
-		if (ret < 0)
-			goto error;
-
-		sub_handle += 1;
-		irq        += 1;
-	}
-
-	return 0;
-
-error:
-	irq_free_hwirq(irq);
-	return ret;
-}
-
-static int irq_remapping_setup_msi_irqs(struct pci_dev *dev,
-					int nvec, int type)
-{
-	if (type == PCI_CAP_ID_MSI)
-		return do_setup_msi_irqs(dev, nvec);
-	else
-		return do_setup_msix_irqs(dev, nvec);
-}
-
-static void eoi_ioapic_pin_remapped(int apic, int pin, int vector)
-{
-	/*
-	 * Intr-remapping uses pin number as the virtual vector
-	 * in the RTE. Actual vector is programmed in
-	 * intr-remapping table entry. Hence for the io-apic
-	 * EOI we use the pin number.
-	 */
-	io_apic_eoi(apic, pin);
-}
-
 static void __init irq_remapping_modify_x86_ops(void)
 {
 	x86_io_apic_ops.disable		= irq_remapping_disable_io_apic;
-	x86_io_apic_ops.set_affinity	= set_remapped_irq_affinity;
-	x86_io_apic_ops.setup_entry	= setup_ioapic_remapped_entry;
-	x86_io_apic_ops.eoi_ioapic_pin	= eoi_ioapic_pin_remapped;
-	x86_msi.setup_msi_irqs		= irq_remapping_setup_msi_irqs;
-	x86_msi.setup_hpet_msi		= setup_hpet_msi_remapped;
-	x86_msi.compose_msi_msg		= compose_remapped_msi_msg;
 }
 
 static __init int setup_nointremap(char *str)
@@ -198,6 +81,15 @@ void set_irq_remapping_broken(void)
 	irq_remap_broken = 1;
 }
 
+bool irq_remapping_cap(enum irq_remap_cap cap)
+{
+	if (!remap_ops || disable_irq_post)
+		return 0;
+
+	return (remap_ops->capability & (1 << cap));
+}
+EXPORT_SYMBOL_GPL(irq_remapping_cap);
+
 int __init irq_remapping_prepare(void)
 {
 	if (disable_irq_remap)
@@ -254,113 +146,48 @@ int __init irq_remap_enable_fault_handling(void)
 	return remap_ops->enable_faulting();
 }
 
-int setup_ioapic_remapped_entry(int irq,
-				struct IO_APIC_route_entry *entry,
-				unsigned int destination, int vector,
-				struct io_apic_irq_attr *attr)
-{
-	if (!remap_ops->setup_ioapic_entry)
-		return -ENODEV;
-
-	return remap_ops->setup_ioapic_entry(irq, entry, destination,
-					     vector, attr);
-}
-
-static int set_remapped_irq_affinity(struct irq_data *data,
-				     const struct cpumask *mask, bool force)
-{
-	if (!config_enabled(CONFIG_SMP) || !remap_ops->set_affinity)
-		return 0;
-
-	return remap_ops->set_affinity(data, mask, force);
-}
-
-void free_remapped_irq(int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	if (irq_remapped(cfg) && remap_ops->free_irq)
-		remap_ops->free_irq(irq);
-}
-
-void compose_remapped_msi_msg(struct pci_dev *pdev,
-			      unsigned int irq, unsigned int dest,
-			      struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	if (!irq_remapped(cfg))
-		native_compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-	else if (remap_ops->compose_msi_msg)
-		remap_ops->compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-}
-
-static int msi_alloc_remapped_irq(struct pci_dev *pdev, int irq, int nvec)
-{
-	if (!remap_ops->msi_alloc_irq)
-		return -ENODEV;
-
-	return remap_ops->msi_alloc_irq(pdev, irq, nvec);
-}
-
-static int msi_setup_remapped_irq(struct pci_dev *pdev, unsigned int irq,
-				  int index, int sub_handle)
-{
-	if (!remap_ops->msi_setup_irq)
-		return -ENODEV;
-
-	return remap_ops->msi_setup_irq(pdev, irq, index, sub_handle);
-}
-
-int setup_hpet_msi_remapped(unsigned int irq, unsigned int id)
-{
-	int ret;
-
-	if (!remap_ops->alloc_hpet_msi)
-		return -ENODEV;
-
-	ret = remap_ops->alloc_hpet_msi(irq, id);
-	if (ret)
-		return -EINVAL;
-
-	return default_setup_hpet_msi(irq, id);
-}
-
 void panic_if_irq_remap(const char *msg)
 {
 	if (irq_remapping_enabled)
 		panic(msg);
 }
 
-static void ir_ack_apic_edge(struct irq_data *data)
+void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(struct irq_data *data)
+/**
+ * irq_remapping_get_ir_irq_domain - Get the irqdomain associated with the IOMMU
+ *				     device serving request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * It's used to get parent irqdomain for HPET and IOAPIC irqdomains.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
 {
-	ack_APIC_irq();
-	eoi_ioapic_irq(data->irq, irqd_cfg(data));
-}
+	if (!remap_ops || !remap_ops->get_ir_irq_domain)
+		return NULL;
 
-static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
-{
-	seq_printf(p, " IR-%s", data->chip->name);
+	return remap_ops->get_ir_irq_domain(info);
 }
 
-void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+/**
+ * irq_remapping_get_irq_domain - Get the irqdomain serving the request @info
+ * @info: interrupt allocation information, used to identify the IOMMU device
+ *
+ * There will be one PCI MSI/MSIX irqdomain associated with each interrupt
+ * remapping device, so this interface is used to retrieve the PCI MSI/MSIX
+ * irqdomain serving request @info.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
 {
-	chip->irq_print_chip = ir_print_prefix;
-	chip->irq_ack = ir_ack_apic_edge;
-	chip->irq_eoi = ir_ack_apic_level;
-	chip->irq_set_affinity = x86_io_apic_ops.set_affinity;
-}
+	if (!remap_ops || !remap_ops->get_irq_domain)
+		return NULL;
 
-bool setup_remapped_irq(int irq, struct irq_cfg *cfg, struct irq_chip *chip)
-{
-	if (!irq_remapped(cfg))
-		return false;
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	irq_remap_modify_chip_defaults(chip);
-	return true;
+	return remap_ops->get_irq_domain(info);
 }
diff --git a/drivers/iommu/irq_remapping.h b/drivers/iommu/irq_remapping.h
index 7c70cc29ffe6..039c7af7b190 100644
--- a/drivers/iommu/irq_remapping.h
+++ b/drivers/iommu/irq_remapping.h
@@ -24,19 +24,22 @@
 
 #ifdef CONFIG_IRQ_REMAP
 
-struct IO_APIC_route_entry;
-struct io_apic_irq_attr;
 struct irq_data;
-struct cpumask;
-struct pci_dev;
 struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
 
 extern int irq_remap_broken;
 extern int disable_sourceid_checking;
 extern int no_x2apic_optout;
 extern int irq_remapping_enabled;
 
+extern int disable_irq_post;
+
 struct irq_remap_ops {
+	/* The supported capabilities */
+	int capability;
+
 	/* Initializes hardware and makes it ready for remapping interrupts */
 	int  (*prepare)(void);
 
@@ -52,40 +55,23 @@ struct irq_remap_ops {
 	/* Enable fault handling */
 	int  (*enable_faulting)(void);
 
-	/* IO-APIC setup routine */
-	int (*setup_ioapic_entry)(int irq, struct IO_APIC_route_entry *,
-				  unsigned int, int,
-				  struct io_apic_irq_attr *);
-
-	/* Set the CPU affinity of a remapped interrupt */
-	int (*set_affinity)(struct irq_data *data, const struct cpumask *mask,
-			    bool force);
-
-	/* Free an IRQ */
-	int (*free_irq)(int);
+	/* Get the irqdomain associated the IOMMU device */
+	struct irq_domain *(*get_ir_irq_domain)(struct irq_alloc_info *);
 
-	/* Create MSI msg to use for interrupt remapping */
-	void (*compose_msi_msg)(struct pci_dev *,
-				unsigned int, unsigned int,
-				struct msi_msg *, u8);
-
-	/* Allocate remapping resources for MSI */
-	int (*msi_alloc_irq)(struct pci_dev *, int, int);
-
-	/* Setup the remapped MSI irq */
-	int (*msi_setup_irq)(struct pci_dev *, unsigned int, int, int);
-
-	/* Setup interrupt remapping for an HPET MSI */
-	int (*alloc_hpet_msi)(unsigned int, unsigned int);
+	/* Get the MSI irqdomain associated with the IOMMU device */
+	struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;
 extern struct irq_remap_ops amd_iommu_irq_ops;
 
+extern void ir_ack_apic_edge(struct irq_data *data);
+
 #else  /* CONFIG_IRQ_REMAP */
 
 #define irq_remapping_enabled 0
 #define irq_remap_broken      0
+#define disable_irq_post      1
 
 #endif /* CONFIG_IRQ_REMAP */
 
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 4015560bf486..ebf0adb8e7ea 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -551,6 +551,15 @@ static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain,
 	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
 }
 
+static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
+					 dma_addr_t iova, size_t size)
+{
+	rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
+	if (size > SPAGE_SIZE)
+		rk_iommu_zap_iova(rk_domain, iova + size - SPAGE_SIZE,
+					SPAGE_SIZE);
+}
+
 static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 				  dma_addr_t iova)
 {
@@ -575,12 +584,6 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
 	rk_table_flush(page_table, NUM_PT_ENTRIES);
 	rk_table_flush(dte_addr, 1);
 
-	/*
-	 * Zap the first iova of newly allocated page table so iommu evicts
-	 * old cached value of new dte from the iotlb.
-	 */
-	rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
-
 done:
 	pt_phys = rk_dte_pt_address(dte);
 	return (u32 *)phys_to_virt(pt_phys);
@@ -630,6 +633,14 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 
 	rk_table_flush(pte_addr, pte_count);
 
+	/*
+	 * Zap the first and last iova to evict from iotlb any previously
+	 * mapped cachelines holding stale values for its dte and pte.
+	 * We only zap the first and last iova, since only they could have
+	 * dte or pte shared with an existing mapping.
+	 */
+	rk_iommu_zap_iova_first_last(rk_domain, iova, size);
+
 	return 0;
 unwind:
 	/* Unmap the range of iovas that we just mapped */
@@ -774,7 +785,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain,
 	list_add_tail(&iommu->node, &rk_domain->iommus);
 	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
 
-	dev_info(dev, "Attached to iommu domain\n");
+	dev_dbg(dev, "Attached to iommu domain\n");
 
 	rk_iommu_disable_stall(iommu);
 
@@ -808,7 +819,7 @@ static void rk_iommu_detach_device(struct iommu_domain *domain,
 
 	iommu->domain = NULL;
 
-	dev_info(dev, "Detached from iommu domain\n");
+	dev_dbg(dev, "Detached from iommu domain\n");
 }
 
 static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
@@ -1004,20 +1015,18 @@ static int rk_iommu_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id rk_iommu_dt_ids[] = {
 	{ .compatible = "rockchip,iommu" },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids);
-#endif
 
 static struct platform_driver rk_iommu_driver = {
 	.probe = rk_iommu_probe,
 	.remove = rk_iommu_remove,
 	.driver = {
 		   .name = "rk_iommu",
-		   .of_match_table = of_match_ptr(rk_iommu_dt_ids),
+		   .of_match_table = rk_iommu_dt_ids,
 	},
 };
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 6de62a96e79c..8a7d7807b596 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -30,6 +30,7 @@ config ARM_GIC_V3_ITS
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_CHIP
 
 config ARM_VIC
@@ -158,3 +159,11 @@ config KEYSTONE_IRQ
 config MIPS_GIC
 	bool
 	select MIPS_CM
+
+config RENESAS_H8300H_INTC
+        bool
+	select IRQ_DOMAIN
+
+config RENESAS_H8S_INTC
+        bool
+	select IRQ_DOMAIN
+\ No newline at end of file
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index dda4927e47a6..f8efb7087760 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -47,3 +47,5 @@ obj-$(CONFIG_KEYSTONE_IRQ)		+= irq-keystone.o
 obj-$(CONFIG_MIPS_GIC)			+= irq-mips-gic.o
 obj-$(CONFIG_ARCH_MEDIATEK)		+= irq-mtk-sysirq.o
 obj-$(CONFIG_ARCH_DIGICOLOR)		+= irq-digicolor.o
+obj-$(CONFIG_RENESAS_H8300H_INTC)	+= irq-renesas-h8300h.o
+obj-$(CONFIG_RENESAS_H8S_INTC)		+= irq-renesas-h8s.o
diff --git a/drivers/irqchip/exynos-combiner.c b/drivers/irqchip/exynos-combiner.c
index 5945223b73fa..5c82e3bdafdf 100644
--- a/drivers/irqchip/exynos-combiner.c
+++ b/drivers/irqchip/exynos-combiner.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/syscore_ops.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/interrupt.h>
@@ -34,9 +35,14 @@ struct combiner_chip_data {
 	unsigned int irq_mask;
 	void __iomem *base;
 	unsigned int parent_irq;
+#ifdef CONFIG_PM
+	u32 pm_save;
+#endif
 };
 
+static struct combiner_chip_data *combiner_data;
 static struct irq_domain *combiner_irq_domain;
+static unsigned int max_nr = 20;
 
 static inline void __iomem *combiner_base(struct irq_data *data)
 {
@@ -164,18 +170,16 @@ static int combiner_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops combiner_irq_domain_ops = {
+static const struct irq_domain_ops combiner_irq_domain_ops = {
 	.xlate	= combiner_irq_domain_xlate,
 	.map	= combiner_irq_domain_map,
 };
 
 static void __init combiner_init(void __iomem *combiner_base,
-				 struct device_node *np,
-				 unsigned int max_nr)
+				 struct device_node *np)
 {
 	int i, irq;
 	unsigned int nr_irq;
-	struct combiner_chip_data *combiner_data;
 
 	nr_irq = max_nr * IRQ_IN_COMBINER;
 
@@ -201,11 +205,59 @@ static void __init combiner_init(void __iomem *combiner_base,
 	}
 }
 
+#ifdef CONFIG_PM
+
+/**
+ * combiner_suspend - save interrupt combiner state before suspend
+ *
+ * Save the interrupt enable set register for all combiner groups since
+ * the state is lost when the system enters into a sleep state.
+ *
+ */
+static int combiner_suspend(void)
+{
+	int i;
+
+	for (i = 0; i < max_nr; i++)
+		combiner_data[i].pm_save =
+			__raw_readl(combiner_data[i].base + COMBINER_ENABLE_SET);
+
+	return 0;
+}
+
+/**
+ * combiner_resume - restore interrupt combiner state after resume
+ *
+ * Restore the interrupt enable set register for all combiner groups since
+ * the state is lost when the system enters into a sleep state on suspend.
+ *
+ */
+static void combiner_resume(void)
+{
+	int i;
+
+	for (i = 0; i < max_nr; i++) {
+		__raw_writel(combiner_data[i].irq_mask,
+			     combiner_data[i].base + COMBINER_ENABLE_CLEAR);
+		__raw_writel(combiner_data[i].pm_save,
+			     combiner_data[i].base + COMBINER_ENABLE_SET);
+	}
+}
+
+#else
+#define combiner_suspend	NULL
+#define combiner_resume		NULL
+#endif
+
+static struct syscore_ops combiner_syscore_ops = {
+	.suspend	= combiner_suspend,
+	.resume		= combiner_resume,
+};
+
 static int __init combiner_of_init(struct device_node *np,
 				   struct device_node *parent)
 {
 	void __iomem *combiner_base;
-	unsigned int max_nr = 20;
 
 	combiner_base = of_iomap(np, 0);
 	if (!combiner_base) {
@@ -219,7 +271,9 @@ static int __init combiner_of_init(struct device_node *np,
 			__func__, max_nr);
 	}
 
-	combiner_init(combiner_base, np, max_nr);
+	combiner_init(combiner_base, np);
+
+	register_syscore_ops(&combiner_syscore_ops);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index daccc8bdbb42..0d3b0fe2f175 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -409,7 +409,7 @@ static struct notifier_block mpic_cascaded_cpu_notifier = {
 };
 #endif /* CONFIG_SMP */
 
-static struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
+static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index a2e8c3f876cb..459bf4429d36 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -339,6 +339,15 @@ static int __init aic5_of_init(struct device_node *node,
 	return 0;
 }
 
+#define NR_SAMA5D2_IRQS		77
+
+static int __init sama5d2_aic5_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAMA5D2_IRQS);
+}
+IRQCHIP_DECLARE(sama5d2_aic5, "atmel,sama5d2-aic", sama5d2_aic5_of_init);
+
 #define NR_SAMA5D3_IRQS		48
 
 static int __init sama5d3_aic5_of_init(struct device_node *node,
diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c
index 5916d6cdafa1..e68c3b60a681 100644
--- a/drivers/irqchip/irq-bcm2835.c
+++ b/drivers/irqchip/irq-bcm2835.c
@@ -135,7 +135,7 @@ static int armctrl_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static struct irq_domain_ops armctrl_ops = {
+static const struct irq_domain_ops armctrl_ops = {
 	.xlate = armctrl_xlate
 };
 
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
index ad96ebb0c7ab..9448e391cb71 100644
--- a/drivers/irqchip/irq-gic-common.c
+++ b/drivers/irqchip/irq-gic-common.c
@@ -24,11 +24,8 @@
 int gic_configure_irq(unsigned int irq, unsigned int type,
 		       void __iomem *base, void (*sync_access)(void))
 {
-	u32 enablemask = 1 << (irq % 32);
-	u32 enableoff = (irq / 32) * 4;
 	u32 confmask = 0x2 << ((irq % 16) * 2);
 	u32 confoff = (irq / 16) * 4;
-	bool enabled = false;
 	u32 val, oldval;
 	int ret = 0;
 
@@ -43,17 +40,6 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 		val |= confmask;
 
 	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		if (sync_access)
-			sync_access();
-		enabled = true;
-	}
-
-	/*
 	 * Write back the new configuration, and possibly re-enable
 	 * the interrupt. If we tried to write a new configuration and failed,
 	 * return an error.
@@ -62,9 +48,6 @@ int gic_configure_irq(unsigned int irq, unsigned int type,
 	if (readl_relaxed(base + GIC_DIST_CONFIG + confoff) != val && val != oldval)
 		ret = -EINVAL;
 
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
-
 	if (sync_access)
 		sync_access();
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 9687f8afebff..1b7e155869f6 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -828,7 +828,14 @@ static int its_alloc_tables(struct its_node *its)
 			u64 typer = readq_relaxed(its->base + GITS_TYPER);
 			u32 ids = GITS_TYPER_DEVBITS(typer);
 
-			order = get_order((1UL << ids) * entry_size);
+			/*
+			 * 'order' was initialized earlier to the default page
+			 * granule of the the ITS.  We can't have an allocation
+			 * smaller than that.  If the requested allocation
+			 * is smaller, round up to the default page granule.
+			 */
+			order = max(get_order((1UL << ids) * entry_size),
+				    order);
 			if (order >= MAX_ORDER) {
 				order = MAX_ORDER - 1;
 				pr_warn("%s: Device Table too large, reduce its page order to %u\n",
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 49875adb6b44..c52f7ba205b4 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -658,6 +658,7 @@ static struct irq_chip gic_chip = {
 	.irq_set_affinity	= gic_set_affinity,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 #define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 7b315e385ba3..8d7e1c8b6d56 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -82,19 +82,6 @@ static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 #define NR_GIC_CPU_IF 8
 static u8 gic_cpu_map[NR_GIC_CPU_IF] __read_mostly;
 
-/*
- * Supported arch specific GIC irq extension.
- * Default make them NULL.
- */
-struct irq_chip gic_arch_extn = {
-	.irq_eoi	= NULL,
-	.irq_mask	= NULL,
-	.irq_unmask	= NULL,
-	.irq_retrigger	= NULL,
-	.irq_set_type	= NULL,
-	.irq_set_wake	= NULL,
-};
-
 #ifndef MAX_GIC_NR
 #define MAX_GIC_NR	1
 #endif
@@ -167,34 +154,16 @@ static int gic_peek_irq(struct irq_data *d, u32 offset)
 
 static void gic_mask_irq(struct irq_data *d)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
 	gic_poke_irq(d, GIC_DIST_ENABLE_CLEAR);
-	if (gic_arch_extn.irq_mask)
-		gic_arch_extn.irq_mask(d);
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 
 static void gic_unmask_irq(struct irq_data *d)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
-	if (gic_arch_extn.irq_unmask)
-		gic_arch_extn.irq_unmask(d);
 	gic_poke_irq(d, GIC_DIST_ENABLE_SET);
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
 }
 
 static void gic_eoi_irq(struct irq_data *d)
 {
-	if (gic_arch_extn.irq_eoi) {
-		raw_spin_lock(&irq_controller_lock);
-		gic_arch_extn.irq_eoi(d);
-		raw_spin_unlock(&irq_controller_lock);
-	}
-
 	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_EOI);
 }
 
@@ -251,8 +220,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
-	unsigned long flags;
-	int ret;
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
@@ -263,25 +230,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 			    type != IRQ_TYPE_EDGE_RISING)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
-
-	if (gic_arch_extn.irq_set_type)
-		gic_arch_extn.irq_set_type(d, type);
-
-	ret = gic_configure_irq(gicirq, type, base, NULL);
-
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
-
-	return ret;
-}
-
-static int gic_retrigger(struct irq_data *d)
-{
-	if (gic_arch_extn.irq_retrigger)
-		return gic_arch_extn.irq_retrigger(d);
-
-	/* the genirq layer expects 0 if we can't retrigger in hardware */
-	return 0;
+	return gic_configure_irq(gicirq, type, base, NULL);
 }
 
 #ifdef CONFIG_SMP
@@ -312,21 +261,6 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 }
 #endif
 
-#ifdef CONFIG_PM
-static int gic_set_wake(struct irq_data *d, unsigned int on)
-{
-	int ret = -ENXIO;
-
-	if (gic_arch_extn.irq_set_wake)
-		ret = gic_arch_extn.irq_set_wake(d, on);
-
-	return ret;
-}
-
-#else
-#define gic_set_wake	NULL
-#endif
-
 static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqstat, irqnr;
@@ -385,13 +319,12 @@ static struct irq_chip gic_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_eoi		= gic_eoi_irq,
 	.irq_set_type		= gic_set_type,
-	.irq_retrigger		= gic_retrigger,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= gic_set_affinity,
 #endif
-	.irq_set_wake		= gic_set_wake,
 	.irq_get_irqchip_state	= gic_irq_get_irqchip_state,
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
@@ -1055,7 +988,6 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 		set_handle_irq(gic_handle_irq);
 	}
 
-	gic_chip.flags |= gic_arch_extn.flags;
 	gic_dist_init(gic);
 	gic_cpu_init(gic);
 	gic_pm_init(gic);
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index 7d6ffb5de84f..0cae45d10695 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -202,6 +202,7 @@ static struct irq_chip hip04_irq_chip = {
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= hip04_irq_set_affinity,
 #endif
+	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
 static u16 hip04_get_cpumask(struct hip04_irq_data *intc)
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index 78e8b3ce5252..81e3cf5b9a1f 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -131,7 +131,7 @@ static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops keystone_irq_ops = {
+static const struct irq_domain_ops keystone_irq_ops = {
 	.map	= keystone_irq_map,
 	.xlate	= irq_domain_xlate_onecell,
 };
@@ -184,8 +184,7 @@ static int keystone_irq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, kirq);
 
-	irq_set_chained_handler(kirq->irq, keystone_irq_handler);
-	irq_set_handler_data(kirq->irq, kirq);
+	irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
 
 	/* clear all source bits */
 	keystone_irq_writel(kirq, ~0x0);
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 57f09cb54464..4400edd1a6c7 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -271,7 +271,7 @@ int gic_get_c0_fdc_int(void)
 				  GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_FDC));
 }
 
-static void gic_handle_shared_int(void)
+static void gic_handle_shared_int(bool chained)
 {
 	unsigned int i, intr, virq;
 	unsigned long *pcpu_mask;
@@ -299,7 +299,10 @@ static void gic_handle_shared_int(void)
 	while (intr != gic_shared_intrs) {
 		virq = irq_linear_revmap(gic_irq_domain,
 					 GIC_SHARED_TO_HWIRQ(intr));
-		do_IRQ(virq);
+		if (chained)
+			generic_handle_irq(virq);
+		else
+			do_IRQ(virq);
 
 		/* go to next pending bit */
 		bitmap_clear(pending, intr, 1);
@@ -431,7 +434,7 @@ static struct irq_chip gic_edge_irq_controller = {
 #endif
 };
 
-static void gic_handle_local_int(void)
+static void gic_handle_local_int(bool chained)
 {
 	unsigned long pending, masked;
 	unsigned int intr, virq;
@@ -445,7 +448,10 @@ static void gic_handle_local_int(void)
 	while (intr != GIC_NUM_LOCAL_INTRS) {
 		virq = irq_linear_revmap(gic_irq_domain,
 					 GIC_LOCAL_TO_HWIRQ(intr));
-		do_IRQ(virq);
+		if (chained)
+			generic_handle_irq(virq);
+		else
+			do_IRQ(virq);
 
 		/* go to next pending bit */
 		bitmap_clear(&pending, intr, 1);
@@ -509,13 +515,14 @@ static struct irq_chip gic_all_vpes_local_irq_controller = {
 
 static void __gic_irq_dispatch(void)
 {
-	gic_handle_local_int();
-	gic_handle_shared_int();
+	gic_handle_local_int(false);
+	gic_handle_shared_int(false);
 }
 
 static void gic_irq_dispatch(unsigned int irq, struct irq_desc *desc)
 {
-	__gic_irq_dispatch();
+	gic_handle_local_int(true);
+	gic_handle_shared_int(true);
 }
 
 #ifdef CONFIG_MIPS_GIC_IPI
@@ -739,7 +746,7 @@ static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
 	return 0;
 }
 
-static struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
 	.xlate = gic_irq_domain_xlate,
 };
diff --git a/drivers/irqchip/irq-mtk-sysirq.c b/drivers/irqchip/irq-mtk-sysirq.c
index eaf0a710e98a..15c13039bba2 100644
--- a/drivers/irqchip/irq-mtk-sysirq.c
+++ b/drivers/irqchip/irq-mtk-sysirq.c
@@ -111,7 +111,7 @@ static int mtk_sysirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &gic_data);
 }
 
-static struct irq_domain_ops sysirq_domain_ops = {
+static const struct irq_domain_ops sysirq_domain_ops = {
 	.xlate = mtk_sysirq_domain_xlate,
 	.alloc = mtk_sysirq_domain_alloc,
 	.free = irq_domain_free_irqs_common,
@@ -144,7 +144,7 @@ static int __init mtk_sysirq_of_init(struct device_node *node,
 	chip_data->intpol_base = ioremap(res.start, size);
 	if (!chip_data->intpol_base) {
 		pr_err("mtk_sysirq: unable to map sysirq register\n");
-		ret = PTR_ERR(chip_data->intpol_base);
+		ret = -ENXIO;
 		goto out_free;
 	}
 
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index e4acf1e3f8e3..04bf97b289cf 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -90,7 +90,7 @@ static int icoll_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops icoll_irq_domain_ops = {
+static const struct irq_domain_ops icoll_irq_domain_ops = {
 	.map = icoll_irq_domain_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c
index 4ff0805fca01..5fac9100f6cb 100644
--- a/drivers/irqchip/irq-nvic.c
+++ b/drivers/irqchip/irq-nvic.c
@@ -49,6 +49,31 @@ nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs)
 	handle_IRQ(irq, regs);
 }
 
+static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	int i, ret;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	struct of_phandle_args *irq_data = arg;
+
+	ret = irq_domain_xlate_onecell(domain, irq_data->np, irq_data->args,
+				   irq_data->args_count, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_map_generic_chip(domain, virq + i, hwirq + i);
+
+	return 0;
+}
+
+static const struct irq_domain_ops nvic_irq_domain_ops = {
+	.xlate = irq_domain_xlate_onecell,
+	.alloc = nvic_irq_domain_alloc,
+	.free = irq_domain_free_irqs_top,
+};
+
 static int __init nvic_of_init(struct device_node *node,
 			       struct device_node *parent)
 {
@@ -70,7 +95,8 @@ static int __init nvic_of_init(struct device_node *node,
 		irqs = NVIC_MAX_IRQ;
 
 	nvic_irq_domain =
-		irq_domain_add_linear(node, irqs, &irq_generic_chip_ops, NULL);
+		irq_domain_add_linear(node, irqs, &nvic_irq_domain_ops, NULL);
+
 	if (!nvic_irq_domain) {
 		pr_warn("Failed to allocate irq domain\n");
 		return -ENOMEM;
diff --git a/drivers/irqchip/irq-renesas-h8300h.c b/drivers/irqchip/irq-renesas-h8300h.c
new file mode 100644
index 000000000000..1870e6bd3dd9
--- /dev/null
+++ b/drivers/irqchip/irq-renesas-h8300h.c
@@ -0,0 +1,95 @@
+/*
+ * H8/300H interrupt controller driver
+ *
+ * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <asm/io.h>
+
+#include "irqchip.h"
+
+static const char ipr_bit[] = {
+	 7,  6,  5,  5,
+	 4,  4,  4,  4,  3,  3,  3,  3,
+	 2,  2,  2,  2,  1,  1,  1,  1,
+	 0,  0,  0,  0, 15, 15, 15, 15,
+	14, 14, 14, 14, 13, 13, 13, 13,
+	-1, -1, -1, -1, 11, 11, 11, 11,
+	10, 10, 10, 10,  9,  9,  9,  9,
+};
+
+static void *intc_baseaddr;
+
+#define IPR ((unsigned long)intc_baseaddr + 6)
+
+static void h8300h_disable_irq(struct irq_data *data)
+{
+	int bit;
+	int irq = data->irq - 12;
+
+	bit = ipr_bit[irq];
+	if (bit >= 0) {
+		if (bit < 8)
+			ctrl_bclr(bit & 7, IPR);
+		else
+			ctrl_bclr(bit & 7, (IPR+1));
+	}
+}
+
+static void h8300h_enable_irq(struct irq_data *data)
+{
+	int bit;
+	int irq = data->irq - 12;
+
+	bit = ipr_bit[irq];
+	if (bit >= 0) {
+		if (bit < 8)
+			ctrl_bset(bit & 7, IPR);
+		else
+			ctrl_bset(bit & 7, (IPR+1));
+	}
+}
+
+struct irq_chip h8300h_irq_chip = {
+	.name		= "H8/300H-INTC",
+	.irq_enable	= h8300h_enable_irq,
+	.irq_disable	= h8300h_disable_irq,
+};
+
+static int irq_map(struct irq_domain *h, unsigned int virq,
+		   irq_hw_number_t hw_irq_num)
+{
+       irq_set_chip_and_handler(virq, &h8300h_irq_chip, handle_simple_irq);
+
+       return 0;
+}
+
+static struct irq_domain_ops irq_ops = {
+       .map    = irq_map,
+       .xlate  = irq_domain_xlate_onecell,
+};
+
+static int __init h8300h_intc_of_init(struct device_node *intc,
+				      struct device_node *parent)
+{
+	struct irq_domain *domain;
+
+	intc_baseaddr = of_iomap(intc, 0);
+	BUG_ON(!intc_baseaddr);
+
+	/* All interrupt priority low */
+	ctrl_outb(0x00, IPR + 0);
+	ctrl_outb(0x00, IPR + 1);
+
+	domain = irq_domain_add_linear(intc, NR_IRQS, &irq_ops, NULL);
+	BUG_ON(!domain);
+	irq_set_default_host(domain);
+	return 0;
+}
+
+IRQCHIP_DECLARE(h8300h_intc, "renesas,h8300h-intc", h8300h_intc_of_init);
diff --git a/drivers/irqchip/irq-renesas-h8s.c b/drivers/irqchip/irq-renesas-h8s.c
new file mode 100644
index 000000000000..64425f4de7d9
--- /dev/null
+++ b/drivers/irqchip/irq-renesas-h8s.c
@@ -0,0 +1,101 @@
+/*
+ * H8S interrupt contoller driver
+ *
+ * Copyright 2015 Yoshinori Sato <ysato@users.sourceforge.jp>
+ */
+
+#include <linux/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <asm/io.h>
+#include "irqchip.h"
+
+static void *intc_baseaddr;
+#define IPRA ((unsigned long)intc_baseaddr)
+
+static const unsigned char ipr_table[] = {
+	0x03, 0x02, 0x01, 0x00, 0x13, 0x12, 0x11, 0x10, /* 16 - 23 */
+	0x23, 0x22, 0x21, 0x20, 0x33, 0x32, 0x31, 0x30, /* 24 - 31 */
+	0x43, 0x42, 0x41, 0x40, 0x53, 0x53, 0x52, 0x52, /* 32 - 39 */
+	0x51, 0x51, 0x51, 0x51, 0x51, 0x51, 0x51, 0x51, /* 40 - 47 */
+	0x50, 0x50, 0x50, 0x50, 0x63, 0x63, 0x63, 0x63, /* 48 - 55 */
+	0x62, 0x62, 0x62, 0x62, 0x62, 0x62, 0x62, 0x62, /* 56 - 63 */
+	0x61, 0x61, 0x61, 0x61, 0x60, 0x60, 0x60, 0x60, /* 64 - 71 */
+	0x73, 0x73, 0x73, 0x73, 0x72, 0x72, 0x72, 0x72, /* 72 - 79 */
+	0x71, 0x71, 0x71, 0x71, 0x70, 0x83, 0x82, 0x81, /* 80 - 87 */
+	0x80, 0x80, 0x80, 0x80, 0x93, 0x93, 0x93, 0x93, /* 88 - 95 */
+	0x92, 0x92, 0x92, 0x92, 0x91, 0x91, 0x91, 0x91, /* 96 - 103 */
+	0x90, 0x90, 0x90, 0x90, 0xa3, 0xa3, 0xa3, 0xa3, /* 104 - 111 */
+	0xa2, 0xa2, 0xa2, 0xa2, 0xa1, 0xa1, 0xa1, 0xa1, /* 112 - 119 */
+	0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, /* 120 - 127 */
+};
+
+static void h8s_disable_irq(struct irq_data *data)
+{
+	int pos;
+	unsigned int addr;
+	unsigned short pri;
+	int irq = data->irq;
+
+	addr = IPRA + ((ipr_table[irq - 16] & 0xf0) >> 3);
+	pos = (ipr_table[irq - 16] & 0x0f) * 4;
+	pri = ~(0x000f << pos);
+	pri &= ctrl_inw(addr);
+	ctrl_outw(pri, addr);
+}
+
+static void h8s_enable_irq(struct irq_data *data)
+{
+	int pos;
+	unsigned int addr;
+	unsigned short pri;
+	int irq = data->irq;
+
+	addr = IPRA + ((ipr_table[irq - 16] & 0xf0) >> 3);
+	pos = (ipr_table[irq - 16] & 0x0f) * 4;
+	pri = ~(0x000f << pos);
+	pri &= ctrl_inw(addr);
+	pri |= 1 << pos;
+	ctrl_outw(pri, addr);
+}
+
+struct irq_chip h8s_irq_chip = {
+	.name		= "H8S-INTC",
+	.irq_enable	= h8s_enable_irq,
+	.irq_disable	= h8s_disable_irq,
+};
+
+static __init int irq_map(struct irq_domain *h, unsigned int virq,
+			  irq_hw_number_t hw_irq_num)
+{
+       irq_set_chip_and_handler(virq, &h8s_irq_chip, handle_simple_irq);
+
+       return 0;
+}
+
+static struct irq_domain_ops irq_ops = {
+       .map    = irq_map,
+       .xlate  = irq_domain_xlate_onecell,
+};
+
+static int __init h8s_intc_of_init(struct device_node *intc,
+				   struct device_node *parent)
+{
+	struct irq_domain *domain;
+	int n;
+
+	intc_baseaddr = of_iomap(intc, 0);
+	BUG_ON(!intc_baseaddr);
+
+	/* All interrupt priority is 0 (disable) */
+	/* IPRA to IPRK */
+	for (n = 0; n <= 'k' - 'a'; n++)
+		ctrl_outw(0x0000, IPRA + (n * 2));
+
+	domain = irq_domain_add_linear(intc, NR_IRQS, &irq_ops, NULL);
+	BUG_ON(!domain);
+	irq_set_default_host(domain);
+	return 0;
+}
+
+IRQCHIP_DECLARE(h8s_intc, "renesas,h8s-intc", h8s_intc_of_init);
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 9a0767b9c89d..0670ab4e3897 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -347,7 +347,7 @@ static int intc_irqpin_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops intc_irqpin_irq_domain_ops = {
+static const struct irq_domain_ops intc_irqpin_irq_domain_ops = {
 	.map	= intc_irqpin_irq_domain_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index cdf80b7794cd..778bd076aeea 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -29,7 +29,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/platform_data/irq-renesas-irqc.h>
 #include <linux/pm_runtime.h>
 
 #define IRQC_IRQ_MAX	32	/* maximum 32 interrupts per driver instance */
@@ -62,7 +61,6 @@ struct irqc_priv {
 	void __iomem *iomem;
 	void __iomem *cpu_int_base;
 	struct irqc_irq irq[IRQC_IRQ_MAX];
-	struct renesas_irqc_config config;
 	unsigned int number_of_irqs;
 	struct platform_device *pdev;
 	struct irq_chip irq_chip;
@@ -168,14 +166,13 @@ static int irqc_irq_domain_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops irqc_irq_domain_ops = {
+static const struct irq_domain_ops irqc_irq_domain_ops = {
 	.map	= irqc_irq_domain_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
 
 static int irqc_probe(struct platform_device *pdev)
 {
-	struct renesas_irqc_config *pdata = pdev->dev.platform_data;
 	struct irqc_priv *p;
 	struct resource *io;
 	struct resource *irq;
@@ -191,10 +188,6 @@ static int irqc_probe(struct platform_device *pdev)
 		goto err0;
 	}
 
-	/* deal with driver instance configuration */
-	if (pdata)
-		memcpy(&p->config, pdata, sizeof(*pdata));
-
 	p->pdev = pdev;
 	platform_set_drvdata(pdev, p);
 
@@ -251,8 +244,7 @@ static int irqc_probe(struct platform_device *pdev)
 	irq_chip->flags	= IRQCHIP_MASK_ON_SUSPEND;
 
 	p->irq_domain = irq_domain_add_simple(pdev->dev.of_node,
-					      p->number_of_irqs,
-					      p->config.irq_base,
+					      p->number_of_irqs, 0,
 					      &irqc_irq_domain_ops, p);
 	if (!p->irq_domain) {
 		ret = -ENXIO;
@@ -272,13 +264,6 @@ static int irqc_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "driving %d irqs\n", p->number_of_irqs);
 
-	/* warn in case of mismatch if irq base is specified */
-	if (p->config.irq_base) {
-		if (p->config.irq_base != p->irq[0].domain_irq)
-			dev_warn(&pdev->dev, "irq base mismatch (%d/%d)\n",
-				 p->config.irq_base, p->irq[0].domain_irq);
-	}
-
 	return 0;
 err3:
 	while (--k >= 0)
diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c
index c8d373fcd823..e96717f45ea1 100644
--- a/drivers/irqchip/irq-s3c24xx.c
+++ b/drivers/irqchip/irq-s3c24xx.c
@@ -502,7 +502,7 @@ err:
 	return -EINVAL;
 }
 
-static struct irq_domain_ops s3c24xx_irq_ops = {
+static const struct irq_domain_ops s3c24xx_irq_ops = {
 	.map = s3c24xx_irq_map,
 	.xlate = irq_domain_xlate_twocell,
 };
@@ -1228,7 +1228,7 @@ static int s3c24xx_irq_xlate_of(struct irq_domain *d, struct device_node *n,
 	return 0;
 }
 
-static struct irq_domain_ops s3c24xx_irq_ops_of = {
+static const struct irq_domain_ops s3c24xx_irq_ops_of = {
 	.map = s3c24xx_irq_map_of,
 	.xlate = s3c24xx_irq_xlate_of,
 };
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 64155b686081..83d6aa6464ee 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -89,7 +89,7 @@ static int sun4i_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops sun4i_irq_ops = {
+static const struct irq_domain_ops sun4i_irq_ops = {
 	.map = sun4i_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 4a9ce5b50c5b..6b2b582433bd 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -104,7 +104,7 @@ static int sunxi_sc_nmi_set_type(struct irq_data *data, unsigned int flow_type)
 	irqd_set_trigger_type(data, flow_type);
 	irq_setup_alt_chip(data, flow_type);
 
-	for (i = 0; i <= gc->num_ct; i++, ct++)
+	for (i = 0; i < gc->num_ct; i++, ct++)
 		if (ct->type & flow_type)
 			ctrl_off = ct->regs.type;
 
diff --git a/drivers/irqchip/irq-tegra.c b/drivers/irqchip/irq-tegra.c
index 51c485d9a877..f67bbd80433e 100644
--- a/drivers/irqchip/irq-tegra.c
+++ b/drivers/irqchip/irq-tegra.c
@@ -264,7 +264,7 @@ static int tegra_ictlr_domain_alloc(struct irq_domain *domain,
 
 		irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i,
 					      &tegra_ictlr_chip,
-					      &info->base[ictlr]);
+					      info->base[ictlr]);
 	}
 
 	parent_args = *args;
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index 1ab451729a5c..888111b76ea0 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -132,7 +132,7 @@ static int fpga_irqdomain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops fpga_irqdomain_ops = {
+static const struct irq_domain_ops fpga_irqdomain_ops = {
 	.map = fpga_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/irqchip/irq-vf610-mscm-ir.c b/drivers/irqchip/irq-vf610-mscm-ir.c
index 9521057d4744..f5c01cbcc73a 100644
--- a/drivers/irqchip/irq-vf610-mscm-ir.c
+++ b/drivers/irqchip/irq-vf610-mscm-ir.c
@@ -47,6 +47,7 @@ struct vf610_mscm_ir_chip_data {
 	void __iomem *mscm_ir_base;
 	u16 cpu_mask;
 	u16 saved_irsprc[MSCM_IRSPRC_NUM];
+	bool is_nvic;
 };
 
 static struct vf610_mscm_ir_chip_data *mscm_ir_data;
@@ -101,7 +102,7 @@ static void vf610_mscm_ir_enable(struct irq_data *data)
 	writew_relaxed(chip_data->cpu_mask,
 		       chip_data->mscm_ir_base + MSCM_IRSPRC(hwirq));
 
-	irq_chip_unmask_parent(data);
+	irq_chip_enable_parent(data);
 }
 
 static void vf610_mscm_ir_disable(struct irq_data *data)
@@ -111,7 +112,7 @@ static void vf610_mscm_ir_disable(struct irq_data *data)
 
 	writew_relaxed(0x0, chip_data->mscm_ir_base + MSCM_IRSPRC(hwirq));
 
-	irq_chip_mask_parent(data);
+	irq_chip_disable_parent(data);
 }
 
 static struct irq_chip vf610_mscm_ir_irq_chip = {
@@ -143,10 +144,17 @@ static int vf610_mscm_ir_domain_alloc(struct irq_domain *domain, unsigned int vi
 					      domain->host_data);
 
 	gic_data.np = domain->parent->of_node;
-	gic_data.args_count = 3;
-	gic_data.args[0] = GIC_SPI;
-	gic_data.args[1] = irq_data->args[0];
-	gic_data.args[2] = irq_data->args[1];
+
+	if (mscm_ir_data->is_nvic) {
+		gic_data.args_count = 1;
+		gic_data.args[0] = irq_data->args[0];
+	} else {
+		gic_data.args_count = 3;
+		gic_data.args[0] = GIC_SPI;
+		gic_data.args[1] = irq_data->args[0];
+		gic_data.args[2] = irq_data->args[1];
+	}
+
 	return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &gic_data);
 }
 
@@ -174,10 +182,9 @@ static int __init vf610_mscm_ir_of_init(struct device_node *node,
 		return -ENOMEM;
 
 	mscm_ir_data->mscm_ir_base = of_io_request_and_map(node, 0, "mscm-ir");
-
-	if (!mscm_ir_data->mscm_ir_base) {
+	if (IS_ERR(mscm_ir_data->mscm_ir_base)) {
 		pr_err("vf610_mscm_ir: unable to map mscm register\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(mscm_ir_data->mscm_ir_base);
 		goto out_free;
 	}
 
@@ -199,6 +206,9 @@ static int __init vf610_mscm_ir_of_init(struct device_node *node,
 		goto out_unmap;
 	}
 
+	if (of_device_is_compatible(domain->parent->of_node, "arm,armv7m-nvic"))
+		mscm_ir_data->is_nvic = true;
+
 	cpu_pm_register_notifier(&mscm_ir_notifier_block);
 
 	return 0;
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 54089debf2dc..d4ce331ea4a0 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -256,7 +256,7 @@ static void __exception_irq_entry vic_handle_irq(struct pt_regs *regs)
 	} while (handled);
 }
 
-static struct irq_domain_ops vic_irqdomain_ops = {
+static const struct irq_domain_ops vic_irqdomain_ops = {
 	.map = vic_irqdomain_map,
 	.xlate = irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/irqchip/irq-vt8500.c b/drivers/irqchip/irq-vt8500.c
index b7af816f2769..0b297009b856 100644
--- a/drivers/irqchip/irq-vt8500.c
+++ b/drivers/irqchip/irq-vt8500.c
@@ -173,7 +173,7 @@ static int vt8500_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops vt8500_irq_domain_ops = {
+static const struct irq_domain_ops vt8500_irq_domain_ops = {
 	.map = vt8500_irq_map,
 	.xlate = irq_domain_xlate_onecell,
 };
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 9c145a7cb056..a45121546caf 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -207,8 +207,7 @@ static void __init spear_shirq_register(struct spear_shirq *shirq,
 	if (!shirq->irq_chip)
 		return;
 
-	irq_set_chained_handler(parent_irq, shirq_handler);
-	irq_set_handler_data(parent_irq, shirq);
+	irq_set_chained_handler_and_data(parent_irq, shirq_handler, shirq);
 
 	for (i = 0; i < shirq->nr_irqs; i++) {
 		irq_set_chip_and_handler(shirq->virq_base + i,
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index 1cc6ca8bfbda..85cfa4f8691f 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -2264,7 +2264,7 @@ static int capidrv_addcontr(u16 contr, struct capi_profile *profp)
 		return -1;
 	}
 	card->owner = THIS_MODULE;
-	init_timer(&card->listentimer);
+	setup_timer(&card->listentimer, listentimerfunc, (unsigned long)card);
 	strcpy(card->name, id);
 	card->contrnr = contr;
 	card->nbchan = profp->nbchannel;
@@ -2331,8 +2331,6 @@ static int capidrv_addcontr(u16 contr, struct capi_profile *profp)
 	card->cipmask = 0x1FFF03FF;	/* any */
 	card->cipmask2 = 0;
 
-	card->listentimer.data = (unsigned long)card;
-	card->listentimer.function = listentimerfunc;
 	send_listen(card);
 	mod_timer(&card->listentimer, jiffies + 60 * HZ);
 
diff --git a/drivers/isdn/hisax/Kconfig b/drivers/isdn/hisax/Kconfig
index 97465ac5a2d5..eb83d94ab4fe 100644
--- a/drivers/isdn/hisax/Kconfig
+++ b/drivers/isdn/hisax/Kconfig
@@ -237,7 +237,7 @@ config HISAX_MIC
 
 config HISAX_NETJET
 	bool "NETjet card"
-	depends on PCI && (BROKEN || !(PPC || PARISC || M68K || (MIPS && !CPU_LITTLE_ENDIAN) || FRV || (XTENSA && !CPU_LITTLE_ENDIAN)))
+	depends on PCI && (BROKEN || !(PPC || PARISC || M68K || (MIPS && !CPU_LITTLE_ENDIAN) || FRV || (XTENSA && !CPU_LITTLE_ENDIAN) || MICROBLAZE))
 	depends on VIRT_TO_BUS
 	help
 	  This enables HiSax support for the NetJet from Traverse
@@ -249,7 +249,7 @@ config HISAX_NETJET
 
 config HISAX_NETJET_U
 	bool "NETspider U card"
-	depends on PCI && (BROKEN || !(PPC || PARISC || M68K || (MIPS && !CPU_LITTLE_ENDIAN) || FRV || (XTENSA && !CPU_LITTLE_ENDIAN)))
+	depends on PCI && (BROKEN || !(PPC || PARISC || M68K || (MIPS && !CPU_LITTLE_ENDIAN) || FRV || (XTENSA && !CPU_LITTLE_ENDIAN) || MICROBLAZE))
 	depends on VIRT_TO_BUS
 	help
 	  This enables HiSax support for the Netspider U interface ISDN card
diff --git a/drivers/isdn/hisax/st5481_usb.c b/drivers/isdn/hisax/st5481_usb.c
index ead0a4fb7448..a0fdbc074b98 100644
--- a/drivers/isdn/hisax/st5481_usb.c
+++ b/drivers/isdn/hisax/st5481_usb.c
@@ -267,8 +267,8 @@ int st5481_setup_usb(struct st5481_adapter *adapter)
 	}
 
 	// The descriptor is wrong for some early samples of the ST5481 chip
-	altsetting->endpoint[3].desc.wMaxPacketSize = __constant_cpu_to_le16(32);
-	altsetting->endpoint[4].desc.wMaxPacketSize = __constant_cpu_to_le16(32);
+	altsetting->endpoint[3].desc.wMaxPacketSize = cpu_to_le16(32);
+	altsetting->endpoint[4].desc.wMaxPacketSize = cpu_to_le16(32);
 
 	// Use alternative setting 3 on interface 0 to have 2B+D
 	if ((status = usb_set_interface(dev, 0, 3)) < 0) {
diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c
index 546b7e81161d..aa5dd5668528 100644
--- a/drivers/isdn/i4l/isdn_net.c
+++ b/drivers/isdn/i4l/isdn_net.c
@@ -58,7 +58,7 @@
  * About SOFTNET:
  * Most of the changes were pretty obvious and basically done by HE already.
  *
- * One problem of the isdn net device code is that is uses struct net_device
+ * One problem of the isdn net device code is that it uses struct net_device
  * for masters and slaves. However, only master interface are registered to
  * the network layer, and therefore, it only makes sense to call netif_*
  * functions on them.
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 8dc7290089bb..0d29b5a6356d 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -601,14 +601,14 @@ static const struct proto_ops data_sock_ops = {
 };
 
 static int
-data_sock_create(struct net *net, struct socket *sock, int protocol)
+data_sock_create(struct net *net, struct socket *sock, int protocol, int kern)
 {
 	struct sock *sk;
 
 	if (sock->type != SOCK_DGRAM)
 		return -ESOCKTNOSUPPORT;
 
-	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto);
+	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern);
 	if (!sk)
 		return -ENOMEM;
 
@@ -756,14 +756,14 @@ static const struct proto_ops base_sock_ops = {
 
 
 static int
-base_sock_create(struct net *net, struct socket *sock, int protocol)
+base_sock_create(struct net *net, struct socket *sock, int protocol, int kern)
 {
 	struct sock *sk;
 
 	if (sock->type != SOCK_RAW)
 		return -ESOCKTNOSUPPORT;
 
-	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto);
+	sk = sk_alloc(net, PF_ISDN, GFP_KERNEL, &mISDN_proto, kern);
 	if (!sk)
 		return -ENOMEM;
 
@@ -785,7 +785,7 @@ mISDN_sock_create(struct net *net, struct socket *sock, int proto, int kern)
 
 	switch (proto) {
 	case ISDN_P_BASE:
-		err = base_sock_create(net, sock, proto);
+		err = base_sock_create(net, sock, proto, kern);
 		break;
 	case ISDN_P_TE_S0:
 	case ISDN_P_NT_S0:
@@ -799,7 +799,7 @@ mISDN_sock_create(struct net *net, struct socket *sock, int proto, int kern)
 	case ISDN_P_B_L2DTMF:
 	case ISDN_P_B_L2DSP:
 	case ISDN_P_B_L2DSPHDLC:
-		err = data_sock_create(net, sock, proto);
+		err = data_sock_create(net, sock, proto, kern);
 		break;
 	default:
 		return err;
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 966b9605f5f0..4191614c4651 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -11,9 +11,6 @@ menuconfig NEW_LEDS
 	  Say Y to enable Linux LED support.  This allows control of supported
 	  LEDs from both userspace and optionally, by kernel events (triggers).
 
-	  This is not related to standard keyboard LEDs which are controlled
-	  via the input system.
-
 if NEW_LEDS
 
 config LEDS_CLASS
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 728681debdbe..7fb2a19ac649 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -187,6 +187,7 @@ void led_classdev_resume(struct led_classdev *led_cdev)
 }
 EXPORT_SYMBOL_GPL(led_classdev_resume);
 
+#ifdef CONFIG_PM_SLEEP
 static int led_suspend(struct device *dev)
 {
 	struct led_classdev *led_cdev = dev_get_drvdata(dev);
@@ -206,11 +207,9 @@ static int led_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
-static const struct dev_pm_ops leds_class_dev_pm_ops = {
-	.suspend        = led_suspend,
-	.resume         = led_resume,
-};
+static SIMPLE_DEV_PM_OPS(leds_class_dev_pm_ops, led_suspend, led_resume);
 
 static int match_name(struct device *dev, const void *data)
 {
diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c
index 7dc93aa004c8..312ffd3d0017 100644
--- a/drivers/lguest/core.c
+++ b/drivers/lguest/core.c
@@ -173,7 +173,7 @@ static void unmap_switcher(void)
 bool lguest_address_ok(const struct lguest *lg,
 		       unsigned long addr, unsigned long len)
 {
-	return (addr+len) / PAGE_SIZE < lg->pfn_limit && (addr+len >= addr);
+	return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr);
 }
 
 /*
diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c
index 5e7559be222a..eb934b0242e0 100644
--- a/drivers/lguest/interrupts_and_traps.c
+++ b/drivers/lguest/interrupts_and_traps.c
@@ -20,7 +20,7 @@
 #include "lg.h"
 
 /* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */
-static unsigned int syscall_vector = SYSCALL_VECTOR;
+static unsigned int syscall_vector = IA32_SYSCALL_VECTOR;
 module_param(syscall_vector, uint, 0444);
 
 /* The address of the interrupt handler is split into two bits: */
@@ -333,8 +333,8 @@ void set_interrupt(struct lg_cpu *cpu, unsigned int irq)
  */
 static bool could_be_syscall(unsigned int num)
 {
-	/* Normal Linux SYSCALL_VECTOR or reserved vector? */
-	return num == SYSCALL_VECTOR || num == syscall_vector;
+	/* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */
+	return num == IA32_SYSCALL_VECTOR || num == syscall_vector;
 }
 
 /* The syscall vector it wants must be unused by Host. */
@@ -351,7 +351,7 @@ bool check_syscall_vector(struct lguest *lg)
 int init_interrupts(void)
 {
 	/* If they want some strange system call vector, reserve it now */
-	if (syscall_vector != SYSCALL_VECTOR) {
+	if (syscall_vector != IA32_SYSCALL_VECTOR) {
 		if (test_bit(syscall_vector, used_vectors) ||
 		    vector_used_by_percpu_irq(syscall_vector)) {
 			printk(KERN_ERR "lg: couldn't reserve syscall %u\n",
@@ -366,7 +366,7 @@ int init_interrupts(void)
 
 void free_interrupts(void)
 {
-	if (syscall_vector != SYSCALL_VECTOR)
+	if (syscall_vector != IA32_SYSCALL_VECTOR)
 		clear_bit(syscall_vector, used_vectors);
 }
 
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 30f2aef69d78..6a4cd771a2be 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -46,7 +46,7 @@
 #include <asm/setup.h>
 #include <asm/lguest.h>
 #include <asm/uaccess.h>
-#include <asm/i387.h>
+#include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 #include "../lg.h"
 
@@ -251,7 +251,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 * we set it now, so we can trap and pass that trap to the Guest if it
 	 * uses the FPU.
 	 */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		stts();
 
 	/*
@@ -283,7 +283,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 
 	/* Clear the host TS bit if it was set above. */
-	if (cpu->ts && user_has_fpu())
+	if (cpu->ts && fpregs_active())
 		clts();
 
 	/*
@@ -297,12 +297,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	/*
 	 * Similarly, if we took a trap because the Guest used the FPU,
 	 * we have to restore the FPU it expects to see.
-	 * math_state_restore() may sleep and we may even move off to
+	 * fpu__restore() may sleep and we may even move off to
 	 * a different CPU. So all the critical stuff should be done
 	 * before this.
 	 */
-	else if (cpu->regs->trapnum == 7 && !user_has_fpu())
-		math_state_restore();
+	else if (cpu->regs->trapnum == 7 && !fpregs_active())
+		fpu__restore(&current->thread.fpu);
 }
 
 /*H:130
diff --git a/drivers/macintosh/nvram.c b/drivers/macintosh/nvram.c
deleted file mode 100644
index f0e03e7937e3..000000000000
--- a/drivers/macintosh/nvram.c
+++ /dev/null
@@ -1,130 +0,0 @@
-/*
- * /dev/nvram driver for Power Macintosh.
- */
-
-#define NVRAM_VERSION "1.0"
-
-#include <linux/module.h>
-
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/miscdevice.h>
-#include <linux/fcntl.h>
-#include <linux/nvram.h>
-#include <linux/init.h>
-#include <asm/uaccess.h>
-#include <asm/nvram.h>
-
-#define NVRAM_SIZE	8192
-
-static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
-{
-	switch (origin) {
-	case 0:
-		break;
-	case 1:
-		offset += file->f_pos;
-		break;
-	case 2:
-		offset += NVRAM_SIZE;
-		break;
-	default:
-		offset = -1;
-	}
-	if (offset < 0)
-		return -EINVAL;
-
-	file->f_pos = offset;
-	return file->f_pos;
-}
-
-static ssize_t read_nvram(struct file *file, char __user *buf,
-			  size_t count, loff_t *ppos)
-{
-	unsigned int i;
-	char __user *p = buf;
-
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
-	if (*ppos >= NVRAM_SIZE)
-		return 0;
-	for (i = *ppos; count > 0 && i < NVRAM_SIZE; ++i, ++p, --count)
-		if (__put_user(nvram_read_byte(i), p))
-			return -EFAULT;
-	*ppos = i;
-	return p - buf;
-}
-
-static ssize_t write_nvram(struct file *file, const char __user *buf,
-			   size_t count, loff_t *ppos)
-{
-	unsigned int i;
-	const char __user *p = buf;
-	char c;
-
-	if (!access_ok(VERIFY_READ, buf, count))
-		return -EFAULT;
-	if (*ppos >= NVRAM_SIZE)
-		return 0;
-	for (i = *ppos; count > 0 && i < NVRAM_SIZE; ++i, ++p, --count) {
-		if (__get_user(c, p))
-			return -EFAULT;
-		nvram_write_byte(c, i);
-	}
-	*ppos = i;
-	return p - buf;
-}
-
-static long nvram_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	switch(cmd) {
-		case PMAC_NVRAM_GET_OFFSET:
-		{
-			int part, offset;
-			if (copy_from_user(&part, (void __user*)arg, sizeof(part)) != 0)
-				return -EFAULT;
-			if (part < pmac_nvram_OF || part > pmac_nvram_NR)
-				return -EINVAL;
-			offset = pmac_get_partition(part);
-			if (copy_to_user((void __user*)arg, &offset, sizeof(offset)) != 0)
-				return -EFAULT;
-			break;
-		}
-
-		default:
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-const struct file_operations nvram_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= nvram_llseek,
-	.read		= read_nvram,
-	.write		= write_nvram,
-	.unlocked_ioctl	= nvram_ioctl,
-};
-
-static struct miscdevice nvram_dev = {
-	NVRAM_MINOR,
-	"nvram",
-	&nvram_fops
-};
-
-int __init nvram_init(void)
-{
-	printk(KERN_INFO "Macintosh non-volatile memory driver v%s\n",
-		NVRAM_VERSION);
-	return misc_register(&nvram_dev);
-}
-
-void __exit nvram_cleanup(void)
-{
-        misc_deregister( &nvram_dev );
-}
-
-module_init(nvram_init);
-module_exit(nvram_cleanup);
-MODULE_LICENSE("GPL");
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index fa028fa82df4..cb64e64a4789 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -55,7 +55,7 @@ static void bch_bio_submit_split_done(struct closure *cl)
 
 	s->bio->bi_end_io = s->bi_end_io;
 	s->bio->bi_private = s->bi_private;
-	bio_endio_nodec(s->bio, 0);
+	bio_endio(s->bio, 0);
 
 	closure_debug_destroy(&s->cl);
 	mempool_free(s, s->p->bio_split_hook);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ab43faddb447..1616f668a4cb 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -619,7 +619,7 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio)
 	bio->bi_end_io		= request_endio;
 	bio->bi_private		= &s->cl;
 
-	atomic_set(&bio->bi_cnt, 3);
+	bio_cnt_set(bio, 3);
 }
 
 static void search_free(struct closure *cl)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 2bc56e2a3526..135a0907e9de 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -177,11 +177,16 @@ static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *mdde
 	 * nr_pending is 0 and In_sync is clear, the entries we return will
 	 * still be in the same position on the list when we re-enter
 	 * list_for_each_entry_continue_rcu.
+	 *
+	 * Note that if entered with 'rdev == NULL' to start at the
+	 * beginning, we temporarily assign 'rdev' to an address which
+	 * isn't really an rdev, but which can be used by
+	 * list_for_each_entry_continue_rcu() to find the first entry.
 	 */
 	rcu_read_lock();
 	if (rdev == NULL)
 		/* start at the beginning */
-		rdev = list_entry_rcu(&mddev->disks, struct md_rdev, same_set);
+		rdev = list_entry(&mddev->disks, struct md_rdev, same_set);
 	else {
 		/* release the previous rdev and start from there. */
 		rdev_dec_pending(rdev, mddev);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 7755af351867..41b2594a80c6 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -86,12 +86,6 @@ static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
 	bio->bi_private = h->bi_private;
-
-	/*
-	 * Must bump bi_remaining to allow bio to complete with
-	 * restored bi_end_io.
-	 */
-	atomic_inc(&bio->bi_remaining);
 }
 
 /*----------------------------------------------------------------*/
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9eeea196328a..5503e43e5f28 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -925,10 +925,11 @@ static int crypt_convert(struct crypt_config *cc,
 
 		switch (r) {
 		/* async */
-		case -EINPROGRESS:
 		case -EBUSY:
 			wait_for_completion(&ctx->restart);
 			reinit_completion(&ctx->restart);
+			/* fall through*/
+		case -EINPROGRESS:
 			ctx->req = NULL;
 			ctx->cc_sector++;
 			continue;
@@ -1345,8 +1346,10 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 	struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx);
 	struct crypt_config *cc = io->cc;
 
-	if (error == -EINPROGRESS)
+	if (error == -EINPROGRESS) {
+		complete(&ctx->restart);
 		return;
+	}
 
 	if (!error && cc->iv_gen_ops && cc->iv_gen_ops->post)
 		error = cc->iv_gen_ops->post(cc, iv_of_dmreq(cc, dmreq), dmreq);
@@ -1357,15 +1360,12 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 	crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
 
 	if (!atomic_dec_and_test(&ctx->cc_pending))
-		goto done;
+		return;
 
 	if (bio_data_dir(io->base_bio) == READ)
 		kcryptd_crypt_read_done(io);
 	else
 		kcryptd_crypt_write_io_submit(io, 1);
-done:
-	if (!completion_done(&ctx->restart))
-		complete(&ctx->restart);
 }
 
 static void kcryptd_crypt(struct work_struct *work)
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 63953477a07c..eff7bdd7731d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -429,9 +429,11 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		/* blk-mq request-based interface */
 		*__clone = blk_get_request(bdev_get_queue(bdev),
 					   rq_data_dir(rq), GFP_ATOMIC);
-		if (IS_ERR(*__clone))
+		if (IS_ERR(*__clone)) {
 			/* ENOMEM, requeue */
+			clear_mapinfo(m, map_context);
 			return r;
+		}
 		(*__clone)->bio = (*__clone)->biotail = NULL;
 		(*__clone)->rq_disk = bdev->bd_disk;
 		(*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 089d62751f7f..743fa9bbae9e 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1254,8 +1254,6 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error)
 			dm_bio_restore(bd, bio);
 			bio_record->details.bi_bdev = NULL;
 
-			atomic_inc(&bio->bi_remaining);
-
 			queue_bio(ms, bio, rw);
 			return DM_ENDIO_INCOMPLETE;
 		}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index f83a0f3fc365..7c82d3ccce87 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1478,7 +1478,6 @@ out:
 	if (full_bio) {
 		full_bio->bi_end_io = pe->full_bio_end_io;
 		full_bio->bi_private = pe->full_bio_private;
-		atomic_inc(&full_bio->bi_remaining);
 	}
 	increment_pending_exceptions_done_count();
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d9b00b8565c6..a5f94125ad01 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -820,6 +820,12 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
 }
 EXPORT_SYMBOL(dm_consume_args);
 
+static bool __table_type_request_based(unsigned table_type)
+{
+	return (table_type == DM_TYPE_REQUEST_BASED ||
+		table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
 static int dm_table_set_type(struct dm_table *t)
 {
 	unsigned i;
@@ -852,8 +858,7 @@ static int dm_table_set_type(struct dm_table *t)
 		 * Determine the type from the live device.
 		 * Default to bio-based if device is new.
 		 */
-		if (live_md_type == DM_TYPE_REQUEST_BASED ||
-		    live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+		if (__table_type_request_based(live_md_type))
 			request_based = 1;
 		else
 			bio_based = 1;
@@ -903,7 +908,7 @@ static int dm_table_set_type(struct dm_table *t)
 			}
 		t->type = DM_TYPE_MQ_REQUEST_BASED;
 
-	} else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+	} else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
 		/* inherit live MD type */
 		t->type = live_md_type;
 
@@ -925,10 +930,7 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-	unsigned table_type = dm_table_get_type(t);
-
-	return (table_type == DM_TYPE_REQUEST_BASED ||
-		table_type == DM_TYPE_MQ_REQUEST_BASED);
+	return __table_type_request_based(dm_table_get_type(t));
 }
 
 bool dm_table_mq_request_based(struct dm_table *t)
@@ -940,21 +942,28 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *
 {
 	unsigned type = dm_table_get_type(t);
 	unsigned per_bio_data_size = 0;
-	struct dm_target *tgt;
 	unsigned i;
 
-	if (unlikely(type == DM_TYPE_NONE)) {
+	switch (type) {
+	case DM_TYPE_BIO_BASED:
+		for (i = 0; i < t->num_targets; i++) {
+			struct dm_target *tgt = t->targets + i;
+
+			per_bio_data_size = max(per_bio_data_size,
+						tgt->per_bio_data_size);
+		}
+		t->mempools = dm_alloc_bio_mempools(t->integrity_supported,
+						    per_bio_data_size);
+		break;
+	case DM_TYPE_REQUEST_BASED:
+	case DM_TYPE_MQ_REQUEST_BASED:
+		t->mempools = dm_alloc_rq_mempools(md, type);
+		break;
+	default:
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	if (type == DM_TYPE_BIO_BASED)
-		for (i = 0; i < t->num_targets; i++) {
-			tgt = t->targets + i;
-			per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size);
-		}
-
-	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, per_bio_data_size);
 	if (!t->mempools)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 921aafd12aee..e852602c0091 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -793,10 +793,9 @@ static void inc_remap_and_issue_cell(struct thin_c *tc,
 
 static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
-	if (m->bio) {
+	if (m->bio)
 		m->bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&m->bio->bi_remaining);
-	}
+
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
 	mempool_free(m, m->tc->pool->mapping_pool);
@@ -810,10 +809,8 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	int r;
 
 	bio = m->bio;
-	if (bio) {
+	if (bio)
 		bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&bio->bi_remaining);
-	}
 
 	if (m->err) {
 		cell_error(pool, m->cell);
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 66616db33e6f..bb9c6a00e4b0 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -459,7 +459,7 @@ static void verity_finish_io(struct dm_verity_io *io, int error)
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_private = io->orig_bi_private;
 
-	bio_endio_nodec(bio, error);
+	bio_endio(bio, error);
 }
 
 static void verity_work(struct work_struct *w)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a930b72314ac..4d6f089a0e9e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -990,57 +990,6 @@ static void clone_endio(struct bio *bio, int error)
 	dec_pending(io, error);
 }
 
-/*
- * Partial completion handling for request-based dm
- */
-static void end_clone_bio(struct bio *clone, int error)
-{
-	struct dm_rq_clone_bio_info *info =
-		container_of(clone, struct dm_rq_clone_bio_info, clone);
-	struct dm_rq_target_io *tio = info->tio;
-	struct bio *bio = info->orig;
-	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
-
-	bio_put(clone);
-
-	if (tio->error)
-		/*
-		 * An error has already been detected on the request.
-		 * Once error occurred, just let clone->end_io() handle
-		 * the remainder.
-		 */
-		return;
-	else if (error) {
-		/*
-		 * Don't notice the error to the upper layer yet.
-		 * The error handling decision is made by the target driver,
-		 * when the request is completed.
-		 */
-		tio->error = error;
-		return;
-	}
-
-	/*
-	 * I/O for the bio successfully completed.
-	 * Notice the data completion to the upper layer.
-	 */
-
-	/*
-	 * bios are processed from the head of the list.
-	 * So the completing bio should always be rq->bio.
-	 * If it's not, something wrong is happening.
-	 */
-	if (tio->orig->bio != bio)
-		DMERR("bio completion is going in the middle of the request");
-
-	/*
-	 * Update the original request.
-	 * Do not use blk_end_request() here, because it may complete
-	 * the original request before the clone, and break the ordering.
-	 */
-	blk_update_request(tio->orig, 0, nr_bytes);
-}
-
 static struct dm_rq_target_io *tio_from_request(struct request *rq)
 {
 	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
@@ -1082,15 +1031,11 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	dm_put(md);
 }
 
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
 {
 	struct dm_rq_target_io *tio = clone->end_io_data;
 	struct mapped_device *md = tio->md;
 
-	WARN_ON_ONCE(must_be_mapped && !clone->q);
-
-	blk_rq_unprep_clone(clone);
-
 	if (md->type == DM_TYPE_MQ_REQUEST_BASED)
 		/* stacked on blk-mq queue(s) */
 		tio->ti->type->release_clone_rq(clone);
@@ -1132,7 +1077,7 @@ static void dm_end_request(struct request *clone, int error)
 			rq->sense_len = clone->sense_len;
 	}
 
-	free_rq_clone(clone, true);
+	free_rq_clone(clone);
 	if (!rq->q->mq_ops)
 		blk_end_request_all(rq, error);
 	else
@@ -1151,7 +1096,7 @@ static void dm_unprep_request(struct request *rq)
 	}
 
 	if (clone)
-		free_rq_clone(clone, false);
+		free_rq_clone(clone);
 }
 
 /*
@@ -1164,6 +1109,7 @@ static void old_requeue_request(struct request *rq)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	blk_requeue_request(q, rq);
+	blk_run_queue_async(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -1724,8 +1670,7 @@ static int dm_merge_bvec(struct request_queue *q,
 	struct mapped_device *md = q->queuedata;
 	struct dm_table *map = dm_get_live_table_fast(md);
 	struct dm_target *ti;
-	sector_t max_sectors;
-	int max_size = 0;
+	sector_t max_sectors, max_size = 0;
 
 	if (unlikely(!map))
 		goto out;
@@ -1740,8 +1685,16 @@ static int dm_merge_bvec(struct request_queue *q,
 	max_sectors = min(max_io_len(bvm->bi_sector, ti),
 			  (sector_t) queue_max_sectors(q));
 	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-	if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
-		max_size = 0;
+
+	/*
+	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+	 * to the targets' merge function since it holds sectors not bytes).
+	 * Just doing this as an interim fix for stable@ because the more
+	 * comprehensive cleanup of switching to sector_t will impact every
+	 * DM target that implements a ->merge hook.
+	 */
+	if (max_size > INT_MAX)
+		max_size = INT_MAX;
 
 	/*
 	 * merge_bvec_fn() returns number of bytes
@@ -1749,7 +1702,7 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * max is precomputed maximal io size
 	 */
 	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, max_size);
+		max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
 	/*
 	 * If the target doesn't support merge method and some of the devices
 	 * provided their merge_bvec method (we know this by looking for the
@@ -1821,39 +1774,13 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
 		dm_complete_request(rq, r);
 }
 
-static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
-				 void *data)
+static void setup_clone(struct request *clone, struct request *rq,
+		        struct dm_rq_target_io *tio)
 {
-	struct dm_rq_target_io *tio = data;
-	struct dm_rq_clone_bio_info *info =
-		container_of(bio, struct dm_rq_clone_bio_info, clone);
-
-	info->orig = bio_orig;
-	info->tio = tio;
-	bio->bi_end_io = end_clone_bio;
-
-	return 0;
-}
-
-static int setup_clone(struct request *clone, struct request *rq,
-		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	int r;
-
-	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
-			      dm_rq_bio_constructor, tio);
-	if (r)
-		return r;
-
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
+	blk_rq_prep_clone(clone, rq);
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
-
 	tio->clone = clone;
-
-	return 0;
 }
 
 static struct request *clone_rq(struct request *rq, struct mapped_device *md,
@@ -1874,12 +1801,7 @@ static struct request *clone_rq(struct request *rq, struct mapped_device *md,
 		clone = tio->clone;
 
 	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		if (alloc_clone)
-			free_clone_request(md, clone);
-		return NULL;
-	}
+	setup_clone(clone, rq, tio);
 
 	return clone;
 }
@@ -1971,13 +1893,9 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
 			dm_kill_unmapped_request(rq, r);
 			return r;
 		}
-		if (IS_ERR(clone))
-			return DM_MAPIO_REQUEUE;
-		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
+		if (r != DM_MAPIO_REMAPPED)
+			return r;
+		setup_clone(clone, rq, tio);
 	}
 
 	switch (r) {
@@ -2431,8 +2349,6 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
-
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
 	md->rq_pool = p->rq_pool;
@@ -2753,13 +2669,15 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
 		/* clone request is allocated at the end of the pdu */
 		tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
-		if (!clone_rq(rq, md, tio, GFP_ATOMIC))
-			return BLK_MQ_RQ_QUEUE_BUSY;
+		(void) clone_rq(rq, md, tio, GFP_ATOMIC);
 		queue_kthread_work(&md->kworker, &tio->work);
 	} else {
 		/* Direct call is fine since .queue_rq allows allocations */
-		if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-			dm_requeue_unmapped_original_request(md, rq);
+		if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+			/* Undo dm_start_request() before requeuing */
+			rq_completed(md, rq_data_dir(rq), false);
+			return BLK_MQ_RQ_QUEUE_BUSY;
+		}
 	}
 
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -3536,48 +3454,23 @@ int dm_noflush_suspending(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
-					    unsigned integrity, unsigned per_bio_data_size)
+struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
+					     unsigned per_bio_data_size)
 {
-	struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL);
-	struct kmem_cache *cachep = NULL;
-	unsigned int pool_size = 0;
+	struct dm_md_mempools *pools;
+	unsigned int pool_size = dm_get_reserved_bio_based_ios();
 	unsigned int front_pad;
 
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
 	if (!pools)
 		return NULL;
 
-	type = filter_md_type(type, md);
-
-	switch (type) {
-	case DM_TYPE_BIO_BASED:
-		cachep = _io_cache;
-		pool_size = dm_get_reserved_bio_based_ios();
-		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
-		break;
-	case DM_TYPE_REQUEST_BASED:
-		cachep = _rq_tio_cache;
-		pool_size = dm_get_reserved_rq_based_ios();
-		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
-		if (!pools->rq_pool)
-			goto out;
-		/* fall through to setup remaining rq-based pools */
-	case DM_TYPE_MQ_REQUEST_BASED:
-		if (!pool_size)
-			pool_size = dm_get_reserved_rq_based_ios();
-		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
-		/* per_bio_data_size is not used. See __bind_mempools(). */
-		WARN_ON(per_bio_data_size != 0);
-		break;
-	default:
-		BUG();
-	}
+	front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) +
+		offsetof(struct dm_target_io, clone);
 
-	if (cachep) {
-		pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
-		if (!pools->io_pool)
-			goto out;
-	}
+	pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+	if (!pools->io_pool)
+		goto out;
 
 	pools->bs = bioset_create_nobvec(pool_size, front_pad);
 	if (!pools->bs)
@@ -3587,10 +3480,34 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		goto out;
 
 	return pools;
-
 out:
 	dm_free_md_mempools(pools);
+	return NULL;
+}
+
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md,
+					    unsigned type)
+{
+	unsigned int pool_size = dm_get_reserved_rq_based_ios();
+	struct dm_md_mempools *pools;
+
+	pools = kzalloc(sizeof(*pools), GFP_KERNEL);
+	if (!pools)
+		return NULL;
 
+	if (filter_md_type(type, md) == DM_TYPE_REQUEST_BASED) {
+		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
+		if (!pools->rq_pool)
+			goto out;
+	}
+
+	pools->io_pool = mempool_create_slab_pool(pool_size, _rq_tio_cache);
+	if (!pools->io_pool)
+		goto out;
+
+	return pools;
+out:
+	dm_free_md_mempools(pools);
 	return NULL;
 }
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 6123c2bf9150..e6e66d087b26 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -222,8 +222,9 @@ void dm_kcopyd_exit(void);
 /*
  * Mempool operations
  */
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
-					    unsigned integrity, unsigned per_bio_data_size);
+struct dm_md_mempools *dm_alloc_bio_mempools(unsigned integrity,
+					     unsigned per_bio_data_size);
+struct dm_md_mempools *dm_alloc_rq_mempools(struct mapped_device *md, unsigned type);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
 /*
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d4f31e195e26..4dbed4a67aaf 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3834,7 +3834,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 				err = -EBUSY;
 		}
 		spin_unlock(&mddev->lock);
-		return err;
+		return err ?: len;
 	}
 	err = mddev_lock(mddev);
 	if (err)
@@ -4211,34 +4211,36 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (cmd_match(page, "frozen"))
-		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-	else
-		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
 	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
-		flush_workqueue(md_misc_wq);
-		if (mddev->sync_thread) {
-			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			if (mddev_lock(mddev) == 0) {
+		if (cmd_match(page, "frozen"))
+			set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		else
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
+		    mddev_lock(mddev) == 0) {
+			flush_workqueue(md_misc_wq);
+			if (mddev->sync_thread) {
+				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 				md_reap_sync_thread(mddev);
-				mddev_unlock(mddev);
 			}
+			mddev_unlock(mddev);
 		}
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
 		return -EBUSY;
 	else if (cmd_match(page, "resync"))
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 	else if (cmd_match(page, "recover")) {
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	} else if (cmd_match(page, "reshape")) {
 		int err;
 		if (mddev->pers->start_reshape == NULL)
 			return -EINVAL;
 		err = mddev_lock(mddev);
 		if (!err) {
+			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 			err = mddev->pers->start_reshape(mddev);
 			mddev_unlock(mddev);
 		}
@@ -4250,6 +4252,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		else if (!cmd_match(page, "repair"))
 			return -EINVAL;
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	}
@@ -4818,12 +4821,12 @@ static void md_free(struct kobject *ko)
 	if (mddev->sysfs_state)
 		sysfs_put(mddev->sysfs_state);
 
+	if (mddev->queue)
+		blk_cleanup_queue(mddev->queue);
 	if (mddev->gendisk) {
 		del_gendisk(mddev->gendisk);
 		put_disk(mddev->gendisk);
 	}
-	if (mddev->queue)
-		blk_cleanup_queue(mddev->queue);
 
 	kfree(mddev);
 }
@@ -8259,6 +8262,7 @@ void md_reap_sync_thread(struct mddev *mddev)
 	if (mddev_is_clustered(mddev))
 		md_cluster_ops->metadata_update_finish(mddev);
 	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 2cb59a641cd2..efb654eb5399 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -188,8 +188,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		}
 		dev[j] = rdev1;
 
-		disk_stack_limits(mddev->gendisk, rdev1->bdev,
-				  rdev1->data_offset << 9);
+		if (mddev->queue)
+			disk_stack_limits(mddev->gendisk, rdev1->bdev,
+					  rdev1->data_offset << 9);
 
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
 			conf->has_merge_bvec = 1;
@@ -523,6 +524,9 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 			 ? (sector & (chunk_sects-1))
 			 : sector_div(sector, chunk_sects));
 
+		/* Restore due to sector_div */
+		sector = bio->bi_iter.bi_sector;
+
 		if (sectors < bio_sectors(bio)) {
 			split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set);
 			bio_chain(split, bio);
@@ -530,7 +534,6 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
 			split = bio;
 		}
 
-		sector = bio->bi_iter.bi_sector;
 		zone = find_zone(mddev->private, &sector);
 		tmp_dev = map_sector(mddev, zone, sector, &sector);
 		split->bi_bdev = tmp_dev->bdev;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e793ab6b3570..f55c3f35b746 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4156,6 +4156,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 77dfd720aaa0..b6793d2e051f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -749,6 +749,7 @@ static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 static bool stripe_can_batch(struct stripe_head *sh)
 {
 	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
+		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
 		is_full_stripe_write(sh);
 }
 
@@ -837,6 +838,15 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
 		    < IO_THRESHOLD)
 			md_wakeup_thread(conf->mddev->thread);
 
+	if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
+		int seq = sh->bm_seq;
+		if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
+		    sh->batch_head->bm_seq > seq)
+			seq = sh->batch_head->bm_seq;
+		set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
+		sh->batch_head->bm_seq = seq;
+	}
+
 	atomic_inc(&sh->count);
 unlock_out:
 	unlock_two_stripes(head, sh);
@@ -1078,9 +1088,6 @@ again:
 			pr_debug("skip op %ld on disc %d for sector %llu\n",
 				bi->bi_rw, i, (unsigned long long)sh->sector);
 			clear_bit(R5_LOCKED, &sh->dev[i].flags);
-			if (sh->batch_head)
-				set_bit(STRIPE_BATCH_ERR,
-					&sh->batch_head->state);
 			set_bit(STRIPE_HANDLE, &sh->state);
 		}
 
@@ -1825,7 +1832,7 @@ again:
 	} else
 		init_async_submit(&submit, 0, tx, NULL, NULL,
 				  to_addr_conv(sh, percpu, j));
-	async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE,  &submit);
+	tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE,  &submit);
 	if (!last_stripe) {
 		j++;
 		sh = list_first_entry(&sh->batch_list, struct stripe_head,
@@ -1971,17 +1978,30 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	put_cpu();
 }
 
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+{
+	struct stripe_head *sh;
+
+	sh = kmem_cache_zalloc(sc, gfp);
+	if (sh) {
+		spin_lock_init(&sh->stripe_lock);
+		spin_lock_init(&sh->batch_lock);
+		INIT_LIST_HEAD(&sh->batch_list);
+		INIT_LIST_HEAD(&sh->lru);
+		atomic_set(&sh->count, 1);
+	}
+	return sh;
+}
 static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 {
 	struct stripe_head *sh;
-	sh = kmem_cache_zalloc(conf->slab_cache, gfp);
+
+	sh = alloc_stripe(conf->slab_cache, gfp);
 	if (!sh)
 		return 0;
 
 	sh->raid_conf = conf;
 
-	spin_lock_init(&sh->stripe_lock);
-
 	if (grow_buffers(sh, gfp)) {
 		shrink_buffers(sh);
 		kmem_cache_free(conf->slab_cache, sh);
@@ -1990,13 +2010,8 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
 	sh->hash_lock_index =
 		conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
 	/* we just created an active stripe so... */
-	atomic_set(&sh->count, 1);
 	atomic_inc(&conf->active_stripes);
-	INIT_LIST_HEAD(&sh->lru);
 
-	spin_lock_init(&sh->batch_lock);
-	INIT_LIST_HEAD(&sh->batch_list);
-	sh->batch_head = NULL;
 	release_stripe(sh);
 	conf->max_nr_stripes++;
 	return 1;
@@ -2060,6 +2075,35 @@ static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags)
 	return ret;
 }
 
+static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
+{
+	unsigned long cpu;
+	int err = 0;
+
+	mddev_suspend(conf->mddev);
+	get_online_cpus();
+	for_each_present_cpu(cpu) {
+		struct raid5_percpu *percpu;
+		struct flex_array *scribble;
+
+		percpu = per_cpu_ptr(conf->percpu, cpu);
+		scribble = scribble_alloc(new_disks,
+					  new_sectors / STRIPE_SECTORS,
+					  GFP_NOIO);
+
+		if (scribble) {
+			flex_array_free(percpu->scribble);
+			percpu->scribble = scribble;
+		} else {
+			err = -ENOMEM;
+			break;
+		}
+	}
+	put_online_cpus();
+	mddev_resume(conf->mddev);
+	return err;
+}
+
 static int resize_stripes(struct r5conf *conf, int newsize)
 {
 	/* Make all the stripes able to hold 'newsize' devices.
@@ -2088,7 +2132,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	struct stripe_head *osh, *nsh;
 	LIST_HEAD(newstripes);
 	struct disk_info *ndisks;
-	unsigned long cpu;
 	int err;
 	struct kmem_cache *sc;
 	int i;
@@ -2109,13 +2152,11 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		return -ENOMEM;
 
 	for (i = conf->max_nr_stripes; i; i--) {
-		nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
+		nsh = alloc_stripe(sc, GFP_KERNEL);
 		if (!nsh)
 			break;
 
 		nsh->raid_conf = conf;
-		spin_lock_init(&nsh->stripe_lock);
-
 		list_add(&nsh->lru, &newstripes);
 	}
 	if (i) {
@@ -2142,13 +2183,11 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 				    lock_device_hash_lock(conf, hash));
 		osh = get_free_stripe(conf, hash);
 		unlock_device_hash_lock(conf, hash);
-		atomic_set(&nsh->count, 1);
+
 		for(i=0; i<conf->pool_size; i++) {
 			nsh->dev[i].page = osh->dev[i].page;
 			nsh->dev[i].orig_page = osh->dev[i].page;
 		}
-		for( ; i<newsize; i++)
-			nsh->dev[i].page = NULL;
 		nsh->hash_lock_index = hash;
 		kmem_cache_free(conf->slab_cache, osh);
 		cnt++;
@@ -2174,25 +2213,6 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	} else
 		err = -ENOMEM;
 
-	get_online_cpus();
-	for_each_present_cpu(cpu) {
-		struct raid5_percpu *percpu;
-		struct flex_array *scribble;
-
-		percpu = per_cpu_ptr(conf->percpu, cpu);
-		scribble = scribble_alloc(newsize, conf->chunk_sectors /
-			STRIPE_SECTORS, GFP_NOIO);
-
-		if (scribble) {
-			flex_array_free(percpu->scribble);
-			percpu->scribble = scribble;
-		} else {
-			err = -ENOMEM;
-			break;
-		}
-	}
-	put_online_cpus();
-
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -2212,7 +2232,8 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 
 	conf->slab_cache = sc;
 	conf->active_name = 1-conf->active_name;
-	conf->pool_size = newsize;
+	if (!err)
+		conf->pool_size = newsize;
 	return err;
 }
 
@@ -2434,7 +2455,7 @@ static void raid5_end_write_request(struct bio *bi, int error)
 	}
 	rdev_dec_pending(rdev, conf->mddev);
 
-	if (sh->batch_head && !uptodate)
+	if (sh->batch_head && !uptodate && !replacement)
 		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
 
 	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
@@ -2976,14 +2997,32 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
 	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
 		(unsigned long long)(*bip)->bi_iter.bi_sector,
 		(unsigned long long)sh->sector, dd_idx);
-	spin_unlock_irq(&sh->stripe_lock);
 
 	if (conf->mddev->bitmap && firstwrite) {
+		/* Cannot hold spinlock over bitmap_startwrite,
+		 * but must ensure this isn't added to a batch until
+		 * we have added to the bitmap and set bm_seq.
+		 * So set STRIPE_BITMAP_PENDING to prevent
+		 * batching.
+		 * If multiple add_stripe_bio() calls race here they
+		 * much all set STRIPE_BITMAP_PENDING.  So only the first one
+		 * to complete "bitmap_startwrite" gets to set
+		 * STRIPE_BIT_DELAY.  This is important as once a stripe
+		 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
+		 * any more.
+		 */
+		set_bit(STRIPE_BITMAP_PENDING, &sh->state);
+		spin_unlock_irq(&sh->stripe_lock);
 		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
 				  STRIPE_SECTORS, 0);
-		sh->bm_seq = conf->seq_flush+1;
-		set_bit(STRIPE_BIT_DELAY, &sh->state);
+		spin_lock_irq(&sh->stripe_lock);
+		clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
+		if (!sh->batch_head) {
+			sh->bm_seq = conf->seq_flush+1;
+			set_bit(STRIPE_BIT_DELAY, &sh->state);
+		}
 	}
+	spin_unlock_irq(&sh->stripe_lock);
 
 	if (stripe_can_batch(sh))
 		stripe_add_to_batch_list(conf, sh);
@@ -3278,7 +3317,9 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 		/* reconstruct-write isn't being forced */
 		return 0;
 	for (i = 0; i < s->failed; i++) {
-		if (!test_bit(R5_UPTODATE, &fdev[i]->flags) &&
+		if (s->failed_num[i] != sh->pd_idx &&
+		    s->failed_num[i] != sh->qd_idx &&
+		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
 		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
 			return 1;
 	}
@@ -3298,6 +3339,7 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 		 */
 		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
 		BUG_ON(test_bit(R5_Wantread, &dev->flags));
+		BUG_ON(sh->batch_head);
 		if ((s->uptodate == disks - 1) &&
 		    (s->failed && (disk_idx == s->failed_num[0] ||
 				   disk_idx == s->failed_num[1]))) {
@@ -3366,7 +3408,6 @@ static void handle_stripe_fill(struct stripe_head *sh,
 {
 	int i;
 
-	BUG_ON(sh->batch_head);
 	/* look for blocks to read/compute, skip this if a compute
 	 * is already in flight, or if the stripe contents are in the
 	 * midst of changing due to a write
@@ -3379,6 +3420,8 @@ static void handle_stripe_fill(struct stripe_head *sh,
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+				    unsigned long handle_flags);
 /* handle_stripe_clean_event
  * any written block on an uptodate or failed drive can be returned.
  * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
@@ -3392,7 +3435,6 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 	int discard_pending = 0;
 	struct stripe_head *head_sh = sh;
 	bool do_endio = false;
-	int wakeup_nr = 0;
 
 	for (i = disks; i--; )
 		if (sh->dev[i].written) {
@@ -3481,44 +3523,8 @@ unhash:
 		if (atomic_dec_and_test(&conf->pending_full_writes))
 			md_wakeup_thread(conf->mddev->thread);
 
-	if (!head_sh->batch_head || !do_endio)
-		return;
-	for (i = 0; i < head_sh->disks; i++) {
-		if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
-			wakeup_nr++;
-	}
-	while (!list_empty(&head_sh->batch_list)) {
-		int i;
-		sh = list_first_entry(&head_sh->batch_list,
-				      struct stripe_head, batch_list);
-		list_del_init(&sh->batch_list);
-
-		set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
-			      head_sh->state & ~((1 << STRIPE_ACTIVE) |
-						 (1 << STRIPE_PREREAD_ACTIVE) |
-						 STRIPE_EXPAND_SYNC_FLAG));
-		sh->check_state = head_sh->check_state;
-		sh->reconstruct_state = head_sh->reconstruct_state;
-		for (i = 0; i < sh->disks; i++) {
-			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
-				wakeup_nr++;
-			sh->dev[i].flags = head_sh->dev[i].flags;
-		}
-
-		spin_lock_irq(&sh->stripe_lock);
-		sh->batch_head = NULL;
-		spin_unlock_irq(&sh->stripe_lock);
-		if (sh->state & STRIPE_EXPAND_SYNC_FLAG)
-			set_bit(STRIPE_HANDLE, &sh->state);
-		release_stripe(sh);
-	}
-
-	spin_lock_irq(&head_sh->stripe_lock);
-	head_sh->batch_head = NULL;
-	spin_unlock_irq(&head_sh->stripe_lock);
-	wake_up_nr(&conf->wait_for_overlap, wakeup_nr);
-	if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG)
-		set_bit(STRIPE_HANDLE, &head_sh->state);
+	if (head_sh->batch_head && do_endio)
+		break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
 }
 
 static void handle_stripe_dirtying(struct r5conf *conf,
@@ -4159,9 +4165,13 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 
 static int clear_batch_ready(struct stripe_head *sh)
 {
+	/* Return '1' if this is a member of batch, or
+	 * '0' if it is a lone stripe or a head which can now be
+	 * handled.
+	 */
 	struct stripe_head *tmp;
 	if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
-		return 0;
+		return (sh->batch_head && sh->batch_head != sh);
 	spin_lock(&sh->stripe_lock);
 	if (!sh->batch_head) {
 		spin_unlock(&sh->stripe_lock);
@@ -4189,46 +4199,65 @@ static int clear_batch_ready(struct stripe_head *sh)
 	return 0;
 }
 
-static void check_break_stripe_batch_list(struct stripe_head *sh)
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+				    unsigned long handle_flags)
 {
-	struct stripe_head *head_sh, *next;
+	struct stripe_head *sh, *next;
 	int i;
+	int do_wakeup = 0;
 
-	if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
-		return;
+	list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
 
-	head_sh = sh;
-	do {
-		sh = list_first_entry(&sh->batch_list,
-				      struct stripe_head, batch_list);
-		BUG_ON(sh == head_sh);
-	} while (!test_bit(STRIPE_DEGRADED, &sh->state));
-
-	while (sh != head_sh) {
-		next = list_first_entry(&sh->batch_list,
-					struct stripe_head, batch_list);
 		list_del_init(&sh->batch_list);
 
-		set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
-			      head_sh->state & ~((1 << STRIPE_ACTIVE) |
-						 (1 << STRIPE_PREREAD_ACTIVE) |
-						 (1 << STRIPE_DEGRADED) |
-						 STRIPE_EXPAND_SYNC_FLAG));
+		WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+					  (1 << STRIPE_SYNCING) |
+					  (1 << STRIPE_REPLACED) |
+					  (1 << STRIPE_PREREAD_ACTIVE) |
+					  (1 << STRIPE_DELAYED) |
+					  (1 << STRIPE_BIT_DELAY) |
+					  (1 << STRIPE_FULL_WRITE) |
+					  (1 << STRIPE_BIOFILL_RUN) |
+					  (1 << STRIPE_COMPUTE_RUN)  |
+					  (1 << STRIPE_OPS_REQ_PENDING) |
+					  (1 << STRIPE_DISCARD) |
+					  (1 << STRIPE_BATCH_READY) |
+					  (1 << STRIPE_BATCH_ERR) |
+					  (1 << STRIPE_BITMAP_PENDING)));
+		WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+					      (1 << STRIPE_REPLACED)));
+
+		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+					    (1 << STRIPE_DEGRADED)),
+			      head_sh->state & (1 << STRIPE_INSYNC));
+
 		sh->check_state = head_sh->check_state;
 		sh->reconstruct_state = head_sh->reconstruct_state;
-		for (i = 0; i < sh->disks; i++)
+		for (i = 0; i < sh->disks; i++) {
+			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+				do_wakeup = 1;
 			sh->dev[i].flags = head_sh->dev[i].flags &
 				(~((1 << R5_WriteError) | (1 << R5_Overlap)));
-
+		}
 		spin_lock_irq(&sh->stripe_lock);
 		sh->batch_head = NULL;
 		spin_unlock_irq(&sh->stripe_lock);
-
-		set_bit(STRIPE_HANDLE, &sh->state);
+		if (handle_flags == 0 ||
+		    sh->state & handle_flags)
+			set_bit(STRIPE_HANDLE, &sh->state);
 		release_stripe(sh);
-
-		sh = next;
 	}
+	spin_lock_irq(&head_sh->stripe_lock);
+	head_sh->batch_head = NULL;
+	spin_unlock_irq(&head_sh->stripe_lock);
+	for (i = 0; i < head_sh->disks; i++)
+		if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
+			do_wakeup = 1;
+	if (head_sh->state & handle_flags)
+		set_bit(STRIPE_HANDLE, &head_sh->state);
+
+	if (do_wakeup)
+		wake_up(&head_sh->raid_conf->wait_for_overlap);
 }
 
 static void handle_stripe(struct stripe_head *sh)
@@ -4253,7 +4282,8 @@ static void handle_stripe(struct stripe_head *sh)
 		return;
 	}
 
-	check_break_stripe_batch_list(sh);
+	if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
+		break_stripe_batch_list(sh, 0);
 
 	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
 		spin_lock(&sh->stripe_lock);
@@ -4307,6 +4337,7 @@ static void handle_stripe(struct stripe_head *sh)
 	if (s.failed > conf->max_degraded) {
 		sh->check_state = 0;
 		sh->reconstruct_state = 0;
+		break_stripe_batch_list(sh, 0);
 		if (s.to_read+s.to_write+s.written)
 			handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
 		if (s.syncing + s.replacing)
@@ -6221,8 +6252,11 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
 		percpu->spare_page = alloc_page(GFP_KERNEL);
 	if (!percpu->scribble)
 		percpu->scribble = scribble_alloc(max(conf->raid_disks,
-			conf->previous_raid_disks), conf->chunk_sectors /
-			STRIPE_SECTORS, GFP_KERNEL);
+						      conf->previous_raid_disks),
+						  max(conf->chunk_sectors,
+						      conf->prev_chunk_sectors)
+						   / STRIPE_SECTORS,
+						  GFP_KERNEL);
 
 	if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
 		free_scratch_buffer(conf, percpu);
@@ -7198,6 +7232,15 @@ static int check_reshape(struct mddev *mddev)
 	if (!check_stripe_cache(mddev))
 		return -ENOSPC;
 
+	if (mddev->new_chunk_sectors > mddev->chunk_sectors ||
+	    mddev->delta_disks > 0)
+		if (resize_chunks(conf,
+				  conf->previous_raid_disks
+				  + max(0, mddev->delta_disks),
+				  max(mddev->new_chunk_sectors,
+				      mddev->chunk_sectors)
+			    ) < 0)
+			return -ENOMEM;
 	return resize_stripes(conf, (conf->previous_raid_disks
 				     + mddev->delta_disks));
 }
@@ -7311,6 +7354,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 	set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
 	mddev->sync_thread = md_register_thread(md_do_sync, mddev,
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 7dc0dd86074b..896d603ad0da 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -337,9 +337,12 @@ enum {
 	STRIPE_ON_RELEASE_LIST,
 	STRIPE_BATCH_READY,
 	STRIPE_BATCH_ERR,
+	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
+				 * to batch yet.
+				 */
 };
 
-#define STRIPE_EXPAND_SYNC_FLAG \
+#define STRIPE_EXPAND_SYNC_FLAGS \
 	((1 << STRIPE_EXPAND_SOURCE) |\
 	(1 << STRIPE_EXPAND_READY) |\
 	(1 << STRIPE_EXPANDING) |\
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index 3ef0f90b128f..157099243d61 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -97,6 +97,7 @@ config MEDIA_CONTROLLER
 config MEDIA_CONTROLLER_DVB
 	bool "Enable Media controller for DVB"
 	depends on MEDIA_CONTROLLER
+	depends on BROKEN
 	---help---
 	  Enable the media controller API support for DVB.
 
diff --git a/drivers/media/pci/cx25821/cx25821-medusa-reg.h b/drivers/media/pci/cx25821/cx25821-medusa-reg.h
index c98ac946b277..2e10643a86b7 100644
--- a/drivers/media/pci/cx25821/cx25821-medusa-reg.h
+++ b/drivers/media/pci/cx25821/cx25821-medusa-reg.h
@@ -84,9 +84,9 @@
 #define	ABIST_BIN4_VGA3				0x01D4
 #define	ABIST_BIN5_VGA4				0x01D8
 #define	ABIST_BIN6_VGA5				0x01DC
-#define	ABIST_BIN7_VGA6				0x0x1E0
-#define	ABIST_CLAMP_A				0x0x1E4
-#define	ABIST_CLAMP_B				0x0x1E8
+#define	ABIST_BIN7_VGA6				0x01E0
+#define	ABIST_CLAMP_A				0x01E4
+#define	ABIST_CLAMP_B				0x01E8
 #define	ABIST_CLAMP_C				0x01EC
 #define	ABIST_CLAMP_D				0x01F0
 #define	ABIST_CLAMP_E				0x01F4
diff --git a/drivers/media/pci/ivtv/Kconfig b/drivers/media/pci/ivtv/Kconfig
index dd6ee57e3a4c..6e5867c57305 100644
--- a/drivers/media/pci/ivtv/Kconfig
+++ b/drivers/media/pci/ivtv/Kconfig
@@ -57,5 +57,8 @@ config VIDEO_FB_IVTV
 	  This is used in the Hauppauge PVR-350 card. There is a driver
 	  homepage at <http://www.ivtvdriver.org>.
 
+	  In order to use this module, you will need to boot with PAT disabled
+	  on x86 systems, using the nopat kernel parameter.
+
 	  To compile this driver as a module, choose M here: the
 	  module will be called ivtvfb.
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index 9ff1230192e8..4cb365d4ffdc 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -44,8 +44,8 @@
 #include <linux/ivtvfb.h>
 #include <linux/slab.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
+#ifdef CONFIG_X86_64
+#include <asm/pat.h>
 #endif
 
 #include "ivtv-driver.h"
@@ -155,12 +155,11 @@ struct osd_info {
 	/* Buffer size */
 	u32 video_buffer_size;
 
-#ifdef CONFIG_MTRR
 	/* video_base rounded down as required by hardware MTRRs */
 	unsigned long fb_start_aligned_physaddr;
 	/* video_base rounded up as required by hardware MTRRs */
 	unsigned long fb_end_aligned_physaddr;
-#endif
+	int wc_cookie;
 
 	/* Store the buffer offset */
 	int set_osd_coords_x;
@@ -1099,6 +1098,8 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 static int ivtvfb_init_io(struct ivtv *itv)
 {
 	struct osd_info *oi = itv->osd_info;
+	/* Find the largest power of two that maps the whole buffer */
+	int size_shift = 31;
 
 	mutex_lock(&itv->serialize_lock);
 	if (ivtv_init_on_first_open(itv)) {
@@ -1132,29 +1133,16 @@ static int ivtvfb_init_io(struct ivtv *itv)
 			oi->video_pbase, oi->video_vbase,
 			oi->video_buffer_size / 1024);
 
-#ifdef CONFIG_MTRR
-	{
-		/* Find the largest power of two that maps the whole buffer */
-		int size_shift = 31;
-
-		while (!(oi->video_buffer_size & (1 << size_shift))) {
-			size_shift--;
-		}
-		size_shift++;
-		oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
-		oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
-		oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
-		oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
-		if (mtrr_add(oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr,
-			     MTRR_TYPE_WRCOMB, 1) < 0) {
-			IVTVFB_INFO("disabled mttr\n");
-			oi->fb_start_aligned_physaddr = 0;
-			oi->fb_end_aligned_physaddr = 0;
-		}
-	}
-#endif
-
+	while (!(oi->video_buffer_size & (1 << size_shift)))
+		size_shift--;
+	size_shift++;
+	oi->fb_start_aligned_physaddr = oi->video_pbase & ~((1 << size_shift) - 1);
+	oi->fb_end_aligned_physaddr = oi->video_pbase + oi->video_buffer_size;
+	oi->fb_end_aligned_physaddr += (1 << size_shift) - 1;
+	oi->fb_end_aligned_physaddr &= ~((1 << size_shift) - 1);
+	oi->wc_cookie = arch_phys_wc_add(oi->fb_start_aligned_physaddr,
+					 oi->fb_end_aligned_physaddr -
+					 oi->fb_start_aligned_physaddr);
 	/* Blank the entire osd. */
 	memset_io(oi->video_vbase, 0, oi->video_buffer_size);
 
@@ -1172,14 +1160,7 @@ static void ivtvfb_release_buffers (struct ivtv *itv)
 
 	/* Release pseudo palette */
 	kfree(oi->ivtvfb_info.pseudo_palette);
-
-#ifdef CONFIG_MTRR
-	if (oi->fb_end_aligned_physaddr) {
-		mtrr_del(-1, oi->fb_start_aligned_physaddr,
-			oi->fb_end_aligned_physaddr - oi->fb_start_aligned_physaddr);
-	}
-#endif
-
+	arch_phys_wc_del(oi->wc_cookie);
 	kfree(oi);
 	itv->osd_info = NULL;
 }
@@ -1284,6 +1265,13 @@ static int __init ivtvfb_init(void)
 	int registered = 0;
 	int err;
 
+#ifdef CONFIG_X86_64
+	if (WARN(pat_enabled(),
+		 "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
+		return -ENODEV;
+	}
+#endif
+
 	if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
 		printk(KERN_ERR "ivtvfb:  ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",
 		     IVTV_MAX_CARDS - 1);
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 187f83629f7e..5dcc0313c38a 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -59,10 +59,6 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>		/* needed for in_interrupt() proto */
 #include <linux/dma-mapping.h>
-#include <asm/io.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
 #include <linux/kthread.h>
 #include <scsi/scsi_host.h>
 
@@ -2820,13 +2816,6 @@ mpt_adapter_dispose(MPT_ADAPTER *ioc)
 	pci_disable_device(ioc->pcidev);
 	pci_release_selected_regions(ioc->pcidev, ioc->bars);
 
-#if defined(CONFIG_MTRR) && 0
-	if (ioc->mtrr_reg > 0) {
-		mtrr_del(ioc->mtrr_reg, 0, 0);
-		dprintk(ioc, printk(MYIOC_s_INFO_FMT "MTRR region de-registered\n", ioc->name));
-	}
-#endif
-
 	/*  Zap the adapter lookup ptr!  */
 	list_del(&ioc->list);
 
@@ -4512,19 +4501,6 @@ PrimeIocFifos(MPT_ADAPTER *ioc)
 
 		ioc->req_frames_low_dma = (u32) (alloc_dma & 0xFFFFFFFF);
 
-#if defined(CONFIG_MTRR) && 0
-		/*
-		 *  Enable Write Combining MTRR for IOC's memory region.
-		 *  (at least as much as we can; "size and base must be
-		 *  multiples of 4 kiB"
-		 */
-		ioc->mtrr_reg = mtrr_add(ioc->req_frames_dma,
-					 sz,
-					 MTRR_TYPE_WRCOMB, 1);
-		dprintk(ioc, printk(MYIOC_s_DEBUG_FMT "MTRR region registered (base:size=%08x:%x)\n",
-				ioc->name, ioc->req_frames_dma, sz));
-#endif
-
 		for (i = 0; i < ioc->req_depth; i++) {
 			alloc_dma += ioc->req_sz;
 			mem += ioc->req_sz;
diff --git a/drivers/message/fusion/mptbase.h b/drivers/message/fusion/mptbase.h
index 8f14090b8b71..813d46311f6a 100644
--- a/drivers/message/fusion/mptbase.h
+++ b/drivers/message/fusion/mptbase.h
@@ -671,7 +671,6 @@ typedef struct _MPT_ADAPTER
 	u8			*HostPageBuffer; /* SAS - host page buffer support */
 	u32			HostPageBuffer_sz;
 	dma_addr_t		HostPageBuffer_dma;
-	int			 mtrr_reg;
 	struct pci_dev		*pcidev;	/* struct pci_dev pointer */
 	int			bars;		/* bitmask of BAR's that must be configured */
 	int			msi_enable;
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 5bdaae15a742..005a88b9f440 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -4090,7 +4090,7 @@ mptsas_handle_queue_full_event(struct fw_event_work *fw_event)
 					continue;
 				}
 				depth = scsi_track_queue_full(sdev,
-				    current_depth - 1);
+					sdev->queue_depth - 1);
 				if (depth > 0)
 					sdev_printk(KERN_INFO, sdev,
 					"Queue depth reduced to (%d)\n",
@@ -4100,7 +4100,7 @@ mptsas_handle_queue_full_event(struct fw_event_work *fw_event)
 					"Tagged Command Queueing is being "
 					"disabled\n");
 				else if (depth == 0)
-					sdev_printk(KERN_INFO, sdev,
+					sdev_printk(KERN_DEBUG, sdev,
 					"Queue depth not changed yet\n");
 			}
 		}
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index d2a85cde68da..e03b7f45b8f7 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -566,7 +566,7 @@ static int pm860x_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops pm860x_irq_domain_ops = {
+static const struct irq_domain_ops pm860x_irq_domain_ops = {
 	.map	= pm860x_irq_domain_map,
 	.xlate	= irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d5ad04dad081..653815950aa2 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -52,7 +52,8 @@ config PMIC_ADP5520
 config MFD_AAT2870_CORE
 	bool "AnalogicTech AAT2870"
 	select MFD_CORE
-	depends on I2C=y && GPIOLIB
+	depends on I2C=y
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  If you say yes here you get support for the AAT2870.
 	  This driver provides common support for accessing the device,
@@ -94,6 +95,8 @@ config MFD_AXP20X
 config MFD_CROS_EC
 	tristate "ChromeOS Embedded Controller"
 	select MFD_CORE
+	select CHROME_PLATFORMS
+	select CROS_EC_PROTO
 	help
 	  If you say Y here you get support for the ChromeOS Embedded
 	  Controller (EC) providing keyboard, battery and power services.
@@ -102,7 +105,7 @@ config MFD_CROS_EC
 
 config MFD_CROS_EC_I2C
 	tristate "ChromeOS Embedded Controller (I2C)"
-	depends on MFD_CROS_EC && I2C
+	depends on MFD_CROS_EC && CROS_EC_PROTO && I2C
 
 	help
 	  If you say Y here, you get support for talking to the ChromeOS
@@ -112,7 +115,7 @@ config MFD_CROS_EC_I2C
 
 config MFD_CROS_EC_SPI
 	tristate "ChromeOS Embedded Controller (SPI)"
-	depends on MFD_CROS_EC && SPI && OF
+	depends on MFD_CROS_EC && CROS_EC_PROTO && SPI && OF
 
 	---help---
 	  If you say Y here, you get support for talking to the ChromeOS EC
@@ -1115,7 +1118,8 @@ config MFD_TPS6586X
 
 config MFD_TPS65910
 	bool "TI TPS65910 Power Management chip"
-	depends on I2C=y && GPIOLIB
+	depends on I2C=y
+	depends on GPIOLIB || COMPILE_TEST
 	select MFD_CORE
 	select REGMAP_I2C
 	select REGMAP_IRQ
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 0e5cfeba107c..ea40e076cb61 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -39,13 +39,13 @@ obj-$(CONFIG_MFD_ARIZONA)	+= arizona-core.o
 obj-$(CONFIG_MFD_ARIZONA)	+= arizona-irq.o
 obj-$(CONFIG_MFD_ARIZONA_I2C)	+= arizona-i2c.o
 obj-$(CONFIG_MFD_ARIZONA_SPI)	+= arizona-spi.o
-ifneq ($(CONFIG_MFD_WM5102),n)
+ifeq ($(CONFIG_MFD_WM5102),y)
 obj-$(CONFIG_MFD_ARIZONA)	+= wm5102-tables.o
 endif
-ifneq ($(CONFIG_MFD_WM5110),n)
+ifeq ($(CONFIG_MFD_WM5110),y)
 obj-$(CONFIG_MFD_ARIZONA)	+= wm5110-tables.o
 endif
-ifneq ($(CONFIG_MFD_WM8997),n)
+ifeq ($(CONFIG_MFD_WM8997),y)
 obj-$(CONFIG_MFD_ARIZONA)	+= wm8997-tables.o
 endif
 obj-$(CONFIG_MFD_WM8400)	+= wm8400-core.o
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index c80a2925f8e5..000da72a0ae9 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -574,7 +574,7 @@ static int ab8500_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops ab8500_irq_ops = {
+static const struct irq_domain_ops ab8500_irq_ops = {
 	.map    = ab8500_irq_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c
index cdd6f3d63314..0236cd7cdce4 100644
--- a/drivers/mfd/ab8500-debugfs.c
+++ b/drivers/mfd/ab8500-debugfs.c
@@ -2885,7 +2885,7 @@ static ssize_t ab8500_subscribe_write(struct file *file,
 	}
 
 	err = request_threaded_irq(user_val, NULL, ab8500_debug_handler,
-				   IRQF_SHARED | IRQF_NO_SUSPEND,
+				   IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
 				   "ab8500-debug", &dev->kobj);
 	if (err < 0) {
 		pr_info("request_threaded_irq failed %d, %lu\n",
diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c
index dabbc93abdd7..c51c1b188d64 100644
--- a/drivers/mfd/ab8500-gpadc.c
+++ b/drivers/mfd/ab8500-gpadc.c
@@ -948,7 +948,8 @@ static int ab8500_gpadc_probe(struct platform_device *pdev)
 	if (gpadc->irq_sw >= 0) {
 		ret = request_threaded_irq(gpadc->irq_sw, NULL,
 			ab8500_bm_gpadcconvend_handler,
-			IRQF_NO_SUSPEND | IRQF_SHARED, "ab8500-gpadc-sw",
+			IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT,
+			"ab8500-gpadc-sw",
 			gpadc);
 		if (ret < 0) {
 			dev_err(gpadc->dev,
@@ -961,7 +962,8 @@ static int ab8500_gpadc_probe(struct platform_device *pdev)
 	if (gpadc->irq_hw >= 0) {
 		ret = request_threaded_irq(gpadc->irq_hw, NULL,
 			ab8500_bm_gpadcconvend_handler,
-			IRQF_NO_SUSPEND | IRQF_SHARED, "ab8500-gpadc-hw",
+			IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT,
+			"ab8500-gpadc-hw",
 			gpadc);
 		if (ret < 0) {
 			dev_err(gpadc->dev,
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index 6ca6dfab50eb..bebf58a06a6b 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -250,20 +250,50 @@ static int arizona_wait_for_boot(struct arizona *arizona)
 	return ret;
 }
 
-static int arizona_apply_hardware_patch(struct arizona* arizona)
+static inline void arizona_enable_reset(struct arizona *arizona)
+{
+	if (arizona->pdata.reset)
+		gpio_set_value_cansleep(arizona->pdata.reset, 0);
+}
+
+static void arizona_disable_reset(struct arizona *arizona)
+{
+	if (arizona->pdata.reset) {
+		switch (arizona->type) {
+		case WM5110:
+		case WM8280:
+			/* Meet requirements for minimum reset duration */
+			msleep(5);
+			break;
+		default:
+			break;
+		}
+
+		gpio_set_value_cansleep(arizona->pdata.reset, 1);
+		msleep(1);
+	}
+}
+
+struct arizona_sysclk_state {
+	unsigned int fll;
+	unsigned int sysclk;
+};
+
+static int arizona_enable_freerun_sysclk(struct arizona *arizona,
+					 struct arizona_sysclk_state *state)
 {
-	unsigned int fll, sysclk;
 	int ret, err;
 
 	/* Cache existing FLL and SYSCLK settings */
-	ret = regmap_read(arizona->regmap, ARIZONA_FLL1_CONTROL_1, &fll);
-	if (ret != 0) {
+	ret = regmap_read(arizona->regmap, ARIZONA_FLL1_CONTROL_1, &state->fll);
+	if (ret) {
 		dev_err(arizona->dev, "Failed to cache FLL settings: %d\n",
 			ret);
 		return ret;
 	}
-	ret = regmap_read(arizona->regmap, ARIZONA_SYSTEM_CLOCK_1, &sysclk);
-	if (ret != 0) {
+	ret = regmap_read(arizona->regmap, ARIZONA_SYSTEM_CLOCK_1,
+			  &state->sysclk);
+	if (ret) {
 		dev_err(arizona->dev, "Failed to cache SYSCLK settings: %d\n",
 			ret);
 		return ret;
@@ -272,7 +302,7 @@ static int arizona_apply_hardware_patch(struct arizona* arizona)
 	/* Start up SYSCLK using the FLL in free running mode */
 	ret = regmap_write(arizona->regmap, ARIZONA_FLL1_CONTROL_1,
 			ARIZONA_FLL1_ENA | ARIZONA_FLL1_FREERUN);
-	if (ret != 0) {
+	if (ret) {
 		dev_err(arizona->dev,
 			"Failed to start FLL in freerunning mode: %d\n",
 			ret);
@@ -281,53 +311,137 @@ static int arizona_apply_hardware_patch(struct arizona* arizona)
 	ret = arizona_poll_reg(arizona, 25, ARIZONA_INTERRUPT_RAW_STATUS_5,
 			       ARIZONA_FLL1_CLOCK_OK_STS,
 			       ARIZONA_FLL1_CLOCK_OK_STS);
-	if (ret != 0) {
+	if (ret) {
 		ret = -ETIMEDOUT;
 		goto err_fll;
 	}
 
 	ret = regmap_write(arizona->regmap, ARIZONA_SYSTEM_CLOCK_1, 0x0144);
-	if (ret != 0) {
+	if (ret) {
 		dev_err(arizona->dev, "Failed to start SYSCLK: %d\n", ret);
 		goto err_fll;
 	}
 
+	return 0;
+
+err_fll:
+	err = regmap_write(arizona->regmap, ARIZONA_FLL1_CONTROL_1, state->fll);
+	if (err)
+		dev_err(arizona->dev,
+			"Failed to re-apply old FLL settings: %d\n", err);
+
+	return ret;
+}
+
+static int arizona_disable_freerun_sysclk(struct arizona *arizona,
+					  struct arizona_sysclk_state *state)
+{
+	int ret;
+
+	ret = regmap_write(arizona->regmap, ARIZONA_SYSTEM_CLOCK_1,
+			   state->sysclk);
+	if (ret) {
+		dev_err(arizona->dev,
+			"Failed to re-apply old SYSCLK settings: %d\n", ret);
+		return ret;
+	}
+
+	ret = regmap_write(arizona->regmap, ARIZONA_FLL1_CONTROL_1, state->fll);
+	if (ret) {
+		dev_err(arizona->dev,
+			"Failed to re-apply old FLL settings: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int wm5102_apply_hardware_patch(struct arizona *arizona)
+{
+	struct arizona_sysclk_state state;
+	int err, ret;
+
+	ret = arizona_enable_freerun_sysclk(arizona, &state);
+	if (ret)
+		return ret;
+
 	/* Start the write sequencer and wait for it to finish */
 	ret = regmap_write(arizona->regmap, ARIZONA_WRITE_SEQUENCER_CTRL_0,
-			ARIZONA_WSEQ_ENA | ARIZONA_WSEQ_START | 160);
-	if (ret != 0) {
+			   ARIZONA_WSEQ_ENA | ARIZONA_WSEQ_START | 160);
+	if (ret) {
 		dev_err(arizona->dev, "Failed to start write sequencer: %d\n",
 			ret);
-		goto err_sysclk;
+		goto err;
 	}
+
 	ret = arizona_poll_reg(arizona, 5, ARIZONA_WRITE_SEQUENCER_CTRL_1,
 			       ARIZONA_WSEQ_BUSY, 0);
-	if (ret != 0) {
+	if (ret) {
 		regmap_write(arizona->regmap, ARIZONA_WRITE_SEQUENCER_CTRL_0,
-				ARIZONA_WSEQ_ABORT);
+			     ARIZONA_WSEQ_ABORT);
 		ret = -ETIMEDOUT;
 	}
 
-err_sysclk:
-	err = regmap_write(arizona->regmap, ARIZONA_SYSTEM_CLOCK_1, sysclk);
-	if (err != 0) {
-		dev_err(arizona->dev,
-			"Failed to re-apply old SYSCLK settings: %d\n",
-			err);
-	}
+err:
+	err = arizona_disable_freerun_sysclk(arizona, &state);
 
-err_fll:
-	err = regmap_write(arizona->regmap, ARIZONA_FLL1_CONTROL_1, fll);
-	if (err != 0) {
+	return ret ?: err;
+}
+
+/*
+ * Register patch to some of the CODECs internal write sequences
+ * to ensure a clean exit from the low power sleep state.
+ */
+static const struct reg_default wm5110_sleep_patch[] = {
+	{ 0x337A, 0xC100 },
+	{ 0x337B, 0x0041 },
+	{ 0x3300, 0xA210 },
+	{ 0x3301, 0x050C },
+};
+
+static int wm5110_apply_sleep_patch(struct arizona *arizona)
+{
+	struct arizona_sysclk_state state;
+	int err, ret;
+
+	ret = arizona_enable_freerun_sysclk(arizona, &state);
+	if (ret)
+		return ret;
+
+	ret = regmap_multi_reg_write_bypassed(arizona->regmap,
+					      wm5110_sleep_patch,
+					      ARRAY_SIZE(wm5110_sleep_patch));
+
+	err = arizona_disable_freerun_sysclk(arizona, &state);
+
+	return ret ?: err;
+}
+
+static int wm5102_clear_write_sequencer(struct arizona *arizona)
+{
+	int ret;
+
+	ret = regmap_write(arizona->regmap, ARIZONA_WRITE_SEQUENCER_CTRL_3,
+			   0x0);
+	if (ret) {
 		dev_err(arizona->dev,
-			"Failed to re-apply old FLL settings: %d\n",
-			err);
+			"Failed to clear write sequencer state: %d\n", ret);
+		return ret;
 	}
 
-	if (ret != 0)
+	arizona_enable_reset(arizona);
+	regulator_disable(arizona->dcvdd);
+
+	msleep(20);
+
+	ret = regulator_enable(arizona->dcvdd);
+	if (ret) {
+		dev_err(arizona->dev, "Failed to re-enable DCVDD: %d\n", ret);
 		return ret;
-	else
-		return err;
+	}
+	arizona_disable_reset(arizona);
+
+	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -338,12 +452,33 @@ static int arizona_runtime_resume(struct device *dev)
 
 	dev_dbg(arizona->dev, "Leaving AoD mode\n");
 
+	if (arizona->has_fully_powered_off) {
+		dev_dbg(arizona->dev, "Re-enabling core supplies\n");
+
+		ret = regulator_bulk_enable(arizona->num_core_supplies,
+					    arizona->core_supplies);
+		if (ret) {
+			dev_err(dev, "Failed to enable core supplies: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
 	ret = regulator_enable(arizona->dcvdd);
 	if (ret != 0) {
 		dev_err(arizona->dev, "Failed to enable DCVDD: %d\n", ret);
+		if (arizona->has_fully_powered_off)
+			regulator_bulk_disable(arizona->num_core_supplies,
+					       arizona->core_supplies);
 		return ret;
 	}
 
+	if (arizona->has_fully_powered_off) {
+		arizona_disable_reset(arizona);
+		enable_irq(arizona->irq);
+		arizona->has_fully_powered_off = false;
+	}
+
 	regcache_cache_only(arizona->regmap, false);
 
 	switch (arizona->type) {
@@ -366,14 +501,53 @@ static int arizona_runtime_resume(struct device *dev)
 			goto err;
 		}
 
-		ret = arizona_apply_hardware_patch(arizona);
-		if (ret != 0) {
+		ret = wm5102_apply_hardware_patch(arizona);
+		if (ret) {
 			dev_err(arizona->dev,
 				"Failed to apply hardware patch: %d\n",
 				ret);
 			goto err;
 		}
 		break;
+	case WM5110:
+	case WM8280:
+		ret = arizona_wait_for_boot(arizona);
+		if (ret)
+			goto err;
+
+		if (arizona->external_dcvdd) {
+			ret = regmap_update_bits(arizona->regmap,
+						 ARIZONA_ISOLATION_CONTROL,
+						 ARIZONA_ISOLATE_DCVDD1, 0);
+			if (ret) {
+				dev_err(arizona->dev,
+					"Failed to connect DCVDD: %d\n", ret);
+				goto err;
+			}
+		} else {
+			/*
+			 * As this is only called for the internal regulator
+			 * (where we know voltage ranges available) it is ok
+			 * to request an exact range.
+			 */
+			ret = regulator_set_voltage(arizona->dcvdd,
+						    1200000, 1200000);
+			if (ret < 0) {
+				dev_err(arizona->dev,
+					"Failed to set resume voltage: %d\n",
+					ret);
+				goto err;
+			}
+		}
+
+		ret = wm5110_apply_sleep_patch(arizona);
+		if (ret) {
+			dev_err(arizona->dev,
+				"Failed to re-apply sleep patch: %d\n",
+				ret);
+			goto err;
+		}
+		break;
 	default:
 		ret = arizona_wait_for_boot(arizona);
 		if (ret != 0) {
@@ -410,10 +584,17 @@ err:
 static int arizona_runtime_suspend(struct device *dev)
 {
 	struct arizona *arizona = dev_get_drvdata(dev);
+	unsigned int val;
 	int ret;
 
 	dev_dbg(arizona->dev, "Entering AoD mode\n");
 
+	ret = regmap_read(arizona->regmap, ARIZONA_JACK_DETECT_ANALOGUE, &val);
+	if (ret) {
+		dev_err(dev, "Failed to check jack det status: %d\n", ret);
+		return ret;
+	}
+
 	if (arizona->external_dcvdd) {
 		ret = regmap_update_bits(arizona->regmap,
 					 ARIZONA_ISOLATION_CONTROL,
@@ -426,10 +607,56 @@ static int arizona_runtime_suspend(struct device *dev)
 		}
 	}
 
+	switch (arizona->type) {
+	case WM5110:
+	case WM8280:
+		if (arizona->external_dcvdd)
+			break;
+
+		/*
+		 * As this is only called for the internal regulator
+		 * (where we know voltage ranges available) it is ok
+		 * to request an exact range.
+		 */
+		ret = regulator_set_voltage(arizona->dcvdd, 1175000, 1175000);
+		if (ret < 0) {
+			dev_err(arizona->dev,
+				"Failed to set suspend voltage: %d\n", ret);
+			return ret;
+		}
+		break;
+	case WM5102:
+		if (!(val & ARIZONA_JD1_ENA)) {
+			ret = regmap_write(arizona->regmap,
+					   ARIZONA_WRITE_SEQUENCER_CTRL_3, 0x0);
+			if (ret) {
+				dev_err(arizona->dev,
+					"Failed to clear write sequencer: %d\n",
+					ret);
+				return ret;
+			}
+		}
+		break;
+	default:
+		break;
+	}
+
 	regcache_cache_only(arizona->regmap, true);
 	regcache_mark_dirty(arizona->regmap);
 	regulator_disable(arizona->dcvdd);
 
+	/* Allow us to completely power down if no jack detection */
+	if (!(val & ARIZONA_JD1_ENA)) {
+		dev_dbg(arizona->dev, "Fully powering off\n");
+
+		arizona->has_fully_powered_off = true;
+
+		disable_irq(arizona->irq);
+		arizona_enable_reset(arizona);
+		regulator_bulk_disable(arizona->num_core_supplies,
+				       arizona->core_supplies);
+	}
+
 	return 0;
 }
 #endif
@@ -728,9 +955,9 @@ int arizona_dev_init(struct arizona *arizona)
 
 	if (arizona->pdata.reset) {
 		/* Start out with /RESET low to put the chip into reset */
-		ret = gpio_request_one(arizona->pdata.reset,
-				       GPIOF_DIR_OUT | GPIOF_INIT_LOW,
-				       "arizona /RESET");
+		ret = devm_gpio_request_one(arizona->dev, arizona->pdata.reset,
+					    GPIOF_DIR_OUT | GPIOF_INIT_LOW,
+					    "arizona /RESET");
 		if (ret != 0) {
 			dev_err(dev, "Failed to request /RESET: %d\n", ret);
 			goto err_dcvdd;
@@ -751,10 +978,7 @@ int arizona_dev_init(struct arizona *arizona)
 		goto err_enable;
 	}
 
-	if (arizona->pdata.reset) {
-		gpio_set_value_cansleep(arizona->pdata.reset, 1);
-		msleep(1);
-	}
+	arizona_disable_reset(arizona);
 
 	regcache_cache_only(arizona->regmap, false);
 
@@ -777,8 +1001,6 @@ int arizona_dev_init(struct arizona *arizona)
 
 	/* If we have a /RESET GPIO we'll already be reset */
 	if (!arizona->pdata.reset) {
-		regcache_mark_dirty(arizona->regmap);
-
 		ret = regmap_write(arizona->regmap, ARIZONA_SOFTWARE_RESET, 0);
 		if (ret != 0) {
 			dev_err(dev, "Failed to reset device: %d\n", ret);
@@ -786,12 +1008,6 @@ int arizona_dev_init(struct arizona *arizona)
 		}
 
 		msleep(1);
-
-		ret = regcache_sync(arizona->regmap);
-		if (ret != 0) {
-			dev_err(dev, "Failed to sync device: %d\n", ret);
-			goto err_reset;
-		}
 	}
 
 	/* Ensure device startup is complete */
@@ -799,21 +1015,24 @@ int arizona_dev_init(struct arizona *arizona)
 	case WM5102:
 		ret = regmap_read(arizona->regmap,
 				  ARIZONA_WRITE_SEQUENCER_CTRL_3, &val);
-		if (ret != 0)
+		if (ret) {
 			dev_err(dev,
 				"Failed to check write sequencer state: %d\n",
 				ret);
-		else if (val & 0x01)
-			break;
-		/* Fall through */
-	default:
-		ret = arizona_wait_for_boot(arizona);
-		if (ret != 0) {
-			dev_err(arizona->dev,
-				"Device failed initial boot: %d\n", ret);
-			goto err_reset;
+		} else if (val & 0x01) {
+			ret = wm5102_clear_write_sequencer(arizona);
+			if (ret)
+				return ret;
 		}
 		break;
+	default:
+		break;
+	}
+
+	ret = arizona_wait_for_boot(arizona);
+	if (ret) {
+		dev_err(arizona->dev, "Device failed initial boot: %d\n", ret);
+		goto err_reset;
 	}
 
 	/* Read the device ID information & do device specific stuff */
@@ -891,14 +1110,24 @@ int arizona_dev_init(struct arizona *arizona)
 
 		switch (arizona->type) {
 		case WM5102:
-			ret = arizona_apply_hardware_patch(arizona);
-			if (ret != 0) {
+			ret = wm5102_apply_hardware_patch(arizona);
+			if (ret) {
 				dev_err(arizona->dev,
 					"Failed to apply hardware patch: %d\n",
 					ret);
 				goto err_reset;
 			}
 			break;
+		case WM5110:
+		case WM8280:
+			ret = wm5110_apply_sleep_patch(arizona);
+			if (ret) {
+				dev_err(arizona->dev,
+					"Failed to apply sleep patch: %d\n",
+					ret);
+				goto err_reset;
+			}
+			break;
 		default:
 			break;
 		}
@@ -977,12 +1206,16 @@ int arizona_dev_init(struct arizona *arizona)
 		/* Default for both is 0 so noop with defaults */
 		val = arizona->pdata.dmic_ref[i]
 			<< ARIZONA_IN1_DMIC_SUP_SHIFT;
-		val |= arizona->pdata.inmode[i] << ARIZONA_IN1_MODE_SHIFT;
+		if (arizona->pdata.inmode[i] & ARIZONA_INMODE_DMIC)
+			val |= 1 << ARIZONA_IN1_MODE_SHIFT;
+		if (arizona->pdata.inmode[i] & ARIZONA_INMODE_SE)
+			val |= 1 << ARIZONA_IN1_SINGLE_ENDED_SHIFT;
 
 		regmap_update_bits(arizona->regmap,
 				   ARIZONA_IN1L_CONTROL + (i * 8),
 				   ARIZONA_IN1_DMIC_SUP_MASK |
-				   ARIZONA_IN1_MODE_MASK, val);
+				   ARIZONA_IN1_MODE_MASK |
+				   ARIZONA_IN1_SINGLE_ENDED_MASK, val);
 	}
 
 	for (i = 0; i < ARIZONA_MAX_OUTPUT; i++) {
@@ -1054,10 +1287,7 @@ int arizona_dev_init(struct arizona *arizona)
 err_irq:
 	arizona_irq_exit(arizona);
 err_reset:
-	if (arizona->pdata.reset) {
-		gpio_set_value_cansleep(arizona->pdata.reset, 0);
-		gpio_free(arizona->pdata.reset);
-	}
+	arizona_enable_reset(arizona);
 	regulator_disable(arizona->dcvdd);
 err_enable:
 	regulator_bulk_disable(arizona->num_core_supplies,
@@ -1082,8 +1312,7 @@ int arizona_dev_exit(struct arizona *arizona)
 	arizona_free_irq(arizona, ARIZONA_IRQ_OVERCLOCKED, arizona);
 	arizona_free_irq(arizona, ARIZONA_IRQ_CLKGEN_ERR, arizona);
 	arizona_irq_exit(arizona);
-	if (arizona->pdata.reset)
-		gpio_set_value_cansleep(arizona->pdata.reset, 0);
+	arizona_enable_reset(arizona);
 
 	regulator_bulk_disable(arizona->num_core_supplies,
 			       arizona->core_supplies);
diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c
index d063b94b94b5..2b9965d53e4e 100644
--- a/drivers/mfd/arizona-irq.c
+++ b/drivers/mfd/arizona-irq.c
@@ -186,7 +186,7 @@ static int arizona_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops arizona_domain_ops = {
+static const struct irq_domain_ops arizona_domain_ops = {
 	.map	= arizona_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index d18029be6a78..6df91556faf3 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -32,6 +32,7 @@
 static const char * const axp20x_model_names[] = {
 	"AXP202",
 	"AXP209",
+	"AXP221",
 	"AXP288",
 };
 
@@ -54,6 +55,25 @@ static const struct regmap_access_table axp20x_volatile_table = {
 	.n_yes_ranges	= ARRAY_SIZE(axp20x_volatile_ranges),
 };
 
+static const struct regmap_range axp22x_writeable_ranges[] = {
+	regmap_reg_range(AXP20X_DATACACHE(0), AXP20X_IRQ5_STATE),
+	regmap_reg_range(AXP20X_DCDC_MODE, AXP22X_BATLOW_THRES1),
+};
+
+static const struct regmap_range axp22x_volatile_ranges[] = {
+	regmap_reg_range(AXP20X_IRQ1_EN, AXP20X_IRQ5_STATE),
+};
+
+static const struct regmap_access_table axp22x_writeable_table = {
+	.yes_ranges	= axp22x_writeable_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(axp22x_writeable_ranges),
+};
+
+static const struct regmap_access_table axp22x_volatile_table = {
+	.yes_ranges	= axp22x_volatile_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(axp22x_volatile_ranges),
+};
+
 static const struct regmap_range axp288_writeable_ranges[] = {
 	regmap_reg_range(AXP20X_DATACACHE(0), AXP20X_IRQ6_STATE),
 	regmap_reg_range(AXP20X_DCDC_MODE, AXP288_FG_TUNE5),
@@ -87,6 +107,20 @@ static struct resource axp20x_pek_resources[] = {
 	},
 };
 
+static struct resource axp22x_pek_resources[] = {
+	{
+		.name   = "PEK_DBR",
+		.start  = AXP22X_IRQ_PEK_RIS_EDGE,
+		.end    = AXP22X_IRQ_PEK_RIS_EDGE,
+		.flags  = IORESOURCE_IRQ,
+	}, {
+		.name   = "PEK_DBF",
+		.start  = AXP22X_IRQ_PEK_FAL_EDGE,
+		.end    = AXP22X_IRQ_PEK_FAL_EDGE,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
 static struct resource axp288_fuel_gauge_resources[] = {
 	{
 		.start = AXP288_IRQ_QWBTU,
@@ -129,6 +163,15 @@ static const struct regmap_config axp20x_regmap_config = {
 	.cache_type	= REGCACHE_RBTREE,
 };
 
+static const struct regmap_config axp22x_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.wr_table	= &axp22x_writeable_table,
+	.volatile_table	= &axp22x_volatile_table,
+	.max_register	= AXP22X_BATLOW_THRES1,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
 static const struct regmap_config axp288_regmap_config = {
 	.reg_bits	= 8,
 	.val_bits	= 8,
@@ -181,6 +224,34 @@ static const struct regmap_irq axp20x_regmap_irqs[] = {
 	INIT_REGMAP_IRQ(AXP20X, GPIO0_INPUT,		4, 0),
 };
 
+static const struct regmap_irq axp22x_regmap_irqs[] = {
+	INIT_REGMAP_IRQ(AXP22X, ACIN_OVER_V,		0, 7),
+	INIT_REGMAP_IRQ(AXP22X, ACIN_PLUGIN,		0, 6),
+	INIT_REGMAP_IRQ(AXP22X, ACIN_REMOVAL,	        0, 5),
+	INIT_REGMAP_IRQ(AXP22X, VBUS_OVER_V,		0, 4),
+	INIT_REGMAP_IRQ(AXP22X, VBUS_PLUGIN,		0, 3),
+	INIT_REGMAP_IRQ(AXP22X, VBUS_REMOVAL,	        0, 2),
+	INIT_REGMAP_IRQ(AXP22X, VBUS_V_LOW,		0, 1),
+	INIT_REGMAP_IRQ(AXP22X, BATT_PLUGIN,		1, 7),
+	INIT_REGMAP_IRQ(AXP22X, BATT_REMOVAL,	        1, 6),
+	INIT_REGMAP_IRQ(AXP22X, BATT_ENT_ACT_MODE,	1, 5),
+	INIT_REGMAP_IRQ(AXP22X, BATT_EXIT_ACT_MODE,	1, 4),
+	INIT_REGMAP_IRQ(AXP22X, CHARG,		        1, 3),
+	INIT_REGMAP_IRQ(AXP22X, CHARG_DONE,		1, 2),
+	INIT_REGMAP_IRQ(AXP22X, BATT_TEMP_HIGH,	        1, 1),
+	INIT_REGMAP_IRQ(AXP22X, BATT_TEMP_LOW,	        1, 0),
+	INIT_REGMAP_IRQ(AXP22X, DIE_TEMP_HIGH,	        2, 7),
+	INIT_REGMAP_IRQ(AXP22X, PEK_SHORT,		2, 1),
+	INIT_REGMAP_IRQ(AXP22X, PEK_LONG,		2, 0),
+	INIT_REGMAP_IRQ(AXP22X, LOW_PWR_LVL1,	        3, 1),
+	INIT_REGMAP_IRQ(AXP22X, LOW_PWR_LVL2,	        3, 0),
+	INIT_REGMAP_IRQ(AXP22X, TIMER,		        4, 7),
+	INIT_REGMAP_IRQ(AXP22X, PEK_RIS_EDGE,	        4, 6),
+	INIT_REGMAP_IRQ(AXP22X, PEK_FAL_EDGE,	        4, 5),
+	INIT_REGMAP_IRQ(AXP22X, GPIO1_INPUT,		4, 1),
+	INIT_REGMAP_IRQ(AXP22X, GPIO0_INPUT,		4, 0),
+};
+
 /* some IRQs are compatible with axp20x models */
 static const struct regmap_irq axp288_regmap_irqs[] = {
 	INIT_REGMAP_IRQ(AXP288, VBUS_FALL,              0, 2),
@@ -224,6 +295,7 @@ static const struct regmap_irq axp288_regmap_irqs[] = {
 static const struct of_device_id axp20x_of_match[] = {
 	{ .compatible = "x-powers,axp202", .data = (void *) AXP202_ID },
 	{ .compatible = "x-powers,axp209", .data = (void *) AXP209_ID },
+	{ .compatible = "x-powers,axp221", .data = (void *) AXP221_ID },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, axp20x_of_match);
@@ -258,6 +330,18 @@ static const struct regmap_irq_chip axp20x_regmap_irq_chip = {
 
 };
 
+static const struct regmap_irq_chip axp22x_regmap_irq_chip = {
+	.name			= "axp22x_irq_chip",
+	.status_base		= AXP20X_IRQ1_STATE,
+	.ack_base		= AXP20X_IRQ1_STATE,
+	.mask_base		= AXP20X_IRQ1_EN,
+	.mask_invert		= true,
+	.init_ack_masked	= true,
+	.irqs			= axp22x_regmap_irqs,
+	.num_irqs		= ARRAY_SIZE(axp22x_regmap_irqs),
+	.num_regs		= 5,
+};
+
 static const struct regmap_irq_chip axp288_regmap_irq_chip = {
 	.name			= "axp288_irq_chip",
 	.status_base		= AXP20X_IRQ1_STATE,
@@ -281,6 +365,16 @@ static struct mfd_cell axp20x_cells[] = {
 	},
 };
 
+static struct mfd_cell axp22x_cells[] = {
+	{
+		.name			= "axp20x-pek",
+		.num_resources		= ARRAY_SIZE(axp22x_pek_resources),
+		.resources		= axp22x_pek_resources,
+	}, {
+		.name			= "axp20x-regulator",
+	},
+};
+
 static struct resource axp288_adc_resources[] = {
 	{
 		.name  = "GPADC",
@@ -426,6 +520,12 @@ static int axp20x_match_device(struct axp20x_dev *axp20x, struct device *dev)
 		axp20x->regmap_cfg = &axp20x_regmap_config;
 		axp20x->regmap_irq_chip = &axp20x_regmap_irq_chip;
 		break;
+	case AXP221_ID:
+		axp20x->nr_cells = ARRAY_SIZE(axp22x_cells);
+		axp20x->cells = axp22x_cells;
+		axp20x->regmap_cfg = &axp22x_regmap_config;
+		axp20x->regmap_irq_chip = &axp22x_regmap_irq_chip;
+		break;
 	case AXP288_ID:
 		axp20x->cells = axp288_cells;
 		axp20x->nr_cells = ARRAY_SIZE(axp288_cells);
diff --git a/drivers/mfd/cros_ec.c b/drivers/mfd/cros_ec.c
index c4aecc6f8373..0eee63542038 100644
--- a/drivers/mfd/cros_ec.c
+++ b/drivers/mfd/cros_ec.c
@@ -17,111 +17,36 @@
  * battery charging and regulator control, firmware update.
  */
 
+#include <linux/of_platform.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/cros_ec.h>
-#include <linux/mfd/cros_ec_commands.h>
-#include <linux/delay.h>
 
-#define EC_COMMAND_RETRIES	50
+#define CROS_EC_DEV_EC_INDEX 0
+#define CROS_EC_DEV_PD_INDEX 1
 
-int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
-		       struct cros_ec_command *msg)
-{
-	uint8_t *out;
-	int csum, i;
-
-	BUG_ON(msg->outsize > EC_PROTO2_MAX_PARAM_SIZE);
-	out = ec_dev->dout;
-	out[0] = EC_CMD_VERSION0 + msg->version;
-	out[1] = msg->command;
-	out[2] = msg->outsize;
-	csum = out[0] + out[1] + out[2];
-	for (i = 0; i < msg->outsize; i++)
-		csum += out[EC_MSG_TX_HEADER_BYTES + i] = msg->outdata[i];
-	out[EC_MSG_TX_HEADER_BYTES + msg->outsize] = (uint8_t)(csum & 0xff);
-
-	return EC_MSG_TX_PROTO_BYTES + msg->outsize;
-}
-EXPORT_SYMBOL(cros_ec_prepare_tx);
-
-int cros_ec_check_result(struct cros_ec_device *ec_dev,
-			 struct cros_ec_command *msg)
-{
-	switch (msg->result) {
-	case EC_RES_SUCCESS:
-		return 0;
-	case EC_RES_IN_PROGRESS:
-		dev_dbg(ec_dev->dev, "command 0x%02x in progress\n",
-			msg->command);
-		return -EAGAIN;
-	default:
-		dev_dbg(ec_dev->dev, "command 0x%02x returned %d\n",
-			msg->command, msg->result);
-		return 0;
-	}
-}
-EXPORT_SYMBOL(cros_ec_check_result);
-
-int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
-		     struct cros_ec_command *msg)
-{
-	int ret;
-
-	mutex_lock(&ec_dev->lock);
-	ret = ec_dev->cmd_xfer(ec_dev, msg);
-	if (msg->result == EC_RES_IN_PROGRESS) {
-		int i;
-		struct cros_ec_command status_msg = { };
-		struct ec_response_get_comms_status *status;
-
-		status_msg.command = EC_CMD_GET_COMMS_STATUS;
-		status_msg.insize = sizeof(*status);
-
-		/*
-		 * Query the EC's status until it's no longer busy or
-		 * we encounter an error.
-		 */
-		for (i = 0; i < EC_COMMAND_RETRIES; i++) {
-			usleep_range(10000, 11000);
-
-			ret = ec_dev->cmd_xfer(ec_dev, &status_msg);
-			if (ret < 0)
-				break;
+static struct cros_ec_platform ec_p = {
+	.ec_name = CROS_EC_DEV_NAME,
+	.cmd_offset = EC_CMD_PASSTHRU_OFFSET(CROS_EC_DEV_EC_INDEX),
+};
 
-			msg->result = status_msg.result;
-			if (status_msg.result != EC_RES_SUCCESS)
-				break;
+static struct cros_ec_platform pd_p = {
+	.ec_name = CROS_EC_DEV_PD_NAME,
+	.cmd_offset = EC_CMD_PASSTHRU_OFFSET(CROS_EC_DEV_PD_INDEX),
+};
 
-			status = (struct ec_response_get_comms_status *)
-				 status_msg.indata;
-			if (!(status->flags & EC_COMMS_STATUS_PROCESSING))
-				break;
-		}
-	}
-	mutex_unlock(&ec_dev->lock);
+static const struct mfd_cell ec_cell = {
+	.name = "cros-ec-ctl",
+	.platform_data = &ec_p,
+	.pdata_size = sizeof(ec_p),
+};
 
-	return ret;
-}
-EXPORT_SYMBOL(cros_ec_cmd_xfer);
-
-static const struct mfd_cell cros_devs[] = {
-	{
-		.name = "cros-ec-keyb",
-		.id = 1,
-		.of_compatible = "google,cros-ec-keyb",
-	},
-	{
-		.name = "cros-ec-i2c-tunnel",
-		.id = 2,
-		.of_compatible = "google,cros-ec-i2c-tunnel",
-	},
-	{
-		.name = "cros-ec-ctl",
-		.id = 3,
-	},
+static const struct mfd_cell ec_pd_cell = {
+	.name = "cros-ec-ctl",
+	.platform_data = &pd_p,
+	.pdata_size = sizeof(pd_p),
 };
 
 int cros_ec_register(struct cros_ec_device *ec_dev)
@@ -129,27 +54,59 @@ int cros_ec_register(struct cros_ec_device *ec_dev)
 	struct device *dev = ec_dev->dev;
 	int err = 0;
 
-	if (ec_dev->din_size) {
-		ec_dev->din = devm_kzalloc(dev, ec_dev->din_size, GFP_KERNEL);
-		if (!ec_dev->din)
-			return -ENOMEM;
-	}
-	if (ec_dev->dout_size) {
-		ec_dev->dout = devm_kzalloc(dev, ec_dev->dout_size, GFP_KERNEL);
-		if (!ec_dev->dout)
-			return -ENOMEM;
-	}
+	ec_dev->max_request = sizeof(struct ec_params_hello);
+	ec_dev->max_response = sizeof(struct ec_response_get_protocol_info);
+	ec_dev->max_passthru = 0;
+
+	ec_dev->din = devm_kzalloc(dev, ec_dev->din_size, GFP_KERNEL);
+	if (!ec_dev->din)
+		return -ENOMEM;
+
+	ec_dev->dout = devm_kzalloc(dev, ec_dev->dout_size, GFP_KERNEL);
+	if (!ec_dev->dout)
+		return -ENOMEM;
 
 	mutex_init(&ec_dev->lock);
 
-	err = mfd_add_devices(dev, 0, cros_devs,
-			      ARRAY_SIZE(cros_devs),
+	cros_ec_query_all(ec_dev);
+
+	err = mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO, &ec_cell, 1,
 			      NULL, ec_dev->irq, NULL);
 	if (err) {
-		dev_err(dev, "failed to add mfd devices\n");
+		dev_err(dev,
+			"Failed to register Embedded Controller subdevice %d\n",
+			err);
 		return err;
 	}
 
+	if (ec_dev->max_passthru) {
+		/*
+		 * Register a PD device as well on top of this device.
+		 * We make the following assumptions:
+		 * - behind an EC, we have a pd
+		 * - only one device added.
+		 * - the EC is responsive at init time (it is not true for a
+		 *   sensor hub.
+		 */
+		err = mfd_add_devices(ec_dev->dev, PLATFORM_DEVID_AUTO,
+				      &ec_pd_cell, 1, NULL, ec_dev->irq, NULL);
+		if (err) {
+			dev_err(dev,
+				"Failed to register Power Delivery subdevice %d\n",
+				err);
+			return err;
+		}
+	}
+
+	if (IS_ENABLED(CONFIG_OF) && dev->of_node) {
+		err = of_platform_populate(dev->of_node, NULL, NULL, dev);
+		if (err) {
+			mfd_remove_devices(dev);
+			dev_err(dev, "Failed to register sub-devices\n");
+			return err;
+		}
+	}
+
 	dev_info(dev, "Chrome EC device registered\n");
 
 	return 0;
diff --git a/drivers/mfd/cros_ec_i2c.c b/drivers/mfd/cros_ec_i2c.c
index c0c30f4f946f..b9a0963ca5c3 100644
--- a/drivers/mfd/cros_ec_i2c.c
+++ b/drivers/mfd/cros_ec_i2c.c
@@ -13,6 +13,7 @@
  * GNU General Public License for more details.
  */
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/i2c.h>
@@ -22,6 +23,32 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+/**
+ * Request format for protocol v3
+ * byte 0	0xda (EC_COMMAND_PROTOCOL_3)
+ * byte 1-8	struct ec_host_request
+ * byte 10-	response data
+ */
+struct ec_host_request_i2c {
+	/* Always 0xda to backward compatible with v2 struct */
+	uint8_t  command_protocol;
+	struct ec_host_request ec_request;
+} __packed;
+
+
+/*
+ * Response format for protocol v3
+ * byte 0	result code
+ * byte 1	packet_length
+ * byte 2-9	struct ec_host_response
+ * byte 10-	response data
+ */
+struct ec_host_response_i2c {
+	uint8_t result;
+	uint8_t packet_length;
+	struct ec_host_response ec_response;
+} __packed;
+
 static inline struct cros_ec_device *to_ec_dev(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -29,6 +56,134 @@ static inline struct cros_ec_device *to_ec_dev(struct device *dev)
 	return i2c_get_clientdata(client);
 }
 
+static int cros_ec_pkt_xfer_i2c(struct cros_ec_device *ec_dev,
+				struct cros_ec_command *msg)
+{
+	struct i2c_client *client = ec_dev->priv;
+	int ret = -ENOMEM;
+	int i;
+	int packet_len;
+	u8 *out_buf = NULL;
+	u8 *in_buf = NULL;
+	u8 sum;
+	struct i2c_msg i2c_msg[2];
+	struct ec_host_response *ec_response;
+	struct ec_host_request_i2c *ec_request_i2c;
+	struct ec_host_response_i2c *ec_response_i2c;
+	int request_header_size = sizeof(struct ec_host_request_i2c);
+	int response_header_size = sizeof(struct ec_host_response_i2c);
+
+	i2c_msg[0].addr = client->addr;
+	i2c_msg[0].flags = 0;
+	i2c_msg[1].addr = client->addr;
+	i2c_msg[1].flags = I2C_M_RD;
+
+	packet_len = msg->insize + response_header_size;
+	BUG_ON(packet_len > ec_dev->din_size);
+	in_buf = ec_dev->din;
+	i2c_msg[1].len = packet_len;
+	i2c_msg[1].buf = (char *) in_buf;
+
+	packet_len = msg->outsize + request_header_size;
+	BUG_ON(packet_len > ec_dev->dout_size);
+	out_buf = ec_dev->dout;
+	i2c_msg[0].len = packet_len;
+	i2c_msg[0].buf = (char *) out_buf;
+
+	/* create request data */
+	ec_request_i2c = (struct ec_host_request_i2c *) out_buf;
+	ec_request_i2c->command_protocol = EC_COMMAND_PROTOCOL_3;
+
+	ec_dev->dout++;
+	ret = cros_ec_prepare_tx(ec_dev, msg);
+	ec_dev->dout--;
+
+	/* send command to EC and read answer */
+	ret = i2c_transfer(client->adapter, i2c_msg, 2);
+	if (ret < 0) {
+		dev_dbg(ec_dev->dev, "i2c transfer failed: %d\n", ret);
+		goto done;
+	} else if (ret != 2) {
+		dev_err(ec_dev->dev, "failed to get response: %d\n", ret);
+		ret = -EIO;
+		goto done;
+	}
+
+	ec_response_i2c = (struct ec_host_response_i2c *) in_buf;
+	msg->result = ec_response_i2c->result;
+	ec_response = &ec_response_i2c->ec_response;
+
+	switch (msg->result) {
+	case EC_RES_SUCCESS:
+		break;
+	case EC_RES_IN_PROGRESS:
+		ret = -EAGAIN;
+		dev_dbg(ec_dev->dev, "command 0x%02x in progress\n",
+			msg->command);
+		goto done;
+
+	default:
+		dev_dbg(ec_dev->dev, "command 0x%02x returned %d\n",
+			msg->command, msg->result);
+		/*
+		 * When we send v3 request to v2 ec, ec won't recognize the
+		 * 0xda (EC_COMMAND_PROTOCOL_3) and will return with status
+		 * EC_RES_INVALID_COMMAND with zero data length.
+		 *
+		 * In case of invalid command for v3 protocol the data length
+		 * will be at least sizeof(struct ec_host_response)
+		 */
+		if (ec_response_i2c->result == EC_RES_INVALID_COMMAND &&
+		    ec_response_i2c->packet_length == 0) {
+			ret = -EPROTONOSUPPORT;
+			goto done;
+		}
+	}
+
+	if (ec_response_i2c->packet_length < sizeof(struct ec_host_response)) {
+		dev_err(ec_dev->dev,
+			"response of %u bytes too short; not a full header\n",
+			ec_response_i2c->packet_length);
+		ret = -EBADMSG;
+		goto done;
+	}
+
+	if (msg->insize < ec_response->data_len) {
+		dev_err(ec_dev->dev,
+			"response data size is too large: expected %u, got %u\n",
+			msg->insize,
+			ec_response->data_len);
+		ret = -EMSGSIZE;
+		goto done;
+	}
+
+	/* copy response packet payload and compute checksum */
+	sum = 0;
+	for (i = 0; i < sizeof(struct ec_host_response); i++)
+		sum += ((u8 *)ec_response)[i];
+
+	memcpy(msg->data,
+	       in_buf + response_header_size,
+	       ec_response->data_len);
+	for (i = 0; i < ec_response->data_len; i++)
+		sum += msg->data[i];
+
+	/* All bytes should sum to zero */
+	if (sum) {
+		dev_err(ec_dev->dev, "bad packet checksum\n");
+		ret = -EBADMSG;
+		goto done;
+	}
+
+	ret = ec_response->data_len;
+
+done:
+	if (msg->command == EC_CMD_REBOOT_EC)
+		msleep(EC_REBOOT_DELAY_MS);
+
+	return ret;
+}
+
 static int cros_ec_cmd_xfer_i2c(struct cros_ec_device *ec_dev,
 				struct cros_ec_command *msg)
 {
@@ -76,7 +231,7 @@ static int cros_ec_cmd_xfer_i2c(struct cros_ec_device *ec_dev,
 	/* copy message payload and compute checksum */
 	sum = out_buf[0] + out_buf[1] + out_buf[2];
 	for (i = 0; i < msg->outsize; i++) {
-		out_buf[3 + i] = msg->outdata[i];
+		out_buf[3 + i] = msg->data[i];
 		sum += out_buf[3 + i];
 	}
 	out_buf[3 + msg->outsize] = sum;
@@ -109,7 +264,7 @@ static int cros_ec_cmd_xfer_i2c(struct cros_ec_device *ec_dev,
 	/* copy response packet payload and compute checksum */
 	sum = in_buf[0] + in_buf[1];
 	for (i = 0; i < len; i++) {
-		msg->indata[i] = in_buf[2 + i];
+		msg->data[i] = in_buf[2 + i];
 		sum += in_buf[2 + i];
 	}
 	dev_dbg(ec_dev->dev, "packet: %*ph, sum = %02x\n",
@@ -121,9 +276,12 @@ static int cros_ec_cmd_xfer_i2c(struct cros_ec_device *ec_dev,
 	}
 
 	ret = len;
- done:
+done:
 	kfree(in_buf);
 	kfree(out_buf);
+	if (msg->command == EC_CMD_REBOOT_EC)
+		msleep(EC_REBOOT_DELAY_MS);
+
 	return ret;
 }
 
@@ -143,9 +301,11 @@ static int cros_ec_i2c_probe(struct i2c_client *client,
 	ec_dev->priv = client;
 	ec_dev->irq = client->irq;
 	ec_dev->cmd_xfer = cros_ec_cmd_xfer_i2c;
-	ec_dev->ec_name = client->name;
+	ec_dev->pkt_xfer = cros_ec_pkt_xfer_i2c;
 	ec_dev->phys_name = client->adapter->name;
-	ec_dev->parent = &client->dev;
+	ec_dev->din_size = sizeof(struct ec_host_response_i2c) +
+			   sizeof(struct ec_response_get_protocol_info);
+	ec_dev->dout_size = sizeof(struct ec_host_request_i2c);
 
 	err = cros_ec_register(ec_dev);
 	if (err) {
diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c
index bf6e08e8013e..16f228dc243f 100644
--- a/drivers/mfd/cros_ec_spi.c
+++ b/drivers/mfd/cros_ec_spi.c
@@ -65,29 +65,26 @@
   */
 #define EC_SPI_RECOVERY_TIME_NS	(200 * 1000)
 
-/*
- * The EC is unresponsive for a time after a reboot command.  Add a
- * simple delay to make sure that the bus stays locked.
- */
-#define EC_REBOOT_DELAY_MS	50
-
 /**
  * struct cros_ec_spi - information about a SPI-connected EC
  *
  * @spi: SPI device we are connected to
  * @last_transfer_ns: time that we last finished a transfer, or 0 if there
  *	if no record
+ * @start_of_msg_delay: used to set the delay_usecs on the spi_transfer that
+ *      is sent when we want to turn on CS at the start of a transaction.
  * @end_of_msg_delay: used to set the delay_usecs on the spi_transfer that
  *      is sent when we want to turn off CS at the end of a transaction.
  */
 struct cros_ec_spi {
 	struct spi_device *spi;
 	s64 last_transfer_ns;
+	unsigned int start_of_msg_delay;
 	unsigned int end_of_msg_delay;
 };
 
 static void debug_packet(struct device *dev, const char *name, u8 *ptr,
-			  int len)
+			 int len)
 {
 #ifdef DEBUG
 	int i;
@@ -100,6 +97,172 @@ static void debug_packet(struct device *dev, const char *name, u8 *ptr,
 #endif
 }
 
+static int terminate_request(struct cros_ec_device *ec_dev)
+{
+	struct cros_ec_spi *ec_spi = ec_dev->priv;
+	struct spi_message msg;
+	struct spi_transfer trans;
+	int ret;
+
+	/*
+	 * Turn off CS, possibly adding a delay to ensure the rising edge
+	 * doesn't come too soon after the end of the data.
+	 */
+	spi_message_init(&msg);
+	memset(&trans, 0, sizeof(trans));
+	trans.delay_usecs = ec_spi->end_of_msg_delay;
+	spi_message_add_tail(&trans, &msg);
+
+	ret = spi_sync(ec_spi->spi, &msg);
+
+	/* Reset end-of-response timer */
+	ec_spi->last_transfer_ns = ktime_get_ns();
+	if (ret < 0) {
+		dev_err(ec_dev->dev,
+			"cs-deassert spi transfer failed: %d\n",
+			ret);
+	}
+
+	return ret;
+}
+
+/**
+ * receive_n_bytes - receive n bytes from the EC.
+ *
+ * Assumes buf is a pointer into the ec_dev->din buffer
+ */
+static int receive_n_bytes(struct cros_ec_device *ec_dev, u8 *buf, int n)
+{
+	struct cros_ec_spi *ec_spi = ec_dev->priv;
+	struct spi_transfer trans;
+	struct spi_message msg;
+	int ret;
+
+	BUG_ON(buf - ec_dev->din + n > ec_dev->din_size);
+
+	memset(&trans, 0, sizeof(trans));
+	trans.cs_change = 1;
+	trans.rx_buf = buf;
+	trans.len = n;
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&trans, &msg);
+	ret = spi_sync(ec_spi->spi, &msg);
+	if (ret < 0)
+		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
+
+	return ret;
+}
+
+/**
+ * cros_ec_spi_receive_packet - Receive a packet from the EC.
+ *
+ * This function has two phases: reading the preamble bytes (since if we read
+ * data from the EC before it is ready to send, we just get preamble) and
+ * reading the actual message.
+ *
+ * The received data is placed into ec_dev->din.
+ *
+ * @ec_dev: ChromeOS EC device
+ * @need_len: Number of message bytes we need to read
+ */
+static int cros_ec_spi_receive_packet(struct cros_ec_device *ec_dev,
+				      int need_len)
+{
+	struct ec_host_response *response;
+	u8 *ptr, *end;
+	int ret;
+	unsigned long deadline;
+	int todo;
+
+	BUG_ON(EC_MSG_PREAMBLE_COUNT > ec_dev->din_size);
+
+	/* Receive data until we see the header byte */
+	deadline = jiffies + msecs_to_jiffies(EC_MSG_DEADLINE_MS);
+	while (true) {
+		unsigned long start_jiffies = jiffies;
+
+		ret = receive_n_bytes(ec_dev,
+				      ec_dev->din,
+				      EC_MSG_PREAMBLE_COUNT);
+		if (ret < 0)
+			return ret;
+
+		ptr = ec_dev->din;
+		for (end = ptr + EC_MSG_PREAMBLE_COUNT; ptr != end; ptr++) {
+			if (*ptr == EC_SPI_FRAME_START) {
+				dev_dbg(ec_dev->dev, "msg found at %zd\n",
+					ptr - ec_dev->din);
+				break;
+			}
+		}
+		if (ptr != end)
+			break;
+
+		/*
+		 * Use the time at the start of the loop as a timeout.  This
+		 * gives us one last shot at getting the transfer and is useful
+		 * in case we got context switched out for a while.
+		 */
+		if (time_after(start_jiffies, deadline)) {
+			dev_warn(ec_dev->dev, "EC failed to respond in time\n");
+			return -ETIMEDOUT;
+		}
+	}
+
+	/*
+	 * ptr now points to the header byte. Copy any valid data to the
+	 * start of our buffer
+	 */
+	todo = end - ++ptr;
+	BUG_ON(todo < 0 || todo > ec_dev->din_size);
+	todo = min(todo, need_len);
+	memmove(ec_dev->din, ptr, todo);
+	ptr = ec_dev->din + todo;
+	dev_dbg(ec_dev->dev, "need %d, got %d bytes from preamble\n",
+		need_len, todo);
+	need_len -= todo;
+
+	/* If the entire response struct wasn't read, get the rest of it. */
+	if (todo < sizeof(*response)) {
+		ret = receive_n_bytes(ec_dev, ptr, sizeof(*response) - todo);
+		if (ret < 0)
+			return -EBADMSG;
+		ptr += (sizeof(*response) - todo);
+		todo = sizeof(*response);
+	}
+
+	response = (struct ec_host_response *)ec_dev->din;
+
+	/* Abort if data_len is too large. */
+	if (response->data_len > ec_dev->din_size)
+		return -EMSGSIZE;
+
+	/* Receive data until we have it all */
+	while (need_len > 0) {
+		/*
+		 * We can't support transfers larger than the SPI FIFO size
+		 * unless we have DMA. We don't have DMA on the ISP SPI ports
+		 * for Exynos. We need a way of asking SPI driver for
+		 * maximum-supported transfer size.
+		 */
+		todo = min(need_len, 256);
+		dev_dbg(ec_dev->dev, "loop, todo=%d, need_len=%d, ptr=%zd\n",
+			todo, need_len, ptr - ec_dev->din);
+
+		ret = receive_n_bytes(ec_dev, ptr, todo);
+		if (ret < 0)
+			return ret;
+
+		ptr += todo;
+		need_len -= todo;
+	}
+
+	dev_dbg(ec_dev->dev, "loop done, ptr=%zd\n", ptr - ec_dev->din);
+
+	return 0;
+}
+
 /**
  * cros_ec_spi_receive_response - Receive a response from the EC.
  *
@@ -115,34 +278,27 @@ static void debug_packet(struct device *dev, const char *name, u8 *ptr,
 static int cros_ec_spi_receive_response(struct cros_ec_device *ec_dev,
 					int need_len)
 {
-	struct cros_ec_spi *ec_spi = ec_dev->priv;
-	struct spi_transfer trans;
-	struct spi_message msg;
 	u8 *ptr, *end;
 	int ret;
 	unsigned long deadline;
 	int todo;
 
+	BUG_ON(EC_MSG_PREAMBLE_COUNT > ec_dev->din_size);
+
 	/* Receive data until we see the header byte */
 	deadline = jiffies + msecs_to_jiffies(EC_MSG_DEADLINE_MS);
 	while (true) {
 		unsigned long start_jiffies = jiffies;
 
-		memset(&trans, 0, sizeof(trans));
-		trans.cs_change = 1;
-		trans.rx_buf = ptr = ec_dev->din;
-		trans.len = EC_MSG_PREAMBLE_COUNT;
-
-		spi_message_init(&msg);
-		spi_message_add_tail(&trans, &msg);
-		ret = spi_sync(ec_spi->spi, &msg);
-		if (ret < 0) {
-			dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
+		ret = receive_n_bytes(ec_dev,
+				      ec_dev->din,
+				      EC_MSG_PREAMBLE_COUNT);
+		if (ret < 0)
 			return ret;
-		}
 
+		ptr = ec_dev->din;
 		for (end = ptr + EC_MSG_PREAMBLE_COUNT; ptr != end; ptr++) {
-			if (*ptr == EC_MSG_HEADER) {
+			if (*ptr == EC_SPI_FRAME_START) {
 				dev_dbg(ec_dev->dev, "msg found at %zd\n",
 					ptr - ec_dev->din);
 				break;
@@ -187,21 +343,9 @@ static int cros_ec_spi_receive_response(struct cros_ec_device *ec_dev,
 		dev_dbg(ec_dev->dev, "loop, todo=%d, need_len=%d, ptr=%zd\n",
 			todo, need_len, ptr - ec_dev->din);
 
-		memset(&trans, 0, sizeof(trans));
-		trans.cs_change = 1;
-		trans.rx_buf = ptr;
-		trans.len = todo;
-		spi_message_init(&msg);
-		spi_message_add_tail(&trans, &msg);
-
-		/* send command to EC and read answer */
-		BUG_ON((u8 *)trans.rx_buf - ec_dev->din + todo >
-				ec_dev->din_size);
-		ret = spi_sync(ec_spi->spi, &msg);
-		if (ret < 0) {
-			dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
+		ret = receive_n_bytes(ec_dev, ptr, todo);
+		if (ret < 0)
 			return ret;
-		}
 
 		debug_packet(ec_dev->dev, "interim", ptr, todo);
 		ptr += todo;
@@ -214,6 +358,138 @@ static int cros_ec_spi_receive_response(struct cros_ec_device *ec_dev,
 }
 
 /**
+ * cros_ec_pkt_xfer_spi - Transfer a packet over SPI and receive the reply
+ *
+ * @ec_dev: ChromeOS EC device
+ * @ec_msg: Message to transfer
+ */
+static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev,
+				struct cros_ec_command *ec_msg)
+{
+	struct ec_host_request *request;
+	struct ec_host_response *response;
+	struct cros_ec_spi *ec_spi = ec_dev->priv;
+	struct spi_transfer trans, trans_delay;
+	struct spi_message msg;
+	int i, len;
+	u8 *ptr;
+	u8 *rx_buf;
+	u8 sum;
+	int ret = 0, final_ret;
+
+	len = cros_ec_prepare_tx(ec_dev, ec_msg);
+	request = (struct ec_host_request *)ec_dev->dout;
+	dev_dbg(ec_dev->dev, "prepared, len=%d\n", len);
+
+	/* If it's too soon to do another transaction, wait */
+	if (ec_spi->last_transfer_ns) {
+		unsigned long delay;	/* The delay completed so far */
+
+		delay = ktime_get_ns() - ec_spi->last_transfer_ns;
+		if (delay < EC_SPI_RECOVERY_TIME_NS)
+			ndelay(EC_SPI_RECOVERY_TIME_NS - delay);
+	}
+
+	rx_buf = kzalloc(len, GFP_KERNEL);
+	if (!rx_buf) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	/*
+	 * Leave a gap between CS assertion and clocking of data to allow the
+	 * EC time to wakeup.
+	 */
+	spi_message_init(&msg);
+	if (ec_spi->start_of_msg_delay) {
+		memset(&trans_delay, 0, sizeof(trans_delay));
+		trans_delay.delay_usecs = ec_spi->start_of_msg_delay;
+		spi_message_add_tail(&trans_delay, &msg);
+	}
+
+	/* Transmit phase - send our message */
+	memset(&trans, 0, sizeof(trans));
+	trans.tx_buf = ec_dev->dout;
+	trans.rx_buf = rx_buf;
+	trans.len = len;
+	trans.cs_change = 1;
+	spi_message_add_tail(&trans, &msg);
+	ret = spi_sync(ec_spi->spi, &msg);
+
+	/* Get the response */
+	if (!ret) {
+		/* Verify that EC can process command */
+		for (i = 0; i < len; i++) {
+			switch (rx_buf[i]) {
+			case EC_SPI_PAST_END:
+			case EC_SPI_RX_BAD_DATA:
+			case EC_SPI_NOT_READY:
+				ret = -EAGAIN;
+				ec_msg->result = EC_RES_IN_PROGRESS;
+			default:
+				break;
+			}
+			if (ret)
+				break;
+		}
+		if (!ret)
+			ret = cros_ec_spi_receive_packet(ec_dev,
+					ec_msg->insize + sizeof(*response));
+	} else {
+		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
+	}
+
+	final_ret = terminate_request(ec_dev);
+	if (!ret)
+		ret = final_ret;
+	if (ret < 0)
+		goto exit;
+
+	ptr = ec_dev->din;
+
+	/* check response error code */
+	response = (struct ec_host_response *)ptr;
+	ec_msg->result = response->result;
+
+	ret = cros_ec_check_result(ec_dev, ec_msg);
+	if (ret)
+		goto exit;
+
+	len = response->data_len;
+	sum = 0;
+	if (len > ec_msg->insize) {
+		dev_err(ec_dev->dev, "packet too long (%d bytes, expected %d)",
+			len, ec_msg->insize);
+		ret = -EMSGSIZE;
+		goto exit;
+	}
+
+	for (i = 0; i < sizeof(*response); i++)
+		sum += ptr[i];
+
+	/* copy response packet payload and compute checksum */
+	memcpy(ec_msg->data, ptr + sizeof(*response), len);
+	for (i = 0; i < len; i++)
+		sum += ec_msg->data[i];
+
+	if (sum) {
+		dev_err(ec_dev->dev,
+			"bad packet checksum, calculated %x\n",
+			sum);
+		ret = -EBADMSG;
+		goto exit;
+	}
+
+	ret = len;
+exit:
+	kfree(rx_buf);
+	if (ec_msg->command == EC_CMD_REBOOT_EC)
+		msleep(EC_REBOOT_DELAY_MS);
+
+	return ret;
+}
+
+/**
  * cros_ec_cmd_xfer_spi - Transfer a message over SPI and receive the reply
  *
  * @ec_dev: ChromeOS EC device
@@ -227,6 +503,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 	struct spi_message msg;
 	int i, len;
 	u8 *ptr;
+	u8 *rx_buf;
 	int sum;
 	int ret = 0, final_ret;
 
@@ -242,10 +519,17 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 			ndelay(EC_SPI_RECOVERY_TIME_NS - delay);
 	}
 
+	rx_buf = kzalloc(len, GFP_KERNEL);
+	if (!rx_buf) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
 	/* Transmit phase - send our message */
 	debug_packet(ec_dev->dev, "out", ec_dev->dout, len);
 	memset(&trans, 0, sizeof(trans));
 	trans.tx_buf = ec_dev->dout;
+	trans.rx_buf = rx_buf;
 	trans.len = len;
 	trans.cs_change = 1;
 	spi_message_init(&msg);
@@ -254,29 +538,32 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 
 	/* Get the response */
 	if (!ret) {
-		ret = cros_ec_spi_receive_response(ec_dev,
-				ec_msg->insize + EC_MSG_TX_PROTO_BYTES);
+		/* Verify that EC can process command */
+		for (i = 0; i < len; i++) {
+			switch (rx_buf[i]) {
+			case EC_SPI_PAST_END:
+			case EC_SPI_RX_BAD_DATA:
+			case EC_SPI_NOT_READY:
+				ret = -EAGAIN;
+				ec_msg->result = EC_RES_IN_PROGRESS;
+			default:
+				break;
+			}
+			if (ret)
+				break;
+		}
+		if (!ret)
+			ret = cros_ec_spi_receive_response(ec_dev,
+					ec_msg->insize + EC_MSG_TX_PROTO_BYTES);
 	} else {
 		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
 	}
 
-	/*
-	 * Turn off CS, possibly adding a delay to ensure the rising edge
-	 * doesn't come too soon after the end of the data.
-	 */
-	spi_message_init(&msg);
-	memset(&trans, 0, sizeof(trans));
-	trans.delay_usecs = ec_spi->end_of_msg_delay;
-	spi_message_add_tail(&trans, &msg);
-
-	final_ret = spi_sync(ec_spi->spi, &msg);
-	ec_spi->last_transfer_ns = ktime_get_ns();
+	final_ret = terminate_request(ec_dev);
 	if (!ret)
 		ret = final_ret;
-	if (ret < 0) {
-		dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret);
+	if (ret < 0)
 		goto exit;
-	}
 
 	ptr = ec_dev->din;
 
@@ -299,7 +586,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 	for (i = 0; i < len; i++) {
 		sum += ptr[i + 2];
 		if (ec_msg->insize)
-			ec_msg->indata[i] = ptr[i + 2];
+			ec_msg->data[i] = ptr[i + 2];
 	}
 	sum &= 0xff;
 
@@ -315,6 +602,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev,
 
 	ret = len;
 exit:
+	kfree(rx_buf);
 	if (ec_msg->command == EC_CMD_REBOOT_EC)
 		msleep(EC_REBOOT_DELAY_MS);
 
@@ -327,6 +615,10 @@ static void cros_ec_spi_dt_probe(struct cros_ec_spi *ec_spi, struct device *dev)
 	u32 val;
 	int ret;
 
+	ret = of_property_read_u32(np, "google,cros-ec-spi-pre-delay", &val);
+	if (!ret)
+		ec_spi->start_of_msg_delay = val;
+
 	ret = of_property_read_u32(np, "google,cros-ec-spi-msg-delay", &val);
 	if (!ret)
 		ec_spi->end_of_msg_delay = val;
@@ -361,11 +653,13 @@ static int cros_ec_spi_probe(struct spi_device *spi)
 	ec_dev->priv = ec_spi;
 	ec_dev->irq = spi->irq;
 	ec_dev->cmd_xfer = cros_ec_cmd_xfer_spi;
-	ec_dev->ec_name = ec_spi->spi->modalias;
+	ec_dev->pkt_xfer = cros_ec_pkt_xfer_spi;
 	ec_dev->phys_name = dev_name(&ec_spi->spi->dev);
-	ec_dev->parent = &ec_spi->spi->dev;
-	ec_dev->din_size = EC_MSG_BYTES + EC_MSG_PREAMBLE_COUNT;
-	ec_dev->dout_size = EC_MSG_BYTES;
+	ec_dev->din_size = EC_MSG_PREAMBLE_COUNT +
+			   sizeof(struct ec_host_response) +
+			   sizeof(struct ec_response_get_protocol_info);
+	ec_dev->dout_size = sizeof(struct ec_host_request);
+
 
 	err = cros_ec_register(ec_dev);
 	if (err) {
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index ae498b53ee40..46e3840c7a37 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -433,6 +433,10 @@ EXPORT_SYMBOL_GPL(da9052_adc_read_temp);
 static const struct mfd_cell da9052_subdev_info[] = {
 	{
 		.name = "da9052-regulator",
+		.id = 0,
+	},
+	{
+		.name = "da9052-regulator",
 		.id = 1,
 	},
 	{
@@ -484,10 +488,6 @@ static const struct mfd_cell da9052_subdev_info[] = {
 		.id = 13,
 	},
 	{
-		.name = "da9052-regulator",
-		.id = 14,
-	},
-	{
 		.name = "da9052-onkey",
 	},
 	{
diff --git a/drivers/mfd/da9052-irq.c b/drivers/mfd/da9052-irq.c
index e65ca194fa98..f4cb4613140b 100644
--- a/drivers/mfd/da9052-irq.c
+++ b/drivers/mfd/da9052-irq.c
@@ -35,7 +35,7 @@
 #define DA9052_IRQ_MASK_POS_7		0x40
 #define DA9052_IRQ_MASK_POS_8		0x80
 
-static struct regmap_irq da9052_irqs[] = {
+static const struct regmap_irq da9052_irqs[] = {
 	[DA9052_IRQ_DCIN] = {
 		.reg_offset = 0,
 		.mask = DA9052_IRQ_MASK_POS_1,
@@ -166,7 +166,7 @@ static struct regmap_irq da9052_irqs[] = {
 	},
 };
 
-static struct regmap_irq_chip da9052_regmap_irq_chip = {
+static const struct regmap_irq_chip da9052_regmap_irq_chip = {
 	.name = "da9052_irq",
 	.status_base = DA9052_EVENT_A_REG,
 	.mask_base = DA9052_IRQ_MASK_A_REG,
diff --git a/drivers/mfd/da9055-core.c b/drivers/mfd/da9055-core.c
index b4d920c1ead1..177e65a12c12 100644
--- a/drivers/mfd/da9055-core.c
+++ b/drivers/mfd/da9055-core.c
@@ -222,7 +222,7 @@ static bool da9055_register_volatile(struct device *dev, unsigned int reg)
 	}
 }
 
-static struct regmap_irq da9055_irqs[] = {
+static const struct regmap_irq da9055_irqs[] = {
 	[DA9055_IRQ_NONKEY] = {
 		.reg_offset = 0,
 		.mask = DA9055_IRQ_NONKEY_MASK,
@@ -245,7 +245,7 @@ static struct regmap_irq da9055_irqs[] = {
 	},
 };
 
-struct regmap_config da9055_regmap_config = {
+const struct regmap_config da9055_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
@@ -367,7 +367,7 @@ static const struct mfd_cell da9055_devs[] = {
 	},
 };
 
-static struct regmap_irq_chip da9055_regmap_irq_chip = {
+static const struct regmap_irq_chip da9055_regmap_irq_chip = {
 	.name = "da9055_irq",
 	.status_base = DA9055_REG_EVENT_A,
 	.mask_base = DA9055_REG_IRQ_MASK_A,
diff --git a/drivers/mfd/da9063-core.c b/drivers/mfd/da9063-core.c
index facd3610ac77..af841c165787 100644
--- a/drivers/mfd/da9063-core.c
+++ b/drivers/mfd/da9063-core.c
@@ -60,6 +60,7 @@ static struct resource da9063_rtc_resources[] = {
 
 static struct resource da9063_onkey_resources[] = {
 	{
+		.name	= "ONKEY",
 		.start	= DA9063_IRQ_ONKEY,
 		.end	= DA9063_IRQ_ONKEY,
 		.flags	= IORESOURCE_IRQ,
@@ -97,6 +98,7 @@ static const struct mfd_cell da9063_devs[] = {
 		.name		= DA9063_DRVNAME_ONKEY,
 		.num_resources	= ARRAY_SIZE(da9063_onkey_resources),
 		.resources	= da9063_onkey_resources,
+		.of_compatible = "dlg,da9063-onkey",
 	},
 	{
 		.name		= DA9063_DRVNAME_RTC,
@@ -109,12 +111,64 @@ static const struct mfd_cell da9063_devs[] = {
 	},
 };
 
+static int da9063_clear_fault_log(struct da9063 *da9063)
+{
+	int ret = 0;
+	int fault_log = 0;
+
+	ret = regmap_read(da9063->regmap, DA9063_REG_FAULT_LOG, &fault_log);
+	if (ret < 0) {
+		dev_err(da9063->dev, "Cannot read FAULT_LOG.\n");
+		return -EIO;
+	}
+
+	if (fault_log) {
+		if (fault_log & DA9063_TWD_ERROR)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_TWD_ERROR\n");
+		if (fault_log & DA9063_POR)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_POR\n");
+		if (fault_log & DA9063_VDD_FAULT)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_VDD_FAULT\n");
+		if (fault_log & DA9063_VDD_START)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_VDD_START\n");
+		if (fault_log & DA9063_TEMP_CRIT)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_TEMP_CRIT\n");
+		if (fault_log & DA9063_KEY_RESET)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_KEY_RESET\n");
+		if (fault_log & DA9063_NSHUTDOWN)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_NSHUTDOWN\n");
+		if (fault_log & DA9063_WAIT_SHUT)
+			dev_dbg(da9063->dev,
+				"Fault log entry detected: DA9063_WAIT_SHUT\n");
+	}
+
+	ret = regmap_write(da9063->regmap,
+			   DA9063_REG_FAULT_LOG,
+			   fault_log);
+	if (ret < 0)
+		dev_err(da9063->dev,
+			"Cannot reset FAULT_LOG values %d\n", ret);
+
+	return ret;
+}
+
 int da9063_device_init(struct da9063 *da9063, unsigned int irq)
 {
 	struct da9063_pdata *pdata = da9063->dev->platform_data;
 	int model, variant_id, variant_code;
 	int ret;
 
+	ret = da9063_clear_fault_log(da9063);
+	if (ret < 0)
+		dev_err(da9063->dev, "Cannot clear fault log\n");
+
 	if (pdata) {
 		da9063->flags = pdata->flags;
 		da9063->irq_base = pdata->irq_base;
diff --git a/drivers/mfd/da9063-irq.c b/drivers/mfd/da9063-irq.c
index 822922602ce9..eaf1ec9208b2 100644
--- a/drivers/mfd/da9063-irq.c
+++ b/drivers/mfd/da9063-irq.c
@@ -34,7 +34,7 @@ struct da9063_irq_data {
 	u8 mask;
 };
 
-static struct regmap_irq da9063_irqs[] = {
+static const struct regmap_irq da9063_irqs[] = {
 	/* DA9063 event A register */
 	[DA9063_IRQ_ONKEY] = {
 		.reg_offset = DA9063_REG_EVENT_A_OFFSET,
@@ -153,7 +153,7 @@ static struct regmap_irq da9063_irqs[] = {
 	},
 };
 
-static struct regmap_irq_chip da9063_irq_chip = {
+static const struct regmap_irq_chip da9063_irq_chip = {
 	.name = "da9063-irq",
 	.irqs = da9063_irqs,
 	.num_irqs = DA9063_NUM_IRQ,
diff --git a/drivers/mfd/da9150-core.c b/drivers/mfd/da9150-core.c
index 5549817df32e..94b9bbd1a69b 100644
--- a/drivers/mfd/da9150-core.c
+++ b/drivers/mfd/da9150-core.c
@@ -164,7 +164,7 @@ void da9150_bulk_write(struct da9150 *da9150, u16 reg, int count, const u8 *buf)
 }
 EXPORT_SYMBOL_GPL(da9150_bulk_write);
 
-static struct regmap_irq da9150_irqs[] = {
+static const struct regmap_irq da9150_irqs[] = {
 	[DA9150_IRQ_VBUS] = {
 		.reg_offset = 0,
 		.mask = DA9150_E_VBUS_MASK,
@@ -251,7 +251,7 @@ static struct regmap_irq da9150_irqs[] = {
 	},
 };
 
-static struct regmap_irq_chip da9150_regmap_irq_chip = {
+static const struct regmap_irq_chip da9150_regmap_irq_chip = {
 	.name = "da9150_irq",
 	.status_base = DA9150_EVENT_E,
 	.mask_base = DA9150_IRQ_MASK_E,
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index cc1a404328c2..8b14740f9fca 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2659,7 +2659,7 @@ static int db8500_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops db8500_irq_ops = {
+static const struct irq_domain_ops db8500_irq_ops = {
 	.map    = db8500_irq_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
diff --git a/drivers/mfd/htc-i2cpld.c b/drivers/mfd/htc-i2cpld.c
index ebb9cf19e347..b54baad30164 100644
--- a/drivers/mfd/htc-i2cpld.c
+++ b/drivers/mfd/htc-i2cpld.c
@@ -564,7 +564,8 @@ static int htcpld_core_probe(struct platform_device *pdev)
 		htcpld->chained_irq = res->start;
 
 		/* Setup the chained interrupt handler */
-		flags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING;
+		flags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING |
+			IRQF_ONESHOT;
 		ret = request_threaded_irq(htcpld->chained_irq,
 					   NULL, htcpld_handler,
 					   flags, pdev->name, htcpld);
diff --git a/drivers/mfd/intel_soc_pmic_core.h b/drivers/mfd/intel_soc_pmic_core.h
index 9498d6719847..ff2464bc172f 100644
--- a/drivers/mfd/intel_soc_pmic_core.h
+++ b/drivers/mfd/intel_soc_pmic_core.h
@@ -24,7 +24,7 @@ struct intel_soc_pmic_config {
 	struct mfd_cell *cell_dev;
 	int n_cell_devs;
 	const struct regmap_config *regmap_config;
-	struct regmap_irq_chip *irq_chip;
+	const struct regmap_irq_chip *irq_chip;
 };
 
 extern struct intel_soc_pmic_config intel_soc_pmic_config_crc;
diff --git a/drivers/mfd/intel_soc_pmic_crc.c b/drivers/mfd/intel_soc_pmic_crc.c
index 4cc1b324e971..7436075e8983 100644
--- a/drivers/mfd/intel_soc_pmic_crc.c
+++ b/drivers/mfd/intel_soc_pmic_crc.c
@@ -143,7 +143,7 @@ static const struct regmap_irq crystal_cove_irqs[] = {
 	},
 };
 
-static struct regmap_irq_chip crystal_cove_irq_chip = {
+static const struct regmap_irq_chip crystal_cove_irq_chip = {
 	.name = "Crystal Cove",
 	.irqs = crystal_cove_irqs,
 	.num_irqs = ARRAY_SIZE(crystal_cove_irqs),
diff --git a/drivers/mfd/janz-cmodio.c b/drivers/mfd/janz-cmodio.c
index 433f823037dd..ec1f46a6be3a 100644
--- a/drivers/mfd/janz-cmodio.c
+++ b/drivers/mfd/janz-cmodio.c
@@ -267,6 +267,10 @@ static void cmodio_pci_remove(struct pci_dev *dev)
 static const struct pci_device_id cmodio_pci_ids[] = {
 	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0101 },
 	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0100 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0201 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_JANZ, 0x0202 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0201 },
+	{ PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_JANZ, 0x0202 },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, cmodio_pci_ids);
diff --git a/drivers/mfd/lp8788-irq.c b/drivers/mfd/lp8788-irq.c
index 23982dbf014d..a87f2b548f71 100644
--- a/drivers/mfd/lp8788-irq.c
+++ b/drivers/mfd/lp8788-irq.c
@@ -151,7 +151,7 @@ static int lp8788_irq_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops lp8788_domain_ops = {
+static const struct irq_domain_ops lp8788_domain_ops = {
 	.map = lp8788_irq_map,
 };
 
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 12d960a60ec4..8de34398abc0 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -934,8 +934,8 @@ gpe0_done:
 	lpc_ich_enable_gpio_space(dev);
 
 	lpc_ich_finalize_cell(dev, &lpc_ich_cells[LPC_GPIO]);
-	ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_GPIO],
-			      1, NULL, 0, NULL);
+	ret = mfd_add_devices(&dev->dev, PLATFORM_DEVID_AUTO,
+			      &lpc_ich_cells[LPC_GPIO], 1, NULL, 0, NULL);
 
 gpio_done:
 	if (acpi_conflict)
@@ -1008,8 +1008,8 @@ static int lpc_ich_init_wdt(struct pci_dev *dev)
 	}
 
 	lpc_ich_finalize_cell(dev, &lpc_ich_cells[LPC_WDT]);
-	ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_WDT],
-			      1, NULL, 0, NULL);
+	ret = mfd_add_devices(&dev->dev, PLATFORM_DEVID_AUTO,
+			      &lpc_ich_cells[LPC_WDT], 1, NULL, 0, NULL);
 
 wdt_done:
 	return ret;
diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c
index 97a787ab3d51..8520bd68c1ff 100644
--- a/drivers/mfd/max8925-core.c
+++ b/drivers/mfd/max8925-core.c
@@ -658,7 +658,7 @@ static int max8925_irq_domain_map(struct irq_domain *d, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops max8925_irq_domain_ops = {
+static const struct irq_domain_ops max8925_irq_domain_ops = {
 	.map	= max8925_irq_domain_map,
 	.xlate	= irq_domain_xlate_onetwocell,
 };
diff --git a/drivers/mfd/max8997-irq.c b/drivers/mfd/max8997-irq.c
index 43fa61413e93..d3025be57f39 100644
--- a/drivers/mfd/max8997-irq.c
+++ b/drivers/mfd/max8997-irq.c
@@ -303,7 +303,7 @@ static int max8997_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops max8997_irq_domain_ops = {
+static const struct irq_domain_ops max8997_irq_domain_ops = {
 	.map = max8997_irq_domain_map,
 };
 
diff --git a/drivers/mfd/max8998-irq.c b/drivers/mfd/max8998-irq.c
index c469477eb778..3702056628a8 100644
--- a/drivers/mfd/max8998-irq.c
+++ b/drivers/mfd/max8998-irq.c
@@ -214,7 +214,7 @@ static int max8998_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops max8998_irq_domain_ops = {
+static const struct irq_domain_ops max8998_irq_domain_ops = {
 	.map = max8998_irq_domain_map,
 };
 
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index 25fd7116493a..3f9f4c874d2a 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -163,7 +163,7 @@ int mc13xxx_irq_request(struct mc13xxx *mc13xxx, int irq,
 	int virq = regmap_irq_get_virq(mc13xxx->irq_data, irq);
 
 	return devm_request_threaded_irq(mc13xxx->dev, virq, NULL, handler,
-					 0, name, dev);
+					 IRQF_ONESHOT, name, dev);
 }
 EXPORT_SYMBOL(mc13xxx_irq_request);
 
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 1aed3b7b8d9b..14fd5cbcf0f2 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -207,9 +207,11 @@ static int mfd_add_device(struct device *parent, int id,
 		}
 
 		if (!cell->ignore_resource_conflicts) {
-			ret = acpi_check_resource_conflict(&res[r]);
-			if (ret)
-				goto fail_alias;
+			if (has_acpi_companion(&pdev->dev)) {
+				ret = acpi_check_resource_conflict(&res[r]);
+				if (ret)
+					goto fail_alias;
+			}
 		}
 	}
 
diff --git a/drivers/mfd/mt6397-core.c b/drivers/mfd/mt6397-core.c
index 09bc7804952a..38a0458f7834 100644
--- a/drivers/mfd/mt6397-core.c
+++ b/drivers/mfd/mt6397-core.c
@@ -34,6 +34,9 @@ static const struct mfd_cell mt6397_devs[] = {
 	}, {
 		.name = "mt6397-clk",
 		.of_compatible = "mediatek,mt6397-clk",
+	}, {
+		.name = "mt6397-pinctrl",
+		.of_compatible = "mediatek,mt6397-pinctrl",
 	},
 };
 
@@ -130,7 +133,7 @@ static int mt6397_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-static struct irq_domain_ops mt6397_irq_domain_ops = {
+static const struct irq_domain_ops mt6397_irq_domain_ops = {
 	.map = mt6397_irq_domain_map,
 };
 
diff --git a/drivers/mfd/si476x-i2c.c b/drivers/mfd/si476x-i2c.c
index 7f87c62d91b3..e3deb466628b 100644
--- a/drivers/mfd/si476x-i2c.c
+++ b/drivers/mfd/si476x-i2c.c
@@ -777,7 +777,8 @@ static int si476x_core_probe(struct i2c_client *client,
 		rval = devm_request_threaded_irq(&client->dev,
 						 client->irq, NULL,
 						 si476x_core_interrupt,
-						 IRQF_TRIGGER_FALLING,
+						 IRQF_TRIGGER_FALLING |
+						 IRQF_ONESHOT,
 						 client->name, core);
 		if (rval < 0) {
 			dev_err(&client->dev, "Could not request IRQ %d\n",
diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index 2d7fae94c861..18c4d72d1d2a 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -989,7 +989,7 @@ static void stmpe_irq_unmap(struct irq_domain *d, unsigned int virq)
 		irq_set_chip_data(virq, NULL);
 }
 
-static struct irq_domain_ops stmpe_irq_ops = {
+static const struct irq_domain_ops stmpe_irq_ops = {
         .map    = stmpe_irq_map,
         .unmap  = stmpe_irq_unmap,
         .xlate  = irq_domain_xlate_twocell,
diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c
index cf356395c9e9..96d420dfc15d 100644
--- a/drivers/mfd/tc3589x.c
+++ b/drivers/mfd/tc3589x.c
@@ -233,7 +233,7 @@ static void tc3589x_irq_unmap(struct irq_domain *d, unsigned int virq)
 	irq_set_chip_data(virq, NULL);
 }
 
-static struct irq_domain_ops tc3589x_irq_ops = {
+static const struct irq_domain_ops tc3589x_irq_ops = {
 	.map    = tc3589x_irq_map,
 	.unmap  = tc3589x_irq_unmap,
 	.xlate  = irq_domain_xlate_onecell,
diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c
index 8e1dbc469580..e0a2583916ce 100644
--- a/drivers/mfd/tps6586x.c
+++ b/drivers/mfd/tps6586x.c
@@ -311,7 +311,7 @@ static int tps6586x_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops tps6586x_domain_ops = {
+static const struct irq_domain_ops tps6586x_domain_ops = {
 	.map    = tps6586x_irq_map,
 	.xlate  = irq_domain_xlate_twocell,
 };
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 1b772ef761cb..a3fa7f4f1fb4 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -674,7 +674,7 @@ int twl4030_sih_setup(struct device *dev, int module, int irq_base)
 	irq_set_handler_data(irq, agent);
 	agent->irq_name = kasprintf(GFP_KERNEL, "twl4030_%s", sih->name);
 	status = request_threaded_irq(irq, NULL, handle_twl4030_sih,
-				      IRQF_EARLY_RESUME,
+				      IRQF_EARLY_RESUME | IRQF_ONESHOT,
 				      agent->irq_name ?: sih->name, NULL);
 
 	dev_info(dev, "%s (irq %d) chaining IRQs %d..%d\n", sih->name,
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index f440aed61305..04b539850e72 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -264,7 +264,9 @@ out:
 	return err;
 }
 
-static int twl4030_config_wakeup12_sequence(u8 address)
+static int
+twl4030_config_wakeup12_sequence(const struct twl4030_power_data *pdata,
+				 u8 address)
 {
 	int err = 0;
 	u8 data;
@@ -293,13 +295,14 @@ static int twl4030_config_wakeup12_sequence(u8 address)
 	if (err)
 		goto out;
 
-	if (machine_is_omap_3430sdp() || machine_is_omap_ldp()) {
+	if (pdata->ac_charger_quirk || machine_is_omap_3430sdp() ||
+	    machine_is_omap_ldp()) {
 		/* Disabling AC charger effect on sleep-active transitions */
 		err = twl_i2c_read_u8(TWL_MODULE_PM_MASTER, &data,
 				      R_CFG_P1_TRANSITION);
 		if (err)
 			goto out;
-		data &= ~(1<<1);
+		data &= ~STARTON_CHG;
 		err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, data,
 				       R_CFG_P1_TRANSITION);
 		if (err)
@@ -459,8 +462,9 @@ static int twl4030_configure_resource(struct twl4030_resconfig *rconfig)
 	return 0;
 }
 
-static int load_twl4030_script(struct twl4030_script *tscript,
-	       u8 address)
+static int load_twl4030_script(const struct twl4030_power_data *pdata,
+			       struct twl4030_script *tscript,
+			       u8 address)
 {
 	int err;
 	static int order;
@@ -487,7 +491,7 @@ static int load_twl4030_script(struct twl4030_script *tscript,
 		if (err)
 			goto out;
 
-		err = twl4030_config_wakeup12_sequence(address);
+		err = twl4030_config_wakeup12_sequence(pdata, address);
 		if (err)
 			goto out;
 		order = 1;
@@ -567,7 +571,7 @@ twl4030_power_configure_scripts(const struct twl4030_power_data *pdata)
 	u8 address = twl4030_start_script_address;
 
 	for (i = 0; i < pdata->num; i++) {
-		err = load_twl4030_script(pdata->scripts[i], address);
+		err = load_twl4030_script(pdata, pdata->scripts[i], address);
 		if (err)
 			return err;
 		address += pdata->scripts[i]->size;
@@ -829,6 +833,21 @@ static struct twl4030_power_data osc_off_idle = {
 	.board_config		= osc_off_rconfig,
 };
 
+static struct twl4030_power_data omap3_idle_ac_quirk = {
+	.scripts		= omap3_idle_scripts,
+	.num			= ARRAY_SIZE(omap3_idle_scripts),
+	.resource_config	= omap3_idle_rconfig,
+	.ac_charger_quirk	= true,
+};
+
+static struct twl4030_power_data omap3_idle_ac_quirk_osc_off = {
+	.scripts		= omap3_idle_scripts,
+	.num			= ARRAY_SIZE(omap3_idle_scripts),
+	.resource_config	= omap3_idle_rconfig,
+	.board_config		= osc_off_rconfig,
+	.ac_charger_quirk	= true,
+};
+
 static const struct of_device_id twl4030_power_of_match[] = {
 	{
 		.compatible = "ti,twl4030-power",
@@ -845,6 +864,18 @@ static const struct of_device_id twl4030_power_of_match[] = {
 		.compatible = "ti,twl4030-power-idle-osc-off",
 		.data = &osc_off_idle,
 	},
+	{
+		.compatible = "ti,twl4030-power-omap3-sdp",
+		.data = &omap3_idle_ac_quirk,
+	},
+	{
+		.compatible = "ti,twl4030-power-omap3-ldp",
+		.data = &omap3_idle_ac_quirk_osc_off,
+	},
+	{
+		.compatible = "ti,twl4030-power-omap3-evm",
+		.data = &omap3_idle_ac_quirk,
+	},
 	{ },
 };
 MODULE_DEVICE_TABLE(of, twl4030_power_of_match);
diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index 2807e1a95663..20fb58179ada 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -376,7 +376,7 @@ static void twl6030_irq_unmap(struct irq_domain *d, unsigned int virq)
 	irq_set_chip_data(virq, NULL);
 }
 
-static struct irq_domain_ops twl6030_irq_domain_ops = {
+static const struct irq_domain_ops twl6030_irq_domain_ops = {
 	.map	= twl6030_irq_map,
 	.unmap	= twl6030_irq_unmap,
 	.xlate	= irq_domain_xlate_onetwocell,
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index 58ea9fdd3a15..3591550598ad 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -566,8 +566,7 @@ static int ucb1x00_probe(struct mcp *mcp)
 	}
 
 	irq_set_irq_type(ucb->irq, IRQ_TYPE_EDGE_RISING);
-	irq_set_handler_data(ucb->irq, ucb);
-	irq_set_chained_handler(ucb->irq, ucb1x00_irq);
+	irq_set_chained_handler_and_data(ucb->irq, ucb1x00_irq, ucb);
 
 	if (pdata && pdata->gpio_base) {
 		ucb->gpio.label = dev_name(&ucb->dev);
diff --git a/drivers/mfd/wm831x-auxadc.c b/drivers/mfd/wm831x-auxadc.c
index 6ee3018d8653..fd789d2eb0f5 100644
--- a/drivers/mfd/wm831x-auxadc.c
+++ b/drivers/mfd/wm831x-auxadc.c
@@ -285,7 +285,8 @@ void wm831x_auxadc_init(struct wm831x *wm831x)
 
 		ret = request_threaded_irq(wm831x_irq(wm831x,
 						      WM831X_IRQ_AUXADC_DATA),
-					   NULL, wm831x_auxadc_irq, 0,
+					   NULL, wm831x_auxadc_irq,
+					   IRQF_ONESHOT,
 					   "auxadc", wm831x);
 		if (ret < 0) {
 			dev_err(wm831x->dev, "AUXADC IRQ request failed: %d\n",
diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c
index 64e512eadf17..3da81263c764 100644
--- a/drivers/mfd/wm831x-irq.c
+++ b/drivers/mfd/wm831x-irq.c
@@ -564,7 +564,7 @@ static int wm831x_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops wm831x_irq_domain_ops = {
+static const struct irq_domain_ops wm831x_irq_domain_ops = {
 	.map	= wm831x_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index f5124a8acad8..8a07c5634aee 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -404,7 +404,8 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 	if (wm8350->irq_base) {
 		ret = request_threaded_irq(wm8350->irq_base +
 					   WM8350_IRQ_AUXADC_DATARDY,
-					   NULL, wm8350_auxadc_irq, 0,
+					   NULL, wm8350_auxadc_irq,
+					   IRQF_ONESHOT,
 					   "auxadc", wm8350);
 		if (ret < 0)
 			dev_warn(wm8350->dev,
diff --git a/drivers/mfd/wm8994-irq.c b/drivers/mfd/wm8994-irq.c
index a14407edbd89..55c380a67686 100644
--- a/drivers/mfd/wm8994-irq.c
+++ b/drivers/mfd/wm8994-irq.c
@@ -28,7 +28,7 @@
 
 #include <linux/delay.h>
 
-static struct regmap_irq wm8994_irqs[] = {
+static const struct regmap_irq wm8994_irqs[] = {
 	[WM8994_IRQ_TEMP_SHUT] = {
 		.reg_offset = 1,
 		.mask = WM8994_TEMP_SHUT_EINT,
@@ -128,7 +128,7 @@ static struct regmap_irq wm8994_irqs[] = {
 	},
 };
 
-static struct regmap_irq_chip wm8994_irq_chip = {
+static const struct regmap_irq_chip wm8994_irq_chip = {
 	.name = "wm8994",
 	.irqs = wm8994_irqs,
 	.num_irqs = ARRAY_SIZE(wm8994_irqs),
@@ -184,7 +184,7 @@ static int wm8994_edge_irq_map(struct irq_domain *h, unsigned int virq,
 	return 0;
 }
 
-static struct irq_domain_ops wm8994_edge_irq_ops = {
+static const struct irq_domain_ops wm8994_edge_irq_ops = {
 	.map	= wm8994_edge_irq_map,
 	.xlate	= irq_domain_xlate_twocell,
 };
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index a990b39b4dfb..b6db9ebd52c2 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -7,10 +7,15 @@ config CXL_BASE
 	default n
 	select PPC_COPRO_BASE
 
+config CXL_KERNEL_API
+	bool
+	default n
+
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
 	depends on PPC_POWERNV && PCI_MSI
 	select CXL_BASE
+	select CXL_KERNEL_API
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index edb494d3ff27..14e3f8219a11 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,6 @@
-cxl-y				+= main.o file.o irq.o fault.o native.o context.o sysfs.o debugfs.o pci.o trace.o
+cxl-y				+= main.o file.o irq.o fault.o native.o
+cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
+cxl-y				+= vphb.o api.o
 obj-$(CONFIG_CXL)		+= cxl.o
 obj-$(CONFIG_CXL_BASE)		+= base.o
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
new file mode 100644
index 000000000000..0c77240ae2fc
--- /dev/null
+++ b/drivers/misc/cxl/api.c
@@ -0,0 +1,331 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <misc/cxl.h>
+
+#include "cxl.h"
+
+struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+	struct cxl_context  *ctx;
+	int rc;
+
+	afu = cxl_pci_to_afu(dev);
+
+	ctx = cxl_context_alloc();
+	if (IS_ERR(ctx))
+		return ctx;
+
+	/* Make it a slave context.  We can promote it later? */
+	rc = cxl_context_init(ctx, afu, false, NULL);
+	if (rc) {
+		kfree(ctx);
+		return ERR_PTR(-ENOMEM);
+	}
+	cxl_assign_psn_space(ctx);
+
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(cxl_dev_context_init);
+
+struct cxl_context *cxl_get_context(struct pci_dev *dev)
+{
+	return dev->dev.archdata.cxl_ctx;
+}
+EXPORT_SYMBOL_GPL(cxl_get_context);
+
+struct device *cxl_get_phys_dev(struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+
+	afu = cxl_pci_to_afu(dev);
+
+	return afu->adapter->dev.parent;
+}
+EXPORT_SYMBOL_GPL(cxl_get_phys_dev);
+
+int cxl_release_context(struct cxl_context *ctx)
+{
+	if (ctx->status != CLOSED)
+		return -EBUSY;
+
+	cxl_context_free(ctx);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_release_context);
+
+int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
+{
+	if (num == 0)
+		num = ctx->afu->pp_irqs;
+	return afu_allocate_irqs(ctx, num);
+}
+EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);
+
+void cxl_free_afu_irqs(struct cxl_context *ctx)
+{
+	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+}
+EXPORT_SYMBOL_GPL(cxl_free_afu_irqs);
+
+static irq_hw_number_t cxl_find_afu_irq(struct cxl_context *ctx, int num)
+{
+	__u16 range;
+	int r;
+
+	WARN_ON(num == 0);
+
+	for (r = 0; r < CXL_IRQ_RANGES; r++) {
+		range = ctx->irqs.range[r];
+		if (num < range) {
+			return ctx->irqs.offset[r] + num;
+		}
+		num -= range;
+	}
+	return 0;
+}
+
+int cxl_map_afu_irq(struct cxl_context *ctx, int num,
+		    irq_handler_t handler, void *cookie, char *name)
+{
+	irq_hw_number_t hwirq;
+
+	/*
+	 * Find interrupt we are to register.
+	 */
+	hwirq = cxl_find_afu_irq(ctx, num);
+	if (!hwirq)
+		return -ENOENT;
+
+	return cxl_map_irq(ctx->afu->adapter, hwirq, handler, cookie, name);
+}
+EXPORT_SYMBOL_GPL(cxl_map_afu_irq);
+
+void cxl_unmap_afu_irq(struct cxl_context *ctx, int num, void *cookie)
+{
+	irq_hw_number_t hwirq;
+	unsigned int virq;
+
+	hwirq = cxl_find_afu_irq(ctx, num);
+	if (!hwirq)
+		return;
+
+	virq = irq_find_mapping(NULL, hwirq);
+	if (virq)
+		cxl_unmap_irq(virq, cookie);
+}
+EXPORT_SYMBOL_GPL(cxl_unmap_afu_irq);
+
+/*
+ * Start a context
+ * Code here similar to afu_ioctl_start_work().
+ */
+int cxl_start_context(struct cxl_context *ctx, u64 wed,
+		      struct task_struct *task)
+{
+	int rc = 0;
+	bool kernel = true;
+
+	pr_devel("%s: pe: %i\n", __func__, ctx->pe);
+
+	mutex_lock(&ctx->status_mutex);
+	if (ctx->status == STARTED)
+		goto out; /* already started */
+
+	if (task) {
+		ctx->pid = get_task_pid(task, PIDTYPE_PID);
+		get_pid(ctx->pid);
+		kernel = false;
+	}
+
+	cxl_ctx_get();
+
+	if ((rc = cxl_attach_process(ctx, kernel, wed , 0))) {
+		put_pid(ctx->pid);
+		cxl_ctx_put();
+		goto out;
+	}
+
+	ctx->status = STARTED;
+	get_device(&ctx->afu->dev);
+out:
+	mutex_unlock(&ctx->status_mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxl_start_context);
+
+int cxl_process_element(struct cxl_context *ctx)
+{
+	return ctx->pe;
+}
+EXPORT_SYMBOL_GPL(cxl_process_element);
+
+/* Stop a context.  Returns 0 on success, otherwise -Errno */
+int cxl_stop_context(struct cxl_context *ctx)
+{
+	int rc;
+
+	rc = __detach_context(ctx);
+	if (!rc)
+		put_device(&ctx->afu->dev);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(cxl_stop_context);
+
+void cxl_set_master(struct cxl_context *ctx)
+{
+	ctx->master = true;
+	cxl_assign_psn_space(ctx);
+}
+EXPORT_SYMBOL_GPL(cxl_set_master);
+
+/* wrappers around afu_* file ops which are EXPORTED */
+int cxl_fd_open(struct inode *inode, struct file *file)
+{
+	return afu_open(inode, file);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_open);
+int cxl_fd_release(struct inode *inode, struct file *file)
+{
+	return afu_release(inode, file);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_release);
+long cxl_fd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return afu_ioctl(file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_ioctl);
+int cxl_fd_mmap(struct file *file, struct vm_area_struct *vm)
+{
+	return afu_mmap(file, vm);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_mmap);
+unsigned int cxl_fd_poll(struct file *file, struct poll_table_struct *poll)
+{
+	return afu_poll(file, poll);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_poll);
+ssize_t cxl_fd_read(struct file *file, char __user *buf, size_t count,
+			loff_t *off)
+{
+	return afu_read(file, buf, count, off);
+}
+EXPORT_SYMBOL_GPL(cxl_fd_read);
+
+#define PATCH_FOPS(NAME) if (!fops->NAME) fops->NAME = afu_fops.NAME
+
+/* Get a struct file and fd for a context and attach the ops */
+struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
+			int *fd)
+{
+	struct file *file;
+	int rc, flags, fdtmp;
+
+	flags = O_RDWR | O_CLOEXEC;
+
+	/* This code is similar to anon_inode_getfd() */
+	rc = get_unused_fd_flags(flags);
+	if (rc < 0)
+		return ERR_PTR(rc);
+	fdtmp = rc;
+
+	/*
+	 * Patch the file ops.  Needs to be careful that this is rentrant safe.
+	 */
+	if (fops) {
+		PATCH_FOPS(open);
+		PATCH_FOPS(poll);
+		PATCH_FOPS(read);
+		PATCH_FOPS(release);
+		PATCH_FOPS(unlocked_ioctl);
+		PATCH_FOPS(compat_ioctl);
+		PATCH_FOPS(mmap);
+	} else /* use default ops */
+		fops = (struct file_operations *)&afu_fops;
+
+	file = anon_inode_getfile("cxl", fops, ctx, flags);
+	if (IS_ERR(file))
+		put_unused_fd(fdtmp);
+	*fd = fdtmp;
+	return file;
+}
+EXPORT_SYMBOL_GPL(cxl_get_fd);
+
+struct cxl_context *cxl_fops_get_context(struct file *file)
+{
+	return file->private_data;
+}
+EXPORT_SYMBOL_GPL(cxl_fops_get_context);
+
+int cxl_start_work(struct cxl_context *ctx,
+		   struct cxl_ioctl_start_work *work)
+{
+	int rc;
+
+	/* code taken from afu_ioctl_start_work */
+	if (!(work->flags & CXL_START_WORK_NUM_IRQS))
+		work->num_interrupts = ctx->afu->pp_irqs;
+	else if ((work->num_interrupts < ctx->afu->pp_irqs) ||
+		 (work->num_interrupts > ctx->afu->irqs_max)) {
+		return -EINVAL;
+	}
+
+	rc = afu_register_irqs(ctx, work->num_interrupts);
+	if (rc)
+		return rc;
+
+	rc = cxl_start_context(ctx, work->work_element_descriptor, current);
+	if (rc < 0) {
+		afu_release_irqs(ctx, ctx);
+		return rc;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_start_work);
+
+void __iomem *cxl_psa_map(struct cxl_context *ctx)
+{
+	struct cxl_afu *afu = ctx->afu;
+	int rc;
+
+	rc = cxl_afu_check_and_enable(afu);
+	if (rc)
+		return NULL;
+
+	pr_devel("%s: psn_phys%llx size:%llx\n",
+		 __func__, afu->psn_phys, afu->adapter->ps_size);
+	return ioremap(ctx->psn_phys, ctx->psn_size);
+}
+EXPORT_SYMBOL_GPL(cxl_psa_map);
+
+void cxl_psa_unmap(void __iomem *addr)
+{
+	iounmap(addr);
+}
+EXPORT_SYMBOL_GPL(cxl_psa_unmap);
+
+int cxl_afu_reset(struct cxl_context *ctx)
+{
+	struct cxl_afu *afu = ctx->afu;
+	int rc;
+
+	rc = __cxl_afu_reset(afu);
+	if (rc)
+		return rc;
+
+	return cxl_afu_check_and_enable(afu);
+}
+EXPORT_SYMBOL_GPL(cxl_afu_reset);
diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c
index 0654ad83675e..a9f0dd3255a2 100644
--- a/drivers/misc/cxl/base.c
+++ b/drivers/misc/cxl/base.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <asm/errno.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 #include "cxl.h"
 
 /* protected by rcu */
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index d1b55fe62817..2a4c80ac322a 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -174,7 +174,7 @@ int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
  * return until all outstanding interrupts for this context have completed. The
  * hardware should no longer access *ctx after this has returned.
  */
-static void __detach_context(struct cxl_context *ctx)
+int __detach_context(struct cxl_context *ctx)
 {
 	enum cxl_context_status status;
 
@@ -183,12 +183,13 @@ static void __detach_context(struct cxl_context *ctx)
 	ctx->status = CLOSED;
 	mutex_unlock(&ctx->status_mutex);
 	if (status != STARTED)
-		return;
+		return -EBUSY;
 
 	WARN_ON(cxl_detach_process(ctx));
-	afu_release_irqs(ctx);
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
-	wake_up_all(&ctx->wq);
+	put_pid(ctx->pid);
+	cxl_ctx_put();
+	return 0;
 }
 
 /*
@@ -199,7 +200,14 @@ static void __detach_context(struct cxl_context *ctx)
  */
 void cxl_context_detach(struct cxl_context *ctx)
 {
-	__detach_context(ctx);
+	int rc;
+
+	rc = __detach_context(ctx);
+	if (rc)
+		return;
+
+	afu_release_irqs(ctx, ctx);
+	wake_up_all(&ctx->wq);
 }
 
 /*
@@ -216,7 +224,7 @@ void cxl_context_detach_all(struct cxl_afu *afu)
 		 * Anything done in here needs to be setup before the IDR is
 		 * created and torn down after the IDR removed
 		 */
-		__detach_context(ctx);
+		cxl_context_detach(ctx);
 
 		/*
 		 * We are force detaching - remove any active PSA mappings so
@@ -232,16 +240,20 @@ void cxl_context_detach_all(struct cxl_afu *afu)
 	mutex_unlock(&afu->contexts_lock);
 }
 
-void cxl_context_free(struct cxl_context *ctx)
+static void reclaim_ctx(struct rcu_head *rcu)
 {
-	mutex_lock(&ctx->afu->contexts_lock);
-	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
-	mutex_unlock(&ctx->afu->contexts_lock);
-	synchronize_rcu();
+	struct cxl_context *ctx = container_of(rcu, struct cxl_context, rcu);
 
 	free_page((u64)ctx->sstp);
 	ctx->sstp = NULL;
 
-	put_pid(ctx->pid);
 	kfree(ctx);
 }
+
+void cxl_context_free(struct cxl_context *ctx)
+{
+	mutex_lock(&ctx->afu->contexts_lock);
+	idr_remove(&ctx->afu->contexts_idr, ctx->pe);
+	mutex_unlock(&ctx->afu->contexts_lock);
+	call_rcu(&ctx->rcu, reclaim_ctx);
+}
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index a1cee4767ec6..4fd66cabde1e 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -18,10 +18,11 @@
 #include <linux/pid.h>
 #include <linux/io.h>
 #include <linux/pci.h>
+#include <linux/fs.h>
 #include <asm/cputable.h>
 #include <asm/mmu.h>
 #include <asm/reg.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include <uapi/misc/cxl.h>
 
@@ -315,8 +316,6 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_MAX_SLICES 4
 #define MAX_AFU_MMIO_REGS 3
 
-#define CXL_MODE_DEDICATED   0x1
-#define CXL_MODE_DIRECTED    0x2
 #define CXL_MODE_TIME_SLICED 0x4
 #define CXL_SUPPORTED_MODES (CXL_MODE_DEDICATED | CXL_MODE_DIRECTED)
 
@@ -362,6 +361,10 @@ struct cxl_afu {
 	struct mutex spa_mutex;
 	spinlock_t afu_cntl_lock;
 
+	/* AFU error buffer fields and bin attribute for sysfs */
+	u64 eb_len, eb_offset;
+	struct bin_attribute attr_eb;
+
 	/*
 	 * Only the first part of the SPA is used for the process element
 	 * linked list. The only other part that software needs to worry about
@@ -375,6 +378,9 @@ struct cxl_afu {
 	int spa_max_procs;
 	unsigned int psl_virq;
 
+	/* pointer to the vphb */
+	struct pci_controller *phb;
+
 	int pp_irqs;
 	int irqs_max;
 	int num_procs;
@@ -455,6 +461,8 @@ struct cxl_context {
 	bool pending_irq;
 	bool pending_fault;
 	bool pending_afu_err;
+
+	struct rcu_head rcu;
 };
 
 struct cxl {
@@ -563,6 +571,9 @@ static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg
 u16 cxl_afu_cr_read16(struct cxl_afu *afu, int cr, u64 off);
 u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off);
 
+ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
+				loff_t off, size_t count);
+
 
 struct cxl_calls {
 	void (*cxl_slbia)(struct mm_struct *mm);
@@ -606,7 +617,7 @@ void cxl_release_psl_err_irq(struct cxl *adapter);
 int cxl_register_serr_irq(struct cxl_afu *afu);
 void cxl_release_serr_irq(struct cxl_afu *afu);
 int afu_register_irqs(struct cxl_context *ctx, u32 count);
-void afu_release_irqs(struct cxl_context *ctx);
+void afu_release_irqs(struct cxl_context *ctx, void *cookie);
 irqreturn_t cxl_slice_irq_err(int irq, void *data);
 
 int cxl_debugfs_init(void);
@@ -629,6 +640,10 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
 		     struct address_space *mapping);
 void cxl_context_free(struct cxl_context *ctx);
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
+unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
+			 irq_handler_t handler, void *cookie, const char *name);
+void cxl_unmap_irq(unsigned int virq, void *cookie);
+int __detach_context(struct cxl_context *ctx);
 
 /* This matches the layout of the H_COLLECT_CA_INT_INFO retbuf */
 struct cxl_irq_info {
@@ -642,6 +657,7 @@ struct cxl_irq_info {
 	u64 padding[3]; /* to match the expected retbuf size for plpar_hcall9 */
 };
 
+void cxl_assign_psn_space(struct cxl_context *ctx);
 int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed,
 			    u64 amr);
 int cxl_detach_process(struct cxl_context *ctx);
@@ -653,11 +669,23 @@ int cxl_check_error(struct cxl_afu *afu);
 int cxl_afu_slbia(struct cxl_afu *afu);
 int cxl_tlb_slb_invalidate(struct cxl *adapter);
 int cxl_afu_disable(struct cxl_afu *afu);
-int cxl_afu_reset(struct cxl_afu *afu);
+int __cxl_afu_reset(struct cxl_afu *afu);
+int cxl_afu_check_and_enable(struct cxl_afu *afu);
 int cxl_psl_purge(struct cxl_afu *afu);
 
 void cxl_stop_trace(struct cxl *cxl);
+int cxl_pci_vphb_add(struct cxl_afu *afu);
+void cxl_pci_vphb_remove(struct cxl_afu *afu);
 
 extern struct pci_driver cxl_pci_driver;
+int afu_allocate_irqs(struct cxl_context *ctx, u32 count);
+
+int afu_open(struct inode *inode, struct file *file);
+int afu_release(struct inode *inode, struct file *file);
+long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+int afu_mmap(struct file *file, struct vm_area_struct *vm);
+unsigned int afu_poll(struct file *file, struct poll_table_struct *poll);
+ssize_t afu_read(struct file *file, char __user *buf, size_t count, loff_t *off);
+extern const struct file_operations afu_fops;
 
 #endif
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 5286b8b704f5..25a5418c55cb 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -172,8 +172,8 @@ void cxl_handle_fault(struct work_struct *fault_work)
 		container_of(fault_work, struct cxl_context, fault_work);
 	u64 dsisr = ctx->dsisr;
 	u64 dar = ctx->dar;
-	struct task_struct *task;
-	struct mm_struct *mm;
+	struct task_struct *task = NULL;
+	struct mm_struct *mm = NULL;
 
 	if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr ||
 	    cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar ||
@@ -194,17 +194,19 @@ void cxl_handle_fault(struct work_struct *fault_work)
 	pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. "
 		"DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar);
 
-	if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
-		pr_devel("cxl_handle_fault unable to get task %i\n",
-			 pid_nr(ctx->pid));
-		cxl_ack_ae(ctx);
-		return;
-	}
-	if (!(mm = get_task_mm(task))) {
-		pr_devel("cxl_handle_fault unable to get mm %i\n",
-			 pid_nr(ctx->pid));
-		cxl_ack_ae(ctx);
-		goto out;
+	if (!ctx->kernel) {
+		if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) {
+			pr_devel("cxl_handle_fault unable to get task %i\n",
+				 pid_nr(ctx->pid));
+			cxl_ack_ae(ctx);
+			return;
+		}
+		if (!(mm = get_task_mm(task))) {
+			pr_devel("cxl_handle_fault unable to get mm %i\n",
+				 pid_nr(ctx->pid));
+			cxl_ack_ae(ctx);
+			goto out;
+		}
 	}
 
 	if (dsisr & CXL_PSL_DSISR_An_DS)
@@ -214,9 +216,11 @@ void cxl_handle_fault(struct work_struct *fault_work)
 	else
 		WARN(1, "cxl_handle_fault has nothing to handle\n");
 
-	mmput(mm);
+	if (mm)
+		mmput(mm);
 out:
-	put_task_struct(task);
+	if (task)
+		put_task_struct(task);
 }
 
 static void cxl_prefault_one(struct cxl_context *ctx, u64 ea)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 2364bcadb9a9..e3f4b69527a9 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -96,7 +96,8 @@ err_put_adapter:
 	put_device(&adapter->dev);
 	return rc;
 }
-static int afu_open(struct inode *inode, struct file *file)
+
+int afu_open(struct inode *inode, struct file *file)
 {
 	return __afu_open(inode, file, false);
 }
@@ -106,7 +107,7 @@ static int afu_master_open(struct inode *inode, struct file *file)
 	return __afu_open(inode, file, true);
 }
 
-static int afu_release(struct inode *inode, struct file *file)
+int afu_release(struct inode *inode, struct file *file)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -128,7 +129,6 @@ static int afu_release(struct inode *inode, struct file *file)
 	 */
 	cxl_context_free(ctx);
 
-	cxl_ctx_put();
 	return 0;
 }
 
@@ -191,7 +191,7 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 
 	if ((rc = cxl_attach_process(ctx, false, work.work_element_descriptor,
 				     amr))) {
-		afu_release_irqs(ctx);
+		afu_release_irqs(ctx, ctx);
 		goto out;
 	}
 
@@ -212,7 +212,26 @@ static long afu_ioctl_process_element(struct cxl_context *ctx,
 	return 0;
 }
 
-static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long afu_ioctl_get_afu_id(struct cxl_context *ctx,
+				 struct cxl_afu_id __user *upafuid)
+{
+	struct cxl_afu_id afuid = { 0 };
+
+	afuid.card_id = ctx->afu->adapter->adapter_num;
+	afuid.afu_offset = ctx->afu->slice;
+	afuid.afu_mode = ctx->afu->current_mode;
+
+	/* set the flag bit in case the afu is a slave */
+	if (ctx->afu->current_mode == CXL_MODE_DIRECTED && !ctx->master)
+		afuid.flags |= CXL_AFUID_FLAG_SLAVE;
+
+	if (copy_to_user(upafuid, &afuid, sizeof(afuid)))
+		return -EFAULT;
+
+	return 0;
+}
+
+long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -225,17 +244,20 @@ static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg);
 	case CXL_IOCTL_GET_PROCESS_ELEMENT:
 		return afu_ioctl_process_element(ctx, (__u32 __user *)arg);
+	case CXL_IOCTL_GET_AFU_ID:
+		return afu_ioctl_get_afu_id(ctx, (struct cxl_afu_id __user *)
+					    arg);
 	}
 	return -EINVAL;
 }
 
-static long afu_compat_ioctl(struct file *file, unsigned int cmd,
+long afu_compat_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	return afu_ioctl(file, cmd, arg);
 }
 
-static int afu_mmap(struct file *file, struct vm_area_struct *vm)
+int afu_mmap(struct file *file, struct vm_area_struct *vm)
 {
 	struct cxl_context *ctx = file->private_data;
 
@@ -246,7 +268,7 @@ static int afu_mmap(struct file *file, struct vm_area_struct *vm)
 	return cxl_context_iomap(ctx, vm);
 }
 
-static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
+unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
 {
 	struct cxl_context *ctx = file->private_data;
 	int mask = 0;
@@ -278,7 +300,7 @@ static inline int ctx_event_pending(struct cxl_context *ctx)
 	    ctx->pending_afu_err || (ctx->status == CLOSED));
 }
 
-static ssize_t afu_read(struct file *file, char __user *buf, size_t count,
+ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 			loff_t *off)
 {
 	struct cxl_context *ctx = file->private_data;
@@ -359,7 +381,11 @@ out:
 	return rc;
 }
 
-static const struct file_operations afu_fops = {
+/* 
+ * Note: if this is updated, we need to update api.c to patch the new ones in
+ * too
+ */
+const struct file_operations afu_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_open,
 	.poll		= afu_poll,
@@ -370,7 +396,7 @@ static const struct file_operations afu_fops = {
 	.mmap           = afu_mmap,
 };
 
-static const struct file_operations afu_master_fops = {
+const struct file_operations afu_master_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_master_open,
 	.poll		= afu_poll,
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index c8929c526691..680cd263436d 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -14,7 +14,7 @@
 #include <linux/slab.h>
 #include <linux/pid.h>
 #include <asm/cputable.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
@@ -416,9 +416,8 @@ void afu_irq_name_free(struct cxl_context *ctx)
 	}
 }
 
-int afu_register_irqs(struct cxl_context *ctx, u32 count)
+int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 {
-	irq_hw_number_t hwirq;
 	int rc, r, i, j = 1;
 	struct cxl_irq_name *irq_name;
 
@@ -458,6 +457,18 @@ int afu_register_irqs(struct cxl_context *ctx, u32 count)
 			j++;
 		}
 	}
+	return 0;
+
+out:
+	afu_irq_name_free(ctx);
+	return -ENOMEM;
+}
+
+void afu_register_hwirqs(struct cxl_context *ctx)
+{
+	irq_hw_number_t hwirq;
+	struct cxl_irq_name *irq_name;
+	int r,i;
 
 	/* We've allocated all memory now, so let's do the irq allocations */
 	irq_name = list_first_entry(&ctx->irq_names, struct cxl_irq_name, list);
@@ -469,15 +480,21 @@ int afu_register_irqs(struct cxl_context *ctx, u32 count)
 			irq_name = list_next_entry(irq_name, list);
 		}
 	}
+}
 
-	return 0;
+int afu_register_irqs(struct cxl_context *ctx, u32 count)
+{
+	int rc;
 
-out:
-	afu_irq_name_free(ctx);
-	return -ENOMEM;
-}
+	rc = afu_allocate_irqs(ctx, count);
+	if (rc)
+		return rc;
+
+	afu_register_hwirqs(ctx);
+	return 0;
+ }
 
-void afu_release_irqs(struct cxl_context *ctx)
+void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 {
 	irq_hw_number_t hwirq;
 	unsigned int virq;
@@ -488,7 +505,7 @@ void afu_release_irqs(struct cxl_context *ctx)
 		for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) {
 			virq = irq_find_mapping(NULL, hwirq);
 			if (virq)
-				cxl_unmap_irq(virq, ctx);
+				cxl_unmap_irq(virq, cookie);
 		}
 	}
 
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 8ccddceead66..833348e2c9cb 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -20,7 +20,7 @@
 #include <linux/idr.h>
 #include <linux/pci.h>
 #include <asm/cputable.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 29185fc61276..10567f245818 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -15,7 +15,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <asm/synch.h>
-#include <misc/cxl.h>
+#include <misc/cxl-base.h>
 
 #include "cxl.h"
 #include "trace.h"
@@ -73,7 +73,7 @@ int cxl_afu_disable(struct cxl_afu *afu)
 }
 
 /* This will disable as well as reset */
-int cxl_afu_reset(struct cxl_afu *afu)
+int __cxl_afu_reset(struct cxl_afu *afu)
 {
 	pr_devel("AFU reset request\n");
 
@@ -83,7 +83,7 @@ int cxl_afu_reset(struct cxl_afu *afu)
 			   false);
 }
 
-static int afu_check_and_enable(struct cxl_afu *afu)
+int cxl_afu_check_and_enable(struct cxl_afu *afu)
 {
 	if (afu->enabled)
 		return 0;
@@ -379,7 +379,7 @@ static int remove_process_element(struct cxl_context *ctx)
 }
 
 
-static void assign_psn_space(struct cxl_context *ctx)
+void cxl_assign_psn_space(struct cxl_context *ctx)
 {
 	if (!ctx->afu->pp_size || ctx->master) {
 		ctx->psn_phys = ctx->afu->psn_phys;
@@ -430,34 +430,46 @@ err:
 #define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE))
 #endif
 
+static u64 calculate_sr(struct cxl_context *ctx)
+{
+	u64 sr = 0;
+
+	if (ctx->master)
+		sr |= CXL_PSL_SR_An_MP;
+	if (mfspr(SPRN_LPCR) & LPCR_TC)
+		sr |= CXL_PSL_SR_An_TC;
+	if (ctx->kernel) {
+		sr |= CXL_PSL_SR_An_R | (mfmsr() & MSR_SF);
+		sr |= CXL_PSL_SR_An_HV;
+	} else {
+		sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
+		set_endian(sr);
+		sr &= ~(CXL_PSL_SR_An_HV);
+		if (!test_tsk_thread_flag(current, TIF_32BIT))
+			sr |= CXL_PSL_SR_An_SF;
+	}
+	return sr;
+}
+
 static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 {
-	u64 sr;
+	u32 pid;
 	int r, result;
 
-	assign_psn_space(ctx);
+	cxl_assign_psn_space(ctx);
 
 	ctx->elem->ctxtime = 0; /* disable */
 	ctx->elem->lpid = cpu_to_be32(mfspr(SPRN_LPID));
 	ctx->elem->haurp = 0; /* disable */
 	ctx->elem->sdr = cpu_to_be64(mfspr(SPRN_SDR1));
 
-	sr = 0;
-	if (ctx->master)
-		sr |= CXL_PSL_SR_An_MP;
-	if (mfspr(SPRN_LPCR) & LPCR_TC)
-		sr |= CXL_PSL_SR_An_TC;
-	/* HV=0, PR=1, R=1 for userspace
-	 * For kernel contexts: this would need to change
-	 */
-	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
-	set_endian(sr);
-	sr &= ~(CXL_PSL_SR_An_HV);
-	if (!test_tsk_thread_flag(current, TIF_32BIT))
-		sr |= CXL_PSL_SR_An_SF;
-	ctx->elem->common.pid = cpu_to_be32(current->pid);
+	pid = current->pid;
+	if (ctx->kernel)
+		pid = 0;
 	ctx->elem->common.tid = 0;
-	ctx->elem->sr = cpu_to_be64(sr);
+	ctx->elem->common.pid = cpu_to_be32(pid);
+
+	ctx->elem->sr = cpu_to_be64(calculate_sr(ctx));
 
 	ctx->elem->common.csrp = 0; /* disable */
 	ctx->elem->common.aurp0 = 0; /* disable */
@@ -477,7 +489,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 	ctx->elem->common.wed = cpu_to_be64(wed);
 
 	/* first guy needs to enable */
-	if ((result = afu_check_and_enable(ctx->afu)))
+	if ((result = cxl_afu_check_and_enable(ctx->afu)))
 		return result;
 
 	add_process_element(ctx);
@@ -495,7 +507,7 @@ static int deactivate_afu_directed(struct cxl_afu *afu)
 	cxl_sysfs_afu_m_remove(afu);
 	cxl_chardev_afu_remove(afu);
 
-	cxl_afu_reset(afu);
+	__cxl_afu_reset(afu);
 	cxl_afu_disable(afu);
 	cxl_psl_purge(afu);
 
@@ -530,20 +542,15 @@ static int activate_dedicated_process(struct cxl_afu *afu)
 static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 {
 	struct cxl_afu *afu = ctx->afu;
-	u64 sr;
+	u64 pid;
 	int rc;
 
-	sr = 0;
-	set_endian(sr);
-	if (ctx->master)
-		sr |= CXL_PSL_SR_An_MP;
-	if (mfspr(SPRN_LPCR) & LPCR_TC)
-		sr |= CXL_PSL_SR_An_TC;
-	sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
-	if (!test_tsk_thread_flag(current, TIF_32BIT))
-		sr |= CXL_PSL_SR_An_SF;
-	cxl_p2n_write(afu, CXL_PSL_PID_TID_An, (u64)current->pid << 32);
-	cxl_p1n_write(afu, CXL_PSL_SR_An, sr);
+	pid = (u64)current->pid << 32;
+	if (ctx->kernel)
+		pid = 0;
+	cxl_p2n_write(afu, CXL_PSL_PID_TID_An, pid);
+
+	cxl_p1n_write(afu, CXL_PSL_SR_An, calculate_sr(ctx));
 
 	if ((rc = cxl_write_sstp(afu, ctx->sstp0, ctx->sstp1)))
 		return rc;
@@ -564,9 +571,9 @@ static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
 	cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
 
 	/* master only context for dedicated */
-	assign_psn_space(ctx);
+	cxl_assign_psn_space(ctx);
 
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		return rc;
 
 	cxl_p2n_write(afu, CXL_PSL_WED_An, wed);
@@ -629,7 +636,7 @@ int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr)
 
 static inline int detach_process_native_dedicated(struct cxl_context *ctx)
 {
-	cxl_afu_reset(ctx->afu);
+	__cxl_afu_reset(ctx->afu);
 	cxl_afu_disable(ctx->afu);
 	cxl_psl_purge(ctx->afu);
 	return 0;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 1ef01647265f..c68ef5806dbe 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -90,6 +90,7 @@
 /* This works a little different than the p1/p2 register accesses to make it
  * easier to pull out individual fields */
 #define AFUD_READ(afu, off)		in_be64(afu->afu_desc_mmio + off)
+#define AFUD_READ_LE(afu, off)		in_le64(afu->afu_desc_mmio + off)
 #define EXTRACT_PPC_BIT(val, bit)	(!!(val & PPC_BIT(bit)))
 #define EXTRACT_PPC_BITS(val, bs, be)	((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be))
 
@@ -204,7 +205,7 @@ static void dump_cxl_config_space(struct pci_dev *dev)
 	dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n",
 		p1_base(dev), p1_size(dev));
 	dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n",
-		p1_base(dev), p2_size(dev));
+		p2_base(dev), p2_size(dev));
 	dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n",
 		pci_resource_start(dev, 4), pci_resource_len(dev, 4));
 
@@ -286,7 +287,8 @@ static void dump_cxl_config_space(struct pci_dev *dev)
 
 static void dump_afu_descriptor(struct cxl_afu *afu)
 {
-	u64 val;
+	u64 val, afu_cr_num, afu_cr_off, afu_cr_len;
+	int i;
 
 #define show_reg(name, what) \
 	dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what)
@@ -296,6 +298,7 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	show_reg("num_of_processes", AFUD_NUM_PROCS(val));
 	show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val));
 	show_reg("req_prog_mode", val & 0xffffULL);
+	afu_cr_num = AFUD_NUM_CRS(val);
 
 	val = AFUD_READ(afu, 0x8);
 	show_reg("Reserved", val);
@@ -307,8 +310,10 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	val = AFUD_READ_CR(afu);
 	show_reg("Reserved", (val >> (63-7)) & 0xff);
 	show_reg("AFU_CR_len", AFUD_CR_LEN(val));
+	afu_cr_len = AFUD_CR_LEN(val) * 256;
 
 	val = AFUD_READ_CR_OFF(afu);
+	afu_cr_off = val;
 	show_reg("AFU_CR_offset", val);
 
 	val = AFUD_READ_PPPSA(afu);
@@ -325,6 +330,11 @@ static void dump_afu_descriptor(struct cxl_afu *afu)
 	val = AFUD_READ_EB_OFF(afu);
 	show_reg("AFU_EB_offset", val);
 
+	for (i = 0; i < afu_cr_num; i++) {
+		val = AFUD_READ_LE(afu, afu_cr_off + i * afu_cr_len);
+		show_reg("CR Vendor", val & 0xffff);
+		show_reg("CR Device", (val >> 16) & 0xffff);
+	}
 #undef show_reg
 }
 
@@ -593,6 +603,22 @@ static int cxl_read_afu_descriptor(struct cxl_afu *afu)
 	afu->crs_len = AFUD_CR_LEN(val) * 256;
 	afu->crs_offset = AFUD_READ_CR_OFF(afu);
 
+
+	/* eb_len is in multiple of 4K */
+	afu->eb_len = AFUD_EB_LEN(AFUD_READ_EB(afu)) * 4096;
+	afu->eb_offset = AFUD_READ_EB_OFF(afu);
+
+	/* eb_off is 4K aligned so lower 12 bits are always zero */
+	if (EXTRACT_PPC_BITS(afu->eb_offset, 0, 11) != 0) {
+		dev_warn(&afu->dev,
+			 "Invalid AFU error buffer offset %Lx\n",
+			 afu->eb_offset);
+		dev_info(&afu->dev,
+			 "Ignoring AFU error buffer in the descriptor\n");
+		/* indicate that no afu buffer exists */
+		afu->eb_len = 0;
+	}
+
 	return 0;
 }
 
@@ -631,7 +657,7 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
 	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
 		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg);
-		if (cxl_afu_reset(afu))
+		if (__cxl_afu_reset(afu))
 			return -EIO;
 		if (cxl_afu_disable(afu))
 			return -EIO;
@@ -672,6 +698,50 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	return 0;
 }
 
+#define ERR_BUFF_MAX_COPY_SIZE PAGE_SIZE
+/*
+ * afu_eb_read:
+ * Called from sysfs and reads the afu error info buffer. The h/w only supports
+ * 4/8 bytes aligned access. So in case the requested offset/count arent 8 byte
+ * aligned the function uses a bounce buffer which can be max PAGE_SIZE.
+ */
+ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
+				loff_t off, size_t count)
+{
+	loff_t aligned_start, aligned_end;
+	size_t aligned_length;
+	void *tbuf;
+	const void __iomem *ebuf = afu->afu_desc_mmio + afu->eb_offset;
+
+	if (count == 0 || off < 0 || (size_t)off >= afu->eb_len)
+		return 0;
+
+	/* calculate aligned read window */
+	count = min((size_t)(afu->eb_len - off), count);
+	aligned_start = round_down(off, 8);
+	aligned_end = round_up(off + count, 8);
+	aligned_length = aligned_end - aligned_start;
+
+	/* max we can copy in one read is PAGE_SIZE */
+	if (aligned_length > ERR_BUFF_MAX_COPY_SIZE) {
+		aligned_length = ERR_BUFF_MAX_COPY_SIZE;
+		count = ERR_BUFF_MAX_COPY_SIZE - (off & 0x7);
+	}
+
+	/* use bounce buffer for copy */
+	tbuf = (void *)__get_free_page(GFP_TEMPORARY);
+	if (!tbuf)
+		return -ENOMEM;
+
+	/* perform aligned read from the mmio region */
+	memcpy_fromio(tbuf, ebuf + aligned_start, aligned_length);
+	memcpy(buf, tbuf + (off & 0x7), count);
+
+	free_page((unsigned long)tbuf);
+
+	return count;
+}
+
 static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 {
 	struct cxl_afu *afu;
@@ -691,7 +761,7 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 		goto err2;
 
 	/* We need to reset the AFU before we can read the AFU descriptor */
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		goto err2;
 
 	if (cxl_verbose)
@@ -731,6 +801,9 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 
 	adapter->afu[afu->slice] = afu;
 
+	if ((rc = cxl_pci_vphb_add(afu)))
+		dev_info(&afu->dev, "Can't register vPHB\n");
+
 	return 0;
 
 err_put2:
@@ -783,8 +856,10 @@ int cxl_reset(struct cxl *adapter)
 
 	dev_info(&dev->dev, "CXL reset\n");
 
-	for (i = 0; i < adapter->slices; i++)
+	for (i = 0; i < adapter->slices; i++) {
+		cxl_pci_vphb_remove(adapter->afu[i]);
 		cxl_remove_afu(adapter->afu[i]);
+	}
 
 	/* pcie_warm_reset requests a fundamental pci reset which includes a
 	 * PERST assert/deassert.  PERST triggers a loading of the image
@@ -857,13 +932,13 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
 	u8 image_state;
 
 	if (!(vsec = find_cxl_vsec(dev))) {
-		dev_err(&adapter->dev, "ABORTING: CXL VSEC not found!\n");
+		dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n");
 		return -ENODEV;
 	}
 
 	CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen);
 	if (vseclen < CXL_VSEC_MIN_SIZE) {
-		pr_err("ABORTING: CXL VSEC too short\n");
+		dev_err(&dev->dev, "ABORTING: CXL VSEC too short\n");
 		return -EINVAL;
 	}
 
@@ -902,24 +977,24 @@ static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev)
 		return -EBUSY;
 
 	if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) {
-		dev_err(&adapter->dev, "ABORTING: CXL requires unsupported features\n");
+		dev_err(&dev->dev, "ABORTING: CXL requires unsupported features\n");
 		return -EINVAL;
 	}
 
 	if (!adapter->slices) {
 		/* Once we support dynamic reprogramming we can use the card if
 		 * it supports loadable AFUs */
-		dev_err(&adapter->dev, "ABORTING: Device has no AFUs\n");
+		dev_err(&dev->dev, "ABORTING: Device has no AFUs\n");
 		return -EINVAL;
 	}
 
 	if (!adapter->afu_desc_off || !adapter->afu_desc_size) {
-		dev_err(&adapter->dev, "ABORTING: VSEC shows no AFU descriptors\n");
+		dev_err(&dev->dev, "ABORTING: VSEC shows no AFU descriptors\n");
 		return -EINVAL;
 	}
 
 	if (adapter->ps_size > p2_size(dev) - adapter->ps_off) {
-		dev_err(&adapter->dev, "ABORTING: Problem state size larger than "
+		dev_err(&dev->dev, "ABORTING: Problem state size larger than "
 				   "available in BAR2: 0x%llx > 0x%llx\n",
 			 adapter->ps_size, p2_size(dev) - adapter->ps_off);
 		return -EINVAL;
@@ -968,6 +1043,15 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	if (!(adapter = cxl_alloc_adapter(dev)))
 		return ERR_PTR(-ENOMEM);
 
+	if ((rc = cxl_read_vsec(adapter, dev)))
+		goto err1;
+
+	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
+		goto err1;
+
+	if ((rc = setup_cxl_bars(dev)))
+		goto err1;
+
 	if ((rc = switch_card_to_cxl(dev)))
 		goto err1;
 
@@ -977,12 +1061,6 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num)))
 		goto err2;
 
-	if ((rc = cxl_read_vsec(adapter, dev)))
-		goto err2;
-
-	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
-		goto err2;
-
 	if ((rc = cxl_update_image_control(adapter)))
 		goto err2;
 
@@ -1067,9 +1145,6 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (cxl_verbose)
 		dump_cxl_config_space(dev);
 
-	if ((rc = setup_cxl_bars(dev)))
-		return rc;
-
 	if ((rc = pci_enable_device(dev))) {
 		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
 		return rc;
@@ -1078,6 +1153,7 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	adapter = cxl_init_adapter(dev);
 	if (IS_ERR(adapter)) {
 		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
+		pci_disable_device(dev);
 		return PTR_ERR(adapter);
 	}
 
@@ -1092,16 +1168,18 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 static void cxl_remove(struct pci_dev *dev)
 {
 	struct cxl *adapter = pci_get_drvdata(dev);
-	int afu;
-
-	dev_warn(&dev->dev, "pci remove\n");
+	struct cxl_afu *afu;
+	int i;
 
 	/*
 	 * Lock to prevent someone grabbing a ref through the adapter list as
 	 * we are removing it
 	 */
-	for (afu = 0; afu < adapter->slices; afu++)
-		cxl_remove_afu(adapter->afu[afu]);
+	for (i = 0; i < adapter->slices; i++) {
+		afu = adapter->afu[i];
+		cxl_pci_vphb_remove(afu);
+		cxl_remove_afu(afu);
+	}
 	cxl_remove_adapter(adapter);
 }
 
@@ -1110,4 +1188,5 @@ struct pci_driver cxl_pci_driver = {
 	.id_table = cxl_pci_tbl,
 	.probe = cxl_probe,
 	.remove = cxl_remove,
+	.shutdown = cxl_remove,
 };
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index d0c38c7bc0c4..31f38bc71a3d 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -185,7 +185,7 @@ static ssize_t reset_store_afu(struct device *device,
 		goto err;
 	}
 
-	if ((rc = cxl_afu_reset(afu)))
+	if ((rc = __cxl_afu_reset(afu)))
 		goto err;
 
 	rc = count;
@@ -356,6 +356,16 @@ static ssize_t api_version_compatible_show(struct device *device,
 	return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION_COMPATIBLE);
 }
 
+static ssize_t afu_eb_read(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr, char *buf,
+			       loff_t off, size_t count)
+{
+	struct cxl_afu *afu = to_cxl_afu(container_of(kobj,
+						      struct device, kobj));
+
+	return cxl_afu_read_err_buffer(afu, buf, off, count);
+}
+
 static struct device_attribute afu_attrs[] = {
 	__ATTR_RO(mmio_size),
 	__ATTR_RO(irqs_min),
@@ -534,6 +544,10 @@ void cxl_sysfs_afu_remove(struct cxl_afu *afu)
 	struct afu_config_record *cr, *tmp;
 	int i;
 
+	/* remove the err buffer bin attribute */
+	if (afu->eb_len)
+		device_remove_bin_file(&afu->dev, &afu->attr_eb);
+
 	for (i = 0; i < ARRAY_SIZE(afu_attrs); i++)
 		device_remove_file(&afu->dev, &afu_attrs[i]);
 
@@ -555,6 +569,22 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu)
 			goto err;
 	}
 
+	/* conditionally create the add the binary file for error info buffer */
+	if (afu->eb_len) {
+		afu->attr_eb.attr.name = "afu_err_buff";
+		afu->attr_eb.attr.mode = S_IRUGO;
+		afu->attr_eb.size = afu->eb_len;
+		afu->attr_eb.read = afu_eb_read;
+
+		rc = device_create_bin_file(&afu->dev, &afu->attr_eb);
+		if (rc) {
+			dev_err(&afu->dev,
+				"Unable to create eb attr for the afu. Err(%d)\n",
+				rc);
+			goto err;
+		}
+	}
+
 	for (i = 0; i < afu->crs_num; i++) {
 		cr = cxl_sysfs_afu_new_cr(afu, i);
 		if (IS_ERR(cr)) {
@@ -570,6 +600,9 @@ err1:
 	cxl_sysfs_afu_remove(afu);
 	return rc;
 err:
+	/* reset the eb_len as we havent created the bin attr */
+	afu->eb_len = 0;
+
 	for (i--; i >= 0; i--)
 		device_remove_file(&afu->dev, &afu_attrs[i]);
 	return rc;
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
new file mode 100644
index 000000000000..b1d1983a84a5
--- /dev/null
+++ b/drivers/misc/cxl/vphb.c
@@ -0,0 +1,270 @@
+/*
+ * Copyright 2014 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/pci.h>
+#include <misc/cxl.h>
+#include "cxl.h"
+
+static int cxl_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
+{
+	if (dma_mask < DMA_BIT_MASK(64)) {
+		pr_info("%s only 64bit DMA supported on CXL", __func__);
+		return -EIO;
+	}
+
+	*(pdev->dev.dma_mask) = dma_mask;
+	return 0;
+}
+
+static int cxl_pci_probe_mode(struct pci_bus *bus)
+{
+	return PCI_PROBE_NORMAL;
+}
+
+static int cxl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	return -ENODEV;
+}
+
+static void cxl_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	/*
+	 * MSI should never be set but need still need to provide this call
+	 * back.
+	 */
+}
+
+static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
+{
+	struct pci_controller *phb;
+	struct cxl_afu *afu;
+	struct cxl_context *ctx;
+
+	phb = pci_bus_to_host(dev->bus);
+	afu = (struct cxl_afu *)phb->private_data;
+	set_dma_ops(&dev->dev, &dma_direct_ops);
+	set_dma_offset(&dev->dev, PAGE_OFFSET);
+
+	/*
+	 * Allocate a context to do cxl things too.  If we eventually do real
+	 * DMA ops, we'll need a default context to attach them to
+	 */
+	ctx = cxl_dev_context_init(dev);
+	if (!ctx)
+		return false;
+	dev->dev.archdata.cxl_ctx = ctx;
+
+	return (cxl_afu_check_and_enable(afu) == 0);
+}
+
+static void cxl_pci_disable_device(struct pci_dev *dev)
+{
+	struct cxl_context *ctx = cxl_get_context(dev);
+
+	if (ctx) {
+		if (ctx->status == STARTED) {
+			dev_err(&dev->dev, "Default context started\n");
+			return;
+		}
+		dev->dev.archdata.cxl_ctx = NULL;
+		cxl_release_context(ctx);
+	}
+}
+
+static resource_size_t cxl_pci_window_alignment(struct pci_bus *bus,
+						unsigned long type)
+{
+	return 1;
+}
+
+static void cxl_pci_reset_secondary_bus(struct pci_dev *dev)
+{
+	/* Should we do an AFU reset here ? */
+}
+
+static int cxl_pcie_cfg_record(u8 bus, u8 devfn)
+{
+	return (bus << 8) + devfn;
+}
+
+static unsigned long cxl_pcie_cfg_addr(struct pci_controller* phb,
+				       u8 bus, u8 devfn, int offset)
+{
+	int record = cxl_pcie_cfg_record(bus, devfn);
+
+	return (unsigned long)phb->cfg_addr + ((unsigned long)phb->cfg_data * record) + offset;
+}
+
+
+static int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn,
+				int offset, int len,
+				volatile void __iomem **ioaddr,
+				u32 *mask, int *shift)
+{
+	struct pci_controller *phb;
+	struct cxl_afu *afu;
+	unsigned long addr;
+
+	phb = pci_bus_to_host(bus);
+	afu = (struct cxl_afu *)phb->private_data;
+	if (phb == NULL)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (cxl_pcie_cfg_record(bus->number, devfn) > afu->crs_num)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (offset >= (unsigned long)phb->cfg_data)
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	addr = cxl_pcie_cfg_addr(phb, bus->number, devfn, offset);
+
+	*ioaddr = (void *)(addr & ~0x3ULL);
+	*shift = ((addr & 0x3) * 8);
+	switch (len) {
+	case 1:
+		*mask = 0xff;
+		break;
+	case 2:
+		*mask = 0xffff;
+		break;
+	default:
+		*mask = 0xffffffff;
+		break;
+	}
+	return 0;
+}
+
+static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+				int offset, int len, u32 *val)
+{
+	volatile void __iomem *ioaddr;
+	int shift, rc;
+	u32 mask;
+
+	rc = cxl_pcie_config_info(bus, devfn, offset, len, &ioaddr,
+				  &mask, &shift);
+	if (rc)
+		return rc;
+
+	/* Can only read 32 bits */
+	*val = (in_le32(ioaddr) >> shift) & mask;
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+				 int offset, int len, u32 val)
+{
+	volatile void __iomem *ioaddr;
+	u32 v, mask;
+	int shift, rc;
+
+	rc = cxl_pcie_config_info(bus, devfn, offset, len, &ioaddr,
+				  &mask, &shift);
+	if (rc)
+		return rc;
+
+	/* Can only write 32 bits so do read-modify-write */
+	mask <<= shift;
+	val <<= shift;
+
+	v = (in_le32(ioaddr) & ~mask) || (val & mask);
+
+	out_le32(ioaddr, v);
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops cxl_pcie_pci_ops =
+{
+	.read = cxl_pcie_read_config,
+	.write = cxl_pcie_write_config,
+};
+
+
+static struct pci_controller_ops cxl_pci_controller_ops =
+{
+	.probe_mode = cxl_pci_probe_mode,
+	.enable_device_hook = cxl_pci_enable_device_hook,
+	.disable_device = cxl_pci_disable_device,
+	.release_device = cxl_pci_disable_device,
+	.window_alignment = cxl_pci_window_alignment,
+	.reset_secondary_bus = cxl_pci_reset_secondary_bus,
+	.setup_msi_irqs = cxl_setup_msi_irqs,
+	.teardown_msi_irqs = cxl_teardown_msi_irqs,
+	.dma_set_mask = cxl_dma_set_mask,
+};
+
+int cxl_pci_vphb_add(struct cxl_afu *afu)
+{
+	struct pci_dev *phys_dev;
+	struct pci_controller *phb, *phys_phb;
+
+	phys_dev = to_pci_dev(afu->adapter->dev.parent);
+	phys_phb = pci_bus_to_host(phys_dev->bus);
+
+	/* Alloc and setup PHB data structure */
+	phb = pcibios_alloc_controller(phys_phb->dn);
+
+	if (!phb)
+		return -ENODEV;
+
+	/* Setup parent in sysfs */
+	phb->parent = &phys_dev->dev;
+
+	/* Setup the PHB using arch provided callback */
+	phb->ops = &cxl_pcie_pci_ops;
+	phb->cfg_addr = afu->afu_desc_mmio + afu->crs_offset;
+	phb->cfg_data = (void *)(u64)afu->crs_len;
+	phb->private_data = afu;
+	phb->controller_ops = cxl_pci_controller_ops;
+
+	/* Scan the bus */
+	pcibios_scan_phb(phb);
+	if (phb->bus == NULL)
+		return -ENXIO;
+
+	/* Claim resources. This might need some rework as well depending
+	 * whether we are doing probe-only or not, like assigning unassigned
+	 * resources etc...
+	 */
+	pcibios_claim_one_bus(phb->bus);
+
+	/* Add probed PCI devices to the device model */
+	pci_bus_add_devices(phb->bus);
+
+	afu->phb = phb;
+
+	return 0;
+}
+
+
+void cxl_pci_vphb_remove(struct cxl_afu *afu)
+{
+	struct pci_controller *phb;
+
+	/* If there is no configuration record we won't have one of these */
+	if (!afu || !afu->phb)
+		return;
+
+	phb = afu->phb;
+
+	pci_remove_root_bus(phb->bus);
+}
+
+struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev)
+{
+	struct pci_controller *phb;
+
+	phb = pci_bus_to_host(dev->bus);
+
+	return (struct cxl_afu *)phb->private_data;
+}
+EXPORT_SYMBOL_GPL(cxl_pci_to_afu);
+
+unsigned int cxl_pci_to_cfg_record(struct pci_dev *dev)
+{
+	return cxl_pcie_cfg_record(dev->bus->number, dev->devfn);
+}
+EXPORT_SYMBOL_GPL(cxl_pci_to_cfg_record);
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 2c25271f8c41..c9c3d20b784b 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -913,6 +913,9 @@ static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
 		if (!err)
 			break;
 
+		/* Re-tune if needed */
+		mmc_retune_recheck(card->host);
+
 		prev_cmd_status_valid = false;
 		pr_err("%s: error %d sending status command, %sing\n",
 		       req->rq_disk->disk_name, err, retry ? "retry" : "abort");
@@ -1029,6 +1032,18 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
 	md->reset_done &= ~type;
 }
 
+int mmc_access_rpmb(struct mmc_queue *mq)
+{
+	struct mmc_blk_data *md = mq->data;
+	/*
+	 * If this is a RPMB partition access, return ture
+	 */
+	if (md && md->part_type == EXT_CSD_PART_CONFIG_ACC_RPMB)
+		return true;
+
+	return false;
+}
+
 static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 {
 	struct mmc_blk_data *md = mq->data;
@@ -1192,6 +1207,7 @@ static int mmc_blk_err_check(struct mmc_card *card,
 						    mmc_active);
 	struct mmc_blk_request *brq = &mq_mrq->brq;
 	struct request *req = mq_mrq->req;
+	int need_retune = card->host->need_retune;
 	int ecc_err = 0, gen_err = 0;
 
 	/*
@@ -1259,6 +1275,12 @@ static int mmc_blk_err_check(struct mmc_card *card,
 	}
 
 	if (brq->data.error) {
+		if (need_retune && !brq->retune_retry_done) {
+			pr_info("%s: retrying because a re-tune was needed\n",
+				req->rq_disk->disk_name);
+			brq->retune_retry_done = 1;
+			return MMC_BLK_RETRY;
+		}
 		pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n",
 		       req->rq_disk->disk_name, brq->data.error,
 		       (unsigned)blk_rq_pos(req),
@@ -1818,7 +1840,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 	struct mmc_blk_data *md = mq->data;
 	struct mmc_card *card = md->queue.card;
 	struct mmc_blk_request *brq = &mq->mqrq_cur->brq;
-	int ret = 1, disable_multi = 0, retry = 0, type;
+	int ret = 1, disable_multi = 0, retry = 0, type, retune_retry_done = 0;
 	enum mmc_blk_status status;
 	struct mmc_queue_req *mq_rq;
 	struct request *req = rqc;
@@ -1898,10 +1920,13 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			break;
 		case MMC_BLK_CMD_ERR:
 			ret = mmc_blk_cmd_err(md, card, brq, req, ret);
-			if (!mmc_blk_reset(md, card->host, type))
-				break;
-			goto cmd_abort;
+			if (mmc_blk_reset(md, card->host, type))
+				goto cmd_abort;
+			if (!ret)
+				goto start_new_req;
+			break;
 		case MMC_BLK_RETRY:
+			retune_retry_done = brq->retune_retry_done;
 			if (retry++ < 5)
 				break;
 			/* Fall through */
@@ -1964,6 +1989,7 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 				mmc_start_req(card->host,
 						&mq_rq->mmc_active, NULL);
 			}
+			mq_rq->brq.retune_retry_done = retune_retry_done;
 		}
 	} while (ret);
 
@@ -2205,7 +2231,8 @@ static struct mmc_blk_data *mmc_blk_alloc(struct mmc_card *card)
 		 * The CSD capacity field is in units of read_blkbits.
 		 * set_capacity takes units of 512 bytes.
 		 */
-		size = card->csd.capacity << (card->csd.read_blkbits - 9);
+		size = (typeof(sector_t))card->csd.capacity
+			<< (card->csd.read_blkbits - 9);
 	}
 
 	return mmc_blk_alloc_req(card, &card->dev, size, false, NULL,
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 53b741398b93..b78cf5d403a3 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -268,8 +268,6 @@ static int mmc_test_wait_busy(struct mmc_test_card *test)
 static int mmc_test_buffer_transfer(struct mmc_test_card *test,
 	u8 *buffer, unsigned addr, unsigned blksz, int write)
 {
-	int ret;
-
 	struct mmc_request mrq = {0};
 	struct mmc_command cmd = {0};
 	struct mmc_command stop = {0};
@@ -292,11 +290,7 @@ static int mmc_test_buffer_transfer(struct mmc_test_card *test,
 	if (data.error)
 		return data.error;
 
-	ret = mmc_test_wait_busy(test);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_wait_busy(test);
 }
 
 static void mmc_test_free_mem(struct mmc_test_mem *mem)
@@ -826,9 +820,7 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 				mmc_test_nonblock_reset(&mrq1, &cmd1,
 							&stop1, &data1);
 		}
-		done_areq = cur_areq;
-		cur_areq = other_areq;
-		other_areq = done_areq;
+		swap(cur_areq, other_areq);
 		dev_addr += blocks;
 	}
 
@@ -994,11 +986,7 @@ static int mmc_test_basic_write(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_basic_read(struct mmc_test_card *test)
@@ -1012,44 +1000,29 @@ static int mmc_test_basic_read(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_simple_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_verify_write(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_verify_read(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_one(&sg, test->buffer, 512);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_multi_write(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1066,16 +1039,11 @@ static int mmc_test_multi_write(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
 }
 
 static int mmc_test_multi_read(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1092,11 +1060,7 @@ static int mmc_test_multi_read(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
 }
 
 static int mmc_test_pow2_write(struct mmc_test_card *test)
@@ -1263,11 +1227,7 @@ static int mmc_test_xfersize_write(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 1, 512, 1);
 }
 
 static int mmc_test_xfersize_read(struct mmc_test_card *test)
@@ -1278,11 +1238,7 @@ static int mmc_test_xfersize_read(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 1, 512, 0);
 }
 
 static int mmc_test_multi_xfersize_write(struct mmc_test_card *test)
@@ -1296,11 +1252,7 @@ static int mmc_test_multi_xfersize_write(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 2, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 2, 512, 1);
 }
 
 static int mmc_test_multi_xfersize_read(struct mmc_test_card *test)
@@ -1314,48 +1266,33 @@ static int mmc_test_multi_xfersize_read(struct mmc_test_card *test)
 	if (ret)
 		return ret;
 
-	ret = mmc_test_broken_transfer(test, 2, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_broken_transfer(test, 2, 512, 0);
 }
 
 #ifdef CONFIG_HIGHMEM
 
 static int mmc_test_write_high(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, 512, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 1);
 }
 
 static int mmc_test_read_high(struct mmc_test_card *test)
 {
-	int ret;
 	struct scatterlist sg;
 
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, 512, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, 1, 512, 0);
 }
 
 static int mmc_test_multi_write_high(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1373,16 +1310,11 @@ static int mmc_test_multi_write_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
 }
 
 static int mmc_test_multi_read_high(struct mmc_test_card *test)
 {
-	int ret;
 	unsigned int size;
 	struct scatterlist sg;
 
@@ -1400,11 +1332,7 @@ static int mmc_test_multi_read_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
-	if (ret)
-		return ret;
-
-	return 0;
+	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
 }
 
 #else
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index 236d194c2883..b5a2b145d89f 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -38,7 +38,7 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 		return BLKPREP_KILL;
 	}
 
-	if (mq && mmc_card_removed(mq->card))
+	if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
 		return BLKPREP_KILL;
 
 	req->cmd_flags |= REQ_DONTPREP;
@@ -56,7 +56,6 @@ static int mmc_queue_thread(void *d)
 	down(&mq->thread_sem);
 	do {
 		struct request *req = NULL;
-		struct mmc_queue_req *tmp;
 		unsigned int cmd_flags = 0;
 
 		spin_lock_irq(q->queue_lock);
@@ -69,6 +68,7 @@ static int mmc_queue_thread(void *d)
 			set_current_state(TASK_RUNNING);
 			cmd_flags = req ? req->cmd_flags : 0;
 			mq->issue_fn(mq, req);
+			cond_resched();
 			if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
 				mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
 				continue; /* fetch again */
@@ -86,9 +86,7 @@ static int mmc_queue_thread(void *d)
 
 			mq->mqrq_prev->brq.mrq.data = NULL;
 			mq->mqrq_prev->req = NULL;
-			tmp = mq->mqrq_prev;
-			mq->mqrq_prev = mq->mqrq_cur;
-			mq->mqrq_cur = tmp;
+			swap(mq->mqrq_prev, mq->mqrq_cur);
 		} else {
 			if (kthread_should_stop()) {
 				set_current_state(TASK_RUNNING);
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index 5752d50049a3..36cddab57d77 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -12,6 +12,7 @@ struct mmc_blk_request {
 	struct mmc_command	cmd;
 	struct mmc_command	stop;
 	struct mmc_data		data;
+	int			retune_retry_done;
 };
 
 enum mmc_packed_type {
@@ -73,4 +74,6 @@ extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 extern int mmc_packed_init(struct mmc_queue *, struct mmc_card *);
 extern void mmc_packed_clean(struct mmc_queue *);
 
+extern int mmc_access_rpmb(struct mmc_queue *);
+
 #endif
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index c296bc098fe2..9ad73f30f744 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -133,6 +133,12 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 	struct mmc_command *cmd = mrq->cmd;
 	int err = cmd->error;
 
+	/* Flag re-tuning needed on CRC errors */
+	if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+	    (mrq->data && mrq->data->error == -EILSEQ) ||
+	    (mrq->stop && mrq->stop->error == -EILSEQ))
+		mmc_retune_needed(host);
+
 	if (err && cmd->retries && mmc_host_is_spi(host)) {
 		if (cmd->resp[0] & R1_SPI_ILLEGAL_COMMAND)
 			cmd->retries = 0;
@@ -186,12 +192,29 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 
 EXPORT_SYMBOL(mmc_request_done);
 
+static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
+{
+	int err;
+
+	/* Assumes host controller has been runtime resumed by mmc_claim_host */
+	err = mmc_retune(host);
+	if (err) {
+		mrq->cmd->error = err;
+		mmc_request_done(host, mrq);
+		return;
+	}
+
+	host->ops->request(host, mrq);
+}
+
 static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 {
 #ifdef CONFIG_MMC_DEBUG
 	unsigned int i, sz;
 	struct scatterlist *sg;
 #endif
+	mmc_retune_hold(host);
+
 	if (mmc_card_removed(host->card))
 		return -ENOMEDIUM;
 
@@ -252,7 +275,7 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 	}
 	mmc_host_clk_hold(host);
 	led_trigger_event(host->led, LED_FULL);
-	host->ops->request(host, mrq);
+	__mmc_start_request(host, mrq);
 
 	return 0;
 }
@@ -301,12 +324,15 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 		use_busy_signal = false;
 	}
 
+	mmc_retune_hold(card->host);
+
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			EXT_CSD_BKOPS_START, 1, timeout,
 			use_busy_signal, true, false);
 	if (err) {
 		pr_warn("%s: Error %d starting bkops\n",
 			mmc_hostname(card->host), err);
+		mmc_retune_release(card->host);
 		goto out;
 	}
 
@@ -317,6 +343,8 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 	 */
 	if (!use_busy_signal)
 		mmc_card_set_doing_bkops(card);
+	else
+		mmc_retune_release(card->host);
 out:
 	mmc_release_host(card->host);
 }
@@ -417,22 +445,22 @@ static int mmc_wait_for_data_req_done(struct mmc_host *host,
 							    host->areq);
 				break; /* return err */
 			} else {
+				mmc_retune_recheck(host);
 				pr_info("%s: req failed (CMD%u): %d, retrying...\n",
 					mmc_hostname(host),
 					cmd->opcode, cmd->error);
 				cmd->retries--;
 				cmd->error = 0;
-				host->ops->request(host, mrq);
+				__mmc_start_request(host, mrq);
 				continue; /* wait for done/new event again */
 			}
 		} else if (context_info->is_new_req) {
 			context_info->is_new_req = false;
-			if (!next_req) {
-				err = MMC_BLK_NEW_REQUEST;
-				break; /* return err */
-			}
+			if (!next_req)
+				return MMC_BLK_NEW_REQUEST;
 		}
 	}
+	mmc_retune_release(host);
 	return err;
 }
 
@@ -467,12 +495,16 @@ static void mmc_wait_for_req_done(struct mmc_host *host,
 		    mmc_card_removed(host->card))
 			break;
 
+		mmc_retune_recheck(host);
+
 		pr_debug("%s: req failed (CMD%u): %d, retrying...\n",
 			 mmc_hostname(host), cmd->opcode, cmd->error);
 		cmd->retries--;
 		cmd->error = 0;
-		host->ops->request(host, mrq);
+		__mmc_start_request(host, mrq);
 	}
+
+	mmc_retune_release(host);
 }
 
 /**
@@ -728,6 +760,7 @@ int mmc_stop_bkops(struct mmc_card *card)
 	 */
 	if (!err || (err == -EINVAL)) {
 		mmc_card_clr_doing_bkops(card);
+		mmc_retune_release(card->host);
 		err = 0;
 	}
 
@@ -1109,6 +1142,8 @@ int mmc_execute_tuning(struct mmc_card *card)
 
 	if (err)
 		pr_err("%s: tuning execution failed\n", mmc_hostname(host));
+	else
+		mmc_retune_enable(host);
 
 	return err;
 }
@@ -1140,6 +1175,8 @@ void mmc_set_bus_width(struct mmc_host *host, unsigned int width)
  */
 void mmc_set_initial_state(struct mmc_host *host)
 {
+	mmc_retune_disable(host);
+
 	if (mmc_host_is_spi(host))
 		host->ios.chip_select = MMC_CS_HIGH;
 	else
@@ -1147,6 +1184,7 @@ void mmc_set_initial_state(struct mmc_host *host)
 	host->ios.bus_mode = MMC_BUSMODE_PUSHPULL;
 	host->ios.bus_width = MMC_BUS_WIDTH_1;
 	host->ios.timing = MMC_TIMING_LEGACY;
+	host->ios.drv_type = 0;
 
 	mmc_set_ios(host);
 }
@@ -1551,8 +1589,8 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
 		goto power_cycle;
 	}
 
-	/* Keep clock gated for at least 5 ms */
-	mmc_delay(5);
+	/* Keep clock gated for at least 10 ms, though spec only says 5 ms */
+	mmc_delay(10);
 	host->ios.clock = clock;
 	mmc_set_ios(host);
 
@@ -1601,6 +1639,44 @@ void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type)
 	mmc_host_clk_release(host);
 }
 
+int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
+			      int card_drv_type, int *drv_type)
+{
+	struct mmc_host *host = card->host;
+	int host_drv_type = SD_DRIVER_TYPE_B;
+	int drive_strength;
+
+	*drv_type = 0;
+
+	if (!host->ops->select_drive_strength)
+		return 0;
+
+	/* Use SD definition of driver strength for hosts */
+	if (host->caps & MMC_CAP_DRIVER_TYPE_A)
+		host_drv_type |= SD_DRIVER_TYPE_A;
+
+	if (host->caps & MMC_CAP_DRIVER_TYPE_C)
+		host_drv_type |= SD_DRIVER_TYPE_C;
+
+	if (host->caps & MMC_CAP_DRIVER_TYPE_D)
+		host_drv_type |= SD_DRIVER_TYPE_D;
+
+	/*
+	 * The drive strength that the hardware can support
+	 * depends on the board design.  Pass the appropriate
+	 * information and let the hardware specific code
+	 * return what is possible given the options
+	 */
+	mmc_host_clk_hold(host);
+	drive_strength = host->ops->select_drive_strength(card, max_dtr,
+							  host_drv_type,
+							  card_drv_type,
+							  drv_type);
+	mmc_host_clk_release(host);
+
+	return drive_strength;
+}
+
 /*
  * Apply power to the MMC stack.  This is a two-stage process.
  * First, we enable power to the card without the clock running.
@@ -1970,6 +2046,8 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	unsigned long timeout;
 	int err;
 
+	mmc_retune_hold(card->host);
+
 	/*
 	 * qty is used to calculate the erase timeout which depends on how many
 	 * erase groups (or allocation units in SD terminology) are affected.
@@ -2073,6 +2151,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	} while (!(cmd.resp[0] & R1_READY_FOR_DATA) ||
 		 (R1_CURRENT_STATE(cmd.resp[0]) == R1_STATE_PRG));
 out:
+	mmc_retune_release(card->host);
 	return err;
 }
 
@@ -2331,7 +2410,8 @@ int mmc_hw_reset(struct mmc_host *host)
 	ret = host->bus_ops->reset(host);
 	mmc_bus_put(host);
 
-	pr_warn("%s: tried to reset card\n", mmc_hostname(host));
+	if (ret != -EOPNOTSUPP)
+		pr_warn("%s: tried to reset card\n", mmc_hostname(host));
 
 	return ret;
 }
@@ -2651,6 +2731,7 @@ int mmc_pm_notify(struct notifier_block *notify_block,
 	switch (mode) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
+	case PM_RESTORE_PREPARE:
 		spin_lock_irqsave(&host->lock, flags);
 		host->rescan_disable = 1;
 		spin_unlock_irqrestore(&host->lock, flags);
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index cfba3c05aab1..1a22a82209b2 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -50,6 +50,8 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr);
 int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage);
 void mmc_set_timing(struct mmc_host *host, unsigned int timing);
 void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type);
+int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
+			      int card_drv_type, int *drv_type);
 void mmc_power_up(struct mmc_host *host, u32 ocr);
 void mmc_power_off(struct mmc_host *host);
 void mmc_power_cycle(struct mmc_host *host, u32 ocr);
@@ -88,6 +90,8 @@ void mmc_remove_card_debugfs(struct mmc_card *card);
 void mmc_init_context_info(struct mmc_host *host);
 
 int mmc_execute_tuning(struct mmc_card *card);
+int mmc_hs200_to_hs400(struct mmc_card *card);
+int mmc_hs400_to_hs200(struct mmc_card *card);
 
 #endif
 
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 8be0df758e68..99a9c9011c50 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -301,6 +301,90 @@ static inline void mmc_host_clk_sysfs_init(struct mmc_host *host)
 
 #endif
 
+void mmc_retune_enable(struct mmc_host *host)
+{
+	host->can_retune = 1;
+	if (host->retune_period)
+		mod_timer(&host->retune_timer,
+			  jiffies + host->retune_period * HZ);
+}
+
+void mmc_retune_disable(struct mmc_host *host)
+{
+	host->can_retune = 0;
+	del_timer_sync(&host->retune_timer);
+	host->retune_now = 0;
+	host->need_retune = 0;
+}
+
+void mmc_retune_timer_stop(struct mmc_host *host)
+{
+	del_timer_sync(&host->retune_timer);
+}
+EXPORT_SYMBOL(mmc_retune_timer_stop);
+
+void mmc_retune_hold(struct mmc_host *host)
+{
+	if (!host->hold_retune)
+		host->retune_now = 1;
+	host->hold_retune += 1;
+}
+
+void mmc_retune_release(struct mmc_host *host)
+{
+	if (host->hold_retune)
+		host->hold_retune -= 1;
+	else
+		WARN_ON(1);
+}
+
+int mmc_retune(struct mmc_host *host)
+{
+	bool return_to_hs400 = false;
+	int err;
+
+	if (host->retune_now)
+		host->retune_now = 0;
+	else
+		return 0;
+
+	if (!host->need_retune || host->doing_retune || !host->card)
+		return 0;
+
+	host->need_retune = 0;
+
+	host->doing_retune = 1;
+
+	if (host->ios.timing == MMC_TIMING_MMC_HS400) {
+		err = mmc_hs400_to_hs200(host->card);
+		if (err)
+			goto out;
+
+		return_to_hs400 = true;
+
+		if (host->ops->prepare_hs400_tuning)
+			host->ops->prepare_hs400_tuning(host, &host->ios);
+	}
+
+	err = mmc_execute_tuning(host->card);
+	if (err)
+		goto out;
+
+	if (return_to_hs400)
+		err = mmc_hs200_to_hs400(host->card);
+out:
+	host->doing_retune = 0;
+
+	return err;
+}
+
+static void mmc_retune_timer(unsigned long data)
+{
+	struct mmc_host *host = (struct mmc_host *)data;
+
+	mmc_retune_needed(host);
+}
+
 /**
  *	mmc_of_parse() - parse host's device-tree node
  *	@host: host whose node should be parsed.
@@ -400,6 +484,9 @@ int mmc_of_parse(struct mmc_host *host)
 	else if (ret != -ENOENT)
 		return ret;
 
+	if (of_property_read_bool(np, "disable-wp"))
+		host->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+
 	/* See the comment on CD inversion above */
 	if (ro_cap_invert ^ ro_gpio_invert)
 		host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
@@ -504,6 +591,7 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 #ifdef CONFIG_PM
 	host->pm_notify.notifier_call = mmc_pm_notify;
 #endif
+	setup_timer(&host->retune_timer, mmc_retune_timer, (unsigned long)host);
 
 	/*
 	 * By default, hosts do not support SGIO or large requests.
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index f2ab9e578126..992bf5397633 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -15,5 +15,11 @@
 int mmc_register_host_class(void);
 void mmc_unregister_host_class(void);
 
+void mmc_retune_enable(struct mmc_host *host);
+void mmc_retune_disable(struct mmc_host *host);
+void mmc_retune_hold(struct mmc_host *host);
+void mmc_retune_release(struct mmc_host *host);
+int mmc_retune(struct mmc_host *host);
+
 #endif
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f36c76f8b232..e726903170a8 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -21,6 +21,7 @@
 #include <linux/mmc/mmc.h>
 
 #include "core.h"
+#include "host.h"
 #include "bus.h"
 #include "mmc_ops.h"
 #include "sd_ops.h"
@@ -266,8 +267,10 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
 			 * calculate the enhanced data area offset, in bytes
 			 */
 			card->ext_csd.enhanced_area_offset =
-				(ext_csd[139] << 24) + (ext_csd[138] << 16) +
-				(ext_csd[137] << 8) + ext_csd[136];
+				(((unsigned long long)ext_csd[139]) << 24) +
+				(((unsigned long long)ext_csd[138]) << 16) +
+				(((unsigned long long)ext_csd[137]) << 8) +
+				(((unsigned long long)ext_csd[136]));
 			if (mmc_card_blockaddr(card))
 				card->ext_csd.enhanced_area_offset <<= 9;
 			/*
@@ -434,6 +437,7 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 	card->ext_csd.raw_trim_mult =
 		ext_csd[EXT_CSD_TRIM_MULT];
 	card->ext_csd.raw_partition_support = ext_csd[EXT_CSD_PARTITION_SUPPORT];
+	card->ext_csd.raw_driver_strength = ext_csd[EXT_CSD_DRIVER_STRENGTH];
 	if (card->ext_csd.rev >= 4) {
 		if (ext_csd[EXT_CSD_PARTITION_SETTING_COMPLETED] &
 		    EXT_CSD_PART_SETTING_COMPLETED)
@@ -1040,6 +1044,7 @@ static int mmc_select_hs400(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
 	int err = 0;
+	u8 val;
 
 	/*
 	 * HS400 mode requires 8-bit bus width
@@ -1055,8 +1060,10 @@ static int mmc_select_hs400(struct mmc_card *card)
 	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
 	mmc_set_bus_speed(card);
 
+	val = EXT_CSD_TIMING_HS |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS,
+			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
 			   true, true, true);
 	if (err) {
@@ -1075,8 +1082,10 @@ static int mmc_select_hs400(struct mmc_card *card)
 		return err;
 	}
 
+	val = EXT_CSD_TIMING_HS400 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS400,
+			   EXT_CSD_HS_TIMING, val,
 			   card->ext_csd.generic_cmd6_time,
 			   true, true, true);
 	if (err) {
@@ -1091,6 +1100,115 @@ static int mmc_select_hs400(struct mmc_card *card)
 	return 0;
 }
 
+int mmc_hs200_to_hs400(struct mmc_card *card)
+{
+	return mmc_select_hs400(card);
+}
+
+/* Caller must hold re-tuning */
+static int mmc_switch_status(struct mmc_card *card)
+{
+	u32 status;
+	int err;
+
+	err = mmc_send_status(card, &status);
+	if (err)
+		return err;
+
+	return mmc_switch_status_error(card->host, status);
+}
+
+int mmc_hs400_to_hs200(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	bool send_status = true;
+	unsigned int max_dtr;
+	int err;
+	u8 val;
+
+	if (host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		send_status = false;
+
+	/* Reduce frequency to HS */
+	max_dtr = card->ext_csd.hs_max_dtr;
+	mmc_set_clock(host, max_dtr);
+
+	/* Switch HS400 to HS DDR */
+	val = EXT_CSD_TIMING_HS |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
+			   val, card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch HS DDR to HS */
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_BUS_WIDTH,
+			   EXT_CSD_BUS_WIDTH_8, card->ext_csd.generic_cmd6_time,
+			   true, send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_HS);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	/* Switch HS to HS200 */
+	val = EXT_CSD_TIMING_HS200 |
+	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_HS_TIMING,
+			   val, card->ext_csd.generic_cmd6_time, true,
+			   send_status, true);
+	if (err)
+		goto out_err;
+
+	mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+
+	if (!send_status) {
+		err = mmc_switch_status(card);
+		if (err)
+			goto out_err;
+	}
+
+	mmc_set_bus_speed(card);
+
+	return 0;
+
+out_err:
+	pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
+	       __func__, err);
+	return err;
+}
+
+static void mmc_select_driver_type(struct mmc_card *card)
+{
+	int card_drv_type, drive_strength, drv_type;
+
+	card_drv_type = card->ext_csd.raw_driver_strength |
+			mmc_driver_type_mask(0);
+
+	drive_strength = mmc_select_drive_strength(card,
+						   card->ext_csd.hs200_max_dtr,
+						   card_drv_type, &drv_type);
+
+	card->drive_strength = drive_strength;
+
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
+}
+
 /*
  * For device supporting HS200 mode, the following sequence
  * should be done before executing the tuning process.
@@ -1102,6 +1220,7 @@ static int mmc_select_hs200(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
 	int err = -EINVAL;
+	u8 val;
 
 	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_2V)
 		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
@@ -1113,14 +1232,18 @@ static int mmc_select_hs200(struct mmc_card *card)
 	if (err)
 		goto err;
 
+	mmc_select_driver_type(card);
+
 	/*
 	 * Set the bus width(4 or 8) with host's support and
 	 * switch to HS200 mode if bus width is set successfully.
 	 */
 	err = mmc_select_bus_width(card);
 	if (!IS_ERR_VALUE(err)) {
+		val = EXT_CSD_TIMING_HS200 |
+		      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-				   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS200,
+				   EXT_CSD_HS_TIMING, val,
 				   card->ext_csd.generic_cmd6_time,
 				   true, true, true);
 		if (!err)
@@ -1511,9 +1634,12 @@ static int mmc_sleep(struct mmc_host *host)
 	unsigned int timeout_ms = DIV_ROUND_UP(card->ext_csd.sa_timeout, 10000);
 	int err;
 
+	/* Re-tuning can't be done once the card is deselected */
+	mmc_retune_hold(host);
+
 	err = mmc_deselect_cards(host);
 	if (err)
-		return err;
+		goto out_release;
 
 	cmd.opcode = MMC_SLEEP_AWAKE;
 	cmd.arg = card->rca << 16;
@@ -1534,7 +1660,7 @@ static int mmc_sleep(struct mmc_host *host)
 
 	err = mmc_wait_for_cmd(host, &cmd, 0);
 	if (err)
-		return err;
+		goto out_release;
 
 	/*
 	 * If the host does not wait while the card signals busy, then we will
@@ -1545,6 +1671,8 @@ static int mmc_sleep(struct mmc_host *host)
 	if (!cmd.busy_timeout || !(host->caps & MMC_CAP_WAIT_WHILE_BUSY))
 		mmc_delay(timeout_ms);
 
+out_release:
+	mmc_retune_release(host);
 	return err;
 }
 
@@ -1782,17 +1910,6 @@ static int mmc_runtime_resume(struct mmc_host *host)
 	return 0;
 }
 
-static int mmc_power_restore(struct mmc_host *host)
-{
-	int ret;
-
-	mmc_claim_host(host);
-	ret = mmc_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
-
-	return ret;
-}
-
 int mmc_can_reset(struct mmc_card *card)
 {
 	u8 rst_n_function;
@@ -1830,7 +1947,7 @@ static int mmc_reset(struct mmc_host *host)
 	mmc_set_initial_state(host);
 	mmc_host_clk_release(host);
 
-	return mmc_power_restore(host);
+	return mmc_init_card(host, card->ocr, card);
 }
 
 static const struct mmc_bus_ops mmc_ops = {
@@ -1840,7 +1957,6 @@ static const struct mmc_bus_ops mmc_ops = {
 	.resume = mmc_resume,
 	.runtime_suspend = mmc_runtime_suspend,
 	.runtime_resume = mmc_runtime_resume,
-	.power_restore = mmc_power_restore,
 	.alive = mmc_alive,
 	.shutdown = mmc_shutdown,
 	.reset = mmc_reset,
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 0ea042dc7443..0e9ae1c276c8 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -19,6 +19,7 @@
 #include <linux/mmc/mmc.h>
 
 #include "core.h"
+#include "host.h"
 #include "mmc_ops.h"
 
 #define MMC_OPS_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
@@ -449,6 +450,21 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc)
 	return err;
 }
 
+int mmc_switch_status_error(struct mmc_host *host, u32 status)
+{
+	if (mmc_host_is_spi(host)) {
+		if (status & R1_SPI_ILLEGAL_COMMAND)
+			return -EBADMSG;
+	} else {
+		if (status & 0xFDFFA000)
+			pr_warn("%s: unexpected status %#x after switch\n",
+				mmc_hostname(host), status);
+		if (status & R1_SWITCH_ERROR)
+			return -EBADMSG;
+	}
+	return 0;
+}
+
 /**
  *	__mmc_switch - modify EXT_CSD register
  *	@card: the MMC card associated with the data transfer
@@ -474,6 +490,8 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 	u32 status = 0;
 	bool use_r1b_resp = use_busy_signal;
 
+	mmc_retune_hold(host);
+
 	/*
 	 * If the cmd timeout and the max_busy_timeout of the host are both
 	 * specified, let's validate them. A failure means we need to prevent
@@ -506,11 +524,11 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 
 	err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
 	if (err)
-		return err;
+		goto out;
 
 	/* No need to check card status in case of unblocking command */
 	if (!use_busy_signal)
-		return 0;
+		goto out;
 
 	/*
 	 * CRC errors shall only be ignored in cases were CMD13 is used to poll
@@ -529,7 +547,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		if (send_status) {
 			err = __mmc_send_status(card, &status, ignore_crc);
 			if (err)
-				return err;
+				goto out;
 		}
 		if ((host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp)
 			break;
@@ -543,29 +561,23 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		 */
 		if (!send_status) {
 			mmc_delay(timeout_ms);
-			return 0;
+			goto out;
 		}
 
 		/* Timeout if the device never leaves the program state. */
 		if (time_after(jiffies, timeout)) {
 			pr_err("%s: Card stuck in programming state! %s\n",
 				mmc_hostname(host), __func__);
-			return -ETIMEDOUT;
+			err = -ETIMEDOUT;
+			goto out;
 		}
 	} while (R1_CURRENT_STATE(status) == R1_STATE_PRG);
 
-	if (mmc_host_is_spi(host)) {
-		if (status & R1_SPI_ILLEGAL_COMMAND)
-			return -EBADMSG;
-	} else {
-		if (status & 0xFDFFA000)
-			pr_warn("%s: unexpected status %#x after switch\n",
-				mmc_hostname(host), status);
-		if (status & R1_SWITCH_ERROR)
-			return -EBADMSG;
-	}
+	err = mmc_switch_status_error(host, status);
+out:
+	mmc_retune_release(host);
 
-	return 0;
+	return err;
 }
 EXPORT_SYMBOL_GPL(__mmc_switch);
 
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index 6f4b00ed93de..f498f9ae21f0 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -27,6 +27,7 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc);
 int mmc_bus_test(struct mmc_card *card, u8 bus_width);
 int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status);
 int mmc_can_ext_csd(struct mmc_card *card);
+int mmc_switch_status_error(struct mmc_host *host, u32 status);
 
 #endif
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 31a9ef256d06..4e7366ab187f 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -386,64 +386,31 @@ out:
 
 static int sd_select_driver_type(struct mmc_card *card, u8 *status)
 {
-	int host_drv_type = SD_DRIVER_TYPE_B;
-	int card_drv_type = SD_DRIVER_TYPE_B;
-	int drive_strength;
+	int card_drv_type, drive_strength, drv_type;
 	int err;
 
-	/*
-	 * If the host doesn't support any of the Driver Types A,C or D,
-	 * or there is no board specific handler then default Driver
-	 * Type B is used.
-	 */
-	if (!(card->host->caps & (MMC_CAP_DRIVER_TYPE_A | MMC_CAP_DRIVER_TYPE_C
-	    | MMC_CAP_DRIVER_TYPE_D)))
-		return 0;
-
-	if (!card->host->ops->select_drive_strength)
-		return 0;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A)
-		host_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_C)
-		host_drv_type |= SD_DRIVER_TYPE_C;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_D)
-		host_drv_type |= SD_DRIVER_TYPE_D;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A)
-		card_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-		card_drv_type |= SD_DRIVER_TYPE_C;
+	card->drive_strength = 0;
 
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D)
-		card_drv_type |= SD_DRIVER_TYPE_D;
+	card_drv_type = card->sw_caps.sd3_drv_type | SD_DRIVER_TYPE_B;
 
-	/*
-	 * The drive strength that the hardware can support
-	 * depends on the board design.  Pass the appropriate
-	 * information and let the hardware specific code
-	 * return what is possible given the options
-	 */
-	mmc_host_clk_hold(card->host);
-	drive_strength = card->host->ops->select_drive_strength(
-		card->sw_caps.uhs_max_dtr,
-		host_drv_type, card_drv_type);
-	mmc_host_clk_release(card->host);
-
-	err = mmc_sd_switch(card, 1, 2, drive_strength, status);
-	if (err)
-		return err;
+	drive_strength = mmc_select_drive_strength(card,
+						   card->sw_caps.uhs_max_dtr,
+						   card_drv_type, &drv_type);
 
-	if ((status[15] & 0xF) != drive_strength) {
-		pr_warn("%s: Problem setting drive strength!\n",
-			mmc_hostname(card->host));
-		return 0;
+	if (drive_strength) {
+		err = mmc_sd_switch(card, 1, 2, drive_strength, status);
+		if (err)
+			return err;
+		if ((status[15] & 0xF) != drive_strength) {
+			pr_warn("%s: Problem setting drive strength!\n",
+				mmc_hostname(card->host));
+			return 0;
+		}
+		card->drive_strength = drive_strength;
 	}
 
-	mmc_set_driver_type(card->host, drive_strength);
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
 
 	return 0;
 }
@@ -804,6 +771,28 @@ int mmc_sd_get_csd(struct mmc_host *host, struct mmc_card *card)
 	return 0;
 }
 
+static int mmc_sd_get_ro(struct mmc_host *host)
+{
+	int ro;
+
+	/*
+	 * Some systems don't feature a write-protect pin and don't need one.
+	 * E.g. because they only have micro-SD card slot. For those systems
+	 * assume that the SD card is always read-write.
+	 */
+	if (host->caps2 & MMC_CAP2_NO_WRITE_PROTECT)
+		return 0;
+
+	if (!host->ops->get_ro)
+		return -1;
+
+	mmc_host_clk_hold(host);
+	ro = host->ops->get_ro(host);
+	mmc_host_clk_release(host);
+
+	return ro;
+}
+
 int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	bool reinit)
 {
@@ -855,13 +844,7 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	 * Check if read-only switch is active.
 	 */
 	if (!reinit) {
-		int ro = -1;
-
-		if (host->ops->get_ro) {
-			mmc_host_clk_hold(card->host);
-			ro = host->ops->get_ro(host);
-			mmc_host_clk_release(card->host);
-		}
+		int ro = mmc_sd_get_ro(host);
 
 		if (ro < 0) {
 			pr_warn("%s: host does not support reading read-only switch, assuming write-enable\n",
@@ -1181,21 +1164,10 @@ static int mmc_sd_runtime_resume(struct mmc_host *host)
 	return 0;
 }
 
-static int mmc_sd_power_restore(struct mmc_host *host)
-{
-	int ret;
-
-	mmc_claim_host(host);
-	ret = mmc_sd_init_card(host, host->card->ocr, host->card);
-	mmc_release_host(host);
-
-	return ret;
-}
-
 static int mmc_sd_reset(struct mmc_host *host)
 {
 	mmc_power_cycle(host, host->card->ocr);
-	return mmc_sd_power_restore(host);
+	return mmc_sd_init_card(host, host->card->ocr, host->card);
 }
 
 static const struct mmc_bus_ops mmc_sd_ops = {
@@ -1205,7 +1177,6 @@ static const struct mmc_bus_ops mmc_sd_ops = {
 	.runtime_resume = mmc_sd_runtime_resume,
 	.suspend = mmc_sd_suspend,
 	.resume = mmc_sd_resume,
-	.power_restore = mmc_sd_power_restore,
 	.alive = mmc_sd_alive,
 	.shutdown = mmc_sd_suspend,
 	.reset = mmc_sd_reset,
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 5bc6c7dbbd60..b91abedcfdca 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -402,69 +402,38 @@ static unsigned char host_drive_to_sdio_drive(int host_strength)
 
 static void sdio_select_driver_type(struct mmc_card *card)
 {
-	int host_drv_type = SD_DRIVER_TYPE_B;
-	int card_drv_type = SD_DRIVER_TYPE_B;
-	int drive_strength;
+	int card_drv_type, drive_strength, drv_type;
 	unsigned char card_strength;
 	int err;
 
-	/*
-	 * If the host doesn't support any of the Driver Types A,C or D,
-	 * or there is no board specific handler then default Driver
-	 * Type B is used.
-	 */
-	if (!(card->host->caps &
-		(MMC_CAP_DRIVER_TYPE_A |
-		 MMC_CAP_DRIVER_TYPE_C |
-		 MMC_CAP_DRIVER_TYPE_D)))
-		return;
-
-	if (!card->host->ops->select_drive_strength)
-		return;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_A)
-		host_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_C)
-		host_drv_type |= SD_DRIVER_TYPE_C;
+	card->drive_strength = 0;
 
-	if (card->host->caps & MMC_CAP_DRIVER_TYPE_D)
-		host_drv_type |= SD_DRIVER_TYPE_D;
+	card_drv_type = card->sw_caps.sd3_drv_type | SD_DRIVER_TYPE_B;
 
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A)
-		card_drv_type |= SD_DRIVER_TYPE_A;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C)
-		card_drv_type |= SD_DRIVER_TYPE_C;
-
-	if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D)
-		card_drv_type |= SD_DRIVER_TYPE_D;
-
-	/*
-	 * The drive strength that the hardware can support
-	 * depends on the board design.  Pass the appropriate
-	 * information and let the hardware specific code
-	 * return what is possible given the options
-	 */
-	drive_strength = card->host->ops->select_drive_strength(
-		card->sw_caps.uhs_max_dtr,
-		host_drv_type, card_drv_type);
+	drive_strength = mmc_select_drive_strength(card,
+						   card->sw_caps.uhs_max_dtr,
+						   card_drv_type, &drv_type);
 
-	/* if error just use default for drive strength B */
-	err = mmc_io_rw_direct(card, 0, 0, SDIO_CCCR_DRIVE_STRENGTH, 0,
-		&card_strength);
-	if (err)
-		return;
+	if (drive_strength) {
+		/* if error just use default for drive strength B */
+		err = mmc_io_rw_direct(card, 0, 0, SDIO_CCCR_DRIVE_STRENGTH, 0,
+				       &card_strength);
+		if (err)
+			return;
 
-	card_strength &= ~(SDIO_DRIVE_DTSx_MASK<<SDIO_DRIVE_DTSx_SHIFT);
-	card_strength |= host_drive_to_sdio_drive(drive_strength);
+		card_strength &= ~(SDIO_DRIVE_DTSx_MASK<<SDIO_DRIVE_DTSx_SHIFT);
+		card_strength |= host_drive_to_sdio_drive(drive_strength);
 
-	err = mmc_io_rw_direct(card, 1, 0, SDIO_CCCR_DRIVE_STRENGTH,
-		card_strength, NULL);
+		/* if error default to drive strength B */
+		err = mmc_io_rw_direct(card, 1, 0, SDIO_CCCR_DRIVE_STRENGTH,
+				       card_strength, NULL);
+		if (err)
+			return;
+		card->drive_strength = drive_strength;
+	}
 
-	/* if error default to drive strength B */
-	if (!err)
-		mmc_set_driver_type(card->host, drive_strength);
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
 }
 
 
@@ -934,8 +903,12 @@ static int mmc_sdio_suspend(struct mmc_host *host)
 		mmc_release_host(host);
 	}
 
-	if (!mmc_card_keep_power(host))
+	if (!mmc_card_keep_power(host)) {
 		mmc_power_off(host);
+	} else if (host->retune_period) {
+		mmc_retune_timer_stop(host);
+		mmc_retune_needed(host);
+	}
 
 	return 0;
 }
@@ -1056,6 +1029,12 @@ static int mmc_sdio_runtime_resume(struct mmc_host *host)
 	return mmc_sdio_power_restore(host);
 }
 
+static int mmc_sdio_reset(struct mmc_host *host)
+{
+	mmc_power_cycle(host, host->card->ocr);
+	return mmc_sdio_power_restore(host);
+}
+
 static const struct mmc_bus_ops mmc_sdio_ops = {
 	.remove = mmc_sdio_remove,
 	.detect = mmc_sdio_detect,
@@ -1066,6 +1045,7 @@ static const struct mmc_bus_ops mmc_sdio_ops = {
 	.runtime_resume = mmc_sdio_runtime_resume,
 	.power_restore = mmc_sdio_power_restore,
 	.alive = mmc_sdio_alive,
+	.reset = mmc_sdio_reset,
 };
 
 
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index bee02e644d62..7e327a6dd53d 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -137,6 +137,10 @@ static int sdio_bus_probe(struct device *dev)
 	if (!id)
 		return -ENODEV;
 
+	ret = dev_pm_domain_attach(dev, false);
+	if (ret == -EPROBE_DEFER)
+		return ret;
+
 	/* Unbound SDIO functions are always suspended.
 	 * During probe, the function is set active and the usage count
 	 * is incremented.  If the driver supports runtime PM,
@@ -166,6 +170,7 @@ static int sdio_bus_probe(struct device *dev)
 disable_runtimepm:
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
 		pm_runtime_put_noidle(dev);
+	dev_pm_domain_detach(dev, false);
 	return ret;
 }
 
@@ -197,6 +202,8 @@ static int sdio_bus_remove(struct device *dev)
 	if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD)
 		pm_runtime_put_sync(dev);
 
+	dev_pm_domain_detach(dev, false);
+
 	return ret;
 }
 
@@ -316,10 +323,8 @@ int sdio_add_func(struct sdio_func *func)
 	sdio_set_of_node(func);
 	sdio_acpi_set_handle(func);
 	ret = device_add(&func->dev);
-	if (ret == 0) {
+	if (ret == 0)
 		sdio_func_set_present(func);
-		dev_pm_domain_attach(&func->dev, false);
-	}
 
 	return ret;
 }
@@ -335,7 +340,6 @@ void sdio_remove_func(struct sdio_func *func)
 	if (!sdio_func_present(func))
 		return;
 
-	dev_pm_domain_detach(&func->dev, false);
 	device_del(&func->dev);
 	of_node_put(func->dev.of_node);
 	put_device(&func->dev);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index b1f837e749fe..fd9a58e216a5 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -219,6 +219,7 @@ config MMC_SDHCI_SIRF
 	tristate "SDHCI support on CSR SiRFprimaII and SiRFmarco SoCs"
 	depends on ARCH_SIRF
 	depends on MMC_SDHCI_PLTFM
+	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the SDHCI support for SiRF System-on-Chip devices.
 
@@ -775,3 +776,11 @@ config MMC_TOSHIBA_PCI
 	tristate "Toshiba Type A SD/MMC Card Interface Driver"
 	depends on PCI
 	help
+
+config MMC_MTK
+	tristate "MediaTek SD/MMC Card Interface support"
+	help
+	  This selects the MediaTek(R) Secure digital and Multimedia card Interface.
+	  If you have a machine with a integrated SD/MMC card reader, say Y or M here.
+	  This is needed if support for any SD/SDIO/MMC devices is required.
+	  If unsure, say N.
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index e3ab5b968651..e928d61c5f4b 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_MMC_SDHCI_F_SDH30)	+= sdhci_f_sdh30.o
 obj-$(CONFIG_MMC_SDHCI_SPEAR)	+= sdhci-spear.o
 obj-$(CONFIG_MMC_WBSD)		+= wbsd.o
 obj-$(CONFIG_MMC_AU1X)		+= au1xmmc.o
+obj-$(CONFIG_MMC_MTK)		+= mtk-sd.o
 obj-$(CONFIG_MMC_OMAP)		+= omap.o
 obj-$(CONFIG_MMC_OMAP_HS)	+= omap_hsmmc.o
 obj-$(CONFIG_MMC_ATMELMCI)	+= atmel-mci.o
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 03d7c7521d97..9a39e0b7e583 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -1304,7 +1304,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	if (ios->clock) {
 		unsigned int clock_min = ~0U;
-		u32 clkdiv;
+		int clkdiv;
 
 		spin_lock_bh(&host->lock);
 		if (!host->mode_reg) {
@@ -1328,7 +1328,12 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		/* Calculate clock divider */
 		if (host->caps.has_odd_clk_div) {
 			clkdiv = DIV_ROUND_UP(host->bus_hz, clock_min) - 2;
-			if (clkdiv > 511) {
+			if (clkdiv < 0) {
+				dev_warn(&mmc->class_dev,
+					 "clock %u too fast; using %lu\n",
+					 clock_min, host->bus_hz / 2);
+				clkdiv = 0;
+			} else if (clkdiv > 511) {
 				dev_warn(&mmc->class_dev,
 				         "clock %u too slow; using %lu\n",
 				         clock_min, host->bus_hz / (511 + 2));
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 1625f908dc70..ea2a2ebc6b91 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -1161,7 +1161,7 @@ static void __init init_mmcsd_host(struct mmc_davinci_host *host)
 	mmc_davinci_reset_ctrl(host, 0);
 }
 
-static struct platform_device_id davinci_mmc_devtype[] = {
+static const struct platform_device_id davinci_mmc_devtype[] = {
 	{
 		.name	= "dm6441-mmc",
 		.driver_data = MMC_CTLR_VERSION_1,
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index e761eb1b1441..1e75309898b7 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -556,4 +556,4 @@ module_platform_driver(dw_mci_exynos_pltfm_driver);
 MODULE_DESCRIPTION("Samsung Specific DW-MSHC Driver Extension");
 MODULE_AUTHOR("Thomas Abraham <thomas.ab@samsung.com");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:dwmmc-exynos");
+MODULE_ALIAS("platform:dwmmc_exynos");
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 650f9cc3f7a6..63c2e2ed1288 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -8,16 +8,30 @@
  * (at your option) any later version.
  */
 
-#include <linux/module.h>
-#include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/mfd/syscon.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/dw_mmc.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #include "dw_mmc.h"
 #include "dw_mmc-pltfm.h"
 
+/*
+ * hi6220 sd only support io voltage 1.8v and 3v
+ * Also need config AO_SCTRL_SEL18 accordingly
+ */
+#define AO_SCTRL_SEL18		BIT(10)
+#define AO_SCTRL_CTRL3		0x40C
+
+struct k3_priv {
+	struct regmap	*reg;
+};
+
 static void dw_mci_k3_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 {
 	int ret;
@@ -33,8 +47,93 @@ static const struct dw_mci_drv_data k3_drv_data = {
 	.set_ios		= dw_mci_k3_set_ios,
 };
 
+static int dw_mci_hi6220_parse_dt(struct dw_mci *host)
+{
+	struct k3_priv *priv;
+
+	priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reg = syscon_regmap_lookup_by_phandle(host->dev->of_node,
+					 "hisilicon,peripheral-syscon");
+	if (IS_ERR(priv->reg))
+		priv->reg = NULL;
+
+	host->priv = priv;
+	return 0;
+}
+
+static int dw_mci_hi6220_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct dw_mci_slot *slot = mmc_priv(mmc);
+	struct k3_priv *priv;
+	struct dw_mci *host;
+	int min_uv, max_uv;
+	int ret;
+
+	host = slot->host;
+	priv = host->priv;
+
+	if (!priv || !priv->reg)
+		return 0;
+
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, 0);
+		min_uv = 3000000;
+		max_uv = 3000000;
+	} else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+		ret = regmap_update_bits(priv->reg, AO_SCTRL_CTRL3,
+					 AO_SCTRL_SEL18, AO_SCTRL_SEL18);
+		min_uv = 1800000;
+		max_uv = 1800000;
+	} else {
+		dev_dbg(host->dev, "voltage not supported\n");
+		return -EINVAL;
+	}
+
+	if (ret) {
+		dev_dbg(host->dev, "switch voltage failed\n");
+		return ret;
+	}
+
+	if (IS_ERR_OR_NULL(mmc->supply.vqmmc))
+		return 0;
+
+	ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+	if (ret) {
+		dev_dbg(host->dev, "Regulator set error %d: %d - %d\n",
+				 ret, min_uv, max_uv);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dw_mci_hi6220_set_ios(struct dw_mci *host, struct mmc_ios *ios)
+{
+	int ret;
+	unsigned int clock;
+
+	clock = (ios->clock <= 25000000) ? 25000000 : ios->clock;
+
+	ret = clk_set_rate(host->biu_clk, clock);
+	if (ret)
+		dev_warn(host->dev, "failed to set rate %uHz\n", clock);
+
+	host->bus_hz = clk_get_rate(host->biu_clk);
+}
+
+static const struct dw_mci_drv_data hi6220_data = {
+	.switch_voltage		= dw_mci_hi6220_switch_voltage,
+	.set_ios		= dw_mci_hi6220_set_ios,
+	.parse_dt		= dw_mci_hi6220_parse_dt,
+};
+
 static const struct of_device_id dw_mci_k3_match[] = {
 	{ .compatible = "hisilicon,hi4511-dw-mshc", .data = &k3_drv_data, },
+	{ .compatible = "hisilicon,hi6220-dw-mshc", .data = &hi6220_data, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, dw_mci_k3_match);
@@ -94,4 +193,4 @@ module_platform_driver(dw_mci_k3_pltfm_driver);
 
 MODULE_DESCRIPTION("K3 Specific DW-MSHC Driver Extension");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:dwmmc-k3");
+MODULE_ALIAS("platform:dwmmc_k3");
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index dbf166f94f1b..de15121bba7d 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -153,5 +153,5 @@ module_platform_driver(dw_mci_rockchip_pltfm_driver);
 
 MODULE_AUTHOR("Addy Ke <addy.ke@rock-chips.com>");
 MODULE_DESCRIPTION("Rockchip Specific DW-MSHC Driver Extension");
-MODULE_ALIAS("platform:dwmmc-rockchip");
+MODULE_ALIAS("platform:dwmmc_rockchip");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 38b29265cc7c..40e9d8e45f25 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -589,9 +589,11 @@ static int dw_mci_idmac_init(struct dw_mci *host)
 		host->ring_size = PAGE_SIZE / sizeof(struct idmac_desc);
 
 		/* Forward link the descriptor list */
-		for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++)
+		for (i = 0, p = host->sg_cpu; i < host->ring_size - 1; i++, p++) {
 			p->des3 = cpu_to_le32(host->sg_dma +
 					(sizeof(struct idmac_desc) * (i + 1)));
+			p->des1 = 0;
+		}
 
 		/* Set the last descriptor as the end-of-ring descriptor */
 		p->des3 = cpu_to_le32(host->sg_dma);
@@ -1234,11 +1236,15 @@ static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct dw_mci_slot *slot = mmc_priv(mmc);
 	struct dw_mci *host = slot->host;
+	const struct dw_mci_drv_data *drv_data = host->drv_data;
 	u32 uhs;
 	u32 v18 = SDMMC_UHS_18V << slot->id;
 	int min_uv, max_uv;
 	int ret;
 
+	if (drv_data && drv_data->switch_voltage)
+		return drv_data->switch_voltage(mmc, ios);
+
 	/*
 	 * Program the voltage.  Note that some instances of dw_mmc may use
 	 * the UHS_REG for this.  For other instances (like exynos) the UHS_REG
@@ -1276,10 +1282,7 @@ static int dw_mci_get_ro(struct mmc_host *mmc)
 	int gpio_ro = mmc_gpio_get_ro(mmc);
 
 	/* Use platform get_ro function, else try on board write protect */
-	if ((slot->quirks & DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT) ||
-			(slot->host->quirks & DW_MCI_QUIRK_NO_WRITE_PROTECT))
-		read_only = 0;
-	else if (!IS_ERR_VALUE(gpio_ro))
+	if (!IS_ERR_VALUE(gpio_ro))
 		read_only = gpio_ro;
 	else
 		read_only =
@@ -1300,7 +1303,8 @@ static int dw_mci_get_cd(struct mmc_host *mmc)
 	int gpio_cd = mmc_gpio_get_cd(mmc);
 
 	/* Use platform get_cd function, else try onboard card detect */
-	if (brd->quirks & DW_MCI_QUIRK_BROKEN_CARD_DETECTION)
+	if ((brd->quirks & DW_MCI_QUIRK_BROKEN_CARD_DETECTION) ||
+	    (mmc->caps & MMC_CAP_NONREMOVABLE))
 		present = 1;
 	else if (!IS_ERR_VALUE(gpio_cd))
 		present = gpio_cd;
@@ -2277,9 +2281,10 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 }
 
 #ifdef CONFIG_OF
-/* given a slot id, find out the device node representing that slot */
-static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
+/* given a slot, find out the device node representing that slot */
+static struct device_node *dw_mci_of_find_slot_node(struct dw_mci_slot *slot)
 {
+	struct device *dev = slot->mmc->parent;
 	struct device_node *np;
 	const __be32 *addr;
 	int len;
@@ -2291,42 +2296,28 @@ static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
 		addr = of_get_property(np, "reg", &len);
 		if (!addr || (len < sizeof(int)))
 			continue;
-		if (be32_to_cpup(addr) == slot)
+		if (be32_to_cpup(addr) == slot->id)
 			return np;
 	}
 	return NULL;
 }
 
-static struct dw_mci_of_slot_quirks {
-	char *quirk;
-	int id;
-} of_slot_quirks[] = {
-	{
-		.quirk	= "disable-wp",
-		.id	= DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT,
-	},
-};
-
-static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
+static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
 {
-	struct device_node *np = dw_mci_of_find_slot_node(dev, slot);
-	int quirks = 0;
-	int idx;
+	struct device_node *np = dw_mci_of_find_slot_node(slot);
 
-	/* get quirks */
-	for (idx = 0; idx < ARRAY_SIZE(of_slot_quirks); idx++)
-		if (of_get_property(np, of_slot_quirks[idx].quirk, NULL)) {
-			dev_warn(dev, "Slot quirk %s is deprecated\n",
-					of_slot_quirks[idx].quirk);
-			quirks |= of_slot_quirks[idx].id;
-		}
+	if (!np)
+		return;
 
-	return quirks;
+	if (of_property_read_bool(np, "disable-wp")) {
+		slot->mmc->caps2 |= MMC_CAP2_NO_WRITE_PROTECT;
+		dev_warn(slot->mmc->parent,
+			"Slot quirk 'disable-wp' is deprecated\n");
+	}
 }
 #else /* CONFIG_OF */
-static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
+static void dw_mci_slot_of_parse(struct dw_mci_slot *slot)
 {
-	return 0;
 }
 #endif /* CONFIG_OF */
 
@@ -2349,8 +2340,6 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	slot->host = host;
 	host->slot[id] = slot;
 
-	slot->quirks = dw_mci_of_get_slot_quirks(host->dev, slot->id);
-
 	mmc->ops = &dw_mci_ops;
 	if (of_property_read_u32_array(host->dev->of_node,
 				       "clock-freq-min-max", freq, 2)) {
@@ -2388,6 +2377,8 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps2)
 		mmc->caps2 = host->pdata->caps2;
 
+	dw_mci_slot_of_parse(slot);
+
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto err_host_allocated;
@@ -2615,9 +2606,6 @@ static struct dw_mci_of_quirks {
 	{
 		.quirk	= "broken-cd",
 		.id	= DW_MCI_QUIRK_BROKEN_CARD_DETECTION,
-	}, {
-		.quirk	= "disable-wp",
-		.id	= DW_MCI_QUIRK_NO_WRITE_PROTECT,
 	},
 };
 
@@ -2938,15 +2926,15 @@ void dw_mci_remove(struct dw_mci *host)
 {
 	int i;
 
-	mci_writel(host, RINTSTS, 0xFFFFFFFF);
-	mci_writel(host, INTMASK, 0); /* disable all mmc interrupt first */
-
 	for (i = 0; i < host->num_slots; i++) {
 		dev_dbg(host->dev, "remove slot %d\n", i);
 		if (host->slot[i])
 			dw_mci_cleanup_slot(host->slot[i], i);
 	}
 
+	mci_writel(host, RINTSTS, 0xFFFFFFFF);
+	mci_writel(host, INTMASK, 0); /* disable all mmc interrupt first */
+
 	/* disable clock to CIU */
 	mci_writel(host, CLKENA, 0);
 	mci_writel(host, CLKSRC, 0);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index f45ab91de339..8ce4674730a6 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -227,7 +227,6 @@ extern int dw_mci_resume(struct dw_mci *host);
  * struct dw_mci_slot - MMC slot state
  * @mmc: The mmc_host representing this slot.
  * @host: The MMC controller this slot is using.
- * @quirks: Slot-level quirks (DW_MCI_SLOT_QUIRK_XXX)
  * @ctype: Card type for this slot.
  * @mrq: mmc_request currently being processed or waiting to be
  *	processed, or NULL when the slot is idle.
@@ -245,8 +244,6 @@ struct dw_mci_slot {
 	struct mmc_host		*mmc;
 	struct dw_mci		*host;
 
-	int			quirks;
-
 	u32			ctype;
 
 	struct mmc_request	*mrq;
@@ -287,5 +284,7 @@ struct dw_mci_drv_data {
 	int		(*execute_tuning)(struct dw_mci_slot *slot);
 	int		(*prepare_hs400_tuning)(struct dw_mci *host,
 						struct mmc_ios *ios);
+	int		(*switch_voltage)(struct mmc_host *mmc,
+					  struct mmc_ios *ios);
 };
 #endif /* _DW_MMC_H_ */
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
new file mode 100644
index 000000000000..7153500dd007
--- /dev/null
+++ b/drivers/mmc/host/mtk-sd.c
@@ -0,0 +1,1462 @@
+/*
+ * Copyright (c) 2014-2015 MediaTek Inc.
+ * Author: Chaotian.Jing <chaotian.jing@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spinlock.h>
+
+#include <linux/mmc/card.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/sdio.h>
+
+#define MAX_BD_NUM          1024
+
+/*--------------------------------------------------------------------------*/
+/* Common Definition                                                        */
+/*--------------------------------------------------------------------------*/
+#define MSDC_BUS_1BITS          0x0
+#define MSDC_BUS_4BITS          0x1
+#define MSDC_BUS_8BITS          0x2
+
+#define MSDC_BURST_64B          0x6
+
+/*--------------------------------------------------------------------------*/
+/* Register Offset                                                          */
+/*--------------------------------------------------------------------------*/
+#define MSDC_CFG         0x0
+#define MSDC_IOCON       0x04
+#define MSDC_PS          0x08
+#define MSDC_INT         0x0c
+#define MSDC_INTEN       0x10
+#define MSDC_FIFOCS      0x14
+#define SDC_CFG          0x30
+#define SDC_CMD          0x34
+#define SDC_ARG          0x38
+#define SDC_STS          0x3c
+#define SDC_RESP0        0x40
+#define SDC_RESP1        0x44
+#define SDC_RESP2        0x48
+#define SDC_RESP3        0x4c
+#define SDC_BLK_NUM      0x50
+#define SDC_ACMD_RESP    0x80
+#define MSDC_DMA_SA      0x90
+#define MSDC_DMA_CTRL    0x98
+#define MSDC_DMA_CFG     0x9c
+#define MSDC_PATCH_BIT   0xb0
+#define MSDC_PATCH_BIT1  0xb4
+#define MSDC_PAD_TUNE    0xec
+
+/*--------------------------------------------------------------------------*/
+/* Register Mask                                                            */
+/*--------------------------------------------------------------------------*/
+
+/* MSDC_CFG mask */
+#define MSDC_CFG_MODE           (0x1 << 0)	/* RW */
+#define MSDC_CFG_CKPDN          (0x1 << 1)	/* RW */
+#define MSDC_CFG_RST            (0x1 << 2)	/* RW */
+#define MSDC_CFG_PIO            (0x1 << 3)	/* RW */
+#define MSDC_CFG_CKDRVEN        (0x1 << 4)	/* RW */
+#define MSDC_CFG_BV18SDT        (0x1 << 5)	/* RW */
+#define MSDC_CFG_BV18PSS        (0x1 << 6)	/* R  */
+#define MSDC_CFG_CKSTB          (0x1 << 7)	/* R  */
+#define MSDC_CFG_CKDIV          (0xff << 8)	/* RW */
+#define MSDC_CFG_CKMOD          (0x3 << 16)	/* RW */
+
+/* MSDC_IOCON mask */
+#define MSDC_IOCON_SDR104CKS    (0x1 << 0)	/* RW */
+#define MSDC_IOCON_RSPL         (0x1 << 1)	/* RW */
+#define MSDC_IOCON_DSPL         (0x1 << 2)	/* RW */
+#define MSDC_IOCON_DDLSEL       (0x1 << 3)	/* RW */
+#define MSDC_IOCON_DDR50CKD     (0x1 << 4)	/* RW */
+#define MSDC_IOCON_DSPLSEL      (0x1 << 5)	/* RW */
+#define MSDC_IOCON_W_DSPL       (0x1 << 8)	/* RW */
+#define MSDC_IOCON_D0SPL        (0x1 << 16)	/* RW */
+#define MSDC_IOCON_D1SPL        (0x1 << 17)	/* RW */
+#define MSDC_IOCON_D2SPL        (0x1 << 18)	/* RW */
+#define MSDC_IOCON_D3SPL        (0x1 << 19)	/* RW */
+#define MSDC_IOCON_D4SPL        (0x1 << 20)	/* RW */
+#define MSDC_IOCON_D5SPL        (0x1 << 21)	/* RW */
+#define MSDC_IOCON_D6SPL        (0x1 << 22)	/* RW */
+#define MSDC_IOCON_D7SPL        (0x1 << 23)	/* RW */
+#define MSDC_IOCON_RISCSZ       (0x3 << 24)	/* RW */
+
+/* MSDC_PS mask */
+#define MSDC_PS_CDEN            (0x1 << 0)	/* RW */
+#define MSDC_PS_CDSTS           (0x1 << 1)	/* R  */
+#define MSDC_PS_CDDEBOUNCE      (0xf << 12)	/* RW */
+#define MSDC_PS_DAT             (0xff << 16)	/* R  */
+#define MSDC_PS_CMD             (0x1 << 24)	/* R  */
+#define MSDC_PS_WP              (0x1 << 31)	/* R  */
+
+/* MSDC_INT mask */
+#define MSDC_INT_MMCIRQ         (0x1 << 0)	/* W1C */
+#define MSDC_INT_CDSC           (0x1 << 1)	/* W1C */
+#define MSDC_INT_ACMDRDY        (0x1 << 3)	/* W1C */
+#define MSDC_INT_ACMDTMO        (0x1 << 4)	/* W1C */
+#define MSDC_INT_ACMDCRCERR     (0x1 << 5)	/* W1C */
+#define MSDC_INT_DMAQ_EMPTY     (0x1 << 6)	/* W1C */
+#define MSDC_INT_SDIOIRQ        (0x1 << 7)	/* W1C */
+#define MSDC_INT_CMDRDY         (0x1 << 8)	/* W1C */
+#define MSDC_INT_CMDTMO         (0x1 << 9)	/* W1C */
+#define MSDC_INT_RSPCRCERR      (0x1 << 10)	/* W1C */
+#define MSDC_INT_CSTA           (0x1 << 11)	/* R */
+#define MSDC_INT_XFER_COMPL     (0x1 << 12)	/* W1C */
+#define MSDC_INT_DXFER_DONE     (0x1 << 13)	/* W1C */
+#define MSDC_INT_DATTMO         (0x1 << 14)	/* W1C */
+#define MSDC_INT_DATCRCERR      (0x1 << 15)	/* W1C */
+#define MSDC_INT_ACMD19_DONE    (0x1 << 16)	/* W1C */
+#define MSDC_INT_DMA_BDCSERR    (0x1 << 17)	/* W1C */
+#define MSDC_INT_DMA_GPDCSERR   (0x1 << 18)	/* W1C */
+#define MSDC_INT_DMA_PROTECT    (0x1 << 19)	/* W1C */
+
+/* MSDC_INTEN mask */
+#define MSDC_INTEN_MMCIRQ       (0x1 << 0)	/* RW */
+#define MSDC_INTEN_CDSC         (0x1 << 1)	/* RW */
+#define MSDC_INTEN_ACMDRDY      (0x1 << 3)	/* RW */
+#define MSDC_INTEN_ACMDTMO      (0x1 << 4)	/* RW */
+#define MSDC_INTEN_ACMDCRCERR   (0x1 << 5)	/* RW */
+#define MSDC_INTEN_DMAQ_EMPTY   (0x1 << 6)	/* RW */
+#define MSDC_INTEN_SDIOIRQ      (0x1 << 7)	/* RW */
+#define MSDC_INTEN_CMDRDY       (0x1 << 8)	/* RW */
+#define MSDC_INTEN_CMDTMO       (0x1 << 9)	/* RW */
+#define MSDC_INTEN_RSPCRCERR    (0x1 << 10)	/* RW */
+#define MSDC_INTEN_CSTA         (0x1 << 11)	/* RW */
+#define MSDC_INTEN_XFER_COMPL   (0x1 << 12)	/* RW */
+#define MSDC_INTEN_DXFER_DONE   (0x1 << 13)	/* RW */
+#define MSDC_INTEN_DATTMO       (0x1 << 14)	/* RW */
+#define MSDC_INTEN_DATCRCERR    (0x1 << 15)	/* RW */
+#define MSDC_INTEN_ACMD19_DONE  (0x1 << 16)	/* RW */
+#define MSDC_INTEN_DMA_BDCSERR  (0x1 << 17)	/* RW */
+#define MSDC_INTEN_DMA_GPDCSERR (0x1 << 18)	/* RW */
+#define MSDC_INTEN_DMA_PROTECT  (0x1 << 19)	/* RW */
+
+/* MSDC_FIFOCS mask */
+#define MSDC_FIFOCS_RXCNT       (0xff << 0)	/* R */
+#define MSDC_FIFOCS_TXCNT       (0xff << 16)	/* R */
+#define MSDC_FIFOCS_CLR         (0x1 << 31)	/* RW */
+
+/* SDC_CFG mask */
+#define SDC_CFG_SDIOINTWKUP     (0x1 << 0)	/* RW */
+#define SDC_CFG_INSWKUP         (0x1 << 1)	/* RW */
+#define SDC_CFG_BUSWIDTH        (0x3 << 16)	/* RW */
+#define SDC_CFG_SDIO            (0x1 << 19)	/* RW */
+#define SDC_CFG_SDIOIDE         (0x1 << 20)	/* RW */
+#define SDC_CFG_INTATGAP        (0x1 << 21)	/* RW */
+#define SDC_CFG_DTOC            (0xff << 24)	/* RW */
+
+/* SDC_STS mask */
+#define SDC_STS_SDCBUSY         (0x1 << 0)	/* RW */
+#define SDC_STS_CMDBUSY         (0x1 << 1)	/* RW */
+#define SDC_STS_SWR_COMPL       (0x1 << 31)	/* RW */
+
+/* MSDC_DMA_CTRL mask */
+#define MSDC_DMA_CTRL_START     (0x1 << 0)	/* W */
+#define MSDC_DMA_CTRL_STOP      (0x1 << 1)	/* W */
+#define MSDC_DMA_CTRL_RESUME    (0x1 << 2)	/* W */
+#define MSDC_DMA_CTRL_MODE      (0x1 << 8)	/* RW */
+#define MSDC_DMA_CTRL_LASTBUF   (0x1 << 10)	/* RW */
+#define MSDC_DMA_CTRL_BRUSTSZ   (0x7 << 12)	/* RW */
+
+/* MSDC_DMA_CFG mask */
+#define MSDC_DMA_CFG_STS        (0x1 << 0)	/* R */
+#define MSDC_DMA_CFG_DECSEN     (0x1 << 1)	/* RW */
+#define MSDC_DMA_CFG_AHBHPROT2  (0x2 << 8)	/* RW */
+#define MSDC_DMA_CFG_ACTIVEEN   (0x2 << 12)	/* RW */
+#define MSDC_DMA_CFG_CS12B16B   (0x1 << 16)	/* RW */
+
+/* MSDC_PATCH_BIT mask */
+#define MSDC_PATCH_BIT_ODDSUPP    (0x1 <<  1)	/* RW */
+#define MSDC_INT_DAT_LATCH_CK_SEL (0x7 <<  7)
+#define MSDC_CKGEN_MSDC_DLY_SEL   (0x1f << 10)
+#define MSDC_PATCH_BIT_IODSSEL    (0x1 << 16)	/* RW */
+#define MSDC_PATCH_BIT_IOINTSEL   (0x1 << 17)	/* RW */
+#define MSDC_PATCH_BIT_BUSYDLY    (0xf << 18)	/* RW */
+#define MSDC_PATCH_BIT_WDOD       (0xf << 22)	/* RW */
+#define MSDC_PATCH_BIT_IDRTSEL    (0x1 << 26)	/* RW */
+#define MSDC_PATCH_BIT_CMDFSEL    (0x1 << 27)	/* RW */
+#define MSDC_PATCH_BIT_INTDLSEL   (0x1 << 28)	/* RW */
+#define MSDC_PATCH_BIT_SPCPUSH    (0x1 << 29)	/* RW */
+#define MSDC_PATCH_BIT_DECRCTMO   (0x1 << 30)	/* RW */
+
+#define REQ_CMD_EIO  (0x1 << 0)
+#define REQ_CMD_TMO  (0x1 << 1)
+#define REQ_DAT_ERR  (0x1 << 2)
+#define REQ_STOP_EIO (0x1 << 3)
+#define REQ_STOP_TMO (0x1 << 4)
+#define REQ_CMD_BUSY (0x1 << 5)
+
+#define MSDC_PREPARE_FLAG (0x1 << 0)
+#define MSDC_ASYNC_FLAG (0x1 << 1)
+#define MSDC_MMAP_FLAG (0x1 << 2)
+
+#define MTK_MMC_AUTOSUSPEND_DELAY	50
+#define CMD_TIMEOUT         (HZ/10 * 5)	/* 100ms x5 */
+#define DAT_TIMEOUT         (HZ    * 5)	/* 1000ms x5 */
+
+/*--------------------------------------------------------------------------*/
+/* Descriptor Structure                                                     */
+/*--------------------------------------------------------------------------*/
+struct mt_gpdma_desc {
+	u32 gpd_info;
+#define GPDMA_DESC_HWO		(0x1 << 0)
+#define GPDMA_DESC_BDP		(0x1 << 1)
+#define GPDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
+#define GPDMA_DESC_INT		(0x1 << 16)
+	u32 next;
+	u32 ptr;
+	u32 gpd_data_len;
+#define GPDMA_DESC_BUFLEN	(0xffff) /* bit0 ~ bit15 */
+#define GPDMA_DESC_EXTLEN	(0xff << 16) /* bit16 ~ bit23 */
+	u32 arg;
+	u32 blknum;
+	u32 cmd;
+};
+
+struct mt_bdma_desc {
+	u32 bd_info;
+#define BDMA_DESC_EOL		(0x1 << 0)
+#define BDMA_DESC_CHECKSUM	(0xff << 8) /* bit8 ~ bit15 */
+#define BDMA_DESC_BLKPAD	(0x1 << 17)
+#define BDMA_DESC_DWPAD		(0x1 << 18)
+	u32 next;
+	u32 ptr;
+	u32 bd_data_len;
+#define BDMA_DESC_BUFLEN	(0xffff) /* bit0 ~ bit15 */
+};
+
+struct msdc_dma {
+	struct scatterlist *sg;	/* I/O scatter list */
+	struct mt_gpdma_desc *gpd;		/* pointer to gpd array */
+	struct mt_bdma_desc *bd;		/* pointer to bd array */
+	dma_addr_t gpd_addr;	/* the physical address of gpd array */
+	dma_addr_t bd_addr;	/* the physical address of bd array */
+};
+
+struct msdc_save_para {
+	u32 msdc_cfg;
+	u32 iocon;
+	u32 sdc_cfg;
+	u32 pad_tune;
+	u32 patch_bit0;
+	u32 patch_bit1;
+};
+
+struct msdc_host {
+	struct device *dev;
+	struct mmc_host *mmc;	/* mmc structure */
+	int cmd_rsp;
+
+	spinlock_t lock;
+	struct mmc_request *mrq;
+	struct mmc_command *cmd;
+	struct mmc_data *data;
+	int error;
+
+	void __iomem *base;		/* host base address */
+
+	struct msdc_dma dma;	/* dma channel */
+	u64 dma_mask;
+
+	u32 timeout_ns;		/* data timeout ns */
+	u32 timeout_clks;	/* data timeout clks */
+
+	struct pinctrl *pinctrl;
+	struct pinctrl_state *pins_default;
+	struct pinctrl_state *pins_uhs;
+	struct delayed_work req_timeout;
+	int irq;		/* host interrupt */
+
+	struct clk *src_clk;	/* msdc source clock */
+	struct clk *h_clk;      /* msdc h_clk */
+	u32 mclk;		/* mmc subsystem clock frequency */
+	u32 src_clk_freq;	/* source clock frequency */
+	u32 sclk;		/* SD/MS bus clock frequency */
+	bool ddr;
+	bool vqmmc_enabled;
+	struct msdc_save_para save_para; /* used when gate HCLK */
+};
+
+static void sdr_set_bits(void __iomem *reg, u32 bs)
+{
+	u32 val = readl(reg);
+
+	val |= bs;
+	writel(val, reg);
+}
+
+static void sdr_clr_bits(void __iomem *reg, u32 bs)
+{
+	u32 val = readl(reg);
+
+	val &= ~bs;
+	writel(val, reg);
+}
+
+static void sdr_set_field(void __iomem *reg, u32 field, u32 val)
+{
+	unsigned int tv = readl(reg);
+
+	tv &= ~field;
+	tv |= ((val) << (ffs((unsigned int)field) - 1));
+	writel(tv, reg);
+}
+
+static void sdr_get_field(void __iomem *reg, u32 field, u32 *val)
+{
+	unsigned int tv = readl(reg);
+
+	*val = ((tv & field) >> (ffs((unsigned int)field) - 1));
+}
+
+static void msdc_reset_hw(struct msdc_host *host)
+{
+	u32 val;
+
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_RST);
+	while (readl(host->base + MSDC_CFG) & MSDC_CFG_RST)
+		cpu_relax();
+
+	sdr_set_bits(host->base + MSDC_FIFOCS, MSDC_FIFOCS_CLR);
+	while (readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_CLR)
+		cpu_relax();
+
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+}
+
+static void msdc_cmd_next(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd);
+
+static u32 data_ints_mask = MSDC_INTEN_XFER_COMPL | MSDC_INTEN_DATTMO |
+			MSDC_INTEN_DATCRCERR | MSDC_INTEN_DMA_BDCSERR |
+			MSDC_INTEN_DMA_GPDCSERR | MSDC_INTEN_DMA_PROTECT;
+
+static u8 msdc_dma_calcs(u8 *buf, u32 len)
+{
+	u32 i, sum = 0;
+
+	for (i = 0; i < len; i++)
+		sum += buf[i];
+	return 0xff - (u8) sum;
+}
+
+static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
+		struct mmc_data *data)
+{
+	unsigned int j, dma_len;
+	dma_addr_t dma_address;
+	u32 dma_ctrl;
+	struct scatterlist *sg;
+	struct mt_gpdma_desc *gpd;
+	struct mt_bdma_desc *bd;
+
+	sg = data->sg;
+
+	gpd = dma->gpd;
+	bd = dma->bd;
+
+	/* modify gpd */
+	gpd->gpd_info |= GPDMA_DESC_HWO;
+	gpd->gpd_info |= GPDMA_DESC_BDP;
+	/* need to clear first. use these bits to calc checksum */
+	gpd->gpd_info &= ~GPDMA_DESC_CHECKSUM;
+	gpd->gpd_info |= msdc_dma_calcs((u8 *) gpd, 16) << 8;
+
+	/* modify bd */
+	for_each_sg(data->sg, sg, data->sg_count, j) {
+		dma_address = sg_dma_address(sg);
+		dma_len = sg_dma_len(sg);
+
+		/* init bd */
+		bd[j].bd_info &= ~BDMA_DESC_BLKPAD;
+		bd[j].bd_info &= ~BDMA_DESC_DWPAD;
+		bd[j].ptr = (u32)dma_address;
+		bd[j].bd_data_len &= ~BDMA_DESC_BUFLEN;
+		bd[j].bd_data_len |= (dma_len & BDMA_DESC_BUFLEN);
+
+		if (j == data->sg_count - 1) /* the last bd */
+			bd[j].bd_info |= BDMA_DESC_EOL;
+		else
+			bd[j].bd_info &= ~BDMA_DESC_EOL;
+
+		/* checksume need to clear first */
+		bd[j].bd_info &= ~BDMA_DESC_CHECKSUM;
+		bd[j].bd_info |= msdc_dma_calcs((u8 *)(&bd[j]), 16) << 8;
+	}
+
+	sdr_set_field(host->base + MSDC_DMA_CFG, MSDC_DMA_CFG_DECSEN, 1);
+	dma_ctrl = readl_relaxed(host->base + MSDC_DMA_CTRL);
+	dma_ctrl &= ~(MSDC_DMA_CTRL_BRUSTSZ | MSDC_DMA_CTRL_MODE);
+	dma_ctrl |= (MSDC_BURST_64B << 12 | 1 << 8);
+	writel_relaxed(dma_ctrl, host->base + MSDC_DMA_CTRL);
+	writel((u32)dma->gpd_addr, host->base + MSDC_DMA_SA);
+}
+
+static void msdc_prepare_data(struct msdc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (!(data->host_cookie & MSDC_PREPARE_FLAG)) {
+		bool read = (data->flags & MMC_DATA_READ) != 0;
+
+		data->host_cookie |= MSDC_PREPARE_FLAG;
+		data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len,
+					   read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static void msdc_unprepare_data(struct msdc_host *host, struct mmc_request *mrq)
+{
+	struct mmc_data *data = mrq->data;
+
+	if (data->host_cookie & MSDC_ASYNC_FLAG)
+		return;
+
+	if (data->host_cookie & MSDC_PREPARE_FLAG) {
+		bool read = (data->flags & MMC_DATA_READ) != 0;
+
+		dma_unmap_sg(host->dev, data->sg, data->sg_len,
+			     read ? DMA_FROM_DEVICE : DMA_TO_DEVICE);
+		data->host_cookie &= ~MSDC_PREPARE_FLAG;
+	}
+}
+
+/* clock control primitives */
+static void msdc_set_timeout(struct msdc_host *host, u32 ns, u32 clks)
+{
+	u32 timeout, clk_ns;
+	u32 mode = 0;
+
+	host->timeout_ns = ns;
+	host->timeout_clks = clks;
+	if (host->sclk == 0) {
+		timeout = 0;
+	} else {
+		clk_ns  = 1000000000UL / host->sclk;
+		timeout = (ns + clk_ns - 1) / clk_ns + clks;
+		/* in 1048576 sclk cycle unit */
+		timeout = (timeout + (0x1 << 20) - 1) >> 20;
+		sdr_get_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD, &mode);
+		/*DDR mode will double the clk cycles for data timeout */
+		timeout = mode >= 2 ? timeout * 2 : timeout;
+		timeout = timeout > 1 ? timeout - 1 : 0;
+		timeout = timeout > 255 ? 255 : timeout;
+	}
+	sdr_set_field(host->base + SDC_CFG, SDC_CFG_DTOC, timeout);
+}
+
+static void msdc_gate_clock(struct msdc_host *host)
+{
+	clk_disable_unprepare(host->src_clk);
+	clk_disable_unprepare(host->h_clk);
+}
+
+static void msdc_ungate_clock(struct msdc_host *host)
+{
+	clk_prepare_enable(host->h_clk);
+	clk_prepare_enable(host->src_clk);
+	while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
+		cpu_relax();
+}
+
+static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
+{
+	u32 mode;
+	u32 flags;
+	u32 div;
+	u32 sclk;
+
+	if (!hz) {
+		dev_dbg(host->dev, "set mclk to 0\n");
+		host->mclk = 0;
+		sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
+		return;
+	}
+
+	flags = readl(host->base + MSDC_INTEN);
+	sdr_clr_bits(host->base + MSDC_INTEN, flags);
+	if (ddr) { /* may need to modify later */
+		mode = 0x2; /* ddr mode and use divisor */
+		if (hz >= (host->src_clk_freq >> 2)) {
+			div = 0; /* mean div = 1/4 */
+			sclk = host->src_clk_freq >> 2; /* sclk = clk / 4 */
+		} else {
+			div = (host->src_clk_freq + ((hz << 2) - 1)) / (hz << 2);
+			sclk = (host->src_clk_freq >> 2) / div;
+			div = (div >> 1);
+		}
+	} else if (hz >= host->src_clk_freq) {
+		mode = 0x1; /* no divisor */
+		div = 0;
+		sclk = host->src_clk_freq;
+	} else {
+		mode = 0x0; /* use divisor */
+		if (hz >= (host->src_clk_freq >> 1)) {
+			div = 0; /* mean div = 1/2 */
+			sclk = host->src_clk_freq >> 1; /* sclk = clk / 2 */
+		} else {
+			div = (host->src_clk_freq + ((hz << 2) - 1)) / (hz << 2);
+			sclk = (host->src_clk_freq >> 2) / div;
+		}
+	}
+	sdr_set_field(host->base + MSDC_CFG, MSDC_CFG_CKMOD | MSDC_CFG_CKDIV,
+			(mode << 8) | (div % 0xff));
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_CKPDN);
+	while (!(readl(host->base + MSDC_CFG) & MSDC_CFG_CKSTB))
+		cpu_relax();
+	host->sclk = sclk;
+	host->mclk = hz;
+	host->ddr = ddr;
+	/* need because clk changed. */
+	msdc_set_timeout(host, host->timeout_ns, host->timeout_clks);
+	sdr_set_bits(host->base + MSDC_INTEN, flags);
+
+	dev_dbg(host->dev, "sclk: %d, ddr: %d\n", host->sclk, ddr);
+}
+
+static inline u32 msdc_cmd_find_resp(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	u32 resp;
+
+	switch (mmc_resp_type(cmd)) {
+		/* Actually, R1, R5, R6, R7 are the same */
+	case MMC_RSP_R1:
+		resp = 0x1;
+		break;
+	case MMC_RSP_R1B:
+		resp = 0x7;
+		break;
+	case MMC_RSP_R2:
+		resp = 0x2;
+		break;
+	case MMC_RSP_R3:
+		resp = 0x3;
+		break;
+	case MMC_RSP_NONE:
+	default:
+		resp = 0x0;
+		break;
+	}
+
+	return resp;
+}
+
+static inline u32 msdc_cmd_prepare_raw_cmd(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	/* rawcmd :
+	 * vol_swt << 30 | auto_cmd << 28 | blklen << 16 | go_irq << 15 |
+	 * stop << 14 | rw << 13 | dtype << 11 | rsptyp << 7 | brk << 6 | opcode
+	 */
+	u32 opcode = cmd->opcode;
+	u32 resp = msdc_cmd_find_resp(host, mrq, cmd);
+	u32 rawcmd = (opcode & 0x3f) | ((resp & 0x7) << 7);
+
+	host->cmd_rsp = resp;
+
+	if ((opcode == SD_IO_RW_DIRECT && cmd->flags == (unsigned int) -1) ||
+	    opcode == MMC_STOP_TRANSMISSION)
+		rawcmd |= (0x1 << 14);
+	else if (opcode == SD_SWITCH_VOLTAGE)
+		rawcmd |= (0x1 << 30);
+	else if (opcode == SD_APP_SEND_SCR ||
+		 opcode == SD_APP_SEND_NUM_WR_BLKS ||
+		 (opcode == SD_SWITCH && mmc_cmd_type(cmd) == MMC_CMD_ADTC) ||
+		 (opcode == SD_APP_SD_STATUS && mmc_cmd_type(cmd) == MMC_CMD_ADTC) ||
+		 (opcode == MMC_SEND_EXT_CSD && mmc_cmd_type(cmd) == MMC_CMD_ADTC))
+		rawcmd |= (0x1 << 11);
+
+	if (cmd->data) {
+		struct mmc_data *data = cmd->data;
+
+		if (mmc_op_multi(opcode)) {
+			if (mmc_card_mmc(host->mmc->card) && mrq->sbc &&
+			    !(mrq->sbc->arg & 0xFFFF0000))
+				rawcmd |= 0x2 << 28; /* AutoCMD23 */
+		}
+
+		rawcmd |= ((data->blksz & 0xFFF) << 16);
+		if (data->flags & MMC_DATA_WRITE)
+			rawcmd |= (0x1 << 13);
+		if (data->blocks > 1)
+			rawcmd |= (0x2 << 11);
+		else
+			rawcmd |= (0x1 << 11);
+		/* Always use dma mode */
+		sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_PIO);
+
+		if (host->timeout_ns != data->timeout_ns ||
+		    host->timeout_clks != data->timeout_clks)
+			msdc_set_timeout(host, data->timeout_ns,
+					data->timeout_clks);
+
+		writel(data->blocks, host->base + SDC_BLK_NUM);
+	}
+	return rawcmd;
+}
+
+static void msdc_start_data(struct msdc_host *host, struct mmc_request *mrq,
+			    struct mmc_command *cmd, struct mmc_data *data)
+{
+	bool read;
+
+	WARN_ON(host->data);
+	host->data = data;
+	read = data->flags & MMC_DATA_READ;
+
+	mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT);
+	msdc_dma_setup(host, &host->dma, data);
+	sdr_set_bits(host->base + MSDC_INTEN, data_ints_mask);
+	sdr_set_field(host->base + MSDC_DMA_CTRL, MSDC_DMA_CTRL_START, 1);
+	dev_dbg(host->dev, "DMA start\n");
+	dev_dbg(host->dev, "%s: cmd=%d DMA data: %d blocks; read=%d\n",
+			__func__, cmd->opcode, data->blocks, read);
+}
+
+static int msdc_auto_cmd_done(struct msdc_host *host, int events,
+		struct mmc_command *cmd)
+{
+	u32 *rsp = cmd->resp;
+
+	rsp[0] = readl(host->base + SDC_ACMD_RESP);
+
+	if (events & MSDC_INT_ACMDRDY) {
+		cmd->error = 0;
+	} else {
+		msdc_reset_hw(host);
+		if (events & MSDC_INT_ACMDCRCERR) {
+			cmd->error = -EILSEQ;
+			host->error |= REQ_STOP_EIO;
+		} else if (events & MSDC_INT_ACMDTMO) {
+			cmd->error = -ETIMEDOUT;
+			host->error |= REQ_STOP_TMO;
+		}
+		dev_err(host->dev,
+			"%s: AUTO_CMD%d arg=%08X; rsp %08X; cmd_error=%d\n",
+			__func__, cmd->opcode, cmd->arg, rsp[0], cmd->error);
+	}
+	return cmd->error;
+}
+
+static void msdc_track_cmd_data(struct msdc_host *host,
+				struct mmc_command *cmd, struct mmc_data *data)
+{
+	if (host->error)
+		dev_dbg(host->dev, "%s: cmd=%d arg=%08X; host->error=0x%08X\n",
+			__func__, cmd->opcode, cmd->arg, host->error);
+}
+
+static void msdc_request_done(struct msdc_host *host, struct mmc_request *mrq)
+{
+	unsigned long flags;
+	bool ret;
+
+	ret = cancel_delayed_work(&host->req_timeout);
+	if (!ret) {
+		/* delay work already running */
+		return;
+	}
+	spin_lock_irqsave(&host->lock, flags);
+	host->mrq = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	msdc_track_cmd_data(host, mrq->cmd, mrq->data);
+	if (mrq->data)
+		msdc_unprepare_data(host, mrq);
+	mmc_request_done(host->mmc, mrq);
+
+	pm_runtime_mark_last_busy(host->dev);
+	pm_runtime_put_autosuspend(host->dev);
+}
+
+/* returns true if command is fully handled; returns false otherwise */
+static bool msdc_cmd_done(struct msdc_host *host, int events,
+			  struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	bool done = false;
+	bool sbc_error;
+	unsigned long flags;
+	u32 *rsp = cmd->resp;
+
+	if (mrq->sbc && cmd == mrq->cmd &&
+	    (events & (MSDC_INT_ACMDRDY | MSDC_INT_ACMDCRCERR
+				   | MSDC_INT_ACMDTMO)))
+		msdc_auto_cmd_done(host, events, mrq->sbc);
+
+	sbc_error = mrq->sbc && mrq->sbc->error;
+
+	if (!sbc_error && !(events & (MSDC_INT_CMDRDY
+					| MSDC_INT_RSPCRCERR
+					| MSDC_INT_CMDTMO)))
+		return done;
+
+	spin_lock_irqsave(&host->lock, flags);
+	done = !host->cmd;
+	host->cmd = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (done)
+		return true;
+
+	sdr_clr_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
+			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
+			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
+			MSDC_INTEN_ACMDTMO);
+	writel(cmd->arg, host->base + SDC_ARG);
+
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		if (cmd->flags & MMC_RSP_136) {
+			rsp[0] = readl(host->base + SDC_RESP3);
+			rsp[1] = readl(host->base + SDC_RESP2);
+			rsp[2] = readl(host->base + SDC_RESP1);
+			rsp[3] = readl(host->base + SDC_RESP0);
+		} else {
+			rsp[0] = readl(host->base + SDC_RESP0);
+		}
+	}
+
+	if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
+		msdc_reset_hw(host);
+		if (events & MSDC_INT_RSPCRCERR) {
+			cmd->error = -EILSEQ;
+			host->error |= REQ_CMD_EIO;
+		} else if (events & MSDC_INT_CMDTMO) {
+			cmd->error = -ETIMEDOUT;
+			host->error |= REQ_CMD_TMO;
+		}
+	}
+	if (cmd->error)
+		dev_dbg(host->dev,
+				"%s: cmd=%d arg=%08X; rsp %08X; cmd_error=%d\n",
+				__func__, cmd->opcode, cmd->arg, rsp[0],
+				cmd->error);
+
+	msdc_cmd_next(host, mrq, cmd);
+	return true;
+}
+
+/* It is the core layer's responsibility to ensure card status
+ * is correct before issue a request. but host design do below
+ * checks recommended.
+ */
+static inline bool msdc_cmd_is_ready(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	/* The max busy time we can endure is 20ms */
+	unsigned long tmo = jiffies + msecs_to_jiffies(20);
+
+	while ((readl(host->base + SDC_STS) & SDC_STS_CMDBUSY) &&
+			time_before(jiffies, tmo))
+		cpu_relax();
+	if (readl(host->base + SDC_STS) & SDC_STS_CMDBUSY) {
+		dev_err(host->dev, "CMD bus busy detected\n");
+		host->error |= REQ_CMD_BUSY;
+		msdc_cmd_done(host, MSDC_INT_CMDTMO, mrq, cmd);
+		return false;
+	}
+
+	if (mmc_resp_type(cmd) == MMC_RSP_R1B || cmd->data) {
+		tmo = jiffies + msecs_to_jiffies(20);
+		/* R1B or with data, should check SDCBUSY */
+		while ((readl(host->base + SDC_STS) & SDC_STS_SDCBUSY) &&
+				time_before(jiffies, tmo))
+			cpu_relax();
+		if (readl(host->base + SDC_STS) & SDC_STS_SDCBUSY) {
+			dev_err(host->dev, "Controller busy detected\n");
+			host->error |= REQ_CMD_BUSY;
+			msdc_cmd_done(host, MSDC_INT_CMDTMO, mrq, cmd);
+			return false;
+		}
+	}
+	return true;
+}
+
+static void msdc_start_command(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	u32 rawcmd;
+
+	WARN_ON(host->cmd);
+	host->cmd = cmd;
+
+	if (!msdc_cmd_is_ready(host, mrq, cmd))
+		return;
+
+	if ((readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_TXCNT) >> 16 ||
+	    readl(host->base + MSDC_FIFOCS) & MSDC_FIFOCS_RXCNT) {
+		dev_err(host->dev, "TX/RX FIFO non-empty before start of IO. Reset\n");
+		msdc_reset_hw(host);
+	}
+
+	cmd->error = 0;
+	rawcmd = msdc_cmd_prepare_raw_cmd(host, mrq, cmd);
+	mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT);
+
+	sdr_set_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
+			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
+			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
+			MSDC_INTEN_ACMDTMO);
+	writel(cmd->arg, host->base + SDC_ARG);
+	writel(rawcmd, host->base + SDC_CMD);
+}
+
+static void msdc_cmd_next(struct msdc_host *host,
+		struct mmc_request *mrq, struct mmc_command *cmd)
+{
+	if (cmd->error || (mrq->sbc && mrq->sbc->error))
+		msdc_request_done(host, mrq);
+	else if (cmd == mrq->sbc)
+		msdc_start_command(host, mrq, mrq->cmd);
+	else if (!cmd->data)
+		msdc_request_done(host, mrq);
+	else
+		msdc_start_data(host, mrq, cmd, cmd->data);
+}
+
+static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+
+	host->error = 0;
+	WARN_ON(host->mrq);
+	host->mrq = mrq;
+
+	pm_runtime_get_sync(host->dev);
+
+	if (mrq->data)
+		msdc_prepare_data(host, mrq);
+
+	/* if SBC is required, we have HW option and SW option.
+	 * if HW option is enabled, and SBC does not have "special" flags,
+	 * use HW option,  otherwise use SW option
+	 */
+	if (mrq->sbc && (!mmc_card_mmc(mmc->card) ||
+	    (mrq->sbc->arg & 0xFFFF0000)))
+		msdc_start_command(host, mrq, mrq->sbc);
+	else
+		msdc_start_command(host, mrq, mrq->cmd);
+}
+
+static void msdc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		bool is_first_req)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (!data)
+		return;
+
+	msdc_prepare_data(host, mrq);
+	data->host_cookie |= MSDC_ASYNC_FLAG;
+}
+
+static void msdc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		int err)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	struct mmc_data *data;
+
+	data = mrq->data;
+	if (!data)
+		return;
+	if (data->host_cookie) {
+		data->host_cookie &= ~MSDC_ASYNC_FLAG;
+		msdc_unprepare_data(host, mrq);
+	}
+}
+
+static void msdc_data_xfer_next(struct msdc_host *host,
+				struct mmc_request *mrq, struct mmc_data *data)
+{
+	if (mmc_op_multi(mrq->cmd->opcode) && mrq->stop && !mrq->stop->error &&
+	    (!data->bytes_xfered || !mrq->sbc))
+		msdc_start_command(host, mrq, mrq->stop);
+	else
+		msdc_request_done(host, mrq);
+}
+
+static bool msdc_data_xfer_done(struct msdc_host *host, u32 events,
+				struct mmc_request *mrq, struct mmc_data *data)
+{
+	struct mmc_command *stop = data->stop;
+	unsigned long flags;
+	bool done;
+	unsigned int check_data = events &
+	    (MSDC_INT_XFER_COMPL | MSDC_INT_DATCRCERR | MSDC_INT_DATTMO
+	     | MSDC_INT_DMA_BDCSERR | MSDC_INT_DMA_GPDCSERR
+	     | MSDC_INT_DMA_PROTECT);
+
+	spin_lock_irqsave(&host->lock, flags);
+	done = !host->data;
+	if (check_data)
+		host->data = NULL;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (done)
+		return true;
+
+	if (check_data || (stop && stop->error)) {
+		dev_dbg(host->dev, "DMA status: 0x%8X\n",
+				readl(host->base + MSDC_DMA_CFG));
+		sdr_set_field(host->base + MSDC_DMA_CTRL, MSDC_DMA_CTRL_STOP,
+				1);
+		while (readl(host->base + MSDC_DMA_CFG) & MSDC_DMA_CFG_STS)
+			cpu_relax();
+		sdr_clr_bits(host->base + MSDC_INTEN, data_ints_mask);
+		dev_dbg(host->dev, "DMA stop\n");
+
+		if ((events & MSDC_INT_XFER_COMPL) && (!stop || !stop->error)) {
+			data->bytes_xfered = data->blocks * data->blksz;
+		} else {
+			dev_err(host->dev, "interrupt events: %x\n", events);
+			msdc_reset_hw(host);
+			host->error |= REQ_DAT_ERR;
+			data->bytes_xfered = 0;
+
+			if (events & MSDC_INT_DATTMO)
+				data->error = -ETIMEDOUT;
+
+			dev_err(host->dev, "%s: cmd=%d; blocks=%d",
+				__func__, mrq->cmd->opcode, data->blocks);
+			dev_err(host->dev, "data_error=%d xfer_size=%d\n",
+					(int)data->error, data->bytes_xfered);
+		}
+
+		msdc_data_xfer_next(host, mrq, data);
+		done = true;
+	}
+	return done;
+}
+
+static void msdc_set_buswidth(struct msdc_host *host, u32 width)
+{
+	u32 val = readl(host->base + SDC_CFG);
+
+	val &= ~SDC_CFG_BUSWIDTH;
+
+	switch (width) {
+	default:
+	case MMC_BUS_WIDTH_1:
+		val |= (MSDC_BUS_1BITS << 16);
+		break;
+	case MMC_BUS_WIDTH_4:
+		val |= (MSDC_BUS_4BITS << 16);
+		break;
+	case MMC_BUS_WIDTH_8:
+		val |= (MSDC_BUS_8BITS << 16);
+		break;
+	}
+
+	writel(val, host->base + SDC_CFG);
+	dev_dbg(host->dev, "Bus Width = %d", width);
+}
+
+static int msdc_ops_switch_volt(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	int min_uv, max_uv;
+	int ret = 0;
+
+	if (!IS_ERR(mmc->supply.vqmmc)) {
+		if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
+			min_uv = 3300000;
+			max_uv = 3300000;
+		} else if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) {
+			min_uv = 1800000;
+			max_uv = 1800000;
+		} else {
+			dev_err(host->dev, "Unsupported signal voltage!\n");
+			return -EINVAL;
+		}
+
+		ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+		if (ret) {
+			dev_err(host->dev,
+					"Regulator set error %d: %d - %d\n",
+					ret, min_uv, max_uv);
+		} else {
+			/* Apply different pinctrl settings for different signal voltage */
+			if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180)
+				pinctrl_select_state(host->pinctrl, host->pins_uhs);
+			else
+				pinctrl_select_state(host->pinctrl, host->pins_default);
+		}
+	}
+	return ret;
+}
+
+static int msdc_card_busy(struct mmc_host *mmc)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	u32 status = readl(host->base + MSDC_PS);
+
+	/* check if any pin between dat[0:3] is low */
+	if (((status >> 16) & 0xf) != 0xf)
+		return 1;
+
+	return 0;
+}
+
+static void msdc_request_timeout(struct work_struct *work)
+{
+	struct msdc_host *host = container_of(work, struct msdc_host,
+			req_timeout.work);
+
+	/* simulate HW timeout status */
+	dev_err(host->dev, "%s: aborting cmd/data/mrq\n", __func__);
+	if (host->mrq) {
+		dev_err(host->dev, "%s: aborting mrq=%p cmd=%d\n", __func__,
+				host->mrq, host->mrq->cmd->opcode);
+		if (host->cmd) {
+			dev_err(host->dev, "%s: aborting cmd=%d\n",
+					__func__, host->cmd->opcode);
+			msdc_cmd_done(host, MSDC_INT_CMDTMO, host->mrq,
+					host->cmd);
+		} else if (host->data) {
+			dev_err(host->dev, "%s: abort data: cmd%d; %d blocks\n",
+					__func__, host->mrq->cmd->opcode,
+					host->data->blocks);
+			msdc_data_xfer_done(host, MSDC_INT_DATTMO, host->mrq,
+					host->data);
+		}
+	}
+}
+
+static irqreturn_t msdc_irq(int irq, void *dev_id)
+{
+	struct msdc_host *host = (struct msdc_host *) dev_id;
+
+	while (true) {
+		unsigned long flags;
+		struct mmc_request *mrq;
+		struct mmc_command *cmd;
+		struct mmc_data *data;
+		u32 events, event_mask;
+
+		spin_lock_irqsave(&host->lock, flags);
+		events = readl(host->base + MSDC_INT);
+		event_mask = readl(host->base + MSDC_INTEN);
+		/* clear interrupts */
+		writel(events & event_mask, host->base + MSDC_INT);
+
+		mrq = host->mrq;
+		cmd = host->cmd;
+		data = host->data;
+		spin_unlock_irqrestore(&host->lock, flags);
+
+		if (!(events & event_mask))
+			break;
+
+		if (!mrq) {
+			dev_err(host->dev,
+				"%s: MRQ=NULL; events=%08X; event_mask=%08X\n",
+				__func__, events, event_mask);
+			WARN_ON(1);
+			break;
+		}
+
+		dev_dbg(host->dev, "%s: events=%08X\n", __func__, events);
+
+		if (cmd)
+			msdc_cmd_done(host, events, mrq, cmd);
+		else if (data)
+			msdc_data_xfer_done(host, events, mrq, data);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void msdc_init_hw(struct msdc_host *host)
+{
+	u32 val;
+
+	/* Configure to MMC/SD mode, clock free running */
+	sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_MODE | MSDC_CFG_CKPDN);
+
+	/* Reset */
+	msdc_reset_hw(host);
+
+	/* Disable card detection */
+	sdr_clr_bits(host->base + MSDC_PS, MSDC_PS_CDEN);
+
+	/* Disable and clear all interrupts */
+	writel(0, host->base + MSDC_INTEN);
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+
+	writel(0, host->base + MSDC_PAD_TUNE);
+	writel(0, host->base + MSDC_IOCON);
+	sdr_set_field(host->base + MSDC_IOCON, MSDC_IOCON_DDLSEL, 1);
+	writel(0x403c004f, host->base + MSDC_PATCH_BIT);
+	sdr_set_field(host->base + MSDC_PATCH_BIT, MSDC_CKGEN_MSDC_DLY_SEL, 1);
+	writel(0xffff0089, host->base + MSDC_PATCH_BIT1);
+	/* Configure to enable SDIO mode.
+	 * it's must otherwise sdio cmd5 failed
+	 */
+	sdr_set_bits(host->base + SDC_CFG, SDC_CFG_SDIO);
+
+	/* disable detect SDIO device interrupt function */
+	sdr_clr_bits(host->base + SDC_CFG, SDC_CFG_SDIOIDE);
+
+	/* Configure to default data timeout */
+	sdr_set_field(host->base + SDC_CFG, SDC_CFG_DTOC, 3);
+
+	dev_dbg(host->dev, "init hardware done!");
+}
+
+static void msdc_deinit_hw(struct msdc_host *host)
+{
+	u32 val;
+	/* Disable and clear all interrupts */
+	writel(0, host->base + MSDC_INTEN);
+
+	val = readl(host->base + MSDC_INT);
+	writel(val, host->base + MSDC_INT);
+}
+
+/* init gpd and bd list in msdc_drv_probe */
+static void msdc_init_gpd_bd(struct msdc_host *host, struct msdc_dma *dma)
+{
+	struct mt_gpdma_desc *gpd = dma->gpd;
+	struct mt_bdma_desc *bd = dma->bd;
+	int i;
+
+	memset(gpd, 0, sizeof(struct mt_gpdma_desc));
+
+	gpd->gpd_info = GPDMA_DESC_BDP; /* hwo, cs, bd pointer */
+	gpd->ptr = (u32)dma->bd_addr; /* physical address */
+
+	memset(bd, 0, sizeof(struct mt_bdma_desc) * MAX_BD_NUM);
+	for (i = 0; i < (MAX_BD_NUM - 1); i++)
+		bd[i].next = (u32)dma->bd_addr + sizeof(*bd) * (i + 1);
+}
+
+static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	int ret;
+	u32 ddr = 0;
+
+	pm_runtime_get_sync(host->dev);
+
+	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
+	    ios->timing == MMC_TIMING_MMC_DDR52)
+		ddr = 1;
+
+	msdc_set_buswidth(host, ios->bus_width);
+
+	/* Suspend/Resume will do power off/on */
+	switch (ios->power_mode) {
+	case MMC_POWER_UP:
+		if (!IS_ERR(mmc->supply.vmmc)) {
+			ret = mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
+					ios->vdd);
+			if (ret) {
+				dev_err(host->dev, "Failed to set vmmc power!\n");
+				goto end;
+			}
+		}
+		break;
+	case MMC_POWER_ON:
+		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
+			ret = regulator_enable(mmc->supply.vqmmc);
+			if (ret)
+				dev_err(host->dev, "Failed to set vqmmc power!\n");
+			else
+				host->vqmmc_enabled = true;
+		}
+		break;
+	case MMC_POWER_OFF:
+		if (!IS_ERR(mmc->supply.vmmc))
+			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);
+
+		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
+			regulator_disable(mmc->supply.vqmmc);
+			host->vqmmc_enabled = false;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (host->mclk != ios->clock || host->ddr != ddr)
+		msdc_set_mclk(host, ddr, ios->clock);
+
+end:
+	pm_runtime_mark_last_busy(host->dev);
+	pm_runtime_put_autosuspend(host->dev);
+}
+
+static struct mmc_host_ops mt_msdc_ops = {
+	.post_req = msdc_post_req,
+	.pre_req = msdc_pre_req,
+	.request = msdc_ops_request,
+	.set_ios = msdc_ops_set_ios,
+	.start_signal_voltage_switch = msdc_ops_switch_volt,
+	.card_busy = msdc_card_busy,
+};
+
+static int msdc_drv_probe(struct platform_device *pdev)
+{
+	struct mmc_host *mmc;
+	struct msdc_host *host;
+	struct resource *res;
+	int ret;
+
+	if (!pdev->dev.of_node) {
+		dev_err(&pdev->dev, "No DT found\n");
+		return -EINVAL;
+	}
+	/* Allocate MMC host for this device */
+	mmc = mmc_alloc_host(sizeof(struct msdc_host), &pdev->dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	host = mmc_priv(mmc);
+	ret = mmc_of_parse(mmc);
+	if (ret)
+		goto host_free;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	host->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
+		goto host_free;
+	}
+
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret == -EPROBE_DEFER)
+		goto host_free;
+
+	host->src_clk = devm_clk_get(&pdev->dev, "source");
+	if (IS_ERR(host->src_clk)) {
+		ret = PTR_ERR(host->src_clk);
+		goto host_free;
+	}
+
+	host->h_clk = devm_clk_get(&pdev->dev, "hclk");
+	if (IS_ERR(host->h_clk)) {
+		ret = PTR_ERR(host->h_clk);
+		goto host_free;
+	}
+
+	host->irq = platform_get_irq(pdev, 0);
+	if (host->irq < 0) {
+		ret = -EINVAL;
+		goto host_free;
+	}
+
+	host->pinctrl = devm_pinctrl_get(&pdev->dev);
+	if (IS_ERR(host->pinctrl)) {
+		ret = PTR_ERR(host->pinctrl);
+		dev_err(&pdev->dev, "Cannot find pinctrl!\n");
+		goto host_free;
+	}
+
+	host->pins_default = pinctrl_lookup_state(host->pinctrl, "default");
+	if (IS_ERR(host->pins_default)) {
+		ret = PTR_ERR(host->pins_default);
+		dev_err(&pdev->dev, "Cannot find pinctrl default!\n");
+		goto host_free;
+	}
+
+	host->pins_uhs = pinctrl_lookup_state(host->pinctrl, "state_uhs");
+	if (IS_ERR(host->pins_uhs)) {
+		ret = PTR_ERR(host->pins_uhs);
+		dev_err(&pdev->dev, "Cannot find pinctrl uhs!\n");
+		goto host_free;
+	}
+
+	host->dev = &pdev->dev;
+	host->mmc = mmc;
+	host->src_clk_freq = clk_get_rate(host->src_clk);
+	/* Set host parameters to mmc */
+	mmc->ops = &mt_msdc_ops;
+	mmc->f_min = host->src_clk_freq / (4 * 255);
+
+	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
+	/* MMC core transfer sizes tunable parameters */
+	mmc->max_segs = MAX_BD_NUM;
+	mmc->max_seg_size = BDMA_DESC_BUFLEN;
+	mmc->max_blk_size = 2048;
+	mmc->max_req_size = 512 * 1024;
+	mmc->max_blk_count = mmc->max_req_size / 512;
+	host->dma_mask = DMA_BIT_MASK(32);
+	mmc_dev(mmc)->dma_mask = &host->dma_mask;
+
+	host->timeout_clks = 3 * 1048576;
+	host->dma.gpd = dma_alloc_coherent(&pdev->dev,
+				sizeof(struct mt_gpdma_desc),
+				&host->dma.gpd_addr, GFP_KERNEL);
+	host->dma.bd = dma_alloc_coherent(&pdev->dev,
+				MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+				&host->dma.bd_addr, GFP_KERNEL);
+	if (!host->dma.gpd || !host->dma.bd) {
+		ret = -ENOMEM;
+		goto release_mem;
+	}
+	msdc_init_gpd_bd(host, &host->dma);
+	INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
+	spin_lock_init(&host->lock);
+
+	platform_set_drvdata(pdev, mmc);
+	msdc_ungate_clock(host);
+	msdc_init_hw(host);
+
+	ret = devm_request_irq(&pdev->dev, host->irq, msdc_irq,
+		IRQF_TRIGGER_LOW | IRQF_ONESHOT, pdev->name, host);
+	if (ret)
+		goto release;
+
+	pm_runtime_set_active(host->dev);
+	pm_runtime_set_autosuspend_delay(host->dev, MTK_MMC_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(host->dev);
+	pm_runtime_enable(host->dev);
+	ret = mmc_add_host(mmc);
+
+	if (ret)
+		goto end;
+
+	return 0;
+end:
+	pm_runtime_disable(host->dev);
+release:
+	platform_set_drvdata(pdev, NULL);
+	msdc_deinit_hw(host);
+	msdc_gate_clock(host);
+release_mem:
+	if (host->dma.gpd)
+		dma_free_coherent(&pdev->dev,
+			sizeof(struct mt_gpdma_desc),
+			host->dma.gpd, host->dma.gpd_addr);
+	if (host->dma.bd)
+		dma_free_coherent(&pdev->dev,
+			MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+			host->dma.bd, host->dma.bd_addr);
+host_free:
+	mmc_free_host(mmc);
+
+	return ret;
+}
+
+static int msdc_drv_remove(struct platform_device *pdev)
+{
+	struct mmc_host *mmc;
+	struct msdc_host *host;
+
+	mmc = platform_get_drvdata(pdev);
+	host = mmc_priv(mmc);
+
+	pm_runtime_get_sync(host->dev);
+
+	platform_set_drvdata(pdev, NULL);
+	mmc_remove_host(host->mmc);
+	msdc_deinit_hw(host);
+	msdc_gate_clock(host);
+
+	pm_runtime_disable(host->dev);
+	pm_runtime_put_noidle(host->dev);
+	dma_free_coherent(&pdev->dev,
+			sizeof(struct mt_gpdma_desc),
+			host->dma.gpd, host->dma.gpd_addr);
+	dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+			host->dma.bd, host->dma.bd_addr);
+
+	mmc_free_host(host->mmc);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static void msdc_save_reg(struct msdc_host *host)
+{
+	host->save_para.msdc_cfg = readl(host->base + MSDC_CFG);
+	host->save_para.iocon = readl(host->base + MSDC_IOCON);
+	host->save_para.sdc_cfg = readl(host->base + SDC_CFG);
+	host->save_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
+	host->save_para.patch_bit0 = readl(host->base + MSDC_PATCH_BIT);
+	host->save_para.patch_bit1 = readl(host->base + MSDC_PATCH_BIT1);
+}
+
+static void msdc_restore_reg(struct msdc_host *host)
+{
+	writel(host->save_para.msdc_cfg, host->base + MSDC_CFG);
+	writel(host->save_para.iocon, host->base + MSDC_IOCON);
+	writel(host->save_para.sdc_cfg, host->base + SDC_CFG);
+	writel(host->save_para.pad_tune, host->base + MSDC_PAD_TUNE);
+	writel(host->save_para.patch_bit0, host->base + MSDC_PATCH_BIT);
+	writel(host->save_para.patch_bit1, host->base + MSDC_PATCH_BIT1);
+}
+
+static int msdc_runtime_suspend(struct device *dev)
+{
+	struct mmc_host *mmc = dev_get_drvdata(dev);
+	struct msdc_host *host = mmc_priv(mmc);
+
+	msdc_save_reg(host);
+	msdc_gate_clock(host);
+	return 0;
+}
+
+static int msdc_runtime_resume(struct device *dev)
+{
+	struct mmc_host *mmc = dev_get_drvdata(dev);
+	struct msdc_host *host = mmc_priv(mmc);
+
+	msdc_ungate_clock(host);
+	msdc_restore_reg(host);
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops msdc_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(msdc_runtime_suspend, msdc_runtime_resume, NULL)
+};
+
+static const struct of_device_id msdc_of_ids[] = {
+	{   .compatible = "mediatek,mt8135-mmc", },
+	{}
+};
+
+static struct platform_driver mt_msdc_driver = {
+	.probe = msdc_drv_probe,
+	.remove = msdc_drv_remove,
+	.driver = {
+		.name = "mtk-msdc",
+		.of_match_table = msdc_of_ids,
+		.pm = &msdc_dev_pm_ops,
+	},
+};
+
+module_platform_driver(mt_msdc_driver);
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MediaTek SD/MMC Card Driver");
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 317d709f7550..d110f9e98c4b 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -605,11 +605,7 @@ static int mxcmci_push(struct mxcmci_host *host, void *_buf, int bytes)
 		mxcmci_writel(host, cpu_to_le32(tmp), MMC_REG_BUFFER_ACCESS);
 	}
 
-	stat = mxcmci_poll_status(host, STATUS_BUF_WRITE_RDY);
-	if (stat)
-		return stat;
-
-	return 0;
+	return mxcmci_poll_status(host, STATUS_BUF_WRITE_RDY);
 }
 
 static int mxcmci_transfer_data(struct mxcmci_host *host)
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index a82411a2c024..d839147e591d 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -549,7 +549,7 @@ static const struct mmc_host_ops mxs_mmc_ops = {
 	.enable_sdio_irq = mxs_mmc_enable_sdio_irq,
 };
 
-static struct platform_device_id mxs_ssp_ids[] = {
+static const struct platform_device_id mxs_ssp_ids[] = {
 	{
 		.name = "imx23-mmc",
 		.driver_data = IMX23_SSP,
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 1d3d6c4bfdc6..93137483ecde 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -1474,7 +1474,7 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id rtsx_pci_sdmmc_ids[] = {
+static const struct platform_device_id rtsx_pci_sdmmc_ids[] = {
 	{
 		.name = DRV_NAME_RTSX_PCI_SDMMC,
 	}, {
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index 88af827e086b..6c71fc9f76c7 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -1439,7 +1439,7 @@ static int rtsx_usb_sdmmc_drv_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id rtsx_usb_sdmmc_ids[] = {
+static const struct platform_device_id rtsx_usb_sdmmc_ids[] = {
 	{
 		.name = "rtsx_usb_sdmmc",
 	}, {
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 94cddf381ba3..6291d5042ef2 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -1856,7 +1856,7 @@ static int s3cmci_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_device_id s3cmci_driver_ids[] = {
+static const struct platform_device_id s3cmci_driver_ids[] = {
 	{
 		.name	= "s3c2410-sdi",
 		.driver_data	= 0,
diff --git a/drivers/mmc/host/sdhci-bcm2835.c b/drivers/mmc/host/sdhci-bcm2835.c
index 0ef0343c603a..1c65d4690e70 100644
--- a/drivers/mmc/host/sdhci-bcm2835.c
+++ b/drivers/mmc/host/sdhci-bcm2835.c
@@ -172,9 +172,19 @@ static int bcm2835_sdhci_probe(struct platform_device *pdev)
 		ret = PTR_ERR(pltfm_host->clk);
 		goto err;
 	}
+	ret = clk_prepare_enable(pltfm_host->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to enable host clk\n");
+		goto err;
+	}
 
-	return sdhci_add_host(host);
+	ret = sdhci_add_host(host);
+	if (ret)
+		goto err_clk;
 
+	return 0;
+err_clk:
+	clk_disable_unprepare(pltfm_host->clk);
 err:
 	sdhci_pltfm_free(pdev);
 	return ret;
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 82f512d87cb8..faf0cb910c96 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -4,7 +4,7 @@
  * derived from the OF-version.
  *
  * Copyright (c) 2010 Pengutronix e.K.
- *   Author: Wolfram Sang <w.sang@pengutronix.de>
+ *   Author: Wolfram Sang <kernel@pengutronix.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -112,6 +112,14 @@
 #define ESDHC_FLAG_STD_TUNING		BIT(5)
 /* The IP has SDHCI_CAPABILITIES_1 register */
 #define ESDHC_FLAG_HAVE_CAP1		BIT(6)
+/*
+ * The IP has errata ERR004536
+ * uSDHC: ADMA Length Mismatch Error occurs if the AHB read access is slow,
+ * when reading data from the card
+ */
+#define ESDHC_FLAG_ERR004536		BIT(7)
+/* The IP supports HS200 mode */
+#define ESDHC_FLAG_HS200		BIT(8)
 
 struct esdhc_soc_data {
 	u32 flags;
@@ -139,7 +147,13 @@ static struct esdhc_soc_data usdhc_imx6q_data = {
 
 static struct esdhc_soc_data usdhc_imx6sl_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
-			| ESDHC_FLAG_HAVE_CAP1,
+			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_ERR004536
+			| ESDHC_FLAG_HS200,
+};
+
+static struct esdhc_soc_data usdhc_imx6sx_data = {
+	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
+			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200,
 };
 
 struct pltfm_imx_data {
@@ -161,7 +175,7 @@ struct pltfm_imx_data {
 	u32 is_ddr;
 };
 
-static struct platform_device_id imx_esdhc_devtype[] = {
+static const struct platform_device_id imx_esdhc_devtype[] = {
 	{
 		.name = "sdhci-esdhc-imx25",
 		.driver_data = (kernel_ulong_t) &esdhc_imx25_data,
@@ -182,6 +196,7 @@ static const struct of_device_id imx_esdhc_dt_ids[] = {
 	{ .compatible = "fsl,imx35-esdhc", .data = &esdhc_imx35_data, },
 	{ .compatible = "fsl,imx51-esdhc", .data = &esdhc_imx51_data, },
 	{ .compatible = "fsl,imx53-esdhc", .data = &esdhc_imx53_data, },
+	{ .compatible = "fsl,imx6sx-usdhc", .data = &usdhc_imx6sx_data, },
 	{ .compatible = "fsl,imx6sl-usdhc", .data = &usdhc_imx6sl_data, },
 	{ .compatible = "fsl,imx6q-usdhc", .data = &usdhc_imx6q_data, },
 	{ /* sentinel */ }
@@ -298,7 +313,7 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 	u32 data;
 
 	if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
-		if (val & SDHCI_INT_CARD_INT) {
+		if ((val & SDHCI_INT_CARD_INT) && !esdhc_is_usdhc(imx_data)) {
 			/*
 			 * Clear and then set D3CD bit to avoid missing the
 			 * card interrupt.  This is a eSDHC controller problem
@@ -313,6 +328,11 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 			data |= ESDHC_CTRL_D3CD;
 			writel(data, host->ioaddr + SDHCI_HOST_CONTROL);
 		}
+
+		if (val & SDHCI_INT_ADMA_ERROR) {
+			val &= ~SDHCI_INT_ADMA_ERROR;
+			val |= ESDHC_INT_VENDOR_SPEC_DMA_ERR;
+		}
 	}
 
 	if (unlikely((imx_data->socdata->flags & ESDHC_FLAG_MULTIBLK_NO_INT)
@@ -333,13 +353,6 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg)
 			}
 	}
 
-	if (unlikely(reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE)) {
-		if (val & SDHCI_INT_ADMA_ERROR) {
-			val &= ~SDHCI_INT_ADMA_ERROR;
-			val |= ESDHC_INT_VENDOR_SPEC_DMA_ERR;
-		}
-	}
-
 	writel(val, host->ioaddr + reg);
 }
 
@@ -903,7 +916,8 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 
 	mmc_of_parse_voltage(np, &host->ocr_mask);
 
-	return 0;
+	/* call to generic mmc_of_parse to support additional capabilities */
+	return mmc_of_parse(host->mmc);
 }
 #else
 static inline int
@@ -924,6 +938,7 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 	struct esdhc_platform_data *boarddata;
 	int err;
 	struct pltfm_imx_data *imx_data;
+	bool dt = true;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_esdhc_imx_pdata, 0);
 	if (IS_ERR(host))
@@ -991,6 +1006,16 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		writel(0x08100810, host->ioaddr + ESDHC_WTMK_LVL);
 		host->quirks2 |= SDHCI_QUIRK2_PRESET_VALUE_BROKEN;
 		host->mmc->caps |= MMC_CAP_1_8V_DDR;
+
+		if (!(imx_data->socdata->flags & ESDHC_FLAG_HS200))
+			host->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
+
+		/*
+		* errata ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL
+		* TO1.1, it's harmless for MX6SL
+		*/
+		writel(readl(host->ioaddr + 0x6c) | BIT(7),
+			host->ioaddr + 0x6c);
 	}
 
 	if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING)
@@ -1002,6 +1027,9 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 			ESDHC_STD_TUNING_EN | ESDHC_TUNING_START_TAP,
 			host->ioaddr + ESDHC_TUNING_CTRL);
 
+	if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
+		host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
+
 	boarddata = &imx_data->boarddata;
 	if (sdhci_esdhc_imx_probe_dt(pdev, host, boarddata) < 0) {
 		if (!host->mmc->parent->platform_data) {
@@ -1011,11 +1039,44 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		}
 		imx_data->boarddata = *((struct esdhc_platform_data *)
 					host->mmc->parent->platform_data);
+		dt = false;
+	}
+	/* write_protect */
+	if (boarddata->wp_type == ESDHC_WP_GPIO && !dt) {
+		err = mmc_gpio_request_ro(host->mmc, boarddata->wp_gpio);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request write-protect gpio!\n");
+			goto disable_clk;
+		}
+		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
 	}
 
 	/* card_detect */
-	if (boarddata->cd_type == ESDHC_CD_CONTROLLER)
+	switch (boarddata->cd_type) {
+	case ESDHC_CD_GPIO:
+		if (dt)
+			break;
+		err = mmc_gpio_request_cd(host->mmc, boarddata->cd_gpio, 0);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request card-detect gpio!\n");
+			goto disable_clk;
+		}
+		/* fall through */
+
+	case ESDHC_CD_CONTROLLER:
+		/* we have a working card_detect back */
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+		break;
+
+	case ESDHC_CD_PERMANENT:
+		host->mmc->caps |= MMC_CAP_NONREMOVABLE;
+		break;
+
+	case ESDHC_CD_NONE:
+		break;
+	}
 
 	switch (boarddata->max_bus_width) {
 	case 8:
@@ -1048,11 +1109,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 	}
 
-	/* call to generic mmc_of_parse to support additional capabilities */
-	err = mmc_of_parse(host->mmc);
-	if (err)
-		goto disable_clk;
-
 	err = sdhci_add_host(host);
 	if (err)
 		goto disable_clk;
@@ -1151,5 +1207,5 @@ static struct platform_driver sdhci_esdhc_imx_driver = {
 module_platform_driver(sdhci_esdhc_imx_driver);
 
 MODULE_DESCRIPTION("SDHCI driver for Freescale i.MX eSDHC");
-MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>");
+MODULE_AUTHOR("Wolfram Sang <kernel@pengutronix.de>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 6287d426c96b..21c0c08dfe54 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include "sdhci-pltfm.h"
 
 #define SDHCI_ARASAN_CLK_CTRL_OFFSET	0x2c
@@ -168,6 +169,11 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 		goto clk_disable_all;
 	}
 
+	if (of_device_is_compatible(pdev->dev.of_node, "arasan,sdhci-4.9a")) {
+		host->quirks |= SDHCI_QUIRK_NO_HISPD_BIT;
+		host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23;
+	}
+
 	sdhci_get_of_property(pdev);
 	pltfm_host = sdhci_priv(host);
 	pltfm_host->priv = sdhci_arasan;
@@ -208,6 +214,7 @@ static int sdhci_arasan_remove(struct platform_device *pdev)
 
 static const struct of_device_id sdhci_arasan_of_match[] = {
 	{ .compatible = "arasan,sdhci-8.9a" },
+	{ .compatible = "arasan,sdhci-4.9a" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sdhci_arasan_of_match);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 22e9111b11ff..797be7549a15 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -199,7 +199,7 @@ static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 
 static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 {
-	int pre_div = 2;
+	int pre_div = 1;
 	int div = 1;
 	u32 temp;
 
@@ -229,7 +229,7 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	dev_dbg(mmc_dev(host->mmc), "desired SD clock: %d, actual: %d\n",
 		clock, host->max_clk / pre_div / div);
-
+	host->mmc->actual_clock = host->max_clk / pre_div / div;
 	pre_div >>= 1;
 	div--;
 
@@ -361,6 +361,13 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
 	sdhci_get_of_property(pdev);
 
 	np = pdev->dev.of_node;
+	if (of_device_is_compatible(np, "fsl,p5040-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p5020-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p4080-esdhc") ||
+	    of_device_is_compatible(np, "fsl,p1020-esdhc") ||
+	    of_device_is_compatible(np, "fsl,t1040-esdhc"))
+		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+
 	if (of_device_is_compatible(np, "fsl,p2020-esdhc")) {
 		/*
 		 * Freescale messed up with P2020 as it has a non-standard
diff --git a/drivers/mmc/host/sdhci-pci-data.c b/drivers/mmc/host/sdhci-pci-data.c
index a611217769f5..56fddc622a54 100644
--- a/drivers/mmc/host/sdhci-pci-data.c
+++ b/drivers/mmc/host/sdhci-pci-data.c
@@ -3,3 +3,6 @@
 
 struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno);
 EXPORT_SYMBOL_GPL(sdhci_pci_get_data);
+
+int sdhci_pci_spt_drive_strength;
+EXPORT_SYMBOL_GPL(sdhci_pci_spt_drive_strength);
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 7a3fc16d0a6c..94f54d2772e8 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
 #include <linux/scatterlist.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
@@ -266,6 +267,69 @@ static void sdhci_pci_int_hw_reset(struct sdhci_host *host)
 	usleep_range(300, 1000);
 }
 
+static int spt_select_drive_strength(struct sdhci_host *host,
+				     struct mmc_card *card,
+				     unsigned int max_dtr,
+				     int host_drv, int card_drv, int *drv_type)
+{
+	int drive_strength;
+
+	if (sdhci_pci_spt_drive_strength > 0)
+		drive_strength = sdhci_pci_spt_drive_strength & 0xf;
+	else
+		drive_strength = 1; /* 33-ohm */
+
+	if ((mmc_driver_type_mask(drive_strength) & card_drv) == 0)
+		drive_strength = 0; /* Default 50-ohm */
+
+	return drive_strength;
+}
+
+/* Try to read the drive strength from the card */
+static void spt_read_drive_strength(struct sdhci_host *host)
+{
+	u32 val, i, t;
+	u16 m;
+
+	if (sdhci_pci_spt_drive_strength)
+		return;
+
+	sdhci_pci_spt_drive_strength = -1;
+
+	m = sdhci_readw(host, SDHCI_HOST_CONTROL2) & 0x7;
+	if (m != 3 && m != 5)
+		return;
+	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	if (val & 0x3)
+		return;
+	sdhci_writel(host, 0x007f0023, SDHCI_INT_ENABLE);
+	sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
+	sdhci_writew(host, 0x10, SDHCI_TRANSFER_MODE);
+	sdhci_writeb(host, 0xe, SDHCI_TIMEOUT_CONTROL);
+	sdhci_writew(host, 512, SDHCI_BLOCK_SIZE);
+	sdhci_writew(host, 1, SDHCI_BLOCK_COUNT);
+	sdhci_writel(host, 0, SDHCI_ARGUMENT);
+	sdhci_writew(host, 0x83b, SDHCI_COMMAND);
+	for (i = 0; i < 1000; i++) {
+		val = sdhci_readl(host, SDHCI_INT_STATUS);
+		if (val & 0xffff8000)
+			return;
+		if (val & 0x20)
+			break;
+		udelay(1);
+	}
+	val = sdhci_readl(host, SDHCI_PRESENT_STATE);
+	if (!(val & 0x800))
+		return;
+	for (i = 0; i < 47; i++)
+		val = sdhci_readl(host, SDHCI_BUFFER);
+	t = val & 0xf00;
+	if (t != 0x200 && t != 0x300)
+		return;
+
+	sdhci_pci_spt_drive_strength = 0x10 | ((val >> 12) & 0xf);
+}
+
 static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE |
@@ -276,6 +340,10 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot)
 	slot->hw_reset = sdhci_pci_int_hw_reset;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BSW_EMMC)
 		slot->host->timeout_clk = 1000; /* 1000 kHz i.e. 1 MHz */
+	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_SPT_EMMC) {
+		spt_read_drive_strength(slot->host);
+		slot->select_drive_strength = spt_select_drive_strength;
+	}
 	return 0;
 }
 
@@ -302,6 +370,7 @@ static const struct sdhci_pci_fixes sdhci_intel_byt_emmc = {
 	.probe_slot	= byt_emmc_probe_slot,
 	.quirks		= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.quirks2	= SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			  SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 |
 			  SDHCI_QUIRK2_STOP_WITH_TC,
 };
 
@@ -655,14 +724,37 @@ static const struct sdhci_pci_fixes sdhci_rtsx = {
 	.probe_slot	= rtsx_probe_slot,
 };
 
+/*AMD chipset generation*/
+enum amd_chipset_gen {
+	AMD_CHIPSET_BEFORE_ML,
+	AMD_CHIPSET_CZ,
+	AMD_CHIPSET_NL,
+	AMD_CHIPSET_UNKNOWN,
+};
+
 static int amd_probe(struct sdhci_pci_chip *chip)
 {
 	struct pci_dev	*smbus_dev;
+	enum amd_chipset_gen gen;
 
 	smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
 			PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, NULL);
+	if (smbus_dev) {
+		gen = AMD_CHIPSET_BEFORE_ML;
+	} else {
+		smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD,
+				PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
+		if (smbus_dev) {
+			if (smbus_dev->revision < 0x51)
+				gen = AMD_CHIPSET_CZ;
+			else
+				gen = AMD_CHIPSET_NL;
+		} else {
+			gen = AMD_CHIPSET_UNKNOWN;
+		}
+	}
 
-	if (smbus_dev && (smbus_dev->revision < 0x51)) {
+	if ((gen == AMD_CHIPSET_BEFORE_ML) || (gen == AMD_CHIPSET_CZ)) {
 		chip->quirks2 |= SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD;
 		chip->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
 	}
@@ -1203,6 +1295,20 @@ static void sdhci_pci_hw_reset(struct sdhci_host *host)
 		slot->hw_reset(host);
 }
 
+static int sdhci_pci_select_drive_strength(struct sdhci_host *host,
+					   struct mmc_card *card,
+					   unsigned int max_dtr, int host_drv,
+					   int card_drv, int *drv_type)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+
+	if (!slot->select_drive_strength)
+		return 0;
+
+	return slot->select_drive_strength(host, card, max_dtr, host_drv,
+					   card_drv, drv_type);
+}
+
 static const struct sdhci_ops sdhci_pci_ops = {
 	.set_clock	= sdhci_set_clock,
 	.enable_dma	= sdhci_pci_enable_dma,
@@ -1210,6 +1316,7 @@ static const struct sdhci_ops sdhci_pci_ops = {
 	.reset		= sdhci_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
+	.select_drive_strength	= sdhci_pci_select_drive_strength,
 };
 
 /*****************************************************************************\
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 1ec684d06d54..541f1cad5247 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -72,6 +72,10 @@ struct sdhci_pci_slot {
 	bool			cd_override_level;
 
 	void (*hw_reset)(struct sdhci_host *host);
+	int (*select_drive_strength)(struct sdhci_host *host,
+				     struct mmc_card *card,
+				     unsigned int max_dtr, int host_drv,
+				     int card_drv, int *drv_type);
 };
 
 struct sdhci_pci_chip {
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index f98008b5ea77..beffd8615489 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -252,9 +252,7 @@ static int sdhci_pxav2_remove(struct platform_device *pdev)
 static struct platform_driver sdhci_pxav2_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav2",
-#ifdef CONFIG_OF
-		.of_match_table = sdhci_pxav2_of_match,
-#endif
+		.of_match_table = of_match_ptr(sdhci_pxav2_of_match),
 		.pm	= SDHCI_PLTFM_PMOPS,
 	},
 	.probe		= sdhci_pxav2_probe,
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index b5103a247bc1..9cd5fc62f130 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -457,12 +457,8 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, host);
 
-	if (host->mmc->pm_caps & MMC_PM_KEEP_POWER) {
+	if (host->mmc->pm_caps & MMC_PM_WAKE_SDIO_IRQ)
 		device_init_wakeup(&pdev->dev, 1);
-		host->mmc->pm_flags |= MMC_PM_WAKE_SDIO_IRQ;
-	} else {
-		device_init_wakeup(&pdev->dev, 0);
-	}
 
 	pm_runtime_put_autosuspend(&pdev->dev);
 
@@ -578,9 +574,7 @@ static const struct dev_pm_ops sdhci_pxav3_pmops = {
 static struct platform_driver sdhci_pxav3_driver = {
 	.driver		= {
 		.name	= "sdhci-pxav3",
-#ifdef CONFIG_OF
-		.of_match_table = sdhci_pxav3_of_match,
-#endif
+		.of_match_table = of_match_ptr(sdhci_pxav3_of_match),
 		.pm	= SDHCI_PXAV3_PMOPS,
 	},
 	.probe		= sdhci_pxav3_probe,
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index c6d2dd7317c1..70c724bc6fc7 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -736,7 +736,7 @@ static struct sdhci_s3c_drv_data exynos4_sdhci_drv_data = {
 #define EXYNOS4_SDHCI_DRV_DATA ((kernel_ulong_t)NULL)
 #endif
 
-static struct platform_device_id sdhci_s3c_driver_ids[] = {
+static const struct platform_device_id sdhci_s3c_driver_ids[] = {
 	{
 		.name		= "s3c-sdhci",
 		.driver_data	= (kernel_ulong_t)NULL,
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 32848eb7ad80..0110bae25b7e 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -17,7 +17,7 @@
 
 #define SDHCI_CLK_DELAY_SETTING 0x4C
 #define SDHCI_SIRF_8BITBUS BIT(3)
-#define SIRF_TUNING_COUNT 128
+#define SIRF_TUNING_COUNT 16384
 
 struct sdhci_sirf_priv {
 	int gpio_cd;
@@ -43,10 +43,43 @@ static void sdhci_sirf_set_bus_width(struct sdhci_host *host, int width)
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 }
 
+static u32 sdhci_sirf_readl_le(struct sdhci_host *host, int reg)
+{
+	u32 val = readl(host->ioaddr + reg);
+
+	if (unlikely((reg == SDHCI_CAPABILITIES_1) &&
+			(host->mmc->caps & MMC_CAP_UHS_SDR50))) {
+		/* fake CAP_1 register */
+		val = SDHCI_SUPPORT_SDR50 | SDHCI_USE_SDR50_TUNING;
+	}
+
+	if (unlikely(reg == SDHCI_SLOT_INT_STATUS)) {
+		u32 prss = val;
+		/* fake chips as V3.0 host conreoller */
+		prss &= ~(0xFF << 16);
+		val = prss | (SDHCI_SPEC_300 << 16);
+	}
+	return val;
+}
+
+static u16 sdhci_sirf_readw_le(struct sdhci_host *host, int reg)
+{
+	u16 ret = 0;
+
+	ret = readw(host->ioaddr + reg);
+
+	if (unlikely(reg == SDHCI_HOST_VERSION)) {
+		ret = readw(host->ioaddr + SDHCI_HOST_VERSION);
+		ret |= SDHCI_SPEC_300;
+	}
+
+	return ret;
+}
+
 static int sdhci_sirf_execute_tuning(struct sdhci_host *host, u32 opcode)
 {
 	int tuning_seq_cnt = 3;
-	u8 phase, tuned_phases[SIRF_TUNING_COUNT];
+	int phase;
 	u8 tuned_phase_cnt = 0;
 	int rc = 0, longest_range = 0;
 	int start = -1, end = 0, tuning_value = -1, range = 0;
@@ -58,6 +91,7 @@ static int sdhci_sirf_execute_tuning(struct sdhci_host *host, u32 opcode)
 
 retry:
 	phase = 0;
+	tuned_phase_cnt = 0;
 	do {
 		sdhci_writel(host,
 			clock_setting | phase,
@@ -65,7 +99,7 @@ retry:
 
 		if (!mmc_send_tuning(mmc)) {
 			/* Tuning is successful at this tuning point */
-			tuned_phases[tuned_phase_cnt++] = phase;
+			tuned_phase_cnt++;
 			dev_dbg(mmc_dev(mmc), "%s: Found good phase = %d\n",
 				 mmc_hostname(mmc), phase);
 			if (start == -1)
@@ -85,7 +119,7 @@ retry:
 			start = -1;
 			end = range = 0;
 		}
-	} while (++phase < ARRAY_SIZE(tuned_phases));
+	} while (++phase < SIRF_TUNING_COUNT);
 
 	if (tuned_phase_cnt && tuning_value > 0) {
 		/*
@@ -112,6 +146,8 @@ retry:
 }
 
 static struct sdhci_ops sdhci_sirf_ops = {
+	.read_l = sdhci_sirf_readl_le,
+	.read_w = sdhci_sirf_readw_le,
 	.platform_execute_tuning = sdhci_sirf_execute_tuning,
 	.set_clock = sdhci_set_clock,
 	.get_max_clock	= sdhci_pltfm_clk_get_max_clock,
diff --git a/drivers/mmc/host/sdhci-st.c b/drivers/mmc/host/sdhci-st.c
index 682f2bb0f4bf..969c2b0d57fd 100644
--- a/drivers/mmc/host/sdhci-st.c
+++ b/drivers/mmc/host/sdhci-st.c
@@ -509,4 +509,4 @@ module_platform_driver(sdhci_st_driver);
 MODULE_DESCRIPTION("SDHCI driver for STMicroelectronics SoCs");
 MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:st-sdhci");
+MODULE_ALIAS("platform:sdhci-st");
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index c80287a02735..bc1445238fb3 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -52,7 +52,6 @@ static void sdhci_finish_data(struct sdhci_host *);
 
 static void sdhci_finish_command(struct sdhci_host *);
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
-static void sdhci_tuning_timer(unsigned long data);
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
 static int sdhci_pre_dma_transfer(struct sdhci_host *host,
 					struct mmc_data *data,
@@ -254,17 +253,6 @@ static void sdhci_init(struct sdhci_host *host, int soft)
 static void sdhci_reinit(struct sdhci_host *host)
 {
 	sdhci_init(host, 0);
-	/*
-	 * Retuning stuffs are affected by different cards inserted and only
-	 * applicable to UHS-I cards. So reset these fields to their initial
-	 * value when card is removed.
-	 */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		host->flags &= ~SDHCI_USING_RETUNING_TIMER;
-
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
 	sdhci_enable_card_detection(host);
 }
 
@@ -328,8 +316,7 @@ static void sdhci_read_block_pio(struct sdhci_host *host)
 	local_irq_save(flags);
 
 	while (blksize) {
-		if (!sg_miter_next(&host->sg_miter))
-			BUG();
+		BUG_ON(!sg_miter_next(&host->sg_miter));
 
 		len = min(host->sg_miter.length, blksize);
 
@@ -374,8 +361,7 @@ static void sdhci_write_block_pio(struct sdhci_host *host)
 	local_irq_save(flags);
 
 	while (blksize) {
-		if (!sg_miter_next(&host->sg_miter))
-			BUG();
+		BUG_ON(!sg_miter_next(&host->sg_miter));
 
 		len = min(host->sg_miter.length, blksize);
 
@@ -848,7 +834,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 			int sg_cnt;
 
 			sg_cnt = sdhci_pre_dma_transfer(host, data, NULL);
-			if (sg_cnt == 0) {
+			if (sg_cnt <= 0) {
 				/*
 				 * This only happens when someone fed
 				 * us an invalid request.
@@ -1353,7 +1339,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	struct sdhci_host *host;
 	int present;
 	unsigned long flags;
-	u32 tuning_opcode;
 
 	host = mmc_priv(mmc);
 
@@ -1387,39 +1372,6 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		host->mrq->cmd->error = -ENOMEDIUM;
 		tasklet_schedule(&host->finish_tasklet);
 	} else {
-		u32 present_state;
-
-		present_state = sdhci_readl(host, SDHCI_PRESENT_STATE);
-		/*
-		 * Check if the re-tuning timer has already expired and there
-		 * is no on-going data transfer and DAT0 is not busy. If so,
-		 * we need to execute tuning procedure before sending command.
-		 */
-		if ((host->flags & SDHCI_NEEDS_RETUNING) &&
-		    !(present_state & (SDHCI_DOING_WRITE | SDHCI_DOING_READ)) &&
-		    (present_state & SDHCI_DATA_0_LVL_MASK)) {
-			if (mmc->card) {
-				/* eMMC uses cmd21 but sd and sdio use cmd19 */
-				tuning_opcode =
-					mmc->card->type == MMC_TYPE_MMC ?
-					MMC_SEND_TUNING_BLOCK_HS200 :
-					MMC_SEND_TUNING_BLOCK;
-
-				/* Here we need to set the host->mrq to NULL,
-				 * in case the pending finish_tasklet
-				 * finishes it incorrectly.
-				 */
-				host->mrq = NULL;
-
-				spin_unlock_irqrestore(&host->lock, flags);
-				sdhci_execute_tuning(mmc, tuning_opcode);
-				spin_lock_irqsave(&host->lock, flags);
-
-				/* Restore original mmc_request structure */
-				host->mrq = mrq;
-			}
-		}
-
 		if (mrq->sbc && !(host->flags & SDHCI_AUTO_CMD23))
 			sdhci_send_command(host, mrq->sbc);
 		else
@@ -1562,8 +1514,17 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 			ctrl_2 &= ~SDHCI_CTRL_DRV_TYPE_MASK;
 			if (ios->drv_type == MMC_SET_DRIVER_TYPE_A)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_A;
+			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_B)
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_B;
 			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_C)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_C;
+			else if (ios->drv_type == MMC_SET_DRIVER_TYPE_D)
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_D;
+			else {
+				pr_warn("%s: invalid driver type, default to "
+					"driver type B\n", mmc_hostname(mmc));
+				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_B;
+			}
 
 			sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 		} else {
@@ -2065,23 +2026,18 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	}
 
 out:
-	host->flags &= ~SDHCI_NEEDS_RETUNING;
-
 	if (tuning_count) {
-		host->flags |= SDHCI_USING_RETUNING_TIMER;
-		mod_timer(&host->tuning_timer, jiffies + tuning_count * HZ);
+		/*
+		 * In case tuning fails, host controllers which support
+		 * re-tuning can try tuning again at a later time, when the
+		 * re-tuning timer expires.  So for these controllers, we
+		 * return 0. Since there might be other controllers who do not
+		 * have this capability, we return error for them.
+		 */
+		err = 0;
 	}
 
-	/*
-	 * In case tuning fails, host controllers which support re-tuning can
-	 * try tuning again at a later time, when the re-tuning timer expires.
-	 * So for these controllers, we return 0. Since there might be other
-	 * controllers who do not have this capability, we return error for
-	 * them. SDHCI_USING_RETUNING_TIMER means the host is currently using
-	 * a retuning timer to do the retuning for the card.
-	 */
-	if (err && (host->flags & SDHCI_USING_RETUNING_TIMER))
-		err = 0;
+	host->mmc->retune_period = err ? 0 : tuning_count;
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
@@ -2092,6 +2048,18 @@ out_unlock:
 	return err;
 }
 
+static int sdhci_select_drive_strength(struct mmc_card *card,
+				       unsigned int max_dtr, int host_drv,
+				       int card_drv, int *drv_type)
+{
+	struct sdhci_host *host = mmc_priv(card->host);
+
+	if (!host->ops->select_drive_strength)
+		return 0;
+
+	return host->ops->select_drive_strength(host, card, max_dtr, host_drv,
+						card_drv, drv_type);
+}
 
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 {
@@ -2236,6 +2204,7 @@ static const struct mmc_host_ops sdhci_ops = {
 	.start_signal_voltage_switch	= sdhci_start_signal_voltage_switch,
 	.prepare_hs400_tuning		= sdhci_prepare_hs400_tuning,
 	.execute_tuning			= sdhci_execute_tuning,
+	.select_drive_strength		= sdhci_select_drive_strength,
 	.card_event			= sdhci_card_event,
 	.card_busy	= sdhci_card_busy,
 };
@@ -2337,20 +2306,6 @@ static void sdhci_timeout_timer(unsigned long data)
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
-static void sdhci_tuning_timer(unsigned long data)
-{
-	struct sdhci_host *host;
-	unsigned long flags;
-
-	host = (struct sdhci_host *)data;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	host->flags |= SDHCI_NEEDS_RETUNING;
-
-	spin_unlock_irqrestore(&host->lock, flags);
-}
-
 /*****************************************************************************\
  *                                                                           *
  * Interrupt handling                                                        *
@@ -2728,11 +2683,8 @@ int sdhci_suspend_host(struct sdhci_host *host)
 {
 	sdhci_disable_card_detection(host);
 
-	/* Disable tuning since we are suspending */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
+	mmc_retune_timer_stop(host->mmc);
+	mmc_retune_needed(host->mmc);
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
 		host->ier = 0;
@@ -2782,10 +2734,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 
 	sdhci_enable_card_detection(host);
 
-	/* Set the re-tuning expiration flag */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER)
-		host->flags |= SDHCI_NEEDS_RETUNING;
-
 	return ret;
 }
 
@@ -2822,11 +2770,8 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host)
 {
 	unsigned long flags;
 
-	/* Disable tuning since we are suspending */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER) {
-		del_timer_sync(&host->tuning_timer);
-		host->flags &= ~SDHCI_NEEDS_RETUNING;
-	}
+	mmc_retune_timer_stop(host->mmc);
+	mmc_retune_needed(host->mmc);
 
 	spin_lock_irqsave(&host->lock, flags);
 	host->ier &= SDHCI_INT_CARD_INT;
@@ -2869,10 +2814,6 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
 		spin_unlock_irqrestore(&host->lock, flags);
 	}
 
-	/* Set the re-tuning expiration flag */
-	if (host->flags & SDHCI_USING_RETUNING_TIMER)
-		host->flags |= SDHCI_NEEDS_RETUNING;
-
 	spin_lock_irqsave(&host->lock, flags);
 
 	host->runtime_suspended = false;
@@ -3315,13 +3256,14 @@ int sdhci_add_host(struct sdhci_host *host)
 				   SDHCI_MAX_CURRENT_MULTIPLIER;
 	}
 
-	/* If OCR set by external regulators, use it instead */
+	/* If OCR set by host, use it instead. */
+	if (host->ocr_mask)
+		ocr_avail = host->ocr_mask;
+
+	/* If OCR set by external regulators, give it highest prio. */
 	if (mmc->ocr_avail)
 		ocr_avail = mmc->ocr_avail;
 
-	if (host->ocr_mask)
-		ocr_avail &= host->ocr_mask;
-
 	mmc->ocr_avail = ocr_avail;
 	mmc->ocr_avail_sdio = ocr_avail;
 	if (host->ocr_avail_sdio)
@@ -3408,13 +3350,6 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	init_waitqueue_head(&host->buf_ready_int);
 
-	if (host->version >= SDHCI_SPEC_300) {
-		/* Initialize re-tuning timer */
-		init_timer(&host->tuning_timer);
-		host->tuning_timer.data = (unsigned long)host;
-		host->tuning_timer.function = sdhci_tuning_timer;
-	}
-
 	sdhci_init(host, 0);
 
 	ret = request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq,
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index e639b7f435e5..5521d29368e4 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -432,13 +432,11 @@ struct sdhci_host {
 #define SDHCI_REQ_USE_DMA	(1<<2)	/* Use DMA for this req. */
 #define SDHCI_DEVICE_DEAD	(1<<3)	/* Device unresponsive */
 #define SDHCI_SDR50_NEEDS_TUNING (1<<4)	/* SDR50 needs tuning */
-#define SDHCI_NEEDS_RETUNING	(1<<5)	/* Host needs retuning */
 #define SDHCI_AUTO_CMD12	(1<<6)	/* Auto CMD12 support */
 #define SDHCI_AUTO_CMD23	(1<<7)	/* Auto CMD23 support */
 #define SDHCI_PV_ENABLED	(1<<8)	/* Preset value enabled */
 #define SDHCI_SDIO_IRQ_ENABLED	(1<<9)	/* SDIO irq enabled */
 #define SDHCI_SDR104_NEEDS_TUNING (1<<10)	/* SDR104/HS200 needs tuning */
-#define SDHCI_USING_RETUNING_TIMER (1<<11)	/* Host is using a retuning timer for the card */
 #define SDHCI_USE_64_BIT_DMA	(1<<12)	/* Use 64-bit DMA */
 #define SDHCI_HS400_TUNING	(1<<13)	/* Tuning for HS400 */
 
@@ -504,7 +502,6 @@ struct sdhci_host {
 	unsigned int		tuning_count;	/* Timer count for re-tuning */
 	unsigned int		tuning_mode;	/* Re-tuning mode supported by host */
 #define SDHCI_TUNING_MODE_1	0
-	struct timer_list	tuning_timer;	/* Timer for tuning */
 
 	struct sdhci_host_next	next_data;
 	unsigned long private[0] ____cacheline_aligned;
@@ -541,6 +538,10 @@ struct sdhci_ops {
 	void	(*platform_init)(struct sdhci_host *host);
 	void    (*card_event)(struct sdhci_host *host);
 	void	(*voltage_switch)(struct sdhci_host *host);
+	int	(*select_drive_strength)(struct sdhci_host *host,
+					 struct mmc_card *card,
+					 unsigned int max_dtr, int host_drv,
+					 int card_drv, int *drv_type);
 };
 
 #ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
diff --git a/drivers/mmc/host/sdhci_f_sdh30.c b/drivers/mmc/host/sdhci_f_sdh30.c
index 2fe8b91481b3..983b8b32ef96 100644
--- a/drivers/mmc/host/sdhci_f_sdh30.c
+++ b/drivers/mmc/host/sdhci_f_sdh30.c
@@ -49,7 +49,7 @@ struct f_sdhost_priv {
 	struct device *dev;
 };
 
-void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
+static void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
 {
 	struct f_sdhost_priv *priv = sdhci_priv(host);
 	u32 ctrl = 0;
@@ -77,12 +77,12 @@ void sdhci_f_sdh30_soft_voltage_switch(struct sdhci_host *host)
 	sdhci_writel(host, ctrl, F_SDH30_TUNING_SETTING);
 }
 
-unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host)
+static unsigned int sdhci_f_sdh30_get_min_clock(struct sdhci_host *host)
 {
 	return F_SDH30_MIN_CLOCK;
 }
 
-void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask)
+static void sdhci_f_sdh30_reset(struct sdhci_host *host, u8 mask)
 {
 	if (sdhci_readw(host, SDHCI_CLOCK_CONTROL) == 0)
 		sdhci_writew(host, 0xBC01, SDHCI_CLOCK_CONTROL);
@@ -114,8 +114,7 @@ static int sdhci_f_sdh30_probe(struct platform_device *pdev)
 		return irq;
 	}
 
-	host = sdhci_alloc_host(dev, sizeof(struct sdhci_host) +
-						sizeof(struct f_sdhost_priv));
+	host = sdhci_alloc_host(dev, sizeof(struct f_sdhost_priv));
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 2b6ef6bd5d5f..5a1fdd405b1a 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -57,6 +57,7 @@
 #include <linux/mmc/slot-gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/mutex.h>
+#include <linux/of_device.h>
 #include <linux/pagemap.h>
 #include <linux/platform_device.h>
 #include <linux/pm_qos.h>
@@ -205,14 +206,14 @@
 #define CLKDEV_MMC_DATA		20000000 /* 20MHz */
 #define CLKDEV_INIT		400000   /* 400 KHz */
 
-enum mmcif_state {
+enum sh_mmcif_state {
 	STATE_IDLE,
 	STATE_REQUEST,
 	STATE_IOS,
 	STATE_TIMEOUT,
 };
 
-enum mmcif_wait_for {
+enum sh_mmcif_wait_for {
 	MMCIF_WAIT_FOR_REQUEST,
 	MMCIF_WAIT_FOR_CMD,
 	MMCIF_WAIT_FOR_MREAD,
@@ -224,12 +225,14 @@ enum mmcif_wait_for {
 	MMCIF_WAIT_FOR_STOP,
 };
 
+/*
+ * difference for each SoC
+ */
 struct sh_mmcif_host {
 	struct mmc_host *mmc;
 	struct mmc_request *mrq;
 	struct platform_device *pd;
-	struct clk *hclk;
-	unsigned int clk;
+	struct clk *clk;
 	int bus_width;
 	unsigned char timing;
 	bool sd_error;
@@ -238,8 +241,8 @@ struct sh_mmcif_host {
 	void __iomem *addr;
 	u32 *pio_ptr;
 	spinlock_t lock;		/* protect sh_mmcif_host::state */
-	enum mmcif_state state;
-	enum mmcif_wait_for wait_for;
+	enum sh_mmcif_state state;
+	enum sh_mmcif_wait_for wait_for;
 	struct delayed_work timeout_work;
 	size_t blocksize;
 	int sg_idx;
@@ -249,6 +252,7 @@ struct sh_mmcif_host {
 	bool ccs_enable;		/* Command Completion Signal support */
 	bool clk_ctrl2_enable;
 	struct mutex thread_lock;
+	u32 clkdiv_map;         /* see CE_CLK_CTRL::CLKDIV */
 
 	/* DMA support */
 	struct dma_chan		*chan_rx;
@@ -257,6 +261,14 @@ struct sh_mmcif_host {
 	bool			dma_active;
 };
 
+static const struct of_device_id sh_mmcif_of_match[] = {
+	{ .compatible = "renesas,sh-mmcif" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sh_mmcif_of_match);
+
+#define sh_mmcif_host_to_dev(host) (&host->pd->dev)
+
 static inline void sh_mmcif_bitset(struct sh_mmcif_host *host,
 					unsigned int reg, u32 val)
 {
@@ -269,15 +281,16 @@ static inline void sh_mmcif_bitclr(struct sh_mmcif_host *host,
 	writel(~val & readl(host->addr + reg), host->addr + reg);
 }
 
-static void mmcif_dma_complete(void *arg)
+static void sh_mmcif_dma_complete(void *arg)
 {
 	struct sh_mmcif_host *host = arg;
 	struct mmc_request *mrq = host->mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 
-	dev_dbg(&host->pd->dev, "Command completed\n");
+	dev_dbg(dev, "Command completed\n");
 
 	if (WARN(!mrq || !mrq->data, "%s: NULL data in DMA completion!\n",
-		 dev_name(&host->pd->dev)))
+		 dev_name(dev)))
 		return;
 
 	complete(&host->dma_complete);
@@ -289,6 +302,7 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 	struct scatterlist *sg = data->sg;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_rx;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cookie_t cookie = -EINVAL;
 	int ret;
 
@@ -301,13 +315,13 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 	}
 
 	if (desc) {
-		desc->callback = mmcif_dma_complete;
+		desc->callback = sh_mmcif_dma_complete;
 		desc->callback_param = host;
 		cookie = dmaengine_submit(desc);
 		sh_mmcif_bitset(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN);
 		dma_async_issue_pending(chan);
 	}
-	dev_dbg(&host->pd->dev, "%s(): mapped %d -> %d, cookie %d\n",
+	dev_dbg(dev, "%s(): mapped %d -> %d, cookie %d\n",
 		__func__, data->sg_len, ret, cookie);
 
 	if (!desc) {
@@ -323,12 +337,12 @@ static void sh_mmcif_start_dma_rx(struct sh_mmcif_host *host)
 			host->chan_tx = NULL;
 			dma_release_channel(chan);
 		}
-		dev_warn(&host->pd->dev,
+		dev_warn(dev,
 			 "DMA failed: %d, falling back to PIO\n", ret);
 		sh_mmcif_bitclr(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN | BUF_ACC_DMAWEN);
 	}
 
-	dev_dbg(&host->pd->dev, "%s(): desc %p, cookie %d, sg[%d]\n", __func__,
+	dev_dbg(dev, "%s(): desc %p, cookie %d, sg[%d]\n", __func__,
 		desc, cookie, data->sg_len);
 }
 
@@ -338,6 +352,7 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 	struct scatterlist *sg = data->sg;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_tx;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cookie_t cookie = -EINVAL;
 	int ret;
 
@@ -350,13 +365,13 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 	}
 
 	if (desc) {
-		desc->callback = mmcif_dma_complete;
+		desc->callback = sh_mmcif_dma_complete;
 		desc->callback_param = host;
 		cookie = dmaengine_submit(desc);
 		sh_mmcif_bitset(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAWEN);
 		dma_async_issue_pending(chan);
 	}
-	dev_dbg(&host->pd->dev, "%s(): mapped %d -> %d, cookie %d\n",
+	dev_dbg(dev, "%s(): mapped %d -> %d, cookie %d\n",
 		__func__, data->sg_len, ret, cookie);
 
 	if (!desc) {
@@ -372,12 +387,12 @@ static void sh_mmcif_start_dma_tx(struct sh_mmcif_host *host)
 			host->chan_rx = NULL;
 			dma_release_channel(chan);
 		}
-		dev_warn(&host->pd->dev,
+		dev_warn(dev,
 			 "DMA failed: %d, falling back to PIO\n", ret);
 		sh_mmcif_bitclr(host, MMCIF_CE_BUF_ACC, BUF_ACC_DMAREN | BUF_ACC_DMAWEN);
 	}
 
-	dev_dbg(&host->pd->dev, "%s(): desc %p, cookie %d\n", __func__,
+	dev_dbg(dev, "%s(): desc %p, cookie %d\n", __func__,
 		desc, cookie);
 }
 
@@ -390,6 +405,7 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 	struct dma_chan *chan;
 	void *slave_data = NULL;
 	struct resource *res;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	dma_cap_mask_t mask;
 	int ret;
 
@@ -402,10 +418,10 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 			(void *)pdata->slave_id_rx;
 
 	chan = dma_request_slave_channel_compat(mask, shdma_chan_filter,
-				slave_data, &host->pd->dev,
+				slave_data, dev,
 				direction == DMA_MEM_TO_DEV ? "tx" : "rx");
 
-	dev_dbg(&host->pd->dev, "%s: %s: got channel %p\n", __func__,
+	dev_dbg(dev, "%s: %s: got channel %p\n", __func__,
 		direction == DMA_MEM_TO_DEV ? "TX" : "RX", chan);
 
 	if (!chan)
@@ -435,12 +451,13 @@ sh_mmcif_request_dma_one(struct sh_mmcif_host *host,
 static void sh_mmcif_request_dma(struct sh_mmcif_host *host,
 				 struct sh_mmcif_plat_data *pdata)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	host->dma_active = false;
 
 	if (pdata) {
 		if (pdata->slave_id_tx <= 0 || pdata->slave_id_rx <= 0)
 			return;
-	} else if (!host->pd->dev.of_node) {
+	} else if (!dev->of_node) {
 		return;
 	}
 
@@ -476,21 +493,59 @@ static void sh_mmcif_release_dma(struct sh_mmcif_host *host)
 
 static void sh_mmcif_clock_control(struct sh_mmcif_host *host, unsigned int clk)
 {
-	struct sh_mmcif_plat_data *p = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *p = dev->platform_data;
 	bool sup_pclk = p ? p->sup_pclk : false;
+	unsigned int current_clk = clk_get_rate(host->clk);
+	unsigned int clkdiv;
 
 	sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_ENABLE);
 	sh_mmcif_bitclr(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR);
 
 	if (!clk)
 		return;
-	if (sup_pclk && clk == host->clk)
-		sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_SUP_PCLK);
-	else
-		sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR &
-				((fls(DIV_ROUND_UP(host->clk,
-						   clk) - 1) - 1) << 16));
 
+	if (host->clkdiv_map) {
+		unsigned int freq, best_freq, myclk, div, diff_min, diff;
+		int i;
+
+		clkdiv = 0;
+		diff_min = ~0;
+		best_freq = 0;
+		for (i = 31; i >= 0; i--) {
+			if (!((1 << i) & host->clkdiv_map))
+				continue;
+
+			/*
+			 * clk = parent_freq / div
+			 * -> parent_freq = clk x div
+			 */
+
+			div = 1 << (i + 1);
+			freq = clk_round_rate(host->clk, clk * div);
+			myclk = freq / div;
+			diff = (myclk > clk) ? myclk - clk : clk - myclk;
+
+			if (diff <= diff_min) {
+				best_freq = freq;
+				clkdiv = i;
+				diff_min = diff;
+			}
+		}
+
+		dev_dbg(dev, "clk %u/%u (%u, 0x%x)\n",
+			(best_freq / (1 << (clkdiv + 1))), clk,
+			best_freq, clkdiv);
+
+		clk_set_rate(host->clk, best_freq);
+		clkdiv = clkdiv << 16;
+	} else if (sup_pclk && clk == current_clk) {
+		clkdiv = CLK_SUP_PCLK;
+	} else {
+		clkdiv = (fls(DIV_ROUND_UP(current_clk, clk) - 1) - 1) << 16;
+	}
+
+	sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_CLEAR & clkdiv);
 	sh_mmcif_bitset(host, MMCIF_CE_CLK_CTRL, CLK_ENABLE);
 }
 
@@ -514,6 +569,7 @@ static void sh_mmcif_sync_reset(struct sh_mmcif_host *host)
 
 static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	u32 state1, state2;
 	int ret, timeout;
 
@@ -521,8 +577,8 @@ static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 
 	state1 = sh_mmcif_readl(host->addr, MMCIF_CE_HOST_STS1);
 	state2 = sh_mmcif_readl(host->addr, MMCIF_CE_HOST_STS2);
-	dev_dbg(&host->pd->dev, "ERR HOST_STS1 = %08x\n", state1);
-	dev_dbg(&host->pd->dev, "ERR HOST_STS2 = %08x\n", state2);
+	dev_dbg(dev, "ERR HOST_STS1 = %08x\n", state1);
+	dev_dbg(dev, "ERR HOST_STS2 = %08x\n", state2);
 
 	if (state1 & STS1_CMDSEQ) {
 		sh_mmcif_bitset(host, MMCIF_CE_CMD_CTRL, CMD_CTRL_BREAK);
@@ -534,25 +590,25 @@ static int sh_mmcif_error_manage(struct sh_mmcif_host *host)
 			mdelay(1);
 		}
 		if (!timeout) {
-			dev_err(&host->pd->dev,
+			dev_err(dev,
 				"Forced end of command sequence timeout err\n");
 			return -EIO;
 		}
 		sh_mmcif_sync_reset(host);
-		dev_dbg(&host->pd->dev, "Forced end of command sequence\n");
+		dev_dbg(dev, "Forced end of command sequence\n");
 		return -EIO;
 	}
 
 	if (state2 & STS2_CRC_ERR) {
-		dev_err(&host->pd->dev, " CRC error: state %u, wait %u\n",
+		dev_err(dev, " CRC error: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -EIO;
 	} else if (state2 & STS2_TIMEOUT_ERR) {
-		dev_err(&host->pd->dev, " Timeout: state %u, wait %u\n",
+		dev_err(dev, " Timeout: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -ETIMEDOUT;
 	} else {
-		dev_dbg(&host->pd->dev, " End/Index error: state %u, wait %u\n",
+		dev_dbg(dev, " End/Index error: state %u, wait %u\n",
 			host->state, host->wait_for);
 		ret = -EIO;
 	}
@@ -593,13 +649,14 @@ static void sh_mmcif_single_read(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_read_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = sg_virt(data->sg);
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -634,13 +691,14 @@ static void sh_mmcif_multi_read(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_mread_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = host->pio_ptr;
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -671,13 +729,14 @@ static void sh_mmcif_single_write(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_write_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = sg_virt(data->sg);
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -712,13 +771,14 @@ static void sh_mmcif_multi_write(struct sh_mmcif_host *host,
 
 static bool sh_mmcif_mwrite_block(struct sh_mmcif_host *host)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = host->mrq->data;
 	u32 *p = host->pio_ptr;
 	int i;
 
 	if (host->sd_error) {
 		data->error = sh_mmcif_error_manage(host);
-		dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, data->error);
+		dev_dbg(dev, "%s(): %d\n", __func__, data->error);
 		return false;
 	}
 
@@ -756,6 +816,7 @@ static void sh_mmcif_get_cmd12response(struct sh_mmcif_host *host,
 static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 			    struct mmc_request *mrq)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	struct mmc_data *data = mrq->data;
 	struct mmc_command *cmd = mrq->cmd;
 	u32 opc = cmd->opcode;
@@ -775,7 +836,7 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 		tmp |= CMD_SET_RTYP_17B;
 		break;
 	default:
-		dev_err(&host->pd->dev, "Unsupported response type.\n");
+		dev_err(dev, "Unsupported response type.\n");
 		break;
 	}
 	switch (opc) {
@@ -803,7 +864,7 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 			tmp |= CMD_SET_DATW_8;
 			break;
 		default:
-			dev_err(&host->pd->dev, "Unsupported bus width.\n");
+			dev_err(dev, "Unsupported bus width.\n");
 			break;
 		}
 		switch (host->timing) {
@@ -846,6 +907,8 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 static int sh_mmcif_data_trans(struct sh_mmcif_host *host,
 			       struct mmc_request *mrq, u32 opc)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
 	switch (opc) {
 	case MMC_READ_MULTIPLE_BLOCK:
 		sh_mmcif_multi_read(host, mrq);
@@ -861,7 +924,7 @@ static int sh_mmcif_data_trans(struct sh_mmcif_host *host,
 		sh_mmcif_single_read(host, mrq);
 		return 0;
 	default:
-		dev_err(&host->pd->dev, "Unsupported CMD%d\n", opc);
+		dev_err(dev, "Unsupported CMD%d\n", opc);
 		return -EINVAL;
 	}
 }
@@ -918,6 +981,8 @@ static void sh_mmcif_start_cmd(struct sh_mmcif_host *host,
 static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 			      struct mmc_request *mrq)
 {
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
 	switch (mrq->cmd->opcode) {
 	case MMC_READ_MULTIPLE_BLOCK:
 		sh_mmcif_bitset(host, MMCIF_CE_INT_MASK, MASK_MCMD12DRE);
@@ -926,7 +991,7 @@ static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 		sh_mmcif_bitset(host, MMCIF_CE_INT_MASK, MASK_MCMD12RBE);
 		break;
 	default:
-		dev_err(&host->pd->dev, "unsupported stop cmd\n");
+		dev_err(dev, "unsupported stop cmd\n");
 		mrq->stop->error = sh_mmcif_error_manage(host);
 		return;
 	}
@@ -937,11 +1002,13 @@ static void sh_mmcif_stop_cmd(struct sh_mmcif_host *host,
 static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
 	if (host->state != STATE_IDLE) {
-		dev_dbg(&host->pd->dev, "%s() rejected, state %u\n", __func__, host->state);
+		dev_dbg(dev, "%s() rejected, state %u\n",
+			__func__, host->state);
 		spin_unlock_irqrestore(&host->lock, flags);
 		mrq->cmd->error = -EAGAIN;
 		mmc_request_done(mmc, mrq);
@@ -972,17 +1039,37 @@ static void sh_mmcif_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	sh_mmcif_start_cmd(host, mrq);
 }
 
-static int sh_mmcif_clk_update(struct sh_mmcif_host *host)
+static void sh_mmcif_clk_setup(struct sh_mmcif_host *host)
 {
-	int ret = clk_prepare_enable(host->hclk);
+	struct device *dev = sh_mmcif_host_to_dev(host);
+
+	if (host->mmc->f_max) {
+		unsigned int f_max, f_min = 0, f_min_old;
+
+		f_max = host->mmc->f_max;
+		for (f_min_old = f_max; f_min_old > 2;) {
+			f_min = clk_round_rate(host->clk, f_min_old / 2);
+			if (f_min == f_min_old)
+				break;
+			f_min_old = f_min;
+		}
+
+		/*
+		 * This driver assumes this SoC is R-Car Gen2 or later
+		 */
+		host->clkdiv_map = 0x3ff;
+
+		host->mmc->f_max = f_max / (1 << ffs(host->clkdiv_map));
+		host->mmc->f_min = f_min / (1 << fls(host->clkdiv_map));
+	} else {
+		unsigned int clk = clk_get_rate(host->clk);
 
-	if (!ret) {
-		host->clk = clk_get_rate(host->hclk);
-		host->mmc->f_max = host->clk / 2;
-		host->mmc->f_min = host->clk / 512;
+		host->mmc->f_max = clk / 2;
+		host->mmc->f_min = clk / 512;
 	}
 
-	return ret;
+	dev_dbg(dev, "clk max/min = %d/%d\n",
+		host->mmc->f_max, host->mmc->f_min);
 }
 
 static void sh_mmcif_set_power(struct sh_mmcif_host *host, struct mmc_ios *ios)
@@ -998,11 +1085,13 @@ static void sh_mmcif_set_power(struct sh_mmcif_host *host, struct mmc_ios *ios)
 static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	spin_lock_irqsave(&host->lock, flags);
 	if (host->state != STATE_IDLE) {
-		dev_dbg(&host->pd->dev, "%s() rejected, state %u\n", __func__, host->state);
+		dev_dbg(dev, "%s() rejected, state %u\n",
+			__func__, host->state);
 		spin_unlock_irqrestore(&host->lock, flags);
 		return;
 	}
@@ -1013,7 +1102,7 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (ios->power_mode == MMC_POWER_UP) {
 		if (!host->card_present) {
 			/* See if we also get DMA */
-			sh_mmcif_request_dma(host, host->pd->dev.platform_data);
+			sh_mmcif_request_dma(host, dev->platform_data);
 			host->card_present = true;
 		}
 		sh_mmcif_set_power(host, ios);
@@ -1027,8 +1116,8 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 			}
 		}
 		if (host->power) {
-			pm_runtime_put_sync(&host->pd->dev);
-			clk_disable_unprepare(host->hclk);
+			pm_runtime_put_sync(dev);
+			clk_disable_unprepare(host->clk);
 			host->power = false;
 			if (ios->power_mode == MMC_POWER_OFF)
 				sh_mmcif_set_power(host, ios);
@@ -1039,8 +1128,9 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	if (ios->clock) {
 		if (!host->power) {
-			sh_mmcif_clk_update(host);
-			pm_runtime_get_sync(&host->pd->dev);
+			clk_prepare_enable(host->clk);
+
+			pm_runtime_get_sync(dev);
 			host->power = true;
 			sh_mmcif_sync_reset(host);
 		}
@@ -1055,7 +1145,8 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 static int sh_mmcif_get_cd(struct mmc_host *mmc)
 {
 	struct sh_mmcif_host *host = mmc_priv(mmc);
-	struct sh_mmcif_plat_data *p = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *p = dev->platform_data;
 	int ret = mmc_gpio_get_cd(mmc);
 
 	if (ret >= 0)
@@ -1077,6 +1168,7 @@ static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
 {
 	struct mmc_command *cmd = host->mrq->cmd;
 	struct mmc_data *data = host->mrq->data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	long time;
 
 	if (host->sd_error) {
@@ -1090,7 +1182,7 @@ static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
 			cmd->error = sh_mmcif_error_manage(host);
 			break;
 		}
-		dev_dbg(&host->pd->dev, "CMD%d error %d\n",
+		dev_dbg(dev, "CMD%d error %d\n",
 			cmd->opcode, cmd->error);
 		host->sd_error = false;
 		return false;
@@ -1170,6 +1262,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 {
 	struct sh_mmcif_host *host = dev_id;
 	struct mmc_request *mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	bool wait = false;
 	unsigned long flags;
 	int wait_work;
@@ -1184,7 +1277,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 
 	mrq = host->mrq;
 	if (!mrq) {
-		dev_dbg(&host->pd->dev, "IRQ thread state %u, wait %u: NULL mrq!\n",
+		dev_dbg(dev, "IRQ thread state %u, wait %u: NULL mrq!\n",
 			host->state, host->wait_for);
 		mutex_unlock(&host->thread_lock);
 		return IRQ_HANDLED;
@@ -1222,7 +1315,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 	case MMCIF_WAIT_FOR_STOP:
 		if (host->sd_error) {
 			mrq->stop->error = sh_mmcif_error_manage(host);
-			dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, mrq->stop->error);
+			dev_dbg(dev, "%s(): %d\n", __func__, mrq->stop->error);
 			break;
 		}
 		sh_mmcif_get_cmd12response(host, mrq->stop);
@@ -1232,7 +1325,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 	case MMCIF_WAIT_FOR_WRITE_END:
 		if (host->sd_error) {
 			mrq->data->error = sh_mmcif_error_manage(host);
-			dev_dbg(&host->pd->dev, "%s(): %d\n", __func__, mrq->data->error);
+			dev_dbg(dev, "%s(): %d\n", __func__, mrq->data->error);
 		}
 		break;
 	default:
@@ -1275,6 +1368,7 @@ static irqreturn_t sh_mmcif_irqt(int irq, void *dev_id)
 static irqreturn_t sh_mmcif_intr(int irq, void *dev_id)
 {
 	struct sh_mmcif_host *host = dev_id;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	u32 state, mask;
 
 	state = sh_mmcif_readl(host->addr, MMCIF_CE_INT);
@@ -1286,32 +1380,33 @@ static irqreturn_t sh_mmcif_intr(int irq, void *dev_id)
 	sh_mmcif_bitclr(host, MMCIF_CE_INT_MASK, state & MASK_CLEAN);
 
 	if (state & ~MASK_CLEAN)
-		dev_dbg(&host->pd->dev, "IRQ state = 0x%08x incompletely cleared\n",
+		dev_dbg(dev, "IRQ state = 0x%08x incompletely cleared\n",
 			state);
 
 	if (state & INT_ERR_STS || state & ~INT_ALL) {
 		host->sd_error = true;
-		dev_dbg(&host->pd->dev, "int err state = 0x%08x\n", state);
+		dev_dbg(dev, "int err state = 0x%08x\n", state);
 	}
 	if (state & ~(INT_CMD12RBE | INT_CMD12CRE)) {
 		if (!host->mrq)
-			dev_dbg(&host->pd->dev, "NULL IRQ state = 0x%08x\n", state);
+			dev_dbg(dev, "NULL IRQ state = 0x%08x\n", state);
 		if (!host->dma_active)
 			return IRQ_WAKE_THREAD;
 		else if (host->sd_error)
-			mmcif_dma_complete(host);
+			sh_mmcif_dma_complete(host);
 	} else {
-		dev_dbg(&host->pd->dev, "Unexpected IRQ 0x%x\n", state);
+		dev_dbg(dev, "Unexpected IRQ 0x%x\n", state);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void mmcif_timeout_work(struct work_struct *work)
+static void sh_mmcif_timeout_work(struct work_struct *work)
 {
 	struct delayed_work *d = container_of(work, struct delayed_work, work);
 	struct sh_mmcif_host *host = container_of(d, struct sh_mmcif_host, timeout_work);
 	struct mmc_request *mrq = host->mrq;
+	struct device *dev = sh_mmcif_host_to_dev(host);
 	unsigned long flags;
 
 	if (host->dying)
@@ -1324,7 +1419,7 @@ static void mmcif_timeout_work(struct work_struct *work)
 		return;
 	}
 
-	dev_err(&host->pd->dev, "Timeout waiting for %u on CMD%u\n",
+	dev_err(dev, "Timeout waiting for %u on CMD%u\n",
 		host->wait_for, mrq->cmd->opcode);
 
 	host->state = STATE_TIMEOUT;
@@ -1361,7 +1456,8 @@ static void mmcif_timeout_work(struct work_struct *work)
 
 static void sh_mmcif_init_ocr(struct sh_mmcif_host *host)
 {
-	struct sh_mmcif_plat_data *pd = host->pd->dev.platform_data;
+	struct device *dev = sh_mmcif_host_to_dev(host);
+	struct sh_mmcif_plat_data *pd = dev->platform_data;
 	struct mmc_host *mmc = host->mmc;
 
 	mmc_regulator_get_supply(mmc);
@@ -1380,7 +1476,8 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	int ret = 0, irq[2];
 	struct mmc_host *mmc;
 	struct sh_mmcif_host *host;
-	struct sh_mmcif_plat_data *pd = pdev->dev.platform_data;
+	struct device *dev = &pdev->dev;
+	struct sh_mmcif_plat_data *pd = dev->platform_data;
 	struct resource *res;
 	void __iomem *reg;
 	const char *name;
@@ -1388,16 +1485,16 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	irq[0] = platform_get_irq(pdev, 0);
 	irq[1] = platform_get_irq(pdev, 1);
 	if (irq[0] < 0) {
-		dev_err(&pdev->dev, "Get irq error\n");
+		dev_err(dev, "Get irq error\n");
 		return -ENXIO;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	reg = devm_ioremap_resource(&pdev->dev, res);
+	reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(reg))
 		return PTR_ERR(reg);
 
-	mmc = mmc_alloc_host(sizeof(struct sh_mmcif_host), &pdev->dev);
+	mmc = mmc_alloc_host(sizeof(struct sh_mmcif_host), dev);
 	if (!mmc)
 		return -ENOMEM;
 
@@ -1408,7 +1505,7 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	host		= mmc_priv(mmc);
 	host->mmc	= mmc;
 	host->addr	= reg;
-	host->timeout	= msecs_to_jiffies(1000);
+	host->timeout	= msecs_to_jiffies(10000);
 	host->ccs_enable = !pd || !pd->ccs_unsupported;
 	host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present;
 
@@ -1430,41 +1527,44 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, host);
 
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_enable(dev);
 	host->power = false;
 
-	host->hclk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(host->hclk)) {
-		ret = PTR_ERR(host->hclk);
-		dev_err(&pdev->dev, "cannot get clock: %d\n", ret);
+	host->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(host->clk)) {
+		ret = PTR_ERR(host->clk);
+		dev_err(dev, "cannot get clock: %d\n", ret);
 		goto err_pm;
 	}
-	ret = sh_mmcif_clk_update(host);
+
+	ret = clk_prepare_enable(host->clk);
 	if (ret < 0)
 		goto err_pm;
 
-	ret = pm_runtime_resume(&pdev->dev);
+	sh_mmcif_clk_setup(host);
+
+	ret = pm_runtime_resume(dev);
 	if (ret < 0)
 		goto err_clk;
 
-	INIT_DELAYED_WORK(&host->timeout_work, mmcif_timeout_work);
+	INIT_DELAYED_WORK(&host->timeout_work, sh_mmcif_timeout_work);
 
 	sh_mmcif_sync_reset(host);
 	sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL);
 
-	name = irq[1] < 0 ? dev_name(&pdev->dev) : "sh_mmc:error";
-	ret = devm_request_threaded_irq(&pdev->dev, irq[0], sh_mmcif_intr,
+	name = irq[1] < 0 ? dev_name(dev) : "sh_mmc:error";
+	ret = devm_request_threaded_irq(dev, irq[0], sh_mmcif_intr,
 					sh_mmcif_irqt, 0, name, host);
 	if (ret) {
-		dev_err(&pdev->dev, "request_irq error (%s)\n", name);
+		dev_err(dev, "request_irq error (%s)\n", name);
 		goto err_clk;
 	}
 	if (irq[1] >= 0) {
-		ret = devm_request_threaded_irq(&pdev->dev, irq[1],
+		ret = devm_request_threaded_irq(dev, irq[1],
 						sh_mmcif_intr, sh_mmcif_irqt,
 						0, "sh_mmc:int", host);
 		if (ret) {
-			dev_err(&pdev->dev, "request_irq error (sh_mmc:int)\n");
+			dev_err(dev, "request_irq error (sh_mmc:int)\n");
 			goto err_clk;
 		}
 	}
@@ -1481,19 +1581,19 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_clk;
 
-	dev_pm_qos_expose_latency_limit(&pdev->dev, 100);
+	dev_pm_qos_expose_latency_limit(dev, 100);
 
-	dev_info(&pdev->dev, "Chip version 0x%04x, clock rate %luMHz\n",
+	dev_info(dev, "Chip version 0x%04x, clock rate %luMHz\n",
 		 sh_mmcif_readl(host->addr, MMCIF_CE_VERSION) & 0xffff,
-		 clk_get_rate(host->hclk) / 1000000UL);
+		 clk_get_rate(host->clk) / 1000000UL);
 
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 	return ret;
 
 err_clk:
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 err_pm:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 err_host:
 	mmc_free_host(mmc);
 	return ret;
@@ -1504,7 +1604,7 @@ static int sh_mmcif_remove(struct platform_device *pdev)
 	struct sh_mmcif_host *host = platform_get_drvdata(pdev);
 
 	host->dying = true;
-	clk_prepare_enable(host->hclk);
+	clk_prepare_enable(host->clk);
 	pm_runtime_get_sync(&pdev->dev);
 
 	dev_pm_qos_hide_latency_limit(&pdev->dev);
@@ -1519,7 +1619,7 @@ static int sh_mmcif_remove(struct platform_device *pdev)
 	 */
 	cancel_delayed_work_sync(&host->timeout_work);
 
-	clk_disable_unprepare(host->hclk);
+	clk_disable_unprepare(host->clk);
 	mmc_free_host(host->mmc);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
@@ -1543,12 +1643,6 @@ static int sh_mmcif_resume(struct device *dev)
 }
 #endif
 
-static const struct of_device_id mmcif_of_match[] = {
-	{ .compatible = "renesas,sh-mmcif" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, mmcif_of_match);
-
 static const struct dev_pm_ops sh_mmcif_dev_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(sh_mmcif_suspend, sh_mmcif_resume)
 };
@@ -1559,7 +1653,7 @@ static struct platform_driver sh_mmcif_driver = {
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.pm	= &sh_mmcif_dev_pm_ops,
-		.of_match_table = mmcif_of_match,
+		.of_match_table = sh_mmcif_of_match,
 	},
 };
 
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index f746df493892..e897e7fc3b14 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -85,8 +85,10 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
+	if (!res) {
+		ret = -EINVAL;
+		goto cell_disable;
+	}
 
 	pdata->flags |= TMIO_MMC_HAVE_HIGH_REG;
 
@@ -101,7 +103,8 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	if (ret)
 		goto host_free;
 
-	ret = request_irq(irq, tmio_mmc_irq, IRQF_TRIGGER_FALLING,
+	ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq,
+				IRQF_TRIGGER_FALLING,
 				dev_name(&pdev->dev), host);
 	if (ret)
 		goto host_remove;
@@ -129,7 +132,6 @@ static int tmio_mmc_remove(struct platform_device *pdev)
 
 	if (mmc) {
 		struct tmio_mmc_host *host = mmc_priv(mmc);
-		free_irq(platform_get_irq(pdev, 0), host);
 		tmio_mmc_host_remove(host);
 		if (cell->disable)
 			cell->disable(pdev);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index dba7e1c19dd7..e3dcf31a8bd6 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1108,7 +1108,8 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	if (ret < 0)
 		goto host_free;
 
-	_host->ctl = ioremap(res_ctl->start, resource_size(res_ctl));
+	_host->ctl = devm_ioremap(&pdev->dev,
+				  res_ctl->start, resource_size(res_ctl));
 	if (!_host->ctl) {
 		ret = -ENOMEM;
 		goto host_free;
@@ -1230,8 +1231,6 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	iounmap(host->ctl);
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index 9f02c28c0204..54479c481a7a 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -16,6 +16,7 @@ config MTD_CFI
 config MTD_JEDECPROBE
 	tristate "Detect non-CFI AMD/JEDEC-compatible flash chips"
 	select MTD_GEN_PROBE
+	select MTD_CFI_UTIL
 	help
 	  This option enables JEDEC-style probing of flash chips which are not
 	  compatible with the Common Flash Interface, but will use the common
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index c50d8cf0f60d..c3624eb571d1 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1295,7 +1295,7 @@ static int do_otp_write(struct map_info *map, struct flchip *chip, loff_t adr,
 		unsigned long bus_ofs = adr & ~(map_bankwidth(map)-1);
 		int gap = adr - bus_ofs;
 		int n = min_t(int, len, map_bankwidth(map) - gap);
-		map_word datum;
+		map_word datum = map_word_ff(map);
 
 		if (n != map_bankwidth(map)) {
 			/* partial write of a word, load old contents */
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index 09c79bd0b4f4..6f16552cd59f 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -23,6 +23,194 @@
 #include <linux/mtd/map.h>
 #include <linux/mtd/cfi.h>
 
+void cfi_udelay(int us)
+{
+	if (us >= 1000) {
+		msleep((us+999)/1000);
+	} else {
+		udelay(us);
+		cond_resched();
+	}
+}
+EXPORT_SYMBOL(cfi_udelay);
+
+/*
+ * Returns the command address according to the given geometry.
+ */
+uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs,
+				struct map_info *map, struct cfi_private *cfi)
+{
+	unsigned bankwidth = map_bankwidth(map);
+	unsigned interleave = cfi_interleave(cfi);
+	unsigned type = cfi->device_type;
+	uint32_t addr;
+
+	addr = (cmd_ofs * type) * interleave;
+
+	/* Modify the unlock address if we are in compatibility mode.
+	 * For 16bit devices on 8 bit busses
+	 * and 32bit devices on 16 bit busses
+	 * set the low bit of the alternating bit sequence of the address.
+	 */
+	if (((type * interleave) > bankwidth) && ((cmd_ofs & 0xff) == 0xaa))
+		addr |= (type >> 1)*interleave;
+
+	return  addr;
+}
+EXPORT_SYMBOL(cfi_build_cmd_addr);
+
+/*
+ * Transforms the CFI command for the given geometry (bus width & interleave).
+ * It looks too long to be inline, but in the common case it should almost all
+ * get optimised away.
+ */
+map_word cfi_build_cmd(u_long cmd, struct map_info *map, struct cfi_private *cfi)
+{
+	map_word val = { {0} };
+	int wordwidth, words_per_bus, chip_mode, chips_per_word;
+	unsigned long onecmd;
+	int i;
+
+	/* We do it this way to give the compiler a fighting chance
+	   of optimising away all the crap for 'bankwidth' larger than
+	   an unsigned long, in the common case where that support is
+	   disabled */
+	if (map_bankwidth_is_large(map)) {
+		wordwidth = sizeof(unsigned long);
+		words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1
+	} else {
+		wordwidth = map_bankwidth(map);
+		words_per_bus = 1;
+	}
+
+	chip_mode = map_bankwidth(map) / cfi_interleave(cfi);
+	chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map);
+
+	/* First, determine what the bit-pattern should be for a single
+	   device, according to chip mode and endianness... */
+	switch (chip_mode) {
+	default: BUG();
+	case 1:
+		onecmd = cmd;
+		break;
+	case 2:
+		onecmd = cpu_to_cfi16(map, cmd);
+		break;
+	case 4:
+		onecmd = cpu_to_cfi32(map, cmd);
+		break;
+	}
+
+	/* Now replicate it across the size of an unsigned long, or
+	   just to the bus width as appropriate */
+	switch (chips_per_word) {
+	default: BUG();
+#if BITS_PER_LONG >= 64
+	case 8:
+		onecmd |= (onecmd << (chip_mode * 32));
+#endif
+	case 4:
+		onecmd |= (onecmd << (chip_mode * 16));
+	case 2:
+		onecmd |= (onecmd << (chip_mode * 8));
+	case 1:
+		;
+	}
+
+	/* And finally, for the multi-word case, replicate it
+	   in all words in the structure */
+	for (i=0; i < words_per_bus; i++) {
+		val.x[i] = onecmd;
+	}
+
+	return val;
+}
+EXPORT_SYMBOL(cfi_build_cmd);
+
+unsigned long cfi_merge_status(map_word val, struct map_info *map,
+					   struct cfi_private *cfi)
+{
+	int wordwidth, words_per_bus, chip_mode, chips_per_word;
+	unsigned long onestat, res = 0;
+	int i;
+
+	/* We do it this way to give the compiler a fighting chance
+	   of optimising away all the crap for 'bankwidth' larger than
+	   an unsigned long, in the common case where that support is
+	   disabled */
+	if (map_bankwidth_is_large(map)) {
+		wordwidth = sizeof(unsigned long);
+		words_per_bus = (map_bankwidth(map)) / wordwidth; // i.e. normally 1
+	} else {
+		wordwidth = map_bankwidth(map);
+		words_per_bus = 1;
+	}
+
+	chip_mode = map_bankwidth(map) / cfi_interleave(cfi);
+	chips_per_word = wordwidth * cfi_interleave(cfi) / map_bankwidth(map);
+
+	onestat = val.x[0];
+	/* Or all status words together */
+	for (i=1; i < words_per_bus; i++) {
+		onestat |= val.x[i];
+	}
+
+	res = onestat;
+	switch(chips_per_word) {
+	default: BUG();
+#if BITS_PER_LONG >= 64
+	case 8:
+		res |= (onestat >> (chip_mode * 32));
+#endif
+	case 4:
+		res |= (onestat >> (chip_mode * 16));
+	case 2:
+		res |= (onestat >> (chip_mode * 8));
+	case 1:
+		;
+	}
+
+	/* Last, determine what the bit-pattern should be for a single
+	   device, according to chip mode and endianness... */
+	switch (chip_mode) {
+	case 1:
+		break;
+	case 2:
+		res = cfi16_to_cpu(map, res);
+		break;
+	case 4:
+		res = cfi32_to_cpu(map, res);
+		break;
+	default: BUG();
+	}
+	return res;
+}
+EXPORT_SYMBOL(cfi_merge_status);
+
+/*
+ * Sends a CFI command to a bank of flash for the given geometry.
+ *
+ * Returns the offset in flash where the command was written.
+ * If prev_val is non-null, it will be set to the value at the command address,
+ * before the command was written.
+ */
+uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t base,
+				struct map_info *map, struct cfi_private *cfi,
+				int type, map_word *prev_val)
+{
+	map_word val;
+	uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, map, cfi);
+	val = cfi_build_cmd(cmd, map, cfi);
+
+	if (prev_val)
+		*prev_val = map_read(map, addr);
+
+	map_write(map, val, addr);
+
+	return addr - base;
+}
+EXPORT_SYMBOL(cfi_send_gen_cmd);
+
 int __xipram cfi_qry_present(struct map_info *map, __u32 base,
 			     struct cfi_private *cfi)
 {
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index c49d0b127fef..f73c41697a00 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -195,6 +195,14 @@ config MTD_BLOCK2MTD
 	  Testing MTD users (eg JFFS2) on large media and media that might
 	  be removed during a write (using the floppy drive).
 
+config MTD_POWERNV_FLASH
+	tristate "powernv flash MTD driver"
+	depends on PPC_POWERNV
+	help
+	  This provides an MTD device to access flash on powernv OPAL
+	  platforms from Linux. This device abstracts away the
+	  firmware interface for flash access.
+
 comment "Disk-On-Chip Device Drivers"
 
 config MTD_DOCG3
diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile
index f0b0e611d1d6..7912d3a0ee34 100644
--- a/drivers/mtd/devices/Makefile
+++ b/drivers/mtd/devices/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_MTD_SPEAR_SMI)	+= spear_smi.o
 obj-$(CONFIG_MTD_SST25L)	+= sst25l.o
 obj-$(CONFIG_MTD_BCM47XXSFLASH)	+= bcm47xxsflash.o
 obj-$(CONFIG_MTD_ST_SPI_FSM)    += st_spi_fsm.o
+obj-$(CONFIG_MTD_POWERNV_FLASH)	+= powernv_flash.o
 
 
 CFLAGS_docg3.o			+= -I$(src)
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index 866d31904475..5e67b4acde78 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -1815,7 +1815,7 @@ static void doc_dbg_unregister(struct docg3 *docg3)
  * @chip_id: The chip ID of the supported chip
  * @mtd: The structure to fill
  */
-static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
+static int __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
 {
 	struct docg3 *docg3 = mtd->priv;
 	int cfg;
@@ -1828,6 +1828,8 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
 	case DOC_CHIPID_G3:
 		mtd->name = kasprintf(GFP_KERNEL, "docg3.%d",
 				      docg3->device_id);
+		if (!mtd->name)
+			return -ENOMEM;
 		docg3->max_block = 2047;
 		break;
 	}
@@ -1850,6 +1852,8 @@ static void __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
 	mtd->_block_isbad = doc_block_isbad;
 	mtd->ecclayout = &docg3_oobinfo;
 	mtd->ecc_strength = DOC_ECC_BCH_T;
+
+	return 0;
 }
 
 /**
@@ -1900,7 +1904,7 @@ doc_probe_device(struct docg3_cascade *cascade, int floor, struct device *dev)
 
 	ret = 0;
 	if (chip_id != (u16)(~chip_id_inv)) {
-		goto nomem3;
+		goto nomem4;
 	}
 
 	switch (chip_id) {
@@ -1910,15 +1914,19 @@ doc_probe_device(struct docg3_cascade *cascade, int floor, struct device *dev)
 		break;
 	default:
 		doc_err("Chip id %04x is not a DiskOnChip G3 chip\n", chip_id);
-		goto nomem3;
+		goto nomem4;
 	}
 
-	doc_set_driver_info(chip_id, mtd);
+	ret = doc_set_driver_info(chip_id, mtd);
+	if (ret)
+		goto nomem4;
 
 	doc_hamming_ecc_init(docg3, DOC_LAYOUT_OOB_PAGEINFO_SZ);
 	doc_reload_bbt(docg3);
 	return mtd;
 
+nomem4:
+	kfree(docg3->bbt);
 nomem3:
 	kfree(mtd);
 nomem2:
@@ -2117,7 +2125,7 @@ static int docg3_release(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id docg3_dt_ids[] = {
+static const struct of_device_id docg3_dt_ids[] = {
 	{ .compatible = "m-systems,diskonchip-g3" },
 	{}
 };
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 7c8b1694a134..d313f948b96c 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -223,7 +223,7 @@ static int m25p_probe(struct spi_device *spi)
 	 */
 	if (data && data->type)
 		flash_name = data->type;
-	else if (!strcmp(spi->modalias, "nor-jedec"))
+	else if (!strcmp(spi->modalias, "spi-nor"))
 		flash_name = NULL; /* auto-detect */
 	else
 		flash_name = spi->modalias;
@@ -255,57 +255,45 @@ static int m25p_remove(struct spi_device *spi)
  * since most of these flash are compatible to some extent, and their
  * differences can often be differentiated by the JEDEC read-ID command, we
  * encourage new users to add support to the spi-nor library, and simply bind
- * against a generic string here (e.g., "nor-jedec").
+ * against a generic string here (e.g., "jedec,spi-nor").
  *
  * Many flash names are kept here in this list (as well as in spi-nor.c) to
  * keep them available as module aliases for existing platforms.
  */
 static const struct spi_device_id m25p_ids[] = {
-	{"at25fs010"},	{"at25fs040"},	{"at25df041a"},	{"at25df321a"},
-	{"at25df641"},	{"at26f004"},	{"at26df081a"},	{"at26df161a"},
-	{"at26df321"},	{"at45db081d"},
-	{"en25f32"},	{"en25p32"},	{"en25q32b"},	{"en25p64"},
-	{"en25q64"},	{"en25qh128"},	{"en25qh256"},
-	{"f25l32pa"},
-	{"mr25h256"},	{"mr25h10"},
-	{"gd25q32"},	{"gd25q64"},
-	{"160s33b"},	{"320s33b"},	{"640s33b"},
-	{"mx25l2005a"},	{"mx25l4005a"},	{"mx25l8005"},	{"mx25l1606e"},
-	{"mx25l3205d"},	{"mx25l3255e"},	{"mx25l6405d"},	{"mx25l12805d"},
-	{"mx25l12855e"},{"mx25l25635e"},{"mx25l25655e"},{"mx66l51235l"},
-	{"mx66l1g55g"},
-	{"n25q064"},	{"n25q128a11"},	{"n25q128a13"},	{"n25q256a"},
-	{"n25q512a"},	{"n25q512ax3"},	{"n25q00"},
-	{"pm25lv512"},	{"pm25lv010"},	{"pm25lq032"},
-	{"s25sl032p"},	{"s25sl064p"},	{"s25fl256s0"},	{"s25fl256s1"},
-	{"s25fl512s"},	{"s70fl01gs"},	{"s25sl12800"},	{"s25sl12801"},
-	{"s25fl129p0"},	{"s25fl129p1"},	{"s25sl004a"},	{"s25sl008a"},
-	{"s25sl016a"},	{"s25sl032a"},	{"s25sl064a"},	{"s25fl008k"},
-	{"s25fl016k"},	{"s25fl064k"},	{"s25fl132k"},
-	{"sst25vf040b"},{"sst25vf080b"},{"sst25vf016b"},{"sst25vf032b"},
-	{"sst25vf064c"},{"sst25wf512"},	{"sst25wf010"},	{"sst25wf020"},
-	{"sst25wf040"},
-	{"m25p05"},	{"m25p10"},	{"m25p20"},	{"m25p40"},
-	{"m25p80"},	{"m25p16"},	{"m25p32"},	{"m25p64"},
-	{"m25p128"},	{"n25q032"},
+	/*
+	 * Entries not used in DTs that should be safe to drop after replacing
+	 * them with "nor-jedec" in platform data.
+	 */
+	{"s25sl064a"},	{"w25x16"},	{"m25p10"},	{"m25px64"},
+
+	/*
+	 * Entries that were used in DTs without "nor-jedec" fallback and should
+	 * be kept for backward compatibility.
+	 */
+	{"at25df321a"},	{"at25df641"},	{"at26df081a"},
+	{"mr25h256"},
+	{"mx25l4005a"},	{"mx25l1606e"},	{"mx25l6405d"},	{"mx25l12805d"},
+	{"mx25l25635e"},{"mx66l51235l"},
+	{"n25q064"},	{"n25q128a11"},	{"n25q128a13"},	{"n25q512a"},
+	{"s25fl256s1"},	{"s25fl512s"},	{"s25sl12801"},	{"s25fl008k"},
+	{"s25fl064k"},
+	{"sst25vf040b"},{"sst25vf016b"},{"sst25vf032b"},{"sst25wf040"},
+	{"m25p40"},	{"m25p80"},	{"m25p16"},	{"m25p32"},
+	{"m25p64"},	{"m25p128"},
+	{"w25x80"},	{"w25x32"},	{"w25q32"},	{"w25q32dw"},
+	{"w25q80bl"},	{"w25q128"},	{"w25q256"},
+
+	/* Flashes that can't be detected using JEDEC */
 	{"m25p05-nonjedec"},	{"m25p10-nonjedec"},	{"m25p20-nonjedec"},
 	{"m25p40-nonjedec"},	{"m25p80-nonjedec"},	{"m25p16-nonjedec"},
 	{"m25p32-nonjedec"},	{"m25p64-nonjedec"},	{"m25p128-nonjedec"},
-	{"m45pe10"},	{"m45pe80"},	{"m45pe16"},
-	{"m25pe20"},	{"m25pe80"},	{"m25pe16"},
-	{"m25px16"},	{"m25px32"},	{"m25px32-s0"},	{"m25px32-s1"},
-	{"m25px64"},	{"m25px80"},
-	{"w25x10"},	{"w25x20"},	{"w25x40"},	{"w25x80"},
-	{"w25x16"},	{"w25x32"},	{"w25q32"},	{"w25q32dw"},
-	{"w25x64"},	{"w25q64"},	{"w25q80"},	{"w25q80bl"},
-	{"w25q128"},	{"w25q256"},	{"cat25c11"},
-	{"cat25c03"},	{"cat25c09"},	{"cat25c17"},	{"cat25128"},
 
 	/*
 	 * Generic support for SPI NOR that can be identified by the JEDEC READ
 	 * ID opcode (0x9F). Use this, if possible.
 	 */
-	{"nor-jedec"},
+	{"spi-nor"},
 	{ },
 };
 MODULE_DEVICE_TABLE(spi, m25p_ids);
diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
new file mode 100644
index 000000000000..d5b870b3fd4e
--- /dev/null
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -0,0 +1,285 @@
+/*
+ * OPAL PNOR flash MTD abstraction
+ *
+ * Copyright IBM 2015
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <asm/opal.h>
+
+
+/*
+ * This driver creates the a Linux MTD abstraction for platform PNOR flash
+ * backed by OPAL calls
+ */
+
+struct powernv_flash {
+	struct mtd_info	mtd;
+	u32 id;
+};
+
+enum flash_op {
+	FLASH_OP_READ,
+	FLASH_OP_WRITE,
+	FLASH_OP_ERASE,
+};
+
+static int powernv_flash_async_op(struct mtd_info *mtd, enum flash_op op,
+		loff_t offset, size_t len, size_t *retlen, u_char *buf)
+{
+	struct powernv_flash *info = (struct powernv_flash *)mtd->priv;
+	struct device *dev = &mtd->dev;
+	int token;
+	struct opal_msg msg;
+	int rc;
+
+	dev_dbg(dev, "%s(op=%d, offset=0x%llx, len=%zu)\n",
+			__func__, op, offset, len);
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		if (token != -ERESTARTSYS)
+			dev_err(dev, "Failed to get an async token\n");
+
+		return token;
+	}
+
+	switch (op) {
+	case FLASH_OP_READ:
+		rc = opal_flash_read(info->id, offset, __pa(buf), len, token);
+		break;
+	case FLASH_OP_WRITE:
+		rc = opal_flash_write(info->id, offset, __pa(buf), len, token);
+		break;
+	case FLASH_OP_ERASE:
+		rc = opal_flash_erase(info->id, offset, len, token);
+		break;
+	default:
+		BUG_ON(1);
+	}
+
+	if (rc != OPAL_ASYNC_COMPLETION) {
+		dev_err(dev, "opal_flash_async_op(op=%d) failed (rc %d)\n",
+				op, rc);
+		opal_async_release_token(token);
+		return -EIO;
+	}
+
+	rc = opal_async_wait_response(token, &msg);
+	opal_async_release_token(token);
+	if (rc) {
+		dev_err(dev, "opal async wait failed (rc %d)\n", rc);
+		return -EIO;
+	}
+
+	rc = be64_to_cpu(msg.params[1]);
+	if (rc == OPAL_SUCCESS) {
+		rc = 0;
+		if (retlen)
+			*retlen = len;
+	} else {
+		rc = -EIO;
+	}
+
+	return rc;
+}
+
+/**
+ * @mtd: the device
+ * @from: the offset to read from
+ * @len: the number of bytes to read
+ * @retlen: the number of bytes actually read
+ * @buf: the filled in buffer
+ *
+ * Returns 0 if read successful, or -ERRNO if an error occurred
+ */
+static int powernv_flash_read(struct mtd_info *mtd, loff_t from, size_t len,
+	     size_t *retlen, u_char *buf)
+{
+	return powernv_flash_async_op(mtd, FLASH_OP_READ, from,
+			len, retlen, buf);
+}
+
+/**
+ * @mtd: the device
+ * @to: the offset to write to
+ * @len: the number of bytes to write
+ * @retlen: the number of bytes actually written
+ * @buf: the buffer to get bytes from
+ *
+ * Returns 0 if write successful, -ERRNO if error occurred
+ */
+static int powernv_flash_write(struct mtd_info *mtd, loff_t to, size_t len,
+		     size_t *retlen, const u_char *buf)
+{
+	return powernv_flash_async_op(mtd, FLASH_OP_WRITE, to,
+			len, retlen, (u_char *)buf);
+}
+
+/**
+ * @mtd: the device
+ * @erase: the erase info
+ * Returns 0 if erase successful or -ERRNO if an error occurred
+ */
+static int powernv_flash_erase(struct mtd_info *mtd, struct erase_info *erase)
+{
+	int rc;
+
+	erase->state = MTD_ERASING;
+
+	/* todo: register our own notifier to do a true async implementation */
+	rc =  powernv_flash_async_op(mtd, FLASH_OP_ERASE, erase->addr,
+			erase->len, NULL, NULL);
+
+	if (rc) {
+		erase->fail_addr = erase->addr;
+		erase->state = MTD_ERASE_FAILED;
+	} else {
+		erase->state = MTD_ERASE_DONE;
+	}
+	mtd_erase_callback(erase);
+	return rc;
+}
+
+/**
+ * powernv_flash_set_driver_info - Fill the mtd_info structure and docg3
+ * structure @pdev: The platform device
+ * @mtd: The structure to fill
+ */
+static int powernv_flash_set_driver_info(struct device *dev,
+		struct mtd_info *mtd)
+{
+	u64 size;
+	u32 erase_size;
+	int rc;
+
+	rc = of_property_read_u32(dev->of_node, "ibm,flash-block-size",
+			&erase_size);
+	if (rc) {
+		dev_err(dev, "couldn't get resource block size information\n");
+		return rc;
+	}
+
+	rc = of_property_read_u64(dev->of_node, "reg", &size);
+	if (rc) {
+		dev_err(dev, "couldn't get resource size information\n");
+		return rc;
+	}
+
+	/*
+	 * Going to have to check what details I need to set and how to
+	 * get them
+	 */
+	mtd->name = of_get_property(dev->of_node, "name", NULL);
+	mtd->type = MTD_NORFLASH;
+	mtd->flags = MTD_WRITEABLE;
+	mtd->size = size;
+	mtd->erasesize = erase_size;
+	mtd->writebufsize = mtd->writesize = 1;
+	mtd->owner = THIS_MODULE;
+	mtd->_erase = powernv_flash_erase;
+	mtd->_read = powernv_flash_read;
+	mtd->_write = powernv_flash_write;
+	mtd->dev.parent = dev;
+	return 0;
+}
+
+/**
+ * powernv_flash_probe
+ * @pdev: platform device
+ *
+ * Returns 0 on success, -ENOMEM, -ENXIO on error
+ */
+static int powernv_flash_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct powernv_flash *data;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	data->mtd.priv = data;
+
+	ret = of_property_read_u32(dev->of_node, "ibm,opal-id", &(data->id));
+	if (ret) {
+		dev_err(dev, "no device property 'ibm,opal-id'\n");
+		goto out;
+	}
+
+	ret = powernv_flash_set_driver_info(dev, &data->mtd);
+	if (ret)
+		goto out;
+
+	dev_set_drvdata(dev, data);
+
+	/*
+	 * The current flash that skiboot exposes is one contiguous flash chip
+	 * with an ffs partition at the start, it should prove easier for users
+	 * to deal with partitions or not as they see fit
+	 */
+	ret = mtd_device_register(&data->mtd, NULL, 0);
+
+out:
+	return ret;
+}
+
+/**
+ * op_release - Release the driver
+ * @pdev: the platform device
+ *
+ * Returns 0
+ */
+static int powernv_flash_release(struct platform_device *pdev)
+{
+	struct powernv_flash *data = dev_get_drvdata(&(pdev->dev));
+
+	/* All resources should be freed automatically */
+	return mtd_device_unregister(&(data->mtd));
+}
+
+static const struct of_device_id powernv_flash_match[] = {
+	{ .compatible = "ibm,opal-flash" },
+	{}
+};
+
+static struct platform_driver powernv_flash_driver = {
+	.driver		= {
+		.name		= "powernv_flash",
+		.of_match_table	= powernv_flash_match,
+	},
+	.remove		= powernv_flash_release,
+	.probe		= powernv_flash_probe,
+};
+
+module_platform_driver(powernv_flash_driver);
+
+MODULE_DEVICE_TABLE(of, powernv_flash_match);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Cyril Bur <cyril.bur@au1.ibm.com>");
+MODULE_DESCRIPTION("MTD abstraction for OPAL flash");
diff --git a/drivers/mtd/devices/spear_smi.c b/drivers/mtd/devices/spear_smi.c
index 508bab3bd0c4..04b24d2b03f2 100644
--- a/drivers/mtd/devices/spear_smi.c
+++ b/drivers/mtd/devices/spear_smi.c
@@ -1,8 +1,8 @@
 /*
  * SMI (Serial Memory Controller) device driver for Serial NOR Flash on
  * SPEAr platform
- * The serial nor interface is largely based on drivers/mtd/m25p80.c,
- * however the SPI interface has been replaced by SMI.
+ * The serial nor interface is largely based on m25p80.c, however the SPI
+ * interface has been replaced by SMI.
  *
  * Copyright © 2010 STMicroelectronics.
  * Ashish Priyadarshi
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index e715ae90632f..7c95a656f9e4 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -326,7 +326,7 @@ config MTD_BFIN_ASYNC
 
 config MTD_GPIO_ADDR
 	tristate "GPIO-assisted Flash Chip Support"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	depends on MTD_COMPLEX_MAPPINGS
 	help
 	  Map driver which allows flashes to be partially physically addressed
diff --git a/drivers/mtd/maps/amd76xrom.c b/drivers/mtd/maps/amd76xrom.c
index f7207b0a76dc..f2b68667ea59 100644
--- a/drivers/mtd/maps/amd76xrom.c
+++ b/drivers/mtd/maps/amd76xrom.c
@@ -138,7 +138,7 @@ static int amd76xrom_init_one(struct pci_dev *pdev,
 	/*
 	 * Try to reserve the window mem region.  If this fails then
 	 * it is likely due to a fragment of the window being
-	 * "reseved" by the BIOS.  In the case that the
+	 * "reserved" by the BIOS.  In the case that the
 	 * request_mem_region() fails then once the rom size is
 	 * discovered we will try to reserve the unreserved fragment.
 	 */
diff --git a/drivers/mtd/maps/dc21285.c b/drivers/mtd/maps/dc21285.c
index f8a7dd14cee0..70a3db3ab856 100644
--- a/drivers/mtd/maps/dc21285.c
+++ b/drivers/mtd/maps/dc21285.c
@@ -38,9 +38,9 @@ static void nw_en_write(void)
 	 * we want to write a bit pattern XXX1 to Xilinx to enable
 	 * the write gate, which will be open for about the next 2ms.
 	 */
-	spin_lock_irqsave(&nw_gpio_lock, flags);
+	raw_spin_lock_irqsave(&nw_gpio_lock, flags);
 	nw_cpld_modify(CPLD_FLASH_WR_ENABLE, CPLD_FLASH_WR_ENABLE);
-	spin_unlock_irqrestore(&nw_gpio_lock, flags);
+	raw_spin_unlock_irqrestore(&nw_gpio_lock, flags);
 
 	/*
 	 * let the ISA bus to catch on...
diff --git a/drivers/mtd/maps/esb2rom.c b/drivers/mtd/maps/esb2rom.c
index f784cf0caa13..76ed651b515b 100644
--- a/drivers/mtd/maps/esb2rom.c
+++ b/drivers/mtd/maps/esb2rom.c
@@ -234,7 +234,7 @@ static int esb2rom_init_one(struct pci_dev *pdev,
 
 	/*
 	 * Try to reserve the window mem region.  If this fails then
-	 * it is likely due to the window being "reseved" by the BIOS.
+	 * it is likely due to the window being "reserved" by the BIOS.
 	 */
 	window->rsrc.name = MOD_NAME;
 	window->rsrc.start = window->phys;
diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c
index c7478e18f485..8636bba42200 100644
--- a/drivers/mtd/maps/ichxrom.c
+++ b/drivers/mtd/maps/ichxrom.c
@@ -167,7 +167,7 @@ static int ichxrom_init_one(struct pci_dev *pdev,
 
 	/*
 	 * Try to reserve the window mem region.  If this fails then
-	 * it is likely due to the window being "reseved" by the BIOS.
+	 * it is likely due to the window being "reserved" by the BIOS.
 	 */
 	window->rsrc.name = MOD_NAME;
 	window->rsrc.start = window->phys;
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
index 33d26f5bee54..e2f878216048 100644
--- a/drivers/mtd/maps/lantiq-flash.c
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -45,7 +45,6 @@ struct ltq_mtd {
 };
 
 static const char ltq_map_name[] = "ltq_nor";
-static const char * const ltq_probe_types[] = { "cmdlinepart", "ofpart", NULL };
 
 static map_word
 ltq_read16(struct map_info *map, unsigned long adr)
@@ -168,8 +167,7 @@ ltq_mtd_probe(struct platform_device *pdev)
 	cfi->addr_unlock2 ^= 1;
 
 	ppdata.of_node = pdev->dev.of_node;
-	err = mtd_device_parse_register(ltq_mtd->mtd, ltq_probe_types,
-					&ppdata, NULL, 0);
+	err = mtd_device_parse_register(ltq_mtd->mtd, NULL, &ppdata, NULL, 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to add partitions\n");
 		goto err_destroy;
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index ff26e979b1a1..774b32fd29e6 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -147,7 +147,7 @@ static void of_free_probes(const char * const *probes)
 		kfree(probes);
 }
 
-static struct of_device_id of_flash_match[];
+static const struct of_device_id of_flash_match[];
 static int of_flash_probe(struct platform_device *dev)
 {
 	const char * const *part_probe_types;
@@ -327,7 +327,7 @@ err_flash_remove:
 	return err;
 }
 
-static struct of_device_id of_flash_match[] = {
+static const struct of_device_id of_flash_match[] = {
 	{
 		.compatible	= "cfi-flash",
 		.data		= (void *)"cfi_probe",
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 2b0c52870999..41acc507b22e 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -197,6 +197,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 		return -ERESTARTSYS; /* FIXME: busy loop! -arnd*/
 
 	mutex_lock(&dev->lock);
+	mutex_lock(&mtd_table_mutex);
 
 	if (dev->open)
 		goto unlock;
@@ -220,6 +221,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode)
 
 unlock:
 	dev->open++;
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;
@@ -230,6 +232,7 @@ error_release:
 error_put:
 	module_put(dev->tr->owner);
 	kref_put(&dev->ref, blktrans_dev_release);
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 	return ret;
@@ -243,6 +246,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode)
 		return;
 
 	mutex_lock(&dev->lock);
+	mutex_lock(&mtd_table_mutex);
 
 	if (--dev->open)
 		goto unlock;
@@ -256,6 +260,7 @@ static void blktrans_release(struct gendisk *disk, fmode_t mode)
 		__put_mtd_device(dev->mtd);
 	}
 unlock:
+	mutex_unlock(&mtd_table_mutex);
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
 }
@@ -273,7 +278,7 @@ static int blktrans_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	if (!dev->mtd)
 		goto unlock;
 
-	ret = dev->tr->getgeo ? dev->tr->getgeo(dev, geo) : 0;
+	ret = dev->tr->getgeo ? dev->tr->getgeo(dev, geo) : -ENOTTY;
 unlock:
 	mutex_unlock(&dev->lock);
 	blktrans_dev_put(dev);
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index d172195fbd15..8bbbb751bf45 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -48,14 +48,34 @@
 static struct backing_dev_info mtd_bdi = {
 };
 
-static int mtd_cls_suspend(struct device *dev, pm_message_t state);
-static int mtd_cls_resume(struct device *dev);
+#ifdef CONFIG_PM_SLEEP
+
+static int mtd_cls_suspend(struct device *dev)
+{
+	struct mtd_info *mtd = dev_get_drvdata(dev);
+
+	return mtd ? mtd_suspend(mtd) : 0;
+}
+
+static int mtd_cls_resume(struct device *dev)
+{
+	struct mtd_info *mtd = dev_get_drvdata(dev);
+
+	if (mtd)
+		mtd_resume(mtd);
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(mtd_cls_pm_ops, mtd_cls_suspend, mtd_cls_resume);
+#define MTD_CLS_PM_OPS (&mtd_cls_pm_ops)
+#else
+#define MTD_CLS_PM_OPS NULL
+#endif
 
 static struct class mtd_class = {
 	.name = "mtd",
 	.owner = THIS_MODULE,
-	.suspend = mtd_cls_suspend,
-	.resume = mtd_cls_resume,
+	.pm = MTD_CLS_PM_OPS,
 };
 
 static DEFINE_IDR(mtd_idr);
@@ -88,22 +108,6 @@ static void mtd_release(struct device *dev)
 	device_destroy(&mtd_class, index + 1);
 }
 
-static int mtd_cls_suspend(struct device *dev, pm_message_t state)
-{
-	struct mtd_info *mtd = dev_get_drvdata(dev);
-
-	return mtd ? mtd_suspend(mtd) : 0;
-}
-
-static int mtd_cls_resume(struct device *dev)
-{
-	struct mtd_info *mtd = dev_get_drvdata(dev);
-
-	if (mtd)
-		mtd_resume(mtd);
-	return 0;
-}
-
 static ssize_t mtd_type_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -375,8 +379,7 @@ static int mtd_reboot_notifier(struct notifier_block *n, unsigned long state,
  *
  *	Add a device to the list of MTD devices present in the system, and
  *	notify each currently active MTD 'user' of its arrival. Returns
- *	zero on success or 1 on failure, which currently will only happen
- *	if there is insufficient memory or a sysfs error.
+ *	zero on success or non-zero on failure.
  */
 
 int add_mtd_device(struct mtd_info *mtd)
@@ -390,8 +393,10 @@ int add_mtd_device(struct mtd_info *mtd)
 	mutex_lock(&mtd_table_mutex);
 
 	i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
-	if (i < 0)
+	if (i < 0) {
+		error = i;
 		goto fail_locked;
+	}
 
 	mtd->index = i;
 	mtd->usecount = 0;
@@ -420,6 +425,8 @@ int add_mtd_device(struct mtd_info *mtd)
 			printk(KERN_WARNING
 			       "%s: unlock failed, writes may not work\n",
 			       mtd->name);
+		/* Ignore unlock failures? */
+		error = 0;
 	}
 
 	/* Caller should have set dev.parent to match the
@@ -430,7 +437,8 @@ int add_mtd_device(struct mtd_info *mtd)
 	mtd->dev.devt = MTD_DEVT(i);
 	dev_set_name(&mtd->dev, "mtd%d", i);
 	dev_set_drvdata(&mtd->dev, mtd);
-	if (device_register(&mtd->dev) != 0)
+	error = device_register(&mtd->dev);
+	if (error)
 		goto fail_added;
 
 	device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
@@ -454,7 +462,7 @@ fail_added:
 	idr_remove(&mtd_idr, i);
 fail_locked:
 	mutex_unlock(&mtd_table_mutex);
-	return 1;
+	return error;
 }
 
 /**
@@ -510,8 +518,8 @@ static int mtd_add_device_partitions(struct mtd_info *mtd,
 
 	if (nbparts == 0 || IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) {
 		ret = add_mtd_device(mtd);
-		if (ret == 1)
-			return -ENODEV;
+		if (ret)
+			return ret;
 	}
 
 	if (nbparts > 0) {
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 5897d8d8fa5a..5b2806a7e5f7 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -76,7 +76,7 @@ config MTD_NAND_DENALI_SCRATCH_REG_ADDR
 
 config MTD_NAND_GPIO
 	tristate "GPIO assisted NAND Flash driver"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  This enables a NAND flash driver where control signals are
 	  connected to GPIO pins, and commands and data are communicated
@@ -394,6 +394,14 @@ config MTD_NAND_GPMI_NAND
 	 block, such as SD card. So pay attention to it when you enable
 	 the GPMI.
 
+config MTD_NAND_BRCMNAND
+	tristate "Broadcom STB NAND controller"
+	depends on ARM || MIPS
+	help
+	  Enables the Broadcom NAND controller driver. The controller was
+	  originally designed for Set-Top Box but is used on various BCM7xxx,
+	  BCM3xxx, BCM63xxx, iProc/Cygnus and more.
+
 config MTD_NAND_BCM47XXNFLASH
 	tristate "Support for NAND flash on BCM4706 BCMA bus"
 	depends on BCMA_NFLASH
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 582bbd05aff7..1f897ec3c242 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -52,5 +52,6 @@ obj-$(CONFIG_MTD_NAND_XWAY)		+= xway_nand.o
 obj-$(CONFIG_MTD_NAND_BCM47XXNFLASH)	+= bcm47xxnflash/
 obj-$(CONFIG_MTD_NAND_SUNXI)		+= sunxi_nand.o
 obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
+obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o
diff --git a/drivers/mtd/nand/brcmnand/Makefile b/drivers/mtd/nand/brcmnand/Makefile
new file mode 100644
index 000000000000..3b1fbfd27d4f
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/Makefile
@@ -0,0 +1,6 @@
+# link order matters; don't link the more generic brcmstb_nand.o before the
+# more specific iproc_nand.o, for instance
+obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= iproc_nand.o
+obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= bcm63138_nand.o
+obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmstb_nand.o
+obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand.o
diff --git a/drivers/mtd/nand/brcmnand/bcm63138_nand.c b/drivers/mtd/nand/brcmnand/bcm63138_nand.c
new file mode 100644
index 000000000000..3f4c44c24e14
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/bcm63138_nand.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright © 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "brcmnand.h"
+
+struct bcm63138_nand_soc_priv {
+	void __iomem *base;
+};
+
+#define BCM63138_NAND_INT_STATUS		0x00
+#define BCM63138_NAND_INT_EN			0x04
+
+enum {
+	BCM63138_CTLRDY		= BIT(4),
+};
+
+static bool bcm63138_nand_intc_ack(struct brcmnand_soc *soc)
+{
+	struct bcm63138_nand_soc_priv *priv = soc->priv;
+	void __iomem *mmio = priv->base + BCM63138_NAND_INT_STATUS;
+	u32 val = brcmnand_readl(mmio);
+
+	if (val & BCM63138_CTLRDY) {
+		brcmnand_writel(val & ~BCM63138_CTLRDY, mmio);
+		return true;
+	}
+
+	return false;
+}
+
+static void bcm63138_nand_intc_set(struct brcmnand_soc *soc, bool en)
+{
+	struct bcm63138_nand_soc_priv *priv = soc->priv;
+	void __iomem *mmio = priv->base + BCM63138_NAND_INT_EN;
+	u32 val = brcmnand_readl(mmio);
+
+	if (en)
+		val |= BCM63138_CTLRDY;
+	else
+		val &= ~BCM63138_CTLRDY;
+
+	brcmnand_writel(val, mmio);
+}
+
+static int bcm63138_nand_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct bcm63138_nand_soc_priv *priv;
+	struct brcmnand_soc *soc;
+	struct resource *res;
+
+	soc = devm_kzalloc(dev, sizeof(*soc), GFP_KERNEL);
+	if (!soc)
+		return -ENOMEM;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand-int-base");
+	priv->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	soc->pdev = pdev;
+	soc->priv = priv;
+	soc->ctlrdy_ack = bcm63138_nand_intc_ack;
+	soc->ctlrdy_set_enabled = bcm63138_nand_intc_set;
+
+	return brcmnand_probe(pdev, soc);
+}
+
+static const struct of_device_id bcm63138_nand_of_match[] = {
+	{ .compatible = "brcm,nand-bcm63138" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, bcm63138_nand_of_match);
+
+static struct platform_driver bcm63138_nand_driver = {
+	.probe			= bcm63138_nand_probe,
+	.remove			= brcmnand_remove,
+	.driver = {
+		.name		= "bcm63138_nand",
+		.pm		= &brcmnand_pm_ops,
+		.of_match_table	= bcm63138_nand_of_match,
+	}
+};
+module_platform_driver(bcm63138_nand_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Brian Norris");
+MODULE_DESCRIPTION("NAND driver for BCM63138");
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c
new file mode 100644
index 000000000000..fddb795eeb71
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/brcmnand.c
@@ -0,0 +1,2246 @@
+/*
+ * Copyright © 2010-2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+#include <linux/ioport.h>
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/mm.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+#include <linux/of.h>
+#include <linux/of_mtd.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/log2.h>
+
+#include "brcmnand.h"
+
+/*
+ * This flag controls if WP stays on between erase/write commands to mitigate
+ * flash corruption due to power glitches. Values:
+ * 0: NAND_WP is not used or not available
+ * 1: NAND_WP is set by default, cleared for erase/write operations
+ * 2: NAND_WP is always cleared
+ */
+static int wp_on = 1;
+module_param(wp_on, int, 0444);
+
+/***********************************************************************
+ * Definitions
+ ***********************************************************************/
+
+#define DRV_NAME			"brcmnand"
+
+#define CMD_NULL			0x00
+#define CMD_PAGE_READ			0x01
+#define CMD_SPARE_AREA_READ		0x02
+#define CMD_STATUS_READ			0x03
+#define CMD_PROGRAM_PAGE		0x04
+#define CMD_PROGRAM_SPARE_AREA		0x05
+#define CMD_COPY_BACK			0x06
+#define CMD_DEVICE_ID_READ		0x07
+#define CMD_BLOCK_ERASE			0x08
+#define CMD_FLASH_RESET			0x09
+#define CMD_BLOCKS_LOCK			0x0a
+#define CMD_BLOCKS_LOCK_DOWN		0x0b
+#define CMD_BLOCKS_UNLOCK		0x0c
+#define CMD_READ_BLOCKS_LOCK_STATUS	0x0d
+#define CMD_PARAMETER_READ		0x0e
+#define CMD_PARAMETER_CHANGE_COL	0x0f
+#define CMD_LOW_LEVEL_OP		0x10
+
+struct brcm_nand_dma_desc {
+	u32 next_desc;
+	u32 next_desc_ext;
+	u32 cmd_irq;
+	u32 dram_addr;
+	u32 dram_addr_ext;
+	u32 tfr_len;
+	u32 total_len;
+	u32 flash_addr;
+	u32 flash_addr_ext;
+	u32 cs;
+	u32 pad2[5];
+	u32 status_valid;
+} __packed;
+
+/* Bitfields for brcm_nand_dma_desc::status_valid */
+#define FLASH_DMA_ECC_ERROR	(1 << 8)
+#define FLASH_DMA_CORR_ERROR	(1 << 9)
+
+/* 512B flash cache in the NAND controller HW */
+#define FC_SHIFT		9U
+#define FC_BYTES		512U
+#define FC_WORDS		(FC_BYTES >> 2)
+
+#define BRCMNAND_MIN_PAGESIZE	512
+#define BRCMNAND_MIN_BLOCKSIZE	(8 * 1024)
+#define BRCMNAND_MIN_DEVSIZE	(4ULL * 1024 * 1024)
+
+/* Controller feature flags */
+enum {
+	BRCMNAND_HAS_1K_SECTORS			= BIT(0),
+	BRCMNAND_HAS_PREFETCH			= BIT(1),
+	BRCMNAND_HAS_CACHE_MODE			= BIT(2),
+	BRCMNAND_HAS_WP				= BIT(3),
+};
+
+struct brcmnand_controller {
+	struct device		*dev;
+	struct nand_hw_control	controller;
+	void __iomem		*nand_base;
+	void __iomem		*nand_fc; /* flash cache */
+	void __iomem		*flash_dma_base;
+	unsigned int		irq;
+	unsigned int		dma_irq;
+	int			nand_version;
+
+	/* Some SoCs provide custom interrupt status register(s) */
+	struct brcmnand_soc	*soc;
+
+	int			cmd_pending;
+	bool			dma_pending;
+	struct completion	done;
+	struct completion	dma_done;
+
+	/* List of NAND hosts (one for each chip-select) */
+	struct list_head host_list;
+
+	struct brcm_nand_dma_desc *dma_desc;
+	dma_addr_t		dma_pa;
+
+	/* in-memory cache of the FLASH_CACHE, used only for some commands */
+	u32			flash_cache[FC_WORDS];
+
+	/* Controller revision details */
+	const u16		*reg_offsets;
+	unsigned int		reg_spacing; /* between CS1, CS2, ... regs */
+	const u8		*cs_offsets; /* within each chip-select */
+	const u8		*cs0_offsets; /* within CS0, if different */
+	unsigned int		max_block_size;
+	const unsigned int	*block_sizes;
+	unsigned int		max_page_size;
+	const unsigned int	*page_sizes;
+	unsigned int		max_oob;
+	u32			features;
+
+	/* for low-power standby/resume only */
+	u32			nand_cs_nand_select;
+	u32			nand_cs_nand_xor;
+	u32			corr_stat_threshold;
+	u32			flash_dma_mode;
+};
+
+struct brcmnand_cfg {
+	u64			device_size;
+	unsigned int		block_size;
+	unsigned int		page_size;
+	unsigned int		spare_area_size;
+	unsigned int		device_width;
+	unsigned int		col_adr_bytes;
+	unsigned int		blk_adr_bytes;
+	unsigned int		ful_adr_bytes;
+	unsigned int		sector_size_1k;
+	unsigned int		ecc_level;
+	/* use for low-power standby/resume only */
+	u32			acc_control;
+	u32			config;
+	u32			config_ext;
+	u32			timing_1;
+	u32			timing_2;
+};
+
+struct brcmnand_host {
+	struct list_head	node;
+	struct device_node	*of_node;
+
+	struct nand_chip	chip;
+	struct mtd_info		mtd;
+	struct platform_device	*pdev;
+	int			cs;
+
+	unsigned int		last_cmd;
+	unsigned int		last_byte;
+	u64			last_addr;
+	struct brcmnand_cfg	hwcfg;
+	struct brcmnand_controller *ctrl;
+};
+
+enum brcmnand_reg {
+	BRCMNAND_CMD_START = 0,
+	BRCMNAND_CMD_EXT_ADDRESS,
+	BRCMNAND_CMD_ADDRESS,
+	BRCMNAND_INTFC_STATUS,
+	BRCMNAND_CS_SELECT,
+	BRCMNAND_CS_XOR,
+	BRCMNAND_LL_OP,
+	BRCMNAND_CS0_BASE,
+	BRCMNAND_CS1_BASE,		/* CS1 regs, if non-contiguous */
+	BRCMNAND_CORR_THRESHOLD,
+	BRCMNAND_CORR_THRESHOLD_EXT,
+	BRCMNAND_UNCORR_COUNT,
+	BRCMNAND_CORR_COUNT,
+	BRCMNAND_CORR_EXT_ADDR,
+	BRCMNAND_CORR_ADDR,
+	BRCMNAND_UNCORR_EXT_ADDR,
+	BRCMNAND_UNCORR_ADDR,
+	BRCMNAND_SEMAPHORE,
+	BRCMNAND_ID,
+	BRCMNAND_ID_EXT,
+	BRCMNAND_LL_RDATA,
+	BRCMNAND_OOB_READ_BASE,
+	BRCMNAND_OOB_READ_10_BASE,	/* offset 0x10, if non-contiguous */
+	BRCMNAND_OOB_WRITE_BASE,
+	BRCMNAND_OOB_WRITE_10_BASE,	/* offset 0x10, if non-contiguous */
+	BRCMNAND_FC_BASE,
+};
+
+/* BRCMNAND v4.0 */
+static const u16 brcmnand_regs_v40[] = {
+	[BRCMNAND_CMD_START]		=  0x04,
+	[BRCMNAND_CMD_EXT_ADDRESS]	=  0x08,
+	[BRCMNAND_CMD_ADDRESS]		=  0x0c,
+	[BRCMNAND_INTFC_STATUS]		=  0x6c,
+	[BRCMNAND_CS_SELECT]		=  0x14,
+	[BRCMNAND_CS_XOR]		=  0x18,
+	[BRCMNAND_LL_OP]		= 0x178,
+	[BRCMNAND_CS0_BASE]		=  0x40,
+	[BRCMNAND_CS1_BASE]		=  0xd0,
+	[BRCMNAND_CORR_THRESHOLD]	=  0x84,
+	[BRCMNAND_CORR_THRESHOLD_EXT]	=     0,
+	[BRCMNAND_UNCORR_COUNT]		=     0,
+	[BRCMNAND_CORR_COUNT]		=     0,
+	[BRCMNAND_CORR_EXT_ADDR]	=  0x70,
+	[BRCMNAND_CORR_ADDR]		=  0x74,
+	[BRCMNAND_UNCORR_EXT_ADDR]	=  0x78,
+	[BRCMNAND_UNCORR_ADDR]		=  0x7c,
+	[BRCMNAND_SEMAPHORE]		=  0x58,
+	[BRCMNAND_ID]			=  0x60,
+	[BRCMNAND_ID_EXT]		=  0x64,
+	[BRCMNAND_LL_RDATA]		= 0x17c,
+	[BRCMNAND_OOB_READ_BASE]	=  0x20,
+	[BRCMNAND_OOB_READ_10_BASE]	= 0x130,
+	[BRCMNAND_OOB_WRITE_BASE]	=  0x30,
+	[BRCMNAND_OOB_WRITE_10_BASE]	=     0,
+	[BRCMNAND_FC_BASE]		= 0x200,
+};
+
+/* BRCMNAND v5.0 */
+static const u16 brcmnand_regs_v50[] = {
+	[BRCMNAND_CMD_START]		=  0x04,
+	[BRCMNAND_CMD_EXT_ADDRESS]	=  0x08,
+	[BRCMNAND_CMD_ADDRESS]		=  0x0c,
+	[BRCMNAND_INTFC_STATUS]		=  0x6c,
+	[BRCMNAND_CS_SELECT]		=  0x14,
+	[BRCMNAND_CS_XOR]		=  0x18,
+	[BRCMNAND_LL_OP]		= 0x178,
+	[BRCMNAND_CS0_BASE]		=  0x40,
+	[BRCMNAND_CS1_BASE]		=  0xd0,
+	[BRCMNAND_CORR_THRESHOLD]	=  0x84,
+	[BRCMNAND_CORR_THRESHOLD_EXT]	=     0,
+	[BRCMNAND_UNCORR_COUNT]		=     0,
+	[BRCMNAND_CORR_COUNT]		=     0,
+	[BRCMNAND_CORR_EXT_ADDR]	=  0x70,
+	[BRCMNAND_CORR_ADDR]		=  0x74,
+	[BRCMNAND_UNCORR_EXT_ADDR]	=  0x78,
+	[BRCMNAND_UNCORR_ADDR]		=  0x7c,
+	[BRCMNAND_SEMAPHORE]		=  0x58,
+	[BRCMNAND_ID]			=  0x60,
+	[BRCMNAND_ID_EXT]		=  0x64,
+	[BRCMNAND_LL_RDATA]		= 0x17c,
+	[BRCMNAND_OOB_READ_BASE]	=  0x20,
+	[BRCMNAND_OOB_READ_10_BASE]	= 0x130,
+	[BRCMNAND_OOB_WRITE_BASE]	=  0x30,
+	[BRCMNAND_OOB_WRITE_10_BASE]	= 0x140,
+	[BRCMNAND_FC_BASE]		= 0x200,
+};
+
+/* BRCMNAND v6.0 - v7.1 */
+static const u16 brcmnand_regs_v60[] = {
+	[BRCMNAND_CMD_START]		=  0x04,
+	[BRCMNAND_CMD_EXT_ADDRESS]	=  0x08,
+	[BRCMNAND_CMD_ADDRESS]		=  0x0c,
+	[BRCMNAND_INTFC_STATUS]		=  0x14,
+	[BRCMNAND_CS_SELECT]		=  0x18,
+	[BRCMNAND_CS_XOR]		=  0x1c,
+	[BRCMNAND_LL_OP]		=  0x20,
+	[BRCMNAND_CS0_BASE]		=  0x50,
+	[BRCMNAND_CS1_BASE]		=     0,
+	[BRCMNAND_CORR_THRESHOLD]	=  0xc0,
+	[BRCMNAND_CORR_THRESHOLD_EXT]	=  0xc4,
+	[BRCMNAND_UNCORR_COUNT]		=  0xfc,
+	[BRCMNAND_CORR_COUNT]		= 0x100,
+	[BRCMNAND_CORR_EXT_ADDR]	= 0x10c,
+	[BRCMNAND_CORR_ADDR]		= 0x110,
+	[BRCMNAND_UNCORR_EXT_ADDR]	= 0x114,
+	[BRCMNAND_UNCORR_ADDR]		= 0x118,
+	[BRCMNAND_SEMAPHORE]		= 0x150,
+	[BRCMNAND_ID]			= 0x194,
+	[BRCMNAND_ID_EXT]		= 0x198,
+	[BRCMNAND_LL_RDATA]		= 0x19c,
+	[BRCMNAND_OOB_READ_BASE]	= 0x200,
+	[BRCMNAND_OOB_READ_10_BASE]	=     0,
+	[BRCMNAND_OOB_WRITE_BASE]	= 0x280,
+	[BRCMNAND_OOB_WRITE_10_BASE]	=     0,
+	[BRCMNAND_FC_BASE]		= 0x400,
+};
+
+enum brcmnand_cs_reg {
+	BRCMNAND_CS_CFG_EXT = 0,
+	BRCMNAND_CS_CFG,
+	BRCMNAND_CS_ACC_CONTROL,
+	BRCMNAND_CS_TIMING1,
+	BRCMNAND_CS_TIMING2,
+};
+
+/* Per chip-select offsets for v7.1 */
+static const u8 brcmnand_cs_offsets_v71[] = {
+	[BRCMNAND_CS_ACC_CONTROL]	= 0x00,
+	[BRCMNAND_CS_CFG_EXT]		= 0x04,
+	[BRCMNAND_CS_CFG]		= 0x08,
+	[BRCMNAND_CS_TIMING1]		= 0x0c,
+	[BRCMNAND_CS_TIMING2]		= 0x10,
+};
+
+/* Per chip-select offsets for pre v7.1, except CS0 on <= v5.0 */
+static const u8 brcmnand_cs_offsets[] = {
+	[BRCMNAND_CS_ACC_CONTROL]	= 0x00,
+	[BRCMNAND_CS_CFG_EXT]		= 0x04,
+	[BRCMNAND_CS_CFG]		= 0x04,
+	[BRCMNAND_CS_TIMING1]		= 0x08,
+	[BRCMNAND_CS_TIMING2]		= 0x0c,
+};
+
+/* Per chip-select offset for <= v5.0 on CS0 only */
+static const u8 brcmnand_cs_offsets_cs0[] = {
+	[BRCMNAND_CS_ACC_CONTROL]	= 0x00,
+	[BRCMNAND_CS_CFG_EXT]		= 0x08,
+	[BRCMNAND_CS_CFG]		= 0x08,
+	[BRCMNAND_CS_TIMING1]		= 0x10,
+	[BRCMNAND_CS_TIMING2]		= 0x14,
+};
+
+/* BRCMNAND_INTFC_STATUS */
+enum {
+	INTFC_FLASH_STATUS		= GENMASK(7, 0),
+
+	INTFC_ERASED			= BIT(27),
+	INTFC_OOB_VALID			= BIT(28),
+	INTFC_CACHE_VALID		= BIT(29),
+	INTFC_FLASH_READY		= BIT(30),
+	INTFC_CTLR_READY		= BIT(31),
+};
+
+static inline u32 nand_readreg(struct brcmnand_controller *ctrl, u32 offs)
+{
+	return brcmnand_readl(ctrl->nand_base + offs);
+}
+
+static inline void nand_writereg(struct brcmnand_controller *ctrl, u32 offs,
+				 u32 val)
+{
+	brcmnand_writel(val, ctrl->nand_base + offs);
+}
+
+static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
+{
+	static const unsigned int block_sizes_v6[] = { 8, 16, 128, 256, 512, 1024, 2048, 0 };
+	static const unsigned int block_sizes_v4[] = { 16, 128, 8, 512, 256, 1024, 2048, 0 };
+	static const unsigned int page_sizes[] = { 512, 2048, 4096, 8192, 0 };
+
+	ctrl->nand_version = nand_readreg(ctrl, 0) & 0xffff;
+
+	/* Only support v4.0+? */
+	if (ctrl->nand_version < 0x0400) {
+		dev_err(ctrl->dev, "version %#x not supported\n",
+			ctrl->nand_version);
+		return -ENODEV;
+	}
+
+	/* Register offsets */
+	if (ctrl->nand_version >= 0x0600)
+		ctrl->reg_offsets = brcmnand_regs_v60;
+	else if (ctrl->nand_version >= 0x0500)
+		ctrl->reg_offsets = brcmnand_regs_v50;
+	else if (ctrl->nand_version >= 0x0400)
+		ctrl->reg_offsets = brcmnand_regs_v40;
+
+	/* Chip-select stride */
+	if (ctrl->nand_version >= 0x0701)
+		ctrl->reg_spacing = 0x14;
+	else
+		ctrl->reg_spacing = 0x10;
+
+	/* Per chip-select registers */
+	if (ctrl->nand_version >= 0x0701) {
+		ctrl->cs_offsets = brcmnand_cs_offsets_v71;
+	} else {
+		ctrl->cs_offsets = brcmnand_cs_offsets;
+
+		/* v5.0 and earlier has a different CS0 offset layout */
+		if (ctrl->nand_version <= 0x0500)
+			ctrl->cs0_offsets = brcmnand_cs_offsets_cs0;
+	}
+
+	/* Page / block sizes */
+	if (ctrl->nand_version >= 0x0701) {
+		/* >= v7.1 use nice power-of-2 values! */
+		ctrl->max_page_size = 16 * 1024;
+		ctrl->max_block_size = 2 * 1024 * 1024;
+	} else {
+		ctrl->page_sizes = page_sizes;
+		if (ctrl->nand_version >= 0x0600)
+			ctrl->block_sizes = block_sizes_v6;
+		else
+			ctrl->block_sizes = block_sizes_v4;
+
+		if (ctrl->nand_version < 0x0400) {
+			ctrl->max_page_size = 4096;
+			ctrl->max_block_size = 512 * 1024;
+		}
+	}
+
+	/* Maximum spare area sector size (per 512B) */
+	if (ctrl->nand_version >= 0x0600)
+		ctrl->max_oob = 64;
+	else if (ctrl->nand_version >= 0x0500)
+		ctrl->max_oob = 32;
+	else
+		ctrl->max_oob = 16;
+
+	/* v6.0 and newer (except v6.1) have prefetch support */
+	if (ctrl->nand_version >= 0x0600 && ctrl->nand_version != 0x0601)
+		ctrl->features |= BRCMNAND_HAS_PREFETCH;
+
+	/*
+	 * v6.x has cache mode, but it's implemented differently. Ignore it for
+	 * now.
+	 */
+	if (ctrl->nand_version >= 0x0700)
+		ctrl->features |= BRCMNAND_HAS_CACHE_MODE;
+
+	if (ctrl->nand_version >= 0x0500)
+		ctrl->features |= BRCMNAND_HAS_1K_SECTORS;
+
+	if (ctrl->nand_version >= 0x0700)
+		ctrl->features |= BRCMNAND_HAS_WP;
+	else if (of_property_read_bool(ctrl->dev->of_node, "brcm,nand-has-wp"))
+		ctrl->features |= BRCMNAND_HAS_WP;
+
+	return 0;
+}
+
+static inline u32 brcmnand_read_reg(struct brcmnand_controller *ctrl,
+		enum brcmnand_reg reg)
+{
+	u16 offs = ctrl->reg_offsets[reg];
+
+	if (offs)
+		return nand_readreg(ctrl, offs);
+	else
+		return 0;
+}
+
+static inline void brcmnand_write_reg(struct brcmnand_controller *ctrl,
+				      enum brcmnand_reg reg, u32 val)
+{
+	u16 offs = ctrl->reg_offsets[reg];
+
+	if (offs)
+		nand_writereg(ctrl, offs, val);
+}
+
+static inline void brcmnand_rmw_reg(struct brcmnand_controller *ctrl,
+				    enum brcmnand_reg reg, u32 mask, unsigned
+				    int shift, u32 val)
+{
+	u32 tmp = brcmnand_read_reg(ctrl, reg);
+
+	tmp &= ~mask;
+	tmp |= val << shift;
+	brcmnand_write_reg(ctrl, reg, tmp);
+}
+
+static inline u32 brcmnand_read_fc(struct brcmnand_controller *ctrl, int word)
+{
+	return __raw_readl(ctrl->nand_fc + word * 4);
+}
+
+static inline void brcmnand_write_fc(struct brcmnand_controller *ctrl,
+				     int word, u32 val)
+{
+	__raw_writel(val, ctrl->nand_fc + word * 4);
+}
+
+static inline u16 brcmnand_cs_offset(struct brcmnand_controller *ctrl, int cs,
+				     enum brcmnand_cs_reg reg)
+{
+	u16 offs_cs0 = ctrl->reg_offsets[BRCMNAND_CS0_BASE];
+	u16 offs_cs1 = ctrl->reg_offsets[BRCMNAND_CS1_BASE];
+	u8 cs_offs;
+
+	if (cs == 0 && ctrl->cs0_offsets)
+		cs_offs = ctrl->cs0_offsets[reg];
+	else
+		cs_offs = ctrl->cs_offsets[reg];
+
+	if (cs && offs_cs1)
+		return offs_cs1 + (cs - 1) * ctrl->reg_spacing + cs_offs;
+
+	return offs_cs0 + cs * ctrl->reg_spacing + cs_offs;
+}
+
+static inline u32 brcmnand_count_corrected(struct brcmnand_controller *ctrl)
+{
+	if (ctrl->nand_version < 0x0600)
+		return 1;
+	return brcmnand_read_reg(ctrl, BRCMNAND_CORR_COUNT);
+}
+
+static void brcmnand_wr_corr_thresh(struct brcmnand_host *host, u8 val)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	unsigned int shift = 0, bits;
+	enum brcmnand_reg reg = BRCMNAND_CORR_THRESHOLD;
+	int cs = host->cs;
+
+	if (ctrl->nand_version >= 0x0600)
+		bits = 6;
+	else if (ctrl->nand_version >= 0x0500)
+		bits = 5;
+	else
+		bits = 4;
+
+	if (ctrl->nand_version >= 0x0600) {
+		if (cs >= 5)
+			reg = BRCMNAND_CORR_THRESHOLD_EXT;
+		shift = (cs % 5) * bits;
+	}
+	brcmnand_rmw_reg(ctrl, reg, (bits - 1) << shift, shift, val);
+}
+
+static inline int brcmnand_cmd_shift(struct brcmnand_controller *ctrl)
+{
+	if (ctrl->nand_version < 0x0700)
+		return 24;
+	return 0;
+}
+
+/***********************************************************************
+ * NAND ACC CONTROL bitfield
+ *
+ * Some bits have remained constant throughout hardware revision, while
+ * others have shifted around.
+ ***********************************************************************/
+
+/* Constant for all versions (where supported) */
+enum {
+	/* See BRCMNAND_HAS_CACHE_MODE */
+	ACC_CONTROL_CACHE_MODE				= BIT(22),
+
+	/* See BRCMNAND_HAS_PREFETCH */
+	ACC_CONTROL_PREFETCH				= BIT(23),
+
+	ACC_CONTROL_PAGE_HIT				= BIT(24),
+	ACC_CONTROL_WR_PREEMPT				= BIT(25),
+	ACC_CONTROL_PARTIAL_PAGE			= BIT(26),
+	ACC_CONTROL_RD_ERASED				= BIT(27),
+	ACC_CONTROL_FAST_PGM_RDIN			= BIT(28),
+	ACC_CONTROL_WR_ECC				= BIT(30),
+	ACC_CONTROL_RD_ECC				= BIT(31),
+};
+
+static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl)
+{
+	if (ctrl->nand_version >= 0x0600)
+		return GENMASK(6, 0);
+	else
+		return GENMASK(5, 0);
+}
+
+#define NAND_ACC_CONTROL_ECC_SHIFT	16
+
+static inline u32 brcmnand_ecc_level_mask(struct brcmnand_controller *ctrl)
+{
+	u32 mask = (ctrl->nand_version >= 0x0600) ? 0x1f : 0x0f;
+
+	return mask << NAND_ACC_CONTROL_ECC_SHIFT;
+}
+
+static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u16 offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_ACC_CONTROL);
+	u32 acc_control = nand_readreg(ctrl, offs);
+	u32 ecc_flags = ACC_CONTROL_WR_ECC | ACC_CONTROL_RD_ECC;
+
+	if (en) {
+		acc_control |= ecc_flags; /* enable RD/WR ECC */
+		acc_control |= host->hwcfg.ecc_level
+			       << NAND_ACC_CONTROL_ECC_SHIFT;
+	} else {
+		acc_control &= ~ecc_flags; /* disable RD/WR ECC */
+		acc_control &= ~brcmnand_ecc_level_mask(ctrl);
+	}
+
+	nand_writereg(ctrl, offs, acc_control);
+}
+
+static inline int brcmnand_sector_1k_shift(struct brcmnand_controller *ctrl)
+{
+	if (ctrl->nand_version >= 0x0600)
+		return 7;
+	else if (ctrl->nand_version >= 0x0500)
+		return 6;
+	else
+		return -1;
+}
+
+static int brcmnand_get_sector_size_1k(struct brcmnand_host *host)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	int shift = brcmnand_sector_1k_shift(ctrl);
+	u16 acc_control_offs = brcmnand_cs_offset(ctrl, host->cs,
+						  BRCMNAND_CS_ACC_CONTROL);
+
+	if (shift < 0)
+		return 0;
+
+	return (nand_readreg(ctrl, acc_control_offs) >> shift) & 0x1;
+}
+
+static void brcmnand_set_sector_size_1k(struct brcmnand_host *host, int val)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	int shift = brcmnand_sector_1k_shift(ctrl);
+	u16 acc_control_offs = brcmnand_cs_offset(ctrl, host->cs,
+						  BRCMNAND_CS_ACC_CONTROL);
+	u32 tmp;
+
+	if (shift < 0)
+		return;
+
+	tmp = nand_readreg(ctrl, acc_control_offs);
+	tmp &= ~(1 << shift);
+	tmp |= (!!val) << shift;
+	nand_writereg(ctrl, acc_control_offs, tmp);
+}
+
+/***********************************************************************
+ * CS_NAND_SELECT
+ ***********************************************************************/
+
+enum {
+	CS_SELECT_NAND_WP			= BIT(29),
+	CS_SELECT_AUTO_DEVICE_ID_CFG		= BIT(30),
+};
+
+static inline void brcmnand_set_wp(struct brcmnand_controller *ctrl, bool en)
+{
+	u32 val = en ? CS_SELECT_NAND_WP : 0;
+
+	brcmnand_rmw_reg(ctrl, BRCMNAND_CS_SELECT, CS_SELECT_NAND_WP, 0, val);
+}
+
+/***********************************************************************
+ * Flash DMA
+ ***********************************************************************/
+
+enum flash_dma_reg {
+	FLASH_DMA_REVISION		= 0x00,
+	FLASH_DMA_FIRST_DESC		= 0x04,
+	FLASH_DMA_FIRST_DESC_EXT	= 0x08,
+	FLASH_DMA_CTRL			= 0x0c,
+	FLASH_DMA_MODE			= 0x10,
+	FLASH_DMA_STATUS		= 0x14,
+	FLASH_DMA_INTERRUPT_DESC	= 0x18,
+	FLASH_DMA_INTERRUPT_DESC_EXT	= 0x1c,
+	FLASH_DMA_ERROR_STATUS		= 0x20,
+	FLASH_DMA_CURRENT_DESC		= 0x24,
+	FLASH_DMA_CURRENT_DESC_EXT	= 0x28,
+};
+
+static inline bool has_flash_dma(struct brcmnand_controller *ctrl)
+{
+	return ctrl->flash_dma_base;
+}
+
+static inline bool flash_dma_buf_ok(const void *buf)
+{
+	return buf && !is_vmalloc_addr(buf) &&
+		likely(IS_ALIGNED((uintptr_t)buf, 4));
+}
+
+static inline void flash_dma_writel(struct brcmnand_controller *ctrl, u8 offs,
+				    u32 val)
+{
+	brcmnand_writel(val, ctrl->flash_dma_base + offs);
+}
+
+static inline u32 flash_dma_readl(struct brcmnand_controller *ctrl, u8 offs)
+{
+	return brcmnand_readl(ctrl->flash_dma_base + offs);
+}
+
+/* Low-level operation types: command, address, write, or read */
+enum brcmnand_llop_type {
+	LL_OP_CMD,
+	LL_OP_ADDR,
+	LL_OP_WR,
+	LL_OP_RD,
+};
+
+/***********************************************************************
+ * Internal support functions
+ ***********************************************************************/
+
+static inline bool is_hamming_ecc(struct brcmnand_cfg *cfg)
+{
+	return cfg->sector_size_1k == 0 && cfg->spare_area_size == 16 &&
+		cfg->ecc_level == 15;
+}
+
+/*
+ * Returns a nand_ecclayout strucutre for the given layout/configuration.
+ * Returns NULL on failure.
+ */
+static struct nand_ecclayout *brcmnand_create_layout(int ecc_level,
+						     struct brcmnand_host *host)
+{
+	struct brcmnand_cfg *cfg = &host->hwcfg;
+	int i, j;
+	struct nand_ecclayout *layout;
+	int req;
+	int sectors;
+	int sas;
+	int idx1, idx2;
+
+	layout = devm_kzalloc(&host->pdev->dev, sizeof(*layout), GFP_KERNEL);
+	if (!layout)
+		return NULL;
+
+	sectors = cfg->page_size / (512 << cfg->sector_size_1k);
+	sas = cfg->spare_area_size << cfg->sector_size_1k;
+
+	/* Hamming */
+	if (is_hamming_ecc(cfg)) {
+		for (i = 0, idx1 = 0, idx2 = 0; i < sectors; i++) {
+			/* First sector of each page may have BBI */
+			if (i == 0) {
+				layout->oobfree[idx2].offset = i * sas + 1;
+				/* Small-page NAND use byte 6 for BBI */
+				if (cfg->page_size == 512)
+					layout->oobfree[idx2].offset--;
+				layout->oobfree[idx2].length = 5;
+			} else {
+				layout->oobfree[idx2].offset = i * sas;
+				layout->oobfree[idx2].length = 6;
+			}
+			idx2++;
+			layout->eccpos[idx1++] = i * sas + 6;
+			layout->eccpos[idx1++] = i * sas + 7;
+			layout->eccpos[idx1++] = i * sas + 8;
+			layout->oobfree[idx2].offset = i * sas + 9;
+			layout->oobfree[idx2].length = 7;
+			idx2++;
+			/* Leave zero-terminated entry for OOBFREE */
+			if (idx1 >= MTD_MAX_ECCPOS_ENTRIES_LARGE ||
+				    idx2 >= MTD_MAX_OOBFREE_ENTRIES_LARGE - 1)
+				break;
+		}
+		goto out;
+	}
+
+	/*
+	 * CONTROLLER_VERSION:
+	 *   < v5.0: ECC_REQ = ceil(BCH_T * 13/8)
+	 *  >= v5.0: ECC_REQ = ceil(BCH_T * 14/8)
+	 * But we will just be conservative.
+	 */
+	req = DIV_ROUND_UP(ecc_level * 14, 8);
+	if (req >= sas) {
+		dev_err(&host->pdev->dev,
+			"error: ECC too large for OOB (ECC bytes %d, spare sector %d)\n",
+			req, sas);
+		return NULL;
+	}
+
+	layout->eccbytes = req * sectors;
+	for (i = 0, idx1 = 0, idx2 = 0; i < sectors; i++) {
+		for (j = sas - req; j < sas && idx1 <
+				MTD_MAX_ECCPOS_ENTRIES_LARGE; j++, idx1++)
+			layout->eccpos[idx1] = i * sas + j;
+
+		/* First sector of each page may have BBI */
+		if (i == 0) {
+			if (cfg->page_size == 512 && (sas - req >= 6)) {
+				/* Small-page NAND use byte 6 for BBI */
+				layout->oobfree[idx2].offset = 0;
+				layout->oobfree[idx2].length = 5;
+				idx2++;
+				if (sas - req > 6) {
+					layout->oobfree[idx2].offset = 6;
+					layout->oobfree[idx2].length =
+						sas - req - 6;
+					idx2++;
+				}
+			} else if (sas > req + 1) {
+				layout->oobfree[idx2].offset = i * sas + 1;
+				layout->oobfree[idx2].length = sas - req - 1;
+				idx2++;
+			}
+		} else if (sas > req) {
+			layout->oobfree[idx2].offset = i * sas;
+			layout->oobfree[idx2].length = sas - req;
+			idx2++;
+		}
+		/* Leave zero-terminated entry for OOBFREE */
+		if (idx1 >= MTD_MAX_ECCPOS_ENTRIES_LARGE ||
+				idx2 >= MTD_MAX_OOBFREE_ENTRIES_LARGE - 1)
+			break;
+	}
+out:
+	/* Sum available OOB */
+	for (i = 0; i < MTD_MAX_OOBFREE_ENTRIES_LARGE; i++)
+		layout->oobavail += layout->oobfree[i].length;
+	return layout;
+}
+
+static struct nand_ecclayout *brcmstb_choose_ecc_layout(
+		struct brcmnand_host *host)
+{
+	struct nand_ecclayout *layout;
+	struct brcmnand_cfg *p = &host->hwcfg;
+	unsigned int ecc_level = p->ecc_level;
+
+	if (p->sector_size_1k)
+		ecc_level <<= 1;
+
+	layout = brcmnand_create_layout(ecc_level, host);
+	if (!layout) {
+		dev_err(&host->pdev->dev,
+				"no proper ecc_layout for this NAND cfg\n");
+		return NULL;
+	}
+
+	return layout;
+}
+
+static void brcmnand_wp(struct mtd_info *mtd, int wp)
+{
+	struct nand_chip *chip = mtd->priv;
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+
+	if ((ctrl->features & BRCMNAND_HAS_WP) && wp_on == 1) {
+		static int old_wp = -1;
+
+		if (old_wp != wp) {
+			dev_dbg(ctrl->dev, "WP %s\n", wp ? "on" : "off");
+			old_wp = wp;
+		}
+		brcmnand_set_wp(ctrl, wp);
+	}
+}
+
+/* Helper functions for reading and writing OOB registers */
+static inline u8 oob_reg_read(struct brcmnand_controller *ctrl, u32 offs)
+{
+	u16 offset0, offset10, reg_offs;
+
+	offset0 = ctrl->reg_offsets[BRCMNAND_OOB_READ_BASE];
+	offset10 = ctrl->reg_offsets[BRCMNAND_OOB_READ_10_BASE];
+
+	if (offs >= ctrl->max_oob)
+		return 0x77;
+
+	if (offs >= 16 && offset10)
+		reg_offs = offset10 + ((offs - 0x10) & ~0x03);
+	else
+		reg_offs = offset0 + (offs & ~0x03);
+
+	return nand_readreg(ctrl, reg_offs) >> (24 - ((offs & 0x03) << 3));
+}
+
+static inline void oob_reg_write(struct brcmnand_controller *ctrl, u32 offs,
+				 u32 data)
+{
+	u16 offset0, offset10, reg_offs;
+
+	offset0 = ctrl->reg_offsets[BRCMNAND_OOB_WRITE_BASE];
+	offset10 = ctrl->reg_offsets[BRCMNAND_OOB_WRITE_10_BASE];
+
+	if (offs >= ctrl->max_oob)
+		return;
+
+	if (offs >= 16 && offset10)
+		reg_offs = offset10 + ((offs - 0x10) & ~0x03);
+	else
+		reg_offs = offset0 + (offs & ~0x03);
+
+	nand_writereg(ctrl, reg_offs, data);
+}
+
+/*
+ * read_oob_from_regs - read data from OOB registers
+ * @ctrl: NAND controller
+ * @i: sub-page sector index
+ * @oob: buffer to read to
+ * @sas: spare area sector size (i.e., OOB size per FLASH_CACHE)
+ * @sector_1k: 1 for 1KiB sectors, 0 for 512B, other values are illegal
+ */
+static int read_oob_from_regs(struct brcmnand_controller *ctrl, int i, u8 *oob,
+			      int sas, int sector_1k)
+{
+	int tbytes = sas << sector_1k;
+	int j;
+
+	/* Adjust OOB values for 1K sector size */
+	if (sector_1k && (i & 0x01))
+		tbytes = max(0, tbytes - (int)ctrl->max_oob);
+	tbytes = min_t(int, tbytes, ctrl->max_oob);
+
+	for (j = 0; j < tbytes; j++)
+		oob[j] = oob_reg_read(ctrl, j);
+	return tbytes;
+}
+
+/*
+ * write_oob_to_regs - write data to OOB registers
+ * @i: sub-page sector index
+ * @oob: buffer to write from
+ * @sas: spare area sector size (i.e., OOB size per FLASH_CACHE)
+ * @sector_1k: 1 for 1KiB sectors, 0 for 512B, other values are illegal
+ */
+static int write_oob_to_regs(struct brcmnand_controller *ctrl, int i,
+			     const u8 *oob, int sas, int sector_1k)
+{
+	int tbytes = sas << sector_1k;
+	int j;
+
+	/* Adjust OOB values for 1K sector size */
+	if (sector_1k && (i & 0x01))
+		tbytes = max(0, tbytes - (int)ctrl->max_oob);
+	tbytes = min_t(int, tbytes, ctrl->max_oob);
+
+	for (j = 0; j < tbytes; j += 4)
+		oob_reg_write(ctrl, j,
+				(oob[j + 0] << 24) |
+				(oob[j + 1] << 16) |
+				(oob[j + 2] <<  8) |
+				(oob[j + 3] <<  0));
+	return tbytes;
+}
+
+static irqreturn_t brcmnand_ctlrdy_irq(int irq, void *data)
+{
+	struct brcmnand_controller *ctrl = data;
+
+	/* Discard all NAND_CTLRDY interrupts during DMA */
+	if (ctrl->dma_pending)
+		return IRQ_HANDLED;
+
+	complete(&ctrl->done);
+	return IRQ_HANDLED;
+}
+
+/* Handle SoC-specific interrupt hardware */
+static irqreturn_t brcmnand_irq(int irq, void *data)
+{
+	struct brcmnand_controller *ctrl = data;
+
+	if (ctrl->soc->ctlrdy_ack(ctrl->soc))
+		return brcmnand_ctlrdy_irq(irq, data);
+
+	return IRQ_NONE;
+}
+
+static irqreturn_t brcmnand_dma_irq(int irq, void *data)
+{
+	struct brcmnand_controller *ctrl = data;
+
+	complete(&ctrl->dma_done);
+
+	return IRQ_HANDLED;
+}
+
+static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u32 intfc;
+
+	dev_dbg(ctrl->dev, "send native cmd %d addr_lo 0x%x\n", cmd,
+		brcmnand_read_reg(ctrl, BRCMNAND_CMD_ADDRESS));
+	BUG_ON(ctrl->cmd_pending != 0);
+	ctrl->cmd_pending = cmd;
+
+	intfc = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
+	BUG_ON(!(intfc & INTFC_CTLR_READY));
+
+	mb(); /* flush previous writes */
+	brcmnand_write_reg(ctrl, BRCMNAND_CMD_START,
+			   cmd << brcmnand_cmd_shift(ctrl));
+}
+
+/***********************************************************************
+ * NAND MTD API: read/program/erase
+ ***********************************************************************/
+
+static void brcmnand_cmd_ctrl(struct mtd_info *mtd, int dat,
+	unsigned int ctrl)
+{
+	/* intentionally left blank */
+}
+
+static int brcmnand_waitfunc(struct mtd_info *mtd, struct nand_chip *this)
+{
+	struct nand_chip *chip = mtd->priv;
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	unsigned long timeo = msecs_to_jiffies(100);
+
+	dev_dbg(ctrl->dev, "wait on native cmd %d\n", ctrl->cmd_pending);
+	if (ctrl->cmd_pending &&
+			wait_for_completion_timeout(&ctrl->done, timeo) <= 0) {
+		u32 cmd = brcmnand_read_reg(ctrl, BRCMNAND_CMD_START)
+					>> brcmnand_cmd_shift(ctrl);
+
+		dev_err_ratelimited(ctrl->dev,
+			"timeout waiting for command %#02x\n", cmd);
+		dev_err_ratelimited(ctrl->dev, "intfc status %08x\n",
+			brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS));
+	}
+	ctrl->cmd_pending = 0;
+	return brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS) &
+				 INTFC_FLASH_STATUS;
+}
+
+enum {
+	LLOP_RE				= BIT(16),
+	LLOP_WE				= BIT(17),
+	LLOP_ALE			= BIT(18),
+	LLOP_CLE			= BIT(19),
+	LLOP_RETURN_IDLE		= BIT(31),
+
+	LLOP_DATA_MASK			= GENMASK(15, 0),
+};
+
+static int brcmnand_low_level_op(struct brcmnand_host *host,
+				 enum brcmnand_llop_type type, u32 data,
+				 bool last_op)
+{
+	struct mtd_info *mtd = &host->mtd;
+	struct nand_chip *chip = &host->chip;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u32 tmp;
+
+	tmp = data & LLOP_DATA_MASK;
+	switch (type) {
+	case LL_OP_CMD:
+		tmp |= LLOP_WE | LLOP_CLE;
+		break;
+	case LL_OP_ADDR:
+		/* WE | ALE */
+		tmp |= LLOP_WE | LLOP_ALE;
+		break;
+	case LL_OP_WR:
+		/* WE */
+		tmp |= LLOP_WE;
+		break;
+	case LL_OP_RD:
+		/* RE */
+		tmp |= LLOP_RE;
+		break;
+	}
+	if (last_op)
+		/* RETURN_IDLE */
+		tmp |= LLOP_RETURN_IDLE;
+
+	dev_dbg(ctrl->dev, "ll_op cmd %#x\n", tmp);
+
+	brcmnand_write_reg(ctrl, BRCMNAND_LL_OP, tmp);
+	(void)brcmnand_read_reg(ctrl, BRCMNAND_LL_OP);
+
+	brcmnand_send_cmd(host, CMD_LOW_LEVEL_OP);
+	return brcmnand_waitfunc(mtd, chip);
+}
+
+static void brcmnand_cmdfunc(struct mtd_info *mtd, unsigned command,
+			     int column, int page_addr)
+{
+	struct nand_chip *chip = mtd->priv;
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u64 addr = (u64)page_addr << chip->page_shift;
+	int native_cmd = 0;
+
+	if (command == NAND_CMD_READID || command == NAND_CMD_PARAM ||
+			command == NAND_CMD_RNDOUT)
+		addr = (u64)column;
+	/* Avoid propagating a negative, don't-care address */
+	else if (page_addr < 0)
+		addr = 0;
+
+	dev_dbg(ctrl->dev, "cmd 0x%x addr 0x%llx\n", command,
+		(unsigned long long)addr);
+
+	host->last_cmd = command;
+	host->last_byte = 0;
+	host->last_addr = addr;
+
+	switch (command) {
+	case NAND_CMD_RESET:
+		native_cmd = CMD_FLASH_RESET;
+		break;
+	case NAND_CMD_STATUS:
+		native_cmd = CMD_STATUS_READ;
+		break;
+	case NAND_CMD_READID:
+		native_cmd = CMD_DEVICE_ID_READ;
+		break;
+	case NAND_CMD_READOOB:
+		native_cmd = CMD_SPARE_AREA_READ;
+		break;
+	case NAND_CMD_ERASE1:
+		native_cmd = CMD_BLOCK_ERASE;
+		brcmnand_wp(mtd, 0);
+		break;
+	case NAND_CMD_PARAM:
+		native_cmd = CMD_PARAMETER_READ;
+		break;
+	case NAND_CMD_SET_FEATURES:
+	case NAND_CMD_GET_FEATURES:
+		brcmnand_low_level_op(host, LL_OP_CMD, command, false);
+		brcmnand_low_level_op(host, LL_OP_ADDR, column, false);
+		break;
+	case NAND_CMD_RNDOUT:
+		native_cmd = CMD_PARAMETER_CHANGE_COL;
+		addr &= ~((u64)(FC_BYTES - 1));
+		/*
+		 * HW quirk: PARAMETER_CHANGE_COL requires SECTOR_SIZE_1K=0
+		 * NB: hwcfg.sector_size_1k may not be initialized yet
+		 */
+		if (brcmnand_get_sector_size_1k(host)) {
+			host->hwcfg.sector_size_1k =
+				brcmnand_get_sector_size_1k(host);
+			brcmnand_set_sector_size_1k(host, 0);
+		}
+		break;
+	}
+
+	if (!native_cmd)
+		return;
+
+	brcmnand_write_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS,
+		(host->cs << 16) | ((addr >> 32) & 0xffff));
+	(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS);
+	brcmnand_write_reg(ctrl, BRCMNAND_CMD_ADDRESS, lower_32_bits(addr));
+	(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_ADDRESS);
+
+	brcmnand_send_cmd(host, native_cmd);
+	brcmnand_waitfunc(mtd, chip);
+
+	if (native_cmd == CMD_PARAMETER_READ ||
+			native_cmd == CMD_PARAMETER_CHANGE_COL) {
+		int i;
+
+		brcmnand_soc_data_bus_prepare(ctrl->soc);
+
+		/*
+		 * Must cache the FLASH_CACHE now, since changes in
+		 * SECTOR_SIZE_1K may invalidate it
+		 */
+		for (i = 0; i < FC_WORDS; i++)
+			ctrl->flash_cache[i] = brcmnand_read_fc(ctrl, i);
+
+		brcmnand_soc_data_bus_unprepare(ctrl->soc);
+
+		/* Cleanup from HW quirk: restore SECTOR_SIZE_1K */
+		if (host->hwcfg.sector_size_1k)
+			brcmnand_set_sector_size_1k(host,
+						    host->hwcfg.sector_size_1k);
+	}
+
+	/* Re-enable protection is necessary only after erase */
+	if (command == NAND_CMD_ERASE1)
+		brcmnand_wp(mtd, 1);
+}
+
+static uint8_t brcmnand_read_byte(struct mtd_info *mtd)
+{
+	struct nand_chip *chip = mtd->priv;
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	uint8_t ret = 0;
+	int addr, offs;
+
+	switch (host->last_cmd) {
+	case NAND_CMD_READID:
+		if (host->last_byte < 4)
+			ret = brcmnand_read_reg(ctrl, BRCMNAND_ID) >>
+				(24 - (host->last_byte << 3));
+		else if (host->last_byte < 8)
+			ret = brcmnand_read_reg(ctrl, BRCMNAND_ID_EXT) >>
+				(56 - (host->last_byte << 3));
+		break;
+
+	case NAND_CMD_READOOB:
+		ret = oob_reg_read(ctrl, host->last_byte);
+		break;
+
+	case NAND_CMD_STATUS:
+		ret = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS) &
+					INTFC_FLASH_STATUS;
+		if (wp_on) /* hide WP status */
+			ret |= NAND_STATUS_WP;
+		break;
+
+	case NAND_CMD_PARAM:
+	case NAND_CMD_RNDOUT:
+		addr = host->last_addr + host->last_byte;
+		offs = addr & (FC_BYTES - 1);
+
+		/* At FC_BYTES boundary, switch to next column */
+		if (host->last_byte > 0 && offs == 0)
+			chip->cmdfunc(mtd, NAND_CMD_RNDOUT, addr, -1);
+
+		ret = ctrl->flash_cache[offs >> 2] >>
+					(24 - ((offs & 0x03) << 3));
+		break;
+	case NAND_CMD_GET_FEATURES:
+		if (host->last_byte >= ONFI_SUBFEATURE_PARAM_LEN) {
+			ret = 0;
+		} else {
+			bool last = host->last_byte ==
+				ONFI_SUBFEATURE_PARAM_LEN - 1;
+			brcmnand_low_level_op(host, LL_OP_RD, 0, last);
+			ret = brcmnand_read_reg(ctrl, BRCMNAND_LL_RDATA) & 0xff;
+		}
+	}
+
+	dev_dbg(ctrl->dev, "read byte = 0x%02x\n", ret);
+	host->last_byte++;
+
+	return ret;
+}
+
+static void brcmnand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++, buf++)
+		*buf = brcmnand_read_byte(mtd);
+}
+
+static void brcmnand_write_buf(struct mtd_info *mtd, const uint8_t *buf,
+				   int len)
+{
+	int i;
+	struct nand_chip *chip = mtd->priv;
+	struct brcmnand_host *host = chip->priv;
+
+	switch (host->last_cmd) {
+	case NAND_CMD_SET_FEATURES:
+		for (i = 0; i < len; i++)
+			brcmnand_low_level_op(host, LL_OP_WR, buf[i],
+						  (i + 1) == len);
+		break;
+	default:
+		BUG();
+		break;
+	}
+}
+
+/**
+ * Construct a FLASH_DMA descriptor as part of a linked list. You must know the
+ * following ahead of time:
+ *  - Is this descriptor the beginning or end of a linked list?
+ *  - What is the (DMA) address of the next descriptor in the linked list?
+ */
+static int brcmnand_fill_dma_desc(struct brcmnand_host *host,
+				  struct brcm_nand_dma_desc *desc, u64 addr,
+				  dma_addr_t buf, u32 len, u8 dma_cmd,
+				  bool begin, bool end,
+				  dma_addr_t next_desc)
+{
+	memset(desc, 0, sizeof(*desc));
+	/* Descriptors are written in native byte order (wordwise) */
+	desc->next_desc = lower_32_bits(next_desc);
+	desc->next_desc_ext = upper_32_bits(next_desc);
+	desc->cmd_irq = (dma_cmd << 24) |
+		(end ? (0x03 << 8) : 0) | /* IRQ | STOP */
+		(!!begin) | ((!!end) << 1); /* head, tail */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	desc->cmd_irq |= 0x01 << 12;
+#endif
+	desc->dram_addr = lower_32_bits(buf);
+	desc->dram_addr_ext = upper_32_bits(buf);
+	desc->tfr_len = len;
+	desc->total_len = len;
+	desc->flash_addr = lower_32_bits(addr);
+	desc->flash_addr_ext = upper_32_bits(addr);
+	desc->cs = host->cs;
+	desc->status_valid = 0x01;
+	return 0;
+}
+
+/**
+ * Kick the FLASH_DMA engine, with a given DMA descriptor
+ */
+static void brcmnand_dma_run(struct brcmnand_host *host, dma_addr_t desc)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	unsigned long timeo = msecs_to_jiffies(100);
+
+	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC, lower_32_bits(desc));
+	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC);
+	flash_dma_writel(ctrl, FLASH_DMA_FIRST_DESC_EXT, upper_32_bits(desc));
+	(void)flash_dma_readl(ctrl, FLASH_DMA_FIRST_DESC_EXT);
+
+	/* Start FLASH_DMA engine */
+	ctrl->dma_pending = true;
+	mb(); /* flush previous writes */
+	flash_dma_writel(ctrl, FLASH_DMA_CTRL, 0x03); /* wake | run */
+
+	if (wait_for_completion_timeout(&ctrl->dma_done, timeo) <= 0) {
+		dev_err(ctrl->dev,
+				"timeout waiting for DMA; status %#x, error status %#x\n",
+				flash_dma_readl(ctrl, FLASH_DMA_STATUS),
+				flash_dma_readl(ctrl, FLASH_DMA_ERROR_STATUS));
+	}
+	ctrl->dma_pending = false;
+	flash_dma_writel(ctrl, FLASH_DMA_CTRL, 0); /* force stop */
+}
+
+static int brcmnand_dma_trans(struct brcmnand_host *host, u64 addr, u32 *buf,
+			      u32 len, u8 dma_cmd)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	dma_addr_t buf_pa;
+	int dir = dma_cmd == CMD_PAGE_READ ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+	buf_pa = dma_map_single(ctrl->dev, buf, len, dir);
+	if (dma_mapping_error(ctrl->dev, buf_pa)) {
+		dev_err(ctrl->dev, "unable to map buffer for DMA\n");
+		return -ENOMEM;
+	}
+
+	brcmnand_fill_dma_desc(host, ctrl->dma_desc, addr, buf_pa, len,
+				   dma_cmd, true, true, 0);
+
+	brcmnand_dma_run(host, ctrl->dma_pa);
+
+	dma_unmap_single(ctrl->dev, buf_pa, len, dir);
+
+	if (ctrl->dma_desc->status_valid & FLASH_DMA_ECC_ERROR)
+		return -EBADMSG;
+	else if (ctrl->dma_desc->status_valid & FLASH_DMA_CORR_ERROR)
+		return -EUCLEAN;
+
+	return 0;
+}
+
+/*
+ * Assumes proper CS is already set
+ */
+static int brcmnand_read_by_pio(struct mtd_info *mtd, struct nand_chip *chip,
+				u64 addr, unsigned int trans, u32 *buf,
+				u8 *oob, u64 *err_addr)
+{
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	int i, j, ret = 0;
+
+	/* Clear error addresses */
+	brcmnand_write_reg(ctrl, BRCMNAND_UNCORR_ADDR, 0);
+	brcmnand_write_reg(ctrl, BRCMNAND_CORR_ADDR, 0);
+
+	brcmnand_write_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS,
+			(host->cs << 16) | ((addr >> 32) & 0xffff));
+	(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS);
+
+	for (i = 0; i < trans; i++, addr += FC_BYTES) {
+		brcmnand_write_reg(ctrl, BRCMNAND_CMD_ADDRESS,
+				   lower_32_bits(addr));
+		(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_ADDRESS);
+		/* SPARE_AREA_READ does not use ECC, so just use PAGE_READ */
+		brcmnand_send_cmd(host, CMD_PAGE_READ);
+		brcmnand_waitfunc(mtd, chip);
+
+		if (likely(buf)) {
+			brcmnand_soc_data_bus_prepare(ctrl->soc);
+
+			for (j = 0; j < FC_WORDS; j++, buf++)
+				*buf = brcmnand_read_fc(ctrl, j);
+
+			brcmnand_soc_data_bus_unprepare(ctrl->soc);
+		}
+
+		if (oob)
+			oob += read_oob_from_regs(ctrl, i, oob,
+					mtd->oobsize / trans,
+					host->hwcfg.sector_size_1k);
+
+		if (!ret) {
+			*err_addr = brcmnand_read_reg(ctrl,
+					BRCMNAND_UNCORR_ADDR) |
+				((u64)(brcmnand_read_reg(ctrl,
+						BRCMNAND_UNCORR_EXT_ADDR)
+					& 0xffff) << 32);
+			if (*err_addr)
+				ret = -EBADMSG;
+		}
+
+		if (!ret) {
+			*err_addr = brcmnand_read_reg(ctrl,
+					BRCMNAND_CORR_ADDR) |
+				((u64)(brcmnand_read_reg(ctrl,
+						BRCMNAND_CORR_EXT_ADDR)
+					& 0xffff) << 32);
+			if (*err_addr)
+				ret = -EUCLEAN;
+		}
+	}
+
+	return ret;
+}
+
+static int brcmnand_read(struct mtd_info *mtd, struct nand_chip *chip,
+			 u64 addr, unsigned int trans, u32 *buf, u8 *oob)
+{
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u64 err_addr = 0;
+	int err;
+
+	dev_dbg(ctrl->dev, "read %llx -> %p\n", (unsigned long long)addr, buf);
+
+	brcmnand_write_reg(ctrl, BRCMNAND_UNCORR_COUNT, 0);
+
+	if (has_flash_dma(ctrl) && !oob && flash_dma_buf_ok(buf)) {
+		err = brcmnand_dma_trans(host, addr, buf, trans * FC_BYTES,
+					     CMD_PAGE_READ);
+		if (err) {
+			if (mtd_is_bitflip_or_eccerr(err))
+				err_addr = addr;
+			else
+				return -EIO;
+		}
+	} else {
+		if (oob)
+			memset(oob, 0x99, mtd->oobsize);
+
+		err = brcmnand_read_by_pio(mtd, chip, addr, trans, buf,
+					       oob, &err_addr);
+	}
+
+	if (mtd_is_eccerr(err)) {
+		dev_dbg(ctrl->dev, "uncorrectable error at 0x%llx\n",
+			(unsigned long long)err_addr);
+		mtd->ecc_stats.failed++;
+		/* NAND layer expects zero on ECC errors */
+		return 0;
+	}
+
+	if (mtd_is_bitflip(err)) {
+		unsigned int corrected = brcmnand_count_corrected(ctrl);
+
+		dev_dbg(ctrl->dev, "corrected error at 0x%llx\n",
+			(unsigned long long)err_addr);
+		mtd->ecc_stats.corrected += corrected;
+		/* Always exceed the software-imposed threshold */
+		return max(mtd->bitflip_threshold, corrected);
+	}
+
+	return 0;
+}
+
+static int brcmnand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
+			      uint8_t *buf, int oob_required, int page)
+{
+	struct brcmnand_host *host = chip->priv;
+	u8 *oob = oob_required ? (u8 *)chip->oob_poi : NULL;
+
+	return brcmnand_read(mtd, chip, host->last_addr,
+			mtd->writesize >> FC_SHIFT, (u32 *)buf, oob);
+}
+
+static int brcmnand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				  uint8_t *buf, int oob_required, int page)
+{
+	struct brcmnand_host *host = chip->priv;
+	u8 *oob = oob_required ? (u8 *)chip->oob_poi : NULL;
+	int ret;
+
+	brcmnand_set_ecc_enabled(host, 0);
+	ret = brcmnand_read(mtd, chip, host->last_addr,
+			mtd->writesize >> FC_SHIFT, (u32 *)buf, oob);
+	brcmnand_set_ecc_enabled(host, 1);
+	return ret;
+}
+
+static int brcmnand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			     int page)
+{
+	return brcmnand_read(mtd, chip, (u64)page << chip->page_shift,
+			mtd->writesize >> FC_SHIFT,
+			NULL, (u8 *)chip->oob_poi);
+}
+
+static int brcmnand_read_oob_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				 int page)
+{
+	struct brcmnand_host *host = chip->priv;
+
+	brcmnand_set_ecc_enabled(host, 0);
+	brcmnand_read(mtd, chip, (u64)page << chip->page_shift,
+		mtd->writesize >> FC_SHIFT,
+		NULL, (u8 *)chip->oob_poi);
+	brcmnand_set_ecc_enabled(host, 1);
+	return 0;
+}
+
+static int brcmnand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				 uint32_t data_offs, uint32_t readlen,
+				 uint8_t *bufpoi, int page)
+{
+	struct brcmnand_host *host = chip->priv;
+
+	return brcmnand_read(mtd, chip, host->last_addr + data_offs,
+			readlen >> FC_SHIFT, (u32 *)bufpoi, NULL);
+}
+
+static int brcmnand_write(struct mtd_info *mtd, struct nand_chip *chip,
+			  u64 addr, const u32 *buf, u8 *oob)
+{
+	struct brcmnand_host *host = chip->priv;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	unsigned int i, j, trans = mtd->writesize >> FC_SHIFT;
+	int status, ret = 0;
+
+	dev_dbg(ctrl->dev, "write %llx <- %p\n", (unsigned long long)addr, buf);
+
+	if (unlikely((u32)buf & 0x03)) {
+		dev_warn(ctrl->dev, "unaligned buffer: %p\n", buf);
+		buf = (u32 *)((u32)buf & ~0x03);
+	}
+
+	brcmnand_wp(mtd, 0);
+
+	for (i = 0; i < ctrl->max_oob; i += 4)
+		oob_reg_write(ctrl, i, 0xffffffff);
+
+	if (has_flash_dma(ctrl) && !oob && flash_dma_buf_ok(buf)) {
+		if (brcmnand_dma_trans(host, addr, (u32 *)buf,
+					mtd->writesize, CMD_PROGRAM_PAGE))
+			ret = -EIO;
+		goto out;
+	}
+
+	brcmnand_write_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS,
+			(host->cs << 16) | ((addr >> 32) & 0xffff));
+	(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_EXT_ADDRESS);
+
+	for (i = 0; i < trans; i++, addr += FC_BYTES) {
+		/* full address MUST be set before populating FC */
+		brcmnand_write_reg(ctrl, BRCMNAND_CMD_ADDRESS,
+				   lower_32_bits(addr));
+		(void)brcmnand_read_reg(ctrl, BRCMNAND_CMD_ADDRESS);
+
+		if (buf) {
+			brcmnand_soc_data_bus_prepare(ctrl->soc);
+
+			for (j = 0; j < FC_WORDS; j++, buf++)
+				brcmnand_write_fc(ctrl, j, *buf);
+
+			brcmnand_soc_data_bus_unprepare(ctrl->soc);
+		} else if (oob) {
+			for (j = 0; j < FC_WORDS; j++)
+				brcmnand_write_fc(ctrl, j, 0xffffffff);
+		}
+
+		if (oob) {
+			oob += write_oob_to_regs(ctrl, i, oob,
+					mtd->oobsize / trans,
+					host->hwcfg.sector_size_1k);
+		}
+
+		/* we cannot use SPARE_AREA_PROGRAM when PARTIAL_PAGE_EN=0 */
+		brcmnand_send_cmd(host, CMD_PROGRAM_PAGE);
+		status = brcmnand_waitfunc(mtd, chip);
+
+		if (status & NAND_STATUS_FAIL) {
+			dev_info(ctrl->dev, "program failed at %llx\n",
+				(unsigned long long)addr);
+			ret = -EIO;
+			goto out;
+		}
+	}
+out:
+	brcmnand_wp(mtd, 1);
+	return ret;
+}
+
+static int brcmnand_write_page(struct mtd_info *mtd, struct nand_chip *chip,
+			       const uint8_t *buf, int oob_required)
+{
+	struct brcmnand_host *host = chip->priv;
+	void *oob = oob_required ? chip->oob_poi : NULL;
+
+	brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
+	return 0;
+}
+
+static int brcmnand_write_page_raw(struct mtd_info *mtd,
+				   struct nand_chip *chip, const uint8_t *buf,
+				   int oob_required)
+{
+	struct brcmnand_host *host = chip->priv;
+	void *oob = oob_required ? chip->oob_poi : NULL;
+
+	brcmnand_set_ecc_enabled(host, 0);
+	brcmnand_write(mtd, chip, host->last_addr, (const u32 *)buf, oob);
+	brcmnand_set_ecc_enabled(host, 1);
+	return 0;
+}
+
+static int brcmnand_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+				  int page)
+{
+	return brcmnand_write(mtd, chip, (u64)page << chip->page_shift,
+				  NULL, chip->oob_poi);
+}
+
+static int brcmnand_write_oob_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				  int page)
+{
+	struct brcmnand_host *host = chip->priv;
+	int ret;
+
+	brcmnand_set_ecc_enabled(host, 0);
+	ret = brcmnand_write(mtd, chip, (u64)page << chip->page_shift, NULL,
+				 (u8 *)chip->oob_poi);
+	brcmnand_set_ecc_enabled(host, 1);
+
+	return ret;
+}
+
+/***********************************************************************
+ * Per-CS setup (1 NAND device)
+ ***********************************************************************/
+
+static int brcmnand_set_cfg(struct brcmnand_host *host,
+			    struct brcmnand_cfg *cfg)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	struct nand_chip *chip = &host->chip;
+	u16 cfg_offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_CFG);
+	u16 cfg_ext_offs = brcmnand_cs_offset(ctrl, host->cs,
+			BRCMNAND_CS_CFG_EXT);
+	u16 acc_control_offs = brcmnand_cs_offset(ctrl, host->cs,
+			BRCMNAND_CS_ACC_CONTROL);
+	u8 block_size = 0, page_size = 0, device_size = 0;
+	u32 tmp;
+
+	if (ctrl->block_sizes) {
+		int i, found;
+
+		for (i = 0, found = 0; ctrl->block_sizes[i]; i++)
+			if (ctrl->block_sizes[i] * 1024 == cfg->block_size) {
+				block_size = i;
+				found = 1;
+			}
+		if (!found) {
+			dev_warn(ctrl->dev, "invalid block size %u\n",
+					cfg->block_size);
+			return -EINVAL;
+		}
+	} else {
+		block_size = ffs(cfg->block_size) - ffs(BRCMNAND_MIN_BLOCKSIZE);
+	}
+
+	if (cfg->block_size < BRCMNAND_MIN_BLOCKSIZE || (ctrl->max_block_size &&
+				cfg->block_size > ctrl->max_block_size)) {
+		dev_warn(ctrl->dev, "invalid block size %u\n",
+				cfg->block_size);
+		block_size = 0;
+	}
+
+	if (ctrl->page_sizes) {
+		int i, found;
+
+		for (i = 0, found = 0; ctrl->page_sizes[i]; i++)
+			if (ctrl->page_sizes[i] == cfg->page_size) {
+				page_size = i;
+				found = 1;
+			}
+		if (!found) {
+			dev_warn(ctrl->dev, "invalid page size %u\n",
+					cfg->page_size);
+			return -EINVAL;
+		}
+	} else {
+		page_size = ffs(cfg->page_size) - ffs(BRCMNAND_MIN_PAGESIZE);
+	}
+
+	if (cfg->page_size < BRCMNAND_MIN_PAGESIZE || (ctrl->max_page_size &&
+				cfg->page_size > ctrl->max_page_size)) {
+		dev_warn(ctrl->dev, "invalid page size %u\n", cfg->page_size);
+		return -EINVAL;
+	}
+
+	if (fls64(cfg->device_size) < fls64(BRCMNAND_MIN_DEVSIZE)) {
+		dev_warn(ctrl->dev, "invalid device size 0x%llx\n",
+			(unsigned long long)cfg->device_size);
+		return -EINVAL;
+	}
+	device_size = fls64(cfg->device_size) - fls64(BRCMNAND_MIN_DEVSIZE);
+
+	tmp = (cfg->blk_adr_bytes << 8) |
+		(cfg->col_adr_bytes << 12) |
+		(cfg->ful_adr_bytes << 16) |
+		(!!(cfg->device_width == 16) << 23) |
+		(device_size << 24);
+	if (cfg_offs == cfg_ext_offs) {
+		tmp |= (page_size << 20) | (block_size << 28);
+		nand_writereg(ctrl, cfg_offs, tmp);
+	} else {
+		nand_writereg(ctrl, cfg_offs, tmp);
+		tmp = page_size | (block_size << 4);
+		nand_writereg(ctrl, cfg_ext_offs, tmp);
+	}
+
+	tmp = nand_readreg(ctrl, acc_control_offs);
+	tmp &= ~brcmnand_ecc_level_mask(ctrl);
+	tmp |= cfg->ecc_level << NAND_ACC_CONTROL_ECC_SHIFT;
+	tmp &= ~brcmnand_spare_area_mask(ctrl);
+	tmp |= cfg->spare_area_size;
+	nand_writereg(ctrl, acc_control_offs, tmp);
+
+	brcmnand_set_sector_size_1k(host, cfg->sector_size_1k);
+
+	/* threshold = ceil(BCH-level * 0.75) */
+	brcmnand_wr_corr_thresh(host, DIV_ROUND_UP(chip->ecc.strength * 3, 4));
+
+	return 0;
+}
+
+static void brcmnand_print_cfg(char *buf, struct brcmnand_cfg *cfg)
+{
+	buf += sprintf(buf,
+		"%lluMiB total, %uKiB blocks, %u%s pages, %uB OOB, %u-bit",
+		(unsigned long long)cfg->device_size >> 20,
+		cfg->block_size >> 10,
+		cfg->page_size >= 1024 ? cfg->page_size >> 10 : cfg->page_size,
+		cfg->page_size >= 1024 ? "KiB" : "B",
+		cfg->spare_area_size, cfg->device_width);
+
+	/* Account for Hamming ECC and for BCH 512B vs 1KiB sectors */
+	if (is_hamming_ecc(cfg))
+		sprintf(buf, ", Hamming ECC");
+	else if (cfg->sector_size_1k)
+		sprintf(buf, ", BCH-%u (1KiB sector)", cfg->ecc_level << 1);
+	else
+		sprintf(buf, ", BCH-%u", cfg->ecc_level);
+}
+
+/*
+ * Minimum number of bytes to address a page. Calculated as:
+ *     roundup(log2(size / page-size) / 8)
+ *
+ * NB: the following does not "round up" for non-power-of-2 'size'; but this is
+ *     OK because many other things will break if 'size' is irregular...
+ */
+static inline int get_blk_adr_bytes(u64 size, u32 writesize)
+{
+	return ALIGN(ilog2(size) - ilog2(writesize), 8) >> 3;
+}
+
+static int brcmnand_setup_dev(struct brcmnand_host *host)
+{
+	struct mtd_info *mtd = &host->mtd;
+	struct nand_chip *chip = &host->chip;
+	struct brcmnand_controller *ctrl = host->ctrl;
+	struct brcmnand_cfg *cfg = &host->hwcfg;
+	char msg[128];
+	u32 offs, tmp, oob_sector;
+	int ret;
+
+	memset(cfg, 0, sizeof(*cfg));
+
+	ret = of_property_read_u32(chip->dn, "brcm,nand-oob-sector-size",
+				   &oob_sector);
+	if (ret) {
+		/* Use detected size */
+		cfg->spare_area_size = mtd->oobsize /
+					(mtd->writesize >> FC_SHIFT);
+	} else {
+		cfg->spare_area_size = oob_sector;
+	}
+	if (cfg->spare_area_size > ctrl->max_oob)
+		cfg->spare_area_size = ctrl->max_oob;
+	/*
+	 * Set oobsize to be consistent with controller's spare_area_size, as
+	 * the rest is inaccessible.
+	 */
+	mtd->oobsize = cfg->spare_area_size * (mtd->writesize >> FC_SHIFT);
+
+	cfg->device_size = mtd->size;
+	cfg->block_size = mtd->erasesize;
+	cfg->page_size = mtd->writesize;
+	cfg->device_width = (chip->options & NAND_BUSWIDTH_16) ? 16 : 8;
+	cfg->col_adr_bytes = 2;
+	cfg->blk_adr_bytes = get_blk_adr_bytes(mtd->size, mtd->writesize);
+
+	switch (chip->ecc.size) {
+	case 512:
+		if (chip->ecc.strength == 1) /* Hamming */
+			cfg->ecc_level = 15;
+		else
+			cfg->ecc_level = chip->ecc.strength;
+		cfg->sector_size_1k = 0;
+		break;
+	case 1024:
+		if (!(ctrl->features & BRCMNAND_HAS_1K_SECTORS)) {
+			dev_err(ctrl->dev, "1KB sectors not supported\n");
+			return -EINVAL;
+		}
+		if (chip->ecc.strength & 0x1) {
+			dev_err(ctrl->dev,
+				"odd ECC not supported with 1KB sectors\n");
+			return -EINVAL;
+		}
+
+		cfg->ecc_level = chip->ecc.strength >> 1;
+		cfg->sector_size_1k = 1;
+		break;
+	default:
+		dev_err(ctrl->dev, "unsupported ECC size: %d\n",
+			chip->ecc.size);
+		return -EINVAL;
+	}
+
+	cfg->ful_adr_bytes = cfg->blk_adr_bytes;
+	if (mtd->writesize > 512)
+		cfg->ful_adr_bytes += cfg->col_adr_bytes;
+	else
+		cfg->ful_adr_bytes += 1;
+
+	ret = brcmnand_set_cfg(host, cfg);
+	if (ret)
+		return ret;
+
+	brcmnand_set_ecc_enabled(host, 1);
+
+	brcmnand_print_cfg(msg, cfg);
+	dev_info(ctrl->dev, "detected %s\n", msg);
+
+	/* Configure ACC_CONTROL */
+	offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_ACC_CONTROL);
+	tmp = nand_readreg(ctrl, offs);
+	tmp &= ~ACC_CONTROL_PARTIAL_PAGE;
+	tmp &= ~ACC_CONTROL_RD_ERASED;
+	tmp &= ~ACC_CONTROL_FAST_PGM_RDIN;
+	if (ctrl->features & BRCMNAND_HAS_PREFETCH) {
+		/*
+		 * FIXME: Flash DMA + prefetch may see spurious erased-page ECC
+		 * errors
+		 */
+		if (has_flash_dma(ctrl))
+			tmp &= ~ACC_CONTROL_PREFETCH;
+		else
+			tmp |= ACC_CONTROL_PREFETCH;
+	}
+	nand_writereg(ctrl, offs, tmp);
+
+	return 0;
+}
+
+static int brcmnand_init_cs(struct brcmnand_host *host)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	struct device_node *dn = host->of_node;
+	struct platform_device *pdev = host->pdev;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int ret;
+	struct mtd_part_parser_data ppdata = { .of_node = dn };
+
+	ret = of_property_read_u32(dn, "reg", &host->cs);
+	if (ret) {
+		dev_err(&pdev->dev, "can't get chip-select\n");
+		return -ENXIO;
+	}
+
+	mtd = &host->mtd;
+	chip = &host->chip;
+
+	chip->dn = dn;
+	chip->priv = host;
+	mtd->priv = chip;
+	mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "brcmnand.%d",
+				   host->cs);
+	mtd->owner = THIS_MODULE;
+	mtd->dev.parent = &pdev->dev;
+
+	chip->IO_ADDR_R = (void __iomem *)0xdeadbeef;
+	chip->IO_ADDR_W = (void __iomem *)0xdeadbeef;
+
+	chip->cmd_ctrl = brcmnand_cmd_ctrl;
+	chip->cmdfunc = brcmnand_cmdfunc;
+	chip->waitfunc = brcmnand_waitfunc;
+	chip->read_byte = brcmnand_read_byte;
+	chip->read_buf = brcmnand_read_buf;
+	chip->write_buf = brcmnand_write_buf;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.read_page = brcmnand_read_page;
+	chip->ecc.read_subpage = brcmnand_read_subpage;
+	chip->ecc.write_page = brcmnand_write_page;
+	chip->ecc.read_page_raw = brcmnand_read_page_raw;
+	chip->ecc.write_page_raw = brcmnand_write_page_raw;
+	chip->ecc.write_oob_raw = brcmnand_write_oob_raw;
+	chip->ecc.read_oob_raw = brcmnand_read_oob_raw;
+	chip->ecc.read_oob = brcmnand_read_oob;
+	chip->ecc.write_oob = brcmnand_write_oob;
+
+	chip->controller = &ctrl->controller;
+
+	if (nand_scan_ident(mtd, 1, NULL))
+		return -ENXIO;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+	/*
+	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
+	 * to/from, and have nand_base pass us a bounce buffer instead, as
+	 * needed.
+	 */
+	chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+	if (of_get_nand_on_flash_bbt(dn))
+		chip->bbt_options |= NAND_BBT_USE_FLASH | NAND_BBT_NO_OOB;
+
+	if (brcmnand_setup_dev(host))
+		return -ENXIO;
+
+	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
+	/* only use our internal HW threshold */
+	mtd->bitflip_threshold = 1;
+
+	chip->ecc.layout = brcmstb_choose_ecc_layout(host);
+	if (!chip->ecc.layout)
+		return -ENXIO;
+
+	if (nand_scan_tail(mtd))
+		return -ENXIO;
+
+	return mtd_device_parse_register(mtd, NULL, &ppdata, NULL, 0);
+}
+
+static void brcmnand_save_restore_cs_config(struct brcmnand_host *host,
+					    int restore)
+{
+	struct brcmnand_controller *ctrl = host->ctrl;
+	u16 cfg_offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_CFG);
+	u16 cfg_ext_offs = brcmnand_cs_offset(ctrl, host->cs,
+			BRCMNAND_CS_CFG_EXT);
+	u16 acc_control_offs = brcmnand_cs_offset(ctrl, host->cs,
+			BRCMNAND_CS_ACC_CONTROL);
+	u16 t1_offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_TIMING1);
+	u16 t2_offs = brcmnand_cs_offset(ctrl, host->cs, BRCMNAND_CS_TIMING2);
+
+	if (restore) {
+		nand_writereg(ctrl, cfg_offs, host->hwcfg.config);
+		if (cfg_offs != cfg_ext_offs)
+			nand_writereg(ctrl, cfg_ext_offs,
+				      host->hwcfg.config_ext);
+		nand_writereg(ctrl, acc_control_offs, host->hwcfg.acc_control);
+		nand_writereg(ctrl, t1_offs, host->hwcfg.timing_1);
+		nand_writereg(ctrl, t2_offs, host->hwcfg.timing_2);
+	} else {
+		host->hwcfg.config = nand_readreg(ctrl, cfg_offs);
+		if (cfg_offs != cfg_ext_offs)
+			host->hwcfg.config_ext =
+				nand_readreg(ctrl, cfg_ext_offs);
+		host->hwcfg.acc_control = nand_readreg(ctrl, acc_control_offs);
+		host->hwcfg.timing_1 = nand_readreg(ctrl, t1_offs);
+		host->hwcfg.timing_2 = nand_readreg(ctrl, t2_offs);
+	}
+}
+
+static int brcmnand_suspend(struct device *dev)
+{
+	struct brcmnand_controller *ctrl = dev_get_drvdata(dev);
+	struct brcmnand_host *host;
+
+	list_for_each_entry(host, &ctrl->host_list, node)
+		brcmnand_save_restore_cs_config(host, 0);
+
+	ctrl->nand_cs_nand_select = brcmnand_read_reg(ctrl, BRCMNAND_CS_SELECT);
+	ctrl->nand_cs_nand_xor = brcmnand_read_reg(ctrl, BRCMNAND_CS_XOR);
+	ctrl->corr_stat_threshold =
+		brcmnand_read_reg(ctrl, BRCMNAND_CORR_THRESHOLD);
+
+	if (has_flash_dma(ctrl))
+		ctrl->flash_dma_mode = flash_dma_readl(ctrl, FLASH_DMA_MODE);
+
+	return 0;
+}
+
+static int brcmnand_resume(struct device *dev)
+{
+	struct brcmnand_controller *ctrl = dev_get_drvdata(dev);
+	struct brcmnand_host *host;
+
+	if (has_flash_dma(ctrl)) {
+		flash_dma_writel(ctrl, FLASH_DMA_MODE, ctrl->flash_dma_mode);
+		flash_dma_writel(ctrl, FLASH_DMA_ERROR_STATUS, 0);
+	}
+
+	brcmnand_write_reg(ctrl, BRCMNAND_CS_SELECT, ctrl->nand_cs_nand_select);
+	brcmnand_write_reg(ctrl, BRCMNAND_CS_XOR, ctrl->nand_cs_nand_xor);
+	brcmnand_write_reg(ctrl, BRCMNAND_CORR_THRESHOLD,
+			ctrl->corr_stat_threshold);
+	if (ctrl->soc) {
+		/* Clear/re-enable interrupt */
+		ctrl->soc->ctlrdy_ack(ctrl->soc);
+		ctrl->soc->ctlrdy_set_enabled(ctrl->soc, true);
+	}
+
+	list_for_each_entry(host, &ctrl->host_list, node) {
+		struct mtd_info *mtd = &host->mtd;
+		struct nand_chip *chip = mtd->priv;
+
+		brcmnand_save_restore_cs_config(host, 1);
+
+		/* Reset the chip, required by some chips after power-up */
+		chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+	}
+
+	return 0;
+}
+
+const struct dev_pm_ops brcmnand_pm_ops = {
+	.suspend		= brcmnand_suspend,
+	.resume			= brcmnand_resume,
+};
+EXPORT_SYMBOL_GPL(brcmnand_pm_ops);
+
+static const struct of_device_id brcmnand_of_match[] = {
+	{ .compatible = "brcm,brcmnand-v4.0" },
+	{ .compatible = "brcm,brcmnand-v5.0" },
+	{ .compatible = "brcm,brcmnand-v6.0" },
+	{ .compatible = "brcm,brcmnand-v6.1" },
+	{ .compatible = "brcm,brcmnand-v7.0" },
+	{ .compatible = "brcm,brcmnand-v7.1" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, brcmnand_of_match);
+
+/***********************************************************************
+ * Platform driver setup (per controller)
+ ***********************************************************************/
+
+int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *dn = dev->of_node, *child;
+	struct brcmnand_controller *ctrl;
+	struct resource *res;
+	int ret;
+
+	/* We only support device-tree instantiation */
+	if (!dn)
+		return -ENODEV;
+
+	if (!of_match_node(brcmnand_of_match, dn))
+		return -ENODEV;
+
+	ctrl = devm_kzalloc(dev, sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, ctrl);
+	ctrl->dev = dev;
+
+	init_completion(&ctrl->done);
+	init_completion(&ctrl->dma_done);
+	spin_lock_init(&ctrl->controller.lock);
+	init_waitqueue_head(&ctrl->controller.wq);
+	INIT_LIST_HEAD(&ctrl->host_list);
+
+	/* NAND register range */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctrl->nand_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ctrl->nand_base))
+		return PTR_ERR(ctrl->nand_base);
+
+	/* Initialize NAND revision */
+	ret = brcmnand_revision_init(ctrl);
+	if (ret)
+		return ret;
+
+	/*
+	 * Most chips have this cache at a fixed offset within 'nand' block.
+	 * Some must specify this region separately.
+	 */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand-cache");
+	if (res) {
+		ctrl->nand_fc = devm_ioremap_resource(dev, res);
+		if (IS_ERR(ctrl->nand_fc))
+			return PTR_ERR(ctrl->nand_fc);
+	} else {
+		ctrl->nand_fc = ctrl->nand_base +
+				ctrl->reg_offsets[BRCMNAND_FC_BASE];
+	}
+
+	/* FLASH_DMA */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "flash-dma");
+	if (res) {
+		ctrl->flash_dma_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(ctrl->flash_dma_base))
+			return PTR_ERR(ctrl->flash_dma_base);
+
+		flash_dma_writel(ctrl, FLASH_DMA_MODE, 1); /* linked-list */
+		flash_dma_writel(ctrl, FLASH_DMA_ERROR_STATUS, 0);
+
+		/* Allocate descriptor(s) */
+		ctrl->dma_desc = dmam_alloc_coherent(dev,
+						     sizeof(*ctrl->dma_desc),
+						     &ctrl->dma_pa, GFP_KERNEL);
+		if (!ctrl->dma_desc)
+			return -ENOMEM;
+
+		ctrl->dma_irq = platform_get_irq(pdev, 1);
+		if ((int)ctrl->dma_irq < 0) {
+			dev_err(dev, "missing FLASH_DMA IRQ\n");
+			return -ENODEV;
+		}
+
+		ret = devm_request_irq(dev, ctrl->dma_irq,
+				brcmnand_dma_irq, 0, DRV_NAME,
+				ctrl);
+		if (ret < 0) {
+			dev_err(dev, "can't allocate IRQ %d: error %d\n",
+					ctrl->dma_irq, ret);
+			return ret;
+		}
+
+		dev_info(dev, "enabling FLASH_DMA\n");
+	}
+
+	/* Disable automatic device ID config, direct addressing */
+	brcmnand_rmw_reg(ctrl, BRCMNAND_CS_SELECT,
+			 CS_SELECT_AUTO_DEVICE_ID_CFG | 0xff, 0, 0);
+	/* Disable XOR addressing */
+	brcmnand_rmw_reg(ctrl, BRCMNAND_CS_XOR, 0xff, 0, 0);
+
+	if (ctrl->features & BRCMNAND_HAS_WP) {
+		/* Permanently disable write protection */
+		if (wp_on == 2)
+			brcmnand_set_wp(ctrl, false);
+	} else {
+		wp_on = 0;
+	}
+
+	/* IRQ */
+	ctrl->irq = platform_get_irq(pdev, 0);
+	if ((int)ctrl->irq < 0) {
+		dev_err(dev, "no IRQ defined\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Some SoCs integrate this controller (e.g., its interrupt bits) in
+	 * interesting ways
+	 */
+	if (soc) {
+		ctrl->soc = soc;
+
+		ret = devm_request_irq(dev, ctrl->irq, brcmnand_irq, 0,
+				       DRV_NAME, ctrl);
+
+		/* Enable interrupt */
+		ctrl->soc->ctlrdy_ack(ctrl->soc);
+		ctrl->soc->ctlrdy_set_enabled(ctrl->soc, true);
+	} else {
+		/* Use standard interrupt infrastructure */
+		ret = devm_request_irq(dev, ctrl->irq, brcmnand_ctlrdy_irq, 0,
+				       DRV_NAME, ctrl);
+	}
+	if (ret < 0) {
+		dev_err(dev, "can't allocate IRQ %d: error %d\n",
+			ctrl->irq, ret);
+		return ret;
+	}
+
+	for_each_available_child_of_node(dn, child) {
+		if (of_device_is_compatible(child, "brcm,nandcs")) {
+			struct brcmnand_host *host;
+
+			host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+			if (!host)
+				return -ENOMEM;
+			host->pdev = pdev;
+			host->ctrl = ctrl;
+			host->of_node = child;
+
+			ret = brcmnand_init_cs(host);
+			if (ret)
+				continue; /* Try all chip-selects */
+
+			list_add_tail(&host->node, &ctrl->host_list);
+		}
+	}
+
+	/* No chip-selects could initialize properly */
+	if (list_empty(&ctrl->host_list))
+		return -ENODEV;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(brcmnand_probe);
+
+int brcmnand_remove(struct platform_device *pdev)
+{
+	struct brcmnand_controller *ctrl = dev_get_drvdata(&pdev->dev);
+	struct brcmnand_host *host;
+
+	list_for_each_entry(host, &ctrl->host_list, node)
+		nand_release(&host->mtd);
+
+	dev_set_drvdata(&pdev->dev, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(brcmnand_remove);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Kevin Cernekee");
+MODULE_AUTHOR("Brian Norris");
+MODULE_DESCRIPTION("NAND driver for Broadcom chips");
+MODULE_ALIAS("platform:brcmnand");
diff --git a/drivers/mtd/nand/brcmnand/brcmnand.h b/drivers/mtd/nand/brcmnand/brcmnand.h
new file mode 100644
index 000000000000..a20c73630b7b
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/brcmnand.h
@@ -0,0 +1,73 @@
+/*
+ * Copyright © 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __BRCMNAND_H__
+#define __BRCMNAND_H__
+
+#include <linux/types.h>
+#include <linux/io.h>
+
+struct platform_device;
+struct dev_pm_ops;
+
+struct brcmnand_soc {
+	struct platform_device *pdev;
+	void *priv;
+	bool (*ctlrdy_ack)(struct brcmnand_soc *soc);
+	void (*ctlrdy_set_enabled)(struct brcmnand_soc *soc, bool en);
+	void (*prepare_data_bus)(struct brcmnand_soc *soc, bool prepare);
+};
+
+static inline void brcmnand_soc_data_bus_prepare(struct brcmnand_soc *soc)
+{
+	if (soc && soc->prepare_data_bus)
+		soc->prepare_data_bus(soc, true);
+}
+
+static inline void brcmnand_soc_data_bus_unprepare(struct brcmnand_soc *soc)
+{
+	if (soc && soc->prepare_data_bus)
+		soc->prepare_data_bus(soc, false);
+}
+
+static inline u32 brcmnand_readl(void __iomem *addr)
+{
+	/*
+	 * MIPS endianness is configured by boot strap, which also reverses all
+	 * bus endianness (i.e., big-endian CPU + big endian bus ==> native
+	 * endian I/O).
+	 *
+	 * Other architectures (e.g., ARM) either do not support big endian, or
+	 * else leave I/O in little endian mode.
+	 */
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+		return __raw_readl(addr);
+	else
+		return readl_relaxed(addr);
+}
+
+static inline void brcmnand_writel(u32 val, void __iomem *addr)
+{
+	/* See brcmnand_readl() comments */
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+		__raw_writel(val, addr);
+	else
+		writel_relaxed(val, addr);
+}
+
+int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc);
+int brcmnand_remove(struct platform_device *pdev);
+
+extern const struct dev_pm_ops brcmnand_pm_ops;
+
+#endif /* __BRCMNAND_H__ */
diff --git a/drivers/mtd/nand/brcmnand/brcmstb_nand.c b/drivers/mtd/nand/brcmnand/brcmstb_nand.c
new file mode 100644
index 000000000000..5c271077ac87
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/brcmstb_nand.c
@@ -0,0 +1,44 @@
+/*
+ * Copyright © 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "brcmnand.h"
+
+static const struct of_device_id brcmstb_nand_of_match[] = {
+	{ .compatible = "brcm,brcmnand" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, brcmstb_nand_of_match);
+
+static int brcmstb_nand_probe(struct platform_device *pdev)
+{
+	return brcmnand_probe(pdev, NULL);
+}
+
+static struct platform_driver brcmstb_nand_driver = {
+	.probe			= brcmstb_nand_probe,
+	.remove			= brcmnand_remove,
+	.driver = {
+		.name		= "brcmstb_nand",
+		.pm		= &brcmnand_pm_ops,
+		.of_match_table = brcmstb_nand_of_match,
+	}
+};
+module_platform_driver(brcmstb_nand_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Brian Norris");
+MODULE_DESCRIPTION("NAND driver for Broadcom STB chips");
diff --git a/drivers/mtd/nand/brcmnand/iproc_nand.c b/drivers/mtd/nand/brcmnand/iproc_nand.c
new file mode 100644
index 000000000000..683495c74620
--- /dev/null
+++ b/drivers/mtd/nand/brcmnand/iproc_nand.c
@@ -0,0 +1,150 @@
+/*
+ * Copyright © 2015 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "brcmnand.h"
+
+struct iproc_nand_soc_priv {
+	void __iomem *idm_base;
+	void __iomem *ext_base;
+	spinlock_t idm_lock;
+};
+
+#define IPROC_NAND_CTLR_READY_OFFSET       0x10
+#define IPROC_NAND_CTLR_READY              BIT(0)
+
+#define IPROC_NAND_IO_CTRL_OFFSET          0x00
+#define IPROC_NAND_APB_LE_MODE             BIT(24)
+#define IPROC_NAND_INT_CTRL_READ_ENABLE    BIT(6)
+
+static bool iproc_nand_intc_ack(struct brcmnand_soc *soc)
+{
+	struct iproc_nand_soc_priv *priv = soc->priv;
+	void __iomem *mmio = priv->ext_base + IPROC_NAND_CTLR_READY_OFFSET;
+	u32 val = brcmnand_readl(mmio);
+
+	if (val & IPROC_NAND_CTLR_READY) {
+		brcmnand_writel(IPROC_NAND_CTLR_READY, mmio);
+		return true;
+	}
+
+	return false;
+}
+
+static void iproc_nand_intc_set(struct brcmnand_soc *soc, bool en)
+{
+	struct iproc_nand_soc_priv *priv = soc->priv;
+	void __iomem *mmio = priv->idm_base + IPROC_NAND_IO_CTRL_OFFSET;
+	u32 val;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->idm_lock, flags);
+
+	val = brcmnand_readl(mmio);
+
+	if (en)
+		val |= IPROC_NAND_INT_CTRL_READ_ENABLE;
+	else
+		val &= ~IPROC_NAND_INT_CTRL_READ_ENABLE;
+
+	brcmnand_writel(val, mmio);
+
+	spin_unlock_irqrestore(&priv->idm_lock, flags);
+}
+
+static void iproc_nand_apb_access(struct brcmnand_soc *soc, bool prepare)
+{
+	struct iproc_nand_soc_priv *priv = soc->priv;
+	void __iomem *mmio = priv->idm_base + IPROC_NAND_IO_CTRL_OFFSET;
+	u32 val;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->idm_lock, flags);
+
+	val = brcmnand_readl(mmio);
+
+	if (prepare)
+		val |= IPROC_NAND_APB_LE_MODE;
+	else
+		val &= ~IPROC_NAND_APB_LE_MODE;
+
+	brcmnand_writel(val, mmio);
+
+	spin_unlock_irqrestore(&priv->idm_lock, flags);
+}
+
+static int iproc_nand_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct iproc_nand_soc_priv *priv;
+	struct brcmnand_soc *soc;
+	struct resource *res;
+
+	soc = devm_kzalloc(dev, sizeof(*soc), GFP_KERNEL);
+	if (!soc)
+		return -ENOMEM;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	spin_lock_init(&priv->idm_lock);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "iproc-idm");
+	priv->idm_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->idm_base))
+		return PTR_ERR(priv->idm_base);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "iproc-ext");
+	priv->ext_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->ext_base))
+		return PTR_ERR(priv->ext_base);
+
+	soc->pdev = pdev;
+	soc->priv = priv;
+	soc->ctlrdy_ack = iproc_nand_intc_ack;
+	soc->ctlrdy_set_enabled = iproc_nand_intc_set;
+	soc->prepare_data_bus = iproc_nand_apb_access;
+
+	return brcmnand_probe(pdev, soc);
+}
+
+static const struct of_device_id iproc_nand_of_match[] = {
+	{ .compatible = "brcm,nand-iproc" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, iproc_nand_of_match);
+
+static struct platform_driver iproc_nand_driver = {
+	.probe			= iproc_nand_probe,
+	.remove			= brcmnand_remove,
+	.driver = {
+		.name		= "iproc_nand",
+		.pm		= &brcmnand_pm_ops,
+		.of_match_table	= iproc_nand_of_match,
+	}
+};
+module_platform_driver(iproc_nand_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Brian Norris");
+MODULE_AUTHOR("Ray Jui");
+MODULE_DESCRIPTION("NAND driver for Broadcom IPROC-based SoCs");
diff --git a/drivers/mtd/nand/cs553x_nand.c b/drivers/mtd/nand/cs553x_nand.c
index 88109d375ae7..aec6045058c7 100644
--- a/drivers/mtd/nand/cs553x_nand.c
+++ b/drivers/mtd/nand/cs553x_nand.c
@@ -237,17 +237,23 @@ static int __init cs553x_init_one(int cs, int mmio, unsigned long adr)
 	/* Enable the following for a flash based bad block table */
 	this->bbt_options = NAND_BBT_USE_FLASH;
 
+	new_mtd->name = kasprintf(GFP_KERNEL, "cs553x_nand_cs%d", cs);
+	if (!new_mtd->name) {
+		err = -ENOMEM;
+		goto out_ior;
+	}
+
 	/* Scan to find existence of the device */
 	if (nand_scan(new_mtd, 1)) {
 		err = -ENXIO;
-		goto out_ior;
+		goto out_free;
 	}
 
-	new_mtd->name = kasprintf(GFP_KERNEL, "cs553x_nand_cs%d", cs);
-
 	cs553x_mtd[cs] = new_mtd;
 	goto out;
 
+out_free:
+	kfree(new_mtd->name);
 out_ior:
 	iounmap(this->IO_ADDR_R);
 out_mtd:
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index f68a7bccecdc..7da266a53979 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -69,6 +69,9 @@ struct doc_priv {
 	int mh0_page;
 	int mh1_page;
 	struct mtd_info *nextdoc;
+
+	/* Handle the last stage of initialization (BBT scan, partitioning) */
+	int (*late_init)(struct mtd_info *mtd);
 };
 
 /* This is the syndrome computed by the HW ecc generator upon reading an empty
@@ -1294,14 +1297,11 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	/* It's safe to set bd=NULL below because NAND_BBT_CREATE is not set.
-	   At least as nand_bbt.c is currently written. */
-	if ((ret = nand_scan_bbt(mtd, NULL)))
+	ret = this->scan_bbt(mtd);
+	if (ret)
 		return ret;
-	mtd_device_register(mtd, NULL, 0);
-	if (!no_autopart)
-		mtd_device_register(mtd, parts, numparts);
-	return 0;
+
+	return mtd_device_register(mtd, parts, no_autopart ? 0 : numparts);
 }
 
 static int __init inftl_scan_bbt(struct mtd_info *mtd)
@@ -1344,10 +1344,10 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md->pattern = "TBB_SYSM";
 	}
 
-	/* It's safe to set bd=NULL below because NAND_BBT_CREATE is not set.
-	   At least as nand_bbt.c is currently written. */
-	if ((ret = nand_scan_bbt(mtd, NULL)))
+	ret = this->scan_bbt(mtd);
+	if (ret)
 		return ret;
+
 	memset((char *)parts, 0, sizeof(parts));
 	numparts = inftl_partscan(mtd, parts);
 	/* At least for now, require the INFTL Media Header.  We could probably
@@ -1355,10 +1355,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 	   autopartitioning, but I want to give it more thought. */
 	if (!numparts)
 		return -EIO;
-	mtd_device_register(mtd, NULL, 0);
-	if (!no_autopart)
-		mtd_device_register(mtd, parts, numparts);
-	return 0;
+	return mtd_device_register(mtd, parts, no_autopart ? 0 : numparts);
 }
 
 static inline int __init doc2000_init(struct mtd_info *mtd)
@@ -1369,7 +1366,7 @@ static inline int __init doc2000_init(struct mtd_info *mtd)
 	this->read_byte = doc2000_read_byte;
 	this->write_buf = doc2000_writebuf;
 	this->read_buf = doc2000_readbuf;
-	this->scan_bbt = nftl_scan_bbt;
+	doc->late_init = nftl_scan_bbt;
 
 	doc->CDSNControl = CDSN_CTRL_FLASH_IO | CDSN_CTRL_ECC_IO;
 	doc2000_count_chips(mtd);
@@ -1396,13 +1393,13 @@ static inline int __init doc2001_init(struct mtd_info *mtd)
 		   can have multiple chips. */
 		doc2000_count_chips(mtd);
 		mtd->name = "DiskOnChip 2000 (INFTL Model)";
-		this->scan_bbt = inftl_scan_bbt;
+		doc->late_init = inftl_scan_bbt;
 		return (4 * doc->chips_per_floor);
 	} else {
 		/* Bog-standard Millennium */
 		doc->chips_per_floor = 1;
 		mtd->name = "DiskOnChip Millennium";
-		this->scan_bbt = nftl_scan_bbt;
+		doc->late_init = nftl_scan_bbt;
 		return 1;
 	}
 }
@@ -1415,7 +1412,7 @@ static inline int __init doc2001plus_init(struct mtd_info *mtd)
 	this->read_byte = doc2001plus_read_byte;
 	this->write_buf = doc2001plus_writebuf;
 	this->read_buf = doc2001plus_readbuf;
-	this->scan_bbt = inftl_scan_bbt;
+	doc->late_init = inftl_scan_bbt;
 	this->cmd_ctrl = NULL;
 	this->select_chip = doc2001plus_select_chip;
 	this->cmdfunc = doc2001plus_command;
@@ -1591,6 +1588,8 @@ static int __init doc_probe(unsigned long physadr)
 	nand->ecc.bytes		= 6;
 	nand->ecc.strength	= 2;
 	nand->bbt_options	= NAND_BBT_USE_FLASH;
+	/* Skip the automatic BBT scan so we can run it manually */
+	nand->options		|= NAND_SKIP_BBTSCAN;
 
 	doc->physadr		= physadr;
 	doc->virtadr		= virtadr;
@@ -1608,7 +1607,7 @@ static int __init doc_probe(unsigned long physadr)
 	else
 		numchips = doc2001_init(mtd);
 
-	if ((ret = nand_scan(mtd, numchips))) {
+	if ((ret = nand_scan(mtd, numchips)) || (ret = doc->late_init(mtd))) {
 		/* DBB note: i believe nand_release is necessary here, as
 		   buffers may have been allocated in nand_base.  Check with
 		   Thomas. FIX ME! */
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index e58af4bfa8c8..793872f18065 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -562,6 +562,7 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
 	dma_cookie_t cookie;
 	unsigned long flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 	int ret;
+	unsigned long time_left;
 
 	if (direction == DMA_TO_DEVICE)
 		chan = host->write_dma_chan;
@@ -601,14 +602,13 @@ static int dma_xfer(struct fsmc_nand_data *host, void *buffer, int len,
 
 	dma_async_issue_pending(chan);
 
-	ret =
+	time_left =
 	wait_for_completion_timeout(&host->dma_access_complete,
 				msecs_to_jiffies(3000));
-	if (ret <= 0) {
+	if (time_left == 0) {
 		dmaengine_terminate_all(chan);
 		dev_err(host->dev, "wait_for_completion_timeout\n");
-		if (!ret)
-			ret = -ETIMEDOUT;
+		ret = -ETIMEDOUT;
 		goto unmap_dma;
 	}
 
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index 1f12e5bfbced..2a49b53c8db9 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -837,7 +837,7 @@ static int mpc5121_nfc_remove(struct platform_device *op)
 	return 0;
 }
 
-static struct of_device_id mpc5121_nfc_match[] = {
+static const struct of_device_id mpc5121_nfc_match[] = {
 	{ .compatible = "fsl,mpc5121-nfc", },
 	{},
 };
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 372e0e38f59b..2426db88db36 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -189,6 +189,7 @@ struct mxc_nand_host {
 	int			clk_act;
 	int			irq;
 	int			eccsize;
+	int			used_oobsize;
 	int			active_cs;
 
 	struct completion	op_completion;
@@ -280,12 +281,44 @@ static void memcpy32_fromio(void *trg, const void __iomem  *src, size_t size)
 		*t++ = __raw_readl(s++);
 }
 
+static void memcpy16_fromio(void *trg, const void __iomem  *src, size_t size)
+{
+	int i;
+	u16 *t = trg;
+	const __iomem u16 *s = src;
+
+	/* We assume that src (IO) is always 32bit aligned */
+	if (PTR_ALIGN(trg, 4) == trg && IS_ALIGNED(size, 4)) {
+		memcpy32_fromio(trg, src, size);
+		return;
+	}
+
+	for (i = 0; i < (size >> 1); i++)
+		*t++ = __raw_readw(s++);
+}
+
 static inline void memcpy32_toio(void __iomem *trg, const void *src, int size)
 {
 	/* __iowrite32_copy use 32bit size values so divide by 4 */
 	__iowrite32_copy(trg, src, size / 4);
 }
 
+static void memcpy16_toio(void __iomem *trg, const void *src, int size)
+{
+	int i;
+	__iomem u16 *t = trg;
+	const u16 *s = src;
+
+	/* We assume that trg (IO) is always 32bit aligned */
+	if (PTR_ALIGN(src, 4) == src && IS_ALIGNED(size, 4)) {
+		memcpy32_toio(trg, src, size);
+		return;
+	}
+
+	for (i = 0; i < (size >> 1); i++)
+		__raw_writew(*s++, t++);
+}
+
 static int check_int_v3(struct mxc_nand_host *host)
 {
 	uint32_t tmp;
@@ -807,32 +840,48 @@ static void mxc_nand_select_chip_v2(struct mtd_info *mtd, int chip)
 }
 
 /*
- * Function to transfer data to/from spare area.
+ * The controller splits a page into data chunks of 512 bytes + partial oob.
+ * There are writesize / 512 such chunks, the size of the partial oob parts is
+ * oobsize / #chunks rounded down to a multiple of 2. The last oob chunk then
+ * contains additionally the byte lost by rounding (if any).
+ * This function handles the needed shuffling between host->data_buf (which
+ * holds a page in natural order, i.e. writesize bytes data + oobsize bytes
+ * spare) and the NFC buffer.
  */
 static void copy_spare(struct mtd_info *mtd, bool bfrom)
 {
 	struct nand_chip *this = mtd->priv;
 	struct mxc_nand_host *host = this->priv;
-	u16 i, j;
-	u16 n = mtd->writesize >> 9;
+	u16 i, oob_chunk_size;
+	u16 num_chunks = mtd->writesize / 512;
+
 	u8 *d = host->data_buf + mtd->writesize;
 	u8 __iomem *s = host->spare0;
-	u16 t = host->devtype_data->spare_len;
+	u16 sparebuf_size = host->devtype_data->spare_len;
 
-	j = (mtd->oobsize / n >> 1) << 1;
+	/* size of oob chunk for all but possibly the last one */
+	oob_chunk_size = (host->used_oobsize / num_chunks) & ~1;
 
 	if (bfrom) {
-		for (i = 0; i < n - 1; i++)
-			memcpy32_fromio(d + i * j, s + i * t, j);
-
-		/* the last section */
-		memcpy32_fromio(d + i * j, s + i * t, mtd->oobsize - i * j);
+		for (i = 0; i < num_chunks - 1; i++)
+			memcpy16_fromio(d + i * oob_chunk_size,
+					s + i * sparebuf_size,
+					oob_chunk_size);
+
+		/* the last chunk */
+		memcpy16_fromio(d + i * oob_chunk_size,
+				s + i * sparebuf_size,
+				host->used_oobsize - i * oob_chunk_size);
 	} else {
-		for (i = 0; i < n - 1; i++)
-			memcpy32_toio(&s[i * t], &d[i * j], j);
-
-		/* the last section */
-		memcpy32_toio(&s[i * t], &d[i * j], mtd->oobsize - i * j);
+		for (i = 0; i < num_chunks - 1; i++)
+			memcpy16_toio(&s[i * sparebuf_size],
+				      &d[i * oob_chunk_size],
+				      oob_chunk_size);
+
+		/* the last chunk */
+		memcpy16_toio(&s[oob_chunk_size * sparebuf_size],
+			      &d[i * oob_chunk_size],
+			      host->used_oobsize - i * oob_chunk_size);
 	}
 }
 
@@ -911,6 +960,23 @@ static int get_eccsize(struct mtd_info *mtd)
 		return 8;
 }
 
+static void ecc_8bit_layout_4k(struct nand_ecclayout *layout)
+{
+	int i, j;
+
+	layout->eccbytes = 8*18;
+	for (i = 0; i < 8; i++)
+		for (j = 0; j < 18; j++)
+			layout->eccpos[i*18 + j] = i*26 + j + 7;
+
+	layout->oobfree[0].offset = 2;
+	layout->oobfree[0].length = 4;
+	for (i = 1; i < 8; i++) {
+		layout->oobfree[i].offset = i*26;
+		layout->oobfree[i].length = 7;
+	}
+}
+
 static void preset_v1(struct mtd_info *mtd)
 {
 	struct nand_chip *nand_chip = mtd->priv;
@@ -1350,7 +1416,7 @@ static inline int is_imx53_nfc(struct mxc_nand_host *host)
 	return host->devtype_data == &imx53_nand_devtype_data;
 }
 
-static struct platform_device_id mxcnd_devtype[] = {
+static const struct platform_device_id mxcnd_devtype[] = {
 	{
 		.name = "imx21-nand",
 		.driver_data = (kernel_ulong_t) &imx21_nand_devtype_data,
@@ -1587,8 +1653,20 @@ static int mxcnd_probe(struct platform_device *pdev)
 
 	if (mtd->writesize == 2048)
 		this->ecc.layout = host->devtype_data->ecclayout_2k;
-	else if (mtd->writesize == 4096)
+	else if (mtd->writesize == 4096) {
 		this->ecc.layout = host->devtype_data->ecclayout_4k;
+		if (get_eccsize(mtd) == 8)
+			ecc_8bit_layout_4k(this->ecc.layout);
+	}
+
+	/*
+	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
+	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
+	 * into copying invalid data to/from the spare IO buffer, as this
+	 * might cause ECC data corruption when doing sub-page write to a
+	 * partially written page.
+	 */
+	host->used_oobsize = min(mtd->oobsize, 218U);
 
 	if (this->ecc.mode == NAND_ECC_HW) {
 		if (is_imx21_nfc(host) || is_imx27_nfc(host))
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index c2e1232cd45c..ceb68ca8277a 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1,6 +1,4 @@
 /*
- *  drivers/mtd/nand.c
- *
  *  Overview:
  *   This is the generic MTD driver for NAND flash devices. It should be
  *   capable of working with almost all NAND chips currently available.
@@ -48,6 +46,7 @@
 #include <linux/leds.h>
 #include <linux/io.h>
 #include <linux/mtd/partitions.h>
+#include <linux/of_mtd.h>
 
 /* Define default oob placement schemes for large and small page devices */
 static struct nand_ecclayout nand_oob_8 = {
@@ -2928,9 +2927,6 @@ static int nand_onfi_get_features(struct mtd_info *mtd, struct nand_chip *chip,
 	      & ONFI_OPT_CMD_SET_GET_FEATURES))
 		return -EINVAL;
 
-	/* clear the sub feature parameters */
-	memset(subfeature_param, 0, ONFI_SUBFEATURE_PARAM_LEN);
-
 	chip->cmdfunc(mtd, NAND_CMD_GET_FEATURES, addr, -1);
 	for (i = 0; i < ONFI_SUBFEATURE_PARAM_LEN; ++i)
 		*subfeature_param++ = chip->read_byte(mtd);
@@ -3689,7 +3685,7 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd,
 			if (find_full_id_nand(mtd, chip, type, id_data, &busw))
 				goto ident_done;
 		} else if (*dev_id == type->dev_id) {
-				break;
+			break;
 		}
 	}
 
@@ -3798,6 +3794,39 @@ ident_done:
 	return type;
 }
 
+static int nand_dt_init(struct mtd_info *mtd, struct nand_chip *chip,
+			struct device_node *dn)
+{
+	int ecc_mode, ecc_strength, ecc_step;
+
+	if (of_get_nand_bus_width(dn) == 16)
+		chip->options |= NAND_BUSWIDTH_16;
+
+	if (of_get_nand_on_flash_bbt(dn))
+		chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	ecc_mode = of_get_nand_ecc_mode(dn);
+	ecc_strength = of_get_nand_ecc_strength(dn);
+	ecc_step = of_get_nand_ecc_step_size(dn);
+
+	if ((ecc_step >= 0 && !(ecc_strength >= 0)) ||
+	    (!(ecc_step >= 0) && ecc_strength >= 0)) {
+		pr_err("must set both strength and step size in DT\n");
+		return -EINVAL;
+	}
+
+	if (ecc_mode >= 0)
+		chip->ecc.mode = ecc_mode;
+
+	if (ecc_strength >= 0)
+		chip->ecc.strength = ecc_strength;
+
+	if (ecc_step > 0)
+		chip->ecc.size = ecc_step;
+
+	return 0;
+}
+
 /**
  * nand_scan_ident - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
@@ -3815,6 +3844,13 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 	int i, nand_maf_id, nand_dev_id;
 	struct nand_chip *chip = mtd->priv;
 	struct nand_flash_dev *type;
+	int ret;
+
+	if (chip->dn) {
+		ret = nand_dt_init(mtd, chip, chip->dn);
+		if (ret)
+			return ret;
+	}
 
 	/* Set the default functions */
 	nand_set_defaults(chip, chip->options & NAND_BUSWIDTH_16);
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index 9bb8453d224e..63a1a36a3f4b 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -1,6 +1,4 @@
 /*
- *  drivers/mtd/nand_bbt.c
- *
  *  Overview:
  *   Bad block table support for the NAND driver
  *
@@ -64,7 +62,6 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/bbm.h>
 #include <linux/mtd/nand.h>
-#include <linux/mtd/nand_ecc.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/vmalloc.h>
@@ -720,7 +717,7 @@ static int write_bbt(struct mtd_info *mtd, uint8_t *buf,
 		/* Must we save the block contents? */
 		if (td->options & NAND_BBT_SAVECONTENT) {
 			/* Make it block aligned */
-			to &= ~((loff_t)((1 << this->bbt_erase_shift) - 1));
+			to &= ~(((loff_t)1 << this->bbt_erase_shift) - 1);
 			len = 1 << this->bbt_erase_shift;
 			res = mtd_read(mtd, to, len, &retlen, buf);
 			if (res < 0) {
@@ -1075,10 +1072,10 @@ static void verify_bbt_descr(struct mtd_info *mtd, struct nand_bbt_descr *bd)
  * The bad block table memory is allocated here. It must be freed by calling
  * the nand_free_bbt function.
  */
-int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
+static int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
 {
 	struct nand_chip *this = mtd->priv;
-	int len, res = 0;
+	int len, res;
 	uint8_t *buf;
 	struct nand_bbt_descr *td = this->bbt_td;
 	struct nand_bbt_descr *md = this->bbt_md;
@@ -1099,10 +1096,9 @@ int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
 	if (!td) {
 		if ((res = nand_memory_bbt(mtd, bd))) {
 			pr_err("nand_bbt: can't scan flash and build the RAM-based BBT\n");
-			kfree(this->bbt);
-			this->bbt = NULL;
+			goto err;
 		}
-		return res;
+		return 0;
 	}
 	verify_bbt_descr(mtd, td);
 	verify_bbt_descr(mtd, md);
@@ -1112,9 +1108,8 @@ int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
 	len += (len >> this->page_shift) * mtd->oobsize;
 	buf = vmalloc(len);
 	if (!buf) {
-		kfree(this->bbt);
-		this->bbt = NULL;
-		return -ENOMEM;
+		res = -ENOMEM;
+		goto err;
 	}
 
 	/* Is the bbt at a given page? */
@@ -1126,6 +1121,8 @@ int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
 	}
 
 	res = check_create(mtd, buf, bd);
+	if (res)
+		goto err;
 
 	/* Prevent the bbt regions from erasing / writing */
 	mark_bbt_region(mtd, td);
@@ -1133,6 +1130,11 @@ int nand_scan_bbt(struct mtd_info *mtd, struct nand_bbt_descr *bd)
 		mark_bbt_region(mtd, md);
 
 	vfree(buf);
+	return 0;
+
+err:
+	kfree(this->bbt);
+	this->bbt = NULL;
 	return res;
 }
 
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index dd620c19c619..7124400d903b 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -1,6 +1,4 @@
 /*
- *  drivers/mtd/nandids.c
- *
  *  Copyright (C) 2002 Thomas Gleixner (tglx@linutronix.de)
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index f2324271b94e..52c0c1a3899c 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -743,6 +743,11 @@ static int init_nandsim(struct mtd_info *mtd)
 			goto error;
 		}
 		ns->partitions[i].name   = get_partition_name(i);
+		if (!ns->partitions[i].name) {
+			NS_ERR("unable to allocate memory.\n");
+			ret = -ENOMEM;
+			goto error;
+		}
 		ns->partitions[i].offset = next_offset;
 		ns->partitions[i].size   = part_sz;
 		next_offset += ns->partitions[i].size;
@@ -756,6 +761,11 @@ static int init_nandsim(struct mtd_info *mtd)
 			goto error;
 		}
 		ns->partitions[i].name   = get_partition_name(i);
+		if (!ns->partitions[i].name) {
+			NS_ERR("unable to allocate memory.\n");
+			ret = -ENOMEM;
+			goto error;
+		}
 		ns->partitions[i].offset = next_offset;
 		ns->partitions[i].size   = remains;
 		ns->nbparts += 1;
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index 3187c6b92d9a..67a1b3f911cf 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -1,6 +1,4 @@
 /*
- *  drivers/mtd/ndfc.c
- *
  *  Overview:
  *   Platform independent driver for NDFC (NanD Flash Controller)
  *   integrated into EP440 cores
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index 4535c263fae5..717cf623fcde 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -24,8 +24,6 @@ struct plat_nand_data {
 	void __iomem		*io_base;
 };
 
-static const char *part_probe_types[] = { "cmdlinepart", NULL };
-
 /*
  * Probe for the NAND device.
  */
@@ -95,7 +93,7 @@ static int plat_nand_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	part_types = pdata->chip.part_probe_types ? : part_probe_types;
+	part_types = pdata->chip.part_probe_types;
 
 	ppdata.of_node = pdev->dev.of_node;
 	err = mtd_device_parse_register(&data->mtd, part_types, &ppdata,
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index a4615fcc3d00..1259cc558ce9 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -22,13 +22,14 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/irq.h>
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_mtd.h>
 
-#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP)
+#if defined(CONFIG_ARM) && (defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP))
 #define ARCH_HAS_DMA
 #endif
 
@@ -483,7 +484,8 @@ static void disable_int(struct pxa3xx_nand_info *info, uint32_t int_mask)
 static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len)
 {
 	if (info->ecc_bch) {
-		int timeout;
+		u32 val;
+		int ret;
 
 		/*
 		 * According to the datasheet, when reading from NDDB
@@ -494,18 +496,14 @@ static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len)
 		 * the polling on the last read.
 		 */
 		while (len > 8) {
-			__raw_readsl(info->mmio_base + NDDB, data, 8);
-
-			for (timeout = 0;
-			     !(nand_readl(info, NDSR) & NDSR_RDDREQ);
-			     timeout++) {
-				if (timeout >= 5) {
-					dev_err(&info->pdev->dev,
-						"Timeout on RDDREQ while draining the FIFO\n");
-					return;
-				}
-
-				mdelay(1);
+			readsl(info->mmio_base + NDDB, data, 8);
+
+			ret = readl_relaxed_poll_timeout(info->mmio_base + NDSR, val,
+							 val & NDSR_RDDREQ, 1000, 5000);
+			if (ret) {
+				dev_err(&info->pdev->dev,
+					"Timeout on RDDREQ while draining the FIFO\n");
+				return;
 			}
 
 			data += 32;
@@ -513,7 +511,7 @@ static void drain_fifo(struct pxa3xx_nand_info *info, void *data, int len)
 		}
 	}
 
-	__raw_readsl(info->mmio_base + NDDB, data, len);
+	readsl(info->mmio_base + NDDB, data, len);
 }
 
 static void handle_data_pio(struct pxa3xx_nand_info *info)
@@ -522,14 +520,14 @@ static void handle_data_pio(struct pxa3xx_nand_info *info)
 
 	switch (info->state) {
 	case STATE_PIO_WRITING:
-		__raw_writesl(info->mmio_base + NDDB,
-			      info->data_buff + info->data_buff_pos,
-			      DIV_ROUND_UP(do_bytes, 4));
+		writesl(info->mmio_base + NDDB,
+			info->data_buff + info->data_buff_pos,
+			DIV_ROUND_UP(do_bytes, 4));
 
 		if (info->oob_size > 0)
-			__raw_writesl(info->mmio_base + NDDB,
-				      info->oob_buff + info->oob_buff_pos,
-				      DIV_ROUND_UP(info->oob_size, 4));
+			writesl(info->mmio_base + NDDB,
+				info->oob_buff + info->oob_buff_pos,
+				DIV_ROUND_UP(info->oob_size, 4));
 		break;
 	case STATE_PIO_READING:
 		drain_fifo(info,
@@ -1630,8 +1628,7 @@ static int alloc_nand_resource(struct platform_device *pdev)
 	info->pdev = pdev;
 	info->variant = pxa3xx_nand_get_variant(pdev);
 	for (cs = 0; cs < pdata->num_cs; cs++) {
-		mtd = (struct mtd_info *)((unsigned int)&info[1] +
-		      (sizeof(*mtd) + sizeof(*host)) * cs);
+		mtd = (void *)&info[1] + (sizeof(*mtd) + sizeof(*host)) * cs;
 		chip = (struct nand_chip *)(&mtd[1]);
 		host = (struct pxa3xx_nand_host *)chip;
 		info->host[cs] = host;
diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c
index baea83f4dea8..77e96d2df96c 100644
--- a/drivers/mtd/nand/r852.c
+++ b/drivers/mtd/nand/r852.c
@@ -653,11 +653,15 @@ static int r852_register_nand_device(struct r852_device *dev)
 	if (sm_register_device(dev->mtd, dev->sm))
 		goto error2;
 
-	if (device_create_file(&dev->mtd->dev, &dev_attr_media_type))
+	if (device_create_file(&dev->mtd->dev, &dev_attr_media_type)) {
 		message("can't create media type sysfs attribute");
+		goto error3;
+	}
 
 	dev->card_registred = 1;
 	return 0;
+error3:
+	nand_release(dev->mtd);
 error2:
 	kfree(dev->mtd);
 error1:
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 0e02be47ce1d..381f67ac6b5a 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -1105,7 +1105,7 @@ static int s3c24xx_nand_resume(struct platform_device *dev)
 
 /* driver device registration */
 
-static struct platform_device_id s3c24xx_driver_ids[] = {
+static const struct platform_device_id s3c24xx_driver_ids[] = {
 	{
 		.name		= "s3c2410-nand",
 		.driver_data	= TYPE_S3C2410,
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 3f81dc8f214c..3b28db458ea0 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -160,14 +160,10 @@ static int xway_nand_probe(struct platform_device *pdev)
 	return 0;
 }
 
-/* allow users to override the partition in DT using the cmdline */
-static const char *part_probes[] = { "cmdlinepart", "ofpart", NULL };
-
 static struct platform_nand_data xway_nand_data = {
 	.chip = {
 		.nr_chips		= 1,
 		.chip_delay		= 30,
-		.part_probe_types	= part_probes,
 	},
 	.ctrl = {
 		.probe		= xway_nand_probe,
diff --git a/drivers/mtd/onenand/samsung.c b/drivers/mtd/onenand/samsung.c
index 19cfb97adbc0..739259513055 100644
--- a/drivers/mtd/onenand/samsung.c
+++ b/drivers/mtd/onenand/samsung.c
@@ -1083,7 +1083,7 @@ static const struct dev_pm_ops s3c_pm_ops = {
 	.resume		= s3c_pm_ops_resume,
 };
 
-static struct platform_device_id s3c_onenand_driver_ids[] = {
+static const struct platform_device_id s3c_onenand_driver_ids[] = {
 	{
 		.name		= "s3c6400-onenand",
 		.driver_data	= TYPE_S3C6400,
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index 5d5d36272bb5..52a872fa1b6e 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -662,7 +662,7 @@ static int fsl_qspi_nor_setup_last(struct fsl_qspi *q)
 	return 0;
 }
 
-static struct of_device_id fsl_qspi_dt_ids[] = {
+static const struct of_device_id fsl_qspi_dt_ids[] = {
 	{ .compatible = "fsl,vf610-qspi", .data = (void *)&vybrid_data, },
 	{ .compatible = "fsl,imx6sx-qspi", .data = (void *)&imx6sx_data, },
 	{ /* sentinel */ }
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 14a5d2325dac..d78831b4422b 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -513,6 +513,13 @@ static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 /* NOTE: double check command sets and memory organization when you add
  * more nor chips.  This current list focusses on newer chips, which
  * have been converging on command sets which including JEDEC ID.
+ *
+ * All newly added entries should describe *hardware* and should use SECT_4K
+ * (or SECT_4K_PMC) if hardware supports erasing 4 KiB sectors. For usage
+ * scenarios excluding small sectors there is config option that can be
+ * disabled: CONFIG_MTD_SPI_NOR_USE_4K_SECTORS.
+ * For historical (and compatibility) reasons (before we got above config) some
+ * old entries may be missing 4K flag.
  */
 static const struct spi_device_id spi_nor_ids[] = {
 	/* Atmel -- some are (confusingly) marketed as "DataFlash" */
@@ -538,7 +545,7 @@ static const struct spi_device_id spi_nor_ids[] = {
 	{ "en25q64",    INFO(0x1c3017, 0, 64 * 1024,  128, SECT_4K) },
 	{ "en25qh128",  INFO(0x1c7018, 0, 64 * 1024,  256, 0) },
 	{ "en25qh256",  INFO(0x1c7019, 0, 64 * 1024,  512, 0) },
-	{ "en25s64",	INFO(0x1c3817, 0, 64 * 1024,  128, 0) },
+	{ "en25s64",	INFO(0x1c3817, 0, 64 * 1024,  128, SECT_4K) },
 
 	/* ESMT */
 	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
@@ -560,7 +567,11 @@ static const struct spi_device_id spi_nor_ids[] = {
 	{ "320s33b",  INFO(0x898912, 0, 64 * 1024,  64, 0) },
 	{ "640s33b",  INFO(0x898913, 0, 64 * 1024, 128, 0) },
 
+	/* ISSI */
+	{ "is25cd512", INFO(0x7f9d20, 0, 32 * 1024,   2, SECT_4K) },
+
 	/* Macronix */
+	{ "mx25l512e",   INFO(0xc22010, 0, 64 * 1024,   1, SECT_4K) },
 	{ "mx25l2005a",  INFO(0xc22012, 0, 64 * 1024,   4, SECT_4K) },
 	{ "mx25l4005a",  INFO(0xc22013, 0, 64 * 1024,   8, SECT_4K) },
 	{ "mx25l8005",   INFO(0xc22014, 0, 64 * 1024,  16, 0) },
@@ -602,7 +613,7 @@ static const struct spi_device_id spi_nor_ids[] = {
 	{ "s70fl01gs",  INFO(0x010221, 0x4d00, 256 * 1024, 256, 0) },
 	{ "s25sl12800", INFO(0x012018, 0x0300, 256 * 1024,  64, 0) },
 	{ "s25sl12801", INFO(0x012018, 0x0301,  64 * 1024, 256, 0) },
-	{ "s25fl128s",	INFO6(0x012018, 0x4d0180, 64 * 1024, 256, SPI_NOR_QUAD_READ) },
+	{ "s25fl128s",	INFO6(0x012018, 0x4d0180, 64 * 1024, 256, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "s25fl129p0", INFO(0x012018, 0x4d00, 256 * 1024,  64, 0) },
 	{ "s25fl129p1", INFO(0x012018, 0x4d01,  64 * 1024, 256, 0) },
 	{ "s25sl004a",  INFO(0x010212,      0,  64 * 1024,   8, 0) },
@@ -613,7 +624,8 @@ static const struct spi_device_id spi_nor_ids[] = {
 	{ "s25fl008k",  INFO(0xef4014,      0,  64 * 1024,  16, SECT_4K) },
 	{ "s25fl016k",  INFO(0xef4015,      0,  64 * 1024,  32, SECT_4K) },
 	{ "s25fl064k",  INFO(0xef4017,      0,  64 * 1024, 128, SECT_4K) },
-	{ "s25fl132k",  INFO(0x014016,      0,  64 * 1024,  64, 0) },
+	{ "s25fl132k",  INFO(0x014016,      0,  64 * 1024,  64, SECT_4K) },
+	{ "s25fl164k",  INFO(0x014017,      0,  64 * 1024, 128, SECT_4K) },
 
 	/* SST -- large erase sizes are "overlays", "sectors" are 4K */
 	{ "sst25vf040b", INFO(0xbf258d, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
diff --git a/drivers/mtd/tests/readtest.c b/drivers/mtd/tests/readtest.c
index a3196b750a22..58df07acdbdb 100644
--- a/drivers/mtd/tests/readtest.c
+++ b/drivers/mtd/tests/readtest.c
@@ -191,9 +191,11 @@ static int __init mtd_readtest_init(void)
 				err = ret;
 		}
 
-		err = mtdtest_relax();
-		if (err)
+		ret = mtdtest_relax();
+		if (ret) {
+			err = ret;
 			goto out;
+		}
 	}
 
 	if (err)
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index db2c05b6fe7f..1a92d30689e7 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -48,6 +48,7 @@
 #include <linux/blk-mq.h>
 #include <linux/hdreg.h>
 #include <linux/scatterlist.h>
+#include <linux/idr.h>
 #include <asm/div64.h>
 
 #include "ubi-media.h"
@@ -310,6 +311,8 @@ static void ubiblock_do_work(struct work_struct *work)
 	blk_rq_map_sg(req->q, req, pdu->usgl.sg);
 
 	ret = ubiblock_read(pdu);
+	rq_flush_dcache_pages(req);
+
 	blk_mq_end_request(req, ret);
 }
 
@@ -351,6 +354,8 @@ static struct blk_mq_ops ubiblock_mq_ops = {
 	.map_queue      = blk_mq_map_queue,
 };
 
+static DEFINE_IDR(ubiblock_minor_idr);
+
 int ubiblock_create(struct ubi_volume_info *vi)
 {
 	struct ubiblock *dev;
@@ -388,7 +393,13 @@ int ubiblock_create(struct ubi_volume_info *vi)
 
 	gd->fops = &ubiblock_ops;
 	gd->major = ubiblock_major;
-	gd->first_minor = dev->ubi_num * UBI_MAX_VOLUMES + dev->vol_id;
+	gd->first_minor = idr_alloc(&ubiblock_minor_idr, dev, 0, 0, GFP_KERNEL);
+	if (gd->first_minor < 0) {
+		dev_err(disk_to_dev(gd),
+			"block: dynamic minor allocation failed");
+		ret = -ENODEV;
+		goto out_put_disk;
+	}
 	gd->private_data = dev;
 	sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id);
 	set_capacity(gd, disk_capacity);
@@ -405,7 +416,7 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	ret = blk_mq_alloc_tag_set(&dev->tag_set);
 	if (ret) {
 		dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed");
-		goto out_put_disk;
+		goto out_remove_minor;
 	}
 
 	dev->rq = blk_mq_init_queue(&dev->tag_set);
@@ -443,6 +454,8 @@ out_free_queue:
 	blk_cleanup_queue(dev->rq);
 out_free_tags:
 	blk_mq_free_tag_set(&dev->tag_set);
+out_remove_minor:
+	idr_remove(&ubiblock_minor_idr, gd->first_minor);
 out_put_disk:
 	put_disk(dev->gd);
 out_free_dev:
@@ -461,6 +474,7 @@ static void ubiblock_cleanup(struct ubiblock *dev)
 	blk_cleanup_queue(dev->rq);
 	blk_mq_free_tag_set(&dev->tag_set);
 	dev_info(disk_to_dev(dev->gd), "released");
+	idr_remove(&ubiblock_minor_idr, dev->gd->first_minor);
 	put_disk(dev->gd);
 }
 
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index b7f824d5ee88..22fd19c0c5d3 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -83,8 +83,6 @@ static struct mtd_dev_param __initdata mtd_dev_param[UBI_MAX_DEVICES];
 static bool fm_autoconvert;
 static bool fm_debug;
 #endif
-/* Root UBI "class" object (corresponds to '/<sysfs>/class/ubi/') */
-struct class *ubi_class;
 
 /* Slab cache for wear-leveling entries */
 struct kmem_cache *ubi_wl_entry_slab;
@@ -113,8 +111,17 @@ static ssize_t ubi_version_show(struct class *class,
 }
 
 /* UBI version attribute ('/<sysfs>/class/ubi/version') */
-static struct class_attribute ubi_version =
-	__ATTR(version, S_IRUGO, ubi_version_show, NULL);
+static struct class_attribute ubi_class_attrs[] = {
+	__ATTR(version, S_IRUGO, ubi_version_show, NULL),
+	__ATTR_NULL
+};
+
+/* Root UBI "class" object (corresponds to '/<sysfs>/class/ubi/') */
+struct class ubi_class = {
+	.name		= UBI_NAME_STR,
+	.owner		= THIS_MODULE,
+	.class_attrs	= ubi_class_attrs,
+};
 
 static ssize_t dev_attribute_show(struct device *dev,
 				  struct device_attribute *attr, char *buf);
@@ -385,6 +392,22 @@ static ssize_t dev_attribute_show(struct device *dev,
 	return ret;
 }
 
+static struct attribute *ubi_dev_attrs[] = {
+	&dev_eraseblock_size.attr,
+	&dev_avail_eraseblocks.attr,
+	&dev_total_eraseblocks.attr,
+	&dev_volumes_count.attr,
+	&dev_max_ec.attr,
+	&dev_reserved_for_bad.attr,
+	&dev_bad_peb_count.attr,
+	&dev_max_vol_count.attr,
+	&dev_min_io_size.attr,
+	&dev_bgt_enabled.attr,
+	&dev_mtd_num.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(ubi_dev);
+
 static void dev_release(struct device *dev)
 {
 	struct ubi_device *ubi = container_of(dev, struct ubi_device, dev);
@@ -407,45 +430,15 @@ static int ubi_sysfs_init(struct ubi_device *ubi, int *ref)
 
 	ubi->dev.release = dev_release;
 	ubi->dev.devt = ubi->cdev.dev;
-	ubi->dev.class = ubi_class;
+	ubi->dev.class = &ubi_class;
+	ubi->dev.groups = ubi_dev_groups;
 	dev_set_name(&ubi->dev, UBI_NAME_STR"%d", ubi->ubi_num);
 	err = device_register(&ubi->dev);
 	if (err)
 		return err;
 
 	*ref = 1;
-	err = device_create_file(&ubi->dev, &dev_eraseblock_size);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_avail_eraseblocks);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_total_eraseblocks);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_volumes_count);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_max_ec);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_reserved_for_bad);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_bad_peb_count);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_max_vol_count);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_min_io_size);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_bgt_enabled);
-	if (err)
-		return err;
-	err = device_create_file(&ubi->dev, &dev_mtd_num);
-	return err;
+	return 0;
 }
 
 /**
@@ -454,17 +447,6 @@ static int ubi_sysfs_init(struct ubi_device *ubi, int *ref)
  */
 static void ubi_sysfs_close(struct ubi_device *ubi)
 {
-	device_remove_file(&ubi->dev, &dev_mtd_num);
-	device_remove_file(&ubi->dev, &dev_bgt_enabled);
-	device_remove_file(&ubi->dev, &dev_min_io_size);
-	device_remove_file(&ubi->dev, &dev_max_vol_count);
-	device_remove_file(&ubi->dev, &dev_bad_peb_count);
-	device_remove_file(&ubi->dev, &dev_reserved_for_bad);
-	device_remove_file(&ubi->dev, &dev_max_ec);
-	device_remove_file(&ubi->dev, &dev_volumes_count);
-	device_remove_file(&ubi->dev, &dev_total_eraseblocks);
-	device_remove_file(&ubi->dev, &dev_avail_eraseblocks);
-	device_remove_file(&ubi->dev, &dev_eraseblock_size);
 	device_unregister(&ubi->dev);
 }
 
@@ -947,8 +929,8 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num,
 	 */
 	ubi->fm_pool.max_size = min(((int)mtd_div_by_eb(ubi->mtd->size,
 		ubi->mtd) / 100) * 5, UBI_FM_MAX_POOL_SIZE);
-	if (ubi->fm_pool.max_size < UBI_FM_MIN_POOL_SIZE)
-		ubi->fm_pool.max_size = UBI_FM_MIN_POOL_SIZE;
+	ubi->fm_pool.max_size = max(ubi->fm_pool.max_size,
+		UBI_FM_MIN_POOL_SIZE);
 
 	ubi->fm_wl_pool.max_size = ubi->fm_pool.max_size / 2;
 	ubi->fm_disabled = !fm_autoconvert;
@@ -1233,23 +1215,14 @@ static int __init ubi_init(void)
 	}
 
 	/* Create base sysfs directory and sysfs files */
-	ubi_class = class_create(THIS_MODULE, UBI_NAME_STR);
-	if (IS_ERR(ubi_class)) {
-		err = PTR_ERR(ubi_class);
-		pr_err("UBI error: cannot create UBI class");
-		goto out;
-	}
-
-	err = class_create_file(ubi_class, &ubi_version);
-	if (err) {
-		pr_err("UBI error: cannot create sysfs file");
-		goto out_class;
-	}
+	err = class_register(&ubi_class);
+	if (err < 0)
+		return err;
 
 	err = misc_register(&ubi_ctrl_cdev);
 	if (err) {
 		pr_err("UBI error: cannot register device");
-		goto out_version;
+		goto out;
 	}
 
 	ubi_wl_entry_slab = kmem_cache_create("ubi_wl_entry_slab",
@@ -1333,11 +1306,8 @@ out_slab:
 	kmem_cache_destroy(ubi_wl_entry_slab);
 out_dev_unreg:
 	misc_deregister(&ubi_ctrl_cdev);
-out_version:
-	class_remove_file(ubi_class, &ubi_version);
-out_class:
-	class_destroy(ubi_class);
 out:
+	class_unregister(&ubi_class);
 	pr_err("UBI error: cannot initialize UBI, error %d", err);
 	return err;
 }
@@ -1358,8 +1328,7 @@ static void __exit ubi_exit(void)
 	ubi_debugfs_exit();
 	kmem_cache_destroy(ubi_wl_entry_slab);
 	misc_deregister(&ubi_ctrl_cdev);
-	class_remove_file(ubi_class, &ubi_version);
-	class_destroy(ubi_class);
+	class_unregister(&ubi_class);
 }
 module_exit(ubi_exit);
 
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 02a6de2f53ee..4aa2fd8633e7 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -88,13 +88,13 @@ size_t ubi_calc_fm_size(struct ubi_device *ubi)
 {
 	size_t size;
 
-	size = sizeof(struct ubi_fm_sb) + \
-		sizeof(struct ubi_fm_hdr) + \
-		sizeof(struct ubi_fm_scan_pool) + \
-		sizeof(struct ubi_fm_scan_pool) + \
-		(ubi->peb_count * sizeof(struct ubi_fm_ec)) + \
-		(sizeof(struct ubi_fm_eba) + \
-		(ubi->peb_count * sizeof(__be32))) + \
+	size = sizeof(struct ubi_fm_sb) +
+		sizeof(struct ubi_fm_hdr) +
+		sizeof(struct ubi_fm_scan_pool) +
+		sizeof(struct ubi_fm_scan_pool) +
+		(ubi->peb_count * sizeof(struct ubi_fm_ec)) +
+		(sizeof(struct ubi_fm_eba) +
+		(ubi->peb_count * sizeof(__be32))) +
 		sizeof(struct ubi_fm_volhdr) * UBI_MAX_VOLUMES;
 	return roundup(size, ubi->leb_size);
 }
@@ -192,8 +192,10 @@ static struct ubi_ainf_volume *add_vol(struct ubi_attach_info *ai, int vol_id,
 
 		if (vol_id > av->vol_id)
 			p = &(*p)->rb_left;
-		else
+		else if (vol_id < av->vol_id)
 			p = &(*p)->rb_right;
+		else
+			return ERR_PTR(-EINVAL);
 	}
 
 	av = kmalloc(sizeof(struct ubi_ainf_volume), GFP_KERNEL);
@@ -314,7 +316,7 @@ static int update_vol(struct ubi_device *ubi, struct ubi_attach_info *ai,
 			list_add_tail(&victim->u.list, &ai->erase);
 
 			if (av->highest_lnum == be32_to_cpu(new_vh->lnum))
-				av->last_data_size = \
+				av->last_data_size =
 					be32_to_cpu(new_vh->data_size);
 
 			dbg_bld("vol %i: AEB %i's PEB %i is the newer",
@@ -601,7 +603,7 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 	struct ubi_ainf_peb *aeb, *tmp_aeb, *_tmp_aeb;
 	struct ubi_fm_sb *fmsb;
 	struct ubi_fm_hdr *fmhdr;
-	struct ubi_fm_scan_pool *fmpl1, *fmpl2;
+	struct ubi_fm_scan_pool *fmpl, *fmpl_wl;
 	struct ubi_fm_ec *fmec;
 	struct ubi_fm_volhdr *fmvhdr;
 	struct ubi_fm_eba *fm_eba;
@@ -631,30 +633,30 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 		goto fail_bad;
 	}
 
-	fmpl1 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
-	fm_pos += sizeof(*fmpl1);
+	fmpl = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
+	fm_pos += sizeof(*fmpl);
 	if (fm_pos >= fm_size)
 		goto fail_bad;
-	if (be32_to_cpu(fmpl1->magic) != UBI_FM_POOL_MAGIC) {
+	if (be32_to_cpu(fmpl->magic) != UBI_FM_POOL_MAGIC) {
 		ubi_err(ubi, "bad fastmap pool magic: 0x%x, expected: 0x%x",
-			be32_to_cpu(fmpl1->magic), UBI_FM_POOL_MAGIC);
+			be32_to_cpu(fmpl->magic), UBI_FM_POOL_MAGIC);
 		goto fail_bad;
 	}
 
-	fmpl2 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
-	fm_pos += sizeof(*fmpl2);
+	fmpl_wl = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
+	fm_pos += sizeof(*fmpl_wl);
 	if (fm_pos >= fm_size)
 		goto fail_bad;
-	if (be32_to_cpu(fmpl2->magic) != UBI_FM_POOL_MAGIC) {
-		ubi_err(ubi, "bad fastmap pool magic: 0x%x, expected: 0x%x",
-			be32_to_cpu(fmpl2->magic), UBI_FM_POOL_MAGIC);
+	if (be32_to_cpu(fmpl_wl->magic) != UBI_FM_POOL_MAGIC) {
+		ubi_err(ubi, "bad fastmap WL pool magic: 0x%x, expected: 0x%x",
+			be32_to_cpu(fmpl_wl->magic), UBI_FM_POOL_MAGIC);
 		goto fail_bad;
 	}
 
-	pool_size = be16_to_cpu(fmpl1->size);
-	wl_pool_size = be16_to_cpu(fmpl2->size);
-	fm->max_pool_size = be16_to_cpu(fmpl1->max_size);
-	fm->max_wl_pool_size = be16_to_cpu(fmpl2->max_size);
+	pool_size = be16_to_cpu(fmpl->size);
+	wl_pool_size = be16_to_cpu(fmpl_wl->size);
+	fm->max_pool_size = be16_to_cpu(fmpl->max_size);
+	fm->max_wl_pool_size = be16_to_cpu(fmpl_wl->max_size);
 
 	if (pool_size > UBI_FM_MAX_POOL_SIZE || pool_size < 0) {
 		ubi_err(ubi, "bad pool size: %i", pool_size);
@@ -748,6 +750,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 
 		if (!av)
 			goto fail_bad;
+		if (PTR_ERR(av) == -EINVAL) {
+			ubi_err(ubi, "volume (ID %i) already exists",
+				fmvhdr->vol_id);
+			goto fail_bad;
+		}
 
 		ai->vols_found++;
 		if (ai->highest_vol_id < be32_to_cpu(fmvhdr->vol_id))
@@ -796,11 +803,11 @@ static int ubi_attach_fastmap(struct ubi_device *ubi,
 		}
 	}
 
-	ret = scan_pool(ubi, ai, fmpl1->pebs, pool_size, &max_sqnum, &free);
+	ret = scan_pool(ubi, ai, fmpl->pebs, pool_size, &max_sqnum, &free);
 	if (ret)
 		goto fail;
 
-	ret = scan_pool(ubi, ai, fmpl2->pebs, wl_pool_size, &max_sqnum, &free);
+	ret = scan_pool(ubi, ai, fmpl_wl->pebs, wl_pool_size, &max_sqnum, &free);
 	if (ret)
 		goto fail;
 
@@ -1083,7 +1090,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	void *fm_raw;
 	struct ubi_fm_sb *fmsb;
 	struct ubi_fm_hdr *fmh;
-	struct ubi_fm_scan_pool *fmpl1, *fmpl2;
+	struct ubi_fm_scan_pool *fmpl, *fmpl_wl;
 	struct ubi_fm_ec *fec;
 	struct ubi_fm_volhdr *fvh;
 	struct ubi_fm_eba *feba;
@@ -1141,25 +1148,25 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	erase_peb_count = 0;
 	vol_count = 0;
 
-	fmpl1 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
-	fm_pos += sizeof(*fmpl1);
-	fmpl1->magic = cpu_to_be32(UBI_FM_POOL_MAGIC);
-	fmpl1->size = cpu_to_be16(ubi->fm_pool.size);
-	fmpl1->max_size = cpu_to_be16(ubi->fm_pool.max_size);
+	fmpl = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
+	fm_pos += sizeof(*fmpl);
+	fmpl->magic = cpu_to_be32(UBI_FM_POOL_MAGIC);
+	fmpl->size = cpu_to_be16(ubi->fm_pool.size);
+	fmpl->max_size = cpu_to_be16(ubi->fm_pool.max_size);
 
 	for (i = 0; i < ubi->fm_pool.size; i++) {
-		fmpl1->pebs[i] = cpu_to_be32(ubi->fm_pool.pebs[i]);
+		fmpl->pebs[i] = cpu_to_be32(ubi->fm_pool.pebs[i]);
 		set_seen(ubi, ubi->fm_pool.pebs[i], seen_pebs);
 	}
 
-	fmpl2 = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
-	fm_pos += sizeof(*fmpl2);
-	fmpl2->magic = cpu_to_be32(UBI_FM_POOL_MAGIC);
-	fmpl2->size = cpu_to_be16(ubi->fm_wl_pool.size);
-	fmpl2->max_size = cpu_to_be16(ubi->fm_wl_pool.max_size);
+	fmpl_wl = (struct ubi_fm_scan_pool *)(fm_raw + fm_pos);
+	fm_pos += sizeof(*fmpl_wl);
+	fmpl_wl->magic = cpu_to_be32(UBI_FM_POOL_MAGIC);
+	fmpl_wl->size = cpu_to_be16(ubi->fm_wl_pool.size);
+	fmpl_wl->max_size = cpu_to_be16(ubi->fm_wl_pool.max_size);
 
 	for (i = 0; i < ubi->fm_wl_pool.size; i++) {
-		fmpl2->pebs[i] = cpu_to_be32(ubi->fm_wl_pool.pebs[i]);
+		fmpl_wl->pebs[i] = cpu_to_be32(ubi->fm_wl_pool.pebs[i]);
 		set_seen(ubi, ubi->fm_wl_pool.pebs[i], seen_pebs);
 	}
 
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index c998212fc680..2974b67f6c6c 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -775,7 +775,7 @@ extern struct kmem_cache *ubi_wl_entry_slab;
 extern const struct file_operations ubi_ctrl_cdev_operations;
 extern const struct file_operations ubi_cdev_operations;
 extern const struct file_operations ubi_vol_cdev_operations;
-extern struct class *ubi_class;
+extern struct class ubi_class;
 extern struct mutex ubi_devices_mutex;
 extern struct blocking_notifier_head ubi_notifiers;
 
diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c
index ff4d97848d1c..1ae17bb9b889 100644
--- a/drivers/mtd/ubi/vmt.c
+++ b/drivers/mtd/ubi/vmt.c
@@ -120,6 +120,19 @@ static ssize_t vol_attribute_show(struct device *dev,
 	return ret;
 }
 
+static struct attribute *volume_dev_attrs[] = {
+	&attr_vol_reserved_ebs.attr,
+	&attr_vol_type.attr,
+	&attr_vol_name.attr,
+	&attr_vol_corrupted.attr,
+	&attr_vol_alignment.attr,
+	&attr_vol_usable_eb_size.attr,
+	&attr_vol_data_bytes.attr,
+	&attr_vol_upd_marker.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(volume_dev);
+
 /* Release method for volume devices */
 static void vol_release(struct device *dev)
 {
@@ -130,64 +143,6 @@ static void vol_release(struct device *dev)
 }
 
 /**
- * volume_sysfs_init - initialize sysfs for new volume.
- * @ubi: UBI device description object
- * @vol: volume description object
- *
- * This function returns zero in case of success and a negative error code in
- * case of failure.
- *
- * Note, this function does not free allocated resources in case of failure -
- * the caller does it. This is because this would cause release() here and the
- * caller would oops.
- */
-static int volume_sysfs_init(struct ubi_device *ubi, struct ubi_volume *vol)
-{
-	int err;
-
-	err = device_create_file(&vol->dev, &attr_vol_reserved_ebs);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_type);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_name);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_corrupted);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_alignment);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_usable_eb_size);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_data_bytes);
-	if (err)
-		return err;
-	err = device_create_file(&vol->dev, &attr_vol_upd_marker);
-	return err;
-}
-
-/**
- * volume_sysfs_close - close sysfs for a volume.
- * @vol: volume description object
- */
-static void volume_sysfs_close(struct ubi_volume *vol)
-{
-	device_remove_file(&vol->dev, &attr_vol_upd_marker);
-	device_remove_file(&vol->dev, &attr_vol_data_bytes);
-	device_remove_file(&vol->dev, &attr_vol_usable_eb_size);
-	device_remove_file(&vol->dev, &attr_vol_alignment);
-	device_remove_file(&vol->dev, &attr_vol_corrupted);
-	device_remove_file(&vol->dev, &attr_vol_name);
-	device_remove_file(&vol->dev, &attr_vol_type);
-	device_remove_file(&vol->dev, &attr_vol_reserved_ebs);
-	device_unregister(&vol->dev);
-}
-
-/**
  * ubi_create_volume - create volume.
  * @ubi: UBI device description object
  * @req: volume creation request
@@ -253,8 +208,8 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 
 	/* Calculate how many eraseblocks are requested */
 	vol->usable_leb_size = ubi->leb_size - ubi->leb_size % req->alignment;
-	vol->reserved_pebs += div_u64(req->bytes + vol->usable_leb_size - 1,
-				      vol->usable_leb_size);
+	vol->reserved_pebs = div_u64(req->bytes + vol->usable_leb_size - 1,
+				     vol->usable_leb_size);
 
 	/* Reserve physical eraseblocks */
 	if (vol->reserved_pebs > ubi->avail_pebs) {
@@ -323,7 +278,8 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	vol->dev.release = vol_release;
 	vol->dev.parent = &ubi->dev;
 	vol->dev.devt = dev;
-	vol->dev.class = ubi_class;
+	vol->dev.class = &ubi_class;
+	vol->dev.groups = volume_dev_groups;
 
 	dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id);
 	err = device_register(&vol->dev);
@@ -332,10 +288,6 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 		goto out_cdev;
 	}
 
-	err = volume_sysfs_init(ubi, vol);
-	if (err)
-		goto out_sysfs;
-
 	/* Fill volume table record */
 	memset(&vtbl_rec, 0, sizeof(struct ubi_vtbl_record));
 	vtbl_rec.reserved_pebs = cpu_to_be32(vol->reserved_pebs);
@@ -372,7 +324,7 @@ out_sysfs:
 	 */
 	do_free = 0;
 	get_device(&vol->dev);
-	volume_sysfs_close(vol);
+	device_unregister(&vol->dev);
 out_cdev:
 	cdev_del(&vol->cdev);
 out_mapping:
@@ -440,7 +392,7 @@ int ubi_remove_volume(struct ubi_volume_desc *desc, int no_vtbl)
 	}
 
 	cdev_del(&vol->cdev);
-	volume_sysfs_close(vol);
+	device_unregister(&vol->dev);
 
 	spin_lock(&ubi->volumes_lock);
 	ubi->rsvd_pebs -= reserved_pebs;
@@ -653,19 +605,13 @@ int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol)
 	vol->dev.release = vol_release;
 	vol->dev.parent = &ubi->dev;
 	vol->dev.devt = dev;
-	vol->dev.class = ubi_class;
+	vol->dev.class = &ubi_class;
+	vol->dev.groups = volume_dev_groups;
 	dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id);
 	err = device_register(&vol->dev);
 	if (err)
 		goto out_cdev;
 
-	err = volume_sysfs_init(ubi, vol);
-	if (err) {
-		cdev_del(&vol->cdev);
-		volume_sysfs_close(vol);
-		return err;
-	}
-
 	self_check_volumes(ubi);
 	return err;
 
@@ -688,7 +634,7 @@ void ubi_free_volume(struct ubi_device *ubi, struct ubi_volume *vol)
 
 	ubi->volumes[vol->vol_id] = NULL;
 	cdev_del(&vol->cdev);
-	volume_sysfs_close(vol);
+	device_unregister(&vol->dev);
 }
 
 /**
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 68c9c5ea676f..80bdd5b88bac 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -70,6 +70,26 @@ static void self_vtbl_check(const struct ubi_device *ubi);
 static struct ubi_vtbl_record empty_vtbl_record;
 
 /**
+ * ubi_update_layout_vol - helper for updatting layout volumes on flash
+ * @ubi: UBI device description object
+ */
+static int ubi_update_layout_vol(struct ubi_device *ubi)
+{
+	struct ubi_volume *layout_vol;
+	int i, err;
+
+	layout_vol = ubi->volumes[vol_id2idx(ubi, UBI_LAYOUT_VOLUME_ID)];
+	for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) {
+		err = ubi_eba_atomic_leb_change(ubi, layout_vol, i, ubi->vtbl,
+						ubi->vtbl_size);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/**
  * ubi_change_vtbl_record - change volume table record.
  * @ubi: UBI device description object
  * @idx: table index to change
@@ -83,12 +103,10 @@ static struct ubi_vtbl_record empty_vtbl_record;
 int ubi_change_vtbl_record(struct ubi_device *ubi, int idx,
 			   struct ubi_vtbl_record *vtbl_rec)
 {
-	int i, err;
+	int err;
 	uint32_t crc;
-	struct ubi_volume *layout_vol;
 
 	ubi_assert(idx >= 0 && idx < ubi->vtbl_slots);
-	layout_vol = ubi->volumes[vol_id2idx(ubi, UBI_LAYOUT_VOLUME_ID)];
 
 	if (!vtbl_rec)
 		vtbl_rec = &empty_vtbl_record;
@@ -98,15 +116,10 @@ int ubi_change_vtbl_record(struct ubi_device *ubi, int idx,
 	}
 
 	memcpy(&ubi->vtbl[idx], vtbl_rec, sizeof(struct ubi_vtbl_record));
-	for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) {
-		err = ubi_eba_atomic_leb_change(ubi, layout_vol, i, ubi->vtbl,
-						ubi->vtbl_size);
-		if (err)
-			return err;
-	}
+	err = ubi_update_layout_vol(ubi);
 
 	self_vtbl_check(ubi);
-	return 0;
+	return err ? err : 0;
 }
 
 /**
@@ -121,9 +134,7 @@ int ubi_change_vtbl_record(struct ubi_device *ubi, int idx,
 int ubi_vtbl_rename_volumes(struct ubi_device *ubi,
 			    struct list_head *rename_list)
 {
-	int i, err;
 	struct ubi_rename_entry *re;
-	struct ubi_volume *layout_vol;
 
 	list_for_each_entry(re, rename_list, list) {
 		uint32_t crc;
@@ -145,15 +156,7 @@ int ubi_vtbl_rename_volumes(struct ubi_device *ubi,
 		vtbl_rec->crc = cpu_to_be32(crc);
 	}
 
-	layout_vol = ubi->volumes[vol_id2idx(ubi, UBI_LAYOUT_VOLUME_ID)];
-	for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) {
-		err = ubi_eba_atomic_leb_change(ubi, layout_vol, i, ubi->vtbl,
-						ubi->vtbl_size);
-		if (err)
-			return err;
-	}
-
-	return 0;
+	return ubi_update_layout_vol(ubi);
 }
 
 /**
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 16214d3d57a4..275d9fb6fe5c 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1581,7 +1581,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	dbg_wl("found %i PEBs", found_pebs);
 
 	if (ubi->fm) {
-		ubi_assert(ubi->good_peb_count == \
+		ubi_assert(ubi->good_peb_count ==
 			   found_pebs + ubi->fm->used_blocks);
 
 		for (i = 0; i < ubi->fm->used_blocks; i++) {
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index df51d6025a90..019fceffc9e5 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -179,6 +179,20 @@ config VXLAN
 	  To compile this driver as a module, choose M here: the module
 	  will be called vxlan.
 
+config GENEVE
+       tristate "Generic Network Virtualization Encapsulation netdev"
+       depends on INET && GENEVE_CORE
+       select NET_IP_TUNNEL
+       ---help---
+	  This allows one to create geneve virtual interfaces that provide
+	  Layer 2 Networks over Layer 3 Networks. GENEVE is often used
+	  to tunnel virtual network infrastructure in virtualized environments.
+	  For more information see:
+	    http://tools.ietf.org/html/draft-gross-geneve-02
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called geneve.
+
 config NETCONSOLE
 	tristate "Network console logging support"
 	---help---
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index e25fdd7d905e..c12cb22478a7 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_TUN) += tun.o
 obj-$(CONFIG_VETH) += veth.o
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
 obj-$(CONFIG_VXLAN) += vxlan.o
+obj-$(CONFIG_GENEVE) += geneve.o
 obj-$(CONFIG_NLMON) += nlmon.o
 
 #
diff --git a/drivers/net/arcnet/Kconfig b/drivers/net/arcnet/Kconfig
index 84fb6349a59a..2a9c3c3abe9b 100644
--- a/drivers/net/arcnet/Kconfig
+++ b/drivers/net/arcnet/Kconfig
@@ -15,10 +15,6 @@ menuconfig ARCNET
 	  COM90xx type card, so say Y (or M) to "ARCnet COM90xx chipset
 	  support" below.
 
-	  You might also want to have a look at the Ethernet-HOWTO, available
-	  from <http://www.tldp.org/docs.html#howto>(even though ARCnet
-	  is not really Ethernet).
-
 	  To compile this driver as a module, choose M here. The module will
 	  be called arcnet.
 
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index fbd54f0e32e8..7fde4d5c2b28 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -75,10 +75,10 @@
 /* Port Key definitions
  * key is determined according to the link speed, duplex and
  * user key (which is yet not supported)
- * --------------------------------------------------------------
- * Port key :	| User key	| Speed		| Duplex	|
- * --------------------------------------------------------------
- * 16		  6		  1		  0
+ *           --------------------------------------------------------------
+ * Port key  | User key (10 bits)           | Speed (5 bits)      | Duplex|
+ *           --------------------------------------------------------------
+ *           |15                           6|5                   1|0
  */
 #define  AD_DUPLEX_KEY_MASKS    0x1
 #define  AD_SPEED_KEY_MASKS     0x3E
@@ -1908,8 +1908,14 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution)
 
 		BOND_AD_INFO(bond).aggregator_identifier = 0;
 
-		BOND_AD_INFO(bond).system.sys_priority = 0xFFFF;
-		BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr);
+		BOND_AD_INFO(bond).system.sys_priority =
+			bond->params.ad_actor_sys_prio;
+		if (is_zero_ether_addr(bond->params.ad_actor_system))
+			BOND_AD_INFO(bond).system.sys_mac_addr =
+			    *((struct mac_addr *)bond->dev->dev_addr);
+		else
+			BOND_AD_INFO(bond).system.sys_mac_addr =
+			    *((struct mac_addr *)bond->params.ad_actor_system);
 
 		/* initialize how many times this module is called in one
 		 * second (should be about every 100ms)
@@ -1945,10 +1951,10 @@ void bond_3ad_bind_slave(struct slave *slave)
 
 		port->slave = slave;
 		port->actor_port_number = SLAVE_AD_INFO(slave)->id;
-		/* key is determined according to the link speed, duplex and user key(which
-		 * is yet not supported)
+		/* key is determined according to the link speed, duplex and
+		 * user key
 		 */
-		port->actor_admin_port_key = 0;
+		port->actor_admin_port_key = bond->params.ad_user_port_key << 6;
 		port->actor_admin_port_key |= __get_duplex(port);
 		port->actor_admin_port_key |= (__get_link_speed(port) << 1);
 		port->actor_oper_port_key = port->actor_admin_port_key;
@@ -1959,6 +1965,8 @@ void bond_3ad_bind_slave(struct slave *slave)
 			port->sm_vars &= ~AD_PORT_LACP_ENABLED;
 		/* actor system is the bond's system */
 		port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr;
+		port->actor_system_priority =
+		    BOND_AD_INFO(bond).system.sys_priority;
 		/* tx timer(to verify that no more than MAX_TX_IN_SECOND
 		 * lacpdu's are sent in one second)
 		 */
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d5fe5d5f490f..19eb990d398c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -76,7 +76,7 @@
 #include <net/netns/generic.h>
 #include <net/pkt_sched.h>
 #include <linux/rculist.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 #include <net/switchdev.h>
 #include <net/bonding.h>
 #include <net/bond_3ad.h>
@@ -1015,10 +1015,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 	netdev_features_t mask;
 	struct slave *slave;
 
-	/* If any slave has the offload feature flag set,
-	 * set the offload flag on the bond.
-	 */
-	mask = features | NETIF_F_HW_SWITCH_OFFLOAD;
+	mask = features;
 
 	features &= ~NETIF_F_ONE_FOR_ALL;
 	features |= NETIF_F_ALL_FOR_ALL;
@@ -3054,16 +3051,15 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 	int noff, proto = -1;
 
 	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
-		return skb_flow_dissect(skb, fk);
+		return skb_flow_dissect_flow_keys(skb, fk);
 
-	fk->ports = 0;
+	fk->ports.ports = 0;
 	noff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
 			return false;
 		iph = ip_hdr(skb);
-		fk->src = iph->saddr;
-		fk->dst = iph->daddr;
+		iph_to_flow_copy_v4addrs(fk, iph);
 		noff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
 			proto = iph->protocol;
@@ -3071,15 +3067,14 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
 			return false;
 		iph6 = ipv6_hdr(skb);
-		fk->src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
-		fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
+		iph_to_flow_copy_v6addrs(fk, iph6);
 		noff += sizeof(*iph6);
 		proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
-		fk->ports = skb_flow_get_ports(skb, noff, proto);
+		fk->ports.ports = skb_flow_get_ports(skb, noff, proto);
 
 	return true;
 }
@@ -3105,8 +3100,9 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
 		hash = bond_eth_hash(skb);
 	else
-		hash = (__force u32)flow.ports;
-	hash ^= (__force u32)flow.dst ^ (__force u32)flow.src;
+		hash = (__force u32)flow.ports.ports;
+	hash ^= (__force u32)flow_get_u32_dst(&flow) ^
+		(__force u32)flow_get_u32_src(&flow);
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 
@@ -4039,8 +4035,12 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_add_slave		= bond_enslave,
 	.ndo_del_slave		= bond_release,
 	.ndo_fix_features	= bond_fix_features,
-	.ndo_bridge_setlink	= ndo_dflt_netdev_switch_port_bridge_setlink,
-	.ndo_bridge_dellink	= ndo_dflt_netdev_switch_port_bridge_dellink,
+	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
+	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
+	.ndo_bridge_dellink	= switchdev_port_bridge_dellink,
+	.ndo_fdb_add		= switchdev_port_fdb_add,
+	.ndo_fdb_del		= switchdev_port_fdb_del,
+	.ndo_fdb_dump		= switchdev_port_fdb_dump,
 	.ndo_features_check	= passthru_features_check,
 };
 
@@ -4140,6 +4140,8 @@ static int bond_check_params(struct bond_params *params)
 	struct bond_opt_value newval;
 	const struct bond_opt_value *valptr;
 	int arp_all_targets_value;
+	u16 ad_actor_sys_prio = 0;
+	u16 ad_user_port_key = 0;
 
 	/* Convert string parameters. */
 	if (mode) {
@@ -4434,6 +4436,24 @@ static int bond_check_params(struct bond_params *params)
 		fail_over_mac_value = BOND_FOM_NONE;
 	}
 
+	bond_opt_initstr(&newval, "default");
+	valptr = bond_opt_parse(
+			bond_opt_get(BOND_OPT_AD_ACTOR_SYS_PRIO),
+				     &newval);
+	if (!valptr) {
+		pr_err("Error: No ad_actor_sys_prio default value");
+		return -EINVAL;
+	}
+	ad_actor_sys_prio = valptr->value;
+
+	valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_USER_PORT_KEY),
+				&newval);
+	if (!valptr) {
+		pr_err("Error: No ad_user_port_key default value");
+		return -EINVAL;
+	}
+	ad_user_port_key = valptr->value;
+
 	if (lp_interval == 0) {
 		pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n",
 			INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL);
@@ -4462,6 +4482,9 @@ static int bond_check_params(struct bond_params *params)
 	params->lp_interval = lp_interval;
 	params->packets_per_slave = packets_per_slave;
 	params->tlb_dynamic_lb = 1; /* Default value */
+	params->ad_actor_sys_prio = ad_actor_sys_prio;
+	eth_zero_addr(params->ad_actor_system);
+	params->ad_user_port_key = ad_user_port_key;
 	if (packets_per_slave > 0) {
 		params->reciprocal_packets_per_slave =
 			reciprocal_value(packets_per_slave);
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 7b1124366011..1bda29249d12 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -28,6 +28,8 @@ static size_t bond_get_slave_size(const struct net_device *bond_dev,
 		nla_total_size(MAX_ADDR_LEN) +	/* IFLA_BOND_SLAVE_PERM_HWADDR */
 		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_QUEUE_ID */
 		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */
+		nla_total_size(sizeof(u8)) +	/* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */
+		nla_total_size(sizeof(u16)) +	/* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */
 		0;
 }
 
@@ -56,12 +58,23 @@ static int bond_fill_slave_info(struct sk_buff *skb,
 
 	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
 		const struct aggregator *agg;
+		const struct port *ad_port;
 
+		ad_port = &SLAVE_AD_INFO(slave)->port;
 		agg = SLAVE_AD_INFO(slave)->port.aggregator;
-		if (agg)
+		if (agg) {
 			if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 					agg->aggregator_identifier))
 				goto nla_put_failure;
+			if (nla_put_u8(skb,
+				       IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE,
+				       ad_port->actor_oper_port_state))
+				goto nla_put_failure;
+			if (nla_put_u16(skb,
+					IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE,
+					ad_port->partner_oper.port_state))
+				goto nla_put_failure;
+		}
 	}
 
 	return 0;
@@ -94,6 +107,10 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = {
 	[IFLA_BOND_AD_LACP_RATE]	= { .type = NLA_U8 },
 	[IFLA_BOND_AD_SELECT]		= { .type = NLA_U8 },
 	[IFLA_BOND_AD_INFO]		= { .type = NLA_NESTED },
+	[IFLA_BOND_AD_ACTOR_SYS_PRIO]	= { .type = NLA_U16 },
+	[IFLA_BOND_AD_USER_PORT_KEY]	= { .type = NLA_U16 },
+	[IFLA_BOND_AD_ACTOR_SYSTEM]	= { .type = NLA_BINARY,
+					    .len  = ETH_ALEN },
 };
 
 static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = {
@@ -379,6 +396,36 @@ static int bond_changelink(struct net_device *bond_dev,
 		if (err)
 			return err;
 	}
+	if (data[IFLA_BOND_AD_ACTOR_SYS_PRIO]) {
+		int actor_sys_prio =
+			nla_get_u16(data[IFLA_BOND_AD_ACTOR_SYS_PRIO]);
+
+		bond_opt_initval(&newval, actor_sys_prio);
+		err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYS_PRIO, &newval);
+		if (err)
+			return err;
+	}
+
+	if (data[IFLA_BOND_AD_USER_PORT_KEY]) {
+		int port_key =
+			nla_get_u16(data[IFLA_BOND_AD_USER_PORT_KEY]);
+
+		bond_opt_initval(&newval, port_key);
+		err = __bond_opt_set(bond, BOND_OPT_AD_USER_PORT_KEY, &newval);
+		if (err)
+			return err;
+	}
+
+	if (data[IFLA_BOND_AD_ACTOR_SYSTEM]) {
+		if (nla_len(data[IFLA_BOND_AD_ACTOR_SYSTEM]) != ETH_ALEN)
+			return -EINVAL;
+
+		bond_opt_initval(&newval,
+				 nla_get_be64(data[IFLA_BOND_AD_ACTOR_SYSTEM]));
+		err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval);
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
@@ -426,6 +473,9 @@ static size_t bond_get_size(const struct net_device *bond_dev)
 		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_ACTOR_KEY */
 		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_PARTNER_KEY*/
 		nla_total_size(ETH_ALEN) +    /* IFLA_BOND_AD_INFO_PARTNER_MAC*/
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_ACTOR_SYS_PRIO */
+		nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_USER_PORT_KEY */
+		nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */
 		0;
 }
 
@@ -551,6 +601,20 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info info;
 
+		if (capable(CAP_NET_ADMIN)) {
+			if (nla_put_u16(skb, IFLA_BOND_AD_ACTOR_SYS_PRIO,
+					bond->params.ad_actor_sys_prio))
+				goto nla_put_failure;
+
+			if (nla_put_u16(skb, IFLA_BOND_AD_USER_PORT_KEY,
+					bond->params.ad_user_port_key))
+				goto nla_put_failure;
+
+			if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM,
+				    sizeof(bond->params.ad_actor_system),
+				    &bond->params.ad_actor_system))
+				goto nla_put_failure;
+		}
 		if (!bond_3ad_get_active_agg_info(bond, &info)) {
 			struct nlattr *nest;
 
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 4df28943d222..e9c624d54dd4 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -70,6 +70,12 @@ static int bond_option_slaves_set(struct bonding *bond,
 				  const struct bond_opt_value *newval);
 static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
 				  const struct bond_opt_value *newval);
+static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
+					     const struct bond_opt_value *newval);
+static int bond_option_ad_actor_system_set(struct bonding *bond,
+					   const struct bond_opt_value *newval);
+static int bond_option_ad_user_port_key_set(struct bonding *bond,
+					    const struct bond_opt_value *newval);
 
 
 static const struct bond_opt_value bond_mode_tbl[] = {
@@ -186,6 +192,18 @@ static const struct bond_opt_value bond_tlb_dynamic_lb_tbl[] = {
 	{ NULL,  -1, 0}
 };
 
+static const struct bond_opt_value bond_ad_actor_sys_prio_tbl[] = {
+	{ "minval",  1,     BOND_VALFLAG_MIN},
+	{ "maxval",  65535, BOND_VALFLAG_MAX | BOND_VALFLAG_DEFAULT},
+	{ NULL,      -1,    0},
+};
+
+static const struct bond_opt_value bond_ad_user_port_key_tbl[] = {
+	{ "minval",  0,     BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT},
+	{ "maxval",  1023,  BOND_VALFLAG_MAX},
+	{ NULL,      -1,    0},
+};
+
 static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 	[BOND_OPT_MODE] = {
 		.id = BOND_OPT_MODE,
@@ -379,6 +397,29 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = {
 		.values = bond_tlb_dynamic_lb_tbl,
 		.flags = BOND_OPTFLAG_IFDOWN,
 		.set = bond_option_tlb_dynamic_lb_set,
+	},
+	[BOND_OPT_AD_ACTOR_SYS_PRIO] = {
+		.id = BOND_OPT_AD_ACTOR_SYS_PRIO,
+		.name = "ad_actor_sys_prio",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.flags = BOND_OPTFLAG_IFDOWN,
+		.values = bond_ad_actor_sys_prio_tbl,
+		.set = bond_option_ad_actor_sys_prio_set,
+	},
+	[BOND_OPT_AD_ACTOR_SYSTEM] = {
+		.id = BOND_OPT_AD_ACTOR_SYSTEM,
+		.name = "ad_actor_system",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.flags = BOND_OPTFLAG_RAWVAL | BOND_OPTFLAG_IFDOWN,
+		.set = bond_option_ad_actor_system_set,
+	},
+	[BOND_OPT_AD_USER_PORT_KEY] = {
+		.id = BOND_OPT_AD_USER_PORT_KEY,
+		.name = "ad_user_port_key",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)),
+		.flags = BOND_OPTFLAG_IFDOWN,
+		.values = bond_ad_user_port_key_tbl,
+		.set = bond_option_ad_user_port_key_set,
 	}
 };
 
@@ -624,7 +665,7 @@ int __bond_opt_set(struct bonding *bond,
 out:
 	if (ret)
 		bond_opt_error_interpret(bond, opt, ret, val);
-	else
+	else if (bond->dev->reg_state == NETREG_REGISTERED)
 		call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev);
 
 	return ret;
@@ -1349,3 +1390,53 @@ static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
 
 	return 0;
 }
+
+static int bond_option_ad_actor_sys_prio_set(struct bonding *bond,
+					     const struct bond_opt_value *newval)
+{
+	netdev_info(bond->dev, "Setting ad_actor_sys_prio to %llu\n",
+		    newval->value);
+
+	bond->params.ad_actor_sys_prio = newval->value;
+	return 0;
+}
+
+static int bond_option_ad_actor_system_set(struct bonding *bond,
+					   const struct bond_opt_value *newval)
+{
+	u8 macaddr[ETH_ALEN];
+	u8 *mac;
+	int i;
+
+	if (newval->string) {
+		i = sscanf(newval->string, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+			   &macaddr[0], &macaddr[1], &macaddr[2],
+			   &macaddr[3], &macaddr[4], &macaddr[5]);
+		if (i != ETH_ALEN)
+			goto err;
+		mac = macaddr;
+	} else {
+		mac = (u8 *)&newval->value;
+	}
+
+	if (!is_valid_ether_addr(mac))
+		goto err;
+
+	netdev_info(bond->dev, "Setting ad_actor_system to %pM\n", mac);
+	ether_addr_copy(bond->params.ad_actor_system, mac);
+	return 0;
+
+err:
+	netdev_err(bond->dev, "Invalid MAC address.\n");
+	return -EINVAL;
+}
+
+static int bond_option_ad_user_port_key_set(struct bonding *bond,
+					    const struct bond_opt_value *newval)
+{
+	netdev_info(bond->dev, "Setting ad_user_port_key to %llu\n",
+		    newval->value);
+
+	bond->params.ad_user_port_key = newval->value;
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index b20b35acb47d..f514fe5e80a5 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -135,23 +135,30 @@ static void bond_info_show_master(struct seq_file *seq)
 					  bond->params.ad_select);
 		seq_printf(seq, "Aggregator selection policy (ad_select): %s\n",
 			   optval->string);
-
-		if (__bond_3ad_get_active_agg_info(bond, &ad_info)) {
-			seq_printf(seq, "bond %s has no active aggregator\n",
-				   bond->dev->name);
-		} else {
-			seq_printf(seq, "Active Aggregator Info:\n");
-
-			seq_printf(seq, "\tAggregator ID: %d\n",
-				   ad_info.aggregator_id);
-			seq_printf(seq, "\tNumber of ports: %d\n",
-				   ad_info.ports);
-			seq_printf(seq, "\tActor Key: %d\n",
-				   ad_info.actor_key);
-			seq_printf(seq, "\tPartner Key: %d\n",
-				   ad_info.partner_key);
-			seq_printf(seq, "\tPartner Mac Address: %pM\n",
-				   ad_info.partner_system);
+		if (capable(CAP_NET_ADMIN)) {
+			seq_printf(seq, "System priority: %d\n",
+				   BOND_AD_INFO(bond).system.sys_priority);
+			seq_printf(seq, "System MAC address: %pM\n",
+				   &BOND_AD_INFO(bond).system.sys_mac_addr);
+
+			if (__bond_3ad_get_active_agg_info(bond, &ad_info)) {
+				seq_printf(seq,
+					   "bond %s has no active aggregator\n",
+					   bond->dev->name);
+			} else {
+				seq_printf(seq, "Active Aggregator Info:\n");
+
+				seq_printf(seq, "\tAggregator ID: %d\n",
+					   ad_info.aggregator_id);
+				seq_printf(seq, "\tNumber of ports: %d\n",
+					   ad_info.ports);
+				seq_printf(seq, "\tActor Key: %d\n",
+					   ad_info.actor_key);
+				seq_printf(seq, "\tPartner Key: %d\n",
+					   ad_info.partner_key);
+				seq_printf(seq, "\tPartner Mac Address: %pM\n",
+					   ad_info.partner_system);
+			}
 		}
 	}
 }
@@ -195,29 +202,35 @@ static void bond_info_show_slave(struct seq_file *seq,
 			seq_printf(seq, "Partner Churned Count: %d\n",
 				   port->churn_partner_count);
 
-			seq_puts(seq, "details actor lacp pdu:\n");
-			seq_printf(seq, "    system priority: %d\n",
-				   port->actor_system_priority);
-			seq_printf(seq, "    port key: %d\n",
-				   port->actor_oper_port_key);
-			seq_printf(seq, "    port priority: %d\n",
-				   port->actor_port_priority);
-			seq_printf(seq, "    port number: %d\n",
-				   port->actor_port_number);
-			seq_printf(seq, "    port state: %d\n",
-				   port->actor_oper_port_state);
-
-			seq_puts(seq, "details partner lacp pdu:\n");
-			seq_printf(seq, "    system priority: %d\n",
-				   port->partner_oper.system_priority);
-			seq_printf(seq, "    oper key: %d\n",
-				   port->partner_oper.key);
-			seq_printf(seq, "    port priority: %d\n",
-				   port->partner_oper.port_priority);
-			seq_printf(seq, "    port number: %d\n",
-				   port->partner_oper.port_number);
-			seq_printf(seq, "    port state: %d\n",
-				   port->partner_oper.port_state);
+			if (capable(CAP_NET_ADMIN)) {
+				seq_puts(seq, "details actor lacp pdu:\n");
+				seq_printf(seq, "    system priority: %d\n",
+					   port->actor_system_priority);
+				seq_printf(seq, "    system mac address: %pM\n",
+					   &port->actor_system);
+				seq_printf(seq, "    port key: %d\n",
+					   port->actor_oper_port_key);
+				seq_printf(seq, "    port priority: %d\n",
+					   port->actor_port_priority);
+				seq_printf(seq, "    port number: %d\n",
+					   port->actor_port_number);
+				seq_printf(seq, "    port state: %d\n",
+					   port->actor_oper_port_state);
+
+				seq_puts(seq, "details partner lacp pdu:\n");
+				seq_printf(seq, "    system priority: %d\n",
+					   port->partner_oper.system_priority);
+				seq_printf(seq, "    system mac address: %pM\n",
+					   &port->partner_oper.system);
+				seq_printf(seq, "    oper key: %d\n",
+					   port->partner_oper.key);
+				seq_printf(seq, "    port priority: %d\n",
+					   port->partner_oper.port_priority);
+				seq_printf(seq, "    port number: %d\n",
+					   port->partner_oper.port_number);
+				seq_printf(seq, "    port state: %d\n",
+					   port->partner_oper.port_state);
+			}
 		} else {
 			seq_puts(seq, "Aggregator ID: N/A\n");
 		}
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 7e9e151d4d61..31835a4dab57 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -549,7 +549,7 @@ static ssize_t bonding_show_ad_actor_key(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -569,7 +569,7 @@ static ssize_t bonding_show_ad_partner_key(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -589,7 +589,7 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) {
 		struct ad_info ad_info;
 		if (!bond_3ad_get_active_agg_info(bond, &ad_info))
 			count = sprintf(buf, "%pM\n", ad_info.partner_system);
@@ -692,6 +692,49 @@ static ssize_t bonding_show_packets_per_slave(struct device *d,
 static DEVICE_ATTR(packets_per_slave, S_IRUGO | S_IWUSR,
 		   bonding_show_packets_per_slave, bonding_sysfs_store_option);
 
+static ssize_t bonding_show_ad_actor_sys_prio(struct device *d,
+					      struct device_attribute *attr,
+					      char *buf)
+{
+	struct bonding *bond = to_bond(d);
+
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN))
+		return sprintf(buf, "%hu\n", bond->params.ad_actor_sys_prio);
+
+	return 0;
+}
+static DEVICE_ATTR(ad_actor_sys_prio, S_IRUGO | S_IWUSR,
+		   bonding_show_ad_actor_sys_prio, bonding_sysfs_store_option);
+
+static ssize_t bonding_show_ad_actor_system(struct device *d,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct bonding *bond = to_bond(d);
+
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN))
+		return sprintf(buf, "%pM\n", bond->params.ad_actor_system);
+
+	return 0;
+}
+
+static DEVICE_ATTR(ad_actor_system, S_IRUGO | S_IWUSR,
+		   bonding_show_ad_actor_system, bonding_sysfs_store_option);
+
+static ssize_t bonding_show_ad_user_port_key(struct device *d,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	struct bonding *bond = to_bond(d);
+
+	if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN))
+		return sprintf(buf, "%hu\n", bond->params.ad_user_port_key);
+
+	return 0;
+}
+static DEVICE_ATTR(ad_user_port_key, S_IRUGO | S_IWUSR,
+		   bonding_show_ad_user_port_key, bonding_sysfs_store_option);
+
 static struct attribute *per_bond_attrs[] = {
 	&dev_attr_slaves.attr,
 	&dev_attr_mode.attr,
@@ -725,6 +768,9 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_lp_interval.attr,
 	&dev_attr_packets_per_slave.attr,
 	&dev_attr_tlb_dynamic_lb.attr,
+	&dev_attr_ad_actor_sys_prio.attr,
+	&dev_attr_ad_actor_system.attr,
+	&dev_attr_ad_user_port_key.attr,
 	NULL,
 };
 
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 23618a831612..7d16c51e6913 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -80,6 +80,36 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf)
 }
 static SLAVE_ATTR_RO(ad_aggregator_id);
 
+static ssize_t ad_actor_oper_port_state_show(struct slave *slave, char *buf)
+{
+	const struct port *ad_port;
+
+	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
+		ad_port = &SLAVE_AD_INFO(slave)->port;
+		if (ad_port->aggregator)
+			return sprintf(buf, "%u\n",
+				       ad_port->actor_oper_port_state);
+	}
+
+	return sprintf(buf, "N/A\n");
+}
+static SLAVE_ATTR_RO(ad_actor_oper_port_state);
+
+static ssize_t ad_partner_oper_port_state_show(struct slave *slave, char *buf)
+{
+	const struct port *ad_port;
+
+	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
+		ad_port = &SLAVE_AD_INFO(slave)->port;
+		if (ad_port->aggregator)
+			return sprintf(buf, "%u\n",
+				       ad_port->partner_oper.port_state);
+	}
+
+	return sprintf(buf, "N/A\n");
+}
+static SLAVE_ATTR_RO(ad_partner_oper_port_state);
+
 static const struct slave_attribute *slave_attrs[] = {
 	&slave_attr_state,
 	&slave_attr_mii_status,
@@ -87,6 +117,8 @@ static const struct slave_attribute *slave_attrs[] = {
 	&slave_attr_perm_hwaddr,
 	&slave_attr_queue_id,
 	&slave_attr_ad_aggregator_id,
+	&slave_attr_ad_actor_oper_port_state,
+	&slave_attr_ad_partner_oper_port_state,
 	NULL
 };
 
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index b0f69248cb71..e9b1810d319f 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -440,6 +440,9 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx)
 		struct can_frame *cf = (struct can_frame *)skb->data;
 		u8 dlc = cf->can_dlc;
 
+		if (!(skb->tstamp.tv64))
+			__net_timestamp(skb);
+
 		netif_rx(priv->echo_skb[idx]);
 		priv->echo_skb[idx] = NULL;
 
@@ -575,6 +578,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
 	if (unlikely(!skb))
 		return NULL;
 
+	__net_timestamp(skb);
 	skb->protocol = htons(ETH_P_CAN);
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -603,6 +607,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev,
 	if (unlikely(!skb))
 		return NULL;
 
+	__net_timestamp(skb);
 	skb->protocol = htons(ETH_P_CANFD);
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index ad0a7e8c2c2b..6201c5a1a884 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -93,13 +93,13 @@
 	(FLEXCAN_CTRL_ERR_BUS | FLEXCAN_CTRL_ERR_STATE)
 
 /* FLEXCAN control register 2 (CTRL2) bits */
-#define FLEXCAN_CRL2_ECRWRE		BIT(29)
-#define FLEXCAN_CRL2_WRMFRZ		BIT(28)
-#define FLEXCAN_CRL2_RFFN(x)		(((x) & 0x0f) << 24)
-#define FLEXCAN_CRL2_TASD(x)		(((x) & 0x1f) << 19)
-#define FLEXCAN_CRL2_MRP		BIT(18)
-#define FLEXCAN_CRL2_RRS		BIT(17)
-#define FLEXCAN_CRL2_EACEN		BIT(16)
+#define FLEXCAN_CTRL2_ECRWRE		BIT(29)
+#define FLEXCAN_CTRL2_WRMFRZ		BIT(28)
+#define FLEXCAN_CTRL2_RFFN(x)		(((x) & 0x0f) << 24)
+#define FLEXCAN_CTRL2_TASD(x)		(((x) & 0x1f) << 19)
+#define FLEXCAN_CTRL2_MRP		BIT(18)
+#define FLEXCAN_CTRL2_RRS		BIT(17)
+#define FLEXCAN_CTRL2_EACEN		BIT(16)
 
 /* FLEXCAN memory error control register (MECR) bits */
 #define FLEXCAN_MECR_ECRWRDIS		BIT(31)
@@ -158,7 +158,6 @@
 	 FLEXCAN_IFLAG_BUF(FLEXCAN_TX_BUF_ID))
 
 /* FLEXCAN message buffers */
-#define FLEXCAN_MB_CNT_CODE(x)		(((x) & 0xf) << 24)
 #define FLEXCAN_MB_CODE_RX_INACTIVE	(0x0 << 24)
 #define FLEXCAN_MB_CODE_RX_EMPTY	(0x4 << 24)
 #define FLEXCAN_MB_CODE_RX_FULL		(0x2 << 24)
@@ -184,14 +183,14 @@
  * FLEXCAN hardware feature flags
  *
  * Below is some version info we got:
- *    SOC   Version   IP-Version  Glitch-  [TR]WRN_INT  Memory err
- *                                Filter?   connected?  detection
- *   MX25  FlexCAN2  03.00.00.00     no         no         no
- *   MX28  FlexCAN2  03.00.04.00    yes        yes         no
- *   MX35  FlexCAN2  03.00.00.00     no         no         no
- *   MX53  FlexCAN2  03.00.00.00    yes         no         no
- *   MX6s  FlexCAN3  10.00.12.00    yes        yes         no
- *   VF610 FlexCAN3  ?               no        yes        yes
+ *    SOC   Version   IP-Version  Glitch- [TR]WRN_INT Memory err RTR re-
+ *                                Filter? connected?  detection  ception in MB
+ *   MX25  FlexCAN2  03.00.00.00     no        no         no        no
+ *   MX28  FlexCAN2  03.00.04.00    yes       yes         no        no
+ *   MX35  FlexCAN2  03.00.00.00     no        no         no        no
+ *   MX53  FlexCAN2  03.00.00.00    yes        no         no        no
+ *   MX6s  FlexCAN3  10.00.12.00    yes       yes         no       yes
+ *   VF610 FlexCAN3  ?               no       yes        yes       yes?
  *
  * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected.
  */
@@ -221,7 +220,7 @@ struct flexcan_regs {
 	u32 imask1;		/* 0x28 */
 	u32 iflag2;		/* 0x2c */
 	u32 iflag1;		/* 0x30 */
-	u32 crl2;		/* 0x34 */
+	u32 ctrl2;		/* 0x34 */
 	u32 esr2;		/* 0x38 */
 	u32 imeur;		/* 0x3c */
 	u32 lrfr;		/* 0x40 */
@@ -230,6 +229,16 @@ struct flexcan_regs {
 	u32 rxfir;		/* 0x4c */
 	u32 _reserved3[12];	/* 0x50 */
 	struct flexcan_mb cantxfg[64];	/* 0x80 */
+	/* FIFO-mode:
+	 *			MB
+	 * 0x080...0x08f	0	RX message buffer
+	 * 0x090...0x0df	1-5	reserverd
+	 * 0x0e0...0x0ff	6-7	8 entry ID table
+	 *				(mx25, mx28, mx35, mx53)
+	 * 0x0e0...0x2df	6-7..37	8..128 entry ID table
+	 *			  	size conf'ed via ctrl2::RFFN
+	 *				(mx6, vf610)
+	 */
 	u32 _reserved4[408];
 	u32 mecr;		/* 0xae0 */
 	u32 erriar;		/* 0xae4 */
@@ -468,7 +477,7 @@ static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct flexcan_regs __iomem *regs = priv->base;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 can_id;
-	u32 ctrl = FLEXCAN_MB_CNT_CODE(0xc) | (cf->can_dlc << 16);
+	u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | (cf->can_dlc << 16);
 
 	if (can_dropped_invalid_skb(dev, skb))
 		return NETDEV_TX_OK;
@@ -815,7 +824,7 @@ static int flexcan_chip_start(struct net_device *dev)
 {
 	struct flexcan_priv *priv = netdev_priv(dev);
 	struct flexcan_regs __iomem *regs = priv->base;
-	u32 reg_mcr, reg_ctrl, reg_crl2, reg_mecr;
+	u32 reg_mcr, reg_ctrl, reg_ctrl2, reg_mecr;
 	int err, i;
 
 	/* enable module */
@@ -918,9 +927,9 @@ static int flexcan_chip_start(struct net_device *dev)
 		 * and Correction of Memory Errors" to write to
 		 * MECR register
 		 */
-		reg_crl2 = flexcan_read(&regs->crl2);
-		reg_crl2 |= FLEXCAN_CRL2_ECRWRE;
-		flexcan_write(reg_crl2, &regs->crl2);
+		reg_ctrl2 = flexcan_read(&regs->ctrl2);
+		reg_ctrl2 |= FLEXCAN_CTRL2_ECRWRE;
+		flexcan_write(reg_ctrl2, &regs->ctrl2);
 
 		reg_mecr = flexcan_read(&regs->mecr);
 		reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS;
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index 4dd183a3643a..c1e85368a198 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -40,6 +40,7 @@
 #define MSYNC_PEER		0x00		/* ICAN only */
 #define MSYNC_LOCL		0x01		/* host only */
 #define TARGET_RUNNING		0x02
+#define FIRMWARE_STAMP		0x60		/* big endian firmware stamp */
 
 #define MSYNC_RB0		0x01
 #define MSYNC_RB1		0x02
@@ -83,6 +84,7 @@
 #define MSG_COFFREQ		0x42
 #define MSG_CONREQ		0x43
 #define MSG_CCONFREQ		0x47
+#define MSG_LMTS		0xb4
 
 /*
  * Janz ICAN3 CAN Inquiry Message Types
@@ -165,6 +167,12 @@
 /* SJA1000 Clock Input */
 #define ICAN3_CAN_CLOCK		8000000
 
+/* Janz ICAN3 firmware types */
+enum ican3_fwtype {
+	ICAN3_FWTYPE_ICANOS,
+	ICAN3_FWTYPE_CAL_CANOPEN,
+};
+
 /* Driver Name */
 #define DRV_NAME "janz-ican3"
 
@@ -215,6 +223,10 @@ struct ican3_dev {
 	struct completion buserror_comp;
 	struct can_berr_counter bec;
 
+	/* firmware type */
+	enum ican3_fwtype fwtype;
+	char fwinfo[32];
+
 	/* old and new style host interface */
 	unsigned int iftype;
 
@@ -750,13 +762,61 @@ static int ican3_set_id_filter(struct ican3_dev *mod, bool accept)
  */
 static int ican3_set_bus_state(struct ican3_dev *mod, bool on)
 {
+	struct can_bittiming *bt = &mod->can.bittiming;
 	struct ican3_msg msg;
+	u8 btr0, btr1;
+	int res;
 
-	memset(&msg, 0, sizeof(msg));
-	msg.spec = on ? MSG_CONREQ : MSG_COFFREQ;
-	msg.len = cpu_to_le16(0);
+	/* This algorithm was stolen from drivers/net/can/sja1000/sja1000.c      */
+	/* The bittiming register command for the ICAN3 just sets the bit timing */
+	/* registers on the SJA1000 chip directly                                */
+	btr0 = ((bt->brp - 1) & 0x3f) | (((bt->sjw - 1) & 0x3) << 6);
+	btr1 = ((bt->prop_seg + bt->phase_seg1 - 1) & 0xf) |
+		(((bt->phase_seg2 - 1) & 0x7) << 4);
+	if (mod->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		btr1 |= 0x80;
 
-	return ican3_send_msg(mod, &msg);
+	if (mod->fwtype == ICAN3_FWTYPE_ICANOS) {
+		if (on) {
+			/* set bittiming */
+			memset(&msg, 0, sizeof(msg));
+			msg.spec = MSG_CBTRREQ;
+			msg.len = cpu_to_le16(4);
+			msg.data[0] = 0x00;
+			msg.data[1] = 0x00;
+			msg.data[2] = btr0;
+			msg.data[3] = btr1;
+
+			res = ican3_send_msg(mod, &msg);
+			if (res)
+				return res;
+		}
+
+		/* can-on/off request */
+		memset(&msg, 0, sizeof(msg));
+		msg.spec = on ? MSG_CONREQ : MSG_COFFREQ;
+		msg.len = cpu_to_le16(0);
+
+		return ican3_send_msg(mod, &msg);
+
+	} else if (mod->fwtype == ICAN3_FWTYPE_CAL_CANOPEN) {
+		memset(&msg, 0, sizeof(msg));
+		msg.spec = MSG_LMTS;
+		if (on) {
+			msg.len = cpu_to_le16(4);
+			msg.data[0] = 0;
+			msg.data[1] = 0;
+			msg.data[2] = btr0;
+			msg.data[3] = btr1;
+		} else {
+			msg.len = cpu_to_le16(2);
+			msg.data[0] = 1;
+			msg.data[1] = 0;
+		}
+
+		return ican3_send_msg(mod, &msg);
+	}
+	return -ENOTSUPP;
 }
 
 static int ican3_set_termination(struct ican3_dev *mod, bool on)
@@ -1402,7 +1462,7 @@ static int ican3_reset_module(struct ican3_dev *mod)
 			return 0;
 
 		msleep(10);
-	} while (time_before(jiffies, start + HZ / 4));
+	} while (time_before(jiffies, start + HZ / 2));
 
 	netdev_err(mod->ndev, "failed to reset CAN module\n");
 	return -ETIMEDOUT;
@@ -1427,6 +1487,17 @@ static int ican3_startup_module(struct ican3_dev *mod)
 		return ret;
 	}
 
+	/* detect firmware */
+	memcpy_fromio(mod->fwinfo, mod->dpm + FIRMWARE_STAMP, sizeof(mod->fwinfo) - 1);
+	if (strncmp(mod->fwinfo, "JANZ-ICAN3", 10)) {
+		netdev_err(mod->ndev, "ICAN3 not detected (found %s)\n", mod->fwinfo);
+		return -ENODEV;
+	}
+	if (strstr(mod->fwinfo, "CAL/CANopen"))
+		mod->fwtype = ICAN3_FWTYPE_CAL_CANOPEN;
+	else
+		mod->fwtype = ICAN3_FWTYPE_ICANOS;
+
 	/* re-enable interrupts so we can send messages */
 	iowrite8(1 << mod->num, &mod->ctrl->int_enable);
 
@@ -1615,36 +1686,6 @@ static const struct can_bittiming_const ican3_bittiming_const = {
 	.brp_inc = 1,
 };
 
-/*
- * This routine was stolen from drivers/net/can/sja1000/sja1000.c
- *
- * The bittiming register command for the ICAN3 just sets the bit timing
- * registers on the SJA1000 chip directly
- */
-static int ican3_set_bittiming(struct net_device *ndev)
-{
-	struct ican3_dev *mod = netdev_priv(ndev);
-	struct can_bittiming *bt = &mod->can.bittiming;
-	struct ican3_msg msg;
-	u8 btr0, btr1;
-
-	btr0 = ((bt->brp - 1) & 0x3f) | (((bt->sjw - 1) & 0x3) << 6);
-	btr1 = ((bt->prop_seg + bt->phase_seg1 - 1) & 0xf) |
-		(((bt->phase_seg2 - 1) & 0x7) << 4);
-	if (mod->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
-		btr1 |= 0x80;
-
-	memset(&msg, 0, sizeof(msg));
-	msg.spec = MSG_CBTRREQ;
-	msg.len = cpu_to_le16(4);
-	msg.data[0] = 0x00;
-	msg.data[1] = 0x00;
-	msg.data[2] = btr0;
-	msg.data[3] = btr1;
-
-	return ican3_send_msg(mod, &msg);
-}
-
 static int ican3_set_mode(struct net_device *ndev, enum can_mode mode)
 {
 	struct ican3_dev *mod = netdev_priv(ndev);
@@ -1730,11 +1771,22 @@ static ssize_t ican3_sysfs_set_term(struct device *dev,
 	return count;
 }
 
+static ssize_t ican3_sysfs_show_fwinfo(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct ican3_dev *mod = netdev_priv(to_net_dev(dev));
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", mod->fwinfo);
+}
+
 static DEVICE_ATTR(termination, S_IWUSR | S_IRUGO, ican3_sysfs_show_term,
 						   ican3_sysfs_set_term);
+static DEVICE_ATTR(fwinfo, S_IRUSR | S_IRUGO, ican3_sysfs_show_fwinfo, NULL);
 
 static struct attribute *ican3_sysfs_attrs[] = {
 	&dev_attr_termination.attr,
+	&dev_attr_fwinfo.attr,
 	NULL,
 };
 
@@ -1794,7 +1846,6 @@ static int ican3_probe(struct platform_device *pdev)
 
 	mod->can.clock.freq = ICAN3_CAN_CLOCK;
 	mod->can.bittiming_const = &ican3_bittiming_const;
-	mod->can.do_set_bittiming = ican3_set_bittiming;
 	mod->can.do_set_mode = ican3_set_mode;
 	mod->can.do_get_berr_counter = ican3_get_berr_counter;
 	mod->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES
@@ -1866,7 +1917,7 @@ static int ican3_probe(struct platform_device *pdev)
 		goto out_free_irq;
 	}
 
-	dev_info(dev, "module %d: registered CAN device\n", pdata->modno);
+	netdev_info(mod->ndev, "module %d: registered CAN device\n", pdata->modno);
 	return 0;
 
 out_free_irq:
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index c837eb91d43e..f64f5290d6f8 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -207,6 +207,7 @@ static void slc_bump(struct slcan *sl)
 	if (!skb)
 		return;
 
+	__net_timestamp(skb);
 	skb->dev = sl->dev;
 	skb->protocol = htons(ETH_P_CAN);
 	skb->pkt_type = PACKET_BROADCAST;
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index bf63fee4e743..c1a95a34d62e 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -190,10 +190,11 @@
 #define RXBEID0_OFF 4
 #define RXBDLC_OFF  5
 #define RXBDAT_OFF  6
-#define RXFSIDH(n) ((n) * 4)
-#define RXFSIDL(n) ((n) * 4 + 1)
-#define RXFEID8(n) ((n) * 4 + 2)
-#define RXFEID0(n) ((n) * 4 + 3)
+#define RXFSID(n) ((n < 3) ? 0 : 4)
+#define RXFSIDH(n) ((n) * 4 + RXFSID(n))
+#define RXFSIDL(n) ((n) * 4 + 1 + RXFSID(n))
+#define RXFEID8(n) ((n) * 4 + 2 + RXFSID(n))
+#define RXFEID0(n) ((n) * 4 + 3 + RXFSID(n))
 #define RXMSIDH(n) ((n) * 4 + 0x20)
 #define RXMSIDL(n) ((n) * 4 + 0x21)
 #define RXMEID8(n) ((n) * 4 + 0x22)
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 674f367087c5..0ce868de855d 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -78,6 +78,9 @@ static void vcan_rx(struct sk_buff *skb, struct net_device *dev)
 	skb->dev       = dev;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
+	if (!(skb->tstamp.tv64))
+		__net_timestamp(skb);
+
 	netif_rx_ni(skb);
 }
 
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 6bddfe062b51..fc55e8e0351d 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -509,10 +509,11 @@ static int xcan_rx(struct net_device *ndev)
 			cf->can_id |= CAN_RTR_FLAG;
 	}
 
-	if (!(id_xcan & XCAN_IDR_SRR_MASK)) {
-		data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
-		data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+	/* DW1/DW2 must always be read to remove message from RXFIFO */
+	data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
+	data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
 
+	if (!(cf->can_id & CAN_RTR_FLAG)) {
 		/* Change Xilinx CAN data format to socketCAN data format */
 		if (cf->can_dlc > 0)
 			*(__be32 *)(cf->data) = cpu_to_be32(data[0]);
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 18550c7ebe6f..7ad0a4d8e475 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -37,22 +37,22 @@ config NET_DSA_MV88E6123_61_65
 	  ethernet switch chips.
 
 config NET_DSA_MV88E6171
-	tristate "Marvell 88E6171/6172 ethernet switch chip support"
+	tristate "Marvell 88E6171/6175/6350/6351 ethernet switch chip support"
 	depends on NET_DSA
 	select NET_DSA_MV88E6XXX
 	select NET_DSA_TAG_EDSA
 	---help---
-	  This enables support for the Marvell 88E6171/6172 ethernet switch
-	  chips.
+	  This enables support for the Marvell 88E6171/6175/6350/6351
+	  ethernet switches chips.
 
 config NET_DSA_MV88E6352
-	tristate "Marvell 88E6176/88E6352 ethernet switch chip support"
+	tristate "Marvell 88E6172/88E6176/88E6352 ethernet switch chip support"
 	depends on NET_DSA
 	select NET_DSA_MV88E6XXX
 	select NET_DSA_TAG_EDSA
 	---help---
-	  This enables support for the Marvell 88E6176 and 88E6352 ethernet
-	  switch chips.
+	  This enables support for the Marvell 88E6172, 88E6176 and 88E6352
+	  ethernet switch chips.
 
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index cedb572bf25a..972982f8bea7 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -24,6 +24,7 @@
 #include <net/dsa.h>
 #include <linux/ethtool.h>
 #include <linux/if_bridge.h>
+#include <linux/brcmphy.h>
 
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
@@ -697,7 +698,7 @@ static int bcm_sf2_sw_setup(struct dsa_switch *ds)
 	/* Include the pseudo-PHY address and the broadcast PHY address to
 	 * divert reads towards our workaround
 	 */
-	ds->phys_mii_mask |= ((1 << 30) | (1 << 0));
+	ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
 
 	rev = reg_readl(priv, REG_SWITCH_REVISION);
 	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
@@ -782,7 +783,7 @@ static int bcm_sf2_sw_phy_read(struct dsa_switch *ds, int addr, int regnum)
 	 */
 	switch (addr) {
 	case 0:
-	case 30:
+	case BRCM_PSEUDO_PHY_ADDR:
 		return bcm_sf2_sw_indir_rw(ds, 1, addr, regnum, 0);
 	default:
 		return 0xffff;
@@ -797,7 +798,7 @@ static int bcm_sf2_sw_phy_write(struct dsa_switch *ds, int addr, int regnum,
 	 */
 	switch (addr) {
 	case 0:
-	case 30:
+	case BRCM_PSEUDO_PHY_ADDR:
 		bcm_sf2_sw_indir_rw(ds, 0, addr, regnum, val);
 		break;
 	}
@@ -911,6 +912,13 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port,
 	 */
 	if (port == 7) {
 		status->link = priv->port_sts[port].link;
+		/* For MoCA interfaces, also force a link down notification
+		 * since some version of the user-space daemon (mocad) use
+		 * cmd->autoneg to force the link, which messes up the PHY
+		 * state machine and make it go in PHY_FORCING state instead.
+		 */
+		if (!status->link)
+			netif_carrier_off(ds->ports[port]);
 		status->duplex = 1;
 	} else {
 		status->link = 1;
diff --git a/drivers/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c
index b4af6d5aff7c..71a29a7ce538 100644
--- a/drivers/net/dsa/mv88e6123_61_65.c
+++ b/drivers/net/dsa/mv88e6123_61_65.c
@@ -54,192 +54,40 @@ static char *mv88e6123_61_65_probe(struct device *host_dev, int sw_addr)
 
 static int mv88e6123_61_65_setup_global(struct dsa_switch *ds)
 {
+	u32 upstream_port = dsa_upstream_port(ds);
 	int ret;
-	int i;
+	u32 reg;
+
+	ret = mv88e6xxx_setup_global(ds);
+	if (ret)
+		return ret;
 
 	/* Disable the PHY polling unit (since there won't be any
 	 * external PHYs to poll), don't discard packets with
 	 * excessive collisions, and mask all interrupt sources.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x04, 0x0000);
-
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	REG_WRITE(REG_GLOBAL, 0x0a, 0x0148);
-
-	/* Configure the priority mapping registers. */
-	ret = mv88e6xxx_config_prio(ds);
-	if (ret < 0)
-		return ret;
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL, 0x0000);
 
 	/* Configure the upstream port, and configure the upstream
 	 * port as the port to which ingress and egress monitor frames
 	 * are to be sent.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1110));
+	reg = upstream_port << GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_ARP_SHIFT;
+	REG_WRITE(REG_GLOBAL, GLOBAL_MONITOR_CONTROL, reg);
 
 	/* Disable remote management for now, and set the switch's
 	 * DSA device number.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x1c, ds->index & 0x1f);
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:2x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x02, 0xffff);
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:0x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x03, 0xffff);
-
-	/* Disable the loopback filter, disable flow control
-	 * messages, disable flood broadcast override, disable
-	 * removing of provider tags, disable ATU age violation
-	 * interrupts, disable tag flow control, force flow
-	 * control priority to the highest, and send all special
-	 * multicast frames to the CPU at the highest priority.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
-
-	/* Program the DSA routing table. */
-	for (i = 0; i < 32; i++) {
-		int nexthop;
-
-		nexthop = 0x1f;
-		if (i != ds->index && i < ds->dst->pd->nr_chips)
-			nexthop = ds->pd->rtable[i] & 0x1f;
-
-		REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
-	}
-
-	/* Clear all trunk masks. */
-	for (i = 0; i < 8; i++)
-		REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0xff);
-
-	/* Clear all trunk mappings. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x08, 0x8000 | (i << 11));
-
-	/* Disable ingress rate limiting by resetting all ingress
-	 * rate limit registers to their initial state.
-	 */
-	for (i = 0; i < 6; i++)
-		REG_WRITE(REG_GLOBAL2, 0x09, 0x9000 | (i << 8));
-
-	/* Initialise cross-chip port VLAN table to reset defaults. */
-	REG_WRITE(REG_GLOBAL2, 0x0b, 0x9000);
-
-	/* Clear the priority override table. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x0f, 0x8000 | (i << 8));
-
-	/* @@@ initialise AVB (22/23) watchdog (27) sdet (29) registers */
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL_2, ds->index & 0x1f);
 
 	return 0;
 }
 
-static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p)
-{
-	int addr = REG_PORT(p);
-	u16 val;
-
-	/* MAC Forcing register: don't force link, speed, duplex
-	 * or flow control state to any particular values on physical
-	 * ports, but force the CPU port and all DSA ports to 1000 Mb/s
-	 * full duplex.
-	 */
-	if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
-		REG_WRITE(addr, 0x01, 0x003e);
-	else
-		REG_WRITE(addr, 0x01, 0x0003);
-
-	/* Do not limit the period of time that this port can be
-	 * paused for by the remote end or the period of time that
-	 * this port can pause the remote end.
-	 */
-	REG_WRITE(addr, 0x02, 0x0000);
-
-	/* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
-	 * disable Header mode, enable IGMP/MLD snooping, disable VLAN
-	 * tunneling, determine priority by looking at 802.1p and IP
-	 * priority fields (IP prio has precedence), and set STP state
-	 * to Forwarding.
-	 *
-	 * If this is the CPU link, use DSA or EDSA tagging depending
-	 * on which tagging mode was configured.
-	 *
-	 * If this is a link to another switch, use DSA tagging mode.
-	 *
-	 * If this is the upstream port for this switch, enable
-	 * forwarding of unknown unicasts and multicasts.
-	 */
-	val = 0x0433;
-	if (dsa_is_cpu_port(ds, p)) {
-		if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
-			val |= 0x3300;
-		else
-			val |= 0x0100;
-	}
-	if (ds->dsa_port_mask & (1 << p))
-		val |= 0x0100;
-	if (p == dsa_upstream_port(ds))
-		val |= 0x000c;
-	REG_WRITE(addr, 0x04, val);
-
-	/* Port Control 2: don't force a good FCS, set the maximum
-	 * frame size to 10240 bytes, don't let the switch add or
-	 * strip 802.1q tags, don't discard tagged or untagged frames
-	 * on this port, do a destination address lookup on all
-	 * received packets as usual, disable ARP mirroring and don't
-	 * send a copy of all transmitted/received frames on this port
-	 * to the CPU.
-	 */
-	REG_WRITE(addr, 0x08, 0x2080);
-
-	/* Egress rate control: disable egress rate control. */
-	REG_WRITE(addr, 0x09, 0x0001);
-
-	/* Egress rate control 2: disable egress rate control. */
-	REG_WRITE(addr, 0x0a, 0x0000);
-
-	/* Port Association Vector: when learning source addresses
-	 * of packets, add the address to the address database using
-	 * a port bitmap that has only the bit for this port set and
-	 * the other bits clear.
-	 */
-	REG_WRITE(addr, 0x0b, 1 << p);
-
-	/* Port ATU control: disable limiting the number of address
-	 * database entries that this port is allowed to use.
-	 */
-	REG_WRITE(addr, 0x0c, 0x0000);
-
-	/* Priority Override: disable DA, SA and VTU priority override. */
-	REG_WRITE(addr, 0x0d, 0x0000);
-
-	/* Port Ethertype: use the Ethertype DSA Ethertype value. */
-	REG_WRITE(addr, 0x0f, ETH_P_EDSA);
-
-	/* Tag Remap: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x18, 0x3210);
-
-	/* Tag Remap 2: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x19, 0x7654);
-
-	return mv88e6xxx_setup_port_common(ds, p);
-}
-
 static int mv88e6123_61_65_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int i;
 	int ret;
 
 	ret = mv88e6xxx_setup_common(ds);
@@ -262,19 +110,11 @@ static int mv88e6123_61_65_setup(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	/* @@@ initialise vtu and atu */
-
 	ret = mv88e6123_61_65_setup_global(ds);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < ps->num_ports; i++) {
-		ret = mv88e6123_61_65_setup_port(ds, i);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
+	return mv88e6xxx_setup_ports(ds);
 }
 
 struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
diff --git a/drivers/net/dsa/mv88e6131.c b/drivers/net/dsa/mv88e6131.c
index e54824fa0d95..32f4a08e9bc9 100644
--- a/drivers/net/dsa/mv88e6131.c
+++ b/drivers/net/dsa/mv88e6131.c
@@ -37,6 +37,8 @@ static char *mv88e6131_probe(struct device *host_dev, int sw_addr)
 			return "Marvell 88E6131 (B2)";
 		if (ret_masked == PORT_SWITCH_ID_6131)
 			return "Marvell 88E6131";
+		if (ret_masked == PORT_SWITCH_ID_6185)
+			return "Marvell 88E6185";
 	}
 
 	return NULL;
@@ -44,186 +46,62 @@ static char *mv88e6131_probe(struct device *host_dev, int sw_addr)
 
 static int mv88e6131_setup_global(struct dsa_switch *ds)
 {
+	u32 upstream_port = dsa_upstream_port(ds);
 	int ret;
-	int i;
+	u32 reg;
+
+	ret = mv88e6xxx_setup_global(ds);
+	if (ret)
+		return ret;
 
 	/* Enable the PHY polling unit, don't discard packets with
 	 * excessive collisions, use a weighted fair queueing scheme
 	 * to arbitrate between packet queues, set the maximum frame
 	 * size to 1632, and mask all interrupt sources.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x04, 0x4400);
-
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	REG_WRITE(REG_GLOBAL, 0x0a, 0x0148);
-
-	/* Configure the priority mapping registers. */
-	ret = mv88e6xxx_config_prio(ds);
-	if (ret < 0)
-		return ret;
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL,
+		  GLOBAL_CONTROL_PPU_ENABLE | GLOBAL_CONTROL_MAX_FRAME_1632);
 
 	/* Set the VLAN ethertype to 0x8100. */
-	REG_WRITE(REG_GLOBAL, 0x19, 0x8100);
+	REG_WRITE(REG_GLOBAL, GLOBAL_CORE_TAG_TYPE, 0x8100);
 
 	/* Disable ARP mirroring, and configure the upstream port as
 	 * the port to which ingress and egress monitor frames are to
 	 * be sent.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1100) | 0x00f0);
+	reg = upstream_port << GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT |
+		GLOBAL_MONITOR_CONTROL_ARP_DISABLED;
+	REG_WRITE(REG_GLOBAL, GLOBAL_MONITOR_CONTROL, reg);
 
 	/* Disable cascade port functionality unless this device
 	 * is used in a cascade configuration, and set the switch's
 	 * DSA device number.
 	 */
 	if (ds->dst->pd->nr_chips > 1)
-		REG_WRITE(REG_GLOBAL, 0x1c, 0xf000 | (ds->index & 0x1f));
+		REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL_2,
+			  GLOBAL_CONTROL_2_MULTIPLE_CASCADE |
+			  (ds->index & 0x1f));
 	else
-		REG_WRITE(REG_GLOBAL, 0x1c, 0xe000 | (ds->index & 0x1f));
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:0x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x03, 0xffff);
-
-	/* Ignore removed tag data on doubly tagged packets, disable
-	 * flow control messages, force flow control priority to the
-	 * highest, and send all special multicast frames to the CPU
-	 * port at the highest priority.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
-
-	/* Program the DSA routing table. */
-	for (i = 0; i < 32; i++) {
-		int nexthop;
-
-		nexthop = 0x1f;
-		if (ds->pd->rtable &&
-		    i != ds->index && i < ds->dst->pd->nr_chips)
-			nexthop = ds->pd->rtable[i] & 0x1f;
-
-		REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
-	}
-
-	/* Clear all trunk masks. */
-	for (i = 0; i < 8; i++)
-		REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0x7ff);
-
-	/* Clear all trunk mappings. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x08, 0x8000 | (i << 11));
+		REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL_2,
+			  GLOBAL_CONTROL_2_NO_CASCADE |
+			  (ds->index & 0x1f));
 
 	/* Force the priority of IGMP/MLD snoop frames and ARP frames
 	 * to the highest setting.
 	 */
-	REG_WRITE(REG_GLOBAL2, 0x0f, 0x00ff);
+	REG_WRITE(REG_GLOBAL2, GLOBAL2_PRIO_OVERRIDE,
+		  GLOBAL2_PRIO_OVERRIDE_FORCE_SNOOP |
+		  7 << GLOBAL2_PRIO_OVERRIDE_SNOOP_SHIFT |
+		  GLOBAL2_PRIO_OVERRIDE_FORCE_ARP |
+		  7 << GLOBAL2_PRIO_OVERRIDE_ARP_SHIFT);
 
 	return 0;
 }
 
-static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
-{
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int addr = REG_PORT(p);
-	u16 val;
-
-	/* MAC Forcing register: don't force link, speed, duplex
-	 * or flow control state to any particular values on physical
-	 * ports, but force the CPU port and all DSA ports to 1000 Mb/s
-	 * (100 Mb/s on 6085) full duplex.
-	 */
-	if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
-		if (ps->id == PORT_SWITCH_ID_6085)
-			REG_WRITE(addr, 0x01, 0x003d); /* 100 Mb/s */
-		else
-			REG_WRITE(addr, 0x01, 0x003e); /* 1000 Mb/s */
-	else
-		REG_WRITE(addr, 0x01, 0x0003);
-
-	/* Port Control: disable Core Tag, disable Drop-on-Lock,
-	 * transmit frames unmodified, disable Header mode,
-	 * enable IGMP/MLD snoop, disable DoubleTag, disable VLAN
-	 * tunneling, determine priority by looking at 802.1p and
-	 * IP priority fields (IP prio has precedence), and set STP
-	 * state to Forwarding.
-	 *
-	 * If this is the upstream port for this switch, enable
-	 * forwarding of unknown unicasts, and enable DSA tagging
-	 * mode.
-	 *
-	 * If this is the link to another switch, use DSA tagging
-	 * mode, but do not enable forwarding of unknown unicasts.
-	 */
-	val = 0x0433;
-	if (p == dsa_upstream_port(ds)) {
-		val |= 0x0104;
-		/* On 6085, unknown multicast forward is controlled
-		 * here rather than in Port Control 2 register.
-		 */
-		if (ps->id == PORT_SWITCH_ID_6085)
-			val |= 0x0008;
-	}
-	if (ds->dsa_port_mask & (1 << p))
-		val |= 0x0100;
-	REG_WRITE(addr, 0x04, val);
-
-	/* Port Control 2: don't force a good FCS, don't use
-	 * VLAN-based, source address-based or destination
-	 * address-based priority overrides, don't let the switch
-	 * add or strip 802.1q tags, don't discard tagged or
-	 * untagged frames on this port, do a destination address
-	 * lookup on received packets as usual, don't send a copy
-	 * of all transmitted/received frames on this port to the
-	 * CPU, and configure the upstream port number.
-	 *
-	 * If this is the upstream port for this switch, enable
-	 * forwarding of unknown multicast addresses.
-	 */
-	if (ps->id == PORT_SWITCH_ID_6085)
-		/* on 6085, bits 3:0 are reserved, bit 6 control ARP
-		 * mirroring, and multicast forward is handled in
-		 * Port Control register.
-		 */
-		REG_WRITE(addr, 0x08, 0x0080);
-	else {
-		val = 0x0080 | dsa_upstream_port(ds);
-		if (p == dsa_upstream_port(ds))
-			val |= 0x0040;
-		REG_WRITE(addr, 0x08, val);
-	}
-
-	/* Rate Control: disable ingress rate limiting. */
-	REG_WRITE(addr, 0x09, 0x0000);
-
-	/* Rate Control 2: disable egress rate limiting. */
-	REG_WRITE(addr, 0x0a, 0x0000);
-
-	/* Port Association Vector: when learning source addresses
-	 * of packets, add the address to the address database using
-	 * a port bitmap that has only the bit for this port set and
-	 * the other bits clear.
-	 */
-	REG_WRITE(addr, 0x0b, 1 << p);
-
-	/* Tag Remap: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x18, 0x3210);
-
-	/* Tag Remap 2: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x19, 0x7654);
-
-	return mv88e6xxx_setup_port_common(ds, p);
-}
-
 static int mv88e6131_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int i;
 	int ret;
 
 	ret = mv88e6xxx_setup_common(ds);
@@ -234,6 +112,7 @@ static int mv88e6131_setup(struct dsa_switch *ds)
 
 	switch (ps->id) {
 	case PORT_SWITCH_ID_6085:
+	case PORT_SWITCH_ID_6185:
 		ps->num_ports = 10;
 		break;
 	case PORT_SWITCH_ID_6095:
@@ -251,19 +130,11 @@ static int mv88e6131_setup(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	/* @@@ initialise vtu and atu */
-
 	ret = mv88e6131_setup_global(ds);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < ps->num_ports; i++) {
-		ret = mv88e6131_setup_port(ds, i);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
+	return mv88e6xxx_setup_ports(ds);
 }
 
 static int mv88e6131_port_to_phy_addr(struct dsa_switch *ds, int port)
diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c
index 9104efea0e3e..1c7808495a9d 100644
--- a/drivers/net/dsa/mv88e6171.c
+++ b/drivers/net/dsa/mv88e6171.c
@@ -1,4 +1,4 @@
-/* net/dsa/mv88e6171.c - Marvell 88e6171/8826172 switch chip support
+/* net/dsa/mv88e6171.c - Marvell 88e6171 switch chip support
  * Copyright (c) 2008-2009 Marvell Semiconductor
  * Copyright (c) 2014 Claudio Leite <leitec@staticky.com>
  *
@@ -29,8 +29,12 @@ static char *mv88e6171_probe(struct device *host_dev, int sw_addr)
 	if (ret >= 0) {
 		if ((ret & 0xfff0) == PORT_SWITCH_ID_6171)
 			return "Marvell 88E6171";
-		if ((ret & 0xfff0) == PORT_SWITCH_ID_6172)
-			return "Marvell 88E6172";
+		if ((ret & 0xfff0) == PORT_SWITCH_ID_6175)
+			return "Marvell 88E6175";
+		if ((ret & 0xfff0) == PORT_SWITCH_ID_6350)
+			return "Marvell 88E6350";
+		if ((ret & 0xfff0) == PORT_SWITCH_ID_6351)
+			return "Marvell 88E6351";
 	}
 
 	return NULL;
@@ -38,196 +42,41 @@ static char *mv88e6171_probe(struct device *host_dev, int sw_addr)
 
 static int mv88e6171_setup_global(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	u32 upstream_port = dsa_upstream_port(ds);
 	int ret;
-	int i;
+	u32 reg;
+
+	ret = mv88e6xxx_setup_global(ds);
+	if (ret)
+		return ret;
 
 	/* Discard packets with excessive collisions, mask all
 	 * interrupt sources, enable PPU.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x04, 0x6000);
-
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	REG_WRITE(REG_GLOBAL, 0x0a, 0x0148);
-
-	/* Configure the priority mapping registers. */
-	ret = mv88e6xxx_config_prio(ds);
-	if (ret < 0)
-		return ret;
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL,
+		  GLOBAL_CONTROL_PPU_ENABLE | GLOBAL_CONTROL_DISCARD_EXCESS);
 
 	/* Configure the upstream port, and configure the upstream
 	 * port as the port to which ingress and egress monitor frames
 	 * are to be sent.
 	 */
-	if (REG_READ(REG_PORT(0), 0x03) == 0x1710)
-		REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1111));
-	else
-		REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1110));
+	reg = upstream_port << GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_ARP_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_MIRROR_SHIFT;
+	REG_WRITE(REG_GLOBAL, GLOBAL_MONITOR_CONTROL, reg);
 
 	/* Disable remote management for now, and set the switch's
 	 * DSA device number.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x1c, ds->index & 0x1f);
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:2x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x02, 0xffff);
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:0x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x03, 0xffff);
-
-	/* Disable the loopback filter, disable flow control
-	 * messages, disable flood broadcast override, disable
-	 * removing of provider tags, disable ATU age violation
-	 * interrupts, disable tag flow control, force flow
-	 * control priority to the highest, and send all special
-	 * multicast frames to the CPU at the highest priority.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
-
-	/* Program the DSA routing table. */
-	for (i = 0; i < 32; i++) {
-		int nexthop;
-
-		nexthop = 0x1f;
-		if (i != ds->index && i < ds->dst->pd->nr_chips)
-			nexthop = ds->pd->rtable[i] & 0x1f;
-
-		REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
-	}
-
-	/* Clear all trunk masks. */
-	for (i = 0; i < ps->num_ports; i++)
-		REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0xff);
-
-	/* Clear all trunk mappings. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x08, 0x8000 | (i << 11));
-
-	/* Disable ingress rate limiting by resetting all ingress
-	 * rate limit registers to their initial state.
-	 */
-	for (i = 0; i < 6; i++)
-		REG_WRITE(REG_GLOBAL2, 0x09, 0x9000 | (i << 8));
-
-	/* Initialise cross-chip port VLAN table to reset defaults. */
-	REG_WRITE(REG_GLOBAL2, 0x0b, 0x9000);
-
-	/* Clear the priority override table. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x0f, 0x8000 | (i << 8));
-
-	/* @@@ initialise AVB (22/23) watchdog (27) sdet (29) registers */
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL_2, ds->index & 0x1f);
 
 	return 0;
 }
 
-static int mv88e6171_setup_port(struct dsa_switch *ds, int p)
-{
-	int addr = REG_PORT(p);
-	u16 val;
-
-	/* MAC Forcing register: don't force link, speed, duplex
-	 * or flow control state to any particular values on physical
-	 * ports, but force the CPU port and all DSA ports to 1000 Mb/s
-	 * full duplex.
-	 */
-	val = REG_READ(addr, 0x01);
-	if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
-		REG_WRITE(addr, 0x01, val | 0x003e);
-	else
-		REG_WRITE(addr, 0x01, val | 0x0003);
-
-	/* Do not limit the period of time that this port can be
-	 * paused for by the remote end or the period of time that
-	 * this port can pause the remote end.
-	 */
-	REG_WRITE(addr, 0x02, 0x0000);
-
-	/* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
-	 * disable Header mode, enable IGMP/MLD snooping, disable VLAN
-	 * tunneling, determine priority by looking at 802.1p and IP
-	 * priority fields (IP prio has precedence), and set STP state
-	 * to Forwarding.
-	 *
-	 * If this is the CPU link, use DSA or EDSA tagging depending
-	 * on which tagging mode was configured.
-	 *
-	 * If this is a link to another switch, use DSA tagging mode.
-	 *
-	 * If this is the upstream port for this switch, enable
-	 * forwarding of unknown unicasts and multicasts.
-	 */
-	val = 0x0433;
-	if (dsa_is_cpu_port(ds, p)) {
-		if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
-			val |= 0x3300;
-		else
-			val |= 0x0100;
-	}
-	if (ds->dsa_port_mask & (1 << p))
-		val |= 0x0100;
-	if (p == dsa_upstream_port(ds))
-		val |= 0x000c;
-	REG_WRITE(addr, 0x04, val);
-
-	/* Port Control 2: don't force a good FCS, set the maximum
-	 * frame size to 10240 bytes, don't let the switch add or
-	 * strip 802.1q tags, don't discard tagged or untagged frames
-	 * on this port, do a destination address lookup on all
-	 * received packets as usual, disable ARP mirroring and don't
-	 * send a copy of all transmitted/received frames on this port
-	 * to the CPU.
-	 */
-	REG_WRITE(addr, 0x08, 0x2080);
-
-	/* Egress rate control: disable egress rate control. */
-	REG_WRITE(addr, 0x09, 0x0001);
-
-	/* Egress rate control 2: disable egress rate control. */
-	REG_WRITE(addr, 0x0a, 0x0000);
-
-	/* Port Association Vector: when learning source addresses
-	 * of packets, add the address to the address database using
-	 * a port bitmap that has only the bit for this port set and
-	 * the other bits clear.
-	 */
-	REG_WRITE(addr, 0x0b, 1 << p);
-
-	/* Port ATU control: disable limiting the number of address
-	 * database entries that this port is allowed to use.
-	 */
-	REG_WRITE(addr, 0x0c, 0x0000);
-
-	/* Priority Override: disable DA, SA and VTU priority override. */
-	REG_WRITE(addr, 0x0d, 0x0000);
-
-	/* Port Ethertype: use the Ethertype DSA Ethertype value. */
-	REG_WRITE(addr, 0x0f, ETH_P_EDSA);
-
-	/* Tag Remap: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x18, 0x3210);
-
-	/* Tag Remap 2: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x19, 0x7654);
-
-	return mv88e6xxx_setup_port_common(ds, p);
-}
-
 static int mv88e6171_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-	int i;
 	int ret;
 
 	ret = mv88e6xxx_setup_common(ds);
@@ -240,44 +89,11 @@ static int mv88e6171_setup(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	/* @@@ initialise vtu and atu */
-
 	ret = mv88e6171_setup_global(ds);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < ps->num_ports; i++) {
-		if (!(dsa_is_cpu_port(ds, i) || ds->phys_port_mask & (1 << i)))
-			continue;
-
-		ret = mv88e6171_setup_port(ds, i);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
-}
-
-static int mv88e6171_get_eee(struct dsa_switch *ds, int port,
-			     struct ethtool_eee *e)
-{
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-
-	if (ps->id == PORT_SWITCH_ID_6172)
-		return mv88e6xxx_get_eee(ds, port, e);
-
-	return -EOPNOTSUPP;
-}
-
-static int mv88e6171_set_eee(struct dsa_switch *ds, int port,
-			     struct phy_device *phydev, struct ethtool_eee *e)
-{
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
-
-	if (ps->id == PORT_SWITCH_ID_6172)
-		return mv88e6xxx_set_eee(ds, port, phydev, e);
-
-	return -EOPNOTSUPP;
+	return mv88e6xxx_setup_ports(ds);
 }
 
 struct dsa_switch_driver mv88e6171_switch_driver = {
@@ -292,8 +108,6 @@ struct dsa_switch_driver mv88e6171_switch_driver = {
 	.get_strings		= mv88e6xxx_get_strings,
 	.get_ethtool_stats	= mv88e6xxx_get_ethtool_stats,
 	.get_sset_count		= mv88e6xxx_get_sset_count,
-	.set_eee		= mv88e6171_set_eee,
-	.get_eee		= mv88e6171_get_eee,
 #ifdef CONFIG_NET_DSA_HWMON
 	.get_temp               = mv88e6xxx_get_temp,
 #endif
@@ -308,4 +122,6 @@ struct dsa_switch_driver mv88e6171_switch_driver = {
 };
 
 MODULE_ALIAS("platform:mv88e6171");
-MODULE_ALIAS("platform:mv88e6172");
+MODULE_ALIAS("platform:mv88e6175");
+MODULE_ALIAS("platform:mv88e6350");
+MODULE_ALIAS("platform:mv88e6351");
diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c
index 126c11b81e75..632815c10a40 100644
--- a/drivers/net/dsa/mv88e6352.c
+++ b/drivers/net/dsa/mv88e6352.c
@@ -32,6 +32,8 @@ static char *mv88e6352_probe(struct device *host_dev, int sw_addr)
 
 	ret = __mv88e6xxx_reg_read(bus, sw_addr, REG_PORT(0), PORT_SWITCH_ID);
 	if (ret >= 0) {
+		if ((ret & 0xfff0) == PORT_SWITCH_ID_6172)
+			return "Marvell 88E6172";
 		if ((ret & 0xfff0) == PORT_SWITCH_ID_6176)
 			return "Marvell 88E6176";
 		if (ret == PORT_SWITCH_ID_6352_A0)
@@ -47,187 +49,37 @@ static char *mv88e6352_probe(struct device *host_dev, int sw_addr)
 
 static int mv88e6352_setup_global(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	u32 upstream_port = dsa_upstream_port(ds);
 	int ret;
-	int i;
+	u32 reg;
+
+	ret = mv88e6xxx_setup_global(ds);
+	if (ret)
+		return ret;
 
 	/* Discard packets with excessive collisions,
 	 * mask all interrupt sources, enable PPU (bit 14, undocumented).
 	 */
-	REG_WRITE(REG_GLOBAL, 0x04, 0x6000);
-
-	/* Set the default address aging time to 5 minutes, and
-	 * enable address learn messages to be sent to all message
-	 * ports.
-	 */
-	REG_WRITE(REG_GLOBAL, 0x0a, 0x0148);
-
-	/* Configure the priority mapping registers. */
-	ret = mv88e6xxx_config_prio(ds);
-	if (ret < 0)
-		return ret;
+	REG_WRITE(REG_GLOBAL, GLOBAL_CONTROL,
+		  GLOBAL_CONTROL_PPU_ENABLE | GLOBAL_CONTROL_DISCARD_EXCESS);
 
 	/* Configure the upstream port, and configure the upstream
 	 * port as the port to which ingress and egress monitor frames
 	 * are to be sent.
 	 */
-	REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1110));
+	reg = upstream_port << GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT |
+		upstream_port << GLOBAL_MONITOR_CONTROL_ARP_SHIFT;
+	REG_WRITE(REG_GLOBAL, GLOBAL_MONITOR_CONTROL, reg);
 
 	/* Disable remote management for now, and set the switch's
 	 * DSA device number.
 	 */
 	REG_WRITE(REG_GLOBAL, 0x1c, ds->index & 0x1f);
 
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:2x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x02, 0xffff);
-
-	/* Send all frames with destination addresses matching
-	 * 01:80:c2:00:00:0x to the CPU port.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x03, 0xffff);
-
-	/* Disable the loopback filter, disable flow control
-	 * messages, disable flood broadcast override, disable
-	 * removing of provider tags, disable ATU age violation
-	 * interrupts, disable tag flow control, force flow
-	 * control priority to the highest, and send all special
-	 * multicast frames to the CPU at the highest priority.
-	 */
-	REG_WRITE(REG_GLOBAL2, 0x05, 0x00ff);
-
-	/* Program the DSA routing table. */
-	for (i = 0; i < 32; i++) {
-		int nexthop = 0x1f;
-
-		if (i != ds->index && i < ds->dst->pd->nr_chips)
-			nexthop = ds->pd->rtable[i] & 0x1f;
-
-		REG_WRITE(REG_GLOBAL2, 0x06, 0x8000 | (i << 8) | nexthop);
-	}
-
-	/* Clear all trunk masks. */
-	for (i = 0; i < 8; i++)
-		REG_WRITE(REG_GLOBAL2, 0x07, 0x8000 | (i << 12) | 0x7f);
-
-	/* Clear all trunk mappings. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x08, 0x8000 | (i << 11));
-
-	/* Disable ingress rate limiting by resetting all ingress
-	 * rate limit registers to their initial state.
-	 */
-	for (i = 0; i < ps->num_ports; i++)
-		REG_WRITE(REG_GLOBAL2, 0x09, 0x9000 | (i << 8));
-
-	/* Initialise cross-chip port VLAN table to reset defaults. */
-	REG_WRITE(REG_GLOBAL2, 0x0b, 0x9000);
-
-	/* Clear the priority override table. */
-	for (i = 0; i < 16; i++)
-		REG_WRITE(REG_GLOBAL2, 0x0f, 0x8000 | (i << 8));
-
-	/* @@@ initialise AVB (22/23) watchdog (27) sdet (29) registers */
-
 	return 0;
 }
 
-static int mv88e6352_setup_port(struct dsa_switch *ds, int p)
-{
-	int addr = REG_PORT(p);
-	u16 val;
-
-	/* MAC Forcing register: don't force link, speed, duplex
-	 * or flow control state to any particular values on physical
-	 * ports, but force the CPU port and all DSA ports to 1000 Mb/s
-	 * full duplex.
-	 */
-	if (dsa_is_cpu_port(ds, p) || ds->dsa_port_mask & (1 << p))
-		REG_WRITE(addr, 0x01, 0x003e);
-	else
-		REG_WRITE(addr, 0x01, 0x0003);
-
-	/* Do not limit the period of time that this port can be
-	 * paused for by the remote end or the period of time that
-	 * this port can pause the remote end.
-	 */
-	REG_WRITE(addr, 0x02, 0x0000);
-
-	/* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
-	 * disable Header mode, enable IGMP/MLD snooping, disable VLAN
-	 * tunneling, determine priority by looking at 802.1p and IP
-	 * priority fields (IP prio has precedence), and set STP state
-	 * to Forwarding.
-	 *
-	 * If this is the CPU link, use DSA or EDSA tagging depending
-	 * on which tagging mode was configured.
-	 *
-	 * If this is a link to another switch, use DSA tagging mode.
-	 *
-	 * If this is the upstream port for this switch, enable
-	 * forwarding of unknown unicasts and multicasts.
-	 */
-	val = 0x0433;
-	if (dsa_is_cpu_port(ds, p)) {
-		if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
-			val |= 0x3300;
-		else
-			val |= 0x0100;
-	}
-	if (ds->dsa_port_mask & (1 << p))
-		val |= 0x0100;
-	if (p == dsa_upstream_port(ds))
-		val |= 0x000c;
-	REG_WRITE(addr, 0x04, val);
-
-	/* Port Control 2: don't force a good FCS, set the maximum
-	 * frame size to 10240 bytes, don't let the switch add or
-	 * strip 802.1q tags, don't discard tagged or untagged frames
-	 * on this port, do a destination address lookup on all
-	 * received packets as usual, disable ARP mirroring and don't
-	 * send a copy of all transmitted/received frames on this port
-	 * to the CPU.
-	 */
-	REG_WRITE(addr, 0x08, 0x2080);
-
-	/* Egress rate control: disable egress rate control. */
-	REG_WRITE(addr, 0x09, 0x0001);
-
-	/* Egress rate control 2: disable egress rate control. */
-	REG_WRITE(addr, 0x0a, 0x0000);
-
-	/* Port Association Vector: when learning source addresses
-	 * of packets, add the address to the address database using
-	 * a port bitmap that has only the bit for this port set and
-	 * the other bits clear.
-	 */
-	REG_WRITE(addr, 0x0b, 1 << p);
-
-	/* Port ATU control: disable limiting the number of address
-	 * database entries that this port is allowed to use.
-	 */
-	REG_WRITE(addr, 0x0c, 0x0000);
-
-	/* Priority Override: disable DA, SA and VTU priority override. */
-	REG_WRITE(addr, 0x0d, 0x0000);
-
-	/* Port Ethertype: use the Ethertype DSA Ethertype value. */
-	REG_WRITE(addr, 0x0f, ETH_P_EDSA);
-
-	/* Tag Remap: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x18, 0x3210);
-
-	/* Tag Remap 2: use an identity 802.1p prio -> switch prio
-	 * mapping.
-	 */
-	REG_WRITE(addr, 0x19, 0x7654);
-
-	return mv88e6xxx_setup_port_common(ds, p);
-}
-
 #ifdef CONFIG_NET_DSA_HWMON
 
 static int mv88e6352_get_temp(struct dsa_switch *ds, int *temp)
@@ -292,7 +144,6 @@ static int mv88e6352_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
-	int i;
 
 	ret = mv88e6xxx_setup_common(ds);
 	if (ret < 0)
@@ -306,19 +157,11 @@ static int mv88e6352_setup(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	/* @@@ initialise vtu and atu */
-
 	ret = mv88e6352_setup_global(ds);
 	if (ret < 0)
 		return ret;
 
-	for (i = 0; i < ps->num_ports; i++) {
-		ret = mv88e6352_setup_port(ds, i);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
+	return mv88e6xxx_setup_ports(ds);
 }
 
 static int mv88e6352_read_eeprom_word(struct dsa_switch *ds, int addr)
@@ -552,3 +395,4 @@ struct dsa_switch_driver mv88e6352_switch_driver = {
 };
 
 MODULE_ALIAS("platform:mv88e6352");
+MODULE_ALIAS("platform:mv88e6172");
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index af639ab4c55b..fd8547c2b79d 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -8,6 +8,7 @@
  * (at your option) any later version.
  */
 
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/etherdevice.h>
 #include <linux/if_bridge.h>
@@ -16,9 +17,38 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
+#include <linux/seq_file.h>
 #include <net/dsa.h>
 #include "mv88e6xxx.h"
 
+/* MDIO bus access can be nested in the case of PHYs connected to the
+ * internal MDIO bus of the switch, which is accessed via MDIO bus of
+ * the Ethernet interface. Avoid lockdep false positives by using
+ * mutex_lock_nested().
+ */
+static int mv88e6xxx_mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
+{
+	int ret;
+
+	mutex_lock_nested(&bus->mdio_lock, SINGLE_DEPTH_NESTING);
+	ret = bus->read(bus, addr, regnum);
+	mutex_unlock(&bus->mdio_lock);
+
+	return ret;
+}
+
+static int mv88e6xxx_mdiobus_write(struct mii_bus *bus, int addr, u32 regnum,
+				   u16 val)
+{
+	int ret;
+
+	mutex_lock_nested(&bus->mdio_lock, SINGLE_DEPTH_NESTING);
+	ret = bus->write(bus, addr, regnum, val);
+	mutex_unlock(&bus->mdio_lock);
+
+	return ret;
+}
+
 /* If the switch's ADDR[4:0] strap pins are strapped to zero, it will
  * use all 32 SMI bus addresses on its SMI bus, and all switch registers
  * will be directly accessible on some {device address,register address}
@@ -33,7 +63,7 @@ static int mv88e6xxx_reg_wait_ready(struct mii_bus *bus, int sw_addr)
 	int i;
 
 	for (i = 0; i < 16; i++) {
-		ret = mdiobus_read(bus, sw_addr, SMI_CMD);
+		ret = mv88e6xxx_mdiobus_read(bus, sw_addr, SMI_CMD);
 		if (ret < 0)
 			return ret;
 
@@ -49,7 +79,7 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg)
 	int ret;
 
 	if (sw_addr == 0)
-		return mdiobus_read(bus, addr, reg);
+		return mv88e6xxx_mdiobus_read(bus, addr, reg);
 
 	/* Wait for the bus to become free. */
 	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
@@ -57,8 +87,8 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg)
 		return ret;
 
 	/* Transmit the read command. */
-	ret = mdiobus_write(bus, sw_addr, SMI_CMD,
-			    SMI_CMD_OP_22_READ | (addr << 5) | reg);
+	ret = mv88e6xxx_mdiobus_write(bus, sw_addr, SMI_CMD,
+				      SMI_CMD_OP_22_READ | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
@@ -68,7 +98,7 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg)
 		return ret;
 
 	/* Read the data. */
-	ret = mdiobus_read(bus, sw_addr, SMI_DATA);
+	ret = mv88e6xxx_mdiobus_read(bus, sw_addr, SMI_DATA);
 	if (ret < 0)
 		return ret;
 
@@ -112,7 +142,7 @@ int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
 	int ret;
 
 	if (sw_addr == 0)
-		return mdiobus_write(bus, addr, reg, val);
+		return mv88e6xxx_mdiobus_write(bus, addr, reg, val);
 
 	/* Wait for the bus to become free. */
 	ret = mv88e6xxx_reg_wait_ready(bus, sw_addr);
@@ -120,13 +150,13 @@ int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
 		return ret;
 
 	/* Transmit the data to write. */
-	ret = mdiobus_write(bus, sw_addr, SMI_DATA, val);
+	ret = mv88e6xxx_mdiobus_write(bus, sw_addr, SMI_DATA, val);
 	if (ret < 0)
 		return ret;
 
 	/* Transmit the write command. */
-	ret = mdiobus_write(bus, sw_addr, SMI_CMD,
-			    SMI_CMD_OP_22_WRITE | (addr << 5) | reg);
+	ret = mv88e6xxx_mdiobus_write(bus, sw_addr, SMI_CMD,
+				      SMI_CMD_OP_22_WRITE | (addr << 5) | reg);
 	if (ret < 0)
 		return ret;
 
@@ -165,24 +195,6 @@ int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 	return ret;
 }
 
-int mv88e6xxx_config_prio(struct dsa_switch *ds)
-{
-	/* Configure the IP ToS mapping registers. */
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_0, 0x0000);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_1, 0x0000);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_2, 0x5555);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_3, 0x5555);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_4, 0xaaaa);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_5, 0xaaaa);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_6, 0xffff);
-	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_7, 0xffff);
-
-	/* Configure the IEEE 802.1p priority mapping register. */
-	REG_WRITE(REG_GLOBAL, GLOBAL_IEEE_PRI, 0xfa41);
-
-	return 0;
-}
-
 int mv88e6xxx_set_addr_direct(struct dsa_switch *ds, u8 *addr)
 {
 	REG_WRITE(REG_GLOBAL, GLOBAL_MAC_01, (addr[0] << 8) | addr[1]);
@@ -217,20 +229,20 @@ int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr)
 	return 0;
 }
 
-/* Must be called with phy mutex held */
+/* Must be called with SMI mutex held */
 static int _mv88e6xxx_phy_read(struct dsa_switch *ds, int addr, int regnum)
 {
 	if (addr >= 0)
-		return mv88e6xxx_reg_read(ds, addr, regnum);
+		return _mv88e6xxx_reg_read(ds, addr, regnum);
 	return 0xffff;
 }
 
-/* Must be called with phy mutex held */
+/* Must be called with SMI mutex held */
 static int _mv88e6xxx_phy_write(struct dsa_switch *ds, int addr, int regnum,
 				u16 val)
 {
 	if (addr >= 0)
-		return mv88e6xxx_reg_write(ds, addr, regnum, val);
+		return _mv88e6xxx_reg_write(ds, addr, regnum, val);
 	return 0;
 }
 
@@ -434,26 +446,113 @@ void mv88e6xxx_poll_link(struct dsa_switch *ds)
 	}
 }
 
+static bool mv88e6xxx_6065_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6031:
+	case PORT_SWITCH_ID_6061:
+	case PORT_SWITCH_ID_6035:
+	case PORT_SWITCH_ID_6065:
+		return true;
+	}
+	return false;
+}
+
+static bool mv88e6xxx_6095_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6092:
+	case PORT_SWITCH_ID_6095:
+		return true;
+	}
+	return false;
+}
+
+static bool mv88e6xxx_6097_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6046:
+	case PORT_SWITCH_ID_6085:
+	case PORT_SWITCH_ID_6096:
+	case PORT_SWITCH_ID_6097:
+		return true;
+	}
+	return false;
+}
+
+static bool mv88e6xxx_6165_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6123:
+	case PORT_SWITCH_ID_6161:
+	case PORT_SWITCH_ID_6165:
+		return true;
+	}
+	return false;
+}
+
+static bool mv88e6xxx_6185_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6121:
+	case PORT_SWITCH_ID_6122:
+	case PORT_SWITCH_ID_6152:
+	case PORT_SWITCH_ID_6155:
+	case PORT_SWITCH_ID_6182:
+	case PORT_SWITCH_ID_6185:
+	case PORT_SWITCH_ID_6108:
+	case PORT_SWITCH_ID_6131:
+		return true;
+	}
+	return false;
+}
+
+static bool mv88e6xxx_6351_family(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+
+	switch (ps->id) {
+	case PORT_SWITCH_ID_6171:
+	case PORT_SWITCH_ID_6175:
+	case PORT_SWITCH_ID_6350:
+	case PORT_SWITCH_ID_6351:
+		return true;
+	}
+	return false;
+}
+
 static bool mv88e6xxx_6352_family(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 
 	switch (ps->id) {
-	case PORT_SWITCH_ID_6352:
 	case PORT_SWITCH_ID_6172:
 	case PORT_SWITCH_ID_6176:
+	case PORT_SWITCH_ID_6240:
+	case PORT_SWITCH_ID_6352:
 		return true;
 	}
 	return false;
 }
 
-static int mv88e6xxx_stats_wait(struct dsa_switch *ds)
+/* Must be called with SMI mutex held */
+static int _mv88e6xxx_stats_wait(struct dsa_switch *ds)
 {
 	int ret;
 	int i;
 
 	for (i = 0; i < 10; i++) {
-		ret = REG_READ(REG_GLOBAL, GLOBAL_STATS_OP);
+		ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_STATS_OP);
 		if ((ret & GLOBAL_STATS_OP_BUSY) == 0)
 			return 0;
 	}
@@ -461,7 +560,8 @@ static int mv88e6xxx_stats_wait(struct dsa_switch *ds)
 	return -ETIMEDOUT;
 }
 
-static int mv88e6xxx_stats_snapshot(struct dsa_switch *ds, int port)
+/* Must be called with SMI mutex held */
+static int _mv88e6xxx_stats_snapshot(struct dsa_switch *ds, int port)
 {
 	int ret;
 
@@ -469,42 +569,45 @@ static int mv88e6xxx_stats_snapshot(struct dsa_switch *ds, int port)
 		port = (port + 1) << 5;
 
 	/* Snapshot the hardware statistics counters for this port. */
-	REG_WRITE(REG_GLOBAL, GLOBAL_STATS_OP,
-		  GLOBAL_STATS_OP_CAPTURE_PORT |
-		  GLOBAL_STATS_OP_HIST_RX_TX | port);
+	ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_STATS_OP,
+				   GLOBAL_STATS_OP_CAPTURE_PORT |
+				   GLOBAL_STATS_OP_HIST_RX_TX | port);
+	if (ret < 0)
+		return ret;
 
 	/* Wait for the snapshotting to complete. */
-	ret = mv88e6xxx_stats_wait(ds);
+	ret = _mv88e6xxx_stats_wait(ds);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static void mv88e6xxx_stats_read(struct dsa_switch *ds, int stat, u32 *val)
+/* Must be called with SMI mutex held */
+static void _mv88e6xxx_stats_read(struct dsa_switch *ds, int stat, u32 *val)
 {
 	u32 _val;
 	int ret;
 
 	*val = 0;
 
-	ret = mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_STATS_OP,
-				  GLOBAL_STATS_OP_READ_CAPTURED |
-				  GLOBAL_STATS_OP_HIST_RX_TX | stat);
+	ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_STATS_OP,
+				   GLOBAL_STATS_OP_READ_CAPTURED |
+				   GLOBAL_STATS_OP_HIST_RX_TX | stat);
 	if (ret < 0)
 		return;
 
-	ret = mv88e6xxx_stats_wait(ds);
+	ret = _mv88e6xxx_stats_wait(ds);
 	if (ret < 0)
 		return;
 
-	ret = mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_STATS_COUNTER_32);
+	ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_STATS_COUNTER_32);
 	if (ret < 0)
 		return;
 
 	_val = ret << 16;
 
-	ret = mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_STATS_COUNTER_01);
+	ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_STATS_COUNTER_01);
 	if (ret < 0)
 		return;
 
@@ -578,6 +681,40 @@ static void _mv88e6xxx_get_strings(struct dsa_switch *ds,
 	}
 }
 
+static uint64_t _mv88e6xxx_get_ethtool_stat(struct dsa_switch *ds,
+					    int stat,
+					    struct mv88e6xxx_hw_stat *stats,
+					    int port)
+{
+	struct mv88e6xxx_hw_stat *s = stats + stat;
+	u32 low;
+	u32 high = 0;
+	int ret;
+	u64 value;
+
+	if (s->reg >= 0x100) {
+		ret = _mv88e6xxx_reg_read(ds, REG_PORT(port),
+					  s->reg - 0x100);
+		if (ret < 0)
+			return UINT64_MAX;
+
+		low = ret;
+		if (s->sizeof_stat == 4) {
+			ret = _mv88e6xxx_reg_read(ds, REG_PORT(port),
+						  s->reg - 0x100 + 1);
+			if (ret < 0)
+				return UINT64_MAX;
+			high = ret;
+		}
+	} else {
+		_mv88e6xxx_stats_read(ds, s->reg, &low);
+		if (s->sizeof_stat == 8)
+			_mv88e6xxx_stats_read(ds, s->reg + 1, &high);
+	}
+	value = (((u64)high) << 16) | low;
+	return value;
+}
+
 static void _mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds,
 					 int nr_stats,
 					 struct mv88e6xxx_hw_stat *stats,
@@ -587,44 +724,19 @@ static void _mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds,
 	int ret;
 	int i;
 
-	mutex_lock(&ps->stats_mutex);
+	mutex_lock(&ps->smi_mutex);
 
-	ret = mv88e6xxx_stats_snapshot(ds, port);
+	ret = _mv88e6xxx_stats_snapshot(ds, port);
 	if (ret < 0) {
-		mutex_unlock(&ps->stats_mutex);
+		mutex_unlock(&ps->smi_mutex);
 		return;
 	}
 
 	/* Read each of the counters. */
-	for (i = 0; i < nr_stats; i++) {
-		struct mv88e6xxx_hw_stat *s = stats + i;
-		u32 low;
-		u32 high = 0;
+	for (i = 0; i < nr_stats; i++)
+		data[i] = _mv88e6xxx_get_ethtool_stat(ds, i, stats, port);
 
-		if (s->reg >= 0x100) {
-			ret = mv88e6xxx_reg_read(ds, REG_PORT(port),
-						 s->reg - 0x100);
-			if (ret < 0)
-				goto error;
-			low = ret;
-			if (s->sizeof_stat == 4) {
-				ret = mv88e6xxx_reg_read(ds, REG_PORT(port),
-							 s->reg - 0x100 + 1);
-				if (ret < 0)
-					goto error;
-				high = ret;
-			}
-			data[i] = (((u64)high) << 16) | low;
-			continue;
-		}
-		mv88e6xxx_stats_read(ds, s->reg, &low);
-		if (s->sizeof_stat == 8)
-			mv88e6xxx_stats_read(ds, s->reg + 1, &high);
-
-		data[i] = (((u64)high) << 32) | low;
-	}
-error:
-	mutex_unlock(&ps->stats_mutex);
+	mutex_unlock(&ps->smi_mutex);
 }
 
 /* All the statistics in the table */
@@ -694,7 +806,7 @@ int  mv88e6xxx_get_temp(struct dsa_switch *ds, int *temp)
 
 	*temp = 0;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 
 	ret = _mv88e6xxx_phy_write(ds, 0x0, 0x16, 0x6);
 	if (ret < 0)
@@ -727,19 +839,23 @@ int  mv88e6xxx_get_temp(struct dsa_switch *ds, int *temp)
 
 error:
 	_mv88e6xxx_phy_write(ds, 0x0, 0x16, 0x0);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 #endif /* CONFIG_NET_DSA_HWMON */
 
-static int mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset, u16 mask)
+/* Must be called with SMI lock held */
+static int _mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset,
+			   u16 mask)
 {
 	unsigned long timeout = jiffies + HZ / 10;
 
 	while (time_before(jiffies, timeout)) {
 		int ret;
 
-		ret = REG_READ(reg, offset);
+		ret = _mv88e6xxx_reg_read(ds, reg, offset);
+		if (ret < 0)
+			return ret;
 		if (!(ret & mask))
 			return 0;
 
@@ -748,10 +864,22 @@ static int mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset, u16 mask)
 	return -ETIMEDOUT;
 }
 
-int mv88e6xxx_phy_wait(struct dsa_switch *ds)
+static int mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset, u16 mask)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int ret;
+
+	mutex_lock(&ps->smi_mutex);
+	ret = _mv88e6xxx_wait(ds, reg, offset, mask);
+	mutex_unlock(&ps->smi_mutex);
+
+	return ret;
+}
+
+static int _mv88e6xxx_phy_wait(struct dsa_switch *ds)
 {
-	return mv88e6xxx_wait(ds, REG_GLOBAL2, GLOBAL2_SMI_OP,
-			      GLOBAL2_SMI_OP_BUSY);
+	return _mv88e6xxx_wait(ds, REG_GLOBAL2, GLOBAL2_SMI_OP,
+			       GLOBAL2_SMI_OP_BUSY);
 }
 
 int mv88e6xxx_eeprom_load_wait(struct dsa_switch *ds)
@@ -767,56 +895,53 @@ int mv88e6xxx_eeprom_busy_wait(struct dsa_switch *ds)
 }
 
 /* Must be called with SMI lock held */
-static int _mv88e6xxx_wait(struct dsa_switch *ds, int reg, int offset, u16 mask)
+static int _mv88e6xxx_atu_wait(struct dsa_switch *ds)
 {
-	unsigned long timeout = jiffies + HZ / 10;
-
-	while (time_before(jiffies, timeout)) {
-		int ret;
-
-		ret = _mv88e6xxx_reg_read(ds, reg, offset);
-		if (ret < 0)
-			return ret;
-		if (!(ret & mask))
-			return 0;
-
-		usleep_range(1000, 2000);
-	}
-	return -ETIMEDOUT;
+	return _mv88e6xxx_wait(ds, REG_GLOBAL, GLOBAL_ATU_OP,
+			       GLOBAL_ATU_OP_BUSY);
 }
 
 /* Must be called with SMI lock held */
-static int _mv88e6xxx_atu_wait(struct dsa_switch *ds)
+static int _mv88e6xxx_scratch_wait(struct dsa_switch *ds)
 {
-	return _mv88e6xxx_wait(ds, REG_GLOBAL, GLOBAL_ATU_OP,
-			       GLOBAL_ATU_OP_BUSY);
+	return _mv88e6xxx_wait(ds, REG_GLOBAL2, GLOBAL2_SCRATCH_MISC,
+			       GLOBAL2_SCRATCH_BUSY);
 }
 
-/* Must be called with phy mutex held */
+/* Must be called with SMI mutex held */
 static int _mv88e6xxx_phy_read_indirect(struct dsa_switch *ds, int addr,
 					int regnum)
 {
 	int ret;
 
-	REG_WRITE(REG_GLOBAL2, GLOBAL2_SMI_OP,
-		  GLOBAL2_SMI_OP_22_READ | (addr << 5) | regnum);
+	ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL2, GLOBAL2_SMI_OP,
+				   GLOBAL2_SMI_OP_22_READ | (addr << 5) |
+				   regnum);
+	if (ret < 0)
+		return ret;
 
-	ret = mv88e6xxx_phy_wait(ds);
+	ret = _mv88e6xxx_phy_wait(ds);
 	if (ret < 0)
 		return ret;
 
-	return REG_READ(REG_GLOBAL2, GLOBAL2_SMI_DATA);
+	return _mv88e6xxx_reg_read(ds, REG_GLOBAL2, GLOBAL2_SMI_DATA);
 }
 
-/* Must be called with phy mutex held */
+/* Must be called with SMI mutex held */
 static int _mv88e6xxx_phy_write_indirect(struct dsa_switch *ds, int addr,
 					 int regnum, u16 val)
 {
-	REG_WRITE(REG_GLOBAL2, GLOBAL2_SMI_DATA, val);
-	REG_WRITE(REG_GLOBAL2, GLOBAL2_SMI_OP,
-		  GLOBAL2_SMI_OP_22_WRITE | (addr << 5) | regnum);
+	int ret;
 
-	return mv88e6xxx_phy_wait(ds);
+	ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL2, GLOBAL2_SMI_DATA, val);
+	if (ret < 0)
+		return ret;
+
+	ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL2, GLOBAL2_SMI_OP,
+				   GLOBAL2_SMI_OP_22_WRITE | (addr << 5) |
+				   regnum);
+
+	return _mv88e6xxx_phy_wait(ds);
 }
 
 int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
@@ -824,7 +949,7 @@ int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int reg;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 
 	reg = _mv88e6xxx_phy_read_indirect(ds, port, 16);
 	if (reg < 0)
@@ -833,7 +958,7 @@ int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
 	e->eee_enabled = !!(reg & 0x0200);
 	e->tx_lpi_enabled = !!(reg & 0x0100);
 
-	reg = mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_STATUS);
+	reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_STATUS);
 	if (reg < 0)
 		goto out;
 
@@ -841,7 +966,7 @@ int mv88e6xxx_get_eee(struct dsa_switch *ds, int port, struct ethtool_eee *e)
 	reg = 0;
 
 out:
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return reg;
 }
 
@@ -852,7 +977,7 @@ int mv88e6xxx_set_eee(struct dsa_switch *ds, int port,
 	int reg;
 	int ret;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 
 	ret = _mv88e6xxx_phy_read_indirect(ds, port, 16);
 	if (ret < 0)
@@ -866,7 +991,7 @@ int mv88e6xxx_set_eee(struct dsa_switch *ds, int port,
 
 	ret = _mv88e6xxx_phy_write_indirect(ds, port, 16, reg);
 out:
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 
 	return ret;
 }
@@ -1241,13 +1366,212 @@ static void mv88e6xxx_bridge_work(struct work_struct *work)
 	}
 }
 
-int mv88e6xxx_setup_port_common(struct dsa_switch *ds, int port)
+static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret, fid;
+	u16 reg;
 
 	mutex_lock(&ps->smi_mutex);
 
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds) ||
+	    mv88e6xxx_6065_family(ds)) {
+		/* MAC Forcing register: don't force link, speed,
+		 * duplex or flow control state to any particular
+		 * values on physical ports, but force the CPU port
+		 * and all DSA ports to their maximum bandwidth and
+		 * full duplex.
+		 */
+		reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL);
+		if (dsa_is_cpu_port(ds, port) ||
+		    ds->dsa_port_mask & (1 << port)) {
+			reg |= PORT_PCS_CTRL_FORCE_LINK |
+				PORT_PCS_CTRL_LINK_UP |
+				PORT_PCS_CTRL_DUPLEX_FULL |
+				PORT_PCS_CTRL_FORCE_DUPLEX;
+			if (mv88e6xxx_6065_family(ds))
+				reg |= PORT_PCS_CTRL_100;
+			else
+				reg |= PORT_PCS_CTRL_1000;
+		} else {
+			reg |= PORT_PCS_CTRL_UNFORCED;
+		}
+
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_PCS_CTRL, reg);
+		if (ret)
+			goto abort;
+	}
+
+	/* Port Control: disable Drop-on-Unlock, disable Drop-on-Lock,
+	 * disable Header mode, enable IGMP/MLD snooping, disable VLAN
+	 * tunneling, determine priority by looking at 802.1p and IP
+	 * priority fields (IP prio has precedence), and set STP state
+	 * to Forwarding.
+	 *
+	 * If this is the CPU link, use DSA or EDSA tagging depending
+	 * on which tagging mode was configured.
+	 *
+	 * If this is a link to another switch, use DSA tagging mode.
+	 *
+	 * If this is the upstream port for this switch, enable
+	 * forwarding of unknown unicasts and multicasts.
+	 */
+	reg = 0;
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds) ||
+	    mv88e6xxx_6185_family(ds))
+		reg = PORT_CONTROL_IGMP_MLD_SNOOP |
+		PORT_CONTROL_USE_TAG | PORT_CONTROL_USE_IP |
+		PORT_CONTROL_STATE_FORWARDING;
+	if (dsa_is_cpu_port(ds, port)) {
+		if (mv88e6xxx_6095_family(ds) || mv88e6xxx_6185_family(ds))
+			reg |= PORT_CONTROL_DSA_TAG;
+		if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+		    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) {
+			if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
+				reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA;
+			else
+				reg |= PORT_CONTROL_FRAME_MODE_DSA;
+		}
+
+		if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+		    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+		    mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds) ||
+		    mv88e6xxx_6185_family(ds)) {
+			if (ds->dst->tag_protocol == DSA_TAG_PROTO_EDSA)
+				reg |= PORT_CONTROL_EGRESS_ADD_TAG;
+		}
+	}
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6095_family(ds) || mv88e6xxx_6065_family(ds)) {
+		if (ds->dsa_port_mask & (1 << port))
+			reg |= PORT_CONTROL_FRAME_MODE_DSA;
+		if (port == dsa_upstream_port(ds))
+			reg |= PORT_CONTROL_FORWARD_UNKNOWN |
+				PORT_CONTROL_FORWARD_UNKNOWN_MC;
+	}
+	if (reg) {
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_CONTROL, reg);
+		if (ret)
+			goto abort;
+	}
+
+	/* Port Control 2: don't force a good FCS, set the maximum
+	 * frame size to 10240 bytes, don't let the switch add or
+	 * strip 802.1q tags, don't discard tagged or untagged frames
+	 * on this port, do a destination address lookup on all
+	 * received packets as usual, disable ARP mirroring and don't
+	 * send a copy of all transmitted/received frames on this port
+	 * to the CPU.
+	 */
+	reg = 0;
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6095_family(ds))
+		reg = PORT_CONTROL_2_MAP_DA;
+
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds))
+		reg |= PORT_CONTROL_2_JUMBO_10240;
+
+	if (mv88e6xxx_6095_family(ds) || mv88e6xxx_6185_family(ds)) {
+		/* Set the upstream port this port should use */
+		reg |= dsa_upstream_port(ds);
+		/* enable forwarding of unknown multicast addresses to
+		 * the upstream port
+		 */
+		if (port == dsa_upstream_port(ds))
+			reg |= PORT_CONTROL_2_FORWARD_UNKNOWN;
+	}
+
+	if (reg) {
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_CONTROL_2, reg);
+		if (ret)
+			goto abort;
+	}
+
+	/* Port Association Vector: when learning source addresses
+	 * of packets, add the address to the address database using
+	 * a port bitmap that has only the bit for this port set and
+	 * the other bits clear.
+	 */
+	ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_ASSOC_VECTOR,
+				   1 << port);
+	if (ret)
+		goto abort;
+
+	/* Egress rate control 2: disable egress rate control. */
+	ret = _mv88e6xxx_reg_write(ds, REG_PORT(port), PORT_RATE_CONTROL_2,
+				   0x0000);
+	if (ret)
+		goto abort;
+
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) {
+		/* Do not limit the period of time that this port can
+		 * be paused for by the remote end or the period of
+		 * time that this port can pause the remote end.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_PAUSE_CTRL, 0x0000);
+		if (ret)
+			goto abort;
+
+		/* Port ATU control: disable limiting the number of
+		 * address database entries that this port is allowed
+		 * to use.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_ATU_CONTROL, 0x0000);
+		/* Priority Override: disable DA, SA and VTU priority
+		 * override.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_PRI_OVERRIDE, 0x0000);
+		if (ret)
+			goto abort;
+
+		/* Port Ethertype: use the Ethertype DSA Ethertype
+		 * value.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_ETH_TYPE, ETH_P_EDSA);
+		if (ret)
+			goto abort;
+		/* Tag Remap: use an identity 802.1p prio -> switch
+		 * prio mapping.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_TAG_REGMAP_0123, 0x3210);
+		if (ret)
+			goto abort;
+
+		/* Tag Remap 2: use an identity 802.1p prio -> switch
+		 * prio mapping.
+		 */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_TAG_REGMAP_4567, 0x7654);
+		if (ret)
+			goto abort;
+	}
+
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds)) {
+		/* Rate Control: disable ingress rate limiting. */
+		ret = _mv88e6xxx_reg_write(ds, REG_PORT(port),
+					   PORT_RATE_CONTROL, 0x0001);
+		if (ret)
+			goto abort;
+	}
+
 	/* Port Control 1: disable trunking, disable sending
 	 * learning messages to this port.
 	 */
@@ -1281,13 +1605,283 @@ abort:
 	return ret;
 }
 
+int mv88e6xxx_setup_ports(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int ret;
+	int i;
+
+	for (i = 0; i < ps->num_ports; i++) {
+		ret = mv88e6xxx_setup_port(ds, i);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+static int mv88e6xxx_regs_show(struct seq_file *s, void *p)
+{
+	struct dsa_switch *ds = s->private;
+
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int reg, port;
+
+	seq_puts(s, "    GLOBAL GLOBAL2 ");
+	for (port = 0 ; port < ps->num_ports; port++)
+		seq_printf(s, " %2d  ", port);
+	seq_puts(s, "\n");
+
+	for (reg = 0; reg < 32; reg++) {
+		seq_printf(s, "%2x: ", reg);
+		seq_printf(s, " %4x    %4x  ",
+			   mv88e6xxx_reg_read(ds, REG_GLOBAL, reg),
+			   mv88e6xxx_reg_read(ds, REG_GLOBAL2, reg));
+
+		for (port = 0 ; port < ps->num_ports; port++)
+			seq_printf(s, "%4x ",
+				   mv88e6xxx_reg_read(ds, REG_PORT(port), reg));
+		seq_puts(s, "\n");
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_regs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mv88e6xxx_regs_show, inode->i_private);
+}
+
+static const struct file_operations mv88e6xxx_regs_fops = {
+	.open   = mv88e6xxx_regs_open,
+	.read   = seq_read,
+	.llseek = no_llseek,
+	.release = single_release,
+	.owner  = THIS_MODULE,
+};
+
+static void mv88e6xxx_atu_show_header(struct seq_file *s)
+{
+	seq_puts(s, "DB   T/P  Vec State Addr\n");
+}
+
+static void mv88e6xxx_atu_show_entry(struct seq_file *s, int dbnum,
+				     unsigned char *addr, int data)
+{
+	bool trunk = !!(data & GLOBAL_ATU_DATA_TRUNK);
+	int portvec = ((data & GLOBAL_ATU_DATA_PORT_VECTOR_MASK) >>
+		       GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT);
+	int state = data & GLOBAL_ATU_DATA_STATE_MASK;
+
+	seq_printf(s, "%03x %5s %10pb   %x   %pM\n",
+		   dbnum, (trunk ? "Trunk" : "Port"), &portvec, state, addr);
+}
+
+static int mv88e6xxx_atu_show_db(struct seq_file *s, struct dsa_switch *ds,
+				 int dbnum)
+{
+	unsigned char bcast[] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+	unsigned char addr[6];
+	int ret, data, state;
+
+	ret = __mv88e6xxx_write_addr(ds, bcast);
+	if (ret < 0)
+		return ret;
+
+	do {
+		ret = _mv88e6xxx_atu_cmd(ds, dbnum, GLOBAL_ATU_OP_GET_NEXT_DB);
+		if (ret < 0)
+			return ret;
+		data = _mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_ATU_DATA);
+		if (data < 0)
+			return data;
+
+		state = data & GLOBAL_ATU_DATA_STATE_MASK;
+		if (state == GLOBAL_ATU_DATA_STATE_UNUSED)
+			break;
+		ret = __mv88e6xxx_read_addr(ds, addr);
+		if (ret < 0)
+			return ret;
+		mv88e6xxx_atu_show_entry(s, dbnum, addr, data);
+	} while (state != GLOBAL_ATU_DATA_STATE_UNUSED);
+
+	return 0;
+}
+
+static int mv88e6xxx_atu_show(struct seq_file *s, void *p)
+{
+	struct dsa_switch *ds = s->private;
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int dbnum;
+
+	mv88e6xxx_atu_show_header(s);
+
+	for (dbnum = 0; dbnum < 255; dbnum++) {
+		mutex_lock(&ps->smi_mutex);
+		mv88e6xxx_atu_show_db(s, ds, dbnum);
+		mutex_unlock(&ps->smi_mutex);
+	}
+
+	return 0;
+}
+
+static int mv88e6xxx_atu_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mv88e6xxx_atu_show, inode->i_private);
+}
+
+static const struct file_operations mv88e6xxx_atu_fops = {
+	.open   = mv88e6xxx_atu_open,
+	.read   = seq_read,
+	.llseek = no_llseek,
+	.release = single_release,
+	.owner  = THIS_MODULE,
+};
+
+static void mv88e6xxx_stats_show_header(struct seq_file *s,
+					struct mv88e6xxx_priv_state *ps)
+{
+	int port;
+
+	seq_puts(s, "      Statistic       ");
+	for (port = 0 ; port < ps->num_ports; port++)
+		seq_printf(s, "Port %2d  ", port);
+	seq_puts(s, "\n");
+}
+
+static int mv88e6xxx_stats_show(struct seq_file *s, void *p)
+{
+	struct dsa_switch *ds = s->private;
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	struct mv88e6xxx_hw_stat *stats = mv88e6xxx_hw_stats;
+	int port, stat, max_stats;
+	uint64_t value;
+
+	if (have_sw_in_discards(ds))
+		max_stats = ARRAY_SIZE(mv88e6xxx_hw_stats);
+	else
+		max_stats = ARRAY_SIZE(mv88e6xxx_hw_stats) - 3;
+
+	mv88e6xxx_stats_show_header(s, ps);
+
+	mutex_lock(&ps->smi_mutex);
+
+	for (stat = 0; stat < max_stats; stat++) {
+		seq_printf(s, "%19s: ", stats[stat].string);
+		for (port = 0 ; port < ps->num_ports; port++) {
+			_mv88e6xxx_stats_snapshot(ds, port);
+			value = _mv88e6xxx_get_ethtool_stat(ds, stat, stats,
+							    port);
+			seq_printf(s, "%8llu ", value);
+		}
+		seq_puts(s, "\n");
+	}
+	mutex_unlock(&ps->smi_mutex);
+
+	return 0;
+}
+
+static int mv88e6xxx_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mv88e6xxx_stats_show, inode->i_private);
+}
+
+static const struct file_operations mv88e6xxx_stats_fops = {
+	.open   = mv88e6xxx_stats_open,
+	.read   = seq_read,
+	.llseek = no_llseek,
+	.release = single_release,
+	.owner  = THIS_MODULE,
+};
+
+static int mv88e6xxx_device_map_show(struct seq_file *s, void *p)
+{
+	struct dsa_switch *ds = s->private;
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int target, ret;
+
+	seq_puts(s, "Target Port\n");
+
+	mutex_lock(&ps->smi_mutex);
+	for (target = 0; target < 32; target++) {
+		ret = _mv88e6xxx_reg_write(
+			ds, REG_GLOBAL2, GLOBAL2_DEVICE_MAPPING,
+			target << GLOBAL2_DEVICE_MAPPING_TARGET_SHIFT);
+		if (ret < 0)
+			goto out;
+		ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL2,
+					  GLOBAL2_DEVICE_MAPPING);
+		seq_printf(s, "  %2d   %2d\n", target,
+			   ret & GLOBAL2_DEVICE_MAPPING_PORT_MASK);
+	}
+out:
+	mutex_unlock(&ps->smi_mutex);
+
+	return 0;
+}
+
+static int mv88e6xxx_device_map_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mv88e6xxx_device_map_show, inode->i_private);
+}
+
+static const struct file_operations mv88e6xxx_device_map_fops = {
+	.open   = mv88e6xxx_device_map_open,
+	.read   = seq_read,
+	.llseek = no_llseek,
+	.release = single_release,
+	.owner  = THIS_MODULE,
+};
+
+static int mv88e6xxx_scratch_show(struct seq_file *s, void *p)
+{
+	struct dsa_switch *ds = s->private;
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int reg, ret;
+
+	seq_puts(s, "Register Value\n");
+
+	mutex_lock(&ps->smi_mutex);
+	for (reg = 0; reg < 0x80; reg++) {
+		ret = _mv88e6xxx_reg_write(
+			ds, REG_GLOBAL2, GLOBAL2_SCRATCH_MISC,
+			reg << GLOBAL2_SCRATCH_REGISTER_SHIFT);
+		if (ret < 0)
+			goto out;
+
+		ret = _mv88e6xxx_scratch_wait(ds);
+		if (ret < 0)
+			goto out;
+
+		ret = _mv88e6xxx_reg_read(ds, REG_GLOBAL2,
+					  GLOBAL2_SCRATCH_MISC);
+		seq_printf(s, "  %2x   %2x\n", reg,
+			   ret & GLOBAL2_SCRATCH_VALUE_MASK);
+	}
+out:
+	mutex_unlock(&ps->smi_mutex);
+
+	return 0;
+}
+
+static int mv88e6xxx_scratch_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mv88e6xxx_scratch_show, inode->i_private);
+}
+
+static const struct file_operations mv88e6xxx_scratch_fops = {
+	.open   = mv88e6xxx_scratch_open,
+	.read   = seq_read,
+	.llseek = no_llseek,
+	.release = single_release,
+	.owner  = THIS_MODULE,
+};
+
 int mv88e6xxx_setup_common(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	char *name;
 
 	mutex_init(&ps->smi_mutex);
-	mutex_init(&ps->stats_mutex);
-	mutex_init(&ps->phy_mutex);
 
 	ps->id = REG_READ(REG_PORT(0), PORT_SWITCH_ID) & 0xfff0;
 
@@ -1295,6 +1889,128 @@ int mv88e6xxx_setup_common(struct dsa_switch *ds)
 
 	INIT_WORK(&ps->bridge_work, mv88e6xxx_bridge_work);
 
+	name = kasprintf(GFP_KERNEL, "dsa%d", ds->index);
+	ps->dbgfs = debugfs_create_dir(name, NULL);
+	kfree(name);
+
+	debugfs_create_file("regs", S_IRUGO, ps->dbgfs, ds,
+			    &mv88e6xxx_regs_fops);
+
+	debugfs_create_file("atu", S_IRUGO, ps->dbgfs, ds,
+			    &mv88e6xxx_atu_fops);
+
+	debugfs_create_file("stats", S_IRUGO, ps->dbgfs, ds,
+			    &mv88e6xxx_stats_fops);
+
+	debugfs_create_file("device_map", S_IRUGO, ps->dbgfs, ds,
+			    &mv88e6xxx_device_map_fops);
+
+	debugfs_create_file("scratch", S_IRUGO, ps->dbgfs, ds,
+			    &mv88e6xxx_scratch_fops);
+	return 0;
+}
+
+int mv88e6xxx_setup_global(struct dsa_switch *ds)
+{
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
+	int i;
+
+	/* Set the default address aging time to 5 minutes, and
+	 * enable address learn messages to be sent to all message
+	 * ports.
+	 */
+	REG_WRITE(REG_GLOBAL, GLOBAL_ATU_CONTROL,
+		  0x0140 | GLOBAL_ATU_CONTROL_LEARN2ALL);
+
+	/* Configure the IP ToS mapping registers. */
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_0, 0x0000);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_1, 0x0000);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_2, 0x5555);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_3, 0x5555);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_4, 0xaaaa);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_5, 0xaaaa);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_6, 0xffff);
+	REG_WRITE(REG_GLOBAL, GLOBAL_IP_PRI_7, 0xffff);
+
+	/* Configure the IEEE 802.1p priority mapping register. */
+	REG_WRITE(REG_GLOBAL, GLOBAL_IEEE_PRI, 0xfa41);
+
+	/* Send all frames with destination addresses matching
+	 * 01:80:c2:00:00:0x to the CPU port.
+	 */
+	REG_WRITE(REG_GLOBAL2, GLOBAL2_MGMT_EN_0X, 0xffff);
+
+	/* Ignore removed tag data on doubly tagged packets, disable
+	 * flow control messages, force flow control priority to the
+	 * highest, and send all special multicast frames to the CPU
+	 * port at the highest priority.
+	 */
+	REG_WRITE(REG_GLOBAL2, GLOBAL2_SWITCH_MGMT,
+		  0x7 | GLOBAL2_SWITCH_MGMT_RSVD2CPU | 0x70 |
+		  GLOBAL2_SWITCH_MGMT_FORCE_FLOW_CTRL_PRI);
+
+	/* Program the DSA routing table. */
+	for (i = 0; i < 32; i++) {
+		int nexthop = 0x1f;
+
+		if (ds->pd->rtable &&
+		    i != ds->index && i < ds->dst->pd->nr_chips)
+			nexthop = ds->pd->rtable[i] & 0x1f;
+
+		REG_WRITE(REG_GLOBAL2, GLOBAL2_DEVICE_MAPPING,
+			  GLOBAL2_DEVICE_MAPPING_UPDATE |
+			  (i << GLOBAL2_DEVICE_MAPPING_TARGET_SHIFT) |
+			  nexthop);
+	}
+
+	/* Clear all trunk masks. */
+	for (i = 0; i < 8; i++)
+		REG_WRITE(REG_GLOBAL2, GLOBAL2_TRUNK_MASK,
+			  0x8000 | (i << GLOBAL2_TRUNK_MASK_NUM_SHIFT) |
+			  ((1 << ps->num_ports) - 1));
+
+	/* Clear all trunk mappings. */
+	for (i = 0; i < 16; i++)
+		REG_WRITE(REG_GLOBAL2, GLOBAL2_TRUNK_MAPPING,
+			  GLOBAL2_TRUNK_MAPPING_UPDATE |
+			  (i << GLOBAL2_TRUNK_MAPPING_ID_SHIFT));
+
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds)) {
+		/* Send all frames with destination addresses matching
+		 * 01:80:c2:00:00:2x to the CPU port.
+		 */
+		REG_WRITE(REG_GLOBAL2, GLOBAL2_MGMT_EN_2X, 0xffff);
+
+		/* Initialise cross-chip port VLAN table to reset
+		 * defaults.
+		 */
+		REG_WRITE(REG_GLOBAL2, GLOBAL2_PVT_ADDR, 0x9000);
+
+		/* Clear the priority override table. */
+		for (i = 0; i < 16; i++)
+			REG_WRITE(REG_GLOBAL2, GLOBAL2_PRIO_OVERRIDE,
+				  0x8000 | (i << 8));
+	}
+
+	if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
+	    mv88e6xxx_6165_family(ds) || mv88e6xxx_6097_family(ds) ||
+	    mv88e6xxx_6185_family(ds) || mv88e6xxx_6095_family(ds)) {
+		/* Disable ingress rate limiting by resetting all
+		 * ingress rate limit registers to their initial
+		 * state.
+		 */
+		for (i = 0; i < ps->num_ports; i++)
+			REG_WRITE(REG_GLOBAL2, GLOBAL2_INGRESS_OP,
+				  0x9000 | (i << 8));
+	}
+
+	/* Clear the statistics counters for all ports */
+	REG_WRITE(REG_GLOBAL, GLOBAL_STATS_OP, GLOBAL_STATS_OP_FLUSH_ALL);
+
+	/* Wait for the flush to complete. */
+	_mv88e6xxx_stats_wait(ds);
+
 	return 0;
 }
 
@@ -1343,14 +2059,14 @@ int mv88e6xxx_phy_page_read(struct dsa_switch *ds, int port, int page, int reg)
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page);
 	if (ret < 0)
 		goto error;
 	ret = _mv88e6xxx_phy_read_indirect(ds, port, reg);
 error:
 	_mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1360,7 +2076,7 @@ int mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page,
 	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_write_indirect(ds, port, 0x16, page);
 	if (ret < 0)
 		goto error;
@@ -1368,7 +2084,7 @@ int mv88e6xxx_phy_page_write(struct dsa_switch *ds, int port, int page,
 	ret = _mv88e6xxx_phy_write_indirect(ds, port, reg, val);
 error:
 	_mv88e6xxx_phy_write_indirect(ds, port, 0x16, 0x0);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1391,9 +2107,9 @@ mv88e6xxx_phy_read(struct dsa_switch *ds, int port, int regnum)
 	if (addr < 0)
 		return addr;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_read(ds, addr, regnum);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1407,9 +2123,9 @@ mv88e6xxx_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val)
 	if (addr < 0)
 		return addr;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_write(ds, addr, regnum, val);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1423,9 +2139,9 @@ mv88e6xxx_phy_read_indirect(struct dsa_switch *ds, int port, int regnum)
 	if (addr < 0)
 		return addr;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_read_indirect(ds, addr, regnum);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1440,9 +2156,9 @@ mv88e6xxx_phy_write_indirect(struct dsa_switch *ds, int port, int regnum,
 	if (addr < 0)
 		return addr;
 
-	mutex_lock(&ps->phy_mutex);
+	mutex_lock(&ps->smi_mutex);
 	ret = _mv88e6xxx_phy_write_indirect(ds, addr, regnum, val);
-	mutex_unlock(&ps->phy_mutex);
+	mutex_unlock(&ps->smi_mutex);
 	return ret;
 }
 
@@ -1469,6 +2185,9 @@ static void __exit mv88e6xxx_cleanup(void)
 #if IS_ENABLED(CONFIG_NET_DSA_MV88E6171)
 	unregister_switch_driver(&mv88e6171_switch_driver);
 #endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6352)
+	unregister_switch_driver(&mv88e6352_switch_driver);
+#endif
 #if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
 	unregister_switch_driver(&mv88e6123_61_65_switch_driver);
 #endif
diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h
index e045154f3364..a650b2656de9 100644
--- a/drivers/net/dsa/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx.h
@@ -11,6 +11,10 @@
 #ifndef __MV88E6XXX_H
 #define __MV88E6XXX_H
 
+#ifndef UINT64_MAX
+#define UINT64_MAX		(u64)(~((u64)0))
+#endif
+
 #define SMI_CMD			0x00
 #define SMI_CMD_BUSY		BIT(15)
 #define SMI_CMD_CLAUSE_22	BIT(12)
@@ -40,9 +44,31 @@
 #define PORT_STATUS_TX_PAUSED	BIT(5)
 #define PORT_STATUS_FLOW_CTRL	BIT(4)
 #define PORT_PCS_CTRL		0x01
+#define PORT_PCS_CTRL_FC		BIT(7)
+#define PORT_PCS_CTRL_FORCE_FC		BIT(6)
+#define PORT_PCS_CTRL_LINK_UP		BIT(5)
+#define PORT_PCS_CTRL_FORCE_LINK	BIT(4)
+#define PORT_PCS_CTRL_DUPLEX_FULL	BIT(3)
+#define PORT_PCS_CTRL_FORCE_DUPLEX	BIT(2)
+#define PORT_PCS_CTRL_10		0x00
+#define PORT_PCS_CTRL_100		0x01
+#define PORT_PCS_CTRL_1000		0x02
+#define PORT_PCS_CTRL_UNFORCED		0x03
+#define PORT_PAUSE_CTRL		0x02
 #define PORT_SWITCH_ID		0x03
+#define PORT_SWITCH_ID_6031	0x0310
+#define PORT_SWITCH_ID_6035	0x0350
+#define PORT_SWITCH_ID_6046	0x0480
+#define PORT_SWITCH_ID_6061	0x0610
+#define PORT_SWITCH_ID_6065	0x0650
 #define PORT_SWITCH_ID_6085	0x04a0
+#define PORT_SWITCH_ID_6092	0x0970
 #define PORT_SWITCH_ID_6095	0x0950
+#define PORT_SWITCH_ID_6096	0x0980
+#define PORT_SWITCH_ID_6097	0x0990
+#define PORT_SWITCH_ID_6108	0x1070
+#define PORT_SWITCH_ID_6121	0x1040
+#define PORT_SWITCH_ID_6122	0x1050
 #define PORT_SWITCH_ID_6123	0x1210
 #define PORT_SWITCH_ID_6123_A1	0x1212
 #define PORT_SWITCH_ID_6123_A2	0x1213
@@ -58,13 +84,38 @@
 #define PORT_SWITCH_ID_6165_A2	0x1653
 #define PORT_SWITCH_ID_6171	0x1710
 #define PORT_SWITCH_ID_6172	0x1720
+#define PORT_SWITCH_ID_6175	0x1750
 #define PORT_SWITCH_ID_6176	0x1760
 #define PORT_SWITCH_ID_6182	0x1a60
 #define PORT_SWITCH_ID_6185	0x1a70
+#define PORT_SWITCH_ID_6240	0x2400
+#define PORT_SWITCH_ID_6320	0x1250
+#define PORT_SWITCH_ID_6350	0x3710
+#define PORT_SWITCH_ID_6351	0x3750
 #define PORT_SWITCH_ID_6352	0x3520
 #define PORT_SWITCH_ID_6352_A0	0x3521
 #define PORT_SWITCH_ID_6352_A1	0x3522
 #define PORT_CONTROL		0x04
+#define PORT_CONTROL_USE_CORE_TAG	BIT(15)
+#define PORT_CONTROL_DROP_ON_LOCK	BIT(14)
+#define PORT_CONTROL_EGRESS_UNMODIFIED	(0x0 << 12)
+#define PORT_CONTROL_EGRESS_UNTAGGED	(0x1 << 12)
+#define PORT_CONTROL_EGRESS_TAGGED	(0x2 << 12)
+#define PORT_CONTROL_EGRESS_ADD_TAG	(0x3 << 12)
+#define PORT_CONTROL_HEADER		BIT(11)
+#define PORT_CONTROL_IGMP_MLD_SNOOP	BIT(10)
+#define PORT_CONTROL_DOUBLE_TAG		BIT(9)
+#define PORT_CONTROL_FRAME_MODE_NORMAL		(0x0 << 8)
+#define PORT_CONTROL_FRAME_MODE_DSA		(0x1 << 8)
+#define PORT_CONTROL_FRAME_MODE_PROVIDER	(0x2 << 8)
+#define PORT_CONTROL_FRAME_ETHER_TYPE_DSA	(0x3 << 8)
+#define PORT_CONTROL_DSA_TAG		BIT(8)
+#define PORT_CONTROL_VLAN_TUNNEL	BIT(7)
+#define PORT_CONTROL_TAG_IF_BOTH	BIT(6)
+#define PORT_CONTROL_USE_IP		BIT(5)
+#define PORT_CONTROL_USE_TAG		BIT(4)
+#define PORT_CONTROL_FORWARD_UNKNOWN_MC	BIT(3)
+#define PORT_CONTROL_FORWARD_UNKNOWN	BIT(2)
 #define PORT_CONTROL_STATE_MASK		0x03
 #define PORT_CONTROL_STATE_DISABLED	0x00
 #define PORT_CONTROL_STATE_BLOCKING	0x01
@@ -74,15 +125,32 @@
 #define PORT_BASE_VLAN		0x06
 #define PORT_DEFAULT_VLAN	0x07
 #define PORT_CONTROL_2		0x08
+#define PORT_CONTROL_2_IGNORE_FCS	BIT(15)
+#define PORT_CONTROL_2_VTU_PRI_OVERRIDE	BIT(14)
+#define PORT_CONTROL_2_SA_PRIO_OVERRIDE	BIT(13)
+#define PORT_CONTROL_2_DA_PRIO_OVERRIDE	BIT(12)
+#define PORT_CONTROL_2_JUMBO_1522	(0x00 << 12)
+#define PORT_CONTROL_2_JUMBO_2048	(0x01 << 12)
+#define PORT_CONTROL_2_JUMBO_10240	(0x02 << 12)
+#define PORT_CONTROL_2_DISCARD_TAGGED	BIT(9)
+#define PORT_CONTROL_2_DISCARD_UNTAGGED	BIT(8)
+#define PORT_CONTROL_2_MAP_DA		BIT(7)
+#define PORT_CONTROL_2_DEFAULT_FORWARD	BIT(6)
+#define PORT_CONTROL_2_FORWARD_UNKNOWN	BIT(6)
+#define PORT_CONTROL_2_EGRESS_MONITOR	BIT(5)
+#define PORT_CONTROL_2_INGRESS_MONITOR	BIT(4)
 #define PORT_RATE_CONTROL	0x09
 #define PORT_RATE_CONTROL_2	0x0a
 #define PORT_ASSOC_VECTOR	0x0b
+#define PORT_ATU_CONTROL	0x0c
+#define PORT_PRI_OVERRIDE	0x0d
+#define PORT_ETH_TYPE		0x0f
 #define PORT_IN_DISCARD_LO	0x10
 #define PORT_IN_DISCARD_HI	0x11
 #define PORT_IN_FILTERED	0x12
 #define PORT_OUT_FILTERED	0x13
-#define PORT_TAG_REGMAP_0123	0x19
-#define PORT_TAG_REGMAP_4567	0x1a
+#define PORT_TAG_REGMAP_0123	0x18
+#define PORT_TAG_REGMAP_4567	0x19
 
 #define REG_GLOBAL		0x1b
 #define GLOBAL_STATUS		0x00
@@ -102,7 +170,7 @@
 #define GLOBAL_CONTROL_DISCARD_EXCESS	BIT(13) /* 6352 */
 #define GLOBAL_CONTROL_SCHED_PRIO	BIT(11) /* 6152 */
 #define GLOBAL_CONTROL_MAX_FRAME_1632	BIT(10) /* 6152 */
-#define GLOBAL_CONTROL_RELOAD_EEPROM	BIT(9)  /* 6152 */
+#define GLOBAL_CONTROL_RELOAD_EEPROM	BIT(9)	/* 6152 */
 #define GLOBAL_CONTROL_DEVICE_EN	BIT(7)
 #define GLOBAL_CONTROL_STATS_DONE_EN	BIT(6)
 #define GLOBAL_CONTROL_VTU_PROBLEM_EN	BIT(5)
@@ -117,6 +185,7 @@
 #define GLOBAL_VTU_DATA_4_7	0x08
 #define GLOBAL_VTU_DATA_8_11	0x09
 #define GLOBAL_ATU_CONTROL	0x0a
+#define GLOBAL_ATU_CONTROL_LEARN2ALL	BIT(3)
 #define GLOBAL_ATU_OP		0x0b
 #define GLOBAL_ATU_OP_BUSY	BIT(15)
 #define GLOBAL_ATU_OP_NOP		(0 << 12)
@@ -128,6 +197,9 @@
 #define GLOBAL_ATU_OP_FLUSH_NON_STATIC_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY)
 #define GLOBAL_ATU_OP_GET_CLR_VIOLATION	  ((7 << 12) | GLOBAL_ATU_OP_BUSY)
 #define GLOBAL_ATU_DATA		0x0c
+#define GLOBAL_ATU_DATA_TRUNK			BIT(15)
+#define GLOBAL_ATU_DATA_PORT_VECTOR_MASK	0x3ff0
+#define GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT	4
 #define GLOBAL_ATU_DATA_STATE_MASK		0x0f
 #define GLOBAL_ATU_DATA_STATE_UNUSED		0x00
 #define GLOBAL_ATU_DATA_STATE_UC_MGMT		0x0d
@@ -151,7 +223,15 @@
 #define GLOBAL_IEEE_PRI		0x18
 #define GLOBAL_CORE_TAG_TYPE	0x19
 #define GLOBAL_MONITOR_CONTROL	0x1a
+#define GLOBAL_MONITOR_CONTROL_INGRESS_SHIFT	12
+#define GLOBAL_MONITOR_CONTROL_EGRESS_SHIFT	8
+#define GLOBAL_MONITOR_CONTROL_ARP_SHIFT	4
+#define GLOBAL_MONITOR_CONTROL_MIRROR_SHIFT	0
+#define GLOBAL_MONITOR_CONTROL_ARP_DISABLED	(0xf0)
 #define GLOBAL_CONTROL_2	0x1c
+#define GLOBAL_CONTROL_2_NO_CASCADE		0xe000
+#define GLOBAL_CONTROL_2_MULTIPLE_CASCADE	0xf000
+
 #define GLOBAL_STATS_OP		0x1d
 #define GLOBAL_STATS_OP_BUSY	BIT(15)
 #define GLOBAL_STATS_OP_NOP		(0 << 12)
@@ -172,9 +252,21 @@
 #define GLOBAL2_MGMT_EN_0X	0x03
 #define GLOBAL2_FLOW_CONTROL	0x04
 #define GLOBAL2_SWITCH_MGMT	0x05
+#define GLOBAL2_SWITCH_MGMT_USE_DOUBLE_TAG_DATA	BIT(15)
+#define GLOBAL2_SWITCH_MGMT_PREVENT_LOOPS	BIT(14)
+#define GLOBAL2_SWITCH_MGMT_FLOW_CONTROL_MSG	BIT(13)
+#define GLOBAL2_SWITCH_MGMT_FORCE_FLOW_CTRL_PRI	BIT(7)
+#define GLOBAL2_SWITCH_MGMT_RSVD2CPU		BIT(3)
 #define GLOBAL2_DEVICE_MAPPING	0x06
+#define GLOBAL2_DEVICE_MAPPING_UPDATE		BIT(15)
+#define GLOBAL2_DEVICE_MAPPING_TARGET_SHIFT	8
+#define GLOBAL2_DEVICE_MAPPING_PORT_MASK	0x0f
 #define GLOBAL2_TRUNK_MASK	0x07
+#define GLOBAL2_TRUNK_MASK_UPDATE		BIT(15)
+#define GLOBAL2_TRUNK_MASK_NUM_SHIFT		12
 #define GLOBAL2_TRUNK_MAPPING	0x08
+#define GLOBAL2_TRUNK_MAPPING_UPDATE		BIT(15)
+#define GLOBAL2_TRUNK_MAPPING_ID_SHIFT		11
 #define GLOBAL2_INGRESS_OP	0x09
 #define GLOBAL2_INGRESS_DATA	0x0a
 #define GLOBAL2_PVT_ADDR	0x0b
@@ -183,6 +275,10 @@
 #define GLOBAL2_SWITCH_MAC_BUSY BIT(15)
 #define GLOBAL2_ATU_STATS	0x0e
 #define GLOBAL2_PRIO_OVERRIDE	0x0f
+#define GLOBAL2_PRIO_OVERRIDE_FORCE_SNOOP	BIT(7)
+#define GLOBAL2_PRIO_OVERRIDE_SNOOP_SHIFT	4
+#define GLOBAL2_PRIO_OVERRIDE_FORCE_ARP		BIT(3)
+#define GLOBAL2_PRIO_OVERRIDE_ARP_SHIFT		0
 #define GLOBAL2_EEPROM_OP	0x14
 #define GLOBAL2_EEPROM_OP_BUSY	BIT(15)
 #define GLOBAL2_EEPROM_OP_LOAD	BIT(11)
@@ -201,6 +297,9 @@
 #define GLOBAL2_SMI_OP_45_READ_DATA	((2 << 10) | GLOBAL2_SMI_OP_BUSY)
 #define GLOBAL2_SMI_DATA	0x19
 #define GLOBAL2_SCRATCH_MISC	0x1a
+#define GLOBAL2_SCRATCH_BUSY		BIT(15)
+#define GLOBAL2_SCRATCH_REGISTER_SHIFT	8
+#define GLOBAL2_SCRATCH_VALUE_MASK	0xff
 #define GLOBAL2_WDOG_CONTROL	0x1b
 #define GLOBAL2_QOS_WEIGHT	0x1c
 #define GLOBAL2_MISC		0x1d
@@ -251,6 +350,8 @@ struct mv88e6xxx_priv_state {
 	u8 port_state[DSA_MAX_PORTS];
 
 	struct work_struct bridge_work;
+
+	struct dentry *dbgfs;
 };
 
 struct mv88e6xxx_hw_stat {
@@ -260,14 +361,14 @@ struct mv88e6xxx_hw_stat {
 };
 
 int mv88e6xxx_switch_reset(struct dsa_switch *ds, bool ppu_active);
-int mv88e6xxx_setup_port_common(struct dsa_switch *ds, int port);
+int mv88e6xxx_setup_ports(struct dsa_switch *ds);
 int mv88e6xxx_setup_common(struct dsa_switch *ds);
+int mv88e6xxx_setup_global(struct dsa_switch *ds);
 int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg);
 int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg);
 int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
 			  int reg, u16 val);
 int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val);
-int mv88e6xxx_config_prio(struct dsa_switch *ds);
 int mv88e6xxx_set_addr_direct(struct dsa_switch *ds, u8 *addr);
 int mv88e6xxx_set_addr_indirect(struct dsa_switch *ds, u8 *addr);
 int mv88e6xxx_phy_read(struct dsa_switch *ds, int port, int regnum);
@@ -289,7 +390,6 @@ int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port);
 void mv88e6xxx_get_regs(struct dsa_switch *ds, int port,
 			struct ethtool_regs *regs, void *_p);
 int  mv88e6xxx_get_temp(struct dsa_switch *ds, int *temp);
-int mv88e6xxx_phy_wait(struct dsa_switch *ds);
 int mv88e6xxx_eeprom_load_wait(struct dsa_switch *ds);
 int mv88e6xxx_eeprom_busy_wait(struct dsa_switch *ds);
 int mv88e6xxx_phy_read_indirect(struct dsa_switch *ds, int addr, int regnum);
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index afaab4b2333f..5b7658bcf020 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_3COM
 	default y
 	depends on ISA || EISA || PCI || PCMCIA
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -23,8 +21,7 @@ config EL3
 	depends on (ISA || EISA)
 	---help---
 	  If you have a network (Ethernet) card belonging to the 3Com
-	  EtherLinkIII series, say Y and read the Ethernet-HOWTO, available
-	  from <http://www.tldp.org/docs.html#howto>.
+	  EtherLinkIII series, say Y here.
 
 	  If your card is not working you may need to use the DOS
 	  setup disk to disable Plug & Play mode, and to select the default
@@ -38,8 +35,7 @@ config 3C515
 	depends on ISA && ISA_DMA_API
 	---help---
 	  If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
-	  network card, say Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  network card, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called 3c515.
@@ -78,9 +74,7 @@ config VORTEX
 	  "Tornado"   (3c905)                                  PCI
 	  "Hurricane" (3c555/3cSOHO)                           PCI
 
-	  If you have such a card, say Y and read the Ethernet-HOWTO,
-	  available from <http://www.tldp.org/docs.html#howto>. More
-	  specific information is in
+	  If you have such a card, say Y here.  More specific information is in
 	  <file:Documentation/networking/vortex.txt> and in the comments at
 	  the beginning of <file:drivers/net/ethernet/3com/3c59x.c>.
 
@@ -97,9 +91,7 @@ config TYPHOON
 	  3CR990SVR, 3CR990SVR95, 3CR990SVR97, 3CR990-FX-95 Server,
 	  3CR990-FX-97 Server, 3C990B-TX-M, 3C990BSVR
 
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called typhoon.
diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig
index 2d89bd00de61..edf72258ab1d 100644
--- a/drivers/net/ethernet/8390/Kconfig
+++ b/drivers/net/ethernet/8390/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_8390
 	default y
 	depends on NET_VENDOR_NATSEMI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -71,9 +69,7 @@ config MAC8390
 	select CRC32
 	---help---
 	  If you want to include a driver to support Nubus or LC-PDS
-	  Ethernet cards using an NS8390 chipset or its equivalent, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  Ethernet cards using an NS8390 chipset or its equivalent, say Y.
 
 config MCF8390
 	tristate "ColdFire NS8390 based Ethernet support"
@@ -95,10 +91,9 @@ config NE2000
 		    ATARI_ETHERNEC)
 	select CRC32
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.  Many Ethernet cards
-	  without a specific driver are compatible with NE2000.
+	  If you have a network (Ethernet) card of this type, say Y here.
+	  Many Ethernet cards without a specific driver are compatible with
+	  the NE2000.
 
 	  If you have a PCI NE2000 card however, say N here and Y to "PCI
 	  NE2000 and clone support" below.
@@ -114,8 +109,7 @@ config NE2K_PCI
 	  This driver is for NE2000 compatible PCI cards. It will not work
 	  with ISA NE2000 cards (they have their own driver, "NE2000/NE1000
 	  support" below). If you have a PCI NE2000 network (Ethernet) card,
-	  say Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  say Y here.
 
 	  This driver also works for the following NE2000 clone cards:
 	  RealTek RTL-8029  Winbond 89C940  Compex RL2000  KTI ET32P2
@@ -164,9 +158,7 @@ config ULTRA
 	depends on ISA
 	select CRC32
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 	  Important: There have been many reports that, with some motherboards
 	  mixing an SMC Ultra and an Adaptec AHA154x SCSI card (or compatible,
@@ -183,9 +175,7 @@ config WD80x3
 	depends on ISA
 	select CRC32
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called wd.
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index eadcb053807e..f3bb1784066b 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -34,6 +34,7 @@ source "drivers/net/ethernet/adi/Kconfig"
 source "drivers/net/ethernet/broadcom/Kconfig"
 source "drivers/net/ethernet/brocade/Kconfig"
 source "drivers/net/ethernet/calxeda/Kconfig"
+source "drivers/net/ethernet/cavium/Kconfig"
 source "drivers/net/ethernet/chelsio/Kconfig"
 source "drivers/net/ethernet/cirrus/Kconfig"
 source "drivers/net/ethernet/cisco/Kconfig"
@@ -66,6 +67,7 @@ config DNET
 source "drivers/net/ethernet/dec/Kconfig"
 source "drivers/net/ethernet/dlink/Kconfig"
 source "drivers/net/ethernet/emulex/Kconfig"
+source "drivers/net/ethernet/ezchip/Kconfig"
 source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/faraday/Kconfig"
 source "drivers/net/ethernet/freescale/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 1367afcd0a8b..c51014b0464f 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_NET_BFIN) += adi/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
 obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
 obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
+obj-$(CONFIG_NET_VENDOR_CAVIUM) += cavium/
 obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
 obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
 obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
@@ -29,6 +30,7 @@ obj-$(CONFIG_DNET) += dnet.o
 obj-$(CONFIG_NET_VENDOR_DEC) += dec/
 obj-$(CONFIG_NET_VENDOR_DLINK) += dlink/
 obj-$(CONFIG_NET_VENDOR_EMULEX) += emulex/
+obj-$(CONFIG_NET_VENDOR_EZCHIP) += ezchip/
 obj-$(CONFIG_NET_VENDOR_EXAR) += neterion/
 obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/
 obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
diff --git a/drivers/net/ethernet/adaptec/Kconfig b/drivers/net/ethernet/adaptec/Kconfig
index 5c804bbe3dab..822cffb4174c 100644
--- a/drivers/net/ethernet/adaptec/Kconfig
+++ b/drivers/net/ethernet/adaptec/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_ADAPTEC
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig
index c9cd3592ab73..6b94ba610399 100644
--- a/drivers/net/ethernet/adi/Kconfig
+++ b/drivers/net/ethernet/adi/Kconfig
@@ -7,8 +7,6 @@ config NET_BFIN
 	depends on BF516 || BF518 || BF526 || BF527 || BF536 || BF537
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
-	  Make sure you know the name of your card. Read the Ethernet-HOWTO,
-	  available from <http://www.tldp.org/docs.html#howto>.
 
 	  If unsure, say Y.
 
diff --git a/drivers/net/ethernet/agere/Kconfig b/drivers/net/ethernet/agere/Kconfig
index 63e805de619e..b6fe9200355a 100644
--- a/drivers/net/ethernet/agere/Kconfig
+++ b/drivers/net/ethernet/agere/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_AGERE
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/allwinner/Kconfig b/drivers/net/ethernet/allwinner/Kconfig
index d8d95d4cd45a..47da7e7a5b6a 100644
--- a/drivers/net/ethernet/allwinner/Kconfig
+++ b/drivers/net/ethernet/allwinner/Kconfig
@@ -9,8 +9,7 @@ config NET_VENDOR_ALLWINNER
 	depends on ARCH_SUNXI
 	---help---
 	  If you have a network (Ethernet) card belonging to this
-	  class, say Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  class, say Y here.
 
 	  Note that the answer to this question doesn't directly
 	  affect the kernel: saying N will just cause the configurator
diff --git a/drivers/net/ethernet/alteon/Kconfig b/drivers/net/ethernet/alteon/Kconfig
index 799a85282070..e06ccab354b5 100644
--- a/drivers/net/ethernet/alteon/Kconfig
+++ b/drivers/net/ethernet/alteon/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_ALTEON
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 089c269637b7..afc62ea804fc 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -37,8 +37,7 @@ config AMD8111_ETH
 	select MII
 	---help---
 	  If you have an AMD 8111-based PCI LANCE ethernet card,
-	  answer Y here and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  answer Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called amd8111e.
@@ -47,10 +46,8 @@ config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
 	depends on ISA && ISA_DMA_API && !ARM
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>. Some LinkSys cards are
-	  of this type.
+	  If you have a network (Ethernet) card of this type, say Y here.
+	  Some LinkSys cards are of this type.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called lance.  This is recommended.
@@ -62,8 +59,7 @@ config PCNET32
 	select MII
 	---help---
 	  If you have a PCnet32 or PCnetPCI based network (Ethernet) card,
-	  answer Y here and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  answer Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called pcnet32.
@@ -144,9 +140,7 @@ config NI65
 	tristate "NI6510 support"
 	depends on ISA && ISA_DMA_API && !ARM
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ni65.
@@ -179,9 +173,8 @@ config SUNLANCE
 
 config AMD_XGBE
 	tristate "AMD 10GbE Ethernet driver"
-	depends on (OF_NET || ACPI) && HAS_IOMEM && HAS_DMA
-	select PHYLIB
-	select AMD_XGBE_PHY
+	depends on ((OF_NET && OF_ADDRESS) || ACPI) && HAS_IOMEM && HAS_DMA
+	depends on ARM64 || COMPILE_TEST
 	select BITREVERSE
 	select CRC32
 	select PTP_1588_CLOCK
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 34c28aac767f..b6fa89102526 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -857,6 +857,48 @@
  */
 #define PCS_MMD_SELECT			0xff
 
+/* SerDes integration register offsets */
+#define SIR0_KR_RT_1			0x002c
+#define SIR0_STATUS			0x0040
+#define SIR1_SPEED			0x0000
+
+/* SerDes integration register entry bit positions and sizes */
+#define SIR0_KR_RT_1_RESET_INDEX	11
+#define SIR0_KR_RT_1_RESET_WIDTH	1
+#define SIR0_STATUS_RX_READY_INDEX	0
+#define SIR0_STATUS_RX_READY_WIDTH	1
+#define SIR0_STATUS_TX_READY_INDEX	8
+#define SIR0_STATUS_TX_READY_WIDTH	1
+#define SIR1_SPEED_CDR_RATE_INDEX	12
+#define SIR1_SPEED_CDR_RATE_WIDTH	4
+#define SIR1_SPEED_DATARATE_INDEX	4
+#define SIR1_SPEED_DATARATE_WIDTH	2
+#define SIR1_SPEED_PLLSEL_INDEX		3
+#define SIR1_SPEED_PLLSEL_WIDTH		1
+#define SIR1_SPEED_RATECHANGE_INDEX	6
+#define SIR1_SPEED_RATECHANGE_WIDTH	1
+#define SIR1_SPEED_TXAMP_INDEX		8
+#define SIR1_SPEED_TXAMP_WIDTH		4
+#define SIR1_SPEED_WORDMODE_INDEX	0
+#define SIR1_SPEED_WORDMODE_WIDTH	3
+
+/* SerDes RxTx register offsets */
+#define RXTX_REG6			0x0018
+#define RXTX_REG20			0x0050
+#define RXTX_REG22			0x0058
+#define RXTX_REG114			0x01c8
+#define RXTX_REG129			0x0204
+
+/* SerDes RxTx register entry bit positions and sizes */
+#define RXTX_REG6_RESETB_RXD_INDEX	8
+#define RXTX_REG6_RESETB_RXD_WIDTH	1
+#define RXTX_REG20_BLWC_ENA_INDEX	2
+#define RXTX_REG20_BLWC_ENA_WIDTH	1
+#define RXTX_REG114_PQ_REG_INDEX	9
+#define RXTX_REG114_PQ_REG_WIDTH	7
+#define RXTX_REG129_RXDFE_CONFIG_INDEX	14
+#define RXTX_REG129_RXDFE_CONFIG_WIDTH	2
+
 /* Descriptor/Packet entry bit positions and sizes */
 #define RX_PACKET_ERRORS_CRC_INDEX		2
 #define RX_PACKET_ERRORS_CRC_WIDTH		1
@@ -973,10 +1015,47 @@
 #define TX_NORMAL_DESC2_VLAN_INSERT		0x2
 
 /* MDIO undefined or vendor specific registers */
+#ifndef MDIO_PMA_10GBR_PMD_CTRL
+#define MDIO_PMA_10GBR_PMD_CTRL		0x0096
+#endif
+
+#ifndef MDIO_PMA_10GBR_FECCTRL
+#define MDIO_PMA_10GBR_FECCTRL		0x00ab
+#endif
+
+#ifndef MDIO_AN_XNP
+#define MDIO_AN_XNP			0x0016
+#endif
+
+#ifndef MDIO_AN_LPX
+#define MDIO_AN_LPX			0x0019
+#endif
+
 #ifndef MDIO_AN_COMP_STAT
 #define MDIO_AN_COMP_STAT		0x0030
 #endif
 
+#ifndef MDIO_AN_INTMASK
+#define MDIO_AN_INTMASK			0x8001
+#endif
+
+#ifndef MDIO_AN_INT
+#define MDIO_AN_INT			0x8002
+#endif
+
+#ifndef MDIO_CTRL1_SPEED1G
+#define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
+#endif
+
+/* MDIO mask values */
+#define XGBE_XNP_MCF_NULL_MESSAGE	0x001
+#define XGBE_XNP_ACK_PROCESSED		BIT(12)
+#define XGBE_XNP_MP_FORMATTED		BIT(13)
+#define XGBE_XNP_NP_EXCHANGE		BIT(15)
+
+#define XGBE_KR_TRAINING_START		BIT(0)
+#define XGBE_KR_TRAINING_ENABLE		BIT(1)
+
 /* Bit setting and getting macros
  *  The get macro will extract the current bit field value from within
  *  the variable
@@ -1119,6 +1198,82 @@ do {									\
 	ioread32((_pdata)->xpcs_regs + (_off))
 
 /* Macros for building, reading or writing register values or bits
+ * within the register values of SerDes integration registers.
+ */
+#define XSIR_GET_BITS(_var, _prefix, _field)                            \
+	GET_BITS((_var),                                                \
+		 _prefix##_##_field##_INDEX,                            \
+		 _prefix##_##_field##_WIDTH)
+
+#define XSIR_SET_BITS(_var, _prefix, _field, _val)                      \
+	SET_BITS((_var),                                                \
+		 _prefix##_##_field##_INDEX,                            \
+		 _prefix##_##_field##_WIDTH, (_val))
+
+#define XSIR0_IOREAD(_pdata, _reg)					\
+	ioread16((_pdata)->sir0_regs + _reg)
+
+#define XSIR0_IOREAD_BITS(_pdata, _reg, _field)				\
+	GET_BITS(XSIR0_IOREAD((_pdata), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XSIR0_IOWRITE(_pdata, _reg, _val)				\
+	iowrite16((_val), (_pdata)->sir0_regs + _reg)
+
+#define XSIR0_IOWRITE_BITS(_pdata, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XSIR0_IOREAD((_pdata), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XSIR0_IOWRITE((_pdata), _reg, reg_val);				\
+} while (0)
+
+#define XSIR1_IOREAD(_pdata, _reg)					\
+	ioread16((_pdata)->sir1_regs + _reg)
+
+#define XSIR1_IOREAD_BITS(_pdata, _reg, _field)				\
+	GET_BITS(XSIR1_IOREAD((_pdata), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XSIR1_IOWRITE(_pdata, _reg, _val)				\
+	iowrite16((_val), (_pdata)->sir1_regs + _reg)
+
+#define XSIR1_IOWRITE_BITS(_pdata, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XSIR1_IOREAD((_pdata), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XSIR1_IOWRITE((_pdata), _reg, reg_val);				\
+} while (0)
+
+/* Macros for building, reading or writing register values or bits
+ * within the register values of SerDes RxTx registers.
+ */
+#define XRXTX_IOREAD(_pdata, _reg)					\
+	ioread16((_pdata)->rxtx_regs + _reg)
+
+#define XRXTX_IOREAD_BITS(_pdata, _reg, _field)				\
+	GET_BITS(XRXTX_IOREAD((_pdata), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XRXTX_IOWRITE(_pdata, _reg, _val)				\
+	iowrite16((_val), (_pdata)->rxtx_regs + _reg)
+
+#define XRXTX_IOWRITE_BITS(_pdata, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XRXTX_IOREAD((_pdata), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XRXTX_IOWRITE((_pdata), _reg, reg_val);				\
+} while (0)
+
+/* Macros for building, reading or writing register values or bits
  * using MDIO.  Different from above because of the use of standardized
  * Linux include values.  No shifting is performed with the bit
  * operations, everything works on mask values.
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
index 8a50b01c2686..a6b9899e285f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dcb.c
@@ -150,9 +150,12 @@ static int xgbe_dcb_ieee_setets(struct net_device *netdev,
 	tc_ets = 0;
 	tc_ets_weight = 0;
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
-		DBGPR("  TC%u: tx_bw=%hhu, rx_bw=%hhu, tsa=%hhu\n", i,
-		      ets->tc_tx_bw[i], ets->tc_rx_bw[i], ets->tc_tsa[i]);
-		DBGPR("  PRIO%u: TC=%hhu\n", i, ets->prio_tc[i]);
+		netif_dbg(pdata, drv, netdev,
+			  "TC%u: tx_bw=%hhu, rx_bw=%hhu, tsa=%hhu\n", i,
+			  ets->tc_tx_bw[i], ets->tc_rx_bw[i],
+			  ets->tc_tsa[i]);
+		netif_dbg(pdata, drv, netdev, "PRIO%u: TC=%hhu\n", i,
+			  ets->prio_tc[i]);
 
 		if ((ets->tc_tx_bw[i] || ets->tc_tsa[i]) &&
 		    (i >= pdata->hw_feat.tc_cnt))
@@ -214,8 +217,9 @@ static int xgbe_dcb_ieee_setpfc(struct net_device *netdev,
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 
-	DBGPR("  cap=%hhu, en=%hhx, mbc=%hhu, delay=%hhu\n",
-	      pfc->pfc_cap, pfc->pfc_en, pfc->mbc, pfc->delay);
+	netif_dbg(pdata, drv, netdev,
+		  "cap=%hhu, en=%#hhx, mbc=%hhu, delay=%hhu\n",
+		  pfc->pfc_cap, pfc->pfc_en, pfc->mbc, pfc->delay);
 
 	if (!pdata->pfc) {
 		pdata->pfc = devm_kzalloc(pdata->dev, sizeof(*pdata->pfc),
@@ -238,9 +242,10 @@ static u8 xgbe_dcb_getdcbx(struct net_device *netdev)
 
 static u8 xgbe_dcb_setdcbx(struct net_device *netdev, u8 dcbx)
 {
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 	u8 support = xgbe_dcb_getdcbx(netdev);
 
-	DBGPR("  DCBX=%#hhx\n", dcbx);
+	netif_dbg(pdata, drv, netdev, "DCBX=%#hhx\n", dcbx);
 
 	if (dcbx & ~support)
 		return 1;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index d81fc6bd4759..dd03ad865caf 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -208,8 +208,9 @@ static int xgbe_init_ring(struct xgbe_prv_data *pdata,
 	if (!ring->rdata)
 		return -ENOMEM;
 
-	DBGPR("    rdesc=0x%p, rdesc_dma=0x%llx, rdata=0x%p\n",
-	      ring->rdesc, ring->rdesc_dma, ring->rdata);
+	netif_dbg(pdata, drv, pdata->netdev,
+		  "rdesc=%p, rdesc_dma=%pad, rdata=%p\n",
+		  ring->rdesc, &ring->rdesc_dma, ring->rdata);
 
 	DBGPR("<--xgbe_init_ring\n");
 
@@ -226,7 +227,9 @@ static int xgbe_alloc_ring_resources(struct xgbe_prv_data *pdata)
 
 	channel = pdata->channel;
 	for (i = 0; i < pdata->channel_count; i++, channel++) {
-		DBGPR("  %s - tx_ring:\n", channel->name);
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Tx ring:\n",
+			  channel->name);
+
 		ret = xgbe_init_ring(pdata, channel->tx_ring,
 				     pdata->tx_desc_count);
 		if (ret) {
@@ -235,12 +238,14 @@ static int xgbe_alloc_ring_resources(struct xgbe_prv_data *pdata)
 			goto err_ring;
 		}
 
-		DBGPR("  %s - rx_ring:\n", channel->name);
+		netif_dbg(pdata, drv, pdata->netdev, "%s - Rx ring:\n",
+			  channel->name);
+
 		ret = xgbe_init_ring(pdata, channel->rx_ring,
 				     pdata->rx_desc_count);
 		if (ret) {
 			netdev_alert(pdata->netdev,
-				     "error initializing Tx ring\n");
+				     "error initializing Rx ring\n");
 			goto err_ring;
 		}
 	}
@@ -476,8 +481,6 @@ static void xgbe_unmap_rdata(struct xgbe_prv_data *pdata,
 
 	if (rdata->state_saved) {
 		rdata->state_saved = 0;
-		rdata->state.incomplete = 0;
-		rdata->state.context_next = 0;
 		rdata->state.skb = NULL;
 		rdata->state.len = 0;
 		rdata->state.error = 0;
@@ -518,8 +521,6 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
 	rdata = XGBE_GET_DESC_DATA(ring, cur_index);
 
 	if (tso) {
-		DBGPR("  TSO packet\n");
-
 		/* Map the TSO header */
 		skb_dma = dma_map_single(pdata->dev, skb->data,
 					 packet->header_len, DMA_TO_DEVICE);
@@ -529,6 +530,9 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
 		}
 		rdata->skb_dma = skb_dma;
 		rdata->skb_dma_len = packet->header_len;
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb header: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, packet->header_len);
 
 		offset = packet->header_len;
 
@@ -550,8 +554,9 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
 		}
 		rdata->skb_dma = skb_dma;
 		rdata->skb_dma_len = len;
-		DBGPR("  skb data: index=%u, dma=0x%llx, len=%u\n",
-		      cur_index, skb_dma, len);
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "skb data: index=%u, dma=%pad, len=%u\n",
+			  cur_index, &skb_dma, len);
 
 		datalen -= len;
 		offset += len;
@@ -563,7 +568,8 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
 	}
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		DBGPR("  mapping frag %u\n", i);
+		netif_dbg(pdata, tx_queued, pdata->netdev,
+			  "mapping frag %u\n", i);
 
 		frag = &skb_shinfo(skb)->frags[i];
 		offset = 0;
@@ -582,8 +588,9 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
 			rdata->skb_dma = skb_dma;
 			rdata->skb_dma_len = len;
 			rdata->mapped_as_page = 1;
-			DBGPR("  skb data: index=%u, dma=0x%llx, len=%u\n",
-			      cur_index, skb_dma, len);
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "skb frag: index=%u, dma=%pad, len=%u\n",
+				  cur_index, &skb_dma, len);
 
 			datalen -= len;
 			offset += len;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 21d9497518fd..506e832c9e9a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -710,7 +710,8 @@ static int xgbe_set_promiscuous_mode(struct xgbe_prv_data *pdata,
 	if (XGMAC_IOREAD_BITS(pdata, MAC_PFR, PR) == val)
 		return 0;
 
-	DBGPR("  %s promiscuous mode\n", enable ? "entering" : "leaving");
+	netif_dbg(pdata, drv, pdata->netdev, "%s promiscuous mode\n",
+		  enable ? "entering" : "leaving");
 	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, PR, val);
 
 	return 0;
@@ -724,7 +725,8 @@ static int xgbe_set_all_multicast_mode(struct xgbe_prv_data *pdata,
 	if (XGMAC_IOREAD_BITS(pdata, MAC_PFR, PM) == val)
 		return 0;
 
-	DBGPR("  %s allmulti mode\n", enable ? "entering" : "leaving");
+	netif_dbg(pdata, drv, pdata->netdev, "%s allmulti mode\n",
+		  enable ? "entering" : "leaving");
 	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, PM, val);
 
 	return 0;
@@ -749,8 +751,9 @@ static void xgbe_set_mac_reg(struct xgbe_prv_data *pdata,
 		mac_addr[0] = ha->addr[4];
 		mac_addr[1] = ha->addr[5];
 
-		DBGPR("  adding mac address %pM at 0x%04x\n", ha->addr,
-		      *mac_reg);
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "adding mac address %pM at %#x\n",
+			  ha->addr, *mac_reg);
 
 		XGMAC_SET_BITS(mac_addr_hi, MAC_MACA1HR, AE, 1);
 	}
@@ -907,23 +910,6 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	else
 		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
 
-	/* If the PCS is changing modes, match the MAC speed to it */
-	if (((mmd_address >> 16) == MDIO_MMD_PCS) &&
-	    ((mmd_address & 0xffff) == MDIO_CTRL2)) {
-		struct phy_device *phydev = pdata->phydev;
-
-		if (mmd_data & MDIO_PCS_CTRL2_TYPE) {
-			/* KX mode */
-			if (phydev->supported & SUPPORTED_1000baseKX_Full)
-				xgbe_set_gmii_speed(pdata);
-			else
-				xgbe_set_gmii_2500_speed(pdata);
-		} else {
-			/* KR mode */
-			xgbe_set_xgmii_speed(pdata);
-		}
-	}
-
 	/* The PCS registers are accessed using mmio. The underlying APB3
 	 * management interface uses indirect addressing to access the MMD
 	 * register sets. This requires accessing of the PCS register in two
@@ -1322,7 +1308,8 @@ static void xgbe_config_dcb_tc(struct xgbe_prv_data *pdata)
 	for (i = 0; i < pdata->hw_feat.tc_cnt; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
-			DBGPR("  TC%u using SP\n", i);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TC%u using SP\n", i);
 			XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
 					       MTL_TSA_SP);
 			break;
@@ -1330,7 +1317,8 @@ static void xgbe_config_dcb_tc(struct xgbe_prv_data *pdata)
 			weight = total_weight * ets->tc_tx_bw[i] / 100;
 			weight = clamp(weight, min_weight, total_weight);
 
-			DBGPR("  TC%u using DWRR (weight %u)\n", i, weight);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TC%u using DWRR (weight %u)\n", i, weight);
 			XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA,
 					       MTL_TSA_ETS);
 			XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_QWR, QW,
@@ -1359,7 +1347,8 @@ static void xgbe_config_dcb_pfc(struct xgbe_prv_data *pdata)
 		}
 		mask &= 0xff;
 
-		DBGPR("  TC%u PFC mask=%#x\n", tc, mask);
+		netif_dbg(pdata, drv, pdata->netdev, "TC%u PFC mask=%#x\n",
+			  tc, mask);
 		reg = MTL_TCPM0R + (MTL_TCPM_INC * (tc / MTL_TCPM_TC_PER_REG));
 		reg_val = XGMAC_IOREAD(pdata, reg);
 
@@ -1457,8 +1446,9 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 	/* Create a context descriptor if this is a TSO packet */
 	if (tso_context || vlan_context) {
 		if (tso_context) {
-			DBGPR("  TSO context descriptor, mss=%u\n",
-			      packet->mss);
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "TSO context descriptor, mss=%u\n",
+				  packet->mss);
 
 			/* Set the MSS size */
 			XGMAC_SET_BITS_LE(rdesc->desc2, TX_CONTEXT_DESC2,
@@ -1476,8 +1466,9 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 		}
 
 		if (vlan_context) {
-			DBGPR("  VLAN context descriptor, ctag=%u\n",
-			      packet->vlan_ctag);
+			netif_dbg(pdata, tx_queued, pdata->netdev,
+				  "VLAN context descriptor, ctag=%u\n",
+				  packet->vlan_ctag);
 
 			/* Mark it as a CONTEXT descriptor */
 			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
@@ -1533,6 +1524,8 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 				  packet->tcp_payload_len);
 		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, TCPHDRLEN,
 				  packet->tcp_header_len / 4);
+
+		pdata->ext_stats.tx_tso_packets++;
 	} else {
 		/* Enable CRC and Pad Insertion */
 		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CPC, 0);
@@ -1594,9 +1587,9 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 	rdesc = rdata->rdesc;
 	XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN, 1);
 
-#ifdef XGMAC_ENABLE_TX_DESC_DUMP
-	xgbe_dump_tx_desc(ring, start_index, packet->rdesc_count, 1);
-#endif
+	if (netif_msg_tx_queued(pdata))
+		xgbe_dump_tx_desc(pdata, ring, start_index,
+				  packet->rdesc_count, 1);
 
 	/* Make sure ownership is written to the descriptor */
 	dma_wmb();
@@ -1618,11 +1611,12 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 
 static int xgbe_dev_read(struct xgbe_channel *channel)
 {
+	struct xgbe_prv_data *pdata = channel->pdata;
 	struct xgbe_ring *ring = channel->rx_ring;
 	struct xgbe_ring_data *rdata;
 	struct xgbe_ring_desc *rdesc;
 	struct xgbe_packet_data *packet = &ring->packet_data;
-	struct net_device *netdev = channel->pdata->netdev;
+	struct net_device *netdev = pdata->netdev;
 	unsigned int err, etlt, l34t;
 
 	DBGPR("-->xgbe_dev_read: cur = %d\n", ring->cur);
@@ -1637,9 +1631,8 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 	/* Make sure descriptor fields are read after reading the OWN bit */
 	dma_rmb();
 
-#ifdef XGMAC_ENABLE_RX_DESC_DUMP
-	xgbe_dump_rx_desc(ring, rdesc, ring->cur);
-#endif
+	if (netif_msg_rx_status(pdata))
+		xgbe_dump_rx_desc(pdata, ring, ring->cur);
 
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, CTXT)) {
 		/* Timestamp Context Descriptor */
@@ -1661,9 +1654,12 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 			       CONTEXT_NEXT, 1);
 
 	/* Get the header length */
-	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD))
+	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, FD)) {
 		rdata->rx.hdr_len = XGMAC_GET_BITS_LE(rdesc->desc2,
 						      RX_NORMAL_DESC2, HL);
+		if (rdata->rx.hdr_len)
+			pdata->ext_stats.rx_split_header_packets++;
+	}
 
 	/* Get the RSS hash */
 	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, RSV)) {
@@ -1700,14 +1696,14 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 		       INCOMPLETE, 0);
 
 	/* Set checksum done indicator as appropriate */
-	if (channel->pdata->netdev->features & NETIF_F_RXCSUM)
+	if (netdev->features & NETIF_F_RXCSUM)
 		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
 			       CSUM_DONE, 1);
 
 	/* Check for errors (only valid in last descriptor) */
 	err = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, ES);
 	etlt = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, ETLT);
-	DBGPR("  err=%u, etlt=%#x\n", err, etlt);
+	netif_dbg(pdata, rx_status, netdev, "err=%u, etlt=%#x\n", err, etlt);
 
 	if (!err || !etlt) {
 		/* No error if err is 0 or etlt is 0 */
@@ -1718,7 +1714,8 @@ static int xgbe_dev_read(struct xgbe_channel *channel)
 			packet->vlan_ctag = XGMAC_GET_BITS_LE(rdesc->desc0,
 							      RX_NORMAL_DESC0,
 							      OVT);
-			DBGPR("  vlan-ctag=0x%04x\n", packet->vlan_ctag);
+			netif_dbg(pdata, rx_status, netdev, "vlan-ctag=%#06x\n",
+				  packet->vlan_ctag);
 		}
 	} else {
 		if ((etlt == 0x05) || (etlt == 0x06))
@@ -2026,9 +2023,9 @@ static void xgbe_config_tx_fifo_size(struct xgbe_prv_data *pdata)
 	for (i = 0; i < pdata->tx_q_count; i++)
 		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TQS, fifo_size);
 
-	netdev_notice(pdata->netdev,
-		      "%d Tx hardware queues, %d byte fifo per queue\n",
-		      pdata->tx_q_count, ((fifo_size + 1) * 256));
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Tx hardware queues, %d byte fifo per queue\n",
+		   pdata->tx_q_count, ((fifo_size + 1) * 256));
 }
 
 static void xgbe_config_rx_fifo_size(struct xgbe_prv_data *pdata)
@@ -2042,9 +2039,9 @@ static void xgbe_config_rx_fifo_size(struct xgbe_prv_data *pdata)
 	for (i = 0; i < pdata->rx_q_count; i++)
 		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RQS, fifo_size);
 
-	netdev_notice(pdata->netdev,
-		      "%d Rx hardware queues, %d byte fifo per queue\n",
-		      pdata->rx_q_count, ((fifo_size + 1) * 256));
+	netif_info(pdata, drv, pdata->netdev,
+		   "%d Rx hardware queues, %d byte fifo per queue\n",
+		   pdata->rx_q_count, ((fifo_size + 1) * 256));
 }
 
 static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
@@ -2063,14 +2060,16 @@ static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
 
 	for (i = 0, queue = 0; i < pdata->hw_feat.tc_cnt; i++) {
 		for (j = 0; j < qptc; j++) {
-			DBGPR("  TXq%u mapped to TC%u\n", queue, i);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
 			XGMAC_MTL_IOWRITE_BITS(pdata, queue, MTL_Q_TQOMR,
 					       Q2TCMAP, i);
 			pdata->q2tc_map[queue++] = i;
 		}
 
 		if (i < qptc_extra) {
-			DBGPR("  TXq%u mapped to TC%u\n", queue, i);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "TXq%u mapped to TC%u\n", queue, i);
 			XGMAC_MTL_IOWRITE_BITS(pdata, queue, MTL_Q_TQOMR,
 					       Q2TCMAP, i);
 			pdata->q2tc_map[queue++] = i;
@@ -2088,13 +2087,15 @@ static void xgbe_config_queue_mapping(struct xgbe_prv_data *pdata)
 	for (i = 0, prio = 0; i < prio_queues;) {
 		mask = 0;
 		for (j = 0; j < ppq; j++) {
-			DBGPR("  PRIO%u mapped to RXq%u\n", prio, i);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
 			mask |= (1 << prio);
 			pdata->prio2q_map[prio++] = i;
 		}
 
 		if (i < ppq_extra) {
-			DBGPR("  PRIO%u mapped to RXq%u\n", prio, i);
+			netif_dbg(pdata, drv, pdata->netdev,
+				  "PRIO%u mapped to RXq%u\n", prio, i);
 			mask |= (1 << prio);
 			pdata->prio2q_map[prio++] = i;
 		}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index db84ddcfec84..1e9c28d19ef8 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -183,9 +183,10 @@ static int xgbe_alloc_channels(struct xgbe_prv_data *pdata)
 			channel->rx_ring = rx_ring++;
 		}
 
-		DBGPR("  %s: queue=%u, dma_regs=%p, dma_irq=%d, tx=%p, rx=%p\n",
-		      channel->name, channel->queue_index, channel->dma_regs,
-		      channel->dma_irq, channel->tx_ring, channel->rx_ring);
+		netif_dbg(pdata, drv, pdata->netdev,
+			  "%s: dma_regs=%p, dma_irq=%d, tx=%p, rx=%p\n",
+			  channel->name, channel->dma_regs, channel->dma_irq,
+			  channel->tx_ring, channel->rx_ring);
 	}
 
 	pdata->channel = channel_mem;
@@ -235,7 +236,8 @@ static int xgbe_maybe_stop_tx_queue(struct xgbe_channel *channel,
 	struct xgbe_prv_data *pdata = channel->pdata;
 
 	if (count > xgbe_tx_avail_desc(ring)) {
-		DBGPR("  Tx queue stopped, not enough descriptors available\n");
+		netif_info(pdata, drv, pdata->netdev,
+			   "Tx queue stopped, not enough descriptors available\n");
 		netif_stop_subqueue(pdata->netdev, channel->queue_index);
 		ring->tx.queue_stopped = 1;
 
@@ -330,7 +332,7 @@ static irqreturn_t xgbe_isr(int irq, void *data)
 	if (!dma_isr)
 		goto isr_done;
 
-	DBGPR("  DMA_ISR = %08x\n", dma_isr);
+	netif_dbg(pdata, intr, pdata->netdev, "DMA_ISR=%#010x\n", dma_isr);
 
 	for (i = 0; i < pdata->channel_count; i++) {
 		if (!(dma_isr & (1 << i)))
@@ -339,7 +341,8 @@ static irqreturn_t xgbe_isr(int irq, void *data)
 		channel = pdata->channel + i;
 
 		dma_ch_isr = XGMAC_DMA_IOREAD(channel, DMA_CH_SR);
-		DBGPR("  DMA_CH%u_ISR = %08x\n", i, dma_ch_isr);
+		netif_dbg(pdata, intr, pdata->netdev, "DMA_CH%u_ISR=%#010x\n",
+			  i, dma_ch_isr);
 
 		/* The TI or RI interrupt bits may still be set even if using
 		 * per channel DMA interrupts. Check to be sure those are not
@@ -386,8 +389,6 @@ static irqreturn_t xgbe_isr(int irq, void *data)
 		}
 	}
 
-	DBGPR("  DMA_ISR = %08x\n", XGMAC_IOREAD(pdata, DMA_ISR));
-
 isr_done:
 	return IRQ_HANDLED;
 }
@@ -423,7 +424,7 @@ static void xgbe_tx_timer(unsigned long data)
 	if (napi_schedule_prep(napi)) {
 		/* Disable Tx and Rx interrupts */
 		if (pdata->per_channel_irq)
-			disable_irq(channel->dma_irq);
+			disable_irq_nosync(channel->dma_irq);
 		else
 			xgbe_disable_rx_tx_ints(pdata);
 
@@ -436,43 +437,61 @@ static void xgbe_tx_timer(unsigned long data)
 	DBGPR("<--xgbe_tx_timer\n");
 }
 
-static void xgbe_init_tx_timers(struct xgbe_prv_data *pdata)
+static void xgbe_service(struct work_struct *work)
+{
+	struct xgbe_prv_data *pdata = container_of(work,
+						   struct xgbe_prv_data,
+						   service_work);
+
+	pdata->phy_if.phy_status(pdata);
+}
+
+static void xgbe_service_timer(unsigned long data)
+{
+	struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
+
+	schedule_work(&pdata->service_work);
+
+	mod_timer(&pdata->service_timer, jiffies + HZ);
+}
+
+static void xgbe_init_timers(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_channel *channel;
 	unsigned int i;
 
-	DBGPR("-->xgbe_init_tx_timers\n");
+	setup_timer(&pdata->service_timer, xgbe_service_timer,
+		    (unsigned long)pdata);
 
 	channel = pdata->channel;
 	for (i = 0; i < pdata->channel_count; i++, channel++) {
 		if (!channel->tx_ring)
 			break;
 
-		DBGPR("  %s adding tx timer\n", channel->name);
 		setup_timer(&channel->tx_timer, xgbe_tx_timer,
 			    (unsigned long)channel);
 	}
+}
 
-	DBGPR("<--xgbe_init_tx_timers\n");
+static void xgbe_start_timers(struct xgbe_prv_data *pdata)
+{
+	mod_timer(&pdata->service_timer, jiffies + HZ);
 }
 
-static void xgbe_stop_tx_timers(struct xgbe_prv_data *pdata)
+static void xgbe_stop_timers(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_channel *channel;
 	unsigned int i;
 
-	DBGPR("-->xgbe_stop_tx_timers\n");
+	del_timer_sync(&pdata->service_timer);
 
 	channel = pdata->channel;
 	for (i = 0; i < pdata->channel_count; i++, channel++) {
 		if (!channel->tx_ring)
 			break;
 
-		DBGPR("  %s deleting tx timer\n", channel->name);
 		del_timer_sync(&channel->tx_timer);
 	}
-
-	DBGPR("<--xgbe_stop_tx_timers\n");
 }
 
 void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata)
@@ -512,6 +531,7 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata)
 						RXFIFOSIZE);
 	hw_feat->tx_fifo_size  = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
 						TXFIFOSIZE);
+	hw_feat->adv_ts_hi     = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, ADVTHWORD);
 	hw_feat->dma_width     = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, ADDR64);
 	hw_feat->dcb           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DCBEN);
 	hw_feat->sph           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN);
@@ -759,112 +779,12 @@ static void xgbe_free_rx_data(struct xgbe_prv_data *pdata)
 	DBGPR("<--xgbe_free_rx_data\n");
 }
 
-static void xgbe_adjust_link(struct net_device *netdev)
-{
-	struct xgbe_prv_data *pdata = netdev_priv(netdev);
-	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	struct phy_device *phydev = pdata->phydev;
-	int new_state = 0;
-
-	if (!phydev)
-		return;
-
-	if (phydev->link) {
-		/* Flow control support */
-		if (pdata->pause_autoneg) {
-			if (phydev->pause || phydev->asym_pause) {
-				pdata->tx_pause = 1;
-				pdata->rx_pause = 1;
-			} else {
-				pdata->tx_pause = 0;
-				pdata->rx_pause = 0;
-			}
-		}
-
-		if (pdata->tx_pause != pdata->phy_tx_pause) {
-			hw_if->config_tx_flow_control(pdata);
-			pdata->phy_tx_pause = pdata->tx_pause;
-		}
-
-		if (pdata->rx_pause != pdata->phy_rx_pause) {
-			hw_if->config_rx_flow_control(pdata);
-			pdata->phy_rx_pause = pdata->rx_pause;
-		}
-
-		/* Speed support */
-		if (phydev->speed != pdata->phy_speed) {
-			new_state = 1;
-
-			switch (phydev->speed) {
-			case SPEED_10000:
-				hw_if->set_xgmii_speed(pdata);
-				break;
-
-			case SPEED_2500:
-				hw_if->set_gmii_2500_speed(pdata);
-				break;
-
-			case SPEED_1000:
-				hw_if->set_gmii_speed(pdata);
-				break;
-			}
-			pdata->phy_speed = phydev->speed;
-		}
-
-		if (phydev->link != pdata->phy_link) {
-			new_state = 1;
-			pdata->phy_link = 1;
-		}
-	} else if (pdata->phy_link) {
-		new_state = 1;
-		pdata->phy_link = 0;
-		pdata->phy_speed = SPEED_UNKNOWN;
-	}
-
-	if (new_state)
-		phy_print_status(phydev);
-}
-
 static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 {
-	struct net_device *netdev = pdata->netdev;
-	struct phy_device *phydev = pdata->phydev;
-	int ret;
-
 	pdata->phy_link = -1;
 	pdata->phy_speed = SPEED_UNKNOWN;
-	pdata->phy_tx_pause = pdata->tx_pause;
-	pdata->phy_rx_pause = pdata->rx_pause;
 
-	ret = phy_connect_direct(netdev, phydev, &xgbe_adjust_link,
-				 pdata->phy_mode);
-	if (ret) {
-		netdev_err(netdev, "phy_connect_direct failed\n");
-		return ret;
-	}
-
-	if (!phydev->drv || (phydev->drv->phy_id == 0)) {
-		netdev_err(netdev, "phy_id not valid\n");
-		ret = -ENODEV;
-		goto err_phy_connect;
-	}
-	DBGPR("  phy_connect_direct succeeded for PHY %s, link=%d\n",
-	      dev_name(&phydev->dev), phydev->link);
-
-	return 0;
-
-err_phy_connect:
-	phy_disconnect(phydev);
-
-	return ret;
-}
-
-static void xgbe_phy_exit(struct xgbe_prv_data *pdata)
-{
-	if (!pdata->phydev)
-		return;
-
-	phy_disconnect(pdata->phydev);
+	return pdata->phy_if.phy_reset(pdata);
 }
 
 int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
@@ -889,13 +809,14 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
 
 	netif_tx_stop_all_queues(netdev);
 
+	xgbe_stop_timers(pdata);
+	flush_workqueue(pdata->dev_workqueue);
+
 	hw_if->powerdown_tx(pdata);
 	hw_if->powerdown_rx(pdata);
 
 	xgbe_napi_disable(pdata, 0);
 
-	phy_stop(pdata->phydev);
-
 	pdata->power_down = 1;
 
 	spin_unlock_irqrestore(&pdata->lock, flags);
@@ -924,8 +845,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 
 	pdata->power_down = 0;
 
-	phy_start(pdata->phydev);
-
 	xgbe_napi_enable(pdata, 0);
 
 	hw_if->powerup_tx(pdata);
@@ -936,6 +855,8 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 
 	netif_tx_start_all_queues(netdev);
 
+	xgbe_start_timers(pdata);
+
 	spin_unlock_irqrestore(&pdata->lock, flags);
 
 	DBGPR("<--xgbe_powerup\n");
@@ -946,6 +867,7 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)
 static int xgbe_start(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_phy_if *phy_if = &pdata->phy_if;
 	struct net_device *netdev = pdata->netdev;
 	int ret;
 
@@ -953,7 +875,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	hw_if->init(pdata);
 
-	phy_start(pdata->phydev);
+	ret = phy_if->phy_start(pdata);
+	if (ret)
+		goto err_phy;
 
 	xgbe_napi_enable(pdata, 1);
 
@@ -964,10 +888,11 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 	hw_if->enable_tx(pdata);
 	hw_if->enable_rx(pdata);
 
-	xgbe_init_tx_timers(pdata);
-
 	netif_tx_start_all_queues(netdev);
 
+	xgbe_start_timers(pdata);
+	schedule_work(&pdata->service_work);
+
 	DBGPR("<--xgbe_start\n");
 
 	return 0;
@@ -975,8 +900,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 err_napi:
 	xgbe_napi_disable(pdata, 1);
 
-	phy_stop(pdata->phydev);
+	phy_if->phy_stop(pdata);
 
+err_phy:
 	hw_if->exit(pdata);
 
 	return ret;
@@ -985,6 +911,7 @@ err_napi:
 static void xgbe_stop(struct xgbe_prv_data *pdata)
 {
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_phy_if *phy_if = &pdata->phy_if;
 	struct xgbe_channel *channel;
 	struct net_device *netdev = pdata->netdev;
 	struct netdev_queue *txq;
@@ -994,7 +921,8 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
 
 	netif_tx_stop_all_queues(netdev);
 
-	xgbe_stop_tx_timers(pdata);
+	xgbe_stop_timers(pdata);
+	flush_workqueue(pdata->dev_workqueue);
 
 	hw_if->disable_tx(pdata);
 	hw_if->disable_rx(pdata);
@@ -1003,7 +931,7 @@ static void xgbe_stop(struct xgbe_prv_data *pdata)
 
 	xgbe_napi_disable(pdata, 1);
 
-	phy_stop(pdata->phydev);
+	phy_if->phy_stop(pdata);
 
 	hw_if->exit(pdata);
 
@@ -1374,7 +1302,7 @@ static int xgbe_open(struct net_device *netdev)
 	ret = clk_prepare_enable(pdata->sysclk);
 	if (ret) {
 		netdev_alert(netdev, "dma clk_prepare_enable failed\n");
-		goto err_phy_init;
+		return ret;
 	}
 
 	ret = clk_prepare_enable(pdata->ptpclk);
@@ -1399,14 +1327,17 @@ static int xgbe_open(struct net_device *netdev)
 	if (ret)
 		goto err_channels;
 
-	/* Initialize the device restart and Tx timestamp work struct */
+	INIT_WORK(&pdata->service_work, xgbe_service);
 	INIT_WORK(&pdata->restart_work, xgbe_restart);
 	INIT_WORK(&pdata->tx_tstamp_work, xgbe_tx_tstamp);
+	xgbe_init_timers(pdata);
 
 	ret = xgbe_start(pdata);
 	if (ret)
 		goto err_rings;
 
+	clear_bit(XGBE_DOWN, &pdata->dev_state);
+
 	DBGPR("<--xgbe_open\n");
 
 	return 0;
@@ -1423,9 +1354,6 @@ err_ptpclk:
 err_sysclk:
 	clk_disable_unprepare(pdata->sysclk);
 
-err_phy_init:
-	xgbe_phy_exit(pdata);
-
 	return ret;
 }
 
@@ -1449,8 +1377,7 @@ static int xgbe_close(struct net_device *netdev)
 	clk_disable_unprepare(pdata->ptpclk);
 	clk_disable_unprepare(pdata->sysclk);
 
-	/* Release the phy */
-	xgbe_phy_exit(pdata);
+	set_bit(XGBE_DOWN, &pdata->dev_state);
 
 	DBGPR("<--xgbe_close\n");
 
@@ -1478,7 +1405,8 @@ static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = NETDEV_TX_OK;
 
 	if (skb->len == 0) {
-		netdev_err(netdev, "empty skb received from stack\n");
+		netif_err(pdata, tx_err, netdev,
+			  "empty skb received from stack\n");
 		dev_kfree_skb_any(skb);
 		goto tx_netdev_return;
 	}
@@ -1494,7 +1422,8 @@ static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	ret = xgbe_prep_tso(skb, packet);
 	if (ret) {
-		netdev_err(netdev, "error processing TSO packet\n");
+		netif_err(pdata, tx_err, netdev,
+			  "error processing TSO packet\n");
 		dev_kfree_skb_any(skb);
 		goto tx_netdev_return;
 	}
@@ -1513,9 +1442,8 @@ static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* Configure required descriptor fields for transmission */
 	hw_if->dev_xmit(channel);
 
-#ifdef XGMAC_ENABLE_TX_PKT_DUMP
-	xgbe_print_pkt(netdev, skb, true);
-#endif
+	if (netif_msg_pktdata(pdata))
+		xgbe_print_pkt(netdev, skb, true);
 
 	/* Stop the queue in advance if there may not be enough descriptors */
 	xgbe_maybe_stop_tx_queue(channel, ring, XGBE_TX_MAX_DESCS);
@@ -1710,7 +1638,8 @@ static int xgbe_setup_tc(struct net_device *netdev, u8 tc)
 			       (pdata->q2tc_map[queue] == i))
 				queue++;
 
-			DBGPR("  TC%u using TXq%u-%u\n", i, offset, queue - 1);
+			netif_dbg(pdata, drv, netdev, "TC%u using TXq%u-%u\n",
+				  i, offset, queue - 1);
 			netdev_set_tc_queue(netdev, i, queue - offset, offset);
 			offset = queue;
 		}
@@ -1820,9 +1749,10 @@ static void xgbe_rx_refresh(struct xgbe_channel *channel)
 			  lower_32_bits(rdata->rdesc_dma));
 }
 
-static struct sk_buff *xgbe_create_skb(struct napi_struct *napi,
+static struct sk_buff *xgbe_create_skb(struct xgbe_prv_data *pdata,
+				       struct napi_struct *napi,
 				       struct xgbe_ring_data *rdata,
-				       unsigned int *len)
+				       unsigned int len)
 {
 	struct sk_buff *skb;
 	u8 *packet;
@@ -1832,14 +1762,31 @@ static struct sk_buff *xgbe_create_skb(struct napi_struct *napi,
 	if (!skb)
 		return NULL;
 
+	/* Start with the header buffer which may contain just the header
+	 * or the header plus data
+	 */
+	dma_sync_single_for_cpu(pdata->dev, rdata->rx.hdr.dma,
+				rdata->rx.hdr.dma_len, DMA_FROM_DEVICE);
+
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
-	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : *len;
+	copy_len = (rdata->rx.hdr_len) ? rdata->rx.hdr_len : len;
 	copy_len = min(rdata->rx.hdr.dma_len, copy_len);
 	skb_copy_to_linear_data(skb, packet, copy_len);
 	skb_put(skb, copy_len);
 
-	*len -= copy_len;
+	len -= copy_len;
+	if (len) {
+		/* Add the remaining data as a frag */
+		dma_sync_single_for_cpu(pdata->dev, rdata->rx.buf.dma,
+					rdata->rx.buf.dma_len, DMA_FROM_DEVICE);
+
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				rdata->rx.buf.pa.pages,
+				rdata->rx.buf.pa.pages_offset,
+				len, rdata->rx.buf.dma_len);
+		rdata->rx.buf.pa.pages = NULL;
+	}
 
 	return skb;
 }
@@ -1877,9 +1824,8 @@ static int xgbe_tx_poll(struct xgbe_channel *channel)
 		 * bit */
 		dma_rmb();
 
-#ifdef XGMAC_ENABLE_TX_DESC_DUMP
-		xgbe_dump_tx_desc(ring, ring->dirty, 1, 0);
-#endif
+		if (netif_msg_tx_done(pdata))
+			xgbe_dump_tx_desc(pdata, ring, ring->dirty, 1, 0);
 
 		if (hw_if->is_last_desc(rdesc)) {
 			tx_packets += rdata->tx.packets;
@@ -1922,7 +1868,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	struct sk_buff *skb;
 	struct skb_shared_hwtstamps *hwtstamps;
 	unsigned int incomplete, error, context_next, context;
-	unsigned int len, put_len, max_len;
+	unsigned int len, rdesc_len, max_len;
 	unsigned int received = 0;
 	int packet_count = 0;
 
@@ -1932,6 +1878,9 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 	if (!ring)
 		return 0;
 
+	incomplete = 0;
+	context_next = 0;
+
 	napi = (pdata->per_channel_irq) ? &channel->napi : &pdata->napi;
 
 	rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
@@ -1941,15 +1890,11 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
 
 		/* First time in loop see if we need to restore state */
 		if (!received && rdata->state_saved) {
-			incomplete = rdata->state.incomplete;
-			context_next = rdata->state.context_next;
 			skb = rdata->state.skb;
 			error = rdata->state.error;
 			len = rdata->state.len;
 		} else {
 			memset(packet, 0, sizeof(*packet));
-			incomplete = 0;
-			context_next = 0;
 			skb = NULL;
 			error = 0;
 			len = 0;
@@ -1983,29 +1928,23 @@ read_again:
 
 		if (error || packet->errors) {
 			if (packet->errors)
-				DBGPR("Error in received packet\n");
+				netif_err(pdata, rx_err, netdev,
+					  "error in received packet\n");
 			dev_kfree_skb(skb);
 			goto next_packet;
 		}
 
 		if (!context) {
-			put_len = rdata->rx.len - len;
-			len += put_len;
-
-			if (!skb) {
-				dma_sync_single_for_cpu(pdata->dev,
-							rdata->rx.hdr.dma,
-							rdata->rx.hdr.dma_len,
-							DMA_FROM_DEVICE);
-
-				skb = xgbe_create_skb(napi, rdata, &put_len);
-				if (!skb) {
+			/* Length is cumulative, get this descriptor's length */
+			rdesc_len = rdata->rx.len - len;
+			len += rdesc_len;
+
+			if (rdesc_len && !skb) {
+				skb = xgbe_create_skb(pdata, napi, rdata,
+						      rdesc_len);
+				if (!skb)
 					error = 1;
-					goto skip_data;
-				}
-			}
-
-			if (put_len) {
+			} else if (rdesc_len) {
 				dma_sync_single_for_cpu(pdata->dev,
 							rdata->rx.buf.dma,
 							rdata->rx.buf.dma_len,
@@ -2014,12 +1953,12 @@ read_again:
 				skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 						rdata->rx.buf.pa.pages,
 						rdata->rx.buf.pa.pages_offset,
-						put_len, rdata->rx.buf.dma_len);
+						rdesc_len,
+						rdata->rx.buf.dma_len);
 				rdata->rx.buf.pa.pages = NULL;
 			}
 		}
 
-skip_data:
 		if (incomplete || context_next)
 			goto read_again;
 
@@ -2033,14 +1972,14 @@ skip_data:
 			max_len += VLAN_HLEN;
 
 		if (skb->len > max_len) {
-			DBGPR("packet length exceeds configured MTU\n");
+			netif_err(pdata, rx_err, netdev,
+				  "packet length exceeds configured MTU\n");
 			dev_kfree_skb(skb);
 			goto next_packet;
 		}
 
-#ifdef XGMAC_ENABLE_RX_PKT_DUMP
-		xgbe_print_pkt(netdev, skb, false);
-#endif
+		if (netif_msg_pktdata(pdata))
+			xgbe_print_pkt(netdev, skb, false);
 
 		skb_checksum_none_assert(skb);
 		if (XGMAC_GET_BITS(packet->attributes,
@@ -2072,7 +2011,6 @@ skip_data:
 		skb_record_rx_queue(skb, channel->queue_index);
 		skb_mark_napi_id(skb, napi);
 
-		netdev->last_rx = jiffies;
 		napi_gro_receive(napi, skb);
 
 next_packet:
@@ -2083,8 +2021,6 @@ next_packet:
 	if (received && (incomplete || context_next)) {
 		rdata = XGBE_GET_DESC_DATA(ring, ring->cur);
 		rdata->state_saved = 1;
-		rdata->state.incomplete = incomplete;
-		rdata->state.context_next = context_next;
 		rdata->state.skb = skb;
 		rdata->state.len = len;
 		rdata->state.error = error;
@@ -2165,8 +2101,8 @@ static int xgbe_all_poll(struct napi_struct *napi, int budget)
 	return processed;
 }
 
-void xgbe_dump_tx_desc(struct xgbe_ring *ring, unsigned int idx,
-		       unsigned int count, unsigned int flag)
+void xgbe_dump_tx_desc(struct xgbe_prv_data *pdata, struct xgbe_ring *ring,
+		       unsigned int idx, unsigned int count, unsigned int flag)
 {
 	struct xgbe_ring_data *rdata;
 	struct xgbe_ring_desc *rdesc;
@@ -2174,20 +2110,29 @@ void xgbe_dump_tx_desc(struct xgbe_ring *ring, unsigned int idx,
 	while (count--) {
 		rdata = XGBE_GET_DESC_DATA(ring, idx);
 		rdesc = rdata->rdesc;
-		pr_alert("TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
-			 (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
-			 le32_to_cpu(rdesc->desc0), le32_to_cpu(rdesc->desc1),
-			 le32_to_cpu(rdesc->desc2), le32_to_cpu(rdesc->desc3));
+		netdev_dbg(pdata->netdev,
+			   "TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
+			   (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
+			   le32_to_cpu(rdesc->desc0),
+			   le32_to_cpu(rdesc->desc1),
+			   le32_to_cpu(rdesc->desc2),
+			   le32_to_cpu(rdesc->desc3));
 		idx++;
 	}
 }
 
-void xgbe_dump_rx_desc(struct xgbe_ring *ring, struct xgbe_ring_desc *desc,
+void xgbe_dump_rx_desc(struct xgbe_prv_data *pdata, struct xgbe_ring *ring,
 		       unsigned int idx)
 {
-	pr_alert("RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n", idx,
-		 le32_to_cpu(desc->desc0), le32_to_cpu(desc->desc1),
-		 le32_to_cpu(desc->desc2), le32_to_cpu(desc->desc3));
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+
+	rdata = XGBE_GET_DESC_DATA(ring, idx);
+	rdesc = rdata->rdesc;
+	netdev_dbg(pdata->netdev,
+		   "RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n",
+		   idx, le32_to_cpu(rdesc->desc0), le32_to_cpu(rdesc->desc1),
+		   le32_to_cpu(rdesc->desc2), le32_to_cpu(rdesc->desc3));
 }
 
 void xgbe_print_pkt(struct net_device *netdev, struct sk_buff *skb, bool tx_rx)
@@ -2197,21 +2142,21 @@ void xgbe_print_pkt(struct net_device *netdev, struct sk_buff *skb, bool tx_rx)
 	unsigned char buffer[128];
 	unsigned int i, j;
 
-	netdev_alert(netdev, "\n************** SKB dump ****************\n");
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
 
-	netdev_alert(netdev, "%s packet of %d bytes\n",
-		     (tx_rx ? "TX" : "RX"), skb->len);
+	netdev_dbg(netdev, "%s packet of %d bytes\n",
+		   (tx_rx ? "TX" : "RX"), skb->len);
 
-	netdev_alert(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
-	netdev_alert(netdev, "Src MAC addr: %pM\n", eth->h_source);
-	netdev_alert(netdev, "Protocol: 0x%04hx\n", ntohs(eth->h_proto));
+	netdev_dbg(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
+	netdev_dbg(netdev, "Src MAC addr: %pM\n", eth->h_source);
+	netdev_dbg(netdev, "Protocol: %#06hx\n", ntohs(eth->h_proto));
 
 	for (i = 0, j = 0; i < skb->len;) {
 		j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx",
 			      buf[i++]);
 
 		if ((i % 32) == 0) {
-			netdev_alert(netdev, "  0x%04x: %s\n", i - 32, buffer);
+			netdev_dbg(netdev, "  %#06x: %s\n", i - 32, buffer);
 			j = 0;
 		} else if ((i % 16) == 0) {
 			buffer[j++] = ' ';
@@ -2221,7 +2166,7 @@ void xgbe_print_pkt(struct net_device *netdev, struct sk_buff *skb, bool tx_rx)
 		}
 	}
 	if (i % 32)
-		netdev_alert(netdev, "  0x%04x: %s\n", i - (i % 32), buffer);
+		netdev_dbg(netdev, "  %#06x: %s\n", i - (i % 32), buffer);
 
-	netdev_alert(netdev, "\n************** SKB dump ****************\n");
+	netdev_dbg(netdev, "\n************** SKB dump ****************\n");
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 5f149e8ee20f..59e090e95c0e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -133,6 +133,12 @@ struct xgbe_stats {
 	  offsetof(struct xgbe_prv_data, mmc_stats._var),	\
 	}
 
+#define XGMAC_EXT_STAT(_string, _var)				\
+	{ _string,						\
+	  FIELD_SIZEOF(struct xgbe_ext_stats, _var),		\
+	  offsetof(struct xgbe_prv_data, ext_stats._var),	\
+	}
+
 static const struct xgbe_stats xgbe_gstring_stats[] = {
 	XGMAC_MMC_STAT("tx_bytes", txoctetcount_gb),
 	XGMAC_MMC_STAT("tx_packets", txframecount_gb),
@@ -140,6 +146,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = {
 	XGMAC_MMC_STAT("tx_broadcast_packets", txbroadcastframes_gb),
 	XGMAC_MMC_STAT("tx_multicast_packets", txmulticastframes_gb),
 	XGMAC_MMC_STAT("tx_vlan_packets", txvlanframes_g),
+	XGMAC_EXT_STAT("tx_tso_packets", tx_tso_packets),
 	XGMAC_MMC_STAT("tx_64_byte_packets", tx64octets_gb),
 	XGMAC_MMC_STAT("tx_65_to_127_byte_packets", tx65to127octets_gb),
 	XGMAC_MMC_STAT("tx_128_to_255_byte_packets", tx128to255octets_gb),
@@ -171,6 +178,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = {
 	XGMAC_MMC_STAT("rx_fifo_overflow_errors", rxfifooverflow),
 	XGMAC_MMC_STAT("rx_watchdog_errors", rxwatchdogerror),
 	XGMAC_MMC_STAT("rx_pause_frames", rxpauseframes),
+	XGMAC_EXT_STAT("rx_split_header_packets", rx_split_header_packets),
 };
 
 #define XGBE_STATS_COUNT	ARRAY_SIZE(xgbe_gstring_stats)
@@ -239,9 +247,9 @@ static void xgbe_get_pauseparam(struct net_device *netdev,
 
 	DBGPR("-->xgbe_get_pauseparam\n");
 
-	pause->autoneg = pdata->pause_autoneg;
-	pause->tx_pause = pdata->tx_pause;
-	pause->rx_pause = pdata->rx_pause;
+	pause->autoneg = pdata->phy.pause_autoneg;
+	pause->tx_pause = pdata->phy.tx_pause;
+	pause->rx_pause = pdata->phy.rx_pause;
 
 	DBGPR("<--xgbe_get_pauseparam\n");
 }
@@ -250,7 +258,6 @@ static int xgbe_set_pauseparam(struct net_device *netdev,
 			       struct ethtool_pauseparam *pause)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
-	struct phy_device *phydev = pdata->phydev;
 	int ret = 0;
 
 	DBGPR("-->xgbe_set_pauseparam\n");
@@ -258,21 +265,26 @@ static int xgbe_set_pauseparam(struct net_device *netdev,
 	DBGPR("  autoneg = %d, tx_pause = %d, rx_pause = %d\n",
 	      pause->autoneg, pause->tx_pause, pause->rx_pause);
 
-	pdata->pause_autoneg = pause->autoneg;
-	if (pause->autoneg) {
-		phydev->advertising |= ADVERTISED_Pause;
-		phydev->advertising |= ADVERTISED_Asym_Pause;
+	if (pause->autoneg && (pdata->phy.autoneg != AUTONEG_ENABLE))
+		return -EINVAL;
+
+	pdata->phy.pause_autoneg = pause->autoneg;
+	pdata->phy.tx_pause = pause->tx_pause;
+	pdata->phy.rx_pause = pause->rx_pause;
 
-	} else {
-		phydev->advertising &= ~ADVERTISED_Pause;
-		phydev->advertising &= ~ADVERTISED_Asym_Pause;
+	pdata->phy.advertising &= ~ADVERTISED_Pause;
+	pdata->phy.advertising &= ~ADVERTISED_Asym_Pause;
 
-		pdata->tx_pause = pause->tx_pause;
-		pdata->rx_pause = pause->rx_pause;
+	if (pause->rx_pause) {
+		pdata->phy.advertising |= ADVERTISED_Pause;
+		pdata->phy.advertising |= ADVERTISED_Asym_Pause;
 	}
 
+	if (pause->tx_pause)
+		pdata->phy.advertising ^= ADVERTISED_Asym_Pause;
+
 	if (netif_running(netdev))
-		ret = phy_start_aneg(phydev);
+		ret = pdata->phy_if.phy_config_aneg(pdata);
 
 	DBGPR("<--xgbe_set_pauseparam\n");
 
@@ -283,36 +295,39 @@ static int xgbe_get_settings(struct net_device *netdev,
 			     struct ethtool_cmd *cmd)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
-	int ret;
 
 	DBGPR("-->xgbe_get_settings\n");
 
-	if (!pdata->phydev)
-		return -ENODEV;
+	cmd->phy_address = pdata->phy.address;
+
+	cmd->supported = pdata->phy.supported;
+	cmd->advertising = pdata->phy.advertising;
+	cmd->lp_advertising = pdata->phy.lp_advertising;
+
+	cmd->autoneg = pdata->phy.autoneg;
+	ethtool_cmd_speed_set(cmd, pdata->phy.speed);
+	cmd->duplex = pdata->phy.duplex;
 
-	ret = phy_ethtool_gset(pdata->phydev, cmd);
+	cmd->port = PORT_NONE;
+	cmd->transceiver = XCVR_INTERNAL;
 
 	DBGPR("<--xgbe_get_settings\n");
 
-	return ret;
+	return 0;
 }
 
 static int xgbe_set_settings(struct net_device *netdev,
 			     struct ethtool_cmd *cmd)
 {
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
-	struct phy_device *phydev = pdata->phydev;
 	u32 speed;
 	int ret;
 
 	DBGPR("-->xgbe_set_settings\n");
 
-	if (!pdata->phydev)
-		return -ENODEV;
-
 	speed = ethtool_cmd_speed(cmd);
 
-	if (cmd->phy_address != phydev->addr)
+	if (cmd->phy_address != pdata->phy.address)
 		return -EINVAL;
 
 	if ((cmd->autoneg != AUTONEG_ENABLE) &&
@@ -333,23 +348,23 @@ static int xgbe_set_settings(struct net_device *netdev,
 			return -EINVAL;
 	}
 
-	cmd->advertising &= phydev->supported;
+	cmd->advertising &= pdata->phy.supported;
 	if ((cmd->autoneg == AUTONEG_ENABLE) && !cmd->advertising)
 		return -EINVAL;
 
 	ret = 0;
-	phydev->autoneg = cmd->autoneg;
-	phydev->speed = speed;
-	phydev->duplex = cmd->duplex;
-	phydev->advertising = cmd->advertising;
+	pdata->phy.autoneg = cmd->autoneg;
+	pdata->phy.speed = speed;
+	pdata->phy.duplex = cmd->duplex;
+	pdata->phy.advertising = cmd->advertising;
 
 	if (cmd->autoneg == AUTONEG_ENABLE)
-		phydev->advertising |= ADVERTISED_Autoneg;
+		pdata->phy.advertising |= ADVERTISED_Autoneg;
 	else
-		phydev->advertising &= ~ADVERTISED_Autoneg;
+		pdata->phy.advertising &= ~ADVERTISED_Autoneg;
 
 	if (netif_running(netdev))
-		ret = phy_start_aneg(phydev);
+		ret = pdata->phy_if.phy_config_aneg(pdata);
 
 	DBGPR("<--xgbe_set_settings\n");
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
index 714905384900..e83bd76abce6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -124,9 +124,11 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_address.h>
+#include <linux/of_platform.h>
 #include <linux/clk.h>
 #include <linux/property.h>
 #include <linux/acpi.h>
+#include <linux/mdio.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -136,6 +138,49 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_VERSION(XGBE_DRV_VERSION);
 MODULE_DESCRIPTION(XGBE_DRV_DESC);
 
+static int debug = -1;
+module_param(debug, int, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(debug, " Network interface message level setting");
+
+static const u32 default_msg_level = (NETIF_MSG_LINK | NETIF_MSG_IFDOWN |
+				      NETIF_MSG_IFUP);
+
+static const u32 xgbe_serdes_blwc[] = {
+	XGBE_SPEED_1000_BLWC,
+	XGBE_SPEED_2500_BLWC,
+	XGBE_SPEED_10000_BLWC,
+};
+
+static const u32 xgbe_serdes_cdr_rate[] = {
+	XGBE_SPEED_1000_CDR,
+	XGBE_SPEED_2500_CDR,
+	XGBE_SPEED_10000_CDR,
+};
+
+static const u32 xgbe_serdes_pq_skew[] = {
+	XGBE_SPEED_1000_PQ,
+	XGBE_SPEED_2500_PQ,
+	XGBE_SPEED_10000_PQ,
+};
+
+static const u32 xgbe_serdes_tx_amp[] = {
+	XGBE_SPEED_1000_TXAMP,
+	XGBE_SPEED_2500_TXAMP,
+	XGBE_SPEED_10000_TXAMP,
+};
+
+static const u32 xgbe_serdes_dfe_tap_cfg[] = {
+	XGBE_SPEED_1000_DFE_TAP_CONFIG,
+	XGBE_SPEED_2500_DFE_TAP_CONFIG,
+	XGBE_SPEED_10000_DFE_TAP_CONFIG,
+};
+
+static const u32 xgbe_serdes_dfe_tap_ena[] = {
+	XGBE_SPEED_1000_DFE_TAP_ENABLE,
+	XGBE_SPEED_2500_DFE_TAP_ENABLE,
+	XGBE_SPEED_10000_DFE_TAP_ENABLE,
+};
+
 static void xgbe_default_config(struct xgbe_prv_data *pdata)
 {
 	DBGPR("-->xgbe_default_config\n");
@@ -153,8 +198,6 @@ static void xgbe_default_config(struct xgbe_prv_data *pdata)
 	pdata->rx_pause = 1;
 	pdata->phy_speed = SPEED_UNKNOWN;
 	pdata->power_down = 0;
-	pdata->default_autoneg = AUTONEG_ENABLE;
-	pdata->default_speed = SPEED_10000;
 
 	DBGPR("<--xgbe_default_config\n");
 }
@@ -162,19 +205,15 @@ static void xgbe_default_config(struct xgbe_prv_data *pdata)
 static void xgbe_init_all_fptrs(struct xgbe_prv_data *pdata)
 {
 	xgbe_init_function_ptrs_dev(&pdata->hw_if);
+	xgbe_init_function_ptrs_phy(&pdata->phy_if);
 	xgbe_init_function_ptrs_desc(&pdata->desc_if);
 }
 
 #ifdef CONFIG_ACPI
 static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
 {
-	struct acpi_device *adev = pdata->adev;
 	struct device *dev = pdata->dev;
 	u32 property;
-	acpi_handle handle;
-	acpi_status status;
-	unsigned long long data;
-	int cca;
 	int ret;
 
 	/* Obtain the system clock setting */
@@ -195,24 +234,6 @@ static int xgbe_acpi_support(struct xgbe_prv_data *pdata)
 	}
 	pdata->ptpclk_rate = property;
 
-	/* Retrieve the device cache coherency value */
-	handle = adev->handle;
-	do {
-		status = acpi_evaluate_integer(handle, "_CCA", NULL, &data);
-		if (!ACPI_FAILURE(status)) {
-			cca = data;
-			break;
-		}
-
-		status = acpi_get_parent(handle, &handle);
-	} while (!ACPI_FAILURE(status));
-
-	if (ACPI_FAILURE(status)) {
-		dev_err(dev, "error obtaining acpi coherency value\n");
-		return -EINVAL;
-	}
-	pdata->coherent = !!cca;
-
 	return 0;
 }
 #else   /* CONFIG_ACPI */
@@ -243,28 +264,84 @@ static int xgbe_of_support(struct xgbe_prv_data *pdata)
 	}
 	pdata->ptpclk_rate = clk_get_rate(pdata->ptpclk);
 
-	/* Retrieve the device cache coherency value */
-	pdata->coherent = of_dma_is_coherent(dev->of_node);
-
 	return 0;
 }
+
+static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+	struct device *dev = pdata->dev;
+	struct device_node *phy_node;
+	struct platform_device *phy_pdev;
+
+	phy_node = of_parse_phandle(dev->of_node, "phy-handle", 0);
+	if (phy_node) {
+		/* Old style device tree:
+		 *   The XGBE and PHY resources are separate
+		 */
+		phy_pdev = of_find_device_by_node(phy_node);
+		of_node_put(phy_node);
+	} else {
+		/* New style device tree:
+		 *   The XGBE and PHY resources are grouped together with
+		 *   the PHY resources listed last
+		 */
+		get_device(dev);
+		phy_pdev = pdata->pdev;
+	}
+
+	return phy_pdev;
+}
 #else   /* CONFIG_OF */
 static int xgbe_of_support(struct xgbe_prv_data *pdata)
 {
 	return -EINVAL;
 }
-#endif  /*CONFIG_OF */
+
+static struct platform_device *xgbe_of_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+	return NULL;
+}
+#endif  /* CONFIG_OF */
+
+static unsigned int xgbe_resource_count(struct platform_device *pdev,
+					unsigned int type)
+{
+	unsigned int count;
+	int i;
+
+	for (i = 0, count = 0; i < pdev->num_resources; i++) {
+		struct resource *res = &pdev->resource[i];
+
+		if (type == resource_type(res))
+			count++;
+	}
+
+	return count;
+}
+
+static struct platform_device *xgbe_get_phy_pdev(struct xgbe_prv_data *pdata)
+{
+	struct platform_device *phy_pdev;
+
+	if (pdata->use_acpi) {
+		get_device(pdata->dev);
+		phy_pdev = pdata->pdev;
+	} else {
+		phy_pdev = xgbe_of_get_phy_pdev(pdata);
+	}
+
+	return phy_pdev;
+}
 
 static int xgbe_probe(struct platform_device *pdev)
 {
 	struct xgbe_prv_data *pdata;
-	struct xgbe_hw_if *hw_if;
-	struct xgbe_desc_if *desc_if;
 	struct net_device *netdev;
-	struct device *dev = &pdev->dev;
+	struct device *dev = &pdev->dev, *phy_dev;
+	struct platform_device *phy_pdev;
 	struct resource *res;
 	const char *phy_mode;
-	unsigned int i;
+	unsigned int i, phy_memnum, phy_irqnum;
 	int ret;
 
 	DBGPR("--> xgbe_probe\n");
@@ -289,9 +366,36 @@ static int xgbe_probe(struct platform_device *pdev)
 	mutex_init(&pdata->rss_mutex);
 	spin_lock_init(&pdata->tstamp_lock);
 
+	pdata->msg_enable = netif_msg_init(debug, default_msg_level);
+
+	set_bit(XGBE_DOWN, &pdata->dev_state);
+
 	/* Check if we should use ACPI or DT */
 	pdata->use_acpi = (!pdata->adev || acpi_disabled) ? 0 : 1;
 
+	phy_pdev = xgbe_get_phy_pdev(pdata);
+	if (!phy_pdev) {
+		dev_err(dev, "unable to obtain phy device\n");
+		ret = -EINVAL;
+		goto err_phydev;
+	}
+	phy_dev = &phy_pdev->dev;
+
+	if (pdev == phy_pdev) {
+		/* New style device tree or ACPI:
+		 *   The XGBE and PHY resources are grouped together with
+		 *   the PHY resources listed last
+		 */
+		phy_memnum = xgbe_resource_count(pdev, IORESOURCE_MEM) - 3;
+		phy_irqnum = xgbe_resource_count(pdev, IORESOURCE_IRQ) - 1;
+	} else {
+		/* Old style device tree:
+		 *   The XGBE and PHY resources are separate
+		 */
+		phy_memnum = 0;
+		phy_irqnum = 0;
+	}
+
 	/* Set and validate the number of descriptors for a ring */
 	BUILD_BUG_ON_NOT_POWER_OF_2(XGBE_TX_DESC_CNT);
 	pdata->tx_desc_count = XGBE_TX_DESC_CNT;
@@ -318,7 +422,8 @@ static int xgbe_probe(struct platform_device *pdev)
 		ret = PTR_ERR(pdata->xgmac_regs);
 		goto err_io;
 	}
-	DBGPR("  xgmac_regs = %p\n", pdata->xgmac_regs);
+	if (netif_msg_probe(pdata))
+		dev_dbg(dev, "xgmac_regs = %p\n", pdata->xgmac_regs);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	pdata->xpcs_regs = devm_ioremap_resource(dev, res);
@@ -327,7 +432,38 @@ static int xgbe_probe(struct platform_device *pdev)
 		ret = PTR_ERR(pdata->xpcs_regs);
 		goto err_io;
 	}
-	DBGPR("  xpcs_regs  = %p\n", pdata->xpcs_regs);
+	if (netif_msg_probe(pdata))
+		dev_dbg(dev, "xpcs_regs  = %p\n", pdata->xpcs_regs);
+
+	res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+	pdata->rxtx_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pdata->rxtx_regs)) {
+		dev_err(dev, "rxtx ioremap failed\n");
+		ret = PTR_ERR(pdata->rxtx_regs);
+		goto err_io;
+	}
+	if (netif_msg_probe(pdata))
+		dev_dbg(dev, "rxtx_regs  = %p\n", pdata->rxtx_regs);
+
+	res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+	pdata->sir0_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pdata->sir0_regs)) {
+		dev_err(dev, "sir0 ioremap failed\n");
+		ret = PTR_ERR(pdata->sir0_regs);
+		goto err_io;
+	}
+	if (netif_msg_probe(pdata))
+		dev_dbg(dev, "sir0_regs  = %p\n", pdata->sir0_regs);
+
+	res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++);
+	pdata->sir1_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pdata->sir1_regs)) {
+		dev_err(dev, "sir1 ioremap failed\n");
+		ret = PTR_ERR(pdata->sir1_regs);
+		goto err_io;
+	}
+	if (netif_msg_probe(pdata))
+		dev_dbg(dev, "sir1_regs  = %p\n", pdata->sir1_regs);
 
 	/* Retrieve the MAC address */
 	ret = device_property_read_u8_array(dev, XGBE_MAC_ADDR_PROPERTY,
@@ -355,6 +491,115 @@ static int xgbe_probe(struct platform_device *pdev)
 	if (device_property_present(dev, XGBE_DMA_IRQS_PROPERTY))
 		pdata->per_channel_irq = 1;
 
+	/* Retrieve the PHY speedset */
+	ret = device_property_read_u32(phy_dev, XGBE_SPEEDSET_PROPERTY,
+				       &pdata->speed_set);
+	if (ret) {
+		dev_err(dev, "invalid %s property\n", XGBE_SPEEDSET_PROPERTY);
+		goto err_io;
+	}
+
+	switch (pdata->speed_set) {
+	case XGBE_SPEEDSET_1000_10000:
+	case XGBE_SPEEDSET_2500_10000:
+		break;
+	default:
+		dev_err(dev, "invalid %s property\n", XGBE_SPEEDSET_PROPERTY);
+		ret = -EINVAL;
+		goto err_io;
+	}
+
+	/* Retrieve the PHY configuration properties */
+	if (device_property_present(phy_dev, XGBE_BLWC_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_BLWC_PROPERTY,
+						     pdata->serdes_blwc,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_BLWC_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_blwc, xgbe_serdes_blwc,
+		       sizeof(pdata->serdes_blwc));
+	}
+
+	if (device_property_present(phy_dev, XGBE_CDR_RATE_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_CDR_RATE_PROPERTY,
+						     pdata->serdes_cdr_rate,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_CDR_RATE_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_cdr_rate, xgbe_serdes_cdr_rate,
+		       sizeof(pdata->serdes_cdr_rate));
+	}
+
+	if (device_property_present(phy_dev, XGBE_PQ_SKEW_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_PQ_SKEW_PROPERTY,
+						     pdata->serdes_pq_skew,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_PQ_SKEW_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_pq_skew, xgbe_serdes_pq_skew,
+		       sizeof(pdata->serdes_pq_skew));
+	}
+
+	if (device_property_present(phy_dev, XGBE_TX_AMP_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_TX_AMP_PROPERTY,
+						     pdata->serdes_tx_amp,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_TX_AMP_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_tx_amp, xgbe_serdes_tx_amp,
+		       sizeof(pdata->serdes_tx_amp));
+	}
+
+	if (device_property_present(phy_dev, XGBE_DFE_CFG_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_DFE_CFG_PROPERTY,
+						     pdata->serdes_dfe_tap_cfg,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_DFE_CFG_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_dfe_tap_cfg, xgbe_serdes_dfe_tap_cfg,
+		       sizeof(pdata->serdes_dfe_tap_cfg));
+	}
+
+	if (device_property_present(phy_dev, XGBE_DFE_ENA_PROPERTY)) {
+		ret = device_property_read_u32_array(phy_dev,
+						     XGBE_DFE_ENA_PROPERTY,
+						     pdata->serdes_dfe_tap_ena,
+						     XGBE_SPEEDS);
+		if (ret) {
+			dev_err(dev, "invalid %s property\n",
+				XGBE_DFE_ENA_PROPERTY);
+			goto err_io;
+		}
+	} else {
+		memcpy(pdata->serdes_dfe_tap_ena, xgbe_serdes_dfe_tap_ena,
+		       sizeof(pdata->serdes_dfe_tap_ena));
+	}
+
 	/* Obtain device settings unique to ACPI/OF */
 	if (pdata->use_acpi)
 		ret = xgbe_acpi_support(pdata);
@@ -364,6 +609,7 @@ static int xgbe_probe(struct platform_device *pdev)
 		goto err_io;
 
 	/* Set the DMA coherency values */
+	pdata->coherent = device_dma_is_coherent(pdata->dev);
 	if (pdata->coherent) {
 		pdata->axdomain = XGBE_DMA_OS_AXDOMAIN;
 		pdata->arcache = XGBE_DMA_OS_ARCACHE;
@@ -382,17 +628,23 @@ static int xgbe_probe(struct platform_device *pdev)
 	}
 	pdata->dev_irq = ret;
 
+	/* Get the auto-negotiation interrupt */
+	ret = platform_get_irq(phy_pdev, phy_irqnum++);
+	if (ret < 0) {
+		dev_err(dev, "platform_get_irq phy 0 failed\n");
+		goto err_io;
+	}
+	pdata->an_irq = ret;
+
 	netdev->irq = pdata->dev_irq;
 	netdev->base_addr = (unsigned long)pdata->xgmac_regs;
 	memcpy(netdev->dev_addr, pdata->mac_addr, netdev->addr_len);
 
 	/* Set all the function pointers */
 	xgbe_init_all_fptrs(pdata);
-	hw_if = &pdata->hw_if;
-	desc_if = &pdata->desc_if;
 
 	/* Issue software reset to device */
-	hw_if->exit(pdata);
+	pdata->hw_if.exit(pdata);
 
 	/* Populate the hardware features */
 	xgbe_get_all_hw_features(pdata);
@@ -401,8 +653,6 @@ static int xgbe_probe(struct platform_device *pdev)
 	xgbe_default_config(pdata);
 
 	/* Set the DMA mask */
-	if (!dev->dma_mask)
-		dev->dma_mask = &dev->coherent_dma_mask;
 	ret = dma_set_mask_and_coherent(dev,
 					DMA_BIT_MASK(pdata->hw_feat.dma_width));
 	if (ret) {
@@ -447,16 +697,8 @@ static int xgbe_probe(struct platform_device *pdev)
 	XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, TCP4TE, 1);
 	XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1);
 
-	/* Prepare to regsiter with MDIO */
-	pdata->mii_bus_id = kasprintf(GFP_KERNEL, "%s", pdev->name);
-	if (!pdata->mii_bus_id) {
-		dev_err(dev, "failed to allocate mii bus id\n");
-		ret = -ENOMEM;
-		goto err_io;
-	}
-	ret = xgbe_mdio_register(pdata);
-	if (ret)
-		goto err_bus_id;
+	/* Call MDIO/PHY initialization routine */
+	pdata->phy_if.phy_init(pdata);
 
 	/* Set device operations */
 	netdev->netdev_ops = xgbe_get_netdev_ops();
@@ -501,26 +743,52 @@ static int xgbe_probe(struct platform_device *pdev)
 	ret = register_netdev(netdev);
 	if (ret) {
 		dev_err(dev, "net device registration failed\n");
-		goto err_reg_netdev;
+		goto err_io;
+	}
+
+	/* Create the PHY/ANEG name based on netdev name */
+	snprintf(pdata->an_name, sizeof(pdata->an_name) - 1, "%s-pcs",
+		 netdev_name(netdev));
+
+	/* Create workqueues */
+	pdata->dev_workqueue =
+		create_singlethread_workqueue(netdev_name(netdev));
+	if (!pdata->dev_workqueue) {
+		netdev_err(netdev, "device workqueue creation failed\n");
+		ret = -ENOMEM;
+		goto err_netdev;
+	}
+
+	pdata->an_workqueue =
+		create_singlethread_workqueue(pdata->an_name);
+	if (!pdata->an_workqueue) {
+		netdev_err(netdev, "phy workqueue creation failed\n");
+		ret = -ENOMEM;
+		goto err_wq;
 	}
 
 	xgbe_ptp_register(pdata);
 
 	xgbe_debugfs_init(pdata);
 
+	platform_device_put(phy_pdev);
+
 	netdev_notice(netdev, "net device enabled\n");
 
 	DBGPR("<-- xgbe_probe\n");
 
 	return 0;
 
-err_reg_netdev:
-	xgbe_mdio_unregister(pdata);
+err_wq:
+	destroy_workqueue(pdata->dev_workqueue);
 
-err_bus_id:
-	kfree(pdata->mii_bus_id);
+err_netdev:
+	unregister_netdev(netdev);
 
 err_io:
+	platform_device_put(phy_pdev);
+
+err_phydev:
 	free_netdev(netdev);
 
 err_alloc:
@@ -540,11 +808,13 @@ static int xgbe_remove(struct platform_device *pdev)
 
 	xgbe_ptp_unregister(pdata);
 
-	unregister_netdev(netdev);
+	flush_workqueue(pdata->an_workqueue);
+	destroy_workqueue(pdata->an_workqueue);
 
-	xgbe_mdio_unregister(pdata);
+	flush_workqueue(pdata->dev_workqueue);
+	destroy_workqueue(pdata->dev_workqueue);
 
-	kfree(pdata->mii_bus_id);
+	unregister_netdev(netdev);
 
 	free_netdev(netdev);
 
@@ -557,16 +827,17 @@ static int xgbe_remove(struct platform_device *pdev)
 static int xgbe_suspend(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
-	int ret;
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	int ret = 0;
 
 	DBGPR("-->xgbe_suspend\n");
 
-	if (!netif_running(netdev)) {
-		DBGPR("<--xgbe_dev_suspend\n");
-		return -EINVAL;
-	}
+	if (netif_running(netdev))
+		ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
 
-	ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
+	pdata->lpm_ctrl = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	pdata->lpm_ctrl |= MDIO_CTRL1_LPOWER;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
 
 	DBGPR("<--xgbe_suspend\n");
 
@@ -576,16 +847,16 @@ static int xgbe_suspend(struct device *dev)
 static int xgbe_resume(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
-	int ret;
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	int ret = 0;
 
 	DBGPR("-->xgbe_resume\n");
 
-	if (!netif_running(netdev)) {
-		DBGPR("<--xgbe_dev_resume\n");
-		return -EINVAL;
-	}
+	pdata->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, pdata->lpm_ctrl);
 
-	ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
+	if (netif_running(netdev))
+		ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
 
 	DBGPR("<--xgbe_resume\n");
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 59e267f3f1b7..9088c3a35a20 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -119,194 +119,1246 @@
 #include <linux/mdio.h>
 #include <linux/phy.h>
 #include <linux/of.h>
+#include <linux/bitops.h>
+#include <linux/jiffies.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
 
-static int xgbe_mdio_read(struct mii_bus *mii, int prtad, int mmd_reg)
+static void xgbe_an_enable_kr_training(struct xgbe_prv_data *pdata)
 {
-	struct xgbe_prv_data *pdata = mii->priv;
-	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	int mmd_data;
+	unsigned int reg;
 
-	DBGPR_MDIO("-->xgbe_mdio_read: prtad=%#x mmd_reg=%#x\n",
-		   prtad, mmd_reg);
+	reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
 
-	mmd_data = hw_if->read_mmd_regs(pdata, prtad, mmd_reg);
+	reg |= XGBE_KR_TRAINING_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
+}
+
+static void xgbe_an_disable_kr_training(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg;
 
-	DBGPR_MDIO("<--xgbe_mdio_read: mmd_data=%#x\n", mmd_data);
+	reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
 
-	return mmd_data;
+	reg &= ~XGBE_KR_TRAINING_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
 }
 
-static int xgbe_mdio_write(struct mii_bus *mii, int prtad, int mmd_reg,
-			   u16 mmd_val)
+static void xgbe_pcs_power_cycle(struct xgbe_prv_data *pdata)
 {
-	struct xgbe_prv_data *pdata = mii->priv;
-	struct xgbe_hw_if *hw_if = &pdata->hw_if;
-	int mmd_data = mmd_val;
+	unsigned int reg;
 
-	DBGPR_MDIO("-->xgbe_mdio_write: prtad=%#x mmd_reg=%#x mmd_data=%#x\n",
-		   prtad, mmd_reg, mmd_data);
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
 
-	hw_if->write_mmd_regs(pdata, prtad, mmd_reg, mmd_data);
+	reg |= MDIO_CTRL1_LPOWER;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
 
-	DBGPR_MDIO("<--xgbe_mdio_write\n");
+	usleep_range(75, 100);
 
-	return 0;
+	reg &= ~MDIO_CTRL1_LPOWER;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
 }
 
-void xgbe_dump_phy_registers(struct xgbe_prv_data *pdata)
+static void xgbe_serdes_start_ratechange(struct xgbe_prv_data *pdata)
 {
-	struct device *dev = pdata->dev;
-	struct phy_device *phydev = pdata->mii->phy_map[XGBE_PRTAD];
-	int i;
-
-	dev_alert(dev, "\n************* PHY Reg dump **********************\n");
-
-	dev_alert(dev, "PCS Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1));
-	dev_alert(dev, "PCS Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1));
-	dev_alert(dev, "Phy Id (PHYS ID 1 %#04x)= %#04x\n", MDIO_DEVID1,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID1));
-	dev_alert(dev, "Phy Id (PHYS ID 2 %#04x)= %#04x\n", MDIO_DEVID2,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID2));
-	dev_alert(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS1,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS1));
-	dev_alert(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS2,
-		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS2));
-
-	dev_alert(dev, "Auto-Neg Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1));
-	dev_alert(dev, "Auto-Neg Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_STAT1));
-	dev_alert(dev, "Auto-Neg Ad Reg 1 (%#04x) = %#04x\n",
-		  MDIO_AN_ADVERTISE,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE));
-	dev_alert(dev, "Auto-Neg Ad Reg 2 (%#04x) = %#04x\n",
-		  MDIO_AN_ADVERTISE + 1,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1));
-	dev_alert(dev, "Auto-Neg Ad Reg 3 (%#04x) = %#04x\n",
-		  MDIO_AN_ADVERTISE + 2,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2));
-	dev_alert(dev, "Auto-Neg Completion Reg (%#04x) = %#04x\n",
-		  MDIO_AN_COMP_STAT,
-		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_COMP_STAT));
-
-	dev_alert(dev, "MMD Device Mask = %#x\n",
-		  phydev->c45_ids.devices_in_package);
-	for (i = 0; i < ARRAY_SIZE(phydev->c45_ids.device_ids); i++)
-		dev_alert(dev, "  MMD %d: ID = %#08x\n", i,
-			  phydev->c45_ids.device_ids[i]);
-
-	dev_alert(dev, "\n*************************************************\n");
-}
-
-int xgbe_mdio_register(struct xgbe_prv_data *pdata)
-{
-	struct mii_bus *mii;
-	struct phy_device *phydev;
-	int ret = 0;
-
-	DBGPR("-->xgbe_mdio_register\n");
-
-	mii = mdiobus_alloc();
-	if (!mii) {
-		dev_err(pdata->dev, "mdiobus_alloc failed\n");
-		return -ENOMEM;
+	/* Assert Rx and Tx ratechange */
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 1);
+}
+
+static void xgbe_serdes_complete_ratechange(struct xgbe_prv_data *pdata)
+{
+	unsigned int wait;
+	u16 status;
+
+	/* Release Rx and Tx ratechange */
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, RATECHANGE, 0);
+
+	/* Wait for Rx and Tx ready */
+	wait = XGBE_RATECHANGE_COUNT;
+	while (wait--) {
+		usleep_range(50, 75);
+
+		status = XSIR0_IOREAD(pdata, SIR0_STATUS);
+		if (XSIR_GET_BITS(status, SIR0_STATUS, RX_READY) &&
+		    XSIR_GET_BITS(status, SIR0_STATUS, TX_READY))
+			goto rx_reset;
 	}
 
-	/* Register on the MDIO bus (don't probe any PHYs) */
-	mii->name = XGBE_PHY_NAME;
-	mii->read = xgbe_mdio_read;
-	mii->write = xgbe_mdio_write;
-	snprintf(mii->id, sizeof(mii->id), "%s", pdata->mii_bus_id);
-	mii->priv = pdata;
-	mii->phy_mask = ~0;
-	mii->parent = pdata->dev;
-	ret = mdiobus_register(mii);
-	if (ret) {
-		dev_err(pdata->dev, "mdiobus_register failed\n");
-		goto err_mdiobus_alloc;
+	netif_dbg(pdata, link, pdata->netdev, "SerDes rx/tx not ready (%#hx)\n",
+		  status);
+
+rx_reset:
+	/* Perform Rx reset for the DFE changes */
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 0);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG6, RESETB_RXD, 1);
+}
+
+static void xgbe_xgmii_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg;
+
+	/* Enable KR training */
+	xgbe_an_enable_kr_training(pdata);
+
+	/* Set MAC to 10G speed */
+	pdata->hw_if.set_xgmii_speed(pdata);
+
+	/* Set PCS to KR/10G speed */
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+	reg &= ~MDIO_PCS_CTRL2_TYPE;
+	reg |= MDIO_PCS_CTRL2_10GBR;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	reg &= ~MDIO_CTRL1_SPEEDSEL;
+	reg |= MDIO_CTRL1_SPEED10G;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+	xgbe_pcs_power_cycle(pdata);
+
+	/* Set SerDes to 10G speed */
+	xgbe_serdes_start_ratechange(pdata);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_10000_RATE);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_10000_WORD);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_10000_PLL);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+			   pdata->serdes_cdr_rate[XGBE_SPEED_10000]);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+			   pdata->serdes_tx_amp[XGBE_SPEED_10000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+			   pdata->serdes_blwc[XGBE_SPEED_10000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+			   pdata->serdes_pq_skew[XGBE_SPEED_10000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+			   pdata->serdes_dfe_tap_cfg[XGBE_SPEED_10000]);
+	XRXTX_IOWRITE(pdata, RXTX_REG22,
+		      pdata->serdes_dfe_tap_ena[XGBE_SPEED_10000]);
+
+	xgbe_serdes_complete_ratechange(pdata);
+
+	netif_dbg(pdata, link, pdata->netdev, "10GbE KR mode set\n");
+}
+
+static void xgbe_gmii_2500_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg;
+
+	/* Disable KR training */
+	xgbe_an_disable_kr_training(pdata);
+
+	/* Set MAC to 2.5G speed */
+	pdata->hw_if.set_gmii_2500_speed(pdata);
+
+	/* Set PCS to KX/1G speed */
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+	reg &= ~MDIO_PCS_CTRL2_TYPE;
+	reg |= MDIO_PCS_CTRL2_10GBX;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	reg &= ~MDIO_CTRL1_SPEEDSEL;
+	reg |= MDIO_CTRL1_SPEED1G;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+	xgbe_pcs_power_cycle(pdata);
+
+	/* Set SerDes to 2.5G speed */
+	xgbe_serdes_start_ratechange(pdata);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_2500_RATE);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_2500_WORD);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_2500_PLL);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+			   pdata->serdes_cdr_rate[XGBE_SPEED_2500]);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+			   pdata->serdes_tx_amp[XGBE_SPEED_2500]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+			   pdata->serdes_blwc[XGBE_SPEED_2500]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+			   pdata->serdes_pq_skew[XGBE_SPEED_2500]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+			   pdata->serdes_dfe_tap_cfg[XGBE_SPEED_2500]);
+	XRXTX_IOWRITE(pdata, RXTX_REG22,
+		      pdata->serdes_dfe_tap_ena[XGBE_SPEED_2500]);
+
+	xgbe_serdes_complete_ratechange(pdata);
+
+	netif_dbg(pdata, link, pdata->netdev, "2.5GbE KX mode set\n");
+}
+
+static void xgbe_gmii_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg;
+
+	/* Disable KR training */
+	xgbe_an_disable_kr_training(pdata);
+
+	/* Set MAC to 1G speed */
+	pdata->hw_if.set_gmii_speed(pdata);
+
+	/* Set PCS to KX/1G speed */
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+	reg &= ~MDIO_PCS_CTRL2_TYPE;
+	reg |= MDIO_PCS_CTRL2_10GBX;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL2, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	reg &= ~MDIO_CTRL1_SPEEDSEL;
+	reg |= MDIO_CTRL1_SPEED1G;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+	xgbe_pcs_power_cycle(pdata);
+
+	/* Set SerDes to 1G speed */
+	xgbe_serdes_start_ratechange(pdata);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, DATARATE, XGBE_SPEED_1000_RATE);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, WORDMODE, XGBE_SPEED_1000_WORD);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, PLLSEL, XGBE_SPEED_1000_PLL);
+
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, CDR_RATE,
+			   pdata->serdes_cdr_rate[XGBE_SPEED_1000]);
+	XSIR1_IOWRITE_BITS(pdata, SIR1_SPEED, TXAMP,
+			   pdata->serdes_tx_amp[XGBE_SPEED_1000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG20, BLWC_ENA,
+			   pdata->serdes_blwc[XGBE_SPEED_1000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG114, PQ_REG,
+			   pdata->serdes_pq_skew[XGBE_SPEED_1000]);
+	XRXTX_IOWRITE_BITS(pdata, RXTX_REG129, RXDFE_CONFIG,
+			   pdata->serdes_dfe_tap_cfg[XGBE_SPEED_1000]);
+	XRXTX_IOWRITE(pdata, RXTX_REG22,
+		      pdata->serdes_dfe_tap_ena[XGBE_SPEED_1000]);
+
+	xgbe_serdes_complete_ratechange(pdata);
+
+	netif_dbg(pdata, link, pdata->netdev, "1GbE KX mode set\n");
+}
+
+static void xgbe_cur_mode(struct xgbe_prv_data *pdata,
+			  enum xgbe_mode *mode)
+{
+	unsigned int reg;
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL2);
+	if ((reg & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR)
+		*mode = XGBE_MODE_KR;
+	else
+		*mode = XGBE_MODE_KX;
+}
+
+static bool xgbe_in_kr_mode(struct xgbe_prv_data *pdata)
+{
+	enum xgbe_mode mode;
+
+	xgbe_cur_mode(pdata, &mode);
+
+	return (mode == XGBE_MODE_KR);
+}
+
+static void xgbe_switch_mode(struct xgbe_prv_data *pdata)
+{
+	/* If we are in KR switch to KX, and vice-versa */
+	if (xgbe_in_kr_mode(pdata)) {
+		if (pdata->speed_set == XGBE_SPEEDSET_1000_10000)
+			xgbe_gmii_mode(pdata);
+		else
+			xgbe_gmii_2500_mode(pdata);
+	} else {
+		xgbe_xgmii_mode(pdata);
 	}
-	DBGPR("  mdiobus_register succeeded for %s\n", pdata->mii_bus_id);
-
-	/* Probe the PCS using Clause 45 */
-	phydev = get_phy_device(mii, XGBE_PRTAD, true);
-	if (IS_ERR(phydev) || !phydev ||
-	    !phydev->c45_ids.device_ids[MDIO_MMD_PCS]) {
-		dev_err(pdata->dev, "get_phy_device failed\n");
-		ret = phydev ? PTR_ERR(phydev) : -ENOLINK;
-		goto err_mdiobus_register;
+}
+
+static void xgbe_set_mode(struct xgbe_prv_data *pdata,
+			  enum xgbe_mode mode)
+{
+	enum xgbe_mode cur_mode;
+
+	xgbe_cur_mode(pdata, &cur_mode);
+	if (mode != cur_mode)
+		xgbe_switch_mode(pdata);
+}
+
+static bool xgbe_use_xgmii_mode(struct xgbe_prv_data *pdata)
+{
+	if (pdata->phy.autoneg == AUTONEG_ENABLE) {
+		if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full)
+			return true;
+	} else {
+		if (pdata->phy.speed == SPEED_10000)
+			return true;
 	}
-	request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT,
-		       MDIO_ID_ARGS(phydev->c45_ids.device_ids[MDIO_MMD_PCS]));
 
-	ret = phy_device_register(phydev);
-	if (ret) {
-		dev_err(pdata->dev, "phy_device_register failed\n");
-		goto err_phy_device;
+	return false;
+}
+
+static bool xgbe_use_gmii_2500_mode(struct xgbe_prv_data *pdata)
+{
+	if (pdata->phy.autoneg == AUTONEG_ENABLE) {
+		if (pdata->phy.advertising & ADVERTISED_2500baseX_Full)
+			return true;
+	} else {
+		if (pdata->phy.speed == SPEED_2500)
+			return true;
 	}
-	if (!phydev->dev.driver) {
-		dev_err(pdata->dev, "phy driver probe failed\n");
-		ret = -EIO;
-		goto err_phy_device;
+
+	return false;
+}
+
+static bool xgbe_use_gmii_mode(struct xgbe_prv_data *pdata)
+{
+	if (pdata->phy.autoneg == AUTONEG_ENABLE) {
+		if (pdata->phy.advertising & ADVERTISED_1000baseKX_Full)
+			return true;
+	} else {
+		if (pdata->phy.speed == SPEED_1000)
+			return true;
 	}
 
-	/* Add a reference to the PHY driver so it can't be unloaded */
-	pdata->phy_module = phydev->dev.driver->owner;
-	if (!try_module_get(pdata->phy_module)) {
-		dev_err(pdata->dev, "try_module_get failed\n");
-		ret = -EIO;
-		goto err_phy_device;
+	return false;
+}
+
+static void xgbe_set_an(struct xgbe_prv_data *pdata, bool enable, bool restart)
+{
+	unsigned int reg;
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1);
+	reg &= ~MDIO_AN_CTRL1_ENABLE;
+
+	if (enable)
+		reg |= MDIO_AN_CTRL1_ENABLE;
+
+	if (restart)
+		reg |= MDIO_AN_CTRL1_RESTART;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
+}
+
+static void xgbe_restart_an(struct xgbe_prv_data *pdata)
+{
+	xgbe_set_an(pdata, true, true);
+
+	netif_dbg(pdata, link, pdata->netdev, "AN enabled/restarted\n");
+}
+
+static void xgbe_disable_an(struct xgbe_prv_data *pdata)
+{
+	xgbe_set_an(pdata, false, false);
+
+	netif_dbg(pdata, link, pdata->netdev, "AN disabled\n");
+}
+
+static enum xgbe_an xgbe_an_tx_training(struct xgbe_prv_data *pdata,
+					enum xgbe_rx *state)
+{
+	unsigned int ad_reg, lp_reg, reg;
+
+	*state = XGBE_RX_COMPLETE;
+
+	/* If we're not in KR mode then we're done */
+	if (!xgbe_in_kr_mode(pdata))
+		return XGBE_AN_PAGE_RECEIVED;
+
+	/* Enable/Disable FEC */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FECCTRL);
+	reg &= ~(MDIO_PMA_10GBR_FECABLE_ABLE | MDIO_PMA_10GBR_FECABLE_ERRABLE);
+	if ((ad_reg & 0xc000) && (lp_reg & 0xc000))
+		reg |= pdata->fec_ability;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FECCTRL, reg);
+
+	/* Start KR training */
+	reg = XMDIO_READ(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
+	if (reg & XGBE_KR_TRAINING_ENABLE) {
+		XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 1);
+
+		reg |= XGBE_KR_TRAINING_START;
+		XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
+			    reg);
+
+		XSIR0_IOWRITE_BITS(pdata, SIR0_KR_RT_1, RESET, 0);
+
+		netif_dbg(pdata, link, pdata->netdev,
+			  "KR training initiated\n");
 	}
 
-	pdata->mii = mii;
-	pdata->mdio_mmd = MDIO_MMD_PCS;
+	return XGBE_AN_PAGE_RECEIVED;
+}
+
+static enum xgbe_an xgbe_an_tx_xnp(struct xgbe_prv_data *pdata,
+				   enum xgbe_rx *state)
+{
+	u16 msg;
+
+	*state = XGBE_RX_XNP;
+
+	msg = XGBE_XNP_MCF_NULL_MESSAGE;
+	msg |= XGBE_XNP_MP_FORMATTED;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_XNP + 2, 0);
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_XNP + 1, 0);
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_XNP, msg);
+
+	return XGBE_AN_PAGE_RECEIVED;
+}
+
+static enum xgbe_an xgbe_an_rx_bpa(struct xgbe_prv_data *pdata,
+				   enum xgbe_rx *state)
+{
+	unsigned int link_support;
+	unsigned int reg, ad_reg, lp_reg;
+
+	/* Read Base Ability register 2 first */
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+
+	/* Check for a supported mode, otherwise restart in a different one */
+	link_support = xgbe_in_kr_mode(pdata) ? 0x80 : 0x20;
+	if (!(reg & link_support))
+		return XGBE_AN_INCOMPAT_LINK;
+
+	/* Check Extended Next Page support */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA);
+
+	return ((ad_reg & XGBE_XNP_NP_EXCHANGE) ||
+		(lp_reg & XGBE_XNP_NP_EXCHANGE))
+	       ? xgbe_an_tx_xnp(pdata, state)
+	       : xgbe_an_tx_training(pdata, state);
+}
+
+static enum xgbe_an xgbe_an_rx_xnp(struct xgbe_prv_data *pdata,
+				   enum xgbe_rx *state)
+{
+	unsigned int ad_reg, lp_reg;
+
+	/* Check Extended Next Page support */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_XNP);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPX);
+
+	return ((ad_reg & XGBE_XNP_NP_EXCHANGE) ||
+		(lp_reg & XGBE_XNP_NP_EXCHANGE))
+	       ? xgbe_an_tx_xnp(pdata, state)
+	       : xgbe_an_tx_training(pdata, state);
+}
+
+static enum xgbe_an xgbe_an_page_received(struct xgbe_prv_data *pdata)
+{
+	enum xgbe_rx *state;
+	unsigned long an_timeout;
+	enum xgbe_an ret;
+
+	if (!pdata->an_start) {
+		pdata->an_start = jiffies;
+	} else {
+		an_timeout = pdata->an_start +
+			     msecs_to_jiffies(XGBE_AN_MS_TIMEOUT);
+		if (time_after(jiffies, an_timeout)) {
+			/* Auto-negotiation timed out, reset state */
+			pdata->kr_state = XGBE_RX_BPA;
+			pdata->kx_state = XGBE_RX_BPA;
+
+			pdata->an_start = jiffies;
+
+			netif_dbg(pdata, link, pdata->netdev,
+				  "AN timed out, resetting state\n");
+		}
+	}
 
-	phydev->autoneg = pdata->default_autoneg;
-	if (phydev->autoneg == AUTONEG_DISABLE) {
-		phydev->speed = pdata->default_speed;
-		phydev->duplex = DUPLEX_FULL;
+	state = xgbe_in_kr_mode(pdata) ? &pdata->kr_state
+					   : &pdata->kx_state;
 
-		phydev->advertising &= ~ADVERTISED_Autoneg;
+	switch (*state) {
+	case XGBE_RX_BPA:
+		ret = xgbe_an_rx_bpa(pdata, state);
+		break;
+
+	case XGBE_RX_XNP:
+		ret = xgbe_an_rx_xnp(pdata, state);
+		break;
+
+	default:
+		ret = XGBE_AN_ERROR;
+	}
+
+	return ret;
+}
+
+static enum xgbe_an xgbe_an_incompat_link(struct xgbe_prv_data *pdata)
+{
+	/* Be sure we aren't looping trying to negotiate */
+	if (xgbe_in_kr_mode(pdata)) {
+		pdata->kr_state = XGBE_RX_ERROR;
+
+		if (!(pdata->phy.advertising & ADVERTISED_1000baseKX_Full) &&
+		    !(pdata->phy.advertising & ADVERTISED_2500baseX_Full))
+			return XGBE_AN_NO_LINK;
+
+		if (pdata->kx_state != XGBE_RX_BPA)
+			return XGBE_AN_NO_LINK;
+	} else {
+		pdata->kx_state = XGBE_RX_ERROR;
+
+		if (!(pdata->phy.advertising & ADVERTISED_10000baseKR_Full))
+			return XGBE_AN_NO_LINK;
+
+		if (pdata->kr_state != XGBE_RX_BPA)
+			return XGBE_AN_NO_LINK;
+	}
+
+	xgbe_disable_an(pdata);
+
+	xgbe_switch_mode(pdata);
+
+	xgbe_restart_an(pdata);
+
+	return XGBE_AN_INCOMPAT_LINK;
+}
+
+static irqreturn_t xgbe_an_isr(int irq, void *data)
+{
+	struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
+
+	netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n");
+
+	/* Interrupt reason must be read and cleared outside of IRQ context */
+	disable_irq_nosync(pdata->an_irq);
+
+	queue_work(pdata->an_workqueue, &pdata->an_irq_work);
+
+	return IRQ_HANDLED;
+}
+
+static void xgbe_an_irq_work(struct work_struct *work)
+{
+	struct xgbe_prv_data *pdata = container_of(work,
+						   struct xgbe_prv_data,
+						   an_irq_work);
+
+	/* Avoid a race between enabling the IRQ and exiting the work by
+	 * waiting for the work to finish and then queueing it
+	 */
+	flush_work(&pdata->an_work);
+	queue_work(pdata->an_workqueue, &pdata->an_work);
+}
+
+static const char *xgbe_state_as_string(enum xgbe_an state)
+{
+	switch (state) {
+	case XGBE_AN_READY:
+		return "Ready";
+	case XGBE_AN_PAGE_RECEIVED:
+		return "Page-Received";
+	case XGBE_AN_INCOMPAT_LINK:
+		return "Incompatible-Link";
+	case XGBE_AN_COMPLETE:
+		return "Complete";
+	case XGBE_AN_NO_LINK:
+		return "No-Link";
+	case XGBE_AN_ERROR:
+		return "Error";
+	default:
+		return "Undefined";
+	}
+}
+
+static void xgbe_an_state_machine(struct work_struct *work)
+{
+	struct xgbe_prv_data *pdata = container_of(work,
+						   struct xgbe_prv_data,
+						   an_work);
+	enum xgbe_an cur_state = pdata->an_state;
+	unsigned int int_reg, int_mask;
+
+	mutex_lock(&pdata->an_mutex);
+
+	/* Read the interrupt */
+	int_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_INT);
+	if (!int_reg)
+		goto out;
+
+next_int:
+	if (int_reg & XGBE_AN_PG_RCV) {
+		pdata->an_state = XGBE_AN_PAGE_RECEIVED;
+		int_mask = XGBE_AN_PG_RCV;
+	} else if (int_reg & XGBE_AN_INC_LINK) {
+		pdata->an_state = XGBE_AN_INCOMPAT_LINK;
+		int_mask = XGBE_AN_INC_LINK;
+	} else if (int_reg & XGBE_AN_INT_CMPLT) {
+		pdata->an_state = XGBE_AN_COMPLETE;
+		int_mask = XGBE_AN_INT_CMPLT;
+	} else {
+		pdata->an_state = XGBE_AN_ERROR;
+		int_mask = 0;
 	}
 
-	pdata->phydev = phydev;
+	/* Clear the interrupt to be processed */
+	int_reg &= ~int_mask;
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, int_reg);
+
+	pdata->an_result = pdata->an_state;
+
+again:
+	netif_dbg(pdata, link, pdata->netdev, "AN %s\n",
+		  xgbe_state_as_string(pdata->an_state));
+
+	cur_state = pdata->an_state;
+
+	switch (pdata->an_state) {
+	case XGBE_AN_READY:
+		pdata->an_supported = 0;
+		break;
+
+	case XGBE_AN_PAGE_RECEIVED:
+		pdata->an_state = xgbe_an_page_received(pdata);
+		pdata->an_supported++;
+		break;
+
+	case XGBE_AN_INCOMPAT_LINK:
+		pdata->an_supported = 0;
+		pdata->parallel_detect = 0;
+		pdata->an_state = xgbe_an_incompat_link(pdata);
+		break;
 
-	DBGPHY_REGS(pdata);
+	case XGBE_AN_COMPLETE:
+		pdata->parallel_detect = pdata->an_supported ? 0 : 1;
+		netif_dbg(pdata, link, pdata->netdev, "%s successful\n",
+			  pdata->an_supported ? "Auto negotiation"
+					      : "Parallel detection");
+		break;
 
-	DBGPR("<--xgbe_mdio_register\n");
+	case XGBE_AN_NO_LINK:
+		break;
+
+	default:
+		pdata->an_state = XGBE_AN_ERROR;
+	}
+
+	if (pdata->an_state == XGBE_AN_NO_LINK) {
+		int_reg = 0;
+		XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+	} else if (pdata->an_state == XGBE_AN_ERROR) {
+		netdev_err(pdata->netdev,
+			   "error during auto-negotiation, state=%u\n",
+			   cur_state);
+
+		int_reg = 0;
+		XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+	}
+
+	if (pdata->an_state >= XGBE_AN_COMPLETE) {
+		pdata->an_result = pdata->an_state;
+		pdata->an_state = XGBE_AN_READY;
+		pdata->kr_state = XGBE_RX_BPA;
+		pdata->kx_state = XGBE_RX_BPA;
+		pdata->an_start = 0;
+
+		netif_dbg(pdata, link, pdata->netdev, "AN result: %s\n",
+			  xgbe_state_as_string(pdata->an_result));
+	}
+
+	if (cur_state != pdata->an_state)
+		goto again;
+
+	if (int_reg)
+		goto next_int;
+
+out:
+	enable_irq(pdata->an_irq);
+
+	mutex_unlock(&pdata->an_mutex);
+}
+
+static void xgbe_an_init(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg;
+
+	/* Set up Advertisement register 3 first */
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+	if (pdata->phy.advertising & ADVERTISED_10000baseR_FEC)
+		reg |= 0xc000;
+	else
+		reg &= ~0xc000;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2, reg);
+
+	/* Set up Advertisement register 2 next */
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+	if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full)
+		reg |= 0x80;
+	else
+		reg &= ~0x80;
+
+	if ((pdata->phy.advertising & ADVERTISED_1000baseKX_Full) ||
+	    (pdata->phy.advertising & ADVERTISED_2500baseX_Full))
+		reg |= 0x20;
+	else
+		reg &= ~0x20;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1, reg);
+
+	/* Set up Advertisement register 1 last */
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	if (pdata->phy.advertising & ADVERTISED_Pause)
+		reg |= 0x400;
+	else
+		reg &= ~0x400;
+
+	if (pdata->phy.advertising & ADVERTISED_Asym_Pause)
+		reg |= 0x800;
+	else
+		reg &= ~0x800;
+
+	/* We don't intend to perform XNP */
+	reg &= ~XGBE_XNP_NP_EXCHANGE;
+
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE, reg);
+
+	netif_dbg(pdata, link, pdata->netdev, "AN initialized\n");
+}
+
+static const char *xgbe_phy_fc_string(struct xgbe_prv_data *pdata)
+{
+	if (pdata->tx_pause && pdata->rx_pause)
+		return "rx/tx";
+	else if (pdata->rx_pause)
+		return "rx";
+	else if (pdata->tx_pause)
+		return "tx";
+	else
+		return "off";
+}
+
+static const char *xgbe_phy_speed_string(int speed)
+{
+	switch (speed) {
+	case SPEED_1000:
+		return "1Gbps";
+	case SPEED_2500:
+		return "2.5Gbps";
+	case SPEED_10000:
+		return "10Gbps";
+	case SPEED_UNKNOWN:
+		return "Unknown";
+	default:
+		return "Unsupported";
+	}
+}
+
+static void xgbe_phy_print_status(struct xgbe_prv_data *pdata)
+{
+	if (pdata->phy.link)
+		netdev_info(pdata->netdev,
+			    "Link is Up - %s/%s - flow control %s\n",
+			    xgbe_phy_speed_string(pdata->phy.speed),
+			    pdata->phy.duplex == DUPLEX_FULL ? "Full" : "Half",
+			    xgbe_phy_fc_string(pdata));
+	else
+		netdev_info(pdata->netdev, "Link is Down\n");
+}
+
+static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata)
+{
+	int new_state = 0;
+
+	if (pdata->phy.link) {
+		/* Flow control support */
+		pdata->pause_autoneg = pdata->phy.pause_autoneg;
+
+		if (pdata->tx_pause != pdata->phy.tx_pause) {
+			new_state = 1;
+			pdata->hw_if.config_tx_flow_control(pdata);
+			pdata->tx_pause = pdata->phy.tx_pause;
+		}
+
+		if (pdata->rx_pause != pdata->phy.rx_pause) {
+			new_state = 1;
+			pdata->hw_if.config_rx_flow_control(pdata);
+			pdata->rx_pause = pdata->phy.rx_pause;
+		}
+
+		/* Speed support */
+		if (pdata->phy_speed != pdata->phy.speed) {
+			new_state = 1;
+			pdata->phy_speed = pdata->phy.speed;
+		}
+
+		if (pdata->phy_link != pdata->phy.link) {
+			new_state = 1;
+			pdata->phy_link = pdata->phy.link;
+		}
+	} else if (pdata->phy_link) {
+		new_state = 1;
+		pdata->phy_link = 0;
+		pdata->phy_speed = SPEED_UNKNOWN;
+	}
+
+	if (new_state && netif_msg_link(pdata))
+		xgbe_phy_print_status(pdata);
+}
+
+static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata)
+{
+	netif_dbg(pdata, link, pdata->netdev, "fixed PHY configuration\n");
+
+	/* Disable auto-negotiation */
+	xgbe_disable_an(pdata);
+
+	/* Validate/Set specified speed */
+	switch (pdata->phy.speed) {
+	case SPEED_10000:
+		xgbe_set_mode(pdata, XGBE_MODE_KR);
+		break;
+
+	case SPEED_2500:
+	case SPEED_1000:
+		xgbe_set_mode(pdata, XGBE_MODE_KX);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Validate duplex mode */
+	if (pdata->phy.duplex != DUPLEX_FULL)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __xgbe_phy_config_aneg(struct xgbe_prv_data *pdata)
+{
+	set_bit(XGBE_LINK_INIT, &pdata->dev_state);
+	pdata->link_check = jiffies;
+
+	if (pdata->phy.autoneg != AUTONEG_ENABLE)
+		return xgbe_phy_config_fixed(pdata);
+
+	netif_dbg(pdata, link, pdata->netdev, "AN PHY configuration\n");
+
+	/* Disable auto-negotiation interrupt */
+	disable_irq(pdata->an_irq);
+
+	/* Start auto-negotiation in a supported mode */
+	if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full) {
+		xgbe_set_mode(pdata, XGBE_MODE_KR);
+	} else if ((pdata->phy.advertising & ADVERTISED_1000baseKX_Full) ||
+		   (pdata->phy.advertising & ADVERTISED_2500baseX_Full)) {
+		xgbe_set_mode(pdata, XGBE_MODE_KX);
+	} else {
+		enable_irq(pdata->an_irq);
+		return -EINVAL;
+	}
+
+	/* Disable and stop any in progress auto-negotiation */
+	xgbe_disable_an(pdata);
+
+	/* Clear any auto-negotitation interrupts */
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	pdata->an_result = XGBE_AN_READY;
+	pdata->an_state = XGBE_AN_READY;
+	pdata->kr_state = XGBE_RX_BPA;
+	pdata->kx_state = XGBE_RX_BPA;
+
+	/* Re-enable auto-negotiation interrupt */
+	enable_irq(pdata->an_irq);
+
+	/* Set up advertisement registers based on current settings */
+	xgbe_an_init(pdata);
+
+	/* Enable and start auto-negotiation */
+	xgbe_restart_an(pdata);
 
 	return 0;
+}
+
+static int xgbe_phy_config_aneg(struct xgbe_prv_data *pdata)
+{
+	int ret;
+
+	mutex_lock(&pdata->an_mutex);
+
+	ret = __xgbe_phy_config_aneg(pdata);
+	if (ret)
+		set_bit(XGBE_LINK_ERR, &pdata->dev_state);
+	else
+		clear_bit(XGBE_LINK_ERR, &pdata->dev_state);
+
+	mutex_unlock(&pdata->an_mutex);
+
+	return ret;
+}
+
+static bool xgbe_phy_aneg_done(struct xgbe_prv_data *pdata)
+{
+	return (pdata->an_result == XGBE_AN_COMPLETE);
+}
+
+static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata)
+{
+	unsigned long link_timeout;
+
+	link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ);
+	if (time_after(jiffies, link_timeout)) {
+		netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n");
+		xgbe_phy_config_aneg(pdata);
+	}
+}
+
+static void xgbe_phy_status_force(struct xgbe_prv_data *pdata)
+{
+	if (xgbe_in_kr_mode(pdata)) {
+		pdata->phy.speed = SPEED_10000;
+	} else {
+		switch (pdata->speed_set) {
+		case XGBE_SPEEDSET_1000_10000:
+			pdata->phy.speed = SPEED_1000;
+			break;
+
+		case XGBE_SPEEDSET_2500_10000:
+			pdata->phy.speed = SPEED_2500;
+			break;
+		}
+	}
+	pdata->phy.duplex = DUPLEX_FULL;
+}
+
+static void xgbe_phy_status_aneg(struct xgbe_prv_data *pdata)
+{
+	unsigned int ad_reg, lp_reg;
+
+	pdata->phy.lp_advertising = 0;
+
+	if ((pdata->phy.autoneg != AUTONEG_ENABLE) || pdata->parallel_detect)
+		return xgbe_phy_status_force(pdata);
+
+	pdata->phy.lp_advertising |= ADVERTISED_Autoneg;
+	pdata->phy.lp_advertising |= ADVERTISED_Backplane;
+
+	/* Compare Advertisement and Link Partner register 1 */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA);
+	if (lp_reg & 0x400)
+		pdata->phy.lp_advertising |= ADVERTISED_Pause;
+	if (lp_reg & 0x800)
+		pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause;
+
+	if (pdata->phy.pause_autoneg) {
+		/* Set flow control based on auto-negotiation result */
+		pdata->phy.tx_pause = 0;
+		pdata->phy.rx_pause = 0;
+
+		if (ad_reg & lp_reg & 0x400) {
+			pdata->phy.tx_pause = 1;
+			pdata->phy.rx_pause = 1;
+		} else if (ad_reg & lp_reg & 0x800) {
+			if (ad_reg & 0x400)
+				pdata->phy.rx_pause = 1;
+			else if (lp_reg & 0x400)
+				pdata->phy.tx_pause = 1;
+		}
+	}
+
+	/* Compare Advertisement and Link Partner register 2 */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+	if (lp_reg & 0x80)
+		pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full;
+	if (lp_reg & 0x20) {
+		switch (pdata->speed_set) {
+		case XGBE_SPEEDSET_1000_10000:
+			pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full;
+			break;
+		case XGBE_SPEEDSET_2500_10000:
+			pdata->phy.lp_advertising |= ADVERTISED_2500baseX_Full;
+			break;
+		}
+	}
+
+	ad_reg &= lp_reg;
+	if (ad_reg & 0x80) {
+		pdata->phy.speed = SPEED_10000;
+		xgbe_set_mode(pdata, XGBE_MODE_KR);
+	} else if (ad_reg & 0x20) {
+		switch (pdata->speed_set) {
+		case XGBE_SPEEDSET_1000_10000:
+			pdata->phy.speed = SPEED_1000;
+			break;
+
+		case XGBE_SPEEDSET_2500_10000:
+			pdata->phy.speed = SPEED_2500;
+			break;
+		}
+
+		xgbe_set_mode(pdata, XGBE_MODE_KX);
+	} else {
+		pdata->phy.speed = SPEED_UNKNOWN;
+	}
+
+	/* Compare Advertisement and Link Partner register 3 */
+	ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+	lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+	if (lp_reg & 0xc000)
+		pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC;
+
+	pdata->phy.duplex = DUPLEX_FULL;
+}
+
+static void xgbe_phy_status(struct xgbe_prv_data *pdata)
+{
+	unsigned int reg, link_aneg;
+
+	if (test_bit(XGBE_LINK_ERR, &pdata->dev_state)) {
+		if (test_and_clear_bit(XGBE_LINK, &pdata->dev_state))
+			netif_carrier_off(pdata->netdev);
+
+		pdata->phy.link = 0;
+		goto adjust_link;
+	}
+
+	link_aneg = (pdata->phy.autoneg == AUTONEG_ENABLE);
+
+	/* Get the link status. Link status is latched low, so read
+	 * once to clear and then read again to get current state
+	 */
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	pdata->phy.link = (reg & MDIO_STAT1_LSTATUS) ? 1 : 0;
+
+	if (pdata->phy.link) {
+		if (link_aneg && !xgbe_phy_aneg_done(pdata)) {
+			xgbe_check_link_timeout(pdata);
+			return;
+		}
+
+		xgbe_phy_status_aneg(pdata);
+
+		if (test_bit(XGBE_LINK_INIT, &pdata->dev_state))
+			clear_bit(XGBE_LINK_INIT, &pdata->dev_state);
+
+		if (!test_bit(XGBE_LINK, &pdata->dev_state)) {
+			set_bit(XGBE_LINK, &pdata->dev_state);
+			netif_carrier_on(pdata->netdev);
+		}
+	} else {
+		if (test_bit(XGBE_LINK_INIT, &pdata->dev_state)) {
+			xgbe_check_link_timeout(pdata);
+
+			if (link_aneg)
+				return;
+		}
+
+		xgbe_phy_status_aneg(pdata);
+
+		if (test_bit(XGBE_LINK, &pdata->dev_state)) {
+			clear_bit(XGBE_LINK, &pdata->dev_state);
+			netif_carrier_off(pdata->netdev);
+		}
+	}
+
+adjust_link:
+	xgbe_phy_adjust_link(pdata);
+}
+
+static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
+{
+	netif_dbg(pdata, link, pdata->netdev, "stopping PHY\n");
+
+	/* Disable auto-negotiation */
+	xgbe_disable_an(pdata);
+
+	/* Disable auto-negotiation interrupts */
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+
+	devm_free_irq(pdata->dev, pdata->an_irq, pdata);
 
-err_phy_device:
-	phy_device_free(phydev);
+	pdata->phy.link = 0;
+	if (test_and_clear_bit(XGBE_LINK, &pdata->dev_state))
+		netif_carrier_off(pdata->netdev);
 
-err_mdiobus_register:
-	mdiobus_unregister(mii);
+	xgbe_phy_adjust_link(pdata);
+}
+
+static int xgbe_phy_start(struct xgbe_prv_data *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	int ret;
+
+	netif_dbg(pdata, link, pdata->netdev, "starting PHY\n");
+
+	ret = devm_request_irq(pdata->dev, pdata->an_irq,
+			       xgbe_an_isr, 0, pdata->an_name,
+			       pdata);
+	if (ret) {
+		netdev_err(netdev, "phy irq request failed\n");
+		return ret;
+	}
+
+	/* Set initial mode - call the mode setting routines
+	 * directly to insure we are properly configured
+	 */
+	if (xgbe_use_xgmii_mode(pdata)) {
+		xgbe_xgmii_mode(pdata);
+	} else if (xgbe_use_gmii_mode(pdata)) {
+		xgbe_gmii_mode(pdata);
+	} else if (xgbe_use_gmii_2500_mode(pdata)) {
+		xgbe_gmii_2500_mode(pdata);
+	} else {
+		ret = -EINVAL;
+		goto err_irq;
+	}
+
+	/* Set up advertisement registers based on current settings */
+	xgbe_an_init(pdata);
+
+	/* Enable auto-negotiation interrupts */
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INTMASK, 0x07);
 
-err_mdiobus_alloc:
-	mdiobus_free(mii);
+	return xgbe_phy_config_aneg(pdata);
+
+err_irq:
+	devm_free_irq(pdata->dev, pdata->an_irq, pdata);
 
 	return ret;
 }
 
-void xgbe_mdio_unregister(struct xgbe_prv_data *pdata)
+static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
+{
+	unsigned int count, reg;
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	reg |= MDIO_CTRL1_RESET;
+	XMDIO_WRITE(pdata, MDIO_MMD_PCS, MDIO_CTRL1, reg);
+
+	count = 50;
+	do {
+		msleep(20);
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1);
+	} while ((reg & MDIO_CTRL1_RESET) && --count);
+
+	if (reg & MDIO_CTRL1_RESET)
+		return -ETIMEDOUT;
+
+	/* Disable auto-negotiation for now */
+	xgbe_disable_an(pdata);
+
+	/* Clear auto-negotiation interrupts */
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	return 0;
+}
+
+static void xgbe_dump_phy_registers(struct xgbe_prv_data *pdata)
 {
-	DBGPR("-->xgbe_mdio_unregister\n");
+	struct device *dev = pdata->dev;
+
+	dev_dbg(dev, "\n************* PHY Reg dump **********************\n");
+
+	dev_dbg(dev, "PCS Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1));
+	dev_dbg(dev, "PCS Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1));
+	dev_dbg(dev, "Phy Id (PHYS ID 1 %#04x)= %#04x\n", MDIO_DEVID1,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID1));
+	dev_dbg(dev, "Phy Id (PHYS ID 2 %#04x)= %#04x\n", MDIO_DEVID2,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID2));
+	dev_dbg(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS1,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS1));
+	dev_dbg(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS2,
+		XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS2));
+
+	dev_dbg(dev, "Auto-Neg Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1));
+	dev_dbg(dev, "Auto-Neg Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_STAT1));
+	dev_dbg(dev, "Auto-Neg Ad Reg 1 (%#04x) = %#04x\n",
+		MDIO_AN_ADVERTISE,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE));
+	dev_dbg(dev, "Auto-Neg Ad Reg 2 (%#04x) = %#04x\n",
+		MDIO_AN_ADVERTISE + 1,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1));
+	dev_dbg(dev, "Auto-Neg Ad Reg 3 (%#04x) = %#04x\n",
+		MDIO_AN_ADVERTISE + 2,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2));
+	dev_dbg(dev, "Auto-Neg Completion Reg (%#04x) = %#04x\n",
+		MDIO_AN_COMP_STAT,
+		XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_COMP_STAT));
+
+	dev_dbg(dev, "\n*************************************************\n");
+}
+
+static void xgbe_phy_init(struct xgbe_prv_data *pdata)
+{
+	mutex_init(&pdata->an_mutex);
+	INIT_WORK(&pdata->an_irq_work, xgbe_an_irq_work);
+	INIT_WORK(&pdata->an_work, xgbe_an_state_machine);
+	pdata->mdio_mmd = MDIO_MMD_PCS;
+
+	/* Initialize supported features */
+	pdata->phy.supported = SUPPORTED_Autoneg;
+	pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	pdata->phy.supported |= SUPPORTED_Backplane;
+	pdata->phy.supported |= SUPPORTED_10000baseKR_Full;
+	switch (pdata->speed_set) {
+	case XGBE_SPEEDSET_1000_10000:
+		pdata->phy.supported |= SUPPORTED_1000baseKX_Full;
+		break;
+	case XGBE_SPEEDSET_2500_10000:
+		pdata->phy.supported |= SUPPORTED_2500baseX_Full;
+		break;
+	}
 
-	pdata->phydev = NULL;
+	pdata->fec_ability = XMDIO_READ(pdata, MDIO_MMD_PMAPMD,
+					MDIO_PMA_10GBR_FECABLE);
+	pdata->fec_ability &= (MDIO_PMA_10GBR_FECABLE_ABLE |
+			       MDIO_PMA_10GBR_FECABLE_ERRABLE);
+	if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE)
+		pdata->phy.supported |= SUPPORTED_10000baseR_FEC;
 
-	module_put(pdata->phy_module);
-	pdata->phy_module = NULL;
+	pdata->phy.advertising = pdata->phy.supported;
 
-	mdiobus_unregister(pdata->mii);
-	pdata->mii->priv = NULL;
+	pdata->phy.address = 0;
+
+	pdata->phy.autoneg = AUTONEG_ENABLE;
+	pdata->phy.speed = SPEED_UNKNOWN;
+	pdata->phy.duplex = DUPLEX_UNKNOWN;
+
+	pdata->phy.link = 0;
+
+	pdata->phy.pause_autoneg = pdata->pause_autoneg;
+	pdata->phy.tx_pause = pdata->tx_pause;
+	pdata->phy.rx_pause = pdata->rx_pause;
+
+	/* Fix up Flow Control advertising */
+	pdata->phy.advertising &= ~ADVERTISED_Pause;
+	pdata->phy.advertising &= ~ADVERTISED_Asym_Pause;
+
+	if (pdata->rx_pause) {
+		pdata->phy.advertising |= ADVERTISED_Pause;
+		pdata->phy.advertising |= ADVERTISED_Asym_Pause;
+	}
+
+	if (pdata->tx_pause)
+		pdata->phy.advertising ^= ADVERTISED_Asym_Pause;
+
+	if (netif_msg_drv(pdata))
+		xgbe_dump_phy_registers(pdata);
+}
+
+void xgbe_init_function_ptrs_phy(struct xgbe_phy_if *phy_if)
+{
+	phy_if->phy_init        = xgbe_phy_init;
 
-	mdiobus_free(pdata->mii);
-	pdata->mii = NULL;
+	phy_if->phy_reset       = xgbe_phy_reset;
+	phy_if->phy_start       = xgbe_phy_start;
+	phy_if->phy_stop        = xgbe_phy_stop;
 
-	DBGPR("<--xgbe_mdio_unregister\n");
+	phy_if->phy_status      = xgbe_phy_status;
+	phy_if->phy_config_aneg = xgbe_phy_config_aneg;
 }
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index e62dfa2deab6..63d72a140053 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -129,7 +129,7 @@
 #include <net/dcbnl.h>
 
 #define XGBE_DRV_NAME		"amd-xgbe"
-#define XGBE_DRV_VERSION	"1.0.0-a"
+#define XGBE_DRV_VERSION	"1.0.2"
 #define XGBE_DRV_DESC		"AMD 10 Gigabit Ethernet Driver"
 
 /* Descriptor related defines */
@@ -178,14 +178,17 @@
 #define XGMAC_JUMBO_PACKET_MTU	9000
 #define XGMAC_MAX_JUMBO_PACKET	9018
 
-/* MDIO bus phy name */
-#define XGBE_PHY_NAME		"amd_xgbe_phy"
-#define XGBE_PRTAD		0
-
 /* Common property names */
 #define XGBE_MAC_ADDR_PROPERTY	"mac-address"
 #define XGBE_PHY_MODE_PROPERTY	"phy-mode"
 #define XGBE_DMA_IRQS_PROPERTY	"amd,per-channel-interrupt"
+#define XGBE_SPEEDSET_PROPERTY	"amd,speed-set"
+#define XGBE_BLWC_PROPERTY	"amd,serdes-blwc"
+#define XGBE_CDR_RATE_PROPERTY	"amd,serdes-cdr-rate"
+#define XGBE_PQ_SKEW_PROPERTY	"amd,serdes-pq-skew"
+#define XGBE_TX_AMP_PROPERTY	"amd,serdes-tx-amp"
+#define XGBE_DFE_CFG_PROPERTY	"amd,serdes-dfe-tap-config"
+#define XGBE_DFE_ENA_PROPERTY	"amd,serdes-dfe-tap-enable"
 
 /* Device-tree clock names */
 #define XGBE_DMA_CLOCK		"dma_clk"
@@ -241,6 +244,49 @@
 #define XGBE_RSS_LOOKUP_TABLE_TYPE	0
 #define XGBE_RSS_HASH_KEY_TYPE		1
 
+/* Auto-negotiation */
+#define XGBE_AN_MS_TIMEOUT		500
+#define XGBE_LINK_TIMEOUT		10
+
+#define XGBE_AN_INT_CMPLT		0x01
+#define XGBE_AN_INC_LINK		0x02
+#define XGBE_AN_PG_RCV			0x04
+#define XGBE_AN_INT_MASK		0x07
+
+/* Rate-change complete wait/retry count */
+#define XGBE_RATECHANGE_COUNT		500
+
+/* Default SerDes settings */
+#define XGBE_SPEED_10000_BLWC		0
+#define XGBE_SPEED_10000_CDR		0x7
+#define XGBE_SPEED_10000_PLL		0x1
+#define XGBE_SPEED_10000_PQ		0x12
+#define XGBE_SPEED_10000_RATE		0x0
+#define XGBE_SPEED_10000_TXAMP		0xa
+#define XGBE_SPEED_10000_WORD		0x7
+#define XGBE_SPEED_10000_DFE_TAP_CONFIG	0x1
+#define XGBE_SPEED_10000_DFE_TAP_ENABLE	0x7f
+
+#define XGBE_SPEED_2500_BLWC		1
+#define XGBE_SPEED_2500_CDR		0x2
+#define XGBE_SPEED_2500_PLL		0x0
+#define XGBE_SPEED_2500_PQ		0xa
+#define XGBE_SPEED_2500_RATE		0x1
+#define XGBE_SPEED_2500_TXAMP		0xf
+#define XGBE_SPEED_2500_WORD		0x1
+#define XGBE_SPEED_2500_DFE_TAP_CONFIG	0x3
+#define XGBE_SPEED_2500_DFE_TAP_ENABLE	0x0
+
+#define XGBE_SPEED_1000_BLWC		1
+#define XGBE_SPEED_1000_CDR		0x2
+#define XGBE_SPEED_1000_PLL		0x0
+#define XGBE_SPEED_1000_PQ		0xa
+#define XGBE_SPEED_1000_RATE		0x3
+#define XGBE_SPEED_1000_TXAMP		0xf
+#define XGBE_SPEED_1000_WORD		0x1
+#define XGBE_SPEED_1000_DFE_TAP_CONFIG	0x3
+#define XGBE_SPEED_1000_DFE_TAP_ENABLE	0x0
+
 struct xgbe_prv_data;
 
 struct xgbe_packet_data {
@@ -334,8 +380,6 @@ struct xgbe_ring_data {
 	 */
 	unsigned int state_saved;
 	struct {
-		unsigned int incomplete;
-		unsigned int context_next;
 		struct sk_buff *skb;
 		unsigned int len;
 		unsigned int error;
@@ -414,6 +458,13 @@ struct xgbe_channel {
 	struct xgbe_ring *rx_ring;
 } ____cacheline_aligned;
 
+enum xgbe_state {
+	XGBE_DOWN,
+	XGBE_LINK,
+	XGBE_LINK_INIT,
+	XGBE_LINK_ERR,
+};
+
 enum xgbe_int {
 	XGMAC_INT_DMA_CH_SR_TI,
 	XGMAC_INT_DMA_CH_SR_TPS,
@@ -445,6 +496,57 @@ enum xgbe_mtl_fifo_size {
 	XGMAC_MTL_FIFO_SIZE_256K = 0x3ff,
 };
 
+enum xgbe_speed {
+	XGBE_SPEED_1000 = 0,
+	XGBE_SPEED_2500,
+	XGBE_SPEED_10000,
+	XGBE_SPEEDS,
+};
+
+enum xgbe_an {
+	XGBE_AN_READY = 0,
+	XGBE_AN_PAGE_RECEIVED,
+	XGBE_AN_INCOMPAT_LINK,
+	XGBE_AN_COMPLETE,
+	XGBE_AN_NO_LINK,
+	XGBE_AN_ERROR,
+};
+
+enum xgbe_rx {
+	XGBE_RX_BPA = 0,
+	XGBE_RX_XNP,
+	XGBE_RX_COMPLETE,
+	XGBE_RX_ERROR,
+};
+
+enum xgbe_mode {
+	XGBE_MODE_KR = 0,
+	XGBE_MODE_KX,
+};
+
+enum xgbe_speedset {
+	XGBE_SPEEDSET_1000_10000 = 0,
+	XGBE_SPEEDSET_2500_10000,
+};
+
+struct xgbe_phy {
+	u32 supported;
+	u32 advertising;
+	u32 lp_advertising;
+
+	int address;
+
+	int autoneg;
+	int speed;
+	int duplex;
+
+	int link;
+
+	int pause_autoneg;
+	int tx_pause;
+	int rx_pause;
+};
+
 struct xgbe_mmc_stats {
 	/* Tx Stats */
 	u64 txoctetcount_gb;
@@ -492,6 +594,11 @@ struct xgbe_mmc_stats {
 	u64 rxwatchdogerror;
 };
 
+struct xgbe_ext_stats {
+	u64 tx_tso_packets;
+	u64 rx_split_header_packets;
+};
+
 struct xgbe_hw_if {
 	int (*tx_complete)(struct xgbe_ring_desc *);
 
@@ -591,6 +698,20 @@ struct xgbe_hw_if {
 	int (*set_rss_lookup_table)(struct xgbe_prv_data *, const u32 *);
 };
 
+struct xgbe_phy_if {
+	/* For initial PHY setup */
+	void (*phy_init)(struct xgbe_prv_data *);
+
+	/* For PHY support when setting device up/down */
+	int (*phy_reset)(struct xgbe_prv_data *);
+	int (*phy_start)(struct xgbe_prv_data *);
+	void (*phy_stop)(struct xgbe_prv_data *);
+
+	/* For PHY support while device is up */
+	void (*phy_status)(struct xgbe_prv_data *);
+	int (*phy_config_aneg)(struct xgbe_prv_data *);
+};
+
 struct xgbe_desc_if {
 	int (*alloc_ring_resources)(struct xgbe_prv_data *);
 	void (*free_ring_resources)(struct xgbe_prv_data *);
@@ -660,6 +781,9 @@ struct xgbe_prv_data {
 	/* XGMAC/XPCS related mmio registers */
 	void __iomem *xgmac_regs;	/* XGMAC CSRs */
 	void __iomem *xpcs_regs;	/* XPCS MMD registers */
+	void __iomem *rxtx_regs;	/* SerDes Rx/Tx CSRs */
+	void __iomem *sir0_regs;	/* SerDes integration registers (1/2) */
+	void __iomem *sir1_regs;	/* SerDes integration registers (2/2) */
 
 	/* Overall device lock */
 	spinlock_t lock;
@@ -670,10 +794,14 @@ struct xgbe_prv_data {
 	/* RSS addressing mutex */
 	struct mutex rss_mutex;
 
+	/* Flags representing xgbe_state */
+	unsigned long dev_state;
+
 	int dev_irq;
 	unsigned int per_channel_irq;
 
 	struct xgbe_hw_if hw_if;
+	struct xgbe_phy_if phy_if;
 	struct xgbe_desc_if desc_if;
 
 	/* AXI DMA settings */
@@ -682,6 +810,11 @@ struct xgbe_prv_data {
 	unsigned int arcache;
 	unsigned int awcache;
 
+	/* Service routine support */
+	struct workqueue_struct *dev_workqueue;
+	struct work_struct service_work;
+	struct timer_list service_timer;
+
 	/* Rings for Tx/Rx on a DMA channel */
 	struct xgbe_channel *channel;
 	unsigned int channel_count;
@@ -729,27 +862,12 @@ struct xgbe_prv_data {
 	u32 rss_table[XGBE_RSS_MAX_TABLE_SIZE];
 	u32 rss_options;
 
-	/* MDIO settings */
-	struct module *phy_module;
-	char *mii_bus_id;
-	struct mii_bus *mii;
-	int mdio_mmd;
-	struct phy_device *phydev;
-	int default_autoneg;
-	int default_speed;
-
-	/* Current PHY settings */
-	phy_interface_t phy_mode;
-	int phy_link;
-	int phy_speed;
-	unsigned int phy_tx_pause;
-	unsigned int phy_rx_pause;
-
 	/* Netdev related settings */
 	unsigned char mac_addr[ETH_ALEN];
 	netdev_features_t netdev_features;
 	struct napi_struct napi;
 	struct xgbe_mmc_stats mmc_stats;
+	struct xgbe_ext_stats ext_stats;
 
 	/* Filtering support */
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
@@ -787,6 +905,54 @@ struct xgbe_prv_data {
 	/* Keeps track of power mode */
 	unsigned int power_down;
 
+	/* Network interface message level setting */
+	u32 msg_enable;
+
+	/* Current PHY settings */
+	phy_interface_t phy_mode;
+	int phy_link;
+	int phy_speed;
+
+	/* MDIO/PHY related settings */
+	struct xgbe_phy phy;
+	int mdio_mmd;
+	unsigned long link_check;
+
+	char an_name[IFNAMSIZ + 32];
+	struct workqueue_struct *an_workqueue;
+
+	int an_irq;
+	struct work_struct an_irq_work;
+
+	unsigned int speed_set;
+
+	/* SerDes UEFI configurable settings.
+	 *   Switching between modes/speeds requires new values for some
+	 *   SerDes settings.  The values can be supplied as device
+	 *   properties in array format.  The first array entry is for
+	 *   1GbE, second for 2.5GbE and third for 10GbE
+	 */
+	u32 serdes_blwc[XGBE_SPEEDS];
+	u32 serdes_cdr_rate[XGBE_SPEEDS];
+	u32 serdes_pq_skew[XGBE_SPEEDS];
+	u32 serdes_tx_amp[XGBE_SPEEDS];
+	u32 serdes_dfe_tap_cfg[XGBE_SPEEDS];
+	u32 serdes_dfe_tap_ena[XGBE_SPEEDS];
+
+	/* Auto-negotiation state machine support */
+	struct mutex an_mutex;
+	enum xgbe_an an_result;
+	enum xgbe_an an_state;
+	enum xgbe_rx kr_state;
+	enum xgbe_rx kx_state;
+	struct work_struct an_work;
+	unsigned int an_supported;
+	unsigned int parallel_detect;
+	unsigned int fec_ability;
+	unsigned long an_start;
+
+	unsigned int lpm_ctrl;		/* CTRL1 for resume */
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *xgbe_debugfs;
 
@@ -800,6 +966,7 @@ struct xgbe_prv_data {
 /* Function prototypes*/
 
 void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *);
+void xgbe_init_function_ptrs_phy(struct xgbe_phy_if *);
 void xgbe_init_function_ptrs_desc(struct xgbe_desc_if *);
 struct net_device_ops *xgbe_get_netdev_ops(void);
 struct ethtool_ops *xgbe_get_ethtool_ops(void);
@@ -807,14 +974,11 @@ struct ethtool_ops *xgbe_get_ethtool_ops(void);
 const struct dcbnl_rtnl_ops *xgbe_get_dcbnl_ops(void);
 #endif
 
-int xgbe_mdio_register(struct xgbe_prv_data *);
-void xgbe_mdio_unregister(struct xgbe_prv_data *);
-void xgbe_dump_phy_registers(struct xgbe_prv_data *);
 void xgbe_ptp_register(struct xgbe_prv_data *);
 void xgbe_ptp_unregister(struct xgbe_prv_data *);
-void xgbe_dump_tx_desc(struct xgbe_ring *, unsigned int, unsigned int,
-		       unsigned int);
-void xgbe_dump_rx_desc(struct xgbe_ring *, struct xgbe_ring_desc *,
+void xgbe_dump_tx_desc(struct xgbe_prv_data *, struct xgbe_ring *,
+		       unsigned int, unsigned int, unsigned int);
+void xgbe_dump_rx_desc(struct xgbe_prv_data *, struct xgbe_ring *,
 		       unsigned int);
 void xgbe_print_pkt(struct net_device *, struct sk_buff *, bool);
 void xgbe_get_all_hw_features(struct xgbe_prv_data *);
@@ -831,18 +995,6 @@ static inline void xgbe_debugfs_init(struct xgbe_prv_data *pdata) {}
 static inline void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) {}
 #endif /* CONFIG_DEBUG_FS */
 
-/* NOTE: Uncomment for TX and RX DESCRIPTOR DUMP in KERNEL LOG */
-#if 0
-#define XGMAC_ENABLE_TX_DESC_DUMP
-#define XGMAC_ENABLE_RX_DESC_DUMP
-#endif
-
-/* NOTE: Uncomment for TX and RX PACKET DUMP in KERNEL LOG */
-#if 0
-#define XGMAC_ENABLE_TX_PKT_DUMP
-#define XGMAC_ENABLE_RX_PKT_DUMP
-#endif
-
 /* NOTE: Uncomment for function trace log messages in KERNEL LOG */
 #if 0
 #define YDEBUG
@@ -852,10 +1004,8 @@ static inline void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) {}
 /* For debug prints */
 #ifdef YDEBUG
 #define DBGPR(x...) pr_alert(x)
-#define DBGPHY_REGS(x...) xgbe_dump_phy_registers(x)
 #else
 #define DBGPR(x...) do { } while (0)
-#define DBGPHY_REGS(x...) do { } while (0)
 #endif
 
 #ifdef YDEBUG_MDIO
diff --git a/drivers/net/ethernet/apm/xgene/Kconfig b/drivers/net/ethernet/apm/xgene/Kconfig
index f4054d242f3c..19e38afbc5ee 100644
--- a/drivers/net/ethernet/apm/xgene/Kconfig
+++ b/drivers/net/ethernet/apm/xgene/Kconfig
@@ -1,6 +1,7 @@
 config NET_XGENE
 	tristate "APM X-Gene SoC Ethernet Driver"
 	depends on HAS_DMA
+	depends on ARCH_XGENE || COMPILE_TEST
 	select PHYLIB
 	help
 	  This is the Ethernet driver for the on-chip ethernet interface on the
diff --git a/drivers/net/ethernet/apm/xgene/Makefile b/drivers/net/ethernet/apm/xgene/Makefile
index 68be565548c0..700b5abe5de5 100644
--- a/drivers/net/ethernet/apm/xgene/Makefile
+++ b/drivers/net/ethernet/apm/xgene/Makefile
@@ -3,5 +3,5 @@
 #
 
 xgene-enet-objs := xgene_enet_hw.o xgene_enet_sgmac.o xgene_enet_xgmac.o \
-		   xgene_enet_main.o xgene_enet_ethtool.o
+		   xgene_enet_main.o xgene_enet_ring2.o xgene_enet_ethtool.o
 obj-$(CONFIG_NET_XGENE) += xgene-enet.o
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index b927021c6c40..a626c4315a89 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -87,10 +87,11 @@ static void xgene_enet_ring_rd32(struct xgene_enet_desc_ring *ring,
 
 static void xgene_enet_write_ring_state(struct xgene_enet_desc_ring *ring)
 {
+	struct xgene_enet_pdata *pdata = netdev_priv(ring->ndev);
 	int i;
 
 	xgene_enet_ring_wr32(ring, CSR_RING_CONFIG, ring->num);
-	for (i = 0; i < NUM_RING_CONFIG; i++) {
+	for (i = 0; i < pdata->ring_ops->num_ring_config; i++) {
 		xgene_enet_ring_wr32(ring, CSR_RING_WR_BASE + (i * 4),
 				     ring->state[i]);
 	}
@@ -98,7 +99,7 @@ static void xgene_enet_write_ring_state(struct xgene_enet_desc_ring *ring)
 
 static void xgene_enet_clr_ring_state(struct xgene_enet_desc_ring *ring)
 {
-	memset(ring->state, 0, sizeof(u32) * NUM_RING_CONFIG);
+	memset(ring->state, 0, sizeof(ring->state));
 	xgene_enet_write_ring_state(ring);
 }
 
@@ -141,8 +142,8 @@ static void xgene_enet_clr_desc_ring_id(struct xgene_enet_desc_ring *ring)
 	xgene_enet_ring_wr32(ring, CSR_RING_ID_BUF, 0);
 }
 
-struct xgene_enet_desc_ring *xgene_enet_setup_ring(
-					struct xgene_enet_desc_ring *ring)
+static struct xgene_enet_desc_ring *xgene_enet_setup_ring(
+				    struct xgene_enet_desc_ring *ring)
 {
 	u32 size = ring->size;
 	u32 i, data;
@@ -168,7 +169,7 @@ struct xgene_enet_desc_ring *xgene_enet_setup_ring(
 	return ring;
 }
 
-void xgene_enet_clear_ring(struct xgene_enet_desc_ring *ring)
+static void xgene_enet_clear_ring(struct xgene_enet_desc_ring *ring)
 {
 	u32 data;
 	bool is_bufpool;
@@ -186,6 +187,22 @@ out:
 	xgene_enet_clr_ring_state(ring);
 }
 
+static void xgene_enet_wr_cmd(struct xgene_enet_desc_ring *ring, int count)
+{
+	iowrite32(count, ring->cmd);
+}
+
+static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring)
+{
+	u32 __iomem *cmd_base = ring->cmd_base;
+	u32 ring_state, num_msgs;
+
+	ring_state = ioread32(&cmd_base[1]);
+	num_msgs = GET_VAL(NUMMSGSINQ, ring_state);
+
+	return num_msgs;
+}
+
 void xgene_enet_parse_error(struct xgene_enet_desc_ring *ring,
 			    struct xgene_enet_pdata *pdata,
 			    enum xgene_enet_err_code status)
@@ -593,7 +610,7 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata)
 	if (!xgene_ring_mgr_init(pdata))
 		return -ENODEV;
 
-	if (pdata->clk) {
+	if (!IS_ERR(pdata->clk)) {
 		clk_prepare_enable(pdata->clk);
 		clk_disable_unprepare(pdata->clk);
 		clk_prepare_enable(pdata->clk);
@@ -612,7 +629,8 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata)
 
 static void xgene_gport_shutdown(struct xgene_enet_pdata *pdata)
 {
-	clk_disable_unprepare(pdata->clk);
+	if (!IS_ERR(pdata->clk))
+		clk_disable_unprepare(pdata->clk);
 }
 
 static int xgene_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
@@ -734,7 +752,7 @@ static int xgene_mdiobus_register(struct xgene_enet_pdata *pdata,
 	if (ret)
 		return -EINVAL;
 
-	phy = get_phy_device(mdio, phy_id, true);
+	phy = get_phy_device(mdio, phy_id, false);
 	if (!phy || IS_ERR(phy))
 		return -EIO;
 
@@ -803,3 +821,12 @@ struct xgene_port_ops xgene_gport_ops = {
 	.cle_bypass = xgene_enet_cle_bypass,
 	.shutdown = xgene_gport_shutdown,
 };
+
+struct xgene_ring_ops xgene_ring1_ops = {
+	.num_ring_config = NUM_RING_CONFIG,
+	.num_ring_id_shift = 6,
+	.setup = xgene_enet_setup_ring,
+	.clear = xgene_enet_clear_ring,
+	.wr_cmd = xgene_enet_wr_cmd,
+	.len = xgene_enet_ring_len,
+};
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
index d9bc89d69266..541bed056012 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.h
@@ -26,6 +26,7 @@
 
 struct xgene_enet_pdata;
 struct xgene_enet_stats;
+struct xgene_enet_desc_ring;
 
 /* clears and then set bits */
 static inline void xgene_set_bits(u32 *dst, u32 val, u32 start, u32 len)
@@ -101,8 +102,8 @@ enum xgene_enet_rm {
 
 #define BLOCK_ETH_CSR_OFFSET		0x2000
 #define BLOCK_ETH_RING_IF_OFFSET	0x9000
+#define BLOCK_ETH_CLKRST_CSR_OFFSET	0xc000
 #define BLOCK_ETH_DIAG_CSR_OFFSET	0xD000
-
 #define BLOCK_ETH_MAC_OFFSET		0x0000
 #define BLOCK_ETH_MAC_CSR_OFFSET	0x2800
 
@@ -261,6 +262,7 @@ enum xgene_enet_ring_type {
 
 enum xgene_ring_owner {
 	RING_OWNER_ETH0,
+	RING_OWNER_ETH1,
 	RING_OWNER_CPU = 15,
 	RING_OWNER_INVALID
 };
@@ -314,9 +316,6 @@ static inline u16 xgene_enet_get_numslots(u16 id, u32 size)
 		      size / WORK_DESC_SIZE;
 }
 
-struct xgene_enet_desc_ring *xgene_enet_setup_ring(
-		struct xgene_enet_desc_ring *ring);
-void xgene_enet_clear_ring(struct xgene_enet_desc_ring *ring);
 void xgene_enet_parse_error(struct xgene_enet_desc_ring *ring,
 			    struct xgene_enet_pdata *pdata,
 			    enum xgene_enet_err_code status);
@@ -327,5 +326,6 @@ bool xgene_ring_mgr_init(struct xgene_enet_pdata *p);
 
 extern struct xgene_mac_ops xgene_gmac_ops;
 extern struct xgene_port_ops xgene_gport_ops;
+extern struct xgene_ring_ops xgene_ring1_ops;
 
 #endif /* __XGENE_ENET_HW_H__ */
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 40d3530d7f30..95153b234c71 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -28,6 +28,9 @@
 #define RES_RING_CSR	1
 #define RES_RING_CMD	2
 
+static const struct of_device_id xgene_enet_of_match[];
+static const struct acpi_device_id xgene_enet_acpi_match[];
+
 static void xgene_enet_init_bufpool(struct xgene_enet_desc_ring *buf_pool)
 {
 	struct xgene_enet_raw_desc16 *raw_desc;
@@ -48,6 +51,7 @@ static int xgene_enet_refill_bufpool(struct xgene_enet_desc_ring *buf_pool,
 {
 	struct sk_buff *skb;
 	struct xgene_enet_raw_desc16 *raw_desc;
+	struct xgene_enet_pdata *pdata;
 	struct net_device *ndev;
 	struct device *dev;
 	dma_addr_t dma_addr;
@@ -58,6 +62,7 @@ static int xgene_enet_refill_bufpool(struct xgene_enet_desc_ring *buf_pool,
 
 	ndev = buf_pool->ndev;
 	dev = ndev_to_dev(buf_pool->ndev);
+	pdata = netdev_priv(ndev);
 	bufdatalen = BUF_LEN_CODE_2K | (SKB_BUFFER_SIZE & GENMASK(11, 0));
 	len = XGENE_ENET_MAX_MTU;
 
@@ -82,7 +87,7 @@ static int xgene_enet_refill_bufpool(struct xgene_enet_desc_ring *buf_pool,
 		tail = (tail + 1) & slots;
 	}
 
-	iowrite32(nbuf, buf_pool->cmd);
+	pdata->ring_ops->wr_cmd(buf_pool, nbuf);
 	buf_pool->tail = tail;
 
 	return 0;
@@ -102,26 +107,16 @@ static u8 xgene_enet_hdr_len(const void *data)
 	return (eth->h_proto == htons(ETH_P_8021Q)) ? VLAN_ETH_HLEN : ETH_HLEN;
 }
 
-static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring)
-{
-	u32 __iomem *cmd_base = ring->cmd_base;
-	u32 ring_state, num_msgs;
-
-	ring_state = ioread32(&cmd_base[1]);
-	num_msgs = ring_state & CREATE_MASK(NUMMSGSINQ_POS, NUMMSGSINQ_LEN);
-
-	return num_msgs >> NUMMSGSINQ_POS;
-}
-
 static void xgene_enet_delete_bufpool(struct xgene_enet_desc_ring *buf_pool)
 {
+	struct xgene_enet_pdata *pdata = netdev_priv(buf_pool->ndev);
 	struct xgene_enet_raw_desc16 *raw_desc;
 	u32 slots = buf_pool->slots - 1;
 	u32 tail = buf_pool->tail;
 	u32 userinfo;
 	int i, len;
 
-	len = xgene_enet_ring_len(buf_pool);
+	len = pdata->ring_ops->len(buf_pool);
 	for (i = 0; i < len; i++) {
 		tail = (tail - 1) & slots;
 		raw_desc = &buf_pool->raw_desc16[tail];
@@ -131,7 +126,7 @@ static void xgene_enet_delete_bufpool(struct xgene_enet_desc_ring *buf_pool)
 		dev_kfree_skb_any(buf_pool->rx_skb[userinfo]);
 	}
 
-	iowrite32(-len, buf_pool->cmd);
+	pdata->ring_ops->wr_cmd(buf_pool, -len);
 	buf_pool->tail = tail;
 }
 
@@ -263,8 +258,8 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
 	struct xgene_enet_desc_ring *cp_ring = tx_ring->cp_ring;
 	u32 tx_level, cq_level;
 
-	tx_level = xgene_enet_ring_len(tx_ring);
-	cq_level = xgene_enet_ring_len(cp_ring);
+	tx_level = pdata->ring_ops->len(tx_ring);
+	cq_level = pdata->ring_ops->len(cp_ring);
 	if (unlikely(tx_level > pdata->tx_qcnt_hi ||
 		     cq_level > pdata->cp_qcnt_hi)) {
 		netif_stop_queue(ndev);
@@ -276,7 +271,7 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	iowrite32(1, tx_ring->cmd);
+	pdata->ring_ops->wr_cmd(tx_ring, 1);
 	skb_tx_timestamp(skb);
 	tx_ring->tail = (tx_ring->tail + 1) & (tx_ring->slots - 1);
 
@@ -389,11 +384,11 @@ static int xgene_enet_process_ring(struct xgene_enet_desc_ring *ring,
 	} while (--budget);
 
 	if (likely(count)) {
-		iowrite32(-count, ring->cmd);
+		pdata->ring_ops->wr_cmd(ring, -count);
 		ring->head = head;
 
 		if (netif_queue_stopped(ring->ndev)) {
-			if (xgene_enet_ring_len(ring) < pdata->cp_qcnt_low)
+			if (pdata->ring_ops->len(ring) < pdata->cp_qcnt_low)
 				netif_wake_queue(ring->ndev);
 		}
 	}
@@ -510,6 +505,7 @@ static int xgene_enet_open(struct net_device *ndev)
 	else
 		schedule_delayed_work(&pdata->link_work, PHY_POLL_LINK_OFF);
 
+	netif_carrier_off(ndev);
 	netif_start_queue(ndev);
 
 	return ret;
@@ -545,7 +541,7 @@ static void xgene_enet_delete_ring(struct xgene_enet_desc_ring *ring)
 	pdata = netdev_priv(ring->ndev);
 	dev = ndev_to_dev(ring->ndev);
 
-	xgene_enet_clear_ring(ring);
+	pdata->ring_ops->clear(ring);
 	dma_free_coherent(dev, ring->size, ring->desc_addr, ring->dma);
 }
 
@@ -598,15 +594,17 @@ static int xgene_enet_get_ring_size(struct device *dev,
 
 static void xgene_enet_free_desc_ring(struct xgene_enet_desc_ring *ring)
 {
+	struct xgene_enet_pdata *pdata;
 	struct device *dev;
 
 	if (!ring)
 		return;
 
 	dev = ndev_to_dev(ring->ndev);
+	pdata = netdev_priv(ring->ndev);
 
 	if (ring->desc_addr) {
-		xgene_enet_clear_ring(ring);
+		pdata->ring_ops->clear(ring);
 		dma_free_coherent(dev, ring->size, ring->desc_addr, ring->dma);
 	}
 	devm_kfree(dev, ring);
@@ -637,6 +635,25 @@ static void xgene_enet_free_desc_rings(struct xgene_enet_pdata *pdata)
 	}
 }
 
+static bool is_irq_mbox_required(struct xgene_enet_pdata *pdata,
+				 struct xgene_enet_desc_ring *ring)
+{
+	if ((pdata->enet_id == XGENE_ENET2) &&
+	    (xgene_enet_ring_owner(ring->id) == RING_OWNER_CPU)) {
+		return true;
+	}
+
+	return false;
+}
+
+static void __iomem *xgene_enet_ring_cmd_base(struct xgene_enet_pdata *pdata,
+					      struct xgene_enet_desc_ring *ring)
+{
+	u8 num_ring_id_shift = pdata->ring_ops->num_ring_id_shift;
+
+	return pdata->ring_cmd_addr + (ring->num << num_ring_id_shift);
+}
+
 static struct xgene_enet_desc_ring *xgene_enet_create_desc_ring(
 			struct net_device *ndev, u32 ring_num,
 			enum xgene_enet_ring_cfgsize cfgsize, u32 ring_id)
@@ -668,9 +685,20 @@ static struct xgene_enet_desc_ring *xgene_enet_create_desc_ring(
 	}
 	ring->size = size;
 
-	ring->cmd_base = pdata->ring_cmd_addr + (ring->num << 6);
+	if (is_irq_mbox_required(pdata, ring)) {
+		ring->irq_mbox_addr = dma_zalloc_coherent(dev, INTR_MBOX_SIZE,
+				&ring->irq_mbox_dma, GFP_KERNEL);
+		if (!ring->irq_mbox_addr) {
+			dma_free_coherent(dev, size, ring->desc_addr,
+					  ring->dma);
+			devm_kfree(dev, ring);
+			return NULL;
+		}
+	}
+
+	ring->cmd_base = xgene_enet_ring_cmd_base(pdata, ring);
 	ring->cmd = ring->cmd_base + INC_DEC_CMD_ADDR;
-	ring = xgene_enet_setup_ring(ring);
+	ring = pdata->ring_ops->setup(ring);
 	netdev_dbg(ndev, "ring info: num=%d  size=%d  id=%d  slots=%d\n",
 		   ring->num, ring->size, ring->id, ring->slots);
 
@@ -682,12 +710,34 @@ static u16 xgene_enet_get_ring_id(enum xgene_ring_owner owner, u8 bufnum)
 	return (owner << 6) | (bufnum & GENMASK(5, 0));
 }
 
+static enum xgene_ring_owner xgene_derive_ring_owner(struct xgene_enet_pdata *p)
+{
+	enum xgene_ring_owner owner;
+
+	if (p->enet_id == XGENE_ENET1) {
+		switch (p->phy_mode) {
+		case PHY_INTERFACE_MODE_SGMII:
+			owner = RING_OWNER_ETH0;
+			break;
+		default:
+			owner = (!p->port_id) ? RING_OWNER_ETH0 :
+						RING_OWNER_ETH1;
+			break;
+		}
+	} else {
+		owner = (!p->port_id) ? RING_OWNER_ETH0 : RING_OWNER_ETH1;
+	}
+
+	return owner;
+}
+
 static int xgene_enet_create_desc_rings(struct net_device *ndev)
 {
 	struct xgene_enet_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = ndev_to_dev(ndev);
 	struct xgene_enet_desc_ring *rx_ring, *tx_ring, *cp_ring;
 	struct xgene_enet_desc_ring *buf_pool = NULL;
+	enum xgene_ring_owner owner;
 	u8 cpu_bufnum = pdata->cpu_bufnum;
 	u8 eth_bufnum = pdata->eth_bufnum;
 	u8 bp_bufnum = pdata->bp_bufnum;
@@ -696,6 +746,7 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev)
 	int ret;
 
 	/* allocate rx descriptor ring */
+	owner = xgene_derive_ring_owner(pdata);
 	ring_id = xgene_enet_get_ring_id(RING_OWNER_CPU, cpu_bufnum++);
 	rx_ring = xgene_enet_create_desc_ring(ndev, ring_num++,
 					      RING_CFGSIZE_16KB, ring_id);
@@ -705,7 +756,8 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev)
 	}
 
 	/* allocate buffer pool for receiving packets */
-	ring_id = xgene_enet_get_ring_id(RING_OWNER_ETH0, bp_bufnum++);
+	owner = xgene_derive_ring_owner(pdata);
+	ring_id = xgene_enet_get_ring_id(owner, bp_bufnum++);
 	buf_pool = xgene_enet_create_desc_ring(ndev, ring_num++,
 					       RING_CFGSIZE_2KB, ring_id);
 	if (!buf_pool) {
@@ -734,7 +786,8 @@ static int xgene_enet_create_desc_rings(struct net_device *ndev)
 	pdata->rx_ring = rx_ring;
 
 	/* allocate tx descriptor ring */
-	ring_id = xgene_enet_get_ring_id(RING_OWNER_ETH0, eth_bufnum++);
+	owner = xgene_derive_ring_owner(pdata);
+	ring_id = xgene_enet_get_ring_id(owner, eth_bufnum++);
 	tx_ring = xgene_enet_create_desc_ring(ndev, ring_num++,
 					      RING_CFGSIZE_16KB, ring_id);
 	if (!tx_ring) {
@@ -818,20 +871,38 @@ static const struct net_device_ops xgene_ndev_ops = {
 	.ndo_set_mac_address = xgene_enet_set_mac_address,
 };
 
-static int xgene_get_port_id(struct device *dev, struct xgene_enet_pdata *pdata)
+#ifdef CONFIG_ACPI
+static int xgene_get_port_id_acpi(struct device *dev,
+				  struct xgene_enet_pdata *pdata)
+{
+	acpi_status status;
+	u64 temp;
+
+	status = acpi_evaluate_integer(ACPI_HANDLE(dev), "_SUN", NULL, &temp);
+	if (ACPI_FAILURE(status)) {
+		pdata->port_id = 0;
+	} else {
+		pdata->port_id = temp;
+	}
+
+	return 0;
+}
+#endif
+
+static int xgene_get_port_id_dt(struct device *dev, struct xgene_enet_pdata *pdata)
 {
 	u32 id = 0;
 	int ret;
 
-	ret = device_property_read_u32(dev, "port-id", &id);
-	if (!ret && id > 1) {
-		dev_err(dev, "Incorrect port-id specified\n");
-		return -ENODEV;
+	ret = of_property_read_u32(dev->of_node, "port-id", &id);
+	if (ret) {
+		pdata->port_id = 0;
+		ret = 0;
+	} else {
+		pdata->port_id = id & BIT(0);
 	}
 
-	pdata->port_id = id;
-
-	return 0;
+	return ret;
 }
 
 static int xgene_get_mac_address(struct device *dev,
@@ -876,6 +947,7 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 	struct device *dev;
 	struct resource *res;
 	void __iomem *base_addr;
+	u32 offset;
 	int ret;
 
 	pdev = pdata->pdev;
@@ -917,7 +989,12 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 		return -ENOMEM;
 	}
 
-	ret = xgene_get_port_id(dev, pdata);
+	if (dev->of_node)
+		ret = xgene_get_port_id_dt(dev, pdata);
+#ifdef CONFIG_ACPI
+	else
+		ret = xgene_get_port_id_acpi(dev, pdata);
+#endif
 	if (ret)
 		return ret;
 
@@ -949,27 +1026,35 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 	if (pdata->phy_mode != PHY_INTERFACE_MODE_RGMII) {
 		ret = platform_get_irq(pdev, 1);
 		if (ret <= 0) {
-			dev_err(dev, "Unable to get ENET Tx completion IRQ\n");
-			ret = ret ? : -ENXIO;
-			return ret;
+			pdata->cq_cnt = 0;
+			dev_info(dev, "Unable to get Tx completion IRQ,"
+				 "using Rx IRQ instead\n");
+		} else {
+			pdata->cq_cnt = XGENE_MAX_TXC_RINGS;
+			pdata->txc_irq = ret;
 		}
-		pdata->txc_irq = ret;
 	}
 
 	pdata->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pdata->clk)) {
 		/* Firmware may have set up the clock already. */
-		pdata->clk = NULL;
+		dev_info(dev, "clocks have been setup already\n");
 	}
 
-	base_addr = pdata->base_addr - (pdata->port_id * MAC_OFFSET);
+	if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII)
+		base_addr = pdata->base_addr - (pdata->port_id * MAC_OFFSET);
+	else
+		base_addr = pdata->base_addr;
 	pdata->eth_csr_addr = base_addr + BLOCK_ETH_CSR_OFFSET;
 	pdata->eth_ring_if_addr = base_addr + BLOCK_ETH_RING_IF_OFFSET;
 	pdata->eth_diag_csr_addr = base_addr + BLOCK_ETH_DIAG_CSR_OFFSET;
 	if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII ||
 	    pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) {
 		pdata->mcx_mac_addr = pdata->base_addr + BLOCK_ETH_MAC_OFFSET;
-		pdata->mcx_mac_csr_addr = base_addr + BLOCK_ETH_MAC_CSR_OFFSET;
+		offset = (pdata->enet_id == XGENE_ENET1) ?
+			  BLOCK_ETH_MAC_CSR_OFFSET :
+			  X2_BLOCK_ETH_MAC_CSR_OFFSET;
+		pdata->mcx_mac_csr_addr = base_addr + offset;
 	} else {
 		pdata->mcx_mac_addr = base_addr + BLOCK_AXG_MAC_OFFSET;
 		pdata->mcx_mac_csr_addr = base_addr + BLOCK_AXG_MAC_CSR_OFFSET;
@@ -1024,33 +1109,52 @@ static void xgene_enet_setup_ops(struct xgene_enet_pdata *pdata)
 		pdata->mac_ops = &xgene_sgmac_ops;
 		pdata->port_ops = &xgene_sgport_ops;
 		pdata->rm = RM1;
-		pdata->cq_cnt = XGENE_MAX_TXC_RINGS;
 		break;
 	default:
 		pdata->mac_ops = &xgene_xgmac_ops;
 		pdata->port_ops = &xgene_xgport_ops;
 		pdata->rm = RM0;
-		pdata->cq_cnt = XGENE_MAX_TXC_RINGS;
 		break;
 	}
 
-	switch (pdata->port_id) {
-	case 0:
-		pdata->cpu_bufnum = START_CPU_BUFNUM_0;
-		pdata->eth_bufnum = START_ETH_BUFNUM_0;
-		pdata->bp_bufnum = START_BP_BUFNUM_0;
-		pdata->ring_num = START_RING_NUM_0;
-		break;
-	case 1:
-		pdata->cpu_bufnum = START_CPU_BUFNUM_1;
-		pdata->eth_bufnum = START_ETH_BUFNUM_1;
-		pdata->bp_bufnum = START_BP_BUFNUM_1;
-		pdata->ring_num = START_RING_NUM_1;
-		break;
-	default:
-		break;
+	if (pdata->enet_id == XGENE_ENET1) {
+		switch (pdata->port_id) {
+		case 0:
+			pdata->cpu_bufnum = START_CPU_BUFNUM_0;
+			pdata->eth_bufnum = START_ETH_BUFNUM_0;
+			pdata->bp_bufnum = START_BP_BUFNUM_0;
+			pdata->ring_num = START_RING_NUM_0;
+			break;
+		case 1:
+			pdata->cpu_bufnum = START_CPU_BUFNUM_1;
+			pdata->eth_bufnum = START_ETH_BUFNUM_1;
+			pdata->bp_bufnum = START_BP_BUFNUM_1;
+			pdata->ring_num = START_RING_NUM_1;
+			break;
+		default:
+			break;
+		}
+		pdata->ring_ops = &xgene_ring1_ops;
+	} else {
+		switch (pdata->port_id) {
+		case 0:
+			pdata->cpu_bufnum = X2_START_CPU_BUFNUM_0;
+			pdata->eth_bufnum = X2_START_ETH_BUFNUM_0;
+			pdata->bp_bufnum = X2_START_BP_BUFNUM_0;
+			pdata->ring_num = X2_START_RING_NUM_0;
+			break;
+		case 1:
+			pdata->cpu_bufnum = X2_START_CPU_BUFNUM_1;
+			pdata->eth_bufnum = X2_START_ETH_BUFNUM_1;
+			pdata->bp_bufnum = X2_START_BP_BUFNUM_1;
+			pdata->ring_num = X2_START_RING_NUM_1;
+			break;
+		default:
+			break;
+		}
+		pdata->rm = RM0;
+		pdata->ring_ops = &xgene_ring2_ops;
 	}
-
 }
 
 static void xgene_enet_napi_add(struct xgene_enet_pdata *pdata)
@@ -1086,6 +1190,7 @@ static int xgene_enet_probe(struct platform_device *pdev)
 	struct xgene_enet_pdata *pdata;
 	struct device *dev = &pdev->dev;
 	struct xgene_mac_ops *mac_ops;
+	const struct of_device_id *of_id;
 	int ret;
 
 	ndev = alloc_etherdev(sizeof(struct xgene_enet_pdata));
@@ -1104,6 +1209,24 @@ static int xgene_enet_probe(struct platform_device *pdev)
 			  NETIF_F_GSO |
 			  NETIF_F_GRO;
 
+	of_id = of_match_device(xgene_enet_of_match, &pdev->dev);
+	if (of_id) {
+		pdata->enet_id = (enum xgene_enet_id)of_id->data;
+	}
+#ifdef CONFIG_ACPI
+	else {
+		const struct acpi_device_id *acpi_id;
+
+		acpi_id = acpi_match_device(xgene_enet_acpi_match, &pdev->dev);
+		if (acpi_id)
+			pdata->enet_id = (enum xgene_enet_id) acpi_id->driver_data;
+	}
+#endif
+	if (!pdata->enet_id) {
+		free_netdev(ndev);
+		return -ENODEV;
+	}
+
 	ret = xgene_enet_get_resources(pdata);
 	if (ret)
 		goto err;
@@ -1165,9 +1288,11 @@ static int xgene_enet_remove(struct platform_device *pdev)
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id xgene_enet_acpi_match[] = {
-	{ "APMC0D05", },
-	{ "APMC0D30", },
-	{ "APMC0D31", },
+	{ "APMC0D05", XGENE_ENET1},
+	{ "APMC0D30", XGENE_ENET1},
+	{ "APMC0D31", XGENE_ENET1},
+	{ "APMC0D26", XGENE_ENET2},
+	{ "APMC0D25", XGENE_ENET2},
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, xgene_enet_acpi_match);
@@ -1175,9 +1300,11 @@ MODULE_DEVICE_TABLE(acpi, xgene_enet_acpi_match);
 
 #ifdef CONFIG_OF
 static const struct of_device_id xgene_enet_of_match[] = {
-	{.compatible = "apm,xgene-enet",},
-	{.compatible = "apm,xgene1-sgenet",},
-	{.compatible = "apm,xgene1-xgenet",},
+	{.compatible = "apm,xgene-enet",    .data = (void *)XGENE_ENET1},
+	{.compatible = "apm,xgene1-sgenet", .data = (void *)XGENE_ENET1},
+	{.compatible = "apm,xgene1-xgenet", .data = (void *)XGENE_ENET1},
+	{.compatible = "apm,xgene2-sgenet", .data = (void *)XGENE_ENET2},
+	{.compatible = "apm,xgene2-xgenet", .data = (void *)XGENE_ENET2},
 	{},
 };
 
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
index 8f3d232b09bc..1c85fc87703a 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h
@@ -35,6 +35,7 @@
 #include <linux/if_vlan.h>
 #include <linux/phy.h>
 #include "xgene_enet_hw.h"
+#include "xgene_enet_ring2.h"
 
 #define XGENE_DRV_VERSION	"v1.0"
 #define XGENE_ENET_MAX_MTU	1536
@@ -51,12 +52,26 @@
 #define START_BP_BUFNUM_1	0x2A
 #define START_RING_NUM_1	264
 
+#define X2_START_CPU_BUFNUM_0	0
+#define X2_START_ETH_BUFNUM_0	0
+#define X2_START_BP_BUFNUM_0	0x20
+#define X2_START_RING_NUM_0	0
+#define X2_START_CPU_BUFNUM_1	0xc
+#define X2_START_ETH_BUFNUM_1	0
+#define X2_START_BP_BUFNUM_1	0x20
+#define X2_START_RING_NUM_1	256
+
 #define IRQ_ID_SIZE		16
 #define XGENE_MAX_TXC_RINGS	1
 
 #define PHY_POLL_LINK_ON	(10 * HZ)
 #define PHY_POLL_LINK_OFF	(PHY_POLL_LINK_ON / 5)
 
+enum xgene_enet_id {
+	XGENE_ENET1 = 1,
+	XGENE_ENET2
+};
+
 /* software context of a descriptor ring */
 struct xgene_enet_desc_ring {
 	struct net_device *ndev;
@@ -68,10 +83,12 @@ struct xgene_enet_desc_ring {
 	u16 irq;
 	char irq_name[IRQ_ID_SIZE];
 	u32 size;
-	u32 state[NUM_RING_CONFIG];
+	u32 state[X2_NUM_RING_CONFIG];
 	void __iomem *cmd_base;
 	void __iomem *cmd;
 	dma_addr_t dma;
+	dma_addr_t irq_mbox_dma;
+	void *irq_mbox_addr;
 	u16 dst_ring_num;
 	u8 nbufpool;
 	struct sk_buff *(*rx_skb);
@@ -105,6 +122,15 @@ struct xgene_port_ops {
 	void (*shutdown)(struct xgene_enet_pdata *pdata);
 };
 
+struct xgene_ring_ops {
+	u8 num_ring_config;
+	u8 num_ring_id_shift;
+	struct xgene_enet_desc_ring * (*setup)(struct xgene_enet_desc_ring *);
+	void (*clear)(struct xgene_enet_desc_ring *);
+	void (*wr_cmd)(struct xgene_enet_desc_ring *, int);
+	u32 (*len)(struct xgene_enet_desc_ring *);
+};
+
 /* ethernet private data */
 struct xgene_enet_pdata {
 	struct net_device *ndev;
@@ -113,6 +139,7 @@ struct xgene_enet_pdata {
 	int phy_speed;
 	struct clk *clk;
 	struct platform_device *pdev;
+	enum xgene_enet_id enet_id;
 	struct xgene_enet_desc_ring *tx_ring;
 	struct xgene_enet_desc_ring *rx_ring;
 	char *dev_name;
@@ -136,6 +163,7 @@ struct xgene_enet_pdata {
 	struct rtnl_link_stats64 stats;
 	struct xgene_mac_ops *mac_ops;
 	struct xgene_port_ops *port_ops;
+	struct xgene_ring_ops *ring_ops;
 	struct delayed_work link_work;
 	u32 port_id;
 	u8 cpu_bufnum;
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
new file mode 100644
index 000000000000..0b6896bb351e
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.c
@@ -0,0 +1,200 @@
+/* Applied Micro X-Gene SoC Ethernet Driver
+ *
+ * Copyright (c) 2015, Applied Micro Circuits Corporation
+ * Author: Iyappan Subramanian <isubramanian@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include "xgene_enet_main.h"
+#include "xgene_enet_hw.h"
+#include "xgene_enet_ring2.h"
+
+static void xgene_enet_ring_init(struct xgene_enet_desc_ring *ring)
+{
+	u32 *ring_cfg = ring->state;
+	u64 addr = ring->dma;
+
+	if (xgene_enet_ring_owner(ring->id) == RING_OWNER_CPU) {
+		ring_cfg[0] |= SET_VAL(X2_INTLINE, ring->id & RING_BUFNUM_MASK);
+		ring_cfg[3] |= SET_BIT(X2_DEQINTEN);
+	}
+	ring_cfg[0] |= SET_VAL(X2_CFGCRID, 1);
+
+	addr >>= 8;
+	ring_cfg[2] |= QCOHERENT | SET_VAL(RINGADDRL, addr);
+
+	addr >>= 27;
+	ring_cfg[3] |= SET_VAL(RINGSIZE, ring->cfgsize)
+		    | ACCEPTLERR
+		    | SET_VAL(RINGADDRH, addr);
+	ring_cfg[4] |= SET_VAL(X2_SELTHRSH, 1);
+	ring_cfg[5] |= SET_BIT(X2_QBASE_AM) | SET_BIT(X2_MSG_AM);
+}
+
+static void xgene_enet_ring_set_type(struct xgene_enet_desc_ring *ring)
+{
+	u32 *ring_cfg = ring->state;
+	bool is_bufpool;
+	u32 val;
+
+	is_bufpool = xgene_enet_is_bufpool(ring->id);
+	val = (is_bufpool) ? RING_BUFPOOL : RING_REGULAR;
+	ring_cfg[4] |= SET_VAL(X2_RINGTYPE, val);
+	if (is_bufpool)
+		ring_cfg[3] |= SET_VAL(RINGMODE, BUFPOOL_MODE);
+}
+
+static void xgene_enet_ring_set_recombbuf(struct xgene_enet_desc_ring *ring)
+{
+	u32 *ring_cfg = ring->state;
+
+	ring_cfg[3] |= RECOMBBUF;
+	ring_cfg[4] |= SET_VAL(X2_RECOMTIMEOUT, 0x7);
+}
+
+static void xgene_enet_ring_wr32(struct xgene_enet_desc_ring *ring,
+				 u32 offset, u32 data)
+{
+	struct xgene_enet_pdata *pdata = netdev_priv(ring->ndev);
+
+	iowrite32(data, pdata->ring_csr_addr + offset);
+}
+
+static void xgene_enet_write_ring_state(struct xgene_enet_desc_ring *ring)
+{
+	struct xgene_enet_pdata *pdata = netdev_priv(ring->ndev);
+	int i;
+
+	xgene_enet_ring_wr32(ring, CSR_RING_CONFIG, ring->num);
+	for (i = 0; i < pdata->ring_ops->num_ring_config; i++) {
+		xgene_enet_ring_wr32(ring, CSR_RING_WR_BASE + (i * 4),
+				     ring->state[i]);
+	}
+}
+
+static void xgene_enet_clr_ring_state(struct xgene_enet_desc_ring *ring)
+{
+	memset(ring->state, 0, sizeof(ring->state));
+	xgene_enet_write_ring_state(ring);
+}
+
+static void xgene_enet_set_ring_state(struct xgene_enet_desc_ring *ring)
+{
+	enum xgene_ring_owner owner;
+
+	xgene_enet_ring_set_type(ring);
+
+	owner = xgene_enet_ring_owner(ring->id);
+	if (owner == RING_OWNER_ETH0 || owner == RING_OWNER_ETH1)
+		xgene_enet_ring_set_recombbuf(ring);
+
+	xgene_enet_ring_init(ring);
+	xgene_enet_write_ring_state(ring);
+}
+
+static void xgene_enet_set_ring_id(struct xgene_enet_desc_ring *ring)
+{
+	u32 ring_id_val, ring_id_buf;
+	bool is_bufpool;
+
+	if (xgene_enet_ring_owner(ring->id) == RING_OWNER_CPU)
+		return;
+
+	is_bufpool = xgene_enet_is_bufpool(ring->id);
+
+	ring_id_val = ring->id & GENMASK(9, 0);
+	ring_id_val |= OVERWRITE;
+
+	ring_id_buf = (ring->num << 9) & GENMASK(18, 9);
+	ring_id_buf |= PREFETCH_BUF_EN;
+	if (is_bufpool)
+		ring_id_buf |= IS_BUFFER_POOL;
+
+	xgene_enet_ring_wr32(ring, CSR_RING_ID, ring_id_val);
+	xgene_enet_ring_wr32(ring, CSR_RING_ID_BUF, ring_id_buf);
+}
+
+static void xgene_enet_clr_desc_ring_id(struct xgene_enet_desc_ring *ring)
+{
+	u32 ring_id;
+
+	ring_id = ring->id | OVERWRITE;
+	xgene_enet_ring_wr32(ring, CSR_RING_ID, ring_id);
+	xgene_enet_ring_wr32(ring, CSR_RING_ID_BUF, 0);
+}
+
+static struct xgene_enet_desc_ring *xgene_enet_setup_ring(
+				    struct xgene_enet_desc_ring *ring)
+{
+	bool is_bufpool;
+	u32 addr, i;
+
+	xgene_enet_clr_ring_state(ring);
+	xgene_enet_set_ring_state(ring);
+	xgene_enet_set_ring_id(ring);
+
+	ring->slots = xgene_enet_get_numslots(ring->id, ring->size);
+
+	is_bufpool = xgene_enet_is_bufpool(ring->id);
+	if (is_bufpool || xgene_enet_ring_owner(ring->id) != RING_OWNER_CPU)
+		return ring;
+
+	addr = CSR_VMID0_INTR_MBOX + (4 * (ring->id & RING_BUFNUM_MASK));
+	xgene_enet_ring_wr32(ring, addr, ring->irq_mbox_dma >> 10);
+
+	for (i = 0; i < ring->slots; i++)
+		xgene_enet_mark_desc_slot_empty(&ring->raw_desc[i]);
+
+	return ring;
+}
+
+static void xgene_enet_clear_ring(struct xgene_enet_desc_ring *ring)
+{
+	xgene_enet_clr_desc_ring_id(ring);
+	xgene_enet_clr_ring_state(ring);
+}
+
+static void xgene_enet_wr_cmd(struct xgene_enet_desc_ring *ring, int count)
+{
+	u32 data = 0;
+
+	if (xgene_enet_ring_owner(ring->id) == RING_OWNER_CPU) {
+		data = SET_VAL(X2_INTLINE, ring->id & RING_BUFNUM_MASK) |
+		       INTR_CLEAR;
+	}
+	data |= (count & GENMASK(16, 0));
+
+	iowrite32(data, ring->cmd);
+}
+
+static u32 xgene_enet_ring_len(struct xgene_enet_desc_ring *ring)
+{
+	u32 __iomem *cmd_base = ring->cmd_base;
+	u32 ring_state, num_msgs;
+
+	ring_state = ioread32(&cmd_base[1]);
+	num_msgs = GET_VAL(X2_NUMMSGSINQ, ring_state);
+
+	return num_msgs;
+}
+
+struct xgene_ring_ops xgene_ring2_ops = {
+	.num_ring_config = X2_NUM_RING_CONFIG,
+	.num_ring_id_shift = 13,
+	.setup = xgene_enet_setup_ring,
+	.clear = xgene_enet_clear_ring,
+	.wr_cmd = xgene_enet_wr_cmd,
+	.len = xgene_enet_ring_len,
+};
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h
new file mode 100644
index 000000000000..8b235db23c42
--- /dev/null
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ring2.h
@@ -0,0 +1,49 @@
+/* Applied Micro X-Gene SoC Ethernet Driver
+ *
+ * Copyright (c) 2015, Applied Micro Circuits Corporation
+ * Author: Iyappan Subramanian <isubramanian@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __XGENE_ENET_RING2_H__
+#define __XGENE_ENET_RING2_H__
+
+#include "xgene_enet_main.h"
+
+#define X2_NUM_RING_CONFIG	6
+
+#define INTR_MBOX_SIZE		1024
+#define CSR_VMID0_INTR_MBOX	0x0270
+#define INTR_CLEAR		BIT(23)
+
+#define X2_MSG_AM_POS		10
+#define X2_QBASE_AM_POS		11
+#define X2_INTLINE_POS		24
+#define X2_INTLINE_LEN		5
+#define X2_CFGCRID_POS		29
+#define X2_CFGCRID_LEN		3
+#define X2_SELTHRSH_POS		7
+#define X2_SELTHRSH_LEN		3
+#define X2_RINGTYPE_POS		23
+#define X2_RINGTYPE_LEN		2
+#define X2_DEQINTEN_POS		29
+#define X2_RECOMTIMEOUT_POS	0
+#define X2_RECOMTIMEOUT_LEN	7
+#define X2_NUMMSGSINQ_POS	0
+#define X2_NUMMSGSINQ_LEN	17
+
+extern struct xgene_ring_ops xgene_ring2_ops;
+
+#endif /* __XGENE_ENET_RING2_H__ */
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
index f27fb6f2a93b..05b817e56fde 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c
@@ -21,6 +21,7 @@
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
 #include "xgene_enet_sgmac.h"
+#include "xgene_enet_xgmac.h"
 
 static void xgene_enet_wr_csr(struct xgene_enet_pdata *p, u32 offset, u32 val)
 {
@@ -39,6 +40,14 @@ static void xgene_enet_wr_diag_csr(struct xgene_enet_pdata *p,
 	iowrite32(val, p->eth_diag_csr_addr + offset);
 }
 
+static void xgene_enet_wr_mcx_csr(struct xgene_enet_pdata *pdata,
+				  u32 offset, u32 val)
+{
+	void __iomem *addr = pdata->mcx_mac_csr_addr + offset;
+
+	iowrite32(val, addr);
+}
+
 static bool xgene_enet_wr_indirect(struct xgene_indirect_ctl *ctl,
 				   u32 wr_addr, u32 wr_data)
 {
@@ -140,8 +149,9 @@ static int xgene_enet_ecc_init(struct xgene_enet_pdata *p)
 
 static void xgene_enet_config_ring_if_assoc(struct xgene_enet_pdata *p)
 {
-	u32 val = 0xffffffff;
+	u32 val;
 
+	val = (p->enet_id == XGENE_ENET1) ? 0xffffffff : 0;
 	xgene_enet_wr_ring_if(p, ENET_CFGSSQMIWQASSOC_ADDR, val);
 	xgene_enet_wr_ring_if(p, ENET_CFGSSQMIFPQASSOC_ADDR, val);
 }
@@ -227,6 +237,8 @@ static void xgene_sgmac_init(struct xgene_enet_pdata *p)
 {
 	u32 data, loop = 10;
 	u32 offset = p->port_id * 4;
+	u32 enet_spare_cfg_reg, rsif_config_reg;
+	u32 cfg_bypass_reg, rx_dv_gate_reg;
 
 	xgene_sgmac_reset(p);
 
@@ -239,7 +251,7 @@ static void xgene_sgmac_init(struct xgene_enet_pdata *p)
 					  SGMII_STATUS_ADDR >> 2);
 		if ((data & AUTO_NEG_COMPLETE) && (data & LINK_STATUS))
 			break;
-		usleep_range(10, 20);
+		usleep_range(1000, 2000);
 	}
 	if (!(data & AUTO_NEG_COMPLETE) || !(data & LINK_STATUS))
 		netdev_err(p->ndev, "Auto-negotiation failed\n");
@@ -249,33 +261,38 @@ static void xgene_sgmac_init(struct xgene_enet_pdata *p)
 	xgene_enet_wr_mac(p, MAC_CONFIG_2_ADDR, data | FULL_DUPLEX2);
 	xgene_enet_wr_mac(p, INTERFACE_CONTROL_ADDR, ENET_GHD_MODE);
 
-	data = xgene_enet_rd_csr(p, ENET_SPARE_CFG_REG_ADDR);
+	if (p->enet_id == XGENE_ENET1) {
+		enet_spare_cfg_reg = ENET_SPARE_CFG_REG_ADDR;
+		rsif_config_reg = RSIF_CONFIG_REG_ADDR;
+		cfg_bypass_reg = CFG_BYPASS_ADDR;
+		rx_dv_gate_reg = SG_RX_DV_GATE_REG_0_ADDR;
+	} else {
+		enet_spare_cfg_reg = XG_ENET_SPARE_CFG_REG_ADDR;
+		rsif_config_reg = XG_RSIF_CONFIG_REG_ADDR;
+		cfg_bypass_reg = XG_CFG_BYPASS_ADDR;
+		rx_dv_gate_reg = XG_MCX_RX_DV_GATE_REG_0_ADDR;
+	}
+
+	data = xgene_enet_rd_csr(p, enet_spare_cfg_reg);
 	data |= MPA_IDLE_WITH_QMI_EMPTY;
-	xgene_enet_wr_csr(p, ENET_SPARE_CFG_REG_ADDR, data);
+	xgene_enet_wr_csr(p, enet_spare_cfg_reg, data);
 
 	xgene_sgmac_set_mac_addr(p);
 
-	data = xgene_enet_rd_csr(p, DEBUG_REG_ADDR);
-	data |= CFG_BYPASS_UNISEC_TX | CFG_BYPASS_UNISEC_RX;
-	xgene_enet_wr_csr(p, DEBUG_REG_ADDR, data);
-
 	/* Adjust MDC clock frequency */
 	data = xgene_enet_rd_mac(p, MII_MGMT_CONFIG_ADDR);
 	MGMT_CLOCK_SEL_SET(&data, 7);
 	xgene_enet_wr_mac(p, MII_MGMT_CONFIG_ADDR, data);
 
 	/* Enable drop if bufpool not available */
-	data = xgene_enet_rd_csr(p, RSIF_CONFIG_REG_ADDR);
+	data = xgene_enet_rd_csr(p, rsif_config_reg);
 	data |= CFG_RSIF_FPBUFF_TIMEOUT_EN;
-	xgene_enet_wr_csr(p, RSIF_CONFIG_REG_ADDR, data);
-
-	/* Rtype should be copied from FP */
-	xgene_enet_wr_csr(p, RSIF_RAM_DBG_REG0_ADDR, 0);
+	xgene_enet_wr_csr(p, rsif_config_reg, data);
 
 	/* Bypass traffic gating */
-	xgene_enet_wr_csr(p, CFG_LINK_AGGR_RESUME_0_ADDR + offset, TX_PORT0);
-	xgene_enet_wr_csr(p, CFG_BYPASS_ADDR, RESUME_TX);
-	xgene_enet_wr_csr(p, SG_RX_DV_GATE_REG_0_ADDR + offset, RESUME_RX0);
+	xgene_enet_wr_csr(p, XG_ENET_SPARE_CFG_REG_1_ADDR, 0x84);
+	xgene_enet_wr_csr(p, cfg_bypass_reg, RESUME_TX);
+	xgene_enet_wr_mcx_csr(p, rx_dv_gate_reg + offset, RESUME_RX0);
 }
 
 static void xgene_sgmac_rxtx(struct xgene_enet_pdata *p, u32 bits, bool set)
@@ -317,9 +334,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *p)
 	if (!xgene_ring_mgr_init(p))
 		return -ENODEV;
 
-	clk_prepare_enable(p->clk);
-	clk_disable_unprepare(p->clk);
-	clk_prepare_enable(p->clk);
+	if (!IS_ERR(p->clk)) {
+		clk_prepare_enable(p->clk);
+		clk_disable_unprepare(p->clk);
+		clk_prepare_enable(p->clk);
+	}
 
 	xgene_enet_ecc_init(p);
 	xgene_enet_config_ring_if_assoc(p);
@@ -331,19 +350,29 @@ static void xgene_enet_cle_bypass(struct xgene_enet_pdata *p,
 				  u32 dst_ring_num, u16 bufpool_id)
 {
 	u32 data, fpsel;
+	u32 cle_bypass_reg0, cle_bypass_reg1;
 	u32 offset = p->port_id * MAC_OFFSET;
 
+	if (p->enet_id == XGENE_ENET1) {
+		cle_bypass_reg0 = CLE_BYPASS_REG0_0_ADDR;
+		cle_bypass_reg1 = CLE_BYPASS_REG1_0_ADDR;
+	} else {
+		cle_bypass_reg0 = XCLE_BYPASS_REG0_ADDR;
+		cle_bypass_reg1 = XCLE_BYPASS_REG1_ADDR;
+	}
+
 	data = CFG_CLE_BYPASS_EN0;
-	xgene_enet_wr_csr(p, CLE_BYPASS_REG0_0_ADDR + offset, data);
+	xgene_enet_wr_csr(p, cle_bypass_reg0 + offset, data);
 
 	fpsel = xgene_enet_ring_bufnum(bufpool_id) - 0x20;
 	data = CFG_CLE_DSTQID0(dst_ring_num) | CFG_CLE_FPSEL0(fpsel);
-	xgene_enet_wr_csr(p, CLE_BYPASS_REG1_0_ADDR + offset, data);
+	xgene_enet_wr_csr(p, cle_bypass_reg1 + offset, data);
 }
 
 static void xgene_enet_shutdown(struct xgene_enet_pdata *p)
 {
-	clk_disable_unprepare(p->clk);
+	if (!IS_ERR(p->clk))
+		clk_disable_unprepare(p->clk);
 }
 
 static void xgene_enet_link_state(struct work_struct *work)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index a18a9d1f1143..05edb847cf26 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -122,7 +122,6 @@ static bool xgene_enet_rd_indirect(void __iomem *addr, void __iomem *rd,
 
 	return true;
 }
-
 static void xgene_enet_rd_mac(struct xgene_enet_pdata *pdata,
 			      u32 rd_addr, u32 *rd_data)
 {
@@ -257,9 +256,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata)
 	if (!xgene_ring_mgr_init(pdata))
 		return -ENODEV;
 
-	clk_prepare_enable(pdata->clk);
-	clk_disable_unprepare(pdata->clk);
-	clk_prepare_enable(pdata->clk);
+	if (!IS_ERR(pdata->clk)) {
+		clk_prepare_enable(pdata->clk);
+		clk_disable_unprepare(pdata->clk);
+		clk_prepare_enable(pdata->clk);
+	}
 
 	xgene_enet_ecc_init(pdata);
 	xgene_enet_config_ring_if_assoc(pdata);
@@ -286,7 +287,8 @@ static void xgene_enet_xgcle_bypass(struct xgene_enet_pdata *pdata,
 
 static void xgene_enet_shutdown(struct xgene_enet_pdata *pdata)
 {
-	clk_disable_unprepare(pdata->clk);
+	if (!IS_ERR(pdata->clk))
+		clk_disable_unprepare(pdata->clk);
 }
 
 static void xgene_enet_link_state(struct work_struct *work)
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
index 5a5296a6d1df..bf0a99435737 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.h
@@ -21,9 +21,28 @@
 #ifndef __XGENE_ENET_XGMAC_H__
 #define __XGENE_ENET_XGMAC_H__
 
+#define X2_BLOCK_ETH_MAC_CSR_OFFSET	0x3000
 #define BLOCK_AXG_MAC_OFFSET		0x0800
 #define BLOCK_AXG_MAC_CSR_OFFSET	0x2000
 
+#define XGENET_CONFIG_REG_ADDR		0x20
+#define XGENET_SRST_ADDR		0x00
+#define XGENET_CLKEN_ADDR		0x08
+
+#define CSR_CLK		BIT(0)
+#define XGENET_CLK	BIT(1)
+#define PCS_CLK		BIT(3)
+#define AN_REF_CLK	BIT(4)
+#define AN_CLK		BIT(5)
+#define AD_CLK		BIT(6)
+
+#define CSR_RST		BIT(0)
+#define XGENET_RST	BIT(1)
+#define PCS_RST		BIT(3)
+#define AN_REF_RST	BIT(4)
+#define AN_RST		BIT(5)
+#define AD_RST		BIT(6)
+
 #define AXGMAC_CONFIG_0			0x0000
 #define AXGMAC_CONFIG_1			0x0004
 #define HSTMACRST			BIT(31)
@@ -38,6 +57,7 @@
 #define HSTMACADR_MSW_ADDR		0x0014
 #define HSTMAXFRAME_LENGTH_ADDR		0x0020
 
+#define XG_MCX_RX_DV_GATE_REG_0_ADDR	0x0004
 #define XG_RSIF_CONFIG_REG_ADDR		0x00a0
 #define XCLE_BYPASS_REG0_ADDR           0x0160
 #define XCLE_BYPASS_REG1_ADDR           0x0164
diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig
index 1375e2dc9468..d19a41b0c6d2 100644
--- a/drivers/net/ethernet/apple/Kconfig
+++ b/drivers/net/ethernet/apple/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_APPLE
 	default y
 	depends on (PPC_PMAC && PPC32) || MAC
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -59,7 +57,6 @@ config MACMACE
 	---help---
 	  Support for the onboard AMD 79C940 MACE Ethernet controller used in
 	  the 660AV and 840AV Macintosh.  If you have one of these Macintoshes
-	  say Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  say Y here.
 
 endif # NET_VENDOR_APPLE
diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig
index dea29ee24da4..52a6b16f57d2 100644
--- a/drivers/net/ethernet/arc/Kconfig
+++ b/drivers/net/ethernet/arc/Kconfig
@@ -6,9 +6,7 @@ config NET_VENDOR_ARC
 	bool "ARC devices"
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/atheros/Kconfig b/drivers/net/ethernet/atheros/Kconfig
index 58ad37c733bc..e05b25675333 100644
--- a/drivers/net/ethernet/atheros/Kconfig
+++ b/drivers/net/ethernet/atheros/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_ATHEROS
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index a6f9142b9048..8be9eab73320 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -26,8 +26,7 @@ config B44
 	select PHYLIB
 	---help---
 	  If you have a network (Ethernet) controller of this type, say Y
-	  or M and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  or M here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called b44.
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 77363d680532..a3b1c07ae0af 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2464,6 +2464,7 @@ err_out_powerdown:
 	ssb_bus_may_powerdown(sdev->bus);
 
 err_out_free_dev:
+	netif_napi_del(&bp->napi);
 	free_netdev(dev);
 
 out:
@@ -2480,6 +2481,7 @@ static void b44_remove_one(struct ssb_device *sdev)
 		b44_unregister_phy_one(bp);
 	ssb_device_disable(sdev, 0);
 	ssb_bus_may_powerdown(sdev->bus);
+	netif_napi_del(&bp->napi);
 	free_netdev(dev);
 	ssb_pcihost_set_power_state(sdev, PCI_D3hot);
 	ssb_set_drvdata(sdev, NULL);
diff --git a/drivers/net/ethernet/broadcom/b44.h b/drivers/net/ethernet/broadcom/b44.h
index 3e9c3fc7591b..65d88d7c5581 100644
--- a/drivers/net/ethernet/broadcom/b44.h
+++ b/drivers/net/ethernet/broadcom/b44.h
@@ -1,6 +1,8 @@
 #ifndef _B44_H
 #define _B44_H
 
+#include <linux/brcmphy.h>
+
 /* Register layout. (These correspond to struct _bcmenettregs in bcm4400.) */
 #define	B44_DEVCTRL	0x0000UL /* Device Control */
 #define  DEVCTRL_MPM		0x00000040 /* Magic Packet PME Enable (B0 only) */
@@ -281,8 +283,10 @@ struct ring_info {
 };
 
 #define B44_MCAST_TABLE_SIZE		32
-#define B44_PHY_ADDR_NO_LOCAL_PHY	30 /* no local phy regs */
-#define B44_PHY_ADDR_NO_PHY		31 /* no phy present at all */
+/* no local phy regs, e.g: Broadcom switches pseudo-PHY */
+#define B44_PHY_ADDR_NO_LOCAL_PHY	BRCM_PSEUDO_PHY_ADDR
+/* no phy present at all */
+#define B44_PHY_ADDR_NO_PHY		31
 #define B44_MDC_RATIO			5000000
 
 #define	B44_STAT_REG_DECLARE		\
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 783543ad1fcf..909ad7a0d480 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -456,6 +456,67 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	return 0;
 }
 
+static int bcm_sysport_get_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u32 reg;
+
+	reg = tdma_readl(priv, TDMA_DESC_RING_INTR_CONTROL(0));
+
+	ec->tx_coalesce_usecs = (reg >> RING_TIMEOUT_SHIFT) * 8192 / 1000;
+	ec->tx_max_coalesced_frames = reg & RING_INTR_THRESH_MASK;
+
+	reg = rdma_readl(priv, RDMA_MBDONE_INTR);
+
+	ec->rx_coalesce_usecs = (reg >> RDMA_TIMEOUT_SHIFT) * 8192 / 1000;
+	ec->rx_max_coalesced_frames = reg & RDMA_INTR_THRESH_MASK;
+
+	return 0;
+}
+
+static int bcm_sysport_set_coalesce(struct net_device *dev,
+				    struct ethtool_coalesce *ec)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned int i;
+	u32 reg;
+
+	/* Base system clock is 125Mhz, DMA timeout is this reference clock
+	 * divided by 1024, which yield roughly 8.192 us, our maximum value has
+	 * to fit in the RING_TIMEOUT_MASK (16 bits).
+	 */
+	if (ec->tx_max_coalesced_frames > RING_INTR_THRESH_MASK ||
+	    ec->tx_coalesce_usecs > (RING_TIMEOUT_MASK * 8) + 1 ||
+	    ec->rx_max_coalesced_frames > RDMA_INTR_THRESH_MASK ||
+	    ec->rx_coalesce_usecs > (RDMA_TIMEOUT_MASK * 8) + 1)
+		return -EINVAL;
+
+	if ((ec->tx_coalesce_usecs == 0 && ec->tx_max_coalesced_frames == 0) ||
+	    (ec->rx_coalesce_usecs == 0 && ec->rx_max_coalesced_frames == 0))
+		return -EINVAL;
+
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		reg = tdma_readl(priv, TDMA_DESC_RING_INTR_CONTROL(i));
+		reg &= ~(RING_INTR_THRESH_MASK |
+			 RING_TIMEOUT_MASK << RING_TIMEOUT_SHIFT);
+		reg |= ec->tx_max_coalesced_frames;
+		reg |= DIV_ROUND_UP(ec->tx_coalesce_usecs * 1000, 8192) <<
+			 RING_TIMEOUT_SHIFT;
+		tdma_writel(priv, reg, TDMA_DESC_RING_INTR_CONTROL(i));
+	}
+
+	reg = rdma_readl(priv, RDMA_MBDONE_INTR);
+	reg &= ~(RDMA_INTR_THRESH_MASK |
+		 RDMA_TIMEOUT_MASK << RDMA_TIMEOUT_SHIFT);
+	reg |= ec->rx_max_coalesced_frames;
+	reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192) <<
+			    RDMA_TIMEOUT_SHIFT;
+	rdma_writel(priv, reg, RDMA_MBDONE_INTR);
+
+	return 0;
+}
+
 static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 {
 	dev_kfree_skb_any(cb->skb);
@@ -463,67 +524,70 @@ static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
 	dma_unmap_addr_set(cb, dma_addr, 0);
 }
 
-static int bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
-				 struct bcm_sysport_cb *cb)
+static struct sk_buff *bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
+					     struct bcm_sysport_cb *cb)
 {
 	struct device *kdev = &priv->pdev->dev;
 	struct net_device *ndev = priv->netdev;
+	struct sk_buff *skb, *rx_skb;
 	dma_addr_t mapping;
-	int ret;
 
-	cb->skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
-	if (!cb->skb) {
+	/* Allocate a new SKB for a new packet */
+	skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
+	if (!skb) {
+		priv->mib.alloc_rx_buff_failed++;
 		netif_err(priv, rx_err, ndev, "SKB alloc failed\n");
-		return -ENOMEM;
+		return NULL;
 	}
 
-	mapping = dma_map_single(kdev, cb->skb->data,
+	mapping = dma_map_single(kdev, skb->data,
 				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
-	ret = dma_mapping_error(kdev, mapping);
-	if (ret) {
+	if (dma_mapping_error(kdev, mapping)) {
 		priv->mib.rx_dma_failed++;
-		bcm_sysport_free_cb(cb);
+		dev_kfree_skb_any(skb);
 		netif_err(priv, rx_err, ndev, "DMA mapping failure\n");
-		return ret;
+		return NULL;
 	}
 
-	dma_unmap_addr_set(cb, dma_addr, mapping);
-	dma_desc_set_addr(priv, priv->rx_bd_assign_ptr, mapping);
+	/* Grab the current SKB on the ring */
+	rx_skb = cb->skb;
+	if (likely(rx_skb))
+		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
+				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
 
-	priv->rx_bd_assign_index++;
-	priv->rx_bd_assign_index &= (priv->num_rx_bds - 1);
-	priv->rx_bd_assign_ptr = priv->rx_bds +
-		(priv->rx_bd_assign_index * DESC_SIZE);
+	/* Put the new SKB on the ring */
+	cb->skb = skb;
+	dma_unmap_addr_set(cb, dma_addr, mapping);
+	dma_desc_set_addr(priv, cb->bd_addr, mapping);
 
 	netif_dbg(priv, rx_status, ndev, "RX refill\n");
 
-	return 0;
+	/* Return the current SKB to the caller */
+	return rx_skb;
 }
 
 static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv)
 {
 	struct bcm_sysport_cb *cb;
-	int ret = 0;
+	struct sk_buff *skb;
 	unsigned int i;
 
 	for (i = 0; i < priv->num_rx_bds; i++) {
-		cb = &priv->rx_cbs[priv->rx_bd_assign_index];
-		if (cb->skb)
-			continue;
-
-		ret = bcm_sysport_rx_refill(priv, cb);
-		if (ret)
-			break;
+		cb = &priv->rx_cbs[i];
+		skb = bcm_sysport_rx_refill(priv, cb);
+		if (skb)
+			dev_kfree_skb(skb);
+		if (!cb->skb)
+			return -ENOMEM;
 	}
 
-	return ret;
+	return 0;
 }
 
 /* Poll the hardware for up to budget packets to process */
 static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 					unsigned int budget)
 {
-	struct device *kdev = &priv->pdev->dev;
 	struct net_device *ndev = priv->netdev;
 	unsigned int processed = 0, to_process;
 	struct bcm_sysport_cb *cb;
@@ -531,7 +595,6 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 	unsigned int p_index;
 	u16 len, status;
 	struct bcm_rsb *rsb;
-	int ret;
 
 	/* Determine how much we should process since last call */
 	p_index = rdma_readl(priv, RDMA_PROD_INDEX);
@@ -549,13 +612,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 
 	while ((processed < to_process) && (processed < budget)) {
 		cb = &priv->rx_cbs[priv->rx_read_ptr];
-		skb = cb->skb;
+		skb = bcm_sysport_rx_refill(priv, cb);
 
-		processed++;
-		priv->rx_read_ptr++;
-
-		if (priv->rx_read_ptr == priv->num_rx_bds)
-			priv->rx_read_ptr = 0;
 
 		/* We do not have a backing SKB, so we do not a corresponding
 		 * DMA mapping for this incoming packet since
@@ -566,12 +624,9 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 			netif_err(priv, rx_err, ndev, "out of memory!\n");
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			goto refill;
+			goto next;
 		}
 
-		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
-				 RX_BUF_LENGTH, DMA_FROM_DEVICE);
-
 		/* Extract the Receive Status Block prepended */
 		rsb = (struct bcm_rsb *)skb->data;
 		len = (rsb->rx_status_len >> DESC_LEN_SHIFT) & DESC_LEN_MASK;
@@ -583,12 +638,20 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 			  p_index, priv->rx_c_index, priv->rx_read_ptr,
 			  len, status);
 
+		if (unlikely(len > RX_BUF_LENGTH)) {
+			netif_err(priv, rx_status, ndev, "oversized packet\n");
+			ndev->stats.rx_length_errors++;
+			ndev->stats.rx_errors++;
+			dev_kfree_skb_any(skb);
+			goto next;
+		}
+
 		if (unlikely(!(status & DESC_EOP) || !(status & DESC_SOP))) {
 			netif_err(priv, rx_status, ndev, "fragmented packet!\n");
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			bcm_sysport_free_cb(cb);
-			goto refill;
+			dev_kfree_skb_any(skb);
+			goto next;
 		}
 
 		if (unlikely(status & (RX_STATUS_ERR | RX_STATUS_OVFLOW))) {
@@ -597,8 +660,8 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 				ndev->stats.rx_over_errors++;
 			ndev->stats.rx_dropped++;
 			ndev->stats.rx_errors++;
-			bcm_sysport_free_cb(cb);
-			goto refill;
+			dev_kfree_skb_any(skb);
+			goto next;
 		}
 
 		skb_put(skb, len);
@@ -625,10 +688,12 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
 		ndev->stats.rx_bytes += len;
 
 		napi_gro_receive(&priv->napi, skb);
-refill:
-		ret = bcm_sysport_rx_refill(priv, cb);
-		if (ret)
-			priv->mib.alloc_rx_buff_failed++;
+next:
+		processed++;
+		priv->rx_read_ptr++;
+
+		if (priv->rx_read_ptr == priv->num_rx_bds)
+			priv->rx_read_ptr = 0;
 	}
 
 	return processed;
@@ -1269,14 +1334,14 @@ static inline int tdma_enable_set(struct bcm_sysport_priv *priv,
 
 static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv)
 {
+	struct bcm_sysport_cb *cb;
 	u32 reg;
 	int ret;
+	int i;
 
 	/* Initialize SW view of the RX ring */
 	priv->num_rx_bds = NUM_RX_DESC;
 	priv->rx_bds = priv->base + SYS_PORT_RDMA_OFFSET;
-	priv->rx_bd_assign_ptr = priv->rx_bds;
-	priv->rx_bd_assign_index = 0;
 	priv->rx_c_index = 0;
 	priv->rx_read_ptr = 0;
 	priv->rx_cbs = kcalloc(priv->num_rx_bds, sizeof(struct bcm_sysport_cb),
@@ -1286,6 +1351,11 @@ static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv)
 		return -ENOMEM;
 	}
 
+	for (i = 0; i < priv->num_rx_bds; i++) {
+		cb = priv->rx_cbs + i;
+		cb->bd_addr = priv->rx_bds + i * DESC_SIZE;
+	}
+
 	ret = bcm_sysport_alloc_rx_bufs(priv);
 	if (ret) {
 		netif_err(priv, hw, priv->netdev, "SKB allocation failed\n");
@@ -1641,6 +1711,8 @@ static struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.get_sset_count		= bcm_sysport_get_sset_count,
 	.get_wol		= bcm_sysport_get_wol,
 	.set_wol		= bcm_sysport_set_wol,
+	.get_coalesce		= bcm_sysport_get_coalesce,
+	.set_coalesce		= bcm_sysport_set_coalesce,
 };
 
 static const struct net_device_ops bcm_sysport_netdev_ops = {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index e2c043eabbf3..f28bf545d7f4 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -292,7 +292,7 @@ struct bcm_rsb {
 #define RDMA_END_ADDR_LO		0x102c
 
 #define RDMA_MBDONE_INTR		0x1030
-#define  RDMA_INTR_THRESH_MASK		0xff
+#define  RDMA_INTR_THRESH_MASK		0x1ff
 #define  RDMA_TIMEOUT_SHIFT		16
 #define  RDMA_TIMEOUT_MASK		0xffff
 
@@ -663,8 +663,6 @@ struct bcm_sysport_priv {
 
 	/* Receive queue */
 	void __iomem		*rx_bds;
-	void __iomem		*rx_bd_assign_ptr;
-	unsigned int		rx_bd_assign_index;
 	struct bcm_sysport_cb	*rx_cbs;
 	unsigned int		num_rx_bds;
 	unsigned int		rx_read_ptr;
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index db27febbb215..4fbb093e0d84 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -13,6 +13,7 @@
 	dev_dbg(&(bgmac)->core->dev, fmt, ##__VA_ARGS__)
 
 #include <linux/bcma/bcma.h>
+#include <linux/brcmphy.h>
 #include <linux/netdevice.h>
 
 #define BGMAC_DEV_CTL				0x000
@@ -349,7 +350,7 @@
 #define BGMAC_DESC_CTL0_SOF			0x80000000	/* Start of frame */
 #define BGMAC_DESC_CTL1_LEN			0x00001FFF
 
-#define BGMAC_PHY_NOREGS			0x1E
+#define BGMAC_PHY_NOREGS			BRCM_PSEUDO_PHY_ADDR
 #define BGMAC_PHY_MASK				0x1F
 
 #define BGMAC_MAX_TX_RINGS			4
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index a3b0f7a0c61e..7a4aaa3c01b6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -357,6 +357,7 @@ struct sw_tx_bd {
 struct sw_rx_page {
 	struct page	*page;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
+	unsigned int	offset;
 };
 
 union db_prod {
@@ -381,9 +382,10 @@ union db_prod {
 
 #define PAGES_PER_SGE_SHIFT	0
 #define PAGES_PER_SGE		(1 << PAGES_PER_SGE_SHIFT)
-#define SGE_PAGE_SIZE		PAGE_SIZE
-#define SGE_PAGE_SHIFT		PAGE_SHIFT
-#define SGE_PAGE_ALIGN(addr)	PAGE_ALIGN((typeof(PAGE_SIZE))(addr))
+#define SGE_PAGE_SHIFT		12
+#define SGE_PAGE_SIZE		(1 << SGE_PAGE_SHIFT)
+#define SGE_PAGE_MASK		(~(SGE_PAGE_SIZE - 1))
+#define SGE_PAGE_ALIGN(addr)	(((addr) + SGE_PAGE_SIZE - 1) & SGE_PAGE_MASK)
 #define SGE_PAGES		(SGE_PAGE_SIZE * PAGES_PER_SGE)
 #define TPA_AGG_SIZE		min_t(u32, (min_t(u32, 8, MAX_SKB_FRAGS) * \
 					    SGE_PAGES), 0xffff)
@@ -526,6 +528,12 @@ enum bnx2x_tpa_mode_t {
 	TPA_MODE_GRO
 };
 
+struct bnx2x_alloc_pool {
+	struct page	*page;
+	dma_addr_t	dma;
+	unsigned int	offset;
+};
+
 struct bnx2x_fastpath {
 	struct bnx2x		*bp; /* parent */
 
@@ -599,6 +607,8 @@ struct bnx2x_fastpath {
 	     4 (for the digits and to make it DWORD aligned) */
 #define FP_NAME_SIZE		(sizeof(((struct net_device *)0)->name) + 8)
 	char			name[FP_NAME_SIZE];
+
+	struct bnx2x_alloc_pool	page_pool;
 };
 
 #define bnx2x_fp(bp, nr, var)	((bp)->fp[(nr)].var)
@@ -1774,7 +1784,7 @@ struct bnx2x {
 	int			stats_state;
 
 	/* used for synchronization of concurrent threads statistics handling */
-	struct mutex		stats_lock;
+	struct semaphore	stats_lock;
 
 	/* used by dmae command loader */
 	struct dmae_command	stats_dmae;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a8bb8f664d3d..e2a65334708d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -544,30 +544,49 @@ static void bnx2x_set_gro_params(struct sk_buff *skb, u16 parsing_flags,
 static int bnx2x_alloc_rx_sge(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 			      u16 index, gfp_t gfp_mask)
 {
-	struct page *page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT);
 	struct sw_rx_page *sw_buf = &fp->rx_page_ring[index];
 	struct eth_rx_sge *sge = &fp->rx_sge_ring[index];
+	struct bnx2x_alloc_pool *pool = &fp->page_pool;
 	dma_addr_t mapping;
 
-	if (unlikely(page == NULL)) {
-		BNX2X_ERR("Can't alloc sge\n");
-		return -ENOMEM;
-	}
+	if (!pool->page || (PAGE_SIZE - pool->offset) < SGE_PAGE_SIZE) {
 
-	mapping = dma_map_page(&bp->pdev->dev, page, 0,
-			       SGE_PAGES, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
-		__free_pages(page, PAGES_PER_SGE_SHIFT);
-		BNX2X_ERR("Can't map sge\n");
-		return -ENOMEM;
+		/* put page reference used by the memory pool, since we
+		 * won't be using this page as the mempool anymore.
+		 */
+		if (pool->page)
+			put_page(pool->page);
+
+		pool->page = alloc_pages(gfp_mask, PAGES_PER_SGE_SHIFT);
+		if (unlikely(!pool->page)) {
+			BNX2X_ERR("Can't alloc sge\n");
+			return -ENOMEM;
+		}
+
+		pool->dma = dma_map_page(&bp->pdev->dev, pool->page, 0,
+					 PAGE_SIZE, DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(&bp->pdev->dev,
+					       pool->dma))) {
+			__free_pages(pool->page, PAGES_PER_SGE_SHIFT);
+			pool->page = NULL;
+			BNX2X_ERR("Can't map sge\n");
+			return -ENOMEM;
+		}
+		pool->offset = 0;
 	}
 
-	sw_buf->page = page;
+	get_page(pool->page);
+	sw_buf->page = pool->page;
+	sw_buf->offset = pool->offset;
+
+	mapping = pool->dma + sw_buf->offset;
 	dma_unmap_addr_set(sw_buf, mapping, mapping);
 
 	sge->addr_hi = cpu_to_le32(U64_HI(mapping));
 	sge->addr_lo = cpu_to_le32(U64_LO(mapping));
 
+	pool->offset += SGE_PAGE_SIZE;
+
 	return 0;
 }
 
@@ -629,20 +648,22 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 			return err;
 		}
 
-		/* Unmap the page as we're going to pass it to the stack */
-		dma_unmap_page(&bp->pdev->dev,
-			       dma_unmap_addr(&old_rx_pg, mapping),
-			       SGE_PAGES, DMA_FROM_DEVICE);
+		dma_unmap_single(&bp->pdev->dev,
+				 dma_unmap_addr(&old_rx_pg, mapping),
+				 SGE_PAGE_SIZE, DMA_FROM_DEVICE);
 		/* Add one frag and update the appropriate fields in the skb */
 		if (fp->mode == TPA_MODE_LRO)
-			skb_fill_page_desc(skb, j, old_rx_pg.page, 0, frag_len);
+			skb_fill_page_desc(skb, j, old_rx_pg.page,
+					   old_rx_pg.offset, frag_len);
 		else { /* GRO */
 			int rem;
 			int offset = 0;
 			for (rem = frag_len; rem > 0; rem -= gro_size) {
 				int len = rem > gro_size ? gro_size : rem;
 				skb_fill_page_desc(skb, frag_id++,
-						   old_rx_pg.page, offset, len);
+						   old_rx_pg.page,
+						   old_rx_pg.offset + offset,
+						   len);
 				if (offset)
 					get_page(old_rx_pg.page);
 				offset += len;
@@ -662,7 +683,7 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 static void bnx2x_frag_free(const struct bnx2x_fastpath *fp, void *data)
 {
 	if (fp->rx_frag_size)
-		put_page(virt_to_head_page(data));
+		skb_free_frag(data);
 	else
 		kfree(data);
 }
@@ -4786,6 +4807,11 @@ int bnx2x_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
+	if (pci_num_vf(bp->pdev)) {
+		DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n");
+		return -EPERM;
+	}
+
 	if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
 		BNX2X_ERR("Can't perform change MTU during parity recovery\n");
 		return -EAGAIN;
@@ -4938,11 +4964,6 @@ int bnx2x_resume(struct pci_dev *pdev)
 	}
 	bp = netdev_priv(dev);
 
-	if (pci_num_vf(bp->pdev)) {
-		DP(BNX2X_MSG_IOV, "VFs are enabled, can not change MTU\n");
-		return -EPERM;
-	}
-
 	if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
 		BNX2X_ERR("Handling parity error recovery. Try again later\n");
 		return -EAGAIN;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index d7a71758e876..2b30081ec26d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -804,9 +804,13 @@ static inline void bnx2x_free_rx_sge(struct bnx2x *bp,
 	if (!page)
 		return;
 
-	dma_unmap_page(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
-		       SGE_PAGES, DMA_FROM_DEVICE);
-	__free_pages(page, PAGES_PER_SGE_SHIFT);
+	/* Since many fragments can share the same page, make sure to
+	 * only unmap and free the page once.
+	 */
+	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(sw_buf, mapping),
+			 SGE_PAGE_SIZE, DMA_FROM_DEVICE);
+
+	put_page(page);
 
 	sw_buf->page = NULL;
 	sge->addr_hi = 0;
@@ -964,6 +968,25 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
 	((u8 *)fw_lo)[1]  = mac[4];
 }
 
+static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp,
+					  struct bnx2x_alloc_pool *pool)
+{
+	if (!pool->page)
+		return;
+
+	/* Page was not fully fragmented.  Unmap unused space */
+	if (pool->offset < PAGE_SIZE) {
+		dma_addr_t dma = pool->dma + pool->offset;
+		int size = PAGE_SIZE - pool->offset;
+
+		dma_unmap_single(&bp->pdev->dev, dma, size, DMA_FROM_DEVICE);
+	}
+
+	put_page(pool->page);
+
+	pool->page = NULL;
+}
+
 static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 					   struct bnx2x_fastpath *fp, int last)
 {
@@ -974,6 +997,8 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 
 	for (i = 0; i < last; i++)
 		bnx2x_free_rx_sge(bp, fp, i);
+
+	bnx2x_free_rx_mem_pool(bp, &fp->page_pool);
 }
 
 static inline void bnx2x_set_next_page_rx_bd(struct bnx2x_fastpath *fp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 556dcc162a62..33501bcddc48 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12054,7 +12054,7 @@ static int bnx2x_init_bp(struct bnx2x *bp)
 	mutex_init(&bp->port.phy_mutex);
 	mutex_init(&bp->fw_mb_mutex);
 	mutex_init(&bp->drv_info_mutex);
-	mutex_init(&bp->stats_lock);
+	sema_init(&bp->stats_lock, 1);
 	bp->drv_info_mng_owner = false;
 
 	INIT_DELAYED_WORK(&bp->sp_task, bnx2x_sp_task);
@@ -13371,8 +13371,13 @@ static int bnx2x_init_one(struct pci_dev *pdev,
 	/* Management FW 'remembers' living interfaces. Allow it some time
 	 * to forget previously living interfaces, allowing a proper re-load.
 	 */
-	if (is_kdump_kernel())
-		msleep(5000);
+	if (is_kdump_kernel()) {
+		ktime_t now = ktime_get_boottime();
+		ktime_t fw_ready_time = ktime_set(5, 0);
+
+		if (ktime_before(now, fw_ready_time))
+			msleep(ktime_ms_delta(fw_ready_time, now));
+	}
 
 	/* An estimated maximum supported CoS number according to the chip
 	 * version.
@@ -13685,9 +13690,10 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
 	cancel_delayed_work_sync(&bp->sp_task);
 	cancel_delayed_work_sync(&bp->period_task);
 
-	mutex_lock(&bp->stats_lock);
-	bp->stats_state = STATS_STATE_DISABLED;
-	mutex_unlock(&bp->stats_lock);
+	if (!down_timeout(&bp->stats_lock, HZ / 10)) {
+		bp->stats_state = STATS_STATE_DISABLED;
+		up(&bp->stats_lock);
+	}
 
 	bnx2x_save_statistics(bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 266b055c2360..69d699f0730a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -1372,19 +1372,23 @@ void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event)
 	 * that context in case someone is in the middle of a transition.
 	 * For other events, wait a bit until lock is taken.
 	 */
-	if (!mutex_trylock(&bp->stats_lock)) {
+	if (down_trylock(&bp->stats_lock)) {
 		if (event == STATS_EVENT_UPDATE)
 			return;
 
 		DP(BNX2X_MSG_STATS,
 		   "Unlikely stats' lock contention [event %d]\n", event);
-		mutex_lock(&bp->stats_lock);
+		if (unlikely(down_timeout(&bp->stats_lock, HZ / 10))) {
+			BNX2X_ERR("Failed to take stats lock [event %d]\n",
+				  event);
+			return;
+		}
 	}
 
 	bnx2x_stats_stm[state][event].action(bp);
 	bp->stats_state = bnx2x_stats_stm[state][event].next_state;
 
-	mutex_unlock(&bp->stats_lock);
+	up(&bp->stats_lock);
 
 	if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
 		DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
@@ -1970,7 +1974,11 @@ int bnx2x_stats_safe_exec(struct bnx2x *bp,
 	/* Wait for statistics to end [while blocking further requests],
 	 * then run supplied function 'safely'.
 	 */
-	mutex_lock(&bp->stats_lock);
+	rc = down_timeout(&bp->stats_lock, HZ / 10);
+	if (unlikely(rc)) {
+		BNX2X_ERR("Failed to take statistics lock for safe execution\n");
+		goto out_no_lock;
+	}
 
 	bnx2x_stats_comp(bp);
 	while (bp->stats_pending && cnt--)
@@ -1988,7 +1996,7 @@ out:
 	/* No need to restart statistics - if they're enabled, the timer
 	 * will restart the statistics.
 	 */
-	mutex_unlock(&bp->stats_lock);
-
+	up(&bp->stats_lock);
+out_no_lock:
 	return rc;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 6043734ea613..b43b2cb9b830 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2770,12 +2770,79 @@ static int bcmgenet_close(struct net_device *dev)
 	return ret;
 }
 
+static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
+{
+	struct bcmgenet_priv *priv = ring->priv;
+	u32 p_index, c_index, intsts, intmsk;
+	struct netdev_queue *txq;
+	unsigned int free_bds;
+	unsigned long flags;
+	bool txq_stopped;
+
+	if (!netif_msg_tx_err(priv))
+		return;
+
+	txq = netdev_get_tx_queue(priv->dev, ring->queue);
+
+	spin_lock_irqsave(&ring->lock, flags);
+	if (ring->index == DESC_INDEX) {
+		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
+		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
+	} else {
+		intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
+		intmsk = 1 << ring->index;
+	}
+	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
+	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
+	txq_stopped = netif_tx_queue_stopped(txq);
+	free_bds = ring->free_bds;
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	netif_err(priv, tx_err, priv->dev, "Ring %d queue %d status summary\n"
+		  "TX queue status: %s, interrupts: %s\n"
+		  "(sw)free_bds: %d (sw)size: %d\n"
+		  "(sw)p_index: %d (hw)p_index: %d\n"
+		  "(sw)c_index: %d (hw)c_index: %d\n"
+		  "(sw)clean_p: %d (sw)write_p: %d\n"
+		  "(sw)cb_ptr: %d (sw)end_ptr: %d\n",
+		  ring->index, ring->queue,
+		  txq_stopped ? "stopped" : "active",
+		  intsts & intmsk ? "enabled" : "disabled",
+		  free_bds, ring->size,
+		  ring->prod_index, p_index & DMA_P_INDEX_MASK,
+		  ring->c_index, c_index & DMA_C_INDEX_MASK,
+		  ring->clean_ptr, ring->write_ptr,
+		  ring->cb_ptr, ring->end_ptr);
+}
+
 static void bcmgenet_timeout(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	u32 int0_enable = 0;
+	u32 int1_enable = 0;
+	unsigned int q;
 
 	netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n");
 
+	bcmgenet_disable_tx_napi(priv);
+
+	for (q = 0; q < priv->hw_params->tx_queues; q++)
+		bcmgenet_dump_tx_queue(&priv->tx_rings[q]);
+	bcmgenet_dump_tx_queue(&priv->tx_rings[DESC_INDEX]);
+
+	bcmgenet_tx_reclaim_all(dev);
+
+	for (q = 0; q < priv->hw_params->tx_queues; q++)
+		int1_enable |= (1 << q);
+
+	int0_enable = UMAC_IRQ_TXDMA_DONE;
+
+	/* Re-enable TX interrupts if disabled */
+	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
+
+	bcmgenet_enable_tx_napi(priv);
+
 	dev->trans_start = jiffies;
 
 	dev->stats.tx_errors++;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e7651b3c6c57..6bef04e2f735 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -47,7 +47,12 @@ static int bcmgenet_mii_read(struct mii_bus *bus, int phy_id, int location)
 			   HZ / 100);
 	ret = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD);
 
-	if (ret & MDIO_READ_FAIL)
+	/* Some broken devices are known not to release the line during
+	 * turn-around, e.g: Broadcom BCM53125 external switches, so check for
+	 * that condition here and ignore the MDIO controller read failure
+	 * indication.
+	 */
+	if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (ret & MDIO_READ_FAIL))
 		return -EIO;
 
 	return ret & 0xffff;
@@ -299,9 +304,6 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 			phy_name = "external RGMII (no delay)";
 		else
 			phy_name = "external RGMII (TX delay)";
-		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
-		reg |= RGMII_MODE_EN | id_mode_dis;
-		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 		bcmgenet_sys_writel(priv,
 				    PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
 		break;
@@ -310,6 +312,15 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		return -EINVAL;
 	}
 
+	/* This is an external PHY (xMII), so we need to enable the RGMII
+	 * block for the interface to work
+	 */
+	if (priv->ext_phy) {
+		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
+		reg |= RGMII_MODE_EN | id_mode_dis;
+		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+	}
+
 	if (init)
 		dev_info(kdev, "configuring instance for %s\n", phy_name);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 069952fa5d64..73c934cf6c61 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6618,7 +6618,7 @@ static void tg3_tx(struct tg3_napi *tnapi)
 static void tg3_frag_free(bool is_frag, void *data)
 {
 	if (is_frag)
-		put_page(virt_to_head_page(data));
+		skb_free_frag(data);
 	else
 		kfree(data);
 }
diff --git a/drivers/net/ethernet/brocade/Kconfig b/drivers/net/ethernet/brocade/Kconfig
index 4e8c0b6c57d0..c4bbe54e2cad 100644
--- a/drivers/net/ethernet/brocade/Kconfig
+++ b/drivers/net/ethernet/brocade/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_BROCADE
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/brocade/bna/Makefile b/drivers/net/ethernet/brocade/bna/Makefile
index 6e10b99733a2..8584abcf5366 100644
--- a/drivers/net/ethernet/brocade/bna/Makefile
+++ b/drivers/net/ethernet/brocade/bna/Makefile
@@ -9,5 +9,3 @@ obj-$(CONFIG_BNA) += bna.o
 bna-objs := bnad.o bnad_ethtool.o bnad_debugfs.o bna_enet.o bna_tx_rx.o
 bna-objs += bfa_msgq.o bfa_ioc.o bfa_ioc_ct.o bfa_cee.o
 bna-objs += cna_fwimg.o
-
-EXTRA_CFLAGS := -Idrivers/net/bna
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c
index cf9f3956f198..95bc8b644a5d 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cee.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c
@@ -282,7 +282,6 @@ bfa_nw_cee_attach(struct bfa_cee *cee, struct bfa_ioc *ioc,
 	cee->ioc = ioc;
 
 	bfa_nw_ioc_mbox_regisr(cee->ioc, BFI_MC_CEE, bfa_cee_isr, cee);
-	bfa_q_qe_init(&cee->ioc_notify);
 	bfa_ioc_notify_init(&cee->ioc_notify, bfa_cee_notify, cee);
 	bfa_nw_ioc_notify_register(cee->ioc, &cee->ioc_notify);
 }
diff --git a/drivers/net/ethernet/brocade/bna/bfa_cs.h b/drivers/net/ethernet/brocade/bna/bfa_cs.h
index af25d8e8fae0..1d11d666d408 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_cs.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_cs.h
@@ -28,19 +28,6 @@
 
 typedef void (*bfa_sm_t)(void *sm, int event);
 
-/* oc - object class eg. bfa_ioc
- * st - state, eg. reset
- * otype - object type, eg. struct bfa_ioc
- * etype - object type, eg. enum ioc_event
- */
-#define bfa_sm_state_decl(oc, st, otype, etype)			\
-	static void oc ## _sm_ ## st(otype * fsm, etype event)
-
-#define bfa_sm_set_state(_sm, _state)	((_sm)->sm = (bfa_sm_t)(_state))
-#define bfa_sm_send_event(_sm, _event)	((_sm)->sm((_sm), (_event)))
-#define bfa_sm_get_state(_sm)		((_sm)->sm)
-#define bfa_sm_cmp_state(_sm, _state)	((_sm)->sm == (bfa_sm_t)(_state))
-
 /* For converting from state machine function to state encoding. */
 struct bfa_sm_table {
 	bfa_sm_t	sm;	/*!< state machine function	*/
@@ -67,7 +54,6 @@ typedef void (*bfa_fsm_t)(void *fsm, int event);
 } while (0)
 
 #define bfa_fsm_send_event(_fsm, _event)	((_fsm)->fsm((_fsm), (_event)))
-#define bfa_fsm_get_state(_fsm)			((_fsm)->fsm)
 #define bfa_fsm_cmp_state(_fsm, _state)					\
 	((_fsm)->fsm == (bfa_fsm_t)(_state))
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs.h b/drivers/net/ethernet/brocade/bna/bfa_defs.h
index 3bfd9da92630..d152b3fa6c54 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs.h
@@ -24,7 +24,6 @@
 #include "bfa_defs_status.h"
 #include "bfa_defs_mfg_comm.h"
 
-#define BFA_STRING_32	32
 #define BFA_VERSION_LEN 64
 
 /* ---------------------- adapter definitions ------------ */
@@ -55,7 +54,7 @@ struct bfa_adapter_attr {
 	char		optrom_ver[BFA_VERSION_LEN];
 	char		os_type[BFA_ADAPTER_OS_TYPE_LEN];
 	struct bfa_mfg_vpd vpd;
-	struct mac mac;
+	u8		mac[ETH_ALEN];
 
 	u8		nports;
 	u8		max_speed;
@@ -187,8 +186,6 @@ enum {
 #define BFA_MFG_SUPPLIER_SERIALNUM_SIZE		20
 #define BFA_MFG_SUPPLIER_REVISION_SIZE		4
 
-#pragma pack(1)
-
 /* BFA adapter manufacturing block definition.
  *
  * All numerical fields are in big-endian format.
@@ -211,7 +208,7 @@ struct bfa_mfg_block {
 	char	supplier_partnum[STRSZ(BFA_MFG_SUPPLIER_PARTNUM_SIZE)];
 	char	supplier_serialnum[STRSZ(BFA_MFG_SUPPLIER_SERIALNUM_SIZE)];
 	char	supplier_revision[STRSZ(BFA_MFG_SUPPLIER_REVISION_SIZE)];
-	mac_t	mfg_mac;	/* base mac address */
+	u8	mfg_mac[ETH_ALEN]; /* base mac address */
 	u8	num_mac;	/* number of mac addresses */
 	u8	rsv2;
 	u32	card_type;	/* card type          */
@@ -227,9 +224,7 @@ struct bfa_mfg_block {
 	char	initial_mode[8]; /* initial mode: hba/cna/nic */
 	u8	rsv4[84];
 	u8	md5_chksum[BFA_MFG_CHKSUM_SIZE]; /* md5 checksum */
-};
-
-#pragma pack()
+} __packed;
 
 /* ---------------------- pci definitions ------------ */
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h b/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
index a37326d44fbb..f048887cbb81 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs_cna.h
@@ -109,8 +109,6 @@ union bfa_port_stats_u {
 	struct bfa_port_eth_stats eth;
 };
 
-#pragma pack(1)
-
 #define BFA_CEE_LLDP_MAX_STRING_LEN (128)
 #define BFA_CEE_DCBX_MAX_PRIORITY	(8)
 #define BFA_CEE_DCBX_MAX_PGID		(8)
@@ -133,7 +131,7 @@ struct bfa_cee_lldp_str {
 	u8 len;
 	u8 rsvd[2];
 	u8 value[BFA_CEE_LLDP_MAX_STRING_LEN];
-};
+} __packed;
 
 /* LLDP parameters */
 struct bfa_cee_lldp_cfg {
@@ -145,7 +143,7 @@ struct bfa_cee_lldp_cfg {
 	struct bfa_cee_lldp_str mgmt_addr;
 	u16 time_to_live;
 	u16 enabled_system_cap;
-};
+} __packed;
 
 enum bfa_cee_dcbx_version {
 	DCBX_PROTOCOL_PRECEE	= 1,
@@ -171,7 +169,7 @@ struct bfa_cee_dcbx_cfg {
 	u8 lls_fcoe; /* FCoE Logical Link Status */
 	u8 lls_lan; /* LAN Logical Link Status */
 	u8 rsvd[2];
-};
+} __packed;
 
 /* CEE status */
 /* Making this to tri-state for the benefit of port list command */
@@ -188,11 +186,11 @@ struct bfa_cee_attr {
 	u8 error_reason;
 	struct bfa_cee_lldp_cfg lldp_remote;
 	struct bfa_cee_dcbx_cfg dcbx_remote;
-	mac_t src_mac;
+	u8 src_mac[ETH_ALEN];
 	u8 link_speed;
 	u8 nw_priority;
 	u8 filler[2];
-};
+} __packed;
 
 /* LLDP/DCBX/CEE Statistics */
 struct bfa_cee_stats {
@@ -214,8 +212,6 @@ struct bfa_cee_stats {
 	u32	cee_status_up;		/*!< CEE status up */
 	u32	cee_hw_cfg_changed;	/*!< CEE hw cfg changed */
 	u32	cee_rx_invalid_cfg;	/*!< CEE invalid cfg */
-};
-
-#pragma pack()
+} __packed;
 
 #endif	/* __BFA_DEFS_CNA_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h b/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
index 7a45cd0b594d..7e17451c94d1 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_defs_mfg_comm.h
@@ -59,8 +59,6 @@ enum {
 	BFA_MFG_TYPE_INVALID = 0,	 /*!< Invalid card type		*/
 };
 
-#pragma pack(1)
-
 /* Check if Mezz card */
 #define bfa_mfg_is_mezz(type) (( \
 	(type) == BFA_MFG_TYPE_JAYHAWK || \
@@ -77,7 +75,7 @@ enum {
 	CB_GPIO_FC4P2   = (4),		/*!< 4G 2port FC card		*/
 	CB_GPIO_FC4P1   = (5),		/*!< 4G 1port FC card		*/
 	CB_GPIO_DFLY    = (6),		/*!< 8G 2port FC mezzanine card	*/
-	CB_GPIO_PROTO   = (1 << 7)	/*!< 8G 2port FC prototypes	*/
+	CB_GPIO_PROTO   = BIT(7)	/*!< 8G 2port FC prototypes	*/
 };
 
 #define bfa_mfg_adapter_prop_init_gpio(gpio, card_type, prop)	\
@@ -86,7 +84,7 @@ do {								\
 		(prop) |= BFI_ADAPTER_PROTO;			\
 		(gpio) &= ~CB_GPIO_PROTO;			\
 	}							\
-	switch ((gpio)) {					\
+	switch (gpio) {						\
 	case CB_GPIO_TTV:					\
 		(prop) |= BFI_ADAPTER_TTV;			\
 	case CB_GPIO_DFLY:					\
@@ -148,8 +146,6 @@ struct bfa_mfg_vpd {
 	u8	len;		/*!< vpd data length excluding header */
 	u8	rsv;
 	u8		data[BFA_MFG_VPD_LEN];	/*!< vpd data */
-};
-
-#pragma pack()
+} __packed;
 
 #endif /* __BFA_DEFS_MFG_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 594a2ab36d31..b7a0f7879de2 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -23,14 +23,6 @@
 
 /* IOC local definitions */
 
-#define bfa_ioc_state_disabled(__sm)			\
-	(((__sm) == BFI_IOC_UNINIT) ||			\
-	 ((__sm) == BFI_IOC_INITING) ||			\
-	 ((__sm) == BFI_IOC_HWINIT) ||			\
-	 ((__sm) == BFI_IOC_DISABLED) ||		\
-	 ((__sm) == BFI_IOC_FAIL) ||			\
-	 ((__sm) == BFI_IOC_CFG_DISABLED))
-
 /* Asic specific macros : see bfa_hw_cb.c and bfa_hw_ct.c for details. */
 
 #define bfa_ioc_firmware_lock(__ioc)			\
@@ -57,12 +49,6 @@
 			((__ioc)->ioc_hwif->ioc_get_fwstate(__ioc))
 #define bfa_ioc_set_alt_ioc_fwstate(__ioc, __fwstate)		\
 		((__ioc)->ioc_hwif->ioc_set_alt_fwstate(__ioc, __fwstate))
-#define bfa_ioc_get_alt_ioc_fwstate(__ioc)		\
-			((__ioc)->ioc_hwif->ioc_get_alt_fwstate(__ioc))
-
-#define bfa_ioc_mbox_cmd_pending(__ioc)		\
-			(!list_empty(&((__ioc)->mbox_mod.cmd_q)) || \
-			readl((__ioc)->ioc_regs.hfn_mbox_cmd))
 
 static bool bfa_nw_auto_recover = true;
 
@@ -1105,12 +1091,9 @@ static void
 bfa_ioc_event_notify(struct bfa_ioc *ioc, enum bfa_ioc_event event)
 {
 	struct bfa_ioc_notify *notify;
-	struct list_head			*qe;
 
-	list_for_each(qe, &ioc->notify_q) {
-		notify = (struct bfa_ioc_notify *)qe;
+	list_for_each_entry(notify, &ioc->notify_q, qe)
 		notify->cbfn(notify->cbarg, event);
-	}
 }
 
 static void
@@ -1321,7 +1304,7 @@ bfa_nw_ioc_fwver_get(struct bfa_ioc *ioc, struct bfi_ioc_image_hdr *fwhdr)
 	for (i = 0; i < (sizeof(struct bfi_ioc_image_hdr) / sizeof(u32));
 	     i++) {
 		fwsig[i] =
-			swab32(readl((loff) + (ioc->ioc_regs.smem_page_start)));
+			swab32(readl(loff + ioc->ioc_regs.smem_page_start));
 		loff += sizeof(u32);
 	}
 }
@@ -1387,7 +1370,7 @@ static enum bfi_ioc_img_ver_cmp
 bfa_ioc_fw_ver_patch_cmp(struct bfi_ioc_image_hdr *base_fwhdr,
 			 struct bfi_ioc_image_hdr *fwhdr_to_cmp)
 {
-	if (bfa_ioc_fw_ver_compatible(base_fwhdr, fwhdr_to_cmp) == false)
+	if (!bfa_ioc_fw_ver_compatible(base_fwhdr, fwhdr_to_cmp))
 		return BFI_IOC_IMG_VER_INCOMP;
 
 	if (fwhdr_to_cmp->fwver.patch > base_fwhdr->fwver.patch)
@@ -1398,7 +1381,7 @@ bfa_ioc_fw_ver_patch_cmp(struct bfi_ioc_image_hdr *base_fwhdr,
 	/* GA takes priority over internal builds of the same patch stream.
 	 * At this point major minor maint and patch numbers are same.
 	 */
-	if (fwhdr_is_ga(base_fwhdr) == true)
+	if (fwhdr_is_ga(base_fwhdr))
 		if (fwhdr_is_ga(fwhdr_to_cmp))
 			return BFI_IOC_IMG_VER_SAME;
 		else
@@ -1692,7 +1675,7 @@ bfa_raw_sem_get(void __iomem *bar)
 {
 	int	locked;
 
-	locked = readl((bar + FLASH_SEM_LOCK_REG));
+	locked = readl(bar + FLASH_SEM_LOCK_REG);
 
 	return !locked;
 }
@@ -1912,10 +1895,8 @@ bfa_ioc_hwinit(struct bfa_ioc *ioc, bool force)
 }
 
 void
-bfa_nw_ioc_timeout(void *ioc_arg)
+bfa_nw_ioc_timeout(struct bfa_ioc *ioc)
 {
-	struct bfa_ioc *ioc = (struct bfa_ioc *) ioc_arg;
-
 	bfa_fsm_send_event(ioc, IOC_E_TIMEOUT);
 }
 
@@ -1980,10 +1961,9 @@ bfa_ioc_send_getattr(struct bfa_ioc *ioc)
 }
 
 void
-bfa_nw_ioc_hb_check(void *cbarg)
+bfa_nw_ioc_hb_check(struct bfa_ioc *ioc)
 {
-	struct bfa_ioc *ioc = cbarg;
-	u32	hb_count;
+	u32 hb_count;
 
 	hb_count = readl(ioc->ioc_regs.heartbeat);
 	if (ioc->hb_count == hb_count) {
@@ -2069,8 +2049,8 @@ bfa_ioc_download_fw(struct bfa_ioc *ioc, u32 boot_type,
 		/**
 		 * write smem
 		 */
-		writel((swab32(fwimg[BFA_IOC_FLASH_OFFSET_IN_CHUNK(i)])),
-			      ((ioc->ioc_regs.smem_page_start) + (loff)));
+		writel(swab32(fwimg[BFA_IOC_FLASH_OFFSET_IN_CHUNK(i)]),
+		       ioc->ioc_regs.smem_page_start + loff);
 
 		loff += sizeof(u32);
 
@@ -2177,7 +2157,8 @@ bfa_ioc_mbox_poll(struct bfa_ioc *ioc)
 	/**
 	 * Enqueue command to firmware.
 	 */
-	bfa_q_deq(&mod->cmd_q, &cmd);
+	cmd = list_first_entry(&mod->cmd_q, struct bfa_mbox_cmd, qe);
+	list_del(&cmd->qe);
 	bfa_ioc_mbox_send(ioc, cmd->msg, sizeof(cmd->msg));
 
 	/**
@@ -2198,8 +2179,10 @@ bfa_ioc_mbox_flush(struct bfa_ioc *ioc)
 	struct bfa_ioc_mbox_mod *mod = &ioc->mbox_mod;
 	struct bfa_mbox_cmd *cmd;
 
-	while (!list_empty(&mod->cmd_q))
-		bfa_q_deq(&mod->cmd_q, &cmd);
+	while (!list_empty(&mod->cmd_q)) {
+		cmd = list_first_entry(&mod->cmd_q, struct bfa_mbox_cmd, qe);
+		list_del(&cmd->qe);
+	}
 }
 
 /**
@@ -2223,14 +2206,14 @@ bfa_nw_ioc_smem_read(struct bfa_ioc *ioc, void *tbuf, u32 soff, u32 sz)
 	/*
 	 *  Hold semaphore to serialize pll init and fwtrc.
 	*/
-	if (bfa_nw_ioc_sem_get(ioc->ioc_regs.ioc_init_sem_reg) == 0)
+	if (!bfa_nw_ioc_sem_get(ioc->ioc_regs.ioc_init_sem_reg))
 		return 1;
 
 	writel(pgnum, ioc->ioc_regs.host_page_num_fn);
 
 	len = sz/sizeof(u32);
 	for (i = 0; i < len; i++) {
-		r32 = swab32(readl((loff) + (ioc->ioc_regs.smem_page_start)));
+		r32 = swab32(readl(loff + ioc->ioc_regs.smem_page_start));
 		buf[i] = be32_to_cpu(r32);
 		loff += sizeof(u32);
 
@@ -2278,7 +2261,7 @@ bfa_nw_ioc_debug_save_ftrc(struct bfa_ioc *ioc)
 	int tlen;
 
 	if (ioc->dbg_fwsave_once) {
-		ioc->dbg_fwsave_once = 0;
+		ioc->dbg_fwsave_once = false;
 		if (ioc->dbg_fwsave_len) {
 			tlen = ioc->dbg_fwsave_len;
 			bfa_nw_ioc_debug_fwtrc(ioc, ioc->dbg_fwsave, &tlen);
@@ -2414,7 +2397,7 @@ bfa_ioc_boot(struct bfa_ioc *ioc, enum bfi_fwboot_type boot_type,
 	if (status == BFA_STATUS_OK)
 		bfa_ioc_lpu_start(ioc);
 	else
-		bfa_nw_iocpf_timeout(ioc);
+		bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
 
 	return status;
 }
@@ -2796,7 +2779,7 @@ bfa_ioc_get_adapter_attr(struct bfa_ioc *ioc,
 		ad_attr->prototype = 0;
 
 	ad_attr->pwwn = bfa_ioc_get_pwwn(ioc);
-	ad_attr->mac  = bfa_nw_ioc_get_mac(ioc);
+	bfa_nw_ioc_get_mac(ioc, ad_attr->mac);
 
 	ad_attr->pcie_gen = ioc_attr->pcie_gen;
 	ad_attr->pcie_lanes = ioc_attr->pcie_lanes;
@@ -2942,10 +2925,10 @@ bfa_ioc_get_pwwn(struct bfa_ioc *ioc)
 	return ioc->attr->pwwn;
 }
 
-mac_t
-bfa_nw_ioc_get_mac(struct bfa_ioc *ioc)
+void
+bfa_nw_ioc_get_mac(struct bfa_ioc *ioc, u8 *mac)
 {
-	return ioc->attr->mac;
+	ether_addr_copy(mac, ioc->attr->mac);
 }
 
 /* Firmware failure detected. Start recovery actions. */
@@ -2997,9 +2980,8 @@ bfa_iocpf_stop(struct bfa_ioc *ioc)
 }
 
 void
-bfa_nw_iocpf_timeout(void *ioc_arg)
+bfa_nw_iocpf_timeout(struct bfa_ioc *ioc)
 {
-	struct bfa_ioc  *ioc = (struct bfa_ioc *) ioc_arg;
 	enum bfa_iocpf_state iocpf_st;
 
 	iocpf_st = bfa_sm_to_state(iocpf_sm_table, ioc->iocpf.fsm);
@@ -3011,10 +2993,8 @@ bfa_nw_iocpf_timeout(void *ioc_arg)
 }
 
 void
-bfa_nw_iocpf_sem_timeout(void *ioc_arg)
+bfa_nw_iocpf_sem_timeout(struct bfa_ioc *ioc)
 {
-	struct bfa_ioc  *ioc = (struct bfa_ioc *) ioc_arg;
-
 	bfa_ioc_hw_sem_get(ioc);
 }
 
@@ -3029,7 +3009,7 @@ bfa_ioc_poll_fwinit(struct bfa_ioc *ioc)
 	}
 
 	if (ioc->iocpf.poll_time >= BFA_IOC_TOV) {
-		bfa_nw_iocpf_timeout(ioc);
+		bfa_fsm_send_event(&ioc->iocpf, IOCPF_E_TIMEOUT);
 	} else {
 		ioc->iocpf.poll_time += BFA_IOC_POLL_TOV;
 		mod_timer(&ioc->iocpf_timer, jiffies +
@@ -3245,7 +3225,6 @@ bfa_nw_flash_attach(struct bfa_flash *flash, struct bfa_ioc *ioc, void *dev)
 	flash->op_busy = 0;
 
 	bfa_nw_ioc_mbox_regisr(flash->ioc, BFI_MC_FLASH, bfa_flash_intr, flash);
-	bfa_q_qe_init(&flash->ioc_notify);
 	bfa_ioc_notify_init(&flash->ioc_notify, bfa_flash_notify, flash);
 	list_add_tail(&flash->ioc_notify.qe, &flash->ioc->notify_q);
 }
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.h b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
index effb7156e7a4..2c0b4c076355 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.h
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.h
@@ -232,12 +232,6 @@ struct bfa_ioc_hwif {
 #define bfa_ioc_asic_gen(__ioc)		((__ioc)->asic_gen)
 #define bfa_ioc_is_default(__ioc)	\
 	(bfa_ioc_pcifn(__ioc) == bfa_ioc_portid(__ioc))
-#define bfa_ioc_fetch_stats(__ioc, __stats) \
-		(((__stats)->drv_stats) = (__ioc)->stats)
-#define bfa_ioc_clr_stats(__ioc)	\
-		memset(&(__ioc)->stats, 0, sizeof((__ioc)->stats))
-#define bfa_ioc_maxfrsize(__ioc)	((__ioc)->attr->maxfrsize)
-#define bfa_ioc_rx_bbcredit(__ioc)	((__ioc)->attr->rx_bbcredit)
 #define bfa_ioc_speed_sup(__ioc)	\
 	BFI_ADAPTER_GETP(SPEED, (__ioc)->attr->adapter_prop)
 #define bfa_ioc_get_nports(__ioc)	\
@@ -268,13 +262,6 @@ void bfa_nw_ioc_mbox_regisr(struct bfa_ioc *ioc, enum bfi_mclass mc,
 	((__ioc)->ioc_hwif->ioc_pll_init((__ioc)->pcidev.pci_bar_kva, \
 			   (__ioc)->asic_mode))
 
-#define	bfa_ioc_isr_mode_set(__ioc, __msix) do {			\
-	if ((__ioc)->ioc_hwif->ioc_isr_mode_set)			\
-		((__ioc)->ioc_hwif->ioc_isr_mode_set(__ioc, __msix));	\
-} while (0)
-#define	bfa_ioc_ownership_reset(__ioc)				\
-			((__ioc)->ioc_hwif->ioc_ownership_reset(__ioc))
-
 #define bfa_ioc_lpu_read_stat(__ioc) do {				\
 		if ((__ioc)->ioc_hwif->ioc_lpu_read_stat)		\
 			((__ioc)->ioc_hwif->ioc_lpu_read_stat(__ioc));	\
@@ -309,7 +296,7 @@ void bfa_nw_ioc_fwver_get(struct bfa_ioc *ioc,
 			struct bfi_ioc_image_hdr *fwhdr);
 bool bfa_nw_ioc_fwver_cmp(struct bfa_ioc *ioc,
 			struct bfi_ioc_image_hdr *fwhdr);
-mac_t bfa_nw_ioc_get_mac(struct bfa_ioc *ioc);
+void bfa_nw_ioc_get_mac(struct bfa_ioc *ioc, u8 *mac);
 void bfa_nw_ioc_debug_memclaim(struct bfa_ioc *ioc, void *dbg_fwsave);
 int bfa_nw_ioc_debug_fwtrc(struct bfa_ioc *ioc, void *trcdata, int *trclen);
 int bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen);
@@ -317,10 +304,10 @@ int bfa_nw_ioc_debug_fwsave(struct bfa_ioc *ioc, void *trcdata, int *trclen);
 /*
  * Timeout APIs
  */
-void bfa_nw_ioc_timeout(void *ioc);
-void bfa_nw_ioc_hb_check(void *ioc);
-void bfa_nw_iocpf_timeout(void *ioc);
-void bfa_nw_iocpf_sem_timeout(void *ioc);
+void bfa_nw_ioc_timeout(struct bfa_ioc *ioc);
+void bfa_nw_ioc_hb_check(struct bfa_ioc *ioc);
+void bfa_nw_iocpf_timeout(struct bfa_ioc *ioc);
+void bfa_nw_iocpf_sem_timeout(struct bfa_ioc *ioc);
 
 /*
  * F/W Image Size & Chunk
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c b/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
index 2e72445dbb4f..74e5ed55ac01 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc_ct.c
@@ -23,8 +23,7 @@
 #include "bfi_reg.h"
 #include "bfa_defs.h"
 
-#define bfa_ioc_ct_sync_pos(__ioc)	\
-		((u32) (1 << bfa_ioc_pcifn(__ioc)))
+#define bfa_ioc_ct_sync_pos(__ioc)	BIT(bfa_ioc_pcifn(__ioc))
 #define BFA_IOC_SYNC_REQD_SH		16
 #define bfa_ioc_ct_get_sync_ackd(__val) (__val & 0x0000ffff)
 #define bfa_ioc_ct_clear_sync_ackd(__val) (__val & 0xffff0000)
@@ -536,7 +535,7 @@ bfa_ioc_ct_sync_ack(struct bfa_ioc *ioc)
 {
 	u32 r32 = readl(ioc->ioc_regs.ioc_fail_sync);
 
-	writel((r32 | bfa_ioc_ct_sync_pos(ioc)), ioc->ioc_regs.ioc_fail_sync);
+	writel(r32 | bfa_ioc_ct_sync_pos(ioc), ioc->ioc_regs.ioc_fail_sync);
 }
 
 static bool
@@ -667,7 +666,7 @@ bfa_ioc_ct_pll_init(void __iomem *rb, enum bfi_asic_mode asic_mode)
 		writel(__PMM_1T_RESET_P, (rb + PMM_1T_RESET_REG_P0));
 		writel(__PMM_1T_RESET_P, (rb + PMM_1T_RESET_REG_P1));
 	}
-	r32 = readl((rb + PSS_CTL_REG));
+	r32 = readl(rb + PSS_CTL_REG);
 	r32 &= ~__PSS_LMEM_RESET;
 	writel(r32, (rb + PSS_CTL_REG));
 	udelay(1000);
@@ -678,7 +677,7 @@ bfa_ioc_ct_pll_init(void __iomem *rb, enum bfi_asic_mode asic_mode)
 
 	writel(__EDRAM_BISTR_START, (rb + MBIST_CTL_REG));
 	udelay(1000);
-	r32 = readl((rb + MBIST_STAT_REG));
+	r32 = readl(rb + MBIST_STAT_REG);
 	writel(0, (rb + MBIST_CTL_REG));
 	return BFA_STATUS_OK;
 }
@@ -691,7 +690,7 @@ bfa_ioc_ct2_sclk_init(void __iomem *rb)
 	/*
 	 * put s_clk PLL and PLL FSM in reset
 	 */
-	r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
 	r32 &= ~(__APP_PLL_SCLK_ENABLE | __APP_PLL_SCLK_LRESETN);
 	r32 |= (__APP_PLL_SCLK_ENARST | __APP_PLL_SCLK_BYPASS |
 		__APP_PLL_SCLK_LOGIC_SOFT_RESET);
@@ -701,28 +700,28 @@ bfa_ioc_ct2_sclk_init(void __iomem *rb)
 	 * Ignore mode and program for the max clock (which is FC16)
 	 * Firmware/NFC will do the PLL init appropriately
 	 */
-	r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
 	r32 &= ~(__APP_PLL_SCLK_REFCLK_SEL | __APP_PLL_SCLK_CLK_DIV2);
 	writel(r32, (rb + CT2_APP_PLL_SCLK_CTL_REG));
 
 	/*
 	 * while doing PLL init dont clock gate ethernet subsystem
 	 */
-	r32 = readl((rb + CT2_CHIP_MISC_PRG));
-	writel((r32 | __ETH_CLK_ENABLE_PORT0),
-				(rb + CT2_CHIP_MISC_PRG));
+	r32 = readl(rb + CT2_CHIP_MISC_PRG);
+	writel(r32 | __ETH_CLK_ENABLE_PORT0,
+	       rb + CT2_CHIP_MISC_PRG);
 
-	r32 = readl((rb + CT2_PCIE_MISC_REG));
-	writel((r32 | __ETH_CLK_ENABLE_PORT1),
-				(rb + CT2_PCIE_MISC_REG));
+	r32 = readl(rb + CT2_PCIE_MISC_REG);
+	writel(r32 | __ETH_CLK_ENABLE_PORT1,
+	       rb + CT2_PCIE_MISC_REG);
 
 	/*
 	 * set sclk value
 	 */
-	r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
 	r32 &= (__P_SCLK_PLL_LOCK | __APP_PLL_SCLK_REFCLK_SEL |
 		__APP_PLL_SCLK_CLK_DIV2);
-	writel(r32 | 0x1061731b, (rb + CT2_APP_PLL_SCLK_CTL_REG));
+	writel(r32 | 0x1061731b, rb + CT2_APP_PLL_SCLK_CTL_REG);
 
 	/*
 	 * poll for s_clk lock or delay 1ms
@@ -743,28 +742,28 @@ bfa_ioc_ct2_lclk_init(void __iomem *rb)
 	/*
 	 * put l_clk PLL and PLL FSM in reset
 	 */
-	r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
 	r32 &= ~(__APP_PLL_LCLK_ENABLE | __APP_PLL_LCLK_LRESETN);
 	r32 |= (__APP_PLL_LCLK_ENARST | __APP_PLL_LCLK_BYPASS |
 		__APP_PLL_LCLK_LOGIC_SOFT_RESET);
-	writel(r32, (rb + CT2_APP_PLL_LCLK_CTL_REG));
+	writel(r32, rb + CT2_APP_PLL_LCLK_CTL_REG);
 
 	/*
 	 * set LPU speed (set for FC16 which will work for other modes)
 	 */
-	r32 = readl((rb + CT2_CHIP_MISC_PRG));
+	r32 = readl(rb + CT2_CHIP_MISC_PRG);
 	writel(r32, (rb + CT2_CHIP_MISC_PRG));
 
 	/*
 	 * set LPU half speed (set for FC16 which will work for other modes)
 	 */
-	r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
-	writel(r32, (rb + CT2_APP_PLL_LCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
+	writel(r32, rb + CT2_APP_PLL_LCLK_CTL_REG);
 
 	/*
 	 * set lclk for mode (set for FC16)
 	 */
-	r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
 	r32 &= (__P_LCLK_PLL_LOCK | __APP_LPUCLK_HALFSPEED);
 	r32 |= 0x20c1731b;
 	writel(r32, (rb + CT2_APP_PLL_LCLK_CTL_REG));
@@ -780,14 +779,14 @@ bfa_ioc_ct2_mem_init(void __iomem *rb)
 {
 	u32 r32;
 
-	r32 = readl((rb + PSS_CTL_REG));
+	r32 = readl(rb + PSS_CTL_REG);
 	r32 &= ~__PSS_LMEM_RESET;
-	writel(r32, (rb + PSS_CTL_REG));
+	writel(r32, rb + PSS_CTL_REG);
 	udelay(1000);
 
-	writel(__EDRAM_BISTR_START, (rb + CT2_MBIST_CTL_REG));
+	writel(__EDRAM_BISTR_START, rb + CT2_MBIST_CTL_REG);
 	udelay(1000);
-	writel(0, (rb + CT2_MBIST_CTL_REG));
+	writel(0, rb + CT2_MBIST_CTL_REG);
 }
 
 static void
@@ -801,22 +800,22 @@ bfa_ioc_ct2_mac_reset(void __iomem *rb)
 	/*
 	 * release soft reset on s_clk & l_clk
 	 */
-	r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
-	writel((r32 & ~__APP_PLL_SCLK_LOGIC_SOFT_RESET),
-			(rb + CT2_APP_PLL_SCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
+	writel(r32 & ~__APP_PLL_SCLK_LOGIC_SOFT_RESET,
+	       rb + CT2_APP_PLL_SCLK_CTL_REG);
 
 	/*
 	 * release soft reset on s_clk & l_clk
 	 */
-	r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
-	writel((r32 & ~__APP_PLL_LCLK_LOGIC_SOFT_RESET),
-			(rb + CT2_APP_PLL_LCLK_CTL_REG));
+	r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
+	writel(r32 & ~__APP_PLL_LCLK_LOGIC_SOFT_RESET,
+	       rb + CT2_APP_PLL_LCLK_CTL_REG);
 
 	/* put port0, port1 MAC & AHB in reset */
-	writel((__CSI_MAC_RESET | __CSI_MAC_AHB_RESET),
-			(rb + CT2_CSI_MAC_CONTROL_REG(0)));
-	writel((__CSI_MAC_RESET | __CSI_MAC_AHB_RESET),
-			(rb + CT2_CSI_MAC_CONTROL_REG(1)));
+	writel(__CSI_MAC_RESET | __CSI_MAC_AHB_RESET,
+	       rb + CT2_CSI_MAC_CONTROL_REG(0));
+	writel(__CSI_MAC_RESET | __CSI_MAC_AHB_RESET,
+	       rb + CT2_CSI_MAC_CONTROL_REG(1));
 }
 
 #define CT2_NFC_MAX_DELAY       1000
@@ -861,8 +860,8 @@ bfa_ioc_ct2_pll_init(void __iomem *rb, enum bfi_asic_mode asic_mode)
 
 	nfc_ver = readl(rb + CT2_RSC_GPR15_REG);
 
-	if ((wgn == (__A2T_AHB_LOAD | __WGN_READY)) &&
-		(nfc_ver >= CT2_NFC_VER_VALID)) {
+	if (wgn == (__A2T_AHB_LOAD | __WGN_READY) &&
+	    nfc_ver >= CT2_NFC_VER_VALID) {
 		if (bfa_ioc_ct2_nfc_halted(rb))
 			bfa_ioc_ct2_nfc_resume(rb);
 		writel(__RESET_AND_START_SCLK_LCLK_PLLS,
@@ -899,19 +898,19 @@ bfa_ioc_ct2_pll_init(void __iomem *rb, enum bfi_asic_mode asic_mode)
 		bfa_ioc_ct2_lclk_init(rb);
 
 		/* release soft reset on s_clk & l_clk */
-		r32 = readl((rb + CT2_APP_PLL_SCLK_CTL_REG));
+		r32 = readl(rb + CT2_APP_PLL_SCLK_CTL_REG);
 		writel(r32 & ~__APP_PLL_SCLK_LOGIC_SOFT_RESET,
 				rb + CT2_APP_PLL_SCLK_CTL_REG);
-		r32 = readl((rb + CT2_APP_PLL_LCLK_CTL_REG));
+		r32 = readl(rb + CT2_APP_PLL_LCLK_CTL_REG);
 		writel(r32 & ~__APP_PLL_LCLK_LOGIC_SOFT_RESET,
 				rb + CT2_APP_PLL_LCLK_CTL_REG);
 	}
 
 	/* Announce flash device presence, if flash was corrupted. */
 	if (wgn == (__WGN_READY | __GLBL_PF_VF_CFG_RDY)) {
-		r32 = readl((rb + PSS_GPIO_OUT_REG));
+		r32 = readl(rb + PSS_GPIO_OUT_REG);
 		writel(r32 & ~1, rb + PSS_GPIO_OUT_REG);
-		r32 = readl((rb + PSS_GPIO_OE_REG));
+		r32 = readl(rb + PSS_GPIO_OE_REG);
 		writel(r32 | 1, rb + PSS_GPIO_OE_REG);
 	}
 
@@ -919,27 +918,27 @@ bfa_ioc_ct2_pll_init(void __iomem *rb, enum bfi_asic_mode asic_mode)
 	 * Mask the interrupts and clear any
 	 * pending interrupts left by BIOS/EFI
 	 */
-	writel(1, (rb + CT2_LPU0_HOSTFN_MBOX0_MSK));
-	writel(1, (rb + CT2_LPU1_HOSTFN_MBOX0_MSK));
+	writel(1, rb + CT2_LPU0_HOSTFN_MBOX0_MSK);
+	writel(1, rb + CT2_LPU1_HOSTFN_MBOX0_MSK);
 
 	/* For first time initialization, no need to clear interrupts */
 	r32 = readl(rb + HOST_SEM5_REG);
 	if (r32 & 0x1) {
-		r32 = readl((rb + CT2_LPU0_HOSTFN_CMD_STAT));
+		r32 = readl(rb + CT2_LPU0_HOSTFN_CMD_STAT);
 		if (r32 == 1) {
-			writel(1, (rb + CT2_LPU0_HOSTFN_CMD_STAT));
-			readl((rb + CT2_LPU0_HOSTFN_CMD_STAT));
+			writel(1, rb + CT2_LPU0_HOSTFN_CMD_STAT);
+			readl(rb + CT2_LPU0_HOSTFN_CMD_STAT);
 		}
-		r32 = readl((rb + CT2_LPU1_HOSTFN_CMD_STAT));
+		r32 = readl(rb + CT2_LPU1_HOSTFN_CMD_STAT);
 		if (r32 == 1) {
-			writel(1, (rb + CT2_LPU1_HOSTFN_CMD_STAT));
-			readl((rb + CT2_LPU1_HOSTFN_CMD_STAT));
+			writel(1, rb + CT2_LPU1_HOSTFN_CMD_STAT);
+			readl(rb + CT2_LPU1_HOSTFN_CMD_STAT);
 		}
 	}
 
 	bfa_ioc_ct2_mem_init(rb);
 
-	writel(BFI_IOC_UNINIT, (rb + CT2_BFA_IOC0_STATE_REG));
-	writel(BFI_IOC_UNINIT, (rb + CT2_BFA_IOC1_STATE_REG));
+	writel(BFI_IOC_UNINIT, rb + CT2_BFA_IOC0_STATE_REG);
+	writel(BFI_IOC_UNINIT, rb + CT2_BFA_IOC1_STATE_REG);
 	return BFA_STATUS_OK;
 }
diff --git a/drivers/net/ethernet/brocade/bna/bfa_msgq.c b/drivers/net/ethernet/brocade/bna/bfa_msgq.c
index c07d5b9372f4..9c5bb24e8abb 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_msgq.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_msgq.c
@@ -66,8 +66,9 @@ cmdq_sm_stopped_entry(struct bfa_msgq_cmdq *cmdq)
 	cmdq->offset = 0;
 	cmdq->bytes_to_copy = 0;
 	while (!list_empty(&cmdq->pending_q)) {
-		bfa_q_deq(&cmdq->pending_q, &cmdq_ent);
-		bfa_q_qe_init(&cmdq_ent->qe);
+		cmdq_ent = list_first_entry(&cmdq->pending_q,
+					    struct bfa_msgq_cmd_entry, qe);
+		list_del(&cmdq_ent->qe);
 		call_cmdq_ent_cbfn(cmdq_ent, BFA_STATUS_FAILED);
 	}
 }
@@ -242,8 +243,8 @@ bfa_msgq_cmdq_ci_update(struct bfa_msgq_cmdq *cmdq, struct bfi_mbmsg *mb)
 
 	/* Walk through pending list to see if the command can be posted */
 	while (!list_empty(&cmdq->pending_q)) {
-		cmd =
-		(struct bfa_msgq_cmd_entry *)bfa_q_first(&cmdq->pending_q);
+		cmd = list_first_entry(&cmdq->pending_q,
+				       struct bfa_msgq_cmd_entry, qe);
 		if (ntohs(cmd->msg_hdr->num_entries) <=
 			BFA_MSGQ_FREE_CNT(cmdq)) {
 			list_del(&cmd->qe);
@@ -615,7 +616,6 @@ bfa_msgq_attach(struct bfa_msgq *msgq, struct bfa_ioc *ioc)
 	bfa_msgq_rspq_attach(&msgq->rspq, msgq);
 
 	bfa_nw_ioc_mbox_regisr(msgq->ioc, BFI_MC_MSGQ, bfa_msgq_isr, msgq);
-	bfa_q_qe_init(&msgq->ioc_notify);
 	bfa_ioc_notify_init(&msgq->ioc_notify, bfa_msgq_notify, msgq);
 	bfa_nw_ioc_notify_register(msgq->ioc, &msgq->ioc_notify);
 }
diff --git a/drivers/net/ethernet/brocade/bna/bfi.h b/drivers/net/ethernet/brocade/bna/bfi.h
index 2bcde4042268..81e59ea8b4f2 100644
--- a/drivers/net/ethernet/brocade/bna/bfi.h
+++ b/drivers/net/ethernet/brocade/bna/bfi.h
@@ -21,8 +21,6 @@
 
 #include "bfa_defs.h"
 
-#pragma pack(1)
-
 /* BFI FW image type */
 #define	BFI_FLASH_CHUNK_SZ			256	/*!< Flash chunk size */
 #define	BFI_FLASH_CHUNK_SZ_WORDS	(BFI_FLASH_CHUNK_SZ/sizeof(u32))
@@ -36,10 +34,10 @@ struct bfi_mhdr {
 		struct {
 			u8	qid;
 			u8	fn_lpu;	/*!< msg destination		    */
-		} h2i;
+		} __packed h2i;
 		u16	i2htok;	/*!< token in msgs to host	    */
-	} mtag;
-};
+	} __packed mtag;
+} __packed;
 
 #define bfi_fn_lpu(__fn, __lpu)	((__fn) << 1 | (__lpu))
 #define bfi_mhdr_2_fn(_mh)	((_mh)->mtag.h2i.fn_lpu >> 1)
@@ -75,14 +73,14 @@ union bfi_addr_u {
 	struct {
 		u32	addr_lo;
 		u32	addr_hi;
-	} a32;
-};
+	} __packed a32;
+} __packed;
 
 /* Generic DMA addr-len pair. */
 struct bfi_alen {
 	union bfi_addr_u	al_addr;	/* DMA addr of buffer	*/
 	u32			al_len;		/* length of buffer */
-};
+} __packed;
 
 /*
  * Large Message structure - 128 Bytes size Msgs
@@ -96,7 +94,7 @@ struct bfi_alen {
 struct bfi_mbmsg {
 	struct bfi_mhdr mh;
 	u32		pl[BFI_MBMSG_SZ];
-};
+} __packed;
 
 /* Supported PCI function class codes (personality) */
 enum bfi_pcifn_class {
@@ -184,19 +182,19 @@ enum bfi_ioc_i2h_msgs {
 struct bfi_ioc_getattr_req {
 	struct bfi_mhdr mh;
 	union bfi_addr_u	attr_addr;
-};
+} __packed;
 
 struct bfi_ioc_attr {
 	u64		mfg_pwwn;	/*!< Mfg port wwn	   */
 	u64		mfg_nwwn;	/*!< Mfg node wwn	   */
-	mac_t		mfg_mac;	/*!< Mfg mac		   */
+	u8		mfg_mac[ETH_ALEN]; /*!< Mfg mac		   */
 	u8		port_mode;	/* enum bfi_port_mode	   */
 	u8		rsvd_a;
 	u64		pwwn;
 	u64		nwwn;
-	mac_t		mac;		/*!< PBC or Mfg mac	   */
+	u8		mac[ETH_ALEN];	/*!< PBC or Mfg mac	   */
 	u16	rsvd_b;
-	mac_t		fcoe_mac;
+	u8		fcoe_mac[ETH_ALEN];
 	u16	rsvd_c;
 	char		brcd_serialnum[STRSZ(BFA_MFG_SERIALNUM_SIZE)];
 	u8		pcie_gen;
@@ -211,14 +209,14 @@ struct bfi_ioc_attr {
 	char		optrom_version[BFA_VERSION_LEN];
 	struct bfa_mfg_vpd vpd;
 	u32	card_type;	/*!< card type			*/
-};
+} __packed;
 
 /* BFI_IOC_I2H_GETATTR_REPLY message */
 struct bfi_ioc_getattr_reply {
 	struct bfi_mhdr mh;	/*!< Common msg header		*/
 	u8			status;	/*!< cfg reply status		*/
 	u8			rsvd[3];
-};
+} __packed;
 
 /* Firmware memory page offsets */
 #define BFI_IOC_SMEM_PG0_CB	(0x40)
@@ -256,7 +254,7 @@ struct bfi_ioc_fwver {
 	u8 build;
 	u8 rsvd[2];
 #endif
-};
+} __packed;
 
 struct bfi_ioc_image_hdr {
 	u32	signature;	/*!< constant signature */
@@ -269,7 +267,7 @@ struct bfi_ioc_image_hdr {
 	u32	rsvd_b[2];
 	struct bfi_ioc_fwver fwver;
 	u32	md5sum[BFI_IOC_MD5SUM_SZ];
-};
+} __packed;
 
 enum bfi_ioc_img_ver_cmp {
 	BFI_IOC_IMG_VER_INCOMP,
@@ -301,7 +299,7 @@ enum bfi_port_mode {
 struct bfi_ioc_hbeat {
 	struct bfi_mhdr mh;		/*!< common msg header		*/
 	u32	   hb_count;	/*!< current heart beat count	*/
-};
+} __packed;
 
 /* IOC hardware/firmware state */
 enum bfi_ioc_state {
@@ -317,8 +315,6 @@ enum bfi_ioc_state {
 	BFI_IOC_MEMTEST		= 9,	/*!< IOC is doing memtest	     */
 };
 
-#define BFI_IOC_ENDIAN_SIG  0x12345678
-
 enum {
 	BFI_ADAPTER_TYPE_FC	= 0x01,		/*!< FC adapters	   */
 	BFI_ADAPTER_TYPE_MK	= 0x0f0000,	/*!< adapter type mask     */
@@ -337,12 +333,6 @@ enum {
 		BFI_ADAPTER_ ## __prop ## _SH)
 #define BFI_ADAPTER_SETP(__prop, __val)				\
 	((__val) << BFI_ADAPTER_ ## __prop ## _SH)
-#define BFI_ADAPTER_IS_PROTO(__adap_type)			\
-	((__adap_type) & BFI_ADAPTER_PROTO)
-#define BFI_ADAPTER_IS_TTV(__adap_type)				\
-	((__adap_type) & BFI_ADAPTER_TTV)
-#define BFI_ADAPTER_IS_UNSUPP(__adap_type)			\
-	((__adap_type) & BFI_ADAPTER_UNSUPP)
 #define BFI_ADAPTER_IS_SPECIAL(__adap_type)			\
 	((__adap_type) & (BFI_ADAPTER_TTV | BFI_ADAPTER_PROTO |	\
 			BFI_ADAPTER_UNSUPP))
@@ -353,7 +343,7 @@ struct bfi_ioc_ctrl_req {
 	u16			clscode;
 	u16			rsvd;
 	u32		tv_sec;
-};
+} __packed;
 
 /* BFI_IOC_I2H_ENABLE_REPLY & BFI_IOC_I2H_DISABLE_REPLY messages */
 struct bfi_ioc_ctrl_reply {
@@ -362,7 +352,7 @@ struct bfi_ioc_ctrl_reply {
 	u8			port_mode;	/*!< enum bfa_mode */
 	u8			cap_bm;		/*!< capability bit mask */
 	u8			rsvd;
-};
+} __packed;
 
 #define BFI_IOC_MSGSZ   8
 /* H2I Messages */
@@ -372,14 +362,14 @@ union bfi_ioc_h2i_msg_u {
 	struct bfi_ioc_ctrl_req disable_req;
 	struct bfi_ioc_getattr_req getattr_req;
 	u32			mboxmsg[BFI_IOC_MSGSZ];
-};
+} __packed;
 
 /* I2H Messages */
 union bfi_ioc_i2h_msg_u {
 	struct bfi_mhdr mh;
 	struct bfi_ioc_ctrl_reply fw_event;
 	u32			mboxmsg[BFI_IOC_MSGSZ];
-};
+} __packed;
 
 /*----------------------------------------------------------------------
  *				MSGQ
@@ -408,7 +398,7 @@ struct bfi_msgq_mhdr {
 	u16	num_entries;
 	u8	enet_id;
 	u8	rsvd[1];
-};
+} __packed;
 
 #define bfi_msgq_mhdr_set(_mh, _mc, _mid, _tok, _enet_id) do {	\
 	(_mh).msg_class	 = (_mc);	\
@@ -430,21 +420,21 @@ struct bfi_msgq {
 	union bfi_addr_u addr;
 	u16 q_depth;     /* Total num of entries in the queue */
 	u8 rsvd[2];
-};
+} __packed;
 
 /* BFI_ENET_MSGQ_CFG_REQ TBD init or cfg? */
 struct bfi_msgq_cfg_req {
 	struct bfi_mhdr mh;
 	struct bfi_msgq cmdq;
 	struct bfi_msgq rspq;
-};
+} __packed;
 
 /* BFI_ENET_MSGQ_CFG_RSP */
 struct bfi_msgq_cfg_rsp {
 	struct bfi_mhdr mh;
 	u8 cmd_status;
 	u8 rsvd[3];
-};
+} __packed;
 
 /* BFI_MSGQ_H2I_DOORBELL */
 struct bfi_msgq_h2i_db {
@@ -452,8 +442,8 @@ struct bfi_msgq_h2i_db {
 	union {
 		u16 cmdq_pi;
 		u16 rspq_ci;
-	} idx;
-};
+	} __packed idx;
+} __packed;
 
 /* BFI_MSGQ_I2H_DOORBELL */
 struct bfi_msgq_i2h_db {
@@ -461,8 +451,8 @@ struct bfi_msgq_i2h_db {
 	union {
 		u16 rspq_pi;
 		u16 cmdq_ci;
-	} idx;
-};
+	} __packed idx;
+} __packed;
 
 #define BFI_CMD_COPY_SZ 28
 
@@ -470,14 +460,14 @@ struct bfi_msgq_i2h_db {
 struct bfi_msgq_h2i_cmdq_copy_rsp {
 	struct bfi_mhdr mh;
 	u8	      data[BFI_CMD_COPY_SZ];
-};
+} __packed;
 
 /* BFI_MSGQ_I2H_CMD_COPY_REQ */
 struct bfi_msgq_i2h_cmdq_copy_req {
 	struct bfi_mhdr mh;
 	u16     offset;
 	u16     len;
-};
+} __packed;
 
 /*
  *      FLASH module specific
@@ -505,7 +495,7 @@ enum bfi_flash_i2h_msgs {
 struct bfi_flash_query_req {
 	struct bfi_mhdr mh;   /* Common msg header */
 	struct bfi_alen alen;
-};
+} __packed;
 
 /*
  * Flash write request
@@ -519,7 +509,7 @@ struct bfi_flash_write_req {
 	u8	rsv[2];
 	u32	offset;
 	u32	length;
-};
+} __packed;
 
 /*
  * Flash read request
@@ -532,7 +522,7 @@ struct bfi_flash_read_req {
 	u32	offset;
 	u32	length;
 	struct bfi_alen alen;
-};
+} __packed;
 
 /*
  * Flash query response
@@ -540,7 +530,7 @@ struct bfi_flash_read_req {
 struct bfi_flash_query_rsp {
 	struct bfi_mhdr mh;	/* Common msg header */
 	u32	status;
-};
+} __packed;
 
 /*
  * Flash read response
@@ -552,7 +542,7 @@ struct bfi_flash_read_rsp {
 	u8	rsv[3];
 	u32	status;
 	u32	length;
-};
+} __packed;
 
 /*
  * Flash write response
@@ -564,8 +554,6 @@ struct bfi_flash_write_rsp {
 	u8	rsv[3];
 	u32	status;
 	u32	length;
-};
-
-#pragma pack()
+} __packed;
 
 #endif /* __BFI_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfi_cna.h b/drivers/net/ethernet/brocade/bna/bfi_cna.h
index bd605bee72ee..fad651101c48 100644
--- a/drivers/net/ethernet/brocade/bna/bfi_cna.h
+++ b/drivers/net/ethernet/brocade/bna/bfi_cna.h
@@ -22,8 +22,6 @@
 #include "bfi.h"
 #include "bfa_defs_cna.h"
 
-#pragma pack(1)
-
 enum bfi_port_h2i {
 	BFI_PORT_H2I_ENABLE_REQ		= (1),
 	BFI_PORT_H2I_DISABLE_REQ	= (2),
@@ -43,7 +41,7 @@ struct bfi_port_generic_req {
 	struct bfi_mhdr mh;		/*!< msg header			    */
 	u32	msgtag;		/*!< msgtag for reply		    */
 	u32	rsvd;
-};
+} __packed;
 
 /* Generic RSP type */
 struct bfi_port_generic_rsp {
@@ -51,13 +49,13 @@ struct bfi_port_generic_rsp {
 	u8		status;		/*!< port enable status		    */
 	u8		rsvd[3];
 	u32	msgtag;		/*!< msgtag for reply		    */
-};
+} __packed;
 
 /* BFI_PORT_H2I_GET_STATS_REQ */
 struct bfi_port_get_stats_req {
 	struct bfi_mhdr mh;		/*!< common msg header		    */
 	union bfi_addr_u   dma_addr;
-};
+} __packed;
 
 union bfi_port_h2i_msg_u {
 	struct bfi_mhdr mh;
@@ -65,7 +63,7 @@ union bfi_port_h2i_msg_u {
 	struct bfi_port_generic_req disable_req;
 	struct bfi_port_get_stats_req getstats_req;
 	struct bfi_port_generic_req clearstats_req;
-};
+} __packed;
 
 union bfi_port_i2h_msg_u {
 	struct bfi_mhdr mh;
@@ -73,7 +71,7 @@ union bfi_port_i2h_msg_u {
 	struct bfi_port_generic_rsp disable_rsp;
 	struct bfi_port_generic_rsp getstats_rsp;
 	struct bfi_port_generic_rsp clearstats_rsp;
-};
+} __packed;
 
 /* @brief Mailbox commands from host to (DCBX/LLDP) firmware */
 enum bfi_cee_h2i_msgs {
@@ -97,7 +95,7 @@ enum bfi_cee_i2h_msgs {
  */
 struct bfi_lldp_reset_stats {
 	struct bfi_mhdr mh;
-};
+} __packed;
 
 /*
  * @brief H2I command structure for resetting the stats.
@@ -105,7 +103,7 @@ struct bfi_lldp_reset_stats {
  */
 struct bfi_cee_reset_stats {
 	struct bfi_mhdr mh;
-};
+} __packed;
 
 /*
  * @brief  get configuration  command from host
@@ -114,7 +112,7 @@ struct bfi_cee_reset_stats {
 struct bfi_cee_get_req {
 	struct bfi_mhdr mh;
 	union bfi_addr_u   dma_addr;
-};
+} __packed;
 
 /*
  * @brief reply message from firmware
@@ -124,7 +122,7 @@ struct bfi_cee_get_rsp {
 	struct bfi_mhdr mh;
 	u8			cmd_status;
 	u8			rsvd[3];
-};
+} __packed;
 
 /*
  * @brief  get configuration  command from host
@@ -133,7 +131,7 @@ struct bfi_cee_get_rsp {
 struct bfi_cee_stats_req {
 	struct bfi_mhdr mh;
 	union bfi_addr_u   dma_addr;
-};
+} __packed;
 
 /*
  * @brief reply message from firmware
@@ -143,22 +141,20 @@ struct bfi_cee_stats_rsp {
 	struct bfi_mhdr mh;
 	u8			cmd_status;
 	u8			rsvd[3];
-};
+} __packed;
 
 /* @brief mailbox command structures from host to firmware */
 union bfi_cee_h2i_msg_u {
 	struct bfi_mhdr mh;
 	struct bfi_cee_get_req get_req;
 	struct bfi_cee_stats_req stats_req;
-};
+} __packed;
 
 /* @brief mailbox message structures from firmware to host	*/
 union bfi_cee_i2h_msg_u {
 	struct bfi_mhdr mh;
 	struct bfi_cee_get_rsp get_rsp;
 	struct bfi_cee_stats_rsp stats_rsp;
-};
-
-#pragma pack()
+} __packed;
 
 #endif /* __BFI_CNA_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bfi_enet.h b/drivers/net/ethernet/brocade/bna/bfi_enet.h
index bccca3bbadb8..d7be7ea8c7f5 100644
--- a/drivers/net/ethernet/brocade/bna/bfi_enet.h
+++ b/drivers/net/ethernet/brocade/bna/bfi_enet.h
@@ -36,8 +36,6 @@
 #include "bfa_defs.h"
 #include "bfi.h"
 
-#pragma pack(1)
-
 #define BFI_ENET_CFG_MAX		32	/* Max resources per PF */
 
 #define BFI_ENET_TXQ_PRIO_MAX		8
@@ -59,8 +57,8 @@ union bfi_addr_be_u {
 	struct {
 		u32	addr_hi;	/* Most Significant 32-bits */
 		u32	addr_lo;	/* Least Significant 32-Bits */
-	} a32;
-};
+	} __packed a32;
+} __packed;
 
 /*	T X   Q U E U E   D E F I N E S      */
 /* TxQ Vector (a.k.a. Tx-Buffer Descriptor) */
@@ -70,13 +68,13 @@ union bfi_addr_be_u {
 #define BFI_ENET_TXQ_WI_EXTENSION	(0x104)	/* Extension WI */
 
 /* TxQ Entry Control Flags */
-#define BFI_ENET_TXQ_WI_CF_FCOE_CRC	(1 << 8)
-#define BFI_ENET_TXQ_WI_CF_IPID_MODE	(1 << 5)
-#define BFI_ENET_TXQ_WI_CF_INS_PRIO	(1 << 4)
-#define BFI_ENET_TXQ_WI_CF_INS_VLAN	(1 << 3)
-#define BFI_ENET_TXQ_WI_CF_UDP_CKSUM	(1 << 2)
-#define BFI_ENET_TXQ_WI_CF_TCP_CKSUM	(1 << 1)
-#define BFI_ENET_TXQ_WI_CF_IP_CKSUM	(1 << 0)
+#define BFI_ENET_TXQ_WI_CF_FCOE_CRC	BIT(8)
+#define BFI_ENET_TXQ_WI_CF_IPID_MODE	BIT(5)
+#define BFI_ENET_TXQ_WI_CF_INS_PRIO	BIT(4)
+#define BFI_ENET_TXQ_WI_CF_INS_VLAN	BIT(3)
+#define BFI_ENET_TXQ_WI_CF_UDP_CKSUM	BIT(2)
+#define BFI_ENET_TXQ_WI_CF_TCP_CKSUM	BIT(1)
+#define BFI_ENET_TXQ_WI_CF_IP_CKSUM	BIT(0)
 
 struct bfi_enet_txq_wi_base {
 	u8			reserved;
@@ -88,28 +86,28 @@ struct bfi_enet_txq_wi_base {
 	u16			vlan_tag;
 	u16			lso_mss;	/* Only 14 LSB are valid */
 	u32			frame_length;	/* Only 24 LSB are valid */
-};
+} __packed;
 
 struct bfi_enet_txq_wi_ext {
 	u16			reserved;
 	u16			opcode;		/* BFI_ENET_TXQ_WI_EXTENSION */
 	u32			reserved2[3];
-};
+} __packed;
 
 struct bfi_enet_txq_wi_vector {			/* Tx Buffer Descriptor */
 	u16			reserved;
 	u16			length;		/* Only 14 LSB are valid */
 	union bfi_addr_be_u	addr;
-};
+} __packed;
 
 /*  TxQ Entry Structure  */
 struct bfi_enet_txq_entry {
 	union {
 		struct bfi_enet_txq_wi_base	base;
 		struct bfi_enet_txq_wi_ext	ext;
-	} wi;
+	} __packed wi;
 	struct bfi_enet_txq_wi_vector vector[BFI_ENET_TXQ_WI_VECT_MAX];
-};
+} __packed;
 
 #define wi_hdr		wi.base
 #define wi_ext_hdr	wi.ext
@@ -120,36 +118,36 @@ struct bfi_enet_txq_entry {
 /*   R X   Q U E U E   D E F I N E S   */
 struct bfi_enet_rxq_entry {
 	union bfi_addr_be_u  rx_buffer;
-};
+} __packed;
 
 /*   R X   C O M P L E T I O N   Q U E U E   D E F I N E S   */
 /* CQ Entry Flags */
-#define	BFI_ENET_CQ_EF_MAC_ERROR	(1 <<  0)
-#define	BFI_ENET_CQ_EF_FCS_ERROR	(1 <<  1)
-#define	BFI_ENET_CQ_EF_TOO_LONG		(1 <<  2)
-#define	BFI_ENET_CQ_EF_FC_CRC_OK	(1 <<  3)
+#define BFI_ENET_CQ_EF_MAC_ERROR	BIT(0)
+#define BFI_ENET_CQ_EF_FCS_ERROR	BIT(1)
+#define BFI_ENET_CQ_EF_TOO_LONG		BIT(2)
+#define BFI_ENET_CQ_EF_FC_CRC_OK	BIT(3)
 
-#define	BFI_ENET_CQ_EF_RSVD1		(1 <<  4)
-#define	BFI_ENET_CQ_EF_L4_CKSUM_OK	(1 <<  5)
-#define	BFI_ENET_CQ_EF_L3_CKSUM_OK	(1 <<  6)
-#define	BFI_ENET_CQ_EF_HDS_HEADER	(1 <<  7)
+#define BFI_ENET_CQ_EF_RSVD1		BIT(4)
+#define BFI_ENET_CQ_EF_L4_CKSUM_OK	BIT(5)
+#define BFI_ENET_CQ_EF_L3_CKSUM_OK	BIT(6)
+#define BFI_ENET_CQ_EF_HDS_HEADER	BIT(7)
 
-#define	BFI_ENET_CQ_EF_UDP		(1 <<  8)
-#define	BFI_ENET_CQ_EF_TCP		(1 <<  9)
-#define	BFI_ENET_CQ_EF_IP_OPTIONS	(1 << 10)
-#define	BFI_ENET_CQ_EF_IPV6		(1 << 11)
+#define BFI_ENET_CQ_EF_UDP		BIT(8)
+#define BFI_ENET_CQ_EF_TCP		BIT(9)
+#define BFI_ENET_CQ_EF_IP_OPTIONS	BIT(10)
+#define BFI_ENET_CQ_EF_IPV6		BIT(11)
 
-#define	BFI_ENET_CQ_EF_IPV4		(1 << 12)
-#define	BFI_ENET_CQ_EF_VLAN		(1 << 13)
-#define	BFI_ENET_CQ_EF_RSS		(1 << 14)
-#define	BFI_ENET_CQ_EF_RSVD2		(1 << 15)
+#define BFI_ENET_CQ_EF_IPV4		BIT(12)
+#define BFI_ENET_CQ_EF_VLAN		BIT(13)
+#define BFI_ENET_CQ_EF_RSS		BIT(14)
+#define BFI_ENET_CQ_EF_RSVD2		BIT(15)
 
-#define	BFI_ENET_CQ_EF_MCAST_MATCH	(1 << 16)
-#define	BFI_ENET_CQ_EF_MCAST		(1 << 17)
-#define BFI_ENET_CQ_EF_BCAST		(1 << 18)
-#define	BFI_ENET_CQ_EF_REMOTE		(1 << 19)
+#define BFI_ENET_CQ_EF_MCAST_MATCH	BIT(16)
+#define BFI_ENET_CQ_EF_MCAST		BIT(17)
+#define BFI_ENET_CQ_EF_BCAST		BIT(18)
+#define BFI_ENET_CQ_EF_REMOTE		BIT(19)
 
-#define	BFI_ENET_CQ_EF_LOCAL		(1 << 20)
+#define BFI_ENET_CQ_EF_LOCAL		BIT(20)
 
 /* CQ Entry Structure */
 struct bfi_enet_cq_entry {
@@ -161,7 +159,7 @@ struct bfi_enet_cq_entry {
 	u8	reserved1;
 	u8	reserved2;
 	u8	rxq_id;
-};
+} __packed;
 
 /*   E N E T   C O N T R O L   P A T H   C O M M A N D S   */
 struct bfi_enet_q {
@@ -169,23 +167,23 @@ struct bfi_enet_q {
 	union bfi_addr_u	first_entry;
 	u16		pages;	/* # of pages */
 	u16		page_sz;
-};
+} __packed;
 
 struct bfi_enet_txq {
 	struct bfi_enet_q	q;
 	u8			priority;
 	u8			rsvd[3];
-};
+} __packed;
 
 struct bfi_enet_rxq {
 	struct bfi_enet_q	q;
 	u16		rx_buffer_size;
 	u16		rsvd;
-};
+} __packed;
 
 struct bfi_enet_cq {
 	struct bfi_enet_q	q;
-};
+} __packed;
 
 struct bfi_enet_ib_cfg {
 	u8		int_pkt_dma;
@@ -198,16 +196,16 @@ struct bfi_enet_ib_cfg {
 	u32	inter_pkt_timeout;
 	u8		inter_pkt_count;
 	u8		rsvd1[3];
-};
+} __packed;
 
 struct bfi_enet_ib {
 	union bfi_addr_u	index_addr;
 	union {
 		u16	msix_index;
 		u16	intx_bitmask;
-	} intr;
+	} __packed intr;
 	u16		rsvd;
-};
+} __packed;
 
 /* ENET command messages */
 enum bfi_enet_h2i_msgs {
@@ -355,7 +353,7 @@ enum bfi_enet_err {
  */
 struct bfi_enet_req {
 	struct bfi_msgq_mhdr mh;
-};
+} __packed;
 
 /* Enable/Disable Request
  *
@@ -370,7 +368,7 @@ struct bfi_enet_enable_req {
 	struct		bfi_msgq_mhdr mh;
 	u8		enable;		/* 1 = enable;  0 = disable */
 	u8		rsvd[3];
-};
+} __packed;
 
 /* Generic Response */
 struct bfi_enet_rsp {
@@ -378,7 +376,7 @@ struct bfi_enet_rsp {
 	u8		error;		/*!< if error see cmd_offset */
 	u8		rsvd;
 	u16		cmd_offset;	/*!< offset to invalid parameter */
-};
+} __packed;
 
 /* GLOBAL CONFIGURATION */
 
@@ -387,7 +385,7 @@ struct bfi_enet_rsp {
  */
 struct bfi_enet_attr_req {
 	struct bfi_msgq_mhdr	mh;
-};
+} __packed;
 
 /* bfi_enet_attr_rsp is used by:
  *	BFI_ENET_I2H_GET_ATTR_RSP
@@ -400,7 +398,7 @@ struct bfi_enet_attr_rsp {
 	u32		max_cfg;
 	u32		max_ucmac;
 	u32		rit_size;
-};
+} __packed;
 
 /* Tx Configuration
  *
@@ -421,7 +419,7 @@ struct bfi_enet_tx_cfg {
 	u8		apply_vlan_filter;
 	u8		add_to_vswitch;
 	u8		rsvd1[1];
-};
+} __packed;
 
 struct bfi_enet_tx_cfg_req {
 	struct bfi_msgq_mhdr mh;
@@ -431,7 +429,7 @@ struct bfi_enet_tx_cfg_req {
 	struct {
 		struct bfi_enet_txq	q;
 		struct bfi_enet_ib	ib;
-	} q_cfg[BFI_ENET_TXQ_PRIO_MAX];
+	} __packed q_cfg[BFI_ENET_TXQ_PRIO_MAX];
 
 	struct bfi_enet_ib_cfg	ib_cfg;
 
@@ -448,7 +446,7 @@ struct bfi_enet_tx_cfg_rsp {
 		u32	i_dbell;	/* PCI base address offset */
 		u8	hw_qid;		/* For debugging */
 		u8	rsvd[3];
-	} q_handles[BFI_ENET_TXQ_PRIO_MAX];
+	} __packed q_handles[BFI_ENET_TXQ_PRIO_MAX];
 };
 
 /* Rx Configuration
@@ -481,13 +479,13 @@ struct bfi_enet_rx_cfg {
 		u8			force_offset;
 		u8			type;
 		u8			rsvd1;
-	} hds;
+	} __packed hds;
 
 	u8		multi_buffer;
 	u8		strip_vlan;
 	u8		drop_untagged;
 	u8		rsvd2;
-};
+} __packed;
 
 /*
  * Multicast frames are received on the ql of q-set index zero.
@@ -504,12 +502,12 @@ struct bfi_enet_rx_cfg_req {
 		struct bfi_enet_rxq	qs;	/* small/header buffers */
 		struct bfi_enet_cq	cq;
 		struct bfi_enet_ib	ib;
-	} q_cfg[BFI_ENET_RX_QSET_MAX];
+	} __packed q_cfg[BFI_ENET_RX_QSET_MAX];
 
 	struct bfi_enet_ib_cfg	ib_cfg;
 
 	struct bfi_enet_rx_cfg	rx_cfg;
-};
+} __packed;
 
 struct bfi_enet_rx_cfg_rsp {
 	struct bfi_msgq_mhdr mh;
@@ -524,8 +522,8 @@ struct bfi_enet_rx_cfg_rsp {
 		u8		hw_sqid;  /* For debugging */
 		u8		hw_cqid;  /* For debugging */
 		u8		rsvd;
-	} q_handles[BFI_ENET_RX_QSET_MAX];
-};
+	} __packed q_handles[BFI_ENET_RX_QSET_MAX];
+} __packed;
 
 /* RIT
  *
@@ -537,7 +535,7 @@ struct bfi_enet_rit_req {
 	u16	size;			/* number of table-entries used */
 	u8	rsvd[2];
 	u8	table[BFI_ENET_RSS_RIT_MAX];
-};
+} __packed;
 
 /* RSS
  *
@@ -556,12 +554,12 @@ struct bfi_enet_rss_cfg {
 	u8	mask;
 	u8	rsvd[2];
 	u32	key[BFI_ENET_RSS_KEY_LEN];
-};
+} __packed;
 
 struct bfi_enet_rss_cfg_req {
 	struct bfi_msgq_mhdr	mh;
 	struct bfi_enet_rss_cfg	cfg;
-};
+} __packed;
 
 /* MAC Unicast
  *
@@ -573,16 +571,16 @@ struct bfi_enet_rss_cfg_req {
  */
 struct bfi_enet_ucast_req {
 	struct bfi_msgq_mhdr	mh;
-	mac_t			mac_addr;
+	u8			mac_addr[ETH_ALEN];
 	u8			rsvd[2];
-};
+} __packed;
 
 /* MAC Unicast + VLAN */
 struct bfi_enet_mac_n_vlan_req {
 	struct bfi_msgq_mhdr	mh;
 	u16			vlan_id;
-	mac_t			mac_addr;
-};
+	u8			mac_addr[ETH_ALEN];
+} __packed;
 
 /* MAC Multicast
  *
@@ -591,9 +589,9 @@ struct bfi_enet_mac_n_vlan_req {
  */
 struct bfi_enet_mcast_add_req {
 	struct bfi_msgq_mhdr	mh;
-	mac_t			mac_addr;
+	u8			mac_addr[ETH_ALEN];
 	u8			rsvd[2];
-};
+} __packed;
 
 /* bfi_enet_mac_mfilter_add_rsp is used by:
  *	BFI_ENET_I2H_MAC_MCAST_ADD_RSP
@@ -605,7 +603,7 @@ struct bfi_enet_mcast_add_rsp {
 	u16			cmd_offset;
 	u16			handle;
 	u8			rsvd1[2];
-};
+} __packed;
 
 /* bfi_enet_mac_mfilter_del_req is used by:
  *	BFI_ENET_H2I_MAC_MCAST_DEL_REQ
@@ -614,7 +612,7 @@ struct bfi_enet_mcast_del_req {
 	struct bfi_msgq_mhdr	mh;
 	u16			handle;
 	u8			rsvd[2];
-};
+} __packed;
 
 /* VLAN
  *
@@ -626,7 +624,7 @@ struct bfi_enet_rx_vlan_req {
 	u8			block_idx;
 	u8			rsvd[3];
 	u32			bit_mask[BFI_ENET_VLAN_WORDS_MAX];
-};
+} __packed;
 
 /* PAUSE
  *
@@ -638,7 +636,7 @@ struct bfi_enet_set_pause_req {
 	u8			rsvd[2];
 	u8			tx_pause;	/* 1 = enable;  0 = disable */
 	u8			rx_pause;	/* 1 = enable;  0 = disable */
-};
+} __packed;
 
 /* DIAGNOSTICS
  *
@@ -650,7 +648,7 @@ struct bfi_enet_diag_lb_req {
 	u8			rsvd[2];
 	u8			mode;		/* cable or Serdes */
 	u8			enable;		/* 1 = enable;  0 = disable */
-};
+} __packed;
 
 /* enum for Loopback opmodes */
 enum {
@@ -671,14 +669,14 @@ struct bfi_enet_stats_req {
 	u32			rx_enet_mask;
 	u32			tx_enet_mask;
 	union bfi_addr_u	host_buffer;
-};
+} __packed;
 
 /* defines for "stats_mask" above. */
-#define BFI_ENET_STATS_MAC    (1 << 0)    /* !< MAC Statistics */
-#define BFI_ENET_STATS_BPC    (1 << 1)    /* !< Pause Stats from BPC */
-#define BFI_ENET_STATS_RAD    (1 << 2)    /* !< Rx Admission Statistics */
-#define BFI_ENET_STATS_RX_FC  (1 << 3)    /* !< Rx FC Stats from RxA */
-#define BFI_ENET_STATS_TX_FC  (1 << 4)    /* !< Tx FC Stats from TxA */
+#define BFI_ENET_STATS_MAC    BIT(0)    /* !< MAC Statistics */
+#define BFI_ENET_STATS_BPC    BIT(1)    /* !< Pause Stats from BPC */
+#define BFI_ENET_STATS_RAD    BIT(2)    /* !< Rx Admission Statistics */
+#define BFI_ENET_STATS_RX_FC  BIT(3)    /* !< Rx FC Stats from RxA */
+#define BFI_ENET_STATS_TX_FC  BIT(4)    /* !< Tx FC Stats from TxA */
 
 #define BFI_ENET_STATS_ALL    0x1f
 
@@ -699,7 +697,7 @@ struct bfi_enet_stats_txf {
 	u64 errors;
 	u64 filter_vlan;      /* frames filtered due to VLAN */
 	u64 filter_mac_sa;    /* frames filtered due to SA check */
-};
+} __packed;
 
 /* RxF Frame Statistics */
 struct bfi_enet_stats_rxf {
@@ -715,7 +713,7 @@ struct bfi_enet_stats_rxf {
 	u64 bcast;
 	u64 bcast_vlan;
 	u64 frame_drops;
-};
+} __packed;
 
 /* FC Tx Frame Statistics */
 struct bfi_enet_stats_fc_tx {
@@ -734,7 +732,7 @@ struct bfi_enet_stats_fc_tx {
 	u64 txf_parity_errors;
 	u64 txf_timeout;
 	u64 txf_fid_parity_errors;
-};
+} __packed;
 
 /* FC Rx Frame Statistics */
 struct bfi_enet_stats_fc_rx {
@@ -749,7 +747,7 @@ struct bfi_enet_stats_fc_rx {
 	u64 rxf_bcast_octets;
 	u64 rxf_bcast;
 	u64 rxf_bcast_vlan;
-};
+} __packed;
 
 /* RAD Frame Statistics */
 struct bfi_enet_stats_rad {
@@ -770,7 +768,7 @@ struct bfi_enet_stats_rad {
 	u64 rx_bcast_vlan;
 
 	u64 rx_drops;
-};
+} __packed;
 
 /* BPC Tx Registers */
 struct bfi_enet_stats_bpc {
@@ -785,7 +783,7 @@ struct bfi_enet_stats_bpc {
 	u64 rx_zero_pause[8];	/*!< Pause cancellation */
 	/*!<Pause initiation rather than retention */
 	u64 rx_first_pause[8];
-};
+} __packed;
 
 /* MAC Rx Statistics */
 struct bfi_enet_stats_mac {
@@ -838,7 +836,7 @@ struct bfi_enet_stats_mac {
 	u64 tx_oversize;
 	u64 tx_undersize;
 	u64 tx_fragments;
-};
+} __packed;
 
 /* Complete statistics, DMAed from fw to host followed by
  * BFI_ENET_I2H_STATS_GET_RSP
@@ -852,8 +850,6 @@ struct bfi_enet_stats {
 	struct bfi_enet_stats_fc_tx	fc_tx_stats;
 	struct bfi_enet_stats_rxf	rxf_stats[BFI_ENET_CFG_MAX];
 	struct bfi_enet_stats_txf	txf_stats[BFI_ENET_CFG_MAX];
-};
-
-#pragma pack()
+} __packed;
 
 #endif  /* __BFI_ENET_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/bna.h b/drivers/net/ethernet/brocade/bna/bna.h
index 8ba72b1f36d9..006dcad9a260 100644
--- a/drivers/net/ethernet/brocade/bna/bna.h
+++ b/drivers/net/ethernet/brocade/bna/bna.h
@@ -28,36 +28,8 @@ extern const u32 bna_napi_dim_vector[][BNA_BIAS_T_MAX];
 
 /*  Macros and constants  */
 
-#define BNA_IOC_TIMER_FREQ		200
-
-/* Log string size */
-#define BNA_MESSAGE_SIZE		256
-
 #define bna_is_small_rxq(_id) ((_id) & 0x1)
 
-#define BNA_MAC_IS_EQUAL(_mac1, _mac2)					\
-	(!memcmp((_mac1), (_mac2), sizeof(mac_t)))
-
-#define BNA_POWER_OF_2(x) (((x) & ((x) - 1)) == 0)
-
-#define BNA_TO_POWER_OF_2(x)						\
-do {									\
-	int _shift = 0;							\
-	while ((x) && (x) != 1) {					\
-		(x) >>= 1;						\
-		_shift++;						\
-	}								\
-	(x) <<= _shift;							\
-} while (0)
-
-#define BNA_TO_POWER_OF_2_HIGH(x)					\
-do {									\
-	int n = 1;							\
-	while (n < (x))							\
-		n <<= 1;						\
-	(x) = n;							\
-} while (0)
-
 /*
  * input : _addr-> os dma addr in host endian format,
  * output : _bna_dma_addr-> pointer to hw dma addr
@@ -80,62 +52,8 @@ do {								\
 	| ((ntohl((_bna_dma_addr)->lsb) & 0xffffffff));	\
 } while (0)
 
-#define	containing_rec(addr, type, field)				\
-	((type *)((unsigned char *)(addr) -				\
-	(unsigned char *)(&((type *)0)->field)))
-
 #define BNA_TXQ_WI_NEEDED(_vectors)	(((_vectors) + 3) >> 2)
 
-/* TxQ element is 64 bytes */
-#define BNA_TXQ_PAGE_INDEX_MAX		(PAGE_SIZE >> 6)
-#define BNA_TXQ_PAGE_INDEX_MAX_SHIFT	(PAGE_SHIFT - 6)
-
-#define BNA_TXQ_QPGE_PTR_GET(_qe_idx, _qpt_ptr, _qe_ptr, _qe_ptr_range) \
-{									\
-	unsigned int page_index;	/* index within a page */	\
-	void *page_addr;						\
-	page_index = (_qe_idx) & (BNA_TXQ_PAGE_INDEX_MAX - 1);		\
-	(_qe_ptr_range) = (BNA_TXQ_PAGE_INDEX_MAX - page_index);	\
-	page_addr = (_qpt_ptr)[((_qe_idx) >>  BNA_TXQ_PAGE_INDEX_MAX_SHIFT)];\
-	(_qe_ptr) = &((struct bna_txq_entry *)(page_addr))[page_index]; \
-}
-
-/* RxQ element is 8 bytes */
-#define BNA_RXQ_PAGE_INDEX_MAX		(PAGE_SIZE >> 3)
-#define BNA_RXQ_PAGE_INDEX_MAX_SHIFT	(PAGE_SHIFT - 3)
-
-#define BNA_RXQ_QPGE_PTR_GET(_qe_idx, _qpt_ptr, _qe_ptr, _qe_ptr_range) \
-{									\
-	unsigned int page_index;	/* index within a page */	\
-	void *page_addr;						\
-	page_index = (_qe_idx) & (BNA_RXQ_PAGE_INDEX_MAX - 1);		\
-	(_qe_ptr_range) = (BNA_RXQ_PAGE_INDEX_MAX - page_index);	\
-	page_addr = (_qpt_ptr)[((_qe_idx) >>				\
-				BNA_RXQ_PAGE_INDEX_MAX_SHIFT)];		\
-	(_qe_ptr) = &((struct bna_rxq_entry *)(page_addr))[page_index]; \
-}
-
-/* CQ element is 16 bytes */
-#define BNA_CQ_PAGE_INDEX_MAX		(PAGE_SIZE >> 4)
-#define BNA_CQ_PAGE_INDEX_MAX_SHIFT	(PAGE_SHIFT - 4)
-
-#define BNA_CQ_QPGE_PTR_GET(_qe_idx, _qpt_ptr, _qe_ptr, _qe_ptr_range)	\
-{									\
-	unsigned int page_index;	  /* index within a page */	\
-	void *page_addr;						\
-									\
-	page_index = (_qe_idx) & (BNA_CQ_PAGE_INDEX_MAX - 1);		\
-	(_qe_ptr_range) = (BNA_CQ_PAGE_INDEX_MAX - page_index);		\
-	page_addr = (_qpt_ptr)[((_qe_idx) >>				\
-				    BNA_CQ_PAGE_INDEX_MAX_SHIFT)];	\
-	(_qe_ptr) = &((struct bna_cq_entry *)(page_addr))[page_index];\
-}
-
-#define BNA_QE_INDX_2_PTR(_cast, _qe_idx, _q_base)			\
-	(&((_cast *)(_q_base))[(_qe_idx)])
-
-#define BNA_QE_INDX_RANGE(_qe_idx, _q_depth) ((_q_depth) - (_qe_idx))
-
 #define BNA_QE_INDX_ADD(_qe_idx, _qe_num, _q_depth)			\
 	((_qe_idx) = ((_qe_idx) + (_qe_num)) & ((_q_depth) - 1))
 
@@ -147,31 +65,10 @@ do {								\
 #define BNA_QE_FREE_CNT(_q_ptr, _q_depth)				\
 	(((_q_ptr)->consumer_index - (_q_ptr)->producer_index - 1) &	\
 	 ((_q_depth) - 1))
-
 #define BNA_QE_IN_USE_CNT(_q_ptr, _q_depth)				\
 	((((_q_ptr)->producer_index - (_q_ptr)->consumer_index)) &	\
 	 (_q_depth - 1))
 
-#define BNA_Q_GET_CI(_q_ptr)		((_q_ptr)->q.consumer_index)
-
-#define BNA_Q_GET_PI(_q_ptr)		((_q_ptr)->q.producer_index)
-
-#define BNA_Q_PI_ADD(_q_ptr, _num)					\
-	(_q_ptr)->q.producer_index =					\
-		(((_q_ptr)->q.producer_index + (_num)) &		\
-		((_q_ptr)->q.q_depth - 1))
-
-#define BNA_Q_CI_ADD(_q_ptr, _num)					\
-	(_q_ptr)->q.consumer_index =					\
-		(((_q_ptr)->q.consumer_index + (_num))			\
-		& ((_q_ptr)->q.q_depth - 1))
-
-#define BNA_Q_FREE_COUNT(_q_ptr)					\
-	(BNA_QE_FREE_CNT(&((_q_ptr)->q), (_q_ptr)->q.q_depth))
-
-#define BNA_Q_IN_USE_COUNT(_q_ptr)					\
-	(BNA_QE_IN_USE_CNT(&(_q_ptr)->q, (_q_ptr)->q.q_depth))
-
 #define BNA_LARGE_PKT_SIZE		1000
 
 #define BNA_UPDATE_PKT_CNT(_pkt, _len)					\
@@ -222,21 +119,6 @@ do {									\
 	}								\
 } while (0)
 
-#define	call_rxf_pause_cbfn(rxf)					\
-do {									\
-	if ((rxf)->oper_state_cbfn) {					\
-		void (*cbfn)(struct bnad *, struct bna_rx *);	\
-		struct bnad *cbarg;					\
-		cbfn = (rxf)->oper_state_cbfn;				\
-		cbarg = (rxf)->oper_state_cbarg;			\
-		(rxf)->oper_state_cbfn = NULL;				\
-		(rxf)->oper_state_cbarg = NULL;				\
-		cbfn(cbarg, rxf->rx);					\
-	}								\
-} while (0)
-
-#define	call_rxf_resume_cbfn(rxf) call_rxf_pause_cbfn(rxf)
-
 #define is_xxx_enable(mode, bitmask, xxx) ((bitmask & xxx) && (mode & xxx))
 
 #define is_xxx_disable(mode, bitmask, xxx) ((bitmask & xxx) && !(mode & xxx))
@@ -326,28 +208,24 @@ do {									\
 #define bna_rx_rid_mask(_bna) ((_bna)->rx_mod.rid_mask)
 
 #define bna_tx_from_rid(_bna, _rid, _tx)				\
-do {								    \
-	struct bna_tx_mod *__tx_mod = &(_bna)->tx_mod;	  \
-	struct bna_tx *__tx;					    \
-	struct list_head *qe;					   \
-	_tx = NULL;						     \
-	list_for_each(qe, &__tx_mod->tx_active_q) {		     \
-		__tx = (struct bna_tx *)qe;			     \
-		if (__tx->rid == (_rid)) {			      \
-			(_tx) = __tx;				   \
-			break;					  \
-		}						       \
-	}							       \
+do {									\
+	struct bna_tx_mod *__tx_mod = &(_bna)->tx_mod;			\
+	struct bna_tx *__tx;						\
+	_tx = NULL;							\
+	list_for_each_entry(__tx, &__tx_mod->tx_active_q, qe) {		\
+		if (__tx->rid == (_rid)) {				\
+			(_tx) = __tx;					\
+			break;						\
+		}							\
+	}								\
 } while (0)
 
 #define bna_rx_from_rid(_bna, _rid, _rx)				\
 do {									\
 	struct bna_rx_mod *__rx_mod = &(_bna)->rx_mod;			\
 	struct bna_rx *__rx;						\
-	struct list_head *qe;						\
 	_rx = NULL;							\
-	list_for_each(qe, &__rx_mod->rx_active_q) {			\
-		__rx = (struct bna_rx *)qe;				\
+	list_for_each_entry(__rx, &__rx_mod->rx_active_q, qe) {		\
 		if (__rx->rid == (_rid)) {				\
 			(_rx) = __rx;					\
 			break;						\
@@ -365,17 +243,14 @@ do {									\
 
 /*  Inline functions  */
 
-static inline struct bna_mac *bna_mac_find(struct list_head *q, u8 *addr)
+static inline struct bna_mac *bna_mac_find(struct list_head *q, const u8 *addr)
 {
-	struct bna_mac *mac = NULL;
-	struct list_head *qe;
-	list_for_each(qe, q) {
-		if (BNA_MAC_IS_EQUAL(((struct bna_mac *)qe)->addr, addr)) {
-			mac = (struct bna_mac *)qe;
-			break;
-		}
-	}
-	return mac;
+	struct bna_mac *mac;
+
+	list_for_each_entry(mac, q, qe)
+		if (ether_addr_equal(mac->addr, addr))
+			return mac;
+	return NULL;
 }
 
 #define bna_attr(_bna) (&(_bna)->ioceth.attr)
@@ -401,7 +276,6 @@ void bna_hw_stats_get(struct bna *bna);
 
 /* APIs for RxF */
 struct bna_mac *bna_cam_mod_mac_get(struct list_head *head);
-void bna_cam_mod_mac_put(struct list_head *tail, struct bna_mac *mac);
 struct bna_mcam_handle *bna_mcam_mod_handle_get(struct bna_mcam_mod *mod);
 void bna_mcam_mod_handle_put(struct bna_mcam_mod *mcam_mod,
 			  struct bna_mcam_handle *handle);
@@ -488,31 +362,19 @@ void bna_rx_cleanup_complete(struct bna_rx *rx);
 void bna_rx_coalescing_timeo_set(struct bna_rx *rx, int coalescing_timeo);
 void bna_rx_dim_reconfig(struct bna *bna, const u32 vector[][BNA_BIAS_T_MAX]);
 void bna_rx_dim_update(struct bna_ccb *ccb);
-enum bna_cb_status
-bna_rx_ucast_set(struct bna_rx *rx, u8 *ucmac,
-		 void (*cbfn)(struct bnad *, struct bna_rx *));
-enum bna_cb_status
-bna_rx_ucast_add(struct bna_rx *rx, u8* ucmac,
-		 void (*cbfn)(struct bnad *, struct bna_rx *));
-enum bna_cb_status
-bna_rx_ucast_del(struct bna_rx *rx, u8 *ucmac,
-		 void (*cbfn)(struct bnad *, struct bna_rx *));
-enum bna_cb_status
-bna_rx_ucast_listset(struct bna_rx *rx, int count, u8 *uclist,
-		     void (*cbfn)(struct bnad *, struct bna_rx *));
-enum bna_cb_status
-bna_rx_mcast_add(struct bna_rx *rx, u8 *mcmac,
-		 void (*cbfn)(struct bnad *, struct bna_rx *));
-enum bna_cb_status
-bna_rx_mcast_listset(struct bna_rx *rx, int count, u8 *mcmac,
-		     void (*cbfn)(struct bnad *, struct bna_rx *));
+enum bna_cb_status bna_rx_ucast_set(struct bna_rx *rx, const u8 *ucmac);
+enum bna_cb_status bna_rx_ucast_listset(struct bna_rx *rx, int count,
+					const u8 *uclist);
+enum bna_cb_status bna_rx_mcast_add(struct bna_rx *rx, const u8 *mcmac,
+				    void (*cbfn)(struct bnad *,
+						 struct bna_rx *));
+enum bna_cb_status bna_rx_mcast_listset(struct bna_rx *rx, int count,
+					const u8 *mcmac);
 void
-bna_rx_mcast_delall(struct bna_rx *rx,
-		    void (*cbfn)(struct bnad *, struct bna_rx *));
+bna_rx_mcast_delall(struct bna_rx *rx);
 enum bna_cb_status
 bna_rx_mode_set(struct bna_rx *rx, enum bna_rxmode rxmode,
-		enum bna_rxmode bitmask,
-		void (*cbfn)(struct bnad *, struct bna_rx *));
+		enum bna_rxmode bitmask);
 void bna_rx_vlan_add(struct bna_rx *rx, int vlan_id);
 void bna_rx_vlan_del(struct bna_rx *rx, int vlan_id);
 void bna_rx_vlanfilter_enable(struct bna_rx *rx);
@@ -532,11 +394,10 @@ void bna_enet_enable(struct bna_enet *enet);
 void bna_enet_disable(struct bna_enet *enet, enum bna_cleanup_type type,
 		      void (*cbfn)(void *));
 void bna_enet_pause_config(struct bna_enet *enet,
-			   struct bna_pause_config *pause_config,
-			   void (*cbfn)(struct bnad *));
+			   struct bna_pause_config *pause_config);
 void bna_enet_mtu_set(struct bna_enet *enet, int mtu,
 		      void (*cbfn)(struct bnad *));
-void bna_enet_perm_mac_get(struct bna_enet *enet, mac_t *mac);
+void bna_enet_perm_mac_get(struct bna_enet *enet, u8 *mac);
 
 /* IOCETH */
 
diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c
index deb8da6ab9cc..4e5c3874a50f 100644
--- a/drivers/net/ethernet/brocade/bna/bna_enet.c
+++ b/drivers/net/ethernet/brocade/bna/bna_enet.c
@@ -207,7 +207,7 @@ bna_bfi_stats_get_rsp(struct bna *bna, struct bfi_msgq_mhdr *msghdr)
 	for (i = 0; i < BFI_ENET_CFG_MAX; i++) {
 		stats_dst = (u64 *)&(bna->stats.hw_stats.rxf_stats[i]);
 		memset(stats_dst, 0, sizeof(struct bfi_enet_stats_rxf));
-		if (rx_enet_mask & ((u32)(1 << i))) {
+		if (rx_enet_mask & BIT(i)) {
 			int k;
 			count = sizeof(struct bfi_enet_stats_rxf) /
 				sizeof(u64);
@@ -222,7 +222,7 @@ bna_bfi_stats_get_rsp(struct bna *bna, struct bfi_msgq_mhdr *msghdr)
 	for (i = 0; i < BFI_ENET_CFG_MAX; i++) {
 		stats_dst = (u64 *)&(bna->stats.hw_stats.txf_stats[i]);
 		memset(stats_dst, 0, sizeof(struct bfi_enet_stats_txf));
-		if (tx_enet_mask & ((u32)(1 << i))) {
+		if (tx_enet_mask & BIT(i)) {
 			int k;
 			count = sizeof(struct bfi_enet_stats_txf) /
 				sizeof(u64);
@@ -884,16 +884,6 @@ do {									\
 	}								\
 } while (0)
 
-#define call_enet_pause_cbfn(enet)					\
-do {									\
-	if ((enet)->pause_cbfn) {					\
-		void (*cbfn)(struct bnad *);				\
-		cbfn = (enet)->pause_cbfn;				\
-		(enet)->pause_cbfn = NULL;				\
-		cbfn((enet)->bna->bnad);				\
-	}								\
-} while (0)
-
 #define call_enet_mtu_cbfn(enet)					\
 do {									\
 	if ((enet)->mtu_cbfn) {						\
@@ -925,7 +915,6 @@ bfa_fsm_state_decl(bna_enet, chld_stop_wait, struct bna_enet,
 static void
 bna_enet_sm_stopped_entry(struct bna_enet *enet)
 {
-	call_enet_pause_cbfn(enet);
 	call_enet_mtu_cbfn(enet);
 	call_enet_stop_cbfn(enet);
 }
@@ -947,7 +936,6 @@ bna_enet_sm_stopped(struct bna_enet *enet, enum bna_enet_event event)
 		break;
 
 	case ENET_E_PAUSE_CFG:
-		call_enet_pause_cbfn(enet);
 		break;
 
 	case ENET_E_MTU_CFG:
@@ -1039,7 +1027,6 @@ bna_enet_sm_started_entry(struct bna_enet *enet)
 	 * NOTE: Do not call bna_enet_chld_start() here, since it will be
 	 * inadvertently called during cfg_wait->started transition as well
 	 */
-	call_enet_pause_cbfn(enet);
 	call_enet_mtu_cbfn(enet);
 }
 
@@ -1211,8 +1198,6 @@ bna_enet_init(struct bna_enet *enet, struct bna *bna)
 	enet->stop_cbfn = NULL;
 	enet->stop_cbarg = NULL;
 
-	enet->pause_cbfn = NULL;
-
 	enet->mtu_cbfn = NULL;
 
 	bfa_fsm_set_state(enet, bna_enet_sm_stopped);
@@ -1308,13 +1293,10 @@ bna_enet_disable(struct bna_enet *enet, enum bna_cleanup_type type,
 
 void
 bna_enet_pause_config(struct bna_enet *enet,
-		      struct bna_pause_config *pause_config,
-		      void (*cbfn)(struct bnad *))
+		      struct bna_pause_config *pause_config)
 {
 	enet->pause_config = *pause_config;
 
-	enet->pause_cbfn = cbfn;
-
 	bfa_fsm_send_event(enet, ENET_E_PAUSE_CFG);
 }
 
@@ -1330,9 +1312,9 @@ bna_enet_mtu_set(struct bna_enet *enet, int mtu,
 }
 
 void
-bna_enet_perm_mac_get(struct bna_enet *enet, mac_t *mac)
+bna_enet_perm_mac_get(struct bna_enet *enet, u8 *mac)
 {
-	*mac = bfa_nw_ioc_get_mac(&enet->bna->ioceth.ioc);
+	bfa_nw_ioc_get_mac(&enet->bna->ioceth.ioc, mac);
 }
 
 /* IOCETH */
@@ -1810,17 +1792,13 @@ bna_ucam_mod_init(struct bna_ucam_mod *ucam_mod, struct bna *bna,
 	res_info[BNA_MOD_RES_MEM_T_UCMAC_ARRAY].res_u.mem_info.mdl[0].kva;
 
 	INIT_LIST_HEAD(&ucam_mod->free_q);
-	for (i = 0; i < bna->ioceth.attr.num_ucmac; i++) {
-		bfa_q_qe_init(&ucam_mod->ucmac[i].qe);
+	for (i = 0; i < bna->ioceth.attr.num_ucmac; i++)
 		list_add_tail(&ucam_mod->ucmac[i].qe, &ucam_mod->free_q);
-	}
 
 	/* A separate queue to allow synchronous setting of a list of MACs */
 	INIT_LIST_HEAD(&ucam_mod->del_q);
-	for (i = i; i < (bna->ioceth.attr.num_ucmac * 2); i++) {
-		bfa_q_qe_init(&ucam_mod->ucmac[i].qe);
+	for (i = i; i < (bna->ioceth.attr.num_ucmac * 2); i++)
 		list_add_tail(&ucam_mod->ucmac[i].qe, &ucam_mod->del_q);
-	}
 
 	ucam_mod->bna = bna;
 }
@@ -1828,17 +1806,6 @@ bna_ucam_mod_init(struct bna_ucam_mod *ucam_mod, struct bna *bna,
 static void
 bna_ucam_mod_uninit(struct bna_ucam_mod *ucam_mod)
 {
-	struct list_head *qe;
-	int i;
-
-	i = 0;
-	list_for_each(qe, &ucam_mod->free_q)
-		i++;
-
-	i = 0;
-	list_for_each(qe, &ucam_mod->del_q)
-		i++;
-
 	ucam_mod->bna = NULL;
 }
 
@@ -1852,27 +1819,21 @@ bna_mcam_mod_init(struct bna_mcam_mod *mcam_mod, struct bna *bna,
 	res_info[BNA_MOD_RES_MEM_T_MCMAC_ARRAY].res_u.mem_info.mdl[0].kva;
 
 	INIT_LIST_HEAD(&mcam_mod->free_q);
-	for (i = 0; i < bna->ioceth.attr.num_mcmac; i++) {
-		bfa_q_qe_init(&mcam_mod->mcmac[i].qe);
+	for (i = 0; i < bna->ioceth.attr.num_mcmac; i++)
 		list_add_tail(&mcam_mod->mcmac[i].qe, &mcam_mod->free_q);
-	}
 
 	mcam_mod->mchandle = (struct bna_mcam_handle *)
 	res_info[BNA_MOD_RES_MEM_T_MCHANDLE_ARRAY].res_u.mem_info.mdl[0].kva;
 
 	INIT_LIST_HEAD(&mcam_mod->free_handle_q);
-	for (i = 0; i < bna->ioceth.attr.num_mcmac; i++) {
-		bfa_q_qe_init(&mcam_mod->mchandle[i].qe);
+	for (i = 0; i < bna->ioceth.attr.num_mcmac; i++)
 		list_add_tail(&mcam_mod->mchandle[i].qe,
-				&mcam_mod->free_handle_q);
-	}
+			      &mcam_mod->free_handle_q);
 
 	/* A separate queue to allow synchronous setting of a list of MACs */
 	INIT_LIST_HEAD(&mcam_mod->del_q);
-	for (i = i; i < (bna->ioceth.attr.num_mcmac * 2); i++) {
-		bfa_q_qe_init(&mcam_mod->mcmac[i].qe);
+	for (i = i; i < (bna->ioceth.attr.num_mcmac * 2); i++)
 		list_add_tail(&mcam_mod->mcmac[i].qe, &mcam_mod->del_q);
-	}
 
 	mcam_mod->bna = bna;
 }
@@ -1880,18 +1841,6 @@ bna_mcam_mod_init(struct bna_mcam_mod *mcam_mod, struct bna *bna,
 static void
 bna_mcam_mod_uninit(struct bna_mcam_mod *mcam_mod)
 {
-	struct list_head *qe;
-	int i;
-
-	i = 0;
-	list_for_each(qe, &mcam_mod->free_q) i++;
-
-	i = 0;
-	list_for_each(qe, &mcam_mod->del_q) i++;
-
-	i = 0;
-	list_for_each(qe, &mcam_mod->free_handle_q) i++;
-
 	mcam_mod->bna = NULL;
 }
 
@@ -2108,32 +2057,26 @@ bna_num_rxp_set(struct bna *bna, int num_rxp)
 struct bna_mac *
 bna_cam_mod_mac_get(struct list_head *head)
 {
-	struct list_head *qe;
-
-	if (list_empty(head))
-		return NULL;
+	struct bna_mac *mac;
 
-	bfa_q_deq(head, &qe);
-	return (struct bna_mac *)qe;
-}
+	mac = list_first_entry_or_null(head, struct bna_mac, qe);
+	if (mac)
+		list_del(&mac->qe);
 
-void
-bna_cam_mod_mac_put(struct list_head *tail, struct bna_mac *mac)
-{
-	list_add_tail(&mac->qe, tail);
+	return mac;
 }
 
 struct bna_mcam_handle *
 bna_mcam_mod_handle_get(struct bna_mcam_mod *mcam_mod)
 {
-	struct list_head *qe;
-
-	if (list_empty(&mcam_mod->free_handle_q))
-		return NULL;
+	struct bna_mcam_handle *handle;
 
-	bfa_q_deq(&mcam_mod->free_handle_q, &qe);
+	handle = list_first_entry_or_null(&mcam_mod->free_handle_q,
+					  struct bna_mcam_handle, qe);
+	if (handle)
+		list_del(&handle->qe);
 
-	return (struct bna_mcam_handle *)qe;
+	return handle;
 }
 
 void
diff --git a/drivers/net/ethernet/brocade/bna/bna_hw_defs.h b/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
index 174af0e9d056..52b45c9935aa 100644
--- a/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
+++ b/drivers/net/ethernet/brocade/bna/bna_hw_defs.h
@@ -213,7 +213,7 @@ do {									\
  * 15 bits (32K) should  be large enough to accumulate, anyways, and the max.
  * acked events to h/w can be (32K + max poll weight) (currently 64).
  */
-#define	BNA_IB_MAX_ACK_EVENTS		(1 << 15)
+#define BNA_IB_MAX_ACK_EVENTS		BIT(15)
 
 /* These macros build the data portion of the TxQ/RxQ doorbell */
 #define BNA_DOORBELL_Q_PRD_IDX(_pi)	(0x80000000 | (_pi))
@@ -282,13 +282,13 @@ do {									\
 #define BNA_TXQ_WI_EXTENSION		(0x104)	/* Extension WI */
 
 /* TxQ Entry Control Flags */
-#define BNA_TXQ_WI_CF_FCOE_CRC		(1 << 8)
-#define BNA_TXQ_WI_CF_IPID_MODE		(1 << 5)
-#define BNA_TXQ_WI_CF_INS_PRIO		(1 << 4)
-#define BNA_TXQ_WI_CF_INS_VLAN		(1 << 3)
-#define BNA_TXQ_WI_CF_UDP_CKSUM		(1 << 2)
-#define BNA_TXQ_WI_CF_TCP_CKSUM		(1 << 1)
-#define BNA_TXQ_WI_CF_IP_CKSUM		(1 << 0)
+#define BNA_TXQ_WI_CF_FCOE_CRC		BIT(8)
+#define BNA_TXQ_WI_CF_IPID_MODE		BIT(5)
+#define BNA_TXQ_WI_CF_INS_PRIO		BIT(4)
+#define BNA_TXQ_WI_CF_INS_VLAN		BIT(3)
+#define BNA_TXQ_WI_CF_UDP_CKSUM		BIT(2)
+#define BNA_TXQ_WI_CF_TCP_CKSUM		BIT(1)
+#define BNA_TXQ_WI_CF_IP_CKSUM		BIT(0)
 
 #define BNA_TXQ_WI_L4_HDR_N_OFFSET(_hdr_size, _offset) \
 		(((_hdr_size) << 10) | ((_offset) & 0x3FF))
@@ -297,36 +297,36 @@ do {									\
  * Completion Q defines
  */
 /* CQ Entry Flags */
-#define	BNA_CQ_EF_MAC_ERROR	(1 <<  0)
-#define	BNA_CQ_EF_FCS_ERROR	(1 <<  1)
-#define	BNA_CQ_EF_TOO_LONG	(1 <<  2)
-#define	BNA_CQ_EF_FC_CRC_OK	(1 <<  3)
-
-#define	BNA_CQ_EF_RSVD1		(1 <<  4)
-#define	BNA_CQ_EF_L4_CKSUM_OK	(1 <<  5)
-#define	BNA_CQ_EF_L3_CKSUM_OK	(1 <<  6)
-#define	BNA_CQ_EF_HDS_HEADER	(1 <<  7)
-
-#define	BNA_CQ_EF_UDP		(1 <<  8)
-#define	BNA_CQ_EF_TCP		(1 <<  9)
-#define	BNA_CQ_EF_IP_OPTIONS	(1 << 10)
-#define	BNA_CQ_EF_IPV6		(1 << 11)
-
-#define	BNA_CQ_EF_IPV4		(1 << 12)
-#define	BNA_CQ_EF_VLAN		(1 << 13)
-#define	BNA_CQ_EF_RSS		(1 << 14)
-#define	BNA_CQ_EF_RSVD2		(1 << 15)
-
-#define	BNA_CQ_EF_MCAST_MATCH   (1 << 16)
-#define	BNA_CQ_EF_MCAST		(1 << 17)
-#define BNA_CQ_EF_BCAST		(1 << 18)
-#define	BNA_CQ_EF_REMOTE	(1 << 19)
-
-#define	BNA_CQ_EF_LOCAL		(1 << 20)
+#define BNA_CQ_EF_MAC_ERROR	BIT(0)
+#define BNA_CQ_EF_FCS_ERROR	BIT(1)
+#define BNA_CQ_EF_TOO_LONG	BIT(2)
+#define BNA_CQ_EF_FC_CRC_OK	BIT(3)
+
+#define BNA_CQ_EF_RSVD1		BIT(4)
+#define BNA_CQ_EF_L4_CKSUM_OK	BIT(5)
+#define BNA_CQ_EF_L3_CKSUM_OK	BIT(6)
+#define BNA_CQ_EF_HDS_HEADER	BIT(7)
+
+#define BNA_CQ_EF_UDP		BIT(8)
+#define BNA_CQ_EF_TCP		BIT(9)
+#define BNA_CQ_EF_IP_OPTIONS	BIT(10)
+#define BNA_CQ_EF_IPV6		BIT(11)
+
+#define BNA_CQ_EF_IPV4		BIT(12)
+#define BNA_CQ_EF_VLAN		BIT(13)
+#define BNA_CQ_EF_RSS		BIT(14)
+#define BNA_CQ_EF_RSVD2		BIT(15)
+
+#define BNA_CQ_EF_MCAST_MATCH   BIT(16)
+#define BNA_CQ_EF_MCAST		BIT(17)
+#define BNA_CQ_EF_BCAST		BIT(18)
+#define BNA_CQ_EF_REMOTE	BIT(19)
+
+#define BNA_CQ_EF_LOCAL		BIT(20)
 /* CAT2 ASIC does not use bit 21 as per the SPEC.
  * Bit 31 is set in every end of frame completion
  */
-#define BNA_CQ_EF_EOP		(1 << 31)
+#define BNA_CQ_EF_EOP		BIT(31)
 
 /* Data structures */
 
diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
index 8ab3a5f62706..5d0753cc7e73 100644
--- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
+++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c
@@ -46,7 +46,6 @@ do {									\
 
 static int bna_rxf_cfg_apply(struct bna_rxf *rxf);
 static void bna_rxf_cfg_reset(struct bna_rxf *rxf);
-static int bna_rxf_fltr_clear(struct bna_rxf *rxf);
 static int bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf);
 static int bna_rxf_promisc_cfg_apply(struct bna_rxf *rxf);
 static int bna_rxf_allmulti_cfg_apply(struct bna_rxf *rxf);
@@ -60,14 +59,10 @@ static int bna_rxf_allmulti_cfg_reset(struct bna_rxf *rxf,
 
 bfa_fsm_state_decl(bna_rxf, stopped, struct bna_rxf,
 			enum bna_rxf_event);
-bfa_fsm_state_decl(bna_rxf, paused, struct bna_rxf,
-			enum bna_rxf_event);
 bfa_fsm_state_decl(bna_rxf, cfg_wait, struct bna_rxf,
 			enum bna_rxf_event);
 bfa_fsm_state_decl(bna_rxf, started, struct bna_rxf,
 			enum bna_rxf_event);
-bfa_fsm_state_decl(bna_rxf, fltr_clr_wait, struct bna_rxf,
-			enum bna_rxf_event);
 bfa_fsm_state_decl(bna_rxf, last_resp_wait, struct bna_rxf,
 			enum bna_rxf_event);
 
@@ -82,11 +77,7 @@ bna_rxf_sm_stopped(struct bna_rxf *rxf, enum bna_rxf_event event)
 {
 	switch (event) {
 	case RXF_E_START:
-		if (rxf->flags & BNA_RXF_F_PAUSED) {
-			bfa_fsm_set_state(rxf, bna_rxf_sm_paused);
-			call_rxf_start_cbfn(rxf);
-		} else
-			bfa_fsm_set_state(rxf, bna_rxf_sm_cfg_wait);
+		bfa_fsm_set_state(rxf, bna_rxf_sm_cfg_wait);
 		break;
 
 	case RXF_E_STOP:
@@ -101,45 +92,6 @@ bna_rxf_sm_stopped(struct bna_rxf *rxf, enum bna_rxf_event event)
 		call_rxf_cam_fltr_cbfn(rxf);
 		break;
 
-	case RXF_E_PAUSE:
-		rxf->flags |= BNA_RXF_F_PAUSED;
-		call_rxf_pause_cbfn(rxf);
-		break;
-
-	case RXF_E_RESUME:
-		rxf->flags &= ~BNA_RXF_F_PAUSED;
-		call_rxf_resume_cbfn(rxf);
-		break;
-
-	default:
-		bfa_sm_fault(event);
-	}
-}
-
-static void
-bna_rxf_sm_paused_entry(struct bna_rxf *rxf)
-{
-	call_rxf_pause_cbfn(rxf);
-}
-
-static void
-bna_rxf_sm_paused(struct bna_rxf *rxf, enum bna_rxf_event event)
-{
-	switch (event) {
-	case RXF_E_STOP:
-	case RXF_E_FAIL:
-		bfa_fsm_set_state(rxf, bna_rxf_sm_stopped);
-		break;
-
-	case RXF_E_CONFIG:
-		call_rxf_cam_fltr_cbfn(rxf);
-		break;
-
-	case RXF_E_RESUME:
-		rxf->flags &= ~BNA_RXF_F_PAUSED;
-		bfa_fsm_set_state(rxf, bna_rxf_sm_cfg_wait);
-		break;
-
 	default:
 		bfa_sm_fault(event);
 	}
@@ -166,7 +118,6 @@ bna_rxf_sm_cfg_wait(struct bna_rxf *rxf, enum bna_rxf_event event)
 		bna_rxf_cfg_reset(rxf);
 		call_rxf_start_cbfn(rxf);
 		call_rxf_cam_fltr_cbfn(rxf);
-		call_rxf_resume_cbfn(rxf);
 		bfa_fsm_set_state(rxf, bna_rxf_sm_stopped);
 		break;
 
@@ -174,12 +125,6 @@ bna_rxf_sm_cfg_wait(struct bna_rxf *rxf, enum bna_rxf_event event)
 		/* No-op */
 		break;
 
-	case RXF_E_PAUSE:
-		rxf->flags |= BNA_RXF_F_PAUSED;
-		call_rxf_start_cbfn(rxf);
-		bfa_fsm_set_state(rxf, bna_rxf_sm_fltr_clr_wait);
-		break;
-
 	case RXF_E_FW_RESP:
 		if (!bna_rxf_cfg_apply(rxf)) {
 			/* No more pending config updates */
@@ -197,7 +142,6 @@ bna_rxf_sm_started_entry(struct bna_rxf *rxf)
 {
 	call_rxf_start_cbfn(rxf);
 	call_rxf_cam_fltr_cbfn(rxf);
-	call_rxf_resume_cbfn(rxf);
 }
 
 static void
@@ -214,41 +158,6 @@ bna_rxf_sm_started(struct bna_rxf *rxf, enum bna_rxf_event event)
 		bfa_fsm_set_state(rxf, bna_rxf_sm_cfg_wait);
 		break;
 
-	case RXF_E_PAUSE:
-		rxf->flags |= BNA_RXF_F_PAUSED;
-		if (!bna_rxf_fltr_clear(rxf))
-			bfa_fsm_set_state(rxf, bna_rxf_sm_paused);
-		else
-			bfa_fsm_set_state(rxf, bna_rxf_sm_fltr_clr_wait);
-		break;
-
-	default:
-		bfa_sm_fault(event);
-	}
-}
-
-static void
-bna_rxf_sm_fltr_clr_wait_entry(struct bna_rxf *rxf)
-{
-}
-
-static void
-bna_rxf_sm_fltr_clr_wait(struct bna_rxf *rxf, enum bna_rxf_event event)
-{
-	switch (event) {
-	case RXF_E_FAIL:
-		bna_rxf_cfg_reset(rxf);
-		call_rxf_pause_cbfn(rxf);
-		bfa_fsm_set_state(rxf, bna_rxf_sm_stopped);
-		break;
-
-	case RXF_E_FW_RESP:
-		if (!bna_rxf_fltr_clear(rxf)) {
-			/* No more pending CAM entries to clear */
-			bfa_fsm_set_state(rxf, bna_rxf_sm_paused);
-		}
-		break;
-
 	default:
 		bfa_sm_fault(event);
 	}
@@ -283,7 +192,7 @@ bna_bfi_ucast_req(struct bna_rxf *rxf, struct bna_mac *mac,
 	bfi_msgq_mhdr_set(req->mh, BFI_MC_ENET, req_type, 0, rxf->rx->rid);
 	req->mh.num_entries = htons(
 	bfi_msgq_num_cmd_entries(sizeof(struct bfi_enet_ucast_req)));
-	memcpy(&req->mac_addr, &mac->addr, sizeof(mac_t));
+	ether_addr_copy(req->mac_addr, mac->addr);
 	bfa_msgq_cmd_set(&rxf->msgq_cmd, NULL, NULL,
 		sizeof(struct bfi_enet_ucast_req), &req->mh);
 	bfa_msgq_cmd_post(&rxf->rx->bna->msgq, &rxf->msgq_cmd);
@@ -299,7 +208,7 @@ bna_bfi_mcast_add_req(struct bna_rxf *rxf, struct bna_mac *mac)
 		0, rxf->rx->rid);
 	req->mh.num_entries = htons(
 	bfi_msgq_num_cmd_entries(sizeof(struct bfi_enet_mcast_add_req)));
-	memcpy(&req->mac_addr, &mac->addr, sizeof(mac_t));
+	ether_addr_copy(req->mac_addr, mac->addr);
 	bfa_msgq_cmd_set(&rxf->msgq_cmd, NULL, NULL,
 		sizeof(struct bfi_enet_mcast_add_req), &req->mh);
 	bfa_msgq_cmd_post(&rxf->rx->bna->msgq, &rxf->msgq_cmd);
@@ -444,22 +353,17 @@ bna_bfi_rss_enable(struct bna_rxf *rxf)
 
 /* This function gets the multicast MAC that has already been added to CAM */
 static struct bna_mac *
-bna_rxf_mcmac_get(struct bna_rxf *rxf, u8 *mac_addr)
+bna_rxf_mcmac_get(struct bna_rxf *rxf, const u8 *mac_addr)
 {
 	struct bna_mac *mac;
-	struct list_head *qe;
 
-	list_for_each(qe, &rxf->mcast_active_q) {
-		mac = (struct bna_mac *)qe;
-		if (BNA_MAC_IS_EQUAL(&mac->addr, mac_addr))
+	list_for_each_entry(mac, &rxf->mcast_active_q, qe)
+		if (ether_addr_equal(mac->addr, mac_addr))
 			return mac;
-	}
 
-	list_for_each(qe, &rxf->mcast_pending_del_q) {
-		mac = (struct bna_mac *)qe;
-		if (BNA_MAC_IS_EQUAL(&mac->addr, mac_addr))
+	list_for_each_entry(mac, &rxf->mcast_pending_del_q, qe)
+		if (ether_addr_equal(mac->addr, mac_addr))
 			return mac;
-	}
 
 	return NULL;
 }
@@ -468,13 +372,10 @@ static struct bna_mcam_handle *
 bna_rxf_mchandle_get(struct bna_rxf *rxf, int handle)
 {
 	struct bna_mcam_handle *mchandle;
-	struct list_head *qe;
 
-	list_for_each(qe, &rxf->mcast_handle_q) {
-		mchandle = (struct bna_mcam_handle *)qe;
+	list_for_each_entry(mchandle, &rxf->mcast_handle_q, qe)
 		if (mchandle->handle == handle)
 			return mchandle;
-	}
 
 	return NULL;
 }
@@ -515,7 +416,6 @@ bna_rxf_mcast_del(struct bna_rxf *rxf, struct bna_mac *mac,
 			ret = 1;
 		}
 		list_del(&mchandle->qe);
-		bfa_q_qe_init(&mchandle->qe);
 		bna_mcam_mod_handle_put(&rxf->rx->bna->mcam_mod, mchandle);
 	}
 	mac->handle = NULL;
@@ -527,26 +427,23 @@ static int
 bna_rxf_mcast_cfg_apply(struct bna_rxf *rxf)
 {
 	struct bna_mac *mac = NULL;
-	struct list_head *qe;
 	int ret;
 
 	/* First delete multicast entries to maintain the count */
 	while (!list_empty(&rxf->mcast_pending_del_q)) {
-		bfa_q_deq(&rxf->mcast_pending_del_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->mcast_pending_del_q,
+				       struct bna_mac, qe);
 		ret = bna_rxf_mcast_del(rxf, mac, BNA_HARD_CLEANUP);
-		bna_cam_mod_mac_put(bna_mcam_mod_del_q(rxf->rx->bna), mac);
+		list_move_tail(&mac->qe, bna_mcam_mod_del_q(rxf->rx->bna));
 		if (ret)
 			return ret;
 	}
 
 	/* Add multicast entries */
 	if (!list_empty(&rxf->mcast_pending_add_q)) {
-		bfa_q_deq(&rxf->mcast_pending_add_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
-		list_add_tail(&mac->qe, &rxf->mcast_active_q);
+		mac = list_first_entry(&rxf->mcast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, &rxf->mcast_active_q);
 		bna_bfi_mcast_add_req(rxf, mac);
 		return 1;
 	}
@@ -566,7 +463,7 @@ bna_rxf_vlan_cfg_apply(struct bna_rxf *rxf)
 			block_idx++;
 			vlan_pending_bitmask >>= 1;
 		}
-		rxf->vlan_pending_bitmask &= ~(1 << block_idx);
+		rxf->vlan_pending_bitmask &= ~BIT(block_idx);
 		bna_bfi_rx_vlan_filter_set(rxf, block_idx);
 		return 1;
 	}
@@ -577,27 +474,24 @@ bna_rxf_vlan_cfg_apply(struct bna_rxf *rxf)
 static int
 bna_rxf_mcast_cfg_reset(struct bna_rxf *rxf, enum bna_cleanup_type cleanup)
 {
-	struct list_head *qe;
 	struct bna_mac *mac;
 	int ret;
 
 	/* Throw away delete pending mcast entries */
 	while (!list_empty(&rxf->mcast_pending_del_q)) {
-		bfa_q_deq(&rxf->mcast_pending_del_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->mcast_pending_del_q,
+				       struct bna_mac, qe);
 		ret = bna_rxf_mcast_del(rxf, mac, cleanup);
-		bna_cam_mod_mac_put(bna_mcam_mod_del_q(rxf->rx->bna), mac);
+		list_move_tail(&mac->qe, bna_mcam_mod_del_q(rxf->rx->bna));
 		if (ret)
 			return ret;
 	}
 
 	/* Move active mcast entries to pending_add_q */
 	while (!list_empty(&rxf->mcast_active_q)) {
-		bfa_q_deq(&rxf->mcast_active_q, &qe);
-		bfa_q_qe_init(qe);
-		list_add_tail(qe, &rxf->mcast_pending_add_q);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->mcast_active_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, &rxf->mcast_pending_add_q);
 		if (bna_rxf_mcast_del(rxf, mac, cleanup))
 			return 1;
 	}
@@ -658,25 +552,6 @@ bna_rxf_cfg_apply(struct bna_rxf *rxf)
 	return 0;
 }
 
-/* Only software reset */
-static int
-bna_rxf_fltr_clear(struct bna_rxf *rxf)
-{
-	if (bna_rxf_ucast_cfg_reset(rxf, BNA_HARD_CLEANUP))
-		return 1;
-
-	if (bna_rxf_mcast_cfg_reset(rxf, BNA_HARD_CLEANUP))
-		return 1;
-
-	if (bna_rxf_promisc_cfg_reset(rxf, BNA_HARD_CLEANUP))
-		return 1;
-
-	if (bna_rxf_allmulti_cfg_reset(rxf, BNA_HARD_CLEANUP))
-		return 1;
-
-	return 0;
-}
-
 static void
 bna_rxf_cfg_reset(struct bna_rxf *rxf)
 {
@@ -693,16 +568,13 @@ bna_rit_init(struct bna_rxf *rxf, int rit_size)
 {
 	struct bna_rx *rx = rxf->rx;
 	struct bna_rxp *rxp;
-	struct list_head *qe;
 	int offset = 0;
 
 	rxf->rit_size = rit_size;
-	list_for_each(qe, &rx->rxp_q) {
-		rxp = (struct bna_rxp *)qe;
+	list_for_each_entry(rxp, &rx->rxp_q, qe) {
 		rxf->rit[offset] = rxp->cq.ccb->id;
 		offset++;
 	}
-
 }
 
 void
@@ -760,9 +632,6 @@ bna_rxf_init(struct bna_rxf *rxf,
 	INIT_LIST_HEAD(&rxf->mcast_active_q);
 	INIT_LIST_HEAD(&rxf->mcast_handle_q);
 
-	if (q_config->paused)
-		rxf->flags |= BNA_RXF_F_PAUSED;
-
 	rxf->rit = (u8 *)
 		res_info[BNA_RX_RES_MEM_T_RIT].res_u.mem_info.mdl[0].kva;
 	bna_rit_init(rxf, q_config->num_paths);
@@ -795,22 +664,21 @@ bna_rxf_uninit(struct bna_rxf *rxf)
 	rxf->ucast_active_set = 0;
 
 	while (!list_empty(&rxf->ucast_pending_add_q)) {
-		bfa_q_deq(&rxf->ucast_pending_add_q, &mac);
-		bfa_q_qe_init(&mac->qe);
-		bna_cam_mod_mac_put(bna_ucam_mod_free_q(rxf->rx->bna), mac);
+		mac = list_first_entry(&rxf->ucast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, bna_ucam_mod_free_q(rxf->rx->bna));
 	}
 
 	if (rxf->ucast_pending_mac) {
-		bfa_q_qe_init(&rxf->ucast_pending_mac->qe);
-		bna_cam_mod_mac_put(bna_ucam_mod_free_q(rxf->rx->bna),
-				    rxf->ucast_pending_mac);
+		list_add_tail(&rxf->ucast_pending_mac->qe,
+			      bna_ucam_mod_free_q(rxf->rx->bna));
 		rxf->ucast_pending_mac = NULL;
 	}
 
 	while (!list_empty(&rxf->mcast_pending_add_q)) {
-		bfa_q_deq(&rxf->mcast_pending_add_q, &mac);
-		bfa_q_qe_init(&mac->qe);
-		bna_cam_mod_mac_put(bna_mcam_mod_free_q(rxf->rx->bna), mac);
+		mac = list_first_entry(&rxf->mcast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, bna_mcam_mod_free_q(rxf->rx->bna));
 	}
 
 	rxf->rxmode_pending = 0;
@@ -823,8 +691,6 @@ bna_rxf_uninit(struct bna_rxf *rxf)
 	rxf->rss_pending = 0;
 	rxf->vlan_strip_pending = false;
 
-	rxf->flags = 0;
-
 	rxf->rx = NULL;
 }
 
@@ -863,8 +729,7 @@ bna_rxf_fail(struct bna_rxf *rxf)
 }
 
 enum bna_cb_status
-bna_rx_ucast_set(struct bna_rx *rx, u8 *ucmac,
-		 void (*cbfn)(struct bnad *, struct bna_rx *))
+bna_rx_ucast_set(struct bna_rx *rx, const u8 *ucmac)
 {
 	struct bna_rxf *rxf = &rx->rxf;
 
@@ -873,12 +738,11 @@ bna_rx_ucast_set(struct bna_rx *rx, u8 *ucmac,
 			bna_cam_mod_mac_get(bna_ucam_mod_free_q(rxf->rx->bna));
 		if (rxf->ucast_pending_mac == NULL)
 			return BNA_CB_UCAST_CAM_FULL;
-		bfa_q_qe_init(&rxf->ucast_pending_mac->qe);
 	}
 
-	memcpy(rxf->ucast_pending_mac->addr, ucmac, ETH_ALEN);
+	ether_addr_copy(rxf->ucast_pending_mac->addr, ucmac);
 	rxf->ucast_pending_set = 1;
-	rxf->cam_fltr_cbfn = cbfn;
+	rxf->cam_fltr_cbfn = NULL;
 	rxf->cam_fltr_cbarg = rx->bna->bnad;
 
 	bfa_fsm_send_event(rxf, RXF_E_CONFIG);
@@ -887,7 +751,7 @@ bna_rx_ucast_set(struct bna_rx *rx, u8 *ucmac,
 }
 
 enum bna_cb_status
-bna_rx_mcast_add(struct bna_rx *rx, u8 *addr,
+bna_rx_mcast_add(struct bna_rx *rx, const u8 *addr,
 		 void (*cbfn)(struct bnad *, struct bna_rx *))
 {
 	struct bna_rxf *rxf = &rx->rxf;
@@ -904,8 +768,7 @@ bna_rx_mcast_add(struct bna_rx *rx, u8 *addr,
 	mac = bna_cam_mod_mac_get(bna_mcam_mod_free_q(rxf->rx->bna));
 	if (mac == NULL)
 		return BNA_CB_MCAST_LIST_FULL;
-	bfa_q_qe_init(&mac->qe);
-	memcpy(mac->addr, addr, ETH_ALEN);
+	ether_addr_copy(mac->addr, addr);
 	list_add_tail(&mac->qe, &rxf->mcast_pending_add_q);
 
 	rxf->cam_fltr_cbfn = cbfn;
@@ -917,35 +780,31 @@ bna_rx_mcast_add(struct bna_rx *rx, u8 *addr,
 }
 
 enum bna_cb_status
-bna_rx_ucast_listset(struct bna_rx *rx, int count, u8 *uclist,
-		     void (*cbfn)(struct bnad *, struct bna_rx *))
+bna_rx_ucast_listset(struct bna_rx *rx, int count, const u8 *uclist)
 {
 	struct bna_ucam_mod *ucam_mod = &rx->bna->ucam_mod;
 	struct bna_rxf *rxf = &rx->rxf;
 	struct list_head list_head;
-	struct list_head *qe;
-	u8 *mcaddr;
+	const u8 *mcaddr;
 	struct bna_mac *mac, *del_mac;
 	int i;
 
 	/* Purge the pending_add_q */
 	while (!list_empty(&rxf->ucast_pending_add_q)) {
-		bfa_q_deq(&rxf->ucast_pending_add_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
-		bna_cam_mod_mac_put(&ucam_mod->free_q, mac);
+		mac = list_first_entry(&rxf->ucast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, &ucam_mod->free_q);
 	}
 
 	/* Schedule active_q entries for deletion */
 	while (!list_empty(&rxf->ucast_active_q)) {
-		bfa_q_deq(&rxf->ucast_active_q, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-
+		mac = list_first_entry(&rxf->ucast_active_q,
+				       struct bna_mac, qe);
 		del_mac = bna_cam_mod_mac_get(&ucam_mod->del_q);
-		memcpy(del_mac, mac, sizeof(*del_mac));
+		ether_addr_copy(del_mac->addr, mac->addr);
+		del_mac->handle = mac->handle;
 		list_add_tail(&del_mac->qe, &rxf->ucast_pending_del_q);
-		bna_cam_mod_mac_put(&ucam_mod->free_q, mac);
+		list_move_tail(&mac->qe, &ucam_mod->free_q);
 	}
 
 	/* Allocate nodes */
@@ -954,69 +813,57 @@ bna_rx_ucast_listset(struct bna_rx *rx, int count, u8 *uclist,
 		mac = bna_cam_mod_mac_get(&ucam_mod->free_q);
 		if (mac == NULL)
 			goto err_return;
-		bfa_q_qe_init(&mac->qe);
-		memcpy(mac->addr, mcaddr, ETH_ALEN);
+		ether_addr_copy(mac->addr, mcaddr);
 		list_add_tail(&mac->qe, &list_head);
 		mcaddr += ETH_ALEN;
 	}
 
 	/* Add the new entries */
 	while (!list_empty(&list_head)) {
-		bfa_q_deq(&list_head, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-		list_add_tail(&mac->qe, &rxf->ucast_pending_add_q);
+		mac = list_first_entry(&list_head, struct bna_mac, qe);
+		list_move_tail(&mac->qe, &rxf->ucast_pending_add_q);
 	}
 
-	rxf->cam_fltr_cbfn = cbfn;
-	rxf->cam_fltr_cbarg = rx->bna->bnad;
 	bfa_fsm_send_event(rxf, RXF_E_CONFIG);
 
 	return BNA_CB_SUCCESS;
 
 err_return:
 	while (!list_empty(&list_head)) {
-		bfa_q_deq(&list_head, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-		bna_cam_mod_mac_put(&ucam_mod->free_q, mac);
+		mac = list_first_entry(&list_head, struct bna_mac, qe);
+		list_move_tail(&mac->qe, &ucam_mod->free_q);
 	}
 
 	return BNA_CB_UCAST_CAM_FULL;
 }
 
 enum bna_cb_status
-bna_rx_mcast_listset(struct bna_rx *rx, int count, u8 *mclist,
-		     void (*cbfn)(struct bnad *, struct bna_rx *))
+bna_rx_mcast_listset(struct bna_rx *rx, int count, const u8 *mclist)
 {
 	struct bna_mcam_mod *mcam_mod = &rx->bna->mcam_mod;
 	struct bna_rxf *rxf = &rx->rxf;
 	struct list_head list_head;
-	struct list_head *qe;
-	u8 *mcaddr;
+	const u8 *mcaddr;
 	struct bna_mac *mac, *del_mac;
 	int i;
 
 	/* Purge the pending_add_q */
 	while (!list_empty(&rxf->mcast_pending_add_q)) {
-		bfa_q_deq(&rxf->mcast_pending_add_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
-		bna_cam_mod_mac_put(&mcam_mod->free_q, mac);
+		mac = list_first_entry(&rxf->mcast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, &mcam_mod->free_q);
 	}
 
 	/* Schedule active_q entries for deletion */
 	while (!list_empty(&rxf->mcast_active_q)) {
-		bfa_q_deq(&rxf->mcast_active_q, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-
+		mac = list_first_entry(&rxf->mcast_active_q,
+				       struct bna_mac, qe);
 		del_mac = bna_cam_mod_mac_get(&mcam_mod->del_q);
-
-		memcpy(del_mac, mac, sizeof(*del_mac));
+		ether_addr_copy(del_mac->addr, mac->addr);
+		del_mac->handle = mac->handle;
 		list_add_tail(&del_mac->qe, &rxf->mcast_pending_del_q);
 		mac->handle = NULL;
-		bna_cam_mod_mac_put(&mcam_mod->free_q, mac);
+		list_move_tail(&mac->qe, &mcam_mod->free_q);
 	}
 
 	/* Allocate nodes */
@@ -1025,8 +872,7 @@ bna_rx_mcast_listset(struct bna_rx *rx, int count, u8 *mclist,
 		mac = bna_cam_mod_mac_get(&mcam_mod->free_q);
 		if (mac == NULL)
 			goto err_return;
-		bfa_q_qe_init(&mac->qe);
-		memcpy(mac->addr, mcaddr, ETH_ALEN);
+		ether_addr_copy(mac->addr, mcaddr);
 		list_add_tail(&mac->qe, &list_head);
 
 		mcaddr += ETH_ALEN;
@@ -1034,70 +880,52 @@ bna_rx_mcast_listset(struct bna_rx *rx, int count, u8 *mclist,
 
 	/* Add the new entries */
 	while (!list_empty(&list_head)) {
-		bfa_q_deq(&list_head, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-		list_add_tail(&mac->qe, &rxf->mcast_pending_add_q);
+		mac = list_first_entry(&list_head, struct bna_mac, qe);
+		list_move_tail(&mac->qe, &rxf->mcast_pending_add_q);
 	}
 
-	rxf->cam_fltr_cbfn = cbfn;
-	rxf->cam_fltr_cbarg = rx->bna->bnad;
 	bfa_fsm_send_event(rxf, RXF_E_CONFIG);
 
 	return BNA_CB_SUCCESS;
 
 err_return:
 	while (!list_empty(&list_head)) {
-		bfa_q_deq(&list_head, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-		bna_cam_mod_mac_put(&mcam_mod->free_q, mac);
+		mac = list_first_entry(&list_head, struct bna_mac, qe);
+		list_move_tail(&mac->qe, &mcam_mod->free_q);
 	}
 
 	return BNA_CB_MCAST_LIST_FULL;
 }
 
 void
-bna_rx_mcast_delall(struct bna_rx *rx,
-		    void (*cbfn)(struct bnad *, struct bna_rx *))
+bna_rx_mcast_delall(struct bna_rx *rx)
 {
 	struct bna_rxf *rxf = &rx->rxf;
-	struct list_head *qe;
 	struct bna_mac *mac, *del_mac;
 	int need_hw_config = 0;
 
 	/* Purge all entries from pending_add_q */
 	while (!list_empty(&rxf->mcast_pending_add_q)) {
-		bfa_q_deq(&rxf->mcast_pending_add_q, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-		bna_cam_mod_mac_put(bna_mcam_mod_free_q(rxf->rx->bna), mac);
+		mac = list_first_entry(&rxf->mcast_pending_add_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, bna_mcam_mod_free_q(rxf->rx->bna));
 	}
 
 	/* Schedule all entries in active_q for deletion */
 	while (!list_empty(&rxf->mcast_active_q)) {
-		bfa_q_deq(&rxf->mcast_active_q, &qe);
-		mac = (struct bna_mac *)qe;
-		bfa_q_qe_init(&mac->qe);
-
+		mac = list_first_entry(&rxf->mcast_active_q,
+				       struct bna_mac, qe);
+		list_del(&mac->qe);
 		del_mac = bna_cam_mod_mac_get(bna_mcam_mod_del_q(rxf->rx->bna));
-
 		memcpy(del_mac, mac, sizeof(*del_mac));
 		list_add_tail(&del_mac->qe, &rxf->mcast_pending_del_q);
 		mac->handle = NULL;
-		bna_cam_mod_mac_put(bna_mcam_mod_free_q(rxf->rx->bna), mac);
+		list_add_tail(&mac->qe, bna_mcam_mod_free_q(rxf->rx->bna));
 		need_hw_config = 1;
 	}
 
-	if (need_hw_config) {
-		rxf->cam_fltr_cbfn = cbfn;
-		rxf->cam_fltr_cbarg = rx->bna->bnad;
+	if (need_hw_config)
 		bfa_fsm_send_event(rxf, RXF_E_CONFIG);
-		return;
-	}
-
-	if (cbfn)
-		(*cbfn)(rx->bna->bnad, rx);
 }
 
 void
@@ -1105,12 +933,12 @@ bna_rx_vlan_add(struct bna_rx *rx, int vlan_id)
 {
 	struct bna_rxf *rxf = &rx->rxf;
 	int index = (vlan_id >> BFI_VLAN_WORD_SHIFT);
-	int bit = (1 << (vlan_id & BFI_VLAN_WORD_MASK));
+	int bit = BIT(vlan_id & BFI_VLAN_WORD_MASK);
 	int group_id = (vlan_id >> BFI_VLAN_BLOCK_SHIFT);
 
 	rxf->vlan_filter_table[index] |= bit;
 	if (rxf->vlan_filter_status == BNA_STATUS_T_ENABLED) {
-		rxf->vlan_pending_bitmask |= (1 << group_id);
+		rxf->vlan_pending_bitmask |= BIT(group_id);
 		bfa_fsm_send_event(rxf, RXF_E_CONFIG);
 	}
 }
@@ -1120,12 +948,12 @@ bna_rx_vlan_del(struct bna_rx *rx, int vlan_id)
 {
 	struct bna_rxf *rxf = &rx->rxf;
 	int index = (vlan_id >> BFI_VLAN_WORD_SHIFT);
-	int bit = (1 << (vlan_id & BFI_VLAN_WORD_MASK));
+	int bit = BIT(vlan_id & BFI_VLAN_WORD_MASK);
 	int group_id = (vlan_id >> BFI_VLAN_BLOCK_SHIFT);
 
 	rxf->vlan_filter_table[index] &= ~bit;
 	if (rxf->vlan_filter_status == BNA_STATUS_T_ENABLED) {
-		rxf->vlan_pending_bitmask |= (1 << group_id);
+		rxf->vlan_pending_bitmask |= BIT(group_id);
 		bfa_fsm_send_event(rxf, RXF_E_CONFIG);
 	}
 }
@@ -1134,23 +962,21 @@ static int
 bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf)
 {
 	struct bna_mac *mac = NULL;
-	struct list_head *qe;
 
 	/* Delete MAC addresses previousely added */
 	if (!list_empty(&rxf->ucast_pending_del_q)) {
-		bfa_q_deq(&rxf->ucast_pending_del_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->ucast_pending_del_q,
+				       struct bna_mac, qe);
 		bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_DEL_REQ);
-		bna_cam_mod_mac_put(bna_ucam_mod_del_q(rxf->rx->bna), mac);
+		list_move_tail(&mac->qe, bna_ucam_mod_del_q(rxf->rx->bna));
 		return 1;
 	}
 
 	/* Set default unicast MAC */
 	if (rxf->ucast_pending_set) {
 		rxf->ucast_pending_set = 0;
-		memcpy(rxf->ucast_active_mac.addr,
-			rxf->ucast_pending_mac->addr, ETH_ALEN);
+		ether_addr_copy(rxf->ucast_active_mac.addr,
+				rxf->ucast_pending_mac->addr);
 		rxf->ucast_active_set = 1;
 		bna_bfi_ucast_req(rxf, &rxf->ucast_active_mac,
 			BFI_ENET_H2I_MAC_UCAST_SET_REQ);
@@ -1159,9 +985,8 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf)
 
 	/* Add additional MAC entries */
 	if (!list_empty(&rxf->ucast_pending_add_q)) {
-		bfa_q_deq(&rxf->ucast_pending_add_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->ucast_pending_add_q,
+				       struct bna_mac, qe);
 		list_add_tail(&mac->qe, &rxf->ucast_active_q);
 		bna_bfi_ucast_req(rxf, mac, BFI_ENET_H2I_MAC_UCAST_ADD_REQ);
 		return 1;
@@ -1173,33 +998,30 @@ bna_rxf_ucast_cfg_apply(struct bna_rxf *rxf)
 static int
 bna_rxf_ucast_cfg_reset(struct bna_rxf *rxf, enum bna_cleanup_type cleanup)
 {
-	struct list_head *qe;
 	struct bna_mac *mac;
 
 	/* Throw away delete pending ucast entries */
 	while (!list_empty(&rxf->ucast_pending_del_q)) {
-		bfa_q_deq(&rxf->ucast_pending_del_q, &qe);
-		bfa_q_qe_init(qe);
-		mac = (struct bna_mac *)qe;
+		mac = list_first_entry(&rxf->ucast_pending_del_q,
+				       struct bna_mac, qe);
 		if (cleanup == BNA_SOFT_CLEANUP)
-			bna_cam_mod_mac_put(bna_ucam_mod_del_q(rxf->rx->bna),
-					    mac);
+			list_move_tail(&mac->qe,
+				       bna_ucam_mod_del_q(rxf->rx->bna));
 		else {
 			bna_bfi_ucast_req(rxf, mac,
-				BFI_ENET_H2I_MAC_UCAST_DEL_REQ);
-			bna_cam_mod_mac_put(bna_ucam_mod_del_q(rxf->rx->bna),
-					    mac);
+					  BFI_ENET_H2I_MAC_UCAST_DEL_REQ);
+			list_move_tail(&mac->qe,
+				       bna_ucam_mod_del_q(rxf->rx->bna));
 			return 1;
 		}
 	}
 
 	/* Move active ucast entries to pending_add_q */
 	while (!list_empty(&rxf->ucast_active_q)) {
-		bfa_q_deq(&rxf->ucast_active_q, &qe);
-		bfa_q_qe_init(qe);
-		list_add_tail(qe, &rxf->ucast_pending_add_q);
+		mac = list_first_entry(&rxf->ucast_active_q,
+				       struct bna_mac, qe);
+		list_move_tail(&mac->qe, &rxf->ucast_pending_add_q);
 		if (cleanup == BNA_HARD_CLEANUP) {
-			mac = (struct bna_mac *)qe;
 			bna_bfi_ucast_req(rxf, mac,
 				BFI_ENET_H2I_MAC_UCAST_DEL_REQ);
 			return 1;
@@ -1654,14 +1476,11 @@ static void
 bna_rx_sm_started_entry(struct bna_rx *rx)
 {
 	struct bna_rxp *rxp;
-	struct list_head *qe_rxp;
 	int is_regular = (rx->type == BNA_RX_T_REGULAR);
 
 	/* Start IB */
-	list_for_each(qe_rxp, &rx->rxp_q) {
-		rxp = (struct bna_rxp *)qe_rxp;
+	list_for_each_entry(rxp, &rx->rxp_q, qe)
 		bna_ib_start(rx->bna, &rxp->cq.ib, is_regular);
-	}
 
 	bna_ethport_cb_rx_started(&rx->bna->ethport);
 }
@@ -1804,7 +1623,6 @@ bna_bfi_rx_enet_start(struct bna_rx *rx)
 	struct bfi_enet_rx_cfg_req *cfg_req = &rx->bfi_enet_cmd.cfg_req;
 	struct bna_rxp *rxp = NULL;
 	struct bna_rxq *q0 = NULL, *q1 = NULL;
-	struct list_head *rxp_qe;
 	int i;
 
 	bfi_msgq_mhdr_set(cfg_req->mh, BFI_MC_ENET,
@@ -1814,11 +1632,9 @@ bna_bfi_rx_enet_start(struct bna_rx *rx)
 
 	cfg_req->rx_cfg.frame_size = bna_enet_mtu_get(&rx->bna->enet);
 	cfg_req->num_queue_sets = rx->num_paths;
-	for (i = 0, rxp_qe = bfa_q_first(&rx->rxp_q);
-		i < rx->num_paths;
-		i++, rxp_qe = bfa_q_next(rxp_qe)) {
-		rxp = (struct bna_rxp *)rxp_qe;
-
+	for (i = 0; i < rx->num_paths; i++) {
+		rxp = rxp ? list_next_entry(rxp, qe)
+			: list_first_entry(&rx->rxp_q, struct bna_rxp, qe);
 		GET_RXQS(rxp, q0, q1);
 		switch (rxp->type) {
 		case BNA_RXP_SLR:
@@ -1921,13 +1737,10 @@ static void
 bna_rx_enet_stop(struct bna_rx *rx)
 {
 	struct bna_rxp *rxp;
-	struct list_head		 *qe_rxp;
 
 	/* Stop IB */
-	list_for_each(qe_rxp, &rx->rxp_q) {
-		rxp = (struct bna_rxp *)qe_rxp;
+	list_for_each_entry(rxp, &rx->rxp_q, qe)
 		bna_ib_stop(rx->bna, &rxp->cq.ib);
-	}
 
 	bna_bfi_rx_enet_stop(rx);
 }
@@ -1957,12 +1770,10 @@ static struct bna_rxq *
 bna_rxq_get(struct bna_rx_mod *rx_mod)
 {
 	struct bna_rxq *rxq = NULL;
-	struct list_head	*qe = NULL;
 
-	bfa_q_deq(&rx_mod->rxq_free_q, &qe);
+	rxq = list_first_entry(&rx_mod->rxq_free_q, struct bna_rxq, qe);
+	list_del(&rxq->qe);
 	rx_mod->rxq_free_count--;
-	rxq = (struct bna_rxq *)qe;
-	bfa_q_qe_init(&rxq->qe);
 
 	return rxq;
 }
@@ -1970,7 +1781,6 @@ bna_rxq_get(struct bna_rx_mod *rx_mod)
 static void
 bna_rxq_put(struct bna_rx_mod *rx_mod, struct bna_rxq *rxq)
 {
-	bfa_q_qe_init(&rxq->qe);
 	list_add_tail(&rxq->qe, &rx_mod->rxq_free_q);
 	rx_mod->rxq_free_count++;
 }
@@ -1978,13 +1788,11 @@ bna_rxq_put(struct bna_rx_mod *rx_mod, struct bna_rxq *rxq)
 static struct bna_rxp *
 bna_rxp_get(struct bna_rx_mod *rx_mod)
 {
-	struct list_head	*qe = NULL;
 	struct bna_rxp *rxp = NULL;
 
-	bfa_q_deq(&rx_mod->rxp_free_q, &qe);
+	rxp = list_first_entry(&rx_mod->rxp_free_q, struct bna_rxp, qe);
+	list_del(&rxp->qe);
 	rx_mod->rxp_free_count--;
-	rxp = (struct bna_rxp *)qe;
-	bfa_q_qe_init(&rxp->qe);
 
 	return rxp;
 }
@@ -1992,7 +1800,6 @@ bna_rxp_get(struct bna_rx_mod *rx_mod)
 static void
 bna_rxp_put(struct bna_rx_mod *rx_mod, struct bna_rxp *rxp)
 {
-	bfa_q_qe_init(&rxp->qe);
 	list_add_tail(&rxp->qe, &rx_mod->rxp_free_q);
 	rx_mod->rxp_free_count++;
 }
@@ -2000,18 +1807,16 @@ bna_rxp_put(struct bna_rx_mod *rx_mod, struct bna_rxp *rxp)
 static struct bna_rx *
 bna_rx_get(struct bna_rx_mod *rx_mod, enum bna_rx_type type)
 {
-	struct list_head	*qe = NULL;
 	struct bna_rx *rx = NULL;
 
-	if (type == BNA_RX_T_REGULAR) {
-		bfa_q_deq(&rx_mod->rx_free_q, &qe);
-	} else
-		bfa_q_deq_tail(&rx_mod->rx_free_q, &qe);
+	BUG_ON(list_empty(&rx_mod->rx_free_q));
+	if (type == BNA_RX_T_REGULAR)
+		rx = list_first_entry(&rx_mod->rx_free_q, struct bna_rx, qe);
+	else
+		rx = list_last_entry(&rx_mod->rx_free_q, struct bna_rx, qe);
 
 	rx_mod->rx_free_count--;
-	rx = (struct bna_rx *)qe;
-	bfa_q_qe_init(&rx->qe);
-	list_add_tail(&rx->qe, &rx_mod->rx_active_q);
+	list_move_tail(&rx->qe, &rx_mod->rx_active_q);
 	rx->type = type;
 
 	return rx;
@@ -2020,32 +1825,13 @@ bna_rx_get(struct bna_rx_mod *rx_mod, enum bna_rx_type type)
 static void
 bna_rx_put(struct bna_rx_mod *rx_mod, struct bna_rx *rx)
 {
-	struct list_head *prev_qe = NULL;
 	struct list_head *qe;
 
-	bfa_q_qe_init(&rx->qe);
-
-	list_for_each(qe, &rx_mod->rx_free_q) {
+	list_for_each_prev(qe, &rx_mod->rx_free_q)
 		if (((struct bna_rx *)qe)->rid < rx->rid)
-			prev_qe = qe;
-		else
 			break;
-	}
-
-	if (prev_qe == NULL) {
-		/* This is the first entry */
-		bfa_q_enq_head(&rx_mod->rx_free_q, &rx->qe);
-	} else if (bfa_q_next(prev_qe) == &rx_mod->rx_free_q) {
-		/* This is the last entry */
-		list_add_tail(&rx->qe, &rx_mod->rx_free_q);
-	} else {
-		/* Somewhere in the middle */
-		bfa_q_next(&rx->qe) = bfa_q_next(prev_qe);
-		bfa_q_prev(&rx->qe) = prev_qe;
-		bfa_q_next(prev_qe) = &rx->qe;
-		bfa_q_prev(bfa_q_next(&rx->qe)) = &rx->qe;
-	}
 
+	list_add(&rx->qe, qe);
 	rx_mod->rx_free_count++;
 }
 
@@ -2199,24 +1985,20 @@ void
 bna_rx_mod_start(struct bna_rx_mod *rx_mod, enum bna_rx_type type)
 {
 	struct bna_rx *rx;
-	struct list_head *qe;
 
 	rx_mod->flags |= BNA_RX_MOD_F_ENET_STARTED;
 	if (type == BNA_RX_T_LOOPBACK)
 		rx_mod->flags |= BNA_RX_MOD_F_ENET_LOOPBACK;
 
-	list_for_each(qe, &rx_mod->rx_active_q) {
-		rx = (struct bna_rx *)qe;
+	list_for_each_entry(rx, &rx_mod->rx_active_q, qe)
 		if (rx->type == type)
 			bna_rx_start(rx);
-	}
 }
 
 void
 bna_rx_mod_stop(struct bna_rx_mod *rx_mod, enum bna_rx_type type)
 {
 	struct bna_rx *rx;
-	struct list_head *qe;
 
 	rx_mod->flags &= ~BNA_RX_MOD_F_ENET_STARTED;
 	rx_mod->flags &= ~BNA_RX_MOD_F_ENET_LOOPBACK;
@@ -2225,13 +2007,11 @@ bna_rx_mod_stop(struct bna_rx_mod *rx_mod, enum bna_rx_type type)
 
 	bfa_wc_init(&rx_mod->rx_stop_wc, bna_rx_mod_cb_rx_stopped_all, rx_mod);
 
-	list_for_each(qe, &rx_mod->rx_active_q) {
-		rx = (struct bna_rx *)qe;
+	list_for_each_entry(rx, &rx_mod->rx_active_q, qe)
 		if (rx->type == type) {
 			bfa_wc_up(&rx_mod->rx_stop_wc);
 			bna_rx_stop(rx);
 		}
-	}
 
 	bfa_wc_wait(&rx_mod->rx_stop_wc);
 }
@@ -2240,15 +2020,12 @@ void
 bna_rx_mod_fail(struct bna_rx_mod *rx_mod)
 {
 	struct bna_rx *rx;
-	struct list_head *qe;
 
 	rx_mod->flags &= ~BNA_RX_MOD_F_ENET_STARTED;
 	rx_mod->flags &= ~BNA_RX_MOD_F_ENET_LOOPBACK;
 
-	list_for_each(qe, &rx_mod->rx_active_q) {
-		rx = (struct bna_rx *)qe;
+	list_for_each_entry(rx, &rx_mod->rx_active_q, qe)
 		bna_rx_fail(rx);
-	}
 }
 
 void bna_rx_mod_init(struct bna_rx_mod *rx_mod, struct bna *bna,
@@ -2282,7 +2059,6 @@ void bna_rx_mod_init(struct bna_rx_mod *rx_mod, struct bna *bna,
 	for (index = 0; index < bna->ioceth.attr.num_rxp; index++) {
 		rx_ptr = &rx_mod->rx[index];
 
-		bfa_q_qe_init(&rx_ptr->qe);
 		INIT_LIST_HEAD(&rx_ptr->rxp_q);
 		rx_ptr->bna = NULL;
 		rx_ptr->rid = index;
@@ -2296,7 +2072,6 @@ void bna_rx_mod_init(struct bna_rx_mod *rx_mod, struct bna *bna,
 	/* build RX-path queue */
 	for (index = 0; index < bna->ioceth.attr.num_rxp; index++) {
 		rxp_ptr = &rx_mod->rxp[index];
-		bfa_q_qe_init(&rxp_ptr->qe);
 		list_add_tail(&rxp_ptr->qe, &rx_mod->rxp_free_q);
 		rx_mod->rxp_free_count++;
 	}
@@ -2304,7 +2079,6 @@ void bna_rx_mod_init(struct bna_rx_mod *rx_mod, struct bna *bna,
 	/* build RXQ queue */
 	for (index = 0; index < (bna->ioceth.attr.num_rxp * 2); index++) {
 		rxq_ptr = &rx_mod->rxq[index];
-		bfa_q_qe_init(&rxq_ptr->qe);
 		list_add_tail(&rxq_ptr->qe, &rx_mod->rxq_free_q);
 		rx_mod->rxq_free_count++;
 	}
@@ -2313,21 +2087,6 @@ void bna_rx_mod_init(struct bna_rx_mod *rx_mod, struct bna *bna,
 void
 bna_rx_mod_uninit(struct bna_rx_mod *rx_mod)
 {
-	struct list_head		*qe;
-	int i;
-
-	i = 0;
-	list_for_each(qe, &rx_mod->rx_free_q)
-		i++;
-
-	i = 0;
-	list_for_each(qe, &rx_mod->rxp_free_q)
-		i++;
-
-	i = 0;
-	list_for_each(qe, &rx_mod->rxq_free_q)
-		i++;
-
 	rx_mod->bna = NULL;
 }
 
@@ -2337,7 +2096,6 @@ bna_bfi_rx_enet_start_rsp(struct bna_rx *rx, struct bfi_msgq_mhdr *msghdr)
 	struct bfi_enet_rx_cfg_rsp *cfg_rsp = &rx->bfi_enet_cmd.cfg_rsp;
 	struct bna_rxp *rxp = NULL;
 	struct bna_rxq *q0 = NULL, *q1 = NULL;
-	struct list_head *rxp_qe;
 	int i;
 
 	bfa_msgq_rsp_copy(&rx->bna->msgq, (u8 *)cfg_rsp,
@@ -2345,10 +2103,8 @@ bna_bfi_rx_enet_start_rsp(struct bna_rx *rx, struct bfi_msgq_mhdr *msghdr)
 
 	rx->hw_id = cfg_rsp->hw_id;
 
-	for (i = 0, rxp_qe = bfa_q_first(&rx->rxp_q);
-		i < rx->num_paths;
-		i++, rxp_qe = bfa_q_next(rxp_qe)) {
-		rxp = (struct bna_rxp *)rxp_qe;
+	for (i = 0, rxp = list_first_entry(&rx->rxp_q, struct bna_rxp, qe);
+	     i < rx->num_paths; i++, rxp = list_next_entry(rxp, qe)) {
 		GET_RXQS(rxp, q0, q1);
 
 		/* Setup doorbells */
@@ -2396,20 +2152,19 @@ bna_rx_res_req(struct bna_rx_config *q_cfg, struct bna_res_info *res_info)
 
 	dq_depth = q_cfg->q0_depth;
 	hq_depth = ((q_cfg->rxp_type == BNA_RXP_SINGLE) ? 0 : q_cfg->q1_depth);
-	cq_depth = dq_depth + hq_depth;
+	cq_depth = roundup_pow_of_two(dq_depth + hq_depth);
 
-	BNA_TO_POWER_OF_2_HIGH(cq_depth);
 	cq_size = cq_depth * BFI_CQ_WI_SIZE;
 	cq_size = ALIGN(cq_size, PAGE_SIZE);
 	cpage_count = SIZE_TO_PAGES(cq_size);
 
-	BNA_TO_POWER_OF_2_HIGH(dq_depth);
+	dq_depth = roundup_pow_of_two(dq_depth);
 	dq_size = dq_depth * BFI_RXQ_WI_SIZE;
 	dq_size = ALIGN(dq_size, PAGE_SIZE);
 	dpage_count = SIZE_TO_PAGES(dq_size);
 
 	if (BNA_RXP_SINGLE != q_cfg->rxp_type) {
-		BNA_TO_POWER_OF_2_HIGH(hq_depth);
+		hq_depth = roundup_pow_of_two(hq_depth);
 		hq_size = hq_depth * BFI_RXQ_WI_SIZE;
 		hq_size = ALIGN(hq_size, PAGE_SIZE);
 		hpage_count = SIZE_TO_PAGES(hq_size);
@@ -2620,7 +2375,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 		if (intr_info->intr_type == BNA_INTR_T_MSIX)
 			rxp->cq.ib.intr_vector = rxp->vector;
 		else
-			rxp->cq.ib.intr_vector = (1 << rxp->vector);
+			rxp->cq.ib.intr_vector = BIT(rxp->vector);
 		rxp->cq.ib.coalescing_timeo = rx_cfg->coalescing_timeo;
 		rxp->cq.ib.interpkt_count = BFI_RX_INTERPKT_COUNT;
 		rxp->cq.ib.interpkt_timeo = BFI_RX_INTERPKT_TIMEO;
@@ -2691,7 +2446,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 		/* if multi-buffer is enabled sum of q0_depth
 		 * and q1_depth need not be a power of 2
 		 */
-		BNA_TO_POWER_OF_2_HIGH(cq_depth);
+		cq_depth = roundup_pow_of_two(cq_depth);
 		rxp->cq.ccb->q_depth = cq_depth;
 		rxp->cq.ccb->cq = &rxp->cq;
 		rxp->cq.ccb->rcb[0] = q0->rcb;
@@ -2725,7 +2480,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad,
 
 	bfa_fsm_set_state(rx, bna_rx_sm_stopped);
 
-	rx_mod->rid_mask |= (1 << rx->rid);
+	rx_mod->rid_mask |= BIT(rx->rid);
 
 	return rx;
 }
@@ -2742,7 +2497,8 @@ bna_rx_destroy(struct bna_rx *rx)
 	bna_rxf_uninit(&rx->rxf);
 
 	while (!list_empty(&rx->rxp_q)) {
-		bfa_q_deq(&rx->rxp_q, &rxp);
+		rxp = list_first_entry(&rx->rxp_q, struct bna_rxp, qe);
+		list_del(&rxp->qe);
 		GET_RXQS(rxp, q0, q1);
 		if (rx->rcb_destroy_cbfn)
 			rx->rcb_destroy_cbfn(rx->bna->bnad, q0->rcb);
@@ -2769,15 +2525,13 @@ bna_rx_destroy(struct bna_rx *rx)
 		bna_rxp_put(rx_mod, rxp);
 	}
 
-	list_for_each(qe, &rx_mod->rx_active_q) {
+	list_for_each(qe, &rx_mod->rx_active_q)
 		if (qe == &rx->qe) {
 			list_del(&rx->qe);
-			bfa_q_qe_init(&rx->qe);
 			break;
 		}
-	}
 
-	rx_mod->rid_mask &= ~(1 << rx->rid);
+	rx_mod->rid_mask &= ~BIT(rx->rid);
 
 	rx->bna = NULL;
 	rx->priv = NULL;
@@ -2844,8 +2598,7 @@ bna_rx_vlan_strip_disable(struct bna_rx *rx)
 
 enum bna_cb_status
 bna_rx_mode_set(struct bna_rx *rx, enum bna_rxmode new_mode,
-		enum bna_rxmode bitmask,
-		void (*cbfn)(struct bnad *, struct bna_rx *))
+		enum bna_rxmode bitmask)
 {
 	struct bna_rxf *rxf = &rx->rxf;
 	int need_hw_config = 0;
@@ -2900,11 +2653,10 @@ bna_rx_mode_set(struct bna_rx *rx, enum bna_rxmode new_mode,
 	/* Trigger h/w if needed */
 
 	if (need_hw_config) {
-		rxf->cam_fltr_cbfn = cbfn;
+		rxf->cam_fltr_cbfn = NULL;
 		rxf->cam_fltr_cbarg = rx->bna->bnad;
 		bfa_fsm_send_event(rxf, RXF_E_CONFIG);
-	} else if (cbfn)
-		(*cbfn)(rx->bna->bnad, rx);
+	}
 
 	return BNA_CB_SUCCESS;
 
@@ -2928,10 +2680,8 @@ void
 bna_rx_coalescing_timeo_set(struct bna_rx *rx, int coalescing_timeo)
 {
 	struct bna_rxp *rxp;
-	struct list_head *qe;
 
-	list_for_each(qe, &rx->rxp_q) {
-		rxp = (struct bna_rxp *)qe;
+	list_for_each_entry(rxp, &rx->rxp_q, qe) {
 		rxp->cq.ccb->rx_coalescing_timeo = coalescing_timeo;
 		bna_ib_coalescing_timeo_set(&rxp->cq.ib, coalescing_timeo);
 	}
@@ -3024,16 +2774,6 @@ do {									\
 	}								\
 } while (0)
 
-#define call_tx_prio_change_cbfn(tx)					\
-do {									\
-	if ((tx)->prio_change_cbfn) {					\
-		void (*cbfn)(struct bnad *, struct bna_tx *);	\
-		cbfn = (tx)->prio_change_cbfn;				\
-		(tx)->prio_change_cbfn = NULL;				\
-		cbfn((tx)->bna->bnad, (tx));				\
-	}								\
-} while (0)
-
 static void bna_tx_mod_cb_tx_stopped(void *tx_mod, struct bna_tx *tx);
 static void bna_bfi_tx_enet_start(struct bna_tx *tx);
 static void bna_tx_enet_stop(struct bna_tx *tx);
@@ -3044,7 +2784,6 @@ enum bna_tx_event {
 	TX_E_FAIL			= 3,
 	TX_E_STARTED			= 4,
 	TX_E_STOPPED			= 5,
-	TX_E_PRIO_CHANGE		= 6,
 	TX_E_CLEANUP_DONE		= 7,
 	TX_E_BW_UPDATE			= 8,
 };
@@ -3085,10 +2824,6 @@ bna_tx_sm_stopped(struct bna_tx *tx, enum bna_tx_event event)
 		/* No-op */
 		break;
 
-	case TX_E_PRIO_CHANGE:
-		call_tx_prio_change_cbfn(tx);
-		break;
-
 	case TX_E_BW_UPDATE:
 		/* No-op */
 		break;
@@ -3109,28 +2844,23 @@ bna_tx_sm_start_wait(struct bna_tx *tx, enum bna_tx_event event)
 {
 	switch (event) {
 	case TX_E_STOP:
-		tx->flags &= ~(BNA_TX_F_PRIO_CHANGED | BNA_TX_F_BW_UPDATED);
+		tx->flags &= ~BNA_TX_F_BW_UPDATED;
 		bfa_fsm_set_state(tx, bna_tx_sm_stop_wait);
 		break;
 
 	case TX_E_FAIL:
-		tx->flags &= ~(BNA_TX_F_PRIO_CHANGED | BNA_TX_F_BW_UPDATED);
+		tx->flags &= ~BNA_TX_F_BW_UPDATED;
 		bfa_fsm_set_state(tx, bna_tx_sm_stopped);
 		break;
 
 	case TX_E_STARTED:
-		if (tx->flags & (BNA_TX_F_PRIO_CHANGED | BNA_TX_F_BW_UPDATED)) {
-			tx->flags &= ~(BNA_TX_F_PRIO_CHANGED |
-				BNA_TX_F_BW_UPDATED);
+		if (tx->flags & BNA_TX_F_BW_UPDATED) {
+			tx->flags &= ~BNA_TX_F_BW_UPDATED;
 			bfa_fsm_set_state(tx, bna_tx_sm_prio_stop_wait);
 		} else
 			bfa_fsm_set_state(tx, bna_tx_sm_started);
 		break;
 
-	case TX_E_PRIO_CHANGE:
-		tx->flags |=  BNA_TX_F_PRIO_CHANGED;
-		break;
-
 	case TX_E_BW_UPDATE:
 		tx->flags |= BNA_TX_F_BW_UPDATED;
 		break;
@@ -3144,11 +2874,9 @@ static void
 bna_tx_sm_started_entry(struct bna_tx *tx)
 {
 	struct bna_txq *txq;
-	struct list_head		 *qe;
 	int is_regular = (tx->type == BNA_TX_T_REGULAR);
 
-	list_for_each(qe, &tx->txq_q) {
-		txq = (struct bna_txq *)qe;
+	list_for_each_entry(txq, &tx->txq_q, qe) {
 		txq->tcb->priority = txq->priority;
 		/* Start IB */
 		bna_ib_start(tx->bna, &txq->ib, is_regular);
@@ -3172,7 +2900,6 @@ bna_tx_sm_started(struct bna_tx *tx, enum bna_tx_event event)
 		tx->tx_cleanup_cbfn(tx->bna->bnad, tx);
 		break;
 
-	case TX_E_PRIO_CHANGE:
 	case TX_E_BW_UPDATE:
 		bfa_fsm_set_state(tx, bna_tx_sm_prio_stop_wait);
 		break;
@@ -3205,7 +2932,6 @@ bna_tx_sm_stop_wait(struct bna_tx *tx, enum bna_tx_event event)
 		bna_tx_enet_stop(tx);
 		break;
 
-	case TX_E_PRIO_CHANGE:
 	case TX_E_BW_UPDATE:
 		/* No-op */
 		break;
@@ -3225,7 +2951,6 @@ bna_tx_sm_cleanup_wait(struct bna_tx *tx, enum bna_tx_event event)
 {
 	switch (event) {
 	case TX_E_FAIL:
-	case TX_E_PRIO_CHANGE:
 	case TX_E_BW_UPDATE:
 		/* No-op */
 		break;
@@ -3256,7 +2981,6 @@ bna_tx_sm_prio_stop_wait(struct bna_tx *tx, enum bna_tx_event event)
 
 	case TX_E_FAIL:
 		bfa_fsm_set_state(tx, bna_tx_sm_failed);
-		call_tx_prio_change_cbfn(tx);
 		tx->tx_cleanup_cbfn(tx->bna->bnad, tx);
 		break;
 
@@ -3264,7 +2988,6 @@ bna_tx_sm_prio_stop_wait(struct bna_tx *tx, enum bna_tx_event event)
 		bfa_fsm_set_state(tx, bna_tx_sm_prio_cleanup_wait);
 		break;
 
-	case TX_E_PRIO_CHANGE:
 	case TX_E_BW_UPDATE:
 		/* No-op */
 		break;
@@ -3277,7 +3000,6 @@ bna_tx_sm_prio_stop_wait(struct bna_tx *tx, enum bna_tx_event event)
 static void
 bna_tx_sm_prio_cleanup_wait_entry(struct bna_tx *tx)
 {
-	call_tx_prio_change_cbfn(tx);
 	tx->tx_cleanup_cbfn(tx->bna->bnad, tx);
 }
 
@@ -3293,7 +3015,6 @@ bna_tx_sm_prio_cleanup_wait(struct bna_tx *tx, enum bna_tx_event event)
 		bfa_fsm_set_state(tx, bna_tx_sm_failed);
 		break;
 
-	case TX_E_PRIO_CHANGE:
 	case TX_E_BW_UPDATE:
 		/* No-op */
 		break;
@@ -3372,7 +3093,6 @@ bna_bfi_tx_enet_start(struct bna_tx *tx)
 {
 	struct bfi_enet_tx_cfg_req *cfg_req = &tx->bfi_enet_cmd.cfg_req;
 	struct bna_txq *txq = NULL;
-	struct list_head *qe;
 	int i;
 
 	bfi_msgq_mhdr_set(cfg_req->mh, BFI_MC_ENET,
@@ -3381,11 +3101,9 @@ bna_bfi_tx_enet_start(struct bna_tx *tx)
 		bfi_msgq_num_cmd_entries(sizeof(struct bfi_enet_tx_cfg_req)));
 
 	cfg_req->num_queues = tx->num_txq;
-	for (i = 0, qe = bfa_q_first(&tx->txq_q);
-		i < tx->num_txq;
-		i++, qe = bfa_q_next(qe)) {
-		txq = (struct bna_txq *)qe;
-
+	for (i = 0; i < tx->num_txq; i++) {
+		txq = txq ? list_next_entry(txq, qe)
+			: list_first_entry(&tx->txq_q, struct bna_txq, qe);
 		bfi_enet_datapath_q_init(&cfg_req->q_cfg[i].q.q, &txq->qpt);
 		cfg_req->q_cfg[i].q.priority = txq->priority;
 
@@ -3437,13 +3155,10 @@ static void
 bna_tx_enet_stop(struct bna_tx *tx)
 {
 	struct bna_txq *txq;
-	struct list_head		 *qe;
 
 	/* Stop IB */
-	list_for_each(qe, &tx->txq_q) {
-		txq = (struct bna_txq *)qe;
+	list_for_each_entry(txq, &tx->txq_q, qe)
 		bna_ib_stop(tx->bna, &txq->ib);
-	}
 
 	bna_bfi_tx_enet_stop(tx);
 }
@@ -3487,18 +3202,15 @@ bna_txq_qpt_setup(struct bna_txq *txq, int page_count, int page_size,
 static struct bna_tx *
 bna_tx_get(struct bna_tx_mod *tx_mod, enum bna_tx_type type)
 {
-	struct list_head	*qe = NULL;
 	struct bna_tx *tx = NULL;
 
 	if (list_empty(&tx_mod->tx_free_q))
 		return NULL;
-	if (type == BNA_TX_T_REGULAR) {
-		bfa_q_deq(&tx_mod->tx_free_q, &qe);
-	} else {
-		bfa_q_deq_tail(&tx_mod->tx_free_q, &qe);
-	}
-	tx = (struct bna_tx *)qe;
-	bfa_q_qe_init(&tx->qe);
+	if (type == BNA_TX_T_REGULAR)
+		tx = list_first_entry(&tx_mod->tx_free_q, struct bna_tx, qe);
+	else
+		tx = list_last_entry(&tx_mod->tx_free_q, struct bna_tx, qe);
+	list_del(&tx->qe);
 	tx->type = type;
 
 	return tx;
@@ -3509,21 +3221,18 @@ bna_tx_free(struct bna_tx *tx)
 {
 	struct bna_tx_mod *tx_mod = &tx->bna->tx_mod;
 	struct bna_txq *txq;
-	struct list_head *prev_qe;
 	struct list_head *qe;
 
 	while (!list_empty(&tx->txq_q)) {
-		bfa_q_deq(&tx->txq_q, &txq);
-		bfa_q_qe_init(&txq->qe);
+		txq = list_first_entry(&tx->txq_q, struct bna_txq, qe);
 		txq->tcb = NULL;
 		txq->tx = NULL;
-		list_add_tail(&txq->qe, &tx_mod->txq_free_q);
+		list_move_tail(&txq->qe, &tx_mod->txq_free_q);
 	}
 
 	list_for_each(qe, &tx_mod->tx_active_q) {
 		if (qe == &tx->qe) {
 			list_del(&tx->qe);
-			bfa_q_qe_init(&tx->qe);
 			break;
 		}
 	}
@@ -3531,28 +3240,11 @@ bna_tx_free(struct bna_tx *tx)
 	tx->bna = NULL;
 	tx->priv = NULL;
 
-	prev_qe = NULL;
-	list_for_each(qe, &tx_mod->tx_free_q) {
+	list_for_each_prev(qe, &tx_mod->tx_free_q)
 		if (((struct bna_tx *)qe)->rid < tx->rid)
-			prev_qe = qe;
-		else {
 			break;
-		}
-	}
 
-	if (prev_qe == NULL) {
-		/* This is the first entry */
-		bfa_q_enq_head(&tx_mod->tx_free_q, &tx->qe);
-	} else if (bfa_q_next(prev_qe) == &tx_mod->tx_free_q) {
-		/* This is the last entry */
-		list_add_tail(&tx->qe, &tx_mod->tx_free_q);
-	} else {
-		/* Somewhere in the middle */
-		bfa_q_next(&tx->qe) = bfa_q_next(prev_qe);
-		bfa_q_prev(&tx->qe) = prev_qe;
-		bfa_q_next(prev_qe) = &tx->qe;
-		bfa_q_prev(bfa_q_next(&tx->qe)) = &tx->qe;
-	}
+	list_add(&tx->qe, qe);
 }
 
 static void
@@ -3585,7 +3277,6 @@ bna_bfi_tx_enet_start_rsp(struct bna_tx *tx, struct bfi_msgq_mhdr *msghdr)
 {
 	struct bfi_enet_tx_cfg_rsp *cfg_rsp = &tx->bfi_enet_cmd.cfg_rsp;
 	struct bna_txq *txq = NULL;
-	struct list_head *qe;
 	int i;
 
 	bfa_msgq_rsp_copy(&tx->bna->msgq, (u8 *)cfg_rsp,
@@ -3593,10 +3284,8 @@ bna_bfi_tx_enet_start_rsp(struct bna_tx *tx, struct bfi_msgq_mhdr *msghdr)
 
 	tx->hw_id = cfg_rsp->hw_id;
 
-	for (i = 0, qe = bfa_q_first(&tx->txq_q);
-		i < tx->num_txq; i++, qe = bfa_q_next(qe)) {
-		txq = (struct bna_txq *)qe;
-
+	for (i = 0, txq = list_first_entry(&tx->txq_q, struct bna_txq, qe);
+	     i < tx->num_txq; i++, txq = list_next_entry(txq, qe)) {
 		/* Setup doorbells */
 		txq->tcb->i_dbell->doorbell_addr =
 			tx->bna->pcidev.pci_bar_kva
@@ -3624,12 +3313,9 @@ void
 bna_bfi_bw_update_aen(struct bna_tx_mod *tx_mod)
 {
 	struct bna_tx *tx;
-	struct list_head		*qe;
 
-	list_for_each(qe, &tx_mod->tx_active_q) {
-		tx = (struct bna_tx *)qe;
+	list_for_each_entry(tx, &tx_mod->tx_active_q, qe)
 		bfa_fsm_send_event(tx, TX_E_BW_UPDATE);
-	}
 }
 
 void
@@ -3689,7 +3375,6 @@ bna_tx_create(struct bna *bna, struct bnad *bnad,
 	struct bna_tx_mod *tx_mod = &bna->tx_mod;
 	struct bna_tx *tx;
 	struct bna_txq *txq;
-	struct list_head *qe;
 	int page_count;
 	int i;
 
@@ -3719,9 +3404,8 @@ bna_tx_create(struct bna *bna, struct bnad *bnad,
 		if (list_empty(&tx_mod->txq_free_q))
 			goto err_return;
 
-		bfa_q_deq(&tx_mod->txq_free_q, &txq);
-		bfa_q_qe_init(&txq->qe);
-		list_add_tail(&txq->qe, &tx->txq_q);
+		txq = list_first_entry(&tx_mod->txq_free_q, struct bna_txq, qe);
+		list_move_tail(&txq->qe, &tx->txq_q);
 		txq->tx = tx;
 	}
 
@@ -3760,8 +3444,7 @@ bna_tx_create(struct bna *bna, struct bnad *bnad,
 	/* TxQ */
 
 	i = 0;
-	list_for_each(qe, &tx->txq_q) {
-		txq = (struct bna_txq *)qe;
+	list_for_each_entry(txq, &tx->txq_q, qe) {
 		txq->tcb = (struct bna_tcb *)
 		res_info[BNA_TX_RES_MEM_T_TCB].res_u.mem_info.mdl[i].kva;
 		txq->tx_packets = 0;
@@ -3779,7 +3462,7 @@ bna_tx_create(struct bna *bna, struct bnad *bnad,
 					intr_info->idl[0].vector :
 					intr_info->idl[i].vector;
 		if (intr_info->intr_type == BNA_INTR_T_INTX)
-			txq->ib.intr_vector = (1 <<  txq->ib.intr_vector);
+			txq->ib.intr_vector = BIT(txq->ib.intr_vector);
 		txq->ib.coalescing_timeo = tx_cfg->coalescing_timeo;
 		txq->ib.interpkt_timeo = BFI_TX_INTERPKT_TIMEO;
 		txq->ib.interpkt_count = BFI_TX_INTERPKT_COUNT;
@@ -3821,7 +3504,7 @@ bna_tx_create(struct bna *bna, struct bnad *bnad,
 
 	bfa_fsm_set_state(tx, bna_tx_sm_stopped);
 
-	tx_mod->rid_mask |= (1 << tx->rid);
+	tx_mod->rid_mask |= BIT(tx->rid);
 
 	return tx;
 
@@ -3834,15 +3517,12 @@ void
 bna_tx_destroy(struct bna_tx *tx)
 {
 	struct bna_txq *txq;
-	struct list_head *qe;
 
-	list_for_each(qe, &tx->txq_q) {
-		txq = (struct bna_txq *)qe;
+	list_for_each_entry(txq, &tx->txq_q, qe)
 		if (tx->tcb_destroy_cbfn)
 			(tx->tcb_destroy_cbfn)(tx->bna->bnad, txq->tcb);
-	}
 
-	tx->bna->tx_mod.rid_mask &= ~(1 << tx->rid);
+	tx->bna->tx_mod.rid_mask &= ~BIT(tx->rid);
 	bna_tx_free(tx);
 }
 
@@ -3920,9 +3600,7 @@ bna_tx_mod_init(struct bna_tx_mod *tx_mod, struct bna *bna,
 
 	for (i = 0; i < bna->ioceth.attr.num_txq; i++) {
 		tx_mod->tx[i].rid = i;
-		bfa_q_qe_init(&tx_mod->tx[i].qe);
 		list_add_tail(&tx_mod->tx[i].qe, &tx_mod->tx_free_q);
-		bfa_q_qe_init(&tx_mod->txq[i].qe);
 		list_add_tail(&tx_mod->txq[i].qe, &tx_mod->txq_free_q);
 	}
 
@@ -3935,17 +3613,6 @@ bna_tx_mod_init(struct bna_tx_mod *tx_mod, struct bna *bna,
 void
 bna_tx_mod_uninit(struct bna_tx_mod *tx_mod)
 {
-	struct list_head		*qe;
-	int i;
-
-	i = 0;
-	list_for_each(qe, &tx_mod->tx_free_q)
-		i++;
-
-	i = 0;
-	list_for_each(qe, &tx_mod->txq_free_q)
-		i++;
-
 	tx_mod->bna = NULL;
 }
 
@@ -3953,24 +3620,20 @@ void
 bna_tx_mod_start(struct bna_tx_mod *tx_mod, enum bna_tx_type type)
 {
 	struct bna_tx *tx;
-	struct list_head		*qe;
 
 	tx_mod->flags |= BNA_TX_MOD_F_ENET_STARTED;
 	if (type == BNA_TX_T_LOOPBACK)
 		tx_mod->flags |= BNA_TX_MOD_F_ENET_LOOPBACK;
 
-	list_for_each(qe, &tx_mod->tx_active_q) {
-		tx = (struct bna_tx *)qe;
+	list_for_each_entry(tx, &tx_mod->tx_active_q, qe)
 		if (tx->type == type)
 			bna_tx_start(tx);
-	}
 }
 
 void
 bna_tx_mod_stop(struct bna_tx_mod *tx_mod, enum bna_tx_type type)
 {
 	struct bna_tx *tx;
-	struct list_head		*qe;
 
 	tx_mod->flags &= ~BNA_TX_MOD_F_ENET_STARTED;
 	tx_mod->flags &= ~BNA_TX_MOD_F_ENET_LOOPBACK;
@@ -3979,13 +3642,11 @@ bna_tx_mod_stop(struct bna_tx_mod *tx_mod, enum bna_tx_type type)
 
 	bfa_wc_init(&tx_mod->tx_stop_wc, bna_tx_mod_cb_tx_stopped_all, tx_mod);
 
-	list_for_each(qe, &tx_mod->tx_active_q) {
-		tx = (struct bna_tx *)qe;
+	list_for_each_entry(tx, &tx_mod->tx_active_q, qe)
 		if (tx->type == type) {
 			bfa_wc_up(&tx_mod->tx_stop_wc);
 			bna_tx_stop(tx);
 		}
-	}
 
 	bfa_wc_wait(&tx_mod->tx_stop_wc);
 }
@@ -3994,25 +3655,19 @@ void
 bna_tx_mod_fail(struct bna_tx_mod *tx_mod)
 {
 	struct bna_tx *tx;
-	struct list_head		*qe;
 
 	tx_mod->flags &= ~BNA_TX_MOD_F_ENET_STARTED;
 	tx_mod->flags &= ~BNA_TX_MOD_F_ENET_LOOPBACK;
 
-	list_for_each(qe, &tx_mod->tx_active_q) {
-		tx = (struct bna_tx *)qe;
+	list_for_each_entry(tx, &tx_mod->tx_active_q, qe)
 		bna_tx_fail(tx);
-	}
 }
 
 void
 bna_tx_coalescing_timeo_set(struct bna_tx *tx, int coalescing_timeo)
 {
 	struct bna_txq *txq;
-	struct list_head *qe;
 
-	list_for_each(qe, &tx->txq_q) {
-		txq = (struct bna_txq *)qe;
+	list_for_each_entry(txq, &tx->txq_q, qe)
 		bna_ib_coalescing_timeo_set(&txq->ib, coalescing_timeo);
-	}
 }
diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
index d0a7a566f5d6..e0e797f2ea14 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -135,7 +135,6 @@ enum bna_tx_type {
 enum bna_tx_flags {
 	BNA_TX_F_ENET_STARTED	= 1,
 	BNA_TX_F_ENABLED	= 2,
-	BNA_TX_F_PRIO_CHANGED	= 4,
 	BNA_TX_F_BW_UPDATED	= 8,
 };
 
@@ -182,17 +181,11 @@ enum bna_rx_mod_flags {
 	BNA_RX_MOD_F_ENET_LOOPBACK	= 2,
 };
 
-enum bna_rxf_flags {
-	BNA_RXF_F_PAUSED		= 1,
-};
-
 enum bna_rxf_event {
 	RXF_E_START			= 1,
 	RXF_E_STOP			= 2,
 	RXF_E_FAIL			= 3,
 	RXF_E_CONFIG			= 4,
-	RXF_E_PAUSE			= 5,
-	RXF_E_RESUME			= 6,
 	RXF_E_FW_RESP			= 7,
 };
 
@@ -362,9 +355,6 @@ struct bna_enet {
 	void (*stop_cbfn)(void *);
 	void			*stop_cbarg;
 
-	/* Callback for bna_enet_pause_config() */
-	void (*pause_cbfn)(struct bnad *);
-
 	/* Callback for bna_enet_mtu_set() */
 	void (*mtu_cbfn)(struct bnad *);
 
@@ -498,9 +488,6 @@ struct bna_tx {
 	void (*stop_cbfn)(void *arg, struct bna_tx *tx);
 	void			*stop_cbarg;
 
-	/* callback for bna_tx_prio_set() */
-	void (*prio_change_cbfn)(struct bnad *bnad, struct bna_tx *tx);
-
 	struct bfa_msgq_cmd_entry msgq_cmd;
 	union {
 		struct bfi_enet_tx_cfg_req	cfg_req;
@@ -676,7 +663,6 @@ struct bna_rx_config {
 	enum bna_rx_type rx_type;
 	int			num_paths;
 	enum bna_rxp_type rxp_type;
-	int			paused;
 	int			coalescing_timeo;
 	/*
 	 * Small/Large (or Header/Data) buffer size to be configured
@@ -721,7 +707,6 @@ struct bna_rxp {
 /* RxF structure (hardware Rx Function) */
 struct bna_rxf {
 	bfa_fsm_t		fsm;
-	enum bna_rxf_flags flags;
 
 	struct bfa_msgq_cmd_entry msgq_cmd;
 	union {
@@ -742,10 +727,6 @@ struct bna_rxf {
 	void (*stop_cbfn) (struct bna_rx *rx);
 	struct bna_rx *stop_cbarg;
 
-	/* callback for bna_rx_receive_pause() / bna_rx_receive_resume() */
-	void (*oper_state_cbfn) (struct bnad *bnad, struct bna_rx *rx);
-	struct bnad *oper_state_cbarg;
-
 	/**
 	 * callback for:
 	 *	bna_rxf_ucast_set()
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 37072a83f9d6..0612b19f6313 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -57,7 +57,8 @@ static u32 bnad_rxqs_per_cq = 2;
 static u32 bna_id;
 static struct mutex bnad_list_mutex;
 static LIST_HEAD(bnad_list);
-static const u8 bnad_bcast_addr[] =  {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
+static const u8 bnad_bcast_addr[] __aligned(2) =
+	{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
 /*
  * Local MACROS
@@ -308,7 +309,7 @@ bnad_rxq_alloc_init(struct bnad *bnad, struct bna_rcb *rcb)
 		}
 	}
 
-	BUG_ON(((PAGE_SIZE << order) % unmap_q->map_size));
+	BUG_ON((PAGE_SIZE << order) % unmap_q->map_size);
 
 	return 0;
 }
@@ -724,7 +725,6 @@ next:
 			cmpl->valid = 0;
 			BNA_QE_INDX_INC(ccb->producer_index, ccb->q_depth);
 		}
-		cmpl = &cq[ccb->producer_index];
 	}
 
 	napi_gro_flush(&rx_ctrl->napi, false);
@@ -757,7 +757,7 @@ bnad_msix_rx(int irq, void *data)
 	struct bna_ccb *ccb = (struct bna_ccb *)data;
 
 	if (ccb) {
-		((struct bnad_rx_ctrl *)(ccb->ctrl))->rx_intr_ctr++;
+		((struct bnad_rx_ctrl *)ccb->ctrl)->rx_intr_ctr++;
 		bnad_netif_rx_schedule_poll(ccb->bnad, ccb);
 	}
 
@@ -875,9 +875,9 @@ bnad_set_netdev_perm_addr(struct bnad *bnad)
 {
 	struct net_device *netdev = bnad->netdev;
 
-	memcpy(netdev->perm_addr, &bnad->perm_addr, netdev->addr_len);
+	ether_addr_copy(netdev->perm_addr, bnad->perm_addr);
 	if (is_zero_ether_addr(netdev->dev_addr))
-		memcpy(netdev->dev_addr, &bnad->perm_addr, netdev->addr_len);
+		ether_addr_copy(netdev->dev_addr, bnad->perm_addr);
 }
 
 /* Control Path Handlers */
@@ -946,8 +946,7 @@ bnad_cb_ethport_link_status(struct bnad *bnad,
 	if (link_up) {
 		if (!netif_carrier_ok(bnad->netdev)) {
 			uint tx_id, tcb_id;
-			printk(KERN_WARNING "bna: %s link up\n",
-				bnad->netdev->name);
+			netdev_info(bnad->netdev, "link up\n");
 			netif_carrier_on(bnad->netdev);
 			BNAD_UPDATE_CTR(bnad, link_toggle);
 			for (tx_id = 0; tx_id < bnad->num_tx; tx_id++) {
@@ -966,10 +965,6 @@ bnad_cb_ethport_link_status(struct bnad *bnad,
 						/*
 						 * Force an immediate
 						 * Transmit Schedule */
-						printk(KERN_INFO "bna: %s %d "
-						      "TXQ_STARTED\n",
-						       bnad->netdev->name,
-						       txq_id);
 						netif_wake_subqueue(
 								bnad->netdev,
 								txq_id);
@@ -987,8 +982,7 @@ bnad_cb_ethport_link_status(struct bnad *bnad,
 		}
 	} else {
 		if (netif_carrier_ok(bnad->netdev)) {
-			printk(KERN_WARNING "bna: %s link down\n",
-				bnad->netdev->name);
+			netdev_info(bnad->netdev, "link down\n");
 			netif_carrier_off(bnad->netdev);
 			BNAD_UPDATE_CTR(bnad, link_toggle);
 		}
@@ -1058,8 +1052,6 @@ bnad_cb_tx_stall(struct bnad *bnad, struct bna_tx *tx)
 		txq_id = tcb->id;
 		clear_bit(BNAD_TXQ_TX_STARTED, &tcb->flags);
 		netif_stop_subqueue(bnad->netdev, txq_id);
-		printk(KERN_INFO "bna: %s %d TXQ_STOPPED\n",
-			bnad->netdev->name, txq_id);
 	}
 }
 
@@ -1082,8 +1074,6 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
 		BUG_ON(*(tcb->hw_consumer_index) != 0);
 
 		if (netif_carrier_ok(bnad->netdev)) {
-			printk(KERN_INFO "bna: %s %d TXQ_STARTED\n",
-				bnad->netdev->name, txq_id);
 			netif_wake_subqueue(bnad->netdev, txq_id);
 			BNAD_UPDATE_CTR(bnad, netif_queue_wakeup);
 		}
@@ -1094,8 +1084,8 @@ bnad_cb_tx_resume(struct bnad *bnad, struct bna_tx *tx)
 	 * get a 0 MAC address. We try to get the MAC address
 	 * again here.
 	 */
-	if (is_zero_ether_addr(&bnad->perm_addr.mac[0])) {
-		bna_enet_perm_mac_get(&bnad->bna.enet, &bnad->perm_addr);
+	if (is_zero_ether_addr(bnad->perm_addr)) {
+		bna_enet_perm_mac_get(&bnad->bna.enet, bnad->perm_addr);
 		bnad_set_netdev_perm_addr(bnad);
 	}
 }
@@ -1703,7 +1693,7 @@ bnad_ioc_timeout(unsigned long data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	bfa_nw_ioc_timeout((void *) &bnad->bna.ioceth.ioc);
+	bfa_nw_ioc_timeout(&bnad->bna.ioceth.ioc);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -1714,7 +1704,7 @@ bnad_ioc_hb_check(unsigned long data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	bfa_nw_ioc_hb_check((void *) &bnad->bna.ioceth.ioc);
+	bfa_nw_ioc_hb_check(&bnad->bna.ioceth.ioc);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -1725,7 +1715,7 @@ bnad_iocpf_timeout(unsigned long data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	bfa_nw_iocpf_timeout((void *) &bnad->bna.ioceth.ioc);
+	bfa_nw_iocpf_timeout(&bnad->bna.ioceth.ioc);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -1736,7 +1726,7 @@ bnad_iocpf_sem_timeout(unsigned long data)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	bfa_nw_iocpf_sem_timeout((void *) &bnad->bna.ioceth.ioc);
+	bfa_nw_iocpf_sem_timeout(&bnad->bna.ioceth.ioc);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
 
@@ -1862,8 +1852,7 @@ bnad_netdev_mc_list_get(struct net_device *netdev, u8 *mc_list)
 	struct netdev_hw_addr *mc_addr;
 
 	netdev_for_each_mc_addr(mc_addr, netdev) {
-		memcpy(&mc_list[i * ETH_ALEN], &mc_addr->addr[0],
-							ETH_ALEN);
+		ether_addr_copy(&mc_list[i * ETH_ALEN], &mc_addr->addr[0]);
 		i++;
 	}
 }
@@ -2137,7 +2126,7 @@ bnad_reinit_rx(struct bnad *bnad)
 		current_err = bnad_setup_rx(bnad, rx_id);
 		if (current_err && !err) {
 			err = current_err;
-			pr_err("RXQ:%u setup failed\n", rx_id);
+			netdev_err(netdev, "RXQ:%u setup failed\n", rx_id);
 		}
 	}
 
@@ -2338,7 +2327,7 @@ bnad_rx_coalescing_timeo_set(struct bnad *bnad)
  * Called with bnad->bna_lock held
  */
 int
-bnad_mac_addr_set_locked(struct bnad *bnad, u8 *mac_addr)
+bnad_mac_addr_set_locked(struct bnad *bnad, const u8 *mac_addr)
 {
 	int ret;
 
@@ -2349,7 +2338,7 @@ bnad_mac_addr_set_locked(struct bnad *bnad, u8 *mac_addr)
 	if (!bnad->rx_info[0].rx)
 		return 0;
 
-	ret = bna_rx_ucast_set(bnad->rx_info[0].rx, mac_addr, NULL);
+	ret = bna_rx_ucast_set(bnad->rx_info[0].rx, mac_addr);
 	if (ret != BNA_CB_SUCCESS)
 		return -EADDRNOTAVAIL;
 
@@ -2367,8 +2356,8 @@ bnad_enable_default_bcast(struct bnad *bnad)
 	init_completion(&bnad->bnad_completions.mcast_comp);
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	ret = bna_rx_mcast_add(rx_info->rx, (u8 *)bnad_bcast_addr,
-				bnad_cb_rx_mcast_add);
+	ret = bna_rx_mcast_add(rx_info->rx, bnad_bcast_addr,
+			       bnad_cb_rx_mcast_add);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
 	if (ret == BNA_CB_SUCCESS)
@@ -2673,8 +2662,9 @@ bnad_enable_msix(struct bnad *bnad)
 	if (ret < 0) {
 		goto intx_mode;
 	} else if (ret < bnad->msix_num) {
-		pr_warn("BNA: %d MSI-X vectors allocated < %d requested\n",
-			ret, bnad->msix_num);
+		dev_warn(&bnad->pcidev->dev,
+			 "%d MSI-X vectors allocated < %d requested\n",
+			 ret, bnad->msix_num);
 
 		spin_lock_irqsave(&bnad->bna_lock, flags);
 		/* ret = #of vectors that we got */
@@ -2696,7 +2686,8 @@ bnad_enable_msix(struct bnad *bnad)
 	return;
 
 intx_mode:
-	pr_warn("BNA: MSI-X enable failed - operating in INTx mode\n");
+	dev_warn(&bnad->pcidev->dev,
+		 "MSI-X enable failed - operating in INTx mode\n");
 
 	kfree(bnad->msix_table);
 	bnad->msix_table = NULL;
@@ -2754,7 +2745,7 @@ bnad_open(struct net_device *netdev)
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	bna_enet_mtu_set(&bnad->bna.enet,
 			 BNAD_FRAME_SIZE(bnad->netdev->mtu), NULL);
-	bna_enet_pause_config(&bnad->bna.enet, &pause_config, NULL);
+	bna_enet_pause_config(&bnad->bna.enet, &pause_config);
 	bna_enet_enable(&bnad->bna.enet);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
@@ -3128,7 +3119,7 @@ bnad_set_rx_ucast_fltr(struct bnad *bnad)
 	int entry;
 
 	if (netdev_uc_empty(bnad->netdev)) {
-		bna_rx_ucast_listset(bnad->rx_info[0].rx, 0, NULL, NULL);
+		bna_rx_ucast_listset(bnad->rx_info[0].rx, 0, NULL);
 		return;
 	}
 
@@ -3141,13 +3132,11 @@ bnad_set_rx_ucast_fltr(struct bnad *bnad)
 
 	entry = 0;
 	netdev_for_each_uc_addr(ha, netdev) {
-		memcpy(&mac_list[entry * ETH_ALEN],
-		       &ha->addr[0], ETH_ALEN);
+		ether_addr_copy(&mac_list[entry * ETH_ALEN], &ha->addr[0]);
 		entry++;
 	}
 
-	ret = bna_rx_ucast_listset(bnad->rx_info[0].rx, entry,
-			mac_list, NULL);
+	ret = bna_rx_ucast_listset(bnad->rx_info[0].rx, entry, mac_list);
 	kfree(mac_list);
 
 	if (ret != BNA_CB_SUCCESS)
@@ -3158,7 +3147,7 @@ bnad_set_rx_ucast_fltr(struct bnad *bnad)
 	/* ucast packets not in UCAM are routed to default function */
 mode_default:
 	bnad->cfg_flags |= BNAD_CF_DEFAULT;
-	bna_rx_ucast_listset(bnad->rx_info[0].rx, 0, NULL, NULL);
+	bna_rx_ucast_listset(bnad->rx_info[0].rx, 0, NULL);
 }
 
 static void
@@ -3183,12 +3172,11 @@ bnad_set_rx_mcast_fltr(struct bnad *bnad)
 	if (mac_list == NULL)
 		goto mode_allmulti;
 
-	memcpy(&mac_list[0], &bnad_bcast_addr[0], ETH_ALEN);
+	ether_addr_copy(&mac_list[0], &bnad_bcast_addr[0]);
 
 	/* copy rest of the MCAST addresses */
 	bnad_netdev_mc_list_get(netdev, mac_list);
-	ret = bna_rx_mcast_listset(bnad->rx_info[0].rx, mc_count + 1,
-			mac_list, NULL);
+	ret = bna_rx_mcast_listset(bnad->rx_info[0].rx, mc_count + 1, mac_list);
 	kfree(mac_list);
 
 	if (ret != BNA_CB_SUCCESS)
@@ -3198,7 +3186,7 @@ bnad_set_rx_mcast_fltr(struct bnad *bnad)
 
 mode_allmulti:
 	bnad->cfg_flags |= BNAD_CF_ALLMULTI;
-	bna_rx_mcast_delall(bnad->rx_info[0].rx, NULL);
+	bna_rx_mcast_delall(bnad->rx_info[0].rx);
 }
 
 void
@@ -3237,7 +3225,7 @@ bnad_set_rx_mode(struct net_device *netdev)
 
 	mode_mask = BNA_RXMODE_PROMISC | BNA_RXMODE_DEFAULT |
 			BNA_RXMODE_ALLMULTI;
-	bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL);
+	bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask);
 
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 }
@@ -3248,19 +3236,18 @@ bnad_set_rx_mode(struct net_device *netdev)
  * in a non-blocking context.
  */
 static int
-bnad_set_mac_address(struct net_device *netdev, void *mac_addr)
+bnad_set_mac_address(struct net_device *netdev, void *addr)
 {
 	int err;
 	struct bnad *bnad = netdev_priv(netdev);
-	struct sockaddr *sa = (struct sockaddr *)mac_addr;
+	struct sockaddr *sa = (struct sockaddr *)addr;
 	unsigned long flags;
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 
 	err = bnad_mac_addr_set_locked(bnad, sa->sa_data);
-
 	if (!err)
-		memcpy(netdev->dev_addr, sa->sa_data, netdev->addr_len);
+		ether_addr_copy(netdev->dev_addr, sa->sa_data);
 
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
@@ -3487,8 +3474,8 @@ bnad_init(struct bnad *bnad,
 		dev_err(&pdev->dev, "ioremap for bar0 failed\n");
 		return -ENOMEM;
 	}
-	pr_info("bar0 mapped to %p, len %llu\n", bnad->bar0,
-	       (unsigned long long) bnad->mmio_len);
+	dev_info(&pdev->dev, "bar0 mapped to %p, len %llu\n", bnad->bar0,
+		 (unsigned long long) bnad->mmio_len);
 
 	spin_lock_irqsave(&bnad->bna_lock, flags);
 	if (!bnad_msix_disable)
@@ -3609,13 +3596,10 @@ bnad_pci_probe(struct pci_dev *pdev,
 	struct bfa_pcidev pcidev_info;
 	unsigned long flags;
 
-	pr_info("bnad_pci_probe : (0x%p, 0x%p) PCI Func : (%d)\n",
-	       pdev, pcidev_id, PCI_FUNC(pdev->devfn));
-
 	mutex_lock(&bnad_fwimg_mutex);
 	if (!cna_get_firmware_buf(pdev)) {
 		mutex_unlock(&bnad_fwimg_mutex);
-		pr_warn("Failed to load Firmware Image!\n");
+		dev_err(&pdev->dev, "failed to load firmware image!\n");
 		return -ENODEV;
 	}
 	mutex_unlock(&bnad_fwimg_mutex);
@@ -3693,17 +3677,13 @@ bnad_pci_probe(struct pci_dev *pdev,
 
 	/* Set up timers */
 	setup_timer(&bnad->bna.ioceth.ioc.ioc_timer, bnad_ioc_timeout,
-				((unsigned long)bnad));
+		    (unsigned long)bnad);
 	setup_timer(&bnad->bna.ioceth.ioc.hb_timer, bnad_ioc_hb_check,
-				((unsigned long)bnad));
+		    (unsigned long)bnad);
 	setup_timer(&bnad->bna.ioceth.ioc.iocpf_timer, bnad_iocpf_timeout,
-				((unsigned long)bnad));
+		    (unsigned long)bnad);
 	setup_timer(&bnad->bna.ioceth.ioc.sem_timer, bnad_iocpf_sem_timeout,
-				((unsigned long)bnad));
-
-	/* Now start the timer before calling IOC */
-	mod_timer(&bnad->bna.ioceth.ioc.iocpf_timer,
-		  jiffies + msecs_to_jiffies(BNA_IOC_TIMER_FREQ));
+		    (unsigned long)bnad);
 
 	/*
 	 * Start the chip
@@ -3712,8 +3692,7 @@ bnad_pci_probe(struct pci_dev *pdev,
 	 */
 	err = bnad_ioceth_enable(bnad);
 	if (err) {
-		pr_err("BNA: Initialization failed err=%d\n",
-		       err);
+		dev_err(&pdev->dev, "initialization failed err=%d\n", err);
 		goto probe_success;
 	}
 
@@ -3746,7 +3725,7 @@ bnad_pci_probe(struct pci_dev *pdev,
 
 	/* Get the burnt-in mac */
 	spin_lock_irqsave(&bnad->bna_lock, flags);
-	bna_enet_perm_mac_get(&bna->enet, &bnad->perm_addr);
+	bna_enet_perm_mac_get(&bna->enet, bnad->perm_addr);
 	bnad_set_netdev_perm_addr(bnad);
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
@@ -3755,7 +3734,7 @@ bnad_pci_probe(struct pci_dev *pdev,
 	/* Finally, reguister with net_device layer */
 	err = register_netdev(netdev);
 	if (err) {
-		pr_err("BNA : Registering with netdev failed\n");
+		dev_err(&pdev->dev, "registering net device failed\n");
 		goto probe_uninit;
 	}
 	set_bit(BNAD_RF_NETDEV_REGISTERED, &bnad->run_flags);
@@ -3807,7 +3786,6 @@ bnad_pci_remove(struct pci_dev *pdev)
 	if (!netdev)
 		return;
 
-	pr_info("%s bnad_pci_remove\n", netdev->name);
 	bnad = netdev_priv(netdev);
 	bna = &bnad->bna;
 
@@ -3868,15 +3846,14 @@ bnad_module_init(void)
 {
 	int err;
 
-	pr_info("QLogic BR-series 10G Ethernet driver - version: %s\n",
-			BNAD_VERSION);
+	pr_info("bna: QLogic BR-series 10G Ethernet driver - version: %s\n",
+		BNAD_VERSION);
 
 	bfa_nw_ioc_auto_recover(bnad_ioc_auto_recover);
 
 	err = pci_register_driver(&bnad_pci_driver);
 	if (err < 0) {
-		pr_err("bna : PCI registration failed in module init "
-		       "(%d)\n", err);
+		pr_err("bna: PCI driver registration failed err=%d\n", err);
 		return err;
 	}
 
diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h
index 7ead6c23edb6..faedbf24777e 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -344,7 +344,7 @@ struct bnad {
 	struct bnad_completion bnad_completions;
 
 	/* Burnt in MAC address */
-	mac_t			perm_addr;
+	u8			perm_addr[ETH_ALEN];
 
 	struct workqueue_struct *work_q;
 
@@ -385,7 +385,7 @@ u32 *cna_get_firmware_buf(struct pci_dev *pdev);
 /* Netdev entry point prototypes */
 void bnad_set_rx_mode(struct net_device *netdev);
 struct net_device_stats *bnad_get_netdev_stats(struct net_device *netdev);
-int bnad_mac_addr_set_locked(struct bnad *bnad, u8 *mac_addr);
+int bnad_mac_addr_set_locked(struct bnad *bnad, const u8 *mac_addr);
 int bnad_enable_default_bcast(struct bnad *bnad);
 void bnad_restore_vlans(struct bnad *bnad, u32 rx_id);
 void bnad_set_ethtool_ops(struct net_device *netdev);
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
index 72c89550417c..8fc246ea1fb8 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -76,8 +76,7 @@ bnad_debugfs_open_fwtrc(struct inode *inode, struct file *file)
 		fw_debug->debug_buffer = NULL;
 		kfree(fw_debug);
 		fw_debug = NULL;
-		pr_warn("bnad %s: Failed to collect fwtrc\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed to collect fwtrc\n");
 		return -ENOMEM;
 	}
 
@@ -117,8 +116,7 @@ bnad_debugfs_open_fwsave(struct inode *inode, struct file *file)
 		fw_debug->debug_buffer = NULL;
 		kfree(fw_debug);
 		fw_debug = NULL;
-		pr_warn("bna %s: Failed to collect fwsave\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed to collect fwsave\n");
 		return -ENOMEM;
 	}
 
@@ -217,8 +215,7 @@ bnad_debugfs_open_drvinfo(struct inode *inode, struct file *file)
 		drv_info->debug_buffer = NULL;
 		kfree(drv_info);
 		drv_info = NULL;
-		pr_warn("bna %s: Failed to collect drvinfo\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed to collect drvinfo\n");
 		return -ENOMEM;
 	}
 
@@ -271,15 +268,15 @@ bna_reg_offset_check(struct bfa_ioc *ioc, u32 offset, u32 len)
 	area = (offset >> 15) & 0x7;
 	if (area == 0) {
 		/* PCIe core register */
-		if ((offset + (len<<2)) > 0x8000)	/* 8k dwords or 32KB */
+		if (offset + (len << 2) > 0x8000)	/* 8k dwords or 32KB */
 			return BFA_STATUS_EINVAL;
 	} else if (area == 0x1) {
 		/* CB 32 KB memory page */
-		if ((offset + (len<<2)) > 0x10000)	/* 8k dwords or 32KB */
+		if (offset + (len << 2) > 0x10000)	/* 8k dwords or 32KB */
 			return BFA_STATUS_EINVAL;
 	} else {
 		/* CB register space 64KB */
-		if ((offset + (len<<2)) > BFA_REG_ADDRMSK(ioc))
+		if (offset + (len << 2) > BFA_REG_ADDRMSK(ioc))
 			return BFA_STATUS_EINVAL;
 	}
 	return BFA_STATUS_OK;
@@ -321,27 +318,20 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
 	unsigned long flags;
 	void *kern_buf;
 
-	/* Allocate memory to store the user space buf */
-	kern_buf = kzalloc(nbytes, GFP_KERNEL);
-	if (!kern_buf)
-		return -ENOMEM;
-
-	if (copy_from_user(kern_buf, (void  __user *)buf, nbytes)) {
-		kfree(kern_buf);
-		return -ENOMEM;
-	}
+	/* Copy the user space buf */
+	kern_buf = memdup_user(buf, nbytes);
+	if (IS_ERR(kern_buf))
+		return PTR_ERR(kern_buf);
 
 	rc = sscanf(kern_buf, "%x:%x", &addr, &len);
 	if (rc < 2) {
-		pr_warn("bna %s: Failed to read user buffer\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed to read user buffer\n");
 		kfree(kern_buf);
 		return -EINVAL;
 	}
 
 	kfree(kern_buf);
 	kfree(bnad->regdata);
-	bnad->regdata = NULL;
 	bnad->reglen = 0;
 
 	bnad->regdata = kzalloc(len << 2, GFP_KERNEL);
@@ -355,8 +345,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf,
 	/* offset and len sanity check */
 	rc = bna_reg_offset_check(ioc, addr, len);
 	if (rc) {
-		pr_warn("bna %s: Failed reg offset check\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed reg offset check\n");
 		kfree(bnad->regdata);
 		bnad->regdata = NULL;
 		bnad->reglen = 0;
@@ -388,20 +377,14 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf,
 	unsigned long flags;
 	void *kern_buf;
 
-	/* Allocate memory to store the user space buf */
-	kern_buf = kzalloc(nbytes, GFP_KERNEL);
-	if (!kern_buf)
-		return -ENOMEM;
-
-	if (copy_from_user(kern_buf, (void  __user *)buf, nbytes)) {
-		kfree(kern_buf);
-		return -ENOMEM;
-	}
+	/* Copy the user space buf */
+	kern_buf = memdup_user(buf, nbytes);
+	if (IS_ERR(kern_buf))
+		return PTR_ERR(kern_buf);
 
 	rc = sscanf(kern_buf, "%x:%x", &addr, &val);
 	if (rc < 2) {
-		pr_warn("bna %s: Failed to read user buffer\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed to read user buffer\n");
 		kfree(kern_buf);
 		return -EINVAL;
 	}
@@ -412,8 +395,7 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf,
 	/* offset and len sanity check */
 	rc = bna_reg_offset_check(ioc, addr, 1);
 	if (rc) {
-		pr_warn("bna %s: Failed reg offset check\n",
-			pci_name(bnad->pcidev));
+		netdev_warn(bnad->netdev, "failed reg offset check\n");
 		return -EINVAL;
 	}
 
@@ -525,7 +507,8 @@ bnad_debugfs_init(struct bnad *bnad)
 		bna_debugfs_root = debugfs_create_dir("bna", NULL);
 		atomic_set(&bna_debugfs_port_count, 0);
 		if (!bna_debugfs_root) {
-			pr_warn("BNA: debugfs root dir creation failed\n");
+			netdev_warn(bnad->netdev,
+				    "debugfs root dir creation failed\n");
 			return;
 		}
 	}
@@ -536,8 +519,8 @@ bnad_debugfs_init(struct bnad *bnad)
 		bnad->port_debugfs_root =
 			debugfs_create_dir(name, bna_debugfs_root);
 		if (!bnad->port_debugfs_root) {
-			pr_warn("bna pci_dev %s: root dir creation failed\n",
-				pci_name(bnad->pcidev));
+			netdev_warn(bnad->netdev,
+				    "debugfs root dir creation failed\n");
 			return;
 		}
 
@@ -552,9 +535,9 @@ bnad_debugfs_init(struct bnad *bnad)
 							bnad,
 							file->fops);
 			if (!bnad->bnad_dentry_files[i]) {
-				pr_warn(
-				     "BNA pci_dev:%s: create %s entry failed\n",
-				     pci_name(bnad->pcidev), file->name);
+				netdev_warn(bnad->netdev,
+					    "create %s entry failed\n",
+					    file->name);
 				return;
 			}
 		}
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index 12f344debd1c..2bdfc5dff4b1 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -445,13 +445,13 @@ bnad_set_ringparam(struct net_device *netdev,
 
 	if (ringparam->rx_pending < BNAD_MIN_Q_DEPTH ||
 	    ringparam->rx_pending > BNAD_MAX_RXQ_DEPTH ||
-	    !BNA_POWER_OF_2(ringparam->rx_pending)) {
+	    !is_power_of_2(ringparam->rx_pending)) {
 		mutex_unlock(&bnad->conf_mutex);
 		return -EINVAL;
 	}
 	if (ringparam->tx_pending < BNAD_MIN_Q_DEPTH ||
 	    ringparam->tx_pending > BNAD_MAX_TXQ_DEPTH ||
-	    !BNA_POWER_OF_2(ringparam->tx_pending)) {
+	    !is_power_of_2(ringparam->tx_pending)) {
 		mutex_unlock(&bnad->conf_mutex);
 		return -EINVAL;
 	}
@@ -533,7 +533,7 @@ bnad_set_pauseparam(struct net_device *netdev,
 		pause_config.rx_pause = pauseparam->rx_pause;
 		pause_config.tx_pause = pauseparam->tx_pause;
 		spin_lock_irqsave(&bnad->bna_lock, flags);
-		bna_enet_pause_config(&bnad->bna.enet, &pause_config, NULL);
+		bna_enet_pause_config(&bnad->bna.enet, &pause_config);
 		spin_unlock_irqrestore(&bnad->bna_lock, flags);
 	}
 	mutex_unlock(&bnad->conf_mutex);
@@ -1080,7 +1080,7 @@ bnad_flash_device(struct net_device *netdev, struct ethtool_flash *eflash)
 
 	ret = request_firmware(&fw, eflash->data, &bnad->pcidev->dev);
 	if (ret) {
-		pr_err("BNA: Can't locate firmware %s\n", eflash->data);
+		netdev_err(netdev, "can't load firmware %s\n", eflash->data);
 		goto out;
 	}
 
@@ -1093,7 +1093,7 @@ bnad_flash_device(struct net_device *netdev, struct ethtool_flash *eflash)
 				bnad->id, (u8 *)fw->data, fw->size, 0,
 				bnad_cb_completion, &fcomp);
 	if (ret != BFA_STATUS_OK) {
-		pr_warn("BNA: Flash update failed with err: %d\n", ret);
+		netdev_warn(netdev, "flash update failed with err=%d\n", ret);
 		ret = -EIO;
 		spin_unlock_irq(&bnad->bna_lock);
 		goto out;
@@ -1103,8 +1103,9 @@ bnad_flash_device(struct net_device *netdev, struct ethtool_flash *eflash)
 	wait_for_completion(&fcomp.comp);
 	if (fcomp.comp_status != BFA_STATUS_OK) {
 		ret = -EIO;
-		pr_warn("BNA: Firmware image update to flash failed with: %d\n",
-			fcomp.comp_status);
+		netdev_warn(netdev,
+			    "firmware image update failed with err=%d\n",
+			    fcomp.comp_status);
 	}
 out:
 	release_firmware(fw);
diff --git a/drivers/net/ethernet/brocade/bna/cna.h b/drivers/net/ethernet/brocade/bna/cna.h
index 28e7d0ffeab1..75f8f1ac9fb7 100644
--- a/drivers/net/ethernet/brocade/bna/cna.h
+++ b/drivers/net/ethernet/brocade/bna/cna.h
@@ -42,66 +42,4 @@ extern char bfa_version[];
 #define CNA_FW_FILE_CT2	"ct2fw-3.2.5.1.bin"
 #define FC_SYMNAME_MAX	256	/*!< max name server symbolic name size */
 
-#pragma pack(1)
-
-typedef struct mac { u8 mac[ETH_ALEN]; } mac_t;
-
-#pragma pack()
-
-#define bfa_q_first(_q) ((void *)(((struct list_head *) (_q))->next))
-#define bfa_q_next(_qe)	(((struct list_head *) (_qe))->next)
-#define bfa_q_prev(_qe) (((struct list_head *) (_qe))->prev)
-
-/*
- * bfa_q_qe_init - to initialize a queue element
- */
-#define bfa_q_qe_init(_qe) {						\
-	bfa_q_next(_qe) = (struct list_head *) NULL;			\
-	bfa_q_prev(_qe) = (struct list_head *) NULL;			\
-}
-
-/*
- * bfa_q_deq - dequeue an element from head of the queue
- */
-#define bfa_q_deq(_q, _qe) {						\
-	if (!list_empty(_q)) {						\
-		(*((struct list_head **) (_qe))) = bfa_q_next(_q);	\
-		bfa_q_prev(bfa_q_next(*((struct list_head **) _qe))) =	\
-						(struct list_head *) (_q); \
-		bfa_q_next(_q) = bfa_q_next(*((struct list_head **) _qe)); \
-		bfa_q_qe_init(*((struct list_head **) _qe));		\
-	} else {							\
-		*((struct list_head **)(_qe)) = NULL;			\
-	}								\
-}
-
-/*
- * bfa_q_deq_tail - dequeue an element from tail of the queue
- */
-#define bfa_q_deq_tail(_q, _qe) {					\
-	if (!list_empty(_q)) {						\
-		*((struct list_head **) (_qe)) = bfa_q_prev(_q);	\
-		bfa_q_next(bfa_q_prev(*((struct list_head **) _qe))) =  \
-						(struct list_head *) (_q); \
-		bfa_q_prev(_q) = bfa_q_prev(*(struct list_head **) _qe);\
-		bfa_q_qe_init(*((struct list_head **) _qe));		\
-	} else {							\
-		*((struct list_head **) (_qe)) = (struct list_head *) NULL; \
-	}								\
-}
-
-/*
- * bfa_add_tail_head - enqueue an element at the head of queue
- */
-#define bfa_q_enq_head(_q, _qe) {					\
-	if (!(bfa_q_next(_qe) == NULL) && (bfa_q_prev(_qe) == NULL))	\
-		pr_err("Assertion failure: %s:%d: %d",			\
-			__FILE__, __LINE__,				\
-		(bfa_q_next(_qe) == NULL) && (bfa_q_prev(_qe) == NULL));\
-	bfa_q_next(_qe) = bfa_q_next(_q);				\
-	bfa_q_prev(_qe) = (struct list_head *) (_q);			\
-	bfa_q_prev(bfa_q_next(_q)) = (struct list_head *) (_qe);	\
-	bfa_q_next(_q) = (struct list_head *) (_qe);			\
-}
-
 #endif /* __CNA_H__ */
diff --git a/drivers/net/ethernet/brocade/bna/cna_fwimg.c b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
index ebf462d8082f..2e7fb97883dc 100644
--- a/drivers/net/ethernet/brocade/bna/cna_fwimg.c
+++ b/drivers/net/ethernet/brocade/bna/cna_fwimg.c
@@ -30,9 +30,10 @@ cna_read_firmware(struct pci_dev *pdev, u32 **bfi_image,
 			u32 *bfi_image_size, char *fw_name)
 {
 	const struct firmware *fw;
+	u32 n;
 
 	if (request_firmware(&fw, fw_name, &pdev->dev)) {
-		pr_alert("Can't locate firmware %s\n", fw_name);
+		dev_alert(&pdev->dev, "can't load firmware %s\n", fw_name);
 		goto error;
 	}
 
@@ -40,6 +41,12 @@ cna_read_firmware(struct pci_dev *pdev, u32 **bfi_image,
 	*bfi_image_size = fw->size/sizeof(u32);
 	bfi_fw = fw;
 
+	/* Convert loaded firmware to host order as it is stored in file
+	 * as sequence of LE32 integers.
+	 */
+	for (n = 0; n < *bfi_image_size; n++)
+		le32_to_cpus(*bfi_image + n);
+
 	return *bfi_image;
 error:
 	return NULL;
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 1ba3e3a67389..f0bcb15d3fec 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -8,8 +8,6 @@ config NET_CADENCE
 	default y
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
-	  Make sure you know the name of your card. Read the Ethernet-HOWTO,
-	  available from <http://www.tldp.org/docs.html#howto>.
 
 	  If unsure, say Y.
 
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 4104d49f005d..caeb39561567 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -54,6 +54,8 @@
 #define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1))
 #define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1))
 
+#define GEM_MTU_MIN_SIZE	68
+
 /*
  * Graceful stop timeouts in us. We should allow up to
  * 1 frame time (10 Mbits/s, full-duplex, ignoring collisions)
@@ -350,6 +352,9 @@ static int macb_mii_probe(struct net_device *dev)
 	else
 		phydev->supported &= PHY_BASIC_FEATURES;
 
+	if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF)
+		phydev->supported &= ~SUPPORTED_1000baseT_Half;
+
 	phydev->advertising = phydev->supported;
 
 	bp->link = 0;
@@ -782,7 +787,7 @@ static int gem_rx(struct macb *bp, int budget)
 		}
 		/* now everything is ready for receiving packet */
 		bp->rx_skbuff[entry] = NULL;
-		len = MACB_BFEXT(RX_FRMLEN, ctrl);
+		len = ctrl & bp->rx_frm_len_mask;
 
 		netdev_vdbg(bp->dev, "gem_rx %u (len %u)\n", entry, len);
 
@@ -828,7 +833,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 	struct macb_dma_desc *desc;
 
 	desc = macb_rx_desc(bp, last_frag);
-	len = MACB_BFEXT(RX_FRMLEN, desc->ctrl);
+	len = desc->ctrl & bp->rx_frm_len_mask;
 
 	netdev_vdbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
 		macb_rx_ring_wrap(first_frag),
@@ -981,7 +986,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 	struct macb_queue *queue = dev_id;
 	struct macb *bp = queue->bp;
 	struct net_device *dev = bp->dev;
-	u32 status;
+	u32 status, ctrl;
 
 	status = queue_readl(queue, ISR);
 
@@ -1037,6 +1042,21 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 		 * add that if/when we get our hands on a full-blown MII PHY.
 		 */
 
+		/* There is a hardware issue under heavy load where DMA can
+		 * stop, this causes endless "used buffer descriptor read"
+		 * interrupts but it can be cleared by re-enabling RX. See
+		 * the at91 manual, section 41.3.1 or the Zynq manual
+		 * section 16.7.4 for details.
+		 */
+		if (status & MACB_BIT(RXUBR)) {
+			ctrl = macb_readl(bp, NCR);
+			macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE));
+			macb_writel(bp, NCR, ctrl | MACB_BIT(RE));
+
+			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
+				macb_writel(bp, ISR, MACB_BIT(RXUBR));
+		}
+
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
 			if (macb_is_gem(bp))
@@ -1633,7 +1653,10 @@ static void macb_init_hw(struct macb *bp)
 	config |= MACB_BF(RBOF, NET_IP_ALIGN);	/* Make eth data aligned */
 	config |= MACB_BIT(PAE);		/* PAuse Enable */
 	config |= MACB_BIT(DRFCS);		/* Discard Rx FCS */
-	config |= MACB_BIT(BIG);		/* Receive oversized frames */
+	if (bp->caps & MACB_CAPS_JUMBO)
+		config |= MACB_BIT(JFRAME);	/* Enable jumbo frames */
+	else
+		config |= MACB_BIT(BIG);	/* Receive oversized frames */
 	if (bp->dev->flags & IFF_PROMISC)
 		config |= MACB_BIT(CAF);	/* Copy All Frames */
 	else if (macb_is_gem(bp) && bp->dev->features & NETIF_F_RXCSUM)
@@ -1642,8 +1665,13 @@ static void macb_init_hw(struct macb *bp)
 		config |= MACB_BIT(NBC);	/* No BroadCast */
 	config |= macb_dbw(bp);
 	macb_writel(bp, NCFGR, config);
+	if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len)
+		gem_writel(bp, JML, bp->jumbo_max_len);
 	bp->speed = SPEED_10;
 	bp->duplex = DUPLEX_HALF;
+	bp->rx_frm_len_mask = MACB_RX_FRMLEN_MASK;
+	if (bp->caps & MACB_CAPS_JUMBO)
+		bp->rx_frm_len_mask = MACB_RX_JFRMLEN_MASK;
 
 	macb_configure_dma(bp);
 
@@ -1847,6 +1875,26 @@ static int macb_close(struct net_device *dev)
 	return 0;
 }
 
+static int macb_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct macb *bp = netdev_priv(dev);
+	u32 max_mtu;
+
+	if (netif_running(dev))
+		return -EBUSY;
+
+	max_mtu = ETH_DATA_LEN;
+	if (bp->caps & MACB_CAPS_JUMBO)
+		max_mtu = gem_readl(bp, JML) - ETH_HLEN - ETH_FCS_LEN;
+
+	if ((new_mtu > max_mtu) || (new_mtu < GEM_MTU_MIN_SIZE))
+		return -EINVAL;
+
+	dev->mtu = new_mtu;
+
+	return 0;
+}
+
 static void gem_update_stats(struct macb *bp)
 {
 	int i;
@@ -2123,7 +2171,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_get_stats		= macb_get_stats,
 	.ndo_do_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_change_mtu		= macb_change_mtu,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= macb_poll_controller,
@@ -2665,6 +2713,13 @@ static const struct macb_config pc302gem_config = {
 	.init = macb_init,
 };
 
+static const struct macb_config sama5d2_config = {
+	.caps = 0,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = macb_init,
+};
+
 static const struct macb_config sama5d3_config = {
 	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE,
 	.dma_burst_length = 16,
@@ -2684,16 +2739,37 @@ static const struct macb_config emac_config = {
 	.init = at91ether_init,
 };
 
+
+static const struct macb_config zynqmp_config = {
+	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE |
+		MACB_CAPS_JUMBO,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = macb_init,
+	.jumbo_max_len = 10240,
+};
+
+static const struct macb_config zynq_config = {
+	.caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE |
+		MACB_CAPS_NO_GIGABIT_HALF,
+	.dma_burst_length = 16,
+	.clk_init = macb_clk_init,
+	.init = macb_init,
+};
+
 static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,at32ap7000-macb" },
 	{ .compatible = "cdns,at91sam9260-macb", .data = &at91sam9260_config },
 	{ .compatible = "cdns,macb" },
 	{ .compatible = "cdns,pc302-gem", .data = &pc302gem_config },
 	{ .compatible = "cdns,gem", .data = &pc302gem_config },
+	{ .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config },
 	{ .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config },
 	{ .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config },
 	{ .compatible = "cdns,at91rm9200-emac", .data = &emac_config },
 	{ .compatible = "cdns,emac", .data = &emac_config },
+	{ .compatible = "cdns,zynqmp-gem", .data = &zynqmp_config},
+	{ .compatible = "cdns,zynq-gem", .data = &zynq_config },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, macb_dt_ids);
@@ -2762,6 +2838,10 @@ static int macb_probe(struct platform_device *pdev)
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
+	if (macb_config->jumbo_max_len) {
+		bp->jumbo_max_len = macb_config->jumbo_max_len;
+	}
+
 	spin_lock_init(&bp->lock);
 
 	/* setup capabilities */
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index eb7d76f7bf6a..d74655993d4b 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -71,6 +71,7 @@
 #define GEM_NCFGR		0x0004 /* Network Config */
 #define GEM_USRIO		0x000c /* User IO */
 #define GEM_DMACFG		0x0010 /* DMA Configuration */
+#define GEM_JML			0x0048 /* Jumbo Max Length */
 #define GEM_HRB			0x0080 /* Hash Bottom */
 #define GEM_HRT			0x0084 /* Hash Top */
 #define GEM_SA1B		0x0088 /* Specific1 Bottom */
@@ -393,10 +394,12 @@
 #define MACB_CAPS_ISR_CLEAR_ON_WRITE		0x00000001
 #define MACB_CAPS_USRIO_HAS_CLKEN		0x00000002
 #define MACB_CAPS_USRIO_DEFAULT_IS_MII		0x00000004
+#define MACB_CAPS_NO_GIGABIT_HALF		0x00000008
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
 #define MACB_CAPS_MACB_IS_GEM			0x80000000
+#define MACB_CAPS_JUMBO				0x00000008
 
 /* Bit manipulation macros */
 #define MACB_BIT(name)					\
@@ -514,6 +517,9 @@ struct macb_dma_desc {
 #define MACB_RX_BROADCAST_OFFSET		31
 #define MACB_RX_BROADCAST_SIZE			1
 
+#define MACB_RX_FRMLEN_MASK			0xFFF
+#define MACB_RX_JFRMLEN_MASK			0x3FFF
+
 /* RX checksum offload disabled: bit 24 clear in NCFGR */
 #define GEM_RX_TYPEID_MATCH_OFFSET		22
 #define GEM_RX_TYPEID_MATCH_SIZE		2
@@ -757,6 +763,7 @@ struct macb_config {
 	int	(*clk_init)(struct platform_device *pdev, struct clk **pclk,
 			    struct clk **hclk, struct clk **tx_clk);
 	int	(*init)(struct platform_device *pdev);
+	int	jumbo_max_len;
 };
 
 struct macb_queue {
@@ -826,6 +833,9 @@ struct macb {
 	unsigned int		max_tx_length;
 
 	u64			ethtool_stats[GEM_STATS_LEN];
+
+	unsigned int		rx_frm_len_mask;
+	unsigned int		jumbo_max_len;
 };
 
 static inline bool macb_is_gem(struct macb *bp)
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
new file mode 100644
index 000000000000..c4d6bbe9458d
--- /dev/null
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -0,0 +1,57 @@
+#
+# Cavium ethernet device configuration
+#
+
+config NET_VENDOR_CAVIUM
+	tristate "Cavium ethernet drivers"
+	depends on PCI
+	default y
+	---help---
+	  Select this option if you want enable Cavium network support.
+
+	  If you have a Cavium SoC or network adapter, say Y.
+
+if NET_VENDOR_CAVIUM
+
+config THUNDER_NIC_PF
+	tristate "Thunder Physical function driver"
+	depends on 64BIT
+	default ARCH_THUNDER
+	select THUNDER_NIC_BGX
+	---help---
+	  This driver supports Thunder's NIC physical function.
+	  The NIC provides the controller and DMA engines to
+	  move network traffic to/from the memory. The NIC
+	  works closely with TNS, BGX and SerDes to implement the
+	  functions replacing and virtualizing those of a typical
+	  standalone PCIe NIC chip.
+
+config THUNDER_NIC_VF
+	tristate "Thunder Virtual function driver"
+	depends on 64BIT
+	default ARCH_THUNDER
+	---help---
+	  This driver supports Thunder's NIC virtual function
+
+config	THUNDER_NIC_BGX
+	tristate "Thunder MAC interface driver (BGX)"
+	depends on 64BIT
+	default ARCH_THUNDER
+	---help---
+	  This driver supports programming and controlling of MAC
+	  interface from NIC physical function driver.
+
+config LIQUIDIO
+	tristate "Cavium LiquidIO support"
+	depends on 64BIT
+	select PTP_1588_CLOCK
+	select FW_LOADER
+	select LIBCRC32C
+	---help---
+	  This driver supports Cavium LiquidIO Intelligent Server Adapters
+	  based on CN66XX and CN68XX chips.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called liquidio.  This is recommended.
+
+endif # NET_VENDOR_CAVIUM
diff --git a/drivers/net/ethernet/cavium/Makefile b/drivers/net/ethernet/cavium/Makefile
new file mode 100644
index 000000000000..d22f886ac291
--- /dev/null
+++ b/drivers/net/ethernet/cavium/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Cavium ethernet device drivers.
+#
+obj-$(CONFIG_NET_VENDOR_CAVIUM) += thunder/
+obj-$(CONFIG_NET_VENDOR_CAVIUM) += liquidio/
diff --git a/drivers/net/ethernet/cavium/liquidio/Makefile b/drivers/net/ethernet/cavium/liquidio/Makefile
new file mode 100644
index 000000000000..2f366806835d
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/Makefile
@@ -0,0 +1,16 @@
+#
+# Cavium Liquidio ethernet device driver
+#
+obj-$(CONFIG_LIQUIDIO) += liquidio.o
+
+liquidio-objs := lio_main.o  \
+	      lio_ethtool.o      \
+	      request_manager.o  \
+	      response_manager.o \
+	      octeon_device.o    \
+	      cn66xx_device.o    \
+	      cn68xx_device.o    \
+	      octeon_mem_ops.o   \
+	      octeon_droq.o      \
+	      octeon_console.o   \
+	      octeon_nic.o
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
new file mode 100644
index 000000000000..8ad7425f89bf
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -0,0 +1,796 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+int lio_cn6xxx_soft_reset(struct octeon_device *oct)
+{
+	octeon_write_csr64(oct, CN6XXX_WIN_WR_MASK_REG, 0xFF);
+
+	dev_dbg(&oct->pci_dev->dev, "BIST enabled for soft reset\n");
+
+	lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_BIST);
+	octeon_write_csr64(oct, CN6XXX_SLI_SCRATCH1, 0x1234ULL);
+
+	lio_pci_readq(oct, CN6XXX_CIU_SOFT_RST);
+	lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_RST);
+
+	/* make sure that the reset is written before starting timer */
+	mmiowb();
+
+	/* Wait for 10ms as Octeon resets. */
+	mdelay(100);
+
+	if (octeon_read_csr64(oct, CN6XXX_SLI_SCRATCH1) == 0x1234ULL) {
+		dev_err(&oct->pci_dev->dev, "Soft reset failed\n");
+		return 1;
+	}
+
+	dev_dbg(&oct->pci_dev->dev, "Reset completed\n");
+	octeon_write_csr64(oct, CN6XXX_WIN_WR_MASK_REG, 0xFF);
+
+	return 0;
+}
+
+void lio_cn6xxx_enable_error_reporting(struct octeon_device *oct)
+{
+	u32 val;
+
+	pci_read_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, &val);
+	if (val & 0x000f0000) {
+		dev_err(&oct->pci_dev->dev, "PCI-E Link error detected: 0x%08x\n",
+			val & 0x000f0000);
+	}
+
+	val |= 0xf;          /* Enable Link error reporting */
+
+	dev_dbg(&oct->pci_dev->dev, "Enabling PCI-E error reporting..\n");
+	pci_write_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, val);
+}
+
+void lio_cn6xxx_setup_pcie_mps(struct octeon_device *oct,
+			       enum octeon_pcie_mps mps)
+{
+	u32 val;
+	u64 r64;
+
+	/* Read config register for MPS */
+	pci_read_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, &val);
+
+	if (mps == PCIE_MPS_DEFAULT) {
+		mps = ((val & (0x7 << 5)) >> 5);
+	} else {
+		val &= ~(0x7 << 5);  /* Turn off any MPS bits */
+		val |= (mps << 5);   /* Set MPS */
+		pci_write_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, val);
+	}
+
+	/* Set MPS in DPI_SLI_PRT0_CFG to the same value. */
+	r64 = lio_pci_readq(oct, CN6XXX_DPI_SLI_PRTX_CFG(oct->pcie_port));
+	r64 |= (mps << 4);
+	lio_pci_writeq(oct, r64, CN6XXX_DPI_SLI_PRTX_CFG(oct->pcie_port));
+}
+
+void lio_cn6xxx_setup_pcie_mrrs(struct octeon_device *oct,
+				enum octeon_pcie_mrrs mrrs)
+{
+	u32 val;
+	u64 r64;
+
+	/* Read config register for MRRS */
+	pci_read_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, &val);
+
+	if (mrrs == PCIE_MRRS_DEFAULT) {
+		mrrs = ((val & (0x7 << 12)) >> 12);
+	} else {
+		val &= ~(0x7 << 12); /* Turn off any MRRS bits */
+		val |= (mrrs << 12); /* Set MRRS */
+		pci_write_config_dword(oct->pci_dev, CN6XXX_PCIE_DEVCTL, val);
+	}
+
+	/* Set MRRS in SLI_S2M_PORT0_CTL to the same value. */
+	r64 = octeon_read_csr64(oct, CN6XXX_SLI_S2M_PORTX_CTL(oct->pcie_port));
+	r64 |= mrrs;
+	octeon_write_csr64(oct, CN6XXX_SLI_S2M_PORTX_CTL(oct->pcie_port), r64);
+
+	/* Set MRRS in DPI_SLI_PRT0_CFG to the same value. */
+	r64 = lio_pci_readq(oct, CN6XXX_DPI_SLI_PRTX_CFG(oct->pcie_port));
+	r64 |= mrrs;
+	lio_pci_writeq(oct, r64, CN6XXX_DPI_SLI_PRTX_CFG(oct->pcie_port));
+}
+
+u32 lio_cn6xxx_coprocessor_clock(struct octeon_device *oct)
+{
+	/* Bits 29:24 of MIO_RST_BOOT holds the ref. clock multiplier
+	 * for SLI.
+	 */
+	return ((lio_pci_readq(oct, CN6XXX_MIO_RST_BOOT) >> 24) & 0x3f) * 50;
+}
+
+u32 lio_cn6xxx_get_oq_ticks(struct octeon_device *oct,
+			    u32 time_intr_in_us)
+{
+	/* This gives the SLI clock per microsec */
+	u32 oqticks_per_us = lio_cn6xxx_coprocessor_clock(oct);
+
+	/* core clock per us / oq ticks will be fractional. TO avoid that
+	 * we use the method below.
+	 */
+
+	/* This gives the clock cycles per millisecond */
+	oqticks_per_us *= 1000;
+
+	/* This gives the oq ticks (1024 core clock cycles) per millisecond */
+	oqticks_per_us /= 1024;
+
+	/* time_intr is in microseconds. The next 2 steps gives the oq ticks
+	 * corressponding to time_intr.
+	 */
+	oqticks_per_us *= time_intr_in_us;
+	oqticks_per_us /= 1000;
+
+	return oqticks_per_us;
+}
+
+void lio_cn6xxx_setup_global_input_regs(struct octeon_device *oct)
+{
+	/* Select Round-Robin Arb, ES, RO, NS for Input Queues */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_INPUT_CONTROL,
+			 CN6XXX_INPUT_CTL_MASK);
+
+	/* Instruction Read Size - Max 4 instructions per PCIE Read */
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_INSTR_RD_SIZE,
+			   0xFFFFFFFFFFFFFFFFULL);
+
+	/* Select PCIE Port for all Input rings. */
+	octeon_write_csr64(oct, CN6XXX_SLI_IN_PCIE_PORT,
+			   (oct->pcie_port * 0x5555555555555555ULL));
+}
+
+static void lio_cn66xx_setup_pkt_ctl_regs(struct octeon_device *oct)
+{
+	u64 pktctl;
+
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+
+	pktctl = octeon_read_csr64(oct, CN6XXX_SLI_PKT_CTL);
+
+	/* 66XX SPECIFIC */
+	if (CFG_GET_OQ_MAX_Q(cn6xxx->conf) <= 4)
+		/* Disable RING_EN if only upto 4 rings are used. */
+		pktctl &= ~(1 << 4);
+	else
+		pktctl |= (1 << 4);
+
+	if (CFG_GET_IS_SLI_BP_ON(cn6xxx->conf))
+		pktctl |= 0xF;
+	else
+		/* Disable per-port backpressure. */
+		pktctl &= ~0xF;
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_CTL, pktctl);
+}
+
+void lio_cn6xxx_setup_global_output_regs(struct octeon_device *oct)
+{
+	u32 time_threshold;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+
+	/* / Select PCI-E Port for all Output queues */
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_PCIE_PORT64,
+			   (oct->pcie_port * 0x5555555555555555ULL));
+
+	if (CFG_GET_IS_SLI_BP_ON(cn6xxx->conf)) {
+		octeon_write_csr64(oct, CN6XXX_SLI_OQ_WMARK, 32);
+	} else {
+		/* / Set Output queue watermark to 0 to disable backpressure */
+		octeon_write_csr64(oct, CN6XXX_SLI_OQ_WMARK, 0);
+	}
+
+	/* / Select Info Ptr for length & data */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_IPTR, 0xFFFFFFFF);
+
+	/* / Select Packet count instead of bytes for SLI_PKTi_CNTS[CNT] */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_BMODE, 0);
+
+	/* / Select ES,RO,NS setting from register for Output Queue Packet
+	 * Address
+	 */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_DPADDR, 0xFFFFFFFF);
+
+	/* No Relaxed Ordering, No Snoop, 64-bit swap for Output
+	 * Queue ScatterList
+	 */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_SLIST_ROR, 0);
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_SLIST_NS, 0);
+
+	/* / ENDIAN_SPECIFIC CHANGES - 0 works for LE. */
+#ifdef __BIG_ENDIAN_BITFIELD
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_SLIST_ES64,
+			   0x5555555555555555ULL);
+#else
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_SLIST_ES64, 0ULL);
+#endif
+
+	/* / No Relaxed Ordering, No Snoop, 64-bit swap for Output Queue Data */
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_DATA_OUT_ROR, 0);
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_DATA_OUT_NS, 0);
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_DATA_OUT_ES64,
+			   0x5555555555555555ULL);
+
+	/* / Set up interrupt packet and time threshold */
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
+			 (u32)CFG_GET_OQ_INTR_PKT(cn6xxx->conf));
+	time_threshold =
+		lio_cn6xxx_get_oq_ticks(oct, (u32)
+					CFG_GET_OQ_INTR_TIME(cn6xxx->conf));
+
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_TIME, time_threshold);
+}
+
+static int lio_cn6xxx_setup_device_regs(struct octeon_device *oct)
+{
+	lio_cn6xxx_setup_pcie_mps(oct, PCIE_MPS_DEFAULT);
+	lio_cn6xxx_setup_pcie_mrrs(oct, PCIE_MRRS_512B);
+	lio_cn6xxx_enable_error_reporting(oct);
+
+	lio_cn6xxx_setup_global_input_regs(oct);
+	lio_cn66xx_setup_pkt_ctl_regs(oct);
+	lio_cn6xxx_setup_global_output_regs(oct);
+
+	/* Default error timeout value should be 0x200000 to avoid host hang
+	 * when reads invalid register
+	 */
+	octeon_write_csr64(oct, CN6XXX_SLI_WINDOW_CTL, 0x200000ULL);
+	return 0;
+}
+
+void lio_cn6xxx_setup_iq_regs(struct octeon_device *oct, u32 iq_no)
+{
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
+
+	/* Disable Packet-by-Packet mode; No Parse Mode or Skip length */
+	octeon_write_csr64(oct, CN6XXX_SLI_IQ_PKT_INSTR_HDR64(iq_no), 0);
+
+	/* Write the start of the input queue's ring and its size  */
+	octeon_write_csr64(oct, CN6XXX_SLI_IQ_BASE_ADDR64(iq_no),
+			   iq->base_addr_dma);
+	octeon_write_csr(oct, CN6XXX_SLI_IQ_SIZE(iq_no), iq->max_count);
+
+	/* Remember the doorbell & instruction count register addr for this
+	 * queue
+	 */
+	iq->doorbell_reg = oct->mmio[0].hw_addr + CN6XXX_SLI_IQ_DOORBELL(iq_no);
+	iq->inst_cnt_reg = oct->mmio[0].hw_addr
+			   + CN6XXX_SLI_IQ_INSTR_COUNT(iq_no);
+	dev_dbg(&oct->pci_dev->dev, "InstQ[%d]:dbell reg @ 0x%p instcnt_reg @ 0x%p\n",
+		iq_no, iq->doorbell_reg, iq->inst_cnt_reg);
+
+	/* Store the current instruction counter
+	 * (used in flush_iq calculation)
+	 */
+	iq->reset_instr_cnt = readl(iq->inst_cnt_reg);
+}
+
+static void lio_cn66xx_setup_iq_regs(struct octeon_device *oct, u32 iq_no)
+{
+	lio_cn6xxx_setup_iq_regs(oct, iq_no);
+
+	/* Backpressure for this queue - WMARK set to all F's. This effectively
+	 * disables the backpressure mechanism.
+	 */
+	octeon_write_csr64(oct, CN66XX_SLI_IQ_BP64(iq_no),
+			   (0xFFFFFFFFULL << 32));
+}
+
+void lio_cn6xxx_setup_oq_regs(struct octeon_device *oct, u32 oq_no)
+{
+	u32 intr;
+	struct octeon_droq *droq = oct->droq[oq_no];
+
+	octeon_write_csr64(oct, CN6XXX_SLI_OQ_BASE_ADDR64(oq_no),
+			   droq->desc_ring_dma);
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_SIZE(oq_no), droq->max_count);
+
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_BUFF_INFO_SIZE(oq_no),
+			 (droq->buffer_size | (OCT_RH_SIZE << 16)));
+
+	/* Get the mapped address of the pkt_sent and pkts_credit regs */
+	droq->pkts_sent_reg =
+		oct->mmio[0].hw_addr + CN6XXX_SLI_OQ_PKTS_SENT(oq_no);
+	droq->pkts_credit_reg =
+		oct->mmio[0].hw_addr + CN6XXX_SLI_OQ_PKTS_CREDIT(oq_no);
+
+	/* Enable this output queue to generate Packet Timer Interrupt */
+	intr = octeon_read_csr(oct, CN6XXX_SLI_PKT_TIME_INT_ENB);
+	intr |= (1 << oq_no);
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_TIME_INT_ENB, intr);
+
+	/* Enable this output queue to generate Packet Timer Interrupt */
+	intr = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT_ENB);
+	intr |= (1 << oq_no);
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_CNT_INT_ENB, intr);
+}
+
+void lio_cn6xxx_enable_io_queues(struct octeon_device *oct)
+{
+	u32 mask;
+
+	mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_INSTR_SIZE);
+	mask |= oct->io_qmask.iq64B;
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_SIZE, mask);
+
+	mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB);
+	mask |= oct->io_qmask.iq;
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, mask);
+
+	mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_OUT_ENB);
+	mask |= oct->io_qmask.oq;
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_ENB, mask);
+}
+
+void lio_cn6xxx_disable_io_queues(struct octeon_device *oct)
+{
+	u32 mask, i, loop = HZ;
+	u32 d32;
+
+	/* Reset the Enable bits for Input Queues. */
+	mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB);
+	mask ^= oct->io_qmask.iq;
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, mask);
+
+	/* Wait until hardware indicates that the queues are out of reset. */
+	mask = oct->io_qmask.iq;
+	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
+	while (((d32 & mask) != mask) && loop--) {
+		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_IQ);
+		schedule_timeout_uninterruptible(1);
+	}
+
+	/* Reset the doorbell register for each Input queue. */
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+		if (!(oct->io_qmask.iq & (1UL << i)))
+			continue;
+		octeon_write_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i), 0xFFFFFFFF);
+		d32 = octeon_read_csr(oct, CN6XXX_SLI_IQ_DOORBELL(i));
+	}
+
+	/* Reset the Enable bits for Output Queues. */
+	mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_OUT_ENB);
+	mask ^= oct->io_qmask.oq;
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_ENB, mask);
+
+	/* Wait until hardware indicates that the queues are out of reset. */
+	loop = HZ;
+	mask = oct->io_qmask.oq;
+	d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
+	while (((d32 & mask) != mask) && loop--) {
+		d32 = octeon_read_csr(oct, CN6XXX_SLI_PORT_IN_RST_OQ);
+		schedule_timeout_uninterruptible(1);
+	}
+	;
+
+	/* Reset the doorbell register for each Output queue. */
+	/* for (i = 0; i < oct->num_oqs; i++) { */
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+		if (!(oct->io_qmask.oq & (1UL << i)))
+			continue;
+		octeon_write_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i), 0xFFFFFFFF);
+		d32 = octeon_read_csr(oct, CN6XXX_SLI_OQ_PKTS_CREDIT(i));
+
+		d32 = octeon_read_csr(oct, CN6XXX_SLI_OQ_PKTS_SENT(i));
+		octeon_write_csr(oct, CN6XXX_SLI_OQ_PKTS_SENT(i), d32);
+	}
+
+	d32 = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT);
+	if (d32)
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_CNT_INT, d32);
+
+	d32 = octeon_read_csr(oct, CN6XXX_SLI_PKT_TIME_INT);
+	if (d32)
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_TIME_INT, d32);
+}
+
+void lio_cn6xxx_reinit_regs(struct octeon_device *oct)
+{
+	u32 i;
+
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+		if (!(oct->io_qmask.iq & (1UL << i)))
+			continue;
+		oct->fn_list.setup_iq_regs(oct, i);
+	}
+
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+		if (!(oct->io_qmask.oq & (1UL << i)))
+			continue;
+		oct->fn_list.setup_oq_regs(oct, i);
+	}
+
+	oct->fn_list.setup_device_regs(oct);
+
+	oct->fn_list.enable_interrupt(oct->chip);
+
+	oct->fn_list.enable_io_queues(oct);
+
+	/* for (i = 0; i < oct->num_oqs; i++) { */
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+		if (!(oct->io_qmask.oq & (1UL << i)))
+			continue;
+		writel(oct->droq[i]->max_count, oct->droq[i]->pkts_credit_reg);
+	}
+}
+
+void
+lio_cn6xxx_bar1_idx_setup(struct octeon_device *oct,
+			  u64 core_addr,
+			  u32 idx,
+			  int valid)
+{
+	u64 bar1;
+
+	if (valid == 0) {
+		bar1 = lio_pci_readq(oct, CN6XXX_BAR1_REG(idx, oct->pcie_port));
+		lio_pci_writeq(oct, (bar1 & 0xFFFFFFFEULL),
+			       CN6XXX_BAR1_REG(idx, oct->pcie_port));
+		bar1 = lio_pci_readq(oct, CN6XXX_BAR1_REG(idx, oct->pcie_port));
+		return;
+	}
+
+	/* Bits 17:4 of the PCI_BAR1_INDEXx stores bits 35:22 of
+	 * the Core Addr
+	 */
+	lio_pci_writeq(oct, (((core_addr >> 22) << 4) | PCI_BAR1_MASK),
+		       CN6XXX_BAR1_REG(idx, oct->pcie_port));
+
+	bar1 = lio_pci_readq(oct, CN6XXX_BAR1_REG(idx, oct->pcie_port));
+}
+
+void lio_cn6xxx_bar1_idx_write(struct octeon_device *oct,
+			       u32 idx,
+			       u32 mask)
+{
+	lio_pci_writeq(oct, mask, CN6XXX_BAR1_REG(idx, oct->pcie_port));
+}
+
+u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx)
+{
+	return (u32)lio_pci_readq(oct, CN6XXX_BAR1_REG(idx, oct->pcie_port));
+}
+
+u32
+lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
+			     struct octeon_instr_queue *iq)
+{
+	u32 new_idx = readl(iq->inst_cnt_reg);
+
+	/* The new instr cnt reg is a 32-bit counter that can roll over. We have
+	 * noted the counter's initial value at init time into
+	 * reset_instr_cnt
+	 */
+	if (iq->reset_instr_cnt < new_idx)
+		new_idx -= iq->reset_instr_cnt;
+	else
+		new_idx += (0xffffffff - iq->reset_instr_cnt) + 1;
+
+	/* Modulo of the new index with the IQ size will give us
+	 * the new index.
+	 */
+	new_idx %= iq->max_count;
+
+	return new_idx;
+}
+
+void lio_cn6xxx_enable_interrupt(void *chip)
+{
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)chip;
+	u64 mask = cn6xxx->intr_mask64 | CN6XXX_INTR_DMA0_FORCE;
+
+	/* Enable Interrupt */
+	writeq(mask, cn6xxx->intr_enb_reg64);
+}
+
+void lio_cn6xxx_disable_interrupt(void *chip)
+{
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)chip;
+
+	/* Disable Interrupts */
+	writeq(0, cn6xxx->intr_enb_reg64);
+
+	/* make sure interrupts are really disabled */
+	mmiowb();
+}
+
+static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct)
+{
+	/* CN63xx Pass2 and newer parts implements the SLI_MAC_NUMBER register
+	 * to determine the PCIE port #
+	 */
+	oct->pcie_port = octeon_read_csr(oct, CN6XXX_SLI_MAC_NUMBER) & 0xff;
+
+	dev_dbg(&oct->pci_dev->dev, "Using PCIE Port %d\n", oct->pcie_port);
+}
+
+void
+lio_cn6xxx_process_pcie_error_intr(struct octeon_device *oct, u64 intr64)
+{
+	dev_err(&oct->pci_dev->dev, "Error Intr: 0x%016llx\n",
+		CVM_CAST64(intr64));
+}
+
+int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
+{
+	struct octeon_droq *droq;
+	u32 oq_no, pkt_count, droq_time_mask, droq_mask, droq_int_enb;
+	u32 droq_cnt_enb, droq_cnt_mask;
+
+	droq_cnt_enb = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT_ENB);
+	droq_cnt_mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_CNT_INT);
+	droq_mask = droq_cnt_mask & droq_cnt_enb;
+
+	droq_time_mask = octeon_read_csr(oct, CN6XXX_SLI_PKT_TIME_INT);
+	droq_int_enb = octeon_read_csr(oct, CN6XXX_SLI_PKT_TIME_INT_ENB);
+	droq_mask |= (droq_time_mask & droq_int_enb);
+
+	droq_mask &= oct->io_qmask.oq;
+
+	oct->droq_intr = 0;
+
+	/* for (oq_no = 0; oq_no < oct->num_oqs; oq_no++) { */
+	for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
+		if (!(droq_mask & (1 << oq_no)))
+			continue;
+
+		droq = oct->droq[oq_no];
+		pkt_count = octeon_droq_check_hw_for_pkts(oct, droq);
+		if (pkt_count) {
+			oct->droq_intr |= (1ULL << oq_no);
+			if (droq->ops.poll_mode) {
+				u32 value;
+				u32 reg;
+
+				struct octeon_cn6xxx *cn6xxx =
+					(struct octeon_cn6xxx *)oct->chip;
+
+				/* disable interrupts for this droq */
+				spin_lock
+					(&cn6xxx->lock_for_droq_int_enb_reg);
+				reg = CN6XXX_SLI_PKT_TIME_INT_ENB;
+				value = octeon_read_csr(oct, reg);
+				value &= ~(1 << oq_no);
+				octeon_write_csr(oct, reg, value);
+				reg = CN6XXX_SLI_PKT_CNT_INT_ENB;
+				value = octeon_read_csr(oct, reg);
+				value &= ~(1 << oq_no);
+				octeon_write_csr(oct, reg, value);
+
+				/* Ensure that the enable register is written.
+				 */
+				mmiowb();
+
+				spin_unlock(&cn6xxx->lock_for_droq_int_enb_reg);
+			}
+		}
+	}
+
+	droq_time_mask &= oct->io_qmask.oq;
+	droq_cnt_mask &= oct->io_qmask.oq;
+
+	/* Reset the PKT_CNT/TIME_INT registers. */
+	if (droq_time_mask)
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_TIME_INT, droq_time_mask);
+
+	if (droq_cnt_mask)      /* reset PKT_CNT register:66xx */
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_CNT_INT, droq_cnt_mask);
+
+	return 0;
+}
+
+irqreturn_t lio_cn6xxx_process_interrupt_regs(void *dev)
+{
+	struct octeon_device *oct = (struct octeon_device *)dev;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+	u64 intr64;
+
+	intr64 = readq(cn6xxx->intr_sum_reg64);
+
+	/* If our device has interrupted, then proceed.
+	 * Also check for all f's if interrupt was triggered on an error
+	 * and the PCI read fails.
+	 */
+	if (!intr64 || (intr64 == 0xFFFFFFFFFFFFFFFFULL))
+		return IRQ_NONE;
+
+	oct->int_status = 0;
+
+	if (intr64 & CN6XXX_INTR_ERR)
+		lio_cn6xxx_process_pcie_error_intr(oct, intr64);
+
+	if (intr64 & CN6XXX_INTR_PKT_DATA) {
+		lio_cn6xxx_process_droq_intr_regs(oct);
+		oct->int_status |= OCT_DEV_INTR_PKT_DATA;
+	}
+
+	if (intr64 & CN6XXX_INTR_DMA0_FORCE)
+		oct->int_status |= OCT_DEV_INTR_DMA0_FORCE;
+
+	if (intr64 & CN6XXX_INTR_DMA1_FORCE)
+		oct->int_status |= OCT_DEV_INTR_DMA1_FORCE;
+
+	/* Clear the current interrupts */
+	writeq(intr64, cn6xxx->intr_sum_reg64);
+
+	return IRQ_HANDLED;
+}
+
+void lio_cn6xxx_setup_reg_address(struct octeon_device *oct,
+				  void *chip,
+				  struct octeon_reg_list *reg_list)
+{
+	u8 __iomem *bar0_pciaddr = oct->mmio[0].hw_addr;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)chip;
+
+	reg_list->pci_win_wr_addr_hi =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_ADDR_HI);
+	reg_list->pci_win_wr_addr_lo =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_ADDR_LO);
+	reg_list->pci_win_wr_addr =
+		(u64 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_ADDR64);
+
+	reg_list->pci_win_rd_addr_hi =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_ADDR_HI);
+	reg_list->pci_win_rd_addr_lo =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_ADDR_LO);
+	reg_list->pci_win_rd_addr =
+		(u64 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_ADDR64);
+
+	reg_list->pci_win_wr_data_hi =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_DATA_HI);
+	reg_list->pci_win_wr_data_lo =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_DATA_LO);
+	reg_list->pci_win_wr_data =
+		(u64 __iomem *)(bar0_pciaddr + CN6XXX_WIN_WR_DATA64);
+
+	reg_list->pci_win_rd_data_hi =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_DATA_HI);
+	reg_list->pci_win_rd_data_lo =
+		(u32 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_DATA_LO);
+	reg_list->pci_win_rd_data =
+		(u64 __iomem *)(bar0_pciaddr + CN6XXX_WIN_RD_DATA64);
+
+	lio_cn6xxx_get_pcie_qlmport(oct);
+
+	cn6xxx->intr_sum_reg64 = bar0_pciaddr + CN6XXX_SLI_INT_SUM64;
+	cn6xxx->intr_mask64 = CN6XXX_INTR_MASK;
+	cn6xxx->intr_enb_reg64 =
+		bar0_pciaddr + CN6XXX_SLI_INT_ENB64(oct->pcie_port);
+}
+
+int lio_setup_cn66xx_octeon_device(struct octeon_device *oct)
+{
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+
+	if (octeon_map_pci_barx(oct, 0, 0))
+		return 1;
+
+	if (octeon_map_pci_barx(oct, 1, MAX_BAR1_IOREMAP_SIZE)) {
+		dev_err(&oct->pci_dev->dev, "%s CN66XX BAR1 map failed\n",
+			__func__);
+		octeon_unmap_pci_barx(oct, 0);
+		return 1;
+	}
+
+	spin_lock_init(&cn6xxx->lock_for_droq_int_enb_reg);
+
+	oct->fn_list.setup_iq_regs = lio_cn66xx_setup_iq_regs;
+	oct->fn_list.setup_oq_regs = lio_cn6xxx_setup_oq_regs;
+
+	oct->fn_list.soft_reset = lio_cn6xxx_soft_reset;
+	oct->fn_list.setup_device_regs = lio_cn6xxx_setup_device_regs;
+	oct->fn_list.reinit_regs = lio_cn6xxx_reinit_regs;
+	oct->fn_list.update_iq_read_idx = lio_cn6xxx_update_read_index;
+
+	oct->fn_list.bar1_idx_setup = lio_cn6xxx_bar1_idx_setup;
+	oct->fn_list.bar1_idx_write = lio_cn6xxx_bar1_idx_write;
+	oct->fn_list.bar1_idx_read = lio_cn6xxx_bar1_idx_read;
+
+	oct->fn_list.process_interrupt_regs = lio_cn6xxx_process_interrupt_regs;
+	oct->fn_list.enable_interrupt = lio_cn6xxx_enable_interrupt;
+	oct->fn_list.disable_interrupt = lio_cn6xxx_disable_interrupt;
+
+	oct->fn_list.enable_io_queues = lio_cn6xxx_enable_io_queues;
+	oct->fn_list.disable_io_queues = lio_cn6xxx_disable_io_queues;
+
+	lio_cn6xxx_setup_reg_address(oct, oct->chip, &oct->reg_list);
+
+	cn6xxx->conf = (struct octeon_config *)
+		       oct_get_config_info(oct, LIO_210SV);
+	if (!cn6xxx->conf) {
+		dev_err(&oct->pci_dev->dev, "%s No Config found for CN66XX\n",
+			__func__);
+		octeon_unmap_pci_barx(oct, 0);
+		octeon_unmap_pci_barx(oct, 1);
+		return 1;
+	}
+
+	oct->coproc_clock_rate = 1000000ULL * lio_cn6xxx_coprocessor_clock(oct);
+
+	return 0;
+}
+
+int lio_validate_cn6xxx_config_info(struct octeon_device *oct,
+				    struct octeon_config *conf6xxx)
+{
+	/* int total_instrs = 0; */
+
+	if (CFG_GET_IQ_MAX_Q(conf6xxx) > CN6XXX_MAX_INPUT_QUEUES) {
+		dev_err(&oct->pci_dev->dev, "%s: Num IQ (%d) exceeds Max (%d)\n",
+			__func__, CFG_GET_IQ_MAX_Q(conf6xxx),
+			CN6XXX_MAX_INPUT_QUEUES);
+		return 1;
+	}
+
+	if (CFG_GET_OQ_MAX_Q(conf6xxx) > CN6XXX_MAX_OUTPUT_QUEUES) {
+		dev_err(&oct->pci_dev->dev, "%s: Num OQ (%d) exceeds Max (%d)\n",
+			__func__, CFG_GET_OQ_MAX_Q(conf6xxx),
+			CN6XXX_MAX_OUTPUT_QUEUES);
+		return 1;
+	}
+
+	if (CFG_GET_IQ_INSTR_TYPE(conf6xxx) != OCTEON_32BYTE_INSTR &&
+	    CFG_GET_IQ_INSTR_TYPE(conf6xxx) != OCTEON_64BYTE_INSTR) {
+		dev_err(&oct->pci_dev->dev, "%s: Invalid instr type for IQ\n",
+			__func__);
+		return 1;
+	}
+	if (!(CFG_GET_OQ_INFO_PTR(conf6xxx)) ||
+	    !(CFG_GET_OQ_REFILL_THRESHOLD(conf6xxx))) {
+		dev_err(&oct->pci_dev->dev, "%s: Invalid parameter for OQ\n",
+			__func__);
+		return 1;
+	}
+
+	if (!(CFG_GET_OQ_INTR_TIME(conf6xxx))) {
+		dev_err(&oct->pci_dev->dev, "%s: No Time Interrupt for OQ\n",
+			__func__);
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
new file mode 100644
index 000000000000..f77918779355
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
@@ -0,0 +1,107 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file  cn66xx_device.h
+ *  \brief Host Driver: Routines that perform CN66XX specific operations.
+ */
+
+#ifndef __CN66XX_DEVICE_H__
+#define  __CN66XX_DEVICE_H__
+
+/* Register address and configuration for a CN6XXX devices.
+ * If device specific changes need to be made then add a struct to include
+ * device specific fields as shown in the commented section
+ */
+struct octeon_cn6xxx {
+	/** PCI interrupt summary register */
+	u8 __iomem *intr_sum_reg64;
+
+	/** PCI interrupt enable register */
+	u8 __iomem *intr_enb_reg64;
+
+	/** The PCI interrupt mask used by interrupt handler */
+	u64 intr_mask64;
+
+	struct octeon_config *conf;
+
+	/* Example additional fields - not used currently
+	 *  struct {
+	 *  }cn6xyz;
+	 */
+
+	/* For the purpose of atomic access to interrupt enable reg */
+	spinlock_t lock_for_droq_int_enb_reg;
+
+};
+
+enum octeon_pcie_mps {
+	PCIE_MPS_DEFAULT = -1,	/* Use the default setup by BIOS */
+	PCIE_MPS_128B = 0,
+	PCIE_MPS_256B = 1
+};
+
+enum octeon_pcie_mrrs {
+	PCIE_MRRS_DEFAULT = -1,	/* Use the default setup by BIOS */
+	PCIE_MRRS_128B = 0,
+	PCIE_MRRS_256B = 1,
+	PCIE_MRRS_512B = 2,
+	PCIE_MRRS_1024B = 3,
+	PCIE_MRRS_2048B = 4,
+	PCIE_MRRS_4096B = 5
+};
+
+/* Common functions for 66xx and 68xx */
+int lio_cn6xxx_soft_reset(struct octeon_device *oct);
+void lio_cn6xxx_enable_error_reporting(struct octeon_device *oct);
+void lio_cn6xxx_setup_pcie_mps(struct octeon_device *oct,
+			       enum octeon_pcie_mps mps);
+void lio_cn6xxx_setup_pcie_mrrs(struct octeon_device *oct,
+				enum octeon_pcie_mrrs mrrs);
+void lio_cn6xxx_setup_global_input_regs(struct octeon_device *oct);
+void lio_cn6xxx_setup_global_output_regs(struct octeon_device *oct);
+void lio_cn6xxx_setup_iq_regs(struct octeon_device *oct, u32 iq_no);
+void lio_cn6xxx_setup_oq_regs(struct octeon_device *oct, u32 oq_no);
+void lio_cn6xxx_enable_io_queues(struct octeon_device *oct);
+void lio_cn6xxx_disable_io_queues(struct octeon_device *oct);
+void lio_cn6xxx_process_pcie_error_intr(struct octeon_device *oct, u64 intr64);
+int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct);
+irqreturn_t lio_cn6xxx_process_interrupt_regs(void *dev);
+void lio_cn6xxx_reinit_regs(struct octeon_device *oct);
+void lio_cn6xxx_bar1_idx_setup(struct octeon_device *oct, u64 core_addr,
+			       u32 idx, int valid);
+void lio_cn6xxx_bar1_idx_write(struct octeon_device *oct, u32 idx, u32 mask);
+u32 lio_cn6xxx_bar1_idx_read(struct octeon_device *oct, u32 idx);
+u32
+lio_cn6xxx_update_read_index(struct octeon_device *oct __attribute__((unused)),
+			     struct octeon_instr_queue *iq);
+void lio_cn6xxx_enable_interrupt(void *chip);
+void lio_cn6xxx_disable_interrupt(void *chip);
+void cn6xxx_get_pcie_qlmport(struct octeon_device *oct);
+void lio_cn6xxx_setup_reg_address(struct octeon_device *oct, void *chip,
+				  struct octeon_reg_list *reg_list);
+u32 lio_cn6xxx_coprocessor_clock(struct octeon_device *oct);
+u32 lio_cn6xxx_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us);
+int lio_setup_cn66xx_octeon_device(struct octeon_device *);
+int lio_validate_cn6xxx_config_info(struct octeon_device *oct,
+				    struct octeon_config *);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
new file mode 100644
index 000000000000..5e3aff242ad3
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h
@@ -0,0 +1,535 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file cn66xx_regs.h
+ *  \brief Host Driver: Register Address and Register Mask values for
+ *  Octeon CN66XX devices.
+ */
+
+#ifndef __CN66XX_REGS_H__
+#define __CN66XX_REGS_H__
+
+#define     CN6XXX_XPANSION_BAR             0x30
+
+#define     CN6XXX_MSI_CAP                  0x50
+#define     CN6XXX_MSI_ADDR_LO              0x54
+#define     CN6XXX_MSI_ADDR_HI              0x58
+#define     CN6XXX_MSI_DATA                 0x5C
+
+#define     CN6XXX_PCIE_CAP                 0x70
+#define     CN6XXX_PCIE_DEVCAP              0x74
+#define     CN6XXX_PCIE_DEVCTL              0x78
+#define     CN6XXX_PCIE_LINKCAP             0x7C
+#define     CN6XXX_PCIE_LINKCTL             0x80
+#define     CN6XXX_PCIE_SLOTCAP             0x84
+#define     CN6XXX_PCIE_SLOTCTL             0x88
+
+#define     CN6XXX_PCIE_ENH_CAP             0x100
+#define     CN6XXX_PCIE_UNCORR_ERR_STATUS   0x104
+#define     CN6XXX_PCIE_UNCORR_ERR_MASK     0x108
+#define     CN6XXX_PCIE_UNCORR_ERR          0x10C
+#define     CN6XXX_PCIE_CORR_ERR_STATUS     0x110
+#define     CN6XXX_PCIE_CORR_ERR_MASK       0x114
+#define     CN6XXX_PCIE_ADV_ERR_CAP         0x118
+
+#define     CN6XXX_PCIE_ACK_REPLAY_TIMER    0x700
+#define     CN6XXX_PCIE_OTHER_MSG           0x704
+#define     CN6XXX_PCIE_PORT_FORCE_LINK     0x708
+#define     CN6XXX_PCIE_ACK_FREQ            0x70C
+#define     CN6XXX_PCIE_PORT_LINK_CTL       0x710
+#define     CN6XXX_PCIE_LANE_SKEW           0x714
+#define     CN6XXX_PCIE_SYM_NUM             0x718
+#define     CN6XXX_PCIE_FLTMSK              0x720
+
+/* ##############  BAR0 Registers ################  */
+
+#define    CN6XXX_SLI_CTL_PORT0                    0x0050
+#define    CN6XXX_SLI_CTL_PORT1                    0x0060
+
+#define    CN6XXX_SLI_WINDOW_CTL                   0x02E0
+#define    CN6XXX_SLI_DBG_DATA                     0x0310
+#define    CN6XXX_SLI_SCRATCH1                     0x03C0
+#define    CN6XXX_SLI_SCRATCH2                     0x03D0
+#define    CN6XXX_SLI_CTL_STATUS                   0x0570
+
+#define    CN6XXX_WIN_WR_ADDR_LO                   0x0000
+#define    CN6XXX_WIN_WR_ADDR_HI                   0x0004
+#define    CN6XXX_WIN_WR_ADDR64                    CN6XXX_WIN_WR_ADDR_LO
+
+#define    CN6XXX_WIN_RD_ADDR_LO                   0x0010
+#define    CN6XXX_WIN_RD_ADDR_HI                   0x0014
+#define    CN6XXX_WIN_RD_ADDR64                    CN6XXX_WIN_RD_ADDR_LO
+
+#define    CN6XXX_WIN_WR_DATA_LO                   0x0020
+#define    CN6XXX_WIN_WR_DATA_HI                   0x0024
+#define    CN6XXX_WIN_WR_DATA64                    CN6XXX_WIN_WR_DATA_LO
+
+#define    CN6XXX_WIN_RD_DATA_LO                   0x0040
+#define    CN6XXX_WIN_RD_DATA_HI                   0x0044
+#define    CN6XXX_WIN_RD_DATA64                    CN6XXX_WIN_RD_DATA_LO
+
+#define    CN6XXX_WIN_WR_MASK_LO                   0x0030
+#define    CN6XXX_WIN_WR_MASK_HI                   0x0034
+#define    CN6XXX_WIN_WR_MASK_REG                  CN6XXX_WIN_WR_MASK_LO
+
+/* 1 register (32-bit) to enable Input queues */
+#define    CN6XXX_SLI_PKT_INSTR_ENB               0x1000
+
+/* 1 register (32-bit) to enable Output queues */
+#define    CN6XXX_SLI_PKT_OUT_ENB                 0x1010
+
+/* 1 register (32-bit) to determine whether Output queues are in reset. */
+#define    CN6XXX_SLI_PORT_IN_RST_OQ              0x11F0
+
+/* 1 register (32-bit) to determine whether Input queues are in reset. */
+#define    CN6XXX_SLI_PORT_IN_RST_IQ              0x11F4
+
+/*###################### REQUEST QUEUE #########################*/
+
+/* 1 register (32-bit) - instr. size of each input queue. */
+#define    CN6XXX_SLI_PKT_INSTR_SIZE             0x1020
+
+/* 32 registers for Input Queue Instr Count - SLI_PKT_IN_DONE0_CNTS */
+#define    CN6XXX_SLI_IQ_INSTR_COUNT_START       0x2000
+
+/* 32 registers for Input Queue Start Addr - SLI_PKT0_INSTR_BADDR */
+#define    CN6XXX_SLI_IQ_BASE_ADDR_START64       0x2800
+
+/* 32 registers for Input Doorbell - SLI_PKT0_INSTR_BAOFF_DBELL */
+#define    CN6XXX_SLI_IQ_DOORBELL_START          0x2C00
+
+/* 32 registers for Input Queue size - SLI_PKT0_INSTR_FIFO_RSIZE */
+#define    CN6XXX_SLI_IQ_SIZE_START              0x3000
+
+/* 32 registers for Instruction Header Options - SLI_PKT0_INSTR_HEADER */
+#define    CN6XXX_SLI_IQ_PKT_INSTR_HDR_START64   0x3400
+
+/* 1 register (64-bit) - Back Pressure for each input queue - SLI_PKT0_IN_BP */
+#define    CN66XX_SLI_INPUT_BP_START64           0x3800
+
+/* Each Input Queue register is at a 16-byte Offset in BAR0 */
+#define    CN6XXX_IQ_OFFSET                      0x10
+
+/* 1 register (32-bit) - ES, RO, NS, Arbitration for Input Queue Data &
+ * gather list fetches. SLI_PKT_INPUT_CONTROL.
+ */
+#define    CN6XXX_SLI_PKT_INPUT_CONTROL          0x1170
+
+/* 1 register (64-bit) - Number of instructions to read at one time
+ * - 2 bits for each input ring. SLI_PKT_INSTR_RD_SIZE.
+ */
+#define    CN6XXX_SLI_PKT_INSTR_RD_SIZE          0x11A0
+
+/* 1 register (64-bit) - Assign Input ring to MAC port
+ * - 2 bits for each input ring. SLI_PKT_IN_PCIE_PORT.
+ */
+#define    CN6XXX_SLI_IN_PCIE_PORT               0x11B0
+
+/*------- Request Queue Macros ---------*/
+#define    CN6XXX_SLI_IQ_BASE_ADDR64(iq)          \
+	(CN6XXX_SLI_IQ_BASE_ADDR_START64 + ((iq) * CN6XXX_IQ_OFFSET))
+
+#define    CN6XXX_SLI_IQ_SIZE(iq)                 \
+	(CN6XXX_SLI_IQ_SIZE_START + ((iq) * CN6XXX_IQ_OFFSET))
+
+#define    CN6XXX_SLI_IQ_PKT_INSTR_HDR64(iq)      \
+	(CN6XXX_SLI_IQ_PKT_INSTR_HDR_START64 + ((iq) * CN6XXX_IQ_OFFSET))
+
+#define    CN6XXX_SLI_IQ_DOORBELL(iq)             \
+	(CN6XXX_SLI_IQ_DOORBELL_START + ((iq) * CN6XXX_IQ_OFFSET))
+
+#define    CN6XXX_SLI_IQ_INSTR_COUNT(iq)          \
+	(CN6XXX_SLI_IQ_INSTR_COUNT_START + ((iq) * CN6XXX_IQ_OFFSET))
+
+#define    CN66XX_SLI_IQ_BP64(iq)                 \
+	(CN66XX_SLI_INPUT_BP_START64 + ((iq) * CN6XXX_IQ_OFFSET))
+
+/*------------------ Masks ----------------*/
+#define    CN6XXX_INPUT_CTL_ROUND_ROBIN_ARB         BIT(22)
+#define    CN6XXX_INPUT_CTL_DATA_NS                 BIT(8)
+#define    CN6XXX_INPUT_CTL_DATA_ES_64B_SWAP        BIT(6)
+#define    CN6XXX_INPUT_CTL_DATA_RO                 BIT(5)
+#define    CN6XXX_INPUT_CTL_USE_CSR                 BIT(4)
+#define    CN6XXX_INPUT_CTL_GATHER_NS               BIT(3)
+#define    CN6XXX_INPUT_CTL_GATHER_ES_64B_SWAP      BIT(2)
+#define    CN6XXX_INPUT_CTL_GATHER_RO               BIT(1)
+
+#ifdef __BIG_ENDIAN_BITFIELD
+#define    CN6XXX_INPUT_CTL_MASK                    \
+	(CN6XXX_INPUT_CTL_DATA_ES_64B_SWAP      \
+	  | CN6XXX_INPUT_CTL_USE_CSR              \
+	  | CN6XXX_INPUT_CTL_GATHER_ES_64B_SWAP)
+#else
+#define    CN6XXX_INPUT_CTL_MASK                    \
+	(CN6XXX_INPUT_CTL_DATA_ES_64B_SWAP     \
+	  | CN6XXX_INPUT_CTL_USE_CSR)
+#endif
+
+/*############################ OUTPUT QUEUE #########################*/
+
+/* 32 registers for Output queue buffer and info size - SLI_PKT0_OUT_SIZE */
+#define    CN6XXX_SLI_OQ0_BUFF_INFO_SIZE         0x0C00
+
+/* 32 registers for Output Queue Start Addr - SLI_PKT0_SLIST_BADDR */
+#define    CN6XXX_SLI_OQ_BASE_ADDR_START64       0x1400
+
+/* 32 registers for Output Queue Packet Credits - SLI_PKT0_SLIST_BAOFF_DBELL */
+#define    CN6XXX_SLI_OQ_PKT_CREDITS_START       0x1800
+
+/* 32 registers for Output Queue size - SLI_PKT0_SLIST_FIFO_RSIZE */
+#define    CN6XXX_SLI_OQ_SIZE_START              0x1C00
+
+/* 32 registers for Output Queue Packet Count - SLI_PKT0_CNTS */
+#define    CN6XXX_SLI_OQ_PKT_SENT_START          0x2400
+
+/* Each Output Queue register is at a 16-byte Offset in BAR0 */
+#define    CN6XXX_OQ_OFFSET                      0x10
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - Relaxed Ordering setting for reading Output Queues descriptors
+ * - SLI_PKT_SLIST_ROR
+ */
+#define    CN6XXX_SLI_PKT_SLIST_ROR              0x1030
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - No Snoop mode for reading Output Queues descriptors
+ * - SLI_PKT_SLIST_NS
+ */
+#define    CN6XXX_SLI_PKT_SLIST_NS               0x1040
+
+/* 1 register (64-bit) - 2 bits for each output queue
+ * - Endian-Swap mode for reading Output Queue descriptors
+ * - SLI_PKT_SLIST_ES
+ */
+#define    CN6XXX_SLI_PKT_SLIST_ES64             0x1050
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - InfoPtr mode for Output Queues.
+ * - SLI_PKT_IPTR
+ */
+#define    CN6XXX_SLI_PKT_IPTR                   0x1070
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - DPTR format selector for Output queues.
+ * - SLI_PKT_DPADDR
+ */
+#define    CN6XXX_SLI_PKT_DPADDR                 0x1080
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - Relaxed Ordering setting for reading Output Queues data
+ * - SLI_PKT_DATA_OUT_ROR
+ */
+#define    CN6XXX_SLI_PKT_DATA_OUT_ROR           0x1090
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - No Snoop mode for reading Output Queues data
+ * - SLI_PKT_DATA_OUT_NS
+ */
+#define    CN6XXX_SLI_PKT_DATA_OUT_NS            0x10A0
+
+/* 1 register (64-bit)  - 2 bits for each output queue
+ * - Endian-Swap mode for reading Output Queue data
+ * - SLI_PKT_DATA_OUT_ES
+ */
+#define    CN6XXX_SLI_PKT_DATA_OUT_ES64          0x10B0
+
+/* 1 register (32-bit) - 1 bit for each output queue
+ * - Controls whether SLI_PKTn_CNTS is incremented for bytes or for packets.
+ * - SLI_PKT_OUT_BMODE
+ */
+#define    CN6XXX_SLI_PKT_OUT_BMODE              0x10D0
+
+/* 1 register (64-bit) - 2 bits for each output queue
+ * - Assign PCIE port for Output queues
+ * - SLI_PKT_PCIE_PORT.
+ */
+#define    CN6XXX_SLI_PKT_PCIE_PORT64            0x10E0
+
+/* 1 (64-bit) register for Output Queue Packet Count Interrupt Threshold
+ * & Time Threshold. The same setting applies to all 32 queues.
+ * The register is defined as a 64-bit registers, but we use the
+ * 32-bit offsets to define distinct addresses.
+ */
+#define    CN6XXX_SLI_OQ_INT_LEVEL_PKTS          0x1120
+#define    CN6XXX_SLI_OQ_INT_LEVEL_TIME          0x1124
+
+/* 1 (64-bit register) for Output Queue backpressure across all rings. */
+#define    CN6XXX_SLI_OQ_WMARK                   0x1180
+
+/* 1 register to control output queue global backpressure & ring enable. */
+#define    CN6XXX_SLI_PKT_CTL                    0x1220
+
+/*------- Output Queue Macros ---------*/
+#define    CN6XXX_SLI_OQ_BASE_ADDR64(oq)          \
+	(CN6XXX_SLI_OQ_BASE_ADDR_START64 + ((oq) * CN6XXX_OQ_OFFSET))
+
+#define    CN6XXX_SLI_OQ_SIZE(oq)                 \
+	(CN6XXX_SLI_OQ_SIZE_START + ((oq) * CN6XXX_OQ_OFFSET))
+
+#define    CN6XXX_SLI_OQ_BUFF_INFO_SIZE(oq)                 \
+	(CN6XXX_SLI_OQ0_BUFF_INFO_SIZE + ((oq) * CN6XXX_OQ_OFFSET))
+
+#define    CN6XXX_SLI_OQ_PKTS_SENT(oq)            \
+	(CN6XXX_SLI_OQ_PKT_SENT_START + ((oq) * CN6XXX_OQ_OFFSET))
+
+#define    CN6XXX_SLI_OQ_PKTS_CREDIT(oq)          \
+	(CN6XXX_SLI_OQ_PKT_CREDITS_START + ((oq) * CN6XXX_OQ_OFFSET))
+
+/*######################### DMA Counters #########################*/
+
+/* 2 registers (64-bit) - DMA Count - 1 for each DMA counter 0/1. */
+#define    CN6XXX_DMA_CNT_START                   0x0400
+
+/* 2 registers (64-bit) - DMA Timer 0/1, contains DMA timer values
+ * SLI_DMA_0_TIM
+ */
+#define    CN6XXX_DMA_TIM_START                   0x0420
+
+/* 2 registers (64-bit) - DMA count & Time Interrupt threshold -
+ * SLI_DMA_0_INT_LEVEL
+ */
+#define    CN6XXX_DMA_INT_LEVEL_START             0x03E0
+
+/* Each DMA register is at a 16-byte Offset in BAR0 */
+#define    CN6XXX_DMA_OFFSET                      0x10
+
+/*---------- DMA Counter Macros ---------*/
+#define    CN6XXX_DMA_CNT(dq)                      \
+	(CN6XXX_DMA_CNT_START + ((dq) * CN6XXX_DMA_OFFSET))
+
+#define    CN6XXX_DMA_INT_LEVEL(dq)                \
+	(CN6XXX_DMA_INT_LEVEL_START + ((dq) * CN6XXX_DMA_OFFSET))
+
+#define    CN6XXX_DMA_PKT_INT_LEVEL(dq)            \
+	(CN6XXX_DMA_INT_LEVEL_START + ((dq) * CN6XXX_DMA_OFFSET))
+
+#define    CN6XXX_DMA_TIME_INT_LEVEL(dq)           \
+	(CN6XXX_DMA_INT_LEVEL_START + 4 + ((dq) * CN6XXX_DMA_OFFSET))
+
+#define    CN6XXX_DMA_TIM(dq)                      \
+	(CN6XXX_DMA_TIM_START + ((dq) * CN6XXX_DMA_OFFSET))
+
+/*######################## INTERRUPTS #########################*/
+
+/* 1 register (64-bit) for Interrupt Summary */
+#define    CN6XXX_SLI_INT_SUM64                  0x0330
+
+/* 1 register (64-bit) for Interrupt Enable */
+#define    CN6XXX_SLI_INT_ENB64_PORT0            0x0340
+#define    CN6XXX_SLI_INT_ENB64_PORT1            0x0350
+
+/* 1 register (32-bit) to enable Output Queue Packet/Byte Count Interrupt */
+#define    CN6XXX_SLI_PKT_CNT_INT_ENB            0x1150
+
+/* 1 register (32-bit) to enable Output Queue Packet Timer Interrupt */
+#define    CN6XXX_SLI_PKT_TIME_INT_ENB           0x1160
+
+/* 1 register (32-bit) to indicate which Output Queue reached pkt threshold */
+#define    CN6XXX_SLI_PKT_CNT_INT                0x1130
+
+/* 1 register (32-bit) to indicate which Output Queue reached time threshold */
+#define    CN6XXX_SLI_PKT_TIME_INT               0x1140
+
+/*------------------ Interrupt Masks ----------------*/
+
+#define    CN6XXX_INTR_RML_TIMEOUT_ERR           BIT(1)
+#define    CN6XXX_INTR_BAR0_RW_TIMEOUT_ERR       BIT(2)
+#define    CN6XXX_INTR_IO2BIG_ERR                BIT(3)
+#define    CN6XXX_INTR_PKT_COUNT                 BIT(4)
+#define    CN6XXX_INTR_PKT_TIME                  BIT(5)
+#define    CN6XXX_INTR_M0UPB0_ERR                BIT(8)
+#define    CN6XXX_INTR_M0UPWI_ERR                BIT(9)
+#define    CN6XXX_INTR_M0UNB0_ERR                BIT(10)
+#define    CN6XXX_INTR_M0UNWI_ERR                BIT(11)
+#define    CN6XXX_INTR_M1UPB0_ERR                BIT(12)
+#define    CN6XXX_INTR_M1UPWI_ERR                BIT(13)
+#define    CN6XXX_INTR_M1UNB0_ERR                BIT(14)
+#define    CN6XXX_INTR_M1UNWI_ERR                BIT(15)
+#define    CN6XXX_INTR_MIO_INT0                  BIT(16)
+#define    CN6XXX_INTR_MIO_INT1                  BIT(17)
+#define    CN6XXX_INTR_MAC_INT0                  BIT(18)
+#define    CN6XXX_INTR_MAC_INT1                  BIT(19)
+
+#define    CN6XXX_INTR_DMA0_FORCE                BIT_ULL(32)
+#define    CN6XXX_INTR_DMA1_FORCE                BIT_ULL(33)
+#define    CN6XXX_INTR_DMA0_COUNT                BIT_ULL(34)
+#define    CN6XXX_INTR_DMA1_COUNT                BIT_ULL(35)
+#define    CN6XXX_INTR_DMA0_TIME                 BIT_ULL(36)
+#define    CN6XXX_INTR_DMA1_TIME                 BIT_ULL(37)
+#define    CN6XXX_INTR_INSTR_DB_OF_ERR           BIT_ULL(48)
+#define    CN6XXX_INTR_SLIST_DB_OF_ERR           BIT_ULL(49)
+#define    CN6XXX_INTR_POUT_ERR                  BIT_ULL(50)
+#define    CN6XXX_INTR_PIN_BP_ERR                BIT_ULL(51)
+#define    CN6XXX_INTR_PGL_ERR                   BIT_ULL(52)
+#define    CN6XXX_INTR_PDI_ERR                   BIT_ULL(53)
+#define    CN6XXX_INTR_POP_ERR                   BIT_ULL(54)
+#define    CN6XXX_INTR_PINS_ERR                  BIT_ULL(55)
+#define    CN6XXX_INTR_SPRT0_ERR                 BIT_ULL(56)
+#define    CN6XXX_INTR_SPRT1_ERR                 BIT_ULL(57)
+#define    CN6XXX_INTR_ILL_PAD_ERR               BIT_ULL(60)
+
+#define    CN6XXX_INTR_DMA0_DATA                 (CN6XXX_INTR_DMA0_TIME)
+
+#define    CN6XXX_INTR_DMA1_DATA                 (CN6XXX_INTR_DMA1_TIME)
+
+#define    CN6XXX_INTR_DMA_DATA                  \
+	(CN6XXX_INTR_DMA0_DATA | CN6XXX_INTR_DMA1_DATA)
+
+#define    CN6XXX_INTR_PKT_DATA                  (CN6XXX_INTR_PKT_TIME | \
+						  CN6XXX_INTR_PKT_COUNT)
+
+/* Sum of interrupts for all PCI-Express Data Interrupts */
+#define    CN6XXX_INTR_PCIE_DATA                 \
+	(CN6XXX_INTR_DMA_DATA | CN6XXX_INTR_PKT_DATA)
+
+#define    CN6XXX_INTR_MIO                       \
+	(CN6XXX_INTR_MIO_INT0 | CN6XXX_INTR_MIO_INT1)
+
+#define    CN6XXX_INTR_MAC                       \
+	(CN6XXX_INTR_MAC_INT0 | CN6XXX_INTR_MAC_INT1)
+
+/* Sum of interrupts for error events */
+#define    CN6XXX_INTR_ERR                       \
+	(CN6XXX_INTR_BAR0_RW_TIMEOUT_ERR    \
+	   | CN6XXX_INTR_IO2BIG_ERR             \
+	   | CN6XXX_INTR_M0UPB0_ERR             \
+	   | CN6XXX_INTR_M0UPWI_ERR             \
+	   | CN6XXX_INTR_M0UNB0_ERR             \
+	   | CN6XXX_INTR_M0UNWI_ERR             \
+	   | CN6XXX_INTR_M1UPB0_ERR             \
+	   | CN6XXX_INTR_M1UPWI_ERR             \
+	   | CN6XXX_INTR_M1UPB0_ERR             \
+	   | CN6XXX_INTR_M1UNWI_ERR             \
+	   | CN6XXX_INTR_INSTR_DB_OF_ERR        \
+	   | CN6XXX_INTR_SLIST_DB_OF_ERR        \
+	   | CN6XXX_INTR_POUT_ERR               \
+	   | CN6XXX_INTR_PIN_BP_ERR             \
+	   | CN6XXX_INTR_PGL_ERR                \
+	   | CN6XXX_INTR_PDI_ERR                \
+	   | CN6XXX_INTR_POP_ERR                \
+	   | CN6XXX_INTR_PINS_ERR               \
+	   | CN6XXX_INTR_SPRT0_ERR              \
+	   | CN6XXX_INTR_SPRT1_ERR              \
+	   | CN6XXX_INTR_ILL_PAD_ERR)
+
+/* Programmed Mask for Interrupt Sum */
+#define    CN6XXX_INTR_MASK                      \
+	(CN6XXX_INTR_PCIE_DATA              \
+	   | CN6XXX_INTR_DMA0_FORCE             \
+	   | CN6XXX_INTR_DMA1_FORCE             \
+	   | CN6XXX_INTR_MIO                    \
+	   | CN6XXX_INTR_MAC                    \
+	   | CN6XXX_INTR_ERR)
+
+#define    CN6XXX_SLI_S2M_PORT0_CTL              0x3D80
+#define    CN6XXX_SLI_S2M_PORT1_CTL              0x3D90
+#define    CN6XXX_SLI_S2M_PORTX_CTL(port)        \
+	(CN6XXX_SLI_S2M_PORT0_CTL + (port * 0x10))
+
+#define    CN6XXX_SLI_INT_ENB64(port)            \
+	(CN6XXX_SLI_INT_ENB64_PORT0 + (port * 0x10))
+
+#define    CN6XXX_SLI_MAC_NUMBER                 0x3E00
+
+/* CN6XXX BAR1 Index registers. */
+#define    CN6XXX_PEM_BAR1_INDEX000                0x00011800C00000A8ULL
+#define    CN6XXX_PEM_OFFSET                       0x0000000001000000ULL
+
+#define    CN6XXX_BAR1_INDEX_START                 CN6XXX_PEM_BAR1_INDEX000
+#define    CN6XXX_PCI_BAR1_OFFSET                  0x8
+
+#define    CN6XXX_BAR1_REG(idx, port) \
+		(CN6XXX_BAR1_INDEX_START + (port * CN6XXX_PEM_OFFSET) + \
+		(CN6XXX_PCI_BAR1_OFFSET * (idx)))
+
+/*############################ DPI #########################*/
+
+#define    CN6XXX_DPI_CTL                 0x0001df0000000040ULL
+
+#define    CN6XXX_DPI_DMA_CONTROL         0x0001df0000000048ULL
+
+#define    CN6XXX_DPI_REQ_GBL_ENB         0x0001df0000000050ULL
+
+#define    CN6XXX_DPI_REQ_ERR_RSP         0x0001df0000000058ULL
+
+#define    CN6XXX_DPI_REQ_ERR_RST         0x0001df0000000060ULL
+
+#define    CN6XXX_DPI_DMA_ENG0_ENB        0x0001df0000000080ULL
+
+#define    CN6XXX_DPI_DMA_ENG_ENB(q_no)   \
+	(CN6XXX_DPI_DMA_ENG0_ENB + (q_no * 8))
+
+#define    CN6XXX_DPI_DMA_ENG0_BUF        0x0001df0000000880ULL
+
+#define    CN6XXX_DPI_DMA_ENG_BUF(q_no)   \
+	(CN6XXX_DPI_DMA_ENG0_BUF + (q_no * 8))
+
+#define    CN6XXX_DPI_SLI_PRT0_CFG        0x0001df0000000900ULL
+#define    CN6XXX_DPI_SLI_PRT1_CFG        0x0001df0000000908ULL
+#define    CN6XXX_DPI_SLI_PRTX_CFG(port)        \
+	(CN6XXX_DPI_SLI_PRT0_CFG + (port * 0x10))
+
+#define    CN6XXX_DPI_DMA_COMMIT_MODE     BIT_ULL(58)
+#define    CN6XXX_DPI_DMA_PKT_HP          BIT_ULL(57)
+#define    CN6XXX_DPI_DMA_PKT_EN          BIT_ULL(56)
+#define    CN6XXX_DPI_DMA_O_ES            BIT_ULL(15)
+#define    CN6XXX_DPI_DMA_O_MODE          BIT_ULL(14)
+
+#define    CN6XXX_DPI_DMA_CTL_MASK             \
+	(CN6XXX_DPI_DMA_COMMIT_MODE    |    \
+	 CN6XXX_DPI_DMA_PKT_HP         |    \
+	 CN6XXX_DPI_DMA_PKT_EN         |    \
+	 CN6XXX_DPI_DMA_O_ES           |    \
+	 CN6XXX_DPI_DMA_O_MODE)
+
+/*############################ CIU #########################*/
+
+#define    CN6XXX_CIU_SOFT_BIST           0x0001070000000738ULL
+#define    CN6XXX_CIU_SOFT_RST            0x0001070000000740ULL
+
+/*############################ MIO #########################*/
+#define    CN6XXX_MIO_PTP_CLOCK_CFG       0x0001070000000f00ULL
+#define    CN6XXX_MIO_PTP_CLOCK_LO        0x0001070000000f08ULL
+#define    CN6XXX_MIO_PTP_CLOCK_HI        0x0001070000000f10ULL
+#define    CN6XXX_MIO_PTP_CLOCK_COMP      0x0001070000000f18ULL
+#define    CN6XXX_MIO_PTP_TIMESTAMP       0x0001070000000f20ULL
+#define    CN6XXX_MIO_PTP_EVT_CNT         0x0001070000000f28ULL
+#define    CN6XXX_MIO_PTP_CKOUT_THRESH_LO 0x0001070000000f30ULL
+#define    CN6XXX_MIO_PTP_CKOUT_THRESH_HI 0x0001070000000f38ULL
+#define    CN6XXX_MIO_PTP_CKOUT_HI_INCR   0x0001070000000f40ULL
+#define    CN6XXX_MIO_PTP_CKOUT_LO_INCR   0x0001070000000f48ULL
+#define    CN6XXX_MIO_PTP_PPS_THRESH_LO   0x0001070000000f50ULL
+#define    CN6XXX_MIO_PTP_PPS_THRESH_HI   0x0001070000000f58ULL
+#define    CN6XXX_MIO_PTP_PPS_HI_INCR     0x0001070000000f60ULL
+#define    CN6XXX_MIO_PTP_PPS_LO_INCR     0x0001070000000f68ULL
+
+#define    CN6XXX_MIO_QLM4_CFG            0x00011800000015B0ULL
+#define    CN6XXX_MIO_RST_BOOT            0x0001180000001600ULL
+
+#define    CN6XXX_MIO_QLM_CFG_MASK        0x7
+
+/*############################ LMC #########################*/
+
+#define    CN6XXX_LMC0_RESET_CTL               0x0001180088000180ULL
+#define    CN6XXX_LMC0_RESET_CTL_DDR3RST_MASK  0x0000000000000001ULL
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
new file mode 100644
index 000000000000..8e830d0c0754
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c
@@ -0,0 +1,198 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+static void lio_cn68xx_set_dpi_regs(struct octeon_device *oct)
+{
+	u32 i;
+	u32 fifo_sizes[6] = { 3, 3, 1, 1, 1, 8 };
+
+	lio_pci_writeq(oct, CN6XXX_DPI_DMA_CTL_MASK, CN6XXX_DPI_DMA_CONTROL);
+	dev_dbg(&oct->pci_dev->dev, "DPI_DMA_CONTROL: 0x%016llx\n",
+		lio_pci_readq(oct, CN6XXX_DPI_DMA_CONTROL));
+
+	for (i = 0; i < 6; i++) {
+		/* Prevent service of instruction queue for all DMA engines
+		 * Engine 5 will remain 0. Engines 0 - 4 will be setup by
+		 * core.
+		 */
+		lio_pci_writeq(oct, 0, CN6XXX_DPI_DMA_ENG_ENB(i));
+		lio_pci_writeq(oct, fifo_sizes[i], CN6XXX_DPI_DMA_ENG_BUF(i));
+		dev_dbg(&oct->pci_dev->dev, "DPI_ENG_BUF%d: 0x%016llx\n", i,
+			lio_pci_readq(oct, CN6XXX_DPI_DMA_ENG_BUF(i)));
+	}
+
+	/* DPI_SLI_PRT_CFG has MPS and MRRS settings that will be set
+	 * separately.
+	 */
+
+	lio_pci_writeq(oct, 1, CN6XXX_DPI_CTL);
+	dev_dbg(&oct->pci_dev->dev, "DPI_CTL: 0x%016llx\n",
+		lio_pci_readq(oct, CN6XXX_DPI_CTL));
+}
+
+static int lio_cn68xx_soft_reset(struct octeon_device *oct)
+{
+	lio_cn6xxx_soft_reset(oct);
+	lio_cn68xx_set_dpi_regs(oct);
+
+	return 0;
+}
+
+static void lio_cn68xx_setup_pkt_ctl_regs(struct octeon_device *oct)
+{
+	struct octeon_cn6xxx *cn68xx = (struct octeon_cn6xxx *)oct->chip;
+	u64 pktctl, tx_pipe, max_oqs;
+
+	pktctl = octeon_read_csr64(oct, CN6XXX_SLI_PKT_CTL);
+
+	/* 68XX specific */
+	max_oqs = CFG_GET_OQ_MAX_Q(CHIP_FIELD(oct, cn6xxx, conf));
+	tx_pipe  = octeon_read_csr64(oct, CN68XX_SLI_TX_PIPE);
+	tx_pipe &= 0xffffffffff00ffffULL; /* clear out NUMP field */
+	tx_pipe |= max_oqs << 16; /* put max_oqs in NUMP field */
+	octeon_write_csr64(oct, CN68XX_SLI_TX_PIPE, tx_pipe);
+
+	if (CFG_GET_IS_SLI_BP_ON(cn68xx->conf))
+		pktctl |= 0xF;
+	else
+		/* Disable per-port backpressure. */
+		pktctl &= ~0xF;
+	octeon_write_csr64(oct, CN6XXX_SLI_PKT_CTL, pktctl);
+}
+
+static int lio_cn68xx_setup_device_regs(struct octeon_device *oct)
+{
+	lio_cn6xxx_setup_pcie_mps(oct, PCIE_MPS_DEFAULT);
+	lio_cn6xxx_setup_pcie_mrrs(oct, PCIE_MRRS_256B);
+	lio_cn6xxx_enable_error_reporting(oct);
+
+	lio_cn6xxx_setup_global_input_regs(oct);
+	lio_cn68xx_setup_pkt_ctl_regs(oct);
+	lio_cn6xxx_setup_global_output_regs(oct);
+
+	/* Default error timeout value should be 0x200000 to avoid host hang
+	 * when reads invalid register
+	 */
+	octeon_write_csr64(oct, CN6XXX_SLI_WINDOW_CTL, 0x200000ULL);
+
+	return 0;
+}
+
+static inline void lio_cn68xx_vendor_message_fix(struct octeon_device *oct)
+{
+	u32 val = 0;
+
+	/* Set M_VEND1_DRP and M_VEND0_DRP bits */
+	pci_read_config_dword(oct->pci_dev, CN6XXX_PCIE_FLTMSK, &val);
+	val |= 0x3;
+	pci_write_config_dword(oct->pci_dev, CN6XXX_PCIE_FLTMSK, val);
+}
+
+int lio_is_210nv(struct octeon_device *oct)
+{
+	u64 mio_qlm4_cfg = lio_pci_readq(oct, CN6XXX_MIO_QLM4_CFG);
+
+	return ((mio_qlm4_cfg & CN6XXX_MIO_QLM_CFG_MASK) == 0);
+}
+
+int lio_setup_cn68xx_octeon_device(struct octeon_device *oct)
+{
+	struct octeon_cn6xxx *cn68xx = (struct octeon_cn6xxx *)oct->chip;
+	u16 card_type = LIO_410NV;
+
+	if (octeon_map_pci_barx(oct, 0, 0))
+		return 1;
+
+	if (octeon_map_pci_barx(oct, 1, MAX_BAR1_IOREMAP_SIZE)) {
+		dev_err(&oct->pci_dev->dev, "%s CN68XX BAR1 map failed\n",
+			__func__);
+		octeon_unmap_pci_barx(oct, 0);
+		return 1;
+	}
+
+	spin_lock_init(&cn68xx->lock_for_droq_int_enb_reg);
+
+	oct->fn_list.setup_iq_regs = lio_cn6xxx_setup_iq_regs;
+	oct->fn_list.setup_oq_regs = lio_cn6xxx_setup_oq_regs;
+
+	oct->fn_list.process_interrupt_regs = lio_cn6xxx_process_interrupt_regs;
+	oct->fn_list.soft_reset = lio_cn68xx_soft_reset;
+	oct->fn_list.setup_device_regs = lio_cn68xx_setup_device_regs;
+	oct->fn_list.reinit_regs = lio_cn6xxx_reinit_regs;
+	oct->fn_list.update_iq_read_idx = lio_cn6xxx_update_read_index;
+
+	oct->fn_list.bar1_idx_setup = lio_cn6xxx_bar1_idx_setup;
+	oct->fn_list.bar1_idx_write = lio_cn6xxx_bar1_idx_write;
+	oct->fn_list.bar1_idx_read = lio_cn6xxx_bar1_idx_read;
+
+	oct->fn_list.enable_interrupt = lio_cn6xxx_enable_interrupt;
+	oct->fn_list.disable_interrupt = lio_cn6xxx_disable_interrupt;
+
+	oct->fn_list.enable_io_queues = lio_cn6xxx_enable_io_queues;
+	oct->fn_list.disable_io_queues = lio_cn6xxx_disable_io_queues;
+
+	lio_cn6xxx_setup_reg_address(oct, oct->chip, &oct->reg_list);
+
+	/* Determine variant of card */
+	if (lio_is_210nv(oct))
+		card_type = LIO_210NV;
+
+	cn68xx->conf = (struct octeon_config *)
+		       oct_get_config_info(oct, card_type);
+	if (!cn68xx->conf) {
+		dev_err(&oct->pci_dev->dev, "%s No Config found for CN68XX %s\n",
+			__func__,
+			(card_type == LIO_410NV) ? LIO_410NV_NAME :
+			LIO_210NV_NAME);
+		octeon_unmap_pci_barx(oct, 0);
+		octeon_unmap_pci_barx(oct, 1);
+		return 1;
+	}
+
+	oct->coproc_clock_rate = 1000000ULL * lio_cn6xxx_coprocessor_clock(oct);
+
+	lio_cn68xx_vendor_message_fix(oct);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
new file mode 100644
index 000000000000..d4e1c9fb0bf2
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.h
@@ -0,0 +1,33 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file  cn68xx_device.h
+ *  \brief Host Driver: Routines that perform CN68XX specific operations.
+ */
+
+#ifndef __CN68XX_DEVICE_H__
+#define  __CN68XX_DEVICE_H__
+
+int lio_setup_cn68xx_octeon_device(struct octeon_device *oct);
+int lio_is_210nv(struct octeon_device *oct);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
new file mode 100644
index 000000000000..38cddbd107b6
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_regs.h
@@ -0,0 +1,51 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file cn68xx_regs.h
+ *  \brief Host Driver: Register Address and Register Mask values for
+ *  Octeon CN68XX devices. The register map for CN66XX is the same
+ *  for most registers. This file has the other registers that are
+ *  68XX-specific.
+ */
+
+#ifndef __CN68XX_REGS_H__
+#define __CN68XX_REGS_H__
+#include "cn66xx_regs.h"
+
+/*###################### REQUEST QUEUE #########################*/
+
+#define    CN68XX_SLI_IQ_PORT0_PKIND             0x0800
+
+#define    CN68XX_SLI_IQ_PORT_PKIND(iq)           \
+	(CN68XX_SLI_IQ_PORT0_PKIND + ((iq) * CN6XXX_IQ_OFFSET))
+
+/*############################ OUTPUT QUEUE #########################*/
+
+/* Starting pipe number and number of pipes used by the SLI packet output. */
+#define    CN68XX_SLI_TX_PIPE                    0x1230
+
+/*######################## INTERRUPTS #########################*/
+
+/*------------------ Interrupt Masks ----------------*/
+#define    CN68XX_INTR_PIPE_ERR                  BIT_ULL(61)
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
new file mode 100644
index 000000000000..160f8077692c
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -0,0 +1,1216 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/ethtool.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+
+struct oct_mdio_cmd_context {
+	int octeon_id;
+	wait_queue_head_t wc;
+	int cond;
+};
+
+struct oct_mdio_cmd_resp {
+	u64 rh;
+	struct oct_mdio_cmd resp;
+	u64 status;
+};
+
+#define OCT_MDIO45_RESP_SIZE   (sizeof(struct oct_mdio_cmd_resp))
+
+/* Octeon's interface mode of operation */
+enum {
+	INTERFACE_MODE_DISABLED,
+	INTERFACE_MODE_RGMII,
+	INTERFACE_MODE_GMII,
+	INTERFACE_MODE_SPI,
+	INTERFACE_MODE_PCIE,
+	INTERFACE_MODE_XAUI,
+	INTERFACE_MODE_SGMII,
+	INTERFACE_MODE_PICMG,
+	INTERFACE_MODE_NPI,
+	INTERFACE_MODE_LOOP,
+	INTERFACE_MODE_SRIO,
+	INTERFACE_MODE_ILK,
+	INTERFACE_MODE_RXAUI,
+	INTERFACE_MODE_QSGMII,
+	INTERFACE_MODE_AGL,
+};
+
+#define ARRAY_LENGTH(a) (sizeof(a) / sizeof((a)[0]))
+#define OCT_ETHTOOL_REGDUMP_LEN  4096
+#define OCT_ETHTOOL_REGSVER  1
+
+static const char oct_iq_stats_strings[][ETH_GSTRING_LEN] = {
+	"Instr posted",
+	"Instr processed",
+	"Instr dropped",
+	"Bytes Sent",
+	"Sgentry_sent",
+	"Inst cntreg",
+	"Tx done",
+	"Tx Iq busy",
+	"Tx dropped",
+	"Tx bytes",
+};
+
+static const char oct_droq_stats_strings[][ETH_GSTRING_LEN] = {
+	"OQ Pkts Received",
+	"OQ Bytes Received",
+	"Dropped no dispatch",
+	"Dropped nomem",
+	"Dropped toomany",
+	"Stack RX cnt",
+	"Stack RX Bytes",
+	"RX dropped",
+};
+
+#define OCTNIC_NCMD_AUTONEG_ON  0x1
+#define OCTNIC_NCMD_PHY_ON      0x2
+
+static int lio_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct oct_link_info *linfo;
+
+	linfo = &lio->linfo;
+
+	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
+		ecmd->port = PORT_FIBRE;
+		ecmd->supported =
+			(SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE |
+			 SUPPORTED_Pause);
+		ecmd->advertising =
+			(ADVERTISED_10000baseT_Full | ADVERTISED_Pause);
+		ecmd->transceiver = XCVR_EXTERNAL;
+		ecmd->autoneg = AUTONEG_DISABLE;
+
+	} else {
+		dev_err(&oct->pci_dev->dev, "Unknown link interface reported\n");
+	}
+
+	if (linfo->link.s.status) {
+		ethtool_cmd_speed_set(ecmd, linfo->link.s.speed);
+		ecmd->duplex = linfo->link.s.duplex;
+	} else {
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
+	}
+
+	return 0;
+}
+
+static void
+lio_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
+{
+	struct lio *lio;
+	struct octeon_device *oct;
+
+	lio = GET_LIO(netdev);
+	oct = lio->oct_dev;
+
+	memset(drvinfo, 0, sizeof(struct ethtool_drvinfo));
+	strcpy(drvinfo->driver, "liquidio");
+	strcpy(drvinfo->version, LIQUIDIO_VERSION);
+	strncpy(drvinfo->fw_version, oct->fw_info.liquidio_firmware_version,
+		ETHTOOL_FWVERS_LEN);
+	strncpy(drvinfo->bus_info, pci_name(oct->pci_dev), 32);
+	drvinfo->regdump_len = OCT_ETHTOOL_REGDUMP_LEN;
+}
+
+static void
+lio_ethtool_get_channels(struct net_device *dev,
+			 struct ethtool_channels *channel)
+{
+	struct lio *lio = GET_LIO(dev);
+	struct octeon_device *oct = lio->oct_dev;
+	u32 max_rx = 0, max_tx = 0, tx_count = 0, rx_count = 0;
+
+	if (OCTEON_CN6XXX(oct)) {
+		struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+
+		max_rx = CFG_GET_OQ_MAX_Q(conf6x);
+		max_tx = CFG_GET_IQ_MAX_Q(conf6x);
+		rx_count = CFG_GET_NUM_RXQS_NIC_IF(conf6x, lio->ifidx);
+		tx_count = CFG_GET_NUM_TXQS_NIC_IF(conf6x, lio->ifidx);
+	}
+
+	channel->max_rx = max_rx;
+	channel->max_tx = max_tx;
+	channel->rx_count = rx_count;
+	channel->tx_count = tx_count;
+}
+
+static int lio_get_eeprom_len(struct net_device *netdev)
+{
+	u8 buf[128];
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+	struct octeon_board_info *board_info;
+	int len;
+
+	board_info = (struct octeon_board_info *)(&oct_dev->boardinfo);
+	len = sprintf(buf, "boardname:%s serialnum:%s maj:%lld min:%lld\n",
+		      board_info->name, board_info->serial_number,
+		      board_info->major, board_info->minor);
+
+	return len;
+}
+
+static int
+lio_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+	       u8 *bytes)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+	struct octeon_board_info *board_info;
+	int len;
+
+	if (eeprom->offset != 0)
+		return -EINVAL;
+
+	eeprom->magic = oct_dev->pci_dev->vendor;
+	board_info = (struct octeon_board_info *)(&oct_dev->boardinfo);
+	len =
+		sprintf((char *)bytes,
+			"boardname:%s serialnum:%s maj:%lld min:%lld\n",
+			board_info->name, board_info->serial_number,
+			board_info->major, board_info->minor);
+
+	return 0;
+}
+
+static int octnet_gpio_access(struct net_device *netdev, int addr, int val)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_GPIO_ACCESS;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = addr;
+	nctrl.ncmd.s.param3 = val;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	nparams.resp_order = OCTEON_RESP_ORDERED;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Callback for when mdio command response arrives
+ */
+static void octnet_mdio_resp_callback(struct octeon_device *oct,
+				      u32 status,
+				      void *buf)
+{
+	struct oct_mdio_cmd_resp *mdio_cmd_rsp;
+	struct oct_mdio_cmd_context *mdio_cmd_ctx;
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
+
+	mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr;
+	mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr;
+
+	oct = lio_get_device(mdio_cmd_ctx->octeon_id);
+	if (status) {
+		dev_err(&oct->pci_dev->dev, "MIDO instruction failed. Status: %llx\n",
+			CVM_CAST64(status));
+		ACCESS_ONCE(mdio_cmd_ctx->cond) = -1;
+	} else {
+		ACCESS_ONCE(mdio_cmd_ctx->cond) = 1;
+	}
+	wake_up_interruptible(&mdio_cmd_ctx->wc);
+}
+
+/* This routine provides PHY access routines for
+ * mdio  clause45 .
+ */
+static int
+octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
+{
+	struct octeon_device *oct_dev = lio->oct_dev;
+	struct octeon_soft_command *sc;
+	struct oct_mdio_cmd_resp *mdio_cmd_rsp;
+	struct oct_mdio_cmd_context *mdio_cmd_ctx;
+	struct oct_mdio_cmd *mdio_cmd;
+	int retval = 0;
+
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  sizeof(struct oct_mdio_cmd),
+					  sizeof(struct oct_mdio_cmd_resp),
+					  sizeof(struct oct_mdio_cmd_context));
+
+	if (!sc)
+		return -ENOMEM;
+
+	mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr;
+	mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr;
+	mdio_cmd = (struct oct_mdio_cmd *)sc->virtdptr;
+
+	ACCESS_ONCE(mdio_cmd_ctx->cond) = 0;
+	mdio_cmd_ctx->octeon_id = lio_get_device_id(oct_dev);
+	mdio_cmd->op = op;
+	mdio_cmd->mdio_addr = loc;
+	if (op)
+		mdio_cmd->value1 = *value;
+	mdio_cmd->value2 = lio->linfo.ifidx;
+	octeon_swap_8B_data((u64 *)mdio_cmd, sizeof(struct oct_mdio_cmd) / 8);
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_MDIO45,
+				    0, 0, 0);
+
+	sc->wait_time = 1000;
+	sc->callback = octnet_mdio_resp_callback;
+	sc->callback_arg = sc;
+
+	init_waitqueue_head(&mdio_cmd_ctx->wc);
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+
+	if (retval) {
+		dev_err(&oct_dev->pci_dev->dev,
+			"octnet_mdio45_access instruction failed status: %x\n",
+			retval);
+		retval =  -EBUSY;
+	} else {
+		/* Sleep on a wait queue till the cond flag indicates that the
+		 * response arrived
+		 */
+		sleep_cond(&mdio_cmd_ctx->wc, &mdio_cmd_ctx->cond);
+		retval = mdio_cmd_rsp->status;
+		if (retval) {
+			dev_err(&oct_dev->pci_dev->dev, "octnet mdio45 access failed\n");
+			retval = -EBUSY;
+		} else {
+			octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp),
+					    sizeof(struct oct_mdio_cmd) / 8);
+
+			if (ACCESS_ONCE(mdio_cmd_ctx->cond) == 1) {
+				if (!op)
+					*value = mdio_cmd_rsp->resp.value1;
+			} else {
+				retval = -EINVAL;
+			}
+		}
+	}
+
+	octeon_free_soft_command(oct_dev, sc);
+
+	return retval;
+}
+
+static int lio_set_phys_id(struct net_device *netdev,
+			   enum ethtool_phys_id_state state)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	int value, ret;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		if (oct->chip_id == OCTEON_CN66XX) {
+			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
+					   VITESSE_PHY_GPIO_DRIVEON);
+			return 2;
+
+		} else if (oct->chip_id == OCTEON_CN68XX) {
+			/* Save the current LED settings */
+			ret = octnet_mdio45_access(lio, 0,
+						   LIO68XX_LED_BEACON_ADDR,
+						   &lio->phy_beacon_val);
+			if (ret)
+				return ret;
+
+			ret = octnet_mdio45_access(lio, 0,
+						   LIO68XX_LED_CTRL_ADDR,
+						   &lio->led_ctrl_val);
+			if (ret)
+				return ret;
+
+			/* Configure Beacon values */
+			value = LIO68XX_LED_BEACON_CFGON;
+			ret =
+				octnet_mdio45_access(lio, 1,
+						     LIO68XX_LED_BEACON_ADDR,
+						     &value);
+			if (ret)
+				return ret;
+
+			value = LIO68XX_LED_CTRL_CFGON;
+			ret =
+				octnet_mdio45_access(lio, 1,
+						     LIO68XX_LED_CTRL_ADDR,
+						     &value);
+			if (ret)
+				return ret;
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	case ETHTOOL_ID_ON:
+		if (oct->chip_id == OCTEON_CN66XX) {
+			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
+					   VITESSE_PHY_GPIO_HIGH);
+
+		} else if (oct->chip_id == OCTEON_CN68XX) {
+			return -EINVAL;
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	case ETHTOOL_ID_OFF:
+		if (oct->chip_id == OCTEON_CN66XX)
+			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
+					   VITESSE_PHY_GPIO_LOW);
+		else if (oct->chip_id == OCTEON_CN68XX)
+			return -EINVAL;
+		else
+			return -EINVAL;
+
+		break;
+
+	case ETHTOOL_ID_INACTIVE:
+		if (oct->chip_id == OCTEON_CN66XX) {
+			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
+					   VITESSE_PHY_GPIO_DRIVEOFF);
+		} else if (oct->chip_id == OCTEON_CN68XX) {
+			/* Restore LED settings */
+			ret = octnet_mdio45_access(lio, 1,
+						   LIO68XX_LED_CTRL_ADDR,
+						   &lio->led_ctrl_val);
+			if (ret)
+				return ret;
+
+			octnet_mdio45_access(lio, 1, LIO68XX_LED_BEACON_ADDR,
+					     &lio->phy_beacon_val);
+			if (ret)
+				return ret;
+
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+lio_ethtool_get_ringparam(struct net_device *netdev,
+			  struct ethtool_ringparam *ering)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	u32 tx_max_pending = 0, rx_max_pending = 0, tx_pending = 0,
+	    rx_pending = 0;
+
+	if (OCTEON_CN6XXX(oct)) {
+		struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+
+		tx_max_pending = CN6XXX_MAX_IQ_DESCRIPTORS;
+		rx_max_pending = CN6XXX_MAX_OQ_DESCRIPTORS;
+		rx_pending = CFG_GET_NUM_RX_DESCS_NIC_IF(conf6x, lio->ifidx);
+		tx_pending = CFG_GET_NUM_TX_DESCS_NIC_IF(conf6x, lio->ifidx);
+	}
+
+	if (lio->mtu > OCTNET_DEFAULT_FRM_SIZE) {
+		ering->rx_pending = 0;
+		ering->rx_max_pending = 0;
+		ering->rx_mini_pending = 0;
+		ering->rx_jumbo_pending = rx_pending;
+		ering->rx_mini_max_pending = 0;
+		ering->rx_jumbo_max_pending = rx_max_pending;
+	} else {
+		ering->rx_pending = rx_pending;
+		ering->rx_max_pending = rx_max_pending;
+		ering->rx_mini_pending = 0;
+		ering->rx_jumbo_pending = 0;
+		ering->rx_mini_max_pending = 0;
+		ering->rx_jumbo_max_pending = 0;
+	}
+
+	ering->tx_pending = tx_pending;
+	ering->tx_max_pending = tx_max_pending;
+}
+
+static u32 lio_get_msglevel(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	return lio->msg_enable;
+}
+
+static void lio_set_msglevel(struct net_device *netdev, u32 msglvl)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if ((msglvl ^ lio->msg_enable) & NETIF_MSG_HW) {
+		if (msglvl & NETIF_MSG_HW)
+			liquidio_set_feature(netdev,
+					     OCTNET_CMD_VERBOSE_ENABLE);
+		else
+			liquidio_set_feature(netdev,
+					     OCTNET_CMD_VERBOSE_DISABLE);
+	}
+
+	lio->msg_enable = msglvl;
+}
+
+static void
+lio_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
+{
+	/* Notes: Not supporting any auto negotiation in these
+	 * drivers. Just report pause frame support.
+	 */
+	pause->tx_pause = 1;
+	pause->rx_pause = 1;    /* TODO: Need to support RX pause frame!!. */
+}
+
+static void
+lio_get_ethtool_stats(struct net_device *netdev,
+		      struct ethtool_stats *stats, u64 *data)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+	int i = 0, j;
+
+	for (j = 0; j < MAX_OCTEON_INSTR_QUEUES; j++) {
+		if (!(oct_dev->io_qmask.iq & (1UL << j)))
+			continue;
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.instr_posted);
+		data[i++] =
+			CVM_CAST64(
+				oct_dev->instr_queue[j]->stats.instr_processed);
+		data[i++] =
+			CVM_CAST64(
+				oct_dev->instr_queue[j]->stats.instr_dropped);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.bytes_sent);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.sgentry_sent);
+		data[i++] =
+			readl(oct_dev->instr_queue[j]->inst_cnt_reg);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_done);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_iq_busy);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_dropped);
+		data[i++] =
+			CVM_CAST64(oct_dev->instr_queue[j]->stats.tx_tot_bytes);
+	}
+
+	/* for (j = 0; j < oct_dev->num_oqs; j++){ */
+	for (j = 0; j < MAX_OCTEON_OUTPUT_QUEUES; j++) {
+		if (!(oct_dev->io_qmask.oq & (1UL << j)))
+			continue;
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.pkts_received);
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.bytes_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.dropped_nodispatch);
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_nomem);
+		data[i++] = CVM_CAST64(oct_dev->droq[j]->stats.dropped_toomany);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_pkts_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_bytes_received);
+		data[i++] =
+			CVM_CAST64(oct_dev->droq[j]->stats.rx_dropped);
+	}
+}
+
+static void lio_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+	int num_iq_stats, num_oq_stats, i, j;
+
+	num_iq_stats = ARRAY_SIZE(oct_iq_stats_strings);
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+		if (!(oct_dev->io_qmask.iq & (1UL << i)))
+			continue;
+		for (j = 0; j < num_iq_stats; j++) {
+			sprintf(data, "IQ%d %s", i, oct_iq_stats_strings[j]);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+
+	num_oq_stats = ARRAY_SIZE(oct_droq_stats_strings);
+	/* for (i = 0; i < oct_dev->num_oqs; i++) { */
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+		if (!(oct_dev->io_qmask.oq & (1UL << i)))
+			continue;
+		for (j = 0; j < num_oq_stats; j++) {
+			sprintf(data, "OQ%d %s", i, oct_droq_stats_strings[j]);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+}
+
+static int lio_get_sset_count(struct net_device *netdev, int sset)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct_dev = lio->oct_dev;
+
+	return (ARRAY_SIZE(oct_iq_stats_strings) * oct_dev->num_iqs) +
+	       (ARRAY_SIZE(oct_droq_stats_strings) * oct_dev->num_oqs);
+}
+
+static int lio_get_intr_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *intr_coal)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+	struct octeon_instr_queue *iq;
+	struct oct_intrmod_cfg *intrmod_cfg;
+
+	intrmod_cfg = &oct->intrmod;
+
+	switch (oct->chip_id) {
+	/* case OCTEON_CN73XX: Todo */
+	/*      break; */
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		if (!intrmod_cfg->intrmod_enable) {
+			intr_coal->rx_coalesce_usecs =
+				CFG_GET_OQ_INTR_TIME(cn6xxx->conf);
+			intr_coal->rx_max_coalesced_frames =
+				CFG_GET_OQ_INTR_PKT(cn6xxx->conf);
+		} else {
+			intr_coal->use_adaptive_rx_coalesce =
+				intrmod_cfg->intrmod_enable;
+			intr_coal->rate_sample_interval =
+				intrmod_cfg->intrmod_check_intrvl;
+			intr_coal->pkt_rate_high =
+				intrmod_cfg->intrmod_maxpkt_ratethr;
+			intr_coal->pkt_rate_low =
+				intrmod_cfg->intrmod_minpkt_ratethr;
+			intr_coal->rx_max_coalesced_frames_high =
+				intrmod_cfg->intrmod_maxcnt_trigger;
+			intr_coal->rx_coalesce_usecs_high =
+				intrmod_cfg->intrmod_maxtmr_trigger;
+			intr_coal->rx_coalesce_usecs_low =
+				intrmod_cfg->intrmod_mintmr_trigger;
+			intr_coal->rx_max_coalesced_frames_low =
+				intrmod_cfg->intrmod_mincnt_trigger;
+		}
+
+		iq = oct->instr_queue[lio->linfo.txpciq[0]];
+		intr_coal->tx_max_coalesced_frames = iq->fill_threshold;
+		break;
+
+	default:
+		netif_info(lio, drv, lio->netdev, "Unknown Chip !!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Callback function for intrmod */
+static void octnet_intrmod_callback(struct octeon_device *oct_dev,
+				    u32 status,
+				    void *ptr)
+{
+	struct oct_intrmod_cmd *cmd = ptr;
+	struct octeon_soft_command *sc = cmd->sc;
+
+	oct_dev = cmd->oct_dev;
+
+	if (status)
+		dev_err(&oct_dev->pci_dev->dev, "intrmod config failed. Status: %llx\n",
+			CVM_CAST64(status));
+	else
+		dev_info(&oct_dev->pci_dev->dev,
+			 "Rx-Adaptive Interrupt moderation enabled:%llx\n",
+			 oct_dev->intrmod.intrmod_enable);
+
+	octeon_free_soft_command(oct_dev, sc);
+}
+
+/*  Configure interrupt moderation parameters */
+static int octnet_set_intrmod_cfg(void *oct, struct oct_intrmod_cfg *intr_cfg)
+{
+	struct octeon_soft_command *sc;
+	struct oct_intrmod_cmd *cmd;
+	struct oct_intrmod_cfg *cfg;
+	int retval;
+	struct octeon_device *oct_dev = (struct octeon_device *)oct;
+
+	/* Alloc soft command */
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct_dev,
+					  sizeof(struct oct_intrmod_cfg),
+					  0,
+					  sizeof(struct oct_intrmod_cmd));
+
+	if (!sc)
+		return -ENOMEM;
+
+	cmd = (struct oct_intrmod_cmd *)sc->ctxptr;
+	cfg = (struct oct_intrmod_cfg *)sc->virtdptr;
+
+	memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg));
+	octeon_swap_8B_data((u64 *)cfg, (sizeof(struct oct_intrmod_cfg)) / 8);
+	cmd->sc = sc;
+	cmd->cfg = cfg;
+	cmd->oct_dev = oct_dev;
+
+	octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
+				    OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
+
+	sc->callback = octnet_intrmod_callback;
+	sc->callback_arg = cmd;
+	sc->wait_time = 1000;
+
+	retval = octeon_send_soft_command(oct_dev, sc);
+	if (retval) {
+		octeon_free_soft_command(oct_dev, sc);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Enable/Disable auto interrupt Moderation */
+static int oct_cfg_adaptive_intr(struct lio *lio, struct ethtool_coalesce
+				 *intr_coal, int adaptive)
+{
+	int ret = 0;
+	struct octeon_device *oct = lio->oct_dev;
+	struct oct_intrmod_cfg *intrmod_cfg;
+
+	intrmod_cfg = &oct->intrmod;
+
+	if (adaptive) {
+		if (intr_coal->rate_sample_interval)
+			intrmod_cfg->intrmod_check_intrvl =
+				intr_coal->rate_sample_interval;
+		else
+			intrmod_cfg->intrmod_check_intrvl =
+				LIO_INTRMOD_CHECK_INTERVAL;
+
+		if (intr_coal->pkt_rate_high)
+			intrmod_cfg->intrmod_maxpkt_ratethr =
+				intr_coal->pkt_rate_high;
+		else
+			intrmod_cfg->intrmod_maxpkt_ratethr =
+				LIO_INTRMOD_MAXPKT_RATETHR;
+
+		if (intr_coal->pkt_rate_low)
+			intrmod_cfg->intrmod_minpkt_ratethr =
+				intr_coal->pkt_rate_low;
+		else
+			intrmod_cfg->intrmod_minpkt_ratethr =
+				LIO_INTRMOD_MINPKT_RATETHR;
+
+		if (intr_coal->rx_max_coalesced_frames_high)
+			intrmod_cfg->intrmod_maxcnt_trigger =
+				intr_coal->rx_max_coalesced_frames_high;
+		else
+			intrmod_cfg->intrmod_maxcnt_trigger =
+				LIO_INTRMOD_MAXCNT_TRIGGER;
+
+		if (intr_coal->rx_coalesce_usecs_high)
+			intrmod_cfg->intrmod_maxtmr_trigger =
+				intr_coal->rx_coalesce_usecs_high;
+		else
+			intrmod_cfg->intrmod_maxtmr_trigger =
+				LIO_INTRMOD_MAXTMR_TRIGGER;
+
+		if (intr_coal->rx_coalesce_usecs_low)
+			intrmod_cfg->intrmod_mintmr_trigger =
+				intr_coal->rx_coalesce_usecs_low;
+		else
+			intrmod_cfg->intrmod_mintmr_trigger =
+				LIO_INTRMOD_MINTMR_TRIGGER;
+
+		if (intr_coal->rx_max_coalesced_frames_low)
+			intrmod_cfg->intrmod_mincnt_trigger =
+				intr_coal->rx_max_coalesced_frames_low;
+		else
+			intrmod_cfg->intrmod_mincnt_trigger =
+				LIO_INTRMOD_MINCNT_TRIGGER;
+	}
+
+	intrmod_cfg->intrmod_enable = adaptive;
+	ret = octnet_set_intrmod_cfg(oct, intrmod_cfg);
+
+	return ret;
+}
+
+static int
+oct_cfg_rx_intrcnt(struct lio *lio, struct ethtool_coalesce *intr_coal)
+{
+	int ret;
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+	u32 rx_max_coalesced_frames;
+
+	if (!intr_coal->rx_max_coalesced_frames)
+		rx_max_coalesced_frames = CN6XXX_OQ_INTR_PKT;
+	else
+		rx_max_coalesced_frames = intr_coal->rx_max_coalesced_frames;
+
+	/* Disable adaptive interrupt modulation */
+	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
+	if (ret)
+		return ret;
+
+	/* Config Cnt based interrupt values */
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_PKTS,
+			 rx_max_coalesced_frames);
+	CFG_SET_OQ_INTR_PKT(cn6xxx->conf, rx_max_coalesced_frames);
+	return 0;
+}
+
+static int oct_cfg_rx_intrtime(struct lio *lio, struct ethtool_coalesce
+			       *intr_coal)
+{
+	int ret;
+	struct octeon_device *oct = lio->oct_dev;
+	struct octeon_cn6xxx *cn6xxx = (struct octeon_cn6xxx *)oct->chip;
+	u32 time_threshold, rx_coalesce_usecs;
+
+	if (!intr_coal->rx_coalesce_usecs)
+		rx_coalesce_usecs = CN6XXX_OQ_INTR_TIME;
+	else
+		rx_coalesce_usecs = intr_coal->rx_coalesce_usecs;
+
+	/* Disable adaptive interrupt modulation */
+	ret = oct_cfg_adaptive_intr(lio, intr_coal, 0);
+	if (ret)
+		return ret;
+
+	/* Config Time based interrupt values */
+	time_threshold = lio_cn6xxx_get_oq_ticks(oct, rx_coalesce_usecs);
+	octeon_write_csr(oct, CN6XXX_SLI_OQ_INT_LEVEL_TIME, time_threshold);
+	CFG_SET_OQ_INTR_TIME(cn6xxx->conf, rx_coalesce_usecs);
+
+	return 0;
+}
+
+static int lio_set_intr_coalesce(struct net_device *netdev,
+				 struct ethtool_coalesce *intr_coal)
+{
+	struct lio *lio = GET_LIO(netdev);
+	int ret;
+	struct octeon_device *oct = lio->oct_dev;
+	u32 j, q_no;
+
+	if ((intr_coal->tx_max_coalesced_frames >= CN6XXX_DB_MIN) &&
+	    (intr_coal->tx_max_coalesced_frames <= CN6XXX_DB_MAX)) {
+		for (j = 0; j < lio->linfo.num_txpciq; j++) {
+			q_no = lio->linfo.txpciq[j];
+			oct->instr_queue[q_no]->fill_threshold =
+				intr_coal->tx_max_coalesced_frames;
+		}
+	} else {
+		dev_err(&oct->pci_dev->dev,
+			"LIQUIDIO: Invalid tx-frames:%d. Range is min:%d max:%d\n",
+			intr_coal->tx_max_coalesced_frames, CN6XXX_DB_MIN,
+			CN6XXX_DB_MAX);
+		return -EINVAL;
+	}
+
+	/* User requested adaptive-rx on */
+	if (intr_coal->use_adaptive_rx_coalesce) {
+		ret = oct_cfg_adaptive_intr(lio, intr_coal, 1);
+		if (ret)
+			goto ret_intrmod;
+	}
+
+	/* User requested adaptive-rx off and rx coalesce */
+	if ((intr_coal->rx_coalesce_usecs) &&
+	    (!intr_coal->use_adaptive_rx_coalesce)) {
+		ret = oct_cfg_rx_intrtime(lio, intr_coal);
+		if (ret)
+			goto ret_intrmod;
+	}
+
+	/* User requested adaptive-rx off and rx coalesce */
+	if ((intr_coal->rx_max_coalesced_frames) &&
+	    (!intr_coal->use_adaptive_rx_coalesce)) {
+		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+		if (ret)
+			goto ret_intrmod;
+	}
+
+	/* User requested adaptive-rx off, so use default coalesce params */
+	if ((!intr_coal->rx_max_coalesced_frames) &&
+	    (!intr_coal->use_adaptive_rx_coalesce) &&
+	    (!intr_coal->rx_coalesce_usecs)) {
+		dev_info(&oct->pci_dev->dev,
+			 "Turning off adaptive-rx interrupt moderation\n");
+		dev_info(&oct->pci_dev->dev,
+			 "Using RX Coalesce Default values rx_coalesce_usecs:%d rx_max_coalesced_frames:%d\n",
+			 CN6XXX_OQ_INTR_TIME, CN6XXX_OQ_INTR_PKT);
+		ret = oct_cfg_rx_intrtime(lio, intr_coal);
+		if (ret)
+			goto ret_intrmod;
+
+		ret = oct_cfg_rx_intrcnt(lio, intr_coal);
+		if (ret)
+			goto ret_intrmod;
+	}
+
+	return 0;
+ret_intrmod:
+	return ret;
+}
+
+static int lio_get_ts_info(struct net_device *netdev,
+			   struct ethtool_ts_info *info)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (lio->ptp_clock)
+		info->phc_index = ptp_clock_index(lio->ptp_clock);
+	else
+		info->phc_index = -1;
+
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
+
+	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			   (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
+			   (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
+
+	return 0;
+}
+
+static int lio_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct oct_link_info *linfo;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+	int ret = 0;
+
+	/* get the link info */
+	linfo = &lio->linfo;
+
+	if (ecmd->autoneg != AUTONEG_ENABLE && ecmd->autoneg != AUTONEG_DISABLE)
+		return -EINVAL;
+
+	if (ecmd->autoneg == AUTONEG_DISABLE && ((ecmd->speed != SPEED_100 &&
+						  ecmd->speed != SPEED_10) ||
+						 (ecmd->duplex != DUPLEX_HALF &&
+						  ecmd->duplex != DUPLEX_FULL)))
+		return -EINVAL;
+
+	/* Ethtool Support is not provided for XAUI and RXAUI Interfaces
+	 * as they operate at fixed Speed and Duplex settings
+	 */
+	if (linfo->link.s.interface == INTERFACE_MODE_XAUI ||
+	    linfo->link.s.interface == INTERFACE_MODE_RXAUI) {
+		dev_info(&oct->pci_dev->dev, "XAUI IFs settings cannot be modified.\n");
+		return -EINVAL;
+	}
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_SETTINGS;
+	nctrl.wait_time = 1000;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	/* Passing the parameters sent by ethtool like Speed, Autoneg & Duplex
+	 * to SE core application using ncmd.s.more & ncmd.s.param
+	 */
+	if (ecmd->autoneg == AUTONEG_ENABLE) {
+		/* Autoneg ON */
+		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON |
+				     OCTNIC_NCMD_AUTONEG_ON;
+		nctrl.ncmd.s.param2 = ecmd->advertising;
+	} else {
+		/* Autoneg OFF */
+		nctrl.ncmd.s.more = OCTNIC_NCMD_PHY_ON;
+
+		nctrl.ncmd.s.param3 = ecmd->duplex;
+
+		nctrl.ncmd.s.param2 = ecmd->speed;
+	}
+
+	nparams.resp_order = OCTEON_RESP_ORDERED;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Failed to set settings\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int lio_nway_reset(struct net_device *netdev)
+{
+	if (netif_running(netdev)) {
+		struct ethtool_cmd ecmd;
+
+		memset(&ecmd, 0, sizeof(struct ethtool_cmd));
+		ecmd.autoneg = 0;
+		ecmd.speed = 0;
+		ecmd.duplex = 0;
+		lio_set_settings(netdev, &ecmd);
+	}
+	return 0;
+}
+
+/* Return register dump len. */
+static int lio_get_regs_len(struct net_device *dev)
+{
+	return OCT_ETHTOOL_REGDUMP_LEN;
+}
+
+static int cn6xxx_read_csr_reg(char *s, struct octeon_device *oct)
+{
+	u32 reg;
+	int i, len = 0;
+
+	/* PCI  Window Registers */
+
+	len += sprintf(s + len, "\n\t Octeon CSR Registers\n\n");
+	reg = CN6XXX_WIN_WR_ADDR_LO;
+	len += sprintf(s + len, "\n[%02x] (WIN_WR_ADDR_LO): %08x\n",
+		       CN6XXX_WIN_WR_ADDR_LO, octeon_read_csr(oct, reg));
+	reg = CN6XXX_WIN_WR_ADDR_HI;
+	len += sprintf(s + len, "[%02x] (WIN_WR_ADDR_HI): %08x\n",
+		       CN6XXX_WIN_WR_ADDR_HI, octeon_read_csr(oct, reg));
+	reg = CN6XXX_WIN_RD_ADDR_LO;
+	len += sprintf(s + len, "[%02x] (WIN_RD_ADDR_LO): %08x\n",
+		       CN6XXX_WIN_RD_ADDR_LO, octeon_read_csr(oct, reg));
+	reg = CN6XXX_WIN_RD_ADDR_HI;
+	len += sprintf(s + len, "[%02x] (WIN_RD_ADDR_HI): %08x\n",
+		       CN6XXX_WIN_RD_ADDR_HI, octeon_read_csr(oct, reg));
+	reg = CN6XXX_WIN_WR_DATA_LO;
+	len += sprintf(s + len, "[%02x] (WIN_WR_DATA_LO): %08x\n",
+		       CN6XXX_WIN_WR_DATA_LO, octeon_read_csr(oct, reg));
+	reg = CN6XXX_WIN_WR_DATA_HI;
+	len += sprintf(s + len, "[%02x] (WIN_WR_DATA_HI): %08x\n",
+		       CN6XXX_WIN_WR_DATA_HI, octeon_read_csr(oct, reg));
+	len += sprintf(s + len, "[%02x] (WIN_WR_MASK_REG): %08x\n",
+		       CN6XXX_WIN_WR_MASK_REG,
+		       octeon_read_csr(oct, CN6XXX_WIN_WR_MASK_REG));
+
+	/* PCI  Interrupt Register */
+	len += sprintf(s + len, "\n[%x] (INT_ENABLE PORT 0): %08x\n",
+		       CN6XXX_SLI_INT_ENB64_PORT0, octeon_read_csr(oct,
+						CN6XXX_SLI_INT_ENB64_PORT0));
+	len += sprintf(s + len, "\n[%x] (INT_ENABLE PORT 1): %08x\n",
+		       CN6XXX_SLI_INT_ENB64_PORT1,
+		       octeon_read_csr(oct, CN6XXX_SLI_INT_ENB64_PORT1));
+	len += sprintf(s + len, "[%x] (INT_SUM): %08x\n", CN6XXX_SLI_INT_SUM64,
+		       octeon_read_csr(oct, CN6XXX_SLI_INT_SUM64));
+
+	/* PCI  Output queue registers */
+	for (i = 0; i < oct->num_oqs; i++) {
+		reg = CN6XXX_SLI_OQ_PKTS_SENT(i);
+		len += sprintf(s + len, "\n[%x] (PKTS_SENT_%d): %08x\n",
+			       reg, i, octeon_read_csr(oct, reg));
+		reg = CN6XXX_SLI_OQ_PKTS_CREDIT(i);
+		len += sprintf(s + len, "[%x] (PKT_CREDITS_%d): %08x\n",
+			       reg, i, octeon_read_csr(oct, reg));
+	}
+	reg = CN6XXX_SLI_OQ_INT_LEVEL_PKTS;
+	len += sprintf(s + len, "\n[%x] (PKTS_SENT_INT_LEVEL): %08x\n",
+		       reg, octeon_read_csr(oct, reg));
+	reg = CN6XXX_SLI_OQ_INT_LEVEL_TIME;
+	len += sprintf(s + len, "[%x] (PKTS_SENT_TIME): %08x\n",
+		       reg, octeon_read_csr(oct, reg));
+
+	/* PCI  Input queue registers */
+	for (i = 0; i <= 3; i++) {
+		u32 reg;
+
+		reg = CN6XXX_SLI_IQ_DOORBELL(i);
+		len += sprintf(s + len, "\n[%x] (INSTR_DOORBELL_%d): %08x\n",
+			       reg, i, octeon_read_csr(oct, reg));
+		reg = CN6XXX_SLI_IQ_INSTR_COUNT(i);
+		len += sprintf(s + len, "[%x] (INSTR_COUNT_%d): %08x\n",
+			       reg, i, octeon_read_csr(oct, reg));
+	}
+
+	/* PCI  DMA registers */
+
+	len += sprintf(s + len, "\n[%x] (DMA_CNT_0): %08x\n",
+		       CN6XXX_DMA_CNT(0),
+		       octeon_read_csr(oct, CN6XXX_DMA_CNT(0)));
+	reg = CN6XXX_DMA_PKT_INT_LEVEL(0);
+	len += sprintf(s + len, "[%x] (DMA_INT_LEV_0): %08x\n",
+		       CN6XXX_DMA_PKT_INT_LEVEL(0), octeon_read_csr(oct, reg));
+	reg = CN6XXX_DMA_TIME_INT_LEVEL(0);
+	len += sprintf(s + len, "[%x] (DMA_TIME_0): %08x\n",
+		       CN6XXX_DMA_TIME_INT_LEVEL(0),
+		       octeon_read_csr(oct, reg));
+
+	len += sprintf(s + len, "\n[%x] (DMA_CNT_1): %08x\n",
+		       CN6XXX_DMA_CNT(1),
+		       octeon_read_csr(oct, CN6XXX_DMA_CNT(1)));
+	reg = CN6XXX_DMA_PKT_INT_LEVEL(1);
+	len += sprintf(s + len, "[%x] (DMA_INT_LEV_1): %08x\n",
+		       CN6XXX_DMA_PKT_INT_LEVEL(1),
+		       octeon_read_csr(oct, reg));
+	reg = CN6XXX_DMA_PKT_INT_LEVEL(1);
+	len += sprintf(s + len, "[%x] (DMA_TIME_1): %08x\n",
+		       CN6XXX_DMA_TIME_INT_LEVEL(1),
+		       octeon_read_csr(oct, reg));
+
+	/* PCI  Index registers */
+
+	len += sprintf(s + len, "\n");
+
+	for (i = 0; i < 16; i++) {
+		reg = lio_pci_readq(oct, CN6XXX_BAR1_REG(i, oct->pcie_port));
+		len += sprintf(s + len, "[%llx] (BAR1_INDEX_%02d): %08x\n",
+			       CN6XXX_BAR1_REG(i, oct->pcie_port), i, reg);
+	}
+
+	return len;
+}
+
+static int cn6xxx_read_config_reg(char *s, struct octeon_device *oct)
+{
+	u32 val;
+	int i, len = 0;
+
+	/* PCI CONFIG Registers */
+
+	len += sprintf(s + len,
+		       "\n\t Octeon Config space Registers\n\n");
+
+	for (i = 0; i <= 13; i++) {
+		pci_read_config_dword(oct->pci_dev, (i * 4), &val);
+		len += sprintf(s + len, "[0x%x] (Config[%d]): 0x%08x\n",
+			       (i * 4), i, val);
+	}
+
+	for (i = 30; i <= 34; i++) {
+		pci_read_config_dword(oct->pci_dev, (i * 4), &val);
+		len += sprintf(s + len, "[0x%x] (Config[%d]): 0x%08x\n",
+			       (i * 4), i, val);
+	}
+
+	return len;
+}
+
+/*  Return register dump user app.  */
+static void lio_get_regs(struct net_device *dev,
+			 struct ethtool_regs *regs, void *regbuf)
+{
+	struct lio *lio = GET_LIO(dev);
+	int len = 0;
+	struct octeon_device *oct = lio->oct_dev;
+
+	memset(regbuf, 0, OCT_ETHTOOL_REGDUMP_LEN);
+	regs->version = OCT_ETHTOOL_REGSVER;
+
+	switch (oct->chip_id) {
+	/* case OCTEON_CN73XX: Todo */
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		len += cn6xxx_read_csr_reg(regbuf + len, oct);
+		len += cn6xxx_read_config_reg(regbuf + len, oct);
+		break;
+	default:
+		dev_err(&oct->pci_dev->dev, "%s Unknown chipid: %d\n",
+			__func__, oct->chip_id);
+	}
+}
+
+static const struct ethtool_ops lio_ethtool_ops = {
+	.get_settings		= lio_get_settings,
+	.get_link		= ethtool_op_get_link,
+	.get_drvinfo		= lio_get_drvinfo,
+	.get_ringparam		= lio_ethtool_get_ringparam,
+	.get_channels		= lio_ethtool_get_channels,
+	.set_phys_id		= lio_set_phys_id,
+	.get_eeprom_len		= lio_get_eeprom_len,
+	.get_eeprom		= lio_get_eeprom,
+	.get_strings		= lio_get_strings,
+	.get_ethtool_stats	= lio_get_ethtool_stats,
+	.get_pauseparam		= lio_get_pauseparam,
+	.get_regs_len		= lio_get_regs_len,
+	.get_regs		= lio_get_regs,
+	.get_msglevel		= lio_get_msglevel,
+	.set_msglevel		= lio_set_msglevel,
+	.get_sset_count		= lio_get_sset_count,
+	.nway_reset		= lio_nway_reset,
+	.set_settings		= lio_set_settings,
+	.get_coalesce		= lio_get_intr_coalesce,
+	.set_coalesce		= lio_set_intr_coalesce,
+	.get_ts_info		= lio_get_ts_info,
+};
+
+void liquidio_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &lio_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
new file mode 100644
index 000000000000..0660deecc2c9
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -0,0 +1,3668 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <linux/net_tstamp.h>
+#include <linux/if_vlan.h>
+#include <linux/firmware.h>
+#include <linux/ethtool.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+
+MODULE_AUTHOR("Cavium Networks, <support@cavium.com>");
+MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(LIQUIDIO_VERSION);
+MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210SV_NAME LIO_FW_NAME_SUFFIX);
+MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210NV_NAME LIO_FW_NAME_SUFFIX);
+MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_410NV_NAME LIO_FW_NAME_SUFFIX);
+
+static int ddr_timeout = 10000;
+module_param(ddr_timeout, int, 0644);
+MODULE_PARM_DESC(ddr_timeout,
+		 "Number of milliseconds to wait for DDR initialization. 0 waits for ddr_timeout to be set to non-zero value before starting to check");
+
+static u32 console_bitmask;
+module_param(console_bitmask, int, 0644);
+MODULE_PARM_DESC(console_bitmask,
+		 "Bitmask indicating which consoles have debug output redirected to syslog.");
+
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+
+static int debug = -1;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
+
+static char fw_type[LIO_MAX_FW_TYPE_LEN];
+module_param_string(fw_type, fw_type, sizeof(fw_type), 0000);
+MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\"");
+
+static int conf_type;
+module_param(conf_type, int, 0);
+MODULE_PARM_DESC(conf_type, "select octeon configuration 0 default 1 ovs");
+
+/* Bit mask values for lio->ifstate */
+#define   LIO_IFSTATE_DROQ_OPS             0x01
+#define   LIO_IFSTATE_REGISTERED           0x02
+#define   LIO_IFSTATE_RUNNING              0x04
+#define   LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
+
+/* Polling interval for determining when NIC application is alive */
+#define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100
+
+/* runtime link query interval */
+#define LIQUIDIO_LINK_QUERY_INTERVAL_MS         1000
+
+struct liquidio_if_cfg_context {
+	int octeon_id;
+
+	wait_queue_head_t wc;
+
+	int cond;
+};
+
+struct liquidio_if_cfg_resp {
+	u64 rh;
+	struct liquidio_if_cfg_info cfg_info;
+	u64 status;
+};
+
+struct oct_link_status_resp {
+	u64 rh;
+	struct oct_link_info link_info;
+	u64 status;
+};
+
+struct oct_timestamp_resp {
+	u64 rh;
+	u64 timestamp;
+	u64 status;
+};
+
+#define OCT_TIMESTAMP_RESP_SIZE (sizeof(struct oct_timestamp_resp))
+
+union tx_info {
+	u64 u64;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u16 gso_size;
+		u16 gso_segs;
+		u32 reserved;
+#else
+		u32 reserved;
+		u16 gso_segs;
+		u16 gso_size;
+#endif
+	} s;
+};
+
+/** Octeon device properties to be used by the NIC module.
+ * Each octeon device in the system will be represented
+ * by this structure in the NIC module.
+ */
+
+#define OCTNIC_MAX_SG  (MAX_SKB_FRAGS)
+
+#define OCTNIC_GSO_MAX_HEADER_SIZE 128
+#define OCTNIC_GSO_MAX_SIZE (GSO_MAX_SIZE - OCTNIC_GSO_MAX_HEADER_SIZE)
+
+/** Structure of a node in list of gather components maintained by
+ * NIC driver for each network device.
+ */
+struct octnic_gather {
+	/** List manipulation. Next and prev pointers. */
+	struct list_head list;
+
+	/** Size of the gather component at sg in bytes. */
+	int sg_size;
+
+	/** Number of bytes that sg was adjusted to make it 8B-aligned. */
+	int adjust;
+
+	/** Gather component that can accommodate max sized fragment list
+	 *  received from the IP layer.
+	 */
+	struct octeon_sg_entry *sg;
+};
+
+/** This structure is used by NIC driver to store information required
+ * to free the sk_buff when the packet has been fetched by Octeon.
+ * Bytes offset below assume worst-case of a 64-bit system.
+ */
+struct octnet_buf_free_info {
+	/** Bytes 1-8.  Pointer to network device private structure. */
+	struct lio *lio;
+
+	/** Bytes 9-16.  Pointer to sk_buff. */
+	struct sk_buff *skb;
+
+	/** Bytes 17-24.  Pointer to gather list. */
+	struct octnic_gather *g;
+
+	/** Bytes 25-32. Physical address of skb->data or gather list. */
+	u64 dptr;
+
+	/** Bytes 33-47. Piggybacked soft command, if any */
+	struct octeon_soft_command *sc;
+};
+
+struct handshake {
+	struct completion init;
+	struct completion started;
+	struct pci_dev *pci_dev;
+	int init_ok;
+	int started_ok;
+};
+
+struct octeon_device_priv {
+	/** Tasklet structures for this device. */
+	struct tasklet_struct droq_tasklet;
+	unsigned long napi_mask;
+};
+
+static int octeon_device_init(struct octeon_device *);
+static void liquidio_remove(struct pci_dev *pdev);
+static int liquidio_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent);
+
+static struct handshake handshake[MAX_OCTEON_DEVICES];
+static struct completion first_stage;
+
+static void octeon_droq_bh(unsigned long pdev)
+{
+	int q_no;
+	int reschedule = 0;
+	struct octeon_device *oct = (struct octeon_device *)pdev;
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)oct->priv;
+
+	/* for (q_no = 0; q_no < oct->num_oqs; q_no++) { */
+	for (q_no = 0; q_no < MAX_OCTEON_OUTPUT_QUEUES; q_no++) {
+		if (!(oct->io_qmask.oq & (1UL << q_no)))
+			continue;
+		reschedule |= octeon_droq_process_packets(oct, oct->droq[q_no],
+							  MAX_PACKET_BUDGET);
+	}
+
+	if (reschedule)
+		tasklet_schedule(&oct_priv->droq_tasklet);
+}
+
+static int lio_wait_for_oq_pkts(struct octeon_device *oct)
+{
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)oct->priv;
+	int retry = 100, pkt_cnt = 0, pending_pkts = 0;
+	int i;
+
+	do {
+		pending_pkts = 0;
+
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+			if (!(oct->io_qmask.oq & (1UL << i)))
+				continue;
+			pkt_cnt += octeon_droq_check_hw_for_pkts(oct,
+								 oct->droq[i]);
+		}
+		if (pkt_cnt > 0) {
+			pending_pkts += pkt_cnt;
+			tasklet_schedule(&oct_priv->droq_tasklet);
+		}
+		pkt_cnt = 0;
+		schedule_timeout_uninterruptible(1);
+
+	} while (retry-- && pending_pkts);
+
+	return pkt_cnt;
+}
+
+void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl,
+					unsigned int bytes_compl)
+{
+	struct netdev_queue *netdev_queue = txq;
+
+	netdev_tx_completed_queue(netdev_queue, pkts_compl, bytes_compl);
+}
+
+void octeon_update_tx_completion_counters(void *buf, int reqtype,
+					  unsigned int *pkts_compl,
+					  unsigned int *bytes_compl)
+{
+	struct octnet_buf_free_info *finfo;
+	struct sk_buff *skb = NULL;
+	struct octeon_soft_command *sc;
+
+	switch (reqtype) {
+	case REQTYPE_NORESP_NET:
+	case REQTYPE_NORESP_NET_SG:
+		finfo = buf;
+		skb = finfo->skb;
+		break;
+
+	case REQTYPE_RESP_NET_SG:
+	case REQTYPE_RESP_NET:
+		sc = buf;
+		skb = sc->callback_arg;
+		break;
+
+	default:
+		return;
+	}
+
+	(*pkts_compl)++;
+	*bytes_compl += skb->len;
+}
+
+void octeon_report_sent_bytes_to_bql(void *buf, int reqtype)
+{
+	struct octnet_buf_free_info *finfo;
+	struct sk_buff *skb;
+	struct octeon_soft_command *sc;
+	struct netdev_queue *txq;
+
+	switch (reqtype) {
+	case REQTYPE_NORESP_NET:
+	case REQTYPE_NORESP_NET_SG:
+		finfo = buf;
+		skb = finfo->skb;
+		break;
+
+	case REQTYPE_RESP_NET_SG:
+	case REQTYPE_RESP_NET:
+		sc = buf;
+		skb = sc->callback_arg;
+		break;
+
+	default:
+		return;
+	}
+
+	txq = netdev_get_tx_queue(skb->dev, skb_get_queue_mapping(skb));
+	netdev_tx_sent_queue(txq, skb->len);
+}
+
+int octeon_console_debug_enabled(u32 console)
+{
+	return (console_bitmask >> (console)) & 0x1;
+}
+
+/**
+ * \brief Forces all IO queues off on a given device
+ * @param oct Pointer to Octeon device
+ */
+static void force_io_queues_off(struct octeon_device *oct)
+{
+	if ((oct->chip_id == OCTEON_CN66XX) ||
+	    (oct->chip_id == OCTEON_CN68XX)) {
+		/* Reset the Enable bits for Input Queues. */
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, 0);
+
+		/* Reset the Enable bits for Output Queues. */
+		octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_ENB, 0);
+	}
+}
+
+/**
+ * \brief wait for all pending requests to complete
+ * @param oct Pointer to Octeon device
+ *
+ * Called during shutdown sequence
+ */
+static int wait_for_pending_requests(struct octeon_device *oct)
+{
+	int i, pcount = 0;
+
+	for (i = 0; i < 100; i++) {
+		pcount =
+			atomic_read(&oct->response_list
+				[OCTEON_ORDERED_SC_LIST].pending_req_count);
+		if (pcount)
+			schedule_timeout_uninterruptible(HZ / 10);
+		 else
+			break;
+	}
+
+	if (pcount)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * \brief Cause device to go quiet so it can be safely removed/reset/etc
+ * @param oct Pointer to Octeon device
+ */
+static inline void pcierror_quiesce_device(struct octeon_device *oct)
+{
+	int i;
+
+	/* Disable the input and output queues now. No more packets will
+	 * arrive from Octeon, but we should wait for all packet processing
+	 * to finish.
+	 */
+	force_io_queues_off(oct);
+
+	/* To allow for in-flight requests */
+	schedule_timeout_uninterruptible(100);
+
+	if (wait_for_pending_requests(oct))
+		dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
+	/* Force all requests waiting to be fetched by OCTEON to complete. */
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+		struct octeon_instr_queue *iq;
+
+		if (!(oct->io_qmask.iq & (1UL << i)))
+			continue;
+		iq = oct->instr_queue[i];
+
+		if (atomic_read(&iq->instr_pending)) {
+			spin_lock_bh(&iq->lock);
+			iq->fill_cnt = 0;
+			iq->octeon_read_index = iq->host_write_index;
+			iq->stats.instr_processed +=
+				atomic_read(&iq->instr_pending);
+			lio_process_iq_request_list(oct, iq);
+			spin_unlock_bh(&iq->lock);
+		}
+	}
+
+	/* Force all pending ordered list requests to time out. */
+	lio_process_ordered_list(oct, 1);
+
+	/* We do not need to wait for output queue packets to be processed. */
+}
+
+/**
+ * \brief Cleanup PCI AER uncorrectable error status
+ * @param dev Pointer to PCI device
+ */
+static void cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
+{
+	int pos = 0x100;
+	u32 status, mask;
+
+	pr_info("%s :\n", __func__);
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
+	if (dev->error_state == pci_channel_io_normal)
+		status &= ~mask;        /* Clear corresponding nonfatal bits */
+	else
+		status &= mask;         /* Clear corresponding fatal bits */
+	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+}
+
+/**
+ * \brief Stop all PCI IO to a given device
+ * @param dev Pointer to Octeon device
+ */
+static void stop_pci_io(struct octeon_device *oct)
+{
+	/* No more instructions will be forwarded. */
+	atomic_set(&oct->status, OCT_DEV_IN_RESET);
+
+	pci_disable_device(oct->pci_dev);
+
+	/* Disable interrupts  */
+	oct->fn_list.disable_interrupt(oct->chip);
+
+	pcierror_quiesce_device(oct);
+
+	/* Release the interrupt line */
+	free_irq(oct->pci_dev->irq, oct);
+
+	if (oct->flags & LIO_FLAG_MSI_ENABLED)
+		pci_disable_msi(oct->pci_dev);
+
+	dev_dbg(&oct->pci_dev->dev, "Device state is now %s\n",
+		lio_get_state_string(&oct->status));
+
+	/* cn63xx_cleanup_aer_uncorrect_error_status(oct->pci_dev); */
+	/* making it a common function for all OCTEON models */
+	cleanup_aer_uncorrect_error_status(oct->pci_dev);
+}
+
+/**
+ * \brief called when PCI error is detected
+ * @param pdev Pointer to PCI device
+ * @param state The current pci connection state
+ *
+ * This function is called after a PCI bus error affecting
+ * this device has been detected.
+ */
+static pci_ers_result_t liquidio_pcie_error_detected(struct pci_dev *pdev,
+						     pci_channel_state_t state)
+{
+	struct octeon_device *oct = pci_get_drvdata(pdev);
+
+	/* Non-correctable Non-fatal errors */
+	if (state == pci_channel_io_normal) {
+		dev_err(&oct->pci_dev->dev, "Non-correctable non-fatal error reported:\n");
+		cleanup_aer_uncorrect_error_status(oct->pci_dev);
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	}
+
+	/* Non-correctable Fatal errors */
+	dev_err(&oct->pci_dev->dev, "Non-correctable FATAL reported by PCI AER driver\n");
+	stop_pci_io(oct);
+
+	/* Always return a DISCONNECT. There is no support for recovery but only
+	 * for a clean shutdown.
+	 */
+	return PCI_ERS_RESULT_DISCONNECT;
+}
+
+/**
+ * \brief mmio handler
+ * @param pdev Pointer to PCI device
+ */
+static pci_ers_result_t liquidio_pcie_mmio_enabled(struct pci_dev *pdev)
+{
+	/* We should never hit this since we never ask for a reset for a Fatal
+	 * Error. We always return DISCONNECT in io_error above.
+	 * But play safe and return RECOVERED for now.
+	 */
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * \brief called after the pci bus has been reset.
+ * @param pdev Pointer to PCI device
+ *
+ * Restart the card from scratch, as if from a cold-boot. Implementation
+ * resembles the first-half of the octeon_resume routine.
+ */
+static pci_ers_result_t liquidio_pcie_slot_reset(struct pci_dev *pdev)
+{
+	/* We should never hit this since we never ask for a reset for a Fatal
+	 * Error. We always return DISCONNECT in io_error above.
+	 * But play safe and return RECOVERED for now.
+	 */
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * \brief called when traffic can start flowing again.
+ * @param pdev Pointer to PCI device
+ *
+ * This callback is called when the error recovery driver tells us that
+ * its OK to resume normal operation. Implementation resembles the
+ * second-half of the octeon_resume routine.
+ */
+static void liquidio_pcie_resume(struct pci_dev *pdev)
+{
+	/* Nothing to be done here. */
+}
+
+#ifdef CONFIG_PM
+/**
+ * \brief called when suspending
+ * @param pdev Pointer to PCI device
+ * @param state state to suspend to
+ */
+static int liquidio_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	return 0;
+}
+
+/**
+ * \brief called when resuming
+ * @param pdev Pointer to PCI device
+ */
+static int liquidio_resume(struct pci_dev *pdev)
+{
+	return 0;
+}
+#endif
+
+/* For PCI-E Advanced Error Recovery (AER) Interface */
+static struct pci_error_handlers liquidio_err_handler = {
+	.error_detected = liquidio_pcie_error_detected,
+	.mmio_enabled	= liquidio_pcie_mmio_enabled,
+	.slot_reset	= liquidio_pcie_slot_reset,
+	.resume		= liquidio_pcie_resume,
+};
+
+static const struct pci_device_id liquidio_pci_tbl[] = {
+	{       /* 68xx */
+		PCI_VENDOR_ID_CAVIUM, 0x91, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0
+	},
+	{       /* 66xx */
+		PCI_VENDOR_ID_CAVIUM, 0x92, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0
+	},
+	{
+		0, 0, 0, 0, 0, 0, 0
+	}
+};
+MODULE_DEVICE_TABLE(pci, liquidio_pci_tbl);
+
+static struct pci_driver liquidio_pci_driver = {
+	.name		= "LiquidIO",
+	.id_table	= liquidio_pci_tbl,
+	.probe		= liquidio_probe,
+	.remove		= liquidio_remove,
+	.err_handler	= &liquidio_err_handler,    /* For AER */
+
+#ifdef CONFIG_PM
+	.suspend	= liquidio_suspend,
+	.resume		= liquidio_resume,
+#endif
+
+};
+
+/**
+ * \brief register PCI driver
+ */
+static int liquidio_init_pci(void)
+{
+	return pci_register_driver(&liquidio_pci_driver);
+}
+
+/**
+ * \brief unregister PCI driver
+ */
+static void liquidio_deinit_pci(void)
+{
+	pci_unregister_driver(&liquidio_pci_driver);
+}
+
+/**
+ * \brief check interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to check
+ */
+static inline int ifstate_check(struct lio *lio, int state_flag)
+{
+	return atomic_read(&lio->ifstate) & state_flag;
+}
+
+/**
+ * \brief set interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to set
+ */
+static inline void ifstate_set(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) | state_flag));
+}
+
+/**
+ * \brief clear interface state
+ * @param lio per-network private data
+ * @param state_flag flag state to clear
+ */
+static inline void ifstate_reset(struct lio *lio, int state_flag)
+{
+	atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag)));
+}
+
+/**
+ * \brief Stop Tx queues
+ * @param netdev network device
+ */
+static inline void txqs_stop(struct net_device *netdev)
+{
+	if (netif_is_multiqueue(netdev)) {
+		int i;
+
+		for (i = 0; i < netdev->num_tx_queues; i++)
+			netif_stop_subqueue(netdev, i);
+	} else {
+		netif_stop_queue(netdev);
+	}
+}
+
+/**
+ * \brief Start Tx queues
+ * @param netdev network device
+ */
+static inline void txqs_start(struct net_device *netdev)
+{
+	if (netif_is_multiqueue(netdev)) {
+		int i;
+
+		for (i = 0; i < netdev->num_tx_queues; i++)
+			netif_start_subqueue(netdev, i);
+	} else {
+		netif_start_queue(netdev);
+	}
+}
+
+/**
+ * \brief Wake Tx queues
+ * @param netdev network device
+ */
+static inline void txqs_wake(struct net_device *netdev)
+{
+	if (netif_is_multiqueue(netdev)) {
+		int i;
+
+		for (i = 0; i < netdev->num_tx_queues; i++)
+			netif_wake_subqueue(netdev, i);
+	} else {
+		netif_wake_queue(netdev);
+	}
+}
+
+/**
+ * \brief Stop Tx queue
+ * @param netdev network device
+ */
+static void stop_txq(struct net_device *netdev)
+{
+	txqs_stop(netdev);
+}
+
+/**
+ * \brief Start Tx queue
+ * @param netdev network device
+ */
+static void start_txq(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if (lio->linfo.link.s.status) {
+		txqs_start(netdev);
+		return;
+	}
+}
+
+/**
+ * \brief Wake a queue
+ * @param netdev network device
+ * @param q which queue to wake
+ */
+static inline void wake_q(struct net_device *netdev, int q)
+{
+	if (netif_is_multiqueue(netdev))
+		netif_wake_subqueue(netdev, q);
+	else
+		netif_wake_queue(netdev);
+}
+
+/**
+ * \brief Stop a queue
+ * @param netdev network device
+ * @param q which queue to stop
+ */
+static inline void stop_q(struct net_device *netdev, int q)
+{
+	if (netif_is_multiqueue(netdev))
+		netif_stop_subqueue(netdev, q);
+	else
+		netif_stop_queue(netdev);
+}
+
+/**
+ * \brief Check Tx queue status, and take appropriate action
+ * @param lio per-network private data
+ * @returns 0 if full, number of queues woken up otherwise
+ */
+static inline int check_txq_status(struct lio *lio)
+{
+	int ret_val = 0;
+
+	if (netif_is_multiqueue(lio->netdev)) {
+		int numqs = lio->netdev->num_tx_queues;
+		int q, iq = 0;
+
+		/* check each sub-queue state */
+		for (q = 0; q < numqs; q++) {
+			iq = lio->linfo.txpciq[q & (lio->linfo.num_txpciq - 1)];
+			if (octnet_iq_is_full(lio->oct_dev, iq))
+				continue;
+			wake_q(lio->netdev, q);
+			ret_val++;
+		}
+	} else {
+		if (octnet_iq_is_full(lio->oct_dev, lio->txq))
+			return 0;
+		wake_q(lio->netdev, lio->txq);
+		ret_val = 1;
+	}
+	return ret_val;
+}
+
+/**
+ * Remove the node at the head of the list. The list would be empty at
+ * the end of this call if there are no more nodes in the list.
+ */
+static inline struct list_head *list_delete_head(struct list_head *root)
+{
+	struct list_head *node;
+
+	if ((root->prev == root) && (root->next == root))
+		node = NULL;
+	else
+		node = root->next;
+
+	if (node)
+		list_del(node);
+
+	return node;
+}
+
+/**
+ * \brief Delete gather list
+ * @param lio per-network private data
+ */
+static void delete_glist(struct lio *lio)
+{
+	struct octnic_gather *g;
+
+	do {
+		g = (struct octnic_gather *)
+		    list_delete_head(&lio->glist);
+		if (g) {
+			if (g->sg)
+				kfree((void *)((unsigned long)g->sg -
+						g->adjust));
+			kfree(g);
+		}
+	} while (g);
+}
+
+/**
+ * \brief Setup gather list
+ * @param lio per-network private data
+ */
+static int setup_glist(struct lio *lio)
+{
+	int i;
+	struct octnic_gather *g;
+
+	INIT_LIST_HEAD(&lio->glist);
+
+	for (i = 0; i < lio->tx_qsize; i++) {
+		g = kmalloc(sizeof(*g), GFP_KERNEL);
+		if (!g)
+			break;
+		memset(g, 0, sizeof(struct octnic_gather));
+
+		g->sg_size =
+			((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE);
+
+		g->sg = kmalloc(g->sg_size + 8, GFP_KERNEL);
+		if (!g->sg) {
+			kfree(g);
+			break;
+		}
+
+		/* The gather component should be aligned on 64-bit boundary */
+		if (((unsigned long)g->sg) & 7) {
+			g->adjust = 8 - (((unsigned long)g->sg) & 7);
+			g->sg = (struct octeon_sg_entry *)
+				((unsigned long)g->sg + g->adjust);
+		}
+		list_add_tail(&g->list, &lio->glist);
+	}
+
+	if (i == lio->tx_qsize)
+		return 0;
+
+	delete_glist(lio);
+	return 1;
+}
+
+/**
+ * \brief Print link information
+ * @param netdev network device
+ */
+static void print_link_info(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) {
+		struct oct_link_info *linfo = &lio->linfo;
+
+		if (linfo->link.s.status) {
+			netif_info(lio, link, lio->netdev, "%d Mbps %s Duplex UP\n",
+				   linfo->link.s.speed,
+				   (linfo->link.s.duplex) ? "Full" : "Half");
+		} else {
+			netif_info(lio, link, lio->netdev, "Link Down\n");
+		}
+	}
+}
+
+/**
+ * \brief Update link status
+ * @param netdev network device
+ * @param ls link status structure
+ *
+ * Called on receipt of a link status response from the core application to
+ * update each interface's link status.
+ */
+static inline void update_link_status(struct net_device *netdev,
+				      union oct_link_status *ls)
+{
+	struct lio *lio = GET_LIO(netdev);
+
+	if ((lio->intf_open) && (lio->linfo.link.u64 != ls->u64)) {
+		lio->linfo.link.u64 = ls->u64;
+
+		print_link_info(netdev);
+
+		if (lio->linfo.link.s.status) {
+			netif_carrier_on(netdev);
+			/* start_txq(netdev); */
+			txqs_wake(netdev);
+		} else {
+			netif_carrier_off(netdev);
+			stop_txq(netdev);
+		}
+	}
+}
+
+/**
+ * \brief Droq packet processor sceduler
+ * @param oct octeon device
+ */
+static
+void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct)
+{
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)oct->priv;
+	u64 oq_no;
+	struct octeon_droq *droq;
+
+	if (oct->int_status & OCT_DEV_INTR_PKT_DATA) {
+		for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES; oq_no++) {
+			if (!(oct->droq_intr & (1 << oq_no)))
+				continue;
+
+			droq = oct->droq[oq_no];
+
+			if (droq->ops.poll_mode) {
+				droq->ops.napi_fn(droq);
+				oct_priv->napi_mask |= (1 << oq_no);
+			} else {
+				tasklet_schedule(&oct_priv->droq_tasklet);
+			}
+		}
+	}
+}
+
+/**
+ * \brief Interrupt handler for octeon
+ * @param irq unused
+ * @param dev octeon device
+ */
+static
+irqreturn_t liquidio_intr_handler(int irq __attribute__((unused)), void *dev)
+{
+	struct octeon_device *oct = (struct octeon_device *)dev;
+	irqreturn_t ret;
+
+	/* Disable our interrupts for the duration of ISR */
+	oct->fn_list.disable_interrupt(oct->chip);
+
+	ret = oct->fn_list.process_interrupt_regs(oct);
+
+	if (ret == IRQ_HANDLED)
+		liquidio_schedule_droq_pkt_handlers(oct);
+
+	/* Re-enable our interrupts  */
+	if (!(atomic_read(&oct->status) == OCT_DEV_IN_RESET))
+		oct->fn_list.enable_interrupt(oct->chip);
+
+	return ret;
+}
+
+/**
+ * \brief Setup interrupt for octeon device
+ * @param oct octeon device
+ *
+ *  Enable interrupt in Octeon device as given in the PCI interrupt mask.
+ */
+static int octeon_setup_interrupt(struct octeon_device *oct)
+{
+	int irqret, err;
+
+	err = pci_enable_msi(oct->pci_dev);
+	if (err)
+		dev_warn(&oct->pci_dev->dev, "Reverting to legacy interrupts. Error: %d\n",
+			 err);
+	else
+		oct->flags |= LIO_FLAG_MSI_ENABLED;
+
+	irqret = request_irq(oct->pci_dev->irq, liquidio_intr_handler,
+			     IRQF_SHARED, "octeon", oct);
+	if (irqret) {
+		if (oct->flags & LIO_FLAG_MSI_ENABLED)
+			pci_disable_msi(oct->pci_dev);
+		dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n",
+			irqret);
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * \brief PCI probe handler
+ * @param pdev PCI device structure
+ * @param ent unused
+ */
+static int liquidio_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct octeon_device *oct_dev = NULL;
+	struct handshake *hs;
+
+	oct_dev = octeon_allocate_device(pdev->device,
+					 sizeof(struct octeon_device_priv));
+	if (!oct_dev) {
+		dev_err(&pdev->dev, "Unable to allocate device\n");
+		return -ENOMEM;
+	}
+
+	dev_info(&pdev->dev, "Initializing device %x:%x.\n",
+		 (u32)pdev->vendor, (u32)pdev->device);
+
+	/* Assign octeon_device for this device to the private data area. */
+	pci_set_drvdata(pdev, oct_dev);
+
+	/* set linux specific device pointer */
+	oct_dev->pci_dev = (void *)pdev;
+
+	hs = &handshake[oct_dev->octeon_id];
+	init_completion(&hs->init);
+	init_completion(&hs->started);
+	hs->pci_dev = pdev;
+
+	if (oct_dev->octeon_id == 0)
+		/* first LiquidIO NIC is detected */
+		complete(&first_stage);
+
+	if (octeon_device_init(oct_dev)) {
+		liquidio_remove(pdev);
+		return -ENOMEM;
+	}
+
+	dev_dbg(&oct_dev->pci_dev->dev, "Device is ready\n");
+
+	return 0;
+}
+
+/**
+ *\brief Destroy resources associated with octeon device
+ * @param pdev PCI device structure
+ * @param ent unused
+ */
+static void octeon_destroy_resources(struct octeon_device *oct)
+{
+	int i;
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)oct->priv;
+
+	struct handshake *hs;
+
+	switch (atomic_read(&oct->status)) {
+	case OCT_DEV_RUNNING:
+	case OCT_DEV_CORE_OK:
+
+		/* No more instructions will be forwarded. */
+		atomic_set(&oct->status, OCT_DEV_IN_RESET);
+
+		oct->app_mode = CVM_DRV_INVALID_APP;
+		dev_dbg(&oct->pci_dev->dev, "Device state is now %s\n",
+			lio_get_state_string(&oct->status));
+
+		schedule_timeout_uninterruptible(HZ / 10);
+
+		/* fallthrough */
+	case OCT_DEV_HOST_OK:
+
+		/* fallthrough */
+	case OCT_DEV_CONSOLE_INIT_DONE:
+		/* Remove any consoles */
+		octeon_remove_consoles(oct);
+
+		/* fallthrough */
+	case OCT_DEV_IO_QUEUES_DONE:
+		if (wait_for_pending_requests(oct))
+			dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
+		if (lio_wait_for_instr_fetch(oct))
+			dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
+
+		/* Disable the input and output queues now. No more packets will
+		 * arrive from Octeon, but we should wait for all packet
+		 * processing to finish.
+		 */
+		oct->fn_list.disable_io_queues(oct);
+
+		if (lio_wait_for_oq_pkts(oct))
+			dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
+
+		/* Disable interrupts  */
+		oct->fn_list.disable_interrupt(oct->chip);
+
+		/* Release the interrupt line */
+		free_irq(oct->pci_dev->irq, oct);
+
+		if (oct->flags & LIO_FLAG_MSI_ENABLED)
+			pci_disable_msi(oct->pci_dev);
+
+		/* Soft reset the octeon device before exiting */
+		oct->fn_list.soft_reset(oct);
+
+		/* Disable the device, releasing the PCI INT */
+		pci_disable_device(oct->pci_dev);
+
+		/* fallthrough */
+	case OCT_DEV_IN_RESET:
+	case OCT_DEV_DROQ_INIT_DONE:
+		/*atomic_set(&oct->status, OCT_DEV_DROQ_INIT_DONE);*/
+		mdelay(100);
+		for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+			if (!(oct->io_qmask.oq & (1UL << i)))
+				continue;
+			octeon_delete_droq(oct, i);
+		}
+
+		/* Force any pending handshakes to complete */
+		for (i = 0; i < MAX_OCTEON_DEVICES; i++) {
+			hs = &handshake[i];
+
+			if (hs->pci_dev) {
+				handshake[oct->octeon_id].init_ok = 0;
+				complete(&handshake[oct->octeon_id].init);
+				handshake[oct->octeon_id].started_ok = 0;
+				complete(&handshake[oct->octeon_id].started);
+			}
+		}
+
+		/* fallthrough */
+	case OCT_DEV_RESP_LIST_INIT_DONE:
+		octeon_delete_response_list(oct);
+
+		/* fallthrough */
+	case OCT_DEV_SC_BUFF_POOL_INIT_DONE:
+		octeon_free_sc_buffer_pool(oct);
+
+		/* fallthrough */
+	case OCT_DEV_INSTR_QUEUE_INIT_DONE:
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+			if (!(oct->io_qmask.iq & (1UL << i)))
+				continue;
+			octeon_delete_instr_queue(oct, i);
+		}
+
+		/* fallthrough */
+	case OCT_DEV_DISPATCH_INIT_DONE:
+		octeon_delete_dispatch_list(oct);
+		cancel_delayed_work_sync(&oct->nic_poll_work.work);
+
+		/* fallthrough */
+	case OCT_DEV_PCI_MAP_DONE:
+		octeon_unmap_pci_barx(oct, 0);
+		octeon_unmap_pci_barx(oct, 1);
+
+		/* fallthrough */
+	case OCT_DEV_BEGIN_STATE:
+		/* Nothing to be done here either */
+		break;
+	}                       /* end switch(oct->status) */
+
+	tasklet_kill(&oct_priv->droq_tasklet);
+}
+
+/**
+ * \brief Send Rx control command
+ * @param lio per-network private data
+ * @param start_stop whether to start or stop
+ */
+static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
+{
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.s.cmd = OCTNET_CMD_RX_CTL;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = start_stop;
+	nctrl.netpndev = (u64)lio->netdev;
+
+	nparams.resp_order = OCTEON_RESP_NORESPONSE;
+
+	if (octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams) < 0)
+		netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n");
+}
+
+/**
+ * \brief Destroy NIC device interface
+ * @param oct octeon device
+ * @param ifidx which interface to destroy
+ *
+ * Cleanup associated with each interface for an Octeon device  when NIC
+ * module is being unloaded or if initialization fails during load.
+ */
+static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx)
+{
+	struct net_device *netdev = oct->props[ifidx].netdev;
+	struct lio *lio;
+
+	if (!netdev) {
+		dev_err(&oct->pci_dev->dev, "%s No netdevice ptr for index %d\n",
+			__func__, ifidx);
+		return;
+	}
+
+	lio = GET_LIO(netdev);
+
+	dev_dbg(&oct->pci_dev->dev, "NIC device cleanup\n");
+
+	send_rx_ctrl_cmd(lio, 0);
+
+	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING)
+		txqs_stop(netdev);
+
+	if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED)
+		unregister_netdev(netdev);
+
+	delete_glist(lio);
+
+	free_netdev(netdev);
+
+	oct->props[ifidx].netdev = NULL;
+}
+
+/**
+ * \brief Stop complete NIC functionality
+ * @param oct octeon device
+ */
+static int liquidio_stop_nic_module(struct octeon_device *oct)
+{
+	int i, j;
+	struct lio *lio;
+
+	dev_dbg(&oct->pci_dev->dev, "Stopping network interfaces\n");
+	if (!oct->ifcount) {
+		dev_err(&oct->pci_dev->dev, "Init for Octeon was not completed\n");
+		return 1;
+	}
+
+	for (i = 0; i < oct->ifcount; i++) {
+		lio = GET_LIO(oct->props[i].netdev);
+		for (j = 0; j < lio->linfo.num_rxpciq; j++)
+			octeon_unregister_droq_ops(oct, lio->linfo.rxpciq[j]);
+	}
+
+	for (i = 0; i < oct->ifcount; i++)
+		liquidio_destroy_nic_device(oct, i);
+
+	dev_dbg(&oct->pci_dev->dev, "Network interfaces stopped\n");
+	return 0;
+}
+
+/**
+ * \brief Cleans up resources at unload time
+ * @param pdev PCI device structure
+ */
+static void liquidio_remove(struct pci_dev *pdev)
+{
+	struct octeon_device *oct_dev = pci_get_drvdata(pdev);
+
+	dev_dbg(&oct_dev->pci_dev->dev, "Stopping device\n");
+
+	if (oct_dev->app_mode && (oct_dev->app_mode == CVM_DRV_NIC_APP))
+		liquidio_stop_nic_module(oct_dev);
+
+	/* Reset the octeon device and cleanup all memory allocated for
+	 * the octeon device by driver.
+	 */
+	octeon_destroy_resources(oct_dev);
+
+	dev_info(&oct_dev->pci_dev->dev, "Device removed\n");
+
+	/* This octeon device has been removed. Update the global
+	 * data structure to reflect this. Free the device structure.
+	 */
+	octeon_free_device_mem(oct_dev);
+}
+
+/**
+ * \brief Identify the Octeon device and to map the BAR address space
+ * @param oct octeon device
+ */
+static int octeon_chip_specific_setup(struct octeon_device *oct)
+{
+	u32 dev_id, rev_id;
+	int ret = 1;
+
+	pci_read_config_dword(oct->pci_dev, 0, &dev_id);
+	pci_read_config_dword(oct->pci_dev, 8, &rev_id);
+	oct->rev_id = rev_id & 0xff;
+
+	switch (dev_id) {
+	case OCTEON_CN68XX_PCIID:
+		oct->chip_id = OCTEON_CN68XX;
+		ret = lio_setup_cn68xx_octeon_device(oct);
+		break;
+
+	case OCTEON_CN66XX_PCIID:
+		oct->chip_id = OCTEON_CN66XX;
+		ret = lio_setup_cn66xx_octeon_device(oct);
+		break;
+	default:
+		dev_err(&oct->pci_dev->dev, "Unknown device found (dev_id: %x)\n",
+			dev_id);
+	}
+
+	if (!ret)
+		dev_info(&oct->pci_dev->dev, "CN68XX PASS%d.%d %s\n",
+			 OCTEON_MAJOR_REV(oct),
+			 OCTEON_MINOR_REV(oct),
+			 octeon_get_conf(oct)->card_name);
+
+	return ret;
+}
+
+/**
+ * \brief PCI initialization for each Octeon device.
+ * @param oct octeon device
+ */
+static int octeon_pci_os_setup(struct octeon_device *oct)
+{
+	/* setup PCI stuff first */
+	if (pci_enable_device(oct->pci_dev)) {
+		dev_err(&oct->pci_dev->dev, "pci_enable_device failed\n");
+		return 1;
+	}
+
+	if (dma_set_mask_and_coherent(&oct->pci_dev->dev, DMA_BIT_MASK(64))) {
+		dev_err(&oct->pci_dev->dev, "Unexpected DMA device capability\n");
+		return 1;
+	}
+
+	/* Enable PCI DMA Master. */
+	pci_set_master(oct->pci_dev);
+
+	return 0;
+}
+
+/**
+ * \brief Check Tx queue state for a given network buffer
+ * @param lio per-network private data
+ * @param skb network buffer
+ */
+static inline int check_txq_state(struct lio *lio, struct sk_buff *skb)
+{
+	int q = 0, iq = 0;
+
+	if (netif_is_multiqueue(lio->netdev)) {
+		q = skb->queue_mapping;
+		iq = lio->linfo.txpciq[(q & (lio->linfo.num_txpciq - 1))];
+	} else {
+		iq = lio->txq;
+	}
+
+	if (octnet_iq_is_full(lio->oct_dev, iq))
+		return 0;
+	wake_q(lio->netdev, q);
+	return 1;
+}
+
+/**
+ * \brief Unmap and free network buffer
+ * @param buf buffer
+ */
+static void free_netbuf(void *buf)
+{
+	struct sk_buff *skb;
+	struct octnet_buf_free_info *finfo;
+	struct lio *lio;
+
+	finfo = (struct octnet_buf_free_info *)buf;
+	skb = finfo->skb;
+	lio = finfo->lio;
+
+	dma_unmap_single(&lio->oct_dev->pci_dev->dev, finfo->dptr, skb->len,
+			 DMA_TO_DEVICE);
+
+	check_txq_state(lio, skb);
+
+	recv_buffer_free((struct sk_buff *)skb);
+}
+
+/**
+ * \brief Unmap and free gather buffer
+ * @param buf buffer
+ */
+static void free_netsgbuf(void *buf)
+{
+	struct octnet_buf_free_info *finfo;
+	struct sk_buff *skb;
+	struct lio *lio;
+	struct octnic_gather *g;
+	int i, frags;
+
+	finfo = (struct octnet_buf_free_info *)buf;
+	skb = finfo->skb;
+	lio = finfo->lio;
+	g = finfo->g;
+	frags = skb_shinfo(skb)->nr_frags;
+
+	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
+			 g->sg[0].ptr[0], (skb->len - skb->data_len),
+			 DMA_TO_DEVICE);
+
+	i = 1;
+	while (frags--) {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1];
+
+		pci_unmap_page((lio->oct_dev)->pci_dev,
+			       g->sg[(i >> 2)].ptr[(i & 3)],
+			       frag->size, DMA_TO_DEVICE);
+		i++;
+	}
+
+	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
+			 finfo->dptr, g->sg_size,
+			 DMA_TO_DEVICE);
+
+	spin_lock(&lio->lock);
+	list_add_tail(&g->list, &lio->glist);
+	spin_unlock(&lio->lock);
+
+	check_txq_state(lio, skb);     /* mq support: sub-queue state check */
+
+	recv_buffer_free((struct sk_buff *)skb);
+}
+
+/**
+ * \brief Unmap and free gather buffer with response
+ * @param buf buffer
+ */
+static void free_netsgbuf_with_resp(void *buf)
+{
+	struct octeon_soft_command *sc;
+	struct octnet_buf_free_info *finfo;
+	struct sk_buff *skb;
+	struct lio *lio;
+	struct octnic_gather *g;
+	int i, frags;
+
+	sc = (struct octeon_soft_command *)buf;
+	skb = (struct sk_buff *)sc->callback_arg;
+	finfo = (struct octnet_buf_free_info *)&skb->cb;
+
+	lio = finfo->lio;
+	g = finfo->g;
+	frags = skb_shinfo(skb)->nr_frags;
+
+	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
+			 g->sg[0].ptr[0], (skb->len - skb->data_len),
+			 DMA_TO_DEVICE);
+
+	i = 1;
+	while (frags--) {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1];
+
+		pci_unmap_page((lio->oct_dev)->pci_dev,
+			       g->sg[(i >> 2)].ptr[(i & 3)],
+			       frag->size, DMA_TO_DEVICE);
+		i++;
+	}
+
+	dma_unmap_single(&lio->oct_dev->pci_dev->dev,
+			 finfo->dptr, g->sg_size,
+			 DMA_TO_DEVICE);
+
+	spin_lock(&lio->lock);
+	list_add_tail(&g->list, &lio->glist);
+	spin_unlock(&lio->lock);
+
+	/* Don't free the skb yet */
+
+	check_txq_state(lio, skb);
+}
+
+/**
+ * \brief Adjust ptp frequency
+ * @param ptp PTP clock info
+ * @param ppb how much to adjust by, in parts-per-billion
+ */
+static int liquidio_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+	struct lio *lio = container_of(ptp, struct lio, ptp_info);
+	struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
+	u64 comp, delta;
+	unsigned long flags;
+	bool neg_adj = false;
+
+	if (ppb < 0) {
+		neg_adj = true;
+		ppb = -ppb;
+	}
+
+	/* The hardware adds the clock compensation value to the
+	 * PTP clock on every coprocessor clock cycle, so we
+	 * compute the delta in terms of coprocessor clocks.
+	 */
+	delta = (u64)ppb << 32;
+	do_div(delta, oct->coproc_clock_rate);
+
+	spin_lock_irqsave(&lio->ptp_lock, flags);
+	comp = lio_pci_readq(oct, CN6XXX_MIO_PTP_CLOCK_COMP);
+	if (neg_adj)
+		comp -= delta;
+	else
+		comp += delta;
+	lio_pci_writeq(oct, comp, CN6XXX_MIO_PTP_CLOCK_COMP);
+	spin_unlock_irqrestore(&lio->ptp_lock, flags);
+
+	return 0;
+}
+
+/**
+ * \brief Adjust ptp time
+ * @param ptp PTP clock info
+ * @param delta how much to adjust by, in nanosecs
+ */
+static int liquidio_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	unsigned long flags;
+	struct lio *lio = container_of(ptp, struct lio, ptp_info);
+
+	spin_lock_irqsave(&lio->ptp_lock, flags);
+	lio->ptp_adjust += delta;
+	spin_unlock_irqrestore(&lio->ptp_lock, flags);
+
+	return 0;
+}
+
+/**
+ * \brief Get hardware clock time, including any adjustment
+ * @param ptp PTP clock info
+ * @param ts timespec
+ */
+static int liquidio_ptp_gettime(struct ptp_clock_info *ptp,
+				struct timespec64 *ts)
+{
+	u64 ns;
+	u32 remainder;
+	unsigned long flags;
+	struct lio *lio = container_of(ptp, struct lio, ptp_info);
+	struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
+
+	spin_lock_irqsave(&lio->ptp_lock, flags);
+	ns = lio_pci_readq(oct, CN6XXX_MIO_PTP_CLOCK_HI);
+	ns += lio->ptp_adjust;
+	spin_unlock_irqrestore(&lio->ptp_lock, flags);
+
+	ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder);
+	ts->tv_nsec = remainder;
+
+	return 0;
+}
+
+/**
+ * \brief Set hardware clock time. Reset adjustment
+ * @param ptp PTP clock info
+ * @param ts timespec
+ */
+static int liquidio_ptp_settime(struct ptp_clock_info *ptp,
+				const struct timespec64 *ts)
+{
+	u64 ns;
+	unsigned long flags;
+	struct lio *lio = container_of(ptp, struct lio, ptp_info);
+	struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
+
+	ns = timespec_to_ns(ts);
+
+	spin_lock_irqsave(&lio->ptp_lock, flags);
+	lio_pci_writeq(oct, ns, CN6XXX_MIO_PTP_CLOCK_HI);
+	lio->ptp_adjust = 0;
+	spin_unlock_irqrestore(&lio->ptp_lock, flags);
+
+	return 0;
+}
+
+/**
+ * \brief Check if PTP is enabled
+ * @param ptp PTP clock info
+ * @param rq request
+ * @param on is it on
+ */
+static int liquidio_ptp_enable(struct ptp_clock_info *ptp,
+			       struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * \brief Open PTP clock source
+ * @param netdev network device
+ */
+static void oct_ptp_open(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
+
+	spin_lock_init(&lio->ptp_lock);
+
+	snprintf(lio->ptp_info.name, 16, "%s", netdev->name);
+	lio->ptp_info.owner = THIS_MODULE;
+	lio->ptp_info.max_adj = 250000000;
+	lio->ptp_info.n_alarm = 0;
+	lio->ptp_info.n_ext_ts = 0;
+	lio->ptp_info.n_per_out = 0;
+	lio->ptp_info.pps = 0;
+	lio->ptp_info.adjfreq = liquidio_ptp_adjfreq;
+	lio->ptp_info.adjtime = liquidio_ptp_adjtime;
+	lio->ptp_info.gettime64 = liquidio_ptp_gettime;
+	lio->ptp_info.settime64 = liquidio_ptp_settime;
+	lio->ptp_info.enable = liquidio_ptp_enable;
+
+	lio->ptp_adjust = 0;
+
+	lio->ptp_clock = ptp_clock_register(&lio->ptp_info,
+					     &oct->pci_dev->dev);
+
+	if (IS_ERR(lio->ptp_clock))
+		lio->ptp_clock = NULL;
+}
+
+/**
+ * \brief Init PTP clock
+ * @param oct octeon device
+ */
+static void liquidio_ptp_init(struct octeon_device *oct)
+{
+	u64 clock_comp, cfg;
+
+	clock_comp = (u64)NSEC_PER_SEC << 32;
+	do_div(clock_comp, oct->coproc_clock_rate);
+	lio_pci_writeq(oct, clock_comp, CN6XXX_MIO_PTP_CLOCK_COMP);
+
+	/* Enable */
+	cfg = lio_pci_readq(oct, CN6XXX_MIO_PTP_CLOCK_CFG);
+	lio_pci_writeq(oct, cfg | 0x01, CN6XXX_MIO_PTP_CLOCK_CFG);
+}
+
+/**
+ * \brief Load firmware to device
+ * @param oct octeon device
+ *
+ * Maps device to firmware filename, requests firmware, and downloads it
+ */
+static int load_firmware(struct octeon_device *oct)
+{
+	int ret = 0;
+	const struct firmware *fw;
+	char fw_name[LIO_MAX_FW_FILENAME_LEN];
+	char *tmp_fw_type;
+
+	if (strncmp(fw_type, LIO_FW_NAME_TYPE_NONE,
+		    sizeof(LIO_FW_NAME_TYPE_NONE)) == 0) {
+		dev_info(&oct->pci_dev->dev, "Skipping firmware load\n");
+		return ret;
+	}
+
+	if (fw_type[0] == '\0')
+		tmp_fw_type = LIO_FW_NAME_TYPE_NIC;
+	else
+		tmp_fw_type = fw_type;
+
+	sprintf(fw_name, "%s%s%s_%s%s", LIO_FW_DIR, LIO_FW_BASE_NAME,
+		octeon_get_conf(oct)->card_name, tmp_fw_type,
+		LIO_FW_NAME_SUFFIX);
+
+	ret = request_firmware(&fw, fw_name, &oct->pci_dev->dev);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev, "Request firmware failed. Could not find file %s.\n.",
+			fw_name);
+		return ret;
+	}
+
+	ret = octeon_download_firmware(oct, fw->data, fw->size);
+
+	release_firmware(fw);
+
+	return ret;
+}
+
+/**
+ * \brief Setup output queue
+ * @param oct octeon device
+ * @param q_no which queue
+ * @param num_descs how many descriptors
+ * @param desc_size size of each descriptor
+ * @param app_ctx application context
+ */
+static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs,
+			     int desc_size, void *app_ctx)
+{
+	int ret_val = 0;
+
+	dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no);
+	/* droq creation and local register settings. */
+	ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx);
+	if (ret_val == -1)
+		return ret_val;
+
+	if (ret_val == 1) {
+		dev_dbg(&oct->pci_dev->dev, "Using default droq %d\n", q_no);
+		return 0;
+	}
+	/* tasklet creation for the droq */
+
+	/* Enable the droq queues */
+	octeon_set_droq_pkt_op(oct, q_no, 1);
+
+	/* Send Credit for Octeon Output queues. Credits are always
+	 * sent after the output queue is enabled.
+	 */
+	writel(oct->droq[q_no]->max_count,
+	       oct->droq[q_no]->pkts_credit_reg);
+
+	return ret_val;
+}
+
+/**
+ * \brief Callback for getting interface configuration
+ * @param status status of request
+ * @param buf pointer to resp structure
+ */
+static void if_cfg_callback(struct octeon_device *oct,
+			    u32 status,
+			    void *buf)
+{
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
+	struct liquidio_if_cfg_resp *resp;
+	struct liquidio_if_cfg_context *ctx;
+
+	resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
+	ctx  = (struct liquidio_if_cfg_context *)sc->ctxptr;
+
+	oct = lio_get_device(ctx->octeon_id);
+	if (resp->status)
+		dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
+			CVM_CAST64(resp->status));
+	ACCESS_ONCE(ctx->cond) = 1;
+
+	/* This barrier is required to be sure that the response has been
+	 * written fully before waking up the handler
+	 */
+	wmb();
+
+	wake_up_interruptible(&ctx->wc);
+}
+
+/**
+ * \brief Select queue based on hash
+ * @param dev Net device
+ * @param skb sk_buff structure
+ * @returns selected queue number
+ */
+static u16 select_q(struct net_device *dev, struct sk_buff *skb,
+		    void *accel_priv, select_queue_fallback_t fallback)
+{
+	int qindex;
+	struct lio *lio;
+
+	lio = GET_LIO(dev);
+	/* select queue on chosen queue_mapping or core */
+	qindex = skb_rx_queue_recorded(skb) ?
+		 skb_get_rx_queue(skb) : smp_processor_id();
+	return (u16)(qindex & (lio->linfo.num_txpciq - 1));
+}
+
+/** Routine to push packets arriving on Octeon interface upto network layer.
+ * @param oct_id   - octeon device id.
+ * @param skbuff   - skbuff struct to be passed to network layer.
+ * @param len      - size of total data received.
+ * @param rh       - Control header associated with the packet
+ * @param param    - additional control data with the packet
+ */
+static void
+liquidio_push_packet(u32 octeon_id,
+		     void *skbuff,
+		     u32 len,
+		     union octeon_rh *rh,
+		     void *param)
+{
+	struct napi_struct *napi = param;
+	struct octeon_device *oct = lio_get_device(octeon_id);
+	struct sk_buff *skb = (struct sk_buff *)skbuff;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	u64 ns;
+	struct net_device *netdev =
+		(struct net_device *)oct->props[rh->r_dh.link].netdev;
+	struct octeon_droq *droq = container_of(param, struct octeon_droq,
+						napi);
+	if (netdev) {
+		int packet_was_received;
+		struct lio *lio = GET_LIO(netdev);
+
+		/* Do not proceed if the interface is not in RUNNING state. */
+		if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) {
+			recv_buffer_free(skb);
+			droq->stats.rx_dropped++;
+			return;
+		}
+
+		skb->dev = netdev;
+
+		if (rh->r_dh.has_hwtstamp) {
+			/* timestamp is included from the hardware at the
+			 * beginning of the packet.
+			 */
+			if (ifstate_check(lio,
+					  LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) {
+				/* Nanoseconds are in the first 64-bits
+				 * of the packet.
+				 */
+				memcpy(&ns, (skb->data), sizeof(ns));
+				shhwtstamps = skb_hwtstamps(skb);
+				shhwtstamps->hwtstamp =
+					ns_to_ktime(ns + lio->ptp_adjust);
+			}
+			skb_pull(skb, sizeof(ns));
+		}
+
+		skb->protocol = eth_type_trans(skb, skb->dev);
+
+		if ((netdev->features & NETIF_F_RXCSUM) &&
+		    (rh->r_dh.csum_verified == CNNIC_CSUM_VERIFIED))
+			/* checksum has already been verified */
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+
+		packet_was_received = napi_gro_receive(napi, skb) != GRO_DROP;
+
+		if (packet_was_received) {
+			droq->stats.rx_bytes_received += len;
+			droq->stats.rx_pkts_received++;
+			netdev->last_rx = jiffies;
+		} else {
+			droq->stats.rx_dropped++;
+			netif_info(lio, rx_err, lio->netdev,
+				   "droq:%d  error rx_dropped:%llu\n",
+				   droq->q_no, droq->stats.rx_dropped);
+		}
+
+	} else {
+		recv_buffer_free(skb);
+	}
+}
+
+/**
+ * \brief wrapper for calling napi_schedule
+ * @param param parameters to pass to napi_schedule
+ *
+ * Used when scheduling on different CPUs
+ */
+static void napi_schedule_wrapper(void *param)
+{
+	struct napi_struct *napi = param;
+
+	napi_schedule(napi);
+}
+
+/**
+ * \brief callback when receive interrupt occurs and we are in NAPI mode
+ * @param arg pointer to octeon output queue
+ */
+static void liquidio_napi_drv_callback(void *arg)
+{
+	struct octeon_droq *droq = arg;
+	int this_cpu = smp_processor_id();
+
+	if (droq->cpu_id == this_cpu) {
+		napi_schedule(&droq->napi);
+	} else {
+		struct call_single_data *csd = &droq->csd;
+
+		csd->func = napi_schedule_wrapper;
+		csd->info = &droq->napi;
+		csd->flags = 0;
+
+		smp_call_function_single_async(droq->cpu_id, csd);
+	}
+}
+
+/**
+ * \brief Main NAPI poll function
+ * @param droq octeon output queue
+ * @param budget maximum number of items to process
+ */
+static int liquidio_napi_do_rx(struct octeon_droq *droq, int budget)
+{
+	int work_done;
+	struct lio *lio = GET_LIO(droq->napi.dev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	work_done = octeon_process_droq_poll_cmd(oct, droq->q_no,
+						 POLL_EVENT_PROCESS_PKTS,
+						 budget);
+	if (work_done < 0) {
+		netif_info(lio, rx_err, lio->netdev,
+			   "Receive work_done < 0, rxq:%d\n", droq->q_no);
+		goto octnet_napi_finish;
+	}
+
+	if (work_done > budget)
+		dev_err(&oct->pci_dev->dev, ">>>> %s work_done: %d budget: %d\n",
+			__func__, work_done, budget);
+
+	return work_done;
+
+octnet_napi_finish:
+	napi_complete(&droq->napi);
+	octeon_process_droq_poll_cmd(oct, droq->q_no, POLL_EVENT_ENABLE_INTR,
+				     0);
+	return 0;
+}
+
+/**
+ * \brief Entry point for NAPI polling
+ * @param napi NAPI structure
+ * @param budget maximum number of items to process
+ */
+static int liquidio_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct octeon_droq *droq;
+	int work_done;
+
+	droq = container_of(napi, struct octeon_droq, napi);
+
+	work_done = liquidio_napi_do_rx(droq, budget);
+
+	if (work_done < budget) {
+		napi_complete(napi);
+		octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no,
+					     POLL_EVENT_ENABLE_INTR, 0);
+		return 0;
+	}
+
+	return work_done;
+}
+
+/**
+ * \brief Setup input and output queues
+ * @param octeon_dev octeon device
+ * @param net_device Net device
+ *
+ * Note: Queues are with respect to the octeon device. Thus
+ * an input queue is for egress packets, and output queues
+ * are for ingress packets.
+ */
+static inline int setup_io_queues(struct octeon_device *octeon_dev,
+				  struct net_device *net_device)
+{
+	static int first_time = 1;
+	static struct octeon_droq_ops droq_ops;
+	static int cpu_id;
+	static int cpu_id_modulus;
+	struct octeon_droq *droq;
+	struct napi_struct *napi;
+	int q, q_no, retval = 0;
+	struct lio *lio;
+	int num_tx_descs;
+
+	lio = GET_LIO(net_device);
+	if (first_time) {
+		first_time = 0;
+		memset(&droq_ops, 0, sizeof(struct octeon_droq_ops));
+
+		droq_ops.fptr = liquidio_push_packet;
+
+		droq_ops.poll_mode = 1;
+		droq_ops.napi_fn = liquidio_napi_drv_callback;
+		cpu_id = 0;
+		cpu_id_modulus = num_present_cpus();
+	}
+
+	/* set up DROQs. */
+	for (q = 0; q < lio->linfo.num_rxpciq; q++) {
+		q_no = lio->linfo.rxpciq[q];
+
+		retval = octeon_setup_droq(octeon_dev, q_no,
+					   CFG_GET_NUM_RX_DESCS_NIC_IF
+						   (octeon_get_conf(octeon_dev),
+						   lio->ifidx),
+					   CFG_GET_NUM_RX_BUF_SIZE_NIC_IF
+						   (octeon_get_conf(octeon_dev),
+						   lio->ifidx), NULL);
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				" %s : Runtime DROQ(RxQ) creation failed.\n",
+				__func__);
+			return 1;
+		}
+
+		droq = octeon_dev->droq[q_no];
+		napi = &droq->napi;
+		netif_napi_add(net_device, napi, liquidio_napi_poll, 64);
+
+		/* designate a CPU for this droq */
+		droq->cpu_id = cpu_id;
+		cpu_id++;
+		if (cpu_id >= cpu_id_modulus)
+			cpu_id = 0;
+
+		octeon_register_droq_ops(octeon_dev, q_no, &droq_ops);
+	}
+
+	/* set up IQs. */
+	for (q = 0; q < lio->linfo.num_txpciq; q++) {
+		num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF(octeon_get_conf
+							   (octeon_dev),
+							   lio->ifidx);
+		retval = octeon_setup_iq(octeon_dev, lio->linfo.txpciq[q],
+					 num_tx_descs,
+					 netdev_get_tx_queue(net_device, q));
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				" %s : Runtime IQ(TxQ) creation failed.\n",
+				__func__);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * \brief Poll routine for checking transmit queue status
+ * @param work work_struct data structure
+ */
+static void octnet_poll_check_txq_status(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct lio *lio = (struct lio *)wk->ctxptr;
+
+	if (!ifstate_check(lio, LIO_IFSTATE_RUNNING))
+		return;
+
+	check_txq_status(lio);
+	queue_delayed_work(lio->txq_status_wq.wq,
+			   &lio->txq_status_wq.wk.work, msecs_to_jiffies(1));
+}
+
+/**
+ * \brief Sets up the txq poll check
+ * @param netdev network device
+ */
+static inline void setup_tx_poll_fn(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	lio->txq_status_wq.wq = create_workqueue("txq-status");
+	if (!lio->txq_status_wq.wq) {
+		dev_err(&oct->pci_dev->dev, "unable to create cavium txq status wq\n");
+		return;
+	}
+	INIT_DELAYED_WORK(&lio->txq_status_wq.wk.work,
+			  octnet_poll_check_txq_status);
+	lio->txq_status_wq.wk.ctxptr = lio;
+	queue_delayed_work(lio->txq_status_wq.wq,
+			   &lio->txq_status_wq.wk.work, msecs_to_jiffies(1));
+}
+
+/**
+ * \brief Net device open for LiquidIO
+ * @param netdev network device
+ */
+static int liquidio_open(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct napi_struct *napi, *n;
+
+	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+		napi_enable(napi);
+
+	oct_ptp_open(netdev);
+
+	ifstate_set(lio, LIO_IFSTATE_RUNNING);
+	setup_tx_poll_fn(netdev);
+	start_txq(netdev);
+
+	netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n");
+	try_module_get(THIS_MODULE);
+
+	/* tell Octeon to start forwarding packets to host */
+	send_rx_ctrl_cmd(lio, 1);
+
+	/* Ready for link status updates */
+	lio->intf_open = 1;
+
+	dev_info(&oct->pci_dev->dev, "%s interface is opened\n",
+		 netdev->name);
+
+	return 0;
+}
+
+/**
+ * \brief Net device stop for LiquidIO
+ * @param netdev network device
+ */
+static int liquidio_stop(struct net_device *netdev)
+{
+	struct napi_struct *napi, *n;
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	netif_info(lio, ifdown, lio->netdev, "Stopping interface!\n");
+	/* Inform that netif carrier is down */
+	lio->intf_open = 0;
+	lio->linfo.link.s.status = 0;
+
+	netif_carrier_off(netdev);
+
+	/* tell Octeon to stop forwarding packets to host */
+	send_rx_ctrl_cmd(lio, 0);
+
+	cancel_delayed_work_sync(&lio->txq_status_wq.wk.work);
+	flush_workqueue(lio->txq_status_wq.wq);
+	destroy_workqueue(lio->txq_status_wq.wq);
+
+	if (lio->ptp_clock) {
+		ptp_clock_unregister(lio->ptp_clock);
+		lio->ptp_clock = NULL;
+	}
+
+	ifstate_reset(lio, LIO_IFSTATE_RUNNING);
+
+	/* This is a hack that allows DHCP to continue working. */
+	set_bit(__LINK_STATE_START, &lio->netdev->state);
+
+	list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list)
+		napi_disable(napi);
+
+	txqs_stop(netdev);
+
+	dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name);
+	module_put(THIS_MODULE);
+
+	return 0;
+}
+
+void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
+{
+	struct octnic_ctrl_pkt *nctrl = (struct octnic_ctrl_pkt *)nctrl_ptr;
+	struct net_device *netdev = (struct net_device *)nctrl->netpndev;
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+
+	switch (nctrl->ncmd.s.cmd) {
+	case OCTNET_CMD_CHANGE_DEVFLAGS:
+	case OCTNET_CMD_SET_MULTI_LIST:
+		break;
+
+	case OCTNET_CMD_CHANGE_MACADDR:
+		/* If command is successful, change the MACADDR. */
+		netif_info(lio, probe, lio->netdev, " MACAddr changed to 0x%llx\n",
+			   CVM_CAST64(nctrl->udd[0]));
+		dev_info(&oct->pci_dev->dev, "%s MACAddr changed to 0x%llx\n",
+			 netdev->name, CVM_CAST64(nctrl->udd[0]));
+		memcpy(netdev->dev_addr, ((u8 *)&nctrl->udd[0]) + 2, ETH_ALEN);
+		break;
+
+	case OCTNET_CMD_CHANGE_MTU:
+		/* If command is successful, change the MTU. */
+		netif_info(lio, probe, lio->netdev, " MTU Changed from %d to %d\n",
+			   netdev->mtu, nctrl->ncmd.s.param2);
+		dev_info(&oct->pci_dev->dev, "%s MTU Changed from %d to %d\n",
+			 netdev->name, netdev->mtu,
+			 nctrl->ncmd.s.param2);
+		netdev->mtu = nctrl->ncmd.s.param2;
+		break;
+
+	case OCTNET_CMD_GPIO_ACCESS:
+		netif_info(lio, probe, lio->netdev, "LED Flashing visual identification\n");
+
+		break;
+
+	case OCTNET_CMD_LRO_ENABLE:
+		dev_info(&oct->pci_dev->dev, "%s LRO Enabled\n", netdev->name);
+		break;
+
+	case OCTNET_CMD_LRO_DISABLE:
+		dev_info(&oct->pci_dev->dev, "%s LRO Disabled\n",
+			 netdev->name);
+		break;
+
+	case OCTNET_CMD_VERBOSE_ENABLE:
+		dev_info(&oct->pci_dev->dev, "%s LRO Enabled\n", netdev->name);
+		break;
+
+	case OCTNET_CMD_VERBOSE_DISABLE:
+		dev_info(&oct->pci_dev->dev, "%s LRO Disabled\n",
+			 netdev->name);
+		break;
+
+	case OCTNET_CMD_SET_SETTINGS:
+		dev_info(&oct->pci_dev->dev, "%s settings changed\n",
+			 netdev->name);
+
+		break;
+
+	default:
+		dev_err(&oct->pci_dev->dev, "%s Unknown cmd %d\n", __func__,
+			nctrl->ncmd.s.cmd);
+	}
+}
+
+/**
+ * \brief Converts a mask based on net device flags
+ * @param netdev network device
+ *
+ * This routine generates a octnet_ifflags mask from the net device flags
+ * received from the OS.
+ */
+static inline enum octnet_ifflags get_new_flags(struct net_device *netdev)
+{
+	enum octnet_ifflags f = OCTNET_IFFLAG_UNICAST;
+
+	if (netdev->flags & IFF_PROMISC)
+		f |= OCTNET_IFFLAG_PROMISC;
+
+	if (netdev->flags & IFF_ALLMULTI)
+		f |= OCTNET_IFFLAG_ALLMULTI;
+
+	if (netdev->flags & IFF_MULTICAST) {
+		f |= OCTNET_IFFLAG_MULTICAST;
+
+		/* Accept all multicast addresses if there are more than we
+		 * can handle
+		 */
+		if (netdev_mc_count(netdev) > MAX_OCTEON_MULTICAST_ADDR)
+			f |= OCTNET_IFFLAG_ALLMULTI;
+	}
+
+	if (netdev->flags & IFF_BROADCAST)
+		f |= OCTNET_IFFLAG_BROADCAST;
+
+	return f;
+}
+
+/**
+ * \brief Net device set_multicast_list
+ * @param netdev network device
+ */
+static void liquidio_set_mcast_list(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+	struct netdev_hw_addr *ha;
+	u64 *mc;
+	int ret, i;
+	int mc_count = min(netdev_mc_count(netdev), MAX_OCTEON_MULTICAST_ADDR);
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	/* Create a ctrl pkt command to be sent to core app. */
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_SET_MULTI_LIST;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = get_new_flags(netdev);
+	nctrl.ncmd.s.param3 = mc_count;
+	nctrl.ncmd.s.more = mc_count;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	/* copy all the addresses into the udd */
+	i = 0;
+	mc = &nctrl.udd[0];
+	netdev_for_each_mc_addr(ha, netdev) {
+		*mc = 0;
+		memcpy(((u8 *)mc) + 2, ha->addr, ETH_ALEN);
+		/* no need to swap bytes */
+
+		if (++mc > &nctrl.udd[mc_count])
+			break;
+	}
+
+	/* Apparently, any activity in this call from the kernel has to
+	 * be atomic. So we won't wait for response.
+	 */
+	nctrl.wait_time = 0;
+
+	nparams.resp_order = OCTEON_RESP_NORESPONSE;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n",
+			ret);
+	}
+}
+
+/**
+ * \brief Net device set_mac_address
+ * @param netdev network device
+ */
+static int liquidio_set_mac(struct net_device *netdev, void *p)
+{
+	int ret = 0;
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct sockaddr *addr = (struct sockaddr *)p;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+
+	if ((!is_valid_ether_addr(addr->sa_data)) ||
+	    (ifstate_check(lio, LIO_IFSTATE_RUNNING)))
+		return -EADDRNOTAVAIL;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = 0;
+	nctrl.ncmd.s.more = 1;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+	nctrl.wait_time = 100;
+
+	nctrl.udd[0] = 0;
+	/* The MAC Address is presented in network byte order. */
+	memcpy((u8 *)&nctrl.udd[0] + 2, addr->sa_data, ETH_ALEN);
+
+	nparams.resp_order = OCTEON_RESP_ORDERED;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "MAC Address change failed\n");
+		return -ENOMEM;
+	}
+	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+	memcpy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data, ETH_ALEN);
+
+	return 0;
+}
+
+/**
+ * \brief Net device get_stats
+ * @param netdev network device
+ */
+static struct net_device_stats *liquidio_get_stats(struct net_device *netdev)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct net_device_stats *stats = &netdev->stats;
+	struct octeon_device *oct;
+	u64 pkts = 0, drop = 0, bytes = 0;
+	struct oct_droq_stats *oq_stats;
+	struct oct_iq_stats *iq_stats;
+	int i, iq_no, oq_no;
+
+	oct = lio->oct_dev;
+
+	for (i = 0; i < lio->linfo.num_txpciq; i++) {
+		iq_no = lio->linfo.txpciq[i];
+		iq_stats = &oct->instr_queue[iq_no]->stats;
+		pkts += iq_stats->tx_done;
+		drop += iq_stats->tx_dropped;
+		bytes += iq_stats->tx_tot_bytes;
+	}
+
+	stats->tx_packets = pkts;
+	stats->tx_bytes = bytes;
+	stats->tx_dropped = drop;
+
+	pkts = 0;
+	drop = 0;
+	bytes = 0;
+
+	for (i = 0; i < lio->linfo.num_rxpciq; i++) {
+		oq_no = lio->linfo.rxpciq[i];
+		oq_stats = &oct->droq[oq_no]->stats;
+		pkts += oq_stats->rx_pkts_received;
+		drop += (oq_stats->rx_dropped +
+			 oq_stats->dropped_nodispatch +
+			 oq_stats->dropped_toomany +
+			 oq_stats->dropped_nomem);
+		bytes += oq_stats->rx_bytes_received;
+	}
+
+	stats->rx_bytes = bytes;
+	stats->rx_packets = pkts;
+	stats->rx_dropped = drop;
+
+	return stats;
+}
+
+/**
+ * \brief Net device change_mtu
+ * @param netdev network device
+ */
+static int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+	int max_frm_size = new_mtu + OCTNET_FRM_HEADER_SIZE;
+	int ret = 0;
+
+	/* Limit the MTU to make sure the ethernet packets are between 64 bytes
+	 * and 65535 bytes
+	 */
+	if ((max_frm_size < OCTNET_MIN_FRM_SIZE) ||
+	    (max_frm_size > OCTNET_MAX_FRM_SIZE)) {
+		dev_err(&oct->pci_dev->dev, "Invalid MTU: %d\n", new_mtu);
+		dev_err(&oct->pci_dev->dev, "Valid range %d and %d\n",
+			(OCTNET_MIN_FRM_SIZE - OCTNET_FRM_HEADER_SIZE),
+			(OCTNET_MAX_FRM_SIZE - OCTNET_FRM_HEADER_SIZE));
+		return -EINVAL;
+	}
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MTU;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = new_mtu;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	nparams.resp_order = OCTEON_RESP_ORDERED;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Failed to set MTU\n");
+		return -1;
+	}
+
+	lio->mtu = new_mtu;
+
+	return 0;
+}
+
+/**
+ * \brief Handler for SIOCSHWTSTAMP ioctl
+ * @param netdev network device
+ * @param ifr interface request
+ * @param cmd command
+ */
+static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	struct hwtstamp_config conf;
+	struct lio *lio = GET_LIO(netdev);
+
+	if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf)))
+		return -EFAULT;
+
+	if (conf.flags)
+		return -EINVAL;
+
+	switch (conf.tx_type) {
+	case HWTSTAMP_TX_ON:
+	case HWTSTAMP_TX_OFF:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (conf.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		break;
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		conf.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (conf.rx_filter == HWTSTAMP_FILTER_ALL)
+		ifstate_set(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
+
+	else
+		ifstate_reset(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED);
+
+	return copy_to_user(ifr->ifr_data, &conf, sizeof(conf)) ? -EFAULT : 0;
+}
+
+/**
+ * \brief ioctl handler
+ * @param netdev network device
+ * @param ifr interface request
+ * @param cmd command
+ */
+static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		return hwtstamp_ioctl(netdev, ifr, cmd);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * \brief handle a Tx timestamp response
+ * @param status response status
+ * @param buf pointer to skb
+ */
+static void handle_timestamp(struct octeon_device *oct,
+			     u32 status,
+			     void *buf)
+{
+	struct octnet_buf_free_info *finfo;
+	struct octeon_soft_command *sc;
+	struct oct_timestamp_resp *resp;
+	struct lio *lio;
+	struct sk_buff *skb = (struct sk_buff *)buf;
+
+	finfo = (struct octnet_buf_free_info *)skb->cb;
+	lio = finfo->lio;
+	sc = finfo->sc;
+	oct = lio->oct_dev;
+	resp = (struct oct_timestamp_resp *)sc->virtrptr;
+
+	if (status != OCTEON_REQUEST_DONE) {
+		dev_err(&oct->pci_dev->dev, "Tx timestamp instruction failed. Status: %llx\n",
+			CVM_CAST64(status));
+		resp->timestamp = 0;
+	}
+
+	octeon_swap_8B_data(&resp->timestamp, 1);
+
+	if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) {
+		struct skb_shared_hwtstamps ts;
+		u64 ns = resp->timestamp;
+
+		netif_info(lio, tx_done, lio->netdev,
+			   "Got resulting SKBTX_HW_TSTAMP skb=%p ns=%016llu\n",
+			   skb, (unsigned long long)ns);
+		ts.hwtstamp = ns_to_ktime(ns + lio->ptp_adjust);
+		skb_tstamp_tx(skb, &ts);
+	}
+
+	octeon_free_soft_command(oct, sc);
+	recv_buffer_free(skb);
+}
+
+/* \brief Send a data packet that will be timestamped
+ * @param oct octeon device
+ * @param ndata pointer to network data
+ * @param finfo pointer to private network data
+ */
+static inline int send_nic_timestamp_pkt(struct octeon_device *oct,
+					 struct octnic_data_pkt *ndata,
+					 struct octnet_buf_free_info *finfo,
+					 int xmit_more)
+{
+	int retval;
+	struct octeon_soft_command *sc;
+	struct octeon_instr_ih *ih;
+	struct octeon_instr_rdp *rdp;
+	struct lio *lio;
+	int ring_doorbell;
+
+	lio = finfo->lio;
+
+	sc = octeon_alloc_soft_command_resp(oct, &ndata->cmd,
+					    sizeof(struct oct_timestamp_resp));
+	finfo->sc = sc;
+
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev, "No memory for timestamped data packet\n");
+		return IQ_SEND_FAILED;
+	}
+
+	if (ndata->reqtype == REQTYPE_NORESP_NET)
+		ndata->reqtype = REQTYPE_RESP_NET;
+	else if (ndata->reqtype == REQTYPE_NORESP_NET_SG)
+		ndata->reqtype = REQTYPE_RESP_NET_SG;
+
+	sc->callback = handle_timestamp;
+	sc->callback_arg = finfo->skb;
+	sc->iq_no = ndata->q_no;
+
+	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
+	rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+
+	ring_doorbell = !xmit_more;
+	retval = octeon_send_command(oct, sc->iq_no, ring_doorbell, &sc->cmd,
+				     sc, ih->dlengsz, ndata->reqtype);
+
+	if (retval) {
+		dev_err(&oct->pci_dev->dev, "timestamp data packet failed status: %x\n",
+			retval);
+		octeon_free_soft_command(oct, sc);
+	} else {
+		netif_info(lio, tx_queued, lio->netdev, "Queued timestamp packet\n");
+	}
+
+	return retval;
+}
+
+static inline int is_ipv4(struct sk_buff *skb)
+{
+	return (skb->protocol == htons(ETH_P_IP)) &&
+	       (ip_hdr(skb)->version == 4);
+}
+
+static inline int is_vlan(struct sk_buff *skb)
+{
+	return skb->protocol == htons(ETH_P_8021Q);
+}
+
+static inline int is_ip_fragmented(struct sk_buff *skb)
+{
+	/* The Don't fragment and Reserved flag fields are ignored.
+	 * IP is fragmented if
+	 * -  the More fragments bit is set (indicating this IP is a fragment
+	 * with more to follow; the current offset could be 0 ).
+	 * -  ths offset field is non-zero.
+	 */
+	return (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) ? 1 : 0;
+}
+
+static inline int is_ipv6(struct sk_buff *skb)
+{
+	return (skb->protocol == htons(ETH_P_IPV6)) &&
+	       (ipv6_hdr(skb)->version == 6);
+}
+
+static inline int is_with_extn_hdr(struct sk_buff *skb)
+{
+	return (ipv6_hdr(skb)->nexthdr != IPPROTO_TCP) &&
+	       (ipv6_hdr(skb)->nexthdr != IPPROTO_UDP);
+}
+
+static inline int is_tcpudp(struct sk_buff *skb)
+{
+	return (ip_hdr(skb)->protocol == IPPROTO_TCP) ||
+	       (ip_hdr(skb)->protocol == IPPROTO_UDP);
+}
+
+static inline u32 get_ipv4_5tuple_tag(struct sk_buff *skb)
+{
+	u32 tag;
+	struct iphdr *iphdr = ip_hdr(skb);
+
+	tag = crc32(0, &iphdr->protocol, 1);
+	tag = crc32(tag, (u8 *)&iphdr->saddr, 8);
+	tag = crc32(tag, skb_transport_header(skb), 4);
+	return tag;
+}
+
+static inline u32 get_ipv6_5tuple_tag(struct sk_buff *skb)
+{
+	u32 tag;
+	struct ipv6hdr *ipv6hdr = ipv6_hdr(skb);
+
+	tag = crc32(0, &ipv6hdr->nexthdr, 1);
+	tag = crc32(tag, (u8 *)&ipv6hdr->saddr, 32);
+	tag = crc32(tag, skb_transport_header(skb), 4);
+	return tag;
+}
+
+/** \brief Transmit networks packets to the Octeon interface
+ * @param skbuff   skbuff struct to be passed to network layer.
+ * @param netdev    pointer to network device
+ * @returns whether the packet was transmitted to the device okay or not
+ *             (NETDEV_TX_OK or NETDEV_TX_BUSY)
+ */
+static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct lio *lio;
+	struct octnet_buf_free_info *finfo;
+	union octnic_cmd_setup cmdsetup;
+	struct octnic_data_pkt ndata;
+	struct octeon_device *oct;
+	struct oct_iq_stats *stats;
+	int cpu = 0, status = 0;
+	int q_idx = 0, iq_no = 0;
+	int xmit_more;
+	u32 tag = 0;
+
+	lio = GET_LIO(netdev);
+	oct = lio->oct_dev;
+
+	if (netif_is_multiqueue(netdev)) {
+		cpu = skb->queue_mapping;
+		q_idx = (cpu & (lio->linfo.num_txpciq - 1));
+		iq_no = lio->linfo.txpciq[q_idx];
+	} else {
+		iq_no = lio->txq;
+	}
+
+	stats = &oct->instr_queue[iq_no]->stats;
+
+	/* Check for all conditions in which the current packet cannot be
+	 * transmitted.
+	 */
+	if (!(atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING) ||
+	    (!lio->linfo.link.s.status) ||
+	    (skb->len <= 0)) {
+		netif_info(lio, tx_err, lio->netdev,
+			   "Transmit failed link_status : %d\n",
+			   lio->linfo.link.s.status);
+		goto lio_xmit_failed;
+	}
+
+	/* Use space in skb->cb to store info used to unmap and
+	 * free the buffers.
+	 */
+	finfo = (struct octnet_buf_free_info *)skb->cb;
+	finfo->lio = lio;
+	finfo->skb = skb;
+	finfo->sc = NULL;
+
+	/* Prepare the attributes for the data to be passed to OSI. */
+	memset(&ndata, 0, sizeof(struct octnic_data_pkt));
+
+	ndata.buf = (void *)finfo;
+
+	ndata.q_no = iq_no;
+
+	if (netif_is_multiqueue(netdev)) {
+		if (octnet_iq_is_full(oct, ndata.q_no)) {
+			/* defer sending if queue is full */
+			netif_info(lio, tx_err, lio->netdev, "Transmit failed iq:%d full\n",
+				   ndata.q_no);
+			stats->tx_iq_busy++;
+			return NETDEV_TX_BUSY;
+		}
+	} else {
+		if (octnet_iq_is_full(oct, lio->txq)) {
+			/* defer sending if queue is full */
+			stats->tx_iq_busy++;
+			netif_info(lio, tx_err, lio->netdev, "Transmit failed iq:%d full\n",
+				   ndata.q_no);
+			return NETDEV_TX_BUSY;
+		}
+	}
+	/* pr_info(" XMIT - valid Qs: %d, 1st Q no: %d, cpu:  %d, q_no:%d\n",
+	 *	lio->linfo.num_txpciq, lio->txq, cpu, ndata.q_no );
+	 */
+
+	ndata.datasize = skb->len;
+
+	cmdsetup.u64 = 0;
+	cmdsetup.s.ifidx = lio->linfo.ifidx;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		if (is_ipv4(skb) && !is_ip_fragmented(skb) && is_tcpudp(skb)) {
+			tag = get_ipv4_5tuple_tag(skb);
+
+			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
+
+			if (ip_hdr(skb)->ihl > 5)
+				cmdsetup.s.ipv4opts_ipv6exthdr =
+						OCT_PKT_PARAM_IPV4OPTS;
+
+		} else if (is_ipv6(skb)) {
+			tag = get_ipv6_5tuple_tag(skb);
+
+			cmdsetup.s.cksum_offset = sizeof(struct ethhdr) + 1;
+
+			if (is_with_extn_hdr(skb))
+				cmdsetup.s.ipv4opts_ipv6exthdr =
+						OCT_PKT_PARAM_IPV6EXTHDR;
+
+		} else if (is_vlan(skb)) {
+			if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
+				== htons(ETH_P_IP) &&
+				!is_ip_fragmented(skb) && is_tcpudp(skb)) {
+				tag = get_ipv4_5tuple_tag(skb);
+
+				cmdsetup.s.cksum_offset =
+					sizeof(struct vlan_ethhdr) + 1;
+
+				if (ip_hdr(skb)->ihl > 5)
+					cmdsetup.s.ipv4opts_ipv6exthdr =
+						OCT_PKT_PARAM_IPV4OPTS;
+
+			} else if (vlan_eth_hdr(skb)->h_vlan_encapsulated_proto
+				== htons(ETH_P_IPV6)) {
+				tag = get_ipv6_5tuple_tag(skb);
+
+				cmdsetup.s.cksum_offset =
+					sizeof(struct vlan_ethhdr) + 1;
+
+				if (is_with_extn_hdr(skb))
+					cmdsetup.s.ipv4opts_ipv6exthdr =
+						OCT_PKT_PARAM_IPV6EXTHDR;
+			}
+		}
+	}
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		cmdsetup.s.timestamp = 1;
+	}
+
+	if (skb_shinfo(skb)->nr_frags == 0) {
+		cmdsetup.s.u.datasize = skb->len;
+		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+		/* Offload checksum calculation for TCP/UDP packets */
+		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
+						skb->data,
+						skb->len,
+						DMA_TO_DEVICE);
+		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
+			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 1\n",
+				__func__);
+			return NETDEV_TX_BUSY;
+		}
+
+		finfo->dptr = ndata.cmd.dptr;
+
+		ndata.reqtype = REQTYPE_NORESP_NET;
+
+	} else {
+		int i, frags;
+		struct skb_frag_struct *frag;
+		struct octnic_gather *g;
+
+		spin_lock(&lio->lock);
+		g = (struct octnic_gather *)list_delete_head(&lio->glist);
+		spin_unlock(&lio->lock);
+
+		if (!g) {
+			netif_info(lio, tx_err, lio->netdev,
+				   "Transmit scatter gather: glist null!\n");
+			goto lio_xmit_failed;
+		}
+
+		cmdsetup.s.gather = 1;
+		cmdsetup.s.u.gatherptrs = (skb_shinfo(skb)->nr_frags + 1);
+		octnet_prepare_pci_cmd(&ndata.cmd, &cmdsetup, tag);
+
+		memset(g->sg, 0, g->sg_size);
+
+		g->sg[0].ptr[0] = dma_map_single(&oct->pci_dev->dev,
+						 skb->data,
+						 (skb->len - skb->data_len),
+						 DMA_TO_DEVICE);
+		if (dma_mapping_error(&oct->pci_dev->dev, g->sg[0].ptr[0])) {
+			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 2\n",
+				__func__);
+			return NETDEV_TX_BUSY;
+		}
+		add_sg_size(&g->sg[0], (skb->len - skb->data_len), 0);
+
+		frags = skb_shinfo(skb)->nr_frags;
+		i = 1;
+		while (frags--) {
+			frag = &skb_shinfo(skb)->frags[i - 1];
+
+			g->sg[(i >> 2)].ptr[(i & 3)] =
+				dma_map_page(&oct->pci_dev->dev,
+					     frag->page.p,
+					     frag->page_offset,
+					     frag->size,
+					     DMA_TO_DEVICE);
+
+			add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3));
+			i++;
+		}
+
+		ndata.cmd.dptr = dma_map_single(&oct->pci_dev->dev,
+						g->sg, g->sg_size,
+						DMA_TO_DEVICE);
+		if (dma_mapping_error(&oct->pci_dev->dev, ndata.cmd.dptr)) {
+			dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n",
+				__func__);
+			dma_unmap_single(&oct->pci_dev->dev, g->sg[0].ptr[0],
+					 skb->len - skb->data_len,
+					 DMA_TO_DEVICE);
+			return NETDEV_TX_BUSY;
+		}
+
+		finfo->dptr = ndata.cmd.dptr;
+		finfo->g = g;
+
+		ndata.reqtype = REQTYPE_NORESP_NET_SG;
+	}
+
+	if (skb_shinfo(skb)->gso_size) {
+		struct octeon_instr_irh *irh =
+			(struct octeon_instr_irh *)&ndata.cmd.irh;
+		union tx_info *tx_info = (union tx_info *)&ndata.cmd.ossp[0];
+
+		irh->len = 1;   /* to indicate that ossp[0] contains tx_info */
+		tx_info->s.gso_size = skb_shinfo(skb)->gso_size;
+		tx_info->s.gso_segs = skb_shinfo(skb)->gso_segs;
+	}
+
+	xmit_more = skb->xmit_more;
+
+	if (unlikely(cmdsetup.s.timestamp))
+		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
+	else
+		status = octnet_send_nic_data_pkt(oct, &ndata, xmit_more);
+	if (status == IQ_SEND_FAILED)
+		goto lio_xmit_failed;
+
+	netif_info(lio, tx_queued, lio->netdev, "Transmit queued successfully\n");
+
+	if (status == IQ_SEND_STOP)
+		stop_q(lio->netdev, q_idx);
+
+	netdev->trans_start = jiffies;
+
+	stats->tx_done++;
+	stats->tx_tot_bytes += skb->len;
+
+	return NETDEV_TX_OK;
+
+lio_xmit_failed:
+	stats->tx_dropped++;
+	netif_info(lio, tx_err, lio->netdev, "IQ%d Transmit dropped:%llu\n",
+		   iq_no, stats->tx_dropped);
+	dma_unmap_single(&oct->pci_dev->dev, ndata.cmd.dptr,
+			 ndata.datasize, DMA_TO_DEVICE);
+	recv_buffer_free(skb);
+	return NETDEV_TX_OK;
+}
+
+/** \brief Network device Tx timeout
+ * @param netdev    pointer to network device
+ */
+static void liquidio_tx_timeout(struct net_device *netdev)
+{
+	struct lio *lio;
+
+	lio = GET_LIO(netdev);
+
+	netif_info(lio, tx_err, lio->netdev,
+		   "Transmit timeout tx_dropped:%ld, waking up queues now!!\n",
+		   netdev->stats.tx_dropped);
+	netdev->trans_start = jiffies;
+	txqs_wake(netdev);
+}
+
+int liquidio_set_feature(struct net_device *netdev, int cmd)
+{
+	struct lio *lio = GET_LIO(netdev);
+	struct octeon_device *oct = lio->oct_dev;
+	struct octnic_ctrl_pkt nctrl;
+	struct octnic_ctrl_params nparams;
+	int ret = 0;
+
+	memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
+
+	nctrl.ncmd.u64 = 0;
+	nctrl.ncmd.s.cmd = cmd;
+	nctrl.ncmd.s.param1 = lio->linfo.ifidx;
+	nctrl.ncmd.s.param2 = OCTNIC_LROIPV4 | OCTNIC_LROIPV6;
+	nctrl.wait_time = 100;
+	nctrl.netpndev = (u64)netdev;
+	nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+
+	nparams.resp_order = OCTEON_RESP_NORESPONSE;
+
+	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl, nparams);
+	if (ret < 0) {
+		dev_err(&oct->pci_dev->dev, "Feature change failed in core (ret: 0x%x)\n",
+			ret);
+	}
+	return ret;
+}
+
+/** \brief Net device fix features
+ * @param netdev  pointer to network device
+ * @param request features requested
+ * @returns updated features list
+ */
+static netdev_features_t liquidio_fix_features(struct net_device *netdev,
+					       netdev_features_t request)
+{
+	struct lio *lio = netdev_priv(netdev);
+
+	if ((request & NETIF_F_RXCSUM) &&
+	    !(lio->dev_capability & NETIF_F_RXCSUM))
+		request &= ~NETIF_F_RXCSUM;
+
+	if ((request & NETIF_F_HW_CSUM) &&
+	    !(lio->dev_capability & NETIF_F_HW_CSUM))
+		request &= ~NETIF_F_HW_CSUM;
+
+	if ((request & NETIF_F_TSO) && !(lio->dev_capability & NETIF_F_TSO))
+		request &= ~NETIF_F_TSO;
+
+	if ((request & NETIF_F_TSO6) && !(lio->dev_capability & NETIF_F_TSO6))
+		request &= ~NETIF_F_TSO6;
+
+	if ((request & NETIF_F_LRO) && !(lio->dev_capability & NETIF_F_LRO))
+		request &= ~NETIF_F_LRO;
+
+	/*Disable LRO if RXCSUM is off */
+	if (!(request & NETIF_F_RXCSUM) && (netdev->features & NETIF_F_LRO) &&
+	    (lio->dev_capability & NETIF_F_LRO))
+		request &= ~NETIF_F_LRO;
+
+	return request;
+}
+
+/** \brief Net device set features
+ * @param netdev  pointer to network device
+ * @param features features to enable/disable
+ */
+static int liquidio_set_features(struct net_device *netdev,
+				 netdev_features_t features)
+{
+	struct lio *lio = netdev_priv(netdev);
+
+	if (!((netdev->features ^ features) & NETIF_F_LRO))
+		return 0;
+
+	if ((features & NETIF_F_LRO) && (lio->dev_capability & NETIF_F_LRO))
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+	else if (!(features & NETIF_F_LRO) &&
+		 (lio->dev_capability & NETIF_F_LRO))
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_DISABLE);
+
+	return 0;
+}
+
+static struct net_device_ops lionetdevops = {
+	.ndo_open		= liquidio_open,
+	.ndo_stop		= liquidio_stop,
+	.ndo_start_xmit		= liquidio_xmit,
+	.ndo_get_stats		= liquidio_get_stats,
+	.ndo_set_mac_address	= liquidio_set_mac,
+	.ndo_set_rx_mode	= liquidio_set_mcast_list,
+	.ndo_tx_timeout		= liquidio_tx_timeout,
+	.ndo_change_mtu		= liquidio_change_mtu,
+	.ndo_do_ioctl		= liquidio_ioctl,
+	.ndo_fix_features	= liquidio_fix_features,
+	.ndo_set_features	= liquidio_set_features,
+};
+
+/** \brief Entry point for the liquidio module
+ */
+static int __init liquidio_init(void)
+{
+	int i;
+	struct handshake *hs;
+
+	init_completion(&first_stage);
+
+	octeon_init_device_list(conf_type);
+
+	if (liquidio_init_pci())
+		return -EINVAL;
+
+	wait_for_completion_timeout(&first_stage, msecs_to_jiffies(1000));
+
+	for (i = 0; i < MAX_OCTEON_DEVICES; i++) {
+		hs = &handshake[i];
+		if (hs->pci_dev) {
+			wait_for_completion(&hs->init);
+			if (!hs->init_ok) {
+				/* init handshake failed */
+				dev_err(&hs->pci_dev->dev,
+					"Failed to init device\n");
+				liquidio_deinit_pci();
+				return -EIO;
+			}
+		}
+	}
+
+	for (i = 0; i < MAX_OCTEON_DEVICES; i++) {
+		hs = &handshake[i];
+		if (hs->pci_dev) {
+			wait_for_completion_timeout(&hs->started,
+						    msecs_to_jiffies(30000));
+			if (!hs->started_ok) {
+				/* starter handshake failed */
+				dev_err(&hs->pci_dev->dev,
+					"Firmware failed to start\n");
+				liquidio_deinit_pci();
+				return -EIO;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf)
+{
+	struct octeon_device *oct = (struct octeon_device *)buf;
+	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
+	int ifidx = 0;
+	union oct_link_status *ls;
+	int i;
+
+	if ((recv_pkt->buffer_size[0] != sizeof(*ls)) ||
+	    (recv_pkt->rh.r_nic_info.ifidx > oct->ifcount)) {
+		dev_err(&oct->pci_dev->dev, "Malformed NIC_INFO, len=%d, ifidx=%d\n",
+			recv_pkt->buffer_size[0],
+			recv_pkt->rh.r_nic_info.ifidx);
+		goto nic_info_err;
+	}
+
+	ifidx = recv_pkt->rh.r_nic_info.ifidx;
+	ls = (union oct_link_status *)get_rbd(recv_pkt->buffer_ptr[0]);
+
+	octeon_swap_8B_data((u64 *)ls, (sizeof(union oct_link_status)) >> 3);
+
+	update_link_status(oct->props[ifidx].netdev, ls);
+
+nic_info_err:
+	for (i = 0; i < recv_pkt->buffer_count; i++)
+		recv_buffer_free(recv_pkt->buffer_ptr[i]);
+	octeon_free_recv_info(recv_info);
+	return 0;
+}
+
+/**
+ * \brief Setup network interfaces
+ * @param octeon_dev  octeon device
+ *
+ * Called during init time for each device. It assumes the NIC
+ * is already up and running.  The link information for each
+ * interface is passed in link_info.
+ */
+static int setup_nic_devices(struct octeon_device *octeon_dev)
+{
+	struct lio *lio = NULL;
+	struct net_device *netdev;
+	u8 mac[6], i, j;
+	struct octeon_soft_command *sc;
+	struct liquidio_if_cfg_context *ctx;
+	struct liquidio_if_cfg_resp *resp;
+	struct octdev_props *props;
+	int retval, num_iqueues, num_oqueues, q_no;
+	u64 q_mask;
+	int num_cpus = num_online_cpus();
+	union oct_nic_if_cfg if_cfg;
+	unsigned int base_queue;
+	unsigned int gmx_port_id;
+	u32 resp_size, ctx_size;
+
+	/* This is to handle link status changes */
+	octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
+				    OPCODE_NIC_INFO,
+				    lio_nic_info, octeon_dev);
+
+	/* REQTYPE_RESP_NET and REQTYPE_SOFT_COMMAND do not have free functions.
+	 * They are handled directly.
+	 */
+	octeon_register_reqtype_free_fn(octeon_dev, REQTYPE_NORESP_NET,
+					free_netbuf);
+
+	octeon_register_reqtype_free_fn(octeon_dev, REQTYPE_NORESP_NET_SG,
+					free_netsgbuf);
+
+	octeon_register_reqtype_free_fn(octeon_dev, REQTYPE_RESP_NET_SG,
+					free_netsgbuf_with_resp);
+
+	for (i = 0; i < octeon_dev->ifcount; i++) {
+		resp_size = sizeof(struct liquidio_if_cfg_resp);
+		ctx_size = sizeof(struct liquidio_if_cfg_context);
+		sc = (struct octeon_soft_command *)
+			octeon_alloc_soft_command(octeon_dev, 0,
+						  resp_size, ctx_size);
+		resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
+		ctx  = (struct liquidio_if_cfg_context *)sc->ctxptr;
+
+		num_iqueues =
+			CFG_GET_NUM_TXQS_NIC_IF(octeon_get_conf(octeon_dev), i);
+		num_oqueues =
+			CFG_GET_NUM_RXQS_NIC_IF(octeon_get_conf(octeon_dev), i);
+		base_queue =
+			CFG_GET_BASE_QUE_NIC_IF(octeon_get_conf(octeon_dev), i);
+		gmx_port_id =
+			CFG_GET_GMXID_NIC_IF(octeon_get_conf(octeon_dev), i);
+		if (num_iqueues > num_cpus)
+			num_iqueues = num_cpus;
+		if (num_oqueues > num_cpus)
+			num_oqueues = num_cpus;
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"requesting config for interface %d, iqs %d, oqs %d\n",
+			i, num_iqueues, num_oqueues);
+		ACCESS_ONCE(ctx->cond) = 0;
+		ctx->octeon_id = lio_get_device_id(octeon_dev);
+		init_waitqueue_head(&ctx->wc);
+
+		if_cfg.u64 = 0;
+		if_cfg.s.num_iqueues = num_iqueues;
+		if_cfg.s.num_oqueues = num_oqueues;
+		if_cfg.s.base_queue = base_queue;
+		if_cfg.s.gmx_port_id = gmx_port_id;
+		octeon_prepare_soft_command(octeon_dev, sc, OPCODE_NIC,
+					    OPCODE_NIC_IF_CFG, i,
+					    if_cfg.u64, 0);
+
+		sc->callback = if_cfg_callback;
+		sc->callback_arg = sc;
+		sc->wait_time = 1000;
+
+		retval = octeon_send_soft_command(octeon_dev, sc);
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				"iq/oq config failed status: %x\n",
+				retval);
+			/* Soft instr is freed by driver in case of failure. */
+			goto setup_nic_dev_fail;
+		}
+
+		/* Sleep on a wait queue till the cond flag indicates that the
+		 * response arrived or timed-out.
+		 */
+		sleep_cond(&ctx->wc, &ctx->cond);
+		retval = resp->status;
+		if (retval) {
+			dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed\n");
+			goto setup_nic_dev_fail;
+		}
+
+		octeon_swap_8B_data((u64 *)(&resp->cfg_info),
+				    (sizeof(struct liquidio_if_cfg_info)) >> 3);
+
+		num_iqueues = hweight64(resp->cfg_info.iqmask);
+		num_oqueues = hweight64(resp->cfg_info.oqmask);
+
+		if (!(num_iqueues) || !(num_oqueues)) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				"Got bad iqueues (%016llx) or oqueues (%016llx) from firmware.\n",
+				resp->cfg_info.iqmask,
+				resp->cfg_info.oqmask);
+			goto setup_nic_dev_fail;
+		}
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d\n",
+			i, resp->cfg_info.iqmask, resp->cfg_info.oqmask,
+			num_iqueues, num_oqueues);
+		netdev = alloc_etherdev_mq(LIO_SIZE, num_iqueues);
+
+		if (!netdev) {
+			dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n");
+			goto setup_nic_dev_fail;
+		}
+
+		props = &octeon_dev->props[i];
+		props->netdev = netdev;
+
+		if (num_iqueues > 1)
+			lionetdevops.ndo_select_queue = select_q;
+
+		/* Associate the routines that will handle different
+		 * netdev tasks.
+		 */
+		netdev->netdev_ops = &lionetdevops;
+
+		lio = GET_LIO(netdev);
+
+		memset(lio, 0, sizeof(struct lio));
+
+		lio->linfo.ifidx = resp->cfg_info.ifidx;
+		lio->ifidx = resp->cfg_info.ifidx;
+
+		lio->linfo.num_rxpciq = num_oqueues;
+		lio->linfo.num_txpciq = num_iqueues;
+		q_mask = resp->cfg_info.oqmask;
+		/* q_mask is 0-based and already verified mask is nonzero */
+		for (j = 0; j < num_oqueues; j++) {
+			q_no = __ffs64(q_mask);
+			q_mask &= (~(1UL << q_no));
+			lio->linfo.rxpciq[j] = q_no;
+		}
+		q_mask = resp->cfg_info.iqmask;
+		for (j = 0; j < num_iqueues; j++) {
+			q_no = __ffs64(q_mask);
+			q_mask &= (~(1UL << q_no));
+			lio->linfo.txpciq[j] = q_no;
+		}
+		lio->linfo.hw_addr = resp->cfg_info.linfo.hw_addr;
+		lio->linfo.gmxport = resp->cfg_info.linfo.gmxport;
+		lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64;
+
+		lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
+
+		lio->dev_capability = NETIF_F_HIGHDMA
+				      | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
+				      | NETIF_F_SG | NETIF_F_RXCSUM
+				      | NETIF_F_TSO | NETIF_F_TSO6
+				      | NETIF_F_LRO;
+		netif_set_gso_max_size(netdev, OCTNIC_GSO_MAX_SIZE);
+
+		netdev->features = lio->dev_capability;
+		netdev->vlan_features = lio->dev_capability;
+
+		netdev->hw_features = lio->dev_capability;
+
+		/* Point to the  properties for octeon device to which this
+		 * interface belongs.
+		 */
+		lio->oct_dev = octeon_dev;
+		lio->octprops = props;
+		lio->netdev = netdev;
+		spin_lock_init(&lio->lock);
+
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"if%d gmx: %d hw_addr: 0x%llx\n", i,
+			lio->linfo.gmxport, CVM_CAST64(lio->linfo.hw_addr));
+
+		/* 64-bit swap required on LE machines */
+		octeon_swap_8B_data(&lio->linfo.hw_addr, 1);
+		for (j = 0; j < 6; j++)
+			mac[j] = *((u8 *)(((u8 *)&lio->linfo.hw_addr) + 2 + j));
+
+		/* Copy MAC Address to OS network device structure */
+
+		ether_addr_copy(netdev->dev_addr, mac);
+
+		if (setup_io_queues(octeon_dev, netdev)) {
+			dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n");
+			goto setup_nic_dev_fail;
+		}
+
+		ifstate_set(lio, LIO_IFSTATE_DROQ_OPS);
+
+		/* By default all interfaces on a single Octeon uses the same
+		 * tx and rx queues
+		 */
+		lio->txq = lio->linfo.txpciq[0];
+		lio->rxq = lio->linfo.rxpciq[0];
+
+		lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq);
+		lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq);
+
+		if (setup_glist(lio)) {
+			dev_err(&octeon_dev->pci_dev->dev,
+				"Gather list allocation failed\n");
+			goto setup_nic_dev_fail;
+		}
+
+		/* Register ethtool support */
+		liquidio_set_ethtool_ops(netdev);
+
+		liquidio_set_feature(netdev, OCTNET_CMD_LRO_ENABLE);
+
+		if ((debug != -1) && (debug & NETIF_MSG_HW))
+			liquidio_set_feature(netdev, OCTNET_CMD_VERBOSE_ENABLE);
+
+		/* Register the network device with the OS */
+		if (register_netdev(netdev)) {
+			dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
+			goto setup_nic_dev_fail;
+		}
+
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"Setup NIC ifidx:%d mac:%02x%02x%02x%02x%02x%02x\n",
+			i, mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+		netif_carrier_off(netdev);
+
+		if (lio->linfo.link.s.status) {
+			netif_carrier_on(netdev);
+			start_txq(netdev);
+		} else {
+			netif_carrier_off(netdev);
+		}
+
+		ifstate_set(lio, LIO_IFSTATE_REGISTERED);
+
+		dev_dbg(&octeon_dev->pci_dev->dev,
+			"NIC ifidx:%d Setup successful\n", i);
+
+		octeon_free_soft_command(octeon_dev, sc);
+	}
+
+	return 0;
+
+setup_nic_dev_fail:
+
+	octeon_free_soft_command(octeon_dev, sc);
+
+	while (i--) {
+		dev_err(&octeon_dev->pci_dev->dev,
+			"NIC ifidx:%d Setup failed\n", i);
+		liquidio_destroy_nic_device(octeon_dev, i);
+	}
+	return -ENODEV;
+}
+
+/**
+ * \brief initialize the NIC
+ * @param oct octeon device
+ *
+ * This initialization routine is called once the Octeon device application is
+ * up and running
+ */
+static int liquidio_init_nic_module(struct octeon_device *oct)
+{
+	struct oct_intrmod_cfg *intrmod_cfg;
+	int retval = 0;
+	int num_nic_ports = CFG_GET_NUM_NIC_PORTS(octeon_get_conf(oct));
+
+	dev_dbg(&oct->pci_dev->dev, "Initializing network interfaces\n");
+
+	/* only default iq and oq were initialized
+	 * initialize the rest as well
+	 */
+	/* run port_config command for each port */
+	oct->ifcount = num_nic_ports;
+
+	memset(oct->props, 0,
+	       sizeof(struct octdev_props) * num_nic_ports);
+
+	retval = setup_nic_devices(oct);
+	if (retval) {
+		dev_err(&oct->pci_dev->dev, "Setup NIC devices failed\n");
+		goto octnet_init_failure;
+	}
+
+	liquidio_ptp_init(oct);
+
+	/* Initialize interrupt moderation params */
+	intrmod_cfg = &((struct octeon_device *)oct)->intrmod;
+	intrmod_cfg->intrmod_enable = 1;
+	intrmod_cfg->intrmod_check_intrvl = LIO_INTRMOD_CHECK_INTERVAL;
+	intrmod_cfg->intrmod_maxpkt_ratethr = LIO_INTRMOD_MAXPKT_RATETHR;
+	intrmod_cfg->intrmod_minpkt_ratethr = LIO_INTRMOD_MINPKT_RATETHR;
+	intrmod_cfg->intrmod_maxcnt_trigger = LIO_INTRMOD_MAXCNT_TRIGGER;
+	intrmod_cfg->intrmod_maxtmr_trigger = LIO_INTRMOD_MAXTMR_TRIGGER;
+	intrmod_cfg->intrmod_mintmr_trigger = LIO_INTRMOD_MINTMR_TRIGGER;
+	intrmod_cfg->intrmod_mincnt_trigger = LIO_INTRMOD_MINCNT_TRIGGER;
+
+	dev_dbg(&oct->pci_dev->dev, "Network interfaces ready\n");
+
+	return retval;
+
+octnet_init_failure:
+
+	oct->ifcount = 0;
+
+	return retval;
+}
+
+/**
+ * \brief starter callback that invokes the remaining initialization work after
+ * the NIC is up and running.
+ * @param octptr  work struct work_struct
+ */
+static void nic_starter(struct work_struct *work)
+{
+	struct octeon_device *oct;
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+
+	oct = (struct octeon_device *)wk->ctxptr;
+
+	if (atomic_read(&oct->status) == OCT_DEV_RUNNING)
+		return;
+
+	/* If the status of the device is CORE_OK, the core
+	 * application has reported its application type. Call
+	 * any registered handlers now and move to the RUNNING
+	 * state.
+	 */
+	if (atomic_read(&oct->status) != OCT_DEV_CORE_OK) {
+		schedule_delayed_work(&oct->nic_poll_work.work,
+				      LIQUIDIO_STARTER_POLL_INTERVAL_MS);
+		return;
+	}
+
+	atomic_set(&oct->status, OCT_DEV_RUNNING);
+
+	if (oct->app_mode && oct->app_mode == CVM_DRV_NIC_APP) {
+		dev_dbg(&oct->pci_dev->dev, "Starting NIC module\n");
+
+		if (liquidio_init_nic_module(oct))
+			dev_err(&oct->pci_dev->dev, "NIC initialization failed\n");
+		else
+			handshake[oct->octeon_id].started_ok = 1;
+	} else {
+		dev_err(&oct->pci_dev->dev,
+			"Unexpected application running on NIC (%d). Check firmware.\n",
+			oct->app_mode);
+	}
+
+	complete(&handshake[oct->octeon_id].started);
+}
+
+/**
+ * \brief Device initialization for each Octeon device that is probed
+ * @param octeon_dev  octeon device
+ */
+static int octeon_device_init(struct octeon_device *octeon_dev)
+{
+	int j, ret;
+	struct octeon_device_priv *oct_priv =
+		(struct octeon_device_priv *)octeon_dev->priv;
+	atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE);
+
+	/* Enable access to the octeon device and make its DMA capability
+	 * known to the OS.
+	 */
+	if (octeon_pci_os_setup(octeon_dev))
+		return 1;
+
+	/* Identify the Octeon type and map the BAR address space. */
+	if (octeon_chip_specific_setup(octeon_dev)) {
+		dev_err(&octeon_dev->pci_dev->dev, "Chip specific setup failed\n");
+		return 1;
+	}
+
+	atomic_set(&octeon_dev->status, OCT_DEV_PCI_MAP_DONE);
+
+	octeon_dev->app_mode = CVM_DRV_INVALID_APP;
+
+	/* Do a soft reset of the Octeon device. */
+	if (octeon_dev->fn_list.soft_reset(octeon_dev))
+		return 1;
+
+	/* Initialize the dispatch mechanism used to push packets arriving on
+	 * Octeon Output queues.
+	 */
+	if (octeon_init_dispatch_list(octeon_dev))
+		return 1;
+
+	octeon_register_dispatch_fn(octeon_dev, OPCODE_NIC,
+				    OPCODE_NIC_CORE_DRV_ACTIVE,
+				    octeon_core_drv_init,
+				    octeon_dev);
+
+	INIT_DELAYED_WORK(&octeon_dev->nic_poll_work.work, nic_starter);
+	octeon_dev->nic_poll_work.ctxptr = (void *)octeon_dev;
+	schedule_delayed_work(&octeon_dev->nic_poll_work.work,
+			      LIQUIDIO_STARTER_POLL_INTERVAL_MS);
+
+	atomic_set(&octeon_dev->status, OCT_DEV_DISPATCH_INIT_DONE);
+
+	octeon_set_io_queues_off(octeon_dev);
+
+	/*  Setup the data structures that manage this Octeon's Input queues. */
+	if (octeon_setup_instr_queues(octeon_dev)) {
+		dev_err(&octeon_dev->pci_dev->dev,
+			"instruction queue initialization failed\n");
+		/* On error, release any previously allocated queues */
+		for (j = 0; j < octeon_dev->num_iqs; j++)
+			octeon_delete_instr_queue(octeon_dev, j);
+		return 1;
+	}
+	atomic_set(&octeon_dev->status, OCT_DEV_INSTR_QUEUE_INIT_DONE);
+
+	/* Initialize soft command buffer pool
+	 */
+	if (octeon_setup_sc_buffer_pool(octeon_dev)) {
+		dev_err(&octeon_dev->pci_dev->dev, "sc buffer pool allocation failed\n");
+		return 1;
+	}
+	atomic_set(&octeon_dev->status, OCT_DEV_SC_BUFF_POOL_INIT_DONE);
+
+	/* Initialize lists to manage the requests of different types that
+	 * arrive from user & kernel applications for this octeon device.
+	 */
+	if (octeon_setup_response_list(octeon_dev)) {
+		dev_err(&octeon_dev->pci_dev->dev, "Response list allocation failed\n");
+		return 1;
+	}
+	atomic_set(&octeon_dev->status, OCT_DEV_RESP_LIST_INIT_DONE);
+
+	if (octeon_setup_output_queues(octeon_dev)) {
+		dev_err(&octeon_dev->pci_dev->dev, "Output queue initialization failed\n");
+		/* Release any previously allocated queues */
+		for (j = 0; j < octeon_dev->num_oqs; j++)
+			octeon_delete_droq(octeon_dev, j);
+	}
+
+	atomic_set(&octeon_dev->status, OCT_DEV_DROQ_INIT_DONE);
+
+	/* The input and output queue registers were setup earlier (the queues
+	 * were not enabled). Any additional registers that need to be
+	 * programmed should be done now.
+	 */
+	ret = octeon_dev->fn_list.setup_device_regs(octeon_dev);
+	if (ret) {
+		dev_err(&octeon_dev->pci_dev->dev,
+			"Failed to configure device registers\n");
+		return ret;
+	}
+
+	/* Initialize the tasklet that handles output queue packet processing.*/
+	dev_dbg(&octeon_dev->pci_dev->dev, "Initializing droq tasklet\n");
+	tasklet_init(&oct_priv->droq_tasklet, octeon_droq_bh,
+		     (unsigned long)octeon_dev);
+
+	/* Setup the interrupt handler and record the INT SUM register address
+	 */
+	octeon_setup_interrupt(octeon_dev);
+
+	/* Enable Octeon device interrupts */
+	octeon_dev->fn_list.enable_interrupt(octeon_dev->chip);
+
+	/* Enable the input and output queues for this Octeon device */
+	octeon_dev->fn_list.enable_io_queues(octeon_dev);
+
+	atomic_set(&octeon_dev->status, OCT_DEV_IO_QUEUES_DONE);
+
+	dev_dbg(&octeon_dev->pci_dev->dev, "Waiting for DDR initialization...\n");
+
+	if (ddr_timeout == 0) {
+		dev_info(&octeon_dev->pci_dev->dev,
+			 "WAITING. Set ddr_timeout to non-zero value to proceed with initialization.\n");
+	}
+
+	schedule_timeout_uninterruptible(HZ * LIO_RESET_SECS);
+
+	/* Wait for the octeon to initialize DDR after the soft-reset. */
+	ret = octeon_wait_for_ddr_init(octeon_dev, &ddr_timeout);
+	if (ret) {
+		dev_err(&octeon_dev->pci_dev->dev,
+			"DDR not initialized. Please confirm that board is configured to boot from Flash, ret: %d\n",
+			ret);
+		return 1;
+	}
+
+	if (octeon_wait_for_bootloader(octeon_dev, 1000) != 0) {
+		dev_err(&octeon_dev->pci_dev->dev, "Board not responding\n");
+		return 1;
+	}
+
+	dev_dbg(&octeon_dev->pci_dev->dev, "Initializing consoles\n");
+	ret = octeon_init_consoles(octeon_dev);
+	if (ret) {
+		dev_err(&octeon_dev->pci_dev->dev, "Could not access board consoles\n");
+		return 1;
+	}
+	ret = octeon_add_console(octeon_dev, 0);
+	if (ret) {
+		dev_err(&octeon_dev->pci_dev->dev, "Could not access board console\n");
+		return 1;
+	}
+
+	atomic_set(&octeon_dev->status, OCT_DEV_CONSOLE_INIT_DONE);
+
+	dev_dbg(&octeon_dev->pci_dev->dev, "Loading firmware\n");
+	ret = load_firmware(octeon_dev);
+	if (ret) {
+		dev_err(&octeon_dev->pci_dev->dev, "Could not load firmware to board\n");
+		return 1;
+	}
+
+	handshake[octeon_dev->octeon_id].init_ok = 1;
+	complete(&handshake[octeon_dev->octeon_id].init);
+
+	atomic_set(&octeon_dev->status, OCT_DEV_HOST_OK);
+
+	/* Send Credit for Octeon Output queues. Credits are always sent after
+	 * the output queue is enabled.
+	 */
+	for (j = 0; j < octeon_dev->num_oqs; j++)
+		writel(octeon_dev->droq[j]->max_count,
+		       octeon_dev->droq[j]->pkts_credit_reg);
+
+	/* Packets can start arriving on the output queues from this point. */
+
+	return 0;
+}
+
+/**
+ * \brief Exits the module
+ */
+static void __exit liquidio_exit(void)
+{
+	liquidio_deinit_pci();
+
+	pr_info("LiquidIO network module is now unloaded\n");
+}
+
+module_init(liquidio_init);
+module_exit(liquidio_exit);
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
new file mode 100644
index 000000000000..0ac347ccc8ba
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -0,0 +1,673 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*!  \file  liquidio_common.h
+ *   \brief Common: Structures and macros used in PCI-NIC package by core and
+ *   host driver.
+ */
+
+#ifndef __LIQUIDIO_COMMON_H__
+#define __LIQUIDIO_COMMON_H__
+
+#include "octeon_config.h"
+
+#define LIQUIDIO_VERSION        "1.1.9"
+#define LIQUIDIO_MAJOR_VERSION  1
+#define LIQUIDIO_MINOR_VERSION  1
+#define LIQUIDIO_MICRO_VERSION  9
+
+#define CONTROL_IQ 0
+/** Tag types used by Octeon cores in its work. */
+enum octeon_tag_type {
+	ORDERED_TAG = 0,
+	ATOMIC_TAG = 1,
+	NULL_TAG = 2,
+	NULL_NULL_TAG = 3
+};
+
+/* pre-defined host->NIC tag values */
+#define LIO_CONTROL  (0x11111110)
+#define LIO_DATA(i)  (0x11111111 + (i))
+
+/* Opcodes used by host driver/apps to perform operations on the core.
+ * These are used to identify the major subsystem that the operation
+ * is for.
+ */
+#define OPCODE_CORE 0           /* used for generic core operations */
+#define OPCODE_NIC  1           /* used for NIC operations */
+#define OPCODE_LAST OPCODE_NIC
+
+/* Subcodes are used by host driver/apps to identify the sub-operation
+ * for the core. They only need to by unique for a given subsystem.
+ */
+#define OPCODE_SUBCODE(op, sub)       (((op & 0x0f) << 8) | ((sub) & 0x7f))
+
+/** OPCODE_CORE subcodes. For future use. */
+
+/** OPCODE_NIC subcodes */
+
+/* This subcode is sent by core PCI driver to indicate cores are ready. */
+#define OPCODE_NIC_CORE_DRV_ACTIVE     0x01
+#define OPCODE_NIC_NW_DATA             0x02     /* network packet data */
+#define OPCODE_NIC_CMD                 0x03
+#define OPCODE_NIC_INFO                0x04
+#define OPCODE_NIC_PORT_STATS          0x05
+#define OPCODE_NIC_MDIO45              0x06
+#define OPCODE_NIC_TIMESTAMP           0x07
+#define OPCODE_NIC_INTRMOD_CFG         0x08
+#define OPCODE_NIC_IF_CFG              0x09
+
+#define CORE_DRV_TEST_SCATTER_OP    0xFFF5
+
+#define OPCODE_SLOW_PATH(rh)  \
+	(OPCODE_SUBCODE(rh->r.opcode, rh->r.subcode) != \
+		OPCODE_SUBCODE(OPCODE_NIC, OPCODE_NIC_NW_DATA))
+
+/* Application codes advertised by the core driver initialization packet. */
+#define CVM_DRV_APP_START           0x0
+#define CVM_DRV_NO_APP              0
+#define CVM_DRV_APP_COUNT           0x2
+#define CVM_DRV_BASE_APP            (CVM_DRV_APP_START + 0x0)
+#define CVM_DRV_NIC_APP             (CVM_DRV_APP_START + 0x1)
+#define CVM_DRV_INVALID_APP         (CVM_DRV_APP_START + 0x2)
+#define CVM_DRV_APP_END             (CVM_DRV_INVALID_APP - 1)
+
+/* Macro to increment index.
+ * Index is incremented by count; if the sum exceeds
+ * max, index is wrapped-around to the start.
+ */
+#define INCR_INDEX(index, count, max)                \
+do {                                                 \
+	if (((index) + (count)) >= (max))            \
+		index = ((index) + (count)) - (max); \
+	else                                         \
+		index += (count);                    \
+} while (0)
+
+#define INCR_INDEX_BY1(index, max)	\
+do {                                    \
+	if ((++(index)) == (max))       \
+		index = 0;	        \
+} while (0)
+
+#define DECR_INDEX(index, count, max)                  \
+do {						       \
+	if ((count) > (index))                         \
+		index = ((max) - ((count - index)));   \
+	else                                           \
+		index -= count;			       \
+} while (0)
+
+#define OCT_BOARD_NAME 32
+#define OCT_SERIAL_LEN 64
+
+/* Structure used by core driver to send indication that the Octeon
+ * application is ready.
+ */
+struct octeon_core_setup {
+	u64 corefreq;
+
+	char boardname[OCT_BOARD_NAME];
+
+	char board_serial_number[OCT_SERIAL_LEN];
+
+	u64 board_rev_major;
+
+	u64 board_rev_minor;
+
+};
+
+/*---------------------------  SCATTER GATHER ENTRY  -----------------------*/
+
+/* The Scatter-Gather List Entry. The scatter or gather component used with
+ * a Octeon input instruction has this format.
+ */
+struct octeon_sg_entry {
+	/** The first 64 bit gives the size of data in each dptr.*/
+	union {
+		u16 size[4];
+		u64 size64;
+	} u;
+
+	/** The 4 dptr pointers for this entry. */
+	u64 ptr[4];
+
+};
+
+#define OCT_SG_ENTRY_SIZE    (sizeof(struct octeon_sg_entry))
+
+/* \brief Add size to gather list
+ * @param sg_entry scatter/gather entry
+ * @param size size to add
+ * @param pos position to add it.
+ */
+static inline void add_sg_size(struct octeon_sg_entry *sg_entry,
+			       u16 size,
+			       u32 pos)
+{
+#ifdef __BIG_ENDIAN_BITFIELD
+	sg_entry->u.size[pos] = size;
+#else
+	sg_entry->u.size[3 - pos] = size;
+#endif
+}
+
+/*------------------------- End Scatter/Gather ---------------------------*/
+
+#define   OCTNET_FRM_PTP_HEADER_SIZE  8
+#define   OCTNET_FRM_HEADER_SIZE     30 /* PTP timestamp + VLAN + Ethernet */
+
+#define   OCTNET_MIN_FRM_SIZE        (64  + OCTNET_FRM_PTP_HEADER_SIZE)
+#define   OCTNET_MAX_FRM_SIZE        (16000 + OCTNET_FRM_HEADER_SIZE)
+
+#define   OCTNET_DEFAULT_FRM_SIZE    (1500 + OCTNET_FRM_HEADER_SIZE)
+
+/** NIC Commands are sent using this Octeon Input Queue */
+#define   OCTNET_CMD_Q                0
+
+/* NIC Command types */
+#define   OCTNET_CMD_CHANGE_MTU       0x1
+#define   OCTNET_CMD_CHANGE_MACADDR   0x2
+#define   OCTNET_CMD_CHANGE_DEVFLAGS  0x3
+#define   OCTNET_CMD_RX_CTL           0x4
+
+#define	  OCTNET_CMD_SET_MULTI_LIST   0x5
+#define   OCTNET_CMD_CLEAR_STATS      0x6
+
+/* command for setting the speed, duplex & autoneg */
+#define   OCTNET_CMD_SET_SETTINGS     0x7
+#define   OCTNET_CMD_SET_FLOW_CTL     0x8
+
+#define   OCTNET_CMD_MDIO_READ_WRITE  0x9
+#define   OCTNET_CMD_GPIO_ACCESS      0xA
+#define   OCTNET_CMD_LRO_ENABLE       0xB
+#define   OCTNET_CMD_LRO_DISABLE      0xC
+#define   OCTNET_CMD_SET_RSS          0xD
+#define   OCTNET_CMD_WRITE_SA         0xE
+#define   OCTNET_CMD_DELETE_SA        0xF
+#define   OCTNET_CMD_UPDATE_SA        0x12
+
+#define   OCTNET_CMD_TNL_RX_CSUM_CTL 0x10
+#define   OCTNET_CMD_TNL_TX_CSUM_CTL 0x11
+#define   OCTNET_CMD_IPSECV2_AH_ESP_CTL 0x13
+#define   OCTNET_CMD_VERBOSE_ENABLE   0x14
+#define   OCTNET_CMD_VERBOSE_DISABLE  0x15
+
+/* RX(packets coming from wire) Checksum verification flags */
+/* TCP/UDP csum */
+#define   CNNIC_L4SUM_VERIFIED             0x1
+#define   CNNIC_IPSUM_VERIFIED             0x2
+#define   CNNIC_TUN_CSUM_VERIFIED          0x4
+#define   CNNIC_CSUM_VERIFIED (CNNIC_IPSUM_VERIFIED | CNNIC_L4SUM_VERIFIED)
+
+/*LROIPV4 and LROIPV6 Flags*/
+#define   OCTNIC_LROIPV4    0x1
+#define   OCTNIC_LROIPV6    0x2
+
+/* Interface flags communicated between host driver and core app. */
+enum octnet_ifflags {
+	OCTNET_IFFLAG_PROMISC   = 0x01,
+	OCTNET_IFFLAG_ALLMULTI  = 0x02,
+	OCTNET_IFFLAG_MULTICAST = 0x04,
+	OCTNET_IFFLAG_BROADCAST = 0x08,
+	OCTNET_IFFLAG_UNICAST   = 0x10
+};
+
+/*   wqe
+ *  ---------------  0
+ * |  wqe  word0-3 |
+ *  ---------------  32
+ * |    PCI IH     |
+ *  ---------------  40
+ * |     RPTR      |
+ *  ---------------  48
+ * |    PCI IRH    |
+ *  ---------------  56
+ * |  OCT_NET_CMD  |
+ *  ---------------  64
+ * | Addtl 8-BData |
+ * |               |
+ *  ---------------
+ */
+
+union octnet_cmd {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 cmd:5;
+
+		u64 more:6; /* How many udd words follow the command */
+
+		u64 param1:29;
+
+		u64 param2:16;
+
+		u64 param3:8;
+
+#else
+
+		u64 param3:8;
+
+		u64 param2:16;
+
+		u64 param1:29;
+
+		u64 more:6;
+
+		u64 cmd:5;
+
+#endif
+	} s;
+
+};
+
+#define   OCTNET_CMD_SIZE     (sizeof(union octnet_cmd))
+
+/** Instruction Header */
+struct octeon_instr_ih {
+#ifdef __BIG_ENDIAN_BITFIELD
+	/** Raw mode indicator 1 = RAW */
+	u64 raw:1;
+
+	/** Gather indicator 1=gather*/
+	u64 gather:1;
+
+	/** Data length OR no. of entries in gather list */
+	u64 dlengsz:14;
+
+	/** Front Data size */
+	u64 fsz:6;
+
+	/** Packet Order / Work Unit selection (1 of 8)*/
+	u64 qos:3;
+
+	/** Core group selection (1 of 16) */
+	u64 grp:4;
+
+	/** Short Raw Packet Indicator 1=short raw pkt */
+	u64 rs:1;
+
+	/** Tag type */
+	u64 tagtype:2;
+
+	/** Tag Value */
+	u64 tag:32;
+#else
+	/** Tag Value */
+	u64 tag:32;
+
+	/** Tag type */
+	u64 tagtype:2;
+
+	/** Short Raw Packet Indicator 1=short raw pkt */
+	u64 rs:1;
+
+	/** Core group selection (1 of 16) */
+	u64 grp:4;
+
+	/** Packet Order / Work Unit selection (1 of 8)*/
+	u64 qos:3;
+
+	/** Front Data size */
+	u64 fsz:6;
+
+	/** Data length OR no. of entries in gather list */
+	u64 dlengsz:14;
+
+	/** Gather indicator 1=gather*/
+	u64 gather:1;
+
+	/** Raw mode indicator 1 = RAW */
+	u64 raw:1;
+#endif
+};
+
+/** Input Request Header */
+struct octeon_instr_irh {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 opcode:4;
+	u64 rflag:1;
+	u64 subcode:7;
+	u64 len:3;
+	u64 rid:13;
+	u64 reserved:4;
+	u64 ossp:32;             /* opcode/subcode specific parameters */
+#else
+	u64 ossp:32;             /* opcode/subcode specific parameters */
+	u64 reserved:4;
+	u64 rid:13;
+	u64 len:3;
+	u64 subcode:7;
+	u64 rflag:1;
+	u64 opcode:4;
+#endif
+};
+
+/** Return Data Parameters */
+struct octeon_instr_rdp {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 reserved:49;
+	u64 pcie_port:3;
+	u64 rlen:12;
+#else
+	u64 rlen:12;
+	u64 pcie_port:3;
+	u64 reserved:49;
+#endif
+};
+
+/** Receive Header */
+union octeon_rh {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 u64;
+	struct {
+		u64 opcode:4;
+		u64 subcode:8;
+		u64 len:3;       /** additional 64-bit words */
+		u64 rid:13;      /** request id in response to pkt sent by host */
+		u64 reserved:4;
+		u64 ossp:32;     /** opcode/subcode specific parameters */
+	} r;
+	struct {
+		u64 opcode:4;
+		u64 subcode:8;
+		u64 len:3;       /** additional 64-bit words */
+		u64 rid:13;      /** request id in response to pkt sent by host */
+		u64 extra:24;
+		u64 link:8;
+		u64 csum_verified:3;     /** checksum verified. */
+		u64 has_hwtstamp:1;      /** Has hardware timestamp. 1 = yes. */
+	} r_dh;
+	struct {
+		u64 opcode:4;
+		u64 subcode:8;
+		u64 len:3;       /** additional 64-bit words */
+		u64 rid:13;      /** request id in response to pkt sent by host */
+		u64 num_gmx_ports:8;
+		u64 max_nic_ports:8;
+		u64 app_cap_flags:4;
+		u64 app_mode:16;
+	} r_core_drv_init;
+	struct {
+		u64 opcode:4;
+		u64 subcode:8;
+		u64 len:3;       /** additional 64-bit words */
+		u64 rid:13;
+		u64 reserved:4;
+		u64 extra:25;
+		u64 ifidx:7;
+	} r_nic_info;
+#else
+	u64 u64;
+	struct {
+		u64 ossp:32;  /** opcode/subcode specific parameters */
+		u64 reserved:4;
+		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 len:3;    /** additional 64-bit words */
+		u64 subcode:8;
+		u64 opcode:4;
+	} r;
+	struct {
+		u64 has_hwtstamp:1;      /** 1 = has hwtstamp */
+		u64 csum_verified:3;     /** checksum verified. */
+		u64 link:8;
+		u64 extra:24;
+		u64 rid:13;   /** req id in response to pkt sent by host */
+		u64 len:3;    /** additional 64-bit words */
+		u64 subcode:8;
+		u64 opcode:4;
+	} r_dh;
+	struct {
+		u64 app_mode:16;
+		u64 app_cap_flags:4;
+		u64 max_nic_ports:8;
+		u64 num_gmx_ports:8;
+		u64 rid:13;
+		u64 len:3;       /** additional 64-bit words */
+		u64 subcode:8;
+		u64 opcode:4;
+	} r_core_drv_init;
+	struct {
+		u64 ifidx:7;
+		u64 extra:25;
+		u64 reserved:4;
+		u64 rid:13;
+		u64 len:3;       /** additional 64-bit words */
+		u64 subcode:8;
+		u64 opcode:4;
+	} r_nic_info;
+#endif
+};
+
+#define  OCT_RH_SIZE   (sizeof(union  octeon_rh))
+
+#define OCT_PKT_PARAM_IPV4OPTS   1
+#define OCT_PKT_PARAM_IPV6EXTHDR 2
+
+union octnic_packet_params {
+	u32 u32;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u32 reserved:6;
+		u32 tnl_csum:1;
+		u32 ip_csum:1;
+		u32 ipv4opts_ipv6exthdr:2;
+		u32 ipsec_ops:4;
+		u32 tsflag:1;
+		u32 csoffset:9;
+		u32 ifidx:8;
+#else
+		u32 ifidx:8;
+		u32 csoffset:9;
+		u32 tsflag:1;
+		u32 ipsec_ops:4;
+		u32 ipv4opts_ipv6exthdr:2;
+		u32 ip_csum:1;
+		u32 tnl_csum:1;
+		u32 reserved:6;
+#endif
+	} s;
+};
+
+/** Status of a RGMII Link on Octeon as seen by core driver. */
+union oct_link_status {
+	u64 u64;
+
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 duplex:8;
+		u64 status:8;
+		u64 mtu:16;
+		u64 speed:16;
+		u64 autoneg:1;
+		u64 interface:4;
+		u64 pause:1;
+		u64 reserved:10;
+#else
+		u64 reserved:10;
+		u64 pause:1;
+		u64 interface:4;
+		u64 autoneg:1;
+		u64 speed:16;
+		u64 mtu:16;
+		u64 status:8;
+		u64 duplex:8;
+#endif
+	} s;
+};
+
+/** Information for a OCTEON ethernet interface shared between core & host. */
+struct oct_link_info {
+	union oct_link_status link;
+	u64 hw_addr;
+
+#ifdef __BIG_ENDIAN_BITFIELD
+	u16 gmxport;
+	u8 rsvd[3];
+	u8 num_txpciq;
+	u8 num_rxpciq;
+	u8 ifidx;
+#else
+	u8 ifidx;
+	u8 num_rxpciq;
+	u8 num_txpciq;
+	u8 rsvd[3];
+	u16 gmxport;
+#endif
+
+	u8 txpciq[MAX_IOQS_PER_NICIF];
+	u8 rxpciq[MAX_IOQS_PER_NICIF];
+};
+
+#define OCT_LINK_INFO_SIZE   (sizeof(struct oct_link_info))
+
+struct liquidio_if_cfg_info {
+	u64 ifidx;
+	u64 iqmask; /** mask for IQs enabled for  the port */
+	u64 oqmask; /** mask for OQs enabled for the port */
+	struct oct_link_info linfo; /** initial link information */
+};
+
+/** Stats for each NIC port in RX direction. */
+struct nic_rx_stats {
+	/* link-level stats */
+	u64 total_rcvd;
+	u64 bytes_rcvd;
+	u64 total_bcst;
+	u64 total_mcst;
+	u64 runts;
+	u64 ctl_rcvd;
+	u64 fifo_err;      /* Accounts for over/under-run of buffers */
+	u64 dmac_drop;
+	u64 fcs_err;
+	u64 jabber_err;
+	u64 l2_err;
+	u64 frame_err;
+
+	/* firmware stats */
+	u64 fw_total_rcvd;
+	u64 fw_total_fwd;
+	u64 fw_err_pko;
+	u64 fw_err_link;
+	u64 fw_err_drop;
+	u64 fw_lro_pkts;   /* Number of packets that are LROed      */
+	u64 fw_lro_octs;   /* Number of octets that are LROed       */
+	u64 fw_total_lro;  /* Number of LRO packets formed          */
+	u64 fw_lro_aborts; /* Number of times lRO of packet aborted */
+	/* intrmod: packet forward rate */
+	u64 fwd_rate;
+};
+
+/** Stats for each NIC port in RX direction. */
+struct nic_tx_stats {
+	/* link-level stats */
+	u64 total_pkts_sent;
+	u64 total_bytes_sent;
+	u64 mcast_pkts_sent;
+	u64 bcast_pkts_sent;
+	u64 ctl_sent;
+	u64 one_collision_sent;   /* Packets sent after one collision*/
+	u64 multi_collision_sent; /* Packets sent after multiple collision*/
+	u64 max_collision_fail;   /* Packets not sent due to max collisions */
+	u64 max_deferral_fail;   /* Packets not sent due to max deferrals */
+	u64 fifo_err;       /* Accounts for over/under-run of buffers */
+	u64 runts;
+	u64 total_collisions; /* Total number of collisions detected */
+
+	/* firmware stats */
+	u64 fw_total_sent;
+	u64 fw_total_fwd;
+	u64 fw_err_pko;
+	u64 fw_err_link;
+	u64 fw_err_drop;
+};
+
+struct oct_link_stats {
+	struct nic_rx_stats fromwire;
+	struct nic_tx_stats fromhost;
+
+};
+
+#define LIO68XX_LED_CTRL_ADDR     0x3501
+#define LIO68XX_LED_CTRL_CFGON    0x1f
+#define LIO68XX_LED_CTRL_CFGOFF   0x100
+#define LIO68XX_LED_BEACON_ADDR   0x3508
+#define LIO68XX_LED_BEACON_CFGON  0x47fd
+#define LIO68XX_LED_BEACON_CFGOFF 0x11fc
+#define VITESSE_PHY_GPIO_DRIVEON  0x1
+#define VITESSE_PHY_GPIO_CFG      0x8
+#define VITESSE_PHY_GPIO_DRIVEOFF 0x4
+#define VITESSE_PHY_GPIO_HIGH     0x2
+#define VITESSE_PHY_GPIO_LOW      0x3
+
+struct oct_mdio_cmd {
+	u64 op;
+	u64 mdio_addr;
+	u64 value1;
+	u64 value2;
+	u64 value3;
+};
+
+#define OCT_LINK_STATS_SIZE   (sizeof(struct oct_link_stats))
+
+#define LIO_INTRMOD_CHECK_INTERVAL  1
+#define LIO_INTRMOD_MAXPKT_RATETHR  196608 /* max pkt rate threshold */
+#define LIO_INTRMOD_MINPKT_RATETHR  9216   /* min pkt rate threshold */
+#define LIO_INTRMOD_MAXCNT_TRIGGER  384    /* max pkts to trigger interrupt */
+#define LIO_INTRMOD_MINCNT_TRIGGER  1      /* min pkts to trigger interrupt */
+#define LIO_INTRMOD_MAXTMR_TRIGGER  128    /* max time to trigger interrupt */
+#define LIO_INTRMOD_MINTMR_TRIGGER  32     /* min time to trigger interrupt */
+
+struct oct_intrmod_cfg {
+	u64 intrmod_enable;
+	u64 intrmod_check_intrvl;
+	u64 intrmod_maxpkt_ratethr;
+	u64 intrmod_minpkt_ratethr;
+	u64 intrmod_maxcnt_trigger;
+	u64 intrmod_maxtmr_trigger;
+	u64 intrmod_mincnt_trigger;
+	u64 intrmod_mintmr_trigger;
+};
+
+#define BASE_QUEUE_NOT_REQUESTED 65535
+
+union oct_nic_if_cfg {
+	u64 u64;
+	struct {
+#ifdef __BIG_ENDIAN_BITFIELD
+		u64 base_queue:16;
+		u64 num_iqueues:16;
+		u64 num_oqueues:16;
+		u64 gmx_port_id:8;
+		u64 reserved:8;
+#else
+		u64 reserved:8;
+		u64 gmx_port_id:8;
+		u64 num_oqueues:16;
+		u64 num_iqueues:16;
+		u64 base_queue:16;
+#endif
+	} s;
+};
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_image.h b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
new file mode 100644
index 000000000000..93819bd8602b
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_image.h
@@ -0,0 +1,57 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#ifndef _LIQUIDIO_IMAGE_H_
+#define _LIQUIDIO_IMAGE_H_
+
+#define LIO_MAX_FW_TYPE_LEN     (8)
+#define LIO_MAX_FW_FILENAME_LEN (256)
+#define LIO_FW_DIR              "liquidio/"
+#define LIO_FW_BASE_NAME        "lio_"
+#define LIO_FW_NAME_SUFFIX      ".bin"
+#define LIO_FW_NAME_TYPE_NIC    "nic"
+#define LIO_FW_NAME_TYPE_NONE   "none"
+#define LIO_MAX_FIRMWARE_VERSION_LEN 16
+
+#define LIO_MAX_BOOTCMD_LEN 1024
+#define LIO_MAX_IMAGES 16
+#define LIO_NIC_MAGIC 0x434E4943     /* "CNIC" */
+struct octeon_firmware_desc {
+	__be64 addr;
+	__be32 len;
+	__be32 crc32;         /* crc32 of image */
+};
+
+/* Following the header is a list of 64-bit aligned binary images,
+ * as described by the desc field.
+ * Numeric fields are in network byte order.
+ */
+struct octeon_firmware_file_header {
+	__be32 magic;
+	char version[LIO_MAX_FIRMWARE_VERSION_LEN];
+	char bootcmd[LIO_MAX_BOOTCMD_LEN];
+	__be32 num_images;
+	struct octeon_firmware_desc desc[LIO_MAX_IMAGES];
+	__be32 pad;
+	__be32 crc32;         /* header checksum */
+};
+
+#endif /* _LIQUIDIO_IMAGE_H_ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
new file mode 100644
index 000000000000..62a8dd5cd3dc
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -0,0 +1,424 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file  octeon_config.h
+ *  \brief Host Driver: Configuration data structures for the host driver.
+ */
+
+#ifndef __OCTEON_CONFIG_H__
+#define __OCTEON_CONFIG_H__
+
+/*--------------------------CONFIG VALUES------------------------*/
+
+/* The following macros affect the way the driver data structures
+ * are generated for Octeon devices.
+ * They can be modified.
+ */
+
+/* Maximum octeon devices defined as MAX_OCTEON_NICIF to support
+ * multiple(<= MAX_OCTEON_NICIF) Miniports
+ */
+#define   MAX_OCTEON_NICIF             32
+#define   MAX_OCTEON_DEVICES           MAX_OCTEON_NICIF
+#define   MAX_OCTEON_LINKS	       MAX_OCTEON_NICIF
+#define   MAX_OCTEON_MULTICAST_ADDR    32
+
+/* CN6xxx IQ configuration macros */
+#define   CN6XXX_MAX_INPUT_QUEUES      32
+#define   CN6XXX_MAX_IQ_DESCRIPTORS    2048
+#define   CN6XXX_DB_MIN                1
+#define   CN6XXX_DB_MAX                8
+#define   CN6XXX_DB_TIMEOUT            1
+
+/* CN6xxx OQ configuration macros */
+#define   CN6XXX_MAX_OUTPUT_QUEUES     32
+#define   CN6XXX_MAX_OQ_DESCRIPTORS    2048
+#define   CN6XXX_OQ_BUF_SIZE           1536
+#define   CN6XXX_OQ_PKTSPER_INTR       ((CN6XXX_MAX_OQ_DESCRIPTORS < 512) ? \
+					(CN6XXX_MAX_OQ_DESCRIPTORS / 4) : 128)
+#define   CN6XXX_OQ_REFIL_THRESHOLD    ((CN6XXX_MAX_OQ_DESCRIPTORS < 512) ? \
+					(CN6XXX_MAX_OQ_DESCRIPTORS / 4) : 128)
+
+#define   CN6XXX_OQ_INTR_PKT           64
+#define   CN6XXX_OQ_INTR_TIME          100
+#define   DEFAULT_NUM_NIC_PORTS_66XX   2
+#define   DEFAULT_NUM_NIC_PORTS_68XX   4
+#define   DEFAULT_NUM_NIC_PORTS_68XX_210NV  2
+
+/* common OCTEON configuration macros */
+#define   CN6XXX_CFG_IO_QUEUES         32
+#define   OCTEON_32BYTE_INSTR          32
+#define   OCTEON_64BYTE_INSTR          64
+#define   OCTEON_MAX_BASE_IOQ          4
+#define   OCTEON_OQ_BUFPTR_MODE        0
+#define   OCTEON_OQ_INFOPTR_MODE       1
+
+#define   OCTEON_DMA_INTR_PKT          64
+#define   OCTEON_DMA_INTR_TIME         1000
+
+#define MAX_TXQS_PER_INTF  8
+#define MAX_RXQS_PER_INTF  8
+#define DEF_TXQS_PER_INTF  4
+#define DEF_RXQS_PER_INTF  4
+
+#define INVALID_IOQ_NO          0xff
+
+#define   DEFAULT_POW_GRP       0
+
+/* Macros to get octeon config params */
+#define CFG_GET_IQ_CFG(cfg)                      ((cfg)->iq)
+#define CFG_GET_IQ_MAX_Q(cfg)                    ((cfg)->iq.max_iqs)
+#define CFG_GET_IQ_PENDING_LIST_SIZE(cfg)        ((cfg)->iq.pending_list_size)
+#define CFG_GET_IQ_INSTR_TYPE(cfg)               ((cfg)->iq.instr_type)
+#define CFG_GET_IQ_DB_MIN(cfg)                   ((cfg)->iq.db_min)
+#define CFG_GET_IQ_DB_TIMEOUT(cfg)               ((cfg)->iq.db_timeout)
+
+#define CFG_GET_OQ_MAX_Q(cfg)                    ((cfg)->oq.max_oqs)
+#define CFG_GET_OQ_INFO_PTR(cfg)                 ((cfg)->oq.info_ptr)
+#define CFG_GET_OQ_PKTS_PER_INTR(cfg)            ((cfg)->oq.pkts_per_intr)
+#define CFG_GET_OQ_REFILL_THRESHOLD(cfg)         ((cfg)->oq.refill_threshold)
+#define CFG_GET_OQ_INTR_PKT(cfg)                 ((cfg)->oq.oq_intr_pkt)
+#define CFG_GET_OQ_INTR_TIME(cfg)                ((cfg)->oq.oq_intr_time)
+#define CFG_SET_OQ_INTR_PKT(cfg, val)            (cfg)->oq.oq_intr_pkt = val
+#define CFG_SET_OQ_INTR_TIME(cfg, val)           (cfg)->oq.oq_intr_time = val
+
+#define CFG_GET_DMA_INTR_PKT(cfg)                ((cfg)->dma.dma_intr_pkt)
+#define CFG_GET_DMA_INTR_TIME(cfg)               ((cfg)->dma.dma_intr_time)
+#define CFG_GET_NUM_NIC_PORTS(cfg)               ((cfg)->num_nic_ports)
+#define CFG_GET_NUM_DEF_TX_DESCS(cfg)            ((cfg)->num_def_tx_descs)
+#define CFG_GET_NUM_DEF_RX_DESCS(cfg)            ((cfg)->num_def_rx_descs)
+#define CFG_GET_DEF_RX_BUF_SIZE(cfg)             ((cfg)->def_rx_buf_size)
+
+#define CFG_GET_MAX_TXQS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].max_txqs)
+#define CFG_GET_NUM_TXQS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].num_txqs)
+#define CFG_GET_MAX_RXQS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].max_rxqs)
+#define CFG_GET_NUM_RXQS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].num_rxqs)
+#define CFG_GET_NUM_RX_DESCS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].num_rx_descs)
+#define CFG_GET_NUM_TX_DESCS_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].num_tx_descs)
+#define CFG_GET_NUM_RX_BUF_SIZE_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].rx_buf_size)
+#define CFG_GET_BASE_QUE_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].base_queue)
+#define CFG_GET_GMXID_NIC_IF(cfg, idx) \
+				((cfg)->nic_if_cfg[idx].gmx_port_id)
+
+#define CFG_GET_CTRL_Q_GRP(cfg)                  ((cfg)->misc.ctrlq_grp)
+#define CFG_GET_HOST_LINK_QUERY_INTERVAL(cfg) \
+				((cfg)->misc.host_link_query_interval)
+#define CFG_GET_OCT_LINK_QUERY_INTERVAL(cfg) \
+				((cfg)->misc.oct_link_query_interval)
+#define CFG_GET_IS_SLI_BP_ON(cfg)                ((cfg)->misc.enable_sli_oq_bp)
+
+/* Max IOQs per OCTEON Link */
+#define MAX_IOQS_PER_NICIF              32
+
+enum lio_card_type {
+	LIO_210SV = 0, /* Two port, 66xx */
+	LIO_210NV,     /* Two port, 68xx */
+	LIO_410NV      /* Four port, 68xx */
+};
+
+#define LIO_210SV_NAME "210sv"
+#define LIO_210NV_NAME "210nv"
+#define LIO_410NV_NAME "410nv"
+
+/** Structure to define the configuration attributes for each Input queue.
+ *  Applicable to all Octeon processors
+ **/
+struct octeon_iq_config {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 reserved:32;
+
+	/** Minimum ticks to wait before checking for pending instructions. */
+	u64 db_timeout:16;
+
+	/** Minimum number of commands pending to be posted to Octeon
+	 *  before driver hits the Input queue doorbell.
+	 */
+	u64 db_min:8;
+
+	/** Command size - 32 or 64 bytes */
+	u64 instr_type:32;
+
+	/** Pending list size (usually set to the sum of the size of all Input
+	 *  queues)
+	 */
+	u64 pending_list_size:32;
+
+	/* Max number of IQs available */
+	u64 max_iqs:8;
+#else
+	/* Max number of IQs available */
+	u64 max_iqs:8;
+
+	/** Pending list size (usually set to the sum of the size of all Input
+	 *  queues)
+	 */
+	u64 pending_list_size:32;
+
+	/** Command size - 32 or 64 bytes */
+	u64 instr_type:32;
+
+	/** Minimum number of commands pending to be posted to Octeon
+	 *  before driver hits the Input queue doorbell.
+	 */
+	u64 db_min:8;
+
+	/** Minimum ticks to wait before checking for pending instructions. */
+	u64 db_timeout:16;
+
+	u64 reserved:32;
+#endif
+};
+
+/** Structure to define the configuration attributes for each Output queue.
+ *  Applicable to all Octeon processors
+ **/
+struct octeon_oq_config {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 reserved:16;
+
+	u64 pkts_per_intr:16;
+
+	/** Interrupt Coalescing (Time Interval). Octeon will interrupt the
+	 *  host if atleast one packet was sent in the time interval specified
+	 *  by this field. The driver uses time interval interrupt coalescing
+	 *  by default. The time is specified in microseconds.
+	 */
+	u64 oq_intr_time:16;
+
+	/** Interrupt Coalescing (Packet Count). Octeon will interrupt the host
+	 *  only if it sent as many packets as specified by this field.
+	 *  The driver
+	 *  usually does not use packet count interrupt coalescing.
+	 */
+	u64 oq_intr_pkt:16;
+
+	/** The number of buffers that were consumed during packet processing by
+	 *   the driver on this Output queue before the driver attempts to
+	 *   replenish
+	 *   the descriptor ring with new buffers.
+	 */
+	u64 refill_threshold:16;
+
+	/** If set, the Output queue uses info-pointer mode. (Default: 1 ) */
+	u64 info_ptr:32;
+
+	/* Max number of OQs available */
+	u64 max_oqs:8;
+
+#else
+	/* Max number of OQs available */
+	u64 max_oqs:8;
+
+	/** If set, the Output queue uses info-pointer mode. (Default: 1 ) */
+	u64 info_ptr:32;
+
+	/** The number of buffers that were consumed during packet processing by
+	 *   the driver on this Output queue before the driver attempts to
+	 *   replenish
+	 *   the descriptor ring with new buffers.
+	 */
+	u64 refill_threshold:16;
+
+	/** Interrupt Coalescing (Packet Count). Octeon will interrupt the host
+	 *  only if it sent as many packets as specified by this field.
+	 *  The driver
+	 *  usually does not use packet count interrupt coalescing.
+	 */
+	u64 oq_intr_pkt:16;
+
+	/** Interrupt Coalescing (Time Interval). Octeon will interrupt the
+	 *  host if atleast one packet was sent in the time interval specified
+	 *  by this field. The driver uses time interval interrupt coalescing
+	 *  by default.  The time is specified in microseconds.
+	 */
+	u64 oq_intr_time:16;
+
+	u64 pkts_per_intr:16;
+
+	u64 reserved:16;
+#endif
+
+};
+
+/** This structure conatins the NIC link configuration attributes,
+ *  common for all the OCTEON Modles.
+ */
+struct octeon_nic_if_config {
+#ifdef __BIG_ENDIAN_BITFIELD
+	u64 reserved:56;
+
+	u64 base_queue:16;
+
+	u64 gmx_port_id:8;
+
+	/* SKB size, We need not change buf size even for Jumbo frames.
+	 * Octeon can send jumbo frames in 4 consecutive descriptors,
+	 */
+	u64 rx_buf_size:16;
+
+	/* Num of desc for tx rings */
+	u64 num_tx_descs:16;
+
+	/* Num of desc for rx rings */
+	u64 num_rx_descs:16;
+
+	/* Actual configured value. Range could be: 1...max_rxqs */
+	u64 num_rxqs:16;
+
+	/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+	u64 max_rxqs:16;
+
+	/* Actual configured value. Range could be: 1...max_txqs */
+	u64 num_txqs:16;
+
+	/* Max Txqs: Half for each of the two ports :max_iq/2 */
+	u64 max_txqs:16;
+#else
+	/* Max Txqs: Half for each of the two ports :max_iq/2 */
+	u64 max_txqs:16;
+
+	/* Actual configured value. Range could be: 1...max_txqs */
+	u64 num_txqs:16;
+
+	/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+	u64 max_rxqs:16;
+
+	/* Actual configured value. Range could be: 1...max_rxqs */
+	u64 num_rxqs:16;
+
+	/* Num of desc for rx rings */
+	u64 num_rx_descs:16;
+
+	/* Num of desc for tx rings */
+	u64 num_tx_descs:16;
+
+	/* SKB size, We need not change buf size even for Jumbo frames.
+	 * Octeon can send jumbo frames in 4 consecutive descriptors,
+	 */
+	u64 rx_buf_size:16;
+
+	u64 gmx_port_id:8;
+
+	u64 base_queue:16;
+
+	u64 reserved:56;
+#endif
+
+};
+
+/** Structure to define the configuration attributes for meta data.
+ *  Applicable to all Octeon processors.
+ */
+
+struct octeon_misc_config {
+#ifdef __BIG_ENDIAN_BITFIELD
+	/** Host link status polling period */
+	u64 host_link_query_interval:32;
+	/** Oct link status polling period */
+	u64 oct_link_query_interval:32;
+
+	u64 enable_sli_oq_bp:1;
+	/** Control IQ Group */
+	u64 ctrlq_grp:4;
+#else
+	/** Control IQ Group */
+	u64 ctrlq_grp:4;
+	/** BP for SLI OQ */
+	u64 enable_sli_oq_bp:1;
+	/** Host link status polling period */
+	u64 oct_link_query_interval:32;
+	/** Oct link status polling period */
+	u64 host_link_query_interval:32;
+#endif
+};
+
+/** Structure to define the configuration for all OCTEON processors. */
+struct octeon_config {
+	u16 card_type;
+	char *card_name;
+
+	/** Input Queue attributes. */
+	struct octeon_iq_config iq;
+
+	/** Output Queue attributes. */
+	struct octeon_oq_config oq;
+
+	/** NIC Port Configuration */
+	struct octeon_nic_if_config nic_if_cfg[MAX_OCTEON_NICIF];
+
+	/** Miscellaneous attributes */
+	struct octeon_misc_config misc;
+
+	int num_nic_ports;
+
+	int num_def_tx_descs;
+
+	/* Num of desc for rx rings */
+	int num_def_rx_descs;
+
+	int def_rx_buf_size;
+
+};
+
+/* The following config values are fixed and should not be modified. */
+
+/* Maximum address space to be mapped for Octeon's BAR1 index-based access. */
+#define  MAX_BAR1_MAP_INDEX                     2
+#define  OCTEON_BAR1_ENTRY_SIZE         (4 * 1024 * 1024)
+
+/* BAR1 Index 0 to (MAX_BAR1_MAP_INDEX - 1) for normal mapped memory access.
+ * Bar1 register at MAX_BAR1_MAP_INDEX used by driver for dynamic access.
+ */
+#define  MAX_BAR1_IOREMAP_SIZE  ((MAX_BAR1_MAP_INDEX + 1) * \
+				 OCTEON_BAR1_ENTRY_SIZE)
+
+/* Response lists - 1 ordered, 1 unordered-blocking, 1 unordered-nonblocking
+ * NoResponse Lists are now maintained with each IQ. (Dec' 2007).
+ */
+#define MAX_RESPONSE_LISTS           4
+
+/* Opcode hash bits. The opcode is hashed on the lower 6-bits to lookup the
+ * dispatch table.
+ */
+#define OPCODE_MASK_BITS             6
+
+/* Mask for the 6-bit lookup hash */
+#define OCTEON_OPCODE_MASK           0x3f
+
+/* Size of the dispatch table. The 6-bit hash can index into 2^6 entries */
+#define DISPATCH_LIST_SIZE                      BIT(OPCODE_MASK_BITS)
+
+/* Maximum number of Octeon Instruction (command) queues */
+#define MAX_OCTEON_INSTR_QUEUES         CN6XXX_MAX_INPUT_QUEUES
+
+/* Maximum number of Octeon Instruction (command) queues */
+#define MAX_OCTEON_OUTPUT_QUEUES        CN6XXX_MAX_OUTPUT_QUEUES
+
+#endif /* __OCTEON_CONFIG_H__  */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
new file mode 100644
index 000000000000..466147e409c9
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -0,0 +1,723 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/**
+ * @file octeon_console.c
+ */
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+static void octeon_remote_lock(void);
+static void octeon_remote_unlock(void);
+static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
+					     const char *name,
+					     u32 flags);
+
+#define MIN(a, b) min((a), (b))
+#define CAST_ULL(v) ((u64)(v))
+
+#define BOOTLOADER_PCI_READ_BUFFER_DATA_ADDR    0x0006c008
+#define BOOTLOADER_PCI_READ_BUFFER_LEN_ADDR     0x0006c004
+#define BOOTLOADER_PCI_READ_BUFFER_OWNER_ADDR   0x0006c000
+#define BOOTLOADER_PCI_READ_DESC_ADDR           0x0006c100
+#define BOOTLOADER_PCI_WRITE_BUFFER_STR_LEN     248
+
+#define OCTEON_PCI_IO_BUF_OWNER_OCTEON    0x00000001
+#define OCTEON_PCI_IO_BUF_OWNER_HOST      0x00000002
+
+/** Can change without breaking ABI */
+#define CVMX_BOOTMEM_NUM_NAMED_BLOCKS 64
+
+/** minimum alignment of bootmem alloced blocks */
+#define CVMX_BOOTMEM_ALIGNMENT_SIZE     (16ull)
+
+/** CVMX bootmem descriptor major version */
+#define CVMX_BOOTMEM_DESC_MAJ_VER   3
+/* CVMX bootmem descriptor minor version */
+#define CVMX_BOOTMEM_DESC_MIN_VER   0
+
+/* Current versions */
+#define OCTEON_PCI_CONSOLE_MAJOR_VERSION    1
+#define OCTEON_PCI_CONSOLE_MINOR_VERSION    0
+#define OCTEON_PCI_CONSOLE_BLOCK_NAME   "__pci_console"
+#define OCTEON_CONSOLE_POLL_INTERVAL_MS  100    /* 10 times per second */
+
+/* First three members of cvmx_bootmem_desc are left in original
+** positions for backwards compatibility.
+** Assumes big endian target
+*/
+struct cvmx_bootmem_desc {
+	/** spinlock to control access to list */
+	u32 lock;
+
+	/** flags for indicating various conditions */
+	u32 flags;
+
+	u64 head_addr;
+
+	/** incremented changed when incompatible changes made */
+	u32 major_version;
+
+	/** incremented changed when compatible changes made,
+	 *  reset to zero when major incremented
+	 */
+	u32 minor_version;
+
+	u64 app_data_addr;
+	u64 app_data_size;
+
+	/** number of elements in named blocks array */
+	u32 nb_num_blocks;
+
+	/** length of name array in bootmem blocks */
+	u32 named_block_name_len;
+
+	/** address of named memory block descriptors */
+	u64 named_block_array_addr;
+};
+
+/* Structure that defines a single console.
+ *
+ * Note: when read_index == write_index, the buffer is empty.
+ * The actual usable size of each console is console_buf_size -1;
+ */
+struct octeon_pci_console {
+	u64 input_base_addr;
+	u32 input_read_index;
+	u32 input_write_index;
+	u64 output_base_addr;
+	u32 output_read_index;
+	u32 output_write_index;
+	u32 lock;
+	u32 buf_size;
+};
+
+/* This is the main container structure that contains all the information
+ * about all PCI consoles.  The address of this structure is passed to various
+ * routines that operation on PCI consoles.
+ */
+struct octeon_pci_console_desc {
+	u32 major_version;
+	u32 minor_version;
+	u32 lock;
+	u32 flags;
+	u32 num_consoles;
+	u32 pad;
+	/* must be 64 bit aligned here... */
+	/* Array of addresses of octeon_pci_console structures */
+	u64 console_addr_array[0];
+	/* Implicit storage for console_addr_array */
+};
+
+/**
+ * This macro returns the size of a member of a structure.
+ * Logically it is the same as "sizeof(s::field)" in C++, but
+ * C lacks the "::" operator.
+ */
+#define SIZEOF_FIELD(s, field) sizeof(((s *)NULL)->field)
+
+/**
+ * This macro returns a member of the cvmx_bootmem_desc
+ * structure. These members can't be directly addressed as
+ * they might be in memory not directly reachable. In the case
+ * where bootmem is compiled with LINUX_HOST, the structure
+ * itself might be located on a remote Octeon. The argument
+ * "field" is the member name of the cvmx_bootmem_desc to read.
+ * Regardless of the type of the field, the return type is always
+ * a u64.
+ */
+#define CVMX_BOOTMEM_DESC_GET_FIELD(oct, field)                              \
+	__cvmx_bootmem_desc_get(oct, oct->bootmem_desc_addr,                 \
+				offsetof(struct cvmx_bootmem_desc, field),   \
+				SIZEOF_FIELD(struct cvmx_bootmem_desc, field))
+
+#define __cvmx_bootmem_lock(flags)
+#define __cvmx_bootmem_unlock(flags)
+
+/**
+ * This macro returns a member of the
+ * cvmx_bootmem_named_block_desc structure. These members can't
+ * be directly addressed as they might be in memory not directly
+ * reachable. In the case where bootmem is compiled with
+ * LINUX_HOST, the structure itself might be located on a remote
+ * Octeon. The argument "field" is the member name of the
+ * cvmx_bootmem_named_block_desc to read. Regardless of the type
+ * of the field, the return type is always a u64. The "addr"
+ * parameter is the physical address of the structure.
+ */
+#define CVMX_BOOTMEM_NAMED_GET_FIELD(oct, addr, field)                   \
+	__cvmx_bootmem_desc_get(oct, addr,                               \
+		offsetof(struct cvmx_bootmem_named_block_desc, field),   \
+		SIZEOF_FIELD(struct cvmx_bootmem_named_block_desc, field))
+
+/**
+ * This function is the implementation of the get macros defined
+ * for individual structure members. The argument are generated
+ * by the macros inorder to read only the needed memory.
+ *
+ * @param oct    Pointer to current octeon device
+ * @param base   64bit physical address of the complete structure
+ * @param offset Offset from the beginning of the structure to the member being
+ *               accessed.
+ * @param size   Size of the structure member.
+ *
+ * @return Value of the structure member promoted into a u64.
+ */
+static inline u64 __cvmx_bootmem_desc_get(struct octeon_device *oct,
+					  u64 base,
+					  u32 offset,
+					  u32 size)
+{
+	base = (1ull << 63) | (base + offset);
+	switch (size) {
+	case 4:
+		return octeon_read_device_mem32(oct, base);
+	case 8:
+		return octeon_read_device_mem64(oct, base);
+	default:
+		return 0;
+	}
+}
+
+/**
+ * This function retrieves the string name of a named block. It is
+ * more complicated than a simple memcpy() since the named block
+ * descriptor may not be directly accessible.
+ *
+ * @param addr   Physical address of the named block descriptor
+ * @param str    String to receive the named block string name
+ * @param len    Length of the string buffer, which must match the length
+ *               stored in the bootmem descriptor.
+ */
+static void CVMX_BOOTMEM_NAMED_GET_NAME(struct octeon_device *oct,
+					u64 addr,
+					char *str,
+					u32 len)
+{
+	addr += offsetof(struct cvmx_bootmem_named_block_desc, name);
+	octeon_pci_read_core_mem(oct, addr, str, len);
+	str[len] = 0;
+}
+
+/* See header file for descriptions of functions */
+
+/**
+ * Check the version information on the bootmem descriptor
+ *
+ * @param exact_match
+ *               Exact major version to check against. A zero means
+ *               check that the version supports named blocks.
+ *
+ * @return Zero if the version is correct. Negative if the version is
+ *         incorrect. Failures also cause a message to be displayed.
+ */
+static int __cvmx_bootmem_check_version(struct octeon_device *oct,
+					u32 exact_match)
+{
+	u32 major_version;
+	u32 minor_version;
+
+	if (!oct->bootmem_desc_addr)
+		oct->bootmem_desc_addr =
+			octeon_read_device_mem64(oct,
+						 BOOTLOADER_PCI_READ_DESC_ADDR);
+	major_version =
+		(u32)CVMX_BOOTMEM_DESC_GET_FIELD(oct, major_version);
+	minor_version =
+		(u32)CVMX_BOOTMEM_DESC_GET_FIELD(oct, minor_version);
+	dev_dbg(&oct->pci_dev->dev, "%s: major_version=%d\n", __func__,
+		major_version);
+	if ((major_version > 3) ||
+	    (exact_match && major_version != exact_match)) {
+		dev_err(&oct->pci_dev->dev, "bootmem ver mismatch %d.%d addr:0x%llx\n",
+			major_version, minor_version,
+			CAST_ULL(oct->bootmem_desc_addr));
+		return -1;
+	} else {
+		return 0;
+	}
+}
+
+static const struct cvmx_bootmem_named_block_desc
+*__cvmx_bootmem_find_named_block_flags(struct octeon_device *oct,
+					const char *name, u32 flags)
+{
+	struct cvmx_bootmem_named_block_desc *desc =
+		&oct->bootmem_named_block_desc;
+	u64 named_addr = cvmx_bootmem_phy_named_block_find(oct, name, flags);
+
+	if (named_addr) {
+		desc->base_addr = CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr,
+							       base_addr);
+		desc->size =
+			CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr, size);
+		strncpy(desc->name, name, sizeof(desc->name));
+		desc->name[sizeof(desc->name) - 1] = 0;
+		return &oct->bootmem_named_block_desc;
+	} else {
+		return NULL;
+	}
+}
+
+static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct,
+					     const char *name,
+					     u32 flags)
+{
+	u64 result = 0;
+
+	__cvmx_bootmem_lock(flags);
+	if (!__cvmx_bootmem_check_version(oct, 3)) {
+		u32 i;
+		u64 named_block_array_addr =
+			CVMX_BOOTMEM_DESC_GET_FIELD(oct,
+						    named_block_array_addr);
+		u32 num_blocks = (u32)
+			CVMX_BOOTMEM_DESC_GET_FIELD(oct, nb_num_blocks);
+		u32 name_length = (u32)
+			CVMX_BOOTMEM_DESC_GET_FIELD(oct, named_block_name_len);
+		u64 named_addr = named_block_array_addr;
+
+		for (i = 0; i < num_blocks; i++) {
+			u64 named_size =
+				CVMX_BOOTMEM_NAMED_GET_FIELD(oct, named_addr,
+							     size);
+			if (name && named_size) {
+				char *name_tmp =
+					kmalloc(name_length + 1, GFP_KERNEL);
+				CVMX_BOOTMEM_NAMED_GET_NAME(oct, named_addr,
+							    name_tmp,
+							    name_length);
+				if (!strncmp(name, name_tmp, name_length)) {
+					result = named_addr;
+					kfree(name_tmp);
+					break;
+				}
+				kfree(name_tmp);
+			} else if (!name && !named_size) {
+				result = named_addr;
+				break;
+			}
+
+			named_addr +=
+				sizeof(struct cvmx_bootmem_named_block_desc);
+		}
+	}
+	__cvmx_bootmem_unlock(flags);
+	return result;
+}
+
+/**
+ * Find a named block on the remote Octeon
+ *
+ * @param name      Name of block to find
+ * @param base_addr Address the block is at (OUTPUT)
+ * @param size      The size of the block (OUTPUT)
+ *
+ * @return Zero on success, One on failure.
+ */
+static int octeon_named_block_find(struct octeon_device *oct, const char *name,
+				   u64 *base_addr, u64 *size)
+{
+	const struct cvmx_bootmem_named_block_desc *named_block;
+
+	octeon_remote_lock();
+	named_block = __cvmx_bootmem_find_named_block_flags(oct, name, 0);
+	octeon_remote_unlock();
+	if (named_block) {
+		*base_addr = named_block->base_addr;
+		*size = named_block->size;
+		return 0;
+	}
+	return 1;
+}
+
+static void octeon_remote_lock(void)
+{
+	/* fill this in if any sharing is needed */
+}
+
+static void octeon_remote_unlock(void)
+{
+	/* fill this in if any sharing is needed */
+}
+
+int octeon_console_send_cmd(struct octeon_device *oct, char *cmd_str,
+			    u32 wait_hundredths)
+{
+	u32 len = strlen(cmd_str);
+
+	dev_dbg(&oct->pci_dev->dev, "sending \"%s\" to bootloader\n", cmd_str);
+
+	if (len > BOOTLOADER_PCI_WRITE_BUFFER_STR_LEN - 1) {
+		dev_err(&oct->pci_dev->dev, "Command string too long, max length is: %d\n",
+			BOOTLOADER_PCI_WRITE_BUFFER_STR_LEN - 1);
+		return -1;
+	}
+
+	if (octeon_wait_for_bootloader(oct, wait_hundredths) != 0) {
+		dev_err(&oct->pci_dev->dev, "Bootloader not ready for command.\n");
+		return -1;
+	}
+
+	/* Write command to bootloader */
+	octeon_remote_lock();
+	octeon_pci_write_core_mem(oct, BOOTLOADER_PCI_READ_BUFFER_DATA_ADDR,
+				  (u8 *)cmd_str, len);
+	octeon_write_device_mem32(oct, BOOTLOADER_PCI_READ_BUFFER_LEN_ADDR,
+				  len);
+	octeon_write_device_mem32(oct, BOOTLOADER_PCI_READ_BUFFER_OWNER_ADDR,
+				  OCTEON_PCI_IO_BUF_OWNER_OCTEON);
+
+	/* Bootloader should accept command very quickly
+	 * if it really was ready
+	 */
+	if (octeon_wait_for_bootloader(oct, 200) != 0) {
+		octeon_remote_unlock();
+		dev_err(&oct->pci_dev->dev, "Bootloader did not accept command.\n");
+		return -1;
+	}
+	octeon_remote_unlock();
+	return 0;
+}
+
+int octeon_wait_for_bootloader(struct octeon_device *oct,
+			       u32 wait_time_hundredths)
+{
+	dev_dbg(&oct->pci_dev->dev, "waiting %d0 ms for bootloader\n",
+		wait_time_hundredths);
+
+	if (octeon_mem_access_ok(oct))
+		return -1;
+
+	while (wait_time_hundredths > 0 &&
+	       octeon_read_device_mem32(oct,
+					BOOTLOADER_PCI_READ_BUFFER_OWNER_ADDR)
+	       != OCTEON_PCI_IO_BUF_OWNER_HOST) {
+		if (--wait_time_hundredths <= 0)
+			return -1;
+		schedule_timeout_uninterruptible(HZ / 100);
+	}
+	return 0;
+}
+
+static void octeon_console_handle_result(struct octeon_device *oct,
+					 size_t console_num,
+					 char *buffer, s32 bytes_read)
+{
+	struct octeon_console *console;
+
+	console = &oct->console[console_num];
+
+	console->waiting = 0;
+}
+
+static char console_buffer[OCTEON_CONSOLE_MAX_READ_BYTES];
+
+static void output_console_line(struct octeon_device *oct,
+				struct octeon_console *console,
+				size_t console_num,
+				char *console_buffer,
+				s32 bytes_read)
+{
+	char *line;
+	s32 i;
+
+	line = console_buffer;
+	for (i = 0; i < bytes_read; i++) {
+		/* Output a line at a time, prefixed */
+		if (console_buffer[i] == '\n') {
+			console_buffer[i] = '\0';
+			if (console->leftover[0]) {
+				dev_info(&oct->pci_dev->dev, "%lu: %s%s\n",
+					 console_num, console->leftover,
+					 line);
+				console->leftover[0] = '\0';
+			} else {
+				dev_info(&oct->pci_dev->dev, "%lu: %s\n",
+					 console_num, line);
+			}
+			line = &console_buffer[i + 1];
+		}
+	}
+
+	/* Save off any leftovers */
+	if (line != &console_buffer[bytes_read]) {
+		console_buffer[bytes_read] = '\0';
+		strcpy(console->leftover, line);
+	}
+}
+
+static void check_console(struct work_struct *work)
+{
+	s32 bytes_read, tries, total_read;
+	struct octeon_console *console;
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct octeon_device *oct = (struct octeon_device *)wk->ctxptr;
+	size_t console_num = wk->ctxul;
+	u32 delay;
+
+	console = &oct->console[console_num];
+	tries = 0;
+	total_read = 0;
+
+	do {
+		/* Take console output regardless of whether it will
+		 * be logged
+		 */
+		bytes_read =
+			octeon_console_read(oct, console_num, console_buffer,
+					    sizeof(console_buffer) - 1, 0);
+		if (bytes_read > 0) {
+			total_read += bytes_read;
+			if (console->waiting) {
+				octeon_console_handle_result(oct, console_num,
+							     console_buffer,
+							     bytes_read);
+			}
+			if (octeon_console_debug_enabled(console_num)) {
+				output_console_line(oct, console, console_num,
+						    console_buffer, bytes_read);
+			}
+		} else if (bytes_read < 0) {
+			dev_err(&oct->pci_dev->dev, "Error reading console %lu, ret=%d\n",
+				console_num, bytes_read);
+		}
+
+		tries++;
+	} while ((bytes_read > 0) && (tries < 16));
+
+	/* If nothing is read after polling the console,
+	 * output any leftovers if any
+	 */
+	if (octeon_console_debug_enabled(console_num) &&
+	    (total_read == 0) && (console->leftover[0])) {
+		dev_info(&oct->pci_dev->dev, "%lu: %s\n",
+			 console_num, console->leftover);
+		console->leftover[0] = '\0';
+	}
+
+	delay = OCTEON_CONSOLE_POLL_INTERVAL_MS;
+
+	schedule_delayed_work(&wk->work, msecs_to_jiffies(delay));
+}
+
+int octeon_init_consoles(struct octeon_device *oct)
+{
+	int ret = 0;
+	u64 addr, size;
+
+	ret = octeon_mem_access_ok(oct);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev, "Memory access not okay'\n");
+		return ret;
+	}
+
+	ret = octeon_named_block_find(oct, OCTEON_PCI_CONSOLE_BLOCK_NAME, &addr,
+				      &size);
+	if (ret) {
+		dev_err(&oct->pci_dev->dev, "Could not find console '%s'\n",
+			OCTEON_PCI_CONSOLE_BLOCK_NAME);
+		return ret;
+	}
+
+	/* num_consoles > 0, is an indication that the consoles
+	 * are accessible
+	 */
+	oct->num_consoles = octeon_read_device_mem32(oct,
+		addr + offsetof(struct octeon_pci_console_desc,
+			num_consoles));
+	oct->console_desc_addr = addr;
+
+	dev_dbg(&oct->pci_dev->dev, "Initialized consoles. %d available\n",
+		oct->num_consoles);
+
+	return ret;
+}
+
+int octeon_add_console(struct octeon_device *oct, u32 console_num)
+{
+	int ret = 0;
+	u32 delay;
+	u64 coreaddr;
+	struct delayed_work *work;
+	struct octeon_console *console;
+
+	if (console_num >= oct->num_consoles) {
+		dev_err(&oct->pci_dev->dev,
+			"trying to read from console number %d when only 0 to %d exist\n",
+			console_num, oct->num_consoles);
+	} else {
+		console = &oct->console[console_num];
+
+		console->waiting = 0;
+
+		coreaddr = oct->console_desc_addr + console_num * 8 +
+			offsetof(struct octeon_pci_console_desc,
+				 console_addr_array);
+		console->addr = octeon_read_device_mem64(oct, coreaddr);
+		coreaddr = console->addr + offsetof(struct octeon_pci_console,
+						    buf_size);
+		console->buffer_size = octeon_read_device_mem32(oct, coreaddr);
+		coreaddr = console->addr + offsetof(struct octeon_pci_console,
+						    input_base_addr);
+		console->input_base_addr =
+			octeon_read_device_mem64(oct, coreaddr);
+		coreaddr = console->addr + offsetof(struct octeon_pci_console,
+						    output_base_addr);
+		console->output_base_addr =
+			octeon_read_device_mem64(oct, coreaddr);
+		console->leftover[0] = '\0';
+
+		work = &oct->console_poll_work[console_num].work;
+
+		INIT_DELAYED_WORK(work, check_console);
+		oct->console_poll_work[console_num].ctxptr = (void *)oct;
+		oct->console_poll_work[console_num].ctxul = console_num;
+		delay = OCTEON_CONSOLE_POLL_INTERVAL_MS;
+		schedule_delayed_work(work, msecs_to_jiffies(delay));
+
+		if (octeon_console_debug_enabled(console_num)) {
+			ret = octeon_console_send_cmd(oct,
+						      "setenv pci_console_active 1",
+						      2000);
+		}
+
+		console->active = 1;
+	}
+
+	return ret;
+}
+
+/**
+ * Removes all consoles
+ *
+ * @param oct         octeon device
+ */
+void octeon_remove_consoles(struct octeon_device *oct)
+{
+	u32 i;
+	struct octeon_console *console;
+
+	for (i = 0; i < oct->num_consoles; i++) {
+		console = &oct->console[i];
+
+		if (!console->active)
+			continue;
+
+		cancel_delayed_work_sync(&oct->console_poll_work[i].
+						work);
+		console->addr = 0;
+		console->buffer_size = 0;
+		console->input_base_addr = 0;
+		console->output_base_addr = 0;
+	}
+
+	oct->num_consoles = 0;
+}
+
+static inline int octeon_console_free_bytes(u32 buffer_size,
+					    u32 wr_idx,
+					    u32 rd_idx)
+{
+	if (rd_idx >= buffer_size || wr_idx >= buffer_size)
+		return -1;
+
+	return ((buffer_size - 1) - (wr_idx - rd_idx)) % buffer_size;
+}
+
+static inline int octeon_console_avail_bytes(u32 buffer_size,
+					     u32 wr_idx,
+					     u32 rd_idx)
+{
+	if (rd_idx >= buffer_size || wr_idx >= buffer_size)
+		return -1;
+
+	return buffer_size - 1 -
+	       octeon_console_free_bytes(buffer_size, wr_idx, rd_idx);
+}
+
+int octeon_console_read(struct octeon_device *oct, u32 console_num,
+			char *buffer, u32 buf_size, u32 flags)
+{
+	int bytes_to_read;
+	u32 rd_idx, wr_idx;
+	struct octeon_console *console;
+
+	if (console_num >= oct->num_consoles) {
+		dev_err(&oct->pci_dev->dev, "Attempted to read from disabled console %d\n",
+			console_num);
+		return 0;
+	}
+
+	console = &oct->console[console_num];
+
+	/* Check to see if any data is available.
+	 * Maybe optimize this with 64-bit read.
+	 */
+	rd_idx = octeon_read_device_mem32(oct, console->addr +
+		offsetof(struct octeon_pci_console, output_read_index));
+	wr_idx = octeon_read_device_mem32(oct, console->addr +
+		offsetof(struct octeon_pci_console, output_write_index));
+
+	bytes_to_read = octeon_console_avail_bytes(console->buffer_size,
+						   wr_idx, rd_idx);
+	if (bytes_to_read <= 0)
+		return bytes_to_read;
+
+	bytes_to_read = MIN(bytes_to_read, (s32)buf_size);
+
+	/* Check to see if what we want to read is not contiguous, and limit
+	 * ourselves to the contiguous block
+	 */
+	if (rd_idx + bytes_to_read >= console->buffer_size)
+		bytes_to_read = console->buffer_size - rd_idx;
+
+	octeon_pci_read_core_mem(oct, console->output_base_addr + rd_idx,
+				 buffer, bytes_to_read);
+	octeon_write_device_mem32(oct, console->addr +
+				  offsetof(struct octeon_pci_console,
+					   output_read_index),
+				  (rd_idx + bytes_to_read) %
+				  console->buffer_size);
+
+	return bytes_to_read;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
new file mode 100644
index 000000000000..0d3106b464b2
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -0,0 +1,1309 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/crc32.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+/** Default configuration
+ *  for CN66XX OCTEON Models.
+ */
+static struct octeon_config default_cn66xx_conf = {
+	.card_type                              = LIO_210SV,
+	.card_name                              = LIO_210SV_NAME,
+
+	/** IQ attributes */
+	.iq					= {
+		.max_iqs			= CN6XXX_CFG_IO_QUEUES,
+		.pending_list_size		=
+			(CN6XXX_MAX_IQ_DESCRIPTORS * CN6XXX_CFG_IO_QUEUES),
+		.instr_type			= OCTEON_64BYTE_INSTR,
+		.db_min				= CN6XXX_DB_MIN,
+		.db_timeout			= CN6XXX_DB_TIMEOUT,
+	}
+	,
+
+	/** OQ attributes */
+	.oq					= {
+		.max_oqs			= CN6XXX_CFG_IO_QUEUES,
+		.info_ptr			= OCTEON_OQ_INFOPTR_MODE,
+		.refill_threshold		= CN6XXX_OQ_REFIL_THRESHOLD,
+		.oq_intr_pkt			= CN6XXX_OQ_INTR_PKT,
+		.oq_intr_time			= CN6XXX_OQ_INTR_TIME,
+		.pkts_per_intr			= CN6XXX_OQ_PKTSPER_INTR,
+	}
+	,
+
+	.num_nic_ports				= DEFAULT_NUM_NIC_PORTS_66XX,
+	.num_def_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+	.num_def_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+	.def_rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+	/* For ethernet interface 0:  Port cfg Attributes */
+	.nic_if_cfg[0] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 0,
+	},
+
+	.nic_if_cfg[1] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 1,
+	},
+
+	/** Miscellaneous attributes */
+	.misc					= {
+		/* Host driver link query interval */
+		.oct_link_query_interval	= 100,
+
+		/* Octeon link query interval */
+		.host_link_query_interval	= 500,
+
+		.enable_sli_oq_bp		= 0,
+
+		/* Control queue group */
+		.ctrlq_grp			= 1,
+	}
+	,
+};
+
+/** Default configuration
+ *  for CN68XX OCTEON Model.
+ */
+
+static struct octeon_config default_cn68xx_conf = {
+	.card_type                              = LIO_410NV,
+	.card_name                              = LIO_410NV_NAME,
+
+	/** IQ attributes */
+	.iq					= {
+		.max_iqs			= CN6XXX_CFG_IO_QUEUES,
+		.pending_list_size		=
+			(CN6XXX_MAX_IQ_DESCRIPTORS * CN6XXX_CFG_IO_QUEUES),
+		.instr_type			= OCTEON_64BYTE_INSTR,
+		.db_min				= CN6XXX_DB_MIN,
+		.db_timeout			= CN6XXX_DB_TIMEOUT,
+	}
+	,
+
+	/** OQ attributes */
+	.oq					= {
+		.max_oqs			= CN6XXX_CFG_IO_QUEUES,
+		.info_ptr			= OCTEON_OQ_INFOPTR_MODE,
+		.refill_threshold		= CN6XXX_OQ_REFIL_THRESHOLD,
+		.oq_intr_pkt			= CN6XXX_OQ_INTR_PKT,
+		.oq_intr_time			= CN6XXX_OQ_INTR_TIME,
+		.pkts_per_intr			= CN6XXX_OQ_PKTSPER_INTR,
+	}
+	,
+
+	.num_nic_ports				= DEFAULT_NUM_NIC_PORTS_68XX,
+	.num_def_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+	.num_def_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+	.def_rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+	.nic_if_cfg[0] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 0,
+	},
+
+	.nic_if_cfg[1] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 1,
+	},
+
+	.nic_if_cfg[2] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 2,
+	},
+
+	.nic_if_cfg[3] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 3,
+	},
+
+	/** Miscellaneous attributes */
+	.misc					= {
+		/* Host driver link query interval */
+		.oct_link_query_interval	= 100,
+
+		/* Octeon link query interval */
+		.host_link_query_interval	= 500,
+
+		.enable_sli_oq_bp		= 0,
+
+		/* Control queue group */
+		.ctrlq_grp			= 1,
+	}
+	,
+};
+
+/** Default configuration
+ *  for CN68XX OCTEON Model.
+ */
+static struct octeon_config default_cn68xx_210nv_conf = {
+	.card_type                              = LIO_210NV,
+	.card_name                              = LIO_210NV_NAME,
+
+	/** IQ attributes */
+
+	.iq					= {
+		.max_iqs			= CN6XXX_CFG_IO_QUEUES,
+		.pending_list_size		=
+			(CN6XXX_MAX_IQ_DESCRIPTORS * CN6XXX_CFG_IO_QUEUES),
+		.instr_type			= OCTEON_64BYTE_INSTR,
+		.db_min				= CN6XXX_DB_MIN,
+		.db_timeout			= CN6XXX_DB_TIMEOUT,
+	}
+	,
+
+	/** OQ attributes */
+	.oq					= {
+		.max_oqs			= CN6XXX_CFG_IO_QUEUES,
+		.info_ptr			= OCTEON_OQ_INFOPTR_MODE,
+		.refill_threshold		= CN6XXX_OQ_REFIL_THRESHOLD,
+		.oq_intr_pkt			= CN6XXX_OQ_INTR_PKT,
+		.oq_intr_time			= CN6XXX_OQ_INTR_TIME,
+		.pkts_per_intr			= CN6XXX_OQ_PKTSPER_INTR,
+	}
+	,
+
+	.num_nic_ports			= DEFAULT_NUM_NIC_PORTS_68XX_210NV,
+	.num_def_rx_descs		= CN6XXX_MAX_OQ_DESCRIPTORS,
+	.num_def_tx_descs		= CN6XXX_MAX_IQ_DESCRIPTORS,
+	.def_rx_buf_size		= CN6XXX_OQ_BUF_SIZE,
+
+	.nic_if_cfg[0] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 0,
+	},
+
+	.nic_if_cfg[1] = {
+		/* Max Txqs: Half for each of the two ports :max_iq/2 */
+		.max_txqs			= MAX_TXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_txqs */
+		.num_txqs			= DEF_TXQS_PER_INTF,
+
+		/* Max Rxqs: Half for each of the two ports :max_oq/2  */
+		.max_rxqs			= MAX_RXQS_PER_INTF,
+
+		/* Actual configured value. Range could be: 1...max_rxqs */
+		.num_rxqs			= DEF_RXQS_PER_INTF,
+
+		/* Num of desc for rx rings */
+		.num_rx_descs			= CN6XXX_MAX_OQ_DESCRIPTORS,
+
+		/* Num of desc for tx rings */
+		.num_tx_descs			= CN6XXX_MAX_IQ_DESCRIPTORS,
+
+		/* SKB size, We need not change buf size even for Jumbo frames.
+		 * Octeon can send jumbo frames in 4 consecutive descriptors,
+		 */
+		.rx_buf_size			= CN6XXX_OQ_BUF_SIZE,
+
+		.base_queue			= BASE_QUEUE_NOT_REQUESTED,
+
+		.gmx_port_id			= 1,
+	},
+
+	/** Miscellaneous attributes */
+	.misc					= {
+		/* Host driver link query interval */
+		.oct_link_query_interval	= 100,
+
+		/* Octeon link query interval */
+		.host_link_query_interval	= 500,
+
+		.enable_sli_oq_bp		= 0,
+
+		/* Control queue group */
+		.ctrlq_grp			= 1,
+	}
+	,
+};
+
+enum {
+	OCTEON_CONFIG_TYPE_DEFAULT = 0,
+	NUM_OCTEON_CONFS,
+};
+
+static struct octeon_config_ptr {
+	u32 conf_type;
+} oct_conf_info[MAX_OCTEON_DEVICES] = {
+	{
+		OCTEON_CONFIG_TYPE_DEFAULT,
+	}, {
+		OCTEON_CONFIG_TYPE_DEFAULT,
+	}, {
+		OCTEON_CONFIG_TYPE_DEFAULT,
+	}, {
+		OCTEON_CONFIG_TYPE_DEFAULT,
+	},
+};
+
+static char oct_dev_state_str[OCT_DEV_STATES + 1][32] = {
+	"BEGIN",	"PCI-MAP-DONE",	      "DISPATCH-INIT-DONE",
+	"IQ-INIT-DONE", "SCBUFF-POOL-INIT-DONE", "RESPLIST-INIT-DONE",
+	"DROQ-INIT-DONE", "IO-QUEUES-INIT-DONE", "CONSOLE-INIT-DONE",
+	"HOST-READY",	"CORE-READY",	      "RUNNING",	   "IN-RESET",
+	"INVALID"
+};
+
+static char oct_dev_app_str[CVM_DRV_APP_COUNT + 1][32] = {
+	"BASE", "NIC", "UNKNOWN"};
+
+static struct octeon_device *octeon_device[MAX_OCTEON_DEVICES];
+static u32 octeon_device_count;
+
+static struct octeon_core_setup core_setup[MAX_OCTEON_DEVICES];
+
+static void oct_set_config_info(int oct_id, int conf_type)
+{
+	if (conf_type < 0 || conf_type > (NUM_OCTEON_CONFS - 1))
+		conf_type = OCTEON_CONFIG_TYPE_DEFAULT;
+	oct_conf_info[oct_id].conf_type = conf_type;
+}
+
+void octeon_init_device_list(int conf_type)
+{
+	int i;
+
+	memset(octeon_device, 0, (sizeof(void *) * MAX_OCTEON_DEVICES));
+	for (i = 0; i <  MAX_OCTEON_DEVICES; i++)
+		oct_set_config_info(i, conf_type);
+}
+
+static void *__retrieve_octeon_config_info(struct octeon_device *oct,
+					   u16 card_type)
+{
+	u32 oct_id = oct->octeon_id;
+	void *ret = NULL;
+
+	switch (oct_conf_info[oct_id].conf_type) {
+	case OCTEON_CONFIG_TYPE_DEFAULT:
+		if (oct->chip_id == OCTEON_CN66XX) {
+			ret = (void *)&default_cn66xx_conf;
+		} else if ((oct->chip_id == OCTEON_CN68XX) &&
+			   (card_type == LIO_210NV)) {
+			ret =  (void *)&default_cn68xx_210nv_conf;
+		} else if ((oct->chip_id == OCTEON_CN68XX) &&
+			   (card_type == LIO_410NV)) {
+			ret =  (void *)&default_cn68xx_conf;
+		}
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+static int __verify_octeon_config_info(struct octeon_device *oct, void *conf)
+{
+	switch (oct->chip_id) {
+	case OCTEON_CN66XX:
+	case OCTEON_CN68XX:
+		return lio_validate_cn6xxx_config_info(oct, conf);
+
+	default:
+		break;
+	}
+
+	return 1;
+}
+
+void *oct_get_config_info(struct octeon_device *oct, u16 card_type)
+{
+	void *conf = NULL;
+
+	conf = __retrieve_octeon_config_info(oct, card_type);
+	if (!conf)
+		return NULL;
+
+	if (__verify_octeon_config_info(oct, conf)) {
+		dev_err(&oct->pci_dev->dev, "Configuration verification failed\n");
+		return NULL;
+	}
+
+	return conf;
+}
+
+char *lio_get_state_string(atomic_t *state_ptr)
+{
+	s32 istate = (s32)atomic_read(state_ptr);
+
+	if (istate > OCT_DEV_STATES || istate < 0)
+		return oct_dev_state_str[OCT_DEV_STATE_INVALID];
+	return oct_dev_state_str[istate];
+}
+
+static char *get_oct_app_string(u32 app_mode)
+{
+	if (app_mode <= CVM_DRV_APP_END)
+		return oct_dev_app_str[app_mode - CVM_DRV_APP_START];
+	return oct_dev_app_str[CVM_DRV_INVALID_APP - CVM_DRV_APP_START];
+}
+
+int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
+			     size_t size)
+{
+	int ret = 0;
+	u8 *p;
+	u8 *buffer;
+	u32 crc32_result;
+	u64 load_addr;
+	u32 image_len;
+	struct octeon_firmware_file_header *h;
+	u32 i;
+
+	if (size < sizeof(struct octeon_firmware_file_header)) {
+		dev_err(&oct->pci_dev->dev, "Firmware file too small (%d < %d).\n",
+			(u32)size,
+			(u32)sizeof(struct octeon_firmware_file_header));
+		return -EINVAL;
+	}
+
+	h = (struct octeon_firmware_file_header *)data;
+
+	if (be32_to_cpu(h->magic) != LIO_NIC_MAGIC) {
+		dev_err(&oct->pci_dev->dev, "Unrecognized firmware file.\n");
+		return -EINVAL;
+	}
+
+	crc32_result =
+		crc32(~0, data,
+		      sizeof(struct octeon_firmware_file_header) -
+		      sizeof(u32)) ^ ~0U;
+	if (crc32_result != be32_to_cpu(h->crc32)) {
+		dev_err(&oct->pci_dev->dev, "Firmware CRC mismatch (0x%08x != 0x%08x).\n",
+			crc32_result, be32_to_cpu(h->crc32));
+		return -EINVAL;
+	}
+
+	if (memcmp(LIQUIDIO_VERSION, h->version, strlen(LIQUIDIO_VERSION))) {
+		dev_err(&oct->pci_dev->dev, "Unmatched firmware version. Expected %s, got %s.\n",
+			LIQUIDIO_VERSION, h->version);
+		return -EINVAL;
+	}
+
+	if (be32_to_cpu(h->num_images) > LIO_MAX_IMAGES) {
+		dev_err(&oct->pci_dev->dev, "Too many images in firmware file (%d).\n",
+			be32_to_cpu(h->num_images));
+		return -EINVAL;
+	}
+
+	dev_info(&oct->pci_dev->dev, "Firmware version: %s\n", h->version);
+	snprintf(oct->fw_info.liquidio_firmware_version, 32, "LIQUIDIO: %s",
+		 h->version);
+
+	buffer = kmalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	memcpy(buffer, data, size);
+
+	p = buffer + sizeof(struct octeon_firmware_file_header);
+
+	/* load all images */
+	for (i = 0; i < be32_to_cpu(h->num_images); i++) {
+		load_addr = be64_to_cpu(h->desc[i].addr);
+		image_len = be32_to_cpu(h->desc[i].len);
+
+		/* validate the image */
+		crc32_result = crc32(~0, p, image_len) ^ ~0U;
+		if (crc32_result != be32_to_cpu(h->desc[i].crc32)) {
+			dev_err(&oct->pci_dev->dev,
+				"Firmware CRC mismatch in image %d (0x%08x != 0x%08x).\n",
+				i, crc32_result,
+				be32_to_cpu(h->desc[i].crc32));
+			ret = -EINVAL;
+			goto done_downloading;
+		}
+
+		/* download the image */
+		octeon_pci_write_core_mem(oct, load_addr, p, image_len);
+
+		p += image_len;
+		dev_dbg(&oct->pci_dev->dev,
+			"Downloaded image %d (%d bytes) to address 0x%016llx\n",
+			i, image_len, load_addr);
+	}
+
+	/* Invoke the bootcmd */
+	ret = octeon_console_send_cmd(oct, h->bootcmd, 50);
+
+done_downloading:
+	kfree(buffer);
+
+	return ret;
+}
+
+void octeon_free_device_mem(struct octeon_device *oct)
+{
+	u32 i;
+
+	for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES; i++) {
+		/* could check  mask as well */
+		if (oct->droq[i])
+			vfree(oct->droq[i]);
+	}
+
+	for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+		/* could check mask as well */
+		if (oct->instr_queue[i])
+			vfree(oct->instr_queue[i]);
+	}
+
+	i = oct->octeon_id;
+	vfree(oct);
+
+	octeon_device[i] = NULL;
+	octeon_device_count--;
+}
+
+static struct octeon_device *octeon_allocate_device_mem(u32 pci_id,
+							u32 priv_size)
+{
+	struct octeon_device *oct;
+	u8 *buf = NULL;
+	u32 octdevsize = 0, configsize = 0, size;
+
+	switch (pci_id) {
+	case OCTEON_CN68XX:
+	case OCTEON_CN66XX:
+		configsize = sizeof(struct octeon_cn6xxx);
+		break;
+
+	default:
+		pr_err("%s: Unknown PCI Device: 0x%x\n",
+		       __func__,
+		       pci_id);
+		return NULL;
+	}
+
+	if (configsize & 0x7)
+		configsize += (8 - (configsize & 0x7));
+
+	octdevsize = sizeof(struct octeon_device);
+	if (octdevsize & 0x7)
+		octdevsize += (8 - (octdevsize & 0x7));
+
+	if (priv_size & 0x7)
+		priv_size += (8 - (priv_size & 0x7));
+
+	size = octdevsize + priv_size + configsize +
+		(sizeof(struct octeon_dispatch) * DISPATCH_LIST_SIZE);
+
+	buf = vmalloc(size);
+	if (!buf)
+		return NULL;
+
+	memset(buf, 0, size);
+
+	oct = (struct octeon_device *)buf;
+	oct->priv = (void *)(buf + octdevsize);
+	oct->chip = (void *)(buf + octdevsize + priv_size);
+	oct->dispatch.dlist = (struct octeon_dispatch *)
+		(buf + octdevsize + priv_size + configsize);
+
+	return oct;
+}
+
+struct octeon_device *octeon_allocate_device(u32 pci_id,
+					     u32 priv_size)
+{
+	u32 oct_idx = 0;
+	struct octeon_device *oct = NULL;
+
+	for (oct_idx = 0; oct_idx < MAX_OCTEON_DEVICES; oct_idx++)
+		if (!octeon_device[oct_idx])
+			break;
+
+	if (oct_idx == MAX_OCTEON_DEVICES)
+		return NULL;
+
+	oct = octeon_allocate_device_mem(pci_id, priv_size);
+	if (!oct)
+		return NULL;
+
+	spin_lock_init(&oct->pci_win_lock);
+	spin_lock_init(&oct->mem_access_lock);
+
+	octeon_device_count++;
+	octeon_device[oct_idx] = oct;
+
+	oct->octeon_id = oct_idx;
+	snprintf((oct->device_name), sizeof(oct->device_name),
+		 "LiquidIO%d", (oct->octeon_id));
+
+	return oct;
+}
+
+int octeon_setup_instr_queues(struct octeon_device *oct)
+{
+	u32 i, num_iqs = 0;
+	u32 num_descs = 0;
+
+	/* this causes queue 0 to be default queue */
+	if (OCTEON_CN6XXX(oct)) {
+		num_iqs = 1;
+		num_descs =
+			CFG_GET_NUM_DEF_TX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
+	}
+
+	oct->num_iqs = 0;
+
+	for (i = 0; i < num_iqs; i++) {
+		oct->instr_queue[i] =
+			vmalloc(sizeof(struct octeon_instr_queue));
+		if (!oct->instr_queue[i])
+			return 1;
+
+		memset(oct->instr_queue[i], 0,
+		       sizeof(struct octeon_instr_queue));
+
+		oct->instr_queue[i]->app_ctx = (void *)(size_t)i;
+		if (octeon_init_instr_queue(oct, i, num_descs))
+			return 1;
+
+		oct->num_iqs++;
+	}
+
+	return 0;
+}
+
+int octeon_setup_output_queues(struct octeon_device *oct)
+{
+	u32 i, num_oqs = 0;
+	u32 num_descs = 0;
+	u32 desc_size = 0;
+
+	/* this causes queue 0 to be default queue */
+	if (OCTEON_CN6XXX(oct)) {
+		/* CFG_GET_OQ_MAX_BASE_Q(CHIP_FIELD(oct, cn6xxx, conf)); */
+		num_oqs = 1;
+		num_descs =
+			CFG_GET_NUM_DEF_RX_DESCS(CHIP_FIELD(oct, cn6xxx, conf));
+		desc_size =
+			CFG_GET_DEF_RX_BUF_SIZE(CHIP_FIELD(oct, cn6xxx, conf));
+	}
+
+	oct->num_oqs = 0;
+
+	for (i = 0; i < num_oqs; i++) {
+		oct->droq[i] = vmalloc(sizeof(*oct->droq[i]));
+		if (!oct->droq[i])
+			return 1;
+
+		memset(oct->droq[i], 0, sizeof(struct octeon_droq));
+
+		if (octeon_init_droq(oct, i, num_descs, desc_size, NULL))
+			return 1;
+
+		oct->num_oqs++;
+	}
+
+	return 0;
+}
+
+void octeon_set_io_queues_off(struct octeon_device *oct)
+{
+	/* Disable the i/p and o/p queues for this Octeon. */
+
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_INSTR_ENB, 0);
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_ENB, 0);
+}
+
+void octeon_set_droq_pkt_op(struct octeon_device *oct,
+			    u32 q_no,
+			    u32 enable)
+{
+	u32 reg_val = 0;
+
+	/* Disable the i/p and o/p queues for this Octeon. */
+	reg_val = octeon_read_csr(oct, CN6XXX_SLI_PKT_OUT_ENB);
+
+	if (enable)
+		reg_val = reg_val | (1 << q_no);
+	else
+		reg_val = reg_val & (~(1 << q_no));
+
+	octeon_write_csr(oct, CN6XXX_SLI_PKT_OUT_ENB, reg_val);
+}
+
+int octeon_init_dispatch_list(struct octeon_device *oct)
+{
+	u32 i;
+
+	oct->dispatch.count = 0;
+
+	for (i = 0; i < DISPATCH_LIST_SIZE; i++) {
+		oct->dispatch.dlist[i].opcode = 0;
+		INIT_LIST_HEAD(&oct->dispatch.dlist[i].list);
+	}
+
+	for (i = 0; i <= REQTYPE_LAST; i++)
+		octeon_register_reqtype_free_fn(oct, i, NULL);
+
+	spin_lock_init(&oct->dispatch.lock);
+
+	return 0;
+}
+
+void octeon_delete_dispatch_list(struct octeon_device *oct)
+{
+	u32 i;
+	struct list_head freelist, *temp, *tmp2;
+
+	INIT_LIST_HEAD(&freelist);
+
+	spin_lock_bh(&oct->dispatch.lock);
+
+	for (i = 0; i < DISPATCH_LIST_SIZE; i++) {
+		struct list_head *dispatch;
+
+		dispatch = &oct->dispatch.dlist[i].list;
+		while (dispatch->next != dispatch) {
+			temp = dispatch->next;
+			list_del(temp);
+			list_add_tail(temp, &freelist);
+		}
+
+		oct->dispatch.dlist[i].opcode = 0;
+	}
+
+	oct->dispatch.count = 0;
+
+	spin_unlock_bh(&oct->dispatch.lock);
+
+	list_for_each_safe(temp, tmp2, &freelist) {
+		list_del(temp);
+		vfree(temp);
+	}
+}
+
+octeon_dispatch_fn_t
+octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
+		    u16 subcode)
+{
+	u32 idx;
+	struct list_head *dispatch;
+	octeon_dispatch_fn_t fn = NULL;
+	u16 combined_opcode = OPCODE_SUBCODE(opcode, subcode);
+
+	idx = combined_opcode & OCTEON_OPCODE_MASK;
+
+	spin_lock_bh(&octeon_dev->dispatch.lock);
+
+	if (octeon_dev->dispatch.count == 0) {
+		spin_unlock_bh(&octeon_dev->dispatch.lock);
+		return NULL;
+	}
+
+	if (!(octeon_dev->dispatch.dlist[idx].opcode)) {
+		spin_unlock_bh(&octeon_dev->dispatch.lock);
+		return NULL;
+	}
+
+	if (octeon_dev->dispatch.dlist[idx].opcode == combined_opcode) {
+		fn = octeon_dev->dispatch.dlist[idx].dispatch_fn;
+	} else {
+		list_for_each(dispatch,
+			      &octeon_dev->dispatch.dlist[idx].list) {
+			if (((struct octeon_dispatch *)dispatch)->opcode ==
+			    combined_opcode) {
+				fn = ((struct octeon_dispatch *)
+				      dispatch)->dispatch_fn;
+				break;
+			}
+		}
+	}
+
+	spin_unlock_bh(&octeon_dev->dispatch.lock);
+	return fn;
+}
+
+/* octeon_register_dispatch_fn
+ * Parameters:
+ *   octeon_id - id of the octeon device.
+ *   opcode    - opcode for which driver should call the registered function
+ *   subcode   - subcode for which driver should call the registered function
+ *   fn        - The function to call when a packet with "opcode" arrives in
+ *		  octeon output queues.
+ *   fn_arg    - The argument to be passed when calling function "fn".
+ * Description:
+ *   Registers a function and its argument to be called when a packet
+ *   arrives in Octeon output queues with "opcode".
+ * Returns:
+ *   Success: 0
+ *   Failure: 1
+ * Locks:
+ *   No locks are held.
+ */
+int
+octeon_register_dispatch_fn(struct octeon_device *oct,
+			    u16 opcode,
+			    u16 subcode,
+			    octeon_dispatch_fn_t fn, void *fn_arg)
+{
+	u32 idx;
+	octeon_dispatch_fn_t pfn;
+	u16 combined_opcode = OPCODE_SUBCODE(opcode, subcode);
+
+	idx = combined_opcode & OCTEON_OPCODE_MASK;
+
+	spin_lock_bh(&oct->dispatch.lock);
+	/* Add dispatch function to first level of lookup table */
+	if (oct->dispatch.dlist[idx].opcode == 0) {
+		oct->dispatch.dlist[idx].opcode = combined_opcode;
+		oct->dispatch.dlist[idx].dispatch_fn = fn;
+		oct->dispatch.dlist[idx].arg = fn_arg;
+		oct->dispatch.count++;
+		spin_unlock_bh(&oct->dispatch.lock);
+		return 0;
+	}
+
+	spin_unlock_bh(&oct->dispatch.lock);
+
+	/* Check if there was a function already registered for this
+	 * opcode/subcode.
+	 */
+	pfn = octeon_get_dispatch(oct, opcode, subcode);
+	if (!pfn) {
+		struct octeon_dispatch *dispatch;
+
+		dev_dbg(&oct->pci_dev->dev,
+			"Adding opcode to dispatch list linked list\n");
+		dispatch = (struct octeon_dispatch *)
+			   vmalloc(sizeof(struct octeon_dispatch));
+		if (!dispatch) {
+			dev_err(&oct->pci_dev->dev,
+				"No memory to add dispatch function\n");
+			return 1;
+		}
+		dispatch->opcode = combined_opcode;
+		dispatch->dispatch_fn = fn;
+		dispatch->arg = fn_arg;
+
+		/* Add dispatch function to linked list of fn ptrs
+		 * at the hashed index.
+		 */
+		spin_lock_bh(&oct->dispatch.lock);
+		list_add(&dispatch->list, &oct->dispatch.dlist[idx].list);
+		oct->dispatch.count++;
+		spin_unlock_bh(&oct->dispatch.lock);
+
+	} else {
+		dev_err(&oct->pci_dev->dev,
+			"Found previously registered dispatch fn for opcode/subcode: %x/%x\n",
+			opcode, subcode);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* octeon_unregister_dispatch_fn
+ * Parameters:
+ *   oct       - octeon device
+ *   opcode    - driver should unregister the function for this opcode
+ *   subcode   - driver should unregister the function for this subcode
+ * Description:
+ *   Unregister the function set for this opcode+subcode.
+ * Returns:
+ *   Success: 0
+ *   Failure: 1
+ * Locks:
+ *   No locks are held.
+ */
+int
+octeon_unregister_dispatch_fn(struct octeon_device *oct, u16 opcode,
+			      u16 subcode)
+{
+	int retval = 0;
+	u32 idx;
+	struct list_head *dispatch, *dfree = NULL, *tmp2;
+	u16 combined_opcode = OPCODE_SUBCODE(opcode, subcode);
+
+	idx = combined_opcode & OCTEON_OPCODE_MASK;
+
+	spin_lock_bh(&oct->dispatch.lock);
+
+	if (oct->dispatch.count == 0) {
+		spin_unlock_bh(&oct->dispatch.lock);
+		dev_err(&oct->pci_dev->dev,
+			"No dispatch functions registered for this device\n");
+		return 1;
+	}
+
+	if (oct->dispatch.dlist[idx].opcode == combined_opcode) {
+		dispatch = &oct->dispatch.dlist[idx].list;
+		if (dispatch->next != dispatch) {
+			dispatch = dispatch->next;
+			oct->dispatch.dlist[idx].opcode =
+				((struct octeon_dispatch *)dispatch)->opcode;
+			oct->dispatch.dlist[idx].dispatch_fn =
+				((struct octeon_dispatch *)
+				 dispatch)->dispatch_fn;
+			oct->dispatch.dlist[idx].arg =
+				((struct octeon_dispatch *)dispatch)->arg;
+			list_del(dispatch);
+			dfree = dispatch;
+		} else {
+			oct->dispatch.dlist[idx].opcode = 0;
+			oct->dispatch.dlist[idx].dispatch_fn = NULL;
+			oct->dispatch.dlist[idx].arg = NULL;
+		}
+	} else {
+		retval = 1;
+		list_for_each_safe(dispatch, tmp2,
+				   &(oct->dispatch.dlist[idx].
+				     list)) {
+			if (((struct octeon_dispatch *)dispatch)->opcode ==
+			    combined_opcode) {
+				list_del(dispatch);
+				dfree = dispatch;
+				retval = 0;
+			}
+		}
+	}
+
+	if (!retval)
+		oct->dispatch.count--;
+
+	spin_unlock_bh(&oct->dispatch.lock);
+
+	if (dfree)
+		vfree(dfree);
+
+	return retval;
+}
+
+int octeon_core_drv_init(struct octeon_recv_info *recv_info, void *buf)
+{
+	u32 i;
+	char app_name[16];
+	struct octeon_device *oct = (struct octeon_device *)buf;
+	struct octeon_recv_pkt *recv_pkt = recv_info->recv_pkt;
+	struct octeon_core_setup *cs = NULL;
+	u32 num_nic_ports = 0;
+
+	if (OCTEON_CN6XXX(oct))
+		num_nic_ports =
+			CFG_GET_NUM_NIC_PORTS(CHIP_FIELD(oct, cn6xxx, conf));
+
+	if (atomic_read(&oct->status) >= OCT_DEV_RUNNING) {
+		dev_err(&oct->pci_dev->dev, "Received CORE OK when device state is 0x%x\n",
+			atomic_read(&oct->status));
+		goto core_drv_init_err;
+	}
+
+	strncpy(app_name,
+		get_oct_app_string(
+		(u32)recv_pkt->rh.r_core_drv_init.app_mode),
+		sizeof(app_name) - 1);
+	oct->app_mode = (u32)recv_pkt->rh.r_core_drv_init.app_mode;
+	if (recv_pkt->rh.r_core_drv_init.app_mode == CVM_DRV_NIC_APP) {
+		oct->fw_info.max_nic_ports =
+			(u32)recv_pkt->rh.r_core_drv_init.max_nic_ports;
+		oct->fw_info.num_gmx_ports =
+			(u32)recv_pkt->rh.r_core_drv_init.num_gmx_ports;
+	}
+
+	if (oct->fw_info.max_nic_ports < num_nic_ports) {
+		dev_err(&oct->pci_dev->dev,
+			"Config has more ports than firmware allows (%d > %d).\n",
+			num_nic_ports, oct->fw_info.max_nic_ports);
+		goto core_drv_init_err;
+	}
+	oct->fw_info.app_cap_flags = recv_pkt->rh.r_core_drv_init.app_cap_flags;
+	oct->fw_info.app_mode = (u32)recv_pkt->rh.r_core_drv_init.app_mode;
+
+	atomic_set(&oct->status, OCT_DEV_CORE_OK);
+
+	cs = &core_setup[oct->octeon_id];
+
+	if (recv_pkt->buffer_size[0] != sizeof(*cs)) {
+		dev_dbg(&oct->pci_dev->dev, "Core setup bytes expected %u found %d\n",
+			(u32)sizeof(*cs),
+			recv_pkt->buffer_size[0]);
+	}
+
+	memcpy(cs, get_rbd(recv_pkt->buffer_ptr[0]), sizeof(*cs));
+	strncpy(oct->boardinfo.name, cs->boardname, OCT_BOARD_NAME);
+	strncpy(oct->boardinfo.serial_number, cs->board_serial_number,
+		OCT_SERIAL_LEN);
+
+	octeon_swap_8B_data((u64 *)cs, (sizeof(*cs) >> 3));
+
+	oct->boardinfo.major = cs->board_rev_major;
+	oct->boardinfo.minor = cs->board_rev_minor;
+
+	dev_info(&oct->pci_dev->dev,
+		 "Running %s (%llu Hz)\n",
+		 app_name, CVM_CAST64(cs->corefreq));
+
+core_drv_init_err:
+	for (i = 0; i < recv_pkt->buffer_count; i++)
+		recv_buffer_free(recv_pkt->buffer_ptr[i]);
+	octeon_free_recv_info(recv_info);
+	return 0;
+}
+
+int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no)
+
+{
+	if (oct && (q_no < MAX_OCTEON_INSTR_QUEUES) &&
+	    (oct->io_qmask.iq & (1UL << q_no)))
+		return oct->instr_queue[q_no]->max_count;
+
+	return -1;
+}
+
+int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no)
+{
+	if (oct && (q_no < MAX_OCTEON_OUTPUT_QUEUES) &&
+	    (oct->io_qmask.oq & (1UL << q_no)))
+		return oct->droq[q_no]->max_count;
+	return -1;
+}
+
+/* Retruns the host firmware handshake OCTEON specific configuration */
+struct octeon_config *octeon_get_conf(struct octeon_device *oct)
+{
+	struct octeon_config *default_oct_conf = NULL;
+
+	/* check the OCTEON Device model & return the corresponding octeon
+	 * configuration
+	 */
+
+	if (OCTEON_CN6XXX(oct)) {
+		default_oct_conf =
+			(struct octeon_config *)(CHIP_FIELD(oct, cn6xxx, conf));
+	}
+
+	return default_oct_conf;
+}
+
+/* scratch register address is same in all the OCT-II and CN70XX models */
+#define CNXX_SLI_SCRATCH1   0x3C0
+
+/** Get the octeon device pointer.
+ *  @param octeon_id  - The id for which the octeon device pointer is required.
+ *  @return Success: Octeon device pointer.
+ *  @return Failure: NULL.
+ */
+struct octeon_device *lio_get_device(u32 octeon_id)
+{
+	if (octeon_id >= MAX_OCTEON_DEVICES)
+		return NULL;
+	else
+		return octeon_device[octeon_id];
+}
+
+u64 lio_pci_readq(struct octeon_device *oct, u64 addr)
+{
+	u64 val64;
+	unsigned long flags;
+	u32 val32, addrhi;
+
+	spin_lock_irqsave(&oct->pci_win_lock, flags);
+
+	/* The windowed read happens when the LSB of the addr is written.
+	 * So write MSB first
+	 */
+	addrhi = (addr >> 32);
+	if ((oct->chip_id == OCTEON_CN66XX) || (oct->chip_id == OCTEON_CN68XX))
+		addrhi |= 0x00060000;
+	writel(addrhi, oct->reg_list.pci_win_rd_addr_hi);
+
+	/* Read back to preserve ordering of writes */
+	val32 = readl(oct->reg_list.pci_win_rd_addr_hi);
+
+	writel(addr & 0xffffffff, oct->reg_list.pci_win_rd_addr_lo);
+	val32 = readl(oct->reg_list.pci_win_rd_addr_lo);
+
+	val64 = readq(oct->reg_list.pci_win_rd_data);
+
+	spin_unlock_irqrestore(&oct->pci_win_lock, flags);
+
+	return val64;
+}
+
+void lio_pci_writeq(struct octeon_device *oct,
+		    u64 val,
+		    u64 addr)
+{
+	u32 val32;
+	unsigned long flags;
+
+	spin_lock_irqsave(&oct->pci_win_lock, flags);
+
+	writeq(addr, oct->reg_list.pci_win_wr_addr);
+
+	/* The write happens when the LSB is written. So write MSB first. */
+	writel(val >> 32, oct->reg_list.pci_win_wr_data_hi);
+	/* Read the MSB to ensure ordering of writes. */
+	val32 = readl(oct->reg_list.pci_win_wr_data_hi);
+
+	writel(val & 0xffffffff, oct->reg_list.pci_win_wr_data_lo);
+
+	spin_unlock_irqrestore(&oct->pci_win_lock, flags);
+}
+
+int octeon_mem_access_ok(struct octeon_device *oct)
+{
+	u64 access_okay = 0;
+
+	/* Check to make sure a DDR interface is enabled */
+	u64 lmc0_reset_ctl = lio_pci_readq(oct, CN6XXX_LMC0_RESET_CTL);
+
+	access_okay = (lmc0_reset_ctl & CN6XXX_LMC0_RESET_CTL_DDR3RST_MASK);
+
+	return access_okay ? 0 : 1;
+}
+
+int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
+{
+	int ret = 1;
+	u32 ms;
+
+	if (!timeout)
+		return ret;
+
+	while (*timeout == 0)
+		schedule_timeout_uninterruptible(HZ / 10);
+
+	for (ms = 0; (ret != 0) && ((*timeout == 0) || (ms <= *timeout));
+	     ms += HZ / 10) {
+		ret = octeon_mem_access_ok(oct);
+
+		/* wait 100 ms */
+		if (ret)
+			schedule_timeout_uninterruptible(HZ / 10);
+	}
+
+	return ret;
+}
+
+/** Get the octeon id assigned to the octeon device passed as argument.
+ *  This function is exported to other modules.
+ *  @param dev - octeon device pointer passed as a void *.
+ *  @return octeon device id
+ */
+int lio_get_device_id(void *dev)
+{
+	struct octeon_device *octeon_dev = (struct octeon_device *)dev;
+	u32 i;
+
+	for (i = 0; i < MAX_OCTEON_DEVICES; i++)
+		if (octeon_device[i] == octeon_dev)
+			return octeon_dev->octeon_id;
+	return -1;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
new file mode 100644
index 000000000000..36e1f85df8c4
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -0,0 +1,649 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+
+/*! \file octeon_device.h
+ *  \brief Host Driver: This file defines the octeon device structure.
+ */
+
+#ifndef _OCTEON_DEVICE_H_
+#define  _OCTEON_DEVICE_H_
+
+/** PCI VendorId Device Id */
+#define  OCTEON_CN68XX_PCIID          0x91177d
+#define  OCTEON_CN66XX_PCIID          0x92177d
+
+/** Driver identifies chips by these Ids, created by clubbing together
+ *  DeviceId+RevisionId; Where Revision Id is not used to distinguish
+ *  between chips, a value of 0 is used for revision id.
+ */
+#define  OCTEON_CN68XX                0x0091
+#define  OCTEON_CN66XX                0x0092
+
+/** Endian-swap modes supported by Octeon. */
+enum octeon_pci_swap_mode {
+	OCTEON_PCI_PASSTHROUGH = 0,
+	OCTEON_PCI_64BIT_SWAP = 1,
+	OCTEON_PCI_32BIT_BYTE_SWAP = 2,
+	OCTEON_PCI_32BIT_LW_SWAP = 3
+};
+
+/*---------------   PCI BAR1 index registers -------------*/
+
+/* BAR1 Mask */
+#define    PCI_BAR1_ENABLE_CA            1
+#define    PCI_BAR1_ENDIAN_MODE          OCTEON_PCI_64BIT_SWAP
+#define    PCI_BAR1_ENTRY_VALID          1
+#define    PCI_BAR1_MASK                 ((PCI_BAR1_ENABLE_CA << 3)   \
+					    | (PCI_BAR1_ENDIAN_MODE << 1) \
+					    | PCI_BAR1_ENTRY_VALID)
+
+/** Octeon Device state.
+ *  Each octeon device goes through each of these states
+ *  as it is initialized.
+ */
+#define    OCT_DEV_BEGIN_STATE            0x0
+#define    OCT_DEV_PCI_MAP_DONE           0x1
+#define    OCT_DEV_DISPATCH_INIT_DONE     0x2
+#define    OCT_DEV_INSTR_QUEUE_INIT_DONE  0x3
+#define    OCT_DEV_SC_BUFF_POOL_INIT_DONE 0x4
+#define    OCT_DEV_RESP_LIST_INIT_DONE    0x5
+#define    OCT_DEV_DROQ_INIT_DONE         0x6
+#define    OCT_DEV_IO_QUEUES_DONE         0x7
+#define    OCT_DEV_CONSOLE_INIT_DONE      0x8
+#define    OCT_DEV_HOST_OK                0x9
+#define    OCT_DEV_CORE_OK                0xa
+#define    OCT_DEV_RUNNING                0xb
+#define    OCT_DEV_IN_RESET               0xc
+#define    OCT_DEV_STATE_INVALID          0xd
+
+#define    OCT_DEV_STATES                 OCT_DEV_STATE_INVALID
+
+/** Octeon Device interrupts
+  *  These interrupt bits are set in int_status filed of
+  *  octeon_device structure
+  */
+#define	   OCT_DEV_INTR_DMA0_FORCE	  0x01
+#define	   OCT_DEV_INTR_DMA1_FORCE	  0x02
+#define	   OCT_DEV_INTR_PKT_DATA	  0x04
+
+#define LIO_RESET_SECS (3)
+
+/*---------------------------DISPATCH LIST-------------------------------*/
+
+/** The dispatch list entry.
+ *  The driver keeps a record of functions registered for each
+ *  response header opcode in this structure. Since the opcode is
+ *  hashed to index into the driver's list, more than one opcode
+ *  can hash to the same entry, in which case the list field points
+ *  to a linked list with the other entries.
+ */
+struct octeon_dispatch {
+	/** List head for this entry */
+	struct list_head list;
+
+	/** The opcode for which the dispatch function & arg should be used */
+	u16 opcode;
+
+	/** The function to be called for a packet received by the driver */
+	octeon_dispatch_fn_t dispatch_fn;
+
+	/* The application specified argument to be passed to the above
+	 * function along with the received packet
+	 */
+	void *arg;
+};
+
+/** The dispatch list structure. */
+struct octeon_dispatch_list {
+	/** access to dispatch list must be atomic */
+	spinlock_t lock;
+
+	/** Count of dispatch functions currently registered */
+	u32 count;
+
+	/** The list of dispatch functions */
+	struct octeon_dispatch *dlist;
+};
+
+/*-----------------------  THE OCTEON DEVICE  ---------------------------*/
+
+#define OCT_MEM_REGIONS     3
+/** PCI address space mapping information.
+ *  Each of the 3 address spaces given by BAR0, BAR2 and BAR4 of
+ *  Octeon gets mapped to different physical address spaces in
+ *  the kernel.
+ */
+struct octeon_mmio {
+	/** PCI address to which the BAR is mapped. */
+	u64 start;
+
+	/** Length of this PCI address space. */
+	u32 len;
+
+	/** Length that has been mapped to phys. address space. */
+	u32 mapped_len;
+
+	/** The physical address to which the PCI address space is mapped. */
+	u8 __iomem *hw_addr;
+
+	/** Flag indicating the mapping was successful. */
+	u32 done;
+};
+
+#define   MAX_OCTEON_MAPS    32
+
+struct octeon_io_enable {
+	u32 iq;
+	u32 oq;
+	u32 iq64B;
+};
+
+struct octeon_reg_list {
+	u32 __iomem *pci_win_wr_addr_hi;
+	u32 __iomem *pci_win_wr_addr_lo;
+	u64 __iomem *pci_win_wr_addr;
+
+	u32 __iomem *pci_win_rd_addr_hi;
+	u32 __iomem *pci_win_rd_addr_lo;
+	u64 __iomem *pci_win_rd_addr;
+
+	u32 __iomem *pci_win_wr_data_hi;
+	u32 __iomem *pci_win_wr_data_lo;
+	u64 __iomem *pci_win_wr_data;
+
+	u32 __iomem *pci_win_rd_data_hi;
+	u32 __iomem *pci_win_rd_data_lo;
+	u64 __iomem *pci_win_rd_data;
+};
+
+#define OCTEON_CONSOLE_MAX_READ_BYTES 512
+struct octeon_console {
+	u32 active;
+	u32 waiting;
+	u64 addr;
+	u32 buffer_size;
+	u64 input_base_addr;
+	u64 output_base_addr;
+	char leftover[OCTEON_CONSOLE_MAX_READ_BYTES];
+};
+
+struct octeon_board_info {
+	char name[OCT_BOARD_NAME];
+	char serial_number[OCT_SERIAL_LEN];
+	u64 major;
+	u64 minor;
+};
+
+struct octeon_fn_list {
+	void (*setup_iq_regs)(struct octeon_device *, u32);
+	void (*setup_oq_regs)(struct octeon_device *, u32);
+
+	irqreturn_t (*process_interrupt_regs)(void *);
+	int (*soft_reset)(struct octeon_device *);
+	int (*setup_device_regs)(struct octeon_device *);
+	void (*reinit_regs)(struct octeon_device *);
+	void (*bar1_idx_setup)(struct octeon_device *, u64, u32, int);
+	void (*bar1_idx_write)(struct octeon_device *, u32, u32);
+	u32 (*bar1_idx_read)(struct octeon_device *, u32);
+	u32 (*update_iq_read_idx)(struct octeon_device *,
+				  struct octeon_instr_queue *);
+
+	void (*enable_oq_pkt_time_intr)(struct octeon_device *, u32);
+	void (*disable_oq_pkt_time_intr)(struct octeon_device *, u32);
+
+	void (*enable_interrupt)(void *);
+	void (*disable_interrupt)(void *);
+
+	void (*enable_io_queues)(struct octeon_device *);
+	void (*disable_io_queues)(struct octeon_device *);
+};
+
+/* Must be multiple of 8, changing breaks ABI */
+#define CVMX_BOOTMEM_NAME_LEN 128
+
+/* Structure for named memory blocks
+ * Number of descriptors
+ * available can be changed without affecting compatiblity,
+ * but name length changes require a bump in the bootmem
+ * descriptor version
+ * Note: This structure must be naturally 64 bit aligned, as a single
+ * memory image will be used by both 32 and 64 bit programs.
+ */
+struct cvmx_bootmem_named_block_desc {
+	/** Base address of named block */
+	u64 base_addr;
+
+	/** Size actually allocated for named block */
+	u64 size;
+
+	/** name of named block */
+	char name[CVMX_BOOTMEM_NAME_LEN];
+};
+
+struct oct_fw_info {
+	u32 max_nic_ports;      /** max nic ports for the device */
+	u32 num_gmx_ports;      /** num gmx ports */
+	u64 app_cap_flags;      /** firmware cap flags */
+
+	/** The core application is running in this mode.
+	 * See octeon-drv-opcodes.h for values.
+	 */
+	u32 app_mode;
+	char   liquidio_firmware_version[32];
+};
+
+/* wrappers around work structs */
+struct cavium_wk {
+	struct delayed_work work;
+	void *ctxptr;
+	size_t ctxul;
+};
+
+struct cavium_wq {
+	struct workqueue_struct *wq;
+	struct cavium_wk wk;
+};
+
+struct octdev_props {
+	/* Each interface in the Octeon device has a network
+	 * device pointer (used for OS specific calls).
+	 */
+	struct net_device *netdev;
+};
+
+/** The Octeon device.
+ *  Each Octeon device has this structure to represent all its
+ *  components.
+ */
+struct octeon_device {
+	/** Lock for PCI window configuration accesses */
+	spinlock_t pci_win_lock;
+
+	/** Lock for memory accesses */
+	spinlock_t mem_access_lock;
+
+	/** PCI device pointer */
+	struct pci_dev *pci_dev;
+
+	/** Chip specific information. */
+	void *chip;
+
+	/** Number of interfaces detected in this octeon device. */
+	u32 ifcount;
+
+	struct octdev_props props[MAX_OCTEON_LINKS];
+
+	/** Octeon Chip type. */
+	u16 chip_id;
+	u16 rev_id;
+
+	/** This device's id - set by the driver. */
+	u32 octeon_id;
+
+	/** This device's PCIe port used for traffic. */
+	u16 pcie_port;
+
+	u16 flags;
+#define LIO_FLAG_MSI_ENABLED                  (u32)(1 << 1)
+#define LIO_FLAG_MSIX_ENABLED                 (u32)(1 << 2)
+
+	/** The state of this device */
+	atomic_t status;
+
+	/** memory mapped io range */
+	struct octeon_mmio mmio[OCT_MEM_REGIONS];
+
+	struct octeon_reg_list reg_list;
+
+	struct octeon_fn_list fn_list;
+
+	struct octeon_board_info boardinfo;
+
+	u32 num_iqs;
+
+	/* The pool containing pre allocated buffers used for soft commands */
+	struct octeon_sc_buffer_pool	sc_buf_pool;
+
+	/** The input instruction queues */
+	struct octeon_instr_queue *instr_queue[MAX_OCTEON_INSTR_QUEUES];
+
+	/** The doubly-linked list of instruction response */
+	struct octeon_response_list response_list[MAX_RESPONSE_LISTS];
+
+	u32 num_oqs;
+
+	/** The DROQ output queues  */
+	struct octeon_droq *droq[MAX_OCTEON_OUTPUT_QUEUES];
+
+	struct octeon_io_enable io_qmask;
+
+	/** List of dispatch functions */
+	struct octeon_dispatch_list dispatch;
+
+	/* Interrupt Moderation */
+	struct oct_intrmod_cfg intrmod;
+
+	u32 int_status;
+
+	u64 droq_intr;
+
+	/** Physical location of the cvmx_bootmem_desc_t in octeon memory */
+	u64 bootmem_desc_addr;
+
+	/** Placeholder memory for named blocks.
+	 * Assumes single-threaded access
+	 */
+	struct cvmx_bootmem_named_block_desc bootmem_named_block_desc;
+
+	/** Address of consoles descriptor */
+	u64 console_desc_addr;
+
+	/** Number of consoles available. 0 means they are inaccessible */
+	u32 num_consoles;
+
+	/* Console caches */
+	struct octeon_console console[MAX_OCTEON_MAPS];
+
+	/* Coprocessor clock rate. */
+	u64 coproc_clock_rate;
+
+	/** The core application is running in this mode. See liquidio_common.h
+	 * for values.
+	 */
+	u32 app_mode;
+
+	struct oct_fw_info fw_info;
+
+	/** The name given to this device. */
+	char device_name[32];
+
+	/** Application Context */
+	void *app_ctx;
+
+	struct cavium_wq dma_comp_wq;
+
+	struct cavium_wq check_db_wq[MAX_OCTEON_INSTR_QUEUES];
+
+	struct cavium_wk nic_poll_work;
+
+	struct cavium_wk console_poll_work[MAX_OCTEON_MAPS];
+
+	void *priv;
+};
+
+#define  OCTEON_CN6XXX(oct)           ((oct->chip_id == OCTEON_CN66XX) || \
+				       (oct->chip_id == OCTEON_CN68XX))
+#define CHIP_FIELD(oct, TYPE, field)             \
+	(((struct octeon_ ## TYPE  *)(oct->chip))->field)
+
+struct oct_intrmod_cmd {
+	struct octeon_device *oct_dev;
+	struct octeon_soft_command *sc;
+	struct oct_intrmod_cfg *cfg;
+};
+
+/*------------------ Function Prototypes ----------------------*/
+
+/** Initialize device list memory */
+void octeon_init_device_list(int conf_type);
+
+/** Free memory for Input and Output queue structures for a octeon device */
+void octeon_free_device_mem(struct octeon_device *);
+
+/* Look up a free entry in the octeon_device table and allocate resources
+ * for the octeon_device structure for an octeon device. Called at init
+ * time.
+ */
+struct octeon_device *octeon_allocate_device(u32 pci_id,
+					     u32 priv_size);
+
+/**  Initialize the driver's dispatch list which is a mix of a hash table
+ *  and a linked list. This is done at driver load time.
+ *  @param octeon_dev - pointer to the octeon device structure.
+ *  @return 0 on success, else -ve error value
+ */
+int octeon_init_dispatch_list(struct octeon_device *octeon_dev);
+
+/**  Delete the driver's dispatch list and all registered entries.
+ * This is done at driver unload time.
+ *  @param octeon_dev - pointer to the octeon device structure.
+ */
+void octeon_delete_dispatch_list(struct octeon_device *octeon_dev);
+
+/** Initialize the core device fields with the info returned by the FW.
+ * @param recv_info - Receive info structure
+ * @param buf       - Receive buffer
+ */
+int octeon_core_drv_init(struct octeon_recv_info *recv_info, void *buf);
+
+/** Gets the dispatch function registered to receive packets with a
+ *  given opcode/subcode.
+ *  @param  octeon_dev  - the octeon device pointer.
+ *  @param  opcode      - the opcode for which the dispatch function
+ *                        is to checked.
+ *  @param  subcode     - the subcode for which the dispatch function
+ *                        is to checked.
+ *
+ *  @return Success: octeon_dispatch_fn_t (dispatch function pointer)
+ *  @return Failure: NULL
+ *
+ *  Looks up the dispatch list to get the dispatch function for a
+ *  given opcode.
+ */
+octeon_dispatch_fn_t
+octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
+		    u16 subcode);
+
+/** Get the octeon device pointer.
+ *  @param octeon_id  - The id for which the octeon device pointer is required.
+ *  @return Success: Octeon device pointer.
+ *  @return Failure: NULL.
+ */
+struct octeon_device *lio_get_device(u32 octeon_id);
+
+/** Get the octeon id assigned to the octeon device passed as argument.
+ *  This function is exported to other modules.
+ *  @param dev - octeon device pointer passed as a void *.
+ *  @return octeon device id
+ */
+int lio_get_device_id(void *dev);
+
+static inline u16 OCTEON_MAJOR_REV(struct octeon_device *oct)
+{
+	u16 rev = (oct->rev_id & 0xC) >> 2;
+
+	return (rev == 0) ? 1 : rev;
+}
+
+static inline u16 OCTEON_MINOR_REV(struct octeon_device *oct)
+{
+	return oct->rev_id & 0x3;
+}
+
+/** Read windowed register.
+ *  @param  oct   -  pointer to the Octeon device.
+ *  @param  addr  -  Address of the register to read.
+ *
+ *  This routine is called to read from the indirectly accessed
+ *  Octeon registers that are visible through a PCI BAR0 mapped window
+ *  register.
+ *  @return  - 64 bit value read from the register.
+ */
+
+u64 lio_pci_readq(struct octeon_device *oct, u64 addr);
+
+/** Write windowed register.
+ *  @param  oct  -  pointer to the Octeon device.
+ *  @param  val  -  Value to write
+ *  @param  addr -  Address of the register to write
+ *
+ *  This routine is called to write to the indirectly accessed
+ *  Octeon registers that are visible through a PCI BAR0 mapped window
+ *  register.
+ *  @return   Nothing.
+ */
+void lio_pci_writeq(struct octeon_device *oct, u64 val, u64 addr);
+
+/* Routines for reading and writing CSRs */
+#define   octeon_write_csr(oct_dev, reg_off, value) \
+		writel(value, oct_dev->mmio[0].hw_addr + reg_off)
+
+#define   octeon_write_csr64(oct_dev, reg_off, val64) \
+		writeq(val64, oct_dev->mmio[0].hw_addr + reg_off)
+
+#define   octeon_read_csr(oct_dev, reg_off)         \
+		readl(oct_dev->mmio[0].hw_addr + reg_off)
+
+#define   octeon_read_csr64(oct_dev, reg_off)         \
+		readq(oct_dev->mmio[0].hw_addr + reg_off)
+
+/**
+ * Checks if memory access is okay
+ *
+ * @param oct which octeon to send to
+ * @return Zero on success, negative on failure.
+ */
+int octeon_mem_access_ok(struct octeon_device *oct);
+
+/**
+ * Waits for DDR initialization.
+ *
+ * @param oct which octeon to send to
+ * @param timeout_in_ms pointer to how long to wait until DDR is initialized
+ * in ms.
+ *                      If contents are 0, it waits until contents are non-zero
+ *                      before starting to check.
+ * @return Zero on success, negative on failure.
+ */
+int octeon_wait_for_ddr_init(struct octeon_device *oct,
+			     u32 *timeout_in_ms);
+
+/**
+ * Wait for u-boot to boot and be waiting for a command.
+ *
+ * @param wait_time_hundredths
+ *               Maximum time to wait
+ *
+ * @return Zero on success, negative on failure.
+ */
+int octeon_wait_for_bootloader(struct octeon_device *oct,
+			       u32 wait_time_hundredths);
+
+/**
+ * Initialize console access
+ *
+ * @param oct which octeon initialize
+ * @return Zero on success, negative on failure.
+ */
+int octeon_init_consoles(struct octeon_device *oct);
+
+/**
+ * Adds access to a console to the device.
+ *
+ * @param oct which octeon to add to
+ * @param console_num which console
+ * @return Zero on success, negative on failure.
+ */
+int octeon_add_console(struct octeon_device *oct, u32 console_num);
+
+/** write or read from a console */
+int octeon_console_write(struct octeon_device *oct, u32 console_num,
+			 char *buffer, u32 write_request_size, u32 flags);
+int octeon_console_write_avail(struct octeon_device *oct, u32 console_num);
+int octeon_console_read(struct octeon_device *oct, u32 console_num,
+			char *buffer, u32 buf_size, u32 flags);
+int octeon_console_read_avail(struct octeon_device *oct, u32 console_num);
+
+/** Removes all attached consoles. */
+void octeon_remove_consoles(struct octeon_device *oct);
+
+/**
+ * Send a string to u-boot on console 0 as a command.
+ *
+ * @param oct which octeon to send to
+ * @param cmd_str String to send
+ * @param wait_hundredths Time to wait for u-boot to accept the command.
+ *
+ * @return Zero on success, negative on failure.
+ */
+int octeon_console_send_cmd(struct octeon_device *oct, char *cmd_str,
+			    u32 wait_hundredths);
+
+/** Parses, validates, and downloads firmware, then boots associated cores.
+ *  @param oct which octeon to download firmware to
+ *  @param data  - The complete firmware file image
+ *  @param size  - The size of the data
+ *
+ *  @return 0 if success.
+ *         -EINVAL if file is incompatible or badly formatted.
+ *         -ENODEV if no handler was found for the application type or an
+ *         invalid octeon id was passed.
+ */
+int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
+			     size_t size);
+
+char *lio_get_state_string(atomic_t *state_ptr);
+
+/** Sets up instruction queues for the device
+ *  @param oct which octeon to setup
+ *
+ *  @return 0 if success. 1 if fails
+ */
+int octeon_setup_instr_queues(struct octeon_device *oct);
+
+/** Sets up output queues for the device
+ *  @param oct which octeon to setup
+ *
+ *  @return 0 if success. 1 if fails
+ */
+int octeon_setup_output_queues(struct octeon_device *oct);
+
+int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no);
+
+int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no);
+
+/** Turns off the input and output queues for the device
+ *  @param oct which octeon to disable
+ */
+void octeon_set_io_queues_off(struct octeon_device *oct);
+
+/** Turns on or off the given output queue for the device
+ *  @param oct which octeon to change
+ *  @param q_no which queue
+ *  @param enable 1 to enable, 0 to disable
+ */
+void octeon_set_droq_pkt_op(struct octeon_device *oct, u32 q_no, u32 enable);
+
+/** Retrieve the config for the device
+ *  @param oct which octeon
+ *  @param card_type type of card
+ *
+ *  @returns pointer to configuration
+ */
+void *oct_get_config_info(struct octeon_device *oct, u16 card_type);
+
+/** Gets the octeon device configuration
+ *  @return - pointer to the octeon configuration struture
+ */
+struct octeon_config *octeon_get_conf(struct octeon_device *oct);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
new file mode 100644
index 000000000000..94b502a0cf33
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -0,0 +1,989 @@
+/**********************************************************************
+* Author: Cavium, Inc.
+*
+* Contact: support@cavium.com
+*          Please include "LiquidIO" in the subject.
+*
+* Copyright (c) 2003-2015 Cavium, Inc.
+*
+* This file is free software; you can redistribute it and/or modify
+* it under the terms of the GNU General Public License, Version 2, as
+* published by the Free Software Foundation.
+*
+* This file is distributed in the hope that it will be useful, but
+* AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+* NONINFRINGEMENT.  See the GNU General Public License for more
+* details.
+*
+* This file may also be available under a different license from Cavium.
+* Contact Cavium, Inc. for more information
+**********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+/* #define CAVIUM_ONLY_PERF_MODE */
+
+#define     CVM_MIN(d1, d2)           (((d1) < (d2)) ? (d1) : (d2))
+#define     CVM_MAX(d1, d2)           (((d1) > (d2)) ? (d1) : (d2))
+
+struct niclist {
+	struct list_head list;
+	void *ptr;
+};
+
+struct __dispatch {
+	struct list_head list;
+	struct octeon_recv_info *rinfo;
+	octeon_dispatch_fn_t disp_fn;
+};
+
+/** Get the argument that the user set when registering dispatch
+ *  function for a given opcode/subcode.
+ *  @param  octeon_dev - the octeon device pointer.
+ *  @param  opcode     - the opcode for which the dispatch argument
+ *                       is to be checked.
+ *  @param  subcode    - the subcode for which the dispatch argument
+ *                       is to be checked.
+ *  @return  Success: void * (argument to the dispatch function)
+ *  @return  Failure: NULL
+ *
+ */
+static inline void *octeon_get_dispatch_arg(struct octeon_device *octeon_dev,
+					    u16 opcode, u16 subcode)
+{
+	int idx;
+	struct list_head *dispatch;
+	void *fn_arg = NULL;
+	u16 combined_opcode = OPCODE_SUBCODE(opcode, subcode);
+
+	idx = combined_opcode & OCTEON_OPCODE_MASK;
+
+	spin_lock_bh(&octeon_dev->dispatch.lock);
+
+	if (octeon_dev->dispatch.count == 0) {
+		spin_unlock_bh(&octeon_dev->dispatch.lock);
+		return NULL;
+	}
+
+	if (octeon_dev->dispatch.dlist[idx].opcode == combined_opcode) {
+		fn_arg = octeon_dev->dispatch.dlist[idx].arg;
+	} else {
+		list_for_each(dispatch,
+			      &octeon_dev->dispatch.dlist[idx].list) {
+			if (((struct octeon_dispatch *)dispatch)->opcode ==
+			    combined_opcode) {
+				fn_arg = ((struct octeon_dispatch *)
+					  dispatch)->arg;
+				break;
+			}
+		}
+	}
+
+	spin_unlock_bh(&octeon_dev->dispatch.lock);
+	return fn_arg;
+}
+
+u32 octeon_droq_check_hw_for_pkts(struct octeon_device *oct,
+				  struct octeon_droq *droq)
+{
+	u32 pkt_count = 0;
+
+	pkt_count = readl(droq->pkts_sent_reg);
+	if (pkt_count) {
+		atomic_add(pkt_count, &droq->pkts_pending);
+		writel(pkt_count, droq->pkts_sent_reg);
+	}
+
+	return pkt_count;
+}
+
+static void octeon_droq_compute_max_packet_bufs(struct octeon_droq *droq)
+{
+	u32 count = 0;
+
+	/* max_empty_descs is the max. no. of descs that can have no buffers.
+	 * If the empty desc count goes beyond this value, we cannot safely
+	 * read in a 64K packet sent by Octeon
+	 * (64K is max pkt size from Octeon)
+	 */
+	droq->max_empty_descs = 0;
+
+	do {
+		droq->max_empty_descs++;
+		count += droq->buffer_size;
+	} while (count < (64 * 1024));
+
+	droq->max_empty_descs = droq->max_count - droq->max_empty_descs;
+}
+
+static void octeon_droq_reset_indices(struct octeon_droq *droq)
+{
+	droq->read_idx = 0;
+	droq->write_idx = 0;
+	droq->refill_idx = 0;
+	droq->refill_count = 0;
+	atomic_set(&droq->pkts_pending, 0);
+}
+
+static void
+octeon_droq_destroy_ring_buffers(struct octeon_device *oct,
+				 struct octeon_droq *droq)
+{
+	u32 i;
+
+	for (i = 0; i < droq->max_count; i++) {
+		if (droq->recv_buf_list[i].buffer) {
+			if (droq->desc_ring) {
+				lio_unmap_ring_info(oct->pci_dev,
+						    (u64)droq->
+						    desc_ring[i].info_ptr,
+						    OCT_DROQ_INFO_SIZE);
+				lio_unmap_ring(oct->pci_dev,
+					       (u64)droq->desc_ring[i].
+					       buffer_ptr,
+					       droq->buffer_size);
+			}
+			recv_buffer_free(droq->recv_buf_list[i].buffer);
+			droq->recv_buf_list[i].buffer = NULL;
+		}
+	}
+
+	octeon_droq_reset_indices(droq);
+}
+
+static int
+octeon_droq_setup_ring_buffers(struct octeon_device *oct,
+			       struct octeon_droq *droq)
+{
+	u32 i;
+	void *buf;
+	struct octeon_droq_desc *desc_ring = droq->desc_ring;
+
+	for (i = 0; i < droq->max_count; i++) {
+		buf = recv_buffer_alloc(oct, droq->q_no, droq->buffer_size);
+
+		if (!buf) {
+			dev_err(&oct->pci_dev->dev, "%s buffer alloc failed\n",
+				__func__);
+			return -ENOMEM;
+		}
+
+		droq->recv_buf_list[i].buffer = buf;
+		droq->recv_buf_list[i].data = get_rbd(buf);
+
+		droq->info_list[i].length = 0;
+
+		/* map ring buffers into memory */
+		desc_ring[i].info_ptr = lio_map_ring_info(droq, i);
+		desc_ring[i].buffer_ptr =
+			lio_map_ring(oct->pci_dev,
+				     droq->recv_buf_list[i].buffer,
+				     droq->buffer_size);
+	}
+
+	octeon_droq_reset_indices(droq);
+
+	octeon_droq_compute_max_packet_bufs(droq);
+
+	return 0;
+}
+
+int octeon_delete_droq(struct octeon_device *oct, u32 q_no)
+{
+	struct octeon_droq *droq = oct->droq[q_no];
+
+	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
+
+	octeon_droq_destroy_ring_buffers(oct, droq);
+
+	if (droq->recv_buf_list)
+		vfree(droq->recv_buf_list);
+
+	if (droq->info_base_addr)
+		cnnic_free_aligned_dma(oct->pci_dev, droq->info_list,
+				       droq->info_alloc_size,
+				       droq->info_base_addr,
+				       droq->info_list_dma);
+
+	if (droq->desc_ring)
+		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
+			     droq->desc_ring, droq->desc_ring_dma);
+
+	memset(droq, 0, OCT_DROQ_SIZE);
+
+	return 0;
+}
+
+int octeon_init_droq(struct octeon_device *oct,
+		     u32 q_no,
+		     u32 num_descs,
+		     u32 desc_size,
+		     void *app_ctx)
+{
+	struct octeon_droq *droq;
+	u32 desc_ring_size = 0, c_num_descs = 0, c_buf_size = 0;
+	u32 c_pkts_per_intr = 0, c_refill_threshold = 0;
+
+	dev_dbg(&oct->pci_dev->dev, "%s[%d]\n", __func__, q_no);
+
+	droq = oct->droq[q_no];
+	memset(droq, 0, OCT_DROQ_SIZE);
+
+	droq->oct_dev = oct;
+	droq->q_no = q_no;
+	if (app_ctx)
+		droq->app_ctx = app_ctx;
+	else
+		droq->app_ctx = (void *)(size_t)q_no;
+
+	c_num_descs = num_descs;
+	c_buf_size = desc_size;
+	if (OCTEON_CN6XXX(oct)) {
+		struct octeon_config *conf6x = CHIP_FIELD(oct, cn6xxx, conf);
+
+		c_pkts_per_intr = (u32)CFG_GET_OQ_PKTS_PER_INTR(conf6x);
+		c_refill_threshold = (u32)CFG_GET_OQ_REFILL_THRESHOLD(conf6x);
+	}
+
+	droq->max_count = c_num_descs;
+	droq->buffer_size = c_buf_size;
+
+	desc_ring_size = droq->max_count * OCT_DROQ_DESC_SIZE;
+	droq->desc_ring = lio_dma_alloc(oct, desc_ring_size,
+					(dma_addr_t *)&droq->desc_ring_dma);
+
+	if (!droq->desc_ring) {
+		dev_err(&oct->pci_dev->dev,
+			"Output queue %d ring alloc failed\n", q_no);
+		return 1;
+	}
+
+	dev_dbg(&oct->pci_dev->dev, "droq[%d]: desc_ring: virt: 0x%p, dma: %lx\n",
+		q_no, droq->desc_ring, droq->desc_ring_dma);
+	dev_dbg(&oct->pci_dev->dev, "droq[%d]: num_desc: %d\n", q_no,
+		droq->max_count);
+
+	droq->info_list =
+		cnnic_alloc_aligned_dma(oct->pci_dev,
+					(droq->max_count * OCT_DROQ_INFO_SIZE),
+					&droq->info_alloc_size,
+					&droq->info_base_addr,
+					&droq->info_list_dma);
+
+	if (!droq->info_list) {
+		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for info list.\n");
+		lio_dma_free(oct, (droq->max_count * OCT_DROQ_DESC_SIZE),
+			     droq->desc_ring, droq->desc_ring_dma);
+		return 1;
+	}
+
+	droq->recv_buf_list = (struct octeon_recv_buffer *)
+			      vmalloc(droq->max_count *
+						OCT_DROQ_RECVBUF_SIZE);
+	if (!droq->recv_buf_list) {
+		dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n");
+		goto init_droq_fail;
+	}
+
+	if (octeon_droq_setup_ring_buffers(oct, droq))
+		goto init_droq_fail;
+
+	droq->pkts_per_intr = c_pkts_per_intr;
+	droq->refill_threshold = c_refill_threshold;
+
+	dev_dbg(&oct->pci_dev->dev, "DROQ INIT: max_empty_descs: %d\n",
+		droq->max_empty_descs);
+
+	spin_lock_init(&droq->lock);
+
+	INIT_LIST_HEAD(&droq->dispatch_list);
+
+	/* For 56xx Pass1, this function won't be called, so no checks. */
+	oct->fn_list.setup_oq_regs(oct, q_no);
+
+	oct->io_qmask.oq |= (1 << q_no);
+
+	return 0;
+
+init_droq_fail:
+	octeon_delete_droq(oct, q_no);
+	return 1;
+}
+
+/* octeon_create_recv_info
+ * Parameters:
+ *  octeon_dev - pointer to the octeon device structure
+ *  droq       - droq in which the packet arrived.
+ *  buf_cnt    - no. of buffers used by the packet.
+ *  idx        - index in the descriptor for the first buffer in the packet.
+ * Description:
+ *  Allocates a recv_info_t and copies the buffer addresses for packet data
+ *  into the recv_pkt space which starts at an 8B offset from recv_info_t.
+ *  Flags the descriptors for refill later. If available descriptors go
+ *  below the threshold to receive a 64K pkt, new buffers are first allocated
+ *  before the recv_pkt_t is created.
+ *  This routine will be called in interrupt context.
+ * Returns:
+ *  Success: Pointer to recv_info_t
+ *  Failure: NULL.
+ * Locks:
+ *  The droq->lock is held when this routine is called.
+ */
+static inline struct octeon_recv_info *octeon_create_recv_info(
+		struct octeon_device *octeon_dev,
+		struct octeon_droq *droq,
+		u32 buf_cnt,
+		u32 idx)
+{
+	struct octeon_droq_info *info;
+	struct octeon_recv_pkt *recv_pkt;
+	struct octeon_recv_info *recv_info;
+	u32 i, bytes_left;
+
+	info = &droq->info_list[idx];
+
+	recv_info = octeon_alloc_recv_info(sizeof(struct __dispatch));
+	if (!recv_info)
+		return NULL;
+
+	recv_pkt = recv_info->recv_pkt;
+	recv_pkt->rh = info->rh;
+	recv_pkt->length = (u32)info->length;
+	recv_pkt->buffer_count = (u16)buf_cnt;
+	recv_pkt->octeon_id = (u16)octeon_dev->octeon_id;
+
+	i = 0;
+	bytes_left = (u32)info->length;
+
+	while (buf_cnt) {
+		lio_unmap_ring(octeon_dev->pci_dev,
+			       (u64)droq->desc_ring[idx].buffer_ptr,
+			       droq->buffer_size);
+
+		recv_pkt->buffer_size[i] =
+			(bytes_left >=
+			 droq->buffer_size) ? droq->buffer_size : bytes_left;
+
+		recv_pkt->buffer_ptr[i] = droq->recv_buf_list[idx].buffer;
+		droq->recv_buf_list[idx].buffer = NULL;
+
+		INCR_INDEX_BY1(idx, droq->max_count);
+		bytes_left -= droq->buffer_size;
+		i++;
+		buf_cnt--;
+	}
+
+	return recv_info;
+}
+
+/* If we were not able to refill all buffers, try to move around
+ * the buffers that were not dispatched.
+ */
+static inline u32
+octeon_droq_refill_pullup_descs(struct octeon_droq *droq,
+				struct octeon_droq_desc *desc_ring)
+{
+	u32 desc_refilled = 0;
+
+	u32 refill_index = droq->refill_idx;
+
+	while (refill_index != droq->read_idx) {
+		if (droq->recv_buf_list[refill_index].buffer) {
+			droq->recv_buf_list[droq->refill_idx].buffer =
+				droq->recv_buf_list[refill_index].buffer;
+			droq->recv_buf_list[droq->refill_idx].data =
+				droq->recv_buf_list[refill_index].data;
+			desc_ring[droq->refill_idx].buffer_ptr =
+				desc_ring[refill_index].buffer_ptr;
+			droq->recv_buf_list[refill_index].buffer = NULL;
+			desc_ring[refill_index].buffer_ptr = 0;
+			do {
+				INCR_INDEX_BY1(droq->refill_idx,
+					       droq->max_count);
+				desc_refilled++;
+				droq->refill_count--;
+			} while (droq->recv_buf_list[droq->refill_idx].
+				 buffer);
+		}
+		INCR_INDEX_BY1(refill_index, droq->max_count);
+	}                       /* while */
+	return desc_refilled;
+}
+
+/* octeon_droq_refill
+ * Parameters:
+ *  droq       - droq in which descriptors require new buffers.
+ * Description:
+ *  Called during normal DROQ processing in interrupt mode or by the poll
+ *  thread to refill the descriptors from which buffers were dispatched
+ *  to upper layers. Attempts to allocate new buffers. If that fails, moves
+ *  up buffers (that were not dispatched) to form a contiguous ring.
+ * Returns:
+ *  No of descriptors refilled.
+ * Locks:
+ *  This routine is called with droq->lock held.
+ */
+static u32
+octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq)
+{
+	struct octeon_droq_desc *desc_ring;
+	void *buf = NULL;
+	u8 *data;
+	u32 desc_refilled = 0;
+
+	desc_ring = droq->desc_ring;
+
+	while (droq->refill_count && (desc_refilled < droq->max_count)) {
+		/* If a valid buffer exists (happens if there is no dispatch),
+		 * reuse
+		 * the buffer, else allocate.
+		 */
+		if (!droq->recv_buf_list[droq->refill_idx].buffer) {
+			buf = recv_buffer_alloc(octeon_dev, droq->q_no,
+						droq->buffer_size);
+			/* If a buffer could not be allocated, no point in
+			 * continuing
+			 */
+			if (!buf)
+				break;
+			droq->recv_buf_list[droq->refill_idx].buffer =
+				buf;
+			data = get_rbd(buf);
+		} else {
+			data = get_rbd(droq->recv_buf_list
+				       [droq->refill_idx].buffer);
+		}
+
+		droq->recv_buf_list[droq->refill_idx].data = data;
+
+		desc_ring[droq->refill_idx].buffer_ptr =
+			lio_map_ring(octeon_dev->pci_dev,
+				     droq->recv_buf_list[droq->
+				     refill_idx].buffer,
+				     droq->buffer_size);
+
+		/* Reset any previous values in the length field. */
+		droq->info_list[droq->refill_idx].length = 0;
+
+		INCR_INDEX_BY1(droq->refill_idx, droq->max_count);
+		desc_refilled++;
+		droq->refill_count--;
+	}
+
+	if (droq->refill_count)
+		desc_refilled +=
+			octeon_droq_refill_pullup_descs(droq, desc_ring);
+
+	/* if droq->refill_count
+	 * The refill count would not change in pass two. We only moved buffers
+	 * to close the gap in the ring, but we would still have the same no. of
+	 * buffers to refill.
+	 */
+	return desc_refilled;
+}
+
+static inline u32
+octeon_droq_get_bufcount(u32 buf_size, u32 total_len)
+{
+	u32 buf_cnt = 0;
+
+	while (total_len > (buf_size * buf_cnt))
+		buf_cnt++;
+	return buf_cnt;
+}
+
+static int
+octeon_droq_dispatch_pkt(struct octeon_device *oct,
+			 struct octeon_droq *droq,
+			 union octeon_rh *rh,
+			 struct octeon_droq_info *info)
+{
+	u32 cnt;
+	octeon_dispatch_fn_t disp_fn;
+	struct octeon_recv_info *rinfo;
+
+	cnt = octeon_droq_get_bufcount(droq->buffer_size, (u32)info->length);
+
+	disp_fn = octeon_get_dispatch(oct, (u16)rh->r.opcode,
+				      (u16)rh->r.subcode);
+	if (disp_fn) {
+		rinfo = octeon_create_recv_info(oct, droq, cnt, droq->read_idx);
+		if (rinfo) {
+			struct __dispatch *rdisp = rinfo->rsvd;
+
+			rdisp->rinfo = rinfo;
+			rdisp->disp_fn = disp_fn;
+			rinfo->recv_pkt->rh = *rh;
+			list_add_tail(&rdisp->list,
+				      &droq->dispatch_list);
+		} else {
+			droq->stats.dropped_nomem++;
+		}
+	} else {
+		dev_err(&oct->pci_dev->dev, "DROQ: No dispatch function\n");
+		droq->stats.dropped_nodispatch++;
+	}                       /* else (dispatch_fn ... */
+
+	return cnt;
+}
+
+static inline void octeon_droq_drop_packets(struct octeon_device *oct,
+					    struct octeon_droq *droq,
+					    u32 cnt)
+{
+	u32 i = 0, buf_cnt;
+	struct octeon_droq_info *info;
+
+	for (i = 0; i < cnt; i++) {
+		info = &droq->info_list[droq->read_idx];
+		octeon_swap_8B_data((u64 *)info, 2);
+
+		if (info->length) {
+			info->length -= OCT_RH_SIZE;
+			droq->stats.bytes_received += info->length;
+			buf_cnt = octeon_droq_get_bufcount(droq->buffer_size,
+							   (u32)info->length);
+		} else {
+			dev_err(&oct->pci_dev->dev, "DROQ: In drop: pkt with len 0\n");
+			buf_cnt = 1;
+		}
+
+		INCR_INDEX(droq->read_idx, buf_cnt, droq->max_count);
+		droq->refill_count += buf_cnt;
+	}
+}
+
+static u32
+octeon_droq_fast_process_packets(struct octeon_device *oct,
+				 struct octeon_droq *droq,
+				 u32 pkts_to_process)
+{
+	struct octeon_droq_info *info;
+	union octeon_rh *rh;
+	u32 pkt, total_len = 0, pkt_count;
+
+	pkt_count = pkts_to_process;
+
+	for (pkt = 0; pkt < pkt_count; pkt++) {
+		u32 pkt_len = 0;
+		struct sk_buff *nicbuf = NULL;
+
+		info = &droq->info_list[droq->read_idx];
+		octeon_swap_8B_data((u64 *)info, 2);
+
+		if (!info->length) {
+			dev_err(&oct->pci_dev->dev,
+				"DROQ[%d] idx: %d len:0, pkt_cnt: %d\n",
+				droq->q_no, droq->read_idx, pkt_count);
+			print_hex_dump_bytes("", DUMP_PREFIX_ADDRESS,
+					     (u8 *)info,
+					     OCT_DROQ_INFO_SIZE);
+			break;
+		}
+
+		/* Len of resp hdr in included in the received data len. */
+		info->length -= OCT_RH_SIZE;
+		rh = &info->rh;
+
+		total_len += (u32)info->length;
+
+		if (OPCODE_SLOW_PATH(rh)) {
+			u32 buf_cnt;
+
+			buf_cnt = octeon_droq_dispatch_pkt(oct, droq, rh, info);
+			INCR_INDEX(droq->read_idx, buf_cnt, droq->max_count);
+			droq->refill_count += buf_cnt;
+		} else {
+			if (info->length <= droq->buffer_size) {
+				lio_unmap_ring(oct->pci_dev,
+					       (u64)droq->desc_ring[
+					       droq->read_idx].buffer_ptr,
+					       droq->buffer_size);
+				pkt_len = (u32)info->length;
+				nicbuf = droq->recv_buf_list[
+					droq->read_idx].buffer;
+				droq->recv_buf_list[droq->read_idx].buffer =
+					NULL;
+				INCR_INDEX_BY1(droq->read_idx, droq->max_count);
+				skb_put(nicbuf, pkt_len);
+				droq->refill_count++;
+			} else {
+				nicbuf = octeon_fast_packet_alloc(oct, droq,
+								  droq->q_no,
+								  (u32)
+								  info->length);
+				pkt_len = 0;
+				/* nicbuf allocation can fail. We'll handle it
+				 * inside the loop.
+				 */
+				while (pkt_len < info->length) {
+					int cpy_len;
+
+					cpy_len = ((pkt_len +
+						droq->buffer_size) >
+						info->length) ?
+						((u32)info->length - pkt_len) :
+						droq->buffer_size;
+
+					if (nicbuf) {
+						lio_unmap_ring(oct->pci_dev,
+							       (u64)
+							       droq->desc_ring
+							       [droq->read_idx].
+							       buffer_ptr,
+							       droq->
+							       buffer_size);
+						octeon_fast_packet_next(droq,
+									nicbuf,
+									cpy_len,
+									droq->
+									read_idx
+									);
+					}
+
+					pkt_len += cpy_len;
+					INCR_INDEX_BY1(droq->read_idx,
+						       droq->max_count);
+					droq->refill_count++;
+				}
+			}
+
+			if (nicbuf) {
+				if (droq->ops.fptr)
+					droq->ops.fptr(oct->octeon_id,
+					nicbuf, pkt_len,
+					rh, &droq->napi);
+				else
+					recv_buffer_free(nicbuf);
+			}
+		}
+
+		if (droq->refill_count >= droq->refill_threshold) {
+			int desc_refilled = octeon_droq_refill(oct, droq);
+
+			/* Flush the droq descriptor data to memory to be sure
+			* that when we update the credits the data in memory
+			* is accurate.
+			*/
+			wmb();
+			writel((desc_refilled), droq->pkts_credit_reg);
+			/* make sure mmio write completes */
+			mmiowb();
+		}
+
+	}                       /* for ( each packet )... */
+
+	/* Increment refill_count by the number of buffers processed. */
+	droq->stats.pkts_received += pkt;
+	droq->stats.bytes_received += total_len;
+
+	if ((droq->ops.drop_on_max) && (pkts_to_process - pkt)) {
+		octeon_droq_drop_packets(oct, droq, (pkts_to_process - pkt));
+
+		droq->stats.dropped_toomany += (pkts_to_process - pkt);
+		return pkts_to_process;
+	}
+
+	return pkt;
+}
+
+int
+octeon_droq_process_packets(struct octeon_device *oct,
+			    struct octeon_droq *droq,
+			    u32 budget)
+{
+	u32 pkt_count = 0, pkts_processed = 0;
+	struct list_head *tmp, *tmp2;
+
+	pkt_count = atomic_read(&droq->pkts_pending);
+	if (!pkt_count)
+		return 0;
+
+	if (pkt_count > budget)
+		pkt_count = budget;
+
+	/* Grab the lock */
+	spin_lock(&droq->lock);
+
+	pkts_processed = octeon_droq_fast_process_packets(oct, droq, pkt_count);
+
+	atomic_sub(pkts_processed, &droq->pkts_pending);
+
+	/* Release the spin lock */
+	spin_unlock(&droq->lock);
+
+	list_for_each_safe(tmp, tmp2, &droq->dispatch_list) {
+		struct __dispatch *rdisp = (struct __dispatch *)tmp;
+
+		list_del(tmp);
+		rdisp->disp_fn(rdisp->rinfo,
+			       octeon_get_dispatch_arg
+			       (oct,
+				(u16)rdisp->rinfo->recv_pkt->rh.r.opcode,
+				(u16)rdisp->rinfo->recv_pkt->rh.r.subcode));
+	}
+
+	/* If there are packets pending. schedule tasklet again */
+	if (atomic_read(&droq->pkts_pending))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * Utility function to poll for packets. check_hw_for_packets must be
+ * called before calling this routine.
+ */
+
+static int
+octeon_droq_process_poll_pkts(struct octeon_device *oct,
+			      struct octeon_droq *droq, u32 budget)
+{
+	struct list_head *tmp, *tmp2;
+	u32 pkts_available = 0, pkts_processed = 0;
+	u32 total_pkts_processed = 0;
+
+	if (budget > droq->max_count)
+		budget = droq->max_count;
+
+	spin_lock(&droq->lock);
+
+	while (total_pkts_processed < budget) {
+		pkts_available =
+			CVM_MIN((budget - total_pkts_processed),
+				(u32)(atomic_read(&droq->pkts_pending)));
+
+		if (pkts_available == 0)
+			break;
+
+		pkts_processed =
+			octeon_droq_fast_process_packets(oct, droq,
+							 pkts_available);
+
+		atomic_sub(pkts_processed, &droq->pkts_pending);
+
+		total_pkts_processed += pkts_processed;
+
+		octeon_droq_check_hw_for_pkts(oct, droq);
+	}
+
+	spin_unlock(&droq->lock);
+
+	list_for_each_safe(tmp, tmp2, &droq->dispatch_list) {
+		struct __dispatch *rdisp = (struct __dispatch *)tmp;
+
+		list_del(tmp);
+		rdisp->disp_fn(rdisp->rinfo,
+			       octeon_get_dispatch_arg
+			       (oct,
+				(u16)rdisp->rinfo->recv_pkt->rh.r.opcode,
+				(u16)rdisp->rinfo->recv_pkt->rh.r.subcode));
+	}
+
+	return total_pkts_processed;
+}
+
+int
+octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no, int cmd,
+			     u32 arg)
+{
+	struct octeon_droq *droq;
+	struct octeon_config *oct_cfg = NULL;
+
+	oct_cfg = octeon_get_conf(oct);
+
+	if (!oct_cfg)
+		return -EINVAL;
+
+	if (q_no >= CFG_GET_OQ_MAX_Q(oct_cfg)) {
+		dev_err(&oct->pci_dev->dev, "%s: droq id (%d) exceeds MAX (%d)\n",
+			__func__, q_no, (oct->num_oqs - 1));
+		return -EINVAL;
+	}
+
+	droq = oct->droq[q_no];
+
+	if (cmd == POLL_EVENT_PROCESS_PKTS)
+		return octeon_droq_process_poll_pkts(oct, droq, arg);
+
+	if (cmd == POLL_EVENT_PENDING_PKTS) {
+		u32 pkt_cnt = atomic_read(&droq->pkts_pending);
+
+		return  octeon_droq_process_packets(oct, droq, pkt_cnt);
+	}
+
+	if (cmd == POLL_EVENT_ENABLE_INTR) {
+		u32 value;
+		unsigned long flags;
+
+		/* Enable Pkt Interrupt */
+		switch (oct->chip_id) {
+		case OCTEON_CN66XX:
+		case OCTEON_CN68XX: {
+			struct octeon_cn6xxx *cn6xxx =
+				(struct octeon_cn6xxx *)oct->chip;
+			spin_lock_irqsave
+				(&cn6xxx->lock_for_droq_int_enb_reg, flags);
+			value =
+				octeon_read_csr(oct,
+						CN6XXX_SLI_PKT_TIME_INT_ENB);
+			value |= (1 << q_no);
+			octeon_write_csr(oct,
+					 CN6XXX_SLI_PKT_TIME_INT_ENB,
+					 value);
+			value =
+				octeon_read_csr(oct,
+						CN6XXX_SLI_PKT_CNT_INT_ENB);
+			value |= (1 << q_no);
+			octeon_write_csr(oct,
+					 CN6XXX_SLI_PKT_CNT_INT_ENB,
+					 value);
+
+			/* don't bother flushing the enables */
+
+			spin_unlock_irqrestore
+				(&cn6xxx->lock_for_droq_int_enb_reg, flags);
+			return 0;
+		}
+		break;
+		}
+
+		return 0;
+	}
+
+	dev_err(&oct->pci_dev->dev, "%s Unknown command: %d\n", __func__, cmd);
+	return -EINVAL;
+}
+
+int octeon_register_droq_ops(struct octeon_device *oct, u32 q_no,
+			     struct octeon_droq_ops *ops)
+{
+	struct octeon_droq *droq;
+	unsigned long flags;
+	struct octeon_config *oct_cfg = NULL;
+
+	oct_cfg = octeon_get_conf(oct);
+
+	if (!oct_cfg)
+		return -EINVAL;
+
+	if (!(ops)) {
+		dev_err(&oct->pci_dev->dev, "%s: droq_ops pointer is NULL\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	if (q_no >= CFG_GET_OQ_MAX_Q(oct_cfg)) {
+		dev_err(&oct->pci_dev->dev, "%s: droq id (%d) exceeds MAX (%d)\n",
+			__func__, q_no, (oct->num_oqs - 1));
+		return -EINVAL;
+	}
+
+	droq = oct->droq[q_no];
+
+	spin_lock_irqsave(&droq->lock, flags);
+
+	memcpy(&droq->ops, ops, sizeof(struct octeon_droq_ops));
+
+	spin_unlock_irqrestore(&droq->lock, flags);
+
+	return 0;
+}
+
+int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no)
+{
+	unsigned long flags;
+	struct octeon_droq *droq;
+	struct octeon_config *oct_cfg = NULL;
+
+	oct_cfg = octeon_get_conf(oct);
+
+	if (!oct_cfg)
+		return -EINVAL;
+
+	if (q_no >= CFG_GET_OQ_MAX_Q(oct_cfg)) {
+		dev_err(&oct->pci_dev->dev, "%s: droq id (%d) exceeds MAX (%d)\n",
+			__func__, q_no, oct->num_oqs - 1);
+		return -EINVAL;
+	}
+
+	droq = oct->droq[q_no];
+
+	if (!droq) {
+		dev_info(&oct->pci_dev->dev,
+			 "Droq id (%d) not available.\n", q_no);
+		return 0;
+	}
+
+	spin_lock_irqsave(&droq->lock, flags);
+
+	droq->ops.fptr = NULL;
+	droq->ops.drop_on_max = 0;
+
+	spin_unlock_irqrestore(&droq->lock, flags);
+
+	return 0;
+}
+
+int octeon_create_droq(struct octeon_device *oct,
+		       u32 q_no, u32 num_descs,
+		       u32 desc_size, void *app_ctx)
+{
+	struct octeon_droq *droq;
+
+	if (oct->droq[q_no]) {
+		dev_dbg(&oct->pci_dev->dev, "Droq already in use. Cannot create droq %d again\n",
+			q_no);
+		return 1;
+	}
+
+	/* Allocate the DS for the new droq. */
+	droq = vmalloc(sizeof(*droq));
+	if (!droq)
+		goto create_droq_fail;
+	memset(droq, 0, sizeof(struct octeon_droq));
+
+	/*Disable the pkt o/p for this Q  */
+	octeon_set_droq_pkt_op(oct, q_no, 0);
+	oct->droq[q_no] = droq;
+
+	/* Initialize the Droq */
+	octeon_init_droq(oct, q_no, num_descs, desc_size, app_ctx);
+
+	oct->num_oqs++;
+
+	dev_dbg(&oct->pci_dev->dev, "%s: Total number of OQ: %d\n", __func__,
+		oct->num_oqs);
+
+	/* Global Droq register settings */
+
+	/* As of now not required, as setting are done for all 32 Droqs at
+	 * the same time.
+	 */
+	return 0;
+
+create_droq_fail:
+	octeon_delete_droq(oct, q_no);
+	return -1;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
new file mode 100644
index 000000000000..7940ccee12d9
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -0,0 +1,426 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*!  \file  octeon_droq.h
+ *   \brief Implementation of Octeon Output queues. "Output" is with
+ *   respect to the Octeon device on the NIC. From this driver's point of
+ *   view they are ingress queues.
+ */
+
+#ifndef __OCTEON_DROQ_H__
+#define __OCTEON_DROQ_H__
+
+/* Default number of packets that will be processed in one iteration. */
+#define MAX_PACKET_BUDGET 0xFFFFFFFF
+
+/** Octeon descriptor format.
+ *  The descriptor ring is made of descriptors which have 2 64-bit values:
+ *  -# Physical (bus) address of the data buffer.
+ *  -# Physical (bus) address of a octeon_droq_info structure.
+ *  The Octeon device DMA's incoming packets and its information at the address
+ *  given by these descriptor fields.
+ */
+struct octeon_droq_desc {
+	/** The buffer pointer */
+	u64 buffer_ptr;
+
+	/** The Info pointer */
+	u64 info_ptr;
+};
+
+#define OCT_DROQ_DESC_SIZE    (sizeof(struct octeon_droq_desc))
+
+/** Information about packet DMA'ed by Octeon.
+ *  The format of the information available at Info Pointer after Octeon
+ *  has posted a packet. Not all descriptors have valid information. Only
+ *  the Info field of the first descriptor for a packet has information
+ *  about the packet.
+ */
+struct octeon_droq_info {
+	/** The Output Receive Header. */
+	union octeon_rh rh;
+
+	/** The Length of the packet. */
+	u64 length;
+};
+
+#define OCT_DROQ_INFO_SIZE   (sizeof(struct octeon_droq_info))
+
+/** Pointer to data buffer.
+ *  Driver keeps a pointer to the data buffer that it made available to
+ *  the Octeon device. Since the descriptor ring keeps physical (bus)
+ *  addresses, this field is required for the driver to keep track of
+ *  the virtual address pointers.
+*/
+struct octeon_recv_buffer {
+	/** Packet buffer, including metadata. */
+	void *buffer;
+
+	/** Data in the packet buffer.  */
+	u8 *data;
+};
+
+#define OCT_DROQ_RECVBUF_SIZE    (sizeof(struct octeon_recv_buffer))
+
+/** Output Queue statistics. Each output queue has four stats fields. */
+struct oct_droq_stats {
+	/** Number of packets received in this queue. */
+	u64 pkts_received;
+
+	/** Bytes received by this queue. */
+	u64 bytes_received;
+
+	/** Packets dropped due to no dispatch function. */
+	u64 dropped_nodispatch;
+
+	/** Packets dropped due to no memory available. */
+	u64 dropped_nomem;
+
+	/** Packets dropped due to large number of pkts to process. */
+	u64 dropped_toomany;
+
+	/** Number of packets  sent to stack from this queue. */
+	u64 rx_pkts_received;
+
+	/** Number of Bytes sent to stack from this queue. */
+	u64 rx_bytes_received;
+
+	/** Num of Packets dropped due to receive path failures. */
+	u64 rx_dropped;
+};
+
+#define POLL_EVENT_INTR_ARRIVED  1
+#define POLL_EVENT_PROCESS_PKTS  2
+#define POLL_EVENT_PENDING_PKTS  3
+#define POLL_EVENT_ENABLE_INTR   4
+
+/* The maximum number of buffers that can be dispatched from the
+ * output/dma queue. Set to 64 assuming 1K buffers in DROQ and the fact that
+ * max packet size from DROQ is 64K.
+ */
+#define    MAX_RECV_BUFS    64
+
+/** Receive Packet format used when dispatching output queue packets
+ *  with non-raw opcodes.
+ *  The received packet will be sent to the upper layers using this
+ *  structure which is passed as a parameter to the dispatch function
+ */
+struct octeon_recv_pkt {
+	/**  Number of buffers in this received packet */
+	u16 buffer_count;
+
+	/** Id of the device that is sending the packet up */
+	u16 octeon_id;
+
+	/** Length of data in the packet buffer */
+	u32 length;
+
+	/** The receive header */
+	union octeon_rh rh;
+
+	/** Pointer to the OS-specific packet buffer */
+	void *buffer_ptr[MAX_RECV_BUFS];
+
+	/** Size of the buffers pointed to by ptr's in buffer_ptr */
+	u32 buffer_size[MAX_RECV_BUFS];
+};
+
+#define OCT_RECV_PKT_SIZE    (sizeof(struct octeon_recv_pkt))
+
+/** The first parameter of a dispatch function.
+ *  For a raw mode opcode, the driver dispatches with the device
+ *  pointer in this structure.
+ *  For non-raw mode opcode, the driver dispatches the recv_pkt
+ *  created to contain the buffers with data received from Octeon.
+ *  ---------------------
+ *  |     *recv_pkt ----|---
+ *  |-------------------|   |
+ *  | 0 or more bytes   |   |
+ *  | reserved by driver|   |
+ *  |-------------------|<-/
+ *  | octeon_recv_pkt   |
+ *  |                   |
+ *  |___________________|
+ */
+struct octeon_recv_info {
+	void *rsvd;
+	struct octeon_recv_pkt *recv_pkt;
+};
+
+#define  OCT_RECV_INFO_SIZE    (sizeof(struct octeon_recv_info))
+
+/** Allocate a recv_info structure. The recv_pkt pointer in the recv_info
+ *  structure is filled in before this call returns.
+ *  @param extra_bytes - extra bytes to be allocated at the end of the recv info
+ *                       structure.
+ *  @return - pointer to a newly allocated recv_info structure.
+ */
+static inline struct octeon_recv_info *octeon_alloc_recv_info(int extra_bytes)
+{
+	struct octeon_recv_info *recv_info;
+	u8 *buf;
+
+	buf = kmalloc(OCT_RECV_PKT_SIZE + OCT_RECV_INFO_SIZE +
+		      extra_bytes, GFP_ATOMIC);
+	if (!buf)
+		return NULL;
+
+	recv_info = (struct octeon_recv_info *)buf;
+	recv_info->recv_pkt =
+		(struct octeon_recv_pkt *)(buf + OCT_RECV_INFO_SIZE);
+	recv_info->rsvd = NULL;
+	if (extra_bytes)
+		recv_info->rsvd = buf + OCT_RECV_INFO_SIZE + OCT_RECV_PKT_SIZE;
+
+	return recv_info;
+}
+
+/** Free a recv_info structure.
+ *  @param recv_info - Pointer to receive_info to be freed
+ */
+static inline void octeon_free_recv_info(struct octeon_recv_info *recv_info)
+{
+	kfree(recv_info);
+}
+
+typedef int (*octeon_dispatch_fn_t)(struct octeon_recv_info *, void *);
+
+/** Used by NIC module to register packet handler and to get device
+ * information for each octeon device.
+ */
+struct octeon_droq_ops {
+	/** This registered function will be called by the driver with
+	 *  the octeon id, pointer to buffer from droq and length of
+	 *  data in the buffer. The receive header gives the port
+	 *  number to the caller.  Function pointer is set by caller.
+	 */
+	void (*fptr)(u32, void *, u32, union octeon_rh *, void *);
+
+	/* This function will be called by the driver for all NAPI related
+	 * events. The first param is the octeon id. The second param is the
+	 * output queue number. The third is the NAPI event that occurred.
+	 */
+	void (*napi_fn)(void *);
+
+	u32 poll_mode;
+
+	/** Flag indicating if the DROQ handler should drop packets that
+	 *  it cannot handle in one iteration. Set by caller.
+	 */
+	u32 drop_on_max;
+};
+
+/** The Descriptor Ring Output Queue structure.
+ *  This structure has all the information required to implement a
+ *  Octeon DROQ.
+ */
+struct octeon_droq {
+	/** A spinlock to protect access to this ring. */
+	spinlock_t lock;
+
+	u32 q_no;
+
+	struct octeon_droq_ops ops;
+
+	struct octeon_device *oct_dev;
+
+	/** The 8B aligned descriptor ring starts at this address. */
+	struct octeon_droq_desc *desc_ring;
+
+	/** Index in the ring where the driver should read the next packet */
+	u32 read_idx;
+
+	/** Index in the ring where Octeon will write the next packet */
+	u32 write_idx;
+
+	/** Index in the ring where the driver will refill the descriptor's
+	 * buffer
+	 */
+	u32 refill_idx;
+
+	/** Packets pending to be processed */
+	atomic_t pkts_pending;
+
+	/** Number of  descriptors in this ring. */
+	u32 max_count;
+
+	/** The number of descriptors pending refill. */
+	u32 refill_count;
+
+	u32 pkts_per_intr;
+	u32 refill_threshold;
+
+	/** The max number of descriptors in DROQ without a buffer.
+	 * This field is used to keep track of empty space threshold. If the
+	 * refill_count reaches this value, the DROQ cannot accept a max-sized
+	 * (64K) packet.
+	 */
+	u32 max_empty_descs;
+
+	/** The 8B aligned info ptrs begin from this address. */
+	struct octeon_droq_info *info_list;
+
+	/** The receive buffer list. This list has the virtual addresses of the
+	 * buffers.
+	 */
+	struct octeon_recv_buffer *recv_buf_list;
+
+	/** The size of each buffer pointed by the buffer pointer. */
+	u32 buffer_size;
+
+	/** Pointer to the mapped packet credit register.
+	 * Host writes number of info/buffer ptrs available to this register
+	 */
+	void  __iomem *pkts_credit_reg;
+
+	/** Pointer to the mapped packet sent register.
+	 * Octeon writes the number of packets DMA'ed to host memory
+	 * in this register.
+	 */
+	void __iomem *pkts_sent_reg;
+
+	struct list_head dispatch_list;
+
+	/** Statistics for this DROQ. */
+	struct oct_droq_stats stats;
+
+	/** DMA mapped address of the DROQ descriptor ring. */
+	size_t desc_ring_dma;
+
+	/** Info ptr list are allocated at this virtual address. */
+	size_t info_base_addr;
+
+	/** DMA mapped address of the info list */
+	size_t info_list_dma;
+
+	/** Allocated size of info list. */
+	u32 info_alloc_size;
+
+	/** application context */
+	void *app_ctx;
+
+	struct napi_struct napi;
+
+	u32 cpu_id;
+
+	struct call_single_data csd;
+};
+
+#define OCT_DROQ_SIZE   (sizeof(struct octeon_droq))
+
+/**
+ *  Allocates space for the descriptor ring for the droq and sets the
+ *   base addr, num desc etc in Octeon registers.
+ *
+ * @param  oct_dev    - pointer to the octeon device structure
+ * @param  q_no       - droq no. ranges from 0 - 3.
+ * @param app_ctx     - pointer to application context
+ * @return Success: 0    Failure: 1
+*/
+int octeon_init_droq(struct octeon_device *oct_dev,
+		     u32 q_no,
+		     u32 num_descs,
+		     u32 desc_size,
+		     void *app_ctx);
+
+/**
+ *  Frees the space for descriptor ring for the droq.
+ *
+ *  @param oct_dev - pointer to the octeon device structure
+ *  @param q_no    - droq no. ranges from 0 - 3.
+ *  @return:    Success: 0    Failure: 1
+*/
+int octeon_delete_droq(struct octeon_device *oct_dev, u32 q_no);
+
+/** Register a change in droq operations. The ops field has a pointer to a
+ * function which will called by the DROQ handler for all packets arriving
+ * on output queues given by q_no irrespective of the type of packet.
+ * The ops field also has a flag which if set tells the DROQ handler to
+ * drop packets if it receives more than what it can process in one
+ * invocation of the handler.
+ * @param oct       - octeon device
+ * @param q_no      - octeon output queue number (0 <= q_no <= MAX_OCTEON_DROQ-1
+ * @param ops       - the droq_ops settings for this queue
+ * @return          - 0 on success, -ENODEV or -EINVAL on error.
+ */
+int
+octeon_register_droq_ops(struct octeon_device *oct,
+			 u32 q_no,
+			 struct octeon_droq_ops *ops);
+
+/** Resets the function pointer and flag settings made by
+ * octeon_register_droq_ops(). After this routine is called, the DROQ handler
+ * will lookup dispatch function for each arriving packet on the output queue
+ * given by q_no.
+ * @param oct       - octeon device
+ * @param q_no      - octeon output queue number (0 <= q_no <= MAX_OCTEON_DROQ-1
+ * @return          - 0 on success, -ENODEV or -EINVAL on error.
+ */
+int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no);
+
+/**   Register a dispatch function for a opcode/subcode. The driver will call
+ *    this dispatch function when it receives a packet with the given
+ *    opcode/subcode in its output queues along with the user specified
+ *    argument.
+ *    @param  oct        - the octeon device to register with.
+ *    @param  opcode     - the opcode for which the dispatch will be registered.
+ *    @param  subcode    - the subcode for which the dispatch will be registered
+ *    @param  fn         - the dispatch function.
+ *    @param  fn_arg     - user specified that will be passed along with the
+ *                         dispatch function by the driver.
+ *    @return Success: 0; Failure: 1
+ */
+int octeon_register_dispatch_fn(struct octeon_device *oct,
+				u16 opcode,
+				u16 subcode,
+				octeon_dispatch_fn_t fn, void *fn_arg);
+
+/**  Remove registration for an opcode/subcode. This will delete the mapping for
+ *   an opcode/subcode. The dispatch function will be unregistered and will no
+ *   longer be called if a packet with the opcode/subcode arrives in the driver
+ *   output queues.
+ *   @param  oct        -  the octeon device to unregister from.
+ *   @param  opcode     -  the opcode to be unregistered.
+ *   @param  subcode    -  the subcode to be unregistered.
+ *
+ *   @return Success: 0; Failure: 1
+ */
+int octeon_unregister_dispatch_fn(struct octeon_device *oct,
+				  u16 opcode,
+				  u16 subcode);
+
+void octeon_droq_print_stats(void);
+
+u32 octeon_droq_check_hw_for_pkts(struct octeon_device *oct,
+				  struct octeon_droq *droq);
+
+int octeon_create_droq(struct octeon_device *oct, u32 q_no,
+		       u32 num_descs, u32 desc_size, void *app_ctx);
+
+int octeon_droq_process_packets(struct octeon_device *oct,
+				struct octeon_droq *droq,
+				u32 budget);
+
+int octeon_process_droq_poll_cmd(struct octeon_device *oct, u32 q_no,
+				 int cmd, u32 arg);
+
+#endif	/*__OCTEON_DROQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
new file mode 100644
index 000000000000..592fe49b589d
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -0,0 +1,319 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*!  \file  octeon_iq.h
+ *   \brief Host Driver: Implementation of Octeon input queues. "Input" is
+ *   with respect to the Octeon device on the NIC. From this driver's
+ *   point of view they are egress queues.
+ */
+
+#ifndef __OCTEON_IQ_H__
+#define  __OCTEON_IQ_H__
+
+#define IQ_STATUS_RUNNING   1
+
+#define IQ_SEND_OK          0
+#define IQ_SEND_STOP        1
+#define IQ_SEND_FAILED     -1
+
+/*-------------------------  INSTRUCTION QUEUE --------------------------*/
+
+/* \cond */
+
+#define REQTYPE_NONE                 0
+#define REQTYPE_NORESP_NET           1
+#define REQTYPE_NORESP_NET_SG        2
+#define REQTYPE_RESP_NET             3
+#define REQTYPE_RESP_NET_SG          4
+#define REQTYPE_SOFT_COMMAND         5
+#define REQTYPE_LAST                 5
+
+struct octeon_request_list {
+	u32 reqtype;
+	void *buf;
+};
+
+/* \endcond */
+
+/** Input Queue statistics. Each input queue has four stats fields. */
+struct oct_iq_stats {
+	u64 instr_posted; /**< Instructions posted to this queue. */
+	u64 instr_processed; /**< Instructions processed in this queue. */
+	u64 instr_dropped; /**< Instructions that could not be processed */
+	u64 bytes_sent;  /**< Bytes sent through this queue. */
+	u64 sgentry_sent;/**< Gather entries sent through this queue. */
+	u64 tx_done;/**< Num of packets sent to network. */
+	u64 tx_iq_busy;/**< Numof times this iq was found to be full. */
+	u64 tx_dropped;/**< Numof pkts dropped dueto xmitpath errors. */
+	u64 tx_tot_bytes;/**< Total count of bytes sento to network. */
+};
+
+#define OCT_IQ_STATS_SIZE   (sizeof(struct oct_iq_stats))
+
+/** The instruction (input) queue.
+ *  The input queue is used to post raw (instruction) mode data or packet
+ *  data to Octeon device from the host. Each input queue (upto 4) for
+ *  a Octeon device has one such structure to represent it.
+*/
+struct octeon_instr_queue {
+	/** A spinlock to protect access to the input ring.  */
+	spinlock_t lock;
+
+	/** Flag that indicates if the queue uses 64 byte commands. */
+	u32 iqcmd_64B:1;
+
+	/** Queue Number. */
+	u32 iq_no:5;
+
+	u32 rsvd:17;
+
+	/* Controls the periodic flushing of iq */
+	u32 do_auto_flush:1;
+
+	u32 status:8;
+
+	/** Maximum no. of instructions in this queue. */
+	u32 max_count;
+
+	/** Index in input ring where the driver should write the next packet */
+	u32 host_write_index;
+
+	/** Index in input ring where Octeon is expected to read the next
+	 * packet.
+	 */
+	u32 octeon_read_index;
+
+	/** This index aids in finding the window in the queue where Octeon
+	  * has read the commands.
+	  */
+	u32 flush_index;
+
+	/** This field keeps track of the instructions pending in this queue. */
+	atomic_t instr_pending;
+
+	u32 reset_instr_cnt;
+
+	/** Pointer to the Virtual Base addr of the input ring. */
+	u8 *base_addr;
+
+	struct octeon_request_list *request_list;
+
+	/** Octeon doorbell register for the ring. */
+	void __iomem *doorbell_reg;
+
+	/** Octeon instruction count register for this ring. */
+	void __iomem *inst_cnt_reg;
+
+	/** Number of instructions pending to be posted to Octeon. */
+	u32 fill_cnt;
+
+	/** The max. number of instructions that can be held pending by the
+	 * driver.
+	 */
+	u32 fill_threshold;
+
+	/** The last time that the doorbell was rung. */
+	u64 last_db_time;
+
+	/** The doorbell timeout. If the doorbell was not rung for this time and
+	  * fill_cnt is non-zero, ring the doorbell again.
+	  */
+	u32 db_timeout;
+
+	/** Statistics for this input queue. */
+	struct oct_iq_stats stats;
+
+	/** DMA mapped base address of the input descriptor ring. */
+	u64 base_addr_dma;
+
+	/** Application context */
+	void *app_ctx;
+};
+
+/*----------------------  INSTRUCTION FORMAT ----------------------------*/
+
+/** 32-byte instruction format.
+ *  Format of instruction for a 32-byte mode input queue.
+ */
+struct octeon_instr_32B {
+	/** Pointer where the input data is available. */
+	u64 dptr;
+
+	/** Instruction Header.  */
+	u64 ih;
+
+	/** Pointer where the response for a RAW mode packet will be written
+	 * by Octeon.
+	 */
+	u64 rptr;
+
+	/** Input Request Header. Additional info about the input. */
+	u64 irh;
+
+};
+
+#define OCT_32B_INSTR_SIZE     (sizeof(struct octeon_instr_32B))
+
+/** 64-byte instruction format.
+ *  Format of instruction for a 64-byte mode input queue.
+ */
+struct octeon_instr_64B {
+	/** Pointer where the input data is available. */
+	u64 dptr;
+
+	/** Instruction Header. */
+	u64 ih;
+
+	/** Input Request Header. */
+	u64 irh;
+
+	/** opcode/subcode specific parameters */
+	u64 ossp[2];
+
+	/** Return Data Parameters */
+	u64 rdp;
+
+	/** Pointer where the response for a RAW mode packet will be written
+	 * by Octeon.
+	 */
+	u64 rptr;
+
+	u64 reserved;
+
+};
+
+#define OCT_64B_INSTR_SIZE     (sizeof(struct octeon_instr_64B))
+
+/** The size of each buffer in soft command buffer pool
+ */
+#define  SOFT_COMMAND_BUFFER_SIZE	1024
+
+struct octeon_soft_command {
+	/** Soft command buffer info. */
+	struct list_head node;
+	u64 dma_addr;
+	u32 size;
+
+	/** Command and return status */
+	struct octeon_instr_64B cmd;
+#define COMPLETION_WORD_INIT    0xffffffffffffffffULL
+	u64 *status_word;
+
+	/** Data buffer info */
+	void *virtdptr;
+	u64 dmadptr;
+	u32 datasize;
+
+	/** Return buffer info */
+	void *virtrptr;
+	u64 dmarptr;
+	u32 rdatasize;
+
+	/** Context buffer info */
+	void *ctxptr;
+	u32  ctxsize;
+
+	/** Time out and callback */
+	size_t wait_time;
+	size_t timeout;
+	u32 iq_no;
+	void (*callback)(struct octeon_device *, u32, void *);
+	void *callback_arg;
+};
+
+/** Maximum number of buffers to allocate into soft command buffer pool
+ */
+#define  MAX_SOFT_COMMAND_BUFFERS	16
+
+/** Head of a soft command buffer pool.
+ */
+struct octeon_sc_buffer_pool {
+	/** List structure to add delete pending entries to */
+	struct list_head head;
+
+	/** A lock for this response list */
+	spinlock_t lock;
+
+	atomic_t alloc_buf_count;
+};
+
+int octeon_setup_sc_buffer_pool(struct octeon_device *oct);
+int octeon_free_sc_buffer_pool(struct octeon_device *oct);
+struct octeon_soft_command *
+	octeon_alloc_soft_command(struct octeon_device *oct,
+				  u32 datasize, u32 rdatasize,
+				  u32 ctxsize);
+void octeon_free_soft_command(struct octeon_device *oct,
+			      struct octeon_soft_command *sc);
+
+/**
+ *  octeon_init_instr_queue()
+ *  @param octeon_dev      - pointer to the octeon device structure.
+ *  @param iq_no           - queue to be initialized (0 <= q_no <= 3).
+ *
+ *  Called at driver init time for each input queue. iq_conf has the
+ *  configuration parameters for the queue.
+ *
+ *  @return  Success: 0   Failure: 1
+ */
+int octeon_init_instr_queue(struct octeon_device *octeon_dev, u32 iq_no,
+			    u32 num_descs);
+
+/**
+ *  octeon_delete_instr_queue()
+ *  @param octeon_dev      - pointer to the octeon device structure.
+ *  @param iq_no           - queue to be deleted (0 <= q_no <= 3).
+ *
+ *  Called at driver unload time for each input queue. Deletes all
+ *  allocated resources for the input queue.
+ *
+ *  @return  Success: 0   Failure: 1
+ */
+int octeon_delete_instr_queue(struct octeon_device *octeon_dev, u32 iq_no);
+
+int lio_wait_for_instr_fetch(struct octeon_device *oct);
+
+int
+octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype,
+				void (*fn)(void *));
+
+int
+lio_process_iq_request_list(struct octeon_device *oct,
+			    struct octeon_instr_queue *iq);
+
+int octeon_send_command(struct octeon_device *oct, u32 iq_no,
+			u32 force_db, void *cmd, void *buf,
+			u32 datasize, u32 reqtype);
+
+void octeon_prepare_soft_command(struct octeon_device *oct,
+				 struct octeon_soft_command *sc,
+				 u8 opcode, u8 subcode,
+				 u32 irh_ossp, u64 ossp0,
+				 u64 ossp1);
+
+int octeon_send_soft_command(struct octeon_device *oct,
+			     struct octeon_soft_command *sc);
+
+int octeon_setup_iq(struct octeon_device *oct, u32 iq_no,
+		    u32 num_descs, void *app_ctx);
+
+#endif				/* __OCTEON_IQ_H__ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
new file mode 100644
index 000000000000..cbd081981180
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -0,0 +1,237 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*! \file octeon_main.h
+ *  \brief Host Driver: This file is included by all host driver source files
+ *  to include common definitions.
+ */
+
+#ifndef _OCTEON_MAIN_H_
+#define  _OCTEON_MAIN_H_
+
+#if BITS_PER_LONG == 32
+#define CVM_CAST64(v) ((long long)(v))
+#elif BITS_PER_LONG == 64
+#define CVM_CAST64(v) ((long long)(long)(v))
+#else
+#error "Unknown system architecture"
+#endif
+
+#define DRV_NAME "LiquidIO"
+
+/**
+ * \brief determines if a given console has debug enabled.
+ * @param console console to check
+ * @returns  1 = enabled. 0 otherwise
+ */
+int octeon_console_debug_enabled(u32 console);
+
+/* BQL-related functions */
+void octeon_report_sent_bytes_to_bql(void *buf, int reqtype);
+void octeon_update_tx_completion_counters(void *buf, int reqtype,
+					  unsigned int *pkts_compl,
+					  unsigned int *bytes_compl);
+void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl,
+					unsigned int bytes_compl);
+
+/** Swap 8B blocks */
+static inline void octeon_swap_8B_data(u64 *data, u32 blocks)
+{
+	while (blocks) {
+		cpu_to_be64s(data);
+		blocks--;
+		data++;
+	}
+}
+
+/**
+  * \brief unmaps a PCI BAR
+  * @param oct Pointer to Octeon device
+  * @param baridx bar index
+  */
+static inline void octeon_unmap_pci_barx(struct octeon_device *oct, int baridx)
+{
+	dev_dbg(&oct->pci_dev->dev, "Freeing PCI mapped regions for Bar%d\n",
+		baridx);
+
+	if (oct->mmio[baridx].done)
+		iounmap(oct->mmio[baridx].hw_addr);
+
+	if (oct->mmio[baridx].start)
+		pci_release_region(oct->pci_dev, baridx * 2);
+}
+
+/**
+ * \brief maps a PCI BAR
+ * @param oct Pointer to Octeon device
+ * @param baridx bar index
+ * @param max_map_len maximum length of mapped memory
+ */
+static inline int octeon_map_pci_barx(struct octeon_device *oct,
+				      int baridx, int max_map_len)
+{
+	u32 mapped_len = 0;
+
+	if (pci_request_region(oct->pci_dev, baridx * 2, DRV_NAME)) {
+		dev_err(&oct->pci_dev->dev, "pci_request_region failed for bar %d\n",
+			baridx);
+		return 1;
+	}
+
+	oct->mmio[baridx].start = pci_resource_start(oct->pci_dev, baridx * 2);
+	oct->mmio[baridx].len = pci_resource_len(oct->pci_dev, baridx * 2);
+
+	mapped_len = oct->mmio[baridx].len;
+	if (!mapped_len)
+		return 1;
+
+	if (max_map_len && (mapped_len > max_map_len))
+		mapped_len = max_map_len;
+
+	oct->mmio[baridx].hw_addr =
+		ioremap(oct->mmio[baridx].start, mapped_len);
+	oct->mmio[baridx].mapped_len = mapped_len;
+
+	dev_dbg(&oct->pci_dev->dev, "BAR%d start: 0x%llx mapped %u of %u bytes\n",
+		baridx, oct->mmio[baridx].start, mapped_len,
+		oct->mmio[baridx].len);
+
+	if (!oct->mmio[baridx].hw_addr) {
+		dev_err(&oct->pci_dev->dev, "error ioremap for bar %d\n",
+			baridx);
+		return 1;
+	}
+	oct->mmio[baridx].done = 1;
+
+	return 0;
+}
+
+static inline void *
+cnnic_alloc_aligned_dma(struct pci_dev *pci_dev,
+			u32 size,
+			u32 *alloc_size,
+			size_t *orig_ptr,
+			size_t *dma_addr __attribute__((unused)))
+{
+	int retries = 0;
+	void *ptr = NULL;
+
+#define OCTEON_MAX_ALLOC_RETRIES     1
+	do {
+		ptr =
+		    (void *)__get_free_pages(GFP_KERNEL,
+					     get_order(size));
+		if ((unsigned long)ptr & 0x07) {
+			free_pages((unsigned long)ptr, get_order(size));
+			ptr = NULL;
+			/* Increment the size required if the first
+			 * attempt failed.
+			 */
+			if (!retries)
+				size += 7;
+		}
+		retries++;
+	} while ((retries <= OCTEON_MAX_ALLOC_RETRIES) && !ptr);
+
+	*alloc_size = size;
+	*orig_ptr = (unsigned long)ptr;
+	if ((unsigned long)ptr & 0x07)
+		ptr = (void *)(((unsigned long)ptr + 7) & ~(7UL));
+	return ptr;
+}
+
+#define cnnic_free_aligned_dma(pci_dev, ptr, size, orig_ptr, dma_addr) \
+		free_pages(orig_ptr, get_order(size))
+
+static inline void
+sleep_cond(wait_queue_head_t *wait_queue, int *condition)
+{
+	wait_queue_t we;
+
+	init_waitqueue_entry(&we, current);
+	add_wait_queue(wait_queue, &we);
+	while (!(ACCESS_ONCE(*condition))) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (signal_pending(current))
+			goto out;
+		schedule();
+	}
+out:
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(wait_queue, &we);
+}
+
+static inline void
+sleep_atomic_cond(wait_queue_head_t *waitq, atomic_t *pcond)
+{
+	wait_queue_t we;
+
+	init_waitqueue_entry(&we, current);
+	add_wait_queue(waitq, &we);
+	while (!atomic_read(pcond)) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (signal_pending(current))
+			goto out;
+		schedule();
+	}
+out:
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(waitq, &we);
+}
+
+/* Gives up the CPU for a timeout period.
+ * Check that the condition is not true before we go to sleep for a
+ * timeout period.
+ */
+static inline void
+sleep_timeout_cond(wait_queue_head_t *wait_queue,
+		   int *condition,
+		   int timeout)
+{
+	wait_queue_t we;
+
+	init_waitqueue_entry(&we, current);
+	add_wait_queue(wait_queue, &we);
+	set_current_state(TASK_INTERRUPTIBLE);
+	if (!(*condition))
+		schedule_timeout(timeout);
+	set_current_state(TASK_RUNNING);
+	remove_wait_queue(wait_queue, &we);
+}
+
+#ifndef ROUNDUP4
+#define ROUNDUP4(val) (((val) + 3) & 0xfffffffc)
+#endif
+
+#ifndef ROUNDUP8
+#define ROUNDUP8(val) (((val) + 7) & 0xfffffff8)
+#endif
+
+#ifndef ROUNDUP16
+#define ROUNDUP16(val) (((val) + 15) & 0xfffffff0)
+#endif
+
+#ifndef ROUNDUP128
+#define ROUNDUP128(val) (((val) + 127) & 0xffffff80)
+#endif
+
+#endif /* _OCTEON_MAIN_H_ */
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
new file mode 100644
index 000000000000..5aecef870377
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c
@@ -0,0 +1,199 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+#define MEMOPS_IDX   MAX_BAR1_MAP_INDEX
+
+static inline void
+octeon_toggle_bar1_swapmode(struct octeon_device *oct __attribute__((unused)),
+			    u32 idx __attribute__((unused)))
+{
+#ifdef __BIG_ENDIAN_BITFIELD
+	u32 mask;
+
+	mask = oct->fn_list.bar1_idx_read(oct, idx);
+	mask = (mask & 0x2) ? (mask & ~2) : (mask | 2);
+	oct->fn_list.bar1_idx_write(oct, idx, mask);
+#endif
+}
+
+static void
+octeon_pci_fastwrite(struct octeon_device *oct, u8 __iomem *mapped_addr,
+		     u8 *hostbuf, u32 len)
+{
+	while ((len) && ((unsigned long)mapped_addr) & 7) {
+		writeb(*(hostbuf++), mapped_addr++);
+		len--;
+	}
+
+	octeon_toggle_bar1_swapmode(oct, MEMOPS_IDX);
+
+	while (len >= 8) {
+		writeq(*((u64 *)hostbuf), mapped_addr);
+		mapped_addr += 8;
+		hostbuf += 8;
+		len -= 8;
+	}
+
+	octeon_toggle_bar1_swapmode(oct, MEMOPS_IDX);
+
+	while (len--)
+		writeb(*(hostbuf++), mapped_addr++);
+}
+
+static void
+octeon_pci_fastread(struct octeon_device *oct, u8 __iomem *mapped_addr,
+		    u8 *hostbuf, u32 len)
+{
+	while ((len) && ((unsigned long)mapped_addr) & 7) {
+		*(hostbuf++) = readb(mapped_addr++);
+		len--;
+	}
+
+	octeon_toggle_bar1_swapmode(oct, MEMOPS_IDX);
+
+	while (len >= 8) {
+		*((u64 *)hostbuf) = readq(mapped_addr);
+		mapped_addr += 8;
+		hostbuf += 8;
+		len -= 8;
+	}
+
+	octeon_toggle_bar1_swapmode(oct, MEMOPS_IDX);
+
+	while (len--)
+		*(hostbuf++) = readb(mapped_addr++);
+}
+
+/* Core mem read/write with temporary bar1 settings. */
+/* op = 1 to read, op = 0 to write. */
+static void
+__octeon_pci_rw_core_mem(struct octeon_device *oct, u64 addr,
+			 u8 *hostbuf, u32 len, u32 op)
+{
+	u32 copy_len = 0, index_reg_val = 0;
+	unsigned long flags;
+	u8 __iomem *mapped_addr;
+
+	spin_lock_irqsave(&oct->mem_access_lock, flags);
+
+	/* Save the original index reg value. */
+	index_reg_val = oct->fn_list.bar1_idx_read(oct, MEMOPS_IDX);
+	do {
+		oct->fn_list.bar1_idx_setup(oct, addr, MEMOPS_IDX, 1);
+		mapped_addr = oct->mmio[1].hw_addr
+		    + (MEMOPS_IDX << 22) + (addr & 0x3fffff);
+
+		/* If operation crosses a 4MB boundary, split the transfer
+		 * at the 4MB
+		 * boundary.
+		 */
+		if (((addr + len - 1) & ~(0x3fffff)) != (addr & ~(0x3fffff))) {
+			copy_len = (u32)(((addr & ~(0x3fffff)) +
+				   (MEMOPS_IDX << 22)) - addr);
+		} else {
+			copy_len = len;
+		}
+
+		if (op) {	/* read from core */
+			octeon_pci_fastread(oct, mapped_addr, hostbuf,
+					    copy_len);
+		} else {
+			octeon_pci_fastwrite(oct, mapped_addr, hostbuf,
+					     copy_len);
+		}
+
+		len -= copy_len;
+		addr += copy_len;
+		hostbuf += copy_len;
+
+	} while (len);
+
+	oct->fn_list.bar1_idx_write(oct, MEMOPS_IDX, index_reg_val);
+
+	spin_unlock_irqrestore(&oct->mem_access_lock, flags);
+}
+
+void
+octeon_pci_read_core_mem(struct octeon_device *oct,
+			 u64 coreaddr,
+			 u8 *buf,
+			 u32 len)
+{
+	__octeon_pci_rw_core_mem(oct, coreaddr, buf, len, 1);
+}
+
+void
+octeon_pci_write_core_mem(struct octeon_device *oct,
+			  u64 coreaddr,
+			  u8 *buf,
+			  u32 len)
+{
+	__octeon_pci_rw_core_mem(oct, coreaddr, buf, len, 0);
+}
+
+u64 octeon_read_device_mem64(struct octeon_device *oct, u64 coreaddr)
+{
+	__be64 ret;
+
+	__octeon_pci_rw_core_mem(oct, coreaddr, (u8 *)&ret, 8, 1);
+
+	return be64_to_cpu(ret);
+}
+
+u32 octeon_read_device_mem32(struct octeon_device *oct, u64 coreaddr)
+{
+	__be32 ret;
+
+	__octeon_pci_rw_core_mem(oct, coreaddr, (u8 *)&ret, 4, 1);
+
+	return be32_to_cpu(ret);
+}
+
+void octeon_write_device_mem32(struct octeon_device *oct, u64 coreaddr,
+			       u32 val)
+{
+	__be32 t = cpu_to_be32(val);
+
+	__octeon_pci_rw_core_mem(oct, coreaddr, (u8 *)&t, 4, 0);
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h
new file mode 100644
index 000000000000..11b183377b44
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.h
@@ -0,0 +1,75 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*!  \file octeon_mem_ops.h
+ *   \brief Host Driver: Routines used to read/write Octeon memory.
+ */
+
+#ifndef __OCTEON_MEM_OPS_H__
+#define __OCTEON_MEM_OPS_H__
+
+/**  Read a 64-bit value from a BAR1 mapped core memory address.
+ *   @param  oct        -  pointer to the octeon device.
+ *   @param  core_addr  -  the address to read from.
+ *
+ *   The range_idx gives the BAR1 index register for the range of address
+ *   in which core_addr is mapped.
+ *
+ *   @return  64-bit value read from Core memory
+ */
+u64 octeon_read_device_mem64(struct octeon_device *oct, u64 core_addr);
+
+/**  Read a 32-bit value from a BAR1 mapped core memory address.
+ *   @param  oct        -  pointer to the octeon device.
+ *   @param  core_addr  -  the address to read from.
+ *
+ *   @return  32-bit value read from Core memory
+ */
+u32 octeon_read_device_mem32(struct octeon_device *oct, u64 core_addr);
+
+/**  Write a 32-bit value to a BAR1 mapped core memory address.
+ *   @param  oct        -  pointer to the octeon device.
+ *   @param  core_addr  -  the address to write to.
+ *   @param  val        -  32-bit value to write.
+ */
+void
+octeon_write_device_mem32(struct octeon_device *oct,
+			  u64 core_addr,
+			  u32 val);
+
+/** Read multiple bytes from Octeon memory.
+ */
+void
+octeon_pci_read_core_mem(struct octeon_device *oct,
+			 u64 coreaddr,
+			 u8 *buf,
+			 u32 len);
+
+/** Write multiple bytes into Octeon memory.
+ */
+void
+octeon_pci_write_core_mem(struct octeon_device *oct,
+			  u64 coreaddr,
+			  u8 *buf,
+			  u32 len);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
new file mode 100644
index 000000000000..b3abe5818fd3
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -0,0 +1,224 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*!  \file  octeon_network.h
+ *   \brief Host NIC Driver: Structure and Macro definitions used by NIC Module.
+ */
+
+#ifndef __OCTEON_NETWORK_H__
+#define __OCTEON_NETWORK_H__
+#include <linux/version.h>
+#include <linux/dma-mapping.h>
+#include <linux/ptp_clock_kernel.h>
+
+/** LiquidIO per-interface network private data */
+struct lio {
+	/** State of the interface. Rx/Tx happens only in the RUNNING state.  */
+	atomic_t ifstate;
+
+	/** Octeon Interface index number. This device will be represented as
+	 *  oct<ifidx> in the system.
+	 */
+	int ifidx;
+
+	/** Octeon Input queue to use to transmit for this network interface. */
+	int txq;
+
+	/** Octeon Output queue from which pkts arrive
+	 * for this network interface.
+	 */
+	int rxq;
+
+	/** Guards the glist */
+	spinlock_t lock;
+
+	/** Linked list of gather components */
+	struct list_head glist;
+
+	/** Pointer to the NIC properties for the Octeon device this network
+	 *  interface is associated with.
+	 */
+	struct octdev_props *octprops;
+
+	/** Pointer to the octeon device structure. */
+	struct octeon_device *oct_dev;
+
+	struct net_device *netdev;
+
+	/** Link information sent by the core application for this interface. */
+	struct oct_link_info linfo;
+
+	/** Size of Tx queue for this octeon device. */
+	u32 tx_qsize;
+
+	/** Size of Rx queue for this octeon device. */
+	u32 rx_qsize;
+
+	/** Size of MTU this octeon device. */
+	u32 mtu;
+
+	/** msg level flag per interface. */
+	u32 msg_enable;
+
+	/** Copy of Interface capabilities: TSO, TSO6, LRO, Chescksums . */
+	u64 dev_capability;
+
+	/** Copy of beacaon reg in phy */
+	u32 phy_beacon_val;
+
+	/** Copy of ctrl reg in phy */
+	u32 led_ctrl_val;
+
+	/* PTP clock information */
+	struct ptp_clock_info ptp_info;
+	struct ptp_clock *ptp_clock;
+	s64 ptp_adjust;
+
+	/* for atomic access to Octeon PTP reg and data struct */
+	spinlock_t ptp_lock;
+
+	/* Interface info */
+	u32	intf_open;
+
+	/* work queue for  txq status */
+	struct cavium_wq	txq_status_wq;
+
+};
+
+#define LIO_SIZE         (sizeof(struct lio))
+#define GET_LIO(netdev)  ((struct lio *)netdev_priv(netdev))
+
+/**
+ * \brief Enable or disable feature
+ * @param netdev    pointer to network device
+ * @param cmd       Command that just requires acknowledgment
+ */
+int liquidio_set_feature(struct net_device *netdev, int cmd);
+
+/**
+ * \brief Link control command completion callback
+ * @param nctrl_ptr pointer to control packet structure
+ *
+ * This routine is called by the callback function when a ctrl pkt sent to
+ * core app completes. The nctrl_ptr contains a copy of the command type
+ * and data sent to the core app. This routine is only called if the ctrl
+ * pkt was sent successfully to the core app.
+ */
+void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr);
+
+/**
+ * \brief Register ethtool operations
+ * @param netdev    pointer to network device
+ */
+void liquidio_set_ethtool_ops(struct net_device *netdev);
+
+static inline void
+*recv_buffer_alloc(struct octeon_device *oct __attribute__((unused)),
+		   u32 q_no __attribute__((unused)), u32 size)
+{
+#define SKB_ADJ_MASK  0x3F
+#define SKB_ADJ       (SKB_ADJ_MASK + 1)
+
+	struct sk_buff *skb = dev_alloc_skb(size + SKB_ADJ);
+
+	if ((unsigned long)skb->data & SKB_ADJ_MASK) {
+		u32 r = SKB_ADJ - ((unsigned long)skb->data & SKB_ADJ_MASK);
+
+		skb_reserve(skb, r);
+	}
+
+	return (void *)skb;
+}
+
+static inline void recv_buffer_free(void *buffer)
+{
+	dev_kfree_skb_any((struct sk_buff *)buffer);
+}
+
+#define lio_dma_alloc(oct, size, dma_addr) \
+	dma_alloc_coherent(&oct->pci_dev->dev, size, dma_addr, GFP_KERNEL)
+#define lio_dma_free(oct, size, virt_addr, dma_addr) \
+	dma_free_coherent(&oct->pci_dev->dev, size, virt_addr, dma_addr)
+
+#define   get_rbd(ptr)      (((struct sk_buff *)(ptr))->data)
+
+static inline u64
+lio_map_ring_info(struct octeon_droq *droq, u32 i)
+{
+	dma_addr_t dma_addr;
+	struct octeon_device *oct = droq->oct_dev;
+
+	dma_addr = dma_map_single(&oct->pci_dev->dev, &droq->info_list[i],
+				  OCT_DROQ_INFO_SIZE, DMA_FROM_DEVICE);
+
+	BUG_ON(dma_mapping_error(&oct->pci_dev->dev, dma_addr));
+
+	return (u64)dma_addr;
+}
+
+static inline void
+lio_unmap_ring_info(struct pci_dev *pci_dev,
+		    u64 info_ptr, u32 size)
+{
+	dma_unmap_single(&pci_dev->dev, info_ptr, size, DMA_FROM_DEVICE);
+}
+
+static inline u64
+lio_map_ring(struct pci_dev *pci_dev,
+	     void *buf, u32 size)
+{
+	dma_addr_t dma_addr;
+
+	dma_addr = dma_map_single(&pci_dev->dev, get_rbd(buf), size,
+				  DMA_FROM_DEVICE);
+
+	BUG_ON(dma_mapping_error(&pci_dev->dev, dma_addr));
+
+	return (u64)dma_addr;
+}
+
+static inline void
+lio_unmap_ring(struct pci_dev *pci_dev,
+	       u64 buf_ptr, u32 size)
+{
+	dma_unmap_single(&pci_dev->dev,
+			 buf_ptr, size,
+			 DMA_FROM_DEVICE);
+}
+
+static inline void *octeon_fast_packet_alloc(struct octeon_device *oct,
+					     struct octeon_droq *droq,
+					     u32 q_no, u32 size)
+{
+	return recv_buffer_alloc(oct, q_no, size);
+}
+
+static inline void octeon_fast_packet_next(struct octeon_droq *droq,
+					   struct sk_buff *nicbuf,
+					   int copy_len,
+					   int idx)
+{
+	memcpy(skb_put(nicbuf, copy_len),
+	       get_rbd(droq->recv_buf_list[idx].buffer), copy_len);
+}
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
new file mode 100644
index 000000000000..1a0191549cb3
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -0,0 +1,189 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+#include "octeon_mem_ops.h"
+
+void *
+octeon_alloc_soft_command_resp(struct octeon_device    *oct,
+			       struct octeon_instr_64B *cmd,
+			       size_t		       rdatasize)
+{
+	struct octeon_soft_command *sc;
+	struct octeon_instr_ih  *ih;
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_rdp *rdp;
+
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct, 0, rdatasize, 0);
+
+	if (!sc)
+		return NULL;
+
+	/* Copy existing command structure into the soft command */
+	memcpy(&sc->cmd, cmd, sizeof(struct octeon_instr_64B));
+
+	/* Add in the response related fields. Opcode and Param are already
+	 * there.
+	 */
+	ih      = (struct octeon_instr_ih *)&sc->cmd.ih;
+	ih->fsz = 40; /* irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
+
+	irh        = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh->rflag = 1; /* a response is required */
+	irh->len   = 4; /* means four 64-bit words immediately follow irh */
+
+	rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+	rdp->pcie_port = oct->pcie_port;
+	rdp->rlen      = rdatasize;
+
+	*sc->status_word = COMPLETION_WORD_INIT;
+
+	sc->wait_time = 1000;
+	sc->timeout = jiffies + sc->wait_time;
+
+	return sc;
+}
+
+int octnet_send_nic_data_pkt(struct octeon_device *oct,
+			     struct octnic_data_pkt *ndata,
+			     u32 xmit_more)
+{
+	int ring_doorbell;
+
+	ring_doorbell = !xmit_more;
+
+	return octeon_send_command(oct, ndata->q_no, ring_doorbell, &ndata->cmd,
+				   ndata->buf, ndata->datasize,
+				   ndata->reqtype);
+}
+
+static void octnet_link_ctrl_callback(struct octeon_device *oct,
+				      u32 status,
+				      void *sc_ptr)
+{
+	struct octeon_soft_command *sc = (struct octeon_soft_command *)sc_ptr;
+	struct octnic_ctrl_pkt *nctrl;
+
+	nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr;
+
+	/* Call the callback function if status is OK.
+	 * Status is OK only if a response was expected and core returned
+	 * success.
+	 * If no response was expected, status is OK if the command was posted
+	 * successfully.
+	 */
+	if (!status && nctrl->cb_fn)
+		nctrl->cb_fn(nctrl);
+
+	octeon_free_soft_command(oct, sc);
+}
+
+static inline struct octeon_soft_command
+*octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct,
+			  struct octnic_ctrl_pkt *nctrl,
+			  struct octnic_ctrl_params nparams)
+{
+	struct octeon_soft_command *sc = NULL;
+	u8 *data;
+	size_t rdatasize;
+	u32 uddsize = 0, datasize = 0;
+
+	uddsize = (u32)(nctrl->ncmd.s.more * 8);
+
+	datasize = OCTNET_CMD_SIZE + uddsize;
+	rdatasize = (nctrl->wait_time) ? 16 : 0;
+
+	sc = (struct octeon_soft_command *)
+		octeon_alloc_soft_command(oct, datasize, rdatasize,
+					  sizeof(struct octnic_ctrl_pkt));
+
+	if (!sc)
+		return NULL;
+
+	memcpy(sc->ctxptr, nctrl, sizeof(struct octnic_ctrl_pkt));
+
+	data = (u8 *)sc->virtdptr;
+
+	memcpy(data, &nctrl->ncmd,  OCTNET_CMD_SIZE);
+
+	octeon_swap_8B_data((u64 *)data, (OCTNET_CMD_SIZE >> 3));
+
+	if (uddsize) {
+		/* Endian-Swap for UDD should have been done by caller. */
+		memcpy(data + OCTNET_CMD_SIZE, nctrl->udd, uddsize);
+	}
+
+	octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD,
+				    0, 0, 0);
+
+	sc->callback = octnet_link_ctrl_callback;
+	sc->callback_arg = sc;
+	sc->wait_time = nctrl->wait_time;
+
+	return sc;
+}
+
+int
+octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
+			 struct octnic_ctrl_pkt *nctrl,
+			 struct octnic_ctrl_params nparams)
+{
+	int retval;
+	struct octeon_soft_command *sc = NULL;
+
+	sc = octnic_alloc_ctrl_pkt_sc(oct, nctrl, nparams);
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev, "%s soft command alloc failed\n",
+			__func__);
+		return -1;
+	}
+
+	retval = octeon_send_soft_command(oct, sc);
+	if (retval) {
+		octeon_free_soft_command(oct, sc);
+		dev_err(&oct->pci_dev->dev, "%s soft command send failed status: %x\n",
+			__func__, retval);
+		return -1;
+	}
+
+	return retval;
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
new file mode 100644
index 000000000000..0238857c8105
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -0,0 +1,227 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*!  \file octeon_nic.h
+ *   \brief Host NIC Driver: Routine to send network data &
+ *   control packet to Octeon.
+ */
+
+#ifndef __OCTEON_NIC_H__
+#define  __OCTEON_NIC_H__
+
+/* Maximum number of 8-byte words can be sent in a NIC control message.
+ */
+#define  MAX_NCTRL_UDD  32
+
+typedef void (*octnic_ctrl_pkt_cb_fn_t) (void *);
+
+/* Structure of control information passed by the NIC module to the OSI
+ * layer when sending control commands to Octeon device software.
+ */
+struct octnic_ctrl_pkt {
+	/** Command to be passed to the Octeon device software. */
+	union octnet_cmd ncmd;
+
+	/** Send buffer  */
+	void *data;
+	u64 dmadata;
+
+	/** Response buffer */
+	void *rdata;
+	u64 dmardata;
+
+	/** Additional data that may be needed by some commands. */
+	u64 udd[MAX_NCTRL_UDD];
+
+	/** Time to wait for Octeon software to respond to this control command.
+	 *  If wait_time is 0, OSI assumes no response is expected.
+	 */
+	size_t wait_time;
+
+	/** The network device that issued the control command. */
+	u64 netpndev;
+
+	/** Callback function called when the command has been fetched */
+	octnic_ctrl_pkt_cb_fn_t cb_fn;
+};
+
+#define MAX_UDD_SIZE(nctrl) (sizeof(nctrl->udd))
+
+/** Structure of data information passed by the NIC module to the OSI
+ * layer when forwarding data to Octeon device software.
+ */
+struct octnic_data_pkt {
+	/** Pointer to information maintained by NIC module for this packet. The
+	 *  OSI layer passes this as-is to the driver.
+	 */
+	void *buf;
+
+	/** Type of buffer passed in "buf" above. */
+	u32 reqtype;
+
+	/** Total data bytes to be transferred in this command. */
+	u32 datasize;
+
+	/** Command to be passed to the Octeon device software. */
+	struct octeon_instr_64B cmd;
+
+	/** Input queue to use to send this command. */
+	u32 q_no;
+
+};
+
+/** Structure passed by NIC module to OSI layer to prepare a command to send
+ * network data to Octeon.
+ */
+union octnic_cmd_setup {
+	struct {
+		u32 ifidx:8;
+		u32 cksum_offset:7;
+		u32 gather:1;
+		u32 timestamp:1;
+		u32 ipv4opts_ipv6exthdr:2;
+		u32 ip_csum:1;
+		u32 tnl_csum:1;
+
+		u32 rsvd:11;
+		union {
+			u32 datasize;
+			u32 gatherptrs;
+		} u;
+	} s;
+
+	u64 u64;
+
+};
+
+struct octnic_ctrl_params {
+	u32 resp_order;
+};
+
+static inline int octnet_iq_is_full(struct octeon_device *oct, u32 q_no)
+{
+	return ((u32)atomic_read(&oct->instr_queue[q_no]->instr_pending)
+		>= (oct->instr_queue[q_no]->max_count - 2));
+}
+
+/** Utility function to prepare a 64B NIC instruction based on a setup command
+ * @param cmd - pointer to instruction to be filled in.
+ * @param setup - pointer to the setup structure
+ * @param q_no - which queue for back pressure
+ *
+ * Assumes the cmd instruction is pre-allocated, but no fields are filled in.
+ */
+static inline void
+octnet_prepare_pci_cmd(struct octeon_instr_64B *cmd,
+		       union octnic_cmd_setup *setup, u32 tag)
+{
+	struct octeon_instr_ih *ih;
+	struct octeon_instr_irh *irh;
+	union octnic_packet_params packet_params;
+
+	memset(cmd, 0, sizeof(struct octeon_instr_64B));
+
+	ih = (struct octeon_instr_ih *)&cmd->ih;
+
+	/* assume that rflag is cleared so therefore front data will only have
+	 * irh and ossp[1] and ossp[2] for a total of 24 bytes
+	 */
+	ih->fsz = 24;
+
+	ih->tagtype = ORDERED_TAG;
+	ih->grp = DEFAULT_POW_GRP;
+
+	if (tag)
+		ih->tag = tag;
+	else
+		ih->tag = LIO_DATA(setup->s.ifidx);
+
+	ih->raw = 1;
+	ih->qos = (setup->s.ifidx & 3) + 4;	/* map qos based on interface */
+
+	if (!setup->s.gather) {
+		ih->dlengsz = setup->s.u.datasize;
+	} else {
+		ih->gather = 1;
+		ih->dlengsz = setup->s.u.gatherptrs;
+	}
+
+	irh = (struct octeon_instr_irh *)&cmd->irh;
+
+	irh->opcode = OPCODE_NIC;
+	irh->subcode = OPCODE_NIC_NW_DATA;
+
+	packet_params.u32 = 0;
+
+	if (setup->s.cksum_offset) {
+		packet_params.s.csoffset = setup->s.cksum_offset;
+		packet_params.s.ipv4opts_ipv6exthdr =
+						setup->s.ipv4opts_ipv6exthdr;
+	}
+
+	packet_params.s.ip_csum = setup->s.ip_csum;
+	packet_params.s.tnl_csum = setup->s.tnl_csum;
+	packet_params.s.ifidx = setup->s.ifidx;
+	packet_params.s.tsflag = setup->s.timestamp;
+
+	irh->ossp = packet_params.u32;
+}
+
+/** Allocate and a soft command with space for a response immediately following
+ * the commnad.
+ * @param oct - octeon device pointer
+ * @param cmd - pointer to the command structure, pre-filled for everything
+ * except the response.
+ * @param rdatasize - size in bytes of the response.
+ *
+ * @returns pointer to allocated buffer with command copied into it, and
+ * response space immediately following.
+ */
+void *
+octeon_alloc_soft_command_resp(struct octeon_device    *oct,
+			       struct octeon_instr_64B *cmd,
+			       size_t		       rdatasize);
+
+/** Send a NIC data packet to the device
+ * @param oct - octeon device pointer
+ * @param ndata - control structure with queueing, and buffer information
+ *
+ * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
+ * queue should be stopped, and IQ_SEND_OK if it sent okay.
+ */
+int octnet_send_nic_data_pkt(struct octeon_device *oct,
+			     struct octnic_data_pkt *ndata, u32 xmit_more);
+
+/** Send a NIC control packet to the device
+ * @param oct - octeon device pointer
+ * @param nctrl - control structure with command, timout, and callback info
+ * @param nparams - response control structure
+ *
+ * @returns IQ_FAILED if it failed to add to the input queue. IQ_STOP if it the
+ * queue should be stopped, and IQ_SEND_OK if it sent okay.
+ */
+int
+octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
+			 struct octnic_ctrl_pkt *nctrl,
+			 struct octnic_ctrl_params nparams);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
new file mode 100644
index 000000000000..356796bf9b87
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -0,0 +1,766 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include <linux/vmalloc.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+
+#define INCR_INSTRQUEUE_PKT_COUNT(octeon_dev_ptr, iq_no, field, count)  \
+	(octeon_dev_ptr->instr_queue[iq_no]->stats.field += count)
+
+struct iq_post_status {
+	int status;
+	int index;
+};
+
+static void check_db_timeout(struct work_struct *work);
+static void  __check_db_timeout(struct octeon_device *oct, unsigned long iq_no);
+
+static void (*reqtype_free_fn[MAX_OCTEON_DEVICES][REQTYPE_LAST + 1]) (void *);
+
+static inline int IQ_INSTR_MODE_64B(struct octeon_device *oct, int iq_no)
+{
+	struct octeon_instr_queue *iq =
+	    (struct octeon_instr_queue *)oct->instr_queue[iq_no];
+	return iq->iqcmd_64B;
+}
+
+#define IQ_INSTR_MODE_32B(oct, iq_no)  (!IQ_INSTR_MODE_64B(oct, iq_no))
+
+/* Define this to return the request status comaptible to old code */
+/*#define OCTEON_USE_OLD_REQ_STATUS*/
+
+/* Return 0 on success, 1 on failure */
+int octeon_init_instr_queue(struct octeon_device *oct,
+			    u32 iq_no, u32 num_descs)
+{
+	struct octeon_instr_queue *iq;
+	struct octeon_iq_config *conf = NULL;
+	u32 q_size;
+	struct cavium_wq *db_wq;
+
+	if (OCTEON_CN6XXX(oct))
+		conf = &(CFG_GET_IQ_CFG(CHIP_FIELD(oct, cn6xxx, conf)));
+
+	if (!conf) {
+		dev_err(&oct->pci_dev->dev, "Unsupported Chip %x\n",
+			oct->chip_id);
+		return 1;
+	}
+
+	if (num_descs & (num_descs - 1)) {
+		dev_err(&oct->pci_dev->dev,
+			"Number of descriptors for instr queue %d not in power of 2.\n",
+			iq_no);
+		return 1;
+	}
+
+	q_size = (u32)conf->instr_type * num_descs;
+
+	iq = oct->instr_queue[iq_no];
+
+	iq->base_addr = lio_dma_alloc(oct, q_size,
+				      (dma_addr_t *)&iq->base_addr_dma);
+	if (!iq->base_addr) {
+		dev_err(&oct->pci_dev->dev, "Cannot allocate memory for instr queue %d\n",
+			iq_no);
+		return 1;
+	}
+
+	iq->max_count = num_descs;
+
+	/* Initialize a list to holds requests that have been posted to Octeon
+	 * but has yet to be fetched by octeon
+	 */
+	iq->request_list = vmalloc(sizeof(*iq->request_list) * num_descs);
+	if (!iq->request_list) {
+		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
+		dev_err(&oct->pci_dev->dev, "Alloc failed for IQ[%d] nr free list\n",
+			iq_no);
+		return 1;
+	}
+
+	memset(iq->request_list, 0, sizeof(*iq->request_list) * num_descs);
+
+	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
+		iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
+
+	iq->iq_no = iq_no;
+	iq->fill_threshold = (u32)conf->db_min;
+	iq->fill_cnt = 0;
+	iq->host_write_index = 0;
+	iq->octeon_read_index = 0;
+	iq->flush_index = 0;
+	iq->last_db_time = 0;
+	iq->do_auto_flush = 1;
+	iq->db_timeout = (u32)conf->db_timeout;
+	atomic_set(&iq->instr_pending, 0);
+
+	/* Initialize the spinlock for this instruction queue */
+	spin_lock_init(&iq->lock);
+
+	oct->io_qmask.iq |= (1 << iq_no);
+
+	/* Set the 32B/64B mode for each input queue */
+	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
+	iq->iqcmd_64B = (conf->instr_type == 64);
+
+	oct->fn_list.setup_iq_regs(oct, iq_no);
+
+	oct->check_db_wq[iq_no].wq = create_workqueue("check_iq_db");
+	if (!oct->check_db_wq[iq_no].wq) {
+		lio_dma_free(oct, q_size, iq->base_addr, iq->base_addr_dma);
+		dev_err(&oct->pci_dev->dev, "check db wq create failed for iq %d\n",
+			iq_no);
+		return 1;
+	}
+
+	db_wq = &oct->check_db_wq[iq_no];
+
+	INIT_DELAYED_WORK(&db_wq->wk.work, check_db_timeout);
+	db_wq->wk.ctxptr = oct;
+	db_wq->wk.ctxul = iq_no;
+	queue_delayed_work(db_wq->wq, &db_wq->wk.work, msecs_to_jiffies(1));
+
+	return 0;
+}
+
+int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no)
+{
+	u64 desc_size = 0, q_size;
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
+
+	cancel_delayed_work_sync(&oct->check_db_wq[iq_no].wk.work);
+	flush_workqueue(oct->check_db_wq[iq_no].wq);
+	destroy_workqueue(oct->check_db_wq[iq_no].wq);
+
+	if (OCTEON_CN6XXX(oct))
+		desc_size =
+		    CFG_GET_IQ_INSTR_TYPE(CHIP_FIELD(oct, cn6xxx, conf));
+
+	if (iq->request_list)
+		vfree(iq->request_list);
+
+	if (iq->base_addr) {
+		q_size = iq->max_count * desc_size;
+		lio_dma_free(oct, (u32)q_size, iq->base_addr,
+			     iq->base_addr_dma);
+		return 0;
+	}
+	return 1;
+}
+
+/* Return 0 on success, 1 on failure */
+int octeon_setup_iq(struct octeon_device *oct,
+		    u32 iq_no,
+		    u32 num_descs,
+		    void *app_ctx)
+{
+	if (oct->instr_queue[iq_no]) {
+		dev_dbg(&oct->pci_dev->dev, "IQ is in use. Cannot create the IQ: %d again\n",
+			iq_no);
+		oct->instr_queue[iq_no]->app_ctx = app_ctx;
+		return 0;
+	}
+	oct->instr_queue[iq_no] =
+	    vmalloc(sizeof(struct octeon_instr_queue));
+	if (!oct->instr_queue[iq_no])
+		return 1;
+
+	memset(oct->instr_queue[iq_no], 0,
+	       sizeof(struct octeon_instr_queue));
+
+	oct->instr_queue[iq_no]->app_ctx = app_ctx;
+	if (octeon_init_instr_queue(oct, iq_no, num_descs)) {
+		vfree(oct->instr_queue[iq_no]);
+		oct->instr_queue[iq_no] = NULL;
+		return 1;
+	}
+
+	oct->num_iqs++;
+	oct->fn_list.enable_io_queues(oct);
+	return 0;
+}
+
+int lio_wait_for_instr_fetch(struct octeon_device *oct)
+{
+	int i, retry = 1000, pending, instr_cnt = 0;
+
+	do {
+		instr_cnt = 0;
+
+		/*for (i = 0; i < oct->num_iqs; i++) {*/
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES; i++) {
+			if (!(oct->io_qmask.iq & (1UL << i)))
+				continue;
+			pending =
+			    atomic_read(&oct->
+					       instr_queue[i]->instr_pending);
+			if (pending)
+				__check_db_timeout(oct, i);
+			instr_cnt += pending;
+		}
+
+		if (instr_cnt == 0)
+			break;
+
+		schedule_timeout_uninterruptible(1);
+
+	} while (retry-- && instr_cnt);
+
+	return instr_cnt;
+}
+
+static inline void
+ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq)
+{
+	if (atomic_read(&oct->status) == OCT_DEV_RUNNING) {
+		writel(iq->fill_cnt, iq->doorbell_reg);
+		/* make sure doorbell write goes through */
+		mmiowb();
+		iq->fill_cnt = 0;
+		iq->last_db_time = jiffies;
+		return;
+	}
+}
+
+static inline void __copy_cmd_into_iq(struct octeon_instr_queue *iq,
+				      u8 *cmd)
+{
+	u8 *iqptr, cmdsize;
+
+	cmdsize = ((iq->iqcmd_64B) ? 64 : 32);
+	iqptr = iq->base_addr + (cmdsize * iq->host_write_index);
+
+	memcpy(iqptr, cmd, cmdsize);
+}
+
+static inline int
+__post_command(struct octeon_device *octeon_dev __attribute__((unused)),
+	       struct octeon_instr_queue *iq,
+	       u32 force_db __attribute__((unused)), u8 *cmd)
+{
+	u32 index = -1;
+
+	/* This ensures that the read index does not wrap around to the same
+	 * position if queue gets full before Octeon could fetch any instr.
+	 */
+	if (atomic_read(&iq->instr_pending) >= (s32)(iq->max_count - 1))
+		return -1;
+
+	__copy_cmd_into_iq(iq, cmd);
+
+	/* "index" is returned, host_write_index is modified. */
+	index = iq->host_write_index;
+	INCR_INDEX_BY1(iq->host_write_index, iq->max_count);
+	iq->fill_cnt++;
+
+	/* Flush the command into memory. We need to be sure the data is in
+	 * memory before indicating that the instruction is pending.
+	 */
+	wmb();
+
+	atomic_inc(&iq->instr_pending);
+
+	return index;
+}
+
+static inline struct iq_post_status
+__post_command2(struct octeon_device *octeon_dev __attribute__((unused)),
+		struct octeon_instr_queue *iq,
+		u32 force_db __attribute__((unused)), u8 *cmd)
+{
+	struct iq_post_status st;
+
+	st.status = IQ_SEND_OK;
+
+	/* This ensures that the read index does not wrap around to the same
+	 * position if queue gets full before Octeon could fetch any instr.
+	 */
+	if (atomic_read(&iq->instr_pending) >= (s32)(iq->max_count - 1)) {
+		st.status = IQ_SEND_FAILED;
+		st.index = -1;
+		return st;
+	}
+
+	if (atomic_read(&iq->instr_pending) >= (s32)(iq->max_count - 2))
+		st.status = IQ_SEND_STOP;
+
+	__copy_cmd_into_iq(iq, cmd);
+
+	/* "index" is returned, host_write_index is modified. */
+	st.index = iq->host_write_index;
+	INCR_INDEX_BY1(iq->host_write_index, iq->max_count);
+	iq->fill_cnt++;
+
+	/* Flush the command into memory. We need to be sure the data is in
+	 * memory before indicating that the instruction is pending.
+	 */
+	wmb();
+
+	atomic_inc(&iq->instr_pending);
+
+	return st;
+}
+
+int
+octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype,
+				void (*fn)(void *))
+{
+	if (reqtype > REQTYPE_LAST) {
+		dev_err(&oct->pci_dev->dev, "%s: Invalid reqtype: %d\n",
+			__func__, reqtype);
+		return -EINVAL;
+	}
+
+	reqtype_free_fn[oct->octeon_id][reqtype] = fn;
+
+	return 0;
+}
+
+static inline void
+__add_to_request_list(struct octeon_instr_queue *iq,
+		      int idx, void *buf, int reqtype)
+{
+	iq->request_list[idx].buf = buf;
+	iq->request_list[idx].reqtype = reqtype;
+}
+
+int
+lio_process_iq_request_list(struct octeon_device *oct,
+			    struct octeon_instr_queue *iq)
+{
+	int reqtype;
+	void *buf;
+	u32 old = iq->flush_index;
+	u32 inst_count = 0;
+	unsigned pkts_compl = 0, bytes_compl = 0;
+	struct octeon_soft_command *sc;
+	struct octeon_instr_irh *irh;
+
+	while (old != iq->octeon_read_index) {
+		reqtype = iq->request_list[old].reqtype;
+		buf     = iq->request_list[old].buf;
+
+		if (reqtype == REQTYPE_NONE)
+			goto skip_this;
+
+		octeon_update_tx_completion_counters(buf, reqtype, &pkts_compl,
+						     &bytes_compl);
+
+		switch (reqtype) {
+		case REQTYPE_NORESP_NET:
+		case REQTYPE_NORESP_NET_SG:
+		case REQTYPE_RESP_NET_SG:
+			reqtype_free_fn[oct->octeon_id][reqtype](buf);
+			break;
+		case REQTYPE_RESP_NET:
+		case REQTYPE_SOFT_COMMAND:
+			sc = buf;
+
+			irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+			if (irh->rflag) {
+				/* We're expecting a response from Octeon.
+				 * It's up to lio_process_ordered_list() to
+				 * process  sc. Add sc to the ordered soft
+				 * command response list because we expect
+				 * a response from Octeon.
+				 */
+				spin_lock_bh(&oct->response_list
+					[OCTEON_ORDERED_SC_LIST].lock);
+				atomic_inc(&oct->response_list
+					[OCTEON_ORDERED_SC_LIST].
+					pending_req_count);
+				list_add_tail(&sc->node, &oct->response_list
+					[OCTEON_ORDERED_SC_LIST].head);
+				spin_unlock_bh(&oct->response_list
+					[OCTEON_ORDERED_SC_LIST].lock);
+			} else {
+				if (sc->callback) {
+					sc->callback(oct, OCTEON_REQUEST_DONE,
+						     sc->callback_arg);
+				}
+			}
+			break;
+		default:
+			dev_err(&oct->pci_dev->dev,
+				"%s Unknown reqtype: %d buf: %p at idx %d\n",
+				__func__, reqtype, buf, old);
+		}
+
+		iq->request_list[old].buf = NULL;
+		iq->request_list[old].reqtype = 0;
+
+ skip_this:
+		inst_count++;
+		INCR_INDEX_BY1(old, iq->max_count);
+	}
+	if (bytes_compl)
+		octeon_report_tx_completion_to_bql(iq->app_ctx, pkts_compl,
+						   bytes_compl);
+	iq->flush_index = old;
+
+	return inst_count;
+}
+
+static inline void
+update_iq_indices(struct octeon_device *oct, struct octeon_instr_queue *iq)
+{
+	u32 inst_processed = 0;
+
+	/* Calculate how many commands Octeon has read and move the read index
+	 * accordingly.
+	 */
+	iq->octeon_read_index = oct->fn_list.update_iq_read_idx(oct, iq);
+
+	/* Move the NORESPONSE requests to the per-device completion list. */
+	if (iq->flush_index != iq->octeon_read_index)
+		inst_processed = lio_process_iq_request_list(oct, iq);
+
+	if (inst_processed) {
+		atomic_sub(inst_processed, &iq->instr_pending);
+		iq->stats.instr_processed += inst_processed;
+	}
+}
+
+static void
+octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq,
+		u32 pending_thresh)
+{
+	if (atomic_read(&iq->instr_pending) >= (s32)pending_thresh) {
+		spin_lock_bh(&iq->lock);
+		update_iq_indices(oct, iq);
+		spin_unlock_bh(&iq->lock);
+	}
+}
+
+static void __check_db_timeout(struct octeon_device *oct, unsigned long iq_no)
+{
+	struct octeon_instr_queue *iq;
+	u64 next_time;
+
+	if (!oct)
+		return;
+	iq = oct->instr_queue[iq_no];
+	if (!iq)
+		return;
+
+	/* If jiffies - last_db_time < db_timeout do nothing  */
+	next_time = iq->last_db_time + iq->db_timeout;
+	if (!time_after(jiffies, (unsigned long)next_time))
+		return;
+	iq->last_db_time = jiffies;
+
+	/* Get the lock and prevent tasklets. This routine gets called from
+	 * the poll thread. Instructions can now be posted in tasklet context
+	 */
+	spin_lock_bh(&iq->lock);
+	if (iq->fill_cnt != 0)
+		ring_doorbell(oct, iq);
+
+	spin_unlock_bh(&iq->lock);
+
+	/* Flush the instruction queue */
+	if (iq->do_auto_flush)
+		octeon_flush_iq(oct, iq, 1);
+}
+
+/* Called by the Poll thread at regular intervals to check the instruction
+ * queue for commands to be posted and for commands that were fetched by Octeon.
+ */
+static void check_db_timeout(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct octeon_device *oct = (struct octeon_device *)wk->ctxptr;
+	unsigned long iq_no = wk->ctxul;
+	struct cavium_wq *db_wq = &oct->check_db_wq[iq_no];
+
+	__check_db_timeout(oct, iq_no);
+	queue_delayed_work(db_wq->wq, &db_wq->wk.work, msecs_to_jiffies(1));
+}
+
+int
+octeon_send_command(struct octeon_device *oct, u32 iq_no,
+		    u32 force_db, void *cmd, void *buf,
+		    u32 datasize, u32 reqtype)
+{
+	struct iq_post_status st;
+	struct octeon_instr_queue *iq = oct->instr_queue[iq_no];
+
+	spin_lock_bh(&iq->lock);
+
+	st = __post_command2(oct, iq, force_db, cmd);
+
+	if (st.status != IQ_SEND_FAILED) {
+		octeon_report_sent_bytes_to_bql(buf, reqtype);
+		__add_to_request_list(iq, st.index, buf, reqtype);
+		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, bytes_sent, datasize);
+		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_posted, 1);
+
+		if (iq->fill_cnt >= iq->fill_threshold || force_db)
+			ring_doorbell(oct, iq);
+	} else {
+		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
+	}
+
+	spin_unlock_bh(&iq->lock);
+
+	if (iq->do_auto_flush)
+		octeon_flush_iq(oct, iq, 2);
+
+	return st.status;
+}
+
+void
+octeon_prepare_soft_command(struct octeon_device *oct,
+			    struct octeon_soft_command *sc,
+			    u8 opcode,
+			    u8 subcode,
+			    u32 irh_ossp,
+			    u64 ossp0,
+			    u64 ossp1)
+{
+	struct octeon_config *oct_cfg;
+	struct octeon_instr_ih *ih;
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_rdp *rdp;
+
+	BUG_ON(opcode > 15);
+	BUG_ON(subcode > 127);
+
+	oct_cfg = octeon_get_conf(oct);
+
+	ih          = (struct octeon_instr_ih *)&sc->cmd.ih;
+	ih->tagtype = ATOMIC_TAG;
+	ih->tag     = LIO_CONTROL;
+	ih->raw     = 1;
+	ih->grp     = CFG_GET_CTRL_Q_GRP(oct_cfg);
+
+	if (sc->datasize) {
+		ih->dlengsz = sc->datasize;
+		ih->rs = 1;
+	}
+
+	irh            = (struct octeon_instr_irh *)&sc->cmd.irh;
+	irh->opcode    = opcode;
+	irh->subcode   = subcode;
+
+	/* opcode/subcode specific parameters (ossp) */
+	irh->ossp       = irh_ossp;
+	sc->cmd.ossp[0] = ossp0;
+	sc->cmd.ossp[1] = ossp1;
+
+	if (sc->rdatasize) {
+		rdp            = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+		rdp->pcie_port = oct->pcie_port;
+		rdp->rlen      = sc->rdatasize;
+
+		irh->rflag =  1;
+		irh->len   =  4;
+		ih->fsz    = 40; /* irh+ossp[0]+ossp[1]+rdp+rptr = 40 bytes */
+	} else {
+		irh->rflag =  0;
+		irh->len   =  2;
+		ih->fsz    = 24; /* irh + ossp[0] + ossp[1] = 24 bytes */
+	}
+
+	while (!(oct->io_qmask.iq & (1 << sc->iq_no)))
+		sc->iq_no++;
+}
+
+int octeon_send_soft_command(struct octeon_device *oct,
+			     struct octeon_soft_command *sc)
+{
+	struct octeon_instr_ih *ih;
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_rdp *rdp;
+
+	ih = (struct octeon_instr_ih *)&sc->cmd.ih;
+	if (ih->dlengsz) {
+		BUG_ON(!sc->dmadptr);
+		sc->cmd.dptr = sc->dmadptr;
+	}
+
+	irh = (struct octeon_instr_irh *)&sc->cmd.irh;
+	if (irh->rflag) {
+		BUG_ON(!sc->dmarptr);
+		BUG_ON(!sc->status_word);
+		*sc->status_word = COMPLETION_WORD_INIT;
+
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+
+		sc->cmd.rptr = sc->dmarptr;
+	}
+
+	if (sc->wait_time)
+		sc->timeout = jiffies + sc->wait_time;
+
+	return octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
+				   (u32)ih->dlengsz, REQTYPE_SOFT_COMMAND);
+}
+
+int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
+{
+	int i;
+	u64 dma_addr;
+	struct octeon_soft_command *sc;
+
+	INIT_LIST_HEAD(&oct->sc_buf_pool.head);
+	spin_lock_init(&oct->sc_buf_pool.lock);
+	atomic_set(&oct->sc_buf_pool.alloc_buf_count, 0);
+
+	for (i = 0; i < MAX_SOFT_COMMAND_BUFFERS; i++) {
+		sc = (struct octeon_soft_command *)
+			lio_dma_alloc(oct,
+				      SOFT_COMMAND_BUFFER_SIZE,
+					  (dma_addr_t *)&dma_addr);
+		if (!sc)
+			return 1;
+
+		sc->dma_addr = dma_addr;
+		sc->size = SOFT_COMMAND_BUFFER_SIZE;
+
+		list_add_tail(&sc->node, &oct->sc_buf_pool.head);
+	}
+
+	return 0;
+}
+
+int octeon_free_sc_buffer_pool(struct octeon_device *oct)
+{
+	struct list_head *tmp, *tmp2;
+	struct octeon_soft_command *sc;
+
+	spin_lock(&oct->sc_buf_pool.lock);
+
+	list_for_each_safe(tmp, tmp2, &oct->sc_buf_pool.head) {
+		list_del(tmp);
+
+		sc = (struct octeon_soft_command *)tmp;
+
+		lio_dma_free(oct, sc->size, sc, sc->dma_addr);
+	}
+
+	INIT_LIST_HEAD(&oct->sc_buf_pool.head);
+
+	spin_unlock(&oct->sc_buf_pool.lock);
+
+	return 0;
+}
+
+struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
+						      u32 datasize,
+						      u32 rdatasize,
+						      u32 ctxsize)
+{
+	u64 dma_addr;
+	u32 size;
+	u32 offset = sizeof(struct octeon_soft_command);
+	struct octeon_soft_command *sc = NULL;
+	struct list_head *tmp;
+
+	BUG_ON((offset + datasize + rdatasize + ctxsize) >
+	       SOFT_COMMAND_BUFFER_SIZE);
+
+	spin_lock(&oct->sc_buf_pool.lock);
+
+	if (list_empty(&oct->sc_buf_pool.head)) {
+		spin_unlock(&oct->sc_buf_pool.lock);
+		return NULL;
+	}
+
+	list_for_each(tmp, &oct->sc_buf_pool.head)
+		break;
+
+	list_del(tmp);
+
+	atomic_inc(&oct->sc_buf_pool.alloc_buf_count);
+
+	spin_unlock(&oct->sc_buf_pool.lock);
+
+	sc = (struct octeon_soft_command *)tmp;
+
+	dma_addr = sc->dma_addr;
+	size = sc->size;
+
+	memset(sc, 0, sc->size);
+
+	sc->dma_addr = dma_addr;
+	sc->size = size;
+
+	if (ctxsize) {
+		sc->ctxptr = (u8 *)sc + offset;
+		sc->ctxsize = ctxsize;
+	}
+
+	/* Start data at 128 byte boundary */
+	offset = (offset + ctxsize + 127) & 0xffffff80;
+
+	if (datasize) {
+		sc->virtdptr = (u8 *)sc + offset;
+		sc->dmadptr = dma_addr + offset;
+		sc->datasize = datasize;
+	}
+
+	/* Start rdata at 128 byte boundary */
+	offset = (offset + datasize + 127) & 0xffffff80;
+
+	if (rdatasize) {
+		BUG_ON(rdatasize < 16);
+		sc->virtrptr = (u8 *)sc + offset;
+		sc->dmarptr = dma_addr + offset;
+		sc->rdatasize = rdatasize;
+		sc->status_word = (u64 *)((u8 *)(sc->virtrptr) + rdatasize - 8);
+	}
+
+	return sc;
+}
+
+void octeon_free_soft_command(struct octeon_device *oct,
+			      struct octeon_soft_command *sc)
+{
+	spin_lock(&oct->sc_buf_pool.lock);
+
+	list_add_tail(&sc->node, &oct->sc_buf_pool.head);
+
+	atomic_dec(&oct->sc_buf_pool.alloc_buf_count);
+
+	spin_unlock(&oct->sc_buf_pool.lock);
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
new file mode 100644
index 000000000000..091f537a946e
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -0,0 +1,178 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+#include <linux/version.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/pci.h>
+#include <linux/kthread.h>
+#include <linux/netdevice.h>
+#include "octeon_config.h"
+#include "liquidio_common.h"
+#include "octeon_droq.h"
+#include "octeon_iq.h"
+#include "response_manager.h"
+#include "octeon_device.h"
+#include "octeon_nic.h"
+#include "octeon_main.h"
+#include "octeon_network.h"
+#include "cn66xx_regs.h"
+#include "cn66xx_device.h"
+#include "cn68xx_regs.h"
+#include "cn68xx_device.h"
+#include "liquidio_image.h"
+
+static void oct_poll_req_completion(struct work_struct *work);
+
+int octeon_setup_response_list(struct octeon_device *oct)
+{
+	int i, ret = 0;
+	struct cavium_wq *cwq;
+
+	for (i = 0; i < MAX_RESPONSE_LISTS; i++) {
+		INIT_LIST_HEAD(&oct->response_list[i].head);
+		spin_lock_init(&oct->response_list[i].lock);
+		atomic_set(&oct->response_list[i].pending_req_count, 0);
+	}
+
+	oct->dma_comp_wq.wq = create_workqueue("dma-comp");
+	if (!oct->dma_comp_wq.wq) {
+		dev_err(&oct->pci_dev->dev, "failed to create wq thread\n");
+		return -ENOMEM;
+	}
+
+	cwq = &oct->dma_comp_wq;
+	INIT_DELAYED_WORK(&cwq->wk.work, oct_poll_req_completion);
+	cwq->wk.ctxptr = oct;
+	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(100));
+
+	return ret;
+}
+
+void octeon_delete_response_list(struct octeon_device *oct)
+{
+	cancel_delayed_work_sync(&oct->dma_comp_wq.wk.work);
+	flush_workqueue(oct->dma_comp_wq.wq);
+	destroy_workqueue(oct->dma_comp_wq.wq);
+}
+
+int lio_process_ordered_list(struct octeon_device *octeon_dev,
+			     u32 force_quit)
+{
+	struct octeon_response_list *ordered_sc_list;
+	struct octeon_soft_command *sc;
+	int request_complete = 0;
+	int resp_to_process = MAX_ORD_REQS_TO_PROCESS;
+	u32 status;
+	u64 status64;
+	struct octeon_instr_rdp *rdp;
+
+	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
+
+	do {
+		spin_lock_bh(&ordered_sc_list->lock);
+
+		if (ordered_sc_list->head.next == &ordered_sc_list->head) {
+			/* ordered_sc_list is empty; there is
+			 * nothing to process
+			 */
+			spin_unlock_bh
+			    (&ordered_sc_list->lock);
+			return 1;
+		}
+
+		sc = (struct octeon_soft_command *)ordered_sc_list->
+		    head.next;
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.rdp;
+
+		status = OCTEON_REQUEST_PENDING;
+
+		/* check if octeon has finished DMA'ing a response
+		 * to where rptr is pointing to
+		 */
+		dma_sync_single_for_cpu(&octeon_dev->pci_dev->dev,
+					sc->cmd.rptr, rdp->rlen,
+					DMA_FROM_DEVICE);
+		status64 = *sc->status_word;
+
+		if (status64 != COMPLETION_WORD_INIT) {
+			if ((status64 & 0xff) != 0xff) {
+				octeon_swap_8B_data(&status64, 1);
+				if (((status64 & 0xff) != 0xff)) {
+					status = (u32)(status64 &
+						       0xffffffffULL);
+				}
+			}
+		} else if (force_quit || (sc->timeout &&
+			time_after(jiffies, (unsigned long)sc->timeout))) {
+			status = OCTEON_REQUEST_TIMEOUT;
+		}
+
+		if (status != OCTEON_REQUEST_PENDING) {
+			/* we have received a response or we have timed out */
+			/* remove node from linked list */
+			list_del(&sc->node);
+			atomic_dec(&octeon_dev->response_list
+					  [OCTEON_ORDERED_SC_LIST].
+					  pending_req_count);
+			spin_unlock_bh
+			    (&ordered_sc_list->lock);
+
+			if (sc->callback)
+				sc->callback(octeon_dev, status,
+					     sc->callback_arg);
+
+			request_complete++;
+
+		} else {
+			/* no response yet */
+			request_complete = 0;
+			spin_unlock_bh
+			    (&ordered_sc_list->lock);
+		}
+
+		/* If we hit the Max Ordered requests to process every loop,
+		 * we quit
+		 * and let this function be invoked the next time the poll
+		 * thread runs
+		 * to process the remaining requests. This function can take up
+		 * the entire CPU if there is no upper limit to the requests
+		 * processed.
+		 */
+		if (request_complete >= resp_to_process)
+			break;
+	} while (request_complete);
+
+	return 0;
+}
+
+static void oct_poll_req_completion(struct work_struct *work)
+{
+	struct cavium_wk *wk = (struct cavium_wk *)work;
+	struct octeon_device *oct = (struct octeon_device *)wk->ctxptr;
+	struct cavium_wq *cwq = &oct->dma_comp_wq;
+
+	lio_process_ordered_list(oct, 0);
+
+	queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(100));
+}
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
new file mode 100644
index 000000000000..7a48752dcb10
--- /dev/null
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -0,0 +1,140 @@
+/**********************************************************************
+ * Author: Cavium, Inc.
+ *
+ * Contact: support@cavium.com
+ *          Please include "LiquidIO" in the subject.
+ *
+ * Copyright (c) 2003-2015 Cavium, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium, Inc. for more information
+ **********************************************************************/
+
+/*! \file response_manager.h
+ *  \brief Host Driver:  Response queues for host instructions.
+ */
+
+#ifndef __RESPONSE_MANAGER_H__
+#define __RESPONSE_MANAGER_H__
+
+/** Maximum ordered requests to process in every invocation of
+ * lio_process_ordered_list(). The function will continue to process requests
+ * as long as it can find one that has finished processing. If it keeps
+ * finding requests that have completed, the function can run for ever. The
+ * value defined here sets an upper limit on the number of requests it can
+ * process before it returns control to the poll thread.
+ */
+#define  MAX_ORD_REQS_TO_PROCESS   4096
+
+/** Head of a response list. There are several response lists in the
+ *  system. One for each response order- Unordered, ordered
+ *  and 1 for noresponse entries on each instruction queue.
+ */
+struct octeon_response_list {
+	/** List structure to add delete pending entries to */
+	struct list_head head;
+
+	/** A lock for this response list */
+	spinlock_t lock;
+
+	atomic_t pending_req_count;
+};
+
+/** The type of response list.
+ */
+enum {
+	OCTEON_ORDERED_LIST = 0,
+	OCTEON_UNORDERED_NONBLOCKING_LIST = 1,
+	OCTEON_UNORDERED_BLOCKING_LIST = 2,
+	OCTEON_ORDERED_SC_LIST = 3
+};
+
+/** Response Order values for a Octeon Request. */
+enum {
+	OCTEON_RESP_ORDERED = 0,
+	OCTEON_RESP_UNORDERED = 1,
+	OCTEON_RESP_NORESPONSE = 2
+};
+
+/** Error codes  used in Octeon Host-Core communication.
+ *
+ *   31            16 15            0
+ *   ---------------------------------
+ *   |               |               |
+ *   ---------------------------------
+ *   Error codes are 32-bit wide. The upper 16-bits, called Major Error Number,
+ *   are reserved to identify the group to which the error code belongs. The
+ *   lower 16-bits, called Minor Error Number, carry the actual code.
+ *
+ *   So error codes are (MAJOR NUMBER << 16)| MINOR_NUMBER.
+ */
+
+/*------------   Error codes used by host driver   -----------------*/
+#define DRIVER_MAJOR_ERROR_CODE           0x0000
+
+/**  A value of 0x00000000 indicates no error i.e. success */
+#define DRIVER_ERROR_NONE                 0x00000000
+
+/**  (Major number: 0x0000; Minor Number: 0x0001) */
+#define DRIVER_ERROR_REQ_PENDING          0x00000001
+#define DRIVER_ERROR_REQ_TIMEOUT          0x00000003
+#define DRIVER_ERROR_REQ_EINTR            0x00000004
+#define DRIVER_ERROR_REQ_ENXIO            0x00000006
+#define DRIVER_ERROR_REQ_ENOMEM           0x0000000C
+#define DRIVER_ERROR_REQ_EINVAL           0x00000016
+#define DRIVER_ERROR_REQ_FAILED           0x000000ff
+
+/** Status for a request.
+ * If a request is not queued to Octeon by the driver, the driver returns
+ * an error condition that's describe by one of the OCTEON_REQ_ERR_* value
+ * below. If the request is successfully queued, the driver will return
+ * a OCTEON_REQUEST_PENDING status. OCTEON_REQUEST_TIMEOUT and
+ * OCTEON_REQUEST_INTERRUPTED are only returned by the driver if the
+ * response for request failed to arrive before a time-out period or if
+ * the request processing * got interrupted due to a signal respectively.
+ */
+enum {
+	OCTEON_REQUEST_DONE = (DRIVER_ERROR_NONE),
+	OCTEON_REQUEST_PENDING = (DRIVER_ERROR_REQ_PENDING),
+	OCTEON_REQUEST_TIMEOUT = (DRIVER_ERROR_REQ_TIMEOUT),
+	OCTEON_REQUEST_INTERRUPTED = (DRIVER_ERROR_REQ_EINTR),
+	OCTEON_REQUEST_NO_DEVICE = (0x00000021),
+	OCTEON_REQUEST_NOT_RUNNING,
+	OCTEON_REQUEST_INVALID_IQ,
+	OCTEON_REQUEST_INVALID_BUFCNT,
+	OCTEON_REQUEST_INVALID_RESP_ORDER,
+	OCTEON_REQUEST_NO_MEMORY,
+	OCTEON_REQUEST_INVALID_BUFSIZE,
+	OCTEON_REQUEST_NO_PENDING_ENTRY,
+	OCTEON_REQUEST_NO_IQ_SPACE = (0x7FFFFFFF)
+
+};
+
+/** Initialize the response lists. The number of response lists to create is
+ * given by count.
+ * @param octeon_dev      - the octeon device structure.
+ */
+int octeon_setup_response_list(struct octeon_device *octeon_dev);
+
+void octeon_delete_response_list(struct octeon_device *octeon_dev);
+
+/** Check the status of first entry in the ordered list. If the instruction at
+ * that entry finished processing or has timed-out, the entry is cleaned.
+ * @param octeon_dev  - the octeon device structure.
+ * @param force_quit - the request is forced to timeout if this is 1
+ * @return 1 if the ordered list is empty, 0 otherwise.
+ */
+int lio_process_ordered_list(struct octeon_device *octeon_dev,
+			     u32 force_quit);
+
+#endif
diff --git a/drivers/net/ethernet/cavium/thunder/Makefile b/drivers/net/ethernet/cavium/thunder/Makefile
new file mode 100644
index 000000000000..5c4615ccaa14
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for Cavium's Thunder ethernet device
+#
+
+obj-$(CONFIG_THUNDER_NIC_BGX) += thunder_bgx.o
+obj-$(CONFIG_THUNDER_NIC_PF) += nicpf.o
+obj-$(CONFIG_THUNDER_NIC_VF) += nicvf.o
+
+nicpf-y := nic_main.o
+nicvf-y := nicvf_main.o nicvf_queues.o
+nicvf-y += nicvf_ethtool.o
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
new file mode 100644
index 000000000000..dda8a02b7322
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -0,0 +1,423 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef NIC_H
+#define	NIC_H
+
+#include <linux/netdevice.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include "thunder_bgx.h"
+
+/* PCI device IDs */
+#define	PCI_DEVICE_ID_THUNDER_NIC_PF		0xA01E
+#define	PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF	0x0011
+#define	PCI_DEVICE_ID_THUNDER_NIC_VF		0xA034
+#define	PCI_DEVICE_ID_THUNDER_BGX		0xA026
+
+/* PCI BAR nos */
+#define	PCI_CFG_REG_BAR_NUM		0
+#define	PCI_MSIX_REG_BAR_NUM		4
+
+/* NIC SRIOV VF count */
+#define	MAX_NUM_VFS_SUPPORTED		128
+#define	DEFAULT_NUM_VF_ENABLED		8
+
+#define	NIC_TNS_BYPASS_MODE		0
+#define	NIC_TNS_MODE			1
+
+/* NIC priv flags */
+#define	NIC_SRIOV_ENABLED		BIT(0)
+
+/* Min/Max packet size */
+#define	NIC_HW_MIN_FRS			64
+#define	NIC_HW_MAX_FRS			9200 /* 9216 max packet including FCS */
+
+/* Max pkinds */
+#define	NIC_MAX_PKIND			16
+
+/* Rx Channels */
+/* Receive channel configuration in TNS bypass mode
+ * Below is configuration in TNS bypass mode
+ * BGX0-LMAC0-CHAN0 - VNIC CHAN0
+ * BGX0-LMAC1-CHAN0 - VNIC CHAN16
+ * ...
+ * BGX1-LMAC0-CHAN0 - VNIC CHAN128
+ * ...
+ * BGX1-LMAC3-CHAN0 - VNIC CHAN174
+ */
+#define	NIC_INTF_COUNT			2  /* Interfaces btw VNIC and TNS/BGX */
+#define	NIC_CHANS_PER_INF		128
+#define	NIC_MAX_CHANS			(NIC_INTF_COUNT * NIC_CHANS_PER_INF)
+#define	NIC_CPI_COUNT			2048 /* No of channel parse indices */
+
+/* TNS bypass mode: 1-1 mapping between VNIC and BGX:LMAC */
+#define NIC_MAX_BGX			MAX_BGX_PER_CN88XX
+#define	NIC_CPI_PER_BGX			(NIC_CPI_COUNT / NIC_MAX_BGX)
+#define	NIC_MAX_CPI_PER_LMAC		64 /* Max when CPI_ALG is IP diffserv */
+#define	NIC_RSSI_PER_BGX		(NIC_RSSI_COUNT / NIC_MAX_BGX)
+
+/* Tx scheduling */
+#define	NIC_MAX_TL4			1024
+#define	NIC_MAX_TL4_SHAPERS		256 /* 1 shaper for 4 TL4s */
+#define	NIC_MAX_TL3			256
+#define	NIC_MAX_TL3_SHAPERS		64  /* 1 shaper for 4 TL3s */
+#define	NIC_MAX_TL2			64
+#define	NIC_MAX_TL2_SHAPERS		2  /* 1 shaper for 32 TL2s */
+#define	NIC_MAX_TL1			2
+
+/* TNS bypass mode */
+#define	NIC_TL2_PER_BGX			32
+#define	NIC_TL4_PER_BGX			(NIC_MAX_TL4 / NIC_MAX_BGX)
+#define	NIC_TL4_PER_LMAC		(NIC_MAX_TL4 / NIC_CHANS_PER_INF)
+
+/* NIC VF Interrupts */
+#define	NICVF_INTR_CQ			0
+#define	NICVF_INTR_SQ			1
+#define	NICVF_INTR_RBDR			2
+#define	NICVF_INTR_PKT_DROP		3
+#define	NICVF_INTR_TCP_TIMER		4
+#define	NICVF_INTR_MBOX			5
+#define	NICVF_INTR_QS_ERR		6
+
+#define	NICVF_INTR_CQ_SHIFT		0
+#define	NICVF_INTR_SQ_SHIFT		8
+#define	NICVF_INTR_RBDR_SHIFT		16
+#define	NICVF_INTR_PKT_DROP_SHIFT	20
+#define	NICVF_INTR_TCP_TIMER_SHIFT	21
+#define	NICVF_INTR_MBOX_SHIFT		22
+#define	NICVF_INTR_QS_ERR_SHIFT		23
+
+#define	NICVF_INTR_CQ_MASK		(0xFF << NICVF_INTR_CQ_SHIFT)
+#define	NICVF_INTR_SQ_MASK		(0xFF << NICVF_INTR_SQ_SHIFT)
+#define	NICVF_INTR_RBDR_MASK		(0x03 << NICVF_INTR_RBDR_SHIFT)
+#define	NICVF_INTR_PKT_DROP_MASK	BIT(NICVF_INTR_PKT_DROP_SHIFT)
+#define	NICVF_INTR_TCP_TIMER_MASK	BIT(NICVF_INTR_TCP_TIMER_SHIFT)
+#define	NICVF_INTR_MBOX_MASK		BIT(NICVF_INTR_MBOX_SHIFT)
+#define	NICVF_INTR_QS_ERR_MASK		BIT(NICVF_INTR_QS_ERR_SHIFT)
+
+/* MSI-X interrupts */
+#define	NIC_PF_MSIX_VECTORS		10
+#define	NIC_VF_MSIX_VECTORS		20
+
+#define NIC_PF_INTR_ID_ECC0_SBE		0
+#define NIC_PF_INTR_ID_ECC0_DBE		1
+#define NIC_PF_INTR_ID_ECC1_SBE		2
+#define NIC_PF_INTR_ID_ECC1_DBE		3
+#define NIC_PF_INTR_ID_ECC2_SBE		4
+#define NIC_PF_INTR_ID_ECC2_DBE		5
+#define NIC_PF_INTR_ID_ECC3_SBE		6
+#define NIC_PF_INTR_ID_ECC3_DBE		7
+#define NIC_PF_INTR_ID_MBOX0		8
+#define NIC_PF_INTR_ID_MBOX1		9
+
+/* Global timer for CQ timer thresh interrupts
+ * Calculated for SCLK of 700Mhz
+ * value written should be a 1/16th of what is expected
+ *
+ * 1 tick per 0.05usec = value of 2.2
+ * This 10% would be covered in CQ timer thresh value
+ */
+#define NICPF_CLK_PER_INT_TICK		2
+
+struct nicvf_cq_poll {
+	u8	cq_idx;		/* Completion queue index */
+	struct	napi_struct napi;
+};
+
+#define	NIC_RSSI_COUNT			4096 /* Total no of RSS indices */
+#define NIC_MAX_RSS_HASH_BITS		8
+#define NIC_MAX_RSS_IDR_TBL_SIZE	(1 << NIC_MAX_RSS_HASH_BITS)
+#define RSS_HASH_KEY_SIZE		5 /* 320 bit key */
+
+struct nicvf_rss_info {
+	bool enable;
+#define	RSS_L2_EXTENDED_HASH_ENA	BIT(0)
+#define	RSS_IP_HASH_ENA			BIT(1)
+#define	RSS_TCP_HASH_ENA		BIT(2)
+#define	RSS_TCP_SYN_DIS			BIT(3)
+#define	RSS_UDP_HASH_ENA		BIT(4)
+#define RSS_L4_EXTENDED_HASH_ENA	BIT(5)
+#define	RSS_ROCE_ENA			BIT(6)
+#define	RSS_L3_BI_DIRECTION_ENA		BIT(7)
+#define	RSS_L4_BI_DIRECTION_ENA		BIT(8)
+	u64 cfg;
+	u8  hash_bits;
+	u16 rss_size;
+	u8  ind_tbl[NIC_MAX_RSS_IDR_TBL_SIZE];
+	u64 key[RSS_HASH_KEY_SIZE];
+} ____cacheline_aligned_in_smp;
+
+enum rx_stats_reg_offset {
+	RX_OCTS = 0x0,
+	RX_UCAST = 0x1,
+	RX_BCAST = 0x2,
+	RX_MCAST = 0x3,
+	RX_RED = 0x4,
+	RX_RED_OCTS = 0x5,
+	RX_ORUN = 0x6,
+	RX_ORUN_OCTS = 0x7,
+	RX_FCS = 0x8,
+	RX_L2ERR = 0x9,
+	RX_DRP_BCAST = 0xa,
+	RX_DRP_MCAST = 0xb,
+	RX_DRP_L3BCAST = 0xc,
+	RX_DRP_L3MCAST = 0xd,
+	RX_STATS_ENUM_LAST,
+};
+
+enum tx_stats_reg_offset {
+	TX_OCTS = 0x0,
+	TX_UCAST = 0x1,
+	TX_BCAST = 0x2,
+	TX_MCAST = 0x3,
+	TX_DROP = 0x4,
+	TX_STATS_ENUM_LAST,
+};
+
+struct nicvf_hw_stats {
+	u64 rx_bytes_ok;
+	u64 rx_ucast_frames_ok;
+	u64 rx_bcast_frames_ok;
+	u64 rx_mcast_frames_ok;
+	u64 rx_fcs_errors;
+	u64 rx_l2_errors;
+	u64 rx_drop_red;
+	u64 rx_drop_red_bytes;
+	u64 rx_drop_overrun;
+	u64 rx_drop_overrun_bytes;
+	u64 rx_drop_bcast;
+	u64 rx_drop_mcast;
+	u64 rx_drop_l3_bcast;
+	u64 rx_drop_l3_mcast;
+	u64 tx_bytes_ok;
+	u64 tx_ucast_frames_ok;
+	u64 tx_bcast_frames_ok;
+	u64 tx_mcast_frames_ok;
+	u64 tx_drops;
+};
+
+struct nicvf_drv_stats {
+	/* Rx */
+	u64 rx_frames_ok;
+	u64 rx_frames_64;
+	u64 rx_frames_127;
+	u64 rx_frames_255;
+	u64 rx_frames_511;
+	u64 rx_frames_1023;
+	u64 rx_frames_1518;
+	u64 rx_frames_jumbo;
+	u64 rx_drops;
+	/* Tx */
+	u64 tx_frames_ok;
+	u64 tx_drops;
+	u64 tx_busy;
+	u64 tx_tso;
+};
+
+struct nicvf {
+	struct net_device	*netdev;
+	struct pci_dev		*pdev;
+	u8			vf_id;
+	u8			node;
+	u8			tns_mode;
+	u16			mtu;
+	struct queue_set	*qs;
+	void __iomem		*reg_base;
+	bool			link_up;
+	u8			duplex;
+	u32			speed;
+	struct page		*rb_page;
+	u32			rb_page_offset;
+	bool			rb_alloc_fail;
+	bool			rb_work_scheduled;
+	struct delayed_work	rbdr_work;
+	struct tasklet_struct	rbdr_task;
+	struct tasklet_struct	qs_err_task;
+	struct tasklet_struct	cq_task;
+	struct nicvf_cq_poll	*napi[8];
+	struct nicvf_rss_info	rss_info;
+	u8			cpi_alg;
+	/* Interrupt coalescing settings */
+	u32			cq_coalesce_usecs;
+
+	u32			msg_enable;
+	struct nicvf_hw_stats   stats;
+	struct nicvf_drv_stats  drv_stats;
+	struct bgx_stats	bgx_stats;
+	struct work_struct	reset_task;
+
+	/* MSI-X  */
+	bool			msix_enabled;
+	u8			num_vec;
+	struct msix_entry	msix_entries[NIC_VF_MSIX_VECTORS];
+	char			irq_name[NIC_VF_MSIX_VECTORS][20];
+	bool			irq_allocated[NIC_VF_MSIX_VECTORS];
+
+	bool			pf_ready_to_rcv_msg;
+	bool			pf_acked;
+	bool			pf_nacked;
+	bool			bgx_stats_acked;
+	bool			set_mac_pending;
+} ____cacheline_aligned_in_smp;
+
+/* PF <--> VF Mailbox communication
+ * Eight 64bit registers are shared between PF and VF.
+ * Separate set for each VF.
+ * Writing '1' into last register mbx7 means end of message.
+ */
+
+/* PF <--> VF mailbox communication */
+#define	NIC_PF_VF_MAILBOX_SIZE		2
+#define	NIC_MBOX_MSG_TIMEOUT		2000 /* ms */
+
+/* Mailbox message types */
+#define	NIC_MBOX_MSG_READY		0x01	/* Is PF ready to rcv msgs */
+#define	NIC_MBOX_MSG_ACK		0x02	/* ACK the message received */
+#define	NIC_MBOX_MSG_NACK		0x03	/* NACK the message received */
+#define	NIC_MBOX_MSG_QS_CFG		0x04	/* Configure Qset */
+#define	NIC_MBOX_MSG_RQ_CFG		0x05	/* Configure receive queue */
+#define	NIC_MBOX_MSG_SQ_CFG		0x06	/* Configure Send queue */
+#define	NIC_MBOX_MSG_RQ_DROP_CFG	0x07	/* Configure receive queue */
+#define	NIC_MBOX_MSG_SET_MAC		0x08	/* Add MAC ID to DMAC filter */
+#define	NIC_MBOX_MSG_SET_MAX_FRS	0x09	/* Set max frame size */
+#define	NIC_MBOX_MSG_CPI_CFG		0x0A	/* Config CPI, RSSI */
+#define	NIC_MBOX_MSG_RSS_SIZE		0x0B	/* Get RSS indir_tbl size */
+#define	NIC_MBOX_MSG_RSS_CFG		0x0C	/* Config RSS table */
+#define	NIC_MBOX_MSG_RSS_CFG_CONT	0x0D	/* RSS config continuation */
+#define	NIC_MBOX_MSG_RQ_BP_CFG		0x0E	/* RQ backpressure config */
+#define	NIC_MBOX_MSG_RQ_SW_SYNC		0x0F	/* Flush inflight pkts to RQ */
+#define	NIC_MBOX_MSG_BGX_STATS		0x10	/* Get stats from BGX */
+#define	NIC_MBOX_MSG_BGX_LINK_CHANGE	0x11	/* BGX:LMAC link status */
+#define NIC_MBOX_MSG_CFG_DONE		0x12	/* VF configuration done */
+#define NIC_MBOX_MSG_SHUTDOWN		0x13	/* VF is being shutdown */
+
+struct nic_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    tns_mode;
+	u8    node_id;
+	u8    mac_addr[ETH_ALEN];
+};
+
+/* Qset configuration */
+struct qs_cfg_msg {
+	u8    msg;
+	u8    num;
+	u64   cfg;
+};
+
+/* Receive queue configuration */
+struct rq_cfg_msg {
+	u8    msg;
+	u8    qs_num;
+	u8    rq_num;
+	u64   cfg;
+};
+
+/* Send queue configuration */
+struct sq_cfg_msg {
+	u8    msg;
+	u8    qs_num;
+	u8    sq_num;
+	u64   cfg;
+};
+
+/* Set VF's MAC address */
+struct set_mac_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    mac_addr[ETH_ALEN];
+};
+
+/* Set Maximum frame size */
+struct set_frs_msg {
+	u8    msg;
+	u8    vf_id;
+	u16   max_frs;
+};
+
+/* Set CPI algorithm type */
+struct cpi_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    rq_cnt;
+	u8    cpi_alg;
+};
+
+/* Get RSS table size */
+struct rss_sz_msg {
+	u8    msg;
+	u8    vf_id;
+	u16   ind_tbl_size;
+};
+
+/* Set RSS configuration */
+struct rss_cfg_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    hash_bits;
+	u8    tbl_len;
+	u8    tbl_offset;
+#define RSS_IND_TBL_LEN_PER_MBX_MSG	8
+	u8    ind_tbl[RSS_IND_TBL_LEN_PER_MBX_MSG];
+};
+
+struct bgx_stats_msg {
+	u8    msg;
+	u8    vf_id;
+	u8    rx;
+	u8    idx;
+	u64   stats;
+};
+
+/* Physical interface link status */
+struct bgx_link_status {
+	u8    msg;
+	u8    link_up;
+	u8    duplex;
+	u32   speed;
+};
+
+/* 128 bit shared memory between PF and each VF */
+union nic_mbx {
+	struct { u8 msg; }	msg;
+	struct nic_cfg_msg	nic_cfg;
+	struct qs_cfg_msg	qs;
+	struct rq_cfg_msg	rq;
+	struct sq_cfg_msg	sq;
+	struct set_mac_msg	mac;
+	struct set_frs_msg	frs;
+	struct cpi_cfg_msg	cpi_cfg;
+	struct rss_sz_msg	rss_size;
+	struct rss_cfg_msg	rss_cfg;
+	struct bgx_stats_msg    bgx_stats;
+	struct bgx_link_status  link_status;
+};
+
+#define NIC_NODE_ID_MASK	0x03
+#define NIC_NODE_ID_SHIFT	44
+
+static inline int nic_get_node_id(struct pci_dev *pdev)
+{
+	u64 addr = pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM);
+	return ((addr >> NIC_NODE_ID_SHIFT) & NIC_NODE_ID_MASK);
+}
+
+int nicvf_set_real_num_queues(struct net_device *netdev,
+			      int tx_queues, int rx_queues);
+int nicvf_open(struct net_device *netdev);
+int nicvf_stop(struct net_device *netdev);
+int nicvf_send_msg_to_pf(struct nicvf *vf, union nic_mbx *mbx);
+void nicvf_config_rss(struct nicvf *nic);
+void nicvf_set_rss_key(struct nicvf *nic);
+void nicvf_set_ethtool_ops(struct net_device *netdev);
+void nicvf_update_stats(struct nicvf *nic);
+void nicvf_update_lmac_stats(struct nicvf *nic);
+
+#endif /* NIC_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
new file mode 100644
index 000000000000..6e0c03169a55
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -0,0 +1,932 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/etherdevice.h>
+#include <linux/of.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "q_struct.h"
+#include "thunder_bgx.h"
+
+#define DRV_NAME	"thunder-nic"
+#define DRV_VERSION	"1.0"
+
+struct nicpf {
+	struct pci_dev		*pdev;
+	u8			rev_id;
+	u8			node;
+	unsigned int		flags;
+	u8			num_vf_en;      /* No of VF enabled */
+	bool			vf_enabled[MAX_NUM_VFS_SUPPORTED];
+	void __iomem		*reg_base;       /* Register start address */
+	struct pkind_cfg	pkind;
+#define	NIC_SET_VF_LMAC_MAP(bgx, lmac)	(((bgx & 0xF) << 4) | (lmac & 0xF))
+#define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
+#define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
+	u8			vf_lmac_map[MAX_LMAC];
+	struct delayed_work     dwork;
+	struct workqueue_struct *check_link;
+	u8			link[MAX_LMAC];
+	u8			duplex[MAX_LMAC];
+	u32			speed[MAX_LMAC];
+	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
+	u16			rss_ind_tbl_size;
+	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
+
+	/* MSI-X */
+	bool			msix_enabled;
+	u8			num_vec;
+	struct msix_entry	msix_entries[NIC_PF_MSIX_VECTORS];
+	bool			irq_allocated[NIC_PF_MSIX_VECTORS];
+};
+
+/* Supported devices */
+static const struct pci_device_id nic_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) },
+	{ 0, }  /* end of table */
+};
+
+MODULE_AUTHOR("Sunil Goutham");
+MODULE_DESCRIPTION("Cavium Thunder NIC Physical Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DEVICE_TABLE(pci, nic_id_table);
+
+/* The Cavium ThunderX network controller can *only* be found in SoCs
+ * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
+ * registers on this platform are implicitly strongly ordered with respect
+ * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use
+ * with no memory barriers in this driver.  The readq()/writeq() functions add
+ * explicit ordering operation which in this case are redundant, and only
+ * add overhead.
+ */
+
+/* Register read/write APIs */
+static void nic_reg_write(struct nicpf *nic, u64 offset, u64 val)
+{
+	writeq_relaxed(val, nic->reg_base + offset);
+}
+
+static u64 nic_reg_read(struct nicpf *nic, u64 offset)
+{
+	return readq_relaxed(nic->reg_base + offset);
+}
+
+/* PF -> VF mailbox communication APIs */
+static void nic_enable_mbx_intr(struct nicpf *nic)
+{
+	/* Enable mailbox interrupt for all 128 VFs */
+	nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S, ~0ull);
+	nic_reg_write(nic, NIC_PF_MAILBOX_ENA_W1S + sizeof(u64), ~0ull);
+}
+
+static void nic_clear_mbx_intr(struct nicpf *nic, int vf, int mbx_reg)
+{
+	nic_reg_write(nic, NIC_PF_MAILBOX_INT + (mbx_reg << 3), BIT_ULL(vf));
+}
+
+static u64 nic_get_mbx_addr(int vf)
+{
+	return NIC_PF_VF_0_127_MAILBOX_0_1 + (vf << NIC_VF_NUM_SHIFT);
+}
+
+/* Send a mailbox message to VF
+ * @vf: vf to which this message to be sent
+ * @mbx: Message to be sent
+ */
+static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx)
+{
+	void __iomem *mbx_addr = nic->reg_base + nic_get_mbx_addr(vf);
+	u64 *msg = (u64 *)mbx;
+
+	/* In first revision HW, mbox interrupt is triggerred
+	 * when PF writes to MBOX(1), in next revisions when
+	 * PF writes to MBOX(0)
+	 */
+	if (nic->rev_id == 0) {
+		/* see the comment for nic_reg_write()/nic_reg_read()
+		 * functions above
+		 */
+		writeq_relaxed(msg[0], mbx_addr);
+		writeq_relaxed(msg[1], mbx_addr + 8);
+	} else {
+		writeq_relaxed(msg[1], mbx_addr + 8);
+		writeq_relaxed(msg[0], mbx_addr);
+	}
+}
+
+/* Responds to VF's READY message with VF's
+ * ID, node, MAC address e.t.c
+ * @vf: VF which sent READY message
+ */
+static void nic_mbx_send_ready(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+	int bgx_idx, lmac;
+	const char *mac;
+
+	mbx.nic_cfg.msg = NIC_MBOX_MSG_READY;
+	mbx.nic_cfg.vf_id = vf;
+
+	mbx.nic_cfg.tns_mode = NIC_TNS_BYPASS_MODE;
+
+	bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+	mac = bgx_get_lmac_mac(nic->node, bgx_idx, lmac);
+	if (mac)
+		ether_addr_copy((u8 *)&mbx.nic_cfg.mac_addr, mac);
+
+	mbx.nic_cfg.node_id = nic->node;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* ACKs VF's mailbox message
+ * @vf: VF to which ACK to be sent
+ */
+static void nic_mbx_send_ack(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_ACK;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* NACKs VF's mailbox message that PF is not able to
+ * complete the action
+ * @vf: VF to which ACK to be sent
+ */
+static void nic_mbx_send_nack(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_NACK;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* Flush all in flight receive packets to memory and
+ * bring down an active RQ
+ */
+static int nic_rcv_queue_sw_sync(struct nicpf *nic)
+{
+	u16 timeout = ~0x00;
+
+	nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x01);
+	/* Wait till sync cycle is finished */
+	while (timeout) {
+		if (nic_reg_read(nic, NIC_PF_SW_SYNC_RX_DONE) & 0x1)
+			break;
+		timeout--;
+	}
+	nic_reg_write(nic, NIC_PF_SW_SYNC_RX, 0x00);
+	if (!timeout) {
+		dev_err(&nic->pdev->dev, "Receive queue software sync failed");
+		return 1;
+	}
+	return 0;
+}
+
+/* Get BGX Rx/Tx stats and respond to VF's request */
+static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx)
+{
+	int bgx_idx, lmac;
+	union nic_mbx mbx = {};
+
+	bgx_idx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[bgx->vf_id]);
+
+	mbx.bgx_stats.msg = NIC_MBOX_MSG_BGX_STATS;
+	mbx.bgx_stats.vf_id = bgx->vf_id;
+	mbx.bgx_stats.rx = bgx->rx;
+	mbx.bgx_stats.idx = bgx->idx;
+	if (bgx->rx)
+		mbx.bgx_stats.stats = bgx_get_rx_stats(nic->node, bgx_idx,
+							    lmac, bgx->idx);
+	else
+		mbx.bgx_stats.stats = bgx_get_tx_stats(nic->node, bgx_idx,
+							    lmac, bgx->idx);
+	nic_send_msg_to_vf(nic, bgx->vf_id, &mbx);
+}
+
+/* Update hardware min/max frame size */
+static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf)
+{
+	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) {
+		dev_err(&nic->pdev->dev,
+			"Invalid MTU setting from VF%d rejected, should be between %d and %d\n",
+			   vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS);
+		return 1;
+	}
+	new_frs += ETH_HLEN;
+	if (new_frs <= nic->pkind.maxlen)
+		return 0;
+
+	nic->pkind.maxlen = new_frs;
+	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind);
+	return 0;
+}
+
+/* Set minimum transmit packet size */
+static void nic_set_tx_pkt_pad(struct nicpf *nic, int size)
+{
+	int lmac;
+	u64 lmac_cfg;
+
+	/* Max value that can be set is 60 */
+	if (size > 60)
+		size = 60;
+
+	for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) {
+		lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3));
+		lmac_cfg &= ~(0xF << 2);
+		lmac_cfg |= ((size / 4) << 2);
+		nic_reg_write(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3), lmac_cfg);
+	}
+}
+
+/* Function to check number of LMACs present and set VF::LMAC mapping.
+ * Mapping will be used while initializing channels.
+ */
+static void nic_set_lmac_vf_mapping(struct nicpf *nic)
+{
+	unsigned bgx_map = bgx_get_map(nic->node);
+	int bgx, next_bgx_lmac = 0;
+	int lmac, lmac_cnt = 0;
+	u64 lmac_credit;
+
+	nic->num_vf_en = 0;
+
+	for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) {
+		if (!(bgx_map & (1 << bgx)))
+			continue;
+		lmac_cnt = bgx_get_lmac_count(nic->node, bgx);
+		for (lmac = 0; lmac < lmac_cnt; lmac++)
+			nic->vf_lmac_map[next_bgx_lmac++] =
+						NIC_SET_VF_LMAC_MAP(bgx, lmac);
+		nic->num_vf_en += lmac_cnt;
+
+		/* Program LMAC credits */
+		lmac_credit = (1ull << 1); /* channel credit enable */
+		lmac_credit |= (0x1ff << 2); /* Max outstanding pkt count */
+		/* 48KB BGX Tx buffer size, each unit is of size 16bytes */
+		lmac_credit |= (((((48 * 1024) / lmac_cnt) -
+				NIC_HW_MAX_FRS) / 16) << 12);
+		lmac = bgx * MAX_LMAC_PER_BGX;
+		for (; lmac < lmac_cnt + (bgx * MAX_LMAC_PER_BGX); lmac++)
+			nic_reg_write(nic,
+				      NIC_PF_LMAC_0_7_CREDIT + (lmac * 8),
+				      lmac_credit);
+	}
+}
+
+#define BGX0_BLOCK 8
+#define BGX1_BLOCK 9
+
+static void nic_init_hw(struct nicpf *nic)
+{
+	int i;
+
+	/* Reset NIC, in case the driver is repeatedly inserted and removed */
+	nic_reg_write(nic, NIC_PF_SOFT_RESET, 1);
+
+	/* Enable NIC HW block */
+	nic_reg_write(nic, NIC_PF_CFG, 0x3);
+
+	/* Enable backpressure */
+	nic_reg_write(nic, NIC_PF_BP_CFG, (1ULL << 6) | 0x03);
+
+	/* Disable TNS mode on both interfaces */
+	nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG,
+		      (NIC_TNS_BYPASS_MODE << 7) | BGX0_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_SEND_CFG | (1 << 8),
+		      (NIC_TNS_BYPASS_MODE << 7) | BGX1_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG,
+		      (1ULL << 63) | BGX0_BLOCK);
+	nic_reg_write(nic, NIC_PF_INTF_0_1_BP_CFG + (1 << 8),
+		      (1ULL << 63) | BGX1_BLOCK);
+
+	/* PKIND configuration */
+	nic->pkind.minlen = 0;
+	nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN;
+	nic->pkind.lenerr_en = 1;
+	nic->pkind.rx_hdr = 0;
+	nic->pkind.hdr_sl = 0;
+
+	for (i = 0; i < NIC_MAX_PKIND; i++)
+		nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (i << 3),
+			      *(u64 *)&nic->pkind);
+
+	nic_set_tx_pkt_pad(nic, NIC_HW_MIN_FRS);
+
+	/* Timer config */
+	nic_reg_write(nic, NIC_PF_INTR_TIMER_CFG, NICPF_CLK_PER_INT_TICK);
+}
+
+/* Channel parse index configuration */
+static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg)
+{
+	u32 vnic, bgx, lmac, chan;
+	u32 padd, cpi_count = 0;
+	u64 cpi_base, cpi, rssi_base, rssi;
+	u8  qset, rq_idx = 0;
+
+	vnic = cfg->vf_id;
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+
+	chan = (lmac * MAX_BGX_CHANS_PER_LMAC) + (bgx * NIC_CHANS_PER_INF);
+	cpi_base = (lmac * NIC_MAX_CPI_PER_LMAC) + (bgx * NIC_CPI_PER_BGX);
+	rssi_base = (lmac * nic->rss_ind_tbl_size) + (bgx * NIC_RSSI_PER_BGX);
+
+	/* Rx channel configuration */
+	nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_BP_CFG | (chan << 3),
+		      (1ull << 63) | (vnic << 0));
+	nic_reg_write(nic, NIC_PF_CHAN_0_255_RX_CFG | (chan << 3),
+		      ((u64)cfg->cpi_alg << 62) | (cpi_base << 48));
+
+	if (cfg->cpi_alg == CPI_ALG_NONE)
+		cpi_count = 1;
+	else if (cfg->cpi_alg == CPI_ALG_VLAN) /* 3 bits of PCP */
+		cpi_count = 8;
+	else if (cfg->cpi_alg == CPI_ALG_VLAN16) /* 3 bits PCP + DEI */
+		cpi_count = 16;
+	else if (cfg->cpi_alg == CPI_ALG_DIFF) /* 6bits DSCP */
+		cpi_count = NIC_MAX_CPI_PER_LMAC;
+
+	/* RSS Qset, Qidx mapping */
+	qset = cfg->vf_id;
+	rssi = rssi_base;
+	for (; rssi < (rssi_base + cfg->rq_cnt); rssi++) {
+		nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3),
+			      (qset << 3) | rq_idx);
+		rq_idx++;
+	}
+
+	rssi = 0;
+	cpi = cpi_base;
+	for (; cpi < (cpi_base + cpi_count); cpi++) {
+		/* Determine port to channel adder */
+		if (cfg->cpi_alg != CPI_ALG_DIFF)
+			padd = cpi % cpi_count;
+		else
+			padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */
+
+		/* Leave RSS_SIZE as '0' to disable RSS */
+		nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3),
+			      (vnic << 24) | (padd << 16) | (rssi_base + rssi));
+
+		if ((rssi + 1) >= cfg->rq_cnt)
+			continue;
+
+		if (cfg->cpi_alg == CPI_ALG_VLAN)
+			rssi++;
+		else if (cfg->cpi_alg == CPI_ALG_VLAN16)
+			rssi = ((cpi - cpi_base) & 0xe) >> 1;
+		else if (cfg->cpi_alg == CPI_ALG_DIFF)
+			rssi = ((cpi - cpi_base) & 0x38) >> 3;
+	}
+	nic->cpi_base[cfg->vf_id] = cpi_base;
+}
+
+/* Responsds to VF with its RSS indirection table size */
+static void nic_send_rss_size(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+	u64  *msg;
+
+	msg = (u64 *)&mbx;
+
+	mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE;
+	mbx.rss_size.ind_tbl_size = nic->rss_ind_tbl_size;
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
+/* Receive side scaling configuration
+ * configure:
+ * - RSS index
+ * - indir table i.e hash::RQ mapping
+ * - no of hash bits to consider
+ */
+static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg)
+{
+	u8  qset, idx = 0;
+	u64 cpi_cfg, cpi_base, rssi_base, rssi;
+
+	cpi_base = nic->cpi_base[cfg->vf_id];
+	cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3));
+	rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset;
+
+	rssi = rssi_base;
+	qset = cfg->vf_id;
+
+	for (; rssi < (rssi_base + cfg->tbl_len); rssi++) {
+		nic_reg_write(nic, NIC_PF_RSSI_0_4097_RQ | (rssi << 3),
+			      (qset << 3) | (cfg->ind_tbl[idx] & 0x7));
+		idx++;
+	}
+
+	cpi_cfg &= ~(0xFULL << 20);
+	cpi_cfg |= (cfg->hash_bits << 20);
+	nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg);
+}
+
+/* 4 level transmit side scheduler configutation
+ * for TNS bypass mode
+ *
+ * Sample configuration for SQ0
+ * VNIC0-SQ0 -> TL4(0)   -> TL3[0]   -> TL2[0]  -> TL1[0] -> BGX0
+ * VNIC1-SQ0 -> TL4(8)   -> TL3[2]   -> TL2[0]  -> TL1[0] -> BGX0
+ * VNIC2-SQ0 -> TL4(16)  -> TL3[4]   -> TL2[1]  -> TL1[0] -> BGX0
+ * VNIC3-SQ0 -> TL4(24)  -> TL3[6]   -> TL2[1]  -> TL1[0] -> BGX0
+ * VNIC4-SQ0 -> TL4(512) -> TL3[128] -> TL2[32] -> TL1[1] -> BGX1
+ * VNIC5-SQ0 -> TL4(520) -> TL3[130] -> TL2[32] -> TL1[1] -> BGX1
+ * VNIC6-SQ0 -> TL4(528) -> TL3[132] -> TL2[33] -> TL1[1] -> BGX1
+ * VNIC7-SQ0 -> TL4(536) -> TL3[134] -> TL2[33] -> TL1[1] -> BGX1
+ */
+static void nic_tx_channel_cfg(struct nicpf *nic, u8 vnic, u8 sq_idx)
+{
+	u32 bgx, lmac, chan;
+	u32 tl2, tl3, tl4;
+	u32 rr_quantum;
+
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vnic]);
+	/* 24 bytes for FCS, IPG and preamble */
+	rr_quantum = ((NIC_HW_MAX_FRS + 24) / 4);
+
+	tl4 = (lmac * NIC_TL4_PER_LMAC) + (bgx * NIC_TL4_PER_BGX);
+	tl4 += sq_idx;
+	tl3 = tl4 / (NIC_MAX_TL4 / NIC_MAX_TL3);
+	nic_reg_write(nic, NIC_PF_QSET_0_127_SQ_0_7_CFG2 |
+		      ((u64)vnic << NIC_QS_ID_SHIFT) |
+		      ((u32)sq_idx << NIC_Q_NUM_SHIFT), tl4);
+	nic_reg_write(nic, NIC_PF_TL4_0_1023_CFG | (tl4 << 3),
+		      ((u64)vnic << 27) | ((u32)sq_idx << 24) | rr_quantum);
+
+	nic_reg_write(nic, NIC_PF_TL3_0_255_CFG | (tl3 << 3), rr_quantum);
+	chan = (lmac * MAX_BGX_CHANS_PER_LMAC) + (bgx * NIC_CHANS_PER_INF);
+	nic_reg_write(nic, NIC_PF_TL3_0_255_CHAN | (tl3 << 3), chan);
+	/* Enable backpressure on the channel */
+	nic_reg_write(nic, NIC_PF_CHAN_0_255_TX_CFG | (chan << 3), 1);
+
+	tl2 = tl3 >> 2;
+	nic_reg_write(nic, NIC_PF_TL3A_0_63_CFG | (tl2 << 3), tl2);
+	nic_reg_write(nic, NIC_PF_TL2_0_63_CFG | (tl2 << 3), rr_quantum);
+	/* No priorities as of now */
+	nic_reg_write(nic, NIC_PF_TL2_0_63_PRI | (tl2 << 3), 0x00);
+}
+
+/* Interrupt handler to handle mailbox messages from VFs */
+static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
+{
+	union nic_mbx mbx = {};
+	u64 *mbx_data;
+	u64 mbx_addr;
+	u64 reg_addr;
+	int bgx, lmac;
+	int i;
+	int ret = 0;
+
+	nic->mbx_lock[vf] = true;
+
+	mbx_addr = nic_get_mbx_addr(vf);
+	mbx_data = (u64 *)&mbx;
+
+	for (i = 0; i < NIC_PF_VF_MAILBOX_SIZE; i++) {
+		*mbx_data = nic_reg_read(nic, mbx_addr);
+		mbx_data++;
+		mbx_addr += sizeof(u64);
+	}
+
+	dev_dbg(&nic->pdev->dev, "%s: Mailbox msg %d from VF%d\n",
+		__func__, mbx.msg.msg, vf);
+	switch (mbx.msg.msg) {
+	case NIC_MBOX_MSG_READY:
+		nic_mbx_send_ready(nic, vf);
+		nic->link[vf] = 0;
+		nic->duplex[vf] = 0;
+		nic->speed[vf] = 0;
+		ret = 1;
+		break;
+	case NIC_MBOX_MSG_QS_CFG:
+		reg_addr = NIC_PF_QSET_0_127_CFG |
+			   (mbx.qs.num << NIC_QS_ID_SHIFT);
+		nic_reg_write(nic, reg_addr, mbx.qs.cfg);
+		break;
+	case NIC_MBOX_MSG_RQ_CFG:
+		reg_addr = NIC_PF_QSET_0_127_RQ_0_7_CFG |
+			   (mbx.rq.qs_num << NIC_QS_ID_SHIFT) |
+			   (mbx.rq.rq_num << NIC_Q_NUM_SHIFT);
+		nic_reg_write(nic, reg_addr, mbx.rq.cfg);
+		break;
+	case NIC_MBOX_MSG_RQ_BP_CFG:
+		reg_addr = NIC_PF_QSET_0_127_RQ_0_7_BP_CFG |
+			   (mbx.rq.qs_num << NIC_QS_ID_SHIFT) |
+			   (mbx.rq.rq_num << NIC_Q_NUM_SHIFT);
+		nic_reg_write(nic, reg_addr, mbx.rq.cfg);
+		break;
+	case NIC_MBOX_MSG_RQ_SW_SYNC:
+		ret = nic_rcv_queue_sw_sync(nic);
+		break;
+	case NIC_MBOX_MSG_RQ_DROP_CFG:
+		reg_addr = NIC_PF_QSET_0_127_RQ_0_7_DROP_CFG |
+			   (mbx.rq.qs_num << NIC_QS_ID_SHIFT) |
+			   (mbx.rq.rq_num << NIC_Q_NUM_SHIFT);
+		nic_reg_write(nic, reg_addr, mbx.rq.cfg);
+		break;
+	case NIC_MBOX_MSG_SQ_CFG:
+		reg_addr = NIC_PF_QSET_0_127_SQ_0_7_CFG |
+			   (mbx.sq.qs_num << NIC_QS_ID_SHIFT) |
+			   (mbx.sq.sq_num << NIC_Q_NUM_SHIFT);
+		nic_reg_write(nic, reg_addr, mbx.sq.cfg);
+		nic_tx_channel_cfg(nic, mbx.qs.num, mbx.sq.sq_num);
+		break;
+	case NIC_MBOX_MSG_SET_MAC:
+		lmac = mbx.mac.vf_id;
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[lmac]);
+		bgx_set_lmac_mac(nic->node, bgx, lmac, mbx.mac.mac_addr);
+		break;
+	case NIC_MBOX_MSG_SET_MAX_FRS:
+		ret = nic_update_hw_frs(nic, mbx.frs.max_frs,
+					mbx.frs.vf_id);
+		break;
+	case NIC_MBOX_MSG_CPI_CFG:
+		nic_config_cpi(nic, &mbx.cpi_cfg);
+		break;
+	case NIC_MBOX_MSG_RSS_SIZE:
+		nic_send_rss_size(nic, vf);
+		goto unlock;
+	case NIC_MBOX_MSG_RSS_CFG:
+	case NIC_MBOX_MSG_RSS_CFG_CONT:
+		nic_config_rss(nic, &mbx.rss_cfg);
+		break;
+	case NIC_MBOX_MSG_CFG_DONE:
+		/* Last message of VF config msg sequence */
+		nic->vf_enabled[vf] = true;
+		goto unlock;
+	case NIC_MBOX_MSG_SHUTDOWN:
+		/* First msg in VF teardown sequence */
+		nic->vf_enabled[vf] = false;
+		break;
+	case NIC_MBOX_MSG_BGX_STATS:
+		nic_get_bgx_stats(nic, &mbx.bgx_stats);
+		goto unlock;
+	default:
+		dev_err(&nic->pdev->dev,
+			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
+		break;
+	}
+
+	if (!ret)
+		nic_mbx_send_ack(nic, vf);
+	else if (mbx.msg.msg != NIC_MBOX_MSG_READY)
+		nic_mbx_send_nack(nic, vf);
+unlock:
+	nic->mbx_lock[vf] = false;
+}
+
+static void nic_mbx_intr_handler (struct nicpf *nic, int mbx)
+{
+	u64 intr;
+	u8  vf, vf_per_mbx_reg = 64;
+
+	intr = nic_reg_read(nic, NIC_PF_MAILBOX_INT + (mbx << 3));
+	dev_dbg(&nic->pdev->dev, "PF interrupt Mbox%d 0x%llx\n", mbx, intr);
+	for (vf = 0; vf < vf_per_mbx_reg; vf++) {
+		if (intr & (1ULL << vf)) {
+			dev_dbg(&nic->pdev->dev, "Intr from VF %d\n",
+				vf + (mbx * vf_per_mbx_reg));
+			if ((vf + (mbx * vf_per_mbx_reg)) > nic->num_vf_en)
+				break;
+			nic_handle_mbx_intr(nic, vf + (mbx * vf_per_mbx_reg));
+			nic_clear_mbx_intr(nic, vf, mbx);
+		}
+	}
+}
+
+static irqreturn_t nic_mbx0_intr_handler (int irq, void *nic_irq)
+{
+	struct nicpf *nic = (struct nicpf *)nic_irq;
+
+	nic_mbx_intr_handler(nic, 0);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nic_mbx1_intr_handler (int irq, void *nic_irq)
+{
+	struct nicpf *nic = (struct nicpf *)nic_irq;
+
+	nic_mbx_intr_handler(nic, 1);
+
+	return IRQ_HANDLED;
+}
+
+static int nic_enable_msix(struct nicpf *nic)
+{
+	int i, ret;
+
+	nic->num_vec = NIC_PF_MSIX_VECTORS;
+
+	for (i = 0; i < nic->num_vec; i++)
+		nic->msix_entries[i].entry = i;
+
+	ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec);
+	if (ret) {
+		dev_err(&nic->pdev->dev,
+			"Request for #%d msix vectors failed\n",
+			   nic->num_vec);
+		return ret;
+	}
+
+	nic->msix_enabled = 1;
+	return 0;
+}
+
+static void nic_disable_msix(struct nicpf *nic)
+{
+	if (nic->msix_enabled) {
+		pci_disable_msix(nic->pdev);
+		nic->msix_enabled = 0;
+		nic->num_vec = 0;
+	}
+}
+
+static void nic_free_all_interrupts(struct nicpf *nic)
+{
+	int irq;
+
+	for (irq = 0; irq < nic->num_vec; irq++) {
+		if (nic->irq_allocated[irq])
+			free_irq(nic->msix_entries[irq].vector, nic);
+		nic->irq_allocated[irq] = false;
+	}
+}
+
+static int nic_register_interrupts(struct nicpf *nic)
+{
+	int ret;
+
+	/* Enable MSI-X */
+	ret = nic_enable_msix(nic);
+	if (ret)
+		return ret;
+
+	/* Register mailbox interrupt handlers */
+	ret = request_irq(nic->msix_entries[NIC_PF_INTR_ID_MBOX0].vector,
+			  nic_mbx0_intr_handler, 0, "NIC Mbox0", nic);
+	if (ret)
+		goto fail;
+
+	nic->irq_allocated[NIC_PF_INTR_ID_MBOX0] = true;
+
+	ret = request_irq(nic->msix_entries[NIC_PF_INTR_ID_MBOX1].vector,
+			  nic_mbx1_intr_handler, 0, "NIC Mbox1", nic);
+	if (ret)
+		goto fail;
+
+	nic->irq_allocated[NIC_PF_INTR_ID_MBOX1] = true;
+
+	/* Enable mailbox interrupt */
+	nic_enable_mbx_intr(nic);
+	return 0;
+
+fail:
+	dev_err(&nic->pdev->dev, "Request irq failed\n");
+	nic_free_all_interrupts(nic);
+	return ret;
+}
+
+static void nic_unregister_interrupts(struct nicpf *nic)
+{
+	nic_free_all_interrupts(nic);
+	nic_disable_msix(nic);
+}
+
+static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
+{
+	int pos = 0;
+	int err;
+	u16 total_vf_cnt;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+	if (!pos) {
+		dev_err(&pdev->dev, "SRIOV capability is not found in PCIe config space\n");
+		return -ENODEV;
+	}
+
+	pci_read_config_word(pdev, (pos + PCI_SRIOV_TOTAL_VF), &total_vf_cnt);
+	if (total_vf_cnt < nic->num_vf_en)
+		nic->num_vf_en = total_vf_cnt;
+
+	if (!total_vf_cnt)
+		return 0;
+
+	err = pci_enable_sriov(pdev, nic->num_vf_en);
+	if (err) {
+		dev_err(&pdev->dev, "SRIOV enable failed, num VF is %d\n",
+			nic->num_vf_en);
+		nic->num_vf_en = 0;
+		return err;
+	}
+
+	dev_info(&pdev->dev, "SRIOV enabled, number of VF available %d\n",
+		 nic->num_vf_en);
+
+	nic->flags |= NIC_SRIOV_ENABLED;
+	return 0;
+}
+
+/* Poll for BGX LMAC link status and update corresponding VF
+ * if there is a change, valid only if internal L2 switch
+ * is not present otherwise VF link is always treated as up
+ */
+static void nic_poll_for_link(struct work_struct *work)
+{
+	union nic_mbx mbx = {};
+	struct nicpf *nic;
+	struct bgx_link_status link;
+	u8 vf, bgx, lmac;
+
+	nic = container_of(work, struct nicpf, dwork.work);
+
+	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+
+	for (vf = 0; vf < nic->num_vf_en; vf++) {
+		/* Poll only if VF is UP */
+		if (!nic->vf_enabled[vf])
+			continue;
+
+		/* Get BGX, LMAC indices for the VF */
+		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+		/* Get interface link status */
+		bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
+
+		/* Inform VF only if link status changed */
+		if (nic->link[vf] == link.link_up)
+			continue;
+
+		if (!nic->mbx_lock[vf]) {
+			nic->link[vf] = link.link_up;
+			nic->duplex[vf] = link.duplex;
+			nic->speed[vf] = link.speed;
+
+			/* Send a mbox message to VF with current link status */
+			mbx.link_status.link_up = link.link_up;
+			mbx.link_status.duplex = link.duplex;
+			mbx.link_status.speed = link.speed;
+			nic_send_msg_to_vf(nic, vf, &mbx);
+		}
+	}
+	queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2);
+}
+
+static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct nicpf *nic;
+	int    err;
+
+	BUILD_BUG_ON(sizeof(union nic_mbx) > 16);
+
+	nic = devm_kzalloc(dev, sizeof(*nic), GFP_KERNEL);
+	if (!nic)
+		return -ENOMEM;
+
+	pci_set_drvdata(pdev, nic);
+
+	nic->pdev = pdev;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		pci_set_drvdata(pdev, NULL);
+		return err;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x\n", err);
+		goto err_disable_device;
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto err_release_regions;
+	}
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get 48-bit DMA for consistent allocations\n");
+		goto err_release_regions;
+	}
+
+	/* MAP PF's configuration registers */
+	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
+	if (!nic->reg_base) {
+		dev_err(dev, "Cannot map config register space, aborting\n");
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &nic->rev_id);
+
+	nic->node = nic_get_node_id(pdev);
+
+	nic_set_lmac_vf_mapping(nic);
+
+	/* Initialize hardware */
+	nic_init_hw(nic);
+
+	/* Set RSS TBL size for each VF */
+	nic->rss_ind_tbl_size = NIC_MAX_RSS_IDR_TBL_SIZE;
+
+	/* Register interrupts */
+	err = nic_register_interrupts(nic);
+	if (err)
+		goto err_release_regions;
+
+	/* Configure SRIOV */
+	err = nic_sriov_init(pdev, nic);
+	if (err)
+		goto err_unregister_interrupts;
+
+	/* Register a physical link status poll fn() */
+	nic->check_link = alloc_workqueue("check_link_status",
+					  WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
+	if (!nic->check_link) {
+		err = -ENOMEM;
+		goto err_disable_sriov;
+	}
+
+	INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link);
+	queue_delayed_work(nic->check_link, &nic->dwork, 0);
+
+	return 0;
+
+err_disable_sriov:
+	if (nic->flags & NIC_SRIOV_ENABLED)
+		pci_disable_sriov(pdev);
+err_unregister_interrupts:
+	nic_unregister_interrupts(nic);
+err_release_regions:
+	pci_release_regions(pdev);
+err_disable_device:
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void nic_remove(struct pci_dev *pdev)
+{
+	struct nicpf *nic = pci_get_drvdata(pdev);
+
+	if (nic->flags & NIC_SRIOV_ENABLED)
+		pci_disable_sriov(pdev);
+
+	if (nic->check_link) {
+		/* Destroy work Queue */
+		cancel_delayed_work(&nic->dwork);
+		flush_workqueue(nic->check_link);
+		destroy_workqueue(nic->check_link);
+	}
+
+	nic_unregister_interrupts(nic);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static struct pci_driver nic_driver = {
+	.name = DRV_NAME,
+	.id_table = nic_id_table,
+	.probe = nic_probe,
+	.remove = nic_remove,
+};
+
+static int __init nic_init_module(void)
+{
+	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
+
+	return pci_register_driver(&nic_driver);
+}
+
+static void __exit nic_cleanup_module(void)
+{
+	pci_unregister_driver(&nic_driver);
+}
+
+module_init(nic_init_module);
+module_exit(nic_cleanup_module);
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
new file mode 100644
index 000000000000..58197bb2f805
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -0,0 +1,213 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef NIC_REG_H
+#define NIC_REG_H
+
+#define   NIC_PF_REG_COUNT			29573
+#define   NIC_VF_REG_COUNT			249
+
+/* Physical function register offsets */
+#define   NIC_PF_CFG				(0x0000)
+#define   NIC_PF_STATUS				(0x0010)
+#define   NIC_PF_INTR_TIMER_CFG			(0x0030)
+#define   NIC_PF_BIST_STATUS			(0x0040)
+#define   NIC_PF_SOFT_RESET			(0x0050)
+#define   NIC_PF_TCP_TIMER			(0x0060)
+#define   NIC_PF_BP_CFG				(0x0080)
+#define   NIC_PF_RRM_CFG			(0x0088)
+#define   NIC_PF_CQM_CF				(0x00A0)
+#define   NIC_PF_CNM_CF				(0x00A8)
+#define   NIC_PF_CNM_STATUS			(0x00B0)
+#define   NIC_PF_CQ_AVG_CFG			(0x00C0)
+#define   NIC_PF_RRM_AVG_CFG			(0x00C8)
+#define   NIC_PF_INTF_0_1_SEND_CFG		(0x0200)
+#define   NIC_PF_INTF_0_1_BP_CFG		(0x0208)
+#define   NIC_PF_INTF_0_1_BP_DIS_0_1		(0x0210)
+#define   NIC_PF_INTF_0_1_BP_SW_0_1		(0x0220)
+#define   NIC_PF_RBDR_BP_STATE_0_3		(0x0240)
+#define   NIC_PF_MAILBOX_INT			(0x0410)
+#define   NIC_PF_MAILBOX_INT_W1S		(0x0430)
+#define   NIC_PF_MAILBOX_ENA_W1C		(0x0450)
+#define   NIC_PF_MAILBOX_ENA_W1S		(0x0470)
+#define   NIC_PF_RX_ETYPE_0_7			(0x0500)
+#define   NIC_PF_PKIND_0_15_CFG			(0x0600)
+#define   NIC_PF_ECC0_FLIP0			(0x1000)
+#define   NIC_PF_ECC1_FLIP0			(0x1008)
+#define   NIC_PF_ECC2_FLIP0			(0x1010)
+#define   NIC_PF_ECC3_FLIP0			(0x1018)
+#define   NIC_PF_ECC0_FLIP1			(0x1080)
+#define   NIC_PF_ECC1_FLIP1			(0x1088)
+#define   NIC_PF_ECC2_FLIP1			(0x1090)
+#define   NIC_PF_ECC3_FLIP1			(0x1098)
+#define   NIC_PF_ECC0_CDIS			(0x1100)
+#define   NIC_PF_ECC1_CDIS			(0x1108)
+#define   NIC_PF_ECC2_CDIS			(0x1110)
+#define   NIC_PF_ECC3_CDIS			(0x1118)
+#define   NIC_PF_BIST0_STATUS			(0x1280)
+#define   NIC_PF_BIST1_STATUS			(0x1288)
+#define   NIC_PF_BIST2_STATUS			(0x1290)
+#define   NIC_PF_BIST3_STATUS			(0x1298)
+#define   NIC_PF_ECC0_SBE_INT			(0x2000)
+#define   NIC_PF_ECC0_SBE_INT_W1S		(0x2008)
+#define   NIC_PF_ECC0_SBE_ENA_W1C		(0x2010)
+#define   NIC_PF_ECC0_SBE_ENA_W1S		(0x2018)
+#define   NIC_PF_ECC0_DBE_INT			(0x2100)
+#define   NIC_PF_ECC0_DBE_INT_W1S		(0x2108)
+#define   NIC_PF_ECC0_DBE_ENA_W1C		(0x2110)
+#define   NIC_PF_ECC0_DBE_ENA_W1S		(0x2118)
+#define   NIC_PF_ECC1_SBE_INT			(0x2200)
+#define   NIC_PF_ECC1_SBE_INT_W1S		(0x2208)
+#define   NIC_PF_ECC1_SBE_ENA_W1C		(0x2210)
+#define   NIC_PF_ECC1_SBE_ENA_W1S		(0x2218)
+#define   NIC_PF_ECC1_DBE_INT			(0x2300)
+#define   NIC_PF_ECC1_DBE_INT_W1S		(0x2308)
+#define   NIC_PF_ECC1_DBE_ENA_W1C		(0x2310)
+#define   NIC_PF_ECC1_DBE_ENA_W1S		(0x2318)
+#define   NIC_PF_ECC2_SBE_INT			(0x2400)
+#define   NIC_PF_ECC2_SBE_INT_W1S		(0x2408)
+#define   NIC_PF_ECC2_SBE_ENA_W1C		(0x2410)
+#define   NIC_PF_ECC2_SBE_ENA_W1S		(0x2418)
+#define   NIC_PF_ECC2_DBE_INT			(0x2500)
+#define   NIC_PF_ECC2_DBE_INT_W1S		(0x2508)
+#define   NIC_PF_ECC2_DBE_ENA_W1C		(0x2510)
+#define   NIC_PF_ECC2_DBE_ENA_W1S		(0x2518)
+#define   NIC_PF_ECC3_SBE_INT			(0x2600)
+#define   NIC_PF_ECC3_SBE_INT_W1S		(0x2608)
+#define   NIC_PF_ECC3_SBE_ENA_W1C		(0x2610)
+#define   NIC_PF_ECC3_SBE_ENA_W1S		(0x2618)
+#define   NIC_PF_ECC3_DBE_INT			(0x2700)
+#define   NIC_PF_ECC3_DBE_INT_W1S		(0x2708)
+#define   NIC_PF_ECC3_DBE_ENA_W1C		(0x2710)
+#define   NIC_PF_ECC3_DBE_ENA_W1S		(0x2718)
+#define   NIC_PF_CPI_0_2047_CFG			(0x200000)
+#define   NIC_PF_RSSI_0_4097_RQ			(0x220000)
+#define   NIC_PF_LMAC_0_7_CFG			(0x240000)
+#define   NIC_PF_LMAC_0_7_SW_XOFF		(0x242000)
+#define   NIC_PF_LMAC_0_7_CREDIT		(0x244000)
+#define   NIC_PF_CHAN_0_255_TX_CFG		(0x400000)
+#define   NIC_PF_CHAN_0_255_RX_CFG		(0x420000)
+#define   NIC_PF_CHAN_0_255_SW_XOFF		(0x440000)
+#define   NIC_PF_CHAN_0_255_CREDIT		(0x460000)
+#define   NIC_PF_CHAN_0_255_RX_BP_CFG		(0x480000)
+#define   NIC_PF_SW_SYNC_RX			(0x490000)
+#define   NIC_PF_SW_SYNC_RX_DONE		(0x490008)
+#define   NIC_PF_TL2_0_63_CFG			(0x500000)
+#define   NIC_PF_TL2_0_63_PRI			(0x520000)
+#define   NIC_PF_TL2_0_63_SH_STATUS		(0x580000)
+#define   NIC_PF_TL3A_0_63_CFG			(0x5F0000)
+#define   NIC_PF_TL3_0_255_CFG			(0x600000)
+#define   NIC_PF_TL3_0_255_CHAN			(0x620000)
+#define   NIC_PF_TL3_0_255_PIR			(0x640000)
+#define   NIC_PF_TL3_0_255_SW_XOFF		(0x660000)
+#define   NIC_PF_TL3_0_255_CNM_RATE		(0x680000)
+#define   NIC_PF_TL3_0_255_SH_STATUS		(0x6A0000)
+#define   NIC_PF_TL4A_0_255_CFG			(0x6F0000)
+#define   NIC_PF_TL4_0_1023_CFG			(0x800000)
+#define   NIC_PF_TL4_0_1023_SW_XOFF		(0x820000)
+#define   NIC_PF_TL4_0_1023_SH_STATUS		(0x840000)
+#define   NIC_PF_TL4A_0_1023_CNM_RATE		(0x880000)
+#define   NIC_PF_TL4A_0_1023_CNM_STATUS		(0x8A0000)
+#define   NIC_PF_VF_0_127_MAILBOX_0_1		(0x20002030)
+#define   NIC_PF_VNIC_0_127_TX_STAT_0_4		(0x20004000)
+#define   NIC_PF_VNIC_0_127_RX_STAT_0_13	(0x20004100)
+#define   NIC_PF_QSET_0_127_LOCK_0_15		(0x20006000)
+#define   NIC_PF_QSET_0_127_CFG			(0x20010000)
+#define   NIC_PF_QSET_0_127_RQ_0_7_CFG		(0x20010400)
+#define   NIC_PF_QSET_0_127_RQ_0_7_DROP_CFG	(0x20010420)
+#define   NIC_PF_QSET_0_127_RQ_0_7_BP_CFG	(0x20010500)
+#define   NIC_PF_QSET_0_127_RQ_0_7_STAT_0_1	(0x20010600)
+#define   NIC_PF_QSET_0_127_SQ_0_7_CFG		(0x20010C00)
+#define   NIC_PF_QSET_0_127_SQ_0_7_CFG2		(0x20010C08)
+#define   NIC_PF_QSET_0_127_SQ_0_7_STAT_0_1	(0x20010D00)
+
+#define   NIC_PF_MSIX_VEC_0_18_ADDR		(0x000000)
+#define   NIC_PF_MSIX_VEC_0_CTL			(0x000008)
+#define   NIC_PF_MSIX_PBA_0			(0x0F0000)
+
+/* Virtual function register offsets */
+#define   NIC_VNIC_CFG				(0x000020)
+#define   NIC_VF_PF_MAILBOX_0_1			(0x000130)
+#define   NIC_VF_INT				(0x000200)
+#define   NIC_VF_INT_W1S			(0x000220)
+#define   NIC_VF_ENA_W1C			(0x000240)
+#define   NIC_VF_ENA_W1S			(0x000260)
+
+#define   NIC_VNIC_RSS_CFG			(0x0020E0)
+#define   NIC_VNIC_RSS_KEY_0_4			(0x002200)
+#define   NIC_VNIC_TX_STAT_0_4			(0x004000)
+#define   NIC_VNIC_RX_STAT_0_13			(0x004100)
+#define   NIC_QSET_RQ_GEN_CFG			(0x010010)
+
+#define   NIC_QSET_CQ_0_7_CFG			(0x010400)
+#define   NIC_QSET_CQ_0_7_CFG2			(0x010408)
+#define   NIC_QSET_CQ_0_7_THRESH		(0x010410)
+#define   NIC_QSET_CQ_0_7_BASE			(0x010420)
+#define   NIC_QSET_CQ_0_7_HEAD			(0x010428)
+#define   NIC_QSET_CQ_0_7_TAIL			(0x010430)
+#define   NIC_QSET_CQ_0_7_DOOR			(0x010438)
+#define   NIC_QSET_CQ_0_7_STATUS		(0x010440)
+#define   NIC_QSET_CQ_0_7_STATUS2		(0x010448)
+#define   NIC_QSET_CQ_0_7_DEBUG			(0x010450)
+
+#define   NIC_QSET_RQ_0_7_CFG			(0x010600)
+#define   NIC_QSET_RQ_0_7_STAT_0_1		(0x010700)
+
+#define   NIC_QSET_SQ_0_7_CFG			(0x010800)
+#define   NIC_QSET_SQ_0_7_THRESH		(0x010810)
+#define   NIC_QSET_SQ_0_7_BASE			(0x010820)
+#define   NIC_QSET_SQ_0_7_HEAD			(0x010828)
+#define   NIC_QSET_SQ_0_7_TAIL			(0x010830)
+#define   NIC_QSET_SQ_0_7_DOOR			(0x010838)
+#define   NIC_QSET_SQ_0_7_STATUS		(0x010840)
+#define   NIC_QSET_SQ_0_7_DEBUG			(0x010848)
+#define   NIC_QSET_SQ_0_7_CNM_CHG		(0x010860)
+#define   NIC_QSET_SQ_0_7_STAT_0_1		(0x010900)
+
+#define   NIC_QSET_RBDR_0_1_CFG			(0x010C00)
+#define   NIC_QSET_RBDR_0_1_THRESH		(0x010C10)
+#define   NIC_QSET_RBDR_0_1_BASE		(0x010C20)
+#define   NIC_QSET_RBDR_0_1_HEAD		(0x010C28)
+#define   NIC_QSET_RBDR_0_1_TAIL		(0x010C30)
+#define   NIC_QSET_RBDR_0_1_DOOR		(0x010C38)
+#define   NIC_QSET_RBDR_0_1_STATUS0		(0x010C40)
+#define   NIC_QSET_RBDR_0_1_STATUS1		(0x010C48)
+#define   NIC_QSET_RBDR_0_1_PREFETCH_STATUS	(0x010C50)
+
+#define   NIC_VF_MSIX_VECTOR_0_19_ADDR		(0x000000)
+#define   NIC_VF_MSIX_VECTOR_0_19_CTL		(0x000008)
+#define   NIC_VF_MSIX_PBA			(0x0F0000)
+
+/* Offsets within registers */
+#define   NIC_MSIX_VEC_SHIFT			4
+#define   NIC_Q_NUM_SHIFT			18
+#define   NIC_QS_ID_SHIFT			21
+#define   NIC_VF_NUM_SHIFT			21
+
+/* Port kind configuration register */
+struct pkind_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_42_63:22;
+	u64 hdr_sl:5;	/* Header skip length */
+	u64 rx_hdr:3;	/* TNS Receive header present */
+	u64 lenerr_en:1;/* L2 length error check enable */
+	u64 reserved_32_32:1;
+	u64 maxlen:16;	/* Max frame size */
+	u64 minlen:16;	/* Min frame size */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 minlen:16;
+	u64 maxlen:16;
+	u64 reserved_32_32:1;
+	u64 lenerr_en:1;
+	u64 rx_hdr:3;
+	u64 hdr_sl:5;
+	u64 reserved_42_63:22;
+#endif
+};
+
+#endif /* NIC_REG_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
new file mode 100644
index 000000000000..16bd2d772db9
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -0,0 +1,600 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+/* ETHTOOL Support for VNIC_VF Device*/
+
+#include <linux/pci.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "nicvf_queues.h"
+#include "q_struct.h"
+#include "thunder_bgx.h"
+
+#define DRV_NAME	"thunder-nicvf"
+#define DRV_VERSION     "1.0"
+
+struct nicvf_stat {
+	char name[ETH_GSTRING_LEN];
+	unsigned int index;
+};
+
+#define NICVF_HW_STAT(stat) { \
+	.name = #stat, \
+	.index = offsetof(struct nicvf_hw_stats, stat) / sizeof(u64), \
+}
+
+#define NICVF_DRV_STAT(stat) { \
+	.name = #stat, \
+	.index = offsetof(struct nicvf_drv_stats, stat) / sizeof(u64), \
+}
+
+static const struct nicvf_stat nicvf_hw_stats[] = {
+	NICVF_HW_STAT(rx_bytes_ok),
+	NICVF_HW_STAT(rx_ucast_frames_ok),
+	NICVF_HW_STAT(rx_bcast_frames_ok),
+	NICVF_HW_STAT(rx_mcast_frames_ok),
+	NICVF_HW_STAT(rx_fcs_errors),
+	NICVF_HW_STAT(rx_l2_errors),
+	NICVF_HW_STAT(rx_drop_red),
+	NICVF_HW_STAT(rx_drop_red_bytes),
+	NICVF_HW_STAT(rx_drop_overrun),
+	NICVF_HW_STAT(rx_drop_overrun_bytes),
+	NICVF_HW_STAT(rx_drop_bcast),
+	NICVF_HW_STAT(rx_drop_mcast),
+	NICVF_HW_STAT(rx_drop_l3_bcast),
+	NICVF_HW_STAT(rx_drop_l3_mcast),
+	NICVF_HW_STAT(tx_bytes_ok),
+	NICVF_HW_STAT(tx_ucast_frames_ok),
+	NICVF_HW_STAT(tx_bcast_frames_ok),
+	NICVF_HW_STAT(tx_mcast_frames_ok),
+};
+
+static const struct nicvf_stat nicvf_drv_stats[] = {
+	NICVF_DRV_STAT(rx_frames_ok),
+	NICVF_DRV_STAT(rx_frames_64),
+	NICVF_DRV_STAT(rx_frames_127),
+	NICVF_DRV_STAT(rx_frames_255),
+	NICVF_DRV_STAT(rx_frames_511),
+	NICVF_DRV_STAT(rx_frames_1023),
+	NICVF_DRV_STAT(rx_frames_1518),
+	NICVF_DRV_STAT(rx_frames_jumbo),
+	NICVF_DRV_STAT(rx_drops),
+	NICVF_DRV_STAT(tx_frames_ok),
+	NICVF_DRV_STAT(tx_busy),
+	NICVF_DRV_STAT(tx_tso),
+	NICVF_DRV_STAT(tx_drops),
+};
+
+static const struct nicvf_stat nicvf_queue_stats[] = {
+	{ "bytes", 0 },
+	{ "frames", 1 },
+};
+
+static const unsigned int nicvf_n_hw_stats = ARRAY_SIZE(nicvf_hw_stats);
+static const unsigned int nicvf_n_drv_stats = ARRAY_SIZE(nicvf_drv_stats);
+static const unsigned int nicvf_n_queue_stats = ARRAY_SIZE(nicvf_queue_stats);
+
+static int nicvf_get_settings(struct net_device *netdev,
+			      struct ethtool_cmd *cmd)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	cmd->supported = 0;
+	cmd->transceiver = XCVR_EXTERNAL;
+	if (nic->speed <= 1000) {
+		cmd->port = PORT_MII;
+		cmd->autoneg = AUTONEG_ENABLE;
+	} else {
+		cmd->port = PORT_FIBRE;
+		cmd->autoneg = AUTONEG_DISABLE;
+	}
+	cmd->duplex = nic->duplex;
+	ethtool_cmd_speed_set(cmd, nic->speed);
+
+	return 0;
+}
+
+static void nicvf_get_drvinfo(struct net_device *netdev,
+			      struct ethtool_drvinfo *info)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(nic->pdev), sizeof(info->bus_info));
+}
+
+static u32 nicvf_get_msglevel(struct net_device *netdev)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	return nic->msg_enable;
+}
+
+static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	nic->msg_enable = lvl;
+}
+
+static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
+{
+	int stats, qidx;
+
+	if (sset != ETH_SS_STATS)
+		return;
+
+	for (stats = 0; stats < nicvf_n_hw_stats; stats++) {
+		memcpy(data, nicvf_hw_stats[stats].name, ETH_GSTRING_LEN);
+		data += ETH_GSTRING_LEN;
+	}
+
+	for (stats = 0; stats < nicvf_n_drv_stats; stats++) {
+		memcpy(data, nicvf_drv_stats[stats].name, ETH_GSTRING_LEN);
+		data += ETH_GSTRING_LEN;
+	}
+
+	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
+			sprintf(data, "rxq%d: %s", qidx,
+				nicvf_queue_stats[stats].name);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+
+	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
+			sprintf(data, "txq%d: %s", qidx,
+				nicvf_queue_stats[stats].name);
+			data += ETH_GSTRING_LEN;
+		}
+	}
+
+	for (stats = 0; stats < BGX_RX_STATS_COUNT; stats++) {
+		sprintf(data, "bgx_rxstat%d: ", stats);
+		data += ETH_GSTRING_LEN;
+	}
+
+	for (stats = 0; stats < BGX_TX_STATS_COUNT; stats++) {
+		sprintf(data, "bgx_txstat%d: ", stats);
+		data += ETH_GSTRING_LEN;
+	}
+}
+
+static int nicvf_get_sset_count(struct net_device *netdev, int sset)
+{
+	if (sset != ETH_SS_STATS)
+		return -EINVAL;
+
+	return nicvf_n_hw_stats + nicvf_n_drv_stats +
+		(nicvf_n_queue_stats *
+		 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+		BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
+}
+
+static void nicvf_get_ethtool_stats(struct net_device *netdev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	int stat, qidx;
+
+	nicvf_update_stats(nic);
+
+	/* Update LMAC stats */
+	nicvf_update_lmac_stats(nic);
+
+	for (stat = 0; stat < nicvf_n_hw_stats; stat++)
+		*(data++) = ((u64 *)&nic->stats)
+				[nicvf_hw_stats[stat].index];
+	for (stat = 0; stat < nicvf_n_drv_stats; stat++)
+		*(data++) = ((u64 *)&nic->drv_stats)
+				[nicvf_drv_stats[stat].index];
+
+	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
+			*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
+					[nicvf_queue_stats[stat].index];
+	}
+
+	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
+			*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
+					[nicvf_queue_stats[stat].index];
+	}
+
+	for (stat = 0; stat < BGX_RX_STATS_COUNT; stat++)
+		*(data++) = nic->bgx_stats.rx_stats[stat];
+	for (stat = 0; stat < BGX_TX_STATS_COUNT; stat++)
+		*(data++) = nic->bgx_stats.tx_stats[stat];
+}
+
+static int nicvf_get_regs_len(struct net_device *dev)
+{
+	return sizeof(u64) * NIC_VF_REG_COUNT;
+}
+
+static void nicvf_get_regs(struct net_device *dev,
+			   struct ethtool_regs *regs, void *reg)
+{
+	struct nicvf *nic = netdev_priv(dev);
+	u64 *p = (u64 *)reg;
+	u64 reg_offset;
+	int mbox, key, stat, q;
+	int i = 0;
+
+	regs->version = 0;
+	memset(p, 0, NIC_VF_REG_COUNT);
+
+	p[i++] = nicvf_reg_read(nic, NIC_VNIC_CFG);
+	/* Mailbox registers */
+	for (mbox = 0; mbox < NIC_PF_VF_MAILBOX_SIZE; mbox++)
+		p[i++] = nicvf_reg_read(nic,
+					NIC_VF_PF_MAILBOX_0_1 | (mbox << 3));
+
+	p[i++] = nicvf_reg_read(nic, NIC_VF_INT);
+	p[i++] = nicvf_reg_read(nic, NIC_VF_INT_W1S);
+	p[i++] = nicvf_reg_read(nic, NIC_VF_ENA_W1C);
+	p[i++] = nicvf_reg_read(nic, NIC_VF_ENA_W1S);
+	p[i++] = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG);
+
+	for (key = 0; key < RSS_HASH_KEY_SIZE; key++)
+		p[i++] = nicvf_reg_read(nic, NIC_VNIC_RSS_KEY_0_4 | (key << 3));
+
+	/* Tx/Rx statistics */
+	for (stat = 0; stat < TX_STATS_ENUM_LAST; stat++)
+		p[i++] = nicvf_reg_read(nic,
+					NIC_VNIC_TX_STAT_0_4 | (stat << 3));
+
+	for (i = 0; i < RX_STATS_ENUM_LAST; i++)
+		p[i++] = nicvf_reg_read(nic,
+					NIC_VNIC_RX_STAT_0_13 | (stat << 3));
+
+	p[i++] = nicvf_reg_read(nic, NIC_QSET_RQ_GEN_CFG);
+
+	/* All completion queue's registers */
+	for (q = 0; q < MAX_CMP_QUEUES_PER_QS; q++) {
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_CFG, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_CFG2, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_THRESH, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_BASE, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_TAIL, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_DOOR, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS2, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_DEBUG, q);
+	}
+
+	/* All receive queue's registers */
+	for (q = 0; q < MAX_RCV_QUEUES_PER_QS; q++) {
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RQ_0_7_CFG, q);
+		p[i++] = nicvf_queue_reg_read(nic,
+						  NIC_QSET_RQ_0_7_STAT_0_1, q);
+		reg_offset = NIC_QSET_RQ_0_7_STAT_0_1 | (1 << 3);
+		p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
+	}
+
+	for (q = 0; q < MAX_SND_QUEUES_PER_QS; q++) {
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_THRESH, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_BASE, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_HEAD, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_TAIL, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q);
+		reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3);
+		p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
+	}
+
+	for (q = 0; q < MAX_RCV_BUF_DESC_RINGS_PER_QS; q++) {
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_CFG, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_THRESH, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_BASE, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_HEAD, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, q);
+		p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_DOOR, q);
+		p[i++] = nicvf_queue_reg_read(nic,
+					      NIC_QSET_RBDR_0_1_STATUS0, q);
+		p[i++] = nicvf_queue_reg_read(nic,
+					      NIC_QSET_RBDR_0_1_STATUS1, q);
+		reg_offset = NIC_QSET_RBDR_0_1_PREFETCH_STATUS;
+		p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
+	}
+}
+
+static int nicvf_get_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *cmd)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	cmd->rx_coalesce_usecs = nic->cq_coalesce_usecs;
+	return 0;
+}
+
+static void nicvf_get_ringparam(struct net_device *netdev,
+				struct ethtool_ringparam *ring)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct queue_set *qs = nic->qs;
+
+	ring->rx_max_pending = MAX_RCV_BUF_COUNT;
+	ring->rx_pending = qs->rbdr_len;
+	ring->tx_max_pending = MAX_SND_QUEUE_LEN;
+	ring->tx_pending = qs->sq_len;
+}
+
+static int nicvf_get_rss_hash_opts(struct nicvf *nic,
+				   struct ethtool_rxnfc *info)
+{
+	info->data = 0;
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		info->data |= RXH_IP_SRC | RXH_IP_DST;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nicvf_get_rxnfc(struct net_device *dev,
+			   struct ethtool_rxnfc *info, u32 *rules)
+{
+	struct nicvf *nic = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = nic->qs->rq_cnt;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXFH:
+		return nicvf_get_rss_hash_opts(nic, info);
+	default:
+		break;
+	}
+	return ret;
+}
+
+static int nicvf_set_rss_hash_opts(struct nicvf *nic,
+				   struct ethtool_rxnfc *info)
+{
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	u64 rss_cfg = nicvf_reg_read(nic, NIC_VNIC_RSS_CFG);
+
+	if (!rss->enable)
+		netdev_err(nic->netdev,
+			   "RSS is disabled, hash cannot be set\n");
+
+	netdev_info(nic->netdev, "Set RSS flow type = %d, data = %lld\n",
+		    info->flow_type, info->data);
+
+	if (!(info->data & RXH_IP_SRC) || !(info->data & RXH_IP_DST))
+		return -EINVAL;
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_cfg &= ~(1ULL << RSS_HASH_TCP);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_cfg |= (1ULL << RSS_HASH_TCP);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_cfg &= ~(1ULL << RSS_HASH_UDP);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_cfg |= (1ULL << RSS_HASH_UDP);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		switch (info->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			rss_cfg &= ~(1ULL << RSS_HASH_L4ETC);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			rss_cfg |= (1ULL << RSS_HASH_L4ETC);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		rss_cfg = RSS_HASH_IP;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	nicvf_reg_write(nic, NIC_VNIC_RSS_CFG, rss_cfg);
+	return 0;
+}
+
+static int nicvf_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
+{
+	struct nicvf *nic = netdev_priv(dev);
+
+	switch (info->cmd) {
+	case ETHTOOL_SRXFH:
+		return nicvf_set_rss_hash_opts(nic, info);
+	default:
+		break;
+	}
+	return -EOPNOTSUPP;
+}
+
+static u32 nicvf_get_rxfh_key_size(struct net_device *netdev)
+{
+	return RSS_HASH_KEY_SIZE * sizeof(u64);
+}
+
+static u32 nicvf_get_rxfh_indir_size(struct net_device *dev)
+{
+	struct nicvf *nic = netdev_priv(dev);
+
+	return nic->rss_info.rss_size;
+}
+
+static int nicvf_get_rxfh(struct net_device *dev, u32 *indir, u8 *hkey,
+			  u8 *hfunc)
+{
+	struct nicvf *nic = netdev_priv(dev);
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	int idx;
+
+	if (indir) {
+		for (idx = 0; idx < rss->rss_size; idx++)
+			indir[idx] = rss->ind_tbl[idx];
+	}
+
+	if (hkey)
+		memcpy(hkey, rss->key, RSS_HASH_KEY_SIZE * sizeof(u64));
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
+	return 0;
+}
+
+static int nicvf_set_rxfh(struct net_device *dev, const u32 *indir,
+			  const u8 *hkey, u8 hfunc)
+{
+	struct nicvf *nic = netdev_priv(dev);
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	int idx;
+
+	if ((nic->qs->rq_cnt <= 1) || (nic->cpi_alg != CPI_ALG_NONE)) {
+		rss->enable = false;
+		rss->hash_bits = 0;
+		return -EIO;
+	}
+
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	rss->enable = true;
+	if (indir) {
+		for (idx = 0; idx < rss->rss_size; idx++)
+			rss->ind_tbl[idx] = indir[idx];
+	}
+
+	if (hkey) {
+		memcpy(rss->key, hkey, RSS_HASH_KEY_SIZE * sizeof(u64));
+		nicvf_set_rss_key(nic);
+	}
+
+	nicvf_config_rss(nic);
+	return 0;
+}
+
+/* Get no of queues device supports and current queue count */
+static void nicvf_get_channels(struct net_device *dev,
+			       struct ethtool_channels *channel)
+{
+	struct nicvf *nic = netdev_priv(dev);
+
+	memset(channel, 0, sizeof(*channel));
+
+	channel->max_rx = MAX_RCV_QUEUES_PER_QS;
+	channel->max_tx = MAX_SND_QUEUES_PER_QS;
+
+	channel->rx_count = nic->qs->rq_cnt;
+	channel->tx_count = nic->qs->sq_cnt;
+}
+
+/* Set no of Tx, Rx queues to be used */
+static int nicvf_set_channels(struct net_device *dev,
+			      struct ethtool_channels *channel)
+{
+	struct nicvf *nic = netdev_priv(dev);
+	int err = 0;
+
+	if (!channel->rx_count || !channel->tx_count)
+		return -EINVAL;
+	if (channel->rx_count > MAX_RCV_QUEUES_PER_QS)
+		return -EINVAL;
+	if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
+		return -EINVAL;
+
+	nic->qs->rq_cnt = channel->rx_count;
+	nic->qs->sq_cnt = channel->tx_count;
+	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
+
+	err = nicvf_set_real_num_queues(dev, nic->qs->sq_cnt, nic->qs->rq_cnt);
+	if (err)
+		return err;
+
+	if (!netif_running(dev))
+		return err;
+
+	nicvf_stop(dev);
+	nicvf_open(dev);
+	netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
+		    nic->qs->sq_cnt, nic->qs->rq_cnt);
+
+	return err;
+}
+
+static const struct ethtool_ops nicvf_ethtool_ops = {
+	.get_settings		= nicvf_get_settings,
+	.get_link		= ethtool_op_get_link,
+	.get_drvinfo		= nicvf_get_drvinfo,
+	.get_msglevel		= nicvf_get_msglevel,
+	.set_msglevel		= nicvf_set_msglevel,
+	.get_strings		= nicvf_get_strings,
+	.get_sset_count		= nicvf_get_sset_count,
+	.get_ethtool_stats	= nicvf_get_ethtool_stats,
+	.get_regs_len		= nicvf_get_regs_len,
+	.get_regs		= nicvf_get_regs,
+	.get_coalesce		= nicvf_get_coalesce,
+	.get_ringparam		= nicvf_get_ringparam,
+	.get_rxnfc		= nicvf_get_rxnfc,
+	.set_rxnfc		= nicvf_set_rxnfc,
+	.get_rxfh_key_size	= nicvf_get_rxfh_key_size,
+	.get_rxfh_indir_size	= nicvf_get_rxfh_indir_size,
+	.get_rxfh		= nicvf_get_rxfh,
+	.set_rxfh		= nicvf_set_rxfh,
+	.get_channels		= nicvf_get_channels,
+	.set_channels		= nicvf_set_channels,
+	.get_ts_info		= ethtool_op_get_ts_info,
+};
+
+void nicvf_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &nicvf_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
new file mode 100644
index 000000000000..8b119a035b7e
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -0,0 +1,1341 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/log2.h>
+#include <linux/prefetch.h>
+#include <linux/irq.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "nicvf_queues.h"
+#include "thunder_bgx.h"
+
+#define DRV_NAME	"thunder-nicvf"
+#define DRV_VERSION	"1.0"
+
+/* Supported devices */
+static const struct pci_device_id nicvf_id_table[] = {
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
+			 PCI_DEVICE_ID_THUNDER_NIC_VF,
+			 PCI_VENDOR_ID_CAVIUM, 0xA11E) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
+			 PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF,
+			 PCI_VENDOR_ID_CAVIUM, 0xA11E) },
+	{ 0, }  /* end of table */
+};
+
+MODULE_AUTHOR("Sunil Goutham");
+MODULE_DESCRIPTION("Cavium Thunder NIC Virtual Function Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DEVICE_TABLE(pci, nicvf_id_table);
+
+static int debug = 0x00;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "Debug message level bitmap");
+
+static int cpi_alg = CPI_ALG_NONE;
+module_param(cpi_alg, int, S_IRUGO);
+MODULE_PARM_DESC(cpi_alg,
+		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
+
+static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic,
+					  struct sk_buff *skb)
+{
+	if (skb->len <= 64)
+		nic->drv_stats.rx_frames_64++;
+	else if (skb->len <= 127)
+		nic->drv_stats.rx_frames_127++;
+	else if (skb->len <= 255)
+		nic->drv_stats.rx_frames_255++;
+	else if (skb->len <= 511)
+		nic->drv_stats.rx_frames_511++;
+	else if (skb->len <= 1023)
+		nic->drv_stats.rx_frames_1023++;
+	else if (skb->len <= 1518)
+		nic->drv_stats.rx_frames_1518++;
+	else
+		nic->drv_stats.rx_frames_jumbo++;
+}
+
+/* The Cavium ThunderX network controller can *only* be found in SoCs
+ * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
+ * registers on this platform are implicitly strongly ordered with respect
+ * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use
+ * with no memory barriers in this driver.  The readq()/writeq() functions add
+ * explicit ordering operation which in this case are redundant, and only
+ * add overhead.
+ */
+
+/* Register read/write APIs */
+void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val)
+{
+	writeq_relaxed(val, nic->reg_base + offset);
+}
+
+u64 nicvf_reg_read(struct nicvf *nic, u64 offset)
+{
+	return readq_relaxed(nic->reg_base + offset);
+}
+
+void nicvf_queue_reg_write(struct nicvf *nic, u64 offset,
+			   u64 qidx, u64 val)
+{
+	void __iomem *addr = nic->reg_base + offset;
+
+	writeq_relaxed(val, addr + (qidx << NIC_Q_NUM_SHIFT));
+}
+
+u64 nicvf_queue_reg_read(struct nicvf *nic, u64 offset, u64 qidx)
+{
+	void __iomem *addr = nic->reg_base + offset;
+
+	return readq_relaxed(addr + (qidx << NIC_Q_NUM_SHIFT));
+}
+
+/* VF -> PF mailbox communication */
+
+static void nicvf_write_to_mbx(struct nicvf *nic, union nic_mbx *mbx)
+{
+	u64 *msg = (u64 *)mbx;
+
+	nicvf_reg_write(nic, NIC_VF_PF_MAILBOX_0_1 + 0, msg[0]);
+	nicvf_reg_write(nic, NIC_VF_PF_MAILBOX_0_1 + 8, msg[1]);
+}
+
+int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
+{
+	int timeout = NIC_MBOX_MSG_TIMEOUT;
+	int sleep = 10;
+
+	nic->pf_acked = false;
+	nic->pf_nacked = false;
+
+	nicvf_write_to_mbx(nic, mbx);
+
+	/* Wait for previous message to be acked, timeout 2sec */
+	while (!nic->pf_acked) {
+		if (nic->pf_nacked)
+			return -EINVAL;
+		msleep(sleep);
+		if (nic->pf_acked)
+			break;
+		timeout -= sleep;
+		if (!timeout) {
+			netdev_err(nic->netdev,
+				   "PF didn't ack to mbox msg %d from VF%d\n",
+				   (mbx->msg.msg & 0xFF), nic->vf_id);
+			return -EBUSY;
+		}
+	}
+	return 0;
+}
+
+/* Checks if VF is able to comminicate with PF
+* and also gets the VNIC number this VF is associated to.
+*/
+static int nicvf_check_pf_ready(struct nicvf *nic)
+{
+	int timeout = 5000, sleep = 20;
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_READY;
+
+	nic->pf_ready_to_rcv_msg = false;
+
+	nicvf_write_to_mbx(nic, &mbx);
+
+	while (!nic->pf_ready_to_rcv_msg) {
+		msleep(sleep);
+		if (nic->pf_ready_to_rcv_msg)
+			break;
+		timeout -= sleep;
+		if (!timeout) {
+			netdev_err(nic->netdev,
+				   "PF didn't respond to READY msg\n");
+			return 0;
+		}
+	}
+	return 1;
+}
+
+static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx)
+{
+	if (bgx->rx)
+		nic->bgx_stats.rx_stats[bgx->idx] = bgx->stats;
+	else
+		nic->bgx_stats.tx_stats[bgx->idx] = bgx->stats;
+}
+
+static void  nicvf_handle_mbx_intr(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+	u64 *mbx_data;
+	u64 mbx_addr;
+	int i;
+
+	mbx_addr = NIC_VF_PF_MAILBOX_0_1;
+	mbx_data = (u64 *)&mbx;
+
+	for (i = 0; i < NIC_PF_VF_MAILBOX_SIZE; i++) {
+		*mbx_data = nicvf_reg_read(nic, mbx_addr);
+		mbx_data++;
+		mbx_addr += sizeof(u64);
+	}
+
+	netdev_dbg(nic->netdev, "Mbox message: msg: 0x%x\n", mbx.msg.msg);
+	switch (mbx.msg.msg) {
+	case NIC_MBOX_MSG_READY:
+		nic->pf_ready_to_rcv_msg = true;
+		nic->vf_id = mbx.nic_cfg.vf_id & 0x7F;
+		nic->tns_mode = mbx.nic_cfg.tns_mode & 0x7F;
+		nic->node = mbx.nic_cfg.node_id;
+		if (!nic->set_mac_pending)
+			ether_addr_copy(nic->netdev->dev_addr,
+					mbx.nic_cfg.mac_addr);
+		nic->link_up = false;
+		nic->duplex = 0;
+		nic->speed = 0;
+		break;
+	case NIC_MBOX_MSG_ACK:
+		nic->pf_acked = true;
+		break;
+	case NIC_MBOX_MSG_NACK:
+		nic->pf_nacked = true;
+		break;
+	case NIC_MBOX_MSG_RSS_SIZE:
+		nic->rss_info.rss_size = mbx.rss_size.ind_tbl_size;
+		nic->pf_acked = true;
+		break;
+	case NIC_MBOX_MSG_BGX_STATS:
+		nicvf_read_bgx_stats(nic, &mbx.bgx_stats);
+		nic->pf_acked = true;
+		nic->bgx_stats_acked = true;
+		break;
+	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
+		nic->pf_acked = true;
+		nic->link_up = mbx.link_status.link_up;
+		nic->duplex = mbx.link_status.duplex;
+		nic->speed = mbx.link_status.speed;
+		if (nic->link_up) {
+			netdev_info(nic->netdev, "%s: Link is Up %d Mbps %s\n",
+				    nic->netdev->name, nic->speed,
+				    nic->duplex == DUPLEX_FULL ?
+				"Full duplex" : "Half duplex");
+			netif_carrier_on(nic->netdev);
+			netif_tx_wake_all_queues(nic->netdev);
+		} else {
+			netdev_info(nic->netdev, "%s: Link is Down\n",
+				    nic->netdev->name);
+			netif_carrier_off(nic->netdev);
+			netif_tx_stop_all_queues(nic->netdev);
+		}
+		break;
+	default:
+		netdev_err(nic->netdev,
+			   "Invalid message from PF, msg 0x%x\n", mbx.msg.msg);
+		break;
+	}
+	nicvf_clear_intr(nic, NICVF_INTR_MBOX, 0);
+}
+
+static int nicvf_hw_set_mac_addr(struct nicvf *nic, struct net_device *netdev)
+{
+	union nic_mbx mbx = {};
+
+	mbx.mac.msg = NIC_MBOX_MSG_SET_MAC;
+	mbx.mac.vf_id = nic->vf_id;
+	ether_addr_copy(mbx.mac.mac_addr, netdev->dev_addr);
+
+	return nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static void nicvf_config_cpi(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.cpi_cfg.msg = NIC_MBOX_MSG_CPI_CFG;
+	mbx.cpi_cfg.vf_id = nic->vf_id;
+	mbx.cpi_cfg.cpi_alg = nic->cpi_alg;
+	mbx.cpi_cfg.rq_cnt = nic->qs->rq_cnt;
+
+	nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static void nicvf_get_rss_size(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.rss_size.msg = NIC_MBOX_MSG_RSS_SIZE;
+	mbx.rss_size.vf_id = nic->vf_id;
+	nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+void nicvf_config_rss(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	int ind_tbl_len = rss->rss_size;
+	int i, nextq = 0;
+
+	mbx.rss_cfg.vf_id = nic->vf_id;
+	mbx.rss_cfg.hash_bits = rss->hash_bits;
+	while (ind_tbl_len) {
+		mbx.rss_cfg.tbl_offset = nextq;
+		mbx.rss_cfg.tbl_len = min(ind_tbl_len,
+					       RSS_IND_TBL_LEN_PER_MBX_MSG);
+		mbx.rss_cfg.msg = mbx.rss_cfg.tbl_offset ?
+			  NIC_MBOX_MSG_RSS_CFG_CONT : NIC_MBOX_MSG_RSS_CFG;
+
+		for (i = 0; i < mbx.rss_cfg.tbl_len; i++)
+			mbx.rss_cfg.ind_tbl[i] = rss->ind_tbl[nextq++];
+
+		nicvf_send_msg_to_pf(nic, &mbx);
+
+		ind_tbl_len -= mbx.rss_cfg.tbl_len;
+	}
+}
+
+void nicvf_set_rss_key(struct nicvf *nic)
+{
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	u64 key_addr = NIC_VNIC_RSS_KEY_0_4;
+	int idx;
+
+	for (idx = 0; idx < RSS_HASH_KEY_SIZE; idx++) {
+		nicvf_reg_write(nic, key_addr, rss->key[idx]);
+		key_addr += sizeof(u64);
+	}
+}
+
+static int nicvf_rss_init(struct nicvf *nic)
+{
+	struct nicvf_rss_info *rss = &nic->rss_info;
+	int idx;
+
+	nicvf_get_rss_size(nic);
+
+	if ((nic->qs->rq_cnt <= 1) || (cpi_alg != CPI_ALG_NONE)) {
+		rss->enable = false;
+		rss->hash_bits = 0;
+		return 0;
+	}
+
+	rss->enable = true;
+
+	/* Using the HW reset value for now */
+	rss->key[0] = 0xFEED0BADFEED0BADULL;
+	rss->key[1] = 0xFEED0BADFEED0BADULL;
+	rss->key[2] = 0xFEED0BADFEED0BADULL;
+	rss->key[3] = 0xFEED0BADFEED0BADULL;
+	rss->key[4] = 0xFEED0BADFEED0BADULL;
+
+	nicvf_set_rss_key(nic);
+
+	rss->cfg = RSS_IP_HASH_ENA | RSS_TCP_HASH_ENA | RSS_UDP_HASH_ENA;
+	nicvf_reg_write(nic, NIC_VNIC_RSS_CFG, rss->cfg);
+
+	rss->hash_bits =  ilog2(rounddown_pow_of_two(rss->rss_size));
+
+	for (idx = 0; idx < rss->rss_size; idx++)
+		rss->ind_tbl[idx] = ethtool_rxfh_indir_default(idx,
+							       nic->qs->rq_cnt);
+	nicvf_config_rss(nic);
+	return 1;
+}
+
+int nicvf_set_real_num_queues(struct net_device *netdev,
+			      int tx_queues, int rx_queues)
+{
+	int err = 0;
+
+	err = netif_set_real_num_tx_queues(netdev, tx_queues);
+	if (err) {
+		netdev_err(netdev,
+			   "Failed to set no of Tx queues: %d\n", tx_queues);
+		return err;
+	}
+
+	err = netif_set_real_num_rx_queues(netdev, rx_queues);
+	if (err)
+		netdev_err(netdev,
+			   "Failed to set no of Rx queues: %d\n", rx_queues);
+	return err;
+}
+
+static int nicvf_init_resources(struct nicvf *nic)
+{
+	int err;
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+
+	/* Enable Qset */
+	nicvf_qset_config(nic, true);
+
+	/* Initialize queues and HW for data transfer */
+	err = nicvf_config_data_transfer(nic, true);
+	if (err) {
+		netdev_err(nic->netdev,
+			   "Failed to alloc/config VF's QSet resources\n");
+		return err;
+	}
+
+	/* Send VF config done msg to PF */
+	nicvf_write_to_mbx(nic, &mbx);
+
+	return 0;
+}
+
+static void nicvf_snd_pkt_handler(struct net_device *netdev,
+				  struct cmp_queue *cq,
+				  struct cqe_send_t *cqe_tx, int cqe_type)
+{
+	struct sk_buff *skb = NULL;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct snd_queue *sq;
+	struct sq_hdr_subdesc *hdr;
+
+	sq = &nic->qs->sq[cqe_tx->sq_idx];
+
+	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, cqe_tx->sqe_ptr);
+	if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER)
+		return;
+
+	netdev_dbg(nic->netdev,
+		   "%s Qset #%d SQ #%d SQ ptr #%d subdesc count %d\n",
+		   __func__, cqe_tx->sq_qs, cqe_tx->sq_idx,
+		   cqe_tx->sqe_ptr, hdr->subdesc_cnt);
+
+	nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+	nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
+	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
+	/* For TSO offloaded packets only one head SKB needs to be freed */
+	if (skb) {
+		prefetch(skb);
+		dev_consume_skb_any(skb);
+	}
+}
+
+static void nicvf_rcv_pkt_handler(struct net_device *netdev,
+				  struct napi_struct *napi,
+				  struct cmp_queue *cq,
+				  struct cqe_rx_t *cqe_rx, int cqe_type)
+{
+	struct sk_buff *skb;
+	struct nicvf *nic = netdev_priv(netdev);
+	int err = 0;
+
+	/* Check for errors */
+	err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx);
+	if (err && !cqe_rx->rb_cnt)
+		return;
+
+	skb = nicvf_get_rcv_skb(nic, cqe_rx);
+	if (!skb) {
+		netdev_dbg(nic->netdev, "Packet not received\n");
+		return;
+	}
+
+	if (netif_msg_pktdata(nic)) {
+		netdev_info(nic->netdev, "%s: skb 0x%p, len=%d\n", netdev->name,
+			    skb, skb->len);
+		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1,
+			       skb->data, skb->len, true);
+	}
+
+	nicvf_set_rx_frame_cnt(nic, skb);
+
+	skb_record_rx_queue(skb, cqe_rx->rq_idx);
+	if (netdev->hw_features & NETIF_F_RXCSUM) {
+		/* HW by default verifies TCP/UDP/SCTP checksums */
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	} else {
+		skb_checksum_none_assert(skb);
+	}
+
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (napi && (netdev->features & NETIF_F_GRO))
+		napi_gro_receive(napi, skb);
+	else
+		netif_receive_skb(skb);
+}
+
+static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
+				 struct napi_struct *napi, int budget)
+{
+	int processed_cqe, work_done = 0;
+	int cqe_count, cqe_head;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct queue_set *qs = nic->qs;
+	struct cmp_queue *cq = &qs->cq[cq_idx];
+	struct cqe_rx_t *cq_desc;
+
+	spin_lock_bh(&cq->lock);
+loop:
+	processed_cqe = 0;
+	/* Get no of valid CQ entries to process */
+	cqe_count = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS, cq_idx);
+	cqe_count &= CQ_CQE_COUNT;
+	if (!cqe_count)
+		goto done;
+
+	/* Get head of the valid CQ entries */
+	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
+	cqe_head &= 0xFFFF;
+
+	netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
+		   __func__, cqe_count, cqe_head);
+	while (processed_cqe < cqe_count) {
+		/* Get the CQ descriptor */
+		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
+		cqe_head++;
+		cqe_head &= (cq->dmem.q_len - 1);
+		/* Initiate prefetch for next descriptor */
+		prefetch((struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head));
+
+		if ((work_done >= budget) && napi &&
+		    (cq_desc->cqe_type != CQE_TYPE_SEND)) {
+			break;
+		}
+
+		netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
+			   cq_desc->cqe_type);
+		switch (cq_desc->cqe_type) {
+		case CQE_TYPE_RX:
+			nicvf_rcv_pkt_handler(netdev, napi, cq,
+					      cq_desc, CQE_TYPE_RX);
+			work_done++;
+		break;
+		case CQE_TYPE_SEND:
+			nicvf_snd_pkt_handler(netdev, cq,
+					      (void *)cq_desc, CQE_TYPE_SEND);
+		break;
+		case CQE_TYPE_INVALID:
+		case CQE_TYPE_RX_SPLIT:
+		case CQE_TYPE_RX_TCP:
+		case CQE_TYPE_SEND_PTP:
+			/* Ignore for now */
+		break;
+		}
+		processed_cqe++;
+	}
+	netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
+		   __func__, processed_cqe, work_done, budget);
+
+	/* Ring doorbell to inform H/W to reuse processed CQEs */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
+			      cq_idx, processed_cqe);
+
+	if ((work_done < budget) && napi)
+		goto loop;
+
+done:
+	spin_unlock_bh(&cq->lock);
+	return work_done;
+}
+
+static int nicvf_poll(struct napi_struct *napi, int budget)
+{
+	u64  cq_head;
+	int  work_done = 0;
+	struct net_device *netdev = napi->dev;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf_cq_poll *cq;
+	struct netdev_queue *txq;
+
+	cq = container_of(napi, struct nicvf_cq_poll, napi);
+	work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
+
+	txq = netdev_get_tx_queue(netdev, cq->cq_idx);
+	if (netif_tx_queue_stopped(txq))
+		netif_tx_wake_queue(txq);
+
+	if (work_done < budget) {
+		/* Slow packet rate, exit polling */
+		napi_complete(napi);
+		/* Re-enable interrupts */
+		cq_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD,
+					       cq->cq_idx);
+		nicvf_clear_intr(nic, NICVF_INTR_CQ, cq->cq_idx);
+		nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_HEAD,
+				      cq->cq_idx, cq_head);
+		nicvf_enable_intr(nic, NICVF_INTR_CQ, cq->cq_idx);
+	}
+	return work_done;
+}
+
+/* Qset error interrupt handler
+ *
+ * As of now only CQ errors are handled
+ */
+static void nicvf_handle_qs_err(unsigned long data)
+{
+	struct nicvf *nic = (struct nicvf *)data;
+	struct queue_set *qs = nic->qs;
+	int qidx;
+	u64 status;
+
+	netif_tx_disable(nic->netdev);
+
+	/* Check if it is CQ err */
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++) {
+		status = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_STATUS,
+					      qidx);
+		if (!(status & CQ_ERR_MASK))
+			continue;
+		/* Process already queued CQEs and reconfig CQ */
+		nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx);
+		nicvf_sq_disable(nic, qidx);
+		nicvf_cq_intr_handler(nic->netdev, qidx, NULL, 0);
+		nicvf_cmp_queue_config(nic, qs, qidx, true);
+		nicvf_sq_free_used_descs(nic->netdev, &qs->sq[qidx], qidx);
+		nicvf_sq_enable(nic, &qs->sq[qidx], qidx);
+
+		nicvf_enable_intr(nic, NICVF_INTR_CQ, qidx);
+	}
+
+	netif_tx_start_all_queues(nic->netdev);
+	/* Re-enable Qset error interrupt */
+	nicvf_enable_intr(nic, NICVF_INTR_QS_ERR, 0);
+}
+
+static irqreturn_t nicvf_misc_intr_handler(int irq, void *nicvf_irq)
+{
+	struct nicvf *nic = (struct nicvf *)nicvf_irq;
+	u64 intr;
+
+	intr = nicvf_reg_read(nic, NIC_VF_INT);
+	/* Check for spurious interrupt */
+	if (!(intr & NICVF_INTR_MBOX_MASK))
+		return IRQ_HANDLED;
+
+	nicvf_handle_mbx_intr(nic);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t nicvf_intr_handler(int irq, void *nicvf_irq)
+{
+	u64 qidx, intr, clear_intr = 0;
+	u64 cq_intr, rbdr_intr, qs_err_intr;
+	struct nicvf *nic = (struct nicvf *)nicvf_irq;
+	struct queue_set *qs = nic->qs;
+	struct nicvf_cq_poll *cq_poll = NULL;
+
+	intr = nicvf_reg_read(nic, NIC_VF_INT);
+	if (netif_msg_intr(nic))
+		netdev_info(nic->netdev, "%s: interrupt status 0x%llx\n",
+			    nic->netdev->name, intr);
+
+	qs_err_intr = intr & NICVF_INTR_QS_ERR_MASK;
+	if (qs_err_intr) {
+		/* Disable Qset err interrupt and schedule softirq */
+		nicvf_disable_intr(nic, NICVF_INTR_QS_ERR, 0);
+		tasklet_hi_schedule(&nic->qs_err_task);
+		clear_intr |= qs_err_intr;
+	}
+
+	/* Disable interrupts and start polling */
+	cq_intr = (intr & NICVF_INTR_CQ_MASK) >> NICVF_INTR_CQ_SHIFT;
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++) {
+		if (!(cq_intr & (1 << qidx)))
+			continue;
+		if (!nicvf_is_intr_enabled(nic, NICVF_INTR_CQ, qidx))
+			continue;
+
+		nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx);
+		clear_intr |= ((1 << qidx) << NICVF_INTR_CQ_SHIFT);
+
+		cq_poll = nic->napi[qidx];
+		/* Schedule NAPI */
+		if (cq_poll)
+			napi_schedule(&cq_poll->napi);
+	}
+
+	/* Handle RBDR interrupts */
+	rbdr_intr = (intr & NICVF_INTR_RBDR_MASK) >> NICVF_INTR_RBDR_SHIFT;
+	if (rbdr_intr) {
+		/* Disable RBDR interrupt and schedule softirq */
+		for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
+			if (!nicvf_is_intr_enabled(nic, NICVF_INTR_RBDR, qidx))
+				continue;
+			nicvf_disable_intr(nic, NICVF_INTR_RBDR, qidx);
+			tasklet_hi_schedule(&nic->rbdr_task);
+			clear_intr |= ((1 << qidx) << NICVF_INTR_RBDR_SHIFT);
+		}
+	}
+
+	/* Clear interrupts */
+	nicvf_reg_write(nic, NIC_VF_INT, clear_intr);
+	return IRQ_HANDLED;
+}
+
+static int nicvf_enable_msix(struct nicvf *nic)
+{
+	int ret, vec;
+
+	nic->num_vec = NIC_VF_MSIX_VECTORS;
+
+	for (vec = 0; vec < nic->num_vec; vec++)
+		nic->msix_entries[vec].entry = vec;
+
+	ret = pci_enable_msix(nic->pdev, nic->msix_entries, nic->num_vec);
+	if (ret) {
+		netdev_err(nic->netdev,
+			   "Req for #%d msix vectors failed\n", nic->num_vec);
+		return 0;
+	}
+	nic->msix_enabled = 1;
+	return 1;
+}
+
+static void nicvf_disable_msix(struct nicvf *nic)
+{
+	if (nic->msix_enabled) {
+		pci_disable_msix(nic->pdev);
+		nic->msix_enabled = 0;
+		nic->num_vec = 0;
+	}
+}
+
+static int nicvf_register_interrupts(struct nicvf *nic)
+{
+	int irq, free, ret = 0;
+	int vector;
+
+	for_each_cq_irq(irq)
+		sprintf(nic->irq_name[irq], "NICVF%d CQ%d",
+			nic->vf_id, irq);
+
+	for_each_sq_irq(irq)
+		sprintf(nic->irq_name[irq], "NICVF%d SQ%d",
+			nic->vf_id, irq - NICVF_INTR_ID_SQ);
+
+	for_each_rbdr_irq(irq)
+		sprintf(nic->irq_name[irq], "NICVF%d RBDR%d",
+			nic->vf_id, irq - NICVF_INTR_ID_RBDR);
+
+	/* Register all interrupts except mailbox */
+	for (irq = 0; irq < NICVF_INTR_ID_SQ; irq++) {
+		vector = nic->msix_entries[irq].vector;
+		ret = request_irq(vector, nicvf_intr_handler,
+				  0, nic->irq_name[irq], nic);
+		if (ret)
+			break;
+		nic->irq_allocated[irq] = true;
+	}
+
+	for (irq = NICVF_INTR_ID_SQ; irq < NICVF_INTR_ID_MISC; irq++) {
+		vector = nic->msix_entries[irq].vector;
+		ret = request_irq(vector, nicvf_intr_handler,
+				  0, nic->irq_name[irq], nic);
+		if (ret)
+			break;
+		nic->irq_allocated[irq] = true;
+	}
+
+	sprintf(nic->irq_name[NICVF_INTR_ID_QS_ERR],
+		"NICVF%d Qset error", nic->vf_id);
+	if (!ret) {
+		vector = nic->msix_entries[NICVF_INTR_ID_QS_ERR].vector;
+		irq = NICVF_INTR_ID_QS_ERR;
+		ret = request_irq(vector, nicvf_intr_handler,
+				  0, nic->irq_name[irq], nic);
+		if (!ret)
+			nic->irq_allocated[irq] = true;
+	}
+
+	if (ret) {
+		netdev_err(nic->netdev, "Request irq failed\n");
+		for (free = 0; free < irq; free++)
+			free_irq(nic->msix_entries[free].vector, nic);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void nicvf_unregister_interrupts(struct nicvf *nic)
+{
+	int irq;
+
+	/* Free registered interrupts */
+	for (irq = 0; irq < nic->num_vec; irq++) {
+		if (nic->irq_allocated[irq])
+			free_irq(nic->msix_entries[irq].vector, nic);
+		nic->irq_allocated[irq] = false;
+	}
+
+	/* Disable MSI-X */
+	nicvf_disable_msix(nic);
+}
+
+/* Initialize MSIX vectors and register MISC interrupt.
+ * Send READY message to PF to check if its alive
+ */
+static int nicvf_register_misc_interrupt(struct nicvf *nic)
+{
+	int ret = 0;
+	int irq = NICVF_INTR_ID_MISC;
+
+	/* Return if mailbox interrupt is already registered */
+	if (nic->msix_enabled)
+		return 0;
+
+	/* Enable MSI-X */
+	if (!nicvf_enable_msix(nic))
+		return 1;
+
+	sprintf(nic->irq_name[irq], "%s Mbox", "NICVF");
+	/* Register Misc interrupt */
+	ret = request_irq(nic->msix_entries[irq].vector,
+			  nicvf_misc_intr_handler, 0, nic->irq_name[irq], nic);
+
+	if (ret)
+		return ret;
+	nic->irq_allocated[irq] = true;
+
+	/* Enable mailbox interrupt */
+	nicvf_enable_intr(nic, NICVF_INTR_MBOX, 0);
+
+	/* Check if VF is able to communicate with PF */
+	if (!nicvf_check_pf_ready(nic)) {
+		nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
+		nicvf_unregister_interrupts(nic);
+		return 1;
+	}
+
+	return 0;
+}
+
+static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	int qid = skb_get_queue_mapping(skb);
+	struct netdev_queue *txq = netdev_get_tx_queue(netdev, qid);
+
+	/* Check for minimum packet length */
+	if (skb->len <= ETH_HLEN) {
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+		netif_tx_stop_queue(txq);
+		nic->drv_stats.tx_busy++;
+		if (netif_msg_tx_err(nic))
+			netdev_warn(netdev,
+				    "%s: Transmit ring full, stopping SQ%d\n",
+				    netdev->name, qid);
+
+		return NETDEV_TX_BUSY;
+	}
+
+	return NETDEV_TX_OK;
+}
+
+int nicvf_stop(struct net_device *netdev)
+{
+	int irq, qidx;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct queue_set *qs = nic->qs;
+	struct nicvf_cq_poll *cq_poll = NULL;
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
+
+	/* Disable RBDR & QS error interrupts */
+	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
+		nicvf_disable_intr(nic, NICVF_INTR_RBDR, qidx);
+		nicvf_clear_intr(nic, NICVF_INTR_RBDR, qidx);
+	}
+	nicvf_disable_intr(nic, NICVF_INTR_QS_ERR, 0);
+	nicvf_clear_intr(nic, NICVF_INTR_QS_ERR, 0);
+
+	/* Wait for pending IRQ handlers to finish */
+	for (irq = 0; irq < nic->num_vec; irq++)
+		synchronize_irq(nic->msix_entries[irq].vector);
+
+	tasklet_kill(&nic->rbdr_task);
+	tasklet_kill(&nic->qs_err_task);
+	if (nic->rb_work_scheduled)
+		cancel_delayed_work_sync(&nic->rbdr_work);
+
+	for (qidx = 0; qidx < nic->qs->cq_cnt; qidx++) {
+		cq_poll = nic->napi[qidx];
+		if (!cq_poll)
+			continue;
+		nic->napi[qidx] = NULL;
+		napi_synchronize(&cq_poll->napi);
+		/* CQ intr is enabled while napi_complete,
+		 * so disable it now
+		 */
+		nicvf_disable_intr(nic, NICVF_INTR_CQ, qidx);
+		nicvf_clear_intr(nic, NICVF_INTR_CQ, qidx);
+		napi_disable(&cq_poll->napi);
+		netif_napi_del(&cq_poll->napi);
+		kfree(cq_poll);
+	}
+
+	/* Free resources */
+	nicvf_config_data_transfer(nic, false);
+
+	/* Disable HW Qset */
+	nicvf_qset_config(nic, false);
+
+	/* disable mailbox interrupt */
+	nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
+
+	nicvf_unregister_interrupts(nic);
+
+	return 0;
+}
+
+int nicvf_open(struct net_device *netdev)
+{
+	int err, qidx;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct queue_set *qs = nic->qs;
+	struct nicvf_cq_poll *cq_poll = NULL;
+
+	nic->mtu = netdev->mtu;
+
+	netif_carrier_off(netdev);
+
+	err = nicvf_register_misc_interrupt(nic);
+	if (err)
+		return err;
+
+	/* Register NAPI handler for processing CQEs */
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++) {
+		cq_poll = kzalloc(sizeof(*cq_poll), GFP_KERNEL);
+		if (!cq_poll) {
+			err = -ENOMEM;
+			goto napi_del;
+		}
+		cq_poll->cq_idx = qidx;
+		netif_napi_add(netdev, &cq_poll->napi, nicvf_poll,
+			       NAPI_POLL_WEIGHT);
+		napi_enable(&cq_poll->napi);
+		nic->napi[qidx] = cq_poll;
+	}
+
+	/* Check if we got MAC address from PF or else generate a radom MAC */
+	if (is_zero_ether_addr(netdev->dev_addr)) {
+		eth_hw_addr_random(netdev);
+		nicvf_hw_set_mac_addr(nic, netdev);
+	}
+
+	if (nic->set_mac_pending) {
+		nic->set_mac_pending = false;
+		nicvf_hw_set_mac_addr(nic, netdev);
+	}
+
+	/* Init tasklet for handling Qset err interrupt */
+	tasklet_init(&nic->qs_err_task, nicvf_handle_qs_err,
+		     (unsigned long)nic);
+
+	/* Init RBDR tasklet which will refill RBDR */
+	tasklet_init(&nic->rbdr_task, nicvf_rbdr_task,
+		     (unsigned long)nic);
+	INIT_DELAYED_WORK(&nic->rbdr_work, nicvf_rbdr_work);
+
+	/* Configure CPI alorithm */
+	nic->cpi_alg = cpi_alg;
+	nicvf_config_cpi(nic);
+
+	/* Configure receive side scaling */
+	nicvf_rss_init(nic);
+
+	err = nicvf_register_interrupts(nic);
+	if (err)
+		goto cleanup;
+
+	/* Initialize the queues */
+	err = nicvf_init_resources(nic);
+	if (err)
+		goto cleanup;
+
+	/* Make sure queue initialization is written */
+	wmb();
+
+	nicvf_reg_write(nic, NIC_VF_INT, -1);
+	/* Enable Qset err interrupt */
+	nicvf_enable_intr(nic, NICVF_INTR_QS_ERR, 0);
+
+	/* Enable completion queue interrupt */
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++)
+		nicvf_enable_intr(nic, NICVF_INTR_CQ, qidx);
+
+	/* Enable RBDR threshold interrupt */
+	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
+		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
+
+	netif_carrier_on(netdev);
+	netif_tx_start_all_queues(netdev);
+
+	return 0;
+cleanup:
+	nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
+	nicvf_unregister_interrupts(nic);
+napi_del:
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++) {
+		cq_poll = nic->napi[qidx];
+		if (!cq_poll)
+			continue;
+		napi_disable(&cq_poll->napi);
+		netif_napi_del(&cq_poll->napi);
+		kfree(cq_poll);
+		nic->napi[qidx] = NULL;
+	}
+	return err;
+}
+
+static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
+{
+	union nic_mbx mbx = {};
+
+	mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS;
+	mbx.frs.max_frs = mtu;
+	mbx.frs.vf_id = nic->vf_id;
+
+	return nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (new_mtu > NIC_HW_MAX_FRS)
+		return -EINVAL;
+
+	if (new_mtu < NIC_HW_MIN_FRS)
+		return -EINVAL;
+
+	if (nicvf_update_hw_max_frs(nic, new_mtu))
+		return -EINVAL;
+	netdev->mtu = new_mtu;
+	nic->mtu = new_mtu;
+
+	return 0;
+}
+
+static int nicvf_set_mac_address(struct net_device *netdev, void *p)
+{
+	struct sockaddr *addr = p;
+	struct nicvf *nic = netdev_priv(netdev);
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+
+	if (nic->msix_enabled) {
+		if (nicvf_hw_set_mac_addr(nic, netdev))
+			return -EBUSY;
+	} else {
+		nic->set_mac_pending = true;
+	}
+
+	return 0;
+}
+
+void nicvf_update_lmac_stats(struct nicvf *nic)
+{
+	int stat = 0;
+	union nic_mbx mbx = {};
+	int timeout;
+
+	if (!netif_running(nic->netdev))
+		return;
+
+	mbx.bgx_stats.msg = NIC_MBOX_MSG_BGX_STATS;
+	mbx.bgx_stats.vf_id = nic->vf_id;
+	/* Rx stats */
+	mbx.bgx_stats.rx = 1;
+	while (stat < BGX_RX_STATS_COUNT) {
+		nic->bgx_stats_acked = 0;
+		mbx.bgx_stats.idx = stat;
+		nicvf_send_msg_to_pf(nic, &mbx);
+		timeout = 0;
+		while ((!nic->bgx_stats_acked) && (timeout < 10)) {
+			msleep(2);
+			timeout++;
+		}
+		stat++;
+	}
+
+	stat = 0;
+
+	/* Tx stats */
+	mbx.bgx_stats.rx = 0;
+	while (stat < BGX_TX_STATS_COUNT) {
+		nic->bgx_stats_acked = 0;
+		mbx.bgx_stats.idx = stat;
+		nicvf_send_msg_to_pf(nic, &mbx);
+		timeout = 0;
+		while ((!nic->bgx_stats_acked) && (timeout < 10)) {
+			msleep(2);
+			timeout++;
+		}
+		stat++;
+	}
+}
+
+void nicvf_update_stats(struct nicvf *nic)
+{
+	int qidx;
+	struct nicvf_hw_stats *stats = &nic->stats;
+	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
+	struct queue_set *qs = nic->qs;
+
+#define GET_RX_STATS(reg) \
+	nicvf_reg_read(nic, NIC_VNIC_RX_STAT_0_13 | (reg << 3))
+#define GET_TX_STATS(reg) \
+	nicvf_reg_read(nic, NIC_VNIC_TX_STAT_0_4 | (reg << 3))
+
+	stats->rx_bytes_ok = GET_RX_STATS(RX_OCTS);
+	stats->rx_ucast_frames_ok = GET_RX_STATS(RX_UCAST);
+	stats->rx_bcast_frames_ok = GET_RX_STATS(RX_BCAST);
+	stats->rx_mcast_frames_ok = GET_RX_STATS(RX_MCAST);
+	stats->rx_fcs_errors = GET_RX_STATS(RX_FCS);
+	stats->rx_l2_errors = GET_RX_STATS(RX_L2ERR);
+	stats->rx_drop_red = GET_RX_STATS(RX_RED);
+	stats->rx_drop_overrun = GET_RX_STATS(RX_ORUN);
+	stats->rx_drop_bcast = GET_RX_STATS(RX_DRP_BCAST);
+	stats->rx_drop_mcast = GET_RX_STATS(RX_DRP_MCAST);
+	stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST);
+	stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST);
+
+	stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS);
+	stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST);
+	stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST);
+	stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST);
+	stats->tx_drops = GET_TX_STATS(TX_DROP);
+
+	drv_stats->rx_frames_ok = stats->rx_ucast_frames_ok +
+				  stats->rx_bcast_frames_ok +
+				  stats->rx_mcast_frames_ok;
+	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
+				  stats->tx_bcast_frames_ok +
+				  stats->tx_mcast_frames_ok;
+	drv_stats->rx_drops = stats->rx_drop_red +
+			      stats->rx_drop_overrun;
+	drv_stats->tx_drops = stats->tx_drops;
+
+	/* Update RQ and SQ stats */
+	for (qidx = 0; qidx < qs->rq_cnt; qidx++)
+		nicvf_update_rq_stats(nic, qidx);
+	for (qidx = 0; qidx < qs->sq_cnt; qidx++)
+		nicvf_update_sq_stats(nic, qidx);
+}
+
+static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev,
+					    struct rtnl_link_stats64 *stats)
+{
+	struct nicvf *nic = netdev_priv(netdev);
+	struct nicvf_hw_stats *hw_stats = &nic->stats;
+	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
+
+	nicvf_update_stats(nic);
+
+	stats->rx_bytes = hw_stats->rx_bytes_ok;
+	stats->rx_packets = drv_stats->rx_frames_ok;
+	stats->rx_dropped = drv_stats->rx_drops;
+
+	stats->tx_bytes = hw_stats->tx_bytes_ok;
+	stats->tx_packets = drv_stats->tx_frames_ok;
+	stats->tx_dropped = drv_stats->tx_drops;
+
+	return stats;
+}
+
+static void nicvf_tx_timeout(struct net_device *dev)
+{
+	struct nicvf *nic = netdev_priv(dev);
+
+	if (netif_msg_tx_err(nic))
+		netdev_warn(dev, "%s: Transmit timed out, resetting\n",
+			    dev->name);
+
+	schedule_work(&nic->reset_task);
+}
+
+static void nicvf_reset_task(struct work_struct *work)
+{
+	struct nicvf *nic;
+
+	nic = container_of(work, struct nicvf, reset_task);
+
+	if (!netif_running(nic->netdev))
+		return;
+
+	nicvf_stop(nic->netdev);
+	nicvf_open(nic->netdev);
+	nic->netdev->trans_start = jiffies;
+}
+
+static const struct net_device_ops nicvf_netdev_ops = {
+	.ndo_open		= nicvf_open,
+	.ndo_stop		= nicvf_stop,
+	.ndo_start_xmit		= nicvf_xmit,
+	.ndo_change_mtu		= nicvf_change_mtu,
+	.ndo_set_mac_address	= nicvf_set_mac_address,
+	.ndo_get_stats64	= nicvf_get_stats64,
+	.ndo_tx_timeout         = nicvf_tx_timeout,
+};
+
+static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *netdev;
+	struct nicvf *nic;
+	struct queue_set *qs;
+	int    err;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		return err;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x\n", err);
+		goto err_disable_device;
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "Unable to get usable DMA configuration\n");
+		goto err_release_regions;
+	}
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
+	if (err) {
+		dev_err(dev, "unable to get 48-bit DMA for consistent allocations\n");
+		goto err_release_regions;
+	}
+
+	netdev = alloc_etherdev_mqs(sizeof(struct nicvf),
+				    MAX_RCV_QUEUES_PER_QS,
+				    MAX_SND_QUEUES_PER_QS);
+	if (!netdev) {
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+
+	pci_set_drvdata(pdev, netdev);
+
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+
+	nic = netdev_priv(netdev);
+	nic->netdev = netdev;
+	nic->pdev = pdev;
+
+	/* MAP VF's configuration registers */
+	nic->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
+	if (!nic->reg_base) {
+		dev_err(dev, "Cannot map config register space, aborting\n");
+		err = -ENOMEM;
+		goto err_free_netdev;
+	}
+
+	err = nicvf_set_qset_resources(nic);
+	if (err)
+		goto err_free_netdev;
+
+	qs = nic->qs;
+
+	err = nicvf_set_real_num_queues(netdev, qs->sq_cnt, qs->rq_cnt);
+	if (err)
+		goto err_free_netdev;
+
+	/* Check if PF is alive and get MAC address for this VF */
+	err = nicvf_register_misc_interrupt(nic);
+	if (err)
+		goto err_free_netdev;
+
+	netdev->features |= (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG |
+			     NETIF_F_TSO | NETIF_F_GRO);
+	netdev->hw_features = netdev->features;
+
+	netdev->netdev_ops = &nicvf_netdev_ops;
+
+	INIT_WORK(&nic->reset_task, nicvf_reset_task);
+
+	err = register_netdev(netdev);
+	if (err) {
+		dev_err(dev, "Failed to register netdevice\n");
+		goto err_unregister_interrupts;
+	}
+
+	nic->msg_enable = debug;
+
+	nicvf_set_ethtool_ops(netdev);
+
+	return 0;
+
+err_unregister_interrupts:
+	nicvf_unregister_interrupts(nic);
+err_free_netdev:
+	pci_set_drvdata(pdev, NULL);
+	free_netdev(netdev);
+err_release_regions:
+	pci_release_regions(pdev);
+err_disable_device:
+	pci_disable_device(pdev);
+	return err;
+}
+
+static void nicvf_remove(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct nicvf *nic = netdev_priv(netdev);
+
+	unregister_netdev(netdev);
+	nicvf_unregister_interrupts(nic);
+	pci_set_drvdata(pdev, NULL);
+	free_netdev(netdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static struct pci_driver nicvf_driver = {
+	.name = DRV_NAME,
+	.id_table = nicvf_id_table,
+	.probe = nicvf_probe,
+	.remove = nicvf_remove,
+};
+
+static int __init nicvf_init_module(void)
+{
+	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
+
+	return pci_register_driver(&nicvf_driver);
+}
+
+static void __exit nicvf_cleanup_module(void)
+{
+	pci_unregister_driver(&nicvf_driver);
+}
+
+module_init(nicvf_init_module);
+module_exit(nicvf_cleanup_module);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
new file mode 100644
index 000000000000..d69d228d11a0
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -0,0 +1,1545 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/etherdevice.h>
+#include <net/ip.h>
+#include <net/tso.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "q_struct.h"
+#include "nicvf_queues.h"
+
+struct rbuf_info {
+	struct page *page;
+	void	*data;
+	u64	offset;
+};
+
+#define GET_RBUF_INFO(x) ((struct rbuf_info *)(x - NICVF_RCV_BUF_ALIGN_BYTES))
+
+/* Poll a register for a specific value */
+static int nicvf_poll_reg(struct nicvf *nic, int qidx,
+			  u64 reg, int bit_pos, int bits, int val)
+{
+	u64 bit_mask;
+	u64 reg_val;
+	int timeout = 10;
+
+	bit_mask = (1ULL << bits) - 1;
+	bit_mask = (bit_mask << bit_pos);
+
+	while (timeout) {
+		reg_val = nicvf_queue_reg_read(nic, reg, qidx);
+		if (((reg_val & bit_mask) >> bit_pos) == val)
+			return 0;
+		usleep_range(1000, 2000);
+		timeout--;
+	}
+	netdev_err(nic->netdev, "Poll on reg 0x%llx failed\n", reg);
+	return 1;
+}
+
+/* Allocate memory for a queue's descriptors */
+static int nicvf_alloc_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem,
+				  int q_len, int desc_size, int align_bytes)
+{
+	dmem->q_len = q_len;
+	dmem->size = (desc_size * q_len) + align_bytes;
+	/* Save address, need it while freeing */
+	dmem->unalign_base = dma_zalloc_coherent(&nic->pdev->dev, dmem->size,
+						&dmem->dma, GFP_KERNEL);
+	if (!dmem->unalign_base)
+		return -ENOMEM;
+
+	/* Align memory address for 'align_bytes' */
+	dmem->phys_base = NICVF_ALIGNED_ADDR((u64)dmem->dma, align_bytes);
+	dmem->base = dmem->unalign_base + (dmem->phys_base - dmem->dma);
+	return 0;
+}
+
+/* Free queue's descriptor memory */
+static void nicvf_free_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem)
+{
+	if (!dmem)
+		return;
+
+	dma_free_coherent(&nic->pdev->dev, dmem->size,
+			  dmem->unalign_base, dmem->dma);
+	dmem->unalign_base = NULL;
+	dmem->base = NULL;
+}
+
+/* Allocate buffer for packet reception
+ * HW returns memory address where packet is DMA'ed but not a pointer
+ * into RBDR ring, so save buffer address at the start of fragment and
+ * align the start address to a cache aligned address
+ */
+static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
+					 u32 buf_len, u64 **rbuf)
+{
+	u64 data;
+	struct rbuf_info *rinfo;
+	int order = get_order(buf_len);
+
+	/* Check if request can be accomodated in previous allocated page */
+	if (nic->rb_page) {
+		if ((nic->rb_page_offset + buf_len + buf_len) >
+		    (PAGE_SIZE << order)) {
+			nic->rb_page = NULL;
+		} else {
+			nic->rb_page_offset += buf_len;
+			get_page(nic->rb_page);
+		}
+	}
+
+	/* Allocate a new page */
+	if (!nic->rb_page) {
+		nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+		if (!nic->rb_page) {
+			netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+			return -ENOMEM;
+		}
+		nic->rb_page_offset = 0;
+	}
+
+	data = (u64)page_address(nic->rb_page) + nic->rb_page_offset;
+
+	/* Align buffer addr to cache line i.e 128 bytes */
+	rinfo = (struct rbuf_info *)(data + NICVF_RCV_BUF_ALIGN_LEN(data));
+	/* Save page address for reference updation */
+	rinfo->page = nic->rb_page;
+	/* Store start address for later retrieval */
+	rinfo->data = (void *)data;
+	/* Store alignment offset */
+	rinfo->offset = NICVF_RCV_BUF_ALIGN_LEN(data);
+
+	data += rinfo->offset;
+
+	/* Give next aligned address to hw for DMA */
+	*rbuf = (u64 *)(data + NICVF_RCV_BUF_ALIGN_BYTES);
+	return 0;
+}
+
+/* Retrieve actual buffer start address and build skb for received packet */
+static struct sk_buff *nicvf_rb_ptr_to_skb(struct nicvf *nic,
+					   u64 rb_ptr, int len)
+{
+	struct sk_buff *skb;
+	struct rbuf_info *rinfo;
+
+	rb_ptr = (u64)phys_to_virt(rb_ptr);
+	/* Get buffer start address and alignment offset */
+	rinfo = GET_RBUF_INFO(rb_ptr);
+
+	/* Now build an skb to give to stack */
+	skb = build_skb(rinfo->data, RCV_FRAG_LEN);
+	if (!skb) {
+		put_page(rinfo->page);
+		return NULL;
+	}
+
+	/* Set correct skb->data */
+	skb_reserve(skb, rinfo->offset + NICVF_RCV_BUF_ALIGN_BYTES);
+
+	prefetch((void *)rb_ptr);
+	return skb;
+}
+
+/* Allocate RBDR ring and populate receive buffers */
+static int  nicvf_init_rbdr(struct nicvf *nic, struct rbdr *rbdr,
+			    int ring_len, int buf_size)
+{
+	int idx;
+	u64 *rbuf;
+	struct rbdr_entry_t *desc;
+	int err;
+
+	err = nicvf_alloc_q_desc_mem(nic, &rbdr->dmem, ring_len,
+				     sizeof(struct rbdr_entry_t),
+				     NICVF_RCV_BUF_ALIGN_BYTES);
+	if (err)
+		return err;
+
+	rbdr->desc = rbdr->dmem.base;
+	/* Buffer size has to be in multiples of 128 bytes */
+	rbdr->dma_size = buf_size;
+	rbdr->enable = true;
+	rbdr->thresh = RBDR_THRESH;
+
+	nic->rb_page = NULL;
+	for (idx = 0; idx < ring_len; idx++) {
+		err = nicvf_alloc_rcv_buffer(nic, GFP_KERNEL, RCV_FRAG_LEN,
+					     &rbuf);
+		if (err)
+			return err;
+
+		desc = GET_RBDR_DESC(rbdr, idx);
+		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+	}
+	return 0;
+}
+
+/* Free RBDR ring and its receive buffers */
+static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
+{
+	int head, tail;
+	u64 buf_addr;
+	struct rbdr_entry_t *desc;
+	struct rbuf_info *rinfo;
+
+	if (!rbdr)
+		return;
+
+	rbdr->enable = false;
+	if (!rbdr->dmem.base)
+		return;
+
+	head = rbdr->head;
+	tail = rbdr->tail;
+
+	/* Free SKBs */
+	while (head != tail) {
+		desc = GET_RBDR_DESC(rbdr, head);
+		buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
+		rinfo = GET_RBUF_INFO((u64)phys_to_virt(buf_addr));
+		put_page(rinfo->page);
+		head++;
+		head &= (rbdr->dmem.q_len - 1);
+	}
+	/* Free SKB of tail desc */
+	desc = GET_RBDR_DESC(rbdr, tail);
+	buf_addr = desc->buf_addr << NICVF_RCV_BUF_ALIGN;
+	rinfo = GET_RBUF_INFO((u64)phys_to_virt(buf_addr));
+	put_page(rinfo->page);
+
+	/* Free RBDR ring */
+	nicvf_free_q_desc_mem(nic, &rbdr->dmem);
+}
+
+/* Refill receive buffer descriptors with new buffers.
+ */
+static void nicvf_refill_rbdr(struct nicvf *nic, gfp_t gfp)
+{
+	struct queue_set *qs = nic->qs;
+	int rbdr_idx = qs->rbdr_cnt;
+	int tail, qcount;
+	int refill_rb_cnt;
+	struct rbdr *rbdr;
+	struct rbdr_entry_t *desc;
+	u64 *rbuf;
+	int new_rb = 0;
+
+refill:
+	if (!rbdr_idx)
+		return;
+	rbdr_idx--;
+	rbdr = &qs->rbdr[rbdr_idx];
+	/* Check if it's enabled */
+	if (!rbdr->enable)
+		goto next_rbdr;
+
+	/* Get no of desc's to be refilled */
+	qcount = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_STATUS0, rbdr_idx);
+	qcount &= 0x7FFFF;
+	/* Doorbell can be ringed with a max of ring size minus 1 */
+	if (qcount >= (qs->rbdr_len - 1))
+		goto next_rbdr;
+	else
+		refill_rb_cnt = qs->rbdr_len - qcount - 1;
+
+	/* Start filling descs from tail */
+	tail = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_TAIL, rbdr_idx) >> 3;
+	while (refill_rb_cnt) {
+		tail++;
+		tail &= (rbdr->dmem.q_len - 1);
+
+		if (nicvf_alloc_rcv_buffer(nic, gfp, RCV_FRAG_LEN, &rbuf))
+			break;
+
+		desc = GET_RBDR_DESC(rbdr, tail);
+		desc->buf_addr = virt_to_phys(rbuf) >> NICVF_RCV_BUF_ALIGN;
+		refill_rb_cnt--;
+		new_rb++;
+	}
+
+	/* make sure all memory stores are done before ringing doorbell */
+	smp_wmb();
+
+	/* Check if buffer allocation failed */
+	if (refill_rb_cnt)
+		nic->rb_alloc_fail = true;
+	else
+		nic->rb_alloc_fail = false;
+
+	/* Notify HW */
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_DOOR,
+			      rbdr_idx, new_rb);
+next_rbdr:
+	/* Re-enable RBDR interrupts only if buffer allocation is success */
+	if (!nic->rb_alloc_fail && rbdr->enable)
+		nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx);
+
+	if (rbdr_idx)
+		goto refill;
+}
+
+/* Alloc rcv buffers in non-atomic mode for better success */
+void nicvf_rbdr_work(struct work_struct *work)
+{
+	struct nicvf *nic = container_of(work, struct nicvf, rbdr_work.work);
+
+	nicvf_refill_rbdr(nic, GFP_KERNEL);
+	if (nic->rb_alloc_fail)
+		schedule_delayed_work(&nic->rbdr_work, msecs_to_jiffies(10));
+	else
+		nic->rb_work_scheduled = false;
+}
+
+/* In Softirq context, alloc rcv buffers in atomic mode */
+void nicvf_rbdr_task(unsigned long data)
+{
+	struct nicvf *nic = (struct nicvf *)data;
+
+	nicvf_refill_rbdr(nic, GFP_ATOMIC);
+	if (nic->rb_alloc_fail) {
+		nic->rb_work_scheduled = true;
+		schedule_delayed_work(&nic->rbdr_work, msecs_to_jiffies(10));
+	}
+}
+
+/* Initialize completion queue */
+static int nicvf_init_cmp_queue(struct nicvf *nic,
+				struct cmp_queue *cq, int q_len)
+{
+	int err;
+
+	err = nicvf_alloc_q_desc_mem(nic, &cq->dmem, q_len, CMP_QUEUE_DESC_SIZE,
+				     NICVF_CQ_BASE_ALIGN_BYTES);
+	if (err)
+		return err;
+
+	cq->desc = cq->dmem.base;
+	cq->thresh = CMP_QUEUE_CQE_THRESH;
+	nic->cq_coalesce_usecs = (CMP_QUEUE_TIMER_THRESH * 0.05) - 1;
+
+	return 0;
+}
+
+static void nicvf_free_cmp_queue(struct nicvf *nic, struct cmp_queue *cq)
+{
+	if (!cq)
+		return;
+	if (!cq->dmem.base)
+		return;
+
+	nicvf_free_q_desc_mem(nic, &cq->dmem);
+}
+
+/* Initialize transmit queue */
+static int nicvf_init_snd_queue(struct nicvf *nic,
+				struct snd_queue *sq, int q_len)
+{
+	int err;
+
+	err = nicvf_alloc_q_desc_mem(nic, &sq->dmem, q_len, SND_QUEUE_DESC_SIZE,
+				     NICVF_SQ_BASE_ALIGN_BYTES);
+	if (err)
+		return err;
+
+	sq->desc = sq->dmem.base;
+	sq->skbuff = kcalloc(q_len, sizeof(u64), GFP_KERNEL);
+	if (!sq->skbuff)
+		return -ENOMEM;
+	sq->head = 0;
+	sq->tail = 0;
+	atomic_set(&sq->free_cnt, q_len - 1);
+	sq->thresh = SND_QUEUE_THRESH;
+
+	/* Preallocate memory for TSO segment's header */
+	sq->tso_hdrs = dma_alloc_coherent(&nic->pdev->dev,
+					  q_len * TSO_HEADER_SIZE,
+					  &sq->tso_hdrs_phys, GFP_KERNEL);
+	if (!sq->tso_hdrs)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
+{
+	if (!sq)
+		return;
+	if (!sq->dmem.base)
+		return;
+
+	if (sq->tso_hdrs)
+		dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+				  sq->tso_hdrs, sq->tso_hdrs_phys);
+
+	kfree(sq->skbuff);
+	nicvf_free_q_desc_mem(nic, &sq->dmem);
+}
+
+static void nicvf_reclaim_snd_queue(struct nicvf *nic,
+				    struct queue_set *qs, int qidx)
+{
+	/* Disable send queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, 0);
+	/* Check if SQ is stopped */
+	if (nicvf_poll_reg(nic, qidx, NIC_QSET_SQ_0_7_STATUS, 21, 1, 0x01))
+		return;
+	/* Reset send queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, NICVF_SQ_RESET);
+}
+
+static void nicvf_reclaim_rcv_queue(struct nicvf *nic,
+				    struct queue_set *qs, int qidx)
+{
+	union nic_mbx mbx = {};
+
+	/* Make sure all packets in the pipeline are written back into mem */
+	mbx.msg.msg = NIC_MBOX_MSG_RQ_SW_SYNC;
+	nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static void nicvf_reclaim_cmp_queue(struct nicvf *nic,
+				    struct queue_set *qs, int qidx)
+{
+	/* Disable timer threshold (doesn't get reset upon CQ reset */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2, qidx, 0);
+	/* Disable completion queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, 0);
+	/* Reset completion queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, NICVF_CQ_RESET);
+}
+
+static void nicvf_reclaim_rbdr(struct nicvf *nic,
+			       struct rbdr *rbdr, int qidx)
+{
+	u64 tmp, fifo_state;
+	int timeout = 10;
+
+	/* Save head and tail pointers for feeing up buffers */
+	rbdr->head = nicvf_queue_reg_read(nic,
+					  NIC_QSET_RBDR_0_1_HEAD,
+					  qidx) >> 3;
+	rbdr->tail = nicvf_queue_reg_read(nic,
+					  NIC_QSET_RBDR_0_1_TAIL,
+					  qidx) >> 3;
+
+	/* If RBDR FIFO is in 'FAIL' state then do a reset first
+	 * before relaiming.
+	 */
+	fifo_state = nicvf_queue_reg_read(nic, NIC_QSET_RBDR_0_1_STATUS0, qidx);
+	if (((fifo_state >> 62) & 0x03) == 0x3)
+		nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG,
+				      qidx, NICVF_RBDR_RESET);
+
+	/* Disable RBDR */
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, qidx, 0);
+	if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x00))
+		return;
+	while (1) {
+		tmp = nicvf_queue_reg_read(nic,
+					   NIC_QSET_RBDR_0_1_PREFETCH_STATUS,
+					   qidx);
+		if ((tmp & 0xFFFFFFFF) == ((tmp >> 32) & 0xFFFFFFFF))
+			break;
+		usleep_range(1000, 2000);
+		timeout--;
+		if (!timeout) {
+			netdev_err(nic->netdev,
+				   "Failed polling on prefetch status\n");
+			return;
+		}
+	}
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG,
+			      qidx, NICVF_RBDR_RESET);
+
+	if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x02))
+		return;
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG, qidx, 0x00);
+	if (nicvf_poll_reg(nic, qidx, NIC_QSET_RBDR_0_1_STATUS0, 62, 2, 0x00))
+		return;
+}
+
+/* Configures receive queue */
+static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
+				   int qidx, bool enable)
+{
+	union nic_mbx mbx = {};
+	struct rcv_queue *rq;
+	struct rq_cfg rq_cfg;
+
+	rq = &qs->rq[qidx];
+	rq->enable = enable;
+
+	/* Disable receive queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, 0);
+
+	if (!rq->enable) {
+		nicvf_reclaim_rcv_queue(nic, qs, qidx);
+		return;
+	}
+
+	rq->cq_qs = qs->vnic_id;
+	rq->cq_idx = qidx;
+	rq->start_rbdr_qs = qs->vnic_id;
+	rq->start_qs_rbdr_idx = qs->rbdr_cnt - 1;
+	rq->cont_rbdr_qs = qs->vnic_id;
+	rq->cont_qs_rbdr_idx = qs->rbdr_cnt - 1;
+	/* all writes of RBDR data to be loaded into L2 Cache as well*/
+	rq->caching = 1;
+
+	/* Send a mailbox msg to PF to config RQ */
+	mbx.rq.msg = NIC_MBOX_MSG_RQ_CFG;
+	mbx.rq.qs_num = qs->vnic_id;
+	mbx.rq.rq_num = qidx;
+	mbx.rq.cfg = (rq->caching << 26) | (rq->cq_qs << 19) |
+			  (rq->cq_idx << 16) | (rq->cont_rbdr_qs << 9) |
+			  (rq->cont_qs_rbdr_idx << 8) |
+			  (rq->start_rbdr_qs << 1) | (rq->start_qs_rbdr_idx);
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	mbx.rq.msg = NIC_MBOX_MSG_RQ_BP_CFG;
+	mbx.rq.cfg = (1ULL << 63) | (1ULL << 62) | (qs->vnic_id << 0);
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	/* RQ drop config
+	 * Enable CQ drop to reserve sufficient CQEs for all tx packets
+	 */
+	mbx.rq.msg = NIC_MBOX_MSG_RQ_DROP_CFG;
+	mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8);
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, qidx, 0x00);
+
+	/* Enable Receive queue */
+	rq_cfg.ena = 1;
+	rq_cfg.tcp_ena = 0;
+	nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
+}
+
+/* Configures completion queue */
+void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
+			    int qidx, bool enable)
+{
+	struct cmp_queue *cq;
+	struct cq_cfg cq_cfg;
+
+	cq = &qs->cq[qidx];
+	cq->enable = enable;
+
+	if (!cq->enable) {
+		nicvf_reclaim_cmp_queue(nic, qs, qidx);
+		return;
+	}
+
+	/* Reset completion queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, NICVF_CQ_RESET);
+
+	if (!cq->enable)
+		return;
+
+	spin_lock_init(&cq->lock);
+	/* Set completion queue base address */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_BASE,
+			      qidx, (u64)(cq->dmem.phys_base));
+
+	/* Enable Completion queue */
+	cq_cfg.ena = 1;
+	cq_cfg.reset = 0;
+	cq_cfg.caching = 0;
+	cq_cfg.qsize = CMP_QSIZE;
+	cq_cfg.avg_con = 0;
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG, qidx, *(u64 *)&cq_cfg);
+
+	/* Set threshold value for interrupt generation */
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_THRESH, qidx, cq->thresh);
+	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2,
+			      qidx, nic->cq_coalesce_usecs);
+}
+
+/* Configures transmit queue */
+static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
+				   int qidx, bool enable)
+{
+	union nic_mbx mbx = {};
+	struct snd_queue *sq;
+	struct sq_cfg sq_cfg;
+
+	sq = &qs->sq[qidx];
+	sq->enable = enable;
+
+	if (!sq->enable) {
+		nicvf_reclaim_snd_queue(nic, qs, qidx);
+		return;
+	}
+
+	/* Reset send queue */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, NICVF_SQ_RESET);
+
+	sq->cq_qs = qs->vnic_id;
+	sq->cq_idx = qidx;
+
+	/* Send a mailbox msg to PF to config SQ */
+	mbx.sq.msg = NIC_MBOX_MSG_SQ_CFG;
+	mbx.sq.qs_num = qs->vnic_id;
+	mbx.sq.sq_num = qidx;
+	mbx.sq.cfg = (sq->cq_qs << 3) | sq->cq_idx;
+	nicvf_send_msg_to_pf(nic, &mbx);
+
+	/* Set queue base address */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_BASE,
+			      qidx, (u64)(sq->dmem.phys_base));
+
+	/* Enable send queue  & set queue size */
+	sq_cfg.ena = 1;
+	sq_cfg.reset = 0;
+	sq_cfg.ldwb = 0;
+	sq_cfg.qsize = SND_QSIZE;
+	sq_cfg.tstmp_bgx_intf = 0;
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, *(u64 *)&sq_cfg);
+
+	/* Set threshold value for interrupt generation */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_THRESH, qidx, sq->thresh);
+
+	/* Set queue:cpu affinity for better load distribution */
+	if (cpu_online(qidx)) {
+		cpumask_set_cpu(qidx, &sq->affinity_mask);
+		netif_set_xps_queue(nic->netdev,
+				    &sq->affinity_mask, qidx);
+	}
+}
+
+/* Configures receive buffer descriptor ring */
+static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
+			      int qidx, bool enable)
+{
+	struct rbdr *rbdr;
+	struct rbdr_cfg rbdr_cfg;
+
+	rbdr = &qs->rbdr[qidx];
+	nicvf_reclaim_rbdr(nic, rbdr, qidx);
+	if (!enable)
+		return;
+
+	/* Set descriptor base address */
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_BASE,
+			      qidx, (u64)(rbdr->dmem.phys_base));
+
+	/* Enable RBDR  & set queue size */
+	/* Buffer size should be in multiples of 128 bytes */
+	rbdr_cfg.ena = 1;
+	rbdr_cfg.reset = 0;
+	rbdr_cfg.ldwb = 0;
+	rbdr_cfg.qsize = RBDR_SIZE;
+	rbdr_cfg.avg_con = 0;
+	rbdr_cfg.lines = rbdr->dma_size / 128;
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_CFG,
+			      qidx, *(u64 *)&rbdr_cfg);
+
+	/* Notify HW */
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_DOOR,
+			      qidx, qs->rbdr_len - 1);
+
+	/* Set threshold value for interrupt generation */
+	nicvf_queue_reg_write(nic, NIC_QSET_RBDR_0_1_THRESH,
+			      qidx, rbdr->thresh - 1);
+}
+
+/* Requests PF to assign and enable Qset */
+void nicvf_qset_config(struct nicvf *nic, bool enable)
+{
+	union nic_mbx mbx = {};
+	struct queue_set *qs = nic->qs;
+	struct qs_cfg *qs_cfg;
+
+	if (!qs) {
+		netdev_warn(nic->netdev,
+			    "Qset is still not allocated, don't init queues\n");
+		return;
+	}
+
+	qs->enable = enable;
+	qs->vnic_id = nic->vf_id;
+
+	/* Send a mailbox msg to PF to config Qset */
+	mbx.qs.msg = NIC_MBOX_MSG_QS_CFG;
+	mbx.qs.num = qs->vnic_id;
+
+	mbx.qs.cfg = 0;
+	qs_cfg = (struct qs_cfg *)&mbx.qs.cfg;
+	if (qs->enable) {
+		qs_cfg->ena = 1;
+#ifdef __BIG_ENDIAN
+		qs_cfg->be = 1;
+#endif
+		qs_cfg->vnic = qs->vnic_id;
+	}
+	nicvf_send_msg_to_pf(nic, &mbx);
+}
+
+static void nicvf_free_resources(struct nicvf *nic)
+{
+	int qidx;
+	struct queue_set *qs = nic->qs;
+
+	/* Free receive buffer descriptor ring */
+	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
+		nicvf_free_rbdr(nic, &qs->rbdr[qidx]);
+
+	/* Free completion queue */
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++)
+		nicvf_free_cmp_queue(nic, &qs->cq[qidx]);
+
+	/* Free send queue */
+	for (qidx = 0; qidx < qs->sq_cnt; qidx++)
+		nicvf_free_snd_queue(nic, &qs->sq[qidx]);
+}
+
+static int nicvf_alloc_resources(struct nicvf *nic)
+{
+	int qidx;
+	struct queue_set *qs = nic->qs;
+
+	/* Alloc receive buffer descriptor ring */
+	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
+		if (nicvf_init_rbdr(nic, &qs->rbdr[qidx], qs->rbdr_len,
+				    DMA_BUFFER_LEN))
+			goto alloc_fail;
+	}
+
+	/* Alloc send queue */
+	for (qidx = 0; qidx < qs->sq_cnt; qidx++) {
+		if (nicvf_init_snd_queue(nic, &qs->sq[qidx], qs->sq_len))
+			goto alloc_fail;
+	}
+
+	/* Alloc completion queue */
+	for (qidx = 0; qidx < qs->cq_cnt; qidx++) {
+		if (nicvf_init_cmp_queue(nic, &qs->cq[qidx], qs->cq_len))
+			goto alloc_fail;
+	}
+
+	return 0;
+alloc_fail:
+	nicvf_free_resources(nic);
+	return -ENOMEM;
+}
+
+int nicvf_set_qset_resources(struct nicvf *nic)
+{
+	struct queue_set *qs;
+
+	qs = devm_kzalloc(&nic->pdev->dev, sizeof(*qs), GFP_KERNEL);
+	if (!qs)
+		return -ENOMEM;
+	nic->qs = qs;
+
+	/* Set count of each queue */
+	qs->rbdr_cnt = RBDR_CNT;
+	qs->rq_cnt = RCV_QUEUE_CNT;
+	qs->sq_cnt = SND_QUEUE_CNT;
+	qs->cq_cnt = CMP_QUEUE_CNT;
+
+	/* Set queue lengths */
+	qs->rbdr_len = RCV_BUF_COUNT;
+	qs->sq_len = SND_QUEUE_LEN;
+	qs->cq_len = CMP_QUEUE_LEN;
+	return 0;
+}
+
+int nicvf_config_data_transfer(struct nicvf *nic, bool enable)
+{
+	bool disable = false;
+	struct queue_set *qs = nic->qs;
+	int qidx;
+
+	if (!qs)
+		return 0;
+
+	if (enable) {
+		if (nicvf_alloc_resources(nic))
+			return -ENOMEM;
+
+		for (qidx = 0; qidx < qs->sq_cnt; qidx++)
+			nicvf_snd_queue_config(nic, qs, qidx, enable);
+		for (qidx = 0; qidx < qs->cq_cnt; qidx++)
+			nicvf_cmp_queue_config(nic, qs, qidx, enable);
+		for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
+			nicvf_rbdr_config(nic, qs, qidx, enable);
+		for (qidx = 0; qidx < qs->rq_cnt; qidx++)
+			nicvf_rcv_queue_config(nic, qs, qidx, enable);
+	} else {
+		for (qidx = 0; qidx < qs->rq_cnt; qidx++)
+			nicvf_rcv_queue_config(nic, qs, qidx, disable);
+		for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
+			nicvf_rbdr_config(nic, qs, qidx, disable);
+		for (qidx = 0; qidx < qs->sq_cnt; qidx++)
+			nicvf_snd_queue_config(nic, qs, qidx, disable);
+		for (qidx = 0; qidx < qs->cq_cnt; qidx++)
+			nicvf_cmp_queue_config(nic, qs, qidx, disable);
+
+		nicvf_free_resources(nic);
+	}
+
+	return 0;
+}
+
+/* Get a free desc from SQ
+ * returns descriptor ponter & descriptor number
+ */
+static inline int nicvf_get_sq_desc(struct snd_queue *sq, int desc_cnt)
+{
+	int qentry;
+
+	qentry = sq->tail;
+	atomic_sub(desc_cnt, &sq->free_cnt);
+	sq->tail += desc_cnt;
+	sq->tail &= (sq->dmem.q_len - 1);
+
+	return qentry;
+}
+
+/* Free descriptor back to SQ for future use */
+void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt)
+{
+	atomic_add(desc_cnt, &sq->free_cnt);
+	sq->head += desc_cnt;
+	sq->head &= (sq->dmem.q_len - 1);
+}
+
+static inline int nicvf_get_nxt_sqentry(struct snd_queue *sq, int qentry)
+{
+	qentry++;
+	qentry &= (sq->dmem.q_len - 1);
+	return qentry;
+}
+
+void nicvf_sq_enable(struct nicvf *nic, struct snd_queue *sq, int qidx)
+{
+	u64 sq_cfg;
+
+	sq_cfg = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, qidx);
+	sq_cfg |= NICVF_SQ_EN;
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, sq_cfg);
+	/* Ring doorbell so that H/W restarts processing SQEs */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR, qidx, 0);
+}
+
+void nicvf_sq_disable(struct nicvf *nic, int qidx)
+{
+	u64 sq_cfg;
+
+	sq_cfg = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CFG, qidx);
+	sq_cfg &= ~NICVF_SQ_EN;
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_CFG, qidx, sq_cfg);
+}
+
+void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
+			      int qidx)
+{
+	u64 head, tail;
+	struct sk_buff *skb;
+	struct nicvf *nic = netdev_priv(netdev);
+	struct sq_hdr_subdesc *hdr;
+
+	head = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_HEAD, qidx) >> 4;
+	tail = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_TAIL, qidx) >> 4;
+	while (sq->head != head) {
+		hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, sq->head);
+		if (hdr->subdesc_type != SQ_DESC_TYPE_HEADER) {
+			nicvf_put_sq_desc(sq, 1);
+			continue;
+		}
+		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
+		atomic64_add(hdr->tot_len,
+			     (atomic64_t *)&netdev->stats.tx_bytes);
+		dev_kfree_skb_any(skb);
+		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
+	}
+}
+
+/* Calculate no of SQ subdescriptors needed to transmit all
+ * segments of this TSO packet.
+ * Taken from 'Tilera network driver' with a minor modification.
+ */
+static int nicvf_tso_count_subdescs(struct sk_buff *skb)
+{
+	struct skb_shared_info *sh = skb_shinfo(skb);
+	unsigned int sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	unsigned int data_len = skb->len - sh_len;
+	unsigned int p_len = sh->gso_size;
+	long f_id = -1;    /* id of the current fragment */
+	long f_size = skb_headlen(skb) - sh_len;  /* current fragment size */
+	long f_used = 0;  /* bytes used from the current fragment */
+	long n;            /* size of the current piece of payload */
+	int num_edescs = 0;
+	int segment;
+
+	for (segment = 0; segment < sh->gso_segs; segment++) {
+		unsigned int p_used = 0;
+
+		/* One edesc for header and for each piece of the payload. */
+		for (num_edescs++; p_used < p_len; num_edescs++) {
+			/* Advance as needed. */
+			while (f_used >= f_size) {
+				f_id++;
+				f_size = skb_frag_size(&sh->frags[f_id]);
+				f_used = 0;
+			}
+
+			/* Use bytes from the current fragment. */
+			n = p_len - p_used;
+			if (n > f_size - f_used)
+				n = f_size - f_used;
+			f_used += n;
+			p_used += n;
+		}
+
+		/* The last segment may be less than gso_size. */
+		data_len -= p_len;
+		if (data_len < p_len)
+			p_len = data_len;
+	}
+
+	/* '+ gso_segs' for SQ_HDR_SUDESCs for each segment */
+	return num_edescs + sh->gso_segs;
+}
+
+/* Get the number of SQ descriptors needed to xmit this skb */
+static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb)
+{
+	int subdesc_cnt = MIN_SQ_DESC_PER_PKT_XMIT;
+
+	if (skb_shinfo(skb)->gso_size) {
+		subdesc_cnt = nicvf_tso_count_subdescs(skb);
+		return subdesc_cnt;
+	}
+
+	if (skb_shinfo(skb)->nr_frags)
+		subdesc_cnt += skb_shinfo(skb)->nr_frags;
+
+	return subdesc_cnt;
+}
+
+/* Add SQ HEADER subdescriptor.
+ * First subdescriptor for every send descriptor.
+ */
+static inline void
+nicvf_sq_add_hdr_subdesc(struct snd_queue *sq, int qentry,
+			 int subdesc_cnt, struct sk_buff *skb, int len)
+{
+	int proto;
+	struct sq_hdr_subdesc *hdr;
+
+	hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+	sq->skbuff[qentry] = (u64)skb;
+
+	memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+	hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+	/* Enable notification via CQE after processing SQE */
+	hdr->post_cqe = 1;
+	/* No of subdescriptors following this */
+	hdr->subdesc_cnt = subdesc_cnt;
+	hdr->tot_len = len;
+
+	/* Offload checksum calculation to HW */
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		if (skb->protocol != htons(ETH_P_IP))
+			return;
+
+		hdr->csum_l3 = 1; /* Enable IP csum calculation */
+		hdr->l3_offset = skb_network_offset(skb);
+		hdr->l4_offset = skb_transport_offset(skb);
+
+		proto = ip_hdr(skb)->protocol;
+		switch (proto) {
+		case IPPROTO_TCP:
+			hdr->csum_l4 = SEND_L4_CSUM_TCP;
+			break;
+		case IPPROTO_UDP:
+			hdr->csum_l4 = SEND_L4_CSUM_UDP;
+			break;
+		case IPPROTO_SCTP:
+			hdr->csum_l4 = SEND_L4_CSUM_SCTP;
+			break;
+		}
+	}
+}
+
+/* SQ GATHER subdescriptor
+ * Must follow HDR descriptor
+ */
+static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
+					       int size, u64 data)
+{
+	struct sq_gather_subdesc *gather;
+
+	qentry &= (sq->dmem.q_len - 1);
+	gather = (struct sq_gather_subdesc *)GET_SQ_DESC(sq, qentry);
+
+	memset(gather, 0, SND_QUEUE_DESC_SIZE);
+	gather->subdesc_type = SQ_DESC_TYPE_GATHER;
+	gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+	gather->size = size;
+	gather->addr = data;
+}
+
+/* Segment a TSO packet into 'gso_size' segments and append
+ * them to SQ for transfer
+ */
+static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
+			       int qentry, struct sk_buff *skb)
+{
+	struct tso_t tso;
+	int seg_subdescs = 0, desc_cnt = 0;
+	int seg_len, total_len, data_left;
+	int hdr_qentry = qentry;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	tso_start(skb, &tso);
+	total_len = skb->len - hdr_len;
+	while (total_len > 0) {
+		char *hdr;
+
+		/* Save Qentry for adding HDR_SUBDESC at the end */
+		hdr_qentry = qentry;
+
+		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
+		total_len -= data_left;
+
+		/* Add segment's header */
+		qentry = nicvf_get_nxt_sqentry(sq, qentry);
+		hdr = sq->tso_hdrs + qentry * TSO_HEADER_SIZE;
+		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
+		nicvf_sq_add_gather_subdesc(sq, qentry, hdr_len,
+					    sq->tso_hdrs_phys +
+					    qentry * TSO_HEADER_SIZE);
+		/* HDR_SUDESC + GATHER */
+		seg_subdescs = 2;
+		seg_len = hdr_len;
+
+		/* Add segment's payload fragments */
+		while (data_left > 0) {
+			int size;
+
+			size = min_t(int, tso.size, data_left);
+
+			qentry = nicvf_get_nxt_sqentry(sq, qentry);
+			nicvf_sq_add_gather_subdesc(sq, qentry, size,
+						    virt_to_phys(tso.data));
+			seg_subdescs++;
+			seg_len += size;
+
+			data_left -= size;
+			tso_build_data(skb, &tso, size);
+		}
+		nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
+					 seg_subdescs - 1, skb, seg_len);
+		sq->skbuff[hdr_qentry] = 0;
+		qentry = nicvf_get_nxt_sqentry(sq, qentry);
+
+		desc_cnt += seg_subdescs;
+	}
+	/* Save SKB in the last segment for freeing */
+	sq->skbuff[hdr_qentry] = (u64)skb;
+
+	/* make sure all memory stores are done before ringing doorbell */
+	smp_wmb();
+
+	/* Inform HW to xmit all TSO segments */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
+			      skb_get_queue_mapping(skb), desc_cnt);
+	return 1;
+}
+
+/* Append an skb to a SQ for packet transfer. */
+int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
+{
+	int i, size;
+	int subdesc_cnt;
+	int sq_num, qentry;
+	struct queue_set *qs = nic->qs;
+	struct snd_queue *sq;
+
+	sq_num = skb_get_queue_mapping(skb);
+	sq = &qs->sq[sq_num];
+
+	subdesc_cnt = nicvf_sq_subdesc_required(nic, skb);
+	if (subdesc_cnt > atomic_read(&sq->free_cnt))
+		goto append_fail;
+
+	qentry = nicvf_get_sq_desc(sq, subdesc_cnt);
+
+	/* Check if its a TSO packet */
+	if (skb_shinfo(skb)->gso_size)
+		return nicvf_sq_append_tso(nic, sq, qentry, skb);
+
+	/* Add SQ header subdesc */
+	nicvf_sq_add_hdr_subdesc(sq, qentry, subdesc_cnt - 1, skb, skb->len);
+
+	/* Add SQ gather subdescs */
+	qentry = nicvf_get_nxt_sqentry(sq, qentry);
+	size = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len;
+	nicvf_sq_add_gather_subdesc(sq, qentry, size, virt_to_phys(skb->data));
+
+	/* Check for scattered buffer */
+	if (!skb_is_nonlinear(skb))
+		goto doorbell;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		const struct skb_frag_struct *frag;
+
+		frag = &skb_shinfo(skb)->frags[i];
+
+		qentry = nicvf_get_nxt_sqentry(sq, qentry);
+		size = skb_frag_size(frag);
+		nicvf_sq_add_gather_subdesc(sq, qentry, size,
+					    virt_to_phys(
+					    skb_frag_address(frag)));
+	}
+
+doorbell:
+	/* make sure all memory stores are done before ringing doorbell */
+	smp_wmb();
+
+	/* Inform HW to xmit new packet */
+	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
+			      sq_num, subdesc_cnt);
+	return 1;
+
+append_fail:
+	netdev_dbg(nic->netdev, "Not enough SQ descriptors to xmit pkt\n");
+	return 0;
+}
+
+static inline unsigned frag_num(unsigned i)
+{
+#ifdef __BIG_ENDIAN
+	return (i & ~3) + 3 - (i & 3);
+#else
+	return i;
+#endif
+}
+
+/* Returns SKB for a received packet */
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
+{
+	int frag;
+	int payload_len = 0;
+	struct sk_buff *skb = NULL;
+	struct sk_buff *skb_frag = NULL;
+	struct sk_buff *prev_frag = NULL;
+	u16 *rb_lens = NULL;
+	u64 *rb_ptrs = NULL;
+
+	rb_lens = (void *)cqe_rx + (3 * sizeof(u64));
+	rb_ptrs = (void *)cqe_rx + (6 * sizeof(u64));
+
+	netdev_dbg(nic->netdev, "%s rb_cnt %d rb0_ptr %llx rb0_sz %d\n",
+		   __func__, cqe_rx->rb_cnt, cqe_rx->rb0_ptr, cqe_rx->rb0_sz);
+
+	for (frag = 0; frag < cqe_rx->rb_cnt; frag++) {
+		payload_len = rb_lens[frag_num(frag)];
+		if (!frag) {
+			/* First fragment */
+			skb = nicvf_rb_ptr_to_skb(nic,
+						  *rb_ptrs - cqe_rx->align_pad,
+						  payload_len);
+			if (!skb)
+				return NULL;
+			skb_reserve(skb, cqe_rx->align_pad);
+			skb_put(skb, payload_len);
+		} else {
+			/* Add fragments */
+			skb_frag = nicvf_rb_ptr_to_skb(nic, *rb_ptrs,
+						       payload_len);
+			if (!skb_frag) {
+				dev_kfree_skb(skb);
+				return NULL;
+			}
+
+			if (!skb_shinfo(skb)->frag_list)
+				skb_shinfo(skb)->frag_list = skb_frag;
+			else
+				prev_frag->next = skb_frag;
+
+			prev_frag = skb_frag;
+			skb->len += payload_len;
+			skb->data_len += payload_len;
+			skb_frag->len = payload_len;
+		}
+		/* Next buffer pointer */
+		rb_ptrs++;
+	}
+	return skb;
+}
+
+/* Enable interrupt */
+void nicvf_enable_intr(struct nicvf *nic, int int_type, int q_idx)
+{
+	u64 reg_val;
+
+	reg_val = nicvf_reg_read(nic, NIC_VF_ENA_W1S);
+
+	switch (int_type) {
+	case NICVF_INTR_CQ:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT);
+		break;
+	case NICVF_INTR_SQ:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT);
+		break;
+	case NICVF_INTR_RBDR:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT);
+		break;
+	case NICVF_INTR_PKT_DROP:
+		reg_val |= (1ULL << NICVF_INTR_PKT_DROP_SHIFT);
+		break;
+	case NICVF_INTR_TCP_TIMER:
+		reg_val |= (1ULL << NICVF_INTR_TCP_TIMER_SHIFT);
+		break;
+	case NICVF_INTR_MBOX:
+		reg_val |= (1ULL << NICVF_INTR_MBOX_SHIFT);
+		break;
+	case NICVF_INTR_QS_ERR:
+		reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT);
+		break;
+	default:
+		netdev_err(nic->netdev,
+			   "Failed to enable interrupt: unknown type\n");
+		break;
+	}
+
+	nicvf_reg_write(nic, NIC_VF_ENA_W1S, reg_val);
+}
+
+/* Disable interrupt */
+void nicvf_disable_intr(struct nicvf *nic, int int_type, int q_idx)
+{
+	u64 reg_val = 0;
+
+	switch (int_type) {
+	case NICVF_INTR_CQ:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT);
+		break;
+	case NICVF_INTR_SQ:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT);
+		break;
+	case NICVF_INTR_RBDR:
+		reg_val |= ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT);
+		break;
+	case NICVF_INTR_PKT_DROP:
+		reg_val |= (1ULL << NICVF_INTR_PKT_DROP_SHIFT);
+		break;
+	case NICVF_INTR_TCP_TIMER:
+		reg_val |= (1ULL << NICVF_INTR_TCP_TIMER_SHIFT);
+		break;
+	case NICVF_INTR_MBOX:
+		reg_val |= (1ULL << NICVF_INTR_MBOX_SHIFT);
+		break;
+	case NICVF_INTR_QS_ERR:
+		reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT);
+		break;
+	default:
+		netdev_err(nic->netdev,
+			   "Failed to disable interrupt: unknown type\n");
+		break;
+	}
+
+	nicvf_reg_write(nic, NIC_VF_ENA_W1C, reg_val);
+}
+
+/* Clear interrupt */
+void nicvf_clear_intr(struct nicvf *nic, int int_type, int q_idx)
+{
+	u64 reg_val = 0;
+
+	switch (int_type) {
+	case NICVF_INTR_CQ:
+		reg_val = ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT);
+		break;
+	case NICVF_INTR_SQ:
+		reg_val = ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT);
+		break;
+	case NICVF_INTR_RBDR:
+		reg_val = ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT);
+		break;
+	case NICVF_INTR_PKT_DROP:
+		reg_val = (1ULL << NICVF_INTR_PKT_DROP_SHIFT);
+		break;
+	case NICVF_INTR_TCP_TIMER:
+		reg_val = (1ULL << NICVF_INTR_TCP_TIMER_SHIFT);
+		break;
+	case NICVF_INTR_MBOX:
+		reg_val = (1ULL << NICVF_INTR_MBOX_SHIFT);
+		break;
+	case NICVF_INTR_QS_ERR:
+		reg_val |= (1ULL << NICVF_INTR_QS_ERR_SHIFT);
+		break;
+	default:
+		netdev_err(nic->netdev,
+			   "Failed to clear interrupt: unknown type\n");
+		break;
+	}
+
+	nicvf_reg_write(nic, NIC_VF_INT, reg_val);
+}
+
+/* Check if interrupt is enabled */
+int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx)
+{
+	u64 reg_val;
+	u64 mask = 0xff;
+
+	reg_val = nicvf_reg_read(nic, NIC_VF_ENA_W1S);
+
+	switch (int_type) {
+	case NICVF_INTR_CQ:
+		mask = ((1ULL << q_idx) << NICVF_INTR_CQ_SHIFT);
+		break;
+	case NICVF_INTR_SQ:
+		mask = ((1ULL << q_idx) << NICVF_INTR_SQ_SHIFT);
+		break;
+	case NICVF_INTR_RBDR:
+		mask = ((1ULL << q_idx) << NICVF_INTR_RBDR_SHIFT);
+		break;
+	case NICVF_INTR_PKT_DROP:
+		mask = NICVF_INTR_PKT_DROP_MASK;
+		break;
+	case NICVF_INTR_TCP_TIMER:
+		mask = NICVF_INTR_TCP_TIMER_MASK;
+		break;
+	case NICVF_INTR_MBOX:
+		mask = NICVF_INTR_MBOX_MASK;
+		break;
+	case NICVF_INTR_QS_ERR:
+		mask = NICVF_INTR_QS_ERR_MASK;
+		break;
+	default:
+		netdev_err(nic->netdev,
+			   "Failed to check interrupt enable: unknown type\n");
+		break;
+	}
+
+	return (reg_val & mask);
+}
+
+void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx)
+{
+	struct rcv_queue *rq;
+
+#define GET_RQ_STATS(reg) \
+	nicvf_reg_read(nic, NIC_QSET_RQ_0_7_STAT_0_1 |\
+			    (rq_idx << NIC_Q_NUM_SHIFT) | (reg << 3))
+
+	rq = &nic->qs->rq[rq_idx];
+	rq->stats.bytes = GET_RQ_STATS(RQ_SQ_STATS_OCTS);
+	rq->stats.pkts = GET_RQ_STATS(RQ_SQ_STATS_PKTS);
+}
+
+void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
+{
+	struct snd_queue *sq;
+
+#define GET_SQ_STATS(reg) \
+	nicvf_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1 |\
+			    (sq_idx << NIC_Q_NUM_SHIFT) | (reg << 3))
+
+	sq = &nic->qs->sq[sq_idx];
+	sq->stats.bytes = GET_SQ_STATS(RQ_SQ_STATS_OCTS);
+	sq->stats.pkts = GET_SQ_STATS(RQ_SQ_STATS_PKTS);
+}
+
+/* Check for errors in the receive cmp.queue entry */
+int nicvf_check_cqe_rx_errs(struct nicvf *nic,
+			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx)
+{
+	struct cmp_queue_stats *stats = &cq->stats;
+
+	if (!cqe_rx->err_level && !cqe_rx->err_opcode) {
+		stats->rx.errop.good++;
+		return 0;
+	}
+
+	if (netif_msg_rx_err(nic))
+		netdev_err(nic->netdev,
+			   "%s: RX error CQE err_level 0x%x err_opcode 0x%x\n",
+			   nic->netdev->name,
+			   cqe_rx->err_level, cqe_rx->err_opcode);
+
+	switch (cqe_rx->err_level) {
+	case CQ_ERRLVL_MAC:
+		stats->rx.errlvl.mac_errs++;
+		break;
+	case CQ_ERRLVL_L2:
+		stats->rx.errlvl.l2_errs++;
+		break;
+	case CQ_ERRLVL_L3:
+		stats->rx.errlvl.l3_errs++;
+		break;
+	case CQ_ERRLVL_L4:
+		stats->rx.errlvl.l4_errs++;
+		break;
+	}
+
+	switch (cqe_rx->err_opcode) {
+	case CQ_RX_ERROP_RE_PARTIAL:
+		stats->rx.errop.partial_pkts++;
+		break;
+	case CQ_RX_ERROP_RE_JABBER:
+		stats->rx.errop.jabber_errs++;
+		break;
+	case CQ_RX_ERROP_RE_FCS:
+		stats->rx.errop.fcs_errs++;
+		break;
+	case CQ_RX_ERROP_RE_TERMINATE:
+		stats->rx.errop.terminate_errs++;
+		break;
+	case CQ_RX_ERROP_RE_RX_CTL:
+		stats->rx.errop.bgx_rx_errs++;
+		break;
+	case CQ_RX_ERROP_PREL2_ERR:
+		stats->rx.errop.prel2_errs++;
+		break;
+	case CQ_RX_ERROP_L2_FRAGMENT:
+		stats->rx.errop.l2_frags++;
+		break;
+	case CQ_RX_ERROP_L2_OVERRUN:
+		stats->rx.errop.l2_overruns++;
+		break;
+	case CQ_RX_ERROP_L2_PFCS:
+		stats->rx.errop.l2_pfcs++;
+		break;
+	case CQ_RX_ERROP_L2_PUNY:
+		stats->rx.errop.l2_puny++;
+		break;
+	case CQ_RX_ERROP_L2_MAL:
+		stats->rx.errop.l2_hdr_malformed++;
+		break;
+	case CQ_RX_ERROP_L2_OVERSIZE:
+		stats->rx.errop.l2_oversize++;
+		break;
+	case CQ_RX_ERROP_L2_UNDERSIZE:
+		stats->rx.errop.l2_undersize++;
+		break;
+	case CQ_RX_ERROP_L2_LENMISM:
+		stats->rx.errop.l2_len_mismatch++;
+		break;
+	case CQ_RX_ERROP_L2_PCLP:
+		stats->rx.errop.l2_pclp++;
+		break;
+	case CQ_RX_ERROP_IP_NOT:
+		stats->rx.errop.non_ip++;
+		break;
+	case CQ_RX_ERROP_IP_CSUM_ERR:
+		stats->rx.errop.ip_csum_err++;
+		break;
+	case CQ_RX_ERROP_IP_MAL:
+		stats->rx.errop.ip_hdr_malformed++;
+		break;
+	case CQ_RX_ERROP_IP_MALD:
+		stats->rx.errop.ip_payload_malformed++;
+		break;
+	case CQ_RX_ERROP_IP_HOP:
+		stats->rx.errop.ip_hop_errs++;
+		break;
+	case CQ_RX_ERROP_L3_ICRC:
+		stats->rx.errop.l3_icrc_errs++;
+		break;
+	case CQ_RX_ERROP_L3_PCLP:
+		stats->rx.errop.l3_pclp++;
+		break;
+	case CQ_RX_ERROP_L4_MAL:
+		stats->rx.errop.l4_malformed++;
+		break;
+	case CQ_RX_ERROP_L4_CHK:
+		stats->rx.errop.l4_csum_errs++;
+		break;
+	case CQ_RX_ERROP_UDP_LEN:
+		stats->rx.errop.udp_len_err++;
+		break;
+	case CQ_RX_ERROP_L4_PORT:
+		stats->rx.errop.bad_l4_port++;
+		break;
+	case CQ_RX_ERROP_TCP_FLAG:
+		stats->rx.errop.bad_tcp_flag++;
+		break;
+	case CQ_RX_ERROP_TCP_OFFSET:
+		stats->rx.errop.tcp_offset_errs++;
+		break;
+	case CQ_RX_ERROP_L4_PCLP:
+		stats->rx.errop.l4_pclp++;
+		break;
+	case CQ_RX_ERROP_RBDR_TRUNC:
+		stats->rx.errop.pkt_truncated++;
+		break;
+	}
+
+	return 1;
+}
+
+/* Check for errors in the send cmp.queue entry */
+int nicvf_check_cqe_tx_errs(struct nicvf *nic,
+			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx)
+{
+	struct cmp_queue_stats *stats = &cq->stats;
+
+	switch (cqe_tx->send_status) {
+	case CQ_TX_ERROP_GOOD:
+		stats->tx.good++;
+		return 0;
+	case CQ_TX_ERROP_DESC_FAULT:
+		stats->tx.desc_fault++;
+		break;
+	case CQ_TX_ERROP_HDR_CONS_ERR:
+		stats->tx.hdr_cons_err++;
+		break;
+	case CQ_TX_ERROP_SUBDC_ERR:
+		stats->tx.subdesc_err++;
+		break;
+	case CQ_TX_ERROP_IMM_SIZE_OFLOW:
+		stats->tx.imm_size_oflow++;
+		break;
+	case CQ_TX_ERROP_DATA_SEQUENCE_ERR:
+		stats->tx.data_seq_err++;
+		break;
+	case CQ_TX_ERROP_MEM_SEQUENCE_ERR:
+		stats->tx.mem_seq_err++;
+		break;
+	case CQ_TX_ERROP_LOCK_VIOL:
+		stats->tx.lock_viol++;
+		break;
+	case CQ_TX_ERROP_DATA_FAULT:
+		stats->tx.data_fault++;
+		break;
+	case CQ_TX_ERROP_TSTMP_CONFLICT:
+		stats->tx.tstmp_conflict++;
+		break;
+	case CQ_TX_ERROP_TSTMP_TIMEOUT:
+		stats->tx.tstmp_timeout++;
+		break;
+	case CQ_TX_ERROP_MEM_FAULT:
+		stats->tx.mem_fault++;
+		break;
+	case CQ_TX_ERROP_CK_OVERLAP:
+		stats->tx.csum_overlap++;
+		break;
+	case CQ_TX_ERROP_CK_OFLOW:
+		stats->tx.csum_overflow++;
+		break;
+	}
+
+	return 1;
+}
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
new file mode 100644
index 000000000000..8341bdf755d1
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -0,0 +1,381 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef NICVF_QUEUES_H
+#define NICVF_QUEUES_H
+
+#include <linux/netdevice.h>
+#include "q_struct.h"
+
+#define MAX_QUEUE_SET			128
+#define MAX_RCV_QUEUES_PER_QS		8
+#define MAX_RCV_BUF_DESC_RINGS_PER_QS	2
+#define MAX_SND_QUEUES_PER_QS		8
+#define MAX_CMP_QUEUES_PER_QS		8
+
+/* VF's queue interrupt ranges */
+#define	NICVF_INTR_ID_CQ		0
+#define	NICVF_INTR_ID_SQ		8
+#define	NICVF_INTR_ID_RBDR		16
+#define	NICVF_INTR_ID_MISC		18
+#define	NICVF_INTR_ID_QS_ERR		19
+
+#define	for_each_cq_irq(irq)	\
+	for (irq = NICVF_INTR_ID_CQ; irq < NICVF_INTR_ID_SQ; irq++)
+#define	for_each_sq_irq(irq)	\
+	for (irq = NICVF_INTR_ID_SQ; irq < NICVF_INTR_ID_RBDR; irq++)
+#define	for_each_rbdr_irq(irq)	\
+	for (irq = NICVF_INTR_ID_RBDR; irq < NICVF_INTR_ID_MISC; irq++)
+
+#define RBDR_SIZE0		0ULL /* 8K entries */
+#define RBDR_SIZE1		1ULL /* 16K entries */
+#define RBDR_SIZE2		2ULL /* 32K entries */
+#define RBDR_SIZE3		3ULL /* 64K entries */
+#define RBDR_SIZE4		4ULL /* 126K entries */
+#define RBDR_SIZE5		5ULL /* 256K entries */
+#define RBDR_SIZE6		6ULL /* 512K entries */
+
+#define SND_QUEUE_SIZE0		0ULL /* 1K entries */
+#define SND_QUEUE_SIZE1		1ULL /* 2K entries */
+#define SND_QUEUE_SIZE2		2ULL /* 4K entries */
+#define SND_QUEUE_SIZE3		3ULL /* 8K entries */
+#define SND_QUEUE_SIZE4		4ULL /* 16K entries */
+#define SND_QUEUE_SIZE5		5ULL /* 32K entries */
+#define SND_QUEUE_SIZE6		6ULL /* 64K entries */
+
+#define CMP_QUEUE_SIZE0		0ULL /* 1K entries */
+#define CMP_QUEUE_SIZE1		1ULL /* 2K entries */
+#define CMP_QUEUE_SIZE2		2ULL /* 4K entries */
+#define CMP_QUEUE_SIZE3		3ULL /* 8K entries */
+#define CMP_QUEUE_SIZE4		4ULL /* 16K entries */
+#define CMP_QUEUE_SIZE5		5ULL /* 32K entries */
+#define CMP_QUEUE_SIZE6		6ULL /* 64K entries */
+
+/* Default queue count per QS, its lengths and threshold values */
+#define RBDR_CNT		1
+#define RCV_QUEUE_CNT		8
+#define SND_QUEUE_CNT		8
+#define CMP_QUEUE_CNT		8 /* Max of RCV and SND qcount */
+
+#define SND_QSIZE		SND_QUEUE_SIZE4
+#define SND_QUEUE_LEN		(1ULL << (SND_QSIZE + 10))
+#define MAX_SND_QUEUE_LEN	(1ULL << (SND_QUEUE_SIZE6 + 10))
+#define SND_QUEUE_THRESH	2ULL
+#define MIN_SQ_DESC_PER_PKT_XMIT	2
+/* Since timestamp not enabled, otherwise 2 */
+#define MAX_CQE_PER_PKT_XMIT		1
+
+#define CMP_QSIZE		CMP_QUEUE_SIZE4
+#define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
+#define CMP_QUEUE_CQE_THRESH	0
+#define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
+
+#define RBDR_SIZE		RBDR_SIZE0
+#define RCV_BUF_COUNT		(1ULL << (RBDR_SIZE + 13))
+#define MAX_RCV_BUF_COUNT	(1ULL << (RBDR_SIZE6 + 13))
+#define RBDR_THRESH		(RCV_BUF_COUNT / 2)
+#define DMA_BUFFER_LEN		2048 /* In multiples of 128bytes */
+#define RCV_FRAG_LEN	(SKB_DATA_ALIGN(DMA_BUFFER_LEN + NET_SKB_PAD) + \
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + \
+			 (NICVF_RCV_BUF_ALIGN_BYTES * 2))
+#define RCV_DATA_OFFSET		NICVF_RCV_BUF_ALIGN_BYTES
+
+#define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
+				 MAX_CQE_PER_PKT_XMIT)
+#define RQ_CQ_DROP		((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+
+/* Descriptor size in bytes */
+#define SND_QUEUE_DESC_SIZE	16
+#define CMP_QUEUE_DESC_SIZE	512
+
+/* Buffer / descriptor alignments */
+#define NICVF_RCV_BUF_ALIGN		7
+#define NICVF_RCV_BUF_ALIGN_BYTES	(1ULL << NICVF_RCV_BUF_ALIGN)
+#define NICVF_CQ_BASE_ALIGN_BYTES	512  /* 9 bits */
+#define NICVF_SQ_BASE_ALIGN_BYTES	128  /* 7 bits */
+
+#define NICVF_ALIGNED_ADDR(ADDR, ALIGN_BYTES)	ALIGN(ADDR, ALIGN_BYTES)
+#define NICVF_ADDR_ALIGN_LEN(ADDR, BYTES)\
+	(NICVF_ALIGNED_ADDR(ADDR, BYTES) - BYTES)
+#define NICVF_RCV_BUF_ALIGN_LEN(X)\
+	(NICVF_ALIGNED_ADDR(X, NICVF_RCV_BUF_ALIGN_BYTES) - X)
+
+/* Queue enable/disable */
+#define NICVF_SQ_EN		BIT_ULL(19)
+
+/* Queue reset */
+#define NICVF_CQ_RESET		BIT_ULL(41)
+#define NICVF_SQ_RESET		BIT_ULL(17)
+#define NICVF_RBDR_RESET	BIT_ULL(43)
+
+enum CQ_RX_ERRLVL_E {
+	CQ_ERRLVL_MAC,
+	CQ_ERRLVL_L2,
+	CQ_ERRLVL_L3,
+	CQ_ERRLVL_L4,
+};
+
+enum CQ_RX_ERROP_E {
+	CQ_RX_ERROP_RE_NONE = 0x0,
+	CQ_RX_ERROP_RE_PARTIAL = 0x1,
+	CQ_RX_ERROP_RE_JABBER = 0x2,
+	CQ_RX_ERROP_RE_FCS = 0x7,
+	CQ_RX_ERROP_RE_TERMINATE = 0x9,
+	CQ_RX_ERROP_RE_RX_CTL = 0xb,
+	CQ_RX_ERROP_PREL2_ERR = 0x1f,
+	CQ_RX_ERROP_L2_FRAGMENT = 0x20,
+	CQ_RX_ERROP_L2_OVERRUN = 0x21,
+	CQ_RX_ERROP_L2_PFCS = 0x22,
+	CQ_RX_ERROP_L2_PUNY = 0x23,
+	CQ_RX_ERROP_L2_MAL = 0x24,
+	CQ_RX_ERROP_L2_OVERSIZE = 0x25,
+	CQ_RX_ERROP_L2_UNDERSIZE = 0x26,
+	CQ_RX_ERROP_L2_LENMISM = 0x27,
+	CQ_RX_ERROP_L2_PCLP = 0x28,
+	CQ_RX_ERROP_IP_NOT = 0x41,
+	CQ_RX_ERROP_IP_CSUM_ERR = 0x42,
+	CQ_RX_ERROP_IP_MAL = 0x43,
+	CQ_RX_ERROP_IP_MALD = 0x44,
+	CQ_RX_ERROP_IP_HOP = 0x45,
+	CQ_RX_ERROP_L3_ICRC = 0x46,
+	CQ_RX_ERROP_L3_PCLP = 0x47,
+	CQ_RX_ERROP_L4_MAL = 0x61,
+	CQ_RX_ERROP_L4_CHK = 0x62,
+	CQ_RX_ERROP_UDP_LEN = 0x63,
+	CQ_RX_ERROP_L4_PORT = 0x64,
+	CQ_RX_ERROP_TCP_FLAG = 0x65,
+	CQ_RX_ERROP_TCP_OFFSET = 0x66,
+	CQ_RX_ERROP_L4_PCLP = 0x67,
+	CQ_RX_ERROP_RBDR_TRUNC = 0x70,
+};
+
+enum CQ_TX_ERROP_E {
+	CQ_TX_ERROP_GOOD = 0x0,
+	CQ_TX_ERROP_DESC_FAULT = 0x10,
+	CQ_TX_ERROP_HDR_CONS_ERR = 0x11,
+	CQ_TX_ERROP_SUBDC_ERR = 0x12,
+	CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80,
+	CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81,
+	CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82,
+	CQ_TX_ERROP_LOCK_VIOL = 0x83,
+	CQ_TX_ERROP_DATA_FAULT = 0x84,
+	CQ_TX_ERROP_TSTMP_CONFLICT = 0x85,
+	CQ_TX_ERROP_TSTMP_TIMEOUT = 0x86,
+	CQ_TX_ERROP_MEM_FAULT = 0x87,
+	CQ_TX_ERROP_CK_OVERLAP = 0x88,
+	CQ_TX_ERROP_CK_OFLOW = 0x89,
+	CQ_TX_ERROP_ENUM_LAST = 0x8a,
+};
+
+struct cmp_queue_stats {
+	struct rx_stats {
+		struct {
+			u64 mac_errs;
+			u64 l2_errs;
+			u64 l3_errs;
+			u64 l4_errs;
+		} errlvl;
+		struct {
+			u64 good;
+			u64 partial_pkts;
+			u64 jabber_errs;
+			u64 fcs_errs;
+			u64 terminate_errs;
+			u64 bgx_rx_errs;
+			u64 prel2_errs;
+			u64 l2_frags;
+			u64 l2_overruns;
+			u64 l2_pfcs;
+			u64 l2_puny;
+			u64 l2_hdr_malformed;
+			u64 l2_oversize;
+			u64 l2_undersize;
+			u64 l2_len_mismatch;
+			u64 l2_pclp;
+			u64 non_ip;
+			u64 ip_csum_err;
+			u64 ip_hdr_malformed;
+			u64 ip_payload_malformed;
+			u64 ip_hop_errs;
+			u64 l3_icrc_errs;
+			u64 l3_pclp;
+			u64 l4_malformed;
+			u64 l4_csum_errs;
+			u64 udp_len_err;
+			u64 bad_l4_port;
+			u64 bad_tcp_flag;
+			u64 tcp_offset_errs;
+			u64 l4_pclp;
+			u64 pkt_truncated;
+		} errop;
+	} rx;
+	struct tx_stats {
+		u64 good;
+		u64 desc_fault;
+		u64 hdr_cons_err;
+		u64 subdesc_err;
+		u64 imm_size_oflow;
+		u64 data_seq_err;
+		u64 mem_seq_err;
+		u64 lock_viol;
+		u64 data_fault;
+		u64 tstmp_conflict;
+		u64 tstmp_timeout;
+		u64 mem_fault;
+		u64 csum_overlap;
+		u64 csum_overflow;
+	} tx;
+} ____cacheline_aligned_in_smp;
+
+enum RQ_SQ_STATS {
+	RQ_SQ_STATS_OCTS,
+	RQ_SQ_STATS_PKTS,
+};
+
+struct rx_tx_queue_stats {
+	u64	bytes;
+	u64	pkts;
+} ____cacheline_aligned_in_smp;
+
+struct q_desc_mem {
+	dma_addr_t	dma;
+	u64		size;
+	u16		q_len;
+	dma_addr_t	phys_base;
+	void		*base;
+	void		*unalign_base;
+};
+
+struct rbdr {
+	bool		enable;
+	u32		dma_size;
+	u32		frag_len;
+	u32		thresh;		/* Threshold level for interrupt */
+	void		*desc;
+	u32		head;
+	u32		tail;
+	struct q_desc_mem   dmem;
+} ____cacheline_aligned_in_smp;
+
+struct rcv_queue {
+	bool		enable;
+	struct	rbdr	*rbdr_start;
+	struct	rbdr	*rbdr_cont;
+	bool		en_tcp_reassembly;
+	u8		cq_qs;  /* CQ's QS to which this RQ is assigned */
+	u8		cq_idx; /* CQ index (0 to 7) in the QS */
+	u8		cont_rbdr_qs;      /* Continue buffer ptrs - QS num */
+	u8		cont_qs_rbdr_idx;  /* RBDR idx in the cont QS */
+	u8		start_rbdr_qs;     /* First buffer ptrs - QS num */
+	u8		start_qs_rbdr_idx; /* RBDR idx in the above QS */
+	u8		caching;
+	struct		rx_tx_queue_stats stats;
+} ____cacheline_aligned_in_smp;
+
+struct cmp_queue {
+	bool		enable;
+	u16		thresh;
+	spinlock_t	lock;  /* lock to serialize processing CQEs */
+	void		*desc;
+	struct q_desc_mem   dmem;
+	struct cmp_queue_stats	stats;
+} ____cacheline_aligned_in_smp;
+
+struct snd_queue {
+	bool		enable;
+	u8		cq_qs;  /* CQ's QS to which this SQ is pointing */
+	u8		cq_idx; /* CQ index (0 to 7) in the above QS */
+	u16		thresh;
+	atomic_t	free_cnt;
+	u32		head;
+	u32		tail;
+	u64		*skbuff;
+	void		*desc;
+
+#define	TSO_HEADER_SIZE	128
+	/* For TSO segment's header */
+	char		*tso_hdrs;
+	dma_addr_t	tso_hdrs_phys;
+
+	cpumask_t	affinity_mask;
+	struct q_desc_mem   dmem;
+	struct rx_tx_queue_stats stats;
+} ____cacheline_aligned_in_smp;
+
+struct queue_set {
+	bool		enable;
+	bool		be_en;
+	u8		vnic_id;
+	u8		rq_cnt;
+	u8		cq_cnt;
+	u64		cq_len;
+	u8		sq_cnt;
+	u64		sq_len;
+	u8		rbdr_cnt;
+	u64		rbdr_len;
+	struct	rcv_queue	rq[MAX_RCV_QUEUES_PER_QS];
+	struct	cmp_queue	cq[MAX_CMP_QUEUES_PER_QS];
+	struct	snd_queue	sq[MAX_SND_QUEUES_PER_QS];
+	struct	rbdr		rbdr[MAX_RCV_BUF_DESC_RINGS_PER_QS];
+} ____cacheline_aligned_in_smp;
+
+#define GET_RBDR_DESC(RING, idx)\
+		(&(((struct rbdr_entry_t *)((RING)->desc))[idx]))
+#define GET_SQ_DESC(RING, idx)\
+		(&(((struct sq_hdr_subdesc *)((RING)->desc))[idx]))
+#define GET_CQ_DESC(RING, idx)\
+		(&(((union cq_desc_t *)((RING)->desc))[idx]))
+
+/* CQ status bits */
+#define	CQ_WR_FULL	BIT(26)
+#define	CQ_WR_DISABLE	BIT(25)
+#define	CQ_WR_FAULT	BIT(24)
+#define	CQ_CQE_COUNT	(0xFFFF << 0)
+
+#define	CQ_ERR_MASK	(CQ_WR_FULL | CQ_WR_DISABLE | CQ_WR_FAULT)
+
+int nicvf_set_qset_resources(struct nicvf *nic);
+int nicvf_config_data_transfer(struct nicvf *nic, bool enable);
+void nicvf_qset_config(struct nicvf *nic, bool enable);
+void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
+			    int qidx, bool enable);
+
+void nicvf_sq_enable(struct nicvf *nic, struct snd_queue *sq, int qidx);
+void nicvf_sq_disable(struct nicvf *nic, int qidx);
+void nicvf_put_sq_desc(struct snd_queue *sq, int desc_cnt);
+void nicvf_sq_free_used_descs(struct net_device *netdev,
+			      struct snd_queue *sq, int qidx);
+int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb);
+
+struct sk_buff *nicvf_get_rcv_skb(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
+void nicvf_rbdr_task(unsigned long data);
+void nicvf_rbdr_work(struct work_struct *work);
+
+void nicvf_enable_intr(struct nicvf *nic, int int_type, int q_idx);
+void nicvf_disable_intr(struct nicvf *nic, int int_type, int q_idx);
+void nicvf_clear_intr(struct nicvf *nic, int int_type, int q_idx);
+int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx);
+
+/* Register access APIs */
+void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val);
+u64  nicvf_reg_read(struct nicvf *nic, u64 offset);
+void nicvf_qset_reg_write(struct nicvf *nic, u64 offset, u64 val);
+u64 nicvf_qset_reg_read(struct nicvf *nic, u64 offset);
+void nicvf_queue_reg_write(struct nicvf *nic, u64 offset,
+			   u64 qidx, u64 val);
+u64  nicvf_queue_reg_read(struct nicvf *nic,
+			  u64 offset, u64 qidx);
+
+/* Stats */
+void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
+void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
+int nicvf_check_cqe_rx_errs(struct nicvf *nic,
+			    struct cmp_queue *cq, struct cqe_rx_t *cqe_rx);
+int nicvf_check_cqe_tx_errs(struct nicvf *nic,
+			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
+#endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/cavium/thunder/q_struct.h b/drivers/net/ethernet/cavium/thunder/q_struct.h
new file mode 100644
index 000000000000..3c1de97b1add
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/q_struct.h
@@ -0,0 +1,701 @@
+/*
+ * This file contains HW queue descriptor formats, config register
+ * structures etc
+ *
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef Q_STRUCT_H
+#define Q_STRUCT_H
+
+/* Load transaction types for reading segment bytes specified by
+ * NIC_SEND_GATHER_S[LD_TYPE].
+ */
+enum nic_send_ld_type_e {
+	NIC_SEND_LD_TYPE_E_LDD = 0x0,
+	NIC_SEND_LD_TYPE_E_LDT = 0x1,
+	NIC_SEND_LD_TYPE_E_LDWB = 0x2,
+	NIC_SEND_LD_TYPE_E_ENUM_LAST = 0x3,
+};
+
+enum ether_type_algorithm {
+	ETYPE_ALG_NONE = 0x0,
+	ETYPE_ALG_SKIP = 0x1,
+	ETYPE_ALG_ENDPARSE = 0x2,
+	ETYPE_ALG_VLAN = 0x3,
+	ETYPE_ALG_VLAN_STRIP = 0x4,
+};
+
+enum layer3_type {
+	L3TYPE_NONE = 0x00,
+	L3TYPE_GRH = 0x01,
+	L3TYPE_IPV4 = 0x04,
+	L3TYPE_IPV4_OPTIONS = 0x05,
+	L3TYPE_IPV6 = 0x06,
+	L3TYPE_IPV6_OPTIONS = 0x07,
+	L3TYPE_ET_STOP = 0x0D,
+	L3TYPE_OTHER = 0x0E,
+};
+
+enum layer4_type {
+	L4TYPE_NONE = 0x00,
+	L4TYPE_IPSEC_ESP = 0x01,
+	L4TYPE_IPFRAG = 0x02,
+	L4TYPE_IPCOMP = 0x03,
+	L4TYPE_TCP = 0x04,
+	L4TYPE_UDP = 0x05,
+	L4TYPE_SCTP = 0x06,
+	L4TYPE_GRE = 0x07,
+	L4TYPE_ROCE_BTH = 0x08,
+	L4TYPE_OTHER = 0x0E,
+};
+
+/* CPI and RSSI configuration */
+enum cpi_algorithm_type {
+	CPI_ALG_NONE = 0x0,
+	CPI_ALG_VLAN = 0x1,
+	CPI_ALG_VLAN16 = 0x2,
+	CPI_ALG_DIFF = 0x3,
+};
+
+enum rss_algorithm_type {
+	RSS_ALG_NONE = 0x00,
+	RSS_ALG_PORT = 0x01,
+	RSS_ALG_IP = 0x02,
+	RSS_ALG_TCP_IP = 0x03,
+	RSS_ALG_UDP_IP = 0x04,
+	RSS_ALG_SCTP_IP = 0x05,
+	RSS_ALG_GRE_IP = 0x06,
+	RSS_ALG_ROCE = 0x07,
+};
+
+enum rss_hash_cfg {
+	RSS_HASH_L2ETC = 0x00,
+	RSS_HASH_IP = 0x01,
+	RSS_HASH_TCP = 0x02,
+	RSS_HASH_TCP_SYN_DIS = 0x03,
+	RSS_HASH_UDP = 0x04,
+	RSS_HASH_L4ETC = 0x05,
+	RSS_HASH_ROCE = 0x06,
+	RSS_L3_BIDI = 0x07,
+	RSS_L4_BIDI = 0x08,
+};
+
+/* Completion queue entry types */
+enum cqe_type {
+	CQE_TYPE_INVALID = 0x0,
+	CQE_TYPE_RX = 0x2,
+	CQE_TYPE_RX_SPLIT = 0x3,
+	CQE_TYPE_RX_TCP = 0x4,
+	CQE_TYPE_SEND = 0x8,
+	CQE_TYPE_SEND_PTP = 0x9,
+};
+
+enum cqe_rx_tcp_status {
+	CQE_RX_STATUS_VALID_TCP_CNXT = 0x00,
+	CQE_RX_STATUS_INVALID_TCP_CNXT = 0x0F,
+};
+
+enum cqe_send_status {
+	CQE_SEND_STATUS_GOOD = 0x00,
+	CQE_SEND_STATUS_DESC_FAULT = 0x01,
+	CQE_SEND_STATUS_HDR_CONS_ERR = 0x11,
+	CQE_SEND_STATUS_SUBDESC_ERR = 0x12,
+	CQE_SEND_STATUS_IMM_SIZE_OFLOW = 0x80,
+	CQE_SEND_STATUS_CRC_SEQ_ERR = 0x81,
+	CQE_SEND_STATUS_DATA_SEQ_ERR = 0x82,
+	CQE_SEND_STATUS_MEM_SEQ_ERR = 0x83,
+	CQE_SEND_STATUS_LOCK_VIOL = 0x84,
+	CQE_SEND_STATUS_LOCK_UFLOW = 0x85,
+	CQE_SEND_STATUS_DATA_FAULT = 0x86,
+	CQE_SEND_STATUS_TSTMP_CONFLICT = 0x87,
+	CQE_SEND_STATUS_TSTMP_TIMEOUT = 0x88,
+	CQE_SEND_STATUS_MEM_FAULT = 0x89,
+	CQE_SEND_STATUS_CSUM_OVERLAP = 0x8A,
+	CQE_SEND_STATUS_CSUM_OVERFLOW = 0x8B,
+};
+
+enum cqe_rx_tcp_end_reason {
+	CQE_RX_TCP_END_FIN_FLAG_DET = 0,
+	CQE_RX_TCP_END_INVALID_FLAG = 1,
+	CQE_RX_TCP_END_TIMEOUT = 2,
+	CQE_RX_TCP_END_OUT_OF_SEQ = 3,
+	CQE_RX_TCP_END_PKT_ERR = 4,
+	CQE_RX_TCP_END_QS_DISABLED = 0x0F,
+};
+
+/* Packet protocol level error enumeration */
+enum cqe_rx_err_level {
+	CQE_RX_ERRLVL_RE = 0x0,
+	CQE_RX_ERRLVL_L2 = 0x1,
+	CQE_RX_ERRLVL_L3 = 0x2,
+	CQE_RX_ERRLVL_L4 = 0x3,
+};
+
+/* Packet protocol level error type enumeration */
+enum cqe_rx_err_opcode {
+	CQE_RX_ERR_RE_NONE = 0x0,
+	CQE_RX_ERR_RE_PARTIAL = 0x1,
+	CQE_RX_ERR_RE_JABBER = 0x2,
+	CQE_RX_ERR_RE_FCS = 0x7,
+	CQE_RX_ERR_RE_TERMINATE = 0x9,
+	CQE_RX_ERR_RE_RX_CTL = 0xb,
+	CQE_RX_ERR_PREL2_ERR = 0x1f,
+	CQE_RX_ERR_L2_FRAGMENT = 0x20,
+	CQE_RX_ERR_L2_OVERRUN = 0x21,
+	CQE_RX_ERR_L2_PFCS = 0x22,
+	CQE_RX_ERR_L2_PUNY = 0x23,
+	CQE_RX_ERR_L2_MAL = 0x24,
+	CQE_RX_ERR_L2_OVERSIZE = 0x25,
+	CQE_RX_ERR_L2_UNDERSIZE = 0x26,
+	CQE_RX_ERR_L2_LENMISM = 0x27,
+	CQE_RX_ERR_L2_PCLP = 0x28,
+	CQE_RX_ERR_IP_NOT = 0x41,
+	CQE_RX_ERR_IP_CHK = 0x42,
+	CQE_RX_ERR_IP_MAL = 0x43,
+	CQE_RX_ERR_IP_MALD = 0x44,
+	CQE_RX_ERR_IP_HOP = 0x45,
+	CQE_RX_ERR_L3_ICRC = 0x46,
+	CQE_RX_ERR_L3_PCLP = 0x47,
+	CQE_RX_ERR_L4_MAL = 0x61,
+	CQE_RX_ERR_L4_CHK = 0x62,
+	CQE_RX_ERR_UDP_LEN = 0x63,
+	CQE_RX_ERR_L4_PORT = 0x64,
+	CQE_RX_ERR_TCP_FLAG = 0x65,
+	CQE_RX_ERR_TCP_OFFSET = 0x66,
+	CQE_RX_ERR_L4_PCLP = 0x67,
+	CQE_RX_ERR_RBDR_TRUNC = 0x70,
+};
+
+struct cqe_rx_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   cqe_type:4; /* W0 */
+	u64   stdn_fault:1;
+	u64   rsvd0:1;
+	u64   rq_qs:7;
+	u64   rq_idx:3;
+	u64   rsvd1:12;
+	u64   rss_alg:4;
+	u64   rsvd2:4;
+	u64   rb_cnt:4;
+	u64   vlan_found:1;
+	u64   vlan_stripped:1;
+	u64   vlan2_found:1;
+	u64   vlan2_stripped:1;
+	u64   l4_type:4;
+	u64   l3_type:4;
+	u64   l2_present:1;
+	u64   err_level:3;
+	u64   err_opcode:8;
+
+	u64   pkt_len:16; /* W1 */
+	u64   l2_ptr:8;
+	u64   l3_ptr:8;
+	u64   l4_ptr:8;
+	u64   cq_pkt_len:8;
+	u64   align_pad:3;
+	u64   rsvd3:1;
+	u64   chan:12;
+
+	u64   rss_tag:32; /* W2 */
+	u64   vlan_tci:16;
+	u64   vlan_ptr:8;
+	u64   vlan2_ptr:8;
+
+	u64   rb3_sz:16; /* W3 */
+	u64   rb2_sz:16;
+	u64   rb1_sz:16;
+	u64   rb0_sz:16;
+
+	u64   rb7_sz:16; /* W4 */
+	u64   rb6_sz:16;
+	u64   rb5_sz:16;
+	u64   rb4_sz:16;
+
+	u64   rb11_sz:16; /* W5 */
+	u64   rb10_sz:16;
+	u64   rb9_sz:16;
+	u64   rb8_sz:16;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   err_opcode:8;
+	u64   err_level:3;
+	u64   l2_present:1;
+	u64   l3_type:4;
+	u64   l4_type:4;
+	u64   vlan2_stripped:1;
+	u64   vlan2_found:1;
+	u64   vlan_stripped:1;
+	u64   vlan_found:1;
+	u64   rb_cnt:4;
+	u64   rsvd2:4;
+	u64   rss_alg:4;
+	u64   rsvd1:12;
+	u64   rq_idx:3;
+	u64   rq_qs:7;
+	u64   rsvd0:1;
+	u64   stdn_fault:1;
+	u64   cqe_type:4; /* W0 */
+	u64   chan:12;
+	u64   rsvd3:1;
+	u64   align_pad:3;
+	u64   cq_pkt_len:8;
+	u64   l4_ptr:8;
+	u64   l3_ptr:8;
+	u64   l2_ptr:8;
+	u64   pkt_len:16; /* W1 */
+	u64   vlan2_ptr:8;
+	u64   vlan_ptr:8;
+	u64   vlan_tci:16;
+	u64   rss_tag:32; /* W2 */
+	u64   rb0_sz:16;
+	u64   rb1_sz:16;
+	u64   rb2_sz:16;
+	u64   rb3_sz:16; /* W3 */
+	u64   rb4_sz:16;
+	u64   rb5_sz:16;
+	u64   rb6_sz:16;
+	u64   rb7_sz:16; /* W4 */
+	u64   rb8_sz:16;
+	u64   rb9_sz:16;
+	u64   rb10_sz:16;
+	u64   rb11_sz:16; /* W5 */
+#endif
+	u64   rb0_ptr:64;
+	u64   rb1_ptr:64;
+	u64   rb2_ptr:64;
+	u64   rb3_ptr:64;
+	u64   rb4_ptr:64;
+	u64   rb5_ptr:64;
+	u64   rb6_ptr:64;
+	u64   rb7_ptr:64;
+	u64   rb8_ptr:64;
+	u64   rb9_ptr:64;
+	u64   rb10_ptr:64;
+	u64   rb11_ptr:64;
+};
+
+struct cqe_rx_tcp_err_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   cqe_type:4; /* W0 */
+	u64   rsvd0:60;
+
+	u64   rsvd1:4; /* W1 */
+	u64   partial_first:1;
+	u64   rsvd2:27;
+	u64   rbdr_bytes:8;
+	u64   rsvd3:24;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   rsvd0:60;
+	u64   cqe_type:4;
+
+	u64   rsvd3:24;
+	u64   rbdr_bytes:8;
+	u64   rsvd2:27;
+	u64   partial_first:1;
+	u64   rsvd1:4;
+#endif
+};
+
+struct cqe_rx_tcp_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   cqe_type:4; /* W0 */
+	u64   rsvd0:52;
+	u64   cq_tcp_status:8;
+
+	u64   rsvd1:32; /* W1 */
+	u64   tcp_cntx_bytes:8;
+	u64   rsvd2:8;
+	u64   tcp_err_bytes:16;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   cq_tcp_status:8;
+	u64   rsvd0:52;
+	u64   cqe_type:4; /* W0 */
+
+	u64   tcp_err_bytes:16;
+	u64   rsvd2:8;
+	u64   tcp_cntx_bytes:8;
+	u64   rsvd1:32; /* W1 */
+#endif
+};
+
+struct cqe_send_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   cqe_type:4; /* W0 */
+	u64   rsvd0:4;
+	u64   sqe_ptr:16;
+	u64   rsvd1:4;
+	u64   rsvd2:10;
+	u64   sq_qs:7;
+	u64   sq_idx:3;
+	u64   rsvd3:8;
+	u64   send_status:8;
+
+	u64   ptp_timestamp:64; /* W1 */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   send_status:8;
+	u64   rsvd3:8;
+	u64   sq_idx:3;
+	u64   sq_qs:7;
+	u64   rsvd2:10;
+	u64   rsvd1:4;
+	u64   sqe_ptr:16;
+	u64   rsvd0:4;
+	u64   cqe_type:4; /* W0 */
+
+	u64   ptp_timestamp:64; /* W1 */
+#endif
+};
+
+union cq_desc_t {
+	u64    u[64];
+	struct cqe_send_t snd_hdr;
+	struct cqe_rx_t rx_hdr;
+	struct cqe_rx_tcp_t rx_tcp_hdr;
+	struct cqe_rx_tcp_err_t rx_tcp_err_hdr;
+};
+
+struct rbdr_entry_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   rsvd0:15;
+	u64   buf_addr:42;
+	u64   cache_align:7;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   cache_align:7;
+	u64   buf_addr:42;
+	u64   rsvd0:15;
+#endif
+};
+
+/* TCP reassembly context */
+struct rbe_tcp_cnxt_t {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64   tcp_pkt_cnt:12;
+	u64   rsvd1:4;
+	u64   align_hdr_bytes:4;
+	u64   align_ptr_bytes:4;
+	u64   ptr_bytes:16;
+	u64   rsvd2:24;
+	u64   cqe_type:4;
+	u64   rsvd0:54;
+	u64   tcp_end_reason:2;
+	u64   tcp_status:4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64   tcp_status:4;
+	u64   tcp_end_reason:2;
+	u64   rsvd0:54;
+	u64   cqe_type:4;
+	u64   rsvd2:24;
+	u64   ptr_bytes:16;
+	u64   align_ptr_bytes:4;
+	u64   align_hdr_bytes:4;
+	u64   rsvd1:4;
+	u64   tcp_pkt_cnt:12;
+#endif
+};
+
+/* Always Big endian */
+struct rx_hdr_t {
+	u64   opaque:32;
+	u64   rss_flow:8;
+	u64   skip_length:6;
+	u64   disable_rss:1;
+	u64   disable_tcp_reassembly:1;
+	u64   nodrop:1;
+	u64   dest_alg:2;
+	u64   rsvd0:2;
+	u64   dest_rq:11;
+};
+
+enum send_l4_csum_type {
+	SEND_L4_CSUM_DISABLE = 0x00,
+	SEND_L4_CSUM_UDP = 0x01,
+	SEND_L4_CSUM_TCP = 0x02,
+	SEND_L4_CSUM_SCTP = 0x03,
+};
+
+enum send_crc_alg {
+	SEND_CRCALG_CRC32 = 0x00,
+	SEND_CRCALG_CRC32C = 0x01,
+	SEND_CRCALG_ICRC = 0x02,
+};
+
+enum send_load_type {
+	SEND_LD_TYPE_LDD = 0x00,
+	SEND_LD_TYPE_LDT = 0x01,
+	SEND_LD_TYPE_LDWB = 0x02,
+};
+
+enum send_mem_alg_type {
+	SEND_MEMALG_SET = 0x00,
+	SEND_MEMALG_ADD = 0x08,
+	SEND_MEMALG_SUB = 0x09,
+	SEND_MEMALG_ADDLEN = 0x0A,
+	SEND_MEMALG_SUBLEN = 0x0B,
+};
+
+enum send_mem_dsz_type {
+	SEND_MEMDSZ_B64 = 0x00,
+	SEND_MEMDSZ_B32 = 0x01,
+	SEND_MEMDSZ_B8 = 0x03,
+};
+
+enum sq_subdesc_type {
+	SQ_DESC_TYPE_INVALID = 0x00,
+	SQ_DESC_TYPE_HEADER = 0x01,
+	SQ_DESC_TYPE_CRC = 0x02,
+	SQ_DESC_TYPE_IMMEDIATE = 0x03,
+	SQ_DESC_TYPE_GATHER = 0x04,
+	SQ_DESC_TYPE_MEMORY = 0x05,
+};
+
+struct sq_crc_subdesc {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64    rsvd1:32;
+	u64    crc_ival:32;
+	u64    subdesc_type:4;
+	u64    crc_alg:2;
+	u64    rsvd0:10;
+	u64    crc_insert_pos:16;
+	u64    hdr_start:16;
+	u64    crc_len:16;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64    crc_len:16;
+	u64    hdr_start:16;
+	u64    crc_insert_pos:16;
+	u64    rsvd0:10;
+	u64    crc_alg:2;
+	u64    subdesc_type:4;
+	u64    crc_ival:32;
+	u64    rsvd1:32;
+#endif
+};
+
+struct sq_gather_subdesc {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64    subdesc_type:4; /* W0 */
+	u64    ld_type:2;
+	u64    rsvd0:42;
+	u64    size:16;
+
+	u64    rsvd1:15; /* W1 */
+	u64    addr:49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64    size:16;
+	u64    rsvd0:42;
+	u64    ld_type:2;
+	u64    subdesc_type:4; /* W0 */
+
+	u64    addr:49;
+	u64    rsvd1:15; /* W1 */
+#endif
+};
+
+/* SQ immediate subdescriptor */
+struct sq_imm_subdesc {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64    subdesc_type:4; /* W0 */
+	u64    rsvd0:46;
+	u64    len:14;
+
+	u64    data:64; /* W1 */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64    len:14;
+	u64    rsvd0:46;
+	u64    subdesc_type:4; /* W0 */
+
+	u64    data:64; /* W1 */
+#endif
+};
+
+struct sq_mem_subdesc {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64    subdesc_type:4; /* W0 */
+	u64    mem_alg:4;
+	u64    mem_dsz:2;
+	u64    wmem:1;
+	u64    rsvd0:21;
+	u64    offset:32;
+
+	u64    rsvd1:15; /* W1 */
+	u64    addr:49;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64    offset:32;
+	u64    rsvd0:21;
+	u64    wmem:1;
+	u64    mem_dsz:2;
+	u64    mem_alg:4;
+	u64    subdesc_type:4; /* W0 */
+
+	u64    addr:49;
+	u64    rsvd1:15; /* W1 */
+#endif
+};
+
+struct sq_hdr_subdesc {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64    subdesc_type:4;
+	u64    tso:1;
+	u64    post_cqe:1; /* Post CQE on no error also */
+	u64    dont_send:1;
+	u64    tstmp:1;
+	u64    subdesc_cnt:8;
+	u64    csum_l4:2;
+	u64    csum_l3:1;
+	u64    rsvd0:5;
+	u64    l4_offset:8;
+	u64    l3_offset:8;
+	u64    rsvd1:4;
+	u64    tot_len:20; /* W0 */
+
+	u64    tso_sdc_cont:8;
+	u64    tso_sdc_first:8;
+	u64    tso_l4_offset:8;
+	u64    tso_flags_last:12;
+	u64    tso_flags_first:12;
+	u64    rsvd2:2;
+	u64    tso_max_paysize:14; /* W1 */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64    tot_len:20;
+	u64    rsvd1:4;
+	u64    l3_offset:8;
+	u64    l4_offset:8;
+	u64    rsvd0:5;
+	u64    csum_l3:1;
+	u64    csum_l4:2;
+	u64    subdesc_cnt:8;
+	u64    tstmp:1;
+	u64    dont_send:1;
+	u64    post_cqe:1; /* Post CQE on no error also */
+	u64    tso:1;
+	u64    subdesc_type:4; /* W0 */
+
+	u64    tso_max_paysize:14;
+	u64    rsvd2:2;
+	u64    tso_flags_first:12;
+	u64    tso_flags_last:12;
+	u64    tso_l4_offset:8;
+	u64    tso_sdc_first:8;
+	u64    tso_sdc_cont:8; /* W1 */
+#endif
+};
+
+/* Queue config register formats */
+struct rq_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_2_63:62;
+	u64 ena:1;
+	u64 tcp_ena:1;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 tcp_ena:1;
+	u64 ena:1;
+	u64 reserved_2_63:62;
+#endif
+};
+
+struct cq_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_43_63:21;
+	u64 ena:1;
+	u64 reset:1;
+	u64 caching:1;
+	u64 reserved_35_39:5;
+	u64 qsize:3;
+	u64 reserved_25_31:7;
+	u64 avg_con:9;
+	u64 reserved_0_15:16;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 reserved_0_15:16;
+	u64 avg_con:9;
+	u64 reserved_25_31:7;
+	u64 qsize:3;
+	u64 reserved_35_39:5;
+	u64 caching:1;
+	u64 reset:1;
+	u64 ena:1;
+	u64 reserved_43_63:21;
+#endif
+};
+
+struct sq_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_20_63:44;
+	u64 ena:1;
+	u64 reserved_18_18:1;
+	u64 reset:1;
+	u64 ldwb:1;
+	u64 reserved_11_15:5;
+	u64 qsize:3;
+	u64 reserved_3_7:5;
+	u64 tstmp_bgx_intf:3;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 tstmp_bgx_intf:3;
+	u64 reserved_3_7:5;
+	u64 qsize:3;
+	u64 reserved_11_15:5;
+	u64 ldwb:1;
+	u64 reset:1;
+	u64 reserved_18_18:1;
+	u64 ena:1;
+	u64 reserved_20_63:44;
+#endif
+};
+
+struct rbdr_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_45_63:19;
+	u64 ena:1;
+	u64 reset:1;
+	u64 ldwb:1;
+	u64 reserved_36_41:6;
+	u64 qsize:4;
+	u64 reserved_25_31:7;
+	u64 avg_con:9;
+	u64 reserved_12_15:4;
+	u64 lines:12;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 lines:12;
+	u64 reserved_12_15:4;
+	u64 avg_con:9;
+	u64 reserved_25_31:7;
+	u64 qsize:4;
+	u64 reserved_36_41:6;
+	u64 ldwb:1;
+	u64 reset:1;
+	u64 ena: 1;
+	u64 reserved_45_63:19;
+#endif
+};
+
+struct qs_cfg {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u64 reserved_32_63:32;
+	u64 ena:1;
+	u64 reserved_27_30:4;
+	u64 sq_ins_ena:1;
+	u64 sq_ins_pos:6;
+	u64 lock_ena:1;
+	u64 lock_viol_cqe_ena:1;
+	u64 send_tstmp_ena:1;
+	u64 be:1;
+	u64 reserved_7_15:9;
+	u64 vnic:7;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u64 vnic:7;
+	u64 reserved_7_15:9;
+	u64 be:1;
+	u64 send_tstmp_ena:1;
+	u64 lock_viol_cqe_ena:1;
+	u64 lock_ena:1;
+	u64 sq_ins_pos:6;
+	u64 sq_ins_ena:1;
+	u64 reserved_27_30:4;
+	u64 ena:1;
+	u64 reserved_32_63:32;
+#endif
+};
+
+#endif /* Q_STRUCT_H */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
new file mode 100644
index 000000000000..633ec05dfe05
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -0,0 +1,966 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+
+#include "nic_reg.h"
+#include "nic.h"
+#include "thunder_bgx.h"
+
+#define DRV_NAME	"thunder-BGX"
+#define DRV_VERSION	"1.0"
+
+struct lmac {
+	struct bgx		*bgx;
+	int			dmac;
+	unsigned char		mac[ETH_ALEN];
+	bool			link_up;
+	int			lmacid; /* ID within BGX */
+	int			lmacid_bd; /* ID on board */
+	struct net_device       netdev;
+	struct phy_device       *phydev;
+	unsigned int            last_duplex;
+	unsigned int            last_link;
+	unsigned int            last_speed;
+	bool			is_sgmii;
+	struct delayed_work	dwork;
+	struct workqueue_struct *check_link;
+};
+
+struct bgx {
+	u8			bgx_id;
+	u8			qlm_mode;
+	struct	lmac		lmac[MAX_LMAC_PER_BGX];
+	int			lmac_count;
+	int                     lmac_type;
+	int                     lane_to_sds;
+	int			use_training;
+	void __iomem		*reg_base;
+	struct pci_dev		*pdev;
+};
+
+static struct bgx *bgx_vnic[MAX_BGX_THUNDER];
+static int lmac_count; /* Total no of LMACs in system */
+
+static int bgx_xaui_check_link(struct lmac *lmac);
+
+/* Supported devices */
+static const struct pci_device_id bgx_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_BGX) },
+	{ 0, }  /* end of table */
+};
+
+MODULE_AUTHOR("Cavium Inc");
+MODULE_DESCRIPTION("Cavium Thunder BGX/MAC Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DEVICE_TABLE(pci, bgx_id_table);
+
+/* The Cavium ThunderX network controller can *only* be found in SoCs
+ * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
+ * registers on this platform are implicitly strongly ordered with respect
+ * to memory accesses. So writeq_relaxed() and readq_relaxed() are safe to use
+ * with no memory barriers in this driver.  The readq()/writeq() functions add
+ * explicit ordering operation which in this case are redundant, and only
+ * add overhead.
+ */
+
+/* Register read/write APIs */
+static u64 bgx_reg_read(struct bgx *bgx, u8 lmac, u64 offset)
+{
+	void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset;
+
+	return readq_relaxed(addr);
+}
+
+static void bgx_reg_write(struct bgx *bgx, u8 lmac, u64 offset, u64 val)
+{
+	void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset;
+
+	writeq_relaxed(val, addr);
+}
+
+static void bgx_reg_modify(struct bgx *bgx, u8 lmac, u64 offset, u64 val)
+{
+	void __iomem *addr = bgx->reg_base + ((u32)lmac << 20) + offset;
+
+	writeq_relaxed(val | readq_relaxed(addr), addr);
+}
+
+static int bgx_poll_reg(struct bgx *bgx, u8 lmac, u64 reg, u64 mask, bool zero)
+{
+	int timeout = 100;
+	u64 reg_val;
+
+	while (timeout) {
+		reg_val = bgx_reg_read(bgx, lmac, reg);
+		if (zero && !(reg_val & mask))
+			return 0;
+		if (!zero && (reg_val & mask))
+			return 0;
+		usleep_range(1000, 2000);
+		timeout--;
+	}
+	return 1;
+}
+
+/* Return number of BGX present in HW */
+unsigned bgx_get_map(int node)
+{
+	int i;
+	unsigned map = 0;
+
+	for (i = 0; i < MAX_BGX_PER_CN88XX; i++) {
+		if (bgx_vnic[(node * MAX_BGX_PER_CN88XX) + i])
+			map |= (1 << i);
+	}
+
+	return map;
+}
+EXPORT_SYMBOL(bgx_get_map);
+
+/* Return number of LMAC configured for this BGX */
+int bgx_get_lmac_count(int node, int bgx_idx)
+{
+	struct bgx *bgx;
+
+	bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	if (bgx)
+		return bgx->lmac_count;
+
+	return 0;
+}
+EXPORT_SYMBOL(bgx_get_lmac_count);
+
+/* Returns the current link status of LMAC */
+void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status)
+{
+	struct bgx_link_status *link = (struct bgx_link_status *)status;
+	struct bgx *bgx;
+	struct lmac *lmac;
+
+	bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	if (!bgx)
+		return;
+
+	lmac = &bgx->lmac[lmacid];
+	link->link_up = lmac->link_up;
+	link->duplex = lmac->last_duplex;
+	link->speed = lmac->last_speed;
+}
+EXPORT_SYMBOL(bgx_get_lmac_link_state);
+
+const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid)
+{
+	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+
+	if (bgx)
+		return bgx->lmac[lmacid].mac;
+
+	return NULL;
+}
+EXPORT_SYMBOL(bgx_get_lmac_mac);
+
+void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
+{
+	struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+
+	if (!bgx)
+		return;
+
+	ether_addr_copy(bgx->lmac[lmacid].mac, mac);
+}
+EXPORT_SYMBOL(bgx_set_lmac_mac);
+
+static void bgx_sgmii_change_link_state(struct lmac *lmac)
+{
+	struct bgx *bgx = lmac->bgx;
+	u64 cmr_cfg;
+	u64 port_cfg = 0;
+	u64 misc_ctl = 0;
+
+	cmr_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_CMRX_CFG);
+	cmr_cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmac->lmacid, BGX_CMRX_CFG, cmr_cfg);
+
+	port_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG);
+	misc_ctl = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_PCS_MISCX_CTL);
+
+	if (lmac->link_up) {
+		misc_ctl &= ~PCS_MISC_CTL_GMX_ENO;
+		port_cfg &= ~GMI_PORT_CFG_DUPLEX;
+		port_cfg |=  (lmac->last_duplex << 2);
+	} else {
+		misc_ctl |= PCS_MISC_CTL_GMX_ENO;
+	}
+
+	switch (lmac->last_speed) {
+	case 10:
+		port_cfg &= ~GMI_PORT_CFG_SPEED; /* speed 0 */
+		port_cfg |= GMI_PORT_CFG_SPEED_MSB;  /* speed_msb 1 */
+		port_cfg &= ~GMI_PORT_CFG_SLOT_TIME; /* slottime 0 */
+		misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK;
+		misc_ctl |= 50; /* samp_pt */
+		bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 64);
+		bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_BURST, 0);
+		break;
+	case 100:
+		port_cfg &= ~GMI_PORT_CFG_SPEED; /* speed 0 */
+		port_cfg &= ~GMI_PORT_CFG_SPEED_MSB; /* speed_msb 0 */
+		port_cfg &= ~GMI_PORT_CFG_SLOT_TIME; /* slottime 0 */
+		misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK;
+		misc_ctl |= 5; /* samp_pt */
+		bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 64);
+		bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_BURST, 0);
+		break;
+	case 1000:
+		port_cfg |= GMI_PORT_CFG_SPEED; /* speed 1 */
+		port_cfg &= ~GMI_PORT_CFG_SPEED_MSB; /* speed_msb 0 */
+		port_cfg |= GMI_PORT_CFG_SLOT_TIME; /* slottime 1 */
+		misc_ctl &= ~PCS_MISC_CTL_SAMP_PT_MASK;
+		misc_ctl |= 1; /* samp_pt */
+		bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_TXX_SLOT, 512);
+		if (lmac->last_duplex)
+			bgx_reg_write(bgx, lmac->lmacid,
+				      BGX_GMP_GMI_TXX_BURST, 0);
+		else
+			bgx_reg_write(bgx, lmac->lmacid,
+				      BGX_GMP_GMI_TXX_BURST, 8192);
+		break;
+	default:
+		break;
+	}
+	bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_PCS_MISCX_CTL, misc_ctl);
+	bgx_reg_write(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG, port_cfg);
+
+	port_cfg = bgx_reg_read(bgx, lmac->lmacid, BGX_GMP_GMI_PRTX_CFG);
+
+	/* renable lmac */
+	cmr_cfg |= CMR_EN;
+	bgx_reg_write(bgx, lmac->lmacid, BGX_CMRX_CFG, cmr_cfg);
+}
+
+static void bgx_lmac_handler(struct net_device *netdev)
+{
+	struct lmac *lmac = container_of(netdev, struct lmac, netdev);
+	struct phy_device *phydev = lmac->phydev;
+	int link_changed = 0;
+
+	if (!lmac)
+		return;
+
+	if (!phydev->link && lmac->last_link)
+		link_changed = -1;
+
+	if (phydev->link &&
+	    (lmac->last_duplex != phydev->duplex ||
+	     lmac->last_link != phydev->link ||
+	     lmac->last_speed != phydev->speed)) {
+			link_changed = 1;
+	}
+
+	lmac->last_link = phydev->link;
+	lmac->last_speed = phydev->speed;
+	lmac->last_duplex = phydev->duplex;
+
+	if (!link_changed)
+		return;
+
+	if (link_changed > 0)
+		lmac->link_up = true;
+	else
+		lmac->link_up = false;
+
+	if (lmac->is_sgmii)
+		bgx_sgmii_change_link_state(lmac);
+	else
+		bgx_xaui_check_link(lmac);
+}
+
+u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx)
+{
+	struct bgx *bgx;
+
+	bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	if (!bgx)
+		return 0;
+
+	if (idx > 8)
+		lmac = 0;
+	return bgx_reg_read(bgx, lmac, BGX_CMRX_RX_STAT0 + (idx * 8));
+}
+EXPORT_SYMBOL(bgx_get_rx_stats);
+
+u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx)
+{
+	struct bgx *bgx;
+
+	bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+	if (!bgx)
+		return 0;
+
+	return bgx_reg_read(bgx, lmac, BGX_CMRX_TX_STAT0 + (idx * 8));
+}
+EXPORT_SYMBOL(bgx_get_tx_stats);
+
+static void bgx_flush_dmac_addrs(struct bgx *bgx, int lmac)
+{
+	u64 offset;
+
+	while (bgx->lmac[lmac].dmac > 0) {
+		offset = ((bgx->lmac[lmac].dmac - 1) * sizeof(u64)) +
+			(lmac * MAX_DMAC_PER_LMAC * sizeof(u64));
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + offset, 0);
+		bgx->lmac[lmac].dmac--;
+	}
+}
+
+static int bgx_lmac_sgmii_init(struct bgx *bgx, int lmacid)
+{
+	u64 cfg;
+
+	bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_THRESH, 0x30);
+	/* max packet size */
+	bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_RXX_JABBER, MAX_FRAME_SIZE);
+
+	/* Disable frame alignment if using preamble */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND);
+	if (cfg & 1)
+		bgx_reg_write(bgx, lmacid, BGX_GMP_GMI_TXX_SGMII_CTL, 0);
+
+	/* Enable lmac */
+	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
+
+	/* PCS reset */
+	bgx_reg_modify(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, PCS_MRX_CTL_RESET);
+	if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_CTL,
+			 PCS_MRX_CTL_RESET, true)) {
+		dev_err(&bgx->pdev->dev, "BGX PCS reset not completed\n");
+		return -1;
+	}
+
+	/* power down, reset autoneg, autoneg enable */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_PCS_MRX_CTL);
+	cfg &= ~PCS_MRX_CTL_PWR_DN;
+	cfg |= (PCS_MRX_CTL_RST_AN | PCS_MRX_CTL_AN_EN);
+	bgx_reg_write(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, cfg);
+
+	if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_STATUS,
+			 PCS_MRX_STATUS_AN_CPT, false)) {
+		dev_err(&bgx->pdev->dev, "BGX AN_CPT not completed\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int bgx_lmac_xaui_init(struct bgx *bgx, int lmacid, int lmac_type)
+{
+	u64 cfg;
+
+	/* Reset SPU */
+	bgx_reg_modify(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET);
+	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET, true)) {
+		dev_err(&bgx->pdev->dev, "BGX SPU reset not completed\n");
+		return -1;
+	}
+
+	/* Disable LMAC */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cfg &= ~CMR_EN;
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+
+	bgx_reg_modify(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_LOW_POWER);
+	/* Set interleaved running disparity for RXAUI */
+	if (bgx->lmac_type != BGX_MODE_RXAUI)
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_MISC_CONTROL, SPU_MISC_CTL_RX_DIS);
+	else
+		bgx_reg_modify(bgx, lmacid, BGX_SPUX_MISC_CONTROL,
+			       SPU_MISC_CTL_RX_DIS | SPU_MISC_CTL_INTLV_RDISP);
+
+	/* clear all interrupts */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_RX_INT);
+	bgx_reg_write(bgx, lmacid, BGX_SMUX_RX_INT, cfg);
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_INT);
+	bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_INT, cfg);
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT);
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg);
+
+	if (bgx->use_training) {
+		bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LP_CUP, 0x00);
+		bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LD_CUP, 0x00);
+		bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_LD_REP, 0x00);
+		/* training enable */
+		bgx_reg_modify(bgx, lmacid,
+			       BGX_SPUX_BR_PMD_CRTL, SPU_PMD_CRTL_TRAIN_EN);
+	}
+
+	/* Append FCS to each packet */
+	bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_APPEND, SMU_TX_APPEND_FCS_D);
+
+	/* Disable forward error correction */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_FEC_CONTROL);
+	cfg &= ~SPU_FEC_CTL_FEC_EN;
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_FEC_CONTROL, cfg);
+
+	/* Disable autoneg */
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_AN_CONTROL);
+	cfg = cfg & ~(SPU_AN_CTL_AN_EN | SPU_AN_CTL_XNP_EN);
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_AN_CONTROL, cfg);
+
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_AN_ADV);
+	if (bgx->lmac_type == BGX_MODE_10G_KR)
+		cfg |= (1 << 23);
+	else if (bgx->lmac_type == BGX_MODE_40G_KR)
+		cfg |= (1 << 24);
+	else
+		cfg &= ~((1 << 23) | (1 << 24));
+	cfg = cfg & (~((1ULL << 25) | (1ULL << 22) | (1ULL << 12)));
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_AN_ADV, cfg);
+
+	cfg = bgx_reg_read(bgx, 0, BGX_SPU_DBG_CONTROL);
+	cfg &= ~SPU_DBG_CTL_AN_ARB_LINK_CHK_EN;
+	bgx_reg_write(bgx, 0, BGX_SPU_DBG_CONTROL, cfg);
+
+	/* Enable lmac */
+	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
+
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_CONTROL1);
+	cfg &= ~SPU_CTL_LOW_POWER;
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_CONTROL1, cfg);
+
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_CTL);
+	cfg &= ~SMU_TX_CTL_UNI_EN;
+	cfg |= SMU_TX_CTL_DIC_EN;
+	bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_CTL, cfg);
+
+	/* take lmac_count into account */
+	bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_THRESH, (0x100 - 1));
+	/* max packet size */
+	bgx_reg_modify(bgx, lmacid, BGX_SMUX_RX_JABBER, MAX_FRAME_SIZE);
+
+	return 0;
+}
+
+static int bgx_xaui_check_link(struct lmac *lmac)
+{
+	struct bgx *bgx = lmac->bgx;
+	int lmacid = lmac->lmacid;
+	int lmac_type = bgx->lmac_type;
+	u64 cfg;
+
+	bgx_reg_modify(bgx, lmacid, BGX_SPUX_MISC_CONTROL, SPU_MISC_CTL_RX_DIS);
+	if (bgx->use_training) {
+		cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT);
+		if (!(cfg & (1ull << 13))) {
+			cfg = (1ull << 13) | (1ull << 14);
+			bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg);
+			cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_BR_PMD_CRTL);
+			cfg |= (1ull << 0);
+			bgx_reg_write(bgx, lmacid, BGX_SPUX_BR_PMD_CRTL, cfg);
+			return -1;
+		}
+	}
+
+	/* wait for PCS to come out of reset */
+	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_CONTROL1, SPU_CTL_RESET, true)) {
+		dev_err(&bgx->pdev->dev, "BGX SPU reset not completed\n");
+		return -1;
+	}
+
+	if ((lmac_type == BGX_MODE_10G_KR) || (lmac_type == BGX_MODE_XFI) ||
+	    (lmac_type == BGX_MODE_40G_KR) || (lmac_type == BGX_MODE_XLAUI)) {
+		if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_BR_STATUS1,
+				 SPU_BR_STATUS_BLK_LOCK, false)) {
+			dev_err(&bgx->pdev->dev,
+				"SPU_BR_STATUS_BLK_LOCK not completed\n");
+			return -1;
+		}
+	} else {
+		if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_BX_STATUS,
+				 SPU_BX_STATUS_RX_ALIGN, false)) {
+			dev_err(&bgx->pdev->dev,
+				"SPU_BX_STATUS_RX_ALIGN not completed\n");
+			return -1;
+		}
+	}
+
+	/* Clear rcvflt bit (latching high) and read it back */
+	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS2, SPU_STATUS2_RCVFLT);
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
+		dev_err(&bgx->pdev->dev, "Receive fault, retry training\n");
+		if (bgx->use_training) {
+			cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_INT);
+			if (!(cfg & (1ull << 13))) {
+				cfg = (1ull << 13) | (1ull << 14);
+				bgx_reg_write(bgx, lmacid, BGX_SPUX_INT, cfg);
+				cfg = bgx_reg_read(bgx, lmacid,
+						   BGX_SPUX_BR_PMD_CRTL);
+				cfg |= (1ull << 0);
+				bgx_reg_write(bgx, lmacid,
+					      BGX_SPUX_BR_PMD_CRTL, cfg);
+				return -1;
+			}
+		}
+		return -1;
+	}
+
+	/* Wait for MAC RX to be ready */
+	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_RX_CTL,
+			 SMU_RX_CTL_STATUS, true)) {
+		dev_err(&bgx->pdev->dev, "SMU RX link not okay\n");
+		return -1;
+	}
+
+	/* Wait for BGX RX to be idle */
+	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_RX_IDLE, false)) {
+		dev_err(&bgx->pdev->dev, "SMU RX not idle\n");
+		return -1;
+	}
+
+	/* Wait for BGX TX to be idle */
+	if (bgx_poll_reg(bgx, lmacid, BGX_SMUX_CTL, SMU_CTL_TX_IDLE, false)) {
+		dev_err(&bgx->pdev->dev, "SMU TX not idle\n");
+		return -1;
+	}
+
+	if (bgx_reg_read(bgx, lmacid, BGX_SPUX_STATUS2) & SPU_STATUS2_RCVFLT) {
+		dev_err(&bgx->pdev->dev, "Receive fault\n");
+		return -1;
+	}
+
+	/* Receive link is latching low. Force it high and verify it */
+	bgx_reg_modify(bgx, lmacid, BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
+	if (bgx_poll_reg(bgx, lmacid, BGX_SPUX_STATUS1,
+			 SPU_STATUS1_RCV_LNK, false)) {
+		dev_err(&bgx->pdev->dev, "SPU receive link down\n");
+		return -1;
+	}
+
+	cfg = bgx_reg_read(bgx, lmacid, BGX_SPUX_MISC_CONTROL);
+	cfg &= ~SPU_MISC_CTL_RX_DIS;
+	bgx_reg_write(bgx, lmacid, BGX_SPUX_MISC_CONTROL, cfg);
+	return 0;
+}
+
+static void bgx_poll_for_link(struct work_struct *work)
+{
+	struct lmac *lmac;
+	u64 link;
+
+	lmac = container_of(work, struct lmac, dwork.work);
+
+	/* Receive link is latching low. Force it high and verify it */
+	bgx_reg_modify(lmac->bgx, lmac->lmacid,
+		       BGX_SPUX_STATUS1, SPU_STATUS1_RCV_LNK);
+	bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1,
+		     SPU_STATUS1_RCV_LNK, false);
+
+	link = bgx_reg_read(lmac->bgx, lmac->lmacid, BGX_SPUX_STATUS1);
+	if (link & SPU_STATUS1_RCV_LNK) {
+		lmac->link_up = 1;
+		if (lmac->bgx->lmac_type == BGX_MODE_XLAUI)
+			lmac->last_speed = 40000;
+		else
+			lmac->last_speed = 10000;
+		lmac->last_duplex = 1;
+	} else {
+		lmac->link_up = 0;
+	}
+
+	if (lmac->last_link != lmac->link_up) {
+		lmac->last_link = lmac->link_up;
+		if (lmac->link_up)
+			bgx_xaui_check_link(lmac);
+	}
+
+	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 2);
+}
+
+static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
+{
+	struct lmac *lmac;
+	u64 cfg;
+
+	lmac = &bgx->lmac[lmacid];
+	lmac->bgx = bgx;
+
+	if (bgx->lmac_type == BGX_MODE_SGMII) {
+		lmac->is_sgmii = 1;
+		if (bgx_lmac_sgmii_init(bgx, lmacid))
+			return -1;
+	} else {
+		lmac->is_sgmii = 0;
+		if (bgx_lmac_xaui_init(bgx, lmacid, bgx->lmac_type))
+			return -1;
+	}
+
+	if (lmac->is_sgmii) {
+		cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND);
+		cfg |= ((1ull << 2) | (1ull << 1)); /* FCS and PAD */
+		bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_APPEND, cfg);
+		bgx_reg_write(bgx, lmacid, BGX_GMP_GMI_TXX_MIN_PKT, 60 - 1);
+	} else {
+		cfg = bgx_reg_read(bgx, lmacid, BGX_SMUX_TX_APPEND);
+		cfg |= ((1ull << 2) | (1ull << 1)); /* FCS and PAD */
+		bgx_reg_modify(bgx, lmacid, BGX_SMUX_TX_APPEND, cfg);
+		bgx_reg_write(bgx, lmacid, BGX_SMUX_TX_MIN_PKT, 60 + 4);
+	}
+
+	/* Enable lmac */
+	bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG,
+		       CMR_EN | CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+
+	/* Restore default cfg, incase low level firmware changed it */
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL, 0x03);
+
+	if ((bgx->lmac_type != BGX_MODE_XFI) &&
+	    (bgx->lmac_type != BGX_MODE_XLAUI) &&
+	    (bgx->lmac_type != BGX_MODE_40G_KR) &&
+	    (bgx->lmac_type != BGX_MODE_10G_KR)) {
+		if (!lmac->phydev)
+			return -ENODEV;
+
+		lmac->phydev->dev_flags = 0;
+
+		if (phy_connect_direct(&lmac->netdev, lmac->phydev,
+				       bgx_lmac_handler,
+				       PHY_INTERFACE_MODE_SGMII))
+			return -ENODEV;
+
+		phy_start_aneg(lmac->phydev);
+	} else {
+		lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
+						   WQ_MEM_RECLAIM, 1);
+		if (!lmac->check_link)
+			return -ENOMEM;
+		INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
+		queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+	}
+
+	return 0;
+}
+
+static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
+{
+	struct lmac *lmac;
+	u64 cmrx_cfg;
+
+	lmac = &bgx->lmac[lmacid];
+	if (lmac->check_link) {
+		/* Destroy work queue */
+		cancel_delayed_work(&lmac->dwork);
+		flush_workqueue(lmac->check_link);
+		destroy_workqueue(lmac->check_link);
+	}
+
+	cmrx_cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+	cmrx_cfg &= ~(1 << 15);
+	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
+	bgx_flush_dmac_addrs(bgx, lmacid);
+
+	if (lmac->phydev)
+		phy_disconnect(lmac->phydev);
+
+	lmac->phydev = NULL;
+}
+
+static void bgx_set_num_ports(struct bgx *bgx)
+{
+	u64 lmac_count;
+
+	switch (bgx->qlm_mode) {
+	case QLM_MODE_SGMII:
+		bgx->lmac_count = 4;
+		bgx->lmac_type = BGX_MODE_SGMII;
+		bgx->lane_to_sds = 0;
+		break;
+	case QLM_MODE_XAUI_1X4:
+		bgx->lmac_count = 1;
+		bgx->lmac_type = BGX_MODE_XAUI;
+		bgx->lane_to_sds = 0xE4;
+			break;
+	case QLM_MODE_RXAUI_2X2:
+		bgx->lmac_count = 2;
+		bgx->lmac_type = BGX_MODE_RXAUI;
+		bgx->lane_to_sds = 0xE4;
+			break;
+	case QLM_MODE_XFI_4X1:
+		bgx->lmac_count = 4;
+		bgx->lmac_type = BGX_MODE_XFI;
+		bgx->lane_to_sds = 0;
+		break;
+	case QLM_MODE_XLAUI_1X4:
+		bgx->lmac_count = 1;
+		bgx->lmac_type = BGX_MODE_XLAUI;
+		bgx->lane_to_sds = 0xE4;
+		break;
+	case QLM_MODE_10G_KR_4X1:
+		bgx->lmac_count = 4;
+		bgx->lmac_type = BGX_MODE_10G_KR;
+		bgx->lane_to_sds = 0;
+		bgx->use_training = 1;
+		break;
+	case QLM_MODE_40G_KR4_1X4:
+		bgx->lmac_count = 1;
+		bgx->lmac_type = BGX_MODE_40G_KR;
+		bgx->lane_to_sds = 0xE4;
+		bgx->use_training = 1;
+		break;
+	default:
+		bgx->lmac_count = 0;
+		break;
+	}
+
+	/* Check if low level firmware has programmed LMAC count
+	 * based on board type, if yes consider that otherwise
+	 * the default static values
+	 */
+	lmac_count = bgx_reg_read(bgx, 0, BGX_CMR_RX_LMACS) & 0x7;
+	if (lmac_count != 4)
+		bgx->lmac_count = lmac_count;
+}
+
+static void bgx_init_hw(struct bgx *bgx)
+{
+	int i;
+
+	bgx_set_num_ports(bgx);
+
+	bgx_reg_modify(bgx, 0, BGX_CMR_GLOBAL_CFG, CMR_GLOBAL_CFG_FCS_STRIP);
+	if (bgx_reg_read(bgx, 0, BGX_CMR_BIST_STATUS))
+		dev_err(&bgx->pdev->dev, "BGX%d BIST failed\n", bgx->bgx_id);
+
+	/* Set lmac type and lane2serdes mapping */
+	for (i = 0; i < bgx->lmac_count; i++) {
+		if (bgx->lmac_type == BGX_MODE_RXAUI) {
+			if (i)
+				bgx->lane_to_sds = 0x0e;
+			else
+				bgx->lane_to_sds = 0x04;
+			bgx_reg_write(bgx, i, BGX_CMRX_CFG,
+				      (bgx->lmac_type << 8) | bgx->lane_to_sds);
+			continue;
+		}
+		bgx_reg_write(bgx, i, BGX_CMRX_CFG,
+			      (bgx->lmac_type << 8) | (bgx->lane_to_sds + i));
+		bgx->lmac[i].lmacid_bd = lmac_count;
+		lmac_count++;
+	}
+
+	bgx_reg_write(bgx, 0, BGX_CMR_TX_LMACS, bgx->lmac_count);
+	bgx_reg_write(bgx, 0, BGX_CMR_RX_LMACS, bgx->lmac_count);
+
+	/* Set the backpressure AND mask */
+	for (i = 0; i < bgx->lmac_count; i++)
+		bgx_reg_modify(bgx, 0, BGX_CMR_CHAN_MSK_AND,
+			       ((1ULL << MAX_BGX_CHANS_PER_LMAC) - 1) <<
+			       (i * MAX_BGX_CHANS_PER_LMAC));
+
+	/* Disable all MAC filtering */
+	for (i = 0; i < RX_DMAC_COUNT; i++)
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_DMACX_CAM + (i * 8), 0x00);
+
+	/* Disable MAC steering (NCSI traffic) */
+	for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++)
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00);
+}
+
+static void bgx_get_qlm_mode(struct bgx *bgx)
+{
+	struct device *dev = &bgx->pdev->dev;
+	int lmac_type;
+	int train_en;
+
+	/* Read LMAC0 type to figure out QLM mode
+	 * This is configured by low level firmware
+	 */
+	lmac_type = bgx_reg_read(bgx, 0, BGX_CMRX_CFG);
+	lmac_type = (lmac_type >> 8) & 0x07;
+
+	train_en = bgx_reg_read(bgx, 0, BGX_SPUX_BR_PMD_CRTL) &
+				SPU_PMD_CRTL_TRAIN_EN;
+
+	switch (lmac_type) {
+	case BGX_MODE_SGMII:
+		bgx->qlm_mode = QLM_MODE_SGMII;
+		dev_info(dev, "BGX%d QLM mode: SGMII\n", bgx->bgx_id);
+		break;
+	case BGX_MODE_XAUI:
+		bgx->qlm_mode = QLM_MODE_XAUI_1X4;
+		dev_info(dev, "BGX%d QLM mode: XAUI\n", bgx->bgx_id);
+		break;
+	case BGX_MODE_RXAUI:
+		bgx->qlm_mode = QLM_MODE_RXAUI_2X2;
+		dev_info(dev, "BGX%d QLM mode: RXAUI\n", bgx->bgx_id);
+		break;
+	case BGX_MODE_XFI:
+		if (!train_en) {
+			bgx->qlm_mode = QLM_MODE_XFI_4X1;
+			dev_info(dev, "BGX%d QLM mode: XFI\n", bgx->bgx_id);
+		} else {
+			bgx->qlm_mode = QLM_MODE_10G_KR_4X1;
+			dev_info(dev, "BGX%d QLM mode: 10G_KR\n", bgx->bgx_id);
+		}
+		break;
+	case BGX_MODE_XLAUI:
+		if (!train_en) {
+			bgx->qlm_mode = QLM_MODE_XLAUI_1X4;
+			dev_info(dev, "BGX%d QLM mode: XLAUI\n", bgx->bgx_id);
+		} else {
+			bgx->qlm_mode = QLM_MODE_40G_KR4_1X4;
+			dev_info(dev, "BGX%d QLM mode: 40G_KR4\n", bgx->bgx_id);
+		}
+		break;
+	default:
+		bgx->qlm_mode = QLM_MODE_SGMII;
+		dev_info(dev, "BGX%d QLM default mode: SGMII\n", bgx->bgx_id);
+	}
+}
+
+static void bgx_init_of(struct bgx *bgx, struct device_node *np)
+{
+	struct device_node *np_child;
+	u8 lmac = 0;
+
+	for_each_child_of_node(np, np_child) {
+		struct device_node *phy_np;
+		const char *mac;
+
+		phy_np = of_parse_phandle(np_child, "phy-handle", 0);
+		if (phy_np)
+			bgx->lmac[lmac].phydev = of_phy_find_device(phy_np);
+
+		mac = of_get_mac_address(np_child);
+		if (mac)
+			ether_addr_copy(bgx->lmac[lmac].mac, mac);
+
+		SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev);
+		bgx->lmac[lmac].lmacid = lmac;
+		lmac++;
+		if (lmac == MAX_LMAC_PER_BGX)
+			break;
+	}
+}
+
+static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	int err;
+	struct device *dev = &pdev->dev;
+	struct bgx *bgx = NULL;
+	struct device_node *np;
+	char bgx_sel[5];
+	u8 lmac;
+
+	bgx = devm_kzalloc(dev, sizeof(*bgx), GFP_KERNEL);
+	if (!bgx)
+		return -ENOMEM;
+	bgx->pdev = pdev;
+
+	pci_set_drvdata(pdev, bgx);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(dev, "Failed to enable PCI device\n");
+		pci_set_drvdata(pdev, NULL);
+		return err;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		dev_err(dev, "PCI request regions failed 0x%x\n", err);
+		goto err_disable_device;
+	}
+
+	/* MAP configuration registers */
+	bgx->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0);
+	if (!bgx->reg_base) {
+		dev_err(dev, "BGX: Cannot map CSR memory space, aborting\n");
+		err = -ENOMEM;
+		goto err_release_regions;
+	}
+	bgx->bgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1;
+	bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_CN88XX;
+
+	bgx_vnic[bgx->bgx_id] = bgx;
+	bgx_get_qlm_mode(bgx);
+
+	snprintf(bgx_sel, 5, "bgx%d", bgx->bgx_id);
+	np = of_find_node_by_name(NULL, bgx_sel);
+	if (np)
+		bgx_init_of(bgx, np);
+
+	bgx_init_hw(bgx);
+
+	/* Enable all LMACs */
+	for (lmac = 0; lmac < bgx->lmac_count; lmac++) {
+		err = bgx_lmac_enable(bgx, lmac);
+		if (err) {
+			dev_err(dev, "BGX%d failed to enable lmac%d\n",
+				bgx->bgx_id, lmac);
+			goto err_enable;
+		}
+	}
+
+	return 0;
+
+err_enable:
+	bgx_vnic[bgx->bgx_id] = NULL;
+err_release_regions:
+	pci_release_regions(pdev);
+err_disable_device:
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	return err;
+}
+
+static void bgx_remove(struct pci_dev *pdev)
+{
+	struct bgx *bgx = pci_get_drvdata(pdev);
+	u8 lmac;
+
+	/* Disable all LMACs */
+	for (lmac = 0; lmac < bgx->lmac_count; lmac++)
+		bgx_lmac_disable(bgx, lmac);
+
+	bgx_vnic[bgx->bgx_id] = NULL;
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static struct pci_driver bgx_driver = {
+	.name = DRV_NAME,
+	.id_table = bgx_id_table,
+	.probe = bgx_probe,
+	.remove = bgx_remove,
+};
+
+static int __init bgx_init_module(void)
+{
+	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
+
+	return pci_register_driver(&bgx_driver);
+}
+
+static void __exit bgx_cleanup_module(void)
+{
+	pci_unregister_driver(&bgx_driver);
+}
+
+module_init(bgx_init_module);
+module_exit(bgx_cleanup_module);
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
new file mode 100644
index 000000000000..ba4f53b7cc2c
--- /dev/null
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -0,0 +1,220 @@
+/*
+ * Copyright (C) 2015 Cavium, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef THUNDER_BGX_H
+#define THUNDER_BGX_H
+
+#define    MAX_BGX_THUNDER			8 /* Max 4 nodes, 2 per node */
+#define    MAX_BGX_PER_CN88XX			2
+#define    MAX_LMAC_PER_BGX			4
+#define    MAX_BGX_CHANS_PER_LMAC		16
+#define    MAX_DMAC_PER_LMAC			8
+#define    MAX_FRAME_SIZE			9216
+
+#define    MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE	2
+
+#define    MAX_LMAC	(MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX)
+
+/* Registers */
+#define BGX_CMRX_CFG			0x00
+#define  CMR_PKT_TX_EN				BIT_ULL(13)
+#define  CMR_PKT_RX_EN				BIT_ULL(14)
+#define  CMR_EN					BIT_ULL(15)
+#define BGX_CMR_GLOBAL_CFG		0x08
+#define  CMR_GLOBAL_CFG_FCS_STRIP		BIT_ULL(6)
+#define BGX_CMRX_RX_ID_MAP		0x60
+#define BGX_CMRX_RX_STAT0		0x70
+#define BGX_CMRX_RX_STAT1		0x78
+#define BGX_CMRX_RX_STAT2		0x80
+#define BGX_CMRX_RX_STAT3		0x88
+#define BGX_CMRX_RX_STAT4		0x90
+#define BGX_CMRX_RX_STAT5		0x98
+#define BGX_CMRX_RX_STAT6		0xA0
+#define BGX_CMRX_RX_STAT7		0xA8
+#define BGX_CMRX_RX_STAT8		0xB0
+#define BGX_CMRX_RX_STAT9		0xB8
+#define BGX_CMRX_RX_STAT10		0xC0
+#define BGX_CMRX_RX_BP_DROP		0xC8
+#define BGX_CMRX_RX_DMAC_CTL		0x0E8
+#define BGX_CMR_RX_DMACX_CAM		0x200
+#define  RX_DMACX_CAM_EN			BIT_ULL(48)
+#define  RX_DMACX_CAM_LMACID(x)			(x << 49)
+#define  RX_DMAC_COUNT				32
+#define BGX_CMR_RX_STREERING		0x300
+#define  RX_TRAFFIC_STEER_RULE_COUNT		8
+#define BGX_CMR_CHAN_MSK_AND		0x450
+#define BGX_CMR_BIST_STATUS		0x460
+#define BGX_CMR_RX_LMACS		0x468
+#define BGX_CMRX_TX_STAT0		0x600
+#define BGX_CMRX_TX_STAT1		0x608
+#define BGX_CMRX_TX_STAT2		0x610
+#define BGX_CMRX_TX_STAT3		0x618
+#define BGX_CMRX_TX_STAT4		0x620
+#define BGX_CMRX_TX_STAT5		0x628
+#define BGX_CMRX_TX_STAT6		0x630
+#define BGX_CMRX_TX_STAT7		0x638
+#define BGX_CMRX_TX_STAT8		0x640
+#define BGX_CMRX_TX_STAT9		0x648
+#define BGX_CMRX_TX_STAT10		0x650
+#define BGX_CMRX_TX_STAT11		0x658
+#define BGX_CMRX_TX_STAT12		0x660
+#define BGX_CMRX_TX_STAT13		0x668
+#define BGX_CMRX_TX_STAT14		0x670
+#define BGX_CMRX_TX_STAT15		0x678
+#define BGX_CMRX_TX_STAT16		0x680
+#define BGX_CMRX_TX_STAT17		0x688
+#define BGX_CMR_TX_LMACS		0x1000
+
+#define BGX_SPUX_CONTROL1		0x10000
+#define  SPU_CTL_LOW_POWER			BIT_ULL(11)
+#define  SPU_CTL_RESET				BIT_ULL(15)
+#define BGX_SPUX_STATUS1		0x10008
+#define  SPU_STATUS1_RCV_LNK			BIT_ULL(2)
+#define BGX_SPUX_STATUS2		0x10020
+#define  SPU_STATUS2_RCVFLT			BIT_ULL(10)
+#define BGX_SPUX_BX_STATUS		0x10028
+#define  SPU_BX_STATUS_RX_ALIGN			BIT_ULL(12)
+#define BGX_SPUX_BR_STATUS1		0x10030
+#define  SPU_BR_STATUS_BLK_LOCK			BIT_ULL(0)
+#define  SPU_BR_STATUS_RCV_LNK			BIT_ULL(12)
+#define BGX_SPUX_BR_PMD_CRTL		0x10068
+#define  SPU_PMD_CRTL_TRAIN_EN			BIT_ULL(1)
+#define BGX_SPUX_BR_PMD_LP_CUP		0x10078
+#define BGX_SPUX_BR_PMD_LD_CUP		0x10088
+#define BGX_SPUX_BR_PMD_LD_REP		0x10090
+#define BGX_SPUX_FEC_CONTROL		0x100A0
+#define  SPU_FEC_CTL_FEC_EN			BIT_ULL(0)
+#define  SPU_FEC_CTL_ERR_EN			BIT_ULL(1)
+#define BGX_SPUX_AN_CONTROL		0x100C8
+#define  SPU_AN_CTL_AN_EN			BIT_ULL(12)
+#define  SPU_AN_CTL_XNP_EN			BIT_ULL(13)
+#define BGX_SPUX_AN_ADV			0x100D8
+#define BGX_SPUX_MISC_CONTROL		0x10218
+#define  SPU_MISC_CTL_INTLV_RDISP		BIT_ULL(10)
+#define  SPU_MISC_CTL_RX_DIS			BIT_ULL(12)
+#define BGX_SPUX_INT			0x10220	/* +(0..3) << 20 */
+#define BGX_SPUX_INT_W1S		0x10228
+#define BGX_SPUX_INT_ENA_W1C		0x10230
+#define BGX_SPUX_INT_ENA_W1S		0x10238
+#define BGX_SPU_DBG_CONTROL		0x10300
+#define  SPU_DBG_CTL_AN_ARB_LINK_CHK_EN		BIT_ULL(18)
+#define  SPU_DBG_CTL_AN_NONCE_MCT_DIS		BIT_ULL(29)
+
+#define BGX_SMUX_RX_INT			0x20000
+#define BGX_SMUX_RX_JABBER		0x20030
+#define BGX_SMUX_RX_CTL			0x20048
+#define  SMU_RX_CTL_STATUS			(3ull << 0)
+#define BGX_SMUX_TX_APPEND		0x20100
+#define  SMU_TX_APPEND_FCS_D			BIT_ULL(2)
+#define BGX_SMUX_TX_MIN_PKT		0x20118
+#define BGX_SMUX_TX_INT			0x20140
+#define BGX_SMUX_TX_CTL			0x20178
+#define  SMU_TX_CTL_DIC_EN			BIT_ULL(0)
+#define  SMU_TX_CTL_UNI_EN			BIT_ULL(1)
+#define  SMU_TX_CTL_LNK_STATUS			(3ull << 4)
+#define BGX_SMUX_TX_THRESH		0x20180
+#define BGX_SMUX_CTL			0x20200
+#define  SMU_CTL_RX_IDLE			BIT_ULL(0)
+#define  SMU_CTL_TX_IDLE			BIT_ULL(1)
+
+#define BGX_GMP_PCS_MRX_CTL		0x30000
+#define	 PCS_MRX_CTL_RST_AN			BIT_ULL(9)
+#define	 PCS_MRX_CTL_PWR_DN			BIT_ULL(11)
+#define	 PCS_MRX_CTL_AN_EN			BIT_ULL(12)
+#define	 PCS_MRX_CTL_RESET			BIT_ULL(15)
+#define BGX_GMP_PCS_MRX_STATUS		0x30008
+#define	 PCS_MRX_STATUS_AN_CPT			BIT_ULL(5)
+#define BGX_GMP_PCS_ANX_AN_RESULTS	0x30020
+#define BGX_GMP_PCS_SGM_AN_ADV		0x30068
+#define BGX_GMP_PCS_MISCX_CTL		0x30078
+#define  PCS_MISC_CTL_GMX_ENO			BIT_ULL(11)
+#define  PCS_MISC_CTL_SAMP_PT_MASK	0x7Full
+#define BGX_GMP_GMI_PRTX_CFG		0x38020
+#define  GMI_PORT_CFG_SPEED			BIT_ULL(1)
+#define  GMI_PORT_CFG_DUPLEX			BIT_ULL(2)
+#define  GMI_PORT_CFG_SLOT_TIME			BIT_ULL(3)
+#define  GMI_PORT_CFG_SPEED_MSB			BIT_ULL(8)
+#define BGX_GMP_GMI_RXX_JABBER		0x38038
+#define BGX_GMP_GMI_TXX_THRESH		0x38210
+#define BGX_GMP_GMI_TXX_APPEND		0x38218
+#define BGX_GMP_GMI_TXX_SLOT		0x38220
+#define BGX_GMP_GMI_TXX_BURST		0x38228
+#define BGX_GMP_GMI_TXX_MIN_PKT		0x38240
+#define BGX_GMP_GMI_TXX_SGMII_CTL	0x38300
+
+#define BGX_MSIX_VEC_0_29_ADDR		0x400000 /* +(0..29) << 4 */
+#define BGX_MSIX_VEC_0_29_CTL		0x400008
+#define BGX_MSIX_PBA_0			0x4F0000
+
+/* MSI-X interrupts */
+#define BGX_MSIX_VECTORS	30
+#define BGX_LMAC_VEC_OFFSET	7
+#define BGX_MSIX_VEC_SHIFT	4
+
+#define CMRX_INT		0
+#define SPUX_INT		1
+#define SMUX_RX_INT		2
+#define SMUX_TX_INT		3
+#define GMPX_PCS_INT		4
+#define GMPX_GMI_RX_INT		5
+#define GMPX_GMI_TX_INT		6
+#define CMR_MEM_INT		28
+#define SPU_MEM_INT		29
+
+#define LMAC_INTR_LINK_UP	BIT(0)
+#define LMAC_INTR_LINK_DOWN	BIT(1)
+
+/*  RX_DMAC_CTL configuration*/
+enum MCAST_MODE {
+		MCAST_MODE_REJECT,
+		MCAST_MODE_ACCEPT,
+		MCAST_MODE_CAM_FILTER,
+		RSVD
+};
+
+#define BCAST_ACCEPT	1
+#define CAM_ACCEPT	1
+
+void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac);
+unsigned bgx_get_map(int node);
+int bgx_get_lmac_count(int node, int bgx);
+const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid);
+void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac);
+void bgx_get_lmac_link_state(int node, int bgx_idx, int lmacid, void *status);
+u64 bgx_get_rx_stats(int node, int bgx_idx, int lmac, int idx);
+u64 bgx_get_tx_stats(int node, int bgx_idx, int lmac, int idx);
+#define BGX_RX_STATS_COUNT 11
+#define BGX_TX_STATS_COUNT 18
+
+struct bgx_stats {
+	u64 rx_stats[BGX_RX_STATS_COUNT];
+	u64 tx_stats[BGX_TX_STATS_COUNT];
+};
+
+enum LMAC_TYPE {
+	BGX_MODE_SGMII = 0, /* 1 lane, 1.250 Gbaud */
+	BGX_MODE_XAUI = 1,  /* 4 lanes, 3.125 Gbaud */
+	BGX_MODE_DXAUI = 1, /* 4 lanes, 6.250 Gbaud */
+	BGX_MODE_RXAUI = 2, /* 2 lanes, 6.250 Gbaud */
+	BGX_MODE_XFI = 3,   /* 1 lane, 10.3125 Gbaud */
+	BGX_MODE_XLAUI = 4, /* 4 lanes, 10.3125 Gbaud */
+	BGX_MODE_10G_KR = 3,/* 1 lane, 10.3125 Gbaud */
+	BGX_MODE_40G_KR = 4,/* 4 lanes, 10.3125 Gbaud */
+};
+
+enum qlm_mode {
+	QLM_MODE_SGMII,         /* SGMII, each lane independent */
+	QLM_MODE_XAUI_1X4,      /* 1 XAUI or DXAUI, 4 lanes */
+	QLM_MODE_RXAUI_2X2,     /* 2 RXAUI, 2 lanes each */
+	QLM_MODE_XFI_4X1,       /* 4 XFI, 1 lane each */
+	QLM_MODE_XLAUI_1X4,     /* 1 XLAUI, 4 lanes each */
+	QLM_MODE_10G_KR_4X1,    /* 4 10GBASE-KR, 1 lane each */
+	QLM_MODE_40G_KR4_1X4,   /* 1 40GBASE-KR4, 4 lanes each */
+};
+
+#endif /* THUNDER_BGX_H */
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index 7daa088a9bb7..a79813a17b6e 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_CHELSIO
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index b96e4bfcac41..8f7aa53a4c4b 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1025,19 +1025,19 @@ int t3_get_edc_fw(struct cphy *phy, int edc_idx, int size)
 {
 	struct adapter *adapter = phy->adapter;
 	const struct firmware *fw;
-	char buf[64];
+	const char *fw_name;
 	u32 csum;
 	const __be32 *p;
 	u16 *cache = phy->phy_cache;
-	int i, ret;
-
-	snprintf(buf, sizeof(buf), get_edc_fw_name(edc_idx));
+	int i, ret = -EINVAL;
 
-	ret = request_firmware(&fw, buf, &adapter->pdev->dev);
+	fw_name = get_edc_fw_name(edc_idx);
+	if (fw_name)
+		ret = request_firmware(&fw, fw_name, &adapter->pdev->dev);
 	if (ret < 0) {
 		dev_err(&adapter->pdev->dev,
 			"could not upgrade firmware: unable to load %s\n",
-			buf);
+			fw_name);
 		return ret;
 	}
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 524d11098c56..629f75d70353 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -46,17 +46,19 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
 #include <asm/io.h>
 #include "cxgb4_uld.h"
 
 #define CH_WARN(adap, fmt, ...) dev_warn(adap->pdev_dev, fmt, ## __VA_ARGS__)
 
 enum {
-	MAX_NPORTS = 4,     /* max # of ports */
-	SERNUM_LEN = 24,    /* Serial # length */
-	EC_LEN     = 16,    /* E/C length */
-	ID_LEN     = 16,    /* ID length */
-	PN_LEN     = 16,    /* Part Number length */
+	MAX_NPORTS	= 4,     /* max # of ports */
+	SERNUM_LEN	= 24,    /* Serial # length */
+	EC_LEN		= 16,    /* E/C length */
+	ID_LEN		= 16,    /* ID length */
+	PN_LEN		= 16,    /* Part Number length */
+	MACADDR_LEN	= 12,    /* MAC Address length */
 };
 
 enum {
@@ -198,23 +200,45 @@ struct lb_port_stats {
 };
 
 struct tp_tcp_stats {
-	u32 tcpOutRsts;
-	u64 tcpInSegs;
-	u64 tcpOutSegs;
-	u64 tcpRetransSegs;
+	u32 tcp_out_rsts;
+	u64 tcp_in_segs;
+	u64 tcp_out_segs;
+	u64 tcp_retrans_segs;
+};
+
+struct tp_usm_stats {
+	u32 frames;
+	u32 drops;
+	u64 octets;
+};
+
+struct tp_fcoe_stats {
+	u32 frames_ddp;
+	u32 frames_drop;
+	u64 octets_ddp;
 };
 
 struct tp_err_stats {
-	u32 macInErrs[4];
-	u32 hdrInErrs[4];
-	u32 tcpInErrs[4];
-	u32 tnlCongDrops[4];
-	u32 ofldChanDrops[4];
-	u32 tnlTxDrops[4];
-	u32 ofldVlanDrops[4];
-	u32 tcp6InErrs[4];
-	u32 ofldNoNeigh;
-	u32 ofldCongDefer;
+	u32 mac_in_errs[4];
+	u32 hdr_in_errs[4];
+	u32 tcp_in_errs[4];
+	u32 tnl_cong_drops[4];
+	u32 ofld_chan_drops[4];
+	u32 tnl_tx_drops[4];
+	u32 ofld_vlan_drops[4];
+	u32 tcp6_in_errs[4];
+	u32 ofld_no_neigh;
+	u32 ofld_cong_defer;
+};
+
+struct tp_cpl_stats {
+	u32 req[4];
+	u32 rsp[4];
+};
+
+struct tp_rdma_stats {
+	u32 rqe_dfr_pkt;
+	u32 rqe_dfr_mod;
 };
 
 struct sge_params {
@@ -224,7 +248,6 @@ struct sge_params {
 };
 
 struct tp_params {
-	unsigned int ntxchan;        /* # of Tx channels */
 	unsigned int tre;            /* log2 of core clocks per TP tick */
 	unsigned int la_mask;        /* what events are recorded by TP LA */
 	unsigned short tx_modq_map;  /* TX modulation scheduler queue to */
@@ -259,6 +282,7 @@ struct vpd_params {
 	u8 sn[SERNUM_LEN + 1];
 	u8 id[ID_LEN + 1];
 	u8 pn[PN_LEN + 1];
+	u8 na[MACADDR_LEN + 1];
 };
 
 struct pci_params {
@@ -273,6 +297,7 @@ struct pci_params {
 
 #define CHELSIO_T4		0x4
 #define CHELSIO_T5		0x5
+#define CHELSIO_T6		0x6
 
 enum chip_type {
 	T4_A1 = CHELSIO_CHIP_CODE(CHELSIO_T4, 1),
@@ -284,6 +309,10 @@ enum chip_type {
 	T5_A1 = CHELSIO_CHIP_CODE(CHELSIO_T5, 1),
 	T5_FIRST_REV	= T5_A0,
 	T5_LAST_REV	= T5_A1,
+
+	T6_A0 = CHELSIO_CHIP_CODE(CHELSIO_T6, 0),
+	T6_FIRST_REV    = T6_A0,
+	T6_LAST_REV     = T6_A0,
 };
 
 struct devlog_params {
@@ -292,6 +321,15 @@ struct devlog_params {
 	u32 size;                       /* size of log */
 };
 
+/* Stores chip specific parameters */
+struct arch_specific_params {
+	u8 nchan;
+	u16 mps_rplc_size;
+	u16 vfcount;
+	u32 sge_fl_db;
+	u16 mps_tcam_size;
+};
+
 struct adapter_params {
 	struct sge_params sge;
 	struct tp_params  tp;
@@ -317,6 +355,7 @@ struct adapter_params {
 	unsigned char nports;             /* # of ethernet ports */
 	unsigned char portvec;
 	enum chip_type chip;               /* chip code */
+	struct arch_specific_params arch;  /* chip specific params */
 	unsigned char offload;
 
 	unsigned char bypass;
@@ -328,6 +367,17 @@ struct adapter_params {
 	unsigned int max_ird_adapter;     /* Max read depth per adapter */
 };
 
+/* State needed to monitor the forward progress of SGE Ingress DMA activities
+ * and possible hangs.
+ */
+struct sge_idma_monitor_state {
+	unsigned int idma_1s_thresh;	/* 1s threshold in Core Clock ticks */
+	unsigned int idma_stalled[2];	/* synthesized stalled timers in HZ */
+	unsigned int idma_state[2];	/* IDMA Hang detect state */
+	unsigned int idma_qid[2];	/* IDMA Hung Ingress Queue ID */
+	unsigned int idma_warn[2];	/* time to warning in HZ */
+};
+
 #include "t4fw_api.h"
 
 #define FW_VERSION(chip) ( \
@@ -421,6 +471,7 @@ struct port_info {
 	u8     rss_mode;
 	struct link_config link_cfg;
 	u16   *rss;
+	struct port_stats stats_base;
 #ifdef CONFIG_CHELSIO_T4_DCB
 	struct port_dcb_info dcb;     /* Data Center Bridging support */
 #endif
@@ -630,12 +681,7 @@ struct sge {
 	u32 fl_align;               /* response queue message alignment */
 	u32 fl_starve_thres;        /* Free List starvation threshold */
 
-	/* State variables for detecting an SGE Ingress DMA hang */
-	unsigned int idma_1s_thresh;/* SGE same State Counter 1s threshold */
-	unsigned int idma_stalled[2];/* SGE synthesized stalled timers in HZ */
-	unsigned int idma_state[2]; /* SGE IDMA Hang detect state */
-	unsigned int idma_qid[2];   /* SGE IDMA Hung Ingress Queue ID */
-
+	struct sge_idma_monitor_state idma_monitor;
 	unsigned int egr_start;
 	unsigned int egr_sz;
 	unsigned int ingr_start;
@@ -644,6 +690,7 @@ struct sge {
 	struct sge_rspq **ingr_map; /* qid->queue ingress queue map */
 	unsigned long *starving_fl;
 	unsigned long *txq_maperr;
+	unsigned long *blocked_fl;
 	struct timer_list rx_timer; /* refills starving FLs */
 	struct timer_list tx_timer; /* checks Tx queues */
 };
@@ -665,6 +712,12 @@ struct l2t_data;
 
 #endif
 
+struct doorbell_stats {
+	u32 db_drop;
+	u32 db_empty;
+	u32 db_full;
+};
+
 struct adapter {
 	void __iomem *regs;
 	void __iomem *bar2;
@@ -672,7 +725,7 @@ struct adapter {
 	struct pci_dev *pdev;
 	struct device *pdev_dev;
 	unsigned int mbox;
-	unsigned int fn;
+	unsigned int pf;
 	unsigned int flags;
 	enum chip_type chip;
 
@@ -682,13 +735,12 @@ struct adapter {
 	struct cxgb4_virt_res vres;
 	unsigned int swintr;
 
-	unsigned int wol;
-
 	struct {
 		unsigned short vec;
 		char desc[IFNAMSIZ + 10];
 	} msix_info[MAX_INGQ + 1];
 
+	struct doorbell_stats db_stats;
 	struct sge sge;
 
 	struct net_device *port[MAX_NPORTS];
@@ -843,6 +895,16 @@ enum {
 	VLAN_REWRITE
 };
 
+static inline int is_offload(const struct adapter *adap)
+{
+	return adap->params.offload;
+}
+
+static inline int is_t6(enum chip_type chip)
+{
+	return CHELSIO_CHIP_VERSION(chip) == CHELSIO_T6;
+}
+
 static inline int is_t5(enum chip_type chip)
 {
 	return CHELSIO_CHIP_VERSION(chip) == CHELSIO_T5;
@@ -887,6 +949,22 @@ static inline void t4_write_reg64(struct adapter *adap, u32 reg_addr, u64 val)
 }
 
 /**
+ * t4_set_hw_addr - store a port's MAC address in SW
+ * @adapter: the adapter
+ * @port_idx: the port index
+ * @hw_addr: the Ethernet address
+ *
+ * Store the Ethernet address of the given port in SW.  Called by the common
+ * code when it retrieves a port's Ethernet address from EEPROM.
+ */
+static inline void t4_set_hw_addr(struct adapter *adapter, int port_idx,
+				  u8 hw_addr[])
+{
+	ether_addr_copy(adapter->port[port_idx]->dev_addr, hw_addr);
+	ether_addr_copy(adapter->port[port_idx]->perm_addr, hw_addr);
+}
+
+/**
  * netdev2pinfo - return the port_info structure associated with a net_device
  * @dev: the netdev
  *
@@ -1055,7 +1133,7 @@ int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
 int t4_ofld_send(struct adapter *adap, struct sk_buff *skb);
 int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     struct net_device *dev, int intr_idx,
-		     struct sge_fl *fl, rspq_handler_t hnd);
+		     struct sge_fl *fl, rspq_handler_t hnd, int cong);
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
 			 unsigned int iqid);
@@ -1095,6 +1173,19 @@ static inline int is_bypass_device(int device)
 	}
 }
 
+static inline int is_10gbt_device(int device)
+{
+	/* this should be set based upon device capabilities */
+	switch (device) {
+	case 0x4409:
+	case 0x4486:
+		return 1;
+
+	default:
+		return 0;
+	}
+}
+
 static inline unsigned int core_ticks_per_usec(const struct adapter *adap)
 {
 	return adap->params.vpd.cclk / 1000;
@@ -1117,9 +1208,19 @@ static inline unsigned int core_ticks_to_us(const struct adapter *adapter,
 void t4_set_reg_field(struct adapter *adap, unsigned int addr, u32 mask,
 		      u32 val);
 
+int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
+			    int size, void *rpl, bool sleep_ok, int timeout);
 int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
 		    void *rpl, bool sleep_ok);
 
+static inline int t4_wr_mbox_timeout(struct adapter *adap, int mbox,
+				     const void *cmd, int size, void *rpl,
+				     int timeout)
+{
+	return t4_wr_mbox_meat_timeout(adap, mbox, cmd, size, rpl, true,
+				       timeout);
+}
+
 static inline int t4_wr_mbox(struct adapter *adap, int mbox, const void *cmd,
 			     int size, void *rpl)
 {
@@ -1147,10 +1248,14 @@ void t4_intr_disable(struct adapter *adapter);
 int t4_slow_intr_handler(struct adapter *adapter);
 
 int t4_wait_dev_ready(void __iomem *regs);
-int t4_link_start(struct adapter *adap, unsigned int mbox, unsigned int port,
+int t4_link_l1cfg(struct adapter *adap, unsigned int mbox, unsigned int port,
 		  struct link_config *lc);
 int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port);
 
+u32 t4_read_pcie_cfg4(struct adapter *adap, int reg);
+u32 t4_get_util_window(struct adapter *adap);
+void t4_setup_memwin(struct adapter *adap, u32 memwin_base, u32 window);
+
 #define T4_MEMORY_WRITE	0
 #define T4_MEMORY_READ	1
 int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len,
@@ -1165,10 +1270,16 @@ unsigned int t4_get_regs_len(struct adapter *adapter);
 void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size);
 
 int t4_seeprom_wp(struct adapter *adapter, bool enable);
-int get_vpd_params(struct adapter *adapter, struct vpd_params *p);
+int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p);
+int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p);
 int t4_read_flash(struct adapter *adapter, unsigned int addr,
 		  unsigned int nwords, u32 *data, int byte_oriented);
 int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
+int t4_load_phy_fw(struct adapter *adap,
+		   int win, spinlock_t *lock,
+		   int (*phy_fw_version)(const u8 *, size_t),
+		   const u8 *phy_fw_data, size_t phy_fw_size);
+int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver);
 int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op);
 int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 		  const u8 *fw_data, unsigned int size, int force);
@@ -1182,9 +1293,10 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 int t4_prep_adapter(struct adapter *adapter);
 
 enum t4_bar2_qtype { T4_BAR2_QTYPE_EGRESS, T4_BAR2_QTYPE_INGRESS };
-int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
+int t4_bar2_sge_qregs(struct adapter *adapter,
 		      unsigned int qid,
 		      enum t4_bar2_qtype qtype,
+		      int user,
 		      u64 *pbar2_qoffset,
 		      unsigned int *pbar2_qid);
 
@@ -1195,12 +1307,15 @@ int t4_init_devlog_params(struct adapter *adapter);
 int t4_init_sge_params(struct adapter *adapter);
 int t4_init_tp_params(struct adapter *adap);
 int t4_filter_field_shift(const struct adapter *adap, int filter_sel);
+int t4_init_rss_mode(struct adapter *adap, int mbox);
 int t4_port_init(struct adapter *adap, int mbox, int pf, int vf);
 void t4_fatal_err(struct adapter *adapter);
 int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid,
 			int start, int n, const u16 *rspq, unsigned int nrspq);
 int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode,
 		       unsigned int flags);
+int t4_config_vi_rss(struct adapter *adapter, int mbox, unsigned int viid,
+		     unsigned int flags, unsigned int defq);
 int t4_read_rss(struct adapter *adapter, u16 *entries);
 void t4_read_rss_key(struct adapter *adapter, u32 *key);
 void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx);
@@ -1211,10 +1326,7 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
 u32 t4_read_rss_pf_map(struct adapter *adapter);
 u32 t4_read_rss_pf_mask(struct adapter *adapter);
 
-int t4_mc_read(struct adapter *adap, int idx, u32 addr, __be32 *data,
-	       u64 *parity);
-int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data,
-		u64 *parity);
+unsigned int t4_get_mps_bg_map(struct adapter *adapter, int idx);
 void t4_pmtx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[]);
 void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[]);
 int t4_read_cim_ibq(struct adapter *adap, unsigned int qid, u32 *data,
@@ -1226,21 +1338,36 @@ int t4_cim_read(struct adapter *adap, unsigned int addr, unsigned int n,
 int t4_cim_write(struct adapter *adap, unsigned int addr, unsigned int n,
 		 const unsigned int *valp);
 int t4_cim_read_la(struct adapter *adap, u32 *la_buf, unsigned int *wrptr);
+void t4_cim_read_pif_la(struct adapter *adap, u32 *pif_req, u32 *pif_rsp,
+			unsigned int *pif_req_wrptr,
+			unsigned int *pif_rsp_wrptr);
+void t4_cim_read_ma_la(struct adapter *adap, u32 *ma_req, u32 *ma_rsp);
 void t4_read_cimq_cfg(struct adapter *adap, u16 *base, u16 *size, u16 *thres);
 const char *t4_get_port_type_description(enum fw_port_type port_type);
 void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p);
+void t4_get_port_stats_offset(struct adapter *adap, int idx,
+			      struct port_stats *stats,
+			      struct port_stats *offset);
+void t4_get_lb_stats(struct adapter *adap, int idx, struct lb_port_stats *p);
 void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log);
 void t4_read_cong_tbl(struct adapter *adap, u16 incr[NMTUS][NCCTRL_WIN]);
 void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr,
 			    unsigned int mask, unsigned int val);
 void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr);
+void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st);
+void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st);
+void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st);
+void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st);
 void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 			 struct tp_tcp_stats *v6);
+void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx,
+		       struct tp_fcoe_stats *st);
 void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
 		  const unsigned short *alpha, const unsigned short *beta);
 
 void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf);
 
+void t4_get_chan_txrate(struct adapter *adap, u64 *nic_rate, u64 *ofld_rate);
 void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid);
 
 void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
@@ -1259,13 +1386,16 @@ int t4_fw_initialize(struct adapter *adap, unsigned int mbox);
 int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int nparams, const u32 *params,
 		    u32 *val);
+int t4_query_params_rw(struct adapter *adap, unsigned int mbox, unsigned int pf,
+		       unsigned int vf, unsigned int nparams, const u32 *params,
+		       u32 *val, int rw);
+int t4_set_params_timeout(struct adapter *adap, unsigned int mbox,
+			  unsigned int pf, unsigned int vf,
+			  unsigned int nparams, const u32 *params,
+			  const u32 *val, int timeout);
 int t4_set_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		  unsigned int vf, unsigned int nparams, const u32 *params,
 		  const u32 *val);
-int t4_set_params_nosleep(struct adapter *adap, unsigned int mbox,
-			  unsigned int pf, unsigned int vf,
-			  unsigned int nparams, const u32 *params,
-			  const u32 *val);
 int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		unsigned int vf, unsigned int txq, unsigned int txq_eth_ctrl,
 		unsigned int rxqi, unsigned int rxq, unsigned int tc,
@@ -1274,6 +1404,9 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
 int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		unsigned int pf, unsigned int vf, unsigned int nmac, u8 *mac,
 		unsigned int *rss_size);
+int t4_free_vi(struct adapter *adap, unsigned int mbox,
+	       unsigned int pf, unsigned int vf,
+	       unsigned int viid);
 int t4_set_rxmode(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		int mtu, int promisc, int all_multi, int bcast, int vlanex,
 		bool sleep_ok);
@@ -1303,6 +1436,7 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
 int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
+int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox);
 int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl);
 void t4_db_full(struct adapter *adapter);
 void t4_db_dropped(struct adapter *adapter);
@@ -1310,4 +1444,9 @@ int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
 			 u32 addr, u32 val);
 void t4_sge_decode_idma_state(struct adapter *adapter, int state);
 void t4_free_mem(void *addr);
+void t4_idma_monitor_init(struct adapter *adapter,
+			  struct sge_idma_monitor_state *idma);
+void t4_idma_monitor(struct adapter *adapter,
+		     struct sge_idma_monitor_state *idma,
+		     int hz, int ticks);
 #endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 371f75e782e5..484eb8c37489 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -182,6 +182,95 @@ static const struct file_operations cim_la_fops = {
 	.release = seq_release_private
 };
 
+static int cim_pif_la_show(struct seq_file *seq, void *v, int idx)
+{
+	const u32 *p = v;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Cntl ID DataBE   Addr                 Data\n");
+	} else if (idx < CIM_PIFLA_SIZE) {
+		seq_printf(seq, " %02x  %02x  %04x  %08x %08x%08x%08x%08x\n",
+			   (p[5] >> 22) & 0xff, (p[5] >> 16) & 0x3f,
+			   p[5] & 0xffff, p[4], p[3], p[2], p[1], p[0]);
+	} else {
+		if (idx == CIM_PIFLA_SIZE)
+			seq_puts(seq, "\nCntl ID               Data\n");
+		seq_printf(seq, " %02x  %02x %08x%08x%08x%08x\n",
+			   (p[4] >> 6) & 0xff, p[4] & 0x3f,
+			   p[3], p[2], p[1], p[0]);
+	}
+	return 0;
+}
+
+static int cim_pif_la_open(struct inode *inode, struct file *file)
+{
+	struct seq_tab *p;
+	struct adapter *adap = inode->i_private;
+
+	p = seq_open_tab(file, 2 * CIM_PIFLA_SIZE, 6 * sizeof(u32), 1,
+			 cim_pif_la_show);
+	if (!p)
+		return -ENOMEM;
+
+	t4_cim_read_pif_la(adap, (u32 *)p->data,
+			   (u32 *)p->data + 6 * CIM_PIFLA_SIZE, NULL, NULL);
+	return 0;
+}
+
+static const struct file_operations cim_pif_la_fops = {
+	.owner   = THIS_MODULE,
+	.open    = cim_pif_la_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private
+};
+
+static int cim_ma_la_show(struct seq_file *seq, void *v, int idx)
+{
+	const u32 *p = v;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "\n");
+	} else if (idx < CIM_MALA_SIZE) {
+		seq_printf(seq, "%02x%08x%08x%08x%08x\n",
+			   p[4], p[3], p[2], p[1], p[0]);
+	} else {
+		if (idx == CIM_MALA_SIZE)
+			seq_puts(seq,
+				 "\nCnt ID Tag UE       Data       RDY VLD\n");
+		seq_printf(seq, "%3u %2u  %x   %u %08x%08x  %u   %u\n",
+			   (p[2] >> 10) & 0xff, (p[2] >> 7) & 7,
+			   (p[2] >> 3) & 0xf, (p[2] >> 2) & 1,
+			   (p[1] >> 2) | ((p[2] & 3) << 30),
+			   (p[0] >> 2) | ((p[1] & 3) << 30), (p[0] >> 1) & 1,
+			   p[0] & 1);
+	}
+	return 0;
+}
+
+static int cim_ma_la_open(struct inode *inode, struct file *file)
+{
+	struct seq_tab *p;
+	struct adapter *adap = inode->i_private;
+
+	p = seq_open_tab(file, 2 * CIM_MALA_SIZE, 5 * sizeof(u32), 1,
+			 cim_ma_la_show);
+	if (!p)
+		return -ENOMEM;
+
+	t4_cim_read_ma_la(adap, (u32 *)p->data,
+			  (u32 *)p->data + 5 * CIM_MALA_SIZE);
+	return 0;
+}
+
+static const struct file_operations cim_ma_la_fops = {
+	.owner   = THIS_MODULE,
+	.open    = cim_ma_la_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private
+};
+
 static int cim_qcfg_show(struct seq_file *seq, void *v)
 {
 	static const char * const qname[] = {
@@ -663,6 +752,39 @@ static const struct file_operations pm_stats_debugfs_fops = {
 	.write   = pm_stats_clear
 };
 
+static int tx_rate_show(struct seq_file *seq, void *v)
+{
+	u64 nrate[NCHAN], orate[NCHAN];
+	struct adapter *adap = seq->private;
+
+	t4_get_chan_txrate(adap, nrate, orate);
+	if (adap->params.arch.nchan == NCHAN) {
+		seq_puts(seq, "              channel 0   channel 1   "
+			 "channel 2   channel 3\n");
+		seq_printf(seq, "NIC B/s:     %10llu  %10llu  %10llu  %10llu\n",
+			   (unsigned long long)nrate[0],
+			   (unsigned long long)nrate[1],
+			   (unsigned long long)nrate[2],
+			   (unsigned long long)nrate[3]);
+		seq_printf(seq, "Offload B/s: %10llu  %10llu  %10llu  %10llu\n",
+			   (unsigned long long)orate[0],
+			   (unsigned long long)orate[1],
+			   (unsigned long long)orate[2],
+			   (unsigned long long)orate[3]);
+	} else {
+		seq_puts(seq, "              channel 0   channel 1\n");
+		seq_printf(seq, "NIC B/s:     %10llu  %10llu\n",
+			   (unsigned long long)nrate[0],
+			   (unsigned long long)nrate[1]);
+		seq_printf(seq, "Offload B/s: %10llu  %10llu\n",
+			   (unsigned long long)orate[0],
+			   (unsigned long long)orate[1]);
+	}
+	return 0;
+}
+
+DEFINE_SIMPLE_DEBUGFS_FILE(tx_rate);
+
 static int cctrl_tbl_show(struct seq_file *seq, void *v)
 {
 	static const char * const dec_fac[] = {
@@ -1084,41 +1206,89 @@ static inline void tcamxy2valmask(u64 x, u64 y, u8 *addr, u64 *mask)
 
 static int mps_tcam_show(struct seq_file *seq, void *v)
 {
-	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "Idx  Ethernet address     Mask     Vld Ports PF"
-			 "  VF              Replication             "
-			 "P0 P1 P2 P3  ML\n");
-	else {
+	struct adapter *adap = seq->private;
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
+
+	if (v == SEQ_START_TOKEN) {
+		if (adap->params.arch.mps_rplc_size > 128)
+			seq_puts(seq, "Idx  Ethernet address     Mask     "
+				 "Vld Ports PF  VF                           "
+				 "Replication                                "
+				 "    P0 P1 P2 P3  ML\n");
+		else
+			seq_puts(seq, "Idx  Ethernet address     Mask     "
+				 "Vld Ports PF  VF              Replication"
+				 "	         P0 P1 P2 P3  ML\n");
+	} else {
 		u64 mask;
 		u8 addr[ETH_ALEN];
-		struct adapter *adap = seq->private;
+		bool replicate;
 		unsigned int idx = (uintptr_t)v - 2;
-		u64 tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx));
-		u64 tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx));
-		u32 cls_lo = t4_read_reg(adap, MPS_CLS_SRAM_L(idx));
-		u32 cls_hi = t4_read_reg(adap, MPS_CLS_SRAM_H(idx));
-		u32 rplc[4] = {0, 0, 0, 0};
+		u64 tcamy, tcamx, val;
+		u32 cls_lo, cls_hi, ctl;
+		u32 rplc[8] = {0};
+
+		if (chip_ver > CHELSIO_T5) {
+			/* CtlCmdType - 0: Read, 1: Write
+			 * CtlTcamSel - 0: TCAM0, 1: TCAM1
+			 * CtlXYBitSel- 0: Y bit, 1: X bit
+			 */
+
+			/* Read tcamy */
+			ctl = CTLCMDTYPE_V(0) | CTLXYBITSEL_V(0);
+			if (idx < 256)
+				ctl |= CTLTCAMINDEX_V(idx) | CTLTCAMSEL_V(0);
+			else
+				ctl |= CTLTCAMINDEX_V(idx - 256) |
+				       CTLTCAMSEL_V(1);
+			t4_write_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A, ctl);
+			val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A);
+			tcamy = DMACH_G(val) << 32;
+			tcamy |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A);
+
+			/* Read tcamx. Change the control param */
+			ctl |= CTLXYBITSEL_V(1);
+			t4_write_reg(adap, MPS_CLS_TCAM_DATA2_CTL_A, ctl);
+			val = t4_read_reg(adap, MPS_CLS_TCAM_DATA1_A);
+			tcamx = DMACH_G(val) << 32;
+			tcamx |= t4_read_reg(adap, MPS_CLS_TCAM_DATA0_A);
+		} else {
+			tcamy = t4_read_reg64(adap, MPS_CLS_TCAM_Y_L(idx));
+			tcamx = t4_read_reg64(adap, MPS_CLS_TCAM_X_L(idx));
+		}
+
+		cls_lo = t4_read_reg(adap, MPS_CLS_SRAM_L(idx));
+		cls_hi = t4_read_reg(adap, MPS_CLS_SRAM_H(idx));
 
 		if (tcamx & tcamy) {
 			seq_printf(seq, "%3u         -\n", idx);
 			goto out;
 		}
 
-		if (cls_lo & REPLICATE_F) {
+		rplc[0] = rplc[1] = rplc[2] = rplc[3] = 0;
+		if (chip_ver > CHELSIO_T5)
+			replicate = (cls_lo & T6_REPLICATE_F);
+		else
+			replicate = (cls_lo & REPLICATE_F);
+
+		if (replicate) {
 			struct fw_ldst_cmd ldst_cmd;
 			int ret;
+			struct fw_ldst_mps_rplc mps_rplc;
+			u32 ldst_addrspc;
 
 			memset(&ldst_cmd, 0, sizeof(ldst_cmd));
+			ldst_addrspc =
+				FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MPS);
 			ldst_cmd.op_to_addrspace =
 				htonl(FW_CMD_OP_V(FW_LDST_CMD) |
 				      FW_CMD_REQUEST_F |
 				      FW_CMD_READ_F |
-				      FW_LDST_CMD_ADDRSPACE_V(
-					      FW_LDST_ADDRSPC_MPS));
+				      ldst_addrspc);
 			ldst_cmd.cycles_to_len16 = htonl(FW_LEN16(ldst_cmd));
-			ldst_cmd.u.mps.fid_ctl =
+			ldst_cmd.u.mps.rplc.fid_idx =
 				htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) |
-				      FW_LDST_CMD_CTL_V(idx));
+				      FW_LDST_CMD_IDX_V(idx));
 			ret = t4_wr_mbox(adap, adap->mbox, &ldst_cmd,
 					 sizeof(ldst_cmd), &ldst_cmd);
 			if (ret)
@@ -1126,30 +1296,69 @@ static int mps_tcam_show(struct seq_file *seq, void *v)
 					 "replication map for idx %d: %d\n",
 					 idx, -ret);
 			else {
-				rplc[0] = ntohl(ldst_cmd.u.mps.rplc31_0);
-				rplc[1] = ntohl(ldst_cmd.u.mps.rplc63_32);
-				rplc[2] = ntohl(ldst_cmd.u.mps.rplc95_64);
-				rplc[3] = ntohl(ldst_cmd.u.mps.rplc127_96);
+				mps_rplc = ldst_cmd.u.mps.rplc;
+				rplc[0] = ntohl(mps_rplc.rplc31_0);
+				rplc[1] = ntohl(mps_rplc.rplc63_32);
+				rplc[2] = ntohl(mps_rplc.rplc95_64);
+				rplc[3] = ntohl(mps_rplc.rplc127_96);
+				if (adap->params.arch.mps_rplc_size > 128) {
+					rplc[4] = ntohl(mps_rplc.rplc159_128);
+					rplc[5] = ntohl(mps_rplc.rplc191_160);
+					rplc[6] = ntohl(mps_rplc.rplc223_192);
+					rplc[7] = ntohl(mps_rplc.rplc255_224);
+				}
 			}
 		}
 
 		tcamxy2valmask(tcamx, tcamy, addr, &mask);
-		seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x %012llx"
-			   "%3c   %#x%4u%4d",
-			   idx, addr[0], addr[1], addr[2], addr[3], addr[4],
-			   addr[5], (unsigned long long)mask,
-			   (cls_lo & SRAM_VLD_F) ? 'Y' : 'N', PORTMAP_G(cls_hi),
-			   PF_G(cls_lo),
-			   (cls_lo & VF_VALID_F) ? VF_G(cls_lo) : -1);
-		if (cls_lo & REPLICATE_F)
-			seq_printf(seq, " %08x %08x %08x %08x",
-				   rplc[3], rplc[2], rplc[1], rplc[0]);
+		if (chip_ver > CHELSIO_T5)
+			seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x "
+				   "%012llx%3c   %#x%4u%4d",
+				   idx, addr[0], addr[1], addr[2], addr[3],
+				   addr[4], addr[5], (unsigned long long)mask,
+				   (cls_lo & T6_SRAM_VLD_F) ? 'Y' : 'N',
+				   PORTMAP_G(cls_hi),
+				   T6_PF_G(cls_lo),
+				   (cls_lo & T6_VF_VALID_F) ?
+				   T6_VF_G(cls_lo) : -1);
 		else
-			seq_printf(seq, "%36c", ' ');
-		seq_printf(seq, "%4u%3u%3u%3u %#x\n",
-			   SRAM_PRIO0_G(cls_lo), SRAM_PRIO1_G(cls_lo),
-			   SRAM_PRIO2_G(cls_lo), SRAM_PRIO3_G(cls_lo),
-			   (cls_lo >> MULTILISTEN0_S) & 0xf);
+			seq_printf(seq, "%3u %02x:%02x:%02x:%02x:%02x:%02x "
+				   "%012llx%3c   %#x%4u%4d",
+				   idx, addr[0], addr[1], addr[2], addr[3],
+				   addr[4], addr[5], (unsigned long long)mask,
+				   (cls_lo & SRAM_VLD_F) ? 'Y' : 'N',
+				   PORTMAP_G(cls_hi),
+				   PF_G(cls_lo),
+				   (cls_lo & VF_VALID_F) ? VF_G(cls_lo) : -1);
+
+		if (replicate) {
+			if (adap->params.arch.mps_rplc_size > 128)
+				seq_printf(seq, " %08x %08x %08x %08x "
+					   "%08x %08x %08x %08x",
+					   rplc[7], rplc[6], rplc[5], rplc[4],
+					   rplc[3], rplc[2], rplc[1], rplc[0]);
+			else
+				seq_printf(seq, " %08x %08x %08x %08x",
+					   rplc[3], rplc[2], rplc[1], rplc[0]);
+		} else {
+			if (adap->params.arch.mps_rplc_size > 128)
+				seq_printf(seq, "%72c", ' ');
+			else
+				seq_printf(seq, "%36c", ' ');
+		}
+
+		if (chip_ver > CHELSIO_T5)
+			seq_printf(seq, "%4u%3u%3u%3u %#x\n",
+				   T6_SRAM_PRIO0_G(cls_lo),
+				   T6_SRAM_PRIO1_G(cls_lo),
+				   T6_SRAM_PRIO2_G(cls_lo),
+				   T6_SRAM_PRIO3_G(cls_lo),
+				   (cls_lo >> T6_MULTILISTEN0_S) & 0xf);
+		else
+			seq_printf(seq, "%4u%3u%3u%3u %#x\n",
+				   SRAM_PRIO0_G(cls_lo), SRAM_PRIO1_G(cls_lo),
+				   SRAM_PRIO2_G(cls_lo), SRAM_PRIO3_G(cls_lo),
+				   (cls_lo >> MULTILISTEN0_S) & 0xf);
 	}
 out:	return 0;
 }
@@ -1222,7 +1431,7 @@ static int sensors_show(struct seq_file *seq, void *v)
 	param[1] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
 		    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DIAG) |
 		    FW_PARAMS_PARAM_Y_V(FW_PARAM_DEV_DIAG_VDD));
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2,
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
 			      param, val);
 
 	if (ret < 0 || val[0] == 0)
@@ -1416,6 +1625,9 @@ static int rss_config_show(struct seq_file *seq, void *v)
 	seq_printf(seq, "  HashDelay:     %3d\n", HASHDELAY_G(rssconf));
 	if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
 		seq_printf(seq, "  VfWrAddr:      %3d\n", VFWRADDR_G(rssconf));
+	else
+		seq_printf(seq, "  VfWrAddr:      %3d\n",
+			   T6_VFWRADDR_G(rssconf));
 	seq_printf(seq, "  KeyMode:       %s\n", keymode[KEYMODE_G(rssconf)]);
 	seq_printf(seq, "  VfWrEn:        %3s\n", yesno(rssconf & VFWREN_F));
 	seq_printf(seq, "  KeyWrEn:       %3s\n", yesno(rssconf & KEYWREN_F));
@@ -1634,14 +1846,14 @@ static int rss_vf_config_open(struct inode *inode, struct file *file)
 	struct adapter *adapter = inode->i_private;
 	struct seq_tab *p;
 	struct rss_vf_conf *vfconf;
-	int vf;
+	int vf, vfcount = adapter->params.arch.vfcount;
 
-	p = seq_open_tab(file, 128, sizeof(*vfconf), 1, rss_vf_config_show);
+	p = seq_open_tab(file, vfcount, sizeof(*vfconf), 1, rss_vf_config_show);
 	if (!p)
 		return -ENOMEM;
 
 	vfconf = (struct rss_vf_conf *)p->data;
-	for (vf = 0; vf < 128; vf++) {
+	for (vf = 0; vf < vfcount; vf++) {
 		t4_read_rss_vf_config(adapter, vf, &vfconf[vf].rss_vf_vfl,
 				      &vfconf[vf].rss_vf_vfh);
 	}
@@ -1959,6 +2171,61 @@ static void add_debugfs_mem(struct adapter *adap, const char *name,
 				 size_mb << 20);
 }
 
+static int blocked_fl_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+static ssize_t blocked_fl_read(struct file *filp, char __user *ubuf,
+			       size_t count, loff_t *ppos)
+{
+	int len;
+	const struct adapter *adap = filp->private_data;
+	char *buf;
+	ssize_t size = (adap->sge.egr_sz + 3) / 4 +
+			adap->sge.egr_sz / 32 + 2; /* includes ,/\n/\0 */
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = snprintf(buf, size - 1, "%*pb\n",
+		       adap->sge.egr_sz, adap->sge.blocked_fl);
+	len += sprintf(buf + len, "\n");
+	size = simple_read_from_buffer(ubuf, count, ppos, buf, len);
+	t4_free_mem(buf);
+	return size;
+}
+
+static ssize_t blocked_fl_write(struct file *filp, const char __user *ubuf,
+				size_t count, loff_t *ppos)
+{
+	int err;
+	unsigned long *t;
+	struct adapter *adap = filp->private_data;
+
+	t = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz), sizeof(long), GFP_KERNEL);
+	if (!t)
+		return -ENOMEM;
+
+	err = bitmap_parse_user(ubuf, count, t, adap->sge.egr_sz);
+	if (err)
+		return err;
+
+	bitmap_copy(adap->sge.blocked_fl, t, adap->sge.egr_sz);
+	t4_free_mem(t);
+	return count;
+}
+
+static const struct file_operations blocked_fl_fops = {
+	.owner   = THIS_MODULE,
+	.open    = blocked_fl_open,
+	.read    = blocked_fl_read,
+	.write   = blocked_fl_write,
+	.llseek  = generic_file_llseek,
+};
+
 /* Add an array of Debug FS files.
  */
 void add_debugfs_files(struct adapter *adap,
@@ -1978,11 +2245,13 @@ void add_debugfs_files(struct adapter *adap,
 int t4_setup_debugfs(struct adapter *adap)
 {
 	int i;
-	u32 size;
+	u32 size = 0;
 	struct dentry *de;
 
 	static struct t4_debugfs_entry t4_debugfs_files[] = {
 		{ "cim_la", &cim_la_fops, S_IRUSR, 0 },
+		{ "cim_pif_la", &cim_pif_la_fops, S_IRUSR, 0 },
+		{ "cim_ma_la", &cim_ma_la_fops, S_IRUSR, 0 },
 		{ "cim_qcfg", &cim_qcfg_fops, S_IRUSR, 0 },
 		{ "clk", &clk_debugfs_fops, S_IRUSR, 0 },
 		{ "devlog", &devlog_fops, S_IRUSR, 0 },
@@ -2018,10 +2287,12 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "ulprx_la", &ulprx_la_fops, S_IRUSR, 0 },
 		{ "sensors", &sensors_debugfs_fops, S_IRUSR, 0 },
 		{ "pm_stats", &pm_stats_debugfs_fops, S_IRUSR, 0 },
+		{ "tx_rate", &tx_rate_debugfs_fops, S_IRUSR, 0 },
 		{ "cctrl", &cctrl_tbl_debugfs_fops, S_IRUSR, 0 },
 #if IS_ENABLED(CONFIG_IPV6)
 		{ "clip_tbl", &clip_tbl_debugfs_fops, S_IRUSR, 0 },
 #endif
+		{ "blocked_fl", &blocked_fl_fops, S_IRUSR | S_IWUSR, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
@@ -2048,12 +2319,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		size = t4_read_reg(adap, MA_EDRAM1_BAR_A);
 		add_debugfs_mem(adap, "edc1", MEM_EDC1, EDRAM1_SIZE_G(size));
 	}
-	if (is_t4(adap->params.chip)) {
-		size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
-		if (i & EXT_MEM_ENABLE_F)
-			add_debugfs_mem(adap, "mc", MEM_MC,
-					EXT_MEM_SIZE_G(size));
-	} else {
+	if (is_t5(adap->params.chip)) {
 		if (i & EXT_MEM0_ENABLE_F) {
 			size = t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A);
 			add_debugfs_mem(adap, "mc0", MEM_MC0,
@@ -2064,6 +2330,11 @@ int t4_setup_debugfs(struct adapter *adap)
 			add_debugfs_mem(adap, "mc1", MEM_MC1,
 					EXT_MEM1_SIZE_G(size));
 		}
+	} else {
+		if (i & EXT_MEM_ENABLE_F)
+			size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
+			add_debugfs_mem(adap, "mc", MEM_MC,
+					EXT_MEM_SIZE_G(size));
 	}
 
 	de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 10d82b51d7ef..687acf71fa15 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -108,15 +108,82 @@ static const char stats_strings[][ETH_GSTRING_LEN] = {
 	"VLANinsertions     ",
 	"GROpackets         ",
 	"GROmerged          ",
-	"WriteCoalSuccess   ",
-	"WriteCoalFail      ",
+};
+
+static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
+	"db_drop                ",
+	"db_full                ",
+	"db_empty               ",
+	"tcp_ipv4_out_rsts      ",
+	"tcp_ipv4_in_segs       ",
+	"tcp_ipv4_out_segs      ",
+	"tcp_ipv4_retrans_segs  ",
+	"tcp_ipv6_out_rsts      ",
+	"tcp_ipv6_in_segs       ",
+	"tcp_ipv6_out_segs      ",
+	"tcp_ipv6_retrans_segs  ",
+	"usm_ddp_frames         ",
+	"usm_ddp_octets         ",
+	"usm_ddp_drops          ",
+	"rdma_no_rqe_mod_defer  ",
+	"rdma_no_rqe_pkt_defer  ",
+	"tp_err_ofld_no_neigh   ",
+	"tp_err_ofld_cong_defer ",
+	"write_coal_success     ",
+	"write_coal_fail        ",
+};
+
+static char channel_stats_strings[][ETH_GSTRING_LEN] = {
+	"--------Channel--------- ",
+	"tp_cpl_requests        ",
+	"tp_cpl_responses       ",
+	"tp_mac_in_errs         ",
+	"tp_hdr_in_errs         ",
+	"tp_tcp_in_errs         ",
+	"tp_tcp6_in_errs        ",
+	"tp_tnl_cong_drops      ",
+	"tp_tnl_tx_drops        ",
+	"tp_ofld_vlan_drops     ",
+	"tp_ofld_chan_drops     ",
+	"fcoe_octets_ddp        ",
+	"fcoe_frames_ddp        ",
+	"fcoe_frames_drop       ",
+};
+
+static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
+	"-------Loopback----------- ",
+	"octets_ok              ",
+	"frames_ok              ",
+	"bcast_frames           ",
+	"mcast_frames           ",
+	"ucast_frames           ",
+	"error_frames           ",
+	"frames_64              ",
+	"frames_65_to_127       ",
+	"frames_128_to_255      ",
+	"frames_256_to_511      ",
+	"frames_512_to_1023     ",
+	"frames_1024_to_1518    ",
+	"frames_1519_to_max     ",
+	"frames_dropped         ",
+	"bg0_frames_dropped     ",
+	"bg1_frames_dropped     ",
+	"bg2_frames_dropped     ",
+	"bg3_frames_dropped     ",
+	"bg0_frames_trunc       ",
+	"bg1_frames_trunc       ",
+	"bg2_frames_trunc       ",
+	"bg3_frames_trunc       ",
 };
 
 static int get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
 	case ETH_SS_STATS:
-		return ARRAY_SIZE(stats_strings);
+		return ARRAY_SIZE(stats_strings) +
+		       ARRAY_SIZE(adapter_stats_strings) +
+		       ARRAY_SIZE(channel_stats_strings) +
+		       ARRAY_SIZE(loopback_stats_strings);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -168,8 +235,18 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 
 static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
-	if (stringset == ETH_SS_STATS)
+	if (stringset == ETH_SS_STATS) {
 		memcpy(data, stats_strings, sizeof(stats_strings));
+		data += sizeof(stats_strings);
+		memcpy(data, adapter_stats_strings,
+		       sizeof(adapter_stats_strings));
+		data += sizeof(adapter_stats_strings);
+		memcpy(data, channel_stats_strings,
+		       sizeof(channel_stats_strings));
+		data += sizeof(channel_stats_strings);
+		memcpy(data, loopback_stats_strings,
+		       sizeof(loopback_stats_strings));
+	}
 }
 
 /* port stats maintained per queue of the port. They should be in the same
@@ -185,6 +262,45 @@ struct queue_port_stats {
 	u64 gro_merged;
 };
 
+struct adapter_stats {
+	u64 db_drop;
+	u64 db_full;
+	u64 db_empty;
+	u64 tcp_v4_out_rsts;
+	u64 tcp_v4_in_segs;
+	u64 tcp_v4_out_segs;
+	u64 tcp_v4_retrans_segs;
+	u64 tcp_v6_out_rsts;
+	u64 tcp_v6_in_segs;
+	u64 tcp_v6_out_segs;
+	u64 tcp_v6_retrans_segs;
+	u64 frames;
+	u64 octets;
+	u64 drops;
+	u64 rqe_dfr_mod;
+	u64 rqe_dfr_pkt;
+	u64 ofld_no_neigh;
+	u64 ofld_cong_defer;
+	u64 wc_success;
+	u64 wc_fail;
+};
+
+struct channel_stats {
+	u64 cpl_req;
+	u64 cpl_rsp;
+	u64 mac_in_errs;
+	u64 hdr_in_errs;
+	u64 tcp_in_errs;
+	u64 tcp6_in_errs;
+	u64 tnl_cong_drops;
+	u64 tnl_tx_drops;
+	u64 ofld_vlan_drops;
+	u64 ofld_chan_drops;
+	u64 octets_ddp;
+	u64 frames_ddp;
+	u64 frames_drop;
+};
+
 static void collect_sge_port_stats(const struct adapter *adap,
 				   const struct port_info *p,
 				   struct queue_port_stats *s)
@@ -205,30 +321,121 @@ static void collect_sge_port_stats(const struct adapter *adap,
 	}
 }
 
+static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
+{
+	struct tp_tcp_stats v4, v6;
+	struct tp_rdma_stats rdma_stats;
+	struct tp_err_stats err_stats;
+	struct tp_usm_stats usm_stats;
+	u64 val1, val2;
+
+	memset(s, 0, sizeof(*s));
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_tcp_stats(adap, &v4, &v6);
+	t4_tp_get_rdma_stats(adap, &rdma_stats);
+	t4_get_usm_stats(adap, &usm_stats);
+	t4_tp_get_err_stats(adap, &err_stats);
+	spin_unlock(&adap->stats_lock);
+
+	s->db_drop = adap->db_stats.db_drop;
+	s->db_full = adap->db_stats.db_full;
+	s->db_empty = adap->db_stats.db_empty;
+
+	s->tcp_v4_out_rsts = v4.tcp_out_rsts;
+	s->tcp_v4_in_segs = v4.tcp_in_segs;
+	s->tcp_v4_out_segs = v4.tcp_out_segs;
+	s->tcp_v4_retrans_segs = v4.tcp_retrans_segs;
+	s->tcp_v6_out_rsts = v6.tcp_out_rsts;
+	s->tcp_v6_in_segs = v6.tcp_in_segs;
+	s->tcp_v6_out_segs = v6.tcp_out_segs;
+	s->tcp_v6_retrans_segs = v6.tcp_retrans_segs;
+
+	if (is_offload(adap)) {
+		s->frames = usm_stats.frames;
+		s->octets = usm_stats.octets;
+		s->drops = usm_stats.drops;
+		s->rqe_dfr_mod = rdma_stats.rqe_dfr_mod;
+		s->rqe_dfr_pkt = rdma_stats.rqe_dfr_pkt;
+	}
+
+	s->ofld_no_neigh = err_stats.ofld_no_neigh;
+	s->ofld_cong_defer = err_stats.ofld_cong_defer;
+
+	if (!is_t4(adap->params.chip)) {
+		int v;
+
+		v = t4_read_reg(adap, SGE_STAT_CFG_A);
+		if (STATSOURCE_T5_G(v) == 7) {
+			val2 = t4_read_reg(adap, SGE_STAT_MATCH_A);
+			val1 = t4_read_reg(adap, SGE_STAT_TOTAL_A);
+			s->wc_success = val1 - val2;
+			s->wc_fail = val2;
+		}
+	}
+}
+
+static void collect_channel_stats(struct adapter *adap, struct channel_stats *s,
+				  u8 i)
+{
+	struct tp_cpl_stats cpl_stats;
+	struct tp_err_stats err_stats;
+	struct tp_fcoe_stats fcoe_stats;
+
+	memset(s, 0, sizeof(*s));
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_cpl_stats(adap, &cpl_stats);
+	t4_tp_get_err_stats(adap, &err_stats);
+	t4_get_fcoe_stats(adap, i, &fcoe_stats);
+	spin_unlock(&adap->stats_lock);
+
+	s->cpl_req = cpl_stats.req[i];
+	s->cpl_rsp = cpl_stats.rsp[i];
+	s->mac_in_errs = err_stats.mac_in_errs[i];
+	s->hdr_in_errs = err_stats.hdr_in_errs[i];
+	s->tcp_in_errs = err_stats.tcp_in_errs[i];
+	s->tcp6_in_errs = err_stats.tcp6_in_errs[i];
+	s->tnl_cong_drops = err_stats.tnl_cong_drops[i];
+	s->tnl_tx_drops = err_stats.tnl_tx_drops[i];
+	s->ofld_vlan_drops = err_stats.ofld_vlan_drops[i];
+	s->ofld_chan_drops = err_stats.ofld_chan_drops[i];
+	s->octets_ddp = fcoe_stats.octets_ddp;
+	s->frames_ddp = fcoe_stats.frames_ddp;
+	s->frames_drop = fcoe_stats.frames_drop;
+}
+
 static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 		      u64 *data)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
-	u32 val1, val2;
+	struct lb_port_stats s;
+	int i;
+	u64 *p0;
 
-	t4_get_port_stats(adapter, pi->tx_chan, (struct port_stats *)data);
+	t4_get_port_stats_offset(adapter, pi->tx_chan,
+				 (struct port_stats *)data,
+				 &pi->stats_base);
 
 	data += sizeof(struct port_stats) / sizeof(u64);
 	collect_sge_port_stats(adapter, pi, (struct queue_port_stats *)data);
 	data += sizeof(struct queue_port_stats) / sizeof(u64);
-	if (!is_t4(adapter->params.chip)) {
-		t4_write_reg(adapter, SGE_STAT_CFG_A, STATSOURCE_T5_V(7));
-		val1 = t4_read_reg(adapter, SGE_STAT_TOTAL_A);
-		val2 = t4_read_reg(adapter, SGE_STAT_MATCH_A);
-		*data = val1 - val2;
-		data++;
-		*data = val2;
-		data++;
-	} else {
-		memset(data, 0, 2 * sizeof(u64));
-		*data += 2;
-	}
+	collect_adapter_stats(adapter, (struct adapter_stats *)data);
+	data += sizeof(struct adapter_stats) / sizeof(u64);
+
+	*data++ = (u64)pi->port_id;
+	collect_channel_stats(adapter, (struct channel_stats *)data,
+			      pi->port_id);
+	data += sizeof(struct channel_stats) / sizeof(u64);
+
+	*data++ = (u64)pi->port_id;
+	memset(&s, 0, sizeof(s));
+	t4_get_lb_stats(adapter, pi->port_id, &s);
+
+	p0 = &s.octets;
+	for (i = 0; i < ARRAY_SIZE(loopback_stats_strings) - 1; i++)
+		*data++ = (unsigned long long)*p0++;
 }
 
 static void get_regs(struct net_device *dev, struct ethtool_regs *regs,
@@ -250,7 +457,7 @@ static int restart_autoneg(struct net_device *dev)
 		return -EAGAIN;
 	if (p->link_cfg.autoneg != AUTONEG_ENABLE)
 		return -EINVAL;
-	t4_restart_aneg(p->adapter, p->adapter->fn, p->tx_chan);
+	t4_restart_aneg(p->adapter, p->adapter->pf, p->tx_chan);
 	return 0;
 }
 
@@ -267,7 +474,7 @@ static int identify_port(struct net_device *dev,
 	else
 		return -EINVAL;
 
-	return t4_identify_port(adap, adap->fn, netdev2pinfo(dev)->viid, val);
+	return t4_identify_port(adap, adap->pf, netdev2pinfo(dev)->viid, val);
 }
 
 static unsigned int from_fw_linkcaps(enum fw_port_type type, unsigned int caps)
@@ -439,7 +646,7 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	lc->autoneg = cmd->autoneg;
 
 	if (netif_running(dev))
-		return t4_link_start(p->adapter, p->adapter->fn, p->tx_chan,
+		return t4_link_l1cfg(p->adapter, p->adapter->pf, p->tx_chan,
 				     lc);
 	return 0;
 }
@@ -472,7 +679,7 @@ static int set_pauseparam(struct net_device *dev,
 	if (epause->tx_pause)
 		lc->requested_fc |= PAUSE_TX;
 	if (netif_running(dev))
-		return t4_link_start(p->adapter, p->adapter->fn, p->tx_chan,
+		return t4_link_l1cfg(p->adapter, p->adapter->pf, p->tx_chan,
 				     lc);
 	return 0;
 }
@@ -578,7 +785,7 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 	const struct sge_rspq *rq = &adap->sge.ethrxq[pi->first_qset].rspq;
 
 	c->rx_coalesce_usecs = qtimer_val(adap, rq);
-	c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN) ?
+	c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN_F) ?
 		adap->sge.counter_val[rq->pktcnt_idx] : 0;
 	c->use_adaptive_rx_coalesce = get_adaptive_rx_setting(dev);
 	return 0;
@@ -617,7 +824,7 @@ static int eeprom_ptov(unsigned int phys_addr, unsigned int fn, unsigned int sz)
  */
 static int eeprom_rd_phys(struct adapter *adap, unsigned int phys_addr, u32 *v)
 {
-	int vaddr = eeprom_ptov(phys_addr, adap->fn, EEPROMPFSIZE);
+	int vaddr = eeprom_ptov(phys_addr, adap->pf, EEPROMPFSIZE);
 
 	if (vaddr >= 0)
 		vaddr = pci_read_vpd(adap->pdev, vaddr, sizeof(u32), v);
@@ -626,7 +833,7 @@ static int eeprom_rd_phys(struct adapter *adap, unsigned int phys_addr, u32 *v)
 
 static int eeprom_wr_phys(struct adapter *adap, unsigned int phys_addr, u32 v)
 {
-	int vaddr = eeprom_ptov(phys_addr, adap->fn, EEPROMPFSIZE);
+	int vaddr = eeprom_ptov(phys_addr, adap->pf, EEPROMPFSIZE);
 
 	if (vaddr >= 0)
 		vaddr = pci_write_vpd(adap->pdev, vaddr, sizeof(u32), &v);
@@ -669,8 +876,8 @@ static int set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	aligned_offset = eeprom->offset & ~3;
 	aligned_len = (eeprom->len + (eeprom->offset & 3) + 3) & ~3;
 
-	if (adapter->fn > 0) {
-		u32 start = 1024 + adapter->fn * EEPROMPFSIZE;
+	if (adapter->pf > 0) {
+		u32 start = 1024 + adapter->pf * EEPROMPFSIZE;
 
 		if (aligned_offset < start ||
 		    aligned_offset + aligned_len > start + EEPROMPFSIZE)
@@ -740,37 +947,6 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef)
 	return ret;
 }
 
-#define WOL_SUPPORTED (WAKE_BCAST | WAKE_MAGIC)
-#define BCAST_CRC 0xa0ccc1a6
-
-static void get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
-{
-	wol->supported = WAKE_BCAST | WAKE_MAGIC;
-	wol->wolopts = netdev2adap(dev)->wol;
-	memset(&wol->sopass, 0, sizeof(wol->sopass));
-}
-
-static int set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
-{
-	int err = 0;
-	struct port_info *pi = netdev_priv(dev);
-
-	if (wol->wolopts & ~WOL_SUPPORTED)
-		return -EINVAL;
-	t4_wol_magic_enable(pi->adapter, pi->tx_chan,
-			    (wol->wolopts & WAKE_MAGIC) ? dev->dev_addr : NULL);
-	if (wol->wolopts & WAKE_BCAST) {
-		err = t4_wol_pat_enable(pi->adapter, pi->tx_chan, 0xfe, ~0ULL,
-					~0ULL, 0, false);
-		if (!err)
-			err = t4_wol_pat_enable(pi->adapter, pi->tx_chan, 1,
-						~6ULL, ~0ULL, BCAST_CRC, true);
-	} else {
-		t4_wol_pat_enable(pi->adapter, pi->tx_chan, 0, 0, 0, 0, false);
-	}
-	return err;
-}
-
 static u32 get_rss_table_size(struct net_device *dev)
 {
 	const struct port_info *pi = netdev_priv(dev);
@@ -900,8 +1076,6 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_ethtool_stats = get_stats,
 	.get_regs_len      = get_regs_len,
 	.get_regs          = get_regs,
-	.get_wol           = get_wol,
-	.set_wol           = set_wol,
 	.get_rxnfc         = get_rxnfc,
 	.get_rxfh_indir_size = get_rss_table_size,
 	.get_rxfh	   = get_rss_table,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 803d91beec6f..c64b5a99bfef 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -135,8 +135,14 @@ struct filter_entry {
 
 #define FW4_FNAME "cxgb4/t4fw.bin"
 #define FW5_FNAME "cxgb4/t5fw.bin"
+#define FW6_FNAME "cxgb4/t6fw.bin"
 #define FW4_CFNAME "cxgb4/t4-config.txt"
 #define FW5_CFNAME "cxgb4/t5-config.txt"
+#define FW6_CFNAME "cxgb4/t6-config.txt"
+#define PHY_AQ1202_FIRMWARE "cxgb4/aq1202_fw.cld"
+#define PHY_BCM84834_FIRMWARE "cxgb4/bcm8483.bin"
+#define PHY_AQ1202_DEVICEID 0x4409
+#define PHY_BCM84834_DEVICEID 0x4486
 
 MODULE_DESCRIPTION(DRV_DESC);
 MODULE_AUTHOR("Chelsio Communications");
@@ -318,8 +324,9 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
 		 * level") we need to issue the Set Parameters Commannd
 		 * without sleeping (timeout < 0).
 		 */
-		err = t4_set_params_nosleep(adap, adap->mbox, adap->fn, 0, 1,
-					    &name, &value);
+		err = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1,
+					    &name, &value,
+					    -FW_CMD_MAX_TIMEOUT);
 
 		if (err)
 			dev_err(adap->pdev_dev,
@@ -382,7 +389,7 @@ static int set_addr_filters(const struct net_device *dev, bool sleep)
 	int uc_cnt = netdev_uc_count(dev);
 	int mc_cnt = netdev_mc_count(dev);
 	const struct port_info *pi = netdev_priv(dev);
-	unsigned int mb = pi->adapter->fn;
+	unsigned int mb = pi->adapter->pf;
 
 	/* first do the secondary unicast addresses */
 	netdev_for_each_uc_addr(ha, dev) {
@@ -439,7 +446,7 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 
 	ret = set_addr_filters(dev, sleep_ok);
 	if (ret == 0)
-		ret = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, mtu,
+		ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, mtu,
 				    (dev->flags & IFF_PROMISC) ? 1 : 0,
 				    (dev->flags & IFF_ALLMULTI) ? 1 : 0, 1, -1,
 				    sleep_ok);
@@ -456,7 +463,7 @@ static int link_start(struct net_device *dev)
 {
 	int ret;
 	struct port_info *pi = netdev_priv(dev);
-	unsigned int mb = pi->adapter->fn;
+	unsigned int mb = pi->adapter->pf;
 
 	/*
 	 * We do not set address filters and promiscuity here, the stack does
@@ -474,7 +481,7 @@ static int link_start(struct net_device *dev)
 		}
 	}
 	if (ret == 0)
-		ret = t4_link_start(pi->adapter, mb, pi->tx_chan,
+		ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan,
 				    &pi->link_cfg);
 	if (ret == 0) {
 		local_bh_disable();
@@ -856,23 +863,39 @@ static void free_msix_queue_irqs(struct adapter *adap)
  *
  *	Sets up the portion of the HW RSS table for the port's VI to distribute
  *	packets to the Rx queues in @queues.
+ *	Should never be called before setting up sge eth rx queues
  */
 int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
 {
 	u16 *rss;
 	int i, err;
-	const struct sge_eth_rxq *q = &pi->adapter->sge.ethrxq[pi->first_qset];
+	struct adapter *adapter = pi->adapter;
+	const struct sge_eth_rxq *rxq;
 
+	rxq = &adapter->sge.ethrxq[pi->first_qset];
 	rss = kmalloc(pi->rss_size * sizeof(u16), GFP_KERNEL);
 	if (!rss)
 		return -ENOMEM;
 
 	/* map the queue indices to queue ids */
 	for (i = 0; i < pi->rss_size; i++, queues++)
-		rss[i] = q[*queues].rspq.abs_id;
+		rss[i] = rxq[*queues].rspq.abs_id;
 
-	err = t4_config_rss_range(pi->adapter, pi->adapter->fn, pi->viid, 0,
+	err = t4_config_rss_range(adapter, adapter->pf, pi->viid, 0,
 				  pi->rss_size, rss, pi->rss_size);
+	/* If Tunnel All Lookup isn't specified in the global RSS
+	 * Configuration, then we need to specify a default Ingress
+	 * Queue for any ingress packets which aren't hashed.  We'll
+	 * use our first ingress queue ...
+	 */
+	if (!err)
+		err = t4_config_vi_rss(adapter, adapter->mbox, pi->viid,
+				       FW_RSS_VI_CONFIG_CMD_IP6FOURTUPEN_F |
+				       FW_RSS_VI_CONFIG_CMD_IP6TWOTUPEN_F |
+				       FW_RSS_VI_CONFIG_CMD_IP4FOURTUPEN_F |
+				       FW_RSS_VI_CONFIG_CMD_IP4TWOTUPEN_F |
+				       FW_RSS_VI_CONFIG_CMD_UDPEN_F,
+				       rss[0]);
 	kfree(rss);
 	return err;
 }
@@ -885,11 +908,15 @@ int cxgb4_write_rss(const struct port_info *pi, const u16 *queues)
  */
 static int setup_rss(struct adapter *adap)
 {
-	int i, err;
+	int i, j, err;
 
 	for_each_port(adap, i) {
 		const struct port_info *pi = adap2pinfo(adap, i);
 
+		/* Fill default values with equal distribution */
+		for (j = 0; j < pi->rss_size; j++)
+			pi->rss[j] = j % pi->nqsets;
+
 		err = cxgb4_write_rss(pi, pi->rss);
 		if (err)
 			return err;
@@ -977,7 +1004,7 @@ static int alloc_ofld_rxqs(struct adapter *adap, struct sge_ofld_rxq *q,
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
 				       adap->port[i / per_chan],
 				       msi_idx, q->fl.size ? &q->fl : NULL,
-				       uldrx_handler);
+				       uldrx_handler, 0);
 		if (err)
 			return err;
 		memset(&q->stats, 0, sizeof(q->stats));
@@ -1007,7 +1034,7 @@ static int setup_sge_queues(struct adapter *adap)
 		msi_idx = 1;         /* vector 0 is for non-queue interrupts */
 	else {
 		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
-				       NULL, NULL);
+				       NULL, NULL, -1);
 		if (err)
 			return err;
 		msi_idx = -((int)s->intrq.abs_id + 1);
@@ -1027,7 +1054,7 @@ static int setup_sge_queues(struct adapter *adap)
 	 *    new/deleted queues.
 	 */
 	err = t4_sge_alloc_rxq(adap, &s->fw_evtq, true, adap->port[0],
-			       msi_idx, NULL, fwevtq_handler);
+			       msi_idx, NULL, fwevtq_handler, -1);
 	if (err) {
 freeout:	t4_free_sge_resources(adap);
 		return err;
@@ -1044,7 +1071,9 @@ freeout:	t4_free_sge_resources(adap);
 				msi_idx++;
 			err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev,
 					       msi_idx, &q->fl,
-					       t4_ethrx_handler);
+					       t4_ethrx_handler,
+					       t4_get_mps_bg_map(adap,
+								 pi->tx_chan));
 			if (err)
 				goto freeout;
 			q->rspq.idx = j;
@@ -1324,11 +1353,6 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return fallback(dev, skb) % dev->real_num_tx_queues;
 }
 
-static inline int is_offload(const struct adapter *adap)
-{
-	return adap->params.offload;
-}
-
 static int closest_timer(const struct sge *s, int time)
 {
 	int i, delta, match = 0, min_delta = INT_MAX;
@@ -1389,8 +1413,8 @@ int cxgb4_set_rspq_intr_params(struct sge_rspq *q,
 			    FW_PARAMS_PARAM_X_V(
 					FW_PARAMS_PARAM_DMAQ_IQ_INTCNTTHRESH) |
 			    FW_PARAMS_PARAM_YZ_V(q->cntxt_id);
-			err = t4_set_params(adap, adap->fn, adap->fn, 0, 1, &v,
-					    &new_idx);
+			err = t4_set_params(adap, adap->mbox, adap->pf, 0, 1,
+					    &v, &new_idx);
 			if (err)
 				return err;
 		}
@@ -1398,7 +1422,7 @@ int cxgb4_set_rspq_intr_params(struct sge_rspq *q,
 	}
 
 	us = us == 0 ? 6 : closest_timer(&adap->sge, us);
-	q->intr_params = QINTR_TIMER_IDX(us) | (cnt > 0 ? QINTR_CNT_EN : 0);
+	q->intr_params = QINTR_TIMER_IDX_V(us) | QINTR_CNT_EN_V(cnt > 0);
 	return 0;
 }
 
@@ -1411,7 +1435,7 @@ static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
 	if (!(changed & NETIF_F_HW_VLAN_CTAG_RX))
 		return 0;
 
-	err = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, -1,
+	err = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, -1,
 			    -1, -1, -1,
 			    !!(features & NETIF_F_HW_VLAN_CTAG_RX), true);
 	if (unlikely(err))
@@ -1694,7 +1718,7 @@ static int tid_init(struct tid_info *t)
 	bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
 	/* Reserve stid 0 for T4/T5 adapters */
 	if (!t->stid_base &&
-	    (is_t4(adap->params.chip) || is_t5(adap->params.chip)))
+	    (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5))
 		__set_bit(0, t->stid_bmap);
 
 	return 0;
@@ -1983,11 +2007,8 @@ EXPORT_SYMBOL(cxgb4_iscsi_init);
 int cxgb4_flush_eq_cache(struct net_device *dev)
 {
 	struct adapter *adap = netdev2adap(dev);
-	int ret;
 
-	ret = t4_fwaddrspace_write(adap, adap->mbox,
-				   0xe1000000 + SGE_CTXT_CMD_A, 0x20000000);
-	return ret;
+	return t4_sge_ctxt_flush(adap, adap->mbox);
 }
 EXPORT_SYMBOL(cxgb4_flush_eq_cache);
 
@@ -2042,25 +2063,6 @@ out:
 }
 EXPORT_SYMBOL(cxgb4_sync_txq_pidx);
 
-void cxgb4_disable_db_coalescing(struct net_device *dev)
-{
-	struct adapter *adap;
-
-	adap = netdev2adap(dev);
-	t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, NOCOALESCE_F,
-			 NOCOALESCE_F);
-}
-EXPORT_SYMBOL(cxgb4_disable_db_coalescing);
-
-void cxgb4_enable_db_coalescing(struct net_device *dev)
-{
-	struct adapter *adap;
-
-	adap = netdev2adap(dev);
-	t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, NOCOALESCE_F, 0);
-}
-EXPORT_SYMBOL(cxgb4_enable_db_coalescing);
-
 int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte)
 {
 	struct adapter *adap;
@@ -2100,10 +2102,7 @@ int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte)
 		if (offset < mc0_end) {
 			memtype = MEM_MC0;
 			memaddr = offset - edc1_end;
-		} else if (is_t4(adap->params.chip)) {
-			/* T4 only has a single memory channel */
-			goto err;
-		} else {
+		} else if (is_t5(adap->params.chip)) {
 			size = t4_read_reg(adap, MA_EXT_MEMORY1_BAR_A);
 			mc1_size = EXT_MEM1_SIZE_G(size) << 20;
 			mc1_end = mc0_end + mc1_size;
@@ -2114,6 +2113,9 @@ int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte)
 				/* offset beyond the end of any memory */
 				goto err;
 			}
+		} else {
+			/* T4/T6 only has a single memory channel */
+			goto err;
 		}
 	}
 
@@ -2145,14 +2147,16 @@ EXPORT_SYMBOL(cxgb4_read_sge_timestamp);
 int cxgb4_bar2_sge_qregs(struct net_device *dev,
 			 unsigned int qid,
 			 enum cxgb4_bar2_qtype qtype,
+			 int user,
 			 u64 *pbar2_qoffset,
 			 unsigned int *pbar2_qid)
 {
-	return cxgb4_t4_bar2_sge_qregs(netdev2adap(dev),
+	return t4_bar2_sge_qregs(netdev2adap(dev),
 				 qid,
 				 (qtype == CXGB4_BAR2_QTYPE_EGRESS
 				  ? T4_BAR2_QTYPE_EGRESS
 				  : T4_BAR2_QTYPE_INGRESS),
+				 user,
 				 pbar2_qoffset,
 				 pbar2_qid);
 }
@@ -2278,9 +2282,13 @@ static void process_db_full(struct work_struct *work)
 	drain_db_fifo(adap, dbfifo_drain_delay);
 	enable_dbs(adap);
 	notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
-	t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
-			 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F,
-			 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F);
+	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
+		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
+				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F,
+				 DBFIFO_HP_INT_F | DBFIFO_LP_INT_F);
+	else
+		t4_set_reg_field(adap, SGE_INT_ENABLE3_A,
+				 DBFIFO_LP_INT_F, DBFIFO_LP_INT_F);
 }
 
 static void sync_txq_pidx(struct adapter *adap, struct sge_txq *q)
@@ -2342,7 +2350,7 @@ static void process_db_drop(struct work_struct *work)
 		drain_db_fifo(adap, dbfifo_drain_delay);
 		enable_dbs(adap);
 		notify_rdma_uld(adap, CXGB4_CONTROL_DB_EMPTY);
-	} else {
+	} else if (is_t5(adap->params.chip)) {
 		u32 dropped_db = t4_read_reg(adap, 0x010ac);
 		u16 qid = (dropped_db >> 15) & 0x1ffff;
 		u16 pidx_inc = dropped_db & 0x1fff;
@@ -2350,8 +2358,8 @@ static void process_db_drop(struct work_struct *work)
 		unsigned int bar2_qid;
 		int ret;
 
-		ret = cxgb4_t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS,
-					&bar2_qoffset, &bar2_qid);
+		ret = t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS,
+					0, &bar2_qoffset, &bar2_qid);
 		if (ret)
 			dev_err(adap->pdev_dev, "doorbell drop recovery: "
 				"qid=%d, pidx_inc=%d\n", qid, pidx_inc);
@@ -2363,7 +2371,8 @@ static void process_db_drop(struct work_struct *work)
 		t4_set_reg_field(adap, 0x10b0, 1<<15, 1<<15);
 	}
 
-	t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0);
+	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
+		t4_set_reg_field(adap, SGE_DOORBELL_CONTROL_A, DROPPED_DB_F, 0);
 }
 
 void t4_db_full(struct adapter *adap)
@@ -2393,7 +2402,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	unsigned short i;
 
 	lli.pdev = adap->pdev;
-	lli.pf = adap->fn;
+	lli.pf = adap->pf;
 	lli.l2t = adap->l2t;
 	lli.tids = &adap->tids;
 	lli.ports = adap->port;
@@ -2432,6 +2441,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.max_ordird_qp = adap->params.max_ordird_qp;
 	lli.max_ird_adapter = adap->params.max_ird_adapter;
 	lli.ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl;
+	lli.nodeid = dev_to_node(adap->pdev_dev);
 
 	handle = ulds[uld].add(&lli);
 	if (IS_ERR(handle)) {
@@ -2729,7 +2739,7 @@ static int cxgb_close(struct net_device *dev)
 
 	netif_tx_stop_all_queues(dev);
 	netif_carrier_off(dev);
-	return t4_enable_vi(adapter, adapter->fn, pi->viid, false, false);
+	return t4_enable_vi(adapter, adapter->pf, pi->viid, false, false);
 }
 
 /* Return an error number if the indicated filter isn't writable ...
@@ -2873,7 +2883,8 @@ static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
 		spin_unlock(&adapter->stats_lock);
 		return ns;
 	}
-	t4_get_port_stats(adapter, p->tx_chan, &stats);
+	t4_get_port_stats_offset(adapter, p->tx_chan, &stats,
+				 &p->stats_base);
 	spin_unlock(&adapter->stats_lock);
 
 	ns->tx_bytes   = stats.tx_octets;
@@ -2932,7 +2943,7 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
 		} else
 			return -EINVAL;
 
-		mbox = pi->adapter->fn;
+		mbox = pi->adapter->pf;
 		if (cmd == SIOCGMIIREG)
 			ret = t4_mdio_rd(pi->adapter, mbox, prtad, devad,
 					 data->reg_num, &data->val_out);
@@ -2959,7 +2970,7 @@ static int cxgb_change_mtu(struct net_device *dev, int new_mtu)
 
 	if (new_mtu < 81 || new_mtu > MAX_MTU)         /* accommodate SACK */
 		return -EINVAL;
-	ret = t4_set_rxmode(pi->adapter, pi->adapter->fn, pi->viid, new_mtu, -1,
+	ret = t4_set_rxmode(pi->adapter, pi->adapter->pf, pi->viid, new_mtu, -1,
 			    -1, -1, -1, true);
 	if (!ret)
 		dev->mtu = new_mtu;
@@ -2975,7 +2986,7 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	ret = t4_change_mac(pi->adapter, pi->adapter->fn, pi->viid,
+	ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid,
 			    pi->xact_addr_filt, addr->sa_data, true, true);
 	if (ret < 0)
 		return ret;
@@ -3034,86 +3045,11 @@ void t4_fatal_err(struct adapter *adap)
 	dev_alert(adap->pdev_dev, "encountered fatal error, adapter stopped\n");
 }
 
-/* Return the specified PCI-E Configuration Space register from our Physical
- * Function.  We try first via a Firmware LDST Command since we prefer to let
- * the firmware own all of these registers, but if that fails we go for it
- * directly ourselves.
- */
-static u32 t4_read_pcie_cfg4(struct adapter *adap, int reg)
-{
-	struct fw_ldst_cmd ldst_cmd;
-	u32 val;
-	int ret;
-
-	/* Construct and send the Firmware LDST Command to retrieve the
-	 * specified PCI-E Configuration Space register.
-	 */
-	memset(&ldst_cmd, 0, sizeof(ldst_cmd));
-	ldst_cmd.op_to_addrspace =
-		htonl(FW_CMD_OP_V(FW_LDST_CMD) |
-		      FW_CMD_REQUEST_F |
-		      FW_CMD_READ_F |
-		      FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_FUNC_PCIE));
-	ldst_cmd.cycles_to_len16 = htonl(FW_LEN16(ldst_cmd));
-	ldst_cmd.u.pcie.select_naccess = FW_LDST_CMD_NACCESS_V(1);
-	ldst_cmd.u.pcie.ctrl_to_fn =
-		(FW_LDST_CMD_LC_F | FW_LDST_CMD_FN_V(adap->fn));
-	ldst_cmd.u.pcie.r = reg;
-	ret = t4_wr_mbox(adap, adap->mbox, &ldst_cmd, sizeof(ldst_cmd),
-			 &ldst_cmd);
-
-	/* If the LDST Command suucceeded, exctract the returned register
-	 * value.  Otherwise read it directly ourself.
-	 */
-	if (ret == 0)
-		val = ntohl(ldst_cmd.u.pcie.data[0]);
-	else
-		t4_hw_pci_read_cfg4(adap, reg, &val);
-
-	return val;
-}
-
 static void setup_memwin(struct adapter *adap)
 {
-	u32 mem_win0_base, mem_win1_base, mem_win2_base, mem_win2_aperture;
+	u32 nic_win_base = t4_get_util_window(adap);
 
-	if (is_t4(adap->params.chip)) {
-		u32 bar0;
-
-		/* Truncation intentional: we only read the bottom 32-bits of
-		 * the 64-bit BAR0/BAR1 ...  We use the hardware backdoor
-		 * mechanism to read BAR0 instead of using
-		 * pci_resource_start() because we could be operating from
-		 * within a Virtual Machine which is trapping our accesses to
-		 * our Configuration Space and we need to set up the PCI-E
-		 * Memory Window decoders with the actual addresses which will
-		 * be coming across the PCI-E link.
-		 */
-		bar0 = t4_read_pcie_cfg4(adap, PCI_BASE_ADDRESS_0);
-		bar0 &= PCI_BASE_ADDRESS_MEM_MASK;
-		adap->t4_bar0 = bar0;
-
-		mem_win0_base = bar0 + MEMWIN0_BASE;
-		mem_win1_base = bar0 + MEMWIN1_BASE;
-		mem_win2_base = bar0 + MEMWIN2_BASE;
-		mem_win2_aperture = MEMWIN2_APERTURE;
-	} else {
-		/* For T5, only relative offset inside the PCIe BAR is passed */
-		mem_win0_base = MEMWIN0_BASE;
-		mem_win1_base = MEMWIN1_BASE;
-		mem_win2_base = MEMWIN2_BASE_T5;
-		mem_win2_aperture = MEMWIN2_APERTURE_T5;
-	}
-	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 0),
-		     mem_win0_base | BIR_V(0) |
-		     WINDOW_V(ilog2(MEMWIN0_APERTURE) - 10));
-	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 1),
-		     mem_win1_base | BIR_V(0) |
-		     WINDOW_V(ilog2(MEMWIN1_APERTURE) - 10));
-	t4_write_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 2),
-		     mem_win2_base | BIR_V(0) |
-		     WINDOW_V(ilog2(mem_win2_aperture) - 10));
-	t4_read_reg(adap, PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, 2));
+	t4_setup_memwin(adap, nic_win_base, MEMWIN_NIC);
 }
 
 static void setup_memwin_rdma(struct adapter *adap)
@@ -3147,7 +3083,7 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
 			       FW_CMD_REQUEST_F | FW_CMD_READ_F);
 	c->cfvalid_to_len16 = htonl(FW_LEN16(*c));
-	ret = t4_wr_mbox(adap, adap->fn, c, sizeof(*c), c);
+	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), c);
 	if (ret < 0)
 		return ret;
 
@@ -3163,18 +3099,18 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	}
 	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
 			       FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
-	ret = t4_wr_mbox(adap, adap->fn, c, sizeof(*c), NULL);
+	ret = t4_wr_mbox(adap, adap->mbox, c, sizeof(*c), NULL);
 	if (ret < 0)
 		return ret;
 
-	ret = t4_config_glbl_rss(adap, adap->fn,
+	ret = t4_config_glbl_rss(adap, adap->pf,
 				 FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL,
 				 FW_RSS_GLB_CONFIG_CMD_TNLMAPEN_F |
 				 FW_RSS_GLB_CONFIG_CMD_TNLALLLKP_F);
 	if (ret < 0)
 		return ret;
 
-	ret = t4_cfg_pfvf(adap, adap->fn, adap->fn, 0, adap->sge.egr_sz, 64,
+	ret = t4_cfg_pfvf(adap, adap->mbox, adap->pf, 0, adap->sge.egr_sz, 64,
 			  MAX_INGQ, 0, 0, 4, 0xf, 0xf, 16, FW_CMD_CAP_PF,
 			  FW_CMD_CAP_PF);
 	if (ret < 0)
@@ -3218,7 +3154,7 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	}
 
 	/* get basic stuff going */
-	return t4_early_init(adap, adap->fn);
+	return t4_early_init(adap, adap->pf);
 }
 
 /*
@@ -3274,6 +3210,142 @@ static int adap_init0_tweaks(struct adapter *adapter)
 	return 0;
 }
 
+/* 10Gb/s-BT PHY Support. chip-external 10Gb/s-BT PHYs are complex chips
+ * unto themselves and they contain their own firmware to perform their
+ * tasks ...
+ */
+static int phy_aq1202_version(const u8 *phy_fw_data,
+			      size_t phy_fw_size)
+{
+	int offset;
+
+	/* At offset 0x8 you're looking for the primary image's
+	 * starting offset which is 3 Bytes wide
+	 *
+	 * At offset 0xa of the primary image, you look for the offset
+	 * of the DRAM segment which is 3 Bytes wide.
+	 *
+	 * The FW version is at offset 0x27e of the DRAM and is 2 Bytes
+	 * wide
+	 */
+	#define be16(__p) (((__p)[0] << 8) | (__p)[1])
+	#define le16(__p) ((__p)[0] | ((__p)[1] << 8))
+	#define le24(__p) (le16(__p) | ((__p)[2] << 16))
+
+	offset = le24(phy_fw_data + 0x8) << 12;
+	offset = le24(phy_fw_data + offset + 0xa);
+	return be16(phy_fw_data + offset + 0x27e);
+
+	#undef be16
+	#undef le16
+	#undef le24
+}
+
+static struct info_10gbt_phy_fw {
+	unsigned int phy_fw_id;		/* PCI Device ID */
+	char *phy_fw_file;		/* /lib/firmware/ PHY Firmware file */
+	int (*phy_fw_version)(const u8 *phy_fw_data, size_t phy_fw_size);
+	int phy_flash;			/* Has FLASH for PHY Firmware */
+} phy_info_array[] = {
+	{
+		PHY_AQ1202_DEVICEID,
+		PHY_AQ1202_FIRMWARE,
+		phy_aq1202_version,
+		1,
+	},
+	{
+		PHY_BCM84834_DEVICEID,
+		PHY_BCM84834_FIRMWARE,
+		NULL,
+		0,
+	},
+	{ 0, NULL, NULL },
+};
+
+static struct info_10gbt_phy_fw *find_phy_info(int devid)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(phy_info_array); i++) {
+		if (phy_info_array[i].phy_fw_id == devid)
+			return &phy_info_array[i];
+	}
+	return NULL;
+}
+
+/* Handle updating of chip-external 10Gb/s-BT PHY firmware.  This needs to
+ * happen after the FW_RESET_CMD but before the FW_INITIALIZE_CMD.  On error
+ * we return a negative error number.  If we transfer new firmware we return 1
+ * (from t4_load_phy_fw()).  If we don't do anything we return 0.
+ */
+static int adap_init0_phy(struct adapter *adap)
+{
+	const struct firmware *phyf;
+	int ret;
+	struct info_10gbt_phy_fw *phy_info;
+
+	/* Use the device ID to determine which PHY file to flash.
+	 */
+	phy_info = find_phy_info(adap->pdev->device);
+	if (!phy_info) {
+		dev_warn(adap->pdev_dev,
+			 "No PHY Firmware file found for this PHY\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* If we have a T4 PHY firmware file under /lib/firmware/cxgb4/, then
+	 * use that. The adapter firmware provides us with a memory buffer
+	 * where we can load a PHY firmware file from the host if we want to
+	 * override the PHY firmware File in flash.
+	 */
+	ret = request_firmware_direct(&phyf, phy_info->phy_fw_file,
+				      adap->pdev_dev);
+	if (ret < 0) {
+		/* For adapters without FLASH attached to PHY for their
+		 * firmware, it's obviously a fatal error if we can't get the
+		 * firmware to the adapter.  For adapters with PHY firmware
+		 * FLASH storage, it's worth a warning if we can't find the
+		 * PHY Firmware but we'll neuter the error ...
+		 */
+		dev_err(adap->pdev_dev, "unable to find PHY Firmware image "
+			"/lib/firmware/%s, error %d\n",
+			phy_info->phy_fw_file, -ret);
+		if (phy_info->phy_flash) {
+			int cur_phy_fw_ver = 0;
+
+			t4_phy_fw_ver(adap, &cur_phy_fw_ver);
+			dev_warn(adap->pdev_dev, "continuing with, on-adapter "
+				 "FLASH copy, version %#x\n", cur_phy_fw_ver);
+			ret = 0;
+		}
+
+		return ret;
+	}
+
+	/* Load PHY Firmware onto adapter.
+	 */
+	ret = t4_load_phy_fw(adap, MEMWIN_NIC, &adap->win0_lock,
+			     phy_info->phy_fw_version,
+			     (u8 *)phyf->data, phyf->size);
+	if (ret < 0)
+		dev_err(adap->pdev_dev, "PHY Firmware transfer error %d\n",
+			-ret);
+	else if (ret > 0) {
+		int new_phy_fw_ver = 0;
+
+		if (phy_info->phy_fw_version)
+			new_phy_fw_ver = phy_info->phy_fw_version(phyf->data,
+								  phyf->size);
+		dev_info(adap->pdev_dev, "Successfully transferred PHY "
+			 "Firmware /lib/firmware/%s, version %#x\n",
+			 phy_info->phy_fw_file, new_phy_fw_ver);
+	}
+
+	release_firmware(phyf);
+
+	return ret;
+}
+
 /*
  * Attempt to initialize the adapter via a Firmware Configuration File.
  */
@@ -3298,6 +3370,16 @@ static int adap_init0_config(struct adapter *adapter, int reset)
 			goto bye;
 	}
 
+	/* If this is a 10Gb/s-BT adapter make sure the chip-external
+	 * 10Gb/s-BT PHYs have up-to-date firmware.  Note that this step needs
+	 * to be performed after any global adapter RESET above since some
+	 * PHYs only have local RAM copies of the PHY firmware.
+	 */
+	if (is_10gbt_device(adapter->pdev->device)) {
+		ret = adap_init0_phy(adapter);
+		if (ret < 0)
+			goto bye;
+	}
 	/*
 	 * If we have a T4 configuration file under /lib/firmware/cxgb4/,
 	 * then use that.  Otherwise, use the configuration file stored
@@ -3310,6 +3392,9 @@ static int adap_init0_config(struct adapter *adapter, int reset)
 	case CHELSIO_T5:
 		fw_config_file = FW5_CFNAME;
 		break;
+	case CHELSIO_T6:
+		fw_config_file = FW6_CFNAME;
+		break;
 	default:
 		dev_err(adapter->pdev_dev, "Device %d is not supported\n",
 		       adapter->pdev->device);
@@ -3335,7 +3420,7 @@ static int adap_init0_config(struct adapter *adapter, int reset)
 			params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
 			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
 			ret = t4_query_params(adapter, adapter->mbox,
-					      adapter->fn, 0, 1, params, val);
+					      adapter->pf, 0, 1, params, val);
 			if (ret == 0) {
 				/*
 				 * For t4_memory_rw() below addresses and
@@ -3506,7 +3591,24 @@ static struct fw_info fw_info_array[] = {
 			.intfver_iscsi = FW_INTFVER(T5, ISCSI),
 			.intfver_fcoe = FW_INTFVER(T5, FCOE),
 		},
+	}, {
+		.chip = CHELSIO_T6,
+		.fs_name = FW6_CFNAME,
+		.fw_mod_name = FW6_FNAME,
+		.fw_hdr = {
+			.chip = FW_HDR_CHIP_T6,
+			.fw_ver = __cpu_to_be32(FW_VERSION(T6)),
+			.intfver_nic = FW_INTFVER(T6, NIC),
+			.intfver_vnic = FW_INTFVER(T6, VNIC),
+			.intfver_ofld = FW_INTFVER(T6, OFLD),
+			.intfver_ri = FW_INTFVER(T6, RI),
+			.intfver_iscsipdu = FW_INTFVER(T6, ISCSIPDU),
+			.intfver_iscsi = FW_INTFVER(T6, ISCSI),
+			.intfver_fcoepdu = FW_INTFVER(T6, FCOEPDU),
+			.intfver_fcoe = FW_INTFVER(T6, FCOE),
+		},
 	}
+
 };
 
 static struct fw_info *find_fw_info(int chip)
@@ -3612,7 +3714,7 @@ static int adap_init0(struct adapter *adap)
 	 * the firmware.  On the other hand, we need these fairly early on
 	 * so we do this right after getting ahold of the firmware.
 	 */
-	ret = get_vpd_params(adap, &adap->params.vpd);
+	ret = t4_get_vpd_params(adap, &adap->params.vpd);
 	if (ret < 0)
 		goto bye;
 
@@ -3624,7 +3726,7 @@ static int adap_init0(struct adapter *adap)
 	v =
 	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
 	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1, &v, &port_vec);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
 	if (ret < 0)
 		goto bye;
 
@@ -3647,7 +3749,7 @@ static int adap_init0(struct adapter *adap)
 		 */
 		params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
 			     FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CF));
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 1,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
 				      params, val);
 
 		/* If the firmware doesn't support Configuration Files,
@@ -3706,7 +3808,7 @@ static int adap_init0(struct adapter *adap)
 	params[3] = FW_PARAM_PFVF(FILTER_START);
 	params[4] = FW_PARAM_PFVF(FILTER_END);
 	params[5] = FW_PARAM_PFVF(IQFLINT_START);
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params, val);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params, val);
 	if (ret < 0)
 		goto bye;
 	adap->sge.egr_start = val[0];
@@ -3724,7 +3826,7 @@ static int adap_init0(struct adapter *adap)
 	 */
 	params[0] = FW_PARAM_PFVF(EQ_END);
 	params[1] = FW_PARAM_PFVF(IQFLINT_END);
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
 	if (ret < 0)
 		goto bye;
 	adap->sge.egr_sz = val[0] - adap->sge.egr_start + 1;
@@ -3745,7 +3847,7 @@ static int adap_init0(struct adapter *adap)
 	}
 
 	/* Allocate the memory for the vaious egress queue bitmaps
-	 * ie starving_fl and txq_maperr.
+	 * ie starving_fl, txq_maperr and blocked_fl.
 	 */
 	adap->sge.starving_fl =	kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
 					sizeof(long), GFP_KERNEL);
@@ -3761,9 +3863,18 @@ static int adap_init0(struct adapter *adap)
 		goto bye;
 	}
 
+#ifdef CONFIG_DEBUG_FS
+	adap->sge.blocked_fl = kcalloc(BITS_TO_LONGS(adap->sge.egr_sz),
+				       sizeof(long), GFP_KERNEL);
+	if (!adap->sge.blocked_fl) {
+		ret = -ENOMEM;
+		goto bye;
+	}
+#endif
+
 	params[0] = FW_PARAM_PFVF(CLIP_START);
 	params[1] = FW_PARAM_PFVF(CLIP_END);
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
 	if (ret < 0)
 		goto bye;
 	adap->clipt_start = val[0];
@@ -3772,7 +3883,7 @@ static int adap_init0(struct adapter *adap)
 	/* query params related to active filter region */
 	params[0] = FW_PARAM_PFVF(ACTIVE_FILTER_START);
 	params[1] = FW_PARAM_PFVF(ACTIVE_FILTER_END);
-	ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params, val);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params, val);
 	/* If Active filter size is set we enable establishing
 	 * offload connection through firmware work request
 	 */
@@ -3789,7 +3900,7 @@ static int adap_init0(struct adapter *adap)
 	 */
 	params[0] = FW_PARAM_PFVF(CPLFW4MSG_ENCAP);
 	val[0] = 1;
-	(void) t4_set_params(adap, adap->mbox, adap->fn, 0, 1, params, val);
+	(void)t4_set_params(adap, adap->mbox, adap->pf, 0, 1, params, val);
 
 	/*
 	 * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL
@@ -3801,7 +3912,7 @@ static int adap_init0(struct adapter *adap)
 		adap->params.ulptx_memwrite_dsgl = false;
 	} else {
 		params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
 				      1, params, val);
 		adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0);
 	}
@@ -3827,7 +3938,7 @@ static int adap_init0(struct adapter *adap)
 		params[3] = FW_PARAM_PFVF(TDDP_START);
 		params[4] = FW_PARAM_PFVF(TDDP_END);
 		params[5] = FW_PARAM_DEV(FLOWC_BUFFIFO_SZ);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
 				      params, val);
 		if (ret < 0)
 			goto bye;
@@ -3865,7 +3976,7 @@ static int adap_init0(struct adapter *adap)
 		params[3] = FW_PARAM_PFVF(RQ_END);
 		params[4] = FW_PARAM_PFVF(PBL_START);
 		params[5] = FW_PARAM_PFVF(PBL_END);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6,
 				      params, val);
 		if (ret < 0)
 			goto bye;
@@ -3882,7 +3993,7 @@ static int adap_init0(struct adapter *adap)
 		params[3] = FW_PARAM_PFVF(CQ_END);
 		params[4] = FW_PARAM_PFVF(OCQ_START);
 		params[5] = FW_PARAM_PFVF(OCQ_END);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 6, params,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 6, params,
 				      val);
 		if (ret < 0)
 			goto bye;
@@ -3895,7 +4006,7 @@ static int adap_init0(struct adapter *adap)
 
 		params[0] = FW_PARAM_DEV(MAXORDIRD_QP);
 		params[1] = FW_PARAM_DEV(MAXIRD_ADAPTER);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2, params,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, params,
 				      val);
 		if (ret < 0) {
 			adap->params.max_ordird_qp = 8;
@@ -3913,7 +4024,7 @@ static int adap_init0(struct adapter *adap)
 	if (caps_cmd.iscsicaps) {
 		params[0] = FW_PARAM_PFVF(ISCSI_START);
 		params[1] = FW_PARAM_PFVF(ISCSI_END);
-		ret = t4_query_params(adap, adap->mbox, adap->fn, 0, 2,
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2,
 				      params, val);
 		if (ret < 0)
 			goto bye;
@@ -3959,8 +4070,8 @@ static int adap_init0(struct adapter *adap)
 			     adap->params.b_wnd);
 	}
 	t4_init_sge_params(adap);
-	t4_init_tp_params(adap);
 	adap->flags |= FW_OK;
+	t4_init_tp_params(adap);
 	return 0;
 
 	/*
@@ -3973,6 +4084,9 @@ bye:
 	kfree(adap->sge.ingr_map);
 	kfree(adap->sge.starving_fl);
 	kfree(adap->sge.txq_maperr);
+#ifdef CONFIG_DEBUG_FS
+	kfree(adap->sge.blocked_fl);
+#endif
 	if (ret != -ETIMEDOUT && ret != -EIO)
 		t4_fw_bye(adap, adap->mbox);
 	return ret;
@@ -4040,7 +4154,7 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 
 	if (t4_wait_dev_ready(adap->regs) < 0)
 		return PCI_ERS_RESULT_DISCONNECT;
-	if (t4_fw_hello(adap, adap->fn, adap->fn, MASTER_MUST, NULL) < 0)
+	if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0)
 		return PCI_ERS_RESULT_DISCONNECT;
 	adap->flags |= FW_OK;
 	if (adap_init1(adap, &c))
@@ -4049,7 +4163,7 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 	for_each_port(adap, i) {
 		struct port_info *p = adap2pinfo(adap, i);
 
-		ret = t4_alloc_vi(adap, adap->fn, p->tx_chan, adap->fn, 0, 1,
+		ret = t4_alloc_vi(adap, adap->mbox, p->tx_chan, adap->pf, 0, 1,
 				  NULL, NULL);
 		if (ret < 0)
 			return PCI_ERS_RESULT_DISCONNECT;
@@ -4340,7 +4454,12 @@ static int enable_msix(struct adapter *adap)
 
 static int init_rss(struct adapter *adap)
 {
-	unsigned int i, j;
+	unsigned int i;
+	int err;
+
+	err = t4_init_rss_mode(adap, adap->mbox);
+	if (err)
+		return err;
 
 	for_each_port(adap, i) {
 		struct port_info *pi = adap2pinfo(adap, i);
@@ -4348,8 +4467,6 @@ static int init_rss(struct adapter *adap)
 		pi->rss = kcalloc(pi->rss_size, sizeof(u16), GFP_KERNEL);
 		if (!pi->rss)
 			return -ENOMEM;
-		for (j = 0; j < pi->rss_size; j++)
-			pi->rss[j] = ethtool_rxfh_indir_default(j, pi->nqsets);
 	}
 	return 0;
 }
@@ -4413,15 +4530,23 @@ static void free_some_resources(struct adapter *adapter)
 	kfree(adapter->sge.ingr_map);
 	kfree(adapter->sge.starving_fl);
 	kfree(adapter->sge.txq_maperr);
+#ifdef CONFIG_DEBUG_FS
+	kfree(adapter->sge.blocked_fl);
+#endif
 	disable_msi(adapter);
 
 	for_each_port(adapter, i)
 		if (adapter->port[i]) {
+			struct port_info *pi = adap2pinfo(adapter, i);
+
+			if (pi->viid != 0)
+				t4_free_vi(adapter, adapter->mbox, adapter->pf,
+					   0, pi->viid);
 			kfree(adap2pinfo(adapter, i)->rss);
 			free_netdev(adapter->port[i]);
 		}
 	if (adapter->flags & FW_OK)
-		t4_fw_bye(adapter, adapter->fn);
+		t4_fw_bye(adapter, adapter->pf);
 }
 
 #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
@@ -4512,7 +4637,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->pdev = pdev;
 	adapter->pdev_dev = &pdev->dev;
 	adapter->mbox = func;
-	adapter->fn = func;
+	adapter->pf = func;
 	adapter->msg_enable = dflt_msg_enable;
 	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
 
@@ -4532,7 +4657,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!is_t4(adapter->params.chip)) {
 		s_qpp = (QUEUESPERPAGEPF0_S +
 			(QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) *
-			adapter->fn);
+			adapter->pf);
 		qpp = 1 << QUEUESPERPAGEPF0_G(t4_read_reg(adapter,
 		      SGE_EGRESS_QUEUES_PER_PAGE_PF_A) >> s_qpp);
 		num_seg = PAGE_SIZE / SEGMENT_SIZE;
@@ -4555,10 +4680,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			err = -ENOMEM;
 			goto out_free_adapter;
 		}
+		t4_write_reg(adapter, SGE_STAT_CFG_A,
+			     STATSOURCE_T5_V(7) | STATMODE_V(0));
 	}
 
 	setup_memwin(adapter);
 	err = adap_init0(adapter);
+#ifdef CONFIG_DEBUG_FS
+	bitmap_zero(adapter->sge.blocked_fl, adapter->sge.egr_sz);
+#endif
 	setup_memwin_rdma(adapter);
 	if (err)
 		goto out_unmap_bar;
@@ -4607,10 +4737,25 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = t4_port_init(adapter, func, func, 0);
 		if (err)
 			goto out_free_dev;
+	} else if (adapter->params.nports == 1) {
+		/* If we don't have a connection to the firmware -- possibly
+		 * because of an error -- grab the raw VPD parameters so we
+		 * can set the proper MAC Address on the debug network
+		 * interface that we've created.
+		 */
+		u8 hw_addr[ETH_ALEN];
+		u8 *na = adapter->params.vpd.na;
+
+		err = t4_get_raw_vpd_params(adapter, &adapter->params.vpd);
+		if (!err) {
+			for (i = 0; i < ETH_ALEN; i++)
+				hw_addr[i] = (hex2val(na[2 * i + 0]) * 16 +
+					      hex2val(na[2 * i + 1]));
+			t4_set_hw_addr(adapter, 0, hw_addr);
+		}
 	}
 
-	/*
-	 * Configure queues and allocate tables now, they can be needed as
+	/* Configure queues and allocate tables now, they can be needed as
 	 * soon as the first register_netdev completes.
 	 */
 	cfg_queues(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 78ab4d406ce2..b27897d4f787 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -264,6 +264,7 @@ struct cxgb4_lld_info {
 	unsigned int max_ordird_qp;          /* Max ORD/IRD depth per RDMA QP */
 	unsigned int max_ird_adapter;        /* Max IRD memory per adapter */
 	bool ulptx_memwrite_dsgl;            /* use of T5 DSGL allowed */
+	int nodeid;			     /* device numa node id */
 };
 
 struct cxgb4_uld_info {
@@ -297,8 +298,6 @@ struct sk_buff *cxgb4_pktgl_to_skb(const struct pkt_gl *gl,
 				   unsigned int skb_len, unsigned int pull_len);
 int cxgb4_sync_txq_pidx(struct net_device *dev, u16 qid, u16 pidx, u16 size);
 int cxgb4_flush_eq_cache(struct net_device *dev);
-void cxgb4_disable_db_coalescing(struct net_device *dev);
-void cxgb4_enable_db_coalescing(struct net_device *dev);
 int cxgb4_read_tpte(struct net_device *dev, u32 stag, __be32 *tpte);
 u64 cxgb4_read_sge_timestamp(struct net_device *dev);
 
@@ -306,6 +305,7 @@ enum cxgb4_bar2_qtype { CXGB4_BAR2_QTYPE_EGRESS, CXGB4_BAR2_QTYPE_INGRESS };
 int cxgb4_bar2_sge_qregs(struct net_device *dev,
 			 unsigned int qid,
 			 enum cxgb4_bar2_qtype qtype,
+			 int user,
 			 u64 *pbar2_qoffset,
 			 unsigned int *pbar2_qid);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 0d2eddab04ef..942db078f33a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -100,16 +100,6 @@
  */
 #define TX_QCHECK_PERIOD (HZ / 2)
 
-/* SGE Hung Ingress DMA Threshold Warning time (in Hz) and Warning Repeat Rate
- * (in RX_QCHECK_PERIOD multiples).  If we find one of the SGE Ingress DMA
- * State Machines in the same state for this amount of time (in HZ) then we'll
- * issue a warning about a potential hang.  We'll repeat the warning as the
- * SGE Ingress DMA Channel appears to be hung every N RX_QCHECK_PERIODs till
- * the situation clears.  If the situation clears, we'll note that as well.
- */
-#define SGE_IDMA_WARN_THRESH (1 * HZ)
-#define SGE_IDMA_WARN_REPEAT (20 * RX_QCHECK_PERIOD)
-
 /*
  * Max number of Tx descriptors to be reclaimed by the Tx timer.
  */
@@ -532,14 +522,17 @@ static void unmap_rx_buf(struct adapter *adap, struct sge_fl *q)
 
 static inline void ring_fl_db(struct adapter *adap, struct sge_fl *q)
 {
-	u32 val;
 	if (q->pend_cred >= 8) {
+		u32 val = adap->params.arch.sge_fl_db;
+
 		if (is_t4(adap->params.chip))
-			val = PIDX_V(q->pend_cred / 8);
+			val |= PIDX_V(q->pend_cred / 8);
 		else
-			val = PIDX_T5_V(q->pend_cred / 8) |
-				DBTYPE_F;
-		val |= DBPRIO_F;
+			val |= PIDX_T5_V(q->pend_cred / 8);
+
+		/* Make sure all memory writes to the Free List queue are
+		 * committed before we tell the hardware about them.
+		 */
 		wmb();
 
 		/* If we don't have access to the new User Doorbell (T5+), use
@@ -594,6 +587,11 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 	struct rx_sw_desc *sd = &q->sdesc[q->pidx];
 	int node;
 
+#ifdef CONFIG_DEBUG_FS
+	if (test_bit(q->cntxt_id - adap->sge.egr_start, adap->sge.blocked_fl))
+		goto out;
+#endif
+
 	gfp |= __GFP_NOWARN;
 	node = dev_to_node(adap->pdev_dev);
 
@@ -930,7 +928,10 @@ static void cxgb_pio_copy(u64 __iomem *dst, u64 *src)
  */
 static inline void ring_tx_db(struct adapter *adap, struct sge_txq *q, int n)
 {
-	wmb();            /* write descriptors before telling HW */
+	/* Make sure that all writes to the TX Descriptors are committed
+	 * before we tell the hardware about them.
+	 */
+	wmb();
 
 	/* If we don't have access to the new User Doorbell (T5+), use the old
 	 * doorbell mechanism; otherwise use the new BAR2 mechanism.
@@ -1032,7 +1033,7 @@ static void inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *q,
  * Figure out what HW csum a packet wants and return the appropriate control
  * bits.
  */
-static u64 hwcsum(const struct sk_buff *skb)
+static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb)
 {
 	int csum_type;
 	const struct iphdr *iph = ip_hdr(skb);
@@ -1047,7 +1048,7 @@ nocsum:			/*
 			 * unknown protocol, disable HW csum
 			 * and hope a bad packet is detected
 			 */
-			return TXPKT_L4CSUM_DIS;
+			return TXPKT_L4CSUM_DIS_F;
 		}
 	} else {
 		/*
@@ -1063,15 +1064,21 @@ nocsum:			/*
 			goto nocsum;
 	}
 
-	if (likely(csum_type >= TX_CSUM_TCPIP))
-		return TXPKT_CSUM_TYPE(csum_type) |
-			TXPKT_IPHDR_LEN(skb_network_header_len(skb)) |
-			TXPKT_ETHHDR_LEN(skb_network_offset(skb) - ETH_HLEN);
-	else {
+	if (likely(csum_type >= TX_CSUM_TCPIP)) {
+		u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb));
+		int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN;
+
+		if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5)
+			hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len);
+		else
+			hdr_len |= T6_TXPKT_ETHHDR_LEN_V(eth_hdr_len);
+		return TXPKT_CSUM_TYPE_V(csum_type) | hdr_len;
+	} else {
 		int start = skb_transport_offset(skb);
 
-		return TXPKT_CSUM_TYPE(csum_type) | TXPKT_CSUM_START(start) |
-			TXPKT_CSUM_LOC(start + skb->csum_offset);
+		return TXPKT_CSUM_TYPE_V(csum_type) |
+			TXPKT_CSUM_START_V(start) |
+			TXPKT_CSUM_LOC_V(start + skb->csum_offset);
 	}
 }
 
@@ -1112,11 +1119,11 @@ cxgb_fcoe_offload(struct sk_buff *skb, struct adapter *adap,
 		return -ENOTSUPP;
 
 	/* FC CRC offload */
-	*cntrl = TXPKT_CSUM_TYPE(TX_CSUM_FCOE) |
-		     TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS |
-		     TXPKT_CSUM_START(CXGB_FCOE_TXPKT_CSUM_START) |
-		     TXPKT_CSUM_END(CXGB_FCOE_TXPKT_CSUM_END) |
-		     TXPKT_CSUM_LOC(CXGB_FCOE_TXPKT_CSUM_END);
+	*cntrl = TXPKT_CSUM_TYPE_V(TX_CSUM_FCOE) |
+		     TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F |
+		     TXPKT_CSUM_START_V(CXGB_FCOE_TXPKT_CSUM_START) |
+		     TXPKT_CSUM_END_V(CXGB_FCOE_TXPKT_CSUM_END) |
+		     TXPKT_CSUM_LOC_V(CXGB_FCOE_TXPKT_CSUM_END);
 	return 0;
 }
 #endif /* CONFIG_CHELSIO_T4_FCOE */
@@ -1130,7 +1137,6 @@ cxgb_fcoe_offload(struct sk_buff *skb, struct adapter *adap,
  */
 netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	int len;
 	u32 wr_mid;
 	u64 cntrl, *end;
 	int qidx, credits;
@@ -1143,6 +1149,7 @@ netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct skb_shared_info *ssi;
 	dma_addr_t addr[MAX_SKB_FRAGS + 1];
 	bool immediate = false;
+	int len, max_pkt_len;
 #ifdef CONFIG_CHELSIO_T4_FCOE
 	int err;
 #endif /* CONFIG_CHELSIO_T4_FCOE */
@@ -1156,13 +1163,20 @@ out_free:	dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
+	/* Discard the packet if the length is greater than mtu */
+	max_pkt_len = ETH_HLEN + dev->mtu;
+	if (skb_vlan_tag_present(skb))
+		max_pkt_len += VLAN_HLEN;
+	if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len)))
+		goto out_free;
+
 	pi = netdev_priv(dev);
 	adap = pi->adapter;
 	qidx = skb_get_queue_mapping(skb);
 	q = &adap->sge.ethtxq[qidx + pi->first_qset];
 
 	reclaim_completed_tx(adap, &q->q, true);
-	cntrl = TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS;
+	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
 
 #ifdef CONFIG_CHELSIO_T4_FCOE
 	err = cxgb_fcoe_offload(skb, adap, pi, &cntrl);
@@ -1213,23 +1227,29 @@ out_free:	dev_kfree_skb_any(skb);
 		len += sizeof(*lso);
 		wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) |
 				       FW_WR_IMMDLEN_V(len));
-		lso->c.lso_ctrl = htonl(LSO_OPCODE(CPL_TX_PKT_LSO) |
-					LSO_FIRST_SLICE | LSO_LAST_SLICE |
-					LSO_IPV6(v6) |
-					LSO_ETHHDR_LEN(eth_xtra_len / 4) |
-					LSO_IPHDR_LEN(l3hdr_len / 4) |
-					LSO_TCPHDR_LEN(tcp_hdr(skb)->doff));
+		lso->c.lso_ctrl = htonl(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+					LSO_FIRST_SLICE_F | LSO_LAST_SLICE_F |
+					LSO_IPV6_V(v6) |
+					LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+					LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+					LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
 		lso->c.ipid_ofst = htons(0);
 		lso->c.mss = htons(ssi->gso_size);
 		lso->c.seqno_offset = htonl(0);
 		if (is_t4(adap->params.chip))
 			lso->c.len = htonl(skb->len);
 		else
-			lso->c.len = htonl(LSO_T5_XFER_SIZE(skb->len));
+			lso->c.len = htonl(LSO_T5_XFER_SIZE_V(skb->len));
 		cpl = (void *)(lso + 1);
-		cntrl = TXPKT_CSUM_TYPE(v6 ? TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
-			TXPKT_IPHDR_LEN(l3hdr_len) |
-			TXPKT_ETHHDR_LEN(eth_xtra_len);
+
+		if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
+			cntrl =	TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+		else
+			cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+
+		cntrl |= TXPKT_CSUM_TYPE_V(v6 ?
+					   TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
+			 TXPKT_IPHDR_LEN_V(l3hdr_len);
 		q->tso++;
 		q->tx_cso += ssi->gso_segs;
 	} else {
@@ -1238,23 +1258,25 @@ out_free:	dev_kfree_skb_any(skb);
 				       FW_WR_IMMDLEN_V(len));
 		cpl = (void *)(wr + 1);
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			cntrl = hwcsum(skb) | TXPKT_IPCSUM_DIS;
+			cntrl = hwcsum(adap->params.chip, skb) |
+				TXPKT_IPCSUM_DIS_F;
 			q->tx_cso++;
 		}
 	}
 
 	if (skb_vlan_tag_present(skb)) {
 		q->vlan_ins++;
-		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(skb_vlan_tag_get(skb));
+		cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
 #ifdef CONFIG_CHELSIO_T4_FCOE
 		if (skb->protocol == htons(ETH_P_FCOE))
-			cntrl |= TXPKT_VLAN(
+			cntrl |= TXPKT_VLAN_V(
 				 ((skb->priority & 0x7) << VLAN_PRIO_SHIFT));
 #endif /* CONFIG_CHELSIO_T4_FCOE */
 	}
 
-	cpl->ctrl0 = htonl(TXPKT_OPCODE(CPL_TX_PKT_XT) |
-			   TXPKT_INTF(pi->tx_chan) | TXPKT_PF(adap->fn));
+	cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT_XT) |
+			   TXPKT_INTF_V(pi->tx_chan) |
+			   TXPKT_PF_V(adap->pf));
 	cpl->pack = htons(0);
 	cpl->len = htons(skb->len);
 	cpl->ctrl1 = cpu_to_be64(cntrl);
@@ -1964,7 +1986,7 @@ static void restore_rx_bufs(const struct pkt_gl *si, struct sge_fl *q,
 static inline bool is_new_response(const struct rsp_ctrl *r,
 				   const struct sge_rspq *q)
 {
-	return RSPD_GEN(r->type_gen) == q->gen;
+	return (r->type_gen >> RSPD_GEN_S) == q->gen;
 }
 
 /**
@@ -2011,19 +2033,19 @@ static int process_responses(struct sge_rspq *q, int budget)
 			break;
 
 		dma_rmb();
-		rsp_type = RSPD_TYPE(rc->type_gen);
-		if (likely(rsp_type == RSP_TYPE_FLBUF)) {
+		rsp_type = RSPD_TYPE_G(rc->type_gen);
+		if (likely(rsp_type == RSPD_TYPE_FLBUF_X)) {
 			struct page_frag *fp;
 			struct pkt_gl si;
 			const struct rx_sw_desc *rsd;
 			u32 len = ntohl(rc->pldbuflen_qid), bufsz, frags;
 
-			if (len & RSPD_NEWBUF) {
+			if (len & RSPD_NEWBUF_F) {
 				if (likely(q->offset > 0)) {
 					free_rx_bufs(q->adap, &rxq->fl, 1);
 					q->offset = 0;
 				}
-				len = RSPD_LEN(len);
+				len = RSPD_LEN_G(len);
 			}
 			si.tot_len = len;
 
@@ -2058,7 +2080,7 @@ static int process_responses(struct sge_rspq *q, int budget)
 				q->offset += ALIGN(fp->size, s->fl_align);
 			else
 				restore_rx_bufs(&si, &rxq->fl, frags);
-		} else if (likely(rsp_type == RSP_TYPE_CPL)) {
+		} else if (likely(rsp_type == RSPD_TYPE_CPL_X)) {
 			ret = q->handler(q, q->cur_desc, NULL);
 		} else {
 			ret = q->handler(q, (const __be64 *)rc, CXGB4_MSG_AN);
@@ -2066,7 +2088,7 @@ static int process_responses(struct sge_rspq *q, int budget)
 
 		if (unlikely(ret)) {
 			/* couldn't process descriptor, back off for recovery */
-			q->next_intr_params = QINTR_TIMER_IDX(NOMEM_TMR_IDX);
+			q->next_intr_params = QINTR_TIMER_IDX_V(NOMEM_TMR_IDX);
 			break;
 		}
 
@@ -2090,7 +2112,7 @@ int cxgb_busy_poll(struct napi_struct *napi)
 		return LL_FLUSH_BUSY;
 
 	work_done = process_responses(q, 4);
-	params = QINTR_TIMER_IDX(TIMERREG_COUNTER0_X) | QINTR_CNT_EN;
+	params = QINTR_TIMER_IDX_V(TIMERREG_COUNTER0_X) | QINTR_CNT_EN_V(1);
 	q->next_intr_params = params;
 	val = CIDXINC_V(work_done) | SEINTARM_V(params);
 
@@ -2137,7 +2159,7 @@ static int napi_rx_handler(struct napi_struct *napi, int budget)
 		int timer_index;
 
 		napi_complete(napi);
-		timer_index = QINTR_TIMER_IDX_GET(q->next_intr_params);
+		timer_index = QINTR_TIMER_IDX_G(q->next_intr_params);
 
 		if (q->adaptive_rx) {
 			if (work_done > max(timer_pkt_quota[timer_index],
@@ -2147,15 +2169,16 @@ static int napi_rx_handler(struct napi_struct *napi, int budget)
 				timer_index = timer_index - 1;
 
 			timer_index = clamp(timer_index, 0, SGE_TIMERREGS - 1);
-			q->next_intr_params = QINTR_TIMER_IDX(timer_index) |
-							      V_QINTR_CNT_EN;
+			q->next_intr_params =
+					QINTR_TIMER_IDX_V(timer_index) |
+					QINTR_CNT_EN_V(0);
 			params = q->next_intr_params;
 		} else {
 			params = q->next_intr_params;
 			q->next_intr_params = q->intr_params;
 		}
 	} else
-		params = QINTR_TIMER_IDX(7);
+		params = QINTR_TIMER_IDX_V(7);
 
 	val = CIDXINC_V(work_done) | SEINTARM_V(params);
 
@@ -2203,7 +2226,7 @@ static unsigned int process_intrq(struct adapter *adap)
 			break;
 
 		dma_rmb();
-		if (RSPD_TYPE(rc->type_gen) == RSP_TYPE_INTR) {
+		if (RSPD_TYPE_G(rc->type_gen) == RSPD_TYPE_INTR_X) {
 			unsigned int qid = ntohl(rc->pldbuflen_qid);
 
 			qid -= adap->sge.ingr_start;
@@ -2279,7 +2302,7 @@ irq_handler_t t4_intr_handler(struct adapter *adap)
 static void sge_rx_timer_cb(unsigned long data)
 {
 	unsigned long m;
-	unsigned int i, idma_same_state_cnt[2];
+	unsigned int i;
 	struct adapter *adap = (struct adapter *)data;
 	struct sge *s = &adap->sge;
 
@@ -2300,67 +2323,16 @@ static void sge_rx_timer_cb(unsigned long data)
 					set_bit(id, s->starving_fl);
 			}
 		}
+	/* The remainder of the SGE RX Timer Callback routine is dedicated to
+	 * global Master PF activities like checking for chip ingress stalls,
+	 * etc.
+	 */
+	if (!(adap->flags & MASTER_PF))
+		goto done;
 
-	t4_write_reg(adap, SGE_DEBUG_INDEX_A, 13);
-	idma_same_state_cnt[0] = t4_read_reg(adap, SGE_DEBUG_DATA_HIGH_A);
-	idma_same_state_cnt[1] = t4_read_reg(adap, SGE_DEBUG_DATA_LOW_A);
-
-	for (i = 0; i < 2; i++) {
-		u32 debug0, debug11;
-
-		/* If the Ingress DMA Same State Counter ("timer") is less
-		 * than 1s, then we can reset our synthesized Stall Timer and
-		 * continue.  If we have previously emitted warnings about a
-		 * potential stalled Ingress Queue, issue a note indicating
-		 * that the Ingress Queue has resumed forward progress.
-		 */
-		if (idma_same_state_cnt[i] < s->idma_1s_thresh) {
-			if (s->idma_stalled[i] >= SGE_IDMA_WARN_THRESH)
-				CH_WARN(adap, "SGE idma%d, queue%u,resumed after %d sec\n",
-					i, s->idma_qid[i],
-					s->idma_stalled[i]/HZ);
-			s->idma_stalled[i] = 0;
-			continue;
-		}
-
-		/* Synthesize an SGE Ingress DMA Same State Timer in the Hz
-		 * domain.  The first time we get here it'll be because we
-		 * passed the 1s Threshold; each additional time it'll be
-		 * because the RX Timer Callback is being fired on its regular
-		 * schedule.
-		 *
-		 * If the stall is below our Potential Hung Ingress Queue
-		 * Warning Threshold, continue.
-		 */
-		if (s->idma_stalled[i] == 0)
-			s->idma_stalled[i] = HZ;
-		else
-			s->idma_stalled[i] += RX_QCHECK_PERIOD;
-
-		if (s->idma_stalled[i] < SGE_IDMA_WARN_THRESH)
-			continue;
-
-		/* We'll issue a warning every SGE_IDMA_WARN_REPEAT Hz */
-		if (((s->idma_stalled[i] - HZ) % SGE_IDMA_WARN_REPEAT) != 0)
-			continue;
-
-		/* Read and save the SGE IDMA State and Queue ID information.
-		 * We do this every time in case it changes across time ...
-		 */
-		t4_write_reg(adap, SGE_DEBUG_INDEX_A, 0);
-		debug0 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW_A);
-		s->idma_state[i] = (debug0 >> (i * 9)) & 0x3f;
-
-		t4_write_reg(adap, SGE_DEBUG_INDEX_A, 11);
-		debug11 = t4_read_reg(adap, SGE_DEBUG_DATA_LOW_A);
-		s->idma_qid[i] = (debug11 >> (i * 16)) & 0xffff;
-
-		CH_WARN(adap, "SGE idma%u, queue%u, maybe stuck state%u %dsecs (debug0=%#x, debug11=%#x)\n",
-			i, s->idma_qid[i], s->idma_state[i],
-			s->idma_stalled[i]/HZ, debug0, debug11);
-		t4_sge_decode_idma_state(adap, s->idma_state[i]);
-	}
+	t4_idma_monitor(adap, &s->idma_monitor, HZ, RX_QCHECK_PERIOD);
 
+done:
 	mod_timer(&s->rx_timer, jiffies + RX_QCHECK_PERIOD);
 }
 
@@ -2429,7 +2401,7 @@ static void __iomem *bar2_address(struct adapter *adapter,
 	u64 bar2_qoffset;
 	int ret;
 
-	ret = cxgb4_t4_bar2_sge_qregs(adapter, qid, qtype,
+	ret = t4_bar2_sge_qregs(adapter, qid, qtype, 0,
 				&bar2_qoffset, pbar2_qid);
 	if (ret)
 		return NULL;
@@ -2437,9 +2409,12 @@ static void __iomem *bar2_address(struct adapter *adapter,
 	return adapter->bar2 + bar2_qoffset;
 }
 
+/* @intr_idx: MSI/MSI-X vector if >=0, -(absolute qid + 1) if < 0
+ * @cong: < 0 -> no congestion feedback, >= 0 -> congestion channel map
+ */
 int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     struct net_device *dev, int intr_idx,
-		     struct sge_fl *fl, rspq_handler_t hnd)
+		     struct sge_fl *fl, rspq_handler_t hnd, int cong)
 {
 	int ret, flsz = 0;
 	struct fw_iq_cmd c;
@@ -2457,12 +2432,13 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	memset(&c, 0, sizeof(c));
 	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_IQ_CMD) | FW_CMD_REQUEST_F |
 			    FW_CMD_WRITE_F | FW_CMD_EXEC_F |
-			    FW_IQ_CMD_PFN_V(adap->fn) | FW_IQ_CMD_VFN_V(0));
+			    FW_IQ_CMD_PFN_V(adap->pf) | FW_IQ_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_IQ_CMD_ALLOC_F | FW_IQ_CMD_IQSTART_F |
 				 FW_LEN16(c));
 	c.type_to_iqandstindex = htonl(FW_IQ_CMD_TYPE_V(FW_IQ_TYPE_FL_INT_CAP) |
 		FW_IQ_CMD_IQASYNCH_V(fwevtq) | FW_IQ_CMD_VIID_V(pi->viid) |
-		FW_IQ_CMD_IQANDST_V(intr_idx < 0) | FW_IQ_CMD_IQANUD_V(1) |
+		FW_IQ_CMD_IQANDST_V(intr_idx < 0) |
+		FW_IQ_CMD_IQANUD_V(UPDATEDELIVERY_INTERRUPT_X) |
 		FW_IQ_CMD_IQANDSTINDEX_V(intr_idx >= 0 ? intr_idx :
 							-intr_idx - 1));
 	c.iqdroprss_to_iqesize = htons(FW_IQ_CMD_IQPCIECH_V(pi->tx_chan) |
@@ -2471,8 +2447,21 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		FW_IQ_CMD_IQESIZE_V(ilog2(iq->iqe_len) - 4));
 	c.iqsize = htons(iq->size);
 	c.iqaddr = cpu_to_be64(iq->phys_addr);
+	if (cong >= 0)
+		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F);
 
 	if (fl) {
+		enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
+
+		/* Allocate the ring for the hardware free list (with space
+		 * for its status page) along with the associated software
+		 * descriptor ring.  The free list size needs to be a multiple
+		 * of the Egress Queue Unit and at least 2 Egress Units larger
+		 * than the SGE's Egress Congrestion Threshold
+		 * (fl_starve_thres - 1).
+		 */
+		if (fl->size < s->fl_starve_thres - 1 + 2 * 8)
+			fl->size = s->fl_starve_thres - 1 + 2 * 8;
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
@@ -2481,17 +2470,25 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 			goto fl_nomem;
 
 		flsz = fl->size / 8 + s->stat_len / sizeof(struct tx_desc);
-		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_FL0PACKEN_F |
-					    FW_IQ_CMD_FL0FETCHRO_F |
-					    FW_IQ_CMD_FL0DATARO_F |
-					    FW_IQ_CMD_FL0PADEN_F);
-		c.fl0dcaen_to_fl0cidxfthresh = htons(FW_IQ_CMD_FL0FBMIN_V(2) |
-				FW_IQ_CMD_FL0FBMAX_V(3));
+		c.iqns_to_fl0congen |= htonl(FW_IQ_CMD_FL0PACKEN_F |
+					     FW_IQ_CMD_FL0FETCHRO_F |
+					     FW_IQ_CMD_FL0DATARO_F |
+					     FW_IQ_CMD_FL0PADEN_F);
+		if (cong >= 0)
+			c.iqns_to_fl0congen |=
+				htonl(FW_IQ_CMD_FL0CNGCHMAP_V(cong) |
+				      FW_IQ_CMD_FL0CONGCIF_F |
+				      FW_IQ_CMD_FL0CONGEN_F);
+		c.fl0dcaen_to_fl0cidxfthresh =
+			htons(FW_IQ_CMD_FL0FBMIN_V(FETCHBURSTMIN_64B_X) |
+			      FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+						   FETCHBURSTMAX_512B_X :
+						   FETCHBURSTMAX_256B_X));
 		c.fl0size = htons(flsz);
 		c.fl0addr = cpu_to_be64(fl->addr);
 	}
 
-	ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c);
+	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret)
 		goto err;
 
@@ -2532,6 +2529,41 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 					     &fl->bar2_qid);
 		refill_fl(adap, fl, fl_cap(fl), GFP_KERNEL);
 	}
+
+	/* For T5 and later we attempt to set up the Congestion Manager values
+	 * of the new RX Ethernet Queue.  This should really be handled by
+	 * firmware because it's more complex than any host driver wants to
+	 * get involved with and it's different per chip and this is almost
+	 * certainly wrong.  Firmware would be wrong as well, but it would be
+	 * a lot easier to fix in one place ...  For now we do something very
+	 * simple (and hopefully less wrong).
+	 */
+	if (!is_t4(adap->params.chip) && cong >= 0) {
+		u32 param, val;
+		int i;
+
+		param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
+			 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_CONM_CTXT) |
+			 FW_PARAMS_PARAM_YZ_V(iq->cntxt_id));
+		if (cong == 0) {
+			val = CONMCTXT_CNGTPMODE_V(CONMCTXT_CNGTPMODE_QUEUE_X);
+		} else {
+			val =
+			    CONMCTXT_CNGTPMODE_V(CONMCTXT_CNGTPMODE_CHANNEL_X);
+			for (i = 0; i < 4; i++) {
+				if (cong & (1 << i))
+					val |=
+					     CONMCTXT_CNGCHMAP_V(1 << (i << 2));
+			}
+		}
+		ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1,
+				    &param, &val);
+		if (ret)
+			dev_warn(adap->pdev_dev, "Failed to set Congestion"
+				 " Manager Context for Ingress Queue %d: %d\n",
+				 iq->cntxt_id, -ret);
+	}
+
 	return 0;
 
 fl_nomem:
@@ -2589,23 +2621,24 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	memset(&c, 0, sizeof(c));
 	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_ETH_CMD) | FW_CMD_REQUEST_F |
 			    FW_CMD_WRITE_F | FW_CMD_EXEC_F |
-			    FW_EQ_ETH_CMD_PFN_V(adap->fn) |
+			    FW_EQ_ETH_CMD_PFN_V(adap->pf) |
 			    FW_EQ_ETH_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F |
 				 FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c));
 	c.viid_pkd = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
 			   FW_EQ_ETH_CMD_VIID_V(pi->viid));
-	c.fetchszm_to_iqid = htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(2) |
-				   FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
-				   FW_EQ_ETH_CMD_FETCHRO_V(1) |
-				   FW_EQ_ETH_CMD_IQID_V(iqid));
-	c.dcaen_to_eqsize = htonl(FW_EQ_ETH_CMD_FBMIN_V(2) |
-				  FW_EQ_ETH_CMD_FBMAX_V(3) |
-				  FW_EQ_ETH_CMD_CIDXFTHRESH_V(5) |
-				  FW_EQ_ETH_CMD_EQSIZE_V(nentries));
+	c.fetchszm_to_iqid =
+		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
+		      FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
+		      FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid));
+	c.dcaen_to_eqsize =
+		htonl(FW_EQ_ETH_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		      FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
+		      FW_EQ_ETH_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
+		      FW_EQ_ETH_CMD_EQSIZE_V(nentries));
 	c.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
-	ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c);
+	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret) {
 		kfree(txq->q.sdesc);
 		txq->q.sdesc = NULL;
@@ -2637,29 +2670,30 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 
 	txq->q.desc = alloc_ring(adap->pdev_dev, nentries,
 				 sizeof(struct tx_desc), 0, &txq->q.phys_addr,
-				 NULL, 0, NUMA_NO_NODE);
+				 NULL, 0, dev_to_node(adap->pdev_dev));
 	if (!txq->q.desc)
 		return -ENOMEM;
 
 	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_CTRL_CMD) | FW_CMD_REQUEST_F |
 			    FW_CMD_WRITE_F | FW_CMD_EXEC_F |
-			    FW_EQ_CTRL_CMD_PFN_V(adap->fn) |
+			    FW_EQ_CTRL_CMD_PFN_V(adap->pf) |
 			    FW_EQ_CTRL_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_EQ_CTRL_CMD_ALLOC_F |
 				 FW_EQ_CTRL_CMD_EQSTART_F | FW_LEN16(c));
 	c.cmpliqid_eqid = htonl(FW_EQ_CTRL_CMD_CMPLIQID_V(cmplqid));
 	c.physeqid_pkd = htonl(0);
-	c.fetchszm_to_iqid = htonl(FW_EQ_CTRL_CMD_HOSTFCMODE_V(2) |
-				   FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) |
-				   FW_EQ_CTRL_CMD_FETCHRO_F |
-				   FW_EQ_CTRL_CMD_IQID_V(iqid));
-	c.dcaen_to_eqsize = htonl(FW_EQ_CTRL_CMD_FBMIN_V(2) |
-				  FW_EQ_CTRL_CMD_FBMAX_V(3) |
-				  FW_EQ_CTRL_CMD_CIDXFTHRESH_V(5) |
-				  FW_EQ_CTRL_CMD_EQSIZE_V(nentries));
+	c.fetchszm_to_iqid =
+		htonl(FW_EQ_CTRL_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
+		      FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) |
+		      FW_EQ_CTRL_CMD_FETCHRO_F | FW_EQ_CTRL_CMD_IQID_V(iqid));
+	c.dcaen_to_eqsize =
+		htonl(FW_EQ_CTRL_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		      FW_EQ_CTRL_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
+		      FW_EQ_CTRL_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
+		      FW_EQ_CTRL_CMD_EQSIZE_V(nentries));
 	c.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
-	ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c);
+	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret) {
 		dma_free_coherent(adap->pdev_dev,
 				  nentries * sizeof(struct tx_desc),
@@ -2697,21 +2731,22 @@ int t4_sge_alloc_ofld_txq(struct adapter *adap, struct sge_ofld_txq *txq,
 	memset(&c, 0, sizeof(c));
 	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_OFLD_CMD) | FW_CMD_REQUEST_F |
 			    FW_CMD_WRITE_F | FW_CMD_EXEC_F |
-			    FW_EQ_OFLD_CMD_PFN_V(adap->fn) |
+			    FW_EQ_OFLD_CMD_PFN_V(adap->pf) |
 			    FW_EQ_OFLD_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_EQ_OFLD_CMD_ALLOC_F |
 				 FW_EQ_OFLD_CMD_EQSTART_F | FW_LEN16(c));
-	c.fetchszm_to_iqid = htonl(FW_EQ_OFLD_CMD_HOSTFCMODE_V(2) |
-				   FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) |
-				   FW_EQ_OFLD_CMD_FETCHRO_F |
-				   FW_EQ_OFLD_CMD_IQID_V(iqid));
-	c.dcaen_to_eqsize = htonl(FW_EQ_OFLD_CMD_FBMIN_V(2) |
-				  FW_EQ_OFLD_CMD_FBMAX_V(3) |
-				  FW_EQ_OFLD_CMD_CIDXFTHRESH_V(5) |
-				  FW_EQ_OFLD_CMD_EQSIZE_V(nentries));
+	c.fetchszm_to_iqid =
+		htonl(FW_EQ_OFLD_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
+		      FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) |
+		      FW_EQ_OFLD_CMD_FETCHRO_F | FW_EQ_OFLD_CMD_IQID_V(iqid));
+	c.dcaen_to_eqsize =
+		htonl(FW_EQ_OFLD_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		      FW_EQ_OFLD_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
+		      FW_EQ_OFLD_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
+		      FW_EQ_OFLD_CMD_EQSIZE_V(nentries));
 	c.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
-	ret = t4_wr_mbox(adap, adap->fn, &c, sizeof(c), &c);
+	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret) {
 		kfree(txq->q.sdesc);
 		txq->q.sdesc = NULL;
@@ -2750,7 +2785,7 @@ static void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq,
 	unsigned int fl_id = fl ? fl->cntxt_id : 0xffff;
 
 	adap->sge.ingr_map[rq->cntxt_id - adap->sge.ingr_start] = NULL;
-	t4_iq_free(adap, adap->fn, adap->fn, 0, FW_IQ_TYPE_FL_INT_CAP,
+	t4_iq_free(adap, adap->mbox, adap->pf, 0, FW_IQ_TYPE_FL_INT_CAP,
 		   rq->cntxt_id, fl_id, 0xffff);
 	dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len,
 			  rq->desc, rq->phys_addr);
@@ -2805,7 +2840,7 @@ void t4_free_sge_resources(struct adapter *adap)
 			free_rspq_fl(adap, &eq->rspq,
 				     eq->fl.size ? &eq->fl : NULL);
 		if (etq->q.desc) {
-			t4_eth_eq_free(adap, adap->fn, adap->fn, 0,
+			t4_eth_eq_free(adap, adap->mbox, adap->pf, 0,
 				       etq->q.cntxt_id);
 			free_tx_desc(adap, &etq->q, etq->q.in_use, true);
 			kfree(etq->q.sdesc);
@@ -2824,7 +2859,7 @@ void t4_free_sge_resources(struct adapter *adap)
 
 		if (q->q.desc) {
 			tasklet_kill(&q->qresume_tsk);
-			t4_ofld_eq_free(adap, adap->fn, adap->fn, 0,
+			t4_ofld_eq_free(adap, adap->mbox, adap->pf, 0,
 					q->q.cntxt_id);
 			free_tx_desc(adap, &q->q, q->q.in_use, false);
 			kfree(q->q.sdesc);
@@ -2839,7 +2874,7 @@ void t4_free_sge_resources(struct adapter *adap)
 
 		if (cq->q.desc) {
 			tasklet_kill(&cq->qresume_tsk);
-			t4_ctrl_eq_free(adap, adap->fn, adap->fn, 0,
+			t4_ctrl_eq_free(adap, adap->mbox, adap->pf, 0,
 					cq->q.cntxt_id);
 			__skb_queue_purge(&cq->sendq);
 			free_txq(adap, &cq->q);
@@ -3023,7 +3058,11 @@ int t4_sge_init(struct adapter *adap)
 	 * Packing Boundary.  T5 introduced the ability to specify these
 	 * separately.  The actual Ingress Packet Data alignment boundary
 	 * within Packed Buffer Mode is the maximum of these two
-	 * specifications.
+	 * specifications.  (Note that it makes no real practical sense to
+	 * have the Pading Boudary be larger than the Packing Boundary but you
+	 * could set the chip up that way and, in fact, legacy T4 code would
+	 * end doing this because it would initialize the Padding Boundary and
+	 * leave the Packing Boundary initialized to 0 (16 bytes).)
 	 */
 	ingpadboundary = 1 << (INGPADBOUNDARY_G(sge_control) +
 			       INGPADBOUNDARY_SHIFT_X);
@@ -3067,11 +3106,14 @@ int t4_sge_init(struct adapter *adap)
 		egress_threshold = EGRTHRESHOLDPACKING_G(sge_conm_ctrl);
 	s->fl_starve_thres = 2*egress_threshold + 1;
 
+	t4_idma_monitor_init(adap, &s->idma_monitor);
+
+	/* Set up timers used for recuring callbacks to process RX and TX
+	 * administrative tasks.
+	 */
 	setup_timer(&s->rx_timer, sge_rx_timer_cb, (unsigned long)adap);
 	setup_timer(&s->tx_timer, sge_tx_timer_cb, (unsigned long)adap);
-	s->idma_1s_thresh = core_ticks_per_usec(adap) * 1000000;  /* 1 s */
-	s->idma_stalled[0] = 0;
-	s->idma_stalled[1] = 0;
+
 	spin_lock_init(&s->intrq_lock);
 
 	return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index e8578a742f2a..2b52aae7ec86 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -150,7 +150,12 @@ void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
  */
 void t4_hw_pci_read_cfg4(struct adapter *adap, int reg, u32 *val)
 {
-	u32 req = ENABLE_F | FUNCTION_V(adap->fn) | REGISTER_V(reg);
+	u32 req = FUNCTION_V(adap->pf) | REGISTER_V(reg);
+
+	if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
+		req |= ENABLE_F;
+	else
+		req |= T6_ENABLE_F;
 
 	if (is_t4(adap->params.chip))
 		req |= LOCALCFG_F;
@@ -214,8 +219,8 @@ static void fw_asrt(struct adapter *adap, u32 mbox_addr)
 	get_mbox_rpl(adap, (__be64 *)&asrt, sizeof(asrt) / 8, mbox_addr);
 	dev_alert(adap->pdev_dev,
 		  "FW assertion at %.16s:%u, val0 %#x, val1 %#x\n",
-		  asrt.u.assert.filename_0_7, ntohl(asrt.u.assert.line),
-		  ntohl(asrt.u.assert.x), ntohl(asrt.u.assert.y));
+		  asrt.u.assert.filename_0_7, be32_to_cpu(asrt.u.assert.line),
+		  be32_to_cpu(asrt.u.assert.x), be32_to_cpu(asrt.u.assert.y));
 }
 
 static void dump_mbox(struct adapter *adap, int mbox, u32 data_reg)
@@ -233,13 +238,14 @@ static void dump_mbox(struct adapter *adap, int mbox, u32 data_reg)
 }
 
 /**
- *	t4_wr_mbox_meat - send a command to FW through the given mailbox
+ *	t4_wr_mbox_meat_timeout - send a command to FW through the given mailbox
  *	@adap: the adapter
  *	@mbox: index of the mailbox to use
  *	@cmd: the command to write
  *	@size: command length in bytes
  *	@rpl: where to optionally store the reply
  *	@sleep_ok: if true we may sleep while awaiting command completion
+ *	@timeout: time to wait for command to finish before timing out
  *
  *	Sends the given command to FW through the selected mailbox and waits
  *	for the FW to execute the command.  If @rpl is not %NULL it is used to
@@ -254,8 +260,8 @@ static void dump_mbox(struct adapter *adap, int mbox, u32 data_reg)
  *	command or FW executes it but signals an error.  In the latter case
  *	the return value is the error code indicated by FW (negated).
  */
-int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
-		    void *rpl, bool sleep_ok)
+int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd,
+			    int size, void *rpl, bool sleep_ok, int timeout)
 {
 	static const int delay[] = {
 		1, 1, 3, 5, 10, 10, 20, 50, 100, 200
@@ -294,7 +300,7 @@ int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
 	delay_idx = 0;
 	ms = delay[0];
 
-	for (i = 0; i < FW_CMD_MAX_TIMEOUT; i += ms) {
+	for (i = 0; i < timeout; i += ms) {
 		if (sleep_ok) {
 			ms = delay[delay_idx];  /* last element may repeat */
 			if (delay_idx < ARRAY_SIZE(delay) - 1)
@@ -332,114 +338,11 @@ int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
 	return -ETIMEDOUT;
 }
 
-/**
- *	t4_mc_read - read from MC through backdoor accesses
- *	@adap: the adapter
- *	@addr: address of first byte requested
- *	@idx: which MC to access
- *	@data: 64 bytes of data containing the requested address
- *	@ecc: where to store the corresponding 64-bit ECC word
- *
- *	Read 64 bytes of data from MC starting at a 64-byte-aligned address
- *	that covers the requested address @addr.  If @parity is not %NULL it
- *	is assigned the 64-bit ECC word for the read data.
- */
-int t4_mc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
-{
-	int i;
-	u32 mc_bist_cmd, mc_bist_cmd_addr, mc_bist_cmd_len;
-	u32 mc_bist_status_rdata, mc_bist_data_pattern;
-
-	if (is_t4(adap->params.chip)) {
-		mc_bist_cmd = MC_BIST_CMD_A;
-		mc_bist_cmd_addr = MC_BIST_CMD_ADDR_A;
-		mc_bist_cmd_len = MC_BIST_CMD_LEN_A;
-		mc_bist_status_rdata = MC_BIST_STATUS_RDATA_A;
-		mc_bist_data_pattern = MC_BIST_DATA_PATTERN_A;
-	} else {
-		mc_bist_cmd = MC_REG(MC_P_BIST_CMD_A, idx);
-		mc_bist_cmd_addr = MC_REG(MC_P_BIST_CMD_ADDR_A, idx);
-		mc_bist_cmd_len = MC_REG(MC_P_BIST_CMD_LEN_A, idx);
-		mc_bist_status_rdata = MC_REG(MC_P_BIST_STATUS_RDATA_A, idx);
-		mc_bist_data_pattern = MC_REG(MC_P_BIST_DATA_PATTERN_A, idx);
-	}
-
-	if (t4_read_reg(adap, mc_bist_cmd) & START_BIST_F)
-		return -EBUSY;
-	t4_write_reg(adap, mc_bist_cmd_addr, addr & ~0x3fU);
-	t4_write_reg(adap, mc_bist_cmd_len, 64);
-	t4_write_reg(adap, mc_bist_data_pattern, 0xc);
-	t4_write_reg(adap, mc_bist_cmd, BIST_OPCODE_V(1) | START_BIST_F |
-		     BIST_CMD_GAP_V(1));
-	i = t4_wait_op_done(adap, mc_bist_cmd, START_BIST_F, 0, 10, 1);
-	if (i)
-		return i;
-
-#define MC_DATA(i) MC_BIST_STATUS_REG(mc_bist_status_rdata, i)
-
-	for (i = 15; i >= 0; i--)
-		*data++ = htonl(t4_read_reg(adap, MC_DATA(i)));
-	if (ecc)
-		*ecc = t4_read_reg64(adap, MC_DATA(16));
-#undef MC_DATA
-	return 0;
-}
-
-/**
- *	t4_edc_read - read from EDC through backdoor accesses
- *	@adap: the adapter
- *	@idx: which EDC to access
- *	@addr: address of first byte requested
- *	@data: 64 bytes of data containing the requested address
- *	@ecc: where to store the corresponding 64-bit ECC word
- *
- *	Read 64 bytes of data from EDC starting at a 64-byte-aligned address
- *	that covers the requested address @addr.  If @parity is not %NULL it
- *	is assigned the 64-bit ECC word for the read data.
- */
-int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
+int t4_wr_mbox_meat(struct adapter *adap, int mbox, const void *cmd, int size,
+		    void *rpl, bool sleep_ok)
 {
-	int i;
-	u32 edc_bist_cmd, edc_bist_cmd_addr, edc_bist_cmd_len;
-	u32 edc_bist_cmd_data_pattern, edc_bist_status_rdata;
-
-	if (is_t4(adap->params.chip)) {
-		edc_bist_cmd = EDC_REG(EDC_BIST_CMD_A, idx);
-		edc_bist_cmd_addr = EDC_REG(EDC_BIST_CMD_ADDR_A, idx);
-		edc_bist_cmd_len = EDC_REG(EDC_BIST_CMD_LEN_A, idx);
-		edc_bist_cmd_data_pattern = EDC_REG(EDC_BIST_DATA_PATTERN_A,
-						    idx);
-		edc_bist_status_rdata = EDC_REG(EDC_BIST_STATUS_RDATA_A,
-						idx);
-	} else {
-		edc_bist_cmd = EDC_REG_T5(EDC_H_BIST_CMD_A, idx);
-		edc_bist_cmd_addr = EDC_REG_T5(EDC_H_BIST_CMD_ADDR_A, idx);
-		edc_bist_cmd_len = EDC_REG_T5(EDC_H_BIST_CMD_LEN_A, idx);
-		edc_bist_cmd_data_pattern =
-			EDC_REG_T5(EDC_H_BIST_DATA_PATTERN_A, idx);
-		edc_bist_status_rdata =
-			 EDC_REG_T5(EDC_H_BIST_STATUS_RDATA_A, idx);
-	}
-
-	if (t4_read_reg(adap, edc_bist_cmd) & START_BIST_F)
-		return -EBUSY;
-	t4_write_reg(adap, edc_bist_cmd_addr, addr & ~0x3fU);
-	t4_write_reg(adap, edc_bist_cmd_len, 64);
-	t4_write_reg(adap, edc_bist_cmd_data_pattern, 0xc);
-	t4_write_reg(adap, edc_bist_cmd,
-		     BIST_OPCODE_V(1) | BIST_CMD_GAP_V(1) | START_BIST_F);
-	i = t4_wait_op_done(adap, edc_bist_cmd, START_BIST_F, 0, 10, 1);
-	if (i)
-		return i;
-
-#define EDC_DATA(i) (EDC_BIST_STATUS_REG(edc_bist_status_rdata, i))
-
-	for (i = 15; i >= 0; i--)
-		*data++ = htonl(t4_read_reg(adap, EDC_DATA(i)));
-	if (ecc)
-		*ecc = t4_read_reg64(adap, EDC_DATA(16));
-#undef EDC_DATA
-	return 0;
+	return t4_wr_mbox_meat_timeout(adap, mbox, cmd, size, rpl, sleep_ok,
+				       FW_CMD_MAX_TIMEOUT);
 }
 
 /**
@@ -483,9 +386,8 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 	/* Offset into the region of memory which is being accessed
 	 * MEM_EDC0 = 0
 	 * MEM_EDC1 = 1
-	 * MEM_MC   = 2 -- T4
-	 * MEM_MC0  = 2 -- For T5
-	 * MEM_MC1  = 3 -- For T5
+	 * MEM_MC   = 2 -- MEM_MC for chips with only 1 memory controller
+	 * MEM_MC1  = 3 -- for chips with 2 memory controllers (e.g. T5)
 	 */
 	edc_size  = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A));
 	if (mtype != MEM_MC1)
@@ -514,7 +416,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 	mem_base = PCIEOFST_G(mem_reg) << PCIEOFST_SHIFT_X;
 	if (is_t4(adap->params.chip))
 		mem_base -= adap->t4_bar0;
-	win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->fn);
+	win_pf = is_t4(adap->params.chip) ? 0 : PFNUM_V(adap->pf);
 
 	/* Calculate our initial PCI-E Memory Window Position and Offset into
 	 * that Window.
@@ -625,6 +527,102 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 	return 0;
 }
 
+/* Return the specified PCI-E Configuration Space register from our Physical
+ * Function.  We try first via a Firmware LDST Command since we prefer to let
+ * the firmware own all of these registers, but if that fails we go for it
+ * directly ourselves.
+ */
+u32 t4_read_pcie_cfg4(struct adapter *adap, int reg)
+{
+	u32 val, ldst_addrspace;
+
+	/* If fw_attach != 0, construct and send the Firmware LDST Command to
+	 * retrieve the specified PCI-E Configuration Space register.
+	 */
+	struct fw_ldst_cmd ldst_cmd;
+	int ret;
+
+	memset(&ldst_cmd, 0, sizeof(ldst_cmd));
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_FUNC_PCIE);
+	ldst_cmd.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+					       FW_CMD_REQUEST_F |
+					       FW_CMD_READ_F |
+					       ldst_addrspace);
+	ldst_cmd.cycles_to_len16 = cpu_to_be32(FW_LEN16(ldst_cmd));
+	ldst_cmd.u.pcie.select_naccess = FW_LDST_CMD_NACCESS_V(1);
+	ldst_cmd.u.pcie.ctrl_to_fn =
+		(FW_LDST_CMD_LC_F | FW_LDST_CMD_FN_V(adap->pf));
+	ldst_cmd.u.pcie.r = reg;
+
+	/* If the LDST Command succeeds, return the result, otherwise
+	 * fall through to reading it directly ourselves ...
+	 */
+	ret = t4_wr_mbox(adap, adap->mbox, &ldst_cmd, sizeof(ldst_cmd),
+			 &ldst_cmd);
+	if (ret == 0)
+		val = be32_to_cpu(ldst_cmd.u.pcie.data[0]);
+	else
+		/* Read the desired Configuration Space register via the PCI-E
+		 * Backdoor mechanism.
+		 */
+		t4_hw_pci_read_cfg4(adap, reg, &val);
+	return val;
+}
+
+/* Get the window based on base passed to it.
+ * Window aperture is currently unhandled, but there is no use case for it
+ * right now
+ */
+static u32 t4_get_window(struct adapter *adap, u32 pci_base, u64 pci_mask,
+			 u32 memwin_base)
+{
+	u32 ret;
+
+	if (is_t4(adap->params.chip)) {
+		u32 bar0;
+
+		/* Truncation intentional: we only read the bottom 32-bits of
+		 * the 64-bit BAR0/BAR1 ...  We use the hardware backdoor
+		 * mechanism to read BAR0 instead of using
+		 * pci_resource_start() because we could be operating from
+		 * within a Virtual Machine which is trapping our accesses to
+		 * our Configuration Space and we need to set up the PCI-E
+		 * Memory Window decoders with the actual addresses which will
+		 * be coming across the PCI-E link.
+		 */
+		bar0 = t4_read_pcie_cfg4(adap, pci_base);
+		bar0 &= pci_mask;
+		adap->t4_bar0 = bar0;
+
+		ret = bar0 + memwin_base;
+	} else {
+		/* For T5, only relative offset inside the PCIe BAR is passed */
+		ret = memwin_base;
+	}
+	return ret;
+}
+
+/* Get the default utility window (win0) used by everyone */
+u32 t4_get_util_window(struct adapter *adap)
+{
+	return t4_get_window(adap, PCI_BASE_ADDRESS_0,
+			     PCI_BASE_ADDRESS_MEM_MASK, MEMWIN0_BASE);
+}
+
+/* Set up memory window for accessing adapter memory ranges.  (Read
+ * back MA register to ensure that changes propagate before we attempt
+ * to use the new values.)
+ */
+void t4_setup_memwin(struct adapter *adap, u32 memwin_base, u32 window)
+{
+	t4_write_reg(adap,
+		     PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, window),
+		     memwin_base | BIR_V(0) |
+		     WINDOW_V(ilog2(MEMWIN0_APERTURE) - WINDOW_SHIFT_X));
+	t4_read_reg(adap,
+		    PCIE_MEM_ACCESS_REG(PCIE_MEM_ACCESS_BASE_WIN_A, window));
+}
+
 /**
  *	t4_get_regs_len - return the size of the chips register set
  *	@adapter: the adapter
@@ -640,6 +638,7 @@ unsigned int t4_get_regs_len(struct adapter *adapter)
 		return T4_REGMAP_SIZE;
 
 	case CHELSIO_T5:
+	case CHELSIO_T6:
 		return T5_REGMAP_SIZE;
 	}
 
@@ -666,7 +665,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x11fc, 0x123c,
 		0x1300, 0x173c,
 		0x1800, 0x18fc,
-		0x3000, 0x30d8,
+		0x3000, 0x305c,
+		0x3068, 0x30d8,
 		0x30e0, 0x5924,
 		0x5960, 0x59d4,
 		0x5a00, 0x5af8,
@@ -729,7 +729,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x19238, 0x1924c,
 		0x193f8, 0x19474,
 		0x19490, 0x194f8,
-		0x19800, 0x19f30,
+		0x19800, 0x19f4c,
 		0x1a000, 0x1a06c,
 		0x1a0b0, 0x1a120,
 		0x1a128, 0x1a138,
@@ -878,7 +878,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x27780, 0x2778c,
 		0x27800, 0x27c38,
 		0x27c80, 0x27d7c,
-		0x27e00, 0x27e04
+		0x27e00, 0x27e04,
 	};
 
 	static const unsigned int t5_reg_ranges[] = {
@@ -888,7 +888,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x1280, 0x173c,
 		0x1800, 0x18fc,
 		0x3000, 0x3028,
-		0x3060, 0x30d8,
+		0x3068, 0x30d8,
 		0x30e0, 0x30fc,
 		0x3140, 0x357c,
 		0x35a8, 0x35cc,
@@ -900,7 +900,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x5940, 0x59dc,
 		0x59fc, 0x5a18,
 		0x5a60, 0x5a9c,
-		0x5b9c, 0x5bfc,
+		0x5b94, 0x5bfc,
 		0x6000, 0x6040,
 		0x6058, 0x614c,
 		0x7700, 0x7798,
@@ -1014,27 +1014,30 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x30800, 0x30834,
 		0x308c0, 0x30908,
 		0x30910, 0x309ac,
-		0x30a00, 0x30a04,
-		0x30a0c, 0x30a2c,
+		0x30a00, 0x30a2c,
 		0x30a44, 0x30a50,
 		0x30a74, 0x30c24,
+		0x30d00, 0x30d00,
 		0x30d08, 0x30d14,
 		0x30d1c, 0x30d20,
 		0x30d3c, 0x30d50,
 		0x31200, 0x3120c,
 		0x31220, 0x31220,
 		0x31240, 0x31240,
-		0x31600, 0x31600,
-		0x31608, 0x3160c,
+		0x31600, 0x3160c,
 		0x31a00, 0x31a1c,
-		0x31e04, 0x31e20,
+		0x31e00, 0x31e20,
 		0x31e38, 0x31e3c,
 		0x31e80, 0x31e80,
 		0x31e88, 0x31ea8,
 		0x31eb0, 0x31eb4,
 		0x31ec8, 0x31ed4,
 		0x31fb8, 0x32004,
-		0x32208, 0x3223c,
+		0x32200, 0x32200,
+		0x32208, 0x32240,
+		0x32248, 0x32280,
+		0x32288, 0x322c0,
+		0x322c8, 0x322fc,
 		0x32600, 0x32630,
 		0x32a00, 0x32abc,
 		0x32b00, 0x32b70,
@@ -1074,27 +1077,30 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x34800, 0x34834,
 		0x348c0, 0x34908,
 		0x34910, 0x349ac,
-		0x34a00, 0x34a04,
-		0x34a0c, 0x34a2c,
+		0x34a00, 0x34a2c,
 		0x34a44, 0x34a50,
 		0x34a74, 0x34c24,
+		0x34d00, 0x34d00,
 		0x34d08, 0x34d14,
 		0x34d1c, 0x34d20,
 		0x34d3c, 0x34d50,
 		0x35200, 0x3520c,
 		0x35220, 0x35220,
 		0x35240, 0x35240,
-		0x35600, 0x35600,
-		0x35608, 0x3560c,
+		0x35600, 0x3560c,
 		0x35a00, 0x35a1c,
-		0x35e04, 0x35e20,
+		0x35e00, 0x35e20,
 		0x35e38, 0x35e3c,
 		0x35e80, 0x35e80,
 		0x35e88, 0x35ea8,
 		0x35eb0, 0x35eb4,
 		0x35ec8, 0x35ed4,
 		0x35fb8, 0x36004,
-		0x36208, 0x3623c,
+		0x36200, 0x36200,
+		0x36208, 0x36240,
+		0x36248, 0x36280,
+		0x36288, 0x362c0,
+		0x362c8, 0x362fc,
 		0x36600, 0x36630,
 		0x36a00, 0x36abc,
 		0x36b00, 0x36b70,
@@ -1134,27 +1140,30 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x38800, 0x38834,
 		0x388c0, 0x38908,
 		0x38910, 0x389ac,
-		0x38a00, 0x38a04,
-		0x38a0c, 0x38a2c,
+		0x38a00, 0x38a2c,
 		0x38a44, 0x38a50,
 		0x38a74, 0x38c24,
+		0x38d00, 0x38d00,
 		0x38d08, 0x38d14,
 		0x38d1c, 0x38d20,
 		0x38d3c, 0x38d50,
 		0x39200, 0x3920c,
 		0x39220, 0x39220,
 		0x39240, 0x39240,
-		0x39600, 0x39600,
-		0x39608, 0x3960c,
+		0x39600, 0x3960c,
 		0x39a00, 0x39a1c,
-		0x39e04, 0x39e20,
+		0x39e00, 0x39e20,
 		0x39e38, 0x39e3c,
 		0x39e80, 0x39e80,
 		0x39e88, 0x39ea8,
 		0x39eb0, 0x39eb4,
 		0x39ec8, 0x39ed4,
 		0x39fb8, 0x3a004,
-		0x3a208, 0x3a23c,
+		0x3a200, 0x3a200,
+		0x3a208, 0x3a240,
+		0x3a248, 0x3a280,
+		0x3a288, 0x3a2c0,
+		0x3a2c8, 0x3a2fc,
 		0x3a600, 0x3a630,
 		0x3aa00, 0x3aabc,
 		0x3ab00, 0x3ab70,
@@ -1194,27 +1203,30 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x3c800, 0x3c834,
 		0x3c8c0, 0x3c908,
 		0x3c910, 0x3c9ac,
-		0x3ca00, 0x3ca04,
-		0x3ca0c, 0x3ca2c,
+		0x3ca00, 0x3ca2c,
 		0x3ca44, 0x3ca50,
 		0x3ca74, 0x3cc24,
+		0x3cd00, 0x3cd00,
 		0x3cd08, 0x3cd14,
 		0x3cd1c, 0x3cd20,
 		0x3cd3c, 0x3cd50,
 		0x3d200, 0x3d20c,
 		0x3d220, 0x3d220,
 		0x3d240, 0x3d240,
-		0x3d600, 0x3d600,
-		0x3d608, 0x3d60c,
+		0x3d600, 0x3d60c,
 		0x3da00, 0x3da1c,
-		0x3de04, 0x3de20,
+		0x3de00, 0x3de20,
 		0x3de38, 0x3de3c,
 		0x3de80, 0x3de80,
 		0x3de88, 0x3dea8,
 		0x3deb0, 0x3deb4,
 		0x3dec8, 0x3ded4,
 		0x3dfb8, 0x3e004,
-		0x3e208, 0x3e23c,
+		0x3e200, 0x3e200,
+		0x3e208, 0x3e240,
+		0x3e248, 0x3e280,
+		0x3e288, 0x3e2c0,
+		0x3e2c8, 0x3e2fc,
 		0x3e600, 0x3e630,
 		0x3ea00, 0x3eabc,
 		0x3eb00, 0x3eb70,
@@ -1247,7 +1259,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x3fcf0, 0x3fcfc,
 		0x40000, 0x4000c,
 		0x40040, 0x40068,
-		0x40080, 0x40144,
+		0x4007c, 0x40144,
 		0x40180, 0x4018c,
 		0x40200, 0x40298,
 		0x402ac, 0x4033c,
@@ -1275,7 +1287,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x47800, 0x47814,
 		0x48000, 0x4800c,
 		0x48040, 0x48068,
-		0x48080, 0x48144,
+		0x4807c, 0x48144,
 		0x48180, 0x4818c,
 		0x48200, 0x48298,
 		0x482ac, 0x4833c,
@@ -1309,6 +1321,344 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		0x51300, 0x51308,
 	};
 
+	static const unsigned int t6_reg_ranges[] = {
+		0x1008, 0x114c,
+		0x1180, 0x11b4,
+		0x11fc, 0x1250,
+		0x1280, 0x133c,
+		0x1800, 0x18fc,
+		0x3000, 0x302c,
+		0x3060, 0x30d8,
+		0x30e0, 0x30fc,
+		0x3140, 0x357c,
+		0x35a8, 0x35cc,
+		0x35ec, 0x35ec,
+		0x3600, 0x5624,
+		0x56cc, 0x575c,
+		0x580c, 0x5814,
+		0x5890, 0x58bc,
+		0x5940, 0x595c,
+		0x5980, 0x598c,
+		0x59b0, 0x59dc,
+		0x59fc, 0x5a18,
+		0x5a60, 0x5a6c,
+		0x5a80, 0x5a9c,
+		0x5b94, 0x5bfc,
+		0x5c10, 0x5ec0,
+		0x5ec8, 0x5ec8,
+		0x6000, 0x6040,
+		0x6058, 0x6154,
+		0x7700, 0x7798,
+		0x77c0, 0x7880,
+		0x78cc, 0x78fc,
+		0x7b00, 0x7c54,
+		0x7d00, 0x7efc,
+		0x8dc0, 0x8de0,
+		0x8df8, 0x8e84,
+		0x8ea0, 0x8f88,
+		0x8fb8, 0x911c,
+		0x9400, 0x9470,
+		0x9600, 0x971c,
+		0x9800, 0x9808,
+		0x9820, 0x983c,
+		0x9850, 0x9864,
+		0x9c00, 0x9c6c,
+		0x9c80, 0x9cec,
+		0x9d00, 0x9d6c,
+		0x9d80, 0x9dec,
+		0x9e00, 0x9e6c,
+		0x9e80, 0x9eec,
+		0x9f00, 0x9f6c,
+		0x9f80, 0xa020,
+		0xd004, 0xd03c,
+		0xdfc0, 0xdfe0,
+		0xe000, 0xf008,
+		0x11000, 0x11014,
+		0x11048, 0x11110,
+		0x11118, 0x1117c,
+		0x11190, 0x11260,
+		0x11300, 0x1130c,
+		0x12000, 0x1205c,
+		0x19040, 0x1906c,
+		0x19078, 0x19080,
+		0x1908c, 0x19124,
+		0x19150, 0x191b0,
+		0x191d0, 0x191e8,
+		0x19238, 0x192b8,
+		0x193f8, 0x19474,
+		0x19490, 0x194cc,
+		0x194f0, 0x194f8,
+		0x19c00, 0x19c80,
+		0x19c94, 0x19cbc,
+		0x19ce4, 0x19d28,
+		0x19d50, 0x19d78,
+		0x19d94, 0x19dc8,
+		0x19df0, 0x19e10,
+		0x19e50, 0x19e6c,
+		0x19ea0, 0x19f34,
+		0x19f40, 0x19f50,
+		0x19f90, 0x19fac,
+		0x19fc4, 0x19fe4,
+		0x1a000, 0x1a06c,
+		0x1a0b0, 0x1a120,
+		0x1a128, 0x1a138,
+		0x1a190, 0x1a1c4,
+		0x1a1fc, 0x1a1fc,
+		0x1e008, 0x1e00c,
+		0x1e040, 0x1e04c,
+		0x1e284, 0x1e290,
+		0x1e2c0, 0x1e2c0,
+		0x1e2e0, 0x1e2e0,
+		0x1e300, 0x1e384,
+		0x1e3c0, 0x1e3c8,
+		0x1e408, 0x1e40c,
+		0x1e440, 0x1e44c,
+		0x1e684, 0x1e690,
+		0x1e6c0, 0x1e6c0,
+		0x1e6e0, 0x1e6e0,
+		0x1e700, 0x1e784,
+		0x1e7c0, 0x1e7c8,
+		0x1e808, 0x1e80c,
+		0x1e840, 0x1e84c,
+		0x1ea84, 0x1ea90,
+		0x1eac0, 0x1eac0,
+		0x1eae0, 0x1eae0,
+		0x1eb00, 0x1eb84,
+		0x1ebc0, 0x1ebc8,
+		0x1ec08, 0x1ec0c,
+		0x1ec40, 0x1ec4c,
+		0x1ee84, 0x1ee90,
+		0x1eec0, 0x1eec0,
+		0x1eee0, 0x1eee0,
+		0x1ef00, 0x1ef84,
+		0x1efc0, 0x1efc8,
+		0x1f008, 0x1f00c,
+		0x1f040, 0x1f04c,
+		0x1f284, 0x1f290,
+		0x1f2c0, 0x1f2c0,
+		0x1f2e0, 0x1f2e0,
+		0x1f300, 0x1f384,
+		0x1f3c0, 0x1f3c8,
+		0x1f408, 0x1f40c,
+		0x1f440, 0x1f44c,
+		0x1f684, 0x1f690,
+		0x1f6c0, 0x1f6c0,
+		0x1f6e0, 0x1f6e0,
+		0x1f700, 0x1f784,
+		0x1f7c0, 0x1f7c8,
+		0x1f808, 0x1f80c,
+		0x1f840, 0x1f84c,
+		0x1fa84, 0x1fa90,
+		0x1fac0, 0x1fac0,
+		0x1fae0, 0x1fae0,
+		0x1fb00, 0x1fb84,
+		0x1fbc0, 0x1fbc8,
+		0x1fc08, 0x1fc0c,
+		0x1fc40, 0x1fc4c,
+		0x1fe84, 0x1fe90,
+		0x1fec0, 0x1fec0,
+		0x1fee0, 0x1fee0,
+		0x1ff00, 0x1ff84,
+		0x1ffc0, 0x1ffc8,
+		0x30000, 0x30070,
+		0x30100, 0x3015c,
+		0x30190, 0x301d0,
+		0x30200, 0x30318,
+		0x30400, 0x3052c,
+		0x30540, 0x3061c,
+		0x30800, 0x3088c,
+		0x308c0, 0x30908,
+		0x30910, 0x309b8,
+		0x30a00, 0x30a04,
+		0x30a0c, 0x30a2c,
+		0x30a44, 0x30a50,
+		0x30a74, 0x30c24,
+		0x30d00, 0x30d3c,
+		0x30d44, 0x30d7c,
+		0x30de0, 0x30de0,
+		0x30e00, 0x30ed4,
+		0x30f00, 0x30fa4,
+		0x30fc0, 0x30fc4,
+		0x31000, 0x31004,
+		0x31080, 0x310fc,
+		0x31208, 0x31220,
+		0x3123c, 0x31254,
+		0x31300, 0x31300,
+		0x31308, 0x3131c,
+		0x31338, 0x3133c,
+		0x31380, 0x31380,
+		0x31388, 0x313a8,
+		0x313b4, 0x313b4,
+		0x31400, 0x31420,
+		0x31438, 0x3143c,
+		0x31480, 0x31480,
+		0x314a8, 0x314a8,
+		0x314b0, 0x314b4,
+		0x314c8, 0x314d4,
+		0x31a40, 0x31a4c,
+		0x31af0, 0x31b20,
+		0x31b38, 0x31b3c,
+		0x31b80, 0x31b80,
+		0x31ba8, 0x31ba8,
+		0x31bb0, 0x31bb4,
+		0x31bc8, 0x31bd4,
+		0x32140, 0x3218c,
+		0x321f0, 0x32200,
+		0x32218, 0x32218,
+		0x32400, 0x32400,
+		0x32408, 0x3241c,
+		0x32618, 0x32620,
+		0x32664, 0x32664,
+		0x326a8, 0x326a8,
+		0x326ec, 0x326ec,
+		0x32a00, 0x32abc,
+		0x32b00, 0x32b78,
+		0x32c00, 0x32c00,
+		0x32c08, 0x32c3c,
+		0x32e00, 0x32e2c,
+		0x32f00, 0x32f2c,
+		0x33000, 0x330ac,
+		0x330c0, 0x331ac,
+		0x331c0, 0x332c4,
+		0x332e4, 0x333c4,
+		0x333e4, 0x334ac,
+		0x334c0, 0x335ac,
+		0x335c0, 0x336c4,
+		0x336e4, 0x337c4,
+		0x337e4, 0x337fc,
+		0x33814, 0x33814,
+		0x33854, 0x33868,
+		0x33880, 0x3388c,
+		0x338c0, 0x338d0,
+		0x338e8, 0x338ec,
+		0x33900, 0x339ac,
+		0x339c0, 0x33ac4,
+		0x33ae4, 0x33b10,
+		0x33b24, 0x33b50,
+		0x33bf0, 0x33c10,
+		0x33c24, 0x33c50,
+		0x33cf0, 0x33cfc,
+		0x34000, 0x34070,
+		0x34100, 0x3415c,
+		0x34190, 0x341d0,
+		0x34200, 0x34318,
+		0x34400, 0x3452c,
+		0x34540, 0x3461c,
+		0x34800, 0x3488c,
+		0x348c0, 0x34908,
+		0x34910, 0x349b8,
+		0x34a00, 0x34a04,
+		0x34a0c, 0x34a2c,
+		0x34a44, 0x34a50,
+		0x34a74, 0x34c24,
+		0x34d00, 0x34d3c,
+		0x34d44, 0x34d7c,
+		0x34de0, 0x34de0,
+		0x34e00, 0x34ed4,
+		0x34f00, 0x34fa4,
+		0x34fc0, 0x34fc4,
+		0x35000, 0x35004,
+		0x35080, 0x350fc,
+		0x35208, 0x35220,
+		0x3523c, 0x35254,
+		0x35300, 0x35300,
+		0x35308, 0x3531c,
+		0x35338, 0x3533c,
+		0x35380, 0x35380,
+		0x35388, 0x353a8,
+		0x353b4, 0x353b4,
+		0x35400, 0x35420,
+		0x35438, 0x3543c,
+		0x35480, 0x35480,
+		0x354a8, 0x354a8,
+		0x354b0, 0x354b4,
+		0x354c8, 0x354d4,
+		0x35a40, 0x35a4c,
+		0x35af0, 0x35b20,
+		0x35b38, 0x35b3c,
+		0x35b80, 0x35b80,
+		0x35ba8, 0x35ba8,
+		0x35bb0, 0x35bb4,
+		0x35bc8, 0x35bd4,
+		0x36140, 0x3618c,
+		0x361f0, 0x36200,
+		0x36218, 0x36218,
+		0x36400, 0x36400,
+		0x36408, 0x3641c,
+		0x36618, 0x36620,
+		0x36664, 0x36664,
+		0x366a8, 0x366a8,
+		0x366ec, 0x366ec,
+		0x36a00, 0x36abc,
+		0x36b00, 0x36b78,
+		0x36c00, 0x36c00,
+		0x36c08, 0x36c3c,
+		0x36e00, 0x36e2c,
+		0x36f00, 0x36f2c,
+		0x37000, 0x370ac,
+		0x370c0, 0x371ac,
+		0x371c0, 0x372c4,
+		0x372e4, 0x373c4,
+		0x373e4, 0x374ac,
+		0x374c0, 0x375ac,
+		0x375c0, 0x376c4,
+		0x376e4, 0x377c4,
+		0x377e4, 0x377fc,
+		0x37814, 0x37814,
+		0x37854, 0x37868,
+		0x37880, 0x3788c,
+		0x378c0, 0x378d0,
+		0x378e8, 0x378ec,
+		0x37900, 0x379ac,
+		0x379c0, 0x37ac4,
+		0x37ae4, 0x37b10,
+		0x37b24, 0x37b50,
+		0x37bf0, 0x37c10,
+		0x37c24, 0x37c50,
+		0x37cf0, 0x37cfc,
+		0x40040, 0x40040,
+		0x40080, 0x40084,
+		0x40100, 0x40100,
+		0x40140, 0x401bc,
+		0x40200, 0x40214,
+		0x40228, 0x40228,
+		0x40240, 0x40258,
+		0x40280, 0x40280,
+		0x40304, 0x40304,
+		0x40330, 0x4033c,
+		0x41304, 0x413dc,
+		0x41400, 0x4141c,
+		0x41480, 0x414d0,
+		0x44000, 0x4407c,
+		0x440c0, 0x4427c,
+		0x442c0, 0x4447c,
+		0x444c0, 0x4467c,
+		0x446c0, 0x4487c,
+		0x448c0, 0x44a7c,
+		0x44ac0, 0x44c7c,
+		0x44cc0, 0x44e7c,
+		0x44ec0, 0x4507c,
+		0x450c0, 0x451fc,
+		0x45800, 0x45868,
+		0x45880, 0x45884,
+		0x458a0, 0x458b0,
+		0x45a00, 0x45a68,
+		0x45a80, 0x45a84,
+		0x45aa0, 0x45ab0,
+		0x460c0, 0x460e4,
+		0x47000, 0x4708c,
+		0x47200, 0x47250,
+		0x47400, 0x47420,
+		0x47600, 0x47618,
+		0x47800, 0x4782c,
+		0x50000, 0x500cc,
+		0x50400, 0x50400,
+		0x50800, 0x508cc,
+		0x50c00, 0x50c00,
+		0x51000, 0x510b0,
+		0x51300, 0x51324,
+	};
+
 	u32 *buf_end = (u32 *)((char *)buf + buf_size);
 	const unsigned int *reg_ranges;
 	int reg_ranges_size, range;
@@ -1328,6 +1678,11 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size)
 		reg_ranges_size = ARRAY_SIZE(t5_reg_ranges);
 		break;
 
+	case CHELSIO_T6:
+		reg_ranges = t6_reg_ranges;
+		reg_ranges_size = ARRAY_SIZE(t6_reg_ranges);
+		break;
+
 	default:
 		dev_err(adap->pdev_dev,
 			"Unsupported chip version %d\n", chip_version);
@@ -1374,17 +1729,16 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable)
 }
 
 /**
- *	get_vpd_params - read VPD parameters from VPD EEPROM
+ *	t4_get_raw_vpd_params - read VPD parameters from VPD EEPROM
  *	@adapter: adapter to read
  *	@p: where to store the parameters
  *
  *	Reads card parameters stored in VPD EEPROM.
  */
-int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
+int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p)
 {
-	u32 cclk_param, cclk_val;
-	int i, ret, addr;
-	int ec, sn, pn;
+	int i, ret = 0, addr;
+	int ec, sn, pn, na;
 	u8 *vpd, csum;
 	unsigned int vpdr_len, kw_offset, id_len;
 
@@ -1392,6 +1746,9 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	if (!vpd)
 		return -ENOMEM;
 
+	/* Card information normally starts at VPD_BASE but early cards had
+	 * it at 0.
+	 */
 	ret = pci_read_vpd(adapter->pdev, VPD_BASE, sizeof(u32), vpd);
 	if (ret < 0)
 		goto out;
@@ -1457,6 +1814,7 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	FIND_VPD_KW(ec, "EC");
 	FIND_VPD_KW(sn, "SN");
 	FIND_VPD_KW(pn, "PN");
+	FIND_VPD_KW(na, "NA");
 #undef FIND_VPD_KW
 
 	memcpy(p->id, vpd + PCI_VPD_LRDT_TAG_SIZE, id_len);
@@ -1469,18 +1827,42 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	i = pci_vpd_info_field_size(vpd + pn - PCI_VPD_INFO_FLD_HDR_SIZE);
 	memcpy(p->pn, vpd + pn, min(i, PN_LEN));
 	strim(p->pn);
+	memcpy(p->na, vpd + na, min(i, MACADDR_LEN));
+	strim((char *)p->na);
 
-	/*
-	 * Ask firmware for the Core Clock since it knows how to translate the
+out:
+	vfree(vpd);
+	return ret;
+}
+
+/**
+ *	t4_get_vpd_params - read VPD parameters & retrieve Core Clock
+ *	@adapter: adapter to read
+ *	@p: where to store the parameters
+ *
+ *	Reads card parameters stored in VPD EEPROM and retrieves the Core
+ *	Clock.  This can only be called after a connection to the firmware
+ *	is established.
+ */
+int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p)
+{
+	u32 cclk_param, cclk_val;
+	int ret;
+
+	/* Grab the raw VPD parameters.
+	 */
+	ret = t4_get_raw_vpd_params(adapter, p);
+	if (ret)
+		return ret;
+
+	/* Ask firmware for the Core Clock since it knows how to translate the
 	 * Reference Clock ('V2') VPD field into a Core Clock value ...
 	 */
 	cclk_param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
 		      FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_CCLK));
-	ret = t4_query_params(adapter, adapter->mbox, 0, 0,
+	ret = t4_query_params(adapter, adapter->mbox, adapter->pf, 0,
 			      1, &cclk_param, &cclk_val);
 
-out:
-	vfree(vpd);
 	if (ret)
 		return ret;
 	p->cclk = cclk_val;
@@ -1618,7 +2000,7 @@ int t4_read_flash(struct adapter *adapter, unsigned int addr,
 		if (ret)
 			return ret;
 		if (byte_oriented)
-			*data = (__force __u32) (htonl(*data));
+			*data = (__force __u32)(cpu_to_be32(*data));
 	}
 	return 0;
 }
@@ -1941,7 +2323,8 @@ static bool t4_fw_matches_chip(const struct adapter *adap,
 	 * which will keep us "honest" in the future ...
 	 */
 	if ((is_t4(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T4) ||
-	    (is_t5(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T5))
+	    (is_t5(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T5) ||
+	    (is_t6(adap->params.chip) && hdr->chip == FW_HDR_CHIP_T6))
 		return true;
 
 	dev_err(adap->pdev_dev,
@@ -1979,7 +2362,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size)
 			"FW image size not multiple of 512 bytes\n");
 		return -EINVAL;
 	}
-	if (ntohs(hdr->len512) * 512 != size) {
+	if ((unsigned int)be16_to_cpu(hdr->len512) * 512 != size) {
 		dev_err(adap->pdev_dev,
 			"FW image size differs from size in FW header\n");
 		return -EINVAL;
@@ -1993,7 +2376,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size)
 		return -EINVAL;
 
 	for (csum = 0, i = 0; i < size / sizeof(csum); i++)
-		csum += ntohl(p[i]);
+		csum += be32_to_cpu(p[i]);
 
 	if (csum != 0xffffffff) {
 		dev_err(adap->pdev_dev,
@@ -2012,7 +2395,7 @@ int t4_load_fw(struct adapter *adap, const u8 *fw_data, unsigned int size)
 	 * first page with a bad version.
 	 */
 	memcpy(first_page, fw_data, SF_PAGE_SIZE);
-	((struct fw_hdr *)first_page)->fw_ver = htonl(0xffffffff);
+	((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff);
 	ret = t4_write_flash(adap, fw_img_start, SF_PAGE_SIZE, first_page);
 	if (ret)
 		goto out;
@@ -2039,6 +2422,147 @@ out:
 }
 
 /**
+ *	t4_phy_fw_ver - return current PHY firmware version
+ *	@adap: the adapter
+ *	@phy_fw_ver: return value buffer for PHY firmware version
+ *
+ *	Returns the current version of external PHY firmware on the
+ *	adapter.
+ */
+int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver)
+{
+	u32 param, val;
+	int ret;
+
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PHYFW) |
+		 FW_PARAMS_PARAM_Y_V(adap->params.portvec) |
+		 FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_VERSION));
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1,
+			      &param, &val);
+	if (ret < 0)
+		return ret;
+	*phy_fw_ver = val;
+	return 0;
+}
+
+/**
+ *	t4_load_phy_fw - download port PHY firmware
+ *	@adap: the adapter
+ *	@win: the PCI-E Memory Window index to use for t4_memory_rw()
+ *	@win_lock: the lock to use to guard the memory copy
+ *	@phy_fw_version: function to check PHY firmware versions
+ *	@phy_fw_data: the PHY firmware image to write
+ *	@phy_fw_size: image size
+ *
+ *	Transfer the specified PHY firmware to the adapter.  If a non-NULL
+ *	@phy_fw_version is supplied, then it will be used to determine if
+ *	it's necessary to perform the transfer by comparing the version
+ *	of any existing adapter PHY firmware with that of the passed in
+ *	PHY firmware image.  If @win_lock is non-NULL then it will be used
+ *	around the call to t4_memory_rw() which transfers the PHY firmware
+ *	to the adapter.
+ *
+ *	A negative error number will be returned if an error occurs.  If
+ *	version number support is available and there's no need to upgrade
+ *	the firmware, 0 will be returned.  If firmware is successfully
+ *	transferred to the adapter, 1 will be retured.
+ *
+ *	NOTE: some adapters only have local RAM to store the PHY firmware.  As
+ *	a result, a RESET of the adapter would cause that RAM to lose its
+ *	contents.  Thus, loading PHY firmware on such adapters must happen
+ *	after any FW_RESET_CMDs ...
+ */
+int t4_load_phy_fw(struct adapter *adap,
+		   int win, spinlock_t *win_lock,
+		   int (*phy_fw_version)(const u8 *, size_t),
+		   const u8 *phy_fw_data, size_t phy_fw_size)
+{
+	unsigned long mtype = 0, maddr = 0;
+	u32 param, val;
+	int cur_phy_fw_ver = 0, new_phy_fw_vers = 0;
+	int ret;
+
+	/* If we have version number support, then check to see if the adapter
+	 * already has up-to-date PHY firmware loaded.
+	 */
+	 if (phy_fw_version) {
+		new_phy_fw_vers = phy_fw_version(phy_fw_data, phy_fw_size);
+		ret = t4_phy_fw_ver(adap, &cur_phy_fw_ver);
+		if (ret < 0)
+			return ret;
+
+		if (cur_phy_fw_ver >= new_phy_fw_vers) {
+			CH_WARN(adap, "PHY Firmware already up-to-date, "
+				"version %#x\n", cur_phy_fw_ver);
+			return 0;
+		}
+	}
+
+	/* Ask the firmware where it wants us to copy the PHY firmware image.
+	 * The size of the file requires a special version of the READ coommand
+	 * which will pass the file size via the values field in PARAMS_CMD and
+	 * retrieve the return value from firmware and place it in the same
+	 * buffer values
+	 */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PHYFW) |
+		 FW_PARAMS_PARAM_Y_V(adap->params.portvec) |
+		 FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD));
+	val = phy_fw_size;
+	ret = t4_query_params_rw(adap, adap->mbox, adap->pf, 0, 1,
+				 &param, &val, 1);
+	if (ret < 0)
+		return ret;
+	mtype = val >> 8;
+	maddr = (val & 0xff) << 16;
+
+	/* Copy the supplied PHY Firmware image to the adapter memory location
+	 * allocated by the adapter firmware.
+	 */
+	if (win_lock)
+		spin_lock_bh(win_lock);
+	ret = t4_memory_rw(adap, win, mtype, maddr,
+			   phy_fw_size, (__be32 *)phy_fw_data,
+			   T4_MEMORY_WRITE);
+	if (win_lock)
+		spin_unlock_bh(win_lock);
+	if (ret)
+		return ret;
+
+	/* Tell the firmware that the PHY firmware image has been written to
+	 * RAM and it can now start copying it over to the PHYs.  The chip
+	 * firmware will RESET the affected PHYs as part of this operation
+	 * leaving them running the new PHY firmware image.
+	 */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PHYFW) |
+		 FW_PARAMS_PARAM_Y_V(adap->params.portvec) |
+		 FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD));
+	ret = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1,
+				    &param, &val, 30000);
+
+	/* If we have version number support, then check to see that the new
+	 * firmware got loaded properly.
+	 */
+	if (phy_fw_version) {
+		ret = t4_phy_fw_ver(adap, &cur_phy_fw_ver);
+		if (ret < 0)
+			return ret;
+
+		if (cur_phy_fw_ver != new_phy_fw_vers) {
+			CH_WARN(adap, "PHY Firmware did not update: "
+				"version on adapter %#x, "
+				"version flashed %#x\n",
+				cur_phy_fw_ver, new_phy_fw_vers);
+			return -ENXIO;
+		}
+	}
+
+	return 1;
+}
+
+/**
  *	t4_fwcache - firmware cache operation
  *	@adap: the adapter
  *	@op  : the operation (flush or flush and invalidate)
@@ -2051,7 +2575,7 @@ int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op)
 	c.op_to_vfn =
 		cpu_to_be32(FW_CMD_OP_V(FW_PARAMS_CMD) |
 			    FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
-			    FW_PARAMS_CMD_PFN_V(adap->fn) |
+			    FW_PARAMS_CMD_PFN_V(adap->pf) |
 			    FW_PARAMS_CMD_VFN_V(0));
 	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
 	c.param[0].mnem =
@@ -2062,6 +2586,61 @@ int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op)
 	return t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), NULL);
 }
 
+void t4_cim_read_pif_la(struct adapter *adap, u32 *pif_req, u32 *pif_rsp,
+			unsigned int *pif_req_wrptr,
+			unsigned int *pif_rsp_wrptr)
+{
+	int i, j;
+	u32 cfg, val, req, rsp;
+
+	cfg = t4_read_reg(adap, CIM_DEBUGCFG_A);
+	if (cfg & LADBGEN_F)
+		t4_write_reg(adap, CIM_DEBUGCFG_A, cfg ^ LADBGEN_F);
+
+	val = t4_read_reg(adap, CIM_DEBUGSTS_A);
+	req = POLADBGWRPTR_G(val);
+	rsp = PILADBGWRPTR_G(val);
+	if (pif_req_wrptr)
+		*pif_req_wrptr = req;
+	if (pif_rsp_wrptr)
+		*pif_rsp_wrptr = rsp;
+
+	for (i = 0; i < CIM_PIFLA_SIZE; i++) {
+		for (j = 0; j < 6; j++) {
+			t4_write_reg(adap, CIM_DEBUGCFG_A, POLADBGRDPTR_V(req) |
+				     PILADBGRDPTR_V(rsp));
+			*pif_req++ = t4_read_reg(adap, CIM_PO_LA_DEBUGDATA_A);
+			*pif_rsp++ = t4_read_reg(adap, CIM_PI_LA_DEBUGDATA_A);
+			req++;
+			rsp++;
+		}
+		req = (req + 2) & POLADBGRDPTR_M;
+		rsp = (rsp + 2) & PILADBGRDPTR_M;
+	}
+	t4_write_reg(adap, CIM_DEBUGCFG_A, cfg);
+}
+
+void t4_cim_read_ma_la(struct adapter *adap, u32 *ma_req, u32 *ma_rsp)
+{
+	u32 cfg;
+	int i, j, idx;
+
+	cfg = t4_read_reg(adap, CIM_DEBUGCFG_A);
+	if (cfg & LADBGEN_F)
+		t4_write_reg(adap, CIM_DEBUGCFG_A, cfg ^ LADBGEN_F);
+
+	for (i = 0; i < CIM_MALA_SIZE; i++) {
+		for (j = 0; j < 5; j++) {
+			idx = 8 * i + j;
+			t4_write_reg(adap, CIM_DEBUGCFG_A, POLADBGRDPTR_V(idx) |
+				     PILADBGRDPTR_V(idx));
+			*ma_req++ = t4_read_reg(adap, CIM_PO_LA_MADEBUGDATA_A);
+			*ma_rsp++ = t4_read_reg(adap, CIM_PI_LA_MADEBUGDATA_A);
+		}
+	}
+	t4_write_reg(adap, CIM_DEBUGCFG_A, cfg);
+}
+
 void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf)
 {
 	unsigned int i, j;
@@ -2082,7 +2661,7 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf)
 		     FW_PORT_CAP_ANEG)
 
 /**
- *	t4_link_start - apply link configuration to MAC/PHY
+ *	t4_link_l1cfg - apply link configuration to MAC/PHY
  *	@phy: the PHY to setup
  *	@mac: the MAC to setup
  *	@lc: the requested link configuration
@@ -2094,7 +2673,7 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf)
  *	- If auto-negotiation is off set the MAC to the proper speed/duplex/FC,
  *	  otherwise do it later based on the outcome of auto-negotiation.
  */
-int t4_link_start(struct adapter *adap, unsigned int mbox, unsigned int port,
+int t4_link_l1cfg(struct adapter *adap, unsigned int mbox, unsigned int port,
 		  struct link_config *lc)
 {
 	struct fw_port_cmd c;
@@ -2107,19 +2686,22 @@ int t4_link_start(struct adapter *adap, unsigned int mbox, unsigned int port,
 		fc |= FW_PORT_CAP_FC_TX;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_portid = htonl(FW_CMD_OP_V(FW_PORT_CMD) | FW_CMD_REQUEST_F |
-			       FW_CMD_EXEC_F | FW_PORT_CMD_PORTID_V(port));
-	c.action_to_len16 = htonl(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) |
-				  FW_LEN16(c));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) |
+				     FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				     FW_PORT_CMD_PORTID_V(port));
+	c.action_to_len16 =
+		cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) |
+			    FW_LEN16(c));
 
 	if (!(lc->supported & FW_PORT_CAP_ANEG)) {
-		c.u.l1cfg.rcap = htonl((lc->supported & ADVERT_MASK) | fc);
+		c.u.l1cfg.rcap = cpu_to_be32((lc->supported & ADVERT_MASK) |
+					     fc);
 		lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX);
 	} else if (lc->autoneg == AUTONEG_DISABLE) {
-		c.u.l1cfg.rcap = htonl(lc->requested_speed | fc | mdi);
+		c.u.l1cfg.rcap = cpu_to_be32(lc->requested_speed | fc | mdi);
 		lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX);
 	} else
-		c.u.l1cfg.rcap = htonl(lc->advertising | fc | mdi);
+		c.u.l1cfg.rcap = cpu_to_be32(lc->advertising | fc | mdi);
 
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
@@ -2137,11 +2719,13 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port)
 	struct fw_port_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_portid = htonl(FW_CMD_OP_V(FW_PORT_CMD) | FW_CMD_REQUEST_F |
-			       FW_CMD_EXEC_F | FW_PORT_CMD_PORTID_V(port));
-	c.action_to_len16 = htonl(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) |
-				  FW_LEN16(c));
-	c.u.l1cfg.rcap = htonl(FW_PORT_CAP_ANEG);
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) |
+				     FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				     FW_PORT_CMD_PORTID_V(port));
+	c.action_to_len16 =
+		cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) |
+			    FW_LEN16(c));
+	c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP_ANEG);
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -2335,6 +2919,7 @@ static void tp_intr_handler(struct adapter *adapter)
 static void sge_intr_handler(struct adapter *adapter)
 {
 	u64 v;
+	u32 err;
 
 	static const struct intr_info sge_intr_info[] = {
 		{ ERR_CPL_EXCEED_IQE_SIZE_F,
@@ -2343,8 +2928,6 @@ static void sge_intr_handler(struct adapter *adapter)
 		  "SGE GTS CIDX increment too large", -1, 0 },
 		{ ERR_CPL_OPCODE_0_F, "SGE received 0-length CPL", -1, 0 },
 		{ DBFIFO_LP_INT_F, NULL, -1, 0, t4_db_full },
-		{ DBFIFO_HP_INT_F, NULL, -1, 0, t4_db_full },
-		{ ERR_DROPPED_DB_F, NULL, -1, 0, t4_db_dropped },
 		{ ERR_DATA_CPL_ON_HIGH_QID1_F | ERR_DATA_CPL_ON_HIGH_QID0_F,
 		  "SGE IQID > 1023 received CPL for FL", -1, 0 },
 		{ ERR_BAD_DB_PIDX3_F, "SGE DBP 3 pidx increment too large", -1,
@@ -2357,13 +2940,19 @@ static void sge_intr_handler(struct adapter *adapter)
 		  0 },
 		{ ERR_ING_CTXT_PRIO_F,
 		  "SGE too many priority ingress contexts", -1, 0 },
-		{ ERR_EGR_CTXT_PRIO_F,
-		  "SGE too many priority egress contexts", -1, 0 },
 		{ INGRESS_SIZE_ERR_F, "SGE illegal ingress QID", -1, 0 },
 		{ EGRESS_SIZE_ERR_F, "SGE illegal egress QID", -1, 0 },
 		{ 0 }
 	};
 
+	static struct intr_info t4t5_sge_intr_info[] = {
+		{ ERR_DROPPED_DB_F, NULL, -1, 0, t4_db_dropped },
+		{ DBFIFO_HP_INT_F, NULL, -1, 0, t4_db_full },
+		{ ERR_EGR_CTXT_PRIO_F,
+		  "SGE too many priority egress contexts", -1, 0 },
+		{ 0 }
+	};
+
 	v = (u64)t4_read_reg(adapter, SGE_INT_CAUSE1_A) |
 		((u64)t4_read_reg(adapter, SGE_INT_CAUSE2_A) << 32);
 	if (v) {
@@ -2373,8 +2962,23 @@ static void sge_intr_handler(struct adapter *adapter)
 		t4_write_reg(adapter, SGE_INT_CAUSE2_A, v >> 32);
 	}
 
-	if (t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A, sge_intr_info) ||
-	    v != 0)
+	v |= t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A, sge_intr_info);
+	if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+		v |= t4_handle_intr_status(adapter, SGE_INT_CAUSE3_A,
+					   t4t5_sge_intr_info);
+
+	err = t4_read_reg(adapter, SGE_ERROR_STATS_A);
+	if (err & ERROR_QID_VALID_F) {
+		dev_err(adapter->pdev_dev, "SGE error for queue %u\n",
+			ERROR_QID_G(err));
+		if (err & UNCAPTURED_ERROR_F)
+			dev_err(adapter->pdev_dev,
+				"SGE UNCAPTURED_ERROR set (clearing)\n");
+		t4_write_reg(adapter, SGE_ERROR_STATS_A, ERROR_QID_VALID_F |
+			     UNCAPTURED_ERROR_F);
+	}
+
+	if (v != 0)
 		t4_fatal_err(adapter);
 }
 
@@ -2547,6 +3151,7 @@ static void cplsw_intr_handler(struct adapter *adapter)
  */
 static void le_intr_handler(struct adapter *adap)
 {
+	enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
 	static const struct intr_info le_intr_info[] = {
 		{ LIPMISS_F, "LE LIP miss", -1, 0 },
 		{ LIP0_F, "LE 0 LIP error", -1, 0 },
@@ -2556,7 +3161,18 @@ static void le_intr_handler(struct adapter *adap)
 		{ 0 }
 	};
 
-	if (t4_handle_intr_status(adap, LE_DB_INT_CAUSE_A, le_intr_info))
+	static struct intr_info t6_le_intr_info[] = {
+		{ T6_LIPMISS_F, "LE LIP miss", -1, 0 },
+		{ T6_LIP0_F, "LE 0 LIP error", -1, 0 },
+		{ TCAMINTPERR_F, "LE parity error", -1, 1 },
+		{ T6_UNKNOWNCMD_F, "LE unknown command", -1, 1 },
+		{ SSRAMINTPERR_F, "LE request queue parity error", -1, 1 },
+		{ 0 }
+	};
+
+	if (t4_handle_intr_status(adap, LE_DB_INT_CAUSE_A,
+				  (chip <= CHELSIO_T5) ?
+				  le_intr_info : t6_le_intr_info))
 		t4_fatal_err(adap);
 }
 
@@ -2825,7 +3441,7 @@ int t4_slow_intr_handler(struct adapter *adapter)
 		pcie_intr_handler(adapter);
 	if (cause & MC_F)
 		mem_intr_handler(adapter, MEM_MC);
-	if (!is_t4(adapter->params.chip) && (cause & MC1_S))
+	if (is_t5(adapter->params.chip) && (cause & MC1_F))
 		mem_intr_handler(adapter, MEM_MC1);
 	if (cause & EDC0_F)
 		mem_intr_handler(adapter, MEM_EDC0);
@@ -2871,17 +3487,18 @@ int t4_slow_intr_handler(struct adapter *adapter)
  */
 void t4_intr_enable(struct adapter *adapter)
 {
+	u32 val = 0;
 	u32 pf = SOURCEPF_G(t4_read_reg(adapter, PL_WHOAMI_A));
 
+	if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+		val = ERR_DROPPED_DB_F | ERR_EGR_CTXT_PRIO_F | DBFIFO_HP_INT_F;
 	t4_write_reg(adapter, SGE_INT_ENABLE3_A, ERR_CPL_EXCEED_IQE_SIZE_F |
 		     ERR_INVALID_CIDX_INC_F | ERR_CPL_OPCODE_0_F |
-		     ERR_DROPPED_DB_F | ERR_DATA_CPL_ON_HIGH_QID1_F |
+		     ERR_DATA_CPL_ON_HIGH_QID1_F | INGRESS_SIZE_ERR_F |
 		     ERR_DATA_CPL_ON_HIGH_QID0_F | ERR_BAD_DB_PIDX3_F |
 		     ERR_BAD_DB_PIDX2_F | ERR_BAD_DB_PIDX1_F |
 		     ERR_BAD_DB_PIDX0_F | ERR_ING_CTXT_PRIO_F |
-		     ERR_EGR_CTXT_PRIO_F | INGRESS_SIZE_ERR_F |
-		     DBFIFO_HP_INT_F | DBFIFO_LP_INT_F |
-		     EGRESS_SIZE_ERR_F);
+		     DBFIFO_LP_INT_F | EGRESS_SIZE_ERR_F | val);
 	t4_write_reg(adapter, MYPF_REG(PL_PF_INT_ENABLE_A), PF_INTR_MASK);
 	t4_set_reg_field(adapter, PL_INT_MAP0_A, 0, 1 << pf);
 }
@@ -2945,18 +3562,18 @@ int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid,
 	struct fw_rss_ind_tbl_cmd cmd;
 
 	memset(&cmd, 0, sizeof(cmd));
-	cmd.op_to_viid = htonl(FW_CMD_OP_V(FW_RSS_IND_TBL_CMD) |
+	cmd.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_RSS_IND_TBL_CMD) |
 			       FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
 			       FW_RSS_IND_TBL_CMD_VIID_V(viid));
-	cmd.retval_len16 = htonl(FW_LEN16(cmd));
+	cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
 
 	/* each fw_rss_ind_tbl_cmd takes up to 32 entries */
 	while (n > 0) {
 		int nq = min(n, 32);
 		__be32 *qp = &cmd.iq0_to_iq2;
 
-		cmd.niqid = htons(nq);
-		cmd.startidx = htons(start);
+		cmd.niqid = cpu_to_be16(nq);
+		cmd.startidx = cpu_to_be16(start);
 
 		start += nq;
 		n -= nq;
@@ -2974,7 +3591,7 @@ int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid,
 			if (++rsp >= rsp_end)
 				rsp = rspq;
 
-			*qp++ = htonl(v);
+			*qp++ = cpu_to_be32(v);
 			nq -= 3;
 		}
 
@@ -3000,20 +3617,46 @@ int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode,
 	struct fw_rss_glb_config_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_write = htonl(FW_CMD_OP_V(FW_RSS_GLB_CONFIG_CMD) |
-			      FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
-	c.retval_len16 = htonl(FW_LEN16(c));
+	c.op_to_write = cpu_to_be32(FW_CMD_OP_V(FW_RSS_GLB_CONFIG_CMD) |
+				    FW_CMD_REQUEST_F | FW_CMD_WRITE_F);
+	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
 	if (mode == FW_RSS_GLB_CONFIG_CMD_MODE_MANUAL) {
-		c.u.manual.mode_pkd = htonl(FW_RSS_GLB_CONFIG_CMD_MODE_V(mode));
+		c.u.manual.mode_pkd =
+			cpu_to_be32(FW_RSS_GLB_CONFIG_CMD_MODE_V(mode));
 	} else if (mode == FW_RSS_GLB_CONFIG_CMD_MODE_BASICVIRTUAL) {
 		c.u.basicvirtual.mode_pkd =
-			htonl(FW_RSS_GLB_CONFIG_CMD_MODE_V(mode));
-		c.u.basicvirtual.synmapen_to_hashtoeplitz = htonl(flags);
+			cpu_to_be32(FW_RSS_GLB_CONFIG_CMD_MODE_V(mode));
+		c.u.basicvirtual.synmapen_to_hashtoeplitz = cpu_to_be32(flags);
 	} else
 		return -EINVAL;
 	return t4_wr_mbox(adapter, mbox, &c, sizeof(c), NULL);
 }
 
+/**
+ *	t4_config_vi_rss - configure per VI RSS settings
+ *	@adapter: the adapter
+ *	@mbox: mbox to use for the FW command
+ *	@viid: the VI id
+ *	@flags: RSS flags
+ *	@defq: id of the default RSS queue for the VI.
+ *
+ *	Configures VI-specific RSS properties.
+ */
+int t4_config_vi_rss(struct adapter *adapter, int mbox, unsigned int viid,
+		     unsigned int flags, unsigned int defq)
+{
+	struct fw_rss_vi_config_cmd c;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_RSS_VI_CONFIG_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+				   FW_RSS_VI_CONFIG_CMD_VIID_V(viid));
+	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
+	c.u.basicvirtual.defaultq_to_udpen = cpu_to_be32(flags |
+					FW_RSS_VI_CONFIG_CMD_DEFAULTQ_V(defq));
+	return t4_wr_mbox(adapter, mbox, &c, sizeof(c), NULL);
+}
+
 /* Read an RSS table row */
 static int rd_rss_row(struct adapter *adap, int row, u32 *val)
 {
@@ -3045,6 +3688,40 @@ int t4_read_rss(struct adapter *adapter, u16 *map)
 }
 
 /**
+ *	t4_fw_tp_pio_rw - Access TP PIO through LDST
+ *	@adap: the adapter
+ *	@vals: where the indirect register values are stored/written
+ *	@nregs: how many indirect registers to read/write
+ *	@start_idx: index of first indirect register to read/write
+ *	@rw: Read (1) or Write (0)
+ *
+ *	Access TP PIO registers through LDST
+ */
+static void t4_fw_tp_pio_rw(struct adapter *adap, u32 *vals, unsigned int nregs,
+			    unsigned int start_index, unsigned int rw)
+{
+	int ret, i;
+	int cmd = FW_LDST_ADDRSPC_TP_PIO;
+	struct fw_ldst_cmd c;
+
+	for (i = 0 ; i < nregs; i++) {
+		memset(&c, 0, sizeof(c));
+		c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+						FW_CMD_REQUEST_F |
+						(rw ? FW_CMD_READ_F :
+						      FW_CMD_WRITE_F) |
+						FW_LDST_CMD_ADDRSPACE_V(cmd));
+		c.cycles_to_len16 = cpu_to_be32(FW_LEN16(c));
+
+		c.u.addrval.addr = cpu_to_be32(start_index + i);
+		c.u.addrval.val  = rw ? 0 : cpu_to_be32(vals[i]);
+		ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
+		if (!ret && rw)
+			vals[i] = be32_to_cpu(c.u.addrval.val);
+	}
+}
+
+/**
  *	t4_read_rss_key - read the global RSS key
  *	@adap: the adapter
  *	@key: 10-entry array holding the 320-bit RSS key
@@ -3053,8 +3730,11 @@ int t4_read_rss(struct adapter *adapter, u16 *map)
  */
 void t4_read_rss_key(struct adapter *adap, u32 *key)
 {
-	t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
-			 TP_RSS_SECRET_KEY0_A);
+	if (adap->flags & FW_OK)
+		t4_fw_tp_pio_rw(adap, key, 10, TP_RSS_SECRET_KEY0_A, 1);
+	else
+		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
+				 TP_RSS_SECRET_KEY0_A);
 }
 
 /**
@@ -3069,11 +3749,32 @@ void t4_read_rss_key(struct adapter *adap, u32 *key)
  */
 void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx)
 {
-	t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
-			  TP_RSS_SECRET_KEY0_A);
-	if (idx >= 0 && idx < 16)
-		t4_write_reg(adap, TP_RSS_CONFIG_VRT_A,
-			     KEYWRADDR_V(idx) | KEYWREN_F);
+	u8 rss_key_addr_cnt = 16;
+	u32 vrt = t4_read_reg(adap, TP_RSS_CONFIG_VRT_A);
+
+	/* T6 and later: for KeyMode 3 (per-vf and per-vf scramble),
+	 * allows access to key addresses 16-63 by using KeyWrAddrX
+	 * as index[5:4](upper 2) into key table
+	 */
+	if ((CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) &&
+	    (vrt & KEYEXTEND_F) && (KEYMODE_G(vrt) == 3))
+		rss_key_addr_cnt = 32;
+
+	if (adap->flags & FW_OK)
+		t4_fw_tp_pio_rw(adap, (void *)key, 10, TP_RSS_SECRET_KEY0_A, 0);
+	else
+		t4_write_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A, key, 10,
+				  TP_RSS_SECRET_KEY0_A);
+
+	if (idx >= 0 && idx < rss_key_addr_cnt) {
+		if (rss_key_addr_cnt > 16)
+			t4_write_reg(adap, TP_RSS_CONFIG_VRT_A,
+				     KEYWRADDRX_V(idx >> 4) |
+				     T6_VFWRADDR_V(idx) | KEYWREN_F);
+		else
+			t4_write_reg(adap, TP_RSS_CONFIG_VRT_A,
+				     KEYWRADDR_V(idx) | KEYWREN_F);
+	}
 }
 
 /**
@@ -3088,8 +3789,12 @@ void t4_write_rss_key(struct adapter *adap, const u32 *key, int idx)
 void t4_read_rss_pf_config(struct adapter *adapter, unsigned int index,
 			   u32 *valp)
 {
-	t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 valp, 1, TP_RSS_PF0_CONFIG_A + index);
+	if (adapter->flags & FW_OK)
+		t4_fw_tp_pio_rw(adapter, valp, 1,
+				TP_RSS_PF0_CONFIG_A + index, 1);
+	else
+		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 valp, 1, TP_RSS_PF0_CONFIG_A + index);
 }
 
 /**
@@ -3107,8 +3812,13 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
 {
 	u32 vrt, mask, data;
 
-	mask = VFWRADDR_V(VFWRADDR_M);
-	data = VFWRADDR_V(index);
+	if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) {
+		mask = VFWRADDR_V(VFWRADDR_M);
+		data = VFWRADDR_V(index);
+	} else {
+		 mask =  T6_VFWRADDR_V(T6_VFWRADDR_M);
+		 data = T6_VFWRADDR_V(index);
+	}
 
 	/* Request that the index'th VF Table values be read into VFL/VFH.
 	 */
@@ -3119,10 +3829,15 @@ void t4_read_rss_vf_config(struct adapter *adapter, unsigned int index,
 
 	/* Grab the VFL/VFH values ...
 	 */
-	t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 vfl, 1, TP_RSS_VFL_CONFIG_A);
-	t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 vfh, 1, TP_RSS_VFH_CONFIG_A);
+	if (adapter->flags & FW_OK) {
+		t4_fw_tp_pio_rw(adapter, vfl, 1, TP_RSS_VFL_CONFIG_A, 1);
+		t4_fw_tp_pio_rw(adapter, vfh, 1, TP_RSS_VFH_CONFIG_A, 1);
+	} else {
+		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 vfl, 1, TP_RSS_VFL_CONFIG_A);
+		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 vfh, 1, TP_RSS_VFH_CONFIG_A);
+	}
 }
 
 /**
@@ -3135,8 +3850,11 @@ u32 t4_read_rss_pf_map(struct adapter *adapter)
 {
 	u32 pfmap;
 
-	t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 &pfmap, 1, TP_RSS_PF_MAP_A);
+	if (adapter->flags & FW_OK)
+		t4_fw_tp_pio_rw(adapter, &pfmap, 1, TP_RSS_PF_MAP_A, 1);
+	else
+		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 &pfmap, 1, TP_RSS_PF_MAP_A);
 	return pfmap;
 }
 
@@ -3150,8 +3868,11 @@ u32 t4_read_rss_pf_mask(struct adapter *adapter)
 {
 	u32 pfmask;
 
-	t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 &pfmask, 1, TP_RSS_PF_MSK_A);
+	if (adapter->flags & FW_OK)
+		t4_fw_tp_pio_rw(adapter, &pfmask, 1, TP_RSS_PF_MSK_A, 1);
+	else
+		t4_read_indirect(adapter, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 &pfmask, 1, TP_RSS_PF_MSK_A);
 	return pfmask;
 }
 
@@ -3176,18 +3897,18 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 	if (v4) {
 		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
 				 ARRAY_SIZE(val), TP_MIB_TCP_OUT_RST_A);
-		v4->tcpOutRsts = STAT(OUT_RST);
-		v4->tcpInSegs  = STAT64(IN_SEG);
-		v4->tcpOutSegs = STAT64(OUT_SEG);
-		v4->tcpRetransSegs = STAT64(RXT_SEG);
+		v4->tcp_out_rsts = STAT(OUT_RST);
+		v4->tcp_in_segs  = STAT64(IN_SEG);
+		v4->tcp_out_segs = STAT64(OUT_SEG);
+		v4->tcp_retrans_segs = STAT64(RXT_SEG);
 	}
 	if (v6) {
 		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
 				 ARRAY_SIZE(val), TP_MIB_TCP_V6OUT_RST_A);
-		v6->tcpOutRsts = STAT(OUT_RST);
-		v6->tcpInSegs  = STAT64(IN_SEG);
-		v6->tcpOutSegs = STAT64(OUT_SEG);
-		v6->tcpRetransSegs = STAT64(RXT_SEG);
+		v6->tcp_out_rsts = STAT(OUT_RST);
+		v6->tcp_in_segs  = STAT64(IN_SEG);
+		v6->tcp_out_segs = STAT64(OUT_SEG);
+		v6->tcp_retrans_segs = STAT64(RXT_SEG);
 	}
 #undef STAT64
 #undef STAT
@@ -3195,6 +3916,130 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 }
 
 /**
+ *	t4_tp_get_err_stats - read TP's error MIB counters
+ *	@adap: the adapter
+ *	@st: holds the counter values
+ *
+ *	Returns the values of TP's error counters.
+ */
+void t4_tp_get_err_stats(struct adapter *adap, struct tp_err_stats *st)
+{
+	/* T6 and later has 2 channels */
+	if (adap->params.arch.nchan == NCHAN) {
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->mac_in_errs, 12, TP_MIB_MAC_IN_ERR_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tnl_cong_drops, 8,
+				 TP_MIB_TNL_CNG_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tnl_tx_drops, 4,
+				 TP_MIB_TNL_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->ofld_vlan_drops, 4,
+				 TP_MIB_OFD_VLN_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tcp6_in_errs, 4,
+				 TP_MIB_TCP_V6IN_ERR_0_A);
+	} else {
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->mac_in_errs, 2, TP_MIB_MAC_IN_ERR_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->hdr_in_errs, 2, TP_MIB_HDR_IN_ERR_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tcp_in_errs, 2, TP_MIB_TCP_IN_ERR_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tnl_cong_drops, 2,
+				 TP_MIB_TNL_CNG_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->ofld_chan_drops, 2,
+				 TP_MIB_OFD_CHN_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tnl_tx_drops, 2, TP_MIB_TNL_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->ofld_vlan_drops, 2,
+				 TP_MIB_OFD_VLN_DROP_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+				 st->tcp6_in_errs, 2, TP_MIB_TCP_V6IN_ERR_0_A);
+	}
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A,
+			 &st->ofld_no_neigh, 2, TP_MIB_OFD_ARP_DROP_A);
+}
+
+/**
+ *	t4_tp_get_cpl_stats - read TP's CPL MIB counters
+ *	@adap: the adapter
+ *	@st: holds the counter values
+ *
+ *	Returns the values of TP's CPL counters.
+ */
+void t4_tp_get_cpl_stats(struct adapter *adap, struct tp_cpl_stats *st)
+{
+	/* T6 and later has 2 channels */
+	if (adap->params.arch.nchan == NCHAN) {
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req,
+				 8, TP_MIB_CPL_IN_REQ_0_A);
+	} else {
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->req,
+				 2, TP_MIB_CPL_IN_REQ_0_A);
+		t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, st->rsp,
+				 2, TP_MIB_CPL_OUT_RSP_0_A);
+	}
+}
+
+/**
+ *	t4_tp_get_rdma_stats - read TP's RDMA MIB counters
+ *	@adap: the adapter
+ *	@st: holds the counter values
+ *
+ *	Returns the values of TP's RDMA counters.
+ */
+void t4_tp_get_rdma_stats(struct adapter *adap, struct tp_rdma_stats *st)
+{
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->rqe_dfr_pkt,
+			 2, TP_MIB_RQE_DFR_PKT_A);
+}
+
+/**
+ *	t4_get_fcoe_stats - read TP's FCoE MIB counters for a port
+ *	@adap: the adapter
+ *	@idx: the port index
+ *	@st: holds the counter values
+ *
+ *	Returns the values of TP's FCoE counters for the selected port.
+ */
+void t4_get_fcoe_stats(struct adapter *adap, unsigned int idx,
+		       struct tp_fcoe_stats *st)
+{
+	u32 val[2];
+
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_ddp,
+			 1, TP_MIB_FCOE_DDP_0_A + idx);
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, &st->frames_drop,
+			 1, TP_MIB_FCOE_DROP_0_A + idx);
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val,
+			 2, TP_MIB_FCOE_BYTE_0_HI_A + 2 * idx);
+	st->octets_ddp = ((u64)val[0] << 32) | val[1];
+}
+
+/**
+ *	t4_get_usm_stats - read TP's non-TCP DDP MIB counters
+ *	@adap: the adapter
+ *	@st: holds the counter values
+ *
+ *	Returns the values of TP's counters for non-TCP directly-placed packets.
+ */
+void t4_get_usm_stats(struct adapter *adap, struct tp_usm_stats *st)
+{
+	u32 val[4];
+
+	t4_read_indirect(adap, TP_MIB_INDEX_A, TP_MIB_DATA_A, val, 4,
+			 TP_MIB_USM_PKTS_A);
+	st->frames = val[0];
+	st->drops = val[1];
+	st->octets = ((u64)val[2] << 32) | val[3];
+}
+
+/**
  *	t4_read_mtu_tbl - returns the values in the HW path MTU table
  *	@adap: the adapter
  *	@mtus: where to store the MTU values
@@ -3346,6 +4191,52 @@ void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
 	}
 }
 
+/* Calculates a rate in bytes/s given the number of 256-byte units per 4K core
+ * clocks.  The formula is
+ *
+ * bytes/s = bytes256 * 256 * ClkFreq / 4096
+ *
+ * which is equivalent to
+ *
+ * bytes/s = 62.5 * bytes256 * ClkFreq_ms
+ */
+static u64 chan_rate(struct adapter *adap, unsigned int bytes256)
+{
+	u64 v = bytes256 * adap->params.vpd.cclk;
+
+	return v * 62 + v / 2;
+}
+
+/**
+ *	t4_get_chan_txrate - get the current per channel Tx rates
+ *	@adap: the adapter
+ *	@nic_rate: rates for NIC traffic
+ *	@ofld_rate: rates for offloaded traffic
+ *
+ *	Return the current Tx rates in bytes/s for NIC and offloaded traffic
+ *	for each channel.
+ */
+void t4_get_chan_txrate(struct adapter *adap, u64 *nic_rate, u64 *ofld_rate)
+{
+	u32 v;
+
+	v = t4_read_reg(adap, TP_TX_TRATE_A);
+	nic_rate[0] = chan_rate(adap, TNLRATE0_G(v));
+	nic_rate[1] = chan_rate(adap, TNLRATE1_G(v));
+	if (adap->params.arch.nchan == NCHAN) {
+		nic_rate[2] = chan_rate(adap, TNLRATE2_G(v));
+		nic_rate[3] = chan_rate(adap, TNLRATE3_G(v));
+	}
+
+	v = t4_read_reg(adap, TP_TX_ORATE_A);
+	ofld_rate[0] = chan_rate(adap, OFDRATE0_G(v));
+	ofld_rate[1] = chan_rate(adap, OFDRATE1_G(v));
+	if (adap->params.arch.nchan == NCHAN) {
+		ofld_rate[2] = chan_rate(adap, OFDRATE2_G(v));
+		ofld_rate[3] = chan_rate(adap, OFDRATE3_G(v));
+	}
+}
+
 /**
  *	t4_pmtx_get_stats - returns the HW stats from PMTX
  *	@adap: the adapter
@@ -3401,7 +4292,7 @@ void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[])
 }
 
 /**
- *	get_mps_bg_map - return the buffer groups associated with a port
+ *	t4_get_mps_bg_map - return the buffer groups associated with a port
  *	@adap: the adapter
  *	@idx: the port index
  *
@@ -3409,7 +4300,7 @@ void t4_pmrx_get_stats(struct adapter *adap, u32 cnt[], u64 cycles[])
  *	with the given port.  Bit i is set if buffer group i is used by the
  *	port.
  */
-static unsigned int get_mps_bg_map(struct adapter *adap, int idx)
+unsigned int t4_get_mps_bg_map(struct adapter *adap, int idx)
 {
 	u32 n = NUMPORTS_G(t4_read_reg(adap, MPS_CMN_CTL_A));
 
@@ -3451,6 +4342,28 @@ const char *t4_get_port_type_description(enum fw_port_type port_type)
 }
 
 /**
+ *      t4_get_port_stats_offset - collect port stats relative to a previous
+ *                                 snapshot
+ *      @adap: The adapter
+ *      @idx: The port
+ *      @stats: Current stats to fill
+ *      @offset: Previous stats snapshot
+ */
+void t4_get_port_stats_offset(struct adapter *adap, int idx,
+			      struct port_stats *stats,
+			      struct port_stats *offset)
+{
+	u64 *s, *o;
+	int i;
+
+	t4_get_port_stats(adap, idx, stats);
+	for (i = 0, s = (u64 *)stats, o = (u64 *)offset;
+			i < (sizeof(struct port_stats) / sizeof(u64));
+			i++, s++, o++)
+		*s -= *o;
+}
+
+/**
  *	t4_get_port_stats - collect port statistics
  *	@adap: the adapter
  *	@idx: the port index
@@ -3460,7 +4373,7 @@ const char *t4_get_port_type_description(enum fw_port_type port_type)
  */
 void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p)
 {
-	u32 bgmap = get_mps_bg_map(adap, idx);
+	u32 bgmap = t4_get_mps_bg_map(adap, idx);
 
 #define GET_STAT(name) \
 	t4_read_reg64(adap, \
@@ -3534,103 +4447,51 @@ void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p)
 }
 
 /**
- *	t4_wol_magic_enable - enable/disable magic packet WoL
- *	@adap: the adapter
- *	@port: the physical port index
- *	@addr: MAC address expected in magic packets, %NULL to disable
- *
- *	Enables/disables magic packet wake-on-LAN for the selected port.
- */
-void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
-			 const u8 *addr)
-{
-	u32 mag_id_reg_l, mag_id_reg_h, port_cfg_reg;
-
-	if (is_t4(adap->params.chip)) {
-		mag_id_reg_l = PORT_REG(port, XGMAC_PORT_MAGIC_MACID_LO);
-		mag_id_reg_h = PORT_REG(port, XGMAC_PORT_MAGIC_MACID_HI);
-		port_cfg_reg = PORT_REG(port, XGMAC_PORT_CFG2_A);
-	} else {
-		mag_id_reg_l = T5_PORT_REG(port, MAC_PORT_MAGIC_MACID_LO);
-		mag_id_reg_h = T5_PORT_REG(port, MAC_PORT_MAGIC_MACID_HI);
-		port_cfg_reg = T5_PORT_REG(port, MAC_PORT_CFG2_A);
-	}
-
-	if (addr) {
-		t4_write_reg(adap, mag_id_reg_l,
-			     (addr[2] << 24) | (addr[3] << 16) |
-			     (addr[4] << 8) | addr[5]);
-		t4_write_reg(adap, mag_id_reg_h,
-			     (addr[0] << 8) | addr[1]);
-	}
-	t4_set_reg_field(adap, port_cfg_reg, MAGICEN_F,
-			 addr ? MAGICEN_F : 0);
-}
-
-/**
- *	t4_wol_pat_enable - enable/disable pattern-based WoL
+ *	t4_get_lb_stats - collect loopback port statistics
  *	@adap: the adapter
- *	@port: the physical port index
- *	@map: bitmap of which HW pattern filters to set
- *	@mask0: byte mask for bytes 0-63 of a packet
- *	@mask1: byte mask for bytes 64-127 of a packet
- *	@crc: Ethernet CRC for selected bytes
- *	@enable: enable/disable switch
+ *	@idx: the loopback port index
+ *	@p: the stats structure to fill
  *
- *	Sets the pattern filters indicated in @map to mask out the bytes
- *	specified in @mask0/@mask1 in received packets and compare the CRC of
- *	the resulting packet against @crc.  If @enable is %true pattern-based
- *	WoL is enabled, otherwise disabled.
+ *	Return HW statistics for the given loopback port.
  */
-int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
-		      u64 mask0, u64 mask1, unsigned int crc, bool enable)
+void t4_get_lb_stats(struct adapter *adap, int idx, struct lb_port_stats *p)
 {
-	int i;
-	u32 port_cfg_reg;
-
-	if (is_t4(adap->params.chip))
-		port_cfg_reg = PORT_REG(port, XGMAC_PORT_CFG2_A);
-	else
-		port_cfg_reg = T5_PORT_REG(port, MAC_PORT_CFG2_A);
-
-	if (!enable) {
-		t4_set_reg_field(adap, port_cfg_reg, PATEN_F, 0);
-		return 0;
-	}
-	if (map > 0xff)
-		return -EINVAL;
+	u32 bgmap = t4_get_mps_bg_map(adap, idx);
 
-#define EPIO_REG(name) \
+#define GET_STAT(name) \
+	t4_read_reg64(adap, \
 	(is_t4(adap->params.chip) ? \
-	 PORT_REG(port, XGMAC_PORT_EPIO_##name##_A) : \
-	 T5_PORT_REG(port, MAC_PORT_EPIO_##name##_A))
-
-	t4_write_reg(adap, EPIO_REG(DATA1), mask0 >> 32);
-	t4_write_reg(adap, EPIO_REG(DATA2), mask1);
-	t4_write_reg(adap, EPIO_REG(DATA3), mask1 >> 32);
-
-	for (i = 0; i < NWOL_PAT; i++, map >>= 1) {
-		if (!(map & 1))
-			continue;
+	PORT_REG(idx, MPS_PORT_STAT_LB_PORT_##name##_L) : \
+	T5_PORT_REG(idx, MPS_PORT_STAT_LB_PORT_##name##_L)))
+#define GET_STAT_COM(name) t4_read_reg64(adap, MPS_STAT_##name##_L)
 
-		/* write byte masks */
-		t4_write_reg(adap, EPIO_REG(DATA0), mask0);
-		t4_write_reg(adap, EPIO_REG(OP), ADDRESS_V(i) | EPIOWR_F);
-		t4_read_reg(adap, EPIO_REG(OP));                /* flush */
-		if (t4_read_reg(adap, EPIO_REG(OP)) & SF_BUSY_F)
-			return -ETIMEDOUT;
-
-		/* write CRC */
-		t4_write_reg(adap, EPIO_REG(DATA0), crc);
-		t4_write_reg(adap, EPIO_REG(OP), ADDRESS_V(i + 32) | EPIOWR_F);
-		t4_read_reg(adap, EPIO_REG(OP));                /* flush */
-		if (t4_read_reg(adap, EPIO_REG(OP)) & SF_BUSY_F)
-			return -ETIMEDOUT;
-	}
-#undef EPIO_REG
+	p->octets           = GET_STAT(BYTES);
+	p->frames           = GET_STAT(FRAMES);
+	p->bcast_frames     = GET_STAT(BCAST);
+	p->mcast_frames     = GET_STAT(MCAST);
+	p->ucast_frames     = GET_STAT(UCAST);
+	p->error_frames     = GET_STAT(ERROR);
+
+	p->frames_64        = GET_STAT(64B);
+	p->frames_65_127    = GET_STAT(65B_127B);
+	p->frames_128_255   = GET_STAT(128B_255B);
+	p->frames_256_511   = GET_STAT(256B_511B);
+	p->frames_512_1023  = GET_STAT(512B_1023B);
+	p->frames_1024_1518 = GET_STAT(1024B_1518B);
+	p->frames_1519_max  = GET_STAT(1519B_MAX);
+	p->drop             = GET_STAT(DROP_FRAMES);
+
+	p->ovflow0 = (bgmap & 1) ? GET_STAT_COM(RX_BG_0_LB_DROP_FRAME) : 0;
+	p->ovflow1 = (bgmap & 2) ? GET_STAT_COM(RX_BG_1_LB_DROP_FRAME) : 0;
+	p->ovflow2 = (bgmap & 4) ? GET_STAT_COM(RX_BG_2_LB_DROP_FRAME) : 0;
+	p->ovflow3 = (bgmap & 8) ? GET_STAT_COM(RX_BG_3_LB_DROP_FRAME) : 0;
+	p->trunc0 = (bgmap & 1) ? GET_STAT_COM(RX_BG_0_LB_TRUNC_FRAME) : 0;
+	p->trunc1 = (bgmap & 2) ? GET_STAT_COM(RX_BG_1_LB_TRUNC_FRAME) : 0;
+	p->trunc2 = (bgmap & 4) ? GET_STAT_COM(RX_BG_2_LB_TRUNC_FRAME) : 0;
+	p->trunc3 = (bgmap & 8) ? GET_STAT_COM(RX_BG_3_LB_TRUNC_FRAME) : 0;
 
-	t4_set_reg_field(adap, PORT_REG(port, XGMAC_PORT_CFG2_A), 0, PATEN_F);
-	return 0;
+#undef GET_STAT
+#undef GET_STAT_COM
 }
 
 /*     t4_mk_filtdelwr - create a delete filter WR
@@ -3644,33 +4505,38 @@ int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
 void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid)
 {
 	memset(wr, 0, sizeof(*wr));
-	wr->op_pkd = htonl(FW_WR_OP_V(FW_FILTER_WR));
-	wr->len16_pkd = htonl(FW_WR_LEN16_V(sizeof(*wr) / 16));
-	wr->tid_to_iq = htonl(FW_FILTER_WR_TID_V(ftid) |
-			FW_FILTER_WR_NOREPLY_V(qid < 0));
-	wr->del_filter_to_l2tix = htonl(FW_FILTER_WR_DEL_FILTER_F);
+	wr->op_pkd = cpu_to_be32(FW_WR_OP_V(FW_FILTER_WR));
+	wr->len16_pkd = cpu_to_be32(FW_WR_LEN16_V(sizeof(*wr) / 16));
+	wr->tid_to_iq = cpu_to_be32(FW_FILTER_WR_TID_V(ftid) |
+				    FW_FILTER_WR_NOREPLY_V(qid < 0));
+	wr->del_filter_to_l2tix = cpu_to_be32(FW_FILTER_WR_DEL_FILTER_F);
 	if (qid >= 0)
-		wr->rx_chan_rx_rpl_iq = htons(FW_FILTER_WR_RX_RPL_IQ_V(qid));
+		wr->rx_chan_rx_rpl_iq =
+			cpu_to_be16(FW_FILTER_WR_RX_RPL_IQ_V(qid));
 }
 
 #define INIT_CMD(var, cmd, rd_wr) do { \
-	(var).op_to_write = htonl(FW_CMD_OP_V(FW_##cmd##_CMD) | \
-				  FW_CMD_REQUEST_F | FW_CMD_##rd_wr##_F); \
-	(var).retval_len16 = htonl(FW_LEN16(var)); \
+	(var).op_to_write = cpu_to_be32(FW_CMD_OP_V(FW_##cmd##_CMD) | \
+					FW_CMD_REQUEST_F | \
+					FW_CMD_##rd_wr##_F); \
+	(var).retval_len16 = cpu_to_be32(FW_LEN16(var)); \
 } while (0)
 
 int t4_fwaddrspace_write(struct adapter *adap, unsigned int mbox,
 			  u32 addr, u32 val)
 {
+	u32 ldst_addrspace;
 	struct fw_ldst_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_addrspace = htonl(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_WRITE_F |
-			    FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_FIRMWARE));
-	c.cycles_to_len16 = htonl(FW_LEN16(c));
-	c.u.addrval.addr = htonl(addr);
-	c.u.addrval.val = htonl(val);
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_FIRMWARE);
+	c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+					FW_CMD_REQUEST_F |
+					FW_CMD_WRITE_F |
+					ldst_addrspace);
+	c.cycles_to_len16 = cpu_to_be32(FW_LEN16(c));
+	c.u.addrval.addr = cpu_to_be32(addr);
+	c.u.addrval.val = cpu_to_be32(val);
 
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
@@ -3690,19 +4556,22 @@ int t4_mdio_rd(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
 	       unsigned int mmd, unsigned int reg, u16 *valp)
 {
 	int ret;
+	u32 ldst_addrspace;
 	struct fw_ldst_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_addrspace = htonl(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F |
-		FW_CMD_READ_F | FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MDIO));
-	c.cycles_to_len16 = htonl(FW_LEN16(c));
-	c.u.mdio.paddr_mmd = htons(FW_LDST_CMD_PADDR_V(phy_addr) |
-				   FW_LDST_CMD_MMD_V(mmd));
-	c.u.mdio.raddr = htons(reg);
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MDIO);
+	c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+					FW_CMD_REQUEST_F | FW_CMD_READ_F |
+					ldst_addrspace);
+	c.cycles_to_len16 = cpu_to_be32(FW_LEN16(c));
+	c.u.mdio.paddr_mmd = cpu_to_be16(FW_LDST_CMD_PADDR_V(phy_addr) |
+					 FW_LDST_CMD_MMD_V(mmd));
+	c.u.mdio.raddr = cpu_to_be16(reg);
 
 	ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
 	if (ret == 0)
-		*valp = ntohs(c.u.mdio.rval);
+		*valp = be16_to_cpu(c.u.mdio.rval);
 	return ret;
 }
 
@@ -3720,16 +4589,19 @@ int t4_mdio_rd(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
 int t4_mdio_wr(struct adapter *adap, unsigned int mbox, unsigned int phy_addr,
 	       unsigned int mmd, unsigned int reg, u16 val)
 {
+	u32 ldst_addrspace;
 	struct fw_ldst_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_addrspace = htonl(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F |
-		FW_CMD_WRITE_F | FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MDIO));
-	c.cycles_to_len16 = htonl(FW_LEN16(c));
-	c.u.mdio.paddr_mmd = htons(FW_LDST_CMD_PADDR_V(phy_addr) |
-				   FW_LDST_CMD_MMD_V(mmd));
-	c.u.mdio.raddr = htons(reg);
-	c.u.mdio.rval = htons(val);
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_MDIO);
+	c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+					FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+					ldst_addrspace);
+	c.cycles_to_len16 = cpu_to_be32(FW_LEN16(c));
+	c.u.mdio.paddr_mmd = cpu_to_be16(FW_LDST_CMD_PADDR_V(phy_addr) |
+					 FW_LDST_CMD_MMD_V(mmd));
+	c.u.mdio.raddr = cpu_to_be16(reg);
+	c.u.mdio.rval = cpu_to_be16(val);
 
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
@@ -3841,6 +4713,32 @@ void t4_sge_decode_idma_state(struct adapter *adapter, int state)
 }
 
 /**
+ *      t4_sge_ctxt_flush - flush the SGE context cache
+ *      @adap: the adapter
+ *      @mbox: mailbox to use for the FW command
+ *
+ *      Issues a FW command through the given mailbox to flush the
+ *      SGE context cache.
+ */
+int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox)
+{
+	int ret;
+	u32 ldst_addrspace;
+	struct fw_ldst_cmd c;
+
+	memset(&c, 0, sizeof(c));
+	ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_SGE_EGRC);
+	c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) |
+					FW_CMD_REQUEST_F | FW_CMD_READ_F |
+					ldst_addrspace);
+	c.cycles_to_len16 = cpu_to_be32(FW_LEN16(c));
+	c.u.idctxt.msg_ctxtflush = cpu_to_be32(FW_LDST_CMD_CTXTFLUSH_F);
+
+	ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
+	return ret;
+}
+
+/**
  *      t4_fw_hello - establish communication with FW
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
@@ -3863,11 +4761,11 @@ int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox,
 retry:
 	memset(&c, 0, sizeof(c));
 	INIT_CMD(c, HELLO, WRITE);
-	c.err_to_clearinit = htonl(
+	c.err_to_clearinit = cpu_to_be32(
 		FW_HELLO_CMD_MASTERDIS_V(master == MASTER_CANT) |
 		FW_HELLO_CMD_MASTERFORCE_V(master == MASTER_MUST) |
-		FW_HELLO_CMD_MBMASTER_V(master == MASTER_MUST ? mbox :
-				      FW_HELLO_CMD_MBMASTER_M) |
+		FW_HELLO_CMD_MBMASTER_V(master == MASTER_MUST ?
+					mbox : FW_HELLO_CMD_MBMASTER_M) |
 		FW_HELLO_CMD_MBASYNCNOT_V(evt_mbox) |
 		FW_HELLO_CMD_STAGE_V(fw_hello_cmd_stage_os) |
 		FW_HELLO_CMD_CLEARINIT_F);
@@ -3888,7 +4786,7 @@ retry:
 		return ret;
 	}
 
-	v = ntohl(c.err_to_clearinit);
+	v = be32_to_cpu(c.err_to_clearinit);
 	master_mbox = FW_HELLO_CMD_MBMASTER_G(v);
 	if (state) {
 		if (v & FW_HELLO_CMD_ERR_F)
@@ -4017,7 +4915,7 @@ int t4_fw_reset(struct adapter *adap, unsigned int mbox, int reset)
 
 	memset(&c, 0, sizeof(c));
 	INIT_CMD(c, RESET, WRITE);
-	c.val = htonl(reset);
+	c.val = cpu_to_be32(reset);
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4050,8 +4948,8 @@ static int t4_fw_halt(struct adapter *adap, unsigned int mbox, int force)
 
 		memset(&c, 0, sizeof(c));
 		INIT_CMD(c, RESET, WRITE);
-		c.val = htonl(PIORST_F | PIORSTMODE_F);
-		c.halt_pkd = htonl(FW_RESET_CMD_HALT_F);
+		c.val = cpu_to_be32(PIORST_F | PIORSTMODE_F);
+		c.halt_pkd = cpu_to_be32(FW_RESET_CMD_HALT_F);
 		ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 	}
 
@@ -4190,7 +5088,7 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 	 * the newly loaded firmware will handle this right by checking
 	 * its header flags to see if it advertises the capability.
 	 */
-	reset = ((ntohl(fw_hdr->flags) & FW_HDR_FLAGS_RESET_HALT) == 0);
+	reset = ((be32_to_cpu(fw_hdr->flags) & FW_HDR_FLAGS_RESET_HALT) == 0);
 	return t4_fw_restart(adap, mbox, reset);
 }
 
@@ -4321,7 +5219,7 @@ int t4_fw_initialize(struct adapter *adap, unsigned int mbox)
 }
 
 /**
- *	t4_query_params - query FW or device parameters
+ *	t4_query_params_rw - query FW or device parameters
  *	@adap: the adapter
  *	@mbox: mailbox to use for the FW command
  *	@pf: the PF
@@ -4329,13 +5227,14 @@ int t4_fw_initialize(struct adapter *adap, unsigned int mbox)
  *	@nparams: the number of parameters
  *	@params: the parameter names
  *	@val: the parameter values
+ *	@rw: Write and read flag
  *
  *	Reads the value of FW or device parameters.  Up to 7 parameters can be
  *	queried at once.
  */
-int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
-		    unsigned int vf, unsigned int nparams, const u32 *params,
-		    u32 *val)
+int t4_query_params_rw(struct adapter *adap, unsigned int mbox, unsigned int pf,
+		       unsigned int vf, unsigned int nparams, const u32 *params,
+		       u32 *val, int rw)
 {
 	int i, ret;
 	struct fw_params_cmd c;
@@ -4345,22 +5244,35 @@ int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		return -EINVAL;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_PARAMS_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_READ_F | FW_PARAMS_CMD_PFN_V(pf) |
-			    FW_PARAMS_CMD_VFN_V(vf));
-	c.retval_len16 = htonl(FW_LEN16(c));
-	for (i = 0; i < nparams; i++, p += 2)
-		*p = htonl(*params++);
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PARAMS_CMD) |
+				  FW_CMD_REQUEST_F | FW_CMD_READ_F |
+				  FW_PARAMS_CMD_PFN_V(pf) |
+				  FW_PARAMS_CMD_VFN_V(vf));
+	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
+
+	for (i = 0; i < nparams; i++) {
+		*p++ = cpu_to_be32(*params++);
+		if (rw)
+			*p = cpu_to_be32(*(val + i));
+		p++;
+	}
 
 	ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
 	if (ret == 0)
 		for (i = 0, p = &c.param[0].val; i < nparams; i++, p += 2)
-			*val++ = ntohl(*p);
+			*val++ = be32_to_cpu(*p);
 	return ret;
 }
 
+int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
+		    unsigned int vf, unsigned int nparams, const u32 *params,
+		    u32 *val)
+{
+	return t4_query_params_rw(adap, mbox, pf, vf, nparams, params, val, 0);
+}
+
 /**
- *      t4_set_params_nosleep - sets FW or device parameters
+ *      t4_set_params_timeout - sets FW or device parameters
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
  *      @pf: the PF
@@ -4368,15 +5280,15 @@ int t4_query_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
  *      @nparams: the number of parameters
  *      @params: the parameter names
  *      @val: the parameter values
+ *      @timeout: the timeout time
  *
- *	 Does not ever sleep
  *      Sets the value of FW or device parameters.  Up to 7 parameters can be
  *      specified at once.
  */
-int t4_set_params_nosleep(struct adapter *adap, unsigned int mbox,
+int t4_set_params_timeout(struct adapter *adap, unsigned int mbox,
 			  unsigned int pf, unsigned int vf,
 			  unsigned int nparams, const u32 *params,
-			  const u32 *val)
+			  const u32 *val, int timeout)
 {
 	struct fw_params_cmd c;
 	__be32 *p = &c.param[0].mnem;
@@ -4386,9 +5298,9 @@ int t4_set_params_nosleep(struct adapter *adap, unsigned int mbox,
 
 	memset(&c, 0, sizeof(c));
 	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PARAMS_CMD) |
-				FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
-				FW_PARAMS_CMD_PFN_V(pf) |
-				FW_PARAMS_CMD_VFN_V(vf));
+				  FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+				  FW_PARAMS_CMD_PFN_V(pf) |
+				  FW_PARAMS_CMD_VFN_V(vf));
 	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
 
 	while (nparams--) {
@@ -4396,7 +5308,7 @@ int t4_set_params_nosleep(struct adapter *adap, unsigned int mbox,
 		*p++ = cpu_to_be32(*val++);
 	}
 
-	return t4_wr_mbox_ns(adap, mbox, &c, sizeof(c), NULL);
+	return t4_wr_mbox_timeout(adap, mbox, &c, sizeof(c), NULL, timeout);
 }
 
 /**
@@ -4416,23 +5328,8 @@ int t4_set_params(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		  unsigned int vf, unsigned int nparams, const u32 *params,
 		  const u32 *val)
 {
-	struct fw_params_cmd c;
-	__be32 *p = &c.param[0].mnem;
-
-	if (nparams > 7)
-		return -EINVAL;
-
-	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_PARAMS_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_WRITE_F | FW_PARAMS_CMD_PFN_V(pf) |
-			    FW_PARAMS_CMD_VFN_V(vf));
-	c.retval_len16 = htonl(FW_LEN16(c));
-	while (nparams--) {
-		*p++ = htonl(*params++);
-		*p++ = htonl(*val++);
-	}
-
-	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
+	return t4_set_params_timeout(adap, mbox, pf, vf, nparams, params, val,
+				     FW_CMD_MAX_TIMEOUT);
 }
 
 /**
@@ -4465,20 +5362,21 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
 	struct fw_pfvf_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_PFVF_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_WRITE_F | FW_PFVF_CMD_PFN_V(pf) |
-			    FW_PFVF_CMD_VFN_V(vf));
-	c.retval_len16 = htonl(FW_LEN16(c));
-	c.niqflint_niq = htonl(FW_PFVF_CMD_NIQFLINT_V(rxqi) |
-			       FW_PFVF_CMD_NIQ_V(rxq));
-	c.type_to_neq = htonl(FW_PFVF_CMD_CMASK_V(cmask) |
-			       FW_PFVF_CMD_PMASK_V(pmask) |
-			       FW_PFVF_CMD_NEQ_V(txq));
-	c.tc_to_nexactf = htonl(FW_PFVF_CMD_TC_V(tc) | FW_PFVF_CMD_NVI_V(vi) |
-				FW_PFVF_CMD_NEXACTF_V(nexact));
-	c.r_caps_to_nethctrl = htonl(FW_PFVF_CMD_R_CAPS_V(rcaps) |
-				     FW_PFVF_CMD_WX_CAPS_V(wxcaps) |
-				     FW_PFVF_CMD_NETHCTRL_V(txq_eth_ctrl));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PFVF_CMD) | FW_CMD_REQUEST_F |
+				  FW_CMD_WRITE_F | FW_PFVF_CMD_PFN_V(pf) |
+				  FW_PFVF_CMD_VFN_V(vf));
+	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
+	c.niqflint_niq = cpu_to_be32(FW_PFVF_CMD_NIQFLINT_V(rxqi) |
+				     FW_PFVF_CMD_NIQ_V(rxq));
+	c.type_to_neq = cpu_to_be32(FW_PFVF_CMD_CMASK_V(cmask) |
+				    FW_PFVF_CMD_PMASK_V(pmask) |
+				    FW_PFVF_CMD_NEQ_V(txq));
+	c.tc_to_nexactf = cpu_to_be32(FW_PFVF_CMD_TC_V(tc) |
+				      FW_PFVF_CMD_NVI_V(vi) |
+				      FW_PFVF_CMD_NEXACTF_V(nexact));
+	c.r_caps_to_nethctrl = cpu_to_be32(FW_PFVF_CMD_R_CAPS_V(rcaps) |
+					FW_PFVF_CMD_WX_CAPS_V(wxcaps) |
+					FW_PFVF_CMD_NETHCTRL_V(txq_eth_ctrl));
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4507,10 +5405,10 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 	struct fw_vi_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_VI_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_WRITE_F | FW_CMD_EXEC_F |
-			    FW_VI_CMD_PFN_V(pf) | FW_VI_CMD_VFN_V(vf));
-	c.alloc_to_len16 = htonl(FW_VI_CMD_ALLOC_F | FW_LEN16(c));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_VI_CMD) | FW_CMD_REQUEST_F |
+				  FW_CMD_WRITE_F | FW_CMD_EXEC_F |
+				  FW_VI_CMD_PFN_V(pf) | FW_VI_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_VI_CMD_ALLOC_F | FW_LEN16(c));
 	c.portid_pkd = FW_VI_CMD_PORTID_V(port);
 	c.nmac = nmac - 1;
 
@@ -4532,8 +5430,35 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		}
 	}
 	if (rss_size)
-		*rss_size = FW_VI_CMD_RSSSIZE_G(ntohs(c.rsssize_pkd));
-	return FW_VI_CMD_VIID_G(ntohs(c.type_viid));
+		*rss_size = FW_VI_CMD_RSSSIZE_G(be16_to_cpu(c.rsssize_pkd));
+	return FW_VI_CMD_VIID_G(be16_to_cpu(c.type_viid));
+}
+
+/**
+ *	t4_free_vi - free a virtual interface
+ *	@adap: the adapter
+ *	@mbox: mailbox to use for the FW command
+ *	@pf: the PF owning the VI
+ *	@vf: the VF owning the VI
+ *	@viid: virtual interface identifiler
+ *
+ *	Free a previously allocated virtual interface.
+ */
+int t4_free_vi(struct adapter *adap, unsigned int mbox, unsigned int pf,
+	       unsigned int vf, unsigned int viid)
+{
+	struct fw_vi_cmd c;
+
+	memset(&c, 0, sizeof(c));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_VI_CMD) |
+				  FW_CMD_REQUEST_F |
+				  FW_CMD_EXEC_F |
+				  FW_VI_CMD_PFN_V(pf) |
+				  FW_VI_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_VI_CMD_FREE_F | FW_LEN16(c));
+	c.type_viid = cpu_to_be16(FW_VI_CMD_VIID_V(viid));
+
+	return t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
 }
 
 /**
@@ -4569,14 +5494,16 @@ int t4_set_rxmode(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		vlanex = FW_VI_RXMODE_CMD_VLANEXEN_M;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_RXMODE_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_WRITE_F | FW_VI_RXMODE_CMD_VIID_V(viid));
-	c.retval_len16 = htonl(FW_LEN16(c));
-	c.mtu_to_vlanexen = htonl(FW_VI_RXMODE_CMD_MTU_V(mtu) |
-				  FW_VI_RXMODE_CMD_PROMISCEN_V(promisc) |
-				  FW_VI_RXMODE_CMD_ALLMULTIEN_V(all_multi) |
-				  FW_VI_RXMODE_CMD_BROADCASTEN_V(bcast) |
-				  FW_VI_RXMODE_CMD_VLANEXEN_V(vlanex));
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_RXMODE_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+				   FW_VI_RXMODE_CMD_VIID_V(viid));
+	c.retval_len16 = cpu_to_be32(FW_LEN16(c));
+	c.mtu_to_vlanexen =
+		cpu_to_be32(FW_VI_RXMODE_CMD_MTU_V(mtu) |
+			    FW_VI_RXMODE_CMD_PROMISCEN_V(promisc) |
+			    FW_VI_RXMODE_CMD_ALLMULTIEN_V(all_multi) |
+			    FW_VI_RXMODE_CMD_BROADCASTEN_V(bcast) |
+			    FW_VI_RXMODE_CMD_VLANEXEN_V(vlanex));
 	return t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), NULL, sleep_ok);
 }
 
@@ -4606,43 +5533,71 @@ int t4_alloc_mac_filt(struct adapter *adap, unsigned int mbox,
 		      unsigned int viid, bool free, unsigned int naddr,
 		      const u8 **addr, u16 *idx, u64 *hash, bool sleep_ok)
 {
-	int i, ret;
+	int offset, ret = 0;
 	struct fw_vi_mac_cmd c;
-	struct fw_vi_mac_exact *p;
-	unsigned int max_naddr = is_t4(adap->params.chip) ?
-				       NUM_MPS_CLS_SRAM_L_INSTANCES :
-				       NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+	unsigned int nfilters = 0;
+	unsigned int max_naddr = adap->params.arch.mps_tcam_size;
+	unsigned int rem = naddr;
 
-	if (naddr > 7)
+	if (naddr > max_naddr)
 		return -EINVAL;
 
-	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_MAC_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_WRITE_F | (free ? FW_CMD_EXEC_F : 0) |
-			     FW_VI_MAC_CMD_VIID_V(viid));
-	c.freemacs_to_len16 = htonl(FW_VI_MAC_CMD_FREEMACS_V(free) |
-				    FW_CMD_LEN16_V((naddr + 2) / 2));
-
-	for (i = 0, p = c.u.exact; i < naddr; i++, p++) {
-		p->valid_to_idx = htons(FW_VI_MAC_CMD_VALID_F |
-				      FW_VI_MAC_CMD_IDX_V(FW_VI_MAC_ADD_MAC));
-		memcpy(p->macaddr, addr[i], sizeof(p->macaddr));
-	}
+	for (offset = 0; offset < naddr ; /**/) {
+		unsigned int fw_naddr = (rem < ARRAY_SIZE(c.u.exact) ?
+					 rem : ARRAY_SIZE(c.u.exact));
+		size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
+						     u.exact[fw_naddr]), 16);
+		struct fw_vi_mac_exact *p;
+		int i;
 
-	ret = t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), &c, sleep_ok);
-	if (ret)
-		return ret;
+		memset(&c, 0, sizeof(c));
+		c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+					   FW_CMD_REQUEST_F |
+					   FW_CMD_WRITE_F |
+					   FW_CMD_EXEC_V(free) |
+					   FW_VI_MAC_CMD_VIID_V(viid));
+		c.freemacs_to_len16 =
+			cpu_to_be32(FW_VI_MAC_CMD_FREEMACS_V(free) |
+				    FW_CMD_LEN16_V(len16));
+
+		for (i = 0, p = c.u.exact; i < fw_naddr; i++, p++) {
+			p->valid_to_idx =
+				cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+					    FW_VI_MAC_CMD_IDX_V(
+						    FW_VI_MAC_ADD_MAC));
+			memcpy(p->macaddr, addr[offset + i],
+			       sizeof(p->macaddr));
+		}
 
-	for (i = 0, p = c.u.exact; i < naddr; i++, p++) {
-		u16 index = FW_VI_MAC_CMD_IDX_G(ntohs(p->valid_to_idx));
+		/* It's okay if we run out of space in our MAC address arena.
+		 * Some of the addresses we submit may get stored so we need
+		 * to run through the reply to see what the results were ...
+		 */
+		ret = t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), &c, sleep_ok);
+		if (ret && ret != -FW_ENOMEM)
+			break;
 
-		if (idx)
-			idx[i] = index >= max_naddr ? 0xffff : index;
-		if (index < max_naddr)
-			ret++;
-		else if (hash)
-			*hash |= (1ULL << hash_mac_addr(addr[i]));
+		for (i = 0, p = c.u.exact; i < fw_naddr; i++, p++) {
+			u16 index = FW_VI_MAC_CMD_IDX_G(
+					be16_to_cpu(p->valid_to_idx));
+
+			if (idx)
+				idx[offset + i] = (index >= max_naddr ?
+						   0xffff : index);
+			if (index < max_naddr)
+				nfilters++;
+			else if (hash)
+				*hash |= (1ULL <<
+					  hash_mac_addr(addr[offset + i]));
+		}
+
+		free = false;
+		offset += fw_naddr;
+		rem -= fw_naddr;
 	}
+
+	if (ret == 0 || ret == -FW_ENOMEM)
+		ret = nfilters;
 	return ret;
 }
 
@@ -4671,26 +5626,25 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
 	int ret, mode;
 	struct fw_vi_mac_cmd c;
 	struct fw_vi_mac_exact *p = c.u.exact;
-	unsigned int max_mac_addr = is_t4(adap->params.chip) ?
-				    NUM_MPS_CLS_SRAM_L_INSTANCES :
-				    NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+	unsigned int max_mac_addr = adap->params.arch.mps_tcam_size;
 
 	if (idx < 0)                             /* new allocation */
 		idx = persist ? FW_VI_MAC_ADD_PERSIST_MAC : FW_VI_MAC_ADD_MAC;
 	mode = add_smt ? FW_VI_MAC_SMT_AND_MPSTCAM : FW_VI_MAC_MPS_TCAM_ENTRY;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_MAC_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_WRITE_F | FW_VI_MAC_CMD_VIID_V(viid));
-	c.freemacs_to_len16 = htonl(FW_CMD_LEN16_V(1));
-	p->valid_to_idx = htons(FW_VI_MAC_CMD_VALID_F |
-				FW_VI_MAC_CMD_SMAC_RESULT_V(mode) |
-				FW_VI_MAC_CMD_IDX_V(idx));
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+				   FW_VI_MAC_CMD_VIID_V(viid));
+	c.freemacs_to_len16 = cpu_to_be32(FW_CMD_LEN16_V(1));
+	p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F |
+				      FW_VI_MAC_CMD_SMAC_RESULT_V(mode) |
+				      FW_VI_MAC_CMD_IDX_V(idx));
 	memcpy(p->macaddr, addr, sizeof(p->macaddr));
 
 	ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
 	if (ret == 0) {
-		ret = FW_VI_MAC_CMD_IDX_G(ntohs(p->valid_to_idx));
+		ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
 		if (ret >= max_mac_addr)
 			ret = -ENOMEM;
 	}
@@ -4714,11 +5668,12 @@ int t4_set_addr_hash(struct adapter *adap, unsigned int mbox, unsigned int viid,
 	struct fw_vi_mac_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_MAC_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_WRITE_F | FW_VI_ENABLE_CMD_VIID_V(viid));
-	c.freemacs_to_len16 = htonl(FW_VI_MAC_CMD_HASHVECEN_F |
-				    FW_VI_MAC_CMD_HASHUNIEN_V(ucast) |
-				    FW_CMD_LEN16_V(1));
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_WRITE_F |
+				   FW_VI_ENABLE_CMD_VIID_V(viid));
+	c.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_HASHVECEN_F |
+					  FW_VI_MAC_CMD_HASHUNIEN_V(ucast) |
+					  FW_CMD_LEN16_V(1));
 	c.u.hash.hashvec = cpu_to_be64(vec);
 	return t4_wr_mbox_meat(adap, mbox, &c, sizeof(c), NULL, sleep_ok);
 }
@@ -4741,12 +5696,13 @@ int t4_enable_vi_params(struct adapter *adap, unsigned int mbox,
 	struct fw_vi_enable_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_ENABLE_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_EXEC_F | FW_VI_ENABLE_CMD_VIID_V(viid));
-
-	c.ien_to_len16 = htonl(FW_VI_ENABLE_CMD_IEN_V(rx_en) |
-			       FW_VI_ENABLE_CMD_EEN_V(tx_en) | FW_LEN16(c) |
-			       FW_VI_ENABLE_CMD_DCB_INFO_V(dcb_en));
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_ENABLE_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				   FW_VI_ENABLE_CMD_VIID_V(viid));
+	c.ien_to_len16 = cpu_to_be32(FW_VI_ENABLE_CMD_IEN_V(rx_en) |
+				     FW_VI_ENABLE_CMD_EEN_V(tx_en) |
+				     FW_VI_ENABLE_CMD_DCB_INFO_V(dcb_en) |
+				     FW_LEN16(c));
 	return t4_wr_mbox_ns(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4781,10 +5737,11 @@ int t4_identify_port(struct adapter *adap, unsigned int mbox, unsigned int viid,
 	struct fw_vi_enable_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_viid = htonl(FW_CMD_OP_V(FW_VI_ENABLE_CMD) | FW_CMD_REQUEST_F |
-			     FW_CMD_EXEC_F | FW_VI_ENABLE_CMD_VIID_V(viid));
-	c.ien_to_len16 = htonl(FW_VI_ENABLE_CMD_LED_F | FW_LEN16(c));
-	c.blinkdur = htons(nblinks);
+	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_ENABLE_CMD) |
+				   FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				   FW_VI_ENABLE_CMD_VIID_V(viid));
+	c.ien_to_len16 = cpu_to_be32(FW_VI_ENABLE_CMD_LED_F | FW_LEN16(c));
+	c.blinkdur = cpu_to_be16(nblinks);
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4808,14 +5765,14 @@ int t4_iq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 	struct fw_iq_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_IQ_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_EXEC_F | FW_IQ_CMD_PFN_V(pf) |
-			    FW_IQ_CMD_VFN_V(vf));
-	c.alloc_to_len16 = htonl(FW_IQ_CMD_FREE_F | FW_LEN16(c));
-	c.type_to_iqandstindex = htonl(FW_IQ_CMD_TYPE_V(iqtype));
-	c.iqid = htons(iqid);
-	c.fl0id = htons(fl0id);
-	c.fl1id = htons(fl1id);
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_IQ_CMD) | FW_CMD_REQUEST_F |
+				  FW_CMD_EXEC_F | FW_IQ_CMD_PFN_V(pf) |
+				  FW_IQ_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_IQ_CMD_FREE_F | FW_LEN16(c));
+	c.type_to_iqandstindex = cpu_to_be32(FW_IQ_CMD_TYPE_V(iqtype));
+	c.iqid = cpu_to_be16(iqid);
+	c.fl0id = cpu_to_be16(fl0id);
+	c.fl1id = cpu_to_be16(fl1id);
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4835,11 +5792,12 @@ int t4_eth_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 	struct fw_eq_eth_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_ETH_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_EXEC_F | FW_EQ_ETH_CMD_PFN_V(pf) |
-			    FW_EQ_ETH_CMD_VFN_V(vf));
-	c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_FREE_F | FW_LEN16(c));
-	c.eqid_pkd = htonl(FW_EQ_ETH_CMD_EQID_V(eqid));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_EQ_ETH_CMD) |
+				  FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				  FW_EQ_ETH_CMD_PFN_V(pf) |
+				  FW_EQ_ETH_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_EQ_ETH_CMD_FREE_F | FW_LEN16(c));
+	c.eqid_pkd = cpu_to_be32(FW_EQ_ETH_CMD_EQID_V(eqid));
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4859,11 +5817,12 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 	struct fw_eq_ctrl_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_CTRL_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_EXEC_F | FW_EQ_CTRL_CMD_PFN_V(pf) |
-			    FW_EQ_CTRL_CMD_VFN_V(vf));
-	c.alloc_to_len16 = htonl(FW_EQ_CTRL_CMD_FREE_F | FW_LEN16(c));
-	c.cmpliqid_eqid = htonl(FW_EQ_CTRL_CMD_EQID_V(eqid));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_EQ_CTRL_CMD) |
+				  FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				  FW_EQ_CTRL_CMD_PFN_V(pf) |
+				  FW_EQ_CTRL_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_EQ_CTRL_CMD_FREE_F | FW_LEN16(c));
+	c.cmpliqid_eqid = cpu_to_be32(FW_EQ_CTRL_CMD_EQID_V(eqid));
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4883,11 +5842,12 @@ int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 	struct fw_eq_ofld_cmd c;
 
 	memset(&c, 0, sizeof(c));
-	c.op_to_vfn = htonl(FW_CMD_OP_V(FW_EQ_OFLD_CMD) | FW_CMD_REQUEST_F |
-			    FW_CMD_EXEC_F | FW_EQ_OFLD_CMD_PFN_V(pf) |
-			    FW_EQ_OFLD_CMD_VFN_V(vf));
-	c.alloc_to_len16 = htonl(FW_EQ_OFLD_CMD_FREE_F | FW_LEN16(c));
-	c.eqid_pkd = htonl(FW_EQ_OFLD_CMD_EQID_V(eqid));
+	c.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_EQ_OFLD_CMD) |
+				  FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
+				  FW_EQ_OFLD_CMD_PFN_V(pf) |
+				  FW_EQ_OFLD_CMD_VFN_V(vf));
+	c.alloc_to_len16 = cpu_to_be32(FW_EQ_OFLD_CMD_FREE_F | FW_LEN16(c));
+	c.eqid_pkd = cpu_to_be32(FW_EQ_OFLD_CMD_EQID_V(eqid));
 	return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
 }
 
@@ -4905,11 +5865,11 @@ int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl)
 	if (opcode == FW_PORT_CMD) {    /* link/module state change message */
 		int speed = 0, fc = 0;
 		const struct fw_port_cmd *p = (void *)rpl;
-		int chan = FW_PORT_CMD_PORTID_G(ntohl(p->op_to_portid));
+		int chan = FW_PORT_CMD_PORTID_G(be32_to_cpu(p->op_to_portid));
 		int port = adap->chan_map[chan];
 		struct port_info *pi = adap2pinfo(adap, port);
 		struct link_config *lc = &pi->link_cfg;
-		u32 stat = ntohl(p->u.info.lstatus_to_modtype);
+		u32 stat = be32_to_cpu(p->u.info.lstatus_to_modtype);
 		int link_ok = (stat & FW_PORT_CMD_LSTATUS_F) != 0;
 		u32 mod = FW_PORT_CMD_MODTYPE_G(stat);
 
@@ -5043,6 +6003,22 @@ static int get_flash_params(struct adapter *adap)
 	return 0;
 }
 
+static void set_pcie_completion_timeout(struct adapter *adapter, u8 range)
+{
+	u16 val;
+	u32 pcie_cap;
+
+	pcie_cap = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
+	if (pcie_cap) {
+		pci_read_config_word(adapter->pdev,
+				     pcie_cap + PCI_EXP_DEVCTL2, &val);
+		val &= ~PCI_EXP_DEVCTL2_COMP_TIMEOUT;
+		val |= range;
+		pci_write_config_word(adapter->pdev,
+				      pcie_cap + PCI_EXP_DEVCTL2, val);
+	}
+}
+
 /**
  *	t4_prep_adapter - prepare SW and HW for operation
  *	@adapter: the adapter
@@ -5075,9 +6051,30 @@ int t4_prep_adapter(struct adapter *adapter)
 	switch (ver) {
 	case CHELSIO_T4:
 		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T4, pl_rev);
+		adapter->params.arch.sge_fl_db = DBPRIO_F;
+		adapter->params.arch.mps_tcam_size =
+				 NUM_MPS_CLS_SRAM_L_INSTANCES;
+		adapter->params.arch.mps_rplc_size = 128;
+		adapter->params.arch.nchan = NCHAN;
+		adapter->params.arch.vfcount = 128;
 		break;
 	case CHELSIO_T5:
 		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T5, pl_rev);
+		adapter->params.arch.sge_fl_db = DBPRIO_F | DBTYPE_F;
+		adapter->params.arch.mps_tcam_size =
+				 NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+		adapter->params.arch.mps_rplc_size = 128;
+		adapter->params.arch.nchan = NCHAN;
+		adapter->params.arch.vfcount = 128;
+		break;
+	case CHELSIO_T6:
+		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T6, pl_rev);
+		adapter->params.arch.sge_fl_db = 0;
+		adapter->params.arch.mps_tcam_size =
+				 NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+		adapter->params.arch.mps_rplc_size = 256;
+		adapter->params.arch.nchan = 2;
+		adapter->params.arch.vfcount = 256;
 		break;
 	default:
 		dev_err(adapter->pdev_dev, "Device %d is not supported\n",
@@ -5094,14 +6091,18 @@ int t4_prep_adapter(struct adapter *adapter)
 	adapter->params.nports = 1;
 	adapter->params.portvec = 1;
 	adapter->params.vpd.cclk = 50000;
+
+	/* Set pci completion timeout value to 4 seconds. */
+	set_pcie_completion_timeout(adapter, 0xd);
 	return 0;
 }
 
 /**
- *	cxgb4_t4_bar2_sge_qregs - return BAR2 SGE Queue register information
+ *	t4_bar2_sge_qregs - return BAR2 SGE Queue register information
  *	@adapter: the adapter
  *	@qid: the Queue ID
  *	@qtype: the Ingress or Egress type for @qid
+ *	@user: true if this request is for a user mode queue
  *	@pbar2_qoffset: BAR2 Queue Offset
  *	@pbar2_qid: BAR2 Queue ID or 0 for Queue ID inferred SGE Queues
  *
@@ -5122,9 +6123,10 @@ int t4_prep_adapter(struct adapter *adapter)
  *	Write Combining Doorbell Buffer. If the BAR2 Queue ID is not 0,
  *	then these "Inferred Queue ID" register may not be used.
  */
-int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
+int t4_bar2_sge_qregs(struct adapter *adapter,
 		      unsigned int qid,
 		      enum t4_bar2_qtype qtype,
+		      int user,
 		      u64 *pbar2_qoffset,
 		      unsigned int *pbar2_qid)
 {
@@ -5132,9 +6134,8 @@ int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
 	u64 bar2_page_offset, bar2_qoffset;
 	unsigned int bar2_qid, bar2_qid_offset, bar2_qinferred;
 
-	/* T4 doesn't support BAR2 SGE Queue registers.
-	 */
-	if (is_t4(adapter->params.chip))
+	/* T4 doesn't support BAR2 SGE Queue registers for kernel mode queues */
+	if (!user && is_t4(adapter->params.chip))
 		return -EINVAL;
 
 	/* Get our SGE Page Size parameters.
@@ -5154,7 +6155,7 @@ int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
 	 *  o The BAR2 Queue ID.
 	 *  o The BAR2 Queue ID Offset into the BAR2 page.
 	 */
-	bar2_page_offset = ((qid >> qpp_shift) << page_shift);
+	bar2_page_offset = ((u64)(qid >> qpp_shift) << page_shift);
 	bar2_qid = qid & qpp_mask;
 	bar2_qid_offset = bar2_qid * SGE_UDB_SIZE;
 
@@ -5223,18 +6224,19 @@ int t4_init_devlog_params(struct adapter *adap)
 	/* Otherwise, ask the firmware for it's Device Log Parameters.
 	 */
 	memset(&devlog_cmd, 0, sizeof(devlog_cmd));
-	devlog_cmd.op_to_write = htonl(FW_CMD_OP_V(FW_DEVLOG_CMD) |
-				       FW_CMD_REQUEST_F | FW_CMD_READ_F);
-	devlog_cmd.retval_len16 = htonl(FW_LEN16(devlog_cmd));
+	devlog_cmd.op_to_write = cpu_to_be32(FW_CMD_OP_V(FW_DEVLOG_CMD) |
+					     FW_CMD_REQUEST_F | FW_CMD_READ_F);
+	devlog_cmd.retval_len16 = cpu_to_be32(FW_LEN16(devlog_cmd));
 	ret = t4_wr_mbox(adap, adap->mbox, &devlog_cmd, sizeof(devlog_cmd),
 			 &devlog_cmd);
 	if (ret)
 		return ret;
 
-	devlog_meminfo = ntohl(devlog_cmd.memtype_devlog_memaddr16_devlog);
+	devlog_meminfo =
+		be32_to_cpu(devlog_cmd.memtype_devlog_memaddr16_devlog);
 	dparams->memtype = FW_DEVLOG_CMD_MEMTYPE_DEVLOG_G(devlog_meminfo);
 	dparams->start = FW_DEVLOG_CMD_MEMADDR16_DEVLOG_G(devlog_meminfo) << 4;
-	dparams->size = ntohl(devlog_cmd.memsize_devlog);
+	dparams->size = be32_to_cpu(devlog_cmd.memsize_devlog);
 
 	return 0;
 }
@@ -5255,13 +6257,13 @@ int t4_init_sge_params(struct adapter *adapter)
 	 */
 	hps = t4_read_reg(adapter, SGE_HOST_PAGE_SIZE_A);
 	s_hps = (HOSTPAGESIZEPF0_S +
-		 (HOSTPAGESIZEPF1_S - HOSTPAGESIZEPF0_S) * adapter->fn);
+		 (HOSTPAGESIZEPF1_S - HOSTPAGESIZEPF0_S) * adapter->pf);
 	sge_params->hps = ((hps >> s_hps) & HOSTPAGESIZEPF0_M);
 
 	/* Extract the SGE Egress and Ingess Queues Per Page for our PF.
 	 */
 	s_qpp = (QUEUESPERPAGEPF0_S +
-		(QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) * adapter->fn);
+		(QUEUESPERPAGEPF1_S - QUEUESPERPAGEPF0_S) * adapter->pf);
 	qpp = t4_read_reg(adapter, SGE_EGRESS_QUEUES_PER_PAGE_PF_A);
 	sge_params->eq_qpp = ((qpp >> s_qpp) & QUEUESPERPAGEPF0_M);
 	qpp = t4_read_reg(adapter, SGE_INGRESS_QUEUES_PER_PAGE_PF_A);
@@ -5292,12 +6294,19 @@ int t4_init_tp_params(struct adapter *adap)
 	/* Cache the adapter's Compressed Filter Mode and global Incress
 	 * Configuration.
 	 */
-	t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 &adap->params.tp.vlan_pri_map, 1,
-			 TP_VLAN_PRI_MAP_A);
-	t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
-			 &adap->params.tp.ingress_config, 1,
-			 TP_INGRESS_CONFIG_A);
+	if (adap->flags & FW_OK) {
+		t4_fw_tp_pio_rw(adap, &adap->params.tp.vlan_pri_map, 1,
+				TP_VLAN_PRI_MAP_A, 1);
+		t4_fw_tp_pio_rw(adap, &adap->params.tp.ingress_config, 1,
+				TP_INGRESS_CONFIG_A, 1);
+	} else {
+		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 &adap->params.tp.vlan_pri_map, 1,
+				 TP_VLAN_PRI_MAP_A);
+		t4_read_indirect(adap, TP_PIO_ADDR_A, TP_PIO_DATA_A,
+				 &adap->params.tp.ingress_config, 1,
+				 TP_INGRESS_CONFIG_A);
+	}
 
 	/* Now that we have TP_VLAN_PRI_MAP cached, we can calculate the field
 	 * shift positions of several elements of the Compressed Filter Tuple
@@ -5373,6 +6382,29 @@ int t4_filter_field_shift(const struct adapter *adap, int filter_sel)
 	return field_shift;
 }
 
+int t4_init_rss_mode(struct adapter *adap, int mbox)
+{
+	int i, ret;
+	struct fw_rss_vi_config_cmd rvc;
+
+	memset(&rvc, 0, sizeof(rvc));
+
+	for_each_port(adap, i) {
+		struct port_info *p = adap2pinfo(adap, i);
+
+		rvc.op_to_viid =
+			cpu_to_be32(FW_CMD_OP_V(FW_RSS_VI_CONFIG_CMD) |
+				    FW_CMD_REQUEST_F | FW_CMD_READ_F |
+				    FW_RSS_VI_CONFIG_CMD_VIID_V(p->viid));
+		rvc.retval_len16 = cpu_to_be32(FW_LEN16(rvc));
+		ret = t4_wr_mbox(adap, mbox, &rvc, sizeof(rvc), &rvc);
+		if (ret)
+			return ret;
+		p->rss_mode = be32_to_cpu(rvc.u.basicvirtual.defaultq_to_udpen);
+	}
+	return 0;
+}
+
 int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
 {
 	u8 addr[6];
@@ -5390,10 +6422,10 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
 		while ((adap->params.portvec & (1 << j)) == 0)
 			j++;
 
-		c.op_to_portid = htonl(FW_CMD_OP_V(FW_PORT_CMD) |
-				       FW_CMD_REQUEST_F | FW_CMD_READ_F |
-				       FW_PORT_CMD_PORTID_V(j));
-		c.action_to_len16 = htonl(
+		c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) |
+					     FW_CMD_REQUEST_F | FW_CMD_READ_F |
+					     FW_PORT_CMD_PORTID_V(j));
+		c.action_to_len16 = cpu_to_be32(
 			FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_GET_PORT_INFO) |
 			FW_LEN16(c));
 		ret = t4_wr_mbox(adap, mbox, &c, sizeof(c), &c);
@@ -5411,22 +6443,23 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
 		memcpy(adap->port[i]->dev_addr, addr, ETH_ALEN);
 		adap->port[i]->dev_port = j;
 
-		ret = ntohl(c.u.info.lstatus_to_modtype);
+		ret = be32_to_cpu(c.u.info.lstatus_to_modtype);
 		p->mdio_addr = (ret & FW_PORT_CMD_MDIOCAP_F) ?
 			FW_PORT_CMD_MDIOADDR_G(ret) : -1;
 		p->port_type = FW_PORT_CMD_PTYPE_G(ret);
 		p->mod_type = FW_PORT_MOD_TYPE_NA;
 
-		rvc.op_to_viid = htonl(FW_CMD_OP_V(FW_RSS_VI_CONFIG_CMD) |
-				       FW_CMD_REQUEST_F | FW_CMD_READ_F |
-				       FW_RSS_VI_CONFIG_CMD_VIID(p->viid));
-		rvc.retval_len16 = htonl(FW_LEN16(rvc));
+		rvc.op_to_viid =
+			cpu_to_be32(FW_CMD_OP_V(FW_RSS_VI_CONFIG_CMD) |
+				    FW_CMD_REQUEST_F | FW_CMD_READ_F |
+				    FW_RSS_VI_CONFIG_CMD_VIID(p->viid));
+		rvc.retval_len16 = cpu_to_be32(FW_LEN16(rvc));
 		ret = t4_wr_mbox(adap, mbox, &rvc, sizeof(rvc), &rvc);
 		if (ret)
 			return ret;
-		p->rss_mode = ntohl(rvc.u.basicvirtual.defaultq_to_udpen);
+		p->rss_mode = be32_to_cpu(rvc.u.basicvirtual.defaultq_to_udpen);
 
-		init_link_config(&p->link_cfg, ntohs(c.u.info.pcap));
+		init_link_config(&p->link_cfg, be16_to_cpu(c.u.info.pcap));
 		j++;
 	}
 	return 0;
@@ -5717,3 +6750,130 @@ void t4_tp_read_la(struct adapter *adap, u64 *la_buf, unsigned int *wrptr)
 		t4_write_reg(adap, TP_DBG_LA_CONFIG_A,
 			     cfg | adap->params.tp.la_mask);
 }
+
+/* SGE Hung Ingress DMA Warning Threshold time and Warning Repeat Rate (in
+ * seconds).  If we find one of the SGE Ingress DMA State Machines in the same
+ * state for more than the Warning Threshold then we'll issue a warning about
+ * a potential hang.  We'll repeat the warning as the SGE Ingress DMA Channel
+ * appears to be hung every Warning Repeat second till the situation clears.
+ * If the situation clears, we'll note that as well.
+ */
+#define SGE_IDMA_WARN_THRESH 1
+#define SGE_IDMA_WARN_REPEAT 300
+
+/**
+ *	t4_idma_monitor_init - initialize SGE Ingress DMA Monitor
+ *	@adapter: the adapter
+ *	@idma: the adapter IDMA Monitor state
+ *
+ *	Initialize the state of an SGE Ingress DMA Monitor.
+ */
+void t4_idma_monitor_init(struct adapter *adapter,
+			  struct sge_idma_monitor_state *idma)
+{
+	/* Initialize the state variables for detecting an SGE Ingress DMA
+	 * hang.  The SGE has internal counters which count up on each clock
+	 * tick whenever the SGE finds its Ingress DMA State Engines in the
+	 * same state they were on the previous clock tick.  The clock used is
+	 * the Core Clock so we have a limit on the maximum "time" they can
+	 * record; typically a very small number of seconds.  For instance,
+	 * with a 600MHz Core Clock, we can only count up to a bit more than
+	 * 7s.  So we'll synthesize a larger counter in order to not run the
+	 * risk of having the "timers" overflow and give us the flexibility to
+	 * maintain a Hung SGE State Machine of our own which operates across
+	 * a longer time frame.
+	 */
+	idma->idma_1s_thresh = core_ticks_per_usec(adapter) * 1000000; /* 1s */
+	idma->idma_stalled[0] = 0;
+	idma->idma_stalled[1] = 0;
+}
+
+/**
+ *	t4_idma_monitor - monitor SGE Ingress DMA state
+ *	@adapter: the adapter
+ *	@idma: the adapter IDMA Monitor state
+ *	@hz: number of ticks/second
+ *	@ticks: number of ticks since the last IDMA Monitor call
+ */
+void t4_idma_monitor(struct adapter *adapter,
+		     struct sge_idma_monitor_state *idma,
+		     int hz, int ticks)
+{
+	int i, idma_same_state_cnt[2];
+
+	 /* Read the SGE Debug Ingress DMA Same State Count registers.  These
+	  * are counters inside the SGE which count up on each clock when the
+	  * SGE finds its Ingress DMA State Engines in the same states they
+	  * were in the previous clock.  The counters will peg out at
+	  * 0xffffffff without wrapping around so once they pass the 1s
+	  * threshold they'll stay above that till the IDMA state changes.
+	  */
+	t4_write_reg(adapter, SGE_DEBUG_INDEX_A, 13);
+	idma_same_state_cnt[0] = t4_read_reg(adapter, SGE_DEBUG_DATA_HIGH_A);
+	idma_same_state_cnt[1] = t4_read_reg(adapter, SGE_DEBUG_DATA_LOW_A);
+
+	for (i = 0; i < 2; i++) {
+		u32 debug0, debug11;
+
+		/* If the Ingress DMA Same State Counter ("timer") is less
+		 * than 1s, then we can reset our synthesized Stall Timer and
+		 * continue.  If we have previously emitted warnings about a
+		 * potential stalled Ingress Queue, issue a note indicating
+		 * that the Ingress Queue has resumed forward progress.
+		 */
+		if (idma_same_state_cnt[i] < idma->idma_1s_thresh) {
+			if (idma->idma_stalled[i] >= SGE_IDMA_WARN_THRESH * hz)
+				dev_warn(adapter->pdev_dev, "SGE idma%d, queue %u, "
+					 "resumed after %d seconds\n",
+					 i, idma->idma_qid[i],
+					 idma->idma_stalled[i] / hz);
+			idma->idma_stalled[i] = 0;
+			continue;
+		}
+
+		/* Synthesize an SGE Ingress DMA Same State Timer in the Hz
+		 * domain.  The first time we get here it'll be because we
+		 * passed the 1s Threshold; each additional time it'll be
+		 * because the RX Timer Callback is being fired on its regular
+		 * schedule.
+		 *
+		 * If the stall is below our Potential Hung Ingress Queue
+		 * Warning Threshold, continue.
+		 */
+		if (idma->idma_stalled[i] == 0) {
+			idma->idma_stalled[i] = hz;
+			idma->idma_warn[i] = 0;
+		} else {
+			idma->idma_stalled[i] += ticks;
+			idma->idma_warn[i] -= ticks;
+		}
+
+		if (idma->idma_stalled[i] < SGE_IDMA_WARN_THRESH * hz)
+			continue;
+
+		/* We'll issue a warning every SGE_IDMA_WARN_REPEAT seconds.
+		 */
+		if (idma->idma_warn[i] > 0)
+			continue;
+		idma->idma_warn[i] = SGE_IDMA_WARN_REPEAT * hz;
+
+		/* Read and save the SGE IDMA State and Queue ID information.
+		 * We do this every time in case it changes across time ...
+		 * can't be too careful ...
+		 */
+		t4_write_reg(adapter, SGE_DEBUG_INDEX_A, 0);
+		debug0 = t4_read_reg(adapter, SGE_DEBUG_DATA_LOW_A);
+		idma->idma_state[i] = (debug0 >> (i * 9)) & 0x3f;
+
+		t4_write_reg(adapter, SGE_DEBUG_INDEX_A, 11);
+		debug11 = t4_read_reg(adapter, SGE_DEBUG_DATA_LOW_A);
+		idma->idma_qid[i] = (debug11 >> (i * 16)) & 0xffff;
+
+		dev_warn(adapter->pdev_dev, "SGE idma%u, queue %u, potentially stuck in "
+			 "state %u for %d seconds (debug0=%#x, debug11=%#x)\n",
+			 i, idma->idma_qid[i], idma->idma_state[i],
+			 idma->idma_stalled[i] / hz,
+			 debug0, debug11);
+		t4_sge_decode_idma_state(adapter, idma->idma_state[i]);
+	}
+}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index 380b15c0417a..c8488f430d19 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -52,8 +52,6 @@ enum {
 	MBOX_LEN       = 64,    /* mailbox size in bytes */
 	TRACE_LEN      = 112,   /* length of trace data and mask */
 	FILTER_OPT_LEN = 36,    /* filter tuple width for optional components */
-	NWOL_PAT       = 8,     /* # of WoL patterns */
-	WOL_PAT_LEN    = 128,   /* length of WoL patterns */
 };
 
 enum {
@@ -61,6 +59,8 @@ enum {
 	CIM_NUM_OBQ    = 6,     /* # of CIM OBQs */
 	CIM_NUM_OBQ_T5 = 8,     /* # of CIM OBQs for T5 adapter */
 	CIMLA_SIZE     = 2048,  /* # of 32-bit words in CIM LA */
+	CIM_PIFLA_SIZE = 64,    /* # of 192-bit words in CIM PIF LA */
+	CIM_MALA_SIZE  = 64,    /* # of 160-bit words in CIM MA LA */
 	CIM_IBQ_SIZE   = 128,   /* # of 128-bit words in a CIM IBQ */
 	CIM_OBQ_SIZE   = 128,   /* # of 128-bit words in a CIM OBQ */
 	TPLA_SIZE      = 128,   /* # of 64-bit words in TP LA */
@@ -152,17 +152,33 @@ struct rsp_ctrl {
 	};
 };
 
-#define RSPD_NEWBUF 0x80000000U
-#define RSPD_LEN(x) (((x) >> 0) & 0x7fffffffU)
-#define RSPD_QID(x) RSPD_LEN(x)
+#define RSPD_NEWBUF_S    31
+#define RSPD_NEWBUF_V(x) ((x) << RSPD_NEWBUF_S)
+#define RSPD_NEWBUF_F    RSPD_NEWBUF_V(1U)
 
-#define RSPD_GEN(x)  ((x) >> 7)
-#define RSPD_TYPE(x) (((x) >> 4) & 3)
+#define RSPD_LEN_S    0
+#define RSPD_LEN_M    0x7fffffff
+#define RSPD_LEN_G(x) (((x) >> RSPD_LEN_S) & RSPD_LEN_M)
 
-#define V_QINTR_CNT_EN	   0x0
-#define QINTR_CNT_EN       0x1
-#define QINTR_TIMER_IDX(x) ((x) << 1)
-#define QINTR_TIMER_IDX_GET(x) (((x) >> 1) & 0x7)
+#define RSPD_QID_S    RSPD_LEN_S
+#define RSPD_QID_M    RSPD_LEN_M
+#define RSPD_QID_G(x) RSPD_LEN_G(x)
+
+#define RSPD_GEN_S    7
+
+#define RSPD_TYPE_S    4
+#define RSPD_TYPE_M    0x3
+#define RSPD_TYPE_G(x) (((x) >> RSPD_TYPE_S) & RSPD_TYPE_M)
+
+/* Rx queue interrupt deferral fields: counter enable and timer index */
+#define QINTR_CNT_EN_S    0
+#define QINTR_CNT_EN_V(x) ((x) << QINTR_CNT_EN_S)
+#define QINTR_CNT_EN_F    QINTR_CNT_EN_V(1U)
+
+#define QINTR_TIMER_IDX_S    1
+#define QINTR_TIMER_IDX_M    0x7
+#define QINTR_TIMER_IDX_V(x) ((x) << QINTR_TIMER_IDX_S)
+#define QINTR_TIMER_IDX_G(x) (((x) >> QINTR_TIMER_IDX_S) & QINTR_TIMER_IDX_M)
 
 /*
  * Flash layout.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 30a2f56e99c2..132cb8fc0bf7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -634,26 +634,9 @@ struct cpl_tid_release {
 
 struct cpl_tx_pkt_core {
 	__be32 ctrl0;
-#define TXPKT_VF(x)        ((x) << 0)
-#define TXPKT_PF(x)        ((x) << 8)
-#define TXPKT_VF_VLD       (1 << 11)
-#define TXPKT_OVLAN_IDX(x) ((x) << 12)
-#define TXPKT_INTF(x)      ((x) << 16)
-#define TXPKT_INS_OVLAN    (1 << 21)
-#define TXPKT_OPCODE(x)    ((x) << 24)
 	__be16 pack;
 	__be16 len;
 	__be64 ctrl1;
-#define TXPKT_CSUM_END(x)   ((x) << 12)
-#define TXPKT_CSUM_START(x) ((x) << 20)
-#define TXPKT_IPHDR_LEN(x)  ((u64)(x) << 20)
-#define TXPKT_CSUM_LOC(x)   ((u64)(x) << 30)
-#define TXPKT_ETHHDR_LEN(x) ((u64)(x) << 34)
-#define TXPKT_CSUM_TYPE(x)  ((u64)(x) << 40)
-#define TXPKT_VLAN(x)       ((u64)(x) << 44)
-#define TXPKT_VLAN_VLD      (1ULL << 60)
-#define TXPKT_IPCSUM_DIS    (1ULL << 62)
-#define TXPKT_L4CSUM_DIS    (1ULL << 63)
 };
 
 struct cpl_tx_pkt {
@@ -663,16 +646,69 @@ struct cpl_tx_pkt {
 
 #define cpl_tx_pkt_xt cpl_tx_pkt
 
+/* cpl_tx_pkt_core.ctrl0 fields */
+#define TXPKT_VF_S    0
+#define TXPKT_VF_V(x) ((x) << TXPKT_VF_S)
+
+#define TXPKT_PF_S    8
+#define TXPKT_PF_V(x) ((x) << TXPKT_PF_S)
+
+#define TXPKT_VF_VLD_S    11
+#define TXPKT_VF_VLD_V(x) ((x) << TXPKT_VF_VLD_S)
+#define TXPKT_VF_VLD_F    TXPKT_VF_VLD_V(1U)
+
+#define TXPKT_OVLAN_IDX_S    12
+#define TXPKT_OVLAN_IDX_V(x) ((x) << TXPKT_OVLAN_IDX_S)
+
+#define TXPKT_INTF_S    16
+#define TXPKT_INTF_V(x) ((x) << TXPKT_INTF_S)
+
+#define TXPKT_INS_OVLAN_S    21
+#define TXPKT_INS_OVLAN_V(x) ((x) << TXPKT_INS_OVLAN_S)
+#define TXPKT_INS_OVLAN_F    TXPKT_INS_OVLAN_V(1U)
+
+#define TXPKT_OPCODE_S    24
+#define TXPKT_OPCODE_V(x) ((x) << TXPKT_OPCODE_S)
+
+/* cpl_tx_pkt_core.ctrl1 fields */
+#define TXPKT_CSUM_END_S    12
+#define TXPKT_CSUM_END_V(x) ((x) << TXPKT_CSUM_END_S)
+
+#define TXPKT_CSUM_START_S    20
+#define TXPKT_CSUM_START_V(x) ((x) << TXPKT_CSUM_START_S)
+
+#define TXPKT_IPHDR_LEN_S    20
+#define TXPKT_IPHDR_LEN_V(x) ((__u64)(x) << TXPKT_IPHDR_LEN_S)
+
+#define TXPKT_CSUM_LOC_S    30
+#define TXPKT_CSUM_LOC_V(x) ((__u64)(x) << TXPKT_CSUM_LOC_S)
+
+#define TXPKT_ETHHDR_LEN_S    34
+#define TXPKT_ETHHDR_LEN_V(x) ((__u64)(x) << TXPKT_ETHHDR_LEN_S)
+
+#define T6_TXPKT_ETHHDR_LEN_S    32
+#define T6_TXPKT_ETHHDR_LEN_V(x) ((__u64)(x) << T6_TXPKT_ETHHDR_LEN_S)
+
+#define TXPKT_CSUM_TYPE_S    40
+#define TXPKT_CSUM_TYPE_V(x) ((__u64)(x) << TXPKT_CSUM_TYPE_S)
+
+#define TXPKT_VLAN_S    44
+#define TXPKT_VLAN_V(x) ((__u64)(x) << TXPKT_VLAN_S)
+
+#define TXPKT_VLAN_VLD_S    60
+#define TXPKT_VLAN_VLD_V(x) ((__u64)(x) << TXPKT_VLAN_VLD_S)
+#define TXPKT_VLAN_VLD_F    TXPKT_VLAN_VLD_V(1ULL)
+
+#define TXPKT_IPCSUM_DIS_S    62
+#define TXPKT_IPCSUM_DIS_V(x) ((__u64)(x) << TXPKT_IPCSUM_DIS_S)
+#define TXPKT_IPCSUM_DIS_F    TXPKT_IPCSUM_DIS_V(1ULL)
+
+#define TXPKT_L4CSUM_DIS_S    63
+#define TXPKT_L4CSUM_DIS_V(x) ((__u64)(x) << TXPKT_L4CSUM_DIS_S)
+#define TXPKT_L4CSUM_DIS_F    TXPKT_L4CSUM_DIS_V(1ULL)
+
 struct cpl_tx_pkt_lso_core {
 	__be32 lso_ctrl;
-#define LSO_TCPHDR_LEN(x) ((x) << 0)
-#define LSO_IPHDR_LEN(x)  ((x) << 4)
-#define LSO_ETHHDR_LEN(x) ((x) << 16)
-#define LSO_IPV6(x)       ((x) << 20)
-#define LSO_LAST_SLICE    (1 << 22)
-#define LSO_FIRST_SLICE   (1 << 23)
-#define LSO_OPCODE(x)     ((x) << 24)
-#define LSO_T5_XFER_SIZE(x) ((x) << 0)
 	__be16 ipid_ofst;
 	__be16 mss;
 	__be32 seqno_offset;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 1a9a6f334d2d..d7ca106927b0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -153,6 +153,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x5088),	/* Custom T570-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5089),	/* Custom T520-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x5090),	/* Custom T540-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5091),	/* Custom T522-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x5092),	/* Custom T520-CR */
 CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
 
 #endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 326674b19983..375a825573b0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -418,6 +418,20 @@
 #define SGE_INGRESS_QUEUES_PER_PAGE_PF_A 0x10f4
 #define SGE_INGRESS_QUEUES_PER_PAGE_VF_A 0x10f8
 
+#define SGE_ERROR_STATS_A 0x1100
+
+#define UNCAPTURED_ERROR_S    18
+#define UNCAPTURED_ERROR_V(x) ((x) << UNCAPTURED_ERROR_S)
+#define UNCAPTURED_ERROR_F    UNCAPTURED_ERROR_V(1U)
+
+#define ERROR_QID_VALID_S    17
+#define ERROR_QID_VALID_V(x) ((x) << ERROR_QID_VALID_S)
+#define ERROR_QID_VALID_F    ERROR_QID_VALID_V(1U)
+
+#define ERROR_QID_S    0
+#define ERROR_QID_M    0x1ffffU
+#define ERROR_QID_G(x) (((x) >> ERROR_QID_S) & ERROR_QID_M)
+
 #define HP_INT_THRESH_S    28
 #define HP_INT_THRESH_M    0xfU
 #define HP_INT_THRESH_V(x) ((x) << HP_INT_THRESH_S)
@@ -448,8 +462,13 @@
 #define SGE_STAT_MATCH_A	0x10e8
 #define SGE_STAT_CFG_A		0x10ec
 
+#define STATMODE_S    2
+#define STATMODE_V(x) ((x) << STATMODE_S)
+
 #define STATSOURCE_T5_S    9
+#define STATSOURCE_T5_M    0xfU
 #define STATSOURCE_T5_V(x) ((x) << STATSOURCE_T5_S)
+#define STATSOURCE_T5_G(x) (((x) >> STATSOURCE_T5_S) & STATSOURCE_T5_M)
 
 #define SGE_DBFIFO_STATUS2_A 0x1118
 
@@ -705,6 +724,10 @@
 #define REGISTER_S    0
 #define REGISTER_V(x) ((x) << REGISTER_S)
 
+#define T6_ENABLE_S    31
+#define T6_ENABLE_V(x) ((x) << T6_ENABLE_S)
+#define T6_ENABLE_F    T6_ENABLE_V(1U)
+
 #define PFNUM_S    0
 #define PFNUM_V(x) ((x) << PFNUM_S)
 
@@ -1338,6 +1361,42 @@
 #define FLMTXFLSTEMPTY_V(x) ((x) << FLMTXFLSTEMPTY_S)
 #define FLMTXFLSTEMPTY_F    FLMTXFLSTEMPTY_V(1U)
 
+#define TP_TX_ORATE_A 0x7ebc
+
+#define OFDRATE3_S    24
+#define OFDRATE3_M    0xffU
+#define OFDRATE3_G(x) (((x) >> OFDRATE3_S) & OFDRATE3_M)
+
+#define OFDRATE2_S    16
+#define OFDRATE2_M    0xffU
+#define OFDRATE2_G(x) (((x) >> OFDRATE2_S) & OFDRATE2_M)
+
+#define OFDRATE1_S    8
+#define OFDRATE1_M    0xffU
+#define OFDRATE1_G(x) (((x) >> OFDRATE1_S) & OFDRATE1_M)
+
+#define OFDRATE0_S    0
+#define OFDRATE0_M    0xffU
+#define OFDRATE0_G(x) (((x) >> OFDRATE0_S) & OFDRATE0_M)
+
+#define TP_TX_TRATE_A 0x7ed0
+
+#define TNLRATE3_S    24
+#define TNLRATE3_M    0xffU
+#define TNLRATE3_G(x) (((x) >> TNLRATE3_S) & TNLRATE3_M)
+
+#define TNLRATE2_S    16
+#define TNLRATE2_M    0xffU
+#define TNLRATE2_G(x) (((x) >> TNLRATE2_S) & TNLRATE2_M)
+
+#define TNLRATE1_S    8
+#define TNLRATE1_M    0xffU
+#define TNLRATE1_G(x) (((x) >> TNLRATE1_S) & TNLRATE1_M)
+
+#define TNLRATE0_S    0
+#define TNLRATE0_M    0xffU
+#define TNLRATE0_G(x) (((x) >> TNLRATE0_S) & TNLRATE0_M)
+
 #define TP_VLAN_PRI_MAP_A 0x140
 
 #define FRAGMENTATION_S    9
@@ -1399,6 +1458,8 @@
 #define CSUM_HAS_PSEUDO_HDR_F    CSUM_HAS_PSEUDO_HDR_V(1U)
 
 #define TP_MIB_MAC_IN_ERR_0_A	0x0
+#define TP_MIB_HDR_IN_ERR_0_A	0x4
+#define TP_MIB_TCP_IN_ERR_0_A	0x8
 #define TP_MIB_TCP_OUT_RST_A	0xc
 #define TP_MIB_TCP_IN_SEG_HI_A	0x10
 #define TP_MIB_TCP_IN_SEG_LO_A	0x11
@@ -1407,11 +1468,19 @@
 #define TP_MIB_TCP_RXT_SEG_HI_A	0x14
 #define TP_MIB_TCP_RXT_SEG_LO_A	0x15
 #define TP_MIB_TNL_CNG_DROP_0_A 0x18
+#define TP_MIB_OFD_CHN_DROP_0_A 0x1c
 #define TP_MIB_TCP_V6IN_ERR_0_A 0x28
 #define TP_MIB_TCP_V6OUT_RST_A	0x2c
 #define TP_MIB_OFD_ARP_DROP_A	0x36
+#define TP_MIB_CPL_IN_REQ_0_A	0x38
+#define TP_MIB_CPL_OUT_RSP_0_A	0x3c
 #define TP_MIB_TNL_DROP_0_A	0x44
+#define TP_MIB_FCOE_DDP_0_A	0x48
+#define TP_MIB_FCOE_DROP_0_A	0x4c
+#define TP_MIB_FCOE_BYTE_0_HI_A	0x50
 #define TP_MIB_OFD_VLN_DROP_0_A	0x58
+#define TP_MIB_USM_PKTS_A	0x5c
+#define TP_MIB_RQE_DFR_PKT_A	0x64
 
 #define ULP_TX_INT_CAUSE_A	0x8dcc
 
@@ -1572,6 +1641,7 @@
 #define MPS_PORT_STAT_LB_PORT_1519B_MAX_L 0x520
 #define MPS_PORT_STAT_LB_PORT_1519B_MAX_H 0x524
 #define MPS_PORT_STAT_LB_PORT_DROP_FRAMES 0x528
+#define MPS_PORT_STAT_LB_PORT_DROP_FRAMES_L 0x528
 #define MPS_PORT_STAT_RX_PORT_BYTES_L 0x540
 #define MPS_PORT_STAT_RX_PORT_BYTES_H 0x544
 #define MPS_PORT_STAT_RX_PORT_FRAMES_L 0x548
@@ -2054,6 +2124,11 @@
 #define VFLKPIDX_M    0xffU
 #define VFLKPIDX_G(x) (((x) >> VFLKPIDX_S) & VFLKPIDX_M)
 
+#define T6_VFWRADDR_S    8
+#define T6_VFWRADDR_M    0xffU
+#define T6_VFWRADDR_V(x) ((x) << T6_VFWRADDR_S)
+#define T6_VFWRADDR_G(x) (((x) >> T6_VFWRADDR_S) & T6_VFWRADDR_M)
+
 #define TP_RSS_CONFIG_CNG_A 0x7e04
 #define TP_RSS_SECRET_KEY0_A 0x40
 #define TP_RSS_PF0_CONFIG_A 0x30
@@ -2175,7 +2250,28 @@
 #define MPS_RX_PERR_INT_CAUSE_A 0x11074
 
 #define MPS_CLS_TCAM_Y_L_A 0xf000
+#define MPS_CLS_TCAM_DATA0_A 0xf000
+#define MPS_CLS_TCAM_DATA1_A 0xf004
+
+#define DMACH_S    0
+#define DMACH_M    0xffffU
+#define DMACH_G(x) (((x) >> DMACH_S) & DMACH_M)
+
 #define MPS_CLS_TCAM_X_L_A 0xf008
+#define MPS_CLS_TCAM_DATA2_CTL_A 0xf008
+
+#define CTLCMDTYPE_S    31
+#define CTLCMDTYPE_V(x) ((x) << CTLCMDTYPE_S)
+#define CTLCMDTYPE_F    CTLCMDTYPE_V(1U)
+
+#define CTLTCAMSEL_S    25
+#define CTLTCAMSEL_V(x) ((x) << CTLTCAMSEL_S)
+
+#define CTLTCAMINDEX_S    17
+#define CTLTCAMINDEX_V(x) ((x) << CTLTCAMINDEX_S)
+
+#define CTLXYBITSEL_S    16
+#define CTLXYBITSEL_V(x) ((x) << CTLXYBITSEL_S)
 
 #define MPS_CLS_TCAM_Y_L(idx) (MPS_CLS_TCAM_Y_L_A + (idx) * 16)
 #define NUM_MPS_CLS_TCAM_Y_L_INSTANCES 512
@@ -2184,6 +2280,45 @@
 #define NUM_MPS_CLS_TCAM_X_L_INSTANCES 512
 
 #define MPS_CLS_SRAM_L_A 0xe000
+
+#define T6_MULTILISTEN0_S    26
+
+#define T6_SRAM_PRIO3_S    23
+#define T6_SRAM_PRIO3_M    0x7U
+#define T6_SRAM_PRIO3_G(x) (((x) >> T6_SRAM_PRIO3_S) & T6_SRAM_PRIO3_M)
+
+#define T6_SRAM_PRIO2_S    20
+#define T6_SRAM_PRIO2_M    0x7U
+#define T6_SRAM_PRIO2_G(x) (((x) >> T6_SRAM_PRIO2_S) & T6_SRAM_PRIO2_M)
+
+#define T6_SRAM_PRIO1_S    17
+#define T6_SRAM_PRIO1_M    0x7U
+#define T6_SRAM_PRIO1_G(x) (((x) >> T6_SRAM_PRIO1_S) & T6_SRAM_PRIO1_M)
+
+#define T6_SRAM_PRIO0_S    14
+#define T6_SRAM_PRIO0_M    0x7U
+#define T6_SRAM_PRIO0_G(x) (((x) >> T6_SRAM_PRIO0_S) & T6_SRAM_PRIO0_M)
+
+#define T6_SRAM_VLD_S    13
+#define T6_SRAM_VLD_V(x) ((x) << T6_SRAM_VLD_S)
+#define T6_SRAM_VLD_F    T6_SRAM_VLD_V(1U)
+
+#define T6_REPLICATE_S    12
+#define T6_REPLICATE_V(x) ((x) << T6_REPLICATE_S)
+#define T6_REPLICATE_F    T6_REPLICATE_V(1U)
+
+#define T6_PF_S    9
+#define T6_PF_M    0x7U
+#define T6_PF_G(x) (((x) >> T6_PF_S) & T6_PF_M)
+
+#define T6_VF_VALID_S    8
+#define T6_VF_VALID_V(x) ((x) << T6_VF_VALID_S)
+#define T6_VF_VALID_F    T6_VF_VALID_V(1U)
+
+#define T6_VF_S    0
+#define T6_VF_M    0xffU
+#define T6_VF_G(x) (((x) >> T6_VF_S) & T6_VF_M)
+
 #define MPS_CLS_SRAM_H_A 0xe004
 
 #define MPS_CLS_SRAM_L(idx) (MPS_CLS_SRAM_L_A + (idx) * 8)
@@ -2433,6 +2568,8 @@
 #define CIM_F    CIM_V(1U)
 
 #define MC1_S    31
+#define MC1_V(x) ((x) << MC1_S)
+#define MC1_F    MC1_V(1U)
 
 #define PL_INT_ENABLE_A 0x19410
 #define PL_INT_MAP0_A 0x19414
@@ -2463,6 +2600,18 @@
 #define REV_V(x) ((x) << REV_S)
 #define REV_G(x) (((x) >> REV_S) & REV_M)
 
+#define T6_UNKNOWNCMD_S    3
+#define T6_UNKNOWNCMD_V(x) ((x) << T6_UNKNOWNCMD_S)
+#define T6_UNKNOWNCMD_F    T6_UNKNOWNCMD_V(1U)
+
+#define T6_LIP0_S    2
+#define T6_LIP0_V(x) ((x) << T6_LIP0_S)
+#define T6_LIP0_F    T6_LIP0_V(1U)
+
+#define T6_LIPMISS_S    1
+#define T6_LIPMISS_V(x) ((x) << T6_LIPMISS_S)
+#define T6_LIPMISS_F    T6_LIPMISS_V(1U)
+
 #define LE_DB_INT_CAUSE_A 0x19c3c
 
 #define REQQPARERR_S    16
@@ -2485,6 +2634,14 @@
 #define LIP0_V(x) ((x) << LIP0_S)
 #define LIP0_F    LIP0_V(1U)
 
+#define TCAMINTPERR_S    13
+#define TCAMINTPERR_V(x) ((x) << TCAMINTPERR_S)
+#define TCAMINTPERR_F    TCAMINTPERR_V(1U)
+
+#define SSRAMINTPERR_S    10
+#define SSRAMINTPERR_V(x) ((x) << SSRAMINTPERR_S)
+#define SSRAMINTPERR_F    SSRAMINTPERR_V(1U)
+
 #define NCSI_INT_CAUSE_A 0x1a0d8
 
 #define CIM_DM_PRTY_ERR_S    8
@@ -2638,6 +2795,33 @@
 
 #define CIM_IBQ_DBG_DATA_A 0x7b68
 #define CIM_OBQ_DBG_DATA_A 0x7b6c
+#define CIM_DEBUGCFG_A 0x7b70
+#define CIM_DEBUGSTS_A 0x7b74
+
+#define POLADBGRDPTR_S		23
+#define POLADBGRDPTR_M		0x1ffU
+#define POLADBGRDPTR_V(x)	((x) << POLADBGRDPTR_S)
+
+#define POLADBGWRPTR_S		16
+#define POLADBGWRPTR_M		0x1ffU
+#define POLADBGWRPTR_G(x)	(((x) >> POLADBGWRPTR_S) & POLADBGWRPTR_M)
+
+#define PILADBGRDPTR_S		14
+#define PILADBGRDPTR_M		0x1ffU
+#define PILADBGRDPTR_V(x)	((x) << PILADBGRDPTR_S)
+
+#define PILADBGWRPTR_S		0
+#define PILADBGWRPTR_M		0x1ffU
+#define PILADBGWRPTR_G(x)	(((x) >> PILADBGWRPTR_S) & PILADBGWRPTR_M)
+
+#define LADBGEN_S	12
+#define LADBGEN_V(x)	((x) << LADBGEN_S)
+#define LADBGEN_F	LADBGEN_V(1U)
+
+#define CIM_PO_LA_DEBUGDATA_A 0x7b78
+#define CIM_PI_LA_DEBUGDATA_A 0x7b7c
+#define CIM_PO_LA_MADEBUGDATA_A	0x7b80
+#define CIM_PI_LA_MADEBUGDATA_A	0x7b84
 
 #define UPDBGLARDEN_S		1
 #define UPDBGLARDEN_V(x)	((x) << UPDBGLARDEN_S)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index 19b2dcf6acde..7bdee3bf75ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -61,6 +61,30 @@
 #define SGE_TIMERREGS			6
 #define TIMERREG_COUNTER0_X		0
 
+#define FETCHBURSTMIN_64B_X		2
+
+#define FETCHBURSTMAX_256B_X		2
+#define FETCHBURSTMAX_512B_X		3
+
+#define HOSTFCMODE_STATUS_PAGE_X	2
+
+#define CIDXFLUSHTHRESH_32_X		5
+
+#define UPDATEDELIVERY_INTERRUPT_X	1
+
+#define RSPD_TYPE_FLBUF_X		0
+#define RSPD_TYPE_CPL_X			1
+#define RSPD_TYPE_INTR_X		2
+
+/* Congestion Manager Definitions.
+ */
+#define CONMCTXT_CNGTPMODE_S		19
+#define CONMCTXT_CNGTPMODE_V(x)		((x) << CONMCTXT_CNGTPMODE_S)
+#define CONMCTXT_CNGCHMAP_S		0
+#define CONMCTXT_CNGCHMAP_V(x)		((x) << CONMCTXT_CNGCHMAP_S)
+#define CONMCTXT_CNGTPMODE_CHANNEL_X	2
+#define CONMCTXT_CNGTPMODE_QUEUE_X	1
+
 /* T5 and later support a new BAR2-based doorbell mechanism for Egress Queues.
  * The User Doorbells are each 128 bytes in length with a Simple Doorbell at
  * offsets 8x and a Write Combining single 64-byte Egress Queue Unit
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 03fbfd1fb3df..ab4674684acc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -772,7 +772,7 @@ struct fw_ldst_cmd {
 		} addrval;
 		struct fw_ldst_idctxt {
 			__be32 physid;
-			__be32 msg_pkd;
+			__be32 msg_ctxtflush;
 			__be32 ctxt_data7;
 			__be32 ctxt_data6;
 			__be32 ctxt_data5;
@@ -788,15 +788,27 @@ struct fw_ldst_cmd {
 			__be16 vctl;
 			__be16 rval;
 		} mdio;
-		struct fw_ldst_mps {
-			__be16 fid_ctl;
-			__be16 rplcpf_pkd;
-			__be32 rplc127_96;
-			__be32 rplc95_64;
-			__be32 rplc63_32;
-			__be32 rplc31_0;
-			__be32 atrb;
-			__be16 vlan[16];
+		union fw_ldst_mps {
+			struct fw_ldst_mps_rplc {
+				__be16 fid_idx;
+				__be16 rplcpf_pkd;
+				__be32 rplc255_224;
+				__be32 rplc223_192;
+				__be32 rplc191_160;
+				__be32 rplc159_128;
+				__be32 rplc127_96;
+				__be32 rplc95_64;
+				__be32 rplc63_32;
+				__be32 rplc31_0;
+			} rplc;
+			struct fw_ldst_mps_atrb {
+				__be16 fid_mpsid;
+				__be16 r2[3];
+				__be32 r3[2];
+				__be32 r4;
+				__be32 atrb;
+				__be16 vlan[16];
+			} atrb;
 		} mps;
 		struct fw_ldst_func {
 			u8 access_ctl;
@@ -822,6 +834,10 @@ struct fw_ldst_cmd {
 #define FW_LDST_CMD_MSG_S       31
 #define FW_LDST_CMD_MSG_V(x)	((x) << FW_LDST_CMD_MSG_S)
 
+#define FW_LDST_CMD_CTXTFLUSH_S		30
+#define FW_LDST_CMD_CTXTFLUSH_V(x)	((x) << FW_LDST_CMD_CTXTFLUSH_S)
+#define FW_LDST_CMD_CTXTFLUSH_F		FW_LDST_CMD_CTXTFLUSH_V(1U)
+
 #define FW_LDST_CMD_PADDR_S     8
 #define FW_LDST_CMD_PADDR_V(x)	((x) << FW_LDST_CMD_PADDR_S)
 
@@ -831,8 +847,8 @@ struct fw_ldst_cmd {
 #define FW_LDST_CMD_FID_S       15
 #define FW_LDST_CMD_FID_V(x)	((x) << FW_LDST_CMD_FID_S)
 
-#define FW_LDST_CMD_CTL_S       0
-#define FW_LDST_CMD_CTL_V(x)	((x) << FW_LDST_CMD_CTL_S)
+#define FW_LDST_CMD_IDX_S	0
+#define FW_LDST_CMD_IDX_V(x)	((x) << FW_LDST_CMD_IDX_S)
 
 #define FW_LDST_CMD_RPLCPF_S    0
 #define FW_LDST_CMD_RPLCPF_V(x)	((x) << FW_LDST_CMD_RPLCPF_S)
@@ -1061,6 +1077,7 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_FWREV = 0x0B,
 	FW_PARAMS_PARAM_DEV_TPREV = 0x0C,
 	FW_PARAMS_PARAM_DEV_CF = 0x0D,
+	FW_PARAMS_PARAM_DEV_PHYFW = 0x0F,
 	FW_PARAMS_PARAM_DEV_DIAG = 0x11,
 	FW_PARAMS_PARAM_DEV_MAXORDIRD_QP = 0x13, /* max supported QP IRD/ORD */
 	FW_PARAMS_PARAM_DEV_MAXIRD_ADAPTER = 0x14, /* max supported adap IRD */
@@ -1123,6 +1140,12 @@ enum fw_params_param_dmaq {
 	FW_PARAMS_PARAM_DMAQ_EQ_CMPLIQID_CTRL = 0x11,
 	FW_PARAMS_PARAM_DMAQ_EQ_SCHEDCLASS_ETH = 0x12,
 	FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH = 0x13,
+	FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20,
+};
+
+enum fw_params_param_dev_phyfw {
+	FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD = 0x00,
+	FW_PARAMS_PARAM_DEV_PHYFW_VERSION = 0x01,
 };
 
 enum fw_params_param_dev_diag {
@@ -1377,6 +1400,7 @@ struct fw_iq_cmd {
 
 #define FW_IQ_CMD_IQFLINTCONGEN_S	27
 #define FW_IQ_CMD_IQFLINTCONGEN_V(x)	((x) << FW_IQ_CMD_IQFLINTCONGEN_S)
+#define FW_IQ_CMD_IQFLINTCONGEN_F	FW_IQ_CMD_IQFLINTCONGEN_V(1U)
 
 #define FW_IQ_CMD_IQFLINTISCSIC_S	26
 #define FW_IQ_CMD_IQFLINTISCSIC_V(x)	((x) << FW_IQ_CMD_IQFLINTISCSIC_S)
@@ -1399,6 +1423,7 @@ struct fw_iq_cmd {
 
 #define FW_IQ_CMD_FL0CONGCIF_S		11
 #define FW_IQ_CMD_FL0CONGCIF_V(x)	((x) << FW_IQ_CMD_FL0CONGCIF_S)
+#define FW_IQ_CMD_FL0CONGCIF_F		FW_IQ_CMD_FL0CONGCIF_V(1U)
 
 #define FW_IQ_CMD_FL0ONCHIP_S		10
 #define FW_IQ_CMD_FL0ONCHIP_V(x)	((x) << FW_IQ_CMD_FL0ONCHIP_S)
@@ -1589,6 +1614,7 @@ struct fw_eq_eth_cmd {
 
 #define FW_EQ_ETH_CMD_FETCHRO_S		22
 #define FW_EQ_ETH_CMD_FETCHRO_V(x)	((x) << FW_EQ_ETH_CMD_FETCHRO_S)
+#define FW_EQ_ETH_CMD_FETCHRO_F		FW_EQ_ETH_CMD_FETCHRO_V(1U)
 
 #define FW_EQ_ETH_CMD_HOSTFCMODE_S	20
 #define FW_EQ_ETH_CMD_HOSTFCMODE_V(x)	((x) << FW_EQ_ETH_CMD_HOSTFCMODE_S)
@@ -2526,13 +2552,8 @@ enum fw_port_mod_sub_type {
 	FW_PORT_MOD_SUB_TYPE_TWINAX_7 = 0xC,
 };
 
-/* port stats */
-#define FW_NUM_PORT_STATS 50
-#define FW_NUM_PORT_TX_STATS 23
-#define FW_NUM_PORT_RX_STATS 27
-
 enum fw_port_stats_tx_index {
-	FW_STAT_TX_PORT_BYTES_IX,
+	FW_STAT_TX_PORT_BYTES_IX = 0,
 	FW_STAT_TX_PORT_FRAMES_IX,
 	FW_STAT_TX_PORT_BCAST_IX,
 	FW_STAT_TX_PORT_MCAST_IX,
@@ -2554,11 +2575,12 @@ enum fw_port_stats_tx_index {
 	FW_STAT_TX_PORT_PPP4_IX,
 	FW_STAT_TX_PORT_PPP5_IX,
 	FW_STAT_TX_PORT_PPP6_IX,
-	FW_STAT_TX_PORT_PPP7_IX
+	FW_STAT_TX_PORT_PPP7_IX,
+	FW_NUM_PORT_TX_STATS
 };
 
 enum fw_port_stat_rx_index {
-	FW_STAT_RX_PORT_BYTES_IX,
+	FW_STAT_RX_PORT_BYTES_IX = 0,
 	FW_STAT_RX_PORT_FRAMES_IX,
 	FW_STAT_RX_PORT_BCAST_IX,
 	FW_STAT_RX_PORT_MCAST_IX,
@@ -2584,9 +2606,14 @@ enum fw_port_stat_rx_index {
 	FW_STAT_RX_PORT_PPP5_IX,
 	FW_STAT_RX_PORT_PPP6_IX,
 	FW_STAT_RX_PORT_PPP7_IX,
-	FW_STAT_RX_PORT_LESS_64B_IX
+	FW_STAT_RX_PORT_LESS_64B_IX,
+	FW_STAT_RX_PORT_MAC_ERROR_IX,
+	FW_NUM_PORT_RX_STATS
 };
 
+/* port stats */
+#define FW_NUM_PORT_STATS (FW_NUM_PORT_TX_STATS + FW_NUM_PORT_RX_STATS)
+
 struct fw_port_stats_cmd {
 	__be32 op_to_portid;
 	__be32 retval_len16;
@@ -3015,7 +3042,8 @@ struct fw_hdr {
 
 enum fw_hdr_chip {
 	FW_HDR_CHIP_T4,
-	FW_HDR_CHIP_T5
+	FW_HDR_CHIP_T5,
+	FW_HDR_CHIP_T6
 };
 
 #define FW_HDR_FW_VER_MAJOR_S	24
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index b9d1cbac0eee..32b213559b02 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -45,4 +45,9 @@
 #define T5FW_VERSION_MICRO 0x20
 #define T5FW_VERSION_BUILD 0x00
 
+#define T6FW_VERSION_MAJOR 0x01
+#define T6FW_VERSION_MINOR 0x0D
+#define T6FW_VERSION_MICRO 0x2D
+#define T6FW_VERSION_BUILD 0x00
+
 #endif
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 1d893b0b7ddf..b2b5e5bbe04c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1021,7 +1021,7 @@ static int closest_thres(const struct sge *s, int thres)
 static unsigned int qtimer_val(const struct adapter *adapter,
 			       const struct sge_rspq *rspq)
 {
-	unsigned int timer_idx = QINTR_TIMER_IDX_GET(rspq->intr_params);
+	unsigned int timer_idx = QINTR_TIMER_IDX_G(rspq->intr_params);
 
 	return timer_idx < SGE_NTIMERS
 		? adapter->sge.timer_val[timer_idx]
@@ -1086,8 +1086,8 @@ static int set_rxq_intr_params(struct adapter *adapter, struct sge_rspq *rspq,
 	 * Update the response queue's interrupt coalescing parameters and
 	 * return success.
 	 */
-	rspq->intr_params = (QINTR_TIMER_IDX(timer_idx) |
-			     (cnt > 0 ? QINTR_CNT_EN : 0));
+	rspq->intr_params = (QINTR_TIMER_IDX_V(timer_idx) |
+			     QINTR_CNT_EN_V(cnt > 0));
 	return 0;
 }
 
@@ -1439,7 +1439,7 @@ static int cxgb4vf_get_coalesce(struct net_device *dev,
 
 	coalesce->rx_coalesce_usecs = qtimer_val(adapter, rspq);
 	coalesce->rx_max_coalesced_frames =
-		((rspq->intr_params & QINTR_CNT_EN)
+		((rspq->intr_params & QINTR_CNT_EN_F)
 		 ? adapter->sge.counter_val[rspq->pktcnt_idx]
 		 : 0);
 	return 0;
@@ -2393,8 +2393,9 @@ static inline void init_rspq(struct sge_rspq *rspq, u8 timer_idx,
 			     u8 pkt_cnt_idx, unsigned int size,
 			     unsigned int iqe_size)
 {
-	rspq->intr_params = (QINTR_TIMER_IDX(timer_idx) |
-			     (pkt_cnt_idx < SGE_NCOUNTERS ? QINTR_CNT_EN : 0));
+	rspq->intr_params = (QINTR_TIMER_IDX_V(timer_idx) |
+			     (pkt_cnt_idx < SGE_NCOUNTERS ?
+			      QINTR_CNT_EN_F : 0));
 	rspq->pktcnt_idx = (pkt_cnt_idx < SGE_NCOUNTERS
 			    ? pkt_cnt_idx
 			    : 0);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 482f6de6817d..ad53e5ad2acd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -524,7 +524,7 @@ static void unmap_rx_buf(struct adapter *adapter, struct sge_fl *fl)
  */
 static inline void ring_fl_db(struct adapter *adapter, struct sge_fl *fl)
 {
-	u32 val;
+	u32 val = adapter->params.arch.sge_fl_db;
 
 	/* The SGE keeps track of its Producer and Consumer Indices in terms
 	 * of Egress Queue Units so we can only tell it about integral numbers
@@ -532,11 +532,9 @@ static inline void ring_fl_db(struct adapter *adapter, struct sge_fl *fl)
 	 */
 	if (fl->pend_cred >= FL_PER_EQ_UNIT) {
 		if (is_t4(adapter->params.chip))
-			val = PIDX_V(fl->pend_cred / FL_PER_EQ_UNIT);
+			val |= PIDX_V(fl->pend_cred / FL_PER_EQ_UNIT);
 		else
-			val = PIDX_T5_V(fl->pend_cred / FL_PER_EQ_UNIT) |
-			      DBTYPE_F;
-		val |= DBPRIO_F;
+			val |= PIDX_T5_V(fl->pend_cred / FL_PER_EQ_UNIT);
 
 		/* Make sure all memory writes to the Free List queue are
 		 * committed before we tell the hardware about them.
@@ -1084,7 +1082,7 @@ static void inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *tq,
  * Figure out what HW csum a packet wants and return the appropriate control
  * bits.
  */
-static u64 hwcsum(const struct sk_buff *skb)
+static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb)
 {
 	int csum_type;
 	const struct iphdr *iph = ip_hdr(skb);
@@ -1100,7 +1098,7 @@ nocsum:
 			 * unknown protocol, disable HW csum
 			 * and hope a bad packet is detected
 			 */
-			return TXPKT_L4CSUM_DIS;
+			return TXPKT_L4CSUM_DIS_F;
 		}
 	} else {
 		/*
@@ -1116,16 +1114,21 @@ nocsum:
 			goto nocsum;
 	}
 
-	if (likely(csum_type >= TX_CSUM_TCPIP))
-		return TXPKT_CSUM_TYPE(csum_type) |
-			TXPKT_IPHDR_LEN(skb_network_header_len(skb)) |
-			TXPKT_ETHHDR_LEN(skb_network_offset(skb) - ETH_HLEN);
-	else {
+	if (likely(csum_type >= TX_CSUM_TCPIP)) {
+		u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb));
+		int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN;
+
+		if (chip <= CHELSIO_T5)
+			hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len);
+		else
+			hdr_len |= T6_TXPKT_ETHHDR_LEN_V(eth_hdr_len);
+		return TXPKT_CSUM_TYPE_V(csum_type) | hdr_len;
+	} else {
 		int start = skb_transport_offset(skb);
 
-		return TXPKT_CSUM_TYPE(csum_type) |
-			TXPKT_CSUM_START(start) |
-			TXPKT_CSUM_LOC(start + skb->csum_offset);
+		return TXPKT_CSUM_TYPE_V(csum_type) |
+			TXPKT_CSUM_START_V(start) |
+			TXPKT_CSUM_LOC_V(start + skb->csum_offset);
 	}
 }
 
@@ -1160,7 +1163,7 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u32 wr_mid;
 	u64 cntrl, *end;
-	int qidx, credits;
+	int qidx, credits, max_pkt_len;
 	unsigned int flits, ndesc;
 	struct adapter *adapter;
 	struct sge_eth_txq *txq;
@@ -1183,6 +1186,13 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb->len < fw_hdr_copy_len))
 		goto out_free;
 
+	/* Discard the packet if the length is greater than mtu */
+	max_pkt_len = ETH_HLEN + dev->mtu;
+	if (skb_vlan_tag_present(skb))
+		max_pkt_len += VLAN_HLEN;
+	if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len)))
+		goto out_free;
+
 	/*
 	 * Figure out which TX Queue we're going to use.
 	 */
@@ -1281,29 +1291,35 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * Fill in the LSO CPL message.
 		 */
 		lso->lso_ctrl =
-			cpu_to_be32(LSO_OPCODE(CPL_TX_PKT_LSO) |
-				    LSO_FIRST_SLICE |
-				    LSO_LAST_SLICE |
-				    LSO_IPV6(v6) |
-				    LSO_ETHHDR_LEN(eth_xtra_len/4) |
-				    LSO_IPHDR_LEN(l3hdr_len/4) |
-				    LSO_TCPHDR_LEN(tcp_hdr(skb)->doff));
+			cpu_to_be32(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+				    LSO_FIRST_SLICE_F |
+				    LSO_LAST_SLICE_F |
+				    LSO_IPV6_V(v6) |
+				    LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+				    LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+				    LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
 		lso->ipid_ofst = cpu_to_be16(0);
 		lso->mss = cpu_to_be16(ssi->gso_size);
 		lso->seqno_offset = cpu_to_be32(0);
 		if (is_t4(adapter->params.chip))
 			lso->len = cpu_to_be32(skb->len);
 		else
-			lso->len = cpu_to_be32(LSO_T5_XFER_SIZE(skb->len));
+			lso->len = cpu_to_be32(LSO_T5_XFER_SIZE_V(skb->len));
 
 		/*
 		 * Set up TX Packet CPL pointer, control word and perform
 		 * accounting.
 		 */
 		cpl = (void *)(lso + 1);
-		cntrl = (TXPKT_CSUM_TYPE(v6 ? TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
-			 TXPKT_IPHDR_LEN(l3hdr_len) |
-			 TXPKT_ETHHDR_LEN(eth_xtra_len));
+
+		if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+			cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+		else
+			cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+
+		cntrl |= TXPKT_CSUM_TYPE_V(v6 ?
+					   TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
+			 TXPKT_IPHDR_LEN_V(l3hdr_len);
 		txq->tso++;
 		txq->tx_cso += ssi->gso_segs;
 	} else {
@@ -1320,10 +1336,11 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		 */
 		cpl = (void *)(wr + 1);
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			cntrl = hwcsum(skb) | TXPKT_IPCSUM_DIS;
+			cntrl = hwcsum(adapter->params.chip, skb) |
+				TXPKT_IPCSUM_DIS_F;
 			txq->tx_cso++;
 		} else
-			cntrl = TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS;
+			cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
 	}
 
 	/*
@@ -1332,15 +1349,15 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	if (skb_vlan_tag_present(skb)) {
 		txq->vlan_ins++;
-		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(skb_vlan_tag_get(skb));
+		cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
 	}
 
 	/*
 	 * Fill in the TX Packet CPL message header.
 	 */
-	cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE(CPL_TX_PKT_XT) |
-				 TXPKT_INTF(pi->port_id) |
-				 TXPKT_PF(0));
+	cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE_V(CPL_TX_PKT_XT) |
+				 TXPKT_INTF_V(pi->port_id) |
+				 TXPKT_PF_V(0));
 	cpl->pack = cpu_to_be16(0);
 	cpl->len = cpu_to_be16(skb->len);
 	cpl->ctrl1 = cpu_to_be64(cntrl);
@@ -1663,7 +1680,7 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 static inline bool is_new_response(const struct rsp_ctrl *rc,
 				   const struct sge_rspq *rspq)
 {
-	return RSPD_GEN(rc->type_gen) == rspq->gen;
+	return ((rc->type_gen >> RSPD_GEN_S) & 0x1) == rspq->gen;
 }
 
 /**
@@ -1752,8 +1769,8 @@ static int process_responses(struct sge_rspq *rspq, int budget)
 		 * SGE.
 		 */
 		dma_rmb();
-		rsp_type = RSPD_TYPE(rc->type_gen);
-		if (likely(rsp_type == RSP_TYPE_FLBUF)) {
+		rsp_type = RSPD_TYPE_G(rc->type_gen);
+		if (likely(rsp_type == RSPD_TYPE_FLBUF_X)) {
 			struct page_frag *fp;
 			struct pkt_gl gl;
 			const struct rx_sw_desc *sdesc;
@@ -1764,7 +1781,7 @@ static int process_responses(struct sge_rspq *rspq, int budget)
 			 * If we get a "new buffer" message from the SGE we
 			 * need to move on to the next Free List buffer.
 			 */
-			if (len & RSPD_NEWBUF) {
+			if (len & RSPD_NEWBUF_F) {
 				/*
 				 * We get one "new buffer" message when we
 				 * first start up a queue so we need to ignore
@@ -1775,7 +1792,7 @@ static int process_responses(struct sge_rspq *rspq, int budget)
 						     1);
 					rspq->offset = 0;
 				}
-				len = RSPD_LEN(len);
+				len = RSPD_LEN_G(len);
 			}
 			gl.tot_len = len;
 
@@ -1818,10 +1835,10 @@ static int process_responses(struct sge_rspq *rspq, int budget)
 				rspq->offset += ALIGN(fp->size, s->fl_align);
 			else
 				restore_rx_bufs(&gl, &rxq->fl, frag);
-		} else if (likely(rsp_type == RSP_TYPE_CPL)) {
+		} else if (likely(rsp_type == RSPD_TYPE_CPL_X)) {
 			ret = rspq->handler(rspq, rspq->cur_desc, NULL);
 		} else {
-			WARN_ON(rsp_type > RSP_TYPE_CPL);
+			WARN_ON(rsp_type > RSPD_TYPE_CPL_X);
 			ret = 0;
 		}
 
@@ -1833,7 +1850,7 @@ static int process_responses(struct sge_rspq *rspq, int budget)
 			 */
 			const int NOMEM_TIMER_IDX = SGE_NTIMERS-1;
 			rspq->next_intr_params =
-				QINTR_TIMER_IDX(NOMEM_TIMER_IDX);
+				QINTR_TIMER_IDX_V(NOMEM_TIMER_IDX);
 			break;
 		}
 
@@ -1875,7 +1892,7 @@ static int napi_rx_handler(struct napi_struct *napi, int budget)
 		intr_params = rspq->next_intr_params;
 		rspq->next_intr_params = rspq->intr_params;
 	} else
-		intr_params = QINTR_TIMER_IDX(SGE_TIMER_UPD_CIDX);
+		intr_params = QINTR_TIMER_IDX_V(SGE_TIMER_UPD_CIDX);
 
 	if (unlikely(work_done == 0))
 		rspq->unhandled_irqs++;
@@ -1936,10 +1953,10 @@ static unsigned int process_intrq(struct adapter *adapter)
 		 * never happen ...
 		 */
 		dma_rmb();
-		if (unlikely(RSPD_TYPE(rc->type_gen) != RSP_TYPE_INTR)) {
+		if (unlikely(RSPD_TYPE_G(rc->type_gen) != RSPD_TYPE_INTR_X)) {
 			dev_err(adapter->pdev_dev,
 				"Unexpected INTRQ response type %d\n",
-				RSPD_TYPE(rc->type_gen));
+				RSPD_TYPE_G(rc->type_gen));
 			continue;
 		}
 
@@ -1951,7 +1968,7 @@ static unsigned int process_intrq(struct adapter *adapter)
 		 * want to either make them fatal and/or conditionalized under
 		 * DEBUG.
 		 */
-		qid = RSPD_QID(be32_to_cpu(rc->pldbuflen_qid));
+		qid = RSPD_QID_G(be32_to_cpu(rc->pldbuflen_qid));
 		iq_idx = IQ_IDX(s, qid);
 		if (unlikely(iq_idx >= MAX_INGQ)) {
 			dev_err(adapter->pdev_dev,
@@ -2154,8 +2171,8 @@ static void __iomem *bar2_address(struct adapter *adapter,
 	u64 bar2_qoffset;
 	int ret;
 
-	ret = t4_bar2_sge_qregs(adapter, qid, qtype,
-				&bar2_qoffset, pbar2_qid);
+	ret = t4vf_bar2_sge_qregs(adapter, qid, qtype,
+				  &bar2_qoffset, pbar2_qid);
 	if (ret)
 		return NULL;
 
@@ -2239,12 +2256,18 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	cmd.iqaddr = cpu_to_be64(rspq->phys_addr);
 
 	if (fl) {
+		enum chip_type chip =
+			CHELSIO_CHIP_VERSION(adapter->params.chip);
 		/*
 		 * Allocate the ring for the hardware free list (with space
 		 * for its status page) along with the associated software
 		 * descriptor ring.  The free list size needs to be a multiple
-		 * of the Egress Queue Unit.
+		 * of the Egress Queue Unit and at least 2 Egress Units larger
+		 * than the SGE's Egress Congrestion Threshold
+		 * (fl_starve_thres - 1).
 		 */
+		if (fl->size < s->fl_starve_thres - 1 + 2 * FL_PER_EQ_UNIT)
+			fl->size = s->fl_starve_thres - 1 + 2 * FL_PER_EQ_UNIT;
 		fl->size = roundup(fl->size, FL_PER_EQ_UNIT);
 		fl->desc = alloc_ring(adapter->pdev_dev, fl->size,
 				      sizeof(__be64), sizeof(struct rx_sw_desc),
@@ -2274,7 +2297,9 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 		cmd.fl0dcaen_to_fl0cidxfthresh =
 			cpu_to_be16(
 				FW_IQ_CMD_FL0FBMIN_V(SGE_FETCHBURSTMIN_64B) |
-				FW_IQ_CMD_FL0FBMAX_V(SGE_FETCHBURSTMAX_512B));
+				FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+						     FETCHBURSTMAX_512B_X :
+						     FETCHBURSTMAX_256B_X));
 		cmd.fl0size = cpu_to_be16(flsz);
 		cmd.fl0addr = cpu_to_be64(fl->addr);
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
index b9debb4f29a3..88b8981b4751 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h
@@ -51,6 +51,7 @@
  */
 #define CHELSIO_T4		0x4
 #define CHELSIO_T5		0x5
+#define CHELSIO_T6		0x6
 
 enum chip_type {
 	T4_A1 = CHELSIO_CHIP_CODE(CHELSIO_T4, 1),
@@ -156,6 +157,12 @@ struct vpd_params {
 	u32 cclk;			/* Core Clock (KHz) */
 };
 
+/* Stores chip specific parameters */
+struct arch_specific_params {
+	u32 sge_fl_db;
+	u16 mps_tcam_size;
+};
+
 /*
  * Global Receive Side Scaling (RSS) parameters in host-native format.
  */
@@ -215,6 +222,7 @@ struct adapter_params {
 	struct vpd_params vpd;		/* Vital Product Data */
 	struct rss_params rss;		/* Receive Side Scaling */
 	struct vf_resources vfres;	/* Virtual Function Resource limits */
+	struct arch_specific_params arch; /* chip specific params */
 	enum chip_type chip;		/* chip code */
 	u8 nports;			/* # of Ethernet "ports" */
 };
@@ -284,11 +292,11 @@ int t4vf_fw_reset(struct adapter *);
 int t4vf_set_params(struct adapter *, unsigned int, const u32 *, const u32 *);
 
 enum t4_bar2_qtype { T4_BAR2_QTYPE_EGRESS, T4_BAR2_QTYPE_INGRESS };
-int t4_bar2_sge_qregs(struct adapter *adapter,
-		      unsigned int qid,
-		      enum t4_bar2_qtype qtype,
-		      u64 *pbar2_qoffset,
-		      unsigned int *pbar2_qid);
+int t4vf_bar2_sge_qregs(struct adapter *adapter,
+			unsigned int qid,
+			enum t4_bar2_qtype qtype,
+			u64 *pbar2_qoffset,
+			unsigned int *pbar2_qid);
 
 int t4vf_get_sge_params(struct adapter *);
 int t4vf_get_vpd_params(struct adapter *);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 966ee900ed00..0db6dc9e9ed2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -428,7 +428,7 @@ int t4vf_set_params(struct adapter *adapter, unsigned int nparams,
 }
 
 /**
- *	t4_bar2_sge_qregs - return BAR2 SGE Queue register information
+ *	t4vf_bar2_sge_qregs - return BAR2 SGE Queue register information
  *	@adapter: the adapter
  *	@qid: the Queue ID
  *	@qtype: the Ingress or Egress type for @qid
@@ -452,11 +452,11 @@ int t4vf_set_params(struct adapter *adapter, unsigned int nparams,
  *	Write Combining Doorbell Buffer. If the BAR2 Queue ID is not 0,
  *	then these "Inferred Queue ID" register may not be used.
  */
-int t4_bar2_sge_qregs(struct adapter *adapter,
-		      unsigned int qid,
-		      enum t4_bar2_qtype qtype,
-		      u64 *pbar2_qoffset,
-		      unsigned int *pbar2_qid)
+int t4vf_bar2_sge_qregs(struct adapter *adapter,
+			unsigned int qid,
+			enum t4_bar2_qtype qtype,
+			u64 *pbar2_qoffset,
+			unsigned int *pbar2_qid)
 {
 	unsigned int page_shift, page_size, qpp_shift, qpp_mask;
 	u64 bar2_page_offset, bar2_qoffset;
@@ -1191,9 +1191,7 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free,
 	unsigned nfilters = 0;
 	unsigned int rem = naddr;
 	struct fw_vi_mac_cmd cmd, rpl;
-	unsigned int max_naddr = is_t4(adapter->params.chip) ?
-				 NUM_MPS_CLS_SRAM_L_INSTANCES :
-				 NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+	unsigned int max_naddr = adapter->params.arch.mps_tcam_size;
 
 	if (naddr > max_naddr)
 		return -EINVAL;
@@ -1285,9 +1283,7 @@ int t4vf_change_mac(struct adapter *adapter, unsigned int viid,
 	struct fw_vi_mac_exact *p = &cmd.u.exact[0];
 	size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
 					     u.exact[1]), 16);
-	unsigned int max_naddr = is_t4(adapter->params.chip) ?
-				 NUM_MPS_CLS_SRAM_L_INSTANCES :
-				 NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+	unsigned int max_mac_addr = adapter->params.arch.mps_tcam_size;
 
 	/*
 	 * If this is a new allocation, determine whether it should be
@@ -1310,7 +1306,7 @@ int t4vf_change_mac(struct adapter *adapter, unsigned int viid,
 	if (ret == 0) {
 		p = &rpl.u.exact[0];
 		ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
-		if (ret >= max_naddr)
+		if (ret >= max_mac_addr)
 			ret = -ENOMEM;
 	}
 	return ret;
@@ -1590,11 +1586,25 @@ int t4vf_prep_adapter(struct adapter *adapter)
 	switch (CHELSIO_PCI_ID_VER(adapter->pdev->device)) {
 	case CHELSIO_T4:
 		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T4, 0);
+		adapter->params.arch.sge_fl_db = DBPRIO_F;
+		adapter->params.arch.mps_tcam_size =
+				NUM_MPS_CLS_SRAM_L_INSTANCES;
 		break;
 
 	case CHELSIO_T5:
 		chipid = REV_G(t4_read_reg(adapter, PL_VF_REV_A));
 		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T5, chipid);
+		adapter->params.arch.sge_fl_db = DBPRIO_F | DBTYPE_F;
+		adapter->params.arch.mps_tcam_size =
+				NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
+		break;
+
+	case CHELSIO_T6:
+		chipid = REV_G(t4_read_reg(adapter, PL_VF_REV_A));
+		adapter->params.chip |= CHELSIO_CHIP_CODE(CHELSIO_T6, chipid);
+		adapter->params.arch.sge_fl_db = 0;
+		adapter->params.arch.mps_tcam_size =
+				NUM_MPS_T5_CLS_SRAM_L_INSTANCES;
 		break;
 	}
 
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 905ac5f5d9a6..5ab912937aff 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_CIRRUS
 	default y
 	depends on ISA || EISA || ARM || MAC
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -23,9 +21,7 @@ config CS89x0
 	depends on ISA || EISA || ARM
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
-	  network (Ethernet) card of this type, say Y and read the
-	  Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto> as well as
+	  network (Ethernet) card of this type, say Y and read the file
 	  <file:Documentation/networking/cs89x0.txt>.
 
 	  To compile this driver as a module, choose M here. The module
@@ -55,9 +51,7 @@ config MAC89x0
 	depends on MAC
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards.  If you have a
-	  Nubus or LC-PDS network (Ethernet) card of this type, say Y and
-	  read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  Nubus or LC-PDS network (Ethernet) card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. This module will
 	  be called mac89x0.
diff --git a/drivers/net/ethernet/cisco/Kconfig b/drivers/net/ethernet/cisco/Kconfig
index 1c7b884e3371..15b713a89620 100644
--- a/drivers/net/ethernet/cisco/Kconfig
+++ b/drivers/net/ethernet/cisco/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_CISCO
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
index 0be6850be8a2..d106186f4f4a 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.c
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -5,7 +5,7 @@
 #include <linux/in.h>
 #include <linux/types.h>
 #include <linux/skbuff.h>
-#include <net/flow_keys.h>
+#include <net/flow_dissector.h>
 #include "enic_res.h"
 #include "enic_clsf.h"
 
@@ -15,14 +15,14 @@
  *	@rq: rq number to steer to
  *
  * This function returns filter_id(hardware_id) of the filter
- * added. In case of error it returns an negative number.
+ * added. In case of error it returns a negative number.
  */
 int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 {
 	int res;
 	struct filter data;
 
-	switch (keys->ip_proto) {
+	switch (keys->basic.ip_proto) {
 	case IPPROTO_TCP:
 		data.u.ipv4.protocol = PROTO_TCP;
 		break;
@@ -33,10 +33,10 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 		return -EPROTONOSUPPORT;
 	};
 	data.type = FILTER_IPV4_5TUPLE;
-	data.u.ipv4.src_addr = ntohl(keys->src);
-	data.u.ipv4.dst_addr = ntohl(keys->dst);
-	data.u.ipv4.src_port = ntohs(keys->port16[0]);
-	data.u.ipv4.dst_port = ntohs(keys->port16[1]);
+	data.u.ipv4.src_addr = ntohl(keys->addrs.v4addrs.src);
+	data.u.ipv4.dst_addr = ntohl(keys->addrs.v4addrs.dst);
+	data.u.ipv4.src_port = ntohs(keys->ports.src);
+	data.u.ipv4.dst_port = ntohs(keys->ports.dst);
 	data.u.ipv4.flags = FILTER_FIELDS_IPV4_5TUPLE;
 
 	spin_lock_bh(&enic->devcmd_lock);
@@ -158,11 +158,11 @@ static struct enic_rfs_fltr_node *htbl_key_search(struct hlist_head *h,
 	struct enic_rfs_fltr_node *tpos;
 
 	hlist_for_each_entry(tpos, h, node)
-		if (tpos->keys.src == k->src &&
-		    tpos->keys.dst == k->dst &&
-		    tpos->keys.ports == k->ports &&
-		    tpos->keys.ip_proto == k->ip_proto &&
-		    tpos->keys.n_proto == k->n_proto)
+		if (tpos->keys.addrs.v4addrs.src == k->addrs.v4addrs.src &&
+		    tpos->keys.addrs.v4addrs.dst == k->addrs.v4addrs.dst &&
+		    tpos->keys.ports.ports == k->ports.ports &&
+		    tpos->keys.basic.ip_proto == k->basic.ip_proto &&
+		    tpos->keys.basic.n_proto == k->basic.n_proto)
 			return tpos;
 	return NULL;
 }
@@ -177,9 +177,10 @@ int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	int res, i;
 
 	enic = netdev_priv(dev);
-	res = skb_flow_dissect(skb, &keys);
-	if (!res || keys.n_proto != htons(ETH_P_IP) ||
-	    (keys.ip_proto != IPPROTO_TCP && keys.ip_proto != IPPROTO_UDP))
+	res = skb_flow_dissect_flow_keys(skb, &keys);
+	if (!res || keys.basic.n_proto != htons(ETH_P_IP) ||
+	    (keys.basic.ip_proto != IPPROTO_TCP &&
+	     keys.basic.ip_proto != IPPROTO_UDP))
 		return -EPROTONOSUPPORT;
 
 	tbl_idx = skb_get_hash_raw(skb) & ENIC_RFS_FLW_MASK;
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 28d9ca675a27..f3f1601a76f3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -131,8 +131,15 @@ static void enic_get_drvinfo(struct net_device *netdev,
 {
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_devcmd_fw_info *fw_info;
+	int err;
 
-	enic_dev_fw_info(enic, &fw_info);
+	err = enic_dev_fw_info(enic, &fw_info);
+	/* return only when pci_zalloc_consistent fails in vnic_dev_fw_info
+	 * For other failures, like devcmd failure, we return previously
+	 * recorded info.
+	 */
+	if (err == -ENOMEM)
+		return;
 
 	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
@@ -181,8 +188,15 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_stats *vstats;
 	unsigned int i;
+	int err;
 
-	enic_dev_stats_dump(enic, &vstats);
+	err = enic_dev_stats_dump(enic, &vstats);
+	/* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump
+	 * For other failures, like devcmd failure, we return previously
+	 * recorded stats.
+	 */
+	if (err == -ENOMEM)
+		return;
 
 	for (i = 0; i < enic_n_tx_stats; i++)
 		*(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].index];
@@ -334,7 +348,7 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 	n = htbl_fltr_search(enic, (u16)fsp->location);
 	if (!n)
 		return -EINVAL;
-	switch (n->keys.ip_proto) {
+	switch (n->keys.basic.ip_proto) {
 	case IPPROTO_TCP:
 		fsp->flow_type = TCP_V4_FLOW;
 		break;
@@ -346,16 +360,16 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
 		break;
 	}
 
-	fsp->h_u.tcp_ip4_spec.ip4src = n->keys.src;
+	fsp->h_u.tcp_ip4_spec.ip4src = flow_get_u32_src(&n->keys);
 	fsp->m_u.tcp_ip4_spec.ip4src = (__u32)~0;
 
-	fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.dst;
+	fsp->h_u.tcp_ip4_spec.ip4dst = flow_get_u32_dst(&n->keys);
 	fsp->m_u.tcp_ip4_spec.ip4dst = (__u32)~0;
 
-	fsp->h_u.tcp_ip4_spec.psrc = n->keys.port16[0];
+	fsp->h_u.tcp_ip4_spec.psrc = n->keys.ports.src;
 	fsp->m_u.tcp_ip4_spec.psrc = (__u16)~0;
 
-	fsp->h_u.tcp_ip4_spec.pdst = n->keys.port16[1];
+	fsp->h_u.tcp_ip4_spec.pdst = n->keys.ports.dst;
 	fsp->m_u.tcp_ip4_spec.pdst = (__u16)~0;
 
 	fsp->ring_cookie = n->rq_id;
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 204bd182473b..eadae1b412c6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -615,8 +615,15 @@ static struct rtnl_link_stats64 *enic_get_stats(struct net_device *netdev,
 {
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_stats *stats;
+	int err;
 
-	enic_dev_stats_dump(enic, &stats);
+	err = enic_dev_stats_dump(enic, &stats);
+	/* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump
+	 * For other failures, like devcmd failure, we return previously
+	 * recorded stats.
+	 */
+	if (err == -ENOMEM)
+		return net_stats;
 
 	net_stats->tx_packets = stats->tx.tx_frames_ok;
 	net_stats->tx_bytes = stats->tx.tx_bytes_ok;
@@ -1407,6 +1414,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 		 */
 		enic_calc_int_moderation(enic, &enic->rq[rq]);
 
+	enic_poll_unlock_napi(&enic->rq[rq]);
 	if (work_done < work_to_do) {
 
 		/* Some work done, but not enough to stay in polling,
@@ -1418,7 +1426,6 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 			enic_set_int_moderation(enic, &enic->rq[rq]);
 		vnic_intr_unmask(&enic->intr[intr]);
 	}
-	enic_poll_unlock_napi(&enic->rq[rq]);
 
 	return work_done;
 }
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index 36a2ed606c91..c4b2183bf352 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -188,16 +188,15 @@ void vnic_rq_clean(struct vnic_rq *rq,
 	struct vnic_rq_buf *buf;
 	u32 fetch_index;
 	unsigned int count = rq->ring.desc_count;
+	int i;
 
 	buf = rq->to_clean;
 
-	while (vnic_rq_desc_used(rq) > 0) {
-
+	for (i = 0; i < rq->ring.desc_count; i++) {
 		(*buf_clean)(rq, buf);
-
-		buf = rq->to_clean = buf->next;
-		rq->ring.desc_avail++;
+		buf = buf->next;
 	}
+	rq->ring.desc_avail = rq->ring.desc_count - 1;
 
 	/* Use current fetch_index as the ring starting point */
 	fetch_index = ioread32(&rq->ctrl->fetch_index);
diff --git a/drivers/net/ethernet/dec/Kconfig b/drivers/net/ethernet/dec/Kconfig
index 68262aa57d01..740bbad5ed38 100644
--- a/drivers/net/ethernet/dec/Kconfig
+++ b/drivers/net/ethernet/dec/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_DEC
 	default y
 	depends on PCI || EISA || CARDBUS
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index eb9ba6e97d04..1003201b5d80 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -21,8 +21,7 @@ config DE2104X
 	  of this type.  (If your card is NOT SMC EtherPower 10/100 PCI
 	  (smc9332dst), you can also try the driver for "Generic DECchip"
 	  cards, below.  However, most people with a network card of this type
-	  will say Y here.) Do read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  will say Y here.)
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called de2104x.
@@ -50,8 +49,7 @@ config TULIP
 	  of this type.  (If your card is NOT SMC EtherPower 10/100 PCI
 	  (smc9332dst), you can also try the driver for "Generic DECchip"
 	  cards, above.  However, most people with a network card of this type
-	  will say Y here.) Do read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  will say Y here.)
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called tulip.
@@ -113,9 +111,7 @@ config DE4X5
 	---help---
 	  This is support for the DIGITAL series of PCI/EISA Ethernet cards.
 	  These include the DE425, DE434, DE435, DE450 and DE500 models.  If
-	  you have a network card of this type, say Y and read the
-	  Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>. More specific
+	  you have a network card of this type, say Y.  More specific
 	  information is contained in
 	  <file:Documentation/networking/de4x5.txt>.
 
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index badff181e719..8966f3159bb2 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -5189,16 +5189,16 @@ de4x5_parse_params(struct net_device *dev)
 	if (strstr(p, "fdx") || strstr(p, "FDX")) lp->params.fdx = true;
 
 	if (strstr(p, "autosense") || strstr(p, "AUTOSENSE")) {
-	    if (strstr(p, "TP")) {
-		lp->params.autosense = TP;
-	    } else if (strstr(p, "TP_NW")) {
+	    if (strstr(p, "TP_NW")) {
 		lp->params.autosense = TP_NW;
+	    } else if (strstr(p, "TP")) {
+		lp->params.autosense = TP;
+	    } else if (strstr(p, "BNC_AUI")) {
+		lp->params.autosense = BNC;
 	    } else if (strstr(p, "BNC")) {
 		lp->params.autosense = BNC;
 	    } else if (strstr(p, "AUI")) {
 		lp->params.autosense = AUI;
-	    } else if (strstr(p, "BNC_AUI")) {
-		lp->params.autosense = BNC;
 	    } else if (strstr(p, "10Mb")) {
 		lp->params.autosense = _10Mb;
 	    } else if (strstr(p, "100Mb")) {
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 2c30c0c83f98..447d09272ab7 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -1115,7 +1115,7 @@ static void uli526x_timer(unsigned long data)
 				netif_carrier_off(dev);
 			}
 		}
-		db->init=0;
+	db->init = 0;
 
 	/* Timer active again */
 	db->timer.expires = ULI526X_TIMER_WUT;
diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig
index c543ac11ce08..f6e858d0b9d4 100644
--- a/drivers/net/ethernet/dlink/Kconfig
+++ b/drivers/net/ethernet/dlink/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_DLINK
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 1274b6fdac8a..cf0a5fcdaaaf 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -463,10 +463,8 @@ rio_open (struct net_device *dev)
 		dw32(MACCtrl, dr32(MACCtrl) | AutoVLANuntagging);
 	}
 
-	init_timer (&np->timer);
+	setup_timer(&np->timer, rio_timer, (unsigned long)dev);
 	np->timer.expires = jiffies + 1*HZ;
-	np->timer.data = (unsigned long) dev;
-	np->timer.function = rio_timer;
 	add_timer (&np->timer);
 
 	/* Start Tx/Rx */
diff --git a/drivers/net/ethernet/emulex/Kconfig b/drivers/net/ethernet/emulex/Kconfig
index 1b8d638c6cb1..fdbb27ceb02f 100644
--- a/drivers/net/ethernet/emulex/Kconfig
+++ b/drivers/net/ethernet/emulex/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_EMULEX
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index ea94a8eb6b35..7108563260ae 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -5,6 +5,15 @@ config BE2NET
 	  This driver implements the NIC functionality for ServerEngines'
 	  10Gbps network adapter - BladeEngine.
 
+config BE2NET_HWMON
+	bool "HWMON support for be2net driver"
+	depends on BE2NET && HWMON
+	depends on !(BE2NET=y && HWMON=m)
+	default y
+	---help---
+	  Say Y here if you want to expose thermal sensor data on
+	  be2net network adapter.
+
 config BE2NET_VXLAN
         bool "VXLAN offload support on be2net driver"
         default y
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 1bf1cdce74ac..8d12b41b3b19 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -31,11 +31,13 @@
 #include <linux/slab.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/cpumask.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
 
 #include "be_hw.h"
 #include "be_roce.h"
 
-#define DRV_VER			"10.6.0.1"
+#define DRV_VER			"10.6.0.2"
 #define DRV_NAME		"be2net"
 #define BE_NAME			"Emulex BladeEngine2"
 #define BE3_NAME		"Emulex BladeEngine3"
@@ -314,7 +316,6 @@ struct be_rx_obj {
 } ____cacheline_aligned_in_smp;
 
 struct be_drv_stats {
-	u32 be_on_die_temperature;
 	u32 eth_red_drops;
 	u32 dma_map_errors;
 	u32 rx_drops_no_pbuf;
@@ -366,6 +367,7 @@ struct be_vf_cfg {
 	u32 tx_rate;
 	u32 plink_tracking;
 	u32 privileges;
+	bool spoofchk;
 };
 
 enum vf_state {
@@ -382,6 +384,7 @@ enum vf_state {
 #define BE_FLAGS_SETUP_DONE			BIT(9)
 #define BE_FLAGS_EVT_INCOMPATIBLE_SFP		BIT(10)
 #define BE_FLAGS_ERR_DETECTION_SCHEDULED	BIT(11)
+#define BE_FLAGS_OS2BMC				BIT(12)
 
 #define BE_UC_PMAC_COUNT			30
 #define BE_VF_UC_PMAC_COUNT			2
@@ -426,6 +429,8 @@ struct be_resources {
 	u32 vf_if_cap_flags;	/* VF if capability flags */
 };
 
+#define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
+
 struct rss_info {
 	u64 rss_flags;
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
@@ -433,6 +438,12 @@ struct rss_info {
 	u8 rss_hkey[RSS_HASH_KEY_LEN];
 };
 
+#define BE_INVALID_DIE_TEMP	0xFF
+struct be_hwmon {
+	struct device *hwmon_dev;
+	u8 be_on_die_temp;  /* Unit: millidegree Celsius */
+};
+
 /* Macros to read/write the 'features' word of be_wrb_params structure.
  */
 #define	BE_WRB_F_BIT(name)			BE_WRB_F_##name##_BIT
@@ -453,7 +464,8 @@ enum {
 	BE_WRB_F_LSO_BIT,		/* LSO */
 	BE_WRB_F_LSO6_BIT,		/* LSO6 */
 	BE_WRB_F_VLAN_BIT,		/* VLAN */
-	BE_WRB_F_VLAN_SKIP_HW_BIT	/* Skip VLAN tag (workaround) */
+	BE_WRB_F_VLAN_SKIP_HW_BIT,	/* Skip VLAN tag (workaround) */
+	BE_WRB_F_OS2BMC_BIT		/* Send packet to the management ring */
 };
 
 /* The structure below provides a HW-agnostic abstraction of WRB params
@@ -514,6 +526,7 @@ struct be_adapter {
 	u16 work_counter;
 
 	struct delayed_work be_err_detection_work;
+	u8 err_flags;
 	u32 flags;
 	u32 cmd_privileges;
 	/* Ethtool knobs and info */
@@ -572,8 +585,11 @@ struct be_adapter {
 	u16 qnq_vid;
 	u32 msg_enable;
 	int be_get_temp_freq;
+	struct be_hwmon hwmon_info;
 	u8 pf_number;
 	struct rss_info rss_info;
+	/* Filters for packets that need to be sent to BMC */
+	u32 bmc_filt_mask;
 };
 
 #define be_physfn(adapter)		(!adapter->virtfn)
@@ -772,26 +788,36 @@ static inline bool is_ipv4_pkt(struct sk_buff *skb)
 	return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
 }
 
-static inline bool be_multi_rxq(const struct be_adapter *adapter)
+#define BE_ERROR_EEH		1
+#define BE_ERROR_UE		BIT(1)
+#define BE_ERROR_FW		BIT(2)
+#define BE_ERROR_HW		(BE_ERROR_EEH | BE_ERROR_UE)
+#define BE_ERROR_ANY		(BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_FW)
+#define BE_CLEAR_ALL		0xFF
+
+static inline u8 be_check_error(struct be_adapter *adapter, u32 err_type)
 {
-	return adapter->num_rx_qs > 1;
+	return (adapter->err_flags & err_type);
 }
 
-static inline bool be_error(struct be_adapter *adapter)
+static inline void be_set_error(struct be_adapter *adapter, int err_type)
 {
-	return adapter->eeh_error || adapter->hw_error || adapter->fw_timeout;
+	struct net_device *netdev = adapter->netdev;
+
+	adapter->err_flags |= err_type;
+	netif_carrier_off(netdev);
+
+	dev_info(&adapter->pdev->dev, "%s: Link down\n", netdev->name);
 }
 
-static inline bool be_hw_error(struct be_adapter *adapter)
+static inline void  be_clear_error(struct be_adapter *adapter, int err_type)
 {
-	return adapter->eeh_error || adapter->hw_error;
+	adapter->err_flags &= ~err_type;
 }
 
-static inline void  be_clear_all_error(struct be_adapter *adapter)
+static inline bool be_multi_rxq(const struct be_adapter *adapter)
 {
-	adapter->eeh_error = false;
-	adapter->hw_error = false;
-	adapter->fw_timeout = false;
+	return adapter->num_rx_qs > 1;
 }
 
 void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm,
@@ -804,6 +830,7 @@ bool be_pause_supported(struct be_adapter *adapter);
 u32 be_get_fw_log_level(struct be_adapter *adapter);
 int be_update_queues(struct be_adapter *adapter);
 int be_poll(struct napi_struct *napi, int budget);
+void be_eqd_update(struct be_adapter *adapter, bool force_update);
 
 /*
  * internal function to initialize-cleanup roce device.
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index fb140faeafb1..9eac3227d2ca 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -93,7 +93,7 @@ static void be_mcc_notify(struct be_adapter *adapter)
 	struct be_queue_info *mccq = &adapter->mcc_obj.q;
 	u32 val = 0;
 
-	if (be_error(adapter))
+	if (be_check_error(adapter, BE_ERROR_ANY))
 		return;
 
 	val |= mccq->id & DB_MCCQ_RING_ID_MASK;
@@ -140,6 +140,7 @@ static bool be_skip_err_log(u8 opcode, u16 base_status, u16 addl_status)
 	if (base_status == MCC_STATUS_NOT_SUPPORTED ||
 	    base_status == MCC_STATUS_ILLEGAL_REQUEST ||
 	    addl_status == MCC_ADDL_STATUS_TOO_MANY_INTERFACES ||
+	    addl_status == MCC_ADDL_STATUS_INSUFFICIENT_VLANS ||
 	    (opcode == OPCODE_COMMON_WRITE_FLASHROM &&
 	    (base_status == MCC_STATUS_ILLEGAL_FIELD ||
 	     addl_status == MCC_ADDL_STATUS_FLASH_IMAGE_CRC_MISMATCH)))
@@ -191,10 +192,12 @@ static void be_async_cmd_process(struct be_adapter *adapter,
 		if (base_status == MCC_STATUS_SUCCESS) {
 			struct be_cmd_resp_get_cntl_addnl_attribs *resp =
 							(void *)resp_hdr;
-			adapter->drv_stats.be_on_die_temperature =
+			adapter->hwmon_info.be_on_die_temp =
 						resp->on_die_temperature;
 		} else {
 			adapter->be_get_temp_freq = 0;
+			adapter->hwmon_info.be_on_die_temp =
+						BE_INVALID_DIE_TEMP;
 		}
 		return;
 	}
@@ -330,6 +333,21 @@ static void be_async_grp5_pvid_state_process(struct be_adapter *adapter,
 	}
 }
 
+#define MGMT_ENABLE_MASK	0x4
+static void be_async_grp5_fw_control_process(struct be_adapter *adapter,
+					     struct be_mcc_compl *compl)
+{
+	struct be_async_fw_control *evt = (struct be_async_fw_control *)compl;
+	u32 evt_dw1 = le32_to_cpu(evt->event_data_word1);
+
+	if (evt_dw1 & MGMT_ENABLE_MASK) {
+		adapter->flags |= BE_FLAGS_OS2BMC;
+		adapter->bmc_filt_mask = le32_to_cpu(evt->event_data_word2);
+	} else {
+		adapter->flags &= ~BE_FLAGS_OS2BMC;
+	}
+}
+
 static void be_async_grp5_evt_process(struct be_adapter *adapter,
 				      struct be_mcc_compl *compl)
 {
@@ -346,6 +364,10 @@ static void be_async_grp5_evt_process(struct be_adapter *adapter,
 	case ASYNC_EVENT_PVID_STATE:
 		be_async_grp5_pvid_state_process(adapter, compl);
 		break;
+	/* Async event to disable/enable os2bmc and/or mac-learning */
+	case ASYNC_EVENT_FW_CONTROL:
+		be_async_grp5_fw_control_process(adapter, compl);
+		break;
 	default:
 		break;
 	}
@@ -486,7 +508,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
 	for (i = 0; i < mcc_timeout; i++) {
-		if (be_error(adapter))
+		if (be_check_error(adapter, BE_ERROR_ANY))
 			return -EIO;
 
 		local_bh_disable();
@@ -499,7 +521,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
-		adapter->fw_timeout = true;
+		be_set_error(adapter, BE_ERROR_FW);
 		return -EIO;
 	}
 	return status;
@@ -538,7 +560,7 @@ static int be_mbox_db_ready_wait(struct be_adapter *adapter, void __iomem *db)
 	u32 ready;
 
 	do {
-		if (be_error(adapter))
+		if (be_check_error(adapter, BE_ERROR_ANY))
 			return -EIO;
 
 		ready = ioread32(db);
@@ -551,7 +573,7 @@ static int be_mbox_db_ready_wait(struct be_adapter *adapter, void __iomem *db)
 
 		if (msecs > 4000) {
 			dev_err(&adapter->pdev->dev, "FW not responding\n");
-			adapter->fw_timeout = true;
+			be_set_error(adapter, BE_ERROR_FW);
 			be_detect_error(adapter);
 			return -1;
 		}
@@ -1457,7 +1479,7 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags,
 		*if_handle = le32_to_cpu(resp->interface_id);
 
 		/* Hack to retrieve VF's pmac-id on BE3 */
-		if (BE3_chip(adapter) && !be_physfn(adapter))
+		if (BE3_chip(adapter) && be_virtfn(adapter))
 			adapter->pmac_id[0] = le32_to_cpu(resp->pmac_id);
 	}
 	return status;
@@ -1720,9 +1742,9 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 	total_size = buf_len;
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
-	get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
-					      get_fat_cmd.size,
-					      &get_fat_cmd.dma);
+	get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     get_fat_cmd.size,
+					     &get_fat_cmd.dma, GFP_ATOMIC);
 	if (!get_fat_cmd.va) {
 		dev_err(&adapter->pdev->dev,
 			"Memory allocation failure while reading FAT data\n");
@@ -1767,8 +1789,8 @@ int be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
-	pci_free_consistent(adapter->pdev, get_fat_cmd.size,
-			    get_fat_cmd.va, get_fat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
+			  get_fat_cmd.va, get_fat_cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
@@ -2215,12 +2237,12 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -EINVAL;
 
 	cmd.size = sizeof(struct be_cmd_resp_port_type);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
 		return -ENOMEM;
 	}
-	memset(cmd.va, 0, cmd.size);
 
 	spin_lock_bh(&adapter->mcc_lock);
 
@@ -2245,7 +2267,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 	}
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
@@ -2720,7 +2742,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -2754,7 +2777,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 				BE_SUPPORTED_SPEED_1GBPS;
 		}
 	}
-	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -2805,8 +2828,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
-	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
-					      &attribs_cmd.dma);
+	attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					     attribs_cmd.size,
+					     &attribs_cmd.dma, GFP_ATOMIC);
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -2833,8 +2857,8 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (attribs_cmd.va)
-		pci_free_consistent(adapter->pdev, attribs_cmd.size,
-				    attribs_cmd.va, attribs_cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, attribs_cmd.size,
+				  attribs_cmd.va, attribs_cmd.dma);
 	return status;
 }
 
@@ -2972,9 +2996,10 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
-	get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
-						   get_mac_list_cmd.size,
-						   &get_mac_list_cmd.dma);
+	get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+						  get_mac_list_cmd.size,
+						  &get_mac_list_cmd.dma,
+						  GFP_ATOMIC);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -3047,8 +3072,8 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 out:
 	spin_unlock_bh(&adapter->mcc_lock);
-	pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
-			    get_mac_list_cmd.va, get_mac_list_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
+			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
 }
 
@@ -3101,8 +3126,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
-	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
-				    &cmd.dma, GFP_KERNEL);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3153,7 +3178,7 @@ int be_cmd_set_mac(struct be_adapter *adapter, u8 *mac, int if_id, u32 dom)
 }
 
 int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
-			  u32 domain, u16 intf_id, u16 hsw_mode)
+			  u32 domain, u16 intf_id, u16 hsw_mode, u8 spoofchk)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_set_hsw_config *req;
@@ -3189,6 +3214,14 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			      ctxt, hsw_mode);
 	}
 
+	/* Enable/disable both mac and vlan spoof checking */
+	if (!BEx_chip(adapter) && spoofchk) {
+		AMAP_SET_BITS(struct amap_set_hsw_context, mac_spoofchk,
+			      ctxt, spoofchk);
+		AMAP_SET_BITS(struct amap_set_hsw_context, vlan_spoofchk,
+			      ctxt, spoofchk);
+	}
+
 	be_dws_cpu_to_le(req->context, sizeof(req->context));
 	status = be_mcc_notify_wait(adapter);
 
@@ -3199,7 +3232,7 @@ err:
 
 /* Get Hyper switch config */
 int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
-			  u32 domain, u16 intf_id, u8 *mode)
+			  u32 domain, u16 intf_id, u8 *mode, bool *spoofchk)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_get_hsw_config *req;
@@ -3247,6 +3280,10 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 		if (mode)
 			*mode = AMAP_GET_BITS(struct amap_get_hsw_resp_context,
 					      port_fwd_type, &resp->context);
+		if (spoofchk)
+			*spoofchk =
+				AMAP_GET_BITS(struct amap_get_hsw_resp_context,
+					      spoofchk, &resp->context);
 	}
 
 err:
@@ -3258,7 +3295,7 @@ static bool be_is_wol_excluded(struct be_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
 
-	if (!be_physfn(adapter))
+	if (be_virtfn(adapter))
 		return true;
 
 	switch (pdev->subsystem_device) {
@@ -3291,7 +3328,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -3326,7 +3364,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 
 }
@@ -3340,8 +3379,9 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 	if (!extfat_cmd.va)
 		return -ENOMEM;
 
@@ -3363,8 +3403,8 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd, cfgs);
 err:
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 	return status;
 }
 
@@ -3377,8 +3417,9 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
-					     &extfat_cmd.dma);
+	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    extfat_cmd.size, &extfat_cmd.dma,
+					    GFP_ATOMIC);
 
 	if (!extfat_cmd.va) {
 		dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
@@ -3396,8 +3437,8 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 				level = cfgs->module[0].trace_lvl[j].dbg_lvl;
 		}
 	}
-	pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
-			    extfat_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, extfat_cmd.size, extfat_cmd.va,
+			  extfat_cmd.dma);
 err:
 	return level;
 }
@@ -3595,7 +3636,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3635,7 +3677,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 err:
 	mutex_unlock(&adapter->mbox_lock);
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3656,7 +3699,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3702,7 +3746,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 		res->vf_if_cap_flags = vf_res->cap_flags;
 err:
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
@@ -3717,7 +3762,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
+	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				     GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -3733,7 +3779,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 	status = be_cmd_notify_wait(adapter, &wrb);
 
 	if (cmd.va)
-		pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
+		dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va,
+				  cmd.dma);
 	return status;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 1ec22300e254..2716e6f30d9a 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -65,7 +65,8 @@ enum mcc_base_status {
 enum mcc_addl_status {
 	MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES = 0x16,
 	MCC_ADDL_STATUS_FLASH_IMAGE_CRC_MISMATCH = 0x4d,
-	MCC_ADDL_STATUS_TOO_MANY_INTERFACES = 0x4a
+	MCC_ADDL_STATUS_TOO_MANY_INTERFACES = 0x4a,
+	MCC_ADDL_STATUS_INSUFFICIENT_VLANS = 0xab
 };
 
 #define CQE_BASE_STATUS_MASK		0xFFFF
@@ -104,6 +105,7 @@ struct be_mcc_compl {
 #define ASYNC_DEBUG_EVENT_TYPE_QNQ	1
 #define ASYNC_EVENT_CODE_SLIPORT	0x11
 #define ASYNC_EVENT_PORT_MISCONFIG	0x9
+#define ASYNC_EVENT_FW_CONTROL		0x5
 
 enum {
 	LINK_DOWN	= 0x0,
@@ -180,6 +182,22 @@ struct be_async_event_misconfig_port {
 	u32 flags;
 } __packed;
 
+#define BMC_FILT_BROADCAST_ARP				BIT(0)
+#define BMC_FILT_BROADCAST_DHCP_CLIENT			BIT(1)
+#define BMC_FILT_BROADCAST_DHCP_SERVER			BIT(2)
+#define BMC_FILT_BROADCAST_NET_BIOS			BIT(3)
+#define BMC_FILT_BROADCAST				BIT(7)
+#define BMC_FILT_MULTICAST_IPV6_NEIGH_ADVER		BIT(8)
+#define BMC_FILT_MULTICAST_IPV6_RA			BIT(9)
+#define BMC_FILT_MULTICAST_IPV6_RAS			BIT(10)
+#define BMC_FILT_MULTICAST				BIT(15)
+struct be_async_fw_control {
+	u32 event_data_word1;
+	u32 event_data_word2;
+	u32 evt_tag;
+	u32 event_data_word4;
+} __packed;
+
 struct be_mcc_mailbox {
 	struct be_mcc_wrb wrb;
 	struct be_mcc_compl compl;
@@ -1109,10 +1127,6 @@ struct be_cmd_req_query_fw_cfg {
 	u32 rsvd[31];
 };
 
-/* ASIC revisions */
-#define ASIC_REV_B0		0x10
-#define ASIC_REV_P2		0x11
-
 struct be_cmd_resp_query_fw_cfg {
 	struct be_cmd_resp_hdr hdr;
 	u32 be_config_number;
@@ -1745,18 +1759,24 @@ struct be_cmd_req_set_mac_list {
 #define PORT_FWD_TYPE_VEPA		0x3
 #define PORT_FWD_TYPE_VEB		0x2
 
+#define ENABLE_MAC_SPOOFCHK		0x2
+#define DISABLE_MAC_SPOOFCHK		0x3
+
 struct amap_set_hsw_context {
 	u8 interface_id[16];
-	u8 rsvd0[14];
+	u8 rsvd0[8];
+	u8 mac_spoofchk[2];
+	u8 rsvd1[4];
 	u8 pvid_valid;
 	u8 pport;
-	u8 rsvd1[6];
+	u8 rsvd2[6];
 	u8 port_fwd_type[3];
-	u8 rsvd2[7];
+	u8 rsvd3[5];
+	u8 vlan_spoofchk[2];
 	u8 pvid[16];
-	u8 rsvd3[32];
 	u8 rsvd4[32];
 	u8 rsvd5[32];
+	u8 rsvd6[32];
 } __packed;
 
 struct be_cmd_req_set_hsw_config {
@@ -1774,11 +1794,13 @@ struct amap_get_hsw_req_context {
 struct amap_get_hsw_resp_context {
 	u8 rsvd0[6];
 	u8 port_fwd_type[3];
-	u8 rsvd1[7];
+	u8 rsvd1[5];
+	u8 spoofchk;
+	u8 rsvd2;
 	u8 pvid[16];
-	u8 rsvd2[32];
 	u8 rsvd3[32];
 	u8 rsvd4[32];
+	u8 rsvd5[32];
 } __packed;
 
 struct be_cmd_req_get_hsw_config {
@@ -2334,9 +2356,9 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array, u8 mac_count,
 			u32 domain);
 int be_cmd_set_mac(struct be_adapter *adapter, u8 *mac, int if_id, u32 dom);
 int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid, u32 domain,
-			  u16 intf_id, u16 hsw_mode);
+			  u16 intf_id, u16 hsw_mode, u8 spoofchk);
 int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid, u32 domain,
-			  u16 intf_id, u8 *mode);
+			  u16 intf_id, u8 *mode, bool *spoofchk);
 int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter);
 int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level);
 int be_cmd_get_fw_log_level(struct be_adapter *adapter);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index b765c24625bf..b2476dbfd103 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -123,7 +123,6 @@ static const struct be_ethtool_stat et_stats[] = {
 	{DRVSTAT_INFO(dma_map_errors)},
 	/* Number of packets dropped due to random early drop function */
 	{DRVSTAT_INFO(eth_red_drops)},
-	{DRVSTAT_INFO(be_on_die_temperature)},
 	{DRVSTAT_INFO(rx_roce_bytes_lsd)},
 	{DRVSTAT_INFO(rx_roce_bytes_msd)},
 	{DRVSTAT_INFO(rx_roce_frames)},
@@ -264,8 +263,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 	int status = 0;
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
-	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
-					   &read_cmd.dma);
+	read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
+					  &read_cmd.dma, GFP_ATOMIC);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -289,8 +288,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 			break;
 		}
 	}
-	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
-			    read_cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, read_cmd.size, read_cmd.va,
+			  read_cmd.dma);
 
 	return status;
 }
@@ -368,6 +367,14 @@ static int be_set_coalesce(struct net_device *netdev,
 		aic++;
 	}
 
+	/* For Skyhawk, the EQD setting happens via EQ_DB when AIC is enabled.
+	 * When AIC is disabled, persistently force set EQD value via the
+	 * FW cmd, so that we don't have to calculate the delay multiplier
+	 * encode value each time EQ_DB is rung
+	 */
+	if (!et->use_adaptive_rx_coalesce && skyhawk_chip(adapter))
+		be_eqd_update(adapter, true);
+
 	return 0;
 }
 
@@ -818,8 +825,9 @@ static int be_test_ddr_dma(struct be_adapter *adapter)
 	};
 
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
-	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, ddrdma_cmd.size,
-					   &ddrdma_cmd.dma, GFP_KERNEL);
+	ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    ddrdma_cmd.size, &ddrdma_cmd.dma,
+					    GFP_KERNEL);
 	if (!ddrdma_cmd.va)
 		return -ENOMEM;
 
@@ -941,8 +949,9 @@ static int be_read_eeprom(struct net_device *netdev,
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
 	eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
-	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, eeprom_cmd.size,
-					   &eeprom_cmd.dma, GFP_KERNEL);
+	eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
+					    eeprom_cmd.size, &eeprom_cmd.dma,
+					    GFP_KERNEL);
 
 	if (!eeprom_cmd.va)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index 48840889db62..c684bb32b487 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -132,6 +132,18 @@
 #define DB_EQ_NUM_POPPED_SHIFT		(16)	/* bits 16 - 28 */
 /* Rearm bit */
 #define DB_EQ_REARM_SHIFT		(29)	/* bit 29 */
+/* Rearm to interrupt delay encoding */
+#define DB_EQ_R2I_DLY_SHIFT		(30)    /* bits 30 - 31 */
+
+/* Rearm to interrupt (R2I) delay multiplier encoding represents 3 different
+ * values configured in CEV_REARM2IRPT_DLY_MULT_CSR register. This value is
+ * programmed by host driver while ringing an EQ doorbell(EQ_DB) if a delay
+ * between rearming the EQ and next interrupt on this EQ is desired.
+ */
+#define	R2I_DLY_ENC_0			0	/* No delay */
+#define	R2I_DLY_ENC_1			1	/* maps to 160us EQ delay */
+#define	R2I_DLY_ENC_2			2	/* maps to 96us EQ delay */
+#define	R2I_DLY_ENC_3			3	/* maps to 48us EQ delay */
 
 /********* Compl Q door bell *************/
 #define DB_CQ_OFFSET 			0x120
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a6dcbf850c1f..6f642426308c 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -179,7 +179,7 @@ static void be_intr_set(struct be_adapter *adapter, bool enable)
 	if (lancer_chip(adapter))
 		return;
 
-	if (adapter->eeh_error)
+	if (be_check_error(adapter, BE_ERROR_EEH))
 		return;
 
 	status = be_cmd_intr_set(adapter, enable);
@@ -191,6 +191,9 @@ static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
 {
 	u32 val = 0;
 
+	if (be_check_error(adapter, BE_ERROR_HW))
+		return;
+
 	val |= qid & DB_RQ_RING_ID_MASK;
 	val |= posted << DB_RQ_NUM_POSTED_SHIFT;
 
@@ -203,6 +206,9 @@ static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
 {
 	u32 val = 0;
 
+	if (be_check_error(adapter, BE_ERROR_HW))
+		return;
+
 	val |= txo->q.id & DB_TXULP_RING_ID_MASK;
 	val |= (posted & DB_TXULP_NUM_POSTED_MASK) << DB_TXULP_NUM_POSTED_SHIFT;
 
@@ -211,14 +217,15 @@ static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
 }
 
 static void be_eq_notify(struct be_adapter *adapter, u16 qid,
-			 bool arm, bool clear_int, u16 num_popped)
+			 bool arm, bool clear_int, u16 num_popped,
+			 u32 eq_delay_mult_enc)
 {
 	u32 val = 0;
 
 	val |= qid & DB_EQ_RING_ID_MASK;
 	val |= ((qid & DB_EQ_RING_ID_EXT_MASK) << DB_EQ_RING_ID_EXT_MASK_SHIFT);
 
-	if (adapter->eeh_error)
+	if (be_check_error(adapter, BE_ERROR_HW))
 		return;
 
 	if (arm)
@@ -227,6 +234,7 @@ static void be_eq_notify(struct be_adapter *adapter, u16 qid,
 		val |= 1 << DB_EQ_CLR_SHIFT;
 	val |= 1 << DB_EQ_EVNT_SHIFT;
 	val |= num_popped << DB_EQ_NUM_POPPED_SHIFT;
+	val |= eq_delay_mult_enc << DB_EQ_R2I_DLY_SHIFT;
 	iowrite32(val, adapter->db + DB_EQ_OFFSET);
 }
 
@@ -238,7 +246,7 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped)
 	val |= ((qid & DB_CQ_RING_ID_EXT_MASK) <<
 			DB_CQ_RING_ID_EXT_MASK_SHIFT);
 
-	if (adapter->eeh_error)
+	if (be_check_error(adapter, BE_ERROR_HW))
 		return;
 
 	if (arm)
@@ -662,6 +670,8 @@ void be_link_status_update(struct be_adapter *adapter, u8 link_status)
 		netif_carrier_on(netdev);
 	else
 		netif_carrier_off(netdev);
+
+	netdev_info(netdev, "Link is %s\n", link_status ? "Up" : "Down");
 }
 
 static void be_tx_stats_update(struct be_tx_obj *txo, struct sk_buff *skb)
@@ -810,6 +820,8 @@ static void wrb_fill_hdr(struct be_adapter *adapter,
 
 	SET_TX_WRB_HDR_BITS(num_wrb, hdr, skb_wrb_cnt(skb));
 	SET_TX_WRB_HDR_BITS(len, hdr, skb->len);
+	SET_TX_WRB_HDR_BITS(mgmt, hdr,
+			    BE_WRB_F_GET(wrb_params->features, OS2BMC));
 }
 
 static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
@@ -1146,6 +1158,130 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo)
 	txo->pend_wrb_cnt = 0;
 }
 
+/* OS2BMC related */
+
+#define DHCP_CLIENT_PORT	68
+#define DHCP_SERVER_PORT	67
+#define NET_BIOS_PORT1		137
+#define NET_BIOS_PORT2		138
+#define DHCPV6_RAS_PORT		547
+
+#define is_mc_allowed_on_bmc(adapter, eh)	\
+	(!is_multicast_filt_enabled(adapter) &&	\
+	 is_multicast_ether_addr(eh->h_dest) &&	\
+	 !is_broadcast_ether_addr(eh->h_dest))
+
+#define is_bc_allowed_on_bmc(adapter, eh)	\
+	(!is_broadcast_filt_enabled(adapter) &&	\
+	 is_broadcast_ether_addr(eh->h_dest))
+
+#define is_arp_allowed_on_bmc(adapter, skb)	\
+	(is_arp(skb) && is_arp_filt_enabled(adapter))
+
+#define is_broadcast_packet(eh, adapter)	\
+		(is_multicast_ether_addr(eh->h_dest) && \
+		!compare_ether_addr(eh->h_dest, adapter->netdev->broadcast))
+
+#define is_arp(skb)	(skb->protocol == htons(ETH_P_ARP))
+
+#define is_arp_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & (BMC_FILT_BROADCAST_ARP))
+
+#define is_dhcp_client_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_BROADCAST_DHCP_CLIENT)
+
+#define is_dhcp_srvr_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_BROADCAST_DHCP_SERVER)
+
+#define is_nbios_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_BROADCAST_NET_BIOS)
+
+#define is_ipv6_na_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask &	\
+			BMC_FILT_MULTICAST_IPV6_NEIGH_ADVER)
+
+#define is_ipv6_ra_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_MULTICAST_IPV6_RA)
+
+#define is_ipv6_ras_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_MULTICAST_IPV6_RAS)
+
+#define is_broadcast_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_BROADCAST)
+
+#define is_multicast_filt_enabled(adapter)	\
+		(adapter->bmc_filt_mask & BMC_FILT_MULTICAST)
+
+static bool be_send_pkt_to_bmc(struct be_adapter *adapter,
+			       struct sk_buff **skb)
+{
+	struct ethhdr *eh = (struct ethhdr *)(*skb)->data;
+	bool os2bmc = false;
+
+	if (!be_is_os2bmc_enabled(adapter))
+		goto done;
+
+	if (!is_multicast_ether_addr(eh->h_dest))
+		goto done;
+
+	if (is_mc_allowed_on_bmc(adapter, eh) ||
+	    is_bc_allowed_on_bmc(adapter, eh) ||
+	    is_arp_allowed_on_bmc(adapter, (*skb))) {
+		os2bmc = true;
+		goto done;
+	}
+
+	if ((*skb)->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *hdr = ipv6_hdr((*skb));
+		u8 nexthdr = hdr->nexthdr;
+
+		if (nexthdr == IPPROTO_ICMPV6) {
+			struct icmp6hdr *icmp6 = icmp6_hdr((*skb));
+
+			switch (icmp6->icmp6_type) {
+			case NDISC_ROUTER_ADVERTISEMENT:
+				os2bmc = is_ipv6_ra_filt_enabled(adapter);
+				goto done;
+			case NDISC_NEIGHBOUR_ADVERTISEMENT:
+				os2bmc = is_ipv6_na_filt_enabled(adapter);
+				goto done;
+			default:
+				break;
+			}
+		}
+	}
+
+	if (is_udp_pkt((*skb))) {
+		struct udphdr *udp = udp_hdr((*skb));
+
+		switch (udp->dest) {
+		case DHCP_CLIENT_PORT:
+			os2bmc = is_dhcp_client_filt_enabled(adapter);
+			goto done;
+		case DHCP_SERVER_PORT:
+			os2bmc = is_dhcp_srvr_filt_enabled(adapter);
+			goto done;
+		case NET_BIOS_PORT1:
+		case NET_BIOS_PORT2:
+			os2bmc = is_nbios_filt_enabled(adapter);
+			goto done;
+		case DHCPV6_RAS_PORT:
+			os2bmc = is_ipv6_ras_filt_enabled(adapter);
+			goto done;
+		default:
+			break;
+		}
+	}
+done:
+	/* For packets over a vlan, which are destined
+	 * to BMC, asic expects the vlan to be inline in the packet.
+	 */
+	if (os2bmc)
+		*skb = be_insert_vlan_in_pkt(adapter, *skb, NULL);
+
+	return os2bmc;
+}
+
 static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -1167,6 +1303,18 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 		goto drop;
 	}
 
+	/* if os2bmc is enabled and if the pkt is destined to bmc,
+	 * enqueue the pkt a 2nd time with mgmt bit set.
+	 */
+	if (be_send_pkt_to_bmc(adapter, &skb)) {
+		BE_WRB_F_SET(wrb_params.features, OS2BMC, 1);
+		wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
+		if (unlikely(!wrb_cnt))
+			goto drop;
+		else
+			skb_get(skb);
+	}
+
 	if (be_is_txq_full(txo)) {
 		netif_stop_subqueue(netdev, q_idx);
 		tx_stats(txo)->tx_stops++;
@@ -1265,7 +1413,8 @@ static int be_vid_config(struct be_adapter *adapter)
 	if (status) {
 		dev_err(dev, "Setting HW VLAN filtering failed\n");
 		/* Set to VLAN promisc mode as setting VLAN filter failed */
-		if (addl_status(status) ==
+		if (addl_status(status) == MCC_ADDL_STATUS_INSUFFICIENT_VLANS ||
+		    addl_status(status) ==
 				MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES)
 			return be_set_vlan_promisc(adapter);
 	} else if (adapter->if_flags & BE_IF_FLAGS_VLAN_PROMISCUOUS) {
@@ -1466,6 +1615,7 @@ static int be_get_vf_config(struct net_device *netdev, int vf,
 	vi->qos = vf_cfg->vlan_tag >> VLAN_PRIO_SHIFT;
 	memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN);
 	vi->linkstate = adapter->vf_cfg[vf].plink_tracking;
+	vi->spoofchk = adapter->vf_cfg[vf].spoofchk;
 
 	return 0;
 }
@@ -1478,7 +1628,7 @@ static int be_set_vf_tvt(struct be_adapter *adapter, int vf, u16 vlan)
 	int status;
 
 	/* Enable Transparent VLAN Tagging */
-	status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_if_id, 0);
+	status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_if_id, 0, 0);
 	if (status)
 		return status;
 
@@ -1507,7 +1657,7 @@ static int be_clear_vf_tvt(struct be_adapter *adapter, int vf)
 
 	/* Reset Transparent VLAN Tagging. */
 	status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, vf + 1,
-				       vf_cfg->if_handle, 0);
+				       vf_cfg->if_handle, 0, 0);
 	if (status)
 		return status;
 
@@ -1642,6 +1792,39 @@ static int be_set_vf_link_state(struct net_device *netdev, int vf,
 	return 0;
 }
 
+static int be_set_vf_spoofchk(struct net_device *netdev, int vf, bool enable)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
+	u8 spoofchk;
+	int status;
+
+	if (!sriov_enabled(adapter))
+		return -EPERM;
+
+	if (vf >= adapter->num_vfs)
+		return -EINVAL;
+
+	if (BEx_chip(adapter))
+		return -EOPNOTSUPP;
+
+	if (enable == vf_cfg->spoofchk)
+		return 0;
+
+	spoofchk = enable ? ENABLE_MAC_SPOOFCHK : DISABLE_MAC_SPOOFCHK;
+
+	status = be_cmd_set_hsw_config(adapter, 0, vf + 1, vf_cfg->if_handle,
+				       0, spoofchk);
+	if (status) {
+		dev_err(&adapter->pdev->dev,
+			"Spoofchk change on VF %d failed: %#x\n", vf, status);
+		return be_cmd_status(status);
+	}
+
+	vf_cfg->spoofchk = enable;
+	return 0;
+}
+
 static void be_aic_update(struct be_aic_obj *aic, u64 rx_pkts, u64 tx_pkts,
 			  ulong now)
 {
@@ -1650,61 +1833,110 @@ static void be_aic_update(struct be_aic_obj *aic, u64 rx_pkts, u64 tx_pkts,
 	aic->jiffies = now;
 }
 
-static void be_eqd_update(struct be_adapter *adapter)
+static int be_get_new_eqd(struct be_eq_obj *eqo)
 {
-	struct be_set_eqd set_eqd[MAX_EVT_QS];
-	int eqd, i, num = 0, start;
+	struct be_adapter *adapter = eqo->adapter;
+	int eqd, start;
 	struct be_aic_obj *aic;
-	struct be_eq_obj *eqo;
 	struct be_rx_obj *rxo;
 	struct be_tx_obj *txo;
-	u64 rx_pkts, tx_pkts;
+	u64 rx_pkts = 0, tx_pkts = 0;
 	ulong now;
 	u32 pps, delta;
+	int i;
 
-	for_all_evt_queues(adapter, eqo, i) {
-		aic = &adapter->aic_obj[eqo->idx];
-		if (!aic->enable) {
-			if (aic->jiffies)
-				aic->jiffies = 0;
-			eqd = aic->et_eqd;
-			goto modify_eqd;
-		}
+	aic = &adapter->aic_obj[eqo->idx];
+	if (!aic->enable) {
+		if (aic->jiffies)
+			aic->jiffies = 0;
+		eqd = aic->et_eqd;
+		return eqd;
+	}
 
-		rxo = &adapter->rx_obj[eqo->idx];
+	for_all_rx_queues_on_eq(adapter, eqo, rxo, i) {
 		do {
 			start = u64_stats_fetch_begin_irq(&rxo->stats.sync);
-			rx_pkts = rxo->stats.rx_pkts;
+			rx_pkts += rxo->stats.rx_pkts;
 		} while (u64_stats_fetch_retry_irq(&rxo->stats.sync, start));
+	}
 
-		txo = &adapter->tx_obj[eqo->idx];
+	for_all_tx_queues_on_eq(adapter, eqo, txo, i) {
 		do {
 			start = u64_stats_fetch_begin_irq(&txo->stats.sync);
-			tx_pkts = txo->stats.tx_reqs;
+			tx_pkts += txo->stats.tx_reqs;
 		} while (u64_stats_fetch_retry_irq(&txo->stats.sync, start));
+	}
 
-		/* Skip, if wrapped around or first calculation */
-		now = jiffies;
-		if (!aic->jiffies || time_before(now, aic->jiffies) ||
-		    rx_pkts < aic->rx_pkts_prev ||
-		    tx_pkts < aic->tx_reqs_prev) {
-			be_aic_update(aic, rx_pkts, tx_pkts, now);
-			continue;
-		}
+	/* Skip, if wrapped around or first calculation */
+	now = jiffies;
+	if (!aic->jiffies || time_before(now, aic->jiffies) ||
+	    rx_pkts < aic->rx_pkts_prev ||
+	    tx_pkts < aic->tx_reqs_prev) {
+		be_aic_update(aic, rx_pkts, tx_pkts, now);
+		return aic->prev_eqd;
+	}
 
-		delta = jiffies_to_msecs(now - aic->jiffies);
-		pps = (((u32)(rx_pkts - aic->rx_pkts_prev) * 1000) / delta) +
-			(((u32)(tx_pkts - aic->tx_reqs_prev) * 1000) / delta);
-		eqd = (pps / 15000) << 2;
+	delta = jiffies_to_msecs(now - aic->jiffies);
+	if (delta == 0)
+		return aic->prev_eqd;
 
-		if (eqd < 8)
-			eqd = 0;
-		eqd = min_t(u32, eqd, aic->max_eqd);
-		eqd = max_t(u32, eqd, aic->min_eqd);
+	pps = (((u32)(rx_pkts - aic->rx_pkts_prev) * 1000) / delta) +
+		(((u32)(tx_pkts - aic->tx_reqs_prev) * 1000) / delta);
+	eqd = (pps / 15000) << 2;
 
-		be_aic_update(aic, rx_pkts, tx_pkts, now);
-modify_eqd:
-		if (eqd != aic->prev_eqd) {
+	if (eqd < 8)
+		eqd = 0;
+	eqd = min_t(u32, eqd, aic->max_eqd);
+	eqd = max_t(u32, eqd, aic->min_eqd);
+
+	be_aic_update(aic, rx_pkts, tx_pkts, now);
+
+	return eqd;
+}
+
+/* For Skyhawk-R only */
+static u32 be_get_eq_delay_mult_enc(struct be_eq_obj *eqo)
+{
+	struct be_adapter *adapter = eqo->adapter;
+	struct be_aic_obj *aic = &adapter->aic_obj[eqo->idx];
+	ulong now = jiffies;
+	int eqd;
+	u32 mult_enc;
+
+	if (!aic->enable)
+		return 0;
+
+	if (time_before_eq(now, aic->jiffies) ||
+	    jiffies_to_msecs(now - aic->jiffies) < 1)
+		eqd = aic->prev_eqd;
+	else
+		eqd = be_get_new_eqd(eqo);
+
+	if (eqd > 100)
+		mult_enc = R2I_DLY_ENC_1;
+	else if (eqd > 60)
+		mult_enc = R2I_DLY_ENC_2;
+	else if (eqd > 20)
+		mult_enc = R2I_DLY_ENC_3;
+	else
+		mult_enc = R2I_DLY_ENC_0;
+
+	aic->prev_eqd = eqd;
+
+	return mult_enc;
+}
+
+void be_eqd_update(struct be_adapter *adapter, bool force_update)
+{
+	struct be_set_eqd set_eqd[MAX_EVT_QS];
+	struct be_aic_obj *aic;
+	struct be_eq_obj *eqo;
+	int i, num = 0, eqd;
+
+	for_all_evt_queues(adapter, eqo, i) {
+		aic = &adapter->aic_obj[eqo->idx];
+		eqd = be_get_new_eqd(eqo);
+		if (force_update || eqd != aic->prev_eqd) {
 			set_eqd[num].delay_multiplier = (eqd * 65)/100;
 			set_eqd[num].eq_id = eqo->q.id;
 			aic->prev_eqd = eqd;
@@ -2212,7 +2444,7 @@ static void be_eq_clean(struct be_eq_obj *eqo)
 {
 	int num = events_get(eqo);
 
-	be_eq_notify(eqo->adapter, eqo->q.id, false, true, num);
+	be_eq_notify(eqo->adapter, eqo->q.id, false, true, num, 0);
 }
 
 static void be_rx_cq_clean(struct be_rx_obj *rxo)
@@ -2236,7 +2468,9 @@ static void be_rx_cq_clean(struct be_rx_obj *rxo)
 			if (lancer_chip(adapter))
 				break;
 
-			if (flush_wait++ > 10 || be_hw_error(adapter)) {
+			if (flush_wait++ > 50 ||
+			    be_check_error(adapter,
+					   BE_ERROR_HW)) {
 				dev_warn(&adapter->pdev->dev,
 					 "did not receive flush compl\n");
 				break;
@@ -2297,7 +2531,8 @@ static void be_tx_compl_clean(struct be_adapter *adapter)
 				pending_txqs--;
 		}
 
-		if (pending_txqs == 0 || ++timeo > 10 || be_hw_error(adapter))
+		if (pending_txqs == 0 || ++timeo > 10 ||
+		    be_check_error(adapter, BE_ERROR_HW))
 			break;
 
 		mdelay(1);
@@ -2358,11 +2593,11 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 				    adapter->cfg_num_qs);
 
 	for_all_evt_queues(adapter, eqo, i) {
+		int numa_node = dev_to_node(&adapter->pdev->dev);
 		if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
 			return -ENOMEM;
-		cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev),
-					    eqo->affinity_mask);
-
+		cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+				eqo->affinity_mask);
 		netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
 			       BE_NAPI_WEIGHT);
 		napi_hash_add(&eqo->napi);
@@ -2573,7 +2808,7 @@ static irqreturn_t be_intx(int irq, void *dev)
 		if (num_evts)
 			eqo->spurious_intr = 0;
 	}
-	be_eq_notify(adapter, eqo->q.id, false, true, num_evts);
+	be_eq_notify(adapter, eqo->q.id, false, true, num_evts, 0);
 
 	/* Return IRQ_HANDLED only for the the first spurious intr
 	 * after a valid intr to stop the kernel from branding
@@ -2589,7 +2824,7 @@ static irqreturn_t be_msix(int irq, void *dev)
 {
 	struct be_eq_obj *eqo = dev;
 
-	be_eq_notify(eqo->adapter, eqo->q.id, false, true, 0);
+	be_eq_notify(eqo->adapter, eqo->q.id, false, true, 0, 0);
 	napi_schedule(&eqo->napi);
 	return IRQ_HANDLED;
 }
@@ -2838,6 +3073,7 @@ int be_poll(struct napi_struct *napi, int budget)
 	int max_work = 0, work, i, num_evts;
 	struct be_rx_obj *rxo;
 	struct be_tx_obj *txo;
+	u32 mult_enc = 0;
 
 	num_evts = events_get(eqo);
 
@@ -2863,10 +3099,18 @@ int be_poll(struct napi_struct *napi, int budget)
 
 	if (max_work < budget) {
 		napi_complete(napi);
-		be_eq_notify(adapter, eqo->q.id, true, false, num_evts);
+
+		/* Skyhawk EQ_DB has a provision to set the rearm to interrupt
+		 * delay via a delay multiplier encoding value
+		 */
+		if (skyhawk_chip(adapter))
+			mult_enc = be_get_eq_delay_mult_enc(eqo);
+
+		be_eq_notify(adapter, eqo->q.id, true, false, num_evts,
+			     mult_enc);
 	} else {
 		/* As we'll continue in polling mode, count and clear events */
-		be_eq_notify(adapter, eqo->q.id, false, false, num_evts);
+		be_eq_notify(adapter, eqo->q.id, false, false, num_evts, 0);
 	}
 	return max_work;
 }
@@ -2898,22 +3142,19 @@ void be_detect_error(struct be_adapter *adapter)
 	u32 ue_lo = 0, ue_hi = 0, ue_lo_mask = 0, ue_hi_mask = 0;
 	u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
 	u32 i;
-	bool error_detected = false;
 	struct device *dev = &adapter->pdev->dev;
-	struct net_device *netdev = adapter->netdev;
 
-	if (be_hw_error(adapter))
+	if (be_check_error(adapter, BE_ERROR_HW))
 		return;
 
 	if (lancer_chip(adapter)) {
 		sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
 		if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
+			be_set_error(adapter, BE_ERROR_UE);
 			sliport_err1 = ioread32(adapter->db +
 						SLIPORT_ERROR1_OFFSET);
 			sliport_err2 = ioread32(adapter->db +
 						SLIPORT_ERROR2_OFFSET);
-			adapter->hw_error = true;
-			error_detected = true;
 			/* Do not log error messages if its a FW reset */
 			if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
 			    sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
@@ -2945,12 +3186,12 @@ void be_detect_error(struct be_adapter *adapter)
 		 */
 
 		if (ue_lo || ue_hi) {
-			error_detected = true;
 			dev_err(dev,
 				"Unrecoverable Error detected in the adapter");
 			dev_err(dev, "Please reboot server to recover");
 			if (skyhawk_chip(adapter))
-				adapter->hw_error = true;
+				be_set_error(adapter, BE_ERROR_UE);
+
 			for (i = 0; ue_lo; ue_lo >>= 1, i++) {
 				if (ue_lo & 1)
 					dev_err(dev, "UE: %s bit set\n",
@@ -2963,8 +3204,6 @@ void be_detect_error(struct be_adapter *adapter)
 			}
 		}
 	}
-	if (error_detected)
-		netif_carrier_off(netdev);
 }
 
 static void be_msix_disable(struct be_adapter *adapter)
@@ -3015,7 +3254,7 @@ fail:
 	dev_warn(dev, "MSIx enable failed\n");
 
 	/* INTx is not supported in VFs, so fail probe if enable_msix fails */
-	if (!be_physfn(adapter))
+	if (be_virtfn(adapter))
 		return num_vec;
 	return 0;
 }
@@ -3062,7 +3301,7 @@ static int be_irq_register(struct be_adapter *adapter)
 		if (status == 0)
 			goto done;
 		/* INTx is not supported for VF */
-		if (!be_physfn(adapter))
+		if (be_virtfn(adapter))
 			return status;
 	}
 
@@ -3229,9 +3468,12 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 
 	memcpy(rss->rss_hkey, rss_key, RSS_HASH_KEY_LEN);
 
-	/* First time posting */
+	/* Post 1 less than RXQ-len to avoid head being equal to tail,
+	 * which is a queue empty condition
+	 */
 	for_all_rx_queues(adapter, rxo, i)
-		be_post_rx_frags(rxo, GFP_KERNEL, MAX_RX_POST);
+		be_post_rx_frags(rxo, GFP_KERNEL, RX_Q_LEN - 1);
+
 	return 0;
 }
 
@@ -3263,7 +3505,7 @@ static int be_open(struct net_device *netdev)
 	for_all_evt_queues(adapter, eqo, i) {
 		napi_enable(&eqo->napi);
 		be_enable_busy_poll(eqo);
-		be_eq_notify(adapter, eqo->q.id, true, true, 0);
+		be_eq_notify(adapter, eqo->q.id, true, true, 0, 0);
 	}
 	adapter->flags |= BE_FLAGS_NAPI_ENABLED;
 
@@ -3563,7 +3805,7 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 
 	/* If a FW profile exists, then cap_flags are updated */
 	cap_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-		    BE_IF_FLAGS_MULTICAST;
+		    BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
 
 	for_all_vfs(adapter, vf_cfg, vf) {
 		if (!BE3_chip(adapter)) {
@@ -3610,6 +3852,7 @@ static int be_vf_setup(struct be_adapter *adapter)
 	struct device *dev = &adapter->pdev->dev;
 	struct be_vf_cfg *vf_cfg;
 	int status, old_vfs, vf;
+	bool spoofchk;
 
 	old_vfs = pci_num_vf(adapter->pdev);
 
@@ -3657,6 +3900,12 @@ static int be_vf_setup(struct be_adapter *adapter)
 		if (!old_vfs)
 			be_cmd_config_qos(adapter, 0, 0, vf + 1);
 
+		status = be_cmd_get_hsw_config(adapter, NULL, vf + 1,
+					       vf_cfg->if_handle, NULL,
+					       &spoofchk);
+		if (!status)
+			vf_cfg->spoofchk = spoofchk;
+
 		if (!old_vfs) {
 			be_cmd_enable_vf(adapter, vf + 1);
 			be_cmd_set_logical_link_config(adapter,
@@ -3733,8 +3982,9 @@ static void BEx_get_resources(struct be_adapter *adapter,
 	 *    *only* if it is RSS-capable.
 	 */
 	if (BE2_chip(adapter) || use_sriov ||  (adapter->port_num > 1) ||
-	    !be_physfn(adapter) || (be_is_mc(adapter) &&
-	    !(adapter->function_caps & BE_FUNCTION_CAPS_RSS))) {
+	    be_virtfn(adapter) ||
+	    (be_is_mc(adapter) &&
+	     !(adapter->function_caps & BE_FUNCTION_CAPS_RSS))) {
 		res->max_tx_qs = 1;
 	} else if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) {
 		struct be_resources super_nic_res = {0};
@@ -4075,7 +4325,7 @@ static int be_func_init(struct be_adapter *adapter)
 		msleep(100);
 
 		/* We can clear all errors when function reset succeeds */
-		be_clear_all_error(adapter);
+		be_clear_error(adapter, BE_CLEAR_ALL);
 	}
 
 	/* Tell FW we're ready to fire cmds */
@@ -4182,7 +4432,7 @@ static void be_netpoll(struct net_device *netdev)
 	int i;
 
 	for_all_evt_queues(adapter, eqo, i) {
-		be_eq_notify(eqo->adapter, eqo->q.id, false, true, 0);
+		be_eq_notify(eqo->adapter, eqo->q.id, false, true, 0, 0);
 		napi_schedule(&eqo->napi);
 	}
 }
@@ -4605,8 +4855,8 @@ static int lancer_fw_download(struct be_adapter *adapter,
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size,
-					  &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
+					   &flash_cmd.dma, GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4666,14 +4916,11 @@ static int lancer_fw_download(struct be_adapter *adapter,
 	return 0;
 }
 
-#define BE2_UFI		2
-#define BE3_UFI		3
-#define BE3R_UFI	10
-#define SH_UFI		4
-#define SH_P2_UFI	11
-
-static int be_get_ufi_type(struct be_adapter *adapter,
-			   struct flash_file_hdr_g3 *fhdr)
+/* Check if the flash image file is compatible with the adapter that
+ * is being flashed.
+ */
+static bool be_check_ufi_compatibility(struct be_adapter *adapter,
+				       struct flash_file_hdr_g3 *fhdr)
 {
 	if (!fhdr) {
 		dev_err(&adapter->pdev->dev, "Invalid FW UFI file");
@@ -4685,43 +4932,22 @@ static int be_get_ufi_type(struct be_adapter *adapter,
 	 */
 	switch (fhdr->build[0]) {
 	case BLD_STR_UFI_TYPE_SH:
-		return (fhdr->asic_type_rev == ASIC_REV_P2) ? SH_P2_UFI :
-								SH_UFI;
+		if (!skyhawk_chip(adapter))
+			return false;
+		break;
 	case BLD_STR_UFI_TYPE_BE3:
-		return (fhdr->asic_type_rev == ASIC_REV_B0) ? BE3R_UFI :
-								BE3_UFI;
+		if (!BE3_chip(adapter))
+			return false;
+		break;
 	case BLD_STR_UFI_TYPE_BE2:
-		return BE2_UFI;
-	default:
-		return -1;
-	}
-}
-
-/* Check if the flash image file is compatible with the adapter that
- * is being flashed.
- * BE3 chips with asic-rev B0 must be flashed only with BE3R_UFI type.
- * Skyhawk chips with asic-rev P2 must be flashed only with SH_P2_UFI type.
- */
-static bool be_check_ufi_compatibility(struct be_adapter *adapter,
-				       struct flash_file_hdr_g3 *fhdr)
-{
-	int ufi_type = be_get_ufi_type(adapter, fhdr);
-
-	switch (ufi_type) {
-	case SH_P2_UFI:
-		return skyhawk_chip(adapter);
-	case SH_UFI:
-		return (skyhawk_chip(adapter) &&
-			adapter->asic_rev < ASIC_REV_P2);
-	case BE3R_UFI:
-		return BE3_chip(adapter);
-	case BE3_UFI:
-		return (BE3_chip(adapter) && adapter->asic_rev < ASIC_REV_B0);
-	case BE2_UFI:
-		return BE2_chip(adapter);
+		if (!BE2_chip(adapter))
+			return false;
+		break;
 	default:
 		return false;
 	}
+
+	return (fhdr->asic_type_rev >= adapter->asic_rev);
 }
 
 static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
@@ -4739,8 +4965,8 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 	}
 
 	flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
-	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
-					  GFP_KERNEL);
+	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
+					   GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -4829,7 +5055,7 @@ static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 					       adapter->if_handle,
 					       mode == BRIDGE_MODE_VEPA ?
 					       PORT_FWD_TYPE_VEPA :
-					       PORT_FWD_TYPE_VEB);
+					       PORT_FWD_TYPE_VEB, 0);
 		if (status)
 			goto err;
 
@@ -4861,7 +5087,8 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		hsw_mode = PORT_FWD_TYPE_VEB;
 	} else {
 		status = be_cmd_get_hsw_config(adapter, NULL, 0,
-					       adapter->if_handle, &hsw_mode);
+					       adapter->if_handle, &hsw_mode,
+					       NULL);
 		if (status)
 			return 0;
 	}
@@ -4869,7 +5096,7 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       hsw_mode == PORT_FWD_TYPE_VEPA ?
 				       BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB,
-				       0, 0, nlflags);
+				       0, 0, nlflags, filter_mask, NULL);
 }
 
 #ifdef CONFIG_BE2NET_VXLAN
@@ -5014,6 +5241,7 @@ static const struct net_device_ops be_netdev_ops = {
 	.ndo_set_vf_rate	= be_set_vf_tx_rate,
 	.ndo_get_vf_config	= be_get_vf_config,
 	.ndo_set_vf_link_state  = be_set_vf_link_state,
+	.ndo_set_vf_spoofchk    = be_set_vf_spoofchk,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= be_netpoll,
 #endif
@@ -5118,7 +5346,7 @@ static void be_err_detection_task(struct work_struct *work)
 
 	be_detect_error(adapter);
 
-	if (adapter->hw_error) {
+	if (be_check_error(adapter, BE_ERROR_HW)) {
 		be_cleanup(adapter);
 
 		/* As of now error recovery support is in Lancer only */
@@ -5182,7 +5410,9 @@ static void be_worker(struct work_struct *work)
 			be_post_rx_frags(rxo, GFP_KERNEL, MAX_RX_POST);
 	}
 
-	be_eqd_update(adapter);
+	/* EQ-delay update for Skyhawk is done while notifying EQ */
+	if (!skyhawk_chip(adapter))
+		be_eqd_update(adapter, false);
 
 	if (adapter->flags & BE_FLAGS_EVT_INCOMPATIBLE_SFP)
 		be_log_sfp_info(adapter);
@@ -5202,7 +5432,7 @@ static void be_unmap_pci_bars(struct be_adapter *adapter)
 
 static int db_bar(struct be_adapter *adapter)
 {
-	if (lancer_chip(adapter) || !be_physfn(adapter))
+	if (lancer_chip(adapter) || be_virtfn(adapter))
 		return 0;
 	else
 		return 4;
@@ -5291,16 +5521,15 @@ static int be_drv_init(struct be_adapter *adapter)
 	int status = 0;
 
 	mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
-	mbox_mem_alloc->va = dma_alloc_coherent(dev, mbox_mem_alloc->size,
-						&mbox_mem_alloc->dma,
-						GFP_KERNEL);
+	mbox_mem_alloc->va = dma_zalloc_coherent(dev, mbox_mem_alloc->size,
+						 &mbox_mem_alloc->dma,
+						 GFP_KERNEL);
 	if (!mbox_mem_alloc->va)
 		return -ENOMEM;
 
 	mbox_mem_align->size = sizeof(struct be_mcc_mailbox);
 	mbox_mem_align->va = PTR_ALIGN(mbox_mem_alloc->va, 16);
 	mbox_mem_align->dma = PTR_ALIGN(mbox_mem_alloc->dma, 16);
-	memset(mbox_mem_align->va, 0, sizeof(struct be_mcc_mailbox));
 
 	rx_filter->size = sizeof(struct be_cmd_req_rx_filter);
 	rx_filter->va = dma_zalloc_coherent(dev, rx_filter->size,
@@ -5382,6 +5611,30 @@ static void be_remove(struct pci_dev *pdev)
 	free_netdev(adapter->netdev);
 }
 
+static ssize_t be_hwmon_show_temp(struct device *dev,
+				  struct device_attribute *dev_attr,
+				  char *buf)
+{
+	struct be_adapter *adapter = dev_get_drvdata(dev);
+
+	/* Unit: millidegree Celsius */
+	if (adapter->hwmon_info.be_on_die_temp == BE_INVALID_DIE_TEMP)
+		return -EIO;
+	else
+		return sprintf(buf, "%u\n",
+			       adapter->hwmon_info.be_on_die_temp * 1000);
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO,
+			  be_hwmon_show_temp, NULL, 1);
+
+static struct attribute *be_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(be_hwmon);
+
 static char *mc_name(struct be_adapter *adapter)
 {
 	char *str = "";	/* default */
@@ -5501,6 +5754,16 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
 
 	be_schedule_err_detection(adapter);
 
+	/* On Die temperature not supported for VF. */
+	if (be_physfn(adapter) && IS_ENABLED(CONFIG_BE2NET_HWMON)) {
+		adapter->hwmon_info.hwmon_dev =
+			devm_hwmon_device_register_with_groups(&pdev->dev,
+							       DRV_NAME,
+							       adapter,
+							       be_hwmon_groups);
+		adapter->hwmon_info.be_on_die_temp = BE_INVALID_DIE_TEMP;
+	}
+
 	dev_info(&pdev->dev, "%s: %s %s port %c\n", nic_name(pdev),
 		 func_name(adapter), mc_name(adapter), adapter->port_name);
 
@@ -5593,8 +5856,8 @@ static pci_ers_result_t be_eeh_err_detected(struct pci_dev *pdev,
 
 	dev_err(&adapter->pdev->dev, "EEH error detected\n");
 
-	if (!adapter->eeh_error) {
-		adapter->eeh_error = true;
+	if (!be_check_error(adapter, BE_ERROR_EEH)) {
+		be_set_error(adapter, BE_ERROR_EEH);
 
 		be_cancel_err_detection(adapter);
 
@@ -5641,7 +5904,7 @@ static pci_ers_result_t be_eeh_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	pci_cleanup_aer_uncorrect_error_status(pdev);
-	be_clear_all_error(adapter);
+	be_clear_error(adapter, BE_CLEAR_ALL);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 132866433a25..60368207bf58 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index e6f7eb1a7d87..cde6ef905ec4 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2005 - 2014 Emulex
+ * Copyright (C) 2005 - 2015 Emulex
  * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig
new file mode 100644
index 000000000000..48ecbc8aaaea
--- /dev/null
+++ b/drivers/net/ethernet/ezchip/Kconfig
@@ -0,0 +1,26 @@
+#
+# EZchip network device configuration
+#
+
+config NET_VENDOR_EZCHIP
+	bool "EZchip devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) device belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about EZchip devices. If you say Y, you will be asked for
+	  your specific device in the following questions.
+
+if NET_VENDOR_EZCHIP
+
+config EZCHIP_NPS_MANAGEMENT_ENET
+	tristate "EZchip NPS management enet support"
+	depends on OF_IRQ && OF_NET
+	---help---
+	  Simple LAN device for debug or management purposes.
+	  Device supports interrupts for RX and TX(completion).
+	  Device does not have DMA ability.
+
+endif
diff --git a/drivers/net/ethernet/ezchip/Makefile b/drivers/net/ethernet/ezchip/Makefile
new file mode 100644
index 000000000000..e490176a8137
--- /dev/null
+++ b/drivers/net/ethernet/ezchip/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_EZCHIP_NPS_MANAGEMENT_ENET) += nps_enet.o
diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c
new file mode 100644
index 000000000000..24a85b292007
--- /dev/null
+++ b/drivers/net/ethernet/ezchip/nps_enet.c
@@ -0,0 +1,658 @@
+/*
+ * Copyright(c) 2015 EZchip Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ */
+
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include "nps_enet.h"
+
+#define DRV_NAME			"nps_mgt_enet"
+
+static void nps_enet_clean_rx_fifo(struct net_device *ndev, u32 frame_len)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	u32 i, len = DIV_ROUND_UP(frame_len, sizeof(u32));
+
+	/* Empty Rx FIFO buffer by reading all words */
+	for (i = 0; i < len; i++)
+		nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF);
+}
+
+static void nps_enet_read_rx_fifo(struct net_device *ndev,
+				  unsigned char *dst, u32 length)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	s32 i, last = length & (sizeof(u32) - 1);
+	u32 *reg = (u32 *)dst, len = length / sizeof(u32);
+	bool dst_is_aligned = IS_ALIGNED((unsigned long)dst, sizeof(u32));
+
+	/* In case dst is not aligned we need an intermediate buffer */
+	if (dst_is_aligned)
+		for (i = 0; i < len; i++, reg++)
+			*reg = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF);
+	else { /* !dst_is_aligned */
+		for (i = 0; i < len; i++, reg++) {
+			u32 buf =
+				nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF);
+
+			/* to accommodate word-unaligned address of "reg"
+			 * we have to do memcpy_toio() instead of simple "=".
+			 */
+			memcpy_toio((void __iomem *)reg, &buf, sizeof(buf));
+		}
+	}
+
+	/* copy last bytes (if any) */
+	if (last) {
+		u32 buf = nps_enet_reg_get(priv, NPS_ENET_REG_RX_BUF);
+
+		memcpy_toio((void __iomem *)reg, &buf, last);
+	}
+}
+
+static u32 nps_enet_rx_handler(struct net_device *ndev)
+{
+	u32 frame_len, err = 0;
+	u32 work_done = 0;
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct sk_buff *skb;
+	struct nps_enet_rx_ctl rx_ctrl;
+
+	rx_ctrl.value = nps_enet_reg_get(priv, NPS_ENET_REG_RX_CTL);
+	frame_len = rx_ctrl.nr;
+
+	/* Check if we got RX */
+	if (!rx_ctrl.cr)
+		return work_done;
+
+	/* If we got here there is a work for us */
+	work_done++;
+
+	/* Check Rx error */
+	if (rx_ctrl.er) {
+		ndev->stats.rx_errors++;
+		err = 1;
+	}
+
+	/* Check Rx CRC error */
+	if (rx_ctrl.crc) {
+		ndev->stats.rx_crc_errors++;
+		ndev->stats.rx_dropped++;
+		err = 1;
+	}
+
+	/* Check Frame length Min 64b */
+	if (unlikely(frame_len < ETH_ZLEN)) {
+		ndev->stats.rx_length_errors++;
+		ndev->stats.rx_dropped++;
+		err = 1;
+	}
+
+	if (err)
+		goto rx_irq_clean;
+
+	/* Skb allocation */
+	skb = netdev_alloc_skb_ip_align(ndev, frame_len);
+	if (unlikely(!skb)) {
+		ndev->stats.rx_errors++;
+		ndev->stats.rx_dropped++;
+		goto rx_irq_clean;
+	}
+
+	/* Copy frame from Rx fifo into the skb */
+	nps_enet_read_rx_fifo(ndev, skb->data, frame_len);
+
+	skb_put(skb, frame_len);
+	skb->protocol = eth_type_trans(skb, ndev);
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	ndev->stats.rx_packets++;
+	ndev->stats.rx_bytes += frame_len;
+	netif_receive_skb(skb);
+
+	goto rx_irq_frame_done;
+
+rx_irq_clean:
+	/* Clean Rx fifo */
+	nps_enet_clean_rx_fifo(ndev, frame_len);
+
+rx_irq_frame_done:
+	/* Ack Rx ctrl register */
+	nps_enet_reg_set(priv, NPS_ENET_REG_RX_CTL, 0);
+
+	return work_done;
+}
+
+static void nps_enet_tx_handler(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_tx_ctl tx_ctrl;
+
+	tx_ctrl.value = nps_enet_reg_get(priv, NPS_ENET_REG_TX_CTL);
+
+	/* Check if we got TX */
+	if (!priv->tx_packet_sent || tx_ctrl.ct)
+		return;
+
+	/* Check Tx transmit error */
+	if (unlikely(tx_ctrl.et)) {
+		ndev->stats.tx_errors++;
+	} else {
+		ndev->stats.tx_packets++;
+		ndev->stats.tx_bytes += tx_ctrl.nt;
+	}
+
+	if (priv->tx_skb) {
+		dev_kfree_skb(priv->tx_skb);
+		priv->tx_skb = NULL;
+	}
+
+	priv->tx_packet_sent = false;
+
+	if (netif_queue_stopped(ndev))
+		netif_wake_queue(ndev);
+}
+
+/**
+ * nps_enet_poll - NAPI poll handler.
+ * @napi:       Pointer to napi_struct structure.
+ * @budget:     How many frames to process on one call.
+ *
+ * returns:     Number of processed frames
+ */
+static int nps_enet_poll(struct napi_struct *napi, int budget)
+{
+	struct net_device *ndev = napi->dev;
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_buf_int_enable buf_int_enable;
+	u32 work_done;
+
+	buf_int_enable.rx_rdy = NPS_ENET_ENABLE;
+	buf_int_enable.tx_done = NPS_ENET_ENABLE;
+	nps_enet_tx_handler(ndev);
+	work_done = nps_enet_rx_handler(ndev);
+	if (work_done < budget) {
+		napi_complete(napi);
+		nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE,
+				 buf_int_enable.value);
+	}
+
+	return work_done;
+}
+
+/**
+ * nps_enet_irq_handler - Global interrupt handler for ENET.
+ * @irq:                irq number.
+ * @dev_instance:       device instance.
+ *
+ * returns: IRQ_HANDLED for all cases.
+ *
+ * EZchip ENET has 2 interrupt causes, and depending on bits raised in
+ * CTRL registers we may tell what is a reason for interrupt to fire up.
+ * We got one for RX and the other for TX (completion).
+ */
+static irqreturn_t nps_enet_irq_handler(s32 irq, void *dev_instance)
+{
+	struct net_device *ndev = dev_instance;
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_buf_int_cause buf_int_cause;
+
+	buf_int_cause.value =
+			nps_enet_reg_get(priv, NPS_ENET_REG_BUF_INT_CAUSE);
+
+	if (buf_int_cause.tx_done || buf_int_cause.rx_rdy)
+		if (likely(napi_schedule_prep(&priv->napi))) {
+			nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0);
+			__napi_schedule(&priv->napi);
+		}
+
+	return IRQ_HANDLED;
+}
+
+static void nps_enet_set_hw_mac_address(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_ge_mac_cfg_1 ge_mac_cfg_1;
+	struct nps_enet_ge_mac_cfg_2 *ge_mac_cfg_2 = &priv->ge_mac_cfg_2;
+
+	/* set MAC address in HW */
+	ge_mac_cfg_1.octet_0 = ndev->dev_addr[0];
+	ge_mac_cfg_1.octet_1 = ndev->dev_addr[1];
+	ge_mac_cfg_1.octet_2 = ndev->dev_addr[2];
+	ge_mac_cfg_1.octet_3 = ndev->dev_addr[3];
+	ge_mac_cfg_2->octet_4 = ndev->dev_addr[4];
+	ge_mac_cfg_2->octet_5 = ndev->dev_addr[5];
+
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_1,
+			 ge_mac_cfg_1.value);
+
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_2,
+			 ge_mac_cfg_2->value);
+}
+
+/**
+ * nps_enet_hw_reset - Reset the network device.
+ * @ndev:       Pointer to the network device.
+ *
+ * This function reset the PCS and TX fifo.
+ * The programming model is to set the relevant reset bits
+ * wait for some time for this to propagate and then unset
+ * the reset bits. This way we ensure that reset procedure
+ * is done successfully by device.
+ */
+static void nps_enet_hw_reset(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_ge_rst ge_rst;
+	struct nps_enet_phase_fifo_ctl phase_fifo_ctl;
+
+	ge_rst.value = 0;
+	phase_fifo_ctl.value = 0;
+	/* Pcs reset sequence*/
+	ge_rst.gmac_0 = NPS_ENET_ENABLE;
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst.value);
+	usleep_range(10, 20);
+	ge_rst.value = 0;
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_RST, ge_rst.value);
+
+	/* Tx fifo reset sequence */
+	phase_fifo_ctl.rst = NPS_ENET_ENABLE;
+	phase_fifo_ctl.init = NPS_ENET_ENABLE;
+	nps_enet_reg_set(priv, NPS_ENET_REG_PHASE_FIFO_CTL,
+			 phase_fifo_ctl.value);
+	usleep_range(10, 20);
+	phase_fifo_ctl.value = 0;
+	nps_enet_reg_set(priv, NPS_ENET_REG_PHASE_FIFO_CTL,
+			 phase_fifo_ctl.value);
+}
+
+static void nps_enet_hw_enable_control(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_ge_mac_cfg_0 ge_mac_cfg_0;
+	struct nps_enet_buf_int_enable buf_int_enable;
+	struct nps_enet_ge_mac_cfg_2 *ge_mac_cfg_2 = &priv->ge_mac_cfg_2;
+	struct nps_enet_ge_mac_cfg_3 *ge_mac_cfg_3 = &priv->ge_mac_cfg_3;
+	s32 max_frame_length;
+
+	ge_mac_cfg_0.value = 0;
+	buf_int_enable.value = 0;
+	/* Enable Rx and Tx statistics */
+	ge_mac_cfg_2->stat_en = NPS_ENET_GE_MAC_CFG_2_STAT_EN;
+
+	/* Discard packets with different MAC address */
+	ge_mac_cfg_2->disc_da = NPS_ENET_ENABLE;
+
+	/* Discard multicast packets */
+	ge_mac_cfg_2->disc_mc = NPS_ENET_ENABLE;
+
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_2,
+			 ge_mac_cfg_2->value);
+
+	/* Discard Packets bigger than max frame length */
+	max_frame_length = ETH_HLEN + ndev->mtu + ETH_FCS_LEN;
+	if (max_frame_length <= NPS_ENET_MAX_FRAME_LENGTH) {
+		ge_mac_cfg_3->max_len = max_frame_length;
+		nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_3,
+				 ge_mac_cfg_3->value);
+	}
+
+	/* Enable interrupts */
+	buf_int_enable.rx_rdy = NPS_ENET_ENABLE;
+	buf_int_enable.tx_done = NPS_ENET_ENABLE;
+	nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE,
+			 buf_int_enable.value);
+
+	/* Write device MAC address to HW */
+	nps_enet_set_hw_mac_address(ndev);
+
+	/* Rx and Tx HW features */
+	ge_mac_cfg_0.tx_pad_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.tx_crc_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.rx_crc_strip = NPS_ENET_ENABLE;
+
+	/* IFG configuration */
+	ge_mac_cfg_0.rx_ifg = NPS_ENET_GE_MAC_CFG_0_RX_IFG;
+	ge_mac_cfg_0.tx_ifg = NPS_ENET_GE_MAC_CFG_0_TX_IFG;
+
+	/* preamble configuration */
+	ge_mac_cfg_0.rx_pr_check_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.tx_pr_len = NPS_ENET_GE_MAC_CFG_0_TX_PR_LEN;
+
+	/* enable flow control frames */
+	ge_mac_cfg_0.tx_fc_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.rx_fc_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.tx_fc_retr = NPS_ENET_GE_MAC_CFG_0_TX_FC_RETR;
+
+	/* Enable Rx and Tx */
+	ge_mac_cfg_0.rx_en = NPS_ENET_ENABLE;
+	ge_mac_cfg_0.tx_en = NPS_ENET_ENABLE;
+
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_0,
+			 ge_mac_cfg_0.value);
+}
+
+static void nps_enet_hw_disable_control(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+
+	/* Disable interrupts */
+	nps_enet_reg_set(priv, NPS_ENET_REG_BUF_INT_ENABLE, 0);
+
+	/* Disable Rx and Tx */
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_0, 0);
+}
+
+static void nps_enet_send_frame(struct net_device *ndev,
+				struct sk_buff *skb)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_tx_ctl tx_ctrl;
+	short length = skb->len;
+	u32 i, len = DIV_ROUND_UP(length, sizeof(u32));
+	u32 *src = (u32 *)virt_to_phys(skb->data);
+	bool src_is_aligned = IS_ALIGNED((unsigned long)src, sizeof(u32));
+
+	tx_ctrl.value = 0;
+	/* In case src is not aligned we need an intermediate buffer */
+	if (src_is_aligned)
+		for (i = 0; i < len; i++, src++)
+			nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, *src);
+	else { /* !src_is_aligned */
+		for (i = 0; i < len; i++, src++) {
+			u32 buf;
+
+			/* to accommodate word-unaligned address of "src"
+			 * we have to do memcpy_fromio() instead of simple "="
+			 */
+			memcpy_fromio(&buf, (void __iomem *)src, sizeof(buf));
+			nps_enet_reg_set(priv, NPS_ENET_REG_TX_BUF, buf);
+		}
+	}
+	/* Write the length of the Frame */
+	tx_ctrl.nt = length;
+
+	/* Indicate SW is done */
+	priv->tx_packet_sent = true;
+	tx_ctrl.ct = NPS_ENET_ENABLE;
+
+	/* Send Frame */
+	nps_enet_reg_set(priv, NPS_ENET_REG_TX_CTL, tx_ctrl.value);
+}
+
+/**
+ * nps_enet_set_mac_address - Set the MAC address for this device.
+ * @ndev:       Pointer to net_device structure.
+ * @p:          6 byte Address to be written as MAC address.
+ *
+ * This function copies the HW address from the sockaddr structure to the
+ * net_device structure and updates the address in HW.
+ *
+ * returns:     -EBUSY if the net device is busy or 0 if the address is set
+ *              successfully.
+ */
+static s32 nps_enet_set_mac_address(struct net_device *ndev, void *p)
+{
+	struct sockaddr *addr = p;
+	s32 res;
+
+	if (netif_running(ndev))
+		return -EBUSY;
+
+	res = eth_mac_addr(ndev, p);
+	if (!res) {
+		ether_addr_copy(ndev->dev_addr, addr->sa_data);
+		nps_enet_set_hw_mac_address(ndev);
+	}
+
+	return res;
+}
+
+/**
+ * nps_enet_set_rx_mode - Change the receive filtering mode.
+ * @ndev:       Pointer to the network device.
+ *
+ * This function enables/disables promiscuous mode
+ */
+static void nps_enet_set_rx_mode(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	struct nps_enet_ge_mac_cfg_2 ge_mac_cfg_2;
+
+	ge_mac_cfg_2.value = priv->ge_mac_cfg_2.value;
+
+	if (ndev->flags & IFF_PROMISC) {
+		ge_mac_cfg_2.disc_da = NPS_ENET_DISABLE;
+		ge_mac_cfg_2.disc_mc = NPS_ENET_DISABLE;
+	} else {
+		ge_mac_cfg_2.disc_da = NPS_ENET_ENABLE;
+		ge_mac_cfg_2.disc_mc = NPS_ENET_ENABLE;
+	}
+
+	nps_enet_reg_set(priv, NPS_ENET_REG_GE_MAC_CFG_2, ge_mac_cfg_2.value);
+}
+
+/**
+ * nps_enet_open - Open the network device.
+ * @ndev:       Pointer to the network device.
+ *
+ * returns: 0, on success or non-zero error value on failure.
+ *
+ * This function sets the MAC address, requests and enables an IRQ
+ * for the ENET device and starts the Tx queue.
+ */
+static s32 nps_enet_open(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+	s32 err;
+
+	/* Reset private variables */
+	priv->tx_packet_sent = false;
+	priv->ge_mac_cfg_2.value = 0;
+	priv->ge_mac_cfg_3.value = 0;
+
+	/* ge_mac_cfg_3 default values */
+	priv->ge_mac_cfg_3.rx_ifg_th = NPS_ENET_GE_MAC_CFG_3_RX_IFG_TH;
+	priv->ge_mac_cfg_3.max_len = NPS_ENET_GE_MAC_CFG_3_MAX_LEN;
+
+	/* Disable HW device */
+	nps_enet_hw_disable_control(ndev);
+
+	/* irq Rx allocation */
+	err = request_irq(priv->irq, nps_enet_irq_handler,
+			  0, "enet-rx-tx", ndev);
+	if (err)
+		return err;
+
+	napi_enable(&priv->napi);
+
+	/* Enable HW device */
+	nps_enet_hw_reset(ndev);
+	nps_enet_hw_enable_control(ndev);
+
+	netif_start_queue(ndev);
+
+	return 0;
+}
+
+/**
+ * nps_enet_stop - Close the network device.
+ * @ndev:       Pointer to the network device.
+ *
+ * This function stops the Tx queue, disables interrupts for the ENET device.
+ */
+static s32 nps_enet_stop(struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+
+	napi_disable(&priv->napi);
+	netif_stop_queue(ndev);
+	nps_enet_hw_disable_control(ndev);
+	free_irq(priv->irq, ndev);
+
+	return 0;
+}
+
+/**
+ * nps_enet_start_xmit - Starts the data transmission.
+ * @skb:        sk_buff pointer that contains data to be Transmitted.
+ * @ndev:       Pointer to net_device structure.
+ *
+ * returns: NETDEV_TX_OK, on success
+ *              NETDEV_TX_BUSY, if any of the descriptors are not free.
+ *
+ * This function is invoked from upper layers to initiate transmission.
+ */
+static netdev_tx_t nps_enet_start_xmit(struct sk_buff *skb,
+				       struct net_device *ndev)
+{
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+
+	/* This driver handles one frame at a time  */
+	netif_stop_queue(ndev);
+
+	nps_enet_send_frame(ndev, skb);
+
+	priv->tx_skb = skb;
+
+	return NETDEV_TX_OK;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void nps_enet_poll_controller(struct net_device *ndev)
+{
+	disable_irq(ndev->irq);
+	nps_enet_irq_handler(ndev->irq, ndev);
+	enable_irq(ndev->irq);
+}
+#endif
+
+static const struct net_device_ops nps_netdev_ops = {
+	.ndo_open		= nps_enet_open,
+	.ndo_stop		= nps_enet_stop,
+	.ndo_start_xmit		= nps_enet_start_xmit,
+	.ndo_set_mac_address	= nps_enet_set_mac_address,
+	.ndo_set_rx_mode        = nps_enet_set_rx_mode,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= nps_enet_poll_controller,
+#endif
+};
+
+static s32 nps_enet_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct net_device *ndev;
+	struct nps_enet_priv *priv;
+	s32 err = 0;
+	const char *mac_addr;
+	struct resource *res_regs;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	ndev = alloc_etherdev(sizeof(struct nps_enet_priv));
+	if (!ndev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, ndev);
+	SET_NETDEV_DEV(ndev, dev);
+	priv = netdev_priv(ndev);
+
+	/* The EZ NET specific entries in the device structure. */
+	ndev->netdev_ops = &nps_netdev_ops;
+	ndev->watchdog_timeo = (400 * HZ / 1000);
+	/* FIXME :: no multicast support yet */
+	ndev->flags &= ~IFF_MULTICAST;
+
+	res_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->regs_base = devm_ioremap_resource(dev, res_regs);
+	if (IS_ERR(priv->regs_base)) {
+		err = PTR_ERR(priv->regs_base);
+		goto out_netdev;
+	}
+	dev_dbg(dev, "Registers base address is 0x%p\n", priv->regs_base);
+
+	/* set kernel MAC address to dev */
+	mac_addr = of_get_mac_address(dev->of_node);
+	if (mac_addr)
+		ether_addr_copy(ndev->dev_addr, mac_addr);
+	else
+		eth_hw_addr_random(ndev);
+
+	/* Get IRQ number */
+	priv->irq = platform_get_irq(pdev, 0);
+	if (!priv->irq) {
+		dev_err(dev, "failed to retrieve <irq Rx-Tx> value from device tree\n");
+		err = -ENODEV;
+		goto out_netdev;
+	}
+
+	netif_napi_add(ndev, &priv->napi, nps_enet_poll,
+		       NPS_ENET_NAPI_POLL_WEIGHT);
+
+	/* Register the driver. Should be the last thing in probe */
+	err = register_netdev(ndev);
+	if (err) {
+		dev_err(dev, "Failed to register ndev for %s, err = 0x%08x\n",
+			ndev->name, (s32)err);
+		goto out_netif_api;
+	}
+
+	dev_info(dev, "(rx/tx=%d)\n", priv->irq);
+	return 0;
+
+out_netif_api:
+	netif_napi_del(&priv->napi);
+out_netdev:
+	if (err)
+		free_netdev(ndev);
+
+	return err;
+}
+
+static s32 nps_enet_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct nps_enet_priv *priv = netdev_priv(ndev);
+
+	unregister_netdev(ndev);
+	free_netdev(ndev);
+	netif_napi_del(&priv->napi);
+
+	return 0;
+}
+
+static const struct of_device_id nps_enet_dt_ids[] = {
+	{ .compatible = "ezchip,nps-mgt-enet" },
+	{ /* Sentinel */ }
+};
+
+static struct platform_driver nps_enet_driver = {
+	.probe = nps_enet_probe,
+	.remove = nps_enet_remove,
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table  = nps_enet_dt_ids,
+	},
+};
+
+module_platform_driver(nps_enet_driver);
+
+MODULE_AUTHOR("EZchip Semiconductor");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/ezchip/nps_enet.h b/drivers/net/ethernet/ezchip/nps_enet.h
new file mode 100644
index 000000000000..fc45c9daa1c2
--- /dev/null
+++ b/drivers/net/ethernet/ezchip/nps_enet.h
@@ -0,0 +1,336 @@
+/*
+ * Copyright(c) 2015 EZchip Technologies.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ */
+
+#ifndef _NPS_ENET_H
+#define _NPS_ENET_H
+
+/* default values */
+#define NPS_ENET_NAPI_POLL_WEIGHT		0x2
+#define NPS_ENET_MAX_FRAME_LENGTH		0x3FFF
+#define NPS_ENET_GE_MAC_CFG_0_TX_FC_RETR	0x7
+#define NPS_ENET_GE_MAC_CFG_0_RX_IFG		0x5
+#define NPS_ENET_GE_MAC_CFG_0_TX_IFG		0xC
+#define NPS_ENET_GE_MAC_CFG_0_TX_PR_LEN		0x7
+#define NPS_ENET_GE_MAC_CFG_2_STAT_EN		0x3
+#define NPS_ENET_GE_MAC_CFG_3_RX_IFG_TH		0x14
+#define NPS_ENET_GE_MAC_CFG_3_MAX_LEN		0x3FFC
+#define NPS_ENET_ENABLE				1
+#define NPS_ENET_DISABLE			0
+
+/* register definitions  */
+#define NPS_ENET_REG_TX_CTL		0x800
+#define NPS_ENET_REG_TX_BUF		0x808
+#define NPS_ENET_REG_RX_CTL		0x810
+#define NPS_ENET_REG_RX_BUF		0x818
+#define NPS_ENET_REG_BUF_INT_ENABLE	0x8C0
+#define NPS_ENET_REG_BUF_INT_CAUSE	0x8C4
+#define NPS_ENET_REG_GE_MAC_CFG_0	0x1000
+#define NPS_ENET_REG_GE_MAC_CFG_1	0x1004
+#define NPS_ENET_REG_GE_MAC_CFG_2	0x1008
+#define NPS_ENET_REG_GE_MAC_CFG_3	0x100C
+#define NPS_ENET_REG_GE_RST		0x1400
+#define NPS_ENET_REG_PHASE_FIFO_CTL	0x1404
+
+/* Tx control register */
+struct nps_enet_tx_ctl {
+	union {
+		/* ct: SW sets to indicate frame ready in Tx buffer for
+		 *     transmission. HW resets to when transmission done
+		 * et: Transmit error
+		 * nt: Length in bytes of Tx frame loaded to Tx buffer
+		 */
+		struct {
+			u32
+			__reserved_1:16,
+			ct:1,
+			et:1,
+			__reserved_2:3,
+			nt:11;
+		};
+
+		u32 value;
+	};
+};
+
+/* Rx control register */
+struct nps_enet_rx_ctl {
+	union {
+		/* cr:  HW sets to indicate frame ready in Rx buffer.
+		 *      SW resets to indicate host read received frame
+		 *      and new frames can be written to Rx buffer
+		 * er:  Rx error indication
+		 * crc: Rx CRC error indication
+		 * nr:  Length in bytes of Rx frame loaded by MAC to Rx buffer
+		 */
+		struct {
+			u32
+			__reserved_1:16,
+			cr:1,
+			er:1,
+			crc:1,
+			__reserved_2:2,
+			nr:11;
+		};
+
+		u32 value;
+	};
+};
+
+/* Interrupt enable for data buffer events register */
+struct nps_enet_buf_int_enable {
+	union {
+		/* tx_done: Interrupt generation in the case when new frame
+		 *          is ready in Rx buffer
+		 * rx_rdy:  Interrupt generation in the case when current frame
+		 *          was read from TX buffer
+		 */
+		struct {
+			u32
+			__reserved:30,
+			tx_done:1,
+			rx_rdy:1;
+		};
+
+		u32 value;
+	};
+};
+
+/* Interrupt cause for data buffer events register */
+struct nps_enet_buf_int_cause {
+	union {
+		/* tx_done: Interrupt in the case when current frame was
+		 *          read from TX buffer.
+		 * rx_rdy:  Interrupt in the case when new frame is ready
+		 *          in RX buffer.
+		 */
+		struct {
+			u32
+			__reserved:30,
+			tx_done:1,
+			rx_rdy:1;
+		};
+
+		u32 value;
+	};
+};
+
+/* Gbps Eth MAC Configuration 0 register */
+struct nps_enet_ge_mac_cfg_0 {
+	union {
+		/* tx_pr_len:          Transmit preamble length in bytes
+		 * tx_ifg_nib:         Tx idle pattern
+		 * nib_mode:           Nibble (4-bit) Mode
+		 * rx_pr_check_en:     Receive preamble Check Enable
+		 * tx_ifg:             Transmit inter-Frame Gap
+		 * rx_ifg:             Receive inter-Frame Gap
+		 * tx_fc_retr:         Transmit Flow Control Retransmit Mode
+		 * rx_length_check_en: Receive Length Check Enable
+		 * rx_crc_ignore:      Results of the CRC check are ignored
+		 * rx_crc_strip:       MAC strips the CRC from received frames
+		 * rx_fc_en:           Receive Flow Control Enable
+		 * tx_crc_en:          Transmit CRC Enabled
+		 * tx_pad_en:          Transmit Padding Enable
+		 * tx_cf_en:           Transmit Flow Control Enable
+		 * tx_en:              Transmit Enable
+		 * rx_en:              Receive Enable
+		 */
+		struct {
+			u32
+			tx_pr_len:4,
+			tx_ifg_nib:4,
+			nib_mode:1,
+			rx_pr_check_en:1,
+			tx_ifg:6,
+			rx_ifg:4,
+			tx_fc_retr:3,
+			rx_length_check_en:1,
+			rx_crc_ignore:1,
+			rx_crc_strip:1,
+			rx_fc_en:1,
+			tx_crc_en:1,
+			tx_pad_en:1,
+			tx_fc_en:1,
+			tx_en:1,
+			rx_en:1;
+		};
+
+		u32 value;
+	};
+};
+
+/* Gbps Eth MAC Configuration 1 register */
+struct nps_enet_ge_mac_cfg_1 {
+	union {
+		/* octet_3: MAC address octet 3
+		 * octet_2: MAC address octet 2
+		 * octet_1: MAC address octet 1
+		 * octet_0: MAC address octet 0
+		 */
+		struct {
+			u32
+			octet_3:8,
+			octet_2:8,
+			octet_1:8,
+			octet_0:8;
+		};
+
+		u32 value;
+	};
+};
+
+/* Gbps Eth MAC Configuration 2 register */
+struct nps_enet_ge_mac_cfg_2 {
+	union {
+		/* transmit_flush_en: MAC flush enable
+		 * stat_en:           RMON statistics interface enable
+		 * disc_da:           Discard frames with DA different
+		 *                    from MAC address
+		 * disc_bc:           Discard broadcast frames
+		 * disc_mc:           Discard multicast frames
+		 * octet_5:           MAC address octet 5
+		 * octet_4:           MAC address octet 4
+		 */
+		struct {
+			u32
+			transmit_flush_en:1,
+			__reserved_1:5,
+			stat_en:2,
+			__reserved_2:1,
+			disc_da:1,
+			disc_bc:1,
+			disc_mc:1,
+			__reserved_3:4,
+			octet_5:8,
+			octet_4:8;
+		};
+
+		u32 value;
+	};
+};
+
+/* Gbps Eth MAC Configuration 3 register */
+struct nps_enet_ge_mac_cfg_3 {
+	union {
+		/* ext_oob_cbfc_sel:  Selects one of the 4 profiles for
+		 *                    extended OOB in-flow-control indication
+		 * max_len:           Maximum receive frame length in bytes
+		 * tx_cbfc_en:        Enable transmission of class-based
+		 *                    flow control packets
+		 * rx_ifg_th:         Threshold for IFG status reporting via OOB
+		 * cf_timeout:        Configurable time to decrement FC counters
+		 * cf_drop:           Drop control frames
+		 * redirect_cbfc_sel: Selects one of CBFC redirect profiles
+		 * rx_cbfc_redir_en:  Enable Rx class-based flow
+		 *                    control redirect
+		 * rx_cbfc_en:        Enable Rx class-based flow control
+		 * tm_hd_mode:        TM header mode
+		 */
+		struct {
+			u32
+			ext_oob_cbfc_sel:2,
+			max_len:14,
+			tx_cbfc_en:1,
+			rx_ifg_th:5,
+			cf_timeout:4,
+			cf_drop:1,
+			redirect_cbfc_sel:2,
+			rx_cbfc_redir_en:1,
+			rx_cbfc_en:1,
+			tm_hd_mode:1;
+		};
+
+		u32 value;
+	};
+};
+
+/* GE MAC, PCS reset control register */
+struct nps_enet_ge_rst {
+	union {
+		/* gmac_0: GE MAC reset
+		 * spcs_0: SGMII PCS reset
+		 */
+		struct {
+			u32
+			__reserved_1:23,
+			gmac_0:1,
+			__reserved_2:7,
+			spcs_0:1;
+		};
+
+		u32 value;
+	};
+};
+
+/* Tx phase sync FIFO control register */
+struct nps_enet_phase_fifo_ctl {
+	union {
+		/* init: initialize serdes TX phase sync FIFO pointers
+		 * rst:  reset serdes TX phase sync FIFO
+		 */
+		struct {
+			u32
+			__reserved:30,
+			init:1,
+			rst:1;
+		};
+
+		u32 value;
+	};
+};
+
+/**
+ * struct nps_enet_priv - Storage of ENET's private information.
+ * @regs_base:      Base address of ENET memory-mapped control registers.
+ * @irq:            For RX/TX IRQ number.
+ * @tx_packet_sent: SW indication if frame is being sent.
+ * @tx_skb:         socket buffer of sent frame.
+ * @napi:           Structure for NAPI.
+ */
+struct nps_enet_priv {
+	void __iomem *regs_base;
+	s32 irq;
+	bool tx_packet_sent;
+	struct sk_buff *tx_skb;
+	struct napi_struct napi;
+	struct nps_enet_ge_mac_cfg_2 ge_mac_cfg_2;
+	struct nps_enet_ge_mac_cfg_3 ge_mac_cfg_3;
+};
+
+/**
+ * nps_reg_set - Sets ENET register with provided value.
+ * @priv:       Pointer to EZchip ENET private data structure.
+ * @reg:        Register offset from base address.
+ * @value:      Value to set in register.
+ */
+static inline void nps_enet_reg_set(struct nps_enet_priv *priv,
+				    s32 reg, s32 value)
+{
+	iowrite32be(value, priv->regs_base + reg);
+}
+
+/**
+ * nps_reg_get - Gets value of specified ENET register.
+ * @priv:       Pointer to EZchip ENET private data structure.
+ * @reg:        Register offset from base address.
+ *
+ * returns:     Value of requested register.
+ */
+static inline u32 nps_enet_reg_get(struct nps_enet_priv *priv, s32 reg)
+{
+	return ioread32be(priv->regs_base + reg);
+}
+
+#endif /* _NPS_ENET_H */
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index 5918c6891694..040c7f163325 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_FARADAY
 	default y
 	depends on ARM
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 25e3425729d0..b8de87b03046 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -9,9 +9,7 @@ config NET_VENDOR_FREESCALE
 		   M523x || M527x || M5272 || M528x || M520x || M532x || \
 		   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 66d47e448e4d..e464aeaeed2c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2118,6 +2118,82 @@ static void fec_enet_get_drvinfo(struct net_device *ndev,
 	strlcpy(info->bus_info, dev_name(&ndev->dev), sizeof(info->bus_info));
 }
 
+static int fec_enet_get_regs_len(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct resource *r;
+	int s = 0;
+
+	r = platform_get_resource(fep->pdev, IORESOURCE_MEM, 0);
+	if (r)
+		s = resource_size(r);
+
+	return s;
+}
+
+/* List of registers that can be safety be read to dump them with ethtool */
+#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
+	defined(CONFIG_M520x) || defined(CONFIG_M532x) ||		\
+	defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
+static u32 fec_enet_register_offset[] = {
+	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
+	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
+	FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_TXIC1,
+	FEC_TXIC2, FEC_RXIC0, FEC_RXIC1, FEC_RXIC2, FEC_HASH_TABLE_HIGH,
+	FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW,
+	FEC_X_WMRK, FEC_R_BOUND, FEC_R_FSTART, FEC_R_DES_START_1,
+	FEC_X_DES_START_1, FEC_R_BUFF_SIZE_1, FEC_R_DES_START_2,
+	FEC_X_DES_START_2, FEC_R_BUFF_SIZE_2, FEC_R_DES_START_0,
+	FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM,
+	FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC, FEC_RCMR_1, FEC_RCMR_2,
+	FEC_DMA_CFG_1, FEC_DMA_CFG_2, FEC_R_DES_ACTIVE_1, FEC_X_DES_ACTIVE_1,
+	FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_2, FEC_QOS_SCHEME,
+	RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT,
+	RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG,
+	RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255,
+	RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047,
+	RMON_T_P_GTE2048, RMON_T_OCTETS,
+	IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF,
+	IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE,
+	IEEE_T_FDXFC, IEEE_T_OCTETS_OK,
+	RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN,
+	RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB,
+	RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255,
+	RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047,
+	RMON_R_P_GTE2048, RMON_R_OCTETS,
+	IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
+	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
+};
+#else
+static u32 fec_enet_register_offset[] = {
+	FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
+	FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
+	FEC_X_DES_ACTIVE_1, FEC_X_DES_ACTIVE_2, FEC_MII_DATA, FEC_MII_SPEED,
+	FEC_R_BOUND, FEC_R_FSTART, FEC_X_WMRK, FEC_X_FSTART, FEC_R_CNTRL,
+	FEC_MAX_FRM_LEN, FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH,
+	FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW, FEC_R_DES_START_0,
+	FEC_R_DES_START_1, FEC_R_DES_START_2, FEC_X_DES_START_0,
+	FEC_X_DES_START_1, FEC_X_DES_START_2, FEC_R_BUFF_SIZE_0,
+	FEC_R_BUFF_SIZE_1, FEC_R_BUFF_SIZE_2
+};
+#endif
+
+static void fec_enet_get_regs(struct net_device *ndev,
+			      struct ethtool_regs *regs, void *regbuf)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+	u32 *buf = (u32 *)regbuf;
+	u32 i, off;
+
+	memset(buf, 0, regs->len);
+
+	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
+		off = fec_enet_register_offset[i] / 4;
+		buf[off] = readl(&theregs[off]);
+	}
+}
+
 static int fec_enet_get_ts_info(struct net_device *ndev,
 				struct ethtool_ts_info *info)
 {
@@ -2515,6 +2591,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_settings		= fec_enet_get_settings,
 	.set_settings		= fec_enet_set_settings,
 	.get_drvinfo		= fec_enet_get_drvinfo,
+	.get_regs_len		= fec_enet_get_regs_len,
+	.get_regs		= fec_enet_get_regs,
 	.nway_reset		= fec_enet_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_coalesce		= fec_enet_get_coalesce,
@@ -2778,12 +2856,14 @@ fec_enet_open(struct net_device *ndev)
 	if (ret)
 		goto err_enet_alloc;
 
+	/* Init MAC prior to mii bus probe */
+	fec_restart(ndev);
+
 	/* Probe and connect to PHY when open the interface */
 	ret = fec_enet_mii_probe(ndev);
 	if (ret)
 		goto err_enet_mii_probe;
 
-	fec_restart(ndev);
 	napi_enable(&fep->napi);
 	phy_start(fep->phy_dev);
 	netif_tx_start_all_queues(ndev);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index a583d89b13c4..a15663ad7f5e 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -353,6 +353,7 @@ static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	tmp = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK;
 	tmp |= corr_ns << FEC_T_INC_CORR_OFFSET;
 	writel(tmp, fep->hwp + FEC_ATIME_INC);
+	corr_period = corr_period > 1 ? corr_period - 1 : corr_period;
 	writel(corr_period, fep->hwp + FEC_ATIME_CORR);
 	/* dummy read to update the timer. */
 	timecounter_read(&fep->tc);
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 9b3639eae676..56316db6c5a6 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -86,7 +86,7 @@ static int fs_enet_rx_napi(struct napi_struct *napi, int budget)
 	struct net_device *dev = fep->ndev;
 	const struct fs_platform_info *fpi = fep->fpi;
 	cbd_t __iomem *bdp;
-	struct sk_buff *skb, *skbn, *skbt;
+	struct sk_buff *skb, *skbn;
 	int received = 0;
 	u16 pkt_len, sc;
 	int curidx;
@@ -161,10 +161,7 @@ static int fs_enet_rx_napi(struct napi_struct *napi, int budget)
 					skb_reserve(skbn, 2);	/* align IP header */
 					skb_copy_from_linear_data(skb,
 						      skbn->data, pkt_len);
-					/* swap */
-					skbt = skb;
-					skb = skbn;
-					skbn = skbt;
+					swap(skb, skbn);
 				}
 			} else {
 				skbn = netdev_alloc_skb(dev, ENET_RX_FRSIZE);
@@ -490,6 +487,9 @@ static struct sk_buff *tx_skb_align_workaround(struct net_device *dev,
 {
 	struct sk_buff *new_skb;
 
+	if (skb_linearize(skb))
+		return NULL;
+
 	/* Alloc new skb */
 	new_skb = netdev_alloc_skb(dev, skb->len + 4);
 	if (!new_skb)
@@ -515,12 +515,27 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	cbd_t __iomem *bdp;
 	int curidx;
 	u16 sc;
-	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int nr_frags;
 	skb_frag_t *frag;
 	int len;
-
 #ifdef CONFIG_FS_ENET_MPC5121_FEC
-	if (((unsigned long)skb->data) & 0x3) {
+	int is_aligned = 1;
+	int i;
+
+	if (!IS_ALIGNED((unsigned long)skb->data, 4)) {
+		is_aligned = 0;
+	} else {
+		nr_frags = skb_shinfo(skb)->nr_frags;
+		frag = skb_shinfo(skb)->frags;
+		for (i = 0; i < nr_frags; i++, frag++) {
+			if (!IS_ALIGNED(frag->page_offset, 4)) {
+				is_aligned = 0;
+				break;
+			}
+		}
+	}
+
+	if (!is_aligned) {
 		skb = tx_skb_align_workaround(dev, skb);
 		if (!skb) {
 			/*
@@ -532,6 +547,7 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 #endif
+
 	spin_lock(&fep->tx_lock);
 
 	/*
@@ -539,6 +555,7 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	bdp = fep->cur_tx;
 
+	nr_frags = skb_shinfo(skb)->nr_frags;
 	if (fep->tx_free <= nr_frags || (CBDR_SC(bdp) & BD_ENET_TX_READY)) {
 		netif_stop_queue(dev);
 		spin_unlock(&fep->tx_lock);
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 4ee080d49bc0..ff875028fdff 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -516,6 +516,15 @@ static struct net_device_stats *gfar_get_stats(struct net_device *dev)
 	return &dev->stats;
 }
 
+static int gfar_set_mac_addr(struct net_device *dev, void *p)
+{
+	eth_mac_addr(dev, p);
+
+	gfar_set_mac_for_addr(dev, 0, dev->dev_addr);
+
+	return 0;
+}
+
 static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_open = gfar_enet_open,
 	.ndo_start_xmit = gfar_start_xmit,
@@ -526,7 +535,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
 	.ndo_get_stats = gfar_get_stats,
-	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_set_mac_address = gfar_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
@@ -1411,6 +1420,8 @@ static int gfar_probe(struct platform_device *ofdev)
 		dev->features |= NETIF_F_HW_VLAN_CTAG_RX;
 	}
 
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
 	gfar_init_addr_hash_table(priv);
 
 	/* Insert receive time stamps into padding alignment bytes */
@@ -2254,7 +2265,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int i, rq = 0;
 	int do_tstamp, do_csum, do_vlan;
 	u32 bufaddr;
-	unsigned long flags;
 	unsigned int nr_frags, nr_txbds, bytes_sent, fcb_len = 0;
 
 	rq = skb->queue_mapping;
@@ -2434,19 +2444,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netdev_tx_sent_queue(txq, bytes_sent);
 
-	/* We can work in parallel with gfar_clean_tx_ring(), except
-	 * when modifying num_txbdfree. Note that we didn't grab the lock
-	 * when we were reading the num_txbdfree and checking for available
-	 * space, that's because outside of this function it can only grow,
-	 * and once we've got needed space, it cannot suddenly disappear.
-	 *
-	 * The lock also protects us from gfar_error(), which can modify
-	 * regs->tstat and thus retrigger the transfers, which is why we
-	 * also must grab the lock before setting ready bit for the first
-	 * to be transmitted BD.
-	 */
-	spin_lock_irqsave(&tx_queue->txlock, flags);
-
 	gfar_wmb();
 
 	txbdp_start->lstatus = cpu_to_be32(lstatus);
@@ -2463,8 +2460,15 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_queue->cur_tx = next_txbd(txbdp, base, tx_queue->tx_ring_size);
 
+	/* We can work in parallel with gfar_clean_tx_ring(), except
+	 * when modifying num_txbdfree. Note that we didn't grab the lock
+	 * when we were reading the num_txbdfree and checking for available
+	 * space, that's because outside of this function it can only grow.
+	 */
+	spin_lock_bh(&tx_queue->txlock);
 	/* reduce TxBD free count */
 	tx_queue->num_txbdfree -= (nr_txbds);
+	spin_unlock_bh(&tx_queue->txlock);
 
 	/* If the next BD still needs to be cleaned up, then the bds
 	 * are full.  We need to tell the kernel to stop sending us stuff.
@@ -2478,9 +2482,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Tell the DMA to go go go */
 	gfar_write(&regs->tstat, TSTAT_CLEAR_THALT >> tx_queue->qindex);
 
-	/* Unlock priv */
-	spin_unlock_irqrestore(&tx_queue->txlock, flags);
-
 	return NETDEV_TX_OK;
 
 dma_map_err:
@@ -2622,7 +2623,6 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 	skb_dirtytx = tx_queue->skb_dirtytx;
 
 	while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) {
-		unsigned long flags;
 
 		frags = skb_shinfo(skb)->nr_frags;
 
@@ -2686,9 +2686,9 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 			      TX_RING_MOD_MASK(tx_ring_size);
 
 		howmany++;
-		spin_lock_irqsave(&tx_queue->txlock, flags);
+		spin_lock(&tx_queue->txlock);
 		tx_queue->num_txbdfree += nr_txbds;
-		spin_unlock_irqrestore(&tx_queue->txlock, flags);
+		spin_unlock(&tx_queue->txlock);
 	}
 
 	/* If we freed a buffer, we can restart transmission, if necessary */
@@ -3411,21 +3411,12 @@ static irqreturn_t gfar_error(int irq, void *grp_id)
 		if (events & IEVENT_CRL)
 			dev->stats.tx_aborted_errors++;
 		if (events & IEVENT_XFUN) {
-			unsigned long flags;
-
 			netif_dbg(priv, tx_err, dev,
 				  "TX FIFO underrun, packet dropped\n");
 			dev->stats.tx_dropped++;
 			atomic64_inc(&priv->extra_stats.tx_underrun);
 
-			local_irq_save(flags);
-			lock_tx_qs(priv);
-
-			/* Reactivate the Tx Queues */
-			gfar_write(&regs->tstat, gfargrp->tstat);
-
-			unlock_tx_qs(priv);
-			local_irq_restore(flags);
+			schedule_work(&priv->reset_task);
 		}
 		netif_dbg(priv, tx_err, dev, "Transmit Error\n");
 	}
diff --git a/drivers/net/ethernet/fujitsu/Kconfig b/drivers/net/ethernet/fujitsu/Kconfig
index 1085257385d2..faee34e44a35 100644
--- a/drivers/net/ethernet/fujitsu/Kconfig
+++ b/drivers/net/ethernet/fujitsu/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_FUJITSU
 	default y
 	depends on PCMCIA
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  the questions about Fujitsu cards. If you say Y, you will be asked for
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index a54d89791311..dead17b5d769 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_HISILICON
 	default y
 	depends on ARM
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 3b39fdddeb57..d49bee38cd31 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -798,7 +798,7 @@ static void hip04_free_ring(struct net_device *ndev, struct device *d)
 
 	for (i = 0; i < RX_DESC_NUM; i++)
 		if (priv->rx_buf[i])
-			put_page(virt_to_head_page(priv->rx_buf[i]));
+			skb_free_frag(priv->rx_buf[i]);
 
 	for (i = 0; i < TX_DESC_NUM; i++)
 		if (priv->tx_skb[i])
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index 0ffdcd381fdd..a5e077eac99a 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -500,7 +500,6 @@ static int hix5hd2_rx(struct net_device *dev, int limit)
 		napi_gro_receive(&priv->napi, skb);
 		dev->stats.rx_packets++;
 		dev->stats.rx_bytes += skb->len;
-		dev->last_rx = jiffies;
 next:
 		pos = dma_ring_incr(pos, RX_DESC_NUM);
 	}
diff --git a/drivers/net/ethernet/hp/Kconfig b/drivers/net/ethernet/hp/Kconfig
index a0b8ece1e3bc..d4df78c2abce 100644
--- a/drivers/net/ethernet/hp/Kconfig
+++ b/drivers/net/ethernet/hp/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_HP
 	default y
 	depends on ISA || EISA || PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -22,9 +20,7 @@ config HP100
 	tristate "HP 10/100VG PCLAN (ISA, EISA, PCI) support"
 	depends on (ISA || EISA || PCI)
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called hp100.
diff --git a/drivers/net/ethernet/i825xx/Kconfig b/drivers/net/ethernet/i825xx/Kconfig
index 9521e68aa3b3..e8d61f670479 100644
--- a/drivers/net/ethernet/i825xx/Kconfig
+++ b/drivers/net/ethernet/i825xx/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_I825XX
 	default y
 	depends on NET_VENDOR_INTEL
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question does not directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig
index 563a1ac71dbc..99c1cebd002d 100644
--- a/drivers/net/ethernet/ibm/Kconfig
+++ b/drivers/net/ethernet/ibm/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_IBM
 	default y
 	depends on PPC_PSERIES || PPC_DCR || (IBMEBUS && SPARSEMEM)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index de7919322190..b60a34d982a9 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2084,12 +2084,8 @@ static void emac_ethtool_get_pauseparam(struct net_device *ndev,
 
 static int emac_get_regs_len(struct emac_instance *dev)
 {
-	if (emac_has_feature(dev, EMAC_FTR_EMAC4))
-		return sizeof(struct emac_ethtool_regs_subhdr) +
-			EMAC4_ETHTOOL_REGS_SIZE(dev);
-	else
 		return sizeof(struct emac_ethtool_regs_subhdr) +
-			EMAC_ETHTOOL_REGS_SIZE(dev);
+			sizeof(struct emac_regs);
 }
 
 static int emac_ethtool_get_regs_len(struct net_device *ndev)
@@ -2114,15 +2110,15 @@ static void *emac_dump_regs(struct emac_instance *dev, void *buf)
 	struct emac_ethtool_regs_subhdr *hdr = buf;
 
 	hdr->index = dev->cell_index;
-	if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
+	if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) {
+		hdr->version = EMAC4SYNC_ETHTOOL_REGS_VER;
+	} else if (emac_has_feature(dev, EMAC_FTR_EMAC4)) {
 		hdr->version = EMAC4_ETHTOOL_REGS_VER;
-		memcpy_fromio(hdr + 1, dev->emacp, EMAC4_ETHTOOL_REGS_SIZE(dev));
-		return (void *)(hdr + 1) + EMAC4_ETHTOOL_REGS_SIZE(dev);
 	} else {
 		hdr->version = EMAC_ETHTOOL_REGS_VER;
-		memcpy_fromio(hdr + 1, dev->emacp, EMAC_ETHTOOL_REGS_SIZE(dev));
-		return (void *)(hdr + 1) + EMAC_ETHTOOL_REGS_SIZE(dev);
 	}
+	memcpy_fromio(hdr + 1, dev->emacp, sizeof(struct emac_regs));
+	return (void *)(hdr + 1) + sizeof(struct emac_regs);
 }
 
 static void emac_ethtool_get_regs(struct net_device *ndev,
@@ -3003,7 +2999,7 @@ static struct platform_driver emac_driver = {
 static void __init emac_make_bootlist(void)
 {
 	struct device_node *np = NULL;
-	int j, max, i = 0, k;
+	int j, max, i = 0;
 	int cell_indices[EMAC_BOOT_LIST_SIZE];
 
 	/* Collect EMACs */
@@ -3030,12 +3026,8 @@ static void __init emac_make_bootlist(void)
 	for (i = 0; max > 1 && (i < (max - 1)); i++)
 		for (j = i; j < max; j++) {
 			if (cell_indices[i] > cell_indices[j]) {
-				np = emac_boot_list[i];
-				emac_boot_list[i] = emac_boot_list[j];
-				emac_boot_list[j] = np;
-				k = cell_indices[i];
-				cell_indices[i] = cell_indices[j];
-				cell_indices[j] = k;
+				swap(emac_boot_list[i], emac_boot_list[j]);
+				swap(cell_indices[i], cell_indices[j]);
 			}
 		}
 }
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 67f342a9f65e..28df37420da9 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -461,10 +461,7 @@ struct emac_ethtool_regs_subhdr {
 };
 
 #define EMAC_ETHTOOL_REGS_VER		0
-#define EMAC_ETHTOOL_REGS_SIZE(dev) 	((dev)->rsrc_regs.end - \
-					 (dev)->rsrc_regs.start + 1)
-#define EMAC4_ETHTOOL_REGS_VER      	1
-#define EMAC4_ETHTOOL_REGS_SIZE(dev)	((dev)->rsrc_regs.end -	\
-					 (dev)->rsrc_regs.start + 1)
+#define EMAC4_ETHTOOL_REGS_VER		1
+#define EMAC4SYNC_ETHTOOL_REGS_VER	2
 
 #endif /* __IBM_NEWEMAC_CORE_H */
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 18134766a114..29bbb628d712 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -58,7 +58,7 @@ static struct kobj_type ktype_veth_pool;
 
 static const char ibmveth_driver_name[] = "ibmveth";
 static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver";
-#define ibmveth_driver_version "1.04"
+#define ibmveth_driver_version "1.05"
 
 MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>");
 MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver");
@@ -100,6 +100,8 @@ struct ibmveth_stat ibmveth_stats[] = {
 	{ "tx_send_failed", IBMVETH_STAT_OFF(tx_send_failed) },
 	{ "fw_enabled_ipv4_csum", IBMVETH_STAT_OFF(fw_ipv4_csum_support) },
 	{ "fw_enabled_ipv6_csum", IBMVETH_STAT_OFF(fw_ipv6_csum_support) },
+	{ "tx_large_packets", IBMVETH_STAT_OFF(tx_large_packets) },
+	{ "rx_large_packets", IBMVETH_STAT_OFF(rx_large_packets) }
 };
 
 /* simple methods of getting data from the current rxq entry */
@@ -852,6 +854,10 @@ static int ibmveth_set_features(struct net_device *dev,
 	struct ibmveth_adapter *adapter = netdev_priv(dev);
 	int rx_csum = !!(features & NETIF_F_RXCSUM);
 	int rc;
+	netdev_features_t changed = features ^ dev->features;
+
+	if (features & NETIF_F_TSO & changed)
+		netdev_info(dev, "TSO feature requires all partitions to have updated driver");
 
 	if (rx_csum == adapter->rx_csum)
 		return 0;
@@ -1035,6 +1041,15 @@ retry_bounce:
 		descs[i+1].fields.address = dma_addr;
 	}
 
+	if (skb_is_gso(skb) && !skb_is_gso_v6(skb)) {
+		/* Put -1 in the IP checksum to tell phyp it
+		 *  is a largesend packet and put the mss in the TCP checksum.
+		 */
+		ip_hdr(skb)->check = 0xffff;
+		tcp_hdr(skb)->check = cpu_to_be16(skb_shinfo(skb)->gso_size);
+		adapter->tx_large_packets++;
+	}
+
 	if (ibmveth_send(adapter, descs)) {
 		adapter->tx_send_failed++;
 		netdev->stats.tx_dropped++;
@@ -1080,6 +1095,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	struct net_device *netdev = adapter->netdev;
 	int frames_processed = 0;
 	unsigned long lpar_rc;
+	struct iphdr *iph;
 
 restart_poll:
 	while (frames_processed < budget) {
@@ -1122,10 +1138,23 @@ restart_poll:
 			skb_put(skb, length);
 			skb->protocol = eth_type_trans(skb, netdev);
 
-			if (csum_good)
+			if (csum_good) {
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
+				if (be16_to_cpu(skb->protocol) == ETH_P_IP) {
+					iph = (struct iphdr *)skb->data;
+
+					/* If the IP checksum is not offloaded and if the packet
+					 *  is large send, the checksum must be rebuilt.
+					 */
+					if (iph->check == 0xffff) {
+						iph->check = 0;
+						iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+						adapter->rx_large_packets++;
+					}
+				}
+			}
 
-			netif_receive_skb(skb);	/* send it up */
+			napi_gro_receive(napi, skb);	/* send it up */
 
 			netdev->stats.rx_packets++;
 			netdev->stats.rx_bytes += length;
@@ -1422,8 +1451,14 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	netdev->features |= netdev->hw_features;
 
+	/* TSO is disabled by default */
+	netdev->hw_features |= NETIF_F_TSO;
+
 	memcpy(netdev->dev_addr, mac_addr_p, ETH_ALEN);
 
+	if (firmware_has_feature(FW_FEATURE_CMO))
+		memcpy(pool_count, pool_count_cmo, sizeof(pool_count));
+
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		struct kobject *kobj = &adapter->rx_buff_pool[i].kobj;
 		int error;
diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h
index 1f37499d4398..41dedb1fb2ae 100644
--- a/drivers/net/ethernet/ibm/ibmveth.h
+++ b/drivers/net/ethernet/ibm/ibmveth.h
@@ -104,7 +104,8 @@ static inline long h_illan_attributes(unsigned long unit_address,
 
 static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
 static int pool_count[] = { 256, 512, 256, 256, 256 };
-static int pool_active[] = { 1, 1, 0, 0, 0};
+static int pool_count_cmo[] = { 256, 512, 256, 256, 64 };
+static int pool_active[] = { 1, 1, 0, 0, 1};
 
 #define IBM_VETH_INVALID_MAP ((u16)0xffff)
 
@@ -160,6 +161,8 @@ struct ibmveth_adapter {
     u64 rx_no_buffer;
     u64 tx_map_failed;
     u64 tx_send_failed;
+    u64 tx_large_packets;
+    u64 rx_large_packets;
 };
 
 /*
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index f4ff465584a0..4163b16489b3 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -6,9 +6,7 @@ config NET_VENDOR_INTEL
 	bool "Intel devices"
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 1a450f4b6b12..d2657a412768 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -874,7 +874,7 @@ static int e100_exec_cb(struct nic *nic, struct sk_buff *skb,
 {
 	struct cb *cb;
 	unsigned long flags;
-	int err = 0;
+	int err;
 
 	spin_lock_irqsave(&nic->cb_lock, flags);
 
@@ -2922,9 +2922,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_master(pdev);
 
-	init_timer(&nic->watchdog);
-	nic->watchdog.function = e100_watchdog;
-	nic->watchdog.data = (unsigned long)nic;
+	setup_timer(&nic->watchdog, e100_watchdog, (unsigned long)nic);
 
 	INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task);
 
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 983eb4e6f7aa..74dc15055971 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -2079,11 +2079,6 @@ static void *e1000_alloc_frag(const struct e1000_adapter *a)
 	return data;
 }
 
-static void e1000_free_frag(const void *data)
-{
-	put_page(virt_to_head_page(data));
-}
-
 /**
  * e1000_clean_rx_ring - Free Rx Buffers per Queue
  * @adapter: board private structure
@@ -2107,7 +2102,7 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter,
 						 adapter->rx_buffer_len,
 						 DMA_FROM_DEVICE);
 			if (buffer_info->rxbuf.data) {
-				e1000_free_frag(buffer_info->rxbuf.data);
+				skb_free_frag(buffer_info->rxbuf.data);
 				buffer_info->rxbuf.data = NULL;
 			}
 		} else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq) {
@@ -4594,28 +4589,28 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 			data = e1000_alloc_frag(adapter);
 			/* Failed allocation, critical failure */
 			if (!data) {
-				e1000_free_frag(olddata);
+				skb_free_frag(olddata);
 				adapter->alloc_rx_buff_failed++;
 				break;
 			}
 
 			if (!e1000_check_64k_bound(adapter, data, bufsz)) {
 				/* give up */
-				e1000_free_frag(data);
-				e1000_free_frag(olddata);
+				skb_free_frag(data);
+				skb_free_frag(olddata);
 				adapter->alloc_rx_buff_failed++;
 				break;
 			}
 
 			/* Use new allocation */
-			e1000_free_frag(olddata);
+			skb_free_frag(olddata);
 		}
 		buffer_info->dma = dma_map_single(&pdev->dev,
 						  data,
 						  adapter->rx_buffer_len,
 						  DMA_FROM_DEVICE);
 		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
-			e1000_free_frag(data);
+			skb_free_frag(data);
 			buffer_info->dma = 0;
 			adapter->alloc_rx_buff_failed++;
 			break;
@@ -4637,7 +4632,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 					 adapter->rx_buffer_len,
 					 DMA_FROM_DEVICE);
 
-			e1000_free_frag(data);
+			skb_free_frag(data);
 			buffer_info->rxbuf.data = NULL;
 			buffer_info->dma = 0;
 
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 08f22f348800..2af603f3e418 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.h b/drivers/net/ethernet/intel/e1000e/80003es2lan.h
index 535a9430976d..a2162e11673e 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.h
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index dc79ed85030b..5f7016442ec4 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -2010,7 +2010,7 @@ const struct e1000_info e1000_82573_info = {
 	.flags2			= FLAG2_DISABLE_ASPM_L1
 				  | FLAG2_DISABLE_ASPM_L0S,
 	.pba			= 20,
-	.max_hw_frame_size	= ETH_FRAME_LEN + ETH_FCS_LEN,
+	.max_hw_frame_size	= VLAN_ETH_FRAME_LEN + ETH_FCS_LEN,
 	.get_variants		= e1000_get_variants_82571,
 	.mac_ops		= &e82571_mac_ops,
 	.phy_ops		= &e82_phy_ops_m88,
diff --git a/drivers/net/ethernet/intel/e1000e/82571.h b/drivers/net/ethernet/intel/e1000e/82571.h
index 2e758f796d60..abc6a9abff98 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.h
+++ b/drivers/net/ethernet/intel/e1000e/82571.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h
index 0570c668ec3d..133d4074dbe4 100644
--- a/drivers/net/ethernet/intel/e1000e/defines.h
+++ b/drivers/net/ethernet/intel/e1000e/defines.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 5d9ceb17b4cb..0b748d1959d9 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -40,6 +40,7 @@
 #include <linux/ptp_classify.h>
 #include <linux/mii.h>
 #include <linux/mdio.h>
+#include <linux/pm_qos.h>
 #include "hw.h"
 
 struct e1000_info;
@@ -97,6 +98,8 @@ struct e1000_info;
 #define DEFAULT_RADV			8
 #define BURST_RDTR			0x20
 #define BURST_RADV			0x20
+#define PCICFG_DESC_RING_STATUS		0xe4
+#define FLUSH_DESC_REQUIRED		0x100
 
 /* in the case of WTHRESH, it appears at least the 82571/2 hardware
  * writes back 4 descriptors when WTHRESH=5, and 3 descriptors when
@@ -383,6 +386,10 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
 #define INCVALUE_SHIFT_25MHz	18
 #define INCPERIOD_25MHz		1
 
+#define INCVALUE_24MHz		125
+#define INCVALUE_SHIFT_24MHz	14
+#define INCPERIOD_24MHz		3
+
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with
  * by simply reading the clock before it overflows.
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 11f486e4ff7b..ad6daa656d3e 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -1516,8 +1516,19 @@ static int e1000_set_es2lan_mac_loopback(struct e1000_adapter *adapter)
 static int e1000_setup_loopback_test(struct e1000_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
-	u32 rctl;
-
+	u32 rctl, fext_nvm11, tarc0;
+
+	if (hw->mac.type == e1000_pch_spt) {
+		fext_nvm11 = er32(FEXTNVM11);
+		fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX;
+		ew32(FEXTNVM11, fext_nvm11);
+		tarc0 = er32(TARC(0));
+		/* clear bits 28 & 29 (control of MULR concurrent requests) */
+		tarc0 &= 0xcfffffff;
+		/* set bit 29 (value of MULR requests is now 2) */
+		tarc0 |= 0x20000000;
+		ew32(TARC(0), tarc0);
+	}
 	if (hw->phy.media_type == e1000_media_type_fiber ||
 	    hw->phy.media_type == e1000_media_type_internal_serdes) {
 		switch (hw->mac.type) {
@@ -1542,7 +1553,7 @@ static int e1000_setup_loopback_test(struct e1000_adapter *adapter)
 static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
-	u32 rctl;
+	u32 rctl, fext_nvm11, tarc0;
 	u16 phy_reg;
 
 	rctl = er32(RCTL);
@@ -1550,6 +1561,16 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter)
 	ew32(RCTL, rctl);
 
 	switch (hw->mac.type) {
+	case e1000_pch_spt:
+		fext_nvm11 = er32(FEXTNVM11);
+		fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX;
+		ew32(FEXTNVM11, fext_nvm11);
+		tarc0 = er32(TARC(0));
+		/* clear bits 28 & 29 (control of MULR concurrent requests) */
+		/* set bit 29 (value of MULR requests is now 0) */
+		tarc0 &= 0xcfffffff;
+		ew32(TARC(0), tarc0);
+		/* fall through */
 	case e1000_80003es2lan:
 		if (hw->phy.media_type == e1000_media_type_fiber ||
 		    hw->phy.media_type == e1000_media_type_internal_serdes) {
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 19e8c487db06..c9da4654e9ca 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 9d81c0317433..b074b9a667b3 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -1014,8 +1014,7 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link)
 		u16 speed, duplex, scale = 0;
 		u16 max_snoop, max_nosnoop;
 		u16 max_ltr_enc;	/* max LTR latency encoded */
-		s64 lat_ns;	/* latency (ns) */
-		s64 value;
+		u64 value;
 		u32 rxa;
 
 		if (!hw->adapter->max_frame_size) {
@@ -1040,14 +1039,11 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link)
 		 * 2^25*(2^10-1) ns.  The scale is encoded as 0=2^0ns,
 		 * 1=2^5ns, 2=2^10ns,...5=2^25ns.
 		 */
-		lat_ns = ((s64)rxa * 1024 -
-			  (2 * (s64)hw->adapter->max_frame_size)) * 8 * 1000;
-		if (lat_ns < 0)
-			lat_ns = 0;
-		else
-			do_div(lat_ns, speed);
+		rxa *= 512;
+		value = (rxa > hw->adapter->max_frame_size) ?
+			(rxa - hw->adapter->max_frame_size) * (16000 / speed) :
+			0;
 
-		value = lat_ns;
 		while (value > PCI_LTR_VALUE_MASK) {
 			scale++;
 			value = DIV_ROUND_UP(value, (1 << 5));
@@ -1563,7 +1559,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter)
 	    ((adapter->hw.mac.type >= e1000_pch2lan) &&
 	     (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LSECCK)))) {
 		adapter->flags &= ~FLAG_HAS_JUMBO_FRAMES;
-		adapter->max_hw_frame_size = ETH_FRAME_LEN + ETH_FCS_LEN;
+		adapter->max_hw_frame_size = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
 
 		hw->mac.ops.blink_led = NULL;
 	}
@@ -5681,7 +5677,7 @@ const struct e1000_info e1000_ich8_info = {
 				  | FLAG_HAS_FLASH
 				  | FLAG_APME_IN_WUC,
 	.pba			= 8,
-	.max_hw_frame_size	= ETH_FRAME_LEN + ETH_FCS_LEN,
+	.max_hw_frame_size	= VLAN_ETH_FRAME_LEN + ETH_FCS_LEN,
 	.get_variants		= e1000_get_variants_ich8lan,
 	.mac_ops		= &ich8_mac_ops,
 	.phy_ops		= &ich8_phy_ops,
@@ -5754,7 +5750,7 @@ const struct e1000_info e1000_pch2_info = {
 	.flags2			= FLAG2_HAS_PHY_STATS
 				  | FLAG2_HAS_EEE,
 	.pba			= 26,
-	.max_hw_frame_size	= 9018,
+	.max_hw_frame_size	= 9022,
 	.get_variants		= e1000_get_variants_ich8lan,
 	.mac_ops		= &ich8_mac_ops,
 	.phy_ops		= &ich8_phy_ops,
@@ -5774,7 +5770,7 @@ const struct e1000_info e1000_pch_lpt_info = {
 	.flags2			= FLAG2_HAS_PHY_STATS
 				  | FLAG2_HAS_EEE,
 	.pba			= 26,
-	.max_hw_frame_size	= 9018,
+	.max_hw_frame_size	= 9022,
 	.get_variants		= e1000_get_variants_ich8lan,
 	.mac_ops		= &ich8_mac_ops,
 	.phy_ops		= &ich8_phy_ops,
@@ -5794,7 +5790,7 @@ const struct e1000_info e1000_pch_spt_info = {
 	.flags2			= FLAG2_HAS_PHY_STATS
 				  | FLAG2_HAS_EEE,
 	.pba			= 26,
-	.max_hw_frame_size	= 9018,
+	.max_hw_frame_size	= 9022,
 	.get_variants		= e1000_get_variants_ich8lan,
 	.mac_ops		= &ich8_mac_ops,
 	.phy_ops		= &ich8_phy_ops,
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index 770a573b9eea..26459853c6be 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -98,8 +98,15 @@
 #define E1000_FEXTNVM6_K1_OFF_ENABLE	0x80000000
 /* bit for disabling packet buffer read */
 #define E1000_FEXTNVM7_DISABLE_PB_READ	0x00040000
-
+#define E1000_FEXTNVM7_SIDE_CLK_UNGATE	0x00000004
 #define E1000_FEXTNVM7_DISABLE_SMB_PERST	0x00000020
+#define E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS	0x00000800
+#define E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS	0x00001000
+#define E1000_FEXTNVM11_DISABLE_PB_READ		0x00000200
+#define E1000_FEXTNVM11_DISABLE_MULR_FIX	0x00002000
+
+/* bit24: RXDCTL thresholds granularity: 0 - cache lines, 1 - descriptors */
+#define E1000_RXDCTL_THRESH_UNIT_DESC 0x01000000
 
 #define K1_ENTRY_LATENCY	0
 #define K1_MIN_TIME		1
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index 30b74d590bee..e59d7c283cd4 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h
index 0513d90cdeea..8284618af9ff 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.h
+++ b/drivers/net/ethernet/intel/e1000e/mac.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c
index 06edfca1a35e..cc9b3befc2bc 100644
--- a/drivers/net/ethernet/intel/e1000e/manage.c
+++ b/drivers/net/ethernet/intel/e1000e/manage.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/manage.h b/drivers/net/ethernet/intel/e1000e/manage.h
index a8c27f98f7b0..0b9ea5952b07 100644
--- a/drivers/net/ethernet/intel/e1000e/manage.h
+++ b/drivers/net/ethernet/intel/e1000e/manage.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index c509a5c900f5..e62b9dcb91fe 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -48,7 +48,7 @@
 
 #define DRV_EXTRAVERSION "-k"
 
-#define DRV_VERSION "2.3.2" DRV_EXTRAVERSION
+#define DRV_VERSION "3.2.5" DRV_EXTRAVERSION
 char e1000e_driver_name[] = "e1000e";
 const char e1000e_driver_version[] = DRV_VERSION;
 
@@ -3525,22 +3525,30 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
 	case e1000_pch_lpt:
-	case e1000_pch_spt:
-		/* On I217, I218 and I219, the clock frequency is 25MHz
-		 * or 96MHz as indicated by the System Clock Frequency
-		 * Indication
-		 */
-		if (((hw->mac.type != e1000_pch_lpt) &&
-		     (hw->mac.type != e1000_pch_spt)) ||
-		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 96MHz frequency */
 			incperiod = INCPERIOD_96MHz;
 			incvalue = INCVALUE_96MHz;
 			shift = INCVALUE_SHIFT_96MHz;
 			adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHz;
+		} else {
+			/* Stable 25MHz frequency */
+			incperiod = INCPERIOD_25MHz;
+			incvalue = INCVALUE_25MHz;
+			shift = INCVALUE_SHIFT_25MHz;
+			adapter->cc.shift = shift;
+		}
+		break;
+	case e1000_pch_spt:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
+			/* Stable 24MHz frequency */
+			incperiod = INCPERIOD_24MHz;
+			incvalue = INCVALUE_24MHz;
+			shift = INCVALUE_SHIFT_24MHz;
+			adapter->cc.shift = shift;
 			break;
 		}
-		/* fall-through */
+		return -EINVAL;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
@@ -3788,6 +3796,108 @@ static void e1000_power_down_phy(struct e1000_adapter *adapter)
 }
 
 /**
+ * e1000_flush_tx_ring - remove all descriptors from the tx_ring
+ *
+ * We want to clear all pending descriptors from the TX ring.
+ * zeroing happens when the HW reads the regs. We  assign the ring itself as
+ * the data of the next descriptor. We don't care about the data we are about
+ * to reset the HW.
+ */
+static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	struct e1000_ring *tx_ring = adapter->tx_ring;
+	struct e1000_tx_desc *tx_desc = NULL;
+	u32 tdt, tctl, txd_lower = E1000_TXD_CMD_IFCS;
+	u16 size = 512;
+
+	tctl = er32(TCTL);
+	ew32(TCTL, tctl | E1000_TCTL_EN);
+	tdt = er32(TDT(0));
+	BUG_ON(tdt != tx_ring->next_to_use);
+	tx_desc =  E1000_TX_DESC(*tx_ring, tx_ring->next_to_use);
+	tx_desc->buffer_addr = tx_ring->dma;
+
+	tx_desc->lower.data = cpu_to_le32(txd_lower | size);
+	tx_desc->upper.data = 0;
+	/* flush descriptors to memory before notifying the HW */
+	wmb();
+	tx_ring->next_to_use++;
+	if (tx_ring->next_to_use == tx_ring->count)
+		tx_ring->next_to_use = 0;
+	ew32(TDT(0), tx_ring->next_to_use);
+	mmiowb();
+	usleep_range(200, 250);
+}
+
+/**
+ * e1000_flush_rx_ring - remove all descriptors from the rx_ring
+ *
+ * Mark all descriptors in the RX ring as consumed and disable the rx ring
+ */
+static void e1000_flush_rx_ring(struct e1000_adapter *adapter)
+{
+	u32 rctl, rxdctl;
+	struct e1000_hw *hw = &adapter->hw;
+
+	rctl = er32(RCTL);
+	ew32(RCTL, rctl & ~E1000_RCTL_EN);
+	e1e_flush();
+	usleep_range(100, 150);
+
+	rxdctl = er32(RXDCTL(0));
+	/* zero the lower 14 bits (prefetch and host thresholds) */
+	rxdctl &= 0xffffc000;
+
+	/* update thresholds: prefetch threshold to 31, host threshold to 1
+	 * and make sure the granularity is "descriptors" and not "cache lines"
+	 */
+	rxdctl |= (0x1F | (1 << 8) | E1000_RXDCTL_THRESH_UNIT_DESC);
+
+	ew32(RXDCTL(0), rxdctl);
+	/* momentarily enable the RX ring for the changes to take effect */
+	ew32(RCTL, rctl | E1000_RCTL_EN);
+	e1e_flush();
+	usleep_range(100, 150);
+	ew32(RCTL, rctl & ~E1000_RCTL_EN);
+}
+
+/**
+ * e1000_flush_desc_rings - remove all descriptors from the descriptor rings
+ *
+ * In i219, the descriptor rings must be emptied before resetting the HW
+ * or before changing the device state to D3 during runtime (runtime PM).
+ *
+ * Failure to do this will cause the HW to enter a unit hang state which can
+ * only be released by PCI reset on the device
+ *
+ */
+
+static void e1000_flush_desc_rings(struct e1000_adapter *adapter)
+{
+	u16 hang_state;
+	u32 fext_nvm11, tdlen;
+	struct e1000_hw *hw = &adapter->hw;
+
+	/* First, disable MULR fix in FEXTNVM11 */
+	fext_nvm11 = er32(FEXTNVM11);
+	fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX;
+	ew32(FEXTNVM11, fext_nvm11);
+	/* do nothing if we're not in faulty state, or if the queue is empty */
+	tdlen = er32(TDLEN(0));
+	pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS,
+			     &hang_state);
+	if (!(hang_state & FLUSH_DESC_REQUIRED) || !tdlen)
+		return;
+	e1000_flush_tx_ring(adapter);
+	/* recheck, maybe the fault is caused by the rx ring */
+	pci_read_config_word(adapter->pdev, PCICFG_DESC_RING_STATUS,
+			     &hang_state);
+	if (hang_state & FLUSH_DESC_REQUIRED)
+		e1000_flush_rx_ring(adapter);
+}
+
+/**
  * e1000e_reset - bring the hardware into a known good state
  *
  * This function boots the hardware and enables some settings that
@@ -3807,7 +3917,7 @@ void e1000e_reset(struct e1000_adapter *adapter)
 	/* reset Packet Buffer Allocation to default */
 	ew32(PBA, pba);
 
-	if (adapter->max_frame_size > ETH_FRAME_LEN + ETH_FCS_LEN) {
+	if (adapter->max_frame_size > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) {
 		/* To maintain wire speed transmits, the Tx FIFO should be
 		 * large enough to accommodate two full transmit packets,
 		 * rounded up to the next 1KB and expressed in KB.  Likewise,
@@ -3943,6 +4053,8 @@ void e1000e_reset(struct e1000_adapter *adapter)
 		}
 	}
 
+	if (hw->mac.type == e1000_pch_spt)
+		e1000_flush_desc_rings(adapter);
 	/* Allow time for pending master requests to run */
 	mac->ops.reset_hw(hw);
 
@@ -4016,6 +4128,20 @@ void e1000e_reset(struct e1000_adapter *adapter)
 		phy_data &= ~IGP02E1000_PM_SPD;
 		e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data);
 	}
+	if (hw->mac.type == e1000_pch_spt && adapter->int_mode == 0) {
+		u32 reg;
+
+		/* Fextnvm7 @ 0xe4[2] = 1 */
+		reg = er32(FEXTNVM7);
+		reg |= E1000_FEXTNVM7_SIDE_CLK_UNGATE;
+		ew32(FEXTNVM7, reg);
+		/* Fextnvm9 @ 0x5bb4[13:12] = 11 */
+		reg = er32(FEXTNVM9);
+		reg |= E1000_FEXTNVM9_IOSFSB_CLKGATE_DIS |
+		       E1000_FEXTNVM9_IOSFSB_CLKREQ_DIS;
+		ew32(FEXTNVM9, reg);
+	}
+
 }
 
 int e1000e_up(struct e1000_adapter *adapter)
@@ -4115,8 +4241,6 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 	spin_unlock(&adapter->stats64_lock);
 
 	e1000e_flush_descriptors(adapter);
-	e1000_clean_tx_ring(adapter->tx_ring);
-	e1000_clean_rx_ring(adapter->rx_ring);
 
 	adapter->link_speed = 0;
 	adapter->link_duplex = 0;
@@ -4127,8 +4251,14 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset)
 	    e1000_lv_jumbo_workaround_ich8lan(hw, false))
 		e_dbg("failed to disable jumbo frame workaround mode\n");
 
-	if (reset && !pci_channel_offline(adapter->pdev))
-		e1000e_reset(adapter);
+	if (!pci_channel_offline(adapter->pdev)) {
+		if (reset)
+			e1000e_reset(adapter);
+		else if (hw->mac.type == e1000_pch_spt)
+			e1000_flush_desc_rings(adapter);
+	}
+	e1000_clean_tx_ring(adapter->tx_ring);
+	e1000_clean_rx_ring(adapter->rx_ring);
 }
 
 void e1000e_reinit_locked(struct e1000_adapter *adapter)
@@ -4151,9 +4281,16 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc)
 						     cc);
 	struct e1000_hw *hw = &adapter->hw;
 	cycle_t systim, systim_next;
+	/* SYSTIMH latching upon SYSTIML read does not work well. To fix that
+	 * we don't want to allow overflow of SYSTIML and a change to SYSTIMH
+	 * to occur between reads, so if we read a vale close to overflow, we
+	 * wait for overflow to occur and read both registers when its safe.
+	 */
+	u32 systim_overflow_latch_fix = 0x3FFFFFFF;
 
-	/* latch SYSTIMH on read of SYSTIML */
-	systim = (cycle_t)er32(SYSTIML);
+	do {
+		systim = (cycle_t)er32(SYSTIML);
+	} while (systim > systim_overflow_latch_fix);
 	systim |= (cycle_t)er32(SYSTIMH) << 32;
 
 	if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) {
@@ -4196,9 +4333,9 @@ static int e1000_sw_init(struct e1000_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 
-	adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN;
+	adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
 	adapter->rx_ps_bsize0 = 128;
-	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+	adapter->max_frame_size = netdev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 	adapter->tx_ring_count = E1000_DEFAULT_TXD;
 	adapter->rx_ring_count = E1000_DEFAULT_RXD;
@@ -5781,17 +5918,17 @@ struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev,
 static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	int max_frame = new_mtu + VLAN_HLEN + ETH_HLEN + ETH_FCS_LEN;
+	int max_frame = new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
 
 	/* Jumbo frame support */
-	if ((max_frame > ETH_FRAME_LEN + ETH_FCS_LEN) &&
+	if ((max_frame > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) &&
 	    !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) {
 		e_err("Jumbo Frames not supported.\n");
 		return -EINVAL;
 	}
 
 	/* Supported frame sizes */
-	if ((new_mtu < ETH_ZLEN + ETH_FCS_LEN + VLAN_HLEN) ||
+	if ((new_mtu < (VLAN_ETH_ZLEN + ETH_FCS_LEN)) ||
 	    (max_frame > adapter->max_hw_frame_size)) {
 		e_err("Unsupported MTU setting\n");
 		return -EINVAL;
@@ -5831,10 +5968,8 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 		adapter->rx_buffer_len = 4096;
 
 	/* adjust allocation if LPE protects us, and we aren't using SBP */
-	if ((max_frame == ETH_FRAME_LEN + ETH_FCS_LEN) ||
-	    (max_frame == ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN))
-		adapter->rx_buffer_len = ETH_FRAME_LEN + VLAN_HLEN
-		    + ETH_FCS_LEN;
+	if (max_frame <= (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN))
+		adapter->rx_buffer_len = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN;
 
 	if (netif_running(netdev))
 		e1000e_up(adapter);
@@ -6678,6 +6813,19 @@ static void e1000_eeprom_checks(struct e1000_adapter *adapter)
 	}
 }
 
+static netdev_features_t e1000_fix_features(struct net_device *netdev,
+					    netdev_features_t features)
+{
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+
+	/* Jumbo frame workaround on 82579 and newer requires CRC be stripped */
+	if ((hw->mac.type >= e1000_pch2lan) && (netdev->mtu > ETH_DATA_LEN))
+		features &= ~NETIF_F_RXFCS;
+
+	return features;
+}
+
 static int e1000_set_features(struct net_device *netdev,
 			      netdev_features_t features)
 {
@@ -6734,6 +6882,7 @@ static const struct net_device_ops e1000e_netdev_ops = {
 	.ndo_poll_controller	= e1000_netpoll,
 #endif
 	.ndo_set_features = e1000_set_features,
+	.ndo_fix_features = e1000_fix_features,
 };
 
 /**
@@ -7289,7 +7438,7 @@ static int __init e1000_init_module(void)
 
 	pr_info("Intel(R) PRO/1000 Network Driver - %s\n",
 		e1000e_driver_version);
-	pr_info("Copyright(c) 1999 - 2014 Intel Corporation.\n");
+	pr_info("Copyright(c) 1999 - 2015 Intel Corporation.\n");
 	ret = pci_register_driver(&e1000_driver);
 
 	return ret;
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index fa6b1036a327..49f205c023bf 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.h b/drivers/net/ethernet/intel/e1000e/nvm.h
index 342bf69efab5..5d46967e0d1f 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.h
+++ b/drivers/net/ethernet/intel/e1000e/nvm.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index aa1923f7ebdd..6d8c39abee16 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index b2005e13fb01..de13aeacae97 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h
index 537d2780b408..55bfe473514d 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.h
+++ b/drivers/net/ethernet/intel/e1000e/phy.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 8d7b21dc7e19..25a0ad5102d6 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h
index 85eefc4832ba..b24e5fee17f2 100644
--- a/drivers/net/ethernet/intel/e1000e/regs.h
+++ b/drivers/net/ethernet/intel/e1000e/regs.h
@@ -1,5 +1,5 @@
 /* Intel PRO/1000 Linux driver
- * Copyright(c) 1999 - 2014 Intel Corporation.
+ * Copyright(c) 1999 - 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -38,6 +38,8 @@
 #define E1000_FEXTNVM4	0x00024	/* Future Extended NVM 4 - RW */
 #define E1000_FEXTNVM6	0x00010	/* Future Extended NVM 6 - RW */
 #define E1000_FEXTNVM7	0x000E4	/* Future Extended NVM 7 - RW */
+#define E1000_FEXTNVM9	0x5BB4  /* Future Extended NVM 9 - RW */
+#define E1000_FEXTNVM11	0x5BBC  /* Future Extended NVM 11 - RW */
 #define E1000_PCIEANACFG	0x00F18	/* PCIE Analog Config */
 #define E1000_FCT	0x00030	/* Flow Control Type - RW */
 #define E1000_VET	0x00038	/* VLAN Ether Type - RW */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
index 4b9d9f88af70..c6dc9683429e 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c
@@ -124,7 +124,7 @@ static void fm10k_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 {
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	char *p = (char *)data;
-	int i;
+	unsigned int i;
 
 	switch (stringset) {
 	case ETH_SS_TEST:
@@ -143,12 +143,13 @@ static void fm10k_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 			p += ETH_GSTRING_LEN;
 		}
 
-		if (interface->hw.mac.type != fm10k_mac_vf)
+		if (interface->hw.mac.type != fm10k_mac_vf) {
 			for (i = 0; i < FM10K_PF_STATS_LEN; i++) {
 				memcpy(p, fm10k_gstrings_pf_stats[i].stat_string,
 				       ETH_GSTRING_LEN);
 				p += ETH_GSTRING_LEN;
 			}
+		}
 
 		for (i = 0; i < interface->hw.mac.max_queues; i++) {
 			sprintf(p, "tx_queue_%u_packets", i);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5b08e6284a3c..94571e6e790c 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -400,11 +400,31 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs)
 	return num_vfs;
 }
 
+static inline void fm10k_reset_vf_info(struct fm10k_intfc *interface,
+				       struct fm10k_vf_info *vf_info)
+{
+	struct fm10k_hw *hw = &interface->hw;
+
+	/* assigning the MAC address will send a mailbox message */
+	fm10k_mbx_lock(interface);
+
+	/* disable LPORT for this VF which clears switch rules */
+	hw->iov.ops.reset_lport(hw, vf_info);
+
+	/* assign new MAC+VLAN for this VF */
+	hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
+
+	/* re-enable the LPORT for this VF */
+	hw->iov.ops.set_lport(hw, vf_info, vf_info->vf_idx,
+			      FM10K_VF_FLAG_MULTI_CAPABLE);
+
+	fm10k_mbx_unlock(interface);
+}
+
 int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac)
 {
 	struct fm10k_intfc *interface = netdev_priv(netdev);
 	struct fm10k_iov_data *iov_data = interface->iov_data;
-	struct fm10k_hw *hw = &interface->hw;
 	struct fm10k_vf_info *vf_info;
 
 	/* verify SR-IOV is active and that vf idx is valid */
@@ -419,13 +439,7 @@ int fm10k_ndo_set_vf_mac(struct net_device *netdev, int vf_idx, u8 *mac)
 	vf_info = &iov_data->vf_info[vf_idx];
 	ether_addr_copy(vf_info->mac, mac);
 
-	/* assigning the MAC will send a mailbox message so lock is needed */
-	fm10k_mbx_lock(interface);
-
-	/* assign MAC address to VF */
-	hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
-
-	fm10k_mbx_unlock(interface);
+	fm10k_reset_vf_info(interface, vf_info);
 
 	return 0;
 }
@@ -455,16 +469,10 @@ int fm10k_ndo_set_vf_vlan(struct net_device *netdev, int vf_idx, u16 vid,
 	/* record default VLAN ID for VF */
 	vf_info->pf_vid = vid;
 
-	/* assigning the VLAN will send a mailbox message so lock is needed */
-	fm10k_mbx_lock(interface);
-
 	/* Clear the VLAN table for the VF */
 	hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, vf_info->vsi, false);
 
-	/* Update VF assignment and trigger reset */
-	hw->iov.ops.assign_default_mac_vlan(hw, vf_info);
-
-	fm10k_mbx_unlock(interface);
+	fm10k_reset_vf_info(interface, vf_info);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 1b0661e3573b..982fdcdc795b 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -269,16 +269,19 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 			      struct sk_buff *skb)
 {
 	struct page *page = rx_buffer->page;
+	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 	unsigned int size = le16_to_cpu(rx_desc->w.length);
 #if (PAGE_SIZE < 8192)
 	unsigned int truesize = FM10K_RX_BUFSZ;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size);
 #endif
+	unsigned int pull_len;
 
-	if ((size <= FM10K_RX_HDR_LEN) && !skb_is_nonlinear(skb)) {
-		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+	if (unlikely(skb_is_nonlinear(skb)))
+		goto add_tail_frag;
 
+	if (likely(size <= FM10K_RX_HDR_LEN)) {
 		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
 
 		/* page is not reserved, we can reuse buffer as-is */
@@ -290,8 +293,21 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 		return false;
 	}
 
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	va += pull_len;
+	size -= pull_len;
+
+add_tail_frag:
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			rx_buffer->page_offset, size, truesize);
+			(unsigned long)va & ~PAGE_MASK, size, truesize);
 
 	return fm10k_can_reuse_rx_page(rx_buffer, page, truesize);
 }
@@ -518,44 +534,6 @@ static bool fm10k_is_non_eop(struct fm10k_ring *rx_ring,
 }
 
 /**
- * fm10k_pull_tail - fm10k specific version of skb_pull_tail
- * @skb: pointer to current skb being adjusted
- *
- * This function is an fm10k specific version of __pskb_pull_tail.  The
- * main difference between this version and the original function is that
- * this function can make several assumptions about the state of things
- * that allow for significant optimizations versus the standard function.
- * As a result we can do things like drop a frag and maintain an accurate
- * truesize for the skb.
- */
-static void fm10k_pull_tail(struct sk_buff *skb)
-{
-	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
-	unsigned char *va;
-	unsigned int pull_len;
-
-	/* it is valid to use page_address instead of kmap since we are
-	 * working with pages allocated out of the lomem pool per
-	 * alloc_page(GFP_ATOMIC)
-	 */
-	va = skb_frag_address(frag);
-
-	/* we need the header to contain the greater of either ETH_HLEN or
-	 * 60 bytes if the skb->len is less than 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
-
-	/* align pull length to size of long to optimize memcpy performance */
-	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
-
-	/* update all of the pointers */
-	skb_frag_size_sub(frag, pull_len);
-	frag->page_offset += pull_len;
-	skb->data_len -= pull_len;
-	skb->tail += pull_len;
-}
-
-/**
  * fm10k_cleanup_headers - Correct corrupted or empty headers
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
@@ -580,10 +558,6 @@ static bool fm10k_cleanup_headers(struct fm10k_ring *rx_ring,
 		return true;
 	}
 
-	/* place header in linear portion of buffer */
-	if (skb_is_nonlinear(skb))
-		fm10k_pull_tail(skb);
-
 	/* if eth_skb_pad returns an error the skb was freed */
 	if (eth_skb_pad(skb))
 		return true;
@@ -610,7 +584,7 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
 	unsigned int total_bytes = 0, total_packets = 0;
 	u16 cleaned_count = fm10k_desc_unused(rx_ring);
 
-	do {
+	while (likely(total_packets < budget)) {
 		union fm10k_rx_desc *rx_desc;
 
 		/* return some buffers to hardware, one at a time is too slow */
@@ -659,7 +633,7 @@ static bool fm10k_clean_rx_irq(struct fm10k_q_vector *q_vector,
 
 		/* update budget accounting */
 		total_packets++;
-	} while (likely(total_packets < budget));
+	}
 
 	/* place incomplete frames back on ring for completion */
 	rx_ring->skb = skb;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
index 1b2738380518..1a4b52637de9 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c
@@ -1259,16 +1259,11 @@ static s32 fm10k_mbx_process_error(struct fm10k_hw *hw,
 				   struct fm10k_mbx_info *mbx)
 {
 	const u32 *hdr = &mbx->mbx_hdr;
-	s32 err_no;
 	u16 head;
 
 	/* we will need to pull all of the fields for verification */
 	head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD);
 
-	/* we only have lower 10 bits of error number so add upper bits */
-	err_no = FM10K_MSG_HDR_FIELD_GET(*hdr, ERR_NO);
-	err_no |= ~FM10K_MSG_HDR_MASK(ERR_NO);
-
 	switch (mbx->state) {
 	case FM10K_STATE_OPEN:
 	case FM10K_STATE_DISCONNECT:
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 2f4f41b7eae7..99228bf46c12 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -923,18 +923,12 @@ static int __fm10k_mc_sync(struct net_device *dev,
 	struct fm10k_intfc *interface = netdev_priv(dev);
 	struct fm10k_hw *hw = &interface->hw;
 	u16 vid, glort = interface->glort;
-	s32 err;
-
-	if (!is_multicast_ether_addr(addr))
-		return -EADDRNOTAVAIL;
 
 	/* update table with current entries */
 	for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 0;
 	     vid < VLAN_N_VID;
 	     vid = fm10k_find_next_vlan(interface, vid)) {
-		err = hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync);
-		if (err)
-			return err;
+		hw->mac.ops.update_mc_addr(hw, glort, addr, vid, sync);
 	}
 
 	return 0;
@@ -1339,8 +1333,7 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv)
 	dglort.rss_l = fls(interface->ring_feature[RING_F_RSS].mask);
 	dglort.pc_l = fls(interface->ring_feature[RING_F_QOS].mask);
 	dglort.glort = interface->glort;
-	if (l2_accel)
-		dglort.shared_l = fls(l2_accel->size);
+	dglort.shared_l = fls(l2_accel->size);
 	hw->mac.ops.configure_dglort_map(hw, &dglort);
 
 	/* If table is empty remove it */
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
index df9fda38bdd1..ce53ff25f88d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c
@@ -1559,6 +1559,7 @@ void fm10k_down(struct fm10k_intfc *interface)
 
 	/* free any buffers still on the rings */
 	fm10k_clean_all_tx_rings(interface);
+	fm10k_clean_all_rx_rings(interface);
 }
 
 /**
@@ -1740,30 +1741,18 @@ static int fm10k_probe(struct pci_dev *pdev,
 	struct fm10k_intfc *interface;
 	struct fm10k_hw *hw;
 	int err;
-	u64 dma_mask;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
 		return err;
 
-	/* By default fm10k only supports a 48 bit DMA mask */
-	dma_mask = DMA_BIT_MASK(48) | dma_get_required_mask(&pdev->dev);
-
-	if ((dma_mask <= DMA_BIT_MASK(32)) ||
-	    dma_set_mask_and_coherent(&pdev->dev, dma_mask)) {
-		dma_mask &= DMA_BIT_MASK(32);
-
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
+	if (err)
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
-		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
-		if (err) {
-			err = dma_set_coherent_mask(&pdev->dev,
-						    DMA_BIT_MASK(32));
-			if (err) {
-				dev_err(&pdev->dev,
-					"No usable DMA configuration, aborting\n");
-				goto err_dma;
-			}
-		}
+	if (err) {
+		dev_err(&pdev->dev,
+			"DMA configuration failed: %d\n", err);
+		goto err_dma;
 	}
 
 	err = pci_request_selected_regions(pdev,
@@ -1772,7 +1761,7 @@ static int fm10k_probe(struct pci_dev *pdev,
 					   fm10k_driver_name);
 	if (err) {
 		dev_err(&pdev->dev,
-			"pci_request_selected_regions failed 0x%x\n", err);
+			"pci_request_selected_regions failed: %d\n", err);
 		goto err_pci_reg;
 	}
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 891e21874b2a..3ca0233b3ea2 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1046,6 +1046,12 @@ static s32 fm10k_iov_reset_resources_pf(struct fm10k_hw *hw,
 		fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx + i), vf_q_idx + i);
 	}
 
+	/* repeat the first ring for all the remaining VF rings */
+	for (i = queues_per_pool; i < qmap_stride; i++) {
+		fm10k_write_reg(hw, FM10K_TQMAP(qmap_idx + i), vf_q_idx);
+		fm10k_write_reg(hw, FM10K_RQMAP(qmap_idx + i), vf_q_idx);
+	}
+
 	return 0;
 }
 
@@ -1345,6 +1351,14 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results,
 			err = fm10k_update_lport_state_pf(hw, vf_info->glort,
 							  1, false);
 
+		/* we need to clear VF_FLAG_ENABLED flags in order to ensure
+		 * that we actually re-enable the LPORT state below. Note that
+		 * this has no impact if the VF is already disabled, as the
+		 * flags are already cleared.
+		 */
+		if (!err)
+			vf_info->vf_flags = FM10K_VF_FLAG_CAPABLE(vf_info);
+
 		/* when enabling the port we should reset the rate limiters */
 		hw->iov.ops.configure_tc(hw, vf_info->vf_idx, vf_info->rate);
 
@@ -1786,8 +1800,8 @@ static s32 fm10k_adjust_systime_pf(struct fm10k_hw *hw, s32 ppb)
 	if (systime_adjust > FM10K_SW_SYSTIME_ADJUST_MASK)
 		return FM10K_ERR_PARAM;
 
-	if (ppb < 0)
-		systime_adjust |= FM10K_SW_SYSTIME_ADJUST_DIR_NEGATIVE;
+	if (ppb > 0)
+		systime_adjust |= FM10K_SW_SYSTIME_ADJUST_DIR_POSITIVE;
 
 	fm10k_write_sw_reg(hw, FM10K_SW_SYSTIME_ADJUST, (u32)systime_adjust);
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
index 7ab1db4fff32..40a0dbc62a04 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h
@@ -81,26 +81,26 @@ struct fm10k_mac_update {
 	__le16	glort;
 	u8	flags;
 	u8	action;
-};
+} __packed;
 
 struct fm10k_global_table_data {
 	__le32	used;
 	__le32	avail;
-};
+} __packed;
 
 struct fm10k_swapi_error {
 	__le32				status;
 	struct fm10k_global_table_data	mac;
 	struct fm10k_global_table_data	nexthop;
 	struct fm10k_global_table_data	ffu;
-};
+} __packed;
 
 struct fm10k_swapi_1588_timestamp {
 	__le64 egress;
 	__le64 ingress;
 	__le16 dglort;
 	__le16 sglort;
-};
+} __packed;
 
 s32 fm10k_msg_lport_map_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
 extern const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[];
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c
index 9043633c3e50..b4945e8abe03 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c
@@ -70,16 +70,16 @@ void fm10k_ts_tx_enqueue(struct fm10k_intfc *interface, struct sk_buff *skb)
 	 * if none are present then insert skb in tail of list
 	 */
 	skb = fm10k_ts_tx_skb(interface, FM10K_CB(clone)->fi.w.dglort);
-	if (!skb)
+	if (!skb) {
+		skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
 		__skb_queue_tail(list, clone);
+	}
 
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	/* if list is already has one then we just free the clone */
 	if (skb)
-		kfree_skb(skb);
-	else
-		skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS;
+		dev_kfree_skb(clone);
 }
 
 void fm10k_ts_tx_hwtstamp(struct fm10k_intfc *interface, __le16 dglort,
@@ -103,9 +103,10 @@ void fm10k_ts_tx_hwtstamp(struct fm10k_intfc *interface, __le16 dglort,
 	if (!skb)
 		return;
 
-	/* timestamp the sk_buff and return it to the socket */
+	/* timestamp the sk_buff and free out copy */
 	fm10k_systime_to_hwtstamp(interface, &shhwtstamps, systime);
-	skb_complete_tx_timestamp(skb, &shhwtstamps);
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
 }
 
 void fm10k_ts_tx_subtask(struct fm10k_intfc *interface)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
index 4af96686c584..2a17d82fa37d 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h
@@ -369,7 +369,7 @@ struct fm10k_hw;
 /* Registers contained in BAR 4 for Switch management */
 #define FM10K_SW_SYSTIME_ADJUST	0x0224D
 #define FM10K_SW_SYSTIME_ADJUST_MASK		0x3FFFFFFF
-#define FM10K_SW_SYSTIME_ADJUST_DIR_NEGATIVE	0x80000000
+#define FM10K_SW_SYSTIME_ADJUST_DIR_POSITIVE	0x80000000
 #define FM10K_SW_SYSTIME_PULSE(_n)	((_n) + 0x02252)
 
 enum fm10k_int_source {
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 33c35d3b7420..ec76c3fa3a04 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -182,6 +182,7 @@ struct i40e_lump_tracking {
 enum i40e_fd_stat_idx {
 	I40E_FD_STAT_ATR,
 	I40E_FD_STAT_SB,
+	I40E_FD_STAT_ATR_TUNNEL,
 	I40E_FD_STAT_PF_COUNT
 };
 #define I40E_FD_STAT_PF_IDX(pf_id) ((pf_id) * I40E_FD_STAT_PF_COUNT)
@@ -189,6 +190,8 @@ enum i40e_fd_stat_idx {
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR)
 #define I40E_FD_SB_STAT_IDX(pf_id)  \
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_SB)
+#define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
+			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
 
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
@@ -263,8 +266,6 @@ struct i40e_pf {
 
 	struct hlist_head fdir_filter_list;
 	u16 fdir_pf_active_filters;
-	u16 fd_sb_cnt_idx;
-	u16 fd_atr_cnt_idx;
 	unsigned long fd_flush_timestamp;
 	u32 fd_flush_cnt;
 	u32 fd_add_err;
@@ -317,6 +318,7 @@ struct i40e_pf {
 #endif
 #define I40E_FLAG_PORT_ID_VALID                (u64)(1 << 28)
 #define I40E_FLAG_DCB_CAPABLE                  (u64)(1 << 29)
+#define I40E_FLAG_VEB_MODE_ENABLED		BIT_ULL(40)
 
 	/* tracks features that get auto disabled by errors */
 	u64 auto_disable_flags;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 34170eabca7d..da0faf478af0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1021,6 +1021,15 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			goto command_write_done;
 		}
 
+		/* By default we are in VEPA mode, if this is the first VF/VMDq
+		 * VSI to be added switch to VEB mode.
+		 */
+		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+			i40e_do_reset_safe(pf,
+					   BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		}
+
 		vsi = i40e_vsi_setup(pf, I40E_VSI_VMDQ2, vsi_seid, 0);
 		if (vsi)
 			dev_info(&pf->pdev->dev, "added VSI %d to relay %d\n",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 4cbaaeb902c4..9a68c65b17ea 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -147,6 +147,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 	I40E_PF_STAT("fdir_flush_cnt", fd_flush_cnt),
 	I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match),
+	I40E_PF_STAT("fdir_atr_tunnel_match", stats.fd_atr_tunnel_match),
 	I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match),
 
 	/* LPI stats */
@@ -1548,6 +1549,17 @@ static int i40e_loopback_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
+static inline bool i40e_active_vfs(struct i40e_pf *pf)
+{
+	struct i40e_vf *vfs = pf->vf;
+	int i;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++)
+		if (vfs[i].vf_states & I40E_VF_STAT_ACTIVE)
+			return true;
+	return false;
+}
+
 static void i40e_diag_test(struct net_device *netdev,
 			   struct ethtool_test *eth_test, u64 *data)
 {
@@ -1560,6 +1572,20 @@ static void i40e_diag_test(struct net_device *netdev,
 		netif_info(pf, drv, netdev, "offline testing starting\n");
 
 		set_bit(__I40E_TESTING, &pf->state);
+
+		if (i40e_active_vfs(pf)) {
+			dev_warn(&pf->pdev->dev,
+				 "Please take active VFS offline and restart the adapter before running NIC diagnostics\n");
+			data[I40E_ETH_TEST_REG]		= 1;
+			data[I40E_ETH_TEST_EEPROM]	= 1;
+			data[I40E_ETH_TEST_INTR]	= 1;
+			data[I40E_ETH_TEST_LOOPBACK]	= 1;
+			data[I40E_ETH_TEST_LINK]	= 1;
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+			clear_bit(__I40E_TESTING, &pf->state);
+			goto skip_ol_tests;
+		}
+
 		/* If the device is online then take it offline */
 		if (if_running)
 			/* indicate we're in test mode */
@@ -1605,6 +1631,8 @@ static void i40e_diag_test(struct net_device *netdev,
 		data[I40E_ETH_TEST_LOOPBACK] = 0;
 	}
 
+skip_ol_tests:
+
 	netif_info(pf, drv, netdev, "testing finished\n");
 }
 
@@ -2265,7 +2293,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	input->pctype = 0;
 	input->dest_vsi = vsi->id;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
-	input->cnt_index  = pf->fd_sb_cnt_idx;
+	input->cnt_index  = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 	input->flow_type = fsp->flow_type;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
index 1803afeef23e..c8b621e0e7cd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c
@@ -118,7 +118,7 @@ static inline int i40e_fcoe_fc_eof(struct sk_buff *skb, u8 *eof)
  *
  * The FC EOF is converted to the value understood by HW for descriptor
  * programming. Never call this w/o calling i40e_fcoe_eof_is_supported()
- * first.
+ * first and that already checks for all supported valid eof values.
  **/
 static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 {
@@ -132,9 +132,12 @@ static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 	case FC_EOF_A:
 		return I40E_TX_DESC_CMD_L4T_EOFT_EOF_A;
 	default:
-		/* FIXME: still returns 0 */
-		pr_err("Unrecognized EOF %x\n", eof);
-		return 0;
+		/* Supported valid eof shall be already checked by
+		 * calling i40e_fcoe_eof_is_supported() first,
+		 * therefore this default case shall never hit.
+		 */
+		WARN_ON(1);
+		return -EINVAL;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a54c14491e3b..48a52b35b614 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_BUILD 4
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -772,9 +772,8 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
 
 	dcb_cfg = &hw->local_dcbx_config;
 
-	/* See if DCB enabled with PFC TC */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED) ||
-	    !(dcb_cfg->pfc.pfcenable)) {
+	/* Collect Link XOFF stats when PFC is disabled */
+	if (!dcb_cfg->pfc.pfcenable) {
 		i40e_update_link_xoff_rx(pf);
 		return;
 	}
@@ -1097,12 +1096,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_jabber, &nsd->rx_jabber);
 
 	/* FDIR stats */
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_atr_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_atr_match, &nsd->fd_atr_match);
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_sb_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_sb_match, &nsd->fd_sb_match);
+	i40e_stat_update32(hw,
+		      I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)),
+		      pf->stat_offsets_loaded,
+		      &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match);
 
 	val = rd32(hw, I40E_PRTPM_EEE_STAT);
 	nsd->tx_lpi_status =
@@ -4739,7 +4744,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 		pf->fd_add_err = pf->fd_atr_cnt = 0;
 		if (pf->fd_tcp_rule > 0) {
 			pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
 			pf->fd_tcp_rule = 0;
 		}
 		i40e_fdir_filter_restore(vsi);
@@ -5428,7 +5434,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
-			dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 		}
 	}
 	/* Wait for some more space to be available to turn on ATR */
@@ -5436,7 +5443,8 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
 		}
 	}
 }
@@ -5469,7 +5477,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 
 		if (!(time_after(jiffies, min_flush_time)) &&
 		    (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) {
-			dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
 			disable_atr = true;
 		}
 
@@ -5496,7 +5505,8 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 			if (!disable_atr)
 				pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 			clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
-			dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 		}
 	}
 }
@@ -6097,6 +6107,10 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 	if (ret)
 		goto end_reconstitute;
 
+	if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+		veb->bridge_mode = BRIDGE_MODE_VEB;
+	else
+		veb->bridge_mode = BRIDGE_MODE_VEPA;
 	i40e_config_bridge_mode(veb);
 
 	/* create the remaining VSIs attached to this VEB */
@@ -7676,12 +7690,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 		pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
-		/* Setup a counter for fd_atr per PF */
-		pf->fd_atr_cnt_idx = I40E_FD_ATR_STAT_IDX(pf->hw.pf_id);
 		if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
 			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-			/* Setup a counter for fd_sb per PF */
-			pf->fd_sb_cnt_idx = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 		} else {
 			dev_info(&pf->pdev->dev,
 				 "Flow Director Sideband mode Disabled in MFP mode\n");
@@ -7771,7 +7781,8 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
 		pf->fdir_pf_active_filters = 0;
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-		dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
+		if (I40E_DEBUG_FD & pf->hw.debug_mask)
+			dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		/* if ATR was auto disabled it can be re-enabled. */
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
@@ -8031,7 +8042,12 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 		} else if (mode != veb->bridge_mode) {
 			/* Existing HW bridge but different mode needs reset */
 			veb->bridge_mode = mode;
-			i40e_do_reset(pf, (1 << __I40E_PF_RESET_REQUESTED));
+			/* TODO: If no VFs or VMDq VSIs, disallow VEB mode */
+			if (mode == BRIDGE_MODE_VEB)
+				pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+			else
+				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+			i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
 			break;
 		}
 	}
@@ -8053,7 +8069,7 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 #ifdef HAVE_BRIDGE_FILTER
 static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				   struct net_device *dev,
-				   u32 __always_unused filter_mask, int nlflags)
+				   u32 filter_mask, int nlflags)
 #else
 static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 				   struct net_device *dev, int nlflags)
@@ -8079,7 +8095,7 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		return 0;
 
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode,
-				       nlflags);
+				       nlflags, 0, 0, filter_mask, NULL);
 }
 #endif /* HAVE_BRIDGE_ATTRIBS */
 
@@ -8343,11 +8359,12 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 		ctxt.uplink_seid = vsi->uplink_seid;
 		ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
 		ctxt.flags = I40E_AQ_VSI_TYPE_PF;
-		if (i40e_is_vsi_uplink_mode_veb(vsi)) {
+		if ((pf->flags & I40E_FLAG_VEB_MODE_ENABLED) &&
+		    (i40e_is_vsi_uplink_mode_veb(vsi))) {
 			ctxt.info.valid_sections |=
-				cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
+			     cpu_to_le16(I40E_AQ_VSI_PROP_SWITCH_VALID);
 			ctxt.info.switch_id =
-				cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
+			   cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB);
 		}
 		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
 		break;
@@ -8746,6 +8763,14 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 					 __func__);
 				return NULL;
 			}
+			/* We come up by default in VEPA mode if SRIOV is not
+			 * already enabled, in which case we can't force VEPA
+			 * mode.
+			 */
+			if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+				veb->bridge_mode = BRIDGE_MODE_VEPA;
+				pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+			}
 			i40e_config_bridge_mode(veb);
 		}
 		for (i = 0; i < I40E_MAX_VEB && !veb; i++) {
@@ -9856,6 +9881,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_switch_setup;
 	}
 
+#ifdef CONFIG_PCI_IOV
+	/* prep for VF support */
+	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
+	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
+	    !test_bit(__I40E_BAD_EEPROM, &pf->state)) {
+		if (pci_num_vf(pdev))
+			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+	}
+#endif
 	err = i40e_setup_pf_switch(pf, false);
 	if (err) {
 		dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 4bd3a80aba82..9a4f2bc70cd2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -165,9 +165,6 @@ int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
 	tx_desc->cmd_type_offset_bsz =
 		build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_SIZE, 0);
 
-	/* set the timestamp */
-	tx_buf->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.
 	 */
@@ -283,7 +280,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 	if (add) {
 		pf->fd_tcp_rule++;
 		if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) {
-			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
 			pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 		}
 	} else {
@@ -291,7 +289,8 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 				  (pf->fd_tcp_rule - 1) : 0;
 		if (pf->fd_tcp_rule == 0) {
 			pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
-			dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
+				dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
 		}
 	}
 
@@ -501,7 +500,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 			    !(pf->auto_disable_flags &
 				     I40E_FLAG_FD_SB_ENABLED)) {
-				dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
+				if (I40E_DEBUG_FD & pf->hw.debug_mask)
+					dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
 				pf->auto_disable_flags |=
 							I40E_FLAG_FD_SB_ENABLED;
 			}
@@ -807,10 +807,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 			 tx_ring->vsi->seid,
 			 tx_ring->queue_index,
 			 tx_ring->next_to_use, i);
-		dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n"
-			 "  time_stamp           <%lx>\n"
-			 "  jiffies              <%lx>\n",
-			 tx_ring->tx_bi[i].time_stamp, jiffies);
 
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
@@ -1653,9 +1649,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
-			/* TODO: shouldn't we increment a counter indicating the
-			 * drop?
-			 */
 			continue;
 		}
 
@@ -1688,7 +1681,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		skb_mark_napi_id(skb, &rx_ring->q_vector->napi);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 
-		rx_ring->netdev->last_rx = jiffies;
 		rx_desc->wb.qword1.status_error_len = 0;
 
 	} while (likely(total_rx_packets < budget));
@@ -1821,7 +1813,6 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 #endif
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 
-		rx_ring->netdev->last_rx = jiffies;
 		rx_desc->wb.qword1.status_error_len = 0;
 	} while (likely(total_rx_packets < budget));
 
@@ -1925,11 +1916,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
  * i40e_atr - Add a Flow Director ATR filter
  * @tx_ring:  ring to add programming descriptor to
  * @skb:      send buffer
- * @flags:    send flags
+ * @tx_flags: send tx flags
  * @protocol: wire protocol
  **/
 static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		     u32 flags, __be16 protocol)
+		     u32 tx_flags, __be16 protocol)
 {
 	struct i40e_filter_program_desc *fdir_desc;
 	struct i40e_pf *pf = tx_ring->vsi->back;
@@ -1954,25 +1945,38 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!tx_ring->atr_sample_rate)
 		return;
 
-	/* snag network header to get L4 type and address */
-	hdr.network = skb_network_header(skb);
+	if (!(tx_flags & (I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6)))
+		return;
 
-	/* Currently only IPv4/IPv6 with TCP is supported */
-	if (protocol == htons(ETH_P_IP)) {
-		if (hdr.ipv4->protocol != IPPROTO_TCP)
-			return;
+	if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL)) {
+		/* snag network header to get L4 type and address */
+		hdr.network = skb_network_header(skb);
 
-		/* access ihl as a u8 to avoid unaligned access on ia64 */
-		hlen = (hdr.network[0] & 0x0F) << 2;
-	} else if (protocol == htons(ETH_P_IPV6)) {
-		if (hdr.ipv6->nexthdr != IPPROTO_TCP)
+		/* Currently only IPv4/IPv6 with TCP is supported
+		 * access ihl as u8 to avoid unaligned access on ia64
+		 */
+		if (tx_flags & I40E_TX_FLAGS_IPV4)
+			hlen = (hdr.network[0] & 0x0F) << 2;
+		else if (protocol == htons(ETH_P_IPV6))
+			hlen = sizeof(struct ipv6hdr);
+		else
 			return;
-
-		hlen = sizeof(struct ipv6hdr);
 	} else {
-		return;
+		hdr.network = skb_inner_network_header(skb);
+		hlen = skb_inner_network_header_len(skb);
 	}
 
+	/* Currently only IPv4/IPv6 with TCP is supported
+	 * Note: tx_flags gets modified to reflect inner protocols in
+	 * tx_enable_csum function if encap is enabled.
+	 */
+	if ((tx_flags & I40E_TX_FLAGS_IPV4) &&
+	    (hdr.ipv4->protocol != IPPROTO_TCP))
+		return;
+	else if ((tx_flags & I40E_TX_FLAGS_IPV6) &&
+		 (hdr.ipv6->nexthdr != IPPROTO_TCP))
+		return;
+
 	th = (struct tcphdr *)(hdr.network + hlen);
 
 	/* Due to lack of space, no more new filters can be programmed */
@@ -2022,9 +2026,16 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 		     I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT;
 
 	dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
-	dtype_cmd |=
-		((u32)pf->fd_atr_cnt_idx << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
-		I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+	if (!(tx_flags & I40E_TX_FLAGS_VXLAN_TUNNEL))
+		dtype_cmd |=
+			((u32)I40E_FD_ATR_STAT_IDX(pf->hw.pf_id) <<
+			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
+			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+	else
+		dtype_cmd |=
+			((u32)I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id) <<
+			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
+			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
 	fdir_desc->rsvd = cpu_to_le32(0);
@@ -2045,13 +2056,13 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
 #ifdef I40E_FCOE
-int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring,
-			       u32 *flags)
-#else
-static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
+inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring,
 				      u32 *flags)
+#else
+static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
+					     struct i40e_ring *tx_ring,
+					     u32 *flags)
 #endif
 {
 	__be16 protocol = skb->protocol;
@@ -2119,16 +2130,14 @@ out:
  * i40e_tso - set up the tso context descriptor
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
- * @tx_flags: the collected send information
- * @protocol: the send protocol
  * @hdr_len:  ptr to the size of the packet header
  * @cd_tunneling: ptr to context descriptor bits
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
  **/
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		    u32 tx_flags, __be16 protocol, u8 *hdr_len,
-		    u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling)
+		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss,
+		    u32 *cd_tunneling)
 {
 	u32 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
@@ -2220,12 +2229,12 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
 /**
  * i40e_tx_enable_csum - Enable Tx checksum offloads
  * @skb: send buffer
- * @tx_flags: Tx flags currently set
+ * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
+static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				u32 *td_cmd, u32 *td_offset,
 				struct i40e_ring *tx_ring,
 				u32 *cd_tunneling)
@@ -2241,6 +2250,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
 			return;
@@ -2250,18 +2260,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		this_ipv6_hdr = inner_ipv6_hdr(skb);
 		this_tcp_hdrlen = inner_tcp_hdrlen(skb);
 
-		if (tx_flags & I40E_TX_FLAGS_IPV4) {
-
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
+		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+			if (*tx_flags & I40E_TX_FLAGS_TSO) {
 				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
 				ip_hdr(skb)->check = 0;
 			} else {
 				*cd_tunneling |=
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
-		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (tx_flags & I40E_TX_FLAGS_TSO)
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
 		}
 
@@ -2273,8 +2282,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 		if (this_ip_hdr->version == 6) {
-			tx_flags &= ~I40E_TX_FLAGS_IPV4;
-			tx_flags |= I40E_TX_FLAGS_IPV6;
+			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
 	} else {
 		network_hdr_len = skb_network_header_len(skb);
@@ -2284,12 +2293,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 	}
 
 	/* Enable IP checksum offloads */
-	if (tx_flags & I40E_TX_FLAGS_IPV4) {
+	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 		l4_hdr = this_ip_hdr->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
-		if (tx_flags & I40E_TX_FLAGS_TSO) {
+		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
 			this_ip_hdr->check = 0;
 		} else {
@@ -2298,7 +2307,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		/* Now set the td_offset for IP header length */
 		*td_offset = (network_hdr_len >> 2) <<
 			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 		l4_hdr = this_ipv6_hdr->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
 		/* Now set the td_offset for IP header length */
@@ -2396,9 +2405,9 @@ static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
  * Returns 0 if stop is not needed
  **/
 #ifdef I40E_FCOE
-int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 #else
-static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 #endif
 {
 	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
@@ -2410,14 +2419,12 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
  * i40e_chk_linearize - Check if there are more than 8 fragments per packet
  * @skb:      send buffer
  * @tx_flags: collected send information
- * @hdr_len:  size of the packet header
  *
  * Note: Our HW can't scatter-gather more than 8 fragments to build
  * a packet on the wire and so we need to figure out the cases where we
  * need to linearize the skb.
  **/
-static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
-			       const u8 hdr_len)
+static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags)
 {
 	struct skb_frag_struct *frag;
 	bool linearize = false;
@@ -2429,7 +2436,7 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
 	gso_segs = skb_shinfo(skb)->gso_segs;
 
 	if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
-		u16 j = 1;
+		u16 j = 0;
 
 		if (num_frags < (I40E_MAX_BUFFER_TXD))
 			goto linearize_chk_done;
@@ -2440,21 +2447,18 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
 			goto linearize_chk_done;
 		}
 		frag = &skb_shinfo(skb)->frags[0];
-		size = hdr_len;
 		/* we might still have more fragments per segment */
 		do {
 			size += skb_frag_size(frag);
 			frag++; j++;
+			if ((size >= skb_shinfo(skb)->gso_size) &&
+			    (j < I40E_MAX_BUFFER_TXD)) {
+				size = (size % skb_shinfo(skb)->gso_size);
+				j = (size) ? 1 : 0;
+			}
 			if (j == I40E_MAX_BUFFER_TXD) {
-				if (size < skb_shinfo(skb)->gso_size) {
-					linearize = true;
-					break;
-				}
-				j = 1;
-				size -= skb_shinfo(skb)->gso_size;
-				if (size)
-					j++;
-				size += hdr_len;
+				linearize = true;
+				break;
 			}
 			num_frags--;
 		} while (num_frags);
@@ -2478,13 +2482,13 @@ linearize_chk_done:
  * @td_offset: offset for checksum or crc
  **/
 #ifdef I40E_FCOE
-void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		 struct i40e_tx_buffer *first, u32 tx_flags,
-		 const u8 hdr_len, u32 td_cmd, u32 td_offset)
-#else
-static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
+inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			struct i40e_tx_buffer *first, u32 tx_flags,
 			const u8 hdr_len, u32 td_cmd, u32 td_offset)
+#else
+static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
+			       struct i40e_tx_buffer *first, u32 tx_flags,
+			       const u8 hdr_len, u32 td_cmd, u32 td_offset)
 #endif
 {
 	unsigned int data_len = skb->data_len;
@@ -2590,9 +2594,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 						 tx_ring->queue_index),
 			     first->bytecount);
 
-	/* set the timestamp */
-	first->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -2645,11 +2646,11 @@ dma_error:
  * one descriptor.
  **/
 #ifdef I40E_FCOE
-int i40e_xmit_descriptor_count(struct sk_buff *skb,
-			       struct i40e_ring *tx_ring)
-#else
-static int i40e_xmit_descriptor_count(struct sk_buff *skb,
+inline int i40e_xmit_descriptor_count(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring)
+#else
+static inline int i40e_xmit_descriptor_count(struct sk_buff *skb,
+					     struct i40e_ring *tx_ring)
 #endif
 {
 	unsigned int f;
@@ -2711,7 +2712,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len,
+	tso = i40e_tso(tx_ring, skb, &hdr_len,
 		       &cd_type_cmd_tso_mss, &cd_tunneling);
 
 	if (tso < 0)
@@ -2724,7 +2725,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (tsyn)
 		tx_flags |= I40E_TX_FLAGS_TSYN;
 
-	if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+	if (i40e_chk_linearize(skb, tx_flags))
 		if (skb_linearize(skb))
 			goto out_drop;
 
@@ -2737,7 +2738,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		tx_flags |= I40E_TX_FLAGS_CSUM;
 
-		i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
+		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
 				    tx_ring, &cd_tunneling);
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 4b0b8102cdc3..0dc48dc9ca61 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -139,6 +139,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_TSYN		(u32)(1 << 8)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -146,7 +147,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 568e855da0f3..9a5a75b1e2bc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1133,6 +1133,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 78d1c4ff565e..23f95cdbdfcc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -980,6 +980,13 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	int pre_existing_vfs = pci_num_vf(pdev);
 	int err = 0;
 
+	if (pf->state & __I40E_TESTING) {
+		dev_warn(&pdev->dev,
+			 "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n");
+		err = -EPERM;
+		goto err_out;
+	}
+
 	dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
 	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
 		i40e_free_vfs(pf);
@@ -1018,11 +1025,19 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
 
-	if (num_vfs)
+	if (num_vfs) {
+		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+			i40e_do_reset_safe(pf,
+					   BIT_ULL(__I40E_PF_RESET_REQUESTED));
+		}
 		return i40e_pci_sriov_enable(pdev, num_vfs);
+	}
 
 	if (!pci_vfs_assigned(pf->pdev)) {
 		i40e_free_vfs(pf);
+		pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED;
+		i40e_do_reset_safe(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED));
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
 		return -EINVAL;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index b077e02a0cc7..f54996f19629 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -322,10 +322,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget)
 			 tx_ring->vsi->seid,
 			 tx_ring->queue_index,
 			 tx_ring->next_to_use, i);
-		dev_info(tx_ring->dev, "tx_bi[next_to_clean]\n"
-			 "  time_stamp           <%lx>\n"
-			 "  jiffies              <%lx>\n",
-			 tx_ring->tx_bi[i].time_stamp, jiffies);
 
 		netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
 
@@ -1128,9 +1124,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
-			/* TODO: shouldn't we increment a counter indicating the
-			 * drop?
-			 */
 			continue;
 		}
 
@@ -1156,7 +1149,6 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 		skb_mark_napi_id(skb, &rx_ring->q_vector->napi);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 
-		rx_ring->netdev->last_rx = jiffies;
 		rx_desc->wb.qword1.status_error_len = 0;
 
 	} while (likely(total_rx_packets < budget));
@@ -1271,7 +1263,6 @@ static int i40e_clean_rx_irq_1buf(struct i40e_ring *rx_ring, int budget)
 			 : 0;
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 
-		rx_ring->netdev->last_rx = jiffies;
 		rx_desc->wb.qword1.status_error_len = 0;
 	} while (likely(total_rx_packets < budget));
 
@@ -1352,7 +1343,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 }
 
 /**
- * i40e_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
+ * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
  * @flags:   the tx flags to be set
@@ -1363,9 +1354,9 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
  * Returns error code indicate the frame should be dropped upon error and the
  * otherwise  returns 0 to indicate the flags has been set properly.
  **/
-static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring,
-				      u32 *flags)
+static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb,
+					       struct i40e_ring *tx_ring,
+					       u32 *flags)
 {
 	__be16 protocol = skb->protocol;
 	u32  tx_flags = 0;
@@ -1408,16 +1399,14 @@ out:
  * i40e_tso - set up the tso context descriptor
  * @tx_ring:  ptr to the ring to send
  * @skb:      ptr to the skb we're sending
- * @tx_flags: the collected send information
- * @protocol: the send protocol
  * @hdr_len:  ptr to the size of the packet header
  * @cd_tunneling: ptr to context descriptor bits
  *
  * Returns 0 if no TSO can happen, 1 if tso is going, or error
  **/
 static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
-		    u32 tx_flags, __be16 protocol, u8 *hdr_len,
-		    u64 *cd_type_cmd_tso_mss, u32 *cd_tunneling)
+		    u8 *hdr_len, u64 *cd_type_cmd_tso_mss,
+		    u32 *cd_tunneling)
 {
 	u32 cd_cmd, cd_tso_len, cd_mss;
 	struct ipv6hdr *ipv6h;
@@ -1468,12 +1457,12 @@ static int i40e_tso(struct i40e_ring *tx_ring, struct sk_buff *skb,
 /**
  * i40e_tx_enable_csum - Enable Tx checksum offloads
  * @skb: send buffer
- * @tx_flags: Tx flags currently set
+ * @tx_flags: pointer to Tx flags currently set
  * @td_cmd: Tx descriptor command bits to set
  * @td_offset: Tx descriptor header offsets to set
  * @cd_tunneling: ptr to context desc bits
  **/
-static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
+static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags,
 				u32 *td_cmd, u32 *td_offset,
 				struct i40e_ring *tx_ring,
 				u32 *cd_tunneling)
@@ -1489,6 +1478,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		switch (ip_hdr(skb)->protocol) {
 		case IPPROTO_UDP:
 			l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING;
+			*tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL;
 			break;
 		default:
 			return;
@@ -1498,18 +1488,17 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		this_ipv6_hdr = inner_ipv6_hdr(skb);
 		this_tcp_hdrlen = inner_tcp_hdrlen(skb);
 
-		if (tx_flags & I40E_TX_FLAGS_IPV4) {
-
-			if (tx_flags & I40E_TX_FLAGS_TSO) {
+		if (*tx_flags & I40E_TX_FLAGS_IPV4) {
+			if (*tx_flags & I40E_TX_FLAGS_TSO) {
 				*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV4;
 				ip_hdr(skb)->check = 0;
 			} else {
 				*cd_tunneling |=
 					 I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM;
 			}
-		} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+		} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 			*cd_tunneling |= I40E_TX_CTX_EXT_IP_IPV6;
-			if (tx_flags & I40E_TX_FLAGS_TSO)
+			if (*tx_flags & I40E_TX_FLAGS_TSO)
 				ip_hdr(skb)->check = 0;
 		}
 
@@ -1521,8 +1510,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 					skb_transport_offset(skb)) >> 1) <<
 				   I40E_TXD_CTX_QW0_NATLEN_SHIFT;
 		if (this_ip_hdr->version == 6) {
-			tx_flags &= ~I40E_TX_FLAGS_IPV4;
-			tx_flags |= I40E_TX_FLAGS_IPV6;
+			*tx_flags &= ~I40E_TX_FLAGS_IPV4;
+			*tx_flags |= I40E_TX_FLAGS_IPV6;
 		}
 
 
@@ -1534,12 +1523,12 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 	}
 
 	/* Enable IP checksum offloads */
-	if (tx_flags & I40E_TX_FLAGS_IPV4) {
+	if (*tx_flags & I40E_TX_FLAGS_IPV4) {
 		l4_hdr = this_ip_hdr->protocol;
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
-		if (tx_flags & I40E_TX_FLAGS_TSO) {
+		if (*tx_flags & I40E_TX_FLAGS_TSO) {
 			*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV4_CSUM;
 			this_ip_hdr->check = 0;
 		} else {
@@ -1548,7 +1537,7 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 tx_flags,
 		/* Now set the td_offset for IP header length */
 		*td_offset = (network_hdr_len >> 2) <<
 			      I40E_TX_DESC_LENGTH_IPLEN_SHIFT;
-	} else if (tx_flags & I40E_TX_FLAGS_IPV6) {
+	} else if (*tx_flags & I40E_TX_FLAGS_IPV6) {
 		l4_hdr = this_ipv6_hdr->nexthdr;
 		*td_cmd |= I40E_TX_DESC_CMD_IIPT_IPV6;
 		/* Now set the td_offset for IP header length */
@@ -1619,14 +1608,12 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring,
  * i40e_chk_linearize - Check if there are more than 8 fragments per packet
  * @skb:      send buffer
  * @tx_flags: collected send information
- * @hdr_len:  size of the packet header
  *
  * Note: Our HW can't scatter-gather more than 8 fragments to build
  * a packet on the wire and so we need to figure out the cases where we
  * need to linearize the skb.
  **/
-static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
-			       const u8 hdr_len)
+static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags)
 {
 	struct skb_frag_struct *frag;
 	bool linearize = false;
@@ -1638,7 +1625,7 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
 	gso_segs = skb_shinfo(skb)->gso_segs;
 
 	if (tx_flags & (I40E_TX_FLAGS_TSO | I40E_TX_FLAGS_FSO)) {
-		u16 j = 1;
+		u16 j = 0;
 
 		if (num_frags < (I40E_MAX_BUFFER_TXD))
 			goto linearize_chk_done;
@@ -1649,21 +1636,18 @@ static bool i40e_chk_linearize(struct sk_buff *skb, u32 tx_flags,
 			goto linearize_chk_done;
 		}
 		frag = &skb_shinfo(skb)->frags[0];
-		size = hdr_len;
 		/* we might still have more fragments per segment */
 		do {
 			size += skb_frag_size(frag);
 			frag++; j++;
+			if ((size >= skb_shinfo(skb)->gso_size) &&
+			    (j < I40E_MAX_BUFFER_TXD)) {
+				size = (size % skb_shinfo(skb)->gso_size);
+				j = (size) ? 1 : 0;
+			}
 			if (j == I40E_MAX_BUFFER_TXD) {
-				if (size < skb_shinfo(skb)->gso_size) {
-					linearize = true;
-					break;
-				}
-				j = 1;
-				size -= skb_shinfo(skb)->gso_size;
-				if (size)
-					j++;
-				size += hdr_len;
+				linearize = true;
+				break;
 			}
 			num_frags--;
 		} while (num_frags);
@@ -1677,7 +1661,44 @@ linearize_chk_done:
 }
 
 /**
- * i40e_tx_map - Build the Tx descriptor
+ * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size:    the size buffer we want to assure is available
+ *
+ * Returns -EBUSY if a stop is needed, else 0
+ **/
+static inline int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	/* Memory barrier before checking head and tail */
+	smp_mb();
+
+	/* Check again in a case another CPU has just made room available. */
+	if (likely(I40E_DESC_UNUSED(tx_ring) < size))
+		return -EBUSY;
+
+	/* A reprieve! - use start_queue because it doesn't call schedule */
+	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
+	++tx_ring->tx_stats.restart_queue;
+	return 0;
+}
+
+/**
+ * i40evf_maybe_stop_tx - 1st level check for tx stop conditions
+ * @tx_ring: the ring to be checked
+ * @size:    the size buffer we want to assure is available
+ *
+ * Returns 0 if stop is not needed
+ **/
+static inline int i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
+{
+	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
+		return 0;
+	return __i40evf_maybe_stop_tx(tx_ring, size);
+}
+
+/**
+ * i40evf_tx_map - Build the Tx descriptor
  * @tx_ring:  ring to send buffer on
  * @skb:      send buffer
  * @first:    first buffer info buffer to use
@@ -1686,9 +1707,9 @@ linearize_chk_done:
  * @td_cmd:   the command field in the descriptor
  * @td_offset: offset for checksum or crc
  **/
-static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
-			struct i40e_tx_buffer *first, u32 tx_flags,
-			const u8 hdr_len, u32 td_cmd, u32 td_offset)
+static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
+				 struct i40e_tx_buffer *first, u32 tx_flags,
+				 const u8 hdr_len, u32 td_cmd, u32 td_offset)
 {
 	unsigned int data_len = skb->data_len;
 	unsigned int size = skb_headlen(skb);
@@ -1794,9 +1815,6 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 						 tx_ring->queue_index),
 			     first->bytecount);
 
-	/* set the timestamp */
-	first->time_stamp = jiffies;
-
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
 	 * applicable for weak-ordered memory model archs,
@@ -1813,8 +1831,12 @@ static void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	tx_ring->next_to_use = i;
 
+	i40evf_maybe_stop_tx(tx_ring, DESC_NEEDED);
 	/* notify HW of packet */
-	writel(i, tx_ring->tail);
+	if (!skb->xmit_more ||
+	    netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev,
+						   tx_ring->queue_index)))
+		writel(i, tx_ring->tail);
 
 	return;
 
@@ -1836,44 +1858,7 @@ dma_error:
 }
 
 /**
- * __i40e_maybe_stop_tx - 2nd level check for tx stop conditions
- * @tx_ring: the ring to be checked
- * @size:    the size buffer we want to assure is available
- *
- * Returns -EBUSY if a stop is needed, else 0
- **/
-static inline int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
-{
-	netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	/* Memory barrier before checking head and tail */
-	smp_mb();
-
-	/* Check again in a case another CPU has just made room available. */
-	if (likely(I40E_DESC_UNUSED(tx_ring) < size))
-		return -EBUSY;
-
-	/* A reprieve! - use start_queue because it doesn't call schedule */
-	netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index);
-	++tx_ring->tx_stats.restart_queue;
-	return 0;
-}
-
-/**
- * i40e_maybe_stop_tx - 1st level check for tx stop conditions
- * @tx_ring: the ring to be checked
- * @size:    the size buffer we want to assure is available
- *
- * Returns 0 if stop is not needed
- **/
-static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
-{
-	if (likely(I40E_DESC_UNUSED(tx_ring) >= size))
-		return 0;
-	return __i40e_maybe_stop_tx(tx_ring, size);
-}
-
-/**
- * i40e_xmit_descriptor_count - calculate number of tx descriptors needed
+ * i40evf_xmit_descriptor_count - calculate number of tx descriptors needed
  * @skb:     send buffer
  * @tx_ring: ring to send buffer on
  *
@@ -1881,8 +1866,8 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
  * there is not enough descriptors available in this ring since we need at least
  * one descriptor.
  **/
-static int i40e_xmit_descriptor_count(struct sk_buff *skb,
-				      struct i40e_ring *tx_ring)
+static inline int i40evf_xmit_descriptor_count(struct sk_buff *skb,
+					       struct i40e_ring *tx_ring)
 {
 	unsigned int f;
 	int count = 0;
@@ -1897,7 +1882,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
 
 	count += TXD_USE_COUNT(skb_headlen(skb));
-	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
+	if (i40evf_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;
 		return 0;
 	}
@@ -1923,11 +1908,11 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	u32 td_cmd = 0;
 	u8 hdr_len = 0;
 	int tso;
-	if (0 == i40e_xmit_descriptor_count(skb, tx_ring))
+	if (0 == i40evf_xmit_descriptor_count(skb, tx_ring))
 		return NETDEV_TX_BUSY;
 
 	/* prepare the xmit flags */
-	if (i40e_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
+	if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags))
 		goto out_drop;
 
 	/* obtain protocol of skb */
@@ -1942,7 +1927,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (protocol == htons(ETH_P_IPV6))
 		tx_flags |= I40E_TX_FLAGS_IPV6;
 
-	tso = i40e_tso(tx_ring, skb, tx_flags, protocol, &hdr_len,
+	tso = i40e_tso(tx_ring, skb, &hdr_len,
 		       &cd_type_cmd_tso_mss, &cd_tunneling);
 
 	if (tso < 0)
@@ -1950,7 +1935,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	else if (tso)
 		tx_flags |= I40E_TX_FLAGS_TSO;
 
-	if (i40e_chk_linearize(skb, tx_flags, hdr_len))
+	if (i40e_chk_linearize(skb, tx_flags))
 		if (skb_linearize(skb))
 			goto out_drop;
 
@@ -1963,17 +1948,15 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		tx_flags |= I40E_TX_FLAGS_CSUM;
 
-		i40e_tx_enable_csum(skb, tx_flags, &td_cmd, &td_offset,
+		i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset,
 				    tx_ring, &cd_tunneling);
 	}
 
 	i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss,
 			   cd_tunneling, cd_l2tag2);
 
-	i40e_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
-		    td_cmd, td_offset);
-
-	i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
+	i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len,
+		      td_cmd, td_offset);
 
 	return NETDEV_TX_OK;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 1e49bb1fbac1..e7a34f899f2c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -138,6 +138,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FCCRC		(u32)(1 << 6)
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -145,7 +146,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index ec9d83a93379..c463ec41579c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -1108,6 +1108,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8457d0306e3a..f287186192bb 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1036,7 +1036,7 @@ static void igb_reset_q_vector(struct igb_adapter *adapter, int v_idx)
 		adapter->tx_ring[q_vector->tx.ring->queue_index] = NULL;
 
 	if (q_vector->rx.ring)
-		adapter->tx_ring[q_vector->rx.ring->queue_index] = NULL;
+		adapter->rx_ring[q_vector->rx.ring->queue_index] = NULL;
 
 	netif_napi_del(&q_vector->napi);
 
@@ -1207,6 +1207,8 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 	q_vector = adapter->q_vector[v_idx];
 	if (!q_vector)
 		q_vector = kzalloc(size, GFP_KERNEL);
+	else
+		memset(q_vector, 0, size);
 	if (!q_vector)
 		return -ENOMEM;
 
@@ -1834,31 +1836,19 @@ void igb_reinit_locked(struct igb_adapter *adapter)
  *
  * @adapter: adapter struct
  **/
-static s32 igb_enable_mas(struct igb_adapter *adapter)
+static void igb_enable_mas(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
-	u32 connsw;
-	s32 ret_val = 0;
-
-	connsw = rd32(E1000_CONNSW);
-	if (!(hw->phy.media_type == e1000_media_type_copper))
-		return ret_val;
+	u32 connsw = rd32(E1000_CONNSW);
 
 	/* configure for SerDes media detect */
-	if (!(connsw & E1000_CONNSW_SERDESD)) {
+	if ((hw->phy.media_type == e1000_media_type_copper) &&
+	    (!(connsw & E1000_CONNSW_SERDESD))) {
 		connsw |= E1000_CONNSW_ENRGSRC;
 		connsw |= E1000_CONNSW_AUTOSENSE_EN;
 		wr32(E1000_CONNSW, connsw);
 		wrfl();
-	} else if (connsw & E1000_CONNSW_SERDESD) {
-		/* already SerDes, no need to enable anything */
-		return ret_val;
-	} else {
-		netdev_info(adapter->netdev,
-			"MAS: Unable to configure feature, disabling..\n");
-		adapter->flags &= ~IGB_FLAG_MAS_ENABLE;
 	}
-	return ret_val;
 }
 
 void igb_reset(struct igb_adapter *adapter)
@@ -1978,10 +1968,9 @@ void igb_reset(struct igb_adapter *adapter)
 		adapter->ei.get_invariants(hw);
 		adapter->flags &= ~IGB_FLAG_MEDIA_RESET;
 	}
-	if (adapter->flags & IGB_FLAG_MAS_ENABLE) {
-		if (igb_enable_mas(adapter))
-			dev_err(&pdev->dev,
-				"Error enabling Media Auto Sense\n");
+	if ((mac->type == e1000_82575) &&
+	    (adapter->flags & IGB_FLAG_MAS_ENABLE)) {
+		igb_enable_mas(adapter);
 	}
 	if (hw->mac.ops.init_hw(hw))
 		dev_err(&pdev->dev, "Hardware Error\n");
@@ -4987,6 +4976,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	struct igb_tx_buffer *first;
 	int tso;
 	u32 tx_flags = 0;
+	unsigned short f;
 	u16 count = TXD_USE_COUNT(skb_headlen(skb));
 	__be16 protocol = vlan_get_protocol(skb);
 	u8 hdr_len = 0;
@@ -4997,14 +4987,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-	if (NETDEV_FRAG_PAGE_MAX_SIZE > IGB_MAX_DATA_PER_TXD) {
-		unsigned short f;
-
-		for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
-			count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-	} else {
-		count += skb_shinfo(skb)->nr_frags;
-	}
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
 
 	if (igb_maybe_stop_tx(tx_ring, count + 3)) {
 		/* this is a hard error */
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index e3b9b63ad010..c3a9392cbc19 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -538,8 +538,8 @@ static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp,
 			igb->perout[i].start.tv_nsec = rq->perout.start.nsec;
 			igb->perout[i].period.tv_sec = ts.tv_sec;
 			igb->perout[i].period.tv_nsec = ts.tv_nsec;
-			wr32(trgttiml, rq->perout.start.sec);
-			wr32(trgttimh, rq->perout.start.nsec);
+			wr32(trgttimh, rq->perout.start.sec);
+			wr32(trgttiml, rq->perout.start.nsec);
 			tsauxc |= tsauxc_mask;
 			tsim |= tsim_mask;
 		} else {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 636f9e350162..ac3ac2a20386 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -643,6 +643,7 @@ struct ixgbe_adapter {
 #define IXGBE_FLAG2_RSS_FIELD_IPV4_UDP		(u32)(1 << 8)
 #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP		(u32)(1 << 9)
 #define IXGBE_FLAG2_PTP_PPS_ENABLED		(u32)(1 << 10)
+#define IXGBE_FLAG2_PHY_INTERRUPT		(u32)(1 << 11)
 
 	/* Tx fast path data */
 	int num_tx_queues;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 824a7ab79ab6..65db69b862fb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -1225,7 +1225,7 @@ static struct ixgbe_phy_operations phy_ops_82598 = {
 	.setup_link_speed	= &ixgbe_setup_phy_link_speed_generic,
 	.read_i2c_sff8472	= &ixgbe_read_i2c_sff8472_82598,
 	.read_i2c_eeprom	= &ixgbe_read_i2c_eeprom_82598,
-	.check_overtemp   = &ixgbe_tn_check_overtemp,
+	.check_overtemp		= &ixgbe_tn_check_overtemp,
 };
 
 struct ixgbe_info ixgbe_82598_info = {
@@ -1234,4 +1234,5 @@ struct ixgbe_info ixgbe_82598_info = {
 	.mac_ops		= &mac_ops_82598,
 	.eeprom_ops		= &eeprom_ops_82598,
 	.phy_ops		= &phy_ops_82598,
+	.mvals			= ixgbe_mvals_8259X,
 };
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index e0c363948bf4..6b87d9634614 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -71,7 +71,7 @@ bool ixgbe_mng_enabled(struct ixgbe_hw *hw)
 {
 	u32 fwsm, manc, factps;
 
-	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
+	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 	if ((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT)
 		return false;
 
@@ -79,7 +79,7 @@ bool ixgbe_mng_enabled(struct ixgbe_hw *hw)
 	if (!(manc & IXGBE_MANC_RCV_TCO_EN))
 		return false;
 
-	factps = IXGBE_READ_REG(hw, IXGBE_FACTPS);
+	factps = IXGBE_READ_REG(hw, IXGBE_FACTPS(hw));
 	if (factps & IXGBE_FACTPS_MNGCG)
 		return false;
 
@@ -510,7 +510,7 @@ static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw)
 	hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_2, &ee_ctrl_2);
 
 	/* Check to see if MNG FW could be enabled */
-	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
+	fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 
 	if (((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT) &&
 	    !hw->wol_enabled &&
@@ -2378,4 +2378,5 @@ struct ixgbe_info ixgbe_82599_info = {
 	.eeprom_ops             = &eeprom_ops_82599,
 	.phy_ops                = &phy_ops_82599,
 	.mbx_ops                = &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_8259X,
 };
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 06d8f3cfa099..4c1c26732b67 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -57,6 +57,11 @@ static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw,
 						 u16 offset);
 static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw);
 
+/* Base table for registers values that change by MAC */
+const u32 ixgbe_mvals_8259X[IXGBE_MVALS_IDX_LIMIT] = {
+	IXGBE_MVALS_INIT(8259X)
+};
+
 /**
  *  ixgbe_device_supports_autoneg_fc - Check if phy supports autoneg flow
  *  control
@@ -91,6 +96,8 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw)
 		case IXGBE_DEV_ID_82599_T3_LOM:
 		case IXGBE_DEV_ID_X540T:
 		case IXGBE_DEV_ID_X540T1:
+		case IXGBE_DEV_ID_X550T:
+		case IXGBE_DEV_ID_X550EM_X_10G_T:
 			supported = true;
 			break;
 		default:
@@ -463,7 +470,7 @@ s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw)
 		}
 	}
 
-	if (hw->mac.type == ixgbe_mac_X540) {
+	if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) {
 		if (hw->phy.id == 0)
 			hw->phy.ops.identify(hw);
 		hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i);
@@ -681,7 +688,7 @@ void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw)
 	bus->lan_id = bus->func;
 
 	/* check for a port swap */
-	reg = IXGBE_READ_REG(hw, IXGBE_FACTPS);
+	reg = IXGBE_READ_REG(hw, IXGBE_FACTPS(hw));
 	if (reg & IXGBE_FACTPS_LFS)
 		bus->func ^= 0x1;
 }
@@ -799,7 +806,7 @@ s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw)
 		 * Check for EEPROM present first.
 		 * If not present leave as none
 		 */
-		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 		if (eec & IXGBE_EEC_PRES) {
 			eeprom->type = ixgbe_eeprom_spi;
 
@@ -1283,14 +1290,14 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw)
 	if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0)
 		return IXGBE_ERR_SWFW_SYNC;
 
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 	/* Request EEPROM Access */
 	eec |= IXGBE_EEC_REQ;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 
 	for (i = 0; i < IXGBE_EEPROM_GRANT_ATTEMPTS; i++) {
-		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 		if (eec & IXGBE_EEC_GNT)
 			break;
 		udelay(5);
@@ -1299,7 +1306,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw)
 	/* Release if grant not acquired */
 	if (!(eec & IXGBE_EEC_GNT)) {
 		eec &= ~IXGBE_EEC_REQ;
-		IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+		IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 		hw_dbg(hw, "Could not acquire EEPROM grant\n");
 
 		hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM);
@@ -1309,7 +1316,7 @@ static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw)
 	/* Setup EEPROM for Read/Write */
 	/* Clear CS and SK */
 	eec &= ~(IXGBE_EEC_CS | IXGBE_EEC_SK);
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(1);
 	return 0;
@@ -1333,7 +1340,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 		 * If the SMBI bit is 0 when we read it, then the bit will be
 		 * set and we have the semaphore
 		 */
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 		if (!(swsm & IXGBE_SWSM_SMBI))
 			break;
 		usleep_range(50, 100);
@@ -1353,7 +1360,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 		 * If the SMBI bit is 0 when we read it, then the bit will be
 		 * set and we have the semaphore
 		 */
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 		if (swsm & IXGBE_SWSM_SMBI) {
 			hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n");
 			return IXGBE_ERR_EEPROM;
@@ -1362,16 +1369,16 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 
 	/* Now get the semaphore between SW/FW through the SWESMBI bit */
 	for (i = 0; i < timeout; i++) {
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 
 		/* Set the SW EEPROM semaphore bit to request access */
 		swsm |= IXGBE_SWSM_SWESMBI;
-		IXGBE_WRITE_REG(hw, IXGBE_SWSM, swsm);
+		IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm);
 
 		/* If we set the bit successfully then we got the
 		 * semaphore.
 		 */
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 		if (swsm & IXGBE_SWSM_SWESMBI)
 			break;
 
@@ -1400,11 +1407,11 @@ static void ixgbe_release_eeprom_semaphore(struct ixgbe_hw *hw)
 {
 	u32 swsm;
 
-	swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+	swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 
 	/* Release both semaphores by writing 0 to the bits SWESMBI and SMBI */
 	swsm &= ~(IXGBE_SWSM_SWESMBI | IXGBE_SWSM_SMBI);
-	IXGBE_WRITE_REG(hw, IXGBE_SWSM, swsm);
+	IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm);
 	IXGBE_WRITE_FLUSH(hw);
 }
 
@@ -1454,15 +1461,15 @@ static void ixgbe_standby_eeprom(struct ixgbe_hw *hw)
 {
 	u32 eec;
 
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 	/* Toggle CS to flush commands */
 	eec |= IXGBE_EEC_CS;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(1);
 	eec &= ~IXGBE_EEC_CS;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(1);
 }
@@ -1480,7 +1487,7 @@ static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data,
 	u32 mask;
 	u32 i;
 
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 	/*
 	 * Mask is used to shift "count" bits of "data" out to the EEPROM
@@ -1501,7 +1508,7 @@ static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data,
 		else
 			eec &= ~IXGBE_EEC_DI;
 
-		IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+		IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 		IXGBE_WRITE_FLUSH(hw);
 
 		udelay(1);
@@ -1518,7 +1525,7 @@ static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data,
 
 	/* We leave the "DI" bit set to "0" when we leave this routine. */
 	eec &= ~IXGBE_EEC_DI;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 	IXGBE_WRITE_FLUSH(hw);
 }
 
@@ -1539,7 +1546,7 @@ static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count)
 	 * the value of the "DO" bit.  During this "shifting in" process the
 	 * "DI" bit should always be clear.
 	 */
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 	eec &= ~(IXGBE_EEC_DO | IXGBE_EEC_DI);
 
@@ -1547,7 +1554,7 @@ static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count)
 		data = data << 1;
 		ixgbe_raise_eeprom_clk(hw, &eec);
 
-		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 		eec &= ~(IXGBE_EEC_DI);
 		if (eec & IXGBE_EEC_DO)
@@ -1571,7 +1578,7 @@ static void ixgbe_raise_eeprom_clk(struct ixgbe_hw *hw, u32 *eec)
 	 * (setting the SK bit), then delay
 	 */
 	*eec = *eec | IXGBE_EEC_SK;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, *eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), *eec);
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(1);
 }
@@ -1588,7 +1595,7 @@ static void ixgbe_lower_eeprom_clk(struct ixgbe_hw *hw, u32 *eec)
 	 * delay
 	 */
 	*eec = *eec & ~IXGBE_EEC_SK;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, *eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), *eec);
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(1);
 }
@@ -1601,19 +1608,19 @@ static void ixgbe_release_eeprom(struct ixgbe_hw *hw)
 {
 	u32 eec;
 
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 	eec |= IXGBE_EEC_CS;  /* Pull CS high */
 	eec &= ~IXGBE_EEC_SK; /* Lower SCK */
 
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 	IXGBE_WRITE_FLUSH(hw);
 
 	udelay(1);
 
 	/* Stop requesting EEPROM access */
 	eec &= ~IXGBE_EEC_REQ;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, eec);
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec);
 
 	hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index f21f8a165ec4..ec015fed8fa7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -118,6 +118,8 @@ bool ixgbe_mng_enabled(struct ixgbe_hw *hw);
 void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb,
 			     u32 headroom, int strategy);
 
+extern const u32 ixgbe_mvals_8259X[IXGBE_MVALS_IDX_LIMIT];
+
 #define IXGBE_I2C_THERMAL_SENSOR_ADDR	0xF8
 #define IXGBE_EMC_INTERNAL_DATA		0x00
 #define IXGBE_EMC_INTERNAL_THERM_LIMIT	0x20
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index eafa9ec802ba..ec7b2324b77b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -207,6 +207,7 @@ static int ixgbe_get_settings(struct net_device *netdev,
 	switch (adapter->hw.phy.type) {
 	case ixgbe_phy_tn:
 	case ixgbe_phy_aq:
+	case ixgbe_phy_x550em_ext_t:
 	case ixgbe_phy_cu_unknown:
 		ecmd->supported |= SUPPORTED_TP;
 		ecmd->advertising |= ADVERTISED_TP;
@@ -470,16 +471,16 @@ static void ixgbe_get_regs(struct net_device *netdev,
 	regs_buff[7] = IXGBE_READ_REG(hw, IXGBE_TCPTIMER);
 
 	/* NVM Register */
-	regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_EEC);
+	regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 	regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_EERD);
-	regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_FLA);
+	regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_FLA(hw));
 	regs_buff[11] = IXGBE_READ_REG(hw, IXGBE_EEMNGCTL);
 	regs_buff[12] = IXGBE_READ_REG(hw, IXGBE_EEMNGDATA);
 	regs_buff[13] = IXGBE_READ_REG(hw, IXGBE_FLMNGCTL);
 	regs_buff[14] = IXGBE_READ_REG(hw, IXGBE_FLMNGDATA);
 	regs_buff[15] = IXGBE_READ_REG(hw, IXGBE_FLMNGCNT);
 	regs_buff[16] = IXGBE_READ_REG(hw, IXGBE_FLOP);
-	regs_buff[17] = IXGBE_READ_REG(hw, IXGBE_GRC);
+	regs_buff[17] = IXGBE_READ_REG(hw, IXGBE_GRC(hw));
 
 	/* Interrupt */
 	/* don't read EICR because it can clear interrupt causes, instead
@@ -2594,18 +2595,35 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fdir_filter *input;
 	union ixgbe_atr_input mask;
+	u8 queue;
 	int err;
 
 	if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
 		return -EOPNOTSUPP;
 
-	/*
-	 * Don't allow programming if the action is a queue greater than
-	 * the number of online Rx queues.
+	/* ring_cookie is a masked into a set of queues and ixgbe pools or
+	 * we use the drop index.
 	 */
-	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
-	    (fsp->ring_cookie >= adapter->num_rx_queues))
-		return -EINVAL;
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		queue = IXGBE_FDIR_DROP_QUEUE;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (!vf && (ring >= adapter->num_rx_queues))
+			return -EINVAL;
+		else if (vf &&
+			 ((vf > adapter->num_vfs) ||
+			   ring >= adapter->num_rx_queues_per_pool))
+			return -EINVAL;
+
+		/* Map the ring onto the absolute queue index */
+		if (!vf)
+			queue = adapter->rx_ring[ring]->reg_idx;
+		else
+			queue = ((vf - 1) *
+				adapter->num_rx_queues_per_pool) + ring;
+	}
 
 	/* Don't allow indexes to exist outside of available space */
 	if (fsp->location >= ((1024 << adapter->fdir_pballoc) - 2)) {
@@ -2683,10 +2701,7 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 
 	/* program filters to filter memory */
 	err = ixgbe_fdir_write_perfect_filter_82599(hw,
-				&input->filter, input->sw_idx,
-				(input->action == IXGBE_FDIR_DROP_QUEUE) ?
-				IXGBE_FDIR_DROP_QUEUE :
-				adapter->rx_ring[input->action]->reg_idx);
+				&input->filter, input->sw_idx, queue);
 	if (err)
 		goto err_out_w_lock;
 
@@ -3053,7 +3068,7 @@ static int ixgbe_get_module_info(struct net_device *dev,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 status;
+	s32 status;
 	u8 sff8472_rev, addr_mode;
 	bool page_swap = false;
 
@@ -3061,14 +3076,14 @@ static int ixgbe_get_module_info(struct net_device *dev,
 	status = hw->phy.ops.read_i2c_eeprom(hw,
 					     IXGBE_SFF_SFF_8472_COMP,
 					     &sff8472_rev);
-	if (status != 0)
+	if (status)
 		return -EIO;
 
 	/* addressing mode is not supported */
 	status = hw->phy.ops.read_i2c_eeprom(hw,
 					     IXGBE_SFF_SFF_8472_SWAP,
 					     &addr_mode);
-	if (status != 0)
+	if (status)
 		return -EIO;
 
 	if (addr_mode & IXGBE_SFF_ADDRESSING_MODE) {
@@ -3095,7 +3110,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 status = IXGBE_ERR_PHY_ADDR_INVALID;
+	s32 status = IXGBE_ERR_PHY_ADDR_INVALID;
 	u8 databyte = 0xFF;
 	int i = 0;
 
@@ -3112,7 +3127,7 @@ static int ixgbe_get_module_eeprom(struct net_device *dev,
 		else
 			status = hw->phy.ops.read_i2c_sff8472(hw, i, &databyte);
 
-		if (status != 0)
+		if (status)
 			return -EIO;
 
 		data[i - ee->offset] = databyte;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 5be12a00e1f4..9aa6104e34ea 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -81,6 +81,8 @@ const char ixgbe_driver_version[] = DRV_VERSION;
 static const char ixgbe_copyright[] =
 				"Copyright (c) 1999-2014 Intel Corporation.";
 
+static const char ixgbe_overheat_msg[] = "Network adapter has been stopped because it has over heated. Restart the computer. If the problem persists, power off the system and replace the adapter";
+
 static const struct ixgbe_info *ixgbe_info_tbl[] = {
 	[board_82598]		= &ixgbe_82598_info,
 	[board_82599]		= &ixgbe_82599_info,
@@ -131,6 +133,7 @@ static const struct pci_device_id ixgbe_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x},
 	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x},
+	{PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x},
 	/* required last entry */
 	{0, }
 };
@@ -2366,7 +2369,7 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
 		 *  - We may have missed the interrupt so always have to
 		 *    check if we  got a LSC
 		 */
-		if (!(eicr & IXGBE_EICR_GPI_SDP0) &&
+		if (!(eicr & IXGBE_EICR_GPI_SDP0_8259X) &&
 		    !(eicr & IXGBE_EICR_LSC))
 			return;
 
@@ -2386,14 +2389,13 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter)
 
 		break;
 	default:
-		if (!(eicr & IXGBE_EICR_GPI_SDP0))
+		if (adapter->hw.mac.type >= ixgbe_mac_X540)
+			return;
+		if (!(eicr & IXGBE_EICR_GPI_SDP0(hw)))
 			return;
 		break;
 	}
-	e_crit(drv,
-	       "Network adapter has been stopped because it has over heated. "
-	       "Restart the computer. If the problem persists, "
-	       "power off the system and replace the adapter\n");
+	e_crit(drv, "%s\n", ixgbe_overheat_msg);
 
 	adapter->interrupt_event = 0;
 }
@@ -2403,15 +2405,17 @@ static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr)
 	struct ixgbe_hw *hw = &adapter->hw;
 
 	if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) &&
-	    (eicr & IXGBE_EICR_GPI_SDP1)) {
+	    (eicr & IXGBE_EICR_GPI_SDP1(hw))) {
 		e_crit(probe, "Fan has stopped, replace the adapter\n");
 		/* write to clear the interrupt */
-		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
+		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw));
 	}
 }
 
 static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
 {
+	struct ixgbe_hw *hw = &adapter->hw;
+
 	if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE))
 		return;
 
@@ -2421,7 +2425,8 @@ static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
 		 * Need to check link state so complete overtemp check
 		 * on service task
 		 */
-		if (((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC)) &&
+		if (((eicr & IXGBE_EICR_GPI_SDP0(hw)) ||
+		     (eicr & IXGBE_EICR_LSC)) &&
 		    (!test_bit(__IXGBE_DOWN, &adapter->state))) {
 			adapter->interrupt_event = eicr;
 			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT;
@@ -2437,28 +2442,46 @@ static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr)
 		return;
 	}
 
-	e_crit(drv,
-	       "Network adapter has been stopped because it has over heated. "
-	       "Restart the computer. If the problem persists, "
-	       "power off the system and replace the adapter\n");
+	e_crit(drv, "%s\n", ixgbe_overheat_msg);
+}
+
+static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
+{
+	switch (hw->mac.type) {
+	case ixgbe_mac_82598EB:
+		if (hw->phy.type == ixgbe_phy_nl)
+			return true;
+		return false;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X550EM_x:
+		switch (hw->mac.ops.get_media_type(hw)) {
+		case ixgbe_media_type_fiber:
+		case ixgbe_media_type_fiber_qsfp:
+			return true;
+		default:
+			return false;
+		}
+	default:
+		return false;
+	}
 }
 
 static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 
-	if (eicr & IXGBE_EICR_GPI_SDP2) {
+	if (eicr & IXGBE_EICR_GPI_SDP2(hw)) {
 		/* Clear the interrupt */
-		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2);
+		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2(hw));
 		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
 			adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET;
 			ixgbe_service_event_schedule(adapter);
 		}
 	}
 
-	if (eicr & IXGBE_EICR_GPI_SDP1) {
+	if (eicr & IXGBE_EICR_GPI_SDP1(hw)) {
 		/* Clear the interrupt */
-		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1);
+		IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw));
 		if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
 			adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG;
 			ixgbe_service_event_schedule(adapter);
@@ -2543,6 +2566,7 @@ static inline void ixgbe_irq_disable_queues(struct ixgbe_adapter *adapter,
 static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
 				    bool flush)
 {
+	struct ixgbe_hw *hw = &adapter->hw;
 	u32 mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE);
 
 	/* don't reenable LSC while waiting for link */
@@ -2552,7 +2576,7 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
 	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
 		switch (adapter->hw.mac.type) {
 		case ixgbe_mac_82599EB:
-			mask |= IXGBE_EIMS_GPI_SDP0;
+			mask |= IXGBE_EIMS_GPI_SDP0(hw);
 			break;
 		case ixgbe_mac_X540:
 		case ixgbe_mac_X550:
@@ -2563,15 +2587,17 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues,
 			break;
 		}
 	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
-		mask |= IXGBE_EIMS_GPI_SDP1;
+		mask |= IXGBE_EIMS_GPI_SDP1(hw);
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_82599EB:
-		mask |= IXGBE_EIMS_GPI_SDP1;
-		mask |= IXGBE_EIMS_GPI_SDP2;
+		mask |= IXGBE_EIMS_GPI_SDP1(hw);
+		mask |= IXGBE_EIMS_GPI_SDP2(hw);
 		/* fall through */
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+		if (adapter->hw.phy.type == ixgbe_phy_x550em_ext_t)
+			mask |= IXGBE_EICR_GPI_SDP0_X540;
 		mask |= IXGBE_EIMS_ECC;
 		mask |= IXGBE_EIMS_MAILBOX;
 		break;
@@ -2626,6 +2652,13 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data)
 	case ixgbe_mac_X540:
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
+		if (hw->phy.type == ixgbe_phy_x550em_ext_t &&
+		    (eicr & IXGBE_EICR_GPI_SDP0_X540)) {
+			adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT;
+			ixgbe_service_event_schedule(adapter);
+			IXGBE_WRITE_REG(hw, IXGBE_EICR,
+					IXGBE_EICR_GPI_SDP0_X540);
+		}
 		if (eicr & IXGBE_EICR_ECC) {
 			e_info(link, "Received ECC Err, initiating reset\n");
 			adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED;
@@ -4703,32 +4736,6 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
 	ixgbe_configure_dfwd(adapter);
 }
 
-static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
-{
-	switch (hw->phy.type) {
-	case ixgbe_phy_sfp_avago:
-	case ixgbe_phy_sfp_ftl:
-	case ixgbe_phy_sfp_intel:
-	case ixgbe_phy_sfp_unknown:
-	case ixgbe_phy_sfp_passive_tyco:
-	case ixgbe_phy_sfp_passive_unknown:
-	case ixgbe_phy_sfp_active_unknown:
-	case ixgbe_phy_sfp_ftl_active:
-	case ixgbe_phy_qsfp_passive_unknown:
-	case ixgbe_phy_qsfp_active_unknown:
-	case ixgbe_phy_qsfp_intel:
-	case ixgbe_phy_qsfp_unknown:
-	/* ixgbe_phy_none is set when no SFP module is present */
-	case ixgbe_phy_none:
-		return true;
-	case ixgbe_phy_nl:
-		if (hw->mac.type == ixgbe_mac_82598EB)
-			return true;
-	default:
-		return false;
-	}
-}
-
 /**
  * ixgbe_sfp_link_config - set up SFP+ link
  * @adapter: pointer to private adapter struct
@@ -4757,7 +4764,7 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 {
 	u32 speed;
 	bool autoneg, link_up = false;
-	u32 ret = IXGBE_ERR_LINK_SETUP;
+	int ret = IXGBE_ERR_LINK_SETUP;
 
 	if (hw->mac.ops.check_link)
 		ret = hw->mac.ops.check_link(hw, &speed, &link_up, false);
@@ -4833,7 +4840,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
 	if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) {
 		switch (adapter->hw.mac.type) {
 		case ixgbe_mac_82599EB:
-			gpie |= IXGBE_SDP0_GPIEN;
+			gpie |= IXGBE_SDP0_GPIEN_8259X;
 			break;
 		case ixgbe_mac_X540:
 			gpie |= IXGBE_EIMS_TS;
@@ -4845,11 +4852,11 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
 
 	/* Enable fan failure interrupt */
 	if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
-		gpie |= IXGBE_SDP1_GPIEN;
+		gpie |= IXGBE_SDP1_GPIEN(hw);
 
 	if (hw->mac.type == ixgbe_mac_82599EB) {
-		gpie |= IXGBE_SDP1_GPIEN;
-		gpie |= IXGBE_SDP2_GPIEN;
+		gpie |= IXGBE_SDP1_GPIEN_8259X;
+		gpie |= IXGBE_SDP2_GPIEN_8259X;
 	}
 
 	IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
@@ -4873,6 +4880,9 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
 	if (hw->mac.ops.enable_tx_laser)
 		hw->mac.ops.enable_tx_laser(hw);
 
+	if (hw->phy.ops.set_phy_power)
+		hw->phy.ops.set_phy_power(hw, true);
+
 	smp_mb__before_atomic();
 	clear_bit(__IXGBE_DOWN, &adapter->state);
 	ixgbe_napi_enable_all(adapter);
@@ -4992,6 +5002,13 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 
 	if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state))
 		ixgbe_ptp_reset(adapter);
+
+	if (hw->phy.ops.set_phy_power) {
+		if (!netif_running(adapter->netdev) && !adapter->wol)
+			hw->phy.ops.set_phy_power(hw, false);
+		else
+			hw->phy.ops.set_phy_power(hw, true);
+	}
 }
 
 /**
@@ -5260,7 +5277,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
 		break;
 	case ixgbe_mac_X540:
-		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM);
+		fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw));
 		if (fwsm & IXGBE_FWSM_TS_ENABLED)
 			adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE;
 		break;
@@ -5672,6 +5689,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 static int ixgbe_open(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
 	int err, queues;
 
 	/* disallow open during test */
@@ -5729,6 +5747,8 @@ err_set_queues:
 	ixgbe_free_irq(adapter);
 err_req_irq:
 	ixgbe_free_all_rx_resources(adapter);
+	if (hw->phy.ops.set_phy_power && !adapter->wol)
+		hw->phy.ops.set_phy_power(&adapter->hw, false);
 err_setup_rx:
 	ixgbe_free_all_tx_resources(adapter);
 err_setup_tx:
@@ -5889,6 +5909,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	}
 
 	*enable_wake = !!wufc;
+	if (hw->phy.ops.set_phy_power && !*enable_wake)
+		hw->phy.ops.set_phy_power(hw, false);
 
 	ixgbe_release_hw_control(adapter);
 
@@ -6718,6 +6740,26 @@ static void ixgbe_service_timer(unsigned long data)
 	ixgbe_service_event_schedule(adapter);
 }
 
+static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 status;
+
+	if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT))
+		return;
+
+	adapter->flags2 &= ~IXGBE_FLAG2_PHY_INTERRUPT;
+
+	if (!hw->phy.ops.handle_lasi)
+		return;
+
+	status = hw->phy.ops.handle_lasi(&adapter->hw);
+	if (status != IXGBE_ERR_OVERTEMP)
+		return;
+
+	e_crit(drv, "%s\n", ixgbe_overheat_msg);
+}
+
 static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter)
 {
 	if (!(adapter->flags2 & IXGBE_FLAG2_RESET_REQUESTED))
@@ -6759,6 +6801,7 @@ static void ixgbe_service_task(struct work_struct *work)
 		return;
 	}
 	ixgbe_reset_subtask(adapter);
+	ixgbe_phy_interrupt_subtask(adapter);
 	ixgbe_sfp_detection_subtask(adapter);
 	ixgbe_sfp_link_config_subtask(adapter);
 	ixgbe_check_overtemp_subtask(adapter);
@@ -8022,7 +8065,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
 		return -EINVAL;
 
 	nla_for_each_nested(attr, br_spec, rem) {
-		u32 status;
+		int status;
 		__u16 mode;
 
 		if (nla_type(attr) != IFLA_BRIDGE_MODE)
@@ -8052,7 +8095,8 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 		return 0;
 
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
-				       adapter->bridge_mode, 0, 0, nlflags);
+				       adapter->bridge_mode, 0, 0, nlflags,
+				       filter_mask, NULL);
 }
 
 static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
@@ -8291,6 +8335,10 @@ int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 		break;
 	case IXGBE_DEV_ID_X540T:
 	case IXGBE_DEV_ID_X540T1:
+	case IXGBE_DEV_ID_X550T:
+	case IXGBE_DEV_ID_X550EM_X_KX4:
+	case IXGBE_DEV_ID_X550EM_X_KR:
+	case IXGBE_DEV_ID_X550EM_X_10G_T:
 		/* check eeprom to see if enabled wol */
 		if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) ||
 		    ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) &&
@@ -8431,10 +8479,11 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup hw api */
 	memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops));
 	hw->mac.type  = ii->mac;
+	hw->mvals     = ii->mvals;
 
 	/* EEPROM */
 	memcpy(&hw->eeprom.ops, ii->eeprom_ops, sizeof(hw->eeprom.ops));
-	eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+	eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 	if (ixgbe_removed(hw->hw_addr)) {
 		err = -EIO;
 		goto err_ioremap;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 8a2be444113d..526a20bf7488 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -317,14 +317,14 @@ bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw)
  **/
 static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw)
 {
-	u32 status;
+	s32 status;
 	u16 phy_id_high = 0;
 	u16 phy_id_low = 0;
 
 	status = hw->phy.ops.read_reg(hw, MDIO_DEVID1, MDIO_MMD_PMAPMD,
 				      &phy_id_high);
 
-	if (status == 0) {
+	if (!status) {
 		hw->phy.id = (u32)(phy_id_high << 16);
 		status = hw->phy.ops.read_reg(hw, MDIO_DEVID2, MDIO_MMD_PMAPMD,
 					      &phy_id_low);
@@ -347,6 +347,7 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id)
 	case TN1010_PHY_ID:
 		phy_type = ixgbe_phy_tn;
 		break;
+	case X550_PHY_ID:
 	case X540_PHY_ID:
 		phy_type = ixgbe_phy_aq;
 		break;
@@ -356,6 +357,9 @@ static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id)
 	case ATH_PHY_ID:
 		phy_type = ixgbe_phy_nl;
 		break;
+	case X557_PHY_ID:
+		phy_type = ixgbe_phy_x550em_ext_t;
+		break;
 	default:
 		phy_type = ixgbe_phy_unknown;
 		break;
@@ -1348,6 +1352,9 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 		return IXGBE_ERR_SFP_NOT_PRESENT;
 	}
 
+	/* LAN ID is needed for sfp_type determination */
+	hw->mac.ops.set_lan_id(hw);
+
 	status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER,
 					     &identifier);
 
@@ -1361,9 +1368,6 @@ static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw)
 
 	hw->phy.id = identifier;
 
-	/* LAN ID is needed for sfp_type determination */
-	hw->mac.ops.set_lan_id(hw);
-
 	status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_10GBE_COMP,
 					     &comp_codes_10g);
 
@@ -1793,7 +1797,7 @@ fail:
  **/
 static void ixgbe_i2c_start(struct ixgbe_hw *hw)
 {
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 
 	/* Start condition must begin with data and clock high */
 	ixgbe_set_i2c_data(hw, &i2cctl, 1);
@@ -1822,7 +1826,7 @@ static void ixgbe_i2c_start(struct ixgbe_hw *hw)
  **/
 static void ixgbe_i2c_stop(struct ixgbe_hw *hw)
 {
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 
 	/* Stop condition must begin with data low and clock high */
 	ixgbe_set_i2c_data(hw, &i2cctl, 0);
@@ -1880,9 +1884,9 @@ static s32 ixgbe_clock_out_i2c_byte(struct ixgbe_hw *hw, u8 data)
 	}
 
 	/* Release SDA line (set high) */
-	i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
-	i2cctl |= IXGBE_I2C_DATA_OUT_BY_MAC(hw);
-	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL_BY_MAC(hw), i2cctl);
+	i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
+	i2cctl |= IXGBE_I2C_DATA_OUT(hw);
+	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl);
 	IXGBE_WRITE_FLUSH(hw);
 
 	return status;
@@ -1898,7 +1902,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw)
 {
 	s32 status = 0;
 	u32 i = 0;
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 	u32 timeout = 10;
 	bool ack = true;
 
@@ -1911,7 +1915,7 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw)
 	/* Poll for ACK.  Note that ACK in I2C spec is
 	 * transition from 1 to 0 */
 	for (i = 0; i < timeout; i++) {
-		i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+		i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 		ack = ixgbe_get_i2c_data(hw, &i2cctl);
 
 		udelay(1);
@@ -1941,14 +1945,14 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw)
  **/
 static s32 ixgbe_clock_in_i2c_bit(struct ixgbe_hw *hw, bool *data)
 {
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 
 	ixgbe_raise_i2c_clk(hw, &i2cctl);
 
 	/* Minimum high period of clock is 4us */
 	udelay(IXGBE_I2C_T_HIGH);
 
-	i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 	*data = ixgbe_get_i2c_data(hw, &i2cctl);
 
 	ixgbe_lower_i2c_clk(hw, &i2cctl);
@@ -1969,7 +1973,7 @@ static s32 ixgbe_clock_in_i2c_bit(struct ixgbe_hw *hw, bool *data)
 static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data)
 {
 	s32 status;
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 
 	status = ixgbe_set_i2c_data(hw, &i2cctl, data);
 	if (status == 0) {
@@ -2005,14 +2009,14 @@ static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl)
 	u32 i2cctl_r = 0;
 
 	for (i = 0; i < timeout; i++) {
-		*i2cctl |= IXGBE_I2C_CLK_OUT_BY_MAC(hw);
-		IXGBE_WRITE_REG(hw, IXGBE_I2CCTL_BY_MAC(hw), *i2cctl);
+		*i2cctl |= IXGBE_I2C_CLK_OUT(hw);
+		IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl);
 		IXGBE_WRITE_FLUSH(hw);
 		/* SCL rise time (1000ns) */
 		udelay(IXGBE_I2C_T_RISE);
 
-		i2cctl_r = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
-		if (i2cctl_r & IXGBE_I2C_CLK_IN_BY_MAC(hw))
+		i2cctl_r = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
+		if (i2cctl_r & IXGBE_I2C_CLK_IN(hw))
 			break;
 	}
 }
@@ -2027,9 +2031,9 @@ static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl)
 static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl)
 {
 
-	*i2cctl &= ~IXGBE_I2C_CLK_OUT_BY_MAC(hw);
+	*i2cctl &= ~IXGBE_I2C_CLK_OUT(hw);
 
-	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL_BY_MAC(hw), *i2cctl);
+	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl);
 	IXGBE_WRITE_FLUSH(hw);
 
 	/* SCL fall time (300ns) */
@@ -2047,18 +2051,18 @@ static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl)
 static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data)
 {
 	if (data)
-		*i2cctl |= IXGBE_I2C_DATA_OUT_BY_MAC(hw);
+		*i2cctl |= IXGBE_I2C_DATA_OUT(hw);
 	else
-		*i2cctl &= ~IXGBE_I2C_DATA_OUT_BY_MAC(hw);
+		*i2cctl &= ~IXGBE_I2C_DATA_OUT(hw);
 
-	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL_BY_MAC(hw), *i2cctl);
+	IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl);
 	IXGBE_WRITE_FLUSH(hw);
 
 	/* Data rise/fall (1000ns/300ns) and set-up time (250ns) */
 	udelay(IXGBE_I2C_T_RISE + IXGBE_I2C_T_FALL + IXGBE_I2C_T_SU_DATA);
 
 	/* Verify data was set correctly */
-	*i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	*i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 	if (data != ixgbe_get_i2c_data(hw, i2cctl)) {
 		hw_dbg(hw, "Error - I2C data was not set to %X.\n", data);
 		return IXGBE_ERR_I2C;
@@ -2076,7 +2080,7 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data)
  **/
 static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl)
 {
-	if (*i2cctl & IXGBE_I2C_DATA_IN_BY_MAC(hw))
+	if (*i2cctl & IXGBE_I2C_DATA_IN(hw))
 		return true;
 	return false;
 }
@@ -2090,7 +2094,7 @@ static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl)
  **/
 static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw)
 {
-	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL_BY_MAC(hw));
+	u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw));
 	u32 i;
 
 	ixgbe_i2c_start(hw);
@@ -2137,3 +2141,36 @@ s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw)
 
 	return IXGBE_ERR_OVERTEMP;
 }
+
+/** ixgbe_set_copper_phy_power - Control power for copper phy
+ *  @hw: pointer to hardware structure
+ *  @on: true for on, false for off
+ **/
+s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on)
+{
+	u32 status;
+	u16 reg;
+
+	/* Bail if we don't have copper phy */
+	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
+		return 0;
+
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
+	if (status)
+		return status;
+
+	if (on) {
+		reg &= ~IXGBE_MDIO_PHY_SET_LOW_POWER_MODE;
+	} else {
+		if (ixgbe_check_reset_blocked(hw))
+			return 0;
+		reg |= IXGBE_MDIO_PHY_SET_LOW_POWER_MODE;
+	}
+
+	status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL,
+				       IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				       reg);
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 434643881287..e45988c4dad5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -145,6 +145,7 @@ s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw,
 					   u16 *firmware_version);
 
 s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw);
+s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on);
 s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw);
 s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw);
 s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index dd6ba5916dfe..b6f424f3b1a8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -91,14 +91,24 @@
 #define IXGBE_DEV_ID_X550_VF		0x1565
 #define IXGBE_DEV_ID_X550EM_X_VF	0x15A8
 
+#define IXGBE_CAT(r, m)	IXGBE_##r##_##m
+
+#define IXGBE_BY_MAC(_hw, r)	((_hw)->mvals[IXGBE_CAT(r, IDX)])
+
 /* General Registers */
 #define IXGBE_CTRL      0x00000
 #define IXGBE_STATUS    0x00008
 #define IXGBE_CTRL_EXT  0x00018
 #define IXGBE_ESDP      0x00020
 #define IXGBE_EODSDP    0x00028
-#define IXGBE_I2CCTL_BY_MAC(_hw)((((_hw)->mac.type >= ixgbe_mac_X550) ? \
-					0x15F5C : 0x00028))
+
+#define IXGBE_I2CCTL_8259X	0x00028
+#define IXGBE_I2CCTL_X540	IXGBE_I2CCTL_8259X
+#define IXGBE_I2CCTL_X550	0x15F5C
+#define IXGBE_I2CCTL_X550EM_x	IXGBE_I2CCTL_X550
+#define IXGBE_I2CCTL_X550EM_a	IXGBE_I2CCTL_X550
+#define IXGBE_I2CCTL(_hw)	IXGBE_BY_MAC((_hw), I2CCTL)
+
 #define IXGBE_LEDCTL    0x00200
 #define IXGBE_FRTIMER   0x00048
 #define IXGBE_TCPTIMER  0x0004C
@@ -106,17 +116,39 @@
 #define IXGBE_EXVET     0x05078
 
 /* NVM Registers */
-#define IXGBE_EEC       0x10010
+#define IXGBE_EEC_8259X		0x10010
+#define IXGBE_EEC_X540		IXGBE_EEC_8259X
+#define IXGBE_EEC_X550		IXGBE_EEC_8259X
+#define IXGBE_EEC_X550EM_x	IXGBE_EEC_8259X
+#define IXGBE_EEC_X550EM_a	0x15FF8
+#define IXGBE_EEC(_hw)		IXGBE_BY_MAC((_hw), EEC)
 #define IXGBE_EERD      0x10014
 #define IXGBE_EEWR      0x10018
-#define IXGBE_FLA       0x1001C
+#define IXGBE_FLA_8259X		0x1001C
+#define IXGBE_FLA_X540		IXGBE_FLA_8259X
+#define IXGBE_FLA_X550		IXGBE_FLA_8259X
+#define IXGBE_FLA_X550EM_x	IXGBE_FLA_8259X
+#define IXGBE_FLA_X550EM_a	0x15F6C
+#define IXGBE_FLA(_hw)		IXGBE_BY_MAC((_hw), FLA)
 #define IXGBE_EEMNGCTL  0x10110
 #define IXGBE_EEMNGDATA 0x10114
 #define IXGBE_FLMNGCTL  0x10118
 #define IXGBE_FLMNGDATA 0x1011C
 #define IXGBE_FLMNGCNT  0x10120
 #define IXGBE_FLOP      0x1013C
-#define IXGBE_GRC       0x10200
+#define IXGBE_GRC_8259X		0x10200
+#define IXGBE_GRC_X540		IXGBE_GRC_8259X
+#define IXGBE_GRC_X550		IXGBE_GRC_8259X
+#define IXGBE_GRC_X550EM_x	IXGBE_GRC_8259X
+#define IXGBE_GRC_X550EM_a	0x15F64
+#define IXGBE_GRC(_hw)		IXGBE_BY_MAC((_hw), GRC)
+
+#define IXGBE_SRAMREL_8259X	0x10210
+#define IXGBE_SRAMREL_X540	IXGBE_SRAMREL_8259X
+#define IXGBE_SRAMREL_X550	IXGBE_SRAMREL_8259X
+#define IXGBE_SRAMREL_X550EM_x	IXGBE_SRAMREL_8259X
+#define IXGBE_SRAMREL_X550EM_a	0x15F6C
+#define IXGBE_SRAMREL(_hw)	IXGBE_BY_MAC((_hw), SRAMREL)
 
 /* General Receive Control */
 #define IXGBE_GRC_MNG  0x00000001 /* Manageability Enable */
@@ -126,14 +158,55 @@
 #define IXGBE_VPDDIAG1  0x10208
 
 /* I2CCTL Bit Masks */
-#define IXGBE_I2C_CLK_IN_BY_MAC(_hw)(((_hw)->mac.type) >= ixgbe_mac_X550 ? \
-					0x00004000 : 0x00000001)
-#define IXGBE_I2C_CLK_OUT_BY_MAC(_hw)(((_hw)->mac.type) >= ixgbe_mac_X550 ? \
-					0x00000200 : 0x00000002)
-#define IXGBE_I2C_DATA_IN_BY_MAC(_hw)(((_hw)->mac.type) >= ixgbe_mac_X550 ? \
-					0x00001000 : 0x00000004)
-#define IXGBE_I2C_DATA_OUT_BY_MAC(_hw)(((_hw)->mac.type) >= ixgbe_mac_X550 ? \
-					0x00000400 : 0x00000008)
+#define IXGBE_I2C_CLK_IN_8259X		0x00000001
+#define IXGBE_I2C_CLK_IN_X540		IXGBE_I2C_CLK_IN_8259X
+#define IXGBE_I2C_CLK_IN_X550		0x00004000
+#define IXGBE_I2C_CLK_IN_X550EM_x	IXGBE_I2C_CLK_IN_X550
+#define IXGBE_I2C_CLK_IN_X550EM_a	IXGBE_I2C_CLK_IN_X550
+#define IXGBE_I2C_CLK_IN(_hw)		IXGBE_BY_MAC((_hw), I2C_CLK_IN)
+
+#define IXGBE_I2C_CLK_OUT_8259X		0x00000002
+#define IXGBE_I2C_CLK_OUT_X540		IXGBE_I2C_CLK_OUT_8259X
+#define IXGBE_I2C_CLK_OUT_X550		0x00000200
+#define IXGBE_I2C_CLK_OUT_X550EM_x	IXGBE_I2C_CLK_OUT_X550
+#define IXGBE_I2C_CLK_OUT_X550EM_a	IXGBE_I2C_CLK_OUT_X550
+#define IXGBE_I2C_CLK_OUT(_hw)		IXGBE_BY_MAC((_hw), I2C_CLK_OUT)
+
+#define IXGBE_I2C_DATA_IN_8259X		0x00000004
+#define IXGBE_I2C_DATA_IN_X540		IXGBE_I2C_DATA_IN_8259X
+#define IXGBE_I2C_DATA_IN_X550		0x00001000
+#define IXGBE_I2C_DATA_IN_X550EM_x	IXGBE_I2C_DATA_IN_X550
+#define IXGBE_I2C_DATA_IN_X550EM_a	IXGBE_I2C_DATA_IN_X550
+#define IXGBE_I2C_DATA_IN(_hw)		IXGBE_BY_MAC((_hw), I2C_DATA_IN)
+
+#define IXGBE_I2C_DATA_OUT_8259X	0x00000008
+#define IXGBE_I2C_DATA_OUT_X540		IXGBE_I2C_DATA_OUT_8259X
+#define IXGBE_I2C_DATA_OUT_X550		0x00000400
+#define IXGBE_I2C_DATA_OUT_X550EM_x	IXGBE_I2C_DATA_OUT_X550
+#define IXGBE_I2C_DATA_OUT_X550EM_a	IXGBE_I2C_DATA_OUT_X550
+#define IXGBE_I2C_DATA_OUT(_hw)		IXGBE_BY_MAC((_hw), I2C_DATA_OUT)
+
+#define IXGBE_I2C_DATA_OE_N_EN_8259X	0
+#define IXGBE_I2C_DATA_OE_N_EN_X540	IXGBE_I2C_DATA_OE_N_EN_8259X
+#define IXGBE_I2C_DATA_OE_N_EN_X550	0x00000800
+#define IXGBE_I2C_DATA_OE_N_EN_X550EM_x	IXGBE_I2C_DATA_OE_N_EN_X550
+#define IXGBE_I2C_DATA_OE_N_EN_X550EM_a	IXGBE_I2C_DATA_OE_N_EN_X550
+#define IXGBE_I2C_DATA_OE_N_EN(_hw)	IXGBE_BY_MAC((_hw), I2C_DATA_OE_N_EN)
+
+#define IXGBE_I2C_BB_EN_8259X		0
+#define IXGBE_I2C_BB_EN_X540		IXGBE_I2C_BB_EN_8259X
+#define IXGBE_I2C_BB_EN_X550		0x00000100
+#define IXGBE_I2C_BB_EN_X550EM_x	IXGBE_I2C_BB_EN_X550
+#define IXGBE_I2C_BB_EN_X550EM_a	IXGBE_I2C_BB_EN_X550
+#define IXGBE_I2C_BB_EN(_hw)		IXGBE_BY_MAC((_hw), I2C_BB_EN)
+
+#define IXGBE_I2C_CLK_OE_N_EN_8259X	0
+#define IXGBE_I2C_CLK_OE_N_EN_X540	IXGBE_I2C_CLK_OE_N_EN_8259X
+#define IXGBE_I2C_CLK_OE_N_EN_X550	0x00002000
+#define IXGBE_I2C_CLK_OE_N_EN_X550EM_x	IXGBE_I2C_CLK_OE_N_EN_X550
+#define IXGBE_I2C_CLK_OE_N_EN_X550EM_a	IXGBE_I2C_CLK_OE_N_EN_X550
+#define IXGBE_I2C_CLK_OE_N_EN(_hw)	 IXGBE_BY_MAC((_hw), I2C_CLK_OE_N_EN)
+
 #define IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT	500
 
 #define IXGBE_I2C_THERMAL_SENSOR_ADDR	0xF8
@@ -835,15 +908,36 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_GSCN_1    0x11024
 #define IXGBE_GSCN_2    0x11028
 #define IXGBE_GSCN_3    0x1102C
-#define IXGBE_FACTPS    0x10150
+#define IXGBE_FACTPS_8259X	0x10150
+#define IXGBE_FACTPS_X540	IXGBE_FACTPS_8259X
+#define IXGBE_FACTPS_X550	IXGBE_FACTPS_8259X
+#define IXGBE_FACTPS_X550EM_x	IXGBE_FACTPS_8259X
+#define IXGBE_FACTPS_X550EM_a	0x15FEC
+#define IXGBE_FACTPS(_hw)	IXGBE_BY_MAC((_hw), FACTPS)
+
 #define IXGBE_PCIEANACTL  0x11040
-#define IXGBE_SWSM      0x10140
-#define IXGBE_FWSM      0x10148
+#define IXGBE_SWSM_8259X	0x10140
+#define IXGBE_SWSM_X540		IXGBE_SWSM_8259X
+#define IXGBE_SWSM_X550		IXGBE_SWSM_8259X
+#define IXGBE_SWSM_X550EM_x	IXGBE_SWSM_8259X
+#define IXGBE_SWSM_X550EM_a	0x15F70
+#define IXGBE_SWSM(_hw)		IXGBE_BY_MAC((_hw), SWSM)
+#define IXGBE_FWSM_8259X	0x10148
+#define IXGBE_FWSM_X540		IXGBE_FWSM_8259X
+#define IXGBE_FWSM_X550		IXGBE_FWSM_8259X
+#define IXGBE_FWSM_X550EM_x	IXGBE_FWSM_8259X
+#define IXGBE_FWSM_X550EM_a	0x15F74
+#define IXGBE_FWSM(_hw)		IXGBE_BY_MAC((_hw), FWSM)
 #define IXGBE_GSSR      0x10160
 #define IXGBE_MREVID    0x11064
 #define IXGBE_DCA_ID    0x11070
 #define IXGBE_DCA_CTRL  0x11074
-#define IXGBE_SWFW_SYNC IXGBE_GSSR
+#define IXGBE_SWFW_SYNC_8259X		IXGBE_GSSR
+#define IXGBE_SWFW_SYNC_X540		IXGBE_SWFW_SYNC_8259X
+#define IXGBE_SWFW_SYNC_X550		IXGBE_SWFW_SYNC_8259X
+#define IXGBE_SWFW_SYNC_X550EM_x	IXGBE_SWFW_SYNC_8259X
+#define IXGBE_SWFW_SYNC_X550EM_a	0x15F78
+#define IXGBE_SWFW_SYNC(_hw)		IXGBE_BY_MAC((_hw), SWFW_SYNC)
 
 /* PCIe registers 82599-specific */
 #define IXGBE_GCR_EXT           0x11050
@@ -855,14 +949,21 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_PHYDAT_82599      0x11044
 #define IXGBE_PHYCTL_82599      0x11048
 #define IXGBE_PBACLR_82599      0x11068
-#define IXGBE_CIAA_82599        0x11088
-#define IXGBE_CIAD_82599        0x1108C
-#define IXGBE_CIAA_X550         0x11508
-#define IXGBE_CIAD_X550         0x11510
-#define IXGBE_CIAA_BY_MAC(_hw)  ((((_hw)->mac.type >= ixgbe_mac_X550) ? \
-				IXGBE_CIAA_X550 : IXGBE_CIAA_82599))
-#define IXGBE_CIAD_BY_MAC(_hw)  ((((_hw)->mac.type >= ixgbe_mac_X550) ? \
-				IXGBE_CIAD_X550 : IXGBE_CIAD_82599))
+
+#define IXGBE_CIAA_8259X	0x11088
+#define IXGBE_CIAA_X540		IXGBE_CIAA_8259X
+#define IXGBE_CIAA_X550		0x11508
+#define IXGBE_CIAA_X550EM_x	IXGBE_CIAA_X550
+#define IXGBE_CIAA_X550EM_a	IXGBE_CIAA_X550
+#define IXGBE_CIAA(_hw)		IXGBE_BY_MAC((_hw), CIAA)
+
+#define IXGBE_CIAD_8259X	0x1108C
+#define IXGBE_CIAD_X540		IXGBE_CIAD_8259X
+#define IXGBE_CIAD_X550		0x11510
+#define IXGBE_CIAD_X550EM_x	IXGBE_CIAD_X550
+#define IXGBE_CIAD_X550EM_a	IXGBE_CIAD_X550
+#define IXGBE_CIAD(_hw)		IXGBE_BY_MAC((_hw), CIAD)
+
 #define IXGBE_PICAUSE           0x110B0
 #define IXGBE_PIENA             0x110B8
 #define IXGBE_CDQ_MBR_82599     0x110B4
@@ -1204,18 +1305,37 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_MDIO_AUTO_NEG_CONTROL	0x0 /* AUTO_NEG Control Reg */
 #define IXGBE_MDIO_AUTO_NEG_STATUS	0x1 /* AUTO_NEG Status Reg */
 #define IXGBE_MDIO_AUTO_NEG_VENDOR_STAT	0xC800 /* AUTO_NEG Vendor Status Reg */
+#define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2 0xCC01 /* AUTO_NEG Vendor Tx Reg */
+#define IXGBE_MDIO_AUTO_NEG_VEN_LSC	0x1 /* AUTO_NEG Vendor Tx LSC */
 #define IXGBE_MDIO_AUTO_NEG_ADVT	0x10 /* AUTO_NEG Advt Reg */
 #define IXGBE_MDIO_AUTO_NEG_LP		0x13 /* AUTO_NEG LP Status Reg */
 #define IXGBE_MDIO_AUTO_NEG_EEE_ADVT	0x3C /* AUTO_NEG EEE Advt Reg */
 
+#define IXGBE_MDIO_PHY_SET_LOW_POWER_MODE	 0x0800 /* Set low power mode */
+
 #define IXGBE_MDIO_TX_VENDOR_ALARMS_3	0xCC02 /* Vendor Alarms 3 Reg */
 #define IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK 0x3 /* PHY Reset Complete Mask */
 #define IXGBE_MDIO_GLOBAL_RES_PR_10 0xC479 /* Global Resv Provisioning 10 Reg */
 #define IXGBE_MDIO_POWER_UP_STALL	0x8000 /* Power Up Stall */
+#define IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK	0xFF00 /* int std mask */
+#define IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG	0xFC00 /* chip std int flag */
+#define IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK	0xFF01 /* int chip-wide mask */
+#define IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG	0xFC01 /* int chip-wide mask */
+#define IXGBE_MDIO_GLOBAL_ALARM_1		0xCC00 /* Global alarm 1 */
+#define IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL	0x4000 /* high temp failure */
+#define IXGBE_MDIO_GLOBAL_INT_MASK		0xD400 /* Global int mask */
+/* autoneg vendor alarm int enable */
+#define IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN	0x1000
+#define IXGBE_MDIO_GLOBAL_ALARM_1_INT		0x4 /* int in Global alarm 1 */
+#define IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN	0x1 /* vendor alarm int enable */
+#define IXGBE_MDIO_GLOBAL_STD_ALM2_INT		0x200 /* vendor alarm2 int mask */
+#define IXGBE_MDIO_GLOBAL_INT_HI_TEMP_EN	0x4000 /* int high temp enable */
 
 #define IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR	0xC30A /* PHY_XS SDA/SCL Addr Reg */
 #define IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA	0xC30B /* PHY_XS SDA/SCL Data Reg */
 #define IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT	0xC30C /* PHY_XS SDA/SCL Stat Reg */
+#define IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK	0xD401 /* PHY TX Vendor LASI */
+#define IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN	0x1 /* PHY TX Vendor LASI enable */
 #define IXGBE_MDIO_PMD_STD_TX_DISABLE_CNTR	0x9 /* Standard Tx Dis Reg */
 #define IXGBE_MDIO_PMD_GLOBAL_TX_DISABLE	0x0001 /* PMD Global Tx Dis */
 
@@ -1233,6 +1353,8 @@ struct ixgbe_thermal_sensor_data {
 #define TN1010_PHY_ID    0x00A19410
 #define TNX_FW_REV       0xB
 #define X540_PHY_ID      0x01540200
+#define X550_PHY_ID      0x01540220
+#define X557_PHY_ID      0x01540240
 #define QT2022_PHY_ID    0x0043A400
 #define ATH_PHY_ID       0x03429050
 #define AQ_FW_REV        0x20
@@ -1253,9 +1375,25 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_CONTROL_SOL_NL     0x0000
 
 /* General purpose Interrupt Enable */
-#define IXGBE_SDP0_GPIEN         0x00000001 /* SDP0 */
-#define IXGBE_SDP1_GPIEN         0x00000002 /* SDP1 */
-#define IXGBE_SDP2_GPIEN         0x00000004 /* SDP2 */
+#define IXGBE_SDP0_GPIEN_8259X		0x00000001 /* SDP0 */
+#define IXGBE_SDP1_GPIEN_8259X		0x00000002 /* SDP1 */
+#define IXGBE_SDP2_GPIEN_8259X		0x00000004 /* SDP2 */
+#define IXGBE_SDP0_GPIEN_X540		0x00000002 /* SDP0 on X540 and X550 */
+#define IXGBE_SDP1_GPIEN_X540		0x00000004 /* SDP1 on X540 and X550 */
+#define IXGBE_SDP2_GPIEN_X540		0x00000008 /* SDP2 on X540 and X550 */
+#define IXGBE_SDP0_GPIEN_X550		IXGBE_SDP0_GPIEN_X540
+#define IXGBE_SDP1_GPIEN_X550		IXGBE_SDP1_GPIEN_X540
+#define IXGBE_SDP2_GPIEN_X550		IXGBE_SDP2_GPIEN_X540
+#define IXGBE_SDP0_GPIEN_X550EM_x	IXGBE_SDP0_GPIEN_X540
+#define IXGBE_SDP1_GPIEN_X550EM_x	IXGBE_SDP1_GPIEN_X540
+#define IXGBE_SDP2_GPIEN_X550EM_x	IXGBE_SDP2_GPIEN_X540
+#define IXGBE_SDP0_GPIEN_X550EM_a	IXGBE_SDP0_GPIEN_X540
+#define IXGBE_SDP1_GPIEN_X550EM_a	IXGBE_SDP1_GPIEN_X540
+#define IXGBE_SDP2_GPIEN_X550EM_a	IXGBE_SDP2_GPIEN_X540
+#define IXGBE_SDP0_GPIEN(_hw)		IXGBE_BY_MAC((_hw), SDP0_GPIEN)
+#define IXGBE_SDP1_GPIEN(_hw)		IXGBE_BY_MAC((_hw), SDP1_GPIEN)
+#define IXGBE_SDP2_GPIEN(_hw)		IXGBE_BY_MAC((_hw), SDP2_GPIEN)
+
 #define IXGBE_GPIE_MSIX_MODE     0x00000010 /* MSI-X mode */
 #define IXGBE_GPIE_OCD           0x00000020 /* Other Clear Disable */
 #define IXGBE_GPIE_EIMEN         0x00000040 /* Immediate Interrupt Enable */
@@ -1417,9 +1555,25 @@ enum {
 #define IXGBE_EICR_MNG          0x00400000 /* Manageability Event Interrupt */
 #define IXGBE_EICR_TS           0x00800000 /* Thermal Sensor Event */
 #define IXGBE_EICR_TIMESYNC     0x01000000 /* Timesync Event */
-#define IXGBE_EICR_GPI_SDP0     0x01000000 /* Gen Purpose Interrupt on SDP0 */
-#define IXGBE_EICR_GPI_SDP1     0x02000000 /* Gen Purpose Interrupt on SDP1 */
-#define IXGBE_EICR_GPI_SDP2     0x04000000 /* Gen Purpose Interrupt on SDP2 */
+#define IXGBE_EICR_GPI_SDP0_8259X	0x01000000 /* Gen Purpose INT on SDP0 */
+#define IXGBE_EICR_GPI_SDP1_8259X	0x02000000 /* Gen Purpose INT on SDP1 */
+#define IXGBE_EICR_GPI_SDP2_8259X	0x04000000 /* Gen Purpose INT on SDP2 */
+#define IXGBE_EICR_GPI_SDP0_X540	0x02000000
+#define IXGBE_EICR_GPI_SDP1_X540	0x04000000
+#define IXGBE_EICR_GPI_SDP2_X540	0x08000000
+#define IXGBE_EICR_GPI_SDP0_X550	IXGBE_EICR_GPI_SDP0_X540
+#define IXGBE_EICR_GPI_SDP1_X550	IXGBE_EICR_GPI_SDP1_X540
+#define IXGBE_EICR_GPI_SDP2_X550	IXGBE_EICR_GPI_SDP2_X540
+#define IXGBE_EICR_GPI_SDP0_X550EM_x	IXGBE_EICR_GPI_SDP0_X540
+#define IXGBE_EICR_GPI_SDP1_X550EM_x	IXGBE_EICR_GPI_SDP1_X540
+#define IXGBE_EICR_GPI_SDP2_X550EM_x	IXGBE_EICR_GPI_SDP2_X540
+#define IXGBE_EICR_GPI_SDP0_X550EM_a	IXGBE_EICR_GPI_SDP0_X540
+#define IXGBE_EICR_GPI_SDP1_X550EM_a	IXGBE_EICR_GPI_SDP1_X540
+#define IXGBE_EICR_GPI_SDP2_X550EM_a	IXGBE_EICR_GPI_SDP2_X540
+#define IXGBE_EICR_GPI_SDP0(_hw)	IXGBE_BY_MAC((_hw), EICR_GPI_SDP0)
+#define IXGBE_EICR_GPI_SDP1(_hw)	IXGBE_BY_MAC((_hw), EICR_GPI_SDP1)
+#define IXGBE_EICR_GPI_SDP2(_hw)	IXGBE_BY_MAC((_hw), EICR_GPI_SDP2)
+
 #define IXGBE_EICR_ECC          0x10000000 /* ECC Error */
 #define IXGBE_EICR_PBUR         0x10000000 /* Packet Buffer Handler Error */
 #define IXGBE_EICR_DHER         0x20000000 /* Descriptor Handler Error */
@@ -1435,9 +1589,9 @@ enum {
 #define IXGBE_EICS_LSC          IXGBE_EICR_LSC       /* Link Status Change */
 #define IXGBE_EICS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EICS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
-#define IXGBE_EICS_GPI_SDP0     IXGBE_EICR_GPI_SDP0  /* SDP0 Gen Purpose Int */
-#define IXGBE_EICS_GPI_SDP1     IXGBE_EICR_GPI_SDP1  /* SDP1 Gen Purpose Int */
-#define IXGBE_EICS_GPI_SDP2     IXGBE_EICR_GPI_SDP2  /* SDP2 Gen Purpose Int */
+#define IXGBE_EICS_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
+#define IXGBE_EICS_GPI_SDP1(_hw)	IXGBE_EICR_GPI_SDP1(_hw)
+#define IXGBE_EICS_GPI_SDP2(_hw)	IXGBE_EICR_GPI_SDP2(_hw)
 #define IXGBE_EICS_ECC          IXGBE_EICR_ECC       /* ECC Error */
 #define IXGBE_EICS_PBUR         IXGBE_EICR_PBUR      /* Pkt Buf Handler Err */
 #define IXGBE_EICS_DHER         IXGBE_EICR_DHER      /* Desc Handler Error */
@@ -1454,9 +1608,9 @@ enum {
 #define IXGBE_EIMS_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMS_TS           IXGBE_EICR_TS        /* Thermel Sensor Event */
 #define IXGBE_EIMS_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
-#define IXGBE_EIMS_GPI_SDP0     IXGBE_EICR_GPI_SDP0  /* SDP0 Gen Purpose Int */
-#define IXGBE_EIMS_GPI_SDP1     IXGBE_EICR_GPI_SDP1  /* SDP1 Gen Purpose Int */
-#define IXGBE_EIMS_GPI_SDP2     IXGBE_EICR_GPI_SDP2  /* SDP2 Gen Purpose Int */
+#define IXGBE_EIMS_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
+#define IXGBE_EIMS_GPI_SDP1(_hw)	IXGBE_EICR_GPI_SDP1(_hw)
+#define IXGBE_EIMS_GPI_SDP2(_hw)	IXGBE_EICR_GPI_SDP2(_hw)
 #define IXGBE_EIMS_ECC          IXGBE_EICR_ECC       /* ECC Error */
 #define IXGBE_EIMS_PBUR         IXGBE_EICR_PBUR      /* Pkt Buf Handler Err */
 #define IXGBE_EIMS_DHER         IXGBE_EICR_DHER      /* Descr Handler Error */
@@ -1472,9 +1626,9 @@ enum {
 #define IXGBE_EIMC_LSC          IXGBE_EICR_LSC       /* Link Status Change */
 #define IXGBE_EIMC_MNG          IXGBE_EICR_MNG       /* MNG Event Interrupt */
 #define IXGBE_EIMC_TIMESYNC     IXGBE_EICR_TIMESYNC  /* Timesync Event */
-#define IXGBE_EIMC_GPI_SDP0     IXGBE_EICR_GPI_SDP0  /* SDP0 Gen Purpose Int */
-#define IXGBE_EIMC_GPI_SDP1     IXGBE_EICR_GPI_SDP1  /* SDP1 Gen Purpose Int */
-#define IXGBE_EIMC_GPI_SDP2     IXGBE_EICR_GPI_SDP2  /* SDP2 Gen Purpose Int */
+#define IXGBE_EIMC_GPI_SDP0(_hw)	IXGBE_EICR_GPI_SDP0(_hw)
+#define IXGBE_EIMC_GPI_SDP1(_hw)	IXGBE_EICR_GPI_SDP1(_hw)
+#define IXGBE_EIMC_GPI_SDP2(_hw)	IXGBE_EICR_GPI_SDP2(_hw)
 #define IXGBE_EIMC_ECC          IXGBE_EICR_ECC       /* ECC Error */
 #define IXGBE_EIMC_PBUR         IXGBE_EICR_PBUR      /* Pkt Buf Handler Err */
 #define IXGBE_EIMC_DHER         IXGBE_EICR_DHER      /* Desc Handler Err */
@@ -2741,6 +2895,37 @@ union ixgbe_atr_hash_dword {
 	__be32 dword;
 };
 
+#define IXGBE_MVALS_INIT(m)		\
+	IXGBE_CAT(EEC, m),		\
+	IXGBE_CAT(FLA, m),		\
+	IXGBE_CAT(GRC, m),		\
+	IXGBE_CAT(SRAMREL, m),		\
+	IXGBE_CAT(FACTPS, m),		\
+	IXGBE_CAT(SWSM, m),		\
+	IXGBE_CAT(SWFW_SYNC, m),	\
+	IXGBE_CAT(FWSM, m),		\
+	IXGBE_CAT(SDP0_GPIEN, m),	\
+	IXGBE_CAT(SDP1_GPIEN, m),	\
+	IXGBE_CAT(SDP2_GPIEN, m),	\
+	IXGBE_CAT(EICR_GPI_SDP0, m),	\
+	IXGBE_CAT(EICR_GPI_SDP1, m),	\
+	IXGBE_CAT(EICR_GPI_SDP2, m),	\
+	IXGBE_CAT(CIAA, m),		\
+	IXGBE_CAT(CIAD, m),		\
+	IXGBE_CAT(I2C_CLK_IN, m),	\
+	IXGBE_CAT(I2C_CLK_OUT, m),	\
+	IXGBE_CAT(I2C_DATA_IN, m),	\
+	IXGBE_CAT(I2C_DATA_OUT, m),	\
+	IXGBE_CAT(I2C_DATA_OE_N_EN, m),	\
+	IXGBE_CAT(I2C_BB_EN, m),	\
+	IXGBE_CAT(I2C_CLK_OE_N_EN, m),	\
+	IXGBE_CAT(I2CCTL, m)
+
+enum ixgbe_mvals {
+	IXGBE_MVALS_INIT(IDX),
+	IXGBE_MVALS_IDX_LIMIT
+};
+
 enum ixgbe_eeprom_type {
 	ixgbe_eeprom_uninitialized = 0,
 	ixgbe_eeprom_spi,
@@ -3112,6 +3297,8 @@ struct ixgbe_phy_operations {
 	s32 (*read_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val);
 	s32 (*write_i2c_combined)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val);
 	s32 (*check_overtemp)(struct ixgbe_hw *);
+	s32 (*set_phy_power)(struct ixgbe_hw *, bool on);
+	s32 (*handle_lasi)(struct ixgbe_hw *hw);
 };
 
 struct ixgbe_eeprom_info {
@@ -3173,6 +3360,7 @@ struct ixgbe_phy_info {
 	bool                            multispeed_fiber;
 	bool                            reset_if_overtemp;
 	bool                            qsfp_shared_i2c_bus;
+	u32				nw_mng_if_sel;
 };
 
 #include "ixgbe_mbx.h"
@@ -3216,6 +3404,7 @@ struct ixgbe_hw {
 	struct ixgbe_eeprom_info	eeprom;
 	struct ixgbe_bus_info		bus;
 	struct ixgbe_mbx_info		mbx;
+	const u32			*mvals;
 	u16				device_id;
 	u16				vendor_id;
 	u16				subsystem_device_id;
@@ -3234,6 +3423,7 @@ struct ixgbe_info {
 	struct ixgbe_eeprom_operations	*eeprom_ops;
 	struct ixgbe_phy_operations	*phy_ops;
 	struct ixgbe_mbx_operations	*mbx_ops;
+	const u32			*mvals;
 };
 
 
@@ -3339,4 +3529,6 @@ struct ixgbe_info {
 #define IXGBE_SB_IOSF_TARGET_KX4_PCS0	2
 #define IXGBE_SB_IOSF_TARGET_KX4_PCS1	3
 
+#define IXGBE_NW_MNG_IF_SEL		0x00011178
+#define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE	BIT(24)
 #endif /* _IXGBE_TYPE_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index f5f948d08b43..032a5870abd1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -202,7 +202,7 @@ s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw)
 		eeprom->semaphore_delay = 10;
 		eeprom->type = ixgbe_flash;
 
-		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 		eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
 				    IXGBE_EEC_SIZE_SHIFT);
 		eeprom->word_size = 1 << (eeprom_size +
@@ -504,8 +504,8 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw)
 		return status;
 	}
 
-	flup = IXGBE_READ_REG(hw, IXGBE_EEC) | IXGBE_EEC_FLUP;
-	IXGBE_WRITE_REG(hw, IXGBE_EEC, flup);
+	flup = IXGBE_READ_REG(hw, IXGBE_EEC(hw)) | IXGBE_EEC_FLUP;
+	IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), flup);
 
 	status = ixgbe_poll_flash_update_done_X540(hw);
 	if (status == 0)
@@ -514,11 +514,11 @@ static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw)
 		hw_dbg(hw, "Flash update time out\n");
 
 	if (hw->revision_id == 0) {
-		flup = IXGBE_READ_REG(hw, IXGBE_EEC);
+		flup = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 
 		if (flup & IXGBE_EEC_SEC1VAL) {
 			flup |= IXGBE_EEC_FLUP;
-			IXGBE_WRITE_REG(hw, IXGBE_EEC, flup);
+			IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), flup);
 		}
 
 		status = ixgbe_poll_flash_update_done_X540(hw);
@@ -544,7 +544,7 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw)
 	u32 reg;
 
 	for (i = 0; i < IXGBE_FLUDONE_ATTEMPTS; i++) {
-		reg = IXGBE_READ_REG(hw, IXGBE_EEC);
+		reg = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 		if (reg & IXGBE_EEC_FLUDONE)
 			return 0;
 		udelay(5);
@@ -580,10 +580,10 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 		if (ixgbe_get_swfw_sync_semaphore(hw))
 			return IXGBE_ERR_SWFW_SYNC;
 
-		swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+		swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 		if (!(swfw_sync & (fwmask | swmask | hwmask))) {
 			swfw_sync |= swmask;
-			IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+			IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync);
 			ixgbe_release_swfw_sync_semaphore(hw);
 			break;
 		} else {
@@ -605,13 +605,13 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 	 * corresponding FW/HW bits in the SW_FW_SYNC register.
 	 */
 	if (i >= timeout) {
-		swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+		swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 		if (swfw_sync & (fwmask | hwmask)) {
 			if (ixgbe_get_swfw_sync_semaphore(hw))
 				return IXGBE_ERR_SWFW_SYNC;
 
 			swfw_sync |= swmask;
-			IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+			IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync);
 			ixgbe_release_swfw_sync_semaphore(hw);
 		}
 	}
@@ -635,9 +635,9 @@ void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask)
 
 	ixgbe_get_swfw_sync_semaphore(hw);
 
-	swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+	swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 	swfw_sync &= ~swmask;
-	IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swfw_sync);
+	IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync);
 
 	ixgbe_release_swfw_sync_semaphore(hw);
 	usleep_range(5000, 10000);
@@ -660,7 +660,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
 		/* If the SMBI bit is 0 when we read it, then the bit will be
 		 * set and we have the semaphore
 		 */
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
 		if (!(swsm & IXGBE_SWSM_SMBI))
 			break;
 		usleep_range(50, 100);
@@ -674,7 +674,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
 
 	/* Now get the semaphore between SW/FW through the REGSMP bit */
 	for (i = 0; i < timeout; i++) {
-		swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+		swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 		if (!(swsm & IXGBE_SWFW_REGSMP))
 			return 0;
 
@@ -696,13 +696,13 @@ static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw)
 
 	/* Release both semaphores by writing 0 to the bits REGSMP and SMBI */
 
-	swsm = IXGBE_READ_REG(hw, IXGBE_SWSM);
-	swsm &= ~IXGBE_SWSM_SMBI;
-	IXGBE_WRITE_REG(hw, IXGBE_SWSM, swsm);
-
-	swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC);
+	swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw));
 	swsm &= ~IXGBE_SWFW_REGSMP;
-	IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC, swsm);
+	IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swsm);
+
+	swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw));
+	swsm &= ~IXGBE_SWSM_SMBI;
+	IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm);
 
 	IXGBE_WRITE_FLUSH(hw);
 }
@@ -850,9 +850,14 @@ static struct ixgbe_phy_operations phy_ops_X540 = {
 	.read_i2c_eeprom        = &ixgbe_read_i2c_eeprom_generic,
 	.write_i2c_eeprom       = &ixgbe_write_i2c_eeprom_generic,
 	.check_overtemp         = &ixgbe_tn_check_overtemp,
+	.set_phy_power          = &ixgbe_set_copper_phy_power,
 	.get_firmware_version   = &ixgbe_get_phy_firmware_version_generic,
 };
 
+static const u32 ixgbe_mvals_X540[IXGBE_MVALS_IDX_LIMIT] = {
+	IXGBE_MVALS_INIT(X540)
+};
+
 struct ixgbe_info ixgbe_X540_info = {
 	.mac                    = ixgbe_mac_X540,
 	.get_invariants         = &ixgbe_get_invariants_X540,
@@ -860,4 +865,5 @@ struct ixgbe_info ixgbe_X540_info = {
 	.eeprom_ops             = &eeprom_ops_X540,
 	.phy_ops                = &phy_ops_X540,
 	.mbx_ops                = &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_X540,
 };
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index cf5cf819a6b8..7581da13e92a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  *  Intel 10 Gigabit PCI Express Linux driver
- *  Copyright(c) 1999 - 2014 Intel Corporation.
+ *  Copyright(c) 1999 - 2015 Intel Corporation.
  *
  *  This program is free software; you can redistribute it and/or modify it
  *  under the terms and conditions of the GNU General Public License,
@@ -26,6 +26,22 @@
 #include "ixgbe_common.h"
 #include "ixgbe_phy.h"
 
+/** ixgbe_setup_mux_ctl - Setup ESDP register for I2C mux control
+ *  @hw: pointer to hardware structure
+ **/
+static void ixgbe_setup_mux_ctl(struct ixgbe_hw *hw)
+{
+	u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
+
+	if (hw->bus.lan_id) {
+		esdp &= ~(IXGBE_ESDP_SDP1_NATIVE | IXGBE_ESDP_SDP1);
+		esdp |= IXGBE_ESDP_SDP1_DIR;
+	}
+	esdp &= ~(IXGBE_ESDP_SDP0_NATIVE | IXGBE_ESDP_SDP0_DIR);
+	IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp);
+	IXGBE_WRITE_FLUSH(hw);
+}
+
 /** ixgbe_identify_phy_x550em - Get PHY type based on device id
  *  @hw: pointer to hardware structure
  *
@@ -33,18 +49,11 @@
  */
 static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw)
 {
-	u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
-
 	switch (hw->device_id) {
 	case IXGBE_DEV_ID_X550EM_X_SFP:
 		/* set up for CS4227 usage */
 		hw->phy.phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM;
-		if (hw->bus.lan_id) {
-			esdp &= ~(IXGBE_ESDP_SDP1_NATIVE | IXGBE_ESDP_SDP1);
-			esdp |= IXGBE_ESDP_SDP1_DIR;
-		}
-		esdp &= ~(IXGBE_ESDP_SDP0_NATIVE | IXGBE_ESDP_SDP0_DIR);
-		IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp);
+		ixgbe_setup_mux_ctl(hw);
 
 		return ixgbe_identify_module_generic(hw);
 	case IXGBE_DEV_ID_X550EM_X_KX4:
@@ -90,7 +99,7 @@ static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw)
 		eeprom->semaphore_delay = 10;
 		eeprom->type = ixgbe_flash;
 
-		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
+		eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw));
 		eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
 				    IXGBE_EEC_SIZE_SHIFT);
 		eeprom->word_size = 1 << (eeprom_size +
@@ -103,6 +112,39 @@ static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw)
 	return 0;
 }
 
+/**
+ * ixgbe_iosf_wait - Wait for IOSF command completion
+ * @hw: pointer to hardware structure
+ * @ctrl: pointer to location to receive final IOSF control value
+ *
+ * Return: failing status on timeout
+ *
+ * Note: ctrl can be NULL if the IOSF control register value is not needed
+ */
+static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl)
+{
+	u32 i, command;
+
+	/* Check every 10 usec to see if the address cycle completed.
+	 * The SB IOSF BUSY bit will clear when the operation is
+	 * complete.
+	 */
+	for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) {
+		command = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL);
+		if (!(command & IXGBE_SB_IOSF_CTRL_BUSY))
+			break;
+		usleep_range(10, 20);
+	}
+	if (ctrl)
+		*ctrl = command;
+	if (i == IXGBE_MDIO_COMMAND_TIMEOUT) {
+		hw_dbg(hw, "IOSF wait timed out\n");
+		return IXGBE_ERR_PHY;
+	}
+
+	return 0;
+}
+
 /** ixgbe_read_iosf_sb_reg_x550 - Writes a value to specified register of the
  *  IOSF device
  *  @hw: pointer to hardware structure
@@ -113,7 +155,17 @@ static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw)
 static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 				       u32 device_type, u32 *data)
 {
-	u32 i, command, error;
+	u32 gssr = IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_PHY0_SM;
+	u32 command, error;
+	s32 ret;
+
+	ret = hw->mac.ops.acquire_swfw_sync(hw, gssr);
+	if (ret)
+		return ret;
+
+	ret = ixgbe_iosf_wait(hw, NULL);
+	if (ret)
+		goto out;
 
 	command = ((reg_addr << IXGBE_SB_IOSF_CTRL_ADDR_SHIFT) |
 		   (device_type << IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT));
@@ -121,17 +173,7 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	/* Write IOSF control register */
 	IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL, command);
 
-	/* Check every 10 usec to see if the address cycle completed.
-	 * The SB IOSF BUSY bit will clear when the operation is
-	 * complete
-	 */
-	for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) {
-		usleep_range(10, 20);
-
-		command = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL);
-		if ((command & IXGBE_SB_IOSF_CTRL_BUSY) == 0)
-			break;
-	}
+	ret = ixgbe_iosf_wait(hw, &command);
 
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
 		error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >>
@@ -140,14 +182,12 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 		return IXGBE_ERR_PHY;
 	}
 
-	if (i == IXGBE_MDIO_COMMAND_TIMEOUT) {
-		hw_dbg(hw, "Read timed out\n");
-		return IXGBE_ERR_PHY;
-	}
-
-	*data = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA);
+	if (!ret)
+		*data = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA);
 
-	return 0;
+out:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return ret;
 }
 
 /** ixgbe_read_ee_hostif_data_X550 - Read EEPROM word using a host interface
@@ -673,6 +713,249 @@ static s32 ixgbe_write_ee_hostif_buffer_X550(struct ixgbe_hw *hw,
 	return status;
 }
 
+/** ixgbe_write_iosf_sb_reg_x550 - Writes a value to specified register of the
+ *  IOSF device
+ *
+ *  @hw: pointer to hardware structure
+ *  @reg_addr: 32 bit PHY register to write
+ *  @device_type: 3 bit device type
+ *  @data: Data to write to the register
+ **/
+static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
+					u32 device_type, u32 data)
+{
+	u32 gssr = IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_PHY0_SM;
+	u32 command, error;
+	s32 ret;
+
+	ret = hw->mac.ops.acquire_swfw_sync(hw, gssr);
+	if (ret)
+		return ret;
+
+	ret = ixgbe_iosf_wait(hw, NULL);
+	if (ret)
+		goto out;
+
+	command = ((reg_addr << IXGBE_SB_IOSF_CTRL_ADDR_SHIFT) |
+		   (device_type << IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT));
+
+	/* Write IOSF control register */
+	IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL, command);
+
+	/* Write IOSF data register */
+	IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA, data);
+
+	ret = ixgbe_iosf_wait(hw, &command);
+
+	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
+		error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >>
+			 IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT;
+		hw_dbg(hw, "Failed to write, error %x\n", error);
+		return IXGBE_ERR_PHY;
+	}
+
+out:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return ret;
+}
+
+/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode.
+ *  @hw: pointer to hardware structure
+ *  @speed: the link speed to force
+ *
+ *  Configures the integrated KR PHY to use iXFI mode. Used to connect an
+ *  internal and external PHY at a specific speed, without autonegotiation.
+ **/
+static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
+{
+	s32 status;
+	u32 reg_val;
+
+	/* Disable AN and force speed to 10G Serial. */
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+					IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
+	reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK;
+
+	/* Select forced link speed for internal PHY. */
+	switch (*speed) {
+	case IXGBE_LINK_SPEED_10GB_FULL:
+		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G;
+		break;
+	case IXGBE_LINK_SPEED_1GB_FULL:
+		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G;
+		break;
+	default:
+		/* Other link speeds are not supported by internal KR PHY. */
+		return IXGBE_ERR_LINK_SETUP;
+	}
+
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	if (status)
+		return status;
+
+	/* Disable training protocol FSM. */
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val |= IXGBE_KRM_RX_TRN_LINKUP_CTRL_CONV_WO_PROTOCOL;
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	if (status)
+		return status;
+
+	/* Disable Flex from training TXFFE. */
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN;
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN;
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN;
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	if (status)
+		return status;
+
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN;
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN;
+	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN;
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	if (status)
+		return status;
+
+	/* Enable override for coefficients. */
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN;
+	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN;
+	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CPLUS1_OVRRD_EN;
+	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CMINUS1_OVRRD_EN;
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	if (status)
+		return status;
+
+	/* Toggle port SW reset by AN reset. */
+	status = ixgbe_read_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	if (status)
+		return status;
+
+	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
+	status = ixgbe_write_iosf_sb_reg_x550(hw,
+				IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+
+	return status;
+}
+
+/**
+ * ixgbe_setup_mac_link_t_X550em - Sets the auto advertised link speed
+ * @hw: pointer to hardware structure
+ * @speed: new link speed
+ * @autoneg_wait_to_complete: true when waiting for completion is needed
+ *
+ * Setup internal/external PHY link speed based on link speed, then set
+ * external PHY auto advertised link speed.
+ *
+ * Returns error status for any failure
+ **/
+static s32 ixgbe_setup_mac_link_t_X550em(struct ixgbe_hw *hw,
+					 ixgbe_link_speed speed,
+					 bool autoneg_wait)
+{
+	s32 status;
+	ixgbe_link_speed force_speed;
+
+	/* Setup internal/external PHY link speed to iXFI (10G), unless
+	 * only 1G is auto advertised then setup KX link.
+	 */
+	if (speed & IXGBE_LINK_SPEED_10GB_FULL)
+		force_speed = IXGBE_LINK_SPEED_10GB_FULL;
+	else
+		force_speed = IXGBE_LINK_SPEED_1GB_FULL;
+
+	/* If internal link mode is XFI, then setup XFI internal link. */
+	if (!(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) {
+		status = ixgbe_setup_ixfi_x550em(hw, &force_speed);
+
+		if (status)
+			return status;
+	}
+
+	return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait);
+}
+
+/** ixgbe_check_link_t_X550em - Determine link and speed status
+  * @hw: pointer to hardware structure
+  * @speed: pointer to link speed
+  * @link_up: true when link is up
+  * @link_up_wait_to_complete: bool used to wait for link up or not
+  *
+  * Check that both the MAC and X557 external PHY have link.
+  **/
+static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw,
+				     ixgbe_link_speed *speed,
+				     bool *link_up,
+				     bool link_up_wait_to_complete)
+{
+	u32 status;
+	u16 autoneg_status;
+
+	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
+		return IXGBE_ERR_CONFIG;
+
+	status = ixgbe_check_mac_link_generic(hw, speed, link_up,
+					      link_up_wait_to_complete);
+
+	/* If check link fails or MAC link is not up, then return */
+	if (status || !(*link_up))
+		return status;
+
+	 /* MAC link is up, so check external PHY link.
+	  * Read this twice back to back to indicate current status.
+	  */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
+				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+				      &autoneg_status);
+	if (status)
+		return status;
+
+	/* If external PHY link is not up, then indicate link not up */
+	if (!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS))
+		*link_up = false;
+
+	return 0;
+}
+
 /** ixgbe_init_mac_link_ops_X550em - init mac link function pointers
  *  @hw: pointer to hardware structure
  **/
@@ -680,13 +963,21 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw)
 {
 	struct ixgbe_mac_info *mac = &hw->mac;
 
-	/* CS4227 does not support autoneg, so disable the laser control
-	 * functions for SFP+ fiber
-	 */
-	if (hw->device_id == IXGBE_DEV_ID_X550EM_X_SFP) {
+	switch (mac->ops.get_media_type(hw)) {
+	case ixgbe_media_type_fiber:
+		/* CS4227 does not support autoneg, so disable the laser control
+		 * functions for SFP+ fiber
+		 */
 		mac->ops.disable_tx_laser = NULL;
 		mac->ops.enable_tx_laser = NULL;
 		mac->ops.flap_tx_laser = NULL;
+		break;
+	case ixgbe_media_type_copper:
+		mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em;
+		mac->ops.check_link = ixgbe_check_link_t_X550em;
+		break;
+	default:
+		break;
 	}
 }
 
@@ -778,169 +1069,221 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw,
 	return 0;
 }
 
-/** ixgbe_write_iosf_sb_reg_x550 - Writes a value to specified register of the
- *  IOSF device
+/**
+ * ixgbe_get_lasi_ext_t_x550em - Determime external Base T PHY interrupt cause
+ * @hw: pointer to hardware structure
+ * @lsc: pointer to boolean flag which indicates whether external Base T
+ *	 PHY interrupt is lsc
  *
- *  @hw: pointer to hardware structure
- *  @reg_addr: 32 bit PHY register to write
- *  @device_type: 3 bit device type
- *  @data: Data to write to the register
+ * Determime if external Base T PHY interrupt cause is high temperature
+ * failure alarm or link status change.
+ *
+ * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature
+ * failure alarm, else return PHY access status.
  **/
-static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
-					u32 device_type, u32 data)
+static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc)
 {
-	u32 i, command, error;
+	u32 status;
+	u16 reg;
 
-	command = ((reg_addr << IXGBE_SB_IOSF_CTRL_ADDR_SHIFT) |
-		   (device_type << IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT));
+	*lsc = false;
 
-	/* Write IOSF control register */
-	IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL, command);
+	/* Vendor alarm triggered */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 
-	/* Write IOSF data register */
-	IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA, data);
+	if (status || !(reg & IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN))
+		return status;
 
-	/* Check every 10 usec to see if the address cycle completed.
-	 * The SB IOSF BUSY bit will clear when the operation is
-	 * complete
-	 */
-	for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) {
-		usleep_range(10, 20);
+	/* Vendor Auto-Neg alarm triggered or Global alarm 1 triggered */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 
-		command = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL);
-		if ((command & IXGBE_SB_IOSF_CTRL_BUSY) == 0)
-			break;
-	}
+	if (status || !(reg & (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN |
+				IXGBE_MDIO_GLOBAL_ALARM_1_INT)))
+		return status;
 
-	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
-		error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >>
-			 IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT;
-		hw_dbg(hw, "Failed to write, error %x\n", error);
-		return IXGBE_ERR_PHY;
-	}
+	/* High temperature failure alarm triggered */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_ALARM_1,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 
-	if (i == IXGBE_MDIO_COMMAND_TIMEOUT) {
-		hw_dbg(hw, "Write timed out\n");
-		return IXGBE_ERR_PHY;
+	if (status)
+		return status;
+
+	/* If high temperature failure, then return over temp error and exit */
+	if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) {
+		/* power down the PHY in case the PHY FW didn't already */
+		ixgbe_set_copper_phy_power(hw, false);
+		return IXGBE_ERR_OVERTEMP;
 	}
 
+	/* Vendor alarm 2 triggered */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG,
+				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE, &reg);
+
+	if (status || !(reg & IXGBE_MDIO_GLOBAL_STD_ALM2_INT))
+		return status;
+
+	/* link connect/disconnect event occurred */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2,
+				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE, &reg);
+
+	if (status)
+		return status;
+
+	/* Indicate LSC */
+	if (reg & IXGBE_MDIO_AUTO_NEG_VEN_LSC)
+		*lsc = true;
+
 	return 0;
 }
 
-/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode.
- *  @hw: pointer to hardware structure
- *  @speed: the link speed to force
+/**
+ * ixgbe_enable_lasi_ext_t_x550em - Enable external Base T PHY interrupts
+ * @hw: pointer to hardware structure
  *
- *  Configures the integrated KR PHY to use iXFI mode. Used to connect an
- *  internal and external PHY at a specific speed, without autonegotiation.
+ * Enable link status change and temperature failure alarm for the external
+ * Base T PHY
+ *
+ * Returns PHY access status
  **/
-static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed)
+static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw)
 {
-	s32 status;
-	u32 reg_val;
+	u32 status;
+	u16 reg;
+	bool lsc;
 
-	/* Disable AN and force speed to 10G Serial. */
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-					IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	/* Clear interrupt flags */
+	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc);
+
+	/* Enable link status change alarm */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK,
+				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE, &reg);
 	if (status)
 		return status;
 
-	reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
-	reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK;
+	reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN;
 
-	/* Select forced link speed for internal PHY. */
-	switch (*speed) {
-	case IXGBE_LINK_SPEED_10GB_FULL:
-		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G;
-		break;
-	case IXGBE_LINK_SPEED_1GB_FULL:
-		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G;
-		break;
-	default:
-		/* Other link speeds are not supported by internal KR PHY. */
-		return IXGBE_ERR_LINK_SETUP;
-	}
-
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK,
+				       IXGBE_MDIO_AUTO_NEG_DEV_TYPE, reg);
 	if (status)
 		return status;
 
-	/* Disable training protocol FSM. */
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	/* Enables high temperature failure alarm */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 	if (status)
 		return status;
 
-	reg_val |= IXGBE_KRM_RX_TRN_LINKUP_CTRL_CONV_WO_PROTOCOL;
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
-	if (status)
-		return status;
+	reg |= IXGBE_MDIO_GLOBAL_INT_HI_TEMP_EN;
 
-	/* Disable Flex from training TXFFE. */
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK,
+				       IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				       reg);
 	if (status)
 		return status;
 
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN;
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN;
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN;
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	/* Enable vendor Auto-Neg alarm and Global Interrupt Mask 1 alarm */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 	if (status)
 		return status;
 
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	if (status)
-		return status;
+	reg |= (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN |
+		IXGBE_MDIO_GLOBAL_ALARM_1_INT);
 
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN;
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN;
-	reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN;
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK,
+				       IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				       reg);
 	if (status)
 		return status;
 
-	/* Enable override for coefficients. */
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+	/* Enable chip-wide vendor alarm */
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK,
+				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				      &reg);
 	if (status)
 		return status;
 
-	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN;
-	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN;
-	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CPLUS1_OVRRD_EN;
-	reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CMINUS1_OVRRD_EN;
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	reg |= IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN;
+
+	status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK,
+				       IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+				       reg);
+
+	return status;
+}
+
+/**
+ * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt
+ * @hw: pointer to hardware structure
+ *
+ * Handle external Base T PHY interrupt. If high temperature
+ * failure alarm then return error, else if link status change
+ * then setup internal/external PHY link
+ *
+ * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature
+ * failure alarm, else return PHY access status.
+ **/
+static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw)
+{
+	struct ixgbe_phy_info *phy = &hw->phy;
+	bool lsc;
+	u32 status;
+
+	status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc);
 	if (status)
 		return status;
 
-	/* Toggle port SW reset by AN reset. */
+	if (lsc)
+		return phy->ops.setup_internal_link(hw);
+
+	return 0;
+}
+
+/**
+ * ixgbe_setup_kr_speed_x550em - Configure the KR PHY for link speed.
+ * @hw: pointer to hardware structure
+ * @speed: link speed
+ *
+ * Configures the integrated KR PHY.
+ **/
+static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw,
+				       ixgbe_link_speed speed)
+{
+	s32 status;
+	u32 reg_val;
+
 	status = ixgbe_read_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
+					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+					IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
 	if (status)
 		return status;
 
+	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
+	reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_FEC_REQ |
+		     IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_FEC);
+	reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR |
+		     IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX);
+
+	/* Advertise 10G support. */
+	if (speed & IXGBE_LINK_SPEED_10GB_FULL)
+		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR;
+
+	/* Advertise 1G support. */
+	if (speed & IXGBE_LINK_SPEED_1GB_FULL)
+		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX;
+
+	/* Restart auto-negotiation. */
 	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
 	status = ixgbe_write_iosf_sb_reg_x550(hw,
-				IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-				IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
+					IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
 
 	return status;
 }
@@ -990,85 +1333,82 @@ static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw)
  **/
 static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw)
 {
-	s32 status;
-	u32 reg_val;
+	return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised);
+}
 
-	status = ixgbe_read_iosf_sb_reg_x550(hw,
-					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-					IXGBE_SB_IOSF_TARGET_KR_PHY, &reg_val);
-	if (status)
-		return status;
+/** ixgbe_ext_phy_t_x550em_get_link - Get ext phy link status
+ *  @hw: address of hardware structure
+ *  @link_up: address of boolean to indicate link status
+ *
+ *  Returns error code if unable to get link status.
+ **/
+static s32 ixgbe_ext_phy_t_x550em_get_link(struct ixgbe_hw *hw, bool *link_up)
+{
+	u32 ret;
+	u16 autoneg_status;
 
-	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE;
-	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_FEC_REQ;
-	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_FEC;
-	reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR |
-		     IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX);
+	*link_up = false;
 
-	/* Advertise 10G support. */
-	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
-		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR;
+	/* read this twice back to back to indicate current status */
+	ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
+				   IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+				   &autoneg_status);
+	if (ret)
+		return ret;
 
-	/* Advertise 1G support. */
-	if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL)
-		reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX;
+	ret = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
+				   IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
+				   &autoneg_status);
+	if (ret)
+		return ret;
 
-	/* Restart auto-negotiation. */
-	reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART;
-	status = ixgbe_write_iosf_sb_reg_x550(hw,
-					IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id),
-					IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val);
+	*link_up = !!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS);
 
-	return status;
+	return 0;
 }
 
-/** ixgbe_setup_internal_phy_x550em - Configure integrated KR PHY
+/** ixgbe_setup_internal_phy_t_x550em - Configure KR PHY to X557 link
  *  @hw: point to hardware structure
  *
- *  Configures the integrated KR PHY to talk to the external PHY. The base
- *  driver will call this function when it gets notification via interrupt from
- *  the external PHY. This function forces the internal PHY into iXFI mode at
- *  the correct speed.
+ *  Configures the link between the integrated KR PHY and the external X557 PHY
+ *  The driver will call this function when it gets a link status change
+ *  interrupt from the X557 PHY. This function configures the link speed
+ *  between the PHYs to match the link speed of the BASE-T link.
  *
- *  A return of a non-zero value indicates an error, and the base driver should
- *  not report link up.
+ * A return of a non-zero value indicates an error, and the base driver should
+ * not report link up.
  **/
-static s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw)
+static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw)
 {
-	u32 status;
-	u16 lasi, autoneg_status, speed;
 	ixgbe_link_speed force_speed;
+	bool link_up;
+	u32 status;
+	u16 speed;
+
+	if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper)
+		return IXGBE_ERR_CONFIG;
 
-	/* Verify that the external link status has changed */
-	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_XENPAK_LASI_STATUS,
-				      IXGBE_MDIO_PMA_PMD_DEV_TYPE, &lasi);
+	/* If link is not up, then there is no setup necessary so return  */
+	status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up);
 	if (status)
 		return status;
 
-	/* If there was no change in link status, we can just exit */
-	if (!(lasi & IXGBE_XENPAK_LASI_LINK_STATUS_ALARM))
+	if (!link_up)
 		return 0;
 
-	/* we read this twice back to back to indicate current status */
-	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
+	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT,
 				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
-				      &autoneg_status);
+				      &speed);
 	if (status)
 		return status;
 
-	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_STATUS,
-				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
-				      &autoneg_status);
+	/* If link is not still up, then no setup is necessary so return */
+	status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up);
 	if (status)
 		return status;
 
-	/* If link is not up return an error indicating treat link as down */
-	if (!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS))
-		return IXGBE_ERR_INVALID_LINK_SETTINGS;
-
-	status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT,
-				      IXGBE_MDIO_AUTO_NEG_DEV_TYPE,
-				      &speed);
+	if (!link_up)
+		return 0;
 
 	/* clear everything but the speed and duplex bits */
 	speed &= IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_MASK;
@@ -1088,6 +1428,22 @@ static s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw)
 	return ixgbe_setup_ixfi_x550em(hw, &force_speed);
 }
 
+/** ixgbe_reset_phy_t_X550em - Performs X557 PHY reset and enables LASI
+ *  @hw: pointer to hardware structure
+ **/
+static s32 ixgbe_reset_phy_t_X550em(struct ixgbe_hw *hw)
+{
+	s32 status;
+
+	status = ixgbe_reset_phy_generic(hw);
+
+	if (status)
+		return status;
+
+	/* Configure Link Status Alarm and Temperature Threshold interrupts */
+	return ixgbe_enable_lasi_ext_t_x550em(hw);
+}
+
 /** ixgbe_init_phy_ops_X550em - PHY/SFP specific init
  *  @hw: pointer to hardware structure
  *
@@ -1098,25 +1454,32 @@ static s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw)
 static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 {
 	struct ixgbe_phy_info *phy = &hw->phy;
+	ixgbe_link_speed speed;
 	s32 ret_val;
-	u32 esdp;
 
-	if (hw->device_id == IXGBE_DEV_ID_X550EM_X_SFP) {
-		esdp = IXGBE_READ_REG(hw, IXGBE_ESDP);
-		phy->phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM;
+	hw->mac.ops.set_lan_id(hw);
 
-		if (hw->bus.lan_id) {
-			esdp &= ~(IXGBE_ESDP_SDP1_NATIVE | IXGBE_ESDP_SDP1);
-			esdp |= IXGBE_ESDP_SDP1_DIR;
+	if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) {
+		phy->phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM;
+		ixgbe_setup_mux_ctl(hw);
+
+		/* Save NW management interface connected on board. This is used
+		 * to determine internal PHY mode.
+		 */
+		phy->nw_mng_if_sel = IXGBE_READ_REG(hw, IXGBE_NW_MNG_IF_SEL);
+
+		/* If internal PHY mode is KR, then initialize KR link */
+		if (phy->nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE) {
+			speed = IXGBE_LINK_SPEED_10GB_FULL |
+				IXGBE_LINK_SPEED_1GB_FULL;
+			ret_val = ixgbe_setup_kr_speed_x550em(hw, speed);
 		}
-		esdp &= ~(IXGBE_ESDP_SDP0_NATIVE | IXGBE_ESDP_SDP0_DIR);
-		IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp);
 	}
 
 	/* Identify the PHY or SFP module */
 	ret_val = phy->ops.identify(hw);
 
-	/* Setup function pointers based on detected SFP module and speeds */
+	/* Setup function pointers based on detected hardware */
 	ixgbe_init_mac_link_ops_X550em(hw);
 	if (phy->sfp_type != ixgbe_sfp_type_unknown)
 		phy->ops.reset = NULL;
@@ -1134,11 +1497,30 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw)
 		phy->ops.write_reg = ixgbe_write_phy_reg_x550em;
 		break;
 	case ixgbe_phy_x550em_ext_t:
-		phy->ops.setup_internal_link = ixgbe_setup_internal_phy_x550em;
+		/* Save NW management interface connected on board. This is used
+		 * to determine internal PHY mode
+		 */
+		phy->nw_mng_if_sel = IXGBE_READ_REG(hw, IXGBE_NW_MNG_IF_SEL);
+
+		/* If internal link mode is XFI, then setup iXFI internal link,
+		 * else setup KR now.
+		 */
+		if (!(phy->nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) {
+			phy->ops.setup_internal_link =
+					ixgbe_setup_internal_phy_t_x550em;
+		} else {
+			speed = IXGBE_LINK_SPEED_10GB_FULL |
+				IXGBE_LINK_SPEED_1GB_FULL;
+			ret_val = ixgbe_setup_kr_speed_x550em(hw, speed);
+		}
+
+		phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em;
+		phy->ops.reset = ixgbe_reset_phy_t_X550em;
 		break;
 	default:
 		break;
 	}
+
 	return ret_val;
 }
 
@@ -1177,67 +1559,37 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw)
  **/
 static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw)
 {
-	u32 status;
+	s32 status;
 	u16 reg;
-	u32 retries = 2;
-
-	do {
-		/* decrement retries counter and exit if we hit 0 */
-		if (retries < 1) {
-			hw_dbg(hw, "External PHY not yet finished resetting.");
-			return IXGBE_ERR_PHY;
-		}
-		retries--;
-
-		status = hw->phy.ops.read_reg(hw,
-					      IXGBE_MDIO_TX_VENDOR_ALARMS_3,
-					      IXGBE_MDIO_PMA_PMD_DEV_TYPE,
-					      &reg);
-		if (status)
-			return status;
 
-		/* Verify PHY FW reset has completed */
-	} while ((reg & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) != 1);
-
-	/* Set port to low power mode */
 	status = hw->phy.ops.read_reg(hw,
-				      IXGBE_MDIO_VENDOR_SPECIFIC_1_CONTROL,
-				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
-				      &reg);
-	if (status)
-		return status;
-
-	/* Enable the transmitter */
-	status = hw->phy.ops.read_reg(hw,
-				      IXGBE_MDIO_PMD_STD_TX_DISABLE_CNTR,
+				      IXGBE_MDIO_TX_VENDOR_ALARMS_3,
 				      IXGBE_MDIO_PMA_PMD_DEV_TYPE,
 				      &reg);
 	if (status)
 		return status;
 
-	reg &= ~IXGBE_MDIO_PMD_GLOBAL_TX_DISABLE;
+	/* If PHY FW reset completed bit is set then this is the first
+	 * SW instance after a power on so the PHY FW must be un-stalled.
+	 */
+	if (reg & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) {
+		status = hw->phy.ops.read_reg(hw,
+					IXGBE_MDIO_GLOBAL_RES_PR_10,
+					IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+					&reg);
+		if (status)
+			return status;
 
-	status = hw->phy.ops.write_reg(hw,
-				       IXGBE_MDIO_PMD_STD_TX_DISABLE_CNTR,
-				       IXGBE_MDIO_PMA_PMD_DEV_TYPE,
-				       reg);
-	if (status)
-		return status;
+		reg &= ~IXGBE_MDIO_POWER_UP_STALL;
 
-	/* Un-stall the PHY FW */
-	status = hw->phy.ops.read_reg(hw,
-				      IXGBE_MDIO_GLOBAL_RES_PR_10,
-				      IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
-				      &reg);
-	if (status)
-		return status;
-
-	reg &= ~IXGBE_MDIO_POWER_UP_STALL;
+		status = hw->phy.ops.write_reg(hw,
+					IXGBE_MDIO_GLOBAL_RES_PR_10,
+					IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
+					reg);
+		if (status)
+			return status;
+	}
 
-	status = hw->phy.ops.write_reg(hw,
-				       IXGBE_MDIO_GLOBAL_RES_PR_10,
-				       IXGBE_MDIO_VENDOR_SPECIFIC_1_DEV_TYPE,
-				       reg);
 	return status;
 }
 
@@ -1254,6 +1606,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 	s32 status;
 	u32 ctrl = 0;
 	u32 i;
+	u32 hlreg0;
 	bool link_up = false;
 
 	/* Call adapter stop to disable Tx/Rx and clear interrupts */
@@ -1338,6 +1691,15 @@ mac_reset_top:
 	hw->mac.num_rar_entries = 128;
 	hw->mac.ops.init_rx_addrs(hw);
 
+	if (hw->device_id == IXGBE_DEV_ID_X550EM_X_10G_T) {
+		hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
+		hlreg0 &= ~IXGBE_HLREG0_MDCSPD;
+		IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);
+	}
+
+	if (hw->device_id == IXGBE_DEV_ID_X550EM_X_SFP)
+		ixgbe_setup_mux_ctl(hw);
+
 	return status;
 }
 
@@ -1490,6 +1852,10 @@ static struct ixgbe_eeprom_operations eeprom_ops_X550EM_x = {
 	.read_i2c_sff8472	= &ixgbe_read_i2c_sff8472_generic, \
 	.read_i2c_eeprom	= &ixgbe_read_i2c_eeprom_generic, \
 	.write_i2c_eeprom	= &ixgbe_write_i2c_eeprom_generic, \
+	.read_reg		= &ixgbe_read_phy_reg_generic, \
+	.write_reg		= &ixgbe_write_phy_reg_generic, \
+	.setup_link		= &ixgbe_setup_phy_link_generic, \
+	.set_phy_power		= &ixgbe_set_copper_phy_power, \
 	.check_overtemp		= &ixgbe_tn_check_overtemp, \
 	.get_firmware_version	= &ixgbe_get_phy_firmware_version_generic,
 
@@ -1497,9 +1863,6 @@ static struct ixgbe_phy_operations phy_ops_X550 = {
 	X550_COMMON_PHY
 	.init			= NULL,
 	.identify		= &ixgbe_identify_phy_generic,
-	.read_reg		= &ixgbe_read_phy_reg_generic,
-	.write_reg		= &ixgbe_write_phy_reg_generic,
-	.setup_link		= &ixgbe_setup_phy_link_generic,
 	.read_i2c_combined	= &ixgbe_read_i2c_combined_generic,
 	.write_i2c_combined	= &ixgbe_write_i2c_combined_generic,
 };
@@ -1508,9 +1871,14 @@ static struct ixgbe_phy_operations phy_ops_X550EM_x = {
 	X550_COMMON_PHY
 	.init			= &ixgbe_init_phy_ops_X550em,
 	.identify		= &ixgbe_identify_phy_x550em,
-	.read_reg		= NULL, /* defined later */
-	.write_reg		= NULL, /* defined later */
-	.setup_link		= NULL, /* defined later */
+};
+
+static const u32 ixgbe_mvals_X550[IXGBE_MVALS_IDX_LIMIT] = {
+	IXGBE_MVALS_INIT(X550)
+};
+
+static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = {
+	IXGBE_MVALS_INIT(X550EM_x)
 };
 
 struct ixgbe_info ixgbe_X550_info = {
@@ -1520,6 +1888,7 @@ struct ixgbe_info ixgbe_X550_info = {
 	.eeprom_ops		= &eeprom_ops_X550,
 	.phy_ops		= &phy_ops_X550,
 	.mbx_ops		= &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_X550,
 };
 
 struct ixgbe_info ixgbe_X550EM_x_info = {
@@ -1529,4 +1898,5 @@ struct ixgbe_info ixgbe_X550EM_x_info = {
 	.eeprom_ops		= &eeprom_ops_X550EM_x,
 	.phy_ops		= &phy_ops_X550EM_x,
 	.mbx_ops		= &mbx_ops_generic,
+	.mvals			= ixgbe_mvals_X550EM_x,
 };
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index a16d267fbce4..e71cdde9cb01 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3612,7 +3612,7 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
 
 	if (!dst_mac || is_link_local_ether_addr(dst_mac)) {
-		dev_kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
 	}
 
diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig
index d323a695dfbc..80af9ffce5ea 100644
--- a/drivers/net/ethernet/marvell/Kconfig
+++ b/drivers/net/ethernet/marvell/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_MARVELL
 	default y
 	depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 1c75829eb166..d52639bc491f 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -3125,9 +3125,8 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 
 	mib_counters_clear(mp);
 
-	init_timer(&mp->mib_counters_timer);
-	mp->mib_counters_timer.data = (unsigned long)mp;
-	mp->mib_counters_timer.function = mib_counters_timer_wrapper;
+	setup_timer(&mp->mib_counters_timer, mib_counters_timer_wrapper,
+		    (unsigned long)mp);
 	mp->mib_counters_timer.expires = jiffies + 30 * HZ;
 
 	spin_lock_init(&mp->mib_counters_lock);
@@ -3136,9 +3135,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 
 	netif_napi_add(dev, &mp->napi, mv643xx_eth_poll, NAPI_POLL_WEIGHT);
 
-	init_timer(&mp->rx_oom);
-	mp->rx_oom.data = (unsigned long)mp;
-	mp->rx_oom.function = oom_timer_wrapper;
+	setup_timer(&mp->rx_oom, oom_timer_wrapper, (unsigned long)mp);
 
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ce5f7f9cff06..5bdf78231a4e 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1013,6 +1013,12 @@ static void mvneta_defaults_set(struct mvneta_port *pp)
 		val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
 		val |= MVNETA_GMAC_1MS_CLOCK_ENABLE;
 		mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
+	} else {
+		val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+		val &= ~(MVNETA_GMAC_INBAND_AN_ENABLE |
+		       MVNETA_GMAC_AN_SPEED_EN |
+		       MVNETA_GMAC_AN_DUPLEX_EN);
+		mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
 	}
 
 	mvneta_set_ucast_table(pp, -1);
@@ -1359,7 +1365,7 @@ static void *mvneta_frag_alloc(const struct mvneta_port *pp)
 static void mvneta_frag_free(const struct mvneta_port *pp, void *data)
 {
 	if (likely(pp->frag_size <= PAGE_SIZE))
-		put_page(virt_to_head_page(data));
+		skb_free_frag(data);
 	else
 		kfree(data);
 }
diff --git a/drivers/net/ethernet/mellanox/Kconfig b/drivers/net/ethernet/mellanox/Kconfig
index 8cf7563a8d92..52a6665b7abf 100644
--- a/drivers/net/ethernet/mellanox/Kconfig
+++ b/drivers/net/ethernet/mellanox/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_MELLANOX
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 4f7dc044601e..82040137d7d9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -49,6 +49,7 @@
 #include "mlx4.h"
 #include "fw.h"
 #include "fw_qos.h"
+#include "mlx4_stats.h"
 
 #define CMD_POLL_TOKEN 0xffff
 #define INBOX_MASK	0xffffffffffffff00ULL
@@ -714,8 +715,13 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 					 msecs_to_jiffies(timeout))) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
-		err = -EIO;
-		goto out_reset;
+		if (op == MLX4_CMD_NOP) {
+			err = -EBUSY;
+			goto out;
+		} else {
+			err = -EIO;
+			goto out_reset;
+		}
 	}
 
 	err = context->result;
@@ -877,7 +883,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 {
 	struct ib_smp *smp = inbox->buf;
 	u32 index;
-	u8 port;
+	u8 port, slave_port;
 	u8 opcode_modifier;
 	u16 *table;
 	int err;
@@ -889,7 +895,8 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 	__be32 slave_cap_mask;
 	__be64 slave_node_guid;
 
-	port = vhcr->in_modifier;
+	slave_port = vhcr->in_modifier;
+	port = mlx4_slave_convert_port(dev, slave, slave_port);
 
 	/* network-view bit is for driver use only, and should not be passed to FW */
 	opcode_modifier = vhcr->op_modifier & ~0x8; /* clear netw view bit */
@@ -925,8 +932,9 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 			if (smp->attr_id == IB_SMP_ATTR_PORT_INFO) {
 				/*get the slave specific caps:*/
 				/*do the command */
+				smp->attr_mod = cpu_to_be32(port);
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					    vhcr->in_modifier, opcode_modifier,
+					    port, opcode_modifier,
 					    vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 				/* modify the response for slaves */
 				if (!err && slave != mlx4_master_func_num(dev)) {
@@ -970,7 +978,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 			}
 			if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) {
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					     vhcr->in_modifier, opcode_modifier,
+					     port, opcode_modifier,
 					     vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 				if (!err) {
 					slave_node_guid =  mlx4_get_slave_node_guid(dev, slave);
@@ -2910,7 +2918,7 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac)
 	port = mlx4_slaves_closest_port(dev, slave, port);
 	s_info = &priv->mfunc.master.vf_admin[slave].vport[port];
 	s_info->mac = mac;
-	mlx4_info(dev, "default mac on vf %d port %d to %llX will take afect only after vf restart\n",
+	mlx4_info(dev, "default mac on vf %d port %d to %llX will take effect only after vf restart\n",
 		  vf, port, s_info->mac);
 	return 0;
 }
@@ -3159,6 +3167,92 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat
 }
 EXPORT_SYMBOL_GPL(mlx4_set_vf_link_state);
 
+int mlx4_get_counter_stats(struct mlx4_dev *dev, int counter_index,
+			   struct mlx4_counter *counter_stats, int reset)
+{
+	struct mlx4_cmd_mailbox *mailbox = NULL;
+	struct mlx4_counter *tmp_counter;
+	int err;
+	u32 if_stat_in_mod;
+
+	if (!counter_stats)
+		return -EINVAL;
+
+	if (counter_index == MLX4_SINK_COUNTER_INDEX(dev))
+		return 0;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memset(mailbox->buf, 0, sizeof(struct mlx4_counter));
+	if_stat_in_mod = counter_index;
+	if (reset)
+		if_stat_in_mod |= MLX4_QUERY_IF_STAT_RESET;
+	err = mlx4_cmd_box(dev, 0, mailbox->dma,
+			   if_stat_in_mod, 0,
+			   MLX4_CMD_QUERY_IF_STAT,
+			   MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
+	if (err) {
+		mlx4_dbg(dev, "%s: failed to read statistics for counter index %d\n",
+			 __func__, counter_index);
+		goto if_stat_out;
+	}
+	tmp_counter = (struct mlx4_counter *)mailbox->buf;
+	counter_stats->counter_mode = tmp_counter->counter_mode;
+	if (counter_stats->counter_mode == 0) {
+		counter_stats->rx_frames =
+			cpu_to_be64(be64_to_cpu(counter_stats->rx_frames) +
+				    be64_to_cpu(tmp_counter->rx_frames));
+		counter_stats->tx_frames =
+			cpu_to_be64(be64_to_cpu(counter_stats->tx_frames) +
+				    be64_to_cpu(tmp_counter->tx_frames));
+		counter_stats->rx_bytes =
+			cpu_to_be64(be64_to_cpu(counter_stats->rx_bytes) +
+				    be64_to_cpu(tmp_counter->rx_bytes));
+		counter_stats->tx_bytes =
+			cpu_to_be64(be64_to_cpu(counter_stats->tx_bytes) +
+				    be64_to_cpu(tmp_counter->tx_bytes));
+	}
+
+if_stat_out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_counter_stats);
+
+int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx,
+		      struct ifla_vf_stats *vf_stats)
+{
+	struct mlx4_counter tmp_vf_stats;
+	int slave;
+	int err = 0;
+
+	if (!vf_stats)
+		return -EINVAL;
+
+	if (!mlx4_is_master(dev))
+		return -EPROTONOSUPPORT;
+
+	slave = mlx4_get_slave_indx(dev, vf_idx);
+	if (slave < 0)
+		return -EINVAL;
+
+	port = mlx4_slaves_closest_port(dev, slave, port);
+	err = mlx4_calc_vf_counters(dev, slave, port, &tmp_vf_stats);
+	if (!err && tmp_vf_stats.counter_mode == 0) {
+		vf_stats->rx_packets = be64_to_cpu(tmp_vf_stats.rx_frames);
+		vf_stats->tx_packets = be64_to_cpu(tmp_vf_stats.tx_frames);
+		vf_stats->rx_bytes = be64_to_cpu(tmp_vf_stats.rx_bytes);
+		vf_stats->tx_bytes = be64_to_cpu(tmp_vf_stats.tx_bytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_vf_stats);
+
 int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -3192,6 +3286,12 @@ int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
 				 int enabled)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
+			&priv->dev, slave);
+	int min_port = find_first_bit(actv_ports.ports,
+				      priv->dev.caps.num_ports) + 1;
+	int max_port = min_port - 1 +
+		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
 
 	if (slave == mlx4_master_func_num(dev))
 		return 0;
@@ -3201,6 +3301,11 @@ int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
 	    enabled < 0 || enabled > 1)
 		return -EINVAL;
 
+	if (min_port == max_port && dev->caps.num_ports > 1) {
+		mlx4_info(dev, "SMI access disallowed for single ported VFs\n");
+		return -EPROTONOSUPPORT;
+	}
+
 	priv->mfunc.master.vf_admin[slave].enable_smi[port] = enabled;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index e71f31387ac6..3348e646db70 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -292,7 +292,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	u64 mtt_addr;
 	int err;
 
-	if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool)
+	if (vector >= dev->caps.num_comp_vectors)
 		return -EINVAL;
 
 	cq->vector = vector;
@@ -319,7 +319,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 		cq_context->flags  |= cpu_to_be32(1 << 19);
 
 	cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index);
-	cq_context->comp_eqn	    = priv->eq_table.eq[vector].eqn;
+	cq_context->comp_eqn	    = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn;
 	cq_context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
 
 	mtt_addr = mlx4_mtt_addr(dev, mtt);
@@ -339,11 +339,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	init_completion(&cq->free);
 	cq->comp = mlx4_add_cq_to_tasklet;
 	cq->tasklet_ctx.priv =
-		&priv->eq_table.eq[cq->vector].tasklet_ctx;
+		&priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].tasklet_ctx;
 	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
 
 
-	cq->irq = priv->eq_table.eq[cq->vector].irq;
+	cq->irq = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].irq;
 	return 0;
 
 err_radix:
@@ -368,7 +368,10 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 	if (err)
 		mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);
 
-	synchronize_irq(priv->eq_table.eq[cq->vector].irq);
+	synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq);
+	if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq !=
+	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
+		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 
 	spin_lock_irq(&cq_table->lock);
 	radix_tree_delete(&cq_table->tree, cq->cqn);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 22da4d0d0f05..63769df872a4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -66,6 +66,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 
 	cq->ring = ring;
 	cq->is_tx = mode;
+	cq->vector = mdev->dev->caps.num_comp_vectors;
 
 	/* Allocate HW buffers on provided NUMA node.
 	 * dev->numa_node is used in mtt range allocation flow.
@@ -101,12 +102,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	int err = 0;
 	char name[25];
 	int timestamp_en = 0;
-	struct cpu_rmap *rmap =
-#ifdef CONFIG_RFS_ACCEL
-		priv->dev->rx_cpu_rmap;
-#else
-		NULL;
-#endif
+	bool assigned_eq = false;
 
 	cq->dev = mdev->pndev[priv->port];
 	cq->mcq.set_ci_db  = cq->wqres.db.db;
@@ -116,23 +112,19 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	memset(cq->buf, 0, cq->buf_size);
 
 	if (cq->is_tx == RX) {
-		if (mdev->dev->caps.comp_pool) {
-			if (!cq->vector) {
-				sprintf(name, "%s-%d", priv->dev->name,
-					cq->ring);
-				/* Set IRQ for specific name (per ring) */
-				if (mlx4_assign_eq(mdev->dev, name, rmap,
-						   &cq->vector)) {
-					cq->vector = (cq->ring + 1 + priv->port)
-					    % mdev->dev->caps.num_comp_vectors;
-					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
-						  name);
-				}
-
+		if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port,
+					     cq->vector)) {
+			cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask);
+
+			err = mlx4_assign_eq(mdev->dev, priv->port,
+					     &cq->vector);
+			if (err) {
+				mlx4_err(mdev, "Failed assigning an EQ to %s\n",
+					 name);
+				goto free_eq;
 			}
-		} else {
-			cq->vector = (cq->ring + 1 + priv->port) %
-				mdev->dev->caps.num_comp_vectors;
+
+			assigned_eq = true;
 		}
 
 		cq->irq_desc =
@@ -159,7 +151,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			    &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq,
 			    cq->vector, 0, timestamp_en);
 	if (err)
-		return err;
+		goto free_eq;
 
 	cq->mcq.comp  = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
 	cq->mcq.event = mlx4_en_cq_event;
@@ -168,13 +160,6 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
 			       NAPI_POLL_WEIGHT);
 	} else {
-		struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
-
-		err = irq_set_affinity_hint(cq->mcq.irq,
-					    ring->affinity_mask);
-		if (err)
-			mlx4_warn(mdev, "Failed setting affinity hint\n");
-
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
 		napi_hash_add(&cq->napi);
 	}
@@ -182,6 +167,12 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	napi_enable(&cq->napi);
 
 	return 0;
+
+free_eq:
+	if (assigned_eq)
+		mlx4_release_eq(mdev->dev, cq->vector);
+	cq->vector = mdev->dev->caps.num_comp_vectors;
+	return err;
 }
 
 void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
@@ -191,9 +182,9 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 
 	mlx4_en_unmap_buffer(&cq->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
-	if (priv->mdev->dev->caps.comp_pool && cq->vector) {
+	if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) &&
+	    cq->is_tx == RX)
 		mlx4_release_eq(priv->mdev->dev, cq->vector);
-	}
 	cq->vector = 0;
 	cq->buf_size = 0;
 	cq->buf = NULL;
@@ -207,7 +198,6 @@ void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	if (!cq->is_tx) {
 		napi_hash_del(&cq->napi);
 		synchronize_rcu();
-		irq_set_affinity_hint(cq->mcq.irq, NULL);
 	}
 	netif_napi_del(&cq->napi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index a2ddf3d75ff8..99ba1c50e585 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -119,6 +119,12 @@ static const char main_strings[][ETH_GSTRING_LEN] = {
 	"queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed",
 	"rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload",
 
+	/* pf statistics */
+	"pf_rx_packets",
+	"pf_rx_bytes",
+	"pf_tx_packets",
+	"pf_tx_bytes",
+
 	/* priority flow control statistics rx */
 	"rx_pause_prio_0", "rx_pause_duration_prio_0",
 	"rx_pause_transition_prio_0",
@@ -368,6 +374,11 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev,
 		if (bitmap_iterator_test(&it))
 			data[index++] = ((unsigned long *)&priv->port_stats)[i];
 
+	for (i = 0; i < NUM_PF_STATS; i++, bitmap_iterator_inc(&it))
+		if (bitmap_iterator_test(&it))
+			data[index++] =
+				((unsigned long *)&priv->pf_stats)[i];
+
 	for (i = 0; i < NUM_FLOW_PRIORITY_STATS_RX;
 	     i++, bitmap_iterator_inc(&it))
 		if (bitmap_iterator_test(&it))
@@ -448,6 +459,12 @@ static void mlx4_en_get_strings(struct net_device *dev,
 				strcpy(data + (index++) * ETH_GSTRING_LEN,
 				       main_strings[strings]);
 
+		for (i = 0; i < NUM_PF_STATS; i++, strings++,
+		     bitmap_iterator_inc(&it))
+			if (bitmap_iterator_test(&it))
+				strcpy(data + (index++) * ETH_GSTRING_LEN,
+				       main_strings[strings]);
+
 		for (i = 0; i < NUM_FLOW_STATS; i++, strings++,
 		     bitmap_iterator_inc(&it))
 			if (bitmap_iterator_test(&it))
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 32f5ec737472..77179d7ae4cc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1501,17 +1501,13 @@ static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
 {
 	struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
 	int numa_node = priv->mdev->dev->numa_node;
-	int ret = 0;
 
 	if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
 		return -ENOMEM;
 
-	ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
-					  ring->affinity_mask);
-	if (ret)
-		free_cpumask_var(ring->affinity_mask);
-
-	return ret;
+	cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node),
+			ring->affinity_mask);
+	return 0;
 }
 
 static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
@@ -1601,6 +1597,9 @@ int mlx4_en_start_port(struct net_device *dev)
 	}
 	mdev->mac_removed[priv->port] = 0;
 
+	priv->counter_index =
+			mlx4_get_default_counter_index(mdev->dev, priv->port);
+
 	err = mlx4_en_config_rss_steer(priv);
 	if (err) {
 		en_err(priv, "Failed configuring rss steering\n");
@@ -1759,6 +1758,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 
 	/* Set port as not active */
 	priv->port_up = false;
+	priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev);
 
 	/* Promsicuous mode */
 	if (mdev->dev->caps.steering_mode ==
@@ -1895,6 +1895,7 @@ static void mlx4_en_clear_stats(struct net_device *dev)
 	       sizeof(priv->rx_priority_flowstats));
 	memset(&priv->tx_priority_flowstats, 0,
 	       sizeof(priv->tx_priority_flowstats));
+	memset(&priv->pf_stats, 0, sizeof(priv->pf_stats));
 
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		priv->tx_ring[i]->bytes = 0;
@@ -1958,7 +1959,6 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 	int i;
 
 #ifdef CONFIG_RFS_ACCEL
-	free_irq_cpu_rmap(priv->dev->rx_cpu_rmap);
 	priv->dev->rx_cpu_rmap = NULL;
 #endif
 
@@ -2016,11 +2016,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 	}
 
 #ifdef CONFIG_RFS_ACCEL
-	if (priv->mdev->dev->caps.comp_pool) {
-		priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool);
-		if (!priv->dev->rx_cpu_rmap)
-			goto err;
-	}
+	priv->dev->rx_cpu_rmap = mlx4_get_cpu_rmap(priv->mdev->dev, priv->port);
 #endif
 
 	return 0;
@@ -2296,6 +2292,15 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st
 	return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state);
 }
 
+static int mlx4_en_get_vf_stats(struct net_device *dev, int vf,
+				struct ifla_vf_stats *vf_stats)
+{
+	struct mlx4_en_priv *en_priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = en_priv->mdev;
+
+	return mlx4_get_vf_stats(mdev->dev, en_priv->port, vf, vf_stats);
+}
+
 #define PORT_ID_BYTE_LEN 8
 static int mlx4_en_get_phys_port_id(struct net_device *dev,
 				    struct netdev_phys_item_id *ppid)
@@ -2493,6 +2498,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_set_vf_rate	= mlx4_en_set_vf_rate,
 	.ndo_set_vf_spoofchk	= mlx4_en_set_vf_spoofchk,
 	.ndo_set_vf_link_state	= mlx4_en_set_vf_link_state,
+	.ndo_get_vf_stats       = mlx4_en_get_vf_stats,
 	.ndo_get_vf_config	= mlx4_en_get_vf_config,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= mlx4_en_netpoll,
@@ -2690,7 +2696,7 @@ void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev,
 				     u8 rx_ppp, u8 rx_pause,
 				     u8 tx_ppp, u8 tx_pause)
 {
-	int last_i = NUM_MAIN_STATS + NUM_PORT_STATS;
+	int last_i = NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PF_STATS;
 
 	if (!mlx4_is_slave(dev) &&
 	    (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN)) {
@@ -2752,6 +2758,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 	bitmap_set(stats_bitmap->bitmap, last_i, NUM_PORT_STATS);
 	last_i += NUM_PORT_STATS;
 
+	if (mlx4_is_master(dev))
+		bitmap_set(stats_bitmap->bitmap, last_i,
+			   NUM_PF_STATS);
+	last_i += NUM_PF_STATS;
+
 	mlx4_en_update_pfc_stats_bitmap(dev, stats_bitmap,
 					rx_ppp, rx_pause,
 					tx_ppp, tx_pause);
@@ -2787,6 +2798,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 
 	priv = netdev_priv(dev);
 	memset(priv, 0, sizeof(struct mlx4_en_priv));
+	priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev);
 	spin_lock_init(&priv->stats_lock);
 	INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode);
 	INIT_WORK(&priv->watchdog_task, mlx4_en_restart);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 54f0e5ab2e55..ee99e67187f5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -139,7 +139,7 @@ static unsigned long en_stats_adder(__be64 *start, __be64 *next, int num)
 	int i;
 	int offset = next - start;
 
-	for (i = 0; i <= num; i++) {
+	for (i = 0; i < num; i++) {
 		ret += be64_to_cpu(*curr);
 		curr += offset;
 	}
@@ -149,6 +149,7 @@ static unsigned long en_stats_adder(__be64 *start, __be64 *next, int num)
 
 int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 {
+	struct mlx4_counter tmp_counter_stats;
 	struct mlx4_en_stat_out_mbox *mlx4_en_stats;
 	struct mlx4_en_stat_out_flow_control_mbox *flowstats;
 	struct mlx4_en_priv *priv = netdev_priv(mdev->pndev[port]);
@@ -156,7 +157,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 	struct mlx4_cmd_mailbox *mailbox;
 	u64 in_mod = reset << 8 | port;
 	int err;
-	int i;
+	int i, counter_index;
 
 	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
 	if (IS_ERR(mailbox))
@@ -202,6 +203,20 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		priv->port_stats.tso_packets       += ring->tso_packets;
 		priv->port_stats.xmit_more         += ring->xmit_more;
 	}
+	if (mlx4_is_master(mdev->dev)) {
+		stats->rx_packets = en_stats_adder(&mlx4_en_stats->RTOT_prio_0,
+						   &mlx4_en_stats->RTOT_prio_1,
+						   NUM_PRIORITIES);
+		stats->tx_packets = en_stats_adder(&mlx4_en_stats->TTOT_prio_0,
+						   &mlx4_en_stats->TTOT_prio_1,
+						   NUM_PRIORITIES);
+		stats->rx_bytes = en_stats_adder(&mlx4_en_stats->ROCT_prio_0,
+						 &mlx4_en_stats->ROCT_prio_1,
+						 NUM_PRIORITIES);
+		stats->tx_bytes = en_stats_adder(&mlx4_en_stats->TOCT_prio_0,
+						 &mlx4_en_stats->TOCT_prio_1,
+						 NUM_PRIORITIES);
+	}
 
 	/* net device stats */
 	stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) +
@@ -296,6 +311,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 
 	spin_unlock_bh(&priv->stats_lock);
 
+	memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats));
+	counter_index = mlx4_get_default_counter_index(mdev->dev, port);
+	err = mlx4_get_counter_stats(mdev->dev, counter_index,
+				     &tmp_counter_stats, reset);
+
 	/* 0xffs indicates invalid value */
 	memset(mailbox->buf, 0xff, sizeof(*flowstats) * MLX4_NUM_PRIORITIES);
 
@@ -314,6 +334,13 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 
 	spin_lock_bh(&priv->stats_lock);
 
+	if (tmp_counter_stats.counter_mode == 0) {
+		priv->pf_stats.rx_bytes   = be64_to_cpu(tmp_counter_stats.rx_bytes);
+		priv->pf_stats.tx_bytes   = be64_to_cpu(tmp_counter_stats.tx_bytes);
+		priv->pf_stats.rx_packets = be64_to_cpu(tmp_counter_stats.rx_frames);
+		priv->pf_stats.tx_packets = be64_to_cpu(tmp_counter_stats.tx_frames);
+	}
+
 	for (i = 0; i < MLX4_NUM_PRIORITIES; i++)	{
 		priv->rx_priority_flowstats[i].rx_pause =
 			be64_to_cpu(flowstats[i].rx_pause);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 34f2fdf4fe5d..e482fa1bb741 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -66,7 +66,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 		context->pri_path.sched_queue |= user_prio << 3;
 		context->pri_path.feup = MLX4_FEUP_FORCE_ETH_UP;
 	}
-	context->pri_path.counter_index = 0xff;
+	context->pri_path.counter_index = priv->counter_index;
 	context->cqn_send = cpu_to_be32(cqn);
 	context->cqn_recv = cpu_to_be32(cqn);
 	context->db_rec_addr = cpu_to_be64(priv->res.db.dma << 2);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 2a77a6b19121..35f726c17e48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -337,15 +337,10 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev)
 	struct mlx4_dev *dev = mdev->dev;
 
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
-		if (!dev->caps.comp_pool)
-			num_of_eqs = max_t(int, MIN_RX_RINGS,
-					   min_t(int,
-						 dev->caps.num_comp_vectors,
-						 DEF_RX_RINGS));
-		else
-			num_of_eqs = min_t(int, MAX_MSIX_P_PORT,
-					   dev->caps.comp_pool/
-					   dev->caps.num_ports) - 1;
+		num_of_eqs = max_t(int, MIN_RX_RINGS,
+				   min_t(int,
+					 mlx4_get_eqs_per_port(mdev->dev, i),
+					 DEF_RX_RINGS));
 
 		num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS :
 			min_t(int, num_of_eqs,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f7bf312fb443..7bed3a88579f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -144,9 +144,9 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->queue_index = queue_index;
 
 	if (queue_index < priv->num_tx_rings_p_up)
-		cpumask_set_cpu_local_first(queue_index,
-					    priv->mdev->dev->numa_node,
-					    &ring->affinity_mask);
+		cpumask_set_cpu(cpumask_local_spread(queue_index,
+						     priv->mdev->dev->numa_node),
+				&ring->affinity_mask);
 
 	*pring = ring;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 2619c9fbf42d..aae13adfb492 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -145,7 +145,7 @@ void mlx4_gen_slave_eqe(struct work_struct *work)
 	struct mlx4_slave_event_eq *slave_eq = &mfunc->master.slave_eq;
 	struct mlx4_eqe *eqe;
 	u8 slave;
-	int i;
+	int i, phys_port, slave_port;
 
 	for (eqe = next_slave_event_eqe(slave_eq); eqe;
 	      eqe = next_slave_event_eqe(slave_eq)) {
@@ -154,9 +154,20 @@ void mlx4_gen_slave_eqe(struct work_struct *work)
 		/* All active slaves need to receive the event */
 		if (slave == ALL_SLAVES) {
 			for (i = 0; i <= dev->persist->num_vfs; i++) {
+				phys_port = 0;
+				if (eqe->type == MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT &&
+				    eqe->subtype == MLX4_DEV_PMC_SUBTYPE_PORT_INFO) {
+					phys_port  = eqe->event.port_mgmt_change.port;
+					slave_port = mlx4_phys_to_slave_port(dev, i, phys_port);
+					if (slave_port < 0) /* VF doesn't have this port */
+						continue;
+					eqe->event.port_mgmt_change.port = slave_port;
+				}
 				if (mlx4_GEN_EQE(dev, i, eqe))
 					mlx4_warn(dev, "Failed to generate event for slave %d\n",
 						  i);
+				if (phys_port)
+					eqe->event.port_mgmt_change.port = phys_port;
 			}
 		} else {
 			if (mlx4_GEN_EQE(dev, slave, eqe))
@@ -210,6 +221,22 @@ static void mlx4_slave_event(struct mlx4_dev *dev, int slave,
 	slave_event(dev, slave, eqe);
 }
 
+#if defined(CONFIG_SMP)
+static void mlx4_set_eq_affinity_hint(struct mlx4_priv *priv, int vec)
+{
+	int hint_err;
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_eq *eq = &priv->eq_table.eq[vec];
+
+	if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask))
+		return;
+
+	hint_err = irq_set_affinity_hint(eq->irq, eq->affinity_mask);
+	if (hint_err)
+		mlx4_warn(dev, "irq_set_affinity_hint failed, err %d\n", hint_err);
+}
+#endif
+
 int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port)
 {
 	struct mlx4_eqe eqe;
@@ -224,7 +251,7 @@ int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port)
 
 	eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT;
 	eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE;
-	eqe.event.port_mgmt_change.port = port;
+	eqe.event.port_mgmt_change.port = mlx4_phys_to_slave_port(dev, slave, port);
 
 	return mlx4_GEN_EQE(dev, slave, &eqe);
 }
@@ -241,7 +268,7 @@ int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port)
 
 	eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT;
 	eqe.subtype = MLX4_DEV_PMC_SUBTYPE_GUID_INFO;
-	eqe.event.port_mgmt_change.port = port;
+	eqe.event.port_mgmt_change.port = mlx4_phys_to_slave_port(dev, slave, port);
 
 	return mlx4_GEN_EQE(dev, slave, &eqe);
 }
@@ -251,6 +278,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port,
 				   u8 port_subtype_change)
 {
 	struct mlx4_eqe eqe;
+	u8 slave_port = mlx4_phys_to_slave_port(dev, slave, port);
 
 	/*don't send if we don't have the that slave */
 	if (dev->persist->num_vfs < slave)
@@ -259,7 +287,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port,
 
 	eqe.type = MLX4_EVENT_TYPE_PORT_CHANGE;
 	eqe.subtype = port_subtype_change;
-	eqe.event.port_change.port = cpu_to_be32(port << 28);
+	eqe.event.port_change.port = cpu_to_be32(slave_port << 28);
 
 	mlx4_dbg(dev, "%s: sending: %d to slave: %d on port: %d\n", __func__,
 		 port_subtype_change, slave, port);
@@ -589,6 +617,10 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						if (SLAVE_PORT_GEN_EVENT_DOWN ==  gen_event) {
 							if (i == mlx4_master_func_num(dev))
 								continue;
+							eqe->event.port_change.port =
+								cpu_to_be32(
+								(be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF)
+								| (mlx4_phys_to_slave_port(dev, i, port) << 28));
 							mlx4_slave_event(dev, i, eqe);
 						}
 					}
@@ -879,8 +911,8 @@ static int mlx4_num_eq_uar(struct mlx4_dev *dev)
 	 * we need to map, take the difference of highest index and
 	 * the lowest index we'll use and add 1.
 	 */
-	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs +
-		 dev->caps.comp_pool)/4 - dev->caps.reserved_eqs/4 + 1;
+	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs) / 4 -
+		dev->caps.reserved_eqs / 4 + 1;
 }
 
 static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
@@ -1069,32 +1101,21 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 static void mlx4_free_irqs(struct mlx4_dev *dev)
 {
 	struct mlx4_eq_table *eq_table = &mlx4_priv(dev)->eq_table;
-	struct mlx4_priv *priv = mlx4_priv(dev);
-	int	i, vec;
+	int	i;
 
 	if (eq_table->have_irq)
 		free_irq(dev->persist->pdev->irq, dev);
 
 	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
 		if (eq_table->eq[i].have_irq) {
+			free_cpumask_var(eq_table->eq[i].affinity_mask);
+#if defined(CONFIG_SMP)
+			irq_set_affinity_hint(eq_table->eq[i].irq, NULL);
+#endif
 			free_irq(eq_table->eq[i].irq, eq_table->eq + i);
 			eq_table->eq[i].have_irq = 0;
 		}
 
-	for (i = 0; i < dev->caps.comp_pool; i++) {
-		/*
-		 * Freeing the assigned irq's
-		 * all bits should be 0, but we need to validate
-		 */
-		if (priv->msix_ctl.pool_bm & 1ULL << i) {
-			/* NO need protecting*/
-			vec = dev->caps.num_comp_vectors + 1 + i;
-			free_irq(priv->eq_table.eq[vec].irq,
-				 &priv->eq_table.eq[vec]);
-		}
-	}
-
-
 	kfree(eq_table->irq_names);
 }
 
@@ -1175,76 +1196,73 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	}
 
 	priv->eq_table.irq_names =
-		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 +
-					     dev->caps.comp_pool),
+		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1),
 			GFP_KERNEL);
 	if (!priv->eq_table.irq_names) {
 		err = -ENOMEM;
-		goto err_out_bitmap;
+		goto err_out_clr_int;
 	}
 
-	for (i = 0; i < dev->caps.num_comp_vectors; ++i) {
-		err = mlx4_create_eq(dev, dev->caps.num_cqs -
-					  dev->caps.reserved_cqs +
-					  MLX4_NUM_SPARE_EQE,
-				     (dev->flags & MLX4_FLAG_MSI_X) ? i : 0,
-				     &priv->eq_table.eq[i]);
-		if (err) {
-			--i;
-			goto err_out_unmap;
-		}
-	}
-
-	err = mlx4_create_eq(dev, MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE,
-			     (dev->flags & MLX4_FLAG_MSI_X) ? dev->caps.num_comp_vectors : 0,
-			     &priv->eq_table.eq[dev->caps.num_comp_vectors]);
-	if (err)
-		goto err_out_comp;
-
-	/*if additional completion vectors poolsize is 0 this loop will not run*/
-	for (i = dev->caps.num_comp_vectors + 1;
-	      i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) {
+	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) {
+		if (i == MLX4_EQ_ASYNC) {
+			err = mlx4_create_eq(dev,
+					     MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE,
+					     0, &priv->eq_table.eq[MLX4_EQ_ASYNC]);
+		} else {
+			struct mlx4_eq	*eq = &priv->eq_table.eq[i];
+#ifdef CONFIG_RFS_ACCEL
+			int port = find_first_bit(eq->actv_ports.ports,
+						  dev->caps.num_ports) + 1;
+
+			if (port <= dev->caps.num_ports) {
+				struct mlx4_port_info *info =
+					&mlx4_priv(dev)->port[port];
+
+				if (!info->rmap) {
+					info->rmap = alloc_irq_cpu_rmap(
+						mlx4_get_eqs_per_port(dev, port));
+					if (!info->rmap) {
+						mlx4_warn(dev, "Failed to allocate cpu rmap\n");
+						err = -ENOMEM;
+						goto err_out_unmap;
+					}
+				}
 
-		err = mlx4_create_eq(dev, dev->caps.num_cqs -
-					  dev->caps.reserved_cqs +
-					  MLX4_NUM_SPARE_EQE,
-				     (dev->flags & MLX4_FLAG_MSI_X) ? i : 0,
-				     &priv->eq_table.eq[i]);
-		if (err) {
-			--i;
-			goto err_out_unmap;
+				err = irq_cpu_rmap_add(
+					info->rmap, eq->irq);
+				if (err)
+					mlx4_warn(dev, "Failed adding irq rmap\n");
+			}
+#endif
+			err = mlx4_create_eq(dev, dev->caps.num_cqs -
+						  dev->caps.reserved_cqs +
+						  MLX4_NUM_SPARE_EQE,
+					     (dev->flags & MLX4_FLAG_MSI_X) ?
+					     i + 1 - !!(i > MLX4_EQ_ASYNC) : 0,
+					     eq);
 		}
+		if (err)
+			goto err_out_unmap;
 	}
 
-
 	if (dev->flags & MLX4_FLAG_MSI_X) {
 		const char *eq_name;
 
-		for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) {
-			if (i < dev->caps.num_comp_vectors) {
-				snprintf(priv->eq_table.irq_names +
-					 i * MLX4_IRQNAME_SIZE,
-					 MLX4_IRQNAME_SIZE,
-					 "mlx4-comp-%d@pci:%s", i,
-					 pci_name(dev->persist->pdev));
-			} else {
-				snprintf(priv->eq_table.irq_names +
-					 i * MLX4_IRQNAME_SIZE,
-					 MLX4_IRQNAME_SIZE,
-					 "mlx4-async@pci:%s",
-					 pci_name(dev->persist->pdev));
-			}
+		snprintf(priv->eq_table.irq_names +
+			 MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE,
+			 MLX4_IRQNAME_SIZE,
+			 "mlx4-async@pci:%s",
+			 pci_name(dev->persist->pdev));
+		eq_name = priv->eq_table.irq_names +
+			MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE;
 
-			eq_name = priv->eq_table.irq_names +
-				  i * MLX4_IRQNAME_SIZE;
-			err = request_irq(priv->eq_table.eq[i].irq,
-					  mlx4_msi_x_interrupt, 0, eq_name,
-					  priv->eq_table.eq + i);
-			if (err)
-				goto err_out_async;
+		err = request_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq,
+				  mlx4_msi_x_interrupt, 0, eq_name,
+				  priv->eq_table.eq + MLX4_EQ_ASYNC);
+		if (err)
+			goto err_out_unmap;
 
-			priv->eq_table.eq[i].have_irq = 1;
-		}
+		priv->eq_table.eq[MLX4_EQ_ASYNC].have_irq = 1;
 	} else {
 		snprintf(priv->eq_table.irq_names,
 			 MLX4_IRQNAME_SIZE,
@@ -1253,36 +1271,38 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		err = request_irq(dev->persist->pdev->irq, mlx4_interrupt,
 				  IRQF_SHARED, priv->eq_table.irq_names, dev);
 		if (err)
-			goto err_out_async;
+			goto err_out_unmap;
 
 		priv->eq_table.have_irq = 1;
 	}
 
 	err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
-			  priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
+			  priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
 	if (err)
 		mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n",
-			   priv->eq_table.eq[dev->caps.num_comp_vectors].eqn, err);
+			   priv->eq_table.eq[MLX4_EQ_ASYNC].eqn, err);
 
-	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
-		eq_set_ci(&priv->eq_table.eq[i], 1);
+	/* arm ASYNC eq */
+	eq_set_ci(&priv->eq_table.eq[MLX4_EQ_ASYNC], 1);
 
 	return 0;
 
-err_out_async:
-	mlx4_free_eq(dev, &priv->eq_table.eq[dev->caps.num_comp_vectors]);
-
-err_out_comp:
-	i = dev->caps.num_comp_vectors - 1;
-
 err_out_unmap:
-	while (i >= 0) {
-		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
-		--i;
+	while (i >= 0)
+		mlx4_free_eq(dev, &priv->eq_table.eq[i--]);
+#ifdef CONFIG_RFS_ACCEL
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		if (mlx4_priv(dev)->port[i].rmap) {
+			free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap);
+			mlx4_priv(dev)->port[i].rmap = NULL;
+		}
 	}
+#endif
+	mlx4_free_irqs(dev);
+
+err_out_clr_int:
 	if (!mlx4_is_slave(dev))
 		mlx4_unmap_clr_int(dev);
-	mlx4_free_irqs(dev);
 
 err_out_bitmap:
 	mlx4_unmap_uar(dev);
@@ -1300,11 +1320,19 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 	int i;
 
 	mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 1,
-		    priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
+		    priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
 
+#ifdef CONFIG_RFS_ACCEL
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		if (mlx4_priv(dev)->port[i].rmap) {
+			free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap);
+			mlx4_priv(dev)->port[i].rmap = NULL;
+		}
+	}
+#endif
 	mlx4_free_irqs(dev);
 
-	for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i)
+	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
 
 	if (!mlx4_is_slave(dev))
@@ -1355,87 +1383,169 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 
 	/* Return to default */
 	mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
-		    priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
+		    priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
 	return err;
 }
 EXPORT_SYMBOL(mlx4_test_interrupts);
 
-int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector)
+bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector)
 {
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	vector = MLX4_CQ_TO_EQ_VECTOR(vector);
+	if (vector < 0 || (vector >= dev->caps.num_comp_vectors + 1) ||
+	    (vector == MLX4_EQ_ASYNC))
+		return false;
+
+	return test_bit(port - 1, priv->eq_table.eq[vector].actv_ports.ports);
+}
+EXPORT_SYMBOL(mlx4_is_eq_vector_valid);
 
+u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port)
+{
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int vec = 0, err = 0, i;
+	unsigned int i;
+	unsigned int sum = 0;
+
+	for (i = 0; i < dev->caps.num_comp_vectors + 1; i++)
+		sum += !!test_bit(port - 1,
+				  priv->eq_table.eq[i].actv_ports.ports);
+
+	return sum;
+}
+EXPORT_SYMBOL(mlx4_get_eqs_per_port);
+
+int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	vector = MLX4_CQ_TO_EQ_VECTOR(vector);
+	if (vector <= 0 || (vector >= dev->caps.num_comp_vectors + 1))
+		return -EINVAL;
+
+	return !!(bitmap_weight(priv->eq_table.eq[vector].actv_ports.ports,
+				dev->caps.num_ports) > 1);
+}
+EXPORT_SYMBOL(mlx4_is_eq_shared);
+
+struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port)
+{
+	return mlx4_priv(dev)->port[port].rmap;
+}
+EXPORT_SYMBOL(mlx4_get_cpu_rmap);
+
+int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int err = 0, i = 0;
+	u32 min_ref_count_val = (u32)-1;
+	int requested_vector = MLX4_CQ_TO_EQ_VECTOR(*vector);
+	int *prequested_vector = NULL;
+
 
 	mutex_lock(&priv->msix_ctl.pool_lock);
-	for (i = 0; !vec && i < dev->caps.comp_pool; i++) {
-		if (~priv->msix_ctl.pool_bm & 1ULL << i) {
-			priv->msix_ctl.pool_bm |= 1ULL << i;
-			vec = dev->caps.num_comp_vectors + 1 + i;
-			snprintf(priv->eq_table.irq_names +
-					vec * MLX4_IRQNAME_SIZE,
-					MLX4_IRQNAME_SIZE, "%s", name);
-#ifdef CONFIG_RFS_ACCEL
-			if (rmap) {
-				err = irq_cpu_rmap_add(rmap,
-						       priv->eq_table.eq[vec].irq);
-				if (err)
-					mlx4_warn(dev, "Failed adding irq rmap\n");
+	if (requested_vector < (dev->caps.num_comp_vectors + 1) &&
+	    (requested_vector >= 0) &&
+	    (requested_vector != MLX4_EQ_ASYNC)) {
+		if (test_bit(port - 1,
+			     priv->eq_table.eq[requested_vector].actv_ports.ports)) {
+			prequested_vector = &requested_vector;
+		} else {
+			struct mlx4_eq *eq;
+
+			for (i = 1; i < port;
+			     requested_vector += mlx4_get_eqs_per_port(dev, i++))
+				;
+
+			eq = &priv->eq_table.eq[requested_vector];
+			if (requested_vector < dev->caps.num_comp_vectors + 1 &&
+			    test_bit(port - 1, eq->actv_ports.ports)) {
+				prequested_vector = &requested_vector;
 			}
-#endif
-			err = request_irq(priv->eq_table.eq[vec].irq,
-					  mlx4_msi_x_interrupt, 0,
-					  &priv->eq_table.irq_names[vec<<5],
-					  priv->eq_table.eq + vec);
-			if (err) {
-				/*zero out bit by fliping it*/
-				priv->msix_ctl.pool_bm ^= 1 << i;
-				vec = 0;
-				continue;
-				/*we dont want to break here*/
+		}
+	}
+
+	if  (!prequested_vector) {
+		requested_vector = -1;
+		for (i = 0; min_ref_count_val && i < dev->caps.num_comp_vectors + 1;
+		     i++) {
+			struct mlx4_eq *eq = &priv->eq_table.eq[i];
+
+			if (min_ref_count_val > eq->ref_count &&
+			    test_bit(port - 1, eq->actv_ports.ports)) {
+				min_ref_count_val = eq->ref_count;
+				requested_vector = i;
 			}
+		}
+
+		if (requested_vector < 0) {
+			err = -ENOSPC;
+			goto err_unlock;
+		}
+
+		prequested_vector = &requested_vector;
+	}
+
+	if (!test_bit(*prequested_vector, priv->msix_ctl.pool_bm) &&
+	    dev->flags & MLX4_FLAG_MSI_X) {
+		set_bit(*prequested_vector, priv->msix_ctl.pool_bm);
+		snprintf(priv->eq_table.irq_names +
+			 *prequested_vector * MLX4_IRQNAME_SIZE,
+			 MLX4_IRQNAME_SIZE, "mlx4-%d@%s",
+			 *prequested_vector, dev_name(&dev->persist->pdev->dev));
 
-			eq_set_ci(&priv->eq_table.eq[vec], 1);
+		err = request_irq(priv->eq_table.eq[*prequested_vector].irq,
+				  mlx4_msi_x_interrupt, 0,
+				  &priv->eq_table.irq_names[*prequested_vector << 5],
+				  priv->eq_table.eq + *prequested_vector);
+
+		if (err) {
+			clear_bit(*prequested_vector, priv->msix_ctl.pool_bm);
+			*prequested_vector = -1;
+		} else {
+#if defined(CONFIG_SMP)
+			mlx4_set_eq_affinity_hint(priv, *prequested_vector);
+#endif
+			eq_set_ci(&priv->eq_table.eq[*prequested_vector], 1);
+			priv->eq_table.eq[*prequested_vector].have_irq = 1;
 		}
 	}
+
+	if (!err && *prequested_vector >= 0)
+		priv->eq_table.eq[*prequested_vector].ref_count++;
+
+err_unlock:
 	mutex_unlock(&priv->msix_ctl.pool_lock);
 
-	if (vec) {
-		*vector = vec;
-	} else {
+	if (!err && *prequested_vector >= 0)
+		*vector = MLX4_EQ_TO_CQ_VECTOR(*prequested_vector);
+	else
 		*vector = 0;
-		err = (i == dev->caps.comp_pool) ? -ENOSPC : err;
-	}
+
 	return err;
 }
 EXPORT_SYMBOL(mlx4_assign_eq);
 
-int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec)
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int cq_vec)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	return priv->eq_table.eq[vec].irq;
+	return priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq_vec)].irq;
 }
 EXPORT_SYMBOL(mlx4_eq_get_irq);
 
 void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	/*bm index*/
-	int i = vec - dev->caps.num_comp_vectors - 1;
-
-	if (likely(i >= 0)) {
-		/*sanity check , making sure were not trying to free irq's
-		  Belonging to a legacy EQ*/
-		mutex_lock(&priv->msix_ctl.pool_lock);
-		if (priv->msix_ctl.pool_bm & 1ULL << i) {
-			free_irq(priv->eq_table.eq[vec].irq,
-				 &priv->eq_table.eq[vec]);
-			priv->msix_ctl.pool_bm &= ~(1ULL << i);
-		}
-		mutex_unlock(&priv->msix_ctl.pool_lock);
-	}
+	int eq_vec = MLX4_CQ_TO_EQ_VECTOR(vec);
 
+	mutex_lock(&priv->msix_ctl.pool_lock);
+	priv->eq_table.eq[eq_vec].ref_count--;
+
+	/* once we allocated EQ, we don't release it because it might be binded
+	 * to cpu_rmap.
+	 */
+	mutex_unlock(&priv->msix_ctl.pool_lock);
 }
 EXPORT_SYMBOL(mlx4_release_eq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index ced5ecab5aa7..12fbfcb44d8a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -479,7 +479,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
-	dev->caps.max_counters = 1 << ilog2(dev_cap->max_counters);
+	if (mlx4_is_master(dev) && (dev->caps.num_ports == 2) &&
+	    (port_type_array[0] == MLX4_PORT_TYPE_IB) &&
+	    (port_type_array[1] == MLX4_PORT_TYPE_ETH)) {
+		mlx4_warn(dev,
+			  "Granular QoS per VF not supported with IB/Eth configuration\n");
+		dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_QOS_VPP;
+	}
+
+	dev->caps.max_counters = dev_cap->max_counters;
 
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
@@ -1674,6 +1682,25 @@ static int map_internal_clock(struct mlx4_dev *dev)
 	return 0;
 }
 
+int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
+				   struct mlx4_clock_params *params)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (mlx4_is_slave(dev))
+		return -ENOTSUPP;
+
+	if (!params)
+		return -EINVAL;
+
+	params->bar = priv->fw.clock_bar;
+	params->offset = priv->fw.clock_offset;
+	params->size = MLX4_CLOCK_SIZE;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_internal_clock_params);
+
 static void unmap_internal_clock(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2193,20 +2220,73 @@ err_free_icm:
 static int mlx4_init_counters_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int nent;
+	int nent_pow2;
 
 	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
 		return -ENOENT;
 
-	nent = dev->caps.max_counters;
-	return mlx4_bitmap_init(&priv->counters_bitmap, nent, nent - 1, 0, 0);
+	if (!dev->caps.max_counters)
+		return -ENOSPC;
+
+	nent_pow2 = roundup_pow_of_two(dev->caps.max_counters);
+	/* reserve last counter index for sink counter */
+	return mlx4_bitmap_init(&priv->counters_bitmap, nent_pow2,
+				nent_pow2 - 1, 0,
+				nent_pow2 - dev->caps.max_counters + 1);
 }
 
 static void mlx4_cleanup_counters_table(struct mlx4_dev *dev)
 {
+	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
+		return;
+
+	if (!dev->caps.max_counters)
+		return;
+
 	mlx4_bitmap_cleanup(&mlx4_priv(dev)->counters_bitmap);
 }
 
+static void mlx4_cleanup_default_counters(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int port;
+
+	for (port = 0; port < dev->caps.num_ports; port++)
+		if (priv->def_counter[port] != -1)
+			mlx4_counter_free(dev,  priv->def_counter[port]);
+}
+
+static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int port, err = 0;
+	u32 idx;
+
+	for (port = 0; port < dev->caps.num_ports; port++)
+		priv->def_counter[port] = -1;
+
+	for (port = 0; port < dev->caps.num_ports; port++) {
+		err = mlx4_counter_alloc(dev, &idx);
+
+		if (!err || err == -ENOSPC) {
+			priv->def_counter[port] = idx;
+		} else if (err == -ENOENT) {
+			err = 0;
+			continue;
+		} else {
+			mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
+				 __func__, port + 1, err);
+			mlx4_cleanup_default_counters(dev);
+			return err;
+		}
+
+		mlx4_dbg(dev, "%s: default counter index %d for port %d\n",
+			 __func__, priv->def_counter[port], port + 1);
+	}
+
+	return err;
+}
+
 int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2215,8 +2295,10 @@ int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
 		return -ENOENT;
 
 	*idx = mlx4_bitmap_alloc(&priv->counters_bitmap);
-	if (*idx == -1)
-		return -ENOMEM;
+	if (*idx == -1) {
+		*idx = MLX4_SINK_COUNTER_INDEX(dev);
+		return -ENOSPC;
+	}
 
 	return 0;
 }
@@ -2239,8 +2321,35 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx)
 }
 EXPORT_SYMBOL_GPL(mlx4_counter_alloc);
 
+static int __mlx4_clear_if_stat(struct mlx4_dev *dev,
+				u8 counter_index)
+{
+	struct mlx4_cmd_mailbox *if_stat_mailbox;
+	int err;
+	u32 if_stat_in_mod = (counter_index & 0xff) | MLX4_QUERY_IF_STAT_RESET;
+
+	if_stat_mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(if_stat_mailbox))
+		return PTR_ERR(if_stat_mailbox);
+
+	err = mlx4_cmd_box(dev, 0, if_stat_mailbox->dma, if_stat_in_mod, 0,
+			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, if_stat_mailbox);
+	return err;
+}
+
 void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
 {
+	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS))
+		return;
+
+	if (idx == MLX4_SINK_COUNTER_INDEX(dev))
+		return;
+
+	__mlx4_clear_if_stat(dev, idx);
+
 	mlx4_bitmap_free(&mlx4_priv(dev)->counters_bitmap, idx, MLX4_USE_RR);
 	return;
 }
@@ -2260,6 +2369,14 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
 }
 EXPORT_SYMBOL_GPL(mlx4_counter_free);
 
+int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return priv->def_counter[port - 1];
+}
+EXPORT_SYMBOL_GPL(mlx4_get_default_counter_index);
+
 void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2364,11 +2481,11 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 	if (err) {
 		if (dev->flags & MLX4_FLAG_MSI_X) {
 			mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n",
-				  priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
+				  priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 			mlx4_warn(dev, "Trying again without MSI-X\n");
 		} else {
 			mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n",
-				 priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
+				 priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
 			mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n");
 		}
 
@@ -2395,10 +2512,18 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 		goto err_srq_table_free;
 	}
 
-	err = mlx4_init_counters_table(dev);
-	if (err && err != -ENOENT) {
-		mlx4_err(dev, "Failed to initialize counters table, aborting\n");
-		goto err_qp_table_free;
+	if (!mlx4_is_slave(dev)) {
+		err = mlx4_init_counters_table(dev);
+		if (err && err != -ENOENT) {
+			mlx4_err(dev, "Failed to initialize counters table, aborting\n");
+			goto err_qp_table_free;
+		}
+	}
+
+	err = mlx4_allocate_default_counters(dev);
+	if (err) {
+		mlx4_err(dev, "Failed to allocate default counters, aborting\n");
+		goto err_counters_table_free;
 	}
 
 	if (!mlx4_is_slave(dev)) {
@@ -2432,15 +2557,19 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 			if (err) {
 				mlx4_err(dev, "Failed to set port %d, aborting\n",
 					 port);
-				goto err_counters_table_free;
+				goto err_default_countes_free;
 			}
 		}
 	}
 
 	return 0;
 
+err_default_countes_free:
+	mlx4_cleanup_default_counters(dev);
+
 err_counters_table_free:
-	mlx4_cleanup_counters_table(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_cleanup_counters_table(dev);
 
 err_qp_table_free:
 	mlx4_cleanup_qp_table(dev);
@@ -2481,14 +2610,45 @@ err_uar_table_free:
 	return err;
 }
 
+static int mlx4_init_affinity_hint(struct mlx4_dev *dev, int port, int eqn)
+{
+	int requested_cpu = 0;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_eq *eq;
+	int off = 0;
+	int i;
+
+	if (eqn > dev->caps.num_comp_vectors)
+		return -EINVAL;
+
+	for (i = 1; i < port; i++)
+		off += mlx4_get_eqs_per_port(dev, i);
+
+	requested_cpu = eqn - off - !!(eqn > MLX4_EQ_ASYNC);
+
+	/* Meaning EQs are shared, and this call comes from the second port */
+	if (requested_cpu < 0)
+		return 0;
+
+	eq = &priv->eq_table.eq[eqn];
+
+	if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_set_cpu(requested_cpu, eq->affinity_mask);
+
+	return 0;
+}
+
 static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct msix_entry *entries;
 	int i;
+	int port = 0;
 
 	if (msi_x) {
-		int nreq = dev->caps.num_ports * num_online_cpus() + MSIX_LEGACY_SZ;
+		int nreq = dev->caps.num_ports * num_online_cpus() + 1;
 
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
 			     nreq);
@@ -2503,20 +2663,55 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 		nreq = pci_enable_msix_range(dev->persist->pdev, entries, 2,
 					     nreq);
 
-		if (nreq < 0) {
+		if (nreq < 0 || nreq < MLX4_EQ_ASYNC) {
 			kfree(entries);
 			goto no_msi;
-		} else if (nreq < MSIX_LEGACY_SZ +
-			   dev->caps.num_ports * MIN_MSIX_P_PORT) {
-			/*Working in legacy mode , all EQ's shared*/
-			dev->caps.comp_pool           = 0;
-			dev->caps.num_comp_vectors = nreq - 1;
-		} else {
-			dev->caps.comp_pool           = nreq - MSIX_LEGACY_SZ;
-			dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1;
 		}
-		for (i = 0; i < nreq; ++i)
-			priv->eq_table.eq[i].irq = entries[i].vector;
+		/* 1 is reserved for events (asyncrounous EQ) */
+		dev->caps.num_comp_vectors = nreq - 1;
+
+		priv->eq_table.eq[MLX4_EQ_ASYNC].irq = entries[0].vector;
+		bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
+			    dev->caps.num_ports);
+
+		for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
+			if (i == MLX4_EQ_ASYNC)
+				continue;
+
+			priv->eq_table.eq[i].irq =
+				entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;
+
+			if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
+				bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
+					    dev->caps.num_ports);
+				/* We don't set affinity hint when there
+				 * aren't enough EQs
+				 */
+			} else {
+				set_bit(port,
+					priv->eq_table.eq[i].actv_ports.ports);
+				if (mlx4_init_affinity_hint(dev, port + 1, i))
+					mlx4_warn(dev, "Couldn't init hint cpumask for EQ %d\n",
+						  i);
+			}
+			/* We divide the Eqs evenly between the two ports.
+			 * (dev->caps.num_comp_vectors / dev->caps.num_ports)
+			 * refers to the number of Eqs per port
+			 * (i.e eqs_per_port). Theoretically, we would like to
+			 * write something like (i + 1) % eqs_per_port == 0.
+			 * However, since there's an asynchronous Eq, we have
+			 * to skip over it by comparing this condition to
+			 * !!((i + 1) > MLX4_EQ_ASYNC).
+			 */
+			if ((dev->caps.num_comp_vectors > dev->caps.num_ports) &&
+			    ((i + 1) %
+			     (dev->caps.num_comp_vectors / dev->caps.num_ports)) ==
+			    !!((i + 1) > MLX4_EQ_ASYNC))
+				/* If dev->caps.num_comp_vectors < dev->caps.num_ports,
+				 * everything is shared anyway.
+				 */
+				port++;
+		}
 
 		dev->flags |= MLX4_FLAG_MSI_X;
 
@@ -2526,10 +2721,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 no_msi:
 	dev->caps.num_comp_vectors = 1;
-	dev->caps.comp_pool	   = 0;
 
-	for (i = 0; i < 2; ++i)
+	BUG_ON(MLX4_EQ_ASYNC >= 2);
+	for (i = 0; i < 2; ++i) {
 		priv->eq_table.eq[i].irq = dev->persist->pdev->irq;
+		if (i != MLX4_EQ_ASYNC) {
+			bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
+				    dev->caps.num_ports);
+		}
+	}
 }
 
 static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
@@ -2594,6 +2794,10 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
 	device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr);
 	device_remove_file(&info->dev->persist->pdev->dev,
 			   &info->port_mtu_attr);
+#ifdef CONFIG_RFS_ACCEL
+	free_irq_cpu_rmap(info->rmap);
+	info->rmap = NULL;
+#endif
 }
 
 static int mlx4_init_steering(struct mlx4_dev *dev)
@@ -2749,6 +2953,7 @@ disable_sriov:
 free_mem:
 	dev->persist->num_vfs = 0;
 	kfree(dev->dev_vfs);
+        dev->dev_vfs = NULL;
 	return dev_flags & ~MLX4_FLAG_MASTER;
 }
 
@@ -2900,6 +3105,7 @@ slave_start:
 								  existing_vfs,
 								  reset_flow);
 
+				mlx4_close_fw(dev);
 				mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
 				dev->flags = dev_flags;
 				if (!SRIOV_VALID_STATE(dev->flags)) {
@@ -2988,18 +3194,6 @@ slave_start:
 	/* In master functions, the communication channel must be initialized
 	 * after obtaining its address from fw */
 	if (mlx4_is_master(dev)) {
-		int ib_ports = 0;
-
-		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
-			ib_ports++;
-
-		if (ib_ports &&
-		    (num_vfs_argc > 1 || probe_vfs_argc > 1)) {
-			mlx4_err(dev,
-				 "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n");
-			err = -EINVAL;
-			goto err_close;
-		}
 		if (dev->caps.num_ports < 2 &&
 		    num_vfs_argc > 1) {
 			err = -EINVAL;
@@ -3036,7 +3230,7 @@ slave_start:
 	if (err)
 		goto err_master_mfunc;
 
-	priv->msix_ctl.pool_bm = 0;
+	bitmap_zero(priv->msix_ctl.pool_bm, MAX_MSIX);
 	mutex_init(&priv->msix_ctl.pool_lock);
 
 	mlx4_enable_msi_x(dev);
@@ -3058,7 +3252,6 @@ slave_start:
 	    !mlx4_is_mfunc(dev)) {
 		dev->flags &= ~MLX4_FLAG_MSI_X;
 		dev->caps.num_comp_vectors = 1;
-		dev->caps.comp_pool	   = 0;
 		pci_disable_msix(pdev);
 		err = mlx4_setup_hca(dev);
 	}
@@ -3109,7 +3302,9 @@ err_port:
 	for (--port; port >= 1; --port)
 		mlx4_cleanup_port_info(&priv->port[port]);
 
-	mlx4_cleanup_counters_table(dev);
+	mlx4_cleanup_default_counters(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_cleanup_counters_table(dev);
 	mlx4_cleanup_qp_table(dev);
 	mlx4_cleanup_srq_table(dev);
 	mlx4_cleanup_cq_table(dev);
@@ -3407,7 +3602,9 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 		mlx4_free_resource_tracker(dev,
 					   RES_TR_FREE_SLAVES_ONLY);
 
-	mlx4_cleanup_counters_table(dev);
+	mlx4_cleanup_default_counters(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_cleanup_counters_table(dev);
 	mlx4_cleanup_qp_table(dev);
 	mlx4_cleanup_srq_table(dev);
 	mlx4_cleanup_cq_table(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 502d3dd2c888..a092c5c34d43 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -65,6 +65,8 @@
 
 #define INIT_HCA_TPT_MW_ENABLE          (1 << 7)
 
+#define MLX4_QUERY_IF_STAT_RESET	BIT(31)
+
 enum {
 	MLX4_HCR_BASE		= 0x80680,
 	MLX4_HCR_SIZE		= 0x0001c,
@@ -287,6 +289,12 @@ struct mlx4_icm_table {
 #define MLX4_CQE_SIZE_MASK_STRIDE	0x3
 #define MLX4_EQE_SIZE_MASK_STRIDE	0x30
 
+#define MLX4_EQ_ASYNC			0
+#define MLX4_EQ_TO_CQ_VECTOR(vector)	((vector) - \
+					 !!((int)(vector) >= MLX4_EQ_ASYNC))
+#define MLX4_CQ_TO_EQ_VECTOR(vector)	((vector) + \
+					 !!((int)(vector) >= MLX4_EQ_ASYNC))
+
 /*
  * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
  */
@@ -391,6 +399,9 @@ struct mlx4_eq {
 	struct mlx4_buf_list   *page_list;
 	struct mlx4_mtt		mtt;
 	struct mlx4_eq_tasklet	tasklet_ctx;
+	struct mlx4_active_ports actv_ports;
+	u32			ref_count;
+	cpumask_var_t		affinity_mask;
 };
 
 struct mlx4_slave_eqe {
@@ -808,6 +819,7 @@ struct mlx4_port_info {
 	struct mlx4_vlan_table	vlan_table;
 	struct mlx4_roce_gid_table gid_table;
 	int			base_qpn;
+	struct cpu_rmap		*rmap;
 };
 
 struct mlx4_sense {
@@ -818,7 +830,7 @@ struct mlx4_sense {
 };
 
 struct mlx4_msix_ctl {
-	u64		pool_bm;
+	DECLARE_BITMAP(pool_bm, MAX_MSIX);
 	struct mutex	pool_lock;
 };
 
@@ -864,6 +876,7 @@ struct mlx4_priv {
 	struct mlx4_qp_table	qp_table;
 	struct mlx4_mcg_table	mcg_table;
 	struct mlx4_bitmap	counters_bitmap;
+	int			def_counter[MLX4_MAX_PORTS];
 
 	struct mlx4_catas_err	catas_err;
 
@@ -997,6 +1010,8 @@ int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		     int start_index, int npages, u64 *page_list);
 int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
 void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
+int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port,
+			  struct mlx4_counter *data);
 int __mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn);
 void __mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index d021f079f181..d5f9adb6a784 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -338,7 +338,7 @@ struct mlx4_en_cq {
 	struct napi_struct	napi;
 	int size;
 	int buf_size;
-	unsigned vector;
+	int vector;
 	enum cq_type is_tx;
 	u16 moder_time;
 	u16 moder_cnt;
@@ -566,6 +566,7 @@ struct mlx4_en_priv {
 #endif
 	struct mlx4_en_perf_stats pstats;
 	struct mlx4_en_pkt_stats pkstats;
+	struct mlx4_en_counter_stats pf_stats;
 	struct mlx4_en_flow_stats_rx rx_priority_flowstats[MLX4_NUM_PRIORITIES];
 	struct mlx4_en_flow_stats_tx tx_priority_flowstats[MLX4_NUM_PRIORITIES];
 	struct mlx4_en_flow_stats_rx rx_flowstats;
@@ -582,6 +583,7 @@ struct mlx4_en_priv {
 	int base_tx_qpn;
 	struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE];
 	struct hwtstamp_config hwtstamp_config;
+	u32 counter_index;
 
 #ifdef CONFIG_MLX4_EN_DCB
 	struct ieee_ets ets;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
index 00555832a4ae..7fd466c0b929 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h
@@ -23,6 +23,14 @@ struct mlx4_en_pkt_stats {
 #define NUM_PKT_STATS		43
 };
 
+struct mlx4_en_counter_stats {
+	unsigned long rx_packets;
+	unsigned long rx_bytes;
+	unsigned long tx_packets;
+	unsigned long tx_bytes;
+#define NUM_PF_STATS      4
+};
+
 struct mlx4_en_port_stats {
 	unsigned long tso_packets;
 	unsigned long xmit_more;
@@ -99,7 +107,7 @@ enum {
 };
 
 #define NUM_ALL_STATS	(NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \
-			 NUM_FLOW_STATS + NUM_PERF_STATS)
+			 NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS)
 
 #define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \
 				  sizeof(((struct net_device_stats *)0)->n))
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 2bf437aafc53..bae8b22edbb7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -82,7 +82,6 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 
 	u64 total_size = 0;
 	struct mlx4_resource *profile;
-	struct mlx4_resource tmp;
 	struct sysinfo si;
 	int i, j;
 
@@ -149,11 +148,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	 */
 	for (i = MLX4_RES_NUM; i > 0; --i)
 		for (j = 1; j < i; ++j) {
-			if (profile[j].size > profile[j - 1].size) {
-				tmp	       = profile[j];
-				profile[j]     = profile[j - 1];
-				profile[j - 1] = tmp;
-			}
+			if (profile[j].size > profile[j - 1].size)
+				swap(profile[j], profile[j - 1]);
 		}
 
 	for (i = 0; i < MLX4_RES_NUM; ++i) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index b75214a80d0e..20268634a9ab 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -749,7 +749,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 
 	{
 		int sort[MLX4_NUM_QP_REGION];
-		int i, j, tmp;
+		int i, j;
 		int last_base = dev->caps.num_qps;
 
 		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
@@ -758,11 +758,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 		for (i = MLX4_NUM_QP_REGION; i > MLX4_QP_REGION_BOTTOM; --i) {
 			for (j = MLX4_QP_REGION_BOTTOM + 2; j < i; ++j) {
 				if (dev->caps.reserved_qps_cnt[sort[j]] >
-				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
-					tmp             = sort[j];
-					sort[j]         = sort[j - 1];
-					sort[j - 1]     = tmp;
-				}
+				    dev->caps.reserved_qps_cnt[sort[j - 1]])
+					swap(sort[j], sort[j - 1]);
 			}
 		}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index c7f28bf4b8e2..731423ca575d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -46,8 +46,11 @@
 
 #include "mlx4.h"
 #include "fw.h"
+#include "mlx4_stats.h"
 
 #define MLX4_MAC_VALID		(1ull << 63)
+#define MLX4_PF_COUNTERS_PER_PORT	2
+#define MLX4_VF_COUNTERS_PER_PORT	1
 
 struct mac_res {
 	struct list_head list;
@@ -459,11 +462,21 @@ void mlx4_init_quotas(struct mlx4_dev *dev)
 	dev->quotas.mpt =
 		priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf];
 }
+
+static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev)
+{
+	/* reduce the sink counter */
+	return (dev->caps.max_counters - 1 -
+		(MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS))
+		/ MLX4_MAX_PORTS;
+}
+
 int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, j;
 	int t;
+	int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev);
 
 	priv->mfunc.master.res_tracker.slave_list =
 		kzalloc(dev->num_slaves * sizeof(struct slave_list),
@@ -499,6 +512,9 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 			res_alloc->allocated = kzalloc((dev->persist->
 							num_vfs + 1) *
 						       sizeof(int), GFP_KERNEL);
+		/* Reduce the sink counter */
+		if (i == RES_COUNTER)
+			res_alloc->res_free = dev->caps.max_counters - 1;
 
 		if (!res_alloc->quota || !res_alloc->guaranteed ||
 		    !res_alloc->allocated)
@@ -577,9 +593,17 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			case RES_COUNTER:
 				res_alloc->quota[t] = dev->caps.max_counters;
-				res_alloc->guaranteed[t] = 0;
 				if (t == mlx4_master_func_num(dev))
-					res_alloc->res_free = res_alloc->quota[t];
+					res_alloc->guaranteed[t] =
+						MLX4_PF_COUNTERS_PER_PORT *
+						MLX4_MAX_PORTS;
+				else if (t <= max_vfs_guarantee_counter)
+					res_alloc->guaranteed[t] =
+						MLX4_VF_COUNTERS_PER_PORT *
+						MLX4_MAX_PORTS;
+				else
+					res_alloc->guaranteed[t] = 0;
+				res_alloc->res_free -= res_alloc->guaranteed[t];
 				break;
 			default:
 				break;
@@ -700,6 +724,9 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 	}
 }
 
+static int handle_counter(struct mlx4_dev *dev, struct mlx4_qp_context *qpc,
+			  u8 slave, int port);
+
 static int update_vport_qp_param(struct mlx4_dev *dev,
 				 struct mlx4_cmd_mailbox *inbox,
 				 u8 slave, u32 qpn)
@@ -715,6 +742,10 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 	qp_type	= (be32_to_cpu(qpc->flags) >> 16) & 0xff;
 
+	err = handle_counter(dev, qpc, slave, port);
+	if (err)
+		goto out;
+
 	if (MLX4_VGT != vp_oper->state.default_vlan) {
 		/* the reserved QPs (special, proxy, tunnel)
 		 * do not operate over vlans
@@ -859,6 +890,83 @@ static void put_res(struct mlx4_dev *dev, int slave, u64 res_id,
 	spin_unlock_irq(mlx4_tlock(dev));
 }
 
+static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			     u64 in_param, u64 *out_param, int port);
+
+static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port,
+				   int counter_index)
+{
+	struct res_common *r;
+	struct res_counter *counter;
+	int ret = 0;
+
+	if (counter_index == MLX4_SINK_COUNTER_INDEX(dev))
+		return ret;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = find_res(dev, counter_index, RES_COUNTER);
+	if (!r || r->owner != slave)
+		ret = -EINVAL;
+	counter = container_of(r, struct res_counter, com);
+	if (!counter->port)
+		counter->port = port;
+
+	spin_unlock_irq(mlx4_tlock(dev));
+	return ret;
+}
+
+static int handle_unexisting_counter(struct mlx4_dev *dev,
+				     struct mlx4_qp_context *qpc, u8 slave,
+				     int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_common *tmp;
+	struct res_counter *counter;
+	u64 counter_idx = MLX4_SINK_COUNTER_INDEX(dev);
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry(tmp,
+			    &tracker->slave_list[slave].res_list[RES_COUNTER],
+			    list) {
+		counter = container_of(tmp, struct res_counter, com);
+		if (port == counter->port) {
+			qpc->pri_path.counter_index  = counter->com.res_id;
+			spin_unlock_irq(mlx4_tlock(dev));
+			return 0;
+		}
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	/* No existing counter, need to allocate a new counter */
+	err = counter_alloc_res(dev, slave, RES_OP_RESERVE, 0, 0, &counter_idx,
+				port);
+	if (err == -ENOENT) {
+		err = 0;
+	} else if (err && err != -ENOSPC) {
+		mlx4_err(dev, "%s: failed to create new counter for slave %d err %d\n",
+			 __func__, slave, err);
+	} else {
+		qpc->pri_path.counter_index = counter_idx;
+		mlx4_dbg(dev, "%s: alloc new counter for slave %d index %d\n",
+			 __func__, slave, qpc->pri_path.counter_index);
+		err = 0;
+	}
+
+	return err;
+}
+
+static int handle_counter(struct mlx4_dev *dev, struct mlx4_qp_context *qpc,
+			  u8 slave, int port)
+{
+	if (qpc->pri_path.counter_index != MLX4_SINK_COUNTER_INDEX(dev))
+		return handle_existing_counter(dev, slave, port,
+					       qpc->pri_path.counter_index);
+
+	return handle_unexisting_counter(dev, qpc, slave, port);
+}
+
 static struct res_common *alloc_qp_tr(int id)
 {
 	struct res_qp *ret;
@@ -952,7 +1060,7 @@ static struct res_common *alloc_srq_tr(int id)
 	return &ret->com;
 }
 
-static struct res_common *alloc_counter_tr(int id)
+static struct res_common *alloc_counter_tr(int id, int port)
 {
 	struct res_counter *ret;
 
@@ -962,6 +1070,7 @@ static struct res_common *alloc_counter_tr(int id)
 
 	ret->com.res_id = id;
 	ret->com.state = RES_COUNTER_ALLOCATED;
+	ret->port = port;
 
 	return &ret->com;
 }
@@ -1022,7 +1131,7 @@ static struct res_common *alloc_tr(u64 id, enum mlx4_resource type, int slave,
 		pr_err("implementation missing\n");
 		return NULL;
 	case RES_COUNTER:
-		ret = alloc_counter_tr(id);
+		ret = alloc_counter_tr(id, extra);
 		break;
 	case RES_XRCD:
 		ret = alloc_xrcdn_tr(id);
@@ -1039,6 +1148,53 @@ static struct res_common *alloc_tr(u64 id, enum mlx4_resource type, int slave,
 	return ret;
 }
 
+int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port,
+			  struct mlx4_counter *data)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_common *tmp;
+	struct res_counter *counter;
+	int *counters_arr;
+	int i = 0, err = 0;
+
+	memset(data, 0, sizeof(*data));
+
+	counters_arr = kmalloc_array(dev->caps.max_counters,
+				     sizeof(*counters_arr), GFP_KERNEL);
+	if (!counters_arr)
+		return -ENOMEM;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry(tmp,
+			    &tracker->slave_list[slave].res_list[RES_COUNTER],
+			    list) {
+		counter = container_of(tmp, struct res_counter, com);
+		if (counter->port == port) {
+			counters_arr[i] = (int)tmp->res_id;
+			i++;
+		}
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+	counters_arr[i] = -1;
+
+	i = 0;
+
+	while (counters_arr[i] != -1) {
+		err = mlx4_get_counter_stats(dev, counters_arr[i], data,
+					     0);
+		if (err) {
+			memset(data, 0, sizeof(*data));
+			goto table_changed;
+		}
+		i++;
+	}
+
+table_changed:
+	kfree(counters_arr);
+	return 0;
+}
+
 static int add_res_range(struct mlx4_dev *dev, int slave, u64 base, int count,
 			 enum mlx4_resource type, int extra)
 {
@@ -2001,7 +2157,7 @@ static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 }
 
 static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
-			     u64 in_param, u64 *out_param)
+			     u64 in_param, u64 *out_param, int port)
 {
 	u32 index;
 	int err;
@@ -2019,7 +2175,7 @@ static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		return err;
 	}
 
-	err = add_res_range(dev, slave, index, 1, RES_COUNTER, 0);
+	err = add_res_range(dev, slave, index, 1, RES_COUNTER, port);
 	if (err) {
 		__mlx4_counter_free(dev, index);
 		mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0);
@@ -2101,7 +2257,7 @@ int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
 
 	case RES_COUNTER:
 		err = counter_alloc_res(dev, slave, vhcr->op_modifier, alop,
-					vhcr->in_param, &vhcr->out_param);
+					vhcr->in_param, &vhcr->out_param, 0);
 		break;
 
 	case RES_XRCD:
@@ -2335,6 +2491,9 @@ static int counter_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		return -EINVAL;
 
 	index = get_param_l(&in_param);
+	if (index == MLX4_SINK_COUNTER_INDEX(dev))
+		return 0;
+
 	err = rem_res_range(dev, slave, index, 1, RES_COUNTER, 0);
 	if (err)
 		return err;
@@ -2703,6 +2862,10 @@ static void adjust_proxy_tun_qkey(struct mlx4_dev *dev, struct mlx4_vhcr *vhcr,
 	context->qkey = cpu_to_be32(qkey);
 }
 
+static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave,
+				 struct mlx4_qp_context *qpc,
+				 struct mlx4_cmd_mailbox *inbox);
+
 int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 			     struct mlx4_vhcr *vhcr,
 			     struct mlx4_cmd_mailbox *inbox,
@@ -2725,6 +2888,10 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	struct res_srq *srq;
 	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
 
+	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
+	if (err)
+		return err;
+
 	err = qp_res_start_move_to(dev, slave, qpn, RES_QP_HW, &qp, 0);
 	if (err)
 		return err;
@@ -2845,7 +3012,7 @@ int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
 {
 	int err;
 	int eqn = vhcr->in_modifier;
-	int res_id = (slave << 8) | eqn;
+	int res_id = (slave << 10) | eqn;
 	struct mlx4_eq_context *eqc = inbox->buf;
 	int mtt_base = eq_get_mtt_addr(eqc) / dev->caps.mtt_entry_sz;
 	int mtt_size = eq_get_mtt_size(eqc);
@@ -3051,7 +3218,7 @@ int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_cmd_info *cmd)
 {
 	int eqn = vhcr->in_modifier;
-	int res_id = eqn | (slave << 8);
+	int res_id = eqn | (slave << 10);
 	struct res_eq *eq;
 	int err;
 
@@ -3108,7 +3275,7 @@ int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
 		return 0;
 
 	mutex_lock(&priv->mfunc.master.gen_eqe_mutex[slave]);
-	res_id = (slave << 8) | event_eq->eqn;
+	res_id = (slave << 10) | event_eq->eqn;
 	err = get_res(dev, slave, res_id, RES_EQ, &req);
 	if (err)
 		goto unlock;
@@ -3131,7 +3298,7 @@ int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
 
 	memcpy(mailbox->buf, (u8 *) eqe, 28);
 
-	in_modifier = (slave & 0xff) | ((event_eq->eqn & 0xff) << 16);
+	in_modifier = (slave & 0xff) | ((event_eq->eqn & 0x3ff) << 16);
 
 	err = mlx4_cmd(dev, mailbox->dma, in_modifier, 0,
 		       MLX4_CMD_GEN_EQE, MLX4_CMD_TIME_CLASS_B,
@@ -3157,7 +3324,7 @@ int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_cmd_info *cmd)
 {
 	int eqn = vhcr->in_modifier;
-	int res_id = eqn | (slave << 8);
+	int res_id = eqn | (slave << 10);
 	struct res_eq *eq;
 	int err;
 
@@ -3187,7 +3354,7 @@ int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
 	int cqn = vhcr->in_modifier;
 	struct mlx4_cq_context *cqc = inbox->buf;
 	int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
-	struct res_cq *cq;
+	struct res_cq *cq = NULL;
 	struct res_mtt *mtt;
 
 	err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq);
@@ -3223,7 +3390,7 @@ int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
 {
 	int err;
 	int cqn = vhcr->in_modifier;
-	struct res_cq *cq;
+	struct res_cq *cq = NULL;
 
 	err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq);
 	if (err)
@@ -3362,7 +3529,7 @@ int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	int srqn = vhcr->in_modifier;
 	struct res_mtt *mtt;
-	struct res_srq *srq;
+	struct res_srq *srq = NULL;
 	struct mlx4_srq_context *srqc = inbox->buf;
 	int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz;
 
@@ -3406,7 +3573,7 @@ int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
 {
 	int err;
 	int srqn = vhcr->in_modifier;
-	struct res_srq *srq;
+	struct res_srq *srq = NULL;
 
 	err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq);
 	if (err)
@@ -3526,8 +3693,8 @@ static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave,
 	pri_sched_queue = (qpc->pri_path.sched_queue & ~(1 << 6)) |
 			  ((port & 1) << 6);
 
-	if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH ||
-	    mlx4_is_eth(dev, port + 1)) {
+	if (optpar & (MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH | MLX4_QP_OPTPAR_SCHED_QUEUE) ||
+	    qpc->pri_path.sched_queue || mlx4_is_eth(dev, port + 1)) {
 		qpc->pri_path.sched_queue = pri_sched_queue;
 	}
 
@@ -3965,6 +4132,22 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header,
 	return 0;
 }
 
+static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
+					 struct _rule_hw *eth_header)
+{
+	if (is_multicast_ether_addr(eth_header->eth.dst_mac) ||
+	    is_broadcast_ether_addr(eth_header->eth.dst_mac)) {
+		struct mlx4_net_trans_rule_hw_eth *eth =
+			(struct mlx4_net_trans_rule_hw_eth *)eth_header;
+		struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1);
+		bool last_rule = next_rule->size == 0 && next_rule->id == 0 &&
+			next_rule->rsvd == 0;
+
+		if (last_rule)
+			ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC);
+	}
+}
+
 /*
  * In case of missing eth header, append eth header with a MAC address
  * assigned to the VF.
@@ -4117,6 +4300,12 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	rule_header = (struct _rule_hw *)(ctrl + 1);
 	header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id));
 
+	if (header_id == MLX4_NET_TRANS_RULE_ID_ETH)
+		handle_eth_header_mcast_prio(ctrl, rule_header);
+
+	if (slave == dev->caps.function)
+		goto execute;
+
 	switch (header_id) {
 	case MLX4_NET_TRANS_RULE_ID_ETH:
 		if (validate_eth_header_mac(slave, rule_header, rlist)) {
@@ -4143,6 +4332,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 		goto err_put;
 	}
 
+execute:
 	err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
 			   vhcr->in_modifier, 0,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
@@ -4714,13 +4904,13 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
 					break;
 
 				case RES_EQ_HW:
-					err = mlx4_cmd(dev, slave, eqn & 0xff,
+					err = mlx4_cmd(dev, slave, eqn & 0x3ff,
 						       1, MLX4_CMD_HW2SW_EQ,
 						       MLX4_CMD_TIME_CLASS_A,
 						       MLX4_CMD_NATIVE);
 					if (err)
 						mlx4_dbg(dev, "rem_slave_eqs: failed to move slave %d eqs %d to SW ownership\n",
-							 slave, eqn);
+							 slave, eqn & 0x3ff);
 					atomic_dec(&eq->mtt->ref_count);
 					state = RES_EQ_RESERVED;
 					break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 8ff57e8e3e91..158c88c69ef9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -3,6 +3,18 @@
 #
 
 config MLX5_CORE
-	tristate
+	tristate "Mellanox Technologies ConnectX-4 and Connect-IB core driver"
 	depends on PCI
 	default n
+	---help---
+	  Core driver for low level functionality of the ConnectX-4 and
+	  Connect-IB cards by Mellanox Technologies.
+
+config MLX5_CORE_EN
+	bool "Mellanox Technologies ConnectX-4 Ethernet support"
+	depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE
+	default n
+	---help---
+	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
+	  Ethernet and Infiniband support in ConnectX-4 are currently mutually
+	  exclusive.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 105780bb980b..26a68b8af2c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -2,4 +2,7 @@ obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
 
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o   \
-		mad.o
+		mad.o transobj.o vport.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o flow_table.o \
+		en_main.o en_flow_table.o en_ethtool.o en_tx.o en_rx.o \
+		en_txrx.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index ac0f7bf4be95..0715b497511f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -42,95 +42,36 @@
 #include "mlx5_core.h"
 
 /* Handling for queue buffers -- we allocate a bunch of memory and
- * register it in a memory region at HCA virtual address 0.  If the
- * requested size is > max_direct, we split the allocation into
- * multiple pages, so we don't require too much contiguous memory.
+ * register it in a memory region at HCA virtual address 0.
  */
 
-int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, int max_direct,
-		   struct mlx5_buf *buf)
+int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf)
 {
 	dma_addr_t t;
 
 	buf->size = size;
-	if (size <= max_direct) {
-		buf->nbufs        = 1;
-		buf->npages       = 1;
-		buf->page_shift   = (u8)get_order(size) + PAGE_SHIFT;
-		buf->direct.buf   = dma_zalloc_coherent(&dev->pdev->dev,
-							size, &t, GFP_KERNEL);
-		if (!buf->direct.buf)
-			return -ENOMEM;
-
-		buf->direct.map = t;
-
-		while (t & ((1 << buf->page_shift) - 1)) {
-			--buf->page_shift;
-			buf->npages *= 2;
-		}
-	} else {
-		int i;
-
-		buf->direct.buf  = NULL;
-		buf->nbufs       = (size + PAGE_SIZE - 1) / PAGE_SIZE;
-		buf->npages      = buf->nbufs;
-		buf->page_shift  = PAGE_SHIFT;
-		buf->page_list   = kcalloc(buf->nbufs, sizeof(*buf->page_list),
-					   GFP_KERNEL);
-		if (!buf->page_list)
-			return -ENOMEM;
-
-		for (i = 0; i < buf->nbufs; i++) {
-			buf->page_list[i].buf =
-				dma_zalloc_coherent(&dev->pdev->dev, PAGE_SIZE,
-						    &t, GFP_KERNEL);
-			if (!buf->page_list[i].buf)
-				goto err_free;
-
-			buf->page_list[i].map = t;
-		}
-
-		if (BITS_PER_LONG == 64) {
-			struct page **pages;
-			pages = kmalloc(sizeof(*pages) * buf->nbufs, GFP_KERNEL);
-			if (!pages)
-				goto err_free;
-			for (i = 0; i < buf->nbufs; i++)
-				pages[i] = virt_to_page(buf->page_list[i].buf);
-			buf->direct.buf = vmap(pages, buf->nbufs, VM_MAP, PAGE_KERNEL);
-			kfree(pages);
-			if (!buf->direct.buf)
-				goto err_free;
-		}
-	}
+	buf->npages       = 1;
+	buf->page_shift   = (u8)get_order(size) + PAGE_SHIFT;
+	buf->direct.buf   = dma_zalloc_coherent(&dev->pdev->dev,
+						size, &t, GFP_KERNEL);
+	if (!buf->direct.buf)
+		return -ENOMEM;
 
-	return 0;
+	buf->direct.map = t;
 
-err_free:
-	mlx5_buf_free(dev, buf);
+	while (t & ((1 << buf->page_shift) - 1)) {
+		--buf->page_shift;
+		buf->npages *= 2;
+	}
 
-	return -ENOMEM;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx5_buf_alloc);
 
 void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf)
 {
-	int i;
-
-	if (buf->nbufs == 1)
-		dma_free_coherent(&dev->pdev->dev, buf->size, buf->direct.buf,
-				  buf->direct.map);
-	else {
-		if (BITS_PER_LONG == 64)
-			vunmap(buf->direct.buf);
-
-		for (i = 0; i < buf->nbufs; i++)
-			if (buf->page_list[i].buf)
-				dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
-						  buf->page_list[i].buf,
-						  buf->page_list[i].map);
-		kfree(buf->page_list);
-	}
+	dma_free_coherent(&dev->pdev->dev, buf->size, buf->direct.buf,
+			  buf->direct.map);
 }
 EXPORT_SYMBOL_GPL(mlx5_buf_free);
 
@@ -230,10 +171,7 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas)
 	int i;
 
 	for (i = 0; i < buf->npages; i++) {
-		if (buf->nbufs == 1)
-			addr = buf->direct.map + (i << buf->page_shift);
-		else
-			addr = buf->page_list[i].map;
+		addr = buf->direct.map + (i << buf->page_shift);
 
 		pas[i] = cpu_to_be64(addr);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e3273faf4568..75ff58dc1ff5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -75,25 +75,6 @@ enum {
 	MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR		= 0x10,
 };
 
-enum {
-	MLX5_CMD_STAT_OK			= 0x0,
-	MLX5_CMD_STAT_INT_ERR			= 0x1,
-	MLX5_CMD_STAT_BAD_OP_ERR		= 0x2,
-	MLX5_CMD_STAT_BAD_PARAM_ERR		= 0x3,
-	MLX5_CMD_STAT_BAD_SYS_STATE_ERR		= 0x4,
-	MLX5_CMD_STAT_BAD_RES_ERR		= 0x5,
-	MLX5_CMD_STAT_RES_BUSY			= 0x6,
-	MLX5_CMD_STAT_LIM_ERR			= 0x8,
-	MLX5_CMD_STAT_BAD_RES_STATE_ERR		= 0x9,
-	MLX5_CMD_STAT_IX_ERR			= 0xa,
-	MLX5_CMD_STAT_NO_RES_ERR		= 0xf,
-	MLX5_CMD_STAT_BAD_INP_LEN_ERR		= 0x50,
-	MLX5_CMD_STAT_BAD_OUTP_LEN_ERR		= 0x51,
-	MLX5_CMD_STAT_BAD_QP_STATE_ERR		= 0x10,
-	MLX5_CMD_STAT_BAD_PKT_ERR		= 0x30,
-	MLX5_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR	= 0x40,
-};
-
 static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd,
 					   struct mlx5_cmd_msg *in,
 					   struct mlx5_cmd_msg *out,
@@ -390,8 +371,17 @@ const char *mlx5_command_str(int command)
 	case MLX5_CMD_OP_ARM_RQ:
 		return "ARM_RQ";
 
-	case MLX5_CMD_OP_RESIZE_SRQ:
-		return "RESIZE_SRQ";
+	case MLX5_CMD_OP_CREATE_XRC_SRQ:
+		return "CREATE_XRC_SRQ";
+
+	case MLX5_CMD_OP_DESTROY_XRC_SRQ:
+		return "DESTROY_XRC_SRQ";
+
+	case MLX5_CMD_OP_QUERY_XRC_SRQ:
+		return "QUERY_XRC_SRQ";
+
+	case MLX5_CMD_OP_ARM_XRC_SRQ:
+		return "ARM_XRC_SRQ";
 
 	case MLX5_CMD_OP_ALLOC_PD:
 		return "ALLOC_PD";
@@ -408,8 +398,8 @@ const char *mlx5_command_str(int command)
 	case MLX5_CMD_OP_ATTACH_TO_MCG:
 		return "ATTACH_TO_MCG";
 
-	case MLX5_CMD_OP_DETACH_FROM_MCG:
-		return "DETACH_FROM_MCG";
+	case MLX5_CMD_OP_DETTACH_FROM_MCG:
+		return "DETTACH_FROM_MCG";
 
 	case MLX5_CMD_OP_ALLOC_XRCD:
 		return "ALLOC_XRCD";
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index eb0cf81f5f45..04ab7e445eae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -219,6 +219,24 @@ int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 }
 EXPORT_SYMBOL(mlx5_core_modify_cq);
 
+int mlx5_core_modify_cq_moderation(struct mlx5_core_dev *dev,
+				   struct mlx5_core_cq *cq,
+				   u16 cq_period,
+				   u16 cq_max_count)
+{
+	struct mlx5_modify_cq_mbox_in in;
+
+	memset(&in, 0, sizeof(in));
+
+	in.cqn              = cpu_to_be32(cq->cqn);
+	in.ctx.cq_period    = cpu_to_be16(cq_period);
+	in.ctx.cq_max_count = cpu_to_be16(cq_max_count);
+	in.field_select     = cpu_to_be32(MLX5_CQ_MODIFY_PERIOD |
+					  MLX5_CQ_MODIFY_COUNT);
+
+	return mlx5_core_modify_cq(dev, cq, &in, sizeof(in));
+}
+
 int mlx5_init_cq_table(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cq_table *table = &dev->priv.cq_table;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
new file mode 100644
index 000000000000..3d23bd657e3c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -0,0 +1,521 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/if_vlan.h>
+#include <linux/etherdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/qp.h>
+#include <linux/mlx5/cq.h>
+#include <linux/mlx5/vport.h>
+#include "wq.h"
+#include "transobj.h"
+#include "mlx5_core.h"
+
+#define MLX5E_MAX_NUM_TC	8
+
+#define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE                0x7
+#define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE                0xd
+
+#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE                0x7
+#define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE                0xa
+#define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE                0xd
+
+#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (16 * 1024)
+#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC      0x10
+#define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS      0x20
+#define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC      0x10
+#define MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS      0x20
+#define MLX5E_PARAMS_DEFAULT_MIN_RX_WQES                0x80
+#define MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ         0x7
+
+#define MLX5E_TX_CQ_POLL_BUDGET        128
+#define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
+
+static const char vport_strings[][ETH_GSTRING_LEN] = {
+	/* vport statistics */
+	"rx_packets",
+	"rx_bytes",
+	"tx_packets",
+	"tx_bytes",
+	"rx_error_packets",
+	"rx_error_bytes",
+	"tx_error_packets",
+	"tx_error_bytes",
+	"rx_unicast_packets",
+	"rx_unicast_bytes",
+	"tx_unicast_packets",
+	"tx_unicast_bytes",
+	"rx_multicast_packets",
+	"rx_multicast_bytes",
+	"tx_multicast_packets",
+	"tx_multicast_bytes",
+	"rx_broadcast_packets",
+	"rx_broadcast_bytes",
+	"tx_broadcast_packets",
+	"tx_broadcast_bytes",
+
+	/* SW counters */
+	"tso_packets",
+	"tso_bytes",
+	"lro_packets",
+	"lro_bytes",
+	"rx_csum_good",
+	"rx_csum_none",
+	"tx_csum_offload",
+	"tx_queue_stopped",
+	"tx_queue_wake",
+	"tx_queue_dropped",
+	"rx_wqe_err",
+};
+
+struct mlx5e_vport_stats {
+	/* HW counters */
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 rx_error_packets;
+	u64 rx_error_bytes;
+	u64 tx_error_packets;
+	u64 tx_error_bytes;
+	u64 rx_unicast_packets;
+	u64 rx_unicast_bytes;
+	u64 tx_unicast_packets;
+	u64 tx_unicast_bytes;
+	u64 rx_multicast_packets;
+	u64 rx_multicast_bytes;
+	u64 tx_multicast_packets;
+	u64 tx_multicast_bytes;
+	u64 rx_broadcast_packets;
+	u64 rx_broadcast_bytes;
+	u64 tx_broadcast_packets;
+	u64 tx_broadcast_bytes;
+
+	/* SW counters */
+	u64 tso_packets;
+	u64 tso_bytes;
+	u64 lro_packets;
+	u64 lro_bytes;
+	u64 rx_csum_good;
+	u64 rx_csum_none;
+	u64 tx_csum_offload;
+	u64 tx_queue_stopped;
+	u64 tx_queue_wake;
+	u64 tx_queue_dropped;
+	u64 rx_wqe_err;
+
+#define NUM_VPORT_COUNTERS     31
+};
+
+static const char rq_stats_strings[][ETH_GSTRING_LEN] = {
+	"packets",
+	"csum_none",
+	"lro_packets",
+	"lro_bytes",
+	"wqe_err"
+};
+
+struct mlx5e_rq_stats {
+	u64 packets;
+	u64 csum_none;
+	u64 lro_packets;
+	u64 lro_bytes;
+	u64 wqe_err;
+#define NUM_RQ_STATS 5
+};
+
+static const char sq_stats_strings[][ETH_GSTRING_LEN] = {
+	"packets",
+	"tso_packets",
+	"tso_bytes",
+	"csum_offload_none",
+	"stopped",
+	"wake",
+	"dropped",
+	"nop"
+};
+
+struct mlx5e_sq_stats {
+	u64 packets;
+	u64 tso_packets;
+	u64 tso_bytes;
+	u64 csum_offload_none;
+	u64 stopped;
+	u64 wake;
+	u64 dropped;
+	u64 nop;
+#define NUM_SQ_STATS 8
+};
+
+struct mlx5e_stats {
+	struct mlx5e_vport_stats   vport;
+};
+
+struct mlx5e_params {
+	u8  log_sq_size;
+	u8  log_rq_size;
+	u16 num_channels;
+	u8  default_vlan_prio;
+	u8  num_tc;
+	u16 rx_cq_moderation_usec;
+	u16 rx_cq_moderation_pkts;
+	u16 tx_cq_moderation_usec;
+	u16 tx_cq_moderation_pkts;
+	u16 min_rx_wqes;
+	u16 rx_hash_log_tbl_sz;
+	bool lro_en;
+	u32 lro_wqe_sz;
+};
+
+enum {
+	MLX5E_RQ_STATE_POST_WQES_ENABLE,
+};
+
+enum cq_flags {
+	MLX5E_CQ_HAS_CQES = 1,
+};
+
+struct mlx5e_cq {
+	/* data path - accessed per cqe */
+	struct mlx5_cqwq           wq;
+	unsigned long              flags;
+
+	/* data path - accessed per napi poll */
+	struct napi_struct        *napi;
+	struct mlx5_core_cq        mcq;
+	struct mlx5e_channel      *channel;
+
+	/* control */
+	struct mlx5_wq_ctrl        wq_ctrl;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_rq {
+	/* data path */
+	struct mlx5_wq_ll      wq;
+	u32                    wqe_sz;
+	struct sk_buff       **skb;
+
+	struct device         *pdev;
+	struct net_device     *netdev;
+	struct mlx5e_rq_stats  stats;
+	struct mlx5e_cq        cq;
+
+	unsigned long          state;
+	int                    ix;
+
+	/* control */
+	struct mlx5_wq_ctrl    wq_ctrl;
+	u32                    rqn;
+	struct mlx5e_channel  *channel;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_tx_skb_cb {
+	u32 num_bytes;
+	u8  num_wqebbs;
+	u8  num_dma;
+};
+
+#define MLX5E_TX_SKB_CB(__skb) ((struct mlx5e_tx_skb_cb *)__skb->cb)
+
+struct mlx5e_sq_dma {
+	dma_addr_t addr;
+	u32        size;
+};
+
+enum {
+	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
+};
+
+struct mlx5e_sq {
+	/* data path */
+
+	/* dirtied @completion */
+	u16                        cc;
+	u32                        dma_fifo_cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+	u32                        bf_offset;
+	struct mlx5e_sq_stats      stats;
+
+	struct mlx5e_cq            cq;
+
+	/* pointers to per packet info: write@xmit, read@completion */
+	struct sk_buff           **skb;
+	struct mlx5e_sq_dma       *dma_fifo;
+
+	/* read only */
+	struct mlx5_wq_cyc         wq;
+	u32                        dma_fifo_mask;
+	void __iomem              *uar_map;
+	struct netdev_queue       *txq;
+	u32                        sqn;
+	u32                        bf_buf_size;
+	u16                        max_inline;
+	u16                        edge;
+	struct device             *pdev;
+	__be32                     mkey_be;
+	unsigned long              state;
+
+	/* control path */
+	struct mlx5_wq_ctrl        wq_ctrl;
+	struct mlx5_uar            uar;
+	struct mlx5e_channel      *channel;
+	int                        tc;
+} ____cacheline_aligned_in_smp;
+
+static inline bool mlx5e_sq_has_room_for(struct mlx5e_sq *sq, u16 n)
+{
+	return (((sq->wq.sz_m1 & (sq->cc - sq->pc)) >= n) ||
+		(sq->cc  == sq->pc));
+}
+
+enum channel_flags {
+	MLX5E_CHANNEL_NAPI_SCHED = 1,
+};
+
+struct mlx5e_channel {
+	/* data path */
+	struct mlx5e_rq            rq;
+	struct mlx5e_sq            sq[MLX5E_MAX_NUM_TC];
+	struct napi_struct         napi;
+	struct device             *pdev;
+	struct net_device         *netdev;
+	__be32                     mkey_be;
+	u8                         num_tc;
+	unsigned long              flags;
+	int                        tc_to_txq_map[MLX5E_MAX_NUM_TC];
+
+	/* control */
+	struct mlx5e_priv         *priv;
+	int                        ix;
+	int                        cpu;
+};
+
+enum mlx5e_traffic_types {
+	MLX5E_TT_IPV4_TCP = 0,
+	MLX5E_TT_IPV6_TCP = 1,
+	MLX5E_TT_IPV4_UDP = 2,
+	MLX5E_TT_IPV6_UDP = 3,
+	MLX5E_TT_IPV4     = 4,
+	MLX5E_TT_IPV6     = 5,
+	MLX5E_TT_ANY      = 6,
+	MLX5E_NUM_TT      = 7,
+};
+
+enum {
+	MLX5E_RQT_SPREADING  = 0,
+	MLX5E_RQT_DEFAULT_RQ = 1,
+	MLX5E_NUM_RQT        = 2,
+};
+
+struct mlx5e_eth_addr_info {
+	u8  addr[ETH_ALEN + 2];
+	u32 tt_vec;
+	u32 ft_ix[MLX5E_NUM_TT]; /* flow table index per traffic type */
+};
+
+#define MLX5E_ETH_ADDR_HASH_SIZE (1 << BITS_PER_BYTE)
+
+struct mlx5e_eth_addr_db {
+	struct hlist_head          netdev_uc[MLX5E_ETH_ADDR_HASH_SIZE];
+	struct hlist_head          netdev_mc[MLX5E_ETH_ADDR_HASH_SIZE];
+	struct mlx5e_eth_addr_info broadcast;
+	struct mlx5e_eth_addr_info allmulti;
+	struct mlx5e_eth_addr_info promisc;
+	bool                       broadcast_enabled;
+	bool                       allmulti_enabled;
+	bool                       promisc_enabled;
+};
+
+enum {
+	MLX5E_STATE_ASYNC_EVENTS_ENABLE,
+	MLX5E_STATE_OPENED,
+};
+
+struct mlx5e_vlan_db {
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+	u32           active_vlans_ft_ix[VLAN_N_VID];
+	u32           untagged_rule_ft_ix;
+	u32           any_vlan_rule_ft_ix;
+	bool          filter_disabled;
+};
+
+struct mlx5e_flow_table {
+	void *vlan;
+	void *main;
+};
+
+struct mlx5e_priv {
+	/* priv data path fields - start */
+	int                        num_tc;
+	int                        default_vlan_prio;
+	struct mlx5e_sq            **txq_to_sq_map;
+	/* priv data path fields - end */
+
+	unsigned long              state;
+	struct mutex               state_lock; /* Protects Interface state */
+	struct mlx5_uar            cq_uar;
+	u32                        pdn;
+	u32                        tdn;
+	struct mlx5_core_mr        mr;
+
+	struct mlx5e_channel     **channel;
+	u32                        tisn[MLX5E_MAX_NUM_TC];
+	u32                        rqtn;
+	u32                        tirn[MLX5E_NUM_TT];
+
+	struct mlx5e_flow_table    ft;
+	struct mlx5e_eth_addr_db   eth_addr;
+	struct mlx5e_vlan_db       vlan;
+
+	struct mlx5e_params        params;
+	spinlock_t                 async_events_spinlock; /* sync hw events */
+	struct work_struct         update_carrier_work;
+	struct work_struct         set_rx_mode_work;
+	struct delayed_work        update_stats_work;
+
+	struct mlx5_core_dev      *mdev;
+	struct net_device         *netdev;
+	struct mlx5e_stats         stats;
+};
+
+#define MLX5E_NET_IP_ALIGN 2
+
+struct mlx5e_tx_wqe {
+	struct mlx5_wqe_ctrl_seg ctrl;
+	struct mlx5_wqe_eth_seg  eth;
+};
+
+struct mlx5e_rx_wqe {
+	struct mlx5_wqe_srq_next_seg  next;
+	struct mlx5_wqe_data_seg      data;
+};
+
+enum mlx5e_link_mode {
+	MLX5E_1000BASE_CX_SGMII	 = 0,
+	MLX5E_1000BASE_KX	 = 1,
+	MLX5E_10GBASE_CX4	 = 2,
+	MLX5E_10GBASE_KX4	 = 3,
+	MLX5E_10GBASE_KR	 = 4,
+	MLX5E_20GBASE_KR2	 = 5,
+	MLX5E_40GBASE_CR4	 = 6,
+	MLX5E_40GBASE_KR4	 = 7,
+	MLX5E_56GBASE_R4	 = 8,
+	MLX5E_10GBASE_CR	 = 12,
+	MLX5E_10GBASE_SR	 = 13,
+	MLX5E_10GBASE_ER	 = 14,
+	MLX5E_40GBASE_SR4	 = 15,
+	MLX5E_40GBASE_LR4	 = 16,
+	MLX5E_100GBASE_CR4	 = 20,
+	MLX5E_100GBASE_SR4	 = 21,
+	MLX5E_100GBASE_KR4	 = 22,
+	MLX5E_100GBASE_LR4	 = 23,
+	MLX5E_100BASE_TX	 = 24,
+	MLX5E_100BASE_T		 = 25,
+	MLX5E_10GBASE_T		 = 26,
+	MLX5E_25GBASE_CR	 = 27,
+	MLX5E_25GBASE_KR	 = 28,
+	MLX5E_25GBASE_SR	 = 29,
+	MLX5E_50GBASE_CR2	 = 30,
+	MLX5E_50GBASE_KR2	 = 31,
+	MLX5E_LINK_MODES_NUMBER,
+};
+
+#define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
+
+void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw);
+u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv, select_queue_fallback_t fallback);
+netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
+
+void mlx5e_completion_event(struct mlx5_core_cq *mcq);
+void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
+int mlx5e_napi_poll(struct napi_struct *napi, int budget);
+bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq);
+bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
+struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq);
+
+void mlx5e_update_stats(struct mlx5e_priv *priv);
+
+int mlx5e_open_flow_table(struct mlx5e_priv *priv);
+void mlx5e_close_flow_table(struct mlx5e_priv *priv);
+void mlx5e_init_eth_addr(struct mlx5e_priv *priv);
+void mlx5e_set_rx_mode_core(struct mlx5e_priv *priv);
+void mlx5e_set_rx_mode_work(struct work_struct *work);
+
+int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
+			  u16 vid);
+int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
+			   u16 vid);
+void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv);
+void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
+int mlx5e_add_all_vlan_rules(struct mlx5e_priv *priv);
+void mlx5e_del_all_vlan_rules(struct mlx5e_priv *priv);
+
+int mlx5e_open_locked(struct net_device *netdev);
+int mlx5e_close_locked(struct net_device *netdev);
+int mlx5e_update_priv_params(struct mlx5e_priv *priv,
+			     struct mlx5e_params *new_params);
+
+static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq,
+				      struct mlx5e_tx_wqe *wqe)
+{
+	/* ensure wqe is visible to device before updating doorbell record */
+	dma_wmb();
+
+	*sq->wq.db = cpu_to_be32(sq->pc);
+
+	/* ensure doorbell record is visible to device before ringing the
+	 * doorbell
+	 */
+	wmb();
+
+	mlx5_write64((__be32 *)&wqe->ctrl,
+		     sq->uar_map + MLX5_BF_OFFSET + sq->bf_offset,
+		     NULL);
+
+	sq->bf_offset ^= sq->bf_buf_size;
+}
+
+static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
+{
+	struct mlx5_core_cq *mcq;
+
+	mcq = &cq->mcq;
+	mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, NULL, cq->wq.cc);
+}
+
+extern const struct ethtool_ops mlx5e_ethtool_ops;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
new file mode 100644
index 000000000000..388938482ff9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -0,0 +1,679 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "en.h"
+
+static void mlx5e_get_drvinfo(struct net_device *dev,
+			      struct ethtool_drvinfo *drvinfo)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	strlcpy(drvinfo->driver, DRIVER_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")",
+		sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "%d.%d.%d",
+		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev));
+	strlcpy(drvinfo->bus_info, pci_name(mdev->pdev),
+		sizeof(drvinfo->bus_info));
+}
+
+static const struct {
+	u32 supported;
+	u32 advertised;
+	u32 speed;
+} ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER] = {
+	[MLX5E_1000BASE_CX_SGMII] = {
+		.supported  = SUPPORTED_1000baseKX_Full,
+		.advertised = ADVERTISED_1000baseKX_Full,
+		.speed      = 1000,
+	},
+	[MLX5E_1000BASE_KX] = {
+		.supported  = SUPPORTED_1000baseKX_Full,
+		.advertised = ADVERTISED_1000baseKX_Full,
+		.speed      = 1000,
+	},
+	[MLX5E_10GBASE_CX4] = {
+		.supported  = SUPPORTED_10000baseKX4_Full,
+		.advertised = ADVERTISED_10000baseKX4_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_10GBASE_KX4] = {
+		.supported  = SUPPORTED_10000baseKX4_Full,
+		.advertised = ADVERTISED_10000baseKX4_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_10GBASE_KR] = {
+		.supported  = SUPPORTED_10000baseKR_Full,
+		.advertised = ADVERTISED_10000baseKR_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_20GBASE_KR2] = {
+		.supported  = SUPPORTED_20000baseKR2_Full,
+		.advertised = ADVERTISED_20000baseKR2_Full,
+		.speed      = 20000,
+	},
+	[MLX5E_40GBASE_CR4] = {
+		.supported  = SUPPORTED_40000baseCR4_Full,
+		.advertised = ADVERTISED_40000baseCR4_Full,
+		.speed      = 40000,
+	},
+	[MLX5E_40GBASE_KR4] = {
+		.supported  = SUPPORTED_40000baseKR4_Full,
+		.advertised = ADVERTISED_40000baseKR4_Full,
+		.speed      = 40000,
+	},
+	[MLX5E_56GBASE_R4] = {
+		.supported  = SUPPORTED_56000baseKR4_Full,
+		.advertised = ADVERTISED_56000baseKR4_Full,
+		.speed      = 56000,
+	},
+	[MLX5E_10GBASE_CR] = {
+		.supported  = SUPPORTED_10000baseKR_Full,
+		.advertised = ADVERTISED_10000baseKR_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_10GBASE_SR] = {
+		.supported  = SUPPORTED_10000baseKR_Full,
+		.advertised = ADVERTISED_10000baseKR_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_10GBASE_ER] = {
+		.supported  = SUPPORTED_10000baseKR_Full,
+		.advertised = ADVERTISED_10000baseKR_Full,
+		.speed      = 10000,
+	},
+	[MLX5E_40GBASE_SR4] = {
+		.supported  = SUPPORTED_40000baseSR4_Full,
+		.advertised = ADVERTISED_40000baseSR4_Full,
+		.speed      = 40000,
+	},
+	[MLX5E_40GBASE_LR4] = {
+		.supported  = SUPPORTED_40000baseLR4_Full,
+		.advertised = ADVERTISED_40000baseLR4_Full,
+		.speed      = 40000,
+	},
+	[MLX5E_100GBASE_CR4] = {
+		.speed      = 100000,
+	},
+	[MLX5E_100GBASE_SR4] = {
+		.speed      = 100000,
+	},
+	[MLX5E_100GBASE_KR4] = {
+		.speed      = 100000,
+	},
+	[MLX5E_100GBASE_LR4] = {
+		.speed      = 100000,
+	},
+	[MLX5E_100BASE_TX]   = {
+		.speed      = 100,
+	},
+	[MLX5E_100BASE_T]    = {
+		.supported  = SUPPORTED_100baseT_Full,
+		.advertised = ADVERTISED_100baseT_Full,
+		.speed      = 100,
+	},
+	[MLX5E_10GBASE_T]    = {
+		.supported  = SUPPORTED_10000baseT_Full,
+		.advertised = ADVERTISED_10000baseT_Full,
+		.speed      = 1000,
+	},
+	[MLX5E_25GBASE_CR]   = {
+		.speed      = 25000,
+	},
+	[MLX5E_25GBASE_KR]   = {
+		.speed      = 25000,
+	},
+	[MLX5E_25GBASE_SR]   = {
+		.speed      = 25000,
+	},
+	[MLX5E_50GBASE_CR2]  = {
+		.speed      = 50000,
+	},
+	[MLX5E_50GBASE_KR2]  = {
+		.speed      = 50000,
+	},
+};
+
+static int mlx5e_get_sset_count(struct net_device *dev, int sset)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return NUM_VPORT_COUNTERS +
+		       priv->params.num_channels * NUM_RQ_STATS +
+		       priv->params.num_channels * priv->num_tc *
+						   NUM_SQ_STATS;
+	/* fallthrough */
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void mlx5e_get_strings(struct net_device *dev,
+			      uint32_t stringset, uint8_t *data)
+{
+	int i, j, tc, idx = 0;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (stringset) {
+	case ETH_SS_PRIV_FLAGS:
+		break;
+
+	case ETH_SS_TEST:
+		break;
+
+	case ETH_SS_STATS:
+		/* VPORT counters */
+		for (i = 0; i < NUM_VPORT_COUNTERS; i++)
+			strcpy(data + (idx++) * ETH_GSTRING_LEN,
+			       vport_strings[i]);
+
+		/* per channel counters */
+		for (i = 0; i < priv->params.num_channels; i++)
+			for (j = 0; j < NUM_RQ_STATS; j++)
+				sprintf(data + (idx++) * ETH_GSTRING_LEN,
+					"rx%d_%s", i, rq_stats_strings[j]);
+
+		for (i = 0; i < priv->params.num_channels; i++)
+			for (tc = 0; tc < priv->num_tc; tc++)
+				for (j = 0; j < NUM_SQ_STATS; j++)
+					sprintf(data +
+						(idx++) * ETH_GSTRING_LEN,
+						"tx%d_%d_%s", i, tc,
+						sq_stats_strings[j]);
+		break;
+	}
+}
+
+static void mlx5e_get_ethtool_stats(struct net_device *dev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int i, j, tc, idx = 0;
+
+	if (!data)
+		return;
+
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_update_stats(priv);
+	mutex_unlock(&priv->state_lock);
+
+	for (i = 0; i < NUM_VPORT_COUNTERS; i++)
+		data[idx++] = ((u64 *)&priv->stats.vport)[i];
+
+	/* per channel counters */
+	for (i = 0; i < priv->params.num_channels; i++)
+		for (j = 0; j < NUM_RQ_STATS; j++)
+			data[idx++] = !test_bit(MLX5E_STATE_OPENED,
+						&priv->state) ? 0 :
+				       ((u64 *)&priv->channel[i]->rq.stats)[j];
+
+	for (i = 0; i < priv->params.num_channels; i++)
+		for (tc = 0; tc < priv->num_tc; tc++)
+			for (j = 0; j < NUM_SQ_STATS; j++)
+				data[idx++] = !test_bit(MLX5E_STATE_OPENED,
+							&priv->state) ? 0 :
+				((u64 *)&priv->channel[i]->sq[tc].stats)[j];
+}
+
+static void mlx5e_get_ringparam(struct net_device *dev,
+				struct ethtool_ringparam *param)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	param->rx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE;
+	param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
+	param->rx_pending     = 1 << priv->params.log_rq_size;
+	param->tx_pending     = 1 << priv->params.log_sq_size;
+}
+
+static int mlx5e_set_ringparam(struct net_device *dev,
+			       struct ethtool_ringparam *param)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_params new_params;
+	u16 min_rx_wqes;
+	u8 log_rq_size;
+	u8 log_sq_size;
+	int err = 0;
+
+	if (param->rx_jumbo_pending) {
+		netdev_info(dev, "%s: rx_jumbo_pending not supported\n",
+			    __func__);
+		return -EINVAL;
+	}
+	if (param->rx_mini_pending) {
+		netdev_info(dev, "%s: rx_mini_pending not supported\n",
+			    __func__);
+		return -EINVAL;
+	}
+	if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) {
+		netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n",
+			    __func__, param->rx_pending,
+			    1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
+		return -EINVAL;
+	}
+	if (param->rx_pending > (1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE)) {
+		netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n",
+			    __func__, param->rx_pending,
+			    1 << MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE);
+		return -EINVAL;
+	}
+	if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) {
+		netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n",
+			    __func__, param->tx_pending,
+			    1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE);
+		return -EINVAL;
+	}
+	if (param->tx_pending > (1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE)) {
+		netdev_info(dev, "%s: tx_pending (%d) > max (%d)\n",
+			    __func__, param->tx_pending,
+			    1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE);
+		return -EINVAL;
+	}
+
+	log_rq_size = order_base_2(param->rx_pending);
+	log_sq_size = order_base_2(param->tx_pending);
+	min_rx_wqes = min_t(u16, param->rx_pending - 1,
+			    MLX5E_PARAMS_DEFAULT_MIN_RX_WQES);
+
+	if (log_rq_size == priv->params.log_rq_size &&
+	    log_sq_size == priv->params.log_sq_size &&
+	    min_rx_wqes == priv->params.min_rx_wqes)
+		return 0;
+
+	mutex_lock(&priv->state_lock);
+	new_params = priv->params;
+	new_params.log_rq_size = log_rq_size;
+	new_params.log_sq_size = log_sq_size;
+	new_params.min_rx_wqes = min_rx_wqes;
+	err = mlx5e_update_priv_params(priv, &new_params);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+static void mlx5e_get_channels(struct net_device *dev,
+			       struct ethtool_channels *ch)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int ncv = priv->mdev->priv.eq_table.num_comp_vectors;
+
+	ch->max_combined   = ncv;
+	ch->combined_count = priv->params.num_channels;
+}
+
+static int mlx5e_set_channels(struct net_device *dev,
+			      struct ethtool_channels *ch)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int ncv = priv->mdev->priv.eq_table.num_comp_vectors;
+	unsigned int count = ch->combined_count;
+	struct mlx5e_params new_params;
+	int err = 0;
+
+	if (!count) {
+		netdev_info(dev, "%s: combined_count=0 not supported\n",
+			    __func__);
+		return -EINVAL;
+	}
+	if (ch->rx_count || ch->tx_count) {
+		netdev_info(dev, "%s: separate rx/tx count not supported\n",
+			    __func__);
+		return -EINVAL;
+	}
+	if (count > ncv) {
+		netdev_info(dev, "%s: count (%d) > max (%d)\n",
+			    __func__, count, ncv);
+		return -EINVAL;
+	}
+
+	if (priv->params.num_channels == count)
+		return 0;
+
+	mutex_lock(&priv->state_lock);
+	new_params = priv->params;
+	new_params.num_channels = count;
+	err = mlx5e_update_priv_params(priv, &new_params);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+static int mlx5e_get_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation_usec;
+	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts;
+	coal->tx_coalesce_usecs       = priv->params.tx_cq_moderation_usec;
+	coal->tx_max_coalesced_frames = priv->params.tx_cq_moderation_pkts;
+
+	return 0;
+}
+
+static int mlx5e_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv    = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channel *c;
+	int tc;
+	int i;
+
+	priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs;
+	priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames;
+	priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs;
+	priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames;
+
+	for (i = 0; i < priv->params.num_channels; ++i) {
+		c = priv->channel[i];
+
+		for (tc = 0; tc < c->num_tc; tc++) {
+			mlx5_core_modify_cq_moderation(mdev,
+						&c->sq[tc].cq.mcq,
+						coal->tx_coalesce_usecs,
+						coal->tx_max_coalesced_frames);
+		}
+
+		mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq,
+					       coal->rx_coalesce_usecs,
+					       coal->rx_max_coalesced_frames);
+	}
+
+	return 0;
+}
+
+static u32 ptys2ethtool_supported_link(u32 eth_proto_cap)
+{
+	int i;
+	u32 supported_modes = 0;
+
+	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
+		if (eth_proto_cap & MLX5E_PROT_MASK(i))
+			supported_modes |= ptys2ethtool_table[i].supported;
+	}
+	return supported_modes;
+}
+
+static u32 ptys2ethtool_adver_link(u32 eth_proto_cap)
+{
+	int i;
+	u32 advertising_modes = 0;
+
+	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
+		if (eth_proto_cap & MLX5E_PROT_MASK(i))
+			advertising_modes |= ptys2ethtool_table[i].advertised;
+	}
+	return advertising_modes;
+}
+
+static u32 ptys2ethtool_supported_port(u32 eth_proto_cap)
+{
+	if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
+			   | MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
+			   | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
+			   | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4)
+			   | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4)
+			   | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) {
+		return SUPPORTED_FIBRE;
+	}
+
+	if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_100GBASE_KR4)
+			   | MLX5E_PROT_MASK(MLX5E_40GBASE_KR4)
+			   | MLX5E_PROT_MASK(MLX5E_10GBASE_KR)
+			   | MLX5E_PROT_MASK(MLX5E_10GBASE_KX4)
+			   | MLX5E_PROT_MASK(MLX5E_1000BASE_KX))) {
+		return SUPPORTED_Backplane;
+	}
+	return 0;
+}
+
+static void get_speed_duplex(struct net_device *netdev,
+			     u32 eth_proto_oper,
+			     struct ethtool_cmd *cmd)
+{
+	int i;
+	u32 speed = SPEED_UNKNOWN;
+	u8 duplex = DUPLEX_UNKNOWN;
+
+	if (!netif_carrier_ok(netdev))
+		goto out;
+
+	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
+		if (eth_proto_oper & MLX5E_PROT_MASK(i)) {
+			speed = ptys2ethtool_table[i].speed;
+			duplex = DUPLEX_FULL;
+			break;
+		}
+	}
+out:
+	ethtool_cmd_speed_set(cmd, speed);
+	cmd->duplex = duplex;
+}
+
+static void get_supported(u32 eth_proto_cap, u32 *supported)
+{
+	*supported |= ptys2ethtool_supported_port(eth_proto_cap);
+	*supported |= ptys2ethtool_supported_link(eth_proto_cap);
+	*supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+}
+
+static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
+			    u8 rx_pause, u32 *advertising)
+{
+	*advertising |= ptys2ethtool_adver_link(eth_proto_cap);
+	*advertising |= tx_pause ? ADVERTISED_Pause : 0;
+	*advertising |= (tx_pause ^ rx_pause) ? ADVERTISED_Asym_Pause : 0;
+}
+
+static u8 get_connector_port(u32 eth_proto)
+{
+	if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
+			 | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4)
+			 | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4)
+			 | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) {
+			return PORT_FIBRE;
+	}
+
+	if (eth_proto & (MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
+			 | MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
+			 | MLX5E_PROT_MASK(MLX5E_100GBASE_CR4))) {
+			return PORT_DA;
+	}
+
+	if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_KX4)
+			 | MLX5E_PROT_MASK(MLX5E_10GBASE_KR)
+			 | MLX5E_PROT_MASK(MLX5E_40GBASE_KR4)
+			 | MLX5E_PROT_MASK(MLX5E_100GBASE_KR4))) {
+			return PORT_NONE;
+	}
+
+	return PORT_OTHER;
+}
+
+static void get_lp_advertising(u32 eth_proto_lp, u32 *lp_advertising)
+{
+	*lp_advertising = ptys2ethtool_adver_link(eth_proto_lp);
+}
+
+static int mlx5e_get_settings(struct net_device *netdev,
+			      struct ethtool_cmd *cmd)
+{
+	struct mlx5e_priv *priv    = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 eth_proto_cap;
+	u32 eth_proto_admin;
+	u32 eth_proto_lp;
+	u32 eth_proto_oper;
+	int err;
+
+	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
+
+	if (err) {
+		netdev_err(netdev, "%s: query port ptys failed: %d\n",
+			   __func__, err);
+		goto err_query_ptys;
+	}
+
+	eth_proto_cap   = MLX5_GET(ptys_reg, out, eth_proto_capability);
+	eth_proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
+	eth_proto_oper  = MLX5_GET(ptys_reg, out, eth_proto_oper);
+	eth_proto_lp    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
+
+	cmd->supported   = 0;
+	cmd->advertising = 0;
+
+	get_supported(eth_proto_cap, &cmd->supported);
+	get_advertising(eth_proto_admin, 0, 0, &cmd->advertising);
+	get_speed_duplex(netdev, eth_proto_oper, cmd);
+
+	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
+
+	cmd->port = get_connector_port(eth_proto_oper);
+	get_lp_advertising(eth_proto_lp, &cmd->lp_advertising);
+
+	cmd->transceiver = XCVR_INTERNAL;
+
+err_query_ptys:
+	return err;
+}
+
+static u32 mlx5e_ethtool2ptys_adver_link(u32 link_modes)
+{
+	u32 i, ptys_modes = 0;
+
+	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
+		if (ptys2ethtool_table[i].advertised & link_modes)
+			ptys_modes |= MLX5E_PROT_MASK(i);
+	}
+
+	return ptys_modes;
+}
+
+static u32 mlx5e_ethtool2ptys_speed_link(u32 speed)
+{
+	u32 i, speed_links = 0;
+
+	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
+		if (ptys2ethtool_table[i].speed == speed)
+			speed_links |= MLX5E_PROT_MASK(i);
+	}
+
+	return speed_links;
+}
+
+static int mlx5e_set_settings(struct net_device *netdev,
+			      struct ethtool_cmd *cmd)
+{
+	struct mlx5e_priv *priv    = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 link_modes;
+	u32 speed;
+	u32 eth_proto_cap, eth_proto_admin;
+	u8 port_status;
+	int err;
+
+	speed = ethtool_cmd_speed(cmd);
+
+	link_modes = cmd->autoneg == AUTONEG_ENABLE ?
+		mlx5e_ethtool2ptys_adver_link(cmd->advertising) :
+		mlx5e_ethtool2ptys_speed_link(speed);
+
+	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
+	if (err) {
+		netdev_err(netdev, "%s: query port eth proto cap failed: %d\n",
+			   __func__, err);
+		goto out;
+	}
+
+	link_modes = link_modes & eth_proto_cap;
+	if (!link_modes) {
+		netdev_err(netdev, "%s: Not supported link mode(s) requested",
+			   __func__);
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = mlx5_query_port_proto_admin(mdev, &eth_proto_admin, MLX5_PTYS_EN);
+	if (err) {
+		netdev_err(netdev, "%s: query port eth proto admin failed: %d\n",
+			   __func__, err);
+		goto out;
+	}
+
+	if (link_modes == eth_proto_admin)
+		goto out;
+
+	err = mlx5_set_port_proto(mdev, link_modes, MLX5_PTYS_EN);
+	if (err) {
+		netdev_err(netdev, "%s: set port eth proto admin failed: %d\n",
+			   __func__, err);
+		goto out;
+	}
+
+	err = mlx5_query_port_status(mdev, &port_status);
+	if (err)
+		goto out;
+
+	if (port_status == MLX5_PORT_DOWN)
+		return 0;
+
+	err = mlx5_set_port_status(mdev, MLX5_PORT_DOWN);
+	if (err)
+		goto out;
+	err = mlx5_set_port_status(mdev, MLX5_PORT_UP);
+out:
+	return err;
+}
+
+const struct ethtool_ops mlx5e_ethtool_ops = {
+	.get_drvinfo       = mlx5e_get_drvinfo,
+	.get_link          = ethtool_op_get_link,
+	.get_strings       = mlx5e_get_strings,
+	.get_sset_count    = mlx5e_get_sset_count,
+	.get_ethtool_stats = mlx5e_get_ethtool_stats,
+	.get_ringparam     = mlx5e_get_ringparam,
+	.set_ringparam     = mlx5e_set_ringparam,
+	.get_channels      = mlx5e_get_channels,
+	.set_channels      = mlx5e_set_channels,
+	.get_coalesce      = mlx5e_get_coalesce,
+	.set_coalesce      = mlx5e_set_coalesce,
+	.get_settings      = mlx5e_get_settings,
+	.set_settings      = mlx5e_set_settings,
+};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c
new file mode 100644
index 000000000000..120db80c47aa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_flow_table.c
@@ -0,0 +1,860 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/list.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/mlx5/flow_table.h>
+#include "en.h"
+
+enum {
+	MLX5E_FULLMATCH = 0,
+	MLX5E_ALLMULTI  = 1,
+	MLX5E_PROMISC   = 2,
+};
+
+enum {
+	MLX5E_UC        = 0,
+	MLX5E_MC_IPV4   = 1,
+	MLX5E_MC_IPV6   = 2,
+	MLX5E_MC_OTHER  = 3,
+};
+
+enum {
+	MLX5E_ACTION_NONE = 0,
+	MLX5E_ACTION_ADD  = 1,
+	MLX5E_ACTION_DEL  = 2,
+};
+
+struct mlx5e_eth_addr_hash_node {
+	struct hlist_node          hlist;
+	u8                         action;
+	struct mlx5e_eth_addr_info ai;
+};
+
+static inline int mlx5e_hash_eth_addr(u8 *addr)
+{
+	return addr[5];
+}
+
+static void mlx5e_add_eth_addr_to_hash(struct hlist_head *hash, u8 *addr)
+{
+	struct mlx5e_eth_addr_hash_node *hn;
+	int ix = mlx5e_hash_eth_addr(addr);
+	int found = 0;
+
+	hlist_for_each_entry(hn, &hash[ix], hlist)
+		if (ether_addr_equal_64bits(hn->ai.addr, addr)) {
+			found = 1;
+			break;
+		}
+
+	if (found) {
+		hn->action = MLX5E_ACTION_NONE;
+		return;
+	}
+
+	hn = kzalloc(sizeof(*hn), GFP_ATOMIC);
+	if (!hn)
+		return;
+
+	ether_addr_copy(hn->ai.addr, addr);
+	hn->action = MLX5E_ACTION_ADD;
+
+	hlist_add_head(&hn->hlist, &hash[ix]);
+}
+
+static void mlx5e_del_eth_addr_from_hash(struct mlx5e_eth_addr_hash_node *hn)
+{
+	hlist_del(&hn->hlist);
+	kfree(hn);
+}
+
+static void mlx5e_del_eth_addr_from_flow_table(struct mlx5e_priv *priv,
+					       struct mlx5e_eth_addr_info *ai)
+{
+	void *ft = priv->ft.main;
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV6_TCP))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_TCP]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV4_TCP))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_TCP]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV6_UDP))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6_UDP]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV4_UDP))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4_UDP]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV6))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV6]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_IPV4))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_IPV4]);
+
+	if (ai->tt_vec & (1 << MLX5E_TT_ANY))
+		mlx5_del_flow_table_entry(ft, ai->ft_ix[MLX5E_TT_ANY]);
+}
+
+static int mlx5e_get_eth_addr_type(u8 *addr)
+{
+	if (is_unicast_ether_addr(addr))
+		return MLX5E_UC;
+
+	if ((addr[0] == 0x01) &&
+	    (addr[1] == 0x00) &&
+	    (addr[2] == 0x5e) &&
+	   !(addr[3] &  0x80))
+		return MLX5E_MC_IPV4;
+
+	if ((addr[0] == 0x33) &&
+	    (addr[1] == 0x33))
+		return MLX5E_MC_IPV6;
+
+	return MLX5E_MC_OTHER;
+}
+
+static u32 mlx5e_get_tt_vec(struct mlx5e_eth_addr_info *ai, int type)
+{
+	int eth_addr_type;
+	u32 ret;
+
+	switch (type) {
+	case MLX5E_FULLMATCH:
+		eth_addr_type = mlx5e_get_eth_addr_type(ai->addr);
+		switch (eth_addr_type) {
+		case MLX5E_UC:
+			ret =
+				(1 << MLX5E_TT_IPV4_TCP) |
+				(1 << MLX5E_TT_IPV6_TCP) |
+				(1 << MLX5E_TT_IPV4_UDP) |
+				(1 << MLX5E_TT_IPV6_UDP) |
+				(1 << MLX5E_TT_IPV4)     |
+				(1 << MLX5E_TT_IPV6)     |
+				(1 << MLX5E_TT_ANY)      |
+				0;
+			break;
+
+		case MLX5E_MC_IPV4:
+			ret =
+				(1 << MLX5E_TT_IPV4_UDP) |
+				(1 << MLX5E_TT_IPV4)     |
+				0;
+			break;
+
+		case MLX5E_MC_IPV6:
+			ret =
+				(1 << MLX5E_TT_IPV6_UDP) |
+				(1 << MLX5E_TT_IPV6)     |
+				0;
+			break;
+
+		case MLX5E_MC_OTHER:
+			ret =
+				(1 << MLX5E_TT_ANY)      |
+				0;
+			break;
+		}
+
+		break;
+
+	case MLX5E_ALLMULTI:
+		ret =
+			(1 << MLX5E_TT_IPV4_UDP) |
+			(1 << MLX5E_TT_IPV6_UDP) |
+			(1 << MLX5E_TT_IPV4)     |
+			(1 << MLX5E_TT_IPV6)     |
+			(1 << MLX5E_TT_ANY)      |
+			0;
+		break;
+
+	default: /* MLX5E_PROMISC */
+		ret =
+			(1 << MLX5E_TT_IPV4_TCP) |
+			(1 << MLX5E_TT_IPV6_TCP) |
+			(1 << MLX5E_TT_IPV4_UDP) |
+			(1 << MLX5E_TT_IPV6_UDP) |
+			(1 << MLX5E_TT_IPV4)     |
+			(1 << MLX5E_TT_IPV6)     |
+			(1 << MLX5E_TT_ANY)      |
+			0;
+		break;
+	}
+
+	return ret;
+}
+
+static int __mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv,
+				     struct mlx5e_eth_addr_info *ai, int type,
+				     void *flow_context, void *match_criteria)
+{
+	u8 match_criteria_enable = 0;
+	void *match_value;
+	void *dest;
+	u8   *dmac;
+	u8   *match_criteria_dmac;
+	void *ft   = priv->ft.main;
+	u32  *tirn = priv->tirn;
+	u32  tt_vec;
+	int  err;
+
+	match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value);
+	dmac = MLX5_ADDR_OF(fte_match_param, match_value,
+			    outer_headers.dmac_47_16);
+	match_criteria_dmac = MLX5_ADDR_OF(fte_match_param, match_criteria,
+					   outer_headers.dmac_47_16);
+	dest = MLX5_ADDR_OF(flow_context, flow_context, destination);
+
+	MLX5_SET(flow_context, flow_context, action,
+		 MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
+	MLX5_SET(flow_context, flow_context, destination_list_size, 1);
+	MLX5_SET(dest_format_struct, dest, destination_type,
+		 MLX5_FLOW_CONTEXT_DEST_TYPE_TIR);
+
+	switch (type) {
+	case MLX5E_FULLMATCH:
+		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		memset(match_criteria_dmac, 0xff, ETH_ALEN);
+		ether_addr_copy(dmac, ai->addr);
+		break;
+
+	case MLX5E_ALLMULTI:
+		match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+		match_criteria_dmac[0] = 0x01;
+		dmac[0] = 0x01;
+		break;
+
+	case MLX5E_PROMISC:
+		break;
+	}
+
+	tt_vec = mlx5e_get_tt_vec(ai, type);
+
+	if (tt_vec & (1 << MLX5E_TT_ANY)) {
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_ANY]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_ANY]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_ANY);
+	}
+
+	match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 outer_headers.ethertype);
+
+	if (tt_vec & (1 << MLX5E_TT_IPV4)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IP);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV4]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV4]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV4);
+	}
+
+	if (tt_vec & (1 << MLX5E_TT_IPV6)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IPV6);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV6]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV6]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV6);
+	}
+
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 outer_headers.ip_protocol);
+	MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol,
+		 IPPROTO_UDP);
+
+	if (tt_vec & (1 << MLX5E_TT_IPV4_UDP)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IP);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV4_UDP]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV4_UDP]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV4_UDP);
+	}
+
+	if (tt_vec & (1 << MLX5E_TT_IPV6_UDP)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IPV6);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV6_UDP]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV6_UDP]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV6_UDP);
+	}
+
+	MLX5_SET(fte_match_param, match_value, outer_headers.ip_protocol,
+		 IPPROTO_TCP);
+
+	if (tt_vec & (1 << MLX5E_TT_IPV4_TCP)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IP);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV4_TCP]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV4_TCP]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV4_TCP);
+	}
+
+	if (tt_vec & (1 << MLX5E_TT_IPV6_TCP)) {
+		MLX5_SET(fte_match_param, match_value, outer_headers.ethertype,
+			 ETH_P_IPV6);
+		MLX5_SET(dest_format_struct, dest, destination_id,
+			 tirn[MLX5E_TT_IPV6_TCP]);
+		err = mlx5_add_flow_table_entry(ft, match_criteria_enable,
+						match_criteria, flow_context,
+						&ai->ft_ix[MLX5E_TT_IPV6_TCP]);
+		if (err) {
+			mlx5e_del_eth_addr_from_flow_table(priv, ai);
+			return err;
+		}
+		ai->tt_vec |= (1 << MLX5E_TT_IPV6_TCP);
+	}
+
+	return 0;
+}
+
+static int mlx5e_add_eth_addr_rule(struct mlx5e_priv *priv,
+				   struct mlx5e_eth_addr_info *ai, int type)
+{
+	u32 *flow_context;
+	u32 *match_criteria;
+	int err;
+
+	flow_context   = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) +
+				      MLX5_ST_SZ_BYTES(dest_format_struct));
+	match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
+	if (!flow_context || !match_criteria) {
+		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
+		err = -ENOMEM;
+		goto add_eth_addr_rule_out;
+	}
+
+	err = __mlx5e_add_eth_addr_rule(priv, ai, type, flow_context,
+					match_criteria);
+	if (err)
+		netdev_err(priv->netdev, "%s: failed\n", __func__);
+
+add_eth_addr_rule_out:
+	kvfree(match_criteria);
+	kvfree(flow_context);
+	return err;
+}
+
+enum mlx5e_vlan_rule_type {
+	MLX5E_VLAN_RULE_TYPE_UNTAGGED,
+	MLX5E_VLAN_RULE_TYPE_ANY_VID,
+	MLX5E_VLAN_RULE_TYPE_MATCH_VID,
+};
+
+static int mlx5e_add_vlan_rule(struct mlx5e_priv *priv,
+			       enum mlx5e_vlan_rule_type rule_type, u16 vid)
+{
+	u8 match_criteria_enable = 0;
+	u32 *flow_context;
+	void *match_value;
+	void *dest;
+	u32 *match_criteria;
+	u32 *ft_ix;
+	int err;
+
+	flow_context   = mlx5_vzalloc(MLX5_ST_SZ_BYTES(flow_context) +
+				      MLX5_ST_SZ_BYTES(dest_format_struct));
+	match_criteria = mlx5_vzalloc(MLX5_ST_SZ_BYTES(fte_match_param));
+	if (!flow_context || !match_criteria) {
+		netdev_err(priv->netdev, "%s: alloc failed\n", __func__);
+		err = -ENOMEM;
+		goto add_vlan_rule_out;
+	}
+	match_value = MLX5_ADDR_OF(flow_context, flow_context, match_value);
+	dest = MLX5_ADDR_OF(flow_context, flow_context, destination);
+
+	MLX5_SET(flow_context, flow_context, action,
+		 MLX5_FLOW_CONTEXT_ACTION_FWD_DEST);
+	MLX5_SET(flow_context, flow_context, destination_list_size, 1);
+	MLX5_SET(dest_format_struct, dest, destination_type,
+		 MLX5_FLOW_CONTEXT_DEST_TYPE_FLOW_TABLE);
+	MLX5_SET(dest_format_struct, dest, destination_id,
+		 mlx5_get_flow_table_id(priv->ft.main));
+
+	match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 outer_headers.vlan_tag);
+
+	switch (rule_type) {
+	case MLX5E_VLAN_RULE_TYPE_UNTAGGED:
+		ft_ix = &priv->vlan.untagged_rule_ft_ix;
+		break;
+	case MLX5E_VLAN_RULE_TYPE_ANY_VID:
+		ft_ix = &priv->vlan.any_vlan_rule_ft_ix;
+		MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag,
+			 1);
+		break;
+	default: /* MLX5E_VLAN_RULE_TYPE_MATCH_VID */
+		ft_ix = &priv->vlan.active_vlans_ft_ix[vid];
+		MLX5_SET(fte_match_param, match_value, outer_headers.vlan_tag,
+			 1);
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 outer_headers.first_vid);
+		MLX5_SET(fte_match_param, match_value, outer_headers.first_vid,
+			 vid);
+		break;
+	}
+
+	err = mlx5_add_flow_table_entry(priv->ft.vlan, match_criteria_enable,
+					match_criteria, flow_context, ft_ix);
+	if (err)
+		netdev_err(priv->netdev, "%s: failed\n", __func__);
+
+add_vlan_rule_out:
+	kvfree(match_criteria);
+	kvfree(flow_context);
+	return err;
+}
+
+static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv,
+				enum mlx5e_vlan_rule_type rule_type, u16 vid)
+{
+	switch (rule_type) {
+	case MLX5E_VLAN_RULE_TYPE_UNTAGGED:
+		mlx5_del_flow_table_entry(priv->ft.vlan,
+					  priv->vlan.untagged_rule_ft_ix);
+		break;
+	case MLX5E_VLAN_RULE_TYPE_ANY_VID:
+		mlx5_del_flow_table_entry(priv->ft.vlan,
+					  priv->vlan.any_vlan_rule_ft_ix);
+		break;
+	case MLX5E_VLAN_RULE_TYPE_MATCH_VID:
+		mlx5_del_flow_table_entry(priv->ft.vlan,
+					  priv->vlan.active_vlans_ft_ix[vid]);
+		break;
+	}
+}
+
+void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv)
+{
+	WARN_ON(!mutex_is_locked(&priv->state_lock));
+
+	if (priv->vlan.filter_disabled) {
+		priv->vlan.filter_disabled = false;
+		if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+			mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID,
+					    0);
+	}
+}
+
+void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv)
+{
+	WARN_ON(!mutex_is_locked(&priv->state_lock));
+
+	if (!priv->vlan.filter_disabled) {
+		priv->vlan.filter_disabled = true;
+		if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+			mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID,
+					    0);
+	}
+}
+
+int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
+			  u16 vid)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	set_bit(vid, priv->vlan.active_vlans);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID,
+					  vid);
+
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
+			   u16 vid)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	mutex_lock(&priv->state_lock);
+
+	clear_bit(vid, priv->vlan.active_vlans);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, vid);
+
+	mutex_unlock(&priv->state_lock);
+
+	return 0;
+}
+
+int mlx5e_add_all_vlan_rules(struct mlx5e_priv *priv)
+{
+	u16 vid;
+	int err;
+
+	for_each_set_bit(vid, priv->vlan.active_vlans, VLAN_N_VID) {
+		err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID,
+					  vid);
+		if (err)
+			return err;
+	}
+
+	err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0);
+	if (err)
+		return err;
+
+	if (priv->vlan.filter_disabled) {
+		err = mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID,
+					  0);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void mlx5e_del_all_vlan_rules(struct mlx5e_priv *priv)
+{
+	u16 vid;
+
+	if (priv->vlan.filter_disabled)
+		mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_ANY_VID, 0);
+
+	mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_UNTAGGED, 0);
+
+	for_each_set_bit(vid, priv->vlan.active_vlans, VLAN_N_VID)
+		mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_VID, vid);
+}
+
+#define mlx5e_for_each_hash_node(hn, tmp, hash, i) \
+	for (i = 0; i < MLX5E_ETH_ADDR_HASH_SIZE; i++) \
+		hlist_for_each_entry_safe(hn, tmp, &hash[i], hlist)
+
+static void mlx5e_execute_action(struct mlx5e_priv *priv,
+				 struct mlx5e_eth_addr_hash_node *hn)
+{
+	switch (hn->action) {
+	case MLX5E_ACTION_ADD:
+		mlx5e_add_eth_addr_rule(priv, &hn->ai, MLX5E_FULLMATCH);
+		hn->action = MLX5E_ACTION_NONE;
+		break;
+
+	case MLX5E_ACTION_DEL:
+		mlx5e_del_eth_addr_from_flow_table(priv, &hn->ai);
+		mlx5e_del_eth_addr_from_hash(hn);
+		break;
+	}
+}
+
+static void mlx5e_sync_netdev_addr(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+	struct netdev_hw_addr *ha;
+
+	netif_addr_lock_bh(netdev);
+
+	mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_uc,
+				   priv->netdev->dev_addr);
+
+	netdev_for_each_uc_addr(ha, netdev)
+		mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_uc, ha->addr);
+
+	netdev_for_each_mc_addr(ha, netdev)
+		mlx5e_add_eth_addr_to_hash(priv->eth_addr.netdev_mc, ha->addr);
+
+	netif_addr_unlock_bh(netdev);
+}
+
+static void mlx5e_apply_netdev_addr(struct mlx5e_priv *priv)
+{
+	struct mlx5e_eth_addr_hash_node *hn;
+	struct hlist_node *tmp;
+	int i;
+
+	mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_uc, i)
+		mlx5e_execute_action(priv, hn);
+
+	mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_mc, i)
+		mlx5e_execute_action(priv, hn);
+}
+
+static void mlx5e_handle_netdev_addr(struct mlx5e_priv *priv)
+{
+	struct mlx5e_eth_addr_hash_node *hn;
+	struct hlist_node *tmp;
+	int i;
+
+	mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_uc, i)
+		hn->action = MLX5E_ACTION_DEL;
+	mlx5e_for_each_hash_node(hn, tmp, priv->eth_addr.netdev_mc, i)
+		hn->action = MLX5E_ACTION_DEL;
+
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_sync_netdev_addr(priv);
+
+	mlx5e_apply_netdev_addr(priv);
+}
+
+void mlx5e_set_rx_mode_core(struct mlx5e_priv *priv)
+{
+	struct mlx5e_eth_addr_db *ea = &priv->eth_addr;
+	struct net_device *ndev = priv->netdev;
+
+	bool rx_mode_enable   = test_bit(MLX5E_STATE_OPENED, &priv->state);
+	bool promisc_enabled   = rx_mode_enable && (ndev->flags & IFF_PROMISC);
+	bool allmulti_enabled  = rx_mode_enable && (ndev->flags & IFF_ALLMULTI);
+	bool broadcast_enabled = rx_mode_enable;
+
+	bool enable_promisc    = !ea->promisc_enabled   &&  promisc_enabled;
+	bool disable_promisc   =  ea->promisc_enabled   && !promisc_enabled;
+	bool enable_allmulti   = !ea->allmulti_enabled  &&  allmulti_enabled;
+	bool disable_allmulti  =  ea->allmulti_enabled  && !allmulti_enabled;
+	bool enable_broadcast  = !ea->broadcast_enabled &&  broadcast_enabled;
+	bool disable_broadcast =  ea->broadcast_enabled && !broadcast_enabled;
+
+	if (enable_promisc)
+		mlx5e_add_eth_addr_rule(priv, &ea->promisc, MLX5E_PROMISC);
+	if (enable_allmulti)
+		mlx5e_add_eth_addr_rule(priv, &ea->allmulti, MLX5E_ALLMULTI);
+	if (enable_broadcast)
+		mlx5e_add_eth_addr_rule(priv, &ea->broadcast, MLX5E_FULLMATCH);
+
+	mlx5e_handle_netdev_addr(priv);
+
+	if (disable_broadcast)
+		mlx5e_del_eth_addr_from_flow_table(priv, &ea->broadcast);
+	if (disable_allmulti)
+		mlx5e_del_eth_addr_from_flow_table(priv, &ea->allmulti);
+	if (disable_promisc)
+		mlx5e_del_eth_addr_from_flow_table(priv, &ea->promisc);
+
+	ea->promisc_enabled   = promisc_enabled;
+	ea->allmulti_enabled  = allmulti_enabled;
+	ea->broadcast_enabled = broadcast_enabled;
+}
+
+void mlx5e_set_rx_mode_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       set_rx_mode_work);
+
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_set_rx_mode_core(priv);
+	mutex_unlock(&priv->state_lock);
+}
+
+void mlx5e_init_eth_addr(struct mlx5e_priv *priv)
+{
+	ether_addr_copy(priv->eth_addr.broadcast.addr, priv->netdev->broadcast);
+}
+
+static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_table_group *g;
+	u8 *dmac;
+
+	g = kcalloc(9, sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return -ENOMEM;
+
+	g[0].log_sz = 2;
+	g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria,
+			 outer_headers.ethertype);
+	MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria,
+			 outer_headers.ip_protocol);
+
+	g[1].log_sz = 1;
+	g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria,
+			 outer_headers.ethertype);
+
+	g[2].log_sz = 0;
+
+	g[3].log_sz = 14;
+	g[3].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[3].match_criteria,
+			    outer_headers.dmac_47_16);
+	memset(dmac, 0xff, ETH_ALEN);
+	MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria,
+			 outer_headers.ethertype);
+	MLX5_SET_TO_ONES(fte_match_param, g[3].match_criteria,
+			 outer_headers.ip_protocol);
+
+	g[4].log_sz = 13;
+	g[4].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[4].match_criteria,
+			    outer_headers.dmac_47_16);
+	memset(dmac, 0xff, ETH_ALEN);
+	MLX5_SET_TO_ONES(fte_match_param, g[4].match_criteria,
+			 outer_headers.ethertype);
+
+	g[5].log_sz = 11;
+	g[5].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[5].match_criteria,
+			    outer_headers.dmac_47_16);
+	memset(dmac, 0xff, ETH_ALEN);
+
+	g[6].log_sz = 2;
+	g[6].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[6].match_criteria,
+			    outer_headers.dmac_47_16);
+	dmac[0] = 0x01;
+	MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria,
+			 outer_headers.ethertype);
+	MLX5_SET_TO_ONES(fte_match_param, g[6].match_criteria,
+			 outer_headers.ip_protocol);
+
+	g[7].log_sz = 1;
+	g[7].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[7].match_criteria,
+			    outer_headers.dmac_47_16);
+	dmac[0] = 0x01;
+	MLX5_SET_TO_ONES(fte_match_param, g[7].match_criteria,
+			 outer_headers.ethertype);
+
+	g[8].log_sz = 0;
+	g[8].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	dmac = MLX5_ADDR_OF(fte_match_param, g[8].match_criteria,
+			    outer_headers.dmac_47_16);
+	dmac[0] = 0x01;
+	priv->ft.main = mlx5_create_flow_table(priv->mdev, 1,
+					       MLX5_FLOW_TABLE_TYPE_NIC_RCV,
+					       9, g);
+	kfree(g);
+
+	return priv->ft.main ? 0 : -ENOMEM;
+}
+
+static void mlx5e_destroy_main_flow_table(struct mlx5e_priv *priv)
+{
+	mlx5_destroy_flow_table(priv->ft.main);
+}
+
+static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_table_group *g;
+
+	g = kcalloc(2, sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return -ENOMEM;
+
+	g[0].log_sz = 12;
+	g[0].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria,
+			 outer_headers.vlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, g[0].match_criteria,
+			 outer_headers.first_vid);
+
+	/* untagged + any vlan id */
+	g[1].log_sz = 1;
+	g[1].match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	MLX5_SET_TO_ONES(fte_match_param, g[1].match_criteria,
+			 outer_headers.vlan_tag);
+
+	priv->ft.vlan = mlx5_create_flow_table(priv->mdev, 0,
+					       MLX5_FLOW_TABLE_TYPE_NIC_RCV,
+					       2, g);
+
+	kfree(g);
+	return priv->ft.vlan ? 0 : -ENOMEM;
+}
+
+static void mlx5e_destroy_vlan_flow_table(struct mlx5e_priv *priv)
+{
+	mlx5_destroy_flow_table(priv->ft.vlan);
+}
+
+int mlx5e_open_flow_table(struct mlx5e_priv *priv)
+{
+	int err;
+
+	err = mlx5e_create_main_flow_table(priv);
+	if (err)
+		return err;
+
+	err = mlx5e_create_vlan_flow_table(priv);
+	if (err)
+		goto err_destroy_main_flow_table;
+
+	return 0;
+
+err_destroy_main_flow_table:
+	mlx5e_destroy_main_flow_table(priv);
+
+	return err;
+}
+
+void mlx5e_close_flow_table(struct mlx5e_priv *priv)
+{
+	mlx5e_destroy_vlan_flow_table(priv);
+	mlx5e_destroy_main_flow_table(priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
new file mode 100644
index 000000000000..40206da1f9d7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -0,0 +1,1915 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mlx5/flow_table.h>
+#include "en.h"
+
+struct mlx5e_rq_param {
+	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
+	struct mlx5_wq_param       wq;
+};
+
+struct mlx5e_sq_param {
+	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
+	struct mlx5_wq_param       wq;
+};
+
+struct mlx5e_cq_param {
+	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
+	struct mlx5_wq_param       wq;
+	u16                        eq_ix;
+};
+
+struct mlx5e_channel_param {
+	struct mlx5e_rq_param      rq;
+	struct mlx5e_sq_param      sq;
+	struct mlx5e_cq_param      rx_cq;
+	struct mlx5e_cq_param      tx_cq;
+};
+
+static void mlx5e_update_carrier(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 port_state;
+
+	port_state = mlx5_query_vport_state(mdev,
+		MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT);
+
+	if (port_state == VPORT_STATE_UP)
+		netif_carrier_on(priv->netdev);
+	else
+		netif_carrier_off(priv->netdev);
+}
+
+static void mlx5e_update_carrier_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       update_carrier_work);
+
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
+		mlx5e_update_carrier(priv);
+	mutex_unlock(&priv->state_lock);
+}
+
+void mlx5e_update_stats(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_vport_stats *s = &priv->stats.vport;
+	struct mlx5e_rq_stats *rq_stats;
+	struct mlx5e_sq_stats *sq_stats;
+	u32 in[MLX5_ST_SZ_DW(query_vport_counter_in)];
+	u32 *out;
+	int outlen = MLX5_ST_SZ_BYTES(query_vport_counter_out);
+	u64 tx_offload_none;
+	int i, j;
+
+	out = mlx5_vzalloc(outlen);
+	if (!out)
+		return;
+
+	/* Collect firts the SW counters and then HW for consistency */
+	s->tso_packets		= 0;
+	s->tso_bytes		= 0;
+	s->tx_queue_stopped	= 0;
+	s->tx_queue_wake	= 0;
+	s->tx_queue_dropped	= 0;
+	tx_offload_none		= 0;
+	s->lro_packets		= 0;
+	s->lro_bytes		= 0;
+	s->rx_csum_none		= 0;
+	s->rx_wqe_err		= 0;
+	for (i = 0; i < priv->params.num_channels; i++) {
+		rq_stats = &priv->channel[i]->rq.stats;
+
+		s->lro_packets	+= rq_stats->lro_packets;
+		s->lro_bytes	+= rq_stats->lro_bytes;
+		s->rx_csum_none	+= rq_stats->csum_none;
+		s->rx_wqe_err   += rq_stats->wqe_err;
+
+		for (j = 0; j < priv->num_tc; j++) {
+			sq_stats = &priv->channel[i]->sq[j].stats;
+
+			s->tso_packets		+= sq_stats->tso_packets;
+			s->tso_bytes		+= sq_stats->tso_bytes;
+			s->tx_queue_stopped	+= sq_stats->stopped;
+			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_queue_dropped	+= sq_stats->dropped;
+			tx_offload_none		+= sq_stats->csum_offload_none;
+		}
+	}
+
+	/* HW counters */
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(query_vport_counter_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
+	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
+	MLX5_SET(query_vport_counter_in, in, other_vport, 0);
+
+	memset(out, 0, outlen);
+
+	if (mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen))
+		goto free_out;
+
+#define MLX5_GET_CTR(p, x) \
+	MLX5_GET64(query_vport_counter_out, p, x)
+
+	s->rx_error_packets     =
+		MLX5_GET_CTR(out, received_errors.packets);
+	s->rx_error_bytes       =
+		MLX5_GET_CTR(out, received_errors.octets);
+	s->tx_error_packets     =
+		MLX5_GET_CTR(out, transmit_errors.packets);
+	s->tx_error_bytes       =
+		MLX5_GET_CTR(out, transmit_errors.octets);
+
+	s->rx_unicast_packets   =
+		MLX5_GET_CTR(out, received_eth_unicast.packets);
+	s->rx_unicast_bytes     =
+		MLX5_GET_CTR(out, received_eth_unicast.octets);
+	s->tx_unicast_packets   =
+		MLX5_GET_CTR(out, transmitted_eth_unicast.packets);
+	s->tx_unicast_bytes     =
+		MLX5_GET_CTR(out, transmitted_eth_unicast.octets);
+
+	s->rx_multicast_packets =
+		MLX5_GET_CTR(out, received_eth_multicast.packets);
+	s->rx_multicast_bytes   =
+		MLX5_GET_CTR(out, received_eth_multicast.octets);
+	s->tx_multicast_packets =
+		MLX5_GET_CTR(out, transmitted_eth_multicast.packets);
+	s->tx_multicast_bytes   =
+		MLX5_GET_CTR(out, transmitted_eth_multicast.octets);
+
+	s->rx_broadcast_packets =
+		MLX5_GET_CTR(out, received_eth_broadcast.packets);
+	s->rx_broadcast_bytes   =
+		MLX5_GET_CTR(out, received_eth_broadcast.octets);
+	s->tx_broadcast_packets =
+		MLX5_GET_CTR(out, transmitted_eth_broadcast.packets);
+	s->tx_broadcast_bytes   =
+		MLX5_GET_CTR(out, transmitted_eth_broadcast.octets);
+
+	s->rx_packets =
+		s->rx_unicast_packets +
+		s->rx_multicast_packets +
+		s->rx_broadcast_packets;
+	s->rx_bytes =
+		s->rx_unicast_bytes +
+		s->rx_multicast_bytes +
+		s->rx_broadcast_bytes;
+	s->tx_packets =
+		s->tx_unicast_packets +
+		s->tx_multicast_packets +
+		s->tx_broadcast_packets;
+	s->tx_bytes =
+		s->tx_unicast_bytes +
+		s->tx_multicast_bytes +
+		s->tx_broadcast_bytes;
+
+	/* Update calculated offload counters */
+	s->tx_csum_offload = s->tx_packets - tx_offload_none;
+	s->rx_csum_good    = s->rx_packets - s->rx_csum_none;
+
+free_out:
+	kvfree(out);
+}
+
+static void mlx5e_update_stats_work(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
+					       update_stats_work);
+	mutex_lock(&priv->state_lock);
+	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		mlx5e_update_stats(priv);
+		schedule_delayed_work(dwork,
+				      msecs_to_jiffies(
+					      MLX5E_UPDATE_STATS_INTERVAL));
+	}
+	mutex_unlock(&priv->state_lock);
+}
+
+static void __mlx5e_async_event(struct mlx5e_priv *priv,
+				enum mlx5_dev_event event)
+{
+	switch (event) {
+	case MLX5_DEV_EVENT_PORT_UP:
+	case MLX5_DEV_EVENT_PORT_DOWN:
+		schedule_work(&priv->update_carrier_work);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
+			      enum mlx5_dev_event event, unsigned long param)
+{
+	struct mlx5e_priv *priv = vpriv;
+
+	spin_lock(&priv->async_events_spinlock);
+	if (test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state))
+		__mlx5e_async_event(priv, event);
+	spin_unlock(&priv->async_events_spinlock);
+}
+
+static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+}
+
+static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
+{
+	spin_lock_irq(&priv->async_events_spinlock);
+	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state);
+	spin_unlock_irq(&priv->async_events_spinlock);
+}
+
+#define MLX5E_HW2SW_MTU(hwmtu) (hwmtu - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN))
+#define MLX5E_SW2HW_MTU(swmtu) (swmtu + (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN))
+
+static int mlx5e_create_rq(struct mlx5e_channel *c,
+			   struct mlx5e_rq_param *param,
+			   struct mlx5e_rq *rq)
+{
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	void *rqc = param->rqc;
+	void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq);
+	int wq_sz;
+	int err;
+	int i;
+
+	err = mlx5_wq_ll_create(mdev, &param->wq, rqc_wq, &rq->wq,
+				&rq->wq_ctrl);
+	if (err)
+		return err;
+
+	rq->wq.db = &rq->wq.db[MLX5_RCV_DBR];
+
+	wq_sz = mlx5_wq_ll_get_size(&rq->wq);
+	rq->skb = kzalloc_node(wq_sz * sizeof(*rq->skb), GFP_KERNEL,
+			       cpu_to_node(c->cpu));
+	if (!rq->skb) {
+		err = -ENOMEM;
+		goto err_rq_wq_destroy;
+	}
+
+	rq->wqe_sz = (priv->params.lro_en) ? priv->params.lro_wqe_sz :
+					     MLX5E_SW2HW_MTU(priv->netdev->mtu);
+	rq->wqe_sz = SKB_DATA_ALIGN(rq->wqe_sz + MLX5E_NET_IP_ALIGN);
+
+	for (i = 0; i < wq_sz; i++) {
+		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i);
+		u32 byte_count = rq->wqe_sz - MLX5E_NET_IP_ALIGN;
+
+		wqe->data.lkey       = c->mkey_be;
+		wqe->data.byte_count =
+			cpu_to_be32(byte_count | MLX5_HW_START_PADDING);
+	}
+
+	rq->pdev    = c->pdev;
+	rq->netdev  = c->netdev;
+	rq->channel = c;
+	rq->ix      = c->ix;
+
+	return 0;
+
+err_rq_wq_destroy:
+	mlx5_wq_destroy(&rq->wq_ctrl);
+
+	return err;
+}
+
+static void mlx5e_destroy_rq(struct mlx5e_rq *rq)
+{
+	kfree(rq->skb);
+	mlx5_wq_destroy(&rq->wq_ctrl);
+}
+
+static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param)
+{
+	struct mlx5e_channel *c = rq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	void *in;
+	void *rqc;
+	void *wq;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(create_rq_in) +
+		sizeof(u64) * rq->wq_ctrl.buf.npages;
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
+	wq  = MLX5_ADDR_OF(rqc, rqc, wq);
+
+	memcpy(rqc, param->rqc, sizeof(param->rqc));
+
+	MLX5_SET(rqc,  rqc, cqn,		c->rq.cq.mcq.cqn);
+	MLX5_SET(rqc,  rqc, state,		MLX5_RQC_STATE_RST);
+	MLX5_SET(rqc,  rqc, flush_in_error_en,	1);
+	MLX5_SET(wq,   wq,  log_wq_pg_sz,	rq->wq_ctrl.buf.page_shift -
+						PAGE_SHIFT);
+	MLX5_SET64(wq, wq,  dbr_addr,		rq->wq_ctrl.db.dma);
+
+	mlx5_fill_page_array(&rq->wq_ctrl.buf,
+			     (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+
+	err = mlx5_core_create_rq(mdev, in, inlen, &rq->rqn);
+
+	kvfree(in);
+
+	return err;
+}
+
+static int mlx5e_modify_rq(struct mlx5e_rq *rq, int curr_state, int next_state)
+{
+	struct mlx5e_channel *c = rq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	void *in;
+	void *rqc;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
+
+	MLX5_SET(modify_rq_in, in, rq_state, curr_state);
+	MLX5_SET(rqc, rqc, state, next_state);
+
+	err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5e_disable_rq(struct mlx5e_rq *rq)
+{
+	struct mlx5e_channel *c = rq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mlx5_core_destroy_rq(mdev, rq->rqn);
+}
+
+static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq)
+{
+	struct mlx5e_channel *c = rq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_wq_ll *wq = &rq->wq;
+	int i;
+
+	for (i = 0; i < 1000; i++) {
+		if (wq->cur_sz >= priv->params.min_rx_wqes)
+			return 0;
+
+		msleep(20);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int mlx5e_open_rq(struct mlx5e_channel *c,
+			 struct mlx5e_rq_param *param,
+			 struct mlx5e_rq *rq)
+{
+	int err;
+
+	err = mlx5e_create_rq(c, param, rq);
+	if (err)
+		return err;
+
+	err = mlx5e_enable_rq(rq, param);
+	if (err)
+		goto err_destroy_rq;
+
+	err = mlx5e_modify_rq(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY);
+	if (err)
+		goto err_disable_rq;
+
+	set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
+	mlx5e_send_nop(&c->sq[0], true); /* trigger mlx5e_post_rx_wqes() */
+
+	return 0;
+
+err_disable_rq:
+	mlx5e_disable_rq(rq);
+err_destroy_rq:
+	mlx5e_destroy_rq(rq);
+
+	return err;
+}
+
+static void mlx5e_close_rq(struct mlx5e_rq *rq)
+{
+	clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
+	napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
+
+	mlx5e_modify_rq(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
+	while (!mlx5_wq_ll_is_empty(&rq->wq))
+		msleep(20);
+
+	/* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
+	napi_synchronize(&rq->channel->napi);
+
+	mlx5e_disable_rq(rq);
+	mlx5e_destroy_rq(rq);
+}
+
+static void mlx5e_free_sq_db(struct mlx5e_sq *sq)
+{
+	kfree(sq->dma_fifo);
+	kfree(sq->skb);
+}
+
+static int mlx5e_alloc_sq_db(struct mlx5e_sq *sq, int numa)
+{
+	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	sq->skb = kzalloc_node(wq_sz * sizeof(*sq->skb), GFP_KERNEL, numa);
+	sq->dma_fifo = kzalloc_node(df_sz * sizeof(*sq->dma_fifo), GFP_KERNEL,
+				    numa);
+
+	if (!sq->skb || !sq->dma_fifo) {
+		mlx5e_free_sq_db(sq);
+		return -ENOMEM;
+	}
+
+	sq->dma_fifo_mask = df_sz - 1;
+
+	return 0;
+}
+
+static int mlx5e_create_sq(struct mlx5e_channel *c,
+			   int tc,
+			   struct mlx5e_sq_param *param,
+			   struct mlx5e_sq *sq)
+{
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	void *sqc = param->sqc;
+	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc, wq);
+	int txq_ix;
+	int err;
+
+	err = mlx5_alloc_map_uar(mdev, &sq->uar);
+	if (err)
+		return err;
+
+	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq,
+				 &sq->wq_ctrl);
+	if (err)
+		goto err_unmap_free_uar;
+
+	sq->wq.db       = &sq->wq.db[MLX5_SND_DBR];
+	sq->uar_map     = sq->uar.map;
+	sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2;
+
+	err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu));
+	if (err)
+		goto err_sq_wq_destroy;
+
+	txq_ix = c->ix + tc * priv->params.num_channels;
+	sq->txq = netdev_get_tx_queue(priv->netdev, txq_ix);
+
+	sq->pdev    = c->pdev;
+	sq->mkey_be = c->mkey_be;
+	sq->channel = c;
+	sq->tc      = tc;
+	sq->edge    = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS;
+	priv->txq_to_sq_map[txq_ix] = sq;
+
+	return 0;
+
+err_sq_wq_destroy:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+
+err_unmap_free_uar:
+	mlx5_unmap_free_uar(mdev, &sq->uar);
+
+	return err;
+}
+
+static void mlx5e_destroy_sq(struct mlx5e_sq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5e_priv *priv = c->priv;
+
+	mlx5e_free_sq_db(sq);
+	mlx5_wq_destroy(&sq->wq_ctrl);
+	mlx5_unmap_free_uar(priv->mdev, &sq->uar);
+}
+
+static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	void *in;
+	void *sqc;
+	void *wq;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
+		sizeof(u64) * sq->wq_ctrl.buf.npages;
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	sqc = MLX5_ADDR_OF(create_sq_in, in, ctx);
+	wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+	memcpy(sqc, param->sqc, sizeof(param->sqc));
+
+	MLX5_SET(sqc,  sqc, user_index,		sq->tc);
+	MLX5_SET(sqc,  sqc, tis_num_0,		priv->tisn[sq->tc]);
+	MLX5_SET(sqc,  sqc, cqn,		c->sq[sq->tc].cq.mcq.cqn);
+	MLX5_SET(sqc,  sqc, state,		MLX5_SQC_STATE_RST);
+	MLX5_SET(sqc,  sqc, tis_lst_sz,		1);
+	MLX5_SET(sqc,  sqc, flush_in_error_en,	1);
+
+	MLX5_SET(wq,   wq, wq_type,       MLX5_WQ_TYPE_CYCLIC);
+	MLX5_SET(wq,   wq, uar_page,      sq->uar.index);
+	MLX5_SET(wq,   wq, log_wq_pg_sz,  sq->wq_ctrl.buf.page_shift -
+					  PAGE_SHIFT);
+	MLX5_SET64(wq, wq, dbr_addr,      sq->wq_ctrl.db.dma);
+
+	mlx5_fill_page_array(&sq->wq_ctrl.buf,
+			     (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+
+	err = mlx5_core_create_sq(mdev, in, inlen, &sq->sqn);
+
+	kvfree(in);
+
+	return err;
+}
+
+static int mlx5e_modify_sq(struct mlx5e_sq *sq, int curr_state, int next_state)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	void *in;
+	void *sqc;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_sq_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
+
+	MLX5_SET(modify_sq_in, in, sq_state, curr_state);
+	MLX5_SET(sqc, sqc, state, next_state);
+
+	err = mlx5_core_modify_sq(mdev, sq->sqn, in, inlen);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5e_disable_sq(struct mlx5e_sq *sq)
+{
+	struct mlx5e_channel *c = sq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mlx5_core_destroy_sq(mdev, sq->sqn);
+}
+
+static int mlx5e_open_sq(struct mlx5e_channel *c,
+			 int tc,
+			 struct mlx5e_sq_param *param,
+			 struct mlx5e_sq *sq)
+{
+	int err;
+
+	err = mlx5e_create_sq(c, tc, param, sq);
+	if (err)
+		return err;
+
+	err = mlx5e_enable_sq(sq, param);
+	if (err)
+		goto err_destroy_sq;
+
+	err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY);
+	if (err)
+		goto err_disable_sq;
+
+	set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
+	netdev_tx_reset_queue(sq->txq);
+	netif_tx_start_queue(sq->txq);
+
+	return 0;
+
+err_disable_sq:
+	mlx5e_disable_sq(sq);
+err_destroy_sq:
+	mlx5e_destroy_sq(sq);
+
+	return err;
+}
+
+static inline void netif_tx_disable_queue(struct netdev_queue *txq)
+{
+	__netif_tx_lock_bh(txq);
+	netif_tx_stop_queue(txq);
+	__netif_tx_unlock_bh(txq);
+}
+
+static void mlx5e_close_sq(struct mlx5e_sq *sq)
+{
+	clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
+	napi_synchronize(&sq->channel->napi); /* prevent netif_tx_wake_queue */
+	netif_tx_disable_queue(sq->txq);
+
+	/* ensure hw is notified of all pending wqes */
+	if (mlx5e_sq_has_room_for(sq, 1))
+		mlx5e_send_nop(sq, true);
+
+	mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+	while (sq->cc != sq->pc) /* wait till sq is empty */
+		msleep(20);
+
+	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
+	napi_synchronize(&sq->channel->napi);
+
+	mlx5e_disable_sq(sq);
+	mlx5e_destroy_sq(sq);
+}
+
+static int mlx5e_create_cq(struct mlx5e_channel *c,
+			   struct mlx5e_cq_param *param,
+			   struct mlx5e_cq *cq)
+{
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_cq *mcq = &cq->mcq;
+	int eqn_not_used;
+	int irqn;
+	int err;
+	u32 i;
+
+	param->wq.numa = cpu_to_node(c->cpu);
+	param->eq_ix   = c->ix;
+
+	err = mlx5_cqwq_create(mdev, &param->wq, param->cqc, &cq->wq,
+			       &cq->wq_ctrl);
+	if (err)
+		return err;
+
+	mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn);
+
+	cq->napi        = &c->napi;
+
+	mcq->cqe_sz     = 64;
+	mcq->set_ci_db  = cq->wq_ctrl.db.db;
+	mcq->arm_db     = cq->wq_ctrl.db.db + 1;
+	*mcq->set_ci_db = 0;
+	*mcq->arm_db    = 0;
+	mcq->vector     = param->eq_ix;
+	mcq->comp       = mlx5e_completion_event;
+	mcq->event      = mlx5e_cq_error_event;
+	mcq->irqn       = irqn;
+	mcq->uar        = &priv->cq_uar;
+
+	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
+		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
+
+		cqe->op_own = 0xf1;
+	}
+
+	cq->channel = c;
+
+	return 0;
+}
+
+static void mlx5e_destroy_cq(struct mlx5e_cq *cq)
+{
+	mlx5_wq_destroy(&cq->wq_ctrl);
+}
+
+static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
+{
+	struct mlx5e_channel *c = cq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_core_cq *mcq = &cq->mcq;
+
+	void *in;
+	void *cqc;
+	int inlen;
+	int irqn_not_used;
+	int eqn;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+		sizeof(u64) * cq->wq_ctrl.buf.npages;
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+
+	memcpy(cqc, param->cqc, sizeof(param->cqc));
+
+	mlx5_fill_page_array(&cq->wq_ctrl.buf,
+			     (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
+
+	mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used);
+
+	MLX5_SET(cqc,   cqc, c_eqn,         eqn);
+	MLX5_SET(cqc,   cqc, uar_page,      mcq->uar->index);
+	MLX5_SET(cqc,   cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
+					    PAGE_SHIFT);
+	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
+
+	err = mlx5_core_create_cq(mdev, mcq, in, inlen);
+
+	kvfree(in);
+
+	if (err)
+		return err;
+
+	mlx5e_cq_arm(cq);
+
+	return 0;
+}
+
+static void mlx5e_disable_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_channel *c = cq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	mlx5_core_destroy_cq(mdev, &cq->mcq);
+}
+
+static int mlx5e_open_cq(struct mlx5e_channel *c,
+			 struct mlx5e_cq_param *param,
+			 struct mlx5e_cq *cq,
+			 u16 moderation_usecs,
+			 u16 moderation_frames)
+{
+	int err;
+	struct mlx5e_priv *priv = c->priv;
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	err = mlx5e_create_cq(c, param, cq);
+	if (err)
+		return err;
+
+	err = mlx5e_enable_cq(cq, param);
+	if (err)
+		goto err_destroy_cq;
+
+	err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq,
+					     moderation_usecs,
+					     moderation_frames);
+	if (err)
+		goto err_destroy_cq;
+
+	return 0;
+
+err_destroy_cq:
+	mlx5e_destroy_cq(cq);
+
+	return err;
+}
+
+static void mlx5e_close_cq(struct mlx5e_cq *cq)
+{
+	mlx5e_disable_cq(cq);
+	mlx5e_destroy_cq(cq);
+}
+
+static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
+{
+	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+}
+
+static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
+			     struct mlx5e_channel_param *cparam)
+{
+	struct mlx5e_priv *priv = c->priv;
+	int err;
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++) {
+		err = mlx5e_open_cq(c, &cparam->tx_cq, &c->sq[tc].cq,
+				    priv->params.tx_cq_moderation_usec,
+				    priv->params.tx_cq_moderation_pkts);
+		if (err)
+			goto err_close_tx_cqs;
+	}
+
+	return 0;
+
+err_close_tx_cqs:
+	for (tc--; tc >= 0; tc--)
+		mlx5e_close_cq(&c->sq[tc].cq);
+
+	return err;
+}
+
+static void mlx5e_close_tx_cqs(struct mlx5e_channel *c)
+{
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_close_cq(&c->sq[tc].cq);
+}
+
+static int mlx5e_open_sqs(struct mlx5e_channel *c,
+			  struct mlx5e_channel_param *cparam)
+{
+	int err;
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++) {
+		err = mlx5e_open_sq(c, tc, &cparam->sq, &c->sq[tc]);
+		if (err)
+			goto err_close_sqs;
+	}
+
+	return 0;
+
+err_close_sqs:
+	for (tc--; tc >= 0; tc--)
+		mlx5e_close_sq(&c->sq[tc]);
+
+	return err;
+}
+
+static void mlx5e_close_sqs(struct mlx5e_channel *c)
+{
+	int tc;
+
+	for (tc = 0; tc < c->num_tc; tc++)
+		mlx5e_close_sq(&c->sq[tc]);
+}
+
+static void mlx5e_build_tc_to_txq_map(struct mlx5e_channel *c,
+				      int num_channels)
+{
+	int i;
+
+	for (i = 0; i < MLX5E_MAX_NUM_TC; i++)
+		c->tc_to_txq_map[i] = c->ix + i * num_channels;
+}
+
+static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
+			      struct mlx5e_channel_param *cparam,
+			      struct mlx5e_channel **cp)
+{
+	struct net_device *netdev = priv->netdev;
+	int cpu = mlx5e_get_cpu(priv, ix);
+	struct mlx5e_channel *c;
+	int err;
+
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	if (!c)
+		return -ENOMEM;
+
+	c->priv     = priv;
+	c->ix       = ix;
+	c->cpu      = cpu;
+	c->pdev     = &priv->mdev->pdev->dev;
+	c->netdev   = priv->netdev;
+	c->mkey_be  = cpu_to_be32(priv->mr.key);
+	c->num_tc   = priv->num_tc;
+
+	mlx5e_build_tc_to_txq_map(c, priv->params.num_channels);
+
+	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
+
+	err = mlx5e_open_tx_cqs(c, cparam);
+	if (err)
+		goto err_napi_del;
+
+	err = mlx5e_open_cq(c, &cparam->rx_cq, &c->rq.cq,
+			    priv->params.rx_cq_moderation_usec,
+			    priv->params.rx_cq_moderation_pkts);
+	if (err)
+		goto err_close_tx_cqs;
+
+	napi_enable(&c->napi);
+
+	err = mlx5e_open_sqs(c, cparam);
+	if (err)
+		goto err_disable_napi;
+
+	err = mlx5e_open_rq(c, &cparam->rq, &c->rq);
+	if (err)
+		goto err_close_sqs;
+
+	netif_set_xps_queue(netdev, get_cpu_mask(c->cpu), ix);
+	*cp = c;
+
+	return 0;
+
+err_close_sqs:
+	mlx5e_close_sqs(c);
+
+err_disable_napi:
+	napi_disable(&c->napi);
+	mlx5e_close_cq(&c->rq.cq);
+
+err_close_tx_cqs:
+	mlx5e_close_tx_cqs(c);
+
+err_napi_del:
+	netif_napi_del(&c->napi);
+	kfree(c);
+
+	return err;
+}
+
+static void mlx5e_close_channel(struct mlx5e_channel *c)
+{
+	mlx5e_close_rq(&c->rq);
+	mlx5e_close_sqs(c);
+	napi_disable(&c->napi);
+	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_tx_cqs(c);
+	netif_napi_del(&c->napi);
+	kfree(c);
+}
+
+static void mlx5e_build_rq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_rq_param *param)
+{
+	void *rqc = param->rqc;
+	void *wq = MLX5_ADDR_OF(rqc, rqc, wq);
+
+	MLX5_SET(wq, wq, wq_type,          MLX5_WQ_TYPE_LINKED_LIST);
+	MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+	MLX5_SET(wq, wq, log_wq_stride,    ilog2(sizeof(struct mlx5e_rx_wqe)));
+	MLX5_SET(wq, wq, log_wq_sz,        priv->params.log_rq_size);
+	MLX5_SET(wq, wq, pd,               priv->pdn);
+
+	param->wq.numa   = dev_to_node(&priv->mdev->pdev->dev);
+	param->wq.linear = 1;
+}
+
+static void mlx5e_build_sq_param(struct mlx5e_priv *priv,
+				 struct mlx5e_sq_param *param)
+{
+	void *sqc = param->sqc;
+	void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+	MLX5_SET(wq, wq, log_wq_sz,     priv->params.log_sq_size);
+	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
+	MLX5_SET(wq, wq, pd,            priv->pdn);
+
+	param->wq.numa = dev_to_node(&priv->mdev->pdev->dev);
+}
+
+static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
+					struct mlx5e_cq_param *param)
+{
+	void *cqc = param->cqc;
+
+	MLX5_SET(cqc, cqc, uar_page, priv->cq_uar.index);
+}
+
+static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_cq_param *param)
+{
+	void *cqc = param->cqc;
+
+	MLX5_SET(cqc, cqc, log_cq_size,  priv->params.log_rq_size);
+
+	mlx5e_build_common_cq_param(priv, param);
+}
+
+static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv,
+				    struct mlx5e_cq_param *param)
+{
+	void *cqc = param->cqc;
+
+	MLX5_SET(cqc, cqc, log_cq_size,  priv->params.log_sq_size);
+
+	mlx5e_build_common_cq_param(priv, param);
+}
+
+static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
+				      struct mlx5e_channel_param *cparam)
+{
+	memset(cparam, 0, sizeof(*cparam));
+
+	mlx5e_build_rq_param(priv, &cparam->rq);
+	mlx5e_build_sq_param(priv, &cparam->sq);
+	mlx5e_build_rx_cq_param(priv, &cparam->rx_cq);
+	mlx5e_build_tx_cq_param(priv, &cparam->tx_cq);
+}
+
+static int mlx5e_open_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channel_param cparam;
+	int err = -ENOMEM;
+	int i;
+	int j;
+
+	priv->channel = kcalloc(priv->params.num_channels,
+				sizeof(struct mlx5e_channel *), GFP_KERNEL);
+
+	priv->txq_to_sq_map = kcalloc(priv->params.num_channels * priv->num_tc,
+				      sizeof(struct mlx5e_sq *), GFP_KERNEL);
+
+	if (!priv->channel || !priv->txq_to_sq_map)
+		goto err_free_txq_to_sq_map;
+
+	mlx5e_build_channel_param(priv, &cparam);
+	for (i = 0; i < priv->params.num_channels; i++) {
+		err = mlx5e_open_channel(priv, i, &cparam, &priv->channel[i]);
+		if (err)
+			goto err_close_channels;
+	}
+
+	for (j = 0; j < priv->params.num_channels; j++) {
+		err = mlx5e_wait_for_min_rx_wqes(&priv->channel[j]->rq);
+		if (err)
+			goto err_close_channels;
+	}
+
+	return 0;
+
+err_close_channels:
+	for (i--; i >= 0; i--)
+		mlx5e_close_channel(priv->channel[i]);
+
+err_free_txq_to_sq_map:
+	kfree(priv->txq_to_sq_map);
+	kfree(priv->channel);
+
+	return err;
+}
+
+static void mlx5e_close_channels(struct mlx5e_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->params.num_channels; i++)
+		mlx5e_close_channel(priv->channel[i]);
+
+	kfree(priv->txq_to_sq_map);
+	kfree(priv->channel);
+}
+
+static int mlx5e_open_tis(struct mlx5e_priv *priv, int tc)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 in[MLX5_ST_SZ_DW(create_tis_in)];
+	void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(tisc, tisc, prio,  tc);
+	MLX5_SET(tisc, tisc, transport_domain, priv->tdn);
+
+	return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]);
+}
+
+static void mlx5e_close_tis(struct mlx5e_priv *priv, int tc)
+{
+	mlx5_core_destroy_tis(priv->mdev, priv->tisn[tc]);
+}
+
+static int mlx5e_open_tises(struct mlx5e_priv *priv)
+{
+	int num_tc = priv->num_tc;
+	int err;
+	int tc;
+
+	for (tc = 0; tc < num_tc; tc++) {
+		err = mlx5e_open_tis(priv, tc);
+		if (err)
+			goto err_close_tises;
+	}
+
+	return 0;
+
+err_close_tises:
+	for (tc--; tc >= 0; tc--)
+		mlx5e_close_tis(priv, tc);
+
+	return err;
+}
+
+static void mlx5e_close_tises(struct mlx5e_priv *priv)
+{
+	int num_tc = priv->num_tc;
+	int tc;
+
+	for (tc = 0; tc < num_tc; tc++)
+		mlx5e_close_tis(priv, tc);
+}
+
+static int mlx5e_open_rqt(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 *in;
+	u32 out[MLX5_ST_SZ_DW(create_rqt_out)];
+	void *rqtc;
+	int inlen;
+	int err;
+	int sz;
+	int i;
+
+	sz = 1 << priv->params.rx_hash_log_tbl_sz;
+
+	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * sz;
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
+
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, sz);
+	MLX5_SET(rqtc, rqtc, rqt_max_size, sz);
+
+	for (i = 0; i < sz; i++) {
+		int ix = i % priv->params.num_channels;
+
+		MLX5_SET(rqtc, rqtc, rq_num[i], priv->channel[ix]->rq.rqn);
+	}
+
+	MLX5_SET(create_rqt_in, in, opcode, MLX5_CMD_OP_CREATE_RQT);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(mdev, in, inlen, out, sizeof(out));
+	if (!err)
+		priv->rqtn = MLX5_GET(create_rqt_out, out, rqtn);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5e_close_rqt(struct mlx5e_priv *priv)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_rqt_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_rqt_in, in, opcode, MLX5_CMD_OP_DESTROY_RQT);
+	MLX5_SET(destroy_rqt_in, in, rqtn, priv->rqtn);
+
+	mlx5_cmd_exec_check_status(priv->mdev, in, sizeof(in), out,
+				   sizeof(out));
+}
+
+static void mlx5e_build_tir_ctx(struct mlx5e_priv *priv, u32 *tirc, int tt)
+{
+	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
+	MLX5_SET(tirc, tirc, transport_domain, priv->tdn);
+
+#define ROUGH_MAX_L2_L3_HDR_SZ 256
+
+#define MLX5_HASH_IP     (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+			  MLX5_HASH_FIELD_SEL_DST_IP)
+
+#define MLX5_HASH_ALL    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+			  MLX5_HASH_FIELD_SEL_DST_IP   |\
+			  MLX5_HASH_FIELD_SEL_L4_SPORT |\
+			  MLX5_HASH_FIELD_SEL_L4_DPORT)
+
+	if (priv->params.lro_en) {
+		MLX5_SET(tirc, tirc, lro_enable_mask,
+			 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
+			 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
+		MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
+			 (priv->params.lro_wqe_sz -
+			  ROUGH_MAX_L2_L3_HDR_SZ) >> 8);
+		MLX5_SET(tirc, tirc, lro_timeout_period_usecs,
+			 MLX5_CAP_ETH(priv->mdev,
+				      lro_timer_supported_periods[3]));
+	}
+
+	switch (tt) {
+	case MLX5E_TT_ANY:
+		MLX5_SET(tirc, tirc, disp_type,
+			 MLX5_TIRC_DISP_TYPE_DIRECT);
+		MLX5_SET(tirc, tirc, inline_rqn,
+			 priv->channel[0]->rq.rqn);
+		break;
+	default:
+		MLX5_SET(tirc, tirc, disp_type,
+			 MLX5_TIRC_DISP_TYPE_INDIRECT);
+		MLX5_SET(tirc, tirc, indirect_table,
+			 priv->rqtn);
+		MLX5_SET(tirc, tirc, rx_hash_fn,
+			 MLX5_TIRC_RX_HASH_FN_HASH_TOEPLITZ);
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		netdev_rss_key_fill(MLX5_ADDR_OF(tirc, tirc,
+						 rx_hash_toeplitz_key),
+				    MLX5_FLD_SZ_BYTES(tirc,
+						      rx_hash_toeplitz_key));
+		break;
+	}
+
+	switch (tt) {
+	case MLX5E_TT_IPV4_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_ALL);
+		break;
+
+	case MLX5E_TT_IPV6_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_ALL);
+		break;
+
+	case MLX5E_TT_IPV4_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_ALL);
+		break;
+
+	case MLX5E_TT_IPV6_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_ALL);
+		break;
+
+	case MLX5E_TT_IPV4:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+
+	case MLX5E_TT_IPV6:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+	}
+}
+
+static int mlx5e_open_tir(struct mlx5e_priv *priv, int tt)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u32 *in;
+	void *tirc;
+	int inlen;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(create_tir_in);
+	in = mlx5_vzalloc(inlen);
+	if (!in)
+		return -ENOMEM;
+
+	tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+
+	mlx5e_build_tir_ctx(priv, tirc, tt);
+
+	err = mlx5_core_create_tir(mdev, in, inlen, &priv->tirn[tt]);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5e_close_tir(struct mlx5e_priv *priv, int tt)
+{
+	mlx5_core_destroy_tir(priv->mdev, priv->tirn[tt]);
+}
+
+static int mlx5e_open_tirs(struct mlx5e_priv *priv)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < MLX5E_NUM_TT; i++) {
+		err = mlx5e_open_tir(priv, i);
+		if (err)
+			goto err_close_tirs;
+	}
+
+	return 0;
+
+err_close_tirs:
+	for (i--; i >= 0; i--)
+		mlx5e_close_tir(priv, i);
+
+	return err;
+}
+
+static void mlx5e_close_tirs(struct mlx5e_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < MLX5E_NUM_TT; i++)
+		mlx5e_close_tir(priv, i);
+}
+
+static int mlx5e_set_dev_port_mtu(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int hw_mtu;
+	int err;
+
+	err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1);
+	if (err)
+		return err;
+
+	mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1);
+
+	if (MLX5E_HW2SW_MTU(hw_mtu) != netdev->mtu)
+		netdev_warn(netdev, "%s: Port MTU %d is different than netdev mtu %d\n",
+			    __func__, MLX5E_HW2SW_MTU(hw_mtu), netdev->mtu);
+
+	netdev->mtu = MLX5E_HW2SW_MTU(hw_mtu);
+	return 0;
+}
+
+int mlx5e_open_locked(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int num_txqs;
+	int err;
+
+	num_txqs = priv->params.num_channels * priv->params.num_tc;
+	netif_set_real_num_tx_queues(netdev, num_txqs);
+	netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
+
+	err = mlx5e_set_dev_port_mtu(netdev);
+	if (err)
+		return err;
+
+	err = mlx5e_open_tises(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_open_tises failed, %d\n",
+			   __func__, err);
+		return err;
+	}
+
+	err = mlx5e_open_channels(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
+			   __func__, err);
+		goto err_close_tises;
+	}
+
+	err = mlx5e_open_rqt(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_open_rqt failed, %d\n",
+			   __func__, err);
+		goto err_close_channels;
+	}
+
+	err = mlx5e_open_tirs(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_open_tir failed, %d\n",
+			   __func__, err);
+		goto err_close_rqls;
+	}
+
+	err = mlx5e_open_flow_table(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_open_flow_table failed, %d\n",
+			   __func__, err);
+		goto err_close_tirs;
+	}
+
+	err = mlx5e_add_all_vlan_rules(priv);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_add_all_vlan_rules failed, %d\n",
+			   __func__, err);
+		goto err_close_flow_table;
+	}
+
+	mlx5e_init_eth_addr(priv);
+
+	set_bit(MLX5E_STATE_OPENED, &priv->state);
+
+	mlx5e_update_carrier(priv);
+	mlx5e_set_rx_mode_core(priv);
+
+	schedule_delayed_work(&priv->update_stats_work, 0);
+	return 0;
+
+err_close_flow_table:
+	mlx5e_close_flow_table(priv);
+
+err_close_tirs:
+	mlx5e_close_tirs(priv);
+
+err_close_rqls:
+	mlx5e_close_rqt(priv);
+
+err_close_channels:
+	mlx5e_close_channels(priv);
+
+err_close_tises:
+	mlx5e_close_tises(priv);
+
+	return err;
+}
+
+static int mlx5e_open(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_open_locked(netdev);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+int mlx5e_close_locked(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	clear_bit(MLX5E_STATE_OPENED, &priv->state);
+
+	mlx5e_set_rx_mode_core(priv);
+	mlx5e_del_all_vlan_rules(priv);
+	netif_carrier_off(priv->netdev);
+	mlx5e_close_flow_table(priv);
+	mlx5e_close_tirs(priv);
+	mlx5e_close_rqt(priv);
+	mlx5e_close_channels(priv);
+	mlx5e_close_tises(priv);
+
+	return 0;
+}
+
+static int mlx5e_close(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err;
+
+	mutex_lock(&priv->state_lock);
+	err = mlx5e_close_locked(netdev);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+int mlx5e_update_priv_params(struct mlx5e_priv *priv,
+			     struct mlx5e_params *new_params)
+{
+	int err = 0;
+	int was_opened;
+
+	WARN_ON(!mutex_is_locked(&priv->state_lock));
+
+	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
+	if (was_opened)
+		mlx5e_close_locked(priv->netdev);
+
+	priv->params = *new_params;
+
+	if (was_opened)
+		err = mlx5e_open_locked(priv->netdev);
+
+	return err;
+}
+
+static struct rtnl_link_stats64 *
+mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
+
+	stats->rx_packets = vstats->rx_packets;
+	stats->rx_bytes   = vstats->rx_bytes;
+	stats->tx_packets = vstats->tx_packets;
+	stats->tx_bytes   = vstats->tx_bytes;
+	stats->multicast  = vstats->rx_multicast_packets +
+			    vstats->tx_multicast_packets;
+	stats->tx_errors  = vstats->tx_error_packets;
+	stats->rx_errors  = vstats->rx_error_packets;
+	stats->tx_dropped = vstats->tx_queue_dropped;
+	stats->rx_crc_errors = 0;
+	stats->rx_length_errors = 0;
+
+	return stats;
+}
+
+static void mlx5e_set_rx_mode(struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	schedule_work(&priv->set_rx_mode_work);
+}
+
+static int mlx5e_set_mac(struct net_device *netdev, void *addr)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	netif_addr_lock_bh(netdev);
+	ether_addr_copy(netdev->dev_addr, saddr->sa_data);
+	netif_addr_unlock_bh(netdev);
+
+	schedule_work(&priv->set_rx_mode_work);
+
+	return 0;
+}
+
+static int mlx5e_set_features(struct net_device *netdev,
+			      netdev_features_t features)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	netdev_features_t changes = features ^ netdev->features;
+	struct mlx5e_params new_params;
+	bool update_params = false;
+
+	mutex_lock(&priv->state_lock);
+	new_params = priv->params;
+
+	if (changes & NETIF_F_LRO) {
+		new_params.lro_en = !!(features & NETIF_F_LRO);
+		update_params = true;
+	}
+
+	if (update_params)
+		mlx5e_update_priv_params(priv, &new_params);
+
+	if (changes & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+			mlx5e_enable_vlan_filter(priv);
+		else
+			mlx5e_disable_vlan_filter(priv);
+	}
+
+	mutex_unlock(&priv->state_lock);
+
+	return 0;
+}
+
+static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int max_mtu;
+	int err;
+
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+
+	if (new_mtu > max_mtu) {
+		netdev_err(netdev,
+			   "%s: Bad MTU (%d) > (%d) Max\n",
+			   __func__, new_mtu, max_mtu);
+		return -EINVAL;
+	}
+
+	mutex_lock(&priv->state_lock);
+	netdev->mtu = new_mtu;
+	err = mlx5e_update_priv_params(priv, &priv->params);
+	mutex_unlock(&priv->state_lock);
+
+	return err;
+}
+
+static struct net_device_ops mlx5e_netdev_ops = {
+	.ndo_open                = mlx5e_open,
+	.ndo_stop                = mlx5e_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_stats64         = mlx5e_get_stats,
+	.ndo_set_rx_mode         = mlx5e_set_rx_mode,
+	.ndo_set_mac_address     = mlx5e_set_mac,
+	.ndo_vlan_rx_add_vid	 = mlx5e_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	 = mlx5e_vlan_rx_kill_vid,
+	.ndo_set_features        = mlx5e_set_features,
+	.ndo_change_mtu		 = mlx5e_change_mtu,
+};
+
+static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
+{
+	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
+		return -ENOTSUPP;
+	if (!MLX5_CAP_GEN(mdev, eth_net_offloads) ||
+	    !MLX5_CAP_GEN(mdev, nic_flow_table) ||
+	    !MLX5_CAP_ETH(mdev, csum_cap) ||
+	    !MLX5_CAP_ETH(mdev, max_lso_cap) ||
+	    !MLX5_CAP_ETH(mdev, vlan_cap) ||
+	    !MLX5_CAP_ETH(mdev, rss_ind_tbl_cap) ||
+	    MLX5_CAP_FLOWTABLE(mdev,
+			       flow_table_properties_nic_receive.max_ft_level)
+			       < 3) {
+		mlx5_core_warn(mdev,
+			       "Not creating net device, some required device capabilities are missing\n");
+		return -ENOTSUPP;
+	}
+	return 0;
+}
+
+static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev,
+				    struct net_device *netdev,
+				    int num_comp_vectors)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	priv->params.log_sq_size           =
+		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	priv->params.log_rq_size           =
+		MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE;
+	priv->params.rx_cq_moderation_usec =
+		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC;
+	priv->params.rx_cq_moderation_pkts =
+		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS;
+	priv->params.tx_cq_moderation_usec =
+		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC;
+	priv->params.tx_cq_moderation_pkts =
+		MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS;
+	priv->params.min_rx_wqes           =
+		MLX5E_PARAMS_DEFAULT_MIN_RX_WQES;
+	priv->params.rx_hash_log_tbl_sz    =
+		(order_base_2(num_comp_vectors) >
+		 MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ) ?
+		order_base_2(num_comp_vectors)           :
+		MLX5E_PARAMS_DEFAULT_RX_HASH_LOG_TBL_SZ;
+	priv->params.num_tc                = 1;
+	priv->params.default_vlan_prio     = 0;
+
+	priv->params.lro_en = false && !!MLX5_CAP_ETH(priv->mdev, lro_cap);
+	priv->params.lro_wqe_sz            =
+		MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+
+	priv->mdev                         = mdev;
+	priv->netdev                       = netdev;
+	priv->params.num_channels          = num_comp_vectors;
+	priv->num_tc                       = priv->params.num_tc;
+	priv->default_vlan_prio            = priv->params.default_vlan_prio;
+
+	spin_lock_init(&priv->async_events_spinlock);
+	mutex_init(&priv->state_lock);
+
+	INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work);
+	INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
+	INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
+}
+
+static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5_query_nic_vport_mac_address(priv->mdev, netdev->dev_addr);
+}
+
+static void mlx5e_build_netdev(struct net_device *netdev)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	SET_NETDEV_DEV(netdev, &mdev->pdev->dev);
+
+	if (priv->num_tc > 1) {
+		mlx5e_netdev_ops.ndo_select_queue = mlx5e_select_queue;
+	}
+
+	netdev->netdev_ops        = &mlx5e_netdev_ops;
+	netdev->watchdog_timeo    = 15 * HZ;
+
+	netdev->ethtool_ops	  = &mlx5e_ethtool_ops;
+
+	netdev->vlan_features    |= NETIF_F_SG;
+	netdev->vlan_features    |= NETIF_F_IP_CSUM;
+	netdev->vlan_features    |= NETIF_F_IPV6_CSUM;
+	netdev->vlan_features    |= NETIF_F_GRO;
+	netdev->vlan_features    |= NETIF_F_TSO;
+	netdev->vlan_features    |= NETIF_F_TSO6;
+	netdev->vlan_features    |= NETIF_F_RXCSUM;
+	netdev->vlan_features    |= NETIF_F_RXHASH;
+
+	if (!!MLX5_CAP_ETH(mdev, lro_cap))
+		netdev->vlan_features    |= NETIF_F_LRO;
+
+	netdev->hw_features       = netdev->vlan_features;
+	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_RX;
+	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->features          = netdev->hw_features;
+	if (!priv->params.lro_en)
+		netdev->features  &= ~NETIF_F_LRO;
+
+	netdev->features         |= NETIF_F_HIGHDMA;
+
+	netdev->priv_flags       |= IFF_UNICAST_FLT;
+
+	mlx5e_set_netdev_dev_addr(netdev);
+}
+
+static int mlx5e_create_mkey(struct mlx5e_priv *priv, u32 pdn,
+			     struct mlx5_core_mr *mr)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5_create_mkey_mbox_in *in;
+	int err;
+
+	in = mlx5_vzalloc(sizeof(*in));
+	if (!in)
+		return -ENOMEM;
+
+	in->seg.flags = MLX5_PERM_LOCAL_WRITE |
+			MLX5_PERM_LOCAL_READ  |
+			MLX5_ACCESS_MODE_PA;
+	in->seg.flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
+	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+
+	err = mlx5_core_create_mkey(mdev, mr, in, sizeof(*in), NULL, NULL,
+				    NULL);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev)
+{
+	struct net_device *netdev;
+	struct mlx5e_priv *priv;
+	int ncv = mdev->priv.eq_table.num_comp_vectors;
+	int err;
+
+	if (mlx5e_check_required_hca_cap(mdev))
+		return NULL;
+
+	netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), ncv, ncv);
+	if (!netdev) {
+		mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
+		return NULL;
+	}
+
+	mlx5e_build_netdev_priv(mdev, netdev, ncv);
+	mlx5e_build_netdev(netdev);
+
+	netif_carrier_off(netdev);
+
+	priv = netdev_priv(netdev);
+
+	err = mlx5_alloc_map_uar(mdev, &priv->cq_uar);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5_alloc_map_uar failed, %d\n",
+			   __func__, err);
+		goto err_free_netdev;
+	}
+
+	err = mlx5_core_alloc_pd(mdev, &priv->pdn);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5_core_alloc_pd failed, %d\n",
+			   __func__, err);
+		goto err_unmap_free_uar;
+	}
+
+	err = mlx5_alloc_transport_domain(mdev, &priv->tdn);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5_alloc_transport_domain failed, %d\n",
+			   __func__, err);
+		goto err_dealloc_pd;
+	}
+
+	err = mlx5e_create_mkey(priv, priv->pdn, &priv->mr);
+	if (err) {
+		netdev_err(netdev, "%s: mlx5e_create_mkey failed, %d\n",
+			   __func__, err);
+		goto err_dealloc_transport_domain;
+	}
+
+	err = register_netdev(netdev);
+	if (err) {
+		netdev_err(netdev, "%s: register_netdev failed, %d\n",
+			   __func__, err);
+		goto err_destroy_mkey;
+	}
+
+	mlx5e_enable_async_events(priv);
+
+	return priv;
+
+err_destroy_mkey:
+	mlx5_core_destroy_mkey(mdev, &priv->mr);
+
+err_dealloc_transport_domain:
+	mlx5_dealloc_transport_domain(mdev, priv->tdn);
+
+err_dealloc_pd:
+	mlx5_core_dealloc_pd(mdev, priv->pdn);
+
+err_unmap_free_uar:
+	mlx5_unmap_free_uar(mdev, &priv->cq_uar);
+
+err_free_netdev:
+	free_netdev(netdev);
+
+	return NULL;
+}
+
+static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv)
+{
+	struct mlx5e_priv *priv = vpriv;
+	struct net_device *netdev = priv->netdev;
+
+	unregister_netdev(netdev);
+	mlx5_core_destroy_mkey(priv->mdev, &priv->mr);
+	mlx5_dealloc_transport_domain(priv->mdev, priv->tdn);
+	mlx5_core_dealloc_pd(priv->mdev, priv->pdn);
+	mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar);
+	mlx5e_disable_async_events(priv);
+	flush_scheduled_work();
+	free_netdev(netdev);
+}
+
+static void *mlx5e_get_netdev(void *vpriv)
+{
+	struct mlx5e_priv *priv = vpriv;
+
+	return priv->netdev;
+}
+
+static struct mlx5_interface mlx5e_interface = {
+	.add       = mlx5e_create_netdev,
+	.remove    = mlx5e_destroy_netdev,
+	.event     = mlx5e_async_event,
+	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
+	.get_dev   = mlx5e_get_netdev,
+};
+
+void mlx5e_init(void)
+{
+	mlx5_register_interface(&mlx5e_interface);
+}
+
+void mlx5e_cleanup(void)
+{
+	mlx5_unregister_interface(&mlx5e_interface);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
new file mode 100644
index 000000000000..9a9374131f5b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include "en.h"
+
+static inline int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq,
+				     struct mlx5e_rx_wqe *wqe, u16 ix)
+{
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+
+	skb = netdev_alloc_skb(rq->netdev, rq->wqe_sz);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	dma_addr = dma_map_single(rq->pdev,
+				  /* hw start padding */
+				  skb->data,
+				  /* hw end padding */
+				  rq->wqe_sz,
+				  DMA_FROM_DEVICE);
+
+	if (unlikely(dma_mapping_error(rq->pdev, dma_addr)))
+		goto err_free_skb;
+
+	skb_reserve(skb, MLX5E_NET_IP_ALIGN);
+
+	*((dma_addr_t *)skb->cb) = dma_addr;
+	wqe->data.addr = cpu_to_be64(dma_addr + MLX5E_NET_IP_ALIGN);
+
+	rq->skb[ix] = skb;
+
+	return 0;
+
+err_free_skb:
+	dev_kfree_skb(skb);
+
+	return -ENOMEM;
+}
+
+bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
+{
+	struct mlx5_wq_ll *wq = &rq->wq;
+
+	if (unlikely(!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state)))
+		return false;
+
+	while (!mlx5_wq_ll_is_full(wq)) {
+		struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
+
+		if (unlikely(mlx5e_alloc_rx_wqe(rq, wqe, wq->head)))
+			break;
+
+		mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
+	}
+
+	/* ensure wqes are visible to device before updating doorbell record */
+	dma_wmb();
+
+	mlx5_wq_ll_update_db_record(wq);
+
+	return !mlx5_wq_ll_is_full(wq);
+}
+
+static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe)
+{
+	struct ethhdr	*eth	= (struct ethhdr *)(skb->data);
+	struct iphdr	*ipv4	= (struct iphdr *)(skb->data + ETH_HLEN);
+	struct ipv6hdr	*ipv6	= (struct ipv6hdr *)(skb->data + ETH_HLEN);
+	struct tcphdr	*tcp;
+
+	u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
+	int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA  == l4_hdr_type) ||
+		       (CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type));
+
+	u16 tot_len = be32_to_cpu(cqe->byte_cnt) - ETH_HLEN;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+					sizeof(struct iphdr));
+		ipv6 = NULL;
+	} else {
+		tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+					sizeof(struct ipv6hdr));
+		ipv4 = NULL;
+	}
+
+	if (get_cqe_lro_tcppsh(cqe))
+		tcp->psh                = 1;
+
+	if (tcp_ack) {
+		tcp->ack                = 1;
+		tcp->ack_seq            = cqe->lro_ack_seq_num;
+		tcp->window             = cqe->lro_tcp_win;
+	}
+
+	if (ipv4) {
+		ipv4->ttl               = cqe->lro_min_ttl;
+		ipv4->tot_len           = cpu_to_be16(tot_len);
+		ipv4->check             = 0;
+		ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
+						       ipv4->ihl);
+	} else {
+		ipv6->hop_limit         = cqe->lro_min_ttl;
+		ipv6->payload_len       = cpu_to_be16(tot_len -
+						      sizeof(struct ipv6hdr));
+	}
+}
+
+static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
+				      struct sk_buff *skb)
+{
+	u8 cht = cqe->rss_hash_type;
+	int ht = (cht & CQE_RSS_HTYPE_L4) ? PKT_HASH_TYPE_L4 :
+		 (cht & CQE_RSS_HTYPE_IP) ? PKT_HASH_TYPE_L3 :
+					    PKT_HASH_TYPE_NONE;
+	skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht);
+}
+
+static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
+				      struct mlx5e_rq *rq,
+				      struct sk_buff *skb)
+{
+	struct net_device *netdev = rq->netdev;
+	u32 cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
+	int lro_num_seg;
+
+	skb_put(skb, cqe_bcnt);
+
+	lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
+	if (lro_num_seg > 1) {
+		mlx5e_lro_update_hdr(skb, cqe);
+		skb_shinfo(skb)->gso_size = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ;
+		rq->stats.lro_packets++;
+		rq->stats.lro_bytes += cqe_bcnt;
+	}
+
+	if (likely(netdev->features & NETIF_F_RXCSUM) &&
+	    (cqe->hds_ip_ext & CQE_L2_OK) &&
+	    (cqe->hds_ip_ext & CQE_L3_OK) &&
+	    (cqe->hds_ip_ext & CQE_L4_OK)) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	} else {
+		skb->ip_summed = CHECKSUM_NONE;
+		rq->stats.csum_none++;
+	}
+
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	skb_record_rx_queue(skb, rq->ix);
+
+	if (likely(netdev->features & NETIF_F_RXHASH))
+		mlx5e_skb_set_hash(cqe, skb);
+
+	if (cqe_has_vlan(cqe))
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       be16_to_cpu(cqe->vlan_info));
+}
+
+bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
+{
+	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
+	int i;
+
+	/* avoid accessing cq (dma coherent memory) if not needed */
+	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
+		return false;
+
+	for (i = 0; i < budget; i++) {
+		struct mlx5e_rx_wqe *wqe;
+		struct mlx5_cqe64 *cqe;
+		struct sk_buff *skb;
+		__be16 wqe_counter_be;
+		u16 wqe_counter;
+
+		cqe = mlx5e_get_cqe(cq);
+		if (!cqe)
+			break;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter_be = cqe->wqe_counter;
+		wqe_counter    = be16_to_cpu(wqe_counter_be);
+		wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+		skb            = rq->skb[wqe_counter];
+		prefetch(skb->data);
+		rq->skb[wqe_counter] = NULL;
+
+		dma_unmap_single(rq->pdev,
+				 *((dma_addr_t *)skb->cb),
+				 rq->wqe_sz,
+				 DMA_FROM_DEVICE);
+
+		if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+			rq->stats.wqe_err++;
+			dev_kfree_skb(skb);
+			goto wq_ll_pop;
+		}
+
+		mlx5e_build_rx_skb(cqe, rq, skb);
+		rq->stats.packets++;
+		napi_gro_receive(cq->napi, skb);
+
+wq_ll_pop:
+		mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+			       &wqe->next.next_wqe_index);
+	}
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	if (i == budget) {
+		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
+		return true;
+	}
+
+	return false;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
new file mode 100644
index 000000000000..03f28f438e55
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -0,0 +1,350 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/tcp.h>
+#include <linux/if_vlan.h>
+#include "en.h"
+
+#define MLX5E_SQ_NOPS_ROOM  MLX5_SEND_WQE_MAX_WQEBBS
+#define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\
+			    MLX5E_SQ_NOPS_ROOM)
+
+void mlx5e_send_nop(struct mlx5e_sq *sq, bool notify_hw)
+{
+	struct mlx5_wq_cyc                *wq  = &sq->wq;
+
+	u16 pi = sq->pc & wq->sz_m1;
+	struct mlx5e_tx_wqe              *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	struct mlx5_wqe_ctrl_seg         *cseg = &wqe->ctrl;
+
+	memset(cseg, 0, sizeof(*cseg));
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_NOP);
+	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | 0x01);
+
+	sq->skb[pi] = NULL;
+	sq->pc++;
+
+	if (notify_hw) {
+		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
+		mlx5e_tx_notify_hw(sq, wqe);
+	}
+}
+
+static void mlx5e_dma_pop_last_pushed(struct mlx5e_sq *sq, dma_addr_t *addr,
+				      u32 *size)
+{
+	sq->dma_fifo_pc--;
+	*addr = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr;
+	*size = sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size;
+}
+
+static void mlx5e_dma_unmap_wqe_err(struct mlx5e_sq *sq, struct sk_buff *skb)
+{
+	dma_addr_t addr;
+	u32 size;
+	int i;
+
+	for (i = 0; i < MLX5E_TX_SKB_CB(skb)->num_dma; i++) {
+		mlx5e_dma_pop_last_pushed(sq, &addr, &size);
+		dma_unmap_single(sq->pdev, addr, size, DMA_TO_DEVICE);
+	}
+}
+
+static inline void mlx5e_dma_push(struct mlx5e_sq *sq, dma_addr_t addr,
+				  u32 size)
+{
+	sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].addr = addr;
+	sq->dma_fifo[sq->dma_fifo_pc & sq->dma_fifo_mask].size = size;
+	sq->dma_fifo_pc++;
+}
+
+static inline void mlx5e_dma_get(struct mlx5e_sq *sq, u32 i, dma_addr_t *addr,
+				 u32 *size)
+{
+	*addr = sq->dma_fifo[i & sq->dma_fifo_mask].addr;
+	*size = sq->dma_fifo[i & sq->dma_fifo_mask].size;
+}
+
+u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv, select_queue_fallback_t fallback)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int channel_ix = fallback(dev, skb);
+	int up = skb_vlan_tag_present(skb)        ?
+		 skb->vlan_tci >> VLAN_PRIO_SHIFT :
+		 priv->default_vlan_prio;
+	int tc = netdev_get_prio_tc_map(dev, up);
+
+	return priv->channel[channel_ix]->tc_to_txq_map[tc];
+}
+
+static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq,
+					    struct sk_buff *skb)
+{
+#define MLX5E_MIN_INLINE 16 /* eth header with vlan (w/o next ethertype) */
+	return MLX5E_MIN_INLINE;
+}
+
+static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb)
+{
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
+
+	u16 pi = sq->pc & wq->sz_m1;
+	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+	struct mlx5_wqe_data_seg *dseg;
+
+	u8  opcode = MLX5_OPCODE_SEND;
+	dma_addr_t dma_addr = 0;
+	u16 headlen;
+	u16 ds_cnt;
+	u16 ihs;
+	int i;
+
+	memset(wqe, 0, sizeof(*wqe));
+
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL))
+		eseg->cs_flags	= MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
+	else
+		sq->stats.csum_offload_none++;
+
+	if (skb_is_gso(skb)) {
+		u32 payload_len;
+
+		eseg->mss    = cpu_to_be16(skb_shinfo(skb)->gso_size);
+		opcode       = MLX5_OPCODE_LSO;
+		ihs          = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		payload_len  = skb->len - ihs;
+		MLX5E_TX_SKB_CB(skb)->num_bytes = skb->len +
+					(skb_shinfo(skb)->gso_segs - 1) * ihs;
+		sq->stats.tso_packets++;
+		sq->stats.tso_bytes += payload_len;
+	} else {
+		ihs = mlx5e_get_inline_hdr_size(sq, skb);
+		MLX5E_TX_SKB_CB(skb)->num_bytes = max_t(unsigned int, skb->len,
+							ETH_ZLEN);
+	}
+
+	skb_copy_from_linear_data(skb, eseg->inline_hdr_start, ihs);
+	skb_pull_inline(skb, ihs);
+
+	eseg->inline_hdr_sz = cpu_to_be16(ihs);
+
+	ds_cnt  = sizeof(*wqe) / MLX5_SEND_WQE_DS;
+	ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr_start),
+			       MLX5_SEND_WQE_DS);
+	dseg    = (struct mlx5_wqe_data_seg *)cseg + ds_cnt;
+
+	MLX5E_TX_SKB_CB(skb)->num_dma = 0;
+
+	headlen = skb_headlen(skb);
+	if (headlen) {
+		dma_addr = dma_map_single(sq->pdev, skb->data, headlen,
+					  DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
+			goto dma_unmap_wqe_err;
+
+		dseg->addr       = cpu_to_be64(dma_addr);
+		dseg->lkey       = sq->mkey_be;
+		dseg->byte_count = cpu_to_be32(headlen);
+
+		mlx5e_dma_push(sq, dma_addr, headlen);
+		MLX5E_TX_SKB_CB(skb)->num_dma++;
+
+		dseg++;
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
+		int fsz = skb_frag_size(frag);
+
+		dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
+					    DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(sq->pdev, dma_addr)))
+			goto dma_unmap_wqe_err;
+
+		dseg->addr       = cpu_to_be64(dma_addr);
+		dseg->lkey       = sq->mkey_be;
+		dseg->byte_count = cpu_to_be32(fsz);
+
+		mlx5e_dma_push(sq, dma_addr, fsz);
+		MLX5E_TX_SKB_CB(skb)->num_dma++;
+
+		dseg++;
+	}
+
+	ds_cnt += MLX5E_TX_SKB_CB(skb)->num_dma;
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode);
+	cseg->qpn_ds           = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+
+	sq->skb[pi] = skb;
+
+	MLX5E_TX_SKB_CB(skb)->num_wqebbs = DIV_ROUND_UP(ds_cnt,
+							MLX5_SEND_WQEBB_NUM_DS);
+	sq->pc += MLX5E_TX_SKB_CB(skb)->num_wqebbs;
+
+	netdev_tx_sent_queue(sq->txq, MLX5E_TX_SKB_CB(skb)->num_bytes);
+
+	if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM))) {
+		netif_tx_stop_queue(sq->txq);
+		sq->stats.stopped++;
+	}
+
+	if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
+		cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
+		mlx5e_tx_notify_hw(sq, wqe);
+	}
+
+	/* fill sq edge with nops to avoid wqe wrap around */
+	while ((sq->pc & wq->sz_m1) > sq->edge)
+		mlx5e_send_nop(sq, false);
+
+	sq->stats.packets++;
+	return NETDEV_TX_OK;
+
+dma_unmap_wqe_err:
+	sq->stats.dropped++;
+	mlx5e_dma_unmap_wqe_err(sq, skb);
+
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_sq *sq = priv->txq_to_sq_map[skb_get_queue_mapping(skb)];
+
+	return mlx5e_sq_xmit(sq, skb);
+}
+
+bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_sq *sq;
+	u32 dma_fifo_cc;
+	u32 nbytes;
+	u16 npkts;
+	u16 sqcc;
+	int i;
+
+	/* avoid accessing cq (dma coherent memory) if not needed */
+	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
+		return false;
+
+	sq = container_of(cq, struct mlx5e_sq, cq);
+
+	npkts = 0;
+	nbytes = 0;
+
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	/* avoid dirtying sq cache line every cqe */
+	dma_fifo_cc = sq->dma_fifo_cc;
+
+	for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) {
+		struct mlx5_cqe64 *cqe;
+		u16 wqe_counter;
+		bool last_wqe;
+
+		cqe = mlx5e_get_cqe(cq);
+		if (!cqe)
+			break;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		do {
+			struct sk_buff *skb;
+			u16 ci;
+			int j;
+
+			last_wqe = (sqcc == wqe_counter);
+
+			ci = sqcc & sq->wq.sz_m1;
+			skb = sq->skb[ci];
+
+			if (unlikely(!skb)) { /* nop */
+				sq->stats.nop++;
+				sqcc++;
+				continue;
+			}
+
+			for (j = 0; j < MLX5E_TX_SKB_CB(skb)->num_dma; j++) {
+				dma_addr_t addr;
+				u32 size;
+
+				mlx5e_dma_get(sq, dma_fifo_cc, &addr, &size);
+				dma_fifo_cc++;
+				dma_unmap_single(sq->pdev, addr, size,
+						 DMA_TO_DEVICE);
+			}
+
+			npkts++;
+			nbytes += MLX5E_TX_SKB_CB(skb)->num_bytes;
+			sqcc += MLX5E_TX_SKB_CB(skb)->num_wqebbs;
+			dev_kfree_skb(skb);
+		} while (!last_wqe);
+	}
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->dma_fifo_cc = dma_fifo_cc;
+	sq->cc = sqcc;
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
+
+	if (netif_tx_queue_stopped(sq->txq) &&
+	    mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) &&
+	    likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) {
+				netif_tx_wake_queue(sq->txq);
+				sq->stats.wake++;
+	}
+	if (i == MLX5E_TX_CQ_POLL_BUDGET) {
+		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
+		return true;
+	}
+
+	return false;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
new file mode 100644
index 000000000000..2c7cb6755d1d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -0,0 +1,105 @@
+/*
+ * Copyright (c) 2015, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "en.h"
+
+struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq)
+{
+	struct mlx5_cqwq *wq = &cq->wq;
+	u32 ci = mlx5_cqwq_get_ci(wq);
+	struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
+	int cqe_ownership_bit = cqe->op_own & MLX5_CQE_OWNER_MASK;
+	int sw_ownership_val = mlx5_cqwq_get_wrap_cnt(wq) & 1;
+
+	if (cqe_ownership_bit != sw_ownership_val)
+		return NULL;
+
+	/* ensure cqe content is read after cqe ownership bit */
+	rmb();
+
+	return cqe;
+}
+
+int mlx5e_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
+					       napi);
+	bool busy = false;
+	int i;
+
+	clear_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags);
+
+	for (i = 0; i < c->num_tc; i++)
+		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq);
+
+	busy |= mlx5e_poll_rx_cq(&c->rq.cq, budget);
+
+	busy |= mlx5e_post_rx_wqes(&c->rq);
+
+	if (busy)
+		return budget;
+
+	napi_complete(napi);
+
+	/* avoid losing completion event during/after polling cqs */
+	if (test_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags)) {
+		napi_schedule(napi);
+		return 0;
+	}
+
+	for (i = 0; i < c->num_tc; i++)
+		mlx5e_cq_arm(&c->sq[i].cq);
+	mlx5e_cq_arm(&c->rq.cq);
+
+	return 0;
+}
+
+void mlx5e_completion_event(struct mlx5_core_cq *mcq)
+{
+	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
+
+	set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
+	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
+	barrier();
+	napi_schedule(cq->napi);
+}
+
+void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
+{
+	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
+	struct mlx5e_channel *c = cq->channel;
+	struct mlx5e_priv *priv = c->priv;
+	struct net_device *netdev = priv->netdev;
+
+	netdev_err(netdev, "%s: cqn=0x%.6x event=0x%.2x\n",
+		   __func__, mcq->cqn, event);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 58800e4f3958..a40b96d4c662 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -339,15 +339,14 @@ static void init_eq_buf(struct mlx5_eq *eq)
 int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		       int nent, u64 mask, const char *name, struct mlx5_uar *uar)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_create_eq_mbox_in *in;
 	struct mlx5_create_eq_mbox_out out;
 	int err;
 	int inlen;
 
 	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
-	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, 2 * PAGE_SIZE,
-			     &eq->buf);
+	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
 	if (err)
 		return err;
 
@@ -378,14 +377,15 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		goto err_in;
 	}
 
-	snprintf(eq->name, MLX5_MAX_EQ_NAME, "%s@pci:%s",
+	snprintf(priv->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
 		 name, pci_name(dev->pdev));
+
 	eq->eqn = out.eq_number;
 	eq->irqn = vecidx;
 	eq->dev = dev;
 	eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET;
-	err = request_irq(table->msix_arr[vecidx].vector, mlx5_msix_handler, 0,
-			  eq->name, eq);
+	err = request_irq(priv->msix_arr[vecidx].vector, mlx5_msix_handler, 0,
+			  priv->irq_info[vecidx].name, eq);
 	if (err)
 		goto err_eq;
 
@@ -401,7 +401,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	return 0;
 
 err_irq:
-	free_irq(table->msix_arr[vecidx].vector, eq);
+	free_irq(priv->msix_arr[vecidx].vector, eq);
 
 err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);
@@ -417,16 +417,15 @@ EXPORT_SYMBOL_GPL(mlx5_create_map_eq);
 
 int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
 	int err;
 
 	mlx5_debug_eq_remove(dev, eq);
-	free_irq(table->msix_arr[eq->irqn].vector, eq);
+	free_irq(dev->priv.msix_arr[eq->irqn].vector, eq);
 	err = mlx5_cmd_destroy_eq(dev, eq->eqn);
 	if (err)
 		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
 			       eq->eqn);
-	synchronize_irq(table->msix_arr[eq->irqn].vector);
+	synchronize_irq(dev->priv.msix_arr[eq->irqn].vector);
 	mlx5_buf_free(dev, &eq->buf);
 
 	return err;
@@ -456,7 +455,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	u32 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 	int err;
 
-	if (dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG)
+	if (MLX5_CAP_GEN(dev, pg))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PAGE_FAULT);
 
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
@@ -479,7 +478,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 
 	err = mlx5_create_map_eq(dev, &table->pages_eq,
 				 MLX5_EQ_VEC_PAGES,
-				 dev->caps.gen.max_vf + 1,
+				 /* TODO: sriov max_vf + */ 1,
 				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
 				 &dev->priv.uuari.uars[0]);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c b/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c
new file mode 100644
index 000000000000..ca90b9bc3b95
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/flow_table.c
@@ -0,0 +1,422 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/export.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/flow_table.h>
+#include "mlx5_core.h"
+
+struct mlx5_ftg {
+	struct mlx5_flow_table_group    g;
+	u32				id;
+	u32				start_ix;
+};
+
+struct mlx5_flow_table {
+	struct mlx5_core_dev	*dev;
+	u8			level;
+	u8			type;
+	u32			id;
+	struct mutex		mutex; /* sync bitmap alloc */
+	u16			num_groups;
+	struct mlx5_ftg		*group;
+	unsigned long		*bitmap;
+	u32			size;
+};
+
+static int mlx5_set_flow_entry_cmd(struct mlx5_flow_table *ft, u32 group_ix,
+				   u32 flow_index, void *flow_context)
+{
+	u32 out[MLX5_ST_SZ_DW(set_fte_out)];
+	u32 *in;
+	void *in_flow_context;
+	int fcdls =
+		MLX5_GET(flow_context, flow_context, destination_list_size) *
+		MLX5_ST_SZ_BYTES(dest_format_struct);
+	int inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fcdls;
+	int err;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in) {
+		mlx5_core_warn(ft->dev, "failed to allocate inbox\n");
+		return -ENOMEM;
+	}
+
+	MLX5_SET(set_fte_in, in, table_type, ft->type);
+	MLX5_SET(set_fte_in, in, table_id,   ft->id);
+	MLX5_SET(set_fte_in, in, flow_index, flow_index);
+	MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY);
+
+	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
+	memcpy(in_flow_context, flow_context,
+	       MLX5_ST_SZ_BYTES(flow_context) + fcdls);
+
+	MLX5_SET(flow_context, in_flow_context, group_id,
+		 ft->group[group_ix].id);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out,
+					 sizeof(out));
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5_del_flow_entry_cmd(struct mlx5_flow_table *ft, u32 flow_index)
+{
+	u32 in[MLX5_ST_SZ_DW(delete_fte_in)];
+	u32 out[MLX5_ST_SZ_DW(delete_fte_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+#define MLX5_SET_DFTEI(p, x, v) MLX5_SET(delete_fte_in, p, x, v)
+	MLX5_SET_DFTEI(in, table_type, ft->type);
+	MLX5_SET_DFTEI(in, table_id,   ft->id);
+	MLX5_SET_DFTEI(in, flow_index, flow_index);
+	MLX5_SET_DFTEI(in, opcode,     MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
+
+	mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out));
+}
+
+static void mlx5_destroy_flow_group_cmd(struct mlx5_flow_table *ft, int i)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+#define MLX5_SET_DFGI(p, x, v) MLX5_SET(destroy_flow_group_in, p, x, v)
+	MLX5_SET_DFGI(in, table_type, ft->type);
+	MLX5_SET_DFGI(in, table_id,   ft->id);
+	MLX5_SET_DFGI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP);
+	MLX5_SET_DFGI(in, group_id, ft->group[i].id);
+	mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_create_flow_group_cmd(struct mlx5_flow_table *ft, int i)
+{
+	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)];
+	u32 *in;
+	void *in_match_criteria;
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table_group *g = &ft->group[i].g;
+	u32 start_ix = ft->group[i].start_ix;
+	u32 end_ix = start_ix + (1 << g->log_sz) - 1;
+	int err;
+
+	in = mlx5_vzalloc(inlen);
+	if (!in) {
+		mlx5_core_warn(ft->dev, "failed to allocate inbox\n");
+		return -ENOMEM;
+	}
+	in_match_criteria = MLX5_ADDR_OF(create_flow_group_in, in,
+					 match_criteria);
+
+	memset(out, 0, sizeof(out));
+
+#define MLX5_SET_CFGI(p, x, v) MLX5_SET(create_flow_group_in, p, x, v)
+	MLX5_SET_CFGI(in, table_type,            ft->type);
+	MLX5_SET_CFGI(in, table_id,              ft->id);
+	MLX5_SET_CFGI(in, opcode,                MLX5_CMD_OP_CREATE_FLOW_GROUP);
+	MLX5_SET_CFGI(in, start_flow_index,      start_ix);
+	MLX5_SET_CFGI(in, end_flow_index,        end_ix);
+	MLX5_SET_CFGI(in, match_criteria_enable, g->match_criteria_enable);
+
+	memcpy(in_match_criteria, g->match_criteria,
+	       MLX5_ST_SZ_BYTES(fte_match_param));
+
+	err = mlx5_cmd_exec_check_status(ft->dev, in, inlen, out,
+					 sizeof(out));
+	if (!err)
+		ft->group[i].id = MLX5_GET(create_flow_group_out, out,
+					   group_id);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void mlx5_destroy_flow_table_groups(struct mlx5_flow_table *ft)
+{
+	int i;
+
+	for (i = 0; i < ft->num_groups; i++)
+		mlx5_destroy_flow_group_cmd(ft, i);
+}
+
+static int mlx5_create_flow_table_groups(struct mlx5_flow_table *ft)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < ft->num_groups; i++) {
+		err = mlx5_create_flow_group_cmd(ft, i);
+		if (err)
+			goto err_destroy_flow_table_groups;
+	}
+
+	return 0;
+
+err_destroy_flow_table_groups:
+	for (i--; i >= 0; i--)
+		mlx5_destroy_flow_group_cmd(ft, i);
+
+	return err;
+}
+
+static int mlx5_create_flow_table_cmd(struct mlx5_flow_table *ft)
+{
+	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)];
+	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(create_flow_table_in, in, table_type, ft->type);
+	MLX5_SET(create_flow_table_in, in, level,      ft->level);
+	MLX5_SET(create_flow_table_in, in, log_size,   order_base_2(ft->size));
+
+	MLX5_SET(create_flow_table_in, in, opcode,
+		 MLX5_CMD_OP_CREATE_FLOW_TABLE);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out,
+					 sizeof(out));
+	if (err)
+		return err;
+
+	ft->id = MLX5_GET(create_flow_table_out, out, table_id);
+
+	return 0;
+}
+
+static void mlx5_destroy_flow_table_cmd(struct mlx5_flow_table *ft)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+#define MLX5_SET_DFTI(p, x, v) MLX5_SET(destroy_flow_table_in, p, x, v)
+	MLX5_SET_DFTI(in, table_type, ft->type);
+	MLX5_SET_DFTI(in, table_id,   ft->id);
+	MLX5_SET_DFTI(in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE);
+
+	mlx5_cmd_exec_check_status(ft->dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_find_group(struct mlx5_flow_table *ft, u8 match_criteria_enable,
+			   u32 *match_criteria, int *group_ix)
+{
+	void *mc_outer = MLX5_ADDR_OF(fte_match_param, match_criteria,
+				      outer_headers);
+	void *mc_misc  = MLX5_ADDR_OF(fte_match_param, match_criteria,
+				      misc_parameters);
+	void *mc_inner = MLX5_ADDR_OF(fte_match_param, match_criteria,
+				      inner_headers);
+	int mc_outer_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4);
+	int mc_misc_sz  = MLX5_ST_SZ_BYTES(fte_match_set_misc);
+	int mc_inner_sz = MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4);
+	int i;
+
+	for (i = 0; i < ft->num_groups; i++) {
+		struct mlx5_flow_table_group *g = &ft->group[i].g;
+		void *gmc_outer = MLX5_ADDR_OF(fte_match_param,
+					       g->match_criteria,
+					       outer_headers);
+		void *gmc_misc  = MLX5_ADDR_OF(fte_match_param,
+					       g->match_criteria,
+					       misc_parameters);
+		void *gmc_inner = MLX5_ADDR_OF(fte_match_param,
+					       g->match_criteria,
+					       inner_headers);
+
+		if (g->match_criteria_enable != match_criteria_enable)
+			continue;
+
+		if (match_criteria_enable & MLX5_MATCH_OUTER_HEADERS)
+			if (memcmp(mc_outer, gmc_outer, mc_outer_sz))
+				continue;
+
+		if (match_criteria_enable & MLX5_MATCH_MISC_PARAMETERS)
+			if (memcmp(mc_misc, gmc_misc, mc_misc_sz))
+				continue;
+
+		if (match_criteria_enable & MLX5_MATCH_INNER_HEADERS)
+			if (memcmp(mc_inner, gmc_inner, mc_inner_sz))
+				continue;
+
+		*group_ix = i;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int alloc_flow_index(struct mlx5_flow_table *ft, int group_ix, u32 *ix)
+{
+	struct mlx5_ftg *g = &ft->group[group_ix];
+	int err = 0;
+
+	mutex_lock(&ft->mutex);
+
+	*ix = find_next_zero_bit(ft->bitmap, ft->size, g->start_ix);
+	if (*ix >= (g->start_ix + (1 << g->g.log_sz)))
+		err = -ENOSPC;
+	else
+		__set_bit(*ix, ft->bitmap);
+
+	mutex_unlock(&ft->mutex);
+
+	return err;
+}
+
+static void mlx5_free_flow_index(struct mlx5_flow_table *ft, u32 ix)
+{
+	__clear_bit(ix, ft->bitmap);
+}
+
+int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable,
+			      void *match_criteria, void *flow_context,
+			      u32 *flow_index)
+{
+	struct mlx5_flow_table *ft = flow_table;
+	int group_ix;
+	int err;
+
+	err = mlx5_find_group(ft, match_criteria_enable, match_criteria,
+			      &group_ix);
+	if (err) {
+		mlx5_core_warn(ft->dev, "mlx5_find_group failed\n");
+		return err;
+	}
+
+	err = alloc_flow_index(ft, group_ix, flow_index);
+	if (err) {
+		mlx5_core_warn(ft->dev, "alloc_flow_index failed\n");
+		return err;
+	}
+
+	return mlx5_set_flow_entry_cmd(ft, group_ix, *flow_index, flow_context);
+}
+EXPORT_SYMBOL(mlx5_add_flow_table_entry);
+
+void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index)
+{
+	struct mlx5_flow_table *ft = flow_table;
+
+	mlx5_del_flow_entry_cmd(ft, flow_index);
+	mlx5_free_flow_index(ft, flow_index);
+}
+EXPORT_SYMBOL(mlx5_del_flow_table_entry);
+
+void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type,
+			     u16 num_groups,
+			     struct mlx5_flow_table_group *group)
+{
+	struct mlx5_flow_table *ft;
+	u32 start_ix = 0;
+	u32 ft_size = 0;
+	void *gr;
+	void *bm;
+	int err;
+	int i;
+
+	for (i = 0; i < num_groups; i++)
+		ft_size += (1 << group[i].log_sz);
+
+	ft = kzalloc(sizeof(*ft), GFP_KERNEL);
+	gr = kcalloc(num_groups, sizeof(struct mlx5_ftg), GFP_KERNEL);
+	bm = kcalloc(BITS_TO_LONGS(ft_size), sizeof(uintptr_t), GFP_KERNEL);
+	if (!ft || !gr || !bm)
+		goto err_free_ft;
+
+	ft->group	= gr;
+	ft->bitmap	= bm;
+	ft->num_groups	= num_groups;
+	ft->level	= level;
+	ft->type	= table_type;
+	ft->size	= ft_size;
+	ft->dev		= dev;
+	mutex_init(&ft->mutex);
+
+	for (i = 0; i < ft->num_groups; i++) {
+		memcpy(&ft->group[i].g, &group[i], sizeof(*group));
+		ft->group[i].start_ix = start_ix;
+		start_ix += 1 << group[i].log_sz;
+	}
+
+	err = mlx5_create_flow_table_cmd(ft);
+	if (err)
+		goto err_free_ft;
+
+	err = mlx5_create_flow_table_groups(ft);
+	if (err)
+		goto err_destroy_flow_table_cmd;
+
+	return ft;
+
+err_destroy_flow_table_cmd:
+	mlx5_destroy_flow_table_cmd(ft);
+
+err_free_ft:
+	mlx5_core_warn(dev, "failed to alloc flow table\n");
+	kfree(bm);
+	kfree(gr);
+	kfree(ft);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mlx5_create_flow_table);
+
+void mlx5_destroy_flow_table(void *flow_table)
+{
+	struct mlx5_flow_table *ft = flow_table;
+
+	mlx5_destroy_flow_table_groups(ft);
+	mlx5_destroy_flow_table_cmd(ft);
+	kfree(ft->bitmap);
+	kfree(ft->group);
+	kfree(ft);
+}
+EXPORT_SYMBOL(mlx5_destroy_flow_table);
+
+u32 mlx5_get_flow_table_id(void *flow_table)
+{
+	struct mlx5_flow_table *ft = flow_table;
+
+	return ft->id;
+}
+EXPORT_SYMBOL(mlx5_get_flow_table_id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 4b4cda3bcc5f..9335e5ae18cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -35,79 +35,133 @@
 #include <linux/module.h>
 #include "mlx5_core.h"
 
-int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev)
+static int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev, u32 *out,
+				  int outlen)
 {
-	struct mlx5_cmd_query_adapter_mbox_out *out;
-	struct mlx5_cmd_query_adapter_mbox_in in;
+	u32 in[MLX5_ST_SZ_DW(query_adapter_in)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(query_adapter_in, in, opcode, MLX5_CMD_OP_QUERY_ADAPTER);
+
+	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_query_board_id(struct mlx5_core_dev *dev)
+{
+	u32 *out;
+	int outlen = MLX5_ST_SZ_BYTES(query_adapter_out);
 	int err;
 
-	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	out = kzalloc(outlen, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
 
-	memset(&in, 0, sizeof(in));
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_ADAPTER);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, sizeof(*out));
+	err = mlx5_cmd_query_adapter(dev, out, outlen);
 	if (err)
-		goto out_out;
-
-	if (out->hdr.status) {
-		err = mlx5_cmd_status_to_err(&out->hdr);
-		goto out_out;
-	}
+		goto out;
 
-	memcpy(dev->board_id, out->vsd_psid, sizeof(out->vsd_psid));
+	memcpy(dev->board_id,
+	       MLX5_ADDR_OF(query_adapter_out, out,
+			    query_adapter_struct.vsd_contd_psid),
+	       MLX5_FLD_SZ_BYTES(query_adapter_out,
+				 query_adapter_struct.vsd_contd_psid));
 
-out_out:
+out:
 	kfree(out);
-
 	return err;
 }
 
-int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev, struct mlx5_caps *caps)
+int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id)
 {
-	return mlx5_core_get_caps(dev, caps, HCA_CAP_OPMOD_GET_CUR);
+	u32 *out;
+	int outlen = MLX5_ST_SZ_BYTES(query_adapter_out);
+	int err;
+
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	err = mlx5_cmd_query_adapter(mdev, out, outlen);
+	if (err)
+		goto out;
+
+	*vendor_id = MLX5_GET(query_adapter_out, out,
+			      query_adapter_struct.ieee_vendor_id);
+out:
+	kfree(out);
+	return err;
 }
+EXPORT_SYMBOL(mlx5_core_query_vendor_id);
 
-int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *caps)
+int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 {
-	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
-	int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	void *out;
 	int err;
 
-	if (!(dev->caps.gen.flags & MLX5_DEV_CAP_FLAG_ON_DMND_PG))
-		return -ENOTSUPP;
+	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR);
+	if (err)
+		return err;
 
-	memset(in, 0, sizeof(in));
-	out = kzalloc(out_sz, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
-	MLX5_SET(query_hca_cap_in, in, op_mod, HCA_CAP_OPMOD_GET_ODP_CUR);
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
+	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_MAX);
 	if (err)
-		goto out;
+		return err;
 
-	err = mlx5_cmd_status_to_err_v2(out);
-	if (err) {
-		mlx5_core_warn(dev, "query cur hca ODP caps failed, %d\n", err);
-		goto out;
+	if (MLX5_CAP_GEN(dev, eth_net_offloads)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS,
+					 HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS,
+					 HCA_CAP_OPMOD_GET_MAX);
+		if (err)
+			return err;
 	}
 
-	memcpy(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct),
-	       sizeof(*caps));
+	if (MLX5_CAP_GEN(dev, pg)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ODP,
+					 HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ODP,
+					 HCA_CAP_OPMOD_GET_MAX);
+		if (err)
+			return err;
+	}
 
-	mlx5_core_dbg(dev, "on-demand paging capabilities:\nrc: %08x\nuc: %08x\nud: %08x\n",
-		be32_to_cpu(caps->per_transport_caps.rc_odp_caps),
-		be32_to_cpu(caps->per_transport_caps.uc_odp_caps),
-		be32_to_cpu(caps->per_transport_caps.ud_odp_caps));
+	if (MLX5_CAP_GEN(dev, atomic)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC,
+					 HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ATOMIC,
+					 HCA_CAP_OPMOD_GET_MAX);
+		if (err)
+			return err;
+	}
 
-out:
-	kfree(out);
-	return err;
+	if (MLX5_CAP_GEN(dev, roce)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE,
+					 HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+		err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE,
+					 HCA_CAP_OPMOD_GET_MAX);
+		if (err)
+			return err;
+	}
+
+	if (MLX5_CAP_GEN(dev, nic_flow_table)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE,
+					 HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+		err = mlx5_core_get_caps(dev, MLX5_CAP_FLOW_TABLE,
+					 HCA_CAP_OPMOD_GET_MAX);
+		if (err)
+			return err;
+	}
+	return 0;
 }
-EXPORT_SYMBOL(mlx5_query_odp_caps);
 
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c
index ee1b0b965f34..1368dac00da0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mad.c
@@ -36,7 +36,7 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, void *inb, void *outb,
+int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		      u16 opmod, u8 port)
 {
 	struct mlx5_mad_ifc_mbox_in *in = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 28425e5ea91f..afad529838de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -38,6 +38,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/io-mapping.h>
+#include <linux/interrupt.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/qp.h>
@@ -47,10 +48,6 @@
 #include <linux/mlx5/mlx5_ifc.h>
 #include "mlx5_core.h"
 
-#define DRIVER_NAME "mlx5_core"
-#define DRIVER_VERSION "3.0"
-#define DRIVER_RELDATE  "January 2015"
-
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver");
 MODULE_LICENSE("Dual BSD/GPL");
@@ -208,24 +205,28 @@ static void release_bar(struct pci_dev *pdev)
 
 static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	int num_eqs = 1 << dev->caps.gen.log_max_eq;
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_eq_table *table = &priv->eq_table;
+	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 	int i;
 
-	nvec = dev->caps.gen.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE;
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_EQ_VEC_COMP_BASE;
 	nvec = min_t(int, nvec, num_eqs);
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	table->msix_arr = kzalloc(nvec * sizeof(*table->msix_arr), GFP_KERNEL);
-	if (!table->msix_arr)
-		return -ENOMEM;
+	priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL);
+
+	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
+	if (!priv->msix_arr || !priv->irq_info)
+		goto err_free_msix;
 
 	for (i = 0; i < nvec; i++)
-		table->msix_arr[i].entry = i;
+		priv->msix_arr[i].entry = i;
 
-	nvec = pci_enable_msix_range(dev->pdev, table->msix_arr,
+	nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr,
 				     MLX5_EQ_VEC_COMP_BASE + 1, nvec);
 	if (nvec < 0)
 		return nvec;
@@ -233,14 +234,20 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
 
 	return 0;
+
+err_free_msix:
+	kfree(priv->irq_info);
+	kfree(priv->msix_arr);
+	return -ENOMEM;
 }
 
 static void mlx5_disable_msix(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_priv *priv = &dev->priv;
 
 	pci_disable_msix(dev->pdev);
-	kfree(table->msix_arr);
+	kfree(priv->irq_info);
+	kfree(priv->msix_arr);
 }
 
 struct mlx5_reg_host_endianess {
@@ -277,98 +284,20 @@ static u16 to_fw_pkey_sz(u32 size)
 	}
 }
 
-/* selectively copy writable fields clearing any reserved area
- */
-static void copy_rw_fields(void *to, struct mlx5_caps *from)
-{
-	__be64 *flags_off = (__be64 *)MLX5_ADDR_OF(cmd_hca_cap, to, reserved_22);
-	u64 v64;
-
-	MLX5_SET(cmd_hca_cap, to, log_max_qp, from->gen.log_max_qp);
-	MLX5_SET(cmd_hca_cap, to, log_max_ra_req_qp, from->gen.log_max_ra_req_qp);
-	MLX5_SET(cmd_hca_cap, to, log_max_ra_res_qp, from->gen.log_max_ra_res_qp);
-	MLX5_SET(cmd_hca_cap, to, pkey_table_size, from->gen.pkey_table_size);
-	MLX5_SET(cmd_hca_cap, to, pkey_table_size, to_fw_pkey_sz(from->gen.pkey_table_size));
-	MLX5_SET(cmd_hca_cap, to, log_uar_page_sz, PAGE_SHIFT - 12);
-	v64 = from->gen.flags & MLX5_CAP_BITS_RW_MASK;
-	*flags_off = cpu_to_be64(v64);
-}
-
-static u16 get_pkey_table_size(int pkey)
-{
-	if (pkey > MLX5_MAX_LOG_PKEY_TABLE)
-		return 0;
-
-	return MLX5_MIN_PKEY_TABLE_SIZE << pkey;
-}
-
-static void fw2drv_caps(struct mlx5_caps *caps, void *out)
-{
-	struct mlx5_general_caps *gen = &caps->gen;
-
-	gen->max_srq_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_srq_sz);
-	gen->max_wqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_qp_sz);
-	gen->log_max_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_qp);
-	gen->log_max_strq = MLX5_GET_PR(cmd_hca_cap, out, log_max_strq_sz);
-	gen->log_max_srq = MLX5_GET_PR(cmd_hca_cap, out, log_max_srqs);
-	gen->max_cqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_cq_sz);
-	gen->log_max_cq = MLX5_GET_PR(cmd_hca_cap, out, log_max_cq);
-	gen->max_eqes = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_max_eq_sz);
-	gen->log_max_mkey = MLX5_GET_PR(cmd_hca_cap, out, log_max_mkey);
-	gen->log_max_eq = MLX5_GET_PR(cmd_hca_cap, out, log_max_eq);
-	gen->max_indirection = MLX5_GET_PR(cmd_hca_cap, out, max_indirection);
-	gen->log_max_mrw_sz = MLX5_GET_PR(cmd_hca_cap, out, log_max_mrw_sz);
-	gen->log_max_bsf_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_bsf_list_size);
-	gen->log_max_klm_list_size = MLX5_GET_PR(cmd_hca_cap, out, log_max_klm_list_size);
-	gen->log_max_ra_req_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_dc);
-	gen->log_max_ra_res_dc = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_dc);
-	gen->log_max_ra_req_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_req_qp);
-	gen->log_max_ra_res_qp = MLX5_GET_PR(cmd_hca_cap, out, log_max_ra_res_qp);
-	gen->max_qp_counters = MLX5_GET_PR(cmd_hca_cap, out, max_qp_cnt);
-	gen->pkey_table_size = get_pkey_table_size(MLX5_GET_PR(cmd_hca_cap, out, pkey_table_size));
-	gen->local_ca_ack_delay = MLX5_GET_PR(cmd_hca_cap, out, local_ca_ack_delay);
-	gen->num_ports = MLX5_GET_PR(cmd_hca_cap, out, num_ports);
-	gen->log_max_msg = MLX5_GET_PR(cmd_hca_cap, out, log_max_msg);
-	gen->stat_rate_support = MLX5_GET_PR(cmd_hca_cap, out, stat_rate_support);
-	gen->flags = be64_to_cpu(*(__be64 *)MLX5_ADDR_OF(cmd_hca_cap, out, reserved_22));
-	pr_debug("flags = 0x%llx\n", gen->flags);
-	gen->uar_sz = MLX5_GET_PR(cmd_hca_cap, out, uar_sz);
-	gen->min_log_pg_sz = MLX5_GET_PR(cmd_hca_cap, out, log_pg_sz);
-	gen->bf_reg_size = MLX5_GET_PR(cmd_hca_cap, out, bf);
-	gen->bf_reg_size = 1 << MLX5_GET_PR(cmd_hca_cap, out, log_bf_reg_size);
-	gen->max_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq);
-	gen->max_rq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_rq);
-	gen->max_dc_sq_desc_sz = MLX5_GET_PR(cmd_hca_cap, out, max_wqe_sz_sq_dc);
-	gen->max_qp_mcg = MLX5_GET_PR(cmd_hca_cap, out, max_qp_mcg);
-	gen->log_max_pd = MLX5_GET_PR(cmd_hca_cap, out, log_max_pd);
-	gen->log_max_xrcd = MLX5_GET_PR(cmd_hca_cap, out, log_max_xrcd);
-	gen->log_uar_page_sz = MLX5_GET_PR(cmd_hca_cap, out, log_uar_page_sz);
-}
-
-static const char *caps_opmod_str(u16 opmod)
-{
-	switch (opmod) {
-	case HCA_CAP_OPMOD_GET_MAX:
-		return "GET_MAX";
-	case HCA_CAP_OPMOD_GET_CUR:
-		return "GET_CUR";
-	default:
-		return "Invalid";
-	}
-}
-
-int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
-		       u16 opmod)
+int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type,
+		       enum mlx5_cap_mode cap_mode)
 {
 	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)];
 	int out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	void *out;
+	void *out, *hca_caps;
+	u16 opmod = (cap_type << 1) | (cap_mode & 0x01);
 	int err;
 
 	memset(in, 0, sizeof(in));
 	out = kzalloc(out_sz, GFP_KERNEL);
 	if (!out)
 		return -ENOMEM;
+
 	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
 	MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
@@ -377,12 +306,30 @@ int mlx5_core_get_caps(struct mlx5_core_dev *dev, struct mlx5_caps *caps,
 
 	err = mlx5_cmd_status_to_err_v2(out);
 	if (err) {
-		mlx5_core_warn(dev, "query max hca cap failed, %d\n", err);
+		mlx5_core_warn(dev,
+			       "QUERY_HCA_CAP : type(%x) opmode(%x) Failed(%d)\n",
+			       cap_type, cap_mode, err);
 		goto query_ex;
 	}
-	mlx5_core_dbg(dev, "%s\n", caps_opmod_str(opmod));
-	fw2drv_caps(caps, MLX5_ADDR_OF(query_hca_cap_out, out, capability_struct));
 
+	hca_caps =  MLX5_ADDR_OF(query_hca_cap_out, out, capability);
+
+	switch (cap_mode) {
+	case HCA_CAP_OPMOD_GET_MAX:
+		memcpy(dev->hca_caps_max[cap_type], hca_caps,
+		       MLX5_UN_SZ_BYTES(hca_cap_union));
+		break;
+	case HCA_CAP_OPMOD_GET_CUR:
+		memcpy(dev->hca_caps_cur[cap_type], hca_caps,
+		       MLX5_UN_SZ_BYTES(hca_cap_union));
+		break;
+	default:
+		mlx5_core_warn(dev,
+			       "Tried to query dev cap type(%x) with wrong opmode(%x)\n",
+			       cap_type, cap_mode);
+		err = -EINVAL;
+		break;
+	}
 query_ex:
 	kfree(out);
 	return err;
@@ -409,49 +356,45 @@ static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
 	void *set_ctx = NULL;
 	struct mlx5_profile *prof = dev->profile;
-	struct mlx5_caps *cur_caps = NULL;
-	struct mlx5_caps *max_caps = NULL;
 	int err = -ENOMEM;
 	int set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	void *set_hca_cap;
 
 	set_ctx = kzalloc(set_sz, GFP_KERNEL);
 	if (!set_ctx)
 		goto query_ex;
 
-	max_caps = kzalloc(sizeof(*max_caps), GFP_KERNEL);
-	if (!max_caps)
-		goto query_ex;
-
-	cur_caps = kzalloc(sizeof(*cur_caps), GFP_KERNEL);
-	if (!cur_caps)
-		goto query_ex;
-
-	err = mlx5_core_get_caps(dev, max_caps, HCA_CAP_OPMOD_GET_MAX);
+	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_MAX);
 	if (err)
 		goto query_ex;
 
-	err = mlx5_core_get_caps(dev, cur_caps, HCA_CAP_OPMOD_GET_CUR);
+	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL, HCA_CAP_OPMOD_GET_CUR);
 	if (err)
 		goto query_ex;
 
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx,
+				   capability);
+	memcpy(set_hca_cap, dev->hca_caps_cur[MLX5_CAP_GENERAL],
+	       MLX5_ST_SZ_BYTES(cmd_hca_cap));
+
+	mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n",
+		      mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(dev, pkey_table_size)),
+		      128);
 	/* we limit the size of the pkey table to 128 entries for now */
-	cur_caps->gen.pkey_table_size = 128;
+	MLX5_SET(cmd_hca_cap, set_hca_cap, pkey_table_size,
+		 to_fw_pkey_sz(128));
 
 	if (prof->mask & MLX5_PROF_MASK_QP_SIZE)
-		cur_caps->gen.log_max_qp = prof->log_max_qp;
+		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_qp,
+			 prof->log_max_qp);
 
-	/* disable checksum */
-	cur_caps->gen.flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM;
+	/* disable cmdif checksum */
+	MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0);
 
-	copy_rw_fields(MLX5_ADDR_OF(set_hca_cap_in, set_ctx, hca_capability_struct),
-		       cur_caps);
 	err = set_caps(dev, set_ctx, set_sz);
 
 query_ex:
-	kfree(cur_caps);
-	kfree(max_caps);
 	kfree(set_ctx);
-
 	return err;
 }
 
@@ -507,6 +450,74 @@ static int mlx5_core_disable_hca(struct mlx5_core_dev *dev)
 	return 0;
 }
 
+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	struct msix_entry *msix = priv->msix_arr;
+	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
+	int numa_node           = dev_to_node(&mdev->pdev->dev);
+	int err;
+
+	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+			priv->irq_info[i].mask);
+
+	err = irq_set_affinity_hint(irq, priv->irq_info[i].mask);
+	if (err) {
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed,irq 0x%.4x",
+			       irq);
+		goto err_clear_mask;
+	}
+
+	return 0;
+
+err_clear_mask:
+	free_cpumask_var(priv->irq_info[i].mask);
+	return err;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	struct msix_entry *msix = priv->msix_arr;
+	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
+
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(priv->irq_info[i].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+		err = mlx5_irq_set_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+		mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, int *irqn)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
@@ -549,7 +560,7 @@ static void free_comp_eqs(struct mlx5_core_dev *dev)
 static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	char name[MLX5_MAX_EQ_NAME];
+	char name[MLX5_MAX_IRQ_NAME];
 	struct mlx5_eq *eq;
 	int ncomp_vec;
 	int nent;
@@ -566,7 +577,7 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 			goto clean;
 		}
 
-		snprintf(name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i);
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq,
 					 i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
 					 name, &dev->priv.uuari.uars[0]);
@@ -588,6 +599,61 @@ clean:
 	return err;
 }
 
+#ifdef CONFIG_MLX5_CORE_EN
+static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
+{
+	u32 query_in[MLX5_ST_SZ_DW(query_issi_in)];
+	u32 query_out[MLX5_ST_SZ_DW(query_issi_out)];
+	u32 set_in[MLX5_ST_SZ_DW(set_issi_in)];
+	u32 set_out[MLX5_ST_SZ_DW(set_issi_out)];
+	int err;
+	u32 sup_issi;
+
+	memset(query_in, 0, sizeof(query_in));
+	memset(query_out, 0, sizeof(query_out));
+
+	MLX5_SET(query_issi_in, query_in, opcode, MLX5_CMD_OP_QUERY_ISSI);
+
+	err = mlx5_cmd_exec_check_status(dev, query_in, sizeof(query_in),
+					 query_out, sizeof(query_out));
+	if (err) {
+		if (((struct mlx5_outbox_hdr *)query_out)->status ==
+		    MLX5_CMD_STAT_BAD_OP_ERR) {
+			pr_debug("Only ISSI 0 is supported\n");
+			return 0;
+		}
+
+		pr_err("failed to query ISSI\n");
+		return err;
+	}
+
+	sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0);
+
+	if (sup_issi & (1 << 1)) {
+		memset(set_in, 0, sizeof(set_in));
+		memset(set_out, 0, sizeof(set_out));
+
+		MLX5_SET(set_issi_in, set_in, opcode, MLX5_CMD_OP_SET_ISSI);
+		MLX5_SET(set_issi_in, set_in, current_issi, 1);
+
+		err = mlx5_cmd_exec_check_status(dev, set_in, sizeof(set_in),
+						 set_out, sizeof(set_out));
+		if (err) {
+			pr_err("failed to set ISSI=1\n");
+			return err;
+		}
+
+		dev->issi = 1;
+
+		return 0;
+	} else if (sup_issi & (1 << 0) || !sup_issi) {
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+#endif
+
 static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -650,6 +716,14 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 		goto err_pagealloc_cleanup;
 	}
 
+#ifdef CONFIG_MLX5_CORE_EN
+	err = mlx5_core_set_issi(dev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to set issi\n");
+		goto err_disable_hca;
+	}
+#endif
+
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
 		dev_err(&pdev->dev, "failed to allocate boot pages\n");
@@ -688,15 +762,15 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 
 	mlx5_start_health_poll(dev);
 
-	err = mlx5_cmd_query_hca_cap(dev, &dev->caps);
+	err = mlx5_query_hca_caps(dev);
 	if (err) {
 		dev_err(&pdev->dev, "query hca failed\n");
 		goto err_stop_poll;
 	}
 
-	err = mlx5_cmd_query_adapter(dev);
+	err = mlx5_query_board_id(dev);
 	if (err) {
-		dev_err(&pdev->dev, "query adapter failed\n");
+		dev_err(&pdev->dev, "query board id failed\n");
 		goto err_stop_poll;
 	}
 
@@ -730,6 +804,12 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 		goto err_stop_eqs;
 	}
 
+	err = mlx5_irq_set_affinity_hints(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_free_comp_eqs;
+	}
+
 	MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock);
 
 	mlx5_init_cq_table(dev);
@@ -739,6 +819,9 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 
 	return 0;
 
+err_free_comp_eqs:
+	free_comp_eqs(dev);
+
 err_stop_eqs:
 	mlx5_stop_eqs(dev);
 
@@ -793,6 +876,7 @@ static void mlx5_dev_cleanup(struct mlx5_core_dev *dev)
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cleanup_cq_table(dev);
+	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_free_uuars(dev, &priv->uuari);
@@ -1048,6 +1132,10 @@ static int __init init(void)
 	if (err)
 		goto err_health;
 
+#ifdef CONFIG_MLX5_CORE_EN
+	mlx5e_init();
+#endif
+
 	return 0;
 
 err_health:
@@ -1060,6 +1148,9 @@ err_debug:
 
 static void __exit cleanup(void)
 {
+#ifdef CONFIG_MLX5_CORE_EN
+	mlx5e_cleanup();
+#endif
 	pci_unregister_driver(&mlx5_core_driver);
 	mlx5_health_cleanup();
 	destroy_workqueue(mlx5_core_wq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
index d79fd85d1dd5..d5a0c2d61a18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mcg.c
@@ -91,7 +91,7 @@ int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn)
 
 	memset(&in, 0, sizeof(in));
 	memset(&out, 0, sizeof(out));
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DETACH_FROM_MCG);
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DETTACH_FROM_MCG);
 	memcpy(in.gid, mgid, sizeof(*mgid));
 	in.qpn = cpu_to_be32(qpn);
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index a051b906afdf..fc88ecaecb4b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -37,6 +37,10 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 
+#define DRIVER_NAME "mlx5_core"
+#define DRIVER_VERSION "3.0-1"
+#define DRIVER_RELDATE  "January 2015"
+
 extern int mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(dev, format, ...)					\
@@ -65,11 +69,20 @@ enum {
 	MLX5_CMD_TIME, /* print command execution time */
 };
 
+static inline int mlx5_cmd_exec_check_status(struct mlx5_core_dev *dev, u32 *in,
+					     int in_size, u32 *out,
+					     int out_size)
+{
+	mlx5_cmd_exec(dev, in, in_size, out, out_size);
+	return mlx5_cmd_status_to_err((struct mlx5_outbox_hdr *)out);
+}
 
-int mlx5_cmd_query_hca_cap(struct mlx5_core_dev *dev,
-			   struct mlx5_caps *caps);
-int mlx5_cmd_query_adapter(struct mlx5_core_dev *dev);
+int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
+int mlx5_query_board_id(struct mlx5_core_dev *dev);
 int mlx5_cmd_init_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 
+void mlx5e_init(void);
+void mlx5e_cleanup(void);
+
 #endif /* __MLX5_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 49e90f2612d8..70147999f657 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -102,3 +102,229 @@ int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps)
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_set_port_caps);
+
+int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
+			 int ptys_size, int proto_mask, u8 local_port)
+{
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(ptys_reg, in, local_port, local_port);
+	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), ptys,
+				   ptys_size, MLX5_REG_PTYS, 0, 0);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_ptys);
+
+int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
+			      u32 *proto_cap, int proto_mask)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
+	if (err)
+		return err;
+
+	if (proto_mask == MLX5_PTYS_EN)
+		*proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
+	else
+		*proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap);
+
+int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
+				u32 *proto_admin, int proto_mask)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
+	if (err)
+		return err;
+
+	if (proto_mask == MLX5_PTYS_EN)
+		*proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
+	else
+		*proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin);
+
+int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
+				    u8 *link_width_oper, u8 local_port)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_IB, local_port);
+	if (err)
+		return err;
+
+	*link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
+
+int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev,
+			       u8 *proto_oper, int proto_mask,
+			       u8 local_port)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, local_port);
+	if (err)
+		return err;
+
+	if (proto_mask == MLX5_PTYS_EN)
+		*proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
+	else
+		*proto_oper = MLX5_GET(ptys_reg, out, ib_proto_oper);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_proto_oper);
+
+int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin,
+			int proto_mask)
+{
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(ptys_reg, in, local_port, 1);
+	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
+	if (proto_mask == MLX5_PTYS_EN)
+		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+	else
+		MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_PTYS, 0, 1);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_set_port_proto);
+
+int mlx5_set_port_status(struct mlx5_core_dev *dev,
+			 enum mlx5_port_status status)
+{
+	u32 in[MLX5_ST_SZ_DW(paos_reg)];
+	u32 out[MLX5_ST_SZ_DW(paos_reg)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(paos_reg, in, admin_status, status);
+	MLX5_SET(paos_reg, in, ase, 1);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out,
+				    sizeof(out), MLX5_REG_PAOS, 0, 1);
+}
+
+int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status)
+{
+	u32 in[MLX5_ST_SZ_DW(paos_reg)];
+	u32 out[MLX5_ST_SZ_DW(paos_reg)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_PAOS, 0, 0);
+	if (err)
+		return err;
+
+	*status = MLX5_GET(paos_reg, out, oper_status);
+	return err;
+}
+
+static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu,
+				int *max_mtu, int *oper_mtu, u8 port)
+{
+	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
+	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(pmtu_reg, in, local_port, port);
+
+	mlx5_core_access_reg(dev, in, sizeof(in), out,
+			     sizeof(out), MLX5_REG_PMTU, 0, 0);
+
+	if (max_mtu)
+		*max_mtu  = MLX5_GET(pmtu_reg, out, max_mtu);
+	if (oper_mtu)
+		*oper_mtu = MLX5_GET(pmtu_reg, out, oper_mtu);
+	if (admin_mtu)
+		*admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu);
+}
+
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port)
+{
+	u32 in[MLX5_ST_SZ_DW(pmtu_reg)];
+	u32 out[MLX5_ST_SZ_DW(pmtu_reg)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(pmtu_reg, in, admin_mtu, mtu);
+	MLX5_SET(pmtu_reg, in, local_port, port);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out,
+				   sizeof(out), MLX5_REG_PMTU, 0, 1);
+}
+EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
+
+void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu,
+			     u8 port)
+{
+	mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port);
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu);
+
+void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu,
+			      u8 port)
+{
+	mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port);
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_oper_mtu);
+
+static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc,
+				int pvlc_size,  u8 local_port)
+{
+	u32 in[MLX5_ST_SZ_DW(pvlc_reg)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(ptys_reg, in, local_port, local_port);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), pvlc,
+				   pvlc_size, MLX5_REG_PVLC, 0, 0);
+
+	return err;
+}
+
+int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
+			      u8 *vl_hw_cap, u8 local_port)
+{
+	u32 out[MLX5_ST_SZ_DW(pvlc_reg)];
+	int err;
+
+	err = mlx5_query_port_pvlc(dev, out, sizeof(out), local_port);
+	if (err)
+		return err;
+
+	*vl_hw_cap = MLX5_GET(pvlc_reg, out, vl_hw_cap);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_port_vl_hw_cap);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index dc7dbf7e9d98..8b494b562263 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -187,10 +187,17 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 	struct mlx5_destroy_qp_mbox_in din;
 	struct mlx5_destroy_qp_mbox_out dout;
 	int err;
+	void *qpc;
 
 	memset(&out, 0, sizeof(out));
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_QP);
 
+	if (dev->issi) {
+		qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+		/* 0xffffff means we ask to work with cqe version 0 */
+		MLX5_SET(qpc, qpc, user_index, 0xffffff);
+	}
+
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
 	if (err) {
 		mlx5_core_warn(dev, "ret %d\n", err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
index f9d25dcd03c1..c48f504ccbeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/srq.h>
 #include <rdma/ib_verbs.h>
 #include "mlx5_core.h"
+#include "transobj.h"
 
 void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
 {
@@ -62,6 +63,74 @@ void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
 		complete(&srq->free);
 }
 
+static int get_pas_size(void *srqc)
+{
+	u32 log_page_size = MLX5_GET(srqc, srqc, log_page_size) + 12;
+	u32 log_srq_size  = MLX5_GET(srqc, srqc, log_srq_size);
+	u32 log_rq_stride = MLX5_GET(srqc, srqc, log_rq_stride);
+	u32 page_offset   = MLX5_GET(srqc, srqc, page_offset);
+	u32 po_quanta	  = 1 << (log_page_size - 6);
+	u32 rq_sz	  = 1 << (log_srq_size + 4 + log_rq_stride);
+	u32 page_size	  = 1 << log_page_size;
+	u32 rq_sz_po      = rq_sz + (page_offset * po_quanta);
+	u32 rq_num_pas	  = (rq_sz_po + page_size - 1) / page_size;
+
+	return rq_num_pas * sizeof(u64);
+}
+
+static void rmpc_srqc_reformat(void *srqc, void *rmpc, bool srqc_to_rmpc)
+{
+	void *wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
+
+	if (srqc_to_rmpc) {
+		switch (MLX5_GET(srqc, srqc, state)) {
+		case MLX5_SRQC_STATE_GOOD:
+			MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+			break;
+		case MLX5_SRQC_STATE_ERROR:
+			MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_ERR);
+			break;
+		default:
+			pr_warn("%s: %d: Unknown srq state = 0x%x\n", __func__,
+				__LINE__, MLX5_GET(srqc, srqc, state));
+			MLX5_SET(rmpc, rmpc, state, MLX5_GET(srqc, srqc, state));
+		}
+
+		MLX5_SET(wq,   wq, wq_signature,  MLX5_GET(srqc,  srqc, wq_signature));
+		MLX5_SET(wq,   wq, log_wq_pg_sz,  MLX5_GET(srqc,  srqc, log_page_size));
+		MLX5_SET(wq,   wq, log_wq_stride, MLX5_GET(srqc,  srqc, log_rq_stride) + 4);
+		MLX5_SET(wq,   wq, log_wq_sz,     MLX5_GET(srqc,  srqc, log_srq_size));
+		MLX5_SET(wq,   wq, page_offset,   MLX5_GET(srqc,  srqc, page_offset));
+		MLX5_SET(wq,   wq, lwm,           MLX5_GET(srqc,  srqc, lwm));
+		MLX5_SET(wq,   wq, pd,            MLX5_GET(srqc,  srqc, pd));
+		MLX5_SET64(wq, wq, dbr_addr, MLX5_GET64(srqc,	  srqc, dbr_addr));
+	} else {
+		switch (MLX5_GET(rmpc, rmpc, state)) {
+		case MLX5_RMPC_STATE_RDY:
+			MLX5_SET(srqc, srqc, state, MLX5_SRQC_STATE_GOOD);
+			break;
+		case MLX5_RMPC_STATE_ERR:
+			MLX5_SET(srqc, srqc, state, MLX5_SRQC_STATE_ERROR);
+			break;
+		default:
+			pr_warn("%s: %d: Unknown rmp state = 0x%x\n",
+				__func__, __LINE__,
+				MLX5_GET(rmpc, rmpc, state));
+			MLX5_SET(srqc, srqc, state,
+				 MLX5_GET(rmpc, rmpc, state));
+		}
+
+		MLX5_SET(srqc,   srqc, wq_signature,   MLX5_GET(wq,   wq, wq_signature));
+		MLX5_SET(srqc,   srqc, log_page_size,  MLX5_GET(wq,   wq, log_wq_pg_sz));
+		MLX5_SET(srqc,   srqc, log_rq_stride,  MLX5_GET(wq,   wq, log_wq_stride) - 4);
+		MLX5_SET(srqc,   srqc, log_srq_size,   MLX5_GET(wq,   wq, log_wq_sz));
+		MLX5_SET(srqc,   srqc, page_offset,    MLX5_GET(wq,   wq, page_offset));
+		MLX5_SET(srqc,   srqc, lwm,	       MLX5_GET(wq,   wq, lwm));
+		MLX5_SET(srqc,   srqc, pd,	       MLX5_GET(wq,   wq, pd));
+		MLX5_SET64(srqc, srqc, dbr_addr,       MLX5_GET64(wq, wq, dbr_addr));
+	}
+}
+
 struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
 {
 	struct mlx5_srq_table *table = &dev->priv.srq_table;
@@ -79,26 +148,311 @@ struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
 }
 EXPORT_SYMBOL(mlx5_core_get_srq);
 
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_create_srq_mbox_in *in, int inlen)
+static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_create_srq_mbox_in *in, int inlen)
 {
 	struct mlx5_create_srq_mbox_out out;
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_destroy_srq_mbox_in din;
-	struct mlx5_destroy_srq_mbox_out dout;
 	int err;
 
 	memset(&out, 0, sizeof(out));
+
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_SRQ);
-	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
-	if (err)
-		return err;
 
-	if (out.hdr.status)
-		return mlx5_cmd_status_to_err(&out.hdr);
+	err = mlx5_cmd_exec_check_status(dev, (u32 *)in, inlen, (u32 *)(&out),
+					 sizeof(out));
 
 	srq->srqn = be32_to_cpu(out.srqn) & 0xffffff;
 
+	return err;
+}
+
+static int destroy_srq_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq)
+{
+	struct mlx5_destroy_srq_mbox_in in;
+	struct mlx5_destroy_srq_mbox_out out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_SRQ);
+	in.srqn = cpu_to_be32(srq->srqn);
+
+	return mlx5_cmd_exec_check_status(dev, (u32 *)(&in), sizeof(in),
+					  (u32 *)(&out), sizeof(out));
+}
+
+static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+		       u16 lwm, int is_srq)
+{
+	struct mlx5_arm_srq_mbox_in	in;
+	struct mlx5_arm_srq_mbox_out	out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_ARM_RQ);
+	in.hdr.opmod = cpu_to_be16(!!is_srq);
+	in.srqn = cpu_to_be32(srq->srqn);
+	in.lwm = cpu_to_be16(lwm);
+
+	return mlx5_cmd_exec_check_status(dev, (u32 *)(&in),
+					  sizeof(in), (u32 *)(&out),
+					  sizeof(out));
+}
+
+static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_query_srq_mbox_out *out)
+{
+	struct mlx5_query_srq_mbox_in in;
+
+	memset(&in, 0, sizeof(in));
+
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SRQ);
+	in.srqn = cpu_to_be32(srq->srqn);
+
+	return mlx5_cmd_exec_check_status(dev, (u32 *)(&in), sizeof(in),
+					  (u32 *)out, sizeof(*out));
+}
+
+static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			      struct mlx5_core_srq *srq,
+			      struct mlx5_create_srq_mbox_in *in,
+			      int srq_inlen)
+{
+	u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
+	void *create_in;
+	void *srqc;
+	void *xrc_srqc;
+	void *pas;
+	int pas_size;
+	int inlen;
+	int err;
+
+	srqc	  = MLX5_ADDR_OF(create_srq_in, in, srq_context_entry);
+	pas_size  = get_pas_size(srqc);
+	inlen	  = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
+	create_in = mlx5_vzalloc(inlen);
+	if (!create_in)
+		return -ENOMEM;
+
+	xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
+				xrc_srq_context_entry);
+	pas	 = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
+
+	memcpy(xrc_srqc, srqc, MLX5_ST_SZ_BYTES(srqc));
+	memcpy(pas, in->pas, pas_size);
+	/* 0xffffff means we ask to work with cqe version 0 */
+	MLX5_SET(xrc_srqc,	    xrc_srqc,  user_index, 0xffffff);
+	MLX5_SET(create_xrc_srq_in, create_in, opcode,
+		 MLX5_CMD_OP_CREATE_XRC_SRQ);
+
+	memset(create_out, 0, sizeof(create_out));
+	err = mlx5_cmd_exec_check_status(dev, create_in, inlen, create_out,
+					 sizeof(create_out));
+	if (err)
+		goto out;
+
+	srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
+out:
+	kvfree(create_in);
+	return err;
+}
+
+static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			       struct mlx5_core_srq *srq)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)];
+	u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)];
+
+	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
+	memset(xrcsrq_out, 0, sizeof(xrcsrq_out));
+
+	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
+		 MLX5_CMD_OP_DESTROY_XRC_SRQ);
+	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+
+	return mlx5_cmd_exec_check_status(dev, xrcsrq_in, sizeof(xrcsrq_in),
+					  xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq, u16 lwm)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)];
+	u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)];
+
+	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
+	memset(xrcsrq_out, 0, sizeof(xrcsrq_out));
+
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod,   MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm,      lwm);
+
+	return  mlx5_cmd_exec_check_status(dev, xrcsrq_in, sizeof(xrcsrq_in),
+					   xrcsrq_out, sizeof(xrcsrq_out));
+}
+
+static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
+			     struct mlx5_core_srq *srq,
+			     struct mlx5_query_srq_mbox_out *out)
+{
+	u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
+	u32 *xrcsrq_out;
+	void *srqc;
+	void *xrc_srqc;
+	int err;
+
+	xrcsrq_out = mlx5_vzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+	if (!xrcsrq_out)
+		return -ENOMEM;
+	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
+
+	MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
+		 MLX5_CMD_OP_QUERY_XRC_SRQ);
+	MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
+	err =  mlx5_cmd_exec_check_status(dev, xrcsrq_in, sizeof(xrcsrq_in),
+					  xrcsrq_out,
+					  MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+	if (err)
+		goto out;
+
+	xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
+				xrc_srq_context_entry);
+	srqc = MLX5_ADDR_OF(query_srq_out, out, srq_context_entry);
+	memcpy(srqc, xrc_srqc, MLX5_ST_SZ_BYTES(srqc));
+
+out:
+	kvfree(xrcsrq_out);
+	return err;
+}
+
+static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			  struct mlx5_create_srq_mbox_in *in, int srq_inlen)
+{
+	void *create_in;
+	void *rmpc;
+	void *srqc;
+	int pas_size;
+	int inlen;
+	int err;
+
+	srqc = MLX5_ADDR_OF(create_srq_in, in, srq_context_entry);
+	pas_size = get_pas_size(srqc);
+	inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
+	create_in = mlx5_vzalloc(inlen);
+	if (!create_in)
+		return -ENOMEM;
+
+	rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
+
+	memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
+	rmpc_srqc_reformat(srqc, rmpc, true);
+
+	err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
+
+	kvfree(create_in);
+	return err;
+}
+
+static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
+			   struct mlx5_core_srq *srq)
+{
+	return mlx5_core_destroy_rmp(dev, srq->srqn);
+}
+
+static int arm_rmp_cmd(struct mlx5_core_dev *dev,
+		       struct mlx5_core_srq *srq,
+		       u16 lwm)
+{
+	void *in;
+	void *rmpc;
+	void *wq;
+	void *bitmask;
+	int err;
+
+	in = mlx5_vzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in));
+	if (!in)
+		return -ENOMEM;
+
+	rmpc =	  MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
+	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
+	wq   =	  MLX5_ADDR_OF(rmpc,	        rmpc, wq);
+
+	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
+	MLX5_SET(modify_rmp_in, in,	 rmpn,      srq->srqn);
+	MLX5_SET(wq,		wq,	 lwm,	    lwm);
+	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
+	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
+
+	err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
+
+	kvfree(in);
+	return err;
+}
+
+static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_query_srq_mbox_out *out)
+{
+	u32 *rmp_out;
+	void *rmpc;
+	void *srqc;
+	int err;
+
+	rmp_out =  mlx5_vzalloc(MLX5_ST_SZ_BYTES(query_rmp_out));
+	if (!rmp_out)
+		return -ENOMEM;
+
+	err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
+	if (err)
+		goto out;
+
+	srqc = MLX5_ADDR_OF(query_srq_out, out,	    srq_context_entry);
+	rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
+	rmpc_srqc_reformat(srqc, rmpc, false);
+
+out:
+	kvfree(rmp_out);
+	return err;
+}
+
+static int create_srq_split(struct mlx5_core_dev *dev,
+			    struct mlx5_core_srq *srq,
+			    struct mlx5_create_srq_mbox_in *in,
+			    int inlen, int is_xrc)
+{
+	if (!dev->issi)
+		return create_srq_cmd(dev, srq, in, inlen);
+	else if (srq->common.res == MLX5_RES_XSRQ)
+		return create_xrc_srq_cmd(dev, srq, in, inlen);
+	else
+		return create_rmp_cmd(dev, srq, in, inlen);
+}
+
+static int destroy_srq_split(struct mlx5_core_dev *dev,
+			     struct mlx5_core_srq *srq)
+{
+	if (!dev->issi)
+		return destroy_srq_cmd(dev, srq);
+	else if (srq->common.res == MLX5_RES_XSRQ)
+		return destroy_xrc_srq_cmd(dev, srq);
+	else
+		return destroy_rmp_cmd(dev, srq);
+}
+
+int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
+			 struct mlx5_create_srq_mbox_in *in, int inlen,
+			 int is_xrc)
+{
+	int err;
+	struct mlx5_srq_table *table = &dev->priv.srq_table;
+
+	srq->common.res = is_xrc ? MLX5_RES_XSRQ : MLX5_RES_SRQ;
+
+	err = create_srq_split(dev, srq, in, inlen, is_xrc);
+	if (err)
+		return err;
+
 	atomic_set(&srq->refcount, 1);
 	init_completion(&srq->free);
 
@@ -107,25 +461,20 @@ int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 	spin_unlock_irq(&table->lock);
 	if (err) {
 		mlx5_core_warn(dev, "err %d, srqn 0x%x\n", err, srq->srqn);
-		goto err_cmd;
+		goto err_destroy_srq_split;
 	}
 
 	return 0;
 
-err_cmd:
-	memset(&din, 0, sizeof(din));
-	memset(&dout, 0, sizeof(dout));
-	din.srqn = cpu_to_be32(srq->srqn);
-	din.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_SRQ);
-	mlx5_cmd_exec(dev, &din, sizeof(din), &dout, sizeof(dout));
+err_destroy_srq_split:
+	destroy_srq_split(dev, srq);
+
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_create_srq);
 
 int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
 {
-	struct mlx5_destroy_srq_mbox_in in;
-	struct mlx5_destroy_srq_mbox_out out;
 	struct mlx5_srq_table *table = &dev->priv.srq_table;
 	struct mlx5_core_srq *tmp;
 	int err;
@@ -142,17 +491,10 @@ int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
 		return -EINVAL;
 	}
 
-	memset(&in, 0, sizeof(in));
-	memset(&out, 0, sizeof(out));
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_SRQ);
-	in.srqn = cpu_to_be32(srq->srqn);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	err = destroy_srq_split(dev, srq);
 	if (err)
 		return err;
 
-	if (out.hdr.status)
-		return mlx5_cmd_status_to_err(&out.hdr);
-
 	if (atomic_dec_and_test(&srq->refcount))
 		complete(&srq->free);
 	wait_for_completion(&srq->free);
@@ -164,48 +506,24 @@ EXPORT_SYMBOL(mlx5_core_destroy_srq);
 int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_query_srq_mbox_out *out)
 {
-	struct mlx5_query_srq_mbox_in in;
-	int err;
-
-	memset(&in, 0, sizeof(in));
-	memset(out, 0, sizeof(*out));
-
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SRQ);
-	in.srqn = cpu_to_be32(srq->srqn);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, sizeof(*out));
-	if (err)
-		return err;
-
-	if (out->hdr.status)
-		return mlx5_cmd_status_to_err(&out->hdr);
-
-	return err;
+	if (!dev->issi)
+		return query_srq_cmd(dev, srq, out);
+	else if (srq->common.res == MLX5_RES_XSRQ)
+		return query_xrc_srq_cmd(dev, srq, out);
+	else
+		return query_rmp_cmd(dev, srq, out);
 }
 EXPORT_SYMBOL(mlx5_core_query_srq);
 
 int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		      u16 lwm, int is_srq)
 {
-	struct mlx5_arm_srq_mbox_in	in;
-	struct mlx5_arm_srq_mbox_out	out;
-	int err;
-
-	memset(&in, 0, sizeof(in));
-	memset(&out, 0, sizeof(out));
-
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_ARM_RQ);
-	in.hdr.opmod = cpu_to_be16(!!is_srq);
-	in.srqn = cpu_to_be32(srq->srqn);
-	in.lwm = cpu_to_be16(lwm);
-
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
-	if (err)
-		return err;
-
-	if (out.hdr.status)
-		return mlx5_cmd_status_to_err(&out.hdr);
-
-	return err;
+	if (!dev->issi)
+		return arm_srq_cmd(dev, srq, lwm, is_srq);
+	else if (srq->common.res == MLX5_RES_XSRQ)
+		return arm_xrc_srq_cmd(dev, srq, lwm);
+	else
+		return arm_rmp_cmd(dev, srq, lwm);
 }
 EXPORT_SYMBOL(mlx5_core_arm_srq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
new file mode 100644
index 000000000000..8d98b03026d5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -0,0 +1,360 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "transobj.h"
+
+int mlx5_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn)
+{
+	u32 in[MLX5_ST_SZ_DW(alloc_transport_domain_in)];
+	u32 out[MLX5_ST_SZ_DW(alloc_transport_domain_out)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+	MLX5_SET(alloc_transport_domain_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_TRANSPORT_DOMAIN);
+
+	err = mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+	if (!err)
+		*tdn = MLX5_GET(alloc_transport_domain_out, out,
+				transport_domain);
+
+	return err;
+}
+
+void mlx5_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn)
+{
+	u32 in[MLX5_ST_SZ_DW(dealloc_transport_domain_in)];
+	u32 out[MLX5_ST_SZ_DW(dealloc_transport_domain_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+	MLX5_SET(dealloc_transport_domain_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_TRANSPORT_DOMAIN);
+	MLX5_SET(dealloc_transport_domain_in, in, transport_domain, tdn);
+
+	mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *rqn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_rq_out)];
+	int err;
+
+	MLX5_SET(create_rq_in, in, opcode, MLX5_CMD_OP_CREATE_RQ);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*rqn = MLX5_GET(create_rq_out, out, rqn);
+
+	return err;
+}
+
+int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_rq_out)];
+
+	MLX5_SET(modify_rq_in, in, rqn, rqn);
+	MLX5_SET(modify_rq_in, in, opcode, MLX5_CMD_OP_MODIFY_RQ);
+
+	memset(out, 0, sizeof(out));
+	return mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+}
+
+void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rq_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_rq_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ);
+	MLX5_SET(destroy_rq_in, in, rqn, rqn);
+
+	mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen, u32 *sqn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_sq_out)];
+	int err;
+
+	MLX5_SET(create_sq_in, in, opcode, MLX5_CMD_OP_CREATE_SQ);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*sqn = MLX5_GET(create_sq_out, out, sqn);
+
+	return err;
+}
+
+int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_sq_out)];
+
+	MLX5_SET(modify_sq_in, in, sqn, sqn);
+	MLX5_SET(modify_sq_in, in, opcode, MLX5_CMD_OP_MODIFY_SQ);
+
+	memset(out, 0, sizeof(out));
+	return mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+}
+
+void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_sq_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_sq_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ);
+	MLX5_SET(destroy_sq_in, in, sqn, sqn);
+
+	mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *tirn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)];
+	int err;
+
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*tirn = MLX5_GET(create_tir_out, out, tirn);
+
+	return err;
+}
+
+void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_tir_out)];
+	u32 out[MLX5_ST_SZ_DW(destroy_tir_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_tir_in, in, opcode, MLX5_CMD_OP_DESTROY_TIR);
+	MLX5_SET(destroy_tir_in, in, tirn, tirn);
+
+	mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *tisn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_tis_out)];
+	int err;
+
+	MLX5_SET(create_tis_in, in, opcode, MLX5_CMD_OP_CREATE_TIS);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*tisn = MLX5_GET(create_tis_out, out, tisn);
+
+	return err;
+}
+
+void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_tis_out)];
+	u32 out[MLX5_ST_SZ_DW(destroy_tis_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_tis_in, in, opcode, MLX5_CMD_OP_DESTROY_TIS);
+	MLX5_SET(destroy_tis_in, in, tisn, tisn);
+
+	mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *rmpn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_rmp_out)];
+	int err;
+
+	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
+
+	return err;
+}
+
+int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)];
+
+	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
+
+	memset(out, 0, sizeof(out));
+	return mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+}
+
+int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)];
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
+	MLX5_SET(destroy_rmp_in, in, rmpn, rmpn);
+
+	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
+					  sizeof(out));
+}
+
+int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_rmp_in)];
+	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
+	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
+
+	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm)
+{
+	void *in;
+	void *rmpc;
+	void *wq;
+	void *bitmask;
+	int  err;
+
+	in = mlx5_vzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in));
+	if (!in)
+		return -ENOMEM;
+
+	rmpc    = MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
+	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
+	wq      = MLX5_ADDR_OF(rmpc,	        rmpc, wq);
+
+	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
+	MLX5_SET(modify_rmp_in, in,	 rmpn,      rmpn);
+	MLX5_SET(wq,		wq,	 lwm,	    lwm);
+	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
+	MLX5_SET(rmpc,		rmpc,	 state,	    MLX5_RMPC_STATE_RDY);
+
+	err =  mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
+
+	kvfree(in);
+
+	return err;
+}
+
+int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			  u32 *xsrqn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
+	int err;
+
+	MLX5_SET(create_xrc_srq_in, in, opcode,     MLX5_CMD_OP_CREATE_XRC_SRQ);
+
+	memset(out, 0, sizeof(out));
+	err = mlx5_cmd_exec_check_status(dev, in, inlen, out, sizeof(out));
+	if (!err)
+		*xsrqn = MLX5_GET(create_xrc_srq_out, out, xrc_srqn);
+
+	return err;
+}
+
+int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)];
+	u32 out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+	MLX5_SET(destroy_xrc_srq_in, in, opcode,   MLX5_CMD_OP_DESTROY_XRC_SRQ);
+	MLX5_SET(destroy_xrc_srq_in, in, xrc_srqn, xsrqn);
+
+	return mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
+					  sizeof(out));
+}
+
+int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u32 *out)
+{
+	u32 in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
+	void *srqc;
+	void *xrc_srqc;
+	int err;
+
+	memset(in, 0, sizeof(in));
+	MLX5_SET(query_xrc_srq_in, in, opcode,   MLX5_CMD_OP_QUERY_XRC_SRQ);
+	MLX5_SET(query_xrc_srq_in, in, xrc_srqn, xsrqn);
+
+	err =  mlx5_cmd_exec_check_status(dev, in, sizeof(in),
+					  out,
+					  MLX5_ST_SZ_BYTES(query_xrc_srq_out));
+	if (!err) {
+		xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, out,
+					xrc_srq_context_entry);
+		srqc = MLX5_ADDR_OF(query_srq_out, out, srq_context_entry);
+		memcpy(srqc, xrc_srqc, MLX5_ST_SZ_BYTES(srqc));
+	}
+
+	return err;
+}
+
+int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
+{
+	u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)];
+	u32 out[MLX5_ST_SZ_DW(arm_xrc_srq_out)];
+
+	memset(in, 0, sizeof(in));
+	memset(out, 0, sizeof(out));
+
+	MLX5_SET(arm_xrc_srq_in, in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
+	MLX5_SET(arm_xrc_srq_in, in, xrc_srqn, xsrqn);
+	MLX5_SET(arm_xrc_srq_in, in, lwm,      lwm);
+	MLX5_SET(arm_xrc_srq_in, in, op_mod,
+		 MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
+
+	return  mlx5_cmd_exec_check_status(dev, in, sizeof(in), out,
+					   sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.h b/drivers/net/ethernet/mellanox/mlx5/core/transobj.h
new file mode 100644
index 000000000000..f9ef244710d5
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __TRANSOBJ_H__
+#define __TRANSOBJ_H__
+
+int mlx5_alloc_transport_domain(struct mlx5_core_dev *dev, u32 *tdn);
+void mlx5_dealloc_transport_domain(struct mlx5_core_dev *dev, u32 tdn);
+int mlx5_core_create_rq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			u32 *rqn);
+int mlx5_core_modify_rq(struct mlx5_core_dev *dev, u32 rqn, u32 *in, int inlen);
+void mlx5_core_destroy_rq(struct mlx5_core_dev *dev, u32 rqn);
+int mlx5_core_create_sq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			u32 *sqn);
+int mlx5_core_modify_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *in, int inlen);
+void mlx5_core_destroy_sq(struct mlx5_core_dev *dev, u32 sqn);
+int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *tirn);
+void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn);
+int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *tisn);
+void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn);
+int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			 u32 *rmpn);
+int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen);
+int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn);
+int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
+int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
+int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
+			  u32 *rmpn);
+int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 rmpn);
+int mlx5_core_query_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u32 *out);
+int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm);
+
+#endif /* __TRANSOBJ_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 5a89bb1d678a..9ef85873ceea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -175,12 +175,13 @@ int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari)
 	for (i = 0; i < tot_uuars; i++) {
 		bf = &uuari->bfs[i];
 
-		bf->buf_size = dev->caps.gen.bf_reg_size / 2;
+		bf->buf_size = (1 << MLX5_CAP_GEN(dev, log_bf_reg_size)) / 2;
 		bf->uar = &uuari->uars[i / MLX5_BF_REGS_PER_PAGE];
 		bf->regreg = uuari->uars[i / MLX5_BF_REGS_PER_PAGE].map;
 		bf->reg = NULL; /* Add WC support */
-		bf->offset = (i % MLX5_BF_REGS_PER_PAGE) * dev->caps.gen.bf_reg_size +
-			MLX5_BF_OFFSET;
+		bf->offset = (i % MLX5_BF_REGS_PER_PAGE) *
+			     (1 << MLX5_CAP_GEN(dev, log_bf_reg_size)) +
+			     MLX5_BF_OFFSET;
 		bf->need_lock = need_uuar_lock(i);
 		spin_lock_init(&bf->lock);
 		spin_lock_init(&bf->lock32);
@@ -223,3 +224,40 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari)
 
 	return 0;
 }
+
+int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
+{
+	phys_addr_t pfn;
+	phys_addr_t uar_bar_start;
+	int err;
+
+	err = mlx5_cmd_alloc_uar(mdev, &uar->index);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_cmd_alloc_uar() failed, %d\n", err);
+		return err;
+	}
+
+	uar_bar_start = pci_resource_start(mdev->pdev, 0);
+	pfn           = (uar_bar_start >> PAGE_SHIFT) + uar->index;
+	uar->map      = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+	if (!uar->map) {
+		mlx5_core_warn(mdev, "ioremap() failed, %d\n", err);
+		err = -ENOMEM;
+		goto err_free_uar;
+	}
+
+	return 0;
+
+err_free_uar:
+	mlx5_cmd_free_uar(mdev, uar->index);
+
+	return err;
+}
+EXPORT_SYMBOL(mlx5_alloc_map_uar);
+
+void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar)
+{
+	iounmap(uar->map);
+	mlx5_cmd_free_uar(mdev, uar->index);
+}
+EXPORT_SYMBOL(mlx5_unmap_free_uar);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
new file mode 100644
index 000000000000..b94177ebcf3a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -0,0 +1,345 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/export.h>
+#include <linux/etherdevice.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
+#include "mlx5_core.h"
+
+u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod)
+{
+	u32 in[MLX5_ST_SZ_DW(query_vport_state_in)];
+	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)];
+	int err;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(query_vport_state_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_VPORT_STATE);
+	MLX5_SET(query_vport_state_in, in, op_mod, opmod);
+
+	err = mlx5_cmd_exec_check_status(mdev, in, sizeof(in), out,
+					 sizeof(out));
+	if (err)
+		mlx5_core_warn(mdev, "MLX5_CMD_OP_QUERY_VPORT_STATE failed\n");
+
+	return MLX5_GET(query_vport_state_out, out, state);
+}
+EXPORT_SYMBOL(mlx5_query_vport_state);
+
+void mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr)
+{
+	u32  in[MLX5_ST_SZ_DW(query_nic_vport_context_in)];
+	u32 *out;
+	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u8 *out_addr;
+
+	out = mlx5_vzalloc(outlen);
+	if (!out)
+		return;
+
+	out_addr = MLX5_ADDR_OF(query_nic_vport_context_out, out,
+				nic_vport_context.permanent_address);
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(query_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
+
+	memset(out, 0, outlen);
+	mlx5_cmd_exec_check_status(mdev, in, sizeof(in), out, outlen);
+
+	ether_addr_copy(addr, &out_addr[2]);
+
+	kvfree(out);
+}
+EXPORT_SYMBOL(mlx5_query_nic_vport_mac_address);
+
+int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport,
+			     u8 port_num, u16  vf_num, u16 gid_index,
+			     union ib_gid *gid)
+{
+	int in_sz = MLX5_ST_SZ_BYTES(query_hca_vport_gid_in);
+	int out_sz = MLX5_ST_SZ_BYTES(query_hca_vport_gid_out);
+	int is_group_manager;
+	void *out = NULL;
+	void *in = NULL;
+	union ib_gid *tmp;
+	int tbsz;
+	int nout;
+	int err;
+
+	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
+	tbsz = mlx5_get_gid_table_len(MLX5_CAP_GEN(dev, gid_table_size));
+	mlx5_core_dbg(dev, "vf_num %d, index %d, gid_table_size %d\n",
+		      vf_num, gid_index, tbsz);
+
+	if (gid_index > tbsz && gid_index != 0xffff)
+		return -EINVAL;
+
+	if (gid_index == 0xffff)
+		nout = tbsz;
+	else
+		nout = 1;
+
+	out_sz += nout * sizeof(*gid);
+
+	in = kzalloc(in_sz, GFP_KERNEL);
+	out = kzalloc(out_sz, GFP_KERNEL);
+	if (!in || !out) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	MLX5_SET(query_hca_vport_gid_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_VPORT_GID);
+	if (other_vport) {
+		if (is_group_manager) {
+			MLX5_SET(query_hca_vport_gid_in, in, vport_number, vf_num);
+			MLX5_SET(query_hca_vport_gid_in, in, other_vport, 1);
+		} else {
+			err = -EPERM;
+			goto out;
+		}
+	}
+	MLX5_SET(query_hca_vport_gid_in, in, gid_index, gid_index);
+
+	if (MLX5_CAP_GEN(dev, num_ports) == 2)
+		MLX5_SET(query_hca_vport_gid_in, in, port_num, port_num);
+
+	err = mlx5_cmd_exec(dev, in, in_sz, out, out_sz);
+	if (err)
+		goto out;
+
+	err = mlx5_cmd_status_to_err_v2(out);
+	if (err)
+		goto out;
+
+	tmp = out + MLX5_ST_SZ_BYTES(query_hca_vport_gid_out);
+	gid->global.subnet_prefix = tmp->global.subnet_prefix;
+	gid->global.interface_id = tmp->global.interface_id;
+
+out:
+	kfree(in);
+	kfree(out);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_gid);
+
+int mlx5_query_hca_vport_pkey(struct mlx5_core_dev *dev, u8 other_vport,
+			      u8 port_num, u16 vf_num, u16 pkey_index,
+			      u16 *pkey)
+{
+	int in_sz = MLX5_ST_SZ_BYTES(query_hca_vport_pkey_in);
+	int out_sz = MLX5_ST_SZ_BYTES(query_hca_vport_pkey_out);
+	int is_group_manager;
+	void *out = NULL;
+	void *in = NULL;
+	void *pkarr;
+	int nout;
+	int tbsz;
+	int err;
+	int i;
+
+	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
+
+	tbsz = mlx5_to_sw_pkey_sz(MLX5_CAP_GEN(dev, pkey_table_size));
+	if (pkey_index > tbsz && pkey_index != 0xffff)
+		return -EINVAL;
+
+	if (pkey_index == 0xffff)
+		nout = tbsz;
+	else
+		nout = 1;
+
+	out_sz += nout * MLX5_ST_SZ_BYTES(pkey);
+
+	in = kzalloc(in_sz, GFP_KERNEL);
+	out = kzalloc(out_sz, GFP_KERNEL);
+	if (!in || !out) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	MLX5_SET(query_hca_vport_pkey_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_VPORT_PKEY);
+	if (other_vport) {
+		if (is_group_manager) {
+			MLX5_SET(query_hca_vport_pkey_in, in, vport_number, vf_num);
+			MLX5_SET(query_hca_vport_pkey_in, in, other_vport, 1);
+		} else {
+			err = -EPERM;
+			goto out;
+		}
+	}
+	MLX5_SET(query_hca_vport_pkey_in, in, pkey_index, pkey_index);
+
+	if (MLX5_CAP_GEN(dev, num_ports) == 2)
+		MLX5_SET(query_hca_vport_pkey_in, in, port_num, port_num);
+
+	err = mlx5_cmd_exec(dev, in, in_sz, out, out_sz);
+	if (err)
+		goto out;
+
+	err = mlx5_cmd_status_to_err_v2(out);
+	if (err)
+		goto out;
+
+	pkarr = MLX5_ADDR_OF(query_hca_vport_pkey_out, out, pkey);
+	for (i = 0; i < nout; i++, pkey++, pkarr += MLX5_ST_SZ_BYTES(pkey))
+		*pkey = MLX5_GET_PR(pkey, pkarr, pkey);
+
+out:
+	kfree(in);
+	kfree(out);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_pkey);
+
+int mlx5_query_hca_vport_context(struct mlx5_core_dev *dev,
+				 u8 other_vport, u8 port_num,
+				 u16 vf_num,
+				 struct mlx5_hca_vport_context *rep)
+{
+	int out_sz = MLX5_ST_SZ_BYTES(query_hca_vport_context_out);
+	int in[MLX5_ST_SZ_DW(query_hca_vport_context_in)];
+	int is_group_manager;
+	void *out;
+	void *ctx;
+	int err;
+
+	is_group_manager = MLX5_CAP_GEN(dev, vport_group_manager);
+
+	memset(in, 0, sizeof(in));
+	out = kzalloc(out_sz, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	MLX5_SET(query_hca_vport_context_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_VPORT_CONTEXT);
+
+	if (other_vport) {
+		if (is_group_manager) {
+			MLX5_SET(query_hca_vport_context_in, in, other_vport, 1);
+			MLX5_SET(query_hca_vport_context_in, in, vport_number, vf_num);
+		} else {
+			err = -EPERM;
+			goto ex;
+		}
+	}
+
+	if (MLX5_CAP_GEN(dev, num_ports) == 2)
+		MLX5_SET(query_hca_vport_context_in, in, port_num, port_num);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out,  out_sz);
+	if (err)
+		goto ex;
+	err = mlx5_cmd_status_to_err_v2(out);
+	if (err)
+		goto ex;
+
+	ctx = MLX5_ADDR_OF(query_hca_vport_context_out, out, hca_vport_context);
+	rep->field_select = MLX5_GET_PR(hca_vport_context, ctx, field_select);
+	rep->sm_virt_aware = MLX5_GET_PR(hca_vport_context, ctx, sm_virt_aware);
+	rep->has_smi = MLX5_GET_PR(hca_vport_context, ctx, has_smi);
+	rep->has_raw = MLX5_GET_PR(hca_vport_context, ctx, has_raw);
+	rep->policy = MLX5_GET_PR(hca_vport_context, ctx, vport_state_policy);
+	rep->phys_state = MLX5_GET_PR(hca_vport_context, ctx,
+				      port_physical_state);
+	rep->vport_state = MLX5_GET_PR(hca_vport_context, ctx, vport_state);
+	rep->port_physical_state = MLX5_GET_PR(hca_vport_context, ctx,
+					       port_physical_state);
+	rep->port_guid = MLX5_GET64_PR(hca_vport_context, ctx, port_guid);
+	rep->node_guid = MLX5_GET64_PR(hca_vport_context, ctx, node_guid);
+	rep->cap_mask1 = MLX5_GET_PR(hca_vport_context, ctx, cap_mask1);
+	rep->cap_mask1_perm = MLX5_GET_PR(hca_vport_context, ctx,
+					  cap_mask1_field_select);
+	rep->cap_mask2 = MLX5_GET_PR(hca_vport_context, ctx, cap_mask2);
+	rep->cap_mask2_perm = MLX5_GET_PR(hca_vport_context, ctx,
+					  cap_mask2_field_select);
+	rep->lid = MLX5_GET_PR(hca_vport_context, ctx, lid);
+	rep->init_type_reply = MLX5_GET_PR(hca_vport_context, ctx,
+					   init_type_reply);
+	rep->lmc = MLX5_GET_PR(hca_vport_context, ctx, lmc);
+	rep->subnet_timeout = MLX5_GET_PR(hca_vport_context, ctx,
+					  subnet_timeout);
+	rep->sm_lid = MLX5_GET_PR(hca_vport_context, ctx, sm_lid);
+	rep->sm_sl = MLX5_GET_PR(hca_vport_context, ctx, sm_sl);
+	rep->qkey_violation_counter = MLX5_GET_PR(hca_vport_context, ctx,
+						  qkey_violation_counter);
+	rep->pkey_violation_counter = MLX5_GET_PR(hca_vport_context, ctx,
+						  pkey_violation_counter);
+	rep->grh_required = MLX5_GET_PR(hca_vport_context, ctx, grh_required);
+	rep->sys_image_guid = MLX5_GET64_PR(hca_vport_context, ctx,
+					    system_image_guid);
+
+ex:
+	kfree(out);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_context);
+
+int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev,
+					   u64 *sys_image_guid)
+{
+	struct mlx5_hca_vport_context *rep;
+	int err;
+
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	err = mlx5_query_hca_vport_context(dev, 0, 1, 0, rep);
+	if (!err)
+		*sys_image_guid = rep->sys_image_guid;
+
+	kfree(rep);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_system_image_guid);
+
+int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
+				   u64 *node_guid)
+{
+	struct mlx5_hca_vport_context *rep;
+	int err;
+
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	err = mlx5_query_hca_vport_context(dev, 0, 1, 0, rep);
+	if (!err)
+		*node_guid = rep->node_guid;
+
+	kfree(rep);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
new file mode 100644
index 000000000000..8388411582cf
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mlx5/driver.h>
+#include "wq.h"
+#include "mlx5_core.h"
+
+u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
+{
+	return (u32)wq->sz_m1 + 1;
+}
+
+u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
+{
+	return wq->sz_m1 + 1;
+}
+
+u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
+{
+	return (u32)wq->sz_m1 + 1;
+}
+
+static u32 mlx5_wq_cyc_get_byte_size(struct mlx5_wq_cyc *wq)
+{
+	return mlx5_wq_cyc_get_size(wq) << wq->log_stride;
+}
+
+static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq)
+{
+	return mlx5_cqwq_get_size(wq) << wq->log_stride;
+}
+
+static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq)
+{
+	return mlx5_wq_ll_get_size(wq) << wq->log_stride;
+}
+
+int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		       void *wqc, struct mlx5_wq_cyc *wq,
+		       struct mlx5_wq_ctrl *wq_ctrl)
+{
+	int err;
+
+	wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride);
+	wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1;
+
+	err = mlx5_db_alloc(mdev, &wq_ctrl->db);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5_buf_alloc(mdev, mlx5_wq_cyc_get_byte_size(wq), &wq_ctrl->buf);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		goto err_db_free;
+	}
+
+	wq->buf = wq_ctrl->buf.direct.buf;
+	wq->db  = wq_ctrl->db.db;
+
+	wq_ctrl->mdev = mdev;
+
+	return 0;
+
+err_db_free:
+	mlx5_db_free(mdev, &wq_ctrl->db);
+
+	return err;
+}
+
+int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		     void *cqc, struct mlx5_cqwq *wq,
+		     struct mlx5_wq_ctrl *wq_ctrl)
+{
+	int err;
+
+	wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz);
+	wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size);
+	wq->sz_m1 = (1 << wq->log_sz) - 1;
+
+	err = mlx5_db_alloc(mdev, &wq_ctrl->db);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5_buf_alloc(mdev, mlx5_cqwq_get_byte_size(wq), &wq_ctrl->buf);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		goto err_db_free;
+	}
+
+	wq->buf = wq_ctrl->buf.direct.buf;
+	wq->db  = wq_ctrl->db.db;
+
+	wq_ctrl->mdev = mdev;
+
+	return 0;
+
+err_db_free:
+	mlx5_db_free(mdev, &wq_ctrl->db);
+
+	return err;
+}
+
+int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		      void *wqc, struct mlx5_wq_ll *wq,
+		      struct mlx5_wq_ctrl *wq_ctrl)
+{
+	struct mlx5_wqe_srq_next_seg *next_seg;
+	int err;
+	int i;
+
+	wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride);
+	wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1;
+
+	err = mlx5_db_alloc(mdev, &wq_ctrl->db);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_db_alloc() failed, %d\n", err);
+		return err;
+	}
+
+	err = mlx5_buf_alloc(mdev, mlx5_wq_ll_get_byte_size(wq), &wq_ctrl->buf);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_buf_alloc() failed, %d\n", err);
+		goto err_db_free;
+	}
+
+	wq->buf = wq_ctrl->buf.direct.buf;
+	wq->db  = wq_ctrl->db.db;
+
+	for (i = 0; i < wq->sz_m1; i++) {
+		next_seg = mlx5_wq_ll_get_wqe(wq, i);
+		next_seg->next_wqe_index = cpu_to_be16(i + 1);
+	}
+	next_seg = mlx5_wq_ll_get_wqe(wq, i);
+	wq->tail_next = &next_seg->next_wqe_index;
+
+	wq_ctrl->mdev = mdev;
+
+	return 0;
+
+err_db_free:
+	mlx5_db_free(mdev, &wq_ctrl->db);
+
+	return err;
+}
+
+void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
+{
+	mlx5_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);
+	mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
new file mode 100644
index 000000000000..e0ddd69fb429
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -0,0 +1,171 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __MLX5_WQ_H__
+#define __MLX5_WQ_H__
+
+#include <linux/mlx5/mlx5_ifc.h>
+
+struct mlx5_wq_param {
+	int		linear;
+	int		numa;
+};
+
+struct mlx5_wq_ctrl {
+	struct mlx5_core_dev	*mdev;
+	struct mlx5_buf		buf;
+	struct mlx5_db		db;
+};
+
+struct mlx5_wq_cyc {
+	void			*buf;
+	__be32			*db;
+	u16			sz_m1;
+	u8			log_stride;
+};
+
+struct mlx5_cqwq {
+	void			*buf;
+	__be32			*db;
+	u32			sz_m1;
+	u32			cc; /* consumer counter */
+	u8			log_sz;
+	u8			log_stride;
+};
+
+struct mlx5_wq_ll {
+	void			*buf;
+	__be32			*db;
+	__be16			*tail_next;
+	u16			sz_m1;
+	u16			head;
+	u16			wqe_ctr;
+	u16			cur_sz;
+	u8			log_stride;
+};
+
+int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		       void *wqc, struct mlx5_wq_cyc *wq,
+		       struct mlx5_wq_ctrl *wq_ctrl);
+u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
+
+int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		     void *cqc, struct mlx5_cqwq *wq,
+		     struct mlx5_wq_ctrl *wq_ctrl);
+u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
+
+int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
+		      void *wqc, struct mlx5_wq_ll *wq,
+		      struct mlx5_wq_ctrl *wq_ctrl);
+u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq);
+
+void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
+
+static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr)
+{
+	return ctr & wq->sz_m1;
+}
+
+static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix)
+{
+	return wq->buf + (ix << wq->log_stride);
+}
+
+static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2)
+{
+	int equal   = (cc1 == cc2);
+	int smaller = 0x8000 & (cc1 - cc2);
+
+	return !equal && !smaller;
+}
+
+static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq)
+{
+	return wq->cc & wq->sz_m1;
+}
+
+static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
+{
+	return wq->buf + (ix << wq->log_stride);
+}
+
+static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq)
+{
+	return wq->cc >> wq->log_sz;
+}
+
+static inline void mlx5_cqwq_pop(struct mlx5_cqwq *wq)
+{
+	wq->cc++;
+}
+
+static inline void mlx5_cqwq_update_db_record(struct mlx5_cqwq *wq)
+{
+	*wq->db = cpu_to_be32(wq->cc & 0xffffff);
+}
+
+static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq)
+{
+	return wq->cur_sz == wq->sz_m1;
+}
+
+static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
+{
+	return !wq->cur_sz;
+}
+
+static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
+{
+	return wq->buf + (ix << wq->log_stride);
+}
+
+static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next)
+{
+	wq->head = head_next;
+	wq->wqe_ctr++;
+	wq->cur_sz++;
+}
+
+static inline void mlx5_wq_ll_pop(struct mlx5_wq_ll *wq, __be16 ix,
+				  __be16 *next_tail_next)
+{
+	*wq->tail_next = ix;
+	wq->tail_next = next_tail_next;
+	wq->cur_sz--;
+}
+
+static inline void mlx5_wq_ll_update_db_record(struct mlx5_wq_ll *wq)
+{
+	*wq->db = cpu_to_be32(wq->wqe_ctr);
+}
+
+#endif /* __MLX5_WQ_H__ */
diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig
index d16b11ed2e52..b7e2f49696b7 100644
--- a/drivers/net/ethernet/micrel/Kconfig
+++ b/drivers/net/ethernet/micrel/Kconfig
@@ -8,9 +8,7 @@ config NET_VENDOR_MICREL
 	depends on (HAS_IOMEM && DMA_ENGINE) || SPI || PCI || HAS_IOMEM || \
 		   (ARM && ARCH_KS8695)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 6f332ebdf3b5..75dc46c5fca2 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -6664,7 +6664,7 @@ static void mib_read_work(struct work_struct *work)
 				wake_up_interruptible(
 					&hw_priv->counter[i].counter);
 			}
-		} else if (jiffies >= hw_priv->counter[i].time) {
+		} else if (time_after_eq(jiffies, hw_priv->counter[i].time)) {
 			/* Only read MIB counters when the port is connected. */
 			if (media_connected == mib->state)
 				hw_priv->counter[i].read = 1;
@@ -6689,7 +6689,7 @@ static void mib_monitor(unsigned long ptr)
 
 	/* This is used to verify Wake-on-LAN is working. */
 	if (hw_priv->pme_wait) {
-		if (hw_priv->pme_wait <= jiffies) {
+		if (time_is_before_eq_jiffies(hw_priv->pme_wait)) {
 			hw_clr_wol_pme_status(&hw_priv->hw);
 			hw_priv->pme_wait = 0;
 		}
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index afaf0c07f37f..3fd8ca6d4e7c 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_MICROCHIP
 	default y
 	depends on SPI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/moxa/Kconfig b/drivers/net/ethernet/moxa/Kconfig
index 1731e050fa27..5b531da36933 100644
--- a/drivers/net/ethernet/moxa/Kconfig
+++ b/drivers/net/ethernet/moxa/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_MOXART
 	default y
 	depends on (ARM && ARCH_MOXART)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 81d0f1c86d6d..becbb5f1f5a7 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -244,7 +244,6 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget)
 		napi_gro_receive(&priv->napi, skb);
 		rx++;
 
-		ndev->last_rx = jiffies;
 		priv->stats.rx_packets++;
 		priv->stats.rx_bytes += len;
 		if (desc0 & RX_DESC0_MULTICAST)
diff --git a/drivers/net/ethernet/myricom/Kconfig b/drivers/net/ethernet/myricom/Kconfig
index 3932d081fa21..9645c7245bbf 100644
--- a/drivers/net/ethernet/myricom/Kconfig
+++ b/drivers/net/ethernet/myricom/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_MYRI
 	default y
 	depends on PCI && INET
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say
-	  Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/natsemi/Kconfig b/drivers/net/ethernet/natsemi/Kconfig
index a100860d45e6..a10ef50e4f12 100644
--- a/drivers/net/ethernet/natsemi/Kconfig
+++ b/drivers/net/ethernet/natsemi/Kconfig
@@ -6,9 +6,7 @@ config NET_VENDOR_NATSEMI
 	bool "National Semi-conductor devices"
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -24,8 +22,7 @@ config MACSONIC
 	  Support for NatSemi SONIC based Ethernet devices.  This includes
 	  the onboard Ethernet in many Quadras as well as some LC-PDS,
 	  a few Nubus and all known Comm Slot Ethernet cards.  If you have
-	  one of these say Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  one of these say Y here.
 
 	  To compile this driver as a module, choose M here. This module will
 	  be called macsonic.
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index 87abb4f10c43..71899009c468 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_EXAR
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say
-	  Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 1e0f72b65459..c28111749e1f 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -5308,7 +5308,8 @@ static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr)
 
 /**
  * s2io_ethtool_sset - Sets different link parameters.
- * @sp : private member of the device structure, which is a pointer to the  * s2io_nic structure.
+ * @sp : private member of the device structure, which is a pointer to the
+ * s2io_nic structure.
  * @info: pointer to the structure with parameters given by ethtool to set
  * link information.
  * Description:
@@ -5793,7 +5794,8 @@ static void s2io_vpd_read(struct s2io_nic *nic)
 
 /**
  *  s2io_ethtool_geeprom  - reads the value stored in the Eeprom.
- *  @sp : private member of the device structure, which is a pointer to the *       s2io_nic structure.
+ *  @sp : private member of the device structure, which is a pointer to the
+ *  s2io_nic structure.
  *  @eeprom : pointer to the user level structure provided by ethtool,
  *  containing all relevant information.
  *  @data_buf : user defined value to be written into Eeprom.
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 9e1aaa7f36bb..5f630a24e491 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1004,8 +1004,6 @@ void vxge_hw_device_clear_tx_rx(struct __vxge_hw_device *hldev)
 static enum vxge_hw_status
 vxge_hw_channel_dtr_alloc(struct __vxge_hw_channel *channel, void **dtrh)
 {
-	void **tmp_arr;
-
 	if (channel->reserve_ptr - channel->reserve_top > 0) {
 _alloc_after_swap:
 		*dtrh =	channel->reserve_arr[--channel->reserve_ptr];
@@ -1020,10 +1018,7 @@ _alloc_after_swap:
 	 * i.e.	no additional lock need	to be done when	we free	a resource */
 
 	if (channel->length - channel->free_ptr > 0) {
-
-		tmp_arr	= channel->reserve_arr;
-		channel->reserve_arr = channel->free_arr;
-		channel->free_arr = tmp_arr;
+		swap(channel->reserve_arr, channel->free_arr);
 		channel->reserve_ptr = channel->length;
 		channel->reserve_top = channel->free_ptr;
 		channel->free_ptr = channel->length;
diff --git a/drivers/net/ethernet/nuvoton/Kconfig b/drivers/net/ethernet/nuvoton/Kconfig
index 01182b559473..71c973f8e50f 100644
--- a/drivers/net/ethernet/nuvoton/Kconfig
+++ b/drivers/net/ethernet/nuvoton/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_NUVOTON
 	default y
 	depends on ARM && ARCH_W90X900
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/nvidia/Kconfig b/drivers/net/ethernet/nvidia/Kconfig
index ace19e7f6d13..4efc9fe84785 100644
--- a/drivers/net/ethernet/nvidia/Kconfig
+++ b/drivers/net/ethernet/nvidia/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_NVIDIA
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -22,9 +20,7 @@ config FORCEDETH
 	tristate "nForce Ethernet support"
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) controller of this type, say Y and
-	  read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) controller of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called forcedeth.
diff --git a/drivers/net/ethernet/oki-semi/Kconfig b/drivers/net/ethernet/oki-semi/Kconfig
index ecd45f9ea9d9..5a975af4824b 100644
--- a/drivers/net/ethernet/oki-semi/Kconfig
+++ b/drivers/net/ethernet/oki-semi/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_OKI
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig
index 8d5180043c70..b5ea2a56106e 100644
--- a/drivers/net/ethernet/packetengines/Kconfig
+++ b/drivers/net/ethernet/packetengines/Kconfig
@@ -7,9 +7,7 @@ config NET_PACKET_ENGINE
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -23,9 +21,7 @@ config HAMACHI
 	depends on PCI
 	select MII
 	---help---
-	  If you have a Gigabit Ethernet card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a Gigabit Ethernet card of this type, say Y here.
 
 	  To compile this driver as a module, choose M here. The module will be
 	  called hamachi.
diff --git a/drivers/net/ethernet/pasemi/Kconfig b/drivers/net/ethernet/pasemi/Kconfig
index 01e6c329d78c..db19c6f49859 100644
--- a/drivers/net/ethernet/pasemi/Kconfig
+++ b/drivers/net/ethernet/pasemi/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_PASEMI
 	default y
 	depends on PPC_PASEMI && PCI && INET
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index d49cba129081..f1f0108c275d 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_QLOGIC
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 8da7c3faf817..7b43a3b4abdc 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1764,7 +1764,7 @@ int netxen_process_cmd_ring(struct netxen_adapter *adapter)
 	int done = 0;
 	struct nx_host_tx_ring *tx_ring = adapter->tx_ring;
 
-	if (!spin_trylock(&adapter->tx_clean_lock))
+	if (!spin_trylock_bh(&adapter->tx_clean_lock))
 		return 1;
 
 	sw_consumer = tx_ring->sw_consumer;
@@ -1819,7 +1819,7 @@ int netxen_process_cmd_ring(struct netxen_adapter *adapter)
 	 */
 	hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
 	done = (sw_consumer == hw_consumer);
-	spin_unlock(&adapter->tx_clean_lock);
+	spin_unlock_bh(&adapter->tx_clean_lock);
 
 	return done;
 }
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index e0c31e3947d1..6409a06bbdf6 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -3025,9 +3025,9 @@ netxen_sysfs_read_dimm(struct file *filp, struct kobject *kobj,
 	u8 dw, rows, cols, banks, ranks;
 	u32 val;
 
-	if (size != sizeof(struct netxen_dimm_cfg)) {
+	if (size < attr->size) {
 		netdev_err(netdev, "Invalid size\n");
-		return -1;
+		return -EINVAL;
 	}
 
 	memset(&dimm, 0, sizeof(struct netxen_dimm_cfg));
@@ -3137,7 +3137,7 @@ out:
 
 static struct bin_attribute bin_attr_dimm = {
 	.attr = { .name = "dimm", .mode = (S_IRUGO | S_IWUSR) },
-	.size = 0,
+	.size = sizeof(struct netxen_dimm_cfg),
 	.read = netxen_sysfs_read_dimm,
 };
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index f221126a5c4e..055f3763e577 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1326,9 +1326,6 @@ struct qlcnic_eswitch {
 };
 
 
-/* Return codes for Error handling */
-#define QL_STATUS_INVALID_PARAM	-1
-
 #define MAX_BW			100	/* % of link speed */
 #define MIN_BW			1	/* % of link speed */
 #define MAX_VLAN_ID		4095
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 367f3976df56..2f6cc423ab1d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -1031,7 +1031,7 @@ int qlcnic_init_pci_info(struct qlcnic_adapter *adapter)
 		pfn = pci_info[i].id;
 
 		if (pfn >= ahw->max_vnic_func) {
-			ret = QL_STATUS_INVALID_PARAM;
+			ret = -EINVAL;
 			dev_err(&adapter->pdev->dev, "%s: Invalid function 0x%x, max 0x%x\n",
 				__func__, pfn, ahw->max_vnic_func);
 			goto err_eswitch;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 59a721fba018..05c28f2c6df7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -24,8 +24,6 @@
 #include <linux/hwmon-sysfs.h>
 #endif
 
-#define QLC_STATUS_UNSUPPORTED_CMD	-2
-
 int qlcnicvf_config_bridged_mode(struct qlcnic_adapter *adapter, u32 enable)
 {
 	return -EOPNOTSUPP;
@@ -166,7 +164,7 @@ static int qlcnic_82xx_store_beacon(struct qlcnic_adapter *adapter,
 	u8 b_state, b_rate;
 
 	if (len != sizeof(u16))
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	memcpy(&beacon, buf, sizeof(u16));
 	err = qlcnic_validate_beacon(adapter, beacon, &b_state, &b_rate);
@@ -383,17 +381,17 @@ static int validate_pm_config(struct qlcnic_adapter *adapter,
 		dest_pci_func = pm_cfg[i].dest_npar;
 		src_index = qlcnic_is_valid_nic_func(adapter, src_pci_func);
 		if (src_index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 
 		dest_index = qlcnic_is_valid_nic_func(adapter, dest_pci_func);
 		if (dest_index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 
 		s_esw_id = adapter->npars[src_index].phy_port;
 		d_esw_id = adapter->npars[dest_index].phy_port;
 
 		if (s_esw_id != d_esw_id)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 	}
 
 	return 0;
@@ -414,7 +412,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp,
 	count	= size / sizeof(struct qlcnic_pm_func_cfg);
 	rem	= size % sizeof(struct qlcnic_pm_func_cfg);
 	if (rem)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32));
 	pm_cfg = (struct qlcnic_pm_func_cfg *)buf;
@@ -427,7 +425,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp,
 		action = !!pm_cfg[i].action;
 		index = qlcnic_is_valid_nic_func(adapter, pci_func);
 		if (index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 
 		id = adapter->npars[index].phy_port;
 		ret = qlcnic_config_port_mirroring(adapter, id,
@@ -440,7 +438,7 @@ static ssize_t qlcnic_sysfs_write_pm_config(struct file *filp,
 		pci_func = pm_cfg[i].pci_func;
 		index = qlcnic_is_valid_nic_func(adapter, pci_func);
 		if (index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 		id = adapter->npars[index].phy_port;
 		adapter->npars[index].enable_pm = !!pm_cfg[i].action;
 		adapter->npars[index].dest_npar = id;
@@ -499,11 +497,11 @@ static int validate_esw_config(struct qlcnic_adapter *adapter,
 	for (i = 0; i < count; i++) {
 		pci_func = esw_cfg[i].pci_func;
 		if (pci_func >= ahw->max_vnic_func)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 
 		if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC)
 			if (qlcnic_is_valid_nic_func(adapter, pci_func) < 0)
-				return QL_STATUS_INVALID_PARAM;
+				return -EINVAL;
 
 		switch (esw_cfg[i].op_mode) {
 		case QLCNIC_PORT_DEFAULTS:
@@ -517,25 +515,25 @@ static int validate_esw_config(struct qlcnic_adapter *adapter,
 
 			if (ret != QLCNIC_NON_PRIV_FUNC) {
 				if (esw_cfg[i].mac_anti_spoof != 0)
-					return QL_STATUS_INVALID_PARAM;
+					return -EINVAL;
 				if (esw_cfg[i].mac_override != 1)
-					return QL_STATUS_INVALID_PARAM;
+					return -EINVAL;
 				if (esw_cfg[i].promisc_mode != 1)
-					return QL_STATUS_INVALID_PARAM;
+					return -EINVAL;
 			}
 			break;
 		case QLCNIC_ADD_VLAN:
 			if (!IS_VALID_VLAN(esw_cfg[i].vlan_id))
-				return QL_STATUS_INVALID_PARAM;
+				return -EINVAL;
 			if (!esw_cfg[i].op_type)
-				return QL_STATUS_INVALID_PARAM;
+				return -EINVAL;
 			break;
 		case QLCNIC_DEL_VLAN:
 			if (!esw_cfg[i].op_type)
-				return QL_STATUS_INVALID_PARAM;
+				return -EINVAL;
 			break;
 		default:
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 		}
 	}
 
@@ -559,7 +557,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file,
 	count	= size / sizeof(struct qlcnic_esw_func_cfg);
 	rem	= size % sizeof(struct qlcnic_esw_func_cfg);
 	if (rem)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32));
 	esw_cfg = (struct qlcnic_esw_func_cfg *)buf;
@@ -570,7 +568,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file,
 	for (i = 0; i < count; i++) {
 		if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC)
 			if (qlcnic_config_switch_port(adapter, &esw_cfg[i]))
-				return QL_STATUS_INVALID_PARAM;
+				return -EINVAL;
 
 		if (adapter->ahw->pci_func != esw_cfg[i].pci_func)
 			continue;
@@ -604,7 +602,7 @@ static ssize_t qlcnic_sysfs_write_esw_config(struct file *file,
 		pci_func = esw_cfg[i].pci_func;
 		index = qlcnic_is_valid_nic_func(adapter, pci_func);
 		if (index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 		npar = &adapter->npars[index];
 		switch (esw_cfg[i].op_mode) {
 		case QLCNIC_PORT_DEFAULTS:
@@ -654,7 +652,7 @@ static ssize_t qlcnic_sysfs_read_esw_config(struct file *file,
 
 		esw_cfg[pci_func].pci_func = pci_func;
 		if (qlcnic_get_eswitch_port_config(adapter, &esw_cfg[pci_func]))
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 	}
 	qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32));
 	return size;
@@ -669,11 +667,11 @@ static int validate_npar_config(struct qlcnic_adapter *adapter,
 	for (i = 0; i < count; i++) {
 		pci_func = np_cfg[i].pci_func;
 		if (qlcnic_is_valid_nic_func(adapter, pci_func) < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 
 		if (!IS_VALID_BW(np_cfg[i].min_bw) ||
 		    !IS_VALID_BW(np_cfg[i].max_bw))
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 	}
 	return 0;
 }
@@ -694,7 +692,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file,
 	count	= size / sizeof(struct qlcnic_npar_func_cfg);
 	rem	= size % sizeof(struct qlcnic_npar_func_cfg);
 	if (rem)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	qlcnic_swap32_buffer((u32 *)buf, size / sizeof(u32));
 	np_cfg = (struct qlcnic_npar_func_cfg *)buf;
@@ -717,7 +715,7 @@ static ssize_t qlcnic_sysfs_write_npar_config(struct file *file,
 			return ret;
 		index = qlcnic_is_valid_nic_func(adapter, pci_func);
 		if (index < 0)
-			return QL_STATUS_INVALID_PARAM;
+			return -EINVAL;
 		adapter->npars[index].min_bw = nic_info.min_tx_bw;
 		adapter->npars[index].max_bw = nic_info.max_tx_bw;
 	}
@@ -784,13 +782,13 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file,
 	int ret;
 
 	if (qlcnic_83xx_check(adapter))
-		return QLC_STATUS_UNSUPPORTED_CMD;
+		return -EOPNOTSUPP;
 
 	if (size != sizeof(struct qlcnic_esw_statistics))
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	if (offset >= adapter->ahw->max_vnic_func)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	memset(&port_stats, 0, size);
 	ret = qlcnic_get_port_stats(adapter, offset, QLCNIC_QUERY_RX_COUNTER,
@@ -819,13 +817,13 @@ static ssize_t qlcnic_sysfs_get_esw_stats(struct file *file,
 	int ret;
 
 	if (qlcnic_83xx_check(adapter))
-		return QLC_STATUS_UNSUPPORTED_CMD;
+		return -EOPNOTSUPP;
 
 	if (size != sizeof(struct qlcnic_esw_statistics))
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	if (offset >= QLCNIC_NIU_MAX_XG_PORTS)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	memset(&esw_stats, 0, size);
 	ret = qlcnic_get_eswitch_stats(adapter, offset, QLCNIC_QUERY_RX_COUNTER,
@@ -853,10 +851,10 @@ static ssize_t qlcnic_sysfs_clear_esw_stats(struct file *file,
 	int ret;
 
 	if (qlcnic_83xx_check(adapter))
-		return QLC_STATUS_UNSUPPORTED_CMD;
+		return -EOPNOTSUPP;
 
 	if (offset >= QLCNIC_NIU_MAX_XG_PORTS)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_ESWITCH, offset,
 				     QLCNIC_QUERY_RX_COUNTER);
@@ -883,10 +881,10 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file,
 	int ret;
 
 	if (qlcnic_83xx_check(adapter))
-		return QLC_STATUS_UNSUPPORTED_CMD;
+		return -EOPNOTSUPP;
 
 	if (offset >= adapter->ahw->max_vnic_func)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_PORT, offset,
 				     QLCNIC_QUERY_RX_COUNTER);
@@ -953,9 +951,7 @@ static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp,
 	struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
 
 	if (!size)
-		return QL_STATUS_INVALID_PARAM;
-	if (!buf)
-		return QL_STATUS_INVALID_PARAM;
+		return -EINVAL;
 
 	count = size / sizeof(u32);
 
@@ -1132,9 +1128,6 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp,
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
 
-	if (!buf)
-		return QL_STATUS_INVALID_PARAM;
-
 	ret = kstrtoul(buf, 16, &data);
 
 	switch (data) {
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 25800a1dedcb..02b7115b6aaa 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -3871,9 +3871,6 @@ static int ql_adapter_reset(struct ql_adapter *qdev)
 		return status;
 	}
 
-	end_jiffies = jiffies +
-		max((unsigned long)1, usecs_to_jiffies(30));
-
 	/* Check if bit is set then skip the mailbox command and
 	 * clear the bit, else we are in normal reset process.
 	 */
@@ -3888,6 +3885,7 @@ static int ql_adapter_reset(struct ql_adapter *qdev)
 
 	ql_write32(qdev, RST_FO, (RST_FO_FR << 16) | RST_FO_FR);
 
+	end_jiffies = jiffies + usecs_to_jiffies(30);
 	do {
 		value = ql_read32(qdev, RST_FO);
 		if ((value & RST_FO_FR) == 0)
diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig
index 9a49f42ac2ba..a76e380cf89a 100644
--- a/drivers/net/ethernet/qualcomm/Kconfig
+++ b/drivers/net/ethernet/qualcomm/Kconfig
@@ -6,9 +6,7 @@ config NET_VENDOR_QUALCOMM
 	bool "Qualcomm devices"
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index f66641d961e3..2f87909f5186 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -839,7 +839,7 @@ static const struct of_device_id qca_spi_of_match[] = {
 MODULE_DEVICE_TABLE(of, qca_spi_of_match);
 
 static int
-qca_spi_probe(struct spi_device *spi_device)
+qca_spi_probe(struct spi_device *spi)
 {
 	struct qcaspi *qca = NULL;
 	struct net_device *qcaspi_devs = NULL;
@@ -847,52 +847,52 @@ qca_spi_probe(struct spi_device *spi_device)
 	u16 signature;
 	const char *mac;
 
-	if (!spi_device->dev.of_node) {
-		dev_err(&spi_device->dev, "Missing device tree\n");
+	if (!spi->dev.of_node) {
+		dev_err(&spi->dev, "Missing device tree\n");
 		return -EINVAL;
 	}
 
-	legacy_mode = of_property_read_bool(spi_device->dev.of_node,
+	legacy_mode = of_property_read_bool(spi->dev.of_node,
 					    "qca,legacy-mode");
 
 	if (qcaspi_clkspeed == 0) {
-		if (spi_device->max_speed_hz)
-			qcaspi_clkspeed = spi_device->max_speed_hz;
+		if (spi->max_speed_hz)
+			qcaspi_clkspeed = spi->max_speed_hz;
 		else
 			qcaspi_clkspeed = QCASPI_CLK_SPEED;
 	}
 
 	if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) ||
 	    (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) {
-		dev_info(&spi_device->dev, "Invalid clkspeed: %d\n",
+		dev_info(&spi->dev, "Invalid clkspeed: %d\n",
 			 qcaspi_clkspeed);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) ||
 	    (qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) {
-		dev_info(&spi_device->dev, "Invalid burst len: %d\n",
+		dev_info(&spi->dev, "Invalid burst len: %d\n",
 			 qcaspi_burst_len);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) ||
 	    (qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) {
-		dev_info(&spi_device->dev, "Invalid pluggable: %d\n",
+		dev_info(&spi->dev, "Invalid pluggable: %d\n",
 			 qcaspi_pluggable);
 		return -EINVAL;
 	}
 
-	dev_info(&spi_device->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n",
+	dev_info(&spi->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n",
 		 QCASPI_DRV_VERSION,
 		 qcaspi_clkspeed,
 		 qcaspi_burst_len,
 		 qcaspi_pluggable);
 
-	spi_device->mode = SPI_MODE_3;
-	spi_device->max_speed_hz = qcaspi_clkspeed;
-	if (spi_setup(spi_device) < 0) {
-		dev_err(&spi_device->dev, "Unable to setup SPI device\n");
+	spi->mode = SPI_MODE_3;
+	spi->max_speed_hz = qcaspi_clkspeed;
+	if (spi_setup(spi) < 0) {
+		dev_err(&spi->dev, "Unable to setup SPI device\n");
 		return -EFAULT;
 	}
 
@@ -905,21 +905,23 @@ qca_spi_probe(struct spi_device *spi_device)
 	qca = netdev_priv(qcaspi_devs);
 	if (!qca) {
 		free_netdev(qcaspi_devs);
-		dev_err(&spi_device->dev, "Fail to retrieve private structure\n");
+		dev_err(&spi->dev, "Fail to retrieve private structure\n");
 		return -ENOMEM;
 	}
 	qca->net_dev = qcaspi_devs;
-	qca->spi_dev = spi_device;
+	qca->spi_dev = spi;
 	qca->legacy_mode = legacy_mode;
 
-	mac = of_get_mac_address(spi_device->dev.of_node);
+	spi_set_drvdata(spi, qcaspi_devs);
+
+	mac = of_get_mac_address(spi->dev.of_node);
 
 	if (mac)
 		ether_addr_copy(qca->net_dev->dev_addr, mac);
 
 	if (!is_valid_ether_addr(qca->net_dev->dev_addr)) {
 		eth_hw_addr_random(qca->net_dev);
-		dev_info(&spi_device->dev, "Using random MAC address: %pM\n",
+		dev_info(&spi->dev, "Using random MAC address: %pM\n",
 			 qca->net_dev->dev_addr);
 	}
 
@@ -930,7 +932,7 @@ qca_spi_probe(struct spi_device *spi_device)
 		qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature);
 
 		if (signature != QCASPI_GOOD_SIGNATURE) {
-			dev_err(&spi_device->dev, "Invalid signature (0x%04X)\n",
+			dev_err(&spi->dev, "Invalid signature (0x%04X)\n",
 				signature);
 			free_netdev(qcaspi_devs);
 			return -EFAULT;
@@ -938,23 +940,21 @@ qca_spi_probe(struct spi_device *spi_device)
 	}
 
 	if (register_netdev(qcaspi_devs)) {
-		dev_info(&spi_device->dev, "Unable to register net device %s\n",
+		dev_info(&spi->dev, "Unable to register net device %s\n",
 			 qcaspi_devs->name);
 		free_netdev(qcaspi_devs);
 		return -EFAULT;
 	}
 
-	spi_set_drvdata(spi_device, qcaspi_devs);
-
 	qcaspi_init_device_debugfs(qca);
 
 	return 0;
 }
 
 static int
-qca_spi_remove(struct spi_device *spi_device)
+qca_spi_remove(struct spi_device *spi)
 {
-	struct net_device *qcaspi_devs = spi_get_drvdata(spi_device);
+	struct net_device *qcaspi_devs = spi_get_drvdata(spi);
 	struct qcaspi *qca = netdev_priv(qcaspi_devs);
 
 	qcaspi_remove_device_debugfs(qca);
diff --git a/drivers/net/ethernet/rdc/Kconfig b/drivers/net/ethernet/rdc/Kconfig
index 2055f7eb2ba9..a9c4e990d29b 100644
--- a/drivers/net/ethernet/rdc/Kconfig
+++ b/drivers/net/ethernet/rdc/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_RDC
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index ae5d027096ed..7c69f4c8134d 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_REALTEK
 	default y
 	depends on PCI || (PARPORT && X86)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -24,8 +22,7 @@ config ATP
 	select CRC32
 	---help---
 	  This is a network (Ethernet) device which attaches to your parallel
-	  port. Read <file:drivers/net/ethernet/realtek/atp.c> as well as the
-	  Ethernet-HOWTO, available from <http://www.tldp.org/docs.html#howto>,
+	  port. Read the file <file:drivers/net/ethernet/realtek/atp.c>
 	  if you want to use this.  If you intend to use this driver, you
 	  should have said N to the "Parallel printer support", because the two
 	  drivers don't like each other.
@@ -40,9 +37,7 @@ config 8139CP
 	select MII
 	---help---
 	  This is a driver for the Fast Ethernet PCI network cards based on
-	  the RTL8139C+ chips. If you have one of those, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  the RTL8139C+ chips. If you have one of those, say Y here.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called 8139cp.  This is recommended.
@@ -54,8 +49,7 @@ config 8139TOO
 	select MII
 	---help---
 	  This is a driver for the Fast Ethernet PCI network cards based on
-	  the RTL 8129/8130/8139 chips. If you have one of those, say Y and
-	  read the Ethernet-HOWTO <http://www.tldp.org/docs.html#howto>.
+	  the RTL 8129/8130/8139 chips. If you have one of those, say Y here.
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called 8139too.  This is recommended.
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index c70ab40d8698..3df51faf18ae 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6884,7 +6884,7 @@ static void r8169_csum_workaround(struct rtl8169_private *tp,
 			rtl8169_start_xmit(nskb, tp->dev);
 		} while (segs);
 
-		dev_kfree_skb(skb);
+		dev_consume_skb_any(skb);
 	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		if (skb_checksum_help(skb) < 0)
 			goto drop;
@@ -6896,7 +6896,7 @@ static void r8169_csum_workaround(struct rtl8169_private *tp,
 drop:
 		stats = &tp->dev->stats;
 		stats->tx_dropped++;
-		dev_kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 	}
 }
 
diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig
index 196e98a2d93b..270c4c9cac7f 100644
--- a/drivers/net/ethernet/renesas/Kconfig
+++ b/drivers/net/ethernet/renesas/Kconfig
@@ -2,6 +2,19 @@
 # Renesas device configuration
 #
 
+config NET_VENDOR_RENESAS
+	bool "Renesas devices"
+	default y
+	---help---
+	  If you have a network (Ethernet) card belonging to this class, say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Renesas devices. If you say Y, you will be asked
+	  for your specific device in the following questions.
+
+if NET_VENDOR_RENESAS
+
 config SH_ETH
 	tristate "Renesas SuperH Ethernet support"
 	depends on HAS_DMA
@@ -15,3 +28,19 @@ config SH_ETH
 	  This driver supporting CPUs are:
 		- SH7619, SH7710, SH7712, SH7724, SH7734, SH7763, SH7757,
 		  R8A7740, R8A777x and R8A779x.
+
+config RAVB
+	tristate "Renesas Ethernet AVB support"
+	depends on HAS_DMA
+	depends on ARCH_SHMOBILE || COMPILE_TEST
+	select CRC32
+	select MII
+	select MDIO_BITBANG
+	select PHYLIB
+	select PTP_1588_CLOCK
+	help
+	  Renesas Ethernet AVB device driver.
+	  This driver supports the following SoCs:
+		- R8A779x.
+
+endif # NET_VENDOR_RENESAS
diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile
index 1c278a8e066a..a05102a7df02 100644
--- a/drivers/net/ethernet/renesas/Makefile
+++ b/drivers/net/ethernet/renesas/Makefile
@@ -3,3 +3,7 @@
 #
 
 obj-$(CONFIG_SH_ETH) += sh_eth.o
+
+ravb-objs := ravb_main.o ravb_ptp.o
+
+obj-$(CONFIG_RAVB) += ravb.o
diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
new file mode 100644
index 000000000000..8aa50ac4e2d6
--- /dev/null
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -0,0 +1,832 @@
+/* Renesas Ethernet AVB device driver
+ *
+ * Copyright (C) 2014-2015 Renesas Electronics Corporation
+ * Copyright (C) 2015 Renesas Solutions Corp.
+ * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ *
+ * Based on the SuperH Ethernet driver
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __RAVB_H__
+#define __RAVB_H__
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mdio-bitbang.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/ptp_clock_kernel.h>
+
+#define BE_TX_RING_SIZE	64	/* TX ring size for Best Effort */
+#define BE_RX_RING_SIZE	1024	/* RX ring size for Best Effort */
+#define NC_TX_RING_SIZE	64	/* TX ring size for Network Control */
+#define NC_RX_RING_SIZE	64	/* RX ring size for Network Control */
+#define BE_TX_RING_MIN	64
+#define BE_RX_RING_MIN	64
+#define BE_TX_RING_MAX	1024
+#define BE_RX_RING_MAX	2048
+
+#define PKT_BUF_SZ	1538
+
+/* Driver's parameters */
+#define RAVB_ALIGN	128
+
+/* Hardware time stamp */
+#define RAVB_TXTSTAMP_VALID	0x00000001	/* TX timestamp valid */
+#define RAVB_TXTSTAMP_ENABLED	0x00000010	/* Enable TX timestamping */
+
+#define RAVB_RXTSTAMP_VALID	0x00000001	/* RX timestamp valid */
+#define RAVB_RXTSTAMP_TYPE	0x00000006	/* RX type mask */
+#define RAVB_RXTSTAMP_TYPE_V2_L2_EVENT 0x00000002
+#define RAVB_RXTSTAMP_TYPE_ALL	0x00000006
+#define RAVB_RXTSTAMP_ENABLED	0x00000010	/* Enable RX timestamping */
+
+enum ravb_reg {
+	/* AVB-DMAC registers */
+	CCC	= 0x0000,
+	DBAT	= 0x0004,
+	DLR	= 0x0008,
+	CSR	= 0x000C,
+	CDAR0	= 0x0010,
+	CDAR1	= 0x0014,
+	CDAR2	= 0x0018,
+	CDAR3	= 0x001C,
+	CDAR4	= 0x0020,
+	CDAR5	= 0x0024,
+	CDAR6	= 0x0028,
+	CDAR7	= 0x002C,
+	CDAR8	= 0x0030,
+	CDAR9	= 0x0034,
+	CDAR10	= 0x0038,
+	CDAR11	= 0x003C,
+	CDAR12	= 0x0040,
+	CDAR13	= 0x0044,
+	CDAR14	= 0x0048,
+	CDAR15	= 0x004C,
+	CDAR16	= 0x0050,
+	CDAR17	= 0x0054,
+	CDAR18	= 0x0058,
+	CDAR19	= 0x005C,
+	CDAR20	= 0x0060,
+	CDAR21	= 0x0064,
+	ESR	= 0x0088,
+	RCR	= 0x0090,
+	RQC0	= 0x0094,
+	RQC1	= 0x0098,
+	RQC2	= 0x009C,
+	RQC3	= 0x00A0,
+	RQC4	= 0x00A4,
+	RPC	= 0x00B0,
+	UFCW	= 0x00BC,
+	UFCS	= 0x00C0,
+	UFCV0	= 0x00C4,
+	UFCV1	= 0x00C8,
+	UFCV2	= 0x00CC,
+	UFCV3	= 0x00D0,
+	UFCV4	= 0x00D4,
+	UFCD0	= 0x00E0,
+	UFCD1	= 0x00E4,
+	UFCD2	= 0x00E8,
+	UFCD3	= 0x00EC,
+	UFCD4	= 0x00F0,
+	SFO	= 0x00FC,
+	SFP0	= 0x0100,
+	SFP1	= 0x0104,
+	SFP2	= 0x0108,
+	SFP3	= 0x010C,
+	SFP4	= 0x0110,
+	SFP5	= 0x0114,
+	SFP6	= 0x0118,
+	SFP7	= 0x011C,
+	SFP8	= 0x0120,
+	SFP9	= 0x0124,
+	SFP10	= 0x0128,
+	SFP11	= 0x012C,
+	SFP12	= 0x0130,
+	SFP13	= 0x0134,
+	SFP14	= 0x0138,
+	SFP15	= 0x013C,
+	SFP16	= 0x0140,
+	SFP17	= 0x0144,
+	SFP18	= 0x0148,
+	SFP19	= 0x014C,
+	SFP20	= 0x0150,
+	SFP21	= 0x0154,
+	SFP22	= 0x0158,
+	SFP23	= 0x015C,
+	SFP24	= 0x0160,
+	SFP25	= 0x0164,
+	SFP26	= 0x0168,
+	SFP27	= 0x016C,
+	SFP28	= 0x0170,
+	SFP29	= 0x0174,
+	SFP30	= 0x0178,
+	SFP31	= 0x017C,
+	SFM0	= 0x01C0,
+	SFM1	= 0x01C4,
+	TGC	= 0x0300,
+	TCCR	= 0x0304,
+	TSR	= 0x0308,
+	TFA0	= 0x0310,
+	TFA1	= 0x0314,
+	TFA2	= 0x0318,
+	CIVR0	= 0x0320,
+	CIVR1	= 0x0324,
+	CDVR0	= 0x0328,
+	CDVR1	= 0x032C,
+	CUL0	= 0x0330,
+	CUL1	= 0x0334,
+	CLL0	= 0x0338,
+	CLL1	= 0x033C,
+	DIC	= 0x0350,
+	DIS	= 0x0354,
+	EIC	= 0x0358,
+	EIS	= 0x035C,
+	RIC0	= 0x0360,
+	RIS0	= 0x0364,
+	RIC1	= 0x0368,
+	RIS1	= 0x036C,
+	RIC2	= 0x0370,
+	RIS2	= 0x0374,
+	TIC	= 0x0378,
+	TIS	= 0x037C,
+	ISS	= 0x0380,
+	GCCR	= 0x0390,
+	GMTT	= 0x0394,
+	GPTC	= 0x0398,
+	GTI	= 0x039C,
+	GTO0	= 0x03A0,
+	GTO1	= 0x03A4,
+	GTO2	= 0x03A8,
+	GIC	= 0x03AC,
+	GIS	= 0x03B0,
+	GCPT	= 0x03B4,	/* Undocumented? */
+	GCT0	= 0x03B8,
+	GCT1	= 0x03BC,
+	GCT2	= 0x03C0,
+
+	/* E-MAC registers */
+	ECMR	= 0x0500,
+	RFLR	= 0x0508,
+	ECSR	= 0x0510,
+	ECSIPR	= 0x0518,
+	PIR	= 0x0520,
+	PSR	= 0x0528,
+	PIPR	= 0x052c,
+	MPR	= 0x0558,
+	PFTCR	= 0x055c,
+	PFRCR	= 0x0560,
+	GECMR	= 0x05b0,
+	MAHR	= 0x05c0,
+	MALR	= 0x05c8,
+	TROCR	= 0x0700,	/* Undocumented? */
+	CDCR	= 0x0708,	/* Undocumented? */
+	LCCR	= 0x0710,	/* Undocumented? */
+	CEFCR	= 0x0740,
+	FRECR	= 0x0748,
+	TSFRCR	= 0x0750,
+	TLFRCR	= 0x0758,
+	RFCR	= 0x0760,
+	CERCR	= 0x0768,	/* Undocumented? */
+	CEECR	= 0x0770,	/* Undocumented? */
+	MAFCR	= 0x0778,
+};
+
+
+/* Register bits of the Ethernet AVB */
+/* CCC */
+enum CCC_BIT {
+	CCC_OPC		= 0x00000003,
+	CCC_OPC_RESET	= 0x00000000,
+	CCC_OPC_CONFIG	= 0x00000001,
+	CCC_OPC_OPERATION = 0x00000002,
+	CCC_DTSR	= 0x00000100,
+	CCC_CSEL	= 0x00030000,
+	CCC_CSEL_HPB	= 0x00010000,
+	CCC_CSEL_ETH_TX	= 0x00020000,
+	CCC_CSEL_GMII_REF = 0x00030000,
+	CCC_BOC		= 0x00100000,	/* Undocumented? */
+	CCC_LBME	= 0x01000000,
+};
+
+/* CSR */
+enum CSR_BIT {
+	CSR_OPS		= 0x0000000F,
+	CSR_OPS_RESET	= 0x00000001,
+	CSR_OPS_CONFIG	= 0x00000002,
+	CSR_OPS_OPERATION = 0x00000004,
+	CSR_OPS_STANDBY	= 0x00000008,	/* Undocumented? */
+	CSR_DTS		= 0x00000100,
+	CSR_TPO0	= 0x00010000,
+	CSR_TPO1	= 0x00020000,
+	CSR_TPO2	= 0x00040000,
+	CSR_TPO3	= 0x00080000,
+	CSR_RPO		= 0x00100000,
+};
+
+/* ESR */
+enum ESR_BIT {
+	ESR_EQN		= 0x0000001F,
+	ESR_ET		= 0x00000F00,
+	ESR_EIL		= 0x00001000,
+};
+
+/* RCR */
+enum RCR_BIT {
+	RCR_EFFS	= 0x00000001,
+	RCR_ENCF	= 0x00000002,
+	RCR_ESF		= 0x0000000C,
+	RCR_ETS0	= 0x00000010,
+	RCR_ETS2	= 0x00000020,
+	RCR_RFCL	= 0x1FFF0000,
+};
+
+/* RQC0/1/2/3/4 */
+enum RQC_BIT {
+	RQC_RSM0	= 0x00000003,
+	RQC_UFCC0	= 0x00000030,
+	RQC_RSM1	= 0x00000300,
+	RQC_UFCC1	= 0x00003000,
+	RQC_RSM2	= 0x00030000,
+	RQC_UFCC2	= 0x00300000,
+	RQC_RSM3	= 0x03000000,
+	RQC_UFCC3	= 0x30000000,
+};
+
+/* RPC */
+enum RPC_BIT {
+	RPC_PCNT	= 0x00000700,
+	RPC_DCNT	= 0x00FF0000,
+};
+
+/* UFCW */
+enum UFCW_BIT {
+	UFCW_WL0	= 0x0000003F,
+	UFCW_WL1	= 0x00003F00,
+	UFCW_WL2	= 0x003F0000,
+	UFCW_WL3	= 0x3F000000,
+};
+
+/* UFCS */
+enum UFCS_BIT {
+	UFCS_SL0	= 0x0000003F,
+	UFCS_SL1	= 0x00003F00,
+	UFCS_SL2	= 0x003F0000,
+	UFCS_SL3	= 0x3F000000,
+};
+
+/* UFCV0/1/2/3/4 */
+enum UFCV_BIT {
+	UFCV_CV0	= 0x0000003F,
+	UFCV_CV1	= 0x00003F00,
+	UFCV_CV2	= 0x003F0000,
+	UFCV_CV3	= 0x3F000000,
+};
+
+/* UFCD0/1/2/3/4 */
+enum UFCD_BIT {
+	UFCD_DV0	= 0x0000003F,
+	UFCD_DV1	= 0x00003F00,
+	UFCD_DV2	= 0x003F0000,
+	UFCD_DV3	= 0x3F000000,
+};
+
+/* SFO */
+enum SFO_BIT {
+	SFO_FPB		= 0x0000003F,
+};
+
+/* RTC */
+enum RTC_BIT {
+	RTC_MFL0	= 0x00000FFF,
+	RTC_MFL1	= 0x0FFF0000,
+};
+
+/* TGC */
+enum TGC_BIT {
+	TGC_TSM0	= 0x00000001,
+	TGC_TSM1	= 0x00000002,
+	TGC_TSM2	= 0x00000004,
+	TGC_TSM3	= 0x00000008,
+	TGC_TQP		= 0x00000030,
+	TGC_TQP_NONAVB	= 0x00000000,
+	TGC_TQP_AVBMODE1 = 0x00000010,
+	TGC_TQP_AVBMODE2 = 0x00000030,
+	TGC_TBD0	= 0x00000300,
+	TGC_TBD1	= 0x00003000,
+	TGC_TBD2	= 0x00030000,
+	TGC_TBD3	= 0x00300000,
+};
+
+/* TCCR */
+enum TCCR_BIT {
+	TCCR_TSRQ0	= 0x00000001,
+	TCCR_TSRQ1	= 0x00000002,
+	TCCR_TSRQ2	= 0x00000004,
+	TCCR_TSRQ3	= 0x00000008,
+	TCCR_TFEN	= 0x00000100,
+	TCCR_TFR	= 0x00000200,
+};
+
+/* TSR */
+enum TSR_BIT {
+	TSR_CCS0	= 0x00000003,
+	TSR_CCS1	= 0x0000000C,
+	TSR_TFFL	= 0x00000700,
+};
+
+/* TFA2 */
+enum TFA2_BIT {
+	TFA2_TSV	= 0x0000FFFF,
+	TFA2_TST	= 0x03FF0000,
+};
+
+/* DIC */
+enum DIC_BIT {
+	DIC_DPE1	= 0x00000002,
+	DIC_DPE2	= 0x00000004,
+	DIC_DPE3	= 0x00000008,
+	DIC_DPE4	= 0x00000010,
+	DIC_DPE5	= 0x00000020,
+	DIC_DPE6	= 0x00000040,
+	DIC_DPE7	= 0x00000080,
+	DIC_DPE8	= 0x00000100,
+	DIC_DPE9	= 0x00000200,
+	DIC_DPE10	= 0x00000400,
+	DIC_DPE11	= 0x00000800,
+	DIC_DPE12	= 0x00001000,
+	DIC_DPE13	= 0x00002000,
+	DIC_DPE14	= 0x00004000,
+	DIC_DPE15	= 0x00008000,
+};
+
+/* DIS */
+enum DIS_BIT {
+	DIS_DPF1	= 0x00000002,
+	DIS_DPF2	= 0x00000004,
+	DIS_DPF3	= 0x00000008,
+	DIS_DPF4	= 0x00000010,
+	DIS_DPF5	= 0x00000020,
+	DIS_DPF6	= 0x00000040,
+	DIS_DPF7	= 0x00000080,
+	DIS_DPF8	= 0x00000100,
+	DIS_DPF9	= 0x00000200,
+	DIS_DPF10	= 0x00000400,
+	DIS_DPF11	= 0x00000800,
+	DIS_DPF12	= 0x00001000,
+	DIS_DPF13	= 0x00002000,
+	DIS_DPF14	= 0x00004000,
+	DIS_DPF15	= 0x00008000,
+};
+
+/* EIC */
+enum EIC_BIT {
+	EIC_MREE	= 0x00000001,
+	EIC_MTEE	= 0x00000002,
+	EIC_QEE		= 0x00000004,
+	EIC_SEE		= 0x00000008,
+	EIC_CLLE0	= 0x00000010,
+	EIC_CLLE1	= 0x00000020,
+	EIC_CULE0	= 0x00000040,
+	EIC_CULE1	= 0x00000080,
+	EIC_TFFE	= 0x00000100,
+};
+
+/* EIS */
+enum EIS_BIT {
+	EIS_MREF	= 0x00000001,
+	EIS_MTEF	= 0x00000002,
+	EIS_QEF		= 0x00000004,
+	EIS_SEF		= 0x00000008,
+	EIS_CLLF0	= 0x00000010,
+	EIS_CLLF1	= 0x00000020,
+	EIS_CULF0	= 0x00000040,
+	EIS_CULF1	= 0x00000080,
+	EIS_TFFF	= 0x00000100,
+	EIS_QFS		= 0x00010000,
+};
+
+/* RIC0 */
+enum RIC0_BIT {
+	RIC0_FRE0	= 0x00000001,
+	RIC0_FRE1	= 0x00000002,
+	RIC0_FRE2	= 0x00000004,
+	RIC0_FRE3	= 0x00000008,
+	RIC0_FRE4	= 0x00000010,
+	RIC0_FRE5	= 0x00000020,
+	RIC0_FRE6	= 0x00000040,
+	RIC0_FRE7	= 0x00000080,
+	RIC0_FRE8	= 0x00000100,
+	RIC0_FRE9	= 0x00000200,
+	RIC0_FRE10	= 0x00000400,
+	RIC0_FRE11	= 0x00000800,
+	RIC0_FRE12	= 0x00001000,
+	RIC0_FRE13	= 0x00002000,
+	RIC0_FRE14	= 0x00004000,
+	RIC0_FRE15	= 0x00008000,
+	RIC0_FRE16	= 0x00010000,
+	RIC0_FRE17	= 0x00020000,
+};
+
+/* RIC0 */
+enum RIS0_BIT {
+	RIS0_FRF0	= 0x00000001,
+	RIS0_FRF1	= 0x00000002,
+	RIS0_FRF2	= 0x00000004,
+	RIS0_FRF3	= 0x00000008,
+	RIS0_FRF4	= 0x00000010,
+	RIS0_FRF5	= 0x00000020,
+	RIS0_FRF6	= 0x00000040,
+	RIS0_FRF7	= 0x00000080,
+	RIS0_FRF8	= 0x00000100,
+	RIS0_FRF9	= 0x00000200,
+	RIS0_FRF10	= 0x00000400,
+	RIS0_FRF11	= 0x00000800,
+	RIS0_FRF12	= 0x00001000,
+	RIS0_FRF13	= 0x00002000,
+	RIS0_FRF14	= 0x00004000,
+	RIS0_FRF15	= 0x00008000,
+	RIS0_FRF16	= 0x00010000,
+	RIS0_FRF17	= 0x00020000,
+};
+
+/* RIC1 */
+enum RIC1_BIT {
+	RIC1_RFWE	= 0x80000000,
+};
+
+/* RIS1 */
+enum RIS1_BIT {
+	RIS1_RFWF	= 0x80000000,
+};
+
+/* RIC2 */
+enum RIC2_BIT {
+	RIC2_QFE0	= 0x00000001,
+	RIC2_QFE1	= 0x00000002,
+	RIC2_QFE2	= 0x00000004,
+	RIC2_QFE3	= 0x00000008,
+	RIC2_QFE4	= 0x00000010,
+	RIC2_QFE5	= 0x00000020,
+	RIC2_QFE6	= 0x00000040,
+	RIC2_QFE7	= 0x00000080,
+	RIC2_QFE8	= 0x00000100,
+	RIC2_QFE9	= 0x00000200,
+	RIC2_QFE10	= 0x00000400,
+	RIC2_QFE11	= 0x00000800,
+	RIC2_QFE12	= 0x00001000,
+	RIC2_QFE13	= 0x00002000,
+	RIC2_QFE14	= 0x00004000,
+	RIC2_QFE15	= 0x00008000,
+	RIC2_QFE16	= 0x00010000,
+	RIC2_QFE17	= 0x00020000,
+	RIC2_RFFE	= 0x80000000,
+};
+
+/* RIS2 */
+enum RIS2_BIT {
+	RIS2_QFF0	= 0x00000001,
+	RIS2_QFF1	= 0x00000002,
+	RIS2_QFF2	= 0x00000004,
+	RIS2_QFF3	= 0x00000008,
+	RIS2_QFF4	= 0x00000010,
+	RIS2_QFF5	= 0x00000020,
+	RIS2_QFF6	= 0x00000040,
+	RIS2_QFF7	= 0x00000080,
+	RIS2_QFF8	= 0x00000100,
+	RIS2_QFF9	= 0x00000200,
+	RIS2_QFF10	= 0x00000400,
+	RIS2_QFF11	= 0x00000800,
+	RIS2_QFF12	= 0x00001000,
+	RIS2_QFF13	= 0x00002000,
+	RIS2_QFF14	= 0x00004000,
+	RIS2_QFF15	= 0x00008000,
+	RIS2_QFF16	= 0x00010000,
+	RIS2_QFF17	= 0x00020000,
+	RIS2_RFFF	= 0x80000000,
+};
+
+/* TIC */
+enum TIC_BIT {
+	TIC_FTE0	= 0x00000001,	/* Undocumented? */
+	TIC_FTE1	= 0x00000002,	/* Undocumented? */
+	TIC_TFUE	= 0x00000100,
+	TIC_TFWE	= 0x00000200,
+};
+
+/* TIS */
+enum TIS_BIT {
+	TIS_FTF0	= 0x00000001,	/* Undocumented? */
+	TIS_FTF1	= 0x00000002,	/* Undocumented? */
+	TIS_TFUF	= 0x00000100,
+	TIS_TFWF	= 0x00000200,
+};
+
+/* ISS */
+enum ISS_BIT {
+	ISS_FRS		= 0x00000001,	/* Undocumented? */
+	ISS_FTS		= 0x00000004,	/* Undocumented? */
+	ISS_ES		= 0x00000040,
+	ISS_MS		= 0x00000080,
+	ISS_TFUS	= 0x00000100,
+	ISS_TFWS	= 0x00000200,
+	ISS_RFWS	= 0x00001000,
+	ISS_CGIS	= 0x00002000,
+	ISS_DPS1	= 0x00020000,
+	ISS_DPS2	= 0x00040000,
+	ISS_DPS3	= 0x00080000,
+	ISS_DPS4	= 0x00100000,
+	ISS_DPS5	= 0x00200000,
+	ISS_DPS6	= 0x00400000,
+	ISS_DPS7	= 0x00800000,
+	ISS_DPS8	= 0x01000000,
+	ISS_DPS9	= 0x02000000,
+	ISS_DPS10	= 0x04000000,
+	ISS_DPS11	= 0x08000000,
+	ISS_DPS12	= 0x10000000,
+	ISS_DPS13	= 0x20000000,
+	ISS_DPS14	= 0x40000000,
+	ISS_DPS15	= 0x80000000,
+};
+
+/* GCCR */
+enum GCCR_BIT {
+	GCCR_TCR	= 0x00000003,
+	GCCR_TCR_NOREQ	= 0x00000000, /* No request */
+	GCCR_TCR_RESET	= 0x00000001, /* gPTP/AVTP presentation timer reset */
+	GCCR_TCR_CAPTURE = 0x00000003, /* Capture value set in GCCR.TCSS */
+	GCCR_LTO	= 0x00000004,
+	GCCR_LTI	= 0x00000008,
+	GCCR_LPTC	= 0x00000010,
+	GCCR_LMTT	= 0x00000020,
+	GCCR_TCSS	= 0x00000300,
+	GCCR_TCSS_GPTP	= 0x00000000,	/* gPTP timer value */
+	GCCR_TCSS_ADJGPTP = 0x00000100, /* Adjusted gPTP timer value */
+	GCCR_TCSS_AVTP	= 0x00000200,	/* AVTP presentation time value */
+};
+
+/* GTI */
+enum GTI_BIT {
+	GTI_TIV		= 0x0FFFFFFF,
+};
+
+/* GIC */
+enum GIC_BIT {
+	GIC_PTCE	= 0x00000001,	/* Undocumented? */
+	GIC_PTME	= 0x00000004,
+};
+
+/* GIS */
+enum GIS_BIT {
+	GIS_PTCF	= 0x00000001,	/* Undocumented? */
+	GIS_PTMF	= 0x00000004,
+};
+
+/* ECMR */
+enum ECMR_BIT {
+	ECMR_PRM	= 0x00000001,
+	ECMR_DM		= 0x00000002,
+	ECMR_TE		= 0x00000020,
+	ECMR_RE		= 0x00000040,
+	ECMR_MPDE	= 0x00000200,
+	ECMR_TXF	= 0x00010000,	/* Undocumented? */
+	ECMR_RXF	= 0x00020000,
+	ECMR_PFR	= 0x00040000,
+	ECMR_ZPF	= 0x00080000,	/* Undocumented? */
+	ECMR_RZPF	= 0x00100000,
+	ECMR_DPAD	= 0x00200000,
+	ECMR_RCSC	= 0x00800000,
+	ECMR_TRCCM	= 0x04000000,
+};
+
+/* ECSR */
+enum ECSR_BIT {
+	ECSR_ICD	= 0x00000001,
+	ECSR_MPD	= 0x00000002,
+	ECSR_LCHNG	= 0x00000004,
+	ECSR_PHYI	= 0x00000008,
+};
+
+/* ECSIPR */
+enum ECSIPR_BIT {
+	ECSIPR_ICDIP	= 0x00000001,
+	ECSIPR_MPDIP	= 0x00000002,
+	ECSIPR_LCHNGIP	= 0x00000004,	/* Undocumented? */
+};
+
+/* PIR */
+enum PIR_BIT {
+	PIR_MDC		= 0x00000001,
+	PIR_MMD		= 0x00000002,
+	PIR_MDO		= 0x00000004,
+	PIR_MDI		= 0x00000008,
+};
+
+/* PSR */
+enum PSR_BIT {
+	PSR_LMON	= 0x00000001,
+};
+
+/* PIPR */
+enum PIPR_BIT {
+	PIPR_PHYIP	= 0x00000001,
+};
+
+/* MPR */
+enum MPR_BIT {
+	MPR_MP		= 0x0000ffff,
+};
+
+/* GECMR */
+enum GECMR_BIT {
+	GECMR_SPEED	= 0x00000001,
+	GECMR_SPEED_100	= 0x00000000,
+	GECMR_SPEED_1000 = 0x00000001,
+};
+
+/* The Ethernet AVB descriptor definitions. */
+struct ravb_desc {
+	__le16 ds;		/* Descriptor size */
+	u8 cc;		/* Content control MSBs (reserved) */
+	u8 die_dt;	/* Descriptor interrupt enable and type */
+	__le32 dptr;	/* Descriptor pointer */
+};
+
+enum DIE_DT {
+	/* Frame data */
+	DT_FMID		= 0x40,
+	DT_FSTART	= 0x50,
+	DT_FEND		= 0x60,
+	DT_FSINGLE	= 0x70,
+	/* Chain control */
+	DT_LINK		= 0x80,
+	DT_LINKFIX	= 0x90,
+	DT_EOS		= 0xa0,
+	/* HW/SW arbitration */
+	DT_FEMPTY	= 0xc0,
+	DT_FEMPTY_IS	= 0xd0,
+	DT_FEMPTY_IC	= 0xe0,
+	DT_FEMPTY_ND	= 0xf0,
+	DT_LEMPTY	= 0x20,
+	DT_EEMPTY	= 0x30,
+};
+
+struct ravb_rx_desc {
+	__le16 ds_cc;	/* Descriptor size and content control LSBs */
+	u8 msc;		/* MAC status code */
+	u8 die_dt;	/* Descriptor interrupt enable and type */
+	__le32 dptr;	/* Descpriptor pointer */
+};
+
+struct ravb_ex_rx_desc {
+	__le16 ds_cc;	/* Descriptor size and content control lower bits */
+	u8 msc;		/* MAC status code */
+	u8 die_dt;	/* Descriptor interrupt enable and type */
+	__le32 dptr;	/* Descpriptor pointer */
+	__le32 ts_n;	/* Timestampe nsec */
+	__le32 ts_sl;	/* Timestamp low */
+	__le16 ts_sh;	/* Timestamp high */
+	__le16 res;	/* Reserved bits */
+};
+
+enum RX_DS_CC_BIT {
+	RX_DS		= 0x0fff, /* Data size */
+	RX_TR		= 0x1000, /* Truncation indication */
+	RX_EI		= 0x2000, /* Error indication */
+	RX_PS		= 0xc000, /* Padding selection */
+};
+
+/* E-MAC status code */
+enum MSC_BIT {
+	MSC_CRC		= 0x01, /* Frame CRC error */
+	MSC_RFE		= 0x02, /* Frame reception error (flagged by PHY) */
+	MSC_RTSF	= 0x04, /* Frame length error (frame too short) */
+	MSC_RTLF	= 0x08, /* Frame length error (frame too long) */
+	MSC_FRE		= 0x10, /* Fraction error (not a multiple of 8 bits) */
+	MSC_CRL		= 0x20, /* Carrier lost */
+	MSC_CEEF	= 0x40, /* Carrier extension error */
+	MSC_MC		= 0x80, /* Multicast frame reception */
+};
+
+struct ravb_tx_desc {
+	__le16 ds_tagl;	/* Descriptor size and frame tag LSBs */
+	u8 tagh_tsr;	/* Frame tag MSBs and timestamp storage request bit */
+	u8 die_dt;	/* Descriptor interrupt enable and type */
+	__le32 dptr;	/* Descpriptor pointer */
+};
+
+enum TX_DS_TAGL_BIT {
+	TX_DS		= 0x0fff, /* Data size */
+	TX_TAGL		= 0xf000, /* Frame tag LSBs */
+};
+
+enum TX_TAGH_TSR_BIT {
+	TX_TAGH		= 0x3f, /* Frame tag MSBs */
+	TX_TSR		= 0x40, /* Timestamp storage request */
+};
+enum RAVB_QUEUE {
+	RAVB_BE = 0,	/* Best Effort Queue */
+	RAVB_NC,	/* Network Control Queue */
+};
+
+#define DBAT_ENTRY_NUM	22
+#define RX_QUEUE_OFFSET	4
+#define NUM_RX_QUEUE	2
+#define NUM_TX_QUEUE	2
+
+struct ravb_tstamp_skb {
+	struct list_head list;
+	struct sk_buff *skb;
+	u16 tag;
+};
+
+struct ravb_ptp_perout {
+	u32 target;
+	u32 period;
+};
+
+#define N_EXT_TS	1
+#define N_PER_OUT	1
+
+struct ravb_ptp {
+	struct ptp_clock *clock;
+	struct ptp_clock_info info;
+	u32 default_addend;
+	u32 current_addend;
+	int extts[N_EXT_TS];
+	struct ravb_ptp_perout perout[N_PER_OUT];
+};
+
+struct ravb_private {
+	struct net_device *ndev;
+	struct platform_device *pdev;
+	void __iomem *addr;
+	struct mdiobb_ctrl mdiobb;
+	u32 num_rx_ring[NUM_RX_QUEUE];
+	u32 num_tx_ring[NUM_TX_QUEUE];
+	u32 desc_bat_size;
+	dma_addr_t desc_bat_dma;
+	struct ravb_desc *desc_bat;
+	dma_addr_t rx_desc_dma[NUM_RX_QUEUE];
+	dma_addr_t tx_desc_dma[NUM_TX_QUEUE];
+	struct ravb_ex_rx_desc *rx_ring[NUM_RX_QUEUE];
+	struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE];
+	struct sk_buff **rx_skb[NUM_RX_QUEUE];
+	struct sk_buff **tx_skb[NUM_TX_QUEUE];
+	void **tx_buffers[NUM_TX_QUEUE];
+	u32 rx_over_errors;
+	u32 rx_fifo_errors;
+	struct net_device_stats stats[NUM_RX_QUEUE];
+	u32 tstamp_tx_ctrl;
+	u32 tstamp_rx_ctrl;
+	struct list_head ts_skb_list;
+	u32 ts_skb_tag;
+	struct ravb_ptp ptp;
+	spinlock_t lock;		/* Register access lock */
+	u32 cur_rx[NUM_RX_QUEUE];	/* Consumer ring indices */
+	u32 dirty_rx[NUM_RX_QUEUE];	/* Producer ring indices */
+	u32 cur_tx[NUM_TX_QUEUE];
+	u32 dirty_tx[NUM_TX_QUEUE];
+	struct napi_struct napi[NUM_RX_QUEUE];
+	struct work_struct work;
+	/* MII transceiver section. */
+	struct mii_bus *mii_bus;	/* MDIO bus control */
+	struct phy_device *phydev;	/* PHY device control */
+	int link;
+	phy_interface_t phy_interface;
+	int msg_enable;
+	int speed;
+	int duplex;
+
+	unsigned no_avb_link:1;
+	unsigned avb_link_active_low:1;
+};
+
+static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	return ioread32(priv->addr + reg);
+}
+
+static inline void ravb_write(struct net_device *ndev, u32 data,
+			      enum ravb_reg reg)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	iowrite32(data, priv->addr + reg);
+}
+
+int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value);
+
+irqreturn_t ravb_ptp_interrupt(struct net_device *ndev);
+void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev);
+void ravb_ptp_stop(struct net_device *ndev);
+
+#endif	/* #ifndef __RAVB_H__ */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
new file mode 100644
index 000000000000..fd9745714d90
--- /dev/null
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -0,0 +1,1824 @@
+/* Renesas Ethernet AVB device driver
+ *
+ * Copyright (C) 2014-2015 Renesas Electronics Corporation
+ * Copyright (C) 2015 Renesas Solutions Corp.
+ * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ *
+ * Based on the SuperH Ethernet driver
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/cache.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "ravb.h"
+
+#define RAVB_DEF_MSG_ENABLE \
+		(NETIF_MSG_LINK	  | \
+		 NETIF_MSG_TIMER  | \
+		 NETIF_MSG_RX_ERR | \
+		 NETIF_MSG_TX_ERR)
+
+int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value)
+{
+	int i;
+
+	for (i = 0; i < 10000; i++) {
+		if ((ravb_read(ndev, reg) & mask) == value)
+			return 0;
+		udelay(10);
+	}
+	return -ETIMEDOUT;
+}
+
+static int ravb_config(struct net_device *ndev)
+{
+	int error;
+
+	/* Set config mode */
+	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) | CCC_OPC_CONFIG,
+		   CCC);
+	/* Check if the operating mode is changed to the config mode */
+	error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG);
+	if (error)
+		netdev_err(ndev, "failed to switch device to config mode\n");
+
+	return error;
+}
+
+static void ravb_set_duplex(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 ecmr = ravb_read(ndev, ECMR);
+
+	if (priv->duplex)	/* Full */
+		ecmr |=  ECMR_DM;
+	else			/* Half */
+		ecmr &= ~ECMR_DM;
+	ravb_write(ndev, ecmr, ECMR);
+}
+
+static void ravb_set_rate(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	switch (priv->speed) {
+	case 100:		/* 100BASE */
+		ravb_write(ndev, GECMR_SPEED_100, GECMR);
+		break;
+	case 1000:		/* 1000BASE */
+		ravb_write(ndev, GECMR_SPEED_1000, GECMR);
+		break;
+	default:
+		break;
+	}
+}
+
+static void ravb_set_buffer_align(struct sk_buff *skb)
+{
+	u32 reserve = (unsigned long)skb->data & (RAVB_ALIGN - 1);
+
+	if (reserve)
+		skb_reserve(skb, RAVB_ALIGN - reserve);
+}
+
+/* Get MAC address from the MAC address registers
+ *
+ * Ethernet AVB device doesn't have ROM for MAC address.
+ * This function gets the MAC address that was used by a bootloader.
+ */
+static void ravb_read_mac_address(struct net_device *ndev, const u8 *mac)
+{
+	if (mac) {
+		ether_addr_copy(ndev->dev_addr, mac);
+	} else {
+		ndev->dev_addr[0] = (ravb_read(ndev, MAHR) >> 24);
+		ndev->dev_addr[1] = (ravb_read(ndev, MAHR) >> 16) & 0xFF;
+		ndev->dev_addr[2] = (ravb_read(ndev, MAHR) >> 8) & 0xFF;
+		ndev->dev_addr[3] = (ravb_read(ndev, MAHR) >> 0) & 0xFF;
+		ndev->dev_addr[4] = (ravb_read(ndev, MALR) >> 8) & 0xFF;
+		ndev->dev_addr[5] = (ravb_read(ndev, MALR) >> 0) & 0xFF;
+	}
+}
+
+static void ravb_mdio_ctrl(struct mdiobb_ctrl *ctrl, u32 mask, int set)
+{
+	struct ravb_private *priv = container_of(ctrl, struct ravb_private,
+						 mdiobb);
+	u32 pir = ravb_read(priv->ndev, PIR);
+
+	if (set)
+		pir |=  mask;
+	else
+		pir &= ~mask;
+	ravb_write(priv->ndev, pir, PIR);
+}
+
+/* MDC pin control */
+static void ravb_set_mdc(struct mdiobb_ctrl *ctrl, int level)
+{
+	ravb_mdio_ctrl(ctrl, PIR_MDC, level);
+}
+
+/* Data I/O pin control */
+static void ravb_set_mdio_dir(struct mdiobb_ctrl *ctrl, int output)
+{
+	ravb_mdio_ctrl(ctrl, PIR_MMD, output);
+}
+
+/* Set data bit */
+static void ravb_set_mdio_data(struct mdiobb_ctrl *ctrl, int value)
+{
+	ravb_mdio_ctrl(ctrl, PIR_MDO, value);
+}
+
+/* Get data bit */
+static int ravb_get_mdio_data(struct mdiobb_ctrl *ctrl)
+{
+	struct ravb_private *priv = container_of(ctrl, struct ravb_private,
+						 mdiobb);
+
+	return (ravb_read(priv->ndev, PIR) & PIR_MDI) != 0;
+}
+
+/* MDIO bus control struct */
+static struct mdiobb_ops bb_ops = {
+	.owner = THIS_MODULE,
+	.set_mdc = ravb_set_mdc,
+	.set_mdio_dir = ravb_set_mdio_dir,
+	.set_mdio_data = ravb_set_mdio_data,
+	.get_mdio_data = ravb_get_mdio_data,
+};
+
+/* Free skb's and DMA buffers for Ethernet AVB */
+static void ravb_ring_free(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int ring_size;
+	int i;
+
+	/* Free RX skb ringbuffer */
+	if (priv->rx_skb[q]) {
+		for (i = 0; i < priv->num_rx_ring[q]; i++)
+			dev_kfree_skb(priv->rx_skb[q][i]);
+	}
+	kfree(priv->rx_skb[q]);
+	priv->rx_skb[q] = NULL;
+
+	/* Free TX skb ringbuffer */
+	if (priv->tx_skb[q]) {
+		for (i = 0; i < priv->num_tx_ring[q]; i++)
+			dev_kfree_skb(priv->tx_skb[q][i]);
+	}
+	kfree(priv->tx_skb[q]);
+	priv->tx_skb[q] = NULL;
+
+	/* Free aligned TX buffers */
+	if (priv->tx_buffers[q]) {
+		for (i = 0; i < priv->num_tx_ring[q]; i++)
+			kfree(priv->tx_buffers[q][i]);
+	}
+	kfree(priv->tx_buffers[q]);
+	priv->tx_buffers[q] = NULL;
+
+	if (priv->rx_ring[q]) {
+		ring_size = sizeof(struct ravb_ex_rx_desc) *
+			    (priv->num_rx_ring[q] + 1);
+		dma_free_coherent(NULL, ring_size, priv->rx_ring[q],
+				  priv->rx_desc_dma[q]);
+		priv->rx_ring[q] = NULL;
+	}
+
+	if (priv->tx_ring[q]) {
+		ring_size = sizeof(struct ravb_tx_desc) *
+			    (priv->num_tx_ring[q] + 1);
+		dma_free_coherent(NULL, ring_size, priv->tx_ring[q],
+				  priv->tx_desc_dma[q]);
+		priv->tx_ring[q] = NULL;
+	}
+}
+
+/* Format skb and descriptor buffer for Ethernet AVB */
+static void ravb_ring_format(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct ravb_ex_rx_desc *rx_desc = NULL;
+	struct ravb_tx_desc *tx_desc = NULL;
+	struct ravb_desc *desc = NULL;
+	int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q];
+	int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q];
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	void *buffer;
+	int i;
+
+	priv->cur_rx[q] = 0;
+	priv->cur_tx[q] = 0;
+	priv->dirty_rx[q] = 0;
+	priv->dirty_tx[q] = 0;
+
+	memset(priv->rx_ring[q], 0, rx_ring_size);
+	/* Build RX ring buffer */
+	for (i = 0; i < priv->num_rx_ring[q]; i++) {
+		priv->rx_skb[q][i] = NULL;
+		skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1);
+		if (!skb)
+			break;
+		ravb_set_buffer_align(skb);
+		/* RX descriptor */
+		rx_desc = &priv->rx_ring[q][i];
+		/* The size of the buffer should be on 16-byte boundary. */
+		rx_desc->ds_cc = cpu_to_le16(ALIGN(PKT_BUF_SZ, 16));
+		dma_addr = dma_map_single(&ndev->dev, skb->data,
+					  ALIGN(PKT_BUF_SZ, 16),
+					  DMA_FROM_DEVICE);
+		if (dma_mapping_error(&ndev->dev, dma_addr)) {
+			dev_kfree_skb(skb);
+			break;
+		}
+		priv->rx_skb[q][i] = skb;
+		rx_desc->dptr = cpu_to_le32(dma_addr);
+		rx_desc->die_dt = DT_FEMPTY;
+	}
+	rx_desc = &priv->rx_ring[q][i];
+	rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
+	rx_desc->die_dt = DT_LINKFIX; /* type */
+	priv->dirty_rx[q] = (u32)(i - priv->num_rx_ring[q]);
+
+	memset(priv->tx_ring[q], 0, tx_ring_size);
+	/* Build TX ring buffer */
+	for (i = 0; i < priv->num_tx_ring[q]; i++) {
+		priv->tx_skb[q][i] = NULL;
+		priv->tx_buffers[q][i] = NULL;
+		buffer = kmalloc(PKT_BUF_SZ + RAVB_ALIGN - 1, GFP_KERNEL);
+		if (!buffer)
+			break;
+		/* Aligned TX buffer */
+		priv->tx_buffers[q][i] = buffer;
+		tx_desc = &priv->tx_ring[q][i];
+		tx_desc->die_dt = DT_EEMPTY;
+	}
+	tx_desc = &priv->tx_ring[q][i];
+	tx_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]);
+	tx_desc->die_dt = DT_LINKFIX; /* type */
+
+	/* RX descriptor base address for best effort */
+	desc = &priv->desc_bat[RX_QUEUE_OFFSET + q];
+	desc->die_dt = DT_LINKFIX; /* type */
+	desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
+
+	/* TX descriptor base address for best effort */
+	desc = &priv->desc_bat[q];
+	desc->die_dt = DT_LINKFIX; /* type */
+	desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]);
+}
+
+/* Init skb and descriptor buffer for Ethernet AVB */
+static int ravb_ring_init(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int ring_size;
+
+	/* Allocate RX and TX skb rings */
+	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
+				  sizeof(*priv->rx_skb[q]), GFP_KERNEL);
+	priv->tx_skb[q] = kcalloc(priv->num_tx_ring[q],
+				  sizeof(*priv->tx_skb[q]), GFP_KERNEL);
+	if (!priv->rx_skb[q] || !priv->tx_skb[q])
+		goto error;
+
+	/* Allocate rings for the aligned buffers */
+	priv->tx_buffers[q] = kcalloc(priv->num_tx_ring[q],
+				      sizeof(*priv->tx_buffers[q]), GFP_KERNEL);
+	if (!priv->tx_buffers[q])
+		goto error;
+
+	/* Allocate all RX descriptors. */
+	ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1);
+	priv->rx_ring[q] = dma_alloc_coherent(NULL, ring_size,
+					      &priv->rx_desc_dma[q],
+					      GFP_KERNEL);
+	if (!priv->rx_ring[q])
+		goto error;
+
+	priv->dirty_rx[q] = 0;
+
+	/* Allocate all TX descriptors. */
+	ring_size = sizeof(struct ravb_tx_desc) * (priv->num_tx_ring[q] + 1);
+	priv->tx_ring[q] = dma_alloc_coherent(NULL, ring_size,
+					      &priv->tx_desc_dma[q],
+					      GFP_KERNEL);
+	if (!priv->tx_ring[q])
+		goto error;
+
+	return 0;
+
+error:
+	ravb_ring_free(ndev, q);
+
+	return -ENOMEM;
+}
+
+/* E-MAC init function */
+static void ravb_emac_init(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 ecmr;
+
+	/* Receive frame limit set register */
+	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
+
+	/* PAUSE prohibition */
+	ecmr =  ravb_read(ndev, ECMR);
+	ecmr &= ECMR_DM;
+	ecmr |= ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) | ECMR_TE | ECMR_RE;
+	ravb_write(ndev, ecmr, ECMR);
+
+	ravb_set_rate(ndev);
+
+	/* Set MAC address */
+	ravb_write(ndev,
+		   (ndev->dev_addr[0] << 24) | (ndev->dev_addr[1] << 16) |
+		   (ndev->dev_addr[2] << 8)  | (ndev->dev_addr[3]), MAHR);
+	ravb_write(ndev,
+		   (ndev->dev_addr[4] << 8)  | (ndev->dev_addr[5]), MALR);
+
+	ravb_write(ndev, 1, MPR);
+
+	/* E-MAC status register clear */
+	ravb_write(ndev, ECSR_ICD | ECSR_MPD, ECSR);
+
+	/* E-MAC interrupt enable register */
+	ravb_write(ndev, ECSIPR_ICDIP | ECSIPR_MPDIP | ECSIPR_LCHNGIP, ECSIPR);
+}
+
+/* Device init function for Ethernet AVB */
+static int ravb_dmac_init(struct net_device *ndev)
+{
+	int error;
+
+	/* Set CONFIG mode */
+	error = ravb_config(ndev);
+	if (error)
+		return error;
+
+	error = ravb_ring_init(ndev, RAVB_BE);
+	if (error)
+		return error;
+	error = ravb_ring_init(ndev, RAVB_NC);
+	if (error) {
+		ravb_ring_free(ndev, RAVB_BE);
+		return error;
+	}
+
+	/* Descriptor format */
+	ravb_ring_format(ndev, RAVB_BE);
+	ravb_ring_format(ndev, RAVB_NC);
+
+#if defined(__LITTLE_ENDIAN)
+	ravb_write(ndev, ravb_read(ndev, CCC) & ~CCC_BOC, CCC);
+#else
+	ravb_write(ndev, ravb_read(ndev, CCC) | CCC_BOC, CCC);
+#endif
+
+	/* Set AVB RX */
+	ravb_write(ndev, RCR_EFFS | RCR_ENCF | RCR_ETS0 | 0x18000000, RCR);
+
+	/* Set FIFO size */
+	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC);
+
+	/* Timestamp enable */
+	ravb_write(ndev, TCCR_TFEN, TCCR);
+
+	/* Interrupt enable: */
+	/* Frame receive */
+	ravb_write(ndev, RIC0_FRE0 | RIC0_FRE1, RIC0);
+	/* Receive FIFO full warning */
+	ravb_write(ndev, RIC1_RFWE, RIC1);
+	/* Receive FIFO full error, descriptor empty */
+	ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2);
+	/* Frame transmitted, timestamp FIFO updated */
+	ravb_write(ndev, TIC_FTE0 | TIC_FTE1 | TIC_TFUE, TIC);
+
+	/* Setting the control will start the AVB-DMAC process. */
+	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) | CCC_OPC_OPERATION,
+		   CCC);
+
+	return 0;
+}
+
+/* Free TX skb function for AVB-IP */
+static int ravb_tx_free(struct net_device *ndev, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &priv->stats[q];
+	struct ravb_tx_desc *desc;
+	int free_num = 0;
+	int entry = 0;
+	u32 size;
+
+	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
+		entry = priv->dirty_tx[q] % priv->num_tx_ring[q];
+		desc = &priv->tx_ring[q][entry];
+		if (desc->die_dt != DT_FEMPTY)
+			break;
+		/* Descriptor type must be checked before all other reads */
+		dma_rmb();
+		size = le16_to_cpu(desc->ds_tagl) & TX_DS;
+		/* Free the original skb. */
+		if (priv->tx_skb[q][entry]) {
+			dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
+					 size, DMA_TO_DEVICE);
+			dev_kfree_skb_any(priv->tx_skb[q][entry]);
+			priv->tx_skb[q][entry] = NULL;
+			free_num++;
+		}
+		stats->tx_packets++;
+		stats->tx_bytes += size;
+		desc->die_dt = DT_EEMPTY;
+	}
+	return free_num;
+}
+
+static void ravb_get_tx_tstamp(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct ravb_tstamp_skb *ts_skb, *ts_skb2;
+	struct skb_shared_hwtstamps shhwtstamps;
+	struct sk_buff *skb;
+	struct timespec64 ts;
+	u16 tag, tfa_tag;
+	int count;
+	u32 tfa2;
+
+	count = (ravb_read(ndev, TSR) & TSR_TFFL) >> 8;
+	while (count--) {
+		tfa2 = ravb_read(ndev, TFA2);
+		tfa_tag = (tfa2 & TFA2_TST) >> 16;
+		ts.tv_nsec = (u64)ravb_read(ndev, TFA0);
+		ts.tv_sec = ((u64)(tfa2 & TFA2_TSV) << 32) |
+			    ravb_read(ndev, TFA1);
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+		shhwtstamps.hwtstamp = timespec64_to_ktime(ts);
+		list_for_each_entry_safe(ts_skb, ts_skb2, &priv->ts_skb_list,
+					 list) {
+			skb = ts_skb->skb;
+			tag = ts_skb->tag;
+			list_del(&ts_skb->list);
+			kfree(ts_skb);
+			if (tag == tfa_tag) {
+				skb_tstamp_tx(skb, &shhwtstamps);
+				break;
+			}
+		}
+		ravb_write(ndev, ravb_read(ndev, TCCR) | TCCR_TFR, TCCR);
+	}
+}
+
+/* Packet receive function for Ethernet AVB */
+static bool ravb_rx(struct net_device *ndev, int *quota, int q)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int entry = priv->cur_rx[q] % priv->num_rx_ring[q];
+	int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) -
+			priv->cur_rx[q];
+	struct net_device_stats *stats = &priv->stats[q];
+	struct ravb_ex_rx_desc *desc;
+	struct sk_buff *skb;
+	dma_addr_t dma_addr;
+	struct timespec64 ts;
+	u16 pkt_len = 0;
+	u8  desc_status;
+	int limit;
+
+	boguscnt = min(boguscnt, *quota);
+	limit = boguscnt;
+	desc = &priv->rx_ring[q][entry];
+	while (desc->die_dt != DT_FEMPTY) {
+		/* Descriptor type must be checked before all other reads */
+		dma_rmb();
+		desc_status = desc->msc;
+		pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
+
+		if (--boguscnt < 0)
+			break;
+
+		if (desc_status & MSC_MC)
+			stats->multicast++;
+
+		if (desc_status & (MSC_CRC | MSC_RFE | MSC_RTSF | MSC_RTLF |
+				   MSC_CEEF)) {
+			stats->rx_errors++;
+			if (desc_status & MSC_CRC)
+				stats->rx_crc_errors++;
+			if (desc_status & MSC_RFE)
+				stats->rx_frame_errors++;
+			if (desc_status & (MSC_RTLF | MSC_RTSF))
+				stats->rx_length_errors++;
+			if (desc_status & MSC_CEEF)
+				stats->rx_missed_errors++;
+		} else {
+			u32 get_ts = priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE;
+
+			skb = priv->rx_skb[q][entry];
+			priv->rx_skb[q][entry] = NULL;
+			dma_sync_single_for_cpu(&ndev->dev,
+						le32_to_cpu(desc->dptr),
+						ALIGN(PKT_BUF_SZ, 16),
+						DMA_FROM_DEVICE);
+			get_ts &= (q == RAVB_NC) ?
+					RAVB_RXTSTAMP_TYPE_V2_L2_EVENT :
+					~RAVB_RXTSTAMP_TYPE_V2_L2_EVENT;
+			if (get_ts) {
+				struct skb_shared_hwtstamps *shhwtstamps;
+
+				shhwtstamps = skb_hwtstamps(skb);
+				memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+				ts.tv_sec = ((u64) le16_to_cpu(desc->ts_sh) <<
+					     32) | le32_to_cpu(desc->ts_sl);
+				ts.tv_nsec = le32_to_cpu(desc->ts_n);
+				shhwtstamps->hwtstamp = timespec64_to_ktime(ts);
+			}
+			skb_put(skb, pkt_len);
+			skb->protocol = eth_type_trans(skb, ndev);
+			napi_gro_receive(&priv->napi[q], skb);
+			stats->rx_packets++;
+			stats->rx_bytes += pkt_len;
+		}
+
+		entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q];
+		desc = &priv->rx_ring[q][entry];
+	}
+
+	/* Refill the RX ring buffers. */
+	for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) {
+		entry = priv->dirty_rx[q] % priv->num_rx_ring[q];
+		desc = &priv->rx_ring[q][entry];
+		/* The size of the buffer should be on 16-byte boundary. */
+		desc->ds_cc = cpu_to_le16(ALIGN(PKT_BUF_SZ, 16));
+
+		if (!priv->rx_skb[q][entry]) {
+			skb = netdev_alloc_skb(ndev,
+					       PKT_BUF_SZ + RAVB_ALIGN - 1);
+			if (!skb)
+				break;	/* Better luck next round. */
+			ravb_set_buffer_align(skb);
+			dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
+					 ALIGN(PKT_BUF_SZ, 16),
+					 DMA_FROM_DEVICE);
+			dma_addr = dma_map_single(&ndev->dev, skb->data,
+						  le16_to_cpu(desc->ds_cc),
+						  DMA_FROM_DEVICE);
+			skb_checksum_none_assert(skb);
+			if (dma_mapping_error(&ndev->dev, dma_addr)) {
+				dev_kfree_skb_any(skb);
+				break;
+			}
+			desc->dptr = cpu_to_le32(dma_addr);
+			priv->rx_skb[q][entry] = skb;
+		}
+		/* Descriptor type must be set after all the above writes */
+		dma_wmb();
+		desc->die_dt = DT_FEMPTY;
+	}
+
+	*quota -= limit - (++boguscnt);
+
+	return boguscnt <= 0;
+}
+
+static void ravb_rcv_snd_disable(struct net_device *ndev)
+{
+	/* Disable TX and RX */
+	ravb_write(ndev, ravb_read(ndev, ECMR) & ~(ECMR_RE | ECMR_TE), ECMR);
+}
+
+static void ravb_rcv_snd_enable(struct net_device *ndev)
+{
+	/* Enable TX and RX */
+	ravb_write(ndev, ravb_read(ndev, ECMR) | ECMR_RE | ECMR_TE, ECMR);
+}
+
+/* function for waiting dma process finished */
+static int ravb_stop_dma(struct net_device *ndev)
+{
+	int error;
+
+	/* Wait for stopping the hardware TX process */
+	error = ravb_wait(ndev, TCCR,
+			  TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, 0);
+	if (error)
+		return error;
+
+	error = ravb_wait(ndev, CSR, CSR_TPO0 | CSR_TPO1 | CSR_TPO2 | CSR_TPO3,
+			  0);
+	if (error)
+		return error;
+
+	/* Stop the E-MAC's RX/TX processes. */
+	ravb_rcv_snd_disable(ndev);
+
+	/* Wait for stopping the RX DMA process */
+	error = ravb_wait(ndev, CSR, CSR_RPO, 0);
+	if (error)
+		return error;
+
+	/* Stop AVB-DMAC process */
+	return ravb_config(ndev);
+}
+
+/* E-MAC interrupt handler */
+static void ravb_emac_interrupt(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 ecsr, psr;
+
+	ecsr = ravb_read(ndev, ECSR);
+	ravb_write(ndev, ecsr, ECSR);	/* clear interrupt */
+	if (ecsr & ECSR_ICD)
+		ndev->stats.tx_carrier_errors++;
+	if (ecsr & ECSR_LCHNG) {
+		/* Link changed */
+		if (priv->no_avb_link)
+			return;
+		psr = ravb_read(ndev, PSR);
+		if (priv->avb_link_active_low)
+			psr ^= PSR_LMON;
+		if (!(psr & PSR_LMON)) {
+			/* DIsable RX and TX */
+			ravb_rcv_snd_disable(ndev);
+		} else {
+			/* Enable RX and TX */
+			ravb_rcv_snd_enable(ndev);
+		}
+	}
+}
+
+/* Error interrupt handler */
+static void ravb_error_interrupt(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 eis, ris2;
+
+	eis = ravb_read(ndev, EIS);
+	ravb_write(ndev, ~EIS_QFS, EIS);
+	if (eis & EIS_QFS) {
+		ris2 = ravb_read(ndev, RIS2);
+		ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF), RIS2);
+
+		/* Receive Descriptor Empty int */
+		if (ris2 & RIS2_QFF0)
+			priv->stats[RAVB_BE].rx_over_errors++;
+
+		    /* Receive Descriptor Empty int */
+		if (ris2 & RIS2_QFF1)
+			priv->stats[RAVB_NC].rx_over_errors++;
+
+		/* Receive FIFO Overflow int */
+		if (ris2 & RIS2_RFFF)
+			priv->rx_fifo_errors++;
+	}
+}
+
+static irqreturn_t ravb_interrupt(int irq, void *dev_id)
+{
+	struct net_device *ndev = dev_id;
+	struct ravb_private *priv = netdev_priv(ndev);
+	irqreturn_t result = IRQ_NONE;
+	u32 iss;
+
+	spin_lock(&priv->lock);
+	/* Get interrupt status */
+	iss = ravb_read(ndev, ISS);
+
+	/* Received and transmitted interrupts */
+	if (iss & (ISS_FRS | ISS_FTS | ISS_TFUS)) {
+		u32 ris0 = ravb_read(ndev, RIS0);
+		u32 ric0 = ravb_read(ndev, RIC0);
+		u32 tis  = ravb_read(ndev, TIS);
+		u32 tic  = ravb_read(ndev, TIC);
+		int q;
+
+		/* Timestamp updated */
+		if (tis & TIS_TFUF) {
+			ravb_write(ndev, ~TIS_TFUF, TIS);
+			ravb_get_tx_tstamp(ndev);
+			result = IRQ_HANDLED;
+		}
+
+		/* Network control and best effort queue RX/TX */
+		for (q = RAVB_NC; q >= RAVB_BE; q--) {
+			if (((ris0 & ric0) & BIT(q)) ||
+			    ((tis  & tic)  & BIT(q))) {
+				if (napi_schedule_prep(&priv->napi[q])) {
+					/* Mask RX and TX interrupts */
+					ravb_write(ndev, ric0 & ~BIT(q), RIC0);
+					ravb_write(ndev, tic  & ~BIT(q), TIC);
+					__napi_schedule(&priv->napi[q]);
+				} else {
+					netdev_warn(ndev,
+						    "ignoring interrupt, rx status 0x%08x, rx mask 0x%08x,\n",
+						    ris0, ric0);
+					netdev_warn(ndev,
+						    "                    tx status 0x%08x, tx mask 0x%08x.\n",
+						    tis, tic);
+				}
+				result = IRQ_HANDLED;
+			}
+		}
+	}
+
+	/* E-MAC status summary */
+	if (iss & ISS_MS) {
+		ravb_emac_interrupt(ndev);
+		result = IRQ_HANDLED;
+	}
+
+	/* Error status summary */
+	if (iss & ISS_ES) {
+		ravb_error_interrupt(ndev);
+		result = IRQ_HANDLED;
+	}
+
+	if (iss & ISS_CGIS)
+		result = ravb_ptp_interrupt(ndev);
+
+	mmiowb();
+	spin_unlock(&priv->lock);
+	return result;
+}
+
+static int ravb_poll(struct napi_struct *napi, int budget)
+{
+	struct net_device *ndev = napi->dev;
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+	int q = napi - priv->napi;
+	int mask = BIT(q);
+	int quota = budget;
+	u32 ris0, tis;
+
+	for (;;) {
+		tis = ravb_read(ndev, TIS);
+		ris0 = ravb_read(ndev, RIS0);
+		if (!((ris0 & mask) || (tis & mask)))
+			break;
+
+		/* Processing RX Descriptor Ring */
+		if (ris0 & mask) {
+			/* Clear RX interrupt */
+			ravb_write(ndev, ~mask, RIS0);
+			if (ravb_rx(ndev, &quota, q))
+				goto out;
+		}
+		/* Processing TX Descriptor Ring */
+		if (tis & mask) {
+			spin_lock_irqsave(&priv->lock, flags);
+			/* Clear TX interrupt */
+			ravb_write(ndev, ~mask, TIS);
+			ravb_tx_free(ndev, q);
+			netif_wake_subqueue(ndev, q);
+			mmiowb();
+			spin_unlock_irqrestore(&priv->lock, flags);
+		}
+	}
+
+	napi_complete(napi);
+
+	/* Re-enable RX/TX interrupts */
+	spin_lock_irqsave(&priv->lock, flags);
+	ravb_write(ndev, ravb_read(ndev, RIC0) | mask, RIC0);
+	ravb_write(ndev, ravb_read(ndev, TIC)  | mask,  TIC);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	/* Receive error message handling */
+	priv->rx_over_errors =  priv->stats[RAVB_BE].rx_over_errors;
+	priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors;
+	if (priv->rx_over_errors != ndev->stats.rx_over_errors) {
+		ndev->stats.rx_over_errors = priv->rx_over_errors;
+		netif_err(priv, rx_err, ndev, "Receive Descriptor Empty\n");
+	}
+	if (priv->rx_fifo_errors != ndev->stats.rx_fifo_errors) {
+		ndev->stats.rx_fifo_errors = priv->rx_fifo_errors;
+		netif_err(priv, rx_err, ndev, "Receive FIFO Overflow\n");
+	}
+out:
+	return budget - quota;
+}
+
+/* PHY state control function */
+static void ravb_adjust_link(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct phy_device *phydev = priv->phydev;
+	bool new_state = false;
+
+	if (phydev->link) {
+		if (phydev->duplex != priv->duplex) {
+			new_state = true;
+			priv->duplex = phydev->duplex;
+			ravb_set_duplex(ndev);
+		}
+
+		if (phydev->speed != priv->speed) {
+			new_state = true;
+			priv->speed = phydev->speed;
+			ravb_set_rate(ndev);
+		}
+		if (!priv->link) {
+			ravb_write(ndev, ravb_read(ndev, ECMR) & ~ECMR_TXF,
+				   ECMR);
+			new_state = true;
+			priv->link = phydev->link;
+			if (priv->no_avb_link)
+				ravb_rcv_snd_enable(ndev);
+		}
+	} else if (priv->link) {
+		new_state = true;
+		priv->link = 0;
+		priv->speed = 0;
+		priv->duplex = -1;
+		if (priv->no_avb_link)
+			ravb_rcv_snd_disable(ndev);
+	}
+
+	if (new_state && netif_msg_link(priv))
+		phy_print_status(phydev);
+}
+
+/* PHY init function */
+static int ravb_phy_init(struct net_device *ndev)
+{
+	struct device_node *np = ndev->dev.parent->of_node;
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct phy_device *phydev;
+	struct device_node *pn;
+
+	priv->link = 0;
+	priv->speed = 0;
+	priv->duplex = -1;
+
+	/* Try connecting to PHY */
+	pn = of_parse_phandle(np, "phy-handle", 0);
+	phydev = of_phy_connect(ndev, pn, ravb_adjust_link, 0,
+				priv->phy_interface);
+	if (!phydev) {
+		netdev_err(ndev, "failed to connect PHY\n");
+		return -ENOENT;
+	}
+
+	netdev_info(ndev, "attached PHY %d (IRQ %d) to driver %s\n",
+		    phydev->addr, phydev->irq, phydev->drv->name);
+
+	priv->phydev = phydev;
+
+	return 0;
+}
+
+/* PHY control start function */
+static int ravb_phy_start(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int error;
+
+	error = ravb_phy_init(ndev);
+	if (error)
+		return error;
+
+	phy_start(priv->phydev);
+
+	return 0;
+}
+
+static int ravb_get_settings(struct net_device *ndev, struct ethtool_cmd *ecmd)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int error = -ENODEV;
+	unsigned long flags;
+
+	if (priv->phydev) {
+		spin_lock_irqsave(&priv->lock, flags);
+		error = phy_ethtool_gset(priv->phydev, ecmd);
+		spin_unlock_irqrestore(&priv->lock, flags);
+	}
+
+	return error;
+}
+
+static int ravb_set_settings(struct net_device *ndev, struct ethtool_cmd *ecmd)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+	int error;
+
+	if (!priv->phydev)
+		return -ENODEV;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Disable TX and RX */
+	ravb_rcv_snd_disable(ndev);
+
+	error = phy_ethtool_sset(priv->phydev, ecmd);
+	if (error)
+		goto error_exit;
+
+	if (ecmd->duplex == DUPLEX_FULL)
+		priv->duplex = 1;
+	else
+		priv->duplex = 0;
+
+	ravb_set_duplex(ndev);
+
+error_exit:
+	mdelay(1);
+
+	/* Enable TX and RX */
+	ravb_rcv_snd_enable(ndev);
+
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_nway_reset(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int error = -ENODEV;
+	unsigned long flags;
+
+	if (priv->phydev) {
+		spin_lock_irqsave(&priv->lock, flags);
+		error = phy_start_aneg(priv->phydev);
+		spin_unlock_irqrestore(&priv->lock, flags);
+	}
+
+	return error;
+}
+
+static u32 ravb_get_msglevel(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	return priv->msg_enable;
+}
+
+static void ravb_set_msglevel(struct net_device *ndev, u32 value)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	priv->msg_enable = value;
+}
+
+static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = {
+	"rx_queue_0_current",
+	"tx_queue_0_current",
+	"rx_queue_0_dirty",
+	"tx_queue_0_dirty",
+	"rx_queue_0_packets",
+	"tx_queue_0_packets",
+	"rx_queue_0_bytes",
+	"tx_queue_0_bytes",
+	"rx_queue_0_mcast_packets",
+	"rx_queue_0_errors",
+	"rx_queue_0_crc_errors",
+	"rx_queue_0_frame_errors",
+	"rx_queue_0_length_errors",
+	"rx_queue_0_missed_errors",
+	"rx_queue_0_over_errors",
+
+	"rx_queue_1_current",
+	"tx_queue_1_current",
+	"rx_queue_1_dirty",
+	"tx_queue_1_dirty",
+	"rx_queue_1_packets",
+	"tx_queue_1_packets",
+	"rx_queue_1_bytes",
+	"tx_queue_1_bytes",
+	"rx_queue_1_mcast_packets",
+	"rx_queue_1_errors",
+	"rx_queue_1_crc_errors",
+	"rx_queue_1_frame_errors_",
+	"rx_queue_1_length_errors",
+	"rx_queue_1_missed_errors",
+	"rx_queue_1_over_errors",
+};
+
+#define RAVB_STATS_LEN	ARRAY_SIZE(ravb_gstrings_stats)
+
+static int ravb_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return RAVB_STATS_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void ravb_get_ethtool_stats(struct net_device *ndev,
+				   struct ethtool_stats *stats, u64 *data)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int i = 0;
+	int q;
+
+	/* Device-specific stats */
+	for (q = RAVB_BE; q < NUM_RX_QUEUE; q++) {
+		struct net_device_stats *stats = &priv->stats[q];
+
+		data[i++] = priv->cur_rx[q];
+		data[i++] = priv->cur_tx[q];
+		data[i++] = priv->dirty_rx[q];
+		data[i++] = priv->dirty_tx[q];
+		data[i++] = stats->rx_packets;
+		data[i++] = stats->tx_packets;
+		data[i++] = stats->rx_bytes;
+		data[i++] = stats->tx_bytes;
+		data[i++] = stats->multicast;
+		data[i++] = stats->rx_errors;
+		data[i++] = stats->rx_crc_errors;
+		data[i++] = stats->rx_frame_errors;
+		data[i++] = stats->rx_length_errors;
+		data[i++] = stats->rx_missed_errors;
+		data[i++] = stats->rx_over_errors;
+	}
+}
+
+static void ravb_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(data, *ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
+		break;
+	}
+}
+
+static void ravb_get_ringparam(struct net_device *ndev,
+			       struct ethtool_ringparam *ring)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	ring->rx_max_pending = BE_RX_RING_MAX;
+	ring->tx_max_pending = BE_TX_RING_MAX;
+	ring->rx_pending = priv->num_rx_ring[RAVB_BE];
+	ring->tx_pending = priv->num_tx_ring[RAVB_BE];
+}
+
+static int ravb_set_ringparam(struct net_device *ndev,
+			      struct ethtool_ringparam *ring)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int error;
+
+	if (ring->tx_pending > BE_TX_RING_MAX ||
+	    ring->rx_pending > BE_RX_RING_MAX ||
+	    ring->tx_pending < BE_TX_RING_MIN ||
+	    ring->rx_pending < BE_RX_RING_MIN)
+		return -EINVAL;
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	if (netif_running(ndev)) {
+		netif_device_detach(ndev);
+		/* Stop PTP Clock driver */
+		ravb_ptp_stop(ndev);
+		/* Wait for DMA stopping */
+		error = ravb_stop_dma(ndev);
+		if (error) {
+			netdev_err(ndev,
+				   "cannot set ringparam! Any AVB processes are still running?\n");
+			return error;
+		}
+		synchronize_irq(ndev->irq);
+
+		/* Free all the skb's in the RX queue and the DMA buffers. */
+		ravb_ring_free(ndev, RAVB_BE);
+		ravb_ring_free(ndev, RAVB_NC);
+	}
+
+	/* Set new parameters */
+	priv->num_rx_ring[RAVB_BE] = ring->rx_pending;
+	priv->num_tx_ring[RAVB_BE] = ring->tx_pending;
+
+	if (netif_running(ndev)) {
+		error = ravb_dmac_init(ndev);
+		if (error) {
+			netdev_err(ndev,
+				   "%s: ravb_dmac_init() failed, error %d\n",
+				   __func__, error);
+			return error;
+		}
+
+		ravb_emac_init(ndev);
+
+		/* Initialise PTP Clock driver */
+		ravb_ptp_init(ndev, priv->pdev);
+
+		netif_device_attach(ndev);
+	}
+
+	return 0;
+}
+
+static int ravb_get_ts_info(struct net_device *ndev,
+			    struct ethtool_ts_info *info)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	info->so_timestamping =
+		SOF_TIMESTAMPING_TX_SOFTWARE |
+		SOF_TIMESTAMPING_RX_SOFTWARE |
+		SOF_TIMESTAMPING_SOFTWARE |
+		SOF_TIMESTAMPING_TX_HARDWARE |
+		SOF_TIMESTAMPING_RX_HARDWARE |
+		SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
+	info->rx_filters =
+		(1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		(1 << HWTSTAMP_FILTER_ALL);
+	info->phc_index = ptp_clock_index(priv->ptp.clock);
+
+	return 0;
+}
+
+static const struct ethtool_ops ravb_ethtool_ops = {
+	.get_settings		= ravb_get_settings,
+	.set_settings		= ravb_set_settings,
+	.nway_reset		= ravb_nway_reset,
+	.get_msglevel		= ravb_get_msglevel,
+	.set_msglevel		= ravb_set_msglevel,
+	.get_link		= ethtool_op_get_link,
+	.get_strings		= ravb_get_strings,
+	.get_ethtool_stats	= ravb_get_ethtool_stats,
+	.get_sset_count		= ravb_get_sset_count,
+	.get_ringparam		= ravb_get_ringparam,
+	.set_ringparam		= ravb_set_ringparam,
+	.get_ts_info		= ravb_get_ts_info,
+};
+
+/* Network device open function for Ethernet AVB */
+static int ravb_open(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	int error;
+
+	napi_enable(&priv->napi[RAVB_BE]);
+	napi_enable(&priv->napi[RAVB_NC]);
+
+	error = request_irq(ndev->irq, ravb_interrupt, IRQF_SHARED, ndev->name,
+			    ndev);
+	if (error) {
+		netdev_err(ndev, "cannot request IRQ\n");
+		goto out_napi_off;
+	}
+
+	/* Device init */
+	error = ravb_dmac_init(ndev);
+	if (error)
+		goto out_free_irq;
+	ravb_emac_init(ndev);
+
+	/* Initialise PTP Clock driver */
+	ravb_ptp_init(ndev, priv->pdev);
+
+	netif_tx_start_all_queues(ndev);
+
+	/* PHY control start */
+	error = ravb_phy_start(ndev);
+	if (error)
+		goto out_ptp_stop;
+
+	return 0;
+
+out_ptp_stop:
+	/* Stop PTP Clock driver */
+	ravb_ptp_stop(ndev);
+out_free_irq:
+	free_irq(ndev->irq, ndev);
+out_napi_off:
+	napi_disable(&priv->napi[RAVB_NC]);
+	napi_disable(&priv->napi[RAVB_BE]);
+	return error;
+}
+
+/* Timeout function for Ethernet AVB */
+static void ravb_tx_timeout(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	netif_err(priv, tx_err, ndev,
+		  "transmit timed out, status %08x, resetting...\n",
+		  ravb_read(ndev, ISS));
+
+	/* tx_errors count up */
+	ndev->stats.tx_errors++;
+
+	schedule_work(&priv->work);
+}
+
+static void ravb_tx_timeout_work(struct work_struct *work)
+{
+	struct ravb_private *priv = container_of(work, struct ravb_private,
+						 work);
+	struct net_device *ndev = priv->ndev;
+
+	netif_tx_stop_all_queues(ndev);
+
+	/* Stop PTP Clock driver */
+	ravb_ptp_stop(ndev);
+
+	/* Wait for DMA stopping */
+	ravb_stop_dma(ndev);
+
+	ravb_ring_free(ndev, RAVB_BE);
+	ravb_ring_free(ndev, RAVB_NC);
+
+	/* Device init */
+	ravb_dmac_init(ndev);
+	ravb_emac_init(ndev);
+
+	/* Initialise PTP Clock driver */
+	ravb_ptp_init(ndev, priv->pdev);
+
+	netif_tx_start_all_queues(ndev);
+}
+
+/* Packet transmit function for Ethernet AVB */
+static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct ravb_tstamp_skb *ts_skb = NULL;
+	u16 q = skb_get_queue_mapping(skb);
+	struct ravb_tx_desc *desc;
+	unsigned long flags;
+	u32 dma_addr;
+	void *buffer;
+	u32 entry;
+	u32 tccr;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q]) {
+		netif_err(priv, tx_queued, ndev,
+			  "still transmitting with the full ring!\n");
+		netif_stop_subqueue(ndev, q);
+		spin_unlock_irqrestore(&priv->lock, flags);
+		return NETDEV_TX_BUSY;
+	}
+	entry = priv->cur_tx[q] % priv->num_tx_ring[q];
+	priv->tx_skb[q][entry] = skb;
+
+	if (skb_put_padto(skb, ETH_ZLEN))
+		goto drop;
+
+	buffer = PTR_ALIGN(priv->tx_buffers[q][entry], RAVB_ALIGN);
+	memcpy(buffer, skb->data, skb->len);
+	desc = &priv->tx_ring[q][entry];
+	desc->ds_tagl = cpu_to_le16(skb->len);
+	dma_addr = dma_map_single(&ndev->dev, buffer, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&ndev->dev, dma_addr))
+		goto drop;
+	desc->dptr = cpu_to_le32(dma_addr);
+
+	/* TX timestamp required */
+	if (q == RAVB_NC) {
+		ts_skb = kmalloc(sizeof(*ts_skb), GFP_ATOMIC);
+		if (!ts_skb) {
+			dma_unmap_single(&ndev->dev, dma_addr, skb->len,
+					 DMA_TO_DEVICE);
+			goto drop;
+		}
+		ts_skb->skb = skb;
+		ts_skb->tag = priv->ts_skb_tag++;
+		priv->ts_skb_tag &= 0x3ff;
+		list_add_tail(&ts_skb->list, &priv->ts_skb_list);
+
+		/* TAG and timestamp required flag */
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		skb_tx_timestamp(skb);
+		desc->tagh_tsr = (ts_skb->tag >> 4) | TX_TSR;
+		desc->ds_tagl |= le16_to_cpu(ts_skb->tag << 12);
+	}
+
+	/* Descriptor type must be set after all the above writes */
+	dma_wmb();
+	desc->die_dt = DT_FSINGLE;
+
+	tccr = ravb_read(ndev, TCCR);
+	if (!(tccr & (TCCR_TSRQ0 << q)))
+		ravb_write(ndev, tccr | (TCCR_TSRQ0 << q), TCCR);
+
+	priv->cur_tx[q]++;
+	if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q] &&
+	    !ravb_tx_free(ndev, q))
+		netif_stop_subqueue(ndev, q);
+
+exit:
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+	return NETDEV_TX_OK;
+
+drop:
+	dev_kfree_skb_any(skb);
+	priv->tx_skb[q][entry] = NULL;
+	goto exit;
+}
+
+static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
+			     void *accel_priv, select_queue_fallback_t fallback)
+{
+	/* If skb needs TX timestamp, it is handled in network control queue */
+	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
+							       RAVB_BE;
+
+}
+
+static struct net_device_stats *ravb_get_stats(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct net_device_stats *nstats, *stats0, *stats1;
+
+	nstats = &ndev->stats;
+	stats0 = &priv->stats[RAVB_BE];
+	stats1 = &priv->stats[RAVB_NC];
+
+	nstats->tx_dropped += ravb_read(ndev, TROCR);
+	ravb_write(ndev, 0, TROCR);	/* (write clear) */
+	nstats->collisions += ravb_read(ndev, CDCR);
+	ravb_write(ndev, 0, CDCR);	/* (write clear) */
+	nstats->tx_carrier_errors += ravb_read(ndev, LCCR);
+	ravb_write(ndev, 0, LCCR);	/* (write clear) */
+
+	nstats->tx_carrier_errors += ravb_read(ndev, CERCR);
+	ravb_write(ndev, 0, CERCR);	/* (write clear) */
+	nstats->tx_carrier_errors += ravb_read(ndev, CEECR);
+	ravb_write(ndev, 0, CEECR);	/* (write clear) */
+
+	nstats->rx_packets = stats0->rx_packets + stats1->rx_packets;
+	nstats->tx_packets = stats0->tx_packets + stats1->tx_packets;
+	nstats->rx_bytes = stats0->rx_bytes + stats1->rx_bytes;
+	nstats->tx_bytes = stats0->tx_bytes + stats1->tx_bytes;
+	nstats->multicast = stats0->multicast + stats1->multicast;
+	nstats->rx_errors = stats0->rx_errors + stats1->rx_errors;
+	nstats->rx_crc_errors = stats0->rx_crc_errors + stats1->rx_crc_errors;
+	nstats->rx_frame_errors =
+		stats0->rx_frame_errors + stats1->rx_frame_errors;
+	nstats->rx_length_errors =
+		stats0->rx_length_errors + stats1->rx_length_errors;
+	nstats->rx_missed_errors =
+		stats0->rx_missed_errors + stats1->rx_missed_errors;
+	nstats->rx_over_errors =
+		stats0->rx_over_errors + stats1->rx_over_errors;
+
+	return nstats;
+}
+
+/* Update promiscuous bit */
+static void ravb_set_rx_mode(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+	u32 ecmr;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ecmr = ravb_read(ndev, ECMR);
+	if (ndev->flags & IFF_PROMISC)
+		ecmr |=  ECMR_PRM;
+	else
+		ecmr &= ~ECMR_PRM;
+	ravb_write(ndev, ecmr, ECMR);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+/* Device close function for Ethernet AVB */
+static int ravb_close(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct ravb_tstamp_skb *ts_skb, *ts_skb2;
+
+	netif_tx_stop_all_queues(ndev);
+
+	/* Disable interrupts by clearing the interrupt masks. */
+	ravb_write(ndev, 0, RIC0);
+	ravb_write(ndev, 0, RIC1);
+	ravb_write(ndev, 0, RIC2);
+	ravb_write(ndev, 0, TIC);
+
+	/* Stop PTP Clock driver */
+	ravb_ptp_stop(ndev);
+
+	/* Set the config mode to stop the AVB-DMAC's processes */
+	if (ravb_stop_dma(ndev) < 0)
+		netdev_err(ndev,
+			   "device will be stopped after h/w processes are done.\n");
+
+	/* Clear the timestamp list */
+	list_for_each_entry_safe(ts_skb, ts_skb2, &priv->ts_skb_list, list) {
+		list_del(&ts_skb->list);
+		kfree(ts_skb);
+	}
+
+	/* PHY disconnect */
+	if (priv->phydev) {
+		phy_stop(priv->phydev);
+		phy_disconnect(priv->phydev);
+		priv->phydev = NULL;
+	}
+
+	free_irq(ndev->irq, ndev);
+
+	napi_disable(&priv->napi[RAVB_NC]);
+	napi_disable(&priv->napi[RAVB_BE]);
+
+	/* Free all the skb's in the RX queue and the DMA buffers. */
+	ravb_ring_free(ndev, RAVB_BE);
+	ravb_ring_free(ndev, RAVB_NC);
+
+	return 0;
+}
+
+static int ravb_hwtstamp_get(struct net_device *ndev, struct ifreq *req)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct hwtstamp_config config;
+
+	config.flags = 0;
+	config.tx_type = priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON :
+						HWTSTAMP_TX_OFF;
+	if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_V2_L2_EVENT)
+		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+	else if (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE_ALL)
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	else
+		config.rx_filter = HWTSTAMP_FILTER_NONE;
+
+	return copy_to_user(req->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
+}
+
+/* Control hardware time stamping */
+static int ravb_hwtstamp_set(struct net_device *ndev, struct ifreq *req)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct hwtstamp_config config;
+	u32 tstamp_rx_ctrl = RAVB_RXTSTAMP_ENABLED;
+	u32 tstamp_tx_ctrl;
+
+	if (copy_from_user(&config, req->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	/* Reserved for future extensions */
+	if (config.flags)
+		return -EINVAL;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		tstamp_tx_ctrl = 0;
+		break;
+	case HWTSTAMP_TX_ON:
+		tstamp_tx_ctrl = RAVB_TXTSTAMP_ENABLED;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		tstamp_rx_ctrl = 0;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+		tstamp_rx_ctrl |= RAVB_RXTSTAMP_TYPE_V2_L2_EVENT;
+		break;
+	default:
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		tstamp_rx_ctrl |= RAVB_RXTSTAMP_TYPE_ALL;
+	}
+
+	priv->tstamp_tx_ctrl = tstamp_tx_ctrl;
+	priv->tstamp_rx_ctrl = tstamp_rx_ctrl;
+
+	return copy_to_user(req->ifr_data, &config, sizeof(config)) ?
+		-EFAULT : 0;
+}
+
+/* ioctl to device function */
+static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct phy_device *phydev = priv->phydev;
+
+	if (!netif_running(ndev))
+		return -EINVAL;
+
+	if (!phydev)
+		return -ENODEV;
+
+	switch (cmd) {
+	case SIOCGHWTSTAMP:
+		return ravb_hwtstamp_get(ndev, req);
+	case SIOCSHWTSTAMP:
+		return ravb_hwtstamp_set(ndev, req);
+	}
+
+	return phy_mii_ioctl(phydev, req, cmd);
+}
+
+static const struct net_device_ops ravb_netdev_ops = {
+	.ndo_open		= ravb_open,
+	.ndo_stop		= ravb_close,
+	.ndo_start_xmit		= ravb_start_xmit,
+	.ndo_select_queue	= ravb_select_queue,
+	.ndo_get_stats		= ravb_get_stats,
+	.ndo_set_rx_mode	= ravb_set_rx_mode,
+	.ndo_tx_timeout		= ravb_tx_timeout,
+	.ndo_do_ioctl		= ravb_do_ioctl,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_change_mtu		= eth_change_mtu,
+};
+
+/* MDIO bus init function */
+static int ravb_mdio_init(struct ravb_private *priv)
+{
+	struct platform_device *pdev = priv->pdev;
+	struct device *dev = &pdev->dev;
+	int error;
+
+	/* Bitbang init */
+	priv->mdiobb.ops = &bb_ops;
+
+	/* MII controller setting */
+	priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb);
+	if (!priv->mii_bus)
+		return -ENOMEM;
+
+	/* Hook up MII support for ethtool */
+	priv->mii_bus->name = "ravb_mii";
+	priv->mii_bus->parent = dev;
+	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+		 pdev->name, pdev->id);
+
+	/* Register MDIO bus */
+	error = of_mdiobus_register(priv->mii_bus, dev->of_node);
+	if (error)
+		goto out_free_bus;
+
+	return 0;
+
+out_free_bus:
+	free_mdio_bitbang(priv->mii_bus);
+	return error;
+}
+
+/* MDIO bus release function */
+static int ravb_mdio_release(struct ravb_private *priv)
+{
+	/* Unregister mdio bus */
+	mdiobus_unregister(priv->mii_bus);
+
+	/* Free bitbang info */
+	free_mdio_bitbang(priv->mii_bus);
+
+	return 0;
+}
+
+static int ravb_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct ravb_private *priv;
+	struct net_device *ndev;
+	int error, irq, q;
+	struct resource *res;
+
+	if (!np) {
+		dev_err(&pdev->dev,
+			"this driver is required to be instantiated from device tree\n");
+		return -EINVAL;
+	}
+
+	/* Get base address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "invalid resource\n");
+		return -EINVAL;
+	}
+
+	ndev = alloc_etherdev_mqs(sizeof(struct ravb_private),
+				  NUM_TX_QUEUE, NUM_RX_QUEUE);
+	if (!ndev)
+		return -ENOMEM;
+
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_sync(&pdev->dev);
+
+	/* The Ether-specific entries in the device structure. */
+	ndev->base_addr = res->start;
+	ndev->dma = -1;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		error = -ENODEV;
+		goto out_release;
+	}
+	ndev->irq = irq;
+
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	priv = netdev_priv(ndev);
+	priv->ndev = ndev;
+	priv->pdev = pdev;
+	priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE;
+	priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE;
+	priv->num_tx_ring[RAVB_NC] = NC_TX_RING_SIZE;
+	priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE;
+	priv->addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->addr)) {
+		error = PTR_ERR(priv->addr);
+		goto out_release;
+	}
+
+	spin_lock_init(&priv->lock);
+	INIT_WORK(&priv->work, ravb_tx_timeout_work);
+
+	priv->phy_interface = of_get_phy_mode(np);
+
+	priv->no_avb_link = of_property_read_bool(np, "renesas,no-ether-link");
+	priv->avb_link_active_low =
+		of_property_read_bool(np, "renesas,ether-link-active-low");
+
+	/* Set function */
+	ndev->netdev_ops = &ravb_netdev_ops;
+	ndev->ethtool_ops = &ravb_ethtool_ops;
+
+	/* Set AVB config mode */
+	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) | CCC_OPC_CONFIG,
+		   CCC);
+
+	/* Set CSEL value */
+	ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_CSEL) | CCC_CSEL_HPB,
+		   CCC);
+
+	/* Set GTI value */
+	ravb_write(ndev, ((1000 << 20) / 130) & GTI_TIV, GTI);
+
+	/* Request GTI loading */
+	ravb_write(ndev, ravb_read(ndev, GCCR) | GCCR_LTI, GCCR);
+
+	/* Allocate descriptor base address table */
+	priv->desc_bat_size = sizeof(struct ravb_desc) * DBAT_ENTRY_NUM;
+	priv->desc_bat = dma_alloc_coherent(NULL, priv->desc_bat_size,
+					    &priv->desc_bat_dma, GFP_KERNEL);
+	if (!priv->desc_bat) {
+		dev_err(&ndev->dev,
+			"Cannot allocate desc base address table (size %d bytes)\n",
+			priv->desc_bat_size);
+		error = -ENOMEM;
+		goto out_release;
+	}
+	for (q = RAVB_BE; q < DBAT_ENTRY_NUM; q++)
+		priv->desc_bat[q].die_dt = DT_EOS;
+	ravb_write(ndev, priv->desc_bat_dma, DBAT);
+
+	/* Initialise HW timestamp list */
+	INIT_LIST_HEAD(&priv->ts_skb_list);
+
+	/* Debug message level */
+	priv->msg_enable = RAVB_DEF_MSG_ENABLE;
+
+	/* Read and set MAC address */
+	ravb_read_mac_address(ndev, of_get_mac_address(np));
+	if (!is_valid_ether_addr(ndev->dev_addr)) {
+		dev_warn(&pdev->dev,
+			 "no valid MAC address supplied, using a random one\n");
+		eth_hw_addr_random(ndev);
+	}
+
+	/* MDIO bus init */
+	error = ravb_mdio_init(priv);
+	if (error) {
+		dev_err(&ndev->dev, "failed to initialize MDIO\n");
+		goto out_dma_free;
+	}
+
+	netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64);
+	netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64);
+
+	/* Network device register */
+	error = register_netdev(ndev);
+	if (error)
+		goto out_napi_del;
+
+	/* Print device information */
+	netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n",
+		    (u32)ndev->base_addr, ndev->dev_addr, ndev->irq);
+
+	platform_set_drvdata(pdev, ndev);
+
+	return 0;
+
+out_napi_del:
+	netif_napi_del(&priv->napi[RAVB_NC]);
+	netif_napi_del(&priv->napi[RAVB_BE]);
+	ravb_mdio_release(priv);
+out_dma_free:
+	dma_free_coherent(NULL, priv->desc_bat_size, priv->desc_bat,
+			  priv->desc_bat_dma);
+out_release:
+	if (ndev)
+		free_netdev(ndev);
+
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+	return error;
+}
+
+static int ravb_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	dma_free_coherent(NULL, priv->desc_bat_size, priv->desc_bat,
+			  priv->desc_bat_dma);
+	/* Set reset mode */
+	ravb_write(ndev, CCC_OPC_RESET, CCC);
+	pm_runtime_put_sync(&pdev->dev);
+	unregister_netdev(ndev);
+	netif_napi_del(&priv->napi[RAVB_NC]);
+	netif_napi_del(&priv->napi[RAVB_BE]);
+	ravb_mdio_release(priv);
+	pm_runtime_disable(&pdev->dev);
+	free_netdev(ndev);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int ravb_runtime_nop(struct device *dev)
+{
+	/* Runtime PM callback shared between ->runtime_suspend()
+	 * and ->runtime_resume(). Simply returns success.
+	 *
+	 * This driver re-initializes all registers after
+	 * pm_runtime_get_sync() anyway so there is no need
+	 * to save and restore registers here.
+	 */
+	return 0;
+}
+
+static const struct dev_pm_ops ravb_dev_pm_ops = {
+	.runtime_suspend = ravb_runtime_nop,
+	.runtime_resume = ravb_runtime_nop,
+};
+
+#define RAVB_PM_OPS (&ravb_dev_pm_ops)
+#else
+#define RAVB_PM_OPS NULL
+#endif
+
+static const struct of_device_id ravb_match_table[] = {
+	{ .compatible = "renesas,etheravb-r8a7790" },
+	{ .compatible = "renesas,etheravb-r8a7794" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ravb_match_table);
+
+static struct platform_driver ravb_driver = {
+	.probe		= ravb_probe,
+	.remove		= ravb_remove,
+	.driver = {
+		.name	= "ravb",
+		.pm	= RAVB_PM_OPS,
+		.of_match_table = ravb_match_table,
+	},
+};
+
+module_platform_driver(ravb_driver);
+
+MODULE_AUTHOR("Mitsuhiro Kimura, Masaru Nagai");
+MODULE_DESCRIPTION("Renesas Ethernet AVB driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
new file mode 100644
index 000000000000..42656da50500
--- /dev/null
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -0,0 +1,357 @@
+/* PTP 1588 clock using the Renesas Ethernet AVB
+ *
+ * Copyright (C) 2013-2015 Renesas Electronics Corporation
+ * Copyright (C) 2015 Renesas Solutions Corp.
+ * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ */
+
+#include "ravb.h"
+
+static int ravb_ptp_tcr_request(struct ravb_private *priv, u32 request)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+
+	error = ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+	if (error)
+		return error;
+
+	ravb_write(ndev, ravb_read(ndev, GCCR) | request, GCCR);
+	return ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_time_read(struct ravb_private *priv, struct timespec64 *ts)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+
+	error = ravb_ptp_tcr_request(priv, GCCR_TCR_CAPTURE);
+	if (error)
+		return error;
+
+	ts->tv_nsec = ravb_read(ndev, GCT0);
+	ts->tv_sec  = ravb_read(ndev, GCT1) |
+		((s64)ravb_read(ndev, GCT2) << 32);
+
+	return 0;
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_time_write(struct ravb_private *priv,
+				const struct timespec64 *ts)
+{
+	struct net_device *ndev = priv->ndev;
+	int error;
+	u32 gccr;
+
+	error = ravb_ptp_tcr_request(priv, GCCR_TCR_RESET);
+	if (error)
+		return error;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LTO)
+		return -EBUSY;
+	ravb_write(ndev, ts->tv_nsec, GTO0);
+	ravb_write(ndev, ts->tv_sec,  GTO1);
+	ravb_write(ndev, (ts->tv_sec >> 32) & 0xffff, GTO2);
+	ravb_write(ndev, gccr | GCCR_LTO, GCCR);
+
+	return 0;
+}
+
+/* Caller must hold the lock */
+static int ravb_ptp_update_compare(struct ravb_private *priv, u32 ns)
+{
+	struct net_device *ndev = priv->ndev;
+	/* When the comparison value (GPTC.PTCV) is in range of
+	 * [x-1 to x+1] (x is the configured increment value in
+	 * GTI.TIV), it may happen that a comparison match is
+	 * not detected when the timer wraps around.
+	 */
+	u32 gti_ns_plus_1 = (priv->ptp.current_addend >> 20) + 1;
+	u32 gccr;
+
+	if (ns < gti_ns_plus_1)
+		ns = gti_ns_plus_1;
+	else if (ns > 0 - gti_ns_plus_1)
+		ns = 0 - gti_ns_plus_1;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LPTC)
+		return -EBUSY;
+	ravb_write(ndev, ns, GPTC);
+	ravb_write(ndev, gccr | GCCR_LPTC, GCCR);
+
+	return 0;
+}
+
+/* PTP clock operations */
+static int ravb_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct net_device *ndev = priv->ndev;
+	unsigned long flags;
+	u32 diff, addend;
+	bool neg_adj = false;
+	u32 gccr;
+
+	if (ppb < 0) {
+		neg_adj = true;
+		ppb = -ppb;
+	}
+	addend = priv->ptp.default_addend;
+	diff = div_u64((u64)addend * ppb, NSEC_PER_SEC);
+
+	addend = neg_adj ? addend - diff : addend + diff;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	priv->ptp.current_addend = addend;
+
+	gccr = ravb_read(ndev, GCCR);
+	if (gccr & GCCR_LTI)
+		return -EBUSY;
+	ravb_write(ndev, addend & GTI_TIV, GTI);
+	ravb_write(ndev, gccr | GCCR_LTI, GCCR);
+
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int ravb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct timespec64 ts;
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_read(priv, &ts);
+	if (!error) {
+		u64 now = ktime_to_ns(timespec64_to_ktime(ts));
+
+		ts = ns_to_timespec64(now + delta);
+		error = ravb_ptp_time_write(priv, &ts);
+	}
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_read(priv, ts);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_settime64(struct ptp_clock_info *ptp,
+			      const struct timespec64 *ts)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	unsigned long flags;
+	int error;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	error = ravb_ptp_time_write(priv, ts);
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_extts(struct ptp_clock_info *ptp,
+			  struct ptp_extts_request *req, int on)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct net_device *ndev = priv->ndev;
+	unsigned long flags;
+	u32 gic;
+
+	if (req->index)
+		return -EINVAL;
+
+	if (priv->ptp.extts[req->index] == on)
+		return 0;
+	priv->ptp.extts[req->index] = on;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	gic = ravb_read(ndev, GIC);
+	if (on)
+		gic |= GIC_PTCE;
+	else
+		gic &= ~GIC_PTCE;
+	ravb_write(ndev, gic, GIC);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return 0;
+}
+
+static int ravb_ptp_perout(struct ptp_clock_info *ptp,
+			   struct ptp_perout_request *req, int on)
+{
+	struct ravb_private *priv = container_of(ptp, struct ravb_private,
+						 ptp.info);
+	struct net_device *ndev = priv->ndev;
+	struct ravb_ptp_perout *perout;
+	unsigned long flags;
+	int error = 0;
+	u32 gic;
+
+	if (req->index)
+		return -EINVAL;
+
+	if (on) {
+		u64 start_ns;
+		u64 period_ns;
+
+		start_ns = req->start.sec * NSEC_PER_SEC + req->start.nsec;
+		period_ns = req->period.sec * NSEC_PER_SEC + req->period.nsec;
+
+		if (start_ns > U32_MAX) {
+			netdev_warn(ndev,
+				    "ptp: start value (nsec) is over limit. Maximum size of start is only 32 bits\n");
+			return -ERANGE;
+		}
+
+		if (period_ns > U32_MAX) {
+			netdev_warn(ndev,
+				    "ptp: period value (nsec) is over limit. Maximum size of period is only 32 bits\n");
+			return -ERANGE;
+		}
+
+		spin_lock_irqsave(&priv->lock, flags);
+
+		perout = &priv->ptp.perout[req->index];
+		perout->target = (u32)start_ns;
+		perout->period = (u32)period_ns;
+		error = ravb_ptp_update_compare(priv, (u32)start_ns);
+		if (!error) {
+			/* Unmask interrupt */
+			gic = ravb_read(ndev, GIC);
+			gic |= GIC_PTME;
+			ravb_write(ndev, gic, GIC);
+		}
+	} else	{
+		spin_lock_irqsave(&priv->lock, flags);
+
+		perout = &priv->ptp.perout[req->index];
+		perout->period = 0;
+
+		/* Mask interrupt */
+		gic = ravb_read(ndev, GIC);
+		gic &= ~GIC_PTME;
+		ravb_write(ndev, gic, GIC);
+	}
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	return error;
+}
+
+static int ravb_ptp_enable(struct ptp_clock_info *ptp,
+			   struct ptp_clock_request *req, int on)
+{
+	switch (req->type) {
+	case PTP_CLK_REQ_EXTTS:
+		return ravb_ptp_extts(ptp, &req->extts, on);
+	case PTP_CLK_REQ_PEROUT:
+		return ravb_ptp_perout(ptp, &req->perout, on);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct ptp_clock_info ravb_ptp_info = {
+	.owner		= THIS_MODULE,
+	.name		= "ravb clock",
+	.max_adj	= 50000000,
+	.n_ext_ts	= N_EXT_TS,
+	.n_per_out	= N_PER_OUT,
+	.adjfreq	= ravb_ptp_adjfreq,
+	.adjtime	= ravb_ptp_adjtime,
+	.gettime64	= ravb_ptp_gettime64,
+	.settime64	= ravb_ptp_settime64,
+	.enable		= ravb_ptp_enable,
+};
+
+/* Caller must hold the lock */
+irqreturn_t ravb_ptp_interrupt(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	u32 gis = ravb_read(ndev, GIS);
+
+	gis &= ravb_read(ndev, GIC);
+	if (gis & GIS_PTCF) {
+		struct ptp_clock_event event;
+
+		event.type = PTP_CLOCK_EXTTS;
+		event.index = 0;
+		event.timestamp = ravb_read(ndev, GCPT);
+		ptp_clock_event(priv->ptp.clock, &event);
+	}
+	if (gis & GIS_PTMF) {
+		struct ravb_ptp_perout *perout = priv->ptp.perout;
+
+		if (perout->period) {
+			perout->target += perout->period;
+			ravb_ptp_update_compare(priv, perout->target);
+		}
+	}
+
+	if (gis) {
+		ravb_write(ndev, ~gis, GIS);
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	unsigned long flags;
+	u32 gccr;
+
+	priv->ptp.info = ravb_ptp_info;
+
+	priv->ptp.default_addend = ravb_read(ndev, GTI);
+	priv->ptp.current_addend = priv->ptp.default_addend;
+
+	spin_lock_irqsave(&priv->lock, flags);
+	ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
+	gccr = ravb_read(ndev, GCCR) & ~GCCR_TCSS;
+	ravb_write(ndev, gccr | GCCR_TCSS_ADJGPTP, GCCR);
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev);
+}
+
+void ravb_ptp_stop(struct net_device *ndev)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	ravb_write(ndev, 0, GIC);
+	ravb_write(ndev, 0, GIS);
+
+	ptp_clock_unregister(priv->ptp.clock);
+}
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index ec251531bd9f..2d8578cade03 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -181,7 +181,7 @@ struct rocker_desc_info {
 	size_t data_size;
 	size_t tlv_size;
 	struct rocker_desc *desc;
-	DEFINE_DMA_UNMAP_ADDR(mapaddr);
+	dma_addr_t mapaddr;
 };
 
 struct rocker_dma_ring_info {
@@ -225,6 +225,7 @@ struct rocker_port {
 	struct napi_struct napi_rx;
 	struct rocker_dma_ring_info tx_ring;
 	struct rocker_dma_ring_info rx_ring;
+	struct list_head trans_mem;
 };
 
 struct rocker {
@@ -236,21 +237,21 @@ struct rocker {
 	struct {
 		u64 id;
 	} hw;
-	spinlock_t cmd_ring_lock;
+	spinlock_t cmd_ring_lock;		/* for cmd ring accesses */
 	struct rocker_dma_ring_info cmd_ring;
 	struct rocker_dma_ring_info event_ring;
 	DECLARE_HASHTABLE(flow_tbl, 16);
-	spinlock_t flow_tbl_lock;
+	spinlock_t flow_tbl_lock;		/* for flow tbl accesses */
 	u64 flow_tbl_next_cookie;
 	DECLARE_HASHTABLE(group_tbl, 16);
-	spinlock_t group_tbl_lock;
+	spinlock_t group_tbl_lock;		/* for group tbl accesses */
 	DECLARE_HASHTABLE(fdb_tbl, 16);
-	spinlock_t fdb_tbl_lock;
+	spinlock_t fdb_tbl_lock;		/* for fdb tbl accesses */
 	unsigned long internal_vlan_bitmap[ROCKER_INTERNAL_VLAN_BITMAP_LEN];
 	DECLARE_HASHTABLE(internal_vlan_tbl, 8);
-	spinlock_t internal_vlan_tbl_lock;
+	spinlock_t internal_vlan_tbl_lock;	/* for vlan tbl accesses */
 	DECLARE_HASHTABLE(neigh_tbl, 16);
-	spinlock_t neigh_tbl_lock;
+	spinlock_t neigh_tbl_lock;		/* for neigh tbl accesses */
 	u32 neigh_tbl_next_index;
 };
 
@@ -294,7 +295,7 @@ static bool rocker_vlan_id_is_internal(__be16 vlan_id)
 	return (_vlan_id >= start && _vlan_id <= end);
 }
 
-static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port,
+static __be16 rocker_port_vid_to_vlan(const struct rocker_port *rocker_port,
 				      u16 vid, bool *pop_vlan)
 {
 	__be16 vlan_id;
@@ -311,7 +312,7 @@ static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port,
 	return vlan_id;
 }
 
-static u16 rocker_port_vlan_to_vid(struct rocker_port *rocker_port,
+static u16 rocker_port_vlan_to_vid(const struct rocker_port *rocker_port,
 				   __be16 vlan_id)
 {
 	if (rocker_vlan_id_is_internal(vlan_id))
@@ -320,11 +321,88 @@ static u16 rocker_port_vlan_to_vid(struct rocker_port *rocker_port,
 	return ntohs(vlan_id);
 }
 
-static bool rocker_port_is_bridged(struct rocker_port *rocker_port)
+static bool rocker_port_is_bridged(const struct rocker_port *rocker_port)
 {
 	return !!rocker_port->bridge_dev;
 }
 
+#define ROCKER_OP_FLAG_REMOVE		BIT(0)
+#define ROCKER_OP_FLAG_NOWAIT		BIT(1)
+#define ROCKER_OP_FLAG_LEARNED		BIT(2)
+#define ROCKER_OP_FLAG_REFRESH		BIT(3)
+
+static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port,
+				     enum switchdev_trans trans, int flags,
+				     size_t size)
+{
+	struct list_head *elem = NULL;
+	gfp_t gfp_flags = (flags & ROCKER_OP_FLAG_NOWAIT) ?
+			  GFP_ATOMIC : GFP_KERNEL;
+
+	/* If in transaction prepare phase, allocate the memory
+	 * and enqueue it on a per-port list.  If in transaction
+	 * commit phase, dequeue the memory from the per-port list
+	 * rather than re-allocating the memory.  The idea is the
+	 * driver code paths for prepare and commit are identical
+	 * so the memory allocated in the prepare phase is the
+	 * memory used in the commit phase.
+	 */
+
+	switch (trans) {
+	case SWITCHDEV_TRANS_PREPARE:
+		elem = kzalloc(size + sizeof(*elem), gfp_flags);
+		if (!elem)
+			return NULL;
+		list_add_tail(elem, &rocker_port->trans_mem);
+		break;
+	case SWITCHDEV_TRANS_COMMIT:
+		BUG_ON(list_empty(&rocker_port->trans_mem));
+		elem = rocker_port->trans_mem.next;
+		list_del_init(elem);
+		break;
+	case SWITCHDEV_TRANS_NONE:
+		elem = kzalloc(size + sizeof(*elem), gfp_flags);
+		if (elem)
+			INIT_LIST_HEAD(elem);
+		break;
+	default:
+		break;
+	}
+
+	return elem ? elem + 1 : NULL;
+}
+
+static void *rocker_port_kzalloc(struct rocker_port *rocker_port,
+				 enum switchdev_trans trans, int flags,
+				 size_t size)
+{
+	return __rocker_port_mem_alloc(rocker_port, trans, flags, size);
+}
+
+static void *rocker_port_kcalloc(struct rocker_port *rocker_port,
+				 enum switchdev_trans trans, int flags,
+				 size_t n, size_t size)
+{
+	return __rocker_port_mem_alloc(rocker_port, trans, flags, n * size);
+}
+
+static void rocker_port_kfree(enum switchdev_trans trans, const void *mem)
+{
+	struct list_head *elem;
+
+	/* Frees are ignored if in transaction prepare phase.  The
+	 * memory remains on the per-port list until freed in the
+	 * commit phase.
+	 */
+
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		return;
+
+	elem = (struct list_head *)mem - 1;
+	BUG_ON(!list_empty(elem));
+	kfree(elem);
+}
+
 struct rocker_wait {
 	wait_queue_head_t wait;
 	bool done;
@@ -343,20 +421,23 @@ static void rocker_wait_init(struct rocker_wait *wait)
 	rocker_wait_reset(wait);
 }
 
-static struct rocker_wait *rocker_wait_create(gfp_t gfp)
+static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port,
+					      enum switchdev_trans trans,
+					      int flags)
 {
 	struct rocker_wait *wait;
 
-	wait = kmalloc(sizeof(*wait), gfp);
+	wait = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*wait));
 	if (!wait)
 		return NULL;
 	rocker_wait_init(wait);
 	return wait;
 }
 
-static void rocker_wait_destroy(struct rocker_wait *work)
+static void rocker_wait_destroy(enum switchdev_trans trans,
+				struct rocker_wait *wait)
 {
-	kfree(work);
+	rocker_port_kfree(trans, wait);
 }
 
 static bool rocker_wait_event_timeout(struct rocker_wait *wait,
@@ -374,18 +455,18 @@ static void rocker_wait_wake_up(struct rocker_wait *wait)
 	wake_up(&wait->wait);
 }
 
-static u32 rocker_msix_vector(struct rocker *rocker, unsigned int vector)
+static u32 rocker_msix_vector(const struct rocker *rocker, unsigned int vector)
 {
 	return rocker->msix_entries[vector].vector;
 }
 
-static u32 rocker_msix_tx_vector(struct rocker_port *rocker_port)
+static u32 rocker_msix_tx_vector(const struct rocker_port *rocker_port)
 {
 	return rocker_msix_vector(rocker_port->rocker,
 				  ROCKER_MSIX_VEC_TX(rocker_port->port_number));
 }
 
-static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port)
+static u32 rocker_msix_rx_vector(const struct rocker_port *rocker_port)
 {
 	return rocker_msix_vector(rocker_port->rocker,
 				  ROCKER_MSIX_VEC_RX(rocker_port->port_number));
@@ -404,9 +485,9 @@ static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port)
  * HW basic testing functions
  *****************************/
 
-static int rocker_reg_test(struct rocker *rocker)
+static int rocker_reg_test(const struct rocker *rocker)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct pci_dev *pdev = rocker->pdev;
 	u64 test_reg;
 	u64 rnd;
 
@@ -434,12 +515,12 @@ static int rocker_reg_test(struct rocker *rocker)
 	return 0;
 }
 
-static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait,
-			       u32 test_type, dma_addr_t dma_handle,
-			       unsigned char *buf, unsigned char *expect,
-			       size_t size)
+static int rocker_dma_test_one(const struct rocker *rocker,
+			       struct rocker_wait *wait, u32 test_type,
+			       dma_addr_t dma_handle, const unsigned char *buf,
+			       const unsigned char *expect, size_t size)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct pci_dev *pdev = rocker->pdev;
 	int i;
 
 	rocker_wait_reset(wait);
@@ -463,7 +544,7 @@ static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait,
 #define ROCKER_TEST_DMA_BUF_SIZE (PAGE_SIZE * 4)
 #define ROCKER_TEST_DMA_FILL_PATTERN 0x96
 
-static int rocker_dma_test_offset(struct rocker *rocker,
+static int rocker_dma_test_offset(const struct rocker *rocker,
 				  struct rocker_wait *wait, int offset)
 {
 	struct pci_dev *pdev = rocker->pdev;
@@ -523,7 +604,8 @@ free_alloc:
 	return err;
 }
 
-static int rocker_dma_test(struct rocker *rocker, struct rocker_wait *wait)
+static int rocker_dma_test(const struct rocker *rocker,
+			   struct rocker_wait *wait)
 {
 	int i;
 	int err;
@@ -545,9 +627,9 @@ static irqreturn_t rocker_test_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int rocker_basic_hw_test(struct rocker *rocker)
+static int rocker_basic_hw_test(const struct rocker *rocker)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct pci_dev *pdev = rocker->pdev;
 	struct rocker_wait wait;
 	int err;
 
@@ -680,7 +762,7 @@ static u64 rocker_tlv_get_u64(const struct rocker_tlv *tlv)
 	return *(u64 *) rocker_tlv_data(tlv);
 }
 
-static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype,
+static void rocker_tlv_parse(const struct rocker_tlv **tb, int maxtype,
 			     const char *buf, int buf_len)
 {
 	const struct rocker_tlv *tlv;
@@ -693,19 +775,19 @@ static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype,
 		u32 type = rocker_tlv_type(tlv);
 
 		if (type > 0 && type <= maxtype)
-			tb[type] = (struct rocker_tlv *) tlv;
+			tb[type] = tlv;
 	}
 }
 
-static void rocker_tlv_parse_nested(struct rocker_tlv **tb, int maxtype,
+static void rocker_tlv_parse_nested(const struct rocker_tlv **tb, int maxtype,
 				    const struct rocker_tlv *tlv)
 {
 	rocker_tlv_parse(tb, maxtype, rocker_tlv_data(tlv),
 			 rocker_tlv_len(tlv));
 }
 
-static void rocker_tlv_parse_desc(struct rocker_tlv **tb, int maxtype,
-				  struct rocker_desc_info *desc_info)
+static void rocker_tlv_parse_desc(const struct rocker_tlv **tb, int maxtype,
+				  const struct rocker_desc_info *desc_info)
 {
 	rocker_tlv_parse(tb, maxtype, desc_info->data,
 			 desc_info->desc->tlv_size);
@@ -790,9 +872,9 @@ static void rocker_tlv_nest_end(struct rocker_desc_info *desc_info,
 }
 
 static void rocker_tlv_nest_cancel(struct rocker_desc_info *desc_info,
-				   struct rocker_tlv *start)
+				   const struct rocker_tlv *start)
 {
-	desc_info->tlv_size = (char *) start - desc_info->data;
+	desc_info->tlv_size = (const char *) start - desc_info->data;
 }
 
 /******************************************
@@ -804,7 +886,7 @@ static u32 __pos_inc(u32 pos, size_t limit)
 	return ++pos == limit ? 0 : pos;
 }
 
-static int rocker_desc_err(struct rocker_desc_info *desc_info)
+static int rocker_desc_err(const struct rocker_desc_info *desc_info)
 {
 	int err = desc_info->desc->comp_err & ~ROCKER_DMA_DESC_COMP_ERR_GEN;
 
@@ -832,31 +914,31 @@ static int rocker_desc_err(struct rocker_desc_info *desc_info)
 	return -EINVAL;
 }
 
-static void rocker_desc_gen_clear(struct rocker_desc_info *desc_info)
+static void rocker_desc_gen_clear(const struct rocker_desc_info *desc_info)
 {
 	desc_info->desc->comp_err &= ~ROCKER_DMA_DESC_COMP_ERR_GEN;
 }
 
-static bool rocker_desc_gen(struct rocker_desc_info *desc_info)
+static bool rocker_desc_gen(const struct rocker_desc_info *desc_info)
 {
 	u32 comp_err = desc_info->desc->comp_err;
 
 	return comp_err & ROCKER_DMA_DESC_COMP_ERR_GEN ? true : false;
 }
 
-static void *rocker_desc_cookie_ptr_get(struct rocker_desc_info *desc_info)
+static void *rocker_desc_cookie_ptr_get(const struct rocker_desc_info *desc_info)
 {
 	return (void *)(uintptr_t)desc_info->desc->cookie;
 }
 
-static void rocker_desc_cookie_ptr_set(struct rocker_desc_info *desc_info,
+static void rocker_desc_cookie_ptr_set(const struct rocker_desc_info *desc_info,
 				       void *ptr)
 {
 	desc_info->desc->cookie = (uintptr_t) ptr;
 }
 
 static struct rocker_desc_info *
-rocker_desc_head_get(struct rocker_dma_ring_info *info)
+rocker_desc_head_get(const struct rocker_dma_ring_info *info)
 {
 	static struct rocker_desc_info *desc_info;
 	u32 head = __pos_inc(info->head, info->size);
@@ -868,15 +950,15 @@ rocker_desc_head_get(struct rocker_dma_ring_info *info)
 	return desc_info;
 }
 
-static void rocker_desc_commit(struct rocker_desc_info *desc_info)
+static void rocker_desc_commit(const struct rocker_desc_info *desc_info)
 {
 	desc_info->desc->buf_size = desc_info->data_size;
 	desc_info->desc->tlv_size = desc_info->tlv_size;
 }
 
-static void rocker_desc_head_set(struct rocker *rocker,
+static void rocker_desc_head_set(const struct rocker *rocker,
 				 struct rocker_dma_ring_info *info,
-				 struct rocker_desc_info *desc_info)
+				 const struct rocker_desc_info *desc_info)
 {
 	u32 head = __pos_inc(info->head, info->size);
 
@@ -901,8 +983,8 @@ rocker_desc_tail_get(struct rocker_dma_ring_info *info)
 	return desc_info;
 }
 
-static void rocker_dma_ring_credits_set(struct rocker *rocker,
-					struct rocker_dma_ring_info *info,
+static void rocker_dma_ring_credits_set(const struct rocker *rocker,
+					const struct rocker_dma_ring_info *info,
 					u32 credits)
 {
 	if (credits)
@@ -915,7 +997,7 @@ static unsigned long rocker_dma_ring_size_fix(size_t size)
 		   min(roundup_pow_of_two(size), ROCKER_DMA_SIZE_MAX));
 }
 
-static int rocker_dma_ring_create(struct rocker *rocker,
+static int rocker_dma_ring_create(const struct rocker *rocker,
 				  unsigned int type,
 				  size_t size,
 				  struct rocker_dma_ring_info *info)
@@ -951,8 +1033,8 @@ static int rocker_dma_ring_create(struct rocker *rocker,
 	return 0;
 }
 
-static void rocker_dma_ring_destroy(struct rocker *rocker,
-				    struct rocker_dma_ring_info *info)
+static void rocker_dma_ring_destroy(const struct rocker *rocker,
+				    const struct rocker_dma_ring_info *info)
 {
 	rocker_write64(rocker, DMA_DESC_ADDR(info->type), 0);
 
@@ -962,7 +1044,7 @@ static void rocker_dma_ring_destroy(struct rocker *rocker,
 	kfree(info->desc_info);
 }
 
-static void rocker_dma_ring_pass_to_producer(struct rocker *rocker,
+static void rocker_dma_ring_pass_to_producer(const struct rocker *rocker,
 					     struct rocker_dma_ring_info *info)
 {
 	int i;
@@ -977,8 +1059,8 @@ static void rocker_dma_ring_pass_to_producer(struct rocker *rocker,
 	rocker_desc_commit(&info->desc_info[i]);
 }
 
-static int rocker_dma_ring_bufs_alloc(struct rocker *rocker,
-				      struct rocker_dma_ring_info *info,
+static int rocker_dma_ring_bufs_alloc(const struct rocker *rocker,
+				      const struct rocker_dma_ring_info *info,
 				      int direction, size_t buf_size)
 {
 	struct pci_dev *pdev = rocker->pdev;
@@ -1015,7 +1097,7 @@ static int rocker_dma_ring_bufs_alloc(struct rocker *rocker,
 
 rollback:
 	for (i--; i >= 0; i--) {
-		struct rocker_desc_info *desc_info = &info->desc_info[i];
+		const struct rocker_desc_info *desc_info = &info->desc_info[i];
 
 		pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr),
 				 desc_info->data_size, direction);
@@ -1024,15 +1106,15 @@ rollback:
 	return err;
 }
 
-static void rocker_dma_ring_bufs_free(struct rocker *rocker,
-				      struct rocker_dma_ring_info *info,
+static void rocker_dma_ring_bufs_free(const struct rocker *rocker,
+				      const struct rocker_dma_ring_info *info,
 				      int direction)
 {
 	struct pci_dev *pdev = rocker->pdev;
 	int i;
 
 	for (i = 0; i < info->size; i++) {
-		struct rocker_desc_info *desc_info = &info->desc_info[i];
+		const struct rocker_desc_info *desc_info = &info->desc_info[i];
 		struct rocker_desc *desc = &info->desc[i];
 
 		desc->buf_addr = 0;
@@ -1045,7 +1127,7 @@ static void rocker_dma_ring_bufs_free(struct rocker *rocker,
 
 static int rocker_dma_rings_init(struct rocker *rocker)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct pci_dev *pdev = rocker->pdev;
 	int err;
 
 	err = rocker_dma_ring_create(rocker, ROCKER_DMA_CMD,
@@ -1102,11 +1184,11 @@ static void rocker_dma_rings_fini(struct rocker *rocker)
 	rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
 }
 
-static int rocker_dma_rx_ring_skb_map(struct rocker *rocker,
-				      struct rocker_port *rocker_port,
+static int rocker_dma_rx_ring_skb_map(const struct rocker_port *rocker_port,
 				      struct rocker_desc_info *desc_info,
 				      struct sk_buff *skb, size_t buf_len)
 {
+	const struct rocker *rocker = rocker_port->rocker;
 	struct pci_dev *pdev = rocker->pdev;
 	dma_addr_t dma_handle;
 
@@ -1126,13 +1208,12 @@ tlv_put_failure:
 	return -EMSGSIZE;
 }
 
-static size_t rocker_port_rx_buf_len(struct rocker_port *rocker_port)
+static size_t rocker_port_rx_buf_len(const struct rocker_port *rocker_port)
 {
 	return rocker_port->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 }
 
-static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker,
-					struct rocker_port *rocker_port,
+static int rocker_dma_rx_ring_skb_alloc(const struct rocker_port *rocker_port,
 					struct rocker_desc_info *desc_info)
 {
 	struct net_device *dev = rocker_port->dev;
@@ -1149,8 +1230,7 @@ static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker,
 	skb = netdev_alloc_skb_ip_align(dev, buf_len);
 	if (!skb)
 		return -ENOMEM;
-	err = rocker_dma_rx_ring_skb_map(rocker, rocker_port, desc_info,
-					 skb, buf_len);
+	err = rocker_dma_rx_ring_skb_map(rocker_port, desc_info, skb, buf_len);
 	if (err) {
 		dev_kfree_skb_any(skb);
 		return err;
@@ -1159,8 +1239,8 @@ static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker,
 	return 0;
 }
 
-static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker,
-					 struct rocker_tlv **attrs)
+static void rocker_dma_rx_ring_skb_unmap(const struct rocker *rocker,
+					 const struct rocker_tlv **attrs)
 {
 	struct pci_dev *pdev = rocker->pdev;
 	dma_addr_t dma_handle;
@@ -1174,10 +1254,10 @@ static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker,
 	pci_unmap_single(pdev, dma_handle, len, PCI_DMA_FROMDEVICE);
 }
 
-static void rocker_dma_rx_ring_skb_free(struct rocker *rocker,
-					struct rocker_desc_info *desc_info)
+static void rocker_dma_rx_ring_skb_free(const struct rocker *rocker,
+					const struct rocker_desc_info *desc_info)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
 	struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info);
 
 	if (!skb)
@@ -1187,15 +1267,15 @@ static void rocker_dma_rx_ring_skb_free(struct rocker *rocker,
 	dev_kfree_skb_any(skb);
 }
 
-static int rocker_dma_rx_ring_skbs_alloc(struct rocker *rocker,
-					 struct rocker_port *rocker_port)
+static int rocker_dma_rx_ring_skbs_alloc(const struct rocker_port *rocker_port)
 {
-	struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	const struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	const struct rocker *rocker = rocker_port->rocker;
 	int i;
 	int err;
 
 	for (i = 0; i < rx_ring->size; i++) {
-		err = rocker_dma_rx_ring_skb_alloc(rocker, rocker_port,
+		err = rocker_dma_rx_ring_skb_alloc(rocker_port,
 						   &rx_ring->desc_info[i]);
 		if (err)
 			goto rollback;
@@ -1208,10 +1288,10 @@ rollback:
 	return err;
 }
 
-static void rocker_dma_rx_ring_skbs_free(struct rocker *rocker,
-					 struct rocker_port *rocker_port)
+static void rocker_dma_rx_ring_skbs_free(const struct rocker_port *rocker_port)
 {
-	struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	const struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+	const struct rocker *rocker = rocker_port->rocker;
 	int i;
 
 	for (i = 0; i < rx_ring->size; i++)
@@ -1257,7 +1337,7 @@ static int rocker_port_dma_rings_init(struct rocker_port *rocker_port)
 		goto err_dma_rx_ring_bufs_alloc;
 	}
 
-	err = rocker_dma_rx_ring_skbs_alloc(rocker, rocker_port);
+	err = rocker_dma_rx_ring_skbs_alloc(rocker_port);
 	if (err) {
 		netdev_err(rocker_port->dev, "failed to alloc rx dma ring skbs\n");
 		goto err_dma_rx_ring_skbs_alloc;
@@ -1283,7 +1363,7 @@ static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port)
 {
 	struct rocker *rocker = rocker_port->rocker;
 
-	rocker_dma_rx_ring_skbs_free(rocker, rocker_port);
+	rocker_dma_rx_ring_skbs_free(rocker_port);
 	rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring,
 				  PCI_DMA_BIDIRECTIONAL);
 	rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring);
@@ -1292,7 +1372,8 @@ static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port)
 	rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring);
 }
 
-static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable)
+static void rocker_port_set_enable(const struct rocker_port *rocker_port,
+				   bool enable)
 {
 	u64 val = rocker_read64(rocker_port->rocker, PORT_PHYS_ENABLE);
 
@@ -1310,7 +1391,7 @@ static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable)
 static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id)
 {
 	struct rocker *rocker = dev_id;
-	struct rocker_desc_info *desc_info;
+	const struct rocker_desc_info *desc_info;
 	struct rocker_wait *wait;
 	u32 credits = 0;
 
@@ -1319,7 +1400,7 @@ static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id)
 		wait = rocker_desc_cookie_ptr_get(desc_info);
 		if (wait->nowait) {
 			rocker_desc_gen_clear(desc_info);
-			rocker_wait_destroy(wait);
+			rocker_wait_destroy(SWITCHDEV_TRANS_NONE, wait);
 		} else {
 			rocker_wait_wake_up(wait);
 		}
@@ -1331,22 +1412,22 @@ static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void rocker_port_link_up(struct rocker_port *rocker_port)
+static void rocker_port_link_up(const struct rocker_port *rocker_port)
 {
 	netif_carrier_on(rocker_port->dev);
 	netdev_info(rocker_port->dev, "Link is up\n");
 }
 
-static void rocker_port_link_down(struct rocker_port *rocker_port)
+static void rocker_port_link_down(const struct rocker_port *rocker_port)
 {
 	netif_carrier_off(rocker_port->dev);
 	netdev_info(rocker_port->dev, "Link is down\n");
 }
 
-static int rocker_event_link_change(struct rocker *rocker,
+static int rocker_event_link_change(const struct rocker *rocker,
 				    const struct rocker_tlv *info)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_EVENT_LINK_CHANGED_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_LINK_CHANGED_MAX + 1];
 	unsigned int port_number;
 	bool link_up;
 	struct rocker_port *rocker_port;
@@ -1373,22 +1454,18 @@ static int rocker_event_link_change(struct rocker *rocker,
 	return 0;
 }
 
-#define ROCKER_OP_FLAG_REMOVE		BIT(0)
-#define ROCKER_OP_FLAG_NOWAIT		BIT(1)
-#define ROCKER_OP_FLAG_LEARNED		BIT(2)
-#define ROCKER_OP_FLAG_REFRESH		BIT(3)
-
 static int rocker_port_fdb(struct rocker_port *rocker_port,
+			   enum switchdev_trans trans,
 			   const unsigned char *addr,
 			   __be16 vlan_id, int flags);
 
-static int rocker_event_mac_vlan_seen(struct rocker *rocker,
+static int rocker_event_mac_vlan_seen(const struct rocker *rocker,
 				      const struct rocker_tlv *info)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1];
 	unsigned int port_number;
 	struct rocker_port *rocker_port;
-	unsigned char *addr;
+	const unsigned char *addr;
 	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_LEARNED;
 	__be16 vlan_id;
 
@@ -1411,14 +1488,15 @@ static int rocker_event_mac_vlan_seen(struct rocker *rocker,
 	    rocker_port->stp_state != BR_STATE_FORWARDING)
 		return 0;
 
-	return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+	return rocker_port_fdb(rocker_port, SWITCHDEV_TRANS_NONE,
+			       addr, vlan_id, flags);
 }
 
-static int rocker_event_process(struct rocker *rocker,
-				struct rocker_desc_info *desc_info)
+static int rocker_event_process(const struct rocker *rocker,
+				const struct rocker_desc_info *desc_info)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAX + 1];
-	struct rocker_tlv *info;
+	const struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAX + 1];
+	const struct rocker_tlv *info;
 	u16 type;
 
 	rocker_tlv_parse_desc(attrs, ROCKER_TLV_EVENT_MAX, desc_info);
@@ -1442,8 +1520,8 @@ static int rocker_event_process(struct rocker *rocker,
 static irqreturn_t rocker_event_irq_handler(int irq, void *dev_id)
 {
 	struct rocker *rocker = dev_id;
-	struct pci_dev *pdev = rocker->pdev;
-	struct rocker_desc_info *desc_info;
+	const struct pci_dev *pdev = rocker->pdev;
+	const struct rocker_desc_info *desc_info;
 	u32 credits = 0;
 	int err;
 
@@ -1487,65 +1565,75 @@ static irqreturn_t rocker_rx_irq_handler(int irq, void *dev_id)
  * Command interface
  ********************/
 
-typedef int (*rocker_cmd_cb_t)(struct rocker *rocker,
-			       struct rocker_port *rocker_port,
-			       struct rocker_desc_info *desc_info,
-			       void *priv);
+typedef int (*rocker_cmd_prep_cb_t)(const struct rocker_port *rocker_port,
+				    struct rocker_desc_info *desc_info,
+				    void *priv);
+
+typedef int (*rocker_cmd_proc_cb_t)(const struct rocker_port *rocker_port,
+				    const struct rocker_desc_info *desc_info,
+				    void *priv);
 
-static int rocker_cmd_exec(struct rocker *rocker,
-			   struct rocker_port *rocker_port,
-			   rocker_cmd_cb_t prepare, void *prepare_priv,
-			   rocker_cmd_cb_t process, void *process_priv,
-			   bool nowait)
+static int rocker_cmd_exec(struct rocker_port *rocker_port,
+			   enum switchdev_trans trans, int flags,
+			   rocker_cmd_prep_cb_t prepare, void *prepare_priv,
+			   rocker_cmd_proc_cb_t process, void *process_priv)
 {
+	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_desc_info *desc_info;
 	struct rocker_wait *wait;
-	unsigned long flags;
+	bool nowait = !!(flags & ROCKER_OP_FLAG_NOWAIT);
+	unsigned long lock_flags;
 	int err;
 
-	wait = rocker_wait_create(nowait ? GFP_ATOMIC : GFP_KERNEL);
+	wait = rocker_wait_create(rocker_port, trans, flags);
 	if (!wait)
 		return -ENOMEM;
 	wait->nowait = nowait;
 
-	spin_lock_irqsave(&rocker->cmd_ring_lock, flags);
+	spin_lock_irqsave(&rocker->cmd_ring_lock, lock_flags);
+
 	desc_info = rocker_desc_head_get(&rocker->cmd_ring);
 	if (!desc_info) {
-		spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+		spin_unlock_irqrestore(&rocker->cmd_ring_lock, lock_flags);
 		err = -EAGAIN;
 		goto out;
 	}
-	err = prepare(rocker, rocker_port, desc_info, prepare_priv);
+
+	err = prepare(rocker_port, desc_info, prepare_priv);
 	if (err) {
-		spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+		spin_unlock_irqrestore(&rocker->cmd_ring_lock, lock_flags);
 		goto out;
 	}
+
 	rocker_desc_cookie_ptr_set(desc_info, wait);
-	rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info);
-	spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+
+	if (trans != SWITCHDEV_TRANS_PREPARE)
+		rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info);
+
+	spin_unlock_irqrestore(&rocker->cmd_ring_lock, lock_flags);
 
 	if (nowait)
 		return 0;
 
-	if (!rocker_wait_event_timeout(wait, HZ / 10))
-		return -EIO;
+	if (trans != SWITCHDEV_TRANS_PREPARE)
+		if (!rocker_wait_event_timeout(wait, HZ / 10))
+			return -EIO;
 
 	err = rocker_desc_err(desc_info);
 	if (err)
 		return err;
 
 	if (process)
-		err = process(rocker, rocker_port, desc_info, process_priv);
+		err = process(rocker_port, desc_info, process_priv);
 
 	rocker_desc_gen_clear(desc_info);
 out:
-	rocker_wait_destroy(wait);
+	rocker_wait_destroy(trans, wait);
 	return err;
 }
 
 static int
-rocker_cmd_get_port_settings_prep(struct rocker *rocker,
-				  struct rocker_port *rocker_port,
+rocker_cmd_get_port_settings_prep(const struct rocker_port *rocker_port,
 				  struct rocker_desc_info *desc_info,
 				  void *priv)
 {
@@ -1565,14 +1653,13 @@ rocker_cmd_get_port_settings_prep(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_get_port_settings_ethtool_proc(struct rocker *rocker,
-					  struct rocker_port *rocker_port,
-					  struct rocker_desc_info *desc_info,
+rocker_cmd_get_port_settings_ethtool_proc(const struct rocker_port *rocker_port,
+					  const struct rocker_desc_info *desc_info,
 					  void *priv)
 {
 	struct ethtool_cmd *ecmd = priv;
-	struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
-	struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+	const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
 	u32 speed;
 	u8 duplex;
 	u8 autoneg;
@@ -1604,15 +1691,14 @@ rocker_cmd_get_port_settings_ethtool_proc(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_get_port_settings_macaddr_proc(struct rocker *rocker,
-					  struct rocker_port *rocker_port,
-					  struct rocker_desc_info *desc_info,
+rocker_cmd_get_port_settings_macaddr_proc(const struct rocker_port *rocker_port,
+					  const struct rocker_desc_info *desc_info,
 					  void *priv)
 {
 	unsigned char *macaddr = priv;
-	struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
-	struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
-	struct rocker_tlv *attr;
+	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+	const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
+	const struct rocker_tlv *attr;
 
 	rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info);
 	if (!attrs[ROCKER_TLV_CMD_INFO])
@@ -1637,17 +1723,16 @@ struct port_name {
 };
 
 static int
-rocker_cmd_get_port_settings_phys_name_proc(struct rocker *rocker,
-					    struct rocker_port *rocker_port,
-					    struct rocker_desc_info *desc_info,
+rocker_cmd_get_port_settings_phys_name_proc(const struct rocker_port *rocker_port,
+					    const struct rocker_desc_info *desc_info,
 					    void *priv)
 {
-	struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
-	struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+	const struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
 	struct port_name *name = priv;
-	struct rocker_tlv *attr;
+	const struct rocker_tlv *attr;
 	size_t i, j, len;
-	char *str;
+	const char *str;
 
 	rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info);
 	if (!attrs[ROCKER_TLV_CMD_INFO])
@@ -1679,8 +1764,7 @@ rocker_cmd_get_port_settings_phys_name_proc(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker,
-					  struct rocker_port *rocker_port,
+rocker_cmd_set_port_settings_ethtool_prep(const struct rocker_port *rocker_port,
 					  struct rocker_desc_info *desc_info,
 					  void *priv)
 {
@@ -1710,12 +1794,11 @@ rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_set_port_settings_macaddr_prep(struct rocker *rocker,
-					  struct rocker_port *rocker_port,
+rocker_cmd_set_port_settings_macaddr_prep(const struct rocker_port *rocker_port,
 					  struct rocker_desc_info *desc_info,
 					  void *priv)
 {
-	unsigned char *macaddr = priv;
+	const unsigned char *macaddr = priv;
 	struct rocker_tlv *cmd_info;
 
 	if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
@@ -1735,8 +1818,7 @@ rocker_cmd_set_port_settings_macaddr_prep(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_set_port_learning_prep(struct rocker *rocker,
-				  struct rocker_port *rocker_port,
+rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port,
 				  struct rocker_desc_info *desc_info,
 				  void *priv)
 {
@@ -1761,46 +1843,48 @@ rocker_cmd_set_port_learning_prep(struct rocker *rocker,
 static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
 						struct ethtool_cmd *ecmd)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
 			       rocker_cmd_get_port_settings_prep, NULL,
 			       rocker_cmd_get_port_settings_ethtool_proc,
-			       ecmd, false);
+			       ecmd);
 }
 
 static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port,
 						unsigned char *macaddr)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
 			       rocker_cmd_get_port_settings_prep, NULL,
 			       rocker_cmd_get_port_settings_macaddr_proc,
-			       macaddr, false);
+			       macaddr);
 }
 
 static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
 						struct ethtool_cmd *ecmd)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
 			       rocker_cmd_set_port_settings_ethtool_prep,
-			       ecmd, NULL, NULL, false);
+			       ecmd, NULL, NULL);
 }
 
 static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port,
 						unsigned char *macaddr)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
 			       rocker_cmd_set_port_settings_macaddr_prep,
-			       macaddr, NULL, NULL, false);
+			       macaddr, NULL, NULL);
 }
 
-static int rocker_port_set_learning(struct rocker_port *rocker_port)
+static int rocker_port_set_learning(struct rocker_port *rocker_port,
+				    enum switchdev_trans trans)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, trans, 0,
 			       rocker_cmd_set_port_learning_prep,
-			       NULL, NULL, NULL, false);
+			       NULL, NULL, NULL);
 }
 
-static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info,
-					   struct rocker_flow_tbl_entry *entry)
+static int
+rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info,
+				const struct rocker_flow_tbl_entry *entry)
 {
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT,
 			       entry->key.ig_port.in_pport))
@@ -1815,8 +1899,9 @@ static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info,
-					struct rocker_flow_tbl_entry *entry)
+static int
+rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info,
+			     const struct rocker_flow_tbl_entry *entry)
 {
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT,
 			       entry->key.vlan.in_pport))
@@ -1838,8 +1923,9 @@ static int rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info,
-					    struct rocker_flow_tbl_entry *entry)
+static int
+rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info,
+				 const struct rocker_flow_tbl_entry *entry)
 {
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT,
 			       entry->key.term_mac.in_pport))
@@ -1875,7 +1961,7 @@ static int rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info,
 
 static int
 rocker_cmd_flow_tbl_add_ucast_routing(struct rocker_desc_info *desc_info,
-				      struct rocker_flow_tbl_entry *entry)
+				      const struct rocker_flow_tbl_entry *entry)
 {
 	if (rocker_tlv_put_be16(desc_info, ROCKER_TLV_OF_DPA_ETHERTYPE,
 				entry->key.ucast_routing.eth_type))
@@ -1896,8 +1982,9 @@ rocker_cmd_flow_tbl_add_ucast_routing(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info,
-					  struct rocker_flow_tbl_entry *entry)
+static int
+rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info,
+			       const struct rocker_flow_tbl_entry *entry)
 {
 	if (entry->key.bridge.has_eth_dst &&
 	    rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
@@ -1929,8 +2016,9 @@ static int rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info,
-				       struct rocker_flow_tbl_entry *entry)
+static int
+rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info,
+			    const struct rocker_flow_tbl_entry *entry)
 {
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_PPORT,
 			       entry->key.acl.in_pport))
@@ -1995,12 +2083,11 @@ static int rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_add(struct rocker *rocker,
-				   struct rocker_port *rocker_port,
+static int rocker_cmd_flow_tbl_add(const struct rocker_port *rocker_port,
 				   struct rocker_desc_info *desc_info,
 				   void *priv)
 {
-	struct rocker_flow_tbl_entry *entry = priv;
+	const struct rocker_flow_tbl_entry *entry = priv;
 	struct rocker_tlv *cmd_info;
 	int err = 0;
 
@@ -2053,8 +2140,7 @@ static int rocker_cmd_flow_tbl_add(struct rocker *rocker,
 	return 0;
 }
 
-static int rocker_cmd_flow_tbl_del(struct rocker *rocker,
-				   struct rocker_port *rocker_port,
+static int rocker_cmd_flow_tbl_del(const struct rocker_port *rocker_port,
 				   struct rocker_desc_info *desc_info,
 				   void *priv)
 {
@@ -2090,7 +2176,7 @@ rocker_cmd_group_tbl_add_l2_interface(struct rocker_desc_info *desc_info,
 
 static int
 rocker_cmd_group_tbl_add_l2_rewrite(struct rocker_desc_info *desc_info,
-				    struct rocker_group_tbl_entry *entry)
+				    const struct rocker_group_tbl_entry *entry)
 {
 	if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID_LOWER,
 			       entry->l2_rewrite.group_id))
@@ -2113,7 +2199,7 @@ rocker_cmd_group_tbl_add_l2_rewrite(struct rocker_desc_info *desc_info,
 
 static int
 rocker_cmd_group_tbl_add_group_ids(struct rocker_desc_info *desc_info,
-				   struct rocker_group_tbl_entry *entry)
+				   const struct rocker_group_tbl_entry *entry)
 {
 	int i;
 	struct rocker_tlv *group_ids;
@@ -2139,7 +2225,7 @@ rocker_cmd_group_tbl_add_group_ids(struct rocker_desc_info *desc_info,
 
 static int
 rocker_cmd_group_tbl_add_l3_unicast(struct rocker_desc_info *desc_info,
-				    struct rocker_group_tbl_entry *entry)
+				    const struct rocker_group_tbl_entry *entry)
 {
 	if (!is_zero_ether_addr(entry->l3_unicast.eth_src) &&
 	    rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC,
@@ -2163,8 +2249,7 @@ rocker_cmd_group_tbl_add_l3_unicast(struct rocker_desc_info *desc_info,
 	return 0;
 }
 
-static int rocker_cmd_group_tbl_add(struct rocker *rocker,
-				    struct rocker_port *rocker_port,
+static int rocker_cmd_group_tbl_add(const struct rocker_port *rocker_port,
 				    struct rocker_desc_info *desc_info,
 				    void *priv)
 {
@@ -2209,8 +2294,7 @@ static int rocker_cmd_group_tbl_add(struct rocker *rocker,
 	return 0;
 }
 
-static int rocker_cmd_group_tbl_del(struct rocker *rocker,
-				    struct rocker_port *rocker_port,
+static int rocker_cmd_group_tbl_del(const struct rocker_port *rocker_port,
 				    struct rocker_desc_info *desc_info,
 				    void *priv)
 {
@@ -2293,7 +2377,8 @@ static void rocker_free_tbls(struct rocker *rocker)
 }
 
 static struct rocker_flow_tbl_entry *
-rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match)
+rocker_flow_tbl_find(const struct rocker *rocker,
+		     const struct rocker_flow_tbl_entry *match)
 {
 	struct rocker_flow_tbl_entry *found;
 	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
@@ -2308,24 +2393,25 @@ rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match)
 }
 
 static int rocker_flow_tbl_add(struct rocker_port *rocker_port,
-			       struct rocker_flow_tbl_entry *match,
-			       bool nowait)
+			       enum switchdev_trans trans, int flags,
+			       struct rocker_flow_tbl_entry *match)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_flow_tbl_entry *found;
 	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
-	unsigned long flags;
+	unsigned long lock_flags;
 
 	match->key_crc32 = crc32(~0, &match->key, key_len);
 
-	spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+	spin_lock_irqsave(&rocker->flow_tbl_lock, lock_flags);
 
 	found = rocker_flow_tbl_find(rocker, match);
 
 	if (found) {
 		match->cookie = found->cookie;
-		hash_del(&found->entry);
-		kfree(found);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
+		rocker_port_kfree(trans, found);
 		found = match;
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD;
 	} else {
@@ -2334,73 +2420,69 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port,
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD;
 	}
 
-	hash_add(rocker->flow_tbl, &found->entry, found->key_crc32);
+	if (trans != SWITCHDEV_TRANS_PREPARE)
+		hash_add(rocker->flow_tbl, &found->entry, found->key_crc32);
 
-	spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+	spin_unlock_irqrestore(&rocker->flow_tbl_lock, lock_flags);
 
-	return rocker_cmd_exec(rocker, rocker_port,
-			       rocker_cmd_flow_tbl_add,
-			       found, NULL, NULL, nowait);
+	return rocker_cmd_exec(rocker_port, trans, flags,
+			       rocker_cmd_flow_tbl_add, found, NULL, NULL);
 }
 
 static int rocker_flow_tbl_del(struct rocker_port *rocker_port,
-			       struct rocker_flow_tbl_entry *match,
-			       bool nowait)
+			       enum switchdev_trans trans, int flags,
+			       struct rocker_flow_tbl_entry *match)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_flow_tbl_entry *found;
 	size_t key_len = match->key_len ? match->key_len : sizeof(found->key);
-	unsigned long flags;
+	unsigned long lock_flags;
 	int err = 0;
 
 	match->key_crc32 = crc32(~0, &match->key, key_len);
 
-	spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+	spin_lock_irqsave(&rocker->flow_tbl_lock, lock_flags);
 
 	found = rocker_flow_tbl_find(rocker, match);
 
 	if (found) {
-		hash_del(&found->entry);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL;
 	}
 
-	spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+	spin_unlock_irqrestore(&rocker->flow_tbl_lock, lock_flags);
 
-	kfree(match);
+	rocker_port_kfree(trans, match);
 
 	if (found) {
-		err = rocker_cmd_exec(rocker, rocker_port,
+		err = rocker_cmd_exec(rocker_port, trans, flags,
 				      rocker_cmd_flow_tbl_del,
-				      found, NULL, NULL, nowait);
-		kfree(found);
+				      found, NULL, NULL);
+		rocker_port_kfree(trans, found);
 	}
 
 	return err;
 }
 
-static gfp_t rocker_op_flags_gfp(int flags)
-{
-	return flags & ROCKER_OP_FLAG_NOWAIT ? GFP_ATOMIC : GFP_KERNEL;
-}
-
 static int rocker_flow_tbl_do(struct rocker_port *rocker_port,
-			      int flags, struct rocker_flow_tbl_entry *entry)
+			      enum switchdev_trans trans, int flags,
+			      struct rocker_flow_tbl_entry *entry)
 {
-	bool nowait = flags & ROCKER_OP_FLAG_NOWAIT;
-
 	if (flags & ROCKER_OP_FLAG_REMOVE)
-		return rocker_flow_tbl_del(rocker_port, entry, nowait);
+		return rocker_flow_tbl_del(rocker_port, trans, flags, entry);
 	else
-		return rocker_flow_tbl_add(rocker_port, entry, nowait);
+		return rocker_flow_tbl_add(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port,
-				   int flags, u32 in_pport, u32 in_pport_mask,
+				   enum switchdev_trans trans, int flags,
+				   u32 in_pport, u32 in_pport_mask,
 				   enum rocker_of_dpa_table_id goto_tbl)
 {
 	struct rocker_flow_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2410,18 +2492,19 @@ static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port,
 	entry->key.ig_port.in_pport_mask = in_pport_mask;
 	entry->key.ig_port.goto_tbl = goto_tbl;
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port,
-				int flags, u32 in_pport,
-				__be16 vlan_id, __be16 vlan_id_mask,
+				enum switchdev_trans trans, int flags,
+				u32 in_pport, __be16 vlan_id,
+				__be16 vlan_id_mask,
 				enum rocker_of_dpa_table_id goto_tbl,
 				bool untagged, __be16 new_vlan_id)
 {
 	struct rocker_flow_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2435,10 +2518,11 @@ static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port,
 	entry->key.vlan.untagged = untagged;
 	entry->key.vlan.new_vlan_id = new_vlan_id;
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port,
+				    enum switchdev_trans trans,
 				    u32 in_pport, u32 in_pport_mask,
 				    __be16 eth_type, const u8 *eth_dst,
 				    const u8 *eth_dst_mask, __be16 vlan_id,
@@ -2447,7 +2531,7 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port,
 {
 	struct rocker_flow_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2471,11 +2555,11 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port,
 	entry->key.term_mac.vlan_id_mask = vlan_id_mask;
 	entry->key.term_mac.copy_to_cpu = copy_to_cpu;
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
-				  int flags,
+				  enum switchdev_trans trans, int flags,
 				  const u8 *eth_dst, const u8 *eth_dst_mask,
 				  __be16 vlan_id, u32 tunnel_id,
 				  enum rocker_of_dpa_table_id goto_tbl,
@@ -2487,7 +2571,7 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
 	bool dflt = !eth_dst || (eth_dst && eth_dst_mask);
 	bool wild = false;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2500,7 +2584,7 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
 	if (eth_dst_mask) {
 		entry->key.bridge.has_eth_dst_mask = 1;
 		ether_addr_copy(entry->key.bridge.eth_dst_mask, eth_dst_mask);
-		if (memcmp(eth_dst_mask, ff_mac, ETH_ALEN))
+		if (!ether_addr_equal(eth_dst_mask, ff_mac))
 			wild = true;
 	}
 
@@ -2525,10 +2609,11 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
 	entry->key.bridge.group_id = group_id;
 	entry->key.bridge.copy_to_cpu = copy_to_cpu;
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port,
+					  enum switchdev_trans trans,
 					  __be16 eth_type, __be32 dst,
 					  __be32 dst_mask, u32 priority,
 					  enum rocker_of_dpa_table_id goto_tbl,
@@ -2536,7 +2621,7 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port,
 {
 	struct rocker_flow_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2550,30 +2635,29 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port,
 	entry->key_len = offsetof(struct rocker_flow_tbl_key,
 				  ucast_routing.group_id);
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_flow_tbl_acl(struct rocker_port *rocker_port,
-			       int flags, u32 in_pport,
-			       u32 in_pport_mask,
+			       enum switchdev_trans trans, int flags,
+			       u32 in_pport, u32 in_pport_mask,
 			       const u8 *eth_src, const u8 *eth_src_mask,
 			       const u8 *eth_dst, const u8 *eth_dst_mask,
-			       __be16 eth_type,
-			       __be16 vlan_id, __be16 vlan_id_mask,
-			       u8 ip_proto, u8 ip_proto_mask,
-			       u8 ip_tos, u8 ip_tos_mask,
+			       __be16 eth_type, __be16 vlan_id,
+			       __be16 vlan_id_mask, u8 ip_proto,
+			       u8 ip_proto_mask, u8 ip_tos, u8 ip_tos_mask,
 			       u32 group_id)
 {
 	u32 priority;
 	struct rocker_flow_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
 	priority = ROCKER_PRIORITY_ACL_NORMAL;
 	if (eth_dst && eth_dst_mask) {
-		if (memcmp(eth_dst_mask, mcast_mac, ETH_ALEN) == 0)
+		if (ether_addr_equal(eth_dst_mask, mcast_mac))
 			priority = ROCKER_PRIORITY_ACL_DFLT;
 		else if (is_link_local_ether_addr(eth_dst))
 			priority = ROCKER_PRIORITY_ACL_CTRL;
@@ -2602,12 +2686,12 @@ static int rocker_flow_tbl_acl(struct rocker_port *rocker_port,
 	entry->key.acl.ip_tos_mask = ip_tos_mask;
 	entry->key.acl.group_id = group_id;
 
-	return rocker_flow_tbl_do(rocker_port, flags, entry);
+	return rocker_flow_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static struct rocker_group_tbl_entry *
-rocker_group_tbl_find(struct rocker *rocker,
-		      struct rocker_group_tbl_entry *match)
+rocker_group_tbl_find(const struct rocker *rocker,
+		      const struct rocker_group_tbl_entry *match)
 {
 	struct rocker_group_tbl_entry *found;
 
@@ -2620,34 +2704,36 @@ rocker_group_tbl_find(struct rocker *rocker,
 	return NULL;
 }
 
-static void rocker_group_tbl_entry_free(struct rocker_group_tbl_entry *entry)
+static void rocker_group_tbl_entry_free(enum switchdev_trans trans,
+					struct rocker_group_tbl_entry *entry)
 {
 	switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) {
 	case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD:
 	case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST:
-		kfree(entry->group_ids);
+		rocker_port_kfree(trans, entry->group_ids);
 		break;
 	default:
 		break;
 	}
-	kfree(entry);
+	rocker_port_kfree(trans, entry);
 }
 
 static int rocker_group_tbl_add(struct rocker_port *rocker_port,
-				struct rocker_group_tbl_entry *match,
-				bool nowait)
+				enum switchdev_trans trans, int flags,
+				struct rocker_group_tbl_entry *match)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_group_tbl_entry *found;
-	unsigned long flags;
+	unsigned long lock_flags;
 
-	spin_lock_irqsave(&rocker->group_tbl_lock, flags);
+	spin_lock_irqsave(&rocker->group_tbl_lock, lock_flags);
 
 	found = rocker_group_tbl_find(rocker, match);
 
 	if (found) {
-		hash_del(&found->entry);
-		rocker_group_tbl_entry_free(found);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
+		rocker_group_tbl_entry_free(trans, found);
 		found = match;
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD;
 	} else {
@@ -2655,116 +2741,118 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port,
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD;
 	}
 
-	hash_add(rocker->group_tbl, &found->entry, found->group_id);
+	if (trans != SWITCHDEV_TRANS_PREPARE)
+		hash_add(rocker->group_tbl, &found->entry, found->group_id);
 
-	spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
+	spin_unlock_irqrestore(&rocker->group_tbl_lock, lock_flags);
 
-	return rocker_cmd_exec(rocker, rocker_port,
-			       rocker_cmd_group_tbl_add,
-			       found, NULL, NULL, nowait);
+	return rocker_cmd_exec(rocker_port, trans, flags,
+			       rocker_cmd_group_tbl_add, found, NULL, NULL);
 }
 
 static int rocker_group_tbl_del(struct rocker_port *rocker_port,
-				struct rocker_group_tbl_entry *match,
-				bool nowait)
+				enum switchdev_trans trans, int flags,
+				struct rocker_group_tbl_entry *match)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_group_tbl_entry *found;
-	unsigned long flags;
+	unsigned long lock_flags;
 	int err = 0;
 
-	spin_lock_irqsave(&rocker->group_tbl_lock, flags);
+	spin_lock_irqsave(&rocker->group_tbl_lock, lock_flags);
 
 	found = rocker_group_tbl_find(rocker, match);
 
 	if (found) {
-		hash_del(&found->entry);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
 		found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL;
 	}
 
-	spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
+	spin_unlock_irqrestore(&rocker->group_tbl_lock, lock_flags);
 
-	rocker_group_tbl_entry_free(match);
+	rocker_group_tbl_entry_free(trans, match);
 
 	if (found) {
-		err = rocker_cmd_exec(rocker, rocker_port,
+		err = rocker_cmd_exec(rocker_port, trans, flags,
 				      rocker_cmd_group_tbl_del,
-				      found, NULL, NULL, nowait);
-		rocker_group_tbl_entry_free(found);
+				      found, NULL, NULL);
+		rocker_group_tbl_entry_free(trans, found);
 	}
 
 	return err;
 }
 
 static int rocker_group_tbl_do(struct rocker_port *rocker_port,
-			       int flags, struct rocker_group_tbl_entry *entry)
+			       enum switchdev_trans trans, int flags,
+			       struct rocker_group_tbl_entry *entry)
 {
-	bool nowait = flags & ROCKER_OP_FLAG_NOWAIT;
-
 	if (flags & ROCKER_OP_FLAG_REMOVE)
-		return rocker_group_tbl_del(rocker_port, entry, nowait);
+		return rocker_group_tbl_del(rocker_port, trans, flags, entry);
 	else
-		return rocker_group_tbl_add(rocker_port, entry, nowait);
+		return rocker_group_tbl_add(rocker_port, trans, flags, entry);
 }
 
 static int rocker_group_l2_interface(struct rocker_port *rocker_port,
-				     int flags, __be16 vlan_id,
-				     u32 out_pport, int pop_vlan)
+				     enum switchdev_trans trans, int flags,
+				     __be16 vlan_id, u32 out_pport,
+				     int pop_vlan)
 {
 	struct rocker_group_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
 	entry->group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport);
 	entry->l2_interface.pop_vlan = pop_vlan;
 
-	return rocker_group_tbl_do(rocker_port, flags, entry);
+	return rocker_group_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_group_l2_fan_out(struct rocker_port *rocker_port,
+				   enum switchdev_trans trans,
 				   int flags, u8 group_count,
-				   u32 *group_ids, u32 group_id)
+				   const u32 *group_ids, u32 group_id)
 {
 	struct rocker_group_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
 	entry->group_id = group_id;
 	entry->group_count = group_count;
 
-	entry->group_ids = kcalloc(group_count, sizeof(u32),
-				   rocker_op_flags_gfp(flags));
+	entry->group_ids = rocker_port_kcalloc(rocker_port, trans, flags,
+					       group_count, sizeof(u32));
 	if (!entry->group_ids) {
-		kfree(entry);
+		rocker_port_kfree(trans, entry);
 		return -ENOMEM;
 	}
 	memcpy(entry->group_ids, group_ids, group_count * sizeof(u32));
 
-	return rocker_group_tbl_do(rocker_port, flags, entry);
+	return rocker_group_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static int rocker_group_l2_flood(struct rocker_port *rocker_port,
-				 int flags, __be16 vlan_id,
-				 u8 group_count, u32 *group_ids,
-				 u32 group_id)
+				 enum switchdev_trans trans, int flags,
+				 __be16 vlan_id, u8 group_count,
+				 const u32 *group_ids, u32 group_id)
 {
-	return rocker_group_l2_fan_out(rocker_port, flags,
+	return rocker_group_l2_fan_out(rocker_port, trans, flags,
 				       group_count, group_ids,
 				       group_id);
 }
 
 static int rocker_group_l3_unicast(struct rocker_port *rocker_port,
-				   int flags, u32 index, u8 *src_mac,
-				   u8 *dst_mac, __be16 vlan_id,
-				   bool ttl_check, u32 pport)
+				   enum switchdev_trans trans, int flags,
+				   u32 index, const u8 *src_mac, const u8 *dst_mac,
+				   __be16 vlan_id, bool ttl_check, u32 pport)
 {
 	struct rocker_group_tbl_entry *entry;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2777,11 +2865,11 @@ static int rocker_group_l3_unicast(struct rocker_port *rocker_port,
 	entry->l3_unicast.ttl_check = ttl_check;
 	entry->l3_unicast.group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, pport);
 
-	return rocker_group_tbl_do(rocker_port, flags, entry);
+	return rocker_group_tbl_do(rocker_port, trans, flags, entry);
 }
 
 static struct rocker_neigh_tbl_entry *
-	rocker_neigh_tbl_find(struct rocker *rocker, __be32 ip_addr)
+rocker_neigh_tbl_find(const struct rocker *rocker, __be32 ip_addr)
 {
 	struct rocker_neigh_tbl_entry *found;
 
@@ -2794,37 +2882,44 @@ static struct rocker_neigh_tbl_entry *
 }
 
 static void _rocker_neigh_add(struct rocker *rocker,
+			      enum switchdev_trans trans,
 			      struct rocker_neigh_tbl_entry *entry)
 {
-	entry->index = rocker->neigh_tbl_next_index++;
+	if (trans != SWITCHDEV_TRANS_COMMIT)
+		entry->index = rocker->neigh_tbl_next_index++;
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		return;
 	entry->ref_count++;
 	hash_add(rocker->neigh_tbl, &entry->entry,
 		 be32_to_cpu(entry->ip_addr));
 }
 
-static void _rocker_neigh_del(struct rocker *rocker,
+static void _rocker_neigh_del(enum switchdev_trans trans,
 			      struct rocker_neigh_tbl_entry *entry)
 {
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		return;
 	if (--entry->ref_count == 0) {
 		hash_del(&entry->entry);
-		kfree(entry);
+		rocker_port_kfree(trans, entry);
 	}
 }
 
-static void _rocker_neigh_update(struct rocker *rocker,
-				 struct rocker_neigh_tbl_entry *entry,
-				 u8 *eth_dst, bool ttl_check)
+static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry,
+				 enum switchdev_trans trans,
+				 const u8 *eth_dst, bool ttl_check)
 {
 	if (eth_dst) {
 		ether_addr_copy(entry->eth_dst, eth_dst);
 		entry->ttl_check = ttl_check;
-	} else {
+	} else if (trans != SWITCHDEV_TRANS_PREPARE) {
 		entry->ref_count++;
 	}
 }
 
 static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
-				  int flags, __be32 ip_addr, u8 *eth_dst)
+				  enum switchdev_trans trans,
+				  int flags, __be32 ip_addr, const u8 *eth_dst)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_neigh_tbl_entry *entry;
@@ -2840,7 +2935,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
 	bool removing;
 	int err = 0;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2857,12 +2952,12 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
 		entry->dev = rocker_port->dev;
 		ether_addr_copy(entry->eth_dst, eth_dst);
 		entry->ttl_check = true;
-		_rocker_neigh_add(rocker, entry);
+		_rocker_neigh_add(rocker, trans, entry);
 	} else if (removing) {
 		memcpy(entry, found, sizeof(*entry));
-		_rocker_neigh_del(rocker, found);
+		_rocker_neigh_del(trans, found);
 	} else if (updating) {
-		_rocker_neigh_update(rocker, found, eth_dst, true);
+		_rocker_neigh_update(found, trans, eth_dst, true);
 		memcpy(entry, found, sizeof(*entry));
 	} else {
 		err = -ENOENT;
@@ -2879,7 +2974,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
 	 * other routes' nexthops.
 	 */
 
-	err = rocker_group_l3_unicast(rocker_port, flags,
+	err = rocker_group_l3_unicast(rocker_port, trans, flags,
 				      entry->index,
 				      rocker_port->dev->dev_addr,
 				      entry->eth_dst,
@@ -2895,7 +2990,7 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
 
 	if (adding || removing) {
 		group_id = ROCKER_GROUP_L3_UNICAST(entry->index);
-		err = rocker_flow_tbl_ucast4_routing(rocker_port,
+		err = rocker_flow_tbl_ucast4_routing(rocker_port, trans,
 						     eth_type, ip_addr,
 						     inet_make_mask(32),
 						     priority, goto_tbl,
@@ -2909,22 +3004,23 @@ static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port,
 
 err_out:
 	if (!adding)
-		kfree(entry);
+		rocker_port_kfree(trans, entry);
 
 	return err;
 }
 
 static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port,
-				    __be32 ip_addr)
+				    enum switchdev_trans trans, __be32 ip_addr)
 {
 	struct net_device *dev = rocker_port->dev;
 	struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr);
 	int err = 0;
 
-	if (!n)
+	if (!n) {
 		n = neigh_create(&arp_tbl, &ip_addr, dev);
-	if (!n)
-		return -ENOMEM;
+		if (IS_ERR(n))
+			return IS_ERR(n);
+	}
 
 	/* If the neigh is already resolved, then go ahead and
 	 * install the entry, otherwise start the ARP process to
@@ -2932,14 +3028,17 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port,
 	 */
 
 	if (n->nud_state & NUD_VALID)
-		err = rocker_port_ipv4_neigh(rocker_port, 0, ip_addr, n->ha);
+		err = rocker_port_ipv4_neigh(rocker_port, trans, 0,
+					     ip_addr, n->ha);
 	else
 		neigh_event_send(n, NULL);
 
+	neigh_release(n);
 	return err;
 }
 
-static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
+static int rocker_port_ipv4_nh(struct rocker_port *rocker_port,
+			       enum switchdev_trans trans, int flags,
 			       __be32 ip_addr, u32 *index)
 {
 	struct rocker *rocker = rocker_port->rocker;
@@ -2952,7 +3051,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
 	bool resolved = true;
 	int err = 0;
 
-	entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+	entry = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*entry));
 	if (!entry)
 		return -ENOMEM;
 
@@ -2969,13 +3068,13 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
 	if (adding) {
 		entry->ip_addr = ip_addr;
 		entry->dev = rocker_port->dev;
-		_rocker_neigh_add(rocker, entry);
+		_rocker_neigh_add(rocker, trans, entry);
 		*index = entry->index;
 		resolved = false;
 	} else if (removing) {
-		_rocker_neigh_del(rocker, found);
+		_rocker_neigh_del(trans, found);
 	} else if (updating) {
-		_rocker_neigh_update(rocker, found, NULL, false);
+		_rocker_neigh_update(found, trans, NULL, false);
 		resolved = !is_zero_ether_addr(found->eth_dst);
 	} else {
 		err = -ENOENT;
@@ -2984,7 +3083,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
 	spin_unlock_irqrestore(&rocker->neigh_tbl_lock, lock_flags);
 
 	if (!adding)
-		kfree(entry);
+		rocker_port_kfree(trans, entry);
 
 	if (err)
 		return err;
@@ -2992,24 +3091,25 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, int flags,
 	/* Resolved means neigh ip_addr is resolved to neigh mac. */
 
 	if (!resolved)
-		err = rocker_port_ipv4_resolve(rocker_port, ip_addr);
+		err = rocker_port_ipv4_resolve(rocker_port, trans, ip_addr);
 
 	return err;
 }
 
 static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port,
+					enum switchdev_trans trans,
 					int flags, __be16 vlan_id)
 {
 	struct rocker_port *p;
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	u32 group_id = ROCKER_GROUP_L2_FLOOD(vlan_id, 0);
 	u32 *group_ids;
 	u8 group_count = 0;
 	int err = 0;
 	int i;
 
-	group_ids = kcalloc(rocker->port_count, sizeof(u32),
-			    rocker_op_flags_gfp(flags));
+	group_ids = rocker_port_kcalloc(rocker_port, trans, flags,
+					rocker->port_count, sizeof(u32));
 	if (!group_ids)
 		return -ENOMEM;
 
@@ -3020,6 +3120,8 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port,
 
 	for (i = 0; i < rocker->port_count; i++) {
 		p = rocker->ports[i];
+		if (!p)
+			continue;
 		if (!rocker_port_is_bridged(p))
 			continue;
 		if (test_bit(ntohs(vlan_id), p->vlan_bitmap)) {
@@ -3032,23 +3134,22 @@ static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port,
 	if (group_count == 0)
 		goto no_ports_in_vlan;
 
-	err = rocker_group_l2_flood(rocker_port, flags, vlan_id,
-				    group_count, group_ids,
-				    group_id);
+	err = rocker_group_l2_flood(rocker_port, trans, flags, vlan_id,
+				    group_count, group_ids, group_id);
 	if (err)
 		netdev_err(rocker_port->dev,
 			   "Error (%d) port VLAN l2 flood group\n", err);
 
 no_ports_in_vlan:
-	kfree(group_ids);
+	rocker_port_kfree(trans, group_ids);
 	return err;
 }
 
 static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port,
-				      int flags, __be16 vlan_id,
-				      bool pop_vlan)
+				      enum switchdev_trans trans, int flags,
+				      __be16 vlan_id, bool pop_vlan)
 {
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	struct rocker_port *p;
 	bool adding = !(flags & ROCKER_OP_FLAG_REMOVE);
 	u32 out_pport;
@@ -3063,9 +3164,8 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port,
 	if (rocker_port->stp_state == BR_STATE_LEARNING ||
 	    rocker_port->stp_state == BR_STATE_FORWARDING) {
 		out_pport = rocker_port->pport;
-		err = rocker_group_l2_interface(rocker_port, flags,
-						vlan_id, out_pport,
-						pop_vlan);
+		err = rocker_group_l2_interface(rocker_port, trans, flags,
+						vlan_id, out_pport, pop_vlan);
 		if (err) {
 			netdev_err(rocker_port->dev,
 				   "Error (%d) port VLAN l2 group for pport %d\n",
@@ -3081,7 +3181,7 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port,
 
 	for (i = 0; i < rocker->port_count; i++) {
 		p = rocker->ports[i];
-		if (test_bit(ntohs(vlan_id), p->vlan_bitmap))
+		if (p && test_bit(ntohs(vlan_id), p->vlan_bitmap))
 			ref++;
 	}
 
@@ -3089,9 +3189,8 @@ static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port,
 		return 0;
 
 	out_pport = 0;
-	err = rocker_group_l2_interface(rocker_port, flags,
-					vlan_id, out_pport,
-					pop_vlan);
+	err = rocker_group_l2_interface(rocker_port, trans, flags,
+					vlan_id, out_pport, pop_vlan);
 	if (err) {
 		netdev_err(rocker_port->dev,
 			   "Error (%d) port VLAN l2 group for CPU port\n", err);
@@ -3147,14 +3246,14 @@ static struct rocker_ctrl {
 };
 
 static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port,
-				     int flags, struct rocker_ctrl *ctrl,
-				     __be16 vlan_id)
+				     enum switchdev_trans trans, int flags,
+				     const struct rocker_ctrl *ctrl, __be16 vlan_id)
 {
 	u32 in_pport = rocker_port->pport;
 	u32 in_pport_mask = 0xffffffff;
 	u32 out_pport = 0;
-	u8 *eth_src = NULL;
-	u8 *eth_src_mask = NULL;
+	const u8 *eth_src = NULL;
+	const u8 *eth_src_mask = NULL;
 	__be16 vlan_id_mask = htons(0xffff);
 	u8 ip_proto = 0;
 	u8 ip_proto_mask = 0;
@@ -3163,7 +3262,7 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port,
 	u32 group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport);
 	int err;
 
-	err = rocker_flow_tbl_acl(rocker_port, flags,
+	err = rocker_flow_tbl_acl(rocker_port, trans, flags,
 				  in_pport, in_pport_mask,
 				  eth_src, eth_src_mask,
 				  ctrl->eth_dst, ctrl->eth_dst_mask,
@@ -3180,7 +3279,8 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port,
 }
 
 static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port,
-					int flags, struct rocker_ctrl *ctrl,
+					enum switchdev_trans trans, int flags,
+					const struct rocker_ctrl *ctrl,
 					__be16 vlan_id)
 {
 	enum rocker_of_dpa_table_id goto_tbl =
@@ -3192,7 +3292,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port,
 	if (!rocker_port_is_bridged(rocker_port))
 		return 0;
 
-	err = rocker_flow_tbl_bridge(rocker_port, flags,
+	err = rocker_flow_tbl_bridge(rocker_port, trans, flags,
 				     ctrl->eth_dst, ctrl->eth_dst_mask,
 				     vlan_id, tunnel_id,
 				     goto_tbl, group_id, ctrl->copy_to_cpu);
@@ -3204,8 +3304,8 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port,
 }
 
 static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port,
-				      int flags, struct rocker_ctrl *ctrl,
-				      __be16 vlan_id)
+				      enum switchdev_trans trans, int flags,
+				      const struct rocker_ctrl *ctrl, __be16 vlan_id)
 {
 	u32 in_pport_mask = 0xffffffff;
 	__be16 vlan_id_mask = htons(0xffff);
@@ -3214,7 +3314,7 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port,
 	if (ntohs(vlan_id) == 0)
 		vlan_id = rocker_port->internal_vlan_id;
 
-	err = rocker_flow_tbl_term_mac(rocker_port,
+	err = rocker_flow_tbl_term_mac(rocker_port, trans,
 				       rocker_port->pport, in_pport_mask,
 				       ctrl->eth_type, ctrl->eth_dst,
 				       ctrl->eth_dst_mask, vlan_id,
@@ -3227,32 +3327,34 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port,
 	return err;
 }
 
-static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, int flags,
-				 struct rocker_ctrl *ctrl, __be16 vlan_id)
+static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port,
+				 enum switchdev_trans trans, int flags,
+				 const struct rocker_ctrl *ctrl, __be16 vlan_id)
 {
 	if (ctrl->acl)
-		return rocker_port_ctrl_vlan_acl(rocker_port, flags,
+		return rocker_port_ctrl_vlan_acl(rocker_port, trans, flags,
 						 ctrl, vlan_id);
 	if (ctrl->bridge)
-		return rocker_port_ctrl_vlan_bridge(rocker_port, flags,
+		return rocker_port_ctrl_vlan_bridge(rocker_port, trans, flags,
 						    ctrl, vlan_id);
 
 	if (ctrl->term)
-		return rocker_port_ctrl_vlan_term(rocker_port, flags,
+		return rocker_port_ctrl_vlan_term(rocker_port, trans, flags,
 						  ctrl, vlan_id);
 
 	return -EOPNOTSUPP;
 }
 
 static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port,
-				     int flags, __be16 vlan_id)
+				     enum switchdev_trans trans, int flags,
+				     __be16 vlan_id)
 {
 	int err = 0;
 	int i;
 
 	for (i = 0; i < ROCKER_CTRL_MAX; i++) {
 		if (rocker_port->ctrls[i]) {
-			err = rocker_port_ctrl_vlan(rocker_port, flags,
+			err = rocker_port_ctrl_vlan(rocker_port, trans, flags,
 						    &rocker_ctrls[i], vlan_id);
 			if (err)
 				return err;
@@ -3262,8 +3364,9 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port,
 	return err;
 }
 
-static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags,
-			    struct rocker_ctrl *ctrl)
+static int rocker_port_ctrl(struct rocker_port *rocker_port,
+			    enum switchdev_trans trans, int flags,
+			    const struct rocker_ctrl *ctrl)
 {
 	u16 vid;
 	int err = 0;
@@ -3271,7 +3374,7 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags,
 	for (vid = 1; vid < VLAN_N_VID; vid++) {
 		if (!test_bit(vid, rocker_port->vlan_bitmap))
 			continue;
-		err = rocker_port_ctrl_vlan(rocker_port, flags,
+		err = rocker_port_ctrl_vlan(rocker_port, trans, flags,
 					    ctrl, htons(vid));
 		if (err)
 			break;
@@ -3280,8 +3383,8 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags,
 	return err;
 }
 
-static int rocker_port_vlan(struct rocker_port *rocker_port, int flags,
-			    u16 vid)
+static int rocker_port_vlan(struct rocker_port *rocker_port,
+			    enum switchdev_trans trans, int flags, u16 vid)
 {
 	enum rocker_of_dpa_table_id goto_tbl =
 		ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC;
@@ -3295,50 +3398,57 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, int flags,
 
 	internal_vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, &untagged);
 
-	if (adding && test_and_set_bit(ntohs(internal_vlan_id),
-				       rocker_port->vlan_bitmap))
+	if (adding && test_bit(ntohs(internal_vlan_id),
+			       rocker_port->vlan_bitmap))
 			return 0; /* already added */
-	else if (!adding && !test_and_clear_bit(ntohs(internal_vlan_id),
-						rocker_port->vlan_bitmap))
+	else if (!adding && !test_bit(ntohs(internal_vlan_id),
+				      rocker_port->vlan_bitmap))
 			return 0; /* already removed */
 
+	change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap);
+
 	if (adding) {
-		err = rocker_port_ctrl_vlan_add(rocker_port, flags,
+		err = rocker_port_ctrl_vlan_add(rocker_port, trans, flags,
 						internal_vlan_id);
 		if (err) {
 			netdev_err(rocker_port->dev,
 				   "Error (%d) port ctrl vlan add\n", err);
-			return err;
+			goto err_out;
 		}
 	}
 
-	err = rocker_port_vlan_l2_groups(rocker_port, flags,
+	err = rocker_port_vlan_l2_groups(rocker_port, trans, flags,
 					 internal_vlan_id, untagged);
 	if (err) {
 		netdev_err(rocker_port->dev,
 			   "Error (%d) port VLAN l2 groups\n", err);
-		return err;
+		goto err_out;
 	}
 
-	err = rocker_port_vlan_flood_group(rocker_port, flags,
+	err = rocker_port_vlan_flood_group(rocker_port, trans, flags,
 					   internal_vlan_id);
 	if (err) {
 		netdev_err(rocker_port->dev,
 			   "Error (%d) port VLAN l2 flood group\n", err);
-		return err;
+		goto err_out;
 	}
 
-	err = rocker_flow_tbl_vlan(rocker_port, flags,
+	err = rocker_flow_tbl_vlan(rocker_port, trans, flags,
 				   in_pport, vlan_id, vlan_id_mask,
 				   goto_tbl, untagged, internal_vlan_id);
 	if (err)
 		netdev_err(rocker_port->dev,
 			   "Error (%d) port VLAN table\n", err);
 
+err_out:
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap);
+
 	return err;
 }
 
-static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
+static int rocker_port_ig_tbl(struct rocker_port *rocker_port,
+			      enum switchdev_trans trans, int flags)
 {
 	enum rocker_of_dpa_table_id goto_tbl;
 	u32 in_pport;
@@ -3353,7 +3463,7 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
 	in_pport_mask = 0xffff0000;
 	goto_tbl = ROCKER_OF_DPA_TABLE_ID_VLAN;
 
-	err = rocker_flow_tbl_ig_port(rocker_port, flags,
+	err = rocker_flow_tbl_ig_port(rocker_port, trans, flags,
 				      in_pport, in_pport_mask,
 				      goto_tbl);
 	if (err)
@@ -3365,7 +3475,8 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
 
 struct rocker_fdb_learn_work {
 	struct work_struct work;
-	struct net_device *dev;
+	struct rocker_port *rocker_port;
+	enum switchdev_trans trans;
 	int flags;
 	u8 addr[ETH_ALEN];
 	u16 vid;
@@ -3373,27 +3484,28 @@ struct rocker_fdb_learn_work {
 
 static void rocker_port_fdb_learn_work(struct work_struct *work)
 {
-	struct rocker_fdb_learn_work *lw =
+	const struct rocker_fdb_learn_work *lw =
 		container_of(work, struct rocker_fdb_learn_work, work);
 	bool removing = (lw->flags & ROCKER_OP_FLAG_REMOVE);
 	bool learned = (lw->flags & ROCKER_OP_FLAG_LEARNED);
-	struct netdev_switch_notifier_fdb_info info;
+	struct switchdev_notifier_fdb_info info;
 
 	info.addr = lw->addr;
 	info.vid = lw->vid;
 
 	if (learned && removing)
-		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_DEL,
-					     lw->dev, &info.info);
+		call_switchdev_notifiers(SWITCHDEV_FDB_DEL,
+					 lw->rocker_port->dev, &info.info);
 	else if (learned && !removing)
-		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_ADD,
-					     lw->dev, &info.info);
+		call_switchdev_notifiers(SWITCHDEV_FDB_ADD,
+					 lw->rocker_port->dev, &info.info);
 
-	kfree(work);
+	rocker_port_kfree(lw->trans, work);
 }
 
 static int rocker_port_fdb_learn(struct rocker_port *rocker_port,
-				 int flags, const u8 *addr, __be16 vlan_id)
+				 enum switchdev_trans trans, int flags,
+				 const u8 *addr, __be16 vlan_id)
 {
 	struct rocker_fdb_learn_work *lw;
 	enum rocker_of_dpa_table_id goto_tbl =
@@ -3409,8 +3521,8 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port,
 		group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_pport);
 
 	if (!(flags & ROCKER_OP_FLAG_REFRESH)) {
-		err = rocker_flow_tbl_bridge(rocker_port, flags, addr, NULL,
-					     vlan_id, tunnel_id, goto_tbl,
+		err = rocker_flow_tbl_bridge(rocker_port, trans, flags, addr,
+					     NULL, vlan_id, tunnel_id, goto_tbl,
 					     group_id, copy_to_cpu);
 		if (err)
 			return err;
@@ -3422,24 +3534,29 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port,
 	if (!rocker_port_is_bridged(rocker_port))
 		return 0;
 
-	lw = kmalloc(sizeof(*lw), rocker_op_flags_gfp(flags));
+	lw = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*lw));
 	if (!lw)
 		return -ENOMEM;
 
 	INIT_WORK(&lw->work, rocker_port_fdb_learn_work);
 
-	lw->dev = rocker_port->dev;
+	lw->rocker_port = rocker_port;
+	lw->trans = trans;
 	lw->flags = flags;
 	ether_addr_copy(lw->addr, addr);
 	lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id);
 
-	schedule_work(&lw->work);
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		rocker_port_kfree(trans, lw);
+	else
+		schedule_work(&lw->work);
 
 	return 0;
 }
 
 static struct rocker_fdb_tbl_entry *
-rocker_fdb_tbl_find(struct rocker *rocker, struct rocker_fdb_tbl_entry *match)
+rocker_fdb_tbl_find(const struct rocker *rocker,
+		    const struct rocker_fdb_tbl_entry *match)
 {
 	struct rocker_fdb_tbl_entry *found;
 
@@ -3451,6 +3568,7 @@ rocker_fdb_tbl_find(struct rocker *rocker, struct rocker_fdb_tbl_entry *match)
 }
 
 static int rocker_port_fdb(struct rocker_port *rocker_port,
+			   enum switchdev_trans trans,
 			   const unsigned char *addr,
 			   __be16 vlan_id, int flags)
 {
@@ -3460,7 +3578,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port,
 	bool removing = (flags & ROCKER_OP_FLAG_REMOVE);
 	unsigned long lock_flags;
 
-	fdb = kzalloc(sizeof(*fdb), rocker_op_flags_gfp(flags));
+	fdb = rocker_port_kzalloc(rocker_port, trans, flags, sizeof(*fdb));
 	if (!fdb)
 		return -ENOMEM;
 
@@ -3475,32 +3593,34 @@ static int rocker_port_fdb(struct rocker_port *rocker_port,
 	found = rocker_fdb_tbl_find(rocker, fdb);
 
 	if (removing && found) {
-		kfree(fdb);
-		hash_del(&found->entry);
+		rocker_port_kfree(trans, fdb);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
 	} else if (!removing && !found) {
-		hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32);
 	}
 
 	spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags);
 
 	/* Check if adding and already exists, or removing and can't find */
 	if (!found != !removing) {
-		kfree(fdb);
+		rocker_port_kfree(trans, fdb);
 		if (!found && removing)
 			return 0;
 		/* Refreshing existing to update aging timers */
 		flags |= ROCKER_OP_FLAG_REFRESH;
 	}
 
-	return rocker_port_fdb_learn(rocker_port, flags, addr, vlan_id);
+	return rocker_port_fdb_learn(rocker_port, trans, flags, addr, vlan_id);
 }
 
-static int rocker_port_fdb_flush(struct rocker_port *rocker_port)
+static int rocker_port_fdb_flush(struct rocker_port *rocker_port,
+				 enum switchdev_trans trans, int flags)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_fdb_tbl_entry *found;
 	unsigned long lock_flags;
-	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE;
 	struct hlist_node *tmp;
 	int bkt;
 	int err = 0;
@@ -3509,6 +3629,8 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port)
 	    rocker_port->stp_state == BR_STATE_FORWARDING)
 		return 0;
 
+	flags |= ROCKER_OP_FLAG_REMOVE;
+
 	spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags);
 
 	hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) {
@@ -3516,12 +3638,13 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port)
 			continue;
 		if (!found->learned)
 			continue;
-		err = rocker_port_fdb_learn(rocker_port, flags,
+		err = rocker_port_fdb_learn(rocker_port, trans, flags,
 					    found->key.addr,
 					    found->key.vlan_id);
 		if (err)
 			goto err_out;
-		hash_del(&found->entry);
+		if (trans != SWITCHDEV_TRANS_PREPARE)
+			hash_del(&found->entry);
 	}
 
 err_out:
@@ -3531,7 +3654,8 @@ err_out:
 }
 
 static int rocker_port_router_mac(struct rocker_port *rocker_port,
-				  int flags, __be16 vlan_id)
+				  enum switchdev_trans trans, int flags,
+				  __be16 vlan_id)
 {
 	u32 in_pport_mask = 0xffffffff;
 	__be16 eth_type;
@@ -3544,7 +3668,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port,
 		vlan_id = rocker_port->internal_vlan_id;
 
 	eth_type = htons(ETH_P_IP);
-	err = rocker_flow_tbl_term_mac(rocker_port,
+	err = rocker_flow_tbl_term_mac(rocker_port, trans,
 				       rocker_port->pport, in_pport_mask,
 				       eth_type, rocker_port->dev->dev_addr,
 				       dst_mac_mask, vlan_id, vlan_id_mask,
@@ -3553,7 +3677,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port,
 		return err;
 
 	eth_type = htons(ETH_P_IPV6);
-	err = rocker_flow_tbl_term_mac(rocker_port,
+	err = rocker_flow_tbl_term_mac(rocker_port, trans,
 				       rocker_port->pport, in_pport_mask,
 				       eth_type, rocker_port->dev->dev_addr,
 				       dst_mac_mask, vlan_id, vlan_id_mask,
@@ -3562,13 +3686,13 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port,
 	return err;
 }
 
-static int rocker_port_fwding(struct rocker_port *rocker_port)
+static int rocker_port_fwding(struct rocker_port *rocker_port,
+			      enum switchdev_trans trans, int flags)
 {
 	bool pop_vlan;
 	u32 out_pport;
 	__be16 vlan_id;
 	u16 vid;
-	int flags = ROCKER_OP_FLAG_NOWAIT;
 	int err;
 
 	/* Port will be forwarding-enabled if its STP state is LEARNING
@@ -3588,9 +3712,8 @@ static int rocker_port_fwding(struct rocker_port *rocker_port)
 			continue;
 		vlan_id = htons(vid);
 		pop_vlan = rocker_vlan_id_is_internal(vlan_id);
-		err = rocker_group_l2_interface(rocker_port, flags,
-						vlan_id, out_pport,
-						pop_vlan);
+		err = rocker_group_l2_interface(rocker_port, trans, flags,
+						vlan_id, out_pport, pop_vlan);
 		if (err) {
 			netdev_err(rocker_port->dev,
 				   "Error (%d) port VLAN l2 group for pport %d\n",
@@ -3602,13 +3725,21 @@ static int rocker_port_fwding(struct rocker_port *rocker_port)
 	return 0;
 }
 
-static int rocker_port_stp_update(struct rocker_port *rocker_port, u8 state)
+static int rocker_port_stp_update(struct rocker_port *rocker_port,
+				  enum switchdev_trans trans, int flags,
+				  u8 state)
 {
 	bool want[ROCKER_CTRL_MAX] = { 0, };
-	int flags;
+	bool prev_ctrls[ROCKER_CTRL_MAX];
+	u8 prev_state;
 	int err;
 	int i;
 
+	if (trans == SWITCHDEV_TRANS_PREPARE) {
+		memcpy(prev_ctrls, rocker_port->ctrls, sizeof(prev_ctrls));
+		prev_state = rocker_port->stp_state;
+	}
+
 	if (rocker_port->stp_state == state)
 		return 0;
 
@@ -3636,45 +3767,57 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, u8 state)
 
 	for (i = 0; i < ROCKER_CTRL_MAX; i++) {
 		if (want[i] != rocker_port->ctrls[i]) {
-			flags = ROCKER_OP_FLAG_NOWAIT |
-				(want[i] ? 0 : ROCKER_OP_FLAG_REMOVE);
-			err = rocker_port_ctrl(rocker_port, flags,
+			int ctrl_flags = flags |
+					 (want[i] ? 0 : ROCKER_OP_FLAG_REMOVE);
+			err = rocker_port_ctrl(rocker_port, trans, ctrl_flags,
 					       &rocker_ctrls[i]);
 			if (err)
-				return err;
+				goto err_out;
 			rocker_port->ctrls[i] = want[i];
 		}
 	}
 
-	err = rocker_port_fdb_flush(rocker_port);
+	err = rocker_port_fdb_flush(rocker_port, trans, flags);
 	if (err)
-		return err;
+		goto err_out;
+
+	err = rocker_port_fwding(rocker_port, trans, flags);
 
-	return rocker_port_fwding(rocker_port);
+err_out:
+	if (trans == SWITCHDEV_TRANS_PREPARE) {
+		memcpy(rocker_port->ctrls, prev_ctrls, sizeof(prev_ctrls));
+		rocker_port->stp_state = prev_state;
+	}
+
+	return err;
 }
 
-static int rocker_port_fwd_enable(struct rocker_port *rocker_port)
+static int rocker_port_fwd_enable(struct rocker_port *rocker_port,
+				  enum switchdev_trans trans, int flags)
 {
 	if (rocker_port_is_bridged(rocker_port))
 		/* bridge STP will enable port */
 		return 0;
 
 	/* port is not bridged, so simulate going to FORWARDING state */
-	return rocker_port_stp_update(rocker_port, BR_STATE_FORWARDING);
+	return rocker_port_stp_update(rocker_port, trans, flags,
+				      BR_STATE_FORWARDING);
 }
 
-static int rocker_port_fwd_disable(struct rocker_port *rocker_port)
+static int rocker_port_fwd_disable(struct rocker_port *rocker_port,
+				   enum switchdev_trans trans, int flags)
 {
 	if (rocker_port_is_bridged(rocker_port))
 		/* bridge STP will disable port */
 		return 0;
 
 	/* port is not bridged, so simulate going to DISABLED state */
-	return rocker_port_stp_update(rocker_port, BR_STATE_DISABLED);
+	return rocker_port_stp_update(rocker_port, trans, flags,
+				      BR_STATE_DISABLED);
 }
 
 static struct rocker_internal_vlan_tbl_entry *
-rocker_internal_vlan_tbl_find(struct rocker *rocker, int ifindex)
+rocker_internal_vlan_tbl_find(const struct rocker *rocker, int ifindex)
 {
 	struct rocker_internal_vlan_tbl_entry *found;
 
@@ -3729,8 +3872,9 @@ found:
 	return found->vlan_id;
 }
 
-static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port,
-					     int ifindex)
+static void
+rocker_port_internal_vlan_id_put(const struct rocker_port *rocker_port,
+				 int ifindex)
 {
 	struct rocker *rocker = rocker_port->rocker;
 	struct rocker_internal_vlan_tbl_entry *found;
@@ -3758,11 +3902,12 @@ not_found:
 	spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, lock_flags);
 }
 
-static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst,
-				int dst_len, struct fib_info *fi, u32 tb_id,
-				int flags)
+static int rocker_port_fib_ipv4(struct rocker_port *rocker_port,
+				enum switchdev_trans trans, __be32 dst,
+				int dst_len, const struct fib_info *fi,
+				u32 tb_id, int flags)
 {
-	struct fib_nh *nh;
+	const struct fib_nh *nh;
 	__be16 eth_type = htons(ETH_P_IP);
 	__be32 dst_mask = inet_make_mask(dst_len);
 	__be16 internal_vlan_id = rocker_port->internal_vlan_id;
@@ -3782,7 +3927,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst,
 	has_gw = !!nh->nh_gw;
 
 	if (has_gw && nh_on_port) {
-		err = rocker_port_ipv4_nh(rocker_port, flags,
+		err = rocker_port_ipv4_nh(rocker_port, trans, flags,
 					  nh->nh_gw, &index);
 		if (err)
 			return err;
@@ -3793,7 +3938,7 @@ static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, __be32 dst,
 		group_id = ROCKER_GROUP_L2_INTERFACE(internal_vlan_id, 0);
 	}
 
-	err = rocker_flow_tbl_ucast4_routing(rocker_port, eth_type, dst,
+	err = rocker_flow_tbl_ucast4_routing(rocker_port, trans, eth_type, dst,
 					     dst_mask, priority, goto_tbl,
 					     group_id, flags);
 	if (err)
@@ -3832,7 +3977,7 @@ static int rocker_port_open(struct net_device *dev)
 		goto err_request_rx_irq;
 	}
 
-	err = rocker_port_fwd_enable(rocker_port);
+	err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE, 0);
 	if (err)
 		goto err_fwd_enable;
 
@@ -3859,7 +4004,8 @@ static int rocker_port_stop(struct net_device *dev)
 	rocker_port_set_enable(rocker_port, false);
 	napi_disable(&rocker_port->napi_rx);
 	napi_disable(&rocker_port->napi_tx);
-	rocker_port_fwd_disable(rocker_port);
+	rocker_port_fwd_disable(rocker_port, SWITCHDEV_TRANS_NONE,
+				ROCKER_OP_FLAG_NOWAIT);
 	free_irq(rocker_msix_rx_vector(rocker_port), rocker_port);
 	free_irq(rocker_msix_tx_vector(rocker_port), rocker_port);
 	rocker_port_dma_rings_fini(rocker_port);
@@ -3867,12 +4013,12 @@ static int rocker_port_stop(struct net_device *dev)
 	return 0;
 }
 
-static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port,
-				       struct rocker_desc_info *desc_info)
+static void rocker_tx_desc_frags_unmap(const struct rocker_port *rocker_port,
+				       const struct rocker_desc_info *desc_info)
 {
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	struct pci_dev *pdev = rocker->pdev;
-	struct rocker_tlv *attrs[ROCKER_TLV_TX_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_TX_MAX + 1];
 	struct rocker_tlv *attr;
 	int rem;
 
@@ -3880,7 +4026,7 @@ static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port,
 	if (!attrs[ROCKER_TLV_TX_FRAGS])
 		return;
 	rocker_tlv_for_each_nested(attr, attrs[ROCKER_TLV_TX_FRAGS], rem) {
-		struct rocker_tlv *frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_MAX + 1];
+		const struct rocker_tlv *frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_MAX + 1];
 		dma_addr_t dma_handle;
 		size_t len;
 
@@ -3897,11 +4043,11 @@ static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port,
 	}
 }
 
-static int rocker_tx_desc_frag_map_put(struct rocker_port *rocker_port,
+static int rocker_tx_desc_frag_map_put(const struct rocker_port *rocker_port,
 				       struct rocker_desc_info *desc_info,
 				       char *buf, size_t buf_len)
 {
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	struct pci_dev *pdev = rocker->pdev;
 	dma_addr_t dma_handle;
 	struct rocker_tlv *frag;
@@ -4006,269 +4152,359 @@ static int rocker_port_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static int rocker_port_vlan_rx_add_vid(struct net_device *dev,
-				       __be16 proto, u16 vid)
+static int rocker_port_get_phys_port_name(struct net_device *dev,
+					  char *buf, size_t len)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
+	struct port_name name = { .buf = buf, .len = len };
 	int err;
 
-	err = rocker_port_vlan(rocker_port, 0, vid);
-	if (err)
-		return err;
+	err = rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
+			      rocker_cmd_get_port_settings_prep, NULL,
+			      rocker_cmd_get_port_settings_phys_name_proc,
+			      &name);
 
-	return rocker_port_router_mac(rocker_port, 0, htons(vid));
+	return err ? -EOPNOTSUPP : 0;
 }
 
-static int rocker_port_vlan_rx_kill_vid(struct net_device *dev,
-					__be16 proto, u16 vid)
+static const struct net_device_ops rocker_port_netdev_ops = {
+	.ndo_open			= rocker_port_open,
+	.ndo_stop			= rocker_port_stop,
+	.ndo_start_xmit			= rocker_port_xmit,
+	.ndo_set_mac_address		= rocker_port_set_mac_address,
+	.ndo_bridge_getlink		= switchdev_port_bridge_getlink,
+	.ndo_bridge_setlink		= switchdev_port_bridge_setlink,
+	.ndo_bridge_dellink		= switchdev_port_bridge_dellink,
+	.ndo_fdb_add			= switchdev_port_fdb_add,
+	.ndo_fdb_del			= switchdev_port_fdb_del,
+	.ndo_fdb_dump			= switchdev_port_fdb_dump,
+	.ndo_get_phys_port_name		= rocker_port_get_phys_port_name,
+};
+
+/********************
+ * swdev interface
+ ********************/
+
+static int rocker_port_attr_get(struct net_device *dev,
+				struct switchdev_attr *attr)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	int err;
+	const struct rocker_port *rocker_port = netdev_priv(dev);
+	const struct rocker *rocker = rocker_port->rocker;
 
-	err = rocker_port_router_mac(rocker_port, ROCKER_OP_FLAG_REMOVE,
-				     htons(vid));
-	if (err)
-		return err;
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_PORT_PARENT_ID:
+		attr->u.ppid.id_len = sizeof(rocker->hw.id);
+		memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len);
+		break;
+	case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS:
+		attr->u.brport_flags = rocker_port->brport_flags;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	return rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, vid);
+	return 0;
 }
 
-static int rocker_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
-			       struct net_device *dev,
-			       const unsigned char *addr, u16 vid,
-			       u16 nlm_flags)
+static void rocker_port_trans_abort(const struct rocker_port *rocker_port)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	__be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, NULL);
-	int flags = 0;
-
-	if (!rocker_port_is_bridged(rocker_port))
-		return -EINVAL;
+	struct list_head *mem, *tmp;
 
-	return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+	list_for_each_safe(mem, tmp, &rocker_port->trans_mem) {
+		list_del(mem);
+		kfree(mem);
+	}
 }
 
-static int rocker_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
-			       struct net_device *dev,
-			       const unsigned char *addr, u16 vid)
+static int rocker_port_brport_flags_set(struct rocker_port *rocker_port,
+					enum switchdev_trans trans,
+					unsigned long brport_flags)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	__be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, NULL);
-	int flags = ROCKER_OP_FLAG_REMOVE;
+	unsigned long orig_flags;
+	int err = 0;
 
-	if (!rocker_port_is_bridged(rocker_port))
-		return -EINVAL;
+	orig_flags = rocker_port->brport_flags;
+	rocker_port->brport_flags = brport_flags;
+	if ((orig_flags ^ rocker_port->brport_flags) & BR_LEARNING)
+		err = rocker_port_set_learning(rocker_port, trans);
+
+	if (trans == SWITCHDEV_TRANS_PREPARE)
+		rocker_port->brport_flags = orig_flags;
 
-	return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+	return err;
 }
 
-static int rocker_fdb_fill_info(struct sk_buff *skb,
-				struct rocker_port *rocker_port,
-				const unsigned char *addr, u16 vid,
-				u32 portid, u32 seq, int type,
-				unsigned int flags)
+static int rocker_port_attr_set(struct net_device *dev,
+				struct switchdev_attr *attr)
 {
-	struct nlmsghdr *nlh;
-	struct ndmsg *ndm;
+	struct rocker_port *rocker_port = netdev_priv(dev);
+	int err = 0;
 
-	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
-	if (!nlh)
-		return -EMSGSIZE;
+	switch (attr->trans) {
+	case SWITCHDEV_TRANS_PREPARE:
+		BUG_ON(!list_empty(&rocker_port->trans_mem));
+		break;
+	case SWITCHDEV_TRANS_ABORT:
+		rocker_port_trans_abort(rocker_port);
+		return 0;
+	default:
+		break;
+	}
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_PORT_STP_STATE:
+		err = rocker_port_stp_update(rocker_port, attr->trans,
+					     ROCKER_OP_FLAG_NOWAIT,
+					     attr->u.stp_state);
+		break;
+	case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS:
+		err = rocker_port_brport_flags_set(rocker_port, attr->trans,
+						   attr->u.brport_flags);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
 
-	ndm = nlmsg_data(nlh);
-	ndm->ndm_family	 = AF_BRIDGE;
-	ndm->ndm_pad1    = 0;
-	ndm->ndm_pad2    = 0;
-	ndm->ndm_flags	 = NTF_SELF;
-	ndm->ndm_type	 = 0;
-	ndm->ndm_ifindex = rocker_port->dev->ifindex;
-	ndm->ndm_state   = NUD_REACHABLE;
+static int rocker_port_vlan_add(struct rocker_port *rocker_port,
+				enum switchdev_trans trans, u16 vid, u16 flags)
+{
+	int err;
 
-	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
-		goto nla_put_failure;
+	/* XXX deal with flags for PVID and untagged */
 
-	if (vid && nla_put_u16(skb, NDA_VLAN, vid))
-		goto nla_put_failure;
+	err = rocker_port_vlan(rocker_port, trans, 0, vid);
+	if (err)
+		return err;
 
-	nlmsg_end(skb, nlh);
-	return 0;
+	err = rocker_port_router_mac(rocker_port, trans, 0, htons(vid));
+	if (err)
+		rocker_port_vlan(rocker_port, trans,
+				 ROCKER_OP_FLAG_REMOVE, vid);
 
-nla_put_failure:
-	nlmsg_cancel(skb, nlh);
-	return -EMSGSIZE;
+	return err;
 }
 
-static int rocker_port_fdb_dump(struct sk_buff *skb,
-				struct netlink_callback *cb,
-				struct net_device *dev,
-				struct net_device *filter_dev,
-				int idx)
+static int rocker_port_vlans_add(struct rocker_port *rocker_port,
+				 enum switchdev_trans trans,
+				 const struct switchdev_obj_vlan *vlan)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	struct rocker *rocker = rocker_port->rocker;
-	struct rocker_fdb_tbl_entry *found;
-	struct hlist_node *tmp;
-	int bkt;
-	unsigned long lock_flags;
-	const unsigned char *addr;
 	u16 vid;
 	int err;
 
-	spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags);
-	hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) {
-		if (found->key.pport != rocker_port->pport)
-			continue;
-		if (idx < cb->args[0])
-			goto skip;
-		addr = found->key.addr;
-		vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id);
-		err = rocker_fdb_fill_info(skb, rocker_port, addr, vid,
-					   NETLINK_CB(cb->skb).portid,
-					   cb->nlh->nlmsg_seq,
-					   RTM_NEWNEIGH, NLM_F_MULTI);
-		if (err < 0)
-			break;
-skip:
-		++idx;
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		err = rocker_port_vlan_add(rocker_port, trans,
+					   vid, vlan->flags);
+		if (err)
+			return err;
 	}
-	spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags);
-	return idx;
+
+	return 0;
 }
 
-static int rocker_port_bridge_setlink(struct net_device *dev,
-				      struct nlmsghdr *nlh, u16 flags)
+static int rocker_port_fdb_add(struct rocker_port *rocker_port,
+			       enum switchdev_trans trans,
+			       const struct switchdev_obj_fdb *fdb)
+{
+	__be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL);
+	int flags = 0;
+
+	if (!rocker_port_is_bridged(rocker_port))
+		return -EINVAL;
+
+	return rocker_port_fdb(rocker_port, trans, fdb->addr, vlan_id, flags);
+}
+
+static int rocker_port_obj_add(struct net_device *dev,
+			       struct switchdev_obj *obj)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
-	struct nlattr *protinfo;
-	struct nlattr *attr;
-	int err;
+	const struct switchdev_obj_ipv4_fib *fib4;
+	int err = 0;
 
-	protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg),
-				   IFLA_PROTINFO);
-	if (protinfo) {
-		attr = nla_find_nested(protinfo, IFLA_BRPORT_LEARNING);
-		if (attr) {
-			if (nla_len(attr) < sizeof(u8))
-				return -EINVAL;
-
-			if (nla_get_u8(attr))
-				rocker_port->brport_flags |= BR_LEARNING;
-			else
-				rocker_port->brport_flags &= ~BR_LEARNING;
-			err = rocker_port_set_learning(rocker_port);
-			if (err)
-				return err;
-		}
-		attr = nla_find_nested(protinfo, IFLA_BRPORT_LEARNING_SYNC);
-		if (attr) {
-			if (nla_len(attr) < sizeof(u8))
-				return -EINVAL;
-
-			if (nla_get_u8(attr))
-				rocker_port->brport_flags |= BR_LEARNING_SYNC;
-			else
-				rocker_port->brport_flags &= ~BR_LEARNING_SYNC;
-		}
+	switch (obj->trans) {
+	case SWITCHDEV_TRANS_PREPARE:
+		BUG_ON(!list_empty(&rocker_port->trans_mem));
+		break;
+	case SWITCHDEV_TRANS_ABORT:
+		rocker_port_trans_abort(rocker_port);
+		return 0;
+	default:
+		break;
 	}
 
-	return 0;
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = rocker_port_vlans_add(rocker_port, obj->trans,
+					    &obj->u.vlan);
+		break;
+	case SWITCHDEV_OBJ_IPV4_FIB:
+		fib4 = &obj->u.ipv4_fib;
+		err = rocker_port_fib_ipv4(rocker_port, obj->trans,
+					   htonl(fib4->dst), fib4->dst_len,
+					   fib4->fi, fib4->tb_id, 0);
+		break;
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = rocker_port_fdb_add(rocker_port, obj->trans, &obj->u.fdb);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
 }
 
-static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-				      struct net_device *dev,
-				      u32 filter_mask, int nlflags)
+static int rocker_port_vlan_del(struct rocker_port *rocker_port,
+				u16 vid, u16 flags)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	u16 mode = BRIDGE_MODE_UNDEF;
-	u32 mask = BR_LEARNING | BR_LEARNING_SYNC;
+	int err;
+
+	err = rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE,
+				     ROCKER_OP_FLAG_REMOVE, htons(vid));
+	if (err)
+		return err;
 
-	return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode,
-				       rocker_port->brport_flags, mask,
-				       nlflags);
+	return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE,
+				ROCKER_OP_FLAG_REMOVE, vid);
 }
 
-static int rocker_port_get_phys_port_name(struct net_device *dev,
-					  char *buf, size_t len)
+static int rocker_port_vlans_del(struct rocker_port *rocker_port,
+				 const struct switchdev_obj_vlan *vlan)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	struct port_name name = { .buf = buf, .len = len };
+	u16 vid;
 	int err;
 
-	err = rocker_cmd_exec(rocker_port->rocker, rocker_port,
-			      rocker_cmd_get_port_settings_prep, NULL,
-			      rocker_cmd_get_port_settings_phys_name_proc,
-			      &name, false);
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		err = rocker_port_vlan_del(rocker_port, vid, vlan->flags);
+		if (err)
+			return err;
+	}
 
-	return err ? -EOPNOTSUPP : 0;
+	return 0;
 }
 
-static const struct net_device_ops rocker_port_netdev_ops = {
-	.ndo_open			= rocker_port_open,
-	.ndo_stop			= rocker_port_stop,
-	.ndo_start_xmit			= rocker_port_xmit,
-	.ndo_set_mac_address		= rocker_port_set_mac_address,
-	.ndo_vlan_rx_add_vid		= rocker_port_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid		= rocker_port_vlan_rx_kill_vid,
-	.ndo_fdb_add			= rocker_port_fdb_add,
-	.ndo_fdb_del			= rocker_port_fdb_del,
-	.ndo_fdb_dump			= rocker_port_fdb_dump,
-	.ndo_bridge_setlink		= rocker_port_bridge_setlink,
-	.ndo_bridge_getlink		= rocker_port_bridge_getlink,
-	.ndo_get_phys_port_name		= rocker_port_get_phys_port_name,
-};
+static int rocker_port_fdb_del(struct rocker_port *rocker_port,
+			       enum switchdev_trans trans,
+			       const struct switchdev_obj_fdb *fdb)
+{
+	__be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL);
+	int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE;
 
-/********************
- * swdev interface
- ********************/
+	if (!rocker_port_is_bridged(rocker_port))
+		return -EINVAL;
+
+	return rocker_port_fdb(rocker_port, trans, fdb->addr, vlan_id, flags);
+}
 
-static int rocker_port_swdev_parent_id_get(struct net_device *dev,
-					   struct netdev_phys_item_id *psid)
+static int rocker_port_obj_del(struct net_device *dev,
+			       struct switchdev_obj *obj)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
-	struct rocker *rocker = rocker_port->rocker;
+	const struct switchdev_obj_ipv4_fib *fib4;
+	int err = 0;
 
-	psid->id_len = sizeof(rocker->hw.id);
-	memcpy(&psid->id, &rocker->hw.id, psid->id_len);
-	return 0;
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = rocker_port_vlans_del(rocker_port, &obj->u.vlan);
+		break;
+	case SWITCHDEV_OBJ_IPV4_FIB:
+		fib4 = &obj->u.ipv4_fib;
+		err = rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE,
+					   htonl(fib4->dst), fib4->dst_len,
+					   fib4->fi, fib4->tb_id,
+					   ROCKER_OP_FLAG_REMOVE);
+		break;
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = rocker_port_fdb_del(rocker_port, obj->trans, &obj->u.fdb);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
 }
 
-static int rocker_port_swdev_port_stp_update(struct net_device *dev, u8 state)
+static int rocker_port_fdb_dump(const struct rocker_port *rocker_port,
+				struct switchdev_obj *obj)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
+	struct rocker *rocker = rocker_port->rocker;
+	struct switchdev_obj_fdb *fdb = &obj->u.fdb;
+	struct rocker_fdb_tbl_entry *found;
+	struct hlist_node *tmp;
+	unsigned long lock_flags;
+	int bkt;
+	int err = 0;
 
-	return rocker_port_stp_update(rocker_port, state);
+	spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags);
+	hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) {
+		if (found->key.pport != rocker_port->pport)
+			continue;
+		fdb->addr = found->key.addr;
+		fdb->vid = rocker_port_vlan_to_vid(rocker_port,
+						   found->key.vlan_id);
+		err = obj->cb(rocker_port->dev, obj);
+		if (err)
+			break;
+	}
+	spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags);
+
+	return err;
 }
 
-static int rocker_port_swdev_fib_ipv4_add(struct net_device *dev,
-					  __be32 dst, int dst_len,
-					  struct fib_info *fi,
-					  u8 tos, u8 type,
-					  u32 nlflags, u32 tb_id)
+static int rocker_port_vlan_dump(const struct rocker_port *rocker_port,
+				 struct switchdev_obj *obj)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	int flags = 0;
+	struct switchdev_obj_vlan *vlan = &obj->u.vlan;
+	u16 vid;
+	int err = 0;
 
-	return rocker_port_fib_ipv4(rocker_port, dst, dst_len,
-				    fi, tb_id, flags);
+	for (vid = 1; vid < VLAN_N_VID; vid++) {
+		if (!test_bit(vid, rocker_port->vlan_bitmap))
+			continue;
+		vlan->flags = 0;
+		if (rocker_vlan_id_is_internal(htons(vid)))
+			vlan->flags |= BRIDGE_VLAN_INFO_PVID;
+		vlan->vid_begin = vlan->vid_end = vid;
+		err = obj->cb(rocker_port->dev, obj);
+		if (err)
+			break;
+	}
+
+	return err;
 }
 
-static int rocker_port_swdev_fib_ipv4_del(struct net_device *dev,
-					  __be32 dst, int dst_len,
-					  struct fib_info *fi,
-					  u8 tos, u8 type, u32 tb_id)
+static int rocker_port_obj_dump(struct net_device *dev,
+				struct switchdev_obj *obj)
 {
-	struct rocker_port *rocker_port = netdev_priv(dev);
-	int flags = ROCKER_OP_FLAG_REMOVE;
+	const struct rocker_port *rocker_port = netdev_priv(dev);
+	int err = 0;
 
-	return rocker_port_fib_ipv4(rocker_port, dst, dst_len,
-				    fi, tb_id, flags);
+	switch (obj->id) {
+	case SWITCHDEV_OBJ_PORT_FDB:
+		err = rocker_port_fdb_dump(rocker_port, obj);
+		break;
+	case SWITCHDEV_OBJ_PORT_VLAN:
+		err = rocker_port_vlan_dump(rocker_port, obj);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
 }
 
-static const struct swdev_ops rocker_port_swdev_ops = {
-	.swdev_parent_id_get		= rocker_port_swdev_parent_id_get,
-	.swdev_port_stp_update		= rocker_port_swdev_port_stp_update,
-	.swdev_fib_ipv4_add		= rocker_port_swdev_fib_ipv4_add,
-	.swdev_fib_ipv4_del		= rocker_port_swdev_fib_ipv4_del,
+static const struct switchdev_ops rocker_port_switchdev_ops = {
+	.switchdev_port_attr_get	= rocker_port_attr_get,
+	.switchdev_port_attr_set	= rocker_port_attr_set,
+	.switchdev_port_obj_add		= rocker_port_obj_add,
+	.switchdev_port_obj_del		= rocker_port_obj_del,
+	.switchdev_port_obj_dump	= rocker_port_obj_dump,
 };
 
 /********************
@@ -4332,8 +4568,7 @@ static void rocker_port_get_strings(struct net_device *netdev, u32 stringset,
 }
 
 static int
-rocker_cmd_get_port_stats_prep(struct rocker *rocker,
-			       struct rocker_port *rocker_port,
+rocker_cmd_get_port_stats_prep(const struct rocker_port *rocker_port,
 			       struct rocker_desc_info *desc_info,
 			       void *priv)
 {
@@ -4357,14 +4592,13 @@ rocker_cmd_get_port_stats_prep(struct rocker *rocker,
 }
 
 static int
-rocker_cmd_get_port_stats_ethtool_proc(struct rocker *rocker,
-				       struct rocker_port *rocker_port,
-				       struct rocker_desc_info *desc_info,
+rocker_cmd_get_port_stats_ethtool_proc(const struct rocker_port *rocker_port,
+				       const struct rocker_desc_info *desc_info,
 				       void *priv)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
-	struct rocker_tlv *stats_attrs[ROCKER_TLV_CMD_PORT_STATS_MAX + 1];
-	struct rocker_tlv *pattr;
+	const struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+	const struct rocker_tlv *stats_attrs[ROCKER_TLV_CMD_PORT_STATS_MAX + 1];
+	const struct rocker_tlv *pattr;
 	u32 pport;
 	u64 *data = priv;
 	int i;
@@ -4398,10 +4632,10 @@ rocker_cmd_get_port_stats_ethtool_proc(struct rocker *rocker,
 static int rocker_cmd_get_port_stats_ethtool(struct rocker_port *rocker_port,
 					     void *priv)
 {
-	return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+	return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0,
 			       rocker_cmd_get_port_stats_prep, NULL,
 			       rocker_cmd_get_port_stats_ethtool_proc,
-			       priv, false);
+			       priv);
 }
 
 static void rocker_port_get_stats(struct net_device *dev,
@@ -4415,8 +4649,6 @@ static void rocker_port_get_stats(struct net_device *dev,
 		for (i = 0; i < ARRAY_SIZE(rocker_port_stats); ++i)
 			data[i] = 0;
 	}
-
-	return;
 }
 
 static int rocker_port_get_sset_count(struct net_device *netdev, int sset)
@@ -4451,8 +4683,8 @@ static struct rocker_port *rocker_port_napi_tx_get(struct napi_struct *napi)
 static int rocker_port_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct rocker_port *rocker_port = rocker_port_napi_tx_get(napi);
-	struct rocker *rocker = rocker_port->rocker;
-	struct rocker_desc_info *desc_info;
+	const struct rocker *rocker = rocker_port->rocker;
+	const struct rocker_desc_info *desc_info;
 	u32 credits = 0;
 	int err;
 
@@ -4470,8 +4702,9 @@ static int rocker_port_poll_tx(struct napi_struct *napi, int budget)
 		if (err == 0) {
 			rocker_port->dev->stats.tx_packets++;
 			rocker_port->dev->stats.tx_bytes += skb->len;
-		} else
+		} else {
 			rocker_port->dev->stats.tx_errors++;
+		}
 
 		dev_kfree_skb_any(skb);
 		credits++;
@@ -4486,11 +4719,11 @@ static int rocker_port_poll_tx(struct napi_struct *napi, int budget)
 	return 0;
 }
 
-static int rocker_port_rx_proc(struct rocker *rocker,
-			       struct rocker_port *rocker_port,
+static int rocker_port_rx_proc(const struct rocker *rocker,
+			       const struct rocker_port *rocker_port,
 			       struct rocker_desc_info *desc_info)
 {
-	struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
+	const struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
 	struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info);
 	size_t rx_len;
 
@@ -4512,7 +4745,7 @@ static int rocker_port_rx_proc(struct rocker *rocker,
 
 	netif_receive_skb(skb);
 
-	return rocker_dma_rx_ring_skb_alloc(rocker, rocker_port, desc_info);
+	return rocker_dma_rx_ring_skb_alloc(rocker_port, desc_info);
 }
 
 static struct rocker_port *rocker_port_napi_rx_get(struct napi_struct *napi)
@@ -4523,7 +4756,7 @@ static struct rocker_port *rocker_port_napi_rx_get(struct napi_struct *napi)
 static int rocker_port_poll_rx(struct napi_struct *napi, int budget)
 {
 	struct rocker_port *rocker_port = rocker_port_napi_rx_get(napi);
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	struct rocker_desc_info *desc_info;
 	u32 credits = 0;
 	int err;
@@ -4563,9 +4796,9 @@ static int rocker_port_poll_rx(struct napi_struct *napi, int budget)
  * PCI driver ops
  *****************/
 
-static void rocker_carrier_init(struct rocker_port *rocker_port)
+static void rocker_carrier_init(const struct rocker_port *rocker_port)
 {
-	struct rocker *rocker = rocker_port->rocker;
+	const struct rocker *rocker = rocker_port->rocker;
 	u64 link_status = rocker_read64(rocker, PORT_PHYS_LINK_STATUS);
 	bool link_up;
 
@@ -4576,23 +4809,26 @@ static void rocker_carrier_init(struct rocker_port *rocker_port)
 		netif_carrier_off(rocker_port->dev);
 }
 
-static void rocker_remove_ports(struct rocker *rocker)
+static void rocker_remove_ports(const struct rocker *rocker)
 {
 	struct rocker_port *rocker_port;
 	int i;
 
 	for (i = 0; i < rocker->port_count; i++) {
 		rocker_port = rocker->ports[i];
-		rocker_port_ig_tbl(rocker_port, ROCKER_OP_FLAG_REMOVE);
+		if (!rocker_port)
+			continue;
+		rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE,
+				   ROCKER_OP_FLAG_REMOVE);
 		unregister_netdev(rocker_port->dev);
 	}
 	kfree(rocker->ports);
 }
 
-static void rocker_port_dev_addr_init(struct rocker *rocker,
-				      struct rocker_port *rocker_port)
+static void rocker_port_dev_addr_init(struct rocker_port *rocker_port)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct rocker *rocker = rocker_port->rocker;
+	const struct pci_dev *pdev = rocker->pdev;
 	int err;
 
 	err = rocker_cmd_get_port_settings_macaddr(rocker_port,
@@ -4605,9 +4841,10 @@ static void rocker_port_dev_addr_init(struct rocker *rocker,
 
 static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 {
-	struct pci_dev *pdev = rocker->pdev;
+	const struct pci_dev *pdev = rocker->pdev;
 	struct rocker_port *rocker_port;
 	struct net_device *dev;
+	u16 untagged_vid = 0;
 	int err;
 
 	dev = alloc_etherdev(sizeof(struct rocker_port));
@@ -4619,20 +4856,19 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	rocker_port->port_number = port_number;
 	rocker_port->pport = port_number + 1;
 	rocker_port->brport_flags = BR_LEARNING | BR_LEARNING_SYNC;
+	INIT_LIST_HEAD(&rocker_port->trans_mem);
 
-	rocker_port_dev_addr_init(rocker, rocker_port);
+	rocker_port_dev_addr_init(rocker_port);
 	dev->netdev_ops = &rocker_port_netdev_ops;
 	dev->ethtool_ops = &rocker_port_ethtool_ops;
-	dev->swdev_ops = &rocker_port_swdev_ops;
+	dev->switchdev_ops = &rocker_port_switchdev_ops;
 	netif_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
 		       NAPI_POLL_WEIGHT);
 	netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
 		       NAPI_POLL_WEIGHT);
 	rocker_carrier_init(rocker_port);
 
-	dev->features |= NETIF_F_NETNS_LOCAL |
-			 NETIF_F_HW_VLAN_CTAG_FILTER |
-			 NETIF_F_HW_SWITCH_OFFLOAD;
+	dev->features |= NETIF_F_NETNS_LOCAL;
 
 	err = register_netdev(dev);
 	if (err) {
@@ -4641,18 +4877,29 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	}
 	rocker->ports[port_number] = rocker_port;
 
-	rocker_port_set_learning(rocker_port);
+	rocker_port_set_learning(rocker_port, SWITCHDEV_TRANS_NONE);
 
-	rocker_port->internal_vlan_id =
-		rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex);
-	err = rocker_port_ig_tbl(rocker_port, 0);
+	err = rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, 0);
 	if (err) {
 		dev_err(&pdev->dev, "install ig port table failed\n");
 		goto err_port_ig_tbl;
 	}
 
+	rocker_port->internal_vlan_id =
+		rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex);
+
+	err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE,
+				   untagged_vid, 0);
+	if (err) {
+		netdev_err(rocker_port->dev, "install untagged VLAN failed\n");
+		goto err_untagged_vlan;
+	}
+
 	return 0;
 
+err_untagged_vlan:
+	rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE,
+			   ROCKER_OP_FLAG_REMOVE);
 err_port_ig_tbl:
 	unregister_netdev(dev);
 err_register_netdev:
@@ -4667,7 +4914,7 @@ static int rocker_probe_ports(struct rocker *rocker)
 	int err;
 
 	alloc_size = sizeof(struct rocker_port *) * rocker->port_count;
-	rocker->ports = kmalloc(alloc_size, GFP_KERNEL);
+	rocker->ports = kzalloc(alloc_size, GFP_KERNEL);
 	if (!rocker->ports)
 		return -ENOMEM;
 	for (i = 0; i < rocker->port_count; i++) {
@@ -4716,7 +4963,7 @@ err_enable_msix:
 	return err;
 }
 
-static void rocker_msix_fini(struct rocker *rocker)
+static void rocker_msix_fini(const struct rocker *rocker)
 {
 	pci_disable_msix(rocker->pdev);
 	kfree(rocker->msix_entries);
@@ -4882,7 +5129,7 @@ static struct pci_driver rocker_pci_driver = {
  * Net device notifier event handler
  ************************************/
 
-static bool rocker_port_dev_check(struct net_device *dev)
+static bool rocker_port_dev_check(const struct net_device *dev)
 {
 	return dev->netdev_ops == &rocker_port_netdev_ops;
 }
@@ -4890,45 +5137,55 @@ static bool rocker_port_dev_check(struct net_device *dev)
 static int rocker_port_bridge_join(struct rocker_port *rocker_port,
 				   struct net_device *bridge)
 {
+	u16 untagged_vid = 0;
 	int err;
 
+	/* Port is joining bridge, so the internal VLAN for the
+	 * port is going to change to the bridge internal VLAN.
+	 * Let's remove untagged VLAN (vid=0) from port and
+	 * re-add once internal VLAN has changed.
+	 */
+
+	err = rocker_port_vlan_del(rocker_port, untagged_vid, 0);
+	if (err)
+		return err;
+
 	rocker_port_internal_vlan_id_put(rocker_port,
 					 rocker_port->dev->ifindex);
+	rocker_port->internal_vlan_id =
+		rocker_port_internal_vlan_id_get(rocker_port, bridge->ifindex);
 
 	rocker_port->bridge_dev = bridge;
 
-	/* Use bridge internal VLAN ID for untagged pkts */
-	err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0);
-	if (err)
-		return err;
-	rocker_port->internal_vlan_id =
-		rocker_port_internal_vlan_id_get(rocker_port,
-						 bridge->ifindex);
-	return rocker_port_vlan(rocker_port, 0, 0);
+	return rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE,
+				    untagged_vid, 0);
 }
 
 static int rocker_port_bridge_leave(struct rocker_port *rocker_port)
 {
+	u16 untagged_vid = 0;
 	int err;
 
-	rocker_port_internal_vlan_id_put(rocker_port,
-					 rocker_port->bridge_dev->ifindex);
-
-	rocker_port->bridge_dev = NULL;
-
-	/* Use port internal VLAN ID for untagged pkts */
-	err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0);
+	err = rocker_port_vlan_del(rocker_port, untagged_vid, 0);
 	if (err)
 		return err;
+
+	rocker_port_internal_vlan_id_put(rocker_port,
+					 rocker_port->bridge_dev->ifindex);
 	rocker_port->internal_vlan_id =
 		rocker_port_internal_vlan_id_get(rocker_port,
 						 rocker_port->dev->ifindex);
-	err = rocker_port_vlan(rocker_port, 0, 0);
+
+	rocker_port->bridge_dev = NULL;
+
+	err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE,
+				   untagged_vid, 0);
 	if (err)
 		return err;
 
 	if (rocker_port->dev->flags & IFF_UP)
-		err = rocker_port_fwd_enable(rocker_port);
+		err = rocker_port_fwd_enable(rocker_port,
+					     SWITCHDEV_TRANS_NONE, 0);
 
 	return err;
 }
@@ -4987,10 +5244,12 @@ static struct notifier_block rocker_netdevice_nb __read_mostly = {
 static int rocker_neigh_update(struct net_device *dev, struct neighbour *n)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
-	int flags = (n->nud_state & NUD_VALID) ? 0 : ROCKER_OP_FLAG_REMOVE;
+	int flags = (n->nud_state & NUD_VALID ? 0 : ROCKER_OP_FLAG_REMOVE) |
+		    ROCKER_OP_FLAG_NOWAIT;
 	__be32 ip_addr = *(__be32 *)n->primary_key;
 
-	return rocker_port_ipv4_neigh(rocker_port, flags, ip_addr, n->ha);
+	return rocker_port_ipv4_neigh(rocker_port, SWITCHDEV_TRANS_NONE,
+				      flags, ip_addr, n->ha);
 }
 
 static int rocker_netevent_event(struct notifier_block *unused,
@@ -5038,7 +5297,7 @@ static int __init rocker_module_init(void)
 	return 0;
 
 err_pci_register_driver:
-	unregister_netdevice_notifier(&rocker_netevent_nb);
+	unregister_netevent_notifier(&rocker_netevent_nb);
 	unregister_netdevice_notifier(&rocker_netdevice_nb);
 	return err;
 }
diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h
index a4e9591d7457..c61fbf968036 100644
--- a/drivers/net/ethernet/rocker/rocker.h
+++ b/drivers/net/ethernet/rocker/rocker.h
@@ -65,9 +65,9 @@ enum {
 #define ROCKER_TEST_DMA_CTRL		0x0034
 
 /* Rocker test register ctrl */
-#define ROCKER_TEST_DMA_CTRL_CLEAR	(1 << 0)
-#define ROCKER_TEST_DMA_CTRL_FILL	(1 << 1)
-#define ROCKER_TEST_DMA_CTRL_INVERT	(1 << 2)
+#define ROCKER_TEST_DMA_CTRL_CLEAR	BIT(0)
+#define ROCKER_TEST_DMA_CTRL_FILL	BIT(1)
+#define ROCKER_TEST_DMA_CTRL_INVERT	BIT(2)
 
 /* Rocker DMA ring register offsets */
 #define ROCKER_DMA_DESC_ADDR(x)		(0x1000 + (x) * 32)  /* 8-byte */
@@ -79,7 +79,7 @@ enum {
 #define ROCKER_DMA_DESC_RES1(x)		(0x101c + (x) * 32)
 
 /* Rocker dma ctrl register bits */
-#define ROCKER_DMA_DESC_CTRL_RESET	(1 << 0)
+#define ROCKER_DMA_DESC_CTRL_RESET	BIT(0)
 
 /* Rocker DMA ring types */
 enum rocker_dma_type {
@@ -111,7 +111,7 @@ struct rocker_desc {
 	u16 comp_err;
 };
 
-#define ROCKER_DMA_DESC_COMP_ERR_GEN	(1 << 15)
+#define ROCKER_DMA_DESC_COMP_ERR_GEN	BIT(15)
 
 /* Rocker DMA TLV struct */
 struct rocker_tlv {
@@ -237,14 +237,14 @@ enum {
 	ROCKER_TLV_RX_MAX = __ROCKER_TLV_RX_MAX - 1,
 };
 
-#define ROCKER_RX_FLAGS_IPV4			(1 << 0)
-#define ROCKER_RX_FLAGS_IPV6			(1 << 1)
-#define ROCKER_RX_FLAGS_CSUM_CALC		(1 << 2)
-#define ROCKER_RX_FLAGS_IPV4_CSUM_GOOD		(1 << 3)
-#define ROCKER_RX_FLAGS_IP_FRAG			(1 << 4)
-#define ROCKER_RX_FLAGS_TCP			(1 << 5)
-#define ROCKER_RX_FLAGS_UDP			(1 << 6)
-#define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD	(1 << 7)
+#define ROCKER_RX_FLAGS_IPV4			BIT(0)
+#define ROCKER_RX_FLAGS_IPV6			BIT(1)
+#define ROCKER_RX_FLAGS_CSUM_CALC		BIT(2)
+#define ROCKER_RX_FLAGS_IPV4_CSUM_GOOD		BIT(3)
+#define ROCKER_RX_FLAGS_IP_FRAG			BIT(4)
+#define ROCKER_RX_FLAGS_TCP			BIT(5)
+#define ROCKER_RX_FLAGS_UDP			BIT(6)
+#define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD	BIT(7)
 
 enum {
 	ROCKER_TLV_TX_UNSPEC,
@@ -460,6 +460,6 @@ enum rocker_of_dpa_overlay_type {
 #define ROCKER_SWITCH_ID		0x0320 /* 8-byte */
 
 /* Rocker control bits */
-#define ROCKER_CONTROL_RESET		(1 << 0)
+#define ROCKER_CONTROL_RESET		BIT(0)
 
 #endif
diff --git a/drivers/net/ethernet/seeq/Kconfig b/drivers/net/ethernet/seeq/Kconfig
index 11f168e46ebe..69c62d89295e 100644
--- a/drivers/net/ethernet/seeq/Kconfig
+++ b/drivers/net/ethernet/seeq/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_SEEQ
 	default y
 	depends on HAS_IOMEM
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 088921294448..4dd92b7b80f4 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -36,3 +36,12 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
+config SFC_MCDI_LOGGING
+	bool "Solarflare SFC9000/SFC9100-family MCDI logging support"
+	depends on SFC
+	default y
+	---help---
+	  This enables support for tracing of MCDI (Management-Controller-to-
+	  Driver-Interface) commands and responses, allowing debugging of
+	  driver/firmware interaction.  The tracing is actually enabled by
+	  a sysfs file 'mcdi_logging' under the PCI device.
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 3a83c0dca8e6..ce8470fe79d5 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -3,6 +3,6 @@ sfc-y			+= efx.o nic.o farch.o falcon.o siena.o ef10.o tx.o \
 			   tenxpress.o txc43128_phy.o falcon_boards.o \
 			   mcdi.o mcdi_port.o mcdi_mon.o ptp.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
-sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o
+sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o siena_sriov.o ef10_sriov.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index fbb6cfa0f5f1..847643455468 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -15,6 +15,7 @@
 #include "nic.h"
 #include "workarounds.h"
 #include "selftest.h"
+#include "ef10_sriov.h"
 #include <linux/in.h>
 #include <linux/jhash.h>
 #include <linux/wait.h>
@@ -30,6 +31,9 @@ enum {
 
 /* The reserved RSS context value */
 #define EFX_EF10_RSS_CONTEXT_INVALID	0xffffffff
+/* The maximum size of a shared RSS context */
+/* TODO: this should really be from the mcdi protocol export */
+#define EFX_EF10_MAX_SHARED_RSS_CONTEXT_SIZE 64UL
 
 /* The filter table(s) are managed by firmware and we have write-only
  * access.  When removing filters we must identify them to the
@@ -77,7 +81,6 @@ struct efx_ef10_filter_table {
 /* An arbitrary search limit for the software hash table */
 #define EFX_EF10_FILTER_SEARCH_LIMIT 200
 
-static void efx_ef10_rx_push_rss_config(struct efx_nic *efx);
 static void efx_ef10_rx_free_indir_table(struct efx_nic *efx);
 static void efx_ef10_filter_table_remove(struct efx_nic *efx);
 
@@ -92,8 +95,49 @@ static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
 
 static unsigned int efx_ef10_mem_map_size(struct efx_nic *efx)
 {
-	return resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]);
+	int bar;
+
+	bar = efx->type->mem_bar;
+	return resource_size(&efx->pci_dev->resource[bar]);
+}
+
+static int efx_ef10_get_pf_index(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
+			  sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+
+	nic_data->pf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_PF);
+	return 0;
+}
+
+#ifdef CONFIG_SFC_SRIOV
+static int efx_ef10_get_vf_index(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
+			  sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+
+	nic_data->vf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_VF);
+	return 0;
 }
+#endif
 
 static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 {
@@ -117,6 +161,13 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 	nic_data->datapath_caps =
 		MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1);
 
+	/* record the DPCPU firmware IDs to determine VEB vswitching support.
+	 */
+	nic_data->rx_dpcpu_fw_id =
+		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID);
+	nic_data->tx_dpcpu_fw_id =
+		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID);
+
 	if (!(nic_data->datapath_caps &
 	      (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))) {
 		netif_err(efx, drv, efx->net_dev,
@@ -147,7 +198,7 @@ static int efx_ef10_get_sysclk_freq(struct efx_nic *efx)
 	return rc > 0 ? rc : -ERANGE;
 }
 
-static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address)
+static int efx_ef10_get_mac_address_pf(struct efx_nic *efx, u8 *mac_address)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN);
 	size_t outlen;
@@ -167,9 +218,66 @@ static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address)
 	return 0;
 }
 
+static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMAX);
+	size_t outlen;
+	int num_addrs, rc;
+
+	MCDI_SET_DWORD(inbuf, VPORT_GET_MAC_ADDRESSES_IN_VPORT_ID,
+		       EVB_PORT_ID_ASSIGNED);
+	rc = efx_mcdi_rpc(efx, MC_CMD_VPORT_GET_MAC_ADDRESSES, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+
+	if (rc)
+		return rc;
+	if (outlen < MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMIN)
+		return -EIO;
+
+	num_addrs = MCDI_DWORD(outbuf,
+			       VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_COUNT);
+
+	WARN_ON(num_addrs != 1);
+
+	ether_addr_copy(mac_address,
+			MCDI_PTR(outbuf, VPORT_GET_MAC_ADDRESSES_OUT_MACADDR));
+
+	return 0;
+}
+
+static ssize_t efx_ef10_show_link_control_flag(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+
+	return sprintf(buf, "%d\n",
+		       ((efx->mcdi->fn_flags) &
+			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL))
+		       ? 1 : 0);
+}
+
+static ssize_t efx_ef10_show_primary_flag(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+
+	return sprintf(buf, "%d\n",
+		       ((efx->mcdi->fn_flags) &
+			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY))
+		       ? 1 : 0);
+}
+
+static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag,
+		   NULL);
+static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL);
+
 static int efx_ef10_probe(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data;
+	struct net_device *net_dev = efx->net_dev;
 	int i, rc;
 
 	/* We can have one VI for each 8K region.  However, until we
@@ -178,7 +286,7 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	efx->max_channels =
 		min_t(unsigned int,
 		      EFX_MAX_CHANNELS,
-		      resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]) /
+		      efx_ef10_mem_map_size(efx) /
 		      (EFX_VI_PAGE_SIZE * EFX_TXQ_TYPES));
 	if (WARN_ON(efx->max_channels == 0))
 		return -EIO;
@@ -188,6 +296,9 @@ static int efx_ef10_probe(struct efx_nic *efx)
 		return -ENOMEM;
 	efx->nic_data = nic_data;
 
+	/* we assume later that we can copy from this buffer in dwords */
+	BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4);
+
 	rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf,
 				  8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL);
 	if (rc)
@@ -209,6 +320,8 @@ static int efx_ef10_probe(struct efx_nic *efx)
 
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
+	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+
 	/* In case we're recovering from a crash (kexec), we want to
 	 * cancel any outstanding request by the previous user of this
 	 * function.  We send a special message using the least
@@ -230,45 +343,85 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	if (rc)
 		goto fail3;
 
+	rc = device_create_file(&efx->pci_dev->dev,
+				&dev_attr_link_control_flag);
+	if (rc)
+		goto fail3;
+
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+	if (rc)
+		goto fail4;
+
+	rc = efx_ef10_get_pf_index(efx);
+	if (rc)
+		goto fail5;
+
 	rc = efx_ef10_init_datapath_caps(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 
 	efx->rx_packet_len_offset =
 		ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE;
 
 	rc = efx_mcdi_port_get_number(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 	efx->port_num = rc;
+	net_dev->dev_port = rc;
 
-	rc = efx_ef10_get_mac_address(efx, efx->net_dev->perm_addr);
+	rc = efx->type->get_mac_address(efx, efx->net_dev->perm_addr);
 	if (rc)
-		goto fail3;
+		goto fail5;
 
 	rc = efx_ef10_get_sysclk_freq(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 	efx->timer_quantum_ns = 1536000 / rc; /* 1536 cycles */
 
-	/* Check whether firmware supports bug 35388 workaround */
+	/* Check whether firmware supports bug 35388 workaround.
+	 * First try to enable it, then if we get EPERM, just
+	 * ask if it's already enabled
+	 */
 	rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true);
-	if (rc == 0)
+	if (rc == 0) {
 		nic_data->workaround_35388 = true;
-	else if (rc != -ENOSYS && rc != -ENOENT)
-		goto fail3;
+	} else if (rc == -EPERM) {
+		unsigned int enabled;
+
+		rc = efx_mcdi_get_workarounds(efx, NULL, &enabled);
+		if (rc)
+			goto fail3;
+		nic_data->workaround_35388 = enabled &
+			MC_CMD_GET_WORKAROUNDS_OUT_BUG35388;
+	} else if (rc != -ENOSYS && rc != -ENOENT) {
+		goto fail5;
+	}
 	netif_dbg(efx, probe, efx->net_dev,
 		  "workaround for bug 35388 is %sabled\n",
 		  nic_data->workaround_35388 ? "en" : "dis");
 
 	rc = efx_mcdi_mon_probe(efx);
-	if (rc)
-		goto fail3;
+	if (rc && rc != -EPERM)
+		goto fail5;
 
 	efx_ptp_probe(efx, NULL);
 
+#ifdef CONFIG_SFC_SRIOV
+	if ((efx->pci_dev->physfn) && (!efx->pci_dev->is_physfn)) {
+		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
+		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+
+		efx_pf->type->get_mac_address(efx_pf, nic_data->port_id);
+	} else
+#endif
+		ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr);
+
 	return 0;
 
+fail5:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+fail4:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);
 fail3:
 	efx_mcdi_fini(efx);
 fail2:
@@ -281,7 +434,7 @@ fail1:
 
 static int efx_ef10_free_vis(struct efx_nic *efx)
 {
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	size_t outlen;
 	int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0,
 				    outbuf, sizeof(outbuf), &outlen);
@@ -352,9 +505,9 @@ static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
 static int efx_ef10_link_piobufs(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	MCDI_DECLARE_BUF(inbuf,
-			 max(MC_CMD_LINK_PIOBUF_IN_LEN,
-			     MC_CMD_UNLINK_PIOBUF_IN_LEN));
+	_MCDI_DECLARE_BUF(inbuf,
+			  max(MC_CMD_LINK_PIOBUF_IN_LEN,
+			      MC_CMD_UNLINK_PIOBUF_IN_LEN));
 	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	unsigned int offset, index;
@@ -363,6 +516,8 @@ static int efx_ef10_link_piobufs(struct efx_nic *efx)
 	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
 	BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);
 
+	memset(inbuf, 0, sizeof(inbuf));
+
 	/* Link a buffer to each VI in the write-combining mapping */
 	for (index = 0; index < nic_data->n_piobufs; ++index) {
 		MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
@@ -475,6 +630,25 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	int rc;
 
+#ifdef CONFIG_SFC_SRIOV
+	struct efx_ef10_nic_data *nic_data_pf;
+	struct pci_dev *pci_dev_pf;
+	struct efx_nic *efx_pf;
+	struct ef10_vf *vf;
+
+	if (efx->pci_dev->is_virtfn) {
+		pci_dev_pf = efx->pci_dev->physfn;
+		if (pci_dev_pf) {
+			efx_pf = pci_get_drvdata(pci_dev_pf);
+			nic_data_pf = efx_pf->nic_data;
+			vf = nic_data_pf->vf + nic_data->vf_index;
+			vf->efx = NULL;
+		} else
+			netif_info(efx, drv, efx->net_dev,
+				   "Could not get the PF id from VF\n");
+	}
+#endif
+
 	efx_ptp_remove(efx);
 
 	efx_mcdi_mon_remove(efx);
@@ -490,11 +664,78 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	if (!nic_data->must_restore_piobufs)
 		efx_ef10_free_piobufs(efx);
 
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);
+
 	efx_mcdi_fini(efx);
 	efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
 	kfree(nic_data);
 }
 
+static int efx_ef10_probe_pf(struct efx_nic *efx)
+{
+	return efx_ef10_probe(efx);
+}
+
+#ifdef CONFIG_SFC_SRIOV
+static int efx_ef10_probe_vf(struct efx_nic *efx)
+{
+	int rc;
+	struct pci_dev *pci_dev_pf;
+
+	/* If the parent PF has no VF data structure, it doesn't know about this
+	 * VF so fail probe.  The VF needs to be re-created.  This can happen
+	 * if the PF driver is unloaded while the VF is assigned to a guest.
+	 */
+	pci_dev_pf = efx->pci_dev->physfn;
+	if (pci_dev_pf) {
+		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+		struct efx_ef10_nic_data *nic_data_pf = efx_pf->nic_data;
+
+		if (!nic_data_pf->vf) {
+			netif_info(efx, drv, efx->net_dev,
+				   "The VF cannot link to its parent PF; "
+				   "please destroy and re-create the VF\n");
+			return -EBUSY;
+		}
+	}
+
+	rc = efx_ef10_probe(efx);
+	if (rc)
+		return rc;
+
+	rc = efx_ef10_get_vf_index(efx);
+	if (rc)
+		goto fail;
+
+	if (efx->pci_dev->is_virtfn) {
+		if (efx->pci_dev->physfn) {
+			struct efx_nic *efx_pf =
+				pci_get_drvdata(efx->pci_dev->physfn);
+			struct efx_ef10_nic_data *nic_data_p = efx_pf->nic_data;
+			struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+			nic_data_p->vf[nic_data->vf_index].efx = efx;
+			nic_data_p->vf[nic_data->vf_index].pci_dev =
+				efx->pci_dev;
+		} else
+			netif_info(efx, drv, efx->net_dev,
+				   "Could not get the PF id from VF\n");
+	}
+
+	return 0;
+
+fail:
+	efx_ef10_remove(efx);
+	return rc;
+}
+#else
+static int efx_ef10_probe_vf(struct efx_nic *efx __attribute__ ((unused)))
+{
+	return 0;
+}
+#endif
+
 static int efx_ef10_alloc_vis(struct efx_nic *efx,
 			      unsigned int min_vis, unsigned int max_vis)
 {
@@ -687,7 +928,9 @@ static int efx_ef10_init_nic(struct efx_nic *efx)
 		nic_data->must_restore_piobufs = false;
 	}
 
-	efx_ef10_rx_push_rss_config(efx);
+	/* don't fail init if RSS setup doesn't work */
+	efx->type->rx_push_rss_config(efx, false, efx->rx_indir_table);
+
 	return 0;
 }
 
@@ -702,6 +945,14 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 }
 
+static enum reset_type efx_ef10_map_reset_reason(enum reset_type reason)
+{
+	if (reason == RESET_TYPE_MC_FAILURE)
+		return RESET_TYPE_DATAPATH;
+
+	return efx_mcdi_map_reset_reason(reason);
+}
+
 static int efx_ef10_map_reset_flags(u32 *flags)
 {
 	enum {
@@ -760,93 +1011,112 @@ static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type)
 	[GENERIC_STAT_ ## ext_name] = { #ext_name, 0, 0 }
 
 static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
-	EF10_DMA_STAT(tx_bytes, TX_BYTES),
-	EF10_DMA_STAT(tx_packets, TX_PKTS),
-	EF10_DMA_STAT(tx_pause, TX_PAUSE_PKTS),
-	EF10_DMA_STAT(tx_control, TX_CONTROL_PKTS),
-	EF10_DMA_STAT(tx_unicast, TX_UNICAST_PKTS),
-	EF10_DMA_STAT(tx_multicast, TX_MULTICAST_PKTS),
-	EF10_DMA_STAT(tx_broadcast, TX_BROADCAST_PKTS),
-	EF10_DMA_STAT(tx_lt64, TX_LT64_PKTS),
-	EF10_DMA_STAT(tx_64, TX_64_PKTS),
-	EF10_DMA_STAT(tx_65_to_127, TX_65_TO_127_PKTS),
-	EF10_DMA_STAT(tx_128_to_255, TX_128_TO_255_PKTS),
-	EF10_DMA_STAT(tx_256_to_511, TX_256_TO_511_PKTS),
-	EF10_DMA_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS),
-	EF10_DMA_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
-	EF10_DMA_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
-	EF10_DMA_STAT(rx_bytes, RX_BYTES),
-	EF10_DMA_INVIS_STAT(rx_bytes_minus_good_bytes, RX_BAD_BYTES),
-	EF10_OTHER_STAT(rx_good_bytes),
-	EF10_OTHER_STAT(rx_bad_bytes),
-	EF10_DMA_STAT(rx_packets, RX_PKTS),
-	EF10_DMA_STAT(rx_good, RX_GOOD_PKTS),
-	EF10_DMA_STAT(rx_bad, RX_BAD_FCS_PKTS),
-	EF10_DMA_STAT(rx_pause, RX_PAUSE_PKTS),
-	EF10_DMA_STAT(rx_control, RX_CONTROL_PKTS),
-	EF10_DMA_STAT(rx_unicast, RX_UNICAST_PKTS),
-	EF10_DMA_STAT(rx_multicast, RX_MULTICAST_PKTS),
-	EF10_DMA_STAT(rx_broadcast, RX_BROADCAST_PKTS),
-	EF10_DMA_STAT(rx_lt64, RX_UNDERSIZE_PKTS),
-	EF10_DMA_STAT(rx_64, RX_64_PKTS),
-	EF10_DMA_STAT(rx_65_to_127, RX_65_TO_127_PKTS),
-	EF10_DMA_STAT(rx_128_to_255, RX_128_TO_255_PKTS),
-	EF10_DMA_STAT(rx_256_to_511, RX_256_TO_511_PKTS),
-	EF10_DMA_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS),
-	EF10_DMA_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
-	EF10_DMA_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
-	EF10_DMA_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS),
-	EF10_DMA_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS),
-	EF10_DMA_STAT(rx_overflow, RX_OVERFLOW_PKTS),
-	EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS),
-	EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS),
-	EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS),
+	EF10_DMA_STAT(port_tx_bytes, TX_BYTES),
+	EF10_DMA_STAT(port_tx_packets, TX_PKTS),
+	EF10_DMA_STAT(port_tx_pause, TX_PAUSE_PKTS),
+	EF10_DMA_STAT(port_tx_control, TX_CONTROL_PKTS),
+	EF10_DMA_STAT(port_tx_unicast, TX_UNICAST_PKTS),
+	EF10_DMA_STAT(port_tx_multicast, TX_MULTICAST_PKTS),
+	EF10_DMA_STAT(port_tx_broadcast, TX_BROADCAST_PKTS),
+	EF10_DMA_STAT(port_tx_lt64, TX_LT64_PKTS),
+	EF10_DMA_STAT(port_tx_64, TX_64_PKTS),
+	EF10_DMA_STAT(port_tx_65_to_127, TX_65_TO_127_PKTS),
+	EF10_DMA_STAT(port_tx_128_to_255, TX_128_TO_255_PKTS),
+	EF10_DMA_STAT(port_tx_256_to_511, TX_256_TO_511_PKTS),
+	EF10_DMA_STAT(port_tx_512_to_1023, TX_512_TO_1023_PKTS),
+	EF10_DMA_STAT(port_tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
+	EF10_DMA_STAT(port_tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_bytes, RX_BYTES),
+	EF10_DMA_INVIS_STAT(port_rx_bytes_minus_good_bytes, RX_BAD_BYTES),
+	EF10_OTHER_STAT(port_rx_good_bytes),
+	EF10_OTHER_STAT(port_rx_bad_bytes),
+	EF10_DMA_STAT(port_rx_packets, RX_PKTS),
+	EF10_DMA_STAT(port_rx_good, RX_GOOD_PKTS),
+	EF10_DMA_STAT(port_rx_bad, RX_BAD_FCS_PKTS),
+	EF10_DMA_STAT(port_rx_pause, RX_PAUSE_PKTS),
+	EF10_DMA_STAT(port_rx_control, RX_CONTROL_PKTS),
+	EF10_DMA_STAT(port_rx_unicast, RX_UNICAST_PKTS),
+	EF10_DMA_STAT(port_rx_multicast, RX_MULTICAST_PKTS),
+	EF10_DMA_STAT(port_rx_broadcast, RX_BROADCAST_PKTS),
+	EF10_DMA_STAT(port_rx_lt64, RX_UNDERSIZE_PKTS),
+	EF10_DMA_STAT(port_rx_64, RX_64_PKTS),
+	EF10_DMA_STAT(port_rx_65_to_127, RX_65_TO_127_PKTS),
+	EF10_DMA_STAT(port_rx_128_to_255, RX_128_TO_255_PKTS),
+	EF10_DMA_STAT(port_rx_256_to_511, RX_256_TO_511_PKTS),
+	EF10_DMA_STAT(port_rx_512_to_1023, RX_512_TO_1023_PKTS),
+	EF10_DMA_STAT(port_rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
+	EF10_DMA_STAT(port_rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_gtjumbo, RX_GTJUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_bad_gtjumbo, RX_JABBER_PKTS),
+	EF10_DMA_STAT(port_rx_overflow, RX_OVERFLOW_PKTS),
+	EF10_DMA_STAT(port_rx_align_error, RX_ALIGN_ERROR_PKTS),
+	EF10_DMA_STAT(port_rx_length_error, RX_LENGTH_ERROR_PKTS),
+	EF10_DMA_STAT(port_rx_nodesc_drops, RX_NODESC_DROPS),
 	GENERIC_SW_STAT(rx_nodesc_trunc),
 	GENERIC_SW_STAT(rx_noskb_drops),
-	EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
-	EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
-	EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
-	EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
-	EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB),
-	EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB),
-	EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING),
-	EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
-	EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
-	EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
-	EF10_DMA_STAT(rx_dp_hlb_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS),
-	EF10_DMA_STAT(rx_dp_hlb_wait, RXDP_EMERGENCY_WAIT_CONDITIONS),
+	EF10_DMA_STAT(port_rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
+	EF10_DMA_STAT(port_rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
+	EF10_DMA_STAT(port_rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
+	EF10_DMA_STAT(port_rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
+	EF10_DMA_STAT(port_rx_pm_trunc_qbb, PM_TRUNC_QBB),
+	EF10_DMA_STAT(port_rx_pm_discard_qbb, PM_DISCARD_QBB),
+	EF10_DMA_STAT(port_rx_pm_discard_mapping, PM_DISCARD_MAPPING),
+	EF10_DMA_STAT(port_rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
+	EF10_DMA_STAT(port_rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
+	EF10_DMA_STAT(port_rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
+	EF10_DMA_STAT(port_rx_dp_hlb_fetch, RXDP_HLB_FETCH_CONDITIONS),
+	EF10_DMA_STAT(port_rx_dp_hlb_wait, RXDP_HLB_WAIT_CONDITIONS),
+	EF10_DMA_STAT(rx_unicast, VADAPTER_RX_UNICAST_PACKETS),
+	EF10_DMA_STAT(rx_unicast_bytes, VADAPTER_RX_UNICAST_BYTES),
+	EF10_DMA_STAT(rx_multicast, VADAPTER_RX_MULTICAST_PACKETS),
+	EF10_DMA_STAT(rx_multicast_bytes, VADAPTER_RX_MULTICAST_BYTES),
+	EF10_DMA_STAT(rx_broadcast, VADAPTER_RX_BROADCAST_PACKETS),
+	EF10_DMA_STAT(rx_broadcast_bytes, VADAPTER_RX_BROADCAST_BYTES),
+	EF10_DMA_STAT(rx_bad, VADAPTER_RX_BAD_PACKETS),
+	EF10_DMA_STAT(rx_bad_bytes, VADAPTER_RX_BAD_BYTES),
+	EF10_DMA_STAT(rx_overflow, VADAPTER_RX_OVERFLOW),
+	EF10_DMA_STAT(tx_unicast, VADAPTER_TX_UNICAST_PACKETS),
+	EF10_DMA_STAT(tx_unicast_bytes, VADAPTER_TX_UNICAST_BYTES),
+	EF10_DMA_STAT(tx_multicast, VADAPTER_TX_MULTICAST_PACKETS),
+	EF10_DMA_STAT(tx_multicast_bytes, VADAPTER_TX_MULTICAST_BYTES),
+	EF10_DMA_STAT(tx_broadcast, VADAPTER_TX_BROADCAST_PACKETS),
+	EF10_DMA_STAT(tx_broadcast_bytes, VADAPTER_TX_BROADCAST_BYTES),
+	EF10_DMA_STAT(tx_bad, VADAPTER_TX_BAD_PACKETS),
+	EF10_DMA_STAT(tx_bad_bytes, VADAPTER_TX_BAD_BYTES),
+	EF10_DMA_STAT(tx_overflow, VADAPTER_TX_OVERFLOW),
 };
 
-#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) |		\
-			       (1ULL << EF10_STAT_tx_packets) |		\
-			       (1ULL << EF10_STAT_tx_pause) |		\
-			       (1ULL << EF10_STAT_tx_unicast) |		\
-			       (1ULL << EF10_STAT_tx_multicast) |	\
-			       (1ULL << EF10_STAT_tx_broadcast) |	\
-			       (1ULL << EF10_STAT_rx_bytes) |		\
-			       (1ULL << EF10_STAT_rx_bytes_minus_good_bytes) | \
-			       (1ULL << EF10_STAT_rx_good_bytes) |	\
-			       (1ULL << EF10_STAT_rx_bad_bytes) |	\
-			       (1ULL << EF10_STAT_rx_packets) |		\
-			       (1ULL << EF10_STAT_rx_good) |		\
-			       (1ULL << EF10_STAT_rx_bad) |		\
-			       (1ULL << EF10_STAT_rx_pause) |		\
-			       (1ULL << EF10_STAT_rx_control) |		\
-			       (1ULL << EF10_STAT_rx_unicast) |		\
-			       (1ULL << EF10_STAT_rx_multicast) |	\
-			       (1ULL << EF10_STAT_rx_broadcast) |	\
-			       (1ULL << EF10_STAT_rx_lt64) |		\
-			       (1ULL << EF10_STAT_rx_64) |		\
-			       (1ULL << EF10_STAT_rx_65_to_127) |	\
-			       (1ULL << EF10_STAT_rx_128_to_255) |	\
-			       (1ULL << EF10_STAT_rx_256_to_511) |	\
-			       (1ULL << EF10_STAT_rx_512_to_1023) |	\
-			       (1ULL << EF10_STAT_rx_1024_to_15xx) |	\
-			       (1ULL << EF10_STAT_rx_15xx_to_jumbo) |	\
-			       (1ULL << EF10_STAT_rx_gtjumbo) |		\
-			       (1ULL << EF10_STAT_rx_bad_gtjumbo) |	\
-			       (1ULL << EF10_STAT_rx_overflow) |	\
-			       (1ULL << EF10_STAT_rx_nodesc_drops) |	\
+#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_port_tx_bytes) |	\
+			       (1ULL << EF10_STAT_port_tx_packets) |	\
+			       (1ULL << EF10_STAT_port_tx_pause) |	\
+			       (1ULL << EF10_STAT_port_tx_unicast) |	\
+			       (1ULL << EF10_STAT_port_tx_multicast) |	\
+			       (1ULL << EF10_STAT_port_tx_broadcast) |	\
+			       (1ULL << EF10_STAT_port_rx_bytes) |	\
+			       (1ULL <<                                 \
+				EF10_STAT_port_rx_bytes_minus_good_bytes) | \
+			       (1ULL << EF10_STAT_port_rx_good_bytes) |	\
+			       (1ULL << EF10_STAT_port_rx_bad_bytes) |	\
+			       (1ULL << EF10_STAT_port_rx_packets) |	\
+			       (1ULL << EF10_STAT_port_rx_good) |	\
+			       (1ULL << EF10_STAT_port_rx_bad) |	\
+			       (1ULL << EF10_STAT_port_rx_pause) |	\
+			       (1ULL << EF10_STAT_port_rx_control) |	\
+			       (1ULL << EF10_STAT_port_rx_unicast) |	\
+			       (1ULL << EF10_STAT_port_rx_multicast) |	\
+			       (1ULL << EF10_STAT_port_rx_broadcast) |	\
+			       (1ULL << EF10_STAT_port_rx_lt64) |	\
+			       (1ULL << EF10_STAT_port_rx_64) |		\
+			       (1ULL << EF10_STAT_port_rx_65_to_127) |	\
+			       (1ULL << EF10_STAT_port_rx_128_to_255) |	\
+			       (1ULL << EF10_STAT_port_rx_256_to_511) |	\
+			       (1ULL << EF10_STAT_port_rx_512_to_1023) |\
+			       (1ULL << EF10_STAT_port_rx_1024_to_15xx) |\
+			       (1ULL << EF10_STAT_port_rx_15xx_to_jumbo) |\
+			       (1ULL << EF10_STAT_port_rx_gtjumbo) |	\
+			       (1ULL << EF10_STAT_port_rx_bad_gtjumbo) |\
+			       (1ULL << EF10_STAT_port_rx_overflow) |	\
+			       (1ULL << EF10_STAT_port_rx_nodesc_drops) |\
 			       (1ULL << GENERIC_STAT_rx_nodesc_trunc) |	\
 			       (1ULL << GENERIC_STAT_rx_noskb_drops))
 
@@ -854,39 +1124,39 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
  * switchable port we do not expose these because they might not
  * include all the packets they should.
  */
-#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_tx_control) |	\
-				 (1ULL << EF10_STAT_tx_lt64) |		\
-				 (1ULL << EF10_STAT_tx_64) |		\
-				 (1ULL << EF10_STAT_tx_65_to_127) |	\
-				 (1ULL << EF10_STAT_tx_128_to_255) |	\
-				 (1ULL << EF10_STAT_tx_256_to_511) |	\
-				 (1ULL << EF10_STAT_tx_512_to_1023) |	\
-				 (1ULL << EF10_STAT_tx_1024_to_15xx) |	\
-				 (1ULL << EF10_STAT_tx_15xx_to_jumbo))
+#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_port_tx_control) |	\
+				 (1ULL << EF10_STAT_port_tx_lt64) |	\
+				 (1ULL << EF10_STAT_port_tx_64) |	\
+				 (1ULL << EF10_STAT_port_tx_65_to_127) |\
+				 (1ULL << EF10_STAT_port_tx_128_to_255) |\
+				 (1ULL << EF10_STAT_port_tx_256_to_511) |\
+				 (1ULL << EF10_STAT_port_tx_512_to_1023) |\
+				 (1ULL << EF10_STAT_port_tx_1024_to_15xx) |\
+				 (1ULL << EF10_STAT_port_tx_15xx_to_jumbo))
 
 /* These statistics are only provided by the 40G MAC.  For a 10G/40G
  * switchable port we do expose these because the errors will otherwise
  * be silent.
  */
-#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) |	\
-				  (1ULL << EF10_STAT_rx_length_error))
+#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_port_rx_align_error) |\
+				  (1ULL << EF10_STAT_port_rx_length_error))
 
 /* These statistics are only provided if the firmware supports the
  * capability PM_AND_RXDP_COUNTERS.
  */
 #define HUNT_PM_AND_RXDP_STAT_MASK (					\
-	(1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) |			\
-	(1ULL << EF10_STAT_rx_pm_discard_bb_overflow) |			\
-	(1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) |			\
-	(1ULL << EF10_STAT_rx_pm_discard_vfifo_full) |			\
-	(1ULL << EF10_STAT_rx_pm_trunc_qbb) |				\
-	(1ULL << EF10_STAT_rx_pm_discard_qbb) |				\
-	(1ULL << EF10_STAT_rx_pm_discard_mapping) |			\
-	(1ULL << EF10_STAT_rx_dp_q_disabled_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_di_dropped_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_streaming_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_hlb_fetch) |				\
-	(1ULL << EF10_STAT_rx_dp_hlb_wait))
+	(1ULL << EF10_STAT_port_rx_pm_trunc_bb_overflow) |		\
+	(1ULL << EF10_STAT_port_rx_pm_discard_bb_overflow) |		\
+	(1ULL << EF10_STAT_port_rx_pm_trunc_vfifo_full) |		\
+	(1ULL << EF10_STAT_port_rx_pm_discard_vfifo_full) |		\
+	(1ULL << EF10_STAT_port_rx_pm_trunc_qbb) |			\
+	(1ULL << EF10_STAT_port_rx_pm_discard_qbb) |			\
+	(1ULL << EF10_STAT_port_rx_pm_discard_mapping) |		\
+	(1ULL << EF10_STAT_port_rx_dp_q_disabled_packets) |		\
+	(1ULL << EF10_STAT_port_rx_dp_di_dropped_packets) |		\
+	(1ULL << EF10_STAT_port_rx_dp_streaming_packets) |		\
+	(1ULL << EF10_STAT_port_rx_dp_hlb_fetch) |			\
+	(1ULL << EF10_STAT_port_rx_dp_hlb_wait))
 
 static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx)
 {
@@ -894,6 +1164,10 @@ static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx)
 	u32 port_caps = efx_mcdi_phy_get_caps(efx);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 
+	if (!(efx->mcdi->fn_flags &
+	      1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL))
+		return 0;
+
 	if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
 		raw_mask |= HUNT_40G_EXTRA_STAT_MASK;
 	else
@@ -908,13 +1182,28 @@ static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx)
 
 static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask)
 {
-	u64 raw_mask = efx_ef10_raw_stat_mask(efx);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	u64 raw_mask[2];
+
+	raw_mask[0] = efx_ef10_raw_stat_mask(efx);
+
+	/* Only show vadaptor stats when EVB capability is present */
+	if (nic_data->datapath_caps &
+	    (1 << MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN)) {
+		raw_mask[0] |= ~((1ULL << EF10_STAT_rx_unicast) - 1);
+		raw_mask[1] = (1ULL << (EF10_STAT_COUNT - 63)) - 1;
+	} else {
+		raw_mask[1] = 0;
+	}
 
 #if BITS_PER_LONG == 64
-	mask[0] = raw_mask;
+	mask[0] = raw_mask[0];
+	mask[1] = raw_mask[1];
 #else
-	mask[0] = raw_mask & 0xffffffff;
-	mask[1] = raw_mask >> 32;
+	mask[0] = raw_mask[0] & 0xffffffff;
+	mask[1] = raw_mask[0] >> 32;
+	mask[2] = raw_mask[1] & 0xffffffff;
+	mask[3] = raw_mask[1] >> 32;
 #endif
 }
 
@@ -927,7 +1216,51 @@ static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names)
 				      mask, names);
 }
 
-static int efx_ef10_try_update_nic_stats(struct efx_nic *efx)
+static size_t efx_ef10_update_stats_common(struct efx_nic *efx, u64 *full_stats,
+					   struct rtnl_link_stats64 *core_stats)
+{
+	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	u64 *stats = nic_data->stats;
+	size_t stats_count = 0, index;
+
+	efx_ef10_get_stat_mask(efx, mask);
+
+	if (full_stats) {
+		for_each_set_bit(index, mask, EF10_STAT_COUNT) {
+			if (efx_ef10_stat_desc[index].name) {
+				*full_stats++ = stats[index];
+				++stats_count;
+			}
+		}
+	}
+
+	if (core_stats) {
+		core_stats->rx_packets = stats[EF10_STAT_rx_unicast] +
+					 stats[EF10_STAT_rx_multicast] +
+					 stats[EF10_STAT_rx_broadcast];
+		core_stats->tx_packets = stats[EF10_STAT_tx_unicast] +
+					 stats[EF10_STAT_tx_multicast] +
+					 stats[EF10_STAT_tx_broadcast];
+		core_stats->rx_bytes = stats[EF10_STAT_rx_unicast_bytes] +
+				       stats[EF10_STAT_rx_multicast_bytes] +
+				       stats[EF10_STAT_rx_broadcast_bytes];
+		core_stats->tx_bytes = stats[EF10_STAT_tx_unicast_bytes] +
+				       stats[EF10_STAT_tx_multicast_bytes] +
+				       stats[EF10_STAT_tx_broadcast_bytes];
+		core_stats->rx_dropped = stats[GENERIC_STAT_rx_nodesc_trunc] +
+					 stats[GENERIC_STAT_rx_noskb_drops];
+		core_stats->multicast = stats[EF10_STAT_rx_multicast];
+		core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad];
+		core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow];
+		core_stats->rx_errors = core_stats->rx_crc_errors;
+		core_stats->tx_errors = stats[EF10_STAT_tx_bad];
+	}
+
+	return stats_count;
+}
+
+static int efx_ef10_try_update_nic_stats_pf(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
@@ -952,67 +1285,114 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx)
 		return -EAGAIN;
 
 	/* Update derived statistics */
-	efx_nic_fix_nodesc_drop_stat(efx, &stats[EF10_STAT_rx_nodesc_drops]);
-	stats[EF10_STAT_rx_good_bytes] =
-		stats[EF10_STAT_rx_bytes] -
-		stats[EF10_STAT_rx_bytes_minus_good_bytes];
-	efx_update_diff_stat(&stats[EF10_STAT_rx_bad_bytes],
-			     stats[EF10_STAT_rx_bytes_minus_good_bytes]);
+	efx_nic_fix_nodesc_drop_stat(efx,
+				     &stats[EF10_STAT_port_rx_nodesc_drops]);
+	stats[EF10_STAT_port_rx_good_bytes] =
+		stats[EF10_STAT_port_rx_bytes] -
+		stats[EF10_STAT_port_rx_bytes_minus_good_bytes];
+	efx_update_diff_stat(&stats[EF10_STAT_port_rx_bad_bytes],
+			     stats[EF10_STAT_port_rx_bytes_minus_good_bytes]);
 	efx_update_sw_stats(efx, stats);
 	return 0;
 }
 
 
-static size_t efx_ef10_update_stats(struct efx_nic *efx, u64 *full_stats,
-				    struct rtnl_link_stats64 *core_stats)
+static size_t efx_ef10_update_stats_pf(struct efx_nic *efx, u64 *full_stats,
+				       struct rtnl_link_stats64 *core_stats)
 {
-	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
-	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	u64 *stats = nic_data->stats;
-	size_t stats_count = 0, index;
 	int retry;
 
-	efx_ef10_get_stat_mask(efx, mask);
-
 	/* If we're unlucky enough to read statistics during the DMA, wait
 	 * up to 10ms for it to finish (typically takes <500us)
 	 */
 	for (retry = 0; retry < 100; ++retry) {
-		if (efx_ef10_try_update_nic_stats(efx) == 0)
+		if (efx_ef10_try_update_nic_stats_pf(efx) == 0)
 			break;
 		udelay(100);
 	}
 
-	if (full_stats) {
-		for_each_set_bit(index, mask, EF10_STAT_COUNT) {
-			if (efx_ef10_stat_desc[index].name) {
-				*full_stats++ = stats[index];
-				++stats_count;
-			}
-		}
+	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
+}
+
+static int efx_ef10_try_update_nic_stats_vf(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	DECLARE_BITMAP(mask, EF10_STAT_COUNT);
+	__le64 generation_start, generation_end;
+	u64 *stats = nic_data->stats;
+	u32 dma_len = MC_CMD_MAC_NSTATS * sizeof(u64);
+	struct efx_buffer stats_buf;
+	__le64 *dma_stats;
+	int rc;
+
+	spin_unlock_bh(&efx->stats_lock);
+
+	if (in_interrupt()) {
+		/* If in atomic context, cannot update stats.  Just update the
+		 * software stats and return so the caller can continue.
+		 */
+		spin_lock_bh(&efx->stats_lock);
+		efx_update_sw_stats(efx, stats);
+		return 0;
 	}
 
-	if (core_stats) {
-		core_stats->rx_packets = stats[EF10_STAT_rx_packets];
-		core_stats->tx_packets = stats[EF10_STAT_tx_packets];
-		core_stats->rx_bytes = stats[EF10_STAT_rx_bytes];
-		core_stats->tx_bytes = stats[EF10_STAT_tx_bytes];
-		core_stats->rx_dropped = stats[EF10_STAT_rx_nodesc_drops] +
-					 stats[GENERIC_STAT_rx_nodesc_trunc] +
-					 stats[GENERIC_STAT_rx_noskb_drops];
-		core_stats->multicast = stats[EF10_STAT_rx_multicast];
-		core_stats->rx_length_errors =
-			stats[EF10_STAT_rx_gtjumbo] +
-			stats[EF10_STAT_rx_length_error];
-		core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad];
-		core_stats->rx_frame_errors = stats[EF10_STAT_rx_align_error];
-		core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow];
-		core_stats->rx_errors = (core_stats->rx_length_errors +
-					 core_stats->rx_crc_errors +
-					 core_stats->rx_frame_errors);
+	efx_ef10_get_stat_mask(efx, mask);
+
+	rc = efx_nic_alloc_buffer(efx, &stats_buf, dma_len, GFP_ATOMIC);
+	if (rc) {
+		spin_lock_bh(&efx->stats_lock);
+		return rc;
 	}
 
-	return stats_count;
+	dma_stats = stats_buf.addr;
+	dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID;
+
+	MCDI_SET_QWORD(inbuf, MAC_STATS_IN_DMA_ADDR, stats_buf.dma_addr);
+	MCDI_POPULATE_DWORD_1(inbuf, MAC_STATS_IN_CMD,
+			      MAC_STATS_IN_DMA, 1);
+	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
+	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
+				NULL, 0, NULL);
+	spin_lock_bh(&efx->stats_lock);
+	if (rc) {
+		/* Expect ENOENT if DMA queues have not been set up */
+		if (rc != -ENOENT || atomic_read(&efx->active_queues))
+			efx_mcdi_display_error(efx, MC_CMD_MAC_STATS,
+					       sizeof(inbuf), NULL, 0, rc);
+		goto out;
+	}
+
+	generation_end = dma_stats[MC_CMD_MAC_GENERATION_END];
+	if (generation_end == EFX_MC_STATS_GENERATION_INVALID) {
+		WARN_ON_ONCE(1);
+		goto out;
+	}
+	rmb();
+	efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask,
+			     stats, stats_buf.addr, false);
+	rmb();
+	generation_start = dma_stats[MC_CMD_MAC_GENERATION_START];
+	if (generation_end != generation_start) {
+		rc = -EAGAIN;
+		goto out;
+	}
+
+	efx_update_sw_stats(efx, stats);
+out:
+	efx_nic_free_buffer(efx, &stats_buf);
+	return rc;
+}
+
+static size_t efx_ef10_update_stats_vf(struct efx_nic *efx, u64 *full_stats,
+				       struct rtnl_link_stats64 *core_stats)
+{
+	if (efx_ef10_try_update_nic_stats_vf(efx))
+		return 0;
+
+	return efx_ef10_update_stats_common(efx, full_stats, core_stats);
 }
 
 static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
@@ -1044,6 +1424,14 @@ static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
 	}
 }
 
+static void efx_ef10_get_wol_vf(struct efx_nic *efx,
+				struct ethtool_wolinfo *wol) {}
+
+static int efx_ef10_set_wol_vf(struct efx_nic *efx, u32 type)
+{
+	return -EOPNOTSUPP;
+}
+
 static void efx_ef10_get_wol(struct efx_nic *efx, struct ethtool_wolinfo *wol)
 {
 	wol->supported = 0;
@@ -1123,13 +1511,17 @@ static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
 	/* All our allocations have been reset */
 	efx_ef10_reset_mc_allocations(efx);
 
+	/* Driver-created vswitches and vports must be re-created */
+	nic_data->must_probe_vswitching = true;
+	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+
 	/* The datapath firmware might have been changed */
 	nic_data->must_check_datapath_caps = true;
 
 	/* MAC statistics have been cleared on the NIC; clear the local
 	 * statistic that we update with efx_update_diff_stat().
 	 */
-	nic_data->stats[EF10_STAT_rx_bad_bytes] = 0;
+	nic_data->stats[EF10_STAT_port_rx_bad_bytes] = 0;
 
 	return -EIO;
 }
@@ -1232,16 +1624,17 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
 						       EFX_BUF_SIZE));
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_TXQ_OUT_LEN);
 	bool csum_offload = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
 	size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
 	struct efx_channel *channel = tx_queue->channel;
 	struct efx_nic *efx = tx_queue->efx;
-	size_t inlen, outlen;
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t inlen;
 	dma_addr_t dma_addr;
 	efx_qword_t *txd;
 	int rc;
 	int i;
+	BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0);
 
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
@@ -1251,7 +1644,7 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 			      INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
 			      INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload);
 	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
-	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+	MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, nic_data->vport_id);
 
 	dma_addr = tx_queue->txd.buf.dma_addr;
 
@@ -1266,7 +1659,7 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
 	inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
-			  outbuf, sizeof(outbuf), &outlen);
+			  NULL, 0, NULL);
 	if (rc)
 		goto fail;
 
@@ -1299,7 +1692,7 @@ fail:
 static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_TXQ_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_TXQ_OUT_LEN);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	struct efx_nic *efx = tx_queue->efx;
 	size_t outlen;
 	int rc;
@@ -1378,19 +1771,33 @@ static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
 	}
 }
 
-static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context)
+static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context,
+				      bool exclusive, unsigned *context_size)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_ALLOC_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	size_t outlen;
 	int rc;
+	u32 alloc_type = exclusive ?
+				MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_EXCLUSIVE :
+				MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_SHARED;
+	unsigned rss_spread = exclusive ?
+				efx->rss_spread :
+				min(rounddown_pow_of_two(efx->rss_spread),
+				    EFX_EF10_MAX_SHARED_RSS_CONTEXT_SIZE);
+
+	if (!exclusive && rss_spread == 1) {
+		*context = EFX_EF10_RSS_CONTEXT_INVALID;
+		if (context_size)
+			*context_size = 1;
+		return 0;
+	}
 
 	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID,
-		       EVB_PORT_ID_ASSIGNED);
-	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE,
-		       MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_EXCLUSIVE);
-	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_NUM_QUEUES,
-		       EFX_MAX_CHANNELS);
+		       nic_data->vport_id);
+	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE, alloc_type);
+	MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_NUM_QUEUES, rss_spread);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_ALLOC, inbuf, sizeof(inbuf),
 		outbuf, sizeof(outbuf), &outlen);
@@ -1402,6 +1809,9 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context)
 
 	*context = MCDI_DWORD(outbuf, RSS_CONTEXT_ALLOC_OUT_RSS_CONTEXT_ID);
 
+	if (context_size)
+		*context_size = rss_spread;
+
 	return 0;
 }
 
@@ -1418,7 +1828,8 @@ static void efx_ef10_free_rss_context(struct efx_nic *efx, u32 context)
 	WARN_ON(rc != 0);
 }
 
-static int efx_ef10_populate_rss_table(struct efx_nic *efx, u32 context)
+static int efx_ef10_populate_rss_table(struct efx_nic *efx, u32 context,
+				       const u32 *rx_indir_table)
 {
 	MCDI_DECLARE_BUF(tablebuf, MC_CMD_RSS_CONTEXT_SET_TABLE_IN_LEN);
 	MCDI_DECLARE_BUF(keybuf, MC_CMD_RSS_CONTEXT_SET_KEY_IN_LEN);
@@ -1432,7 +1843,7 @@ static int efx_ef10_populate_rss_table(struct efx_nic *efx, u32 context)
 	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); ++i)
 		MCDI_PTR(tablebuf,
 			 RSS_CONTEXT_SET_TABLE_IN_INDIRECTION_TABLE)[i] =
-				(u8) efx->rx_indir_table[i];
+				(u8) rx_indir_table[i];
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_TABLE, tablebuf,
 			  sizeof(tablebuf), NULL, 0, NULL);
@@ -1460,27 +1871,119 @@ static void efx_ef10_rx_free_indir_table(struct efx_nic *efx)
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 }
 
-static void efx_ef10_rx_push_rss_config(struct efx_nic *efx)
+static int efx_ef10_rx_push_shared_rss_config(struct efx_nic *efx,
+					      unsigned *context_size)
 {
+	u32 new_rx_rss_context;
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	int rc;
+	int rc = efx_ef10_alloc_rss_context(efx, &new_rx_rss_context,
+					    false, context_size);
 
-	netif_dbg(efx, drv, efx->net_dev, "pushing RSS config\n");
+	if (rc != 0)
+		return rc;
 
-	if (nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID) {
-		rc = efx_ef10_alloc_rss_context(efx, &nic_data->rx_rss_context);
-		if (rc != 0)
-			goto fail;
+	nic_data->rx_rss_context = new_rx_rss_context;
+	nic_data->rx_rss_context_exclusive = false;
+	efx_set_default_rx_indir_table(efx);
+	return 0;
+}
+
+static int efx_ef10_rx_push_exclusive_rss_config(struct efx_nic *efx,
+						 const u32 *rx_indir_table)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	int rc;
+	u32 new_rx_rss_context;
+
+	if (nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID ||
+	    !nic_data->rx_rss_context_exclusive) {
+		rc = efx_ef10_alloc_rss_context(efx, &new_rx_rss_context,
+						true, NULL);
+		if (rc == -EOPNOTSUPP)
+			return rc;
+		else if (rc != 0)
+			goto fail1;
+	} else {
+		new_rx_rss_context = nic_data->rx_rss_context;
 	}
 
-	rc = efx_ef10_populate_rss_table(efx, nic_data->rx_rss_context);
+	rc = efx_ef10_populate_rss_table(efx, new_rx_rss_context,
+					 rx_indir_table);
 	if (rc != 0)
-		goto fail;
+		goto fail2;
 
-	return;
+	if (nic_data->rx_rss_context != new_rx_rss_context)
+		efx_ef10_rx_free_indir_table(efx);
+	nic_data->rx_rss_context = new_rx_rss_context;
+	nic_data->rx_rss_context_exclusive = true;
+	if (rx_indir_table != efx->rx_indir_table)
+		memcpy(efx->rx_indir_table, rx_indir_table,
+		       sizeof(efx->rx_indir_table));
+	return 0;
 
-fail:
+fail2:
+	if (new_rx_rss_context != nic_data->rx_rss_context)
+		efx_ef10_free_rss_context(efx, new_rx_rss_context);
+fail1:
 	netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+	return rc;
+}
+
+static int efx_ef10_pf_rx_push_rss_config(struct efx_nic *efx, bool user,
+					  const u32 *rx_indir_table)
+{
+	int rc;
+
+	if (efx->rss_spread == 1)
+		return 0;
+
+	rc = efx_ef10_rx_push_exclusive_rss_config(efx, rx_indir_table);
+
+	if (rc == -ENOBUFS && !user) {
+		unsigned context_size;
+		bool mismatch = false;
+		size_t i;
+
+		for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table) && !mismatch;
+		     i++)
+			mismatch = rx_indir_table[i] !=
+				ethtool_rxfh_indir_default(i, efx->rss_spread);
+
+		rc = efx_ef10_rx_push_shared_rss_config(efx, &context_size);
+		if (rc == 0) {
+			if (context_size != efx->rss_spread)
+				netif_warn(efx, probe, efx->net_dev,
+					   "Could not allocate an exclusive RSS"
+					   " context; allocated a shared one of"
+					   " different size."
+					   " Wanted %u, got %u.\n",
+					   efx->rss_spread, context_size);
+			else if (mismatch)
+				netif_warn(efx, probe, efx->net_dev,
+					   "Could not allocate an exclusive RSS"
+					   " context; allocated a shared one but"
+					   " could not apply custom"
+					   " indirection.\n");
+			else
+				netif_info(efx, probe, efx->net_dev,
+					   "Could not allocate an exclusive RSS"
+					   " context; allocated a shared one.\n");
+		}
+	}
+	return rc;
+}
+
+static int efx_ef10_vf_rx_push_rss_config(struct efx_nic *efx, bool user,
+					  const u32 *rx_indir_table
+					  __attribute__ ((unused)))
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	if (user)
+		return -EOPNOTSUPP;
+	if (nic_data->rx_rss_context != EFX_EF10_RSS_CONTEXT_INVALID)
+		return 0;
+	return efx_ef10_rx_push_shared_rss_config(efx, NULL);
 }
 
 static int efx_ef10_rx_probe(struct efx_rx_queue *rx_queue)
@@ -1496,14 +1999,15 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
 	MCDI_DECLARE_BUF(inbuf,
 			 MC_CMD_INIT_RXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
 						EFX_BUF_SIZE));
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_RXQ_OUT_LEN);
 	struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
 	size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
 	struct efx_nic *efx = rx_queue->efx;
-	size_t inlen, outlen;
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t inlen;
 	dma_addr_t dma_addr;
 	int rc;
 	int i;
+	BUILD_BUG_ON(MC_CMD_INIT_RXQ_OUT_LEN != 0);
 
 	rx_queue->scatter_n = 0;
 	rx_queue->scatter_len = 0;
@@ -1517,7 +2021,7 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
 			      INIT_RXQ_IN_FLAG_PREFIX, 1,
 			      INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
-	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, nic_data->vport_id);
 
 	dma_addr = rx_queue->rxd.buf.dma_addr;
 
@@ -1532,7 +2036,7 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
 	inlen = MC_CMD_INIT_RXQ_IN_LEN(entries);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_INIT_RXQ, inbuf, inlen,
-			  outbuf, sizeof(outbuf), &outlen);
+			  NULL, 0, NULL);
 	if (rc)
 		netdev_WARN(efx->net_dev, "failed to initialise RXQ %d\n",
 			    efx_rx_queue_index(rx_queue));
@@ -1541,7 +2045,7 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
 static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_RXQ_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_RXQ_OUT_LEN);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	struct efx_nic *efx = rx_queue->efx;
 	size_t outlen;
 	int rc;
@@ -1703,7 +2207,7 @@ static int efx_ef10_ev_init(struct efx_channel *channel)
 static void efx_ef10_ev_fini(struct efx_channel *channel)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_EVQ_OUT_LEN);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	struct efx_nic *efx = channel->efx;
 	size_t outlen;
 	int rc;
@@ -2286,11 +2790,12 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx,
 			       match_fields);
 	}
 
-	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_PORT_ID, nic_data->vport_id);
 	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_DEST,
 		       spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ?
 		       MC_CMD_FILTER_OP_IN_RX_DEST_DROP :
 		       MC_CMD_FILTER_OP_IN_RX_DEST_HOST);
+	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_TX_DOMAIN, 0);
 	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_TX_DEST,
 		       MC_CMD_FILTER_OP_IN_TX_DEST_DEFAULT);
 	MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_QUEUE,
@@ -3055,6 +3560,9 @@ fail:
 	return rc;
 }
 
+/* Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
 static void efx_ef10_filter_table_restore(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
@@ -3064,9 +3572,14 @@ static void efx_ef10_filter_table_restore(struct efx_nic *efx)
 	bool failed = false;
 	int rc;
 
+	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
+
 	if (!nic_data->must_restore_filters)
 		return;
 
+	if (!table)
+		return;
+
 	spin_lock_bh(&efx->filter_lock);
 
 	for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
@@ -3102,6 +3615,7 @@ static void efx_ef10_filter_table_restore(struct efx_nic *efx)
 		nic_data->must_restore_filters = false;
 }
 
+/* Caller must hold efx->filter_sem for write */
 static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
@@ -3110,6 +3624,10 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 	unsigned int filter_idx;
 	int rc;
 
+	efx->filter_state = NULL;
+	if (!table)
+		return;
+
 	for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
 		spec = efx_ef10_filter_entry_spec(table, filter_idx);
 		if (!spec)
@@ -3135,6 +3653,9 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx)
 	kfree(table);
 }
 
+/* Caller must hold efx->filter_sem for read if race against
+ * efx_ef10_filter_table_remove() is possible
+ */
 static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
 {
 	struct efx_ef10_filter_table *table = efx->filter_state;
@@ -3149,6 +3670,9 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
 	if (!efx_dev_registered(efx))
 		return;
 
+	if (!table)
+		return;
+
 	/* Mark old filters that may need to be removed */
 	spin_lock_bh(&efx->filter_lock);
 	n = table->dev_uc_count < 0 ? 1 : table->dev_uc_count;
@@ -3280,6 +3804,78 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
 	WARN_ON(remove_failed);
 }
 
+static int efx_ef10_set_mac_address(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_SET_MAC_IN_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	bool was_enabled = efx->port_enabled;
+	int rc;
+
+	efx_device_detach_sync(efx);
+	efx_net_stop(efx->net_dev);
+	down_write(&efx->filter_sem);
+	efx_ef10_filter_table_remove(efx);
+
+	ether_addr_copy(MCDI_PTR(inbuf, VADAPTOR_SET_MAC_IN_MACADDR),
+			efx->net_dev->dev_addr);
+	MCDI_SET_DWORD(inbuf, VADAPTOR_SET_MAC_IN_UPSTREAM_PORT_ID,
+		       nic_data->vport_id);
+	rc = efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
+			  sizeof(inbuf), NULL, 0, NULL);
+
+	efx_ef10_filter_table_probe(efx);
+	up_write(&efx->filter_sem);
+	if (was_enabled)
+		efx_net_open(efx->net_dev);
+	netif_device_attach(efx->net_dev);
+
+#if !defined(CONFIG_SFC_SRIOV)
+	if (rc == -EPERM)
+		netif_err(efx, drv, efx->net_dev,
+			  "Cannot change MAC address; use sfboot to enable mac-spoofing"
+			  " on this interface\n");
+#else
+	if (rc == -EPERM) {
+		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
+
+		/* Switch to PF and change MAC address on vport */
+		if (efx->pci_dev->is_virtfn && pci_dev_pf) {
+			struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+
+			if (!efx_ef10_sriov_set_vf_mac(efx_pf,
+						       nic_data->vf_index,
+						       efx->net_dev->dev_addr))
+				return 0;
+		}
+		netif_err(efx, drv, efx->net_dev,
+			  "Cannot change MAC address; use sfboot to enable mac-spoofing"
+			  " on this interface\n");
+	} else if (efx->pci_dev->is_virtfn) {
+		/* Successfully changed by VF (with MAC spoofing), so update the
+		 * parent PF if possible.
+		 */
+		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
+
+		if (pci_dev_pf) {
+			struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+			struct efx_ef10_nic_data *nic_data = efx_pf->nic_data;
+			unsigned int i;
+
+			for (i = 0; i < efx_pf->vf_count; ++i) {
+				struct ef10_vf *vf = nic_data->vf + i;
+
+				if (vf->efx == efx) {
+					ether_addr_copy(vf->mac,
+							efx->net_dev->dev_addr);
+					return 0;
+				}
+			}
+		}
+	}
+#endif
+	return rc;
+}
+
 static int efx_ef10_mac_reconfigure(struct efx_nic *efx)
 {
 	efx_ef10_filter_sync_rx_mode(efx);
@@ -3287,6 +3883,13 @@ static int efx_ef10_mac_reconfigure(struct efx_nic *efx)
 	return efx_mcdi_set_mac(efx);
 }
 
+static int efx_ef10_mac_reconfigure_vf(struct efx_nic *efx)
+{
+	efx_ef10_filter_sync_rx_mode(efx);
+
+	return 0;
+}
+
 static int efx_ef10_start_bist(struct efx_nic *efx, u32 bist_type)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN);
@@ -3494,6 +4097,9 @@ static void efx_ef10_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
 	_efx_writed(efx, cpu_to_le32(host_time), ER_DZ_MC_DB_LWRD);
 }
 
+static void efx_ef10_ptp_write_host_time_vf(struct efx_nic *efx,
+					    u32 host_time) {}
+
 static int efx_ef10_rx_enable_timestamping(struct efx_channel *channel,
 					   bool temp)
 {
@@ -3571,6 +4177,12 @@ static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en,
 	return 0;
 }
 
+static int efx_ef10_ptp_set_ts_config_vf(struct efx_nic *efx,
+					 struct hwtstamp_config *init)
+{
+	return -EOPNOTSUPP;
+}
+
 static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
 				      struct hwtstamp_config *init)
 {
@@ -3607,14 +4219,118 @@ static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
 	}
 }
 
+const struct efx_nic_type efx_hunt_a0_vf_nic_type = {
+	.is_vf = true,
+	.mem_bar = EFX_MEM_VF_BAR,
+	.mem_map_size = efx_ef10_mem_map_size,
+	.probe = efx_ef10_probe_vf,
+	.remove = efx_ef10_remove,
+	.dimension_resources = efx_ef10_dimension_resources,
+	.init = efx_ef10_init_nic,
+	.fini = efx_port_dummy_op_void,
+	.map_reset_reason = efx_ef10_map_reset_reason,
+	.map_reset_flags = efx_ef10_map_reset_flags,
+	.reset = efx_ef10_reset,
+	.probe_port = efx_mcdi_port_probe,
+	.remove_port = efx_mcdi_port_remove,
+	.fini_dmaq = efx_ef10_fini_dmaq,
+	.prepare_flr = efx_ef10_prepare_flr,
+	.finish_flr = efx_port_dummy_op_void,
+	.describe_stats = efx_ef10_describe_stats,
+	.update_stats = efx_ef10_update_stats_vf,
+	.start_stats = efx_port_dummy_op_void,
+	.pull_stats = efx_port_dummy_op_void,
+	.stop_stats = efx_port_dummy_op_void,
+	.set_id_led = efx_mcdi_set_id_led,
+	.push_irq_moderation = efx_ef10_push_irq_moderation,
+	.reconfigure_mac = efx_ef10_mac_reconfigure_vf,
+	.check_mac_fault = efx_mcdi_mac_check_fault,
+	.reconfigure_port = efx_mcdi_port_reconfigure,
+	.get_wol = efx_ef10_get_wol_vf,
+	.set_wol = efx_ef10_set_wol_vf,
+	.resume_wol = efx_port_dummy_op_void,
+	.mcdi_request = efx_ef10_mcdi_request,
+	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
+	.mcdi_read_response = efx_ef10_mcdi_read_response,
+	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
+	.irq_enable_master = efx_port_dummy_op_void,
+	.irq_test_generate = efx_ef10_irq_test_generate,
+	.irq_disable_non_ev = efx_port_dummy_op_void,
+	.irq_handle_msi = efx_ef10_msi_interrupt,
+	.irq_handle_legacy = efx_ef10_legacy_interrupt,
+	.tx_probe = efx_ef10_tx_probe,
+	.tx_init = efx_ef10_tx_init,
+	.tx_remove = efx_ef10_tx_remove,
+	.tx_write = efx_ef10_tx_write,
+	.rx_push_rss_config = efx_ef10_vf_rx_push_rss_config,
+	.rx_probe = efx_ef10_rx_probe,
+	.rx_init = efx_ef10_rx_init,
+	.rx_remove = efx_ef10_rx_remove,
+	.rx_write = efx_ef10_rx_write,
+	.rx_defer_refill = efx_ef10_rx_defer_refill,
+	.ev_probe = efx_ef10_ev_probe,
+	.ev_init = efx_ef10_ev_init,
+	.ev_fini = efx_ef10_ev_fini,
+	.ev_remove = efx_ef10_ev_remove,
+	.ev_process = efx_ef10_ev_process,
+	.ev_read_ack = efx_ef10_ev_read_ack,
+	.ev_test_generate = efx_ef10_ev_test_generate,
+	.filter_table_probe = efx_ef10_filter_table_probe,
+	.filter_table_restore = efx_ef10_filter_table_restore,
+	.filter_table_remove = efx_ef10_filter_table_remove,
+	.filter_update_rx_scatter = efx_ef10_filter_update_rx_scatter,
+	.filter_insert = efx_ef10_filter_insert,
+	.filter_remove_safe = efx_ef10_filter_remove_safe,
+	.filter_get_safe = efx_ef10_filter_get_safe,
+	.filter_clear_rx = efx_ef10_filter_clear_rx,
+	.filter_count_rx_used = efx_ef10_filter_count_rx_used,
+	.filter_get_rx_id_limit = efx_ef10_filter_get_rx_id_limit,
+	.filter_get_rx_ids = efx_ef10_filter_get_rx_ids,
+#ifdef CONFIG_RFS_ACCEL
+	.filter_rfs_insert = efx_ef10_filter_rfs_insert,
+	.filter_rfs_expire_one = efx_ef10_filter_rfs_expire_one,
+#endif
+#ifdef CONFIG_SFC_MTD
+	.mtd_probe = efx_port_dummy_op_int,
+#endif
+	.ptp_write_host_time = efx_ef10_ptp_write_host_time_vf,
+	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config_vf,
+#ifdef CONFIG_SFC_SRIOV
+	.vswitching_probe = efx_ef10_vswitching_probe_vf,
+	.vswitching_restore = efx_ef10_vswitching_restore_vf,
+	.vswitching_remove = efx_ef10_vswitching_remove_vf,
+	.sriov_get_phys_port_id = efx_ef10_sriov_get_phys_port_id,
+#endif
+	.get_mac_address = efx_ef10_get_mac_address_vf,
+	.set_mac_address = efx_ef10_set_mac_address,
+
+	.revision = EFX_REV_HUNT_A0,
+	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
+	.rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
+	.rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
+	.rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
+	.can_rx_scatter = true,
+	.always_rx_scatter = true,
+	.max_interrupt_mode = EFX_INT_MODE_MSIX,
+	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
+	.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
+	.mcdi_max_ver = 2,
+	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
+	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
+			    1 << HWTSTAMP_FILTER_ALL,
+};
+
 const struct efx_nic_type efx_hunt_a0_nic_type = {
+	.is_vf = false,
+	.mem_bar = EFX_MEM_BAR,
 	.mem_map_size = efx_ef10_mem_map_size,
-	.probe = efx_ef10_probe,
+	.probe = efx_ef10_probe_pf,
 	.remove = efx_ef10_remove,
 	.dimension_resources = efx_ef10_dimension_resources,
 	.init = efx_ef10_init_nic,
 	.fini = efx_port_dummy_op_void,
-	.map_reset_reason = efx_mcdi_map_reset_reason,
+	.map_reset_reason = efx_ef10_map_reset_reason,
 	.map_reset_flags = efx_ef10_map_reset_flags,
 	.reset = efx_ef10_reset,
 	.probe_port = efx_mcdi_port_probe,
@@ -3623,7 +4339,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.prepare_flr = efx_ef10_prepare_flr,
 	.finish_flr = efx_port_dummy_op_void,
 	.describe_stats = efx_ef10_describe_stats,
-	.update_stats = efx_ef10_update_stats,
+	.update_stats = efx_ef10_update_stats_pf,
 	.start_stats = efx_mcdi_mac_start_stats,
 	.pull_stats = efx_mcdi_mac_pull_stats,
 	.stop_stats = efx_mcdi_mac_stop_stats,
@@ -3650,7 +4366,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.tx_init = efx_ef10_tx_init,
 	.tx_remove = efx_ef10_tx_remove,
 	.tx_write = efx_ef10_tx_write,
-	.rx_push_rss_config = efx_ef10_rx_push_rss_config,
+	.rx_push_rss_config = efx_ef10_pf_rx_push_rss_config,
 	.rx_probe = efx_ef10_rx_probe,
 	.rx_init = efx_ef10_rx_init,
 	.rx_remove = efx_ef10_rx_remove,
@@ -3689,11 +4405,24 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
 	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
 	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
+#ifdef CONFIG_SFC_SRIOV
+	.sriov_configure = efx_ef10_sriov_configure,
 	.sriov_init = efx_ef10_sriov_init,
 	.sriov_fini = efx_ef10_sriov_fini,
-	.sriov_mac_address_changed = efx_ef10_sriov_mac_address_changed,
 	.sriov_wanted = efx_ef10_sriov_wanted,
 	.sriov_reset = efx_ef10_sriov_reset,
+	.sriov_flr = efx_ef10_sriov_flr,
+	.sriov_set_vf_mac = efx_ef10_sriov_set_vf_mac,
+	.sriov_set_vf_vlan = efx_ef10_sriov_set_vf_vlan,
+	.sriov_set_vf_spoofchk = efx_ef10_sriov_set_vf_spoofchk,
+	.sriov_get_vf_config = efx_ef10_sriov_get_vf_config,
+	.sriov_set_vf_link_state = efx_ef10_sriov_set_vf_link_state,
+	.vswitching_probe = efx_ef10_vswitching_probe_pf,
+	.vswitching_restore = efx_ef10_vswitching_restore_pf,
+	.vswitching_remove = efx_ef10_vswitching_remove_pf,
+#endif
+	.get_mac_address = efx_ef10_get_mac_address_pf,
+	.set_mac_address = efx_ef10_set_mac_address,
 
 	.revision = EFX_REV_HUNT_A0,
 	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
new file mode 100644
index 000000000000..6c9b6e45509a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -0,0 +1,783 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#include <linux/pci.h>
+#include <linux/module.h>
+#include "net_driver.h"
+#include "ef10_sriov.h"
+#include "efx.h"
+#include "nic.h"
+#include "mcdi_pcol.h"
+
+static int efx_ef10_evb_port_assign(struct efx_nic *efx, unsigned int port_id,
+				    unsigned int vf_fn)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_EVB_PORT_ASSIGN_IN_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	MCDI_SET_DWORD(inbuf, EVB_PORT_ASSIGN_IN_PORT_ID, port_id);
+	MCDI_POPULATE_DWORD_2(inbuf, EVB_PORT_ASSIGN_IN_FUNCTION,
+			      EVB_PORT_ASSIGN_IN_PF, nic_data->pf_index,
+			      EVB_PORT_ASSIGN_IN_VF, vf_fn);
+
+	return efx_mcdi_rpc(efx, MC_CMD_EVB_PORT_ASSIGN, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static int efx_ef10_vport_add_mac(struct efx_nic *efx,
+				  unsigned int port_id, u8 *mac)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VPORT_ADD_MAC_ADDRESS_IN_VPORT_ID, port_id);
+	ether_addr_copy(MCDI_PTR(inbuf, VPORT_ADD_MAC_ADDRESS_IN_MACADDR), mac);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VPORT_ADD_MAC_ADDRESS, inbuf,
+			    sizeof(inbuf), NULL, 0, NULL);
+}
+
+static int efx_ef10_vport_del_mac(struct efx_nic *efx,
+				  unsigned int port_id, u8 *mac)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID, port_id);
+	ether_addr_copy(MCDI_PTR(inbuf, VPORT_DEL_MAC_ADDRESS_IN_MACADDR), mac);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VPORT_DEL_MAC_ADDRESS, inbuf,
+			    sizeof(inbuf), NULL, 0, NULL);
+}
+
+static int efx_ef10_vswitch_alloc(struct efx_nic *efx, unsigned int port_id,
+				  unsigned int vswitch_type)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VSWITCH_ALLOC_IN_LEN);
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, VSWITCH_ALLOC_IN_UPSTREAM_PORT_ID, port_id);
+	MCDI_SET_DWORD(inbuf, VSWITCH_ALLOC_IN_TYPE, vswitch_type);
+	MCDI_SET_DWORD(inbuf, VSWITCH_ALLOC_IN_NUM_VLAN_TAGS, 2);
+	MCDI_POPULATE_DWORD_1(inbuf, VSWITCH_ALLOC_IN_FLAGS,
+			      VSWITCH_ALLOC_IN_FLAG_AUTO_PORT, 0);
+
+	/* Quietly try to allocate 2 VLAN tags */
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_VSWITCH_ALLOC, inbuf, sizeof(inbuf),
+				NULL, 0, NULL);
+
+	/* If 2 VLAN tags is too many, revert to trying with 1 VLAN tags */
+	if (rc == -EPROTO) {
+		MCDI_SET_DWORD(inbuf, VSWITCH_ALLOC_IN_NUM_VLAN_TAGS, 1);
+		rc = efx_mcdi_rpc(efx, MC_CMD_VSWITCH_ALLOC, inbuf,
+				  sizeof(inbuf), NULL, 0, NULL);
+	} else if (rc) {
+		efx_mcdi_display_error(efx, MC_CMD_VSWITCH_ALLOC,
+				       MC_CMD_VSWITCH_ALLOC_IN_LEN,
+				       NULL, 0, rc);
+	}
+	return rc;
+}
+
+static int efx_ef10_vswitch_free(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VSWITCH_FREE_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VSWITCH_FREE_IN_UPSTREAM_PORT_ID, port_id);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VSWITCH_FREE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static int efx_ef10_vport_alloc(struct efx_nic *efx,
+				unsigned int port_id_in,
+				unsigned int vport_type,
+				u16 vlan,
+				unsigned int *port_id_out)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ALLOC_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_VPORT_ALLOC_OUT_LEN);
+	size_t outlen;
+	int rc;
+
+	EFX_WARN_ON_PARANOID(!port_id_out);
+
+	MCDI_SET_DWORD(inbuf, VPORT_ALLOC_IN_UPSTREAM_PORT_ID, port_id_in);
+	MCDI_SET_DWORD(inbuf, VPORT_ALLOC_IN_TYPE, vport_type);
+	MCDI_SET_DWORD(inbuf, VPORT_ALLOC_IN_NUM_VLAN_TAGS,
+		       (vlan != EFX_EF10_NO_VLAN));
+	MCDI_POPULATE_DWORD_1(inbuf, VPORT_ALLOC_IN_FLAGS,
+			      VPORT_ALLOC_IN_FLAG_AUTO_PORT, 0);
+	if (vlan != EFX_EF10_NO_VLAN)
+		MCDI_POPULATE_DWORD_1(inbuf, VPORT_ALLOC_IN_VLAN_TAGS,
+				      VPORT_ALLOC_IN_VLAN_TAG_0, vlan);
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_VPORT_ALLOC, inbuf, sizeof(inbuf),
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < MC_CMD_VPORT_ALLOC_OUT_LEN)
+		return -EIO;
+
+	*port_id_out = MCDI_DWORD(outbuf, VPORT_ALLOC_OUT_VPORT_ID);
+	return 0;
+}
+
+static int efx_ef10_vport_free(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_FREE_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VPORT_FREE_IN_VPORT_ID, port_id);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VPORT_FREE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID, port_id);
+	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_ALLOC, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_FREE_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VADAPTOR_FREE_IN_UPSTREAM_PORT_ID, port_id);
+	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_FREE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static void efx_ef10_sriov_free_vf_vports(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	int i;
+
+	if (!nic_data->vf)
+		return;
+
+	for (i = 0; i < efx->vf_count; i++) {
+		struct ef10_vf *vf = nic_data->vf + i;
+
+		/* If VF is assigned, do not free the vport  */
+		if (vf->pci_dev &&
+		    vf->pci_dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED)
+			continue;
+
+		if (vf->vport_assigned) {
+			efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, i);
+			vf->vport_assigned = 0;
+		}
+
+		if (!is_zero_ether_addr(vf->mac)) {
+			efx_ef10_vport_del_mac(efx, vf->vport_id, vf->mac);
+			eth_zero_addr(vf->mac);
+		}
+
+		if (vf->vport_id) {
+			efx_ef10_vport_free(efx, vf->vport_id);
+			vf->vport_id = 0;
+		}
+
+		vf->efx = NULL;
+	}
+}
+
+static void efx_ef10_sriov_free_vf_vswitching(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	efx_ef10_sriov_free_vf_vports(efx);
+	kfree(nic_data->vf);
+	nic_data->vf = NULL;
+}
+
+static int efx_ef10_sriov_assign_vf_vport(struct efx_nic *efx,
+					  unsigned int vf_i)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct ef10_vf *vf = nic_data->vf + vf_i;
+	int rc;
+
+	if (WARN_ON_ONCE(!nic_data->vf))
+		return -EOPNOTSUPP;
+
+	rc = efx_ef10_vport_alloc(efx, EVB_PORT_ID_ASSIGNED,
+				  MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
+				  vf->vlan, &vf->vport_id);
+	if (rc)
+		return rc;
+
+	rc = efx_ef10_vport_add_mac(efx, vf->vport_id, vf->mac);
+	if (rc) {
+		eth_zero_addr(vf->mac);
+		return rc;
+	}
+
+	rc =  efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
+	if (rc)
+		return rc;
+
+	vf->vport_assigned = 1;
+	return 0;
+}
+
+static int efx_ef10_sriov_alloc_vf_vswitching(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	unsigned int i;
+	int rc;
+
+	nic_data->vf = kcalloc(efx->vf_count, sizeof(struct ef10_vf),
+			       GFP_KERNEL);
+	if (!nic_data->vf)
+		return -ENOMEM;
+
+	for (i = 0; i < efx->vf_count; i++) {
+		random_ether_addr(nic_data->vf[i].mac);
+		nic_data->vf[i].efx = NULL;
+		nic_data->vf[i].vlan = EFX_EF10_NO_VLAN;
+
+		rc = efx_ef10_sriov_assign_vf_vport(efx, i);
+		if (rc)
+			goto fail;
+	}
+
+	return 0;
+fail:
+	efx_ef10_sriov_free_vf_vports(efx);
+	kfree(nic_data->vf);
+	nic_data->vf = NULL;
+	return rc;
+}
+
+static int efx_ef10_sriov_restore_vf_vswitching(struct efx_nic *efx)
+{
+	unsigned int i;
+	int rc;
+
+	for (i = 0; i < efx->vf_count; i++) {
+		rc = efx_ef10_sriov_assign_vf_vport(efx, i);
+		if (rc)
+			goto fail;
+	}
+
+	return 0;
+fail:
+	efx_ef10_sriov_free_vf_vswitching(efx);
+	return rc;
+}
+
+/* On top of the default firmware vswitch setup, create a VEB vswitch and
+ * expansion vport for use by this function.
+ */
+int efx_ef10_vswitching_probe_pf(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct net_device *net_dev = efx->net_dev;
+	int rc;
+
+	if (pci_sriov_get_totalvfs(efx->pci_dev) <= 0) {
+		/* vswitch not needed as we have no VFs */
+		efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+		return 0;
+	}
+
+	rc = efx_ef10_vswitch_alloc(efx, EVB_PORT_ID_ASSIGNED,
+				    MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VEB);
+	if (rc)
+		goto fail1;
+
+	rc = efx_ef10_vport_alloc(efx, EVB_PORT_ID_ASSIGNED,
+				  MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
+				  EFX_EF10_NO_VLAN, &nic_data->vport_id);
+	if (rc)
+		goto fail2;
+
+	rc = efx_ef10_vport_add_mac(efx, nic_data->vport_id, net_dev->dev_addr);
+	if (rc)
+		goto fail3;
+	ether_addr_copy(nic_data->vport_mac, net_dev->dev_addr);
+
+	rc = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	if (rc)
+		goto fail4;
+
+	return 0;
+fail4:
+	efx_ef10_vport_del_mac(efx, nic_data->vport_id, nic_data->vport_mac);
+	eth_zero_addr(nic_data->vport_mac);
+fail3:
+	efx_ef10_vport_free(efx, nic_data->vport_id);
+	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+fail2:
+	efx_ef10_vswitch_free(efx, EVB_PORT_ID_ASSIGNED);
+fail1:
+	return rc;
+}
+
+int efx_ef10_vswitching_probe_vf(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	return efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+}
+
+int efx_ef10_vswitching_restore_pf(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	int rc;
+
+	if (!nic_data->must_probe_vswitching)
+		return 0;
+
+	rc = efx_ef10_vswitching_probe_pf(efx);
+	if (rc)
+		goto fail;
+
+	rc = efx_ef10_sriov_restore_vf_vswitching(efx);
+	if (rc)
+		goto fail;
+
+	nic_data->must_probe_vswitching = false;
+fail:
+	return rc;
+}
+
+int efx_ef10_vswitching_restore_vf(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	int rc;
+
+	if (!nic_data->must_probe_vswitching)
+		return 0;
+
+	rc = efx_ef10_vadaptor_free(efx, EVB_PORT_ID_ASSIGNED);
+	if (rc)
+		return rc;
+
+	nic_data->must_probe_vswitching = false;
+	return 0;
+}
+
+void efx_ef10_vswitching_remove_pf(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	efx_ef10_sriov_free_vf_vswitching(efx);
+
+	efx_ef10_vadaptor_free(efx, nic_data->vport_id);
+
+	if (nic_data->vport_id == EVB_PORT_ID_ASSIGNED)
+		return; /* No vswitch was ever created */
+
+	if (!is_zero_ether_addr(nic_data->vport_mac)) {
+		efx_ef10_vport_del_mac(efx, nic_data->vport_id,
+				       efx->net_dev->dev_addr);
+		eth_zero_addr(nic_data->vport_mac);
+	}
+	efx_ef10_vport_free(efx, nic_data->vport_id);
+	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+
+	/* Only free the vswitch if no VFs are assigned */
+	if (!pci_vfs_assigned(efx->pci_dev))
+		efx_ef10_vswitch_free(efx, nic_data->vport_id);
+}
+
+void efx_ef10_vswitching_remove_vf(struct efx_nic *efx)
+{
+	efx_ef10_vadaptor_free(efx, EVB_PORT_ID_ASSIGNED);
+}
+
+static int efx_ef10_pci_sriov_enable(struct efx_nic *efx, int num_vfs)
+{
+	int rc = 0;
+	struct pci_dev *dev = efx->pci_dev;
+
+	efx->vf_count = num_vfs;
+
+	rc = efx_ef10_sriov_alloc_vf_vswitching(efx);
+	if (rc)
+		goto fail1;
+
+	rc = pci_enable_sriov(dev, num_vfs);
+	if (rc)
+		goto fail2;
+
+	return 0;
+fail2:
+	efx_ef10_sriov_free_vf_vswitching(efx);
+fail1:
+	efx->vf_count = 0;
+	netif_err(efx, probe, efx->net_dev,
+		  "Failed to enable SRIOV VFs\n");
+	return rc;
+}
+
+static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force)
+{
+	struct pci_dev *dev = efx->pci_dev;
+	unsigned int vfs_assigned = 0;
+
+	vfs_assigned = pci_vfs_assigned(dev);
+
+	if (vfs_assigned && !force) {
+		netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; "
+			   "please detach them before disabling SR-IOV\n");
+		return -EBUSY;
+	}
+
+	if (!vfs_assigned)
+		pci_disable_sriov(dev);
+
+	efx_ef10_sriov_free_vf_vswitching(efx);
+	efx->vf_count = 0;
+	return 0;
+}
+
+int efx_ef10_sriov_configure(struct efx_nic *efx, int num_vfs)
+{
+	if (num_vfs == 0)
+		return efx_ef10_pci_sriov_disable(efx, false);
+	else
+		return efx_ef10_pci_sriov_enable(efx, num_vfs);
+}
+
+int efx_ef10_sriov_init(struct efx_nic *efx)
+{
+	return 0;
+}
+
+void efx_ef10_sriov_fini(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	unsigned int i;
+	int rc;
+
+	if (!nic_data->vf) {
+		/* Remove any un-assigned orphaned VFs */
+		if (pci_num_vf(efx->pci_dev) && !pci_vfs_assigned(efx->pci_dev))
+			pci_disable_sriov(efx->pci_dev);
+		return;
+	}
+
+	/* Remove any VFs in the host */
+	for (i = 0; i < efx->vf_count; ++i) {
+		struct efx_nic *vf_efx = nic_data->vf[i].efx;
+
+		if (vf_efx)
+			vf_efx->pci_dev->driver->remove(vf_efx->pci_dev);
+	}
+
+	rc = efx_ef10_pci_sriov_disable(efx, true);
+	if (rc)
+		netif_dbg(efx, drv, efx->net_dev,
+			  "Disabling SRIOV was not successful rc=%d\n", rc);
+	else
+		netif_dbg(efx, drv, efx->net_dev, "SRIOV disabled\n");
+}
+
+static int efx_ef10_vport_del_vf_mac(struct efx_nic *efx, unsigned int port_id,
+				     u8 *mac)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN);
+	MCDI_DECLARE_BUF_ERR(outbuf);
+	size_t outlen;
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID, port_id);
+	ether_addr_copy(MCDI_PTR(inbuf, VPORT_DEL_MAC_ADDRESS_IN_MACADDR), mac);
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_VPORT_DEL_MAC_ADDRESS, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+
+	return rc;
+}
+
+int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct ef10_vf *vf;
+	int rc;
+
+	if (!nic_data->vf)
+		return -EOPNOTSUPP;
+
+	if (vf_i >= efx->vf_count)
+		return -EINVAL;
+	vf = nic_data->vf + vf_i;
+
+	if (vf->efx) {
+		efx_device_detach_sync(vf->efx);
+		efx_net_stop(vf->efx->net_dev);
+
+		down_write(&vf->efx->filter_sem);
+		vf->efx->type->filter_table_remove(vf->efx);
+
+		rc = efx_ef10_vadaptor_free(vf->efx, EVB_PORT_ID_ASSIGNED);
+		if (rc) {
+			up_write(&vf->efx->filter_sem);
+			return rc;
+		}
+	}
+
+	rc = efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, vf_i);
+	if (rc)
+		return rc;
+
+	if (!is_zero_ether_addr(vf->mac)) {
+		rc = efx_ef10_vport_del_vf_mac(efx, vf->vport_id, vf->mac);
+		if (rc)
+			return rc;
+	}
+
+	if (!is_zero_ether_addr(mac)) {
+		rc = efx_ef10_vport_add_mac(efx, vf->vport_id, mac);
+		if (rc) {
+			eth_zero_addr(vf->mac);
+			goto fail;
+		}
+		if (vf->efx)
+			ether_addr_copy(vf->efx->net_dev->dev_addr, mac);
+	}
+
+	ether_addr_copy(vf->mac, mac);
+
+	rc = efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
+	if (rc)
+		goto fail;
+
+	if (vf->efx) {
+		/* VF cannot use the vport_id that the PF created */
+		rc = efx_ef10_vadaptor_alloc(vf->efx, EVB_PORT_ID_ASSIGNED);
+		if (rc) {
+			up_write(&vf->efx->filter_sem);
+			return rc;
+		}
+		vf->efx->type->filter_table_probe(vf->efx);
+		up_write(&vf->efx->filter_sem);
+		efx_net_open(vf->efx->net_dev);
+		netif_device_attach(vf->efx->net_dev);
+	}
+
+	return 0;
+
+fail:
+	memset(vf->mac, 0, ETH_ALEN);
+	return rc;
+}
+
+int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
+			       u8 qos)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct ef10_vf *vf;
+	u16 old_vlan, new_vlan;
+	int rc = 0, rc2 = 0;
+
+	if (vf_i >= efx->vf_count)
+		return -EINVAL;
+	if (qos != 0)
+		return -EINVAL;
+
+	vf = nic_data->vf + vf_i;
+
+	new_vlan = (vlan == 0) ? EFX_EF10_NO_VLAN : vlan;
+	if (new_vlan == vf->vlan)
+		return 0;
+
+	if (vf->efx) {
+		efx_device_detach_sync(vf->efx);
+		efx_net_stop(vf->efx->net_dev);
+
+		down_write(&vf->efx->filter_sem);
+		vf->efx->type->filter_table_remove(vf->efx);
+
+		rc = efx_ef10_vadaptor_free(vf->efx, EVB_PORT_ID_ASSIGNED);
+		if (rc)
+			goto restore_filters;
+	}
+
+	if (vf->vport_assigned) {
+		rc = efx_ef10_evb_port_assign(efx, EVB_PORT_ID_NULL, vf_i);
+		if (rc) {
+			netif_warn(efx, drv, efx->net_dev,
+				   "Failed to change vlan on VF %d.\n", vf_i);
+			netif_warn(efx, drv, efx->net_dev,
+				   "This is likely because the VF is bound to a driver in a VM.\n");
+			netif_warn(efx, drv, efx->net_dev,
+				   "Please unload the driver in the VM.\n");
+			goto restore_vadaptor;
+		}
+		vf->vport_assigned = 0;
+	}
+
+	if (!is_zero_ether_addr(vf->mac)) {
+		rc = efx_ef10_vport_del_mac(efx, vf->vport_id, vf->mac);
+		if (rc)
+			goto restore_evb_port;
+	}
+
+	if (vf->vport_id) {
+		rc = efx_ef10_vport_free(efx, vf->vport_id);
+		if (rc)
+			goto restore_mac;
+		vf->vport_id = 0;
+	}
+
+	/* Do the actual vlan change */
+	old_vlan = vf->vlan;
+	vf->vlan = new_vlan;
+
+	/* Restore everything in reverse order */
+	rc = efx_ef10_vport_alloc(efx, EVB_PORT_ID_ASSIGNED,
+				  MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
+				  vf->vlan, &vf->vport_id);
+	if (rc)
+		goto reset_nic;
+
+restore_mac:
+	if (!is_zero_ether_addr(vf->mac)) {
+		rc2 = efx_ef10_vport_add_mac(efx, vf->vport_id, vf->mac);
+		if (rc2) {
+			eth_zero_addr(vf->mac);
+			goto reset_nic;
+		}
+	}
+
+restore_evb_port:
+	rc2 = efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
+	if (rc2)
+		goto reset_nic;
+	else
+		vf->vport_assigned = 1;
+
+restore_vadaptor:
+	if (vf->efx) {
+		rc2 = efx_ef10_vadaptor_alloc(vf->efx, EVB_PORT_ID_ASSIGNED);
+		if (rc2)
+			goto reset_nic;
+	}
+
+restore_filters:
+	if (vf->efx) {
+		rc2 = vf->efx->type->filter_table_probe(vf->efx);
+		if (rc2)
+			goto reset_nic;
+
+		up_write(&vf->efx->filter_sem);
+
+		rc2 = efx_net_open(vf->efx->net_dev);
+		if (rc2)
+			goto reset_nic;
+
+		netif_device_attach(vf->efx->net_dev);
+	}
+	return rc;
+
+reset_nic:
+	if (vf->efx) {
+		up_write(&vf->efx->filter_sem);
+		netif_err(efx, drv, efx->net_dev,
+			  "Failed to restore VF - scheduling reset.\n");
+		efx_schedule_reset(vf->efx, RESET_TYPE_DATAPATH);
+	} else {
+		netif_err(efx, drv, efx->net_dev,
+			  "Failed to restore the VF and cannot reset the VF "
+			  "- VF is not functional.\n");
+		netif_err(efx, drv, efx->net_dev,
+			  "Please reload the driver attached to the VF.\n");
+	}
+
+	return rc ? rc : rc2;
+}
+
+int efx_ef10_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf_i,
+				   bool spoofchk)
+{
+	return spoofchk ? -EOPNOTSUPP : 0;
+}
+
+int efx_ef10_sriov_set_vf_link_state(struct efx_nic *efx, int vf_i,
+				     int link_state)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_LINK_STATE_MODE_IN_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	BUILD_BUG_ON(IFLA_VF_LINK_STATE_AUTO !=
+		     MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_AUTO);
+	BUILD_BUG_ON(IFLA_VF_LINK_STATE_ENABLE !=
+		     MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_UP);
+	BUILD_BUG_ON(IFLA_VF_LINK_STATE_DISABLE !=
+		     MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_DOWN);
+	MCDI_POPULATE_DWORD_2(inbuf, LINK_STATE_MODE_IN_FUNCTION,
+			      LINK_STATE_MODE_IN_FUNCTION_PF,
+			      nic_data->pf_index,
+			      LINK_STATE_MODE_IN_FUNCTION_VF, vf_i);
+	MCDI_SET_DWORD(inbuf, LINK_STATE_MODE_IN_NEW_MODE, link_state);
+	return efx_mcdi_rpc(efx, MC_CMD_LINK_STATE_MODE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL); /* don't care what old mode was */
+}
+
+int efx_ef10_sriov_get_vf_config(struct efx_nic *efx, int vf_i,
+				 struct ifla_vf_info *ivf)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_LINK_STATE_MODE_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_LINK_STATE_MODE_OUT_LEN);
+
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	struct ef10_vf *vf;
+	size_t outlen;
+	int rc;
+
+	if (vf_i >= efx->vf_count)
+		return -EINVAL;
+
+	if (!nic_data->vf)
+		return -EOPNOTSUPP;
+
+	vf = nic_data->vf + vf_i;
+
+	ivf->vf = vf_i;
+	ivf->min_tx_rate = 0;
+	ivf->max_tx_rate = 0;
+	ether_addr_copy(ivf->mac, vf->mac);
+	ivf->vlan = (vf->vlan == EFX_EF10_NO_VLAN) ? 0 : vf->vlan;
+	ivf->qos = 0;
+
+	MCDI_POPULATE_DWORD_2(inbuf, LINK_STATE_MODE_IN_FUNCTION,
+			      LINK_STATE_MODE_IN_FUNCTION_PF,
+			      nic_data->pf_index,
+			      LINK_STATE_MODE_IN_FUNCTION_VF, vf_i);
+	MCDI_SET_DWORD(inbuf, LINK_STATE_MODE_IN_NEW_MODE,
+		       MC_CMD_LINK_STATE_MODE_IN_DO_NOT_CHANGE);
+	rc = efx_mcdi_rpc(efx, MC_CMD_LINK_STATE_MODE, inbuf, sizeof(inbuf),
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < MC_CMD_LINK_STATE_MODE_OUT_LEN)
+		return -EIO;
+	ivf->linkstate = MCDI_DWORD(outbuf, LINK_STATE_MODE_OUT_OLD_MODE);
+
+	return 0;
+}
+
+int efx_ef10_sriov_get_phys_port_id(struct efx_nic *efx,
+				    struct netdev_phys_item_id *ppid)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+	if (!is_valid_ether_addr(nic_data->port_id))
+		return -EOPNOTSUPP;
+
+	ppid->id_len = ETH_ALEN;
+	memcpy(ppid->id, nic_data->port_id, ppid->id_len);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
new file mode 100644
index 000000000000..db4ef537c610
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -0,0 +1,69 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EF10_SRIOV_H
+#define EF10_SRIOV_H
+
+#include "net_driver.h"
+
+/**
+ * struct ef10_vf - PF's store of VF data
+ * @efx: efx_nic struct for the current VF
+ * @pci_dev: the pci_dev struct for the VF, retained while the VF is assigned
+ * @vport_id: vport ID for the VF
+ * @vport_assigned: record whether the vport is currently assigned to the VF
+ * @mac: MAC address for the VF, zero when address is removed from the vport
+ * @vlan: Default VLAN for the VF or #EFX_EF10_NO_VLAN
+ */
+struct ef10_vf {
+	struct efx_nic *efx;
+	struct pci_dev *pci_dev;
+	unsigned int vport_id;
+	unsigned int vport_assigned;
+	u8 mac[ETH_ALEN];
+	u16 vlan;
+#define EFX_EF10_NO_VLAN       0
+};
+
+static inline bool efx_ef10_sriov_wanted(struct efx_nic *efx)
+{
+	return false;
+}
+
+int efx_ef10_sriov_configure(struct efx_nic *efx, int num_vfs);
+int efx_ef10_sriov_init(struct efx_nic *efx);
+static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {}
+void efx_ef10_sriov_fini(struct efx_nic *efx);
+static inline void efx_ef10_sriov_flr(struct efx_nic *efx, unsigned vf_i) {}
+
+int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac);
+
+int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i,
+			       u16 vlan, u8 qos);
+
+int efx_ef10_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf,
+				   bool spoofchk);
+
+int efx_ef10_sriov_get_vf_config(struct efx_nic *efx, int vf_i,
+				 struct ifla_vf_info *ivf);
+
+int efx_ef10_sriov_set_vf_link_state(struct efx_nic *efx, int vf_i,
+				     int link_state);
+
+int efx_ef10_sriov_get_phys_port_id(struct efx_nic *efx,
+				    struct netdev_phys_item_id *ppid);
+
+int efx_ef10_vswitching_probe_pf(struct efx_nic *efx);
+int efx_ef10_vswitching_probe_vf(struct efx_nic *efx);
+int efx_ef10_vswitching_restore_pf(struct efx_nic *efx);
+int efx_ef10_vswitching_restore_vf(struct efx_nic *efx);
+void efx_ef10_vswitching_remove_pf(struct efx_nic *efx);
+void efx_ef10_vswitching_remove_vf(struct efx_nic *efx);
+
+#endif /* EF10_SRIOV_H */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 4b00545a3ace..804b9ad553d3 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -26,6 +26,7 @@
 #include "efx.h"
 #include "nic.h"
 #include "selftest.h"
+#include "sriov.h"
 
 #include "mcdi.h"
 #include "workarounds.h"
@@ -76,6 +77,7 @@ const char *const efx_reset_type_names[] = {
 	[RESET_TYPE_RECOVER_OR_ALL]     = "RECOVER_OR_ALL",
 	[RESET_TYPE_WORLD]              = "WORLD",
 	[RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE",
+	[RESET_TYPE_DATAPATH]           = "DATAPATH",
 	[RESET_TYPE_MC_BIST]		= "MC_BIST",
 	[RESET_TYPE_DISABLE]            = "DISABLE",
 	[RESET_TYPE_TX_WATCHDOG]        = "TX_WATCHDOG",
@@ -948,6 +950,16 @@ void efx_link_set_wanted_fc(struct efx_nic *efx, u8 wanted_fc)
 
 static void efx_fini_port(struct efx_nic *efx);
 
+/* We assume that efx->type->reconfigure_mac will always try to sync RX
+ * filters and therefore needs to read-lock the filter table against freeing
+ */
+void efx_mac_reconfigure(struct efx_nic *efx)
+{
+	down_read(&efx->filter_sem);
+	efx->type->reconfigure_mac(efx);
+	up_read(&efx->filter_sem);
+}
+
 /* Push loopback/power/transmit disable settings to the PHY, and reconfigure
  * the MAC appropriately. All other PHY configuration changes are pushed
  * through phy_op->set_settings(), and pushed asynchronously to the MAC
@@ -1001,7 +1013,7 @@ static void efx_mac_work(struct work_struct *data)
 
 	mutex_lock(&efx->mac_lock);
 	if (efx->port_enabled)
-		efx->type->reconfigure_mac(efx);
+		efx_mac_reconfigure(efx);
 	mutex_unlock(&efx->mac_lock);
 }
 
@@ -1041,11 +1053,11 @@ static int efx_init_port(struct efx_nic *efx)
 
 	/* Reconfigure the MAC before creating dma queues (required for
 	 * Falcon/A1 where RX_INGR_EN/TX_DRAIN_EN isn't supported) */
-	efx->type->reconfigure_mac(efx);
+	efx_mac_reconfigure(efx);
 
 	/* Ensure the PHY advertises the correct flow control settings */
 	rc = efx->phy_op->reconfigure(efx);
-	if (rc)
+	if (rc && rc != -EPERM)
 		goto fail2;
 
 	mutex_unlock(&efx->mac_lock);
@@ -1067,7 +1079,7 @@ static void efx_start_port(struct efx_nic *efx)
 	efx->port_enabled = true;
 
 	/* Ensure MAC ingress/egress is enabled */
-	efx->type->reconfigure_mac(efx);
+	efx_mac_reconfigure(efx);
 
 	mutex_unlock(&efx->mac_lock);
 }
@@ -1200,10 +1212,12 @@ static int efx_init_io(struct efx_nic *efx)
 	struct pci_dev *pci_dev = efx->pci_dev;
 	dma_addr_t dma_mask = efx->type->max_dma_mask;
 	unsigned int mem_map_size = efx->type->mem_map_size(efx);
-	int rc;
+	int rc, bar;
 
 	netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
 
+	bar = efx->type->mem_bar;
+
 	rc = pci_enable_device(pci_dev);
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
@@ -1234,8 +1248,8 @@ static int efx_init_io(struct efx_nic *efx)
 	netif_dbg(efx, probe, efx->net_dev,
 		  "using DMA mask %llx\n", (unsigned long long) dma_mask);
 
-	efx->membase_phys = pci_resource_start(efx->pci_dev, EFX_MEM_BAR);
-	rc = pci_request_region(pci_dev, EFX_MEM_BAR, "sfc");
+	efx->membase_phys = pci_resource_start(efx->pci_dev, bar);
+	rc = pci_request_region(pci_dev, bar, "sfc");
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "request for memory BAR failed\n");
@@ -1258,7 +1272,7 @@ static int efx_init_io(struct efx_nic *efx)
 	return 0;
 
  fail4:
-	pci_release_region(efx->pci_dev, EFX_MEM_BAR);
+	pci_release_region(efx->pci_dev, bar);
  fail3:
 	efx->membase_phys = 0;
  fail2:
@@ -1269,6 +1283,8 @@ static int efx_init_io(struct efx_nic *efx)
 
 static void efx_fini_io(struct efx_nic *efx)
 {
+	int bar;
+
 	netif_dbg(efx, drv, efx->net_dev, "shutting down I/O\n");
 
 	if (efx->membase) {
@@ -1277,11 +1293,23 @@ static void efx_fini_io(struct efx_nic *efx)
 	}
 
 	if (efx->membase_phys) {
-		pci_release_region(efx->pci_dev, EFX_MEM_BAR);
+		bar = efx->type->mem_bar;
+		pci_release_region(efx->pci_dev, bar);
 		efx->membase_phys = 0;
 	}
 
-	pci_disable_device(efx->pci_dev);
+	/* Don't disable bus-mastering if VFs are assigned */
+	if (!pci_vfs_assigned(efx->pci_dev))
+		pci_disable_device(efx->pci_dev);
+}
+
+void efx_set_default_rx_indir_table(struct efx_nic *efx)
+{
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
+		efx->rx_indir_table[i] =
+			ethtool_rxfh_indir_default(i, efx->rss_spread);
 }
 
 static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
@@ -1304,7 +1332,7 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 			if (!cpumask_test_cpu(cpu, thread_mask)) {
 				++count;
 				cpumask_or(thread_mask, thread_mask,
-					   topology_thread_cpumask(cpu));
+					   topology_sibling_cpumask(cpu));
 			}
 		}
 
@@ -1314,15 +1342,19 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 	/* If RSS is requested for the PF *and* VFs then we can't write RSS
 	 * table entries that are inaccessible to VFs
 	 */
-	if (efx->type->sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
-	    count > efx_vf_size(efx)) {
-		netif_warn(efx, probe, efx->net_dev,
-			   "Reducing number of RSS channels from %u to %u for "
-			   "VF support. Increase vf-msix-limit to use more "
-			   "channels on the PF.\n",
-			   count, efx_vf_size(efx));
-		count = efx_vf_size(efx);
+#ifdef CONFIG_SFC_SRIOV
+	if (efx->type->sriov_wanted) {
+		if (efx->type->sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
+		    count > efx_vf_size(efx)) {
+			netif_warn(efx, probe, efx->net_dev,
+				   "Reducing number of RSS channels from %u to %u for "
+				   "VF support. Increase vf-msix-limit to use more "
+				   "channels on the PF.\n",
+				   count, efx_vf_size(efx));
+			count = efx_vf_size(efx);
+		}
 	}
+#endif
 
 	return count;
 }
@@ -1426,10 +1458,15 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 	}
 
 	/* RSS might be usable on VFs even if it is disabled on the PF */
-
-	efx->rss_spread = ((efx->n_rx_channels > 1 ||
-			    !efx->type->sriov_wanted(efx)) ?
-			   efx->n_rx_channels : efx_vf_size(efx));
+#ifdef CONFIG_SFC_SRIOV
+	if (efx->type->sriov_wanted) {
+		efx->rss_spread = ((efx->n_rx_channels > 1 ||
+				    !efx->type->sriov_wanted(efx)) ?
+				   efx->n_rx_channels : efx_vf_size(efx));
+		return 0;
+	}
+#endif
+	efx->rss_spread = efx->n_rx_channels;
 
 	return 0;
 }
@@ -1593,7 +1630,6 @@ static void efx_set_channels(struct efx_nic *efx)
 
 static int efx_probe_nic(struct efx_nic *efx)
 {
-	size_t i;
 	int rc;
 
 	netif_dbg(efx, probe, efx->net_dev, "creating NIC\n");
@@ -1616,10 +1652,9 @@ static int efx_probe_nic(struct efx_nic *efx)
 		goto fail2;
 
 	if (efx->n_channels > 1)
-		netdev_rss_key_fill(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
-	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
-		efx->rx_indir_table[i] =
-			ethtool_rxfh_indir_default(i, efx->rss_spread);
+		netdev_rss_key_fill(&efx->rx_hash_key,
+				    sizeof(efx->rx_hash_key));
+	efx_set_default_rx_indir_table(efx);
 
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
@@ -1650,10 +1685,11 @@ static int efx_probe_filters(struct efx_nic *efx)
 	int rc;
 
 	spin_lock_init(&efx->filter_lock);
-
+	init_rwsem(&efx->filter_sem);
+	down_write(&efx->filter_sem);
 	rc = efx->type->filter_table_probe(efx);
 	if (rc)
-		return rc;
+		goto out_unlock;
 
 #ifdef CONFIG_RFS_ACCEL
 	if (efx->type->offload_features & NETIF_F_NTUPLE) {
@@ -1662,12 +1698,14 @@ static int efx_probe_filters(struct efx_nic *efx)
 					   GFP_KERNEL);
 		if (!efx->rps_flow_id) {
 			efx->type->filter_table_remove(efx);
-			return -ENOMEM;
+			rc = -ENOMEM;
+			goto out_unlock;
 		}
 	}
 #endif
-
-	return 0;
+out_unlock:
+	up_write(&efx->filter_sem);
+	return rc;
 }
 
 static void efx_remove_filters(struct efx_nic *efx)
@@ -1675,12 +1713,16 @@ static void efx_remove_filters(struct efx_nic *efx)
 #ifdef CONFIG_RFS_ACCEL
 	kfree(efx->rps_flow_id);
 #endif
+	down_write(&efx->filter_sem);
 	efx->type->filter_table_remove(efx);
+	up_write(&efx->filter_sem);
 }
 
 static void efx_restore_filters(struct efx_nic *efx)
 {
+	down_read(&efx->filter_sem);
 	efx->type->filter_table_restore(efx);
+	up_read(&efx->filter_sem);
 }
 
 /**************************************************************************
@@ -1712,21 +1754,33 @@ static int efx_probe_all(struct efx_nic *efx)
 	}
 	efx->rxq_entries = efx->txq_entries = EFX_DEFAULT_DMAQ_SIZE;
 
+#ifdef CONFIG_SFC_SRIOV
+	rc = efx->type->vswitching_probe(efx);
+	if (rc) /* not fatal; the PF will still work fine */
+		netif_warn(efx, probe, efx->net_dev,
+			   "failed to setup vswitching rc=%d;"
+			   " VFs may not function\n", rc);
+#endif
+
 	rc = efx_probe_filters(efx);
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "failed to create filter tables\n");
-		goto fail3;
+		goto fail4;
 	}
 
 	rc = efx_probe_channels(efx);
 	if (rc)
-		goto fail4;
+		goto fail5;
 
 	return 0;
 
- fail4:
+ fail5:
 	efx_remove_filters(efx);
+ fail4:
+#ifdef CONFIG_SFC_SRIOV
+	efx->type->vswitching_remove(efx);
+#endif
  fail3:
 	efx_remove_port(efx);
  fail2:
@@ -1816,6 +1870,9 @@ static void efx_remove_all(struct efx_nic *efx)
 {
 	efx_remove_channels(efx);
 	efx_remove_filters(efx);
+#ifdef CONFIG_SFC_SRIOV
+	efx->type->vswitching_remove(efx);
+#endif
 	efx_remove_port(efx);
 	efx_remove_nic(efx);
 }
@@ -2059,7 +2116,7 @@ static int efx_busy_poll(struct napi_struct *napi)
  *************************************************************************/
 
 /* Context: process, rtnl_lock() held. */
-static int efx_net_open(struct net_device *net_dev)
+int efx_net_open(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	int rc;
@@ -2088,7 +2145,7 @@ static int efx_net_open(struct net_device *net_dev)
  * Note that the kernel will ignore our return code; this method
  * should really be a void.
  */
-static int efx_net_stop(struct net_device *net_dev)
+int efx_net_stop(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
@@ -2146,7 +2203,7 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 
 	mutex_lock(&efx->mac_lock);
 	net_dev->mtu = new_mtu;
-	efx->type->reconfigure_mac(efx);
+	efx_mac_reconfigure(efx);
 	mutex_unlock(&efx->mac_lock);
 
 	efx_start_all(efx);
@@ -2159,6 +2216,8 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct sockaddr *addr = data;
 	u8 *new_addr = addr->sa_data;
+	u8 old_addr[6];
+	int rc;
 
 	if (!is_valid_ether_addr(new_addr)) {
 		netif_err(efx, drv, efx->net_dev,
@@ -2167,12 +2226,20 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
 		return -EADDRNOTAVAIL;
 	}
 
+	/* save old address */
+	ether_addr_copy(old_addr, net_dev->dev_addr);
 	ether_addr_copy(net_dev->dev_addr, new_addr);
-	efx->type->sriov_mac_address_changed(efx);
+	if (efx->type->set_mac_address) {
+		rc = efx->type->set_mac_address(efx);
+		if (rc) {
+			ether_addr_copy(net_dev->dev_addr, old_addr);
+			return rc;
+		}
+	}
 
 	/* Reconfigure the MAC */
 	mutex_lock(&efx->mac_lock);
-	efx->type->reconfigure_mac(efx);
+	efx_mac_reconfigure(efx);
 	mutex_unlock(&efx->mac_lock);
 
 	return 0;
@@ -2199,7 +2266,7 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 	return 0;
 }
 
-static const struct net_device_ops efx_farch_netdev_ops = {
+static const struct net_device_ops efx_netdev_ops = {
 	.ndo_open		= efx_net_open,
 	.ndo_stop		= efx_net_stop,
 	.ndo_get_stats64	= efx_net_stats,
@@ -2212,10 +2279,12 @@ static const struct net_device_ops efx_farch_netdev_ops = {
 	.ndo_set_rx_mode	= efx_set_rx_mode,
 	.ndo_set_features	= efx_set_features,
 #ifdef CONFIG_SFC_SRIOV
-	.ndo_set_vf_mac		= efx_siena_sriov_set_vf_mac,
-	.ndo_set_vf_vlan	= efx_siena_sriov_set_vf_vlan,
-	.ndo_set_vf_spoofchk	= efx_siena_sriov_set_vf_spoofchk,
-	.ndo_get_vf_config	= efx_siena_sriov_get_vf_config,
+	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
+	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
+	.ndo_set_vf_spoofchk	= efx_sriov_set_vf_spoofchk,
+	.ndo_get_vf_config	= efx_sriov_get_vf_config,
+	.ndo_set_vf_link_state  = efx_sriov_set_vf_link_state,
+	.ndo_get_phys_port_id   = efx_sriov_get_phys_port_id,
 #endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = efx_netpoll,
@@ -2229,29 +2298,6 @@ static const struct net_device_ops efx_farch_netdev_ops = {
 #endif
 };
 
-static const struct net_device_ops efx_ef10_netdev_ops = {
-	.ndo_open		= efx_net_open,
-	.ndo_stop		= efx_net_stop,
-	.ndo_get_stats64	= efx_net_stats,
-	.ndo_tx_timeout		= efx_watchdog,
-	.ndo_start_xmit		= efx_hard_start_xmit,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= efx_ioctl,
-	.ndo_change_mtu		= efx_change_mtu,
-	.ndo_set_mac_address	= efx_set_mac_address,
-	.ndo_set_rx_mode	= efx_set_rx_mode,
-	.ndo_set_features	= efx_set_features,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= efx_netpoll,
-#endif
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	.ndo_busy_poll		= efx_busy_poll,
-#endif
-#ifdef CONFIG_RFS_ACCEL
-	.ndo_rx_flow_steer	= efx_filter_rfs,
-#endif
-};
-
 static void efx_update_name(struct efx_nic *efx)
 {
 	strcpy(efx->name, efx->net_dev->name);
@@ -2264,8 +2310,7 @@ static int efx_netdev_event(struct notifier_block *this,
 {
 	struct net_device *net_dev = netdev_notifier_info_to_dev(ptr);
 
-	if ((net_dev->netdev_ops == &efx_farch_netdev_ops ||
-	     net_dev->netdev_ops == &efx_ef10_netdev_ops) &&
+	if ((net_dev->netdev_ops == &efx_netdev_ops) &&
 	    event == NETDEV_CHANGENAME)
 		efx_update_name(netdev_priv(net_dev));
 
@@ -2284,6 +2329,28 @@ show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
 }
 static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled);
+}
+static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+	bool enable = count > 0 && *buf != '0';
+
+	mcdi->logging_enabled = enable;
+	return count;
+}
+static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log);
+#endif
+
 static int efx_register_netdev(struct efx_nic *efx)
 {
 	struct net_device *net_dev = efx->net_dev;
@@ -2292,12 +2359,9 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 	net_dev->watchdog_timeo = 5 * HZ;
 	net_dev->irq = efx->pci_dev->irq;
-	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
-		net_dev->netdev_ops = &efx_ef10_netdev_ops;
+	net_dev->netdev_ops = &efx_netdev_ops;
+	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
 		net_dev->priv_flags |= IFF_UNICAST_FLT;
-	} else {
-		net_dev->netdev_ops = &efx_farch_netdev_ops;
-	}
 	net_dev->ethtool_ops = &efx_ethtool_ops;
 	net_dev->gso_max_segs = EFX_TSO_MAX_SEGS;
 
@@ -2344,9 +2408,21 @@ static int efx_register_netdev(struct efx_nic *efx)
 			  "failed to init net dev attributes\n");
 		goto fail_registered;
 	}
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+	if (rc) {
+		netif_err(efx, drv, efx->net_dev,
+			  "failed to init net dev attributes\n");
+		goto fail_attr_mcdi_logging;
+	}
+#endif
 
 	return 0;
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+fail_attr_mcdi_logging:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+#endif
 fail_registered:
 	rtnl_lock();
 	efx_dissociate(efx);
@@ -2365,13 +2441,14 @@ static void efx_unregister_netdev(struct efx_nic *efx)
 
 	BUG_ON(netdev_priv(efx->net_dev) != efx);
 
-	strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
-	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
-
-	rtnl_lock();
-	unregister_netdevice(efx->net_dev);
-	efx->state = STATE_UNINIT;
-	rtnl_unlock();
+	if (efx_dev_registered(efx)) {
+		strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
+#ifdef CONFIG_SFC_MCDI_LOGGING
+		device_remove_file(&efx->pci_dev->dev, &dev_attr_mcdi_logging);
+#endif
+		device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+		unregister_netdev(efx->net_dev);
+	}
 }
 
 /**************************************************************************
@@ -2393,7 +2470,8 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
 	efx_disable_interrupts(efx);
 
 	mutex_lock(&efx->mac_lock);
-	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE)
+	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
+	    method != RESET_TYPE_DATAPATH)
 		efx->phy_op->fini(efx);
 	efx->type->fini(efx);
 }
@@ -2422,11 +2500,13 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 	if (!ok)
 		goto fail;
 
-	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE) {
+	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
+	    method != RESET_TYPE_DATAPATH) {
 		rc = efx->phy_op->init(efx);
 		if (rc)
 			goto fail;
-		if (efx->phy_op->reconfigure(efx))
+		rc = efx->phy_op->reconfigure(efx);
+		if (rc && rc != -EPERM)
 			netif_err(efx, drv, efx->net_dev,
 				  "could not restore PHY settings\n");
 	}
@@ -2434,8 +2514,20 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 	rc = efx_enable_interrupts(efx);
 	if (rc)
 		goto fail;
+
+#ifdef CONFIG_SFC_SRIOV
+	rc = efx->type->vswitching_restore(efx);
+	if (rc) /* not fatal; the PF will still work fine */
+		netif_warn(efx, probe, efx->net_dev,
+			   "failed to restore vswitching rc=%d;"
+			   " VFs may not function\n", rc);
+#endif
+
+	down_read(&efx->filter_sem);
 	efx_restore_filters(efx);
-	efx->type->sriov_reset(efx);
+	up_read(&efx->filter_sem);
+	if (efx->type->sriov_reset)
+		efx->type->sriov_reset(efx);
 
 	mutex_unlock(&efx->mac_lock);
 
@@ -2605,6 +2697,7 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
 	case RESET_TYPE_WORLD:
 	case RESET_TYPE_DISABLE:
 	case RESET_TYPE_RECOVER_OR_DISABLE:
+	case RESET_TYPE_DATAPATH:
 	case RESET_TYPE_MC_BIST:
 	case RESET_TYPE_MCDI_TIMEOUT:
 		method = type;
@@ -2655,6 +2748,8 @@ static const struct pci_device_id efx_pci_table[] = {
 	 .driver_data = (unsigned long) &siena_a0_nic_type},
 	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0903),  /* SFC9120 PF */
 	 .driver_data = (unsigned long) &efx_hunt_a0_nic_type},
+	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1903),  /* SFC9120 VF */
+	 .driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
 	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0923),  /* SFC9140 PF */
 	 .driver_data = (unsigned long) &efx_hunt_a0_nic_type},
 	{0}			/* end of list */
@@ -2809,7 +2904,8 @@ static void efx_pci_remove_main(struct efx_nic *efx)
 }
 
 /* Final NIC shutdown
- * This is called only at module unload (or hotplug removal).
+ * This is called only at module unload (or hotplug removal).  A PF can call
+ * this on its VFs to ensure they are unbound first.
  */
 static void efx_pci_remove(struct pci_dev *pci_dev)
 {
@@ -2824,9 +2920,12 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 	efx_dissociate(efx);
 	dev_close(efx->net_dev);
 	efx_disable_interrupts(efx);
+	efx->state = STATE_UNINIT;
 	rtnl_unlock();
 
-	efx->type->sriov_fini(efx);
+	if (efx->type->sriov_fini)
+		efx->type->sriov_fini(efx);
+
 	efx_unregister_netdev(efx);
 
 	efx_mtd_remove(efx);
@@ -3008,7 +3107,8 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	netif_info(efx, probe, efx->net_dev,
 		   "Solarflare NIC detected\n");
 
-	efx_probe_vpd_strings(efx);
+	if (!efx->type->is_vf)
+		efx_probe_vpd_strings(efx);
 
 	/* Set up basic I/O (BAR mappings etc) */
 	rc = efx_init_io(efx);
@@ -3023,10 +3123,12 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto fail4;
 
-	rc = efx->type->sriov_init(efx);
-	if (rc)
-		netif_err(efx, probe, efx->net_dev,
-			  "SR-IOV can't be enabled rc %d\n", rc);
+	if (efx->type->sriov_init) {
+		rc = efx->type->sriov_init(efx);
+		if (rc)
+			netif_err(efx, probe, efx->net_dev,
+				  "SR-IOV can't be enabled rc %d\n", rc);
+	}
 
 	netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");
 
@@ -3058,6 +3160,26 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	return rc;
 }
 
+/* efx_pci_sriov_configure returns the actual number of Virtual Functions
+ * enabled on success
+ */
+#ifdef CONFIG_SFC_SRIOV
+static int efx_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
+{
+	int rc;
+	struct efx_nic *efx = pci_get_drvdata(dev);
+
+	if (efx->type->sriov_configure) {
+		rc = efx->type->sriov_configure(efx, num_vfs);
+		if (rc)
+			return rc;
+		else
+			return num_vfs;
+	} else
+		return -EOPNOTSUPP;
+}
+#endif
+
 static int efx_pm_freeze(struct device *dev)
 {
 	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
@@ -3280,6 +3402,9 @@ static struct pci_driver efx_pci_driver = {
 	.remove		= efx_pci_remove,
 	.driver.pm	= &efx_pm_ops,
 	.err_handler	= &efx_err_handlers,
+#ifdef CONFIG_SFC_SRIOV
+	.sriov_configure = efx_pci_sriov_configure,
+#endif
 };
 
 /**************************************************************************
@@ -3302,9 +3427,11 @@ static int __init efx_init_module(void)
 	if (rc)
 		goto err_notifier;
 
+#ifdef CONFIG_SFC_SRIOV
 	rc = efx_init_sriov();
 	if (rc)
 		goto err_sriov;
+#endif
 
 	reset_workqueue = create_singlethread_workqueue("sfc_reset");
 	if (!reset_workqueue) {
@@ -3321,8 +3448,10 @@ static int __init efx_init_module(void)
  err_pci:
 	destroy_workqueue(reset_workqueue);
  err_reset:
+#ifdef CONFIG_SFC_SRIOV
 	efx_fini_sriov();
  err_sriov:
+#endif
 	unregister_netdevice_notifier(&efx_netdev_notifier);
  err_notifier:
 	return rc;
@@ -3334,7 +3463,9 @@ static void __exit efx_exit_module(void)
 
 	pci_unregister_driver(&efx_pci_driver);
 	destroy_workqueue(reset_workqueue);
+#ifdef CONFIG_SFC_SRIOV
 	efx_fini_sriov();
+#endif
 	unregister_netdevice_notifier(&efx_netdev_notifier);
 
 }
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 2587c582a821..acb1e0718485 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -15,7 +15,12 @@
 #include "filter.h"
 
 /* All controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
+/* All VFs use BAR 0/1 for memory */
 #define EFX_MEM_BAR 2
+#define EFX_MEM_VF_BAR 0
+
+int efx_net_open(struct net_device *net_dev);
+int efx_net_stop(struct net_device *net_dev);
 
 /* TX */
 int efx_probe_tx_queue(struct efx_tx_queue *tx_queue);
@@ -32,6 +37,7 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx);
 extern unsigned int efx_piobuf_size;
 
 /* RX */
+void efx_set_default_rx_indir_table(struct efx_nic *efx);
 void efx_rx_config_page_split(struct efx_nic *efx);
 int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
 void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
@@ -71,6 +77,8 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
 
 /* Filters */
 
+void efx_mac_reconfigure(struct efx_nic *efx);
+
 /**
  * efx_filter_insert_filter - add or replace a filter
  * @efx: NIC in which to insert the filter
@@ -220,6 +228,13 @@ static inline void efx_mtd_rename(struct efx_nic *efx) {}
 static inline void efx_mtd_remove(struct efx_nic *efx) {}
 #endif
 
+#ifdef CONFIG_SFC_SRIOV
+static inline unsigned int efx_vf_size(struct efx_nic *efx)
+{
+	return 1 << efx->vi_scale;
+}
+#endif
+
 static inline void efx_schedule_channel(struct efx_channel *channel)
 {
 	netif_vdbg(channel->efx, intr, channel->efx->net_dev,
diff --git a/drivers/net/ethernet/sfc/enum.h b/drivers/net/ethernet/sfc/enum.h
index d1dbb5fb31bb..c94f56271dd4 100644
--- a/drivers/net/ethernet/sfc/enum.h
+++ b/drivers/net/ethernet/sfc/enum.h
@@ -143,6 +143,7 @@ enum efx_loopback_mode {
  * @RESET_TYPE_WORLD: Reset as much as possible
  * @RESET_TYPE_RECOVER_OR_DISABLE: Try to recover. Apply RESET_TYPE_DISABLE if
  * unsuccessful.
+ * @RESET_TYPE_DATAPATH: Reset datapath only.
  * @RESET_TYPE_MC_BIST: MC entering BIST mode.
  * @RESET_TYPE_DISABLE: Reset datapath, MAC and PHY; leave NIC disabled
  * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog
@@ -159,6 +160,7 @@ enum reset_type {
 	RESET_TYPE_ALL,
 	RESET_TYPE_WORLD,
 	RESET_TYPE_RECOVER_OR_DISABLE,
+	RESET_TYPE_DATAPATH,
 	RESET_TYPE_MC_BIST,
 	RESET_TYPE_DISABLE,
 	RESET_TYPE_MAX_METHOD,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 4835bc0d0de8..034797661f96 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -734,7 +734,7 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
 	/* Reconfigure the MAC. The PHY *may* generate a link state change event
 	 * if the user just changed the advertised capabilities, but there's no
 	 * harm doing this twice */
-	efx->type->reconfigure_mac(efx);
+	efx_mac_reconfigure(efx);
 
 out:
 	mutex_unlock(&efx->mac_lock);
@@ -1109,9 +1109,8 @@ static int efx_ethtool_set_rxfh(struct net_device *net_dev, const u32 *indir,
 		return -EOPNOTSUPP;
 	if (!indir)
 		return 0;
-	memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table));
-	efx->type->rx_push_rss_config(efx);
-	return 0;
+
+	return efx->type->rx_push_rss_config(efx, true, indir);
 }
 
 static int efx_ethtool_get_ts_info(struct net_device *net_dev,
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index f166c8ef38a3..80e69af21642 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -477,16 +477,29 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
  *
  **************************************************************************
  */
+static int dummy_rx_push_rss_config(struct efx_nic *efx, bool user,
+				    const u32 *rx_indir_table)
+{
+	(void) efx;
+	(void) user;
+	(void) rx_indir_table;
+	return -ENOSYS;
+}
 
-static void falcon_b0_rx_push_rss_config(struct efx_nic *efx)
+static int falcon_b0_rx_push_rss_config(struct efx_nic *efx, bool user,
+					const u32 *rx_indir_table)
 {
 	efx_oword_t temp;
 
+	(void) user;
 	/* Set hash key for IPv4 */
 	memcpy(&temp, efx->rx_hash_key, sizeof(temp));
 	efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
 
+	memcpy(efx->rx_indir_table, rx_indir_table,
+	       sizeof(efx->rx_indir_table));
 	efx_farch_rx_push_indir_table(efx);
+	return 0;
 }
 
 /**************************************************************************
@@ -2507,7 +2520,7 @@ static int falcon_init_nic(struct efx_nic *efx)
 	falcon_init_rx_cfg(efx);
 
 	if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
-		falcon_b0_rx_push_rss_config(efx);
+		falcon_b0_rx_push_rss_config(efx, false, efx->rx_indir_table);
 
 		/* Set destination of both TX and RX Flush events */
 		EFX_POPULATE_OWORD_1(temp, FRF_BZ_FLS_EVQ_ID, 0);
@@ -2687,6 +2700,8 @@ static int falcon_set_wol(struct efx_nic *efx, u32 type)
  */
 
 const struct efx_nic_type falcon_a1_nic_type = {
+	.is_vf = false,
+	.mem_bar = EFX_MEM_BAR,
 	.mem_map_size = falcon_a1_mem_map_size,
 	.probe = falcon_probe_nic,
 	.remove = falcon_remove_nic,
@@ -2729,7 +2744,7 @@ const struct efx_nic_type falcon_a1_nic_type = {
 	.tx_init = efx_farch_tx_init,
 	.tx_remove = efx_farch_tx_remove,
 	.tx_write = efx_farch_tx_write,
-	.rx_push_rss_config = efx_port_dummy_op_void,
+	.rx_push_rss_config = dummy_rx_push_rss_config,
 	.rx_probe = efx_farch_rx_probe,
 	.rx_init = efx_farch_rx_init,
 	.rx_remove = efx_farch_rx_remove,
@@ -2766,11 +2781,6 @@ const struct efx_nic_type falcon_a1_nic_type = {
 	.mtd_write = falcon_mtd_write,
 	.mtd_sync = falcon_mtd_sync,
 #endif
-	.sriov_init = efx_falcon_sriov_init,
-	.sriov_fini = efx_falcon_sriov_fini,
-	.sriov_mac_address_changed = efx_falcon_sriov_mac_address_changed,
-	.sriov_wanted = efx_falcon_sriov_wanted,
-	.sriov_reset = efx_falcon_sriov_reset,
 
 	.revision = EFX_REV_FALCON_A1,
 	.txd_ptr_tbl_base = FR_AA_TX_DESC_PTR_TBL_KER,
@@ -2788,6 +2798,8 @@ const struct efx_nic_type falcon_a1_nic_type = {
 };
 
 const struct efx_nic_type falcon_b0_nic_type = {
+	.is_vf = false,
+	.mem_bar = EFX_MEM_BAR,
 	.mem_map_size = falcon_b0_mem_map_size,
 	.probe = falcon_probe_nic,
 	.remove = falcon_remove_nic,
@@ -2867,11 +2879,6 @@ const struct efx_nic_type falcon_b0_nic_type = {
 	.mtd_write = falcon_mtd_write,
 	.mtd_sync = falcon_mtd_sync,
 #endif
-	.sriov_init = efx_falcon_sriov_init,
-	.sriov_fini = efx_falcon_sriov_fini,
-	.sriov_mac_address_changed = efx_falcon_sriov_mac_address_changed,
-	.sriov_wanted = efx_falcon_sriov_wanted,
-	.sriov_reset = efx_falcon_sriov_reset,
 
 	.revision = EFX_REV_FALCON_B0,
 	.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index bb89e96a125e..f08266f0eca2 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -20,6 +20,8 @@
 #include "efx.h"
 #include "nic.h"
 #include "farch_regs.h"
+#include "sriov.h"
+#include "siena_sriov.h"
 #include "io.h"
 #include "workarounds.h"
 
@@ -1198,13 +1200,17 @@ efx_farch_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
 		netif_vdbg(efx, hw, efx->net_dev, "channel %d TXQ %d flushed\n",
 			   channel->channel, ev_sub_data);
 		efx_farch_handle_tx_flush_done(efx, event);
+#ifdef CONFIG_SFC_SRIOV
 		efx_siena_sriov_tx_flush_done(efx, event);
+#endif
 		break;
 	case FSE_AZ_RX_DESCQ_FLS_DONE_EV:
 		netif_vdbg(efx, hw, efx->net_dev, "channel %d RXQ %d flushed\n",
 			   channel->channel, ev_sub_data);
 		efx_farch_handle_rx_flush_done(efx, event);
+#ifdef CONFIG_SFC_SRIOV
 		efx_siena_sriov_rx_flush_done(efx, event);
+#endif
 		break;
 	case FSE_AZ_EVQ_INIT_DONE_EV:
 		netif_dbg(efx, hw, efx->net_dev,
@@ -1242,8 +1248,11 @@ efx_farch_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
 				  " RX Q %d is disabled.\n", ev_sub_data,
 				  ev_sub_data);
 			efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
-		} else
+		}
+#ifdef CONFIG_SFC_SRIOV
+		else
 			efx_siena_sriov_desc_fetch_err(efx, ev_sub_data);
+#endif
 		break;
 	case FSE_BZ_TX_DSC_ERROR_EV:
 		if (ev_sub_data < EFX_VI_BASE) {
@@ -1252,8 +1261,11 @@ efx_farch_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
 				  " TX Q %d is disabled.\n", ev_sub_data,
 				  ev_sub_data);
 			efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
-		} else
+		}
+#ifdef CONFIG_SFC_SRIOV
+		else
 			efx_siena_sriov_desc_fetch_err(efx, ev_sub_data);
+#endif
 		break;
 	default:
 		netif_vdbg(efx, hw, efx->net_dev,
@@ -1317,9 +1329,11 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget)
 		case FSE_AZ_EV_CODE_DRIVER_EV:
 			efx_farch_handle_driver_event(channel, &event);
 			break;
+#ifdef CONFIG_SFC_SRIOV
 		case FSE_CZ_EV_CODE_USER_EV:
 			efx_siena_sriov_event(channel, &event);
 			break;
+#endif
 		case FSE_CZ_EV_CODE_MCDI_EV:
 			efx_mcdi_process_event(channel, &event);
 			break;
@@ -1685,28 +1699,32 @@ void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
 	vi_count = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES);
 
 #ifdef CONFIG_SFC_SRIOV
-	if (efx->type->sriov_wanted(efx)) {
-		unsigned vi_dc_entries, buftbl_free, entries_per_vf, vf_limit;
-
-		nic_data->vf_buftbl_base = buftbl_min;
-
-		vi_dc_entries = RX_DC_ENTRIES + TX_DC_ENTRIES;
-		vi_count = max(vi_count, EFX_VI_BASE);
-		buftbl_free = (sram_lim_qw - buftbl_min -
-			       vi_count * vi_dc_entries);
-
-		entries_per_vf = ((vi_dc_entries + EFX_VF_BUFTBL_PER_VI) *
-				  efx_vf_size(efx));
-		vf_limit = min(buftbl_free / entries_per_vf,
-			       (1024U - EFX_VI_BASE) >> efx->vi_scale);
-
-		if (efx->vf_count > vf_limit) {
-			netif_err(efx, probe, efx->net_dev,
-				  "Reducing VF count from from %d to %d\n",
-				  efx->vf_count, vf_limit);
-			efx->vf_count = vf_limit;
+	if (efx->type->sriov_wanted) {
+		if (efx->type->sriov_wanted(efx)) {
+			unsigned vi_dc_entries, buftbl_free;
+			unsigned entries_per_vf, vf_limit;
+
+			nic_data->vf_buftbl_base = buftbl_min;
+
+			vi_dc_entries = RX_DC_ENTRIES + TX_DC_ENTRIES;
+			vi_count = max(vi_count, EFX_VI_BASE);
+			buftbl_free = (sram_lim_qw - buftbl_min -
+				       vi_count * vi_dc_entries);
+
+			entries_per_vf = ((vi_dc_entries +
+					   EFX_VF_BUFTBL_PER_VI) *
+					  efx_vf_size(efx));
+			vf_limit = min(buftbl_free / entries_per_vf,
+				       (1024U - EFX_VI_BASE) >> efx->vi_scale);
+
+			if (efx->vf_count > vf_limit) {
+				netif_err(efx, probe, efx->net_dev,
+					  "Reducing VF count from from %d to %d\n",
+					  efx->vf_count, vf_limit);
+				efx->vf_count = vf_limit;
+			}
+			vi_count += efx->vf_count * efx_vf_size(efx);
 		}
-		vi_count += efx->vf_count * efx_vf_size(efx);
 	}
 #endif
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index d37928f01949..81640f8bb811 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/moduleparam.h>
 #include <asm/cmpxchg.h>
 #include "net_driver.h"
 #include "nic.h"
@@ -54,18 +55,32 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 static bool efx_mcdi_poll_once(struct efx_nic *efx);
 static void efx_mcdi_abandon(struct efx_nic *efx);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+static bool mcdi_logging_default;
+module_param(mcdi_logging_default, bool, 0644);
+MODULE_PARM_DESC(mcdi_logging_default,
+		 "Enable MCDI logging on newly-probed functions");
+#endif
+
 int efx_mcdi_init(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi;
 	bool already_attached;
-	int rc;
+	int rc = -ENOMEM;
 
 	efx->mcdi = kzalloc(sizeof(*efx->mcdi), GFP_KERNEL);
 	if (!efx->mcdi)
-		return -ENOMEM;
+		goto fail;
 
 	mcdi = efx_mcdi(efx);
 	mcdi->efx = efx;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	/* consuming code assumes buffer is page-sized */
+	mcdi->logging_buffer = (char *)__get_free_page(GFP_KERNEL);
+	if (!mcdi->logging_buffer)
+		goto fail1;
+	mcdi->logging_enabled = mcdi_logging_default;
+#endif
 	init_waitqueue_head(&mcdi->wq);
 	spin_lock_init(&mcdi->iface_lock);
 	mcdi->state = MCDI_STATE_QUIESCENT;
@@ -81,7 +96,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	/* Recover from a failed assertion before probing */
 	rc = efx_mcdi_handle_assertion(efx);
 	if (rc)
-		return rc;
+		goto fail2;
 
 	/* Let the MC (and BMC, if this is a LOM) know that the driver
 	 * is loaded. We should do this before we reset the NIC.
@@ -90,7 +105,7 @@ int efx_mcdi_init(struct efx_nic *efx)
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "Unable to register driver with MCPU\n");
-		return rc;
+		goto fail2;
 	}
 	if (already_attached)
 		/* Not a fatal error */
@@ -102,6 +117,15 @@ int efx_mcdi_init(struct efx_nic *efx)
 		efx->primary = efx;
 
 	return 0;
+fail2:
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)mcdi->logging_buffer);
+fail1:
+#endif
+	kfree(efx->mcdi);
+	efx->mcdi = NULL;
+fail:
+	return rc;
 }
 
 void efx_mcdi_fini(struct efx_nic *efx)
@@ -114,6 +138,10 @@ void efx_mcdi_fini(struct efx_nic *efx)
 	/* Relinquish the device (back to the BMC, if this is a LOM) */
 	efx_mcdi_drv_attach(efx, false, NULL);
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	free_page((unsigned long)efx->mcdi->iface.logging_buffer);
+#endif
+
 	kfree(efx->mcdi);
 }
 
@@ -121,6 +149,9 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 				  const efx_dword_t *inbuf, size_t inlen)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr[2];
 	size_t hdr_len;
 	u32 xflags, seqno;
@@ -165,6 +196,31 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
 		hdr_len = 8;
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		int bytes = 0;
+		int i;
+		/* Lengths should always be a whole number of dwords, so scream
+		 * if they're not.
+		 */
+		WARN_ON_ONCE(hdr_len % 4);
+		WARN_ON_ONCE(inlen % 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr[i].u32[0]));
+
+		for (i = 0; i < inlen / 4 && bytes < PAGE_SIZE; i++)
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(inbuf[i].u32[0]));
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC REQ:%s\n", buf);
+	}
+#endif
+
 	efx->type->mcdi_request(efx, hdr, hdr_len, inbuf, inlen);
 
 	mcdi->new_epoch = false;
@@ -206,6 +262,9 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
 	unsigned int respseq, respcmd, error;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *buf = mcdi->logging_buffer; /* page-sized */
+#endif
 	efx_dword_t hdr;
 
 	efx->type->mcdi_read_response(efx, &hdr, 0, 4);
@@ -223,6 +282,39 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx)
 			EFX_DWORD_FIELD(hdr, MC_CMD_V2_EXTN_IN_ACTUAL_LEN);
 	}
 
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	if (mcdi->logging_enabled && !WARN_ON_ONCE(!buf)) {
+		size_t hdr_len, data_len;
+		int bytes = 0;
+		int i;
+
+		WARN_ON_ONCE(mcdi->resp_hdr_len % 4);
+		hdr_len = mcdi->resp_hdr_len / 4;
+		/* MCDI_DECLARE_BUF ensures that underlying buffer is padded
+		 * to dword size, and the MCDI buffer is always dword size
+		 */
+		data_len = DIV_ROUND_UP(mcdi->resp_data_len, 4);
+
+		/* We own the logging buffer, as only one MCDI can be in
+		 * progress on a NIC at any one time.  So no need for locking.
+		 */
+		for (i = 0; i < hdr_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr, (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		for (i = 0; i < data_len && bytes < PAGE_SIZE; i++) {
+			efx->type->mcdi_read_response(efx, &hdr,
+					mcdi->resp_hdr_len + (i * 4), 4);
+			bytes += snprintf(buf + bytes, PAGE_SIZE - bytes,
+					  " %08x", le32_to_cpu(hdr.u32[0]));
+		}
+
+		netif_info(efx, hw, efx->net_dev, "MCDI RPC RESP:%s\n", buf);
+	}
+#endif
+
 	if (error && mcdi->resp_data_len == 0) {
 		netif_err(efx, hw, efx->net_dev, "MC rebooted\n");
 		mcdi->resprc = -EIO;
@@ -406,7 +498,7 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
 	struct efx_mcdi_async_param *async;
 	size_t hdr_len, data_len, err_len;
 	efx_dword_t *outbuf;
-	MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+	MCDI_DECLARE_BUF_ERR(errbuf);
 	int rc;
 
 	if (cmpxchg(&mcdi->state,
@@ -534,7 +626,7 @@ static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
 				size_t *outlen_actual, bool quiet)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+	MCDI_DECLARE_BUF_ERR(errbuf);
 	int rc;
 
 	if (mcdi->mode == MCDI_MODE_POLL)
@@ -1035,7 +1127,9 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 		/* MAC stats are gather lazily.  We can ignore this. */
 		break;
 	case MCDI_EVENT_CODE_FLR:
-		efx_siena_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));
+		if (efx->type->sriov_flr)
+			efx->type->sriov_flr(efx,
+					     MCDI_EVENT_FIELD(*event, FLR_VF));
 		break;
 	case MCDI_EVENT_CODE_PTP_RX:
 	case MCDI_EVENT_CODE_PTP_FAULT:
@@ -1081,9 +1175,7 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 
 void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
 {
-	MCDI_DECLARE_BUF(outbuf,
-			 max(MC_CMD_GET_VERSION_OUT_LEN,
-			     MC_CMD_GET_CAPABILITIES_OUT_LEN));
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_VERSION_OUT_LEN);
 	size_t outlength;
 	const __le16 *ver_words;
 	size_t offset;
@@ -1108,19 +1200,11 @@ void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
 	 * single version.  Report which variants are running.
 	 */
 	if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
-		BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0);
-		rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0,
-				  outbuf, sizeof(outbuf), &outlength);
-		if (rc || outlength < MC_CMD_GET_CAPABILITIES_OUT_LEN)
-			offset += snprintf(
-				buf + offset, len - offset, " rx? tx?");
-		else
-			offset += snprintf(
-				buf + offset, len - offset, " rx%x tx%x",
-				MCDI_WORD(outbuf,
-					  GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID),
-				MCDI_WORD(outbuf,
-					  GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID));
+		struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+		offset += snprintf(buf + offset, len - offset, " rx%x tx%x",
+				   nic_data->rx_dpcpu_fw_id,
+				   nic_data->tx_dpcpu_fw_id);
 
 		/* It's theoretically possible for the string to exceed 31
 		 * characters, though in practice the first three version
@@ -1150,10 +1234,26 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 	MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_UPDATE, 1);
 	MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_FIRMWARE_ID, MC_CMD_FW_LOW_LATENCY);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf),
+				outbuf, sizeof(outbuf), &outlen);
+	/* If we're not the primary PF, trying to ATTACH with a FIRMWARE_ID
+	 * specified will fail with EPERM, and we have to tell the MC we don't
+	 * care what firmware we get.
+	 */
+	if (rc == -EPERM) {
+		netif_dbg(efx, probe, efx->net_dev,
+			  "efx_mcdi_drv_attach with fw-variant setting failed EPERM, trying without it\n");
+		MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_FIRMWARE_ID,
+			       MC_CMD_FW_DONT_CARE);
+		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_DRV_ATTACH, inbuf,
+					sizeof(inbuf), outbuf, sizeof(outbuf),
+					&outlen);
+	}
+	if (rc) {
+		efx_mcdi_display_error(efx, MC_CMD_DRV_ATTACH, sizeof(inbuf),
+				       outbuf, outlen, rc);
 		goto fail;
+	}
 	if (outlen < MC_CMD_DRV_ATTACH_OUT_LEN) {
 		rc = -EIO;
 		goto fail;
@@ -1178,16 +1278,6 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 	 * and are completely trusted by firmware.  Abort probing
 	 * if that's not true for this function.
 	 */
-	if (driver_operating &&
-	    (efx->mcdi->fn_flags &
-	     (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
-	      1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) !=
-	    (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
-	     1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) {
-		netif_err(efx, probe, efx->net_dev,
-			  "This driver version only supports one function per port\n");
-		return -ENODEV;
-	}
 
 	if (was_attached != NULL)
 		*was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE);
@@ -1385,10 +1475,13 @@ fail1:
 	return rc;
 }
 
+/* Returns 1 if an assertion was read, 0 if no assertion had fired,
+ * negative on error.
+ */
 static int efx_mcdi_read_assertion(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_ASSERTS_IN_LEN);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN);
 	unsigned int flags, index;
 	const char *reason;
 	size_t outlen;
@@ -1406,6 +1499,8 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
 		rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_ASSERTS,
 					inbuf, MC_CMD_GET_ASSERTS_IN_LEN,
 					outbuf, sizeof(outbuf), &outlen);
+		if (rc == -EPERM)
+			return 0;
 	} while ((rc == -EINTR || rc == -EIO) && retry-- > 0);
 
 	if (rc) {
@@ -1443,24 +1538,31 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
 			  MCDI_ARRAY_DWORD(outbuf, GET_ASSERTS_OUT_GP_REGS_OFFS,
 					   index));
 
-	return 0;
+	return 1;
 }
 
-static void efx_mcdi_exit_assertion(struct efx_nic *efx)
+static int efx_mcdi_exit_assertion(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_REBOOT_IN_LEN);
+	int rc;
 
 	/* If the MC is running debug firmware, it might now be
 	 * waiting for a debugger to attach, but we just want it to
 	 * reboot.  We set a flag that makes the command a no-op if it
-	 * has already done so.  We don't know what return code to
-	 * expect (0 or -EIO), so ignore it.
+	 * has already done so.
+	 * The MCDI will thus return either 0 or -EIO.
 	 */
 	BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0);
 	MCDI_SET_DWORD(inbuf, REBOOT_IN_FLAGS,
 		       MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION);
-	(void) efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
-			    NULL, 0, NULL);
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
+				NULL, 0, NULL);
+	if (rc == -EIO)
+		rc = 0;
+	if (rc)
+		efx_mcdi_display_error(efx, MC_CMD_REBOOT, MC_CMD_REBOOT_IN_LEN,
+				       NULL, 0, rc);
+	return rc;
 }
 
 int efx_mcdi_handle_assertion(struct efx_nic *efx)
@@ -1468,12 +1570,10 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx)
 	int rc;
 
 	rc = efx_mcdi_read_assertion(efx);
-	if (rc)
+	if (rc <= 0)
 		return rc;
 
-	efx_mcdi_exit_assertion(efx);
-
-	return 0;
+	return efx_mcdi_exit_assertion(efx);
 }
 
 void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode)
@@ -1550,7 +1650,9 @@ int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method)
 	if (rc)
 		return rc;
 
-	if (method == RESET_TYPE_WORLD)
+	if (method == RESET_TYPE_DATAPATH)
+		return 0;
+	else if (method == RESET_TYPE_WORLD)
 		return efx_mcdi_reset_mc(efx);
 	else
 		return efx_mcdi_reset_func(efx);
@@ -1688,6 +1790,36 @@ int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled)
 			    NULL, 0, NULL);
 }
 
+int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out,
+			     unsigned int *enabled_out)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_WORKAROUNDS_OUT_LEN);
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_WORKAROUNDS, NULL, 0,
+			  outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		goto fail;
+
+	if (outlen < MC_CMD_GET_WORKAROUNDS_OUT_LEN) {
+		rc = -EIO;
+		goto fail;
+	}
+
+	if (impl_out)
+		*impl_out = MCDI_DWORD(outbuf, GET_WORKAROUNDS_OUT_IMPLEMENTED);
+
+	if (enabled_out)
+		*enabled_out = MCDI_DWORD(outbuf, GET_WORKAROUNDS_OUT_ENABLED);
+
+	return 0;
+
+fail:
+	netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+	return rc;
+}
+
 #ifdef CONFIG_SFC_MTD
 
 #define EFX_MCDI_NVRAM_LEN_MAX 128
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 56465f7465a2..1838afe2da92 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -58,6 +58,8 @@ enum efx_mcdi_mode {
  *	enabled
  * @async_list: Queue of asynchronous requests
  * @async_timer: Timer for asynchronous request timeout
+ * @logging_buffer: buffer that may be used to build MCDI tracing messages
+ * @logging_enabled: whether to trace MCDI
  */
 struct efx_mcdi_iface {
 	struct efx_nic *efx;
@@ -74,6 +76,10 @@ struct efx_mcdi_iface {
 	spinlock_t async_lock;
 	struct list_head async_list;
 	struct timer_list async_timer;
+#ifdef CONFIG_SFC_MCDI_LOGGING
+	char *logging_buffer;
+	bool logging_enabled;
+#endif
 };
 
 struct efx_mcdi_mon {
@@ -176,10 +182,12 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
  * 32-bit-aligned.  Also, on Siena we must copy to the MC shared
  * memory strictly 32 bits at a time, so add any necessary padding.
  */
-#define MCDI_DECLARE_BUF(_name, _len)					\
+#define _MCDI_DECLARE_BUF(_name, _len)					\
 	efx_dword_t _name[DIV_ROUND_UP(_len, 4)]
-#define MCDI_DECLARE_BUF_OUT_OR_ERR(_name, _len)			\
-	MCDI_DECLARE_BUF(_name, max_t(size_t, _len, 8))
+#define MCDI_DECLARE_BUF(_name, _len)					\
+	_MCDI_DECLARE_BUF(_name, _len) = {{{0}}}
+#define MCDI_DECLARE_BUF_ERR(_name)					\
+	MCDI_DECLARE_BUF(_name, 8)
 #define _MCDI_PTR(_buf, _offset)					\
 	((u8 *)(_buf) + (_offset))
 #define MCDI_PTR(_buf, _field)						\
@@ -339,6 +347,8 @@ bool efx_mcdi_mac_check_fault(struct efx_nic *efx);
 enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason);
 int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method);
 int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled);
+int efx_mcdi_get_workarounds(struct efx_nic *efx, unsigned int *impl_out,
+			     unsigned int *enabled_out);
 
 #ifdef CONFIG_SFC_MCDI_MON
 int efx_mcdi_mon_probe(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index e028de10e1b7..45fca9fc66b7 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -638,6 +638,8 @@
  */
 #define MC_CMD_READ32 0x1
 
+#define MC_CMD_0x1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_READ32_IN msgrequest */
 #define    MC_CMD_READ32_IN_LEN 8
 #define       MC_CMD_READ32_IN_ADDR_OFST 0
@@ -659,6 +661,8 @@
  */
 #define MC_CMD_WRITE32 0x2
 
+#define MC_CMD_0x2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_WRITE32_IN msgrequest */
 #define    MC_CMD_WRITE32_IN_LENMIN 8
 #define    MC_CMD_WRITE32_IN_LENMAX 252
@@ -679,6 +683,8 @@
  */
 #define MC_CMD_COPYCODE 0x3
 
+#define MC_CMD_0x3_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_COPYCODE_IN msgrequest */
 #define    MC_CMD_COPYCODE_IN_LEN 16
 /* Source address */
@@ -717,6 +723,8 @@
  */
 #define MC_CMD_SET_FUNC 0x4
 
+#define MC_CMD_0x4_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_FUNC_IN msgrequest */
 #define    MC_CMD_SET_FUNC_IN_LEN 4
 /* Set function */
@@ -732,6 +740,8 @@
  */
 #define MC_CMD_GET_BOOT_STATUS 0x5
 
+#define MC_CMD_0x5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_BOOT_STATUS_IN msgrequest */
 #define    MC_CMD_GET_BOOT_STATUS_IN_LEN 0
 
@@ -758,6 +768,8 @@
  */
 #define MC_CMD_GET_ASSERTS 0x6
 
+#define MC_CMD_0x6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_ASSERTS_IN msgrequest */
 #define    MC_CMD_GET_ASSERTS_IN_LEN 4
 /* Set to clear assertion */
@@ -794,6 +806,8 @@
  */
 #define MC_CMD_LOG_CTRL 0x7
 
+#define MC_CMD_0x7_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_LOG_CTRL_IN msgrequest */
 #define    MC_CMD_LOG_CTRL_IN_LEN 8
 /* Log destination */
@@ -814,6 +828,8 @@
  */
 #define MC_CMD_GET_VERSION 0x8
 
+#define MC_CMD_0x8_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_VERSION_IN msgrequest */
 #define    MC_CMD_GET_VERSION_IN_LEN 0
 
@@ -870,6 +886,8 @@
  */
 #define MC_CMD_PTP 0xb
 
+#define MC_CMD_0xb_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_PTP_IN msgrequest */
 #define    MC_CMD_PTP_IN_LEN 1
 /* PTP operation code */
@@ -1404,6 +1422,8 @@
  */
 #define MC_CMD_CSR_READ32 0xc
 
+#define MC_CMD_0xc_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_CSR_READ32_IN msgrequest */
 #define    MC_CMD_CSR_READ32_IN_LEN 12
 /* Address */
@@ -1428,6 +1448,8 @@
  */
 #define MC_CMD_CSR_WRITE32 0xd
 
+#define MC_CMD_0xd_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_CSR_WRITE32_IN msgrequest */
 #define    MC_CMD_CSR_WRITE32_IN_LENMIN 12
 #define    MC_CMD_CSR_WRITE32_IN_LENMAX 252
@@ -1452,6 +1474,8 @@
  */
 #define MC_CMD_HP 0x54
 
+#define MC_CMD_0x54_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_HP_IN msgrequest */
 #define    MC_CMD_HP_IN_LEN 16
 /* HP OCSD sub-command. When address is not NULL, request activation of OCSD at
@@ -1493,6 +1517,8 @@
  */
 #define MC_CMD_STACKINFO 0xf
 
+#define MC_CMD_0xf_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_STACKINFO_IN msgrequest */
 #define    MC_CMD_STACKINFO_IN_LEN 0
 
@@ -1513,6 +1539,8 @@
  */
 #define MC_CMD_MDIO_READ 0x10
 
+#define MC_CMD_0x10_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_MDIO_READ_IN msgrequest */
 #define    MC_CMD_MDIO_READ_IN_LEN 16
 /* Bus number; there are two MDIO buses: one for the internal PHY, and one for
@@ -1552,6 +1580,8 @@
  */
 #define MC_CMD_MDIO_WRITE 0x11
 
+#define MC_CMD_0x11_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_MDIO_WRITE_IN msgrequest */
 #define    MC_CMD_MDIO_WRITE_IN_LEN 20
 /* Bus number; there are two MDIO buses: one for the internal PHY, and one for
@@ -1591,6 +1621,8 @@
  */
 #define MC_CMD_DBI_WRITE 0x12
 
+#define MC_CMD_0x12_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DBI_WRITE_IN msgrequest */
 #define    MC_CMD_DBI_WRITE_IN_LENMIN 12
 #define    MC_CMD_DBI_WRITE_IN_LENMAX 252
@@ -1739,6 +1771,8 @@
  */
 #define MC_CMD_GET_BOARD_CFG 0x18
 
+#define MC_CMD_0x18_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_BOARD_CFG_IN msgrequest */
 #define    MC_CMD_GET_BOARD_CFG_IN_LEN 0
 
@@ -1778,6 +1812,8 @@
  */
 #define MC_CMD_DBI_READX 0x19
 
+#define MC_CMD_0x19_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DBI_READX_IN msgrequest */
 #define    MC_CMD_DBI_READX_IN_LENMIN 8
 #define    MC_CMD_DBI_READX_IN_LENMAX 248
@@ -1822,6 +1858,8 @@
  */
 #define MC_CMD_SET_RAND_SEED 0x1a
 
+#define MC_CMD_0x1a_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_RAND_SEED_IN msgrequest */
 #define    MC_CMD_SET_RAND_SEED_IN_LEN 16
 /* Seed value. */
@@ -1863,6 +1901,8 @@
  */
 #define MC_CMD_DRV_ATTACH 0x1c
 
+#define MC_CMD_0x1c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_DRV_ATTACH_IN msgrequest */
 #define    MC_CMD_DRV_ATTACH_IN_LEN 12
 /* new state (0=detached, 1=attached) to set if UPDATE=1 */
@@ -1875,6 +1915,8 @@
 #define          MC_CMD_FW_FULL_FEATURED 0x0
 /* enum: Prefer to use firmware with fewer features but lower latency */
 #define          MC_CMD_FW_LOW_LATENCY 0x1
+/* enum: Only this option is allowed for non-admin functions */
+#define          MC_CMD_FW_DONT_CARE  0xffffffff
 
 /* MC_CMD_DRV_ATTACH_OUT msgresponse */
 #define    MC_CMD_DRV_ATTACH_OUT_LEN 4
@@ -1920,6 +1962,8 @@
  */
 #define MC_CMD_PORT_RESET 0x20
 
+#define MC_CMD_0x20_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_PORT_RESET_IN msgrequest */
 #define    MC_CMD_PORT_RESET_IN_LEN 0
 
@@ -1934,6 +1978,7 @@
  * extended version of the deprecated MC_CMD_PORT_RESET with added fields.
  */
 #define MC_CMD_ENTITY_RESET 0x20
+/*      MC_CMD_0x20_PRIVILEGE_CTG SRIOV_CTG_GENERAL */
 
 /* MC_CMD_ENTITY_RESET_IN msgrequest */
 #define    MC_CMD_ENTITY_RESET_IN_LEN 4
@@ -2023,6 +2068,8 @@
  */
 #define MC_CMD_PUTS 0x23
 
+#define MC_CMD_0x23_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_PUTS_IN msgrequest */
 #define    MC_CMD_PUTS_IN_LENMIN 13
 #define    MC_CMD_PUTS_IN_LENMAX 252
@@ -2050,6 +2097,8 @@
  */
 #define MC_CMD_GET_PHY_CFG 0x24
 
+#define MC_CMD_0x24_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_PHY_CFG_IN msgrequest */
 #define    MC_CMD_GET_PHY_CFG_IN_LEN 0
 
@@ -2149,6 +2198,8 @@
  */
 #define MC_CMD_START_BIST 0x25
 
+#define MC_CMD_0x25_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_START_BIST_IN msgrequest */
 #define    MC_CMD_START_BIST_IN_LEN 4
 /* Type of test. */
@@ -2185,6 +2236,8 @@
  */
 #define MC_CMD_POLL_BIST 0x26
 
+#define MC_CMD_0x26_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_POLL_BIST_IN msgrequest */
 #define    MC_CMD_POLL_BIST_IN_LEN 0
 
@@ -2344,6 +2397,8 @@
  */
 #define MC_CMD_GET_LOOPBACK_MODES 0x28
 
+#define MC_CMD_0x28_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_LOOPBACK_MODES_IN msgrequest */
 #define    MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0
 
@@ -2463,6 +2518,8 @@
  */
 #define MC_CMD_GET_LINK 0x29
 
+#define MC_CMD_0x29_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_LINK_IN msgrequest */
 #define    MC_CMD_GET_LINK_IN_LEN 0
 
@@ -2519,6 +2576,8 @@
  */
 #define MC_CMD_SET_LINK 0x2a
 
+#define MC_CMD_0x2a_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_SET_LINK_IN msgrequest */
 #define    MC_CMD_SET_LINK_IN_LEN 16
 /* ??? */
@@ -2550,6 +2609,8 @@
  */
 #define MC_CMD_SET_ID_LED 0x2b
 
+#define MC_CMD_0x2b_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_SET_ID_LED_IN msgrequest */
 #define    MC_CMD_SET_ID_LED_IN_LEN 4
 /* Set LED state. */
@@ -2568,6 +2629,8 @@
  */
 #define MC_CMD_SET_MAC 0x2c
 
+#define MC_CMD_0x2c_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_SET_MAC_IN msgrequest */
 #define    MC_CMD_SET_MAC_IN_LEN 24
 /* The MTU is the MTU programmed directly into the XMAC/GMAC (inclusive of
@@ -2609,6 +2672,8 @@
  */
 #define MC_CMD_PHY_STATS 0x2d
 
+#define MC_CMD_0x2d_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_PHY_STATS_IN msgrequest */
 #define    MC_CMD_PHY_STATS_IN_LEN 8
 /* ??? */
@@ -2687,8 +2752,10 @@
  */
 #define MC_CMD_MAC_STATS 0x2e
 
+#define MC_CMD_0x2e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_MAC_STATS_IN msgrequest */
-#define    MC_CMD_MAC_STATS_IN_LEN 16
+#define    MC_CMD_MAC_STATS_IN_LEN 20
 /* ??? */
 #define       MC_CMD_MAC_STATS_IN_DMA_ADDR_OFST 0
 #define       MC_CMD_MAC_STATS_IN_DMA_ADDR_LEN 8
@@ -2710,6 +2777,8 @@
 #define        MC_CMD_MAC_STATS_IN_PERIOD_MS_LBN 16
 #define        MC_CMD_MAC_STATS_IN_PERIOD_MS_WIDTH 16
 #define       MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12
+/* port id so vadapter stats can be provided */
+#define       MC_CMD_MAC_STATS_IN_PORT_ID_OFST 16
 
 /* MC_CMD_MAC_STATS_OUT_DMA msgresponse */
 #define    MC_CMD_MAC_STATS_OUT_DMA_LEN 0
@@ -2824,11 +2893,31 @@
 /* enum: RXDP counter: Number of times an emergency descriptor fetch was
  * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only.
  */
-#define          MC_CMD_MAC_RXDP_EMERGENCY_FETCH_CONDITIONS  0x47
+#define          MC_CMD_MAC_RXDP_HLB_FETCH_CONDITIONS  0x47
 /* enum: RXDP counter: Number of times the DPCPU waited for an existing
  * descriptor fetch. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only.
  */
-#define          MC_CMD_MAC_RXDP_EMERGENCY_WAIT_CONDITIONS  0x48
+#define          MC_CMD_MAC_RXDP_HLB_WAIT_CONDITIONS  0x48
+#define          MC_CMD_MAC_VADAPTER_RX_DMABUF_START  0x4c /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_UNICAST_PACKETS  0x4c /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_UNICAST_BYTES  0x4d /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_MULTICAST_PACKETS  0x4e /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_MULTICAST_BYTES  0x4f /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_BROADCAST_PACKETS  0x50 /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_BROADCAST_BYTES  0x51 /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_BAD_PACKETS  0x52 /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_BAD_BYTES  0x53 /* enum */
+#define          MC_CMD_MAC_VADAPTER_RX_OVERFLOW  0x54 /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_DMABUF_START  0x57 /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_UNICAST_PACKETS  0x57 /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_UNICAST_BYTES  0x58 /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_MULTICAST_PACKETS  0x59 /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_MULTICAST_BYTES  0x5a /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_BROADCAST_PACKETS  0x5b /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_BROADCAST_BYTES  0x5c /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_BAD_PACKETS  0x5d /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_BAD_BYTES  0x5e /* enum */
+#define          MC_CMD_MAC_VADAPTER_TX_OVERFLOW  0x5f /* enum */
 /* enum: Start of GMAC stats buffer space, for Siena only. */
 #define          MC_CMD_GMAC_DMABUF_START  0x40
 /* enum: End of GMAC stats buffer space, for Siena only. */
@@ -2926,6 +3015,8 @@
  */
 #define MC_CMD_WOL_FILTER_SET 0x32
 
+#define MC_CMD_0x32_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_WOL_FILTER_SET_IN msgrequest */
 #define    MC_CMD_WOL_FILTER_SET_IN_LEN 192
 #define       MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0
@@ -3020,6 +3111,8 @@
  */
 #define MC_CMD_WOL_FILTER_REMOVE 0x33
 
+#define MC_CMD_0x33_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_WOL_FILTER_REMOVE_IN msgrequest */
 #define    MC_CMD_WOL_FILTER_REMOVE_IN_LEN 4
 #define       MC_CMD_WOL_FILTER_REMOVE_IN_FILTER_ID_OFST 0
@@ -3035,6 +3128,8 @@
  */
 #define MC_CMD_WOL_FILTER_RESET 0x34
 
+#define MC_CMD_0x34_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_WOL_FILTER_RESET_IN msgrequest */
 #define    MC_CMD_WOL_FILTER_RESET_IN_LEN 4
 #define       MC_CMD_WOL_FILTER_RESET_IN_MASK_OFST 0
@@ -3069,6 +3164,8 @@
  */
 #define MC_CMD_NVRAM_TYPES 0x36
 
+#define MC_CMD_0x36_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_TYPES_IN msgrequest */
 #define    MC_CMD_NVRAM_TYPES_IN_LEN 0
 
@@ -3125,6 +3222,8 @@
  */
 #define MC_CMD_NVRAM_INFO 0x37
 
+#define MC_CMD_0x37_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_INFO_IN msgrequest */
 #define    MC_CMD_NVRAM_INFO_IN_LEN 4
 #define       MC_CMD_NVRAM_INFO_IN_TYPE_OFST 0
@@ -3157,6 +3256,8 @@
  */
 #define MC_CMD_NVRAM_UPDATE_START 0x38
 
+#define MC_CMD_0x38_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_UPDATE_START_IN msgrequest */
 #define    MC_CMD_NVRAM_UPDATE_START_IN_LEN 4
 #define       MC_CMD_NVRAM_UPDATE_START_IN_TYPE_OFST 0
@@ -3175,6 +3276,8 @@
  */
 #define MC_CMD_NVRAM_READ 0x39
 
+#define MC_CMD_0x39_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_READ_IN msgrequest */
 #define    MC_CMD_NVRAM_READ_IN_LEN 12
 #define       MC_CMD_NVRAM_READ_IN_TYPE_OFST 0
@@ -3202,6 +3305,8 @@
  */
 #define MC_CMD_NVRAM_WRITE 0x3a
 
+#define MC_CMD_0x3a_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_WRITE_IN msgrequest */
 #define    MC_CMD_NVRAM_WRITE_IN_LENMIN 13
 #define    MC_CMD_NVRAM_WRITE_IN_LENMAX 252
@@ -3228,6 +3333,8 @@
  */
 #define MC_CMD_NVRAM_ERASE 0x3b
 
+#define MC_CMD_0x3b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_ERASE_IN msgrequest */
 #define    MC_CMD_NVRAM_ERASE_IN_LEN 12
 #define       MC_CMD_NVRAM_ERASE_IN_TYPE_OFST 0
@@ -3248,6 +3355,8 @@
  */
 #define MC_CMD_NVRAM_UPDATE_FINISH 0x3c
 
+#define MC_CMD_0x3c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_UPDATE_FINISH_IN msgrequest */
 #define    MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN 8
 #define       MC_CMD_NVRAM_UPDATE_FINISH_IN_TYPE_OFST 0
@@ -3279,6 +3388,8 @@
  */
 #define MC_CMD_REBOOT 0x3d
 
+#define MC_CMD_0x3d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_REBOOT_IN msgrequest */
 #define    MC_CMD_REBOOT_IN_LEN 4
 #define       MC_CMD_REBOOT_IN_FLAGS_OFST 0
@@ -3316,6 +3427,8 @@
  */
 #define MC_CMD_REBOOT_MODE 0x3f
 
+#define MC_CMD_0x3f_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_REBOOT_MODE_IN msgrequest */
 #define    MC_CMD_REBOOT_MODE_IN_LEN 4
 #define       MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0
@@ -3368,6 +3481,8 @@
  */
 #define MC_CMD_SENSOR_INFO 0x41
 
+#define MC_CMD_0x41_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SENSOR_INFO_IN msgrequest */
 #define    MC_CMD_SENSOR_INFO_IN_LEN 0
 
@@ -3542,6 +3657,8 @@
  */
 #define MC_CMD_READ_SENSORS 0x42
 
+#define MC_CMD_0x42_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_READ_SENSORS_IN msgrequest */
 #define    MC_CMD_READ_SENSORS_IN_LEN 8
 /* DMA address of host buffer for sensor readings (must be 4Kbyte aligned). */
@@ -3602,6 +3719,8 @@
  */
 #define MC_CMD_GET_PHY_STATE 0x43
 
+#define MC_CMD_0x43_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_PHY_STATE_IN msgrequest */
 #define    MC_CMD_GET_PHY_STATE_IN_LEN 0
 
@@ -3636,6 +3755,8 @@
  */
 #define MC_CMD_WOL_FILTER_GET 0x45
 
+#define MC_CMD_0x45_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_WOL_FILTER_GET_IN msgrequest */
 #define    MC_CMD_WOL_FILTER_GET_IN_LEN 0
 
@@ -3651,6 +3772,8 @@
  */
 #define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46
 
+#define MC_CMD_0x46_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN msgrequest */
 #define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMIN 8
 #define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX 252
@@ -3692,6 +3815,8 @@
  */
 #define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD 0x47
 
+#define MC_CMD_0x47_PRIVILEGE_CTG SRIOV_CTG_LINK
+
 /* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN msgrequest */
 #define    MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8
 #define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
@@ -3722,6 +3847,8 @@
  */
 #define MC_CMD_TESTASSERT 0x49
 
+#define MC_CMD_0x49_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_TESTASSERT_IN msgrequest */
 #define    MC_CMD_TESTASSERT_IN_LEN 0
 
@@ -3739,6 +3866,8 @@
  */
 #define MC_CMD_WORKAROUND 0x4a
 
+#define MC_CMD_0x4a_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_WORKAROUND_IN msgrequest */
 #define    MC_CMD_WORKAROUND_IN_LEN 8
 #define       MC_CMD_WORKAROUND_IN_TYPE_OFST 0
@@ -3765,6 +3894,8 @@
  */
 #define MC_CMD_GET_PHY_MEDIA_INFO 0x4b
 
+#define MC_CMD_0x4b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_PHY_MEDIA_INFO_IN msgrequest */
 #define    MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN 4
 #define       MC_CMD_GET_PHY_MEDIA_INFO_IN_PAGE_OFST 0
@@ -3788,6 +3919,8 @@
  */
 #define MC_CMD_NVRAM_TEST 0x4c
 
+#define MC_CMD_0x4c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_TEST_IN msgrequest */
 #define    MC_CMD_NVRAM_TEST_IN_LEN 4
 #define       MC_CMD_NVRAM_TEST_IN_TYPE_OFST 0
@@ -3849,6 +3982,8 @@
  */
 #define MC_CMD_SENSOR_SET_LIMS 0x4e
 
+#define MC_CMD_0x4e_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SENSOR_SET_LIMS_IN msgrequest */
 #define    MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
 #define       MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
@@ -3890,6 +4025,8 @@
  */
 #define MC_CMD_NVRAM_PARTITIONS 0x51
 
+#define MC_CMD_0x51_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_PARTITIONS_IN msgrequest */
 #define    MC_CMD_NVRAM_PARTITIONS_IN_LEN 0
 
@@ -3913,6 +4050,8 @@
  */
 #define MC_CMD_NVRAM_METADATA 0x52
 
+#define MC_CMD_0x52_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_NVRAM_METADATA_IN msgrequest */
 #define    MC_CMD_NVRAM_METADATA_IN_LEN 4
 /* Partition type ID code */
@@ -3958,6 +4097,8 @@
  */
 #define MC_CMD_GET_MAC_ADDRESSES 0x55
 
+#define MC_CMD_0x55_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_MAC_ADDRESSES_IN msgrequest */
 #define    MC_CMD_GET_MAC_ADDRESSES_IN_LEN 0
 
@@ -4087,11 +4228,66 @@
 
 
 /***********************************/
+/* MC_CMD_GET_WORKAROUNDS
+ * Read the list of all implemented and all currently enabled workarounds. The
+ * enums here must correspond with those in MC_CMD_WORKAROUND.
+ */
+#define MC_CMD_GET_WORKAROUNDS 0x59
+
+/* MC_CMD_GET_WORKAROUNDS_OUT msgresponse */
+#define    MC_CMD_GET_WORKAROUNDS_OUT_LEN 8
+/* Each workaround is represented by a single bit according to the enums below.
+ */
+#define       MC_CMD_GET_WORKAROUNDS_OUT_IMPLEMENTED_OFST 0
+#define       MC_CMD_GET_WORKAROUNDS_OUT_ENABLED_OFST 4
+/* enum: Bug 17230 work around. */
+#define          MC_CMD_GET_WORKAROUNDS_OUT_BUG17230 0x2
+/* enum: Bug 35388 work around (unsafe EVQ writes). */
+#define          MC_CMD_GET_WORKAROUNDS_OUT_BUG35388 0x4
+/* enum: Bug35017 workaround (A64 tables must be identity map) */
+#define          MC_CMD_GET_WORKAROUNDS_OUT_BUG35017 0x8
+
+
+/***********************************/
+/* MC_CMD_LINK_STATE_MODE
+ * Read/set link state mode of a VF
+ */
+#define MC_CMD_LINK_STATE_MODE 0x5c
+
+#define MC_CMD_0x5c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_LINK_STATE_MODE_IN msgrequest */
+#define    MC_CMD_LINK_STATE_MODE_IN_LEN 8
+/* The target function to have its link state mode read or set, must be a VF
+ * e.g. VF 1,3 = 0x00030001
+ */
+#define       MC_CMD_LINK_STATE_MODE_IN_FUNCTION_OFST 0
+#define        MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_LBN 0
+#define        MC_CMD_LINK_STATE_MODE_IN_FUNCTION_PF_WIDTH 16
+#define        MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_LBN 16
+#define        MC_CMD_LINK_STATE_MODE_IN_FUNCTION_VF_WIDTH 16
+/* New link state mode to be set */
+#define       MC_CMD_LINK_STATE_MODE_IN_NEW_MODE_OFST 4
+#define          MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_AUTO       0x0 /* enum */
+#define          MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_UP         0x1 /* enum */
+#define          MC_CMD_LINK_STATE_MODE_IN_LINK_STATE_DOWN       0x2 /* enum */
+/* enum: Use this value to just read the existing setting without modifying it.
+ */
+#define          MC_CMD_LINK_STATE_MODE_IN_DO_NOT_CHANGE         0xffffffff
+
+/* MC_CMD_LINK_STATE_MODE_OUT msgresponse */
+#define    MC_CMD_LINK_STATE_MODE_OUT_LEN 4
+#define       MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_OFST 0
+
+
+/***********************************/
 /* MC_CMD_READ_REGS
  * Get a dump of the MCPU registers
  */
 #define MC_CMD_READ_REGS 0x50
 
+#define MC_CMD_0x50_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_READ_REGS_IN msgrequest */
 #define    MC_CMD_READ_REGS_IN_LEN 0
 
@@ -4115,6 +4311,8 @@
  */
 #define MC_CMD_INIT_EVQ 0x80
 
+#define MC_CMD_0x80_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_INIT_EVQ_IN msgrequest */
 #define    MC_CMD_INIT_EVQ_IN_LENMIN 44
 #define    MC_CMD_INIT_EVQ_IN_LENMAX 548
@@ -4213,6 +4411,8 @@
  */
 #define MC_CMD_INIT_RXQ 0x81
 
+#define MC_CMD_0x81_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_INIT_RXQ_IN msgrequest */
 #define    MC_CMD_INIT_RXQ_IN_LENMIN 36
 #define    MC_CMD_INIT_RXQ_IN_LENMAX 252
@@ -4265,6 +4465,8 @@
  */
 #define MC_CMD_INIT_TXQ 0x82
 
+#define MC_CMD_0x82_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_INIT_TXQ_IN msgrequest */
 #define    MC_CMD_INIT_TXQ_IN_LENMIN 36
 #define    MC_CMD_INIT_TXQ_IN_LENMAX 252
@@ -4322,6 +4524,8 @@
  */
 #define MC_CMD_FINI_EVQ 0x83
 
+#define MC_CMD_0x83_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_FINI_EVQ_IN msgrequest */
 #define    MC_CMD_FINI_EVQ_IN_LEN 4
 /* Instance of EVQ to destroy. Should be the same instance as that previously
@@ -4339,6 +4543,8 @@
  */
 #define MC_CMD_FINI_RXQ 0x84
 
+#define MC_CMD_0x84_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_FINI_RXQ_IN msgrequest */
 #define    MC_CMD_FINI_RXQ_IN_LEN 4
 /* Instance of RXQ to destroy */
@@ -4354,6 +4560,8 @@
  */
 #define MC_CMD_FINI_TXQ 0x85
 
+#define MC_CMD_0x85_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_FINI_TXQ_IN msgrequest */
 #define    MC_CMD_FINI_TXQ_IN_LEN 4
 /* Instance of TXQ to destroy */
@@ -4369,6 +4577,8 @@
  */
 #define MC_CMD_DRIVER_EVENT 0x86
 
+#define MC_CMD_0x86_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_DRIVER_EVENT_IN msgrequest */
 #define    MC_CMD_DRIVER_EVENT_IN_LEN 12
 /* Handle of target EVQ */
@@ -4392,6 +4602,8 @@
  */
 #define MC_CMD_PROXY_CMD 0x5b
 
+#define MC_CMD_0x5b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_PROXY_CMD_IN msgrequest */
 #define    MC_CMD_PROXY_CMD_IN_LEN 4
 /* The handle of the target function. */
@@ -4414,6 +4626,8 @@
  */
 #define MC_CMD_ALLOC_BUFTBL_CHUNK 0x87
 
+#define MC_CMD_0x87_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_ALLOC_BUFTBL_CHUNK_IN msgrequest */
 #define    MC_CMD_ALLOC_BUFTBL_CHUNK_IN_LEN 8
 /* Owner ID to use */
@@ -4437,6 +4651,8 @@
  */
 #define MC_CMD_PROGRAM_BUFTBL_ENTRIES 0x88
 
+#define MC_CMD_0x88_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN msgrequest */
 #define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMIN 20
 #define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 268
@@ -4463,6 +4679,8 @@
  */
 #define MC_CMD_FREE_BUFTBL_CHUNK 0x89
 
+#define MC_CMD_0x89_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_FREE_BUFTBL_CHUNK_IN msgrequest */
 #define    MC_CMD_FREE_BUFTBL_CHUNK_IN_LEN 4
 #define       MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_OFST 0
@@ -4477,6 +4695,8 @@
  */
 #define MC_CMD_FILTER_OP 0x8a
 
+#define MC_CMD_0x8a_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_FILTER_OP_IN msgrequest */
 #define    MC_CMD_FILTER_OP_IN_LEN 108
 /* identifies the type of operation requested */
@@ -4637,6 +4857,8 @@
  */
 #define MC_CMD_GET_PARSER_DISP_INFO 0xe4
 
+#define MC_CMD_0xe4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_PARSER_DISP_INFO_IN msgrequest */
 #define    MC_CMD_GET_PARSER_DISP_INFO_IN_LEN 4
 /* identifies the type of operation requested */
@@ -4669,6 +4891,8 @@
  */
 #define MC_CMD_PARSER_DISP_RW 0xe5
 
+#define MC_CMD_0xe5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_PARSER_DISP_RW_IN msgrequest */
 #define    MC_CMD_PARSER_DISP_RW_IN_LEN 32
 /* identifies the target of the operation */
@@ -4719,6 +4943,8 @@
  */
 #define MC_CMD_GET_PF_COUNT 0xb6
 
+#define MC_CMD_0xb6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_PF_COUNT_IN msgrequest */
 #define    MC_CMD_GET_PF_COUNT_IN_LEN 0
 
@@ -4750,6 +4976,8 @@
  */
 #define MC_CMD_GET_PORT_ASSIGNMENT 0xb8
 
+#define MC_CMD_0xb8_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_PORT_ASSIGNMENT_IN msgrequest */
 #define    MC_CMD_GET_PORT_ASSIGNMENT_IN_LEN 0
 
@@ -4765,6 +4993,8 @@
  */
 #define MC_CMD_SET_PORT_ASSIGNMENT 0xb9
 
+#define MC_CMD_0xb9_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_PORT_ASSIGNMENT_IN msgrequest */
 #define    MC_CMD_SET_PORT_ASSIGNMENT_IN_LEN 4
 /* Identifies the port assignment for this function. */
@@ -4780,6 +5010,8 @@
  */
 #define MC_CMD_ALLOC_VIS 0x8b
 
+#define MC_CMD_0x8b_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_ALLOC_VIS_IN msgrequest */
 #define    MC_CMD_ALLOC_VIS_IN_LEN 8
 /* The minimum number of VIs that is acceptable */
@@ -4804,6 +5036,8 @@
  */
 #define MC_CMD_FREE_VIS 0x8c
 
+#define MC_CMD_0x8c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_FREE_VIS_IN msgrequest */
 #define    MC_CMD_FREE_VIS_IN_LEN 0
 
@@ -4817,6 +5051,8 @@
  */
 #define MC_CMD_GET_SRIOV_CFG 0xba
 
+#define MC_CMD_0xba_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_SRIOV_CFG_IN msgrequest */
 #define    MC_CMD_GET_SRIOV_CFG_IN_LEN 0
 
@@ -4841,6 +5077,8 @@
  */
 #define MC_CMD_SET_SRIOV_CFG 0xbb
 
+#define MC_CMD_0xbb_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_SRIOV_CFG_IN msgrequest */
 #define    MC_CMD_SET_SRIOV_CFG_IN_LEN 20
 /* Number of VFs currently enabled. */
@@ -4870,6 +5108,8 @@
  */
 #define MC_CMD_GET_VI_ALLOC_INFO 0x8d
 
+#define MC_CMD_0x8d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_VI_ALLOC_INFO_IN msgrequest */
 #define    MC_CMD_GET_VI_ALLOC_INFO_IN_LEN 0
 
@@ -4889,6 +5129,8 @@
  */
 #define MC_CMD_DUMP_VI_STATE 0x8e
 
+#define MC_CMD_0x8e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_DUMP_VI_STATE_IN msgrequest */
 #define    MC_CMD_DUMP_VI_STATE_IN_LEN 4
 /* The VI number to query. */
@@ -4998,6 +5240,8 @@
  */
 #define MC_CMD_ALLOC_PIOBUF 0x8f
 
+#define MC_CMD_0x8f_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_ALLOC_PIOBUF_IN msgrequest */
 #define    MC_CMD_ALLOC_PIOBUF_IN_LEN 0
 
@@ -5013,6 +5257,8 @@
  */
 #define MC_CMD_FREE_PIOBUF 0x90
 
+#define MC_CMD_0x90_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_FREE_PIOBUF_IN msgrequest */
 #define    MC_CMD_FREE_PIOBUF_IN_LEN 4
 /* Handle for allocated push I/O buffer. */
@@ -5028,6 +5274,8 @@
  */
 #define MC_CMD_GET_VI_TLP_PROCESSING 0xb0
 
+#define MC_CMD_0xb0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_VI_TLP_PROCESSING_IN msgrequest */
 #define    MC_CMD_GET_VI_TLP_PROCESSING_IN_LEN 4
 /* VI number to get information for. */
@@ -5062,6 +5310,8 @@
  */
 #define MC_CMD_SET_VI_TLP_PROCESSING 0xb1
 
+#define MC_CMD_0xb1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_SET_VI_TLP_PROCESSING_IN msgrequest */
 #define    MC_CMD_SET_VI_TLP_PROCESSING_IN_LEN 8
 /* VI number to set information for. */
@@ -5096,6 +5346,8 @@
  */
 #define MC_CMD_GET_TLP_PROCESSING_GLOBALS 0xbc
 
+#define MC_CMD_0xbc_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN msgrequest */
 #define    MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_LEN 4
 #define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
@@ -5157,6 +5409,8 @@
  */
 #define MC_CMD_SET_TLP_PROCESSING_GLOBALS 0xbd
 
+#define MC_CMD_0xbd_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN msgrequest */
 #define    MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_LEN 8
 #define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
@@ -5203,6 +5457,8 @@
  */
 #define MC_CMD_SATELLITE_DOWNLOAD 0x91
 
+#define MC_CMD_0x91_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SATELLITE_DOWNLOAD_IN msgrequest: The reset requirements for the CPUs
  * are subtle, and so downloads must proceed in a number of phases.
  *
@@ -5318,6 +5574,7 @@
  */
 #define MC_CMD_GET_CAPABILITIES 0xbe
 
+#define MC_CMD_0xbe_PRIVILEGE_CTG SRIOV_CTG_GENERAL
 /* MC_CMD_GET_CAPABILITIES_IN msgrequest */
 #define    MC_CMD_GET_CAPABILITIES_IN_LEN 0
 
@@ -5343,6 +5600,8 @@
 #define        MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1
 #define        MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27
 #define        MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_OUT_EVB_WIDTH 1
 /* RxDPCPU firmware id. */
 #define       MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4
 #define       MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2
@@ -5433,6 +5692,8 @@
  */
 #define MC_CMD_TCM_BUCKET_ALLOC 0xb2
 
+#define MC_CMD_0xb2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_TCM_BUCKET_ALLOC_IN msgrequest */
 #define    MC_CMD_TCM_BUCKET_ALLOC_IN_LEN 0
 
@@ -5448,6 +5709,8 @@
  */
 #define MC_CMD_TCM_BUCKET_FREE 0xb3
 
+#define MC_CMD_0xb3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_TCM_BUCKET_FREE_IN msgrequest */
 #define    MC_CMD_TCM_BUCKET_FREE_IN_LEN 4
 /* the bucket id */
@@ -5463,6 +5726,8 @@
  */
 #define MC_CMD_TCM_BUCKET_INIT 0xb4
 
+#define MC_CMD_0xb4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_TCM_BUCKET_INIT_IN msgrequest */
 #define    MC_CMD_TCM_BUCKET_INIT_IN_LEN 8
 /* the bucket id */
@@ -5480,6 +5745,8 @@
  */
 #define MC_CMD_TCM_TXQ_INIT 0xb5
 
+#define MC_CMD_0xb5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_TCM_TXQ_INIT_IN msgrequest */
 #define    MC_CMD_TCM_TXQ_INIT_IN_LEN 28
 /* the txq id */
@@ -5511,6 +5778,8 @@
  */
 #define MC_CMD_LINK_PIOBUF 0x92
 
+#define MC_CMD_0x92_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_LINK_PIOBUF_IN msgrequest */
 #define    MC_CMD_LINK_PIOBUF_IN_LEN 8
 /* Handle for allocated push I/O buffer. */
@@ -5528,6 +5797,8 @@
  */
 #define MC_CMD_UNLINK_PIOBUF 0x93
 
+#define MC_CMD_0x93_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_UNLINK_PIOBUF_IN msgrequest */
 #define    MC_CMD_UNLINK_PIOBUF_IN_LEN 4
 /* Function Local Instance (VI) number. */
@@ -5543,6 +5814,8 @@
  */
 #define MC_CMD_VSWITCH_ALLOC 0x94
 
+#define MC_CMD_0x94_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VSWITCH_ALLOC_IN msgrequest */
 #define    MC_CMD_VSWITCH_ALLOC_IN_LEN 16
 /* The port to connect to the v-switch's upstream port. */
@@ -5572,6 +5845,8 @@
  */
 #define MC_CMD_VSWITCH_FREE 0x95
 
+#define MC_CMD_0x95_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VSWITCH_FREE_IN msgrequest */
 #define    MC_CMD_VSWITCH_FREE_IN_LEN 4
 /* The port to which the v-switch is connected. */
@@ -5587,6 +5862,8 @@
  */
 #define MC_CMD_VPORT_ALLOC 0x96
 
+#define MC_CMD_0x96_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VPORT_ALLOC_IN msgrequest */
 #define    MC_CMD_VPORT_ALLOC_IN_LEN 20
 /* The port to which the v-switch is connected. */
@@ -5636,6 +5913,8 @@
  */
 #define MC_CMD_VPORT_FREE 0x97
 
+#define MC_CMD_0x97_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VPORT_FREE_IN msgrequest */
 #define    MC_CMD_VPORT_FREE_IN_LEN 4
 /* The handle of the v-port */
@@ -5651,8 +5930,10 @@
  */
 #define MC_CMD_VADAPTOR_ALLOC 0x98
 
+#define MC_CMD_0x98_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VADAPTOR_ALLOC_IN msgrequest */
-#define    MC_CMD_VADAPTOR_ALLOC_IN_LEN 16
+#define    MC_CMD_VADAPTOR_ALLOC_IN_LEN 30
 /* The port to connect to the v-adaptor's port. */
 #define       MC_CMD_VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
 /* Flags controlling v-adaptor creation */
@@ -5661,6 +5942,19 @@
 #define        MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_WIDTH 1
 /* The number of VLAN tags to strip on receive */
 #define       MC_CMD_VADAPTOR_ALLOC_IN_NUM_VLANS_OFST 12
+/* The number of VLAN tags to transparently insert/remove. */
+#define       MC_CMD_VADAPTOR_ALLOC_IN_NUM_VLAN_TAGS_OFST 16
+/* The actual VLAN tags to insert/remove */
+#define       MC_CMD_VADAPTOR_ALLOC_IN_VLAN_TAGS_OFST 20
+#define        MC_CMD_VADAPTOR_ALLOC_IN_VLAN_TAG_0_LBN 0
+#define        MC_CMD_VADAPTOR_ALLOC_IN_VLAN_TAG_0_WIDTH 16
+#define        MC_CMD_VADAPTOR_ALLOC_IN_VLAN_TAG_1_LBN 16
+#define        MC_CMD_VADAPTOR_ALLOC_IN_VLAN_TAG_1_WIDTH 16
+/* The MAC address to assign to this v-adaptor */
+#define       MC_CMD_VADAPTOR_ALLOC_IN_MACADDR_OFST 24
+#define       MC_CMD_VADAPTOR_ALLOC_IN_MACADDR_LEN 6
+/* enum: Derive the MAC address from the upstream port */
+#define          MC_CMD_VADAPTOR_ALLOC_IN_AUTO_MAC  0x0
 
 /* MC_CMD_VADAPTOR_ALLOC_OUT msgresponse */
 #define    MC_CMD_VADAPTOR_ALLOC_OUT_LEN 0
@@ -5672,6 +5966,8 @@
  */
 #define MC_CMD_VADAPTOR_FREE 0x99
 
+#define MC_CMD_0x99_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VADAPTOR_FREE_IN msgrequest */
 #define    MC_CMD_VADAPTOR_FREE_IN_LEN 4
 /* The port to which the v-adaptor is connected. */
@@ -5682,11 +5978,53 @@
 
 
 /***********************************/
+/* MC_CMD_VADAPTOR_SET_MAC
+ * assign a new MAC address to a v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_SET_MAC 0x5d
+
+#define MC_CMD_0x5d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VADAPTOR_SET_MAC_IN msgrequest */
+#define    MC_CMD_VADAPTOR_SET_MAC_IN_LEN 10
+/* The port to which the v-adaptor is connected. */
+#define       MC_CMD_VADAPTOR_SET_MAC_IN_UPSTREAM_PORT_ID_OFST 0
+/* The new MAC address to assign to this v-adaptor */
+#define       MC_CMD_VADAPTOR_SET_MAC_IN_MACADDR_OFST 4
+#define       MC_CMD_VADAPTOR_SET_MAC_IN_MACADDR_LEN 6
+
+/* MC_CMD_VADAPTOR_SET_MAC_OUT msgresponse */
+#define    MC_CMD_VADAPTOR_SET_MAC_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VADAPTOR_GET_MAC
+ * read the MAC address assigned to a v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_GET_MAC 0x5e
+
+#define MC_CMD_0x5e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_VADAPTOR_GET_MAC_IN msgrequest */
+#define    MC_CMD_VADAPTOR_GET_MAC_IN_LEN 4
+/* The port to which the v-adaptor is connected. */
+#define       MC_CMD_VADAPTOR_GET_MAC_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VADAPTOR_GET_MAC_OUT msgresponse */
+#define    MC_CMD_VADAPTOR_GET_MAC_OUT_LEN 6
+/* The MAC address assigned to this v-adaptor */
+#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_OFST 0
+#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_LEN 6
+
+
+/***********************************/
 /* MC_CMD_EVB_PORT_ASSIGN
  * assign a port to a PCI function.
  */
 #define MC_CMD_EVB_PORT_ASSIGN 0x9a
 
+#define MC_CMD_0x9a_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_EVB_PORT_ASSIGN_IN msgrequest */
 #define    MC_CMD_EVB_PORT_ASSIGN_IN_LEN 8
 /* The port to assign. */
@@ -5708,6 +6046,8 @@
  */
 #define MC_CMD_RDWR_A64_REGIONS 0x9b
 
+#define MC_CMD_0x9b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_RDWR_A64_REGIONS_IN msgrequest */
 #define    MC_CMD_RDWR_A64_REGIONS_IN_LEN 17
 #define       MC_CMD_RDWR_A64_REGIONS_IN_REGION0_OFST 0
@@ -5736,6 +6076,8 @@
  */
 #define MC_CMD_ONLOAD_STACK_ALLOC 0x9c
 
+#define MC_CMD_0x9c_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_ONLOAD_STACK_ALLOC_IN msgrequest */
 #define    MC_CMD_ONLOAD_STACK_ALLOC_IN_LEN 4
 /* The handle of the owning upstream port */
@@ -5753,6 +6095,8 @@
  */
 #define MC_CMD_ONLOAD_STACK_FREE 0x9d
 
+#define MC_CMD_0x9d_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
+
 /* MC_CMD_ONLOAD_STACK_FREE_IN msgrequest */
 #define    MC_CMD_ONLOAD_STACK_FREE_IN_LEN 4
 /* The handle of the Onload stack */
@@ -5768,6 +6112,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_ALLOC 0x9e
 
+#define MC_CMD_0x9e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_ALLOC_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_ALLOC_IN_LEN 12
 /* The handle of the owning upstream port */
@@ -5800,6 +6146,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_FREE 0x9f
 
+#define MC_CMD_0x9f_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_FREE_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_FREE_IN_LEN 4
 /* The handle of the RSS context */
@@ -5815,6 +6163,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_SET_KEY 0xa0
 
+#define MC_CMD_0xa0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_SET_KEY_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_SET_KEY_IN_LEN 44
 /* The handle of the RSS context */
@@ -5833,6 +6183,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_GET_KEY 0xa1
 
+#define MC_CMD_0xa1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_GET_KEY_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_GET_KEY_IN_LEN 4
 /* The handle of the RSS context */
@@ -5851,6 +6203,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_SET_TABLE 0xa2
 
+#define MC_CMD_0xa2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_SET_TABLE_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_SET_TABLE_IN_LEN 132
 /* The handle of the RSS context */
@@ -5869,6 +6223,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_GET_TABLE 0xa3
 
+#define MC_CMD_0xa3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_GET_TABLE_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_GET_TABLE_IN_LEN 4
 /* The handle of the RSS context */
@@ -5887,6 +6243,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_SET_FLAGS 0xe1
 
+#define MC_CMD_0xe1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_SET_FLAGS_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN 8
 /* The handle of the RSS context */
@@ -5912,6 +6270,8 @@
  */
 #define MC_CMD_RSS_CONTEXT_GET_FLAGS 0xe2
 
+#define MC_CMD_0xe2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_RSS_CONTEXT_GET_FLAGS_IN msgrequest */
 #define    MC_CMD_RSS_CONTEXT_GET_FLAGS_IN_LEN 4
 /* The handle of the RSS context */
@@ -5937,6 +6297,8 @@
  */
 #define MC_CMD_DOT1P_MAPPING_ALLOC 0xa4
 
+#define MC_CMD_0xa4_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DOT1P_MAPPING_ALLOC_IN msgrequest */
 #define    MC_CMD_DOT1P_MAPPING_ALLOC_IN_LEN 8
 /* The handle of the owning upstream port */
@@ -5959,6 +6321,8 @@
  */
 #define MC_CMD_DOT1P_MAPPING_FREE 0xa5
 
+#define MC_CMD_0xa5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DOT1P_MAPPING_FREE_IN msgrequest */
 #define    MC_CMD_DOT1P_MAPPING_FREE_IN_LEN 4
 /* The handle of the .1p mapping */
@@ -5974,6 +6338,8 @@
  */
 #define MC_CMD_DOT1P_MAPPING_SET_TABLE 0xa6
 
+#define MC_CMD_0xa6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DOT1P_MAPPING_SET_TABLE_IN msgrequest */
 #define    MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_LEN 36
 /* The handle of the .1p mapping */
@@ -5994,6 +6360,8 @@
  */
 #define MC_CMD_DOT1P_MAPPING_GET_TABLE 0xa7
 
+#define MC_CMD_0xa7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DOT1P_MAPPING_GET_TABLE_IN msgrequest */
 #define    MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_LEN 4
 /* The handle of the .1p mapping */
@@ -6014,6 +6382,8 @@
  */
 #define MC_CMD_GET_VECTOR_CFG 0xbf
 
+#define MC_CMD_0xbf_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_VECTOR_CFG_IN msgrequest */
 #define    MC_CMD_GET_VECTOR_CFG_IN_LEN 0
 
@@ -6033,6 +6403,8 @@
  */
 #define MC_CMD_SET_VECTOR_CFG 0xc0
 
+#define MC_CMD_0xc0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_SET_VECTOR_CFG_IN msgrequest */
 #define    MC_CMD_SET_VECTOR_CFG_IN_LEN 12
 /* Base absolute interrupt vector number, or MC_CMD_RESOURCE_INSTANCE_ANY to
@@ -6423,6 +6795,8 @@
  */
 #define MC_CMD_VPORT_ADD_MAC_ADDRESS 0xa8
 
+#define MC_CMD_0xa8_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VPORT_ADD_MAC_ADDRESS_IN msgrequest */
 #define    MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN 10
 /* The handle of the v-port */
@@ -6441,6 +6815,8 @@
  */
 #define MC_CMD_VPORT_DEL_MAC_ADDRESS 0xa9
 
+#define MC_CMD_0xa9_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VPORT_DEL_MAC_ADDRESS_IN msgrequest */
 #define    MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN 10
 /* The handle of the v-port */
@@ -6459,6 +6835,8 @@
  */
 #define MC_CMD_VPORT_GET_MAC_ADDRESSES 0xaa
 
+#define MC_CMD_0xaa_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_VPORT_GET_MAC_ADDRESSES_IN msgrequest */
 #define    MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_LEN 4
 /* The handle of the v-port */
@@ -6486,6 +6864,8 @@
  */
 #define MC_CMD_DUMP_BUFTBL_ENTRIES 0xab
 
+#define MC_CMD_0xab_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DUMP_BUFTBL_ENTRIES_IN msgrequest */
 #define    MC_CMD_DUMP_BUFTBL_ENTRIES_IN_LEN 8
 /* Index of the first buffer table entry. */
@@ -6510,6 +6890,8 @@
  */
 #define MC_CMD_SET_RXDP_CONFIG 0xc1
 
+#define MC_CMD_0xc1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_RXDP_CONFIG_IN msgrequest */
 #define    MC_CMD_SET_RXDP_CONFIG_IN_LEN 4
 #define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
@@ -6526,6 +6908,8 @@
  */
 #define MC_CMD_GET_RXDP_CONFIG 0xc2
 
+#define MC_CMD_0xc2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_RXDP_CONFIG_IN msgrequest */
 #define    MC_CMD_GET_RXDP_CONFIG_IN_LEN 0
 
@@ -6890,6 +7274,8 @@
  */
 #define MC_CMD_GET_CLOCK 0xac
 
+#define MC_CMD_0xac_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_CLOCK_IN msgrequest */
 #define    MC_CMD_GET_CLOCK_IN_LEN 0
 
@@ -6907,6 +7293,8 @@
  */
 #define MC_CMD_SET_CLOCK 0xad
 
+#define MC_CMD_0xad_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_CLOCK_IN msgrequest */
 #define    MC_CMD_SET_CLOCK_IN_LEN 12
 /* Requested system frequency in MHz; 0 leaves unchanged. */
@@ -6932,6 +7320,8 @@
  */
 #define MC_CMD_DPCPU_RPC 0xae
 
+#define MC_CMD_0xae_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DPCPU_RPC_IN msgrequest */
 #define    MC_CMD_DPCPU_RPC_IN_LEN 36
 #define       MC_CMD_DPCPU_RPC_IN_CPU_OFST 0
@@ -7016,6 +7406,8 @@
  */
 #define MC_CMD_TRIGGER_INTERRUPT 0xe3
 
+#define MC_CMD_0xe3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_TRIGGER_INTERRUPT_IN msgrequest */
 #define    MC_CMD_TRIGGER_INTERRUPT_IN_LEN 4
 /* Interrupt level relative to base for function. */
@@ -7031,6 +7423,8 @@
  */
 #define MC_CMD_CAP_BLK_READ 0xe7
 
+#define MC_CMD_0xe7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_CAP_BLK_READ_IN msgrequest */
 #define    MC_CMD_CAP_BLK_READ_IN_LEN 12
 #define       MC_CMD_CAP_BLK_READ_IN_CAP_REG_OFST 0
@@ -7055,6 +7449,8 @@
  */
 #define MC_CMD_DUMP_DO 0xe8
 
+#define MC_CMD_0xe8_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DUMP_DO_IN msgrequest */
 #define    MC_CMD_DUMP_DO_IN_LEN 52
 #define       MC_CMD_DUMP_DO_IN_PADDING_OFST 0
@@ -7108,6 +7504,8 @@
  */
 #define MC_CMD_DUMP_CONFIGURE_UNSOLICITED 0xe9
 
+#define MC_CMD_0xe9_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN msgrequest */
 #define    MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_LEN 52
 #define       MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_ENABLE_OFST 0
@@ -7151,6 +7549,8 @@
  */
 #define MC_CMD_SET_PSU 0xea
 
+#define MC_CMD_0xea_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_PSU_IN msgrequest */
 #define    MC_CMD_SET_PSU_IN_LEN 12
 #define       MC_CMD_SET_PSU_IN_PARAM_OFST 0
@@ -7171,6 +7571,8 @@
  */
 #define MC_CMD_GET_FUNCTION_INFO 0xec
 
+#define MC_CMD_0xec_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_FUNCTION_INFO_IN msgrequest */
 #define    MC_CMD_GET_FUNCTION_INFO_IN_LEN 0
 
@@ -7188,6 +7590,8 @@
  */
 #define MC_CMD_ENABLE_OFFLINE_BIST 0xed
 
+#define MC_CMD_0xed_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_ENABLE_OFFLINE_BIST_IN msgrequest */
 #define    MC_CMD_ENABLE_OFFLINE_BIST_IN_LEN 0
 
@@ -7203,6 +7607,8 @@
  */
 #define MC_CMD_UART_SEND_DATA 0xee
 
+#define MC_CMD_0xee_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_UART_SEND_DATA_OUT msgrequest */
 #define    MC_CMD_UART_SEND_DATA_OUT_LENMIN 16
 #define    MC_CMD_UART_SEND_DATA_OUT_LENMAX 252
@@ -7231,6 +7637,8 @@
  */
 #define MC_CMD_UART_RECV_DATA 0xef
 
+#define MC_CMD_0xef_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_UART_RECV_DATA_OUT msgrequest */
 #define    MC_CMD_UART_RECV_DATA_OUT_LEN 16
 /* CRC32 over OFFSET, LENGTH, RESERVED */
@@ -7266,6 +7674,8 @@
  */
 #define MC_CMD_READ_FUSES 0xf0
 
+#define MC_CMD_0xf0_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_READ_FUSES_IN msgrequest */
 #define    MC_CMD_READ_FUSES_IN_LEN 8
 /* Offset in OTP to read */
@@ -7292,6 +7702,8 @@
  */
 #define MC_CMD_KR_TUNE 0xf1
 
+#define MC_CMD_0xf1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_KR_TUNE_IN msgrequest */
 #define    MC_CMD_KR_TUNE_IN_LENMIN 4
 #define    MC_CMD_KR_TUNE_IN_LENMAX 252
@@ -7550,6 +7962,8 @@
  */
 #define MC_CMD_PCIE_TUNE 0xf2
 
+#define MC_CMD_0xf2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_PCIE_TUNE_IN msgrequest */
 #define    MC_CMD_PCIE_TUNE_IN_LENMIN 4
 #define    MC_CMD_PCIE_TUNE_IN_LENMAX 252
@@ -7711,6 +8125,8 @@
  */
 #define MC_CMD_LICENSING 0xf3
 
+#define MC_CMD_0xf3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_LICENSING_IN msgrequest */
 #define    MC_CMD_LICENSING_IN_LEN 4
 /* identifies the type of operation requested */
@@ -7756,6 +8172,8 @@
  */
 #define MC_CMD_MC2MC_PROXY 0xf4
 
+#define MC_CMD_0xf4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_MC2MC_PROXY_IN msgrequest */
 #define    MC_CMD_MC2MC_PROXY_IN_LEN 0
 
@@ -7771,6 +8189,8 @@
  */
 #define MC_CMD_GET_LICENSED_APP_STATE 0xf5
 
+#define MC_CMD_0xf5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_GET_LICENSED_APP_STATE_IN msgrequest */
 #define    MC_CMD_GET_LICENSED_APP_STATE_IN_LEN 4
 /* application ID to query (LICENSED_APP_ID_xxx) */
@@ -7792,6 +8212,8 @@
  */
 #define MC_CMD_LICENSED_APP_OP 0xf6
 
+#define MC_CMD_0xf6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
 /* MC_CMD_LICENSED_APP_OP_IN msgrequest */
 #define    MC_CMD_LICENSED_APP_OP_IN_LENMIN 8
 #define    MC_CMD_LICENSED_APP_OP_IN_LENMAX 252
@@ -7847,6 +8269,8 @@
  */
 #define MC_CMD_SET_PORT_SNIFF_CONFIG 0xf7
 
+#define MC_CMD_0xf7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_SET_PORT_SNIFF_CONFIG_IN msgrequest */
 #define    MC_CMD_SET_PORT_SNIFF_CONFIG_IN_LEN 16
 /* configuration flags */
@@ -7881,6 +8305,8 @@
  */
 #define MC_CMD_GET_PORT_SNIFF_CONFIG 0xf8
 
+#define MC_CMD_0xf8_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+
 /* MC_CMD_GET_PORT_SNIFF_CONFIG_IN msgrequest */
 #define    MC_CMD_GET_PORT_SNIFF_CONFIG_IN_LEN 0
 
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index fb19b70eac01..7f295c4d7b80 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -865,6 +865,7 @@ int efx_mcdi_set_mac(struct efx_nic *efx)
 
 	BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0);
 
+	/* This has no effect on EF10 */
 	ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
 			efx->net_dev->dev_addr);
 
@@ -923,6 +924,7 @@ enum efx_stats_action {
 static int efx_mcdi_mac_stats(struct efx_nic *efx,
 			      enum efx_stats_action action, int clear)
 {
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN);
 	int rc;
 	int change = action == EFX_STATS_PULL ? 0 : 1;
@@ -944,9 +946,14 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx,
 			      MAC_STATS_IN_PERIODIC_NOEVENT, 1,
 			      MAC_STATS_IN_PERIOD_MS, period);
 	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
-
-	rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
-			  NULL, 0, NULL);
+	MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, nic_data->vport_id);
+
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
+				NULL, 0, NULL);
+	/* Expect ENOENT if DMA queues have not been set up */
+	if (rc && (rc != -ENOENT || atomic_read(&efx->active_queues)))
+		efx_mcdi_display_error(efx, MC_CMD_MAC_STATS, sizeof(inbuf),
+				       NULL, 0, rc);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 325dd94bca46..d72f522bf9c3 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -25,6 +25,7 @@
 #include <linux/highmem.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/vmalloc.h>
 #include <linux/i2c.h>
 #include <linux/mtd/mtd.h>
@@ -793,7 +794,6 @@ union efx_multicast_hash {
 	efx_oword_t oword[EFX_MCAST_HASH_ENTRIES / sizeof(efx_oword_t) / 8];
 };
 
-struct efx_vf;
 struct vfdi_status;
 
 /**
@@ -897,7 +897,8 @@ struct vfdi_status;
  * @loopback_mode: Loopback status
  * @loopback_modes: Supported loopback mode bitmask
  * @loopback_selftest: Offline self-test private state
- * @filter_lock: Filter table lock
+ * @filter_sem: Filter table rw_semaphore, for freeing the table
+ * @filter_lock: Filter table lock, for mere content changes
  * @filter_state: Architecture-dependent filter table state
  * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS,
  *	indexed by filter ID
@@ -909,7 +910,6 @@ struct vfdi_status;
  *	completed (either success or failure). Not used when MCDI is used to
  *	flush receive queues.
  * @flush_wq: wait queue used by efx_nic_flush_queues() to wait for flush completions.
- * @vf: Array of &struct efx_vf objects.
  * @vf_count: Number of VFs intended to be enabled.
  * @vf_init_count: Number of VFs that have been fully initialised.
  * @vi_scale: log2 number of vnics per VF.
@@ -1040,6 +1040,7 @@ struct efx_nic {
 
 	void *loopback_selftest;
 
+	struct rw_semaphore filter_sem;
 	spinlock_t filter_lock;
 	void *filter_state;
 #ifdef CONFIG_RFS_ACCEL
@@ -1053,7 +1054,6 @@ struct efx_nic {
 	wait_queue_head_t flush_wq;
 
 #ifdef CONFIG_SFC_SRIOV
-	struct efx_vf *vf;
 	unsigned vf_count;
 	unsigned vf_init_count;
 	unsigned vi_scale;
@@ -1092,6 +1092,7 @@ struct efx_mtd_partition {
 
 /**
  * struct efx_nic_type - Efx device type definition
+ * @mem_bar: Get the memory BAR
  * @mem_map_size: Get memory BAR mapped size
  * @probe: Probe the controller
  * @remove: Free resources allocated by probe()
@@ -1204,6 +1205,7 @@ struct efx_mtd_partition {
  * @ptp_set_ts_config: Set hardware timestamp configuration.  The flags
  *	and tx_type will already have been validated but this operation
  *	must validate and update rx_filter.
+ * @set_mac_address: Set the MAC address of the device
  * @revision: Hardware architecture revision
  * @txd_ptr_tbl_base: TX descriptor ring base address
  * @rxd_ptr_tbl_base: RX descriptor ring base address
@@ -1226,6 +1228,8 @@ struct efx_mtd_partition {
  * @hwtstamp_filters: Mask of hardware timestamp filter types supported
  */
 struct efx_nic_type {
+	bool is_vf;
+	unsigned int mem_bar;
 	unsigned int (*mem_map_size)(struct efx_nic *efx);
 	int (*probe)(struct efx_nic *efx);
 	void (*remove)(struct efx_nic *efx);
@@ -1277,7 +1281,8 @@ struct efx_nic_type {
 	void (*tx_init)(struct efx_tx_queue *tx_queue);
 	void (*tx_remove)(struct efx_tx_queue *tx_queue);
 	void (*tx_write)(struct efx_tx_queue *tx_queue);
-	void (*rx_push_rss_config)(struct efx_nic *efx);
+	int (*rx_push_rss_config)(struct efx_nic *efx, bool user,
+				  const u32 *rx_indir_table);
 	int (*rx_probe)(struct efx_rx_queue *rx_queue);
 	void (*rx_init)(struct efx_rx_queue *rx_queue);
 	void (*rx_remove)(struct efx_rx_queue *rx_queue);
@@ -1330,11 +1335,28 @@ struct efx_nic_type {
 	int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
 	int (*ptp_set_ts_config)(struct efx_nic *efx,
 				 struct hwtstamp_config *init);
+	int (*sriov_configure)(struct efx_nic *efx, int num_vfs);
 	int (*sriov_init)(struct efx_nic *efx);
 	void (*sriov_fini)(struct efx_nic *efx);
-	void (*sriov_mac_address_changed)(struct efx_nic *efx);
 	bool (*sriov_wanted)(struct efx_nic *efx);
 	void (*sriov_reset)(struct efx_nic *efx);
+	void (*sriov_flr)(struct efx_nic *efx, unsigned vf_i);
+	int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, u8 *mac);
+	int (*sriov_set_vf_vlan)(struct efx_nic *efx, int vf_i, u16 vlan,
+				 u8 qos);
+	int (*sriov_set_vf_spoofchk)(struct efx_nic *efx, int vf_i,
+				     bool spoofchk);
+	int (*sriov_get_vf_config)(struct efx_nic *efx, int vf_i,
+				   struct ifla_vf_info *ivi);
+	int (*sriov_set_vf_link_state)(struct efx_nic *efx, int vf_i,
+				       int link_state);
+	int (*sriov_get_phys_port_id)(struct efx_nic *efx,
+				      struct netdev_phys_item_id *ppid);
+	int (*vswitching_probe)(struct efx_nic *efx);
+	int (*vswitching_restore)(struct efx_nic *efx);
+	void (*vswitching_remove)(struct efx_nic *efx);
+	int (*get_mac_address)(struct efx_nic *efx, unsigned char *perm_addr);
+	int (*set_mac_address)(struct efx_nic *efx);
 
 	int revision;
 	unsigned int txd_ptr_tbl_base;
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 93d10cbbd1cf..31ff9084d9a4 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -381,6 +381,7 @@ enum {
  * @efx: Pointer back to main interface structure
  * @wol_filter_id: Wake-on-LAN packet filter id
  * @stats: Hardware statistics
+ * @vf: Array of &struct siena_vf objects
  * @vf_buftbl_base: The zeroth buffer table index used to back VF queues.
  * @vfdi_status: Common VFDI status page to be dmad to VF address space.
  * @local_addr_list: List of local addresses. Protected by %local_lock.
@@ -394,6 +395,7 @@ struct siena_nic_data {
 	int wol_filter_id;
 	u64 stats[SIENA_STAT_COUNT];
 #ifdef CONFIG_SFC_SRIOV
+	struct siena_vf *vf;
 	struct efx_channel *vfdi_channel;
 	unsigned vf_buftbl_base;
 	struct efx_buffer vfdi_status;
@@ -405,59 +407,77 @@ struct siena_nic_data {
 };
 
 enum {
-	EF10_STAT_tx_bytes = GENERIC_STAT_COUNT,
-	EF10_STAT_tx_packets,
-	EF10_STAT_tx_pause,
-	EF10_STAT_tx_control,
-	EF10_STAT_tx_unicast,
-	EF10_STAT_tx_multicast,
-	EF10_STAT_tx_broadcast,
-	EF10_STAT_tx_lt64,
-	EF10_STAT_tx_64,
-	EF10_STAT_tx_65_to_127,
-	EF10_STAT_tx_128_to_255,
-	EF10_STAT_tx_256_to_511,
-	EF10_STAT_tx_512_to_1023,
-	EF10_STAT_tx_1024_to_15xx,
-	EF10_STAT_tx_15xx_to_jumbo,
-	EF10_STAT_rx_bytes,
-	EF10_STAT_rx_bytes_minus_good_bytes,
-	EF10_STAT_rx_good_bytes,
-	EF10_STAT_rx_bad_bytes,
-	EF10_STAT_rx_packets,
-	EF10_STAT_rx_good,
-	EF10_STAT_rx_bad,
-	EF10_STAT_rx_pause,
-	EF10_STAT_rx_control,
+	EF10_STAT_port_tx_bytes = GENERIC_STAT_COUNT,
+	EF10_STAT_port_tx_packets,
+	EF10_STAT_port_tx_pause,
+	EF10_STAT_port_tx_control,
+	EF10_STAT_port_tx_unicast,
+	EF10_STAT_port_tx_multicast,
+	EF10_STAT_port_tx_broadcast,
+	EF10_STAT_port_tx_lt64,
+	EF10_STAT_port_tx_64,
+	EF10_STAT_port_tx_65_to_127,
+	EF10_STAT_port_tx_128_to_255,
+	EF10_STAT_port_tx_256_to_511,
+	EF10_STAT_port_tx_512_to_1023,
+	EF10_STAT_port_tx_1024_to_15xx,
+	EF10_STAT_port_tx_15xx_to_jumbo,
+	EF10_STAT_port_rx_bytes,
+	EF10_STAT_port_rx_bytes_minus_good_bytes,
+	EF10_STAT_port_rx_good_bytes,
+	EF10_STAT_port_rx_bad_bytes,
+	EF10_STAT_port_rx_packets,
+	EF10_STAT_port_rx_good,
+	EF10_STAT_port_rx_bad,
+	EF10_STAT_port_rx_pause,
+	EF10_STAT_port_rx_control,
+	EF10_STAT_port_rx_unicast,
+	EF10_STAT_port_rx_multicast,
+	EF10_STAT_port_rx_broadcast,
+	EF10_STAT_port_rx_lt64,
+	EF10_STAT_port_rx_64,
+	EF10_STAT_port_rx_65_to_127,
+	EF10_STAT_port_rx_128_to_255,
+	EF10_STAT_port_rx_256_to_511,
+	EF10_STAT_port_rx_512_to_1023,
+	EF10_STAT_port_rx_1024_to_15xx,
+	EF10_STAT_port_rx_15xx_to_jumbo,
+	EF10_STAT_port_rx_gtjumbo,
+	EF10_STAT_port_rx_bad_gtjumbo,
+	EF10_STAT_port_rx_overflow,
+	EF10_STAT_port_rx_align_error,
+	EF10_STAT_port_rx_length_error,
+	EF10_STAT_port_rx_nodesc_drops,
+	EF10_STAT_port_rx_pm_trunc_bb_overflow,
+	EF10_STAT_port_rx_pm_discard_bb_overflow,
+	EF10_STAT_port_rx_pm_trunc_vfifo_full,
+	EF10_STAT_port_rx_pm_discard_vfifo_full,
+	EF10_STAT_port_rx_pm_trunc_qbb,
+	EF10_STAT_port_rx_pm_discard_qbb,
+	EF10_STAT_port_rx_pm_discard_mapping,
+	EF10_STAT_port_rx_dp_q_disabled_packets,
+	EF10_STAT_port_rx_dp_di_dropped_packets,
+	EF10_STAT_port_rx_dp_streaming_packets,
+	EF10_STAT_port_rx_dp_hlb_fetch,
+	EF10_STAT_port_rx_dp_hlb_wait,
 	EF10_STAT_rx_unicast,
+	EF10_STAT_rx_unicast_bytes,
 	EF10_STAT_rx_multicast,
+	EF10_STAT_rx_multicast_bytes,
 	EF10_STAT_rx_broadcast,
-	EF10_STAT_rx_lt64,
-	EF10_STAT_rx_64,
-	EF10_STAT_rx_65_to_127,
-	EF10_STAT_rx_128_to_255,
-	EF10_STAT_rx_256_to_511,
-	EF10_STAT_rx_512_to_1023,
-	EF10_STAT_rx_1024_to_15xx,
-	EF10_STAT_rx_15xx_to_jumbo,
-	EF10_STAT_rx_gtjumbo,
-	EF10_STAT_rx_bad_gtjumbo,
+	EF10_STAT_rx_broadcast_bytes,
+	EF10_STAT_rx_bad,
+	EF10_STAT_rx_bad_bytes,
 	EF10_STAT_rx_overflow,
-	EF10_STAT_rx_align_error,
-	EF10_STAT_rx_length_error,
-	EF10_STAT_rx_nodesc_drops,
-	EF10_STAT_rx_pm_trunc_bb_overflow,
-	EF10_STAT_rx_pm_discard_bb_overflow,
-	EF10_STAT_rx_pm_trunc_vfifo_full,
-	EF10_STAT_rx_pm_discard_vfifo_full,
-	EF10_STAT_rx_pm_trunc_qbb,
-	EF10_STAT_rx_pm_discard_qbb,
-	EF10_STAT_rx_pm_discard_mapping,
-	EF10_STAT_rx_dp_q_disabled_packets,
-	EF10_STAT_rx_dp_di_dropped_packets,
-	EF10_STAT_rx_dp_streaming_packets,
-	EF10_STAT_rx_dp_hlb_fetch,
-	EF10_STAT_rx_dp_hlb_wait,
+	EF10_STAT_tx_unicast,
+	EF10_STAT_tx_unicast_bytes,
+	EF10_STAT_tx_multicast,
+	EF10_STAT_tx_multicast_bytes,
+	EF10_STAT_tx_broadcast,
+	EF10_STAT_tx_broadcast_bytes,
+	EF10_STAT_tx_bad,
+	EF10_STAT_tx_bad_bytes,
+	EF10_STAT_tx_overflow,
 	EF10_STAT_COUNT
 };
 
@@ -483,12 +503,21 @@ enum {
  * @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC
  *	reboot
  * @rx_rss_context: Firmware handle for our RSS context
+ * @rx_rss_context_exclusive: Whether our RSS context is exclusive or shared
  * @stats: Hardware statistics
  * @workaround_35388: Flag: firmware supports workaround for bug 35388
  * @must_check_datapath_caps: Flag: @datapath_caps needs to be revalidated
  *	after MC reboot
  * @datapath_caps: Capabilities of datapath firmware (FLAGS1 field of
  *	%MC_CMD_GET_CAPABILITIES response)
+ * @rx_dpcpu_fw_id: Firmware ID of the RxDPCPU
+ * @tx_dpcpu_fw_id: Firmware ID of the TxDPCPU
+ * @vport_id: The function's vport ID, only relevant for PFs
+ * @must_probe_vswitching: Flag: vswitching has yet to be setup after MC reboot
+ * @pf_index: The number for this PF, or the parent PF if this is a VF
+#ifdef CONFIG_SFC_SRIOV
+ * @vf: Pointer to VF data structure
+#endif
  */
 struct efx_ef10_nic_data {
 	struct efx_buffer mcdi_buf;
@@ -503,126 +532,27 @@ struct efx_ef10_nic_data {
 	unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT];
 	bool must_restore_piobufs;
 	u32 rx_rss_context;
+	bool rx_rss_context_exclusive;
 	u64 stats[EF10_STAT_COUNT];
 	bool workaround_35388;
 	bool must_check_datapath_caps;
 	u32 datapath_caps;
-};
-
-/*
- * On the SFC9000 family each port is associated with 1 PCI physical
- * function (PF) handled by sfc and a configurable number of virtual
- * functions (VFs) that may be handled by some other driver, often in
- * a VM guest.  The queue pointer registers are mapped in both PF and
- * VF BARs such that an 8K region provides access to a single RX, TX
- * and event queue (collectively a Virtual Interface, VI or VNIC).
- *
- * The PF has access to all 1024 VIs while VFs are mapped to VIs
- * according to VI_BASE and VI_SCALE: VF i has access to VIs numbered
- * in range [VI_BASE + i << VI_SCALE, VI_BASE + i + 1 << VI_SCALE).
- * The number of VIs and the VI_SCALE value are configurable but must
- * be established at boot time by firmware.
- */
-
-/* Maximum VI_SCALE parameter supported by Siena */
-#define EFX_VI_SCALE_MAX 6
-/* Base VI to use for SR-IOV. Must be aligned to (1 << EFX_VI_SCALE_MAX),
- * so this is the smallest allowed value. */
-#define EFX_VI_BASE 128U
-/* Maximum number of VFs allowed */
-#define EFX_VF_COUNT_MAX 127
-/* Limit EVQs on VFs to be only 8k to reduce buffer table reservation */
-#define EFX_MAX_VF_EVQ_SIZE 8192UL
-/* The number of buffer table entries reserved for each VI on a VF */
-#define EFX_VF_BUFTBL_PER_VI					\
-	((EFX_MAX_VF_EVQ_SIZE + 2 * EFX_MAX_DMAQ_SIZE) *	\
-	 sizeof(efx_qword_t) / EFX_BUF_SIZE)
-
+	unsigned int rx_dpcpu_fw_id;
+	unsigned int tx_dpcpu_fw_id;
+	unsigned int vport_id;
+	bool must_probe_vswitching;
+	unsigned int pf_index;
+	u8 port_id[ETH_ALEN];
 #ifdef CONFIG_SFC_SRIOV
-
-/* SIENA */
-static inline bool efx_siena_sriov_wanted(struct efx_nic *efx)
-{
-	return efx->vf_count != 0;
-}
-
-static inline bool efx_siena_sriov_enabled(struct efx_nic *efx)
-{
-	return efx->vf_init_count != 0;
-}
-
-static inline unsigned int efx_vf_size(struct efx_nic *efx)
-{
-	return 1 << efx->vi_scale;
-}
+	unsigned int vf_index;
+	struct ef10_vf *vf;
+#endif
+	u8 vport_mac[ETH_ALEN];
+};
 
 int efx_init_sriov(void);
-void efx_siena_sriov_probe(struct efx_nic *efx);
-int efx_siena_sriov_init(struct efx_nic *efx);
-void efx_siena_sriov_mac_address_changed(struct efx_nic *efx);
-void efx_siena_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event);
-void efx_siena_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event);
-void efx_siena_sriov_event(struct efx_channel *channel, efx_qword_t *event);
-void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq);
-void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr);
-void efx_siena_sriov_reset(struct efx_nic *efx);
-void efx_siena_sriov_fini(struct efx_nic *efx);
 void efx_fini_sriov(void);
 
-/* EF10 */
-static inline bool efx_ef10_sriov_wanted(struct efx_nic *efx) { return false; }
-static inline int efx_ef10_sriov_init(struct efx_nic *efx) { return -EOPNOTSUPP; }
-static inline void efx_ef10_sriov_mac_address_changed(struct efx_nic *efx) {}
-static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {}
-static inline void efx_ef10_sriov_fini(struct efx_nic *efx) {}
-
-#else
-
-/* SIENA */
-static inline bool efx_siena_sriov_wanted(struct efx_nic *efx) { return false; }
-static inline bool efx_siena_sriov_enabled(struct efx_nic *efx) { return false; }
-static inline unsigned int efx_vf_size(struct efx_nic *efx) { return 0; }
-static inline int efx_init_sriov(void) { return 0; }
-static inline void efx_siena_sriov_probe(struct efx_nic *efx) {}
-static inline int efx_siena_sriov_init(struct efx_nic *efx) { return -EOPNOTSUPP; }
-static inline void efx_siena_sriov_mac_address_changed(struct efx_nic *efx) {}
-static inline void efx_siena_sriov_tx_flush_done(struct efx_nic *efx,
-						 efx_qword_t *event) {}
-static inline void efx_siena_sriov_rx_flush_done(struct efx_nic *efx,
-						 efx_qword_t *event) {}
-static inline void efx_siena_sriov_event(struct efx_channel *channel,
-					 efx_qword_t *event) {}
-static inline void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx,
-						  unsigned dmaq) {}
-static inline void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr) {}
-static inline void efx_siena_sriov_reset(struct efx_nic *efx) {}
-static inline void efx_siena_sriov_fini(struct efx_nic *efx) {}
-static inline void efx_fini_sriov(void) {}
-
-/* EF10 */
-static inline bool efx_ef10_sriov_wanted(struct efx_nic *efx) { return false; }
-static inline int efx_ef10_sriov_init(struct efx_nic *efx) { return -EOPNOTSUPP; }
-static inline void efx_ef10_sriov_mac_address_changed(struct efx_nic *efx) {}
-static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {}
-static inline void efx_ef10_sriov_fini(struct efx_nic *efx) {}
-
-#endif
-
-/* FALCON */
-static inline bool efx_falcon_sriov_wanted(struct efx_nic *efx) { return false; }
-static inline int efx_falcon_sriov_init(struct efx_nic *efx) { return -EOPNOTSUPP; }
-static inline void efx_falcon_sriov_mac_address_changed(struct efx_nic *efx) {}
-static inline void efx_falcon_sriov_reset(struct efx_nic *efx) {}
-static inline void efx_falcon_sriov_fini(struct efx_nic *efx) {}
-
-int efx_siena_sriov_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
-int efx_siena_sriov_set_vf_vlan(struct net_device *dev, int vf,
-				u16 vlan, u8 qos);
-int efx_siena_sriov_get_vf_config(struct net_device *dev, int vf,
-				  struct ifla_vf_info *ivf);
-int efx_siena_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
-				    bool spoofchk);
-
 struct ethtool_ts_info;
 int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel);
 void efx_ptp_defer_probe_with_channel(struct efx_nic *efx);
@@ -654,6 +584,7 @@ extern const struct efx_nic_type falcon_a1_nic_type;
 extern const struct efx_nic_type falcon_b0_nic_type;
 extern const struct efx_nic_type siena_a0_nic_type;
 extern const struct efx_nic_type efx_hunt_a0_nic_type;
+extern const struct efx_nic_type efx_hunt_a0_vf_nic_type;
 
 /**************************************************************************
  *
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index a2e9aee05cdd..ad62615a93dc 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -306,7 +306,7 @@ struct efx_ptp_data {
 	struct work_struct pps_work;
 	struct workqueue_struct *pps_workwq;
 	bool nic_ts_enabled;
-	MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX);
+	_MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX);
 
 	unsigned int good_syncs;
 	unsigned int fast_syncs;
@@ -389,11 +389,8 @@ size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats)
 	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
 	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
 			  outbuf, sizeof(outbuf), NULL);
-	if (rc) {
-		netif_err(efx, hw, efx->net_dev,
-			  "MC_CMD_PTP_OP_STATUS failed (%d)\n", rc);
+	if (rc)
 		memset(outbuf, 0, sizeof(outbuf));
-	}
 	efx_nic_update_stats(efx_ptp_stat_desc, PTP_STAT_COUNT,
 			     efx_ptp_stat_mask,
 			     stats, _MCDI_PTR(outbuf, 0), false);
@@ -490,14 +487,20 @@ static int efx_ptp_get_attributes(struct efx_nic *efx)
 	 */
 	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_GET_ATTRIBUTES);
 	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
-	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &out_len);
-	if (rc == 0)
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+				outbuf, sizeof(outbuf), &out_len);
+	if (rc == 0) {
 		fmt = MCDI_DWORD(outbuf, PTP_OUT_GET_ATTRIBUTES_TIME_FORMAT);
-	else if (rc == -EINVAL)
+	} else if (rc == -EINVAL) {
 		fmt = MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS;
-	else
+	} else if (rc == -EPERM) {
+		netif_info(efx, probe, efx->net_dev, "no PTP support\n");
+		return rc;
+	} else {
+		efx_mcdi_display_error(efx, MC_CMD_PTP, sizeof(inbuf),
+				       outbuf, sizeof(outbuf), rc);
 		return rc;
+	}
 
 	if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION) {
 		ptp->ns_to_nic_time = efx_ptp_ns_to_s27;
@@ -541,8 +544,8 @@ static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx)
 		       MC_CMD_PTP_OP_GET_TIMESTAMP_CORRECTIONS);
 	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), NULL);
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+				outbuf, sizeof(outbuf), NULL);
 	if (rc == 0) {
 		efx->ptp_data->ts_corrections.tx = MCDI_DWORD(outbuf,
 			PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT);
@@ -558,6 +561,8 @@ static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx)
 		efx->ptp_data->ts_corrections.pps_out = 0;
 		efx->ptp_data->ts_corrections.pps_in = 0;
 	} else {
+		efx_mcdi_display_error(efx, MC_CMD_PTP, sizeof(inbuf), outbuf,
+				       sizeof(outbuf), rc);
 		return rc;
 	}
 
@@ -568,7 +573,7 @@ static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx)
 static int efx_ptp_enable(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ENABLE_LEN);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	int rc;
 
 	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE);
@@ -596,7 +601,7 @@ static int efx_ptp_enable(struct efx_nic *efx)
 static int efx_ptp_disable(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_DISABLE_LEN);
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	int rc;
 
 	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE);
@@ -604,7 +609,12 @@ static int efx_ptp_disable(struct efx_nic *efx)
 	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
 				outbuf, sizeof(outbuf), NULL);
 	rc = (rc == -EALREADY) ? 0 : rc;
-	if (rc)
+	/* If we get ENOSYS, the NIC doesn't support PTP, and thus this function
+	 * should only have been called during probe.
+	 */
+	if (rc == -ENOSYS || rc == -EPERM)
+		netif_info(efx, probe, efx->net_dev, "no PTP support\n");
+	else if (rc)
 		efx_mcdi_display_error(efx, MC_CMD_PTP,
 				       MC_CMD_PTP_IN_DISABLE_LEN,
 				       outbuf, sizeof(outbuf), rc);
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index c0ad95d2f63d..809ea4610a77 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -224,12 +224,17 @@ static void efx_unmap_rx_buffer(struct efx_nic *efx,
 	}
 }
 
-static void efx_free_rx_buffer(struct efx_rx_buffer *rx_buf)
+static void efx_free_rx_buffers(struct efx_rx_queue *rx_queue,
+				struct efx_rx_buffer *rx_buf,
+				unsigned int num_bufs)
 {
-	if (rx_buf->page) {
-		put_page(rx_buf->page);
-		rx_buf->page = NULL;
-	}
+	do {
+		if (rx_buf->page) {
+			put_page(rx_buf->page);
+			rx_buf->page = NULL;
+		}
+		rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+	} while (--num_bufs);
 }
 
 /* Attempt to recycle the page if there is an RX recycle ring; the page can
@@ -278,7 +283,7 @@ static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
 	/* If this is the last buffer in a page, unmap and free it. */
 	if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
 		efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
-		efx_free_rx_buffer(rx_buf);
+		efx_free_rx_buffers(rx_queue, rx_buf, 1);
 	}
 	rx_buf->page = NULL;
 }
@@ -304,10 +309,7 @@ static void efx_discard_rx_packet(struct efx_channel *channel,
 
 	efx_recycle_rx_pages(channel, rx_buf, n_frags);
 
-	do {
-		efx_free_rx_buffer(rx_buf);
-		rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
-	} while (--n_frags);
+	efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
 }
 
 /**
@@ -431,11 +433,10 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
 
 	skb = napi_get_frags(napi);
 	if (unlikely(!skb)) {
-		while (n_frags--) {
-			put_page(rx_buf->page);
-			rx_buf->page = NULL;
-			rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
-		}
+		struct efx_rx_queue *rx_queue;
+
+		rx_queue = efx_channel_get_rx_queue(channel);
+		efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
 		return;
 	}
 
@@ -622,7 +623,10 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 
 	skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len);
 	if (unlikely(skb == NULL)) {
-		efx_free_rx_buffer(rx_buf);
+		struct efx_rx_queue *rx_queue;
+
+		rx_queue = efx_channel_get_rx_queue(channel);
+		efx_free_rx_buffers(rx_queue, rx_buf, n_frags);
 		return;
 	}
 	skb_record_rx_queue(skb, channel->rx_queue.core_index);
@@ -661,8 +665,12 @@ void __efx_rx_packet(struct efx_channel *channel)
 	 * loopback layer, and free the rx_buf here
 	 */
 	if (unlikely(efx->loopback_selftest)) {
+		struct efx_rx_queue *rx_queue;
+
 		efx_loopback_rx_packet(efx, eh, rx_buf->len);
-		efx_free_rx_buffer(rx_buf);
+		rx_queue = efx_channel_get_rx_queue(channel);
+		efx_free_rx_buffers(rx_queue, rx_buf,
+				    channel->rx_pkt_n_frags);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index f12c811938d2..b323b9167526 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -25,6 +25,7 @@
 #include "mcdi.h"
 #include "mcdi_pcol.h"
 #include "selftest.h"
+#include "siena_sriov.h"
 
 /* Hardware control for SFC9000 family including SFL9021 (aka Siena). */
 
@@ -306,7 +307,9 @@ static int siena_probe_nic(struct efx_nic *efx)
 	if (rc)
 		goto fail5;
 
+#ifdef CONFIG_SFC_SRIOV
 	efx_siena_sriov_probe(efx);
+#endif
 	efx_ptp_defer_probe_with_channel(efx);
 
 	return 0;
@@ -321,7 +324,8 @@ fail1:
 	return rc;
 }
 
-static void siena_rx_push_rss_config(struct efx_nic *efx)
+static int siena_rx_push_rss_config(struct efx_nic *efx, bool user,
+				    const u32 *rx_indir_table)
 {
 	efx_oword_t temp;
 
@@ -343,7 +347,11 @@ static void siena_rx_push_rss_config(struct efx_nic *efx)
 	       FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
 	efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
 
+	memcpy(efx->rx_indir_table, rx_indir_table,
+	       sizeof(efx->rx_indir_table));
 	efx_farch_rx_push_indir_table(efx);
+
+	return 0;
 }
 
 /* This call performs hardware-specific global initialisation, such as
@@ -386,7 +394,7 @@ static int siena_init_nic(struct efx_nic *efx)
 			    EFX_RX_USR_BUF_SIZE >> 5);
 	efx_writeo(efx, &temp, FR_AZ_RX_CFG);
 
-	siena_rx_push_rss_config(efx);
+	siena_rx_push_rss_config(efx, false, efx->rx_indir_table);
 
 	/* Enable event logging */
 	rc = efx_mcdi_log_ctrl(efx, true, false, 0);
@@ -909,6 +917,8 @@ fail:
  */
 
 const struct efx_nic_type siena_a0_nic_type = {
+	.is_vf = false,
+	.mem_bar = EFX_MEM_BAR,
 	.mem_map_size = siena_mem_map_size,
 	.probe = siena_probe_nic,
 	.remove = siena_remove_nic,
@@ -996,11 +1006,22 @@ const struct efx_nic_type siena_a0_nic_type = {
 #endif
 	.ptp_write_host_time = siena_ptp_write_host_time,
 	.ptp_set_ts_config = siena_ptp_set_ts_config,
+#ifdef CONFIG_SFC_SRIOV
+	.sriov_configure = efx_siena_sriov_configure,
 	.sriov_init = efx_siena_sriov_init,
 	.sriov_fini = efx_siena_sriov_fini,
-	.sriov_mac_address_changed = efx_siena_sriov_mac_address_changed,
 	.sriov_wanted = efx_siena_sriov_wanted,
 	.sriov_reset = efx_siena_sriov_reset,
+	.sriov_flr = efx_siena_sriov_flr,
+	.sriov_set_vf_mac = efx_siena_sriov_set_vf_mac,
+	.sriov_set_vf_vlan = efx_siena_sriov_set_vf_vlan,
+	.sriov_set_vf_spoofchk = efx_siena_sriov_set_vf_spoofchk,
+	.sriov_get_vf_config = efx_siena_sriov_get_vf_config,
+	.vswitching_probe = efx_port_dummy_op_int,
+	.vswitching_restore = efx_port_dummy_op_int,
+	.vswitching_remove = efx_port_dummy_op_void,
+	.set_mac_address = efx_siena_sriov_mac_address_changed,
+#endif
 
 	.revision = EFX_REV_SIENA_A0,
 	.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index fe83430796fd..da7b94f34604 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -16,6 +16,7 @@
 #include "filter.h"
 #include "mcdi_pcol.h"
 #include "farch_regs.h"
+#include "siena_sriov.h"
 #include "vfdi.h"
 
 /* Number of longs required to track all the VIs in a VF */
@@ -38,7 +39,7 @@ enum efx_vf_tx_filter_mode {
 };
 
 /**
- * struct efx_vf - Back-end resource and protocol state for a PCI VF
+ * struct siena_vf - Back-end resource and protocol state for a PCI VF
  * @efx: The Efx NIC owning this VF
  * @pci_rid: The PCI requester ID for this VF
  * @pci_name: The PCI name (formatted address) of this VF
@@ -83,7 +84,7 @@ enum efx_vf_tx_filter_mode {
  * @rxq_retry_count: Number of receive queues in @rxq_retry_mask.
  * @reset_work: Work item to schedule a VF reset.
  */
-struct efx_vf {
+struct siena_vf {
 	struct efx_nic *efx;
 	unsigned int pci_rid;
 	char pci_name[13]; /* dddd:bb:dd.f */
@@ -189,7 +190,7 @@ MODULE_PARM_DESC(max_vfs,
  */
 static struct workqueue_struct *vfdi_workqueue;
 
-static unsigned abs_index(struct efx_vf *vf, unsigned index)
+static unsigned abs_index(struct siena_vf *vf, unsigned index)
 {
 	return EFX_VI_BASE + vf->index * efx_vf_size(vf->efx) + index;
 }
@@ -207,8 +208,8 @@ static int efx_siena_sriov_cmd(struct efx_nic *efx, bool enable,
 	MCDI_SET_DWORD(inbuf, SRIOV_IN_VI_BASE, EFX_VI_BASE);
 	MCDI_SET_DWORD(inbuf, SRIOV_IN_VF_COUNT, efx->vf_count);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_SRIOV, inbuf, MC_CMD_SRIOV_IN_LEN,
-			  outbuf, MC_CMD_SRIOV_OUT_LEN, &outlen);
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_SRIOV, inbuf, MC_CMD_SRIOV_IN_LEN,
+				outbuf, MC_CMD_SRIOV_OUT_LEN, &outlen);
 	if (rc)
 		return rc;
 	if (outlen < MC_CMD_SRIOV_OUT_LEN)
@@ -299,7 +300,7 @@ out:
 /* The TX filter is entirely controlled by this driver, and is modified
  * underneath the feet of the VF
  */
-static void efx_siena_sriov_reset_tx_filter(struct efx_vf *vf)
+static void efx_siena_sriov_reset_tx_filter(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct efx_filter_spec filter;
@@ -343,7 +344,7 @@ static void efx_siena_sriov_reset_tx_filter(struct efx_vf *vf)
 }
 
 /* The RX filter is managed here on behalf of the VF driver */
-static void efx_siena_sriov_reset_rx_filter(struct efx_vf *vf)
+static void efx_siena_sriov_reset_rx_filter(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct efx_filter_spec filter;
@@ -382,7 +383,7 @@ static void efx_siena_sriov_reset_rx_filter(struct efx_vf *vf)
 	}
 }
 
-static void __efx_siena_sriov_update_vf_addr(struct efx_vf *vf)
+static void __efx_siena_sriov_update_vf_addr(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct siena_nic_data *nic_data = efx->nic_data;
@@ -397,7 +398,7 @@ static void __efx_siena_sriov_update_vf_addr(struct efx_vf *vf)
  * local_page_list, either by acquiring local_lock or by running from
  * efx_siena_sriov_peer_work()
  */
-static void __efx_siena_sriov_push_vf_status(struct efx_vf *vf)
+static void __efx_siena_sriov_push_vf_status(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct siena_nic_data *nic_data = efx->nic_data;
@@ -509,8 +510,9 @@ static bool bad_buf_count(unsigned buf_count, unsigned max_entry_count)
  * Optionally set VF index and VI index within the VF.
  */
 static bool map_vi_index(struct efx_nic *efx, unsigned abs_index,
-			 struct efx_vf **vf_out, unsigned *rel_index_out)
+			 struct siena_vf **vf_out, unsigned *rel_index_out)
 {
+	struct siena_nic_data *nic_data = efx->nic_data;
 	unsigned vf_i;
 
 	if (abs_index < EFX_VI_BASE)
@@ -520,13 +522,13 @@ static bool map_vi_index(struct efx_nic *efx, unsigned abs_index,
 		return true;
 
 	if (vf_out)
-		*vf_out = efx->vf + vf_i;
+		*vf_out = nic_data->vf + vf_i;
 	if (rel_index_out)
 		*rel_index_out = abs_index % efx_vf_size(efx);
 	return false;
 }
 
-static int efx_vfdi_init_evq(struct efx_vf *vf)
+static int efx_vfdi_init_evq(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct vfdi_req *req = vf->buf.addr;
@@ -567,7 +569,7 @@ static int efx_vfdi_init_evq(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-static int efx_vfdi_init_rxq(struct efx_vf *vf)
+static int efx_vfdi_init_rxq(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct vfdi_req *req = vf->buf.addr;
@@ -608,7 +610,7 @@ static int efx_vfdi_init_rxq(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-static int efx_vfdi_init_txq(struct efx_vf *vf)
+static int efx_vfdi_init_txq(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct vfdi_req *req = vf->buf.addr;
@@ -655,7 +657,7 @@ static int efx_vfdi_init_txq(struct efx_vf *vf)
 }
 
 /* Returns true when efx_vfdi_fini_all_queues should wake */
-static bool efx_vfdi_flush_wake(struct efx_vf *vf)
+static bool efx_vfdi_flush_wake(struct siena_vf *vf)
 {
 	/* Ensure that all updates are visible to efx_vfdi_fini_all_queues() */
 	smp_mb();
@@ -664,7 +666,7 @@ static bool efx_vfdi_flush_wake(struct efx_vf *vf)
 		atomic_read(&vf->rxq_retry_count);
 }
 
-static void efx_vfdi_flush_clear(struct efx_vf *vf)
+static void efx_vfdi_flush_clear(struct siena_vf *vf)
 {
 	memset(vf->txq_mask, 0, sizeof(vf->txq_mask));
 	vf->txq_count = 0;
@@ -674,7 +676,7 @@ static void efx_vfdi_flush_clear(struct efx_vf *vf)
 	atomic_set(&vf->rxq_retry_count, 0);
 }
 
-static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
+static int efx_vfdi_fini_all_queues(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	efx_oword_t reg;
@@ -757,7 +759,7 @@ static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
 	return timeout ? 0 : VFDI_RC_ETIMEDOUT;
 }
 
-static int efx_vfdi_insert_filter(struct efx_vf *vf)
+static int efx_vfdi_insert_filter(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct siena_nic_data *nic_data = efx->nic_data;
@@ -789,7 +791,7 @@ static int efx_vfdi_insert_filter(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-static int efx_vfdi_remove_all_filters(struct efx_vf *vf)
+static int efx_vfdi_remove_all_filters(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct siena_nic_data *nic_data = efx->nic_data;
@@ -801,7 +803,7 @@ static int efx_vfdi_remove_all_filters(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-static int efx_vfdi_set_status_page(struct efx_vf *vf)
+static int efx_vfdi_set_status_page(struct siena_vf *vf)
 {
 	struct efx_nic *efx = vf->efx;
 	struct siena_nic_data *nic_data = efx->nic_data;
@@ -846,7 +848,7 @@ static int efx_vfdi_set_status_page(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-static int efx_vfdi_clear_status_page(struct efx_vf *vf)
+static int efx_vfdi_clear_status_page(struct siena_vf *vf)
 {
 	mutex_lock(&vf->status_lock);
 	vf->status_addr = 0;
@@ -855,7 +857,7 @@ static int efx_vfdi_clear_status_page(struct efx_vf *vf)
 	return VFDI_RC_SUCCESS;
 }
 
-typedef int (*efx_vfdi_op_t)(struct efx_vf *vf);
+typedef int (*efx_vfdi_op_t)(struct siena_vf *vf);
 
 static const efx_vfdi_op_t vfdi_ops[VFDI_OP_LIMIT] = {
 	[VFDI_OP_INIT_EVQ] = efx_vfdi_init_evq,
@@ -870,7 +872,7 @@ static const efx_vfdi_op_t vfdi_ops[VFDI_OP_LIMIT] = {
 
 static void efx_siena_sriov_vfdi(struct work_struct *work)
 {
-	struct efx_vf *vf = container_of(work, struct efx_vf, req);
+	struct siena_vf *vf = container_of(work, struct siena_vf, req);
 	struct efx_nic *efx = vf->efx;
 	struct vfdi_req *req = vf->buf.addr;
 	struct efx_memcpy_req copy[2];
@@ -936,7 +938,8 @@ static void efx_siena_sriov_vfdi(struct work_struct *work)
  * event ring in guest memory with VFDI reset events, then (re-initialise) the
  * event queue to raise an interrupt. The guest driver will then recover.
  */
-static void efx_siena_sriov_reset_vf(struct efx_vf *vf,
+
+static void efx_siena_sriov_reset_vf(struct siena_vf *vf,
 				     struct efx_buffer *buffer)
 {
 	struct efx_nic *efx = vf->efx;
@@ -1006,7 +1009,7 @@ static void efx_siena_sriov_reset_vf(struct efx_vf *vf,
 
 static void efx_siena_sriov_reset_vf_work(struct work_struct *work)
 {
-	struct efx_vf *vf = container_of(work, struct efx_vf, req);
+	struct siena_vf *vf = container_of(work, struct siena_vf, req);
 	struct efx_nic *efx = vf->efx;
 	struct efx_buffer buf;
 
@@ -1055,8 +1058,10 @@ void efx_siena_sriov_probe(struct efx_nic *efx)
 	if (!max_vfs)
 		return;
 
-	if (efx_siena_sriov_cmd(efx, false, &efx->vi_scale, &count))
+	if (efx_siena_sriov_cmd(efx, false, &efx->vi_scale, &count)) {
+		netif_info(efx, probe, efx->net_dev, "no SR-IOV VFs probed\n");
 		return;
+	}
 	if (count > 0 && count > max_vfs)
 		count = max_vfs;
 
@@ -1077,7 +1082,7 @@ static void efx_siena_sriov_peer_work(struct work_struct *data)
 						       peer_work);
 	struct efx_nic *efx = nic_data->efx;
 	struct vfdi_status *vfdi_status = nic_data->vfdi_status.addr;
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	struct efx_local_addr *local_addr;
 	struct vfdi_endpoint *peer;
 	struct efx_endpoint_page *epp;
@@ -1099,7 +1104,7 @@ static void efx_siena_sriov_peer_work(struct work_struct *data)
 	peer_space = ARRAY_SIZE(vfdi_status->peers) - 1;
 	peer_count = 1;
 	for (pos = 0; pos < efx->vf_count; ++pos) {
-		vf = efx->vf + pos;
+		vf = nic_data->vf + pos;
 
 		mutex_lock(&vf->status_lock);
 		if (vf->rx_filtering && !is_zero_ether_addr(vf->addr.mac_addr)) {
@@ -1155,7 +1160,7 @@ static void efx_siena_sriov_peer_work(struct work_struct *data)
 
 	/* Finally, push the pages */
 	for (pos = 0; pos < efx->vf_count; ++pos) {
-		vf = efx->vf + pos;
+		vf = nic_data->vf + pos;
 
 		mutex_lock(&vf->status_lock);
 		if (vf->status_addr)
@@ -1190,14 +1195,16 @@ static void efx_siena_sriov_free_local(struct efx_nic *efx)
 static int efx_siena_sriov_vf_alloc(struct efx_nic *efx)
 {
 	unsigned index;
-	struct efx_vf *vf;
+	struct siena_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
 
-	efx->vf = kzalloc(sizeof(struct efx_vf) * efx->vf_count, GFP_KERNEL);
-	if (!efx->vf)
+	nic_data->vf = kcalloc(efx->vf_count, sizeof(*nic_data->vf),
+			       GFP_KERNEL);
+	if (!nic_data->vf)
 		return -ENOMEM;
 
 	for (index = 0; index < efx->vf_count; ++index) {
-		vf = efx->vf + index;
+		vf = nic_data->vf + index;
 
 		vf->efx = efx;
 		vf->index = index;
@@ -1216,11 +1223,12 @@ static int efx_siena_sriov_vf_alloc(struct efx_nic *efx)
 
 static void efx_siena_sriov_vfs_fini(struct efx_nic *efx)
 {
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 	unsigned int pos;
 
 	for (pos = 0; pos < efx->vf_count; ++pos) {
-		vf = efx->vf + pos;
+		vf = nic_data->vf + pos;
 
 		efx_nic_free_buffer(efx, &vf->buf);
 		kfree(vf->peer_page_addrs);
@@ -1237,7 +1245,7 @@ static int efx_siena_sriov_vfs_init(struct efx_nic *efx)
 	struct siena_nic_data *nic_data = efx->nic_data;
 	unsigned index, devfn, sriov, buftbl_base;
 	u16 offset, stride;
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	int rc;
 
 	sriov = pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV);
@@ -1250,7 +1258,7 @@ static int efx_siena_sriov_vfs_init(struct efx_nic *efx)
 	buftbl_base = nic_data->vf_buftbl_base;
 	devfn = pci_dev->devfn + offset;
 	for (index = 0; index < efx->vf_count; ++index) {
-		vf = efx->vf + index;
+		vf = nic_data->vf + index;
 
 		/* Reserve buffer entries */
 		vf->buftbl_base = buftbl_base;
@@ -1350,7 +1358,7 @@ fail_pci:
 fail_vfs:
 	cancel_work_sync(&nic_data->peer_work);
 	efx_siena_sriov_free_local(efx);
-	kfree(efx->vf);
+	kfree(nic_data->vf);
 fail_alloc:
 	efx_nic_free_buffer(efx, &nic_data->vfdi_status);
 fail_status:
@@ -1361,7 +1369,7 @@ fail_cmd:
 
 void efx_siena_sriov_fini(struct efx_nic *efx)
 {
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	unsigned int pos;
 	struct siena_nic_data *nic_data = efx->nic_data;
 
@@ -1377,7 +1385,7 @@ void efx_siena_sriov_fini(struct efx_nic *efx)
 
 	/* Flush all reconfiguration work */
 	for (pos = 0; pos < efx->vf_count; ++pos) {
-		vf = efx->vf + pos;
+		vf = nic_data->vf + pos;
 		cancel_work_sync(&vf->req);
 		cancel_work_sync(&vf->reset_work);
 	}
@@ -1388,7 +1396,7 @@ void efx_siena_sriov_fini(struct efx_nic *efx)
 	/* Tear down back-end state */
 	efx_siena_sriov_vfs_fini(efx);
 	efx_siena_sriov_free_local(efx);
-	kfree(efx->vf);
+	kfree(nic_data->vf);
 	efx_nic_free_buffer(efx, &nic_data->vfdi_status);
 	efx_siena_sriov_cmd(efx, false, NULL, NULL);
 }
@@ -1396,7 +1404,7 @@ void efx_siena_sriov_fini(struct efx_nic *efx)
 void efx_siena_sriov_event(struct efx_channel *channel, efx_qword_t *event)
 {
 	struct efx_nic *efx = channel->efx;
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	unsigned qid, seq, type, data;
 
 	qid = EFX_QWORD_FIELD(*event, FSF_CZ_USER_QID);
@@ -1452,11 +1460,12 @@ error:
 
 void efx_siena_sriov_flr(struct efx_nic *efx, unsigned vf_i)
 {
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 
 	if (vf_i > efx->vf_init_count)
 		return;
-	vf = efx->vf + vf_i;
+	vf = nic_data->vf + vf_i;
 	netif_info(efx, hw, efx->net_dev,
 		   "FLR on VF %s\n", vf->pci_name);
 
@@ -1467,21 +1476,23 @@ void efx_siena_sriov_flr(struct efx_nic *efx, unsigned vf_i)
 	vf->evq0_count = 0;
 }
 
-void efx_siena_sriov_mac_address_changed(struct efx_nic *efx)
+int efx_siena_sriov_mac_address_changed(struct efx_nic *efx)
 {
 	struct siena_nic_data *nic_data = efx->nic_data;
 	struct vfdi_status *vfdi_status = nic_data->vfdi_status.addr;
 
 	if (!efx->vf_init_count)
-		return;
+		return 0;
 	ether_addr_copy(vfdi_status->peers[0].mac_addr,
 			efx->net_dev->dev_addr);
 	queue_work(vfdi_workqueue, &nic_data->peer_work);
+
+	return 0;
 }
 
 void efx_siena_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
 {
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	unsigned queue, qid;
 
 	queue = EFX_QWORD_FIELD(*event,  FSF_AZ_DRIVER_EV_SUBDATA);
@@ -1500,7 +1511,7 @@ void efx_siena_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
 
 void efx_siena_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
 {
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	unsigned ev_failed, queue, qid;
 
 	queue = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
@@ -1525,7 +1536,7 @@ void efx_siena_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
 /* Called from napi. Schedule the reset work item */
 void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq)
 {
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 	unsigned int rel;
 
 	if (map_vi_index(efx, dmaq, &vf, &rel))
@@ -1541,9 +1552,10 @@ void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq)
 /* Reset all VFs */
 void efx_siena_sriov_reset(struct efx_nic *efx)
 {
+	struct siena_nic_data *nic_data = efx->nic_data;
 	unsigned int vf_i;
 	struct efx_buffer buf;
-	struct efx_vf *vf;
+	struct siena_vf *vf;
 
 	ASSERT_RTNL();
 
@@ -1557,7 +1569,7 @@ void efx_siena_sriov_reset(struct efx_nic *efx)
 		return;
 
 	for (vf_i = 0; vf_i < efx->vf_init_count; ++vf_i) {
-		vf = efx->vf + vf_i;
+		vf = nic_data->vf + vf_i;
 		efx_siena_sriov_reset_vf(vf, &buf);
 	}
 
@@ -1573,7 +1585,6 @@ int efx_init_sriov(void)
 	vfdi_workqueue = create_singlethread_workqueue("sfc_vfdi");
 	if (!vfdi_workqueue)
 		return -ENOMEM;
-
 	return 0;
 }
 
@@ -1582,14 +1593,14 @@ void efx_fini_sriov(void)
 	destroy_workqueue(vfdi_workqueue);
 }
 
-int efx_siena_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac)
+int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac)
 {
-	struct efx_nic *efx = netdev_priv(net_dev);
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 
 	if (vf_i >= efx->vf_init_count)
 		return -EINVAL;
-	vf = efx->vf + vf_i;
+	vf = nic_data->vf + vf_i;
 
 	mutex_lock(&vf->status_lock);
 	ether_addr_copy(vf->addr.mac_addr, mac);
@@ -1599,16 +1610,16 @@ int efx_siena_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac)
 	return 0;
 }
 
-int efx_siena_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i,
+int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i,
 				u16 vlan, u8 qos)
 {
-	struct efx_nic *efx = netdev_priv(net_dev);
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 	u16 tci;
 
 	if (vf_i >= efx->vf_init_count)
 		return -EINVAL;
-	vf = efx->vf + vf_i;
+	vf = nic_data->vf + vf_i;
 
 	mutex_lock(&vf->status_lock);
 	tci = (vlan & VLAN_VID_MASK) | ((qos & 0x7) << VLAN_PRIO_SHIFT);
@@ -1619,16 +1630,16 @@ int efx_siena_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i,
 	return 0;
 }
 
-int efx_siena_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i,
+int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf_i,
 				    bool spoofchk)
 {
-	struct efx_nic *efx = netdev_priv(net_dev);
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 	int rc;
 
 	if (vf_i >= efx->vf_init_count)
 		return -EINVAL;
-	vf = efx->vf + vf_i;
+	vf = nic_data->vf + vf_i;
 
 	mutex_lock(&vf->txq_lock);
 	if (vf->txq_count == 0) {
@@ -1643,16 +1654,16 @@ int efx_siena_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i,
 	return rc;
 }
 
-int efx_siena_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
+int efx_siena_sriov_get_vf_config(struct efx_nic *efx, int vf_i,
 				  struct ifla_vf_info *ivi)
 {
-	struct efx_nic *efx = netdev_priv(net_dev);
-	struct efx_vf *vf;
+	struct siena_nic_data *nic_data = efx->nic_data;
+	struct siena_vf *vf;
 	u16 tci;
 
 	if (vf_i >= efx->vf_init_count)
 		return -EINVAL;
-	vf = efx->vf + vf_i;
+	vf = nic_data->vf + vf_i;
 
 	ivi->vf = vf_i;
 	ether_addr_copy(ivi->mac, vf->addr.mac_addr);
@@ -1666,3 +1677,12 @@ int efx_siena_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
 	return 0;
 }
 
+bool efx_siena_sriov_wanted(struct efx_nic *efx)
+{
+	return efx->vf_count != 0;
+}
+
+int efx_siena_sriov_configure(struct efx_nic *efx, int num_vfs)
+{
+	return 0;
+}
diff --git a/drivers/net/ethernet/sfc/siena_sriov.h b/drivers/net/ethernet/sfc/siena_sriov.h
new file mode 100644
index 000000000000..d88d4dab170a
--- /dev/null
+++ b/drivers/net/ethernet/sfc/siena_sriov.h
@@ -0,0 +1,79 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef SIENA_SRIOV_H
+#define SIENA_SRIOV_H
+
+#include "net_driver.h"
+
+/* On the SFC9000 family each port is associated with 1 PCI physical
+ * function (PF) handled by sfc and a configurable number of virtual
+ * functions (VFs) that may be handled by some other driver, often in
+ * a VM guest.  The queue pointer registers are mapped in both PF and
+ * VF BARs such that an 8K region provides access to a single RX, TX
+ * and event queue (collectively a Virtual Interface, VI or VNIC).
+ *
+ * The PF has access to all 1024 VIs while VFs are mapped to VIs
+ * according to VI_BASE and VI_SCALE: VF i has access to VIs numbered
+ * in range [VI_BASE + i << VI_SCALE, VI_BASE + i + 1 << VI_SCALE).
+ * The number of VIs and the VI_SCALE value are configurable but must
+ * be established at boot time by firmware.
+ */
+
+/* Maximum VI_SCALE parameter supported by Siena */
+#define EFX_VI_SCALE_MAX 6
+/* Base VI to use for SR-IOV. Must be aligned to (1 << EFX_VI_SCALE_MAX),
+ * so this is the smallest allowed value.
+ */
+#define EFX_VI_BASE 128U
+/* Maximum number of VFs allowed */
+#define EFX_VF_COUNT_MAX 127
+/* Limit EVQs on VFs to be only 8k to reduce buffer table reservation */
+#define EFX_MAX_VF_EVQ_SIZE 8192UL
+/* The number of buffer table entries reserved for each VI on a VF */
+#define EFX_VF_BUFTBL_PER_VI					\
+	((EFX_MAX_VF_EVQ_SIZE + 2 * EFX_MAX_DMAQ_SIZE) *	\
+	 sizeof(efx_qword_t) / EFX_BUF_SIZE)
+
+int efx_siena_sriov_configure(struct efx_nic *efx, int num_vfs);
+int efx_siena_sriov_init(struct efx_nic *efx);
+void efx_siena_sriov_fini(struct efx_nic *efx);
+int efx_siena_sriov_mac_address_changed(struct efx_nic *efx);
+bool efx_siena_sriov_wanted(struct efx_nic *efx);
+void efx_siena_sriov_reset(struct efx_nic *efx);
+void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr);
+
+int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac);
+int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf,
+				u16 vlan, u8 qos);
+int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf,
+				    bool spoofchk);
+int efx_siena_sriov_get_vf_config(struct efx_nic *efx, int vf,
+				  struct ifla_vf_info *ivf);
+
+#ifdef CONFIG_SFC_SRIOV
+
+static inline bool efx_siena_sriov_enabled(struct efx_nic *efx)
+{
+	return efx->vf_init_count != 0;
+}
+#else /* !CONFIG_SFC_SRIOV */
+static inline bool efx_siena_sriov_enabled(struct efx_nic *efx)
+{
+	return false;
+}
+#endif /* CONFIG_SFC_SRIOV */
+
+void efx_siena_sriov_probe(struct efx_nic *efx);
+void efx_siena_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+void efx_siena_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+void efx_siena_sriov_event(struct efx_channel *channel, efx_qword_t *event);
+void efx_siena_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq);
+
+#endif /* SIENA_SRIOV_H */
diff --git a/drivers/net/ethernet/sfc/sriov.c b/drivers/net/ethernet/sfc/sriov.c
new file mode 100644
index 000000000000..816c44689e67
--- /dev/null
+++ b/drivers/net/ethernet/sfc/sriov.c
@@ -0,0 +1,83 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2014-2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#include <linux/module.h>
+#include "net_driver.h"
+#include "nic.h"
+#include "sriov.h"
+
+int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_set_vf_mac)
+		return efx->type->sriov_set_vf_mac(efx, vf_i, mac);
+	else
+		return -EOPNOTSUPP;
+}
+
+int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan,
+			  u8 qos)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_set_vf_vlan) {
+		if ((vlan & ~VLAN_VID_MASK) ||
+		    (qos & ~(VLAN_PRIO_MASK >> VLAN_PRIO_SHIFT)))
+			return -EINVAL;
+
+		return efx->type->sriov_set_vf_vlan(efx, vf_i, vlan, qos);
+	} else {
+		return -EOPNOTSUPP;
+	}
+}
+
+int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i,
+			      bool spoofchk)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_set_vf_spoofchk)
+		return efx->type->sriov_set_vf_spoofchk(efx, vf_i, spoofchk);
+	else
+		return -EOPNOTSUPP;
+}
+
+int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
+			    struct ifla_vf_info *ivi)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_get_vf_config)
+		return efx->type->sriov_get_vf_config(efx, vf_i, ivi);
+	else
+		return -EOPNOTSUPP;
+}
+
+int efx_sriov_set_vf_link_state(struct net_device *net_dev, int vf_i,
+				int link_state)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_set_vf_link_state)
+		return efx->type->sriov_set_vf_link_state(efx, vf_i,
+							  link_state);
+	else
+		return -EOPNOTSUPP;
+}
+
+int efx_sriov_get_phys_port_id(struct net_device *net_dev,
+			       struct netdev_phys_item_id *ppid)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
+
+	if (efx->type->sriov_get_phys_port_id)
+		return efx->type->sriov_get_phys_port_id(efx, ppid);
+	else
+		return -EOPNOTSUPP;
+}
diff --git a/drivers/net/ethernet/sfc/sriov.h b/drivers/net/ethernet/sfc/sriov.h
new file mode 100644
index 000000000000..400df526586d
--- /dev/null
+++ b/drivers/net/ethernet/sfc/sriov.h
@@ -0,0 +1,31 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2014-2015 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_SRIOV_H
+#define EFX_SRIOV_H
+
+#include "net_driver.h"
+
+#ifdef CONFIG_SFC_SRIOV
+
+int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac);
+int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i, u16 vlan,
+			  u8 qos);
+int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i,
+			      bool spoofchk);
+int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
+			    struct ifla_vf_info *ivi);
+int efx_sriov_set_vf_link_state(struct net_device *net_dev, int vf_i,
+				int link_state);
+int efx_sriov_get_phys_port_id(struct net_device *net_dev,
+			       struct netdev_phys_item_id *ppid);
+
+#endif /* CONFIG_SFC_SRIOV */
+
+#endif /* EFX_SRIOV_H */
diff --git a/drivers/net/ethernet/sgi/Kconfig b/drivers/net/ethernet/sgi/Kconfig
index e832f46660c9..fbbb21c13e95 100644
--- a/drivers/net/ethernet/sgi/Kconfig
+++ b/drivers/net/ethernet/sgi/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_SGI
 	default y
 	depends on (PCI && SGI_IP27) || SGI_IP32
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -24,9 +22,7 @@ config SGI_IOC3_ETH
 	select CRC32
 	select MII
 	---help---
-	  If you have a network (Ethernet) card of this type, say Y and read
-	  the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card of this type, say Y here.
 
 config SGI_O2MACE_ETH
 	tristate "SGI O2 MACE Fast Ethernet support"
diff --git a/drivers/net/ethernet/silan/Kconfig b/drivers/net/ethernet/silan/Kconfig
index 3409b3f97a1b..ac982be38510 100644
--- a/drivers/net/ethernet/silan/Kconfig
+++ b/drivers/net/ethernet/silan/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_SILAN
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/sis/Kconfig b/drivers/net/ethernet/sis/Kconfig
index 68d052b09af1..22ec98ec9d3e 100644
--- a/drivers/net/ethernet/sis/Kconfig
+++ b/drivers/net/ethernet/sis/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_SIS
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 3e97a8b43147..eb9230e2092f 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -9,9 +9,7 @@ config NET_VENDOR_SMSC
 		   ISA || M32R || MAC || MIPS || MN10300 || NIOS2 || PCI || \
 		   PCMCIA || SUPERH || XTENSA
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -29,8 +27,7 @@ config SMC9194
 	  option if you have a DELL laptop with the docking station, or
 	  another SMC9192/9194 based chipset.  Say Y if you want it compiled
 	  into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt> and the Ethernet-HOWTO,
-	  available from <http://www.tldp.org/docs.html#howto>.
+	  <file:Documentation/networking/smc9.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called smc9194.
@@ -46,8 +43,7 @@ config SMC91X
 	  This is a driver for SMC's 91x series of Ethernet chipsets,
 	  including the SMC91C94 and the SMC91C111. Say Y if you want it
 	  compiled into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt>  and the Ethernet-HOWTO,
-	  available from  <http://www.tldp.org/docs.html#howto>.
+	  <file:Documentation/networking/smc9.txt>.
 
 	  This driver is also available as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want).
@@ -85,9 +81,7 @@ config SMC911X
 	---help---
 	  This is a driver for SMSC's LAN911x series of Ethernet chipsets
 	  including the new LAN9115, LAN9116, LAN9117, and LAN9118.
-	  Say Y if you want it compiled into the kernel,
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  Say Y here if you want it compiled into the kernel.
 
 	  This driver is also available as a module. The module will be
 	  called smc911x.  If you want to compile it as a module, say M
@@ -122,9 +116,7 @@ config SMSC9420
 	select SMSC_PHY
 	---help---
 	  This is a driver for SMSC's LAN9420 PCI ethernet adapter.
-	  Say Y if you want it compiled into the kernel,
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  Say Y here if you want it compiled into the kernel.
 
 	  This driver is also available as a module. The module will be
 	  called smsc9420.  If you want to compile it as a module, say M
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 14b363a25c02..630f0b7800e4 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2238,9 +2238,10 @@ static int smc_drv_probe(struct platform_device *pdev)
 	const struct of_device_id *match = NULL;
 	struct smc_local *lp;
 	struct net_device *ndev;
-	struct resource *res, *ires;
+	struct resource *res;
 	unsigned int __iomem *addr;
 	unsigned long irq_flags = SMC_IRQ_FLAGS;
+	unsigned long irq_resflags;
 	int ret;
 
 	ndev = alloc_etherdev(sizeof(struct smc_local));
@@ -2332,16 +2333,19 @@ static int smc_drv_probe(struct platform_device *pdev)
 		goto out_free_netdev;
 	}
 
-	ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!ires) {
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq <= 0) {
 		ret = -ENODEV;
 		goto out_release_io;
 	}
-
-	ndev->irq = ires->start;
-
-	if (irq_flags == -1 || ires->flags & IRQF_TRIGGER_MASK)
-		irq_flags = ires->flags & IRQF_TRIGGER_MASK;
+	/*
+	 * If this platform does not specify any special irqflags, or if
+	 * the resource supplies a trigger, override the irqflags with
+	 * the trigger flags from the resource.
+	 */
+	irq_resflags = irqd_get_trigger_type(irq_get_irq_data(ndev->irq));
+	if (irq_flags == -1 || irq_resflags & IRQF_TRIGGER_MASK)
+		irq_flags = irq_resflags & IRQF_TRIGGER_MASK;
 
 	ret = smc_request_attrib(pdev, ndev);
 	if (ret)
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 41047c9143d0..959aeeade0c9 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2418,9 +2418,9 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 	struct net_device *dev;
 	struct smsc911x_data *pdata;
 	struct smsc911x_platform_config *config = dev_get_platdata(&pdev->dev);
-	struct resource *res, *irq_res;
+	struct resource *res;
 	unsigned int intcfg = 0;
-	int res_size, irq_flags;
+	int res_size, irq, irq_flags;
 	int retval;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
@@ -2434,8 +2434,8 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 	}
 	res_size = resource_size(res);
 
-	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!irq_res) {
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
 		pr_warn("Could not allocate irq resource\n");
 		retval = -ENODEV;
 		goto out_0;
@@ -2455,8 +2455,8 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	pdata = netdev_priv(dev);
-	dev->irq = irq_res->start;
-	irq_flags = irq_res->flags & IRQF_TRIGGER_MASK;
+	dev->irq = irq;
+	irq_flags = irq_get_trigger_type(irq);
 	pdata->ioaddr = ioremap_nocache(res->start, res_size);
 
 	pdata->dev = dev;
diff --git a/drivers/net/ethernet/stmicro/Kconfig b/drivers/net/ethernet/stmicro/Kconfig
index f4a80da00650..1c1157d2bd40 100644
--- a/drivers/net/ethernet/stmicro/Kconfig
+++ b/drivers/net/ethernet/stmicro/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_STMICRO
 	default y
 	depends on HAS_IOMEM
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 7d3af190be55..cec147d1d34f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -16,6 +16,7 @@ if STMMAC_ETH
 config STMMAC_PLATFORM
 	tristate "STMMAC Platform bus support"
 	depends on STMMAC_ETH
+	select MFD_SYSCON
 	default y
 	---help---
 	  This selects the platform specific bus support for the stmmac driver.
@@ -26,6 +27,95 @@ config STMMAC_PLATFORM
 
 	  If unsure, say N.
 
+if STMMAC_PLATFORM
+
+config DWMAC_GENERIC
+	tristate "Generic driver for DWMAC"
+	default STMMAC_PLATFORM
+	---help---
+	  Generic DWMAC driver for platforms that don't require any
+	  platform specific code to function or is using platform
+	  data for setup.
+
+config DWMAC_IPQ806X
+	tristate "QCA IPQ806x DWMAC support"
+	default ARCH_QCOM
+	depends on OF
+	select MFD_SYSCON
+	help
+	  Support for QCA IPQ806X DWMAC Ethernet.
+
+	  This selects the IPQ806x SoC glue layer support for the stmmac
+	  device driver. This driver does not use any of the hardware
+	  acceleration features available on this SoC. Network devices
+	  will behave like standard non-accelerated ethernet interfaces.
+
+config DWMAC_LPC18XX
+	tristate "NXP LPC18xx/43xx DWMAC support"
+	default ARCH_LPC18XX
+	depends on OF
+	select MFD_SYSCON
+	---help---
+	  Support for NXP LPC18xx/43xx DWMAC Ethernet.
+
+config DWMAC_MESON
+	tristate "Amlogic Meson dwmac support"
+	default ARCH_MESON
+	depends on OF
+	help
+	  Support for Ethernet controller on Amlogic Meson SoCs.
+
+	  This selects the Amlogic Meson SoC glue layer support for
+	  the stmmac device driver. This driver is used for Meson6 and
+	  Meson8 SoCs.
+
+config DWMAC_ROCKCHIP
+	tristate "Rockchip dwmac support"
+	default ARCH_ROCKCHIP
+	depends on OF
+	select MFD_SYSCON
+	help
+	  Support for Ethernet controller on Rockchip RK3288 SoC.
+
+	  This selects the Rockchip RK3288 SoC glue layer support for
+	  the stmmac device driver.
+
+config DWMAC_SOCFPGA
+	tristate "SOCFPGA dwmac support"
+	default ARCH_SOCFPGA
+	depends on OF
+	select MFD_SYSCON
+	help
+	  Support for ethernet controller on Altera SOCFPGA
+
+	  This selects the Altera SOCFPGA SoC glue layer support
+	  for the stmmac device driver. This driver is used for
+	  arria5 and cyclone5 FPGA SoCs.
+
+config DWMAC_STI
+	tristate "STi GMAC support"
+	default ARCH_STI
+	depends on OF
+	select MFD_SYSCON
+	---help---
+	  Support for ethernet controller on STi SOCs.
+
+	  This selects STi SoC glue layer support for the stmmac
+	  device driver. This driver is used on for the STi series
+	  SOCs GMAC ethernet controller.
+
+config DWMAC_SUNXI
+	tristate "Allwinner GMAC support"
+	default ARCH_SUNXI
+	depends on OF
+	---help---
+	  Support for Allwinner A20/A31 GMAC ethernet controllers.
+
+	  This selects Allwinner SoC glue layer support for the
+	  stmmac device driver. This driver is used for A20/A31
+	  GMAC ethernet controller.
+endif
+
 config STMMAC_PCI
 	tristate "STMMAC PCI bus support"
 	depends on STMMAC_ETH && PCI
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 73c2715a27f3..b3901616f4f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -4,9 +4,17 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o $(stmmac-y)
 
-obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o
-stmmac-platform-objs:= stmmac_platform.o dwmac-meson.o dwmac-sunxi.o	\
-		       dwmac-sti.o dwmac-socfpga.o dwmac-rk.o
+# Ordering matters. Generic driver must be last.
+obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
+obj-$(CONFIG_DWMAC_IPQ806X)	+= dwmac-ipq806x.o
+obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
+obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o
+obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
+obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-socfpga.o
+obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
+obj-$(CONFIG_DWMAC_SUNXI)	+= dwmac-sunxi.o
+obj-$(CONFIG_DWMAC_GENERIC)	+= dwmac-generic.o
+stmmac-platform-objs:= stmmac_platform.o
 
 obj-$(CONFIG_STMMAC_PCI) += stmmac-pci.o
 stmmac-pci-objs:= stmmac_pci.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index ad3996038018..799c2929c536 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -158,6 +158,8 @@ struct dma_desc {
 			u32 buffer2_size:13;
 			u32 reserved4:3;
 		} etx;		/* -- enhanced -- */
+
+		u64 all_flags;
 	} des01;
 	unsigned int des2;
 	unsigned int des3;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
new file mode 100644
index 000000000000..e817a1a44379
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
@@ -0,0 +1,41 @@
+/*
+ * Generic DWMAC platform driver
+ *
+ * Copyright (C) 2007-2011  STMicroelectronics Ltd
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "stmmac.h"
+#include "stmmac_platform.h"
+
+static const struct of_device_id dwmac_generic_match[] = {
+	{ .compatible = "st,spear600-gmac"},
+	{ .compatible = "snps,dwmac-3.610"},
+	{ .compatible = "snps,dwmac-3.70a"},
+	{ .compatible = "snps,dwmac-3.710"},
+	{ .compatible = "snps,dwmac"},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, dwmac_generic_match);
+
+static struct platform_driver dwmac_generic_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = STMMAC_RESOURCE_NAME,
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = of_match_ptr(dwmac_generic_match),
+	},
+};
+module_platform_driver(dwmac_generic_driver);
+
+MODULE_DESCRIPTION("Generic dwmac driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
new file mode 100644
index 000000000000..7e3129e7f143
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -0,0 +1,365 @@
+/*
+ * Qualcomm Atheros IPQ806x GMAC glue layer
+ *
+ * Copyright (C) 2015 The Linux Foundation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+#include <linux/reset.h>
+#include <linux/of_net.h>
+#include <linux/mfd/syscon.h>
+#include <linux/stmmac.h>
+#include <linux/of_mdio.h>
+#include <linux/module.h>
+
+#include "stmmac_platform.h"
+
+#define NSS_COMMON_CLK_GATE			0x8
+#define NSS_COMMON_CLK_GATE_PTP_EN(x)		BIT(0x10 + x)
+#define NSS_COMMON_CLK_GATE_RGMII_RX_EN(x)	BIT(0x9 + (x * 2))
+#define NSS_COMMON_CLK_GATE_RGMII_TX_EN(x)	BIT(0x8 + (x * 2))
+#define NSS_COMMON_CLK_GATE_GMII_RX_EN(x)	BIT(0x4 + x)
+#define NSS_COMMON_CLK_GATE_GMII_TX_EN(x)	BIT(0x0 + x)
+
+#define NSS_COMMON_CLK_DIV0			0xC
+#define NSS_COMMON_CLK_DIV_OFFSET(x)		(x * 8)
+#define NSS_COMMON_CLK_DIV_MASK			0x7f
+
+#define NSS_COMMON_CLK_SRC_CTRL			0x14
+#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x)	(1 << x)
+/* Mode is coded on 1 bit but is different depending on the MAC ID:
+ * MAC0: QSGMII=0 RGMII=1
+ * MAC1: QSGMII=0 SGMII=0 RGMII=1
+ * MAC2 & MAC3: QSGMII=0 SGMII=1
+ */
+#define NSS_COMMON_CLK_SRC_CTRL_RGMII(x)	1
+#define NSS_COMMON_CLK_SRC_CTRL_SGMII(x)	((x >= 2) ? 1 : 0)
+
+#define NSS_COMMON_MACSEC_CTL			0x28
+#define NSS_COMMON_MACSEC_CTL_EXT_BYPASS_EN(x)	(1 << x)
+
+#define NSS_COMMON_GMAC_CTL(x)			(0x30 + (x * 4))
+#define NSS_COMMON_GMAC_CTL_CSYS_REQ		BIT(19)
+#define NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL	BIT(16)
+#define NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET	8
+#define NSS_COMMON_GMAC_CTL_IFG_OFFSET		0
+#define NSS_COMMON_GMAC_CTL_IFG_MASK		0x3f
+
+#define NSS_COMMON_CLK_DIV_RGMII_1000		1
+#define NSS_COMMON_CLK_DIV_RGMII_100		9
+#define NSS_COMMON_CLK_DIV_RGMII_10		99
+#define NSS_COMMON_CLK_DIV_SGMII_1000		0
+#define NSS_COMMON_CLK_DIV_SGMII_100		4
+#define NSS_COMMON_CLK_DIV_SGMII_10		49
+
+#define QSGMII_PCS_MODE_CTL			0x68
+#define QSGMII_PCS_MODE_CTL_AUTONEG_EN(x)	BIT((x * 8) + 7)
+
+#define QSGMII_PCS_CAL_LCKDT_CTL		0x120
+#define QSGMII_PCS_CAL_LCKDT_CTL_RST		BIT(19)
+
+/* Only GMAC1/2/3 support SGMII and their CTL register are not contiguous */
+#define QSGMII_PHY_SGMII_CTL(x)			((x == 1) ? 0x134 : \
+						 (0x13c + (4 * (x - 2))))
+#define QSGMII_PHY_CDR_EN			BIT(0)
+#define QSGMII_PHY_RX_FRONT_EN			BIT(1)
+#define QSGMII_PHY_RX_SIGNAL_DETECT_EN		BIT(2)
+#define QSGMII_PHY_TX_DRIVER_EN			BIT(3)
+#define QSGMII_PHY_QSGMII_EN			BIT(7)
+#define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET	12
+#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK		0x7
+#define QSGMII_PHY_RX_DC_BIAS_OFFSET		18
+#define QSGMII_PHY_RX_DC_BIAS_MASK		0x3
+#define QSGMII_PHY_RX_INPUT_EQU_OFFSET		20
+#define QSGMII_PHY_RX_INPUT_EQU_MASK		0x3
+#define QSGMII_PHY_CDR_PI_SLEW_OFFSET		22
+#define QSGMII_PHY_CDR_PI_SLEW_MASK		0x3
+#define QSGMII_PHY_TX_DRV_AMP_OFFSET		28
+#define QSGMII_PHY_TX_DRV_AMP_MASK		0xf
+
+struct ipq806x_gmac {
+	struct platform_device *pdev;
+	struct regmap *nss_common;
+	struct regmap *qsgmii_csr;
+	uint32_t id;
+	struct clk *core_clk;
+	phy_interface_t phy_mode;
+};
+
+static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+{
+	struct device *dev = &gmac->pdev->dev;
+	int div;
+
+	switch (speed) {
+	case SPEED_1000:
+		div = NSS_COMMON_CLK_DIV_SGMII_1000;
+		break;
+
+	case SPEED_100:
+		div = NSS_COMMON_CLK_DIV_SGMII_100;
+		break;
+
+	case SPEED_10:
+		div = NSS_COMMON_CLK_DIV_SGMII_10;
+		break;
+
+	default:
+		dev_err(dev, "Speed %dMbps not supported in SGMII\n", speed);
+		return -EINVAL;
+	}
+
+	return div;
+}
+
+static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+{
+	struct device *dev = &gmac->pdev->dev;
+	int div;
+
+	switch (speed) {
+	case SPEED_1000:
+		div = NSS_COMMON_CLK_DIV_RGMII_1000;
+		break;
+
+	case SPEED_100:
+		div = NSS_COMMON_CLK_DIV_RGMII_100;
+		break;
+
+	case SPEED_10:
+		div = NSS_COMMON_CLK_DIV_RGMII_10;
+		break;
+
+	default:
+		dev_err(dev, "Speed %dMbps not supported in RGMII\n", speed);
+		return -EINVAL;
+	}
+
+	return div;
+}
+
+static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed)
+{
+	uint32_t clk_bits, val;
+	int div;
+
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		div = get_clk_div_rgmii(gmac, speed);
+		clk_bits = NSS_COMMON_CLK_GATE_RGMII_RX_EN(gmac->id) |
+			   NSS_COMMON_CLK_GATE_RGMII_TX_EN(gmac->id);
+		break;
+
+	case PHY_INTERFACE_MODE_SGMII:
+		div = get_clk_div_sgmii(gmac, speed);
+		clk_bits = NSS_COMMON_CLK_GATE_GMII_RX_EN(gmac->id) |
+			   NSS_COMMON_CLK_GATE_GMII_TX_EN(gmac->id);
+		break;
+
+	default:
+		dev_err(&gmac->pdev->dev, "Unsupported PHY mode: \"%s\"\n",
+			phy_modes(gmac->phy_mode));
+		return -EINVAL;
+	}
+
+	/* Disable the clocks */
+	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
+	val &= ~clk_bits;
+	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
+
+	/* Set the divider */
+	regmap_read(gmac->nss_common, NSS_COMMON_CLK_DIV0, &val);
+	val &= ~(NSS_COMMON_CLK_DIV_MASK
+		 << NSS_COMMON_CLK_DIV_OFFSET(gmac->id));
+	val |= div << NSS_COMMON_CLK_DIV_OFFSET(gmac->id);
+	regmap_write(gmac->nss_common, NSS_COMMON_CLK_DIV0, val);
+
+	/* Enable the clock back */
+	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
+	val |= clk_bits;
+	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
+
+	return 0;
+}
+
+static void *ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
+{
+	struct device *dev = &gmac->pdev->dev;
+
+	gmac->phy_mode = of_get_phy_mode(dev->of_node);
+	if (gmac->phy_mode < 0) {
+		dev_err(dev, "missing phy mode property\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (of_property_read_u32(dev->of_node, "qcom,id", &gmac->id) < 0) {
+		dev_err(dev, "missing qcom id property\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* The GMACs are called 1 to 4 in the documentation, but to simplify the
+	 * code and keep it consistent with the Linux convention, we'll number
+	 * them from 0 to 3 here.
+	 */
+	if (gmac->id < 0 || gmac->id > 3) {
+		dev_err(dev, "invalid gmac id\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	gmac->core_clk = devm_clk_get(dev, "stmmaceth");
+	if (IS_ERR(gmac->core_clk)) {
+		dev_err(dev, "missing stmmaceth clk property\n");
+		return gmac->core_clk;
+	}
+	clk_set_rate(gmac->core_clk, 266000000);
+
+	/* Setup the register map for the nss common registers */
+	gmac->nss_common = syscon_regmap_lookup_by_phandle(dev->of_node,
+							   "qcom,nss-common");
+	if (IS_ERR(gmac->nss_common)) {
+		dev_err(dev, "missing nss-common node\n");
+		return gmac->nss_common;
+	}
+
+	/* Setup the register map for the qsgmii csr registers */
+	gmac->qsgmii_csr = syscon_regmap_lookup_by_phandle(dev->of_node,
+							   "qcom,qsgmii-csr");
+	if (IS_ERR(gmac->qsgmii_csr)) {
+		dev_err(dev, "missing qsgmii-csr node\n");
+		return gmac->qsgmii_csr;
+	}
+
+	return NULL;
+}
+
+static void *ipq806x_gmac_setup(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ipq806x_gmac *gmac;
+	int val;
+	void *err;
+
+	gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL);
+	if (!gmac)
+		return ERR_PTR(-ENOMEM);
+
+	gmac->pdev = pdev;
+
+	err = ipq806x_gmac_of_parse(gmac);
+	if (err) {
+		dev_err(dev, "device tree parsing error\n");
+		return err;
+	}
+
+	regmap_write(gmac->qsgmii_csr, QSGMII_PCS_CAL_LCKDT_CTL,
+		     QSGMII_PCS_CAL_LCKDT_CTL_RST);
+
+	/* Inter frame gap is set to 12 */
+	val = 12 << NSS_COMMON_GMAC_CTL_IFG_OFFSET |
+	      12 << NSS_COMMON_GMAC_CTL_IFG_LIMIT_OFFSET;
+	/* We also initiate an AXI low power exit request */
+	val |= NSS_COMMON_GMAC_CTL_CSYS_REQ;
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		val |= NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL;
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		val &= ~NSS_COMMON_GMAC_CTL_PHY_IFACE_SEL;
+		break;
+	default:
+		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
+			phy_modes(gmac->phy_mode));
+		return NULL;
+	}
+	regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val);
+
+	/* Configure the clock src according to the mode */
+	regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val);
+	val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
+	switch (gmac->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) <<
+			NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		val |= NSS_COMMON_CLK_SRC_CTRL_SGMII(gmac->id) <<
+			NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
+		break;
+	default:
+		dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n",
+			phy_modes(gmac->phy_mode));
+		return NULL;
+	}
+	regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val);
+
+	/* Enable PTP clock */
+	regmap_read(gmac->nss_common, NSS_COMMON_CLK_GATE, &val);
+	val |= NSS_COMMON_CLK_GATE_PTP_EN(gmac->id);
+	regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val);
+
+	if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) {
+		regmap_write(gmac->qsgmii_csr, QSGMII_PHY_SGMII_CTL(gmac->id),
+			     QSGMII_PHY_CDR_EN |
+			     QSGMII_PHY_RX_FRONT_EN |
+			     QSGMII_PHY_RX_SIGNAL_DETECT_EN |
+			     QSGMII_PHY_TX_DRIVER_EN |
+			     QSGMII_PHY_QSGMII_EN |
+			     0x4 << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET |
+			     0x3 << QSGMII_PHY_RX_DC_BIAS_OFFSET |
+			     0x1 << QSGMII_PHY_RX_INPUT_EQU_OFFSET |
+			     0x2 << QSGMII_PHY_CDR_PI_SLEW_OFFSET |
+			     0xC << QSGMII_PHY_TX_DRV_AMP_OFFSET);
+	}
+
+	return gmac;
+}
+
+static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed)
+{
+	struct ipq806x_gmac *gmac = priv;
+
+	ipq806x_gmac_set_speed(gmac, speed);
+}
+
+static const struct stmmac_of_data ipq806x_gmac_data = {
+	.has_gmac	= 1,
+	.setup		= ipq806x_gmac_setup,
+	.fix_mac_speed	= ipq806x_gmac_fix_mac_speed,
+};
+
+static const struct of_device_id ipq806x_gmac_dwmac_match[] = {
+	{ .compatible = "qcom,ipq806x-gmac", .data = &ipq806x_gmac_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ipq806x_gmac_dwmac_match);
+
+static struct platform_driver ipq806x_gmac_dwmac_driver = {
+	.probe = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name		= "ipq806x-gmac-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table	= ipq806x_gmac_dwmac_match,
+	},
+};
+module_platform_driver(ipq806x_gmac_dwmac_driver);
+
+MODULE_AUTHOR("Mathieu Olivari <mathieu@codeaurora.org>");
+MODULE_DESCRIPTION("Qualcomm Atheros IPQ806x DWMAC specific glue layer");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c
new file mode 100644
index 000000000000..cb888d3ebbdc
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c
@@ -0,0 +1,99 @@
+/*
+ * DWMAC glue for NXP LPC18xx/LPC43xx Ethernet
+ *
+ * Copyright (C) 2015 Joachim Eastwood <manabian@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/stmmac.h>
+
+#include "stmmac_platform.h"
+
+/* Register defines for CREG syscon */
+#define LPC18XX_CREG_CREG6			0x12c
+# define LPC18XX_CREG_CREG6_ETHMODE_MASK	0x7
+# define LPC18XX_CREG_CREG6_ETHMODE_MII		0x0
+# define LPC18XX_CREG_CREG6_ETHMODE_RMII	0x4
+
+struct lpc18xx_dwmac_priv_data {
+	struct regmap *reg;
+	int interface;
+};
+
+static void *lpc18xx_dwmac_setup(struct platform_device *pdev)
+{
+	struct lpc18xx_dwmac_priv_data *dwmac;
+
+	dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
+	if (!dwmac)
+		return ERR_PTR(-ENOMEM);
+
+	dwmac->interface = of_get_phy_mode(pdev->dev.of_node);
+	if (dwmac->interface < 0)
+		return ERR_PTR(dwmac->interface);
+
+	dwmac->reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg");
+	if (IS_ERR(dwmac->reg)) {
+		dev_err(&pdev->dev, "Syscon lookup failed\n");
+		return dwmac->reg;
+	}
+
+	return dwmac;
+}
+
+static int lpc18xx_dwmac_init(struct platform_device *pdev, void *priv)
+{
+	struct lpc18xx_dwmac_priv_data *dwmac = priv;
+	u8 ethmode;
+
+	if (dwmac->interface == PHY_INTERFACE_MODE_MII) {
+		ethmode = LPC18XX_CREG_CREG6_ETHMODE_MII;
+	} else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) {
+		ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII;
+	} else {
+		dev_err(&pdev->dev, "Only MII and RMII mode supported\n");
+		return -EINVAL;
+	}
+
+	regmap_update_bits(dwmac->reg, LPC18XX_CREG_CREG6,
+			   LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode);
+
+	return 0;
+}
+
+static const struct stmmac_of_data lpc18xx_dwmac_data = {
+	.has_gmac = 1,
+	.setup = lpc18xx_dwmac_setup,
+	.init = lpc18xx_dwmac_init,
+};
+
+static const struct of_device_id lpc18xx_dwmac_match[] = {
+	{ .compatible = "nxp,lpc1850-dwmac", .data = &lpc18xx_dwmac_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, lpc18xx_dwmac_match);
+
+static struct platform_driver lpc18xx_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "lpc18xx-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = lpc18xx_dwmac_match,
+	},
+};
+module_platform_driver(lpc18xx_dwmac_driver);
+
+MODULE_AUTHOR("Joachim Eastwood <manabian@gmail.com>");
+MODULE_DESCRIPTION("DWMAC glue for LPC18xx/43xx Ethernet");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index cca028d632f6..61a324a87d09 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -15,6 +15,7 @@
 #include <linux/ethtool.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/stmmac.h>
 
@@ -63,7 +64,28 @@ static void *meson6_dwmac_setup(struct platform_device *pdev)
 	return dwmac;
 }
 
-const struct stmmac_of_data meson6_dwmac_data = {
+static const struct stmmac_of_data meson6_dwmac_data = {
 	.setup		= meson6_dwmac_setup,
 	.fix_mac_speed	= meson6_dwmac_fix_mac_speed,
 };
+
+static const struct of_device_id meson6_dwmac_match[] = {
+	{ .compatible = "amlogic,meson6-dwmac", .data = &meson6_dwmac_data},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, meson6_dwmac_match);
+
+static struct platform_driver meson6_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "meson6-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = meson6_dwmac_match,
+	},
+};
+module_platform_driver(meson6_dwmac_driver);
+
+MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
+MODULE_DESCRIPTION("Amlogic Meson DWMAC glue layer");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 6249a4ec08f0..00a1e1e09d4f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -22,23 +22,36 @@
 #include <linux/phy.h>
 #include <linux/of_net.h>
 #include <linux/gpio.h>
+#include <linux/module.h>
 #include <linux/of_gpio.h>
 #include <linux/of_device.h>
+#include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 
+#include "stmmac_platform.h"
+
+struct rk_priv_data;
+struct rk_gmac_ops {
+	void (*set_to_rgmii)(struct rk_priv_data *bsp_priv,
+			     int tx_delay, int rx_delay);
+	void (*set_to_rmii)(struct rk_priv_data *bsp_priv);
+	void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed);
+	void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed);
+};
+
 struct rk_priv_data {
 	struct platform_device *pdev;
 	int phy_iface;
 	struct regulator *regulator;
+	struct rk_gmac_ops *ops;
 
 	bool clk_enabled;
 	bool clock_input;
 
 	struct clk *clk_mac;
-	struct clk *clk_mac_pll;
 	struct clk *gmac_clkin;
 	struct clk *mac_clk_rx;
 	struct clk *mac_clk_tx;
@@ -61,103 +74,228 @@ struct rk_priv_data {
 
 #define RK3288_GRF_SOC_CON1	0x0248
 #define RK3288_GRF_SOC_CON3	0x0250
-#define RK3288_GRF_GPIO3D_E	0x01ec
-#define RK3288_GRF_GPIO4A_E	0x01f0
-#define RK3288_GRF_GPIO4B_E	0x01f4
 
 /*RK3288_GRF_SOC_CON1*/
-#define GMAC_PHY_INTF_SEL_RGMII	(GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8))
-#define GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8))
-#define GMAC_FLOW_CTRL		GRF_BIT(9)
-#define GMAC_FLOW_CTRL_CLR	GRF_CLR_BIT(9)
-#define GMAC_SPEED_10M		GRF_CLR_BIT(10)
-#define GMAC_SPEED_100M		GRF_BIT(10)
-#define GMAC_RMII_CLK_25M	GRF_BIT(11)
-#define GMAC_RMII_CLK_2_5M	GRF_CLR_BIT(11)
-#define GMAC_CLK_125M		(GRF_CLR_BIT(12) | GRF_CLR_BIT(13))
-#define GMAC_CLK_25M		(GRF_BIT(12) | GRF_BIT(13))
-#define GMAC_CLK_2_5M		(GRF_CLR_BIT(12) | GRF_BIT(13))
-#define GMAC_RMII_MODE		GRF_BIT(14)
-#define GMAC_RMII_MODE_CLR	GRF_CLR_BIT(14)
+#define RK3288_GMAC_PHY_INTF_SEL_RGMII	(GRF_BIT(6) | GRF_CLR_BIT(7) | \
+					 GRF_CLR_BIT(8))
+#define RK3288_GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | \
+					 GRF_BIT(8))
+#define RK3288_GMAC_FLOW_CTRL		GRF_BIT(9)
+#define RK3288_GMAC_FLOW_CTRL_CLR	GRF_CLR_BIT(9)
+#define RK3288_GMAC_SPEED_10M		GRF_CLR_BIT(10)
+#define RK3288_GMAC_SPEED_100M		GRF_BIT(10)
+#define RK3288_GMAC_RMII_CLK_25M	GRF_BIT(11)
+#define RK3288_GMAC_RMII_CLK_2_5M	GRF_CLR_BIT(11)
+#define RK3288_GMAC_CLK_125M		(GRF_CLR_BIT(12) | GRF_CLR_BIT(13))
+#define RK3288_GMAC_CLK_25M		(GRF_BIT(12) | GRF_BIT(13))
+#define RK3288_GMAC_CLK_2_5M		(GRF_CLR_BIT(12) | GRF_BIT(13))
+#define RK3288_GMAC_RMII_MODE		GRF_BIT(14)
+#define RK3288_GMAC_RMII_MODE_CLR	GRF_CLR_BIT(14)
 
 /*RK3288_GRF_SOC_CON3*/
-#define GMAC_TXCLK_DLY_ENABLE	GRF_BIT(14)
-#define GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(14)
-#define GMAC_RXCLK_DLY_ENABLE	GRF_BIT(15)
-#define GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(15)
-#define GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 7)
-#define GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 0)
-
-static void set_to_rgmii(struct rk_priv_data *bsp_priv,
-			 int tx_delay, int rx_delay)
+#define RK3288_GMAC_TXCLK_DLY_ENABLE	GRF_BIT(14)
+#define RK3288_GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(14)
+#define RK3288_GMAC_RXCLK_DLY_ENABLE	GRF_BIT(15)
+#define RK3288_GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(15)
+#define RK3288_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 7)
+#define RK3288_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 0)
+
+static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		dev_err(dev, "Missing rockchip,grf property\n");
 		return;
 	}
 
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
-		     GMAC_PHY_INTF_SEL_RGMII | GMAC_RMII_MODE_CLR);
+		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3288_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3,
-		     GMAC_RXCLK_DLY_ENABLE | GMAC_TXCLK_DLY_ENABLE |
-		     GMAC_CLK_RX_DL_CFG(rx_delay) |
-		     GMAC_CLK_TX_DL_CFG(tx_delay));
+		     RK3288_GMAC_RXCLK_DLY_ENABLE |
+		     RK3288_GMAC_TXCLK_DLY_ENABLE |
+		     RK3288_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3288_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
 
-static void set_to_rmii(struct rk_priv_data *bsp_priv)
+static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		dev_err(dev, "Missing rockchip,grf property\n");
 		return;
 	}
 
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
-		     GMAC_PHY_INTF_SEL_RMII | GMAC_RMII_MODE);
+		     RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE);
 }
 
-static void set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+static void rk3288_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		dev_err(dev, "Missing rockchip,grf property\n");
 		return;
 	}
 
 	if (speed == 10)
-		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, GMAC_CLK_2_5M);
+		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
+			     RK3288_GMAC_CLK_2_5M);
 	else if (speed == 100)
-		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, GMAC_CLK_25M);
+		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
+			     RK3288_GMAC_CLK_25M);
 	else if (speed == 1000)
-		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, GMAC_CLK_125M);
+		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
+			     RK3288_GMAC_CLK_125M);
 	else
 		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
 }
 
-static void set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+static void rk3288_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		dev_err(dev, "Missing rockchip,grf property\n");
 		return;
 	}
 
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
-			     GMAC_RMII_CLK_2_5M | GMAC_SPEED_10M);
+			     RK3288_GMAC_RMII_CLK_2_5M |
+			     RK3288_GMAC_SPEED_10M);
 	} else if (speed == 100) {
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
-			     GMAC_RMII_CLK_25M | GMAC_SPEED_100M);
+			     RK3288_GMAC_RMII_CLK_25M |
+			     RK3288_GMAC_SPEED_100M);
 	} else {
 		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
 	}
 }
 
+struct rk_gmac_ops rk3288_ops = {
+	.set_to_rgmii = rk3288_set_to_rgmii,
+	.set_to_rmii = rk3288_set_to_rmii,
+	.set_rgmii_speed = rk3288_set_rgmii_speed,
+	.set_rmii_speed = rk3288_set_rmii_speed,
+};
+
+#define RK3368_GRF_SOC_CON15	0x043c
+#define RK3368_GRF_SOC_CON16	0x0440
+
+/* RK3368_GRF_SOC_CON15 */
+#define RK3368_GMAC_PHY_INTF_SEL_RGMII	(GRF_BIT(9) | GRF_CLR_BIT(10) | \
+					 GRF_CLR_BIT(11))
+#define RK3368_GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \
+					 GRF_BIT(11))
+#define RK3368_GMAC_FLOW_CTRL		GRF_BIT(8)
+#define RK3368_GMAC_FLOW_CTRL_CLR	GRF_CLR_BIT(8)
+#define RK3368_GMAC_SPEED_10M		GRF_CLR_BIT(7)
+#define RK3368_GMAC_SPEED_100M		GRF_BIT(7)
+#define RK3368_GMAC_RMII_CLK_25M	GRF_BIT(3)
+#define RK3368_GMAC_RMII_CLK_2_5M	GRF_CLR_BIT(3)
+#define RK3368_GMAC_CLK_125M		(GRF_CLR_BIT(4) | GRF_CLR_BIT(5))
+#define RK3368_GMAC_CLK_25M		(GRF_BIT(4) | GRF_BIT(5))
+#define RK3368_GMAC_CLK_2_5M		(GRF_CLR_BIT(4) | GRF_BIT(5))
+#define RK3368_GMAC_RMII_MODE		GRF_BIT(6)
+#define RK3368_GMAC_RMII_MODE_CLR	GRF_CLR_BIT(6)
+
+/* RK3368_GRF_SOC_CON16 */
+#define RK3368_GMAC_TXCLK_DLY_ENABLE	GRF_BIT(7)
+#define RK3368_GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(7)
+#define RK3368_GMAC_RXCLK_DLY_ENABLE	GRF_BIT(15)
+#define RK3368_GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(15)
+#define RK3368_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 8)
+#define RK3368_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0x7F, 0)
+
+static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
+		     RK3368_GMAC_RMII_MODE_CLR);
+	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16,
+		     RK3368_GMAC_RXCLK_DLY_ENABLE |
+		     RK3368_GMAC_TXCLK_DLY_ENABLE |
+		     RK3368_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3368_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+		     RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE);
+}
+
+static void rk3368_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+			     RK3368_GMAC_CLK_2_5M);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+			     RK3368_GMAC_CLK_25M);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+			     RK3368_GMAC_CLK_125M);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3368_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+			     RK3368_GMAC_RMII_CLK_2_5M |
+			     RK3368_GMAC_SPEED_10M);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
+			     RK3368_GMAC_RMII_CLK_25M |
+			     RK3368_GMAC_SPEED_100M);
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+struct rk_gmac_ops rk3368_ops = {
+	.set_to_rgmii = rk3368_set_to_rgmii,
+	.set_to_rmii = rk3368_set_to_rmii,
+	.set_rgmii_speed = rk3368_set_rgmii_speed,
+	.set_rmii_speed = rk3368_set_rmii_speed,
+};
+
 static int gmac_clk_init(struct rk_priv_data *bsp_priv)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
@@ -166,49 +304,49 @@ static int gmac_clk_init(struct rk_priv_data *bsp_priv)
 
 	bsp_priv->mac_clk_rx = devm_clk_get(dev, "mac_clk_rx");
 	if (IS_ERR(bsp_priv->mac_clk_rx))
-		dev_err(dev, "%s: cannot get clock %s\n",
-			__func__, "mac_clk_rx");
+		dev_err(dev, "cannot get clock %s\n",
+			"mac_clk_rx");
 
 	bsp_priv->mac_clk_tx = devm_clk_get(dev, "mac_clk_tx");
 	if (IS_ERR(bsp_priv->mac_clk_tx))
-		dev_err(dev, "%s: cannot get clock %s\n",
-			__func__, "mac_clk_tx");
+		dev_err(dev, "cannot get clock %s\n",
+			"mac_clk_tx");
 
 	bsp_priv->aclk_mac = devm_clk_get(dev, "aclk_mac");
 	if (IS_ERR(bsp_priv->aclk_mac))
-		dev_err(dev, "%s: cannot get clock %s\n",
-			__func__, "aclk_mac");
+		dev_err(dev, "cannot get clock %s\n",
+			"aclk_mac");
 
 	bsp_priv->pclk_mac = devm_clk_get(dev, "pclk_mac");
 	if (IS_ERR(bsp_priv->pclk_mac))
-		dev_err(dev, "%s: cannot get clock %s\n",
-			__func__, "pclk_mac");
+		dev_err(dev, "cannot get clock %s\n",
+			"pclk_mac");
 
 	bsp_priv->clk_mac = devm_clk_get(dev, "stmmaceth");
 	if (IS_ERR(bsp_priv->clk_mac))
-		dev_err(dev, "%s: cannot get clock %s\n",
-			__func__, "stmmaceth");
+		dev_err(dev, "cannot get clock %s\n",
+			"stmmaceth");
 
 	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
 		bsp_priv->clk_mac_ref = devm_clk_get(dev, "clk_mac_ref");
 		if (IS_ERR(bsp_priv->clk_mac_ref))
-			dev_err(dev, "%s: cannot get clock %s\n",
-				__func__, "clk_mac_ref");
+			dev_err(dev, "cannot get clock %s\n",
+				"clk_mac_ref");
 
 		if (!bsp_priv->clock_input) {
 			bsp_priv->clk_mac_refout =
 				devm_clk_get(dev, "clk_mac_refout");
 			if (IS_ERR(bsp_priv->clk_mac_refout))
-				dev_err(dev, "%s: cannot get clock %s\n",
-					__func__, "clk_mac_refout");
+				dev_err(dev, "cannot get clock %s\n",
+					"clk_mac_refout");
 		}
 	}
 
 	if (bsp_priv->clock_input) {
-		dev_info(dev, "%s: clock input from PHY\n", __func__);
+		dev_info(dev, "clock input from PHY\n");
 	} else {
 		if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
-			clk_set_rate(bsp_priv->clk_mac_pll, 50000000);
+			clk_set_rate(bsp_priv->clk_mac, 50000000);
 	}
 
 	return 0;
@@ -292,26 +430,25 @@ static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable)
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (!ldo) {
-		dev_err(dev, "%s: no regulator found\n", __func__);
+		dev_err(dev, "no regulator found\n");
 		return -1;
 	}
 
 	if (enable) {
 		ret = regulator_enable(ldo);
 		if (ret)
-			dev_err(dev, "%s: fail to enable phy-supply\n",
-				__func__);
+			dev_err(dev, "fail to enable phy-supply\n");
 	} else {
 		ret = regulator_disable(ldo);
 		if (ret)
-			dev_err(dev, "%s: fail to disable phy-supply\n",
-				__func__);
+			dev_err(dev, "fail to disable phy-supply\n");
 	}
 
 	return 0;
 }
 
-static void *rk_gmac_setup(struct platform_device *pdev)
+static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
+					  struct rk_gmac_ops *ops)
 {
 	struct rk_priv_data *bsp_priv;
 	struct device *dev = &pdev->dev;
@@ -324,6 +461,7 @@ static void *rk_gmac_setup(struct platform_device *pdev)
 		return ERR_PTR(-ENOMEM);
 
 	bsp_priv->phy_iface = of_get_phy_mode(dev->of_node);
+	bsp_priv->ops = ops;
 
 	bsp_priv->regulator = devm_regulator_get_optional(dev, "phy");
 	if (IS_ERR(bsp_priv->regulator)) {
@@ -337,12 +475,11 @@ static void *rk_gmac_setup(struct platform_device *pdev)
 
 	ret = of_property_read_string(dev->of_node, "clock_in_out", &strings);
 	if (ret) {
-		dev_err(dev, "%s: Can not read property: clock_in_out.\n",
-			__func__);
+		dev_err(dev, "Can not read property: clock_in_out.\n");
 		bsp_priv->clock_input = true;
 	} else {
-		dev_info(dev, "%s: clock input or output? (%s).\n",
-			 __func__, strings);
+		dev_info(dev, "clock input or output? (%s).\n",
+			 strings);
 		if (!strcmp(strings, "input"))
 			bsp_priv->clock_input = true;
 		else
@@ -352,22 +489,22 @@ static void *rk_gmac_setup(struct platform_device *pdev)
 	ret = of_property_read_u32(dev->of_node, "tx_delay", &value);
 	if (ret) {
 		bsp_priv->tx_delay = 0x30;
-		dev_err(dev, "%s: Can not read property: tx_delay.", __func__);
-		dev_err(dev, "%s: set tx_delay to 0x%x\n",
-			__func__, bsp_priv->tx_delay);
+		dev_err(dev, "Can not read property: tx_delay.");
+		dev_err(dev, "set tx_delay to 0x%x\n",
+			bsp_priv->tx_delay);
 	} else {
-		dev_info(dev, "%s: TX delay(0x%x).\n", __func__, value);
+		dev_info(dev, "TX delay(0x%x).\n", value);
 		bsp_priv->tx_delay = value;
 	}
 
 	ret = of_property_read_u32(dev->of_node, "rx_delay", &value);
 	if (ret) {
 		bsp_priv->rx_delay = 0x10;
-		dev_err(dev, "%s: Can not read property: rx_delay.", __func__);
-		dev_err(dev, "%s: set rx_delay to 0x%x\n",
-			__func__, bsp_priv->rx_delay);
+		dev_err(dev, "Can not read property: rx_delay.");
+		dev_err(dev, "set rx_delay to 0x%x\n",
+			bsp_priv->rx_delay);
 	} else {
-		dev_info(dev, "%s: RX delay(0x%x).\n", __func__, value);
+		dev_info(dev, "RX delay(0x%x).\n", value);
 		bsp_priv->rx_delay = value;
 	}
 
@@ -377,13 +514,14 @@ static void *rk_gmac_setup(struct platform_device *pdev)
 
 	/*rmii or rgmii*/
 	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
-		dev_info(dev, "%s: init for RGMII\n", __func__);
-		set_to_rgmii(bsp_priv, bsp_priv->tx_delay, bsp_priv->rx_delay);
+		dev_info(dev, "init for RGMII\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay,
+					    bsp_priv->rx_delay);
 	} else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
-		dev_info(dev, "%s: init for RMII\n", __func__);
-		set_to_rmii(bsp_priv);
+		dev_info(dev, "init for RMII\n");
+		bsp_priv->ops->set_to_rmii(bsp_priv);
 	} else {
-		dev_err(dev, "%s: NO interface defined!\n", __func__);
+		dev_err(dev, "NO interface defined!\n");
 	}
 
 	gmac_clk_init(bsp_priv);
@@ -391,6 +529,16 @@ static void *rk_gmac_setup(struct platform_device *pdev)
 	return bsp_priv;
 }
 
+static void *rk3288_gmac_setup(struct platform_device *pdev)
+{
+	return rk_gmac_setup(pdev, &rk3288_ops);
+}
+
+static void *rk3368_gmac_setup(struct platform_device *pdev)
+{
+	return rk_gmac_setup(pdev, &rk3368_ops);
+}
+
 static int rk_gmac_init(struct platform_device *pdev, void *priv)
 {
 	struct rk_priv_data *bsp_priv = priv;
@@ -421,17 +569,47 @@ static void rk_fix_speed(void *priv, unsigned int speed)
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII)
-		set_rgmii_speed(bsp_priv, speed);
+		bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
 	else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
-		set_rmii_speed(bsp_priv, speed);
+		bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
 	else
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
 }
 
-const struct stmmac_of_data rk3288_gmac_data = {
+static const struct stmmac_of_data rk3288_gmac_data = {
 	.has_gmac = 1,
 	.fix_mac_speed = rk_fix_speed,
-	.setup = rk_gmac_setup,
+	.setup = rk3288_gmac_setup,
 	.init = rk_gmac_init,
 	.exit = rk_gmac_exit,
 };
+
+static const struct stmmac_of_data rk3368_gmac_data = {
+	.has_gmac = 1,
+	.fix_mac_speed = rk_fix_speed,
+	.setup = rk3368_gmac_setup,
+	.init = rk_gmac_init,
+	.exit = rk_gmac_exit,
+};
+
+static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_gmac_data},
+	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_gmac_data},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, rk_gmac_dwmac_match);
+
+static struct platform_driver rk_gmac_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "rk_gmac-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = rk_gmac_dwmac_match,
+	},
+};
+module_platform_driver(rk_gmac_dwmac_driver);
+
+MODULE_AUTHOR("Chen-Zhi (Roger Chen) <roger.chen@rock-chips.com>");
+MODULE_DESCRIPTION("Rockchip RK3288 DWMAC specific glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 5a36bd2c7837..8141c5b844ae 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -257,9 +257,28 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv)
 	return ret;
 }
 
-const struct stmmac_of_data socfpga_gmac_data = {
+static const struct stmmac_of_data socfpga_gmac_data = {
 	.setup = socfpga_dwmac_probe,
 	.init = socfpga_dwmac_init,
 	.exit = socfpga_dwmac_exit,
 	.fix_mac_speed = socfpga_dwmac_fix_mac_speed,
 };
+
+static const struct of_device_id socfpga_dwmac_match[] = {
+	{ .compatible = "altr,socfpga-stmmac", .data = &socfpga_gmac_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, socfpga_dwmac_match);
+
+static struct platform_driver socfpga_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "socfpga-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = socfpga_dwmac_match,
+	},
+};
+module_platform_driver(socfpga_dwmac_driver);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index bb6e2dc61bec..a2e8111c5d14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -17,6 +17,7 @@
 #include <linux/stmmac.h>
 #include <linux/phy.h>
 #include <linux/mfd/syscon.h>
+#include <linux/module.h>
 #include <linux/regmap.h>
 #include <linux/clk.h>
 #include <linux/of.h>
@@ -351,16 +352,40 @@ static void *sti_dwmac_setup(struct platform_device *pdev)
 	return dwmac;
 }
 
-const struct stmmac_of_data stih4xx_dwmac_data = {
+static const struct stmmac_of_data stih4xx_dwmac_data = {
 	.fix_mac_speed = stih4xx_fix_retime_src,
 	.setup = sti_dwmac_setup,
 	.init = stix4xx_init,
 	.exit = sti_dwmac_exit,
 };
 
-const struct stmmac_of_data stid127_dwmac_data = {
+static const struct stmmac_of_data stid127_dwmac_data = {
 	.fix_mac_speed = stid127_fix_retime_src,
 	.setup = sti_dwmac_setup,
 	.init = stid127_init,
 	.exit = sti_dwmac_exit,
 };
+
+static const struct of_device_id sti_dwmac_match[] = {
+	{ .compatible = "st,stih415-dwmac", .data = &stih4xx_dwmac_data},
+	{ .compatible = "st,stih416-dwmac", .data = &stih4xx_dwmac_data},
+	{ .compatible = "st,stid127-dwmac", .data = &stid127_dwmac_data},
+	{ .compatible = "st,stih407-dwmac", .data = &stih4xx_dwmac_data},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sti_dwmac_match);
+
+static struct platform_driver sti_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "sti-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = sti_dwmac_match,
+	},
+};
+module_platform_driver(sti_dwmac_driver);
+
+MODULE_AUTHOR("Srinivas Kandagatla <srinivas.kandagatla@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics DWMAC Specific Glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index c5ea9ab75b03..15048ca39759 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -18,7 +18,9 @@
 
 #include <linux/stmmac.h>
 #include <linux/clk.h>
+#include <linux/module.h>
 #include <linux/phy.h>
+#include <linux/platform_device.h>
 #include <linux/of_net.h>
 #include <linux/regulator/consumer.h>
 
@@ -132,7 +134,7 @@ static void sun7i_fix_speed(void *priv, unsigned int speed)
 
 /* of_data specifying hardware features and callbacks.
  * hardware features were copied from Allwinner drivers. */
-const struct stmmac_of_data sun7i_gmac_data = {
+static const struct stmmac_of_data sun7i_gmac_data = {
 	.has_gmac = 1,
 	.tx_coe = 1,
 	.fix_mac_speed = sun7i_fix_speed,
@@ -140,3 +142,24 @@ const struct stmmac_of_data sun7i_gmac_data = {
 	.init = sun7i_gmac_init,
 	.exit = sun7i_gmac_exit,
 };
+
+static const struct of_device_id sun7i_dwmac_match[] = {
+	{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, sun7i_dwmac_match);
+
+static struct platform_driver sun7i_dwmac_driver = {
+	.probe  = stmmac_pltfr_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "sun7i-dwmac",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = sun7i_dwmac_match,
+	},
+};
+module_platform_driver(sun7i_dwmac_driver);
+
+MODULE_AUTHOR("Chen-Yu Tsai <wens@csie.org>");
+MODULE_DESCRIPTION("Allwinner sunxi DWMAC specific glue layer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 1e2bcf5f89e1..7d944449f5ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -240,6 +240,7 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 				  int mode, int end)
 {
+	p->des01.all_flags = 0;
 	p->des01.erx.own = 1;
 	p->des01.erx.buffer1_size = BUF_SIZE_8KiB - 1;
 
@@ -254,7 +255,7 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 
 static void enh_desc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des01.etx.own = 0;
+	p->des01.all_flags = 0;
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_tx_set_on_chain(p, end);
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 35ad4f427ae2..48c3456445b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -123,6 +123,7 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 			       int end)
 {
+	p->des01.all_flags = 0;
 	p->des01.rx.own = 1;
 	p->des01.rx.buffer1_size = BUF_SIZE_2KiB - 1;
 
@@ -137,7 +138,7 @@ static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
 
 static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
 {
-	p->des01.tx.own = 0;
+	p->des01.all_flags = 0;
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_tx_set_on_chain(p, end);
 	else
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 2ac9552d1fa3..1f3b33a6c6a8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -34,6 +34,14 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/reset.h>
 
+struct stmmac_resources {
+	void __iomem *addr;
+	const char *mac;
+	int wol_irq;
+	int lpi_irq;
+	int irq;
+};
+
 struct stmmac_tx_info {
 	dma_addr_t buf;
 	bool map_as_page;
@@ -117,6 +125,12 @@ struct stmmac_priv {
 	int use_riwt;
 	int irq_wake;
 	spinlock_t ptp_lock;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *dbgfs_dir;
+	struct dentry *dbgfs_rings_status;
+	struct dentry *dbgfs_dma_cap;
+#endif
 };
 
 int stmmac_mdio_unregister(struct net_device *ndev);
@@ -129,9 +143,9 @@ void stmmac_ptp_unregister(struct stmmac_priv *priv);
 int stmmac_resume(struct net_device *ndev);
 int stmmac_suspend(struct net_device *ndev);
 int stmmac_dvr_remove(struct net_device *ndev);
-struct stmmac_priv *stmmac_dvr_probe(struct device *device,
-				     struct plat_stmmacenet_data *plat_dat,
-				     void __iomem *addr);
+int stmmac_dvr_probe(struct device *device,
+		     struct plat_stmmacenet_data *plat_dat,
+		     struct stmmac_resources *res);
 void stmmac_disable_eee_mode(struct stmmac_priv *priv);
 bool stmmac_eee_init(struct stmmac_priv *priv);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 05c146f718a3..50f7a7a26821 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -52,6 +52,7 @@
 #include "stmmac_ptp.h"
 #include "stmmac.h"
 #include <linux/reset.h>
+#include <linux/of_mdio.h>
 
 #define STMMAC_ALIGN(x)	L1_CACHE_ALIGN(x)
 
@@ -118,7 +119,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
 
 #ifdef CONFIG_DEBUG_FS
 static int stmmac_init_fs(struct net_device *dev);
-static void stmmac_exit_fs(void);
+static void stmmac_exit_fs(struct net_device *dev);
 #endif
 
 #define STMMAC_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
@@ -816,18 +817,25 @@ static int stmmac_init_phy(struct net_device *dev)
 	priv->speed = 0;
 	priv->oldduplex = -1;
 
-	if (priv->plat->phy_bus_name)
-		snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
-			 priv->plat->phy_bus_name, priv->plat->bus_id);
-	else
-		snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
-			 priv->plat->bus_id);
+	if (priv->plat->phy_node) {
+		phydev = of_phy_connect(dev, priv->plat->phy_node,
+					&stmmac_adjust_link, 0, interface);
+	} else {
+		if (priv->plat->phy_bus_name)
+			snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
+				 priv->plat->phy_bus_name, priv->plat->bus_id);
+		else
+			snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
+				 priv->plat->bus_id);
 
-	snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
-		 priv->plat->phy_addr);
-	pr_debug("stmmac_init_phy:  trying to attach to %s\n", phy_id_fmt);
+		snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+			 priv->plat->phy_addr);
+		pr_debug("stmmac_init_phy:  trying to attach to %s\n",
+			 phy_id_fmt);
 
-	phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, interface);
+		phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link,
+				     interface);
+	}
 
 	if (IS_ERR(phydev)) {
 		pr_err("%s: Could not attach to PHY\n", dev->name);
@@ -848,7 +856,7 @@ static int stmmac_init_phy(struct net_device *dev)
 	 * device as well.
 	 * Note: phydev->phy_id is the result of reading the UID PHY registers.
 	 */
-	if (phydev->phy_id == 0) {
+	if (!priv->plat->phy_node && phydev->phy_id == 0) {
 		phy_disconnect(phydev);
 		return -ENODEV;
 	}
@@ -975,13 +983,11 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct sk_buff *skb;
 
-	skb = __netdev_alloc_skb(priv->dev, priv->dma_buf_sz + NET_IP_ALIGN,
-				 flags);
+	skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
 	if (!skb) {
 		pr_err("%s: Rx init fails; skb is NULL\n", __func__);
 		return -ENOMEM;
 	}
-	skb_reserve(skb, NET_IP_ALIGN);
 	priv->rx_skbuff[i] = skb;
 	priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
 						priv->dma_buf_sz,
@@ -1189,41 +1195,41 @@ static int alloc_dma_desc_resources(struct stmmac_priv *priv)
 		goto err_tx_skbuff;
 
 	if (priv->extend_desc) {
-		priv->dma_erx = dma_alloc_coherent(priv->device, rxsize *
-						   sizeof(struct
-							  dma_extended_desc),
-						   &priv->dma_rx_phy,
-						   GFP_KERNEL);
+		priv->dma_erx = dma_zalloc_coherent(priv->device, rxsize *
+						    sizeof(struct
+							   dma_extended_desc),
+						    &priv->dma_rx_phy,
+						    GFP_KERNEL);
 		if (!priv->dma_erx)
 			goto err_dma;
 
-		priv->dma_etx = dma_alloc_coherent(priv->device, txsize *
-						   sizeof(struct
-							  dma_extended_desc),
-						   &priv->dma_tx_phy,
-						   GFP_KERNEL);
+		priv->dma_etx = dma_zalloc_coherent(priv->device, txsize *
+						    sizeof(struct
+							   dma_extended_desc),
+						    &priv->dma_tx_phy,
+						    GFP_KERNEL);
 		if (!priv->dma_etx) {
 			dma_free_coherent(priv->device, priv->dma_rx_size *
-					sizeof(struct dma_extended_desc),
-					priv->dma_erx, priv->dma_rx_phy);
+					  sizeof(struct dma_extended_desc),
+					  priv->dma_erx, priv->dma_rx_phy);
 			goto err_dma;
 		}
 	} else {
-		priv->dma_rx = dma_alloc_coherent(priv->device, rxsize *
-						  sizeof(struct dma_desc),
-						  &priv->dma_rx_phy,
-						  GFP_KERNEL);
+		priv->dma_rx = dma_zalloc_coherent(priv->device, rxsize *
+						   sizeof(struct dma_desc),
+						   &priv->dma_rx_phy,
+						   GFP_KERNEL);
 		if (!priv->dma_rx)
 			goto err_dma;
 
-		priv->dma_tx = dma_alloc_coherent(priv->device, txsize *
-						  sizeof(struct dma_desc),
-						  &priv->dma_tx_phy,
-						  GFP_KERNEL);
+		priv->dma_tx = dma_zalloc_coherent(priv->device, txsize *
+						   sizeof(struct dma_desc),
+						   &priv->dma_tx_phy,
+						   GFP_KERNEL);
 		if (!priv->dma_tx) {
 			dma_free_coherent(priv->device, priv->dma_rx_size *
-					sizeof(struct dma_desc),
-					priv->dma_rx, priv->dma_rx_phy);
+					  sizeof(struct dma_desc),
+					  priv->dma_rx, priv->dma_rx_phy);
 			goto err_dma;
 		}
 	}
@@ -1916,7 +1922,7 @@ static int stmmac_release(struct net_device *dev)
 	netif_carrier_off(dev);
 
 #ifdef CONFIG_DEBUG_FS
-	stmmac_exit_fs();
+	stmmac_exit_fs(dev);
 #endif
 
 	stmmac_release_ptp(priv);
@@ -2508,8 +2514,6 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 
 #ifdef CONFIG_DEBUG_FS
 static struct dentry *stmmac_fs_dir;
-static struct dentry *stmmac_rings_status;
-static struct dentry *stmmac_dma_cap;
 
 static void sysfs_display_ring(void *head, int size, int extend_desc,
 			       struct seq_file *seq)
@@ -2648,36 +2652,39 @@ static const struct file_operations stmmac_dma_cap_fops = {
 
 static int stmmac_init_fs(struct net_device *dev)
 {
-	/* Create debugfs entries */
-	stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
-		pr_err("ERROR %s, debugfs create directory failed\n",
-		       STMMAC_RESOURCE_NAME);
+	/* Create per netdev entries */
+	priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir);
+
+	if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) {
+		pr_err("ERROR %s/%s, debugfs create directory failed\n",
+		       STMMAC_RESOURCE_NAME, dev->name);
 
 		return -ENOMEM;
 	}
 
 	/* Entry to report DMA RX/TX rings */
-	stmmac_rings_status = debugfs_create_file("descriptors_status",
-						  S_IRUGO, stmmac_fs_dir, dev,
-						  &stmmac_rings_status_fops);
+	priv->dbgfs_rings_status =
+		debugfs_create_file("descriptors_status", S_IRUGO,
+				    priv->dbgfs_dir, dev,
+				    &stmmac_rings_status_fops);
 
-	if (!stmmac_rings_status || IS_ERR(stmmac_rings_status)) {
+	if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) {
 		pr_info("ERROR creating stmmac ring debugfs file\n");
-		debugfs_remove(stmmac_fs_dir);
+		debugfs_remove_recursive(priv->dbgfs_dir);
 
 		return -ENOMEM;
 	}
 
 	/* Entry to report the DMA HW features */
-	stmmac_dma_cap = debugfs_create_file("dma_cap", S_IRUGO, stmmac_fs_dir,
-					     dev, &stmmac_dma_cap_fops);
+	priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", S_IRUGO,
+					    priv->dbgfs_dir,
+					    dev, &stmmac_dma_cap_fops);
 
-	if (!stmmac_dma_cap || IS_ERR(stmmac_dma_cap)) {
+	if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) {
 		pr_info("ERROR creating stmmac MMC debugfs file\n");
-		debugfs_remove(stmmac_rings_status);
-		debugfs_remove(stmmac_fs_dir);
+		debugfs_remove_recursive(priv->dbgfs_dir);
 
 		return -ENOMEM;
 	}
@@ -2685,11 +2692,11 @@ static int stmmac_init_fs(struct net_device *dev)
 	return 0;
 }
 
-static void stmmac_exit_fs(void)
+static void stmmac_exit_fs(struct net_device *dev)
 {
-	debugfs_remove(stmmac_rings_status);
-	debugfs_remove(stmmac_dma_cap);
-	debugfs_remove(stmmac_fs_dir);
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	debugfs_remove_recursive(priv->dbgfs_dir);
 }
 #endif /* CONFIG_DEBUG_FS */
 
@@ -2799,16 +2806,15 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
  * stmmac_dvr_probe
  * @device: device pointer
  * @plat_dat: platform data pointer
- * @addr: iobase memory address
+ * @res: stmmac resource pointer
  * Description: this is the main probe function used to
  * call the alloc_etherdev, allocate the priv structure.
  * Return:
- * on success the new private structure is returned, otherwise the error
- * pointer.
+ * returns 0 on success, otherwise errno.
  */
-struct stmmac_priv *stmmac_dvr_probe(struct device *device,
-				     struct plat_stmmacenet_data *plat_dat,
-				     void __iomem *addr)
+int stmmac_dvr_probe(struct device *device,
+		     struct plat_stmmacenet_data *plat_dat,
+		     struct stmmac_resources *res)
 {
 	int ret = 0;
 	struct net_device *ndev = NULL;
@@ -2816,7 +2822,7 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
 
 	ndev = alloc_etherdev(sizeof(struct stmmac_priv));
 	if (!ndev)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	SET_NETDEV_DEV(ndev, device);
 
@@ -2827,8 +2833,17 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
 	stmmac_set_ethtool_ops(ndev);
 	priv->pause = pause;
 	priv->plat = plat_dat;
-	priv->ioaddr = addr;
-	priv->dev->base_addr = (unsigned long)addr;
+	priv->ioaddr = res->addr;
+	priv->dev->base_addr = (unsigned long)res->addr;
+
+	priv->dev->irq = res->irq;
+	priv->wol_irq = res->wol_irq;
+	priv->lpi_irq = res->lpi_irq;
+
+	if (res->mac)
+		memcpy(priv->dev->dev_addr, res->mac, ETH_ALEN);
+
+	dev_set_drvdata(device, priv);
 
 	/* Verify driver arguments */
 	stmmac_verify_args();
@@ -2943,7 +2958,7 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
 		}
 	}
 
-	return priv;
+	return 0;
 
 error_mdio_register:
 	unregister_netdev(ndev);
@@ -2956,7 +2971,7 @@ error_pclk_get:
 error_clk_get:
 	free_netdev(ndev);
 
-	return ERR_PTR(ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(stmmac_dvr_probe);
 
@@ -3149,6 +3164,35 @@ err:
 __setup("stmmaceth=", stmmac_cmdline_opt);
 #endif /* MODULE */
 
+static int __init stmmac_init(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	/* Create debugfs main directory if it doesn't exist yet */
+	if (!stmmac_fs_dir) {
+		stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL);
+
+		if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) {
+			pr_err("ERROR %s, debugfs create directory failed\n",
+			       STMMAC_RESOURCE_NAME);
+
+			return -ENOMEM;
+		}
+	}
+#endif
+
+	return 0;
+}
+
+static void __exit stmmac_exit(void)
+{
+#ifdef CONFIG_DEBUG_FS
+	debugfs_remove_recursive(stmmac_fs_dir);
+#endif
+}
+
+module_init(stmmac_init)
+module_exit(stmmac_exit)
+
 MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet device driver");
 MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 3bca908716e2..d71a721ea61c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -163,7 +163,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 {
 	struct stmmac_pci_info *info = (struct stmmac_pci_info *)id->driver_data;
 	struct plat_stmmacenet_data *plat;
-	struct stmmac_priv *priv;
+	struct stmmac_resources res;
 	int i;
 	int ret;
 
@@ -214,19 +214,12 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
 
 	pci_enable_msi(pdev);
 
-	priv = stmmac_dvr_probe(&pdev->dev, plat, pcim_iomap_table(pdev)[i]);
-	if (IS_ERR(priv)) {
-		dev_err(&pdev->dev, "%s: main driver probe failed\n", __func__);
-		return PTR_ERR(priv);
-	}
-	priv->dev->irq = pdev->irq;
-	priv->wol_irq = pdev->irq;
-
-	pci_set_drvdata(pdev, priv->dev);
+	memset(&res, 0, sizeof(res));
+	res.addr = pcim_iomap_table(pdev)[i];
+	res.wol_irq = pdev->irq;
+	res.irq = pdev->irq;
 
-	dev_dbg(&pdev->dev, "STMMAC PCI driver registration completed\n");
-
-	return 0;
+	return stmmac_dvr_probe(&pdev->dev, plat, &res);
 }
 
 /**
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 705bbdf93940..f3918c7e7eeb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -23,33 +23,16 @@
 *******************************************************************************/
 
 #include <linux/platform_device.h>
+#include <linux/module.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/of_device.h>
+#include <linux/of_mdio.h>
 
 #include "stmmac.h"
 #include "stmmac_platform.h"
 
-static const struct of_device_id stmmac_dt_ids[] = {
-	/* SoC specific glue layers should come before generic bindings */
-	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_gmac_data},
-	{ .compatible = "amlogic,meson6-dwmac", .data = &meson6_dwmac_data},
-	{ .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data},
-	{ .compatible = "st,stih415-dwmac", .data = &stih4xx_dwmac_data},
-	{ .compatible = "st,stih416-dwmac", .data = &stih4xx_dwmac_data},
-	{ .compatible = "st,stid127-dwmac", .data = &stid127_dwmac_data},
-	{ .compatible = "st,stih407-dwmac", .data = &stih4xx_dwmac_data},
-	{ .compatible = "altr,socfpga-stmmac", .data = &socfpga_gmac_data },
-	{ .compatible = "st,spear600-gmac"},
-	{ .compatible = "snps,dwmac-3.610"},
-	{ .compatible = "snps,dwmac-3.70a"},
-	{ .compatible = "snps,dwmac-3.710"},
-	{ .compatible = "snps,dwmac"},
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, stmmac_dt_ids);
-
 #ifdef CONFIG_OF
 
 /**
@@ -128,14 +111,9 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
 	struct device_node *np = pdev->dev.of_node;
 	struct stmmac_dma_cfg *dma_cfg;
 	const struct of_device_id *device;
+	struct device *dev = &pdev->dev;
 
-	if (!np)
-		return -ENODEV;
-
-	device = of_match_device(stmmac_dt_ids, &pdev->dev);
-	if (!device)
-		return -ENODEV;
-
+	device = of_match_device(dev->driver->of_match_table, dev);
 	if (device->data) {
 		const struct stmmac_of_data *data = device->data;
 		plat->has_gmac = data->has_gmac;
@@ -167,13 +145,24 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
 
+	/* If we find a phy-handle property, use it as the PHY */
+	plat->phy_node = of_parse_phandle(np, "phy-handle", 0);
+
+	/* If phy-handle is not specified, check if we have a fixed-phy */
+	if (!plat->phy_node && of_phy_is_fixed_link(np)) {
+		if ((of_phy_register_fixed_link(np) < 0))
+			return -ENODEV;
+
+		plat->phy_node = of_node_get(np);
+	}
+
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
 	if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
 		dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
 
-	if (plat->phy_bus_name)
+	if (plat->phy_node || plat->phy_bus_name)
 		plat->mdio_bus_data = NULL;
 	else
 		plat->mdio_bus_data =
@@ -231,8 +220,10 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
 	if (of_find_property(np, "snps,pbl", NULL)) {
 		dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
 				       GFP_KERNEL);
-		if (!dma_cfg)
+		if (!dma_cfg) {
+			of_node_put(np);
 			return -ENOMEM;
+		}
 		plat->dma_cfg = dma_cfg;
 		of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
 		dma_cfg->fixed_burst =
@@ -267,27 +258,26 @@ static int stmmac_probe_config_dt(struct platform_device *pdev,
  * the necessary platform resources, invoke custom helper (if required) and
  * invoke the main probe function.
  */
-static int stmmac_pltfr_probe(struct platform_device *pdev)
+int stmmac_pltfr_probe(struct platform_device *pdev)
 {
+	struct stmmac_resources stmmac_res;
 	int ret = 0;
 	struct resource *res;
 	struct device *dev = &pdev->dev;
-	void __iomem *addr = NULL;
-	struct stmmac_priv *priv = NULL;
 	struct plat_stmmacenet_data *plat_dat = NULL;
-	const char *mac = NULL;
-	int irq, wol_irq, lpi_irq;
+
+	memset(&stmmac_res, 0, sizeof(stmmac_res));
 
 	/* Get IRQ information early to have an ability to ask for deferred
 	 * probe if needed before we went too far with resource allocation.
 	 */
-	irq = platform_get_irq_byname(pdev, "macirq");
-	if (irq < 0) {
-		if (irq != -EPROBE_DEFER) {
+	stmmac_res.irq = platform_get_irq_byname(pdev, "macirq");
+	if (stmmac_res.irq < 0) {
+		if (stmmac_res.irq != -EPROBE_DEFER) {
 			dev_err(dev,
 				"MAC IRQ configuration information not found\n");
 		}
-		return irq;
+		return stmmac_res.irq;
 	}
 
 	/* On some platforms e.g. SPEAr the wake up irq differs from the mac irq
@@ -297,21 +287,21 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
 	 * In case the wake up interrupt is not passed from the platform
 	 * so the driver will continue to use the mac irq (ndev->irq)
 	 */
-	wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
-	if (wol_irq < 0) {
-		if (wol_irq == -EPROBE_DEFER)
+	stmmac_res.wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
+	if (stmmac_res.wol_irq < 0) {
+		if (stmmac_res.wol_irq == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
-		wol_irq = irq;
+		stmmac_res.wol_irq = stmmac_res.irq;
 	}
 
-	lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
-	if (lpi_irq == -EPROBE_DEFER)
+	stmmac_res.lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
+	if (stmmac_res.lpi_irq == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	addr = devm_ioremap_resource(dev, res);
-	if (IS_ERR(addr))
-		return PTR_ERR(addr);
+	stmmac_res.addr = devm_ioremap_resource(dev, res);
+	if (IS_ERR(stmmac_res.addr))
+		return PTR_ERR(stmmac_res.addr);
 
 	plat_dat = dev_get_platdata(&pdev->dev);
 
@@ -331,7 +321,7 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
 	plat_dat->unicast_filter_entries = 1;
 
 	if (pdev->dev.of_node) {
-		ret = stmmac_probe_config_dt(pdev, plat_dat, &mac);
+		ret = stmmac_probe_config_dt(pdev, plat_dat, &stmmac_res.mac);
 		if (ret) {
 			pr_err("%s: main dt probe failed", __func__);
 			return ret;
@@ -352,27 +342,9 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
 			return ret;
 	}
 
-	priv = stmmac_dvr_probe(&(pdev->dev), plat_dat, addr);
-	if (IS_ERR(priv)) {
-		pr_err("%s: main driver probe failed", __func__);
-		return PTR_ERR(priv);
-	}
-
-	/* Copy IRQ values to priv structure which is now avaialble */
-	priv->dev->irq = irq;
-	priv->wol_irq = wol_irq;
-	priv->lpi_irq = lpi_irq;
-
-	/* Get MAC address if available (DT) */
-	if (mac)
-		memcpy(priv->dev->dev_addr, mac, ETH_ALEN);
-
-	platform_set_drvdata(pdev, priv->dev);
-
-	pr_debug("STMMAC platform driver registration completed");
-
-	return 0;
+	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 }
+EXPORT_SYMBOL_GPL(stmmac_pltfr_probe);
 
 /**
  * stmmac_pltfr_remove
@@ -380,7 +352,7 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
  * Description: this function calls the main to free the net resources
  * and calls the platforms hook and release the resources (e.g. mem).
  */
-static int stmmac_pltfr_remove(struct platform_device *pdev)
+int stmmac_pltfr_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -394,6 +366,7 @@ static int stmmac_pltfr_remove(struct platform_device *pdev)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(stmmac_pltfr_remove);
 
 #ifdef CONFIG_PM_SLEEP
 /**
@@ -437,21 +410,6 @@ static int stmmac_pltfr_resume(struct device *dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-static SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops,
-			 stmmac_pltfr_suspend, stmmac_pltfr_resume);
-
-static struct platform_driver stmmac_pltfr_driver = {
-	.probe = stmmac_pltfr_probe,
-	.remove = stmmac_pltfr_remove,
-	.driver = {
-		   .name = STMMAC_RESOURCE_NAME,
-		   .pm = &stmmac_pltfr_pm_ops,
-		   .of_match_table = of_match_ptr(stmmac_dt_ids),
-	},
-};
-
-module_platform_driver(stmmac_pltfr_driver);
-
-MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet PLATFORM driver");
-MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
-MODULE_LICENSE("GPL");
+SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
+				       stmmac_pltfr_resume);
+EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
index 093eb99e5ffd..71da86d7bd00 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h
@@ -19,11 +19,8 @@
 #ifndef __STMMAC_PLATFORM_H__
 #define __STMMAC_PLATFORM_H__
 
-extern const struct stmmac_of_data meson6_dwmac_data;
-extern const struct stmmac_of_data sun7i_gmac_data;
-extern const struct stmmac_of_data stih4xx_dwmac_data;
-extern const struct stmmac_of_data stid127_dwmac_data;
-extern const struct stmmac_of_data socfpga_gmac_data;
-extern const struct stmmac_of_data rk3288_gmac_data;
+int stmmac_pltfr_probe(struct platform_device *pdev);
+int stmmac_pltfr_remove(struct platform_device *pdev);
+extern const struct dev_pm_ops stmmac_pltfr_pm_ops;
 
 #endif /* __STMMAC_PLATFORM_H__ */
diff --git a/drivers/net/ethernet/sun/Kconfig b/drivers/net/ethernet/sun/Kconfig
index 3074aa374c6b..dee94b67638c 100644
--- a/drivers/net/ethernet/sun/Kconfig
+++ b/drivers/net/ethernet/sun/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_SUN
 	default y
 	depends on SUN3 || SBUS || PCI || SUN_LDOMS
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say
-	  Y and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 3dc1f68b322d..6ce973187225 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -3058,7 +3058,6 @@ static void cas_init_mac(struct cas *cp)
 	/* setup core arbitration weight register */
 	writel(CAWR_RR_DIS, cp->regs + REG_CAWR);
 
-	/* XXX Use pci_dma_burst_advice() */
 #if !defined(CONFIG_SPARC64) && !defined(CONFIG_ALPHA)
 	/* set the infinite burst register for chips that don't have
 	 * pci issues.
diff --git a/drivers/net/ethernet/tehuti/Kconfig b/drivers/net/ethernet/tehuti/Kconfig
index 1fc027eda33e..b17f0ca3f395 100644
--- a/drivers/net/ethernet/tehuti/Kconfig
+++ b/drivers/net/ethernet/tehuti/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_TEHUTI
 	default y
 	depends on PCI
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 631e0afd07d2..e7f0b7d95b65 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_TI
 	default y
 	depends on PCI || EISA || AR7 || ARCH_DAVINCI || ARCH_OMAP2PLUS || ARCH_KEYSTONE
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -110,9 +108,7 @@ config TLAN
 	depends on (PCI || EISA)
 	---help---
 	  If you have a PCI Ethernet network card based on the ThunderLAN chip
-	  which is supported by this driver, say Y and read the
-	  Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  which is supported by this driver, say Y here.
 
 	  Devices currently supported by this driver are Compaq Netelligent,
 	  Compaq NetFlex and Olicom cards.  Please read the file
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b536b4c82752..462820514fae 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1361,7 +1361,6 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 	if (cpsw_common_res_usage_state(priv) <= 1) {
 		cpts_unregister(priv->cpts);
 		cpsw_intr_disable(priv);
-		cpdma_ctlr_int_ctrl(priv->dma, false);
 		cpdma_ctlr_stop(priv->dma);
 		cpsw_ale_stop(priv->ale);
 	}
@@ -1456,7 +1455,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 
 		if (priv->cpts->rx_enable)
 			ctrl |= CTRL_V2_RX_TS_BITS;
-	break;
+		break;
 	case CPSW_VERSION_3:
 	default:
 		ctrl &= ~CTRL_V3_ALL_TS_MASK;
@@ -1466,7 +1465,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 
 		if (priv->cpts->rx_enable)
 			ctrl |= CTRL_V3_RX_TS_BITS;
-	break;
+		break;
 	}
 
 	mtype = (30 << TS_SEQ_ID_OFFSET_SHIFT) | EVENT_MSG_BITS;
@@ -1589,10 +1588,8 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev)
 	cpsw_err(priv, tx_err, "transmit timeout, restarting dma\n");
 	ndev->stats.tx_errors++;
 	cpsw_intr_disable(priv);
-	cpdma_ctlr_int_ctrl(priv->dma, false);
 	cpdma_chan_stop(priv->txch);
 	cpdma_chan_start(priv->txch);
-	cpdma_ctlr_int_ctrl(priv->dma, true);
 	cpsw_intr_enable(priv);
 }
 
@@ -1629,10 +1626,8 @@ static void cpsw_ndo_poll_controller(struct net_device *ndev)
 	struct cpsw_priv *priv = netdev_priv(ndev);
 
 	cpsw_intr_disable(priv);
-	cpdma_ctlr_int_ctrl(priv->dma, false);
 	cpsw_rx_interrupt(priv->irqs_table[0], priv);
 	cpsw_tx_interrupt(priv->irqs_table[1], priv);
-	cpdma_ctlr_int_ctrl(priv->dma, true);
 	cpsw_intr_enable(priv);
 }
 #endif
diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 6e927b4583aa..43b061bd8e07 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -268,39 +268,6 @@ int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
 }
 EXPORT_SYMBOL_GPL(cpsw_ale_flush_multicast);
 
-static void cpsw_ale_flush_ucast(struct cpsw_ale *ale, u32 *ale_entry,
-				 int port_mask)
-{
-	int port;
-
-	port = cpsw_ale_get_port_num(ale_entry);
-	if ((BIT(port) & port_mask) == 0)
-		return; /* ports dont intersect, not interested */
-	cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
-}
-
-int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask)
-{
-	u32 ale_entry[ALE_ENTRY_WORDS];
-	int ret, idx;
-
-	for (idx = 0; idx < ale->params.ale_entries; idx++) {
-		cpsw_ale_read(ale, idx, ale_entry);
-		ret = cpsw_ale_get_entry_type(ale_entry);
-		if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR)
-			continue;
-
-		if (cpsw_ale_get_mcast(ale_entry))
-			cpsw_ale_flush_mcast(ale, ale_entry, port_mask);
-		else
-			cpsw_ale_flush_ucast(ale, ale_entry, port_mask);
-
-		cpsw_ale_write(ale, idx, ale_entry);
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cpsw_ale_flush);
-
 static inline void cpsw_ale_set_vlan_entry_type(u32 *ale_entry,
 						int flags, u16 vid)
 {
@@ -752,18 +719,6 @@ static void cpsw_ale_timer(unsigned long arg)
 	}
 }
 
-int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout)
-{
-	del_timer_sync(&ale->timer);
-	ale->ageout = ageout * HZ;
-	if (ale->ageout) {
-		ale->timer.expires = jiffies + ale->ageout;
-		add_timer(&ale->timer);
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cpsw_ale_set_ageout);
-
 void cpsw_ale_start(struct cpsw_ale *ale)
 {
 	u32 rev;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index af1e7ecd87c6..a7001894f3da 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -90,8 +90,6 @@ int cpsw_ale_destroy(struct cpsw_ale *ale);
 void cpsw_ale_start(struct cpsw_ale *ale);
 void cpsw_ale_stop(struct cpsw_ale *ale);
 
-int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout);
-int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask);
 int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid);
 int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port,
 		       int flags, u16 vid);
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 43efc3a0cda5..5ec4ed3f6c8d 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -537,7 +537,7 @@ int netcp_unregister_rxhook(struct netcp_intf *netcp_priv, int order,
 static void netcp_frag_free(bool is_frag, void *ptr)
 {
 	if (is_frag)
-		put_page(virt_to_head_page(ptr));
+		skb_free_frag(ptr);
 	else
 		kfree(ptr);
 }
@@ -698,7 +698,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp)
 		}
 	}
 
-	netcp->ndev->last_rx = jiffies;
 	netcp->ndev->stats.rx_packets++;
 	netcp->ndev->stats.rx_bytes += skb->len;
 
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index 3d8f60d9643e..6f0a4495c7f3 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -721,9 +721,6 @@ static bool tile_net_poll_aux(struct tile_net_cpu *info, int index)
 	if (!hash_default)
 		__inv_buffer(buf, len);
 
-	/* ISSUE: Is this needed? */
-	dev->last_rx = jiffies;
-
 #ifdef TILE_NET_DUMP_PACKETS
 	dump_packet(buf, len, "rx");
 #endif /* TILE_NET_DUMP_PACKETS */
diff --git a/drivers/net/ethernet/toshiba/Kconfig b/drivers/net/ethernet/toshiba/Kconfig
index 5d244b6b5e3a..6f1d5b623768 100644
--- a/drivers/net/ethernet/toshiba/Kconfig
+++ b/drivers/net/ethernet/toshiba/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_TOSHIBA
 	default y
 	depends on PCI && (PPC_IBM_CELL_BLADE || MIPS) || PPC_PS3
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index ac62a5e248b0..79f0ec4e51ac 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -102,6 +102,18 @@ static void gelic_card_get_ether_port_status(struct gelic_card *card,
 	}
 }
 
+/**
+ * gelic_descr_get_status -- returns the status of a descriptor
+ * @descr: descriptor to look at
+ *
+ * returns the status as in the dmac_cmd_status field of the descriptor
+ */
+static enum gelic_descr_dma_status
+gelic_descr_get_status(struct gelic_descr *descr)
+{
+	return be32_to_cpu(descr->dmac_cmd_status) & GELIC_DESCR_DMA_STAT_MASK;
+}
+
 static int gelic_card_set_link_mode(struct gelic_card *card, int mode)
 {
 	int status;
@@ -278,18 +290,6 @@ void gelic_card_down(struct gelic_card *card)
 }
 
 /**
- * gelic_descr_get_status -- returns the status of a descriptor
- * @descr: descriptor to look at
- *
- * returns the status as in the dmac_cmd_status field of the descriptor
- */
-static enum gelic_descr_dma_status
-gelic_descr_get_status(struct gelic_descr *descr)
-{
-	return be32_to_cpu(descr->dmac_cmd_status) & GELIC_DESCR_DMA_STAT_MASK;
-}
-
-/**
  * gelic_card_free_chain - free descriptor chain
  * @card: card structure
  * @descr_in: address of desc
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 8e9371a3388a..3c54a2cae5df 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -604,8 +604,7 @@ spider_net_set_multi(struct net_device *netdev)
 	int i;
 	u32 reg;
 	struct spider_net_card *card = netdev_priv(netdev);
-	unsigned long bitmask[SPIDER_NET_MULTICAST_HASHES / BITS_PER_LONG] =
-		{0, };
+	DECLARE_BITMAP(bitmask, SPIDER_NET_MULTICAST_HASHES) = {};
 
 	spider_net_set_promisc(card);
 
diff --git a/drivers/net/ethernet/tundra/Kconfig b/drivers/net/ethernet/tundra/Kconfig
index cf7d69b62c42..81d845e4e23b 100644
--- a/drivers/net/ethernet/tundra/Kconfig
+++ b/drivers/net/ethernet/tundra/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_TUNDRA
 	default y
 	depends on TSI108_BRIDGE
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index f66ddaee0c87..8b0b1d6aca72 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -6,9 +6,7 @@ config NET_VENDOR_VIA
 	bool "VIA devices"
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -19,7 +17,7 @@ if NET_VENDOR_VIA
 
 config VIA_RHINE
 	tristate "VIA Rhine support"
-	depends on (PCI || USE_OF)
+	depends on (PCI || OF_IRQ)
 	select CRC32
 	select MII
 	---help---
@@ -43,7 +41,7 @@ config VIA_RHINE_MMIO
 
 config VIA_VELOCITY
 	tristate "VIA Velocity support"
-	depends on (PCI || USE_OF)
+	depends on (PCI || (OF_ADDRESS && OF_IRQ))
 	select CRC32
 	select CRC_CCITT
 	select MII
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index de2850497c09..a83263743665 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -96,7 +96,6 @@ static const int multicast_filter_limit = 32;
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
@@ -472,8 +471,7 @@ struct rhine_private {
 
 	/* Frequently used values: keep some adjacent for cache effect. */
 	u32 quirks;
-	struct rx_desc *rx_head_desc;
-	unsigned int cur_rx, dirty_rx;	/* Producer/consumer ring indices */
+	unsigned int cur_rx;
 	unsigned int cur_tx, dirty_tx;
 	unsigned int rx_buf_sz;		/* Based on MTU+slack. */
 	struct rhine_stats rx_stats;
@@ -1213,17 +1211,61 @@ static void free_ring(struct net_device* dev)
 
 }
 
-static void alloc_rbufs(struct net_device *dev)
+struct rhine_skb_dma {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+};
+
+static inline int rhine_skb_dma_init(struct net_device *dev,
+				     struct rhine_skb_dma *sd)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	struct device *hwdev = dev->dev.parent;
-	dma_addr_t next;
+	const int size = rp->rx_buf_sz;
+
+	sd->skb = netdev_alloc_skb(dev, size);
+	if (!sd->skb)
+		return -ENOMEM;
+
+	sd->dma = dma_map_single(hwdev, sd->skb->data, size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(hwdev, sd->dma))) {
+		netif_err(rp, drv, dev, "Rx DMA mapping failure\n");
+		dev_kfree_skb_any(sd->skb);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void rhine_reset_rbufs(struct rhine_private *rp)
+{
 	int i;
 
-	rp->dirty_rx = rp->cur_rx = 0;
+	rp->cur_rx = 0;
+
+	for (i = 0; i < RX_RING_SIZE; i++)
+		rp->rx_ring[i].rx_status = cpu_to_le32(DescOwn);
+}
+
+static inline void rhine_skb_dma_nic_store(struct rhine_private *rp,
+					   struct rhine_skb_dma *sd, int entry)
+{
+	rp->rx_skbuff_dma[entry] = sd->dma;
+	rp->rx_skbuff[entry] = sd->skb;
+
+	rp->rx_ring[entry].addr = cpu_to_le32(sd->dma);
+	dma_wmb();
+}
+
+static void free_rbufs(struct net_device* dev);
+
+static int alloc_rbufs(struct net_device *dev)
+{
+	struct rhine_private *rp = netdev_priv(dev);
+	dma_addr_t next;
+	int rc, i;
 
 	rp->rx_buf_sz = (dev->mtu <= 1500 ? PKT_BUF_SZ : dev->mtu + 32);
-	rp->rx_head_desc = &rp->rx_ring[0];
 	next = rp->rx_ring_dma;
 
 	/* Init the ring entries */
@@ -1239,23 +1281,20 @@ static void alloc_rbufs(struct net_device *dev)
 
 	/* Fill in the Rx buffers.  Handle allocation failure gracefully. */
 	for (i = 0; i < RX_RING_SIZE; i++) {
-		struct sk_buff *skb = netdev_alloc_skb(dev, rp->rx_buf_sz);
-		rp->rx_skbuff[i] = skb;
-		if (skb == NULL)
-			break;
+		struct rhine_skb_dma sd;
 
-		rp->rx_skbuff_dma[i] =
-			dma_map_single(hwdev, skb->data, rp->rx_buf_sz,
-				       DMA_FROM_DEVICE);
-		if (dma_mapping_error(hwdev, rp->rx_skbuff_dma[i])) {
-			rp->rx_skbuff_dma[i] = 0;
-			dev_kfree_skb(skb);
-			break;
+		rc = rhine_skb_dma_init(dev, &sd);
+		if (rc < 0) {
+			free_rbufs(dev);
+			goto out;
 		}
-		rp->rx_ring[i].addr = cpu_to_le32(rp->rx_skbuff_dma[i]);
-		rp->rx_ring[i].rx_status = cpu_to_le32(DescOwn);
+
+		rhine_skb_dma_nic_store(rp, &sd, i);
 	}
-	rp->dirty_rx = (unsigned int)(i - RX_RING_SIZE);
+
+	rhine_reset_rbufs(rp);
+out:
+	return rc;
 }
 
 static void free_rbufs(struct net_device* dev)
@@ -1659,16 +1698,18 @@ static int rhine_open(struct net_device *dev)
 
 	rc = request_irq(rp->irq, rhine_interrupt, IRQF_SHARED, dev->name, dev);
 	if (rc)
-		return rc;
+		goto out;
 
 	netif_dbg(rp, ifup, dev, "%s() irq %d\n", __func__, rp->irq);
 
 	rc = alloc_ring(dev);
-	if (rc) {
-		free_irq(rp->irq, dev);
-		return rc;
-	}
-	alloc_rbufs(dev);
+	if (rc < 0)
+		goto out_free_irq;
+
+	rc = alloc_rbufs(dev);
+	if (rc < 0)
+		goto out_free_ring;
+
 	alloc_tbufs(dev);
 	rhine_chip_reset(dev);
 	rhine_task_enable(rp);
@@ -1680,7 +1721,14 @@ static int rhine_open(struct net_device *dev)
 
 	netif_start_queue(dev);
 
-	return 0;
+out:
+	return rc;
+
+out_free_ring:
+	free_ring(dev);
+out_free_irq:
+	free_irq(rp->irq, dev);
+	goto out;
 }
 
 static void rhine_reset_task(struct work_struct *work)
@@ -1700,9 +1748,9 @@ static void rhine_reset_task(struct work_struct *work)
 
 	/* clear all descriptors */
 	free_tbufs(dev);
-	free_rbufs(dev);
 	alloc_tbufs(dev);
-	alloc_rbufs(dev);
+
+	rhine_reset_rbufs(rp);
 
 	/* Reinitialize the hardware. */
 	rhine_chip_reset(dev);
@@ -1730,6 +1778,11 @@ static void rhine_tx_timeout(struct net_device *dev)
 	schedule_work(&rp->reset_task);
 }
 
+static inline bool rhine_tx_queue_full(struct rhine_private *rp)
+{
+	return (rp->cur_tx - rp->dirty_tx) >= TX_QUEUE_LEN;
+}
+
 static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 				  struct net_device *dev)
 {
@@ -1800,11 +1853,17 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 
 	netdev_sent_queue(dev, skb->len);
 	/* lock eth irq */
-	wmb();
+	dma_wmb();
 	rp->tx_ring[entry].tx_status |= cpu_to_le32(DescOwn);
 	wmb();
 
 	rp->cur_tx++;
+	/*
+	 * Nobody wants cur_tx write to rot for ages after the NIC will have
+	 * seen the transmit request, especially as the transmit completion
+	 * handler could miss it.
+	 */
+	smp_wmb();
 
 	/* Non-x86 Todo: explicitly flush cache lines here. */
 
@@ -1817,8 +1876,14 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 	       ioaddr + ChipCmd1);
 	IOSYNC;
 
-	if (rp->cur_tx == rp->dirty_tx + TX_QUEUE_LEN)
+	/* dirty_tx may be pessimistically out-of-sync. See rhine_tx. */
+	if (rhine_tx_queue_full(rp)) {
 		netif_stop_queue(dev);
+		smp_rmb();
+		/* Rejuvenate. */
+		if (!rhine_tx_queue_full(rp))
+			netif_wake_queue(dev);
+	}
 
 	netif_dbg(rp, tx_queued, dev, "Transmit frame #%d queued in slot %d\n",
 		  rp->cur_tx - 1, entry);
@@ -1866,13 +1931,24 @@ static void rhine_tx(struct net_device *dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	struct device *hwdev = dev->dev.parent;
-	int txstatus = 0, entry = rp->dirty_tx % TX_RING_SIZE;
 	unsigned int pkts_compl = 0, bytes_compl = 0;
+	unsigned int dirty_tx = rp->dirty_tx;
+	unsigned int cur_tx;
 	struct sk_buff *skb;
 
+	/*
+	 * The race with rhine_start_tx does not matter here as long as the
+	 * driver enforces a value of cur_tx that was relevant when the
+	 * packet was scheduled to the network chipset.
+	 * Executive summary: smp_rmb() balances smp_wmb() in rhine_start_tx.
+	 */
+	smp_rmb();
+	cur_tx = rp->cur_tx;
 	/* find and cleanup dirty tx descriptors */
-	while (rp->dirty_tx != rp->cur_tx) {
-		txstatus = le32_to_cpu(rp->tx_ring[entry].tx_status);
+	while (dirty_tx != cur_tx) {
+		unsigned int entry = dirty_tx % TX_RING_SIZE;
+		u32 txstatus = le32_to_cpu(rp->tx_ring[entry].tx_status);
+
 		netif_dbg(rp, tx_done, dev, "Tx scavenge %d status %08x\n",
 			  entry, txstatus);
 		if (txstatus & DescOwn)
@@ -1921,12 +1997,23 @@ static void rhine_tx(struct net_device *dev)
 		pkts_compl++;
 		dev_consume_skb_any(skb);
 		rp->tx_skbuff[entry] = NULL;
-		entry = (++rp->dirty_tx) % TX_RING_SIZE;
+		dirty_tx++;
 	}
 
+	rp->dirty_tx = dirty_tx;
+	/* Pity we can't rely on the nearby BQL completion implicit barrier. */
+	smp_wmb();
+
 	netdev_completed_queue(dev, pkts_compl, bytes_compl);
-	if ((rp->cur_tx - rp->dirty_tx) < TX_QUEUE_LEN - 4)
+
+	/* cur_tx may be optimistically out-of-sync. See rhine_start_tx. */
+	if (!rhine_tx_queue_full(rp) && netif_queue_stopped(dev)) {
 		netif_wake_queue(dev);
+		smp_rmb();
+		/* Rejuvenate. */
+		if (rhine_tx_queue_full(rp))
+			netif_stop_queue(dev);
+	}
 }
 
 /**
@@ -1944,22 +2031,33 @@ static inline u16 rhine_get_vlan_tci(struct sk_buff *skb, int data_size)
 	return be16_to_cpup((__be16 *)trailer);
 }
 
+static inline void rhine_rx_vlan_tag(struct sk_buff *skb, struct rx_desc *desc,
+				     int data_size)
+{
+	dma_rmb();
+	if (unlikely(desc->desc_length & cpu_to_le32(DescTag))) {
+		u16 vlan_tci;
+
+		vlan_tci = rhine_get_vlan_tci(skb, data_size);
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+	}
+}
+
 /* Process up to limit frames from receive ring */
 static int rhine_rx(struct net_device *dev, int limit)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 	struct device *hwdev = dev->dev.parent;
-	int count;
 	int entry = rp->cur_rx % RX_RING_SIZE;
+	int count;
 
 	netif_dbg(rp, rx_status, dev, "%s(), entry %d status %08x\n", __func__,
-		  entry, le32_to_cpu(rp->rx_head_desc->rx_status));
+		  entry, le32_to_cpu(rp->rx_ring[entry].rx_status));
 
 	/* If EOP is set on the next entry, it's a new packet. Send it up. */
 	for (count = 0; count < limit; ++count) {
-		struct rx_desc *desc = rp->rx_head_desc;
+		struct rx_desc *desc = rp->rx_ring + entry;
 		u32 desc_status = le32_to_cpu(desc->rx_status);
-		u32 desc_length = le32_to_cpu(desc->desc_length);
 		int data_size = desc_status >> 16;
 
 		if (desc_status & DescOwn)
@@ -1975,10 +2073,6 @@ static int rhine_rx(struct net_device *dev, int limit)
 	"entry %#x length %d status %08x!\n",
 					    entry, data_size,
 					    desc_status);
-				netdev_warn(dev,
-					    "Oversized Ethernet frame %p vs %p\n",
-					    rp->rx_head_desc,
-					    &rp->rx_ring[entry]);
 				dev->stats.rx_length_errors++;
 			} else if (desc_status & RxErr) {
 				/* There was a error. */
@@ -2000,16 +2094,17 @@ static int rhine_rx(struct net_device *dev, int limit)
 				}
 			}
 		} else {
-			struct sk_buff *skb = NULL;
 			/* Length should omit the CRC */
 			int pkt_len = data_size - 4;
-			u16 vlan_tci = 0;
+			struct sk_buff *skb;
 
 			/* Check if the packet is long enough to accept without
 			   copying to a minimally-sized skbuff. */
-			if (pkt_len < rx_copybreak)
+			if (pkt_len < rx_copybreak) {
 				skb = netdev_alloc_skb_ip_align(dev, pkt_len);
-			if (skb) {
+				if (unlikely(!skb))
+					goto drop;
+
 				dma_sync_single_for_cpu(hwdev,
 							rp->rx_skbuff_dma[entry],
 							rp->rx_buf_sz,
@@ -2018,32 +2113,31 @@ static int rhine_rx(struct net_device *dev, int limit)
 				skb_copy_to_linear_data(skb,
 						 rp->rx_skbuff[entry]->data,
 						 pkt_len);
-				skb_put(skb, pkt_len);
+
 				dma_sync_single_for_device(hwdev,
 							   rp->rx_skbuff_dma[entry],
 							   rp->rx_buf_sz,
 							   DMA_FROM_DEVICE);
 			} else {
+				struct rhine_skb_dma sd;
+
+				if (unlikely(rhine_skb_dma_init(dev, &sd) < 0))
+					goto drop;
+
 				skb = rp->rx_skbuff[entry];
-				if (skb == NULL) {
-					netdev_err(dev, "Inconsistent Rx descriptor chain\n");
-					break;
-				}
-				rp->rx_skbuff[entry] = NULL;
-				skb_put(skb, pkt_len);
+
 				dma_unmap_single(hwdev,
 						 rp->rx_skbuff_dma[entry],
 						 rp->rx_buf_sz,
 						 DMA_FROM_DEVICE);
+				rhine_skb_dma_nic_store(rp, &sd, entry);
 			}
 
-			if (unlikely(desc_length & DescTag))
-				vlan_tci = rhine_get_vlan_tci(skb, data_size);
-
+			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, dev);
 
-			if (unlikely(desc_length & DescTag))
-				__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+			rhine_rx_vlan_tag(skb, desc, data_size);
+
 			netif_receive_skb(skb);
 
 			u64_stats_update_begin(&rp->rx_stats.syncp);
@@ -2051,35 +2145,16 @@ static int rhine_rx(struct net_device *dev, int limit)
 			rp->rx_stats.packets++;
 			u64_stats_update_end(&rp->rx_stats.syncp);
 		}
+give_descriptor_to_nic:
+		desc->rx_status = cpu_to_le32(DescOwn);
 		entry = (++rp->cur_rx) % RX_RING_SIZE;
-		rp->rx_head_desc = &rp->rx_ring[entry];
-	}
-
-	/* Refill the Rx ring buffers. */
-	for (; rp->cur_rx - rp->dirty_rx > 0; rp->dirty_rx++) {
-		struct sk_buff *skb;
-		entry = rp->dirty_rx % RX_RING_SIZE;
-		if (rp->rx_skbuff[entry] == NULL) {
-			skb = netdev_alloc_skb(dev, rp->rx_buf_sz);
-			rp->rx_skbuff[entry] = skb;
-			if (skb == NULL)
-				break;	/* Better luck next round. */
-			rp->rx_skbuff_dma[entry] =
-				dma_map_single(hwdev, skb->data,
-					       rp->rx_buf_sz,
-					       DMA_FROM_DEVICE);
-			if (dma_mapping_error(hwdev,
-					      rp->rx_skbuff_dma[entry])) {
-				dev_kfree_skb(skb);
-				rp->rx_skbuff_dma[entry] = 0;
-				break;
-			}
-			rp->rx_ring[entry].addr = cpu_to_le32(rp->rx_skbuff_dma[entry]);
-		}
-		rp->rx_ring[entry].rx_status = cpu_to_le32(DescOwn);
 	}
 
 	return count;
+
+drop:
+	dev->stats.rx_dropped++;
+	goto give_descriptor_to_nic;
 }
 
 static void rhine_restart_tx(struct net_device *dev) {
@@ -2484,9 +2559,8 @@ static int rhine_resume(struct device *device)
 	enable_mmio(rp->pioaddr, rp->quirks);
 	rhine_power_init(dev);
 	free_tbufs(dev);
-	free_rbufs(dev);
 	alloc_tbufs(dev);
-	alloc_rbufs(dev);
+	rhine_reset_rbufs(rp);
 	rhine_task_enable(rp);
 	spin_lock_bh(&rp->lock);
 	init_registers(dev);
diff --git a/drivers/net/ethernet/wiznet/Kconfig b/drivers/net/ethernet/wiznet/Kconfig
index b4d281626fb4..f98b91d21f33 100644
--- a/drivers/net/ethernet/wiznet/Kconfig
+++ b/drivers/net/ethernet/wiznet/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_WIZNET
 	depends on HAS_IOMEM
 	default y
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig
index 7b90a5eba099..4f5c024c6192 100644
--- a/drivers/net/ethernet/xilinx/Kconfig
+++ b/drivers/net/ethernet/xilinx/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_XILINX
 	default y
 	depends on PPC || PPC32 || MICROBLAZE || ARCH_ZYNQ
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 690a4c36b316..5a1068df7038 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -62,12 +62,12 @@
 
 u32 temac_ior(struct temac_local *lp, int offset)
 {
-	return in_be32((u32 *)(lp->regs + offset));
+	return in_be32(lp->regs + offset);
 }
 
 void temac_iow(struct temac_local *lp, int offset, u32 value)
 {
-	out_be32((u32 *) (lp->regs + offset), value);
+	out_be32(lp->regs + offset, value);
 }
 
 int temac_indirect_busywait(struct temac_local *lp)
@@ -124,7 +124,7 @@ void temac_indirect_out32(struct temac_local *lp, int reg, u32 value)
  */
 static u32 temac_dma_in32(struct temac_local *lp, int reg)
 {
-	return in_be32((u32 *)(lp->sdma_regs + (reg << 2)));
+	return in_be32(lp->sdma_regs + (reg << 2));
 }
 
 /**
@@ -134,7 +134,7 @@ static u32 temac_dma_in32(struct temac_local *lp, int reg)
  */
 static void temac_dma_out32(struct temac_local *lp, int reg, u32 value)
 {
-	out_be32((u32 *)(lp->sdma_regs + (reg << 2)), value);
+	out_be32(lp->sdma_regs + (reg << 2), value);
 }
 
 /* DMA register access functions can be DCR based or memory mapped.
@@ -400,7 +400,7 @@ static void temac_set_multicast_list(struct net_device *ndev)
 	mutex_unlock(&lp->indirect_mutex);
 }
 
-struct temac_option {
+static struct temac_option {
 	int flg;
 	u32 opt;
 	u32 reg;
@@ -587,7 +587,7 @@ static void temac_device_reset(struct net_device *ndev)
 	ndev->trans_start = jiffies; /* prevent tx timeout */
 }
 
-void temac_adjust_link(struct net_device *ndev)
+static void temac_adjust_link(struct net_device *ndev)
 {
 	struct temac_local *lp = netdev_priv(ndev);
 	struct phy_device *phy = lp->phy_dev;
@@ -688,10 +688,8 @@ static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
 	if (temac_check_tx_bd_space(lp, num_frag)) {
-		if (!netif_queue_stopped(ndev)) {
+		if (!netif_queue_stopped(ndev))
 			netif_stop_queue(ndev);
-			return NETDEV_TX_BUSY;
-		}
 		return NETDEV_TX_BUSY;
 	}
 
@@ -707,8 +705,8 @@ static int temac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	cur_p->app0 |= STS_CTRL_APP0_SOP;
 	cur_p->len = skb_headlen(skb);
-	cur_p->phys = dma_map_single(ndev->dev.parent, skb->data, skb->len,
-				     DMA_TO_DEVICE);
+	cur_p->phys = dma_map_single(ndev->dev.parent, skb->data,
+				     skb_headlen(skb), DMA_TO_DEVICE);
 	cur_p->app4 = (unsigned long)skb;
 
 	for (ii = 0; ii < num_frag; ii++) {
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 4c9b4fa1d3c1..7cb9abac95c8 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -11,16 +11,16 @@
 #include <linux/netdevice.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/if_vlan.h>
 
 /* Packet size info */
 #define XAE_HDR_SIZE			14 /* Size of Ethernet header */
-#define XAE_HDR_VLAN_SIZE		18 /* Size of an Ethernet hdr + VLAN */
 #define XAE_TRL_SIZE			 4 /* Size of Ethernet trailer (FCS) */
 #define XAE_MTU			      1500 /* Max MTU of an Ethernet frame */
 #define XAE_JUMBO_MTU		      9000 /* Max MTU of a jumbo Eth. frame */
 
 #define XAE_MAX_FRAME_SIZE	 (XAE_MTU + XAE_HDR_SIZE + XAE_TRL_SIZE)
-#define XAE_MAX_VLAN_FRAME_SIZE  (XAE_MTU + XAE_HDR_VLAN_SIZE + XAE_TRL_SIZE)
+#define XAE_MAX_VLAN_FRAME_SIZE  (XAE_MTU + VLAN_ETH_HLEN + XAE_TRL_SIZE)
 #define XAE_MAX_JUMBO_FRAME_SIZE (XAE_JUMBO_MTU + XAE_HDR_SIZE + XAE_TRL_SIZE)
 
 /* Configuration options */
@@ -38,18 +38,21 @@
 #define XAE_OPTION_FLOW_CONTROL			(1 << 4)
 
 /* Strip FCS and PAD from incoming frames. Note: PAD from VLAN frames is not
- * stripped. Default: disabled (set) */
+ * stripped. Default: disabled (set)
+ */
 #define XAE_OPTION_FCS_STRIP			(1 << 5)
 
 /* Generate FCS field and add PAD automatically for outgoing frames.
- * Default: enabled (set) */
+ * Default: enabled (set)
+ */
 #define XAE_OPTION_FCS_INSERT			(1 << 6)
 
 /* Enable Length/Type error checking for incoming frames. When this option is
  * set, the MAC will filter frames that have a mismatched type/length field
  * and if XAE_OPTION_REPORT_RXERR is set, the user is notified when these
  * types of frames are encountered. When this option is cleared, the MAC will
- * allow these types of frames to be received. Default: enabled (set) */
+ * allow these types of frames to be received. Default: enabled (set)
+ */
 #define XAE_OPTION_LENTYPE_ERR			(1 << 7)
 
 /* Enable the transmitter. Default: enabled (set) */
@@ -159,12 +162,12 @@
 #define XAE_MDIO_MWD_OFFSET	0x00000508 /* MII Management Write Data */
 #define XAE_MDIO_MRD_OFFSET	0x0000050C /* MII Management Read Data */
 #define XAE_MDIO_MIS_OFFSET	0x00000600 /* MII Management Interrupt Status */
-#define XAE_MDIO_MIP_OFFSET	0x00000620 /* MII Mgmt Interrupt Pending
-					    * register offset */
-#define XAE_MDIO_MIE_OFFSET	0x00000640 /* MII Management Interrupt Enable
-					    * register offset */
-#define XAE_MDIO_MIC_OFFSET	0x00000660 /* MII Management Interrupt Clear
-					    * register offset. */
+/* MII Mgmt Interrupt Pending register offset */
+#define XAE_MDIO_MIP_OFFSET	0x00000620
+/* MII Management Interrupt Enable register offset */
+#define XAE_MDIO_MIE_OFFSET	0x00000640
+/* MII Management Interrupt Clear register offset. */
+#define XAE_MDIO_MIC_OFFSET	0x00000660
 #define XAE_UAW0_OFFSET		0x00000700 /* Unicast address word 0 */
 #define XAE_UAW1_OFFSET		0x00000704 /* Unicast address word 1 */
 #define XAE_FMI_OFFSET		0x00000708 /* Filter Mask Index */
@@ -176,18 +179,17 @@
 #define XAE_MCAST_TABLE_OFFSET	0x00020000 /* Multicast table address */
 
 /* Bit Masks for Axi Ethernet RAF register */
-#define XAE_RAF_MCSTREJ_MASK		0x00000002 /* Reject receive multicast
-						    * destination address */
-#define XAE_RAF_BCSTREJ_MASK		0x00000004 /* Reject receive broadcast
-						    * destination address */
+/* Reject receive multicast destination address */
+#define XAE_RAF_MCSTREJ_MASK		0x00000002
+/* Reject receive broadcast destination address */
+#define XAE_RAF_BCSTREJ_MASK		0x00000004
 #define XAE_RAF_TXVTAGMODE_MASK		0x00000018 /* Tx VLAN TAG mode */
 #define XAE_RAF_RXVTAGMODE_MASK		0x00000060 /* Rx VLAN TAG mode */
 #define XAE_RAF_TXVSTRPMODE_MASK	0x00000180 /* Tx VLAN STRIP mode */
 #define XAE_RAF_RXVSTRPMODE_MASK	0x00000600 /* Rx VLAN STRIP mode */
 #define XAE_RAF_NEWFNCENBL_MASK		0x00000800 /* New function mode */
-#define XAE_RAF_EMULTIFLTRENBL_MASK	0x00001000 /* Exteneded Multicast
-						    * Filtering mode
-						    */
+/* Exteneded Multicast Filtering mode */
+#define XAE_RAF_EMULTIFLTRENBL_MASK	0x00001000
 #define XAE_RAF_STATSRST_MASK		0x00002000 /* Stats. Counter Reset */
 #define XAE_RAF_RXBADFRMEN_MASK		0x00004000 /* Recv Bad Frame Enable */
 #define XAE_RAF_TXVTAGMODE_SHIFT	3 /* Tx Tag mode shift bits */
@@ -197,15 +199,16 @@
 
 /* Bit Masks for Axi Ethernet TPF and IFGP registers */
 #define XAE_TPF_TPFV_MASK		0x0000FFFF /* Tx pause frame value */
-#define XAE_IFGP0_IFGP_MASK		0x0000007F /* Transmit inter-frame
-						    * gap adjustment value */
+/* Transmit inter-frame gap adjustment value */
+#define XAE_IFGP0_IFGP_MASK		0x0000007F
 
 /* Bit Masks for Axi Ethernet IS, IE and IP registers, Same masks apply
- * for all 3 registers. */
-#define XAE_INT_HARDACSCMPLT_MASK	0x00000001 /* Hard register access
-						    * complete */
-#define XAE_INT_AUTONEG_MASK		0x00000002 /* Auto negotiation
-						    * complete */
+ * for all 3 registers.
+ */
+/* Hard register access complete */
+#define XAE_INT_HARDACSCMPLT_MASK	0x00000001
+/* Auto negotiation complete */
+#define XAE_INT_AUTONEG_MASK		0x00000002
 #define XAE_INT_RXCMPIT_MASK		0x00000004 /* Rx complete */
 #define XAE_INT_RXRJECT_MASK		0x00000008 /* Rx frame rejected */
 #define XAE_INT_RXFIFOOVR_MASK		0x00000010 /* Rx fifo overrun */
@@ -215,10 +218,9 @@
 #define XAE_INT_PHYRSTCMPLT_MASK	0x00000100 /* Phy Reset complete */
 #define XAE_INT_ALL_MASK		0x0000003F /* All the ints */
 
+/* INT bits that indicate receive errors */
 #define XAE_INT_RECV_ERROR_MASK				\
-	(XAE_INT_RXRJECT_MASK | XAE_INT_RXFIFOOVR_MASK) /* INT bits that
-							 * indicate receive
-							 * errors */
+	(XAE_INT_RXRJECT_MASK | XAE_INT_RXFIFOOVR_MASK)
 
 /* Bit masks for Axi Ethernet VLAN TPID Word 0 register */
 #define XAE_TPID_0_MASK		0x0000FFFF /* TPID 0 */
@@ -231,27 +233,28 @@
 /* Bit masks for Axi Ethernet RCW1 register */
 #define XAE_RCW1_RST_MASK	0x80000000 /* Reset */
 #define XAE_RCW1_JUM_MASK	0x40000000 /* Jumbo frame enable */
-#define XAE_RCW1_FCS_MASK	0x20000000 /* In-Band FCS enable
-					    * (FCS not stripped) */
+/* In-Band FCS enable (FCS not stripped) */
+#define XAE_RCW1_FCS_MASK	0x20000000
 #define XAE_RCW1_RX_MASK	0x10000000 /* Receiver enable */
 #define XAE_RCW1_VLAN_MASK	0x08000000 /* VLAN frame enable */
-#define XAE_RCW1_LT_DIS_MASK	0x02000000 /* Length/type field valid check
-					    * disable */
-#define XAE_RCW1_CL_DIS_MASK	0x01000000 /* Control frame Length check
-					    * disable */
-#define XAE_RCW1_PAUSEADDR_MASK 0x0000FFFF /* Pause frame source address
-					    * bits [47:32]. Bits [31:0] are
-					    * stored in register RCW0 */
+/* Length/type field valid check disable */
+#define XAE_RCW1_LT_DIS_MASK	0x02000000
+/* Control frame Length check disable */
+#define XAE_RCW1_CL_DIS_MASK	0x01000000
+/* Pause frame source address bits [47:32]. Bits [31:0] are
+ * stored in register RCW0
+ */
+#define XAE_RCW1_PAUSEADDR_MASK 0x0000FFFF
 
 /* Bit masks for Axi Ethernet TC register */
 #define XAE_TC_RST_MASK		0x80000000 /* Reset */
 #define XAE_TC_JUM_MASK		0x40000000 /* Jumbo frame enable */
-#define XAE_TC_FCS_MASK		0x20000000 /* In-Band FCS enable
-					    * (FCS not generated) */
+/* In-Band FCS enable (FCS not generated) */
+#define XAE_TC_FCS_MASK		0x20000000
 #define XAE_TC_TX_MASK		0x10000000 /* Transmitter enable */
 #define XAE_TC_VLAN_MASK	0x08000000 /* VLAN frame enable */
-#define XAE_TC_IFG_MASK		0x02000000 /* Inter-frame gap adjustment
-					    * enable */
+/* Inter-frame gap adjustment enable */
+#define XAE_TC_IFG_MASK		0x02000000
 
 /* Bit masks for Axi Ethernet FCC register */
 #define XAE_FCC_FCRX_MASK	0x20000000 /* Rx flow control enable */
@@ -301,10 +304,10 @@
 #define XAE_MDIO_INT_MIIM_RDY_MASK	0x00000001 /* MIIM Interrupt */
 
 /* Bit masks for Axi Ethernet UAW1 register */
-#define XAE_UAW1_UNICASTADDR_MASK	0x0000FFFF /* Station address bits
-						    * [47:32]; Station address
-						    * bits [31:0] are stored in
-						    * register UAW0 */
+/* Station address bits [47:32]; Station address
+ * bits [31:0] are stored in register UAW0
+ */
+#define XAE_UAW1_UNICASTADDR_MASK	0x0000FFFF
 
 /* Bit masks for Axi Ethernet FMI register */
 #define XAE_FMI_PM_MASK			0x80000000 /* Promis. mode enable */
@@ -320,8 +323,8 @@
 #define XAE_PHY_TYPE_SGMII		4
 #define XAE_PHY_TYPE_1000BASE_X		5
 
-#define XAE_MULTICAST_CAM_TABLE_NUM	4 /* Total number of entries in the
-					   * hardware multicast table. */
+ /* Total number of entries in the hardware multicast table. */
+#define XAE_MULTICAST_CAM_TABLE_NUM	4
 
 /* Axi Ethernet Synthesis features */
 #define XAE_FEATURE_PARTIAL_RX_CSUM	(1 << 0)
@@ -407,8 +410,11 @@ struct axidma_bd {
  *		  Txed/Rxed in the existing hardware. If jumbo option is
  *		  supported, the maximum frame size would be 9k. Else it is
  *		  1522 bytes (assuming support for basic VLAN)
- * @jumbo_support: Stores hardware configuration for jumbo support. If hardware
- *		   can handle jumbo packets, this entry will be 1, else 0.
+ * @rxmem:	Stores rx memory size for jumbo frame handling.
+ * @csum_offload_on_tx_path:	Stores the checksum selection on TX side.
+ * @csum_offload_on_rx_path:	Stores the checksum selection on RX side.
+ * @coalesce_count_rx:	Store the irq coalesce on RX side.
+ * @coalesce_count_tx:	Store the irq coalesce on TX side.
  */
 struct axienet_local {
 	struct net_device *ndev;
@@ -446,7 +452,7 @@ struct axienet_local {
 	u32 rx_bd_ci;
 
 	u32 max_frm_size;
-	u32 jumbo_support;
+	u32 rxmem;
 
 	int csum_offload_on_tx_path;
 	int csum_offload_on_rx_path;
@@ -472,7 +478,7 @@ struct axienet_option {
  * @lp:         Pointer to axienet local structure
  * @offset:     Address offset from the base address of Axi Ethernet core
  *
- * returns: The contents of the Axi Ethernet register
+ * Return: The contents of the Axi Ethernet register
  *
  * This function returns the contents of the corresponding register.
  */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 28b7e7d9c272..4208dd7ef101 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -117,7 +117,7 @@ static struct axienet_option axienet_options[] = {
  * @lp:		Pointer to axienet local structure
  * @reg:	Address offset from the base address of the Axi DMA core
  *
- * returns: The contents of the Axi DMA register
+ * Return: The contents of the Axi DMA register
  *
  * This function returns the contents of the corresponding Axi DMA register.
  */
@@ -179,8 +179,7 @@ static void axienet_dma_bd_release(struct net_device *ndev)
  * axienet_dma_bd_init - Setup buffer descriptor rings for Axi DMA
  * @ndev:	Pointer to the net_device structure
  *
- * returns: 0, on success
- *	    -ENOMEM, on failure
+ * Return: 0, on success -ENOMEM, on failure
  *
  * This function is called to initialize the Rx and Tx DMA descriptor
  * rings. This initializes the descriptors with required default values
@@ -198,9 +197,7 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 	lp->tx_bd_tail = 0;
 	lp->rx_bd_ci = 0;
 
-	/*
-	 * Allocate the Tx and Rx buffer descriptors.
-	 */
+	/* Allocate the Tx and Rx buffer descriptors. */
 	lp->tx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
 					  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
 					  &lp->tx_bd_p, GFP_KERNEL);
@@ -263,7 +260,8 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
 
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
-	 * halted state. This will make the Rx side ready for reception.*/
+	 * halted state. This will make the Rx side ready for reception.
+	 */
 	axienet_dma_out32(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
@@ -273,7 +271,8 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
-	 * tail pointer register that the Tx channel will start transmitting */
+	 * tail pointer register that the Tx channel will start transmitting.
+	 */
 	axienet_dma_out32(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
@@ -320,7 +319,7 @@ static void axienet_set_mac_address(struct net_device *ndev, void *address)
  * @ndev:	Pointer to the net_device structure
  * @p:		6 byte Address to be written as MAC address
  *
- * returns: 0 for all conditions. Presently, there is no failure case.
+ * Return: 0 for all conditions. Presently, there is no failure case.
  *
  * This function is called to initialize the MAC address of the Axi Ethernet
  * core. It calls the core specific axienet_set_mac_address. This is the
@@ -354,7 +353,8 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 	    netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) {
 		/* We must make the kernel realize we had to move into
 		 * promiscuous mode. If it was a promiscuous mode request
-		 * the flag is already set. If not we set it. */
+		 * the flag is already set. If not we set it.
+		 */
 		ndev->flags |= IFF_PROMISC;
 		reg = axienet_ior(lp, XAE_FMI_OFFSET);
 		reg |= XAE_FMI_PM_MASK;
@@ -438,14 +438,15 @@ static void __axienet_device_reset(struct axienet_local *lp,
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
 	 * commands/transfers will be flushed or completed during this
-	 * reset process. */
+	 * reset process.
+	 */
 	axienet_dma_out32(lp, offset, XAXIDMA_CR_RESET_MASK);
 	timeout = DELAY_OF_ONE_MILLISEC;
 	while (axienet_dma_in32(lp, offset) & XAXIDMA_CR_RESET_MASK) {
 		udelay(1);
 		if (--timeout == 0) {
-			dev_err(dev, "axienet_device_reset DMA "
-				"reset timeout!\n");
+			netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
+				   __func__);
 			break;
 		}
 	}
@@ -471,19 +472,21 @@ static void axienet_device_reset(struct net_device *ndev)
 	__axienet_device_reset(lp, &ndev->dev, XAXIDMA_RX_CR_OFFSET);
 
 	lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE;
+	lp->options |= XAE_OPTION_VLAN;
 	lp->options &= (~XAE_OPTION_JUMBO);
 
 	if ((ndev->mtu > XAE_MTU) &&
-	    (ndev->mtu <= XAE_JUMBO_MTU) &&
-	    (lp->jumbo_support)) {
-		lp->max_frm_size = ndev->mtu + XAE_HDR_VLAN_SIZE +
-				   XAE_TRL_SIZE;
-		lp->options |= XAE_OPTION_JUMBO;
+		(ndev->mtu <= XAE_JUMBO_MTU)) {
+		lp->max_frm_size = ndev->mtu + VLAN_ETH_HLEN +
+					XAE_TRL_SIZE;
+
+		if (lp->max_frm_size <= lp->rxmem)
+			lp->options |= XAE_OPTION_JUMBO;
 	}
 
 	if (axienet_dma_bd_init(ndev)) {
-		dev_err(&ndev->dev, "axienet_device_reset descriptor "
-			"allocation failed\n");
+		netdev_err(ndev, "%s: descriptor allocation failed\n",
+			   __func__);
 	}
 
 	axienet_status = axienet_ior(lp, XAE_RCW1_OFFSET);
@@ -497,7 +500,8 @@ static void axienet_device_reset(struct net_device *ndev)
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
 	/* Sync default options with HW but leave receiver and
-	 * transmitter disabled.*/
+	 * transmitter disabled.
+	 */
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 	axienet_set_mac_address(ndev, NULL);
@@ -558,8 +562,8 @@ static void axienet_adjust_link(struct net_device *ndev)
 			lp->last_link = link_state;
 			phy_print_status(phy);
 		} else {
-			dev_err(&ndev->dev, "Error setting Axi Ethernet "
-				"mac speed\n");
+			netdev_err(ndev,
+				   "Error setting Axi Ethernet mac speed\n");
 		}
 	}
 }
@@ -617,7 +621,7 @@ static void axienet_start_xmit_done(struct net_device *ndev)
  * @lp:		Pointer to the axienet_local structure
  * @num_frag:	The number of BDs to check for
  *
- * returns: 0, on success
+ * Return: 0, on success
  *	    NETDEV_TX_BUSY, if any of the descriptors are not free
  *
  * This function is invoked before BDs are allocated and transmission starts.
@@ -640,7 +644,7 @@ static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
  * @skb:	sk_buff pointer that contains data to be Txed.
  * @ndev:	Pointer to net_device structure.
  *
- * returns: NETDEV_TX_OK, on success
+ * Return: NETDEV_TX_OK, on success
  *	    NETDEV_TX_BUSY, if any of the descriptors are not free
  *
  * This function is invoked from upper layers to initiate transmission. The
@@ -726,15 +730,15 @@ static void axienet_recv(struct net_device *ndev)
 	u32 csumstatus;
 	u32 size = 0;
 	u32 packets = 0;
-	dma_addr_t tail_p;
+	dma_addr_t tail_p = 0;
 	struct axienet_local *lp = netdev_priv(ndev);
 	struct sk_buff *skb, *new_skb;
 	struct axidma_bd *cur_p;
 
-	tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
 	cur_p = &lp->rx_bd_v[lp->rx_bd_ci];
 
 	while ((cur_p->status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
+		tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
 		skb = (struct sk_buff *) (cur_p->sw_id_offset);
 		length = cur_p->app4 & 0x0000FFFF;
 
@@ -786,7 +790,8 @@ static void axienet_recv(struct net_device *ndev)
 	ndev->stats.rx_packets += packets;
 	ndev->stats.rx_bytes += size;
 
-	axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
+	if (tail_p)
+		axienet_dma_out32(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
 }
 
 /**
@@ -794,7 +799,7 @@ static void axienet_recv(struct net_device *ndev)
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * returns: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED for all cases.
  *
  * This is the Axi DMA Tx done Isr. It invokes "axienet_start_xmit_done"
  * to complete the BD processing.
@@ -808,6 +813,7 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 
 	status = axienet_dma_in32(lp, XAXIDMA_TX_SR_OFFSET);
 	if (status & (XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK)) {
+		axienet_dma_out32(lp, XAXIDMA_TX_SR_OFFSET, status);
 		axienet_start_xmit_done(lp->ndev);
 		goto out;
 	}
@@ -831,9 +837,9 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
 
 		tasklet_schedule(&lp->dma_err_tasklet);
+		axienet_dma_out32(lp, XAXIDMA_TX_SR_OFFSET, status);
 	}
 out:
-	axienet_dma_out32(lp, XAXIDMA_TX_SR_OFFSET, status);
 	return IRQ_HANDLED;
 }
 
@@ -842,7 +848,7 @@ out:
  * @irq:	irq number
  * @_ndev:	net_device pointer
  *
- * returns: IRQ_HANDLED for all cases.
+ * Return: IRQ_HANDLED for all cases.
  *
  * This is the Axi DMA Rx Isr. It invokes "axienet_recv" to complete the BD
  * processing.
@@ -856,6 +862,7 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 
 	status = axienet_dma_in32(lp, XAXIDMA_RX_SR_OFFSET);
 	if (status & (XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK)) {
+		axienet_dma_out32(lp, XAXIDMA_RX_SR_OFFSET, status);
 		axienet_recv(lp->ndev);
 		goto out;
 	}
@@ -879,9 +886,9 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
 
 		tasklet_schedule(&lp->dma_err_tasklet);
+		axienet_dma_out32(lp, XAXIDMA_RX_SR_OFFSET, status);
 	}
 out:
-	axienet_dma_out32(lp, XAXIDMA_RX_SR_OFFSET, status);
 	return IRQ_HANDLED;
 }
 
@@ -891,7 +898,7 @@ static void axienet_dma_err_handler(unsigned long data);
  * axienet_open - Driver open routine.
  * @ndev:	Pointer to net_device structure
  *
- * returns: 0, on success.
+ * Return: 0, on success.
  *	    -ENODEV, if PHY cannot be connected to
  *	    non-zero error value on failure
  *
@@ -914,7 +921,8 @@ static int axienet_open(struct net_device *ndev)
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
 	 * including the MDIO. If MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards. */
+	 * process is started, MDIO will be broken afterwards.
+	 */
 	axienet_iow(lp, XAE_MDIO_MC_OFFSET,
 		    (mdio_mcreg & (~XAE_MDIO_MC_MDIOEN_MASK)));
 	axienet_device_reset(ndev);
@@ -925,14 +933,20 @@ static int axienet_open(struct net_device *ndev)
 		return ret;
 
 	if (lp->phy_node) {
-		lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node,
+		if (lp->phy_type == XAE_PHY_TYPE_GMII) {
+			lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node,
 					     axienet_adjust_link, 0,
 					     PHY_INTERFACE_MODE_GMII);
-		if (!lp->phy_dev) {
-			dev_err(lp->dev, "of_phy_connect() failed\n");
-			return -ENODEV;
+		} else if (lp->phy_type == XAE_PHY_TYPE_RGMII_2_0) {
+			lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node,
+					     axienet_adjust_link, 0,
+					     PHY_INTERFACE_MODE_RGMII_ID);
 		}
-		phy_start(lp->phy_dev);
+
+		if (!lp->phy_dev)
+			dev_err(lp->dev, "of_phy_connect() failed\n");
+		else
+			phy_start(lp->phy_dev);
 	}
 
 	/* Enable tasklets for Axi DMA error handling */
@@ -965,7 +979,7 @@ err_tx_irq:
  * axienet_stop - Driver stop routine.
  * @ndev:	Pointer to net_device structure
  *
- * returns: 0, on success.
+ * Return: 0, on success.
  *
  * This is the driver stop routine. It calls phy_disconnect to stop the PHY
  * device. It also removes the interrupt handlers and disables the interrupts.
@@ -1005,7 +1019,7 @@ static int axienet_stop(struct net_device *ndev)
  * @ndev:	Pointer to net_device structure
  * @new_mtu:	New mtu value to be applied
  *
- * returns: Always returns 0 (success).
+ * Return: Always returns 0 (success).
  *
  * This is the change mtu driver routine. It checks if the Axi Ethernet
  * hardware supports jumbo frames before changing the mtu. This can be
@@ -1017,15 +1031,15 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu)
 
 	if (netif_running(ndev))
 		return -EBUSY;
-	if (lp->jumbo_support) {
-		if ((new_mtu > XAE_JUMBO_MTU) || (new_mtu < 64))
-			return -EINVAL;
-		ndev->mtu = new_mtu;
-	} else {
-		if ((new_mtu > XAE_MTU) || (new_mtu < 64))
-			return -EINVAL;
-		ndev->mtu = new_mtu;
-	}
+
+	if ((new_mtu + VLAN_ETH_HLEN +
+		XAE_TRL_SIZE) > lp->rxmem)
+		return -EINVAL;
+
+	if ((new_mtu > XAE_JUMBO_MTU) || (new_mtu < 64))
+		return -EINVAL;
+
+	ndev->mtu = new_mtu;
 
 	return 0;
 }
@@ -1072,6 +1086,8 @@ static const struct net_device_ops axienet_netdev_ops = {
  * not be found, the function returns -ENODEV. This function calls the
  * relevant PHY ethtool API to get the PHY settings.
  * Issue "ethtool ethX" under linux prompt to execute this function.
+ *
+ * Return: 0 on success, -ENODEV if PHY doesn't exist
  */
 static int axienet_ethtools_get_settings(struct net_device *ndev,
 					 struct ethtool_cmd *ecmd)
@@ -1093,6 +1109,8 @@ static int axienet_ethtools_get_settings(struct net_device *ndev,
  * relevant PHY ethtool API to set the PHY.
  * Issue e.g. "ethtool -s ethX speed 1000" under linux prompt to execute this
  * function.
+ *
+ * Return: 0 on success, -ENODEV if PHY doesn't exist
  */
 static int axienet_ethtools_set_settings(struct net_device *ndev,
 					 struct ethtool_cmd *ecmd)
@@ -1127,6 +1145,8 @@ static void axienet_ethtools_get_drvinfo(struct net_device *ndev,
  *
  * This implements ethtool command for getting the total register length
  * information.
+ *
+ * Return: the total regs length
  */
 static int axienet_ethtools_get_regs_len(struct net_device *ndev)
 {
@@ -1213,11 +1233,13 @@ axienet_ethtools_get_pauseparam(struct net_device *ndev,
  * axienet_ethtools_set_pauseparam - Set device pause parameter(flow control)
  *				     settings.
  * @ndev:	Pointer to net_device structure
- * @epauseparam:Pointer to ethtool_pauseparam structure
+ * @epauseparm:Pointer to ethtool_pauseparam structure
  *
  * This implements ethtool command for enabling flow control on Rx and Tx
  * paths. Issue "ethtool -A ethX tx on|off" under linux prompt to execute this
  * function.
+ *
+ * Return: 0 on success, -EFAULT if device is running
  */
 static int
 axienet_ethtools_set_pauseparam(struct net_device *ndev,
@@ -1227,8 +1249,8 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
 	struct axienet_local *lp = netdev_priv(ndev);
 
 	if (netif_running(ndev)) {
-		printk(KERN_ERR	"%s: Please stop netif before applying "
-		       "configruation\n", ndev->name);
+		netdev_err(ndev,
+			   "Please stop netif before applying configuration\n");
 		return -EFAULT;
 	}
 
@@ -1254,6 +1276,8 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
  * This implements ethtool command for getting the DMA interrupt coalescing
  * count on Tx and Rx paths. Issue "ethtool -c ethX" under linux prompt to
  * execute this function.
+ *
+ * Return: 0 always
  */
 static int axienet_ethtools_get_coalesce(struct net_device *ndev,
 					 struct ethtool_coalesce *ecoalesce)
@@ -1277,6 +1301,8 @@ static int axienet_ethtools_get_coalesce(struct net_device *ndev,
  * This implements ethtool command for setting the DMA interrupt coalescing
  * count on Tx and Rx paths. Issue "ethtool -C ethX rx-frames 5" under linux
  * prompt to execute this function.
+ *
+ * Return: 0, on success, Non-zero error value on failure.
  */
 static int axienet_ethtools_set_coalesce(struct net_device *ndev,
 					 struct ethtool_coalesce *ecoalesce)
@@ -1284,8 +1310,8 @@ static int axienet_ethtools_set_coalesce(struct net_device *ndev,
 	struct axienet_local *lp = netdev_priv(ndev);
 
 	if (netif_running(ndev)) {
-		printk(KERN_ERR	"%s: Please stop netif before applying "
-		       "configruation\n", ndev->name);
+		netdev_err(ndev,
+			   "Please stop netif before applying configuration\n");
 		return -EFAULT;
 	}
 
@@ -1354,7 +1380,8 @@ static void axienet_dma_err_handler(unsigned long data)
 	/* Disable the MDIO interface till Axi Ethernet Reset is completed.
 	 * When we do an Axi Ethernet reset, it resets the complete core
 	 * including the MDIO. So if MDIO is not disabled when the reset
-	 * process is started, MDIO will be broken afterwards. */
+	 * process is started, MDIO will be broken afterwards.
+	 */
 	axienet_iow(lp, XAE_MDIO_MC_OFFSET, (mdio_mcreg &
 		    ~XAE_MDIO_MC_MDIOEN_MASK));
 
@@ -1425,7 +1452,8 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
 
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
-	 * halted state. This will make the Rx side ready for reception.*/
+	 * halted state. This will make the Rx side ready for reception.
+	 */
 	axienet_dma_out32(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET,
@@ -1435,7 +1463,8 @@ static void axienet_dma_err_handler(unsigned long data)
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
-	 * tail pointer register that the Tx channel will start transmitting */
+	 * tail pointer register that the Tx channel will start transmitting
+	 */
 	axienet_dma_out32(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET,
@@ -1451,7 +1480,8 @@ static void axienet_dma_err_handler(unsigned long data)
 	axienet_iow(lp, XAE_FCC_OFFSET, XAE_FCC_FCRX_MASK);
 
 	/* Sync default options with HW but leave receiver and
-	 * transmitter disabled.*/
+	 * transmitter disabled.
+	 */
 	axienet_setoptions(ndev, lp->options &
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 	axienet_set_mac_address(ndev, NULL);
@@ -1460,11 +1490,10 @@ static void axienet_dma_err_handler(unsigned long data)
 }
 
 /**
- * axienet_of_probe - Axi Ethernet probe function.
- * @op:		Pointer to platform device structure.
- * @match:	Pointer to device id structure
+ * axienet_probe - Axi Ethernet probe function.
+ * @pdev:	Pointer to platform device structure.
  *
- * returns: 0, on success
+ * Return: 0, on success
  *	    Non-zero error value on failure.
  *
  * This is the probe routine for Axi Ethernet driver. This is called before
@@ -1472,22 +1501,23 @@ static void axienet_dma_err_handler(unsigned long data)
  * device. Parses through device tree and populates fields of
  * axienet_local. It registers the Ethernet device.
  */
-static int axienet_of_probe(struct platform_device *op)
+static int axienet_probe(struct platform_device *pdev)
 {
-	__be32 *p;
-	int size, ret = 0;
+	int ret;
 	struct device_node *np;
 	struct axienet_local *lp;
 	struct net_device *ndev;
-	const void *addr;
+	u8 mac_addr[6];
+	struct resource *ethres, dmares;
+	u32 value;
 
 	ndev = alloc_etherdev(sizeof(*lp));
 	if (!ndev)
 		return -ENOMEM;
 
-	platform_set_drvdata(op, ndev);
+	platform_set_drvdata(pdev, ndev);
 
-	SET_NETDEV_DEV(ndev, &op->dev);
+	SET_NETDEV_DEV(ndev, &pdev->dev);
 	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
 	ndev->features = NETIF_F_SG;
 	ndev->netdev_ops = &axienet_netdev_ops;
@@ -1495,21 +1525,23 @@ static int axienet_of_probe(struct platform_device *op)
 
 	lp = netdev_priv(ndev);
 	lp->ndev = ndev;
-	lp->dev = &op->dev;
+	lp->dev = &pdev->dev;
 	lp->options = XAE_OPTION_DEFAULTS;
 	/* Map device registers */
-	lp->regs = of_iomap(op->dev.of_node, 0);
+	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	lp->regs = devm_ioremap_resource(&pdev->dev, ethres);
 	if (!lp->regs) {
-		dev_err(&op->dev, "could not map Axi Ethernet regs.\n");
+		dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n");
 		ret = -ENOMEM;
-		goto nodev;
+		goto free_netdev;
 	}
+
 	/* Setup checksum offload, but default to off if not specified */
 	lp->features = 0;
 
-	p = (__be32 *) of_get_property(op->dev.of_node, "xlnx,txcsum", NULL);
-	if (p) {
-		switch (be32_to_cpup(p)) {
+	ret = of_property_read_u32(pdev->dev.of_node, "xlnx,txcsum", &value);
+	if (!ret) {
+		switch (value) {
 		case 1:
 			lp->csum_offload_on_tx_path =
 				XAE_FEATURE_PARTIAL_TX_CSUM;
@@ -1528,9 +1560,9 @@ static int axienet_of_probe(struct platform_device *op)
 			lp->csum_offload_on_tx_path = XAE_NO_CSUM_OFFLOAD;
 		}
 	}
-	p = (__be32 *) of_get_property(op->dev.of_node, "xlnx,rxcsum", NULL);
-	if (p) {
-		switch (be32_to_cpup(p)) {
+	ret = of_property_read_u32(pdev->dev.of_node, "xlnx,rxcsum", &value);
+	if (!ret) {
+		switch (value) {
 		case 1:
 			lp->csum_offload_on_rx_path =
 				XAE_FEATURE_PARTIAL_RX_CSUM;
@@ -1546,82 +1578,77 @@ static int axienet_of_probe(struct platform_device *op)
 		}
 	}
 	/* For supporting jumbo frames, the Axi Ethernet hardware must have
-	 * a larger Rx/Tx Memory. Typically, the size must be more than or
-	 * equal to 16384 bytes, so that we can enable jumbo option and start
-	 * supporting jumbo frames. Here we check for memory allocated for
-	 * Rx/Tx in the hardware from the device-tree and accordingly set
-	 * flags. */
-	p = (__be32 *) of_get_property(op->dev.of_node, "xlnx,rxmem", NULL);
-	if (p) {
-		if ((be32_to_cpup(p)) >= 0x4000)
-			lp->jumbo_support = 1;
-	}
-	p = (__be32 *) of_get_property(op->dev.of_node, "xlnx,phy-type", NULL);
-	if (p)
-		lp->phy_type = be32_to_cpup(p);
+	 * a larger Rx/Tx Memory. Typically, the size must be large so that
+	 * we can enable jumbo option and start supporting jumbo frames.
+	 * Here we check for memory allocated for Rx/Tx in the hardware from
+	 * the device-tree and accordingly set flags.
+	 */
+	of_property_read_u32(pdev->dev.of_node, "xlnx,rxmem", &lp->rxmem);
+	of_property_read_u32(pdev->dev.of_node, "xlnx,phy-type", &lp->phy_type);
 
 	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
-	np = of_parse_phandle(op->dev.of_node, "axistream-connected", 0);
-	if (!np) {
-		dev_err(&op->dev, "could not find DMA node\n");
-		ret = -ENODEV;
-		goto err_iounmap;
+	np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
+	if (IS_ERR(np)) {
+		dev_err(&pdev->dev, "could not find DMA node\n");
+		ret = PTR_ERR(np);
+		goto free_netdev;
 	}
-	lp->dma_regs = of_iomap(np, 0);
-	if (lp->dma_regs) {
-		dev_dbg(&op->dev, "MEM base: %p\n", lp->dma_regs);
-	} else {
-		dev_err(&op->dev, "unable to map DMA registers\n");
-		of_node_put(np);
+	ret = of_address_to_resource(np, 0, &dmares);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to get DMA resource\n");
+		goto free_netdev;
+	}
+	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
+	if (!lp->dma_regs) {
+		dev_err(&pdev->dev, "could not map DMA regs\n");
+		ret = -ENOMEM;
+		goto free_netdev;
 	}
 	lp->rx_irq = irq_of_parse_and_map(np, 1);
 	lp->tx_irq = irq_of_parse_and_map(np, 0);
 	of_node_put(np);
 	if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
-		dev_err(&op->dev, "could not determine irqs\n");
+		dev_err(&pdev->dev, "could not determine irqs\n");
 		ret = -ENOMEM;
-		goto err_iounmap_2;
+		goto free_netdev;
 	}
 
 	/* Retrieve the MAC address */
-	addr = of_get_property(op->dev.of_node, "local-mac-address", &size);
-	if ((!addr) || (size != 6)) {
-		dev_err(&op->dev, "could not find MAC address\n");
-		ret = -ENODEV;
-		goto err_iounmap_2;
+	ret = of_property_read_u8_array(pdev->dev.of_node,
+					"local-mac-address", mac_addr, 6);
+	if (ret) {
+		dev_err(&pdev->dev, "could not find MAC address\n");
+		goto free_netdev;
 	}
-	axienet_set_mac_address(ndev, (void *) addr);
+	axienet_set_mac_address(ndev, (void *)mac_addr);
 
 	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 
-	lp->phy_node = of_parse_phandle(op->dev.of_node, "phy-handle", 0);
-	ret = axienet_mdio_setup(lp, op->dev.of_node);
-	if (ret)
-		dev_warn(&op->dev, "error registering MDIO bus\n");
+	lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (lp->phy_node) {
+		ret = axienet_mdio_setup(lp, pdev->dev.of_node);
+		if (ret)
+			dev_warn(&pdev->dev, "error registering MDIO bus\n");
+	}
 
 	ret = register_netdev(lp->ndev);
 	if (ret) {
 		dev_err(lp->dev, "register_netdev() error (%i)\n", ret);
-		goto err_iounmap_2;
+		goto free_netdev;
 	}
 
 	return 0;
 
-err_iounmap_2:
-	if (lp->dma_regs)
-		iounmap(lp->dma_regs);
-err_iounmap:
-	iounmap(lp->regs);
-nodev:
+free_netdev:
 	free_netdev(ndev);
-	ndev = NULL;
+
 	return ret;
 }
 
-static int axienet_of_remove(struct platform_device *op)
+static int axienet_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(op);
+	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct axienet_local *lp = netdev_priv(ndev);
 
 	axienet_mdio_teardown(lp);
@@ -1630,24 +1657,21 @@ static int axienet_of_remove(struct platform_device *op)
 	of_node_put(lp->phy_node);
 	lp->phy_node = NULL;
 
-	iounmap(lp->regs);
-	if (lp->dma_regs)
-		iounmap(lp->dma_regs);
 	free_netdev(ndev);
 
 	return 0;
 }
 
-static struct platform_driver axienet_of_driver = {
-	.probe = axienet_of_probe,
-	.remove = axienet_of_remove,
+static struct platform_driver axienet_driver = {
+	.probe = axienet_probe,
+	.remove = axienet_remove,
 	.driver = {
 		 .name = "xilinx_axienet",
 		 .of_match_table = axienet_of_match,
 	},
 };
 
-module_platform_driver(axienet_of_driver);
+module_platform_driver(axienet_driver);
 
 MODULE_DESCRIPTION("Xilinx Axi Ethernet driver");
 MODULE_AUTHOR("Xilinx");
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 3b67d60d4378..2a5a16834c01 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -37,7 +37,7 @@ int axienet_mdio_wait_until_ready(struct axienet_local *lp)
  * @phy_id:	Address of the PHY device
  * @reg:	PHY register to read
  *
- * returns:	The register contents on success, -ETIMEDOUT on a timeout
+ * Return:	The register contents on success, -ETIMEDOUT on a timeout
  *
  * Reads the contents of the requested register from the requested PHY
  * address by first writing the details into MCR register. After a while
@@ -80,7 +80,7 @@ static int axienet_mdio_read(struct mii_bus *bus, int phy_id, int reg)
  * @reg:	PHY register to write to
  * @val:	Value to be written into the register
  *
- * returns:	0 on success, -ETIMEDOUT on a timeout
+ * Return:	0 on success, -ETIMEDOUT on a timeout
  *
  * Writes the value to the requested register by first writing the value
  * into MWD register. The the MCR register is then appropriately setup
@@ -119,7 +119,7 @@ static int axienet_mdio_write(struct mii_bus *bus, int phy_id, int reg,
  * @lp:		Pointer to axienet local data structure.
  * @np:		Pointer to device node
  *
- * returns:	0 on success, -ETIMEDOUT on a timeout, -ENOMEM when
+ * Return:	0 on success, -ETIMEDOUT on a timeout, -ENOMEM when
  *		mdiobus_alloc (to allocate memory for mii bus structure) fails.
  *
  * Sets up the MDIO interface by initializing the MDIO clock and enabling the
@@ -161,19 +161,19 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
 
 	np1 = of_find_node_by_name(NULL, "cpu");
 	if (!np1) {
-		printk(KERN_WARNING "%s(): Could not find CPU device node.",
-		       __func__);
-		printk(KERN_WARNING "Setting MDIO clock divisor to "
-		       "default %d\n", DEFAULT_CLOCK_DIVISOR);
+		netdev_warn(lp->ndev, "Could not find CPU device node.\n");
+		netdev_warn(lp->ndev,
+			    "Setting MDIO clock divisor to default %d\n",
+			    DEFAULT_CLOCK_DIVISOR);
 		clk_div = DEFAULT_CLOCK_DIVISOR;
 		goto issue;
 	}
 	property_p = (u32 *) of_get_property(np1, "clock-frequency", NULL);
 	if (!property_p) {
-		printk(KERN_WARNING "%s(): Could not find CPU property: "
-		       "clock-frequency.", __func__);
-		printk(KERN_WARNING "Setting MDIO clock divisor to "
-		       "default %d\n", DEFAULT_CLOCK_DIVISOR);
+		netdev_warn(lp->ndev, "clock-frequency property not found.\n");
+		netdev_warn(lp->ndev,
+			    "Setting MDIO clock divisor to default %d\n",
+			    DEFAULT_CLOCK_DIVISOR);
 		clk_div = DEFAULT_CLOCK_DIVISOR;
 		of_node_put(np1);
 		goto issue;
@@ -183,12 +183,14 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np)
 	clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1;
 	/* If there is any remainder from the division of
 	 * fHOST / (MAX_MDIO_FREQ * 2), then we need to add
-	 * 1 to the clock divisor or we will surely be above 2.5 MHz */
+	 * 1 to the clock divisor or we will surely be above 2.5 MHz
+	 */
 	if (host_clock % (MAX_MDIO_FREQ * 2))
 		clk_div++;
 
-	printk(KERN_DEBUG "%s(): Setting MDIO clock divisor to %u based "
-	       "on %u Hz host clock.\n", __func__, clk_div, host_clock);
+	netdev_dbg(lp->ndev,
+		   "Setting MDIO clock divisor to %u/%u Hz host clock.\n",
+		   clk_div, host_clock);
 
 	of_node_put(np1);
 issue:
diff --git a/drivers/net/ethernet/xircom/Kconfig b/drivers/net/ethernet/xircom/Kconfig
index 69f56a6de821..d6208a4c9866 100644
--- a/drivers/net/ethernet/xircom/Kconfig
+++ b/drivers/net/ethernet/xircom/Kconfig
@@ -7,9 +7,7 @@ config NET_VENDOR_XIRCOM
 	default y
 	depends on PCMCIA
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig
index b81bc9fca378..af3432fe9a5e 100644
--- a/drivers/net/ethernet/xscale/Kconfig
+++ b/drivers/net/ethernet/xscale/Kconfig
@@ -8,9 +8,7 @@ config NET_VENDOR_XSCALE
 	depends on NET_VENDOR_INTEL && (ARM && ARCH_IXP4XX && \
 		   IXP4XX_NPE && IXP4XX_QMGR)
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question does not directly affect the
 	  kernel: saying N will just cause the configurator to skip all
diff --git a/drivers/net/fddi/skfp/srf.c b/drivers/net/fddi/skfp/srf.c
index cc27dea3414e..9956680402de 100644
--- a/drivers/net/fddi/skfp/srf.c
+++ b/drivers/net/fddi/skfp/srf.c
@@ -414,7 +414,7 @@ static void smt_send_srf(struct s_smc *smc)
 	smt->smt_len = SMT_MAX_INFO_LEN - pcon.pc_len ;
 	mb->sm_len = smt->smt_len + sizeof(struct smt_header) ;
 
-	DB_SMT("SRF: sending SRF at %x, len %d\n",smt,mb->sm_len) ;
+	DB_SMT("SRF: sending SRF at %p, len %d\n",smt,mb->sm_len) ;
 	DB_SMT("SRF: state SR%d Threshold %d\n",
 		smc->srf.sr_state,smc->srf.SRThreshold/TICKS_PER_SECOND) ;
 #ifdef	DEBUG
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
new file mode 100644
index 000000000000..78d49d186e05
--- /dev/null
+++ b/drivers/net/geneve.c
@@ -0,0 +1,523 @@
+/*
+ * GENEVE: Generic Network Virtualization Encapsulation
+ *
+ * Copyright (c) 2015 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/hash.h>
+#include <net/rtnetlink.h>
+#include <net/geneve.h>
+
+#define GENEVE_NETDEV_VER	"0.6"
+
+#define GENEVE_UDP_PORT		6081
+
+#define GENEVE_N_VID		(1u << 24)
+#define GENEVE_VID_MASK		(GENEVE_N_VID - 1)
+
+#define VNI_HASH_BITS		10
+#define VNI_HASH_SIZE		(1<<VNI_HASH_BITS)
+
+static bool log_ecn_error = true;
+module_param(log_ecn_error, bool, 0644);
+MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
+
+/* per-network namespace private data for this module */
+struct geneve_net {
+	struct list_head  geneve_list;
+	struct hlist_head vni_list[VNI_HASH_SIZE];
+};
+
+/* Pseudo network device */
+struct geneve_dev {
+	struct hlist_node  hlist;	/* vni hash table */
+	struct net	   *net;	/* netns for packet i/o */
+	struct net_device  *dev;	/* netdev for geneve tunnel */
+	struct geneve_sock *sock;	/* socket used for geneve tunnel */
+	u8                 vni[3];	/* virtual network ID for tunnel */
+	u8                 ttl;		/* TTL override */
+	u8                 tos;		/* TOS override */
+	struct sockaddr_in remote;	/* IPv4 address for link partner */
+	struct list_head   next;	/* geneve's per namespace list */
+};
+
+static int geneve_net_id;
+
+static inline __u32 geneve_net_vni_hash(u8 vni[3])
+{
+	__u32 vnid;
+
+	vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
+	return hash_32(vnid, VNI_HASH_BITS);
+}
+
+/* geneve receive/decap routine */
+static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
+{
+	struct genevehdr *gnvh = geneve_hdr(skb);
+	struct geneve_dev *dummy, *geneve = NULL;
+	struct geneve_net *gn;
+	struct iphdr *iph = NULL;
+	struct pcpu_sw_netstats *stats;
+	struct hlist_head *vni_list_head;
+	int err = 0;
+	__u32 hash;
+
+	iph = ip_hdr(skb); /* Still outer IP header... */
+
+	gn = gs->rcv_data;
+
+	/* Find the device for this VNI */
+	hash = geneve_net_vni_hash(gnvh->vni);
+	vni_list_head = &gn->vni_list[hash];
+	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
+		if (!memcmp(gnvh->vni, dummy->vni, sizeof(dummy->vni)) &&
+		    iph->saddr == dummy->remote.sin_addr.s_addr) {
+			geneve = dummy;
+			break;
+		}
+	}
+	if (!geneve)
+		goto drop;
+
+	/* Drop packets w/ critical options,
+	 * since we don't support any...
+	 */
+	if (gnvh->critical)
+		goto drop;
+
+	skb_reset_mac_header(skb);
+	skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
+	skb->protocol = eth_type_trans(skb, geneve->dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+
+	/* Ignore packet loops (and multicast echo) */
+	if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
+		goto drop;
+
+	skb_reset_network_header(skb);
+
+	iph = ip_hdr(skb); /* Now inner IP header... */
+	err = IP_ECN_decapsulate(iph, skb);
+
+	if (unlikely(err)) {
+		if (log_ecn_error)
+			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+					     &iph->saddr, iph->tos);
+		if (err > 1) {
+			++geneve->dev->stats.rx_frame_errors;
+			++geneve->dev->stats.rx_errors;
+			goto drop;
+		}
+	}
+
+	stats = this_cpu_ptr(geneve->dev->tstats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+
+	netif_rx(skb);
+
+	return;
+drop:
+	/* Consume bad packet */
+	kfree_skb(skb);
+}
+
+/* Setup stats when device is created */
+static int geneve_init(struct net_device *dev)
+{
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void geneve_uninit(struct net_device *dev)
+{
+	free_percpu(dev->tstats);
+}
+
+static int geneve_open(struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct net *net = geneve->net;
+	struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
+	struct geneve_sock *gs;
+
+	gs = geneve_sock_add(net, htons(GENEVE_UDP_PORT), geneve_rx, gn,
+	                     false, false);
+	if (IS_ERR(gs))
+		return PTR_ERR(gs);
+
+	geneve->sock = gs;
+
+	return 0;
+}
+
+static int geneve_stop(struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_sock *gs = geneve->sock;
+
+	geneve_sock_release(gs);
+
+	return 0;
+}
+
+static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	struct geneve_sock *gs = geneve->sock;
+	struct rtable *rt = NULL;
+	const struct iphdr *iip; /* interior IP header */
+	struct flowi4 fl4;
+	int err;
+	__be16 sport;
+	__u8 tos, ttl;
+
+	iip = ip_hdr(skb);
+
+	skb_reset_mac_header(skb);
+
+	/* TODO: port min/max limits should be configurable */
+	sport = udp_flow_src_port(dev_net(dev), skb, 0, 0, true);
+
+	tos = geneve->tos;
+	if (tos == 1)
+		tos = ip_tunnel_get_dsfield(iip, skb);
+
+	memset(&fl4, 0, sizeof(fl4));
+	fl4.flowi4_tos = RT_TOS(tos);
+	fl4.daddr = geneve->remote.sin_addr.s_addr;
+	rt = ip_route_output_key(geneve->net, &fl4);
+	if (IS_ERR(rt)) {
+		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
+		dev->stats.tx_carrier_errors++;
+		goto tx_error;
+	}
+	if (rt->dst.dev == dev) { /* is this necessary? */
+		netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr);
+		dev->stats.collisions++;
+		goto rt_tx_error;
+	}
+
+	tos = ip_tunnel_ecn_encap(tos, iip, skb);
+
+	ttl = geneve->ttl;
+	if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
+		ttl = 1;
+
+	ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+	/* no need to handle local destination and encap bypass...yet... */
+
+	err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr,
+	                      tos, ttl, 0, sport, htons(GENEVE_UDP_PORT), 0,
+	                      geneve->vni, 0, NULL, false,
+	                      !net_eq(geneve->net, dev_net(geneve->dev)));
+	if (err < 0)
+		ip_rt_put(rt);
+
+	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
+
+	return NETDEV_TX_OK;
+
+rt_tx_error:
+	ip_rt_put(rt);
+tx_error:
+	dev->stats.tx_errors++;
+	dev_kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops geneve_netdev_ops = {
+	.ndo_init		= geneve_init,
+	.ndo_uninit		= geneve_uninit,
+	.ndo_open		= geneve_open,
+	.ndo_stop		= geneve_stop,
+	.ndo_start_xmit		= geneve_xmit,
+	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr,
+};
+
+static void geneve_get_drvinfo(struct net_device *dev,
+			       struct ethtool_drvinfo *drvinfo)
+{
+	strlcpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version));
+	strlcpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver));
+}
+
+static const struct ethtool_ops geneve_ethtool_ops = {
+	.get_drvinfo	= geneve_get_drvinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+/* Info for udev, that this is a virtual tunnel endpoint */
+static struct device_type geneve_type = {
+	.name = "geneve",
+};
+
+/* Initialize the device structure. */
+static void geneve_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->netdev_ops = &geneve_netdev_ops;
+	dev->ethtool_ops = &geneve_ethtool_ops;
+	dev->destructor = free_netdev;
+
+	SET_NETDEV_DEVTYPE(dev, &geneve_type);
+
+	dev->tx_queue_len = 0;
+	dev->features    |= NETIF_F_LLTX;
+	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM;
+	dev->features    |= NETIF_F_RXCSUM;
+	dev->features    |= NETIF_F_GSO_SOFTWARE;
+
+	dev->vlan_features = dev->features;
+	dev->features    |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+
+	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
+	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+
+	netif_keep_dst(dev);
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+}
+
+static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
+	[IFLA_GENEVE_ID]		= { .type = NLA_U32 },
+	[IFLA_GENEVE_REMOTE]		= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+	[IFLA_GENEVE_TTL]		= { .type = NLA_U8 },
+	[IFLA_GENEVE_TOS]		= { .type = NLA_U8 },
+};
+
+static int geneve_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	if (data[IFLA_GENEVE_ID]) {
+		__u32 vni =  nla_get_u32(data[IFLA_GENEVE_ID]);
+
+		if (vni >= GENEVE_VID_MASK)
+			return -ERANGE;
+	}
+
+	return 0;
+}
+
+static int geneve_newlink(struct net *net, struct net_device *dev,
+			 struct nlattr *tb[], struct nlattr *data[])
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev *dummy, *geneve = netdev_priv(dev);
+	struct hlist_head *vni_list_head;
+	struct sockaddr_in remote;	/* IPv4 address for link partner */
+	__u32 vni, hash;
+	int err;
+
+	if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
+		return -EINVAL;
+
+	geneve->net = net;
+	geneve->dev = dev;
+
+	vni = nla_get_u32(data[IFLA_GENEVE_ID]);
+	geneve->vni[0] = (vni & 0x00ff0000) >> 16;
+	geneve->vni[1] = (vni & 0x0000ff00) >> 8;
+	geneve->vni[2] =  vni & 0x000000ff;
+
+	geneve->remote.sin_addr.s_addr =
+		nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);
+	if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr)))
+		return -EINVAL;
+
+	remote = geneve->remote;
+	hash = geneve_net_vni_hash(geneve->vni);
+	vni_list_head = &gn->vni_list[hash];
+	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
+		if (!memcmp(geneve->vni, dummy->vni, sizeof(dummy->vni)) &&
+		    !memcmp(&remote, &dummy->remote, sizeof(dummy->remote)))
+			return -EBUSY;
+	}
+
+	if (tb[IFLA_ADDRESS] == NULL)
+		eth_hw_addr_random(dev);
+
+	err = register_netdevice(dev);
+	if (err)
+		return err;
+
+	if (data[IFLA_GENEVE_TTL])
+		geneve->ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
+
+	if (data[IFLA_GENEVE_TOS])
+		geneve->tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
+
+	list_add(&geneve->next, &gn->geneve_list);
+
+	hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]);
+
+	return 0;
+}
+
+static void geneve_dellink(struct net_device *dev, struct list_head *head)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+
+	if (!hlist_unhashed(&geneve->hlist))
+		hlist_del_rcu(&geneve->hlist);
+
+	list_del(&geneve->next);
+	unregister_netdevice_queue(dev, head);
+}
+
+static size_t geneve_get_size(const struct net_device *dev)
+{
+	return nla_total_size(sizeof(__u32)) +	/* IFLA_GENEVE_ID */
+		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
+		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
+		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
+		0;
+}
+
+static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct geneve_dev *geneve = netdev_priv(dev);
+	__u32 vni;
+
+	vni = (geneve->vni[0] << 16) | (geneve->vni[1] << 8) | geneve->vni[2];
+	if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
+		goto nla_put_failure;
+
+	if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
+			    geneve->remote.sin_addr.s_addr))
+		goto nla_put_failure;
+
+	if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) ||
+	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops geneve_link_ops __read_mostly = {
+	.kind		= "geneve",
+	.maxtype	= IFLA_GENEVE_MAX,
+	.policy		= geneve_policy,
+	.priv_size	= sizeof(struct geneve_dev),
+	.setup		= geneve_setup,
+	.validate	= geneve_validate,
+	.newlink	= geneve_newlink,
+	.dellink	= geneve_dellink,
+	.get_size	= geneve_get_size,
+	.fill_info	= geneve_fill_info,
+};
+
+static __net_init int geneve_init_net(struct net *net)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	unsigned int h;
+
+	INIT_LIST_HEAD(&gn->geneve_list);
+
+	for (h = 0; h < VNI_HASH_SIZE; ++h)
+		INIT_HLIST_HEAD(&gn->vni_list[h]);
+
+	return 0;
+}
+
+static void __net_exit geneve_exit_net(struct net *net)
+{
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	struct geneve_dev *geneve, *next;
+	struct net_device *dev, *aux;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+
+	/* gather any geneve devices that were moved into this ns */
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &geneve_link_ops)
+			unregister_netdevice_queue(dev, &list);
+
+	/* now gather any other geneve devices that were created in this ns */
+	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
+		/* If geneve->dev is in the same netns, it was already added
+		 * to the list by the previous loop.
+		 */
+		if (!net_eq(dev_net(geneve->dev), net))
+			unregister_netdevice_queue(geneve->dev, &list);
+	}
+
+	/* unregister the devices gathered above */
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
+static struct pernet_operations geneve_net_ops = {
+	.init = geneve_init_net,
+	.exit = geneve_exit_net,
+	.id   = &geneve_net_id,
+	.size = sizeof(struct geneve_net),
+};
+
+static int __init geneve_init_module(void)
+{
+	int rc;
+
+	rc = register_pernet_subsys(&geneve_net_ops);
+	if (rc)
+		goto out1;
+
+	rc = rtnl_link_register(&geneve_link_ops);
+	if (rc)
+		goto out2;
+
+	return 0;
+out2:
+	unregister_pernet_subsys(&geneve_net_ops);
+out1:
+	return rc;
+}
+late_initcall(geneve_init_module);
+
+static void __exit geneve_cleanup_module(void)
+{
+	rtnl_link_unregister(&geneve_link_ops);
+	unregister_pernet_subsys(&geneve_net_ops);
+}
+module_exit(geneve_cleanup_module);
+
+MODULE_LICENSE("GPL");
+MODULE_VERSION(GENEVE_NETDEV_VER);
+MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>");
+MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic");
+MODULE_ALIAS_RTNL_LINK("geneve");
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 63ff08a26da8..7856b6ccf5c5 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -76,7 +76,6 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/stat.h>
-#include <linux/netfilter.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 41071d32bc8e..dd4544085db3 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -161,6 +161,7 @@ struct netvsc_device_info {
 	unsigned char mac_adr[ETH_ALEN];
 	bool link_state;	/* 0 - link up, 1 - link down */
 	int  ring_size;
+	u32  max_num_vrss_chns;
 };
 
 enum rndis_device_state {
@@ -611,6 +612,12 @@ struct multi_send_data {
 	u32 count; /* counter of batched packets */
 };
 
+struct netvsc_stats {
+	u64 packets;
+	u64 bytes;
+	struct u64_stats_sync syncp;
+};
+
 /* The context of the netvsc device  */
 struct net_device_context {
 	/* point back to our device context */
@@ -618,6 +625,9 @@ struct net_device_context {
 	struct delayed_work dwork;
 	struct work_struct work;
 	u32 msg_enable; /* debug level */
+
+	struct netvsc_stats __percpu *tx_stats;
+	struct netvsc_stats __percpu *rx_stats;
 };
 
 /* Per netvsc device */
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 2d9ef533cc48..23126a74f357 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
+#include <linux/vmalloc.h>
 #include <asm/sync_bitops.h>
 
 #include "hyperv_net.h"
@@ -227,13 +228,18 @@ static int netvsc_init_buf(struct hv_device *device)
 	struct netvsc_device *net_device;
 	struct nvsp_message *init_packet;
 	struct net_device *ndev;
+	int node;
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
 		return -ENODEV;
 	ndev = net_device->ndev;
 
-	net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+	node = cpu_to_node(device->channel->target_cpu);
+	net_device->recv_buf = vzalloc_node(net_device->recv_buf_size, node);
+	if (!net_device->recv_buf)
+		net_device->recv_buf = vzalloc(net_device->recv_buf_size);
+
 	if (!net_device->recv_buf) {
 		netdev_err(ndev, "unable to allocate receive "
 			"buffer of size %d\n", net_device->recv_buf_size);
@@ -321,7 +327,9 @@ static int netvsc_init_buf(struct hv_device *device)
 
 	/* Now setup the send buffer.
 	 */
-	net_device->send_buf = vzalloc(net_device->send_buf_size);
+	net_device->send_buf = vzalloc_node(net_device->send_buf_size, node);
+	if (!net_device->send_buf)
+		net_device->send_buf = vzalloc(net_device->send_buf_size);
 	if (!net_device->send_buf) {
 		netdev_err(ndev, "unable to allocate send "
 			   "buffer of size %d\n", net_device->send_buf_size);
@@ -743,6 +751,7 @@ static inline int netvsc_send_pkt(
 	u64 req_id;
 	int ret;
 	struct hv_page_buffer *pgbuf;
+	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
 	if (packet->is_data_pkt) {
@@ -769,32 +778,42 @@ static inline int netvsc_send_pkt(
 	if (out_channel->rescind)
 		return -ENODEV;
 
+	/*
+	 * It is possible that once we successfully place this packet
+	 * on the ringbuffer, we may stop the queue. In that case, we want
+	 * to notify the host independent of the xmit_more flag. We don't
+	 * need to be precise here; in the worst case we may signal the host
+	 * unnecessarily.
+	 */
+	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
+		packet->xmit_more = false;
+
 	if (packet->page_buf_cnt) {
 		pgbuf = packet->cp_partial ? packet->page_buf +
 			packet->rmsg_pgcnt : packet->page_buf;
-		ret = vmbus_sendpacket_pagebuffer(out_channel,
-						  pgbuf,
-						  packet->page_buf_cnt,
-						  &nvmsg,
-						  sizeof(struct nvsp_message),
-						  req_id);
+		ret = vmbus_sendpacket_pagebuffer_ctl(out_channel,
+						      pgbuf,
+						      packet->page_buf_cnt,
+						      &nvmsg,
+						      sizeof(struct nvsp_message),
+						      req_id,
+						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+						      !packet->xmit_more);
 	} else {
-		ret = vmbus_sendpacket(
-				out_channel, &nvmsg,
-				sizeof(struct nvsp_message),
-				req_id,
-				VM_PKT_DATA_INBAND,
-				VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+		ret = vmbus_sendpacket_ctl(out_channel, &nvmsg,
+					   sizeof(struct nvsp_message),
+					   req_id,
+					   VM_PKT_DATA_INBAND,
+					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+					   !packet->xmit_more);
 	}
 
 	if (ret == 0) {
 		atomic_inc(&net_device->num_outstanding_sends);
 		atomic_inc(&net_device->queue_sends[q_idx]);
 
-		if (hv_ringbuf_avail_percent(&out_channel->outbound) <
-			RING_AVAIL_PERCENT_LOWATER) {
-			netif_tx_stop_queue(netdev_get_tx_queue(
-					    ndev, q_idx));
+		if (ring_avail < RING_AVAIL_PERCENT_LOWATER) {
+			netif_tx_stop_queue(netdev_get_tx_queue(ndev, q_idx));
 
 			if (atomic_read(&net_device->
 				queue_sends[q_idx]) < 1)
@@ -826,7 +845,6 @@ int netvsc_send(struct hv_device *device,
 	u16 q_idx = packet->q_idx;
 	u32 pktlen = packet->total_data_buflen, msd_len = 0;
 	unsigned int section_index = NETVSC_INVALID_INDEX;
-	struct sk_buff *skb = NULL;
 	unsigned long flag;
 	struct multi_send_data *msdp;
 	struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL;
@@ -924,12 +942,8 @@ int netvsc_send(struct hv_device *device,
 	if (cur_send)
 		ret = netvsc_send_pkt(cur_send, net_device);
 
-	if (ret != 0) {
-		if (section_index != NETVSC_INVALID_INDEX)
-			netvsc_free_send_slot(net_device, section_index);
-	} else if (skb) {
-		dev_kfree_skb_any(skb);
-	}
+	if (ret != 0 && section_index != NETVSC_INVALID_INDEX)
+		netvsc_free_send_slot(net_device, section_index);
 
 	return ret;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 5993c7e2d723..358475ed9b59 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -46,6 +46,8 @@ static int ring_size = 128;
 module_param(ring_size, int, S_IRUGO);
 MODULE_PARM_DESC(ring_size, "Ring buffer size (# of pages)");
 
+static int max_num_vrss_chns = 8;
+
 static const u32 default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE |
 				NETIF_MSG_LINK | NETIF_MSG_IFUP |
 				NETIF_MSG_IFDOWN | NETIF_MSG_RX_ERR |
@@ -196,12 +198,12 @@ static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
 	struct flow_keys flow;
 	int data_len;
 
-	if (!skb_flow_dissect(skb, &flow) ||
-	    !(flow.n_proto == htons(ETH_P_IP) ||
-	      flow.n_proto == htons(ETH_P_IPV6)))
+	if (!skb_flow_dissect_flow_keys(skb, &flow) ||
+	    !(flow.basic.n_proto == htons(ETH_P_IP) ||
+	      flow.basic.n_proto == htons(ETH_P_IPV6)))
 		return false;
 
-	if (flow.ip_proto == IPPROTO_TCP)
+	if (flow.basic.ip_proto == IPPROTO_TCP)
 		data_len = 12;
 	else
 		data_len = 8;
@@ -391,7 +393,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	u32 skb_length;
 	u32 pkt_sz;
 	struct hv_page_buffer page_buf[MAX_PAGE_BUFFER_COUNT];
-
+	struct netvsc_stats *tx_stats = this_cpu_ptr(net_device_ctx->tx_stats);
 
 	/* We will atmost need two pages to describe the rndis
 	 * header. We can only transmit MAX_PAGE_BUFFER_COUNT number
@@ -580,8 +582,10 @@ do_send:
 
 drop:
 	if (ret == 0) {
-		net->stats.tx_bytes += skb_length;
-		net->stats.tx_packets++;
+		u64_stats_update_begin(&tx_stats->syncp);
+		tx_stats->packets++;
+		tx_stats->bytes += skb_length;
+		u64_stats_update_end(&tx_stats->syncp);
 	} else {
 		if (ret != -EAGAIN) {
 			dev_kfree_skb_any(skb);
@@ -644,13 +648,17 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 				struct ndis_tcp_ip_checksum_info *csum_info)
 {
 	struct net_device *net;
+	struct net_device_context *net_device_ctx;
 	struct sk_buff *skb;
+	struct netvsc_stats *rx_stats;
 
 	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
 	if (!net || net->reg_state != NETREG_REGISTERED) {
 		packet->status = NVSP_STAT_FAIL;
 		return 0;
 	}
+	net_device_ctx = netdev_priv(net);
+	rx_stats = this_cpu_ptr(net_device_ctx->rx_stats);
 
 	/* Allocate a skb - TODO direct I/O to pages? */
 	skb = netdev_alloc_skb_ip_align(net, packet->total_data_buflen);
@@ -686,8 +694,10 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	skb_record_rx_queue(skb, packet->channel->
 			    offermsg.offer.sub_channel_index);
 
-	net->stats.rx_packets++;
-	net->stats.rx_bytes += packet->total_data_buflen;
+	u64_stats_update_begin(&rx_stats->syncp);
+	rx_stats->packets++;
+	rx_stats->bytes += packet->total_data_buflen;
+	u64_stats_update_end(&rx_stats->syncp);
 
 	/*
 	 * Pass the skb back up. Network stack will deallocate the skb when it
@@ -747,12 +757,53 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	ndevctx->device_ctx = hdev;
 	hv_set_drvdata(hdev, ndev);
 	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	rndis_filter_device_add(hdev, &device_info);
 	netif_tx_wake_all_queues(ndev);
 
 	return 0;
 }
 
+static struct rtnl_link_stats64 *netvsc_get_stats64(struct net_device *net,
+						    struct rtnl_link_stats64 *t)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct netvsc_stats *tx_stats = per_cpu_ptr(ndev_ctx->tx_stats,
+							    cpu);
+		struct netvsc_stats *rx_stats = per_cpu_ptr(ndev_ctx->rx_stats,
+							    cpu);
+		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+			tx_packets = tx_stats->packets;
+			tx_bytes = tx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
+
+		do {
+			start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+			rx_packets = rx_stats->packets;
+			rx_bytes = rx_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
+
+		t->tx_bytes	+= tx_bytes;
+		t->tx_packets	+= tx_packets;
+		t->rx_bytes	+= rx_bytes;
+		t->rx_packets	+= rx_packets;
+	}
+
+	t->tx_dropped	= net->stats.tx_dropped;
+	t->tx_errors	= net->stats.tx_dropped;
+
+	t->rx_dropped	= net->stats.rx_dropped;
+	t->rx_errors	= net->stats.rx_errors;
+
+	return t;
+}
 
 static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
 {
@@ -804,6 +855,7 @@ static const struct net_device_ops device_ops = {
 	.ndo_validate_addr =		eth_validate_addr,
 	.ndo_set_mac_address =		netvsc_set_mac_addr,
 	.ndo_select_queue =		netvsc_select_queue,
+	.ndo_get_stats64 =		netvsc_get_stats64,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller =		netvsc_poll_controller,
 #endif
@@ -855,6 +907,14 @@ static void netvsc_link_change(struct work_struct *w)
 		netdev_notify_peers(net);
 }
 
+static void netvsc_free_netdev(struct net_device *netdev)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(netdev);
+
+	free_percpu(net_device_ctx->tx_stats);
+	free_percpu(net_device_ctx->rx_stats);
+	free_netdev(netdev);
+}
 
 static int netvsc_probe(struct hv_device *dev,
 			const struct hv_vmbus_device_id *dev_id)
@@ -883,6 +943,18 @@ static int netvsc_probe(struct hv_device *dev,
 		netdev_dbg(net, "netvsc msg_enable: %d\n",
 			   net_device_ctx->msg_enable);
 
+	net_device_ctx->tx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->tx_stats) {
+		free_netdev(net);
+		return -ENOMEM;
+	}
+	net_device_ctx->rx_stats = netdev_alloc_pcpu_stats(struct netvsc_stats);
+	if (!net_device_ctx->rx_stats) {
+		free_percpu(net_device_ctx->tx_stats);
+		free_netdev(net);
+		return -ENOMEM;
+	}
+
 	hv_set_drvdata(dev, net);
 	INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
 	INIT_WORK(&net_device_ctx->work, do_set_multicast);
@@ -906,10 +978,11 @@ static int netvsc_probe(struct hv_device *dev,
 
 	/* Notify the netvsc driver of the new device */
 	device_info.ring_size = ring_size;
+	device_info.max_num_vrss_chns = max_num_vrss_chns;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 		hv_set_drvdata(dev, NULL);
 		return ret;
 	}
@@ -923,7 +996,7 @@ static int netvsc_probe(struct hv_device *dev,
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
 		rndis_filter_device_remove(dev);
-		free_netdev(net);
+		netvsc_free_netdev(net);
 	} else {
 		schedule_delayed_work(&net_device_ctx->dwork, 0);
 	}
@@ -962,7 +1035,7 @@ static int netvsc_remove(struct hv_device *dev)
 	 */
 	rndis_filter_device_remove(dev);
 
-	free_netdev(net);
+	netvsc_free_netdev(net);
 	return 0;
 }
 
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9118cea91882..236aeb76ef22 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -27,6 +27,7 @@
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
 #include <linux/nls.h>
+#include <linux/vmalloc.h>
 
 #include "hyperv_net.h"
 
@@ -1013,6 +1014,9 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct ndis_recv_scale_cap rsscap;
 	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 	u32 mtu, size;
+	u32 num_rss_qs;
+	const struct cpumask *node_cpu_mask;
+	u32 num_possible_rss_qs;
 
 	rndis_device = get_rndis_device();
 	if (!rndis_device)
@@ -1100,9 +1104,18 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret || rsscap.num_recv_que < 2)
 		goto out;
 
+	num_rss_qs = min(device_info->max_num_vrss_chns, rsscap.num_recv_que);
+
 	net_device->max_chn = rsscap.num_recv_que;
-	net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ?
-			       num_online_cpus() : rsscap.num_recv_que;
+
+	/*
+	 * We will limit the VRSS channels to the number CPUs in the NUMA node
+	 * the primary channel is currently bound to.
+	 */
+	node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu));
+	num_possible_rss_qs = cpumask_weight(node_cpu_mask);
+	net_device->num_chn = min(num_possible_rss_qs, num_rss_qs);
+
 	if (net_device->num_chn == 1)
 		goto out;
 
diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig
index 1a3c3e57aa0b..1dd5ab8e5054 100644
--- a/drivers/net/ieee802154/Kconfig
+++ b/drivers/net/ieee802154/Kconfig
@@ -53,3 +53,13 @@ config IEEE802154_CC2520
 
 	  This driver can also be built as a module. To do so, say M here.
 	  the module will be called 'cc2520'.
+
+config IEEE802154_ATUSB
+	tristate "ATUSB transceiver driver"
+	depends on IEEE802154_DRIVERS && MAC802154 && USB
+	---help---
+	  Say Y here to enable the ATUSB IEEE 802.15.4 wireless
+	  controller.
+
+	  This driver can also be built as a module. To do so say M here.
+	  The module will be called 'atusb'.
diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile
index d77fa4d77e27..cf1d2a6db023 100644
--- a/drivers/net/ieee802154/Makefile
+++ b/drivers/net/ieee802154/Makefile
@@ -2,3 +2,4 @@ obj-$(CONFIG_IEEE802154_FAKELB) += fakelb.o
 obj-$(CONFIG_IEEE802154_AT86RF230) += at86rf230.o
 obj-$(CONFIG_IEEE802154_MRF24J40) += mrf24j40.o
 obj-$(CONFIG_IEEE802154_CC2520) += cc2520.o
+obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 38026650c038..f7bd9f3ddaac 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -35,6 +35,8 @@
 #include <net/mac802154.h>
 #include <net/cfg802154.h>
 
+#include "at86rf230.h"
+
 struct at86rf230_local;
 /* at86rf2xx chip depend data.
  * All timings are in us.
@@ -45,12 +47,14 @@ struct at86rf2xx_chip_data {
 	u16 t_reset_to_off;
 	u16 t_off_to_aack;
 	u16 t_off_to_tx_on;
+	u16 t_off_to_sleep;
+	u16 t_sleep_to_off;
 	u16 t_frame;
 	u16 t_p_ack;
 	int rssi_base_val;
 
 	int (*set_channel)(struct at86rf230_local *, u8, u8);
-	int (*get_desense_steps)(struct at86rf230_local *, s32);
+	int (*set_txpower)(struct at86rf230_local *, s32);
 };
 
 #define AT86RF2XX_MAX_BUF		(127 + 3)
@@ -85,6 +89,8 @@ struct at86rf230_local {
 	struct ieee802154_hw *hw;
 	struct at86rf2xx_chip_data *data;
 	struct regmap *regmap;
+	int slp_tr;
+	bool sleep;
 
 	struct completion state_complete;
 	struct at86rf230_state_change state;
@@ -95,203 +101,12 @@ struct at86rf230_local {
 	unsigned long cal_timeout;
 	s8 max_frame_retries;
 	bool is_tx;
+	bool is_tx_from_off;
 	u8 tx_retry;
 	struct sk_buff *tx_skb;
 	struct at86rf230_state_change tx;
 };
 
-#define	RG_TRX_STATUS	(0x01)
-#define	SR_TRX_STATUS		0x01, 0x1f, 0
-#define	SR_RESERVED_01_3	0x01, 0x20, 5
-#define	SR_CCA_STATUS		0x01, 0x40, 6
-#define	SR_CCA_DONE		0x01, 0x80, 7
-#define	RG_TRX_STATE	(0x02)
-#define	SR_TRX_CMD		0x02, 0x1f, 0
-#define	SR_TRAC_STATUS		0x02, 0xe0, 5
-#define	RG_TRX_CTRL_0	(0x03)
-#define	SR_CLKM_CTRL		0x03, 0x07, 0
-#define	SR_CLKM_SHA_SEL		0x03, 0x08, 3
-#define	SR_PAD_IO_CLKM		0x03, 0x30, 4
-#define	SR_PAD_IO		0x03, 0xc0, 6
-#define	RG_TRX_CTRL_1	(0x04)
-#define	SR_IRQ_POLARITY		0x04, 0x01, 0
-#define	SR_IRQ_MASK_MODE	0x04, 0x02, 1
-#define	SR_SPI_CMD_MODE		0x04, 0x0c, 2
-#define	SR_RX_BL_CTRL		0x04, 0x10, 4
-#define	SR_TX_AUTO_CRC_ON	0x04, 0x20, 5
-#define	SR_IRQ_2_EXT_EN		0x04, 0x40, 6
-#define	SR_PA_EXT_EN		0x04, 0x80, 7
-#define	RG_PHY_TX_PWR	(0x05)
-#define	SR_TX_PWR		0x05, 0x0f, 0
-#define	SR_PA_LT		0x05, 0x30, 4
-#define	SR_PA_BUF_LT		0x05, 0xc0, 6
-#define	RG_PHY_RSSI	(0x06)
-#define	SR_RSSI			0x06, 0x1f, 0
-#define	SR_RND_VALUE		0x06, 0x60, 5
-#define	SR_RX_CRC_VALID		0x06, 0x80, 7
-#define	RG_PHY_ED_LEVEL	(0x07)
-#define	SR_ED_LEVEL		0x07, 0xff, 0
-#define	RG_PHY_CC_CCA	(0x08)
-#define	SR_CHANNEL		0x08, 0x1f, 0
-#define	SR_CCA_MODE		0x08, 0x60, 5
-#define	SR_CCA_REQUEST		0x08, 0x80, 7
-#define	RG_CCA_THRES	(0x09)
-#define	SR_CCA_ED_THRES		0x09, 0x0f, 0
-#define	SR_RESERVED_09_1	0x09, 0xf0, 4
-#define	RG_RX_CTRL	(0x0a)
-#define	SR_PDT_THRES		0x0a, 0x0f, 0
-#define	SR_RESERVED_0a_1	0x0a, 0xf0, 4
-#define	RG_SFD_VALUE	(0x0b)
-#define	SR_SFD_VALUE		0x0b, 0xff, 0
-#define	RG_TRX_CTRL_2	(0x0c)
-#define	SR_OQPSK_DATA_RATE	0x0c, 0x03, 0
-#define	SR_SUB_MODE		0x0c, 0x04, 2
-#define	SR_BPSK_QPSK		0x0c, 0x08, 3
-#define	SR_OQPSK_SUB1_RC_EN	0x0c, 0x10, 4
-#define	SR_RESERVED_0c_5	0x0c, 0x60, 5
-#define	SR_RX_SAFE_MODE		0x0c, 0x80, 7
-#define	RG_ANT_DIV	(0x0d)
-#define	SR_ANT_CTRL		0x0d, 0x03, 0
-#define	SR_ANT_EXT_SW_EN	0x0d, 0x04, 2
-#define	SR_ANT_DIV_EN		0x0d, 0x08, 3
-#define	SR_RESERVED_0d_2	0x0d, 0x70, 4
-#define	SR_ANT_SEL		0x0d, 0x80, 7
-#define	RG_IRQ_MASK	(0x0e)
-#define	SR_IRQ_MASK		0x0e, 0xff, 0
-#define	RG_IRQ_STATUS	(0x0f)
-#define	SR_IRQ_0_PLL_LOCK	0x0f, 0x01, 0
-#define	SR_IRQ_1_PLL_UNLOCK	0x0f, 0x02, 1
-#define	SR_IRQ_2_RX_START	0x0f, 0x04, 2
-#define	SR_IRQ_3_TRX_END	0x0f, 0x08, 3
-#define	SR_IRQ_4_CCA_ED_DONE	0x0f, 0x10, 4
-#define	SR_IRQ_5_AMI		0x0f, 0x20, 5
-#define	SR_IRQ_6_TRX_UR		0x0f, 0x40, 6
-#define	SR_IRQ_7_BAT_LOW	0x0f, 0x80, 7
-#define	RG_VREG_CTRL	(0x10)
-#define	SR_RESERVED_10_6	0x10, 0x03, 0
-#define	SR_DVDD_OK		0x10, 0x04, 2
-#define	SR_DVREG_EXT		0x10, 0x08, 3
-#define	SR_RESERVED_10_3	0x10, 0x30, 4
-#define	SR_AVDD_OK		0x10, 0x40, 6
-#define	SR_AVREG_EXT		0x10, 0x80, 7
-#define	RG_BATMON	(0x11)
-#define	SR_BATMON_VTH		0x11, 0x0f, 0
-#define	SR_BATMON_HR		0x11, 0x10, 4
-#define	SR_BATMON_OK		0x11, 0x20, 5
-#define	SR_RESERVED_11_1	0x11, 0xc0, 6
-#define	RG_XOSC_CTRL	(0x12)
-#define	SR_XTAL_TRIM		0x12, 0x0f, 0
-#define	SR_XTAL_MODE		0x12, 0xf0, 4
-#define	RG_RX_SYN	(0x15)
-#define	SR_RX_PDT_LEVEL		0x15, 0x0f, 0
-#define	SR_RESERVED_15_2	0x15, 0x70, 4
-#define	SR_RX_PDT_DIS		0x15, 0x80, 7
-#define	RG_XAH_CTRL_1	(0x17)
-#define	SR_RESERVED_17_8	0x17, 0x01, 0
-#define	SR_AACK_PROM_MODE	0x17, 0x02, 1
-#define	SR_AACK_ACK_TIME	0x17, 0x04, 2
-#define	SR_RESERVED_17_5	0x17, 0x08, 3
-#define	SR_AACK_UPLD_RES_FT	0x17, 0x10, 4
-#define	SR_AACK_FLTR_RES_FT	0x17, 0x20, 5
-#define	SR_CSMA_LBT_MODE	0x17, 0x40, 6
-#define	SR_RESERVED_17_1	0x17, 0x80, 7
-#define	RG_FTN_CTRL	(0x18)
-#define	SR_RESERVED_18_2	0x18, 0x7f, 0
-#define	SR_FTN_START		0x18, 0x80, 7
-#define	RG_PLL_CF	(0x1a)
-#define	SR_RESERVED_1a_2	0x1a, 0x7f, 0
-#define	SR_PLL_CF_START		0x1a, 0x80, 7
-#define	RG_PLL_DCU	(0x1b)
-#define	SR_RESERVED_1b_3	0x1b, 0x3f, 0
-#define	SR_RESERVED_1b_2	0x1b, 0x40, 6
-#define	SR_PLL_DCU_START	0x1b, 0x80, 7
-#define	RG_PART_NUM	(0x1c)
-#define	SR_PART_NUM		0x1c, 0xff, 0
-#define	RG_VERSION_NUM	(0x1d)
-#define	SR_VERSION_NUM		0x1d, 0xff, 0
-#define	RG_MAN_ID_0	(0x1e)
-#define	SR_MAN_ID_0		0x1e, 0xff, 0
-#define	RG_MAN_ID_1	(0x1f)
-#define	SR_MAN_ID_1		0x1f, 0xff, 0
-#define	RG_SHORT_ADDR_0	(0x20)
-#define	SR_SHORT_ADDR_0		0x20, 0xff, 0
-#define	RG_SHORT_ADDR_1	(0x21)
-#define	SR_SHORT_ADDR_1		0x21, 0xff, 0
-#define	RG_PAN_ID_0	(0x22)
-#define	SR_PAN_ID_0		0x22, 0xff, 0
-#define	RG_PAN_ID_1	(0x23)
-#define	SR_PAN_ID_1		0x23, 0xff, 0
-#define	RG_IEEE_ADDR_0	(0x24)
-#define	SR_IEEE_ADDR_0		0x24, 0xff, 0
-#define	RG_IEEE_ADDR_1	(0x25)
-#define	SR_IEEE_ADDR_1		0x25, 0xff, 0
-#define	RG_IEEE_ADDR_2	(0x26)
-#define	SR_IEEE_ADDR_2		0x26, 0xff, 0
-#define	RG_IEEE_ADDR_3	(0x27)
-#define	SR_IEEE_ADDR_3		0x27, 0xff, 0
-#define	RG_IEEE_ADDR_4	(0x28)
-#define	SR_IEEE_ADDR_4		0x28, 0xff, 0
-#define	RG_IEEE_ADDR_5	(0x29)
-#define	SR_IEEE_ADDR_5		0x29, 0xff, 0
-#define	RG_IEEE_ADDR_6	(0x2a)
-#define	SR_IEEE_ADDR_6		0x2a, 0xff, 0
-#define	RG_IEEE_ADDR_7	(0x2b)
-#define	SR_IEEE_ADDR_7		0x2b, 0xff, 0
-#define	RG_XAH_CTRL_0	(0x2c)
-#define	SR_SLOTTED_OPERATION	0x2c, 0x01, 0
-#define	SR_MAX_CSMA_RETRIES	0x2c, 0x0e, 1
-#define	SR_MAX_FRAME_RETRIES	0x2c, 0xf0, 4
-#define	RG_CSMA_SEED_0	(0x2d)
-#define	SR_CSMA_SEED_0		0x2d, 0xff, 0
-#define	RG_CSMA_SEED_1	(0x2e)
-#define	SR_CSMA_SEED_1		0x2e, 0x07, 0
-#define	SR_AACK_I_AM_COORD	0x2e, 0x08, 3
-#define	SR_AACK_DIS_ACK		0x2e, 0x10, 4
-#define	SR_AACK_SET_PD		0x2e, 0x20, 5
-#define	SR_AACK_FVN_MODE	0x2e, 0xc0, 6
-#define	RG_CSMA_BE	(0x2f)
-#define	SR_MIN_BE		0x2f, 0x0f, 0
-#define	SR_MAX_BE		0x2f, 0xf0, 4
-
-#define CMD_REG		0x80
-#define CMD_REG_MASK	0x3f
-#define CMD_WRITE	0x40
-#define CMD_FB		0x20
-
-#define IRQ_BAT_LOW	(1 << 7)
-#define IRQ_TRX_UR	(1 << 6)
-#define IRQ_AMI		(1 << 5)
-#define IRQ_CCA_ED	(1 << 4)
-#define IRQ_TRX_END	(1 << 3)
-#define IRQ_RX_START	(1 << 2)
-#define IRQ_PLL_UNL	(1 << 1)
-#define IRQ_PLL_LOCK	(1 << 0)
-
-#define IRQ_ACTIVE_HIGH	0
-#define IRQ_ACTIVE_LOW	1
-
-#define STATE_P_ON		0x00	/* BUSY */
-#define STATE_BUSY_RX		0x01
-#define STATE_BUSY_TX		0x02
-#define STATE_FORCE_TRX_OFF	0x03
-#define STATE_FORCE_TX_ON	0x04	/* IDLE */
-/* 0x05 */				/* INVALID_PARAMETER */
-#define STATE_RX_ON		0x06
-/* 0x07 */				/* SUCCESS */
-#define STATE_TRX_OFF		0x08
-#define STATE_TX_ON		0x09
-/* 0x0a - 0x0e */			/* 0x0a - UNSUPPORTED_ATTRIBUTE */
-#define STATE_SLEEP		0x0F
-#define STATE_PREP_DEEP_SLEEP	0x10
-#define STATE_BUSY_RX_AACK	0x11
-#define STATE_BUSY_TX_ARET	0x12
-#define STATE_RX_AACK_ON	0x16
-#define STATE_TX_ARET_ON	0x19
-#define STATE_RX_ON_NOCLK	0x1C
-#define STATE_RX_AACK_ON_NOCLK	0x1D
-#define STATE_BUSY_RX_AACK_NOCLK 0x1E
-#define STATE_TRANSITION_IN_PROGRESS 0x1F
-
 #define AT86RF2XX_NUMREGS 0x3F
 
 static void
@@ -300,18 +115,66 @@ at86rf230_async_state_change(struct at86rf230_local *lp,
 			     const u8 state, void (*complete)(void *context),
 			     const bool irq_enable);
 
+static inline void
+at86rf230_sleep(struct at86rf230_local *lp)
+{
+	if (gpio_is_valid(lp->slp_tr)) {
+		gpio_set_value(lp->slp_tr, 1);
+		usleep_range(lp->data->t_off_to_sleep,
+			     lp->data->t_off_to_sleep + 10);
+		lp->sleep = true;
+	}
+}
+
+static inline void
+at86rf230_awake(struct at86rf230_local *lp)
+{
+	if (gpio_is_valid(lp->slp_tr)) {
+		gpio_set_value(lp->slp_tr, 0);
+		usleep_range(lp->data->t_sleep_to_off,
+			     lp->data->t_sleep_to_off + 100);
+		lp->sleep = false;
+	}
+}
+
 static inline int
 __at86rf230_write(struct at86rf230_local *lp,
 		  unsigned int addr, unsigned int data)
 {
-	return regmap_write(lp->regmap, addr, data);
+	bool sleep = lp->sleep;
+	int ret;
+
+	/* awake for register setting if sleep */
+	if (sleep)
+		at86rf230_awake(lp);
+
+	ret = regmap_write(lp->regmap, addr, data);
+
+	/* sleep again if was sleeping */
+	if (sleep)
+		at86rf230_sleep(lp);
+
+	return ret;
 }
 
 static inline int
 __at86rf230_read(struct at86rf230_local *lp,
 		 unsigned int addr, unsigned int *data)
 {
-	return regmap_read(lp->regmap, addr, data);
+	bool sleep = lp->sleep;
+	int ret;
+
+	/* awake for register setting if sleep */
+	if (sleep)
+		at86rf230_awake(lp);
+
+	ret = regmap_read(lp->regmap, addr, data);
+
+	/* sleep again if was sleeping */
+	if (sleep)
+		at86rf230_sleep(lp);
+
+	return ret;
 }
 
 static inline int
@@ -333,7 +196,28 @@ at86rf230_write_subreg(struct at86rf230_local *lp,
 		       unsigned int addr, unsigned int mask,
 		       unsigned int shift, unsigned int data)
 {
-	return regmap_update_bits(lp->regmap, addr, mask, data << shift);
+	bool sleep = lp->sleep;
+	int ret;
+
+	/* awake for register setting if sleep */
+	if (sleep)
+		at86rf230_awake(lp);
+
+	ret = regmap_update_bits(lp->regmap, addr, mask, data << shift);
+
+	/* sleep again if was sleeping */
+	if (sleep)
+		at86rf230_sleep(lp);
+
+	return ret;
+}
+
+static inline void
+at86rf230_slp_tr_rising_edge(struct at86rf230_local *lp)
+{
+	gpio_set_value(lp->slp_tr, 1);
+	udelay(1);
+	gpio_set_value(lp->slp_tr, 0);
 }
 
 static bool
@@ -509,7 +393,7 @@ at86rf230_async_state_assert(void *context)
 	struct at86rf230_state_change *ctx = context;
 	struct at86rf230_local *lp = ctx->lp;
 	const u8 *buf = ctx->buf;
-	const u8 trx_state = buf[1] & 0x1f;
+	const u8 trx_state = buf[1] & TRX_STATE_MASK;
 
 	/* Assert state change */
 	if (trx_state != ctx->to_state) {
@@ -609,11 +493,17 @@ at86rf230_async_state_delay(void *context)
 		switch (ctx->to_state) {
 		case STATE_RX_AACK_ON:
 			tim = ktime_set(0, c->t_off_to_aack * NSEC_PER_USEC);
+			/* state change from TRX_OFF to RX_AACK_ON to do a
+			 * calibration, we need to reset the timeout for the
+			 * next one.
+			 */
+			lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
 			goto change;
+		case STATE_TX_ARET_ON:
 		case STATE_TX_ON:
 			tim = ktime_set(0, c->t_off_to_tx_on * NSEC_PER_USEC);
-			/* state change from TRX_OFF to TX_ON to do a
-			 * calibration, we need to reset the timeout for the
+			/* state change from TRX_OFF to TX_ON or ARET_ON to do
+			 * a calibration, we need to reset the timeout for the
 			 * next one.
 			 */
 			lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
@@ -667,7 +557,7 @@ at86rf230_async_state_change_start(void *context)
 	struct at86rf230_state_change *ctx = context;
 	struct at86rf230_local *lp = ctx->lp;
 	u8 *buf = ctx->buf;
-	const u8 trx_state = buf[1] & 0x1f;
+	const u8 trx_state = buf[1] & TRX_STATE_MASK;
 	int rc;
 
 	/* Check for "possible" STATE_TRANSITION_IN_PROGRESS */
@@ -773,16 +663,6 @@ at86rf230_tx_on(void *context)
 }
 
 static void
-at86rf230_tx_trac_error(void *context)
-{
-	struct at86rf230_state_change *ctx = context;
-	struct at86rf230_local *lp = ctx->lp;
-
-	at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
-				     at86rf230_tx_on, true);
-}
-
-static void
 at86rf230_tx_trac_check(void *context)
 {
 	struct at86rf230_state_change *ctx = context;
@@ -791,12 +671,12 @@ at86rf230_tx_trac_check(void *context)
 	const u8 trac = (buf[1] & 0xe0) >> 5;
 
 	/* If trac status is different than zero we need to do a state change
-	 * to STATE_FORCE_TRX_OFF then STATE_TX_ON to recover the transceiver
-	 * state to TX_ON.
+	 * to STATE_FORCE_TRX_OFF then STATE_RX_AACK_ON to recover the
+	 * transceiver.
 	 */
 	if (trac)
 		at86rf230_async_state_change(lp, ctx, STATE_FORCE_TRX_OFF,
-					     at86rf230_tx_trac_error, true);
+					     at86rf230_tx_on, true);
 	else
 		at86rf230_tx_on(context);
 }
@@ -941,13 +821,18 @@ at86rf230_write_frame_complete(void *context)
 	u8 *buf = ctx->buf;
 	int rc;
 
-	buf[0] = (RG_TRX_STATE & CMD_REG_MASK) | CMD_REG | CMD_WRITE;
-	buf[1] = STATE_BUSY_TX;
 	ctx->trx.len = 2;
-	ctx->msg.complete = NULL;
-	rc = spi_async(lp->spi, &ctx->msg);
-	if (rc)
-		at86rf230_async_error(lp, ctx, rc);
+
+	if (gpio_is_valid(lp->slp_tr)) {
+		at86rf230_slp_tr_rising_edge(lp);
+	} else {
+		buf[0] = (RG_TRX_STATE & CMD_REG_MASK) | CMD_REG | CMD_WRITE;
+		buf[1] = STATE_BUSY_TX;
+		ctx->msg.complete = NULL;
+		rc = spi_async(lp->spi, &ctx->msg);
+		if (rc)
+			at86rf230_async_error(lp, ctx, rc);
+	}
 }
 
 static void
@@ -993,12 +878,21 @@ at86rf230_xmit_start(void *context)
 	 * are in STATE_TX_ON. The pfad differs here, so we change
 	 * the complete handler.
 	 */
-	if (lp->tx_aret)
-		at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
-					     at86rf230_xmit_tx_on, false);
-	else
+	if (lp->tx_aret) {
+		if (lp->is_tx_from_off) {
+			lp->is_tx_from_off = false;
+			at86rf230_async_state_change(lp, ctx, STATE_TX_ARET_ON,
+						     at86rf230_write_frame,
+						     false);
+		} else {
+			at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
+						     at86rf230_xmit_tx_on,
+						     false);
+		}
+	} else {
 		at86rf230_async_state_change(lp, ctx, STATE_TX_ON,
 					     at86rf230_write_frame, false);
+	}
 }
 
 static int
@@ -1017,11 +911,13 @@ at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 	 * to TX_ON, the lp->cal_timeout should be reinit by state_delay
 	 * function then to start in the next 5 minutes.
 	 */
-	if (time_is_before_jiffies(lp->cal_timeout))
+	if (time_is_before_jiffies(lp->cal_timeout)) {
+		lp->is_tx_from_off = true;
 		at86rf230_async_state_change(lp, ctx, STATE_TRX_OFF,
 					     at86rf230_xmit_start, false);
-	else
+	} else {
 		at86rf230_xmit_start(ctx);
+	}
 
 	return 0;
 }
@@ -1039,14 +935,32 @@ at86rf230_start(struct ieee802154_hw *hw)
 {
 	struct at86rf230_local *lp = hw->priv;
 
-	lp->cal_timeout = jiffies + AT86RF2XX_CAL_LOOP_TIMEOUT;
-	return at86rf230_sync_state_change(hw->priv, STATE_RX_AACK_ON);
+	at86rf230_awake(lp);
+	enable_irq(lp->spi->irq);
+
+	return at86rf230_sync_state_change(lp, STATE_RX_AACK_ON);
 }
 
 static void
 at86rf230_stop(struct ieee802154_hw *hw)
 {
-	at86rf230_sync_state_change(hw->priv, STATE_FORCE_TRX_OFF);
+	struct at86rf230_local *lp = hw->priv;
+	u8 csma_seed[2];
+
+	at86rf230_sync_state_change(lp, STATE_FORCE_TRX_OFF);
+
+	disable_irq(lp->spi->irq);
+
+	/* It's recommended to set random new csma_seeds before sleep state.
+	 * Makes only sense in the stop callback, not doing this inside of
+	 * at86rf230_sleep, this is also used when we don't transmit afterwards
+	 * when calling start callback again.
+	 */
+	get_random_bytes(csma_seed, ARRAY_SIZE(csma_seed));
+	at86rf230_write_subreg(lp, SR_CSMA_SEED_0, csma_seed[0]);
+	at86rf230_write_subreg(lp, SR_CSMA_SEED_1, csma_seed[1]);
+
+	at86rf230_sleep(lp);
 }
 
 static int
@@ -1055,6 +969,50 @@ at86rf23x_set_channel(struct at86rf230_local *lp, u8 page, u8 channel)
 	return at86rf230_write_subreg(lp, SR_CHANNEL, channel);
 }
 
+#define AT86RF2XX_MAX_ED_LEVELS 0xF
+static const s32 at86rf23x_ed_levels[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+	-9100, -8900, -8700, -8500, -8300, -8100, -7900, -7700, -7500, -7300,
+	-7100, -6900, -6700, -6500, -6300, -6100,
+};
+
+static const s32 at86rf212_ed_levels_100[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+	-10000, -9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200,
+	-8000, -7800, -7600, -7400, -7200, -7000,
+};
+
+static const s32 at86rf212_ed_levels_98[AT86RF2XX_MAX_ED_LEVELS + 1] = {
+	-9800, -9600, -9400, -9200, -9000, -8800, -8600, -8400, -8200, -8000,
+	-7800, -7600, -7400, -7200, -7000, -6800,
+};
+
+static inline int
+at86rf212_update_cca_ed_level(struct at86rf230_local *lp, int rssi_base_val)
+{
+	unsigned int cca_ed_thres;
+	int rc;
+
+	rc = at86rf230_read_subreg(lp, SR_CCA_ED_THRES, &cca_ed_thres);
+	if (rc < 0)
+		return rc;
+
+	switch (rssi_base_val) {
+	case -98:
+		lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_98;
+		lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_98);
+		lp->hw->phy->cca_ed_level = at86rf212_ed_levels_98[cca_ed_thres];
+		break;
+	case -100:
+		lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+		lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
+		lp->hw->phy->cca_ed_level = at86rf212_ed_levels_100[cca_ed_thres];
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	return 0;
+}
+
 static int
 at86rf212_set_channel(struct at86rf230_local *lp, u8 page, u8 channel)
 {
@@ -1077,6 +1035,10 @@ at86rf212_set_channel(struct at86rf230_local *lp, u8 page, u8 channel)
 	if (rc < 0)
 		return rc;
 
+	rc = at86rf212_update_cca_ed_level(lp, lp->data->rssi_base_val);
+	if (rc < 0)
+		return rc;
+
 	/* This sets the symbol_duration according frequency on the 212.
 	 * TODO move this handling while set channel and page in cfg802154.
 	 * We can do that, this timings are according 802.15.4 standard.
@@ -1172,23 +1134,56 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 	return 0;
 }
 
+#define AT86RF23X_MAX_TX_POWERS 0xF
+static const s32 at86rf233_powers[AT86RF23X_MAX_TX_POWERS + 1] = {
+	400, 370, 340, 300, 250, 200, 100, 0, -100, -200, -300, -400, -600,
+	-800, -1200, -1700,
+};
+
+static const s32 at86rf231_powers[AT86RF23X_MAX_TX_POWERS + 1] = {
+	300, 280, 230, 180, 130, 70, 0, -100, -200, -300, -400, -500, -700,
+	-900, -1200, -1700,
+};
+
+#define AT86RF212_MAX_TX_POWERS 0x1F
+static const s32 at86rf212_powers[AT86RF212_MAX_TX_POWERS + 1] = {
+	500, 400, 300, 200, 100, 0, -100, -200, -300, -400, -500, -600, -700,
+	-800, -900, -1000, -1100, -1200, -1300, -1400, -1500, -1600, -1700,
+	-1800, -1900, -2000, -2100, -2200, -2300, -2400, -2500, -2600,
+};
+
+static int
+at86rf23x_set_txpower(struct at86rf230_local *lp, s32 mbm)
+{
+	u32 i;
+
+	for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) {
+		if (lp->hw->phy->supported.tx_powers[i] == mbm)
+			return at86rf230_write_subreg(lp, SR_TX_PWR_23X, i);
+	}
+
+	return -EINVAL;
+}
+
 static int
-at86rf230_set_txpower(struct ieee802154_hw *hw, s8 db)
+at86rf212_set_txpower(struct at86rf230_local *lp, s32 mbm)
 {
-	struct at86rf230_local *lp = hw->priv;
+	u32 i;
 
-	/* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five
-	 * bits decrease power in 1dB steps. 0x60 represents extra PA gain of
-	 * 0dB.
-	 * thus, supported values for db range from -26 to 5, for 31dB of
-	 * reduction to 0dB of reduction.
-	 */
-	if (db > 5 || db < -26)
-		return -EINVAL;
+	for (i = 0; i < lp->hw->phy->supported.tx_powers_size; i++) {
+		if (lp->hw->phy->supported.tx_powers[i] == mbm)
+			return at86rf230_write_subreg(lp, SR_TX_PWR_212, i);
+	}
+
+	return -EINVAL;
+}
 
-	db = -(db - 5);
+static int
+at86rf230_set_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+	struct at86rf230_local *lp = hw->priv;
 
-	return __at86rf230_write(lp, RG_PHY_TX_PWR, 0x60 | db);
+	return lp->data->set_txpower(lp, mbm);
 }
 
 static int
@@ -1233,28 +1228,19 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw,
 	return at86rf230_write_subreg(lp, SR_CCA_MODE, val);
 }
 
-static int
-at86rf212_get_desens_steps(struct at86rf230_local *lp, s32 level)
-{
-	return (level - lp->data->rssi_base_val) * 100 / 207;
-}
-
-static int
-at86rf23x_get_desens_steps(struct at86rf230_local *lp, s32 level)
-{
-	return (level - lp->data->rssi_base_val) / 2;
-}
 
 static int
-at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 level)
+at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
 {
 	struct at86rf230_local *lp = hw->priv;
+	u32 i;
 
-	if (level < lp->data->rssi_base_val || level > 30)
-		return -EINVAL;
+	for (i = 0; i < hw->phy->supported.cca_ed_levels_size; i++) {
+		if (hw->phy->supported.cca_ed_levels[i] == mbm)
+			return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, i);
+	}
 
-	return at86rf230_write_subreg(lp, SR_CCA_ED_THRES,
-				      lp->data->get_desense_steps(lp, level));
+	return -EINVAL;
 }
 
 static int
@@ -1340,11 +1326,13 @@ static struct at86rf2xx_chip_data at86rf233_data = {
 	.t_reset_to_off = 26,
 	.t_off_to_aack = 80,
 	.t_off_to_tx_on = 80,
+	.t_off_to_sleep = 35,
+	.t_sleep_to_off = 210,
 	.t_frame = 4096,
 	.t_p_ack = 545,
 	.rssi_base_val = -91,
 	.set_channel = at86rf23x_set_channel,
-	.get_desense_steps = at86rf23x_get_desens_steps
+	.set_txpower = at86rf23x_set_txpower,
 };
 
 static struct at86rf2xx_chip_data at86rf231_data = {
@@ -1353,11 +1341,13 @@ static struct at86rf2xx_chip_data at86rf231_data = {
 	.t_reset_to_off = 37,
 	.t_off_to_aack = 110,
 	.t_off_to_tx_on = 110,
+	.t_off_to_sleep = 35,
+	.t_sleep_to_off = 380,
 	.t_frame = 4096,
 	.t_p_ack = 545,
 	.rssi_base_val = -91,
 	.set_channel = at86rf23x_set_channel,
-	.get_desense_steps = at86rf23x_get_desens_steps
+	.set_txpower = at86rf23x_set_txpower,
 };
 
 static struct at86rf2xx_chip_data at86rf212_data = {
@@ -1366,11 +1356,13 @@ static struct at86rf2xx_chip_data at86rf212_data = {
 	.t_reset_to_off = 26,
 	.t_off_to_aack = 200,
 	.t_off_to_tx_on = 200,
+	.t_off_to_sleep = 35,
+	.t_sleep_to_off = 380,
 	.t_frame = 4096,
 	.t_p_ack = 545,
 	.rssi_base_val = -100,
 	.set_channel = at86rf212_set_channel,
-	.get_desense_steps = at86rf212_get_desens_steps
+	.set_txpower = at86rf212_set_txpower,
 };
 
 static int at86rf230_hw_init(struct at86rf230_local *lp, u8 xtal_trim)
@@ -1542,9 +1534,22 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 		return -EINVAL;
 	}
 
-	lp->hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AACK |
-			IEEE802154_HW_TXPOWER | IEEE802154_HW_ARET |
-			IEEE802154_HW_AFILT | IEEE802154_HW_PROMISCUOUS;
+	lp->hw->flags = IEEE802154_HW_TX_OMIT_CKSUM |
+			IEEE802154_HW_CSMA_PARAMS |
+			IEEE802154_HW_FRAME_RETRIES | IEEE802154_HW_AFILT |
+			IEEE802154_HW_PROMISCUOUS;
+
+	lp->hw->phy->flags = WPAN_PHY_FLAG_TXPOWER |
+			     WPAN_PHY_FLAG_CCA_ED_LEVEL |
+			     WPAN_PHY_FLAG_CCA_MODE;
+
+	lp->hw->phy->supported.cca_modes = BIT(NL802154_CCA_ENERGY) |
+		BIT(NL802154_CCA_CARRIER) | BIT(NL802154_CCA_ENERGY_CARRIER);
+	lp->hw->phy->supported.cca_opts = BIT(NL802154_CCA_OPT_ENERGY_CARRIER_AND) |
+		BIT(NL802154_CCA_OPT_ENERGY_CARRIER_OR);
+
+	lp->hw->phy->supported.cca_ed_levels = at86rf23x_ed_levels;
+	lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf23x_ed_levels);
 
 	lp->hw->phy->cca.mode = NL802154_CCA_ENERGY;
 
@@ -1552,36 +1557,49 @@ at86rf230_detect_device(struct at86rf230_local *lp)
 	case 2:
 		chip = "at86rf230";
 		rc = -ENOTSUPP;
-		break;
+		goto not_supp;
 	case 3:
 		chip = "at86rf231";
 		lp->data = &at86rf231_data;
-		lp->hw->phy->channels_supported[0] = 0x7FFF800;
+		lp->hw->phy->supported.channels[0] = 0x7FFF800;
 		lp->hw->phy->current_channel = 11;
 		lp->hw->phy->symbol_duration = 16;
+		lp->hw->phy->supported.tx_powers = at86rf231_powers;
+		lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf231_powers);
 		break;
 	case 7:
 		chip = "at86rf212";
 		lp->data = &at86rf212_data;
 		lp->hw->flags |= IEEE802154_HW_LBT;
-		lp->hw->phy->channels_supported[0] = 0x00007FF;
-		lp->hw->phy->channels_supported[2] = 0x00007FF;
+		lp->hw->phy->supported.channels[0] = 0x00007FF;
+		lp->hw->phy->supported.channels[2] = 0x00007FF;
 		lp->hw->phy->current_channel = 5;
 		lp->hw->phy->symbol_duration = 25;
+		lp->hw->phy->supported.lbt = NL802154_SUPPORTED_BOOL_BOTH;
+		lp->hw->phy->supported.tx_powers = at86rf212_powers;
+		lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf212_powers);
+		lp->hw->phy->supported.cca_ed_levels = at86rf212_ed_levels_100;
+		lp->hw->phy->supported.cca_ed_levels_size = ARRAY_SIZE(at86rf212_ed_levels_100);
 		break;
 	case 11:
 		chip = "at86rf233";
 		lp->data = &at86rf233_data;
-		lp->hw->phy->channels_supported[0] = 0x7FFF800;
+		lp->hw->phy->supported.channels[0] = 0x7FFF800;
 		lp->hw->phy->current_channel = 13;
 		lp->hw->phy->symbol_duration = 16;
+		lp->hw->phy->supported.tx_powers = at86rf233_powers;
+		lp->hw->phy->supported.tx_powers_size = ARRAY_SIZE(at86rf233_powers);
 		break;
 	default:
 		chip = "unknown";
 		rc = -ENOTSUPP;
-		break;
+		goto not_supp;
 	}
 
+	lp->hw->phy->cca_ed_level = lp->hw->phy->supported.cca_ed_levels[7];
+	lp->hw->phy->transmit_power = lp->hw->phy->supported.tx_powers[0];
+
+not_supp:
 	dev_info(&lp->spi->dev, "Detected %s chip version %d\n", chip, version);
 
 	return rc;
@@ -1673,8 +1691,8 @@ static int at86rf230_probe(struct spi_device *spi)
 	lp = hw->priv;
 	lp->hw = hw;
 	lp->spi = spi;
+	lp->slp_tr = slp_tr;
 	hw->parent = &spi->dev;
-	hw->vif_data_size = sizeof(*lp);
 	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
 
 	lp->regmap = devm_regmap_init_spi(spi, &at86rf230_regmap_spi_config);
@@ -1706,13 +1724,19 @@ static int at86rf230_probe(struct spi_device *spi)
 
 	irq_type = irq_get_trigger_type(spi->irq);
 	if (!irq_type)
-		irq_type = IRQF_TRIGGER_RISING;
+		irq_type = IRQF_TRIGGER_HIGH;
 
 	rc = devm_request_irq(&spi->dev, spi->irq, at86rf230_isr,
 			      IRQF_SHARED | irq_type, dev_name(&spi->dev), lp);
 	if (rc)
 		goto free_dev;
 
+	/* disable_irq by default and wait for starting hardware */
+	disable_irq(spi->irq);
+
+	/* going into sleep by default */
+	at86rf230_sleep(lp);
+
 	rc = ieee802154_register_hw(lp->hw);
 	if (rc)
 		goto free_dev;
diff --git a/drivers/net/ieee802154/at86rf230.h b/drivers/net/ieee802154/at86rf230.h
new file mode 100644
index 000000000000..1e6d1cc677f6
--- /dev/null
+++ b/drivers/net/ieee802154/at86rf230.h
@@ -0,0 +1,220 @@
+/*
+ * AT86RF230/RF231 driver
+ *
+ * Copyright (C) 2009-2012 Siemens AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+#ifndef _AT86RF230_H
+#define _AT86RF230_H
+
+#define RG_TRX_STATUS	(0x01)
+#define SR_TRX_STATUS		0x01, 0x1f, 0
+#define SR_RESERVED_01_3	0x01, 0x20, 5
+#define SR_CCA_STATUS		0x01, 0x40, 6
+#define SR_CCA_DONE		0x01, 0x80, 7
+#define RG_TRX_STATE	(0x02)
+#define SR_TRX_CMD		0x02, 0x1f, 0
+#define SR_TRAC_STATUS		0x02, 0xe0, 5
+#define RG_TRX_CTRL_0	(0x03)
+#define SR_CLKM_CTRL		0x03, 0x07, 0
+#define SR_CLKM_SHA_SEL		0x03, 0x08, 3
+#define SR_PAD_IO_CLKM		0x03, 0x30, 4
+#define SR_PAD_IO		0x03, 0xc0, 6
+#define RG_TRX_CTRL_1	(0x04)
+#define SR_IRQ_POLARITY		0x04, 0x01, 0
+#define SR_IRQ_MASK_MODE	0x04, 0x02, 1
+#define SR_SPI_CMD_MODE		0x04, 0x0c, 2
+#define SR_RX_BL_CTRL		0x04, 0x10, 4
+#define SR_TX_AUTO_CRC_ON	0x04, 0x20, 5
+#define SR_IRQ_2_EXT_EN		0x04, 0x40, 6
+#define SR_PA_EXT_EN		0x04, 0x80, 7
+#define RG_PHY_TX_PWR	(0x05)
+#define SR_TX_PWR_23X		0x05, 0x0f, 0
+#define SR_PA_LT_230		0x05, 0x30, 4
+#define SR_PA_BUF_LT_230	0x05, 0xc0, 6
+#define SR_TX_PWR_212		0x05, 0x1f, 0
+#define SR_GC_PA_212		0x05, 0x60, 5
+#define SR_PA_BOOST_LT_212	0x05, 0x80, 7
+#define RG_PHY_RSSI	(0x06)
+#define SR_RSSI			0x06, 0x1f, 0
+#define SR_RND_VALUE		0x06, 0x60, 5
+#define SR_RX_CRC_VALID		0x06, 0x80, 7
+#define RG_PHY_ED_LEVEL	(0x07)
+#define SR_ED_LEVEL		0x07, 0xff, 0
+#define RG_PHY_CC_CCA	(0x08)
+#define SR_CHANNEL		0x08, 0x1f, 0
+#define SR_CCA_MODE		0x08, 0x60, 5
+#define SR_CCA_REQUEST		0x08, 0x80, 7
+#define RG_CCA_THRES	(0x09)
+#define SR_CCA_ED_THRES		0x09, 0x0f, 0
+#define SR_RESERVED_09_1	0x09, 0xf0, 4
+#define RG_RX_CTRL	(0x0a)
+#define SR_PDT_THRES		0x0a, 0x0f, 0
+#define SR_RESERVED_0a_1	0x0a, 0xf0, 4
+#define RG_SFD_VALUE	(0x0b)
+#define SR_SFD_VALUE		0x0b, 0xff, 0
+#define RG_TRX_CTRL_2	(0x0c)
+#define SR_OQPSK_DATA_RATE	0x0c, 0x03, 0
+#define SR_SUB_MODE		0x0c, 0x04, 2
+#define SR_BPSK_QPSK		0x0c, 0x08, 3
+#define SR_OQPSK_SUB1_RC_EN	0x0c, 0x10, 4
+#define SR_RESERVED_0c_5	0x0c, 0x60, 5
+#define SR_RX_SAFE_MODE		0x0c, 0x80, 7
+#define RG_ANT_DIV	(0x0d)
+#define SR_ANT_CTRL		0x0d, 0x03, 0
+#define SR_ANT_EXT_SW_EN	0x0d, 0x04, 2
+#define SR_ANT_DIV_EN		0x0d, 0x08, 3
+#define SR_RESERVED_0d_2	0x0d, 0x70, 4
+#define SR_ANT_SEL		0x0d, 0x80, 7
+#define RG_IRQ_MASK	(0x0e)
+#define SR_IRQ_MASK		0x0e, 0xff, 0
+#define RG_IRQ_STATUS	(0x0f)
+#define SR_IRQ_0_PLL_LOCK	0x0f, 0x01, 0
+#define SR_IRQ_1_PLL_UNLOCK	0x0f, 0x02, 1
+#define SR_IRQ_2_RX_START	0x0f, 0x04, 2
+#define SR_IRQ_3_TRX_END	0x0f, 0x08, 3
+#define SR_IRQ_4_CCA_ED_DONE	0x0f, 0x10, 4
+#define SR_IRQ_5_AMI		0x0f, 0x20, 5
+#define SR_IRQ_6_TRX_UR		0x0f, 0x40, 6
+#define SR_IRQ_7_BAT_LOW	0x0f, 0x80, 7
+#define RG_VREG_CTRL	(0x10)
+#define SR_RESERVED_10_6	0x10, 0x03, 0
+#define SR_DVDD_OK		0x10, 0x04, 2
+#define SR_DVREG_EXT		0x10, 0x08, 3
+#define SR_RESERVED_10_3	0x10, 0x30, 4
+#define SR_AVDD_OK		0x10, 0x40, 6
+#define SR_AVREG_EXT		0x10, 0x80, 7
+#define RG_BATMON	(0x11)
+#define SR_BATMON_VTH		0x11, 0x0f, 0
+#define SR_BATMON_HR		0x11, 0x10, 4
+#define SR_BATMON_OK		0x11, 0x20, 5
+#define SR_RESERVED_11_1	0x11, 0xc0, 6
+#define RG_XOSC_CTRL	(0x12)
+#define SR_XTAL_TRIM		0x12, 0x0f, 0
+#define SR_XTAL_MODE		0x12, 0xf0, 4
+#define RG_RX_SYN	(0x15)
+#define SR_RX_PDT_LEVEL		0x15, 0x0f, 0
+#define SR_RESERVED_15_2	0x15, 0x70, 4
+#define SR_RX_PDT_DIS		0x15, 0x80, 7
+#define RG_XAH_CTRL_1	(0x17)
+#define SR_RESERVED_17_8	0x17, 0x01, 0
+#define SR_AACK_PROM_MODE	0x17, 0x02, 1
+#define SR_AACK_ACK_TIME	0x17, 0x04, 2
+#define SR_RESERVED_17_5	0x17, 0x08, 3
+#define SR_AACK_UPLD_RES_FT	0x17, 0x10, 4
+#define SR_AACK_FLTR_RES_FT	0x17, 0x20, 5
+#define SR_CSMA_LBT_MODE	0x17, 0x40, 6
+#define SR_RESERVED_17_1	0x17, 0x80, 7
+#define RG_FTN_CTRL	(0x18)
+#define SR_RESERVED_18_2	0x18, 0x7f, 0
+#define SR_FTN_START		0x18, 0x80, 7
+#define RG_PLL_CF	(0x1a)
+#define SR_RESERVED_1a_2	0x1a, 0x7f, 0
+#define SR_PLL_CF_START		0x1a, 0x80, 7
+#define RG_PLL_DCU	(0x1b)
+#define SR_RESERVED_1b_3	0x1b, 0x3f, 0
+#define SR_RESERVED_1b_2	0x1b, 0x40, 6
+#define SR_PLL_DCU_START	0x1b, 0x80, 7
+#define RG_PART_NUM	(0x1c)
+#define SR_PART_NUM		0x1c, 0xff, 0
+#define RG_VERSION_NUM	(0x1d)
+#define SR_VERSION_NUM		0x1d, 0xff, 0
+#define RG_MAN_ID_0	(0x1e)
+#define SR_MAN_ID_0		0x1e, 0xff, 0
+#define RG_MAN_ID_1	(0x1f)
+#define SR_MAN_ID_1		0x1f, 0xff, 0
+#define RG_SHORT_ADDR_0	(0x20)
+#define SR_SHORT_ADDR_0		0x20, 0xff, 0
+#define RG_SHORT_ADDR_1	(0x21)
+#define SR_SHORT_ADDR_1		0x21, 0xff, 0
+#define RG_PAN_ID_0	(0x22)
+#define SR_PAN_ID_0		0x22, 0xff, 0
+#define RG_PAN_ID_1	(0x23)
+#define SR_PAN_ID_1		0x23, 0xff, 0
+#define RG_IEEE_ADDR_0	(0x24)
+#define SR_IEEE_ADDR_0		0x24, 0xff, 0
+#define RG_IEEE_ADDR_1	(0x25)
+#define SR_IEEE_ADDR_1		0x25, 0xff, 0
+#define RG_IEEE_ADDR_2	(0x26)
+#define SR_IEEE_ADDR_2		0x26, 0xff, 0
+#define RG_IEEE_ADDR_3	(0x27)
+#define SR_IEEE_ADDR_3		0x27, 0xff, 0
+#define RG_IEEE_ADDR_4	(0x28)
+#define SR_IEEE_ADDR_4		0x28, 0xff, 0
+#define RG_IEEE_ADDR_5	(0x29)
+#define SR_IEEE_ADDR_5		0x29, 0xff, 0
+#define RG_IEEE_ADDR_6	(0x2a)
+#define SR_IEEE_ADDR_6		0x2a, 0xff, 0
+#define RG_IEEE_ADDR_7	(0x2b)
+#define SR_IEEE_ADDR_7		0x2b, 0xff, 0
+#define RG_XAH_CTRL_0	(0x2c)
+#define SR_SLOTTED_OPERATION	0x2c, 0x01, 0
+#define SR_MAX_CSMA_RETRIES	0x2c, 0x0e, 1
+#define SR_MAX_FRAME_RETRIES	0x2c, 0xf0, 4
+#define RG_CSMA_SEED_0	(0x2d)
+#define SR_CSMA_SEED_0		0x2d, 0xff, 0
+#define RG_CSMA_SEED_1	(0x2e)
+#define SR_CSMA_SEED_1		0x2e, 0x07, 0
+#define SR_AACK_I_AM_COORD	0x2e, 0x08, 3
+#define SR_AACK_DIS_ACK		0x2e, 0x10, 4
+#define SR_AACK_SET_PD		0x2e, 0x20, 5
+#define SR_AACK_FVN_MODE	0x2e, 0xc0, 6
+#define RG_CSMA_BE	(0x2f)
+#define SR_MIN_BE		0x2f, 0x0f, 0
+#define SR_MAX_BE		0x2f, 0xf0, 4
+
+#define CMD_REG		0x80
+#define CMD_REG_MASK	0x3f
+#define CMD_WRITE	0x40
+#define CMD_FB		0x20
+
+#define IRQ_BAT_LOW	BIT(7)
+#define IRQ_TRX_UR	BIT(6)
+#define IRQ_AMI		BIT(5)
+#define IRQ_CCA_ED	BIT(4)
+#define IRQ_TRX_END	BIT(3)
+#define IRQ_RX_START	BIT(2)
+#define IRQ_PLL_UNL	BIT(1)
+#define IRQ_PLL_LOCK	BIT(0)
+
+#define IRQ_ACTIVE_HIGH	0
+#define IRQ_ACTIVE_LOW	1
+
+#define STATE_P_ON		0x00	/* BUSY */
+#define STATE_BUSY_RX		0x01
+#define STATE_BUSY_TX		0x02
+#define STATE_FORCE_TRX_OFF	0x03
+#define STATE_FORCE_TX_ON	0x04	/* IDLE */
+/* 0x05 */				/* INVALID_PARAMETER */
+#define STATE_RX_ON		0x06
+/* 0x07 */				/* SUCCESS */
+#define STATE_TRX_OFF		0x08
+#define STATE_TX_ON		0x09
+/* 0x0a - 0x0e */			/* 0x0a - UNSUPPORTED_ATTRIBUTE */
+#define STATE_SLEEP		0x0F
+#define STATE_PREP_DEEP_SLEEP	0x10
+#define STATE_BUSY_RX_AACK	0x11
+#define STATE_BUSY_TX_ARET	0x12
+#define STATE_RX_AACK_ON	0x16
+#define STATE_TX_ARET_ON	0x19
+#define STATE_RX_ON_NOCLK	0x1C
+#define STATE_RX_AACK_ON_NOCLK	0x1D
+#define STATE_BUSY_RX_AACK_NOCLK 0x1E
+#define STATE_TRANSITION_IN_PROGRESS 0x1F
+
+#define TRX_STATE_MASK		(0x1F)
+
+#endif /* !_AT86RF230_H */
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
new file mode 100644
index 000000000000..80dfc725b8dc
--- /dev/null
+++ b/drivers/net/ieee802154/atusb.c
@@ -0,0 +1,762 @@
+/*
+ * atusb.c - Driver for the ATUSB IEEE 802.15.4 dongle
+ *
+ * Written 2013 by Werner Almesberger <werner@almesberger.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2
+ *
+ * Based on at86rf230.c and spi_atusb.c.
+ * at86rf230.c is
+ * Copyright (C) 2009 Siemens AG
+ * Written by: Dmitry Eremin-Solenikov <dmitry.baryshkov@siemens.com>
+ *
+ * spi_atusb.c is
+ * Copyright (c) 2011 Richard Sharpe <realrichardsharpe@gmail.com>
+ * Copyright (c) 2011 Stefan Schmidt <stefan@datenfreihafen.org>
+ * Copyright (c) 2011 Werner Almesberger <werner@almesberger.net>
+ *
+ * USB initialization is
+ * Copyright (c) 2013 Alexander Aring <alex.aring@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/usb.h>
+#include <linux/skbuff.h>
+
+#include <net/cfg802154.h>
+#include <net/mac802154.h>
+
+#include "at86rf230.h"
+#include "atusb.h"
+
+#define ATUSB_JEDEC_ATMEL	0x1f	/* JEDEC manufacturer ID */
+
+#define ATUSB_NUM_RX_URBS	4	/* allow for a bit of local latency */
+#define ATUSB_ALLOC_DELAY_MS	100	/* delay after failed allocation */
+#define ATUSB_TX_TIMEOUT_MS	200	/* on the air timeout */
+
+struct atusb {
+	struct ieee802154_hw *hw;
+	struct usb_device *usb_dev;
+	int shutdown;			/* non-zero if shutting down */
+	int err;			/* set by first error */
+
+	/* RX variables */
+	struct delayed_work work;	/* memory allocations */
+	struct usb_anchor idle_urbs;	/* URBs waiting to be submitted */
+	struct usb_anchor rx_urbs;	/* URBs waiting for reception */
+
+	/* TX variables */
+	struct usb_ctrlrequest tx_dr;
+	struct urb *tx_urb;
+	struct sk_buff *tx_skb;
+	uint8_t tx_ack_seq;		/* current TX ACK sequence number */
+};
+
+/* ----- USB commands without data ----------------------------------------- */
+
+/* To reduce the number of error checks in the code, we record the first error
+ * in atusb->err and reject all subsequent requests until the error is cleared.
+ */
+
+static int atusb_control_msg(struct atusb *atusb, unsigned int pipe,
+			     __u8 request, __u8 requesttype,
+			     __u16 value, __u16 index,
+			     void *data, __u16 size, int timeout)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	int ret;
+
+	if (atusb->err)
+		return atusb->err;
+
+	ret = usb_control_msg(usb_dev, pipe, request, requesttype,
+			      value, index, data, size, timeout);
+	if (ret < 0) {
+		atusb->err = ret;
+		dev_err(&usb_dev->dev,
+			"atusb_control_msg: req 0x%02x val 0x%x idx 0x%x, error %d\n",
+			request, value, index, ret);
+	}
+	return ret;
+}
+
+static int atusb_command(struct atusb *atusb, uint8_t cmd, uint8_t arg)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+
+	dev_dbg(&usb_dev->dev, "atusb_command: cmd = 0x%x\n", cmd);
+	return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0),
+				 cmd, ATUSB_REQ_TO_DEV, arg, 0, NULL, 0, 1000);
+}
+
+static int atusb_write_reg(struct atusb *atusb, uint8_t reg, uint8_t value)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+
+	dev_dbg(&usb_dev->dev, "atusb_write_reg: 0x%02x <- 0x%02x\n",
+		reg, value);
+	return atusb_control_msg(atusb, usb_sndctrlpipe(usb_dev, 0),
+				 ATUSB_REG_WRITE, ATUSB_REQ_TO_DEV,
+				 value, reg, NULL, 0, 1000);
+}
+
+static int atusb_read_reg(struct atusb *atusb, uint8_t reg)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	int ret;
+	uint8_t value;
+
+	dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg);
+	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
+				ATUSB_REG_READ, ATUSB_REQ_FROM_DEV,
+				0, reg, &value, 1, 1000);
+	return ret >= 0 ? value : ret;
+}
+
+static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
+			      uint8_t shift, uint8_t value)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	uint8_t orig, tmp;
+	int ret = 0;
+
+	dev_dbg(&usb_dev->dev, "atusb_write_subreg: 0x%02x <- 0x%02x\n",
+		reg, value);
+
+	orig = atusb_read_reg(atusb, reg);
+
+	/* Write the value only into that part of the register which is allowed
+	 * by the mask. All other bits stay as before.
+	 */
+	tmp = orig & ~mask;
+	tmp |= (value << shift) & mask;
+
+	if (tmp != orig)
+		ret = atusb_write_reg(atusb, reg, tmp);
+
+	return ret;
+}
+
+static int atusb_get_and_clear_error(struct atusb *atusb)
+{
+	int err = atusb->err;
+
+	atusb->err = 0;
+	return err;
+}
+
+/* ----- skb allocation ---------------------------------------------------- */
+
+#define MAX_PSDU	127
+#define MAX_RX_XFER	(1 + MAX_PSDU + 2 + 1)	/* PHR+PSDU+CRC+LQI */
+
+#define SKB_ATUSB(skb)	(*(struct atusb **)(skb)->cb)
+
+static void atusb_in(struct urb *urb);
+
+static int atusb_submit_rx_urb(struct atusb *atusb, struct urb *urb)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	struct sk_buff *skb = urb->context;
+	int ret;
+
+	if (!skb) {
+		skb = alloc_skb(MAX_RX_XFER, GFP_KERNEL);
+		if (!skb) {
+			dev_warn_ratelimited(&usb_dev->dev,
+					     "atusb_in: can't allocate skb\n");
+			return -ENOMEM;
+		}
+		skb_put(skb, MAX_RX_XFER);
+		SKB_ATUSB(skb) = atusb;
+	}
+
+	usb_fill_bulk_urb(urb, usb_dev, usb_rcvbulkpipe(usb_dev, 1),
+			  skb->data, MAX_RX_XFER, atusb_in, skb);
+	usb_anchor_urb(urb, &atusb->rx_urbs);
+
+	ret = usb_submit_urb(urb, GFP_KERNEL);
+	if (ret) {
+		usb_unanchor_urb(urb);
+		kfree_skb(skb);
+		urb->context = NULL;
+	}
+	return ret;
+}
+
+static void atusb_work_urbs(struct work_struct *work)
+{
+	struct atusb *atusb =
+	    container_of(to_delayed_work(work), struct atusb, work);
+	struct usb_device *usb_dev = atusb->usb_dev;
+	struct urb *urb;
+	int ret;
+
+	if (atusb->shutdown)
+		return;
+
+	do {
+		urb = usb_get_from_anchor(&atusb->idle_urbs);
+		if (!urb)
+			return;
+		ret = atusb_submit_rx_urb(atusb, urb);
+	} while (!ret);
+
+	usb_anchor_urb(urb, &atusb->idle_urbs);
+	dev_warn_ratelimited(&usb_dev->dev,
+			     "atusb_in: can't allocate/submit URB (%d)\n", ret);
+	schedule_delayed_work(&atusb->work,
+			      msecs_to_jiffies(ATUSB_ALLOC_DELAY_MS) + 1);
+}
+
+/* ----- Asynchronous USB -------------------------------------------------- */
+
+static void atusb_tx_done(struct atusb *atusb, uint8_t seq)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	uint8_t expect = atusb->tx_ack_seq;
+
+	dev_dbg(&usb_dev->dev, "atusb_tx_done (0x%02x/0x%02x)\n", seq, expect);
+	if (seq == expect) {
+		/* TODO check for ifs handling in firmware */
+		ieee802154_xmit_complete(atusb->hw, atusb->tx_skb, false);
+	} else {
+		/* TODO I experience this case when atusb has a tx complete
+		 * irq before probing, we should fix the firmware it's an
+		 * unlikely case now that seq == expect is then true, but can
+		 * happen and fail with a tx_skb = NULL;
+		 */
+		ieee802154_wake_queue(atusb->hw);
+		if (atusb->tx_skb)
+			dev_kfree_skb_irq(atusb->tx_skb);
+	}
+}
+
+static void atusb_in_good(struct urb *urb)
+{
+	struct usb_device *usb_dev = urb->dev;
+	struct sk_buff *skb = urb->context;
+	struct atusb *atusb = SKB_ATUSB(skb);
+	uint8_t len, lqi;
+
+	if (!urb->actual_length) {
+		dev_dbg(&usb_dev->dev, "atusb_in: zero-sized URB ?\n");
+		return;
+	}
+
+	len = *skb->data;
+
+	if (urb->actual_length == 1) {
+		atusb_tx_done(atusb, len);
+		return;
+	}
+
+	if (len + 1 > urb->actual_length - 1) {
+		dev_dbg(&usb_dev->dev, "atusb_in: frame len %d+1 > URB %u-1\n",
+			len, urb->actual_length);
+		return;
+	}
+
+	if (!ieee802154_is_valid_psdu_len(len)) {
+		dev_dbg(&usb_dev->dev, "atusb_in: frame corrupted\n");
+		return;
+	}
+
+	lqi = skb->data[len + 1];
+	dev_dbg(&usb_dev->dev, "atusb_in: rx len %d lqi 0x%02x\n", len, lqi);
+	skb_pull(skb, 1);	/* remove PHR */
+	skb_trim(skb, len);	/* get payload only */
+	ieee802154_rx_irqsafe(atusb->hw, skb, lqi);
+	urb->context = NULL;	/* skb is gone */
+}
+
+static void atusb_in(struct urb *urb)
+{
+	struct usb_device *usb_dev = urb->dev;
+	struct sk_buff *skb = urb->context;
+	struct atusb *atusb = SKB_ATUSB(skb);
+
+	dev_dbg(&usb_dev->dev, "atusb_in: status %d len %d\n",
+		urb->status, urb->actual_length);
+	if (urb->status) {
+		if (urb->status == -ENOENT) { /* being killed */
+			kfree_skb(skb);
+			urb->context = NULL;
+			return;
+		}
+		dev_dbg(&usb_dev->dev, "atusb_in: URB error %d\n", urb->status);
+	} else {
+		atusb_in_good(urb);
+	}
+
+	usb_anchor_urb(urb, &atusb->idle_urbs);
+	if (!atusb->shutdown)
+		schedule_delayed_work(&atusb->work, 0);
+}
+
+/* ----- URB allocation/deallocation --------------------------------------- */
+
+static void atusb_free_urbs(struct atusb *atusb)
+{
+	struct urb *urb;
+
+	while (1) {
+		urb = usb_get_from_anchor(&atusb->idle_urbs);
+		if (!urb)
+			break;
+		if (urb->context)
+			kfree_skb(urb->context);
+		usb_free_urb(urb);
+	}
+}
+
+static int atusb_alloc_urbs(struct atusb *atusb, int n)
+{
+	struct urb *urb;
+
+	while (n) {
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			atusb_free_urbs(atusb);
+			return -ENOMEM;
+		}
+		usb_anchor_urb(urb, &atusb->idle_urbs);
+		n--;
+	}
+	return 0;
+}
+
+/* ----- IEEE 802.15.4 interface operations -------------------------------- */
+
+static void atusb_xmit_complete(struct urb *urb)
+{
+	dev_dbg(&urb->dev->dev, "atusb_xmit urb completed");
+}
+
+static int atusb_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	struct atusb *atusb = hw->priv;
+	struct usb_device *usb_dev = atusb->usb_dev;
+	int ret;
+
+	dev_dbg(&usb_dev->dev, "atusb_xmit (%d)\n", skb->len);
+	atusb->tx_skb = skb;
+	atusb->tx_ack_seq++;
+	atusb->tx_dr.wIndex = cpu_to_le16(atusb->tx_ack_seq);
+	atusb->tx_dr.wLength = cpu_to_le16(skb->len);
+
+	usb_fill_control_urb(atusb->tx_urb, usb_dev,
+			     usb_sndctrlpipe(usb_dev, 0),
+			     (unsigned char *)&atusb->tx_dr, skb->data,
+			     skb->len, atusb_xmit_complete, NULL);
+	ret = usb_submit_urb(atusb->tx_urb, GFP_ATOMIC);
+	dev_dbg(&usb_dev->dev, "atusb_xmit done (%d)\n", ret);
+	return ret;
+}
+
+static int atusb_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	struct atusb *atusb = hw->priv;
+	int ret;
+
+	/* This implicitly sets the CCA (Clear Channel Assessment) mode to 0,
+	 * "Mode 3a, Carrier sense OR energy above threshold".
+	 * We should probably make this configurable. @@@
+	 */
+	ret = atusb_write_reg(atusb, RG_PHY_CC_CCA, channel);
+	if (ret < 0)
+		return ret;
+	msleep(1);	/* @@@ ugly synchronization */
+	return 0;
+}
+
+static int atusb_ed(struct ieee802154_hw *hw, u8 *level)
+{
+	BUG_ON(!level);
+	*level = 0xbe;
+	return 0;
+}
+
+static int atusb_set_hw_addr_filt(struct ieee802154_hw *hw,
+				  struct ieee802154_hw_addr_filt *filt,
+				  unsigned long changed)
+{
+	struct atusb *atusb = hw->priv;
+	struct device *dev = &atusb->usb_dev->dev;
+
+	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
+		u16 addr = le16_to_cpu(filt->short_addr);
+
+		dev_vdbg(dev, "atusb_set_hw_addr_filt called for saddr\n");
+		atusb_write_reg(atusb, RG_SHORT_ADDR_0, addr);
+		atusb_write_reg(atusb, RG_SHORT_ADDR_1, addr >> 8);
+	}
+
+	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
+		u16 pan = le16_to_cpu(filt->pan_id);
+
+		dev_vdbg(dev, "atusb_set_hw_addr_filt called for pan id\n");
+		atusb_write_reg(atusb, RG_PAN_ID_0, pan);
+		atusb_write_reg(atusb, RG_PAN_ID_1, pan >> 8);
+	}
+
+	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
+		u8 i, addr[IEEE802154_EXTENDED_ADDR_LEN];
+
+		memcpy(addr, &filt->ieee_addr, IEEE802154_EXTENDED_ADDR_LEN);
+		dev_vdbg(dev, "atusb_set_hw_addr_filt called for IEEE addr\n");
+		for (i = 0; i < 8; i++)
+			atusb_write_reg(atusb, RG_IEEE_ADDR_0 + i, addr[i]);
+	}
+
+	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
+		dev_vdbg(dev,
+			 "atusb_set_hw_addr_filt called for panc change\n");
+		if (filt->pan_coord)
+			atusb_write_subreg(atusb, SR_AACK_I_AM_COORD, 1);
+		else
+			atusb_write_subreg(atusb, SR_AACK_I_AM_COORD, 0);
+	}
+
+	return atusb_get_and_clear_error(atusb);
+}
+
+static int atusb_start(struct ieee802154_hw *hw)
+{
+	struct atusb *atusb = hw->priv;
+	struct usb_device *usb_dev = atusb->usb_dev;
+	int ret;
+
+	dev_dbg(&usb_dev->dev, "atusb_start\n");
+	schedule_delayed_work(&atusb->work, 0);
+	atusb_command(atusb, ATUSB_RX_MODE, 1);
+	ret = atusb_get_and_clear_error(atusb);
+	if (ret < 0)
+		usb_kill_anchored_urbs(&atusb->idle_urbs);
+	return ret;
+}
+
+static void atusb_stop(struct ieee802154_hw *hw)
+{
+	struct atusb *atusb = hw->priv;
+	struct usb_device *usb_dev = atusb->usb_dev;
+
+	dev_dbg(&usb_dev->dev, "atusb_stop\n");
+	usb_kill_anchored_urbs(&atusb->idle_urbs);
+	atusb_command(atusb, ATUSB_RX_MODE, 0);
+	atusb_get_and_clear_error(atusb);
+}
+
+#define ATUSB_MAX_TX_POWERS 0xF
+static const s32 atusb_powers[ATUSB_MAX_TX_POWERS + 1] = {
+	300, 280, 230, 180, 130, 70, 0, -100, -200, -300, -400, -500, -700,
+	-900, -1200, -1700,
+};
+
+static int
+atusb_set_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+	struct atusb *atusb = hw->priv;
+	u32 i;
+
+	for (i = 0; i < hw->phy->supported.tx_powers_size; i++) {
+		if (hw->phy->supported.tx_powers[i] == mbm)
+			return atusb_write_subreg(atusb, SR_TX_PWR_23X, i);
+	}
+
+	return -EINVAL;
+}
+
+static int
+atusb_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
+{
+	struct atusb *atusb = hw->priv;
+	int ret;
+
+	if (on) {
+		ret = atusb_write_subreg(atusb, SR_AACK_DIS_ACK, 1);
+		if (ret < 0)
+			return ret;
+
+		ret = atusb_write_subreg(atusb, SR_AACK_PROM_MODE, 1);
+		if (ret < 0)
+			return ret;
+	} else {
+		ret = atusb_write_subreg(atusb, SR_AACK_PROM_MODE, 0);
+		if (ret < 0)
+			return ret;
+
+		ret = atusb_write_subreg(atusb, SR_AACK_DIS_ACK, 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static struct ieee802154_ops atusb_ops = {
+	.owner			= THIS_MODULE,
+	.xmit_async		= atusb_xmit,
+	.ed			= atusb_ed,
+	.set_channel		= atusb_channel,
+	.start			= atusb_start,
+	.stop			= atusb_stop,
+	.set_hw_addr_filt	= atusb_set_hw_addr_filt,
+	.set_txpower		= atusb_set_txpower,
+	.set_promiscuous_mode	= atusb_set_promiscuous_mode,
+};
+
+/* ----- Firmware and chip version information ----------------------------- */
+
+static int atusb_get_and_show_revision(struct atusb *atusb)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	unsigned char buffer[3];
+	int ret;
+
+	/* Get a couple of the ATMega Firmware values */
+	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
+				ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0,
+				buffer, 3, 1000);
+	if (ret >= 0)
+		dev_info(&usb_dev->dev,
+			 "Firmware: major: %u, minor: %u, hardware type: %u\n",
+			 buffer[0], buffer[1], buffer[2]);
+	if (buffer[0] == 0 && buffer[1] < 2) {
+		dev_info(&usb_dev->dev,
+			 "Firmware version (%u.%u) is predates our first public release.",
+			 buffer[0], buffer[1]);
+		dev_info(&usb_dev->dev, "Please update to version 0.2 or newer");
+	}
+
+	return ret;
+}
+
+static int atusb_get_and_show_build(struct atusb *atusb)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	char build[ATUSB_BUILD_SIZE + 1];
+	int ret;
+
+	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
+				ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0,
+				build, ATUSB_BUILD_SIZE, 1000);
+	if (ret >= 0) {
+		build[ret] = 0;
+		dev_info(&usb_dev->dev, "Firmware: build %s\n", build);
+	}
+
+	return ret;
+}
+
+static int atusb_get_and_show_chip(struct atusb *atusb)
+{
+	struct usb_device *usb_dev = atusb->usb_dev;
+	uint8_t man_id_0, man_id_1, part_num, version_num;
+
+	man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0);
+	man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1);
+	part_num = atusb_read_reg(atusb, RG_PART_NUM);
+	version_num = atusb_read_reg(atusb, RG_VERSION_NUM);
+
+	if (atusb->err)
+		return atusb->err;
+
+	if ((man_id_1 << 8 | man_id_0) != ATUSB_JEDEC_ATMEL) {
+		dev_err(&usb_dev->dev,
+			"non-Atmel transceiver xxxx%02x%02x\n",
+			man_id_1, man_id_0);
+		goto fail;
+	}
+	if (part_num != 3 && part_num != 2) {
+		dev_err(&usb_dev->dev,
+			"unexpected transceiver, part 0x%02x version 0x%02x\n",
+			part_num, version_num);
+		goto fail;
+	}
+
+	dev_info(&usb_dev->dev, "ATUSB: AT86RF231 version %d\n", version_num);
+
+	return 0;
+
+fail:
+	atusb->err = -ENODEV;
+	return -ENODEV;
+}
+
+/* ----- Setup ------------------------------------------------------------- */
+
+static int atusb_probe(struct usb_interface *interface,
+		       const struct usb_device_id *id)
+{
+	struct usb_device *usb_dev = interface_to_usbdev(interface);
+	struct ieee802154_hw *hw;
+	struct atusb *atusb = NULL;
+	int ret = -ENOMEM;
+
+	hw = ieee802154_alloc_hw(sizeof(struct atusb), &atusb_ops);
+	if (!hw)
+		return -ENOMEM;
+
+	atusb = hw->priv;
+	atusb->hw = hw;
+	atusb->usb_dev = usb_get_dev(usb_dev);
+	usb_set_intfdata(interface, atusb);
+
+	atusb->shutdown = 0;
+	atusb->err = 0;
+	INIT_DELAYED_WORK(&atusb->work, atusb_work_urbs);
+	init_usb_anchor(&atusb->idle_urbs);
+	init_usb_anchor(&atusb->rx_urbs);
+
+	if (atusb_alloc_urbs(atusb, ATUSB_NUM_RX_URBS))
+		goto fail;
+
+	atusb->tx_dr.bRequestType = ATUSB_REQ_TO_DEV;
+	atusb->tx_dr.bRequest = ATUSB_TX;
+	atusb->tx_dr.wValue = cpu_to_le16(0);
+
+	atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!atusb->tx_urb)
+		goto fail;
+
+	hw->parent = &usb_dev->dev;
+	hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT |
+		    IEEE802154_HW_PROMISCUOUS;
+
+	hw->phy->flags = WPAN_PHY_FLAG_TXPOWER;
+
+	hw->phy->current_page = 0;
+	hw->phy->current_channel = 11;	/* reset default */
+	hw->phy->supported.channels[0] = 0x7FFF800;
+	hw->phy->supported.tx_powers = atusb_powers;
+	hw->phy->supported.tx_powers_size = ARRAY_SIZE(atusb_powers);
+	hw->phy->transmit_power = hw->phy->supported.tx_powers[0];
+	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
+
+	atusb_command(atusb, ATUSB_RF_RESET, 0);
+	atusb_get_and_show_chip(atusb);
+	atusb_get_and_show_revision(atusb);
+	atusb_get_and_show_build(atusb);
+	ret = atusb_get_and_clear_error(atusb);
+	if (ret) {
+		dev_err(&atusb->usb_dev->dev,
+			"%s: initialization failed, error = %d\n",
+			__func__, ret);
+		goto fail;
+	}
+
+	ret = ieee802154_register_hw(hw);
+	if (ret)
+		goto fail;
+
+	/* If we just powered on, we're now in P_ON and need to enter TRX_OFF
+	 * explicitly. Any resets after that will send us straight to TRX_OFF,
+	 * making the command below redundant.
+	 */
+	atusb_write_reg(atusb, RG_TRX_STATE, STATE_FORCE_TRX_OFF);
+	msleep(1);	/* reset => TRX_OFF, tTR13 = 37 us */
+
+#if 0
+	/* Calculating the maximum time available to empty the frame buffer
+	 * on reception:
+	 *
+	 * According to [1], the inter-frame gap is
+	 * R * 20 * 16 us + 128 us
+	 * where R is a random number from 0 to 7. Furthermore, we have 20 bit
+	 * times (80 us at 250 kbps) of SHR of the next frame before the
+	 * transceiver begins storing data in the frame buffer.
+	 *
+	 * This yields a minimum time of 208 us between the last data of a
+	 * frame and the first data of the next frame. This time is further
+	 * reduced by interrupt latency in the atusb firmware.
+	 *
+	 * atusb currently needs about 500 us to retrieve a maximum-sized
+	 * frame. We therefore have to allow reception of a new frame to begin
+	 * while we retrieve the previous frame.
+	 *
+	 * [1] "JN-AN-1035 Calculating data rates in an IEEE 802.15.4-based
+	 *      network", Jennic 2006.
+	 *     http://www.jennic.com/download_file.php?supportFile=JN-AN-1035%20Calculating%20802-15-4%20Data%20Rates-1v0.pdf
+	 */
+
+	atusb_write_subreg(atusb, SR_RX_SAFE_MODE, 1);
+#endif
+	atusb_write_reg(atusb, RG_IRQ_MASK, 0xff);
+
+	ret = atusb_get_and_clear_error(atusb);
+	if (!ret)
+		return 0;
+
+	dev_err(&atusb->usb_dev->dev,
+		"%s: setup failed, error = %d\n",
+		__func__, ret);
+
+	ieee802154_unregister_hw(hw);
+fail:
+	atusb_free_urbs(atusb);
+	usb_kill_urb(atusb->tx_urb);
+	usb_free_urb(atusb->tx_urb);
+	usb_put_dev(usb_dev);
+	ieee802154_free_hw(hw);
+	return ret;
+}
+
+static void atusb_disconnect(struct usb_interface *interface)
+{
+	struct atusb *atusb = usb_get_intfdata(interface);
+
+	dev_dbg(&atusb->usb_dev->dev, "atusb_disconnect\n");
+
+	atusb->shutdown = 1;
+	cancel_delayed_work_sync(&atusb->work);
+
+	usb_kill_anchored_urbs(&atusb->rx_urbs);
+	atusb_free_urbs(atusb);
+	usb_kill_urb(atusb->tx_urb);
+	usb_free_urb(atusb->tx_urb);
+
+	ieee802154_unregister_hw(atusb->hw);
+
+	ieee802154_free_hw(atusb->hw);
+
+	usb_set_intfdata(interface, NULL);
+	usb_put_dev(atusb->usb_dev);
+
+	pr_debug("atusb_disconnect done\n");
+}
+
+/* The devices we work with */
+static const struct usb_device_id atusb_device_table[] = {
+	{
+		.match_flags		= USB_DEVICE_ID_MATCH_DEVICE |
+					  USB_DEVICE_ID_MATCH_INT_INFO,
+		.idVendor		= ATUSB_VENDOR_ID,
+		.idProduct		= ATUSB_PRODUCT_ID,
+		.bInterfaceClass	= USB_CLASS_VENDOR_SPEC
+	},
+	/* end with null element */
+	{}
+};
+MODULE_DEVICE_TABLE(usb, atusb_device_table);
+
+static struct usb_driver atusb_driver = {
+	.name		= "atusb",
+	.probe		= atusb_probe,
+	.disconnect	= atusb_disconnect,
+	.id_table	= atusb_device_table,
+};
+module_usb_driver(atusb_driver);
+
+MODULE_AUTHOR("Alexander Aring <alex.aring@gmail.com>");
+MODULE_AUTHOR("Richard Sharpe <realrichardsharpe@gmail.com>");
+MODULE_AUTHOR("Stefan Schmidt <stefan@datenfreihafen.org>");
+MODULE_AUTHOR("Werner Almesberger <werner@almesberger.net>");
+MODULE_DESCRIPTION("ATUSB IEEE 802.15.4 Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ieee802154/atusb.h b/drivers/net/ieee802154/atusb.h
new file mode 100644
index 000000000000..0690edcad57b
--- /dev/null
+++ b/drivers/net/ieee802154/atusb.h
@@ -0,0 +1,84 @@
+/*
+ * atusb.h - Definitions shared between kernel and ATUSB firmware
+ *
+ * Written 2013 by Werner Almesberger <werner@almesberger.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2, or
+ * (at your option) any later version.
+ *
+ * This file should be identical for kernel and firmware.
+ * Kernel: drivers/net/ieee802154/atusb.h
+ * Firmware: ben-wpan/atusb/fw/include/atusb/atusb.h
+ */
+
+#ifndef _ATUSB_H
+#define _ATUSB_H
+
+#define ATUSB_VENDOR_ID	0x20b7	/* Qi Hardware*/
+#define ATUSB_PRODUCT_ID 0x1540	/* 802.15.4, device 0 */
+				/*     -- -         - */
+
+#define ATUSB_BUILD_SIZE 256	/* maximum build version/date message length */
+
+/* Commands to our device. Make sure this is synced with the firmware */
+enum atusb_requests {
+	ATUSB_ID			= 0x00,	/* system status/control grp */
+	ATUSB_BUILD,
+	ATUSB_RESET,
+	ATUSB_RF_RESET			= 0x10,	/* debug/test group */
+	ATUSB_POLL_INT,
+	ATUSB_TEST,			/* atusb-sil only */
+	ATUSB_TIMER,
+	ATUSB_GPIO,
+	ATUSB_SLP_TR,
+	ATUSB_GPIO_CLEANUP,
+	ATUSB_REG_WRITE			= 0x20,	/* transceiver group */
+	ATUSB_REG_READ,
+	ATUSB_BUF_WRITE,
+	ATUSB_BUF_READ,
+	ATUSB_SRAM_WRITE,
+	ATUSB_SRAM_READ,
+	ATUSB_SPI_WRITE			= 0x30,	/* SPI group */
+	ATUSB_SPI_READ1,
+	ATUSB_SPI_READ2,
+	ATUSB_SPI_WRITE2_SYNC,
+	ATUSB_RX_MODE			= 0x40, /* HardMAC group */
+	ATUSB_TX,
+};
+
+/* Direction	bRequest		wValue		wIndex	wLength
+ *
+ * ->host	ATUSB_ID		-		-	3
+ * ->host	ATUSB_BUILD		-		-	#bytes
+ * host->	ATUSB_RESET		-		-	0
+ *
+ * host->	ATUSB_RF_RESET		-		-	0
+ * ->host	ATUSB_POLL_INT		-		-	1
+ * host->	ATUSB_TEST		-		-	0
+ * ->host	ATUSB_TIMER		-		-	#bytes (6)
+ * ->host	ATUSB_GPIO		dir+data	mask+p#	3
+ * host->	ATUSB_SLP_TR		-		-	0
+ * host->	ATUSB_GPIO_CLEANUP	-		-	0
+ *
+ * host->	ATUSB_REG_WRITE		value		addr	0
+ * ->host	ATUSB_REG_READ		-		addr	1
+ * host->	ATUSB_BUF_WRITE		-		-	#bytes
+ * ->host	ATUSB_BUF_READ		-		-	#bytes
+ * host->	ATUSB_SRAM_WRITE	-		addr	#bytes
+ * ->host	ATUSB_SRAM_READ		-		addr	#bytes
+ *
+ * host->	ATUSB_SPI_WRITE		byte0		byte1	#bytes
+ * ->host	ATUSB_SPI_READ1		byte0		-	#bytes
+ * ->host	ATUSB_SPI_READ2		byte0		byte1	#bytes
+ * ->host	ATUSB_SPI_WRITE2_SYNC	byte0		byte1	0/1
+ *
+ * host->	ATUSB_RX_MODE		on		-	0
+ * host->	ATUSB_TX		flags		ack_seq	#bytes
+ */
+
+#define ATUSB_REQ_FROM_DEV	(USB_TYPE_VENDOR | USB_DIR_IN)
+#define ATUSB_REQ_TO_DEV	(USB_TYPE_VENDOR | USB_DIR_OUT)
+
+#endif /* !_ATUSB_H */
diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c
index f833b8bb6663..b6fc29579667 100644
--- a/drivers/net/ieee802154/cc2520.c
+++ b/drivers/net/ieee802154/cc2520.c
@@ -196,6 +196,7 @@ struct cc2520_private {
 	u8 *buf;			/* SPI TX/Rx data buffer */
 	struct mutex buffer_mutex;	/* SPI buffer mutex */
 	bool is_tx;			/* Flag for sync b/w Tx and Rx */
+	bool amplified;			/* Flag for CC2591 */
 	int fifo_pin;			/* FIFO GPIO pin number */
 	struct work_struct fifop_irqwork;/* Workqueue for FIFOP */
 	spinlock_t lock;		/* Lock for is_tx*/
@@ -589,22 +590,23 @@ cc2520_filter(struct ieee802154_hw *hw,
 	      struct ieee802154_hw_addr_filt *filt, unsigned long changed)
 {
 	struct cc2520_private *priv = hw->priv;
+	int ret = 0;
 
 	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 panid = le16_to_cpu(filt->pan_id);
 
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for pan id\n");
-		cc2520_write_ram(priv, CC2520RAM_PANID,
-				 sizeof(panid), (u8 *)&panid);
+		ret = cc2520_write_ram(priv, CC2520RAM_PANID,
+				       sizeof(panid), (u8 *)&panid);
 	}
 
 	if (changed & IEEE802154_AFILT_IEEEADDR_CHANGED) {
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for IEEE addr\n");
-		cc2520_write_ram(priv, CC2520RAM_IEEEADDR,
-				 sizeof(filt->ieee_addr),
-				 (u8 *)&filt->ieee_addr);
+		ret = cc2520_write_ram(priv, CC2520RAM_IEEEADDR,
+				       sizeof(filt->ieee_addr),
+				       (u8 *)&filt->ieee_addr);
 	}
 
 	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
@@ -612,20 +614,113 @@ cc2520_filter(struct ieee802154_hw *hw,
 
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for saddr\n");
-		cc2520_write_ram(priv, CC2520RAM_SHORTADDR,
-				 sizeof(addr), (u8 *)&addr);
+		ret = cc2520_write_ram(priv, CC2520RAM_SHORTADDR,
+				       sizeof(addr), (u8 *)&addr);
 	}
 
 	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
 		dev_vdbg(&priv->spi->dev,
 			 "cc2520_filter called for panc change\n");
 		if (filt->pan_coord)
-			cc2520_write_register(priv, CC2520_FRMFILT0, 0x02);
+			ret = cc2520_write_register(priv, CC2520_FRMFILT0,
+						    0x02);
 		else
-			cc2520_write_register(priv, CC2520_FRMFILT0, 0x00);
+			ret = cc2520_write_register(priv, CC2520_FRMFILT0,
+						    0x00);
 	}
 
-	return 0;
+	return ret;
+}
+
+static inline int cc2520_set_tx_power(struct cc2520_private *priv, s32 mbm)
+{
+	u8 power;
+
+	switch (mbm) {
+	case 500:
+		power = 0xF7;
+		break;
+	case 300:
+		power = 0xF2;
+		break;
+	case 200:
+		power = 0xAB;
+		break;
+	case 100:
+		power = 0x13;
+		break;
+	case 0:
+		power = 0x32;
+		break;
+	case -200:
+		power = 0x81;
+		break;
+	case -400:
+		power = 0x88;
+		break;
+	case -700:
+		power = 0x2C;
+		break;
+	case -1800:
+		power = 0x03;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc2520_write_register(priv, CC2520_TXPOWER, power);
+}
+
+static inline int cc2520_cc2591_set_tx_power(struct cc2520_private *priv,
+					     s32 mbm)
+{
+	u8 power;
+
+	switch (mbm) {
+	case 1700:
+		power = 0xF9;
+		break;
+	case 1600:
+		power = 0xF0;
+		break;
+	case 1400:
+		power = 0xA0;
+		break;
+	case 1100:
+		power = 0x2C;
+		break;
+	case -100:
+		power = 0x03;
+		break;
+	case -800:
+		power = 0x01;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return cc2520_write_register(priv, CC2520_TXPOWER, power);
+}
+
+#define CC2520_MAX_TX_POWERS 0x8
+static const s32 cc2520_powers[CC2520_MAX_TX_POWERS + 1] = {
+	500, 300, 200, 100, 0, -200, -400, -700, -1800,
+};
+
+#define CC2520_CC2591_MAX_TX_POWERS 0x5
+static const s32 cc2520_cc2591_powers[CC2520_CC2591_MAX_TX_POWERS + 1] = {
+	1700, 1600, 1400, 1100, -100, -800,
+};
+
+static int
+cc2520_set_txpower(struct ieee802154_hw *hw, s32 mbm)
+{
+	struct cc2520_private *priv = hw->priv;
+
+	if (!priv->amplified)
+		return cc2520_set_tx_power(priv, mbm);
+
+	return cc2520_cc2591_set_tx_power(priv, mbm);
 }
 
 static const struct ieee802154_ops cc2520_ops = {
@@ -636,6 +731,7 @@ static const struct ieee802154_ops cc2520_ops = {
 	.ed = cc2520_ed,
 	.set_channel = cc2520_set_channel,
 	.set_hw_addr_filt = cc2520_filter,
+	.set_txpower = cc2520_set_txpower,
 };
 
 static int cc2520_register(struct cc2520_private *priv)
@@ -649,13 +745,25 @@ static int cc2520_register(struct cc2520_private *priv)
 	priv->hw->priv = priv;
 	priv->hw->parent = &priv->spi->dev;
 	priv->hw->extra_tx_headroom = 0;
-	priv->hw->vif_data_size = sizeof(*priv);
 	ieee802154_random_extended_addr(&priv->hw->phy->perm_extended_addr);
 
 	/* We do support only 2.4 Ghz */
-	priv->hw->phy->channels_supported[0] = 0x7FFF800;
-	priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
-			  IEEE802154_HW_AFILT;
+	priv->hw->phy->supported.channels[0] = 0x7FFF800;
+	priv->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AFILT;
+
+	priv->hw->phy->flags = WPAN_PHY_FLAG_TXPOWER;
+
+	if (!priv->amplified) {
+		priv->hw->phy->supported.tx_powers = cc2520_powers;
+		priv->hw->phy->supported.tx_powers_size = ARRAY_SIZE(cc2520_powers);
+		priv->hw->phy->transmit_power = priv->hw->phy->supported.tx_powers[4];
+	} else {
+		priv->hw->phy->supported.tx_powers = cc2520_cc2591_powers;
+		priv->hw->phy->supported.tx_powers_size = ARRAY_SIZE(cc2520_cc2591_powers);
+		priv->hw->phy->transmit_power = priv->hw->phy->supported.tx_powers[0];
+	}
+
+	priv->hw->phy->current_channel = 11;
 
 	dev_vdbg(&priv->spi->dev, "registered cc2520\n");
 	ret = ieee802154_register_hw(priv->hw);
@@ -738,7 +846,9 @@ static int cc2520_get_platform_data(struct spi_device *spi,
 	pdata->vreg = of_get_named_gpio(np, "vreg-gpio", 0);
 	pdata->reset = of_get_named_gpio(np, "reset-gpio", 0);
 
-	pdata->amplified = of_property_read_bool(np, "amplified");
+	/* CC2591 front end for CC2520 */
+	if (of_property_read_bool(np, "amplified"))
+		priv->amplified = true;
 
 	return 0;
 }
@@ -781,11 +891,7 @@ static int cc2520_hw_init(struct cc2520_private *priv)
 	 * amplifier. See section 8 page 17 of TI application note AN065.
 	 * http://www.ti.com/lit/an/swra229a/swra229a.pdf
 	 */
-	if (pdata.amplified) {
-		ret = cc2520_write_register(priv, CC2520_TXPOWER, 0xF9);
-		if (ret)
-			goto err_ret;
-
+	if (priv->amplified) {
 		ret = cc2520_write_register(priv, CC2520_AGCCTRL1, 0x16);
 		if (ret)
 			goto err_ret;
@@ -806,10 +912,6 @@ static int cc2520_hw_init(struct cc2520_private *priv)
 		if (ret)
 			goto err_ret;
 	} else {
-		ret = cc2520_write_register(priv, CC2520_TXPOWER, 0xF7);
-		if (ret)
-			goto err_ret;
-
 		ret = cc2520_write_register(priv, CC2520_AGCCTRL1, 0x11);
 		if (ret)
 			goto err_ret;
@@ -904,6 +1006,9 @@ static int cc2520_probe(struct spi_device *spi)
 	spin_lock_init(&priv->lock);
 	init_completion(&priv->tx_complete);
 
+	/* Assumption that CC2591 is not connected */
+	priv->amplified = false;
+
 	/* Request all the gpio's */
 	if (!gpio_is_valid(pdata.fifo)) {
 		dev_err(&spi->dev, "fifo gpio is not valid\n");
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index dc2bfb600b4b..860d4aed8274 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -27,25 +27,27 @@
 #include <net/mac802154.h>
 #include <net/cfg802154.h>
 
-static int numlbs = 1;
+static int numlbs = 2;
 
-struct fakelb_dev_priv {
+static LIST_HEAD(fakelb_phys);
+static DEFINE_SPINLOCK(fakelb_phys_lock);
+
+static LIST_HEAD(fakelb_ifup_phys);
+static DEFINE_RWLOCK(fakelb_ifup_phys_lock);
+
+struct fakelb_phy {
 	struct ieee802154_hw *hw;
 
-	struct list_head list;
-	struct fakelb_priv *fake;
+	u8 page;
+	u8 channel;
 
-	spinlock_t lock;
-	bool working;
-};
+	bool suspended;
 
-struct fakelb_priv {
 	struct list_head list;
-	rwlock_t lock;
+	struct list_head list_ifup;
 };
 
-static int
-fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
+static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 {
 	BUG_ON(!level);
 	*level = 0xbe;
@@ -53,78 +55,66 @@ fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 	return 0;
 }
 
-static int
-fakelb_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+static int fakelb_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 {
-	pr_debug("set channel to %d\n", channel);
+	struct fakelb_phy *phy = hw->priv;
 
+	write_lock_bh(&fakelb_ifup_phys_lock);
+	phy->page = page;
+	phy->channel = channel;
+	write_unlock_bh(&fakelb_ifup_phys_lock);
 	return 0;
 }
 
-static void
-fakelb_hw_deliver(struct fakelb_dev_priv *priv, struct sk_buff *skb)
+static int fakelb_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 {
-	struct sk_buff *newskb;
+	struct fakelb_phy *current_phy = hw->priv, *phy;
 
-	spin_lock(&priv->lock);
-	if (priv->working) {
-		newskb = pskb_copy(skb, GFP_ATOMIC);
-		ieee802154_rx_irqsafe(priv->hw, newskb, 0xcc);
-	}
-	spin_unlock(&priv->lock);
-}
+	read_lock_bh(&fakelb_ifup_phys_lock);
+	WARN_ON(current_phy->suspended);
+	list_for_each_entry(phy, &fakelb_ifup_phys, list_ifup) {
+		if (current_phy == phy)
+			continue;
 
-static int
-fakelb_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
-{
-	struct fakelb_dev_priv *priv = hw->priv;
-	struct fakelb_priv *fake = priv->fake;
-
-	read_lock_bh(&fake->lock);
-	if (priv->list.next == priv->list.prev) {
-		/* we are the only one device */
-		fakelb_hw_deliver(priv, skb);
-	} else {
-		struct fakelb_dev_priv *dp;
-		list_for_each_entry(dp, &priv->fake->list, list) {
-			if (dp != priv &&
-			    (dp->hw->phy->current_channel ==
-			     priv->hw->phy->current_channel))
-				fakelb_hw_deliver(dp, skb);
+		if (current_phy->page == phy->page &&
+		    current_phy->channel == phy->channel) {
+			struct sk_buff *newskb = pskb_copy(skb, GFP_ATOMIC);
+
+			if (newskb)
+				ieee802154_rx_irqsafe(phy->hw, newskb, 0xcc);
 		}
 	}
-	read_unlock_bh(&fake->lock);
+	read_unlock_bh(&fakelb_ifup_phys_lock);
 
+	ieee802154_xmit_complete(hw, skb, false);
 	return 0;
 }
 
-static int
-fakelb_hw_start(struct ieee802154_hw *hw) {
-	struct fakelb_dev_priv *priv = hw->priv;
-	int ret = 0;
+static int fakelb_hw_start(struct ieee802154_hw *hw)
+{
+	struct fakelb_phy *phy = hw->priv;
 
-	spin_lock(&priv->lock);
-	if (priv->working)
-		ret = -EBUSY;
-	else
-		priv->working = 1;
-	spin_unlock(&priv->lock);
+	write_lock_bh(&fakelb_ifup_phys_lock);
+	phy->suspended = false;
+	list_add(&phy->list_ifup, &fakelb_ifup_phys);
+	write_unlock_bh(&fakelb_ifup_phys_lock);
 
-	return ret;
+	return 0;
 }
 
-static void
-fakelb_hw_stop(struct ieee802154_hw *hw) {
-	struct fakelb_dev_priv *priv = hw->priv;
+static void fakelb_hw_stop(struct ieee802154_hw *hw)
+{
+	struct fakelb_phy *phy = hw->priv;
 
-	spin_lock(&priv->lock);
-	priv->working = 0;
-	spin_unlock(&priv->lock);
+	write_lock_bh(&fakelb_ifup_phys_lock);
+	phy->suspended = true;
+	list_del(&phy->list_ifup);
+	write_unlock_bh(&fakelb_ifup_phys_lock);
 }
 
 static const struct ieee802154_ops fakelb_ops = {
 	.owner = THIS_MODULE,
-	.xmit_sync = fakelb_hw_xmit,
+	.xmit_async = fakelb_hw_xmit,
 	.ed = fakelb_hw_ed,
 	.set_channel = fakelb_hw_channel,
 	.start = fakelb_hw_start,
@@ -135,54 +125,54 @@ static const struct ieee802154_ops fakelb_ops = {
 module_param(numlbs, int, 0);
 MODULE_PARM_DESC(numlbs, " number of pseudo devices");
 
-static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake)
+static int fakelb_add_one(struct device *dev)
 {
-	struct fakelb_dev_priv *priv;
-	int err;
 	struct ieee802154_hw *hw;
+	struct fakelb_phy *phy;
+	int err;
 
-	hw = ieee802154_alloc_hw(sizeof(*priv), &fakelb_ops);
+	hw = ieee802154_alloc_hw(sizeof(*phy), &fakelb_ops);
 	if (!hw)
 		return -ENOMEM;
 
-	priv = hw->priv;
-	priv->hw = hw;
+	phy = hw->priv;
+	phy->hw = hw;
 
 	/* 868 MHz BPSK	802.15.4-2003 */
-	hw->phy->channels_supported[0] |= 1;
+	hw->phy->supported.channels[0] |= 1;
 	/* 915 MHz BPSK	802.15.4-2003 */
-	hw->phy->channels_supported[0] |= 0x7fe;
+	hw->phy->supported.channels[0] |= 0x7fe;
 	/* 2.4 GHz O-QPSK 802.15.4-2003 */
-	hw->phy->channels_supported[0] |= 0x7FFF800;
+	hw->phy->supported.channels[0] |= 0x7FFF800;
 	/* 868 MHz ASK 802.15.4-2006 */
-	hw->phy->channels_supported[1] |= 1;
+	hw->phy->supported.channels[1] |= 1;
 	/* 915 MHz ASK 802.15.4-2006 */
-	hw->phy->channels_supported[1] |= 0x7fe;
+	hw->phy->supported.channels[1] |= 0x7fe;
 	/* 868 MHz O-QPSK 802.15.4-2006 */
-	hw->phy->channels_supported[2] |= 1;
+	hw->phy->supported.channels[2] |= 1;
 	/* 915 MHz O-QPSK 802.15.4-2006 */
-	hw->phy->channels_supported[2] |= 0x7fe;
+	hw->phy->supported.channels[2] |= 0x7fe;
 	/* 2.4 GHz CSS 802.15.4a-2007 */
-	hw->phy->channels_supported[3] |= 0x3fff;
+	hw->phy->supported.channels[3] |= 0x3fff;
 	/* UWB Sub-gigahertz 802.15.4a-2007 */
-	hw->phy->channels_supported[4] |= 1;
+	hw->phy->supported.channels[4] |= 1;
 	/* UWB Low band 802.15.4a-2007 */
-	hw->phy->channels_supported[4] |= 0x1e;
+	hw->phy->supported.channels[4] |= 0x1e;
 	/* UWB High band 802.15.4a-2007 */
-	hw->phy->channels_supported[4] |= 0xffe0;
+	hw->phy->supported.channels[4] |= 0xffe0;
 	/* 750 MHz O-QPSK 802.15.4c-2009 */
-	hw->phy->channels_supported[5] |= 0xf;
+	hw->phy->supported.channels[5] |= 0xf;
 	/* 750 MHz MPSK 802.15.4c-2009 */
-	hw->phy->channels_supported[5] |= 0xf0;
+	hw->phy->supported.channels[5] |= 0xf0;
 	/* 950 MHz BPSK 802.15.4d-2009 */
-	hw->phy->channels_supported[6] |= 0x3ff;
+	hw->phy->supported.channels[6] |= 0x3ff;
 	/* 950 MHz GFSK 802.15.4d-2009 */
-	hw->phy->channels_supported[6] |= 0x3ffc00;
+	hw->phy->supported.channels[6] |= 0x3ffc00;
 
-	INIT_LIST_HEAD(&priv->list);
-	priv->fake = fake;
-
-	spin_lock_init(&priv->lock);
+	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
+	/* fake phy channel 13 as default */
+	hw->phy->current_channel = 13;
+	phy->channel = hw->phy->current_channel;
 
 	hw->parent = dev;
 
@@ -190,67 +180,55 @@ static int fakelb_add_one(struct device *dev, struct fakelb_priv *fake)
 	if (err)
 		goto err_reg;
 
-	write_lock_bh(&fake->lock);
-	list_add_tail(&priv->list, &fake->list);
-	write_unlock_bh(&fake->lock);
+	spin_lock(&fakelb_phys_lock);
+	list_add_tail(&phy->list, &fakelb_phys);
+	spin_unlock(&fakelb_phys_lock);
 
 	return 0;
 
 err_reg:
-	ieee802154_free_hw(priv->hw);
+	ieee802154_free_hw(phy->hw);
 	return err;
 }
 
-static void fakelb_del(struct fakelb_dev_priv *priv)
+static void fakelb_del(struct fakelb_phy *phy)
 {
-	write_lock_bh(&priv->fake->lock);
-	list_del(&priv->list);
-	write_unlock_bh(&priv->fake->lock);
+	list_del(&phy->list);
 
-	ieee802154_unregister_hw(priv->hw);
-	ieee802154_free_hw(priv->hw);
+	ieee802154_unregister_hw(phy->hw);
+	ieee802154_free_hw(phy->hw);
 }
 
 static int fakelb_probe(struct platform_device *pdev)
 {
-	struct fakelb_priv *priv;
-	struct fakelb_dev_priv *dp;
-	int err = -ENOMEM;
-	int i;
-
-	priv = devm_kzalloc(&pdev->dev, sizeof(struct fakelb_priv),
-			    GFP_KERNEL);
-	if (!priv)
-		goto err_alloc;
-
-	INIT_LIST_HEAD(&priv->list);
-	rwlock_init(&priv->lock);
+	struct fakelb_phy *phy, *tmp;
+	int err, i;
 
 	for (i = 0; i < numlbs; i++) {
-		err = fakelb_add_one(&pdev->dev, priv);
+		err = fakelb_add_one(&pdev->dev);
 		if (err < 0)
 			goto err_slave;
 	}
 
-	platform_set_drvdata(pdev, priv);
 	dev_info(&pdev->dev, "added ieee802154 hardware\n");
 	return 0;
 
 err_slave:
-	list_for_each_entry(dp, &priv->list, list)
-		fakelb_del(dp);
-err_alloc:
+	spin_lock(&fakelb_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &fakelb_phys, list)
+		fakelb_del(phy);
+	spin_unlock(&fakelb_phys_lock);
 	return err;
 }
 
 static int fakelb_remove(struct platform_device *pdev)
 {
-	struct fakelb_priv *priv = platform_get_drvdata(pdev);
-	struct fakelb_dev_priv *dp, *temp;
-
-	list_for_each_entry_safe(dp, temp, &priv->list, list)
-		fakelb_del(dp);
+	struct fakelb_phy *phy, *tmp;
 
+	spin_lock(&fakelb_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &fakelb_phys, list)
+		fakelb_del(phy);
+	spin_unlock(&fakelb_phys_lock);
 	return 0;
 }
 
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index fba2dfd910f7..2549760e039f 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -533,6 +533,7 @@ static int mrf24j40_handle_rx(struct mrf24j40 *devrec)
 	u8 lqi = 0;
 	u8 val;
 	int ret = 0;
+	int ret2;
 	struct sk_buff *skb;
 
 	/* Turn off reception of packets off the air. This prevents the
@@ -569,9 +570,9 @@ static int mrf24j40_handle_rx(struct mrf24j40 *devrec)
 
 out:
 	/* Turn back on reception of packets off the air. */
-	ret = read_short_reg(devrec, REG_BBREG1, &val);
-	if (ret)
-		return ret;
+	ret2 = read_short_reg(devrec, REG_BBREG1, &val);
+	if (ret2)
+		return ret2;
 	val &= ~0x4; /* Clear RXDECINV */
 	write_short_reg(devrec, REG_BBREG1, val);
 
@@ -750,9 +751,8 @@ static int mrf24j40_probe(struct spi_device *spi)
 
 	devrec->hw->priv = devrec;
 	devrec->hw->parent = &devrec->spi->dev;
-	devrec->hw->phy->channels_supported[0] = CHANNEL_MASK;
-	devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK |
-			    IEEE802154_HW_AFILT;
+	devrec->hw->phy->supported.channels[0] = CHANNEL_MASK;
+	devrec->hw->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AFILT;
 
 	dev_dbg(printdev(devrec), "registered mrf24j40\n");
 	ret = ieee802154_register_hw(devrec->hw);
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 54549a6223dd..953a97492fab 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -39,6 +39,8 @@
 #define IPVLAN_MAC_FILTER_SIZE	(1 << IPVLAN_MAC_FILTER_BITS)
 #define IPVLAN_MAC_FILTER_MASK	(IPVLAN_MAC_FILTER_SIZE - 1)
 
+#define IPVLAN_QBACKLOG_LIMIT	1000
+
 typedef enum {
 	IPVL_IPV6 = 0,
 	IPVL_ICMPV6,
@@ -93,6 +95,8 @@ struct ipvl_port {
 	struct hlist_head	hlhead[IPVLAN_HASH_SIZE];
 	struct list_head	ipvlans;
 	struct rcu_head		rcu;
+	struct work_struct	wq;
+	struct sk_buff_head	backlog;
 	int			count;
 	u16			mode;
 };
@@ -112,6 +116,7 @@ void ipvlan_set_port_mode(struct ipvl_port *port, u32 nval);
 void ipvlan_init_secret(void);
 unsigned int ipvlan_mac_hash(const unsigned char *addr);
 rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb);
+void ipvlan_process_multicast(struct work_struct *work);
 int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev);
 void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr);
 struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index c30b5c300c05..8afbedad620d 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -189,62 +189,69 @@ unsigned int ipvlan_mac_hash(const unsigned char *addr)
 	return hash & IPVLAN_MAC_FILTER_MASK;
 }
 
-static void ipvlan_multicast_frame(struct ipvl_port *port, struct sk_buff *skb,
-				   const struct ipvl_dev *in_dev, bool local)
+void ipvlan_process_multicast(struct work_struct *work)
 {
-	struct ethhdr *eth = eth_hdr(skb);
+	struct ipvl_port *port = container_of(work, struct ipvl_port, wq);
+	struct ethhdr *ethh;
 	struct ipvl_dev *ipvlan;
-	struct sk_buff *nskb;
+	struct sk_buff *skb, *nskb;
+	struct sk_buff_head list;
 	unsigned int len;
 	unsigned int mac_hash;
 	int ret;
+	u8 pkt_type;
+	bool hlocal, dlocal;
 
-	if (skb->protocol == htons(ETH_P_PAUSE))
-		return;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
-		if (local && (ipvlan == in_dev))
-			continue;
+	__skb_queue_head_init(&list);
 
-		mac_hash = ipvlan_mac_hash(eth->h_dest);
-		if (!test_bit(mac_hash, ipvlan->mac_filters))
-			continue;
+	spin_lock_bh(&port->backlog.lock);
+	skb_queue_splice_tail_init(&port->backlog, &list);
+	spin_unlock_bh(&port->backlog.lock);
 
-		ret = NET_RX_DROP;
-		len = skb->len + ETH_HLEN;
-		nskb = skb_clone(skb, GFP_ATOMIC);
-		if (!nskb)
-			goto mcast_acct;
+	while ((skb = __skb_dequeue(&list)) != NULL) {
+		ethh = eth_hdr(skb);
+		hlocal = ether_addr_equal(ethh->h_source, port->dev->dev_addr);
+		mac_hash = ipvlan_mac_hash(ethh->h_dest);
 
-		if (ether_addr_equal(eth->h_dest, ipvlan->phy_dev->broadcast))
-			nskb->pkt_type = PACKET_BROADCAST;
+		if (ether_addr_equal(ethh->h_dest, port->dev->broadcast))
+			pkt_type = PACKET_BROADCAST;
 		else
-			nskb->pkt_type = PACKET_MULTICAST;
-
-		nskb->dev = ipvlan->dev;
-		if (local)
-			ret = dev_forward_skb(ipvlan->dev, nskb);
-		else
-			ret = netif_rx(nskb);
-mcast_acct:
-		ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
-	}
-	rcu_read_unlock();
-
-	/* Locally generated? ...Forward a copy to the main-device as
-	 * well. On the RX side we'll ignore it (wont give it to any
-	 * of the virtual devices.
-	 */
-	if (local) {
-		nskb = skb_clone(skb, GFP_ATOMIC);
-		if (nskb) {
-			if (ether_addr_equal(eth->h_dest, port->dev->broadcast))
-				nskb->pkt_type = PACKET_BROADCAST;
+			pkt_type = PACKET_MULTICAST;
+
+		dlocal = false;
+		rcu_read_lock();
+		list_for_each_entry_rcu(ipvlan, &port->ipvlans, pnode) {
+			if (hlocal && (ipvlan->dev == skb->dev)) {
+				dlocal = true;
+				continue;
+			}
+			if (!test_bit(mac_hash, ipvlan->mac_filters))
+				continue;
+
+			ret = NET_RX_DROP;
+			len = skb->len + ETH_HLEN;
+			nskb = skb_clone(skb, GFP_ATOMIC);
+			if (!nskb)
+				goto acct;
+
+			nskb->pkt_type = pkt_type;
+			nskb->dev = ipvlan->dev;
+			if (hlocal)
+				ret = dev_forward_skb(ipvlan->dev, nskb);
 			else
-				nskb->pkt_type = PACKET_MULTICAST;
-
-			dev_forward_skb(port->dev, nskb);
+				ret = netif_rx(nskb);
+acct:
+			ipvlan_count_rx(ipvlan, len, ret == NET_RX_SUCCESS, true);
+		}
+		rcu_read_unlock();
+
+		if (dlocal) {
+			/* If the packet originated here, send it out. */
+			skb->dev = port->dev;
+			skb->pkt_type = pkt_type;
+			dev_queue_xmit(skb);
+		} else {
+			kfree_skb(skb);
 		}
 	}
 }
@@ -446,6 +453,26 @@ out:
 	return ret;
 }
 
+static void ipvlan_multicast_enqueue(struct ipvl_port *port,
+				     struct sk_buff *skb)
+{
+	if (skb->protocol == htons(ETH_P_PAUSE)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	spin_lock(&port->backlog.lock);
+	if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) {
+		__skb_queue_tail(&port->backlog, skb);
+		spin_unlock(&port->backlog.lock);
+		schedule_work(&port->wq);
+	} else {
+		spin_unlock(&port->backlog.lock);
+		atomic_long_inc(&skb->dev->rx_dropped);
+		kfree_skb(skb);
+	}
+}
+
 static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct ipvl_dev *ipvlan = netdev_priv(dev);
@@ -493,11 +520,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
 		return dev_forward_skb(ipvlan->phy_dev, skb);
 
 	} else if (is_multicast_ether_addr(eth->h_dest)) {
-		u8 ip_summed = skb->ip_summed;
-
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		ipvlan_multicast_frame(ipvlan->port, skb, ipvlan, true);
-		skb->ip_summed = ip_summed;
+		ipvlan_multicast_enqueue(ipvlan->port, skb);
+		return NET_XMIT_SUCCESS;
 	}
 
 	skb->dev = ipvlan->phy_dev;
@@ -581,8 +605,18 @@ static rx_handler_result_t ipvlan_handle_mode_l2(struct sk_buff **pskb,
 	int addr_type;
 
 	if (is_multicast_ether_addr(eth->h_dest)) {
-		if (ipvlan_external_frame(skb, port))
-			ipvlan_multicast_frame(port, skb, NULL, false);
+		if (ipvlan_external_frame(skb, port)) {
+			struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+			/* External frames are queued for device local
+			 * distribution, but a copy is given to master
+			 * straight away to avoid sending duplicates later
+			 * when work-queue processes this frame. This is
+			 * achieved by returning RX_HANDLER_PASS.
+			 */
+			if (nskb)
+				ipvlan_multicast_enqueue(port, nskb);
+		}
 	} else {
 		struct ipvl_addr *addr;
 
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 77b92a0fe557..1acc283160d9 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -54,6 +54,9 @@ static int ipvlan_port_create(struct net_device *dev)
 	for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++)
 		INIT_HLIST_HEAD(&port->hlhead[idx]);
 
+	skb_queue_head_init(&port->backlog);
+	INIT_WORK(&port->wq, ipvlan_process_multicast);
+
 	err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port);
 	if (err)
 		goto err;
@@ -72,6 +75,8 @@ static void ipvlan_port_destroy(struct net_device *dev)
 
 	dev->priv_flags &= ~IFF_IPVLAN_MASTER;
 	netdev_rx_handler_unregister(dev);
+	cancel_work_sync(&port->wq);
+	__skb_queue_purge(&port->backlog);
 	kfree_rcu(port, rcu);
 }
 
@@ -213,17 +218,6 @@ static void ipvlan_change_rx_flags(struct net_device *dev, int change)
 		dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1);
 }
 
-static void ipvlan_set_broadcast_mac_filter(struct ipvl_dev *ipvlan, bool set)
-{
-	struct net_device *dev = ipvlan->dev;
-	unsigned int hashbit = ipvlan_mac_hash(dev->broadcast);
-
-	if (set && !test_bit(hashbit, ipvlan->mac_filters))
-		__set_bit(hashbit, ipvlan->mac_filters);
-	else if (!set && test_bit(hashbit, ipvlan->mac_filters))
-		__clear_bit(hashbit, ipvlan->mac_filters);
-}
-
 static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
@@ -238,6 +232,12 @@ static void ipvlan_set_multicast_mac_filter(struct net_device *dev)
 		netdev_for_each_mc_addr(ha, dev)
 			__set_bit(ipvlan_mac_hash(ha->addr), mc_filters);
 
+		/* Turn-on broadcast bit irrespective of address family,
+		 * since broadcast is deferred to a work-queue, hence no
+		 * impact on fast-path processing.
+		 */
+		__set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters);
+
 		bitmap_copy(ipvlan->mac_filters, mc_filters,
 			    IPVLAN_MAC_FILTER_SIZE);
 	}
@@ -705,7 +705,6 @@ static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
 	 */
 	if (netif_running(ipvlan->dev))
 		ipvlan_ht_addr_add(ipvlan, addr);
-	ipvlan_set_broadcast_mac_filter(ipvlan, true);
 
 	return 0;
 }
@@ -722,8 +721,6 @@ static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr)
 	list_del(&addr->anode);
 	ipvlan->ipv4cnt--;
 	WARN_ON(ipvlan->ipv4cnt < 0);
-	if (!ipvlan->ipv4cnt)
-	    ipvlan_set_broadcast_mac_filter(ipvlan, false);
 	kfree_rcu(addr, rcu);
 
 	return;
diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c
index f6c916312577..25f21968fa5c 100644
--- a/drivers/net/irda/irda-usb.c
+++ b/drivers/net/irda/irda-usb.c
@@ -848,7 +848,9 @@ static void irda_usb_receive(struct urb *urb)
 		 * Jean II */
 		self->rx_defer_timer.function = irda_usb_rx_defer_expired;
 		self->rx_defer_timer.data = (unsigned long) urb;
-		mod_timer(&self->rx_defer_timer, jiffies + (10 * HZ / 1000));
+		mod_timer(&self->rx_defer_timer,
+			  jiffies + msecs_to_jiffies(10));
+
 		return;
 	}
 	
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b227a13f6473..9f59f17dc317 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -599,10 +599,18 @@ static int macvlan_open(struct net_device *dev)
 			goto del_unicast;
 	}
 
+	if (dev->flags & IFF_PROMISC) {
+		err = dev_set_promiscuity(lowerdev, 1);
+		if (err < 0)
+			goto clear_multi;
+	}
+
 hash_add:
 	macvlan_hash_add(vlan);
 	return 0;
 
+clear_multi:
+	dev_set_allmulti(lowerdev, -1);
 del_unicast:
 	dev_uc_del(lowerdev, dev->dev_addr);
 out:
@@ -638,6 +646,9 @@ static int macvlan_stop(struct net_device *dev)
 	if (dev->flags & IFF_ALLMULTI)
 		dev_set_allmulti(lowerdev, -1);
 
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(lowerdev, -1);
+
 	dev_uc_del(lowerdev, dev->dev_addr);
 
 hash_del:
@@ -696,6 +707,10 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	if (dev->flags & IFF_UP) {
 		if (change & IFF_ALLMULTI)
 			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+		if (change & IFF_PROMISC)
+			dev_set_promiscuity(lowerdev,
+					    dev->flags & IFF_PROMISC ? 1 : -1);
+
 	}
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 8c350c5d54ad..6a64197f5bce 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -263,27 +263,21 @@ out:
 static void macvtap_del_queues(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
-	struct macvtap_queue *q, *tmp, *qlist[MAX_MACVTAP_QUEUES];
-	int i, j = 0;
+	struct macvtap_queue *q, *tmp;
 
 	ASSERT_RTNL();
 	list_for_each_entry_safe(q, tmp, &vlan->queue_list, next) {
 		list_del_init(&q->next);
-		qlist[j++] = q;
 		RCU_INIT_POINTER(q->vlan, NULL);
 		if (q->enabled)
 			vlan->numvtaps--;
 		vlan->numqueues--;
+		sock_put(&q->sk);
 	}
-	for (i = 0; i < vlan->numvtaps; i++)
-		RCU_INIT_POINTER(vlan->taps[i], NULL);
 	BUG_ON(vlan->numvtaps);
 	BUG_ON(vlan->numqueues);
 	/* guarantee that any future macvtap_set_queue will fail */
 	vlan->numvtaps = MAX_MACVTAP_QUEUES;
-
-	for (--j; j >= 0; j--)
-		sock_put(&qlist[j]->sk);
 }
 
 static rx_handler_result_t macvtap_handle_frame(struct sk_buff **pskb)
@@ -476,7 +470,7 @@ static int macvtap_open(struct inode *inode, struct file *file)
 
 	err = -ENOMEM;
 	q = (struct macvtap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
-					     &macvtap_proto);
+					     &macvtap_proto, 0);
 	if (!q)
 		goto out;
 
@@ -1006,6 +1000,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 	unsigned int __user *up = argp;
 	unsigned short u;
 	int __user *sp = argp;
+	struct sockaddr sa;
 	int s;
 	int ret;
 
@@ -1101,6 +1096,37 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 		rtnl_unlock();
 		return ret;
 
+	case SIOCGIFHWADDR:
+		rtnl_lock();
+		vlan = macvtap_get_vlan(q);
+		if (!vlan) {
+			rtnl_unlock();
+			return -ENOLINK;
+		}
+		ret = 0;
+		u = vlan->dev->type;
+		if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) ||
+		    copy_to_user(&ifr->ifr_hwaddr.sa_data, vlan->dev->dev_addr, ETH_ALEN) ||
+		    put_user(u, &ifr->ifr_hwaddr.sa_family))
+			ret = -EFAULT;
+		macvtap_put_vlan(vlan);
+		rtnl_unlock();
+		return ret;
+
+	case SIOCSIFHWADDR:
+		if (copy_from_user(&sa, &ifr->ifr_hwaddr, sizeof(sa)))
+			return -EFAULT;
+		rtnl_lock();
+		vlan = macvtap_get_vlan(q);
+		if (!vlan) {
+			rtnl_unlock();
+			return -ENOLINK;
+		}
+		ret = dev_set_mac_address(vlan->dev, &sa);
+		macvtap_put_vlan(vlan);
+		rtnl_unlock();
+		return ret;
+
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 8fadaa14b9f0..cf18940f4e84 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -24,12 +24,6 @@ config AMD_PHY
 	---help---
 	  Currently supports the am79c874
 
-config AMD_XGBE_PHY
-	tristate "Driver for the AMD 10GbE (amd-xgbe) PHYs"
-	depends on (OF || ACPI) && HAS_IOMEM
-	---help---
-	  Currently supports the AMD 10GbE PHY
-
 config MARVELL_PHY
 	tristate "Drivers for Marvell PHYs"
 	---help---
@@ -118,6 +112,11 @@ config MICREL_PHY
 	---help---
 	  Supports the KSZ9021, VSC8201, KS8001 PHYs.
 
+config DP83867_PHY
+	tristate "Drivers for Texas Instruments DP83867 Gigabit PHY"
+	---help---
+	  Currently supports the DP83867 PHY.
+
 config FIXED_PHY
 	tristate "Driver for MDIO Bus/PHY emulation with fixed speed/link PHYs"
 	depends on PHYLIB
@@ -211,7 +210,6 @@ config MDIO_BCM_UNIMAC
 	  This hardware can be found in the Broadcom GENET Ethernet MAC
 	  controllers as well as some Broadcom Ethernet switches such as the
 	  Starfighter 2 switches.
-
 endif # PHYLIB
 
 config MICREL_KS8995MA
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 501ea7699a2d..fcc25a0c45cd 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO_BITBANG)	+= mdio-bitbang.o
 obj-$(CONFIG_MDIO_GPIO)		+= mdio-gpio.o
 obj-$(CONFIG_NATIONAL_PHY)	+= national.o
 obj-$(CONFIG_DP83640_PHY)	+= dp83640.o
+obj-$(CONFIG_DP83867_PHY)	+= dp83867.o
 obj-$(CONFIG_STE10XP)		+= ste10Xp.o
 obj-$(CONFIG_MICREL_PHY)	+= micrel.o
 obj-$(CONFIG_MDIO_OCTEON)	+= mdio-octeon.o
@@ -33,5 +34,4 @@ obj-$(CONFIG_MDIO_BUS_MUX_GPIO)	+= mdio-mux-gpio.o
 obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o
 obj-$(CONFIG_MDIO_SUN4I)	+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_MOXART)	+= mdio-moxart.o
-obj-$(CONFIG_AMD_XGBE_PHY)	+= amd-xgbe-phy.o
 obj-$(CONFIG_MDIO_BCM_UNIMAC)	+= mdio-bcm-unimac.o
diff --git a/drivers/net/phy/amd-xgbe-phy.c b/drivers/net/phy/amd-xgbe-phy.c
deleted file mode 100644
index fb276f64cd64..000000000000
--- a/drivers/net/phy/amd-xgbe-phy.c
+++ /dev/null
@@ -1,1862 +0,0 @@
-/*
- * AMD 10Gb Ethernet PHY driver
- *
- * This file is available to you under your choice of the following two
- * licenses:
- *
- * License 1: GPLv2
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- *
- * This file is free software; you may copy, redistribute and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 2 of the License, or (at
- * your option) any later version.
- *
- * This file is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- *
- * License 2: Modified BSD
- *
- * Copyright (c) 2014 Advanced Micro Devices, Inc.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Advanced Micro Devices, Inc. nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/errno.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/workqueue.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/mii.h>
-#include <linux/ethtool.h>
-#include <linux/phy.h>
-#include <linux/mdio.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_platform.h>
-#include <linux/of_device.h>
-#include <linux/uaccess.h>
-#include <linux/bitops.h>
-#include <linux/property.h>
-#include <linux/acpi.h>
-#include <linux/jiffies.h>
-
-MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>");
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION("1.0.0-a");
-MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver");
-
-#define XGBE_PHY_ID	0x000162d0
-#define XGBE_PHY_MASK	0xfffffff0
-
-#define XGBE_PHY_SPEEDSET_PROPERTY	"amd,speed-set"
-#define XGBE_PHY_BLWC_PROPERTY		"amd,serdes-blwc"
-#define XGBE_PHY_CDR_RATE_PROPERTY	"amd,serdes-cdr-rate"
-#define XGBE_PHY_PQ_SKEW_PROPERTY	"amd,serdes-pq-skew"
-#define XGBE_PHY_TX_AMP_PROPERTY	"amd,serdes-tx-amp"
-#define XGBE_PHY_DFE_CFG_PROPERTY	"amd,serdes-dfe-tap-config"
-#define XGBE_PHY_DFE_ENA_PROPERTY	"amd,serdes-dfe-tap-enable"
-
-#define XGBE_PHY_SPEEDS			3
-#define XGBE_PHY_SPEED_1000		0
-#define XGBE_PHY_SPEED_2500		1
-#define XGBE_PHY_SPEED_10000		2
-
-#define XGBE_AN_MS_TIMEOUT		500
-
-#define XGBE_AN_INT_CMPLT		0x01
-#define XGBE_AN_INC_LINK		0x02
-#define XGBE_AN_PG_RCV			0x04
-#define XGBE_AN_INT_MASK		0x07
-
-#define XNP_MCF_NULL_MESSAGE		0x001
-#define XNP_ACK_PROCESSED		BIT(12)
-#define XNP_MP_FORMATTED		BIT(13)
-#define XNP_NP_EXCHANGE			BIT(15)
-
-#define XGBE_PHY_RATECHANGE_COUNT	500
-
-#define XGBE_PHY_KR_TRAINING_START	0x01
-#define XGBE_PHY_KR_TRAINING_ENABLE	0x02
-
-#define XGBE_PHY_FEC_ENABLE		0x01
-#define XGBE_PHY_FEC_FORWARD		0x02
-#define XGBE_PHY_FEC_MASK		0x03
-
-#ifndef MDIO_PMA_10GBR_PMD_CTRL
-#define MDIO_PMA_10GBR_PMD_CTRL		0x0096
-#endif
-
-#ifndef MDIO_PMA_10GBR_FEC_ABILITY
-#define MDIO_PMA_10GBR_FEC_ABILITY	0x00aa
-#endif
-
-#ifndef MDIO_PMA_10GBR_FEC_CTRL
-#define MDIO_PMA_10GBR_FEC_CTRL		0x00ab
-#endif
-
-#ifndef MDIO_AN_XNP
-#define MDIO_AN_XNP			0x0016
-#endif
-
-#ifndef MDIO_AN_LPX
-#define MDIO_AN_LPX			0x0019
-#endif
-
-#ifndef MDIO_AN_INTMASK
-#define MDIO_AN_INTMASK			0x8001
-#endif
-
-#ifndef MDIO_AN_INT
-#define MDIO_AN_INT			0x8002
-#endif
-
-#ifndef MDIO_CTRL1_SPEED1G
-#define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
-#endif
-
-/* SerDes integration register offsets */
-#define SIR0_KR_RT_1			0x002c
-#define SIR0_STATUS			0x0040
-#define SIR1_SPEED			0x0000
-
-/* SerDes integration register entry bit positions and sizes */
-#define SIR0_KR_RT_1_RESET_INDEX	11
-#define SIR0_KR_RT_1_RESET_WIDTH	1
-#define SIR0_STATUS_RX_READY_INDEX	0
-#define SIR0_STATUS_RX_READY_WIDTH	1
-#define SIR0_STATUS_TX_READY_INDEX	8
-#define SIR0_STATUS_TX_READY_WIDTH	1
-#define SIR1_SPEED_CDR_RATE_INDEX	12
-#define SIR1_SPEED_CDR_RATE_WIDTH	4
-#define SIR1_SPEED_DATARATE_INDEX	4
-#define SIR1_SPEED_DATARATE_WIDTH	2
-#define SIR1_SPEED_PLLSEL_INDEX		3
-#define SIR1_SPEED_PLLSEL_WIDTH		1
-#define SIR1_SPEED_RATECHANGE_INDEX	6
-#define SIR1_SPEED_RATECHANGE_WIDTH	1
-#define SIR1_SPEED_TXAMP_INDEX		8
-#define SIR1_SPEED_TXAMP_WIDTH		4
-#define SIR1_SPEED_WORDMODE_INDEX	0
-#define SIR1_SPEED_WORDMODE_WIDTH	3
-
-#define SPEED_10000_BLWC		0
-#define SPEED_10000_CDR			0x7
-#define SPEED_10000_PLL			0x1
-#define SPEED_10000_PQ			0x12
-#define SPEED_10000_RATE		0x0
-#define SPEED_10000_TXAMP		0xa
-#define SPEED_10000_WORD		0x7
-#define SPEED_10000_DFE_TAP_CONFIG	0x1
-#define SPEED_10000_DFE_TAP_ENABLE	0x7f
-
-#define SPEED_2500_BLWC			1
-#define SPEED_2500_CDR			0x2
-#define SPEED_2500_PLL			0x0
-#define SPEED_2500_PQ			0xa
-#define SPEED_2500_RATE			0x1
-#define SPEED_2500_TXAMP		0xf
-#define SPEED_2500_WORD			0x1
-#define SPEED_2500_DFE_TAP_CONFIG	0x3
-#define SPEED_2500_DFE_TAP_ENABLE	0x0
-
-#define SPEED_1000_BLWC			1
-#define SPEED_1000_CDR			0x2
-#define SPEED_1000_PLL			0x0
-#define SPEED_1000_PQ			0xa
-#define SPEED_1000_RATE			0x3
-#define SPEED_1000_TXAMP		0xf
-#define SPEED_1000_WORD			0x1
-#define SPEED_1000_DFE_TAP_CONFIG	0x3
-#define SPEED_1000_DFE_TAP_ENABLE	0x0
-
-/* SerDes RxTx register offsets */
-#define RXTX_REG6			0x0018
-#define RXTX_REG20			0x0050
-#define RXTX_REG22			0x0058
-#define RXTX_REG114			0x01c8
-#define RXTX_REG129			0x0204
-
-/* SerDes RxTx register entry bit positions and sizes */
-#define RXTX_REG6_RESETB_RXD_INDEX	8
-#define RXTX_REG6_RESETB_RXD_WIDTH	1
-#define RXTX_REG20_BLWC_ENA_INDEX	2
-#define RXTX_REG20_BLWC_ENA_WIDTH	1
-#define RXTX_REG114_PQ_REG_INDEX	9
-#define RXTX_REG114_PQ_REG_WIDTH	7
-#define RXTX_REG129_RXDFE_CONFIG_INDEX	14
-#define RXTX_REG129_RXDFE_CONFIG_WIDTH	2
-
-/* Bit setting and getting macros
- *  The get macro will extract the current bit field value from within
- *  the variable
- *
- *  The set macro will clear the current bit field value within the
- *  variable and then set the bit field of the variable to the
- *  specified value
- */
-#define GET_BITS(_var, _index, _width)					\
-	(((_var) >> (_index)) & ((0x1 << (_width)) - 1))
-
-#define SET_BITS(_var, _index, _width, _val)				\
-do {									\
-	(_var) &= ~(((0x1 << (_width)) - 1) << (_index));		\
-	(_var) |= (((_val) & ((0x1 << (_width)) - 1)) << (_index));	\
-} while (0)
-
-#define XSIR_GET_BITS(_var, _prefix, _field)				\
-	GET_BITS((_var),						\
-		 _prefix##_##_field##_INDEX,				\
-		 _prefix##_##_field##_WIDTH)
-
-#define XSIR_SET_BITS(_var, _prefix, _field, _val)			\
-	SET_BITS((_var),						\
-		 _prefix##_##_field##_INDEX,				\
-		 _prefix##_##_field##_WIDTH, (_val))
-
-/* Macros for reading or writing SerDes integration registers
- *  The ioread macros will get bit fields or full values using the
- *  register definitions formed using the input names
- *
- *  The iowrite macros will set bit fields or full values using the
- *  register definitions formed using the input names
- */
-#define XSIR0_IOREAD(_priv, _reg)					\
-	ioread16((_priv)->sir0_regs + _reg)
-
-#define XSIR0_IOREAD_BITS(_priv, _reg, _field)				\
-	GET_BITS(XSIR0_IOREAD((_priv), _reg),				\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH)
-
-#define XSIR0_IOWRITE(_priv, _reg, _val)				\
-	iowrite16((_val), (_priv)->sir0_regs + _reg)
-
-#define XSIR0_IOWRITE_BITS(_priv, _reg, _field, _val)			\
-do {									\
-	u16 reg_val = XSIR0_IOREAD((_priv), _reg);			\
-	SET_BITS(reg_val,						\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH, (_val));			\
-	XSIR0_IOWRITE((_priv), _reg, reg_val);				\
-} while (0)
-
-#define XSIR1_IOREAD(_priv, _reg)					\
-	ioread16((_priv)->sir1_regs + _reg)
-
-#define XSIR1_IOREAD_BITS(_priv, _reg, _field)				\
-	GET_BITS(XSIR1_IOREAD((_priv), _reg),				\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH)
-
-#define XSIR1_IOWRITE(_priv, _reg, _val)				\
-	iowrite16((_val), (_priv)->sir1_regs + _reg)
-
-#define XSIR1_IOWRITE_BITS(_priv, _reg, _field, _val)			\
-do {									\
-	u16 reg_val = XSIR1_IOREAD((_priv), _reg);			\
-	SET_BITS(reg_val,						\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH, (_val));			\
-	XSIR1_IOWRITE((_priv), _reg, reg_val);				\
-} while (0)
-
-/* Macros for reading or writing SerDes RxTx registers
- *  The ioread macros will get bit fields or full values using the
- *  register definitions formed using the input names
- *
- *  The iowrite macros will set bit fields or full values using the
- *  register definitions formed using the input names
- */
-#define XRXTX_IOREAD(_priv, _reg)					\
-	ioread16((_priv)->rxtx_regs + _reg)
-
-#define XRXTX_IOREAD_BITS(_priv, _reg, _field)				\
-	GET_BITS(XRXTX_IOREAD((_priv), _reg),				\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH)
-
-#define XRXTX_IOWRITE(_priv, _reg, _val)				\
-	iowrite16((_val), (_priv)->rxtx_regs + _reg)
-
-#define XRXTX_IOWRITE_BITS(_priv, _reg, _field, _val)			\
-do {									\
-	u16 reg_val = XRXTX_IOREAD((_priv), _reg);			\
-	SET_BITS(reg_val,						\
-		 _reg##_##_field##_INDEX,				\
-		 _reg##_##_field##_WIDTH, (_val));			\
-	XRXTX_IOWRITE((_priv), _reg, reg_val);				\
-} while (0)
-
-static const u32 amd_xgbe_phy_serdes_blwc[] = {
-	SPEED_1000_BLWC,
-	SPEED_2500_BLWC,
-	SPEED_10000_BLWC,
-};
-
-static const u32 amd_xgbe_phy_serdes_cdr_rate[] = {
-	SPEED_1000_CDR,
-	SPEED_2500_CDR,
-	SPEED_10000_CDR,
-};
-
-static const u32 amd_xgbe_phy_serdes_pq_skew[] = {
-	SPEED_1000_PQ,
-	SPEED_2500_PQ,
-	SPEED_10000_PQ,
-};
-
-static const u32 amd_xgbe_phy_serdes_tx_amp[] = {
-	SPEED_1000_TXAMP,
-	SPEED_2500_TXAMP,
-	SPEED_10000_TXAMP,
-};
-
-static const u32 amd_xgbe_phy_serdes_dfe_tap_cfg[] = {
-	SPEED_1000_DFE_TAP_CONFIG,
-	SPEED_2500_DFE_TAP_CONFIG,
-	SPEED_10000_DFE_TAP_CONFIG,
-};
-
-static const u32 amd_xgbe_phy_serdes_dfe_tap_ena[] = {
-	SPEED_1000_DFE_TAP_ENABLE,
-	SPEED_2500_DFE_TAP_ENABLE,
-	SPEED_10000_DFE_TAP_ENABLE,
-};
-
-enum amd_xgbe_phy_an {
-	AMD_XGBE_AN_READY = 0,
-	AMD_XGBE_AN_PAGE_RECEIVED,
-	AMD_XGBE_AN_INCOMPAT_LINK,
-	AMD_XGBE_AN_COMPLETE,
-	AMD_XGBE_AN_NO_LINK,
-	AMD_XGBE_AN_ERROR,
-};
-
-enum amd_xgbe_phy_rx {
-	AMD_XGBE_RX_BPA = 0,
-	AMD_XGBE_RX_XNP,
-	AMD_XGBE_RX_COMPLETE,
-	AMD_XGBE_RX_ERROR,
-};
-
-enum amd_xgbe_phy_mode {
-	AMD_XGBE_MODE_KR,
-	AMD_XGBE_MODE_KX,
-};
-
-enum amd_xgbe_phy_speedset {
-	AMD_XGBE_PHY_SPEEDSET_1000_10000 = 0,
-	AMD_XGBE_PHY_SPEEDSET_2500_10000,
-};
-
-struct amd_xgbe_phy_priv {
-	struct platform_device *pdev;
-	struct acpi_device *adev;
-	struct device *dev;
-
-	struct phy_device *phydev;
-
-	/* SerDes related mmio resources */
-	struct resource *rxtx_res;
-	struct resource *sir0_res;
-	struct resource *sir1_res;
-
-	/* SerDes related mmio registers */
-	void __iomem *rxtx_regs;	/* SerDes Rx/Tx CSRs */
-	void __iomem *sir0_regs;	/* SerDes integration registers (1/2) */
-	void __iomem *sir1_regs;	/* SerDes integration registers (2/2) */
-
-	int an_irq;
-	char an_irq_name[IFNAMSIZ + 32];
-	struct work_struct an_irq_work;
-	unsigned int an_irq_allocated;
-
-	unsigned int speed_set;
-
-	/* SerDes UEFI configurable settings.
-	 *   Switching between modes/speeds requires new values for some
-	 *   SerDes settings.  The values can be supplied as device
-	 *   properties in array format.  The first array entry is for
-	 *   1GbE, second for 2.5GbE and third for 10GbE
-	 */
-	u32 serdes_blwc[XGBE_PHY_SPEEDS];
-	u32 serdes_cdr_rate[XGBE_PHY_SPEEDS];
-	u32 serdes_pq_skew[XGBE_PHY_SPEEDS];
-	u32 serdes_tx_amp[XGBE_PHY_SPEEDS];
-	u32 serdes_dfe_tap_cfg[XGBE_PHY_SPEEDS];
-	u32 serdes_dfe_tap_ena[XGBE_PHY_SPEEDS];
-
-	/* Auto-negotiation state machine support */
-	struct mutex an_mutex;
-	enum amd_xgbe_phy_an an_result;
-	enum amd_xgbe_phy_an an_state;
-	enum amd_xgbe_phy_rx kr_state;
-	enum amd_xgbe_phy_rx kx_state;
-	struct work_struct an_work;
-	struct workqueue_struct *an_workqueue;
-	unsigned int an_supported;
-	unsigned int parallel_detect;
-	unsigned int fec_ability;
-	unsigned long an_start;
-
-	unsigned int lpm_ctrl;		/* CTRL1 for resume */
-};
-
-static int amd_xgbe_an_enable_kr_training(struct phy_device *phydev)
-{
-	int ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
-	if (ret < 0)
-		return ret;
-
-	ret |= XGBE_PHY_KR_TRAINING_ENABLE;
-	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, ret);
-
-	return 0;
-}
-
-static int amd_xgbe_an_disable_kr_training(struct phy_device *phydev)
-{
-	int ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~XGBE_PHY_KR_TRAINING_ENABLE;
-	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, ret);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_pcs_power_cycle(struct phy_device *phydev)
-{
-	int ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret |= MDIO_CTRL1_LPOWER;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	usleep_range(75, 100);
-
-	ret &= ~MDIO_CTRL1_LPOWER;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	return 0;
-}
-
-static void amd_xgbe_phy_serdes_start_ratechange(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-
-	/* Assert Rx and Tx ratechange */
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, RATECHANGE, 1);
-}
-
-static void amd_xgbe_phy_serdes_complete_ratechange(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	unsigned int wait;
-	u16 status;
-
-	/* Release Rx and Tx ratechange */
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, RATECHANGE, 0);
-
-	/* Wait for Rx and Tx ready */
-	wait = XGBE_PHY_RATECHANGE_COUNT;
-	while (wait--) {
-		usleep_range(50, 75);
-
-		status = XSIR0_IOREAD(priv, SIR0_STATUS);
-		if (XSIR_GET_BITS(status, SIR0_STATUS, RX_READY) &&
-		    XSIR_GET_BITS(status, SIR0_STATUS, TX_READY))
-			goto rx_reset;
-	}
-
-	netdev_dbg(phydev->attached_dev, "SerDes rx/tx not ready (%#hx)\n",
-		   status);
-
-rx_reset:
-	/* Perform Rx reset for the DFE changes */
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG6, RESETB_RXD, 0);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG6, RESETB_RXD, 1);
-}
-
-static int amd_xgbe_phy_xgmii_mode(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* Enable KR training */
-	ret = amd_xgbe_an_enable_kr_training(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set PCS to KR/10G speed */
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_PCS_CTRL2_TYPE;
-	ret |= MDIO_PCS_CTRL2_10GBR;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_CTRL1_SPEEDSEL;
-	ret |= MDIO_CTRL1_SPEED10G;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set SerDes to 10G speed */
-	amd_xgbe_phy_serdes_start_ratechange(phydev);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_10000_RATE);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_10000_WORD);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_10000_PLL);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, CDR_RATE,
-			   priv->serdes_cdr_rate[XGBE_PHY_SPEED_10000]);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP,
-			   priv->serdes_tx_amp[XGBE_PHY_SPEED_10000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA,
-			   priv->serdes_blwc[XGBE_PHY_SPEED_10000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG,
-			   priv->serdes_pq_skew[XGBE_PHY_SPEED_10000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG129, RXDFE_CONFIG,
-			   priv->serdes_dfe_tap_cfg[XGBE_PHY_SPEED_10000]);
-	XRXTX_IOWRITE(priv, RXTX_REG22,
-		      priv->serdes_dfe_tap_ena[XGBE_PHY_SPEED_10000]);
-
-	amd_xgbe_phy_serdes_complete_ratechange(phydev);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_gmii_2500_mode(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* Disable KR training */
-	ret = amd_xgbe_an_disable_kr_training(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set PCS to KX/1G speed */
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_PCS_CTRL2_TYPE;
-	ret |= MDIO_PCS_CTRL2_10GBX;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_CTRL1_SPEEDSEL;
-	ret |= MDIO_CTRL1_SPEED1G;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set SerDes to 2.5G speed */
-	amd_xgbe_phy_serdes_start_ratechange(phydev);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_2500_RATE);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_2500_WORD);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_2500_PLL);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, CDR_RATE,
-			   priv->serdes_cdr_rate[XGBE_PHY_SPEED_2500]);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP,
-			   priv->serdes_tx_amp[XGBE_PHY_SPEED_2500]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA,
-			   priv->serdes_blwc[XGBE_PHY_SPEED_2500]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG,
-			   priv->serdes_pq_skew[XGBE_PHY_SPEED_2500]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG129, RXDFE_CONFIG,
-			   priv->serdes_dfe_tap_cfg[XGBE_PHY_SPEED_2500]);
-	XRXTX_IOWRITE(priv, RXTX_REG22,
-		      priv->serdes_dfe_tap_ena[XGBE_PHY_SPEED_2500]);
-
-	amd_xgbe_phy_serdes_complete_ratechange(phydev);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_gmii_mode(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* Disable KR training */
-	ret = amd_xgbe_an_disable_kr_training(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set PCS to KX/1G speed */
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_PCS_CTRL2_TYPE;
-	ret |= MDIO_PCS_CTRL2_10GBX;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_CTRL1_SPEEDSEL;
-	ret |= MDIO_CTRL1_SPEED1G;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Set SerDes to 1G speed */
-	amd_xgbe_phy_serdes_start_ratechange(phydev);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_1000_RATE);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_1000_WORD);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_1000_PLL);
-
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, CDR_RATE,
-			   priv->serdes_cdr_rate[XGBE_PHY_SPEED_1000]);
-	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP,
-			   priv->serdes_tx_amp[XGBE_PHY_SPEED_1000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA,
-			   priv->serdes_blwc[XGBE_PHY_SPEED_1000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG,
-			   priv->serdes_pq_skew[XGBE_PHY_SPEED_1000]);
-	XRXTX_IOWRITE_BITS(priv, RXTX_REG129, RXDFE_CONFIG,
-			   priv->serdes_dfe_tap_cfg[XGBE_PHY_SPEED_1000]);
-	XRXTX_IOWRITE(priv, RXTX_REG22,
-		      priv->serdes_dfe_tap_ena[XGBE_PHY_SPEED_1000]);
-
-	amd_xgbe_phy_serdes_complete_ratechange(phydev);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_cur_mode(struct phy_device *phydev,
-				 enum amd_xgbe_phy_mode *mode)
-{
-	int ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
-	if (ret < 0)
-		return ret;
-
-	if ((ret & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR)
-		*mode = AMD_XGBE_MODE_KR;
-	else
-		*mode = AMD_XGBE_MODE_KX;
-
-	return 0;
-}
-
-static bool amd_xgbe_phy_in_kr_mode(struct phy_device *phydev)
-{
-	enum amd_xgbe_phy_mode mode;
-
-	if (amd_xgbe_phy_cur_mode(phydev, &mode))
-		return false;
-
-	return (mode == AMD_XGBE_MODE_KR);
-}
-
-static int amd_xgbe_phy_switch_mode(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* If we are in KR switch to KX, and vice-versa */
-	if (amd_xgbe_phy_in_kr_mode(phydev)) {
-		if (priv->speed_set == AMD_XGBE_PHY_SPEEDSET_1000_10000)
-			ret = amd_xgbe_phy_gmii_mode(phydev);
-		else
-			ret = amd_xgbe_phy_gmii_2500_mode(phydev);
-	} else {
-		ret = amd_xgbe_phy_xgmii_mode(phydev);
-	}
-
-	return ret;
-}
-
-static int amd_xgbe_phy_set_mode(struct phy_device *phydev,
-				 enum amd_xgbe_phy_mode mode)
-{
-	enum amd_xgbe_phy_mode cur_mode;
-	int ret;
-
-	ret = amd_xgbe_phy_cur_mode(phydev, &cur_mode);
-	if (ret)
-		return ret;
-
-	if (mode != cur_mode)
-		ret = amd_xgbe_phy_switch_mode(phydev);
-
-	return ret;
-}
-
-static int amd_xgbe_phy_set_an(struct phy_device *phydev, bool enable,
-			       bool restart)
-{
-	int ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret &= ~MDIO_AN_CTRL1_ENABLE;
-
-	if (enable)
-		ret |= MDIO_AN_CTRL1_ENABLE;
-
-	if (restart)
-		ret |= MDIO_AN_CTRL1_RESTART;
-
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, ret);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_restart_an(struct phy_device *phydev)
-{
-	return amd_xgbe_phy_set_an(phydev, true, true);
-}
-
-static int amd_xgbe_phy_disable_an(struct phy_device *phydev)
-{
-	return amd_xgbe_phy_set_an(phydev, false, false);
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_tx_training(struct phy_device *phydev,
-						    enum amd_xgbe_phy_rx *state)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ad_reg, lp_reg, ret;
-
-	*state = AMD_XGBE_RX_COMPLETE;
-
-	/* If we're not in KR mode then we're done */
-	if (!amd_xgbe_phy_in_kr_mode(phydev))
-		return AMD_XGBE_AN_PAGE_RECEIVED;
-
-	/* Enable/Disable FEC */
-	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
-	if (ad_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 2);
-	if (lp_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_CTRL);
-	if (ret < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	ret &= ~XGBE_PHY_FEC_MASK;
-	if ((ad_reg & 0xc000) && (lp_reg & 0xc000))
-		ret |= priv->fec_ability;
-
-	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_CTRL, ret);
-
-	/* Start KR training */
-	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
-	if (ret < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	if (ret & XGBE_PHY_KR_TRAINING_ENABLE) {
-		XSIR0_IOWRITE_BITS(priv, SIR0_KR_RT_1, RESET, 1);
-
-		ret |= XGBE_PHY_KR_TRAINING_START;
-		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL,
-			      ret);
-
-		XSIR0_IOWRITE_BITS(priv, SIR0_KR_RT_1, RESET, 0);
-	}
-
-	return AMD_XGBE_AN_PAGE_RECEIVED;
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_tx_xnp(struct phy_device *phydev,
-					       enum amd_xgbe_phy_rx *state)
-{
-	u16 msg;
-
-	*state = AMD_XGBE_RX_XNP;
-
-	msg = XNP_MCF_NULL_MESSAGE;
-	msg |= XNP_MP_FORMATTED;
-
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP + 2, 0);
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP + 1, 0);
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP, msg);
-
-	return AMD_XGBE_AN_PAGE_RECEIVED;
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_rx_bpa(struct phy_device *phydev,
-					       enum amd_xgbe_phy_rx *state)
-{
-	unsigned int link_support;
-	int ret, ad_reg, lp_reg;
-
-	/* Read Base Ability register 2 first */
-	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 1);
-	if (ret < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	/* Check for a supported mode, otherwise restart in a different one */
-	link_support = amd_xgbe_phy_in_kr_mode(phydev) ? 0x80 : 0x20;
-	if (!(ret & link_support))
-		return AMD_XGBE_AN_INCOMPAT_LINK;
-
-	/* Check Extended Next Page support */
-	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
-	if (ad_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
-	if (lp_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	return ((ad_reg & XNP_NP_EXCHANGE) || (lp_reg & XNP_NP_EXCHANGE)) ?
-	       amd_xgbe_an_tx_xnp(phydev, state) :
-	       amd_xgbe_an_tx_training(phydev, state);
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_rx_xnp(struct phy_device *phydev,
-					       enum amd_xgbe_phy_rx *state)
-{
-	int ad_reg, lp_reg;
-
-	/* Check Extended Next Page support */
-	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP);
-	if (ad_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPX);
-	if (lp_reg < 0)
-		return AMD_XGBE_AN_ERROR;
-
-	return ((ad_reg & XNP_NP_EXCHANGE) || (lp_reg & XNP_NP_EXCHANGE)) ?
-	       amd_xgbe_an_tx_xnp(phydev, state) :
-	       amd_xgbe_an_tx_training(phydev, state);
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_page_received(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	enum amd_xgbe_phy_rx *state;
-	unsigned long an_timeout;
-	int ret;
-
-	if (!priv->an_start) {
-		priv->an_start = jiffies;
-	} else {
-		an_timeout = priv->an_start +
-			     msecs_to_jiffies(XGBE_AN_MS_TIMEOUT);
-		if (time_after(jiffies, an_timeout)) {
-			/* Auto-negotiation timed out, reset state */
-			priv->kr_state = AMD_XGBE_RX_BPA;
-			priv->kx_state = AMD_XGBE_RX_BPA;
-
-			priv->an_start = jiffies;
-		}
-	}
-
-	state = amd_xgbe_phy_in_kr_mode(phydev) ? &priv->kr_state
-						: &priv->kx_state;
-
-	switch (*state) {
-	case AMD_XGBE_RX_BPA:
-		ret = amd_xgbe_an_rx_bpa(phydev, state);
-		break;
-
-	case AMD_XGBE_RX_XNP:
-		ret = amd_xgbe_an_rx_xnp(phydev, state);
-		break;
-
-	default:
-		ret = AMD_XGBE_AN_ERROR;
-	}
-
-	return ret;
-}
-
-static enum amd_xgbe_phy_an amd_xgbe_an_incompat_link(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* Be sure we aren't looping trying to negotiate */
-	if (amd_xgbe_phy_in_kr_mode(phydev)) {
-		priv->kr_state = AMD_XGBE_RX_ERROR;
-
-		if (!(phydev->advertising & SUPPORTED_1000baseKX_Full) &&
-		    !(phydev->advertising & SUPPORTED_2500baseX_Full))
-			return AMD_XGBE_AN_NO_LINK;
-
-		if (priv->kx_state != AMD_XGBE_RX_BPA)
-			return AMD_XGBE_AN_NO_LINK;
-	} else {
-		priv->kx_state = AMD_XGBE_RX_ERROR;
-
-		if (!(phydev->advertising & SUPPORTED_10000baseKR_Full))
-			return AMD_XGBE_AN_NO_LINK;
-
-		if (priv->kr_state != AMD_XGBE_RX_BPA)
-			return AMD_XGBE_AN_NO_LINK;
-	}
-
-	ret = amd_xgbe_phy_disable_an(phydev);
-	if (ret)
-		return AMD_XGBE_AN_ERROR;
-
-	ret = amd_xgbe_phy_switch_mode(phydev);
-	if (ret)
-		return AMD_XGBE_AN_ERROR;
-
-	ret = amd_xgbe_phy_restart_an(phydev);
-	if (ret)
-		return AMD_XGBE_AN_ERROR;
-
-	return AMD_XGBE_AN_INCOMPAT_LINK;
-}
-
-static irqreturn_t amd_xgbe_an_isr(int irq, void *data)
-{
-	struct amd_xgbe_phy_priv *priv = (struct amd_xgbe_phy_priv *)data;
-
-	/* Interrupt reason must be read and cleared outside of IRQ context */
-	disable_irq_nosync(priv->an_irq);
-
-	queue_work(priv->an_workqueue, &priv->an_irq_work);
-
-	return IRQ_HANDLED;
-}
-
-static void amd_xgbe_an_irq_work(struct work_struct *work)
-{
-	struct amd_xgbe_phy_priv *priv = container_of(work,
-						      struct amd_xgbe_phy_priv,
-						      an_irq_work);
-
-	/* Avoid a race between enabling the IRQ and exiting the work by
-	 * waiting for the work to finish and then queueing it
-	 */
-	flush_work(&priv->an_work);
-	queue_work(priv->an_workqueue, &priv->an_work);
-}
-
-static void amd_xgbe_an_state_machine(struct work_struct *work)
-{
-	struct amd_xgbe_phy_priv *priv = container_of(work,
-						      struct amd_xgbe_phy_priv,
-						      an_work);
-	struct phy_device *phydev = priv->phydev;
-	enum amd_xgbe_phy_an cur_state = priv->an_state;
-	int int_reg, int_mask;
-
-	mutex_lock(&priv->an_mutex);
-
-	/* Read the interrupt */
-	int_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT);
-	if (!int_reg)
-		goto out;
-
-next_int:
-	if (int_reg < 0) {
-		priv->an_state = AMD_XGBE_AN_ERROR;
-		int_mask = XGBE_AN_INT_MASK;
-	} else if (int_reg & XGBE_AN_PG_RCV) {
-		priv->an_state = AMD_XGBE_AN_PAGE_RECEIVED;
-		int_mask = XGBE_AN_PG_RCV;
-	} else if (int_reg & XGBE_AN_INC_LINK) {
-		priv->an_state = AMD_XGBE_AN_INCOMPAT_LINK;
-		int_mask = XGBE_AN_INC_LINK;
-	} else if (int_reg & XGBE_AN_INT_CMPLT) {
-		priv->an_state = AMD_XGBE_AN_COMPLETE;
-		int_mask = XGBE_AN_INT_CMPLT;
-	} else {
-		priv->an_state = AMD_XGBE_AN_ERROR;
-		int_mask = 0;
-	}
-
-	/* Clear the interrupt to be processed */
-	int_reg &= ~int_mask;
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, int_reg);
-
-	priv->an_result = priv->an_state;
-
-again:
-	cur_state = priv->an_state;
-
-	switch (priv->an_state) {
-	case AMD_XGBE_AN_READY:
-		priv->an_supported = 0;
-		break;
-
-	case AMD_XGBE_AN_PAGE_RECEIVED:
-		priv->an_state = amd_xgbe_an_page_received(phydev);
-		priv->an_supported++;
-		break;
-
-	case AMD_XGBE_AN_INCOMPAT_LINK:
-		priv->an_supported = 0;
-		priv->parallel_detect = 0;
-		priv->an_state = amd_xgbe_an_incompat_link(phydev);
-		break;
-
-	case AMD_XGBE_AN_COMPLETE:
-		priv->parallel_detect = priv->an_supported ? 0 : 1;
-		netdev_dbg(phydev->attached_dev, "%s successful\n",
-			   priv->an_supported ? "Auto negotiation"
-					      : "Parallel detection");
-		break;
-
-	case AMD_XGBE_AN_NO_LINK:
-		break;
-
-	default:
-		priv->an_state = AMD_XGBE_AN_ERROR;
-	}
-
-	if (priv->an_state == AMD_XGBE_AN_NO_LINK) {
-		int_reg = 0;
-		phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
-	} else if (priv->an_state == AMD_XGBE_AN_ERROR) {
-		netdev_err(phydev->attached_dev,
-			   "error during auto-negotiation, state=%u\n",
-			   cur_state);
-
-		int_reg = 0;
-		phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
-	}
-
-	if (priv->an_state >= AMD_XGBE_AN_COMPLETE) {
-		priv->an_result = priv->an_state;
-		priv->an_state = AMD_XGBE_AN_READY;
-		priv->kr_state = AMD_XGBE_RX_BPA;
-		priv->kx_state = AMD_XGBE_RX_BPA;
-		priv->an_start = 0;
-	}
-
-	if (cur_state != priv->an_state)
-		goto again;
-
-	if (int_reg)
-		goto next_int;
-
-out:
-	enable_irq(priv->an_irq);
-
-	mutex_unlock(&priv->an_mutex);
-}
-
-static int amd_xgbe_an_init(struct phy_device *phydev)
-{
-	int ret;
-
-	/* Set up Advertisement register 3 first */
-	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
-	if (ret < 0)
-		return ret;
-
-	if (phydev->advertising & SUPPORTED_10000baseR_FEC)
-		ret |= 0xc000;
-	else
-		ret &= ~0xc000;
-
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2, ret);
-
-	/* Set up Advertisement register 2 next */
-	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
-	if (ret < 0)
-		return ret;
-
-	if (phydev->advertising & SUPPORTED_10000baseKR_Full)
-		ret |= 0x80;
-	else
-		ret &= ~0x80;
-
-	if ((phydev->advertising & SUPPORTED_1000baseKX_Full) ||
-	    (phydev->advertising & SUPPORTED_2500baseX_Full))
-		ret |= 0x20;
-	else
-		ret &= ~0x20;
-
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1, ret);
-
-	/* Set up Advertisement register 1 last */
-	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
-	if (ret < 0)
-		return ret;
-
-	if (phydev->advertising & SUPPORTED_Pause)
-		ret |= 0x400;
-	else
-		ret &= ~0x400;
-
-	if (phydev->advertising & SUPPORTED_Asym_Pause)
-		ret |= 0x800;
-	else
-		ret &= ~0x800;
-
-	/* We don't intend to perform XNP */
-	ret &= ~XNP_NP_EXCHANGE;
-
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, ret);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_soft_reset(struct phy_device *phydev)
-{
-	int count, ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	ret |= MDIO_CTRL1_RESET;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	count = 50;
-	do {
-		msleep(20);
-		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-		if (ret < 0)
-			return ret;
-	} while ((ret & MDIO_CTRL1_RESET) && --count);
-
-	if (ret & MDIO_CTRL1_RESET)
-		return -ETIMEDOUT;
-
-	/* Disable auto-negotiation for now */
-	ret = amd_xgbe_phy_disable_an(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Clear auto-negotiation interrupts */
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_config_init(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	struct net_device *netdev = phydev->attached_dev;
-	int ret;
-
-	if (!priv->an_irq_allocated) {
-		/* Allocate the auto-negotiation workqueue and interrupt */
-		snprintf(priv->an_irq_name, sizeof(priv->an_irq_name) - 1,
-			 "%s-pcs", netdev_name(netdev));
-
-		priv->an_workqueue =
-			create_singlethread_workqueue(priv->an_irq_name);
-		if (!priv->an_workqueue) {
-			netdev_err(netdev, "phy workqueue creation failed\n");
-			return -ENOMEM;
-		}
-
-		ret = devm_request_irq(priv->dev, priv->an_irq,
-				       amd_xgbe_an_isr, 0, priv->an_irq_name,
-				       priv);
-		if (ret) {
-			netdev_err(netdev, "phy irq request failed\n");
-			destroy_workqueue(priv->an_workqueue);
-			return ret;
-		}
-
-		priv->an_irq_allocated = 1;
-	}
-
-	/* Set initial mode - call the mode setting routines
-	 * directly to insure we are properly configured
-	 */
-	if (phydev->advertising & SUPPORTED_10000baseKR_Full)
-		ret = amd_xgbe_phy_xgmii_mode(phydev);
-	else if (phydev->advertising & SUPPORTED_1000baseKX_Full)
-		ret = amd_xgbe_phy_gmii_mode(phydev);
-	else if (phydev->advertising & SUPPORTED_2500baseX_Full)
-		ret = amd_xgbe_phy_gmii_2500_mode(phydev);
-	else
-		ret = -EINVAL;
-	if (ret < 0)
-		return ret;
-
-	/* Set up advertisement registers based on current settings */
-	ret = amd_xgbe_an_init(phydev);
-	if (ret)
-		return ret;
-
-	/* Enable auto-negotiation interrupts */
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INTMASK, 0x07);
-
-	return 0;
-}
-
-static int amd_xgbe_phy_setup_forced(struct phy_device *phydev)
-{
-	int ret;
-
-	/* Disable auto-negotiation */
-	ret = amd_xgbe_phy_disable_an(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Validate/Set specified speed */
-	switch (phydev->speed) {
-	case SPEED_10000:
-		ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KR);
-		break;
-
-	case SPEED_2500:
-	case SPEED_1000:
-		ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX);
-		break;
-
-	default:
-		ret = -EINVAL;
-	}
-
-	if (ret < 0)
-		return ret;
-
-	/* Validate duplex mode */
-	if (phydev->duplex != DUPLEX_FULL)
-		return -EINVAL;
-
-	phydev->pause = 0;
-	phydev->asym_pause = 0;
-
-	return 0;
-}
-
-static int __amd_xgbe_phy_config_aneg(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	u32 mmd_mask = phydev->c45_ids.devices_in_package;
-	int ret;
-
-	if (phydev->autoneg != AUTONEG_ENABLE)
-		return amd_xgbe_phy_setup_forced(phydev);
-
-	/* Make sure we have the AN MMD present */
-	if (!(mmd_mask & MDIO_DEVS_AN))
-		return -EINVAL;
-
-	/* Disable auto-negotiation interrupt */
-	disable_irq(priv->an_irq);
-
-	/* Start auto-negotiation in a supported mode */
-	if (phydev->advertising & SUPPORTED_10000baseKR_Full)
-		ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KR);
-	else if ((phydev->advertising & SUPPORTED_1000baseKX_Full) ||
-		 (phydev->advertising & SUPPORTED_2500baseX_Full))
-		ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX);
-	else
-		ret = -EINVAL;
-	if (ret < 0) {
-		enable_irq(priv->an_irq);
-		return ret;
-	}
-
-	/* Disable and stop any in progress auto-negotiation */
-	ret = amd_xgbe_phy_disable_an(phydev);
-	if (ret < 0)
-		return ret;
-
-	/* Clear any auto-negotitation interrupts */
-	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
-
-	priv->an_result = AMD_XGBE_AN_READY;
-	priv->an_state = AMD_XGBE_AN_READY;
-	priv->kr_state = AMD_XGBE_RX_BPA;
-	priv->kx_state = AMD_XGBE_RX_BPA;
-
-	/* Re-enable auto-negotiation interrupt */
-	enable_irq(priv->an_irq);
-
-	/* Set up advertisement registers based on current settings */
-	ret = amd_xgbe_an_init(phydev);
-	if (ret)
-		return ret;
-
-	/* Enable and start auto-negotiation */
-	return amd_xgbe_phy_restart_an(phydev);
-}
-
-static int amd_xgbe_phy_config_aneg(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	mutex_lock(&priv->an_mutex);
-
-	ret = __amd_xgbe_phy_config_aneg(phydev);
-
-	mutex_unlock(&priv->an_mutex);
-
-	return ret;
-}
-
-static int amd_xgbe_phy_aneg_done(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-
-	return (priv->an_result == AMD_XGBE_AN_COMPLETE);
-}
-
-static int amd_xgbe_phy_update_link(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	/* If we're doing auto-negotiation don't report link down */
-	if (priv->an_state != AMD_XGBE_AN_READY) {
-		phydev->link = 1;
-		return 0;
-	}
-
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
-	 */
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1);
-	if (ret < 0)
-		return ret;
-
-	phydev->link = (ret & MDIO_STAT1_LSTATUS) ? 1 : 0;
-
-	return 0;
-}
-
-static int amd_xgbe_phy_read_status(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	u32 mmd_mask = phydev->c45_ids.devices_in_package;
-	int ret, ad_ret, lp_ret;
-
-	ret = amd_xgbe_phy_update_link(phydev);
-	if (ret)
-		return ret;
-
-	if ((phydev->autoneg == AUTONEG_ENABLE) &&
-	    !priv->parallel_detect) {
-		if (!(mmd_mask & MDIO_DEVS_AN))
-			return -EINVAL;
-
-		if (!amd_xgbe_phy_aneg_done(phydev))
-			return 0;
-
-		/* Compare Advertisement and Link Partner register 1 */
-		ad_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
-		if (ad_ret < 0)
-			return ad_ret;
-		lp_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
-		if (lp_ret < 0)
-			return lp_ret;
-
-		ad_ret &= lp_ret;
-		phydev->pause = (ad_ret & 0x400) ? 1 : 0;
-		phydev->asym_pause = (ad_ret & 0x800) ? 1 : 0;
-
-		/* Compare Advertisement and Link Partner register 2 */
-		ad_ret = phy_read_mmd(phydev, MDIO_MMD_AN,
-				      MDIO_AN_ADVERTISE + 1);
-		if (ad_ret < 0)
-			return ad_ret;
-		lp_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 1);
-		if (lp_ret < 0)
-			return lp_ret;
-
-		ad_ret &= lp_ret;
-		if (ad_ret & 0x80) {
-			phydev->speed = SPEED_10000;
-			ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KR);
-			if (ret)
-				return ret;
-		} else {
-			switch (priv->speed_set) {
-			case AMD_XGBE_PHY_SPEEDSET_1000_10000:
-				phydev->speed = SPEED_1000;
-				break;
-
-			case AMD_XGBE_PHY_SPEEDSET_2500_10000:
-				phydev->speed = SPEED_2500;
-				break;
-			}
-
-			ret = amd_xgbe_phy_set_mode(phydev, AMD_XGBE_MODE_KX);
-			if (ret)
-				return ret;
-		}
-
-		phydev->duplex = DUPLEX_FULL;
-	} else {
-		if (amd_xgbe_phy_in_kr_mode(phydev)) {
-			phydev->speed = SPEED_10000;
-		} else {
-			switch (priv->speed_set) {
-			case AMD_XGBE_PHY_SPEEDSET_1000_10000:
-				phydev->speed = SPEED_1000;
-				break;
-
-			case AMD_XGBE_PHY_SPEEDSET_2500_10000:
-				phydev->speed = SPEED_2500;
-				break;
-			}
-		}
-		phydev->duplex = DUPLEX_FULL;
-		phydev->pause = 0;
-		phydev->asym_pause = 0;
-	}
-
-	return 0;
-}
-
-static int amd_xgbe_phy_suspend(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	int ret;
-
-	mutex_lock(&phydev->lock);
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
-	if (ret < 0)
-		goto unlock;
-
-	priv->lpm_ctrl = ret;
-
-	ret |= MDIO_CTRL1_LPOWER;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
-
-	ret = 0;
-
-unlock:
-	mutex_unlock(&phydev->lock);
-
-	return ret;
-}
-
-static int amd_xgbe_phy_resume(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-
-	mutex_lock(&phydev->lock);
-
-	priv->lpm_ctrl &= ~MDIO_CTRL1_LPOWER;
-	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, priv->lpm_ctrl);
-
-	mutex_unlock(&phydev->lock);
-
-	return 0;
-}
-
-static unsigned int amd_xgbe_phy_resource_count(struct platform_device *pdev,
-						unsigned int type)
-{
-	unsigned int count;
-	int i;
-
-	for (i = 0, count = 0; i < pdev->num_resources; i++) {
-		struct resource *r = &pdev->resource[i];
-
-		if (type == resource_type(r))
-			count++;
-	}
-
-	return count;
-}
-
-static int amd_xgbe_phy_probe(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv;
-	struct platform_device *phy_pdev;
-	struct device *dev, *phy_dev;
-	unsigned int phy_resnum, phy_irqnum;
-	int ret;
-
-	if (!phydev->bus || !phydev->bus->parent)
-		return -EINVAL;
-
-	dev = phydev->bus->parent;
-
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->pdev = to_platform_device(dev);
-	priv->adev = ACPI_COMPANION(dev);
-	priv->dev = dev;
-	priv->phydev = phydev;
-	mutex_init(&priv->an_mutex);
-	INIT_WORK(&priv->an_irq_work, amd_xgbe_an_irq_work);
-	INIT_WORK(&priv->an_work, amd_xgbe_an_state_machine);
-
-	if (!priv->adev || acpi_disabled) {
-		struct device_node *bus_node;
-		struct device_node *phy_node;
-
-		bus_node = priv->dev->of_node;
-		phy_node = of_parse_phandle(bus_node, "phy-handle", 0);
-		if (!phy_node) {
-			dev_err(dev, "unable to parse phy-handle\n");
-			ret = -EINVAL;
-			goto err_priv;
-		}
-
-		phy_pdev = of_find_device_by_node(phy_node);
-		of_node_put(phy_node);
-
-		if (!phy_pdev) {
-			dev_err(dev, "unable to obtain phy device\n");
-			ret = -EINVAL;
-			goto err_priv;
-		}
-
-		phy_resnum = 0;
-		phy_irqnum = 0;
-	} else {
-		/* In ACPI, the XGBE and PHY resources are the grouped
-		 * together with the PHY resources at the end
-		 */
-		phy_pdev = priv->pdev;
-		phy_resnum = amd_xgbe_phy_resource_count(phy_pdev,
-							 IORESOURCE_MEM) - 3;
-		phy_irqnum = amd_xgbe_phy_resource_count(phy_pdev,
-							 IORESOURCE_IRQ) - 1;
-	}
-	phy_dev = &phy_pdev->dev;
-
-	/* Get the device mmio areas */
-	priv->rxtx_res = platform_get_resource(phy_pdev, IORESOURCE_MEM,
-					       phy_resnum++);
-	priv->rxtx_regs = devm_ioremap_resource(dev, priv->rxtx_res);
-	if (IS_ERR(priv->rxtx_regs)) {
-		dev_err(dev, "rxtx ioremap failed\n");
-		ret = PTR_ERR(priv->rxtx_regs);
-		goto err_put;
-	}
-
-	priv->sir0_res = platform_get_resource(phy_pdev, IORESOURCE_MEM,
-					       phy_resnum++);
-	priv->sir0_regs = devm_ioremap_resource(dev, priv->sir0_res);
-	if (IS_ERR(priv->sir0_regs)) {
-		dev_err(dev, "sir0 ioremap failed\n");
-		ret = PTR_ERR(priv->sir0_regs);
-		goto err_rxtx;
-	}
-
-	priv->sir1_res = platform_get_resource(phy_pdev, IORESOURCE_MEM,
-					       phy_resnum++);
-	priv->sir1_regs = devm_ioremap_resource(dev, priv->sir1_res);
-	if (IS_ERR(priv->sir1_regs)) {
-		dev_err(dev, "sir1 ioremap failed\n");
-		ret = PTR_ERR(priv->sir1_regs);
-		goto err_sir0;
-	}
-
-	/* Get the auto-negotiation interrupt */
-	ret = platform_get_irq(phy_pdev, phy_irqnum);
-	if (ret < 0) {
-		dev_err(dev, "platform_get_irq failed\n");
-		goto err_sir1;
-	}
-	priv->an_irq = ret;
-
-	/* Get the device speed set property */
-	ret = device_property_read_u32(phy_dev, XGBE_PHY_SPEEDSET_PROPERTY,
-				       &priv->speed_set);
-	if (ret) {
-		dev_err(dev, "invalid %s property\n",
-			XGBE_PHY_SPEEDSET_PROPERTY);
-		goto err_sir1;
-	}
-
-	switch (priv->speed_set) {
-	case AMD_XGBE_PHY_SPEEDSET_1000_10000:
-	case AMD_XGBE_PHY_SPEEDSET_2500_10000:
-		break;
-	default:
-		dev_err(dev, "invalid %s property\n",
-			XGBE_PHY_SPEEDSET_PROPERTY);
-		ret = -EINVAL;
-		goto err_sir1;
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_BLWC_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_BLWC_PROPERTY,
-						     priv->serdes_blwc,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_BLWC_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_blwc, amd_xgbe_phy_serdes_blwc,
-		       sizeof(priv->serdes_blwc));
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_CDR_RATE_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_CDR_RATE_PROPERTY,
-						     priv->serdes_cdr_rate,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_CDR_RATE_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_cdr_rate, amd_xgbe_phy_serdes_cdr_rate,
-		       sizeof(priv->serdes_cdr_rate));
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_PQ_SKEW_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_PQ_SKEW_PROPERTY,
-						     priv->serdes_pq_skew,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_PQ_SKEW_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_pq_skew, amd_xgbe_phy_serdes_pq_skew,
-		       sizeof(priv->serdes_pq_skew));
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_TX_AMP_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_TX_AMP_PROPERTY,
-						     priv->serdes_tx_amp,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_TX_AMP_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_tx_amp, amd_xgbe_phy_serdes_tx_amp,
-		       sizeof(priv->serdes_tx_amp));
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_DFE_CFG_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_DFE_CFG_PROPERTY,
-						     priv->serdes_dfe_tap_cfg,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_DFE_CFG_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_dfe_tap_cfg,
-		       amd_xgbe_phy_serdes_dfe_tap_cfg,
-		       sizeof(priv->serdes_dfe_tap_cfg));
-	}
-
-	if (device_property_present(phy_dev, XGBE_PHY_DFE_ENA_PROPERTY)) {
-		ret = device_property_read_u32_array(phy_dev,
-						     XGBE_PHY_DFE_ENA_PROPERTY,
-						     priv->serdes_dfe_tap_ena,
-						     XGBE_PHY_SPEEDS);
-		if (ret) {
-			dev_err(dev, "invalid %s property\n",
-				XGBE_PHY_DFE_ENA_PROPERTY);
-			goto err_sir1;
-		}
-	} else {
-		memcpy(priv->serdes_dfe_tap_ena,
-		       amd_xgbe_phy_serdes_dfe_tap_ena,
-		       sizeof(priv->serdes_dfe_tap_ena));
-	}
-
-	/* Initialize supported features */
-	phydev->supported = SUPPORTED_Autoneg;
-	phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
-	phydev->supported |= SUPPORTED_Backplane;
-	phydev->supported |= SUPPORTED_10000baseKR_Full;
-	switch (priv->speed_set) {
-	case AMD_XGBE_PHY_SPEEDSET_1000_10000:
-		phydev->supported |= SUPPORTED_1000baseKX_Full;
-		break;
-	case AMD_XGBE_PHY_SPEEDSET_2500_10000:
-		phydev->supported |= SUPPORTED_2500baseX_Full;
-		break;
-	}
-
-	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_ABILITY);
-	if (ret < 0)
-		return ret;
-	priv->fec_ability = ret & XGBE_PHY_FEC_MASK;
-	if (priv->fec_ability & XGBE_PHY_FEC_ENABLE)
-		phydev->supported |= SUPPORTED_10000baseR_FEC;
-
-	phydev->advertising = phydev->supported;
-
-	phydev->priv = priv;
-
-	if (!priv->adev || acpi_disabled)
-		platform_device_put(phy_pdev);
-
-	return 0;
-
-err_sir1:
-	devm_iounmap(dev, priv->sir1_regs);
-	devm_release_mem_region(dev, priv->sir1_res->start,
-				resource_size(priv->sir1_res));
-
-err_sir0:
-	devm_iounmap(dev, priv->sir0_regs);
-	devm_release_mem_region(dev, priv->sir0_res->start,
-				resource_size(priv->sir0_res));
-
-err_rxtx:
-	devm_iounmap(dev, priv->rxtx_regs);
-	devm_release_mem_region(dev, priv->rxtx_res->start,
-				resource_size(priv->rxtx_res));
-
-err_put:
-	if (!priv->adev || acpi_disabled)
-		platform_device_put(phy_pdev);
-
-err_priv:
-	devm_kfree(dev, priv);
-
-	return ret;
-}
-
-static void amd_xgbe_phy_remove(struct phy_device *phydev)
-{
-	struct amd_xgbe_phy_priv *priv = phydev->priv;
-	struct device *dev = priv->dev;
-
-	if (priv->an_irq_allocated) {
-		devm_free_irq(dev, priv->an_irq, priv);
-
-		flush_workqueue(priv->an_workqueue);
-		destroy_workqueue(priv->an_workqueue);
-	}
-
-	/* Release resources */
-	devm_iounmap(dev, priv->sir1_regs);
-	devm_release_mem_region(dev, priv->sir1_res->start,
-				resource_size(priv->sir1_res));
-
-	devm_iounmap(dev, priv->sir0_regs);
-	devm_release_mem_region(dev, priv->sir0_res->start,
-				resource_size(priv->sir0_res));
-
-	devm_iounmap(dev, priv->rxtx_regs);
-	devm_release_mem_region(dev, priv->rxtx_res->start,
-				resource_size(priv->rxtx_res));
-
-	devm_kfree(dev, priv);
-}
-
-static int amd_xgbe_match_phy_device(struct phy_device *phydev)
-{
-	return phydev->c45_ids.device_ids[MDIO_MMD_PCS] == XGBE_PHY_ID;
-}
-
-static struct phy_driver amd_xgbe_phy_driver[] = {
-	{
-		.phy_id			= XGBE_PHY_ID,
-		.phy_id_mask		= XGBE_PHY_MASK,
-		.name			= "AMD XGBE PHY",
-		.features		= 0,
-		.flags			= PHY_IS_INTERNAL,
-		.probe			= amd_xgbe_phy_probe,
-		.remove			= amd_xgbe_phy_remove,
-		.soft_reset		= amd_xgbe_phy_soft_reset,
-		.config_init		= amd_xgbe_phy_config_init,
-		.suspend		= amd_xgbe_phy_suspend,
-		.resume			= amd_xgbe_phy_resume,
-		.config_aneg		= amd_xgbe_phy_config_aneg,
-		.aneg_done		= amd_xgbe_phy_aneg_done,
-		.read_status		= amd_xgbe_phy_read_status,
-		.match_phy_device	= amd_xgbe_match_phy_device,
-		.driver			= {
-			.owner = THIS_MODULE,
-		},
-	},
-};
-
-module_phy_driver(amd_xgbe_phy_driver);
-
-static struct mdio_device_id __maybe_unused amd_xgbe_phy_ids[] = {
-	{ XGBE_PHY_ID, XGBE_PHY_MASK },
-	{ }
-};
-MODULE_DEVICE_TABLE(mdio, amd_xgbe_phy_ids);
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 64c74c6a4828..4dea85bfc545 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -136,8 +136,8 @@ static int bcm7xxx_28nm_d0_afe_config_init(struct phy_device *phydev)
 	/* AFE_RX_LP_COUNTER, set RX bandwidth to maximum */
 	phy_write_misc(phydev, AFE_RX_LP_COUNTER, 0x7fc0);
 
-	/* AFE_TX_CONFIG, set 1000BT Cfeed=110 for all ports */
-	phy_write_misc(phydev, AFE_TX_CONFIG, 0x0061);
+	/* AFE_TX_CONFIG, set 100BT Cfeed=011 to improve rise/fall time */
+	phy_write_misc(phydev, AFE_TX_CONFIG, 0x431);
 
 	/* AFE_VDCA_ICTRL_0, set Iq=1101 instead of 0111 for AB symmetry */
 	phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da);
@@ -167,6 +167,9 @@ static int bcm7xxx_28nm_e0_plus_afe_config_init(struct phy_device *phydev)
 	/* AFE_RXCONFIG_1, provide more margin for INL/DNL measurement */
 	phy_write_misc(phydev, AFE_RXCONFIG_1, 0x9b2f);
 
+	/* AFE_TX_CONFIG, set 100BT Cfeed=011 to improve rise/fall time */
+	phy_write_misc(phydev, AFE_TX_CONFIG, 0x431);
+
 	/* AFE_VDCA_ICTRL_0, set Iq=1101 instead of 0111 for AB symmetry */
 	phy_write_misc(phydev, AFE_VDCA_ICTRL_0, 0xa7da);
 
@@ -404,7 +407,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	.name           = "Broadcom BCM7425",
 	.features       = PHY_GBIT_FEATURES |
 			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
-	.flags          = 0,
+	.flags          = PHY_IS_INTERNAL,
 	.config_init    = bcm7xxx_config_init,
 	.config_aneg    = genphy_config_aneg,
 	.read_status    = genphy_read_status,
diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c
index 0d16c7d9e1bf..2a328703b4ae 100644
--- a/drivers/net/phy/davicom.c
+++ b/drivers/net/phy/davicom.c
@@ -158,6 +158,18 @@ static struct phy_driver dm91xx_driver[] = {
 	.config_intr	= dm9161_config_intr,
 	.driver		= { .owner = THIS_MODULE,},
 }, {
+	.phy_id		= 0x0181b8b0,
+	.name		= "Davicom DM9161B/C",
+	.phy_id_mask	= 0x0ffffff0,
+	.features	= PHY_BASIC_FEATURES,
+	.flags		= PHY_HAS_INTERRUPT,
+	.config_init	= dm9161_config_init,
+	.config_aneg	= dm9161_config_aneg,
+	.read_status	= genphy_read_status,
+	.ack_interrupt	= dm9161_ack_interrupt,
+	.config_intr	= dm9161_config_intr,
+	.driver		= { .owner = THIS_MODULE,},
+}, {
 	.phy_id		= 0x0181b8a0,
 	.name		= "Davicom DM9161A",
 	.phy_id_mask	= 0x0ffffff0,
@@ -186,6 +198,7 @@ module_phy_driver(dm91xx_driver);
 
 static struct mdio_device_id __maybe_unused davicom_tbl[] = {
 	{ 0x0181b880, 0x0ffffff0 },
+	{ 0x0181b8b0, 0x0ffffff0 },
 	{ 0x0181b8a0, 0x0ffffff0 },
 	{ 0x00181b80, 0x0ffffff0 },
 	{ }
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 496e02f961d3..00cb41e71312 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -47,7 +47,7 @@
 #define PSF_TX		0x1000
 #define EXT_EVENT	1
 #define CAL_EVENT	7
-#define CAL_TRIGGER	7
+#define CAL_TRIGGER	1
 #define DP83640_N_PINS	12
 
 #define MII_DP83640_MICR 0x11
@@ -496,7 +496,9 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp,
 			else
 				evnt |= EVNT_RISE;
 		}
+		mutex_lock(&clock->extreg_lock);
 		ext_write(0, phydev, PAGE5, PTP_EVNT, evnt);
+		mutex_unlock(&clock->extreg_lock);
 		return 0;
 
 	case PTP_CLK_REQ_PEROUT:
@@ -532,6 +534,8 @@ static u8 status_frame_src[6] = { 0x08, 0x00, 0x17, 0x0B, 0x6B, 0x0F };
 
 static void enable_status_frames(struct phy_device *phydev, bool on)
 {
+	struct dp83640_private *dp83640 = phydev->priv;
+	struct dp83640_clock *clock = dp83640->clock;
 	u16 cfg0 = 0, ver;
 
 	if (on)
@@ -539,9 +543,13 @@ static void enable_status_frames(struct phy_device *phydev, bool on)
 
 	ver = (PSF_PTPVER & VERSIONPTP_MASK) << VERSIONPTP_SHIFT;
 
+	mutex_lock(&clock->extreg_lock);
+
 	ext_write(0, phydev, PAGE5, PSF_CFG0, cfg0);
 	ext_write(0, phydev, PAGE6, PSF_CFG1, ver);
 
+	mutex_unlock(&clock->extreg_lock);
+
 	if (!phydev->attached_dev) {
 		pr_warn("expected to find an attached netdevice\n");
 		return;
@@ -838,7 +846,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	list_del_init(&rxts->list);
 	phy2rxts(phy_rxts, rxts);
 
-	spin_lock_irqsave(&dp83640->rx_queue.lock, flags);
+	spin_lock(&dp83640->rx_queue.lock);
 	skb_queue_walk(&dp83640->rx_queue, skb) {
 		struct dp83640_skb_info *skb_info;
 
@@ -853,7 +861,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&dp83640->rx_queue.lock, flags);
+	spin_unlock(&dp83640->rx_queue.lock);
 
 	if (!shhwtstamps)
 		list_add_tail(&rxts->list, &dp83640->rxts);
@@ -1173,11 +1181,18 @@ static int dp83640_config_init(struct phy_device *phydev)
 
 	if (clock->chosen && !list_empty(&clock->phylist))
 		recalibrate(clock);
-	else
+	else {
+		mutex_lock(&clock->extreg_lock);
 		enable_broadcast(phydev, clock->page, 1);
+		mutex_unlock(&clock->extreg_lock);
+	}
 
 	enable_status_frames(phydev, true);
+
+	mutex_lock(&clock->extreg_lock);
 	ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE);
+	mutex_unlock(&clock->extreg_lock);
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
new file mode 100644
index 000000000000..c7a12e2e07b7
--- /dev/null
+++ b/drivers/net/phy/dp83867.c
@@ -0,0 +1,239 @@
+/*
+ * Driver for the Texas Instruments DP83867 PHY
+ *
+ * Copyright (C) 2015 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/ethtool.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/phy.h>
+
+#include <dt-bindings/net/ti-dp83867.h>
+
+#define DP83867_PHY_ID		0x2000a231
+#define DP83867_DEVADDR		0x1f
+
+#define MII_DP83867_PHYCTRL	0x10
+#define MII_DP83867_MICR	0x12
+#define MII_DP83867_ISR		0x13
+#define DP83867_CTRL		0x1f
+
+/* Extended Registers */
+#define DP83867_RGMIICTL	0x0032
+#define DP83867_RGMIIDCTL	0x0086
+
+#define DP83867_SW_RESET	BIT(15)
+#define DP83867_SW_RESTART	BIT(14)
+
+/* MICR Interrupt bits */
+#define MII_DP83867_MICR_AN_ERR_INT_EN		BIT(15)
+#define MII_DP83867_MICR_SPEED_CHNG_INT_EN	BIT(14)
+#define MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN	BIT(13)
+#define MII_DP83867_MICR_PAGE_RXD_INT_EN	BIT(12)
+#define MII_DP83867_MICR_AUTONEG_COMP_INT_EN	BIT(11)
+#define MII_DP83867_MICR_LINK_STS_CHNG_INT_EN	BIT(10)
+#define MII_DP83867_MICR_FALSE_CARRIER_INT_EN	BIT(8)
+#define MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN	BIT(4)
+#define MII_DP83867_MICR_WOL_INT_EN		BIT(3)
+#define MII_DP83867_MICR_XGMII_ERR_INT_EN	BIT(2)
+#define MII_DP83867_MICR_POL_CHNG_INT_EN	BIT(1)
+#define MII_DP83867_MICR_JABBER_INT_EN		BIT(0)
+
+/* RGMIICTL bits */
+#define DP83867_RGMII_TX_CLK_DELAY_EN		BIT(1)
+#define DP83867_RGMII_RX_CLK_DELAY_EN		BIT(0)
+
+/* PHY CTRL bits */
+#define DP83867_PHYCR_FIFO_DEPTH_SHIFT		14
+
+/* RGMIIDCTL bits */
+#define DP83867_RGMII_TX_CLK_DELAY_SHIFT	4
+
+struct dp83867_private {
+	int rx_id_delay;
+	int tx_id_delay;
+	int fifo_depth;
+};
+
+static int dp83867_ack_interrupt(struct phy_device *phydev)
+{
+	int err = phy_read(phydev, MII_DP83867_ISR);
+
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int dp83867_config_intr(struct phy_device *phydev)
+{
+	int micr_status;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		micr_status = phy_read(phydev, MII_DP83867_MICR);
+		if (micr_status < 0)
+			return micr_status;
+
+		micr_status |=
+			(MII_DP83867_MICR_AN_ERR_INT_EN |
+			MII_DP83867_MICR_SPEED_CHNG_INT_EN |
+			MII_DP83867_MICR_DUP_MODE_CHNG_INT_EN |
+			MII_DP83867_MICR_SLEEP_MODE_CHNG_INT_EN);
+
+		return phy_write(phydev, MII_DP83867_MICR, micr_status);
+	}
+
+	micr_status = 0x0;
+	return phy_write(phydev, MII_DP83867_MICR, micr_status);
+}
+
+#ifdef CONFIG_OF_MDIO
+static int dp83867_of_init(struct phy_device *phydev)
+{
+	struct dp83867_private *dp83867 = phydev->priv;
+	struct device *dev = &phydev->dev;
+	struct device_node *of_node = dev->of_node;
+	int ret;
+
+	if (!of_node && dev->parent->of_node)
+		of_node = dev->parent->of_node;
+
+	if (!phydev->dev.of_node)
+		return -ENODEV;
+
+	ret = of_property_read_u32(of_node, "ti,rx-internal-delay",
+				   &dp83867->rx_id_delay);
+	if (ret)
+		return ret;
+
+	ret = of_property_read_u32(of_node, "ti,tx-internal-delay",
+				   &dp83867->tx_id_delay);
+	if (ret)
+		return ret;
+
+	ret = of_property_read_u32(of_node, "ti,fifo-depth",
+				   &dp83867->fifo_depth);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+#else
+static int dp83867_of_init(struct phy_device *phydev)
+{
+	return 0;
+}
+#endif /* CONFIG_OF_MDIO */
+
+static int dp83867_config_init(struct phy_device *phydev)
+{
+	struct dp83867_private *dp83867;
+	int ret;
+	u16 val, delay;
+
+	if (!phydev->priv) {
+		dp83867 = devm_kzalloc(&phydev->dev, sizeof(*dp83867),
+				       GFP_KERNEL);
+		if (!dp83867)
+			return -ENOMEM;
+
+		phydev->priv = dp83867;
+		ret = dp83867_of_init(phydev);
+		if (ret)
+			return ret;
+	} else {
+		dp83867 = (struct dp83867_private *)phydev->priv;
+	}
+
+	if (phy_interface_is_rgmii(phydev)) {
+		ret = phy_write(phydev, MII_DP83867_PHYCTRL,
+			(dp83867->fifo_depth << DP83867_PHYCR_FIFO_DEPTH_SHIFT));
+		if (ret)
+			return ret;
+	}
+
+	if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) ||
+	    (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
+		val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
+					    DP83867_DEVADDR, phydev->addr);
+
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
+			val |= (DP83867_RGMII_TX_CLK_DELAY_EN | DP83867_RGMII_RX_CLK_DELAY_EN);
+
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
+			val |= DP83867_RGMII_TX_CLK_DELAY_EN;
+
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
+			val |= DP83867_RGMII_RX_CLK_DELAY_EN;
+
+		phy_write_mmd_indirect(phydev, DP83867_RGMIICTL,
+				       DP83867_DEVADDR, phydev->addr, val);
+
+		delay = (dp83867->rx_id_delay |
+			(dp83867->tx_id_delay << DP83867_RGMII_TX_CLK_DELAY_SHIFT));
+
+		phy_write_mmd_indirect(phydev, DP83867_RGMIIDCTL,
+				       DP83867_DEVADDR, phydev->addr, delay);
+	}
+
+	return 0;
+}
+
+static int dp83867_phy_reset(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESET);
+	if (err < 0)
+		return err;
+
+	return dp83867_config_init(phydev);
+}
+
+static struct phy_driver dp83867_driver[] = {
+	{
+		.phy_id		= DP83867_PHY_ID,
+		.phy_id_mask	= 0xfffffff0,
+		.name		= "TI DP83867",
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+
+		.config_init	= dp83867_config_init,
+		.soft_reset	= dp83867_phy_reset,
+
+		/* IRQ related */
+		.ack_interrupt	= dp83867_ack_interrupt,
+		.config_intr	= dp83867_config_intr,
+
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+
+		.driver		= {.owner = THIS_MODULE,}
+	},
+};
+module_phy_driver(dp83867_driver);
+
+static struct mdio_device_id __maybe_unused dp83867_tbl[] = {
+	{ DP83867_PHY_ID, 0xfffffff0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, dp83867_tbl);
+
+MODULE_DESCRIPTION("Texas Instruments DP83867 PHY driver");
+MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 8644f039d922..0dbc445a5fa0 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -139,10 +139,7 @@ static int ip1001_config_init(struct phy_device *phydev)
 	if (c < 0)
 		return c;
 
-	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
+	if (phy_interface_is_rgmii(phydev)) {
 
 		c = phy_read(phydev, IP10XX_SPEC_CTRL_STATUS);
 		if (c < 0)
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 1b1698f98818..f721444c2b0a 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -317,10 +317,7 @@ static int m88e1121_config_aneg(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
+	if (phy_interface_is_rgmii(phydev)) {
 
 		mscr = phy_read(phydev, MII_88E1121_PHY_MSCR_REG) &
 			MII_88E1121_PHY_MSCR_DELAY_MASK;
@@ -469,10 +466,7 @@ static int m88e1111_config_init(struct phy_device *phydev)
 	int err;
 	int temp;
 
-	if ((phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)) {
+	if (phy_interface_is_rgmii(phydev)) {
 
 		temp = phy_read(phydev, MII_M1111_PHY_EXT_CR);
 		if (temp < 0)
diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c
index 414fdf1f343f..fc7abc50b4f1 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -81,7 +81,13 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 		return -ETIMEDOUT;
 
 	cmd = __raw_readl(priv->base + MDIO_CMD);
-	if (cmd & MDIO_READ_FAIL)
+
+	/* Some broken devices are known not to release the line during
+	 * turn-around, e.g: Broadcom BCM53125 external switches, so check for
+	 * that condition here and ignore the MDIO controller read failure
+	 * indication.
+	 */
+	if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (cmd & MDIO_READ_FAIL))
 		return -EIO;
 
 	return cmd & 0xffff;
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index daec9b05d168..61a543c788cc 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -165,8 +165,11 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
 
 	ctrl->ops->set_mdio_dir(ctrl, 0);
 
-	/* check the turnaround bit: the PHY should be driving it to zero */
-	if (mdiobb_get_bit(ctrl) != 0) {
+	/* check the turnaround bit: the PHY should be driving it to zero, if this
+	 * PHY is listed in phy_ignore_ta_mask as having broken TA, skip that
+	 */
+	if (mdiobb_get_bit(ctrl) != 0 &&
+	    !(bus->phy_ignore_ta_mask & (1 << phy))) {
 		/* PHY didn't drive TA low -- flush any bits it
 		 * may be trying to send.
 		 */
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index c9cb486c753d..7dc21e56a7aa 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -158,6 +158,7 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 	new_bus->name = "GPIO Bitbanged MDIO",
 
 	new_bus->phy_mask = pdata->phy_mask;
+	new_bus->phy_ignore_ta_mask = pdata->phy_ignore_ta_mask;
 	new_bus->irq = pdata->irqs;
 	new_bus->parent = dev;
 
@@ -168,7 +169,10 @@ static struct mii_bus *mdio_gpio_bus_init(struct device *dev,
 		if (!new_bus->irq[i])
 			new_bus->irq[i] = PHY_POLL;
 
-	snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id);
+	if (bus_id != -1)
+		snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id);
+	else
+		strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE);
 
 	if (devm_gpio_request(dev, bitbang->mdc, "mdc"))
 		goto out_free_bus;
diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 66edd99bc302..7ddb1ab70891 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -35,7 +35,8 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 	for (n = 0; n < s->gpios->ndescs; n++)
 		values[n] = (desired_child >> n) & 1;
 
-	gpiod_set_array_cansleep(s->gpios->ndescs, s->gpios->desc, values);
+	gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc,
+				       values);
 
 	return 0;
 }
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 1190fd8f0088..499185eaf413 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -288,9 +288,10 @@ static int kszphy_config_init(struct phy_device *phydev)
 }
 
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
-				       struct device_node *of_node, u16 reg,
-				       char *field1, char *field2,
-				       char *field3, char *field4)
+				       const struct device_node *of_node,
+				       u16 reg,
+				       const char *field1, const char *field2,
+				       const char *field3, const char *field4)
 {
 	int val1 = -1;
 	int val2 = -2;
@@ -336,8 +337,8 @@ static int ksz9021_load_values_from_of(struct phy_device *phydev,
 
 static int ksz9021_config_init(struct phy_device *phydev)
 {
-	struct device *dev = &phydev->dev;
-	struct device_node *of_node = dev->of_node;
+	const struct device *dev = &phydev->dev;
+	const struct device_node *of_node = dev->of_node;
 
 	if (!of_node && dev->parent->of_node)
 		of_node = dev->parent->of_node;
@@ -365,6 +366,11 @@ static int ksz9021_config_init(struct phy_device *phydev)
 #define KSZ9031_PS_TO_REG		60
 
 /* Extended registers */
+/* MMD Address 0x0 */
+#define MII_KSZ9031RN_FLP_BURST_TX_LO	3
+#define MII_KSZ9031RN_FLP_BURST_TX_HI	4
+
+/* MMD Address 0x2 */
 #define MII_KSZ9031RN_CONTROL_PAD_SKEW	4
 #define MII_KSZ9031RN_RX_DATA_PAD_SKEW	5
 #define MII_KSZ9031RN_TX_DATA_PAD_SKEW	6
@@ -389,9 +395,9 @@ static int ksz9031_extended_read(struct phy_device *phydev,
 }
 
 static int ksz9031_of_load_skew_values(struct phy_device *phydev,
-				       struct device_node *of_node,
+				       const struct device_node *of_node,
 				       u16 reg, size_t field_sz,
-				       char *field[], u8 numfields)
+				       const char *field[], u8 numfields)
 {
 	int val[4] = {-1, -2, -3, -4};
 	int matches = 0;
@@ -425,20 +431,36 @@ static int ksz9031_of_load_skew_values(struct phy_device *phydev,
 	return ksz9031_extended_write(phydev, OP_DATA, 2, reg, newval);
 }
 
+static int ksz9031_center_flp_timing(struct phy_device *phydev)
+{
+	int result;
+
+	/* Center KSZ9031RNX FLP timing at 16ms. */
+	result = ksz9031_extended_write(phydev, OP_DATA, 0,
+					MII_KSZ9031RN_FLP_BURST_TX_HI, 0x0006);
+	result = ksz9031_extended_write(phydev, OP_DATA, 0,
+					MII_KSZ9031RN_FLP_BURST_TX_LO, 0x1A80);
+
+	if (result)
+		return result;
+
+	return genphy_restart_aneg(phydev);
+}
+
 static int ksz9031_config_init(struct phy_device *phydev)
 {
-	struct device *dev = &phydev->dev;
-	struct device_node *of_node = dev->of_node;
-	char *clk_skews[2] = {"rxc-skew-ps", "txc-skew-ps"};
-	char *rx_data_skews[4] = {
+	const struct device *dev = &phydev->dev;
+	const struct device_node *of_node = dev->of_node;
+	static const char *clk_skews[2] = {"rxc-skew-ps", "txc-skew-ps"};
+	static const char *rx_data_skews[4] = {
 		"rxd0-skew-ps", "rxd1-skew-ps",
 		"rxd2-skew-ps", "rxd3-skew-ps"
 	};
-	char *tx_data_skews[4] = {
+	static const char *tx_data_skews[4] = {
 		"txd0-skew-ps", "txd1-skew-ps",
 		"txd2-skew-ps", "txd3-skew-ps"
 	};
-	char *control_skews[2] = {"txen-skew-ps", "rxdv-skew-ps"};
+	static const char *control_skews[2] = {"txen-skew-ps", "rxdv-skew-ps"};
 
 	if (!of_node && dev->parent->of_node)
 		of_node = dev->parent->of_node;
@@ -460,7 +482,8 @@ static int ksz9031_config_init(struct phy_device *phydev)
 				MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4,
 				tx_data_skews, 4);
 	}
-	return 0;
+
+	return ksz9031_center_flp_timing(phydev);
 }
 
 #define KSZ8873MLL_GLOBAL_CONTROL_4	0x06
@@ -519,7 +542,7 @@ ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int ptrad, int devnum,
 static int kszphy_probe(struct phy_device *phydev)
 {
 	const struct kszphy_type *type = phydev->drv->driver_data;
-	struct device_node *np = phydev->dev.of_node;
+	const struct device_node *np = phydev->dev.of_node;
 	struct kszphy_priv *priv;
 	struct clk *clk;
 	int ret;
@@ -548,7 +571,8 @@ static int kszphy_probe(struct phy_device *phydev)
 	}
 
 	clk = devm_clk_get(&phydev->dev, "rmii-ref");
-	if (!IS_ERR(clk)) {
+	/* NOTE: clk may be NULL if building without CONFIG_HAVE_CLK */
+	if (!IS_ERR_OR_NULL(clk)) {
 		unsigned long rate = clk_get_rate(clk);
 		bool rmii_ref_clk_sel_25_mhz;
 
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 52cd8db2c57d..b2197b506acb 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -58,6 +58,31 @@ static const char *phy_speed_to_str(int speed)
 	}
 }
 
+#define PHY_STATE_STR(_state)			\
+	case PHY_##_state:			\
+		return __stringify(_state);	\
+
+static const char *phy_state_to_str(enum phy_state st)
+{
+	switch (st) {
+	PHY_STATE_STR(DOWN)
+	PHY_STATE_STR(STARTING)
+	PHY_STATE_STR(READY)
+	PHY_STATE_STR(PENDING)
+	PHY_STATE_STR(UP)
+	PHY_STATE_STR(AN)
+	PHY_STATE_STR(RUNNING)
+	PHY_STATE_STR(NOLINK)
+	PHY_STATE_STR(FORCING)
+	PHY_STATE_STR(CHANGELINK)
+	PHY_STATE_STR(HALTED)
+	PHY_STATE_STR(RESUMING)
+	}
+
+	return NULL;
+}
+
+
 /**
  * phy_print_status - Convenience function to print out the current phy status
  * @phydev: the phy_device struct
@@ -742,6 +767,9 @@ EXPORT_SYMBOL(phy_stop);
  */
 void phy_start(struct phy_device *phydev)
 {
+	bool do_resume = false;
+	int err = 0;
+
 	mutex_lock(&phydev->lock);
 
 	switch (phydev->state) {
@@ -752,11 +780,22 @@ void phy_start(struct phy_device *phydev)
 		phydev->state = PHY_UP;
 		break;
 	case PHY_HALTED:
+		/* make sure interrupts are re-enabled for the PHY */
+		err = phy_enable_interrupts(phydev);
+		if (err < 0)
+			break;
+
 		phydev->state = PHY_RESUMING;
+		do_resume = true;
+		break;
 	default:
 		break;
 	}
 	mutex_unlock(&phydev->lock);
+
+	/* if phy was suspended, bring the physical link up again */
+	if (do_resume)
+		phy_resume(phydev);
 }
 EXPORT_SYMBOL(phy_start);
 
@@ -769,11 +808,14 @@ void phy_state_machine(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct phy_device *phydev =
 			container_of(dwork, struct phy_device, state_queue);
-	bool needs_aneg = false, do_suspend = false, do_resume = false;
+	bool needs_aneg = false, do_suspend = false;
+	enum phy_state old_state;
 	int err = 0;
 
 	mutex_lock(&phydev->lock);
 
+	old_state = phydev->state;
+
 	if (phydev->drv->link_change_notify)
 		phydev->drv->link_change_notify(phydev);
 
@@ -888,14 +930,6 @@ void phy_state_machine(struct work_struct *work)
 		}
 		break;
 	case PHY_RESUMING:
-		err = phy_clear_interrupt(phydev);
-		if (err)
-			break;
-
-		err = phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED);
-		if (err)
-			break;
-
 		if (AUTONEG_ENABLE == phydev->autoneg) {
 			err = phy_aneg_done(phydev);
 			if (err < 0)
@@ -933,7 +967,6 @@ void phy_state_machine(struct work_struct *work)
 			}
 			phydev->adjust_link(phydev->attached_dev);
 		}
-		do_resume = true;
 		break;
 	}
 
@@ -943,12 +976,13 @@ void phy_state_machine(struct work_struct *work)
 		err = phy_start_aneg(phydev);
 	else if (do_suspend)
 		phy_suspend(phydev);
-	else if (do_resume)
-		phy_resume(phydev);
 
 	if (err < 0)
 		phy_error(phydev);
 
+	dev_dbg(&phydev->dev, "PHY state change %s -> %s\n",
+		phy_state_to_str(old_state), phy_state_to_str(phydev->state));
+
 	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
 			   PHY_STATE_TIME * HZ);
 }
@@ -1053,13 +1087,13 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 {
 	/* According to 802.3az,the EEE is supported only in full duplex-mode.
 	 * Also EEE feature is active when core is operating with MII, GMII
-	 * or RGMII. Internal PHYs are also allowed to proceed and should
-	 * return an error if they do not support EEE.
+	 * or RGMII (all kinds). Internal PHYs are also allowed to proceed and
+	 * should return an error if they do not support EEE.
 	 */
 	if ((phydev->duplex == DUPLEX_FULL) &&
 	    ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
 	    (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
-	    (phydev->interface == PHY_INTERFACE_MODE_RGMII) ||
+	     phy_interface_is_rgmii(phydev) ||
 	     phy_is_internal(phydev))) {
 		int eee_lp, eee_cap, eee_adv;
 		u32 lp, cap, adv;
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 96a0f0fab3ca..45353613b2ed 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -22,8 +22,12 @@
 #define RTL821x_INER		0x12
 #define RTL821x_INER_INIT	0x6400
 #define RTL821x_INSR		0x13
+#define RTL8211E_INER_LINK_STATUS 0x400
 
-#define	RTL8211E_INER_LINK_STATUS	0x400
+#define RTL8211F_INER_LINK_STATUS 0x0010
+#define RTL8211F_INSR		0x1d
+#define RTL8211F_PAGE_SELECT	0x1f
+#define RTL8211F_TX_DELAY	0x100
 
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
@@ -38,6 +42,18 @@ static int rtl821x_ack_interrupt(struct phy_device *phydev)
 	return (err < 0) ? err : 0;
 }
 
+static int rtl8211f_ack_interrupt(struct phy_device *phydev)
+{
+	int err;
+
+	phy_write(phydev, RTL8211F_PAGE_SELECT, 0xa43);
+	err = phy_read(phydev, RTL8211F_INSR);
+	/* restore to default page 0 */
+	phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+
+	return (err < 0) ? err : 0;
+}
+
 static int rtl8211b_config_intr(struct phy_device *phydev)
 {
 	int err;
@@ -64,6 +80,41 @@ static int rtl8211e_config_intr(struct phy_device *phydev)
 	return err;
 }
 
+static int rtl8211f_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		err = phy_write(phydev, RTL821x_INER,
+				RTL8211F_INER_LINK_STATUS);
+	else
+		err = phy_write(phydev, RTL821x_INER, 0);
+
+	return err;
+}
+
+static int rtl8211f_config_init(struct phy_device *phydev)
+{
+	int ret;
+	u16 reg;
+
+	ret = genphy_config_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII) {
+		/* enable TXDLY */
+		phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08);
+		reg = phy_read(phydev, 0x11);
+		reg |= RTL8211F_TX_DELAY;
+		phy_write(phydev, 0x11, reg);
+		/* restore to default page 0 */
+		phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0);
+	}
+
+	return 0;
+}
+
 static struct phy_driver realtek_drvs[] = {
 	{
 		.phy_id         = 0x00008201,
@@ -98,6 +149,20 @@ static struct phy_driver realtek_drvs[] = {
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 		.driver		= { .owner = THIS_MODULE,},
+	}, {
+		.phy_id		= 0x001cc916,
+		.name		= "RTL8211F Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_aneg	= &genphy_config_aneg,
+		.config_init	= &rtl8211f_config_init,
+		.read_status	= &genphy_read_status,
+		.ack_interrupt	= &rtl8211f_ack_interrupt,
+		.config_intr	= &rtl8211f_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.driver		= { .owner = THIS_MODULE },
 	},
 };
 
@@ -106,6 +171,7 @@ module_phy_driver(realtek_drvs);
 static struct mdio_device_id __maybe_unused realtek_tbl[] = {
 	{ 0x001cc912, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
+	{ 0x001cc916, 0x001fffff },
 	{ }
 };
 
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index aa1dd926623a..3837ae344f63 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -465,6 +465,10 @@ static void pppoe_unbind_sock_work(struct work_struct *work)
 	struct sock *sk = sk_pppox(po);
 
 	lock_sock(sk);
+	if (po->pppoe_dev) {
+		dev_put(po->pppoe_dev);
+		po->pppoe_dev = NULL;
+	}
 	pppox_unbind_sock(sk);
 	release_sock(sk);
 	sock_put(sk);
@@ -546,11 +550,11 @@ static struct proto pppoe_sk_proto __read_mostly = {
  * Initialize a new struct sock.
  *
  **********************************************************************/
-static int pppoe_create(struct net *net, struct socket *sock)
+static int pppoe_create(struct net *net, struct socket *sock, int kern)
 {
 	struct sock *sk;
 
-	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto);
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, kern);
 	if (!sk)
 		return -ENOMEM;
 
diff --git a/drivers/net/ppp/pppox.c b/drivers/net/ppp/pppox.c
index 2940e9fe351b..0e1b30622477 100644
--- a/drivers/net/ppp/pppox.c
+++ b/drivers/net/ppp/pppox.c
@@ -118,7 +118,7 @@ static int pppox_create(struct net *net, struct socket *sock, int protocol,
 	    !try_module_get(pppox_protos[protocol]->owner))
 		goto out;
 
-	rc = pppox_protos[protocol]->create(net, sock);
+	rc = pppox_protos[protocol]->create(net, sock, kern);
 
 	module_put(pppox_protos[protocol]->owner);
 out:
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index e3bfbd4d0136..686f37daa262 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -28,8 +28,6 @@
 #include <linux/file.h>
 #include <linux/in.h>
 #include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
 #include <linux/rcupdate.h>
 #include <linux/spinlock.h>
 
@@ -561,14 +559,14 @@ static void pptp_sock_destruct(struct sock *sk)
 	skb_queue_purge(&sk->sk_receive_queue);
 }
 
-static int pptp_create(struct net *net, struct socket *sock)
+static int pptp_create(struct net *net, struct socket *sock, int kern)
 {
 	int error = -ENOMEM;
 	struct sock *sk;
 	struct pppox_sock *po;
 	struct pptp_opt *opt;
 
-	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto);
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto, kern);
 	if (!sk)
 		goto out;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6928448f6b7f..daa054b3ff03 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1924,7 +1924,7 @@ static netdev_features_t team_fix_features(struct net_device *dev,
 	struct team *team = netdev_priv(dev);
 	netdev_features_t mask;
 
-	mask = features | NETIF_F_HW_SWITCH_OFFLOAD;
+	mask = features;
 	features &= ~NETIF_F_ONE_FOR_ALL;
 	features |= NETIF_F_ALL_FOR_ALL;
 
@@ -1977,8 +1977,12 @@ static const struct net_device_ops team_netdev_ops = {
 	.ndo_del_slave		= team_del_slave,
 	.ndo_fix_features	= team_fix_features,
 	.ndo_change_carrier     = team_change_carrier,
-	.ndo_bridge_setlink     = ndo_dflt_netdev_switch_port_bridge_setlink,
-	.ndo_bridge_dellink     = ndo_dflt_netdev_switch_port_bridge_dellink,
+	.ndo_bridge_setlink	= switchdev_port_bridge_setlink,
+	.ndo_bridge_getlink	= switchdev_port_bridge_getlink,
+	.ndo_bridge_dellink	= switchdev_port_bridge_dellink,
+	.ndo_fdb_add		= switchdev_port_fdb_add,
+	.ndo_fdb_del		= switchdev_port_fdb_del,
+	.ndo_fdb_dump		= switchdev_port_fdb_dump,
 	.ndo_features_check	= passthru_features_check,
 };
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e470ae59d405..1a1c4f7b3ec5 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -146,7 +146,6 @@ struct tun_file {
 	struct socket socket;
 	struct socket_wq wq;
 	struct tun_struct __rcu *tun;
-	struct net *net;
 	struct fasync_struct *fasync;
 	/* only used for fasnyc */
 	unsigned int flags;
@@ -493,10 +492,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 			    tun->dev->reg_state == NETREG_REGISTERED)
 				unregister_netdevice(tun->dev);
 		}
-
-		BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
-				 &tfile->socket.flags));
-		sk_release_kernel(&tfile->sk);
+		sock_put(&tfile->sk);
 	}
 }
 
@@ -1492,18 +1488,10 @@ out:
 	return ret;
 }
 
-static int tun_release(struct socket *sock)
-{
-	if (sock->sk)
-		sock_put(sock->sk);
-	return 0;
-}
-
 /* Ops structure to mimic raw sockets with tun */
 static const struct proto_ops tun_socket_ops = {
 	.sendmsg = tun_sendmsg,
 	.recvmsg = tun_recvmsg,
-	.release = tun_release,
 };
 
 static struct proto tun_proto = {
@@ -1865,7 +1853,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	if (cmd == TUNSETIFF && !tun) {
 		ifr.ifr_name[IFNAMSIZ-1] = '\0';
 
-		ret = tun_set_iff(tfile->net, file, &ifr);
+		ret = tun_set_iff(sock_net(&tfile->sk), file, &ifr);
 
 		if (ret)
 			goto unlock;
@@ -2154,16 +2142,16 @@ out:
 
 static int tun_chr_open(struct inode *inode, struct file * file)
 {
+	struct net *net = current->nsproxy->net_ns;
 	struct tun_file *tfile;
 
 	DBG1(KERN_INFO, "tunX: tun_chr_open\n");
 
-	tfile = (struct tun_file *)sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL,
-					    &tun_proto);
+	tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+					    &tun_proto, 0);
 	if (!tfile)
 		return -ENOMEM;
 	RCU_INIT_POINTER(tfile->tun, NULL);
-	tfile->net = get_net(current->nsproxy->net_ns);
 	tfile->flags = 0;
 	tfile->ifindex = 0;
 
@@ -2174,13 +2162,11 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 	tfile->socket.ops = &tun_socket_ops;
 
 	sock_init_data(&tfile->socket, &tfile->sk);
-	sk_change_net(&tfile->sk, tfile->net);
 
 	tfile->sk.sk_write_space = tun_sock_write_space;
 	tfile->sk.sk_sndbuf = INT_MAX;
 
 	file->private_data = tfile;
-	set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags);
 	INIT_LIST_HEAD(&tfile->next);
 
 	sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);
@@ -2191,10 +2177,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 static int tun_chr_close(struct inode *inode, struct file *file)
 {
 	struct tun_file *tfile = file->private_data;
-	struct net *net = tfile->net;
 
 	tun_detach(tfile, true);
-	put_net(net);
 
 	return 0;
 }
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index c3e4da9e79ca..8067b8fbb0ee 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -1182,7 +1182,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * payload data instead.
 	 */
 	usbnet_set_skb_tx_stats(skb_out, n,
-				ctx->tx_curr_frame_payload - skb_out->len);
+				(long)ctx->tx_curr_frame_payload - skb_out->len);
 
 	return skb_out;
 
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index ac4d03b328b1..aafa1a1898e4 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -4116,6 +4116,7 @@ static struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
 	{}
 };
 
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 733f4feb2ef3..3c86b107275a 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1285,7 +1285,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb,
 				     struct net_device *net)
 {
 	struct usbnet		*dev = netdev_priv(net);
-	int			length;
+	unsigned int			length;
 	struct urb		*urb = NULL;
 	struct skb_data		*entry;
 	struct driver_info	*info = dev->driver_info;
@@ -1413,7 +1413,7 @@ not_drop:
 		}
 	} else
 		netif_dbg(dev, tx_queued, dev->net,
-			  "> tx, len %d, type 0x%x\n", length, skb->protocol);
+			  "> tx, len %u, type 0x%x\n", length, skb->protocol);
 #ifdef CONFIG_PM
 deferred:
 #endif
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h
index 3718d024f638..221a53025fd0 100644
--- a/drivers/net/vmxnet3/vmxnet3_defs.h
+++ b/drivers/net/vmxnet3/vmxnet3_defs.h
@@ -1,7 +1,7 @@
 /*
  * Linux driver for VMware's vmxnet3 ethernet NIC.
  *
- * Copyright (C) 2008-2009, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2015, VMware, Inc. All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -277,6 +277,40 @@ struct Vmxnet3_RxCompDesc {
 #endif  /* __BIG_ENDIAN_BITFIELD */
 };
 
+struct Vmxnet3_RxCompDescExt {
+	__le32		dword1;
+	u8		segCnt;       /* Number of aggregated packets */
+	u8		dupAckCnt;    /* Number of duplicate Acks */
+	__le16		tsDelta;      /* TCP timestamp difference */
+	__le32		dword2;
+#ifdef __BIG_ENDIAN_BITFIELD
+	u32		gen:1;        /* generation bit */
+	u32		type:7;       /* completion type */
+	u32		fcs:1;        /* Frame CRC correct */
+	u32		frg:1;        /* IP Fragment */
+	u32		v4:1;         /* IPv4 */
+	u32		v6:1;         /* IPv6 */
+	u32		ipc:1;        /* IP Checksum Correct */
+	u32		tcp:1;        /* TCP packet */
+	u32		udp:1;        /* UDP packet */
+	u32		tuc:1;        /* TCP/UDP Checksum Correct */
+	u32		mss:16;
+#else
+	u32		mss:16;
+	u32		tuc:1;        /* TCP/UDP Checksum Correct */
+	u32		udp:1;        /* UDP packet */
+	u32		tcp:1;        /* TCP packet */
+	u32		ipc:1;        /* IP Checksum Correct */
+	u32		v6:1;         /* IPv6 */
+	u32		v4:1;         /* IPv4 */
+	u32		frg:1;        /* IP Fragment */
+	u32		fcs:1;        /* Frame CRC correct */
+	u32		type:7;       /* completion type */
+	u32		gen:1;        /* generation bit */
+#endif  /* __BIG_ENDIAN_BITFIELD */
+};
+
+
 /* fields in RxCompDesc we access via Vmxnet3_GenericDesc.dword[3] */
 #define VMXNET3_RCD_TUC_SHIFT	16
 #define VMXNET3_RCD_IPC_SHIFT	19
@@ -310,6 +344,7 @@ union Vmxnet3_GenericDesc {
 	struct Vmxnet3_RxDesc		rxd;
 	struct Vmxnet3_TxCompDesc	tcd;
 	struct Vmxnet3_RxCompDesc	rcd;
+	struct Vmxnet3_RxCompDescExt 	rcdExt;
 };
 
 #define VMXNET3_INIT_GEN       1
@@ -361,6 +396,7 @@ enum {
 /* completion descriptor types */
 #define VMXNET3_CDTYPE_TXCOMP      0    /* Tx Completion Descriptor */
 #define VMXNET3_CDTYPE_RXCOMP      3    /* Rx Completion Descriptor */
+#define VMXNET3_CDTYPE_RXCOMP_LRO  4    /* Rx Completion Descriptor for LRO */
 
 enum {
 	VMXNET3_GOS_BITS_UNK    = 0,   /* unknown */
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 61c0840c448c..da11bb5e9c7f 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -861,6 +861,9 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 					     , skb_headlen(skb));
 		}
 
+		if (skb->len <= VMXNET3_HDR_COPY_SIZE)
+			ctx->copy_size = skb->len;
+
 		/* make sure headers are accessible directly */
 		if (unlikely(!pskb_may_pull(skb, ctx->copy_size)))
 			goto err;
@@ -1160,6 +1163,52 @@ vmxnet3_rx_error(struct vmxnet3_rx_queue *rq, struct Vmxnet3_RxCompDesc *rcd,
 }
 
 
+static u32
+vmxnet3_get_hdr_len(struct vmxnet3_adapter *adapter, struct sk_buff *skb,
+		    union Vmxnet3_GenericDesc *gdesc)
+{
+	u32 hlen, maplen;
+	union {
+		void *ptr;
+		struct ethhdr *eth;
+		struct iphdr *ipv4;
+		struct ipv6hdr *ipv6;
+		struct tcphdr *tcp;
+	} hdr;
+	BUG_ON(gdesc->rcd.tcp == 0);
+
+	maplen = skb_headlen(skb);
+	if (unlikely(sizeof(struct iphdr) + sizeof(struct tcphdr) > maplen))
+		return 0;
+
+	hdr.eth = eth_hdr(skb);
+	if (gdesc->rcd.v4) {
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IP));
+		hdr.ptr += sizeof(struct ethhdr);
+		BUG_ON(hdr.ipv4->protocol != IPPROTO_TCP);
+		hlen = hdr.ipv4->ihl << 2;
+		hdr.ptr += hdr.ipv4->ihl << 2;
+	} else if (gdesc->rcd.v6) {
+		BUG_ON(hdr.eth->h_proto != htons(ETH_P_IPV6));
+		hdr.ptr += sizeof(struct ethhdr);
+		/* Use an estimated value, since we also need to handle
+		 * TSO case.
+		 */
+		if (hdr.ipv6->nexthdr != IPPROTO_TCP)
+			return sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
+		hlen = sizeof(struct ipv6hdr);
+		hdr.ptr += sizeof(struct ipv6hdr);
+	} else {
+		/* Non-IP pkt, dont estimate header length */
+		return 0;
+	}
+
+	if (hlen + sizeof(struct tcphdr) > maplen)
+		return 0;
+
+	return (hlen + (hdr.tcp->doff << 2));
+}
+
 static int
 vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 		       struct vmxnet3_adapter *adapter, int quota)
@@ -1171,6 +1220,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 	bool skip_page_frags = false;
 	struct Vmxnet3_RxCompDesc *rcd;
 	struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx;
+	u16 segCnt = 0, mss = 0;
 #ifdef __BIG_ENDIAN_BITFIELD
 	struct Vmxnet3_RxDesc rxCmdDesc;
 	struct Vmxnet3_RxCompDesc rxComp;
@@ -1259,7 +1309,19 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 						       PCI_DMA_FROMDEVICE);
 			rxd->addr = cpu_to_le64(rbi->dma_addr);
 			rxd->len = rbi->len;
-
+			if (adapter->version == 2 &&
+			    rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) {
+				struct Vmxnet3_RxCompDescExt *rcdlro;
+				rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd;
+
+				segCnt = rcdlro->segCnt;
+				BUG_ON(segCnt <= 1);
+				mss = rcdlro->mss;
+				if (unlikely(segCnt <= 1))
+					segCnt = 0;
+			} else {
+				segCnt = 0;
+			}
 		} else {
 			BUG_ON(ctx->skb == NULL && !skip_page_frags);
 
@@ -1273,47 +1335,75 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 			if (skip_page_frags)
 				goto rcd_done;
 
-			new_page = alloc_page(GFP_ATOMIC);
-			if (unlikely(new_page == NULL)) {
+			if (rcd->len) {
+				new_page = alloc_page(GFP_ATOMIC);
 				/* Replacement page frag could not be allocated.
 				 * Reuse this page. Drop the pkt and free the
 				 * skb which contained this page as a frag. Skip
 				 * processing all the following non-sop frags.
 				 */
-				rq->stats.rx_buf_alloc_failure++;
-				dev_kfree_skb(ctx->skb);
-				ctx->skb = NULL;
-				skip_page_frags = true;
-				goto rcd_done;
-			}
+				if (unlikely(!new_page)) {
+					rq->stats.rx_buf_alloc_failure++;
+					dev_kfree_skb(ctx->skb);
+					ctx->skb = NULL;
+					skip_page_frags = true;
+					goto rcd_done;
+				}
 
-			if (rcd->len) {
 				dma_unmap_page(&adapter->pdev->dev,
 					       rbi->dma_addr, rbi->len,
 					       PCI_DMA_FROMDEVICE);
 
 				vmxnet3_append_frag(ctx->skb, rcd, rbi);
-			}
 
-			/* Immediate refill */
-			rbi->page = new_page;
-			rbi->dma_addr = dma_map_page(&adapter->pdev->dev,
-						     rbi->page,
-						     0, PAGE_SIZE,
-						     PCI_DMA_FROMDEVICE);
-			rxd->addr = cpu_to_le64(rbi->dma_addr);
-			rxd->len = rbi->len;
+				/* Immediate refill */
+				rbi->page = new_page;
+				rbi->dma_addr = dma_map_page(&adapter->pdev->dev
+							, rbi->page,
+							0, PAGE_SIZE,
+							PCI_DMA_FROMDEVICE);
+				rxd->addr = cpu_to_le64(rbi->dma_addr);
+				rxd->len = rbi->len;
+			}
 		}
 
 
 		skb = ctx->skb;
 		if (rcd->eop) {
+			u32 mtu = adapter->netdev->mtu;
 			skb->len += skb->data_len;
 
 			vmxnet3_rx_csum(adapter, skb,
 					(union Vmxnet3_GenericDesc *)rcd);
 			skb->protocol = eth_type_trans(skb, adapter->netdev);
-
+			if (!rcd->tcp || !adapter->lro)
+				goto not_lro;
+
+			if (segCnt != 0 && mss != 0) {
+				skb_shinfo(skb)->gso_type = rcd->v4 ?
+					SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				skb_shinfo(skb)->gso_size = mss;
+				skb_shinfo(skb)->gso_segs = segCnt;
+			} else if (segCnt != 0 || skb->len > mtu) {
+				u32 hlen;
+
+				hlen = vmxnet3_get_hdr_len(adapter, skb,
+					(union Vmxnet3_GenericDesc *)rcd);
+				if (hlen == 0)
+					goto not_lro;
+
+				skb_shinfo(skb)->gso_type =
+					rcd->v4 ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+				if (segCnt != 0) {
+					skb_shinfo(skb)->gso_segs = segCnt;
+					skb_shinfo(skb)->gso_size =
+						DIV_ROUND_UP(skb->len -
+							hlen, segCnt);
+				} else {
+					skb_shinfo(skb)->gso_size = mtu - hlen;
+				}
+			}
+not_lro:
 			if (unlikely(rcd->ts))
 				__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rcd->tci);
 
@@ -3038,14 +3128,19 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 		goto err_alloc_pci;
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS);
-	if (ver & 1) {
+	if (ver & 2) {
+		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 2);
+		adapter->version = 2;
+	} else if (ver & 1) {
 		VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1);
+		adapter->version = 1;
 	} else {
 		dev_err(&pdev->dev,
 			"Incompatible h/w version (0x%x) for adapter\n", ver);
 		err = -EBUSY;
 		goto err_ver;
 	}
+	dev_dbg(&pdev->dev, "Using device version %d\n", adapter->version);
 
 	ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS);
 	if (ver & 1) {
@@ -3184,6 +3279,32 @@ vmxnet3_remove_device(struct pci_dev *pdev)
 	free_netdev(netdev);
 }
 
+static void vmxnet3_shutdown_device(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	unsigned long flags;
+
+	/* Reset_work may be in the middle of resetting the device, wait for its
+	 * completion.
+	 */
+	while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state))
+		msleep(1);
+
+	if (test_and_set_bit(VMXNET3_STATE_BIT_QUIESCED,
+			     &adapter->state)) {
+		clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+		return;
+	}
+	spin_lock_irqsave(&adapter->cmd_lock, flags);
+	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
+			       VMXNET3_CMD_QUIESCE_DEV);
+	spin_unlock_irqrestore(&adapter->cmd_lock, flags);
+	vmxnet3_disable_all_intrs(adapter);
+
+	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
+}
+
 
 #ifdef CONFIG_PM
 
@@ -3360,6 +3481,7 @@ static struct pci_driver vmxnet3_driver = {
 	.id_table	= vmxnet3_pciid_table,
 	.probe		= vmxnet3_probe_device,
 	.remove		= vmxnet3_remove_device,
+	.shutdown	= vmxnet3_shutdown_device,
 #ifdef CONFIG_PM
 	.driver.pm	= &vmxnet3_pm_ops,
 #endif
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 6bb769ae7de9..e9f1075f7d4c 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -328,6 +328,10 @@ struct vmxnet3_adapter {
 
 	u8			__iomem *hw_addr0; /* for BAR 0 */
 	u8			__iomem *hw_addr1; /* for BAR 1 */
+	u8                              version;
+
+	bool				rxcsum;
+	bool				lro;
 
 #ifdef VMXNET3_RSS
 	struct UPT1_RSSConf		*rss_conf;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 27a5f954f8e9..34c519eb1db5 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -336,7 +336,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 
 	if (!net_eq(dev_net(vxlan->dev), vxlan->net) &&
 	    nla_put_s32(skb, NDA_LINK_NETNSID,
-			peernet2id(dev_net(vxlan->dev), vxlan->net)))
+			peernet2id_alloc(dev_net(vxlan->dev), vxlan->net)))
 		goto nla_put_failure;
 
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
@@ -1921,6 +1921,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		memset(&fl4, 0, sizeof(fl4));
 		fl4.flowi4_oif = rdst->remote_ifindex;
 		fl4.flowi4_tos = RT_TOS(tos);
+		fl4.flowi4_mark = skb->mark;
+		fl4.flowi4_proto = IPPROTO_UDP;
 		fl4.daddr = dst->sin.sin_addr.s_addr;
 		fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
 
@@ -1981,6 +1983,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		fl6.flowi6_oif = rdst->remote_ifindex;
 		fl6.daddr = dst->sin6.sin6_addr;
 		fl6.saddr = vxlan->saddr.sin6.sin6_addr;
+		fl6.flowi6_mark = skb->mark;
 		fl6.flowi6_proto = IPPROTO_UDP;
 
 		if (ipv6_stub->ipv6_dst_lookup(sk, &ndst, &fl6)) {
@@ -2128,9 +2131,10 @@ static void vxlan_cleanup(unsigned long arg)
 	if (!netif_running(vxlan->dev))
 		return;
 
-	spin_lock_bh(&vxlan->hash_lock);
 	for (h = 0; h < FDB_HASH_SIZE; ++h) {
 		struct hlist_node *p, *n;
+
+		spin_lock_bh(&vxlan->hash_lock);
 		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
 			struct vxlan_fdb *f
 				= container_of(p, struct vxlan_fdb, hlist);
@@ -2149,8 +2153,8 @@ static void vxlan_cleanup(unsigned long arg)
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
+		spin_unlock_bh(&vxlan->hash_lock);
 	}
-	spin_unlock_bh(&vxlan->hash_lock);
 
 	mod_timer(&vxlan->age_timer, next_timer);
 }
@@ -2961,7 +2965,7 @@ static void __net_exit vxlan_exit_net(struct net *net)
 		 * to the list by the previous loop.
 		 */
 		if (!net_eq(dev_net(vxlan->dev), net))
-			unregister_netdevice_queue(dev, &list);
+			unregister_netdevice_queue(vxlan->dev, &list);
 	}
 
 	unregister_netdevice_many(&list);
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index bcfa01add7cc..7193b7304fdd 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -517,7 +517,7 @@ static int cosa_probe(int base, int irq, int dma)
 		 */
 		set_current_state(TASK_INTERRUPTIBLE);
 		cosa_putstatus(cosa, SR_TX_INT_ENA);
-		schedule_timeout(30);
+		schedule_timeout(msecs_to_jiffies(300));
 		irq = probe_irq_off(irqs);
 		/* Disable all IRQs from the card */
 		cosa_putstatus(cosa, 0);
diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c
index 08223569cebd..7a72407208b1 100644
--- a/drivers/net/wan/dscc4.c
+++ b/drivers/net/wan/dscc4.c
@@ -551,7 +551,7 @@ static int dscc4_wait_ack_cec(struct dscc4_dev_priv *dpriv,
 			       msg, i);
 			goto done;
 		}
-		schedule_timeout_uninterruptible(10);
+		schedule_timeout_uninterruptible(msecs_to_jiffies(100));
 		rmb();
 	} while (++i > 0);
 	netdev_err(dev, "%s timeout\n", msg);
@@ -596,7 +596,7 @@ static inline int dscc4_xpr_ack(struct dscc4_dev_priv *dpriv)
 		    (dpriv->iqtx[cur] & cpu_to_le32(Xpr)))
 			break;
 		smp_rmb();
-		schedule_timeout_uninterruptible(10);
+		schedule_timeout_uninterruptible(msecs_to_jiffies(100));
 	} while (++i > 0);
 
 	return (i >= 0 ) ? i : -EAGAIN;
@@ -1033,7 +1033,7 @@ static void dscc4_pci_reset(struct pci_dev *pdev, void __iomem *ioaddr)
 	/* Flush posted writes */
 	readl(ioaddr + GSTAR);
 
-	schedule_timeout_uninterruptible(10);
+	schedule_timeout_uninterruptible(msecs_to_jiffies(100));
 
 	for (i = 0; i < 16; i++)
 		pci_write_config_dword(pdev, i << 2, dscc4_pci_config_store[i]);
@@ -1046,7 +1046,6 @@ static void dscc4_pci_reset(struct pci_dev *pdev, void __iomem *ioaddr)
 static int dscc4_open(struct net_device *dev)
 {
 	struct dscc4_dev_priv *dpriv = dscc4_priv(dev);
-	struct dscc4_pci_priv *ppriv;
 	int ret = -EAGAIN;
 
 	if ((dscc4_loopback_check(dpriv) < 0))
@@ -1055,8 +1054,6 @@ static int dscc4_open(struct net_device *dev)
 	if ((ret = hdlc_open(dev)))
 		goto err;
 
-	ppriv = dpriv->pci_priv;
-
 	/*
 	 * Due to various bugs, there is no way to reliably reset a
 	 * specific port (manufacturer's dependent special PCI #RST wiring
diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c
index 2f5eda8a7227..6676607164d6 100644
--- a/drivers/net/wan/lapbether.c
+++ b/drivers/net/wan/lapbether.c
@@ -40,7 +40,6 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/stat.h>
-#include <linux/netfilter.h>
 #include <linux/module.h>
 #include <linux/lapb.h>
 #include <linux/init.h>
diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 16604bdf5197..a63ab2e83105 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -277,6 +277,7 @@ source "drivers/net/wireless/libertas/Kconfig"
 source "drivers/net/wireless/orinoco/Kconfig"
 source "drivers/net/wireless/p54/Kconfig"
 source "drivers/net/wireless/rt2x00/Kconfig"
+source "drivers/net/wireless/mediatek/Kconfig"
 source "drivers/net/wireless/rtlwifi/Kconfig"
 source "drivers/net/wireless/ti/Kconfig"
 source "drivers/net/wireless/zd1211rw/Kconfig"
diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile
index 0c8891686718..6b9e729dd8ac 100644
--- a/